{ "best_metric": null, "best_model_checkpoint": null, "epoch": 79.95132541133455, "global_step": 333040, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 9.999999979867155e-05, "loss": 1.4635, "step": 10 }, { "epoch": 0.0, "learning_rate": 9.99999991946862e-05, "loss": 1.429, "step": 20 }, { "epoch": 0.01, "learning_rate": 9.999999818804396e-05, "loss": 1.3619, "step": 30 }, { "epoch": 0.01, "learning_rate": 9.99999967787448e-05, "loss": 1.2271, "step": 40 }, { "epoch": 0.01, "learning_rate": 9.99999949667888e-05, "loss": 1.1693, "step": 50 }, { "epoch": 0.01, "learning_rate": 9.999999275217593e-05, "loss": 1.1097, "step": 60 }, { "epoch": 0.02, "learning_rate": 9.99999901349062e-05, "loss": 1.1182, "step": 70 }, { "epoch": 0.02, "learning_rate": 9.999998711497966e-05, "loss": 1.1083, "step": 80 }, { "epoch": 0.02, "learning_rate": 9.999998369239631e-05, "loss": 1.0931, "step": 90 }, { "epoch": 0.02, "learning_rate": 9.99999798671562e-05, "loss": 1.0561, "step": 100 }, { "epoch": 0.03, "learning_rate": 9.999997563925934e-05, "loss": 1.1237, "step": 110 }, { "epoch": 0.03, "learning_rate": 9.999997100870578e-05, "loss": 1.1205, "step": 120 }, { "epoch": 0.03, "learning_rate": 9.999996597549555e-05, "loss": 1.0449, "step": 130 }, { "epoch": 0.03, "learning_rate": 9.999996053962867e-05, "loss": 1.0498, "step": 140 }, { "epoch": 0.03, "learning_rate": 9.999995470110524e-05, "loss": 1.059, "step": 150 }, { "epoch": 0.04, "learning_rate": 9.999994845992525e-05, "loss": 1.126, "step": 160 }, { "epoch": 0.04, "learning_rate": 9.999994181608878e-05, "loss": 1.0593, "step": 170 }, { "epoch": 0.04, "learning_rate": 9.999993476959586e-05, "loss": 1.078, "step": 180 }, { "epoch": 0.04, "learning_rate": 9.999992732044659e-05, "loss": 1.0791, "step": 190 }, { "epoch": 0.05, "learning_rate": 9.999991946864098e-05, "loss": 1.0659, "step": 200 }, { "epoch": 0.05, "learning_rate": 9.999991121417913e-05, "loss": 1.0617, "step": 210 }, { "epoch": 0.05, "learning_rate": 9.999990255706109e-05, "loss": 1.1062, "step": 220 }, { "epoch": 0.05, "learning_rate": 9.999989349728692e-05, "loss": 1.0447, "step": 230 }, { "epoch": 0.05, "learning_rate": 9.999988403485671e-05, "loss": 1.0779, "step": 240 }, { "epoch": 0.06, "learning_rate": 9.999987416977052e-05, "loss": 1.0616, "step": 250 }, { "epoch": 0.06, "learning_rate": 9.999986390202846e-05, "loss": 1.1526, "step": 260 }, { "epoch": 0.06, "learning_rate": 9.999985323163059e-05, "loss": 1.0515, "step": 270 }, { "epoch": 0.06, "learning_rate": 9.9999842158577e-05, "loss": 1.0532, "step": 280 }, { "epoch": 0.07, "learning_rate": 9.999983068286778e-05, "loss": 1.0308, "step": 290 }, { "epoch": 0.07, "learning_rate": 9.9999818804503e-05, "loss": 1.0542, "step": 300 }, { "epoch": 0.07, "learning_rate": 9.99998065234828e-05, "loss": 1.0145, "step": 310 }, { "epoch": 0.07, "learning_rate": 9.999979383980725e-05, "loss": 0.9995, "step": 320 }, { "epoch": 0.08, "learning_rate": 9.999978075347644e-05, "loss": 1.0501, "step": 330 }, { "epoch": 0.08, "learning_rate": 9.999976726449051e-05, "loss": 1.0005, "step": 340 }, { "epoch": 0.08, "learning_rate": 9.999975337284955e-05, "loss": 1.0359, "step": 350 }, { "epoch": 0.08, "learning_rate": 9.999973907855366e-05, "loss": 1.0249, "step": 360 }, { "epoch": 0.08, "learning_rate": 9.999972438160299e-05, "loss": 0.9936, "step": 370 }, { "epoch": 0.09, "learning_rate": 9.999970928199763e-05, "loss": 1.0094, "step": 380 }, { "epoch": 0.09, "learning_rate": 9.99996937797377e-05, "loss": 1.0176, "step": 390 }, { "epoch": 0.09, "learning_rate": 9.999967787482333e-05, "loss": 0.9975, "step": 400 }, { "epoch": 0.09, "learning_rate": 9.999966156725465e-05, "loss": 1.0125, "step": 410 }, { "epoch": 0.1, "learning_rate": 9.99996448570318e-05, "loss": 0.9809, "step": 420 }, { "epoch": 0.1, "learning_rate": 9.99996277441549e-05, "loss": 0.9991, "step": 430 }, { "epoch": 0.1, "learning_rate": 9.999961022862412e-05, "loss": 0.9724, "step": 440 }, { "epoch": 0.1, "learning_rate": 9.999959231043956e-05, "loss": 0.9526, "step": 450 }, { "epoch": 0.11, "learning_rate": 9.999957398960138e-05, "loss": 0.9919, "step": 460 }, { "epoch": 0.11, "learning_rate": 9.99995552661097e-05, "loss": 0.9604, "step": 470 }, { "epoch": 0.11, "learning_rate": 9.999953613996474e-05, "loss": 0.9581, "step": 480 }, { "epoch": 0.11, "learning_rate": 9.99995166111666e-05, "loss": 0.9585, "step": 490 }, { "epoch": 0.11, "learning_rate": 9.999949667971544e-05, "loss": 0.9671, "step": 500 }, { "epoch": 0.12, "learning_rate": 9.999947634561144e-05, "loss": 0.9607, "step": 510 }, { "epoch": 0.12, "learning_rate": 9.999945560885475e-05, "loss": 0.9567, "step": 520 }, { "epoch": 0.12, "learning_rate": 9.999943446944556e-05, "loss": 0.9437, "step": 530 }, { "epoch": 0.12, "learning_rate": 9.999941292738399e-05, "loss": 0.9638, "step": 540 }, { "epoch": 0.13, "learning_rate": 9.999939098267026e-05, "loss": 0.9298, "step": 550 }, { "epoch": 0.13, "learning_rate": 9.999936863530452e-05, "loss": 0.9222, "step": 560 }, { "epoch": 0.13, "learning_rate": 9.9999345885287e-05, "loss": 0.9248, "step": 570 }, { "epoch": 0.13, "learning_rate": 9.99993227326178e-05, "loss": 0.9255, "step": 580 }, { "epoch": 0.13, "learning_rate": 9.999929917729717e-05, "loss": 0.932, "step": 590 }, { "epoch": 0.14, "learning_rate": 9.999927521932528e-05, "loss": 0.9272, "step": 600 }, { "epoch": 0.14, "learning_rate": 9.999925085870232e-05, "loss": 0.9011, "step": 610 }, { "epoch": 0.14, "learning_rate": 9.999922609542849e-05, "loss": 0.919, "step": 620 }, { "epoch": 0.14, "learning_rate": 9.9999200929504e-05, "loss": 0.8553, "step": 630 }, { "epoch": 0.15, "learning_rate": 9.999917536092901e-05, "loss": 0.8936, "step": 640 }, { "epoch": 0.15, "learning_rate": 9.99991493897038e-05, "loss": 0.9369, "step": 650 }, { "epoch": 0.15, "learning_rate": 9.999912301582852e-05, "loss": 0.8954, "step": 660 }, { "epoch": 0.15, "learning_rate": 9.99990962393034e-05, "loss": 0.8763, "step": 670 }, { "epoch": 0.16, "learning_rate": 9.999906906012866e-05, "loss": 0.8899, "step": 680 }, { "epoch": 0.16, "learning_rate": 9.99990414783045e-05, "loss": 0.9103, "step": 690 }, { "epoch": 0.16, "learning_rate": 9.999901349383116e-05, "loss": 0.9228, "step": 700 }, { "epoch": 0.16, "learning_rate": 9.999898510670887e-05, "loss": 0.8987, "step": 710 }, { "epoch": 0.16, "learning_rate": 9.999895631693786e-05, "loss": 0.8737, "step": 720 }, { "epoch": 0.17, "learning_rate": 9.999892712451833e-05, "loss": 0.8383, "step": 730 }, { "epoch": 0.17, "learning_rate": 9.999889752945054e-05, "loss": 0.8689, "step": 740 }, { "epoch": 0.17, "learning_rate": 9.999886753173474e-05, "loss": 0.8627, "step": 750 }, { "epoch": 0.17, "learning_rate": 9.999883713137114e-05, "loss": 0.853, "step": 760 }, { "epoch": 0.18, "learning_rate": 9.999880632836001e-05, "loss": 0.8543, "step": 770 }, { "epoch": 0.18, "learning_rate": 9.999877512270159e-05, "loss": 0.8343, "step": 780 }, { "epoch": 0.18, "learning_rate": 9.999874351439613e-05, "loss": 0.8811, "step": 790 }, { "epoch": 0.18, "learning_rate": 9.999871150344389e-05, "loss": 0.8363, "step": 800 }, { "epoch": 0.19, "learning_rate": 9.999867908984512e-05, "loss": 0.8282, "step": 810 }, { "epoch": 0.19, "learning_rate": 9.999864627360007e-05, "loss": 0.8575, "step": 820 }, { "epoch": 0.19, "learning_rate": 9.999861305470904e-05, "loss": 0.8695, "step": 830 }, { "epoch": 0.19, "learning_rate": 9.999857943317227e-05, "loss": 0.8308, "step": 840 }, { "epoch": 0.19, "learning_rate": 9.999854540899003e-05, "loss": 0.8417, "step": 850 }, { "epoch": 0.2, "learning_rate": 9.999851098216262e-05, "loss": 0.8379, "step": 860 }, { "epoch": 0.2, "learning_rate": 9.999847615269027e-05, "loss": 0.8171, "step": 870 }, { "epoch": 0.2, "learning_rate": 9.999844092057331e-05, "loss": 0.8024, "step": 880 }, { "epoch": 0.2, "learning_rate": 9.9998405285812e-05, "loss": 0.7949, "step": 890 }, { "epoch": 0.21, "learning_rate": 9.999836924840663e-05, "loss": 0.8386, "step": 900 }, { "epoch": 0.21, "learning_rate": 9.999833280835749e-05, "loss": 0.8033, "step": 910 }, { "epoch": 0.21, "learning_rate": 9.999829596566487e-05, "loss": 0.8054, "step": 920 }, { "epoch": 0.21, "learning_rate": 9.999825872032907e-05, "loss": 0.849, "step": 930 }, { "epoch": 0.21, "learning_rate": 9.999822107235038e-05, "loss": 0.823, "step": 940 }, { "epoch": 0.22, "learning_rate": 9.999818302172912e-05, "loss": 0.8505, "step": 950 }, { "epoch": 0.22, "learning_rate": 9.999814456846558e-05, "loss": 0.814, "step": 960 }, { "epoch": 0.22, "learning_rate": 9.999810571256011e-05, "loss": 0.8678, "step": 970 }, { "epoch": 0.22, "learning_rate": 9.999806645401297e-05, "loss": 0.8011, "step": 980 }, { "epoch": 0.23, "learning_rate": 9.999802679282451e-05, "loss": 0.7961, "step": 990 }, { "epoch": 0.23, "learning_rate": 9.999798672899503e-05, "loss": 0.8372, "step": 1000 }, { "epoch": 0.23, "learning_rate": 9.999794626252485e-05, "loss": 0.858, "step": 1010 }, { "epoch": 0.23, "learning_rate": 9.999790539341432e-05, "loss": 0.8392, "step": 1020 }, { "epoch": 0.24, "learning_rate": 9.999786412166375e-05, "loss": 0.8099, "step": 1030 }, { "epoch": 0.24, "learning_rate": 9.999782244727346e-05, "loss": 0.8224, "step": 1040 }, { "epoch": 0.24, "learning_rate": 9.999778037024383e-05, "loss": 0.8334, "step": 1050 }, { "epoch": 0.24, "learning_rate": 9.999773789057518e-05, "loss": 0.8055, "step": 1060 }, { "epoch": 0.24, "learning_rate": 9.999769500826781e-05, "loss": 0.8339, "step": 1070 }, { "epoch": 0.25, "learning_rate": 9.999765172332212e-05, "loss": 0.8717, "step": 1080 }, { "epoch": 0.25, "learning_rate": 9.999760803573843e-05, "loss": 0.808, "step": 1090 }, { "epoch": 0.25, "learning_rate": 9.999756394551711e-05, "loss": 0.7978, "step": 1100 }, { "epoch": 0.25, "learning_rate": 9.999751945265851e-05, "loss": 0.7908, "step": 1110 }, { "epoch": 0.26, "learning_rate": 9.999747455716297e-05, "loss": 0.7996, "step": 1120 }, { "epoch": 0.26, "learning_rate": 9.999742925903087e-05, "loss": 0.8582, "step": 1130 }, { "epoch": 0.26, "learning_rate": 9.999738355826256e-05, "loss": 0.8247, "step": 1140 }, { "epoch": 0.26, "learning_rate": 9.999733745485842e-05, "loss": 0.8085, "step": 1150 }, { "epoch": 0.27, "learning_rate": 9.999729094881883e-05, "loss": 0.8387, "step": 1160 }, { "epoch": 0.27, "learning_rate": 9.999724404014414e-05, "loss": 0.8103, "step": 1170 }, { "epoch": 0.27, "learning_rate": 9.999719672883476e-05, "loss": 0.8184, "step": 1180 }, { "epoch": 0.27, "learning_rate": 9.999714901489103e-05, "loss": 0.7992, "step": 1190 }, { "epoch": 0.27, "learning_rate": 9.999710089831338e-05, "loss": 0.7716, "step": 1200 }, { "epoch": 0.28, "learning_rate": 9.999705237910215e-05, "loss": 0.7628, "step": 1210 }, { "epoch": 0.28, "learning_rate": 9.999700345725778e-05, "loss": 0.8049, "step": 1220 }, { "epoch": 0.28, "learning_rate": 9.999695413278062e-05, "loss": 0.8045, "step": 1230 }, { "epoch": 0.28, "learning_rate": 9.999690440567109e-05, "loss": 0.82, "step": 1240 }, { "epoch": 0.29, "learning_rate": 9.999685427592959e-05, "loss": 0.7653, "step": 1250 }, { "epoch": 0.29, "learning_rate": 9.999680374355652e-05, "loss": 0.7784, "step": 1260 }, { "epoch": 0.29, "learning_rate": 9.999675280855228e-05, "loss": 0.8231, "step": 1270 }, { "epoch": 0.29, "learning_rate": 9.999670147091729e-05, "loss": 0.8063, "step": 1280 }, { "epoch": 0.29, "learning_rate": 9.999664973065195e-05, "loss": 0.7787, "step": 1290 }, { "epoch": 0.3, "learning_rate": 9.99965975877567e-05, "loss": 0.8184, "step": 1300 }, { "epoch": 0.3, "learning_rate": 9.999654504223195e-05, "loss": 0.7919, "step": 1310 }, { "epoch": 0.3, "learning_rate": 9.999649209407812e-05, "loss": 0.8284, "step": 1320 }, { "epoch": 0.3, "learning_rate": 9.999643874329562e-05, "loss": 0.8074, "step": 1330 }, { "epoch": 0.31, "learning_rate": 9.999638498988491e-05, "loss": 0.7814, "step": 1340 }, { "epoch": 0.31, "learning_rate": 9.999633083384643e-05, "loss": 0.7822, "step": 1350 }, { "epoch": 0.31, "learning_rate": 9.999627627518056e-05, "loss": 0.7752, "step": 1360 }, { "epoch": 0.31, "learning_rate": 9.99962213138878e-05, "loss": 0.8033, "step": 1370 }, { "epoch": 0.32, "learning_rate": 9.999616594996854e-05, "loss": 0.7522, "step": 1380 }, { "epoch": 0.32, "learning_rate": 9.999611018342328e-05, "loss": 0.8013, "step": 1390 }, { "epoch": 0.32, "learning_rate": 9.999605401425243e-05, "loss": 0.8007, "step": 1400 }, { "epoch": 0.32, "learning_rate": 9.999599744245645e-05, "loss": 0.8369, "step": 1410 }, { "epoch": 0.32, "learning_rate": 9.999594046803581e-05, "loss": 0.774, "step": 1420 }, { "epoch": 0.33, "learning_rate": 9.999588309099095e-05, "loss": 0.8058, "step": 1430 }, { "epoch": 0.33, "learning_rate": 9.999582531132234e-05, "loss": 0.7925, "step": 1440 }, { "epoch": 0.33, "learning_rate": 9.999576712903047e-05, "loss": 0.8155, "step": 1450 }, { "epoch": 0.33, "learning_rate": 9.999570854411576e-05, "loss": 0.7546, "step": 1460 }, { "epoch": 0.34, "learning_rate": 9.999564955657873e-05, "loss": 0.7608, "step": 1470 }, { "epoch": 0.34, "learning_rate": 9.99955901664198e-05, "loss": 0.7872, "step": 1480 }, { "epoch": 0.34, "learning_rate": 9.99955303736395e-05, "loss": 0.7543, "step": 1490 }, { "epoch": 0.34, "learning_rate": 9.99954701782383e-05, "loss": 0.7825, "step": 1500 }, { "epoch": 0.35, "learning_rate": 9.999540958021665e-05, "loss": 0.7743, "step": 1510 }, { "epoch": 0.35, "learning_rate": 9.999534857957508e-05, "loss": 0.7825, "step": 1520 }, { "epoch": 0.35, "learning_rate": 9.999528717631405e-05, "loss": 0.7701, "step": 1530 }, { "epoch": 0.35, "learning_rate": 9.99952253704341e-05, "loss": 0.7972, "step": 1540 }, { "epoch": 0.35, "learning_rate": 9.999516316193568e-05, "loss": 0.779, "step": 1550 }, { "epoch": 0.36, "learning_rate": 9.99951005508193e-05, "loss": 0.7896, "step": 1560 }, { "epoch": 0.36, "learning_rate": 9.99950375370855e-05, "loss": 0.8369, "step": 1570 }, { "epoch": 0.36, "learning_rate": 9.999497412073474e-05, "loss": 0.8068, "step": 1580 }, { "epoch": 0.36, "learning_rate": 9.999491030176755e-05, "loss": 0.7602, "step": 1590 }, { "epoch": 0.37, "learning_rate": 9.999484608018446e-05, "loss": 0.8207, "step": 1600 }, { "epoch": 0.37, "learning_rate": 9.999478145598596e-05, "loss": 0.8092, "step": 1610 }, { "epoch": 0.37, "learning_rate": 9.999471642917258e-05, "loss": 0.789, "step": 1620 }, { "epoch": 0.37, "learning_rate": 9.999465099974485e-05, "loss": 0.802, "step": 1630 }, { "epoch": 0.37, "learning_rate": 9.99945851677033e-05, "loss": 0.7736, "step": 1640 }, { "epoch": 0.38, "learning_rate": 9.999451893304845e-05, "loss": 0.7491, "step": 1650 }, { "epoch": 0.38, "learning_rate": 9.999445229578084e-05, "loss": 0.7582, "step": 1660 }, { "epoch": 0.38, "learning_rate": 9.9994385255901e-05, "loss": 0.7585, "step": 1670 }, { "epoch": 0.38, "learning_rate": 9.999431781340947e-05, "loss": 0.7968, "step": 1680 }, { "epoch": 0.39, "learning_rate": 9.99942499683068e-05, "loss": 0.7311, "step": 1690 }, { "epoch": 0.39, "learning_rate": 9.999418172059353e-05, "loss": 0.7751, "step": 1700 }, { "epoch": 0.39, "learning_rate": 9.999411307027022e-05, "loss": 0.7988, "step": 1710 }, { "epoch": 0.39, "learning_rate": 9.99940440173374e-05, "loss": 0.7704, "step": 1720 }, { "epoch": 0.4, "learning_rate": 9.999397456179567e-05, "loss": 0.8388, "step": 1730 }, { "epoch": 0.4, "learning_rate": 9.999390470364554e-05, "loss": 0.7792, "step": 1740 }, { "epoch": 0.4, "learning_rate": 9.999383444288759e-05, "loss": 0.7706, "step": 1750 }, { "epoch": 0.4, "learning_rate": 9.999376377952239e-05, "loss": 0.7818, "step": 1760 }, { "epoch": 0.4, "learning_rate": 9.999369271355052e-05, "loss": 0.8088, "step": 1770 }, { "epoch": 0.41, "learning_rate": 9.999362124497254e-05, "loss": 0.7698, "step": 1780 }, { "epoch": 0.41, "learning_rate": 9.9993549373789e-05, "loss": 0.7719, "step": 1790 }, { "epoch": 0.41, "learning_rate": 9.999347710000053e-05, "loss": 0.7991, "step": 1800 }, { "epoch": 0.41, "learning_rate": 9.999340442360768e-05, "loss": 0.7797, "step": 1810 }, { "epoch": 0.42, "learning_rate": 9.999333134461104e-05, "loss": 0.7811, "step": 1820 }, { "epoch": 0.42, "learning_rate": 9.999325786301122e-05, "loss": 0.812, "step": 1830 }, { "epoch": 0.42, "learning_rate": 9.999318397880877e-05, "loss": 0.8146, "step": 1840 }, { "epoch": 0.42, "learning_rate": 9.99931096920043e-05, "loss": 0.7788, "step": 1850 }, { "epoch": 0.43, "learning_rate": 9.999303500259845e-05, "loss": 0.8158, "step": 1860 }, { "epoch": 0.43, "learning_rate": 9.999295991059176e-05, "loss": 0.7829, "step": 1870 }, { "epoch": 0.43, "learning_rate": 9.999288441598487e-05, "loss": 0.759, "step": 1880 }, { "epoch": 0.43, "learning_rate": 9.999280851877836e-05, "loss": 0.787, "step": 1890 }, { "epoch": 0.43, "learning_rate": 9.99927322189729e-05, "loss": 0.7932, "step": 1900 }, { "epoch": 0.44, "learning_rate": 9.999265551656905e-05, "loss": 0.8195, "step": 1910 }, { "epoch": 0.44, "learning_rate": 9.999257841156742e-05, "loss": 0.7727, "step": 1920 }, { "epoch": 0.44, "learning_rate": 9.999250090396868e-05, "loss": 0.7645, "step": 1930 }, { "epoch": 0.44, "learning_rate": 9.999242299377343e-05, "loss": 0.8221, "step": 1940 }, { "epoch": 0.45, "learning_rate": 9.999234468098227e-05, "loss": 0.7897, "step": 1950 }, { "epoch": 0.45, "learning_rate": 9.999226596559587e-05, "loss": 0.7622, "step": 1960 }, { "epoch": 0.45, "learning_rate": 9.999218684761487e-05, "loss": 0.7505, "step": 1970 }, { "epoch": 0.45, "learning_rate": 9.999210732703986e-05, "loss": 0.7421, "step": 1980 }, { "epoch": 0.45, "learning_rate": 9.999202740387152e-05, "loss": 0.8287, "step": 1990 }, { "epoch": 0.46, "learning_rate": 9.999194707811049e-05, "loss": 0.811, "step": 2000 }, { "epoch": 0.46, "learning_rate": 9.99918663497574e-05, "loss": 0.8109, "step": 2010 }, { "epoch": 0.46, "learning_rate": 9.999178521881289e-05, "loss": 0.8101, "step": 2020 }, { "epoch": 0.46, "learning_rate": 9.999170368527766e-05, "loss": 0.7553, "step": 2030 }, { "epoch": 0.47, "learning_rate": 9.999162174915232e-05, "loss": 0.7774, "step": 2040 }, { "epoch": 0.47, "learning_rate": 9.999153941043755e-05, "loss": 0.7804, "step": 2050 }, { "epoch": 0.47, "learning_rate": 9.999145666913403e-05, "loss": 0.7897, "step": 2060 }, { "epoch": 0.47, "learning_rate": 9.999137352524239e-05, "loss": 0.7999, "step": 2070 }, { "epoch": 0.48, "learning_rate": 9.999128997876333e-05, "loss": 0.7554, "step": 2080 }, { "epoch": 0.48, "learning_rate": 9.999120602969749e-05, "loss": 0.8022, "step": 2090 }, { "epoch": 0.48, "learning_rate": 9.999112167804558e-05, "loss": 0.7382, "step": 2100 }, { "epoch": 0.48, "learning_rate": 9.999103692380826e-05, "loss": 0.7654, "step": 2110 }, { "epoch": 0.48, "learning_rate": 9.999095176698622e-05, "loss": 0.7522, "step": 2120 }, { "epoch": 0.49, "learning_rate": 9.999086620758016e-05, "loss": 0.7691, "step": 2130 }, { "epoch": 0.49, "learning_rate": 9.999078024559072e-05, "loss": 0.8046, "step": 2140 }, { "epoch": 0.49, "learning_rate": 9.999069388101865e-05, "loss": 0.7927, "step": 2150 }, { "epoch": 0.49, "learning_rate": 9.99906071138646e-05, "loss": 0.7603, "step": 2160 }, { "epoch": 0.5, "learning_rate": 9.999051994412932e-05, "loss": 0.7559, "step": 2170 }, { "epoch": 0.5, "learning_rate": 9.999043237181345e-05, "loss": 0.7471, "step": 2180 }, { "epoch": 0.5, "learning_rate": 9.999034439691775e-05, "loss": 0.751, "step": 2190 }, { "epoch": 0.5, "learning_rate": 9.999025601944289e-05, "loss": 0.7536, "step": 2200 }, { "epoch": 0.51, "learning_rate": 9.999016723938961e-05, "loss": 0.7553, "step": 2210 }, { "epoch": 0.51, "learning_rate": 9.999007805675859e-05, "loss": 0.78, "step": 2220 }, { "epoch": 0.51, "learning_rate": 9.998998847155059e-05, "loss": 0.8154, "step": 2230 }, { "epoch": 0.51, "learning_rate": 9.99898984837663e-05, "loss": 0.8013, "step": 2240 }, { "epoch": 0.51, "learning_rate": 9.998980809340647e-05, "loss": 0.7671, "step": 2250 }, { "epoch": 0.52, "learning_rate": 9.998971730047181e-05, "loss": 0.817, "step": 2260 }, { "epoch": 0.52, "learning_rate": 9.998962610496305e-05, "loss": 0.7537, "step": 2270 }, { "epoch": 0.52, "learning_rate": 9.998953450688093e-05, "loss": 0.7734, "step": 2280 }, { "epoch": 0.52, "learning_rate": 9.998944250622618e-05, "loss": 0.7771, "step": 2290 }, { "epoch": 0.53, "learning_rate": 9.998935010299956e-05, "loss": 0.7246, "step": 2300 }, { "epoch": 0.53, "learning_rate": 9.99892572972018e-05, "loss": 0.7692, "step": 2310 }, { "epoch": 0.53, "learning_rate": 9.998916408883365e-05, "loss": 0.7664, "step": 2320 }, { "epoch": 0.53, "learning_rate": 9.998907047789585e-05, "loss": 0.8047, "step": 2330 }, { "epoch": 0.53, "learning_rate": 9.998897646438916e-05, "loss": 0.8031, "step": 2340 }, { "epoch": 0.54, "learning_rate": 9.998888204831436e-05, "loss": 0.7931, "step": 2350 }, { "epoch": 0.54, "learning_rate": 9.998878722967218e-05, "loss": 0.7858, "step": 2360 }, { "epoch": 0.54, "learning_rate": 9.99886920084634e-05, "loss": 0.7611, "step": 2370 }, { "epoch": 0.54, "learning_rate": 9.998859638468878e-05, "loss": 0.769, "step": 2380 }, { "epoch": 0.55, "learning_rate": 9.998850035834909e-05, "loss": 0.7823, "step": 2390 }, { "epoch": 0.55, "learning_rate": 9.99884039294451e-05, "loss": 0.7592, "step": 2400 }, { "epoch": 0.55, "learning_rate": 9.99883070979776e-05, "loss": 0.7894, "step": 2410 }, { "epoch": 0.55, "learning_rate": 9.998820986394737e-05, "loss": 0.7717, "step": 2420 }, { "epoch": 0.56, "learning_rate": 9.998811222735518e-05, "loss": 0.8143, "step": 2430 }, { "epoch": 0.56, "learning_rate": 9.998801418820181e-05, "loss": 0.7853, "step": 2440 }, { "epoch": 0.56, "learning_rate": 9.998791574648807e-05, "loss": 0.7772, "step": 2450 }, { "epoch": 0.56, "learning_rate": 9.998781690221474e-05, "loss": 0.7323, "step": 2460 }, { "epoch": 0.56, "learning_rate": 9.998771765538262e-05, "loss": 0.7637, "step": 2470 }, { "epoch": 0.57, "learning_rate": 9.99876180059925e-05, "loss": 0.7797, "step": 2480 }, { "epoch": 0.57, "learning_rate": 9.998751795404519e-05, "loss": 0.7617, "step": 2490 }, { "epoch": 0.57, "learning_rate": 9.998741749954152e-05, "loss": 0.7695, "step": 2500 }, { "epoch": 0.57, "learning_rate": 9.998731664248227e-05, "loss": 0.7513, "step": 2510 }, { "epoch": 0.58, "learning_rate": 9.998721538286824e-05, "loss": 0.7383, "step": 2520 }, { "epoch": 0.58, "learning_rate": 9.998711372070026e-05, "loss": 0.7793, "step": 2530 }, { "epoch": 0.58, "learning_rate": 9.998701165597916e-05, "loss": 0.7799, "step": 2540 }, { "epoch": 0.58, "learning_rate": 9.998690918870577e-05, "loss": 0.7719, "step": 2550 }, { "epoch": 0.59, "learning_rate": 9.998680631888089e-05, "loss": 0.8047, "step": 2560 }, { "epoch": 0.59, "learning_rate": 9.998670304650535e-05, "loss": 0.7367, "step": 2570 }, { "epoch": 0.59, "learning_rate": 9.998659937158e-05, "loss": 0.7857, "step": 2580 }, { "epoch": 0.59, "learning_rate": 9.998649529410567e-05, "loss": 0.7944, "step": 2590 }, { "epoch": 0.59, "learning_rate": 9.998639081408316e-05, "loss": 0.7377, "step": 2600 }, { "epoch": 0.6, "learning_rate": 9.998628593151339e-05, "loss": 0.7475, "step": 2610 }, { "epoch": 0.6, "learning_rate": 9.998618064639711e-05, "loss": 0.8119, "step": 2620 }, { "epoch": 0.6, "learning_rate": 9.998607495873524e-05, "loss": 0.7552, "step": 2630 }, { "epoch": 0.6, "learning_rate": 9.998596886852862e-05, "loss": 0.7821, "step": 2640 }, { "epoch": 0.61, "learning_rate": 9.998586237577807e-05, "loss": 0.7943, "step": 2650 }, { "epoch": 0.61, "learning_rate": 9.998575548048447e-05, "loss": 0.7588, "step": 2660 }, { "epoch": 0.61, "learning_rate": 9.99856481826487e-05, "loss": 0.7298, "step": 2670 }, { "epoch": 0.61, "learning_rate": 9.998554048227158e-05, "loss": 0.7719, "step": 2680 }, { "epoch": 0.61, "learning_rate": 9.998543237935403e-05, "loss": 0.7876, "step": 2690 }, { "epoch": 0.62, "learning_rate": 9.998532387389686e-05, "loss": 0.7934, "step": 2700 }, { "epoch": 0.62, "learning_rate": 9.9985214965901e-05, "loss": 0.7564, "step": 2710 }, { "epoch": 0.62, "learning_rate": 9.99851056553673e-05, "loss": 0.7636, "step": 2720 }, { "epoch": 0.62, "learning_rate": 9.998499594229662e-05, "loss": 0.7314, "step": 2730 }, { "epoch": 0.63, "learning_rate": 9.99848858266899e-05, "loss": 0.7562, "step": 2740 }, { "epoch": 0.63, "learning_rate": 9.998477530854798e-05, "loss": 0.7705, "step": 2750 }, { "epoch": 0.63, "learning_rate": 9.998466438787176e-05, "loss": 0.7818, "step": 2760 }, { "epoch": 0.63, "learning_rate": 9.998455306466214e-05, "loss": 0.7677, "step": 2770 }, { "epoch": 0.64, "learning_rate": 9.998444133892e-05, "loss": 0.7525, "step": 2780 }, { "epoch": 0.64, "learning_rate": 9.998432921064626e-05, "loss": 0.7293, "step": 2790 }, { "epoch": 0.64, "learning_rate": 9.998421667984183e-05, "loss": 0.8038, "step": 2800 }, { "epoch": 0.64, "learning_rate": 9.99841037465076e-05, "loss": 0.8003, "step": 2810 }, { "epoch": 0.64, "learning_rate": 9.998399041064448e-05, "loss": 0.728, "step": 2820 }, { "epoch": 0.65, "learning_rate": 9.998387667225337e-05, "loss": 0.741, "step": 2830 }, { "epoch": 0.65, "learning_rate": 9.998376253133522e-05, "loss": 0.8303, "step": 2840 }, { "epoch": 0.65, "learning_rate": 9.99836479878909e-05, "loss": 0.7791, "step": 2850 }, { "epoch": 0.65, "learning_rate": 9.99835330419214e-05, "loss": 0.7785, "step": 2860 }, { "epoch": 0.66, "learning_rate": 9.998341769342758e-05, "loss": 0.7482, "step": 2870 }, { "epoch": 0.66, "learning_rate": 9.998330194241041e-05, "loss": 0.7651, "step": 2880 }, { "epoch": 0.66, "learning_rate": 9.99831857888708e-05, "loss": 0.7277, "step": 2890 }, { "epoch": 0.66, "learning_rate": 9.99830692328097e-05, "loss": 0.7481, "step": 2900 }, { "epoch": 0.66, "learning_rate": 9.998295227422805e-05, "loss": 0.7617, "step": 2910 }, { "epoch": 0.67, "learning_rate": 9.998283491312677e-05, "loss": 0.7357, "step": 2920 }, { "epoch": 0.67, "learning_rate": 9.998271714950683e-05, "loss": 0.743, "step": 2930 }, { "epoch": 0.67, "learning_rate": 9.998259898336916e-05, "loss": 0.7716, "step": 2940 }, { "epoch": 0.67, "learning_rate": 9.998248041471474e-05, "loss": 0.7611, "step": 2950 }, { "epoch": 0.68, "learning_rate": 9.998236144354449e-05, "loss": 0.7567, "step": 2960 }, { "epoch": 0.68, "learning_rate": 9.998224206985938e-05, "loss": 0.7757, "step": 2970 }, { "epoch": 0.68, "learning_rate": 9.998212229366038e-05, "loss": 0.7256, "step": 2980 }, { "epoch": 0.68, "learning_rate": 9.998200211494844e-05, "loss": 0.7641, "step": 2990 }, { "epoch": 0.69, "learning_rate": 9.998188153372455e-05, "loss": 0.7392, "step": 3000 }, { "epoch": 0.69, "learning_rate": 9.998176054998965e-05, "loss": 0.7497, "step": 3010 }, { "epoch": 0.69, "learning_rate": 9.998163916374475e-05, "loss": 0.7198, "step": 3020 }, { "epoch": 0.69, "learning_rate": 9.99815173749908e-05, "loss": 0.7968, "step": 3030 }, { "epoch": 0.69, "learning_rate": 9.998139518372879e-05, "loss": 0.7576, "step": 3040 }, { "epoch": 0.7, "learning_rate": 9.998127258995971e-05, "loss": 0.751, "step": 3050 }, { "epoch": 0.7, "learning_rate": 9.998114959368452e-05, "loss": 0.7608, "step": 3060 }, { "epoch": 0.7, "learning_rate": 9.998102619490425e-05, "loss": 0.771, "step": 3070 }, { "epoch": 0.7, "learning_rate": 9.998090239361989e-05, "loss": 0.7408, "step": 3080 }, { "epoch": 0.71, "learning_rate": 9.99807781898324e-05, "loss": 0.7831, "step": 3090 }, { "epoch": 0.71, "learning_rate": 9.998065358354281e-05, "loss": 0.7497, "step": 3100 }, { "epoch": 0.71, "learning_rate": 9.998052857475213e-05, "loss": 0.7479, "step": 3110 }, { "epoch": 0.71, "learning_rate": 9.998040316346133e-05, "loss": 0.7662, "step": 3120 }, { "epoch": 0.72, "learning_rate": 9.998027734967144e-05, "loss": 0.7726, "step": 3130 }, { "epoch": 0.72, "learning_rate": 9.99801511333835e-05, "loss": 0.7098, "step": 3140 }, { "epoch": 0.72, "learning_rate": 9.99800245145985e-05, "loss": 0.7213, "step": 3150 }, { "epoch": 0.72, "learning_rate": 9.997989749331744e-05, "loss": 0.7357, "step": 3160 }, { "epoch": 0.72, "learning_rate": 9.997977006954138e-05, "loss": 0.7481, "step": 3170 }, { "epoch": 0.73, "learning_rate": 9.997964224327134e-05, "loss": 0.7273, "step": 3180 }, { "epoch": 0.73, "learning_rate": 9.997951401450834e-05, "loss": 0.7562, "step": 3190 }, { "epoch": 0.73, "learning_rate": 9.99793853832534e-05, "loss": 0.7091, "step": 3200 }, { "epoch": 0.73, "learning_rate": 9.997925634950758e-05, "loss": 0.7928, "step": 3210 }, { "epoch": 0.74, "learning_rate": 9.99791269132719e-05, "loss": 0.732, "step": 3220 }, { "epoch": 0.74, "learning_rate": 9.997899707454741e-05, "loss": 0.7565, "step": 3230 }, { "epoch": 0.74, "learning_rate": 9.997886683333516e-05, "loss": 0.7919, "step": 3240 }, { "epoch": 0.74, "learning_rate": 9.99787361896362e-05, "loss": 0.717, "step": 3250 }, { "epoch": 0.74, "learning_rate": 9.997860514345157e-05, "loss": 0.7479, "step": 3260 }, { "epoch": 0.75, "learning_rate": 9.997847369478234e-05, "loss": 0.773, "step": 3270 }, { "epoch": 0.75, "learning_rate": 9.997834184362956e-05, "loss": 0.7129, "step": 3280 }, { "epoch": 0.75, "learning_rate": 9.997820958999428e-05, "loss": 0.753, "step": 3290 }, { "epoch": 0.75, "learning_rate": 9.99780769338776e-05, "loss": 0.7377, "step": 3300 }, { "epoch": 0.76, "learning_rate": 9.997794387528056e-05, "loss": 0.7472, "step": 3310 }, { "epoch": 0.76, "learning_rate": 9.997781041420422e-05, "loss": 0.7896, "step": 3320 }, { "epoch": 0.76, "learning_rate": 9.997767655064969e-05, "loss": 0.7245, "step": 3330 }, { "epoch": 0.76, "learning_rate": 9.997754228461804e-05, "loss": 0.775, "step": 3340 }, { "epoch": 0.77, "learning_rate": 9.997740761611032e-05, "loss": 0.756, "step": 3350 }, { "epoch": 0.77, "learning_rate": 9.997727254512766e-05, "loss": 0.7377, "step": 3360 }, { "epoch": 0.77, "learning_rate": 9.99771370716711e-05, "loss": 0.7387, "step": 3370 }, { "epoch": 0.77, "learning_rate": 9.997700119574177e-05, "loss": 0.7619, "step": 3380 }, { "epoch": 0.77, "learning_rate": 9.997686491734076e-05, "loss": 0.7859, "step": 3390 }, { "epoch": 0.78, "learning_rate": 9.997672823646913e-05, "loss": 0.7433, "step": 3400 }, { "epoch": 0.78, "learning_rate": 9.997659115312802e-05, "loss": 0.7626, "step": 3410 }, { "epoch": 0.78, "learning_rate": 9.997645366731852e-05, "loss": 0.7535, "step": 3420 }, { "epoch": 0.78, "learning_rate": 9.997631577904174e-05, "loss": 0.7537, "step": 3430 }, { "epoch": 0.79, "learning_rate": 9.997617748829879e-05, "loss": 0.7371, "step": 3440 }, { "epoch": 0.79, "learning_rate": 9.997603879509079e-05, "loss": 0.7454, "step": 3450 }, { "epoch": 0.79, "learning_rate": 9.997589969941885e-05, "loss": 0.7323, "step": 3460 }, { "epoch": 0.79, "learning_rate": 9.997576020128407e-05, "loss": 0.7482, "step": 3470 }, { "epoch": 0.8, "learning_rate": 9.997562030068761e-05, "loss": 0.7263, "step": 3480 }, { "epoch": 0.8, "learning_rate": 9.997547999763058e-05, "loss": 0.802, "step": 3490 }, { "epoch": 0.8, "learning_rate": 9.997533929211412e-05, "loss": 0.7351, "step": 3500 }, { "epoch": 0.8, "learning_rate": 9.997519818413934e-05, "loss": 0.7244, "step": 3510 }, { "epoch": 0.8, "learning_rate": 9.997505667370738e-05, "loss": 0.7484, "step": 3520 }, { "epoch": 0.81, "learning_rate": 9.997491476081941e-05, "loss": 0.7063, "step": 3530 }, { "epoch": 0.81, "learning_rate": 9.997477244547654e-05, "loss": 0.7539, "step": 3540 }, { "epoch": 0.81, "learning_rate": 9.997462972767993e-05, "loss": 0.7501, "step": 3550 }, { "epoch": 0.81, "learning_rate": 9.997448660743072e-05, "loss": 0.7608, "step": 3560 }, { "epoch": 0.82, "learning_rate": 9.997434308473009e-05, "loss": 0.7565, "step": 3570 }, { "epoch": 0.82, "learning_rate": 9.997419915957916e-05, "loss": 0.7733, "step": 3580 }, { "epoch": 0.82, "learning_rate": 9.99740548319791e-05, "loss": 0.7561, "step": 3590 }, { "epoch": 0.82, "learning_rate": 9.997391010193109e-05, "loss": 0.745, "step": 3600 }, { "epoch": 0.82, "learning_rate": 9.997376496943628e-05, "loss": 0.7263, "step": 3610 }, { "epoch": 0.83, "learning_rate": 9.997361943449583e-05, "loss": 0.7184, "step": 3620 }, { "epoch": 0.83, "learning_rate": 9.997347349711093e-05, "loss": 0.7419, "step": 3630 }, { "epoch": 0.83, "learning_rate": 9.997332715728276e-05, "loss": 0.7045, "step": 3640 }, { "epoch": 0.83, "learning_rate": 9.997318041501246e-05, "loss": 0.7274, "step": 3650 }, { "epoch": 0.84, "learning_rate": 9.997303327030128e-05, "loss": 0.7221, "step": 3660 }, { "epoch": 0.84, "learning_rate": 9.997288572315034e-05, "loss": 0.746, "step": 3670 }, { "epoch": 0.84, "learning_rate": 9.997273777356084e-05, "loss": 0.7567, "step": 3680 }, { "epoch": 0.84, "learning_rate": 9.9972589421534e-05, "loss": 0.7371, "step": 3690 }, { "epoch": 0.85, "learning_rate": 9.9972440667071e-05, "loss": 0.7221, "step": 3700 }, { "epoch": 0.85, "learning_rate": 9.997229151017303e-05, "loss": 0.7165, "step": 3710 }, { "epoch": 0.85, "learning_rate": 9.99721419508413e-05, "loss": 0.7352, "step": 3720 }, { "epoch": 0.85, "learning_rate": 9.9971991989077e-05, "loss": 0.7312, "step": 3730 }, { "epoch": 0.85, "learning_rate": 9.997184162488137e-05, "loss": 0.7267, "step": 3740 }, { "epoch": 0.86, "learning_rate": 9.99716908582556e-05, "loss": 0.7608, "step": 3750 }, { "epoch": 0.86, "learning_rate": 9.997153968920088e-05, "loss": 0.7019, "step": 3760 }, { "epoch": 0.86, "learning_rate": 9.997138811771847e-05, "loss": 0.7292, "step": 3770 }, { "epoch": 0.86, "learning_rate": 9.997123614380957e-05, "loss": 0.7505, "step": 3780 }, { "epoch": 0.87, "learning_rate": 9.99710837674754e-05, "loss": 0.7473, "step": 3790 }, { "epoch": 0.87, "learning_rate": 9.997093098871721e-05, "loss": 0.6957, "step": 3800 }, { "epoch": 0.87, "learning_rate": 9.997077780753619e-05, "loss": 0.7302, "step": 3810 }, { "epoch": 0.87, "learning_rate": 9.997062422393362e-05, "loss": 0.7496, "step": 3820 }, { "epoch": 0.88, "learning_rate": 9.99704702379107e-05, "loss": 0.7499, "step": 3830 }, { "epoch": 0.88, "learning_rate": 9.997031584946868e-05, "loss": 0.7067, "step": 3840 }, { "epoch": 0.88, "learning_rate": 9.997016105860883e-05, "loss": 0.7392, "step": 3850 }, { "epoch": 0.88, "learning_rate": 9.997000586533236e-05, "loss": 0.7406, "step": 3860 }, { "epoch": 0.88, "learning_rate": 9.996985026964053e-05, "loss": 0.726, "step": 3870 }, { "epoch": 0.89, "learning_rate": 9.99696942715346e-05, "loss": 0.7309, "step": 3880 }, { "epoch": 0.89, "learning_rate": 9.996953787101581e-05, "loss": 0.7302, "step": 3890 }, { "epoch": 0.89, "learning_rate": 9.996938106808547e-05, "loss": 0.7121, "step": 3900 }, { "epoch": 0.89, "learning_rate": 9.996922386274478e-05, "loss": 0.7331, "step": 3910 }, { "epoch": 0.9, "learning_rate": 9.996906625499503e-05, "loss": 0.8017, "step": 3920 }, { "epoch": 0.9, "learning_rate": 9.99689082448375e-05, "loss": 0.7476, "step": 3930 }, { "epoch": 0.9, "learning_rate": 9.996874983227345e-05, "loss": 0.7584, "step": 3940 }, { "epoch": 0.9, "learning_rate": 9.996859101730416e-05, "loss": 0.7654, "step": 3950 }, { "epoch": 0.9, "learning_rate": 9.99684317999309e-05, "loss": 0.7129, "step": 3960 }, { "epoch": 0.91, "learning_rate": 9.996827218015496e-05, "loss": 0.7749, "step": 3970 }, { "epoch": 0.91, "learning_rate": 9.996811215797764e-05, "loss": 0.7694, "step": 3980 }, { "epoch": 0.91, "learning_rate": 9.99679517334002e-05, "loss": 0.6959, "step": 3990 }, { "epoch": 0.91, "learning_rate": 9.996779090642396e-05, "loss": 0.7254, "step": 4000 }, { "epoch": 0.92, "learning_rate": 9.996762967705018e-05, "loss": 0.7344, "step": 4010 }, { "epoch": 0.92, "learning_rate": 9.996746804528019e-05, "loss": 0.7212, "step": 4020 }, { "epoch": 0.92, "learning_rate": 9.996730601111529e-05, "loss": 0.7375, "step": 4030 }, { "epoch": 0.92, "learning_rate": 9.996714357455677e-05, "loss": 0.7372, "step": 4040 }, { "epoch": 0.93, "learning_rate": 9.996698073560595e-05, "loss": 0.7156, "step": 4050 }, { "epoch": 0.93, "learning_rate": 9.996681749426413e-05, "loss": 0.7249, "step": 4060 }, { "epoch": 0.93, "learning_rate": 9.996665385053263e-05, "loss": 0.7088, "step": 4070 }, { "epoch": 0.93, "learning_rate": 9.996648980441277e-05, "loss": 0.7792, "step": 4080 }, { "epoch": 0.93, "learning_rate": 9.996632535590587e-05, "loss": 0.7576, "step": 4090 }, { "epoch": 0.94, "learning_rate": 9.996616050501324e-05, "loss": 0.7254, "step": 4100 }, { "epoch": 0.94, "learning_rate": 9.996599525173624e-05, "loss": 0.7462, "step": 4110 }, { "epoch": 0.94, "learning_rate": 9.996582959607617e-05, "loss": 0.7838, "step": 4120 }, { "epoch": 0.94, "learning_rate": 9.996566353803438e-05, "loss": 0.7282, "step": 4130 }, { "epoch": 0.95, "learning_rate": 9.996549707761221e-05, "loss": 0.7414, "step": 4140 }, { "epoch": 0.95, "learning_rate": 9.996533021481099e-05, "loss": 0.7263, "step": 4150 }, { "epoch": 0.95, "learning_rate": 9.996516294963207e-05, "loss": 0.7236, "step": 4160 }, { "epoch": 1.0, "learning_rate": 9.996499528207679e-05, "loss": 0.7049, "step": 4170 }, { "epoch": 1.0, "learning_rate": 9.99648272121465e-05, "loss": 0.743, "step": 4180 }, { "epoch": 1.01, "learning_rate": 9.996465873984257e-05, "loss": 0.7669, "step": 4190 }, { "epoch": 1.01, "learning_rate": 9.996448986516633e-05, "loss": 0.7021, "step": 4200 }, { "epoch": 1.01, "learning_rate": 9.996432058811918e-05, "loss": 0.7505, "step": 4210 }, { "epoch": 1.01, "learning_rate": 9.996415090870244e-05, "loss": 0.688, "step": 4220 }, { "epoch": 1.02, "learning_rate": 9.996398082691749e-05, "loss": 0.6933, "step": 4230 }, { "epoch": 1.02, "learning_rate": 9.996381034276571e-05, "loss": 0.6841, "step": 4240 }, { "epoch": 1.02, "learning_rate": 9.996363945624847e-05, "loss": 0.6953, "step": 4250 }, { "epoch": 1.02, "learning_rate": 9.996346816736714e-05, "loss": 0.7284, "step": 4260 }, { "epoch": 1.02, "learning_rate": 9.996329647612312e-05, "loss": 0.7713, "step": 4270 }, { "epoch": 1.03, "learning_rate": 9.996312438251776e-05, "loss": 0.7431, "step": 4280 }, { "epoch": 1.03, "learning_rate": 9.996295188655245e-05, "loss": 0.7257, "step": 4290 }, { "epoch": 1.03, "learning_rate": 9.996277898822861e-05, "loss": 0.7438, "step": 4300 }, { "epoch": 1.03, "learning_rate": 9.99626056875476e-05, "loss": 0.7546, "step": 4310 }, { "epoch": 1.04, "learning_rate": 9.996243198451084e-05, "loss": 0.7636, "step": 4320 }, { "epoch": 1.04, "learning_rate": 9.996225787911971e-05, "loss": 0.7656, "step": 4330 }, { "epoch": 1.04, "learning_rate": 9.996208337137563e-05, "loss": 0.7748, "step": 4340 }, { "epoch": 1.04, "learning_rate": 9.996190846127999e-05, "loss": 0.7948, "step": 4350 }, { "epoch": 1.05, "learning_rate": 9.996173314883419e-05, "loss": 0.7245, "step": 4360 }, { "epoch": 1.05, "learning_rate": 9.996155743403968e-05, "loss": 0.7236, "step": 4370 }, { "epoch": 1.05, "learning_rate": 9.996138131689783e-05, "loss": 0.734, "step": 4380 }, { "epoch": 1.05, "learning_rate": 9.996120479741008e-05, "loss": 0.7079, "step": 4390 }, { "epoch": 1.05, "learning_rate": 9.996102787557786e-05, "loss": 0.7113, "step": 4400 }, { "epoch": 1.06, "learning_rate": 9.996085055140258e-05, "loss": 0.7183, "step": 4410 }, { "epoch": 1.06, "learning_rate": 9.996067282488568e-05, "loss": 0.7211, "step": 4420 }, { "epoch": 1.06, "learning_rate": 9.996049469602858e-05, "loss": 0.7498, "step": 4430 }, { "epoch": 1.06, "learning_rate": 9.99603161648327e-05, "loss": 0.6828, "step": 4440 }, { "epoch": 1.07, "learning_rate": 9.996013723129951e-05, "loss": 0.7085, "step": 4450 }, { "epoch": 1.07, "learning_rate": 9.995995789543044e-05, "loss": 0.7047, "step": 4460 }, { "epoch": 1.07, "learning_rate": 9.995977815722694e-05, "loss": 0.7392, "step": 4470 }, { "epoch": 1.07, "learning_rate": 9.995959801669043e-05, "loss": 0.7072, "step": 4480 }, { "epoch": 1.07, "learning_rate": 9.995941747382241e-05, "loss": 0.7167, "step": 4490 }, { "epoch": 1.08, "learning_rate": 9.995923652862427e-05, "loss": 0.7108, "step": 4500 }, { "epoch": 1.08, "learning_rate": 9.995905518109752e-05, "loss": 0.7446, "step": 4510 }, { "epoch": 1.08, "learning_rate": 9.99588734312436e-05, "loss": 0.7753, "step": 4520 }, { "epoch": 1.08, "learning_rate": 9.995869127906396e-05, "loss": 0.6988, "step": 4530 }, { "epoch": 1.09, "learning_rate": 9.99585087245601e-05, "loss": 0.7413, "step": 4540 }, { "epoch": 1.09, "learning_rate": 9.995832576773348e-05, "loss": 0.694, "step": 4550 }, { "epoch": 1.09, "learning_rate": 9.995814240858554e-05, "loss": 0.7751, "step": 4560 }, { "epoch": 1.09, "learning_rate": 9.995795864711779e-05, "loss": 0.7196, "step": 4570 }, { "epoch": 1.1, "learning_rate": 9.995777448333171e-05, "loss": 0.731, "step": 4580 }, { "epoch": 1.1, "learning_rate": 9.995758991722877e-05, "loss": 0.7152, "step": 4590 }, { "epoch": 1.1, "learning_rate": 9.995740494881045e-05, "loss": 0.7127, "step": 4600 }, { "epoch": 1.1, "learning_rate": 9.995721957807826e-05, "loss": 0.7059, "step": 4610 }, { "epoch": 1.1, "learning_rate": 9.99570338050337e-05, "loss": 0.7176, "step": 4620 }, { "epoch": 1.11, "learning_rate": 9.995684762967823e-05, "loss": 0.744, "step": 4630 }, { "epoch": 1.11, "learning_rate": 9.995666105201338e-05, "loss": 0.6988, "step": 4640 }, { "epoch": 1.11, "learning_rate": 9.995647407204063e-05, "loss": 0.7206, "step": 4650 }, { "epoch": 1.11, "learning_rate": 9.995628668976152e-05, "loss": 0.7054, "step": 4660 }, { "epoch": 1.12, "learning_rate": 9.995609890517751e-05, "loss": 0.7137, "step": 4670 }, { "epoch": 1.12, "learning_rate": 9.995591071829014e-05, "loss": 0.7117, "step": 4680 }, { "epoch": 1.12, "learning_rate": 9.995572212910094e-05, "loss": 0.732, "step": 4690 }, { "epoch": 1.12, "learning_rate": 9.995553313761141e-05, "loss": 0.7288, "step": 4700 }, { "epoch": 1.12, "learning_rate": 9.995534374382307e-05, "loss": 0.751, "step": 4710 }, { "epoch": 1.13, "learning_rate": 9.995515394773744e-05, "loss": 0.7029, "step": 4720 }, { "epoch": 1.13, "learning_rate": 9.995496374935606e-05, "loss": 0.681, "step": 4730 }, { "epoch": 1.13, "learning_rate": 9.995477314868049e-05, "loss": 0.7057, "step": 4740 }, { "epoch": 1.13, "learning_rate": 9.995458214571221e-05, "loss": 0.7453, "step": 4750 }, { "epoch": 1.14, "learning_rate": 9.995439074045278e-05, "loss": 0.728, "step": 4760 }, { "epoch": 1.14, "learning_rate": 9.995419893290376e-05, "loss": 0.7319, "step": 4770 }, { "epoch": 1.14, "learning_rate": 9.995400672306667e-05, "loss": 0.7272, "step": 4780 }, { "epoch": 1.14, "learning_rate": 9.995381411094307e-05, "loss": 0.7315, "step": 4790 }, { "epoch": 1.15, "learning_rate": 9.995362109653451e-05, "loss": 0.7154, "step": 4800 }, { "epoch": 1.15, "learning_rate": 9.995342767984253e-05, "loss": 0.7399, "step": 4810 }, { "epoch": 1.15, "learning_rate": 9.995323386086872e-05, "loss": 0.7521, "step": 4820 }, { "epoch": 1.15, "learning_rate": 9.995303963961463e-05, "loss": 0.738, "step": 4830 }, { "epoch": 1.15, "learning_rate": 9.995284501608177e-05, "loss": 0.7542, "step": 4840 }, { "epoch": 1.16, "learning_rate": 9.995264999027178e-05, "loss": 0.7182, "step": 4850 }, { "epoch": 1.16, "learning_rate": 9.995245456218621e-05, "loss": 0.7464, "step": 4860 }, { "epoch": 1.16, "learning_rate": 9.995225873182663e-05, "loss": 0.7309, "step": 4870 }, { "epoch": 1.16, "learning_rate": 9.99520624991946e-05, "loss": 0.7021, "step": 4880 }, { "epoch": 1.17, "learning_rate": 9.995186586429172e-05, "loss": 0.7096, "step": 4890 }, { "epoch": 1.17, "learning_rate": 9.995166882711958e-05, "loss": 0.7541, "step": 4900 }, { "epoch": 1.17, "learning_rate": 9.995147138767972e-05, "loss": 0.7224, "step": 4910 }, { "epoch": 1.17, "learning_rate": 9.99512735459738e-05, "loss": 0.7286, "step": 4920 }, { "epoch": 1.18, "learning_rate": 9.995107530200337e-05, "loss": 0.7673, "step": 4930 }, { "epoch": 1.18, "learning_rate": 9.995087665577001e-05, "loss": 0.784, "step": 4940 }, { "epoch": 1.18, "learning_rate": 9.995067760727536e-05, "loss": 0.6848, "step": 4950 }, { "epoch": 1.18, "learning_rate": 9.995047815652101e-05, "loss": 0.7347, "step": 4960 }, { "epoch": 1.18, "learning_rate": 9.995027830350857e-05, "loss": 0.7256, "step": 4970 }, { "epoch": 1.19, "learning_rate": 9.995007804823964e-05, "loss": 0.7066, "step": 4980 }, { "epoch": 1.19, "learning_rate": 9.994987739071583e-05, "loss": 0.7273, "step": 4990 }, { "epoch": 1.19, "learning_rate": 9.994967633093876e-05, "loss": 0.7153, "step": 5000 }, { "epoch": 1.19, "learning_rate": 9.994947486891005e-05, "loss": 0.6853, "step": 5010 }, { "epoch": 1.2, "learning_rate": 9.994927300463133e-05, "loss": 0.7008, "step": 5020 }, { "epoch": 1.2, "learning_rate": 9.994907073810422e-05, "loss": 0.7345, "step": 5030 }, { "epoch": 1.2, "learning_rate": 9.994886806933034e-05, "loss": 0.7002, "step": 5040 }, { "epoch": 1.2, "learning_rate": 9.994866499831133e-05, "loss": 0.7144, "step": 5050 }, { "epoch": 1.2, "learning_rate": 9.994846152504882e-05, "loss": 0.7207, "step": 5060 }, { "epoch": 1.21, "learning_rate": 9.994825764954448e-05, "loss": 0.6638, "step": 5070 }, { "epoch": 1.21, "learning_rate": 9.994805337179989e-05, "loss": 0.7056, "step": 5080 }, { "epoch": 1.21, "learning_rate": 9.994784869181674e-05, "loss": 0.7584, "step": 5090 }, { "epoch": 1.21, "learning_rate": 9.994764360959667e-05, "loss": 0.7144, "step": 5100 }, { "epoch": 1.22, "learning_rate": 9.994743812514135e-05, "loss": 0.7034, "step": 5110 }, { "epoch": 1.22, "learning_rate": 9.99472322384524e-05, "loss": 0.6945, "step": 5120 }, { "epoch": 1.22, "learning_rate": 9.994702594953149e-05, "loss": 0.7131, "step": 5130 }, { "epoch": 1.22, "learning_rate": 9.994681925838029e-05, "loss": 0.6923, "step": 5140 }, { "epoch": 1.23, "learning_rate": 9.994661216500045e-05, "loss": 0.7255, "step": 5150 }, { "epoch": 1.23, "learning_rate": 9.994640466939367e-05, "loss": 0.7153, "step": 5160 }, { "epoch": 1.23, "learning_rate": 9.994619677156156e-05, "loss": 0.6788, "step": 5170 }, { "epoch": 1.23, "learning_rate": 9.994598847150587e-05, "loss": 0.6831, "step": 5180 }, { "epoch": 1.23, "learning_rate": 9.994577976922821e-05, "loss": 0.7484, "step": 5190 }, { "epoch": 1.24, "learning_rate": 9.994557066473032e-05, "loss": 0.7197, "step": 5200 }, { "epoch": 1.24, "learning_rate": 9.994536115801383e-05, "loss": 0.6957, "step": 5210 }, { "epoch": 1.24, "learning_rate": 9.994515124908046e-05, "loss": 0.7147, "step": 5220 }, { "epoch": 1.24, "learning_rate": 9.994494093793188e-05, "loss": 0.707, "step": 5230 }, { "epoch": 1.25, "learning_rate": 9.994473022456981e-05, "loss": 0.7083, "step": 5240 }, { "epoch": 1.25, "learning_rate": 9.994451910899592e-05, "loss": 0.7206, "step": 5250 }, { "epoch": 1.25, "learning_rate": 9.994430759121195e-05, "loss": 0.7158, "step": 5260 }, { "epoch": 1.25, "learning_rate": 9.994409567121954e-05, "loss": 0.6968, "step": 5270 }, { "epoch": 1.26, "learning_rate": 9.994388334902045e-05, "loss": 0.7157, "step": 5280 }, { "epoch": 1.26, "learning_rate": 9.994367062461636e-05, "loss": 0.7115, "step": 5290 }, { "epoch": 1.26, "learning_rate": 9.9943457498009e-05, "loss": 0.7123, "step": 5300 }, { "epoch": 1.26, "learning_rate": 9.99432439692001e-05, "loss": 0.7153, "step": 5310 }, { "epoch": 1.26, "learning_rate": 9.994303003819134e-05, "loss": 0.7059, "step": 5320 }, { "epoch": 1.27, "learning_rate": 9.994281570498447e-05, "loss": 0.7243, "step": 5330 }, { "epoch": 1.27, "learning_rate": 9.994260096958121e-05, "loss": 0.6694, "step": 5340 }, { "epoch": 1.27, "learning_rate": 9.994238583198329e-05, "loss": 0.7294, "step": 5350 }, { "epoch": 1.27, "learning_rate": 9.994217029219246e-05, "loss": 0.6871, "step": 5360 }, { "epoch": 1.28, "learning_rate": 9.994195435021041e-05, "loss": 0.7094, "step": 5370 }, { "epoch": 1.28, "learning_rate": 9.994173800603891e-05, "loss": 0.7244, "step": 5380 }, { "epoch": 1.28, "learning_rate": 9.99415212596797e-05, "loss": 0.735, "step": 5390 }, { "epoch": 1.28, "learning_rate": 9.994130411113453e-05, "loss": 0.6658, "step": 5400 }, { "epoch": 1.28, "learning_rate": 9.994108656040515e-05, "loss": 0.729, "step": 5410 }, { "epoch": 1.29, "learning_rate": 9.99408686074933e-05, "loss": 0.7003, "step": 5420 }, { "epoch": 1.29, "learning_rate": 9.994065025240075e-05, "loss": 0.7036, "step": 5430 }, { "epoch": 1.29, "learning_rate": 9.994043149512924e-05, "loss": 0.7071, "step": 5440 }, { "epoch": 1.29, "learning_rate": 9.994021233568054e-05, "loss": 0.7129, "step": 5450 }, { "epoch": 1.3, "learning_rate": 9.993999277405641e-05, "loss": 0.6988, "step": 5460 }, { "epoch": 1.3, "learning_rate": 9.993977281025862e-05, "loss": 0.7033, "step": 5470 }, { "epoch": 1.3, "learning_rate": 9.993955244428897e-05, "loss": 0.7122, "step": 5480 }, { "epoch": 1.3, "learning_rate": 9.993933167614917e-05, "loss": 0.695, "step": 5490 }, { "epoch": 1.31, "learning_rate": 9.993911050584106e-05, "loss": 0.7298, "step": 5500 }, { "epoch": 1.31, "learning_rate": 9.99388889333664e-05, "loss": 0.7049, "step": 5510 }, { "epoch": 1.31, "learning_rate": 9.993866695872698e-05, "loss": 0.6855, "step": 5520 }, { "epoch": 1.31, "learning_rate": 9.993844458192456e-05, "loss": 0.6959, "step": 5530 }, { "epoch": 1.31, "learning_rate": 9.993822180296097e-05, "loss": 0.7332, "step": 5540 }, { "epoch": 1.32, "learning_rate": 9.993799862183797e-05, "loss": 0.7247, "step": 5550 }, { "epoch": 1.32, "learning_rate": 9.99377750385574e-05, "loss": 0.6798, "step": 5560 }, { "epoch": 1.32, "learning_rate": 9.993755105312101e-05, "loss": 0.7181, "step": 5570 }, { "epoch": 1.32, "learning_rate": 9.993732666553063e-05, "loss": 0.6869, "step": 5580 }, { "epoch": 1.33, "learning_rate": 9.993710187578807e-05, "loss": 0.7106, "step": 5590 }, { "epoch": 1.33, "learning_rate": 9.993687668389513e-05, "loss": 0.692, "step": 5600 }, { "epoch": 1.33, "learning_rate": 9.993665108985362e-05, "loss": 0.7108, "step": 5610 }, { "epoch": 1.33, "learning_rate": 9.993642509366537e-05, "loss": 0.722, "step": 5620 }, { "epoch": 1.34, "learning_rate": 9.99361986953322e-05, "loss": 0.7457, "step": 5630 }, { "epoch": 1.34, "learning_rate": 9.993597189485593e-05, "loss": 0.7321, "step": 5640 }, { "epoch": 1.34, "learning_rate": 9.993574469223837e-05, "loss": 0.7412, "step": 5650 }, { "epoch": 1.34, "learning_rate": 9.993551708748138e-05, "loss": 0.6875, "step": 5660 }, { "epoch": 1.34, "learning_rate": 9.993528908058676e-05, "loss": 0.6758, "step": 5670 }, { "epoch": 1.35, "learning_rate": 9.993506067155639e-05, "loss": 0.7037, "step": 5680 }, { "epoch": 1.35, "learning_rate": 9.993483186039205e-05, "loss": 0.6866, "step": 5690 }, { "epoch": 1.35, "learning_rate": 9.993460264709563e-05, "loss": 0.7129, "step": 5700 }, { "epoch": 1.35, "learning_rate": 9.993437303166897e-05, "loss": 0.7235, "step": 5710 }, { "epoch": 1.36, "learning_rate": 9.993414301411391e-05, "loss": 0.704, "step": 5720 }, { "epoch": 1.36, "learning_rate": 9.993391259443228e-05, "loss": 0.7238, "step": 5730 }, { "epoch": 1.36, "learning_rate": 9.993368177262598e-05, "loss": 0.7624, "step": 5740 }, { "epoch": 1.36, "learning_rate": 9.993345054869683e-05, "loss": 0.7178, "step": 5750 }, { "epoch": 1.36, "learning_rate": 9.993321892264671e-05, "loss": 0.7613, "step": 5760 }, { "epoch": 1.37, "learning_rate": 9.99329868944775e-05, "loss": 0.7241, "step": 5770 }, { "epoch": 1.37, "learning_rate": 9.993275446419105e-05, "loss": 0.693, "step": 5780 }, { "epoch": 1.37, "learning_rate": 9.993252163178923e-05, "loss": 0.6925, "step": 5790 }, { "epoch": 1.37, "learning_rate": 9.993228839727391e-05, "loss": 0.7125, "step": 5800 }, { "epoch": 1.38, "learning_rate": 9.9932054760647e-05, "loss": 0.7026, "step": 5810 }, { "epoch": 1.38, "learning_rate": 9.993182072191034e-05, "loss": 0.7025, "step": 5820 }, { "epoch": 1.38, "learning_rate": 9.993158628106585e-05, "loss": 0.6816, "step": 5830 }, { "epoch": 1.38, "learning_rate": 9.993135143811539e-05, "loss": 0.6957, "step": 5840 }, { "epoch": 1.39, "learning_rate": 9.993111619306086e-05, "loss": 0.7104, "step": 5850 }, { "epoch": 1.39, "learning_rate": 9.993088054590416e-05, "loss": 0.6965, "step": 5860 }, { "epoch": 1.39, "learning_rate": 9.99306444966472e-05, "loss": 0.7079, "step": 5870 }, { "epoch": 1.39, "learning_rate": 9.993040804529185e-05, "loss": 0.7191, "step": 5880 }, { "epoch": 1.39, "learning_rate": 9.993017119184004e-05, "loss": 0.7073, "step": 5890 }, { "epoch": 1.4, "learning_rate": 9.992993393629367e-05, "loss": 0.7001, "step": 5900 }, { "epoch": 1.4, "learning_rate": 9.992969627865464e-05, "loss": 0.6944, "step": 5910 }, { "epoch": 1.4, "learning_rate": 9.992945821892488e-05, "loss": 0.708, "step": 5920 }, { "epoch": 1.4, "learning_rate": 9.99292197571063e-05, "loss": 0.6982, "step": 5930 }, { "epoch": 1.41, "learning_rate": 9.992898089320081e-05, "loss": 0.6823, "step": 5940 }, { "epoch": 1.41, "learning_rate": 9.992874162721035e-05, "loss": 0.7281, "step": 5950 }, { "epoch": 1.41, "learning_rate": 9.992850195913684e-05, "loss": 0.7073, "step": 5960 }, { "epoch": 1.41, "learning_rate": 9.992826188898222e-05, "loss": 0.6957, "step": 5970 }, { "epoch": 1.42, "learning_rate": 9.99280214167484e-05, "loss": 0.7159, "step": 5980 }, { "epoch": 1.42, "learning_rate": 9.992778054243733e-05, "loss": 0.704, "step": 5990 }, { "epoch": 1.42, "learning_rate": 9.992753926605096e-05, "loss": 0.7177, "step": 6000 }, { "epoch": 1.42, "learning_rate": 9.992729758759121e-05, "loss": 0.7089, "step": 6010 }, { "epoch": 1.42, "learning_rate": 9.992705550706006e-05, "loss": 0.7151, "step": 6020 }, { "epoch": 1.43, "learning_rate": 9.992681302445943e-05, "loss": 0.7194, "step": 6030 }, { "epoch": 1.43, "learning_rate": 9.992657013979127e-05, "loss": 0.6672, "step": 6040 }, { "epoch": 1.43, "learning_rate": 9.992632685305756e-05, "loss": 0.7123, "step": 6050 }, { "epoch": 1.43, "learning_rate": 9.992608316426026e-05, "loss": 0.7347, "step": 6060 }, { "epoch": 1.44, "learning_rate": 9.99258390734013e-05, "loss": 0.7295, "step": 6070 }, { "epoch": 1.44, "learning_rate": 9.992559458048267e-05, "loss": 0.6933, "step": 6080 }, { "epoch": 1.44, "learning_rate": 9.992534968550633e-05, "loss": 0.6699, "step": 6090 }, { "epoch": 1.44, "learning_rate": 9.992510438847427e-05, "loss": 0.6938, "step": 6100 }, { "epoch": 1.44, "learning_rate": 9.992485868938843e-05, "loss": 0.7641, "step": 6110 }, { "epoch": 1.45, "learning_rate": 9.992461258825084e-05, "loss": 0.6728, "step": 6120 }, { "epoch": 1.45, "learning_rate": 9.992436608506343e-05, "loss": 0.7007, "step": 6130 }, { "epoch": 1.45, "learning_rate": 9.99241191798282e-05, "loss": 0.6977, "step": 6140 }, { "epoch": 1.45, "learning_rate": 9.992387187254717e-05, "loss": 0.7102, "step": 6150 }, { "epoch": 1.46, "learning_rate": 9.99236241632223e-05, "loss": 0.7342, "step": 6160 }, { "epoch": 1.46, "learning_rate": 9.992337605185557e-05, "loss": 0.7129, "step": 6170 }, { "epoch": 1.46, "learning_rate": 9.992312753844904e-05, "loss": 0.7107, "step": 6180 }, { "epoch": 1.46, "learning_rate": 9.992287862300464e-05, "loss": 0.6708, "step": 6190 }, { "epoch": 1.47, "learning_rate": 9.992262930552441e-05, "loss": 0.7296, "step": 6200 }, { "epoch": 1.47, "learning_rate": 9.992237958601037e-05, "loss": 0.6915, "step": 6210 }, { "epoch": 1.47, "learning_rate": 9.99221294644645e-05, "loss": 0.684, "step": 6220 }, { "epoch": 1.47, "learning_rate": 9.992187894088884e-05, "loss": 0.7592, "step": 6230 }, { "epoch": 1.47, "learning_rate": 9.992162801528539e-05, "loss": 0.7163, "step": 6240 }, { "epoch": 1.48, "learning_rate": 9.992137668765617e-05, "loss": 0.6997, "step": 6250 }, { "epoch": 1.48, "learning_rate": 9.992112495800324e-05, "loss": 0.718, "step": 6260 }, { "epoch": 1.48, "learning_rate": 9.992087282632857e-05, "loss": 0.7375, "step": 6270 }, { "epoch": 1.48, "learning_rate": 9.992062029263422e-05, "loss": 0.6893, "step": 6280 }, { "epoch": 1.49, "learning_rate": 9.992036735692223e-05, "loss": 0.7288, "step": 6290 }, { "epoch": 1.49, "learning_rate": 9.992011401919463e-05, "loss": 0.6999, "step": 6300 }, { "epoch": 1.49, "learning_rate": 9.991986027945346e-05, "loss": 0.6744, "step": 6310 }, { "epoch": 1.49, "learning_rate": 9.991960613770077e-05, "loss": 0.7387, "step": 6320 }, { "epoch": 1.5, "learning_rate": 9.991935159393859e-05, "loss": 0.6959, "step": 6330 }, { "epoch": 1.5, "learning_rate": 9.991909664816899e-05, "loss": 0.7125, "step": 6340 }, { "epoch": 1.5, "learning_rate": 9.991884130039399e-05, "loss": 0.7234, "step": 6350 }, { "epoch": 1.5, "learning_rate": 9.99185855506157e-05, "loss": 0.6989, "step": 6360 }, { "epoch": 1.5, "learning_rate": 9.991832939883613e-05, "loss": 0.6843, "step": 6370 }, { "epoch": 1.51, "learning_rate": 9.991807284505737e-05, "loss": 0.6875, "step": 6380 }, { "epoch": 1.51, "learning_rate": 9.991781588928147e-05, "loss": 0.6728, "step": 6390 }, { "epoch": 1.51, "learning_rate": 9.991755853151051e-05, "loss": 0.7305, "step": 6400 }, { "epoch": 1.51, "learning_rate": 9.991730077174656e-05, "loss": 0.6981, "step": 6410 }, { "epoch": 1.52, "learning_rate": 9.99170426099917e-05, "loss": 0.6955, "step": 6420 }, { "epoch": 1.52, "learning_rate": 9.991678404624801e-05, "loss": 0.7102, "step": 6430 }, { "epoch": 1.52, "learning_rate": 9.991652508051754e-05, "loss": 0.7186, "step": 6440 }, { "epoch": 1.52, "learning_rate": 9.991626571280242e-05, "loss": 0.7249, "step": 6450 }, { "epoch": 1.52, "learning_rate": 9.991600594310473e-05, "loss": 0.6453, "step": 6460 }, { "epoch": 1.53, "learning_rate": 9.991574577142654e-05, "loss": 0.7129, "step": 6470 }, { "epoch": 1.53, "learning_rate": 9.991548519776996e-05, "loss": 0.7137, "step": 6480 }, { "epoch": 1.53, "learning_rate": 9.991522422213708e-05, "loss": 0.747, "step": 6490 }, { "epoch": 1.53, "learning_rate": 9.991496284453002e-05, "loss": 0.7346, "step": 6500 }, { "epoch": 1.54, "learning_rate": 9.991470106495086e-05, "loss": 0.6987, "step": 6510 }, { "epoch": 1.54, "learning_rate": 9.991443888340174e-05, "loss": 0.7078, "step": 6520 }, { "epoch": 1.54, "learning_rate": 9.991417629988474e-05, "loss": 0.7218, "step": 6530 }, { "epoch": 1.54, "learning_rate": 9.991391331440199e-05, "loss": 0.7191, "step": 6540 }, { "epoch": 1.55, "learning_rate": 9.99136499269556e-05, "loss": 0.7185, "step": 6550 }, { "epoch": 1.55, "learning_rate": 9.991338613754771e-05, "loss": 0.7423, "step": 6560 }, { "epoch": 1.55, "learning_rate": 9.991312194618041e-05, "loss": 0.7315, "step": 6570 }, { "epoch": 1.55, "learning_rate": 9.991285735285587e-05, "loss": 0.7471, "step": 6580 }, { "epoch": 1.55, "learning_rate": 9.991259235757619e-05, "loss": 0.702, "step": 6590 }, { "epoch": 1.56, "learning_rate": 9.99123269603435e-05, "loss": 0.7342, "step": 6600 }, { "epoch": 1.56, "learning_rate": 9.991206116115996e-05, "loss": 0.7189, "step": 6610 }, { "epoch": 1.56, "learning_rate": 9.991179496002771e-05, "loss": 0.7018, "step": 6620 }, { "epoch": 1.56, "learning_rate": 9.991152835694888e-05, "loss": 0.7122, "step": 6630 }, { "epoch": 1.57, "learning_rate": 9.991126135192561e-05, "loss": 0.7695, "step": 6640 }, { "epoch": 1.57, "learning_rate": 9.991099394496007e-05, "loss": 0.6999, "step": 6650 }, { "epoch": 1.57, "learning_rate": 9.991072613605441e-05, "loss": 0.6928, "step": 6660 }, { "epoch": 1.57, "learning_rate": 9.991045792521077e-05, "loss": 0.7178, "step": 6670 }, { "epoch": 1.58, "learning_rate": 9.991018931243133e-05, "loss": 0.6955, "step": 6680 }, { "epoch": 1.58, "learning_rate": 9.990992029771824e-05, "loss": 0.6863, "step": 6690 }, { "epoch": 1.58, "learning_rate": 9.990965088107367e-05, "loss": 0.7124, "step": 6700 }, { "epoch": 1.58, "learning_rate": 9.99093810624998e-05, "loss": 0.7353, "step": 6710 }, { "epoch": 1.58, "learning_rate": 9.990911084199878e-05, "loss": 0.6896, "step": 6720 }, { "epoch": 1.59, "learning_rate": 9.990884021957282e-05, "loss": 0.731, "step": 6730 }, { "epoch": 1.59, "learning_rate": 9.990856919522407e-05, "loss": 0.6812, "step": 6740 }, { "epoch": 1.59, "learning_rate": 9.990829776895472e-05, "loss": 0.7244, "step": 6750 }, { "epoch": 1.59, "learning_rate": 9.990802594076696e-05, "loss": 0.741, "step": 6760 }, { "epoch": 1.6, "learning_rate": 9.990775371066296e-05, "loss": 0.7432, "step": 6770 }, { "epoch": 1.6, "learning_rate": 9.990748107864496e-05, "loss": 0.6789, "step": 6780 }, { "epoch": 1.6, "learning_rate": 9.99072080447151e-05, "loss": 0.6791, "step": 6790 }, { "epoch": 1.6, "learning_rate": 9.990693460887562e-05, "loss": 0.73, "step": 6800 }, { "epoch": 1.6, "learning_rate": 9.990666077112869e-05, "loss": 0.7127, "step": 6810 }, { "epoch": 1.61, "learning_rate": 9.990638653147655e-05, "loss": 0.7442, "step": 6820 }, { "epoch": 1.61, "learning_rate": 9.990611188992138e-05, "loss": 0.7131, "step": 6830 }, { "epoch": 1.61, "learning_rate": 9.99058368464654e-05, "loss": 0.7008, "step": 6840 }, { "epoch": 1.61, "learning_rate": 9.990556140111082e-05, "loss": 0.7148, "step": 6850 }, { "epoch": 1.62, "learning_rate": 9.990528555385987e-05, "loss": 0.7294, "step": 6860 }, { "epoch": 1.62, "learning_rate": 9.990500930471475e-05, "loss": 0.7311, "step": 6870 }, { "epoch": 1.62, "learning_rate": 9.990473265367773e-05, "loss": 0.7263, "step": 6880 }, { "epoch": 1.62, "learning_rate": 9.990445560075098e-05, "loss": 0.7142, "step": 6890 }, { "epoch": 1.63, "learning_rate": 9.990417814593677e-05, "loss": 0.719, "step": 6900 }, { "epoch": 1.63, "learning_rate": 9.990390028923733e-05, "loss": 0.7375, "step": 6910 }, { "epoch": 1.63, "learning_rate": 9.990362203065488e-05, "loss": 0.6987, "step": 6920 }, { "epoch": 1.63, "learning_rate": 9.990334337019169e-05, "loss": 0.7565, "step": 6930 }, { "epoch": 1.63, "learning_rate": 9.990306430784997e-05, "loss": 0.6895, "step": 6940 }, { "epoch": 1.64, "learning_rate": 9.9902784843632e-05, "loss": 0.69, "step": 6950 }, { "epoch": 1.64, "learning_rate": 9.990250497754e-05, "loss": 0.659, "step": 6960 }, { "epoch": 1.64, "learning_rate": 9.990222470957624e-05, "loss": 0.7146, "step": 6970 }, { "epoch": 1.64, "learning_rate": 9.990194403974298e-05, "loss": 0.7412, "step": 6980 }, { "epoch": 1.65, "learning_rate": 9.990166296804246e-05, "loss": 0.727, "step": 6990 }, { "epoch": 1.65, "learning_rate": 9.990138149447699e-05, "loss": 0.7005, "step": 7000 }, { "epoch": 1.65, "learning_rate": 9.990109961904877e-05, "loss": 0.6583, "step": 7010 }, { "epoch": 1.65, "learning_rate": 9.990081734176014e-05, "loss": 0.6881, "step": 7020 }, { "epoch": 1.66, "learning_rate": 9.990053466261331e-05, "loss": 0.6797, "step": 7030 }, { "epoch": 1.66, "learning_rate": 9.99002515816106e-05, "loss": 0.7566, "step": 7040 }, { "epoch": 1.66, "learning_rate": 9.989996809875426e-05, "loss": 0.694, "step": 7050 }, { "epoch": 1.66, "learning_rate": 9.989968421404661e-05, "loss": 0.6755, "step": 7060 }, { "epoch": 1.66, "learning_rate": 9.989939992748989e-05, "loss": 0.7267, "step": 7070 }, { "epoch": 1.67, "learning_rate": 9.989911523908642e-05, "loss": 0.7226, "step": 7080 }, { "epoch": 1.67, "learning_rate": 9.989883014883849e-05, "loss": 0.7217, "step": 7090 }, { "epoch": 1.67, "learning_rate": 9.989854465674841e-05, "loss": 0.7426, "step": 7100 }, { "epoch": 1.67, "learning_rate": 9.989825876281845e-05, "loss": 0.7091, "step": 7110 }, { "epoch": 1.68, "learning_rate": 9.98979724670509e-05, "loss": 0.7018, "step": 7120 }, { "epoch": 1.68, "learning_rate": 9.989768576944811e-05, "loss": 0.6973, "step": 7130 }, { "epoch": 1.68, "learning_rate": 9.989739867001236e-05, "loss": 0.6642, "step": 7140 }, { "epoch": 1.68, "learning_rate": 9.989711116874598e-05, "loss": 0.7022, "step": 7150 }, { "epoch": 1.68, "learning_rate": 9.989682326565127e-05, "loss": 0.738, "step": 7160 }, { "epoch": 1.69, "learning_rate": 9.989653496073055e-05, "loss": 0.7096, "step": 7170 }, { "epoch": 1.69, "learning_rate": 9.989624625398615e-05, "loss": 0.7264, "step": 7180 }, { "epoch": 1.69, "learning_rate": 9.989595714542038e-05, "loss": 0.701, "step": 7190 }, { "epoch": 1.69, "learning_rate": 9.98956676350356e-05, "loss": 0.7227, "step": 7200 }, { "epoch": 1.7, "learning_rate": 9.989537772283411e-05, "loss": 0.6958, "step": 7210 }, { "epoch": 1.7, "learning_rate": 9.989508740881824e-05, "loss": 0.6948, "step": 7220 }, { "epoch": 1.7, "learning_rate": 9.989479669299035e-05, "loss": 0.712, "step": 7230 }, { "epoch": 1.7, "learning_rate": 9.989450557535279e-05, "loss": 0.7358, "step": 7240 }, { "epoch": 1.71, "learning_rate": 9.989421405590786e-05, "loss": 0.7571, "step": 7250 }, { "epoch": 1.71, "learning_rate": 9.989392213465795e-05, "loss": 0.6779, "step": 7260 }, { "epoch": 1.71, "learning_rate": 9.98936298116054e-05, "loss": 0.6676, "step": 7270 }, { "epoch": 1.71, "learning_rate": 9.989333708675257e-05, "loss": 0.672, "step": 7280 }, { "epoch": 1.71, "learning_rate": 9.98930439601018e-05, "loss": 0.7342, "step": 7290 }, { "epoch": 1.72, "learning_rate": 9.989275043165544e-05, "loss": 0.7033, "step": 7300 }, { "epoch": 1.72, "learning_rate": 9.98924565014159e-05, "loss": 0.729, "step": 7310 }, { "epoch": 1.72, "learning_rate": 9.98921621693855e-05, "loss": 0.7169, "step": 7320 }, { "epoch": 1.72, "learning_rate": 9.989186743556665e-05, "loss": 0.6813, "step": 7330 }, { "epoch": 1.73, "learning_rate": 9.989157229996169e-05, "loss": 0.6898, "step": 7340 }, { "epoch": 1.73, "learning_rate": 9.989127676257302e-05, "loss": 0.707, "step": 7350 }, { "epoch": 1.73, "learning_rate": 9.989098082340299e-05, "loss": 0.6744, "step": 7360 }, { "epoch": 1.73, "learning_rate": 9.989068448245403e-05, "loss": 0.7012, "step": 7370 }, { "epoch": 1.74, "learning_rate": 9.989038773972848e-05, "loss": 0.7165, "step": 7380 }, { "epoch": 1.74, "learning_rate": 9.989009059522875e-05, "loss": 0.7148, "step": 7390 }, { "epoch": 1.74, "learning_rate": 9.988979304895725e-05, "loss": 0.6796, "step": 7400 }, { "epoch": 1.74, "learning_rate": 9.988949510091634e-05, "loss": 0.6752, "step": 7410 }, { "epoch": 1.74, "learning_rate": 9.988919675110844e-05, "loss": 0.6944, "step": 7420 }, { "epoch": 1.75, "learning_rate": 9.988889799953595e-05, "loss": 0.6758, "step": 7430 }, { "epoch": 1.75, "learning_rate": 9.98885988462013e-05, "loss": 0.696, "step": 7440 }, { "epoch": 1.75, "learning_rate": 9.988829929110686e-05, "loss": 0.6756, "step": 7450 }, { "epoch": 1.75, "learning_rate": 9.988799933425505e-05, "loss": 0.68, "step": 7460 }, { "epoch": 1.76, "learning_rate": 9.988769897564832e-05, "loss": 0.7081, "step": 7470 }, { "epoch": 1.76, "learning_rate": 9.988739821528903e-05, "loss": 0.733, "step": 7480 }, { "epoch": 1.76, "learning_rate": 9.988709705317965e-05, "loss": 0.6732, "step": 7490 }, { "epoch": 1.76, "learning_rate": 9.988679548932259e-05, "loss": 0.6511, "step": 7500 }, { "epoch": 1.76, "learning_rate": 9.988649352372028e-05, "loss": 0.7321, "step": 7510 }, { "epoch": 1.77, "learning_rate": 9.988619115637514e-05, "loss": 0.7072, "step": 7520 }, { "epoch": 1.77, "learning_rate": 9.988588838728963e-05, "loss": 0.6944, "step": 7530 }, { "epoch": 1.77, "learning_rate": 9.988558521646617e-05, "loss": 0.7127, "step": 7540 }, { "epoch": 1.77, "learning_rate": 9.988528164390721e-05, "loss": 0.6582, "step": 7550 }, { "epoch": 1.78, "learning_rate": 9.988497766961518e-05, "loss": 0.6925, "step": 7560 }, { "epoch": 1.78, "learning_rate": 9.988467329359253e-05, "loss": 0.6811, "step": 7570 }, { "epoch": 1.78, "learning_rate": 9.988436851584172e-05, "loss": 0.6818, "step": 7580 }, { "epoch": 1.78, "learning_rate": 9.988406333636521e-05, "loss": 0.7014, "step": 7590 }, { "epoch": 1.79, "learning_rate": 9.988375775516548e-05, "loss": 0.7043, "step": 7600 }, { "epoch": 1.79, "learning_rate": 9.988345177224493e-05, "loss": 0.7384, "step": 7610 }, { "epoch": 1.79, "learning_rate": 9.988314538760605e-05, "loss": 0.7082, "step": 7620 }, { "epoch": 1.79, "learning_rate": 9.988283860125134e-05, "loss": 0.6992, "step": 7630 }, { "epoch": 1.79, "learning_rate": 9.988253141318322e-05, "loss": 0.7262, "step": 7640 }, { "epoch": 1.8, "learning_rate": 9.988222382340419e-05, "loss": 0.7147, "step": 7650 }, { "epoch": 1.8, "learning_rate": 9.988191583191673e-05, "loss": 0.7, "step": 7660 }, { "epoch": 1.8, "learning_rate": 9.988160743872332e-05, "loss": 0.6858, "step": 7670 }, { "epoch": 1.8, "learning_rate": 9.988129864382645e-05, "loss": 0.6812, "step": 7680 }, { "epoch": 1.81, "learning_rate": 9.988098944722856e-05, "loss": 0.7165, "step": 7690 }, { "epoch": 1.81, "learning_rate": 9.988067984893221e-05, "loss": 0.6826, "step": 7700 }, { "epoch": 1.81, "learning_rate": 9.988036984893984e-05, "loss": 0.6957, "step": 7710 }, { "epoch": 1.81, "learning_rate": 9.988005944725398e-05, "loss": 0.7344, "step": 7720 }, { "epoch": 1.82, "learning_rate": 9.98797486438771e-05, "loss": 0.6827, "step": 7730 }, { "epoch": 1.82, "learning_rate": 9.987943743881173e-05, "loss": 0.6976, "step": 7740 }, { "epoch": 1.82, "learning_rate": 9.987912583206036e-05, "loss": 0.7247, "step": 7750 }, { "epoch": 1.82, "learning_rate": 9.98788138236255e-05, "loss": 0.7113, "step": 7760 }, { "epoch": 1.82, "learning_rate": 9.987850141350967e-05, "loss": 0.712, "step": 7770 }, { "epoch": 1.83, "learning_rate": 9.987818860171538e-05, "loss": 0.663, "step": 7780 }, { "epoch": 1.83, "learning_rate": 9.987787538824513e-05, "loss": 0.6977, "step": 7790 }, { "epoch": 1.83, "learning_rate": 9.987756177310149e-05, "loss": 0.7291, "step": 7800 }, { "epoch": 1.83, "learning_rate": 9.987724775628696e-05, "loss": 0.7396, "step": 7810 }, { "epoch": 1.84, "learning_rate": 9.987693333780406e-05, "loss": 0.7018, "step": 7820 }, { "epoch": 1.84, "learning_rate": 9.987661851765532e-05, "loss": 0.6724, "step": 7830 }, { "epoch": 1.84, "learning_rate": 9.98763032958433e-05, "loss": 0.6832, "step": 7840 }, { "epoch": 1.84, "learning_rate": 9.987598767237051e-05, "loss": 0.686, "step": 7850 }, { "epoch": 1.84, "learning_rate": 9.987567164723952e-05, "loss": 0.6915, "step": 7860 }, { "epoch": 1.85, "learning_rate": 9.987535522045285e-05, "loss": 0.6689, "step": 7870 }, { "epoch": 1.85, "learning_rate": 9.987503839201308e-05, "loss": 0.6887, "step": 7880 }, { "epoch": 1.85, "learning_rate": 9.987472116192271e-05, "loss": 0.6862, "step": 7890 }, { "epoch": 1.85, "learning_rate": 9.987440353018435e-05, "loss": 0.7366, "step": 7900 }, { "epoch": 1.86, "learning_rate": 9.987408549680052e-05, "loss": 0.7004, "step": 7910 }, { "epoch": 1.86, "learning_rate": 9.98737670617738e-05, "loss": 0.6608, "step": 7920 }, { "epoch": 1.86, "learning_rate": 9.987344822510674e-05, "loss": 0.7506, "step": 7930 }, { "epoch": 1.86, "learning_rate": 9.987312898680192e-05, "loss": 0.7474, "step": 7940 }, { "epoch": 1.87, "learning_rate": 9.987280934686189e-05, "loss": 0.7372, "step": 7950 }, { "epoch": 1.87, "learning_rate": 9.987248930528927e-05, "loss": 0.6971, "step": 7960 }, { "epoch": 1.87, "learning_rate": 9.98721688620866e-05, "loss": 0.6965, "step": 7970 }, { "epoch": 1.87, "learning_rate": 9.987184801725647e-05, "loss": 0.7041, "step": 7980 }, { "epoch": 1.87, "learning_rate": 9.987152677080145e-05, "loss": 0.7245, "step": 7990 }, { "epoch": 1.88, "learning_rate": 9.987120512272414e-05, "loss": 0.7196, "step": 8000 }, { "epoch": 1.88, "learning_rate": 9.987088307302714e-05, "loss": 0.6989, "step": 8010 }, { "epoch": 1.88, "learning_rate": 9.987056062171302e-05, "loss": 0.7107, "step": 8020 }, { "epoch": 1.88, "learning_rate": 9.987023776878442e-05, "loss": 0.693, "step": 8030 }, { "epoch": 1.89, "learning_rate": 9.986991451424388e-05, "loss": 0.6985, "step": 8040 }, { "epoch": 1.89, "learning_rate": 9.986959085809405e-05, "loss": 0.7126, "step": 8050 }, { "epoch": 1.89, "learning_rate": 9.986926680033751e-05, "loss": 0.6976, "step": 8060 }, { "epoch": 1.89, "learning_rate": 9.986894234097688e-05, "loss": 0.7281, "step": 8070 }, { "epoch": 1.9, "learning_rate": 9.986861748001478e-05, "loss": 0.6533, "step": 8080 }, { "epoch": 1.9, "learning_rate": 9.986829221745382e-05, "loss": 0.6099, "step": 8090 }, { "epoch": 1.9, "learning_rate": 9.986796655329661e-05, "loss": 0.6495, "step": 8100 }, { "epoch": 1.9, "learning_rate": 9.986764048754578e-05, "loss": 0.6624, "step": 8110 }, { "epoch": 1.9, "learning_rate": 9.986731402020398e-05, "loss": 0.6737, "step": 8120 }, { "epoch": 1.91, "learning_rate": 9.986698715127378e-05, "loss": 0.713, "step": 8130 }, { "epoch": 1.91, "learning_rate": 9.986665988075787e-05, "loss": 0.6971, "step": 8140 }, { "epoch": 1.91, "learning_rate": 9.986633220865885e-05, "loss": 0.7057, "step": 8150 }, { "epoch": 1.91, "learning_rate": 9.986600413497938e-05, "loss": 0.6894, "step": 8160 }, { "epoch": 1.92, "learning_rate": 9.98656756597221e-05, "loss": 0.6958, "step": 8170 }, { "epoch": 1.92, "learning_rate": 9.986534678288963e-05, "loss": 0.7216, "step": 8180 }, { "epoch": 1.92, "learning_rate": 9.986501750448466e-05, "loss": 0.6635, "step": 8190 }, { "epoch": 1.92, "learning_rate": 9.986468782450982e-05, "loss": 0.6952, "step": 8200 }, { "epoch": 1.92, "learning_rate": 9.986435774296774e-05, "loss": 0.7242, "step": 8210 }, { "epoch": 1.93, "learning_rate": 9.986402725986112e-05, "loss": 0.7047, "step": 8220 }, { "epoch": 1.93, "learning_rate": 9.986369637519262e-05, "loss": 0.7475, "step": 8230 }, { "epoch": 1.93, "learning_rate": 9.986336508896485e-05, "loss": 0.7056, "step": 8240 }, { "epoch": 1.93, "learning_rate": 9.986303340118055e-05, "loss": 0.7132, "step": 8250 }, { "epoch": 1.94, "learning_rate": 9.986270131184234e-05, "loss": 0.6621, "step": 8260 }, { "epoch": 1.94, "learning_rate": 9.986236882095292e-05, "loss": 0.6859, "step": 8270 }, { "epoch": 1.94, "learning_rate": 9.986203592851496e-05, "loss": 0.6993, "step": 8280 }, { "epoch": 1.94, "learning_rate": 9.986170263453114e-05, "loss": 0.6878, "step": 8290 }, { "epoch": 1.95, "learning_rate": 9.986136893900416e-05, "loss": 0.6714, "step": 8300 }, { "epoch": 1.95, "learning_rate": 9.986103484193668e-05, "loss": 0.6675, "step": 8310 }, { "epoch": 1.95, "learning_rate": 9.986070034333139e-05, "loss": 0.7115, "step": 8320 }, { "epoch": 2.0, "learning_rate": 9.986036544319099e-05, "loss": 0.6652, "step": 8330 }, { "epoch": 2.0, "learning_rate": 9.986003014151821e-05, "loss": 0.6547, "step": 8340 }, { "epoch": 2.01, "learning_rate": 9.985969443831571e-05, "loss": 0.6702, "step": 8350 }, { "epoch": 2.01, "learning_rate": 9.985935833358621e-05, "loss": 0.6794, "step": 8360 }, { "epoch": 2.01, "learning_rate": 9.985902182733242e-05, "loss": 0.7236, "step": 8370 }, { "epoch": 2.01, "learning_rate": 9.985868491955703e-05, "loss": 0.6951, "step": 8380 }, { "epoch": 2.01, "learning_rate": 9.985834761026278e-05, "loss": 0.6908, "step": 8390 }, { "epoch": 2.02, "learning_rate": 9.985800989945237e-05, "loss": 0.6475, "step": 8400 }, { "epoch": 2.02, "learning_rate": 9.985767178712853e-05, "loss": 0.6927, "step": 8410 }, { "epoch": 2.02, "learning_rate": 9.985733327329396e-05, "loss": 0.6629, "step": 8420 }, { "epoch": 2.02, "learning_rate": 9.985699435795141e-05, "loss": 0.644, "step": 8430 }, { "epoch": 2.03, "learning_rate": 9.98566550411036e-05, "loss": 0.6767, "step": 8440 }, { "epoch": 2.03, "learning_rate": 9.985631532275326e-05, "loss": 0.6598, "step": 8450 }, { "epoch": 2.03, "learning_rate": 9.985597520290313e-05, "loss": 0.6815, "step": 8460 }, { "epoch": 2.03, "learning_rate": 9.985563468155595e-05, "loss": 0.6722, "step": 8470 }, { "epoch": 2.04, "learning_rate": 9.985529375871447e-05, "loss": 0.7015, "step": 8480 }, { "epoch": 2.04, "learning_rate": 9.985495243438143e-05, "loss": 0.6916, "step": 8490 }, { "epoch": 2.04, "learning_rate": 9.985461070855955e-05, "loss": 0.6744, "step": 8500 }, { "epoch": 2.04, "learning_rate": 9.985426858125162e-05, "loss": 0.7029, "step": 8510 }, { "epoch": 2.04, "learning_rate": 9.985392605246039e-05, "loss": 0.69, "step": 8520 }, { "epoch": 2.05, "learning_rate": 9.98535831221886e-05, "loss": 0.6997, "step": 8530 }, { "epoch": 2.05, "learning_rate": 9.985323979043903e-05, "loss": 0.7169, "step": 8540 }, { "epoch": 2.05, "learning_rate": 9.985289605721444e-05, "loss": 0.6894, "step": 8550 }, { "epoch": 2.05, "learning_rate": 9.98525519225176e-05, "loss": 0.7218, "step": 8560 }, { "epoch": 2.06, "learning_rate": 9.985220738635126e-05, "loss": 0.7292, "step": 8570 }, { "epoch": 2.06, "learning_rate": 9.98518624487182e-05, "loss": 0.6915, "step": 8580 }, { "epoch": 2.06, "learning_rate": 9.985151710962124e-05, "loss": 0.7209, "step": 8590 }, { "epoch": 2.06, "learning_rate": 9.985117136906311e-05, "loss": 0.7397, "step": 8600 }, { "epoch": 2.06, "learning_rate": 9.985082522704662e-05, "loss": 0.6868, "step": 8610 }, { "epoch": 2.07, "learning_rate": 9.985047868357455e-05, "loss": 0.7087, "step": 8620 }, { "epoch": 2.07, "learning_rate": 9.985013173864971e-05, "loss": 0.6659, "step": 8630 }, { "epoch": 2.07, "learning_rate": 9.984978439227486e-05, "loss": 0.6885, "step": 8640 }, { "epoch": 2.07, "learning_rate": 9.984943664445283e-05, "loss": 0.7233, "step": 8650 }, { "epoch": 2.08, "learning_rate": 9.984908849518638e-05, "loss": 0.6936, "step": 8660 }, { "epoch": 2.08, "learning_rate": 9.984873994447835e-05, "loss": 0.6598, "step": 8670 }, { "epoch": 2.08, "learning_rate": 9.984839099233154e-05, "loss": 0.6742, "step": 8680 }, { "epoch": 2.08, "learning_rate": 9.984804163874875e-05, "loss": 0.673, "step": 8690 }, { "epoch": 2.09, "learning_rate": 9.98476918837328e-05, "loss": 0.7021, "step": 8700 }, { "epoch": 2.09, "learning_rate": 9.984734172728652e-05, "loss": 0.6405, "step": 8710 }, { "epoch": 2.09, "learning_rate": 9.984699116941269e-05, "loss": 0.6777, "step": 8720 }, { "epoch": 2.09, "learning_rate": 9.984664021011416e-05, "loss": 0.6872, "step": 8730 }, { "epoch": 2.09, "learning_rate": 9.984628884939378e-05, "loss": 0.719, "step": 8740 }, { "epoch": 2.1, "learning_rate": 9.984593708725433e-05, "loss": 0.6946, "step": 8750 }, { "epoch": 2.1, "learning_rate": 9.984558492369866e-05, "loss": 0.692, "step": 8760 }, { "epoch": 2.1, "learning_rate": 9.984523235872965e-05, "loss": 0.6662, "step": 8770 }, { "epoch": 2.1, "learning_rate": 9.984487939235008e-05, "loss": 0.7028, "step": 8780 }, { "epoch": 2.11, "learning_rate": 9.98445260245628e-05, "loss": 0.6815, "step": 8790 }, { "epoch": 2.11, "learning_rate": 9.98441722553707e-05, "loss": 0.7043, "step": 8800 }, { "epoch": 2.11, "learning_rate": 9.984381808477657e-05, "loss": 0.7003, "step": 8810 }, { "epoch": 2.11, "learning_rate": 9.98434635127833e-05, "loss": 0.7059, "step": 8820 }, { "epoch": 2.12, "learning_rate": 9.984310853939375e-05, "loss": 0.6706, "step": 8830 }, { "epoch": 2.12, "learning_rate": 9.984275316461075e-05, "loss": 0.6704, "step": 8840 }, { "epoch": 2.12, "learning_rate": 9.98423973884372e-05, "loss": 0.6871, "step": 8850 }, { "epoch": 2.12, "learning_rate": 9.984204121087592e-05, "loss": 0.6517, "step": 8860 }, { "epoch": 2.12, "learning_rate": 9.984168463192982e-05, "loss": 0.6796, "step": 8870 }, { "epoch": 2.13, "learning_rate": 9.984132765160174e-05, "loss": 0.6911, "step": 8880 }, { "epoch": 2.13, "learning_rate": 9.984097026989457e-05, "loss": 0.6612, "step": 8890 }, { "epoch": 2.13, "learning_rate": 9.98406124868112e-05, "loss": 0.7146, "step": 8900 }, { "epoch": 2.13, "learning_rate": 9.984025430235446e-05, "loss": 0.671, "step": 8910 }, { "epoch": 2.14, "learning_rate": 9.98398957165273e-05, "loss": 0.6499, "step": 8920 }, { "epoch": 2.14, "learning_rate": 9.983953672933257e-05, "loss": 0.6951, "step": 8930 }, { "epoch": 2.14, "learning_rate": 9.983917734077319e-05, "loss": 0.7237, "step": 8940 }, { "epoch": 2.14, "learning_rate": 9.983881755085201e-05, "loss": 0.688, "step": 8950 }, { "epoch": 2.14, "learning_rate": 9.983845735957196e-05, "loss": 0.6529, "step": 8960 }, { "epoch": 2.15, "learning_rate": 9.983809676693592e-05, "loss": 0.6553, "step": 8970 }, { "epoch": 2.15, "learning_rate": 9.983773577294681e-05, "loss": 0.6381, "step": 8980 }, { "epoch": 2.15, "learning_rate": 9.983737437760756e-05, "loss": 0.6689, "step": 8990 }, { "epoch": 2.15, "learning_rate": 9.983701258092102e-05, "loss": 0.6863, "step": 9000 }, { "epoch": 2.16, "learning_rate": 9.983665038289016e-05, "loss": 0.6671, "step": 9010 }, { "epoch": 2.16, "learning_rate": 9.983628778351785e-05, "loss": 0.6749, "step": 9020 }, { "epoch": 2.16, "learning_rate": 9.983592478280705e-05, "loss": 0.6807, "step": 9030 }, { "epoch": 2.16, "learning_rate": 9.983556138076068e-05, "loss": 0.6992, "step": 9040 }, { "epoch": 2.17, "learning_rate": 9.983519757738164e-05, "loss": 0.6386, "step": 9050 }, { "epoch": 2.17, "learning_rate": 9.983483337267288e-05, "loss": 0.6916, "step": 9060 }, { "epoch": 2.17, "learning_rate": 9.983446876663732e-05, "loss": 0.714, "step": 9070 }, { "epoch": 2.17, "learning_rate": 9.98341037592779e-05, "loss": 0.6388, "step": 9080 }, { "epoch": 2.17, "learning_rate": 9.983373835059756e-05, "loss": 0.7334, "step": 9090 }, { "epoch": 2.18, "learning_rate": 9.983337254059926e-05, "loss": 0.6959, "step": 9100 }, { "epoch": 2.18, "learning_rate": 9.983300632928592e-05, "loss": 0.6444, "step": 9110 }, { "epoch": 2.18, "learning_rate": 9.98326397166605e-05, "loss": 0.7171, "step": 9120 }, { "epoch": 2.18, "learning_rate": 9.983227270272595e-05, "loss": 0.6842, "step": 9130 }, { "epoch": 2.19, "learning_rate": 9.983190528748523e-05, "loss": 0.6662, "step": 9140 }, { "epoch": 2.19, "learning_rate": 9.983153747094132e-05, "loss": 0.6504, "step": 9150 }, { "epoch": 2.19, "learning_rate": 9.983116925309712e-05, "loss": 0.6537, "step": 9160 }, { "epoch": 2.19, "learning_rate": 9.983080063395567e-05, "loss": 0.6611, "step": 9170 }, { "epoch": 2.2, "learning_rate": 9.983043161351988e-05, "loss": 0.6909, "step": 9180 }, { "epoch": 2.2, "learning_rate": 9.983006219179276e-05, "loss": 0.6832, "step": 9190 }, { "epoch": 2.2, "learning_rate": 9.982969236877726e-05, "loss": 0.7001, "step": 9200 }, { "epoch": 2.2, "learning_rate": 9.982932214447636e-05, "loss": 0.7196, "step": 9210 }, { "epoch": 2.2, "learning_rate": 9.982895151889306e-05, "loss": 0.646, "step": 9220 }, { "epoch": 2.21, "learning_rate": 9.982858049203033e-05, "loss": 0.6707, "step": 9230 }, { "epoch": 2.21, "learning_rate": 9.982820906389117e-05, "loss": 0.6778, "step": 9240 }, { "epoch": 2.21, "learning_rate": 9.982783723447856e-05, "loss": 0.6907, "step": 9250 }, { "epoch": 2.21, "learning_rate": 9.98274650037955e-05, "loss": 0.6828, "step": 9260 }, { "epoch": 2.22, "learning_rate": 9.982709237184496e-05, "loss": 0.6993, "step": 9270 }, { "epoch": 2.22, "learning_rate": 9.982671933862999e-05, "loss": 0.649, "step": 9280 }, { "epoch": 2.22, "learning_rate": 9.982634590415358e-05, "loss": 0.6531, "step": 9290 }, { "epoch": 2.22, "learning_rate": 9.98259720684187e-05, "loss": 0.6504, "step": 9300 }, { "epoch": 2.22, "learning_rate": 9.98255978314284e-05, "loss": 0.676, "step": 9310 }, { "epoch": 2.23, "learning_rate": 9.98252231931857e-05, "loss": 0.7138, "step": 9320 }, { "epoch": 2.23, "learning_rate": 9.982484815369357e-05, "loss": 0.7155, "step": 9330 }, { "epoch": 2.23, "learning_rate": 9.982447271295508e-05, "loss": 0.6688, "step": 9340 }, { "epoch": 2.23, "learning_rate": 9.982409687097322e-05, "loss": 0.6459, "step": 9350 }, { "epoch": 2.24, "learning_rate": 9.982372062775104e-05, "loss": 0.6807, "step": 9360 }, { "epoch": 2.24, "learning_rate": 9.982334398329155e-05, "loss": 0.6852, "step": 9370 }, { "epoch": 2.24, "learning_rate": 9.98229669375978e-05, "loss": 0.7132, "step": 9380 }, { "epoch": 2.24, "learning_rate": 9.982258949067281e-05, "loss": 0.6595, "step": 9390 }, { "epoch": 2.25, "learning_rate": 9.982221164251964e-05, "loss": 0.7096, "step": 9400 }, { "epoch": 2.25, "learning_rate": 9.98218333931413e-05, "loss": 0.7009, "step": 9410 }, { "epoch": 2.25, "learning_rate": 9.982145474254088e-05, "loss": 0.659, "step": 9420 }, { "epoch": 2.25, "learning_rate": 9.982107569072138e-05, "loss": 0.67, "step": 9430 }, { "epoch": 2.25, "learning_rate": 9.98206962376859e-05, "loss": 0.6523, "step": 9440 }, { "epoch": 2.26, "learning_rate": 9.982031638343749e-05, "loss": 0.6747, "step": 9450 }, { "epoch": 2.26, "learning_rate": 9.981993612797917e-05, "loss": 0.6384, "step": 9460 }, { "epoch": 2.26, "learning_rate": 9.981955547131403e-05, "loss": 0.6516, "step": 9470 }, { "epoch": 2.26, "learning_rate": 9.981917441344514e-05, "loss": 0.6827, "step": 9480 }, { "epoch": 2.27, "learning_rate": 9.981879295437555e-05, "loss": 0.6854, "step": 9490 }, { "epoch": 2.27, "learning_rate": 9.981841109410834e-05, "loss": 0.6514, "step": 9500 }, { "epoch": 2.27, "learning_rate": 9.981802883264661e-05, "loss": 0.6703, "step": 9510 }, { "epoch": 2.27, "learning_rate": 9.981764616999339e-05, "loss": 0.6859, "step": 9520 }, { "epoch": 2.28, "learning_rate": 9.98172631061518e-05, "loss": 0.662, "step": 9530 }, { "epoch": 2.28, "learning_rate": 9.981687964112492e-05, "loss": 0.7213, "step": 9540 }, { "epoch": 2.28, "learning_rate": 9.981649577491581e-05, "loss": 0.6942, "step": 9550 }, { "epoch": 2.28, "learning_rate": 9.98161115075276e-05, "loss": 0.6134, "step": 9560 }, { "epoch": 2.28, "learning_rate": 9.981572683896336e-05, "loss": 0.6676, "step": 9570 }, { "epoch": 2.29, "learning_rate": 9.981534176922619e-05, "loss": 0.6968, "step": 9580 }, { "epoch": 2.29, "learning_rate": 9.981495629831921e-05, "loss": 0.6926, "step": 9590 }, { "epoch": 2.29, "learning_rate": 9.98145704262455e-05, "loss": 0.7014, "step": 9600 }, { "epoch": 2.29, "learning_rate": 9.981418415300817e-05, "loss": 0.6957, "step": 9610 }, { "epoch": 2.3, "learning_rate": 9.981379747861034e-05, "loss": 0.638, "step": 9620 }, { "epoch": 2.3, "learning_rate": 9.981341040305511e-05, "loss": 0.647, "step": 9630 }, { "epoch": 2.3, "learning_rate": 9.981302292634565e-05, "loss": 0.6821, "step": 9640 }, { "epoch": 2.3, "learning_rate": 9.9812635048485e-05, "loss": 0.6789, "step": 9650 }, { "epoch": 2.3, "learning_rate": 9.981224676947634e-05, "loss": 0.6701, "step": 9660 }, { "epoch": 2.31, "learning_rate": 9.981185808932278e-05, "loss": 0.7329, "step": 9670 }, { "epoch": 2.31, "learning_rate": 9.981146900802745e-05, "loss": 0.6748, "step": 9680 }, { "epoch": 2.31, "learning_rate": 9.981107952559348e-05, "loss": 0.726, "step": 9690 }, { "epoch": 2.31, "learning_rate": 9.9810689642024e-05, "loss": 0.6679, "step": 9700 }, { "epoch": 2.32, "learning_rate": 9.981029935732217e-05, "loss": 0.6669, "step": 9710 }, { "epoch": 2.32, "learning_rate": 9.980990867149111e-05, "loss": 0.6909, "step": 9720 }, { "epoch": 2.32, "learning_rate": 9.9809517584534e-05, "loss": 0.6632, "step": 9730 }, { "epoch": 2.32, "learning_rate": 9.980912609645396e-05, "loss": 0.634, "step": 9740 }, { "epoch": 2.33, "learning_rate": 9.980873420725413e-05, "loss": 0.6864, "step": 9750 }, { "epoch": 2.33, "learning_rate": 9.980834191693772e-05, "loss": 0.6945, "step": 9760 }, { "epoch": 2.33, "learning_rate": 9.980794922550785e-05, "loss": 0.6707, "step": 9770 }, { "epoch": 2.33, "learning_rate": 9.980755613296767e-05, "loss": 0.6925, "step": 9780 }, { "epoch": 2.33, "learning_rate": 9.980716263932038e-05, "loss": 0.6526, "step": 9790 }, { "epoch": 2.34, "learning_rate": 9.980676874456913e-05, "loss": 0.6922, "step": 9800 }, { "epoch": 2.34, "learning_rate": 9.980637444871708e-05, "loss": 0.6676, "step": 9810 }, { "epoch": 2.34, "learning_rate": 9.980597975176744e-05, "loss": 0.6783, "step": 9820 }, { "epoch": 2.34, "learning_rate": 9.980558465372337e-05, "loss": 0.6531, "step": 9830 }, { "epoch": 2.35, "learning_rate": 9.980518915458803e-05, "loss": 0.6916, "step": 9840 }, { "epoch": 2.35, "learning_rate": 9.980479325436464e-05, "loss": 0.7337, "step": 9850 }, { "epoch": 2.35, "learning_rate": 9.980439695305638e-05, "loss": 0.6708, "step": 9860 }, { "epoch": 2.35, "learning_rate": 9.980400025066643e-05, "loss": 0.6371, "step": 9870 }, { "epoch": 2.36, "learning_rate": 9.980360314719799e-05, "loss": 0.6656, "step": 9880 }, { "epoch": 2.36, "learning_rate": 9.980320564265424e-05, "loss": 0.6382, "step": 9890 }, { "epoch": 2.36, "learning_rate": 9.980280773703843e-05, "loss": 0.6647, "step": 9900 }, { "epoch": 2.36, "learning_rate": 9.98024094303537e-05, "loss": 0.6723, "step": 9910 }, { "epoch": 2.36, "learning_rate": 9.980201072260332e-05, "loss": 0.695, "step": 9920 }, { "epoch": 2.37, "learning_rate": 9.980161161379047e-05, "loss": 0.6539, "step": 9930 }, { "epoch": 2.37, "learning_rate": 9.980121210391835e-05, "loss": 0.6675, "step": 9940 }, { "epoch": 2.37, "learning_rate": 9.98008121929902e-05, "loss": 0.6907, "step": 9950 }, { "epoch": 2.37, "learning_rate": 9.980041188100924e-05, "loss": 0.6749, "step": 9960 }, { "epoch": 2.38, "learning_rate": 9.980001116797868e-05, "loss": 0.6938, "step": 9970 }, { "epoch": 2.38, "learning_rate": 9.979961005390176e-05, "loss": 0.7062, "step": 9980 }, { "epoch": 2.38, "learning_rate": 9.979920853878171e-05, "loss": 0.6803, "step": 9990 }, { "epoch": 2.38, "learning_rate": 9.979880662262175e-05, "loss": 0.6896, "step": 10000 }, { "epoch": 2.38, "learning_rate": 9.979840430542511e-05, "loss": 0.7021, "step": 10010 }, { "epoch": 2.39, "learning_rate": 9.979800158719508e-05, "loss": 0.6893, "step": 10020 }, { "epoch": 2.39, "learning_rate": 9.979759846793484e-05, "loss": 0.6378, "step": 10030 }, { "epoch": 2.39, "learning_rate": 9.979719494764767e-05, "loss": 0.6384, "step": 10040 }, { "epoch": 2.39, "learning_rate": 9.979679102633682e-05, "loss": 0.6631, "step": 10050 }, { "epoch": 2.4, "learning_rate": 9.979638670400555e-05, "loss": 0.6744, "step": 10060 }, { "epoch": 2.4, "learning_rate": 9.979598198065707e-05, "loss": 0.645, "step": 10070 }, { "epoch": 2.4, "learning_rate": 9.979557685629471e-05, "loss": 0.6318, "step": 10080 }, { "epoch": 2.4, "learning_rate": 9.979517133092166e-05, "loss": 0.6679, "step": 10090 }, { "epoch": 2.41, "learning_rate": 9.979476540454125e-05, "loss": 0.7014, "step": 10100 }, { "epoch": 2.41, "learning_rate": 9.97943590771567e-05, "loss": 0.6715, "step": 10110 }, { "epoch": 2.41, "learning_rate": 9.979395234877131e-05, "loss": 0.6538, "step": 10120 }, { "epoch": 2.41, "learning_rate": 9.979354521938833e-05, "loss": 0.7331, "step": 10130 }, { "epoch": 2.41, "learning_rate": 9.979313768901108e-05, "loss": 0.7549, "step": 10140 }, { "epoch": 2.42, "learning_rate": 9.97927297576428e-05, "loss": 0.6971, "step": 10150 }, { "epoch": 2.42, "learning_rate": 9.97923214252868e-05, "loss": 0.6612, "step": 10160 }, { "epoch": 2.42, "learning_rate": 9.979191269194636e-05, "loss": 0.6692, "step": 10170 }, { "epoch": 2.42, "learning_rate": 9.979150355762479e-05, "loss": 0.6537, "step": 10180 }, { "epoch": 2.43, "learning_rate": 9.979109402232535e-05, "loss": 0.7032, "step": 10190 }, { "epoch": 2.43, "learning_rate": 9.979068408605136e-05, "loss": 0.661, "step": 10200 }, { "epoch": 2.43, "learning_rate": 9.979027374880611e-05, "loss": 0.6831, "step": 10210 }, { "epoch": 2.43, "learning_rate": 9.978986301059292e-05, "loss": 0.6827, "step": 10220 }, { "epoch": 2.44, "learning_rate": 9.978945187141509e-05, "loss": 0.6685, "step": 10230 }, { "epoch": 2.44, "learning_rate": 9.978904033127593e-05, "loss": 0.6825, "step": 10240 }, { "epoch": 2.44, "learning_rate": 9.978862839017875e-05, "loss": 0.6156, "step": 10250 }, { "epoch": 2.44, "learning_rate": 9.978821604812687e-05, "loss": 0.6675, "step": 10260 }, { "epoch": 2.44, "learning_rate": 9.978780330512362e-05, "loss": 0.6881, "step": 10270 }, { "epoch": 2.45, "learning_rate": 9.978739016117232e-05, "loss": 0.6979, "step": 10280 }, { "epoch": 2.45, "learning_rate": 9.978697661627628e-05, "loss": 0.6496, "step": 10290 }, { "epoch": 2.45, "learning_rate": 9.978656267043884e-05, "loss": 0.6626, "step": 10300 }, { "epoch": 2.45, "learning_rate": 9.978614832366335e-05, "loss": 0.6401, "step": 10310 }, { "epoch": 2.46, "learning_rate": 9.978573357595314e-05, "loss": 0.7221, "step": 10320 }, { "epoch": 2.46, "learning_rate": 9.978531842731153e-05, "loss": 0.6713, "step": 10330 }, { "epoch": 2.46, "learning_rate": 9.978490287774188e-05, "loss": 0.6562, "step": 10340 }, { "epoch": 2.46, "learning_rate": 9.978448692724754e-05, "loss": 0.6715, "step": 10350 }, { "epoch": 2.46, "learning_rate": 9.978407057583186e-05, "loss": 0.6596, "step": 10360 }, { "epoch": 2.47, "learning_rate": 9.978365382349817e-05, "loss": 0.6658, "step": 10370 }, { "epoch": 2.47, "learning_rate": 9.978323667024985e-05, "loss": 0.6769, "step": 10380 }, { "epoch": 2.47, "learning_rate": 9.978281911609024e-05, "loss": 0.7263, "step": 10390 }, { "epoch": 2.47, "learning_rate": 9.978240116102274e-05, "loss": 0.6787, "step": 10400 }, { "epoch": 2.48, "learning_rate": 9.978198280505067e-05, "loss": 0.6672, "step": 10410 }, { "epoch": 2.48, "learning_rate": 9.978156404817743e-05, "loss": 0.6757, "step": 10420 }, { "epoch": 2.48, "learning_rate": 9.978114489040638e-05, "loss": 0.6533, "step": 10430 }, { "epoch": 2.48, "learning_rate": 9.978072533174089e-05, "loss": 0.6552, "step": 10440 }, { "epoch": 2.49, "learning_rate": 9.978030537218435e-05, "loss": 0.7155, "step": 10450 }, { "epoch": 2.49, "learning_rate": 9.977988501174014e-05, "loss": 0.6719, "step": 10460 }, { "epoch": 2.49, "learning_rate": 9.977946425041164e-05, "loss": 0.673, "step": 10470 }, { "epoch": 2.49, "learning_rate": 9.977904308820224e-05, "loss": 0.6772, "step": 10480 }, { "epoch": 2.49, "learning_rate": 9.977862152511534e-05, "loss": 0.6764, "step": 10490 }, { "epoch": 2.5, "learning_rate": 9.977819956115434e-05, "loss": 0.6713, "step": 10500 }, { "epoch": 2.5, "learning_rate": 9.977777719632262e-05, "loss": 0.6557, "step": 10510 }, { "epoch": 2.5, "learning_rate": 9.977735443062357e-05, "loss": 0.6746, "step": 10520 }, { "epoch": 2.5, "learning_rate": 9.977693126406062e-05, "loss": 0.6676, "step": 10530 }, { "epoch": 2.51, "learning_rate": 9.977650769663717e-05, "loss": 0.6675, "step": 10540 }, { "epoch": 2.51, "learning_rate": 9.977608372835665e-05, "loss": 0.6461, "step": 10550 }, { "epoch": 2.51, "learning_rate": 9.977565935922244e-05, "loss": 0.6381, "step": 10560 }, { "epoch": 2.51, "learning_rate": 9.977523458923798e-05, "loss": 0.6689, "step": 10570 }, { "epoch": 2.52, "learning_rate": 9.977480941840667e-05, "loss": 0.6638, "step": 10580 }, { "epoch": 2.52, "learning_rate": 9.977438384673197e-05, "loss": 0.6663, "step": 10590 }, { "epoch": 2.52, "learning_rate": 9.977395787421728e-05, "loss": 0.6587, "step": 10600 }, { "epoch": 2.52, "learning_rate": 9.977353150086602e-05, "loss": 0.6731, "step": 10610 }, { "epoch": 2.52, "learning_rate": 9.977310472668164e-05, "loss": 0.6614, "step": 10620 }, { "epoch": 2.53, "learning_rate": 9.97726775516676e-05, "loss": 0.6389, "step": 10630 }, { "epoch": 2.53, "learning_rate": 9.977224997582728e-05, "loss": 0.6872, "step": 10640 }, { "epoch": 2.53, "learning_rate": 9.977182199916419e-05, "loss": 0.7204, "step": 10650 }, { "epoch": 2.53, "learning_rate": 9.977139362168173e-05, "loss": 0.6609, "step": 10660 }, { "epoch": 2.54, "learning_rate": 9.977096484338337e-05, "loss": 0.7147, "step": 10670 }, { "epoch": 2.54, "learning_rate": 9.977053566427257e-05, "loss": 0.668, "step": 10680 }, { "epoch": 2.54, "learning_rate": 9.977010608435276e-05, "loss": 0.6878, "step": 10690 }, { "epoch": 2.54, "learning_rate": 9.976967610362742e-05, "loss": 0.6805, "step": 10700 }, { "epoch": 2.54, "learning_rate": 9.97692457221e-05, "loss": 0.6646, "step": 10710 }, { "epoch": 2.55, "learning_rate": 9.976881493977399e-05, "loss": 0.6796, "step": 10720 }, { "epoch": 2.55, "learning_rate": 9.976838375665282e-05, "loss": 0.7003, "step": 10730 }, { "epoch": 2.55, "learning_rate": 9.976795217274e-05, "loss": 0.6729, "step": 10740 }, { "epoch": 2.55, "learning_rate": 9.976752018803899e-05, "loss": 0.7184, "step": 10750 }, { "epoch": 2.56, "learning_rate": 9.976708780255326e-05, "loss": 0.6812, "step": 10760 }, { "epoch": 2.56, "learning_rate": 9.976665501628631e-05, "loss": 0.691, "step": 10770 }, { "epoch": 2.56, "learning_rate": 9.976622182924161e-05, "loss": 0.6945, "step": 10780 }, { "epoch": 2.56, "learning_rate": 9.976578824142266e-05, "loss": 0.6899, "step": 10790 }, { "epoch": 2.57, "learning_rate": 9.976535425283295e-05, "loss": 0.7024, "step": 10800 }, { "epoch": 2.57, "learning_rate": 9.976491986347596e-05, "loss": 0.6798, "step": 10810 }, { "epoch": 2.57, "learning_rate": 9.976448507335521e-05, "loss": 0.7222, "step": 10820 }, { "epoch": 2.57, "learning_rate": 9.976404988247418e-05, "loss": 0.7107, "step": 10830 }, { "epoch": 2.57, "learning_rate": 9.97636142908364e-05, "loss": 0.671, "step": 10840 }, { "epoch": 2.58, "learning_rate": 9.976317829844536e-05, "loss": 0.6891, "step": 10850 }, { "epoch": 2.58, "learning_rate": 9.976274190530456e-05, "loss": 0.6606, "step": 10860 }, { "epoch": 2.58, "learning_rate": 9.976230511141755e-05, "loss": 0.6764, "step": 10870 }, { "epoch": 2.58, "learning_rate": 9.976186791678782e-05, "loss": 0.7144, "step": 10880 }, { "epoch": 2.59, "learning_rate": 9.97614303214189e-05, "loss": 0.6626, "step": 10890 }, { "epoch": 2.59, "learning_rate": 9.976099232531431e-05, "loss": 0.6246, "step": 10900 }, { "epoch": 2.59, "learning_rate": 9.976055392847757e-05, "loss": 0.6787, "step": 10910 }, { "epoch": 2.59, "learning_rate": 9.976011513091223e-05, "loss": 0.7266, "step": 10920 }, { "epoch": 2.6, "learning_rate": 9.975967593262181e-05, "loss": 0.6576, "step": 10930 }, { "epoch": 2.6, "learning_rate": 9.975923633360985e-05, "loss": 0.6549, "step": 10940 }, { "epoch": 2.6, "learning_rate": 9.975879633387989e-05, "loss": 0.7007, "step": 10950 }, { "epoch": 2.6, "learning_rate": 9.975835593343548e-05, "loss": 0.6719, "step": 10960 }, { "epoch": 2.6, "learning_rate": 9.975791513228015e-05, "loss": 0.6339, "step": 10970 }, { "epoch": 2.61, "learning_rate": 9.975747393041745e-05, "loss": 0.6605, "step": 10980 }, { "epoch": 2.61, "learning_rate": 9.975703232785097e-05, "loss": 0.6522, "step": 10990 }, { "epoch": 2.61, "learning_rate": 9.975659032458422e-05, "loss": 0.7271, "step": 11000 }, { "epoch": 2.61, "learning_rate": 9.975614792062078e-05, "loss": 0.7039, "step": 11010 }, { "epoch": 2.62, "learning_rate": 9.975570511596422e-05, "loss": 0.71, "step": 11020 }, { "epoch": 2.62, "learning_rate": 9.97552619106181e-05, "loss": 0.6452, "step": 11030 }, { "epoch": 2.62, "learning_rate": 9.975481830458598e-05, "loss": 0.671, "step": 11040 }, { "epoch": 2.62, "learning_rate": 9.975437429787142e-05, "loss": 0.6589, "step": 11050 }, { "epoch": 2.62, "learning_rate": 9.975392989047805e-05, "loss": 0.6525, "step": 11060 }, { "epoch": 2.63, "learning_rate": 9.975348508240939e-05, "loss": 0.6926, "step": 11070 }, { "epoch": 2.63, "learning_rate": 9.975303987366906e-05, "loss": 0.6962, "step": 11080 }, { "epoch": 2.63, "learning_rate": 9.97525942642606e-05, "loss": 0.6725, "step": 11090 }, { "epoch": 2.63, "learning_rate": 9.975214825418766e-05, "loss": 0.7, "step": 11100 }, { "epoch": 2.64, "learning_rate": 9.97517018434538e-05, "loss": 0.6669, "step": 11110 }, { "epoch": 2.64, "learning_rate": 9.975125503206262e-05, "loss": 0.6875, "step": 11120 }, { "epoch": 2.64, "learning_rate": 9.97508078200177e-05, "loss": 0.6854, "step": 11130 }, { "epoch": 2.64, "learning_rate": 9.975036020732267e-05, "loss": 0.6615, "step": 11140 }, { "epoch": 2.65, "learning_rate": 9.974991219398111e-05, "loss": 0.6738, "step": 11150 }, { "epoch": 2.65, "learning_rate": 9.974946377999664e-05, "loss": 0.6495, "step": 11160 }, { "epoch": 2.65, "learning_rate": 9.974901496537286e-05, "loss": 0.6963, "step": 11170 }, { "epoch": 2.65, "learning_rate": 9.974856575011342e-05, "loss": 0.6871, "step": 11180 }, { "epoch": 2.65, "learning_rate": 9.974811613422189e-05, "loss": 0.6636, "step": 11190 }, { "epoch": 2.66, "learning_rate": 9.974766611770192e-05, "loss": 0.6624, "step": 11200 }, { "epoch": 2.66, "learning_rate": 9.974721570055713e-05, "loss": 0.6477, "step": 11210 }, { "epoch": 2.66, "learning_rate": 9.974676488279113e-05, "loss": 0.6479, "step": 11220 }, { "epoch": 2.66, "learning_rate": 9.974631366440759e-05, "loss": 0.6792, "step": 11230 }, { "epoch": 2.67, "learning_rate": 9.97458620454101e-05, "loss": 0.6781, "step": 11240 }, { "epoch": 2.67, "learning_rate": 9.974541002580231e-05, "loss": 0.6571, "step": 11250 }, { "epoch": 2.67, "learning_rate": 9.974495760558788e-05, "loss": 0.6533, "step": 11260 }, { "epoch": 2.67, "learning_rate": 9.974450478477043e-05, "loss": 0.6846, "step": 11270 }, { "epoch": 2.68, "learning_rate": 9.974405156335363e-05, "loss": 0.6938, "step": 11280 }, { "epoch": 2.68, "learning_rate": 9.974359794134109e-05, "loss": 0.6645, "step": 11290 }, { "epoch": 2.68, "learning_rate": 9.97431439187365e-05, "loss": 0.6957, "step": 11300 }, { "epoch": 2.68, "learning_rate": 9.97426894955435e-05, "loss": 0.6893, "step": 11310 }, { "epoch": 2.68, "learning_rate": 9.974223467176577e-05, "loss": 0.6954, "step": 11320 }, { "epoch": 2.69, "learning_rate": 9.974177944740695e-05, "loss": 0.7145, "step": 11330 }, { "epoch": 2.69, "learning_rate": 9.97413238224707e-05, "loss": 0.6807, "step": 11340 }, { "epoch": 2.69, "learning_rate": 9.974086779696072e-05, "loss": 0.6647, "step": 11350 }, { "epoch": 2.69, "learning_rate": 9.974041137088066e-05, "loss": 0.6495, "step": 11360 }, { "epoch": 2.7, "learning_rate": 9.97399545442342e-05, "loss": 0.6868, "step": 11370 }, { "epoch": 2.7, "learning_rate": 9.9739497317025e-05, "loss": 0.6485, "step": 11380 }, { "epoch": 2.7, "learning_rate": 9.973903968925678e-05, "loss": 0.6261, "step": 11390 }, { "epoch": 2.7, "learning_rate": 9.973858166093319e-05, "loss": 0.6998, "step": 11400 }, { "epoch": 2.7, "learning_rate": 9.973812323205795e-05, "loss": 0.6781, "step": 11410 }, { "epoch": 2.71, "learning_rate": 9.973766440263474e-05, "loss": 0.6792, "step": 11420 }, { "epoch": 2.71, "learning_rate": 9.973720517266725e-05, "loss": 0.6702, "step": 11430 }, { "epoch": 2.71, "learning_rate": 9.973674554215917e-05, "loss": 0.6606, "step": 11440 }, { "epoch": 2.71, "learning_rate": 9.973628551111423e-05, "loss": 0.6572, "step": 11450 }, { "epoch": 2.72, "learning_rate": 9.97358250795361e-05, "loss": 0.6868, "step": 11460 }, { "epoch": 2.72, "learning_rate": 9.97353642474285e-05, "loss": 0.6755, "step": 11470 }, { "epoch": 2.72, "learning_rate": 9.973490301479516e-05, "loss": 0.6628, "step": 11480 }, { "epoch": 2.72, "learning_rate": 9.973444138163976e-05, "loss": 0.6835, "step": 11490 }, { "epoch": 2.73, "learning_rate": 9.973397934796606e-05, "loss": 0.704, "step": 11500 }, { "epoch": 2.73, "learning_rate": 9.973351691377775e-05, "loss": 0.6829, "step": 11510 }, { "epoch": 2.73, "learning_rate": 9.973305407907855e-05, "loss": 0.677, "step": 11520 }, { "epoch": 2.73, "learning_rate": 9.973259084387223e-05, "loss": 0.6328, "step": 11530 }, { "epoch": 2.73, "learning_rate": 9.973212720816246e-05, "loss": 0.6494, "step": 11540 }, { "epoch": 2.74, "learning_rate": 9.973166317195302e-05, "loss": 0.6847, "step": 11550 }, { "epoch": 2.74, "learning_rate": 9.973119873524762e-05, "loss": 0.6465, "step": 11560 }, { "epoch": 2.74, "learning_rate": 9.973073389805e-05, "loss": 0.6613, "step": 11570 }, { "epoch": 2.74, "learning_rate": 9.973026866036394e-05, "loss": 0.6541, "step": 11580 }, { "epoch": 2.75, "learning_rate": 9.972980302219315e-05, "loss": 0.6759, "step": 11590 }, { "epoch": 2.75, "learning_rate": 9.972933698354139e-05, "loss": 0.6388, "step": 11600 }, { "epoch": 2.75, "learning_rate": 9.972887054441243e-05, "loss": 0.6478, "step": 11610 }, { "epoch": 2.75, "learning_rate": 9.972840370480998e-05, "loss": 0.6501, "step": 11620 }, { "epoch": 2.76, "learning_rate": 9.972793646473786e-05, "loss": 0.696, "step": 11630 }, { "epoch": 2.76, "learning_rate": 9.972746882419977e-05, "loss": 0.6739, "step": 11640 }, { "epoch": 2.76, "learning_rate": 9.972700078319953e-05, "loss": 0.6939, "step": 11650 }, { "epoch": 2.76, "learning_rate": 9.972653234174088e-05, "loss": 0.6241, "step": 11660 }, { "epoch": 2.76, "learning_rate": 9.97260634998276e-05, "loss": 0.702, "step": 11670 }, { "epoch": 2.77, "learning_rate": 9.972559425746347e-05, "loss": 0.691, "step": 11680 }, { "epoch": 2.77, "learning_rate": 9.972512461465227e-05, "loss": 0.6603, "step": 11690 }, { "epoch": 2.77, "learning_rate": 9.972465457139777e-05, "loss": 0.6648, "step": 11700 }, { "epoch": 2.77, "learning_rate": 9.972418412770376e-05, "loss": 0.6282, "step": 11710 }, { "epoch": 2.78, "learning_rate": 9.972371328357403e-05, "loss": 0.6529, "step": 11720 }, { "epoch": 2.78, "learning_rate": 9.972324203901237e-05, "loss": 0.6586, "step": 11730 }, { "epoch": 2.78, "learning_rate": 9.972277039402257e-05, "loss": 0.6871, "step": 11740 }, { "epoch": 2.78, "learning_rate": 9.972229834860845e-05, "loss": 0.6793, "step": 11750 }, { "epoch": 2.78, "learning_rate": 9.972182590277379e-05, "loss": 0.6611, "step": 11760 }, { "epoch": 2.79, "learning_rate": 9.972135305652242e-05, "loss": 0.6079, "step": 11770 }, { "epoch": 2.79, "learning_rate": 9.97208798098581e-05, "loss": 0.655, "step": 11780 }, { "epoch": 2.79, "learning_rate": 9.972040616278468e-05, "loss": 0.6181, "step": 11790 }, { "epoch": 2.79, "learning_rate": 9.971993211530597e-05, "loss": 0.6592, "step": 11800 }, { "epoch": 2.8, "learning_rate": 9.971945766742579e-05, "loss": 0.6198, "step": 11810 }, { "epoch": 2.8, "learning_rate": 9.971898281914793e-05, "loss": 0.6436, "step": 11820 }, { "epoch": 2.8, "learning_rate": 9.971850757047626e-05, "loss": 0.6705, "step": 11830 }, { "epoch": 2.8, "learning_rate": 9.971803192141458e-05, "loss": 0.6424, "step": 11840 }, { "epoch": 2.81, "learning_rate": 9.971755587196672e-05, "loss": 0.6642, "step": 11850 }, { "epoch": 2.81, "learning_rate": 9.971707942213652e-05, "loss": 0.6393, "step": 11860 }, { "epoch": 2.81, "learning_rate": 9.971660257192781e-05, "loss": 0.6207, "step": 11870 }, { "epoch": 2.81, "learning_rate": 9.971612532134444e-05, "loss": 0.6418, "step": 11880 }, { "epoch": 2.81, "learning_rate": 9.971564767039025e-05, "loss": 0.6424, "step": 11890 }, { "epoch": 2.82, "learning_rate": 9.971516961906908e-05, "loss": 0.6811, "step": 11900 }, { "epoch": 2.82, "learning_rate": 9.971469116738479e-05, "loss": 0.7022, "step": 11910 }, { "epoch": 2.82, "learning_rate": 9.971421231534124e-05, "loss": 0.6699, "step": 11920 }, { "epoch": 2.82, "learning_rate": 9.971373306294226e-05, "loss": 0.6953, "step": 11930 }, { "epoch": 2.83, "learning_rate": 9.971325341019173e-05, "loss": 0.6576, "step": 11940 }, { "epoch": 2.83, "learning_rate": 9.97127733570935e-05, "loss": 0.6604, "step": 11950 }, { "epoch": 2.83, "learning_rate": 9.971229290365144e-05, "loss": 0.6508, "step": 11960 }, { "epoch": 2.83, "learning_rate": 9.971181204986944e-05, "loss": 0.6731, "step": 11970 }, { "epoch": 2.84, "learning_rate": 9.971133079575134e-05, "loss": 0.681, "step": 11980 }, { "epoch": 2.84, "learning_rate": 9.971084914130105e-05, "loss": 0.6509, "step": 11990 }, { "epoch": 2.84, "learning_rate": 9.97103670865224e-05, "loss": 0.6795, "step": 12000 }, { "epoch": 2.84, "learning_rate": 9.970988463141931e-05, "loss": 0.6996, "step": 12010 }, { "epoch": 2.84, "learning_rate": 9.970940177599566e-05, "loss": 0.6715, "step": 12020 }, { "epoch": 2.85, "learning_rate": 9.970891852025534e-05, "loss": 0.639, "step": 12030 }, { "epoch": 2.85, "learning_rate": 9.970843486420223e-05, "loss": 0.6796, "step": 12040 }, { "epoch": 2.85, "learning_rate": 9.970795080784023e-05, "loss": 0.6497, "step": 12050 }, { "epoch": 2.85, "learning_rate": 9.970746635117325e-05, "loss": 0.6564, "step": 12060 }, { "epoch": 2.86, "learning_rate": 9.970698149420516e-05, "loss": 0.6384, "step": 12070 }, { "epoch": 2.86, "learning_rate": 9.970649623693991e-05, "loss": 0.6318, "step": 12080 }, { "epoch": 2.86, "learning_rate": 9.970601057938138e-05, "loss": 0.6669, "step": 12090 }, { "epoch": 2.86, "learning_rate": 9.970552452153346e-05, "loss": 0.6615, "step": 12100 }, { "epoch": 2.86, "learning_rate": 9.970503806340011e-05, "loss": 0.6813, "step": 12110 }, { "epoch": 2.87, "learning_rate": 9.970455120498523e-05, "loss": 0.689, "step": 12120 }, { "epoch": 2.87, "learning_rate": 9.970406394629273e-05, "loss": 0.6922, "step": 12130 }, { "epoch": 2.87, "learning_rate": 9.970357628732654e-05, "loss": 0.6714, "step": 12140 }, { "epoch": 2.87, "learning_rate": 9.970308822809058e-05, "loss": 0.6405, "step": 12150 }, { "epoch": 2.88, "learning_rate": 9.97025997685888e-05, "loss": 0.6454, "step": 12160 }, { "epoch": 2.88, "learning_rate": 9.970211090882512e-05, "loss": 0.6694, "step": 12170 }, { "epoch": 2.88, "learning_rate": 9.970162164880348e-05, "loss": 0.6836, "step": 12180 }, { "epoch": 2.88, "learning_rate": 9.970113198852781e-05, "loss": 0.6202, "step": 12190 }, { "epoch": 2.89, "learning_rate": 9.970064192800207e-05, "loss": 0.6451, "step": 12200 }, { "epoch": 2.89, "learning_rate": 9.97001514672302e-05, "loss": 0.7164, "step": 12210 }, { "epoch": 2.89, "learning_rate": 9.969966060621614e-05, "loss": 0.6714, "step": 12220 }, { "epoch": 2.89, "learning_rate": 9.969916934496386e-05, "loss": 0.6676, "step": 12230 }, { "epoch": 2.89, "learning_rate": 9.969867768347732e-05, "loss": 0.675, "step": 12240 }, { "epoch": 2.9, "learning_rate": 9.969818562176044e-05, "loss": 0.6613, "step": 12250 }, { "epoch": 2.9, "learning_rate": 9.969769315981723e-05, "loss": 0.6449, "step": 12260 }, { "epoch": 2.9, "learning_rate": 9.969720029765162e-05, "loss": 0.6053, "step": 12270 }, { "epoch": 2.9, "learning_rate": 9.969670703526762e-05, "loss": 0.6381, "step": 12280 }, { "epoch": 2.91, "learning_rate": 9.969621337266914e-05, "loss": 0.6609, "step": 12290 }, { "epoch": 2.91, "learning_rate": 9.969571930986022e-05, "loss": 0.6657, "step": 12300 }, { "epoch": 2.91, "learning_rate": 9.969522484684481e-05, "loss": 0.6393, "step": 12310 }, { "epoch": 2.91, "learning_rate": 9.96947299836269e-05, "loss": 0.6614, "step": 12320 }, { "epoch": 2.91, "learning_rate": 9.969423472021044e-05, "loss": 0.6686, "step": 12330 }, { "epoch": 2.92, "learning_rate": 9.969373905659947e-05, "loss": 0.6458, "step": 12340 }, { "epoch": 2.92, "learning_rate": 9.969324299279796e-05, "loss": 0.6537, "step": 12350 }, { "epoch": 2.92, "learning_rate": 9.969274652880989e-05, "loss": 0.6724, "step": 12360 }, { "epoch": 2.92, "learning_rate": 9.969224966463928e-05, "loss": 0.6388, "step": 12370 }, { "epoch": 2.93, "learning_rate": 9.969175240029013e-05, "loss": 0.5823, "step": 12380 }, { "epoch": 2.93, "learning_rate": 9.969125473576642e-05, "loss": 0.6726, "step": 12390 }, { "epoch": 2.93, "learning_rate": 9.96907566710722e-05, "loss": 0.6256, "step": 12400 }, { "epoch": 2.93, "learning_rate": 9.969025820621143e-05, "loss": 0.6659, "step": 12410 }, { "epoch": 2.94, "learning_rate": 9.968975934118815e-05, "loss": 0.6509, "step": 12420 }, { "epoch": 2.94, "learning_rate": 9.968926007600641e-05, "loss": 0.6011, "step": 12430 }, { "epoch": 2.94, "learning_rate": 9.968876041067017e-05, "loss": 0.6449, "step": 12440 }, { "epoch": 2.94, "learning_rate": 9.968826034518349e-05, "loss": 0.683, "step": 12450 }, { "epoch": 2.94, "learning_rate": 9.968775987955039e-05, "loss": 0.6767, "step": 12460 }, { "epoch": 2.95, "learning_rate": 9.96872590137749e-05, "loss": 0.657, "step": 12470 }, { "epoch": 2.95, "learning_rate": 9.968675774786105e-05, "loss": 0.626, "step": 12480 }, { "epoch": 3.0, "learning_rate": 9.96862560818129e-05, "loss": 0.6644, "step": 12490 }, { "epoch": 3.0, "learning_rate": 9.968575401563445e-05, "loss": 0.6466, "step": 12500 }, { "epoch": 3.0, "learning_rate": 9.968525154932975e-05, "loss": 0.6406, "step": 12510 }, { "epoch": 3.01, "learning_rate": 9.968474868290288e-05, "loss": 0.6407, "step": 12520 }, { "epoch": 3.01, "learning_rate": 9.968424541635787e-05, "loss": 0.6415, "step": 12530 }, { "epoch": 3.01, "learning_rate": 9.968374174969877e-05, "loss": 0.6259, "step": 12540 }, { "epoch": 3.01, "learning_rate": 9.968323768292964e-05, "loss": 0.6272, "step": 12550 }, { "epoch": 3.02, "learning_rate": 9.968273321605452e-05, "loss": 0.6503, "step": 12560 }, { "epoch": 3.02, "learning_rate": 9.968222834907752e-05, "loss": 0.7009, "step": 12570 }, { "epoch": 3.02, "learning_rate": 9.968172308200265e-05, "loss": 0.6586, "step": 12580 }, { "epoch": 3.02, "learning_rate": 9.968121741483403e-05, "loss": 0.6317, "step": 12590 }, { "epoch": 3.03, "learning_rate": 9.968071134757569e-05, "loss": 0.6403, "step": 12600 }, { "epoch": 3.03, "learning_rate": 9.968020488023173e-05, "loss": 0.6379, "step": 12610 }, { "epoch": 3.03, "learning_rate": 9.967969801280621e-05, "loss": 0.6618, "step": 12620 }, { "epoch": 3.03, "learning_rate": 9.967919074530323e-05, "loss": 0.615, "step": 12630 }, { "epoch": 3.03, "learning_rate": 9.967868307772687e-05, "loss": 0.7118, "step": 12640 }, { "epoch": 3.04, "learning_rate": 9.96781750100812e-05, "loss": 0.6485, "step": 12650 }, { "epoch": 3.04, "learning_rate": 9.967766654237036e-05, "loss": 0.6438, "step": 12660 }, { "epoch": 3.04, "learning_rate": 9.96771576745984e-05, "loss": 0.6485, "step": 12670 }, { "epoch": 3.04, "learning_rate": 9.967664840676942e-05, "loss": 0.6287, "step": 12680 }, { "epoch": 3.05, "learning_rate": 9.967613873888755e-05, "loss": 0.6381, "step": 12690 }, { "epoch": 3.05, "learning_rate": 9.967562867095686e-05, "loss": 0.6299, "step": 12700 }, { "epoch": 3.05, "learning_rate": 9.967511820298147e-05, "loss": 0.6774, "step": 12710 }, { "epoch": 3.05, "learning_rate": 9.967460733496552e-05, "loss": 0.6517, "step": 12720 }, { "epoch": 3.06, "learning_rate": 9.967409606691309e-05, "loss": 0.6105, "step": 12730 }, { "epoch": 3.06, "learning_rate": 9.967358439882829e-05, "loss": 0.6612, "step": 12740 }, { "epoch": 3.06, "learning_rate": 9.967307233071526e-05, "loss": 0.5884, "step": 12750 }, { "epoch": 3.06, "learning_rate": 9.967255986257814e-05, "loss": 0.6662, "step": 12760 }, { "epoch": 3.06, "learning_rate": 9.967204699442103e-05, "loss": 0.6442, "step": 12770 }, { "epoch": 3.07, "learning_rate": 9.967153372624805e-05, "loss": 0.6675, "step": 12780 }, { "epoch": 3.07, "learning_rate": 9.967102005806337e-05, "loss": 0.622, "step": 12790 }, { "epoch": 3.07, "learning_rate": 9.967050598987111e-05, "loss": 0.6597, "step": 12800 }, { "epoch": 3.07, "learning_rate": 9.96699915216754e-05, "loss": 0.6332, "step": 12810 }, { "epoch": 3.08, "learning_rate": 9.966947665348038e-05, "loss": 0.6026, "step": 12820 }, { "epoch": 3.08, "learning_rate": 9.966896138529023e-05, "loss": 0.6331, "step": 12830 }, { "epoch": 3.08, "learning_rate": 9.966844571710906e-05, "loss": 0.6581, "step": 12840 }, { "epoch": 3.08, "learning_rate": 9.966792964894105e-05, "loss": 0.66, "step": 12850 }, { "epoch": 3.08, "learning_rate": 9.966741318079034e-05, "loss": 0.6526, "step": 12860 }, { "epoch": 3.09, "learning_rate": 9.96668963126611e-05, "loss": 0.6129, "step": 12870 }, { "epoch": 3.09, "learning_rate": 9.966637904455748e-05, "loss": 0.6528, "step": 12880 }, { "epoch": 3.09, "learning_rate": 9.966586137648367e-05, "loss": 0.6027, "step": 12890 }, { "epoch": 3.09, "learning_rate": 9.96653433084438e-05, "loss": 0.6602, "step": 12900 }, { "epoch": 3.1, "learning_rate": 9.966482484044206e-05, "loss": 0.6519, "step": 12910 }, { "epoch": 3.1, "learning_rate": 9.966430597248265e-05, "loss": 0.6755, "step": 12920 }, { "epoch": 3.1, "learning_rate": 9.96637867045697e-05, "loss": 0.6464, "step": 12930 }, { "epoch": 3.1, "learning_rate": 9.966326703670744e-05, "loss": 0.6875, "step": 12940 }, { "epoch": 3.11, "learning_rate": 9.966274696890003e-05, "loss": 0.7026, "step": 12950 }, { "epoch": 3.11, "learning_rate": 9.966222650115167e-05, "loss": 0.6554, "step": 12960 }, { "epoch": 3.11, "learning_rate": 9.966170563346653e-05, "loss": 0.6232, "step": 12970 }, { "epoch": 3.11, "learning_rate": 9.966118436584882e-05, "loss": 0.6382, "step": 12980 }, { "epoch": 3.11, "learning_rate": 9.966066269830275e-05, "loss": 0.6625, "step": 12990 }, { "epoch": 3.12, "learning_rate": 9.966014063083249e-05, "loss": 0.6102, "step": 13000 }, { "epoch": 3.12, "learning_rate": 9.965961816344227e-05, "loss": 0.6373, "step": 13010 }, { "epoch": 3.12, "learning_rate": 9.965909529613629e-05, "loss": 0.6092, "step": 13020 }, { "epoch": 3.12, "learning_rate": 9.965857202891877e-05, "loss": 0.6393, "step": 13030 }, { "epoch": 3.13, "learning_rate": 9.965804836179389e-05, "loss": 0.6222, "step": 13040 }, { "epoch": 3.13, "learning_rate": 9.96575242947659e-05, "loss": 0.6456, "step": 13050 }, { "epoch": 3.13, "learning_rate": 9.965699982783902e-05, "loss": 0.6347, "step": 13060 }, { "epoch": 3.13, "learning_rate": 9.965647496101745e-05, "loss": 0.6604, "step": 13070 }, { "epoch": 3.14, "learning_rate": 9.965594969430545e-05, "loss": 0.6844, "step": 13080 }, { "epoch": 3.14, "learning_rate": 9.965542402770723e-05, "loss": 0.6487, "step": 13090 }, { "epoch": 3.14, "learning_rate": 9.9654897961227e-05, "loss": 0.6449, "step": 13100 }, { "epoch": 3.14, "learning_rate": 9.965437149486905e-05, "loss": 0.6637, "step": 13110 }, { "epoch": 3.14, "learning_rate": 9.965384462863757e-05, "loss": 0.639, "step": 13120 }, { "epoch": 3.15, "learning_rate": 9.965331736253683e-05, "loss": 0.6098, "step": 13130 }, { "epoch": 3.15, "learning_rate": 9.965278969657108e-05, "loss": 0.6724, "step": 13140 }, { "epoch": 3.15, "learning_rate": 9.965226163074455e-05, "loss": 0.6367, "step": 13150 }, { "epoch": 3.15, "learning_rate": 9.965173316506151e-05, "loss": 0.6323, "step": 13160 }, { "epoch": 3.16, "learning_rate": 9.96512042995262e-05, "loss": 0.6311, "step": 13170 }, { "epoch": 3.16, "learning_rate": 9.965067503414289e-05, "loss": 0.6766, "step": 13180 }, { "epoch": 3.16, "learning_rate": 9.965014536891584e-05, "loss": 0.673, "step": 13190 }, { "epoch": 3.16, "learning_rate": 9.96496153038493e-05, "loss": 0.6535, "step": 13200 }, { "epoch": 3.16, "learning_rate": 9.964908483894759e-05, "loss": 0.6196, "step": 13210 }, { "epoch": 3.17, "learning_rate": 9.964855397421491e-05, "loss": 0.636, "step": 13220 }, { "epoch": 3.17, "learning_rate": 9.964802270965559e-05, "loss": 0.6337, "step": 13230 }, { "epoch": 3.17, "learning_rate": 9.964749104527389e-05, "loss": 0.6417, "step": 13240 }, { "epoch": 3.17, "learning_rate": 9.964695898107408e-05, "loss": 0.6378, "step": 13250 }, { "epoch": 3.18, "learning_rate": 9.964642651706044e-05, "loss": 0.6891, "step": 13260 }, { "epoch": 3.18, "learning_rate": 9.964589365323729e-05, "loss": 0.6227, "step": 13270 }, { "epoch": 3.18, "learning_rate": 9.964536038960891e-05, "loss": 0.6018, "step": 13280 }, { "epoch": 3.18, "learning_rate": 9.964482672617959e-05, "loss": 0.6271, "step": 13290 }, { "epoch": 3.19, "learning_rate": 9.964429266295361e-05, "loss": 0.6793, "step": 13300 }, { "epoch": 3.19, "learning_rate": 9.964375819993531e-05, "loss": 0.6349, "step": 13310 }, { "epoch": 3.19, "learning_rate": 9.964322333712896e-05, "loss": 0.6532, "step": 13320 }, { "epoch": 3.19, "learning_rate": 9.964268807453887e-05, "loss": 0.5762, "step": 13330 }, { "epoch": 3.19, "learning_rate": 9.964215241216937e-05, "loss": 0.6986, "step": 13340 }, { "epoch": 3.2, "learning_rate": 9.964161635002476e-05, "loss": 0.6547, "step": 13350 }, { "epoch": 3.2, "learning_rate": 9.964107988810937e-05, "loss": 0.6283, "step": 13360 }, { "epoch": 3.2, "learning_rate": 9.96405430264275e-05, "loss": 0.6406, "step": 13370 }, { "epoch": 3.2, "learning_rate": 9.964000576498348e-05, "loss": 0.6628, "step": 13380 }, { "epoch": 3.21, "learning_rate": 9.963946810378165e-05, "loss": 0.6807, "step": 13390 }, { "epoch": 3.21, "learning_rate": 9.963893004282632e-05, "loss": 0.5875, "step": 13400 }, { "epoch": 3.21, "learning_rate": 9.963839158212184e-05, "loss": 0.6779, "step": 13410 }, { "epoch": 3.21, "learning_rate": 9.963785272167254e-05, "loss": 0.6323, "step": 13420 }, { "epoch": 3.22, "learning_rate": 9.963731346148274e-05, "loss": 0.6278, "step": 13430 }, { "epoch": 3.22, "learning_rate": 9.963677380155683e-05, "loss": 0.6281, "step": 13440 }, { "epoch": 3.22, "learning_rate": 9.963623374189912e-05, "loss": 0.6145, "step": 13450 }, { "epoch": 3.22, "learning_rate": 9.963569328251396e-05, "loss": 0.615, "step": 13460 }, { "epoch": 3.22, "learning_rate": 9.963515242340572e-05, "loss": 0.6173, "step": 13470 }, { "epoch": 3.23, "learning_rate": 9.963461116457873e-05, "loss": 0.6406, "step": 13480 }, { "epoch": 3.23, "learning_rate": 9.963406950603737e-05, "loss": 0.6554, "step": 13490 }, { "epoch": 3.23, "learning_rate": 9.9633527447786e-05, "loss": 0.6385, "step": 13500 }, { "epoch": 3.23, "learning_rate": 9.963298498982898e-05, "loss": 0.6536, "step": 13510 }, { "epoch": 3.24, "learning_rate": 9.963244213217069e-05, "loss": 0.6488, "step": 13520 }, { "epoch": 3.24, "learning_rate": 9.963189887481548e-05, "loss": 0.671, "step": 13530 }, { "epoch": 3.24, "learning_rate": 9.963135521776773e-05, "loss": 0.6475, "step": 13540 }, { "epoch": 3.24, "learning_rate": 9.963081116103184e-05, "loss": 0.663, "step": 13550 }, { "epoch": 3.24, "learning_rate": 9.963026670461215e-05, "loss": 0.6619, "step": 13560 }, { "epoch": 3.25, "learning_rate": 9.96297218485131e-05, "loss": 0.6325, "step": 13570 }, { "epoch": 3.25, "learning_rate": 9.962917659273903e-05, "loss": 0.6343, "step": 13580 }, { "epoch": 3.25, "learning_rate": 9.962863093729436e-05, "loss": 0.655, "step": 13590 }, { "epoch": 3.25, "learning_rate": 9.962808488218346e-05, "loss": 0.6532, "step": 13600 }, { "epoch": 3.26, "learning_rate": 9.962753842741074e-05, "loss": 0.64, "step": 13610 }, { "epoch": 3.26, "learning_rate": 9.962699157298061e-05, "loss": 0.6656, "step": 13620 }, { "epoch": 3.26, "learning_rate": 9.962644431889747e-05, "loss": 0.6456, "step": 13630 }, { "epoch": 3.26, "learning_rate": 9.962589666516572e-05, "loss": 0.5948, "step": 13640 }, { "epoch": 3.27, "learning_rate": 9.962534861178977e-05, "loss": 0.6481, "step": 13650 }, { "epoch": 3.27, "learning_rate": 9.962480015877403e-05, "loss": 0.5834, "step": 13660 }, { "epoch": 3.27, "learning_rate": 9.962425130612295e-05, "loss": 0.6373, "step": 13670 }, { "epoch": 3.27, "learning_rate": 9.962370205384089e-05, "loss": 0.6224, "step": 13680 }, { "epoch": 3.27, "learning_rate": 9.962315240193232e-05, "loss": 0.6583, "step": 13690 }, { "epoch": 3.28, "learning_rate": 9.962260235040166e-05, "loss": 0.6195, "step": 13700 }, { "epoch": 3.28, "learning_rate": 9.962205189925332e-05, "loss": 0.6707, "step": 13710 }, { "epoch": 3.28, "learning_rate": 9.962150104849175e-05, "loss": 0.6914, "step": 13720 }, { "epoch": 3.28, "learning_rate": 9.962094979812138e-05, "loss": 0.6234, "step": 13730 }, { "epoch": 3.29, "learning_rate": 9.962039814814665e-05, "loss": 0.6636, "step": 13740 }, { "epoch": 3.29, "learning_rate": 9.9619846098572e-05, "loss": 0.6098, "step": 13750 }, { "epoch": 3.29, "learning_rate": 9.96192936494019e-05, "loss": 0.6063, "step": 13760 }, { "epoch": 3.29, "learning_rate": 9.961874080064075e-05, "loss": 0.6306, "step": 13770 }, { "epoch": 3.3, "learning_rate": 9.961818755229304e-05, "loss": 0.6134, "step": 13780 }, { "epoch": 3.3, "learning_rate": 9.961763390436322e-05, "loss": 0.635, "step": 13790 }, { "epoch": 3.3, "learning_rate": 9.961707985685574e-05, "loss": 0.5951, "step": 13800 }, { "epoch": 3.3, "learning_rate": 9.961652540977507e-05, "loss": 0.6296, "step": 13810 }, { "epoch": 3.3, "learning_rate": 9.961597056312566e-05, "loss": 0.6372, "step": 13820 }, { "epoch": 3.31, "learning_rate": 9.9615415316912e-05, "loss": 0.6122, "step": 13830 }, { "epoch": 3.31, "learning_rate": 9.961485967113855e-05, "loss": 0.6323, "step": 13840 }, { "epoch": 3.31, "learning_rate": 9.96143036258098e-05, "loss": 0.6079, "step": 13850 }, { "epoch": 3.31, "learning_rate": 9.961374718093019e-05, "loss": 0.6892, "step": 13860 }, { "epoch": 3.32, "learning_rate": 9.961319033650423e-05, "loss": 0.6373, "step": 13870 }, { "epoch": 3.32, "learning_rate": 9.96126330925364e-05, "loss": 0.6211, "step": 13880 }, { "epoch": 3.32, "learning_rate": 9.961207544903119e-05, "loss": 0.627, "step": 13890 }, { "epoch": 3.32, "learning_rate": 9.961151740599308e-05, "loss": 0.6629, "step": 13900 }, { "epoch": 3.32, "learning_rate": 9.961095896342657e-05, "loss": 0.639, "step": 13910 }, { "epoch": 3.33, "learning_rate": 9.961040012133617e-05, "loss": 0.643, "step": 13920 }, { "epoch": 3.33, "learning_rate": 9.960984087972635e-05, "loss": 0.6433, "step": 13930 }, { "epoch": 3.33, "learning_rate": 9.960928123860165e-05, "loss": 0.6245, "step": 13940 }, { "epoch": 3.33, "learning_rate": 9.960872119796655e-05, "loss": 0.6772, "step": 13950 }, { "epoch": 3.34, "learning_rate": 9.960816075782558e-05, "loss": 0.6398, "step": 13960 }, { "epoch": 3.34, "learning_rate": 9.960759991818323e-05, "loss": 0.6092, "step": 13970 }, { "epoch": 3.34, "learning_rate": 9.960703867904404e-05, "loss": 0.6496, "step": 13980 }, { "epoch": 3.34, "learning_rate": 9.960647704041251e-05, "loss": 0.6358, "step": 13990 }, { "epoch": 3.35, "learning_rate": 9.960591500229316e-05, "loss": 0.6455, "step": 14000 }, { "epoch": 3.35, "learning_rate": 9.960535256469054e-05, "loss": 0.6707, "step": 14010 }, { "epoch": 3.35, "learning_rate": 9.960478972760918e-05, "loss": 0.637, "step": 14020 }, { "epoch": 3.35, "learning_rate": 9.960422649105359e-05, "loss": 0.6571, "step": 14030 }, { "epoch": 3.35, "learning_rate": 9.960366285502831e-05, "loss": 0.639, "step": 14040 }, { "epoch": 3.36, "learning_rate": 9.96030988195379e-05, "loss": 0.6578, "step": 14050 }, { "epoch": 3.36, "learning_rate": 9.960253438458687e-05, "loss": 0.6243, "step": 14060 }, { "epoch": 3.36, "learning_rate": 9.96019695501798e-05, "loss": 0.6127, "step": 14070 }, { "epoch": 3.36, "learning_rate": 9.960140431632121e-05, "loss": 0.6762, "step": 14080 }, { "epoch": 3.37, "learning_rate": 9.960083868301566e-05, "loss": 0.6389, "step": 14090 }, { "epoch": 3.37, "learning_rate": 9.960027265026771e-05, "loss": 0.6523, "step": 14100 }, { "epoch": 3.37, "learning_rate": 9.959970621808192e-05, "loss": 0.6373, "step": 14110 }, { "epoch": 3.37, "learning_rate": 9.959913938646284e-05, "loss": 0.6263, "step": 14120 }, { "epoch": 3.38, "learning_rate": 9.959857215541506e-05, "loss": 0.6325, "step": 14130 }, { "epoch": 3.38, "learning_rate": 9.959800452494313e-05, "loss": 0.6828, "step": 14140 }, { "epoch": 3.38, "learning_rate": 9.95974364950516e-05, "loss": 0.5928, "step": 14150 }, { "epoch": 3.38, "learning_rate": 9.959686806574509e-05, "loss": 0.627, "step": 14160 }, { "epoch": 3.38, "learning_rate": 9.959629923702814e-05, "loss": 0.6194, "step": 14170 }, { "epoch": 3.39, "learning_rate": 9.959573000890535e-05, "loss": 0.6557, "step": 14180 }, { "epoch": 3.39, "learning_rate": 9.95951603813813e-05, "loss": 0.6098, "step": 14190 }, { "epoch": 3.39, "learning_rate": 9.959459035446057e-05, "loss": 0.6393, "step": 14200 }, { "epoch": 3.39, "learning_rate": 9.959401992814776e-05, "loss": 0.6377, "step": 14210 }, { "epoch": 3.4, "learning_rate": 9.959344910244746e-05, "loss": 0.6533, "step": 14220 }, { "epoch": 3.4, "learning_rate": 9.959287787736427e-05, "loss": 0.6175, "step": 14230 }, { "epoch": 3.4, "learning_rate": 9.959230625290279e-05, "loss": 0.6453, "step": 14240 }, { "epoch": 3.4, "learning_rate": 9.959173422906763e-05, "loss": 0.6361, "step": 14250 }, { "epoch": 3.4, "learning_rate": 9.959116180586336e-05, "loss": 0.6074, "step": 14260 }, { "epoch": 3.41, "learning_rate": 9.959058898329463e-05, "loss": 0.6106, "step": 14270 }, { "epoch": 3.41, "learning_rate": 9.959001576136605e-05, "loss": 0.6252, "step": 14280 }, { "epoch": 3.41, "learning_rate": 9.958944214008222e-05, "loss": 0.6315, "step": 14290 }, { "epoch": 3.41, "learning_rate": 9.958886811944777e-05, "loss": 0.641, "step": 14300 }, { "epoch": 3.42, "learning_rate": 9.958829369946732e-05, "loss": 0.6748, "step": 14310 }, { "epoch": 3.42, "learning_rate": 9.958771888014548e-05, "loss": 0.6669, "step": 14320 }, { "epoch": 3.42, "learning_rate": 9.958714366148692e-05, "loss": 0.6169, "step": 14330 }, { "epoch": 3.42, "learning_rate": 9.958656804349622e-05, "loss": 0.6406, "step": 14340 }, { "epoch": 3.43, "learning_rate": 9.958599202617806e-05, "loss": 0.5971, "step": 14350 }, { "epoch": 3.43, "learning_rate": 9.958541560953705e-05, "loss": 0.656, "step": 14360 }, { "epoch": 3.43, "learning_rate": 9.958483879357784e-05, "loss": 0.663, "step": 14370 }, { "epoch": 3.43, "learning_rate": 9.958426157830508e-05, "loss": 0.6394, "step": 14380 }, { "epoch": 3.43, "learning_rate": 9.958368396372341e-05, "loss": 0.6706, "step": 14390 }, { "epoch": 3.44, "learning_rate": 9.958310594983751e-05, "loss": 0.6222, "step": 14400 }, { "epoch": 3.44, "learning_rate": 9.9582527536652e-05, "loss": 0.6198, "step": 14410 }, { "epoch": 3.44, "learning_rate": 9.958194872417155e-05, "loss": 0.6136, "step": 14420 }, { "epoch": 3.44, "learning_rate": 9.958136951240083e-05, "loss": 0.6509, "step": 14430 }, { "epoch": 3.45, "learning_rate": 9.958078990134448e-05, "loss": 0.6374, "step": 14440 }, { "epoch": 3.45, "learning_rate": 9.958020989100718e-05, "loss": 0.6304, "step": 14450 }, { "epoch": 3.45, "learning_rate": 9.957962948139362e-05, "loss": 0.6173, "step": 14460 }, { "epoch": 3.45, "learning_rate": 9.957904867250845e-05, "loss": 0.6703, "step": 14470 }, { "epoch": 3.45, "learning_rate": 9.957846746435637e-05, "loss": 0.6109, "step": 14480 }, { "epoch": 3.46, "learning_rate": 9.957788585694203e-05, "loss": 0.5905, "step": 14490 }, { "epoch": 3.46, "learning_rate": 9.957730385027014e-05, "loss": 0.6587, "step": 14500 }, { "epoch": 3.46, "learning_rate": 9.957672144434538e-05, "loss": 0.6373, "step": 14510 }, { "epoch": 3.46, "learning_rate": 9.957613863917243e-05, "loss": 0.5992, "step": 14520 }, { "epoch": 3.47, "learning_rate": 9.957555543475599e-05, "loss": 0.6598, "step": 14530 }, { "epoch": 3.47, "learning_rate": 9.957497183110077e-05, "loss": 0.6678, "step": 14540 }, { "epoch": 3.47, "learning_rate": 9.957438782821145e-05, "loss": 0.6338, "step": 14550 }, { "epoch": 3.47, "learning_rate": 9.957380342609275e-05, "loss": 0.6444, "step": 14560 }, { "epoch": 3.48, "learning_rate": 9.957321862474936e-05, "loss": 0.6206, "step": 14570 }, { "epoch": 3.48, "learning_rate": 9.957263342418599e-05, "loss": 0.6472, "step": 14580 }, { "epoch": 3.48, "learning_rate": 9.957204782440736e-05, "loss": 0.6267, "step": 14590 }, { "epoch": 3.48, "learning_rate": 9.957146182541818e-05, "loss": 0.6421, "step": 14600 }, { "epoch": 3.48, "learning_rate": 9.957087542722318e-05, "loss": 0.6427, "step": 14610 }, { "epoch": 3.49, "learning_rate": 9.95702886298271e-05, "loss": 0.6881, "step": 14620 }, { "epoch": 3.49, "learning_rate": 9.956970143323461e-05, "loss": 0.6747, "step": 14630 }, { "epoch": 3.49, "learning_rate": 9.956911383745047e-05, "loss": 0.6332, "step": 14640 }, { "epoch": 3.49, "learning_rate": 9.956852584247943e-05, "loss": 0.6766, "step": 14650 }, { "epoch": 3.5, "learning_rate": 9.95679374483262e-05, "loss": 0.6332, "step": 14660 }, { "epoch": 3.5, "learning_rate": 9.956734865499553e-05, "loss": 0.6338, "step": 14670 }, { "epoch": 3.5, "learning_rate": 9.956675946249216e-05, "loss": 0.6254, "step": 14680 }, { "epoch": 3.5, "learning_rate": 9.956616987082083e-05, "loss": 0.6232, "step": 14690 }, { "epoch": 3.51, "learning_rate": 9.956557987998629e-05, "loss": 0.6261, "step": 14700 }, { "epoch": 3.51, "learning_rate": 9.956498948999329e-05, "loss": 0.6774, "step": 14710 }, { "epoch": 3.51, "learning_rate": 9.95643987008466e-05, "loss": 0.6589, "step": 14720 }, { "epoch": 3.51, "learning_rate": 9.956380751255095e-05, "loss": 0.6117, "step": 14730 }, { "epoch": 3.51, "learning_rate": 9.956321592511112e-05, "loss": 0.6734, "step": 14740 }, { "epoch": 3.52, "learning_rate": 9.956262393853186e-05, "loss": 0.6061, "step": 14750 }, { "epoch": 3.52, "learning_rate": 9.956203155281796e-05, "loss": 0.6465, "step": 14760 }, { "epoch": 3.52, "learning_rate": 9.956143876797417e-05, "loss": 0.6656, "step": 14770 }, { "epoch": 3.52, "learning_rate": 9.95608455840053e-05, "loss": 0.615, "step": 14780 }, { "epoch": 3.53, "learning_rate": 9.956025200091605e-05, "loss": 0.6138, "step": 14790 }, { "epoch": 3.53, "learning_rate": 9.955965801871128e-05, "loss": 0.6321, "step": 14800 }, { "epoch": 3.53, "learning_rate": 9.955906363739573e-05, "loss": 0.6565, "step": 14810 }, { "epoch": 3.53, "learning_rate": 9.95584688569742e-05, "loss": 0.6093, "step": 14820 }, { "epoch": 3.53, "learning_rate": 9.955787367745148e-05, "loss": 0.6708, "step": 14830 }, { "epoch": 3.54, "learning_rate": 9.955727809883237e-05, "loss": 0.6291, "step": 14840 }, { "epoch": 3.54, "learning_rate": 9.955668212112165e-05, "loss": 0.6749, "step": 14850 }, { "epoch": 3.54, "learning_rate": 9.955608574432412e-05, "loss": 0.6005, "step": 14860 }, { "epoch": 3.54, "learning_rate": 9.95554889684446e-05, "loss": 0.6627, "step": 14870 }, { "epoch": 3.55, "learning_rate": 9.955489179348788e-05, "loss": 0.6361, "step": 14880 }, { "epoch": 3.55, "learning_rate": 9.955429421945878e-05, "loss": 0.7008, "step": 14890 }, { "epoch": 3.55, "learning_rate": 9.95536962463621e-05, "loss": 0.6637, "step": 14900 }, { "epoch": 3.55, "learning_rate": 9.955309787420267e-05, "loss": 0.6949, "step": 14910 }, { "epoch": 3.56, "learning_rate": 9.95524991029853e-05, "loss": 0.6958, "step": 14920 }, { "epoch": 3.56, "learning_rate": 9.955189993271481e-05, "loss": 0.6327, "step": 14930 }, { "epoch": 3.56, "learning_rate": 9.955130036339603e-05, "loss": 0.6567, "step": 14940 }, { "epoch": 3.56, "learning_rate": 9.955070039503378e-05, "loss": 0.6721, "step": 14950 }, { "epoch": 3.56, "learning_rate": 9.955010002763293e-05, "loss": 0.7082, "step": 14960 }, { "epoch": 3.57, "learning_rate": 9.954949926119825e-05, "loss": 0.6656, "step": 14970 }, { "epoch": 3.57, "learning_rate": 9.954889809573462e-05, "loss": 0.694, "step": 14980 }, { "epoch": 3.57, "learning_rate": 9.954829653124688e-05, "loss": 0.6885, "step": 14990 }, { "epoch": 3.57, "learning_rate": 9.954769456773986e-05, "loss": 0.6255, "step": 15000 }, { "epoch": 3.58, "learning_rate": 9.954709220521841e-05, "loss": 0.6498, "step": 15010 }, { "epoch": 3.58, "learning_rate": 9.95464894436874e-05, "loss": 0.6429, "step": 15020 }, { "epoch": 3.58, "learning_rate": 9.954588628315167e-05, "loss": 0.6614, "step": 15030 }, { "epoch": 3.58, "learning_rate": 9.954528272361607e-05, "loss": 0.6817, "step": 15040 }, { "epoch": 3.59, "learning_rate": 9.954467876508546e-05, "loss": 0.6352, "step": 15050 }, { "epoch": 3.59, "learning_rate": 9.954407440756473e-05, "loss": 0.6318, "step": 15060 }, { "epoch": 3.59, "learning_rate": 9.954346965105872e-05, "loss": 0.6769, "step": 15070 }, { "epoch": 3.59, "learning_rate": 9.954286449557231e-05, "loss": 0.6463, "step": 15080 }, { "epoch": 3.59, "learning_rate": 9.954225894111036e-05, "loss": 0.7126, "step": 15090 }, { "epoch": 3.6, "learning_rate": 9.954165298767778e-05, "loss": 0.6577, "step": 15100 }, { "epoch": 3.6, "learning_rate": 9.95410466352794e-05, "loss": 0.6936, "step": 15110 }, { "epoch": 3.6, "learning_rate": 9.954043988392017e-05, "loss": 0.6756, "step": 15120 }, { "epoch": 3.6, "learning_rate": 9.953983273360491e-05, "loss": 0.6899, "step": 15130 }, { "epoch": 3.61, "learning_rate": 9.953922518433855e-05, "loss": 0.6347, "step": 15140 }, { "epoch": 3.61, "learning_rate": 9.953861723612597e-05, "loss": 0.6537, "step": 15150 }, { "epoch": 3.61, "learning_rate": 9.953800888897207e-05, "loss": 0.6928, "step": 15160 }, { "epoch": 3.61, "learning_rate": 9.953740014288173e-05, "loss": 0.6249, "step": 15170 }, { "epoch": 3.61, "learning_rate": 9.953679099785988e-05, "loss": 0.6619, "step": 15180 }, { "epoch": 3.62, "learning_rate": 9.953618145391142e-05, "loss": 0.6452, "step": 15190 }, { "epoch": 3.62, "learning_rate": 9.953557151104124e-05, "loss": 0.6204, "step": 15200 }, { "epoch": 3.62, "learning_rate": 9.953496116925425e-05, "loss": 0.6549, "step": 15210 }, { "epoch": 3.62, "learning_rate": 9.953435042855541e-05, "loss": 0.6635, "step": 15220 }, { "epoch": 3.63, "learning_rate": 9.95337392889496e-05, "loss": 0.6637, "step": 15230 }, { "epoch": 3.63, "learning_rate": 9.953312775044172e-05, "loss": 0.6465, "step": 15240 }, { "epoch": 3.63, "learning_rate": 9.953251581303676e-05, "loss": 0.675, "step": 15250 }, { "epoch": 3.63, "learning_rate": 9.95319034767396e-05, "loss": 0.6468, "step": 15260 }, { "epoch": 3.64, "learning_rate": 9.953129074155516e-05, "loss": 0.6494, "step": 15270 }, { "epoch": 3.64, "learning_rate": 9.953067760748842e-05, "loss": 0.6244, "step": 15280 }, { "epoch": 3.64, "learning_rate": 9.95300640745443e-05, "loss": 0.6291, "step": 15290 }, { "epoch": 3.64, "learning_rate": 9.952945014272771e-05, "loss": 0.6334, "step": 15300 }, { "epoch": 3.64, "learning_rate": 9.952883581204365e-05, "loss": 0.6416, "step": 15310 }, { "epoch": 3.65, "learning_rate": 9.952822108249702e-05, "loss": 0.6511, "step": 15320 }, { "epoch": 3.65, "learning_rate": 9.952760595409281e-05, "loss": 0.6445, "step": 15330 }, { "epoch": 3.65, "learning_rate": 9.952699042683593e-05, "loss": 0.6382, "step": 15340 }, { "epoch": 3.65, "learning_rate": 9.952637450073135e-05, "loss": 0.6605, "step": 15350 }, { "epoch": 3.66, "learning_rate": 9.952575817578407e-05, "loss": 0.6129, "step": 15360 }, { "epoch": 3.66, "learning_rate": 9.952514145199899e-05, "loss": 0.6249, "step": 15370 }, { "epoch": 3.66, "learning_rate": 9.952452432938113e-05, "loss": 0.6217, "step": 15380 }, { "epoch": 3.66, "learning_rate": 9.952390680793543e-05, "loss": 0.6745, "step": 15390 }, { "epoch": 3.67, "learning_rate": 9.952328888766687e-05, "loss": 0.6388, "step": 15400 }, { "epoch": 3.67, "learning_rate": 9.952267056858043e-05, "loss": 0.6333, "step": 15410 }, { "epoch": 3.67, "learning_rate": 9.952205185068108e-05, "loss": 0.6208, "step": 15420 }, { "epoch": 3.67, "learning_rate": 9.952143273397381e-05, "loss": 0.6229, "step": 15430 }, { "epoch": 3.67, "learning_rate": 9.952081321846362e-05, "loss": 0.6561, "step": 15440 }, { "epoch": 3.68, "learning_rate": 9.952019330415547e-05, "loss": 0.6481, "step": 15450 }, { "epoch": 3.68, "learning_rate": 9.951957299105438e-05, "loss": 0.6405, "step": 15460 }, { "epoch": 3.68, "learning_rate": 9.951895227916532e-05, "loss": 0.6483, "step": 15470 }, { "epoch": 3.68, "learning_rate": 9.951833116849331e-05, "loss": 0.7158, "step": 15480 }, { "epoch": 3.69, "learning_rate": 9.951770965904332e-05, "loss": 0.6569, "step": 15490 }, { "epoch": 3.69, "learning_rate": 9.95170877508204e-05, "loss": 0.5872, "step": 15500 }, { "epoch": 3.69, "learning_rate": 9.951646544382953e-05, "loss": 0.648, "step": 15510 }, { "epoch": 3.69, "learning_rate": 9.951584273807573e-05, "loss": 0.6682, "step": 15520 }, { "epoch": 3.69, "learning_rate": 9.951521963356402e-05, "loss": 0.6109, "step": 15530 }, { "epoch": 3.7, "learning_rate": 9.95145961302994e-05, "loss": 0.6244, "step": 15540 }, { "epoch": 3.7, "learning_rate": 9.95139722282869e-05, "loss": 0.6937, "step": 15550 }, { "epoch": 3.7, "learning_rate": 9.951334792753155e-05, "loss": 0.6317, "step": 15560 }, { "epoch": 3.7, "learning_rate": 9.951272322803838e-05, "loss": 0.647, "step": 15570 }, { "epoch": 3.71, "learning_rate": 9.951209812981239e-05, "loss": 0.6684, "step": 15580 }, { "epoch": 3.71, "learning_rate": 9.951147263285868e-05, "loss": 0.6235, "step": 15590 }, { "epoch": 3.71, "learning_rate": 9.95108467371822e-05, "loss": 0.6038, "step": 15600 }, { "epoch": 3.71, "learning_rate": 9.951022044278806e-05, "loss": 0.6365, "step": 15610 }, { "epoch": 3.72, "learning_rate": 9.950959374968127e-05, "loss": 0.6293, "step": 15620 }, { "epoch": 3.72, "learning_rate": 9.95089666578669e-05, "loss": 0.6174, "step": 15630 }, { "epoch": 3.72, "learning_rate": 9.950833916734998e-05, "loss": 0.6658, "step": 15640 }, { "epoch": 3.72, "learning_rate": 9.950771127813556e-05, "loss": 0.6625, "step": 15650 }, { "epoch": 3.72, "learning_rate": 9.950708299022871e-05, "loss": 0.6548, "step": 15660 }, { "epoch": 3.73, "learning_rate": 9.95064543036345e-05, "loss": 0.6681, "step": 15670 }, { "epoch": 3.73, "learning_rate": 9.950582521835797e-05, "loss": 0.626, "step": 15680 }, { "epoch": 3.73, "learning_rate": 9.950519573440418e-05, "loss": 0.6788, "step": 15690 }, { "epoch": 3.73, "learning_rate": 9.950456585177824e-05, "loss": 0.6471, "step": 15700 }, { "epoch": 3.74, "learning_rate": 9.950393557048518e-05, "loss": 0.6419, "step": 15710 }, { "epoch": 3.74, "learning_rate": 9.950330489053009e-05, "loss": 0.6752, "step": 15720 }, { "epoch": 3.74, "learning_rate": 9.950267381191806e-05, "loss": 0.6119, "step": 15730 }, { "epoch": 3.74, "learning_rate": 9.950204233465417e-05, "loss": 0.6596, "step": 15740 }, { "epoch": 3.75, "learning_rate": 9.950141045874349e-05, "loss": 0.625, "step": 15750 }, { "epoch": 3.75, "learning_rate": 9.95007781841911e-05, "loss": 0.6545, "step": 15760 }, { "epoch": 3.75, "learning_rate": 9.950014551100213e-05, "loss": 0.6148, "step": 15770 }, { "epoch": 3.75, "learning_rate": 9.949951243918165e-05, "loss": 0.6672, "step": 15780 }, { "epoch": 3.75, "learning_rate": 9.949887896873478e-05, "loss": 0.6144, "step": 15790 }, { "epoch": 3.76, "learning_rate": 9.949824509966657e-05, "loss": 0.6639, "step": 15800 }, { "epoch": 3.76, "learning_rate": 9.949761083198218e-05, "loss": 0.6652, "step": 15810 }, { "epoch": 3.76, "learning_rate": 9.949697616568669e-05, "loss": 0.6418, "step": 15820 }, { "epoch": 3.76, "learning_rate": 9.949634110078523e-05, "loss": 0.6251, "step": 15830 }, { "epoch": 3.77, "learning_rate": 9.94957056372829e-05, "loss": 0.5759, "step": 15840 }, { "epoch": 3.77, "learning_rate": 9.949506977518478e-05, "loss": 0.611, "step": 15850 }, { "epoch": 3.77, "learning_rate": 9.949443351449608e-05, "loss": 0.6394, "step": 15860 }, { "epoch": 3.77, "learning_rate": 9.949379685522184e-05, "loss": 0.616, "step": 15870 }, { "epoch": 3.77, "learning_rate": 9.949315979736724e-05, "loss": 0.6318, "step": 15880 }, { "epoch": 3.78, "learning_rate": 9.94925223409374e-05, "loss": 0.6181, "step": 15890 }, { "epoch": 3.78, "learning_rate": 9.949188448593743e-05, "loss": 0.6177, "step": 15900 }, { "epoch": 3.78, "learning_rate": 9.949124623237246e-05, "loss": 0.6613, "step": 15910 }, { "epoch": 3.78, "learning_rate": 9.949060758024768e-05, "loss": 0.6088, "step": 15920 }, { "epoch": 3.79, "learning_rate": 9.948996852956821e-05, "loss": 0.6472, "step": 15930 }, { "epoch": 3.79, "learning_rate": 9.948932908033917e-05, "loss": 0.6209, "step": 15940 }, { "epoch": 3.79, "learning_rate": 9.948868923256575e-05, "loss": 0.6917, "step": 15950 }, { "epoch": 3.79, "learning_rate": 9.948804898625308e-05, "loss": 0.6508, "step": 15960 }, { "epoch": 3.8, "learning_rate": 9.94874083414063e-05, "loss": 0.6534, "step": 15970 }, { "epoch": 3.8, "learning_rate": 9.94867672980306e-05, "loss": 0.6244, "step": 15980 }, { "epoch": 3.8, "learning_rate": 9.948612585613113e-05, "loss": 0.6634, "step": 15990 }, { "epoch": 3.8, "learning_rate": 9.948548401571308e-05, "loss": 0.6791, "step": 16000 }, { "epoch": 3.8, "learning_rate": 9.948484177678155e-05, "loss": 0.6492, "step": 16010 }, { "epoch": 3.81, "learning_rate": 9.948419913934179e-05, "loss": 0.6346, "step": 16020 }, { "epoch": 3.81, "learning_rate": 9.948355610339894e-05, "loss": 0.6113, "step": 16030 }, { "epoch": 3.81, "learning_rate": 9.948291266895817e-05, "loss": 0.6406, "step": 16040 }, { "epoch": 3.81, "learning_rate": 9.948226883602467e-05, "loss": 0.6288, "step": 16050 }, { "epoch": 3.82, "learning_rate": 9.948162460460364e-05, "loss": 0.6015, "step": 16060 }, { "epoch": 3.82, "learning_rate": 9.948097997470025e-05, "loss": 0.6623, "step": 16070 }, { "epoch": 3.82, "learning_rate": 9.948033494631969e-05, "loss": 0.6221, "step": 16080 }, { "epoch": 3.82, "learning_rate": 9.947968951946717e-05, "loss": 0.6569, "step": 16090 }, { "epoch": 3.83, "learning_rate": 9.947904369414788e-05, "loss": 0.6223, "step": 16100 }, { "epoch": 3.83, "learning_rate": 9.947839747036703e-05, "loss": 0.6051, "step": 16110 }, { "epoch": 3.83, "learning_rate": 9.94777508481298e-05, "loss": 0.6327, "step": 16120 }, { "epoch": 3.83, "learning_rate": 9.947710382744142e-05, "loss": 0.6401, "step": 16130 }, { "epoch": 3.83, "learning_rate": 9.947645640830707e-05, "loss": 0.6824, "step": 16140 }, { "epoch": 3.84, "learning_rate": 9.947580859073201e-05, "loss": 0.6528, "step": 16150 }, { "epoch": 3.84, "learning_rate": 9.947516037472142e-05, "loss": 0.6303, "step": 16160 }, { "epoch": 3.84, "learning_rate": 9.947451176028056e-05, "loss": 0.6072, "step": 16170 }, { "epoch": 3.84, "learning_rate": 9.94738627474146e-05, "loss": 0.6899, "step": 16180 }, { "epoch": 3.85, "learning_rate": 9.947321333612879e-05, "loss": 0.6765, "step": 16190 }, { "epoch": 3.85, "learning_rate": 9.947256352642837e-05, "loss": 0.5987, "step": 16200 }, { "epoch": 3.85, "learning_rate": 9.947191331831857e-05, "loss": 0.6576, "step": 16210 }, { "epoch": 3.85, "learning_rate": 9.947126271180462e-05, "loss": 0.6137, "step": 16220 }, { "epoch": 3.85, "learning_rate": 9.947061170689176e-05, "loss": 0.583, "step": 16230 }, { "epoch": 3.86, "learning_rate": 9.946996030358523e-05, "loss": 0.664, "step": 16240 }, { "epoch": 3.86, "learning_rate": 9.946930850189029e-05, "loss": 0.6144, "step": 16250 }, { "epoch": 3.86, "learning_rate": 9.946865630181216e-05, "loss": 0.6397, "step": 16260 }, { "epoch": 3.86, "learning_rate": 9.946800370335613e-05, "loss": 0.6156, "step": 16270 }, { "epoch": 3.87, "learning_rate": 9.946735070652743e-05, "loss": 0.5985, "step": 16280 }, { "epoch": 3.87, "learning_rate": 9.946669731133133e-05, "loss": 0.6384, "step": 16290 }, { "epoch": 3.87, "learning_rate": 9.946604351777308e-05, "loss": 0.6403, "step": 16300 }, { "epoch": 3.87, "learning_rate": 9.946538932585797e-05, "loss": 0.6788, "step": 16310 }, { "epoch": 3.88, "learning_rate": 9.946473473559121e-05, "loss": 0.5712, "step": 16320 }, { "epoch": 3.88, "learning_rate": 9.946407974697815e-05, "loss": 0.6276, "step": 16330 }, { "epoch": 3.88, "learning_rate": 9.946342436002401e-05, "loss": 0.6577, "step": 16340 }, { "epoch": 3.88, "learning_rate": 9.946276857473409e-05, "loss": 0.6131, "step": 16350 }, { "epoch": 3.88, "learning_rate": 9.946211239111367e-05, "loss": 0.6532, "step": 16360 }, { "epoch": 3.89, "learning_rate": 9.946145580916803e-05, "loss": 0.6513, "step": 16370 }, { "epoch": 3.89, "learning_rate": 9.946079882890244e-05, "loss": 0.5881, "step": 16380 }, { "epoch": 3.89, "learning_rate": 9.946014145032223e-05, "loss": 0.6368, "step": 16390 }, { "epoch": 3.89, "learning_rate": 9.945948367343267e-05, "loss": 0.6502, "step": 16400 }, { "epoch": 3.9, "learning_rate": 9.945882549823906e-05, "loss": 0.63, "step": 16410 }, { "epoch": 3.9, "learning_rate": 9.945816692474668e-05, "loss": 0.6048, "step": 16420 }, { "epoch": 3.9, "learning_rate": 9.945750795296087e-05, "loss": 0.6534, "step": 16430 }, { "epoch": 3.9, "learning_rate": 9.945684858288693e-05, "loss": 0.6117, "step": 16440 }, { "epoch": 3.91, "learning_rate": 9.945618881453014e-05, "loss": 0.6016, "step": 16450 }, { "epoch": 3.91, "learning_rate": 9.945552864789585e-05, "loss": 0.6419, "step": 16460 }, { "epoch": 3.91, "learning_rate": 9.945486808298935e-05, "loss": 0.6134, "step": 16470 }, { "epoch": 3.91, "learning_rate": 9.945420711981597e-05, "loss": 0.6435, "step": 16480 }, { "epoch": 3.91, "learning_rate": 9.945354575838104e-05, "loss": 0.6294, "step": 16490 }, { "epoch": 3.92, "learning_rate": 9.945288399868988e-05, "loss": 0.629, "step": 16500 }, { "epoch": 3.92, "learning_rate": 9.945222184074781e-05, "loss": 0.6306, "step": 16510 }, { "epoch": 3.92, "learning_rate": 9.945155928456016e-05, "loss": 0.6161, "step": 16520 }, { "epoch": 3.92, "learning_rate": 9.945089633013229e-05, "loss": 0.6478, "step": 16530 }, { "epoch": 3.93, "learning_rate": 9.945023297746953e-05, "loss": 0.6218, "step": 16540 }, { "epoch": 3.93, "learning_rate": 9.94495692265772e-05, "loss": 0.6654, "step": 16550 }, { "epoch": 3.93, "learning_rate": 9.944890507746068e-05, "loss": 0.6068, "step": 16560 }, { "epoch": 3.93, "learning_rate": 9.944824053012529e-05, "loss": 0.616, "step": 16570 }, { "epoch": 3.93, "learning_rate": 9.944757558457639e-05, "loss": 0.633, "step": 16580 }, { "epoch": 3.94, "learning_rate": 9.944691024081933e-05, "loss": 0.6375, "step": 16590 }, { "epoch": 3.94, "learning_rate": 9.94462444988595e-05, "loss": 0.6438, "step": 16600 }, { "epoch": 3.94, "learning_rate": 9.944557835870223e-05, "loss": 0.6302, "step": 16610 }, { "epoch": 3.94, "learning_rate": 9.944491182035287e-05, "loss": 0.6745, "step": 16620 }, { "epoch": 3.95, "learning_rate": 9.944424488381683e-05, "loss": 0.6417, "step": 16630 }, { "epoch": 3.95, "learning_rate": 9.944357754909945e-05, "loss": 0.6333, "step": 16640 }, { "epoch": 3.95, "learning_rate": 9.944290981620613e-05, "loss": 0.5791, "step": 16650 }, { "epoch": 4.0, "learning_rate": 9.94422416851422e-05, "loss": 0.6171, "step": 16660 }, { "epoch": 4.0, "learning_rate": 9.94415731559131e-05, "loss": 0.6365, "step": 16670 }, { "epoch": 4.01, "learning_rate": 9.944090422852417e-05, "loss": 0.66, "step": 16680 }, { "epoch": 4.01, "learning_rate": 9.944023490298083e-05, "loss": 0.6351, "step": 16690 }, { "epoch": 4.01, "learning_rate": 9.943956517928843e-05, "loss": 0.6382, "step": 16700 }, { "epoch": 4.01, "learning_rate": 9.943889505745238e-05, "loss": 0.59, "step": 16710 }, { "epoch": 4.02, "learning_rate": 9.943822453747811e-05, "loss": 0.5959, "step": 16720 }, { "epoch": 4.02, "learning_rate": 9.943755361937099e-05, "loss": 0.6494, "step": 16730 }, { "epoch": 4.02, "learning_rate": 9.943688230313641e-05, "loss": 0.63, "step": 16740 }, { "epoch": 4.02, "learning_rate": 9.94362105887798e-05, "loss": 0.628, "step": 16750 }, { "epoch": 4.02, "learning_rate": 9.943553847630655e-05, "loss": 0.6158, "step": 16760 }, { "epoch": 4.03, "learning_rate": 9.94348659657221e-05, "loss": 0.651, "step": 16770 }, { "epoch": 4.03, "learning_rate": 9.943419305703184e-05, "loss": 0.6223, "step": 16780 }, { "epoch": 4.03, "learning_rate": 9.94335197502412e-05, "loss": 0.6382, "step": 16790 }, { "epoch": 4.03, "learning_rate": 9.94328460453556e-05, "loss": 0.6176, "step": 16800 }, { "epoch": 4.04, "learning_rate": 9.943217194238048e-05, "loss": 0.6288, "step": 16810 }, { "epoch": 4.04, "learning_rate": 9.943149744132122e-05, "loss": 0.6039, "step": 16820 }, { "epoch": 4.04, "learning_rate": 9.943082254218332e-05, "loss": 0.585, "step": 16830 }, { "epoch": 4.04, "learning_rate": 9.943014724497217e-05, "loss": 0.6419, "step": 16840 }, { "epoch": 4.05, "learning_rate": 9.942947154969323e-05, "loss": 0.6177, "step": 16850 }, { "epoch": 4.05, "learning_rate": 9.942879545635192e-05, "loss": 0.6361, "step": 16860 }, { "epoch": 4.05, "learning_rate": 9.94281189649537e-05, "loss": 0.639, "step": 16870 }, { "epoch": 4.05, "learning_rate": 9.9427442075504e-05, "loss": 0.6103, "step": 16880 }, { "epoch": 4.05, "learning_rate": 9.94267647880083e-05, "loss": 0.6319, "step": 16890 }, { "epoch": 4.06, "learning_rate": 9.942608710247205e-05, "loss": 0.6216, "step": 16900 }, { "epoch": 4.06, "learning_rate": 9.942540901890069e-05, "loss": 0.6202, "step": 16910 }, { "epoch": 4.06, "learning_rate": 9.942473053729968e-05, "loss": 0.58, "step": 16920 }, { "epoch": 4.06, "learning_rate": 9.942405165767449e-05, "loss": 0.591, "step": 16930 }, { "epoch": 4.07, "learning_rate": 9.942337238003059e-05, "loss": 0.6441, "step": 16940 }, { "epoch": 4.07, "learning_rate": 9.942269270437346e-05, "loss": 0.6581, "step": 16950 }, { "epoch": 4.07, "learning_rate": 9.942201263070854e-05, "loss": 0.634, "step": 16960 }, { "epoch": 4.07, "learning_rate": 9.942133215904134e-05, "loss": 0.5723, "step": 16970 }, { "epoch": 4.07, "learning_rate": 9.942065128937735e-05, "loss": 0.636, "step": 16980 }, { "epoch": 4.08, "learning_rate": 9.9419970021722e-05, "loss": 0.6135, "step": 16990 }, { "epoch": 4.08, "learning_rate": 9.941928835608083e-05, "loss": 0.6617, "step": 17000 }, { "epoch": 4.08, "learning_rate": 9.941860629245929e-05, "loss": 0.6075, "step": 17010 }, { "epoch": 4.08, "learning_rate": 9.94179238308629e-05, "loss": 0.6159, "step": 17020 }, { "epoch": 4.09, "learning_rate": 9.941724097129714e-05, "loss": 0.6063, "step": 17030 }, { "epoch": 4.09, "learning_rate": 9.941655771376753e-05, "loss": 0.5885, "step": 17040 }, { "epoch": 4.09, "learning_rate": 9.941587405827955e-05, "loss": 0.6353, "step": 17050 }, { "epoch": 4.09, "learning_rate": 9.941519000483872e-05, "loss": 0.6261, "step": 17060 }, { "epoch": 4.1, "learning_rate": 9.941450555345054e-05, "loss": 0.6217, "step": 17070 }, { "epoch": 4.1, "learning_rate": 9.941382070412053e-05, "loss": 0.5674, "step": 17080 }, { "epoch": 4.1, "learning_rate": 9.94131354568542e-05, "loss": 0.6142, "step": 17090 }, { "epoch": 4.1, "learning_rate": 9.941244981165705e-05, "loss": 0.6247, "step": 17100 }, { "epoch": 4.1, "learning_rate": 9.941176376853462e-05, "loss": 0.5937, "step": 17110 }, { "epoch": 4.11, "learning_rate": 9.941107732749246e-05, "loss": 0.6002, "step": 17120 }, { "epoch": 4.11, "learning_rate": 9.941039048853605e-05, "loss": 0.5859, "step": 17130 }, { "epoch": 4.11, "learning_rate": 9.940970325167096e-05, "loss": 0.617, "step": 17140 }, { "epoch": 4.11, "learning_rate": 9.94090156169027e-05, "loss": 0.6415, "step": 17150 }, { "epoch": 4.12, "learning_rate": 9.940832758423682e-05, "loss": 0.568, "step": 17160 }, { "epoch": 4.12, "learning_rate": 9.940763915367885e-05, "loss": 0.5905, "step": 17170 }, { "epoch": 4.12, "learning_rate": 9.940695032523435e-05, "loss": 0.5756, "step": 17180 }, { "epoch": 4.12, "learning_rate": 9.940626109890885e-05, "loss": 0.56, "step": 17190 }, { "epoch": 4.13, "learning_rate": 9.94055714747079e-05, "loss": 0.6192, "step": 17200 }, { "epoch": 4.13, "learning_rate": 9.940488145263708e-05, "loss": 0.613, "step": 17210 }, { "epoch": 4.13, "learning_rate": 9.940419103270192e-05, "loss": 0.6314, "step": 17220 }, { "epoch": 4.13, "learning_rate": 9.940350021490798e-05, "loss": 0.6648, "step": 17230 }, { "epoch": 4.13, "learning_rate": 9.940280899926086e-05, "loss": 0.6271, "step": 17240 }, { "epoch": 4.14, "learning_rate": 9.940211738576609e-05, "loss": 0.6038, "step": 17250 }, { "epoch": 4.14, "learning_rate": 9.940142537442922e-05, "loss": 0.5894, "step": 17260 }, { "epoch": 4.14, "learning_rate": 9.940073296525588e-05, "loss": 0.6135, "step": 17270 }, { "epoch": 4.14, "learning_rate": 9.940004015825159e-05, "loss": 0.6145, "step": 17280 }, { "epoch": 4.15, "learning_rate": 9.9399346953422e-05, "loss": 0.5658, "step": 17290 }, { "epoch": 4.15, "learning_rate": 9.939865335077261e-05, "loss": 0.542, "step": 17300 }, { "epoch": 4.15, "learning_rate": 9.939795935030907e-05, "loss": 0.5774, "step": 17310 }, { "epoch": 4.15, "learning_rate": 9.939726495203691e-05, "loss": 0.5732, "step": 17320 }, { "epoch": 4.15, "learning_rate": 9.939657015596179e-05, "loss": 0.5935, "step": 17330 }, { "epoch": 4.16, "learning_rate": 9.939587496208926e-05, "loss": 0.6146, "step": 17340 }, { "epoch": 4.16, "learning_rate": 9.939517937042493e-05, "loss": 0.6334, "step": 17350 }, { "epoch": 4.16, "learning_rate": 9.939448338097438e-05, "loss": 0.6045, "step": 17360 }, { "epoch": 4.16, "learning_rate": 9.939378699374326e-05, "loss": 0.5661, "step": 17370 }, { "epoch": 4.17, "learning_rate": 9.939309020873716e-05, "loss": 0.5869, "step": 17380 }, { "epoch": 4.17, "learning_rate": 9.939239302596167e-05, "loss": 0.6414, "step": 17390 }, { "epoch": 4.17, "learning_rate": 9.939169544542242e-05, "loss": 0.659, "step": 17400 }, { "epoch": 4.17, "learning_rate": 9.939099746712503e-05, "loss": 0.6048, "step": 17410 }, { "epoch": 4.18, "learning_rate": 9.939029909107513e-05, "loss": 0.6134, "step": 17420 }, { "epoch": 4.18, "learning_rate": 9.938960031727832e-05, "loss": 0.5759, "step": 17430 }, { "epoch": 4.18, "learning_rate": 9.938890114574024e-05, "loss": 0.6123, "step": 17440 }, { "epoch": 4.18, "learning_rate": 9.938820157646653e-05, "loss": 0.6294, "step": 17450 }, { "epoch": 4.18, "learning_rate": 9.93875016094628e-05, "loss": 0.6534, "step": 17460 }, { "epoch": 4.19, "learning_rate": 9.938680124473472e-05, "loss": 0.6076, "step": 17470 }, { "epoch": 4.19, "learning_rate": 9.93861004822879e-05, "loss": 0.6058, "step": 17480 }, { "epoch": 4.19, "learning_rate": 9.938539932212799e-05, "loss": 0.6076, "step": 17490 }, { "epoch": 4.19, "learning_rate": 9.938469776426065e-05, "loss": 0.633, "step": 17500 }, { "epoch": 4.2, "learning_rate": 9.938399580869151e-05, "loss": 0.5806, "step": 17510 }, { "epoch": 4.2, "learning_rate": 9.938329345542625e-05, "loss": 0.6082, "step": 17520 }, { "epoch": 4.2, "learning_rate": 9.938259070447049e-05, "loss": 0.6283, "step": 17530 }, { "epoch": 4.2, "learning_rate": 9.938188755582993e-05, "loss": 0.6191, "step": 17540 }, { "epoch": 4.21, "learning_rate": 9.93811840095102e-05, "loss": 0.6142, "step": 17550 }, { "epoch": 4.21, "learning_rate": 9.938048006551698e-05, "loss": 0.5527, "step": 17560 }, { "epoch": 4.21, "learning_rate": 9.937977572385593e-05, "loss": 0.6457, "step": 17570 }, { "epoch": 4.21, "learning_rate": 9.937907098453274e-05, "loss": 0.6121, "step": 17580 }, { "epoch": 4.21, "learning_rate": 9.937836584755307e-05, "loss": 0.6386, "step": 17590 }, { "epoch": 4.22, "learning_rate": 9.937766031292259e-05, "loss": 0.6287, "step": 17600 }, { "epoch": 4.22, "learning_rate": 9.937695438064703e-05, "loss": 0.6016, "step": 17610 }, { "epoch": 4.22, "learning_rate": 9.9376248050732e-05, "loss": 0.6201, "step": 17620 }, { "epoch": 4.22, "learning_rate": 9.937554132318325e-05, "loss": 0.6641, "step": 17630 }, { "epoch": 4.23, "learning_rate": 9.937483419800644e-05, "loss": 0.5934, "step": 17640 }, { "epoch": 4.23, "learning_rate": 9.937412667520727e-05, "loss": 0.5892, "step": 17650 }, { "epoch": 4.23, "learning_rate": 9.937341875479145e-05, "loss": 0.6194, "step": 17660 }, { "epoch": 4.23, "learning_rate": 9.937271043676468e-05, "loss": 0.6406, "step": 17670 }, { "epoch": 4.23, "learning_rate": 9.937200172113263e-05, "loss": 0.614, "step": 17680 }, { "epoch": 4.24, "learning_rate": 9.937129260790105e-05, "loss": 0.6348, "step": 17690 }, { "epoch": 4.24, "learning_rate": 9.937058309707565e-05, "loss": 0.6187, "step": 17700 }, { "epoch": 4.24, "learning_rate": 9.936987318866211e-05, "loss": 0.6118, "step": 17710 }, { "epoch": 4.24, "learning_rate": 9.936916288266617e-05, "loss": 0.6271, "step": 17720 }, { "epoch": 4.25, "learning_rate": 9.936845217909354e-05, "loss": 0.5711, "step": 17730 }, { "epoch": 4.25, "learning_rate": 9.936774107794995e-05, "loss": 0.5787, "step": 17740 }, { "epoch": 4.25, "learning_rate": 9.936702957924113e-05, "loss": 0.5916, "step": 17750 }, { "epoch": 4.25, "learning_rate": 9.936631768297281e-05, "loss": 0.6283, "step": 17760 }, { "epoch": 4.26, "learning_rate": 9.936560538915072e-05, "loss": 0.6045, "step": 17770 }, { "epoch": 4.26, "learning_rate": 9.936489269778057e-05, "loss": 0.6068, "step": 17780 }, { "epoch": 4.26, "learning_rate": 9.936417960886815e-05, "loss": 0.6095, "step": 17790 }, { "epoch": 4.26, "learning_rate": 9.936346612241916e-05, "loss": 0.6406, "step": 17800 }, { "epoch": 4.26, "learning_rate": 9.936275223843937e-05, "loss": 0.6769, "step": 17810 }, { "epoch": 4.27, "learning_rate": 9.936203795693453e-05, "loss": 0.6147, "step": 17820 }, { "epoch": 4.27, "learning_rate": 9.936132327791037e-05, "loss": 0.5869, "step": 17830 }, { "epoch": 4.27, "learning_rate": 9.936060820137266e-05, "loss": 0.585, "step": 17840 }, { "epoch": 4.27, "learning_rate": 9.935989272732716e-05, "loss": 0.5953, "step": 17850 }, { "epoch": 4.28, "learning_rate": 9.935917685577962e-05, "loss": 0.6111, "step": 17860 }, { "epoch": 4.28, "learning_rate": 9.935846058673583e-05, "loss": 0.6198, "step": 17870 }, { "epoch": 4.28, "learning_rate": 9.935774392020154e-05, "loss": 0.5975, "step": 17880 }, { "epoch": 4.28, "learning_rate": 9.935702685618251e-05, "loss": 0.6108, "step": 17890 }, { "epoch": 4.29, "learning_rate": 9.935630939468454e-05, "loss": 0.61, "step": 17900 }, { "epoch": 4.29, "learning_rate": 9.93555915357134e-05, "loss": 0.6519, "step": 17910 }, { "epoch": 4.29, "learning_rate": 9.935487327927486e-05, "loss": 0.639, "step": 17920 }, { "epoch": 4.29, "learning_rate": 9.935415462537472e-05, "loss": 0.5703, "step": 17930 }, { "epoch": 4.29, "learning_rate": 9.935343557401874e-05, "loss": 0.5725, "step": 17940 }, { "epoch": 4.3, "learning_rate": 9.935271612521275e-05, "loss": 0.6059, "step": 17950 }, { "epoch": 4.3, "learning_rate": 9.935199627896252e-05, "loss": 0.6012, "step": 17960 }, { "epoch": 4.3, "learning_rate": 9.935127603527385e-05, "loss": 0.5705, "step": 17970 }, { "epoch": 4.3, "learning_rate": 9.935055539415253e-05, "loss": 0.6252, "step": 17980 }, { "epoch": 4.31, "learning_rate": 9.934983435560438e-05, "loss": 0.6076, "step": 17990 }, { "epoch": 4.31, "learning_rate": 9.934911291963522e-05, "loss": 0.5582, "step": 18000 }, { "epoch": 4.31, "learning_rate": 9.934839108625081e-05, "loss": 0.5817, "step": 18010 }, { "epoch": 4.31, "learning_rate": 9.9347668855457e-05, "loss": 0.6037, "step": 18020 }, { "epoch": 4.31, "learning_rate": 9.934694622725961e-05, "loss": 0.5701, "step": 18030 }, { "epoch": 4.32, "learning_rate": 9.934622320166445e-05, "loss": 0.5883, "step": 18040 }, { "epoch": 4.32, "learning_rate": 9.934549977867734e-05, "loss": 0.586, "step": 18050 }, { "epoch": 4.32, "learning_rate": 9.93447759583041e-05, "loss": 0.5829, "step": 18060 }, { "epoch": 4.32, "learning_rate": 9.934405174055057e-05, "loss": 0.5767, "step": 18070 }, { "epoch": 4.33, "learning_rate": 9.934332712542258e-05, "loss": 0.6077, "step": 18080 }, { "epoch": 4.33, "learning_rate": 9.934260211292598e-05, "loss": 0.5779, "step": 18090 }, { "epoch": 4.33, "learning_rate": 9.934187670306657e-05, "loss": 0.5846, "step": 18100 }, { "epoch": 4.33, "learning_rate": 9.934115089585023e-05, "loss": 0.6234, "step": 18110 }, { "epoch": 4.34, "learning_rate": 9.934042469128277e-05, "loss": 0.5787, "step": 18120 }, { "epoch": 4.34, "learning_rate": 9.933969808937008e-05, "loss": 0.6287, "step": 18130 }, { "epoch": 4.34, "learning_rate": 9.933897109011798e-05, "loss": 0.6016, "step": 18140 }, { "epoch": 4.34, "learning_rate": 9.933824369353233e-05, "loss": 0.56, "step": 18150 }, { "epoch": 4.34, "learning_rate": 9.9337515899619e-05, "loss": 0.5864, "step": 18160 }, { "epoch": 4.35, "learning_rate": 9.933678770838384e-05, "loss": 0.5357, "step": 18170 }, { "epoch": 4.35, "learning_rate": 9.933605911983273e-05, "loss": 0.6268, "step": 18180 }, { "epoch": 4.35, "learning_rate": 9.93353301339715e-05, "loss": 0.5838, "step": 18190 }, { "epoch": 4.35, "learning_rate": 9.933460075080606e-05, "loss": 0.5404, "step": 18200 }, { "epoch": 4.36, "learning_rate": 9.933387097034225e-05, "loss": 0.602, "step": 18210 }, { "epoch": 4.36, "learning_rate": 9.9333140792586e-05, "loss": 0.5987, "step": 18220 }, { "epoch": 4.36, "learning_rate": 9.933241021754314e-05, "loss": 0.6073, "step": 18230 }, { "epoch": 4.36, "learning_rate": 9.933167924521956e-05, "loss": 0.5962, "step": 18240 }, { "epoch": 4.37, "learning_rate": 9.933094787562116e-05, "loss": 0.6066, "step": 18250 }, { "epoch": 4.37, "learning_rate": 9.933021610875384e-05, "loss": 0.5843, "step": 18260 }, { "epoch": 4.37, "learning_rate": 9.932948394462347e-05, "loss": 0.594, "step": 18270 }, { "epoch": 4.37, "learning_rate": 9.932875138323597e-05, "loss": 0.6391, "step": 18280 }, { "epoch": 4.37, "learning_rate": 9.93280184245972e-05, "loss": 0.572, "step": 18290 }, { "epoch": 4.38, "learning_rate": 9.93272850687131e-05, "loss": 0.6263, "step": 18300 }, { "epoch": 4.38, "learning_rate": 9.932655131558955e-05, "loss": 0.5971, "step": 18310 }, { "epoch": 4.38, "learning_rate": 9.932581716523248e-05, "loss": 0.6502, "step": 18320 }, { "epoch": 4.38, "learning_rate": 9.932508261764782e-05, "loss": 0.5961, "step": 18330 }, { "epoch": 4.39, "learning_rate": 9.932434767284142e-05, "loss": 0.6233, "step": 18340 }, { "epoch": 4.39, "learning_rate": 9.932361233081927e-05, "loss": 0.5951, "step": 18350 }, { "epoch": 4.39, "learning_rate": 9.932287659158724e-05, "loss": 0.6061, "step": 18360 }, { "epoch": 4.39, "learning_rate": 9.932214045515128e-05, "loss": 0.589, "step": 18370 }, { "epoch": 4.39, "learning_rate": 9.932140392151732e-05, "loss": 0.5915, "step": 18380 }, { "epoch": 4.4, "learning_rate": 9.932066699069127e-05, "loss": 0.6411, "step": 18390 }, { "epoch": 4.4, "learning_rate": 9.931992966267909e-05, "loss": 0.6111, "step": 18400 }, { "epoch": 4.4, "learning_rate": 9.931919193748671e-05, "loss": 0.6359, "step": 18410 }, { "epoch": 4.4, "learning_rate": 9.931845381512007e-05, "loss": 0.6043, "step": 18420 }, { "epoch": 4.41, "learning_rate": 9.931771529558512e-05, "loss": 0.6137, "step": 18430 }, { "epoch": 4.41, "learning_rate": 9.931697637888777e-05, "loss": 0.6249, "step": 18440 }, { "epoch": 4.41, "learning_rate": 9.931623706503402e-05, "loss": 0.6304, "step": 18450 }, { "epoch": 4.41, "learning_rate": 9.931549735402981e-05, "loss": 0.5685, "step": 18460 }, { "epoch": 4.42, "learning_rate": 9.931475724588109e-05, "loss": 0.5878, "step": 18470 }, { "epoch": 4.42, "learning_rate": 9.931401674059382e-05, "loss": 0.5857, "step": 18480 }, { "epoch": 4.42, "learning_rate": 9.931327583817396e-05, "loss": 0.6257, "step": 18490 }, { "epoch": 4.42, "learning_rate": 9.931253453862747e-05, "loss": 0.5973, "step": 18500 }, { "epoch": 4.42, "learning_rate": 9.931179284196035e-05, "loss": 0.6056, "step": 18510 }, { "epoch": 4.43, "learning_rate": 9.931105074817855e-05, "loss": 0.568, "step": 18520 }, { "epoch": 4.43, "learning_rate": 9.931030825728805e-05, "loss": 0.6217, "step": 18530 }, { "epoch": 4.43, "learning_rate": 9.930956536929483e-05, "loss": 0.6363, "step": 18540 }, { "epoch": 4.43, "learning_rate": 9.930882208420486e-05, "loss": 0.6162, "step": 18550 }, { "epoch": 4.44, "learning_rate": 9.930807840202416e-05, "loss": 0.5946, "step": 18560 }, { "epoch": 4.44, "learning_rate": 9.930733432275869e-05, "loss": 0.5543, "step": 18570 }, { "epoch": 4.44, "learning_rate": 9.930658984641444e-05, "loss": 0.5619, "step": 18580 }, { "epoch": 4.44, "learning_rate": 9.930584497299741e-05, "loss": 0.6178, "step": 18590 }, { "epoch": 4.45, "learning_rate": 9.930509970251363e-05, "loss": 0.6062, "step": 18600 }, { "epoch": 4.45, "learning_rate": 9.930435403496906e-05, "loss": 0.5881, "step": 18610 }, { "epoch": 4.45, "learning_rate": 9.930360797036972e-05, "loss": 0.5906, "step": 18620 }, { "epoch": 4.45, "learning_rate": 9.930286150872161e-05, "loss": 0.6051, "step": 18630 }, { "epoch": 4.45, "learning_rate": 9.930211465003077e-05, "loss": 0.5695, "step": 18640 }, { "epoch": 4.46, "learning_rate": 9.930136739430318e-05, "loss": 0.6094, "step": 18650 }, { "epoch": 4.46, "learning_rate": 9.930061974154488e-05, "loss": 0.5987, "step": 18660 }, { "epoch": 4.46, "learning_rate": 9.929987169176188e-05, "loss": 0.5961, "step": 18670 }, { "epoch": 4.46, "learning_rate": 9.929912324496019e-05, "loss": 0.6047, "step": 18680 }, { "epoch": 4.47, "learning_rate": 9.929837440114587e-05, "loss": 0.5874, "step": 18690 }, { "epoch": 4.47, "learning_rate": 9.929762516032492e-05, "loss": 0.6516, "step": 18700 }, { "epoch": 4.47, "learning_rate": 9.929687552250342e-05, "loss": 0.6073, "step": 18710 }, { "epoch": 4.47, "learning_rate": 9.929612548768735e-05, "loss": 0.5745, "step": 18720 }, { "epoch": 4.47, "learning_rate": 9.929537505588277e-05, "loss": 0.5991, "step": 18730 }, { "epoch": 4.48, "learning_rate": 9.929462422709574e-05, "loss": 0.6515, "step": 18740 }, { "epoch": 4.48, "learning_rate": 9.92938730013323e-05, "loss": 0.5899, "step": 18750 }, { "epoch": 4.48, "learning_rate": 9.92931213785985e-05, "loss": 0.5901, "step": 18760 }, { "epoch": 4.48, "learning_rate": 9.929236935890038e-05, "loss": 0.6061, "step": 18770 }, { "epoch": 4.49, "learning_rate": 9.9291616942244e-05, "loss": 0.6289, "step": 18780 }, { "epoch": 4.49, "learning_rate": 9.929086412863545e-05, "loss": 0.6042, "step": 18790 }, { "epoch": 4.49, "learning_rate": 9.929011091808073e-05, "loss": 0.61, "step": 18800 }, { "epoch": 4.49, "learning_rate": 9.928935731058595e-05, "loss": 0.6133, "step": 18810 }, { "epoch": 4.5, "learning_rate": 9.928860330615719e-05, "loss": 0.5922, "step": 18820 }, { "epoch": 4.5, "learning_rate": 9.928784890480049e-05, "loss": 0.62, "step": 18830 }, { "epoch": 4.5, "learning_rate": 9.928709410652193e-05, "loss": 0.573, "step": 18840 }, { "epoch": 4.5, "learning_rate": 9.928633891132762e-05, "loss": 0.5625, "step": 18850 }, { "epoch": 4.5, "learning_rate": 9.92855833192236e-05, "loss": 0.6391, "step": 18860 }, { "epoch": 4.51, "learning_rate": 9.928482733021597e-05, "loss": 0.6031, "step": 18870 }, { "epoch": 4.51, "learning_rate": 9.928407094431083e-05, "loss": 0.6098, "step": 18880 }, { "epoch": 4.51, "learning_rate": 9.928331416151426e-05, "loss": 0.5945, "step": 18890 }, { "epoch": 4.51, "learning_rate": 9.928255698183235e-05, "loss": 0.5814, "step": 18900 }, { "epoch": 4.52, "learning_rate": 9.928179940527123e-05, "loss": 0.5666, "step": 18910 }, { "epoch": 4.52, "learning_rate": 9.928104143183694e-05, "loss": 0.5894, "step": 18920 }, { "epoch": 4.52, "learning_rate": 9.928028306153565e-05, "loss": 0.5987, "step": 18930 }, { "epoch": 4.52, "learning_rate": 9.927952429437342e-05, "loss": 0.5921, "step": 18940 }, { "epoch": 4.53, "learning_rate": 9.927876513035639e-05, "loss": 0.6122, "step": 18950 }, { "epoch": 4.53, "learning_rate": 9.927800556949065e-05, "loss": 0.6455, "step": 18960 }, { "epoch": 4.53, "learning_rate": 9.927724561178233e-05, "loss": 0.5957, "step": 18970 }, { "epoch": 4.53, "learning_rate": 9.927648525723754e-05, "loss": 0.656, "step": 18980 }, { "epoch": 4.53, "learning_rate": 9.927572450586242e-05, "loss": 0.6261, "step": 18990 }, { "epoch": 4.54, "learning_rate": 9.927496335766309e-05, "loss": 0.5724, "step": 19000 }, { "epoch": 4.54, "learning_rate": 9.927420181264567e-05, "loss": 0.6074, "step": 19010 }, { "epoch": 4.54, "learning_rate": 9.927343987081631e-05, "loss": 0.6268, "step": 19020 }, { "epoch": 4.54, "learning_rate": 9.927267753218112e-05, "loss": 0.6217, "step": 19030 }, { "epoch": 4.55, "learning_rate": 9.927191479674628e-05, "loss": 0.6193, "step": 19040 }, { "epoch": 4.55, "learning_rate": 9.927115166451789e-05, "loss": 0.6031, "step": 19050 }, { "epoch": 4.55, "learning_rate": 9.927038813550211e-05, "loss": 0.6582, "step": 19060 }, { "epoch": 4.55, "learning_rate": 9.926962420970511e-05, "loss": 0.6361, "step": 19070 }, { "epoch": 4.55, "learning_rate": 9.926885988713301e-05, "loss": 0.6554, "step": 19080 }, { "epoch": 4.56, "learning_rate": 9.926809516779198e-05, "loss": 0.6568, "step": 19090 }, { "epoch": 4.56, "learning_rate": 9.926733005168819e-05, "loss": 0.6082, "step": 19100 }, { "epoch": 4.56, "learning_rate": 9.926656453882778e-05, "loss": 0.5901, "step": 19110 }, { "epoch": 4.56, "learning_rate": 9.926579862921692e-05, "loss": 0.6291, "step": 19120 }, { "epoch": 4.57, "learning_rate": 9.92650323228618e-05, "loss": 0.6255, "step": 19130 }, { "epoch": 4.57, "learning_rate": 9.926426561976855e-05, "loss": 0.6066, "step": 19140 }, { "epoch": 4.57, "learning_rate": 9.926349851994337e-05, "loss": 0.6154, "step": 19150 }, { "epoch": 4.57, "learning_rate": 9.926273102339245e-05, "loss": 0.6051, "step": 19160 }, { "epoch": 4.58, "learning_rate": 9.926196313012194e-05, "loss": 0.6532, "step": 19170 }, { "epoch": 4.58, "learning_rate": 9.926119484013805e-05, "loss": 0.6598, "step": 19180 }, { "epoch": 4.58, "learning_rate": 9.926042615344696e-05, "loss": 0.6704, "step": 19190 }, { "epoch": 4.58, "learning_rate": 9.925965707005484e-05, "loss": 0.6543, "step": 19200 }, { "epoch": 4.58, "learning_rate": 9.925888758996793e-05, "loss": 0.6243, "step": 19210 }, { "epoch": 4.59, "learning_rate": 9.925811771319237e-05, "loss": 0.6081, "step": 19220 }, { "epoch": 4.59, "learning_rate": 9.92573474397344e-05, "loss": 0.5682, "step": 19230 }, { "epoch": 4.59, "learning_rate": 9.92565767696002e-05, "loss": 0.6284, "step": 19240 }, { "epoch": 4.59, "learning_rate": 9.925580570279601e-05, "loss": 0.6554, "step": 19250 }, { "epoch": 4.6, "learning_rate": 9.9255034239328e-05, "loss": 0.6374, "step": 19260 }, { "epoch": 4.6, "learning_rate": 9.925426237920241e-05, "loss": 0.6221, "step": 19270 }, { "epoch": 4.6, "learning_rate": 9.925349012242543e-05, "loss": 0.6448, "step": 19280 }, { "epoch": 4.6, "learning_rate": 9.925271746900331e-05, "loss": 0.6777, "step": 19290 }, { "epoch": 4.61, "learning_rate": 9.925194441894225e-05, "loss": 0.606, "step": 19300 }, { "epoch": 4.61, "learning_rate": 9.925117097224847e-05, "loss": 0.6588, "step": 19310 }, { "epoch": 4.61, "learning_rate": 9.925039712892821e-05, "loss": 0.5948, "step": 19320 }, { "epoch": 4.61, "learning_rate": 9.924962288898773e-05, "loss": 0.6096, "step": 19330 }, { "epoch": 4.61, "learning_rate": 9.924884825243322e-05, "loss": 0.6062, "step": 19340 }, { "epoch": 4.62, "learning_rate": 9.924807321927093e-05, "loss": 0.682, "step": 19350 }, { "epoch": 4.62, "learning_rate": 9.924729778950712e-05, "loss": 0.5797, "step": 19360 }, { "epoch": 4.62, "learning_rate": 9.924652196314801e-05, "loss": 0.6437, "step": 19370 }, { "epoch": 4.62, "learning_rate": 9.924574574019987e-05, "loss": 0.6175, "step": 19380 }, { "epoch": 4.63, "learning_rate": 9.924496912066893e-05, "loss": 0.5774, "step": 19390 }, { "epoch": 4.63, "learning_rate": 9.924419210456147e-05, "loss": 0.5638, "step": 19400 }, { "epoch": 4.63, "learning_rate": 9.924341469188372e-05, "loss": 0.6141, "step": 19410 }, { "epoch": 4.63, "learning_rate": 9.924263688264194e-05, "loss": 0.624, "step": 19420 }, { "epoch": 4.63, "learning_rate": 9.924185867684243e-05, "loss": 0.6002, "step": 19430 }, { "epoch": 4.64, "learning_rate": 9.924108007449142e-05, "loss": 0.6121, "step": 19440 }, { "epoch": 4.64, "learning_rate": 9.92403010755952e-05, "loss": 0.6159, "step": 19450 }, { "epoch": 4.64, "learning_rate": 9.923952168016004e-05, "loss": 0.6339, "step": 19460 }, { "epoch": 4.64, "learning_rate": 9.923874188819222e-05, "loss": 0.588, "step": 19470 }, { "epoch": 4.65, "learning_rate": 9.923796169969801e-05, "loss": 0.6092, "step": 19480 }, { "epoch": 4.65, "learning_rate": 9.923718111468369e-05, "loss": 0.6566, "step": 19490 }, { "epoch": 4.65, "learning_rate": 9.923640013315556e-05, "loss": 0.5959, "step": 19500 }, { "epoch": 4.65, "learning_rate": 9.923561875511989e-05, "loss": 0.6413, "step": 19510 }, { "epoch": 4.66, "learning_rate": 9.9234836980583e-05, "loss": 0.636, "step": 19520 }, { "epoch": 4.66, "learning_rate": 9.923405480955116e-05, "loss": 0.6308, "step": 19530 }, { "epoch": 4.66, "learning_rate": 9.923327224203067e-05, "loss": 0.6599, "step": 19540 }, { "epoch": 4.66, "learning_rate": 9.923248927802786e-05, "loss": 0.6305, "step": 19550 }, { "epoch": 4.66, "learning_rate": 9.923170591754901e-05, "loss": 0.6058, "step": 19560 }, { "epoch": 4.67, "learning_rate": 9.923092216060044e-05, "loss": 0.6133, "step": 19570 }, { "epoch": 4.67, "learning_rate": 9.923013800718845e-05, "loss": 0.6349, "step": 19580 }, { "epoch": 4.67, "learning_rate": 9.922935345731936e-05, "loss": 0.5852, "step": 19590 }, { "epoch": 4.67, "learning_rate": 9.922856851099951e-05, "loss": 0.6707, "step": 19600 }, { "epoch": 4.68, "learning_rate": 9.922778316823518e-05, "loss": 0.6591, "step": 19610 }, { "epoch": 4.68, "learning_rate": 9.922699742903272e-05, "loss": 0.6019, "step": 19620 }, { "epoch": 4.68, "learning_rate": 9.922621129339847e-05, "loss": 0.608, "step": 19630 }, { "epoch": 4.68, "learning_rate": 9.922542476133872e-05, "loss": 0.6574, "step": 19640 }, { "epoch": 4.69, "learning_rate": 9.922463783285985e-05, "loss": 0.6307, "step": 19650 }, { "epoch": 4.69, "learning_rate": 9.922385050796815e-05, "loss": 0.5819, "step": 19660 }, { "epoch": 4.69, "learning_rate": 9.922306278667e-05, "loss": 0.5818, "step": 19670 }, { "epoch": 4.69, "learning_rate": 9.922227466897174e-05, "loss": 0.6274, "step": 19680 }, { "epoch": 4.69, "learning_rate": 9.922148615487969e-05, "loss": 0.6107, "step": 19690 }, { "epoch": 4.7, "learning_rate": 9.922069724440021e-05, "loss": 0.5949, "step": 19700 }, { "epoch": 4.7, "learning_rate": 9.921990793753969e-05, "loss": 0.6273, "step": 19710 }, { "epoch": 4.7, "learning_rate": 9.921911823430443e-05, "loss": 0.5788, "step": 19720 }, { "epoch": 4.7, "learning_rate": 9.921832813470082e-05, "loss": 0.5939, "step": 19730 }, { "epoch": 4.71, "learning_rate": 9.921753763873523e-05, "loss": 0.6662, "step": 19740 }, { "epoch": 4.71, "learning_rate": 9.921674674641402e-05, "loss": 0.6028, "step": 19750 }, { "epoch": 4.71, "learning_rate": 9.921595545774354e-05, "loss": 0.6023, "step": 19760 }, { "epoch": 4.71, "learning_rate": 9.921516377273016e-05, "loss": 0.6354, "step": 19770 }, { "epoch": 4.71, "learning_rate": 9.92143716913803e-05, "loss": 0.5813, "step": 19780 }, { "epoch": 4.72, "learning_rate": 9.921357921370029e-05, "loss": 0.6114, "step": 19790 }, { "epoch": 4.72, "learning_rate": 9.921278633969655e-05, "loss": 0.6317, "step": 19800 }, { "epoch": 4.72, "learning_rate": 9.921199306937544e-05, "loss": 0.6158, "step": 19810 }, { "epoch": 4.72, "learning_rate": 9.921119940274335e-05, "loss": 0.6277, "step": 19820 }, { "epoch": 4.73, "learning_rate": 9.921040533980669e-05, "loss": 0.6088, "step": 19830 }, { "epoch": 4.73, "learning_rate": 9.920961088057184e-05, "loss": 0.6109, "step": 19840 }, { "epoch": 4.73, "learning_rate": 9.920881602504519e-05, "loss": 0.5992, "step": 19850 }, { "epoch": 4.73, "learning_rate": 9.920802077323314e-05, "loss": 0.6285, "step": 19860 }, { "epoch": 4.74, "learning_rate": 9.920722512514213e-05, "loss": 0.6084, "step": 19870 }, { "epoch": 4.74, "learning_rate": 9.920642908077853e-05, "loss": 0.6265, "step": 19880 }, { "epoch": 4.74, "learning_rate": 9.920563264014877e-05, "loss": 0.6018, "step": 19890 }, { "epoch": 4.74, "learning_rate": 9.920483580325925e-05, "loss": 0.6654, "step": 19900 }, { "epoch": 4.74, "learning_rate": 9.92040385701164e-05, "loss": 0.5931, "step": 19910 }, { "epoch": 4.75, "learning_rate": 9.920324094072663e-05, "loss": 0.6254, "step": 19920 }, { "epoch": 4.75, "learning_rate": 9.920244291509637e-05, "loss": 0.6409, "step": 19930 }, { "epoch": 4.75, "learning_rate": 9.920164449323203e-05, "loss": 0.589, "step": 19940 }, { "epoch": 4.75, "learning_rate": 9.920084567514008e-05, "loss": 0.6315, "step": 19950 }, { "epoch": 4.76, "learning_rate": 9.92000464608269e-05, "loss": 0.5961, "step": 19960 }, { "epoch": 4.76, "learning_rate": 9.919924685029897e-05, "loss": 0.5929, "step": 19970 }, { "epoch": 4.76, "learning_rate": 9.919844684356272e-05, "loss": 0.6176, "step": 19980 }, { "epoch": 4.76, "learning_rate": 9.919764644062457e-05, "loss": 0.6242, "step": 19990 }, { "epoch": 4.77, "learning_rate": 9.919684564149099e-05, "loss": 0.5678, "step": 20000 }, { "epoch": 4.77, "learning_rate": 9.919604444616842e-05, "loss": 0.5812, "step": 20010 }, { "epoch": 4.77, "learning_rate": 9.91952428546633e-05, "loss": 0.6424, "step": 20020 }, { "epoch": 4.77, "learning_rate": 9.919444086698211e-05, "loss": 0.6247, "step": 20030 }, { "epoch": 4.77, "learning_rate": 9.91936384831313e-05, "loss": 0.6076, "step": 20040 }, { "epoch": 4.78, "learning_rate": 9.919283570311731e-05, "loss": 0.5852, "step": 20050 }, { "epoch": 4.78, "learning_rate": 9.919203252694664e-05, "loss": 0.5919, "step": 20060 }, { "epoch": 4.78, "learning_rate": 9.919122895462573e-05, "loss": 0.6139, "step": 20070 }, { "epoch": 4.78, "learning_rate": 9.919042498616107e-05, "loss": 0.6149, "step": 20080 }, { "epoch": 4.79, "learning_rate": 9.918962062155912e-05, "loss": 0.5771, "step": 20090 }, { "epoch": 4.79, "learning_rate": 9.918881586082637e-05, "loss": 0.5877, "step": 20100 }, { "epoch": 4.79, "learning_rate": 9.918801070396929e-05, "loss": 0.6262, "step": 20110 }, { "epoch": 4.79, "learning_rate": 9.918720515099436e-05, "loss": 0.5988, "step": 20120 }, { "epoch": 4.79, "learning_rate": 9.918639920190808e-05, "loss": 0.5627, "step": 20130 }, { "epoch": 4.8, "learning_rate": 9.918559285671696e-05, "loss": 0.6098, "step": 20140 }, { "epoch": 4.8, "learning_rate": 9.918478611542745e-05, "loss": 0.6047, "step": 20150 }, { "epoch": 4.8, "learning_rate": 9.918397897804607e-05, "loss": 0.5794, "step": 20160 }, { "epoch": 4.8, "learning_rate": 9.918317144457932e-05, "loss": 0.6213, "step": 20170 }, { "epoch": 4.81, "learning_rate": 9.91823635150337e-05, "loss": 0.5861, "step": 20180 }, { "epoch": 4.81, "learning_rate": 9.918155518941569e-05, "loss": 0.5691, "step": 20190 }, { "epoch": 4.81, "learning_rate": 9.918074646773186e-05, "loss": 0.5795, "step": 20200 }, { "epoch": 4.81, "learning_rate": 9.917993734998868e-05, "loss": 0.6364, "step": 20210 }, { "epoch": 4.82, "learning_rate": 9.917912783619267e-05, "loss": 0.6011, "step": 20220 }, { "epoch": 4.82, "learning_rate": 9.917831792635037e-05, "loss": 0.6186, "step": 20230 }, { "epoch": 4.82, "learning_rate": 9.917750762046827e-05, "loss": 0.6283, "step": 20240 }, { "epoch": 4.82, "learning_rate": 9.917669691855291e-05, "loss": 0.6108, "step": 20250 }, { "epoch": 4.82, "learning_rate": 9.917588582061083e-05, "loss": 0.6352, "step": 20260 }, { "epoch": 4.83, "learning_rate": 9.917507432664854e-05, "loss": 0.5886, "step": 20270 }, { "epoch": 4.83, "learning_rate": 9.917426243667261e-05, "loss": 0.6245, "step": 20280 }, { "epoch": 4.83, "learning_rate": 9.917345015068953e-05, "loss": 0.61, "step": 20290 }, { "epoch": 4.83, "learning_rate": 9.917263746870589e-05, "loss": 0.5765, "step": 20300 }, { "epoch": 4.84, "learning_rate": 9.91718243907282e-05, "loss": 0.6456, "step": 20310 }, { "epoch": 4.84, "learning_rate": 9.917101091676302e-05, "loss": 0.5966, "step": 20320 }, { "epoch": 4.84, "learning_rate": 9.917019704681689e-05, "loss": 0.5925, "step": 20330 }, { "epoch": 4.84, "learning_rate": 9.916938278089639e-05, "loss": 0.5625, "step": 20340 }, { "epoch": 4.85, "learning_rate": 9.916856811900805e-05, "loss": 0.5787, "step": 20350 }, { "epoch": 4.85, "learning_rate": 9.916775306115847e-05, "loss": 0.6373, "step": 20360 }, { "epoch": 4.85, "learning_rate": 9.916693760735416e-05, "loss": 0.5986, "step": 20370 }, { "epoch": 4.85, "learning_rate": 9.916612175760171e-05, "loss": 0.5673, "step": 20380 }, { "epoch": 4.85, "learning_rate": 9.91653055119077e-05, "loss": 0.6464, "step": 20390 }, { "epoch": 4.86, "learning_rate": 9.916448887027872e-05, "loss": 0.5858, "step": 20400 }, { "epoch": 4.86, "learning_rate": 9.916367183272129e-05, "loss": 0.6424, "step": 20410 }, { "epoch": 4.86, "learning_rate": 9.916285439924204e-05, "loss": 0.6176, "step": 20420 }, { "epoch": 4.86, "learning_rate": 9.916203656984754e-05, "loss": 0.5863, "step": 20430 }, { "epoch": 4.87, "learning_rate": 9.916121834454436e-05, "loss": 0.5437, "step": 20440 }, { "epoch": 4.87, "learning_rate": 9.91603997233391e-05, "loss": 0.5968, "step": 20450 }, { "epoch": 4.87, "learning_rate": 9.915958070623836e-05, "loss": 0.5997, "step": 20460 }, { "epoch": 4.87, "learning_rate": 9.915876129324875e-05, "loss": 0.5964, "step": 20470 }, { "epoch": 4.87, "learning_rate": 9.915794148437683e-05, "loss": 0.6192, "step": 20480 }, { "epoch": 4.88, "learning_rate": 9.915712127962922e-05, "loss": 0.5737, "step": 20490 }, { "epoch": 4.88, "learning_rate": 9.915630067901252e-05, "loss": 0.6094, "step": 20500 }, { "epoch": 4.88, "learning_rate": 9.915547968253335e-05, "loss": 0.6351, "step": 20510 }, { "epoch": 4.88, "learning_rate": 9.915465829019832e-05, "loss": 0.597, "step": 20520 }, { "epoch": 4.89, "learning_rate": 9.915383650201404e-05, "loss": 0.5493, "step": 20530 }, { "epoch": 4.89, "learning_rate": 9.915301431798711e-05, "loss": 0.5635, "step": 20540 }, { "epoch": 4.89, "learning_rate": 9.91521917381242e-05, "loss": 0.6245, "step": 20550 }, { "epoch": 4.89, "learning_rate": 9.915136876243189e-05, "loss": 0.6152, "step": 20560 }, { "epoch": 4.9, "learning_rate": 9.915054539091682e-05, "loss": 0.601, "step": 20570 }, { "epoch": 4.9, "learning_rate": 9.914972162358562e-05, "loss": 0.6241, "step": 20580 }, { "epoch": 4.9, "learning_rate": 9.914889746044493e-05, "loss": 0.5405, "step": 20590 }, { "epoch": 4.9, "learning_rate": 9.914807290150138e-05, "loss": 0.6659, "step": 20600 }, { "epoch": 4.9, "learning_rate": 9.914724794676162e-05, "loss": 0.6098, "step": 20610 }, { "epoch": 4.91, "learning_rate": 9.914642259623228e-05, "loss": 0.6184, "step": 20620 }, { "epoch": 4.91, "learning_rate": 9.914559684992002e-05, "loss": 0.603, "step": 20630 }, { "epoch": 4.91, "learning_rate": 9.914477070783148e-05, "loss": 0.5952, "step": 20640 }, { "epoch": 4.91, "learning_rate": 9.914394416997331e-05, "loss": 0.6203, "step": 20650 }, { "epoch": 4.92, "learning_rate": 9.914311723635219e-05, "loss": 0.6099, "step": 20660 }, { "epoch": 4.92, "learning_rate": 9.914228990697474e-05, "loss": 0.598, "step": 20670 }, { "epoch": 4.92, "learning_rate": 9.914146218184766e-05, "loss": 0.5849, "step": 20680 }, { "epoch": 4.92, "learning_rate": 9.91406340609776e-05, "loss": 0.5969, "step": 20690 }, { "epoch": 4.93, "learning_rate": 9.913980554437124e-05, "loss": 0.5729, "step": 20700 }, { "epoch": 4.93, "learning_rate": 9.913897663203522e-05, "loss": 0.5387, "step": 20710 }, { "epoch": 4.93, "learning_rate": 9.913814732397623e-05, "loss": 0.5693, "step": 20720 }, { "epoch": 4.93, "learning_rate": 9.913731762020098e-05, "loss": 0.6148, "step": 20730 }, { "epoch": 4.93, "learning_rate": 9.913648752071612e-05, "loss": 0.6155, "step": 20740 }, { "epoch": 4.94, "learning_rate": 9.913565702552835e-05, "loss": 0.5679, "step": 20750 }, { "epoch": 4.94, "learning_rate": 9.913482613464434e-05, "loss": 0.6023, "step": 20760 }, { "epoch": 4.94, "learning_rate": 9.91339948480708e-05, "loss": 0.6045, "step": 20770 }, { "epoch": 4.94, "learning_rate": 9.91331631658144e-05, "loss": 0.5564, "step": 20780 }, { "epoch": 4.95, "learning_rate": 9.913233108788187e-05, "loss": 0.6267, "step": 20790 }, { "epoch": 4.95, "learning_rate": 9.913149861427988e-05, "loss": 0.5981, "step": 20800 }, { "epoch": 4.95, "learning_rate": 9.913066574501515e-05, "loss": 0.5671, "step": 20810 }, { "epoch": 5.0, "learning_rate": 9.91298324800944e-05, "loss": 0.6231, "step": 20820 }, { "epoch": 5.0, "learning_rate": 9.912899881952433e-05, "loss": 0.5839, "step": 20830 }, { "epoch": 5.01, "learning_rate": 9.912816476331164e-05, "loss": 0.5699, "step": 20840 }, { "epoch": 5.01, "learning_rate": 9.912733031146305e-05, "loss": 0.586, "step": 20850 }, { "epoch": 5.01, "learning_rate": 9.91264954639853e-05, "loss": 0.5771, "step": 20860 }, { "epoch": 5.01, "learning_rate": 9.912566022088508e-05, "loss": 0.5692, "step": 20870 }, { "epoch": 5.01, "learning_rate": 9.912482458216916e-05, "loss": 0.5928, "step": 20880 }, { "epoch": 5.02, "learning_rate": 9.912398854784423e-05, "loss": 0.5834, "step": 20890 }, { "epoch": 5.02, "learning_rate": 9.912315211791702e-05, "loss": 0.5497, "step": 20900 }, { "epoch": 5.02, "learning_rate": 9.912231529239432e-05, "loss": 0.64, "step": 20910 }, { "epoch": 5.02, "learning_rate": 9.912147807128283e-05, "loss": 0.58, "step": 20920 }, { "epoch": 5.03, "learning_rate": 9.912064045458928e-05, "loss": 0.5951, "step": 20930 }, { "epoch": 5.03, "learning_rate": 9.911980244232043e-05, "loss": 0.6342, "step": 20940 }, { "epoch": 5.03, "learning_rate": 9.911896403448304e-05, "loss": 0.5985, "step": 20950 }, { "epoch": 5.03, "learning_rate": 9.911812523108384e-05, "loss": 0.608, "step": 20960 }, { "epoch": 5.04, "learning_rate": 9.91172860321296e-05, "loss": 0.5438, "step": 20970 }, { "epoch": 5.04, "learning_rate": 9.911644643762708e-05, "loss": 0.5759, "step": 20980 }, { "epoch": 5.04, "learning_rate": 9.911560644758303e-05, "loss": 0.5634, "step": 20990 }, { "epoch": 5.04, "learning_rate": 9.911476606200422e-05, "loss": 0.5194, "step": 21000 }, { "epoch": 5.04, "learning_rate": 9.911392528089742e-05, "loss": 0.5791, "step": 21010 }, { "epoch": 5.05, "learning_rate": 9.91130841042694e-05, "loss": 0.5328, "step": 21020 }, { "epoch": 5.05, "learning_rate": 9.911224253212695e-05, "loss": 0.5937, "step": 21030 }, { "epoch": 5.05, "learning_rate": 9.91114005644768e-05, "loss": 0.5889, "step": 21040 }, { "epoch": 5.05, "learning_rate": 9.911055820132577e-05, "loss": 0.5757, "step": 21050 }, { "epoch": 5.06, "learning_rate": 9.910971544268065e-05, "loss": 0.5638, "step": 21060 }, { "epoch": 5.06, "learning_rate": 9.910887228854821e-05, "loss": 0.5558, "step": 21070 }, { "epoch": 5.06, "learning_rate": 9.910802873893524e-05, "loss": 0.5652, "step": 21080 }, { "epoch": 5.06, "learning_rate": 9.91071847938485e-05, "loss": 0.5229, "step": 21090 }, { "epoch": 5.07, "learning_rate": 9.910634045329485e-05, "loss": 0.6113, "step": 21100 }, { "epoch": 5.07, "learning_rate": 9.910549571728107e-05, "loss": 0.5656, "step": 21110 }, { "epoch": 5.07, "learning_rate": 9.910465058581395e-05, "loss": 0.5772, "step": 21120 }, { "epoch": 5.07, "learning_rate": 9.910380505890028e-05, "loss": 0.5761, "step": 21130 }, { "epoch": 5.07, "learning_rate": 9.91029591365469e-05, "loss": 0.6045, "step": 21140 }, { "epoch": 5.08, "learning_rate": 9.910211281876063e-05, "loss": 0.558, "step": 21150 }, { "epoch": 5.08, "learning_rate": 9.910126610554824e-05, "loss": 0.5991, "step": 21160 }, { "epoch": 5.08, "learning_rate": 9.910041899691657e-05, "loss": 0.5898, "step": 21170 }, { "epoch": 5.08, "learning_rate": 9.909957149287248e-05, "loss": 0.6199, "step": 21180 }, { "epoch": 5.09, "learning_rate": 9.909872359342273e-05, "loss": 0.6071, "step": 21190 }, { "epoch": 5.09, "learning_rate": 9.909787529857421e-05, "loss": 0.5557, "step": 21200 }, { "epoch": 5.09, "learning_rate": 9.90970266083337e-05, "loss": 0.5797, "step": 21210 }, { "epoch": 5.09, "learning_rate": 9.909617752270806e-05, "loss": 0.6005, "step": 21220 }, { "epoch": 5.09, "learning_rate": 9.909532804170412e-05, "loss": 0.5463, "step": 21230 }, { "epoch": 5.1, "learning_rate": 9.909447816532874e-05, "loss": 0.5995, "step": 21240 }, { "epoch": 5.1, "learning_rate": 9.909362789358873e-05, "loss": 0.5869, "step": 21250 }, { "epoch": 5.1, "learning_rate": 9.909277722649098e-05, "loss": 0.5526, "step": 21260 }, { "epoch": 5.1, "learning_rate": 9.90919261640423e-05, "loss": 0.5332, "step": 21270 }, { "epoch": 5.11, "learning_rate": 9.909107470624956e-05, "loss": 0.5611, "step": 21280 }, { "epoch": 5.11, "learning_rate": 9.909022285311964e-05, "loss": 0.6134, "step": 21290 }, { "epoch": 5.11, "learning_rate": 9.908937060465935e-05, "loss": 0.5781, "step": 21300 }, { "epoch": 5.11, "learning_rate": 9.908851796087559e-05, "loss": 0.5537, "step": 21310 }, { "epoch": 5.12, "learning_rate": 9.908766492177524e-05, "loss": 0.5453, "step": 21320 }, { "epoch": 5.12, "learning_rate": 9.908681148736512e-05, "loss": 0.5847, "step": 21330 }, { "epoch": 5.12, "learning_rate": 9.908595765765214e-05, "loss": 0.5738, "step": 21340 }, { "epoch": 5.12, "learning_rate": 9.908510343264316e-05, "loss": 0.5363, "step": 21350 }, { "epoch": 5.12, "learning_rate": 9.908424881234508e-05, "loss": 0.5654, "step": 21360 }, { "epoch": 5.13, "learning_rate": 9.908339379676474e-05, "loss": 0.5596, "step": 21370 }, { "epoch": 5.13, "learning_rate": 9.908253838590908e-05, "loss": 0.6036, "step": 21380 }, { "epoch": 5.13, "learning_rate": 9.908168257978497e-05, "loss": 0.5806, "step": 21390 }, { "epoch": 5.13, "learning_rate": 9.908082637839926e-05, "loss": 0.5591, "step": 21400 }, { "epoch": 5.14, "learning_rate": 9.90799697817589e-05, "loss": 0.6056, "step": 21410 }, { "epoch": 5.14, "learning_rate": 9.907911278987076e-05, "loss": 0.5971, "step": 21420 }, { "epoch": 5.14, "learning_rate": 9.907825540274176e-05, "loss": 0.5354, "step": 21430 }, { "epoch": 5.14, "learning_rate": 9.907739762037879e-05, "loss": 0.5664, "step": 21440 }, { "epoch": 5.15, "learning_rate": 9.907653944278876e-05, "loss": 0.5876, "step": 21450 }, { "epoch": 5.15, "learning_rate": 9.907568086997858e-05, "loss": 0.5883, "step": 21460 }, { "epoch": 5.15, "learning_rate": 9.907482190195517e-05, "loss": 0.563, "step": 21470 }, { "epoch": 5.15, "learning_rate": 9.907396253872543e-05, "loss": 0.541, "step": 21480 }, { "epoch": 5.15, "learning_rate": 9.907310278029631e-05, "loss": 0.5599, "step": 21490 }, { "epoch": 5.16, "learning_rate": 9.907224262667472e-05, "loss": 0.6037, "step": 21500 }, { "epoch": 5.16, "learning_rate": 9.907138207786757e-05, "loss": 0.5506, "step": 21510 }, { "epoch": 5.16, "learning_rate": 9.907052113388183e-05, "loss": 0.5895, "step": 21520 }, { "epoch": 5.16, "learning_rate": 9.906965979472437e-05, "loss": 0.5613, "step": 21530 }, { "epoch": 5.17, "learning_rate": 9.906879806040221e-05, "loss": 0.5416, "step": 21540 }, { "epoch": 5.17, "learning_rate": 9.906793593092222e-05, "loss": 0.5988, "step": 21550 }, { "epoch": 5.17, "learning_rate": 9.906707340629137e-05, "loss": 0.5821, "step": 21560 }, { "epoch": 5.17, "learning_rate": 9.90662104865166e-05, "loss": 0.5647, "step": 21570 }, { "epoch": 5.17, "learning_rate": 9.906534717160487e-05, "loss": 0.618, "step": 21580 }, { "epoch": 5.18, "learning_rate": 9.906448346156313e-05, "loss": 0.5585, "step": 21590 }, { "epoch": 5.18, "learning_rate": 9.906361935639832e-05, "loss": 0.5635, "step": 21600 }, { "epoch": 5.18, "learning_rate": 9.906275485611743e-05, "loss": 0.5686, "step": 21610 }, { "epoch": 5.18, "learning_rate": 9.906188996072738e-05, "loss": 0.5632, "step": 21620 }, { "epoch": 5.19, "learning_rate": 9.906102467023515e-05, "loss": 0.5664, "step": 21630 }, { "epoch": 5.19, "learning_rate": 9.906015898464773e-05, "loss": 0.5578, "step": 21640 }, { "epoch": 5.19, "learning_rate": 9.905929290397206e-05, "loss": 0.5806, "step": 21650 }, { "epoch": 5.19, "learning_rate": 9.905842642821517e-05, "loss": 0.527, "step": 21660 }, { "epoch": 5.2, "learning_rate": 9.905755955738396e-05, "loss": 0.5837, "step": 21670 }, { "epoch": 5.2, "learning_rate": 9.905669229148546e-05, "loss": 0.616, "step": 21680 }, { "epoch": 5.2, "learning_rate": 9.905582463052664e-05, "loss": 0.5669, "step": 21690 }, { "epoch": 5.2, "learning_rate": 9.905495657451451e-05, "loss": 0.5751, "step": 21700 }, { "epoch": 5.2, "learning_rate": 9.905408812345605e-05, "loss": 0.5769, "step": 21710 }, { "epoch": 5.21, "learning_rate": 9.905321927735822e-05, "loss": 0.5751, "step": 21720 }, { "epoch": 5.21, "learning_rate": 9.905235003622804e-05, "loss": 0.5577, "step": 21730 }, { "epoch": 5.21, "learning_rate": 9.905148040007253e-05, "loss": 0.5542, "step": 21740 }, { "epoch": 5.21, "learning_rate": 9.905061036889868e-05, "loss": 0.5656, "step": 21750 }, { "epoch": 5.22, "learning_rate": 9.904973994271349e-05, "loss": 0.551, "step": 21760 }, { "epoch": 5.22, "learning_rate": 9.904886912152395e-05, "loss": 0.5867, "step": 21770 }, { "epoch": 5.22, "learning_rate": 9.904799790533711e-05, "loss": 0.5867, "step": 21780 }, { "epoch": 5.22, "learning_rate": 9.904712629415997e-05, "loss": 0.5585, "step": 21790 }, { "epoch": 5.23, "learning_rate": 9.904625428799957e-05, "loss": 0.5424, "step": 21800 }, { "epoch": 5.23, "learning_rate": 9.90453818868629e-05, "loss": 0.5835, "step": 21810 }, { "epoch": 5.23, "learning_rate": 9.904450909075699e-05, "loss": 0.5752, "step": 21820 }, { "epoch": 5.23, "learning_rate": 9.904363589968888e-05, "loss": 0.5336, "step": 21830 }, { "epoch": 5.23, "learning_rate": 9.90427623136656e-05, "loss": 0.554, "step": 21840 }, { "epoch": 5.24, "learning_rate": 9.904188833269419e-05, "loss": 0.5439, "step": 21850 }, { "epoch": 5.24, "learning_rate": 9.904101395678167e-05, "loss": 0.5416, "step": 21860 }, { "epoch": 5.24, "learning_rate": 9.904013918593512e-05, "loss": 0.5387, "step": 21870 }, { "epoch": 5.24, "learning_rate": 9.903926402016153e-05, "loss": 0.6001, "step": 21880 }, { "epoch": 5.25, "learning_rate": 9.903838845946798e-05, "loss": 0.5462, "step": 21890 }, { "epoch": 5.25, "learning_rate": 9.903751250386153e-05, "loss": 0.6156, "step": 21900 }, { "epoch": 5.25, "learning_rate": 9.903663615334921e-05, "loss": 0.5557, "step": 21910 }, { "epoch": 5.25, "learning_rate": 9.90357594079381e-05, "loss": 0.5185, "step": 21920 }, { "epoch": 5.25, "learning_rate": 9.903488226763524e-05, "loss": 0.5981, "step": 21930 }, { "epoch": 5.26, "learning_rate": 9.903400473244772e-05, "loss": 0.5994, "step": 21940 }, { "epoch": 5.26, "learning_rate": 9.903312680238258e-05, "loss": 0.5254, "step": 21950 }, { "epoch": 5.26, "learning_rate": 9.90322484774469e-05, "loss": 0.5753, "step": 21960 }, { "epoch": 5.26, "learning_rate": 9.903136975764775e-05, "loss": 0.5624, "step": 21970 }, { "epoch": 5.27, "learning_rate": 9.903049064299221e-05, "loss": 0.5384, "step": 21980 }, { "epoch": 5.27, "learning_rate": 9.902961113348737e-05, "loss": 0.5631, "step": 21990 }, { "epoch": 5.27, "learning_rate": 9.90287312291403e-05, "loss": 0.5678, "step": 22000 }, { "epoch": 5.27, "learning_rate": 9.902785092995807e-05, "loss": 0.5923, "step": 22010 }, { "epoch": 5.28, "learning_rate": 9.902697023594781e-05, "loss": 0.57, "step": 22020 }, { "epoch": 5.28, "learning_rate": 9.902608914711658e-05, "loss": 0.5383, "step": 22030 }, { "epoch": 5.28, "learning_rate": 9.90252076634715e-05, "loss": 0.5786, "step": 22040 }, { "epoch": 5.28, "learning_rate": 9.902432578501963e-05, "loss": 0.5439, "step": 22050 }, { "epoch": 5.28, "learning_rate": 9.902344351176811e-05, "loss": 0.5705, "step": 22060 }, { "epoch": 5.29, "learning_rate": 9.902256084372403e-05, "loss": 0.5786, "step": 22070 }, { "epoch": 5.29, "learning_rate": 9.90216777808945e-05, "loss": 0.5746, "step": 22080 }, { "epoch": 5.29, "learning_rate": 9.902079432328664e-05, "loss": 0.6407, "step": 22090 }, { "epoch": 5.29, "learning_rate": 9.901991047090755e-05, "loss": 0.5792, "step": 22100 }, { "epoch": 5.3, "learning_rate": 9.901902622376434e-05, "loss": 0.6131, "step": 22110 }, { "epoch": 5.3, "learning_rate": 9.901814158186416e-05, "loss": 0.609, "step": 22120 }, { "epoch": 5.3, "learning_rate": 9.901725654521411e-05, "loss": 0.5538, "step": 22130 }, { "epoch": 5.3, "learning_rate": 9.901637111382133e-05, "loss": 0.5955, "step": 22140 }, { "epoch": 5.31, "learning_rate": 9.901548528769294e-05, "loss": 0.5506, "step": 22150 }, { "epoch": 5.31, "learning_rate": 9.901459906683608e-05, "loss": 0.5796, "step": 22160 }, { "epoch": 5.31, "learning_rate": 9.90137124512579e-05, "loss": 0.5637, "step": 22170 }, { "epoch": 5.31, "learning_rate": 9.901282544096552e-05, "loss": 0.6011, "step": 22180 }, { "epoch": 5.31, "learning_rate": 9.901193803596609e-05, "loss": 0.5745, "step": 22190 }, { "epoch": 5.32, "learning_rate": 9.901105023626676e-05, "loss": 0.6157, "step": 22200 }, { "epoch": 5.32, "learning_rate": 9.901016204187466e-05, "loss": 0.5792, "step": 22210 }, { "epoch": 5.32, "learning_rate": 9.900927345279697e-05, "loss": 0.6338, "step": 22220 }, { "epoch": 5.32, "learning_rate": 9.900838446904084e-05, "loss": 0.5927, "step": 22230 }, { "epoch": 5.33, "learning_rate": 9.900749509061341e-05, "loss": 0.5416, "step": 22240 }, { "epoch": 5.33, "learning_rate": 9.900660531752186e-05, "loss": 0.5298, "step": 22250 }, { "epoch": 5.33, "learning_rate": 9.900571514977336e-05, "loss": 0.5648, "step": 22260 }, { "epoch": 5.33, "learning_rate": 9.900482458737507e-05, "loss": 0.5485, "step": 22270 }, { "epoch": 5.33, "learning_rate": 9.900393363033415e-05, "loss": 0.5699, "step": 22280 }, { "epoch": 5.34, "learning_rate": 9.90030422786578e-05, "loss": 0.5766, "step": 22290 }, { "epoch": 5.34, "learning_rate": 9.900215053235318e-05, "loss": 0.534, "step": 22300 }, { "epoch": 5.34, "learning_rate": 9.900125839142747e-05, "loss": 0.5532, "step": 22310 }, { "epoch": 5.34, "learning_rate": 9.900036585588788e-05, "loss": 0.5523, "step": 22320 }, { "epoch": 5.35, "learning_rate": 9.899947292574157e-05, "loss": 0.6096, "step": 22330 }, { "epoch": 5.35, "learning_rate": 9.899857960099573e-05, "loss": 0.5532, "step": 22340 }, { "epoch": 5.35, "learning_rate": 9.899768588165757e-05, "loss": 0.578, "step": 22350 }, { "epoch": 5.35, "learning_rate": 9.899679176773429e-05, "loss": 0.562, "step": 22360 }, { "epoch": 5.36, "learning_rate": 9.899589725923305e-05, "loss": 0.5621, "step": 22370 }, { "epoch": 5.36, "learning_rate": 9.899500235616112e-05, "loss": 0.5565, "step": 22380 }, { "epoch": 5.36, "learning_rate": 9.899410705852567e-05, "loss": 0.5749, "step": 22390 }, { "epoch": 5.36, "learning_rate": 9.899321136633389e-05, "loss": 0.5509, "step": 22400 }, { "epoch": 5.36, "learning_rate": 9.899231527959303e-05, "loss": 0.5824, "step": 22410 }, { "epoch": 5.37, "learning_rate": 9.899141879831028e-05, "loss": 0.5826, "step": 22420 }, { "epoch": 5.37, "learning_rate": 9.89905219224929e-05, "loss": 0.5508, "step": 22430 }, { "epoch": 5.37, "learning_rate": 9.898962465214805e-05, "loss": 0.5314, "step": 22440 }, { "epoch": 5.37, "learning_rate": 9.8988726987283e-05, "loss": 0.5432, "step": 22450 }, { "epoch": 5.38, "learning_rate": 9.898782892790497e-05, "loss": 0.571, "step": 22460 }, { "epoch": 5.38, "learning_rate": 9.898693047402119e-05, "loss": 0.5797, "step": 22470 }, { "epoch": 5.38, "learning_rate": 9.898603162563889e-05, "loss": 0.5738, "step": 22480 }, { "epoch": 5.38, "learning_rate": 9.898513238276533e-05, "loss": 0.5864, "step": 22490 }, { "epoch": 5.39, "learning_rate": 9.898423274540772e-05, "loss": 0.59, "step": 22500 }, { "epoch": 5.39, "learning_rate": 9.898333271357332e-05, "loss": 0.5648, "step": 22510 }, { "epoch": 5.39, "learning_rate": 9.89824322872694e-05, "loss": 0.5526, "step": 22520 }, { "epoch": 5.39, "learning_rate": 9.898153146650318e-05, "loss": 0.5694, "step": 22530 }, { "epoch": 5.39, "learning_rate": 9.898063025128191e-05, "loss": 0.5366, "step": 22540 }, { "epoch": 5.4, "learning_rate": 9.897972864161288e-05, "loss": 0.5614, "step": 22550 }, { "epoch": 5.4, "learning_rate": 9.897882663750333e-05, "loss": 0.564, "step": 22560 }, { "epoch": 5.4, "learning_rate": 9.897792423896052e-05, "loss": 0.5881, "step": 22570 }, { "epoch": 5.4, "learning_rate": 9.897702144599172e-05, "loss": 0.5808, "step": 22580 }, { "epoch": 5.41, "learning_rate": 9.897611825860423e-05, "loss": 0.5306, "step": 22590 }, { "epoch": 5.41, "learning_rate": 9.897521467680527e-05, "loss": 0.6015, "step": 22600 }, { "epoch": 5.41, "learning_rate": 9.897431070060217e-05, "loss": 0.5486, "step": 22610 }, { "epoch": 5.41, "learning_rate": 9.897340633000216e-05, "loss": 0.5703, "step": 22620 }, { "epoch": 5.41, "learning_rate": 9.897250156501256e-05, "loss": 0.5884, "step": 22630 }, { "epoch": 5.42, "learning_rate": 9.897159640564064e-05, "loss": 0.5397, "step": 22640 }, { "epoch": 5.42, "learning_rate": 9.89706908518937e-05, "loss": 0.5926, "step": 22650 }, { "epoch": 5.42, "learning_rate": 9.896978490377902e-05, "loss": 0.6206, "step": 22660 }, { "epoch": 5.42, "learning_rate": 9.89688785613039e-05, "loss": 0.5926, "step": 22670 }, { "epoch": 5.43, "learning_rate": 9.896797182447563e-05, "loss": 0.5449, "step": 22680 }, { "epoch": 5.43, "learning_rate": 9.896706469330155e-05, "loss": 0.535, "step": 22690 }, { "epoch": 5.43, "learning_rate": 9.896615716778892e-05, "loss": 0.5254, "step": 22700 }, { "epoch": 5.43, "learning_rate": 9.896524924794506e-05, "loss": 0.5373, "step": 22710 }, { "epoch": 5.44, "learning_rate": 9.896434093377731e-05, "loss": 0.5667, "step": 22720 }, { "epoch": 5.44, "learning_rate": 9.896343222529295e-05, "loss": 0.5711, "step": 22730 }, { "epoch": 5.44, "learning_rate": 9.89625231224993e-05, "loss": 0.5546, "step": 22740 }, { "epoch": 5.44, "learning_rate": 9.896161362540371e-05, "loss": 0.5472, "step": 22750 }, { "epoch": 5.44, "learning_rate": 9.896070373401347e-05, "loss": 0.5809, "step": 22760 }, { "epoch": 5.45, "learning_rate": 9.895979344833594e-05, "loss": 0.586, "step": 22770 }, { "epoch": 5.45, "learning_rate": 9.895888276837841e-05, "loss": 0.5529, "step": 22780 }, { "epoch": 5.45, "learning_rate": 9.895797169414826e-05, "loss": 0.573, "step": 22790 }, { "epoch": 5.45, "learning_rate": 9.895706022565282e-05, "loss": 0.5534, "step": 22800 }, { "epoch": 5.46, "learning_rate": 9.895614836289936e-05, "loss": 0.548, "step": 22810 }, { "epoch": 5.46, "learning_rate": 9.895523610589532e-05, "loss": 0.5915, "step": 22820 }, { "epoch": 5.46, "learning_rate": 9.8954323454648e-05, "loss": 0.5791, "step": 22830 }, { "epoch": 5.46, "learning_rate": 9.895341040916475e-05, "loss": 0.5375, "step": 22840 }, { "epoch": 5.47, "learning_rate": 9.895249696945292e-05, "loss": 0.5681, "step": 22850 }, { "epoch": 5.47, "learning_rate": 9.895158313551989e-05, "loss": 0.5609, "step": 22860 }, { "epoch": 5.47, "learning_rate": 9.895066890737299e-05, "loss": 0.5576, "step": 22870 }, { "epoch": 5.47, "learning_rate": 9.894975428501961e-05, "loss": 0.5663, "step": 22880 }, { "epoch": 5.47, "learning_rate": 9.894883926846709e-05, "loss": 0.5244, "step": 22890 }, { "epoch": 5.48, "learning_rate": 9.89479238577228e-05, "loss": 0.5623, "step": 22900 }, { "epoch": 5.48, "learning_rate": 9.894700805279414e-05, "loss": 0.5657, "step": 22910 }, { "epoch": 5.48, "learning_rate": 9.894609185368846e-05, "loss": 0.5258, "step": 22920 }, { "epoch": 5.48, "learning_rate": 9.894517526041314e-05, "loss": 0.538, "step": 22930 }, { "epoch": 5.49, "learning_rate": 9.894425827297558e-05, "loss": 0.541, "step": 22940 }, { "epoch": 5.49, "learning_rate": 9.894334089138313e-05, "loss": 0.5869, "step": 22950 }, { "epoch": 5.49, "learning_rate": 9.894242311564322e-05, "loss": 0.4942, "step": 22960 }, { "epoch": 5.49, "learning_rate": 9.89415049457632e-05, "loss": 0.5622, "step": 22970 }, { "epoch": 5.49, "learning_rate": 9.894058638175049e-05, "loss": 0.5136, "step": 22980 }, { "epoch": 5.5, "learning_rate": 9.893966742361248e-05, "loss": 0.579, "step": 22990 }, { "epoch": 5.5, "learning_rate": 9.893874807135658e-05, "loss": 0.5891, "step": 23000 }, { "epoch": 5.5, "learning_rate": 9.893782832499017e-05, "loss": 0.521, "step": 23010 }, { "epoch": 5.5, "learning_rate": 9.89369081845207e-05, "loss": 0.5525, "step": 23020 }, { "epoch": 5.51, "learning_rate": 9.893598764995553e-05, "loss": 0.55, "step": 23030 }, { "epoch": 5.51, "learning_rate": 9.893506672130211e-05, "loss": 0.566, "step": 23040 }, { "epoch": 5.51, "learning_rate": 9.893414539856782e-05, "loss": 0.5584, "step": 23050 }, { "epoch": 5.51, "learning_rate": 9.893322368176012e-05, "loss": 0.571, "step": 23060 }, { "epoch": 5.52, "learning_rate": 9.89323015708864e-05, "loss": 0.5952, "step": 23070 }, { "epoch": 5.52, "learning_rate": 9.893137906595411e-05, "loss": 0.602, "step": 23080 }, { "epoch": 5.52, "learning_rate": 9.893045616697067e-05, "loss": 0.5676, "step": 23090 }, { "epoch": 5.52, "learning_rate": 9.892953287394351e-05, "loss": 0.5664, "step": 23100 }, { "epoch": 5.52, "learning_rate": 9.892860918688006e-05, "loss": 0.5631, "step": 23110 }, { "epoch": 5.53, "learning_rate": 9.892768510578777e-05, "loss": 0.5318, "step": 23120 }, { "epoch": 5.53, "learning_rate": 9.892676063067408e-05, "loss": 0.5548, "step": 23130 }, { "epoch": 5.53, "learning_rate": 9.892583576154643e-05, "loss": 0.5838, "step": 23140 }, { "epoch": 5.53, "learning_rate": 9.892491049841226e-05, "loss": 0.5877, "step": 23150 }, { "epoch": 5.54, "learning_rate": 9.892398484127905e-05, "loss": 0.614, "step": 23160 }, { "epoch": 5.54, "learning_rate": 9.892305879015422e-05, "loss": 0.5696, "step": 23170 }, { "epoch": 5.54, "learning_rate": 9.892213234504525e-05, "loss": 0.6199, "step": 23180 }, { "epoch": 5.54, "learning_rate": 9.89212055059596e-05, "loss": 0.6369, "step": 23190 }, { "epoch": 5.55, "learning_rate": 9.892027827290471e-05, "loss": 0.6042, "step": 23200 }, { "epoch": 5.55, "learning_rate": 9.891935064588809e-05, "loss": 0.6453, "step": 23210 }, { "epoch": 5.55, "learning_rate": 9.891842262491718e-05, "loss": 0.5824, "step": 23220 }, { "epoch": 5.55, "learning_rate": 9.891749420999942e-05, "loss": 0.5871, "step": 23230 }, { "epoch": 5.55, "learning_rate": 9.891656540114238e-05, "loss": 0.6108, "step": 23240 }, { "epoch": 5.56, "learning_rate": 9.891563619835345e-05, "loss": 0.6371, "step": 23250 }, { "epoch": 5.56, "learning_rate": 9.891470660164018e-05, "loss": 0.6023, "step": 23260 }, { "epoch": 5.56, "learning_rate": 9.891377661100999e-05, "loss": 0.5651, "step": 23270 }, { "epoch": 5.56, "learning_rate": 9.891284622647041e-05, "loss": 0.5645, "step": 23280 }, { "epoch": 5.57, "learning_rate": 9.891191544802895e-05, "loss": 0.5748, "step": 23290 }, { "epoch": 5.57, "learning_rate": 9.891098427569307e-05, "loss": 0.6015, "step": 23300 }, { "epoch": 5.57, "learning_rate": 9.891005270947027e-05, "loss": 0.6046, "step": 23310 }, { "epoch": 5.57, "learning_rate": 9.890912074936806e-05, "loss": 0.575, "step": 23320 }, { "epoch": 5.57, "learning_rate": 9.890818839539398e-05, "loss": 0.5585, "step": 23330 }, { "epoch": 5.58, "learning_rate": 9.890725564755547e-05, "loss": 0.6092, "step": 23340 }, { "epoch": 5.58, "learning_rate": 9.89063225058601e-05, "loss": 0.6362, "step": 23350 }, { "epoch": 5.58, "learning_rate": 9.890538897031536e-05, "loss": 0.5707, "step": 23360 }, { "epoch": 5.58, "learning_rate": 9.890445504092878e-05, "loss": 0.5868, "step": 23370 }, { "epoch": 5.59, "learning_rate": 9.890352071770786e-05, "loss": 0.5808, "step": 23380 }, { "epoch": 5.59, "learning_rate": 9.890258600066013e-05, "loss": 0.5616, "step": 23390 }, { "epoch": 5.59, "learning_rate": 9.890165088979313e-05, "loss": 0.5951, "step": 23400 }, { "epoch": 5.59, "learning_rate": 9.890071538511438e-05, "loss": 0.568, "step": 23410 }, { "epoch": 5.6, "learning_rate": 9.889977948663143e-05, "loss": 0.5802, "step": 23420 }, { "epoch": 5.6, "learning_rate": 9.88988431943518e-05, "loss": 0.5675, "step": 23430 }, { "epoch": 5.6, "learning_rate": 9.889790650828303e-05, "loss": 0.6307, "step": 23440 }, { "epoch": 5.6, "learning_rate": 9.889696942843267e-05, "loss": 0.6298, "step": 23450 }, { "epoch": 5.6, "learning_rate": 9.889603195480825e-05, "loss": 0.5781, "step": 23460 }, { "epoch": 5.61, "learning_rate": 9.889509408741736e-05, "loss": 0.6012, "step": 23470 }, { "epoch": 5.61, "learning_rate": 9.88941558262675e-05, "loss": 0.5509, "step": 23480 }, { "epoch": 5.61, "learning_rate": 9.889321717136627e-05, "loss": 0.5429, "step": 23490 }, { "epoch": 5.61, "learning_rate": 9.889227812272123e-05, "loss": 0.5802, "step": 23500 }, { "epoch": 5.62, "learning_rate": 9.88913386803399e-05, "loss": 0.5834, "step": 23510 }, { "epoch": 5.62, "learning_rate": 9.889039884422988e-05, "loss": 0.6022, "step": 23520 }, { "epoch": 5.62, "learning_rate": 9.888945861439872e-05, "loss": 0.5542, "step": 23530 }, { "epoch": 5.62, "learning_rate": 9.8888517990854e-05, "loss": 0.5726, "step": 23540 }, { "epoch": 5.62, "learning_rate": 9.88875769736033e-05, "loss": 0.5966, "step": 23550 }, { "epoch": 5.63, "learning_rate": 9.888663556265418e-05, "loss": 0.6199, "step": 23560 }, { "epoch": 5.63, "learning_rate": 9.888569375801427e-05, "loss": 0.588, "step": 23570 }, { "epoch": 5.63, "learning_rate": 9.888475155969108e-05, "loss": 0.5603, "step": 23580 }, { "epoch": 5.63, "learning_rate": 9.888380896769225e-05, "loss": 0.5862, "step": 23590 }, { "epoch": 5.64, "learning_rate": 9.888286598202537e-05, "loss": 0.6241, "step": 23600 }, { "epoch": 5.64, "learning_rate": 9.8881922602698e-05, "loss": 0.5686, "step": 23610 }, { "epoch": 5.64, "learning_rate": 9.888097882971777e-05, "loss": 0.6383, "step": 23620 }, { "epoch": 5.64, "learning_rate": 9.888003466309228e-05, "loss": 0.5894, "step": 23630 }, { "epoch": 5.65, "learning_rate": 9.88790901028291e-05, "loss": 0.5702, "step": 23640 }, { "epoch": 5.65, "learning_rate": 9.887814514893588e-05, "loss": 0.5948, "step": 23650 }, { "epoch": 5.65, "learning_rate": 9.88771998014202e-05, "loss": 0.5804, "step": 23660 }, { "epoch": 5.65, "learning_rate": 9.887625406028967e-05, "loss": 0.5463, "step": 23670 }, { "epoch": 5.65, "learning_rate": 9.887530792555192e-05, "loss": 0.571, "step": 23680 }, { "epoch": 5.66, "learning_rate": 9.887436139721459e-05, "loss": 0.5808, "step": 23690 }, { "epoch": 5.66, "learning_rate": 9.887341447528527e-05, "loss": 0.5902, "step": 23700 }, { "epoch": 5.66, "learning_rate": 9.88724671597716e-05, "loss": 0.5655, "step": 23710 }, { "epoch": 5.66, "learning_rate": 9.88715194506812e-05, "loss": 0.5686, "step": 23720 }, { "epoch": 5.67, "learning_rate": 9.88705713480217e-05, "loss": 0.5942, "step": 23730 }, { "epoch": 5.67, "learning_rate": 9.886962285180075e-05, "loss": 0.5822, "step": 23740 }, { "epoch": 5.67, "learning_rate": 9.886867396202597e-05, "loss": 0.5908, "step": 23750 }, { "epoch": 5.67, "learning_rate": 9.886772467870502e-05, "loss": 0.5503, "step": 23760 }, { "epoch": 5.68, "learning_rate": 9.886677500184553e-05, "loss": 0.5918, "step": 23770 }, { "epoch": 5.68, "learning_rate": 9.886582493145517e-05, "loss": 0.5856, "step": 23780 }, { "epoch": 5.68, "learning_rate": 9.886487446754156e-05, "loss": 0.5885, "step": 23790 }, { "epoch": 5.68, "learning_rate": 9.886392361011239e-05, "loss": 0.5586, "step": 23800 }, { "epoch": 5.68, "learning_rate": 9.886297235917528e-05, "loss": 0.5651, "step": 23810 }, { "epoch": 5.69, "learning_rate": 9.88620207147379e-05, "loss": 0.5986, "step": 23820 }, { "epoch": 5.69, "learning_rate": 9.886106867680793e-05, "loss": 0.5588, "step": 23830 }, { "epoch": 5.69, "learning_rate": 9.886011624539303e-05, "loss": 0.5511, "step": 23840 }, { "epoch": 5.69, "learning_rate": 9.885916342050088e-05, "loss": 0.5934, "step": 23850 }, { "epoch": 5.7, "learning_rate": 9.885821020213912e-05, "loss": 0.616, "step": 23860 }, { "epoch": 5.7, "learning_rate": 9.885725659031546e-05, "loss": 0.5414, "step": 23870 }, { "epoch": 5.7, "learning_rate": 9.885630258503757e-05, "loss": 0.5617, "step": 23880 }, { "epoch": 5.7, "learning_rate": 9.885534818631313e-05, "loss": 0.6054, "step": 23890 }, { "epoch": 5.7, "learning_rate": 9.885439339414982e-05, "loss": 0.5387, "step": 23900 }, { "epoch": 5.71, "learning_rate": 9.885343820855532e-05, "loss": 0.5682, "step": 23910 }, { "epoch": 5.71, "learning_rate": 9.885248262953736e-05, "loss": 0.5835, "step": 23920 }, { "epoch": 5.71, "learning_rate": 9.88515266571036e-05, "loss": 0.5757, "step": 23930 }, { "epoch": 5.71, "learning_rate": 9.885057029126177e-05, "loss": 0.5862, "step": 23940 }, { "epoch": 5.72, "learning_rate": 9.884961353201953e-05, "loss": 0.5944, "step": 23950 }, { "epoch": 5.72, "learning_rate": 9.884865637938463e-05, "loss": 0.5776, "step": 23960 }, { "epoch": 5.72, "learning_rate": 9.884769883336475e-05, "loss": 0.5527, "step": 23970 }, { "epoch": 5.72, "learning_rate": 9.884674089396759e-05, "loss": 0.5584, "step": 23980 }, { "epoch": 5.73, "learning_rate": 9.884578256120089e-05, "loss": 0.5507, "step": 23990 }, { "epoch": 5.73, "learning_rate": 9.884482383507238e-05, "loss": 0.5647, "step": 24000 }, { "epoch": 5.73, "learning_rate": 9.884386471558974e-05, "loss": 0.5473, "step": 24010 }, { "epoch": 5.73, "learning_rate": 9.884290520276072e-05, "loss": 0.5921, "step": 24020 }, { "epoch": 5.73, "learning_rate": 9.884194529659305e-05, "loss": 0.5537, "step": 24030 }, { "epoch": 5.74, "learning_rate": 9.884098499709444e-05, "loss": 0.6029, "step": 24040 }, { "epoch": 5.74, "learning_rate": 9.884002430427263e-05, "loss": 0.5619, "step": 24050 }, { "epoch": 5.74, "learning_rate": 9.883906321813536e-05, "loss": 0.5885, "step": 24060 }, { "epoch": 5.74, "learning_rate": 9.88381017386904e-05, "loss": 0.5305, "step": 24070 }, { "epoch": 5.75, "learning_rate": 9.883713986594543e-05, "loss": 0.5576, "step": 24080 }, { "epoch": 5.75, "learning_rate": 9.883617759990824e-05, "loss": 0.6276, "step": 24090 }, { "epoch": 5.75, "learning_rate": 9.883521494058657e-05, "loss": 0.5824, "step": 24100 }, { "epoch": 5.75, "learning_rate": 9.883425188798818e-05, "loss": 0.5752, "step": 24110 }, { "epoch": 5.76, "learning_rate": 9.883328844212081e-05, "loss": 0.5866, "step": 24120 }, { "epoch": 5.76, "learning_rate": 9.883232460299224e-05, "loss": 0.5979, "step": 24130 }, { "epoch": 5.76, "learning_rate": 9.88313603706102e-05, "loss": 0.5538, "step": 24140 }, { "epoch": 5.76, "learning_rate": 9.883039574498248e-05, "loss": 0.5756, "step": 24150 }, { "epoch": 5.76, "learning_rate": 9.882943072611684e-05, "loss": 0.5522, "step": 24160 }, { "epoch": 5.77, "learning_rate": 9.882846531402106e-05, "loss": 0.5639, "step": 24170 }, { "epoch": 5.77, "learning_rate": 9.882749950870291e-05, "loss": 0.5771, "step": 24180 }, { "epoch": 5.77, "learning_rate": 9.882653331017016e-05, "loss": 0.6003, "step": 24190 }, { "epoch": 5.77, "learning_rate": 9.882556671843058e-05, "loss": 0.5533, "step": 24200 }, { "epoch": 5.78, "learning_rate": 9.882459973349198e-05, "loss": 0.5549, "step": 24210 }, { "epoch": 5.78, "learning_rate": 9.882363235536216e-05, "loss": 0.5733, "step": 24220 }, { "epoch": 5.78, "learning_rate": 9.882266458404887e-05, "loss": 0.5709, "step": 24230 }, { "epoch": 5.78, "learning_rate": 9.882169641955991e-05, "loss": 0.561, "step": 24240 }, { "epoch": 5.78, "learning_rate": 9.88207278619031e-05, "loss": 0.5681, "step": 24250 }, { "epoch": 5.79, "learning_rate": 9.881975891108624e-05, "loss": 0.5607, "step": 24260 }, { "epoch": 5.79, "learning_rate": 9.88187895671171e-05, "loss": 0.573, "step": 24270 }, { "epoch": 5.79, "learning_rate": 9.881781983000354e-05, "loss": 0.551, "step": 24280 }, { "epoch": 5.79, "learning_rate": 9.881684969975332e-05, "loss": 0.5797, "step": 24290 }, { "epoch": 5.8, "learning_rate": 9.881587917637425e-05, "loss": 0.5791, "step": 24300 }, { "epoch": 5.8, "learning_rate": 9.881490825987418e-05, "loss": 0.5747, "step": 24310 }, { "epoch": 5.8, "learning_rate": 9.881393695026091e-05, "loss": 0.5877, "step": 24320 }, { "epoch": 5.8, "learning_rate": 9.881296524754228e-05, "loss": 0.601, "step": 24330 }, { "epoch": 5.81, "learning_rate": 9.881199315172609e-05, "loss": 0.5446, "step": 24340 }, { "epoch": 5.81, "learning_rate": 9.881102066282018e-05, "loss": 0.5572, "step": 24350 }, { "epoch": 5.81, "learning_rate": 9.881004778083239e-05, "loss": 0.5354, "step": 24360 }, { "epoch": 5.81, "learning_rate": 9.880907450577055e-05, "loss": 0.5369, "step": 24370 }, { "epoch": 5.81, "learning_rate": 9.88081008376425e-05, "loss": 0.5624, "step": 24380 }, { "epoch": 5.82, "learning_rate": 9.880712677645605e-05, "loss": 0.5856, "step": 24390 }, { "epoch": 5.82, "learning_rate": 9.880615232221908e-05, "loss": 0.5293, "step": 24400 }, { "epoch": 5.82, "learning_rate": 9.880517747493942e-05, "loss": 0.5532, "step": 24410 }, { "epoch": 5.82, "learning_rate": 9.880420223462495e-05, "loss": 0.5585, "step": 24420 }, { "epoch": 5.83, "learning_rate": 9.88032266012835e-05, "loss": 0.5741, "step": 24430 }, { "epoch": 5.83, "learning_rate": 9.88022505749229e-05, "loss": 0.6137, "step": 24440 }, { "epoch": 5.83, "learning_rate": 9.880127415555108e-05, "loss": 0.5389, "step": 24450 }, { "epoch": 5.83, "learning_rate": 9.880029734317581e-05, "loss": 0.5612, "step": 24460 }, { "epoch": 5.84, "learning_rate": 9.879932013780505e-05, "loss": 0.584, "step": 24470 }, { "epoch": 5.84, "learning_rate": 9.879834253944662e-05, "loss": 0.5339, "step": 24480 }, { "epoch": 5.84, "learning_rate": 9.879736454810838e-05, "loss": 0.5694, "step": 24490 }, { "epoch": 5.84, "learning_rate": 9.879638616379825e-05, "loss": 0.5943, "step": 24500 }, { "epoch": 5.84, "learning_rate": 9.879540738652407e-05, "loss": 0.5943, "step": 24510 }, { "epoch": 5.85, "learning_rate": 9.879442821629374e-05, "loss": 0.5124, "step": 24520 }, { "epoch": 5.85, "learning_rate": 9.879344865311515e-05, "loss": 0.5998, "step": 24530 }, { "epoch": 5.85, "learning_rate": 9.879246869699618e-05, "loss": 0.5991, "step": 24540 }, { "epoch": 5.85, "learning_rate": 9.879148834794472e-05, "loss": 0.571, "step": 24550 }, { "epoch": 5.86, "learning_rate": 9.879050760596869e-05, "loss": 0.5666, "step": 24560 }, { "epoch": 5.86, "learning_rate": 9.878952647107593e-05, "loss": 0.5491, "step": 24570 }, { "epoch": 5.86, "learning_rate": 9.87885449432744e-05, "loss": 0.5867, "step": 24580 }, { "epoch": 5.86, "learning_rate": 9.878756302257197e-05, "loss": 0.5392, "step": 24590 }, { "epoch": 5.86, "learning_rate": 9.878658070897658e-05, "loss": 0.5296, "step": 24600 }, { "epoch": 5.87, "learning_rate": 9.87855980024961e-05, "loss": 0.5581, "step": 24610 }, { "epoch": 5.87, "learning_rate": 9.878461490313847e-05, "loss": 0.5613, "step": 24620 }, { "epoch": 5.87, "learning_rate": 9.87836314109116e-05, "loss": 0.5581, "step": 24630 }, { "epoch": 5.87, "learning_rate": 9.878264752582341e-05, "loss": 0.5635, "step": 24640 }, { "epoch": 5.88, "learning_rate": 9.878166324788183e-05, "loss": 0.5746, "step": 24650 }, { "epoch": 5.88, "learning_rate": 9.878067857709478e-05, "loss": 0.5262, "step": 24660 }, { "epoch": 5.88, "learning_rate": 9.877969351347019e-05, "loss": 0.4927, "step": 24670 }, { "epoch": 5.88, "learning_rate": 9.8778708057016e-05, "loss": 0.571, "step": 24680 }, { "epoch": 5.89, "learning_rate": 9.877772220774012e-05, "loss": 0.5454, "step": 24690 }, { "epoch": 5.89, "learning_rate": 9.877673596565051e-05, "loss": 0.5612, "step": 24700 }, { "epoch": 5.89, "learning_rate": 9.877574933075514e-05, "loss": 0.5608, "step": 24710 }, { "epoch": 5.89, "learning_rate": 9.87747623030619e-05, "loss": 0.5626, "step": 24720 }, { "epoch": 5.89, "learning_rate": 9.877377488257877e-05, "loss": 0.5896, "step": 24730 }, { "epoch": 5.9, "learning_rate": 9.87727870693137e-05, "loss": 0.559, "step": 24740 }, { "epoch": 5.9, "learning_rate": 9.877179886327465e-05, "loss": 0.5366, "step": 24750 }, { "epoch": 5.9, "learning_rate": 9.877081026446957e-05, "loss": 0.5309, "step": 24760 }, { "epoch": 5.9, "learning_rate": 9.876982127290641e-05, "loss": 0.5403, "step": 24770 }, { "epoch": 5.91, "learning_rate": 9.876883188859315e-05, "loss": 0.583, "step": 24780 }, { "epoch": 5.91, "learning_rate": 9.876784211153775e-05, "loss": 0.5704, "step": 24790 }, { "epoch": 5.91, "learning_rate": 9.87668519417482e-05, "loss": 0.5359, "step": 24800 }, { "epoch": 5.91, "learning_rate": 9.876586137923245e-05, "loss": 0.5675, "step": 24810 }, { "epoch": 5.92, "learning_rate": 9.87648704239985e-05, "loss": 0.5616, "step": 24820 }, { "epoch": 5.92, "learning_rate": 9.876387907605429e-05, "loss": 0.523, "step": 24830 }, { "epoch": 5.92, "learning_rate": 9.876288733540784e-05, "loss": 0.5933, "step": 24840 }, { "epoch": 5.92, "learning_rate": 9.876189520206712e-05, "loss": 0.5354, "step": 24850 }, { "epoch": 5.92, "learning_rate": 9.876090267604014e-05, "loss": 0.5818, "step": 24860 }, { "epoch": 5.93, "learning_rate": 9.875990975733486e-05, "loss": 0.5627, "step": 24870 }, { "epoch": 5.93, "learning_rate": 9.875891644595931e-05, "loss": 0.4833, "step": 24880 }, { "epoch": 5.93, "learning_rate": 9.875792274192148e-05, "loss": 0.5394, "step": 24890 }, { "epoch": 5.93, "learning_rate": 9.875692864522935e-05, "loss": 0.5787, "step": 24900 }, { "epoch": 5.94, "learning_rate": 9.875593415589095e-05, "loss": 0.5407, "step": 24910 }, { "epoch": 5.94, "learning_rate": 9.875493927391429e-05, "loss": 0.5301, "step": 24920 }, { "epoch": 5.94, "learning_rate": 9.875394399930735e-05, "loss": 0.5236, "step": 24930 }, { "epoch": 5.94, "learning_rate": 9.875294833207818e-05, "loss": 0.5162, "step": 24940 }, { "epoch": 5.94, "learning_rate": 9.87519522722348e-05, "loss": 0.5705, "step": 24950 }, { "epoch": 5.95, "learning_rate": 9.87509558197852e-05, "loss": 0.5844, "step": 24960 }, { "epoch": 5.95, "learning_rate": 9.874995897473743e-05, "loss": 0.5946, "step": 24970 }, { "epoch": 6.0, "learning_rate": 9.874896173709952e-05, "loss": 0.5241, "step": 24980 }, { "epoch": 6.0, "learning_rate": 9.874796410687948e-05, "loss": 0.5342, "step": 24990 }, { "epoch": 6.01, "learning_rate": 9.874696608408535e-05, "loss": 0.5228, "step": 25000 }, { "epoch": 6.01, "learning_rate": 9.874596766872517e-05, "loss": 0.5511, "step": 25010 }, { "epoch": 6.01, "learning_rate": 9.8744968860807e-05, "loss": 0.5122, "step": 25020 }, { "epoch": 6.01, "learning_rate": 9.874396966033885e-05, "loss": 0.5414, "step": 25030 }, { "epoch": 6.01, "learning_rate": 9.874297006732878e-05, "loss": 0.5509, "step": 25040 }, { "epoch": 6.02, "learning_rate": 9.874197008178485e-05, "loss": 0.548, "step": 25050 }, { "epoch": 6.02, "learning_rate": 9.874096970371512e-05, "loss": 0.5326, "step": 25060 }, { "epoch": 6.02, "learning_rate": 9.87399689331276e-05, "loss": 0.5145, "step": 25070 }, { "epoch": 6.02, "learning_rate": 9.873896777003042e-05, "loss": 0.5325, "step": 25080 }, { "epoch": 6.03, "learning_rate": 9.873796621443157e-05, "loss": 0.5578, "step": 25090 }, { "epoch": 6.03, "learning_rate": 9.873696426633916e-05, "loss": 0.5859, "step": 25100 }, { "epoch": 6.03, "learning_rate": 9.873596192576125e-05, "loss": 0.5583, "step": 25110 }, { "epoch": 6.03, "learning_rate": 9.873495919270593e-05, "loss": 0.5641, "step": 25120 }, { "epoch": 6.03, "learning_rate": 9.873395606718123e-05, "loss": 0.547, "step": 25130 }, { "epoch": 6.04, "learning_rate": 9.873295254919526e-05, "loss": 0.5277, "step": 25140 }, { "epoch": 6.04, "learning_rate": 9.873194863875609e-05, "loss": 0.5241, "step": 25150 }, { "epoch": 6.04, "learning_rate": 9.873094433587181e-05, "loss": 0.5597, "step": 25160 }, { "epoch": 6.04, "learning_rate": 9.87299396405505e-05, "loss": 0.5126, "step": 25170 }, { "epoch": 6.05, "learning_rate": 9.872893455280028e-05, "loss": 0.5356, "step": 25180 }, { "epoch": 6.05, "learning_rate": 9.872792907262922e-05, "loss": 0.5192, "step": 25190 }, { "epoch": 6.05, "learning_rate": 9.872692320004541e-05, "loss": 0.5284, "step": 25200 }, { "epoch": 6.05, "learning_rate": 9.872591693505698e-05, "loss": 0.5218, "step": 25210 }, { "epoch": 6.06, "learning_rate": 9.872491027767199e-05, "loss": 0.555, "step": 25220 }, { "epoch": 6.06, "learning_rate": 9.872390322789857e-05, "loss": 0.5459, "step": 25230 }, { "epoch": 6.06, "learning_rate": 9.872289578574484e-05, "loss": 0.5104, "step": 25240 }, { "epoch": 6.06, "learning_rate": 9.87218879512189e-05, "loss": 0.5186, "step": 25250 }, { "epoch": 6.06, "learning_rate": 9.872087972432887e-05, "loss": 0.5267, "step": 25260 }, { "epoch": 6.07, "learning_rate": 9.871987110508287e-05, "loss": 0.5428, "step": 25270 }, { "epoch": 6.07, "learning_rate": 9.871886209348903e-05, "loss": 0.5125, "step": 25280 }, { "epoch": 6.07, "learning_rate": 9.871785268955546e-05, "loss": 0.5384, "step": 25290 }, { "epoch": 6.07, "learning_rate": 9.87168428932903e-05, "loss": 0.5359, "step": 25300 }, { "epoch": 6.08, "learning_rate": 9.871583270470167e-05, "loss": 0.5238, "step": 25310 }, { "epoch": 6.08, "learning_rate": 9.871482212379773e-05, "loss": 0.538, "step": 25320 }, { "epoch": 6.08, "learning_rate": 9.871381115058657e-05, "loss": 0.5529, "step": 25330 }, { "epoch": 6.08, "learning_rate": 9.87127997850764e-05, "loss": 0.5251, "step": 25340 }, { "epoch": 6.09, "learning_rate": 9.871178802727531e-05, "loss": 0.5225, "step": 25350 }, { "epoch": 6.09, "learning_rate": 9.871077587719147e-05, "loss": 0.4784, "step": 25360 }, { "epoch": 6.09, "learning_rate": 9.870976333483301e-05, "loss": 0.5241, "step": 25370 }, { "epoch": 6.09, "learning_rate": 9.870875040020812e-05, "loss": 0.5419, "step": 25380 }, { "epoch": 6.09, "learning_rate": 9.870773707332494e-05, "loss": 0.5185, "step": 25390 }, { "epoch": 6.1, "learning_rate": 9.870672335419162e-05, "loss": 0.5582, "step": 25400 }, { "epoch": 6.1, "learning_rate": 9.870570924281634e-05, "loss": 0.5324, "step": 25410 }, { "epoch": 6.1, "learning_rate": 9.870469473920725e-05, "loss": 0.5145, "step": 25420 }, { "epoch": 6.1, "learning_rate": 9.870367984337255e-05, "loss": 0.5138, "step": 25430 }, { "epoch": 6.11, "learning_rate": 9.870266455532036e-05, "loss": 0.5367, "step": 25440 }, { "epoch": 6.11, "learning_rate": 9.870164887505891e-05, "loss": 0.5213, "step": 25450 }, { "epoch": 6.11, "learning_rate": 9.870063280259636e-05, "loss": 0.5719, "step": 25460 }, { "epoch": 6.11, "learning_rate": 9.869961633794089e-05, "loss": 0.5507, "step": 25470 }, { "epoch": 6.11, "learning_rate": 9.869859948110067e-05, "loss": 0.5003, "step": 25480 }, { "epoch": 6.12, "learning_rate": 9.869758223208392e-05, "loss": 0.5378, "step": 25490 }, { "epoch": 6.12, "learning_rate": 9.86965645908988e-05, "loss": 0.5519, "step": 25500 }, { "epoch": 6.12, "learning_rate": 9.869554655755355e-05, "loss": 0.5475, "step": 25510 }, { "epoch": 6.12, "learning_rate": 9.869452813205632e-05, "loss": 0.5227, "step": 25520 }, { "epoch": 6.13, "learning_rate": 9.869350931441535e-05, "loss": 0.5337, "step": 25530 }, { "epoch": 6.13, "learning_rate": 9.869249010463881e-05, "loss": 0.5406, "step": 25540 }, { "epoch": 6.13, "learning_rate": 9.869147050273492e-05, "loss": 0.5005, "step": 25550 }, { "epoch": 6.13, "learning_rate": 9.869045050871191e-05, "loss": 0.5327, "step": 25560 }, { "epoch": 6.14, "learning_rate": 9.868943012257797e-05, "loss": 0.5189, "step": 25570 }, { "epoch": 6.14, "learning_rate": 9.868840934434134e-05, "loss": 0.5781, "step": 25580 }, { "epoch": 6.14, "learning_rate": 9.868738817401021e-05, "loss": 0.5163, "step": 25590 }, { "epoch": 6.14, "learning_rate": 9.868636661159283e-05, "loss": 0.5723, "step": 25600 }, { "epoch": 6.14, "learning_rate": 9.868534465709743e-05, "loss": 0.5822, "step": 25610 }, { "epoch": 6.15, "learning_rate": 9.868432231053222e-05, "loss": 0.5262, "step": 25620 }, { "epoch": 6.15, "learning_rate": 9.868329957190543e-05, "loss": 0.5064, "step": 25630 }, { "epoch": 6.15, "learning_rate": 9.868227644122531e-05, "loss": 0.513, "step": 25640 }, { "epoch": 6.15, "learning_rate": 9.868125291850011e-05, "loss": 0.498, "step": 25650 }, { "epoch": 6.16, "learning_rate": 9.868022900373806e-05, "loss": 0.4958, "step": 25660 }, { "epoch": 6.16, "learning_rate": 9.867920469694738e-05, "loss": 0.5305, "step": 25670 }, { "epoch": 6.16, "learning_rate": 9.867817999813638e-05, "loss": 0.5164, "step": 25680 }, { "epoch": 6.16, "learning_rate": 9.867715490731324e-05, "loss": 0.5539, "step": 25690 }, { "epoch": 6.16, "learning_rate": 9.867612942448628e-05, "loss": 0.566, "step": 25700 }, { "epoch": 6.17, "learning_rate": 9.867510354966372e-05, "loss": 0.532, "step": 25710 }, { "epoch": 6.17, "learning_rate": 9.867407728285383e-05, "loss": 0.5452, "step": 25720 }, { "epoch": 6.17, "learning_rate": 9.867305062406487e-05, "loss": 0.5851, "step": 25730 }, { "epoch": 6.17, "learning_rate": 9.867202357330511e-05, "loss": 0.5608, "step": 25740 }, { "epoch": 6.18, "learning_rate": 9.867099613058283e-05, "loss": 0.5315, "step": 25750 }, { "epoch": 6.18, "learning_rate": 9.86699682959063e-05, "loss": 0.5054, "step": 25760 }, { "epoch": 6.18, "learning_rate": 9.866894006928381e-05, "loss": 0.5176, "step": 25770 }, { "epoch": 6.18, "learning_rate": 9.866791145072362e-05, "loss": 0.5829, "step": 25780 }, { "epoch": 6.19, "learning_rate": 9.866688244023401e-05, "loss": 0.5184, "step": 25790 }, { "epoch": 6.19, "learning_rate": 9.866585303782327e-05, "loss": 0.5741, "step": 25800 }, { "epoch": 6.19, "learning_rate": 9.866482324349971e-05, "loss": 0.5407, "step": 25810 }, { "epoch": 6.19, "learning_rate": 9.866379305727161e-05, "loss": 0.5663, "step": 25820 }, { "epoch": 6.19, "learning_rate": 9.866276247914727e-05, "loss": 0.5325, "step": 25830 }, { "epoch": 6.2, "learning_rate": 9.866173150913499e-05, "loss": 0.5096, "step": 25840 }, { "epoch": 6.2, "learning_rate": 9.866070014724305e-05, "loss": 0.4955, "step": 25850 }, { "epoch": 6.2, "learning_rate": 9.865966839347977e-05, "loss": 0.5252, "step": 25860 }, { "epoch": 6.2, "learning_rate": 9.865863624785348e-05, "loss": 0.5509, "step": 25870 }, { "epoch": 6.21, "learning_rate": 9.865760371037247e-05, "loss": 0.5511, "step": 25880 }, { "epoch": 6.21, "learning_rate": 9.865657078104505e-05, "loss": 0.5029, "step": 25890 }, { "epoch": 6.21, "learning_rate": 9.865553745987956e-05, "loss": 0.5116, "step": 25900 }, { "epoch": 6.21, "learning_rate": 9.86545037468843e-05, "loss": 0.5079, "step": 25910 }, { "epoch": 6.22, "learning_rate": 9.86534696420676e-05, "loss": 0.5189, "step": 25920 }, { "epoch": 6.22, "learning_rate": 9.865243514543782e-05, "loss": 0.4955, "step": 25930 }, { "epoch": 6.22, "learning_rate": 9.865140025700323e-05, "loss": 0.5417, "step": 25940 }, { "epoch": 6.22, "learning_rate": 9.865036497677222e-05, "loss": 0.5823, "step": 25950 }, { "epoch": 6.22, "learning_rate": 9.86493293047531e-05, "loss": 0.5308, "step": 25960 }, { "epoch": 6.23, "learning_rate": 9.864829324095422e-05, "loss": 0.5236, "step": 25970 }, { "epoch": 6.23, "learning_rate": 9.86472567853839e-05, "loss": 0.5909, "step": 25980 }, { "epoch": 6.23, "learning_rate": 9.864621993805051e-05, "loss": 0.541, "step": 25990 }, { "epoch": 6.23, "learning_rate": 9.864518269896239e-05, "loss": 0.5266, "step": 26000 }, { "epoch": 6.24, "learning_rate": 9.864414506812792e-05, "loss": 0.564, "step": 26010 }, { "epoch": 6.24, "learning_rate": 9.864310704555541e-05, "loss": 0.5388, "step": 26020 }, { "epoch": 6.24, "learning_rate": 9.864206863125326e-05, "loss": 0.5344, "step": 26030 }, { "epoch": 6.24, "learning_rate": 9.86410298252298e-05, "loss": 0.5851, "step": 26040 }, { "epoch": 6.24, "learning_rate": 9.863999062749342e-05, "loss": 0.5228, "step": 26050 }, { "epoch": 6.25, "learning_rate": 9.86389510380525e-05, "loss": 0.538, "step": 26060 }, { "epoch": 6.25, "learning_rate": 9.863791105691536e-05, "loss": 0.5133, "step": 26070 }, { "epoch": 6.25, "learning_rate": 9.863687068409043e-05, "loss": 0.5526, "step": 26080 }, { "epoch": 6.25, "learning_rate": 9.863582991958604e-05, "loss": 0.4956, "step": 26090 }, { "epoch": 6.26, "learning_rate": 9.863478876341063e-05, "loss": 0.5262, "step": 26100 }, { "epoch": 6.26, "learning_rate": 9.863374721557253e-05, "loss": 0.4927, "step": 26110 }, { "epoch": 6.26, "learning_rate": 9.863270527608015e-05, "loss": 0.5458, "step": 26120 }, { "epoch": 6.26, "learning_rate": 9.863166294494189e-05, "loss": 0.5385, "step": 26130 }, { "epoch": 6.27, "learning_rate": 9.863062022216613e-05, "loss": 0.5465, "step": 26140 }, { "epoch": 6.27, "learning_rate": 9.862957710776126e-05, "loss": 0.5577, "step": 26150 }, { "epoch": 6.27, "learning_rate": 9.86285336017357e-05, "loss": 0.5336, "step": 26160 }, { "epoch": 6.27, "learning_rate": 9.862748970409786e-05, "loss": 0.5545, "step": 26170 }, { "epoch": 6.27, "learning_rate": 9.862644541485612e-05, "loss": 0.5715, "step": 26180 }, { "epoch": 6.28, "learning_rate": 9.86254007340189e-05, "loss": 0.5583, "step": 26190 }, { "epoch": 6.28, "learning_rate": 9.862435566159461e-05, "loss": 0.4996, "step": 26200 }, { "epoch": 6.28, "learning_rate": 9.862331019759167e-05, "loss": 0.5428, "step": 26210 }, { "epoch": 6.28, "learning_rate": 9.862226434201851e-05, "loss": 0.5401, "step": 26220 }, { "epoch": 6.29, "learning_rate": 9.862121809488353e-05, "loss": 0.5194, "step": 26230 }, { "epoch": 6.29, "learning_rate": 9.86201714561952e-05, "loss": 0.5353, "step": 26240 }, { "epoch": 6.29, "learning_rate": 9.861912442596188e-05, "loss": 0.5447, "step": 26250 }, { "epoch": 6.29, "learning_rate": 9.861807700419205e-05, "loss": 0.5367, "step": 26260 }, { "epoch": 6.3, "learning_rate": 9.861702919089415e-05, "loss": 0.5298, "step": 26270 }, { "epoch": 6.3, "learning_rate": 9.861598098607658e-05, "loss": 0.5741, "step": 26280 }, { "epoch": 6.3, "learning_rate": 9.861493238974782e-05, "loss": 0.5009, "step": 26290 }, { "epoch": 6.3, "learning_rate": 9.861388340191629e-05, "loss": 0.531, "step": 26300 }, { "epoch": 6.3, "learning_rate": 9.861283402259045e-05, "loss": 0.5376, "step": 26310 }, { "epoch": 6.31, "learning_rate": 9.861178425177873e-05, "loss": 0.5488, "step": 26320 }, { "epoch": 6.31, "learning_rate": 9.861073408948961e-05, "loss": 0.5427, "step": 26330 }, { "epoch": 6.31, "learning_rate": 9.860968353573155e-05, "loss": 0.5547, "step": 26340 }, { "epoch": 6.31, "learning_rate": 9.860863259051299e-05, "loss": 0.5017, "step": 26350 }, { "epoch": 6.32, "learning_rate": 9.86075812538424e-05, "loss": 0.4556, "step": 26360 }, { "epoch": 6.32, "learning_rate": 9.860652952572824e-05, "loss": 0.5829, "step": 26370 }, { "epoch": 6.32, "learning_rate": 9.860547740617898e-05, "loss": 0.5128, "step": 26380 }, { "epoch": 6.32, "learning_rate": 9.860442489520312e-05, "loss": 0.5195, "step": 26390 }, { "epoch": 6.32, "learning_rate": 9.860337199280912e-05, "loss": 0.5149, "step": 26400 }, { "epoch": 6.33, "learning_rate": 9.860231869900542e-05, "loss": 0.5109, "step": 26410 }, { "epoch": 6.33, "learning_rate": 9.860126501380056e-05, "loss": 0.5234, "step": 26420 }, { "epoch": 6.33, "learning_rate": 9.860021093720302e-05, "loss": 0.5591, "step": 26430 }, { "epoch": 6.33, "learning_rate": 9.859915646922124e-05, "loss": 0.507, "step": 26440 }, { "epoch": 6.34, "learning_rate": 9.859810160986377e-05, "loss": 0.5372, "step": 26450 }, { "epoch": 6.34, "learning_rate": 9.859704635913907e-05, "loss": 0.5374, "step": 26460 }, { "epoch": 6.34, "learning_rate": 9.859599071705565e-05, "loss": 0.5292, "step": 26470 }, { "epoch": 6.34, "learning_rate": 9.8594934683622e-05, "loss": 0.4676, "step": 26480 }, { "epoch": 6.35, "learning_rate": 9.859387825884663e-05, "loss": 0.4718, "step": 26490 }, { "epoch": 6.35, "learning_rate": 9.859282144273804e-05, "loss": 0.5382, "step": 26500 }, { "epoch": 6.35, "learning_rate": 9.859176423530478e-05, "loss": 0.4771, "step": 26510 }, { "epoch": 6.35, "learning_rate": 9.85907066365553e-05, "loss": 0.4535, "step": 26520 }, { "epoch": 6.35, "learning_rate": 9.858964864649818e-05, "loss": 0.514, "step": 26530 }, { "epoch": 6.36, "learning_rate": 9.858859026514188e-05, "loss": 0.5513, "step": 26540 }, { "epoch": 6.36, "learning_rate": 9.858753149249499e-05, "loss": 0.5356, "step": 26550 }, { "epoch": 6.36, "learning_rate": 9.8586472328566e-05, "loss": 0.5389, "step": 26560 }, { "epoch": 6.36, "learning_rate": 9.858541277336341e-05, "loss": 0.5108, "step": 26570 }, { "epoch": 6.37, "learning_rate": 9.85843528268958e-05, "loss": 0.5048, "step": 26580 }, { "epoch": 6.37, "learning_rate": 9.858329248917169e-05, "loss": 0.5274, "step": 26590 }, { "epoch": 6.37, "learning_rate": 9.858223176019961e-05, "loss": 0.5276, "step": 26600 }, { "epoch": 6.37, "learning_rate": 9.858117063998813e-05, "loss": 0.5163, "step": 26610 }, { "epoch": 6.38, "learning_rate": 9.858010912854577e-05, "loss": 0.5289, "step": 26620 }, { "epoch": 6.38, "learning_rate": 9.857904722588106e-05, "loss": 0.5125, "step": 26630 }, { "epoch": 6.38, "learning_rate": 9.85779849320026e-05, "loss": 0.5532, "step": 26640 }, { "epoch": 6.38, "learning_rate": 9.85769222469189e-05, "loss": 0.577, "step": 26650 }, { "epoch": 6.38, "learning_rate": 9.857585917063856e-05, "loss": 0.5368, "step": 26660 }, { "epoch": 6.39, "learning_rate": 9.857479570317012e-05, "loss": 0.4726, "step": 26670 }, { "epoch": 6.39, "learning_rate": 9.857373184452212e-05, "loss": 0.5272, "step": 26680 }, { "epoch": 6.39, "learning_rate": 9.857266759470318e-05, "loss": 0.5462, "step": 26690 }, { "epoch": 6.39, "learning_rate": 9.857160295372182e-05, "loss": 0.5857, "step": 26700 }, { "epoch": 6.4, "learning_rate": 9.857053792158665e-05, "loss": 0.4841, "step": 26710 }, { "epoch": 6.4, "learning_rate": 9.856947249830624e-05, "loss": 0.513, "step": 26720 }, { "epoch": 6.4, "learning_rate": 9.856840668388914e-05, "loss": 0.5059, "step": 26730 }, { "epoch": 6.4, "learning_rate": 9.856734047834397e-05, "loss": 0.4741, "step": 26740 }, { "epoch": 6.4, "learning_rate": 9.856627388167929e-05, "loss": 0.5326, "step": 26750 }, { "epoch": 6.41, "learning_rate": 9.856520689390372e-05, "loss": 0.5108, "step": 26760 }, { "epoch": 6.41, "learning_rate": 9.856413951502581e-05, "loss": 0.5321, "step": 26770 }, { "epoch": 6.41, "learning_rate": 9.85630717450542e-05, "loss": 0.5174, "step": 26780 }, { "epoch": 6.41, "learning_rate": 9.856200358399746e-05, "loss": 0.5519, "step": 26790 }, { "epoch": 6.42, "learning_rate": 9.856093503186421e-05, "loss": 0.4866, "step": 26800 }, { "epoch": 6.42, "learning_rate": 9.855986608866303e-05, "loss": 0.5246, "step": 26810 }, { "epoch": 6.42, "learning_rate": 9.855879675440255e-05, "loss": 0.5039, "step": 26820 }, { "epoch": 6.42, "learning_rate": 9.855772702909139e-05, "loss": 0.5434, "step": 26830 }, { "epoch": 6.43, "learning_rate": 9.855665691273814e-05, "loss": 0.542, "step": 26840 }, { "epoch": 6.43, "learning_rate": 9.855558640535144e-05, "loss": 0.5744, "step": 26850 }, { "epoch": 6.43, "learning_rate": 9.855451550693988e-05, "loss": 0.4438, "step": 26860 }, { "epoch": 6.43, "learning_rate": 9.855344421751209e-05, "loss": 0.49, "step": 26870 }, { "epoch": 6.43, "learning_rate": 9.855237253707674e-05, "loss": 0.4798, "step": 26880 }, { "epoch": 6.44, "learning_rate": 9.855130046564242e-05, "loss": 0.5423, "step": 26890 }, { "epoch": 6.44, "learning_rate": 9.855022800321778e-05, "loss": 0.4847, "step": 26900 }, { "epoch": 6.44, "learning_rate": 9.854915514981145e-05, "loss": 0.4976, "step": 26910 }, { "epoch": 6.44, "learning_rate": 9.854808190543205e-05, "loss": 0.5045, "step": 26920 }, { "epoch": 6.45, "learning_rate": 9.854700827008827e-05, "loss": 0.4832, "step": 26930 }, { "epoch": 6.45, "learning_rate": 9.854593424378873e-05, "loss": 0.5165, "step": 26940 }, { "epoch": 6.45, "learning_rate": 9.854485982654208e-05, "loss": 0.5721, "step": 26950 }, { "epoch": 6.45, "learning_rate": 9.854378501835695e-05, "loss": 0.5452, "step": 26960 }, { "epoch": 6.46, "learning_rate": 9.854270981924203e-05, "loss": 0.5598, "step": 26970 }, { "epoch": 6.46, "learning_rate": 9.854163422920597e-05, "loss": 0.5034, "step": 26980 }, { "epoch": 6.46, "learning_rate": 9.854055824825742e-05, "loss": 0.4819, "step": 26990 }, { "epoch": 6.46, "learning_rate": 9.853948187640504e-05, "loss": 0.5228, "step": 27000 }, { "epoch": 6.46, "learning_rate": 9.853840511365756e-05, "loss": 0.525, "step": 27010 }, { "epoch": 6.47, "learning_rate": 9.853732796002355e-05, "loss": 0.4708, "step": 27020 }, { "epoch": 6.47, "learning_rate": 9.853625041551175e-05, "loss": 0.4827, "step": 27030 }, { "epoch": 6.47, "learning_rate": 9.853517248013085e-05, "loss": 0.4895, "step": 27040 }, { "epoch": 6.47, "learning_rate": 9.853409415388948e-05, "loss": 0.496, "step": 27050 }, { "epoch": 6.48, "learning_rate": 9.853301543679636e-05, "loss": 0.5371, "step": 27060 }, { "epoch": 6.48, "learning_rate": 9.853193632886016e-05, "loss": 0.5193, "step": 27070 }, { "epoch": 6.48, "learning_rate": 9.853085683008958e-05, "loss": 0.5177, "step": 27080 }, { "epoch": 6.48, "learning_rate": 9.852977694049331e-05, "loss": 0.5343, "step": 27090 }, { "epoch": 6.48, "learning_rate": 9.852869666008005e-05, "loss": 0.5066, "step": 27100 }, { "epoch": 6.49, "learning_rate": 9.852761598885849e-05, "loss": 0.4701, "step": 27110 }, { "epoch": 6.49, "learning_rate": 9.852653492683735e-05, "loss": 0.5278, "step": 27120 }, { "epoch": 6.49, "learning_rate": 9.852545347402531e-05, "loss": 0.5146, "step": 27130 }, { "epoch": 6.49, "learning_rate": 9.85243716304311e-05, "loss": 0.4653, "step": 27140 }, { "epoch": 6.5, "learning_rate": 9.852328939606342e-05, "loss": 0.4954, "step": 27150 }, { "epoch": 6.5, "learning_rate": 9.8522206770931e-05, "loss": 0.5092, "step": 27160 }, { "epoch": 6.5, "learning_rate": 9.852112375504254e-05, "loss": 0.5232, "step": 27170 }, { "epoch": 6.5, "learning_rate": 9.852004034840678e-05, "loss": 0.4928, "step": 27180 }, { "epoch": 6.51, "learning_rate": 9.851895655103244e-05, "loss": 0.4736, "step": 27190 }, { "epoch": 6.51, "learning_rate": 9.851787236292824e-05, "loss": 0.4882, "step": 27200 }, { "epoch": 6.51, "learning_rate": 9.851678778410292e-05, "loss": 0.5259, "step": 27210 }, { "epoch": 6.51, "learning_rate": 9.851570281456519e-05, "loss": 0.4869, "step": 27220 }, { "epoch": 6.51, "learning_rate": 9.851461745432382e-05, "loss": 0.5202, "step": 27230 }, { "epoch": 6.52, "learning_rate": 9.851353170338755e-05, "loss": 0.5347, "step": 27240 }, { "epoch": 6.52, "learning_rate": 9.85124455617651e-05, "loss": 0.5377, "step": 27250 }, { "epoch": 6.52, "learning_rate": 9.851135902946522e-05, "loss": 0.5299, "step": 27260 }, { "epoch": 6.52, "learning_rate": 9.851027210649668e-05, "loss": 0.531, "step": 27270 }, { "epoch": 6.53, "learning_rate": 9.850918479286822e-05, "loss": 0.5242, "step": 27280 }, { "epoch": 6.53, "learning_rate": 9.85080970885886e-05, "loss": 0.5348, "step": 27290 }, { "epoch": 6.53, "learning_rate": 9.850700899366658e-05, "loss": 0.5329, "step": 27300 }, { "epoch": 6.53, "learning_rate": 9.850592050811092e-05, "loss": 0.5574, "step": 27310 }, { "epoch": 6.54, "learning_rate": 9.850483163193036e-05, "loss": 0.5831, "step": 27320 }, { "epoch": 6.54, "learning_rate": 9.850374236513372e-05, "loss": 0.5798, "step": 27330 }, { "epoch": 6.54, "learning_rate": 9.850265270772974e-05, "loss": 0.6008, "step": 27340 }, { "epoch": 6.54, "learning_rate": 9.850156265972721e-05, "loss": 0.5637, "step": 27350 }, { "epoch": 6.54, "learning_rate": 9.850047222113488e-05, "loss": 0.5336, "step": 27360 }, { "epoch": 6.55, "learning_rate": 9.849938139196157e-05, "loss": 0.5544, "step": 27370 }, { "epoch": 6.55, "learning_rate": 9.849829017221604e-05, "loss": 0.5631, "step": 27380 }, { "epoch": 6.55, "learning_rate": 9.849719856190707e-05, "loss": 0.5535, "step": 27390 }, { "epoch": 6.55, "learning_rate": 9.849610656104349e-05, "loss": 0.5379, "step": 27400 }, { "epoch": 6.56, "learning_rate": 9.849501416963405e-05, "loss": 0.5632, "step": 27410 }, { "epoch": 6.56, "learning_rate": 9.849392138768758e-05, "loss": 0.5948, "step": 27420 }, { "epoch": 6.56, "learning_rate": 9.849282821521285e-05, "loss": 0.5594, "step": 27430 }, { "epoch": 6.56, "learning_rate": 9.849173465221869e-05, "loss": 0.5888, "step": 27440 }, { "epoch": 6.56, "learning_rate": 9.84906406987139e-05, "loss": 0.5744, "step": 27450 }, { "epoch": 6.57, "learning_rate": 9.848954635470726e-05, "loss": 0.5385, "step": 27460 }, { "epoch": 6.57, "learning_rate": 9.848845162020763e-05, "loss": 0.5664, "step": 27470 }, { "epoch": 6.57, "learning_rate": 9.84873564952238e-05, "loss": 0.586, "step": 27480 }, { "epoch": 6.57, "learning_rate": 9.84862609797646e-05, "loss": 0.5546, "step": 27490 }, { "epoch": 6.58, "learning_rate": 9.848516507383885e-05, "loss": 0.5405, "step": 27500 }, { "epoch": 6.58, "learning_rate": 9.848406877745536e-05, "loss": 0.5776, "step": 27510 }, { "epoch": 6.58, "learning_rate": 9.848297209062299e-05, "loss": 0.5333, "step": 27520 }, { "epoch": 6.58, "learning_rate": 9.848187501335053e-05, "loss": 0.5766, "step": 27530 }, { "epoch": 6.59, "learning_rate": 9.848077754564684e-05, "loss": 0.5354, "step": 27540 }, { "epoch": 6.59, "learning_rate": 9.847967968752076e-05, "loss": 0.5706, "step": 27550 }, { "epoch": 6.59, "learning_rate": 9.847858143898112e-05, "loss": 0.5764, "step": 27560 }, { "epoch": 6.59, "learning_rate": 9.847748280003679e-05, "loss": 0.5278, "step": 27570 }, { "epoch": 6.59, "learning_rate": 9.847638377069657e-05, "loss": 0.5619, "step": 27580 }, { "epoch": 6.6, "learning_rate": 9.847528435096936e-05, "loss": 0.5591, "step": 27590 }, { "epoch": 6.6, "learning_rate": 9.847418454086399e-05, "loss": 0.5423, "step": 27600 }, { "epoch": 6.6, "learning_rate": 9.847308434038932e-05, "loss": 0.5462, "step": 27610 }, { "epoch": 6.6, "learning_rate": 9.84719837495542e-05, "loss": 0.5423, "step": 27620 }, { "epoch": 6.61, "learning_rate": 9.847088276836752e-05, "loss": 0.5772, "step": 27630 }, { "epoch": 6.61, "learning_rate": 9.846978139683811e-05, "loss": 0.5214, "step": 27640 }, { "epoch": 6.61, "learning_rate": 9.846867963497486e-05, "loss": 0.5533, "step": 27650 }, { "epoch": 6.61, "learning_rate": 9.846757748278665e-05, "loss": 0.5522, "step": 27660 }, { "epoch": 6.62, "learning_rate": 9.846647494028236e-05, "loss": 0.508, "step": 27670 }, { "epoch": 6.62, "learning_rate": 9.846537200747083e-05, "loss": 0.5262, "step": 27680 }, { "epoch": 6.62, "learning_rate": 9.846426868436099e-05, "loss": 0.525, "step": 27690 }, { "epoch": 6.62, "learning_rate": 9.846316497096169e-05, "loss": 0.588, "step": 27700 }, { "epoch": 6.62, "learning_rate": 9.846206086728183e-05, "loss": 0.5799, "step": 27710 }, { "epoch": 6.63, "learning_rate": 9.846095637333032e-05, "loss": 0.5763, "step": 27720 }, { "epoch": 6.63, "learning_rate": 9.845985148911602e-05, "loss": 0.5342, "step": 27730 }, { "epoch": 6.63, "learning_rate": 9.845874621464785e-05, "loss": 0.5704, "step": 27740 }, { "epoch": 6.63, "learning_rate": 9.845764054993472e-05, "loss": 0.6017, "step": 27750 }, { "epoch": 6.64, "learning_rate": 9.84565344949855e-05, "loss": 0.5681, "step": 27760 }, { "epoch": 6.64, "learning_rate": 9.845542804980913e-05, "loss": 0.5017, "step": 27770 }, { "epoch": 6.64, "learning_rate": 9.84543212144145e-05, "loss": 0.5205, "step": 27780 }, { "epoch": 6.64, "learning_rate": 9.845321398881053e-05, "loss": 0.5654, "step": 27790 }, { "epoch": 6.64, "learning_rate": 9.845210637300615e-05, "loss": 0.5708, "step": 27800 }, { "epoch": 6.65, "learning_rate": 9.845099836701026e-05, "loss": 0.5486, "step": 27810 }, { "epoch": 6.65, "learning_rate": 9.84498899708318e-05, "loss": 0.6072, "step": 27820 }, { "epoch": 6.65, "learning_rate": 9.844878118447968e-05, "loss": 0.5863, "step": 27830 }, { "epoch": 6.65, "learning_rate": 9.844767200796284e-05, "loss": 0.6043, "step": 27840 }, { "epoch": 6.66, "learning_rate": 9.84465624412902e-05, "loss": 0.5556, "step": 27850 }, { "epoch": 6.66, "learning_rate": 9.844545248447072e-05, "loss": 0.5671, "step": 27860 }, { "epoch": 6.66, "learning_rate": 9.844434213751332e-05, "loss": 0.6204, "step": 27870 }, { "epoch": 6.66, "learning_rate": 9.844323140042693e-05, "loss": 0.5224, "step": 27880 }, { "epoch": 6.67, "learning_rate": 9.844212027322053e-05, "loss": 0.5405, "step": 27890 }, { "epoch": 6.67, "learning_rate": 9.844100875590303e-05, "loss": 0.5763, "step": 27900 }, { "epoch": 6.67, "learning_rate": 9.84398968484834e-05, "loss": 0.5778, "step": 27910 }, { "epoch": 6.67, "learning_rate": 9.84387845509706e-05, "loss": 0.5545, "step": 27920 }, { "epoch": 6.67, "learning_rate": 9.843767186337358e-05, "loss": 0.5097, "step": 27930 }, { "epoch": 6.68, "learning_rate": 9.84365587857013e-05, "loss": 0.5462, "step": 27940 }, { "epoch": 6.68, "learning_rate": 9.843544531796271e-05, "loss": 0.5605, "step": 27950 }, { "epoch": 6.68, "learning_rate": 9.843433146016682e-05, "loss": 0.527, "step": 27960 }, { "epoch": 6.68, "learning_rate": 9.843321721232255e-05, "loss": 0.5858, "step": 27970 }, { "epoch": 6.69, "learning_rate": 9.843210257443891e-05, "loss": 0.556, "step": 27980 }, { "epoch": 6.69, "learning_rate": 9.843098754652485e-05, "loss": 0.5248, "step": 27990 }, { "epoch": 6.69, "learning_rate": 9.842987212858936e-05, "loss": 0.5468, "step": 28000 }, { "epoch": 6.69, "learning_rate": 9.842875632064144e-05, "loss": 0.5486, "step": 28010 }, { "epoch": 6.7, "learning_rate": 9.842764012269004e-05, "loss": 0.5669, "step": 28020 }, { "epoch": 6.7, "learning_rate": 9.842652353474418e-05, "loss": 0.527, "step": 28030 }, { "epoch": 6.7, "learning_rate": 9.842540655681285e-05, "loss": 0.5353, "step": 28040 }, { "epoch": 6.7, "learning_rate": 9.842428918890502e-05, "loss": 0.4635, "step": 28050 }, { "epoch": 6.7, "learning_rate": 9.842317143102971e-05, "loss": 0.5655, "step": 28060 }, { "epoch": 6.71, "learning_rate": 9.84220532831959e-05, "loss": 0.5358, "step": 28070 }, { "epoch": 6.71, "learning_rate": 9.842093474541263e-05, "loss": 0.5871, "step": 28080 }, { "epoch": 6.71, "learning_rate": 9.841981581768887e-05, "loss": 0.525, "step": 28090 }, { "epoch": 6.71, "learning_rate": 9.841869650003365e-05, "loss": 0.5058, "step": 28100 }, { "epoch": 6.72, "learning_rate": 9.8417576792456e-05, "loss": 0.5776, "step": 28110 }, { "epoch": 6.72, "learning_rate": 9.841645669496491e-05, "loss": 0.5335, "step": 28120 }, { "epoch": 6.72, "learning_rate": 9.84153362075694e-05, "loss": 0.52, "step": 28130 }, { "epoch": 6.72, "learning_rate": 9.841421533027852e-05, "loss": 0.5613, "step": 28140 }, { "epoch": 6.72, "learning_rate": 9.841309406310127e-05, "loss": 0.5452, "step": 28150 }, { "epoch": 6.73, "learning_rate": 9.841197240604669e-05, "loss": 0.5783, "step": 28160 }, { "epoch": 6.73, "learning_rate": 9.841085035912383e-05, "loss": 0.5662, "step": 28170 }, { "epoch": 6.73, "learning_rate": 9.840972792234169e-05, "loss": 0.5655, "step": 28180 }, { "epoch": 6.73, "learning_rate": 9.840860509570932e-05, "loss": 0.5662, "step": 28190 }, { "epoch": 6.74, "learning_rate": 9.840748187923578e-05, "loss": 0.5112, "step": 28200 }, { "epoch": 6.74, "learning_rate": 9.840635827293011e-05, "loss": 0.5085, "step": 28210 }, { "epoch": 6.74, "learning_rate": 9.840523427680136e-05, "loss": 0.5306, "step": 28220 }, { "epoch": 6.74, "learning_rate": 9.840410989085857e-05, "loss": 0.4987, "step": 28230 }, { "epoch": 6.75, "learning_rate": 9.84029851151108e-05, "loss": 0.5855, "step": 28240 }, { "epoch": 6.75, "learning_rate": 9.84018599495671e-05, "loss": 0.5486, "step": 28250 }, { "epoch": 6.75, "learning_rate": 9.840073439423654e-05, "loss": 0.5452, "step": 28260 }, { "epoch": 6.75, "learning_rate": 9.839960844912819e-05, "loss": 0.4922, "step": 28270 }, { "epoch": 6.75, "learning_rate": 9.839848211425111e-05, "loss": 0.5651, "step": 28280 }, { "epoch": 6.76, "learning_rate": 9.839735538961437e-05, "loss": 0.5223, "step": 28290 }, { "epoch": 6.76, "learning_rate": 9.839622827522705e-05, "loss": 0.5281, "step": 28300 }, { "epoch": 6.76, "learning_rate": 9.839510077109821e-05, "loss": 0.5491, "step": 28310 }, { "epoch": 6.76, "learning_rate": 9.839397287723695e-05, "loss": 0.5574, "step": 28320 }, { "epoch": 6.77, "learning_rate": 9.839284459365236e-05, "loss": 0.519, "step": 28330 }, { "epoch": 6.77, "learning_rate": 9.839171592035349e-05, "loss": 0.5158, "step": 28340 }, { "epoch": 6.77, "learning_rate": 9.839058685734946e-05, "loss": 0.5437, "step": 28350 }, { "epoch": 6.77, "learning_rate": 9.838945740464935e-05, "loss": 0.5306, "step": 28360 }, { "epoch": 6.78, "learning_rate": 9.838832756226226e-05, "loss": 0.5454, "step": 28370 }, { "epoch": 6.78, "learning_rate": 9.838719733019729e-05, "loss": 0.4993, "step": 28380 }, { "epoch": 6.78, "learning_rate": 9.838606670846353e-05, "loss": 0.5279, "step": 28390 }, { "epoch": 6.78, "learning_rate": 9.838493569707012e-05, "loss": 0.5198, "step": 28400 }, { "epoch": 6.78, "learning_rate": 9.838380429602611e-05, "loss": 0.5592, "step": 28410 }, { "epoch": 6.79, "learning_rate": 9.838267250534066e-05, "loss": 0.5551, "step": 28420 }, { "epoch": 6.79, "learning_rate": 9.838154032502288e-05, "loss": 0.526, "step": 28430 }, { "epoch": 6.79, "learning_rate": 9.838040775508186e-05, "loss": 0.571, "step": 28440 }, { "epoch": 6.79, "learning_rate": 9.837927479552675e-05, "loss": 0.5617, "step": 28450 }, { "epoch": 6.8, "learning_rate": 9.837814144636665e-05, "loss": 0.5571, "step": 28460 }, { "epoch": 6.8, "learning_rate": 9.83770077076107e-05, "loss": 0.5584, "step": 28470 }, { "epoch": 6.8, "learning_rate": 9.837587357926803e-05, "loss": 0.5441, "step": 28480 }, { "epoch": 6.8, "learning_rate": 9.837473906134777e-05, "loss": 0.5391, "step": 28490 }, { "epoch": 6.8, "learning_rate": 9.837360415385905e-05, "loss": 0.5386, "step": 28500 }, { "epoch": 6.81, "learning_rate": 9.837246885681103e-05, "loss": 0.5371, "step": 28510 }, { "epoch": 6.81, "learning_rate": 9.837133317021284e-05, "loss": 0.5759, "step": 28520 }, { "epoch": 6.81, "learning_rate": 9.837019709407361e-05, "loss": 0.5425, "step": 28530 }, { "epoch": 6.81, "learning_rate": 9.836906062840252e-05, "loss": 0.5513, "step": 28540 }, { "epoch": 6.82, "learning_rate": 9.83679237732087e-05, "loss": 0.5216, "step": 28550 }, { "epoch": 6.82, "learning_rate": 9.836678652850132e-05, "loss": 0.5613, "step": 28560 }, { "epoch": 6.82, "learning_rate": 9.836564889428952e-05, "loss": 0.4722, "step": 28570 }, { "epoch": 6.82, "learning_rate": 9.836451087058249e-05, "loss": 0.4818, "step": 28580 }, { "epoch": 6.83, "learning_rate": 9.836337245738936e-05, "loss": 0.5111, "step": 28590 }, { "epoch": 6.83, "learning_rate": 9.836223365471932e-05, "loss": 0.5446, "step": 28600 }, { "epoch": 6.83, "learning_rate": 9.836109446258153e-05, "loss": 0.5101, "step": 28610 }, { "epoch": 6.83, "learning_rate": 9.835995488098517e-05, "loss": 0.5176, "step": 28620 }, { "epoch": 6.83, "learning_rate": 9.835881490993944e-05, "loss": 0.567, "step": 28630 }, { "epoch": 6.84, "learning_rate": 9.835767454945347e-05, "loss": 0.4824, "step": 28640 }, { "epoch": 6.84, "learning_rate": 9.835653379953648e-05, "loss": 0.4622, "step": 28650 }, { "epoch": 6.84, "learning_rate": 9.835539266019764e-05, "loss": 0.4841, "step": 28660 }, { "epoch": 6.84, "learning_rate": 9.835425113144616e-05, "loss": 0.502, "step": 28670 }, { "epoch": 6.85, "learning_rate": 9.835310921329121e-05, "loss": 0.5088, "step": 28680 }, { "epoch": 6.85, "learning_rate": 9.8351966905742e-05, "loss": 0.5268, "step": 28690 }, { "epoch": 6.85, "learning_rate": 9.835082420880772e-05, "loss": 0.5095, "step": 28700 }, { "epoch": 6.85, "learning_rate": 9.834968112249759e-05, "loss": 0.4982, "step": 28710 }, { "epoch": 6.86, "learning_rate": 9.83485376468208e-05, "loss": 0.527, "step": 28720 }, { "epoch": 6.86, "learning_rate": 9.834739378178654e-05, "loss": 0.518, "step": 28730 }, { "epoch": 6.86, "learning_rate": 9.834624952740407e-05, "loss": 0.5373, "step": 28740 }, { "epoch": 6.86, "learning_rate": 9.834510488368256e-05, "loss": 0.5906, "step": 28750 }, { "epoch": 6.86, "learning_rate": 9.834395985063125e-05, "loss": 0.4904, "step": 28760 }, { "epoch": 6.87, "learning_rate": 9.834281442825937e-05, "loss": 0.5201, "step": 28770 }, { "epoch": 6.87, "learning_rate": 9.834166861657613e-05, "loss": 0.486, "step": 28780 }, { "epoch": 6.87, "learning_rate": 9.834052241559074e-05, "loss": 0.5323, "step": 28790 }, { "epoch": 6.87, "learning_rate": 9.833937582531245e-05, "loss": 0.5099, "step": 28800 }, { "epoch": 6.88, "learning_rate": 9.833822884575052e-05, "loss": 0.5326, "step": 28810 }, { "epoch": 6.88, "learning_rate": 9.833708147691414e-05, "loss": 0.4868, "step": 28820 }, { "epoch": 6.88, "learning_rate": 9.833593371881255e-05, "loss": 0.6107, "step": 28830 }, { "epoch": 6.88, "learning_rate": 9.833478557145505e-05, "loss": 0.502, "step": 28840 }, { "epoch": 6.88, "learning_rate": 9.833363703485084e-05, "loss": 0.5566, "step": 28850 }, { "epoch": 6.89, "learning_rate": 9.833248810900916e-05, "loss": 0.5025, "step": 28860 }, { "epoch": 6.89, "learning_rate": 9.83313387939393e-05, "loss": 0.547, "step": 28870 }, { "epoch": 6.89, "learning_rate": 9.833018908965049e-05, "loss": 0.4913, "step": 28880 }, { "epoch": 6.89, "learning_rate": 9.832903899615198e-05, "loss": 0.5502, "step": 28890 }, { "epoch": 6.9, "learning_rate": 9.832788851345306e-05, "loss": 0.5284, "step": 28900 }, { "epoch": 6.9, "learning_rate": 9.832673764156298e-05, "loss": 0.4827, "step": 28910 }, { "epoch": 6.9, "learning_rate": 9.8325586380491e-05, "loss": 0.5174, "step": 28920 }, { "epoch": 6.9, "learning_rate": 9.832443473024642e-05, "loss": 0.525, "step": 28930 }, { "epoch": 6.91, "learning_rate": 9.83232826908385e-05, "loss": 0.451, "step": 28940 }, { "epoch": 6.91, "learning_rate": 9.83221302622765e-05, "loss": 0.5323, "step": 28950 }, { "epoch": 6.91, "learning_rate": 9.832097744456971e-05, "loss": 0.5092, "step": 28960 }, { "epoch": 6.91, "learning_rate": 9.83198242377274e-05, "loss": 0.557, "step": 28970 }, { "epoch": 6.91, "learning_rate": 9.831867064175891e-05, "loss": 0.5525, "step": 28980 }, { "epoch": 6.92, "learning_rate": 9.831751665667349e-05, "loss": 0.5024, "step": 28990 }, { "epoch": 6.92, "learning_rate": 9.831636228248042e-05, "loss": 0.5273, "step": 29000 }, { "epoch": 6.92, "learning_rate": 9.831520751918902e-05, "loss": 0.5213, "step": 29010 }, { "epoch": 6.92, "learning_rate": 9.83140523668086e-05, "loss": 0.5084, "step": 29020 }, { "epoch": 6.93, "learning_rate": 9.831289682534842e-05, "loss": 0.5125, "step": 29030 }, { "epoch": 6.93, "learning_rate": 9.831174089481783e-05, "loss": 0.4997, "step": 29040 }, { "epoch": 6.93, "learning_rate": 9.83105845752261e-05, "loss": 0.5036, "step": 29050 }, { "epoch": 6.93, "learning_rate": 9.830942786658259e-05, "loss": 0.5072, "step": 29060 }, { "epoch": 6.94, "learning_rate": 9.830827076889657e-05, "loss": 0.5293, "step": 29070 }, { "epoch": 6.94, "learning_rate": 9.830711328217739e-05, "loss": 0.4897, "step": 29080 }, { "epoch": 6.94, "learning_rate": 9.830595540643435e-05, "loss": 0.485, "step": 29090 }, { "epoch": 6.94, "learning_rate": 9.830479714167678e-05, "loss": 0.5282, "step": 29100 }, { "epoch": 6.94, "learning_rate": 9.8303638487914e-05, "loss": 0.4734, "step": 29110 }, { "epoch": 6.95, "learning_rate": 9.830247944515537e-05, "loss": 0.4871, "step": 29120 }, { "epoch": 6.95, "learning_rate": 9.830132001341019e-05, "loss": 0.5424, "step": 29130 }, { "epoch": 6.95, "learning_rate": 9.830016019268781e-05, "loss": 0.4876, "step": 29140 }, { "epoch": 7.0, "learning_rate": 9.829899998299758e-05, "loss": 0.4887, "step": 29150 }, { "epoch": 7.0, "learning_rate": 9.829783938434885e-05, "loss": 0.5291, "step": 29160 }, { "epoch": 7.01, "learning_rate": 9.829667839675092e-05, "loss": 0.535, "step": 29170 }, { "epoch": 7.01, "learning_rate": 9.829551702021319e-05, "loss": 0.4983, "step": 29180 }, { "epoch": 7.01, "learning_rate": 9.829435525474499e-05, "loss": 0.562, "step": 29190 }, { "epoch": 7.01, "learning_rate": 9.829319310035567e-05, "loss": 0.4941, "step": 29200 }, { "epoch": 7.02, "learning_rate": 9.829203055705462e-05, "loss": 0.4774, "step": 29210 }, { "epoch": 7.02, "learning_rate": 9.829086762485116e-05, "loss": 0.4887, "step": 29220 }, { "epoch": 7.02, "learning_rate": 9.828970430375469e-05, "loss": 0.5382, "step": 29230 }, { "epoch": 7.02, "learning_rate": 9.828854059377457e-05, "loss": 0.5645, "step": 29240 }, { "epoch": 7.02, "learning_rate": 9.828737649492015e-05, "loss": 0.473, "step": 29250 }, { "epoch": 7.03, "learning_rate": 9.828621200720083e-05, "loss": 0.5176, "step": 29260 }, { "epoch": 7.03, "learning_rate": 9.828504713062597e-05, "loss": 0.5192, "step": 29270 }, { "epoch": 7.03, "learning_rate": 9.828388186520496e-05, "loss": 0.5709, "step": 29280 }, { "epoch": 7.03, "learning_rate": 9.828271621094719e-05, "loss": 0.4829, "step": 29290 }, { "epoch": 7.04, "learning_rate": 9.828155016786205e-05, "loss": 0.4995, "step": 29300 }, { "epoch": 7.04, "learning_rate": 9.828038373595889e-05, "loss": 0.5285, "step": 29310 }, { "epoch": 7.04, "learning_rate": 9.827921691524716e-05, "loss": 0.504, "step": 29320 }, { "epoch": 7.04, "learning_rate": 9.827804970573621e-05, "loss": 0.4835, "step": 29330 }, { "epoch": 7.05, "learning_rate": 9.827688210743548e-05, "loss": 0.5236, "step": 29340 }, { "epoch": 7.05, "learning_rate": 9.827571412035435e-05, "loss": 0.543, "step": 29350 }, { "epoch": 7.05, "learning_rate": 9.827454574450223e-05, "loss": 0.5568, "step": 29360 }, { "epoch": 7.05, "learning_rate": 9.827337697988852e-05, "loss": 0.4632, "step": 29370 }, { "epoch": 7.05, "learning_rate": 9.827220782652266e-05, "loss": 0.5351, "step": 29380 }, { "epoch": 7.06, "learning_rate": 9.827103828441402e-05, "loss": 0.481, "step": 29390 }, { "epoch": 7.06, "learning_rate": 9.826986835357206e-05, "loss": 0.5298, "step": 29400 }, { "epoch": 7.06, "learning_rate": 9.826869803400618e-05, "loss": 0.4456, "step": 29410 }, { "epoch": 7.06, "learning_rate": 9.826752732572582e-05, "loss": 0.4635, "step": 29420 }, { "epoch": 7.07, "learning_rate": 9.826635622874039e-05, "loss": 0.5136, "step": 29430 }, { "epoch": 7.07, "learning_rate": 9.826518474305932e-05, "loss": 0.511, "step": 29440 }, { "epoch": 7.07, "learning_rate": 9.826401286869208e-05, "loss": 0.5402, "step": 29450 }, { "epoch": 7.07, "learning_rate": 9.826284060564807e-05, "loss": 0.487, "step": 29460 }, { "epoch": 7.08, "learning_rate": 9.826166795393674e-05, "loss": 0.4852, "step": 29470 }, { "epoch": 7.08, "learning_rate": 9.826049491356752e-05, "loss": 0.4494, "step": 29480 }, { "epoch": 7.08, "learning_rate": 9.825932148454989e-05, "loss": 0.5185, "step": 29490 }, { "epoch": 7.08, "learning_rate": 9.825814766689327e-05, "loss": 0.5222, "step": 29500 }, { "epoch": 7.08, "learning_rate": 9.825697346060714e-05, "loss": 0.5505, "step": 29510 }, { "epoch": 7.09, "learning_rate": 9.825579886570093e-05, "loss": 0.5195, "step": 29520 }, { "epoch": 7.09, "learning_rate": 9.825462388218411e-05, "loss": 0.5731, "step": 29530 }, { "epoch": 7.09, "learning_rate": 9.825344851006615e-05, "loss": 0.4988, "step": 29540 }, { "epoch": 7.09, "learning_rate": 9.825227274935649e-05, "loss": 0.4864, "step": 29550 }, { "epoch": 7.1, "learning_rate": 9.825109660006464e-05, "loss": 0.5133, "step": 29560 }, { "epoch": 7.1, "learning_rate": 9.824992006220001e-05, "loss": 0.4767, "step": 29570 }, { "epoch": 7.1, "learning_rate": 9.824874313577214e-05, "loss": 0.5255, "step": 29580 }, { "epoch": 7.1, "learning_rate": 9.824756582079049e-05, "loss": 0.5201, "step": 29590 }, { "epoch": 7.1, "learning_rate": 9.82463881172645e-05, "loss": 0.5224, "step": 29600 }, { "epoch": 7.11, "learning_rate": 9.824521002520371e-05, "loss": 0.4914, "step": 29610 }, { "epoch": 7.11, "learning_rate": 9.824403154461759e-05, "loss": 0.4974, "step": 29620 }, { "epoch": 7.11, "learning_rate": 9.82428526755156e-05, "loss": 0.5303, "step": 29630 }, { "epoch": 7.11, "learning_rate": 9.824167341790726e-05, "loss": 0.5035, "step": 29640 }, { "epoch": 7.12, "learning_rate": 9.824049377180207e-05, "loss": 0.5413, "step": 29650 }, { "epoch": 7.12, "learning_rate": 9.823931373720954e-05, "loss": 0.4998, "step": 29660 }, { "epoch": 7.12, "learning_rate": 9.823813331413914e-05, "loss": 0.4822, "step": 29670 }, { "epoch": 7.12, "learning_rate": 9.823695250260039e-05, "loss": 0.5102, "step": 29680 }, { "epoch": 7.13, "learning_rate": 9.82357713026028e-05, "loss": 0.5171, "step": 29690 }, { "epoch": 7.13, "learning_rate": 9.82345897141559e-05, "loss": 0.4992, "step": 29700 }, { "epoch": 7.13, "learning_rate": 9.823340773726917e-05, "loss": 0.5094, "step": 29710 }, { "epoch": 7.13, "learning_rate": 9.823222537195216e-05, "loss": 0.4453, "step": 29720 }, { "epoch": 7.13, "learning_rate": 9.823104261821438e-05, "loss": 0.4745, "step": 29730 }, { "epoch": 7.14, "learning_rate": 9.822985947606536e-05, "loss": 0.4822, "step": 29740 }, { "epoch": 7.14, "learning_rate": 9.822867594551462e-05, "loss": 0.4547, "step": 29750 }, { "epoch": 7.14, "learning_rate": 9.822749202657169e-05, "loss": 0.473, "step": 29760 }, { "epoch": 7.14, "learning_rate": 9.82263077192461e-05, "loss": 0.522, "step": 29770 }, { "epoch": 7.15, "learning_rate": 9.82251230235474e-05, "loss": 0.4612, "step": 29780 }, { "epoch": 7.15, "learning_rate": 9.822393793948514e-05, "loss": 0.4911, "step": 29790 }, { "epoch": 7.15, "learning_rate": 9.822275246706885e-05, "loss": 0.4429, "step": 29800 }, { "epoch": 7.15, "learning_rate": 9.822156660630806e-05, "loss": 0.5472, "step": 29810 }, { "epoch": 7.16, "learning_rate": 9.822038035721235e-05, "loss": 0.4823, "step": 29820 }, { "epoch": 7.16, "learning_rate": 9.821919371979124e-05, "loss": 0.4704, "step": 29830 }, { "epoch": 7.16, "learning_rate": 9.821800669405433e-05, "loss": 0.4852, "step": 29840 }, { "epoch": 7.16, "learning_rate": 9.821681928001114e-05, "loss": 0.4954, "step": 29850 }, { "epoch": 7.16, "learning_rate": 9.821563147767125e-05, "loss": 0.5068, "step": 29860 }, { "epoch": 7.17, "learning_rate": 9.821444328704423e-05, "loss": 0.5198, "step": 29870 }, { "epoch": 7.17, "learning_rate": 9.821325470813965e-05, "loss": 0.4565, "step": 29880 }, { "epoch": 7.17, "learning_rate": 9.821206574096706e-05, "loss": 0.4917, "step": 29890 }, { "epoch": 7.17, "learning_rate": 9.821087638553605e-05, "loss": 0.4946, "step": 29900 }, { "epoch": 7.18, "learning_rate": 9.820968664185619e-05, "loss": 0.5185, "step": 29910 }, { "epoch": 7.18, "learning_rate": 9.820849650993709e-05, "loss": 0.4692, "step": 29920 }, { "epoch": 7.18, "learning_rate": 9.82073059897883e-05, "loss": 0.5358, "step": 29930 }, { "epoch": 7.18, "learning_rate": 9.820611508141941e-05, "loss": 0.4242, "step": 29940 }, { "epoch": 7.18, "learning_rate": 9.820492378484003e-05, "loss": 0.4705, "step": 29950 }, { "epoch": 7.19, "learning_rate": 9.820373210005973e-05, "loss": 0.4868, "step": 29960 }, { "epoch": 7.19, "learning_rate": 9.820254002708813e-05, "loss": 0.5474, "step": 29970 }, { "epoch": 7.19, "learning_rate": 9.820134756593482e-05, "loss": 0.4441, "step": 29980 }, { "epoch": 7.19, "learning_rate": 9.820015471660941e-05, "loss": 0.5077, "step": 29990 }, { "epoch": 7.2, "learning_rate": 9.819896147912148e-05, "loss": 0.5336, "step": 30000 }, { "epoch": 7.2, "learning_rate": 9.819776785348069e-05, "loss": 0.4829, "step": 30010 }, { "epoch": 7.2, "learning_rate": 9.81965738396966e-05, "loss": 0.5164, "step": 30020 }, { "epoch": 7.2, "learning_rate": 9.819537943777886e-05, "loss": 0.4607, "step": 30030 }, { "epoch": 7.21, "learning_rate": 9.819418464773706e-05, "loss": 0.4927, "step": 30040 }, { "epoch": 7.21, "learning_rate": 9.819298946958084e-05, "loss": 0.4998, "step": 30050 }, { "epoch": 7.21, "learning_rate": 9.819179390331983e-05, "loss": 0.5436, "step": 30060 }, { "epoch": 7.21, "learning_rate": 9.819059794896365e-05, "loss": 0.4615, "step": 30070 }, { "epoch": 7.21, "learning_rate": 9.818940160652193e-05, "loss": 0.4685, "step": 30080 }, { "epoch": 7.22, "learning_rate": 9.81882048760043e-05, "loss": 0.5559, "step": 30090 }, { "epoch": 7.22, "learning_rate": 9.81870077574204e-05, "loss": 0.5084, "step": 30100 }, { "epoch": 7.22, "learning_rate": 9.818581025077989e-05, "loss": 0.476, "step": 30110 }, { "epoch": 7.22, "learning_rate": 9.818461235609238e-05, "loss": 0.4936, "step": 30120 }, { "epoch": 7.23, "learning_rate": 9.818341407336756e-05, "loss": 0.4845, "step": 30130 }, { "epoch": 7.23, "learning_rate": 9.818221540261503e-05, "loss": 0.5204, "step": 30140 }, { "epoch": 7.23, "learning_rate": 9.818101634384446e-05, "loss": 0.45, "step": 30150 }, { "epoch": 7.23, "learning_rate": 9.817981689706555e-05, "loss": 0.5129, "step": 30160 }, { "epoch": 7.24, "learning_rate": 9.81786170622879e-05, "loss": 0.5038, "step": 30170 }, { "epoch": 7.24, "learning_rate": 9.81774168395212e-05, "loss": 0.4578, "step": 30180 }, { "epoch": 7.24, "learning_rate": 9.817621622877511e-05, "loss": 0.4806, "step": 30190 }, { "epoch": 7.24, "learning_rate": 9.81750152300593e-05, "loss": 0.5311, "step": 30200 }, { "epoch": 7.24, "learning_rate": 9.817381384338343e-05, "loss": 0.469, "step": 30210 }, { "epoch": 7.25, "learning_rate": 9.81726120687572e-05, "loss": 0.5017, "step": 30220 }, { "epoch": 7.25, "learning_rate": 9.817140990619027e-05, "loss": 0.5345, "step": 30230 }, { "epoch": 7.25, "learning_rate": 9.817020735569231e-05, "loss": 0.5167, "step": 30240 }, { "epoch": 7.25, "learning_rate": 9.816900441727305e-05, "loss": 0.4873, "step": 30250 }, { "epoch": 7.26, "learning_rate": 9.816780109094213e-05, "loss": 0.4887, "step": 30260 }, { "epoch": 7.26, "learning_rate": 9.816659737670925e-05, "loss": 0.5151, "step": 30270 }, { "epoch": 7.26, "learning_rate": 9.816539327458413e-05, "loss": 0.5032, "step": 30280 }, { "epoch": 7.26, "learning_rate": 9.816418878457644e-05, "loss": 0.4982, "step": 30290 }, { "epoch": 7.26, "learning_rate": 9.816298390669589e-05, "loss": 0.4405, "step": 30300 }, { "epoch": 7.27, "learning_rate": 9.816177864095217e-05, "loss": 0.4818, "step": 30310 }, { "epoch": 7.27, "learning_rate": 9.816057298735501e-05, "loss": 0.4995, "step": 30320 }, { "epoch": 7.27, "learning_rate": 9.81593669459141e-05, "loss": 0.4904, "step": 30330 }, { "epoch": 7.27, "learning_rate": 9.815816051663917e-05, "loss": 0.5032, "step": 30340 }, { "epoch": 7.28, "learning_rate": 9.815695369953993e-05, "loss": 0.4813, "step": 30350 }, { "epoch": 7.28, "learning_rate": 9.815574649462607e-05, "loss": 0.4962, "step": 30360 }, { "epoch": 7.28, "learning_rate": 9.815453890190735e-05, "loss": 0.5209, "step": 30370 }, { "epoch": 7.28, "learning_rate": 9.815333092139347e-05, "loss": 0.4988, "step": 30380 }, { "epoch": 7.29, "learning_rate": 9.815212255309418e-05, "loss": 0.4503, "step": 30390 }, { "epoch": 7.29, "learning_rate": 9.81509137970192e-05, "loss": 0.4299, "step": 30400 }, { "epoch": 7.29, "learning_rate": 9.814970465317825e-05, "loss": 0.4726, "step": 30410 }, { "epoch": 7.29, "learning_rate": 9.814849512158109e-05, "loss": 0.474, "step": 30420 }, { "epoch": 7.29, "learning_rate": 9.814728520223744e-05, "loss": 0.4602, "step": 30430 }, { "epoch": 7.3, "learning_rate": 9.814607489515707e-05, "loss": 0.4762, "step": 30440 }, { "epoch": 7.3, "learning_rate": 9.814486420034971e-05, "loss": 0.5162, "step": 30450 }, { "epoch": 7.3, "learning_rate": 9.814365311782511e-05, "loss": 0.4604, "step": 30460 }, { "epoch": 7.3, "learning_rate": 9.814244164759302e-05, "loss": 0.4872, "step": 30470 }, { "epoch": 7.31, "learning_rate": 9.81412297896632e-05, "loss": 0.436, "step": 30480 }, { "epoch": 7.31, "learning_rate": 9.814001754404543e-05, "loss": 0.4881, "step": 30490 }, { "epoch": 7.31, "learning_rate": 9.813880491074942e-05, "loss": 0.475, "step": 30500 }, { "epoch": 7.31, "learning_rate": 9.8137591889785e-05, "loss": 0.5271, "step": 30510 }, { "epoch": 7.32, "learning_rate": 9.813637848116188e-05, "loss": 0.4672, "step": 30520 }, { "epoch": 7.32, "learning_rate": 9.813516468488988e-05, "loss": 0.4925, "step": 30530 }, { "epoch": 7.32, "learning_rate": 9.813395050097874e-05, "loss": 0.4555, "step": 30540 }, { "epoch": 7.32, "learning_rate": 9.813273592943825e-05, "loss": 0.4473, "step": 30550 }, { "epoch": 7.32, "learning_rate": 9.81315209702782e-05, "loss": 0.4964, "step": 30560 }, { "epoch": 7.33, "learning_rate": 9.813030562350835e-05, "loss": 0.4753, "step": 30570 }, { "epoch": 7.33, "learning_rate": 9.812908988913854e-05, "loss": 0.5083, "step": 30580 }, { "epoch": 7.33, "learning_rate": 9.812787376717849e-05, "loss": 0.456, "step": 30590 }, { "epoch": 7.33, "learning_rate": 9.812665725763805e-05, "loss": 0.4526, "step": 30600 }, { "epoch": 7.34, "learning_rate": 9.812544036052697e-05, "loss": 0.5087, "step": 30610 }, { "epoch": 7.34, "learning_rate": 9.81242230758551e-05, "loss": 0.4693, "step": 30620 }, { "epoch": 7.34, "learning_rate": 9.812300540363221e-05, "loss": 0.5131, "step": 30630 }, { "epoch": 7.34, "learning_rate": 9.812178734386811e-05, "loss": 0.4694, "step": 30640 }, { "epoch": 7.34, "learning_rate": 9.812056889657262e-05, "loss": 0.4752, "step": 30650 }, { "epoch": 7.35, "learning_rate": 9.811935006175553e-05, "loss": 0.5498, "step": 30660 }, { "epoch": 7.35, "learning_rate": 9.811813083942668e-05, "loss": 0.4703, "step": 30670 }, { "epoch": 7.35, "learning_rate": 9.811691122959588e-05, "loss": 0.4203, "step": 30680 }, { "epoch": 7.35, "learning_rate": 9.811569123227295e-05, "loss": 0.5095, "step": 30690 }, { "epoch": 7.36, "learning_rate": 9.811447084746772e-05, "loss": 0.5273, "step": 30700 }, { "epoch": 7.36, "learning_rate": 9.811325007519001e-05, "loss": 0.4602, "step": 30710 }, { "epoch": 7.36, "learning_rate": 9.811202891544965e-05, "loss": 0.5256, "step": 30720 }, { "epoch": 7.36, "learning_rate": 9.811080736825649e-05, "loss": 0.4479, "step": 30730 }, { "epoch": 7.37, "learning_rate": 9.810958543362034e-05, "loss": 0.5136, "step": 30740 }, { "epoch": 7.37, "learning_rate": 9.810836311155107e-05, "loss": 0.5074, "step": 30750 }, { "epoch": 7.37, "learning_rate": 9.810714040205851e-05, "loss": 0.4891, "step": 30760 }, { "epoch": 7.37, "learning_rate": 9.81059173051525e-05, "loss": 0.4996, "step": 30770 }, { "epoch": 7.37, "learning_rate": 9.81046938208429e-05, "loss": 0.4801, "step": 30780 }, { "epoch": 7.38, "learning_rate": 9.810346994913955e-05, "loss": 0.4884, "step": 30790 }, { "epoch": 7.38, "learning_rate": 9.810224569005233e-05, "loss": 0.4596, "step": 30800 }, { "epoch": 7.38, "learning_rate": 9.810102104359108e-05, "loss": 0.4729, "step": 30810 }, { "epoch": 7.38, "learning_rate": 9.809979600976567e-05, "loss": 0.4865, "step": 30820 }, { "epoch": 7.39, "learning_rate": 9.809857058858596e-05, "loss": 0.447, "step": 30830 }, { "epoch": 7.39, "learning_rate": 9.80973447800618e-05, "loss": 0.53, "step": 30840 }, { "epoch": 7.39, "learning_rate": 9.809611858420312e-05, "loss": 0.4779, "step": 30850 }, { "epoch": 7.39, "learning_rate": 9.809489200101973e-05, "loss": 0.4697, "step": 30860 }, { "epoch": 7.4, "learning_rate": 9.809366503052153e-05, "loss": 0.4476, "step": 30870 }, { "epoch": 7.4, "learning_rate": 9.809243767271843e-05, "loss": 0.486, "step": 30880 }, { "epoch": 7.4, "learning_rate": 9.809120992762027e-05, "loss": 0.5143, "step": 30890 }, { "epoch": 7.4, "learning_rate": 9.808998179523696e-05, "loss": 0.4825, "step": 30900 }, { "epoch": 7.4, "learning_rate": 9.80887532755784e-05, "loss": 0.42, "step": 30910 }, { "epoch": 7.41, "learning_rate": 9.808752436865447e-05, "loss": 0.4972, "step": 30920 }, { "epoch": 7.41, "learning_rate": 9.808629507447505e-05, "loss": 0.4716, "step": 30930 }, { "epoch": 7.41, "learning_rate": 9.808506539305007e-05, "loss": 0.5254, "step": 30940 }, { "epoch": 7.41, "learning_rate": 9.808383532438941e-05, "loss": 0.4454, "step": 30950 }, { "epoch": 7.42, "learning_rate": 9.808260486850301e-05, "loss": 0.4776, "step": 30960 }, { "epoch": 7.42, "learning_rate": 9.808137402540072e-05, "loss": 0.4712, "step": 30970 }, { "epoch": 7.42, "learning_rate": 9.808014279509252e-05, "loss": 0.4738, "step": 30980 }, { "epoch": 7.42, "learning_rate": 9.807891117758827e-05, "loss": 0.4678, "step": 30990 }, { "epoch": 7.42, "learning_rate": 9.807767917289792e-05, "loss": 0.4614, "step": 31000 }, { "epoch": 7.43, "learning_rate": 9.807644678103139e-05, "loss": 0.4816, "step": 31010 }, { "epoch": 7.43, "learning_rate": 9.807521400199857e-05, "loss": 0.4543, "step": 31020 }, { "epoch": 7.43, "learning_rate": 9.807398083580943e-05, "loss": 0.4894, "step": 31030 }, { "epoch": 7.43, "learning_rate": 9.807274728247389e-05, "loss": 0.4954, "step": 31040 }, { "epoch": 7.44, "learning_rate": 9.807151334200187e-05, "loss": 0.5159, "step": 31050 }, { "epoch": 7.44, "learning_rate": 9.807027901440334e-05, "loss": 0.4006, "step": 31060 }, { "epoch": 7.44, "learning_rate": 9.806904429968818e-05, "loss": 0.4261, "step": 31070 }, { "epoch": 7.44, "learning_rate": 9.80678091978664e-05, "loss": 0.4051, "step": 31080 }, { "epoch": 7.45, "learning_rate": 9.80665737089479e-05, "loss": 0.5325, "step": 31090 }, { "epoch": 7.45, "learning_rate": 9.806533783294265e-05, "loss": 0.4896, "step": 31100 }, { "epoch": 7.45, "learning_rate": 9.80641015698606e-05, "loss": 0.4827, "step": 31110 }, { "epoch": 7.45, "learning_rate": 9.806286491971171e-05, "loss": 0.4575, "step": 31120 }, { "epoch": 7.45, "learning_rate": 9.806162788250593e-05, "loss": 0.4861, "step": 31130 }, { "epoch": 7.46, "learning_rate": 9.806039045825322e-05, "loss": 0.5113, "step": 31140 }, { "epoch": 7.46, "learning_rate": 9.805915264696354e-05, "loss": 0.4824, "step": 31150 }, { "epoch": 7.46, "learning_rate": 9.805791444864688e-05, "loss": 0.4657, "step": 31160 }, { "epoch": 7.46, "learning_rate": 9.80566758633132e-05, "loss": 0.432, "step": 31170 }, { "epoch": 7.47, "learning_rate": 9.805543689097248e-05, "loss": 0.4812, "step": 31180 }, { "epoch": 7.47, "learning_rate": 9.805419753163469e-05, "loss": 0.505, "step": 31190 }, { "epoch": 7.47, "learning_rate": 9.80529577853098e-05, "loss": 0.4588, "step": 31200 }, { "epoch": 7.47, "learning_rate": 9.805171765200782e-05, "loss": 0.4883, "step": 31210 }, { "epoch": 7.48, "learning_rate": 9.805047713173874e-05, "loss": 0.4565, "step": 31220 }, { "epoch": 7.48, "learning_rate": 9.804923622451251e-05, "loss": 0.4555, "step": 31230 }, { "epoch": 7.48, "learning_rate": 9.804799493033914e-05, "loss": 0.4931, "step": 31240 }, { "epoch": 7.48, "learning_rate": 9.804675324922865e-05, "loss": 0.4016, "step": 31250 }, { "epoch": 7.48, "learning_rate": 9.804551118119103e-05, "loss": 0.4993, "step": 31260 }, { "epoch": 7.49, "learning_rate": 9.804426872623626e-05, "loss": 0.5038, "step": 31270 }, { "epoch": 7.49, "learning_rate": 9.804302588437437e-05, "loss": 0.4769, "step": 31280 }, { "epoch": 7.49, "learning_rate": 9.804178265561534e-05, "loss": 0.5052, "step": 31290 }, { "epoch": 7.49, "learning_rate": 9.804053903996923e-05, "loss": 0.482, "step": 31300 }, { "epoch": 7.5, "learning_rate": 9.803929503744601e-05, "loss": 0.5015, "step": 31310 }, { "epoch": 7.5, "learning_rate": 9.803805064805571e-05, "loss": 0.5012, "step": 31320 }, { "epoch": 7.5, "learning_rate": 9.803680587180837e-05, "loss": 0.4482, "step": 31330 }, { "epoch": 7.5, "learning_rate": 9.8035560708714e-05, "loss": 0.5171, "step": 31340 }, { "epoch": 7.5, "learning_rate": 9.803431515878262e-05, "loss": 0.4409, "step": 31350 }, { "epoch": 7.51, "learning_rate": 9.803306922202426e-05, "loss": 0.4865, "step": 31360 }, { "epoch": 7.51, "learning_rate": 9.803182289844899e-05, "loss": 0.4338, "step": 31370 }, { "epoch": 7.51, "learning_rate": 9.803057618806679e-05, "loss": 0.4592, "step": 31380 }, { "epoch": 7.51, "learning_rate": 9.802932909088775e-05, "loss": 0.457, "step": 31390 }, { "epoch": 7.52, "learning_rate": 9.802808160692188e-05, "loss": 0.4662, "step": 31400 }, { "epoch": 7.52, "learning_rate": 9.802683373617924e-05, "loss": 0.4702, "step": 31410 }, { "epoch": 7.52, "learning_rate": 9.80255854786699e-05, "loss": 0.4748, "step": 31420 }, { "epoch": 7.52, "learning_rate": 9.802433683440386e-05, "loss": 0.4835, "step": 31430 }, { "epoch": 7.53, "learning_rate": 9.80230878033912e-05, "loss": 0.4635, "step": 31440 }, { "epoch": 7.53, "learning_rate": 9.8021838385642e-05, "loss": 0.5284, "step": 31450 }, { "epoch": 7.53, "learning_rate": 9.802058858116631e-05, "loss": 0.5218, "step": 31460 }, { "epoch": 7.53, "learning_rate": 9.801933838997417e-05, "loss": 0.5334, "step": 31470 }, { "epoch": 7.53, "learning_rate": 9.801808781207568e-05, "loss": 0.5625, "step": 31480 }, { "epoch": 7.54, "learning_rate": 9.801683684748091e-05, "loss": 0.4805, "step": 31490 }, { "epoch": 7.54, "learning_rate": 9.801558549619992e-05, "loss": 0.5243, "step": 31500 }, { "epoch": 7.54, "learning_rate": 9.801433375824278e-05, "loss": 0.5818, "step": 31510 }, { "epoch": 7.54, "learning_rate": 9.80130816336196e-05, "loss": 0.5355, "step": 31520 }, { "epoch": 7.55, "learning_rate": 9.801182912234044e-05, "loss": 0.545, "step": 31530 }, { "epoch": 7.55, "learning_rate": 9.801057622441537e-05, "loss": 0.4656, "step": 31540 }, { "epoch": 7.55, "learning_rate": 9.800932293985452e-05, "loss": 0.5731, "step": 31550 }, { "epoch": 7.55, "learning_rate": 9.800806926866796e-05, "loss": 0.5371, "step": 31560 }, { "epoch": 7.56, "learning_rate": 9.800681521086578e-05, "loss": 0.4843, "step": 31570 }, { "epoch": 7.56, "learning_rate": 9.800556076645811e-05, "loss": 0.5279, "step": 31580 }, { "epoch": 7.56, "learning_rate": 9.800430593545502e-05, "loss": 0.5682, "step": 31590 }, { "epoch": 7.56, "learning_rate": 9.800305071786664e-05, "loss": 0.513, "step": 31600 }, { "epoch": 7.56, "learning_rate": 9.800179511370304e-05, "loss": 0.5551, "step": 31610 }, { "epoch": 7.57, "learning_rate": 9.800053912297438e-05, "loss": 0.5373, "step": 31620 }, { "epoch": 7.57, "learning_rate": 9.799928274569075e-05, "loss": 0.5036, "step": 31630 }, { "epoch": 7.57, "learning_rate": 9.799802598186226e-05, "loss": 0.5374, "step": 31640 }, { "epoch": 7.57, "learning_rate": 9.799676883149904e-05, "loss": 0.4593, "step": 31650 }, { "epoch": 7.58, "learning_rate": 9.799551129461121e-05, "loss": 0.5783, "step": 31660 }, { "epoch": 7.58, "learning_rate": 9.799425337120891e-05, "loss": 0.5337, "step": 31670 }, { "epoch": 7.58, "learning_rate": 9.799299506130226e-05, "loss": 0.5489, "step": 31680 }, { "epoch": 7.58, "learning_rate": 9.79917363649014e-05, "loss": 0.5195, "step": 31690 }, { "epoch": 7.58, "learning_rate": 9.799047728201644e-05, "loss": 0.5311, "step": 31700 }, { "epoch": 7.59, "learning_rate": 9.798921781265756e-05, "loss": 0.4959, "step": 31710 }, { "epoch": 7.59, "learning_rate": 9.798795795683489e-05, "loss": 0.5181, "step": 31720 }, { "epoch": 7.59, "learning_rate": 9.798669771455855e-05, "loss": 0.5164, "step": 31730 }, { "epoch": 7.59, "learning_rate": 9.798543708583872e-05, "loss": 0.503, "step": 31740 }, { "epoch": 7.6, "learning_rate": 9.798417607068554e-05, "loss": 0.5037, "step": 31750 }, { "epoch": 7.6, "learning_rate": 9.798291466910916e-05, "loss": 0.4927, "step": 31760 }, { "epoch": 7.6, "learning_rate": 9.798165288111975e-05, "loss": 0.4835, "step": 31770 }, { "epoch": 7.6, "learning_rate": 9.798039070672746e-05, "loss": 0.5086, "step": 31780 }, { "epoch": 7.61, "learning_rate": 9.797912814594247e-05, "loss": 0.5281, "step": 31790 }, { "epoch": 7.61, "learning_rate": 9.797786519877492e-05, "loss": 0.5001, "step": 31800 }, { "epoch": 7.61, "learning_rate": 9.7976601865235e-05, "loss": 0.4286, "step": 31810 }, { "epoch": 7.61, "learning_rate": 9.797533814533291e-05, "loss": 0.452, "step": 31820 }, { "epoch": 7.61, "learning_rate": 9.797407403907876e-05, "loss": 0.59, "step": 31830 }, { "epoch": 7.62, "learning_rate": 9.797280954648279e-05, "loss": 0.5334, "step": 31840 }, { "epoch": 7.62, "learning_rate": 9.797154466755516e-05, "loss": 0.507, "step": 31850 }, { "epoch": 7.62, "learning_rate": 9.797027940230606e-05, "loss": 0.5178, "step": 31860 }, { "epoch": 7.62, "learning_rate": 9.796901375074567e-05, "loss": 0.4952, "step": 31870 }, { "epoch": 7.63, "learning_rate": 9.79677477128842e-05, "loss": 0.5122, "step": 31880 }, { "epoch": 7.63, "learning_rate": 9.796648128873181e-05, "loss": 0.5599, "step": 31890 }, { "epoch": 7.63, "learning_rate": 9.796521447829876e-05, "loss": 0.4861, "step": 31900 }, { "epoch": 7.63, "learning_rate": 9.796394728159519e-05, "loss": 0.5293, "step": 31910 }, { "epoch": 7.64, "learning_rate": 9.796267969863133e-05, "loss": 0.5015, "step": 31920 }, { "epoch": 7.64, "learning_rate": 9.79614117294174e-05, "loss": 0.4827, "step": 31930 }, { "epoch": 7.64, "learning_rate": 9.79601433739636e-05, "loss": 0.5409, "step": 31940 }, { "epoch": 7.64, "learning_rate": 9.795887463228013e-05, "loss": 0.5353, "step": 31950 }, { "epoch": 7.64, "learning_rate": 9.795760550437724e-05, "loss": 0.4785, "step": 31960 }, { "epoch": 7.65, "learning_rate": 9.795633599026512e-05, "loss": 0.4823, "step": 31970 }, { "epoch": 7.65, "learning_rate": 9.795506608995402e-05, "loss": 0.5019, "step": 31980 }, { "epoch": 7.65, "learning_rate": 9.795379580345414e-05, "loss": 0.5112, "step": 31990 }, { "epoch": 7.65, "learning_rate": 9.795252513077572e-05, "loss": 0.5533, "step": 32000 }, { "epoch": 7.66, "learning_rate": 9.7951254071929e-05, "loss": 0.5346, "step": 32010 }, { "epoch": 7.66, "learning_rate": 9.794998262692421e-05, "loss": 0.5329, "step": 32020 }, { "epoch": 7.66, "learning_rate": 9.79487107957716e-05, "loss": 0.5218, "step": 32030 }, { "epoch": 7.66, "learning_rate": 9.794743857848138e-05, "loss": 0.5276, "step": 32040 }, { "epoch": 7.66, "learning_rate": 9.794616597506383e-05, "loss": 0.462, "step": 32050 }, { "epoch": 7.67, "learning_rate": 9.794489298552919e-05, "loss": 0.5201, "step": 32060 }, { "epoch": 7.67, "learning_rate": 9.79436196098877e-05, "loss": 0.4596, "step": 32070 }, { "epoch": 7.67, "learning_rate": 9.794234584814962e-05, "loss": 0.5096, "step": 32080 }, { "epoch": 7.67, "learning_rate": 9.794107170032522e-05, "loss": 0.4615, "step": 32090 }, { "epoch": 7.68, "learning_rate": 9.793979716642473e-05, "loss": 0.491, "step": 32100 }, { "epoch": 7.68, "learning_rate": 9.793852224645845e-05, "loss": 0.52, "step": 32110 }, { "epoch": 7.68, "learning_rate": 9.793724694043664e-05, "loss": 0.4821, "step": 32120 }, { "epoch": 7.68, "learning_rate": 9.793597124836955e-05, "loss": 0.5219, "step": 32130 }, { "epoch": 7.69, "learning_rate": 9.793469517026748e-05, "loss": 0.5423, "step": 32140 }, { "epoch": 7.69, "learning_rate": 9.793341870614068e-05, "loss": 0.504, "step": 32150 }, { "epoch": 7.69, "learning_rate": 9.793214185599945e-05, "loss": 0.5374, "step": 32160 }, { "epoch": 7.69, "learning_rate": 9.793086461985406e-05, "loss": 0.53, "step": 32170 }, { "epoch": 7.69, "learning_rate": 9.792958699771479e-05, "loss": 0.4937, "step": 32180 }, { "epoch": 7.7, "learning_rate": 9.792830898959196e-05, "loss": 0.491, "step": 32190 }, { "epoch": 7.7, "learning_rate": 9.792703059549582e-05, "loss": 0.5101, "step": 32200 }, { "epoch": 7.7, "learning_rate": 9.79257518154367e-05, "loss": 0.4597, "step": 32210 }, { "epoch": 7.7, "learning_rate": 9.792447264942487e-05, "loss": 0.482, "step": 32220 }, { "epoch": 7.71, "learning_rate": 9.792319309747066e-05, "loss": 0.532, "step": 32230 }, { "epoch": 7.71, "learning_rate": 9.792191315958434e-05, "loss": 0.4979, "step": 32240 }, { "epoch": 7.71, "learning_rate": 9.792063283577627e-05, "loss": 0.4797, "step": 32250 }, { "epoch": 7.71, "learning_rate": 9.79193521260567e-05, "loss": 0.4754, "step": 32260 }, { "epoch": 7.72, "learning_rate": 9.791807103043598e-05, "loss": 0.4939, "step": 32270 }, { "epoch": 7.72, "learning_rate": 9.791678954892441e-05, "loss": 0.5006, "step": 32280 }, { "epoch": 7.72, "learning_rate": 9.791550768153233e-05, "loss": 0.5226, "step": 32290 }, { "epoch": 7.72, "learning_rate": 9.791422542827004e-05, "loss": 0.4734, "step": 32300 }, { "epoch": 7.72, "learning_rate": 9.791294278914789e-05, "loss": 0.4866, "step": 32310 }, { "epoch": 7.73, "learning_rate": 9.79116597641762e-05, "loss": 0.4747, "step": 32320 }, { "epoch": 7.73, "learning_rate": 9.791037635336529e-05, "loss": 0.4985, "step": 32330 }, { "epoch": 7.73, "learning_rate": 9.790909255672551e-05, "loss": 0.4996, "step": 32340 }, { "epoch": 7.73, "learning_rate": 9.790780837426718e-05, "loss": 0.5066, "step": 32350 }, { "epoch": 7.74, "learning_rate": 9.790652380600067e-05, "loss": 0.4781, "step": 32360 }, { "epoch": 7.74, "learning_rate": 9.790523885193631e-05, "loss": 0.4815, "step": 32370 }, { "epoch": 7.74, "learning_rate": 9.790395351208444e-05, "loss": 0.4834, "step": 32380 }, { "epoch": 7.74, "learning_rate": 9.790266778645543e-05, "loss": 0.5032, "step": 32390 }, { "epoch": 7.74, "learning_rate": 9.790138167505961e-05, "loss": 0.4404, "step": 32400 }, { "epoch": 7.75, "learning_rate": 9.790009517790735e-05, "loss": 0.5375, "step": 32410 }, { "epoch": 7.75, "learning_rate": 9.789880829500901e-05, "loss": 0.4423, "step": 32420 }, { "epoch": 7.75, "learning_rate": 9.789752102637497e-05, "loss": 0.5251, "step": 32430 }, { "epoch": 7.75, "learning_rate": 9.789623337201557e-05, "loss": 0.5035, "step": 32440 }, { "epoch": 7.76, "learning_rate": 9.78949453319412e-05, "loss": 0.5285, "step": 32450 }, { "epoch": 7.76, "learning_rate": 9.78936569061622e-05, "loss": 0.4757, "step": 32460 }, { "epoch": 7.76, "learning_rate": 9.789236809468898e-05, "loss": 0.4304, "step": 32470 }, { "epoch": 7.76, "learning_rate": 9.78910788975319e-05, "loss": 0.5035, "step": 32480 }, { "epoch": 7.77, "learning_rate": 9.788978931470138e-05, "loss": 0.4676, "step": 32490 }, { "epoch": 7.77, "learning_rate": 9.788849934620776e-05, "loss": 0.4948, "step": 32500 }, { "epoch": 7.77, "learning_rate": 9.788720899206143e-05, "loss": 0.503, "step": 32510 }, { "epoch": 7.77, "learning_rate": 9.78859182522728e-05, "loss": 0.5115, "step": 32520 }, { "epoch": 7.77, "learning_rate": 9.788462712685227e-05, "loss": 0.4586, "step": 32530 }, { "epoch": 7.78, "learning_rate": 9.78833356158102e-05, "loss": 0.476, "step": 32540 }, { "epoch": 7.78, "learning_rate": 9.788204371915705e-05, "loss": 0.4814, "step": 32550 }, { "epoch": 7.78, "learning_rate": 9.788075143690317e-05, "loss": 0.5222, "step": 32560 }, { "epoch": 7.78, "learning_rate": 9.7879458769059e-05, "loss": 0.465, "step": 32570 }, { "epoch": 7.79, "learning_rate": 9.787816571563493e-05, "loss": 0.4666, "step": 32580 }, { "epoch": 7.79, "learning_rate": 9.78768722766414e-05, "loss": 0.4572, "step": 32590 }, { "epoch": 7.79, "learning_rate": 9.78755784520888e-05, "loss": 0.4952, "step": 32600 }, { "epoch": 7.79, "learning_rate": 9.787428424198754e-05, "loss": 0.5553, "step": 32610 }, { "epoch": 7.8, "learning_rate": 9.787298964634807e-05, "loss": 0.4926, "step": 32620 }, { "epoch": 7.8, "learning_rate": 9.78716946651808e-05, "loss": 0.4849, "step": 32630 }, { "epoch": 7.8, "learning_rate": 9.787039929849617e-05, "loss": 0.4522, "step": 32640 }, { "epoch": 7.8, "learning_rate": 9.786910354630461e-05, "loss": 0.4838, "step": 32650 }, { "epoch": 7.8, "learning_rate": 9.786780740861654e-05, "loss": 0.4261, "step": 32660 }, { "epoch": 7.81, "learning_rate": 9.78665108854424e-05, "loss": 0.5132, "step": 32670 }, { "epoch": 7.81, "learning_rate": 9.786521397679266e-05, "loss": 0.4629, "step": 32680 }, { "epoch": 7.81, "learning_rate": 9.786391668267774e-05, "loss": 0.4182, "step": 32690 }, { "epoch": 7.81, "learning_rate": 9.78626190031081e-05, "loss": 0.4525, "step": 32700 }, { "epoch": 7.82, "learning_rate": 9.786132093809417e-05, "loss": 0.5025, "step": 32710 }, { "epoch": 7.82, "learning_rate": 9.78600224876464e-05, "loss": 0.4552, "step": 32720 }, { "epoch": 7.82, "learning_rate": 9.785872365177529e-05, "loss": 0.55, "step": 32730 }, { "epoch": 7.82, "learning_rate": 9.785742443049124e-05, "loss": 0.437, "step": 32740 }, { "epoch": 7.82, "learning_rate": 9.785612482380477e-05, "loss": 0.4465, "step": 32750 }, { "epoch": 7.83, "learning_rate": 9.78548248317263e-05, "loss": 0.4604, "step": 32760 }, { "epoch": 7.83, "learning_rate": 9.785352445426634e-05, "loss": 0.5025, "step": 32770 }, { "epoch": 7.83, "learning_rate": 9.785222369143533e-05, "loss": 0.4394, "step": 32780 }, { "epoch": 7.83, "learning_rate": 9.785092254324375e-05, "loss": 0.5014, "step": 32790 }, { "epoch": 7.84, "learning_rate": 9.78496210097021e-05, "loss": 0.4693, "step": 32800 }, { "epoch": 7.84, "learning_rate": 9.784831909082083e-05, "loss": 0.4553, "step": 32810 }, { "epoch": 7.84, "learning_rate": 9.784701678661045e-05, "loss": 0.4944, "step": 32820 }, { "epoch": 7.84, "learning_rate": 9.784571409708143e-05, "loss": 0.4973, "step": 32830 }, { "epoch": 7.85, "learning_rate": 9.784441102224427e-05, "loss": 0.473, "step": 32840 }, { "epoch": 7.85, "learning_rate": 9.784310756210948e-05, "loss": 0.4554, "step": 32850 }, { "epoch": 7.85, "learning_rate": 9.784180371668752e-05, "loss": 0.475, "step": 32860 }, { "epoch": 7.85, "learning_rate": 9.784049948598892e-05, "loss": 0.4994, "step": 32870 }, { "epoch": 7.85, "learning_rate": 9.783919487002417e-05, "loss": 0.4695, "step": 32880 }, { "epoch": 7.86, "learning_rate": 9.783788986880378e-05, "loss": 0.4635, "step": 32890 }, { "epoch": 7.86, "learning_rate": 9.783658448233825e-05, "loss": 0.4502, "step": 32900 }, { "epoch": 7.86, "learning_rate": 9.78352787106381e-05, "loss": 0.4823, "step": 32910 }, { "epoch": 7.86, "learning_rate": 9.783397255371387e-05, "loss": 0.468, "step": 32920 }, { "epoch": 7.87, "learning_rate": 9.783266601157603e-05, "loss": 0.4931, "step": 32930 }, { "epoch": 7.87, "learning_rate": 9.783135908423513e-05, "loss": 0.4598, "step": 32940 }, { "epoch": 7.87, "learning_rate": 9.78300517717017e-05, "loss": 0.4582, "step": 32950 }, { "epoch": 7.87, "learning_rate": 9.782874407398626e-05, "loss": 0.4684, "step": 32960 }, { "epoch": 7.88, "learning_rate": 9.782743599109934e-05, "loss": 0.4616, "step": 32970 }, { "epoch": 7.88, "learning_rate": 9.782612752305147e-05, "loss": 0.5011, "step": 32980 }, { "epoch": 7.88, "learning_rate": 9.78248186698532e-05, "loss": 0.438, "step": 32990 }, { "epoch": 7.88, "learning_rate": 9.782350943151505e-05, "loss": 0.4988, "step": 33000 }, { "epoch": 7.88, "learning_rate": 9.782219980804759e-05, "loss": 0.5066, "step": 33010 }, { "epoch": 7.89, "learning_rate": 9.782088979946136e-05, "loss": 0.4592, "step": 33020 }, { "epoch": 7.89, "learning_rate": 9.781957940576687e-05, "loss": 0.4758, "step": 33030 }, { "epoch": 7.89, "learning_rate": 9.781826862697474e-05, "loss": 0.4665, "step": 33040 }, { "epoch": 7.89, "learning_rate": 9.781695746309548e-05, "loss": 0.4019, "step": 33050 }, { "epoch": 7.9, "learning_rate": 9.781564591413965e-05, "loss": 0.4352, "step": 33060 }, { "epoch": 7.9, "learning_rate": 9.781433398011782e-05, "loss": 0.5068, "step": 33070 }, { "epoch": 7.9, "learning_rate": 9.781302166104056e-05, "loss": 0.4583, "step": 33080 }, { "epoch": 7.9, "learning_rate": 9.781170895691844e-05, "loss": 0.4745, "step": 33090 }, { "epoch": 7.9, "learning_rate": 9.781039586776203e-05, "loss": 0.4732, "step": 33100 }, { "epoch": 7.91, "learning_rate": 9.78090823935819e-05, "loss": 0.4584, "step": 33110 }, { "epoch": 7.91, "learning_rate": 9.780776853438863e-05, "loss": 0.4676, "step": 33120 }, { "epoch": 7.91, "learning_rate": 9.780645429019279e-05, "loss": 0.4453, "step": 33130 }, { "epoch": 7.91, "learning_rate": 9.7805139661005e-05, "loss": 0.5405, "step": 33140 }, { "epoch": 7.92, "learning_rate": 9.78038246468358e-05, "loss": 0.5096, "step": 33150 }, { "epoch": 7.92, "learning_rate": 9.78025092476958e-05, "loss": 0.4864, "step": 33160 }, { "epoch": 7.92, "learning_rate": 9.780119346359559e-05, "loss": 0.4533, "step": 33170 }, { "epoch": 7.92, "learning_rate": 9.779987729454577e-05, "loss": 0.4841, "step": 33180 }, { "epoch": 7.93, "learning_rate": 9.779856074055695e-05, "loss": 0.4903, "step": 33190 }, { "epoch": 7.93, "learning_rate": 9.779724380163971e-05, "loss": 0.427, "step": 33200 }, { "epoch": 7.93, "learning_rate": 9.779592647780468e-05, "loss": 0.4504, "step": 33210 }, { "epoch": 7.93, "learning_rate": 9.779460876906244e-05, "loss": 0.5264, "step": 33220 }, { "epoch": 7.93, "learning_rate": 9.779329067542362e-05, "loss": 0.4961, "step": 33230 }, { "epoch": 7.94, "learning_rate": 9.779197219689884e-05, "loss": 0.4498, "step": 33240 }, { "epoch": 7.94, "learning_rate": 9.779065333349871e-05, "loss": 0.479, "step": 33250 }, { "epoch": 7.94, "learning_rate": 9.778933408523385e-05, "loss": 0.4488, "step": 33260 }, { "epoch": 7.94, "learning_rate": 9.778801445211487e-05, "loss": 0.4543, "step": 33270 }, { "epoch": 7.95, "learning_rate": 9.778669443415244e-05, "loss": 0.4833, "step": 33280 }, { "epoch": 7.95, "learning_rate": 9.778537403135714e-05, "loss": 0.4678, "step": 33290 }, { "epoch": 7.95, "learning_rate": 9.778405324373963e-05, "loss": 0.4133, "step": 33300 }, { "epoch": 8.0, "learning_rate": 9.778273207131055e-05, "loss": 0.4455, "step": 33310 }, { "epoch": 8.0, "learning_rate": 9.778141051408052e-05, "loss": 0.423, "step": 33320 }, { "epoch": 8.01, "learning_rate": 9.77800885720602e-05, "loss": 0.451, "step": 33330 }, { "epoch": 8.01, "learning_rate": 9.777876624526023e-05, "loss": 0.4876, "step": 33340 }, { "epoch": 8.01, "learning_rate": 9.777744353369127e-05, "loss": 0.409, "step": 33350 }, { "epoch": 8.01, "learning_rate": 9.777612043736395e-05, "loss": 0.4434, "step": 33360 }, { "epoch": 8.02, "learning_rate": 9.777479695628894e-05, "loss": 0.4501, "step": 33370 }, { "epoch": 8.02, "learning_rate": 9.777347309047688e-05, "loss": 0.4373, "step": 33380 }, { "epoch": 8.02, "learning_rate": 9.777214883993846e-05, "loss": 0.4835, "step": 33390 }, { "epoch": 8.02, "learning_rate": 9.777082420468433e-05, "loss": 0.4911, "step": 33400 }, { "epoch": 8.02, "learning_rate": 9.776949918472515e-05, "loss": 0.4368, "step": 33410 }, { "epoch": 8.03, "learning_rate": 9.776817378007162e-05, "loss": 0.4511, "step": 33420 }, { "epoch": 8.03, "learning_rate": 9.776684799073437e-05, "loss": 0.4685, "step": 33430 }, { "epoch": 8.03, "learning_rate": 9.77655218167241e-05, "loss": 0.4367, "step": 33440 }, { "epoch": 8.03, "learning_rate": 9.776419525805149e-05, "loss": 0.457, "step": 33450 }, { "epoch": 8.04, "learning_rate": 9.776286831472723e-05, "loss": 0.4161, "step": 33460 }, { "epoch": 8.04, "learning_rate": 9.7761540986762e-05, "loss": 0.4767, "step": 33470 }, { "epoch": 8.04, "learning_rate": 9.776021327416647e-05, "loss": 0.4871, "step": 33480 }, { "epoch": 8.04, "learning_rate": 9.775888517695136e-05, "loss": 0.4689, "step": 33490 }, { "epoch": 8.04, "learning_rate": 9.775755669512734e-05, "loss": 0.4628, "step": 33500 }, { "epoch": 8.05, "learning_rate": 9.775622782870512e-05, "loss": 0.4817, "step": 33510 }, { "epoch": 8.05, "learning_rate": 9.775489857769543e-05, "loss": 0.4472, "step": 33520 }, { "epoch": 8.05, "learning_rate": 9.775356894210894e-05, "loss": 0.4815, "step": 33530 }, { "epoch": 8.05, "learning_rate": 9.775223892195635e-05, "loss": 0.4846, "step": 33540 }, { "epoch": 8.06, "learning_rate": 9.77509085172484e-05, "loss": 0.4333, "step": 33550 }, { "epoch": 8.06, "learning_rate": 9.77495777279958e-05, "loss": 0.447, "step": 33560 }, { "epoch": 8.06, "learning_rate": 9.774824655420925e-05, "loss": 0.4125, "step": 33570 }, { "epoch": 8.06, "learning_rate": 9.774691499589948e-05, "loss": 0.4681, "step": 33580 }, { "epoch": 8.07, "learning_rate": 9.774558305307721e-05, "loss": 0.4824, "step": 33590 }, { "epoch": 8.07, "learning_rate": 9.774425072575317e-05, "loss": 0.4461, "step": 33600 }, { "epoch": 8.07, "learning_rate": 9.774291801393807e-05, "loss": 0.4093, "step": 33610 }, { "epoch": 8.07, "learning_rate": 9.774158491764268e-05, "loss": 0.4727, "step": 33620 }, { "epoch": 8.07, "learning_rate": 9.77402514368777e-05, "loss": 0.3993, "step": 33630 }, { "epoch": 8.08, "learning_rate": 9.77389175716539e-05, "loss": 0.3986, "step": 33640 }, { "epoch": 8.08, "learning_rate": 9.7737583321982e-05, "loss": 0.4332, "step": 33650 }, { "epoch": 8.08, "learning_rate": 9.773624868787277e-05, "loss": 0.4522, "step": 33660 }, { "epoch": 8.08, "learning_rate": 9.773491366933691e-05, "loss": 0.4662, "step": 33670 }, { "epoch": 8.09, "learning_rate": 9.773357826638521e-05, "loss": 0.454, "step": 33680 }, { "epoch": 8.09, "learning_rate": 9.773224247902841e-05, "loss": 0.4117, "step": 33690 }, { "epoch": 8.09, "learning_rate": 9.773090630727729e-05, "loss": 0.4209, "step": 33700 }, { "epoch": 8.09, "learning_rate": 9.772956975114257e-05, "loss": 0.4723, "step": 33710 }, { "epoch": 8.1, "learning_rate": 9.772823281063504e-05, "loss": 0.461, "step": 33720 }, { "epoch": 8.1, "learning_rate": 9.772689548576547e-05, "loss": 0.422, "step": 33730 }, { "epoch": 8.1, "learning_rate": 9.772555777654461e-05, "loss": 0.3838, "step": 33740 }, { "epoch": 8.1, "learning_rate": 9.772421968298326e-05, "loss": 0.4842, "step": 33750 }, { "epoch": 8.1, "learning_rate": 9.772288120509217e-05, "loss": 0.4869, "step": 33760 }, { "epoch": 8.11, "learning_rate": 9.772154234288212e-05, "loss": 0.4275, "step": 33770 }, { "epoch": 8.11, "learning_rate": 9.772020309636391e-05, "loss": 0.4291, "step": 33780 }, { "epoch": 8.11, "learning_rate": 9.771886346554833e-05, "loss": 0.4584, "step": 33790 }, { "epoch": 8.11, "learning_rate": 9.771752345044614e-05, "loss": 0.4446, "step": 33800 }, { "epoch": 8.12, "learning_rate": 9.771618305106814e-05, "loss": 0.4334, "step": 33810 }, { "epoch": 8.12, "learning_rate": 9.771484226742515e-05, "loss": 0.4653, "step": 33820 }, { "epoch": 8.12, "learning_rate": 9.771350109952792e-05, "loss": 0.489, "step": 33830 }, { "epoch": 8.12, "learning_rate": 9.771215954738731e-05, "loss": 0.4773, "step": 33840 }, { "epoch": 8.12, "learning_rate": 9.771081761101406e-05, "loss": 0.4256, "step": 33850 }, { "epoch": 8.13, "learning_rate": 9.770947529041902e-05, "loss": 0.4598, "step": 33860 }, { "epoch": 8.13, "learning_rate": 9.7708132585613e-05, "loss": 0.4487, "step": 33870 }, { "epoch": 8.13, "learning_rate": 9.77067894966068e-05, "loss": 0.4394, "step": 33880 }, { "epoch": 8.13, "learning_rate": 9.770544602341123e-05, "loss": 0.5007, "step": 33890 }, { "epoch": 8.14, "learning_rate": 9.770410216603713e-05, "loss": 0.5111, "step": 33900 }, { "epoch": 8.14, "learning_rate": 9.770275792449531e-05, "loss": 0.4672, "step": 33910 }, { "epoch": 8.14, "learning_rate": 9.770141329879657e-05, "loss": 0.4186, "step": 33920 }, { "epoch": 8.14, "learning_rate": 9.770006828895178e-05, "loss": 0.3755, "step": 33930 }, { "epoch": 8.15, "learning_rate": 9.769872289497175e-05, "loss": 0.4698, "step": 33940 }, { "epoch": 8.15, "learning_rate": 9.769737711686733e-05, "loss": 0.4233, "step": 33950 }, { "epoch": 8.15, "learning_rate": 9.769603095464933e-05, "loss": 0.4811, "step": 33960 }, { "epoch": 8.15, "learning_rate": 9.769468440832861e-05, "loss": 0.4324, "step": 33970 }, { "epoch": 8.15, "learning_rate": 9.769333747791603e-05, "loss": 0.4703, "step": 33980 }, { "epoch": 8.16, "learning_rate": 9.769199016342242e-05, "loss": 0.4511, "step": 33990 }, { "epoch": 8.16, "learning_rate": 9.76906424648586e-05, "loss": 0.4722, "step": 34000 }, { "epoch": 8.16, "learning_rate": 9.768929438223546e-05, "loss": 0.4482, "step": 34010 }, { "epoch": 8.16, "learning_rate": 9.768794591556387e-05, "loss": 0.4246, "step": 34020 }, { "epoch": 8.17, "learning_rate": 9.768659706485466e-05, "loss": 0.4558, "step": 34030 }, { "epoch": 8.17, "learning_rate": 9.768524783011869e-05, "loss": 0.4478, "step": 34040 }, { "epoch": 8.17, "learning_rate": 9.768389821136684e-05, "loss": 0.4632, "step": 34050 }, { "epoch": 8.17, "learning_rate": 9.768254820860997e-05, "loss": 0.478, "step": 34060 }, { "epoch": 8.18, "learning_rate": 9.768119782185897e-05, "loss": 0.4433, "step": 34070 }, { "epoch": 8.18, "learning_rate": 9.767984705112469e-05, "loss": 0.4473, "step": 34080 }, { "epoch": 8.18, "learning_rate": 9.767849589641803e-05, "loss": 0.4491, "step": 34090 }, { "epoch": 8.18, "learning_rate": 9.767714435774984e-05, "loss": 0.4705, "step": 34100 }, { "epoch": 8.18, "learning_rate": 9.767579243513103e-05, "loss": 0.4419, "step": 34110 }, { "epoch": 8.19, "learning_rate": 9.76744401285725e-05, "loss": 0.4777, "step": 34120 }, { "epoch": 8.19, "learning_rate": 9.76730874380851e-05, "loss": 0.427, "step": 34130 }, { "epoch": 8.19, "learning_rate": 9.767173436367975e-05, "loss": 0.491, "step": 34140 }, { "epoch": 8.19, "learning_rate": 9.767038090536735e-05, "loss": 0.4336, "step": 34150 }, { "epoch": 8.2, "learning_rate": 9.766902706315879e-05, "loss": 0.4284, "step": 34160 }, { "epoch": 8.2, "learning_rate": 9.766767283706497e-05, "loss": 0.4816, "step": 34170 }, { "epoch": 8.2, "learning_rate": 9.76663182270968e-05, "loss": 0.4959, "step": 34180 }, { "epoch": 8.2, "learning_rate": 9.76649632332652e-05, "loss": 0.4713, "step": 34190 }, { "epoch": 8.2, "learning_rate": 9.766360785558106e-05, "loss": 0.4212, "step": 34200 }, { "epoch": 8.21, "learning_rate": 9.766225209405531e-05, "loss": 0.4215, "step": 34210 }, { "epoch": 8.21, "learning_rate": 9.766089594869885e-05, "loss": 0.4792, "step": 34220 }, { "epoch": 8.21, "learning_rate": 9.765953941952262e-05, "loss": 0.3975, "step": 34230 }, { "epoch": 8.21, "learning_rate": 9.765818250653756e-05, "loss": 0.4253, "step": 34240 }, { "epoch": 8.22, "learning_rate": 9.765682520975455e-05, "loss": 0.4763, "step": 34250 }, { "epoch": 8.22, "learning_rate": 9.765546752918456e-05, "loss": 0.4852, "step": 34260 }, { "epoch": 8.22, "learning_rate": 9.76541094648385e-05, "loss": 0.4376, "step": 34270 }, { "epoch": 8.22, "learning_rate": 9.765275101672733e-05, "loss": 0.3769, "step": 34280 }, { "epoch": 8.23, "learning_rate": 9.765139218486197e-05, "loss": 0.3843, "step": 34290 }, { "epoch": 8.23, "learning_rate": 9.765003296925337e-05, "loss": 0.4577, "step": 34300 }, { "epoch": 8.23, "learning_rate": 9.764867336991248e-05, "loss": 0.4517, "step": 34310 }, { "epoch": 8.23, "learning_rate": 9.764731338685025e-05, "loss": 0.4355, "step": 34320 }, { "epoch": 8.23, "learning_rate": 9.764595302007761e-05, "loss": 0.4556, "step": 34330 }, { "epoch": 8.24, "learning_rate": 9.764459226960555e-05, "loss": 0.4323, "step": 34340 }, { "epoch": 8.24, "learning_rate": 9.7643231135445e-05, "loss": 0.4332, "step": 34350 }, { "epoch": 8.24, "learning_rate": 9.764186961760694e-05, "loss": 0.4231, "step": 34360 }, { "epoch": 8.24, "learning_rate": 9.764050771610232e-05, "loss": 0.4174, "step": 34370 }, { "epoch": 8.25, "learning_rate": 9.763914543094213e-05, "loss": 0.3975, "step": 34380 }, { "epoch": 8.25, "learning_rate": 9.763778276213731e-05, "loss": 0.4381, "step": 34390 }, { "epoch": 8.25, "learning_rate": 9.763641970969885e-05, "loss": 0.4524, "step": 34400 }, { "epoch": 8.25, "learning_rate": 9.763505627363771e-05, "loss": 0.4095, "step": 34410 }, { "epoch": 8.26, "learning_rate": 9.763369245396491e-05, "loss": 0.394, "step": 34420 }, { "epoch": 8.26, "learning_rate": 9.76323282506914e-05, "loss": 0.4138, "step": 34430 }, { "epoch": 8.26, "learning_rate": 9.763096366382818e-05, "loss": 0.4549, "step": 34440 }, { "epoch": 8.26, "learning_rate": 9.762959869338623e-05, "loss": 0.408, "step": 34450 }, { "epoch": 8.26, "learning_rate": 9.762823333937654e-05, "loss": 0.4765, "step": 34460 }, { "epoch": 8.27, "learning_rate": 9.762686760181013e-05, "loss": 0.4309, "step": 34470 }, { "epoch": 8.27, "learning_rate": 9.762550148069795e-05, "loss": 0.386, "step": 34480 }, { "epoch": 8.27, "learning_rate": 9.762413497605105e-05, "loss": 0.4007, "step": 34490 }, { "epoch": 8.27, "learning_rate": 9.762276808788042e-05, "loss": 0.4286, "step": 34500 }, { "epoch": 8.28, "learning_rate": 9.762140081619705e-05, "loss": 0.4465, "step": 34510 }, { "epoch": 8.28, "learning_rate": 9.762003316101197e-05, "loss": 0.4496, "step": 34520 }, { "epoch": 8.28, "learning_rate": 9.76186651223362e-05, "loss": 0.411, "step": 34530 }, { "epoch": 8.28, "learning_rate": 9.761729670018072e-05, "loss": 0.4117, "step": 34540 }, { "epoch": 8.28, "learning_rate": 9.761592789455661e-05, "loss": 0.4288, "step": 34550 }, { "epoch": 8.29, "learning_rate": 9.761455870547482e-05, "loss": 0.4106, "step": 34560 }, { "epoch": 8.29, "learning_rate": 9.761318913294643e-05, "loss": 0.4207, "step": 34570 }, { "epoch": 8.29, "learning_rate": 9.761181917698248e-05, "loss": 0.3782, "step": 34580 }, { "epoch": 8.29, "learning_rate": 9.761044883759395e-05, "loss": 0.462, "step": 34590 }, { "epoch": 8.3, "learning_rate": 9.760907811479192e-05, "loss": 0.3755, "step": 34600 }, { "epoch": 8.3, "learning_rate": 9.760770700858739e-05, "loss": 0.4317, "step": 34610 }, { "epoch": 8.3, "learning_rate": 9.760633551899143e-05, "loss": 0.4263, "step": 34620 }, { "epoch": 8.3, "learning_rate": 9.760496364601509e-05, "loss": 0.4406, "step": 34630 }, { "epoch": 8.31, "learning_rate": 9.76035913896694e-05, "loss": 0.4246, "step": 34640 }, { "epoch": 8.31, "learning_rate": 9.76022187499654e-05, "loss": 0.4243, "step": 34650 }, { "epoch": 8.31, "learning_rate": 9.760084572691419e-05, "loss": 0.4246, "step": 34660 }, { "epoch": 8.31, "learning_rate": 9.759947232052678e-05, "loss": 0.4205, "step": 34670 }, { "epoch": 8.31, "learning_rate": 9.759809853081424e-05, "loss": 0.4425, "step": 34680 }, { "epoch": 8.32, "learning_rate": 9.759672435778765e-05, "loss": 0.3901, "step": 34690 }, { "epoch": 8.32, "learning_rate": 9.759534980145807e-05, "loss": 0.3905, "step": 34700 }, { "epoch": 8.32, "learning_rate": 9.759397486183657e-05, "loss": 0.4746, "step": 34710 }, { "epoch": 8.32, "learning_rate": 9.75925995389342e-05, "loss": 0.4527, "step": 34720 }, { "epoch": 8.33, "learning_rate": 9.759122383276208e-05, "loss": 0.4138, "step": 34730 }, { "epoch": 8.33, "learning_rate": 9.758984774333125e-05, "loss": 0.4297, "step": 34740 }, { "epoch": 8.33, "learning_rate": 9.758847127065281e-05, "loss": 0.4511, "step": 34750 }, { "epoch": 8.33, "learning_rate": 9.758709441473784e-05, "loss": 0.4097, "step": 34760 }, { "epoch": 8.34, "learning_rate": 9.758571717559744e-05, "loss": 0.4396, "step": 34770 }, { "epoch": 8.34, "learning_rate": 9.758433955324267e-05, "loss": 0.4475, "step": 34780 }, { "epoch": 8.34, "learning_rate": 9.758296154768466e-05, "loss": 0.4676, "step": 34790 }, { "epoch": 8.34, "learning_rate": 9.758158315893449e-05, "loss": 0.4568, "step": 34800 }, { "epoch": 8.34, "learning_rate": 9.758020438700325e-05, "loss": 0.4622, "step": 34810 }, { "epoch": 8.35, "learning_rate": 9.757882523190207e-05, "loss": 0.4699, "step": 34820 }, { "epoch": 8.35, "learning_rate": 9.757744569364202e-05, "loss": 0.4449, "step": 34830 }, { "epoch": 8.35, "learning_rate": 9.757606577223425e-05, "loss": 0.4665, "step": 34840 }, { "epoch": 8.35, "learning_rate": 9.757468546768985e-05, "loss": 0.4625, "step": 34850 }, { "epoch": 8.36, "learning_rate": 9.757330478001993e-05, "loss": 0.4356, "step": 34860 }, { "epoch": 8.36, "learning_rate": 9.757192370923564e-05, "loss": 0.4844, "step": 34870 }, { "epoch": 8.36, "learning_rate": 9.757054225534808e-05, "loss": 0.4068, "step": 34880 }, { "epoch": 8.36, "learning_rate": 9.756916041836834e-05, "loss": 0.4298, "step": 34890 }, { "epoch": 8.36, "learning_rate": 9.756777819830763e-05, "loss": 0.4215, "step": 34900 }, { "epoch": 8.37, "learning_rate": 9.7566395595177e-05, "loss": 0.4509, "step": 34910 }, { "epoch": 8.37, "learning_rate": 9.756501260898763e-05, "loss": 0.4102, "step": 34920 }, { "epoch": 8.37, "learning_rate": 9.756362923975065e-05, "loss": 0.4867, "step": 34930 }, { "epoch": 8.37, "learning_rate": 9.75622454874772e-05, "loss": 0.4466, "step": 34940 }, { "epoch": 8.38, "learning_rate": 9.75608613521784e-05, "loss": 0.448, "step": 34950 }, { "epoch": 8.38, "learning_rate": 9.755947683386546e-05, "loss": 0.413, "step": 34960 }, { "epoch": 8.38, "learning_rate": 9.755809193254945e-05, "loss": 0.4217, "step": 34970 }, { "epoch": 8.38, "learning_rate": 9.755670664824158e-05, "loss": 0.3872, "step": 34980 }, { "epoch": 8.39, "learning_rate": 9.755532098095297e-05, "loss": 0.4217, "step": 34990 }, { "epoch": 8.39, "learning_rate": 9.75539349306948e-05, "loss": 0.4286, "step": 35000 }, { "epoch": 8.39, "learning_rate": 9.755254849747823e-05, "loss": 0.4272, "step": 35010 }, { "epoch": 8.39, "learning_rate": 9.755116168131442e-05, "loss": 0.4604, "step": 35020 }, { "epoch": 8.39, "learning_rate": 9.754977448221454e-05, "loss": 0.4781, "step": 35030 }, { "epoch": 8.4, "learning_rate": 9.754838690018976e-05, "loss": 0.4446, "step": 35040 }, { "epoch": 8.4, "learning_rate": 9.754699893525127e-05, "loss": 0.4157, "step": 35050 }, { "epoch": 8.4, "learning_rate": 9.754561058741021e-05, "loss": 0.4972, "step": 35060 }, { "epoch": 8.4, "learning_rate": 9.75442218566778e-05, "loss": 0.4402, "step": 35070 }, { "epoch": 8.41, "learning_rate": 9.75428327430652e-05, "loss": 0.4425, "step": 35080 }, { "epoch": 8.41, "learning_rate": 9.754144324658361e-05, "loss": 0.4244, "step": 35090 }, { "epoch": 8.41, "learning_rate": 9.754005336724421e-05, "loss": 0.4497, "step": 35100 }, { "epoch": 8.41, "learning_rate": 9.75386631050582e-05, "loss": 0.3923, "step": 35110 }, { "epoch": 8.41, "learning_rate": 9.753727246003676e-05, "loss": 0.4163, "step": 35120 }, { "epoch": 8.42, "learning_rate": 9.753588143219112e-05, "loss": 0.4256, "step": 35130 }, { "epoch": 8.42, "learning_rate": 9.753449002153246e-05, "loss": 0.4382, "step": 35140 }, { "epoch": 8.42, "learning_rate": 9.753309822807199e-05, "loss": 0.4303, "step": 35150 }, { "epoch": 8.42, "learning_rate": 9.753170605182092e-05, "loss": 0.4225, "step": 35160 }, { "epoch": 8.43, "learning_rate": 9.753031349279045e-05, "loss": 0.383, "step": 35170 }, { "epoch": 8.43, "learning_rate": 9.75289205509918e-05, "loss": 0.3978, "step": 35180 }, { "epoch": 8.43, "learning_rate": 9.752752722643619e-05, "loss": 0.4447, "step": 35190 }, { "epoch": 8.43, "learning_rate": 9.752613351913485e-05, "loss": 0.3569, "step": 35200 }, { "epoch": 8.44, "learning_rate": 9.7524739429099e-05, "loss": 0.4614, "step": 35210 }, { "epoch": 8.44, "learning_rate": 9.752334495633985e-05, "loss": 0.4499, "step": 35220 }, { "epoch": 8.44, "learning_rate": 9.752195010086866e-05, "loss": 0.428, "step": 35230 }, { "epoch": 8.44, "learning_rate": 9.752055486269662e-05, "loss": 0.4438, "step": 35240 }, { "epoch": 8.44, "learning_rate": 9.751915924183501e-05, "loss": 0.428, "step": 35250 }, { "epoch": 8.45, "learning_rate": 9.751776323829504e-05, "loss": 0.4535, "step": 35260 }, { "epoch": 8.45, "learning_rate": 9.751636685208798e-05, "loss": 0.3795, "step": 35270 }, { "epoch": 8.45, "learning_rate": 9.751497008322503e-05, "loss": 0.4641, "step": 35280 }, { "epoch": 8.45, "learning_rate": 9.751357293171749e-05, "loss": 0.5245, "step": 35290 }, { "epoch": 8.46, "learning_rate": 9.751217539757657e-05, "loss": 0.4571, "step": 35300 }, { "epoch": 8.46, "learning_rate": 9.751077748081357e-05, "loss": 0.4135, "step": 35310 }, { "epoch": 8.46, "learning_rate": 9.750937918143968e-05, "loss": 0.4477, "step": 35320 }, { "epoch": 8.46, "learning_rate": 9.750798049946623e-05, "loss": 0.4405, "step": 35330 }, { "epoch": 8.47, "learning_rate": 9.750658143490444e-05, "loss": 0.4223, "step": 35340 }, { "epoch": 8.47, "learning_rate": 9.750518198776559e-05, "loss": 0.3727, "step": 35350 }, { "epoch": 8.47, "learning_rate": 9.750378215806097e-05, "loss": 0.4403, "step": 35360 }, { "epoch": 8.47, "learning_rate": 9.750238194580181e-05, "loss": 0.4179, "step": 35370 }, { "epoch": 8.47, "learning_rate": 9.750098135099943e-05, "loss": 0.4006, "step": 35380 }, { "epoch": 8.48, "learning_rate": 9.749958037366508e-05, "loss": 0.4365, "step": 35390 }, { "epoch": 8.48, "learning_rate": 9.749817901381005e-05, "loss": 0.4108, "step": 35400 }, { "epoch": 8.48, "learning_rate": 9.749677727144563e-05, "loss": 0.4124, "step": 35410 }, { "epoch": 8.48, "learning_rate": 9.74953751465831e-05, "loss": 0.4646, "step": 35420 }, { "epoch": 8.49, "learning_rate": 9.749397263923377e-05, "loss": 0.4349, "step": 35430 }, { "epoch": 8.49, "learning_rate": 9.74925697494089e-05, "loss": 0.4149, "step": 35440 }, { "epoch": 8.49, "learning_rate": 9.749116647711983e-05, "loss": 0.4449, "step": 35450 }, { "epoch": 8.49, "learning_rate": 9.748976282237783e-05, "loss": 0.4048, "step": 35460 }, { "epoch": 8.49, "learning_rate": 9.748835878519421e-05, "loss": 0.5212, "step": 35470 }, { "epoch": 8.5, "learning_rate": 9.748695436558029e-05, "loss": 0.4399, "step": 35480 }, { "epoch": 8.5, "learning_rate": 9.748554956354736e-05, "loss": 0.4275, "step": 35490 }, { "epoch": 8.5, "learning_rate": 9.748414437910675e-05, "loss": 0.385, "step": 35500 }, { "epoch": 8.5, "learning_rate": 9.748273881226977e-05, "loss": 0.4299, "step": 35510 }, { "epoch": 8.51, "learning_rate": 9.748133286304774e-05, "loss": 0.4864, "step": 35520 }, { "epoch": 8.51, "learning_rate": 9.747992653145196e-05, "loss": 0.4155, "step": 35530 }, { "epoch": 8.51, "learning_rate": 9.747851981749381e-05, "loss": 0.4431, "step": 35540 }, { "epoch": 8.51, "learning_rate": 9.747711272118457e-05, "loss": 0.4004, "step": 35550 }, { "epoch": 8.52, "learning_rate": 9.747570524253559e-05, "loss": 0.3747, "step": 35560 }, { "epoch": 8.52, "learning_rate": 9.74742973815582e-05, "loss": 0.4129, "step": 35570 }, { "epoch": 8.52, "learning_rate": 9.747288913826374e-05, "loss": 0.4321, "step": 35580 }, { "epoch": 8.52, "learning_rate": 9.747148051266354e-05, "loss": 0.4395, "step": 35590 }, { "epoch": 8.52, "learning_rate": 9.747007150476897e-05, "loss": 0.4816, "step": 35600 }, { "epoch": 8.53, "learning_rate": 9.746866211459134e-05, "loss": 0.4127, "step": 35610 }, { "epoch": 8.53, "learning_rate": 9.746725234214204e-05, "loss": 0.4017, "step": 35620 }, { "epoch": 8.53, "learning_rate": 9.746584218743239e-05, "loss": 0.5071, "step": 35630 }, { "epoch": 8.53, "learning_rate": 9.746443165047376e-05, "loss": 0.476, "step": 35640 }, { "epoch": 8.54, "learning_rate": 9.746302073127752e-05, "loss": 0.4704, "step": 35650 }, { "epoch": 8.54, "learning_rate": 9.746160942985502e-05, "loss": 0.4786, "step": 35660 }, { "epoch": 8.54, "learning_rate": 9.746019774621761e-05, "loss": 0.5423, "step": 35670 }, { "epoch": 8.54, "learning_rate": 9.74587856803767e-05, "loss": 0.5224, "step": 35680 }, { "epoch": 8.55, "learning_rate": 9.745737323234362e-05, "loss": 0.4847, "step": 35690 }, { "epoch": 8.55, "learning_rate": 9.745596040212977e-05, "loss": 0.4499, "step": 35700 }, { "epoch": 8.55, "learning_rate": 9.745454718974651e-05, "loss": 0.5015, "step": 35710 }, { "epoch": 8.55, "learning_rate": 9.745313359520524e-05, "loss": 0.4921, "step": 35720 }, { "epoch": 8.55, "learning_rate": 9.745171961851734e-05, "loss": 0.4633, "step": 35730 }, { "epoch": 8.56, "learning_rate": 9.745030525969416e-05, "loss": 0.4751, "step": 35740 }, { "epoch": 8.56, "learning_rate": 9.744889051874716e-05, "loss": 0.4991, "step": 35750 }, { "epoch": 8.56, "learning_rate": 9.744747539568766e-05, "loss": 0.4471, "step": 35760 }, { "epoch": 8.56, "learning_rate": 9.744605989052711e-05, "loss": 0.4865, "step": 35770 }, { "epoch": 8.57, "learning_rate": 9.744464400327689e-05, "loss": 0.4652, "step": 35780 }, { "epoch": 8.57, "learning_rate": 9.744322773394838e-05, "loss": 0.5315, "step": 35790 }, { "epoch": 8.57, "learning_rate": 9.744181108255303e-05, "loss": 0.5018, "step": 35800 }, { "epoch": 8.57, "learning_rate": 9.744039404910222e-05, "loss": 0.464, "step": 35810 }, { "epoch": 8.57, "learning_rate": 9.743897663360736e-05, "loss": 0.4591, "step": 35820 }, { "epoch": 8.58, "learning_rate": 9.743755883607988e-05, "loss": 0.4924, "step": 35830 }, { "epoch": 8.58, "learning_rate": 9.743614065653119e-05, "loss": 0.4913, "step": 35840 }, { "epoch": 8.58, "learning_rate": 9.743472209497271e-05, "loss": 0.4559, "step": 35850 }, { "epoch": 8.58, "learning_rate": 9.743330315141585e-05, "loss": 0.459, "step": 35860 }, { "epoch": 8.59, "learning_rate": 9.743188382587208e-05, "loss": 0.5005, "step": 35870 }, { "epoch": 8.59, "learning_rate": 9.743046411835277e-05, "loss": 0.4489, "step": 35880 }, { "epoch": 8.59, "learning_rate": 9.74290440288694e-05, "loss": 0.5026, "step": 35890 }, { "epoch": 8.59, "learning_rate": 9.742762355743339e-05, "loss": 0.4868, "step": 35900 }, { "epoch": 8.6, "learning_rate": 9.742620270405618e-05, "loss": 0.4924, "step": 35910 }, { "epoch": 8.6, "learning_rate": 9.74247814687492e-05, "loss": 0.4405, "step": 35920 }, { "epoch": 8.6, "learning_rate": 9.742335985152394e-05, "loss": 0.4626, "step": 35930 }, { "epoch": 8.6, "learning_rate": 9.742193785239178e-05, "loss": 0.493, "step": 35940 }, { "epoch": 8.6, "learning_rate": 9.742051547136421e-05, "loss": 0.5469, "step": 35950 }, { "epoch": 8.61, "learning_rate": 9.741909270845271e-05, "loss": 0.4645, "step": 35960 }, { "epoch": 8.61, "learning_rate": 9.741766956366869e-05, "loss": 0.4769, "step": 35970 }, { "epoch": 8.61, "learning_rate": 9.741624603702363e-05, "loss": 0.4809, "step": 35980 }, { "epoch": 8.61, "learning_rate": 9.741482212852899e-05, "loss": 0.4482, "step": 35990 }, { "epoch": 8.62, "learning_rate": 9.741339783819625e-05, "loss": 0.4532, "step": 36000 }, { "epoch": 8.62, "learning_rate": 9.741197316603687e-05, "loss": 0.4905, "step": 36010 }, { "epoch": 8.62, "learning_rate": 9.741054811206233e-05, "loss": 0.4565, "step": 36020 }, { "epoch": 8.62, "learning_rate": 9.74091226762841e-05, "loss": 0.4348, "step": 36030 }, { "epoch": 8.63, "learning_rate": 9.740769685871365e-05, "loss": 0.465, "step": 36040 }, { "epoch": 8.63, "learning_rate": 9.740627065936247e-05, "loss": 0.4922, "step": 36050 }, { "epoch": 8.63, "learning_rate": 9.740484407824207e-05, "loss": 0.438, "step": 36060 }, { "epoch": 8.63, "learning_rate": 9.74034171153639e-05, "loss": 0.4834, "step": 36070 }, { "epoch": 8.63, "learning_rate": 9.740198977073946e-05, "loss": 0.4341, "step": 36080 }, { "epoch": 8.64, "learning_rate": 9.740056204438026e-05, "loss": 0.4846, "step": 36090 }, { "epoch": 8.64, "learning_rate": 9.739913393629781e-05, "loss": 0.5168, "step": 36100 }, { "epoch": 8.64, "learning_rate": 9.739770544650356e-05, "loss": 0.4958, "step": 36110 }, { "epoch": 8.64, "learning_rate": 9.739627657500904e-05, "loss": 0.4425, "step": 36120 }, { "epoch": 8.65, "learning_rate": 9.73948473218258e-05, "loss": 0.4762, "step": 36130 }, { "epoch": 8.65, "learning_rate": 9.739341768696528e-05, "loss": 0.5125, "step": 36140 }, { "epoch": 8.65, "learning_rate": 9.739198767043904e-05, "loss": 0.4872, "step": 36150 }, { "epoch": 8.65, "learning_rate": 9.739055727225856e-05, "loss": 0.428, "step": 36160 }, { "epoch": 8.65, "learning_rate": 9.73891264924354e-05, "loss": 0.4748, "step": 36170 }, { "epoch": 8.66, "learning_rate": 9.738769533098106e-05, "loss": 0.4684, "step": 36180 }, { "epoch": 8.66, "learning_rate": 9.738626378790705e-05, "loss": 0.4787, "step": 36190 }, { "epoch": 8.66, "learning_rate": 9.738483186322494e-05, "loss": 0.4443, "step": 36200 }, { "epoch": 8.66, "learning_rate": 9.738339955694622e-05, "loss": 0.4276, "step": 36210 }, { "epoch": 8.67, "learning_rate": 9.738196686908246e-05, "loss": 0.4865, "step": 36220 }, { "epoch": 8.67, "learning_rate": 9.738053379964516e-05, "loss": 0.478, "step": 36230 }, { "epoch": 8.67, "learning_rate": 9.737910034864587e-05, "loss": 0.4363, "step": 36240 }, { "epoch": 8.67, "learning_rate": 9.737766651609617e-05, "loss": 0.4601, "step": 36250 }, { "epoch": 8.68, "learning_rate": 9.737623230200757e-05, "loss": 0.4433, "step": 36260 }, { "epoch": 8.68, "learning_rate": 9.737479770639162e-05, "loss": 0.4492, "step": 36270 }, { "epoch": 8.68, "learning_rate": 9.73733627292599e-05, "loss": 0.4441, "step": 36280 }, { "epoch": 8.68, "learning_rate": 9.737192737062395e-05, "loss": 0.4573, "step": 36290 }, { "epoch": 8.68, "learning_rate": 9.737049163049532e-05, "loss": 0.5356, "step": 36300 }, { "epoch": 8.69, "learning_rate": 9.736905550888557e-05, "loss": 0.466, "step": 36310 }, { "epoch": 8.69, "learning_rate": 9.73676190058063e-05, "loss": 0.4623, "step": 36320 }, { "epoch": 8.69, "learning_rate": 9.736618212126905e-05, "loss": 0.427, "step": 36330 }, { "epoch": 8.69, "learning_rate": 9.736474485528539e-05, "loss": 0.4395, "step": 36340 }, { "epoch": 8.7, "learning_rate": 9.736330720786689e-05, "loss": 0.445, "step": 36350 }, { "epoch": 8.7, "learning_rate": 9.736186917902516e-05, "loss": 0.4185, "step": 36360 }, { "epoch": 8.7, "learning_rate": 9.736043076877174e-05, "loss": 0.4908, "step": 36370 }, { "epoch": 8.7, "learning_rate": 9.735899197711824e-05, "loss": 0.4638, "step": 36380 }, { "epoch": 8.71, "learning_rate": 9.735755280407625e-05, "loss": 0.4639, "step": 36390 }, { "epoch": 8.71, "learning_rate": 9.735611324965733e-05, "loss": 0.4563, "step": 36400 }, { "epoch": 8.71, "learning_rate": 9.73546733138731e-05, "loss": 0.4307, "step": 36410 }, { "epoch": 8.71, "learning_rate": 9.735323299673516e-05, "loss": 0.4308, "step": 36420 }, { "epoch": 8.71, "learning_rate": 9.735179229825509e-05, "loss": 0.4692, "step": 36430 }, { "epoch": 8.72, "learning_rate": 9.735035121844449e-05, "loss": 0.48, "step": 36440 }, { "epoch": 8.72, "learning_rate": 9.734890975731498e-05, "loss": 0.4509, "step": 36450 }, { "epoch": 8.72, "learning_rate": 9.734746791487816e-05, "loss": 0.481, "step": 36460 }, { "epoch": 8.72, "learning_rate": 9.734602569114563e-05, "loss": 0.5382, "step": 36470 }, { "epoch": 8.73, "learning_rate": 9.734458308612906e-05, "loss": 0.4702, "step": 36480 }, { "epoch": 8.73, "learning_rate": 9.734314009983999e-05, "loss": 0.459, "step": 36490 }, { "epoch": 8.73, "learning_rate": 9.734169673229008e-05, "loss": 0.4833, "step": 36500 }, { "epoch": 8.73, "learning_rate": 9.734025298349097e-05, "loss": 0.4893, "step": 36510 }, { "epoch": 8.73, "learning_rate": 9.733880885345425e-05, "loss": 0.4127, "step": 36520 }, { "epoch": 8.74, "learning_rate": 9.733736434219158e-05, "loss": 0.4661, "step": 36530 }, { "epoch": 8.74, "learning_rate": 9.733591944971457e-05, "loss": 0.5103, "step": 36540 }, { "epoch": 8.74, "learning_rate": 9.733447417603488e-05, "loss": 0.4977, "step": 36550 }, { "epoch": 8.74, "learning_rate": 9.733302852116411e-05, "loss": 0.4395, "step": 36560 }, { "epoch": 8.75, "learning_rate": 9.733158248511394e-05, "loss": 0.5048, "step": 36570 }, { "epoch": 8.75, "learning_rate": 9.733013606789601e-05, "loss": 0.4294, "step": 36580 }, { "epoch": 8.75, "learning_rate": 9.732868926952194e-05, "loss": 0.4545, "step": 36590 }, { "epoch": 8.75, "learning_rate": 9.732724209000341e-05, "loss": 0.4774, "step": 36600 }, { "epoch": 8.76, "learning_rate": 9.732579452935207e-05, "loss": 0.4912, "step": 36610 }, { "epoch": 8.76, "learning_rate": 9.732434658757956e-05, "loss": 0.501, "step": 36620 }, { "epoch": 8.76, "learning_rate": 9.732289826469757e-05, "loss": 0.4696, "step": 36630 }, { "epoch": 8.76, "learning_rate": 9.732144956071774e-05, "loss": 0.4273, "step": 36640 }, { "epoch": 8.76, "learning_rate": 9.732000047565175e-05, "loss": 0.4208, "step": 36650 }, { "epoch": 8.77, "learning_rate": 9.731855100951126e-05, "loss": 0.4721, "step": 36660 }, { "epoch": 8.77, "learning_rate": 9.731710116230794e-05, "loss": 0.4145, "step": 36670 }, { "epoch": 8.77, "learning_rate": 9.731565093405347e-05, "loss": 0.4293, "step": 36680 }, { "epoch": 8.77, "learning_rate": 9.731420032475953e-05, "loss": 0.4232, "step": 36690 }, { "epoch": 8.78, "learning_rate": 9.731274933443781e-05, "loss": 0.4795, "step": 36700 }, { "epoch": 8.78, "learning_rate": 9.731129796309998e-05, "loss": 0.4036, "step": 36710 }, { "epoch": 8.78, "learning_rate": 9.730984621075776e-05, "loss": 0.4726, "step": 36720 }, { "epoch": 8.78, "learning_rate": 9.730839407742279e-05, "loss": 0.4727, "step": 36730 }, { "epoch": 8.79, "learning_rate": 9.73069415631068e-05, "loss": 0.4269, "step": 36740 }, { "epoch": 8.79, "learning_rate": 9.730548866782148e-05, "loss": 0.3904, "step": 36750 }, { "epoch": 8.79, "learning_rate": 9.730403539157853e-05, "loss": 0.4305, "step": 36760 }, { "epoch": 8.79, "learning_rate": 9.730258173438965e-05, "loss": 0.5366, "step": 36770 }, { "epoch": 8.79, "learning_rate": 9.730112769626655e-05, "loss": 0.4341, "step": 36780 }, { "epoch": 8.8, "learning_rate": 9.729967327722094e-05, "loss": 0.4302, "step": 36790 }, { "epoch": 8.8, "learning_rate": 9.729821847726452e-05, "loss": 0.4543, "step": 36800 }, { "epoch": 8.8, "learning_rate": 9.729676329640903e-05, "loss": 0.3825, "step": 36810 }, { "epoch": 8.8, "learning_rate": 9.729530773466617e-05, "loss": 0.4407, "step": 36820 }, { "epoch": 8.81, "learning_rate": 9.729385179204767e-05, "loss": 0.4532, "step": 36830 }, { "epoch": 8.81, "learning_rate": 9.729239546856523e-05, "loss": 0.3721, "step": 36840 }, { "epoch": 8.81, "learning_rate": 9.729093876423063e-05, "loss": 0.4351, "step": 36850 }, { "epoch": 8.81, "learning_rate": 9.728948167905557e-05, "loss": 0.3707, "step": 36860 }, { "epoch": 8.81, "learning_rate": 9.728802421305176e-05, "loss": 0.4438, "step": 36870 }, { "epoch": 8.82, "learning_rate": 9.728656636623099e-05, "loss": 0.443, "step": 36880 }, { "epoch": 8.82, "learning_rate": 9.728510813860495e-05, "loss": 0.4519, "step": 36890 }, { "epoch": 8.82, "learning_rate": 9.728364953018543e-05, "loss": 0.4614, "step": 36900 }, { "epoch": 8.82, "learning_rate": 9.728219054098414e-05, "loss": 0.3874, "step": 36910 }, { "epoch": 8.83, "learning_rate": 9.728073117101285e-05, "loss": 0.3807, "step": 36920 }, { "epoch": 8.83, "learning_rate": 9.727927142028328e-05, "loss": 0.4038, "step": 36930 }, { "epoch": 8.83, "learning_rate": 9.727781128880722e-05, "loss": 0.5026, "step": 36940 }, { "epoch": 8.83, "learning_rate": 9.727635077659643e-05, "loss": 0.4772, "step": 36950 }, { "epoch": 8.84, "learning_rate": 9.727488988366264e-05, "loss": 0.4362, "step": 36960 }, { "epoch": 8.84, "learning_rate": 9.727342861001766e-05, "loss": 0.4175, "step": 36970 }, { "epoch": 8.84, "learning_rate": 9.727196695567322e-05, "loss": 0.44, "step": 36980 }, { "epoch": 8.84, "learning_rate": 9.727050492064111e-05, "loss": 0.4051, "step": 36990 }, { "epoch": 8.84, "learning_rate": 9.726904250493309e-05, "loss": 0.4836, "step": 37000 }, { "epoch": 8.85, "learning_rate": 9.726757970856096e-05, "loss": 0.4082, "step": 37010 }, { "epoch": 8.85, "learning_rate": 9.726611653153647e-05, "loss": 0.4796, "step": 37020 }, { "epoch": 8.85, "learning_rate": 9.726465297387142e-05, "loss": 0.4684, "step": 37030 }, { "epoch": 8.85, "learning_rate": 9.726318903557759e-05, "loss": 0.4905, "step": 37040 }, { "epoch": 8.86, "learning_rate": 9.72617247166668e-05, "loss": 0.3975, "step": 37050 }, { "epoch": 8.86, "learning_rate": 9.726026001715078e-05, "loss": 0.4257, "step": 37060 }, { "epoch": 8.86, "learning_rate": 9.725879493704137e-05, "loss": 0.416, "step": 37070 }, { "epoch": 8.86, "learning_rate": 9.725732947635038e-05, "loss": 0.4527, "step": 37080 }, { "epoch": 8.87, "learning_rate": 9.725586363508957e-05, "loss": 0.4743, "step": 37090 }, { "epoch": 8.87, "learning_rate": 9.725439741327078e-05, "loss": 0.4, "step": 37100 }, { "epoch": 8.87, "learning_rate": 9.72529308109058e-05, "loss": 0.4517, "step": 37110 }, { "epoch": 8.87, "learning_rate": 9.725146382800643e-05, "loss": 0.4097, "step": 37120 }, { "epoch": 8.87, "learning_rate": 9.724999646458453e-05, "loss": 0.4464, "step": 37130 }, { "epoch": 8.88, "learning_rate": 9.724852872065187e-05, "loss": 0.491, "step": 37140 }, { "epoch": 8.88, "learning_rate": 9.724706059622026e-05, "loss": 0.4602, "step": 37150 }, { "epoch": 8.88, "learning_rate": 9.724559209130157e-05, "loss": 0.4343, "step": 37160 }, { "epoch": 8.88, "learning_rate": 9.724412320590761e-05, "loss": 0.4056, "step": 37170 }, { "epoch": 8.89, "learning_rate": 9.72426539400502e-05, "loss": 0.4634, "step": 37180 }, { "epoch": 8.89, "learning_rate": 9.724118429374117e-05, "loss": 0.4539, "step": 37190 }, { "epoch": 8.89, "learning_rate": 9.723971426699236e-05, "loss": 0.4576, "step": 37200 }, { "epoch": 8.89, "learning_rate": 9.723824385981562e-05, "loss": 0.4422, "step": 37210 }, { "epoch": 8.89, "learning_rate": 9.723677307222278e-05, "loss": 0.4765, "step": 37220 }, { "epoch": 8.9, "learning_rate": 9.723530190422567e-05, "loss": 0.4269, "step": 37230 }, { "epoch": 8.9, "learning_rate": 9.723383035583617e-05, "loss": 0.4564, "step": 37240 }, { "epoch": 8.9, "learning_rate": 9.72323584270661e-05, "loss": 0.4344, "step": 37250 }, { "epoch": 8.9, "learning_rate": 9.723088611792733e-05, "loss": 0.4568, "step": 37260 }, { "epoch": 8.91, "learning_rate": 9.722941342843172e-05, "loss": 0.3769, "step": 37270 }, { "epoch": 8.91, "learning_rate": 9.722794035859111e-05, "loss": 0.4294, "step": 37280 }, { "epoch": 8.91, "learning_rate": 9.722646690841739e-05, "loss": 0.4849, "step": 37290 }, { "epoch": 8.91, "learning_rate": 9.72249930779224e-05, "loss": 0.3861, "step": 37300 }, { "epoch": 8.92, "learning_rate": 9.722351886711803e-05, "loss": 0.4554, "step": 37310 }, { "epoch": 8.92, "learning_rate": 9.722204427601613e-05, "loss": 0.4636, "step": 37320 }, { "epoch": 8.92, "learning_rate": 9.72205693046286e-05, "loss": 0.4322, "step": 37330 }, { "epoch": 8.92, "learning_rate": 9.72190939529673e-05, "loss": 0.4368, "step": 37340 }, { "epoch": 8.92, "learning_rate": 9.721761822104413e-05, "loss": 0.452, "step": 37350 }, { "epoch": 8.93, "learning_rate": 9.721614210887096e-05, "loss": 0.3905, "step": 37360 }, { "epoch": 8.93, "learning_rate": 9.721466561645966e-05, "loss": 0.4935, "step": 37370 }, { "epoch": 8.93, "learning_rate": 9.721318874382215e-05, "loss": 0.5014, "step": 37380 }, { "epoch": 8.93, "learning_rate": 9.721171149097031e-05, "loss": 0.4146, "step": 37390 }, { "epoch": 8.94, "learning_rate": 9.721023385791605e-05, "loss": 0.4158, "step": 37400 }, { "epoch": 8.94, "learning_rate": 9.720875584467126e-05, "loss": 0.4204, "step": 37410 }, { "epoch": 8.94, "learning_rate": 9.720727745124783e-05, "loss": 0.4253, "step": 37420 }, { "epoch": 8.94, "learning_rate": 9.720579867765768e-05, "loss": 0.4754, "step": 37430 }, { "epoch": 8.95, "learning_rate": 9.720431952391271e-05, "loss": 0.4241, "step": 37440 }, { "epoch": 8.95, "learning_rate": 9.720283999002485e-05, "loss": 0.4476, "step": 37450 }, { "epoch": 8.95, "learning_rate": 9.720136007600599e-05, "loss": 0.4054, "step": 37460 }, { "epoch": 9.0, "learning_rate": 9.719987978186807e-05, "loss": 0.4265, "step": 37470 }, { "epoch": 9.0, "learning_rate": 9.719839910762301e-05, "loss": 0.4471, "step": 37480 }, { "epoch": 9.01, "learning_rate": 9.719691805328271e-05, "loss": 0.4314, "step": 37490 }, { "epoch": 9.01, "learning_rate": 9.719543661885913e-05, "loss": 0.3903, "step": 37500 }, { "epoch": 9.01, "learning_rate": 9.719395480436417e-05, "loss": 0.4151, "step": 37510 }, { "epoch": 9.01, "learning_rate": 9.719247260980977e-05, "loss": 0.3933, "step": 37520 }, { "epoch": 9.01, "learning_rate": 9.719099003520789e-05, "loss": 0.4186, "step": 37530 }, { "epoch": 9.02, "learning_rate": 9.718950708057044e-05, "loss": 0.4512, "step": 37540 }, { "epoch": 9.02, "learning_rate": 9.718802374590938e-05, "loss": 0.3844, "step": 37550 }, { "epoch": 9.02, "learning_rate": 9.718654003123664e-05, "loss": 0.382, "step": 37560 }, { "epoch": 9.02, "learning_rate": 9.718505593656419e-05, "loss": 0.449, "step": 37570 }, { "epoch": 9.03, "learning_rate": 9.718357146190398e-05, "loss": 0.4057, "step": 37580 }, { "epoch": 9.03, "learning_rate": 9.718208660726793e-05, "loss": 0.3612, "step": 37590 }, { "epoch": 9.03, "learning_rate": 9.718060137266804e-05, "loss": 0.4059, "step": 37600 }, { "epoch": 9.03, "learning_rate": 9.717911575811624e-05, "loss": 0.345, "step": 37610 }, { "epoch": 9.03, "learning_rate": 9.717762976362452e-05, "loss": 0.4429, "step": 37620 }, { "epoch": 9.04, "learning_rate": 9.717614338920483e-05, "loss": 0.4303, "step": 37630 }, { "epoch": 9.04, "learning_rate": 9.717465663486916e-05, "loss": 0.434, "step": 37640 }, { "epoch": 9.04, "learning_rate": 9.717316950062945e-05, "loss": 0.3969, "step": 37650 }, { "epoch": 9.04, "learning_rate": 9.717168198649769e-05, "loss": 0.3662, "step": 37660 }, { "epoch": 9.05, "learning_rate": 9.717019409248586e-05, "loss": 0.4103, "step": 37670 }, { "epoch": 9.05, "learning_rate": 9.716870581860596e-05, "loss": 0.4106, "step": 37680 }, { "epoch": 9.05, "learning_rate": 9.716721716486994e-05, "loss": 0.4067, "step": 37690 }, { "epoch": 9.05, "learning_rate": 9.716572813128982e-05, "loss": 0.4503, "step": 37700 }, { "epoch": 9.06, "learning_rate": 9.716423871787758e-05, "loss": 0.3995, "step": 37710 }, { "epoch": 9.06, "learning_rate": 9.716274892464522e-05, "loss": 0.4156, "step": 37720 }, { "epoch": 9.06, "learning_rate": 9.716125875160474e-05, "loss": 0.4003, "step": 37730 }, { "epoch": 9.06, "learning_rate": 9.71597681987681e-05, "loss": 0.435, "step": 37740 }, { "epoch": 9.06, "learning_rate": 9.715827726614736e-05, "loss": 0.3976, "step": 37750 }, { "epoch": 9.07, "learning_rate": 9.715678595375449e-05, "loss": 0.3992, "step": 37760 }, { "epoch": 9.07, "learning_rate": 9.715529426160152e-05, "loss": 0.4044, "step": 37770 }, { "epoch": 9.07, "learning_rate": 9.715380218970045e-05, "loss": 0.3749, "step": 37780 }, { "epoch": 9.07, "learning_rate": 9.71523097380633e-05, "loss": 0.4256, "step": 37790 }, { "epoch": 9.08, "learning_rate": 9.715081690670212e-05, "loss": 0.4085, "step": 37800 }, { "epoch": 9.08, "learning_rate": 9.714932369562886e-05, "loss": 0.4122, "step": 37810 }, { "epoch": 9.08, "learning_rate": 9.71478301048556e-05, "loss": 0.3859, "step": 37820 }, { "epoch": 9.08, "learning_rate": 9.714633613439436e-05, "loss": 0.3586, "step": 37830 }, { "epoch": 9.09, "learning_rate": 9.714484178425718e-05, "loss": 0.3964, "step": 37840 }, { "epoch": 9.09, "learning_rate": 9.714334705445606e-05, "loss": 0.4166, "step": 37850 }, { "epoch": 9.09, "learning_rate": 9.714185194500305e-05, "loss": 0.4156, "step": 37860 }, { "epoch": 9.09, "learning_rate": 9.714035645591022e-05, "loss": 0.4312, "step": 37870 }, { "epoch": 9.09, "learning_rate": 9.713886058718958e-05, "loss": 0.3769, "step": 37880 }, { "epoch": 9.1, "learning_rate": 9.713736433885318e-05, "loss": 0.4092, "step": 37890 }, { "epoch": 9.1, "learning_rate": 9.71358677109131e-05, "loss": 0.38, "step": 37900 }, { "epoch": 9.1, "learning_rate": 9.713437070338136e-05, "loss": 0.4309, "step": 37910 }, { "epoch": 9.1, "learning_rate": 9.713287331627001e-05, "loss": 0.3866, "step": 37920 }, { "epoch": 9.11, "learning_rate": 9.713137554959116e-05, "loss": 0.372, "step": 37930 }, { "epoch": 9.11, "learning_rate": 9.71298774033568e-05, "loss": 0.4539, "step": 37940 }, { "epoch": 9.11, "learning_rate": 9.712837887757905e-05, "loss": 0.3631, "step": 37950 }, { "epoch": 9.11, "learning_rate": 9.712687997226994e-05, "loss": 0.3935, "step": 37960 }, { "epoch": 9.11, "learning_rate": 9.712538068744157e-05, "loss": 0.3868, "step": 37970 }, { "epoch": 9.12, "learning_rate": 9.712388102310602e-05, "loss": 0.3352, "step": 37980 }, { "epoch": 9.12, "learning_rate": 9.712238097927533e-05, "loss": 0.4006, "step": 37990 }, { "epoch": 9.12, "learning_rate": 9.712088055596161e-05, "loss": 0.3518, "step": 38000 }, { "epoch": 9.12, "learning_rate": 9.71193797531769e-05, "loss": 0.3986, "step": 38010 }, { "epoch": 9.13, "learning_rate": 9.711787857093336e-05, "loss": 0.3981, "step": 38020 }, { "epoch": 9.13, "learning_rate": 9.711637700924303e-05, "loss": 0.3852, "step": 38030 }, { "epoch": 9.13, "learning_rate": 9.7114875068118e-05, "loss": 0.4307, "step": 38040 }, { "epoch": 9.13, "learning_rate": 9.71133727475704e-05, "loss": 0.4351, "step": 38050 }, { "epoch": 9.14, "learning_rate": 9.711187004761228e-05, "loss": 0.405, "step": 38060 }, { "epoch": 9.14, "learning_rate": 9.711036696825577e-05, "loss": 0.3704, "step": 38070 }, { "epoch": 9.14, "learning_rate": 9.710886350951298e-05, "loss": 0.3739, "step": 38080 }, { "epoch": 9.14, "learning_rate": 9.710735967139601e-05, "loss": 0.408, "step": 38090 }, { "epoch": 9.14, "learning_rate": 9.710585545391695e-05, "loss": 0.4334, "step": 38100 }, { "epoch": 9.15, "learning_rate": 9.710435085708795e-05, "loss": 0.4483, "step": 38110 }, { "epoch": 9.15, "learning_rate": 9.710284588092111e-05, "loss": 0.4029, "step": 38120 }, { "epoch": 9.15, "learning_rate": 9.710134052542854e-05, "loss": 0.4237, "step": 38130 }, { "epoch": 9.15, "learning_rate": 9.709983479062238e-05, "loss": 0.4414, "step": 38140 }, { "epoch": 9.16, "learning_rate": 9.709832867651474e-05, "loss": 0.4178, "step": 38150 }, { "epoch": 9.16, "learning_rate": 9.709682218311776e-05, "loss": 0.3723, "step": 38160 }, { "epoch": 9.16, "learning_rate": 9.709531531044359e-05, "loss": 0.3899, "step": 38170 }, { "epoch": 9.16, "learning_rate": 9.70938080585043e-05, "loss": 0.4226, "step": 38180 }, { "epoch": 9.17, "learning_rate": 9.70923004273121e-05, "loss": 0.3998, "step": 38190 }, { "epoch": 9.17, "learning_rate": 9.709079241687911e-05, "loss": 0.4055, "step": 38200 }, { "epoch": 9.17, "learning_rate": 9.708928402721745e-05, "loss": 0.3898, "step": 38210 }, { "epoch": 9.17, "learning_rate": 9.70877752583393e-05, "loss": 0.3697, "step": 38220 }, { "epoch": 9.17, "learning_rate": 9.708626611025678e-05, "loss": 0.3734, "step": 38230 }, { "epoch": 9.18, "learning_rate": 9.708475658298206e-05, "loss": 0.3631, "step": 38240 }, { "epoch": 9.18, "learning_rate": 9.70832466765273e-05, "loss": 0.3491, "step": 38250 }, { "epoch": 9.18, "learning_rate": 9.708173639090465e-05, "loss": 0.3741, "step": 38260 }, { "epoch": 9.18, "learning_rate": 9.708022572612629e-05, "loss": 0.3935, "step": 38270 }, { "epoch": 9.19, "learning_rate": 9.707871468220435e-05, "loss": 0.4401, "step": 38280 }, { "epoch": 9.19, "learning_rate": 9.707720325915104e-05, "loss": 0.4517, "step": 38290 }, { "epoch": 9.19, "learning_rate": 9.707569145697851e-05, "loss": 0.4039, "step": 38300 }, { "epoch": 9.19, "learning_rate": 9.707417927569893e-05, "loss": 0.3857, "step": 38310 }, { "epoch": 9.19, "learning_rate": 9.707266671532449e-05, "loss": 0.4038, "step": 38320 }, { "epoch": 9.2, "learning_rate": 9.707115377586737e-05, "loss": 0.4069, "step": 38330 }, { "epoch": 9.2, "learning_rate": 9.706964045733975e-05, "loss": 0.3678, "step": 38340 }, { "epoch": 9.2, "learning_rate": 9.70681267597538e-05, "loss": 0.3744, "step": 38350 }, { "epoch": 9.2, "learning_rate": 9.706661268312175e-05, "loss": 0.3563, "step": 38360 }, { "epoch": 9.21, "learning_rate": 9.706509822745576e-05, "loss": 0.3943, "step": 38370 }, { "epoch": 9.21, "learning_rate": 9.706358339276803e-05, "loss": 0.4111, "step": 38380 }, { "epoch": 9.21, "learning_rate": 9.706206817907077e-05, "loss": 0.3776, "step": 38390 }, { "epoch": 9.21, "learning_rate": 9.706055258637619e-05, "loss": 0.4279, "step": 38400 }, { "epoch": 9.22, "learning_rate": 9.705903661469646e-05, "loss": 0.4172, "step": 38410 }, { "epoch": 9.22, "learning_rate": 9.705752026404382e-05, "loss": 0.396, "step": 38420 }, { "epoch": 9.22, "learning_rate": 9.705600353443048e-05, "loss": 0.4234, "step": 38430 }, { "epoch": 9.22, "learning_rate": 9.705448642586866e-05, "loss": 0.4293, "step": 38440 }, { "epoch": 9.22, "learning_rate": 9.705296893837054e-05, "loss": 0.4279, "step": 38450 }, { "epoch": 9.23, "learning_rate": 9.705145107194838e-05, "loss": 0.3897, "step": 38460 }, { "epoch": 9.23, "learning_rate": 9.704993282661436e-05, "loss": 0.4102, "step": 38470 }, { "epoch": 9.23, "learning_rate": 9.704841420238076e-05, "loss": 0.4491, "step": 38480 }, { "epoch": 9.23, "learning_rate": 9.704689519925978e-05, "loss": 0.4324, "step": 38490 }, { "epoch": 9.24, "learning_rate": 9.704537581726368e-05, "loss": 0.4023, "step": 38500 }, { "epoch": 9.24, "learning_rate": 9.704385605640464e-05, "loss": 0.4032, "step": 38510 }, { "epoch": 9.24, "learning_rate": 9.704233591669494e-05, "loss": 0.4926, "step": 38520 }, { "epoch": 9.24, "learning_rate": 9.704081539814682e-05, "loss": 0.3708, "step": 38530 }, { "epoch": 9.25, "learning_rate": 9.703929450077251e-05, "loss": 0.3534, "step": 38540 }, { "epoch": 9.25, "learning_rate": 9.70377732245843e-05, "loss": 0.4181, "step": 38550 }, { "epoch": 9.25, "learning_rate": 9.703625156959438e-05, "loss": 0.4061, "step": 38560 }, { "epoch": 9.25, "learning_rate": 9.703472953581502e-05, "loss": 0.4472, "step": 38570 }, { "epoch": 9.25, "learning_rate": 9.703320712325852e-05, "loss": 0.395, "step": 38580 }, { "epoch": 9.26, "learning_rate": 9.703168433193709e-05, "loss": 0.3597, "step": 38590 }, { "epoch": 9.26, "learning_rate": 9.703016116186301e-05, "loss": 0.3938, "step": 38600 }, { "epoch": 9.26, "learning_rate": 9.702863761304856e-05, "loss": 0.3851, "step": 38610 }, { "epoch": 9.26, "learning_rate": 9.7027113685506e-05, "loss": 0.3924, "step": 38620 }, { "epoch": 9.27, "learning_rate": 9.70255893792476e-05, "loss": 0.4459, "step": 38630 }, { "epoch": 9.27, "learning_rate": 9.702406469428564e-05, "loss": 0.4137, "step": 38640 }, { "epoch": 9.27, "learning_rate": 9.702253963063238e-05, "loss": 0.3768, "step": 38650 }, { "epoch": 9.27, "learning_rate": 9.702101418830013e-05, "loss": 0.374, "step": 38660 }, { "epoch": 9.27, "learning_rate": 9.701948836730115e-05, "loss": 0.4914, "step": 38670 }, { "epoch": 9.28, "learning_rate": 9.701796216764774e-05, "loss": 0.399, "step": 38680 }, { "epoch": 9.28, "learning_rate": 9.70164355893522e-05, "loss": 0.3679, "step": 38690 }, { "epoch": 9.28, "learning_rate": 9.701490863242682e-05, "loss": 0.385, "step": 38700 }, { "epoch": 9.28, "learning_rate": 9.701338129688387e-05, "loss": 0.3908, "step": 38710 }, { "epoch": 9.29, "learning_rate": 9.701185358273567e-05, "loss": 0.4373, "step": 38720 }, { "epoch": 9.29, "learning_rate": 9.701032548999453e-05, "loss": 0.4549, "step": 38730 }, { "epoch": 9.29, "learning_rate": 9.700879701867276e-05, "loss": 0.4047, "step": 38740 }, { "epoch": 9.29, "learning_rate": 9.700726816878263e-05, "loss": 0.4033, "step": 38750 }, { "epoch": 9.3, "learning_rate": 9.700573894033652e-05, "loss": 0.3731, "step": 38760 }, { "epoch": 9.3, "learning_rate": 9.700420933334666e-05, "loss": 0.3976, "step": 38770 }, { "epoch": 9.3, "learning_rate": 9.700267934782545e-05, "loss": 0.4247, "step": 38780 }, { "epoch": 9.3, "learning_rate": 9.700114898378515e-05, "loss": 0.4081, "step": 38790 }, { "epoch": 9.3, "learning_rate": 9.699961824123811e-05, "loss": 0.3962, "step": 38800 }, { "epoch": 9.31, "learning_rate": 9.699808712019667e-05, "loss": 0.4082, "step": 38810 }, { "epoch": 9.31, "learning_rate": 9.699655562067313e-05, "loss": 0.4304, "step": 38820 }, { "epoch": 9.31, "learning_rate": 9.699502374267986e-05, "loss": 0.3793, "step": 38830 }, { "epoch": 9.31, "learning_rate": 9.699349148622915e-05, "loss": 0.3975, "step": 38840 }, { "epoch": 9.32, "learning_rate": 9.699195885133338e-05, "loss": 0.3878, "step": 38850 }, { "epoch": 9.32, "learning_rate": 9.699042583800488e-05, "loss": 0.3806, "step": 38860 }, { "epoch": 9.32, "learning_rate": 9.698889244625599e-05, "loss": 0.4061, "step": 38870 }, { "epoch": 9.32, "learning_rate": 9.698735867609906e-05, "loss": 0.4195, "step": 38880 }, { "epoch": 9.33, "learning_rate": 9.698582452754644e-05, "loss": 0.3808, "step": 38890 }, { "epoch": 9.33, "learning_rate": 9.698429000061049e-05, "loss": 0.4066, "step": 38900 }, { "epoch": 9.33, "learning_rate": 9.698275509530357e-05, "loss": 0.4371, "step": 38910 }, { "epoch": 9.33, "learning_rate": 9.698121981163803e-05, "loss": 0.349, "step": 38920 }, { "epoch": 9.33, "learning_rate": 9.697968414962625e-05, "loss": 0.3552, "step": 38930 }, { "epoch": 9.34, "learning_rate": 9.697814810928058e-05, "loss": 0.4431, "step": 38940 }, { "epoch": 9.34, "learning_rate": 9.69766116906134e-05, "loss": 0.4139, "step": 38950 }, { "epoch": 9.34, "learning_rate": 9.69750748936371e-05, "loss": 0.4569, "step": 38960 }, { "epoch": 9.34, "learning_rate": 9.697353771836401e-05, "loss": 0.3651, "step": 38970 }, { "epoch": 9.35, "learning_rate": 9.697200016480654e-05, "loss": 0.3728, "step": 38980 }, { "epoch": 9.35, "learning_rate": 9.697046223297707e-05, "loss": 0.3804, "step": 38990 }, { "epoch": 9.35, "learning_rate": 9.696892392288798e-05, "loss": 0.3902, "step": 39000 }, { "epoch": 9.35, "learning_rate": 9.696738523455169e-05, "loss": 0.395, "step": 39010 }, { "epoch": 9.35, "learning_rate": 9.696584616798052e-05, "loss": 0.3656, "step": 39020 }, { "epoch": 9.36, "learning_rate": 9.696430672318693e-05, "loss": 0.4364, "step": 39030 }, { "epoch": 9.36, "learning_rate": 9.696276690018329e-05, "loss": 0.4169, "step": 39040 }, { "epoch": 9.36, "learning_rate": 9.696122669898201e-05, "loss": 0.3915, "step": 39050 }, { "epoch": 9.36, "learning_rate": 9.695968611959548e-05, "loss": 0.3645, "step": 39060 }, { "epoch": 9.37, "learning_rate": 9.695814516203612e-05, "loss": 0.3766, "step": 39070 }, { "epoch": 9.37, "learning_rate": 9.695660382631632e-05, "loss": 0.3589, "step": 39080 }, { "epoch": 9.37, "learning_rate": 9.695506211244852e-05, "loss": 0.3953, "step": 39090 }, { "epoch": 9.37, "learning_rate": 9.695352002044513e-05, "loss": 0.3636, "step": 39100 }, { "epoch": 9.38, "learning_rate": 9.695197755031855e-05, "loss": 0.3888, "step": 39110 }, { "epoch": 9.38, "learning_rate": 9.69504347020812e-05, "loss": 0.3891, "step": 39120 }, { "epoch": 9.38, "learning_rate": 9.694889147574554e-05, "loss": 0.3874, "step": 39130 }, { "epoch": 9.38, "learning_rate": 9.694734787132396e-05, "loss": 0.3727, "step": 39140 }, { "epoch": 9.38, "learning_rate": 9.694580388882892e-05, "loss": 0.3809, "step": 39150 }, { "epoch": 9.39, "learning_rate": 9.694425952827283e-05, "loss": 0.3187, "step": 39160 }, { "epoch": 9.39, "learning_rate": 9.694271478966814e-05, "loss": 0.3879, "step": 39170 }, { "epoch": 9.39, "learning_rate": 9.694116967302729e-05, "loss": 0.4144, "step": 39180 }, { "epoch": 9.39, "learning_rate": 9.693962417836271e-05, "loss": 0.4149, "step": 39190 }, { "epoch": 9.4, "learning_rate": 9.693807830568686e-05, "loss": 0.333, "step": 39200 }, { "epoch": 9.4, "learning_rate": 9.693653205501218e-05, "loss": 0.4022, "step": 39210 }, { "epoch": 9.4, "learning_rate": 9.693498542635115e-05, "loss": 0.3859, "step": 39220 }, { "epoch": 9.4, "learning_rate": 9.693343841971618e-05, "loss": 0.4258, "step": 39230 }, { "epoch": 9.41, "learning_rate": 9.693189103511976e-05, "loss": 0.3672, "step": 39240 }, { "epoch": 9.41, "learning_rate": 9.693034327257433e-05, "loss": 0.3766, "step": 39250 }, { "epoch": 9.41, "learning_rate": 9.692879513209239e-05, "loss": 0.3862, "step": 39260 }, { "epoch": 9.41, "learning_rate": 9.692724661368637e-05, "loss": 0.4012, "step": 39270 }, { "epoch": 9.41, "learning_rate": 9.692569771736874e-05, "loss": 0.4558, "step": 39280 }, { "epoch": 9.42, "learning_rate": 9.692414844315201e-05, "loss": 0.3769, "step": 39290 }, { "epoch": 9.42, "learning_rate": 9.692259879104864e-05, "loss": 0.3504, "step": 39300 }, { "epoch": 9.42, "learning_rate": 9.692104876107108e-05, "loss": 0.401, "step": 39310 }, { "epoch": 9.42, "learning_rate": 9.691949835323184e-05, "loss": 0.353, "step": 39320 }, { "epoch": 9.43, "learning_rate": 9.691794756754343e-05, "loss": 0.3853, "step": 39330 }, { "epoch": 9.43, "learning_rate": 9.691639640401829e-05, "loss": 0.336, "step": 39340 }, { "epoch": 9.43, "learning_rate": 9.691484486266892e-05, "loss": 0.343, "step": 39350 }, { "epoch": 9.43, "learning_rate": 9.691329294350784e-05, "loss": 0.341, "step": 39360 }, { "epoch": 9.43, "learning_rate": 9.691174064654753e-05, "loss": 0.3795, "step": 39370 }, { "epoch": 9.44, "learning_rate": 9.69101879718005e-05, "loss": 0.3864, "step": 39380 }, { "epoch": 9.44, "learning_rate": 9.690863491927926e-05, "loss": 0.4157, "step": 39390 }, { "epoch": 9.44, "learning_rate": 9.69070814889963e-05, "loss": 0.4241, "step": 39400 }, { "epoch": 9.44, "learning_rate": 9.690552768096413e-05, "loss": 0.4187, "step": 39410 }, { "epoch": 9.45, "learning_rate": 9.690397349519527e-05, "loss": 0.3567, "step": 39420 }, { "epoch": 9.45, "learning_rate": 9.690241893170224e-05, "loss": 0.395, "step": 39430 }, { "epoch": 9.45, "learning_rate": 9.690086399049756e-05, "loss": 0.4237, "step": 39440 }, { "epoch": 9.45, "learning_rate": 9.689930867159373e-05, "loss": 0.3958, "step": 39450 }, { "epoch": 9.46, "learning_rate": 9.689775297500332e-05, "loss": 0.3281, "step": 39460 }, { "epoch": 9.46, "learning_rate": 9.689619690073881e-05, "loss": 0.3951, "step": 39470 }, { "epoch": 9.46, "learning_rate": 9.689464044881276e-05, "loss": 0.3643, "step": 39480 }, { "epoch": 9.46, "learning_rate": 9.68930836192377e-05, "loss": 0.3917, "step": 39490 }, { "epoch": 9.46, "learning_rate": 9.689152641202614e-05, "loss": 0.3443, "step": 39500 }, { "epoch": 9.47, "learning_rate": 9.688996882719069e-05, "loss": 0.4083, "step": 39510 }, { "epoch": 9.47, "learning_rate": 9.688841086474381e-05, "loss": 0.3617, "step": 39520 }, { "epoch": 9.47, "learning_rate": 9.688685252469809e-05, "loss": 0.392, "step": 39530 }, { "epoch": 9.47, "learning_rate": 9.688529380706608e-05, "loss": 0.3942, "step": 39540 }, { "epoch": 9.48, "learning_rate": 9.688373471186032e-05, "loss": 0.4462, "step": 39550 }, { "epoch": 9.48, "learning_rate": 9.688217523909338e-05, "loss": 0.3802, "step": 39560 }, { "epoch": 9.48, "learning_rate": 9.68806153887778e-05, "loss": 0.4291, "step": 39570 }, { "epoch": 9.48, "learning_rate": 9.687905516092615e-05, "loss": 0.4368, "step": 39580 }, { "epoch": 9.49, "learning_rate": 9.687749455555101e-05, "loss": 0.34, "step": 39590 }, { "epoch": 9.49, "learning_rate": 9.687593357266492e-05, "loss": 0.3704, "step": 39600 }, { "epoch": 9.49, "learning_rate": 9.687437221228048e-05, "loss": 0.4423, "step": 39610 }, { "epoch": 9.49, "learning_rate": 9.687281047441023e-05, "loss": 0.3694, "step": 39620 }, { "epoch": 9.49, "learning_rate": 9.687124835906678e-05, "loss": 0.3677, "step": 39630 }, { "epoch": 9.5, "learning_rate": 9.686968586626271e-05, "loss": 0.3936, "step": 39640 }, { "epoch": 9.5, "learning_rate": 9.686812299601057e-05, "loss": 0.4159, "step": 39650 }, { "epoch": 9.5, "learning_rate": 9.686655974832297e-05, "loss": 0.3571, "step": 39660 }, { "epoch": 9.5, "learning_rate": 9.686499612321249e-05, "loss": 0.344, "step": 39670 }, { "epoch": 9.51, "learning_rate": 9.686343212069174e-05, "loss": 0.3491, "step": 39680 }, { "epoch": 9.51, "learning_rate": 9.686186774077329e-05, "loss": 0.3608, "step": 39690 }, { "epoch": 9.51, "learning_rate": 9.686030298346972e-05, "loss": 0.3842, "step": 39700 }, { "epoch": 9.51, "learning_rate": 9.68587378487937e-05, "loss": 0.3201, "step": 39710 }, { "epoch": 9.51, "learning_rate": 9.685717233675779e-05, "loss": 0.3911, "step": 39720 }, { "epoch": 9.52, "learning_rate": 9.68556064473746e-05, "loss": 0.3527, "step": 39730 }, { "epoch": 9.52, "learning_rate": 9.685404018065674e-05, "loss": 0.3973, "step": 39740 }, { "epoch": 9.52, "learning_rate": 9.685247353661682e-05, "loss": 0.3544, "step": 39750 }, { "epoch": 9.52, "learning_rate": 9.685090651526747e-05, "loss": 0.3642, "step": 39760 }, { "epoch": 9.53, "learning_rate": 9.684933911662129e-05, "loss": 0.4301, "step": 39770 }, { "epoch": 9.53, "learning_rate": 9.684777134069093e-05, "loss": 0.4228, "step": 39780 }, { "epoch": 9.53, "learning_rate": 9.6846203187489e-05, "loss": 0.394, "step": 39790 }, { "epoch": 9.53, "learning_rate": 9.684463465702811e-05, "loss": 0.4303, "step": 39800 }, { "epoch": 9.54, "learning_rate": 9.684306574932091e-05, "loss": 0.4148, "step": 39810 }, { "epoch": 9.54, "learning_rate": 9.684149646438005e-05, "loss": 0.4736, "step": 39820 }, { "epoch": 9.54, "learning_rate": 9.683992680221817e-05, "loss": 0.4417, "step": 39830 }, { "epoch": 9.54, "learning_rate": 9.683835676284784e-05, "loss": 0.4766, "step": 39840 }, { "epoch": 9.54, "learning_rate": 9.68367863462818e-05, "loss": 0.4412, "step": 39850 }, { "epoch": 9.55, "learning_rate": 9.683521555253264e-05, "loss": 0.4219, "step": 39860 }, { "epoch": 9.55, "learning_rate": 9.683364438161302e-05, "loss": 0.3905, "step": 39870 }, { "epoch": 9.55, "learning_rate": 9.68320728335356e-05, "loss": 0.4737, "step": 39880 }, { "epoch": 9.55, "learning_rate": 9.683050090831303e-05, "loss": 0.4399, "step": 39890 }, { "epoch": 9.56, "learning_rate": 9.682892860595799e-05, "loss": 0.4264, "step": 39900 }, { "epoch": 9.56, "learning_rate": 9.682735592648308e-05, "loss": 0.421, "step": 39910 }, { "epoch": 9.56, "learning_rate": 9.682578286990105e-05, "loss": 0.4122, "step": 39920 }, { "epoch": 9.56, "learning_rate": 9.68242094362245e-05, "loss": 0.4668, "step": 39930 }, { "epoch": 9.57, "learning_rate": 9.682263562546614e-05, "loss": 0.4067, "step": 39940 }, { "epoch": 9.57, "learning_rate": 9.682106143763863e-05, "loss": 0.4349, "step": 39950 }, { "epoch": 9.57, "learning_rate": 9.681948687275463e-05, "loss": 0.4141, "step": 39960 }, { "epoch": 9.57, "learning_rate": 9.681791193082685e-05, "loss": 0.4947, "step": 39970 }, { "epoch": 9.57, "learning_rate": 9.681633661186798e-05, "loss": 0.4192, "step": 39980 }, { "epoch": 9.58, "learning_rate": 9.681476091589067e-05, "loss": 0.4305, "step": 39990 }, { "epoch": 9.58, "learning_rate": 9.681318484290762e-05, "loss": 0.3919, "step": 40000 }, { "epoch": 9.58, "learning_rate": 9.681160839293155e-05, "loss": 0.4391, "step": 40010 }, { "epoch": 9.58, "learning_rate": 9.681003156597512e-05, "loss": 0.3919, "step": 40020 }, { "epoch": 9.59, "learning_rate": 9.680845436205105e-05, "loss": 0.4344, "step": 40030 }, { "epoch": 9.59, "learning_rate": 9.680687678117203e-05, "loss": 0.3953, "step": 40040 }, { "epoch": 9.59, "learning_rate": 9.680529882335077e-05, "loss": 0.4698, "step": 40050 }, { "epoch": 9.59, "learning_rate": 9.680372048859998e-05, "loss": 0.4224, "step": 40060 }, { "epoch": 9.59, "learning_rate": 9.680214177693237e-05, "loss": 0.4805, "step": 40070 }, { "epoch": 9.6, "learning_rate": 9.680056268836064e-05, "loss": 0.4661, "step": 40080 }, { "epoch": 9.6, "learning_rate": 9.679898322289753e-05, "loss": 0.4003, "step": 40090 }, { "epoch": 9.6, "learning_rate": 9.679740338055574e-05, "loss": 0.4423, "step": 40100 }, { "epoch": 9.6, "learning_rate": 9.679582316134799e-05, "loss": 0.4369, "step": 40110 }, { "epoch": 9.61, "learning_rate": 9.679424256528702e-05, "loss": 0.4263, "step": 40120 }, { "epoch": 9.61, "learning_rate": 9.679266159238558e-05, "loss": 0.4216, "step": 40130 }, { "epoch": 9.61, "learning_rate": 9.679108024265635e-05, "loss": 0.3991, "step": 40140 }, { "epoch": 9.61, "learning_rate": 9.67894985161121e-05, "loss": 0.4191, "step": 40150 }, { "epoch": 9.62, "learning_rate": 9.678791641276554e-05, "loss": 0.4493, "step": 40160 }, { "epoch": 9.62, "learning_rate": 9.678633393262946e-05, "loss": 0.4453, "step": 40170 }, { "epoch": 9.62, "learning_rate": 9.678475107571655e-05, "loss": 0.423, "step": 40180 }, { "epoch": 9.62, "learning_rate": 9.67831678420396e-05, "loss": 0.4646, "step": 40190 }, { "epoch": 9.62, "learning_rate": 9.678158423161133e-05, "loss": 0.4337, "step": 40200 }, { "epoch": 9.63, "learning_rate": 9.678000024444448e-05, "loss": 0.4342, "step": 40210 }, { "epoch": 9.63, "learning_rate": 9.677841588055187e-05, "loss": 0.3945, "step": 40220 }, { "epoch": 9.63, "learning_rate": 9.67768311399462e-05, "loss": 0.4687, "step": 40230 }, { "epoch": 9.63, "learning_rate": 9.677524602264026e-05, "loss": 0.4555, "step": 40240 }, { "epoch": 9.64, "learning_rate": 9.67736605286468e-05, "loss": 0.4285, "step": 40250 }, { "epoch": 9.64, "learning_rate": 9.677207465797859e-05, "loss": 0.4096, "step": 40260 }, { "epoch": 9.64, "learning_rate": 9.67704884106484e-05, "loss": 0.4641, "step": 40270 }, { "epoch": 9.64, "learning_rate": 9.676890178666903e-05, "loss": 0.4793, "step": 40280 }, { "epoch": 9.65, "learning_rate": 9.676731478605321e-05, "loss": 0.4683, "step": 40290 }, { "epoch": 9.65, "learning_rate": 9.676572740881378e-05, "loss": 0.4128, "step": 40300 }, { "epoch": 9.65, "learning_rate": 9.676413965496347e-05, "loss": 0.4684, "step": 40310 }, { "epoch": 9.65, "learning_rate": 9.676255152451508e-05, "loss": 0.4626, "step": 40320 }, { "epoch": 9.65, "learning_rate": 9.676096301748142e-05, "loss": 0.4041, "step": 40330 }, { "epoch": 9.66, "learning_rate": 9.675937413387527e-05, "loss": 0.3276, "step": 40340 }, { "epoch": 9.66, "learning_rate": 9.675778487370941e-05, "loss": 0.4186, "step": 40350 }, { "epoch": 9.66, "learning_rate": 9.675619523699669e-05, "loss": 0.4741, "step": 40360 }, { "epoch": 9.66, "learning_rate": 9.675460522374984e-05, "loss": 0.4238, "step": 40370 }, { "epoch": 9.67, "learning_rate": 9.67530148339817e-05, "loss": 0.4302, "step": 40380 }, { "epoch": 9.67, "learning_rate": 9.675142406770509e-05, "loss": 0.3934, "step": 40390 }, { "epoch": 9.67, "learning_rate": 9.67498329249328e-05, "loss": 0.4299, "step": 40400 }, { "epoch": 9.67, "learning_rate": 9.674824140567765e-05, "loss": 0.4148, "step": 40410 }, { "epoch": 9.67, "learning_rate": 9.674664950995247e-05, "loss": 0.4153, "step": 40420 }, { "epoch": 9.68, "learning_rate": 9.674505723777005e-05, "loss": 0.3456, "step": 40430 }, { "epoch": 9.68, "learning_rate": 9.674346458914326e-05, "loss": 0.4781, "step": 40440 }, { "epoch": 9.68, "learning_rate": 9.674187156408486e-05, "loss": 0.4222, "step": 40450 }, { "epoch": 9.68, "learning_rate": 9.674027816260773e-05, "loss": 0.4108, "step": 40460 }, { "epoch": 9.69, "learning_rate": 9.673868438472468e-05, "loss": 0.3873, "step": 40470 }, { "epoch": 9.69, "learning_rate": 9.673709023044857e-05, "loss": 0.4042, "step": 40480 }, { "epoch": 9.69, "learning_rate": 9.673549569979221e-05, "loss": 0.4424, "step": 40490 }, { "epoch": 9.69, "learning_rate": 9.673390079276844e-05, "loss": 0.4615, "step": 40500 }, { "epoch": 9.7, "learning_rate": 9.673230550939015e-05, "loss": 0.3972, "step": 40510 }, { "epoch": 9.7, "learning_rate": 9.673070984967012e-05, "loss": 0.451, "step": 40520 }, { "epoch": 9.7, "learning_rate": 9.672911381362124e-05, "loss": 0.4103, "step": 40530 }, { "epoch": 9.7, "learning_rate": 9.672751740125636e-05, "loss": 0.4296, "step": 40540 }, { "epoch": 9.7, "learning_rate": 9.672592061258831e-05, "loss": 0.4466, "step": 40550 }, { "epoch": 9.71, "learning_rate": 9.672432344763e-05, "loss": 0.3862, "step": 40560 }, { "epoch": 9.71, "learning_rate": 9.672272590639424e-05, "loss": 0.3962, "step": 40570 }, { "epoch": 9.71, "learning_rate": 9.672112798889394e-05, "loss": 0.37, "step": 40580 }, { "epoch": 9.71, "learning_rate": 9.671952969514194e-05, "loss": 0.4052, "step": 40590 }, { "epoch": 9.72, "learning_rate": 9.67179310251511e-05, "loss": 0.4055, "step": 40600 }, { "epoch": 9.72, "learning_rate": 9.671633197893433e-05, "loss": 0.3993, "step": 40610 }, { "epoch": 9.72, "learning_rate": 9.671473255650447e-05, "loss": 0.3993, "step": 40620 }, { "epoch": 9.72, "learning_rate": 9.671313275787443e-05, "loss": 0.4294, "step": 40630 }, { "epoch": 9.73, "learning_rate": 9.671153258305709e-05, "loss": 0.4404, "step": 40640 }, { "epoch": 9.73, "learning_rate": 9.670993203206531e-05, "loss": 0.3317, "step": 40650 }, { "epoch": 9.73, "learning_rate": 9.670833110491203e-05, "loss": 0.4739, "step": 40660 }, { "epoch": 9.73, "learning_rate": 9.670672980161009e-05, "loss": 0.411, "step": 40670 }, { "epoch": 9.73, "learning_rate": 9.670512812217241e-05, "loss": 0.3857, "step": 40680 }, { "epoch": 9.74, "learning_rate": 9.670352606661189e-05, "loss": 0.4223, "step": 40690 }, { "epoch": 9.74, "learning_rate": 9.67019236349414e-05, "loss": 0.3831, "step": 40700 }, { "epoch": 9.74, "learning_rate": 9.67003208271739e-05, "loss": 0.454, "step": 40710 }, { "epoch": 9.74, "learning_rate": 9.669871764332225e-05, "loss": 0.4623, "step": 40720 }, { "epoch": 9.75, "learning_rate": 9.66971140833994e-05, "loss": 0.4007, "step": 40730 }, { "epoch": 9.75, "learning_rate": 9.669551014741823e-05, "loss": 0.3959, "step": 40740 }, { "epoch": 9.75, "learning_rate": 9.669390583539169e-05, "loss": 0.3658, "step": 40750 }, { "epoch": 9.75, "learning_rate": 9.669230114733266e-05, "loss": 0.4331, "step": 40760 }, { "epoch": 9.75, "learning_rate": 9.669069608325408e-05, "loss": 0.4388, "step": 40770 }, { "epoch": 9.76, "learning_rate": 9.668909064316888e-05, "loss": 0.4435, "step": 40780 }, { "epoch": 9.76, "learning_rate": 9.668748482709e-05, "loss": 0.395, "step": 40790 }, { "epoch": 9.76, "learning_rate": 9.668587863503035e-05, "loss": 0.4209, "step": 40800 }, { "epoch": 9.76, "learning_rate": 9.668427206700288e-05, "loss": 0.4653, "step": 40810 }, { "epoch": 9.77, "learning_rate": 9.668266512302051e-05, "loss": 0.4629, "step": 40820 }, { "epoch": 9.77, "learning_rate": 9.66810578030962e-05, "loss": 0.4311, "step": 40830 }, { "epoch": 9.77, "learning_rate": 9.667945010724289e-05, "loss": 0.4266, "step": 40840 }, { "epoch": 9.77, "learning_rate": 9.667784203547352e-05, "loss": 0.4037, "step": 40850 }, { "epoch": 9.78, "learning_rate": 9.667623358780105e-05, "loss": 0.4084, "step": 40860 }, { "epoch": 9.78, "learning_rate": 9.667462476423841e-05, "loss": 0.4005, "step": 40870 }, { "epoch": 9.78, "learning_rate": 9.66730155647986e-05, "loss": 0.4293, "step": 40880 }, { "epoch": 9.78, "learning_rate": 9.667140598949453e-05, "loss": 0.4015, "step": 40890 }, { "epoch": 9.78, "learning_rate": 9.666979603833919e-05, "loss": 0.3316, "step": 40900 }, { "epoch": 9.79, "learning_rate": 9.666818571134554e-05, "loss": 0.4352, "step": 40910 }, { "epoch": 9.79, "learning_rate": 9.666657500852654e-05, "loss": 0.3929, "step": 40920 }, { "epoch": 9.79, "learning_rate": 9.666496392989518e-05, "loss": 0.4227, "step": 40930 }, { "epoch": 9.79, "learning_rate": 9.666335247546442e-05, "loss": 0.3553, "step": 40940 }, { "epoch": 9.8, "learning_rate": 9.666174064524724e-05, "loss": 0.4079, "step": 40950 }, { "epoch": 9.8, "learning_rate": 9.666012843925663e-05, "loss": 0.3567, "step": 40960 }, { "epoch": 9.8, "learning_rate": 9.665851585750554e-05, "loss": 0.3906, "step": 40970 }, { "epoch": 9.8, "learning_rate": 9.665690290000699e-05, "loss": 0.3626, "step": 40980 }, { "epoch": 9.81, "learning_rate": 9.665528956677396e-05, "loss": 0.4631, "step": 40990 }, { "epoch": 9.81, "learning_rate": 9.665367585781946e-05, "loss": 0.4318, "step": 41000 }, { "epoch": 9.81, "learning_rate": 9.665206177315645e-05, "loss": 0.342, "step": 41010 }, { "epoch": 9.81, "learning_rate": 9.665044731279796e-05, "loss": 0.3885, "step": 41020 }, { "epoch": 9.81, "learning_rate": 9.664883247675696e-05, "loss": 0.3419, "step": 41030 }, { "epoch": 9.82, "learning_rate": 9.664721726504646e-05, "loss": 0.3968, "step": 41040 }, { "epoch": 9.82, "learning_rate": 9.664560167767952e-05, "loss": 0.4329, "step": 41050 }, { "epoch": 9.82, "learning_rate": 9.664398571466908e-05, "loss": 0.4226, "step": 41060 }, { "epoch": 9.82, "learning_rate": 9.664236937602819e-05, "loss": 0.3786, "step": 41070 }, { "epoch": 9.83, "learning_rate": 9.664075266176986e-05, "loss": 0.3796, "step": 41080 }, { "epoch": 9.83, "learning_rate": 9.663913557190712e-05, "loss": 0.4111, "step": 41090 }, { "epoch": 9.83, "learning_rate": 9.663751810645297e-05, "loss": 0.3986, "step": 41100 }, { "epoch": 9.83, "learning_rate": 9.663590026542044e-05, "loss": 0.421, "step": 41110 }, { "epoch": 9.83, "learning_rate": 9.663428204882258e-05, "loss": 0.3886, "step": 41120 }, { "epoch": 9.84, "learning_rate": 9.66326634566724e-05, "loss": 0.3684, "step": 41130 }, { "epoch": 9.84, "learning_rate": 9.663104448898295e-05, "loss": 0.3829, "step": 41140 }, { "epoch": 9.84, "learning_rate": 9.662942514576726e-05, "loss": 0.3403, "step": 41150 }, { "epoch": 9.84, "learning_rate": 9.662780542703837e-05, "loss": 0.393, "step": 41160 }, { "epoch": 9.85, "learning_rate": 9.662618533280933e-05, "loss": 0.4432, "step": 41170 }, { "epoch": 9.85, "learning_rate": 9.662456486309316e-05, "loss": 0.408, "step": 41180 }, { "epoch": 9.85, "learning_rate": 9.662294401790298e-05, "loss": 0.3362, "step": 41190 }, { "epoch": 9.85, "learning_rate": 9.662132279725176e-05, "loss": 0.4049, "step": 41200 }, { "epoch": 9.86, "learning_rate": 9.66197012011526e-05, "loss": 0.3863, "step": 41210 }, { "epoch": 9.86, "learning_rate": 9.661807922961854e-05, "loss": 0.3565, "step": 41220 }, { "epoch": 9.86, "learning_rate": 9.661645688266265e-05, "loss": 0.4222, "step": 41230 }, { "epoch": 9.86, "learning_rate": 9.661483416029801e-05, "loss": 0.4112, "step": 41240 }, { "epoch": 9.86, "learning_rate": 9.661321106253768e-05, "loss": 0.3467, "step": 41250 }, { "epoch": 9.87, "learning_rate": 9.661158758939472e-05, "loss": 0.4093, "step": 41260 }, { "epoch": 9.87, "learning_rate": 9.66099637408822e-05, "loss": 0.4723, "step": 41270 }, { "epoch": 9.87, "learning_rate": 9.660833951701321e-05, "loss": 0.4137, "step": 41280 }, { "epoch": 9.87, "learning_rate": 9.660671491780084e-05, "loss": 0.3585, "step": 41290 }, { "epoch": 9.88, "learning_rate": 9.660508994325814e-05, "loss": 0.4095, "step": 41300 }, { "epoch": 9.88, "learning_rate": 9.660346459339824e-05, "loss": 0.356, "step": 41310 }, { "epoch": 9.88, "learning_rate": 9.66018388682342e-05, "loss": 0.4049, "step": 41320 }, { "epoch": 9.88, "learning_rate": 9.66002127677791e-05, "loss": 0.4145, "step": 41330 }, { "epoch": 9.89, "learning_rate": 9.659858629204607e-05, "loss": 0.4173, "step": 41340 }, { "epoch": 9.89, "learning_rate": 9.659695944104818e-05, "loss": 0.3662, "step": 41350 }, { "epoch": 9.89, "learning_rate": 9.659533221479855e-05, "loss": 0.372, "step": 41360 }, { "epoch": 9.89, "learning_rate": 9.659370461331027e-05, "loss": 0.3652, "step": 41370 }, { "epoch": 9.89, "learning_rate": 9.659207663659647e-05, "loss": 0.3406, "step": 41380 }, { "epoch": 9.9, "learning_rate": 9.659044828467023e-05, "loss": 0.3884, "step": 41390 }, { "epoch": 9.9, "learning_rate": 9.658881955754469e-05, "loss": 0.4343, "step": 41400 }, { "epoch": 9.9, "learning_rate": 9.658719045523294e-05, "loss": 0.3789, "step": 41410 }, { "epoch": 9.9, "learning_rate": 9.658556097774811e-05, "loss": 0.3951, "step": 41420 }, { "epoch": 9.91, "learning_rate": 9.658393112510334e-05, "loss": 0.3677, "step": 41430 }, { "epoch": 9.91, "learning_rate": 9.658230089731174e-05, "loss": 0.4221, "step": 41440 }, { "epoch": 9.91, "learning_rate": 9.658067029438643e-05, "loss": 0.3395, "step": 41450 }, { "epoch": 9.91, "learning_rate": 9.657903931634056e-05, "loss": 0.3698, "step": 41460 }, { "epoch": 9.91, "learning_rate": 9.657740796318726e-05, "loss": 0.3943, "step": 41470 }, { "epoch": 9.92, "learning_rate": 9.657577623493965e-05, "loss": 0.3827, "step": 41480 }, { "epoch": 9.92, "learning_rate": 9.65741441316109e-05, "loss": 0.3997, "step": 41490 }, { "epoch": 9.92, "learning_rate": 9.657251165321412e-05, "loss": 0.3592, "step": 41500 }, { "epoch": 9.92, "learning_rate": 9.657087879976247e-05, "loss": 0.3702, "step": 41510 }, { "epoch": 9.93, "learning_rate": 9.656924557126913e-05, "loss": 0.352, "step": 41520 }, { "epoch": 9.93, "learning_rate": 9.65676119677472e-05, "loss": 0.3968, "step": 41530 }, { "epoch": 9.93, "learning_rate": 9.656597798920987e-05, "loss": 0.4173, "step": 41540 }, { "epoch": 9.93, "learning_rate": 9.656434363567031e-05, "loss": 0.3621, "step": 41550 }, { "epoch": 9.94, "learning_rate": 9.656270890714164e-05, "loss": 0.4456, "step": 41560 }, { "epoch": 9.94, "learning_rate": 9.656107380363706e-05, "loss": 0.3606, "step": 41570 }, { "epoch": 9.94, "learning_rate": 9.655943832516972e-05, "loss": 0.3476, "step": 41580 }, { "epoch": 9.94, "learning_rate": 9.655780247175279e-05, "loss": 0.44, "step": 41590 }, { "epoch": 9.94, "learning_rate": 9.655616624339945e-05, "loss": 0.376, "step": 41600 }, { "epoch": 9.95, "learning_rate": 9.655452964012287e-05, "loss": 0.379, "step": 41610 }, { "epoch": 9.95, "learning_rate": 9.655289266193624e-05, "loss": 0.371, "step": 41620 }, { "epoch": 9.95, "learning_rate": 9.655125530885274e-05, "loss": 0.4068, "step": 41630 }, { "epoch": 10.0, "learning_rate": 9.654961758088556e-05, "loss": 0.3966, "step": 41640 }, { "epoch": 10.0, "learning_rate": 9.654797947804787e-05, "loss": 0.3682, "step": 41650 }, { "epoch": 10.01, "learning_rate": 9.65463410003529e-05, "loss": 0.4053, "step": 41660 }, { "epoch": 10.01, "learning_rate": 9.65447021478138e-05, "loss": 0.3703, "step": 41670 }, { "epoch": 10.01, "learning_rate": 9.654306292044379e-05, "loss": 0.3875, "step": 41680 }, { "epoch": 10.01, "learning_rate": 9.654142331825607e-05, "loss": 0.3801, "step": 41690 }, { "epoch": 10.02, "learning_rate": 9.653978334126384e-05, "loss": 0.4174, "step": 41700 }, { "epoch": 10.02, "learning_rate": 9.65381429894803e-05, "loss": 0.3858, "step": 41710 }, { "epoch": 10.02, "learning_rate": 9.653650226291869e-05, "loss": 0.3927, "step": 41720 }, { "epoch": 10.02, "learning_rate": 9.653486116159218e-05, "loss": 0.3916, "step": 41730 }, { "epoch": 10.03, "learning_rate": 9.653321968551403e-05, "loss": 0.3687, "step": 41740 }, { "epoch": 10.03, "learning_rate": 9.653157783469742e-05, "loss": 0.3638, "step": 41750 }, { "epoch": 10.03, "learning_rate": 9.65299356091556e-05, "loss": 0.3879, "step": 41760 }, { "epoch": 10.03, "learning_rate": 9.652829300890178e-05, "loss": 0.3658, "step": 41770 }, { "epoch": 10.03, "learning_rate": 9.652665003394921e-05, "loss": 0.3918, "step": 41780 }, { "epoch": 10.04, "learning_rate": 9.652500668431108e-05, "loss": 0.3632, "step": 41790 }, { "epoch": 10.04, "learning_rate": 9.652336296000066e-05, "loss": 0.3615, "step": 41800 }, { "epoch": 10.04, "learning_rate": 9.652171886103119e-05, "loss": 0.4006, "step": 41810 }, { "epoch": 10.04, "learning_rate": 9.652007438741585e-05, "loss": 0.4148, "step": 41820 }, { "epoch": 10.05, "learning_rate": 9.651842953916797e-05, "loss": 0.3684, "step": 41830 }, { "epoch": 10.05, "learning_rate": 9.651678431630074e-05, "loss": 0.3516, "step": 41840 }, { "epoch": 10.05, "learning_rate": 9.651513871882742e-05, "loss": 0.3982, "step": 41850 }, { "epoch": 10.05, "learning_rate": 9.651349274676128e-05, "loss": 0.3689, "step": 41860 }, { "epoch": 10.05, "learning_rate": 9.651184640011556e-05, "loss": 0.3374, "step": 41870 }, { "epoch": 10.06, "learning_rate": 9.651019967890351e-05, "loss": 0.3649, "step": 41880 }, { "epoch": 10.06, "learning_rate": 9.65085525831384e-05, "loss": 0.3978, "step": 41890 }, { "epoch": 10.06, "learning_rate": 9.65069051128335e-05, "loss": 0.3759, "step": 41900 }, { "epoch": 10.06, "learning_rate": 9.650525726800207e-05, "loss": 0.3769, "step": 41910 }, { "epoch": 10.07, "learning_rate": 9.650360904865738e-05, "loss": 0.407, "step": 41920 }, { "epoch": 10.07, "learning_rate": 9.650196045481272e-05, "loss": 0.3826, "step": 41930 }, { "epoch": 10.07, "learning_rate": 9.650031148648133e-05, "loss": 0.4182, "step": 41940 }, { "epoch": 10.07, "learning_rate": 9.649866214367653e-05, "loss": 0.3759, "step": 41950 }, { "epoch": 10.08, "learning_rate": 9.649701242641158e-05, "loss": 0.3956, "step": 41960 }, { "epoch": 10.08, "learning_rate": 9.649536233469976e-05, "loss": 0.3448, "step": 41970 }, { "epoch": 10.08, "learning_rate": 9.649371186855438e-05, "loss": 0.3779, "step": 41980 }, { "epoch": 10.08, "learning_rate": 9.649206102798872e-05, "loss": 0.3193, "step": 41990 }, { "epoch": 10.08, "learning_rate": 9.649040981301608e-05, "loss": 0.3911, "step": 42000 }, { "epoch": 10.09, "learning_rate": 9.648875822364973e-05, "loss": 0.3806, "step": 42010 }, { "epoch": 10.09, "learning_rate": 9.6487106259903e-05, "loss": 0.3871, "step": 42020 }, { "epoch": 10.09, "learning_rate": 9.648545392178919e-05, "loss": 0.4361, "step": 42030 }, { "epoch": 10.09, "learning_rate": 9.64838012093216e-05, "loss": 0.4112, "step": 42040 }, { "epoch": 10.1, "learning_rate": 9.648214812251355e-05, "loss": 0.3396, "step": 42050 }, { "epoch": 10.1, "learning_rate": 9.648049466137833e-05, "loss": 0.3965, "step": 42060 }, { "epoch": 10.1, "learning_rate": 9.647884082592928e-05, "loss": 0.3113, "step": 42070 }, { "epoch": 10.1, "learning_rate": 9.64771866161797e-05, "loss": 0.4048, "step": 42080 }, { "epoch": 10.11, "learning_rate": 9.647553203214292e-05, "loss": 0.3452, "step": 42090 }, { "epoch": 10.11, "learning_rate": 9.647387707383226e-05, "loss": 0.3514, "step": 42100 }, { "epoch": 10.11, "learning_rate": 9.647222174126106e-05, "loss": 0.413, "step": 42110 }, { "epoch": 10.11, "learning_rate": 9.647056603444264e-05, "loss": 0.3754, "step": 42120 }, { "epoch": 10.11, "learning_rate": 9.646890995339033e-05, "loss": 0.397, "step": 42130 }, { "epoch": 10.12, "learning_rate": 9.64672534981175e-05, "loss": 0.3422, "step": 42140 }, { "epoch": 10.12, "learning_rate": 9.646559666863744e-05, "loss": 0.3848, "step": 42150 }, { "epoch": 10.12, "learning_rate": 9.64639394649635e-05, "loss": 0.3345, "step": 42160 }, { "epoch": 10.12, "learning_rate": 9.646228188710906e-05, "loss": 0.3581, "step": 42170 }, { "epoch": 10.13, "learning_rate": 9.646062393508746e-05, "loss": 0.3902, "step": 42180 }, { "epoch": 10.13, "learning_rate": 9.645896560891202e-05, "loss": 0.4054, "step": 42190 }, { "epoch": 10.13, "learning_rate": 9.645730690859613e-05, "loss": 0.3316, "step": 42200 }, { "epoch": 10.13, "learning_rate": 9.645564783415313e-05, "loss": 0.36, "step": 42210 }, { "epoch": 10.13, "learning_rate": 9.645398838559637e-05, "loss": 0.3709, "step": 42220 }, { "epoch": 10.14, "learning_rate": 9.645232856293924e-05, "loss": 0.3618, "step": 42230 }, { "epoch": 10.14, "learning_rate": 9.64506683661951e-05, "loss": 0.4045, "step": 42240 }, { "epoch": 10.14, "learning_rate": 9.644900779537731e-05, "loss": 0.3428, "step": 42250 }, { "epoch": 10.14, "learning_rate": 9.644734685049926e-05, "loss": 0.3719, "step": 42260 }, { "epoch": 10.15, "learning_rate": 9.64456855315743e-05, "loss": 0.3929, "step": 42270 }, { "epoch": 10.15, "learning_rate": 9.644402383861581e-05, "loss": 0.3721, "step": 42280 }, { "epoch": 10.15, "learning_rate": 9.644236177163719e-05, "loss": 0.3651, "step": 42290 }, { "epoch": 10.15, "learning_rate": 9.644069933065182e-05, "loss": 0.3803, "step": 42300 }, { "epoch": 10.16, "learning_rate": 9.643903651567311e-05, "loss": 0.3819, "step": 42310 }, { "epoch": 10.16, "learning_rate": 9.64373733267144e-05, "loss": 0.36, "step": 42320 }, { "epoch": 10.16, "learning_rate": 9.643570976378913e-05, "loss": 0.3814, "step": 42330 }, { "epoch": 10.16, "learning_rate": 9.643404582691067e-05, "loss": 0.3564, "step": 42340 }, { "epoch": 10.16, "learning_rate": 9.643238151609243e-05, "loss": 0.321, "step": 42350 }, { "epoch": 10.17, "learning_rate": 9.643071683134782e-05, "loss": 0.4369, "step": 42360 }, { "epoch": 10.17, "learning_rate": 9.642905177269021e-05, "loss": 0.3536, "step": 42370 }, { "epoch": 10.17, "learning_rate": 9.642738634013307e-05, "loss": 0.4075, "step": 42380 }, { "epoch": 10.17, "learning_rate": 9.642572053368975e-05, "loss": 0.342, "step": 42390 }, { "epoch": 10.18, "learning_rate": 9.64240543533737e-05, "loss": 0.3748, "step": 42400 }, { "epoch": 10.18, "learning_rate": 9.642238779919835e-05, "loss": 0.3307, "step": 42410 }, { "epoch": 10.18, "learning_rate": 9.642072087117708e-05, "loss": 0.3904, "step": 42420 }, { "epoch": 10.18, "learning_rate": 9.641905356932335e-05, "loss": 0.3669, "step": 42430 }, { "epoch": 10.19, "learning_rate": 9.641738589365055e-05, "loss": 0.3798, "step": 42440 }, { "epoch": 10.19, "learning_rate": 9.641571784417216e-05, "loss": 0.3443, "step": 42450 }, { "epoch": 10.19, "learning_rate": 9.641404942090158e-05, "loss": 0.3969, "step": 42460 }, { "epoch": 10.19, "learning_rate": 9.641238062385224e-05, "loss": 0.3318, "step": 42470 }, { "epoch": 10.19, "learning_rate": 9.641071145303759e-05, "loss": 0.3612, "step": 42480 }, { "epoch": 10.2, "learning_rate": 9.640904190847108e-05, "loss": 0.3652, "step": 42490 }, { "epoch": 10.2, "learning_rate": 9.640737199016616e-05, "loss": 0.3673, "step": 42500 }, { "epoch": 10.2, "learning_rate": 9.640570169813625e-05, "loss": 0.329, "step": 42510 }, { "epoch": 10.2, "learning_rate": 9.640403103239484e-05, "loss": 0.378, "step": 42520 }, { "epoch": 10.21, "learning_rate": 9.640235999295534e-05, "loss": 0.3294, "step": 42530 }, { "epoch": 10.21, "learning_rate": 9.640068857983124e-05, "loss": 0.3933, "step": 42540 }, { "epoch": 10.21, "learning_rate": 9.639901679303598e-05, "loss": 0.3462, "step": 42550 }, { "epoch": 10.21, "learning_rate": 9.639734463258303e-05, "loss": 0.3589, "step": 42560 }, { "epoch": 10.21, "learning_rate": 9.639567209848588e-05, "loss": 0.4051, "step": 42570 }, { "epoch": 10.22, "learning_rate": 9.639399919075796e-05, "loss": 0.3254, "step": 42580 }, { "epoch": 10.22, "learning_rate": 9.639232590941276e-05, "loss": 0.3383, "step": 42590 }, { "epoch": 10.22, "learning_rate": 9.639065225446375e-05, "loss": 0.313, "step": 42600 }, { "epoch": 10.22, "learning_rate": 9.63889782259244e-05, "loss": 0.3779, "step": 42610 }, { "epoch": 10.23, "learning_rate": 9.638730382380825e-05, "loss": 0.3086, "step": 42620 }, { "epoch": 10.23, "learning_rate": 9.63856290481287e-05, "loss": 0.3632, "step": 42630 }, { "epoch": 10.23, "learning_rate": 9.63839538988993e-05, "loss": 0.3796, "step": 42640 }, { "epoch": 10.23, "learning_rate": 9.638227837613349e-05, "loss": 0.3178, "step": 42650 }, { "epoch": 10.24, "learning_rate": 9.638060247984479e-05, "loss": 0.3648, "step": 42660 }, { "epoch": 10.24, "learning_rate": 9.637892621004672e-05, "loss": 0.3548, "step": 42670 }, { "epoch": 10.24, "learning_rate": 9.637724956675274e-05, "loss": 0.3275, "step": 42680 }, { "epoch": 10.24, "learning_rate": 9.637557254997635e-05, "loss": 0.3837, "step": 42690 }, { "epoch": 10.24, "learning_rate": 9.63738951597311e-05, "loss": 0.3716, "step": 42700 }, { "epoch": 10.25, "learning_rate": 9.637221739603045e-05, "loss": 0.3685, "step": 42710 }, { "epoch": 10.25, "learning_rate": 9.637053925888794e-05, "loss": 0.3513, "step": 42720 }, { "epoch": 10.25, "learning_rate": 9.636886074831709e-05, "loss": 0.3811, "step": 42730 }, { "epoch": 10.25, "learning_rate": 9.636718186433137e-05, "loss": 0.3742, "step": 42740 }, { "epoch": 10.26, "learning_rate": 9.636550260694435e-05, "loss": 0.3538, "step": 42750 }, { "epoch": 10.26, "learning_rate": 9.636382297616954e-05, "loss": 0.3251, "step": 42760 }, { "epoch": 10.26, "learning_rate": 9.636214297202045e-05, "loss": 0.3719, "step": 42770 }, { "epoch": 10.26, "learning_rate": 9.636046259451064e-05, "loss": 0.3784, "step": 42780 }, { "epoch": 10.27, "learning_rate": 9.635878184365361e-05, "loss": 0.3166, "step": 42790 }, { "epoch": 10.27, "learning_rate": 9.635710071946291e-05, "loss": 0.3672, "step": 42800 }, { "epoch": 10.27, "learning_rate": 9.635541922195208e-05, "loss": 0.3478, "step": 42810 }, { "epoch": 10.27, "learning_rate": 9.635373735113466e-05, "loss": 0.3796, "step": 42820 }, { "epoch": 10.27, "learning_rate": 9.635205510702421e-05, "loss": 0.351, "step": 42830 }, { "epoch": 10.28, "learning_rate": 9.635037248963423e-05, "loss": 0.3657, "step": 42840 }, { "epoch": 10.28, "learning_rate": 9.634868949897833e-05, "loss": 0.3728, "step": 42850 }, { "epoch": 10.28, "learning_rate": 9.634700613507002e-05, "loss": 0.372, "step": 42860 }, { "epoch": 10.28, "learning_rate": 9.634532239792287e-05, "loss": 0.3491, "step": 42870 }, { "epoch": 10.29, "learning_rate": 9.634363828755044e-05, "loss": 0.382, "step": 42880 }, { "epoch": 10.29, "learning_rate": 9.63419538039663e-05, "loss": 0.3652, "step": 42890 }, { "epoch": 10.29, "learning_rate": 9.634026894718401e-05, "loss": 0.3279, "step": 42900 }, { "epoch": 10.29, "learning_rate": 9.633858371721714e-05, "loss": 0.327, "step": 42910 }, { "epoch": 10.29, "learning_rate": 9.633689811407925e-05, "loss": 0.3375, "step": 42920 }, { "epoch": 10.3, "learning_rate": 9.633521213778392e-05, "loss": 0.3238, "step": 42930 }, { "epoch": 10.3, "learning_rate": 9.633352578834471e-05, "loss": 0.3799, "step": 42940 }, { "epoch": 10.3, "learning_rate": 9.633183906577526e-05, "loss": 0.371, "step": 42950 }, { "epoch": 10.3, "learning_rate": 9.633015197008908e-05, "loss": 0.3263, "step": 42960 }, { "epoch": 10.31, "learning_rate": 9.632846450129981e-05, "loss": 0.2916, "step": 42970 }, { "epoch": 10.31, "learning_rate": 9.632677665942102e-05, "loss": 0.348, "step": 42980 }, { "epoch": 10.31, "learning_rate": 9.632508844446628e-05, "loss": 0.3812, "step": 42990 }, { "epoch": 10.31, "learning_rate": 9.632339985644923e-05, "loss": 0.396, "step": 43000 }, { "epoch": 10.32, "learning_rate": 9.632171089538344e-05, "loss": 0.3527, "step": 43010 }, { "epoch": 10.32, "learning_rate": 9.632002156128252e-05, "loss": 0.3275, "step": 43020 }, { "epoch": 10.32, "learning_rate": 9.631833185416006e-05, "loss": 0.3583, "step": 43030 }, { "epoch": 10.32, "learning_rate": 9.631664177402968e-05, "loss": 0.3189, "step": 43040 }, { "epoch": 10.32, "learning_rate": 9.6314951320905e-05, "loss": 0.3459, "step": 43050 }, { "epoch": 10.33, "learning_rate": 9.631326049479961e-05, "loss": 0.339, "step": 43060 }, { "epoch": 10.33, "learning_rate": 9.631156929572716e-05, "loss": 0.327, "step": 43070 }, { "epoch": 10.33, "learning_rate": 9.630987772370123e-05, "loss": 0.3478, "step": 43080 }, { "epoch": 10.33, "learning_rate": 9.630818577873545e-05, "loss": 0.3115, "step": 43090 }, { "epoch": 10.34, "learning_rate": 9.63064934608435e-05, "loss": 0.3779, "step": 43100 }, { "epoch": 10.34, "learning_rate": 9.630480077003893e-05, "loss": 0.3475, "step": 43110 }, { "epoch": 10.34, "learning_rate": 9.630310770633542e-05, "loss": 0.3054, "step": 43120 }, { "epoch": 10.34, "learning_rate": 9.630141426974658e-05, "loss": 0.4314, "step": 43130 }, { "epoch": 10.35, "learning_rate": 9.629972046028607e-05, "loss": 0.301, "step": 43140 }, { "epoch": 10.35, "learning_rate": 9.629802627796752e-05, "loss": 0.36, "step": 43150 }, { "epoch": 10.35, "learning_rate": 9.629633172280457e-05, "loss": 0.3417, "step": 43160 }, { "epoch": 10.35, "learning_rate": 9.629463679481086e-05, "loss": 0.346, "step": 43170 }, { "epoch": 10.35, "learning_rate": 9.629294149400005e-05, "loss": 0.3533, "step": 43180 }, { "epoch": 10.36, "learning_rate": 9.62912458203858e-05, "loss": 0.3345, "step": 43190 }, { "epoch": 10.36, "learning_rate": 9.628954977398175e-05, "loss": 0.3402, "step": 43200 }, { "epoch": 10.36, "learning_rate": 9.628785335480157e-05, "loss": 0.3338, "step": 43210 }, { "epoch": 10.36, "learning_rate": 9.628615656285892e-05, "loss": 0.3584, "step": 43220 }, { "epoch": 10.37, "learning_rate": 9.628445939816743e-05, "loss": 0.3361, "step": 43230 }, { "epoch": 10.37, "learning_rate": 9.628276186074083e-05, "loss": 0.3602, "step": 43240 }, { "epoch": 10.37, "learning_rate": 9.628106395059275e-05, "loss": 0.364, "step": 43250 }, { "epoch": 10.37, "learning_rate": 9.627936566773687e-05, "loss": 0.3325, "step": 43260 }, { "epoch": 10.37, "learning_rate": 9.627766701218688e-05, "loss": 0.384, "step": 43270 }, { "epoch": 10.38, "learning_rate": 9.627596798395644e-05, "loss": 0.3087, "step": 43280 }, { "epoch": 10.38, "learning_rate": 9.627426858305926e-05, "loss": 0.3502, "step": 43290 }, { "epoch": 10.38, "learning_rate": 9.627256880950898e-05, "loss": 0.3355, "step": 43300 }, { "epoch": 10.38, "learning_rate": 9.627086866331932e-05, "loss": 0.3281, "step": 43310 }, { "epoch": 10.39, "learning_rate": 9.626916814450397e-05, "loss": 0.4018, "step": 43320 }, { "epoch": 10.39, "learning_rate": 9.626746725307662e-05, "loss": 0.3927, "step": 43330 }, { "epoch": 10.39, "learning_rate": 9.626576598905097e-05, "loss": 0.3818, "step": 43340 }, { "epoch": 10.39, "learning_rate": 9.626406435244073e-05, "loss": 0.3295, "step": 43350 }, { "epoch": 10.4, "learning_rate": 9.626236234325958e-05, "loss": 0.3909, "step": 43360 }, { "epoch": 10.4, "learning_rate": 9.626065996152125e-05, "loss": 0.3355, "step": 43370 }, { "epoch": 10.4, "learning_rate": 9.625895720723941e-05, "loss": 0.3209, "step": 43380 }, { "epoch": 10.4, "learning_rate": 9.625725408042782e-05, "loss": 0.3313, "step": 43390 }, { "epoch": 10.4, "learning_rate": 9.625555058110018e-05, "loss": 0.3185, "step": 43400 }, { "epoch": 10.41, "learning_rate": 9.625384670927022e-05, "loss": 0.3675, "step": 43410 }, { "epoch": 10.41, "learning_rate": 9.625214246495162e-05, "loss": 0.3678, "step": 43420 }, { "epoch": 10.41, "learning_rate": 9.625043784815814e-05, "loss": 0.3171, "step": 43430 }, { "epoch": 10.41, "learning_rate": 9.62487328589035e-05, "loss": 0.3341, "step": 43440 }, { "epoch": 10.42, "learning_rate": 9.624702749720143e-05, "loss": 0.3455, "step": 43450 }, { "epoch": 10.42, "learning_rate": 9.624532176306567e-05, "loss": 0.3037, "step": 43460 }, { "epoch": 10.42, "learning_rate": 9.624361565650995e-05, "loss": 0.3965, "step": 43470 }, { "epoch": 10.42, "learning_rate": 9.624190917754799e-05, "loss": 0.3105, "step": 43480 }, { "epoch": 10.43, "learning_rate": 9.624020232619355e-05, "loss": 0.3602, "step": 43490 }, { "epoch": 10.43, "learning_rate": 9.62384951024604e-05, "loss": 0.3283, "step": 43500 }, { "epoch": 10.43, "learning_rate": 9.623678750636225e-05, "loss": 0.3294, "step": 43510 }, { "epoch": 10.43, "learning_rate": 9.623507953791287e-05, "loss": 0.3342, "step": 43520 }, { "epoch": 10.43, "learning_rate": 9.623337119712601e-05, "loss": 0.3056, "step": 43530 }, { "epoch": 10.44, "learning_rate": 9.623166248401543e-05, "loss": 0.2887, "step": 43540 }, { "epoch": 10.44, "learning_rate": 9.622995339859488e-05, "loss": 0.3024, "step": 43550 }, { "epoch": 10.44, "learning_rate": 9.622824394087815e-05, "loss": 0.3471, "step": 43560 }, { "epoch": 10.44, "learning_rate": 9.622653411087899e-05, "loss": 0.3561, "step": 43570 }, { "epoch": 10.45, "learning_rate": 9.622482390861116e-05, "loss": 0.3043, "step": 43580 }, { "epoch": 10.45, "learning_rate": 9.622311333408844e-05, "loss": 0.3621, "step": 43590 }, { "epoch": 10.45, "learning_rate": 9.62214023873246e-05, "loss": 0.302, "step": 43600 }, { "epoch": 10.45, "learning_rate": 9.621969106833344e-05, "loss": 0.3112, "step": 43610 }, { "epoch": 10.45, "learning_rate": 9.621797937712873e-05, "loss": 0.3224, "step": 43620 }, { "epoch": 10.46, "learning_rate": 9.621626731372424e-05, "loss": 0.3588, "step": 43630 }, { "epoch": 10.46, "learning_rate": 9.621455487813378e-05, "loss": 0.3057, "step": 43640 }, { "epoch": 10.46, "learning_rate": 9.621284207037111e-05, "loss": 0.3448, "step": 43650 }, { "epoch": 10.46, "learning_rate": 9.621112889045005e-05, "loss": 0.3299, "step": 43660 }, { "epoch": 10.47, "learning_rate": 9.620941533838439e-05, "loss": 0.3554, "step": 43670 }, { "epoch": 10.47, "learning_rate": 9.620770141418793e-05, "loss": 0.3583, "step": 43680 }, { "epoch": 10.47, "learning_rate": 9.620598711787448e-05, "loss": 0.3303, "step": 43690 }, { "epoch": 10.47, "learning_rate": 9.620427244945783e-05, "loss": 0.3203, "step": 43700 }, { "epoch": 10.48, "learning_rate": 9.620255740895178e-05, "loss": 0.3833, "step": 43710 }, { "epoch": 10.48, "learning_rate": 9.620084199637019e-05, "loss": 0.339, "step": 43720 }, { "epoch": 10.48, "learning_rate": 9.619912621172683e-05, "loss": 0.3292, "step": 43730 }, { "epoch": 10.48, "learning_rate": 9.619741005503551e-05, "loss": 0.3687, "step": 43740 }, { "epoch": 10.48, "learning_rate": 9.619569352631007e-05, "loss": 0.31, "step": 43750 }, { "epoch": 10.49, "learning_rate": 9.619397662556435e-05, "loss": 0.2894, "step": 43760 }, { "epoch": 10.49, "learning_rate": 9.619225935281214e-05, "loss": 0.3907, "step": 43770 }, { "epoch": 10.49, "learning_rate": 9.619054170806729e-05, "loss": 0.3627, "step": 43780 }, { "epoch": 10.49, "learning_rate": 9.618882369134366e-05, "loss": 0.3895, "step": 43790 }, { "epoch": 10.5, "learning_rate": 9.618710530265503e-05, "loss": 0.3355, "step": 43800 }, { "epoch": 10.5, "learning_rate": 9.618538654201525e-05, "loss": 0.3693, "step": 43810 }, { "epoch": 10.5, "learning_rate": 9.61836674094382e-05, "loss": 0.3603, "step": 43820 }, { "epoch": 10.5, "learning_rate": 9.618194790493771e-05, "loss": 0.3444, "step": 43830 }, { "epoch": 10.51, "learning_rate": 9.61802280285276e-05, "loss": 0.3294, "step": 43840 }, { "epoch": 10.51, "learning_rate": 9.617850778022173e-05, "loss": 0.3785, "step": 43850 }, { "epoch": 10.51, "learning_rate": 9.617678716003398e-05, "loss": 0.4061, "step": 43860 }, { "epoch": 10.51, "learning_rate": 9.617506616797818e-05, "loss": 0.3472, "step": 43870 }, { "epoch": 10.51, "learning_rate": 9.61733448040682e-05, "loss": 0.3677, "step": 43880 }, { "epoch": 10.52, "learning_rate": 9.61716230683179e-05, "loss": 0.3421, "step": 43890 }, { "epoch": 10.52, "learning_rate": 9.616990096074115e-05, "loss": 0.3193, "step": 43900 }, { "epoch": 10.52, "learning_rate": 9.61681784813518e-05, "loss": 0.3336, "step": 43910 }, { "epoch": 10.52, "learning_rate": 9.616645563016373e-05, "loss": 0.3585, "step": 43920 }, { "epoch": 10.53, "learning_rate": 9.616473240719084e-05, "loss": 0.393, "step": 43930 }, { "epoch": 10.53, "learning_rate": 9.616300881244698e-05, "loss": 0.365, "step": 43940 }, { "epoch": 10.53, "learning_rate": 9.616128484594601e-05, "loss": 0.3898, "step": 43950 }, { "epoch": 10.53, "learning_rate": 9.615956050770187e-05, "loss": 0.3854, "step": 43960 }, { "epoch": 10.53, "learning_rate": 9.615783579772841e-05, "loss": 0.3776, "step": 43970 }, { "epoch": 10.54, "learning_rate": 9.615611071603953e-05, "loss": 0.4282, "step": 43980 }, { "epoch": 10.54, "learning_rate": 9.615438526264912e-05, "loss": 0.3708, "step": 43990 }, { "epoch": 10.54, "learning_rate": 9.615265943757106e-05, "loss": 0.3556, "step": 44000 }, { "epoch": 10.54, "learning_rate": 9.615093324081928e-05, "loss": 0.4129, "step": 44010 }, { "epoch": 10.55, "learning_rate": 9.614920667240764e-05, "loss": 0.4263, "step": 44020 }, { "epoch": 10.55, "learning_rate": 9.614747973235009e-05, "loss": 0.3415, "step": 44030 }, { "epoch": 10.55, "learning_rate": 9.614575242066051e-05, "loss": 0.41, "step": 44040 }, { "epoch": 10.55, "learning_rate": 9.61440247373528e-05, "loss": 0.3947, "step": 44050 }, { "epoch": 10.56, "learning_rate": 9.61422966824409e-05, "loss": 0.4678, "step": 44060 }, { "epoch": 10.56, "learning_rate": 9.614056825593871e-05, "loss": 0.4096, "step": 44070 }, { "epoch": 10.56, "learning_rate": 9.613883945786015e-05, "loss": 0.3755, "step": 44080 }, { "epoch": 10.56, "learning_rate": 9.613711028821915e-05, "loss": 0.3813, "step": 44090 }, { "epoch": 10.56, "learning_rate": 9.613538074702964e-05, "loss": 0.3634, "step": 44100 }, { "epoch": 10.57, "learning_rate": 9.613365083430553e-05, "loss": 0.4191, "step": 44110 }, { "epoch": 10.57, "learning_rate": 9.613192055006076e-05, "loss": 0.3744, "step": 44120 }, { "epoch": 10.57, "learning_rate": 9.613018989430926e-05, "loss": 0.44, "step": 44130 }, { "epoch": 10.57, "learning_rate": 9.612845886706499e-05, "loss": 0.3549, "step": 44140 }, { "epoch": 10.58, "learning_rate": 9.612672746834185e-05, "loss": 0.4489, "step": 44150 }, { "epoch": 10.58, "learning_rate": 9.612499569815383e-05, "loss": 0.3967, "step": 44160 }, { "epoch": 10.58, "learning_rate": 9.612326355651484e-05, "loss": 0.3232, "step": 44170 }, { "epoch": 10.58, "learning_rate": 9.612153104343883e-05, "loss": 0.3732, "step": 44180 }, { "epoch": 10.59, "learning_rate": 9.611979815893979e-05, "loss": 0.3245, "step": 44190 }, { "epoch": 10.59, "learning_rate": 9.611806490303163e-05, "loss": 0.3773, "step": 44200 }, { "epoch": 10.59, "learning_rate": 9.611633127572832e-05, "loss": 0.42, "step": 44210 }, { "epoch": 10.59, "learning_rate": 9.611459727704384e-05, "loss": 0.4149, "step": 44220 }, { "epoch": 10.59, "learning_rate": 9.611286290699213e-05, "loss": 0.4184, "step": 44230 }, { "epoch": 10.6, "learning_rate": 9.611112816558718e-05, "loss": 0.3613, "step": 44240 }, { "epoch": 10.6, "learning_rate": 9.610939305284294e-05, "loss": 0.3573, "step": 44250 }, { "epoch": 10.6, "learning_rate": 9.61076575687734e-05, "loss": 0.375, "step": 44260 }, { "epoch": 10.6, "learning_rate": 9.610592171339252e-05, "loss": 0.3406, "step": 44270 }, { "epoch": 10.61, "learning_rate": 9.61041854867143e-05, "loss": 0.3496, "step": 44280 }, { "epoch": 10.61, "learning_rate": 9.61024488887527e-05, "loss": 0.3582, "step": 44290 }, { "epoch": 10.61, "learning_rate": 9.610071191952171e-05, "loss": 0.4085, "step": 44300 }, { "epoch": 10.61, "learning_rate": 9.609897457903534e-05, "loss": 0.3799, "step": 44310 }, { "epoch": 10.61, "learning_rate": 9.609723686730753e-05, "loss": 0.3841, "step": 44320 }, { "epoch": 10.62, "learning_rate": 9.609549878435233e-05, "loss": 0.3647, "step": 44330 }, { "epoch": 10.62, "learning_rate": 9.609376033018372e-05, "loss": 0.3494, "step": 44340 }, { "epoch": 10.62, "learning_rate": 9.609202150481568e-05, "loss": 0.3597, "step": 44350 }, { "epoch": 10.62, "learning_rate": 9.609028230826225e-05, "loss": 0.4265, "step": 44360 }, { "epoch": 10.63, "learning_rate": 9.608854274053739e-05, "loss": 0.42, "step": 44370 }, { "epoch": 10.63, "learning_rate": 9.608680280165514e-05, "loss": 0.3615, "step": 44380 }, { "epoch": 10.63, "learning_rate": 9.60850624916295e-05, "loss": 0.3899, "step": 44390 }, { "epoch": 10.63, "learning_rate": 9.60833218104745e-05, "loss": 0.3993, "step": 44400 }, { "epoch": 10.64, "learning_rate": 9.608158075820415e-05, "loss": 0.3458, "step": 44410 }, { "epoch": 10.64, "learning_rate": 9.607983933483244e-05, "loss": 0.4036, "step": 44420 }, { "epoch": 10.64, "learning_rate": 9.607809754037344e-05, "loss": 0.3298, "step": 44430 }, { "epoch": 10.64, "learning_rate": 9.607635537484117e-05, "loss": 0.3665, "step": 44440 }, { "epoch": 10.64, "learning_rate": 9.607461283824965e-05, "loss": 0.4225, "step": 44450 }, { "epoch": 10.65, "learning_rate": 9.60728699306129e-05, "loss": 0.434, "step": 44460 }, { "epoch": 10.65, "learning_rate": 9.607112665194496e-05, "loss": 0.3434, "step": 44470 }, { "epoch": 10.65, "learning_rate": 9.606938300225989e-05, "loss": 0.3806, "step": 44480 }, { "epoch": 10.65, "learning_rate": 9.606763898157172e-05, "loss": 0.3875, "step": 44490 }, { "epoch": 10.66, "learning_rate": 9.606589458989448e-05, "loss": 0.3293, "step": 44500 }, { "epoch": 10.66, "learning_rate": 9.606414982724223e-05, "loss": 0.4003, "step": 44510 }, { "epoch": 10.66, "learning_rate": 9.606240469362903e-05, "loss": 0.3681, "step": 44520 }, { "epoch": 10.66, "learning_rate": 9.606065918906893e-05, "loss": 0.3612, "step": 44530 }, { "epoch": 10.66, "learning_rate": 9.605891331357598e-05, "loss": 0.3748, "step": 44540 }, { "epoch": 10.67, "learning_rate": 9.605716706716424e-05, "loss": 0.3698, "step": 44550 }, { "epoch": 10.67, "learning_rate": 9.605542044984778e-05, "loss": 0.3966, "step": 44560 }, { "epoch": 10.67, "learning_rate": 9.605367346164064e-05, "loss": 0.4109, "step": 44570 }, { "epoch": 10.67, "learning_rate": 9.605192610255694e-05, "loss": 0.4062, "step": 44580 }, { "epoch": 10.68, "learning_rate": 9.60501783726107e-05, "loss": 0.3626, "step": 44590 }, { "epoch": 10.68, "learning_rate": 9.604843027181602e-05, "loss": 0.4111, "step": 44600 }, { "epoch": 10.68, "learning_rate": 9.6046681800187e-05, "loss": 0.3798, "step": 44610 }, { "epoch": 10.68, "learning_rate": 9.604493295773767e-05, "loss": 0.4235, "step": 44620 }, { "epoch": 10.69, "learning_rate": 9.604318374448213e-05, "loss": 0.4077, "step": 44630 }, { "epoch": 10.69, "learning_rate": 9.604143416043449e-05, "loss": 0.3029, "step": 44640 }, { "epoch": 10.69, "learning_rate": 9.60396842056088e-05, "loss": 0.4248, "step": 44650 }, { "epoch": 10.69, "learning_rate": 9.60379338800192e-05, "loss": 0.3392, "step": 44660 }, { "epoch": 10.69, "learning_rate": 9.603618318367976e-05, "loss": 0.3829, "step": 44670 }, { "epoch": 10.7, "learning_rate": 9.603443211660459e-05, "loss": 0.3125, "step": 44680 }, { "epoch": 10.7, "learning_rate": 9.603268067880776e-05, "loss": 0.3588, "step": 44690 }, { "epoch": 10.7, "learning_rate": 9.60309288703034e-05, "loss": 0.4197, "step": 44700 }, { "epoch": 10.7, "learning_rate": 9.602917669110563e-05, "loss": 0.3883, "step": 44710 }, { "epoch": 10.71, "learning_rate": 9.602742414122853e-05, "loss": 0.3274, "step": 44720 }, { "epoch": 10.71, "learning_rate": 9.602567122068624e-05, "loss": 0.365, "step": 44730 }, { "epoch": 10.71, "learning_rate": 9.602391792949289e-05, "loss": 0.3862, "step": 44740 }, { "epoch": 10.71, "learning_rate": 9.602216426766252e-05, "loss": 0.3739, "step": 44750 }, { "epoch": 10.72, "learning_rate": 9.602041023520935e-05, "loss": 0.3802, "step": 44760 }, { "epoch": 10.72, "learning_rate": 9.601865583214745e-05, "loss": 0.4054, "step": 44770 }, { "epoch": 10.72, "learning_rate": 9.601690105849095e-05, "loss": 0.3658, "step": 44780 }, { "epoch": 10.72, "learning_rate": 9.6015145914254e-05, "loss": 0.3122, "step": 44790 }, { "epoch": 10.72, "learning_rate": 9.601339039945074e-05, "loss": 0.4011, "step": 44800 }, { "epoch": 10.73, "learning_rate": 9.601163451409528e-05, "loss": 0.3915, "step": 44810 }, { "epoch": 10.73, "learning_rate": 9.600987825820178e-05, "loss": 0.3611, "step": 44820 }, { "epoch": 10.73, "learning_rate": 9.600812163178438e-05, "loss": 0.3507, "step": 44830 }, { "epoch": 10.73, "learning_rate": 9.600636463485721e-05, "loss": 0.3459, "step": 44840 }, { "epoch": 10.74, "learning_rate": 9.600460726743446e-05, "loss": 0.3685, "step": 44850 }, { "epoch": 10.74, "learning_rate": 9.600284952953024e-05, "loss": 0.3828, "step": 44860 }, { "epoch": 10.74, "learning_rate": 9.600109142115872e-05, "loss": 0.3895, "step": 44870 }, { "epoch": 10.74, "learning_rate": 9.599933294233406e-05, "loss": 0.3678, "step": 44880 }, { "epoch": 10.74, "learning_rate": 9.599757409307043e-05, "loss": 0.3884, "step": 44890 }, { "epoch": 10.75, "learning_rate": 9.599581487338198e-05, "loss": 0.3773, "step": 44900 }, { "epoch": 10.75, "learning_rate": 9.599405528328289e-05, "loss": 0.3317, "step": 44910 }, { "epoch": 10.75, "learning_rate": 9.59922953227873e-05, "loss": 0.3395, "step": 44920 }, { "epoch": 10.75, "learning_rate": 9.599053499190944e-05, "loss": 0.3613, "step": 44930 }, { "epoch": 10.76, "learning_rate": 9.598877429066344e-05, "loss": 0.3556, "step": 44940 }, { "epoch": 10.76, "learning_rate": 9.598701321906347e-05, "loss": 0.3964, "step": 44950 }, { "epoch": 10.76, "learning_rate": 9.598525177712375e-05, "loss": 0.4159, "step": 44960 }, { "epoch": 10.76, "learning_rate": 9.598348996485846e-05, "loss": 0.3799, "step": 44970 }, { "epoch": 10.77, "learning_rate": 9.598172778228176e-05, "loss": 0.3204, "step": 44980 }, { "epoch": 10.77, "learning_rate": 9.597996522940786e-05, "loss": 0.3427, "step": 44990 }, { "epoch": 10.77, "learning_rate": 9.597820230625097e-05, "loss": 0.3295, "step": 45000 }, { "epoch": 10.77, "learning_rate": 9.597643901282524e-05, "loss": 0.3606, "step": 45010 }, { "epoch": 10.77, "learning_rate": 9.597467534914492e-05, "loss": 0.3303, "step": 45020 }, { "epoch": 10.78, "learning_rate": 9.597291131522419e-05, "loss": 0.3058, "step": 45030 }, { "epoch": 10.78, "learning_rate": 9.597114691107725e-05, "loss": 0.3378, "step": 45040 }, { "epoch": 10.78, "learning_rate": 9.596938213671831e-05, "loss": 0.3653, "step": 45050 }, { "epoch": 10.78, "learning_rate": 9.596761699216161e-05, "loss": 0.3339, "step": 45060 }, { "epoch": 10.79, "learning_rate": 9.596585147742135e-05, "loss": 0.3134, "step": 45070 }, { "epoch": 10.79, "learning_rate": 9.596408559251171e-05, "loss": 0.3205, "step": 45080 }, { "epoch": 10.79, "learning_rate": 9.596231933744698e-05, "loss": 0.3544, "step": 45090 }, { "epoch": 10.79, "learning_rate": 9.596055271224131e-05, "loss": 0.3555, "step": 45100 }, { "epoch": 10.8, "learning_rate": 9.595878571690898e-05, "loss": 0.3787, "step": 45110 }, { "epoch": 10.8, "learning_rate": 9.59570183514642e-05, "loss": 0.3836, "step": 45120 }, { "epoch": 10.8, "learning_rate": 9.595525061592122e-05, "loss": 0.3273, "step": 45130 }, { "epoch": 10.8, "learning_rate": 9.595348251029425e-05, "loss": 0.3365, "step": 45140 }, { "epoch": 10.8, "learning_rate": 9.595171403459755e-05, "loss": 0.3633, "step": 45150 }, { "epoch": 10.81, "learning_rate": 9.594994518884535e-05, "loss": 0.3879, "step": 45160 }, { "epoch": 10.81, "learning_rate": 9.594817597305188e-05, "loss": 0.3505, "step": 45170 }, { "epoch": 10.81, "learning_rate": 9.594640638723142e-05, "loss": 0.3542, "step": 45180 }, { "epoch": 10.81, "learning_rate": 9.594463643139821e-05, "loss": 0.3742, "step": 45190 }, { "epoch": 10.82, "learning_rate": 9.59428661055665e-05, "loss": 0.377, "step": 45200 }, { "epoch": 10.82, "learning_rate": 9.594109540975054e-05, "loss": 0.3227, "step": 45210 }, { "epoch": 10.82, "learning_rate": 9.59393243439646e-05, "loss": 0.3217, "step": 45220 }, { "epoch": 10.82, "learning_rate": 9.593755290822292e-05, "loss": 0.321, "step": 45230 }, { "epoch": 10.82, "learning_rate": 9.593578110253982e-05, "loss": 0.4187, "step": 45240 }, { "epoch": 10.83, "learning_rate": 9.593400892692951e-05, "loss": 0.3371, "step": 45250 }, { "epoch": 10.83, "learning_rate": 9.59322363814063e-05, "loss": 0.3619, "step": 45260 }, { "epoch": 10.83, "learning_rate": 9.593046346598442e-05, "loss": 0.3484, "step": 45270 }, { "epoch": 10.83, "learning_rate": 9.59286901806782e-05, "loss": 0.3713, "step": 45280 }, { "epoch": 10.84, "learning_rate": 9.59269165255019e-05, "loss": 0.3111, "step": 45290 }, { "epoch": 10.84, "learning_rate": 9.592514250046977e-05, "loss": 0.3501, "step": 45300 }, { "epoch": 10.84, "learning_rate": 9.592336810559617e-05, "loss": 0.3135, "step": 45310 }, { "epoch": 10.84, "learning_rate": 9.592159334089532e-05, "loss": 0.3762, "step": 45320 }, { "epoch": 10.85, "learning_rate": 9.591981820638154e-05, "loss": 0.3677, "step": 45330 }, { "epoch": 10.85, "learning_rate": 9.591804270206913e-05, "loss": 0.3624, "step": 45340 }, { "epoch": 10.85, "learning_rate": 9.591626682797239e-05, "loss": 0.3299, "step": 45350 }, { "epoch": 10.85, "learning_rate": 9.59144905841056e-05, "loss": 0.3337, "step": 45360 }, { "epoch": 10.85, "learning_rate": 9.591271397048309e-05, "loss": 0.3749, "step": 45370 }, { "epoch": 10.86, "learning_rate": 9.591093698711915e-05, "loss": 0.3659, "step": 45380 }, { "epoch": 10.86, "learning_rate": 9.590915963402809e-05, "loss": 0.3131, "step": 45390 }, { "epoch": 10.86, "learning_rate": 9.590738191122423e-05, "loss": 0.3732, "step": 45400 }, { "epoch": 10.86, "learning_rate": 9.59056038187219e-05, "loss": 0.3967, "step": 45410 }, { "epoch": 10.87, "learning_rate": 9.590382535653539e-05, "loss": 0.3946, "step": 45420 }, { "epoch": 10.87, "learning_rate": 9.590204652467905e-05, "loss": 0.3419, "step": 45430 }, { "epoch": 10.87, "learning_rate": 9.59002673231672e-05, "loss": 0.4086, "step": 45440 }, { "epoch": 10.87, "learning_rate": 9.589848775201413e-05, "loss": 0.3299, "step": 45450 }, { "epoch": 10.88, "learning_rate": 9.589670781123422e-05, "loss": 0.3526, "step": 45460 }, { "epoch": 10.88, "learning_rate": 9.589492750084178e-05, "loss": 0.3327, "step": 45470 }, { "epoch": 10.88, "learning_rate": 9.589314682085116e-05, "loss": 0.3116, "step": 45480 }, { "epoch": 10.88, "learning_rate": 9.589136577127669e-05, "loss": 0.3869, "step": 45490 }, { "epoch": 10.88, "learning_rate": 9.588958435213271e-05, "loss": 0.3082, "step": 45500 }, { "epoch": 10.89, "learning_rate": 9.588780256343357e-05, "loss": 0.3485, "step": 45510 }, { "epoch": 10.89, "learning_rate": 9.588602040519363e-05, "loss": 0.2829, "step": 45520 }, { "epoch": 10.89, "learning_rate": 9.588423787742722e-05, "loss": 0.3485, "step": 45530 }, { "epoch": 10.89, "learning_rate": 9.588245498014872e-05, "loss": 0.3779, "step": 45540 }, { "epoch": 10.9, "learning_rate": 9.588067171337248e-05, "loss": 0.3775, "step": 45550 }, { "epoch": 10.9, "learning_rate": 9.587888807711284e-05, "loss": 0.3262, "step": 45560 }, { "epoch": 10.9, "learning_rate": 9.587710407138419e-05, "loss": 0.3389, "step": 45570 }, { "epoch": 10.9, "learning_rate": 9.58753196962009e-05, "loss": 0.3017, "step": 45580 }, { "epoch": 10.9, "learning_rate": 9.587353495157731e-05, "loss": 0.3602, "step": 45590 }, { "epoch": 10.91, "learning_rate": 9.587174983752781e-05, "loss": 0.3917, "step": 45600 }, { "epoch": 10.91, "learning_rate": 9.586996435406676e-05, "loss": 0.3328, "step": 45610 }, { "epoch": 10.91, "learning_rate": 9.586817850120859e-05, "loss": 0.3845, "step": 45620 }, { "epoch": 10.91, "learning_rate": 9.586639227896763e-05, "loss": 0.3958, "step": 45630 }, { "epoch": 10.92, "learning_rate": 9.586460568735826e-05, "loss": 0.3848, "step": 45640 }, { "epoch": 10.92, "learning_rate": 9.586281872639492e-05, "loss": 0.3442, "step": 45650 }, { "epoch": 10.92, "learning_rate": 9.586103139609197e-05, "loss": 0.3424, "step": 45660 }, { "epoch": 10.92, "learning_rate": 9.585924369646377e-05, "loss": 0.3357, "step": 45670 }, { "epoch": 10.93, "learning_rate": 9.585745562752478e-05, "loss": 0.3936, "step": 45680 }, { "epoch": 10.93, "learning_rate": 9.585566718928935e-05, "loss": 0.3359, "step": 45690 }, { "epoch": 10.93, "learning_rate": 9.58538783817719e-05, "loss": 0.3701, "step": 45700 }, { "epoch": 10.93, "learning_rate": 9.585208920498687e-05, "loss": 0.3129, "step": 45710 }, { "epoch": 10.93, "learning_rate": 9.58502996589486e-05, "loss": 0.3269, "step": 45720 }, { "epoch": 10.94, "learning_rate": 9.584850974367154e-05, "loss": 0.4116, "step": 45730 }, { "epoch": 10.94, "learning_rate": 9.584671945917011e-05, "loss": 0.3687, "step": 45740 }, { "epoch": 10.94, "learning_rate": 9.584492880545872e-05, "loss": 0.4041, "step": 45750 }, { "epoch": 10.94, "learning_rate": 9.584313778255179e-05, "loss": 0.3257, "step": 45760 }, { "epoch": 10.95, "learning_rate": 9.584134639046374e-05, "loss": 0.337, "step": 45770 }, { "epoch": 10.95, "learning_rate": 9.583955462920899e-05, "loss": 0.2977, "step": 45780 }, { "epoch": 10.95, "learning_rate": 9.5837762498802e-05, "loss": 0.3915, "step": 45790 }, { "epoch": 11.0, "learning_rate": 9.583596999925717e-05, "loss": 0.3278, "step": 45800 }, { "epoch": 11.0, "learning_rate": 9.583417713058893e-05, "loss": 0.3375, "step": 45810 }, { "epoch": 11.01, "learning_rate": 9.583238389281175e-05, "loss": 0.319, "step": 45820 }, { "epoch": 11.01, "learning_rate": 9.583059028594006e-05, "loss": 0.2831, "step": 45830 }, { "epoch": 11.01, "learning_rate": 9.582879630998829e-05, "loss": 0.3159, "step": 45840 }, { "epoch": 11.01, "learning_rate": 9.582700196497089e-05, "loss": 0.3207, "step": 45850 }, { "epoch": 11.02, "learning_rate": 9.582520725090231e-05, "loss": 0.3847, "step": 45860 }, { "epoch": 11.02, "learning_rate": 9.582341216779704e-05, "loss": 0.2978, "step": 45870 }, { "epoch": 11.02, "learning_rate": 9.582161671566949e-05, "loss": 0.3209, "step": 45880 }, { "epoch": 11.02, "learning_rate": 9.581982089453412e-05, "loss": 0.3257, "step": 45890 }, { "epoch": 11.02, "learning_rate": 9.581802470440541e-05, "loss": 0.3116, "step": 45900 }, { "epoch": 11.03, "learning_rate": 9.581622814529785e-05, "loss": 0.3004, "step": 45910 }, { "epoch": 11.03, "learning_rate": 9.581443121722585e-05, "loss": 0.3396, "step": 45920 }, { "epoch": 11.03, "learning_rate": 9.581263392020392e-05, "loss": 0.3018, "step": 45930 }, { "epoch": 11.03, "learning_rate": 9.581083625424652e-05, "loss": 0.3115, "step": 45940 }, { "epoch": 11.04, "learning_rate": 9.580903821936814e-05, "loss": 0.2813, "step": 45950 }, { "epoch": 11.04, "learning_rate": 9.580723981558324e-05, "loss": 0.3295, "step": 45960 }, { "epoch": 11.04, "learning_rate": 9.580544104290632e-05, "loss": 0.3617, "step": 45970 }, { "epoch": 11.04, "learning_rate": 9.580364190135187e-05, "loss": 0.316, "step": 45980 }, { "epoch": 11.05, "learning_rate": 9.580184239093435e-05, "loss": 0.3116, "step": 45990 }, { "epoch": 11.05, "learning_rate": 9.580004251166827e-05, "loss": 0.3186, "step": 46000 }, { "epoch": 11.05, "learning_rate": 9.579824226356814e-05, "loss": 0.3466, "step": 46010 }, { "epoch": 11.05, "learning_rate": 9.579644164664843e-05, "loss": 0.3197, "step": 46020 }, { "epoch": 11.05, "learning_rate": 9.579464066092366e-05, "loss": 0.3429, "step": 46030 }, { "epoch": 11.06, "learning_rate": 9.579283930640832e-05, "loss": 0.33, "step": 46040 }, { "epoch": 11.06, "learning_rate": 9.579103758311692e-05, "loss": 0.3678, "step": 46050 }, { "epoch": 11.06, "learning_rate": 9.578923549106399e-05, "loss": 0.3386, "step": 46060 }, { "epoch": 11.06, "learning_rate": 9.5787433030264e-05, "loss": 0.3588, "step": 46070 }, { "epoch": 11.07, "learning_rate": 9.578563020073153e-05, "loss": 0.3666, "step": 46080 }, { "epoch": 11.07, "learning_rate": 9.578382700248102e-05, "loss": 0.3026, "step": 46090 }, { "epoch": 11.07, "learning_rate": 9.578202343552705e-05, "loss": 0.2774, "step": 46100 }, { "epoch": 11.07, "learning_rate": 9.578021949988411e-05, "loss": 0.373, "step": 46110 }, { "epoch": 11.07, "learning_rate": 9.577841519556675e-05, "loss": 0.3293, "step": 46120 }, { "epoch": 11.08, "learning_rate": 9.57766105225895e-05, "loss": 0.3261, "step": 46130 }, { "epoch": 11.08, "learning_rate": 9.577480548096687e-05, "loss": 0.3086, "step": 46140 }, { "epoch": 11.08, "learning_rate": 9.577300007071342e-05, "loss": 0.3083, "step": 46150 }, { "epoch": 11.08, "learning_rate": 9.577119429184368e-05, "loss": 0.385, "step": 46160 }, { "epoch": 11.09, "learning_rate": 9.576938814437219e-05, "loss": 0.3125, "step": 46170 }, { "epoch": 11.09, "learning_rate": 9.576758162831351e-05, "loss": 0.317, "step": 46180 }, { "epoch": 11.09, "learning_rate": 9.576577474368217e-05, "loss": 0.3389, "step": 46190 }, { "epoch": 11.09, "learning_rate": 9.576396749049272e-05, "loss": 0.3036, "step": 46200 }, { "epoch": 11.1, "learning_rate": 9.576215986875973e-05, "loss": 0.3122, "step": 46210 }, { "epoch": 11.1, "learning_rate": 9.576035187849774e-05, "loss": 0.3545, "step": 46220 }, { "epoch": 11.1, "learning_rate": 9.575854351972134e-05, "loss": 0.3081, "step": 46230 }, { "epoch": 11.1, "learning_rate": 9.575673479244505e-05, "loss": 0.3354, "step": 46240 }, { "epoch": 11.1, "learning_rate": 9.575492569668347e-05, "loss": 0.3323, "step": 46250 }, { "epoch": 11.11, "learning_rate": 9.575311623245114e-05, "loss": 0.276, "step": 46260 }, { "epoch": 11.11, "learning_rate": 9.575130639976267e-05, "loss": 0.3332, "step": 46270 }, { "epoch": 11.11, "learning_rate": 9.57494961986326e-05, "loss": 0.3033, "step": 46280 }, { "epoch": 11.11, "learning_rate": 9.574768562907552e-05, "loss": 0.318, "step": 46290 }, { "epoch": 11.12, "learning_rate": 9.574587469110602e-05, "loss": 0.3201, "step": 46300 }, { "epoch": 11.12, "learning_rate": 9.574406338473867e-05, "loss": 0.3368, "step": 46310 }, { "epoch": 11.12, "learning_rate": 9.574225170998808e-05, "loss": 0.344, "step": 46320 }, { "epoch": 11.12, "learning_rate": 9.574043966686879e-05, "loss": 0.2978, "step": 46330 }, { "epoch": 11.12, "learning_rate": 9.573862725539544e-05, "loss": 0.3115, "step": 46340 }, { "epoch": 11.13, "learning_rate": 9.573681447558262e-05, "loss": 0.2868, "step": 46350 }, { "epoch": 11.13, "learning_rate": 9.573500132744491e-05, "loss": 0.2999, "step": 46360 }, { "epoch": 11.13, "learning_rate": 9.573318781099691e-05, "loss": 0.3641, "step": 46370 }, { "epoch": 11.13, "learning_rate": 9.573137392625324e-05, "loss": 0.3302, "step": 46380 }, { "epoch": 11.14, "learning_rate": 9.57295596732285e-05, "loss": 0.2741, "step": 46390 }, { "epoch": 11.14, "learning_rate": 9.572774505193731e-05, "loss": 0.3299, "step": 46400 }, { "epoch": 11.14, "learning_rate": 9.572593006239427e-05, "loss": 0.3063, "step": 46410 }, { "epoch": 11.14, "learning_rate": 9.572411470461402e-05, "loss": 0.3435, "step": 46420 }, { "epoch": 11.15, "learning_rate": 9.572229897861114e-05, "loss": 0.3253, "step": 46430 }, { "epoch": 11.15, "learning_rate": 9.572048288440028e-05, "loss": 0.3005, "step": 46440 }, { "epoch": 11.15, "learning_rate": 9.571866642199607e-05, "loss": 0.3351, "step": 46450 }, { "epoch": 11.15, "learning_rate": 9.571684959141312e-05, "loss": 0.3122, "step": 46460 }, { "epoch": 11.15, "learning_rate": 9.571503239266607e-05, "loss": 0.3066, "step": 46470 }, { "epoch": 11.16, "learning_rate": 9.571321482576954e-05, "loss": 0.2948, "step": 46480 }, { "epoch": 11.16, "learning_rate": 9.57113968907382e-05, "loss": 0.3499, "step": 46490 }, { "epoch": 11.16, "learning_rate": 9.570957858758666e-05, "loss": 0.3033, "step": 46500 }, { "epoch": 11.16, "learning_rate": 9.570775991632957e-05, "loss": 0.3309, "step": 46510 }, { "epoch": 11.17, "learning_rate": 9.57059408769816e-05, "loss": 0.346, "step": 46520 }, { "epoch": 11.17, "learning_rate": 9.570412146955734e-05, "loss": 0.3562, "step": 46530 }, { "epoch": 11.17, "learning_rate": 9.570230169407151e-05, "loss": 0.3812, "step": 46540 }, { "epoch": 11.17, "learning_rate": 9.570048155053872e-05, "loss": 0.3356, "step": 46550 }, { "epoch": 11.18, "learning_rate": 9.569866103897365e-05, "loss": 0.3552, "step": 46560 }, { "epoch": 11.18, "learning_rate": 9.569684015939095e-05, "loss": 0.3033, "step": 46570 }, { "epoch": 11.18, "learning_rate": 9.569501891180529e-05, "loss": 0.3206, "step": 46580 }, { "epoch": 11.18, "learning_rate": 9.569319729623133e-05, "loss": 0.3265, "step": 46590 }, { "epoch": 11.18, "learning_rate": 9.569137531268375e-05, "loss": 0.3425, "step": 46600 }, { "epoch": 11.19, "learning_rate": 9.568955296117721e-05, "loss": 0.3258, "step": 46610 }, { "epoch": 11.19, "learning_rate": 9.568773024172639e-05, "loss": 0.2897, "step": 46620 }, { "epoch": 11.19, "learning_rate": 9.568590715434597e-05, "loss": 0.3424, "step": 46630 }, { "epoch": 11.19, "learning_rate": 9.568408369905065e-05, "loss": 0.2897, "step": 46640 }, { "epoch": 11.2, "learning_rate": 9.568225987585508e-05, "loss": 0.3222, "step": 46650 }, { "epoch": 11.2, "learning_rate": 9.568043568477399e-05, "loss": 0.2945, "step": 46660 }, { "epoch": 11.2, "learning_rate": 9.567861112582201e-05, "loss": 0.2969, "step": 46670 }, { "epoch": 11.2, "learning_rate": 9.567678619901389e-05, "loss": 0.356, "step": 46680 }, { "epoch": 11.2, "learning_rate": 9.56749609043643e-05, "loss": 0.3181, "step": 46690 }, { "epoch": 11.21, "learning_rate": 9.567313524188794e-05, "loss": 0.287, "step": 46700 }, { "epoch": 11.21, "learning_rate": 9.567130921159951e-05, "loss": 0.3808, "step": 46710 }, { "epoch": 11.21, "learning_rate": 9.566948281351373e-05, "loss": 0.2661, "step": 46720 }, { "epoch": 11.21, "learning_rate": 9.56676560476453e-05, "loss": 0.3497, "step": 46730 }, { "epoch": 11.22, "learning_rate": 9.566582891400894e-05, "loss": 0.3099, "step": 46740 }, { "epoch": 11.22, "learning_rate": 9.566400141261934e-05, "loss": 0.3548, "step": 46750 }, { "epoch": 11.22, "learning_rate": 9.566217354349124e-05, "loss": 0.3157, "step": 46760 }, { "epoch": 11.22, "learning_rate": 9.566034530663934e-05, "loss": 0.3588, "step": 46770 }, { "epoch": 11.23, "learning_rate": 9.565851670207839e-05, "loss": 0.2331, "step": 46780 }, { "epoch": 11.23, "learning_rate": 9.56566877298231e-05, "loss": 0.2982, "step": 46790 }, { "epoch": 11.23, "learning_rate": 9.56548583898882e-05, "loss": 0.3134, "step": 46800 }, { "epoch": 11.23, "learning_rate": 9.565302868228842e-05, "loss": 0.3162, "step": 46810 }, { "epoch": 11.23, "learning_rate": 9.56511986070385e-05, "loss": 0.3457, "step": 46820 }, { "epoch": 11.24, "learning_rate": 9.564936816415318e-05, "loss": 0.3374, "step": 46830 }, { "epoch": 11.24, "learning_rate": 9.564753735364718e-05, "loss": 0.303, "step": 46840 }, { "epoch": 11.24, "learning_rate": 9.564570617553528e-05, "loss": 0.3082, "step": 46850 }, { "epoch": 11.24, "learning_rate": 9.564387462983217e-05, "loss": 0.3061, "step": 46860 }, { "epoch": 11.25, "learning_rate": 9.564204271655268e-05, "loss": 0.2981, "step": 46870 }, { "epoch": 11.25, "learning_rate": 9.56402104357115e-05, "loss": 0.275, "step": 46880 }, { "epoch": 11.25, "learning_rate": 9.563837778732339e-05, "loss": 0.2879, "step": 46890 }, { "epoch": 11.25, "learning_rate": 9.563654477140314e-05, "loss": 0.3162, "step": 46900 }, { "epoch": 11.26, "learning_rate": 9.563471138796549e-05, "loss": 0.3188, "step": 46910 }, { "epoch": 11.26, "learning_rate": 9.563287763702522e-05, "loss": 0.3062, "step": 46920 }, { "epoch": 11.26, "learning_rate": 9.563104351859706e-05, "loss": 0.2851, "step": 46930 }, { "epoch": 11.26, "learning_rate": 9.562920903269583e-05, "loss": 0.2731, "step": 46940 }, { "epoch": 11.26, "learning_rate": 9.562737417933628e-05, "loss": 0.2805, "step": 46950 }, { "epoch": 11.27, "learning_rate": 9.562553895853316e-05, "loss": 0.3594, "step": 46960 }, { "epoch": 11.27, "learning_rate": 9.562370337030131e-05, "loss": 0.2463, "step": 46970 }, { "epoch": 11.27, "learning_rate": 9.562186741465547e-05, "loss": 0.2948, "step": 46980 }, { "epoch": 11.27, "learning_rate": 9.562003109161042e-05, "loss": 0.3111, "step": 46990 }, { "epoch": 11.28, "learning_rate": 9.561819440118098e-05, "loss": 0.296, "step": 47000 }, { "epoch": 11.28, "learning_rate": 9.56163573433819e-05, "loss": 0.3826, "step": 47010 }, { "epoch": 11.28, "learning_rate": 9.5614519918228e-05, "loss": 0.2554, "step": 47020 }, { "epoch": 11.28, "learning_rate": 9.561268212573409e-05, "loss": 0.3182, "step": 47030 }, { "epoch": 11.28, "learning_rate": 9.561084396591494e-05, "loss": 0.3411, "step": 47040 }, { "epoch": 11.29, "learning_rate": 9.560900543878537e-05, "loss": 0.3483, "step": 47050 }, { "epoch": 11.29, "learning_rate": 9.560716654436019e-05, "loss": 0.3383, "step": 47060 }, { "epoch": 11.29, "learning_rate": 9.560532728265419e-05, "loss": 0.3099, "step": 47070 }, { "epoch": 11.29, "learning_rate": 9.56034876536822e-05, "loss": 0.3283, "step": 47080 }, { "epoch": 11.3, "learning_rate": 9.560164765745903e-05, "loss": 0.2776, "step": 47090 }, { "epoch": 11.3, "learning_rate": 9.559980729399949e-05, "loss": 0.3127, "step": 47100 }, { "epoch": 11.3, "learning_rate": 9.559796656331841e-05, "loss": 0.3025, "step": 47110 }, { "epoch": 11.3, "learning_rate": 9.559612546543059e-05, "loss": 0.2854, "step": 47120 }, { "epoch": 11.31, "learning_rate": 9.559428400035091e-05, "loss": 0.3442, "step": 47130 }, { "epoch": 11.31, "learning_rate": 9.559244216809416e-05, "loss": 0.3629, "step": 47140 }, { "epoch": 11.31, "learning_rate": 9.559059996867516e-05, "loss": 0.248, "step": 47150 }, { "epoch": 11.31, "learning_rate": 9.558875740210877e-05, "loss": 0.3169, "step": 47160 }, { "epoch": 11.31, "learning_rate": 9.558691446840984e-05, "loss": 0.2935, "step": 47170 }, { "epoch": 11.32, "learning_rate": 9.558507116759317e-05, "loss": 0.3089, "step": 47180 }, { "epoch": 11.32, "learning_rate": 9.558322749967364e-05, "loss": 0.3425, "step": 47190 }, { "epoch": 11.32, "learning_rate": 9.558138346466609e-05, "loss": 0.3163, "step": 47200 }, { "epoch": 11.32, "learning_rate": 9.557953906258537e-05, "loss": 0.3083, "step": 47210 }, { "epoch": 11.33, "learning_rate": 9.557769429344631e-05, "loss": 0.3106, "step": 47220 }, { "epoch": 11.33, "learning_rate": 9.55758491572638e-05, "loss": 0.2925, "step": 47230 }, { "epoch": 11.33, "learning_rate": 9.557400365405266e-05, "loss": 0.3393, "step": 47240 }, { "epoch": 11.33, "learning_rate": 9.557215778382782e-05, "loss": 0.3295, "step": 47250 }, { "epoch": 11.34, "learning_rate": 9.557031154660407e-05, "loss": 0.2692, "step": 47260 }, { "epoch": 11.34, "learning_rate": 9.556846494239633e-05, "loss": 0.3393, "step": 47270 }, { "epoch": 11.34, "learning_rate": 9.556661797121943e-05, "loss": 0.3204, "step": 47280 }, { "epoch": 11.34, "learning_rate": 9.556477063308828e-05, "loss": 0.2762, "step": 47290 }, { "epoch": 11.34, "learning_rate": 9.556292292801773e-05, "loss": 0.3109, "step": 47300 }, { "epoch": 11.35, "learning_rate": 9.556107485602268e-05, "loss": 0.2663, "step": 47310 }, { "epoch": 11.35, "learning_rate": 9.5559226417118e-05, "loss": 0.3186, "step": 47320 }, { "epoch": 11.35, "learning_rate": 9.555737761131858e-05, "loss": 0.371, "step": 47330 }, { "epoch": 11.35, "learning_rate": 9.555552843863931e-05, "loss": 0.3224, "step": 47340 }, { "epoch": 11.36, "learning_rate": 9.555367889909507e-05, "loss": 0.3073, "step": 47350 }, { "epoch": 11.36, "learning_rate": 9.555182899270079e-05, "loss": 0.3973, "step": 47360 }, { "epoch": 11.36, "learning_rate": 9.554997871947133e-05, "loss": 0.346, "step": 47370 }, { "epoch": 11.36, "learning_rate": 9.55481280794216e-05, "loss": 0.3643, "step": 47380 }, { "epoch": 11.36, "learning_rate": 9.554627707256649e-05, "loss": 0.3104, "step": 47390 }, { "epoch": 11.37, "learning_rate": 9.554442569892094e-05, "loss": 0.3089, "step": 47400 }, { "epoch": 11.37, "learning_rate": 9.554257395849984e-05, "loss": 0.2954, "step": 47410 }, { "epoch": 11.37, "learning_rate": 9.554072185131811e-05, "loss": 0.2721, "step": 47420 }, { "epoch": 11.37, "learning_rate": 9.553886937739065e-05, "loss": 0.3336, "step": 47430 }, { "epoch": 11.38, "learning_rate": 9.55370165367324e-05, "loss": 0.2578, "step": 47440 }, { "epoch": 11.38, "learning_rate": 9.553516332935826e-05, "loss": 0.2608, "step": 47450 }, { "epoch": 11.38, "learning_rate": 9.553330975528316e-05, "loss": 0.3401, "step": 47460 }, { "epoch": 11.38, "learning_rate": 9.553145581452204e-05, "loss": 0.288, "step": 47470 }, { "epoch": 11.39, "learning_rate": 9.552960150708981e-05, "loss": 0.317, "step": 47480 }, { "epoch": 11.39, "learning_rate": 9.552774683300142e-05, "loss": 0.2925, "step": 47490 }, { "epoch": 11.39, "learning_rate": 9.55258917922718e-05, "loss": 0.271, "step": 47500 }, { "epoch": 11.39, "learning_rate": 9.552403638491589e-05, "loss": 0.2902, "step": 47510 }, { "epoch": 11.39, "learning_rate": 9.552218061094863e-05, "loss": 0.2887, "step": 47520 }, { "epoch": 11.4, "learning_rate": 9.552032447038495e-05, "loss": 0.2739, "step": 47530 }, { "epoch": 11.4, "learning_rate": 9.551846796323982e-05, "loss": 0.2827, "step": 47540 }, { "epoch": 11.4, "learning_rate": 9.551661108952818e-05, "loss": 0.325, "step": 47550 }, { "epoch": 11.4, "learning_rate": 9.5514753849265e-05, "loss": 0.2406, "step": 47560 }, { "epoch": 11.41, "learning_rate": 9.551289624246523e-05, "loss": 0.3261, "step": 47570 }, { "epoch": 11.41, "learning_rate": 9.551103826914381e-05, "loss": 0.2855, "step": 47580 }, { "epoch": 11.41, "learning_rate": 9.55091799293157e-05, "loss": 0.3002, "step": 47590 }, { "epoch": 11.41, "learning_rate": 9.550732122299591e-05, "loss": 0.3032, "step": 47600 }, { "epoch": 11.42, "learning_rate": 9.550546215019935e-05, "loss": 0.3516, "step": 47610 }, { "epoch": 11.42, "learning_rate": 9.550360271094105e-05, "loss": 0.2912, "step": 47620 }, { "epoch": 11.42, "learning_rate": 9.550174290523595e-05, "loss": 0.2819, "step": 47630 }, { "epoch": 11.42, "learning_rate": 9.549988273309902e-05, "loss": 0.2828, "step": 47640 }, { "epoch": 11.42, "learning_rate": 9.549802219454525e-05, "loss": 0.3638, "step": 47650 }, { "epoch": 11.43, "learning_rate": 9.549616128958963e-05, "loss": 0.3216, "step": 47660 }, { "epoch": 11.43, "learning_rate": 9.549430001824715e-05, "loss": 0.3476, "step": 47670 }, { "epoch": 11.43, "learning_rate": 9.549243838053279e-05, "loss": 0.2829, "step": 47680 }, { "epoch": 11.43, "learning_rate": 9.549057637646154e-05, "loss": 0.2985, "step": 47690 }, { "epoch": 11.44, "learning_rate": 9.54887140060484e-05, "loss": 0.2935, "step": 47700 }, { "epoch": 11.44, "learning_rate": 9.548685126930837e-05, "loss": 0.3061, "step": 47710 }, { "epoch": 11.44, "learning_rate": 9.548498816625643e-05, "loss": 0.2622, "step": 47720 }, { "epoch": 11.44, "learning_rate": 9.54831246969076e-05, "loss": 0.3318, "step": 47730 }, { "epoch": 11.44, "learning_rate": 9.54812608612769e-05, "loss": 0.2919, "step": 47740 }, { "epoch": 11.45, "learning_rate": 9.547939665937935e-05, "loss": 0.3319, "step": 47750 }, { "epoch": 11.45, "learning_rate": 9.54775320912299e-05, "loss": 0.2873, "step": 47760 }, { "epoch": 11.45, "learning_rate": 9.547566715684362e-05, "loss": 0.3451, "step": 47770 }, { "epoch": 11.45, "learning_rate": 9.547380185623552e-05, "loss": 0.3032, "step": 47780 }, { "epoch": 11.46, "learning_rate": 9.54719361894206e-05, "loss": 0.315, "step": 47790 }, { "epoch": 11.46, "learning_rate": 9.547007015641391e-05, "loss": 0.2788, "step": 47800 }, { "epoch": 11.46, "learning_rate": 9.546820375723049e-05, "loss": 0.2675, "step": 47810 }, { "epoch": 11.46, "learning_rate": 9.546633699188532e-05, "loss": 0.3305, "step": 47820 }, { "epoch": 11.47, "learning_rate": 9.546446986039345e-05, "loss": 0.3504, "step": 47830 }, { "epoch": 11.47, "learning_rate": 9.546260236276996e-05, "loss": 0.2639, "step": 47840 }, { "epoch": 11.47, "learning_rate": 9.546073449902983e-05, "loss": 0.3569, "step": 47850 }, { "epoch": 11.47, "learning_rate": 9.545886626918816e-05, "loss": 0.3026, "step": 47860 }, { "epoch": 11.47, "learning_rate": 9.545699767325994e-05, "loss": 0.3271, "step": 47870 }, { "epoch": 11.48, "learning_rate": 9.545512871126025e-05, "loss": 0.2921, "step": 47880 }, { "epoch": 11.48, "learning_rate": 9.545325938320413e-05, "loss": 0.3168, "step": 47890 }, { "epoch": 11.48, "learning_rate": 9.545138968910663e-05, "loss": 0.2136, "step": 47900 }, { "epoch": 11.48, "learning_rate": 9.544951962898281e-05, "loss": 0.265, "step": 47910 }, { "epoch": 11.49, "learning_rate": 9.544764920284775e-05, "loss": 0.3138, "step": 47920 }, { "epoch": 11.49, "learning_rate": 9.544577841071649e-05, "loss": 0.2825, "step": 47930 }, { "epoch": 11.49, "learning_rate": 9.54439072526041e-05, "loss": 0.3107, "step": 47940 }, { "epoch": 11.49, "learning_rate": 9.544203572852566e-05, "loss": 0.3029, "step": 47950 }, { "epoch": 11.5, "learning_rate": 9.544016383849623e-05, "loss": 0.3561, "step": 47960 }, { "epoch": 11.5, "learning_rate": 9.543829158253088e-05, "loss": 0.3379, "step": 47970 }, { "epoch": 11.5, "learning_rate": 9.54364189606447e-05, "loss": 0.271, "step": 47980 }, { "epoch": 11.5, "learning_rate": 9.543454597285278e-05, "loss": 0.2922, "step": 47990 }, { "epoch": 11.5, "learning_rate": 9.543267261917016e-05, "loss": 0.2804, "step": 48000 }, { "epoch": 11.51, "learning_rate": 9.543079889961198e-05, "loss": 0.2984, "step": 48010 }, { "epoch": 11.51, "learning_rate": 9.542892481419328e-05, "loss": 0.2978, "step": 48020 }, { "epoch": 11.51, "learning_rate": 9.542705036292918e-05, "loss": 0.2955, "step": 48030 }, { "epoch": 11.51, "learning_rate": 9.542517554583479e-05, "loss": 0.29, "step": 48040 }, { "epoch": 11.52, "learning_rate": 9.542330036292518e-05, "loss": 0.3148, "step": 48050 }, { "epoch": 11.52, "learning_rate": 9.542142481421546e-05, "loss": 0.2743, "step": 48060 }, { "epoch": 11.52, "learning_rate": 9.541954889972074e-05, "loss": 0.2998, "step": 48070 }, { "epoch": 11.52, "learning_rate": 9.541767261945612e-05, "loss": 0.2923, "step": 48080 }, { "epoch": 11.52, "learning_rate": 9.54157959734367e-05, "loss": 0.3302, "step": 48090 }, { "epoch": 11.53, "learning_rate": 9.541391896167762e-05, "loss": 0.3032, "step": 48100 }, { "epoch": 11.53, "learning_rate": 9.541204158419397e-05, "loss": 0.3228, "step": 48110 }, { "epoch": 11.53, "learning_rate": 9.54101638410009e-05, "loss": 0.3517, "step": 48120 }, { "epoch": 11.53, "learning_rate": 9.540828573211349e-05, "loss": 0.2732, "step": 48130 }, { "epoch": 11.54, "learning_rate": 9.54064072575469e-05, "loss": 0.3403, "step": 48140 }, { "epoch": 11.54, "learning_rate": 9.540452841731623e-05, "loss": 0.3424, "step": 48150 }, { "epoch": 11.54, "learning_rate": 9.540264921143664e-05, "loss": 0.4295, "step": 48160 }, { "epoch": 11.54, "learning_rate": 9.540076963992323e-05, "loss": 0.3727, "step": 48170 }, { "epoch": 11.55, "learning_rate": 9.539888970279116e-05, "loss": 0.3586, "step": 48180 }, { "epoch": 11.55, "learning_rate": 9.539700940005558e-05, "loss": 0.3973, "step": 48190 }, { "epoch": 11.55, "learning_rate": 9.53951287317316e-05, "loss": 0.3587, "step": 48200 }, { "epoch": 11.55, "learning_rate": 9.539324769783437e-05, "loss": 0.4085, "step": 48210 }, { "epoch": 11.55, "learning_rate": 9.539136629837908e-05, "loss": 0.4134, "step": 48220 }, { "epoch": 11.56, "learning_rate": 9.538948453338083e-05, "loss": 0.3565, "step": 48230 }, { "epoch": 11.56, "learning_rate": 9.538760240285479e-05, "loss": 0.3331, "step": 48240 }, { "epoch": 11.56, "learning_rate": 9.538571990681614e-05, "loss": 0.3582, "step": 48250 }, { "epoch": 11.56, "learning_rate": 9.538383704528e-05, "loss": 0.4161, "step": 48260 }, { "epoch": 11.57, "learning_rate": 9.538195381826157e-05, "loss": 0.3295, "step": 48270 }, { "epoch": 11.57, "learning_rate": 9.5380070225776e-05, "loss": 0.3479, "step": 48280 }, { "epoch": 11.57, "learning_rate": 9.537818626783845e-05, "loss": 0.3164, "step": 48290 }, { "epoch": 11.57, "learning_rate": 9.537630194446412e-05, "loss": 0.3165, "step": 48300 }, { "epoch": 11.58, "learning_rate": 9.537441725566815e-05, "loss": 0.3789, "step": 48310 }, { "epoch": 11.58, "learning_rate": 9.537253220146574e-05, "loss": 0.3411, "step": 48320 }, { "epoch": 11.58, "learning_rate": 9.537064678187205e-05, "loss": 0.3425, "step": 48330 }, { "epoch": 11.58, "learning_rate": 9.536876099690228e-05, "loss": 0.3189, "step": 48340 }, { "epoch": 11.58, "learning_rate": 9.536687484657163e-05, "loss": 0.3458, "step": 48350 }, { "epoch": 11.59, "learning_rate": 9.536498833089526e-05, "loss": 0.3501, "step": 48360 }, { "epoch": 11.59, "learning_rate": 9.53631014498884e-05, "loss": 0.3318, "step": 48370 }, { "epoch": 11.59, "learning_rate": 9.536121420356619e-05, "loss": 0.36, "step": 48380 }, { "epoch": 11.59, "learning_rate": 9.535932659194388e-05, "loss": 0.3325, "step": 48390 }, { "epoch": 11.6, "learning_rate": 9.535743861503664e-05, "loss": 0.3154, "step": 48400 }, { "epoch": 11.6, "learning_rate": 9.535555027285969e-05, "loss": 0.3347, "step": 48410 }, { "epoch": 11.6, "learning_rate": 9.535366156542823e-05, "loss": 0.4086, "step": 48420 }, { "epoch": 11.6, "learning_rate": 9.535177249275747e-05, "loss": 0.388, "step": 48430 }, { "epoch": 11.6, "learning_rate": 9.534988305486263e-05, "loss": 0.3846, "step": 48440 }, { "epoch": 11.61, "learning_rate": 9.534799325175891e-05, "loss": 0.4067, "step": 48450 }, { "epoch": 11.61, "learning_rate": 9.534610308346156e-05, "loss": 0.3369, "step": 48460 }, { "epoch": 11.61, "learning_rate": 9.534421254998576e-05, "loss": 0.3223, "step": 48470 }, { "epoch": 11.61, "learning_rate": 9.534232165134678e-05, "loss": 0.3829, "step": 48480 }, { "epoch": 11.62, "learning_rate": 9.53404303875598e-05, "loss": 0.4313, "step": 48490 }, { "epoch": 11.62, "learning_rate": 9.533853875864008e-05, "loss": 0.3476, "step": 48500 }, { "epoch": 11.62, "learning_rate": 9.533664676460285e-05, "loss": 0.3675, "step": 48510 }, { "epoch": 11.62, "learning_rate": 9.533475440546336e-05, "loss": 0.3531, "step": 48520 }, { "epoch": 11.63, "learning_rate": 9.533286168123681e-05, "loss": 0.3142, "step": 48530 }, { "epoch": 11.63, "learning_rate": 9.533096859193849e-05, "loss": 0.3125, "step": 48540 }, { "epoch": 11.63, "learning_rate": 9.53290751375836e-05, "loss": 0.3455, "step": 48550 }, { "epoch": 11.63, "learning_rate": 9.532718131818741e-05, "loss": 0.3138, "step": 48560 }, { "epoch": 11.63, "learning_rate": 9.532528713376518e-05, "loss": 0.3343, "step": 48570 }, { "epoch": 11.64, "learning_rate": 9.532339258433216e-05, "loss": 0.3859, "step": 48580 }, { "epoch": 11.64, "learning_rate": 9.53214976699036e-05, "loss": 0.3498, "step": 48590 }, { "epoch": 11.64, "learning_rate": 9.531960239049476e-05, "loss": 0.3383, "step": 48600 }, { "epoch": 11.64, "learning_rate": 9.531770674612089e-05, "loss": 0.31, "step": 48610 }, { "epoch": 11.65, "learning_rate": 9.53158107367973e-05, "loss": 0.3286, "step": 48620 }, { "epoch": 11.65, "learning_rate": 9.53139143625392e-05, "loss": 0.3528, "step": 48630 }, { "epoch": 11.65, "learning_rate": 9.53120176233619e-05, "loss": 0.3044, "step": 48640 }, { "epoch": 11.65, "learning_rate": 9.531012051928068e-05, "loss": 0.3472, "step": 48650 }, { "epoch": 11.66, "learning_rate": 9.53082230503108e-05, "loss": 0.3577, "step": 48660 }, { "epoch": 11.66, "learning_rate": 9.530632521646754e-05, "loss": 0.3153, "step": 48670 }, { "epoch": 11.66, "learning_rate": 9.530442701776618e-05, "loss": 0.3358, "step": 48680 }, { "epoch": 11.66, "learning_rate": 9.530252845422202e-05, "loss": 0.307, "step": 48690 }, { "epoch": 11.66, "learning_rate": 9.530062952585037e-05, "loss": 0.3619, "step": 48700 }, { "epoch": 11.67, "learning_rate": 9.529873023266647e-05, "loss": 0.3699, "step": 48710 }, { "epoch": 11.67, "learning_rate": 9.529683057468564e-05, "loss": 0.3197, "step": 48720 }, { "epoch": 11.67, "learning_rate": 9.52949305519232e-05, "loss": 0.3086, "step": 48730 }, { "epoch": 11.67, "learning_rate": 9.52930301643944e-05, "loss": 0.3043, "step": 48740 }, { "epoch": 11.68, "learning_rate": 9.52911294121146e-05, "loss": 0.3761, "step": 48750 }, { "epoch": 11.68, "learning_rate": 9.528922829509908e-05, "loss": 0.345, "step": 48760 }, { "epoch": 11.68, "learning_rate": 9.528732681336314e-05, "loss": 0.3479, "step": 48770 }, { "epoch": 11.68, "learning_rate": 9.52854249669221e-05, "loss": 0.3351, "step": 48780 }, { "epoch": 11.68, "learning_rate": 9.52835227557913e-05, "loss": 0.3111, "step": 48790 }, { "epoch": 11.69, "learning_rate": 9.528162017998603e-05, "loss": 0.3391, "step": 48800 }, { "epoch": 11.69, "learning_rate": 9.527971723952162e-05, "loss": 0.3398, "step": 48810 }, { "epoch": 11.69, "learning_rate": 9.52778139344134e-05, "loss": 0.3238, "step": 48820 }, { "epoch": 11.69, "learning_rate": 9.527591026467668e-05, "loss": 0.299, "step": 48830 }, { "epoch": 11.7, "learning_rate": 9.527400623032682e-05, "loss": 0.3165, "step": 48840 }, { "epoch": 11.7, "learning_rate": 9.527210183137914e-05, "loss": 0.3257, "step": 48850 }, { "epoch": 11.7, "learning_rate": 9.527019706784897e-05, "loss": 0.3051, "step": 48860 }, { "epoch": 11.7, "learning_rate": 9.526829193975164e-05, "loss": 0.3089, "step": 48870 }, { "epoch": 11.71, "learning_rate": 9.52663864471025e-05, "loss": 0.3391, "step": 48880 }, { "epoch": 11.71, "learning_rate": 9.526448058991693e-05, "loss": 0.3103, "step": 48890 }, { "epoch": 11.71, "learning_rate": 9.526257436821022e-05, "loss": 0.2697, "step": 48900 }, { "epoch": 11.71, "learning_rate": 9.526066778199778e-05, "loss": 0.3827, "step": 48910 }, { "epoch": 11.71, "learning_rate": 9.525876083129491e-05, "loss": 0.3464, "step": 48920 }, { "epoch": 11.72, "learning_rate": 9.525685351611699e-05, "loss": 0.3937, "step": 48930 }, { "epoch": 11.72, "learning_rate": 9.52549458364794e-05, "loss": 0.3152, "step": 48940 }, { "epoch": 11.72, "learning_rate": 9.525303779239747e-05, "loss": 0.3361, "step": 48950 }, { "epoch": 11.72, "learning_rate": 9.525112938388658e-05, "loss": 0.2498, "step": 48960 }, { "epoch": 11.73, "learning_rate": 9.52492206109621e-05, "loss": 0.3483, "step": 48970 }, { "epoch": 11.73, "learning_rate": 9.524731147363939e-05, "loss": 0.2834, "step": 48980 }, { "epoch": 11.73, "learning_rate": 9.524540197193385e-05, "loss": 0.3293, "step": 48990 }, { "epoch": 11.73, "learning_rate": 9.524349210586083e-05, "loss": 0.3233, "step": 49000 }, { "epoch": 11.74, "learning_rate": 9.524158187543572e-05, "loss": 0.3818, "step": 49010 }, { "epoch": 11.74, "learning_rate": 9.523967128067391e-05, "loss": 0.2731, "step": 49020 }, { "epoch": 11.74, "learning_rate": 9.523776032159079e-05, "loss": 0.3526, "step": 49030 }, { "epoch": 11.74, "learning_rate": 9.523584899820173e-05, "loss": 0.3682, "step": 49040 }, { "epoch": 11.74, "learning_rate": 9.523393731052213e-05, "loss": 0.3321, "step": 49050 }, { "epoch": 11.75, "learning_rate": 9.52320252585674e-05, "loss": 0.3547, "step": 49060 }, { "epoch": 11.75, "learning_rate": 9.523011284235292e-05, "loss": 0.3213, "step": 49070 }, { "epoch": 11.75, "learning_rate": 9.522820006189408e-05, "loss": 0.3371, "step": 49080 }, { "epoch": 11.75, "learning_rate": 9.522628691720632e-05, "loss": 0.3514, "step": 49090 }, { "epoch": 11.76, "learning_rate": 9.522437340830503e-05, "loss": 0.3028, "step": 49100 }, { "epoch": 11.76, "learning_rate": 9.522245953520561e-05, "loss": 0.3109, "step": 49110 }, { "epoch": 11.76, "learning_rate": 9.522054529792347e-05, "loss": 0.3142, "step": 49120 }, { "epoch": 11.76, "learning_rate": 9.521863069647406e-05, "loss": 0.2808, "step": 49130 }, { "epoch": 11.76, "learning_rate": 9.521671573087277e-05, "loss": 0.2942, "step": 49140 }, { "epoch": 11.77, "learning_rate": 9.5214800401135e-05, "loss": 0.3293, "step": 49150 }, { "epoch": 11.77, "learning_rate": 9.521288470727623e-05, "loss": 0.3459, "step": 49160 }, { "epoch": 11.77, "learning_rate": 9.521096864931183e-05, "loss": 0.3932, "step": 49170 }, { "epoch": 11.77, "learning_rate": 9.520905222725728e-05, "loss": 0.3098, "step": 49180 }, { "epoch": 11.78, "learning_rate": 9.520713544112798e-05, "loss": 0.2924, "step": 49190 }, { "epoch": 11.78, "learning_rate": 9.520521829093938e-05, "loss": 0.292, "step": 49200 }, { "epoch": 11.78, "learning_rate": 9.520330077670692e-05, "loss": 0.367, "step": 49210 }, { "epoch": 11.78, "learning_rate": 9.520138289844603e-05, "loss": 0.3115, "step": 49220 }, { "epoch": 11.79, "learning_rate": 9.519946465617218e-05, "loss": 0.3718, "step": 49230 }, { "epoch": 11.79, "learning_rate": 9.519754604990079e-05, "loss": 0.3522, "step": 49240 }, { "epoch": 11.79, "learning_rate": 9.519562707964731e-05, "loss": 0.3313, "step": 49250 }, { "epoch": 11.79, "learning_rate": 9.519370774542721e-05, "loss": 0.3384, "step": 49260 }, { "epoch": 11.79, "learning_rate": 9.519178804725595e-05, "loss": 0.3794, "step": 49270 }, { "epoch": 11.8, "learning_rate": 9.518986798514898e-05, "loss": 0.2722, "step": 49280 }, { "epoch": 11.8, "learning_rate": 9.518794755912177e-05, "loss": 0.2948, "step": 49290 }, { "epoch": 11.8, "learning_rate": 9.518602676918978e-05, "loss": 0.3076, "step": 49300 }, { "epoch": 11.8, "learning_rate": 9.518410561536846e-05, "loss": 0.3164, "step": 49310 }, { "epoch": 11.81, "learning_rate": 9.518218409767332e-05, "loss": 0.2722, "step": 49320 }, { "epoch": 11.81, "learning_rate": 9.51802622161198e-05, "loss": 0.3143, "step": 49330 }, { "epoch": 11.81, "learning_rate": 9.517833997072338e-05, "loss": 0.3347, "step": 49340 }, { "epoch": 11.81, "learning_rate": 9.517641736149958e-05, "loss": 0.3407, "step": 49350 }, { "epoch": 11.82, "learning_rate": 9.517449438846384e-05, "loss": 0.3102, "step": 49360 }, { "epoch": 11.82, "learning_rate": 9.517257105163167e-05, "loss": 0.3308, "step": 49370 }, { "epoch": 11.82, "learning_rate": 9.517064735101853e-05, "loss": 0.3495, "step": 49380 }, { "epoch": 11.82, "learning_rate": 9.516872328663994e-05, "loss": 0.3047, "step": 49390 }, { "epoch": 11.82, "learning_rate": 9.516679885851138e-05, "loss": 0.2753, "step": 49400 }, { "epoch": 11.83, "learning_rate": 9.516487406664836e-05, "loss": 0.308, "step": 49410 }, { "epoch": 11.83, "learning_rate": 9.516294891106638e-05, "loss": 0.341, "step": 49420 }, { "epoch": 11.83, "learning_rate": 9.516102339178092e-05, "loss": 0.288, "step": 49430 }, { "epoch": 11.83, "learning_rate": 9.515909750880752e-05, "loss": 0.3299, "step": 49440 }, { "epoch": 11.84, "learning_rate": 9.515717126216166e-05, "loss": 0.3157, "step": 49450 }, { "epoch": 11.84, "learning_rate": 9.515524465185888e-05, "loss": 0.3511, "step": 49460 }, { "epoch": 11.84, "learning_rate": 9.515331767791467e-05, "loss": 0.3896, "step": 49470 }, { "epoch": 11.84, "learning_rate": 9.515139034034456e-05, "loss": 0.3578, "step": 49480 }, { "epoch": 11.84, "learning_rate": 9.514946263916407e-05, "loss": 0.3163, "step": 49490 }, { "epoch": 11.85, "learning_rate": 9.514753457438873e-05, "loss": 0.2663, "step": 49500 }, { "epoch": 11.85, "learning_rate": 9.514560614603405e-05, "loss": 0.2988, "step": 49510 }, { "epoch": 11.85, "learning_rate": 9.514367735411558e-05, "loss": 0.305, "step": 49520 }, { "epoch": 11.85, "learning_rate": 9.514174819864885e-05, "loss": 0.3331, "step": 49530 }, { "epoch": 11.86, "learning_rate": 9.513981867964937e-05, "loss": 0.3916, "step": 49540 }, { "epoch": 11.86, "learning_rate": 9.513788879713271e-05, "loss": 0.3317, "step": 49550 }, { "epoch": 11.86, "learning_rate": 9.513595855111441e-05, "loss": 0.3071, "step": 49560 }, { "epoch": 11.86, "learning_rate": 9.513402794160999e-05, "loss": 0.3877, "step": 49570 }, { "epoch": 11.87, "learning_rate": 9.513209696863501e-05, "loss": 0.3193, "step": 49580 }, { "epoch": 11.87, "learning_rate": 9.513016563220503e-05, "loss": 0.3417, "step": 49590 }, { "epoch": 11.87, "learning_rate": 9.512823393233558e-05, "loss": 0.2672, "step": 49600 }, { "epoch": 11.87, "learning_rate": 9.512630186904225e-05, "loss": 0.3495, "step": 49610 }, { "epoch": 11.87, "learning_rate": 9.512436944234058e-05, "loss": 0.3731, "step": 49620 }, { "epoch": 11.88, "learning_rate": 9.512243665224614e-05, "loss": 0.2645, "step": 49630 }, { "epoch": 11.88, "learning_rate": 9.512050349877448e-05, "loss": 0.3032, "step": 49640 }, { "epoch": 11.88, "learning_rate": 9.511856998194117e-05, "loss": 0.3133, "step": 49650 }, { "epoch": 11.88, "learning_rate": 9.511663610176177e-05, "loss": 0.335, "step": 49660 }, { "epoch": 11.89, "learning_rate": 9.511470185825191e-05, "loss": 0.2679, "step": 49670 }, { "epoch": 11.89, "learning_rate": 9.51127672514271e-05, "loss": 0.3193, "step": 49680 }, { "epoch": 11.89, "learning_rate": 9.511083228130295e-05, "loss": 0.2904, "step": 49690 }, { "epoch": 11.89, "learning_rate": 9.510889694789505e-05, "loss": 0.2855, "step": 49700 }, { "epoch": 11.9, "learning_rate": 9.510696125121898e-05, "loss": 0.2777, "step": 49710 }, { "epoch": 11.9, "learning_rate": 9.51050251912903e-05, "loss": 0.3417, "step": 49720 }, { "epoch": 11.9, "learning_rate": 9.510308876812465e-05, "loss": 0.324, "step": 49730 }, { "epoch": 11.9, "learning_rate": 9.510115198173759e-05, "loss": 0.2732, "step": 49740 }, { "epoch": 11.9, "learning_rate": 9.509921483214473e-05, "loss": 0.3014, "step": 49750 }, { "epoch": 11.91, "learning_rate": 9.509727731936165e-05, "loss": 0.3142, "step": 49760 }, { "epoch": 11.91, "learning_rate": 9.509533944340399e-05, "loss": 0.3486, "step": 49770 }, { "epoch": 11.91, "learning_rate": 9.509340120428733e-05, "loss": 0.287, "step": 49780 }, { "epoch": 11.91, "learning_rate": 9.509146260202728e-05, "loss": 0.3311, "step": 49790 }, { "epoch": 11.92, "learning_rate": 9.508952363663946e-05, "loss": 0.2991, "step": 49800 }, { "epoch": 11.92, "learning_rate": 9.508758430813946e-05, "loss": 0.3201, "step": 49810 }, { "epoch": 11.92, "learning_rate": 9.508564461654294e-05, "loss": 0.2752, "step": 49820 }, { "epoch": 11.92, "learning_rate": 9.50837045618655e-05, "loss": 0.338, "step": 49830 }, { "epoch": 11.92, "learning_rate": 9.508176414412277e-05, "loss": 0.3573, "step": 49840 }, { "epoch": 11.93, "learning_rate": 9.507982336333036e-05, "loss": 0.278, "step": 49850 }, { "epoch": 11.93, "learning_rate": 9.50778822195039e-05, "loss": 0.3574, "step": 49860 }, { "epoch": 11.93, "learning_rate": 9.507594071265904e-05, "loss": 0.2798, "step": 49870 }, { "epoch": 11.93, "learning_rate": 9.50739988428114e-05, "loss": 0.2543, "step": 49880 }, { "epoch": 11.94, "learning_rate": 9.507205660997665e-05, "loss": 0.3321, "step": 49890 }, { "epoch": 11.94, "learning_rate": 9.507011401417037e-05, "loss": 0.3213, "step": 49900 }, { "epoch": 11.94, "learning_rate": 9.506817105540826e-05, "loss": 0.3055, "step": 49910 }, { "epoch": 11.94, "learning_rate": 9.506622773370594e-05, "loss": 0.2811, "step": 49920 }, { "epoch": 11.95, "learning_rate": 9.506428404907908e-05, "loss": 0.3227, "step": 49930 }, { "epoch": 11.95, "learning_rate": 9.506234000154331e-05, "loss": 0.2896, "step": 49940 }, { "epoch": 11.95, "learning_rate": 9.506039559111428e-05, "loss": 0.2733, "step": 49950 }, { "epoch": 12.0, "learning_rate": 9.505845081780768e-05, "loss": 0.3069, "step": 49960 }, { "epoch": 12.0, "learning_rate": 9.505650568163915e-05, "loss": 0.2902, "step": 49970 }, { "epoch": 12.01, "learning_rate": 9.505456018262436e-05, "loss": 0.2853, "step": 49980 }, { "epoch": 12.01, "learning_rate": 9.505261432077896e-05, "loss": 0.3281, "step": 49990 }, { "epoch": 12.01, "learning_rate": 9.505066809611866e-05, "loss": 0.2627, "step": 50000 }, { "epoch": 12.01, "learning_rate": 9.504872150865911e-05, "loss": 0.298, "step": 50010 }, { "epoch": 12.01, "learning_rate": 9.504677455841598e-05, "loss": 0.273, "step": 50020 }, { "epoch": 12.02, "learning_rate": 9.504482724540496e-05, "loss": 0.2889, "step": 50030 }, { "epoch": 12.02, "learning_rate": 9.50428795696417e-05, "loss": 0.2668, "step": 50040 }, { "epoch": 12.02, "learning_rate": 9.504093153114195e-05, "loss": 0.271, "step": 50050 }, { "epoch": 12.02, "learning_rate": 9.503898312992134e-05, "loss": 0.3164, "step": 50060 }, { "epoch": 12.03, "learning_rate": 9.503703436599558e-05, "loss": 0.2928, "step": 50070 }, { "epoch": 12.03, "learning_rate": 9.503508523938039e-05, "loss": 0.2424, "step": 50080 }, { "epoch": 12.03, "learning_rate": 9.503313575009141e-05, "loss": 0.2634, "step": 50090 }, { "epoch": 12.03, "learning_rate": 9.503118589814438e-05, "loss": 0.2886, "step": 50100 }, { "epoch": 12.04, "learning_rate": 9.502923568355499e-05, "loss": 0.2719, "step": 50110 }, { "epoch": 12.04, "learning_rate": 9.502728510633897e-05, "loss": 0.243, "step": 50120 }, { "epoch": 12.04, "learning_rate": 9.502533416651199e-05, "loss": 0.3259, "step": 50130 }, { "epoch": 12.04, "learning_rate": 9.502338286408976e-05, "loss": 0.2471, "step": 50140 }, { "epoch": 12.04, "learning_rate": 9.502143119908804e-05, "loss": 0.2783, "step": 50150 }, { "epoch": 12.05, "learning_rate": 9.50194791715225e-05, "loss": 0.2489, "step": 50160 }, { "epoch": 12.05, "learning_rate": 9.50175267814089e-05, "loss": 0.3223, "step": 50170 }, { "epoch": 12.05, "learning_rate": 9.501557402876292e-05, "loss": 0.2955, "step": 50180 }, { "epoch": 12.05, "learning_rate": 9.501362091360031e-05, "loss": 0.3286, "step": 50190 }, { "epoch": 12.06, "learning_rate": 9.501166743593682e-05, "loss": 0.2956, "step": 50200 }, { "epoch": 12.06, "learning_rate": 9.500971359578813e-05, "loss": 0.2194, "step": 50210 }, { "epoch": 12.06, "learning_rate": 9.500775939317002e-05, "loss": 0.272, "step": 50220 }, { "epoch": 12.06, "learning_rate": 9.50058048280982e-05, "loss": 0.2853, "step": 50230 }, { "epoch": 12.06, "learning_rate": 9.500384990058841e-05, "loss": 0.2587, "step": 50240 }, { "epoch": 12.07, "learning_rate": 9.500189461065642e-05, "loss": 0.2682, "step": 50250 }, { "epoch": 12.07, "learning_rate": 9.499993895831796e-05, "loss": 0.2725, "step": 50260 }, { "epoch": 12.07, "learning_rate": 9.499798294358879e-05, "loss": 0.243, "step": 50270 }, { "epoch": 12.07, "learning_rate": 9.499602656648463e-05, "loss": 0.3024, "step": 50280 }, { "epoch": 12.08, "learning_rate": 9.499406982702126e-05, "loss": 0.3345, "step": 50290 }, { "epoch": 12.08, "learning_rate": 9.499211272521445e-05, "loss": 0.295, "step": 50300 }, { "epoch": 12.08, "learning_rate": 9.499015526107992e-05, "loss": 0.3165, "step": 50310 }, { "epoch": 12.08, "learning_rate": 9.498819743463347e-05, "loss": 0.297, "step": 50320 }, { "epoch": 12.09, "learning_rate": 9.498623924589085e-05, "loss": 0.2353, "step": 50330 }, { "epoch": 12.09, "learning_rate": 9.498428069486785e-05, "loss": 0.2899, "step": 50340 }, { "epoch": 12.09, "learning_rate": 9.49823217815802e-05, "loss": 0.2644, "step": 50350 }, { "epoch": 12.09, "learning_rate": 9.498036250604373e-05, "loss": 0.2336, "step": 50360 }, { "epoch": 12.09, "learning_rate": 9.497840286827418e-05, "loss": 0.2887, "step": 50370 }, { "epoch": 12.1, "learning_rate": 9.497644286828734e-05, "loss": 0.2546, "step": 50380 }, { "epoch": 12.1, "learning_rate": 9.497448250609899e-05, "loss": 0.2459, "step": 50390 }, { "epoch": 12.1, "learning_rate": 9.497252178172493e-05, "loss": 0.3013, "step": 50400 }, { "epoch": 12.1, "learning_rate": 9.497056069518095e-05, "loss": 0.3167, "step": 50410 }, { "epoch": 12.11, "learning_rate": 9.496859924648283e-05, "loss": 0.2503, "step": 50420 }, { "epoch": 12.11, "learning_rate": 9.496663743564638e-05, "loss": 0.3085, "step": 50430 }, { "epoch": 12.11, "learning_rate": 9.496467526268738e-05, "loss": 0.337, "step": 50440 }, { "epoch": 12.11, "learning_rate": 9.496271272762165e-05, "loss": 0.3181, "step": 50450 }, { "epoch": 12.12, "learning_rate": 9.496074983046497e-05, "loss": 0.2668, "step": 50460 }, { "epoch": 12.12, "learning_rate": 9.495878657123318e-05, "loss": 0.316, "step": 50470 }, { "epoch": 12.12, "learning_rate": 9.495682294994208e-05, "loss": 0.263, "step": 50480 }, { "epoch": 12.12, "learning_rate": 9.495485896660748e-05, "loss": 0.2883, "step": 50490 }, { "epoch": 12.12, "learning_rate": 9.495289462124518e-05, "loss": 0.3161, "step": 50500 }, { "epoch": 12.13, "learning_rate": 9.4950929913871e-05, "loss": 0.2805, "step": 50510 }, { "epoch": 12.13, "learning_rate": 9.49489648445008e-05, "loss": 0.2932, "step": 50520 }, { "epoch": 12.13, "learning_rate": 9.494699941315038e-05, "loss": 0.292, "step": 50530 }, { "epoch": 12.13, "learning_rate": 9.494503361983556e-05, "loss": 0.2671, "step": 50540 }, { "epoch": 12.14, "learning_rate": 9.494306746457218e-05, "loss": 0.3335, "step": 50550 }, { "epoch": 12.14, "learning_rate": 9.494110094737607e-05, "loss": 0.2851, "step": 50560 }, { "epoch": 12.14, "learning_rate": 9.493913406826308e-05, "loss": 0.314, "step": 50570 }, { "epoch": 12.14, "learning_rate": 9.493716682724903e-05, "loss": 0.3057, "step": 50580 }, { "epoch": 12.14, "learning_rate": 9.493519922434977e-05, "loss": 0.2424, "step": 50590 }, { "epoch": 12.15, "learning_rate": 9.493323125958115e-05, "loss": 0.3401, "step": 50600 }, { "epoch": 12.15, "learning_rate": 9.493126293295902e-05, "loss": 0.3033, "step": 50610 }, { "epoch": 12.15, "learning_rate": 9.492929424449923e-05, "loss": 0.2633, "step": 50620 }, { "epoch": 12.15, "learning_rate": 9.492732519421762e-05, "loss": 0.2976, "step": 50630 }, { "epoch": 12.16, "learning_rate": 9.492535578213007e-05, "loss": 0.287, "step": 50640 }, { "epoch": 12.16, "learning_rate": 9.49233860082524e-05, "loss": 0.2735, "step": 50650 }, { "epoch": 12.16, "learning_rate": 9.492141587260052e-05, "loss": 0.2475, "step": 50660 }, { "epoch": 12.16, "learning_rate": 9.491944537519029e-05, "loss": 0.2924, "step": 50670 }, { "epoch": 12.17, "learning_rate": 9.491747451603755e-05, "loss": 0.2822, "step": 50680 }, { "epoch": 12.17, "learning_rate": 9.491550329515819e-05, "loss": 0.3143, "step": 50690 }, { "epoch": 12.17, "learning_rate": 9.491353171256808e-05, "loss": 0.3225, "step": 50700 }, { "epoch": 12.17, "learning_rate": 9.491155976828309e-05, "loss": 0.3138, "step": 50710 }, { "epoch": 12.17, "learning_rate": 9.49095874623191e-05, "loss": 0.2743, "step": 50720 }, { "epoch": 12.18, "learning_rate": 9.490761479469203e-05, "loss": 0.2847, "step": 50730 }, { "epoch": 12.18, "learning_rate": 9.490564176541772e-05, "loss": 0.2643, "step": 50740 }, { "epoch": 12.18, "learning_rate": 9.490366837451209e-05, "loss": 0.3218, "step": 50750 }, { "epoch": 12.18, "learning_rate": 9.490169462199101e-05, "loss": 0.3059, "step": 50760 }, { "epoch": 12.19, "learning_rate": 9.48997205078704e-05, "loss": 0.3059, "step": 50770 }, { "epoch": 12.19, "learning_rate": 9.489774603216611e-05, "loss": 0.2752, "step": 50780 }, { "epoch": 12.19, "learning_rate": 9.48957711948941e-05, "loss": 0.299, "step": 50790 }, { "epoch": 12.19, "learning_rate": 9.489379599607022e-05, "loss": 0.2543, "step": 50800 }, { "epoch": 12.2, "learning_rate": 9.489182043571043e-05, "loss": 0.3163, "step": 50810 }, { "epoch": 12.2, "learning_rate": 9.48898445138306e-05, "loss": 0.2966, "step": 50820 }, { "epoch": 12.2, "learning_rate": 9.488786823044666e-05, "loss": 0.2842, "step": 50830 }, { "epoch": 12.2, "learning_rate": 9.488589158557453e-05, "loss": 0.2827, "step": 50840 }, { "epoch": 12.2, "learning_rate": 9.488391457923009e-05, "loss": 0.2797, "step": 50850 }, { "epoch": 12.21, "learning_rate": 9.48819372114293e-05, "loss": 0.3159, "step": 50860 }, { "epoch": 12.21, "learning_rate": 9.487995948218809e-05, "loss": 0.2658, "step": 50870 }, { "epoch": 12.21, "learning_rate": 9.487798139152235e-05, "loss": 0.2377, "step": 50880 }, { "epoch": 12.21, "learning_rate": 9.487600293944803e-05, "loss": 0.282, "step": 50890 }, { "epoch": 12.22, "learning_rate": 9.487402412598108e-05, "loss": 0.2848, "step": 50900 }, { "epoch": 12.22, "learning_rate": 9.487204495113741e-05, "loss": 0.3121, "step": 50910 }, { "epoch": 12.22, "learning_rate": 9.487006541493296e-05, "loss": 0.3005, "step": 50920 }, { "epoch": 12.22, "learning_rate": 9.486808551738369e-05, "loss": 0.2717, "step": 50930 }, { "epoch": 12.22, "learning_rate": 9.486610525850552e-05, "loss": 0.3057, "step": 50940 }, { "epoch": 12.23, "learning_rate": 9.486412463831442e-05, "loss": 0.2332, "step": 50950 }, { "epoch": 12.23, "learning_rate": 9.486214365682633e-05, "loss": 0.2778, "step": 50960 }, { "epoch": 12.23, "learning_rate": 9.486016231405721e-05, "loss": 0.3278, "step": 50970 }, { "epoch": 12.23, "learning_rate": 9.4858180610023e-05, "loss": 0.2869, "step": 50980 }, { "epoch": 12.24, "learning_rate": 9.485619854473966e-05, "loss": 0.2198, "step": 50990 }, { "epoch": 12.24, "learning_rate": 9.485421611822318e-05, "loss": 0.2846, "step": 51000 }, { "epoch": 12.24, "learning_rate": 9.48522333304895e-05, "loss": 0.2567, "step": 51010 }, { "epoch": 12.24, "learning_rate": 9.485025018155458e-05, "loss": 0.276, "step": 51020 }, { "epoch": 12.25, "learning_rate": 9.48482666714344e-05, "loss": 0.3216, "step": 51030 }, { "epoch": 12.25, "learning_rate": 9.484628280014496e-05, "loss": 0.2753, "step": 51040 }, { "epoch": 12.25, "learning_rate": 9.484429856770221e-05, "loss": 0.3031, "step": 51050 }, { "epoch": 12.25, "learning_rate": 9.484231397412212e-05, "loss": 0.274, "step": 51060 }, { "epoch": 12.25, "learning_rate": 9.484032901942068e-05, "loss": 0.3296, "step": 51070 }, { "epoch": 12.26, "learning_rate": 9.483834370361388e-05, "loss": 0.3053, "step": 51080 }, { "epoch": 12.26, "learning_rate": 9.483635802671773e-05, "loss": 0.289, "step": 51090 }, { "epoch": 12.26, "learning_rate": 9.483437198874819e-05, "loss": 0.211, "step": 51100 }, { "epoch": 12.26, "learning_rate": 9.483238558972125e-05, "loss": 0.2673, "step": 51110 }, { "epoch": 12.27, "learning_rate": 9.483039882965292e-05, "loss": 0.2578, "step": 51120 }, { "epoch": 12.27, "learning_rate": 9.48284117085592e-05, "loss": 0.2888, "step": 51130 }, { "epoch": 12.27, "learning_rate": 9.482642422645612e-05, "loss": 0.2714, "step": 51140 }, { "epoch": 12.27, "learning_rate": 9.482443638335962e-05, "loss": 0.2567, "step": 51150 }, { "epoch": 12.28, "learning_rate": 9.482244817928577e-05, "loss": 0.2678, "step": 51160 }, { "epoch": 12.28, "learning_rate": 9.482045961425054e-05, "loss": 0.2764, "step": 51170 }, { "epoch": 12.28, "learning_rate": 9.481847068826996e-05, "loss": 0.3044, "step": 51180 }, { "epoch": 12.28, "learning_rate": 9.481648140136005e-05, "loss": 0.2516, "step": 51190 }, { "epoch": 12.28, "learning_rate": 9.481449175353685e-05, "loss": 0.2931, "step": 51200 }, { "epoch": 12.29, "learning_rate": 9.481250174481634e-05, "loss": 0.2502, "step": 51210 }, { "epoch": 12.29, "learning_rate": 9.481051137521458e-05, "loss": 0.2515, "step": 51220 }, { "epoch": 12.29, "learning_rate": 9.480852064474756e-05, "loss": 0.2318, "step": 51230 }, { "epoch": 12.29, "learning_rate": 9.480652955343137e-05, "loss": 0.3212, "step": 51240 }, { "epoch": 12.3, "learning_rate": 9.480453810128198e-05, "loss": 0.2354, "step": 51250 }, { "epoch": 12.3, "learning_rate": 9.480254628831549e-05, "loss": 0.2146, "step": 51260 }, { "epoch": 12.3, "learning_rate": 9.48005541145479e-05, "loss": 0.3216, "step": 51270 }, { "epoch": 12.3, "learning_rate": 9.479856157999524e-05, "loss": 0.2854, "step": 51280 }, { "epoch": 12.3, "learning_rate": 9.479656868467359e-05, "loss": 0.2283, "step": 51290 }, { "epoch": 12.31, "learning_rate": 9.4794575428599e-05, "loss": 0.3255, "step": 51300 }, { "epoch": 12.31, "learning_rate": 9.479258181178749e-05, "loss": 0.2819, "step": 51310 }, { "epoch": 12.31, "learning_rate": 9.479058783425517e-05, "loss": 0.3011, "step": 51320 }, { "epoch": 12.31, "learning_rate": 9.478859349601802e-05, "loss": 0.2564, "step": 51330 }, { "epoch": 12.32, "learning_rate": 9.478659879709218e-05, "loss": 0.2476, "step": 51340 }, { "epoch": 12.32, "learning_rate": 9.478460373749365e-05, "loss": 0.3112, "step": 51350 }, { "epoch": 12.32, "learning_rate": 9.478260831723853e-05, "loss": 0.3433, "step": 51360 }, { "epoch": 12.32, "learning_rate": 9.47806125363429e-05, "loss": 0.2725, "step": 51370 }, { "epoch": 12.33, "learning_rate": 9.477861639482279e-05, "loss": 0.3155, "step": 51380 }, { "epoch": 12.33, "learning_rate": 9.47766198926943e-05, "loss": 0.2657, "step": 51390 }, { "epoch": 12.33, "learning_rate": 9.477462302997353e-05, "loss": 0.2147, "step": 51400 }, { "epoch": 12.33, "learning_rate": 9.477262580667652e-05, "loss": 0.2314, "step": 51410 }, { "epoch": 12.33, "learning_rate": 9.477062822281939e-05, "loss": 0.2548, "step": 51420 }, { "epoch": 12.34, "learning_rate": 9.47686302784182e-05, "loss": 0.2893, "step": 51430 }, { "epoch": 12.34, "learning_rate": 9.476663197348905e-05, "loss": 0.229, "step": 51440 }, { "epoch": 12.34, "learning_rate": 9.476463330804803e-05, "loss": 0.2879, "step": 51450 }, { "epoch": 12.34, "learning_rate": 9.476263428211123e-05, "loss": 0.3313, "step": 51460 }, { "epoch": 12.35, "learning_rate": 9.476063489569478e-05, "loss": 0.2729, "step": 51470 }, { "epoch": 12.35, "learning_rate": 9.475863514881473e-05, "loss": 0.2912, "step": 51480 }, { "epoch": 12.35, "learning_rate": 9.475663504148724e-05, "loss": 0.2462, "step": 51490 }, { "epoch": 12.35, "learning_rate": 9.475463457372837e-05, "loss": 0.283, "step": 51500 }, { "epoch": 12.36, "learning_rate": 9.475263374555425e-05, "loss": 0.2448, "step": 51510 }, { "epoch": 12.36, "learning_rate": 9.4750632556981e-05, "loss": 0.273, "step": 51520 }, { "epoch": 12.36, "learning_rate": 9.474863100802473e-05, "loss": 0.2873, "step": 51530 }, { "epoch": 12.36, "learning_rate": 9.474662909870156e-05, "loss": 0.2808, "step": 51540 }, { "epoch": 12.36, "learning_rate": 9.474462682902758e-05, "loss": 0.2689, "step": 51550 }, { "epoch": 12.37, "learning_rate": 9.474262419901897e-05, "loss": 0.2831, "step": 51560 }, { "epoch": 12.37, "learning_rate": 9.474062120869183e-05, "loss": 0.2418, "step": 51570 }, { "epoch": 12.37, "learning_rate": 9.473861785806228e-05, "loss": 0.2359, "step": 51580 }, { "epoch": 12.37, "learning_rate": 9.473661414714645e-05, "loss": 0.2704, "step": 51590 }, { "epoch": 12.38, "learning_rate": 9.473461007596051e-05, "loss": 0.2694, "step": 51600 }, { "epoch": 12.38, "learning_rate": 9.473260564452058e-05, "loss": 0.2782, "step": 51610 }, { "epoch": 12.38, "learning_rate": 9.47306008528428e-05, "loss": 0.2482, "step": 51620 }, { "epoch": 12.38, "learning_rate": 9.47285957009433e-05, "loss": 0.2522, "step": 51630 }, { "epoch": 12.38, "learning_rate": 9.472659018883827e-05, "loss": 0.2939, "step": 51640 }, { "epoch": 12.39, "learning_rate": 9.472458431654381e-05, "loss": 0.2906, "step": 51650 }, { "epoch": 12.39, "learning_rate": 9.472257808407612e-05, "loss": 0.2871, "step": 51660 }, { "epoch": 12.39, "learning_rate": 9.472057149145132e-05, "loss": 0.2938, "step": 51670 }, { "epoch": 12.39, "learning_rate": 9.471856453868558e-05, "loss": 0.2445, "step": 51680 }, { "epoch": 12.4, "learning_rate": 9.471655722579507e-05, "loss": 0.2728, "step": 51690 }, { "epoch": 12.4, "learning_rate": 9.471454955279594e-05, "loss": 0.2664, "step": 51700 }, { "epoch": 12.4, "learning_rate": 9.47125415197044e-05, "loss": 0.2353, "step": 51710 }, { "epoch": 12.4, "learning_rate": 9.471053312653658e-05, "loss": 0.2493, "step": 51720 }, { "epoch": 12.41, "learning_rate": 9.470852437330865e-05, "loss": 0.2766, "step": 51730 }, { "epoch": 12.41, "learning_rate": 9.47065152600368e-05, "loss": 0.2914, "step": 51740 }, { "epoch": 12.41, "learning_rate": 9.470450578673722e-05, "loss": 0.2654, "step": 51750 }, { "epoch": 12.41, "learning_rate": 9.470249595342609e-05, "loss": 0.2366, "step": 51760 }, { "epoch": 12.41, "learning_rate": 9.470048576011957e-05, "loss": 0.2919, "step": 51770 }, { "epoch": 12.42, "learning_rate": 9.469847520683388e-05, "loss": 0.2817, "step": 51780 }, { "epoch": 12.42, "learning_rate": 9.46964642935852e-05, "loss": 0.2875, "step": 51790 }, { "epoch": 12.42, "learning_rate": 9.46944530203897e-05, "loss": 0.2638, "step": 51800 }, { "epoch": 12.42, "learning_rate": 9.469244138726363e-05, "loss": 0.2372, "step": 51810 }, { "epoch": 12.43, "learning_rate": 9.469042939422314e-05, "loss": 0.3339, "step": 51820 }, { "epoch": 12.43, "learning_rate": 9.468841704128447e-05, "loss": 0.2606, "step": 51830 }, { "epoch": 12.43, "learning_rate": 9.468640432846378e-05, "loss": 0.2466, "step": 51840 }, { "epoch": 12.43, "learning_rate": 9.468439125577733e-05, "loss": 0.2925, "step": 51850 }, { "epoch": 12.44, "learning_rate": 9.468237782324129e-05, "loss": 0.2974, "step": 51860 }, { "epoch": 12.44, "learning_rate": 9.468036403087192e-05, "loss": 0.2694, "step": 51870 }, { "epoch": 12.44, "learning_rate": 9.46783498786854e-05, "loss": 0.2489, "step": 51880 }, { "epoch": 12.44, "learning_rate": 9.467633536669794e-05, "loss": 0.2101, "step": 51890 }, { "epoch": 12.44, "learning_rate": 9.46743204949258e-05, "loss": 0.2502, "step": 51900 }, { "epoch": 12.45, "learning_rate": 9.467230526338517e-05, "loss": 0.2817, "step": 51910 }, { "epoch": 12.45, "learning_rate": 9.467028967209233e-05, "loss": 0.2688, "step": 51920 }, { "epoch": 12.45, "learning_rate": 9.466827372106346e-05, "loss": 0.2607, "step": 51930 }, { "epoch": 12.45, "learning_rate": 9.466625741031483e-05, "loss": 0.2912, "step": 51940 }, { "epoch": 12.46, "learning_rate": 9.466424073986264e-05, "loss": 0.2712, "step": 51950 }, { "epoch": 12.46, "learning_rate": 9.466222370972317e-05, "loss": 0.3358, "step": 51960 }, { "epoch": 12.46, "learning_rate": 9.466020631991263e-05, "loss": 0.2797, "step": 51970 }, { "epoch": 12.46, "learning_rate": 9.46581885704473e-05, "loss": 0.2618, "step": 51980 }, { "epoch": 12.46, "learning_rate": 9.46561704613434e-05, "loss": 0.2587, "step": 51990 }, { "epoch": 12.47, "learning_rate": 9.465415199261721e-05, "loss": 0.2537, "step": 52000 }, { "epoch": 12.47, "learning_rate": 9.465213316428497e-05, "loss": 0.2729, "step": 52010 }, { "epoch": 12.47, "learning_rate": 9.465011397636292e-05, "loss": 0.2662, "step": 52020 }, { "epoch": 12.47, "learning_rate": 9.464809442886735e-05, "loss": 0.2883, "step": 52030 }, { "epoch": 12.48, "learning_rate": 9.46460745218145e-05, "loss": 0.2902, "step": 52040 }, { "epoch": 12.48, "learning_rate": 9.464405425522065e-05, "loss": 0.2374, "step": 52050 }, { "epoch": 12.48, "learning_rate": 9.464203362910207e-05, "loss": 0.2873, "step": 52060 }, { "epoch": 12.48, "learning_rate": 9.464001264347504e-05, "loss": 0.2213, "step": 52070 }, { "epoch": 12.49, "learning_rate": 9.463799129835582e-05, "loss": 0.2534, "step": 52080 }, { "epoch": 12.49, "learning_rate": 9.463596959376069e-05, "loss": 0.243, "step": 52090 }, { "epoch": 12.49, "learning_rate": 9.463394752970593e-05, "loss": 0.2643, "step": 52100 }, { "epoch": 12.49, "learning_rate": 9.463192510620782e-05, "loss": 0.274, "step": 52110 }, { "epoch": 12.49, "learning_rate": 9.462990232328268e-05, "loss": 0.2253, "step": 52120 }, { "epoch": 12.5, "learning_rate": 9.462787918094675e-05, "loss": 0.237, "step": 52130 }, { "epoch": 12.5, "learning_rate": 9.462585567921638e-05, "loss": 0.2319, "step": 52140 }, { "epoch": 12.5, "learning_rate": 9.462383181810781e-05, "loss": 0.2124, "step": 52150 }, { "epoch": 12.5, "learning_rate": 9.462180759763737e-05, "loss": 0.3086, "step": 52160 }, { "epoch": 12.51, "learning_rate": 9.461978301782134e-05, "loss": 0.2625, "step": 52170 }, { "epoch": 12.51, "learning_rate": 9.461775807867604e-05, "loss": 0.2681, "step": 52180 }, { "epoch": 12.51, "learning_rate": 9.461573278021779e-05, "loss": 0.2912, "step": 52190 }, { "epoch": 12.51, "learning_rate": 9.461370712246286e-05, "loss": 0.2834, "step": 52200 }, { "epoch": 12.52, "learning_rate": 9.461168110542762e-05, "loss": 0.2523, "step": 52210 }, { "epoch": 12.52, "learning_rate": 9.460965472912832e-05, "loss": 0.2201, "step": 52220 }, { "epoch": 12.52, "learning_rate": 9.460762799358134e-05, "loss": 0.231, "step": 52230 }, { "epoch": 12.52, "learning_rate": 9.460560089880294e-05, "loss": 0.2375, "step": 52240 }, { "epoch": 12.52, "learning_rate": 9.460357344480952e-05, "loss": 0.2848, "step": 52250 }, { "epoch": 12.53, "learning_rate": 9.460154563161733e-05, "loss": 0.2855, "step": 52260 }, { "epoch": 12.53, "learning_rate": 9.459951745924277e-05, "loss": 0.2469, "step": 52270 }, { "epoch": 12.53, "learning_rate": 9.45974889277021e-05, "loss": 0.3385, "step": 52280 }, { "epoch": 12.53, "learning_rate": 9.459546003701172e-05, "loss": 0.346, "step": 52290 }, { "epoch": 12.54, "learning_rate": 9.459343078718792e-05, "loss": 0.2856, "step": 52300 }, { "epoch": 12.54, "learning_rate": 9.459140117824709e-05, "loss": 0.3434, "step": 52310 }, { "epoch": 12.54, "learning_rate": 9.458937121020554e-05, "loss": 0.2887, "step": 52320 }, { "epoch": 12.54, "learning_rate": 9.458734088307964e-05, "loss": 0.3636, "step": 52330 }, { "epoch": 12.54, "learning_rate": 9.45853101968857e-05, "loss": 0.3474, "step": 52340 }, { "epoch": 12.55, "learning_rate": 9.458327915164013e-05, "loss": 0.3339, "step": 52350 }, { "epoch": 12.55, "learning_rate": 9.458124774735923e-05, "loss": 0.3074, "step": 52360 }, { "epoch": 12.55, "learning_rate": 9.457921598405942e-05, "loss": 0.3053, "step": 52370 }, { "epoch": 12.55, "learning_rate": 9.4577183861757e-05, "loss": 0.3851, "step": 52380 }, { "epoch": 12.56, "learning_rate": 9.457515138046838e-05, "loss": 0.4063, "step": 52390 }, { "epoch": 12.56, "learning_rate": 9.457311854020992e-05, "loss": 0.3285, "step": 52400 }, { "epoch": 12.56, "learning_rate": 9.457108534099797e-05, "loss": 0.3204, "step": 52410 }, { "epoch": 12.56, "learning_rate": 9.45690517828489e-05, "loss": 0.3004, "step": 52420 }, { "epoch": 12.57, "learning_rate": 9.456701786577913e-05, "loss": 0.3245, "step": 52430 }, { "epoch": 12.57, "learning_rate": 9.4564983589805e-05, "loss": 0.3368, "step": 52440 }, { "epoch": 12.57, "learning_rate": 9.456294895494291e-05, "loss": 0.3071, "step": 52450 }, { "epoch": 12.57, "learning_rate": 9.456091396120923e-05, "loss": 0.3317, "step": 52460 }, { "epoch": 12.57, "learning_rate": 9.455887860862036e-05, "loss": 0.336, "step": 52470 }, { "epoch": 12.58, "learning_rate": 9.45568428971927e-05, "loss": 0.3192, "step": 52480 }, { "epoch": 12.58, "learning_rate": 9.455480682694262e-05, "loss": 0.2818, "step": 52490 }, { "epoch": 12.58, "learning_rate": 9.455277039788654e-05, "loss": 0.2865, "step": 52500 }, { "epoch": 12.58, "learning_rate": 9.455073361004086e-05, "loss": 0.3707, "step": 52510 }, { "epoch": 12.59, "learning_rate": 9.454869646342194e-05, "loss": 0.2767, "step": 52520 }, { "epoch": 12.59, "learning_rate": 9.454665895804624e-05, "loss": 0.3408, "step": 52530 }, { "epoch": 12.59, "learning_rate": 9.454462109393015e-05, "loss": 0.3025, "step": 52540 }, { "epoch": 12.59, "learning_rate": 9.454258287109006e-05, "loss": 0.3234, "step": 52550 }, { "epoch": 12.6, "learning_rate": 9.45405442895424e-05, "loss": 0.3482, "step": 52560 }, { "epoch": 12.6, "learning_rate": 9.453850534930359e-05, "loss": 0.3552, "step": 52570 }, { "epoch": 12.6, "learning_rate": 9.453646605039004e-05, "loss": 0.3638, "step": 52580 }, { "epoch": 12.6, "learning_rate": 9.45344263928182e-05, "loss": 0.2862, "step": 52590 }, { "epoch": 12.6, "learning_rate": 9.453238637660447e-05, "loss": 0.2886, "step": 52600 }, { "epoch": 12.61, "learning_rate": 9.453034600176528e-05, "loss": 0.3602, "step": 52610 }, { "epoch": 12.61, "learning_rate": 9.452830526831707e-05, "loss": 0.3244, "step": 52620 }, { "epoch": 12.61, "learning_rate": 9.452626417627626e-05, "loss": 0.3333, "step": 52630 }, { "epoch": 12.61, "learning_rate": 9.45242227256593e-05, "loss": 0.2557, "step": 52640 }, { "epoch": 12.62, "learning_rate": 9.452218091648264e-05, "loss": 0.3071, "step": 52650 }, { "epoch": 12.62, "learning_rate": 9.45201387487627e-05, "loss": 0.3178, "step": 52660 }, { "epoch": 12.62, "learning_rate": 9.451809622251595e-05, "loss": 0.3172, "step": 52670 }, { "epoch": 12.62, "learning_rate": 9.451605333775881e-05, "loss": 0.2603, "step": 52680 }, { "epoch": 12.62, "learning_rate": 9.451401009450776e-05, "loss": 0.3664, "step": 52690 }, { "epoch": 12.63, "learning_rate": 9.451196649277923e-05, "loss": 0.3012, "step": 52700 }, { "epoch": 12.63, "learning_rate": 9.450992253258968e-05, "loss": 0.3021, "step": 52710 }, { "epoch": 12.63, "learning_rate": 9.450787821395559e-05, "loss": 0.3173, "step": 52720 }, { "epoch": 12.63, "learning_rate": 9.450583353689342e-05, "loss": 0.3414, "step": 52730 }, { "epoch": 12.64, "learning_rate": 9.450378850141961e-05, "loss": 0.2682, "step": 52740 }, { "epoch": 12.64, "learning_rate": 9.450174310755067e-05, "loss": 0.3274, "step": 52750 }, { "epoch": 12.64, "learning_rate": 9.449969735530302e-05, "loss": 0.2931, "step": 52760 }, { "epoch": 12.64, "learning_rate": 9.449765124469318e-05, "loss": 0.2946, "step": 52770 }, { "epoch": 12.65, "learning_rate": 9.449560477573762e-05, "loss": 0.3347, "step": 52780 }, { "epoch": 12.65, "learning_rate": 9.44935579484528e-05, "loss": 0.3275, "step": 52790 }, { "epoch": 12.65, "learning_rate": 9.449151076285521e-05, "loss": 0.2587, "step": 52800 }, { "epoch": 12.65, "learning_rate": 9.448946321896135e-05, "loss": 0.3325, "step": 52810 }, { "epoch": 12.65, "learning_rate": 9.448741531678771e-05, "loss": 0.3021, "step": 52820 }, { "epoch": 12.66, "learning_rate": 9.448536705635076e-05, "loss": 0.339, "step": 52830 }, { "epoch": 12.66, "learning_rate": 9.4483318437667e-05, "loss": 0.3323, "step": 52840 }, { "epoch": 12.66, "learning_rate": 9.448126946075295e-05, "loss": 0.3681, "step": 52850 }, { "epoch": 12.66, "learning_rate": 9.447922012562509e-05, "loss": 0.2545, "step": 52860 }, { "epoch": 12.67, "learning_rate": 9.447717043229993e-05, "loss": 0.357, "step": 52870 }, { "epoch": 12.67, "learning_rate": 9.447512038079398e-05, "loss": 0.2886, "step": 52880 }, { "epoch": 12.67, "learning_rate": 9.447306997112373e-05, "loss": 0.2943, "step": 52890 }, { "epoch": 12.67, "learning_rate": 9.447101920330572e-05, "loss": 0.2983, "step": 52900 }, { "epoch": 12.68, "learning_rate": 9.446896807735645e-05, "loss": 0.2941, "step": 52910 }, { "epoch": 12.68, "learning_rate": 9.446691659329245e-05, "loss": 0.2991, "step": 52920 }, { "epoch": 12.68, "learning_rate": 9.446486475113024e-05, "loss": 0.3081, "step": 52930 }, { "epoch": 12.68, "learning_rate": 9.446281255088631e-05, "loss": 0.2768, "step": 52940 }, { "epoch": 12.68, "learning_rate": 9.446075999257723e-05, "loss": 0.3546, "step": 52950 }, { "epoch": 12.69, "learning_rate": 9.445870707621948e-05, "loss": 0.306, "step": 52960 }, { "epoch": 12.69, "learning_rate": 9.445665380182967e-05, "loss": 0.278, "step": 52970 }, { "epoch": 12.69, "learning_rate": 9.445460016942425e-05, "loss": 0.382, "step": 52980 }, { "epoch": 12.69, "learning_rate": 9.445254617901981e-05, "loss": 0.3519, "step": 52990 }, { "epoch": 12.7, "learning_rate": 9.44504918306329e-05, "loss": 0.2841, "step": 53000 }, { "epoch": 12.7, "learning_rate": 9.444843712428002e-05, "loss": 0.3394, "step": 53010 }, { "epoch": 12.7, "learning_rate": 9.444638205997773e-05, "loss": 0.31, "step": 53020 }, { "epoch": 12.7, "learning_rate": 9.44443266377426e-05, "loss": 0.3348, "step": 53030 }, { "epoch": 12.7, "learning_rate": 9.444227085759119e-05, "loss": 0.2849, "step": 53040 }, { "epoch": 12.71, "learning_rate": 9.444021471954004e-05, "loss": 0.2696, "step": 53050 }, { "epoch": 12.71, "learning_rate": 9.443815822360566e-05, "loss": 0.3313, "step": 53060 }, { "epoch": 12.71, "learning_rate": 9.44361013698047e-05, "loss": 0.328, "step": 53070 }, { "epoch": 12.71, "learning_rate": 9.443404415815367e-05, "loss": 0.3143, "step": 53080 }, { "epoch": 12.72, "learning_rate": 9.443198658866914e-05, "loss": 0.307, "step": 53090 }, { "epoch": 12.72, "learning_rate": 9.442992866136768e-05, "loss": 0.3116, "step": 53100 }, { "epoch": 12.72, "learning_rate": 9.442787037626589e-05, "loss": 0.3624, "step": 53110 }, { "epoch": 12.72, "learning_rate": 9.442581173338032e-05, "loss": 0.349, "step": 53120 }, { "epoch": 12.73, "learning_rate": 9.442375273272755e-05, "loss": 0.2391, "step": 53130 }, { "epoch": 12.73, "learning_rate": 9.442169337432417e-05, "loss": 0.278, "step": 53140 }, { "epoch": 12.73, "learning_rate": 9.441963365818676e-05, "loss": 0.2912, "step": 53150 }, { "epoch": 12.73, "learning_rate": 9.441757358433191e-05, "loss": 0.2929, "step": 53160 }, { "epoch": 12.73, "learning_rate": 9.441551315277621e-05, "loss": 0.3032, "step": 53170 }, { "epoch": 12.74, "learning_rate": 9.441345236353624e-05, "loss": 0.2677, "step": 53180 }, { "epoch": 12.74, "learning_rate": 9.44113912166286e-05, "loss": 0.2961, "step": 53190 }, { "epoch": 12.74, "learning_rate": 9.440932971206991e-05, "loss": 0.3271, "step": 53200 }, { "epoch": 12.74, "learning_rate": 9.440726784987677e-05, "loss": 0.3176, "step": 53210 }, { "epoch": 12.75, "learning_rate": 9.440520563006574e-05, "loss": 0.3459, "step": 53220 }, { "epoch": 12.75, "learning_rate": 9.440314305265347e-05, "loss": 0.2391, "step": 53230 }, { "epoch": 12.75, "learning_rate": 9.440108011765657e-05, "loss": 0.2754, "step": 53240 }, { "epoch": 12.75, "learning_rate": 9.439901682509163e-05, "loss": 0.3663, "step": 53250 }, { "epoch": 12.76, "learning_rate": 9.439695317497529e-05, "loss": 0.3028, "step": 53260 }, { "epoch": 12.76, "learning_rate": 9.439488916732415e-05, "loss": 0.3047, "step": 53270 }, { "epoch": 12.76, "learning_rate": 9.439282480215484e-05, "loss": 0.2951, "step": 53280 }, { "epoch": 12.76, "learning_rate": 9.439076007948398e-05, "loss": 0.2544, "step": 53290 }, { "epoch": 12.76, "learning_rate": 9.43886949993282e-05, "loss": 0.3099, "step": 53300 }, { "epoch": 12.77, "learning_rate": 9.438662956170412e-05, "loss": 0.2833, "step": 53310 }, { "epoch": 12.77, "learning_rate": 9.438456376662842e-05, "loss": 0.2947, "step": 53320 }, { "epoch": 12.77, "learning_rate": 9.438249761411766e-05, "loss": 0.2703, "step": 53330 }, { "epoch": 12.77, "learning_rate": 9.438043110418854e-05, "loss": 0.233, "step": 53340 }, { "epoch": 12.78, "learning_rate": 9.437836423685766e-05, "loss": 0.2937, "step": 53350 }, { "epoch": 12.78, "learning_rate": 9.437629701214171e-05, "loss": 0.3008, "step": 53360 }, { "epoch": 12.78, "learning_rate": 9.437422943005731e-05, "loss": 0.326, "step": 53370 }, { "epoch": 12.78, "learning_rate": 9.437216149062111e-05, "loss": 0.281, "step": 53380 }, { "epoch": 12.78, "learning_rate": 9.437009319384978e-05, "loss": 0.2867, "step": 53390 }, { "epoch": 12.79, "learning_rate": 9.436802453975994e-05, "loss": 0.2652, "step": 53400 }, { "epoch": 12.79, "learning_rate": 9.436595552836828e-05, "loss": 0.2873, "step": 53410 }, { "epoch": 12.79, "learning_rate": 9.436388615969148e-05, "loss": 0.3075, "step": 53420 }, { "epoch": 12.79, "learning_rate": 9.436181643374616e-05, "loss": 0.2607, "step": 53430 }, { "epoch": 12.8, "learning_rate": 9.4359746350549e-05, "loss": 0.2978, "step": 53440 }, { "epoch": 12.8, "learning_rate": 9.435767591011669e-05, "loss": 0.3303, "step": 53450 }, { "epoch": 12.8, "learning_rate": 9.435560511246589e-05, "loss": 0.2504, "step": 53460 }, { "epoch": 12.8, "learning_rate": 9.435353395761326e-05, "loss": 0.309, "step": 53470 }, { "epoch": 12.81, "learning_rate": 9.435146244557552e-05, "loss": 0.2327, "step": 53480 }, { "epoch": 12.81, "learning_rate": 9.434939057636933e-05, "loss": 0.2465, "step": 53490 }, { "epoch": 12.81, "learning_rate": 9.434731835001136e-05, "loss": 0.2713, "step": 53500 }, { "epoch": 12.81, "learning_rate": 9.434524576651833e-05, "loss": 0.241, "step": 53510 }, { "epoch": 12.81, "learning_rate": 9.43431728259069e-05, "loss": 0.2975, "step": 53520 }, { "epoch": 12.82, "learning_rate": 9.434109952819379e-05, "loss": 0.2659, "step": 53530 }, { "epoch": 12.82, "learning_rate": 9.433902587339568e-05, "loss": 0.2801, "step": 53540 }, { "epoch": 12.82, "learning_rate": 9.433695186152925e-05, "loss": 0.2953, "step": 53550 }, { "epoch": 12.82, "learning_rate": 9.433487749261126e-05, "loss": 0.2864, "step": 53560 }, { "epoch": 12.83, "learning_rate": 9.433280276665835e-05, "loss": 0.2519, "step": 53570 }, { "epoch": 12.83, "learning_rate": 9.433072768368729e-05, "loss": 0.3264, "step": 53580 }, { "epoch": 12.83, "learning_rate": 9.432865224371475e-05, "loss": 0.2398, "step": 53590 }, { "epoch": 12.83, "learning_rate": 9.432657644675744e-05, "loss": 0.2817, "step": 53600 }, { "epoch": 12.84, "learning_rate": 9.432450029283209e-05, "loss": 0.3006, "step": 53610 }, { "epoch": 12.84, "learning_rate": 9.432242378195543e-05, "loss": 0.2468, "step": 53620 }, { "epoch": 12.84, "learning_rate": 9.432034691414417e-05, "loss": 0.3073, "step": 53630 }, { "epoch": 12.84, "learning_rate": 9.431826968941503e-05, "loss": 0.2948, "step": 53640 }, { "epoch": 12.84, "learning_rate": 9.431619210778477e-05, "loss": 0.2876, "step": 53650 }, { "epoch": 12.85, "learning_rate": 9.431411416927007e-05, "loss": 0.3052, "step": 53660 }, { "epoch": 12.85, "learning_rate": 9.431203587388771e-05, "loss": 0.289, "step": 53670 }, { "epoch": 12.85, "learning_rate": 9.430995722165439e-05, "loss": 0.2958, "step": 53680 }, { "epoch": 12.85, "learning_rate": 9.430787821258687e-05, "loss": 0.2901, "step": 53690 }, { "epoch": 12.86, "learning_rate": 9.43057988467019e-05, "loss": 0.2954, "step": 53700 }, { "epoch": 12.86, "learning_rate": 9.430371912401622e-05, "loss": 0.2704, "step": 53710 }, { "epoch": 12.86, "learning_rate": 9.430163904454656e-05, "loss": 0.2206, "step": 53720 }, { "epoch": 12.86, "learning_rate": 9.429955860830967e-05, "loss": 0.2402, "step": 53730 }, { "epoch": 12.86, "learning_rate": 9.429747781532234e-05, "loss": 0.2576, "step": 53740 }, { "epoch": 12.87, "learning_rate": 9.429539666560132e-05, "loss": 0.2365, "step": 53750 }, { "epoch": 12.87, "learning_rate": 9.429331515916333e-05, "loss": 0.3326, "step": 53760 }, { "epoch": 12.87, "learning_rate": 9.429123329602517e-05, "loss": 0.2517, "step": 53770 }, { "epoch": 12.87, "learning_rate": 9.428915107620358e-05, "loss": 0.3082, "step": 53780 }, { "epoch": 12.88, "learning_rate": 9.428706849971535e-05, "loss": 0.3267, "step": 53790 }, { "epoch": 12.88, "learning_rate": 9.428498556657725e-05, "loss": 0.2533, "step": 53800 }, { "epoch": 12.88, "learning_rate": 9.428290227680603e-05, "loss": 0.2599, "step": 53810 }, { "epoch": 12.88, "learning_rate": 9.428081863041851e-05, "loss": 0.2883, "step": 53820 }, { "epoch": 12.89, "learning_rate": 9.427873462743142e-05, "loss": 0.2639, "step": 53830 }, { "epoch": 12.89, "learning_rate": 9.427665026786159e-05, "loss": 0.2823, "step": 53840 }, { "epoch": 12.89, "learning_rate": 9.427456555172576e-05, "loss": 0.2499, "step": 53850 }, { "epoch": 12.89, "learning_rate": 9.427248047904076e-05, "loss": 0.2762, "step": 53860 }, { "epoch": 12.89, "learning_rate": 9.427039504982334e-05, "loss": 0.2843, "step": 53870 }, { "epoch": 12.9, "learning_rate": 9.426830926409034e-05, "loss": 0.2907, "step": 53880 }, { "epoch": 12.9, "learning_rate": 9.426622312185851e-05, "loss": 0.3123, "step": 53890 }, { "epoch": 12.9, "learning_rate": 9.42641366231447e-05, "loss": 0.2455, "step": 53900 }, { "epoch": 12.9, "learning_rate": 9.426204976796567e-05, "loss": 0.2958, "step": 53910 }, { "epoch": 12.91, "learning_rate": 9.425996255633824e-05, "loss": 0.255, "step": 53920 }, { "epoch": 12.91, "learning_rate": 9.425787498827922e-05, "loss": 0.2463, "step": 53930 }, { "epoch": 12.91, "learning_rate": 9.425578706380544e-05, "loss": 0.2631, "step": 53940 }, { "epoch": 12.91, "learning_rate": 9.425369878293369e-05, "loss": 0.2824, "step": 53950 }, { "epoch": 12.91, "learning_rate": 9.42516101456808e-05, "loss": 0.2527, "step": 53960 }, { "epoch": 12.92, "learning_rate": 9.424952115206356e-05, "loss": 0.29, "step": 53970 }, { "epoch": 12.92, "learning_rate": 9.424743180209885e-05, "loss": 0.2672, "step": 53980 }, { "epoch": 12.92, "learning_rate": 9.424534209580343e-05, "loss": 0.2471, "step": 53990 }, { "epoch": 12.92, "learning_rate": 9.424325203319417e-05, "loss": 0.2384, "step": 54000 }, { "epoch": 12.93, "learning_rate": 9.42411616142879e-05, "loss": 0.2239, "step": 54010 }, { "epoch": 12.93, "learning_rate": 9.423907083910146e-05, "loss": 0.2939, "step": 54020 }, { "epoch": 12.93, "learning_rate": 9.423697970765166e-05, "loss": 0.2452, "step": 54030 }, { "epoch": 12.93, "learning_rate": 9.423488821995537e-05, "loss": 0.2253, "step": 54040 }, { "epoch": 12.94, "learning_rate": 9.42327963760294e-05, "loss": 0.2751, "step": 54050 }, { "epoch": 12.94, "learning_rate": 9.423070417589061e-05, "loss": 0.2652, "step": 54060 }, { "epoch": 12.94, "learning_rate": 9.422861161955587e-05, "loss": 0.2864, "step": 54070 }, { "epoch": 12.94, "learning_rate": 9.4226518707042e-05, "loss": 0.2629, "step": 54080 }, { "epoch": 12.94, "learning_rate": 9.422442543836588e-05, "loss": 0.2708, "step": 54090 }, { "epoch": 12.95, "learning_rate": 9.422233181354437e-05, "loss": 0.2952, "step": 54100 }, { "epoch": 12.95, "learning_rate": 9.422023783259428e-05, "loss": 0.25, "step": 54110 }, { "epoch": 13.0, "learning_rate": 9.421814349553253e-05, "loss": 0.2946, "step": 54120 }, { "epoch": 13.0, "learning_rate": 9.421604880237598e-05, "loss": 0.2067, "step": 54130 }, { "epoch": 13.0, "learning_rate": 9.421395375314146e-05, "loss": 0.274, "step": 54140 }, { "epoch": 13.01, "learning_rate": 9.421185834784587e-05, "loss": 0.3069, "step": 54150 }, { "epoch": 13.01, "learning_rate": 9.420976258650609e-05, "loss": 0.2842, "step": 54160 }, { "epoch": 13.01, "learning_rate": 9.420766646913899e-05, "loss": 0.2596, "step": 54170 }, { "epoch": 13.01, "learning_rate": 9.420556999576144e-05, "loss": 0.2752, "step": 54180 }, { "epoch": 13.02, "learning_rate": 9.420347316639034e-05, "loss": 0.2854, "step": 54190 }, { "epoch": 13.02, "learning_rate": 9.420137598104257e-05, "loss": 0.2775, "step": 54200 }, { "epoch": 13.02, "learning_rate": 9.4199278439735e-05, "loss": 0.2549, "step": 54210 }, { "epoch": 13.02, "learning_rate": 9.419718054248455e-05, "loss": 0.2619, "step": 54220 }, { "epoch": 13.03, "learning_rate": 9.419508228930811e-05, "loss": 0.2765, "step": 54230 }, { "epoch": 13.03, "learning_rate": 9.419298368022256e-05, "loss": 0.2557, "step": 54240 }, { "epoch": 13.03, "learning_rate": 9.419088471524482e-05, "loss": 0.2159, "step": 54250 }, { "epoch": 13.03, "learning_rate": 9.418878539439178e-05, "loss": 0.2524, "step": 54260 }, { "epoch": 13.03, "learning_rate": 9.418668571768035e-05, "loss": 0.2367, "step": 54270 }, { "epoch": 13.04, "learning_rate": 9.418458568512742e-05, "loss": 0.282, "step": 54280 }, { "epoch": 13.04, "learning_rate": 9.418248529674996e-05, "loss": 0.2707, "step": 54290 }, { "epoch": 13.04, "learning_rate": 9.418038455256481e-05, "loss": 0.2577, "step": 54300 }, { "epoch": 13.04, "learning_rate": 9.417828345258895e-05, "loss": 0.2451, "step": 54310 }, { "epoch": 13.05, "learning_rate": 9.417618199683926e-05, "loss": 0.2312, "step": 54320 }, { "epoch": 13.05, "learning_rate": 9.41740801853327e-05, "loss": 0.2825, "step": 54330 }, { "epoch": 13.05, "learning_rate": 9.417197801808614e-05, "loss": 0.2464, "step": 54340 }, { "epoch": 13.05, "learning_rate": 9.416987549511656e-05, "loss": 0.2749, "step": 54350 }, { "epoch": 13.06, "learning_rate": 9.416777261644087e-05, "loss": 0.2744, "step": 54360 }, { "epoch": 13.06, "learning_rate": 9.416566938207602e-05, "loss": 0.2847, "step": 54370 }, { "epoch": 13.06, "learning_rate": 9.416356579203894e-05, "loss": 0.2481, "step": 54380 }, { "epoch": 13.06, "learning_rate": 9.416146184634654e-05, "loss": 0.3004, "step": 54390 }, { "epoch": 13.06, "learning_rate": 9.415935754501582e-05, "loss": 0.2641, "step": 54400 }, { "epoch": 13.07, "learning_rate": 9.415725288806368e-05, "loss": 0.2397, "step": 54410 }, { "epoch": 13.07, "learning_rate": 9.415514787550708e-05, "loss": 0.2473, "step": 54420 }, { "epoch": 13.07, "learning_rate": 9.415304250736299e-05, "loss": 0.2442, "step": 54430 }, { "epoch": 13.07, "learning_rate": 9.415093678364836e-05, "loss": 0.2777, "step": 54440 }, { "epoch": 13.08, "learning_rate": 9.414883070438013e-05, "loss": 0.2635, "step": 54450 }, { "epoch": 13.08, "learning_rate": 9.414672426957527e-05, "loss": 0.2495, "step": 54460 }, { "epoch": 13.08, "learning_rate": 9.414461747925075e-05, "loss": 0.2696, "step": 54470 }, { "epoch": 13.08, "learning_rate": 9.414251033342353e-05, "loss": 0.2048, "step": 54480 }, { "epoch": 13.08, "learning_rate": 9.414040283211058e-05, "loss": 0.2569, "step": 54490 }, { "epoch": 13.09, "learning_rate": 9.413829497532887e-05, "loss": 0.2132, "step": 54500 }, { "epoch": 13.09, "learning_rate": 9.413618676309538e-05, "loss": 0.2787, "step": 54510 }, { "epoch": 13.09, "learning_rate": 9.413407819542708e-05, "loss": 0.2649, "step": 54520 }, { "epoch": 13.09, "learning_rate": 9.413196927234096e-05, "loss": 0.3004, "step": 54530 }, { "epoch": 13.1, "learning_rate": 9.4129859993854e-05, "loss": 0.2504, "step": 54540 }, { "epoch": 13.1, "learning_rate": 9.412775035998318e-05, "loss": 0.2844, "step": 54550 }, { "epoch": 13.1, "learning_rate": 9.41256403707455e-05, "loss": 0.2598, "step": 54560 }, { "epoch": 13.1, "learning_rate": 9.412353002615795e-05, "loss": 0.2549, "step": 54570 }, { "epoch": 13.11, "learning_rate": 9.41214193262375e-05, "loss": 0.2614, "step": 54580 }, { "epoch": 13.11, "learning_rate": 9.41193082710012e-05, "loss": 0.2463, "step": 54590 }, { "epoch": 13.11, "learning_rate": 9.411719686046598e-05, "loss": 0.2534, "step": 54600 }, { "epoch": 13.11, "learning_rate": 9.411508509464891e-05, "loss": 0.2552, "step": 54610 }, { "epoch": 13.11, "learning_rate": 9.411297297356696e-05, "loss": 0.259, "step": 54620 }, { "epoch": 13.12, "learning_rate": 9.411086049723716e-05, "loss": 0.2445, "step": 54630 }, { "epoch": 13.12, "learning_rate": 9.41087476656765e-05, "loss": 0.2369, "step": 54640 }, { "epoch": 13.12, "learning_rate": 9.410663447890202e-05, "loss": 0.2991, "step": 54650 }, { "epoch": 13.12, "learning_rate": 9.41045209369307e-05, "loss": 0.2573, "step": 54660 }, { "epoch": 13.13, "learning_rate": 9.41024070397796e-05, "loss": 0.2635, "step": 54670 }, { "epoch": 13.13, "learning_rate": 9.410029278746572e-05, "loss": 0.2277, "step": 54680 }, { "epoch": 13.13, "learning_rate": 9.40981781800061e-05, "loss": 0.2837, "step": 54690 }, { "epoch": 13.13, "learning_rate": 9.409606321741775e-05, "loss": 0.2281, "step": 54700 }, { "epoch": 13.14, "learning_rate": 9.409394789971772e-05, "loss": 0.2428, "step": 54710 }, { "epoch": 13.14, "learning_rate": 9.409183222692305e-05, "loss": 0.2523, "step": 54720 }, { "epoch": 13.14, "learning_rate": 9.408971619905078e-05, "loss": 0.2241, "step": 54730 }, { "epoch": 13.14, "learning_rate": 9.408759981611791e-05, "loss": 0.2901, "step": 54740 }, { "epoch": 13.14, "learning_rate": 9.408548307814153e-05, "loss": 0.2898, "step": 54750 }, { "epoch": 13.15, "learning_rate": 9.408336598513865e-05, "loss": 0.2819, "step": 54760 }, { "epoch": 13.15, "learning_rate": 9.408124853712635e-05, "loss": 0.2068, "step": 54770 }, { "epoch": 13.15, "learning_rate": 9.407913073412167e-05, "loss": 0.2517, "step": 54780 }, { "epoch": 13.15, "learning_rate": 9.407701257614167e-05, "loss": 0.2796, "step": 54790 }, { "epoch": 13.16, "learning_rate": 9.407489406320339e-05, "loss": 0.2735, "step": 54800 }, { "epoch": 13.16, "learning_rate": 9.407277519532391e-05, "loss": 0.2891, "step": 54810 }, { "epoch": 13.16, "learning_rate": 9.407065597252029e-05, "loss": 0.2642, "step": 54820 }, { "epoch": 13.16, "learning_rate": 9.406853639480959e-05, "loss": 0.2271, "step": 54830 }, { "epoch": 13.16, "learning_rate": 9.406641646220888e-05, "loss": 0.2688, "step": 54840 }, { "epoch": 13.17, "learning_rate": 9.406429617473524e-05, "loss": 0.2528, "step": 54850 }, { "epoch": 13.17, "learning_rate": 9.406217553240573e-05, "loss": 0.2494, "step": 54860 }, { "epoch": 13.17, "learning_rate": 9.406005453523744e-05, "loss": 0.2767, "step": 54870 }, { "epoch": 13.17, "learning_rate": 9.405793318324744e-05, "loss": 0.2524, "step": 54880 }, { "epoch": 13.18, "learning_rate": 9.405581147645284e-05, "loss": 0.2257, "step": 54890 }, { "epoch": 13.18, "learning_rate": 9.405368941487071e-05, "loss": 0.2283, "step": 54900 }, { "epoch": 13.18, "learning_rate": 9.405156699851811e-05, "loss": 0.2647, "step": 54910 }, { "epoch": 13.18, "learning_rate": 9.404944422741219e-05, "loss": 0.2288, "step": 54920 }, { "epoch": 13.19, "learning_rate": 9.404732110156999e-05, "loss": 0.2246, "step": 54930 }, { "epoch": 13.19, "learning_rate": 9.404519762100865e-05, "loss": 0.2009, "step": 54940 }, { "epoch": 13.19, "learning_rate": 9.404307378574523e-05, "loss": 0.2906, "step": 54950 }, { "epoch": 13.19, "learning_rate": 9.404094959579688e-05, "loss": 0.2105, "step": 54960 }, { "epoch": 13.19, "learning_rate": 9.403882505118069e-05, "loss": 0.2651, "step": 54970 }, { "epoch": 13.2, "learning_rate": 9.403670015191373e-05, "loss": 0.2532, "step": 54980 }, { "epoch": 13.2, "learning_rate": 9.403457489801318e-05, "loss": 0.2577, "step": 54990 }, { "epoch": 13.2, "learning_rate": 9.403244928949608e-05, "loss": 0.2872, "step": 55000 }, { "epoch": 13.2, "learning_rate": 9.403032332637962e-05, "loss": 0.2729, "step": 55010 }, { "epoch": 13.21, "learning_rate": 9.402819700868087e-05, "loss": 0.212, "step": 55020 }, { "epoch": 13.21, "learning_rate": 9.402607033641697e-05, "loss": 0.2515, "step": 55030 }, { "epoch": 13.21, "learning_rate": 9.402394330960506e-05, "loss": 0.2328, "step": 55040 }, { "epoch": 13.21, "learning_rate": 9.402181592826225e-05, "loss": 0.2998, "step": 55050 }, { "epoch": 13.22, "learning_rate": 9.401968819240567e-05, "loss": 0.2184, "step": 55060 }, { "epoch": 13.22, "learning_rate": 9.401756010205247e-05, "loss": 0.2803, "step": 55070 }, { "epoch": 13.22, "learning_rate": 9.401543165721977e-05, "loss": 0.2735, "step": 55080 }, { "epoch": 13.22, "learning_rate": 9.401330285792476e-05, "loss": 0.2783, "step": 55090 }, { "epoch": 13.22, "learning_rate": 9.40111737041845e-05, "loss": 0.2782, "step": 55100 }, { "epoch": 13.23, "learning_rate": 9.400904419601622e-05, "loss": 0.2535, "step": 55110 }, { "epoch": 13.23, "learning_rate": 9.4006914333437e-05, "loss": 0.2714, "step": 55120 }, { "epoch": 13.23, "learning_rate": 9.400478411646404e-05, "loss": 0.2374, "step": 55130 }, { "epoch": 13.23, "learning_rate": 9.400265354511448e-05, "loss": 0.2656, "step": 55140 }, { "epoch": 13.24, "learning_rate": 9.400052261940546e-05, "loss": 0.2533, "step": 55150 }, { "epoch": 13.24, "learning_rate": 9.399839133935417e-05, "loss": 0.2805, "step": 55160 }, { "epoch": 13.24, "learning_rate": 9.399625970497776e-05, "loss": 0.2219, "step": 55170 }, { "epoch": 13.24, "learning_rate": 9.39941277162934e-05, "loss": 0.2889, "step": 55180 }, { "epoch": 13.24, "learning_rate": 9.399199537331825e-05, "loss": 0.2279, "step": 55190 }, { "epoch": 13.25, "learning_rate": 9.398986267606948e-05, "loss": 0.262, "step": 55200 }, { "epoch": 13.25, "learning_rate": 9.398772962456429e-05, "loss": 0.2229, "step": 55210 }, { "epoch": 13.25, "learning_rate": 9.398559621881984e-05, "loss": 0.2901, "step": 55220 }, { "epoch": 13.25, "learning_rate": 9.39834624588533e-05, "loss": 0.2261, "step": 55230 }, { "epoch": 13.26, "learning_rate": 9.398132834468187e-05, "loss": 0.2624, "step": 55240 }, { "epoch": 13.26, "learning_rate": 9.397919387632273e-05, "loss": 0.2209, "step": 55250 }, { "epoch": 13.26, "learning_rate": 9.397705905379306e-05, "loss": 0.2691, "step": 55260 }, { "epoch": 13.26, "learning_rate": 9.397492387711006e-05, "loss": 0.2824, "step": 55270 }, { "epoch": 13.27, "learning_rate": 9.397278834629096e-05, "loss": 0.2646, "step": 55280 }, { "epoch": 13.27, "learning_rate": 9.397065246135289e-05, "loss": 0.2762, "step": 55290 }, { "epoch": 13.27, "learning_rate": 9.396851622231308e-05, "loss": 0.2271, "step": 55300 }, { "epoch": 13.27, "learning_rate": 9.396637962918878e-05, "loss": 0.2173, "step": 55310 }, { "epoch": 13.27, "learning_rate": 9.396424268199712e-05, "loss": 0.2484, "step": 55320 }, { "epoch": 13.28, "learning_rate": 9.396210538075534e-05, "loss": 0.2115, "step": 55330 }, { "epoch": 13.28, "learning_rate": 9.395996772548068e-05, "loss": 0.2613, "step": 55340 }, { "epoch": 13.28, "learning_rate": 9.395782971619032e-05, "loss": 0.2444, "step": 55350 }, { "epoch": 13.28, "learning_rate": 9.39556913529015e-05, "loss": 0.2137, "step": 55360 }, { "epoch": 13.29, "learning_rate": 9.395355263563142e-05, "loss": 0.2403, "step": 55370 }, { "epoch": 13.29, "learning_rate": 9.395141356439731e-05, "loss": 0.2971, "step": 55380 }, { "epoch": 13.29, "learning_rate": 9.394927413921639e-05, "loss": 0.2475, "step": 55390 }, { "epoch": 13.29, "learning_rate": 9.394713436010591e-05, "loss": 0.2673, "step": 55400 }, { "epoch": 13.3, "learning_rate": 9.394499422708309e-05, "loss": 0.223, "step": 55410 }, { "epoch": 13.3, "learning_rate": 9.394285374016515e-05, "loss": 0.2452, "step": 55420 }, { "epoch": 13.3, "learning_rate": 9.394071289936936e-05, "loss": 0.2187, "step": 55430 }, { "epoch": 13.3, "learning_rate": 9.393857170471294e-05, "loss": 0.2756, "step": 55440 }, { "epoch": 13.3, "learning_rate": 9.393643015621314e-05, "loss": 0.2511, "step": 55450 }, { "epoch": 13.31, "learning_rate": 9.393428825388719e-05, "loss": 0.2319, "step": 55460 }, { "epoch": 13.31, "learning_rate": 9.393214599775235e-05, "loss": 0.2659, "step": 55470 }, { "epoch": 13.31, "learning_rate": 9.393000338782588e-05, "loss": 0.2066, "step": 55480 }, { "epoch": 13.31, "learning_rate": 9.392786042412503e-05, "loss": 0.2519, "step": 55490 }, { "epoch": 13.32, "learning_rate": 9.392571710666705e-05, "loss": 0.2637, "step": 55500 }, { "epoch": 13.32, "learning_rate": 9.392357343546921e-05, "loss": 0.2222, "step": 55510 }, { "epoch": 13.32, "learning_rate": 9.392142941054878e-05, "loss": 0.2556, "step": 55520 }, { "epoch": 13.32, "learning_rate": 9.3919285031923e-05, "loss": 0.2459, "step": 55530 }, { "epoch": 13.32, "learning_rate": 9.391714029960915e-05, "loss": 0.2433, "step": 55540 }, { "epoch": 13.33, "learning_rate": 9.391499521362452e-05, "loss": 0.1976, "step": 55550 }, { "epoch": 13.33, "learning_rate": 9.391284977398636e-05, "loss": 0.1837, "step": 55560 }, { "epoch": 13.33, "learning_rate": 9.391070398071195e-05, "loss": 0.2639, "step": 55570 }, { "epoch": 13.33, "learning_rate": 9.39085578338186e-05, "loss": 0.2414, "step": 55580 }, { "epoch": 13.34, "learning_rate": 9.390641133332357e-05, "loss": 0.2464, "step": 55590 }, { "epoch": 13.34, "learning_rate": 9.390426447924412e-05, "loss": 0.255, "step": 55600 }, { "epoch": 13.34, "learning_rate": 9.39021172715976e-05, "loss": 0.178, "step": 55610 }, { "epoch": 13.34, "learning_rate": 9.389996971040124e-05, "loss": 0.2218, "step": 55620 }, { "epoch": 13.35, "learning_rate": 9.389782179567239e-05, "loss": 0.3008, "step": 55630 }, { "epoch": 13.35, "learning_rate": 9.389567352742831e-05, "loss": 0.2498, "step": 55640 }, { "epoch": 13.35, "learning_rate": 9.38935249056863e-05, "loss": 0.3133, "step": 55650 }, { "epoch": 13.35, "learning_rate": 9.389137593046369e-05, "loss": 0.2573, "step": 55660 }, { "epoch": 13.35, "learning_rate": 9.388922660177777e-05, "loss": 0.2499, "step": 55670 }, { "epoch": 13.36, "learning_rate": 9.388707691964584e-05, "loss": 0.2005, "step": 55680 }, { "epoch": 13.36, "learning_rate": 9.388492688408523e-05, "loss": 0.2064, "step": 55690 }, { "epoch": 13.36, "learning_rate": 9.388277649511324e-05, "loss": 0.2262, "step": 55700 }, { "epoch": 13.36, "learning_rate": 9.388062575274719e-05, "loss": 0.2248, "step": 55710 }, { "epoch": 13.37, "learning_rate": 9.387847465700439e-05, "loss": 0.2725, "step": 55720 }, { "epoch": 13.37, "learning_rate": 9.38763232079022e-05, "loss": 0.2316, "step": 55730 }, { "epoch": 13.37, "learning_rate": 9.387417140545792e-05, "loss": 0.2086, "step": 55740 }, { "epoch": 13.37, "learning_rate": 9.387201924968886e-05, "loss": 0.2288, "step": 55750 }, { "epoch": 13.38, "learning_rate": 9.386986674061238e-05, "loss": 0.2059, "step": 55760 }, { "epoch": 13.38, "learning_rate": 9.386771387824581e-05, "loss": 0.2133, "step": 55770 }, { "epoch": 13.38, "learning_rate": 9.38655606626065e-05, "loss": 0.2341, "step": 55780 }, { "epoch": 13.38, "learning_rate": 9.386340709371175e-05, "loss": 0.2418, "step": 55790 }, { "epoch": 13.38, "learning_rate": 9.386125317157892e-05, "loss": 0.273, "step": 55800 }, { "epoch": 13.39, "learning_rate": 9.38590988962254e-05, "loss": 0.1827, "step": 55810 }, { "epoch": 13.39, "learning_rate": 9.385694426766847e-05, "loss": 0.2431, "step": 55820 }, { "epoch": 13.39, "learning_rate": 9.385478928592553e-05, "loss": 0.1843, "step": 55830 }, { "epoch": 13.39, "learning_rate": 9.38526339510139e-05, "loss": 0.211, "step": 55840 }, { "epoch": 13.4, "learning_rate": 9.385047826295098e-05, "loss": 0.2578, "step": 55850 }, { "epoch": 13.4, "learning_rate": 9.384832222175407e-05, "loss": 0.244, "step": 55860 }, { "epoch": 13.4, "learning_rate": 9.384616582744059e-05, "loss": 0.27, "step": 55870 }, { "epoch": 13.4, "learning_rate": 9.384400908002789e-05, "loss": 0.2366, "step": 55880 }, { "epoch": 13.4, "learning_rate": 9.384185197953331e-05, "loss": 0.2005, "step": 55890 }, { "epoch": 13.41, "learning_rate": 9.383969452597426e-05, "loss": 0.2317, "step": 55900 }, { "epoch": 13.41, "learning_rate": 9.383753671936808e-05, "loss": 0.2349, "step": 55910 }, { "epoch": 13.41, "learning_rate": 9.383537855973218e-05, "loss": 0.2227, "step": 55920 }, { "epoch": 13.41, "learning_rate": 9.383322004708393e-05, "loss": 0.2217, "step": 55930 }, { "epoch": 13.42, "learning_rate": 9.38310611814407e-05, "loss": 0.174, "step": 55940 }, { "epoch": 13.42, "learning_rate": 9.382890196281989e-05, "loss": 0.2128, "step": 55950 }, { "epoch": 13.42, "learning_rate": 9.382674239123885e-05, "loss": 0.261, "step": 55960 }, { "epoch": 13.42, "learning_rate": 9.382458246671504e-05, "loss": 0.2441, "step": 55970 }, { "epoch": 13.43, "learning_rate": 9.38224221892658e-05, "loss": 0.2667, "step": 55980 }, { "epoch": 13.43, "learning_rate": 9.382026155890854e-05, "loss": 0.2209, "step": 55990 }, { "epoch": 13.43, "learning_rate": 9.381810057566068e-05, "loss": 0.2358, "step": 56000 }, { "epoch": 13.43, "learning_rate": 9.38159392395396e-05, "loss": 0.1962, "step": 56010 }, { "epoch": 13.43, "learning_rate": 9.38137775505627e-05, "loss": 0.2174, "step": 56020 }, { "epoch": 13.44, "learning_rate": 9.381161550874742e-05, "loss": 0.2517, "step": 56030 }, { "epoch": 13.44, "learning_rate": 9.380945311411113e-05, "loss": 0.2018, "step": 56040 }, { "epoch": 13.44, "learning_rate": 9.380729036667129e-05, "loss": 0.2424, "step": 56050 }, { "epoch": 13.44, "learning_rate": 9.380512726644528e-05, "loss": 0.2096, "step": 56060 }, { "epoch": 13.45, "learning_rate": 9.380296381345053e-05, "loss": 0.2585, "step": 56070 }, { "epoch": 13.45, "learning_rate": 9.380080000770447e-05, "loss": 0.2459, "step": 56080 }, { "epoch": 13.45, "learning_rate": 9.379863584922452e-05, "loss": 0.2576, "step": 56090 }, { "epoch": 13.45, "learning_rate": 9.379647133802812e-05, "loss": 0.2177, "step": 56100 }, { "epoch": 13.45, "learning_rate": 9.379430647413267e-05, "loss": 0.2119, "step": 56110 }, { "epoch": 13.46, "learning_rate": 9.379214125755562e-05, "loss": 0.2628, "step": 56120 }, { "epoch": 13.46, "learning_rate": 9.378997568831442e-05, "loss": 0.23, "step": 56130 }, { "epoch": 13.46, "learning_rate": 9.378780976642652e-05, "loss": 0.2291, "step": 56140 }, { "epoch": 13.46, "learning_rate": 9.378564349190932e-05, "loss": 0.2361, "step": 56150 }, { "epoch": 13.47, "learning_rate": 9.378347686478028e-05, "loss": 0.2898, "step": 56160 }, { "epoch": 13.47, "learning_rate": 9.378130988505688e-05, "loss": 0.2636, "step": 56170 }, { "epoch": 13.47, "learning_rate": 9.377914255275653e-05, "loss": 0.2686, "step": 56180 }, { "epoch": 13.47, "learning_rate": 9.37769748678967e-05, "loss": 0.202, "step": 56190 }, { "epoch": 13.48, "learning_rate": 9.377480683049487e-05, "loss": 0.2519, "step": 56200 }, { "epoch": 13.48, "learning_rate": 9.377263844056845e-05, "loss": 0.2425, "step": 56210 }, { "epoch": 13.48, "learning_rate": 9.377046969813494e-05, "loss": 0.1985, "step": 56220 }, { "epoch": 13.48, "learning_rate": 9.37683006032118e-05, "loss": 0.1977, "step": 56230 }, { "epoch": 13.48, "learning_rate": 9.37661311558165e-05, "loss": 0.2348, "step": 56240 }, { "epoch": 13.49, "learning_rate": 9.376396135596648e-05, "loss": 0.2815, "step": 56250 }, { "epoch": 13.49, "learning_rate": 9.376179120367925e-05, "loss": 0.2751, "step": 56260 }, { "epoch": 13.49, "learning_rate": 9.375962069897228e-05, "loss": 0.2012, "step": 56270 }, { "epoch": 13.49, "learning_rate": 9.375744984186304e-05, "loss": 0.2663, "step": 56280 }, { "epoch": 13.5, "learning_rate": 9.3755278632369e-05, "loss": 0.2264, "step": 56290 }, { "epoch": 13.5, "learning_rate": 9.375310707050766e-05, "loss": 0.2332, "step": 56300 }, { "epoch": 13.5, "learning_rate": 9.375093515629653e-05, "loss": 0.2557, "step": 56310 }, { "epoch": 13.5, "learning_rate": 9.374876288975308e-05, "loss": 0.2461, "step": 56320 }, { "epoch": 13.51, "learning_rate": 9.374659027089479e-05, "loss": 0.2613, "step": 56330 }, { "epoch": 13.51, "learning_rate": 9.374441729973916e-05, "loss": 0.2507, "step": 56340 }, { "epoch": 13.51, "learning_rate": 9.374224397630372e-05, "loss": 0.2416, "step": 56350 }, { "epoch": 13.51, "learning_rate": 9.374007030060592e-05, "loss": 0.2618, "step": 56360 }, { "epoch": 13.51, "learning_rate": 9.373789627266332e-05, "loss": 0.2488, "step": 56370 }, { "epoch": 13.52, "learning_rate": 9.37357218924934e-05, "loss": 0.2257, "step": 56380 }, { "epoch": 13.52, "learning_rate": 9.373354716011366e-05, "loss": 0.2684, "step": 56390 }, { "epoch": 13.52, "learning_rate": 9.373137207554164e-05, "loss": 0.2662, "step": 56400 }, { "epoch": 13.52, "learning_rate": 9.372919663879484e-05, "loss": 0.2412, "step": 56410 }, { "epoch": 13.53, "learning_rate": 9.372702084989079e-05, "loss": 0.2819, "step": 56420 }, { "epoch": 13.53, "learning_rate": 9.372484470884699e-05, "loss": 0.276, "step": 56430 }, { "epoch": 13.53, "learning_rate": 9.372266821568098e-05, "loss": 0.2757, "step": 56440 }, { "epoch": 13.53, "learning_rate": 9.37204913704103e-05, "loss": 0.2548, "step": 56450 }, { "epoch": 13.53, "learning_rate": 9.371831417305245e-05, "loss": 0.3213, "step": 56460 }, { "epoch": 13.54, "learning_rate": 9.3716136623625e-05, "loss": 0.3227, "step": 56470 }, { "epoch": 13.54, "learning_rate": 9.371395872214546e-05, "loss": 0.3018, "step": 56480 }, { "epoch": 13.54, "learning_rate": 9.371178046863137e-05, "loss": 0.2901, "step": 56490 }, { "epoch": 13.54, "learning_rate": 9.370960186310029e-05, "loss": 0.2912, "step": 56500 }, { "epoch": 13.55, "learning_rate": 9.370742290556972e-05, "loss": 0.2633, "step": 56510 }, { "epoch": 13.55, "learning_rate": 9.370524359605726e-05, "loss": 0.273, "step": 56520 }, { "epoch": 13.55, "learning_rate": 9.370306393458044e-05, "loss": 0.3172, "step": 56530 }, { "epoch": 13.55, "learning_rate": 9.370088392115682e-05, "loss": 0.3079, "step": 56540 }, { "epoch": 13.56, "learning_rate": 9.369870355580394e-05, "loss": 0.2886, "step": 56550 }, { "epoch": 13.56, "learning_rate": 9.369652283853937e-05, "loss": 0.2484, "step": 56560 }, { "epoch": 13.56, "learning_rate": 9.369434176938066e-05, "loss": 0.275, "step": 56570 }, { "epoch": 13.56, "learning_rate": 9.36921603483454e-05, "loss": 0.2798, "step": 56580 }, { "epoch": 13.56, "learning_rate": 9.368997857545112e-05, "loss": 0.2694, "step": 56590 }, { "epoch": 13.57, "learning_rate": 9.368779645071542e-05, "loss": 0.3032, "step": 56600 }, { "epoch": 13.57, "learning_rate": 9.368561397415587e-05, "loss": 0.2828, "step": 56610 }, { "epoch": 13.57, "learning_rate": 9.368343114579004e-05, "loss": 0.2939, "step": 56620 }, { "epoch": 13.57, "learning_rate": 9.368124796563549e-05, "loss": 0.2782, "step": 56630 }, { "epoch": 13.58, "learning_rate": 9.367906443370984e-05, "loss": 0.2709, "step": 56640 }, { "epoch": 13.58, "learning_rate": 9.367688055003064e-05, "loss": 0.2904, "step": 56650 }, { "epoch": 13.58, "learning_rate": 9.367469631461549e-05, "loss": 0.261, "step": 56660 }, { "epoch": 13.58, "learning_rate": 9.3672511727482e-05, "loss": 0.2758, "step": 56670 }, { "epoch": 13.59, "learning_rate": 9.367032678864774e-05, "loss": 0.2877, "step": 56680 }, { "epoch": 13.59, "learning_rate": 9.36681414981303e-05, "loss": 0.3, "step": 56690 }, { "epoch": 13.59, "learning_rate": 9.366595585594728e-05, "loss": 0.2401, "step": 56700 }, { "epoch": 13.59, "learning_rate": 9.366376986211629e-05, "loss": 0.2798, "step": 56710 }, { "epoch": 13.59, "learning_rate": 9.366158351665495e-05, "loss": 0.2741, "step": 56720 }, { "epoch": 13.6, "learning_rate": 9.365939681958084e-05, "loss": 0.2545, "step": 56730 }, { "epoch": 13.6, "learning_rate": 9.365720977091157e-05, "loss": 0.277, "step": 56740 }, { "epoch": 13.6, "learning_rate": 9.365502237066478e-05, "loss": 0.2898, "step": 56750 }, { "epoch": 13.6, "learning_rate": 9.365283461885805e-05, "loss": 0.296, "step": 56760 }, { "epoch": 13.61, "learning_rate": 9.365064651550903e-05, "loss": 0.2717, "step": 56770 }, { "epoch": 13.61, "learning_rate": 9.364845806063533e-05, "loss": 0.2486, "step": 56780 }, { "epoch": 13.61, "learning_rate": 9.364626925425457e-05, "loss": 0.2808, "step": 56790 }, { "epoch": 13.61, "learning_rate": 9.364408009638437e-05, "loss": 0.2848, "step": 56800 }, { "epoch": 13.61, "learning_rate": 9.364189058704237e-05, "loss": 0.2953, "step": 56810 }, { "epoch": 13.62, "learning_rate": 9.36397007262462e-05, "loss": 0.301, "step": 56820 }, { "epoch": 13.62, "learning_rate": 9.363751051401351e-05, "loss": 0.2716, "step": 56830 }, { "epoch": 13.62, "learning_rate": 9.363531995036189e-05, "loss": 0.2686, "step": 56840 }, { "epoch": 13.62, "learning_rate": 9.363312903530904e-05, "loss": 0.25, "step": 56850 }, { "epoch": 13.63, "learning_rate": 9.363093776887258e-05, "loss": 0.2585, "step": 56860 }, { "epoch": 13.63, "learning_rate": 9.362874615107013e-05, "loss": 0.2501, "step": 56870 }, { "epoch": 13.63, "learning_rate": 9.362655418191939e-05, "loss": 0.2574, "step": 56880 }, { "epoch": 13.63, "learning_rate": 9.362436186143797e-05, "loss": 0.2725, "step": 56890 }, { "epoch": 13.64, "learning_rate": 9.362216918964354e-05, "loss": 0.3047, "step": 56900 }, { "epoch": 13.64, "learning_rate": 9.361997616655379e-05, "loss": 0.2836, "step": 56910 }, { "epoch": 13.64, "learning_rate": 9.361778279218632e-05, "loss": 0.2739, "step": 56920 }, { "epoch": 13.64, "learning_rate": 9.361558906655883e-05, "loss": 0.2351, "step": 56930 }, { "epoch": 13.64, "learning_rate": 9.361339498968897e-05, "loss": 0.237, "step": 56940 }, { "epoch": 13.65, "learning_rate": 9.361120056159443e-05, "loss": 0.2896, "step": 56950 }, { "epoch": 13.65, "learning_rate": 9.360900578229288e-05, "loss": 0.2652, "step": 56960 }, { "epoch": 13.65, "learning_rate": 9.360681065180196e-05, "loss": 0.257, "step": 56970 }, { "epoch": 13.65, "learning_rate": 9.360461517013939e-05, "loss": 0.2964, "step": 56980 }, { "epoch": 13.66, "learning_rate": 9.360241933732283e-05, "loss": 0.2458, "step": 56990 }, { "epoch": 13.66, "learning_rate": 9.360022315336998e-05, "loss": 0.265, "step": 57000 }, { "epoch": 13.66, "learning_rate": 9.35980266182985e-05, "loss": 0.2665, "step": 57010 }, { "epoch": 13.66, "learning_rate": 9.359582973212609e-05, "loss": 0.29, "step": 57020 }, { "epoch": 13.67, "learning_rate": 9.359363249487045e-05, "loss": 0.2892, "step": 57030 }, { "epoch": 13.67, "learning_rate": 9.359143490654927e-05, "loss": 0.2724, "step": 57040 }, { "epoch": 13.67, "learning_rate": 9.358923696718025e-05, "loss": 0.2416, "step": 57050 }, { "epoch": 13.67, "learning_rate": 9.35870386767811e-05, "loss": 0.2984, "step": 57060 }, { "epoch": 13.67, "learning_rate": 9.358484003536948e-05, "loss": 0.2525, "step": 57070 }, { "epoch": 13.68, "learning_rate": 9.358264104296314e-05, "loss": 0.2845, "step": 57080 }, { "epoch": 13.68, "learning_rate": 9.358044169957977e-05, "loss": 0.2704, "step": 57090 }, { "epoch": 13.68, "learning_rate": 9.357824200523709e-05, "loss": 0.2701, "step": 57100 }, { "epoch": 13.68, "learning_rate": 9.35760419599528e-05, "loss": 0.2242, "step": 57110 }, { "epoch": 13.69, "learning_rate": 9.357384156374464e-05, "loss": 0.2895, "step": 57120 }, { "epoch": 13.69, "learning_rate": 9.357164081663033e-05, "loss": 0.2773, "step": 57130 }, { "epoch": 13.69, "learning_rate": 9.356943971862757e-05, "loss": 0.2767, "step": 57140 }, { "epoch": 13.69, "learning_rate": 9.356723826975409e-05, "loss": 0.2601, "step": 57150 }, { "epoch": 13.69, "learning_rate": 9.356503647002763e-05, "loss": 0.2288, "step": 57160 }, { "epoch": 13.7, "learning_rate": 9.356283431946591e-05, "loss": 0.308, "step": 57170 }, { "epoch": 13.7, "learning_rate": 9.356063181808668e-05, "loss": 0.2731, "step": 57180 }, { "epoch": 13.7, "learning_rate": 9.355842896590768e-05, "loss": 0.2349, "step": 57190 }, { "epoch": 13.7, "learning_rate": 9.355622576294661e-05, "loss": 0.2215, "step": 57200 }, { "epoch": 13.71, "learning_rate": 9.355402220922126e-05, "loss": 0.2493, "step": 57210 }, { "epoch": 13.71, "learning_rate": 9.355181830474935e-05, "loss": 0.3222, "step": 57220 }, { "epoch": 13.71, "learning_rate": 9.354961404954863e-05, "loss": 0.2034, "step": 57230 }, { "epoch": 13.71, "learning_rate": 9.354740944363686e-05, "loss": 0.315, "step": 57240 }, { "epoch": 13.72, "learning_rate": 9.354520448703179e-05, "loss": 0.2739, "step": 57250 }, { "epoch": 13.72, "learning_rate": 9.354299917975118e-05, "loss": 0.2984, "step": 57260 }, { "epoch": 13.72, "learning_rate": 9.354079352181278e-05, "loss": 0.2812, "step": 57270 }, { "epoch": 13.72, "learning_rate": 9.353858751323436e-05, "loss": 0.2736, "step": 57280 }, { "epoch": 13.72, "learning_rate": 9.353638115403369e-05, "loss": 0.2267, "step": 57290 }, { "epoch": 13.73, "learning_rate": 9.353417444422853e-05, "loss": 0.2607, "step": 57300 }, { "epoch": 13.73, "learning_rate": 9.353196738383665e-05, "loss": 0.2529, "step": 57310 }, { "epoch": 13.73, "learning_rate": 9.352975997287583e-05, "loss": 0.2802, "step": 57320 }, { "epoch": 13.73, "learning_rate": 9.352755221136385e-05, "loss": 0.2939, "step": 57330 }, { "epoch": 13.74, "learning_rate": 9.352534409931845e-05, "loss": 0.2841, "step": 57340 }, { "epoch": 13.74, "learning_rate": 9.352313563675747e-05, "loss": 0.2872, "step": 57350 }, { "epoch": 13.74, "learning_rate": 9.352092682369868e-05, "loss": 0.2258, "step": 57360 }, { "epoch": 13.74, "learning_rate": 9.351871766015985e-05, "loss": 0.2202, "step": 57370 }, { "epoch": 13.75, "learning_rate": 9.351650814615877e-05, "loss": 0.258, "step": 57380 }, { "epoch": 13.75, "learning_rate": 9.351429828171325e-05, "loss": 0.2784, "step": 57390 }, { "epoch": 13.75, "learning_rate": 9.351208806684106e-05, "loss": 0.259, "step": 57400 }, { "epoch": 13.75, "learning_rate": 9.350987750156004e-05, "loss": 0.2357, "step": 57410 }, { "epoch": 13.75, "learning_rate": 9.350766658588797e-05, "loss": 0.3046, "step": 57420 }, { "epoch": 13.76, "learning_rate": 9.350545531984265e-05, "loss": 0.3161, "step": 57430 }, { "epoch": 13.76, "learning_rate": 9.350324370344188e-05, "loss": 0.2549, "step": 57440 }, { "epoch": 13.76, "learning_rate": 9.350103173670349e-05, "loss": 0.2509, "step": 57450 }, { "epoch": 13.76, "learning_rate": 9.349881941964529e-05, "loss": 0.2994, "step": 57460 }, { "epoch": 13.77, "learning_rate": 9.34966067522851e-05, "loss": 0.2562, "step": 57470 }, { "epoch": 13.77, "learning_rate": 9.349439373464071e-05, "loss": 0.2728, "step": 57480 }, { "epoch": 13.77, "learning_rate": 9.349218036672997e-05, "loss": 0.2226, "step": 57490 }, { "epoch": 13.77, "learning_rate": 9.34899666485707e-05, "loss": 0.2332, "step": 57500 }, { "epoch": 13.77, "learning_rate": 9.348775258018072e-05, "loss": 0.2408, "step": 57510 }, { "epoch": 13.78, "learning_rate": 9.348553816157786e-05, "loss": 0.2629, "step": 57520 }, { "epoch": 13.78, "learning_rate": 9.348332339277996e-05, "loss": 0.2417, "step": 57530 }, { "epoch": 13.78, "learning_rate": 9.348110827380487e-05, "loss": 0.2456, "step": 57540 }, { "epoch": 13.78, "learning_rate": 9.34788928046704e-05, "loss": 0.2465, "step": 57550 }, { "epoch": 13.79, "learning_rate": 9.34766769853944e-05, "loss": 0.2802, "step": 57560 }, { "epoch": 13.79, "learning_rate": 9.347446081599473e-05, "loss": 0.2325, "step": 57570 }, { "epoch": 13.79, "learning_rate": 9.347224429648922e-05, "loss": 0.211, "step": 57580 }, { "epoch": 13.79, "learning_rate": 9.347002742689573e-05, "loss": 0.2195, "step": 57590 }, { "epoch": 13.8, "learning_rate": 9.346781020723209e-05, "loss": 0.2467, "step": 57600 }, { "epoch": 13.8, "learning_rate": 9.346559263751617e-05, "loss": 0.2164, "step": 57610 }, { "epoch": 13.8, "learning_rate": 9.346337471776586e-05, "loss": 0.2376, "step": 57620 }, { "epoch": 13.8, "learning_rate": 9.346115644799897e-05, "loss": 0.2146, "step": 57630 }, { "epoch": 13.8, "learning_rate": 9.34589378282334e-05, "loss": 0.1966, "step": 57640 }, { "epoch": 13.81, "learning_rate": 9.345671885848699e-05, "loss": 0.2284, "step": 57650 }, { "epoch": 13.81, "learning_rate": 9.345449953877764e-05, "loss": 0.2649, "step": 57660 }, { "epoch": 13.81, "learning_rate": 9.34522798691232e-05, "loss": 0.2463, "step": 57670 }, { "epoch": 13.81, "learning_rate": 9.345005984954155e-05, "loss": 0.2858, "step": 57680 }, { "epoch": 13.82, "learning_rate": 9.344783948005057e-05, "loss": 0.2296, "step": 57690 }, { "epoch": 13.82, "learning_rate": 9.344561876066813e-05, "loss": 0.2722, "step": 57700 }, { "epoch": 13.82, "learning_rate": 9.344339769141214e-05, "loss": 0.2443, "step": 57710 }, { "epoch": 13.82, "learning_rate": 9.344117627230047e-05, "loss": 0.2383, "step": 57720 }, { "epoch": 13.83, "learning_rate": 9.3438954503351e-05, "loss": 0.2625, "step": 57730 }, { "epoch": 13.83, "learning_rate": 9.343673238458164e-05, "loss": 0.2181, "step": 57740 }, { "epoch": 13.83, "learning_rate": 9.343450991601025e-05, "loss": 0.2231, "step": 57750 }, { "epoch": 13.83, "learning_rate": 9.34322870976548e-05, "loss": 0.2305, "step": 57760 }, { "epoch": 13.83, "learning_rate": 9.343006392953311e-05, "loss": 0.228, "step": 57770 }, { "epoch": 13.84, "learning_rate": 9.342784041166315e-05, "loss": 0.2962, "step": 57780 }, { "epoch": 13.84, "learning_rate": 9.342561654406277e-05, "loss": 0.2426, "step": 57790 }, { "epoch": 13.84, "learning_rate": 9.342339232674992e-05, "loss": 0.2229, "step": 57800 }, { "epoch": 13.84, "learning_rate": 9.342116775974248e-05, "loss": 0.2636, "step": 57810 }, { "epoch": 13.85, "learning_rate": 9.341894284305841e-05, "loss": 0.2666, "step": 57820 }, { "epoch": 13.85, "learning_rate": 9.341671757671558e-05, "loss": 0.2609, "step": 57830 }, { "epoch": 13.85, "learning_rate": 9.341449196073191e-05, "loss": 0.2402, "step": 57840 }, { "epoch": 13.85, "learning_rate": 9.341226599512539e-05, "loss": 0.2426, "step": 57850 }, { "epoch": 13.85, "learning_rate": 9.341003967991386e-05, "loss": 0.2714, "step": 57860 }, { "epoch": 13.86, "learning_rate": 9.34078130151153e-05, "loss": 0.2222, "step": 57870 }, { "epoch": 13.86, "learning_rate": 9.340558600074762e-05, "loss": 0.234, "step": 57880 }, { "epoch": 13.86, "learning_rate": 9.340335863682877e-05, "loss": 0.298, "step": 57890 }, { "epoch": 13.86, "learning_rate": 9.340113092337668e-05, "loss": 0.2687, "step": 57900 }, { "epoch": 13.87, "learning_rate": 9.33989028604093e-05, "loss": 0.2301, "step": 57910 }, { "epoch": 13.87, "learning_rate": 9.339667444794455e-05, "loss": 0.234, "step": 57920 }, { "epoch": 13.87, "learning_rate": 9.33944456860004e-05, "loss": 0.2574, "step": 57930 }, { "epoch": 13.87, "learning_rate": 9.339221657459478e-05, "loss": 0.2596, "step": 57940 }, { "epoch": 13.88, "learning_rate": 9.338998711374565e-05, "loss": 0.2874, "step": 57950 }, { "epoch": 13.88, "learning_rate": 9.338775730347098e-05, "loss": 0.2207, "step": 57960 }, { "epoch": 13.88, "learning_rate": 9.338552714378869e-05, "loss": 0.232, "step": 57970 }, { "epoch": 13.88, "learning_rate": 9.338329663471676e-05, "loss": 0.2138, "step": 57980 }, { "epoch": 13.88, "learning_rate": 9.338106577627317e-05, "loss": 0.2691, "step": 57990 }, { "epoch": 13.89, "learning_rate": 9.337883456847585e-05, "loss": 0.1989, "step": 58000 }, { "epoch": 13.89, "learning_rate": 9.33766030113428e-05, "loss": 0.2545, "step": 58010 }, { "epoch": 13.89, "learning_rate": 9.337437110489198e-05, "loss": 0.2541, "step": 58020 }, { "epoch": 13.89, "learning_rate": 9.337213884914133e-05, "loss": 0.2644, "step": 58030 }, { "epoch": 13.9, "learning_rate": 9.336990624410888e-05, "loss": 0.3051, "step": 58040 }, { "epoch": 13.9, "learning_rate": 9.336767328981259e-05, "loss": 0.2162, "step": 58050 }, { "epoch": 13.9, "learning_rate": 9.336543998627045e-05, "loss": 0.2791, "step": 58060 }, { "epoch": 13.9, "learning_rate": 9.336320633350042e-05, "loss": 0.2445, "step": 58070 }, { "epoch": 13.91, "learning_rate": 9.33609723315205e-05, "loss": 0.2033, "step": 58080 }, { "epoch": 13.91, "learning_rate": 9.33587379803487e-05, "loss": 0.2055, "step": 58090 }, { "epoch": 13.91, "learning_rate": 9.335650328000298e-05, "loss": 0.2117, "step": 58100 }, { "epoch": 13.91, "learning_rate": 9.335426823050137e-05, "loss": 0.2464, "step": 58110 }, { "epoch": 13.91, "learning_rate": 9.335203283186182e-05, "loss": 0.2368, "step": 58120 }, { "epoch": 13.92, "learning_rate": 9.334979708410239e-05, "loss": 0.2556, "step": 58130 }, { "epoch": 13.92, "learning_rate": 9.334756098724106e-05, "loss": 0.2222, "step": 58140 }, { "epoch": 13.92, "learning_rate": 9.334532454129584e-05, "loss": 0.1804, "step": 58150 }, { "epoch": 13.92, "learning_rate": 9.334308774628473e-05, "loss": 0.276, "step": 58160 }, { "epoch": 13.93, "learning_rate": 9.334085060222575e-05, "loss": 0.2756, "step": 58170 }, { "epoch": 13.93, "learning_rate": 9.333861310913691e-05, "loss": 0.2515, "step": 58180 }, { "epoch": 13.93, "learning_rate": 9.333637526703625e-05, "loss": 0.228, "step": 58190 }, { "epoch": 13.93, "learning_rate": 9.333413707594177e-05, "loss": 0.236, "step": 58200 }, { "epoch": 13.93, "learning_rate": 9.33318985358715e-05, "loss": 0.2805, "step": 58210 }, { "epoch": 13.94, "learning_rate": 9.332965964684346e-05, "loss": 0.2034, "step": 58220 }, { "epoch": 13.94, "learning_rate": 9.33274204088757e-05, "loss": 0.1811, "step": 58230 }, { "epoch": 13.94, "learning_rate": 9.332518082198624e-05, "loss": 0.2032, "step": 58240 }, { "epoch": 13.94, "learning_rate": 9.33229408861931e-05, "loss": 0.2226, "step": 58250 }, { "epoch": 13.95, "learning_rate": 9.332070060151436e-05, "loss": 0.2187, "step": 58260 }, { "epoch": 13.95, "learning_rate": 9.331845996796804e-05, "loss": 0.2477, "step": 58270 }, { "epoch": 13.95, "learning_rate": 9.331621898557217e-05, "loss": 0.2067, "step": 58280 }, { "epoch": 14.0, "learning_rate": 9.331397765434482e-05, "loss": 0.2261, "step": 58290 }, { "epoch": 14.0, "learning_rate": 9.331173597430402e-05, "loss": 0.2162, "step": 58300 }, { "epoch": 14.01, "learning_rate": 9.330949394546782e-05, "loss": 0.2072, "step": 58310 }, { "epoch": 14.01, "learning_rate": 9.33072515678543e-05, "loss": 0.2112, "step": 58320 }, { "epoch": 14.01, "learning_rate": 9.33050088414815e-05, "loss": 0.2017, "step": 58330 }, { "epoch": 14.01, "learning_rate": 9.330276576636748e-05, "loss": 0.1603, "step": 58340 }, { "epoch": 14.02, "learning_rate": 9.330052234253032e-05, "loss": 0.2022, "step": 58350 }, { "epoch": 14.02, "learning_rate": 9.329827856998807e-05, "loss": 0.2226, "step": 58360 }, { "epoch": 14.02, "learning_rate": 9.32960344487588e-05, "loss": 0.2351, "step": 58370 }, { "epoch": 14.02, "learning_rate": 9.329378997886058e-05, "loss": 0.2071, "step": 58380 }, { "epoch": 14.02, "learning_rate": 9.32915451603115e-05, "loss": 0.183, "step": 58390 }, { "epoch": 14.03, "learning_rate": 9.328929999312964e-05, "loss": 0.2514, "step": 58400 }, { "epoch": 14.03, "learning_rate": 9.328705447733308e-05, "loss": 0.2181, "step": 58410 }, { "epoch": 14.03, "learning_rate": 9.328480861293987e-05, "loss": 0.2214, "step": 58420 }, { "epoch": 14.03, "learning_rate": 9.328256239996813e-05, "loss": 0.19, "step": 58430 }, { "epoch": 14.04, "learning_rate": 9.328031583843593e-05, "loss": 0.2437, "step": 58440 }, { "epoch": 14.04, "learning_rate": 9.327806892836137e-05, "loss": 0.2202, "step": 58450 }, { "epoch": 14.04, "learning_rate": 9.327582166976256e-05, "loss": 0.2091, "step": 58460 }, { "epoch": 14.04, "learning_rate": 9.327357406265758e-05, "loss": 0.2457, "step": 58470 }, { "epoch": 14.05, "learning_rate": 9.327132610706454e-05, "loss": 0.21, "step": 58480 }, { "epoch": 14.05, "learning_rate": 9.326907780300153e-05, "loss": 0.2024, "step": 58490 }, { "epoch": 14.05, "learning_rate": 9.326682915048666e-05, "loss": 0.1743, "step": 58500 }, { "epoch": 14.05, "learning_rate": 9.326458014953805e-05, "loss": 0.2169, "step": 58510 }, { "epoch": 14.05, "learning_rate": 9.32623308001738e-05, "loss": 0.2061, "step": 58520 }, { "epoch": 14.06, "learning_rate": 9.326008110241202e-05, "loss": 0.2066, "step": 58530 }, { "epoch": 14.06, "learning_rate": 9.325783105627084e-05, "loss": 0.2355, "step": 58540 }, { "epoch": 14.06, "learning_rate": 9.325558066176836e-05, "loss": 0.2585, "step": 58550 }, { "epoch": 14.06, "learning_rate": 9.325332991892273e-05, "loss": 0.2094, "step": 58560 }, { "epoch": 14.07, "learning_rate": 9.325107882775207e-05, "loss": 0.2533, "step": 58570 }, { "epoch": 14.07, "learning_rate": 9.32488273882745e-05, "loss": 0.2107, "step": 58580 }, { "epoch": 14.07, "learning_rate": 9.324657560050813e-05, "loss": 0.2201, "step": 58590 }, { "epoch": 14.07, "learning_rate": 9.324432346447114e-05, "loss": 0.2225, "step": 58600 }, { "epoch": 14.07, "learning_rate": 9.324207098018162e-05, "loss": 0.2551, "step": 58610 }, { "epoch": 14.08, "learning_rate": 9.323981814765777e-05, "loss": 0.2582, "step": 58620 }, { "epoch": 14.08, "learning_rate": 9.323756496691767e-05, "loss": 0.2449, "step": 58630 }, { "epoch": 14.08, "learning_rate": 9.323531143797949e-05, "loss": 0.254, "step": 58640 }, { "epoch": 14.08, "learning_rate": 9.323305756086138e-05, "loss": 0.2195, "step": 58650 }, { "epoch": 14.09, "learning_rate": 9.323080333558149e-05, "loss": 0.2043, "step": 58660 }, { "epoch": 14.09, "learning_rate": 9.322854876215796e-05, "loss": 0.2521, "step": 58670 }, { "epoch": 14.09, "learning_rate": 9.322629384060898e-05, "loss": 0.2281, "step": 58680 }, { "epoch": 14.09, "learning_rate": 9.322403857095268e-05, "loss": 0.2387, "step": 58690 }, { "epoch": 14.1, "learning_rate": 9.322178295320723e-05, "loss": 0.262, "step": 58700 }, { "epoch": 14.1, "learning_rate": 9.321952698739078e-05, "loss": 0.2544, "step": 58710 }, { "epoch": 14.1, "learning_rate": 9.321727067352153e-05, "loss": 0.2215, "step": 58720 }, { "epoch": 14.1, "learning_rate": 9.321501401161763e-05, "loss": 0.239, "step": 58730 }, { "epoch": 14.1, "learning_rate": 9.321275700169725e-05, "loss": 0.1967, "step": 58740 }, { "epoch": 14.11, "learning_rate": 9.321049964377858e-05, "loss": 0.1871, "step": 58750 }, { "epoch": 14.11, "learning_rate": 9.320824193787978e-05, "loss": 0.1983, "step": 58760 }, { "epoch": 14.11, "learning_rate": 9.320598388401906e-05, "loss": 0.2008, "step": 58770 }, { "epoch": 14.11, "learning_rate": 9.320372548221457e-05, "loss": 0.2545, "step": 58780 }, { "epoch": 14.12, "learning_rate": 9.320146673248452e-05, "loss": 0.1807, "step": 58790 }, { "epoch": 14.12, "learning_rate": 9.31992076348471e-05, "loss": 0.2284, "step": 58800 }, { "epoch": 14.12, "learning_rate": 9.319694818932048e-05, "loss": 0.2295, "step": 58810 }, { "epoch": 14.12, "learning_rate": 9.31946883959229e-05, "loss": 0.2246, "step": 58820 }, { "epoch": 14.13, "learning_rate": 9.31924282546725e-05, "loss": 0.2181, "step": 58830 }, { "epoch": 14.13, "learning_rate": 9.319016776558754e-05, "loss": 0.1899, "step": 58840 }, { "epoch": 14.13, "learning_rate": 9.318790692868618e-05, "loss": 0.2723, "step": 58850 }, { "epoch": 14.13, "learning_rate": 9.318564574398664e-05, "loss": 0.2058, "step": 58860 }, { "epoch": 14.13, "learning_rate": 9.318338421150714e-05, "loss": 0.2277, "step": 58870 }, { "epoch": 14.14, "learning_rate": 9.318112233126589e-05, "loss": 0.2985, "step": 58880 }, { "epoch": 14.14, "learning_rate": 9.317886010328109e-05, "loss": 0.1948, "step": 58890 }, { "epoch": 14.14, "learning_rate": 9.317659752757096e-05, "loss": 0.1996, "step": 58900 }, { "epoch": 14.14, "learning_rate": 9.317433460415375e-05, "loss": 0.2005, "step": 58910 }, { "epoch": 14.15, "learning_rate": 9.317207133304765e-05, "loss": 0.24, "step": 58920 }, { "epoch": 14.15, "learning_rate": 9.31698077142709e-05, "loss": 0.2077, "step": 58930 }, { "epoch": 14.15, "learning_rate": 9.316754374784174e-05, "loss": 0.2004, "step": 58940 }, { "epoch": 14.15, "learning_rate": 9.316527943377837e-05, "loss": 0.2181, "step": 58950 }, { "epoch": 14.15, "learning_rate": 9.316301477209906e-05, "loss": 0.206, "step": 58960 }, { "epoch": 14.16, "learning_rate": 9.316074976282203e-05, "loss": 0.2147, "step": 58970 }, { "epoch": 14.16, "learning_rate": 9.315848440596553e-05, "loss": 0.206, "step": 58980 }, { "epoch": 14.16, "learning_rate": 9.31562187015478e-05, "loss": 0.195, "step": 58990 }, { "epoch": 14.16, "learning_rate": 9.315395264958706e-05, "loss": 0.2357, "step": 59000 }, { "epoch": 14.17, "learning_rate": 9.31516862501016e-05, "loss": 0.2046, "step": 59010 }, { "epoch": 14.17, "learning_rate": 9.314941950310964e-05, "loss": 0.2008, "step": 59020 }, { "epoch": 14.17, "learning_rate": 9.314715240862947e-05, "loss": 0.2471, "step": 59030 }, { "epoch": 14.17, "learning_rate": 9.31448849666793e-05, "loss": 0.2204, "step": 59040 }, { "epoch": 14.18, "learning_rate": 9.314261717727743e-05, "loss": 0.1971, "step": 59050 }, { "epoch": 14.18, "learning_rate": 9.31403490404421e-05, "loss": 0.1789, "step": 59060 }, { "epoch": 14.18, "learning_rate": 9.31380805561916e-05, "loss": 0.2324, "step": 59070 }, { "epoch": 14.18, "learning_rate": 9.313581172454417e-05, "loss": 0.2437, "step": 59080 }, { "epoch": 14.18, "learning_rate": 9.313354254551808e-05, "loss": 0.2, "step": 59090 }, { "epoch": 14.19, "learning_rate": 9.313127301913162e-05, "loss": 0.185, "step": 59100 }, { "epoch": 14.19, "learning_rate": 9.312900314540308e-05, "loss": 0.1976, "step": 59110 }, { "epoch": 14.19, "learning_rate": 9.312673292435073e-05, "loss": 0.2228, "step": 59120 }, { "epoch": 14.19, "learning_rate": 9.312446235599282e-05, "loss": 0.2051, "step": 59130 }, { "epoch": 14.2, "learning_rate": 9.312219144034767e-05, "loss": 0.1899, "step": 59140 }, { "epoch": 14.2, "learning_rate": 9.311992017743356e-05, "loss": 0.2214, "step": 59150 }, { "epoch": 14.2, "learning_rate": 9.311764856726879e-05, "loss": 0.2124, "step": 59160 }, { "epoch": 14.2, "learning_rate": 9.311537660987163e-05, "loss": 0.2423, "step": 59170 }, { "epoch": 14.21, "learning_rate": 9.31131043052604e-05, "loss": 0.1833, "step": 59180 }, { "epoch": 14.21, "learning_rate": 9.311083165345337e-05, "loss": 0.1931, "step": 59190 }, { "epoch": 14.21, "learning_rate": 9.310855865446888e-05, "loss": 0.2174, "step": 59200 }, { "epoch": 14.21, "learning_rate": 9.310628530832521e-05, "loss": 0.176, "step": 59210 }, { "epoch": 14.21, "learning_rate": 9.310401161504067e-05, "loss": 0.1963, "step": 59220 }, { "epoch": 14.22, "learning_rate": 9.310173757463357e-05, "loss": 0.2502, "step": 59230 }, { "epoch": 14.22, "learning_rate": 9.309946318712224e-05, "loss": 0.2475, "step": 59240 }, { "epoch": 14.22, "learning_rate": 9.309718845252498e-05, "loss": 0.2331, "step": 59250 }, { "epoch": 14.22, "learning_rate": 9.30949133708601e-05, "loss": 0.2358, "step": 59260 }, { "epoch": 14.23, "learning_rate": 9.309263794214594e-05, "loss": 0.2344, "step": 59270 }, { "epoch": 14.23, "learning_rate": 9.309036216640081e-05, "loss": 0.2519, "step": 59280 }, { "epoch": 14.23, "learning_rate": 9.308808604364305e-05, "loss": 0.227, "step": 59290 }, { "epoch": 14.23, "learning_rate": 9.308580957389099e-05, "loss": 0.1913, "step": 59300 }, { "epoch": 14.23, "learning_rate": 9.308353275716296e-05, "loss": 0.2481, "step": 59310 }, { "epoch": 14.24, "learning_rate": 9.308125559347729e-05, "loss": 0.2102, "step": 59320 }, { "epoch": 14.24, "learning_rate": 9.30789780828523e-05, "loss": 0.2238, "step": 59330 }, { "epoch": 14.24, "learning_rate": 9.307670022530638e-05, "loss": 0.2156, "step": 59340 }, { "epoch": 14.24, "learning_rate": 9.307442202085783e-05, "loss": 0.1772, "step": 59350 }, { "epoch": 14.25, "learning_rate": 9.307214346952502e-05, "loss": 0.199, "step": 59360 }, { "epoch": 14.25, "learning_rate": 9.306986457132629e-05, "loss": 0.2186, "step": 59370 }, { "epoch": 14.25, "learning_rate": 9.306758532628e-05, "loss": 0.2079, "step": 59380 }, { "epoch": 14.25, "learning_rate": 9.306530573440449e-05, "loss": 0.2135, "step": 59390 }, { "epoch": 14.26, "learning_rate": 9.306302579571813e-05, "loss": 0.2276, "step": 59400 }, { "epoch": 14.26, "learning_rate": 9.306074551023928e-05, "loss": 0.1765, "step": 59410 }, { "epoch": 14.26, "learning_rate": 9.30584648779863e-05, "loss": 0.1936, "step": 59420 }, { "epoch": 14.26, "learning_rate": 9.305618389897757e-05, "loss": 0.2451, "step": 59430 }, { "epoch": 14.26, "learning_rate": 9.305390257323144e-05, "loss": 0.189, "step": 59440 }, { "epoch": 14.27, "learning_rate": 9.305162090076627e-05, "loss": 0.2245, "step": 59450 }, { "epoch": 14.27, "learning_rate": 9.304933888160047e-05, "loss": 0.2032, "step": 59460 }, { "epoch": 14.27, "learning_rate": 9.30470565157524e-05, "loss": 0.2055, "step": 59470 }, { "epoch": 14.27, "learning_rate": 9.304477380324044e-05, "loss": 0.2144, "step": 59480 }, { "epoch": 14.28, "learning_rate": 9.304249074408297e-05, "loss": 0.2116, "step": 59490 }, { "epoch": 14.28, "learning_rate": 9.304020733829838e-05, "loss": 0.2251, "step": 59500 }, { "epoch": 14.28, "learning_rate": 9.303792358590506e-05, "loss": 0.2021, "step": 59510 }, { "epoch": 14.28, "learning_rate": 9.30356394869214e-05, "loss": 0.2097, "step": 59520 }, { "epoch": 14.29, "learning_rate": 9.303335504136579e-05, "loss": 0.2079, "step": 59530 }, { "epoch": 14.29, "learning_rate": 9.303107024925663e-05, "loss": 0.225, "step": 59540 }, { "epoch": 14.29, "learning_rate": 9.302878511061232e-05, "loss": 0.222, "step": 59550 }, { "epoch": 14.29, "learning_rate": 9.302649962545128e-05, "loss": 0.2285, "step": 59560 }, { "epoch": 14.29, "learning_rate": 9.302421379379188e-05, "loss": 0.2133, "step": 59570 }, { "epoch": 14.3, "learning_rate": 9.302192761565256e-05, "loss": 0.2168, "step": 59580 }, { "epoch": 14.3, "learning_rate": 9.30196410910517e-05, "loss": 0.2321, "step": 59590 }, { "epoch": 14.3, "learning_rate": 9.301735422000774e-05, "loss": 0.1905, "step": 59600 }, { "epoch": 14.3, "learning_rate": 9.30150670025391e-05, "loss": 0.2254, "step": 59610 }, { "epoch": 14.31, "learning_rate": 9.301277943866417e-05, "loss": 0.1929, "step": 59620 }, { "epoch": 14.31, "learning_rate": 9.30104915284014e-05, "loss": 0.2002, "step": 59630 }, { "epoch": 14.31, "learning_rate": 9.30082032717692e-05, "loss": 0.2388, "step": 59640 }, { "epoch": 14.31, "learning_rate": 9.300591466878599e-05, "loss": 0.1938, "step": 59650 }, { "epoch": 14.31, "learning_rate": 9.300362571947023e-05, "loss": 0.1897, "step": 59660 }, { "epoch": 14.32, "learning_rate": 9.300133642384032e-05, "loss": 0.1876, "step": 59670 }, { "epoch": 14.32, "learning_rate": 9.299904678191472e-05, "loss": 0.2312, "step": 59680 }, { "epoch": 14.32, "learning_rate": 9.299675679371186e-05, "loss": 0.1837, "step": 59690 }, { "epoch": 14.32, "learning_rate": 9.299446645925017e-05, "loss": 0.2084, "step": 59700 }, { "epoch": 14.33, "learning_rate": 9.299217577854812e-05, "loss": 0.2367, "step": 59710 }, { "epoch": 14.33, "learning_rate": 9.298988475162414e-05, "loss": 0.2055, "step": 59720 }, { "epoch": 14.33, "learning_rate": 9.298759337849668e-05, "loss": 0.229, "step": 59730 }, { "epoch": 14.33, "learning_rate": 9.29853016591842e-05, "loss": 0.1913, "step": 59740 }, { "epoch": 14.34, "learning_rate": 9.298300959370514e-05, "loss": 0.2222, "step": 59750 }, { "epoch": 14.34, "learning_rate": 9.298071718207799e-05, "loss": 0.2302, "step": 59760 }, { "epoch": 14.34, "learning_rate": 9.297842442432116e-05, "loss": 0.2169, "step": 59770 }, { "epoch": 14.34, "learning_rate": 9.297613132045318e-05, "loss": 0.2464, "step": 59780 }, { "epoch": 14.34, "learning_rate": 9.297383787049245e-05, "loss": 0.2088, "step": 59790 }, { "epoch": 14.35, "learning_rate": 9.29715440744575e-05, "loss": 0.2004, "step": 59800 }, { "epoch": 14.35, "learning_rate": 9.296924993236675e-05, "loss": 0.2249, "step": 59810 }, { "epoch": 14.35, "learning_rate": 9.29669554442387e-05, "loss": 0.2072, "step": 59820 }, { "epoch": 14.35, "learning_rate": 9.296466061009183e-05, "loss": 0.1958, "step": 59830 }, { "epoch": 14.36, "learning_rate": 9.296236542994463e-05, "loss": 0.2554, "step": 59840 }, { "epoch": 14.36, "learning_rate": 9.296006990381556e-05, "loss": 0.1844, "step": 59850 }, { "epoch": 14.36, "learning_rate": 9.29577740317231e-05, "loss": 0.1656, "step": 59860 }, { "epoch": 14.36, "learning_rate": 9.295547781368576e-05, "loss": 0.2109, "step": 59870 }, { "epoch": 14.37, "learning_rate": 9.295318124972205e-05, "loss": 0.2016, "step": 59880 }, { "epoch": 14.37, "learning_rate": 9.295088433985042e-05, "loss": 0.2398, "step": 59890 }, { "epoch": 14.37, "learning_rate": 9.29485870840894e-05, "loss": 0.2418, "step": 59900 }, { "epoch": 14.37, "learning_rate": 9.294628948245747e-05, "loss": 0.1787, "step": 59910 }, { "epoch": 14.37, "learning_rate": 9.294399153497315e-05, "loss": 0.1934, "step": 59920 }, { "epoch": 14.38, "learning_rate": 9.294169324165493e-05, "loss": 0.2532, "step": 59930 }, { "epoch": 14.38, "learning_rate": 9.293939460252134e-05, "loss": 0.2013, "step": 59940 }, { "epoch": 14.38, "learning_rate": 9.293709561759085e-05, "loss": 0.2159, "step": 59950 }, { "epoch": 14.38, "learning_rate": 9.293479628688201e-05, "loss": 0.192, "step": 59960 }, { "epoch": 14.39, "learning_rate": 9.293249661041335e-05, "loss": 0.214, "step": 59970 }, { "epoch": 14.39, "learning_rate": 9.293019658820336e-05, "loss": 0.2426, "step": 59980 }, { "epoch": 14.39, "learning_rate": 9.292789622027056e-05, "loss": 0.1953, "step": 59990 }, { "epoch": 14.39, "learning_rate": 9.292559550663349e-05, "loss": 0.2248, "step": 60000 }, { "epoch": 14.39, "learning_rate": 9.292329444731067e-05, "loss": 0.2206, "step": 60010 }, { "epoch": 14.4, "learning_rate": 9.292099304232064e-05, "loss": 0.2085, "step": 60020 }, { "epoch": 14.4, "learning_rate": 9.291869129168192e-05, "loss": 0.2088, "step": 60030 }, { "epoch": 14.4, "learning_rate": 9.291638919541306e-05, "loss": 0.1944, "step": 60040 }, { "epoch": 14.4, "learning_rate": 9.291408675353258e-05, "loss": 0.2174, "step": 60050 }, { "epoch": 14.41, "learning_rate": 9.291178396605904e-05, "loss": 0.2762, "step": 60060 }, { "epoch": 14.41, "learning_rate": 9.290948083301098e-05, "loss": 0.1906, "step": 60070 }, { "epoch": 14.41, "learning_rate": 9.290717735440695e-05, "loss": 0.2088, "step": 60080 }, { "epoch": 14.41, "learning_rate": 9.290487353026551e-05, "loss": 0.2256, "step": 60090 }, { "epoch": 14.42, "learning_rate": 9.290256936060518e-05, "loss": 0.215, "step": 60100 }, { "epoch": 14.42, "learning_rate": 9.290026484544455e-05, "loss": 0.2189, "step": 60110 }, { "epoch": 14.42, "learning_rate": 9.289795998480216e-05, "loss": 0.1976, "step": 60120 }, { "epoch": 14.42, "learning_rate": 9.289565477869658e-05, "loss": 0.2225, "step": 60130 }, { "epoch": 14.42, "learning_rate": 9.289334922714635e-05, "loss": 0.2237, "step": 60140 }, { "epoch": 14.43, "learning_rate": 9.289104333017007e-05, "loss": 0.1771, "step": 60150 }, { "epoch": 14.43, "learning_rate": 9.288873708778631e-05, "loss": 0.2066, "step": 60160 }, { "epoch": 14.43, "learning_rate": 9.288643050001361e-05, "loss": 0.2404, "step": 60170 }, { "epoch": 14.43, "learning_rate": 9.288412356687058e-05, "loss": 0.1919, "step": 60180 }, { "epoch": 14.44, "learning_rate": 9.288181628837575e-05, "loss": 0.1946, "step": 60190 }, { "epoch": 14.44, "learning_rate": 9.287950866454778e-05, "loss": 0.1818, "step": 60200 }, { "epoch": 14.44, "learning_rate": 9.287720069540517e-05, "loss": 0.1981, "step": 60210 }, { "epoch": 14.44, "learning_rate": 9.287489238096656e-05, "loss": 0.2277, "step": 60220 }, { "epoch": 14.45, "learning_rate": 9.287258372125052e-05, "loss": 0.2275, "step": 60230 }, { "epoch": 14.45, "learning_rate": 9.287027471627563e-05, "loss": 0.2073, "step": 60240 }, { "epoch": 14.45, "learning_rate": 9.286796536606053e-05, "loss": 0.2152, "step": 60250 }, { "epoch": 14.45, "learning_rate": 9.286565567062375e-05, "loss": 0.2167, "step": 60260 }, { "epoch": 14.45, "learning_rate": 9.286334562998395e-05, "loss": 0.2273, "step": 60270 }, { "epoch": 14.46, "learning_rate": 9.286103524415971e-05, "loss": 0.1642, "step": 60280 }, { "epoch": 14.46, "learning_rate": 9.285872451316963e-05, "loss": 0.2166, "step": 60290 }, { "epoch": 14.46, "learning_rate": 9.285641343703232e-05, "loss": 0.2416, "step": 60300 }, { "epoch": 14.46, "learning_rate": 9.285410201576642e-05, "loss": 0.1942, "step": 60310 }, { "epoch": 14.47, "learning_rate": 9.285179024939048e-05, "loss": 0.1806, "step": 60320 }, { "epoch": 14.47, "learning_rate": 9.28494781379232e-05, "loss": 0.196, "step": 60330 }, { "epoch": 14.47, "learning_rate": 9.284716568138312e-05, "loss": 0.2049, "step": 60340 }, { "epoch": 14.47, "learning_rate": 9.284485287978892e-05, "loss": 0.2493, "step": 60350 }, { "epoch": 14.47, "learning_rate": 9.28425397331592e-05, "loss": 0.1765, "step": 60360 }, { "epoch": 14.48, "learning_rate": 9.284022624151258e-05, "loss": 0.2335, "step": 60370 }, { "epoch": 14.48, "learning_rate": 9.283791240486772e-05, "loss": 0.2256, "step": 60380 }, { "epoch": 14.48, "learning_rate": 9.283559822324324e-05, "loss": 0.1947, "step": 60390 }, { "epoch": 14.48, "learning_rate": 9.283328369665777e-05, "loss": 0.2021, "step": 60400 }, { "epoch": 14.49, "learning_rate": 9.283096882512995e-05, "loss": 0.2135, "step": 60410 }, { "epoch": 14.49, "learning_rate": 9.282865360867842e-05, "loss": 0.1862, "step": 60420 }, { "epoch": 14.49, "learning_rate": 9.282633804732183e-05, "loss": 0.1516, "step": 60430 }, { "epoch": 14.49, "learning_rate": 9.282402214107884e-05, "loss": 0.2545, "step": 60440 }, { "epoch": 14.5, "learning_rate": 9.282170588996808e-05, "loss": 0.2141, "step": 60450 }, { "epoch": 14.5, "learning_rate": 9.281938929400821e-05, "loss": 0.2208, "step": 60460 }, { "epoch": 14.5, "learning_rate": 9.281707235321789e-05, "loss": 0.1996, "step": 60470 }, { "epoch": 14.5, "learning_rate": 9.281475506761577e-05, "loss": 0.1723, "step": 60480 }, { "epoch": 14.5, "learning_rate": 9.281243743722051e-05, "loss": 0.1665, "step": 60490 }, { "epoch": 14.51, "learning_rate": 9.28101194620508e-05, "loss": 0.2504, "step": 60500 }, { "epoch": 14.51, "learning_rate": 9.280780114212526e-05, "loss": 0.2117, "step": 60510 }, { "epoch": 14.51, "learning_rate": 9.280548247746261e-05, "loss": 0.2063, "step": 60520 }, { "epoch": 14.51, "learning_rate": 9.280316346808149e-05, "loss": 0.2025, "step": 60530 }, { "epoch": 14.52, "learning_rate": 9.280084411400059e-05, "loss": 0.1886, "step": 60540 }, { "epoch": 14.52, "learning_rate": 9.279852441523857e-05, "loss": 0.1728, "step": 60550 }, { "epoch": 14.52, "learning_rate": 9.279620437181416e-05, "loss": 0.1599, "step": 60560 }, { "epoch": 14.52, "learning_rate": 9.279388398374598e-05, "loss": 0.2275, "step": 60570 }, { "epoch": 14.53, "learning_rate": 9.279156325105273e-05, "loss": 0.1889, "step": 60580 }, { "epoch": 14.53, "learning_rate": 9.278924217375315e-05, "loss": 0.1835, "step": 60590 }, { "epoch": 14.53, "learning_rate": 9.278692075186587e-05, "loss": 0.2106, "step": 60600 }, { "epoch": 14.53, "learning_rate": 9.278459898540961e-05, "loss": 0.2203, "step": 60610 }, { "epoch": 14.53, "learning_rate": 9.278227687440309e-05, "loss": 0.243, "step": 60620 }, { "epoch": 14.54, "learning_rate": 9.277995441886496e-05, "loss": 0.2801, "step": 60630 }, { "epoch": 14.54, "learning_rate": 9.277763161881397e-05, "loss": 0.2822, "step": 60640 }, { "epoch": 14.54, "learning_rate": 9.27753084742688e-05, "loss": 0.2903, "step": 60650 }, { "epoch": 14.54, "learning_rate": 9.277298498524816e-05, "loss": 0.2481, "step": 60660 }, { "epoch": 14.55, "learning_rate": 9.277066115177078e-05, "loss": 0.2958, "step": 60670 }, { "epoch": 14.55, "learning_rate": 9.276833697385534e-05, "loss": 0.3138, "step": 60680 }, { "epoch": 14.55, "learning_rate": 9.27660124515206e-05, "loss": 0.2307, "step": 60690 }, { "epoch": 14.55, "learning_rate": 9.276368758478524e-05, "loss": 0.2368, "step": 60700 }, { "epoch": 14.55, "learning_rate": 9.276136237366802e-05, "loss": 0.267, "step": 60710 }, { "epoch": 14.56, "learning_rate": 9.275903681818763e-05, "loss": 0.2447, "step": 60720 }, { "epoch": 14.56, "learning_rate": 9.275671091836282e-05, "loss": 0.2737, "step": 60730 }, { "epoch": 14.56, "learning_rate": 9.275438467421231e-05, "loss": 0.1931, "step": 60740 }, { "epoch": 14.56, "learning_rate": 9.275205808575483e-05, "loss": 0.271, "step": 60750 }, { "epoch": 14.57, "learning_rate": 9.274973115300914e-05, "loss": 0.2925, "step": 60760 }, { "epoch": 14.57, "learning_rate": 9.274740387599395e-05, "loss": 0.244, "step": 60770 }, { "epoch": 14.57, "learning_rate": 9.274507625472803e-05, "loss": 0.2482, "step": 60780 }, { "epoch": 14.57, "learning_rate": 9.27427482892301e-05, "loss": 0.2495, "step": 60790 }, { "epoch": 14.58, "learning_rate": 9.27404199795189e-05, "loss": 0.261, "step": 60800 }, { "epoch": 14.58, "learning_rate": 9.273809132561322e-05, "loss": 0.2852, "step": 60810 }, { "epoch": 14.58, "learning_rate": 9.273576232753179e-05, "loss": 0.2569, "step": 60820 }, { "epoch": 14.58, "learning_rate": 9.273343298529335e-05, "loss": 0.1964, "step": 60830 }, { "epoch": 14.58, "learning_rate": 9.27311032989167e-05, "loss": 0.2688, "step": 60840 }, { "epoch": 14.59, "learning_rate": 9.272877326842055e-05, "loss": 0.2953, "step": 60850 }, { "epoch": 14.59, "learning_rate": 9.27264428938237e-05, "loss": 0.269, "step": 60860 }, { "epoch": 14.59, "learning_rate": 9.272411217514492e-05, "loss": 0.2127, "step": 60870 }, { "epoch": 14.59, "learning_rate": 9.272178111240294e-05, "loss": 0.2688, "step": 60880 }, { "epoch": 14.6, "learning_rate": 9.271944970561658e-05, "loss": 0.2759, "step": 60890 }, { "epoch": 14.6, "learning_rate": 9.271711795480457e-05, "loss": 0.2323, "step": 60900 }, { "epoch": 14.6, "learning_rate": 9.271478585998574e-05, "loss": 0.1965, "step": 60910 }, { "epoch": 14.6, "learning_rate": 9.271245342117882e-05, "loss": 0.2733, "step": 60920 }, { "epoch": 14.61, "learning_rate": 9.271012063840263e-05, "loss": 0.2674, "step": 60930 }, { "epoch": 14.61, "learning_rate": 9.270778751167595e-05, "loss": 0.2542, "step": 60940 }, { "epoch": 14.61, "learning_rate": 9.270545404101754e-05, "loss": 0.2272, "step": 60950 }, { "epoch": 14.61, "learning_rate": 9.270312022644623e-05, "loss": 0.2412, "step": 60960 }, { "epoch": 14.61, "learning_rate": 9.270078606798078e-05, "loss": 0.2852, "step": 60970 }, { "epoch": 14.62, "learning_rate": 9.269845156564001e-05, "loss": 0.2508, "step": 60980 }, { "epoch": 14.62, "learning_rate": 9.269611671944271e-05, "loss": 0.2425, "step": 60990 }, { "epoch": 14.62, "learning_rate": 9.26937815294077e-05, "loss": 0.1913, "step": 61000 }, { "epoch": 14.62, "learning_rate": 9.269144599555377e-05, "loss": 0.2224, "step": 61010 }, { "epoch": 14.63, "learning_rate": 9.268911011789974e-05, "loss": 0.2955, "step": 61020 }, { "epoch": 14.63, "learning_rate": 9.26867738964644e-05, "loss": 0.2578, "step": 61030 }, { "epoch": 14.63, "learning_rate": 9.268443733126657e-05, "loss": 0.1773, "step": 61040 }, { "epoch": 14.63, "learning_rate": 9.26821004223251e-05, "loss": 0.23, "step": 61050 }, { "epoch": 14.63, "learning_rate": 9.267976316965875e-05, "loss": 0.2697, "step": 61060 }, { "epoch": 14.64, "learning_rate": 9.267742557328639e-05, "loss": 0.2384, "step": 61070 }, { "epoch": 14.64, "learning_rate": 9.267508763322684e-05, "loss": 0.255, "step": 61080 }, { "epoch": 14.64, "learning_rate": 9.26727493494989e-05, "loss": 0.2557, "step": 61090 }, { "epoch": 14.64, "learning_rate": 9.267041072212143e-05, "loss": 0.2443, "step": 61100 }, { "epoch": 14.65, "learning_rate": 9.266807175111324e-05, "loss": 0.2628, "step": 61110 }, { "epoch": 14.65, "learning_rate": 9.266573243649319e-05, "loss": 0.281, "step": 61120 }, { "epoch": 14.65, "learning_rate": 9.266339277828009e-05, "loss": 0.2739, "step": 61130 }, { "epoch": 14.65, "learning_rate": 9.266105277649282e-05, "loss": 0.2568, "step": 61140 }, { "epoch": 14.66, "learning_rate": 9.265871243115019e-05, "loss": 0.2311, "step": 61150 }, { "epoch": 14.66, "learning_rate": 9.265637174227106e-05, "loss": 0.2451, "step": 61160 }, { "epoch": 14.66, "learning_rate": 9.265403070987427e-05, "loss": 0.2903, "step": 61170 }, { "epoch": 14.66, "learning_rate": 9.26516893339787e-05, "loss": 0.2424, "step": 61180 }, { "epoch": 14.66, "learning_rate": 9.264934761460317e-05, "loss": 0.2601, "step": 61190 }, { "epoch": 14.67, "learning_rate": 9.264700555176658e-05, "loss": 0.209, "step": 61200 }, { "epoch": 14.67, "learning_rate": 9.264466314548774e-05, "loss": 0.2314, "step": 61210 }, { "epoch": 14.67, "learning_rate": 9.264232039578556e-05, "loss": 0.2473, "step": 61220 }, { "epoch": 14.67, "learning_rate": 9.263997730267887e-05, "loss": 0.2216, "step": 61230 }, { "epoch": 14.68, "learning_rate": 9.263763386618656e-05, "loss": 0.2424, "step": 61240 }, { "epoch": 14.68, "learning_rate": 9.26352900863275e-05, "loss": 0.3073, "step": 61250 }, { "epoch": 14.68, "learning_rate": 9.263294596312057e-05, "loss": 0.1925, "step": 61260 }, { "epoch": 14.68, "learning_rate": 9.263060149658462e-05, "loss": 0.2296, "step": 61270 }, { "epoch": 14.69, "learning_rate": 9.262825668673858e-05, "loss": 0.2986, "step": 61280 }, { "epoch": 14.69, "learning_rate": 9.262591153360129e-05, "loss": 0.2473, "step": 61290 }, { "epoch": 14.69, "learning_rate": 9.262356603719164e-05, "loss": 0.251, "step": 61300 }, { "epoch": 14.69, "learning_rate": 9.262122019752855e-05, "loss": 0.2378, "step": 61310 }, { "epoch": 14.69, "learning_rate": 9.261887401463088e-05, "loss": 0.2304, "step": 61320 }, { "epoch": 14.7, "learning_rate": 9.261652748851753e-05, "loss": 0.2507, "step": 61330 }, { "epoch": 14.7, "learning_rate": 9.26141806192074e-05, "loss": 0.267, "step": 61340 }, { "epoch": 14.7, "learning_rate": 9.261183340671937e-05, "loss": 0.1955, "step": 61350 }, { "epoch": 14.7, "learning_rate": 9.260948585107238e-05, "loss": 0.2308, "step": 61360 }, { "epoch": 14.71, "learning_rate": 9.260713795228533e-05, "loss": 0.2038, "step": 61370 }, { "epoch": 14.71, "learning_rate": 9.260478971037711e-05, "loss": 0.254, "step": 61380 }, { "epoch": 14.71, "learning_rate": 9.260244112536664e-05, "loss": 0.2165, "step": 61390 }, { "epoch": 14.71, "learning_rate": 9.260009219727282e-05, "loss": 0.2844, "step": 61400 }, { "epoch": 14.71, "learning_rate": 9.259774292611458e-05, "loss": 0.2461, "step": 61410 }, { "epoch": 14.72, "learning_rate": 9.259539331191082e-05, "loss": 0.3119, "step": 61420 }, { "epoch": 14.72, "learning_rate": 9.259304335468051e-05, "loss": 0.2721, "step": 61430 }, { "epoch": 14.72, "learning_rate": 9.259069305444252e-05, "loss": 0.2302, "step": 61440 }, { "epoch": 14.72, "learning_rate": 9.25883424112158e-05, "loss": 0.2381, "step": 61450 }, { "epoch": 14.73, "learning_rate": 9.258599142501928e-05, "loss": 0.246, "step": 61460 }, { "epoch": 14.73, "learning_rate": 9.258364009587189e-05, "loss": 0.2482, "step": 61470 }, { "epoch": 14.73, "learning_rate": 9.258128842379257e-05, "loss": 0.2274, "step": 61480 }, { "epoch": 14.73, "learning_rate": 9.257893640880027e-05, "loss": 0.2627, "step": 61490 }, { "epoch": 14.74, "learning_rate": 9.257658405091389e-05, "loss": 0.2786, "step": 61500 }, { "epoch": 14.74, "learning_rate": 9.257423135015241e-05, "loss": 0.2763, "step": 61510 }, { "epoch": 14.74, "learning_rate": 9.257187830653478e-05, "loss": 0.2246, "step": 61520 }, { "epoch": 14.74, "learning_rate": 9.256952492007992e-05, "loss": 0.2472, "step": 61530 }, { "epoch": 14.74, "learning_rate": 9.25671711908068e-05, "loss": 0.2646, "step": 61540 }, { "epoch": 14.75, "learning_rate": 9.256481711873439e-05, "loss": 0.2528, "step": 61550 }, { "epoch": 14.75, "learning_rate": 9.256246270388161e-05, "loss": 0.2296, "step": 61560 }, { "epoch": 14.75, "learning_rate": 9.256010794626747e-05, "loss": 0.2311, "step": 61570 }, { "epoch": 14.75, "learning_rate": 9.255775284591088e-05, "loss": 0.2467, "step": 61580 }, { "epoch": 14.76, "learning_rate": 9.255539740283083e-05, "loss": 0.2565, "step": 61590 }, { "epoch": 14.76, "learning_rate": 9.25530416170463e-05, "loss": 0.1988, "step": 61600 }, { "epoch": 14.76, "learning_rate": 9.255068548857625e-05, "loss": 0.2138, "step": 61610 }, { "epoch": 14.76, "learning_rate": 9.254832901743966e-05, "loss": 0.2125, "step": 61620 }, { "epoch": 14.77, "learning_rate": 9.254597220365549e-05, "loss": 0.2208, "step": 61630 }, { "epoch": 14.77, "learning_rate": 9.254361504724273e-05, "loss": 0.258, "step": 61640 }, { "epoch": 14.77, "learning_rate": 9.254125754822039e-05, "loss": 0.2294, "step": 61650 }, { "epoch": 14.77, "learning_rate": 9.253889970660741e-05, "loss": 0.2228, "step": 61660 }, { "epoch": 14.77, "learning_rate": 9.253654152242279e-05, "loss": 0.2216, "step": 61670 }, { "epoch": 14.78, "learning_rate": 9.253418299568555e-05, "loss": 0.2085, "step": 61680 }, { "epoch": 14.78, "learning_rate": 9.253182412641464e-05, "loss": 0.2275, "step": 61690 }, { "epoch": 14.78, "learning_rate": 9.252946491462909e-05, "loss": 0.2232, "step": 61700 }, { "epoch": 14.78, "learning_rate": 9.25271053603479e-05, "loss": 0.229, "step": 61710 }, { "epoch": 14.79, "learning_rate": 9.252474546359004e-05, "loss": 0.2675, "step": 61720 }, { "epoch": 14.79, "learning_rate": 9.252238522437453e-05, "loss": 0.2053, "step": 61730 }, { "epoch": 14.79, "learning_rate": 9.25200246427204e-05, "loss": 0.1749, "step": 61740 }, { "epoch": 14.79, "learning_rate": 9.251766371864663e-05, "loss": 0.2934, "step": 61750 }, { "epoch": 14.79, "learning_rate": 9.251530245217225e-05, "loss": 0.173, "step": 61760 }, { "epoch": 14.8, "learning_rate": 9.251294084331627e-05, "loss": 0.243, "step": 61770 }, { "epoch": 14.8, "learning_rate": 9.25105788920977e-05, "loss": 0.2461, "step": 61780 }, { "epoch": 14.8, "learning_rate": 9.250821659853556e-05, "loss": 0.2018, "step": 61790 }, { "epoch": 14.8, "learning_rate": 9.250585396264891e-05, "loss": 0.2384, "step": 61800 }, { "epoch": 14.81, "learning_rate": 9.250349098445674e-05, "loss": 0.2626, "step": 61810 }, { "epoch": 14.81, "learning_rate": 9.250112766397808e-05, "loss": 0.214, "step": 61820 }, { "epoch": 14.81, "learning_rate": 9.249876400123198e-05, "loss": 0.2166, "step": 61830 }, { "epoch": 14.81, "learning_rate": 9.249639999623747e-05, "loss": 0.2073, "step": 61840 }, { "epoch": 14.82, "learning_rate": 9.249403564901358e-05, "loss": 0.1869, "step": 61850 }, { "epoch": 14.82, "learning_rate": 9.249167095957934e-05, "loss": 0.2802, "step": 61860 }, { "epoch": 14.82, "learning_rate": 9.248930592795382e-05, "loss": 0.1977, "step": 61870 }, { "epoch": 14.82, "learning_rate": 9.248694055415605e-05, "loss": 0.2317, "step": 61880 }, { "epoch": 14.82, "learning_rate": 9.248457483820509e-05, "loss": 0.2592, "step": 61890 }, { "epoch": 14.83, "learning_rate": 9.248220878011997e-05, "loss": 0.2344, "step": 61900 }, { "epoch": 14.83, "learning_rate": 9.247984237991977e-05, "loss": 0.1849, "step": 61910 }, { "epoch": 14.83, "learning_rate": 9.247747563762353e-05, "loss": 0.199, "step": 61920 }, { "epoch": 14.83, "learning_rate": 9.247510855325032e-05, "loss": 0.2168, "step": 61930 }, { "epoch": 14.84, "learning_rate": 9.247274112681918e-05, "loss": 0.229, "step": 61940 }, { "epoch": 14.84, "learning_rate": 9.24703733583492e-05, "loss": 0.2433, "step": 61950 }, { "epoch": 14.84, "learning_rate": 9.246800524785946e-05, "loss": 0.2784, "step": 61960 }, { "epoch": 14.84, "learning_rate": 9.246563679536899e-05, "loss": 0.2471, "step": 61970 }, { "epoch": 14.85, "learning_rate": 9.246326800089689e-05, "loss": 0.1885, "step": 61980 }, { "epoch": 14.85, "learning_rate": 9.246089886446221e-05, "loss": 0.2055, "step": 61990 }, { "epoch": 14.85, "learning_rate": 9.245852938608408e-05, "loss": 0.2101, "step": 62000 }, { "epoch": 14.85, "learning_rate": 9.245615956578152e-05, "loss": 0.2716, "step": 62010 }, { "epoch": 14.85, "learning_rate": 9.245378940357368e-05, "loss": 0.2124, "step": 62020 }, { "epoch": 14.86, "learning_rate": 9.24514188994796e-05, "loss": 0.2138, "step": 62030 }, { "epoch": 14.86, "learning_rate": 9.244904805351837e-05, "loss": 0.155, "step": 62040 }, { "epoch": 14.86, "learning_rate": 9.244667686570911e-05, "loss": 0.2607, "step": 62050 }, { "epoch": 14.86, "learning_rate": 9.244430533607089e-05, "loss": 0.2215, "step": 62060 }, { "epoch": 14.87, "learning_rate": 9.244193346462284e-05, "loss": 0.2087, "step": 62070 }, { "epoch": 14.87, "learning_rate": 9.243956125138402e-05, "loss": 0.1928, "step": 62080 }, { "epoch": 14.87, "learning_rate": 9.243718869637357e-05, "loss": 0.2684, "step": 62090 }, { "epoch": 14.87, "learning_rate": 9.243481579961057e-05, "loss": 0.2457, "step": 62100 }, { "epoch": 14.87, "learning_rate": 9.243244256111412e-05, "loss": 0.2273, "step": 62110 }, { "epoch": 14.88, "learning_rate": 9.243006898090338e-05, "loss": 0.254, "step": 62120 }, { "epoch": 14.88, "learning_rate": 9.242769505899743e-05, "loss": 0.2478, "step": 62130 }, { "epoch": 14.88, "learning_rate": 9.242532079541539e-05, "loss": 0.2436, "step": 62140 }, { "epoch": 14.88, "learning_rate": 9.24229461901764e-05, "loss": 0.2321, "step": 62150 }, { "epoch": 14.89, "learning_rate": 9.242057124329954e-05, "loss": 0.195, "step": 62160 }, { "epoch": 14.89, "learning_rate": 9.241819595480399e-05, "loss": 0.2479, "step": 62170 }, { "epoch": 14.89, "learning_rate": 9.241582032470884e-05, "loss": 0.2352, "step": 62180 }, { "epoch": 14.89, "learning_rate": 9.241344435303323e-05, "loss": 0.2084, "step": 62190 }, { "epoch": 14.9, "learning_rate": 9.24110680397963e-05, "loss": 0.1766, "step": 62200 }, { "epoch": 14.9, "learning_rate": 9.240869138501719e-05, "loss": 0.2679, "step": 62210 }, { "epoch": 14.9, "learning_rate": 9.240631438871504e-05, "loss": 0.1935, "step": 62220 }, { "epoch": 14.9, "learning_rate": 9.240393705090896e-05, "loss": 0.2484, "step": 62230 }, { "epoch": 14.9, "learning_rate": 9.240155937161813e-05, "loss": 0.2094, "step": 62240 }, { "epoch": 14.91, "learning_rate": 9.239918135086169e-05, "loss": 0.2143, "step": 62250 }, { "epoch": 14.91, "learning_rate": 9.239680298865879e-05, "loss": 0.208, "step": 62260 }, { "epoch": 14.91, "learning_rate": 9.239442428502859e-05, "loss": 0.1985, "step": 62270 }, { "epoch": 14.91, "learning_rate": 9.239204523999023e-05, "loss": 0.2354, "step": 62280 }, { "epoch": 14.92, "learning_rate": 9.238966585356288e-05, "loss": 0.2427, "step": 62290 }, { "epoch": 14.92, "learning_rate": 9.238728612576571e-05, "loss": 0.1961, "step": 62300 }, { "epoch": 14.92, "learning_rate": 9.238490605661785e-05, "loss": 0.1826, "step": 62310 }, { "epoch": 14.92, "learning_rate": 9.23825256461385e-05, "loss": 0.2136, "step": 62320 }, { "epoch": 14.93, "learning_rate": 9.238014489434683e-05, "loss": 0.2024, "step": 62330 }, { "epoch": 14.93, "learning_rate": 9.237776380126198e-05, "loss": 0.1882, "step": 62340 }, { "epoch": 14.93, "learning_rate": 9.237538236690316e-05, "loss": 0.2042, "step": 62350 }, { "epoch": 14.93, "learning_rate": 9.237300059128954e-05, "loss": 0.2158, "step": 62360 }, { "epoch": 14.93, "learning_rate": 9.237061847444028e-05, "loss": 0.2192, "step": 62370 }, { "epoch": 14.94, "learning_rate": 9.236823601637461e-05, "loss": 0.2203, "step": 62380 }, { "epoch": 14.94, "learning_rate": 9.236585321711167e-05, "loss": 0.1859, "step": 62390 }, { "epoch": 14.94, "learning_rate": 9.236347007667066e-05, "loss": 0.1921, "step": 62400 }, { "epoch": 14.94, "learning_rate": 9.236108659507077e-05, "loss": 0.2104, "step": 62410 }, { "epoch": 14.95, "learning_rate": 9.235870277233121e-05, "loss": 0.2321, "step": 62420 }, { "epoch": 14.95, "learning_rate": 9.235631860847118e-05, "loss": 0.2015, "step": 62430 }, { "epoch": 14.95, "learning_rate": 9.235393410350985e-05, "loss": 0.2306, "step": 62440 }, { "epoch": 15.0, "learning_rate": 9.235154925746645e-05, "loss": 0.1996, "step": 62450 }, { "epoch": 15.0, "learning_rate": 9.234916407036018e-05, "loss": 0.2028, "step": 62460 }, { "epoch": 15.01, "learning_rate": 9.234677854221023e-05, "loss": 0.1894, "step": 62470 }, { "epoch": 15.01, "learning_rate": 9.234439267303585e-05, "loss": 0.194, "step": 62480 }, { "epoch": 15.01, "learning_rate": 9.234200646285623e-05, "loss": 0.2119, "step": 62490 }, { "epoch": 15.01, "learning_rate": 9.233961991169055e-05, "loss": 0.1933, "step": 62500 }, { "epoch": 15.01, "learning_rate": 9.23372330195581e-05, "loss": 0.1981, "step": 62510 }, { "epoch": 15.02, "learning_rate": 9.233484578647806e-05, "loss": 0.2052, "step": 62520 }, { "epoch": 15.02, "learning_rate": 9.233245821246966e-05, "loss": 0.2144, "step": 62530 }, { "epoch": 15.02, "learning_rate": 9.233007029755211e-05, "loss": 0.2217, "step": 62540 }, { "epoch": 15.02, "learning_rate": 9.23276820417447e-05, "loss": 0.2201, "step": 62550 }, { "epoch": 15.03, "learning_rate": 9.23252934450666e-05, "loss": 0.181, "step": 62560 }, { "epoch": 15.03, "learning_rate": 9.232290450753707e-05, "loss": 0.2018, "step": 62570 }, { "epoch": 15.03, "learning_rate": 9.232051522917533e-05, "loss": 0.2, "step": 62580 }, { "epoch": 15.03, "learning_rate": 9.231812561000066e-05, "loss": 0.182, "step": 62590 }, { "epoch": 15.04, "learning_rate": 9.231573565003228e-05, "loss": 0.1885, "step": 62600 }, { "epoch": 15.04, "learning_rate": 9.231334534928944e-05, "loss": 0.1801, "step": 62610 }, { "epoch": 15.04, "learning_rate": 9.231095470779138e-05, "loss": 0.2168, "step": 62620 }, { "epoch": 15.04, "learning_rate": 9.230856372555736e-05, "loss": 0.2016, "step": 62630 }, { "epoch": 15.04, "learning_rate": 9.230617240260664e-05, "loss": 0.2173, "step": 62640 }, { "epoch": 15.05, "learning_rate": 9.230378073895847e-05, "loss": 0.2293, "step": 62650 }, { "epoch": 15.05, "learning_rate": 9.230138873463213e-05, "loss": 0.2047, "step": 62660 }, { "epoch": 15.05, "learning_rate": 9.229899638964685e-05, "loss": 0.1805, "step": 62670 }, { "epoch": 15.05, "learning_rate": 9.229660370402191e-05, "loss": 0.206, "step": 62680 }, { "epoch": 15.06, "learning_rate": 9.229421067777658e-05, "loss": 0.184, "step": 62690 }, { "epoch": 15.06, "learning_rate": 9.229181731093014e-05, "loss": 0.2628, "step": 62700 }, { "epoch": 15.06, "learning_rate": 9.228942360350185e-05, "loss": 0.2134, "step": 62710 }, { "epoch": 15.06, "learning_rate": 9.228702955551101e-05, "loss": 0.1904, "step": 62720 }, { "epoch": 15.07, "learning_rate": 9.228463516697686e-05, "loss": 0.2402, "step": 62730 }, { "epoch": 15.07, "learning_rate": 9.228224043791872e-05, "loss": 0.155, "step": 62740 }, { "epoch": 15.07, "learning_rate": 9.227984536835586e-05, "loss": 0.1671, "step": 62750 }, { "epoch": 15.07, "learning_rate": 9.227744995830756e-05, "loss": 0.2028, "step": 62760 }, { "epoch": 15.07, "learning_rate": 9.227505420779313e-05, "loss": 0.1897, "step": 62770 }, { "epoch": 15.08, "learning_rate": 9.227265811683184e-05, "loss": 0.175, "step": 62780 }, { "epoch": 15.08, "learning_rate": 9.227026168544299e-05, "loss": 0.2228, "step": 62790 }, { "epoch": 15.08, "learning_rate": 9.22678649136459e-05, "loss": 0.1699, "step": 62800 }, { "epoch": 15.08, "learning_rate": 9.226546780145985e-05, "loss": 0.215, "step": 62810 }, { "epoch": 15.09, "learning_rate": 9.226307034890417e-05, "loss": 0.1764, "step": 62820 }, { "epoch": 15.09, "learning_rate": 9.226067255599814e-05, "loss": 0.2082, "step": 62830 }, { "epoch": 15.09, "learning_rate": 9.22582744227611e-05, "loss": 0.2289, "step": 62840 }, { "epoch": 15.09, "learning_rate": 9.22558759492123e-05, "loss": 0.1869, "step": 62850 }, { "epoch": 15.09, "learning_rate": 9.225347713537113e-05, "loss": 0.1751, "step": 62860 }, { "epoch": 15.1, "learning_rate": 9.225107798125686e-05, "loss": 0.1777, "step": 62870 }, { "epoch": 15.1, "learning_rate": 9.224867848688883e-05, "loss": 0.2234, "step": 62880 }, { "epoch": 15.1, "learning_rate": 9.224627865228637e-05, "loss": 0.2147, "step": 62890 }, { "epoch": 15.1, "learning_rate": 9.224387847746878e-05, "loss": 0.1991, "step": 62900 }, { "epoch": 15.11, "learning_rate": 9.224147796245541e-05, "loss": 0.1443, "step": 62910 }, { "epoch": 15.11, "learning_rate": 9.223907710726558e-05, "loss": 0.194, "step": 62920 }, { "epoch": 15.11, "learning_rate": 9.223667591191864e-05, "loss": 0.2328, "step": 62930 }, { "epoch": 15.11, "learning_rate": 9.223427437643391e-05, "loss": 0.1976, "step": 62940 }, { "epoch": 15.12, "learning_rate": 9.223187250083074e-05, "loss": 0.1972, "step": 62950 }, { "epoch": 15.12, "learning_rate": 9.222947028512847e-05, "loss": 0.213, "step": 62960 }, { "epoch": 15.12, "learning_rate": 9.222706772934646e-05, "loss": 0.1638, "step": 62970 }, { "epoch": 15.12, "learning_rate": 9.222466483350402e-05, "loss": 0.155, "step": 62980 }, { "epoch": 15.12, "learning_rate": 9.222226159762056e-05, "loss": 0.2034, "step": 62990 }, { "epoch": 15.13, "learning_rate": 9.221985802171536e-05, "loss": 0.1666, "step": 63000 }, { "epoch": 15.13, "learning_rate": 9.221745410580782e-05, "loss": 0.1976, "step": 63010 }, { "epoch": 15.13, "learning_rate": 9.221504984991731e-05, "loss": 0.2679, "step": 63020 }, { "epoch": 15.13, "learning_rate": 9.221264525406317e-05, "loss": 0.2047, "step": 63030 }, { "epoch": 15.14, "learning_rate": 9.221024031826476e-05, "loss": 0.1854, "step": 63040 }, { "epoch": 15.14, "learning_rate": 9.220783504254147e-05, "loss": 0.2325, "step": 63050 }, { "epoch": 15.14, "learning_rate": 9.220542942691266e-05, "loss": 0.189, "step": 63060 }, { "epoch": 15.14, "learning_rate": 9.220302347139769e-05, "loss": 0.1955, "step": 63070 }, { "epoch": 15.15, "learning_rate": 9.220061717601593e-05, "loss": 0.2275, "step": 63080 }, { "epoch": 15.15, "learning_rate": 9.219821054078682e-05, "loss": 0.2116, "step": 63090 }, { "epoch": 15.15, "learning_rate": 9.219580356572966e-05, "loss": 0.2058, "step": 63100 }, { "epoch": 15.15, "learning_rate": 9.219339625086387e-05, "loss": 0.2025, "step": 63110 }, { "epoch": 15.15, "learning_rate": 9.219098859620884e-05, "loss": 0.2187, "step": 63120 }, { "epoch": 15.16, "learning_rate": 9.218858060178394e-05, "loss": 0.2112, "step": 63130 }, { "epoch": 15.16, "learning_rate": 9.21861722676086e-05, "loss": 0.2309, "step": 63140 }, { "epoch": 15.16, "learning_rate": 9.218376359370218e-05, "loss": 0.1846, "step": 63150 }, { "epoch": 15.16, "learning_rate": 9.218135458008409e-05, "loss": 0.1931, "step": 63160 }, { "epoch": 15.17, "learning_rate": 9.217894522677372e-05, "loss": 0.1889, "step": 63170 }, { "epoch": 15.17, "learning_rate": 9.217653553379048e-05, "loss": 0.1731, "step": 63180 }, { "epoch": 15.17, "learning_rate": 9.217412550115378e-05, "loss": 0.1908, "step": 63190 }, { "epoch": 15.17, "learning_rate": 9.217171512888304e-05, "loss": 0.2184, "step": 63200 }, { "epoch": 15.17, "learning_rate": 9.216930441699765e-05, "loss": 0.221, "step": 63210 }, { "epoch": 15.18, "learning_rate": 9.216689336551703e-05, "loss": 0.1871, "step": 63220 }, { "epoch": 15.18, "learning_rate": 9.216448197446058e-05, "loss": 0.1888, "step": 63230 }, { "epoch": 15.18, "learning_rate": 9.216207024384774e-05, "loss": 0.1789, "step": 63240 }, { "epoch": 15.18, "learning_rate": 9.215965817369794e-05, "loss": 0.2098, "step": 63250 }, { "epoch": 15.19, "learning_rate": 9.215724576403058e-05, "loss": 0.1777, "step": 63260 }, { "epoch": 15.19, "learning_rate": 9.215483301486511e-05, "loss": 0.157, "step": 63270 }, { "epoch": 15.19, "learning_rate": 9.215241992622095e-05, "loss": 0.1807, "step": 63280 }, { "epoch": 15.19, "learning_rate": 9.215000649811752e-05, "loss": 0.1708, "step": 63290 }, { "epoch": 15.2, "learning_rate": 9.214759273057427e-05, "loss": 0.1779, "step": 63300 }, { "epoch": 15.2, "learning_rate": 9.214517862361065e-05, "loss": 0.1725, "step": 63310 }, { "epoch": 15.2, "learning_rate": 9.214276417724607e-05, "loss": 0.2252, "step": 63320 }, { "epoch": 15.2, "learning_rate": 9.214034939150001e-05, "loss": 0.1905, "step": 63330 }, { "epoch": 15.2, "learning_rate": 9.21379342663919e-05, "loss": 0.2401, "step": 63340 }, { "epoch": 15.21, "learning_rate": 9.213551880194118e-05, "loss": 0.1855, "step": 63350 }, { "epoch": 15.21, "learning_rate": 9.213310299816731e-05, "loss": 0.1786, "step": 63360 }, { "epoch": 15.21, "learning_rate": 9.213068685508975e-05, "loss": 0.1777, "step": 63370 }, { "epoch": 15.21, "learning_rate": 9.212827037272793e-05, "loss": 0.2301, "step": 63380 }, { "epoch": 15.22, "learning_rate": 9.212585355110134e-05, "loss": 0.1916, "step": 63390 }, { "epoch": 15.22, "learning_rate": 9.212343639022945e-05, "loss": 0.218, "step": 63400 }, { "epoch": 15.22, "learning_rate": 9.212101889013172e-05, "loss": 0.1977, "step": 63410 }, { "epoch": 15.22, "learning_rate": 9.211860105082759e-05, "loss": 0.1692, "step": 63420 }, { "epoch": 15.23, "learning_rate": 9.211618287233656e-05, "loss": 0.1526, "step": 63430 }, { "epoch": 15.23, "learning_rate": 9.211376435467809e-05, "loss": 0.1756, "step": 63440 }, { "epoch": 15.23, "learning_rate": 9.211134549787166e-05, "loss": 0.2249, "step": 63450 }, { "epoch": 15.23, "learning_rate": 9.210892630193675e-05, "loss": 0.2059, "step": 63460 }, { "epoch": 15.23, "learning_rate": 9.210650676689286e-05, "loss": 0.1755, "step": 63470 }, { "epoch": 15.24, "learning_rate": 9.210408689275944e-05, "loss": 0.2029, "step": 63480 }, { "epoch": 15.24, "learning_rate": 9.2101666679556e-05, "loss": 0.2054, "step": 63490 }, { "epoch": 15.24, "learning_rate": 9.209924612730202e-05, "loss": 0.1765, "step": 63500 }, { "epoch": 15.24, "learning_rate": 9.2096825236017e-05, "loss": 0.1942, "step": 63510 }, { "epoch": 15.25, "learning_rate": 9.209440400572044e-05, "loss": 0.208, "step": 63520 }, { "epoch": 15.25, "learning_rate": 9.209198243643183e-05, "loss": 0.1683, "step": 63530 }, { "epoch": 15.25, "learning_rate": 9.208956052817068e-05, "loss": 0.1943, "step": 63540 }, { "epoch": 15.25, "learning_rate": 9.208713828095648e-05, "loss": 0.2197, "step": 63550 }, { "epoch": 15.25, "learning_rate": 9.208471569480875e-05, "loss": 0.1648, "step": 63560 }, { "epoch": 15.26, "learning_rate": 9.2082292769747e-05, "loss": 0.1508, "step": 63570 }, { "epoch": 15.26, "learning_rate": 9.207986950579073e-05, "loss": 0.1815, "step": 63580 }, { "epoch": 15.26, "learning_rate": 9.207744590295946e-05, "loss": 0.173, "step": 63590 }, { "epoch": 15.26, "learning_rate": 9.207502196127271e-05, "loss": 0.1701, "step": 63600 }, { "epoch": 15.27, "learning_rate": 9.207259768075001e-05, "loss": 0.1604, "step": 63610 }, { "epoch": 15.27, "learning_rate": 9.207017306141084e-05, "loss": 0.2217, "step": 63620 }, { "epoch": 15.27, "learning_rate": 9.206774810327479e-05, "loss": 0.1689, "step": 63630 }, { "epoch": 15.27, "learning_rate": 9.206532280636136e-05, "loss": 0.1617, "step": 63640 }, { "epoch": 15.28, "learning_rate": 9.206289717069005e-05, "loss": 0.2164, "step": 63650 }, { "epoch": 15.28, "learning_rate": 9.206047119628044e-05, "loss": 0.1924, "step": 63660 }, { "epoch": 15.28, "learning_rate": 9.205804488315204e-05, "loss": 0.2366, "step": 63670 }, { "epoch": 15.28, "learning_rate": 9.205561823132441e-05, "loss": 0.2447, "step": 63680 }, { "epoch": 15.28, "learning_rate": 9.205319124081707e-05, "loss": 0.2218, "step": 63690 }, { "epoch": 15.29, "learning_rate": 9.205076391164957e-05, "loss": 0.1907, "step": 63700 }, { "epoch": 15.29, "learning_rate": 9.204833624384148e-05, "loss": 0.1692, "step": 63710 }, { "epoch": 15.29, "learning_rate": 9.204590823741232e-05, "loss": 0.1941, "step": 63720 }, { "epoch": 15.29, "learning_rate": 9.204347989238166e-05, "loss": 0.1709, "step": 63730 }, { "epoch": 15.3, "learning_rate": 9.204105120876907e-05, "loss": 0.2299, "step": 63740 }, { "epoch": 15.3, "learning_rate": 9.203862218659406e-05, "loss": 0.2083, "step": 63750 }, { "epoch": 15.3, "learning_rate": 9.203619282587625e-05, "loss": 0.218, "step": 63760 }, { "epoch": 15.3, "learning_rate": 9.203376312663516e-05, "loss": 0.2086, "step": 63770 }, { "epoch": 15.31, "learning_rate": 9.203133308889036e-05, "loss": 0.1713, "step": 63780 }, { "epoch": 15.31, "learning_rate": 9.202890271266145e-05, "loss": 0.1955, "step": 63790 }, { "epoch": 15.31, "learning_rate": 9.202647199796798e-05, "loss": 0.2091, "step": 63800 }, { "epoch": 15.31, "learning_rate": 9.202404094482953e-05, "loss": 0.1879, "step": 63810 }, { "epoch": 15.31, "learning_rate": 9.202160955326567e-05, "loss": 0.1539, "step": 63820 }, { "epoch": 15.32, "learning_rate": 9.201917782329599e-05, "loss": 0.1668, "step": 63830 }, { "epoch": 15.32, "learning_rate": 9.201674575494008e-05, "loss": 0.1855, "step": 63840 }, { "epoch": 15.32, "learning_rate": 9.201431334821751e-05, "loss": 0.1902, "step": 63850 }, { "epoch": 15.32, "learning_rate": 9.201188060314787e-05, "loss": 0.2593, "step": 63860 }, { "epoch": 15.33, "learning_rate": 9.200944751975076e-05, "loss": 0.1802, "step": 63870 }, { "epoch": 15.33, "learning_rate": 9.200701409804576e-05, "loss": 0.1932, "step": 63880 }, { "epoch": 15.33, "learning_rate": 9.200458033805248e-05, "loss": 0.1916, "step": 63890 }, { "epoch": 15.33, "learning_rate": 9.20021462397905e-05, "loss": 0.1809, "step": 63900 }, { "epoch": 15.33, "learning_rate": 9.199971180327947e-05, "loss": 0.2084, "step": 63910 }, { "epoch": 15.34, "learning_rate": 9.199727702853895e-05, "loss": 0.1726, "step": 63920 }, { "epoch": 15.34, "learning_rate": 9.199484191558856e-05, "loss": 0.1864, "step": 63930 }, { "epoch": 15.34, "learning_rate": 9.199240646444791e-05, "loss": 0.1468, "step": 63940 }, { "epoch": 15.34, "learning_rate": 9.19899706751366e-05, "loss": 0.1926, "step": 63950 }, { "epoch": 15.35, "learning_rate": 9.198753454767428e-05, "loss": 0.1991, "step": 63960 }, { "epoch": 15.35, "learning_rate": 9.198509808208054e-05, "loss": 0.1925, "step": 63970 }, { "epoch": 15.35, "learning_rate": 9.198266127837501e-05, "loss": 0.1763, "step": 63980 }, { "epoch": 15.35, "learning_rate": 9.19802241365773e-05, "loss": 0.1571, "step": 63990 }, { "epoch": 15.36, "learning_rate": 9.197778665670706e-05, "loss": 0.2508, "step": 64000 }, { "epoch": 15.36, "learning_rate": 9.197534883878391e-05, "loss": 0.2109, "step": 64010 }, { "epoch": 15.36, "learning_rate": 9.197291068282747e-05, "loss": 0.1516, "step": 64020 }, { "epoch": 15.36, "learning_rate": 9.197047218885739e-05, "loss": 0.1671, "step": 64030 }, { "epoch": 15.36, "learning_rate": 9.196803335689331e-05, "loss": 0.2224, "step": 64040 }, { "epoch": 15.37, "learning_rate": 9.196559418695487e-05, "loss": 0.1534, "step": 64050 }, { "epoch": 15.37, "learning_rate": 9.196315467906169e-05, "loss": 0.1578, "step": 64060 }, { "epoch": 15.37, "learning_rate": 9.196071483323343e-05, "loss": 0.161, "step": 64070 }, { "epoch": 15.37, "learning_rate": 9.195827464948976e-05, "loss": 0.1847, "step": 64080 }, { "epoch": 15.38, "learning_rate": 9.19558341278503e-05, "loss": 0.1881, "step": 64090 }, { "epoch": 15.38, "learning_rate": 9.19533932683347e-05, "loss": 0.2258, "step": 64100 }, { "epoch": 15.38, "learning_rate": 9.195095207096265e-05, "loss": 0.1885, "step": 64110 }, { "epoch": 15.38, "learning_rate": 9.194851053575379e-05, "loss": 0.1568, "step": 64120 }, { "epoch": 15.39, "learning_rate": 9.19460686627278e-05, "loss": 0.1784, "step": 64130 }, { "epoch": 15.39, "learning_rate": 9.19436264519043e-05, "loss": 0.2248, "step": 64140 }, { "epoch": 15.39, "learning_rate": 9.194118390330299e-05, "loss": 0.2011, "step": 64150 }, { "epoch": 15.39, "learning_rate": 9.193874101694355e-05, "loss": 0.159, "step": 64160 }, { "epoch": 15.39, "learning_rate": 9.193629779284562e-05, "loss": 0.1746, "step": 64170 }, { "epoch": 15.4, "learning_rate": 9.193385423102892e-05, "loss": 0.1786, "step": 64180 }, { "epoch": 15.4, "learning_rate": 9.193141033151307e-05, "loss": 0.1671, "step": 64190 }, { "epoch": 15.4, "learning_rate": 9.19289660943178e-05, "loss": 0.1961, "step": 64200 }, { "epoch": 15.4, "learning_rate": 9.192652151946279e-05, "loss": 0.2054, "step": 64210 }, { "epoch": 15.41, "learning_rate": 9.192407660696769e-05, "loss": 0.1519, "step": 64220 }, { "epoch": 15.41, "learning_rate": 9.192163135685223e-05, "loss": 0.1939, "step": 64230 }, { "epoch": 15.41, "learning_rate": 9.191918576913608e-05, "loss": 0.2283, "step": 64240 }, { "epoch": 15.41, "learning_rate": 9.191673984383894e-05, "loss": 0.1783, "step": 64250 }, { "epoch": 15.41, "learning_rate": 9.19142935809805e-05, "loss": 0.1597, "step": 64260 }, { "epoch": 15.42, "learning_rate": 9.191184698058049e-05, "loss": 0.1625, "step": 64270 }, { "epoch": 15.42, "learning_rate": 9.190940004265855e-05, "loss": 0.1808, "step": 64280 }, { "epoch": 15.42, "learning_rate": 9.190695276723446e-05, "loss": 0.1446, "step": 64290 }, { "epoch": 15.42, "learning_rate": 9.190450515432788e-05, "loss": 0.1689, "step": 64300 }, { "epoch": 15.43, "learning_rate": 9.190205720395855e-05, "loss": 0.1804, "step": 64310 }, { "epoch": 15.43, "learning_rate": 9.189960891614615e-05, "loss": 0.2503, "step": 64320 }, { "epoch": 15.43, "learning_rate": 9.189716029091042e-05, "loss": 0.1652, "step": 64330 }, { "epoch": 15.43, "learning_rate": 9.189471132827108e-05, "loss": 0.1932, "step": 64340 }, { "epoch": 15.44, "learning_rate": 9.189226202824783e-05, "loss": 0.1711, "step": 64350 }, { "epoch": 15.44, "learning_rate": 9.188981239086043e-05, "loss": 0.1563, "step": 64360 }, { "epoch": 15.44, "learning_rate": 9.188736241612856e-05, "loss": 0.1776, "step": 64370 }, { "epoch": 15.44, "learning_rate": 9.1884912104072e-05, "loss": 0.1949, "step": 64380 }, { "epoch": 15.44, "learning_rate": 9.188246145471046e-05, "loss": 0.2075, "step": 64390 }, { "epoch": 15.45, "learning_rate": 9.188001046806367e-05, "loss": 0.1607, "step": 64400 }, { "epoch": 15.45, "learning_rate": 9.187755914415138e-05, "loss": 0.2027, "step": 64410 }, { "epoch": 15.45, "learning_rate": 9.187510748299333e-05, "loss": 0.166, "step": 64420 }, { "epoch": 15.45, "learning_rate": 9.187265548460924e-05, "loss": 0.2064, "step": 64430 }, { "epoch": 15.46, "learning_rate": 9.187020314901889e-05, "loss": 0.2126, "step": 64440 }, { "epoch": 15.46, "learning_rate": 9.1867750476242e-05, "loss": 0.1887, "step": 64450 }, { "epoch": 15.46, "learning_rate": 9.186529746629835e-05, "loss": 0.1954, "step": 64460 }, { "epoch": 15.46, "learning_rate": 9.186284411920767e-05, "loss": 0.1652, "step": 64470 }, { "epoch": 15.47, "learning_rate": 9.186039043498972e-05, "loss": 0.1952, "step": 64480 }, { "epoch": 15.47, "learning_rate": 9.185793641366427e-05, "loss": 0.1752, "step": 64490 }, { "epoch": 15.47, "learning_rate": 9.18554820552511e-05, "loss": 0.197, "step": 64500 }, { "epoch": 15.47, "learning_rate": 9.185302735976993e-05, "loss": 0.1712, "step": 64510 }, { "epoch": 15.47, "learning_rate": 9.185057232724056e-05, "loss": 0.1292, "step": 64520 }, { "epoch": 15.48, "learning_rate": 9.184811695768275e-05, "loss": 0.1886, "step": 64530 }, { "epoch": 15.48, "learning_rate": 9.18456612511163e-05, "loss": 0.179, "step": 64540 }, { "epoch": 15.48, "learning_rate": 9.184320520756094e-05, "loss": 0.2066, "step": 64550 }, { "epoch": 15.48, "learning_rate": 9.184074882703646e-05, "loss": 0.159, "step": 64560 }, { "epoch": 15.49, "learning_rate": 9.183829210956268e-05, "loss": 0.1923, "step": 64570 }, { "epoch": 15.49, "learning_rate": 9.183583505515934e-05, "loss": 0.1617, "step": 64580 }, { "epoch": 15.49, "learning_rate": 9.183337766384625e-05, "loss": 0.2063, "step": 64590 }, { "epoch": 15.49, "learning_rate": 9.183091993564319e-05, "loss": 0.1527, "step": 64600 }, { "epoch": 15.49, "learning_rate": 9.182846187056998e-05, "loss": 0.1755, "step": 64610 }, { "epoch": 15.5, "learning_rate": 9.182600346864636e-05, "loss": 0.1542, "step": 64620 }, { "epoch": 15.5, "learning_rate": 9.182354472989217e-05, "loss": 0.2093, "step": 64630 }, { "epoch": 15.5, "learning_rate": 9.18210856543272e-05, "loss": 0.1593, "step": 64640 }, { "epoch": 15.5, "learning_rate": 9.181862624197126e-05, "loss": 0.1965, "step": 64650 }, { "epoch": 15.51, "learning_rate": 9.181616649284415e-05, "loss": 0.1736, "step": 64660 }, { "epoch": 15.51, "learning_rate": 9.181370640696567e-05, "loss": 0.1574, "step": 64670 }, { "epoch": 15.51, "learning_rate": 9.181124598435564e-05, "loss": 0.1859, "step": 64680 }, { "epoch": 15.51, "learning_rate": 9.180878522503388e-05, "loss": 0.2087, "step": 64690 }, { "epoch": 15.52, "learning_rate": 9.18063241290202e-05, "loss": 0.1974, "step": 64700 }, { "epoch": 15.52, "learning_rate": 9.180386269633442e-05, "loss": 0.1791, "step": 64710 }, { "epoch": 15.52, "learning_rate": 9.180140092699637e-05, "loss": 0.2354, "step": 64720 }, { "epoch": 15.52, "learning_rate": 9.179893882102583e-05, "loss": 0.2298, "step": 64730 }, { "epoch": 15.52, "learning_rate": 9.17964763784427e-05, "loss": 0.1664, "step": 64740 }, { "epoch": 15.53, "learning_rate": 9.179401359926678e-05, "loss": 0.2207, "step": 64750 }, { "epoch": 15.53, "learning_rate": 9.179155048351789e-05, "loss": 0.208, "step": 64760 }, { "epoch": 15.53, "learning_rate": 9.178908703121586e-05, "loss": 0.2063, "step": 64770 }, { "epoch": 15.53, "learning_rate": 9.178662324238055e-05, "loss": 0.2184, "step": 64780 }, { "epoch": 15.54, "learning_rate": 9.17841591170318e-05, "loss": 0.2088, "step": 64790 }, { "epoch": 15.54, "learning_rate": 9.178169465518944e-05, "loss": 0.2806, "step": 64800 }, { "epoch": 15.54, "learning_rate": 9.177922985687334e-05, "loss": 0.2746, "step": 64810 }, { "epoch": 15.54, "learning_rate": 9.177676472210332e-05, "loss": 0.2855, "step": 64820 }, { "epoch": 15.55, "learning_rate": 9.177429925089924e-05, "loss": 0.2483, "step": 64830 }, { "epoch": 15.55, "learning_rate": 9.177183344328097e-05, "loss": 0.2226, "step": 64840 }, { "epoch": 15.55, "learning_rate": 9.176936729926837e-05, "loss": 0.2396, "step": 64850 }, { "epoch": 15.55, "learning_rate": 9.176690081888128e-05, "loss": 0.2652, "step": 64860 }, { "epoch": 15.55, "learning_rate": 9.176443400213956e-05, "loss": 0.188, "step": 64870 }, { "epoch": 15.56, "learning_rate": 9.176196684906311e-05, "loss": 0.2205, "step": 64880 }, { "epoch": 15.56, "learning_rate": 9.175949935967175e-05, "loss": 0.2411, "step": 64890 }, { "epoch": 15.56, "learning_rate": 9.175703153398538e-05, "loss": 0.2333, "step": 64900 }, { "epoch": 15.56, "learning_rate": 9.175456337202388e-05, "loss": 0.2689, "step": 64910 }, { "epoch": 15.57, "learning_rate": 9.175209487380713e-05, "loss": 0.2359, "step": 64920 }, { "epoch": 15.57, "learning_rate": 9.174962603935498e-05, "loss": 0.2507, "step": 64930 }, { "epoch": 15.57, "learning_rate": 9.174715686868733e-05, "loss": 0.2307, "step": 64940 }, { "epoch": 15.57, "learning_rate": 9.174468736182404e-05, "loss": 0.1796, "step": 64950 }, { "epoch": 15.57, "learning_rate": 9.174221751878505e-05, "loss": 0.2306, "step": 64960 }, { "epoch": 15.58, "learning_rate": 9.17397473395902e-05, "loss": 0.2378, "step": 64970 }, { "epoch": 15.58, "learning_rate": 9.173727682425942e-05, "loss": 0.2491, "step": 64980 }, { "epoch": 15.58, "learning_rate": 9.173480597281259e-05, "loss": 0.1955, "step": 64990 }, { "epoch": 15.58, "learning_rate": 9.17323347852696e-05, "loss": 0.2242, "step": 65000 }, { "epoch": 15.59, "learning_rate": 9.172986326165034e-05, "loss": 0.2049, "step": 65010 }, { "epoch": 15.59, "learning_rate": 9.172739140197473e-05, "loss": 0.2534, "step": 65020 }, { "epoch": 15.59, "learning_rate": 9.172491920626269e-05, "loss": 0.2321, "step": 65030 }, { "epoch": 15.59, "learning_rate": 9.172244667453411e-05, "loss": 0.2553, "step": 65040 }, { "epoch": 15.6, "learning_rate": 9.171997380680892e-05, "loss": 0.2346, "step": 65050 }, { "epoch": 15.6, "learning_rate": 9.171750060310701e-05, "loss": 0.2695, "step": 65060 }, { "epoch": 15.6, "learning_rate": 9.17150270634483e-05, "loss": 0.1887, "step": 65070 }, { "epoch": 15.6, "learning_rate": 9.171255318785272e-05, "loss": 0.1966, "step": 65080 }, { "epoch": 15.6, "learning_rate": 9.171007897634021e-05, "loss": 0.2173, "step": 65090 }, { "epoch": 15.61, "learning_rate": 9.170760442893066e-05, "loss": 0.2183, "step": 65100 }, { "epoch": 15.61, "learning_rate": 9.1705129545644e-05, "loss": 0.1871, "step": 65110 }, { "epoch": 15.61, "learning_rate": 9.17026543265002e-05, "loss": 0.2277, "step": 65120 }, { "epoch": 15.61, "learning_rate": 9.170017877151916e-05, "loss": 0.2577, "step": 65130 }, { "epoch": 15.62, "learning_rate": 9.169770288072082e-05, "loss": 0.1898, "step": 65140 }, { "epoch": 15.62, "learning_rate": 9.169522665412512e-05, "loss": 0.2462, "step": 65150 }, { "epoch": 15.62, "learning_rate": 9.1692750091752e-05, "loss": 0.2155, "step": 65160 }, { "epoch": 15.62, "learning_rate": 9.169027319362142e-05, "loss": 0.2137, "step": 65170 }, { "epoch": 15.62, "learning_rate": 9.168779595975331e-05, "loss": 0.2121, "step": 65180 }, { "epoch": 15.63, "learning_rate": 9.168531839016762e-05, "loss": 0.1903, "step": 65190 }, { "epoch": 15.63, "learning_rate": 9.168284048488431e-05, "loss": 0.1746, "step": 65200 }, { "epoch": 15.63, "learning_rate": 9.168036224392334e-05, "loss": 0.1954, "step": 65210 }, { "epoch": 15.63, "learning_rate": 9.167788366730464e-05, "loss": 0.277, "step": 65220 }, { "epoch": 15.64, "learning_rate": 9.167540475504818e-05, "loss": 0.238, "step": 65230 }, { "epoch": 15.64, "learning_rate": 9.167292550717396e-05, "loss": 0.2043, "step": 65240 }, { "epoch": 15.64, "learning_rate": 9.16704459237019e-05, "loss": 0.1748, "step": 65250 }, { "epoch": 15.64, "learning_rate": 9.166796600465199e-05, "loss": 0.205, "step": 65260 }, { "epoch": 15.65, "learning_rate": 9.16654857500442e-05, "loss": 0.1686, "step": 65270 }, { "epoch": 15.65, "learning_rate": 9.16630051598985e-05, "loss": 0.24, "step": 65280 }, { "epoch": 15.65, "learning_rate": 9.166052423423485e-05, "loss": 0.1748, "step": 65290 }, { "epoch": 15.65, "learning_rate": 9.165804297307328e-05, "loss": 0.208, "step": 65300 }, { "epoch": 15.65, "learning_rate": 9.165556137643372e-05, "loss": 0.2566, "step": 65310 }, { "epoch": 15.66, "learning_rate": 9.165307944433617e-05, "loss": 0.1814, "step": 65320 }, { "epoch": 15.66, "learning_rate": 9.165059717680064e-05, "loss": 0.2022, "step": 65330 }, { "epoch": 15.66, "learning_rate": 9.164811457384707e-05, "loss": 0.1656, "step": 65340 }, { "epoch": 15.66, "learning_rate": 9.164563163549552e-05, "loss": 0.2491, "step": 65350 }, { "epoch": 15.67, "learning_rate": 9.164314836176592e-05, "loss": 0.2095, "step": 65360 }, { "epoch": 15.67, "learning_rate": 9.16406647526783e-05, "loss": 0.2175, "step": 65370 }, { "epoch": 15.67, "learning_rate": 9.163818080825267e-05, "loss": 0.1807, "step": 65380 }, { "epoch": 15.67, "learning_rate": 9.163569652850901e-05, "loss": 0.1912, "step": 65390 }, { "epoch": 15.68, "learning_rate": 9.163321191346735e-05, "loss": 0.2351, "step": 65400 }, { "epoch": 15.68, "learning_rate": 9.163072696314767e-05, "loss": 0.2142, "step": 65410 }, { "epoch": 15.68, "learning_rate": 9.162824167757002e-05, "loss": 0.2325, "step": 65420 }, { "epoch": 15.68, "learning_rate": 9.162575605675437e-05, "loss": 0.1935, "step": 65430 }, { "epoch": 15.68, "learning_rate": 9.162327010072079e-05, "loss": 0.2098, "step": 65440 }, { "epoch": 15.69, "learning_rate": 9.162078380948924e-05, "loss": 0.171, "step": 65450 }, { "epoch": 15.69, "learning_rate": 9.161829718307977e-05, "loss": 0.1896, "step": 65460 }, { "epoch": 15.69, "learning_rate": 9.161581022151242e-05, "loss": 0.1966, "step": 65470 }, { "epoch": 15.69, "learning_rate": 9.161332292480721e-05, "loss": 0.2422, "step": 65480 }, { "epoch": 15.7, "learning_rate": 9.161083529298415e-05, "loss": 0.1586, "step": 65490 }, { "epoch": 15.7, "learning_rate": 9.16083473260633e-05, "loss": 0.2443, "step": 65500 }, { "epoch": 15.7, "learning_rate": 9.160585902406469e-05, "loss": 0.2215, "step": 65510 }, { "epoch": 15.7, "learning_rate": 9.160337038700835e-05, "loss": 0.1468, "step": 65520 }, { "epoch": 15.7, "learning_rate": 9.160088141491431e-05, "loss": 0.228, "step": 65530 }, { "epoch": 15.71, "learning_rate": 9.159839210780265e-05, "loss": 0.2621, "step": 65540 }, { "epoch": 15.71, "learning_rate": 9.159590246569337e-05, "loss": 0.2059, "step": 65550 }, { "epoch": 15.71, "learning_rate": 9.159341248860656e-05, "loss": 0.21, "step": 65560 }, { "epoch": 15.71, "learning_rate": 9.159092217656227e-05, "loss": 0.1884, "step": 65570 }, { "epoch": 15.72, "learning_rate": 9.158843152958052e-05, "loss": 0.2744, "step": 65580 }, { "epoch": 15.72, "learning_rate": 9.158594054768139e-05, "loss": 0.2049, "step": 65590 }, { "epoch": 15.72, "learning_rate": 9.158344923088496e-05, "loss": 0.1826, "step": 65600 }, { "epoch": 15.72, "learning_rate": 9.158095757921125e-05, "loss": 0.2342, "step": 65610 }, { "epoch": 15.73, "learning_rate": 9.157846559268035e-05, "loss": 0.219, "step": 65620 }, { "epoch": 15.73, "learning_rate": 9.157597327131233e-05, "loss": 0.2019, "step": 65630 }, { "epoch": 15.73, "learning_rate": 9.157348061512727e-05, "loss": 0.1802, "step": 65640 }, { "epoch": 15.73, "learning_rate": 9.157098762414522e-05, "loss": 0.2031, "step": 65650 }, { "epoch": 15.73, "learning_rate": 9.156849429838628e-05, "loss": 0.2221, "step": 65660 }, { "epoch": 15.74, "learning_rate": 9.156600063787049e-05, "loss": 0.2028, "step": 65670 }, { "epoch": 15.74, "learning_rate": 9.156350664261797e-05, "loss": 0.2225, "step": 65680 }, { "epoch": 15.74, "learning_rate": 9.15610123126488e-05, "loss": 0.2128, "step": 65690 }, { "epoch": 15.74, "learning_rate": 9.155851764798305e-05, "loss": 0.2216, "step": 65700 }, { "epoch": 15.75, "learning_rate": 9.155602264864083e-05, "loss": 0.141, "step": 65710 }, { "epoch": 15.75, "learning_rate": 9.155352731464222e-05, "loss": 0.1757, "step": 65720 }, { "epoch": 15.75, "learning_rate": 9.155103164600731e-05, "loss": 0.2097, "step": 65730 }, { "epoch": 15.75, "learning_rate": 9.154853564275622e-05, "loss": 0.2091, "step": 65740 }, { "epoch": 15.76, "learning_rate": 9.154603930490903e-05, "loss": 0.1968, "step": 65750 }, { "epoch": 15.76, "learning_rate": 9.154354263248585e-05, "loss": 0.202, "step": 65760 }, { "epoch": 15.76, "learning_rate": 9.154104562550679e-05, "loss": 0.1591, "step": 65770 }, { "epoch": 15.76, "learning_rate": 9.153854828399193e-05, "loss": 0.2245, "step": 65780 }, { "epoch": 15.76, "learning_rate": 9.153605060796144e-05, "loss": 0.1975, "step": 65790 }, { "epoch": 15.77, "learning_rate": 9.153355259743537e-05, "loss": 0.2029, "step": 65800 }, { "epoch": 15.77, "learning_rate": 9.153105425243389e-05, "loss": 0.2034, "step": 65810 }, { "epoch": 15.77, "learning_rate": 9.152855557297708e-05, "loss": 0.2073, "step": 65820 }, { "epoch": 15.77, "learning_rate": 9.15260565590851e-05, "loss": 0.1685, "step": 65830 }, { "epoch": 15.78, "learning_rate": 9.152355721077803e-05, "loss": 0.2189, "step": 65840 }, { "epoch": 15.78, "learning_rate": 9.152105752807603e-05, "loss": 0.1794, "step": 65850 }, { "epoch": 15.78, "learning_rate": 9.151855751099923e-05, "loss": 0.1991, "step": 65860 }, { "epoch": 15.78, "learning_rate": 9.151605715956775e-05, "loss": 0.1933, "step": 65870 }, { "epoch": 15.78, "learning_rate": 9.15135564738017e-05, "loss": 0.1924, "step": 65880 }, { "epoch": 15.79, "learning_rate": 9.15110554537213e-05, "loss": 0.2195, "step": 65890 }, { "epoch": 15.79, "learning_rate": 9.15085540993466e-05, "loss": 0.1693, "step": 65900 }, { "epoch": 15.79, "learning_rate": 9.150605241069781e-05, "loss": 0.1564, "step": 65910 }, { "epoch": 15.79, "learning_rate": 9.150355038779504e-05, "loss": 0.1747, "step": 65920 }, { "epoch": 15.8, "learning_rate": 9.150104803065845e-05, "loss": 0.22, "step": 65930 }, { "epoch": 15.8, "learning_rate": 9.149854533930817e-05, "loss": 0.2132, "step": 65940 }, { "epoch": 15.8, "learning_rate": 9.14960423137644e-05, "loss": 0.2383, "step": 65950 }, { "epoch": 15.8, "learning_rate": 9.149353895404727e-05, "loss": 0.1936, "step": 65960 }, { "epoch": 15.81, "learning_rate": 9.149103526017692e-05, "loss": 0.2203, "step": 65970 }, { "epoch": 15.81, "learning_rate": 9.148853123217356e-05, "loss": 0.2137, "step": 65980 }, { "epoch": 15.81, "learning_rate": 9.148602687005731e-05, "loss": 0.1999, "step": 65990 }, { "epoch": 15.81, "learning_rate": 9.148352217384838e-05, "loss": 0.1927, "step": 66000 }, { "epoch": 15.81, "learning_rate": 9.148101714356691e-05, "loss": 0.1695, "step": 66010 }, { "epoch": 15.82, "learning_rate": 9.147851177923308e-05, "loss": 0.187, "step": 66020 }, { "epoch": 15.82, "learning_rate": 9.147600608086705e-05, "loss": 0.1704, "step": 66030 }, { "epoch": 15.82, "learning_rate": 9.147350004848905e-05, "loss": 0.2081, "step": 66040 }, { "epoch": 15.82, "learning_rate": 9.147099368211922e-05, "loss": 0.1546, "step": 66050 }, { "epoch": 15.83, "learning_rate": 9.146848698177775e-05, "loss": 0.2321, "step": 66060 }, { "epoch": 15.83, "learning_rate": 9.146597994748482e-05, "loss": 0.1845, "step": 66070 }, { "epoch": 15.83, "learning_rate": 9.146347257926062e-05, "loss": 0.1859, "step": 66080 }, { "epoch": 15.83, "learning_rate": 9.146096487712538e-05, "loss": 0.2474, "step": 66090 }, { "epoch": 15.84, "learning_rate": 9.145845684109924e-05, "loss": 0.2352, "step": 66100 }, { "epoch": 15.84, "learning_rate": 9.145594847120244e-05, "loss": 0.2091, "step": 66110 }, { "epoch": 15.84, "learning_rate": 9.145343976745515e-05, "loss": 0.1795, "step": 66120 }, { "epoch": 15.84, "learning_rate": 9.145093072987761e-05, "loss": 0.2238, "step": 66130 }, { "epoch": 15.84, "learning_rate": 9.144842135848998e-05, "loss": 0.21, "step": 66140 }, { "epoch": 15.85, "learning_rate": 9.14459116533125e-05, "loss": 0.1689, "step": 66150 }, { "epoch": 15.85, "learning_rate": 9.144340161436537e-05, "loss": 0.1979, "step": 66160 }, { "epoch": 15.85, "learning_rate": 9.14408912416688e-05, "loss": 0.2256, "step": 66170 }, { "epoch": 15.85, "learning_rate": 9.143838053524302e-05, "loss": 0.1736, "step": 66180 }, { "epoch": 15.86, "learning_rate": 9.143586949510823e-05, "loss": 0.1957, "step": 66190 }, { "epoch": 15.86, "learning_rate": 9.143335812128468e-05, "loss": 0.2265, "step": 66200 }, { "epoch": 15.86, "learning_rate": 9.143084641379255e-05, "loss": 0.1593, "step": 66210 }, { "epoch": 15.86, "learning_rate": 9.142833437265212e-05, "loss": 0.1997, "step": 66220 }, { "epoch": 15.86, "learning_rate": 9.142582199788358e-05, "loss": 0.1821, "step": 66230 }, { "epoch": 15.87, "learning_rate": 9.142330928950718e-05, "loss": 0.1774, "step": 66240 }, { "epoch": 15.87, "learning_rate": 9.142079624754315e-05, "loss": 0.2031, "step": 66250 }, { "epoch": 15.87, "learning_rate": 9.141828287201173e-05, "loss": 0.18, "step": 66260 }, { "epoch": 15.87, "learning_rate": 9.141576916293315e-05, "loss": 0.1927, "step": 66270 }, { "epoch": 15.88, "learning_rate": 9.141325512032768e-05, "loss": 0.1896, "step": 66280 }, { "epoch": 15.88, "learning_rate": 9.141074074421554e-05, "loss": 0.1503, "step": 66290 }, { "epoch": 15.88, "learning_rate": 9.1408226034617e-05, "loss": 0.2034, "step": 66300 }, { "epoch": 15.88, "learning_rate": 9.140571099155229e-05, "loss": 0.145, "step": 66310 }, { "epoch": 15.89, "learning_rate": 9.140319561504167e-05, "loss": 0.1455, "step": 66320 }, { "epoch": 15.89, "learning_rate": 9.140067990510539e-05, "loss": 0.2065, "step": 66330 }, { "epoch": 15.89, "learning_rate": 9.139816386176372e-05, "loss": 0.1713, "step": 66340 }, { "epoch": 15.89, "learning_rate": 9.139564748503696e-05, "loss": 0.1931, "step": 66350 }, { "epoch": 15.89, "learning_rate": 9.139313077494529e-05, "loss": 0.2639, "step": 66360 }, { "epoch": 15.9, "learning_rate": 9.139061373150905e-05, "loss": 0.2162, "step": 66370 }, { "epoch": 15.9, "learning_rate": 9.138809635474848e-05, "loss": 0.1758, "step": 66380 }, { "epoch": 15.9, "learning_rate": 9.138557864468384e-05, "loss": 0.187, "step": 66390 }, { "epoch": 15.9, "learning_rate": 9.138306060133544e-05, "loss": 0.1593, "step": 66400 }, { "epoch": 15.91, "learning_rate": 9.138054222472352e-05, "loss": 0.1728, "step": 66410 }, { "epoch": 15.91, "learning_rate": 9.137802351486839e-05, "loss": 0.1492, "step": 66420 }, { "epoch": 15.91, "learning_rate": 9.137550447179034e-05, "loss": 0.1971, "step": 66430 }, { "epoch": 15.91, "learning_rate": 9.13729850955096e-05, "loss": 0.2132, "step": 66440 }, { "epoch": 15.92, "learning_rate": 9.137046538604654e-05, "loss": 0.1565, "step": 66450 }, { "epoch": 15.92, "learning_rate": 9.136794534342139e-05, "loss": 0.1637, "step": 66460 }, { "epoch": 15.92, "learning_rate": 9.136542496765448e-05, "loss": 0.1708, "step": 66470 }, { "epoch": 15.92, "learning_rate": 9.136290425876608e-05, "loss": 0.1809, "step": 66480 }, { "epoch": 15.92, "learning_rate": 9.13603832167765e-05, "loss": 0.2041, "step": 66490 }, { "epoch": 15.93, "learning_rate": 9.135786184170605e-05, "loss": 0.1756, "step": 66500 }, { "epoch": 15.93, "learning_rate": 9.135534013357503e-05, "loss": 0.1624, "step": 66510 }, { "epoch": 15.93, "learning_rate": 9.135281809240373e-05, "loss": 0.2005, "step": 66520 }, { "epoch": 15.93, "learning_rate": 9.13502957182125e-05, "loss": 0.2133, "step": 66530 }, { "epoch": 15.94, "learning_rate": 9.134777301102163e-05, "loss": 0.1982, "step": 66540 }, { "epoch": 15.94, "learning_rate": 9.13452499708514e-05, "loss": 0.1663, "step": 66550 }, { "epoch": 15.94, "learning_rate": 9.134272659772221e-05, "loss": 0.1675, "step": 66560 }, { "epoch": 15.94, "learning_rate": 9.13402028916543e-05, "loss": 0.1651, "step": 66570 }, { "epoch": 15.94, "learning_rate": 9.133767885266805e-05, "loss": 0.171, "step": 66580 }, { "epoch": 15.95, "learning_rate": 9.133515448078376e-05, "loss": 0.2003, "step": 66590 }, { "epoch": 15.95, "learning_rate": 9.133262977602175e-05, "loss": 0.1857, "step": 66600 }, { "epoch": 16.0, "learning_rate": 9.13301047384024e-05, "loss": 0.1647, "step": 66610 }, { "epoch": 16.0, "learning_rate": 9.132757936794598e-05, "loss": 0.1406, "step": 66620 }, { "epoch": 16.01, "learning_rate": 9.132505366467287e-05, "loss": 0.1812, "step": 66630 }, { "epoch": 16.01, "learning_rate": 9.132252762860338e-05, "loss": 0.1928, "step": 66640 }, { "epoch": 16.01, "learning_rate": 9.13200012597579e-05, "loss": 0.2015, "step": 66650 }, { "epoch": 16.01, "learning_rate": 9.131747455815672e-05, "loss": 0.1787, "step": 66660 }, { "epoch": 16.01, "learning_rate": 9.131494752382022e-05, "loss": 0.2034, "step": 66670 }, { "epoch": 16.02, "learning_rate": 9.131242015676875e-05, "loss": 0.1814, "step": 66680 }, { "epoch": 16.02, "learning_rate": 9.130989245702266e-05, "loss": 0.1867, "step": 66690 }, { "epoch": 16.02, "learning_rate": 9.130736442460228e-05, "loss": 0.1657, "step": 66700 }, { "epoch": 16.02, "learning_rate": 9.130483605952802e-05, "loss": 0.1602, "step": 66710 }, { "epoch": 16.03, "learning_rate": 9.13023073618202e-05, "loss": 0.1805, "step": 66720 }, { "epoch": 16.03, "learning_rate": 9.129977833149918e-05, "loss": 0.153, "step": 66730 }, { "epoch": 16.03, "learning_rate": 9.129724896858538e-05, "loss": 0.1993, "step": 66740 }, { "epoch": 16.03, "learning_rate": 9.129471927309911e-05, "loss": 0.152, "step": 66750 }, { "epoch": 16.03, "learning_rate": 9.129218924506076e-05, "loss": 0.1607, "step": 66760 }, { "epoch": 16.04, "learning_rate": 9.128965888449072e-05, "loss": 0.1439, "step": 66770 }, { "epoch": 16.04, "learning_rate": 9.128712819140936e-05, "loss": 0.1631, "step": 66780 }, { "epoch": 16.04, "learning_rate": 9.128459716583705e-05, "loss": 0.2078, "step": 66790 }, { "epoch": 16.04, "learning_rate": 9.128206580779418e-05, "loss": 0.1903, "step": 66800 }, { "epoch": 16.05, "learning_rate": 9.127953411730112e-05, "loss": 0.2138, "step": 66810 }, { "epoch": 16.05, "learning_rate": 9.12770020943783e-05, "loss": 0.208, "step": 66820 }, { "epoch": 16.05, "learning_rate": 9.127446973904606e-05, "loss": 0.1499, "step": 66830 }, { "epoch": 16.05, "learning_rate": 9.127193705132484e-05, "loss": 0.1764, "step": 66840 }, { "epoch": 16.06, "learning_rate": 9.126940403123499e-05, "loss": 0.2065, "step": 66850 }, { "epoch": 16.06, "learning_rate": 9.126687067879694e-05, "loss": 0.1583, "step": 66860 }, { "epoch": 16.06, "learning_rate": 9.12643369940311e-05, "loss": 0.1755, "step": 66870 }, { "epoch": 16.06, "learning_rate": 9.126180297695783e-05, "loss": 0.1865, "step": 66880 }, { "epoch": 16.06, "learning_rate": 9.125926862759758e-05, "loss": 0.1584, "step": 66890 }, { "epoch": 16.07, "learning_rate": 9.125673394597074e-05, "loss": 0.2011, "step": 66900 }, { "epoch": 16.07, "learning_rate": 9.125419893209773e-05, "loss": 0.1514, "step": 66910 }, { "epoch": 16.07, "learning_rate": 9.125166358599895e-05, "loss": 0.1362, "step": 66920 }, { "epoch": 16.07, "learning_rate": 9.124912790769485e-05, "loss": 0.1775, "step": 66930 }, { "epoch": 16.08, "learning_rate": 9.12465918972058e-05, "loss": 0.1789, "step": 66940 }, { "epoch": 16.08, "learning_rate": 9.124405555455226e-05, "loss": 0.188, "step": 66950 }, { "epoch": 16.08, "learning_rate": 9.124151887975465e-05, "loss": 0.1803, "step": 66960 }, { "epoch": 16.08, "learning_rate": 9.12389818728334e-05, "loss": 0.1806, "step": 66970 }, { "epoch": 16.09, "learning_rate": 9.123644453380892e-05, "loss": 0.1614, "step": 66980 }, { "epoch": 16.09, "learning_rate": 9.123390686270169e-05, "loss": 0.1893, "step": 66990 }, { "epoch": 16.09, "learning_rate": 9.123136885953208e-05, "loss": 0.1614, "step": 67000 }, { "epoch": 16.09, "learning_rate": 9.122883052432058e-05, "loss": 0.1792, "step": 67010 }, { "epoch": 16.09, "learning_rate": 9.122629185708762e-05, "loss": 0.1837, "step": 67020 }, { "epoch": 16.1, "learning_rate": 9.122375285785363e-05, "loss": 0.1579, "step": 67030 }, { "epoch": 16.1, "learning_rate": 9.122121352663908e-05, "loss": 0.117, "step": 67040 }, { "epoch": 16.1, "learning_rate": 9.121867386346438e-05, "loss": 0.2068, "step": 67050 }, { "epoch": 16.1, "learning_rate": 9.121613386835004e-05, "loss": 0.1656, "step": 67060 }, { "epoch": 16.11, "learning_rate": 9.121359354131646e-05, "loss": 0.169, "step": 67070 }, { "epoch": 16.11, "learning_rate": 9.121105288238415e-05, "loss": 0.1662, "step": 67080 }, { "epoch": 16.11, "learning_rate": 9.12085118915735e-05, "loss": 0.1612, "step": 67090 }, { "epoch": 16.11, "learning_rate": 9.120597056890505e-05, "loss": 0.1691, "step": 67100 }, { "epoch": 16.11, "learning_rate": 9.120342891439922e-05, "loss": 0.2011, "step": 67110 }, { "epoch": 16.12, "learning_rate": 9.12008869280765e-05, "loss": 0.1308, "step": 67120 }, { "epoch": 16.12, "learning_rate": 9.119834460995733e-05, "loss": 0.1584, "step": 67130 }, { "epoch": 16.12, "learning_rate": 9.119580196006221e-05, "loss": 0.1715, "step": 67140 }, { "epoch": 16.12, "learning_rate": 9.11932589784116e-05, "loss": 0.1551, "step": 67150 }, { "epoch": 16.13, "learning_rate": 9.119071566502599e-05, "loss": 0.1761, "step": 67160 }, { "epoch": 16.13, "learning_rate": 9.118817201992589e-05, "loss": 0.1545, "step": 67170 }, { "epoch": 16.13, "learning_rate": 9.118562804313172e-05, "loss": 0.1719, "step": 67180 }, { "epoch": 16.13, "learning_rate": 9.118308373466402e-05, "loss": 0.1555, "step": 67190 }, { "epoch": 16.14, "learning_rate": 9.118053909454325e-05, "loss": 0.1719, "step": 67200 }, { "epoch": 16.14, "learning_rate": 9.117799412278992e-05, "loss": 0.217, "step": 67210 }, { "epoch": 16.14, "learning_rate": 9.11754488194245e-05, "loss": 0.1429, "step": 67220 }, { "epoch": 16.14, "learning_rate": 9.117290318446754e-05, "loss": 0.156, "step": 67230 }, { "epoch": 16.14, "learning_rate": 9.117035721793947e-05, "loss": 0.1531, "step": 67240 }, { "epoch": 16.15, "learning_rate": 9.116781091986086e-05, "loss": 0.2049, "step": 67250 }, { "epoch": 16.15, "learning_rate": 9.116526429025216e-05, "loss": 0.1642, "step": 67260 }, { "epoch": 16.15, "learning_rate": 9.116271732913392e-05, "loss": 0.1869, "step": 67270 }, { "epoch": 16.15, "learning_rate": 9.116017003652664e-05, "loss": 0.1774, "step": 67280 }, { "epoch": 16.16, "learning_rate": 9.115762241245081e-05, "loss": 0.1705, "step": 67290 }, { "epoch": 16.16, "learning_rate": 9.115507445692697e-05, "loss": 0.1462, "step": 67300 }, { "epoch": 16.16, "learning_rate": 9.115252616997564e-05, "loss": 0.121, "step": 67310 }, { "epoch": 16.16, "learning_rate": 9.114997755161734e-05, "loss": 0.1492, "step": 67320 }, { "epoch": 16.16, "learning_rate": 9.114742860187258e-05, "loss": 0.1782, "step": 67330 }, { "epoch": 16.17, "learning_rate": 9.11448793207619e-05, "loss": 0.1731, "step": 67340 }, { "epoch": 16.17, "learning_rate": 9.114232970830583e-05, "loss": 0.2004, "step": 67350 }, { "epoch": 16.17, "learning_rate": 9.113977976452488e-05, "loss": 0.1588, "step": 67360 }, { "epoch": 16.17, "learning_rate": 9.113722948943962e-05, "loss": 0.1067, "step": 67370 }, { "epoch": 16.18, "learning_rate": 9.113467888307057e-05, "loss": 0.1412, "step": 67380 }, { "epoch": 16.18, "learning_rate": 9.113212794543827e-05, "loss": 0.1628, "step": 67390 }, { "epoch": 16.18, "learning_rate": 9.112957667656326e-05, "loss": 0.1482, "step": 67400 }, { "epoch": 16.18, "learning_rate": 9.112702507646611e-05, "loss": 0.2126, "step": 67410 }, { "epoch": 16.19, "learning_rate": 9.112447314516734e-05, "loss": 0.1751, "step": 67420 }, { "epoch": 16.19, "learning_rate": 9.11219208826875e-05, "loss": 0.1482, "step": 67430 }, { "epoch": 16.19, "learning_rate": 9.111936828904716e-05, "loss": 0.161, "step": 67440 }, { "epoch": 16.19, "learning_rate": 9.111681536426687e-05, "loss": 0.1787, "step": 67450 }, { "epoch": 16.19, "learning_rate": 9.111426210836719e-05, "loss": 0.2123, "step": 67460 }, { "epoch": 16.2, "learning_rate": 9.111170852136868e-05, "loss": 0.1897, "step": 67470 }, { "epoch": 16.2, "learning_rate": 9.11091546032919e-05, "loss": 0.204, "step": 67480 }, { "epoch": 16.2, "learning_rate": 9.110660035415744e-05, "loss": 0.1953, "step": 67490 }, { "epoch": 16.2, "learning_rate": 9.110404577398584e-05, "loss": 0.204, "step": 67500 }, { "epoch": 16.21, "learning_rate": 9.110149086279768e-05, "loss": 0.1558, "step": 67510 }, { "epoch": 16.21, "learning_rate": 9.109893562061354e-05, "loss": 0.1591, "step": 67520 }, { "epoch": 16.21, "learning_rate": 9.1096380047454e-05, "loss": 0.1672, "step": 67530 }, { "epoch": 16.21, "learning_rate": 9.109382414333965e-05, "loss": 0.1295, "step": 67540 }, { "epoch": 16.22, "learning_rate": 9.109126790829105e-05, "loss": 0.1686, "step": 67550 }, { "epoch": 16.22, "learning_rate": 9.10887113423288e-05, "loss": 0.1958, "step": 67560 }, { "epoch": 16.22, "learning_rate": 9.108615444547349e-05, "loss": 0.1401, "step": 67570 }, { "epoch": 16.22, "learning_rate": 9.108359721774568e-05, "loss": 0.1743, "step": 67580 }, { "epoch": 16.22, "learning_rate": 9.108103965916601e-05, "loss": 0.2076, "step": 67590 }, { "epoch": 16.23, "learning_rate": 9.107848176975507e-05, "loss": 0.1668, "step": 67600 }, { "epoch": 16.23, "learning_rate": 9.107592354953342e-05, "loss": 0.1765, "step": 67610 }, { "epoch": 16.23, "learning_rate": 9.10733649985217e-05, "loss": 0.2215, "step": 67620 }, { "epoch": 16.23, "learning_rate": 9.107080611674049e-05, "loss": 0.1924, "step": 67630 }, { "epoch": 16.24, "learning_rate": 9.106824690421042e-05, "loss": 0.1733, "step": 67640 }, { "epoch": 16.24, "learning_rate": 9.106568736095209e-05, "loss": 0.1926, "step": 67650 }, { "epoch": 16.24, "learning_rate": 9.106312748698609e-05, "loss": 0.1479, "step": 67660 }, { "epoch": 16.24, "learning_rate": 9.106056728233307e-05, "loss": 0.1675, "step": 67670 }, { "epoch": 16.24, "learning_rate": 9.105800674701364e-05, "loss": 0.1921, "step": 67680 }, { "epoch": 16.25, "learning_rate": 9.10554458810484e-05, "loss": 0.1537, "step": 67690 }, { "epoch": 16.25, "learning_rate": 9.105288468445798e-05, "loss": 0.1454, "step": 67700 }, { "epoch": 16.25, "learning_rate": 9.105032315726302e-05, "loss": 0.178, "step": 67710 }, { "epoch": 16.25, "learning_rate": 9.104776129948416e-05, "loss": 0.1902, "step": 67720 }, { "epoch": 16.26, "learning_rate": 9.104519911114198e-05, "loss": 0.1433, "step": 67730 }, { "epoch": 16.26, "learning_rate": 9.104263659225717e-05, "loss": 0.2071, "step": 67740 }, { "epoch": 16.26, "learning_rate": 9.104007374285032e-05, "loss": 0.2055, "step": 67750 }, { "epoch": 16.26, "learning_rate": 9.103751056294212e-05, "loss": 0.1579, "step": 67760 }, { "epoch": 16.27, "learning_rate": 9.103494705255316e-05, "loss": 0.2091, "step": 67770 }, { "epoch": 16.27, "learning_rate": 9.103238321170411e-05, "loss": 0.1889, "step": 67780 }, { "epoch": 16.27, "learning_rate": 9.102981904041561e-05, "loss": 0.1771, "step": 67790 }, { "epoch": 16.27, "learning_rate": 9.10272545387083e-05, "loss": 0.2086, "step": 67800 }, { "epoch": 16.27, "learning_rate": 9.102468970660287e-05, "loss": 0.1823, "step": 67810 }, { "epoch": 16.28, "learning_rate": 9.102212454411994e-05, "loss": 0.1811, "step": 67820 }, { "epoch": 16.28, "learning_rate": 9.101955905128018e-05, "loss": 0.1401, "step": 67830 }, { "epoch": 16.28, "learning_rate": 9.101699322810424e-05, "loss": 0.1845, "step": 67840 }, { "epoch": 16.28, "learning_rate": 9.101442707461281e-05, "loss": 0.1649, "step": 67850 }, { "epoch": 16.29, "learning_rate": 9.101186059082652e-05, "loss": 0.1474, "step": 67860 }, { "epoch": 16.29, "learning_rate": 9.100929377676605e-05, "loss": 0.1688, "step": 67870 }, { "epoch": 16.29, "learning_rate": 9.100672663245209e-05, "loss": 0.1931, "step": 67880 }, { "epoch": 16.29, "learning_rate": 9.100415915790528e-05, "loss": 0.1636, "step": 67890 }, { "epoch": 16.3, "learning_rate": 9.100159135314633e-05, "loss": 0.1401, "step": 67900 }, { "epoch": 16.3, "learning_rate": 9.09990232181959e-05, "loss": 0.1709, "step": 67910 }, { "epoch": 16.3, "learning_rate": 9.099645475307468e-05, "loss": 0.1517, "step": 67920 }, { "epoch": 16.3, "learning_rate": 9.099388595780334e-05, "loss": 0.1621, "step": 67930 }, { "epoch": 16.3, "learning_rate": 9.099131683240258e-05, "loss": 0.1426, "step": 67940 }, { "epoch": 16.31, "learning_rate": 9.09887473768931e-05, "loss": 0.2155, "step": 67950 }, { "epoch": 16.31, "learning_rate": 9.098617759129558e-05, "loss": 0.1501, "step": 67960 }, { "epoch": 16.31, "learning_rate": 9.098360747563068e-05, "loss": 0.1674, "step": 67970 }, { "epoch": 16.31, "learning_rate": 9.098103702991916e-05, "loss": 0.1513, "step": 67980 }, { "epoch": 16.32, "learning_rate": 9.097846625418169e-05, "loss": 0.2225, "step": 67990 }, { "epoch": 16.32, "learning_rate": 9.097589514843896e-05, "loss": 0.1458, "step": 68000 }, { "epoch": 16.32, "learning_rate": 9.09733237127117e-05, "loss": 0.1327, "step": 68010 }, { "epoch": 16.32, "learning_rate": 9.09707519470206e-05, "loss": 0.1703, "step": 68020 }, { "epoch": 16.32, "learning_rate": 9.096817985138639e-05, "loss": 0.1678, "step": 68030 }, { "epoch": 16.33, "learning_rate": 9.096560742582976e-05, "loss": 0.1662, "step": 68040 }, { "epoch": 16.33, "learning_rate": 9.096303467037144e-05, "loss": 0.2295, "step": 68050 }, { "epoch": 16.33, "learning_rate": 9.096046158503216e-05, "loss": 0.1404, "step": 68060 }, { "epoch": 16.33, "learning_rate": 9.095788816983262e-05, "loss": 0.1541, "step": 68070 }, { "epoch": 16.34, "learning_rate": 9.095531442479355e-05, "loss": 0.1829, "step": 68080 }, { "epoch": 16.34, "learning_rate": 9.095274034993566e-05, "loss": 0.1823, "step": 68090 }, { "epoch": 16.34, "learning_rate": 9.095016594527972e-05, "loss": 0.1395, "step": 68100 }, { "epoch": 16.34, "learning_rate": 9.094759121084644e-05, "loss": 0.1691, "step": 68110 }, { "epoch": 16.35, "learning_rate": 9.094501614665655e-05, "loss": 0.2, "step": 68120 }, { "epoch": 16.35, "learning_rate": 9.094244075273079e-05, "loss": 0.14, "step": 68130 }, { "epoch": 16.35, "learning_rate": 9.093986502908991e-05, "loss": 0.1666, "step": 68140 }, { "epoch": 16.35, "learning_rate": 9.093728897575463e-05, "loss": 0.1848, "step": 68150 }, { "epoch": 16.35, "learning_rate": 9.093471259274572e-05, "loss": 0.1422, "step": 68160 }, { "epoch": 16.36, "learning_rate": 9.093213588008391e-05, "loss": 0.1898, "step": 68170 }, { "epoch": 16.36, "learning_rate": 9.092955883778998e-05, "loss": 0.1427, "step": 68180 }, { "epoch": 16.36, "learning_rate": 9.092698146588464e-05, "loss": 0.1663, "step": 68190 }, { "epoch": 16.36, "learning_rate": 9.092440376438869e-05, "loss": 0.1411, "step": 68200 }, { "epoch": 16.37, "learning_rate": 9.092182573332284e-05, "loss": 0.1801, "step": 68210 }, { "epoch": 16.37, "learning_rate": 9.091924737270789e-05, "loss": 0.1585, "step": 68220 }, { "epoch": 16.37, "learning_rate": 9.09166686825646e-05, "loss": 0.1237, "step": 68230 }, { "epoch": 16.37, "learning_rate": 9.091408966291372e-05, "loss": 0.1563, "step": 68240 }, { "epoch": 16.38, "learning_rate": 9.091151031377603e-05, "loss": 0.1872, "step": 68250 }, { "epoch": 16.38, "learning_rate": 9.09089306351723e-05, "loss": 0.1727, "step": 68260 }, { "epoch": 16.38, "learning_rate": 9.09063506271233e-05, "loss": 0.1538, "step": 68270 }, { "epoch": 16.38, "learning_rate": 9.090377028964981e-05, "loss": 0.1473, "step": 68280 }, { "epoch": 16.38, "learning_rate": 9.09011896227726e-05, "loss": 0.1908, "step": 68290 }, { "epoch": 16.39, "learning_rate": 9.089860862651248e-05, "loss": 0.1614, "step": 68300 }, { "epoch": 16.39, "learning_rate": 9.089602730089022e-05, "loss": 0.1446, "step": 68310 }, { "epoch": 16.39, "learning_rate": 9.089344564592659e-05, "loss": 0.1653, "step": 68320 }, { "epoch": 16.39, "learning_rate": 9.089086366164241e-05, "loss": 0.128, "step": 68330 }, { "epoch": 16.4, "learning_rate": 9.088828134805846e-05, "loss": 0.2243, "step": 68340 }, { "epoch": 16.4, "learning_rate": 9.088569870519552e-05, "loss": 0.157, "step": 68350 }, { "epoch": 16.4, "learning_rate": 9.088311573307441e-05, "loss": 0.1926, "step": 68360 }, { "epoch": 16.4, "learning_rate": 9.088053243171594e-05, "loss": 0.1223, "step": 68370 }, { "epoch": 16.4, "learning_rate": 9.087794880114089e-05, "loss": 0.2301, "step": 68380 }, { "epoch": 16.41, "learning_rate": 9.087536484137007e-05, "loss": 0.1768, "step": 68390 }, { "epoch": 16.41, "learning_rate": 9.08727805524243e-05, "loss": 0.1531, "step": 68400 }, { "epoch": 16.41, "learning_rate": 9.087019593432439e-05, "loss": 0.1895, "step": 68410 }, { "epoch": 16.41, "learning_rate": 9.086761098709113e-05, "loss": 0.1367, "step": 68420 }, { "epoch": 16.42, "learning_rate": 9.086502571074537e-05, "loss": 0.1434, "step": 68430 }, { "epoch": 16.42, "learning_rate": 9.086244010530792e-05, "loss": 0.1599, "step": 68440 }, { "epoch": 16.42, "learning_rate": 9.08598541707996e-05, "loss": 0.1557, "step": 68450 }, { "epoch": 16.42, "learning_rate": 9.085726790724122e-05, "loss": 0.1661, "step": 68460 }, { "epoch": 16.43, "learning_rate": 9.085468131465363e-05, "loss": 0.1412, "step": 68470 }, { "epoch": 16.43, "learning_rate": 9.085209439305764e-05, "loss": 0.1694, "step": 68480 }, { "epoch": 16.43, "learning_rate": 9.084950714247412e-05, "loss": 0.1785, "step": 68490 }, { "epoch": 16.43, "learning_rate": 9.084691956292384e-05, "loss": 0.1882, "step": 68500 }, { "epoch": 16.43, "learning_rate": 9.08443316544277e-05, "loss": 0.1437, "step": 68510 }, { "epoch": 16.44, "learning_rate": 9.084174341700654e-05, "loss": 0.1917, "step": 68520 }, { "epoch": 16.44, "learning_rate": 9.083915485068114e-05, "loss": 0.1902, "step": 68530 }, { "epoch": 16.44, "learning_rate": 9.083656595547241e-05, "loss": 0.1775, "step": 68540 }, { "epoch": 16.44, "learning_rate": 9.083397673140117e-05, "loss": 0.1584, "step": 68550 }, { "epoch": 16.45, "learning_rate": 9.08313871784883e-05, "loss": 0.1424, "step": 68560 }, { "epoch": 16.45, "learning_rate": 9.08287972967546e-05, "loss": 0.1263, "step": 68570 }, { "epoch": 16.45, "learning_rate": 9.082620708622096e-05, "loss": 0.1507, "step": 68580 }, { "epoch": 16.45, "learning_rate": 9.082361654690825e-05, "loss": 0.2021, "step": 68590 }, { "epoch": 16.46, "learning_rate": 9.082102567883733e-05, "loss": 0.1722, "step": 68600 }, { "epoch": 16.46, "learning_rate": 9.081843448202905e-05, "loss": 0.1426, "step": 68610 }, { "epoch": 16.46, "learning_rate": 9.081584295650427e-05, "loss": 0.1656, "step": 68620 }, { "epoch": 16.46, "learning_rate": 9.081325110228386e-05, "loss": 0.1701, "step": 68630 }, { "epoch": 16.46, "learning_rate": 9.081065891938873e-05, "loss": 0.1777, "step": 68640 }, { "epoch": 16.47, "learning_rate": 9.080806640783973e-05, "loss": 0.1837, "step": 68650 }, { "epoch": 16.47, "learning_rate": 9.080547356765773e-05, "loss": 0.1654, "step": 68660 }, { "epoch": 16.47, "learning_rate": 9.080288039886362e-05, "loss": 0.1877, "step": 68670 }, { "epoch": 16.47, "learning_rate": 9.080028690147828e-05, "loss": 0.12, "step": 68680 }, { "epoch": 16.48, "learning_rate": 9.07976930755226e-05, "loss": 0.173, "step": 68690 }, { "epoch": 16.48, "learning_rate": 9.079509892101746e-05, "loss": 0.1837, "step": 68700 }, { "epoch": 16.48, "learning_rate": 9.079250443798374e-05, "loss": 0.2, "step": 68710 }, { "epoch": 16.48, "learning_rate": 9.078990962644235e-05, "loss": 0.165, "step": 68720 }, { "epoch": 16.48, "learning_rate": 9.078731448641422e-05, "loss": 0.1798, "step": 68730 }, { "epoch": 16.49, "learning_rate": 9.078471901792021e-05, "loss": 0.1682, "step": 68740 }, { "epoch": 16.49, "learning_rate": 9.07821232209812e-05, "loss": 0.151, "step": 68750 }, { "epoch": 16.49, "learning_rate": 9.077952709561815e-05, "loss": 0.1948, "step": 68760 }, { "epoch": 16.49, "learning_rate": 9.077693064185191e-05, "loss": 0.123, "step": 68770 }, { "epoch": 16.5, "learning_rate": 9.077433385970343e-05, "loss": 0.1312, "step": 68780 }, { "epoch": 16.5, "learning_rate": 9.077173674919361e-05, "loss": 0.1248, "step": 68790 }, { "epoch": 16.5, "learning_rate": 9.076913931034337e-05, "loss": 0.201, "step": 68800 }, { "epoch": 16.5, "learning_rate": 9.076654154317363e-05, "loss": 0.1322, "step": 68810 }, { "epoch": 16.51, "learning_rate": 9.076394344770529e-05, "loss": 0.1559, "step": 68820 }, { "epoch": 16.51, "learning_rate": 9.07613450239593e-05, "loss": 0.1554, "step": 68830 }, { "epoch": 16.51, "learning_rate": 9.075874627195654e-05, "loss": 0.1746, "step": 68840 }, { "epoch": 16.51, "learning_rate": 9.075614719171798e-05, "loss": 0.1552, "step": 68850 }, { "epoch": 16.51, "learning_rate": 9.075354778326455e-05, "loss": 0.1479, "step": 68860 }, { "epoch": 16.52, "learning_rate": 9.075094804661719e-05, "loss": 0.19, "step": 68870 }, { "epoch": 16.52, "learning_rate": 9.074834798179679e-05, "loss": 0.2058, "step": 68880 }, { "epoch": 16.52, "learning_rate": 9.074574758882433e-05, "loss": 0.1949, "step": 68890 }, { "epoch": 16.52, "learning_rate": 9.074314686772074e-05, "loss": 0.1865, "step": 68900 }, { "epoch": 16.53, "learning_rate": 9.074054581850696e-05, "loss": 0.159, "step": 68910 }, { "epoch": 16.53, "learning_rate": 9.073794444120395e-05, "loss": 0.1908, "step": 68920 }, { "epoch": 16.53, "learning_rate": 9.073534273583264e-05, "loss": 0.2514, "step": 68930 }, { "epoch": 16.53, "learning_rate": 9.0732740702414e-05, "loss": 0.1669, "step": 68940 }, { "epoch": 16.54, "learning_rate": 9.073013834096895e-05, "loss": 0.1782, "step": 68950 }, { "epoch": 16.54, "learning_rate": 9.07275356515185e-05, "loss": 0.1804, "step": 68960 }, { "epoch": 16.54, "learning_rate": 9.072493263408358e-05, "loss": 0.2333, "step": 68970 }, { "epoch": 16.54, "learning_rate": 9.072232928868514e-05, "loss": 0.2274, "step": 68980 }, { "epoch": 16.54, "learning_rate": 9.071972561534416e-05, "loss": 0.2105, "step": 68990 }, { "epoch": 16.55, "learning_rate": 9.071712161408162e-05, "loss": 0.263, "step": 69000 }, { "epoch": 16.55, "learning_rate": 9.071451728491847e-05, "loss": 0.2002, "step": 69010 }, { "epoch": 16.55, "learning_rate": 9.07119126278757e-05, "loss": 0.2084, "step": 69020 }, { "epoch": 16.55, "learning_rate": 9.070930764297428e-05, "loss": 0.2361, "step": 69030 }, { "epoch": 16.56, "learning_rate": 9.070670233023517e-05, "loss": 0.2138, "step": 69040 }, { "epoch": 16.56, "learning_rate": 9.070409668967938e-05, "loss": 0.231, "step": 69050 }, { "epoch": 16.56, "learning_rate": 9.070149072132787e-05, "loss": 0.1816, "step": 69060 }, { "epoch": 16.56, "learning_rate": 9.069888442520165e-05, "loss": 0.1828, "step": 69070 }, { "epoch": 16.56, "learning_rate": 9.069627780132169e-05, "loss": 0.233, "step": 69080 }, { "epoch": 16.57, "learning_rate": 9.069367084970896e-05, "loss": 0.2074, "step": 69090 }, { "epoch": 16.57, "learning_rate": 9.06910635703845e-05, "loss": 0.2233, "step": 69100 }, { "epoch": 16.57, "learning_rate": 9.06884559633693e-05, "loss": 0.221, "step": 69110 }, { "epoch": 16.57, "learning_rate": 9.068584802868433e-05, "loss": 0.2148, "step": 69120 }, { "epoch": 16.58, "learning_rate": 9.068323976635063e-05, "loss": 0.1835, "step": 69130 }, { "epoch": 16.58, "learning_rate": 9.068063117638917e-05, "loss": 0.228, "step": 69140 }, { "epoch": 16.58, "learning_rate": 9.067802225882095e-05, "loss": 0.1875, "step": 69150 }, { "epoch": 16.58, "learning_rate": 9.067541301366703e-05, "loss": 0.2024, "step": 69160 }, { "epoch": 16.59, "learning_rate": 9.067280344094839e-05, "loss": 0.1754, "step": 69170 }, { "epoch": 16.59, "learning_rate": 9.067019354068604e-05, "loss": 0.1607, "step": 69180 }, { "epoch": 16.59, "learning_rate": 9.066758331290101e-05, "loss": 0.1448, "step": 69190 }, { "epoch": 16.59, "learning_rate": 9.066497275761433e-05, "loss": 0.1753, "step": 69200 }, { "epoch": 16.59, "learning_rate": 9.066236187484698e-05, "loss": 0.2389, "step": 69210 }, { "epoch": 16.6, "learning_rate": 9.065975066462002e-05, "loss": 0.2033, "step": 69220 }, { "epoch": 16.6, "learning_rate": 9.06571391269545e-05, "loss": 0.2557, "step": 69230 }, { "epoch": 16.6, "learning_rate": 9.06545272618714e-05, "loss": 0.1948, "step": 69240 }, { "epoch": 16.6, "learning_rate": 9.065191506939178e-05, "loss": 0.1863, "step": 69250 }, { "epoch": 16.61, "learning_rate": 9.064930254953671e-05, "loss": 0.1631, "step": 69260 }, { "epoch": 16.61, "learning_rate": 9.064668970232716e-05, "loss": 0.2066, "step": 69270 }, { "epoch": 16.61, "learning_rate": 9.064407652778423e-05, "loss": 0.1734, "step": 69280 }, { "epoch": 16.61, "learning_rate": 9.064146302592893e-05, "loss": 0.1765, "step": 69290 }, { "epoch": 16.62, "learning_rate": 9.063884919678232e-05, "loss": 0.1704, "step": 69300 }, { "epoch": 16.62, "learning_rate": 9.063623504036543e-05, "loss": 0.202, "step": 69310 }, { "epoch": 16.62, "learning_rate": 9.063362055669935e-05, "loss": 0.1706, "step": 69320 }, { "epoch": 16.62, "learning_rate": 9.06310057458051e-05, "loss": 0.1868, "step": 69330 }, { "epoch": 16.62, "learning_rate": 9.062839060770376e-05, "loss": 0.1974, "step": 69340 }, { "epoch": 16.63, "learning_rate": 9.062577514241637e-05, "loss": 0.2036, "step": 69350 }, { "epoch": 16.63, "learning_rate": 9.062315934996401e-05, "loss": 0.1314, "step": 69360 }, { "epoch": 16.63, "learning_rate": 9.062054323036775e-05, "loss": 0.1835, "step": 69370 }, { "epoch": 16.63, "learning_rate": 9.061792678364863e-05, "loss": 0.2541, "step": 69380 }, { "epoch": 16.64, "learning_rate": 9.061531000982774e-05, "loss": 0.163, "step": 69390 }, { "epoch": 16.64, "learning_rate": 9.061269290892618e-05, "loss": 0.1778, "step": 69400 }, { "epoch": 16.64, "learning_rate": 9.061007548096496e-05, "loss": 0.2059, "step": 69410 }, { "epoch": 16.64, "learning_rate": 9.060745772596521e-05, "loss": 0.1585, "step": 69420 }, { "epoch": 16.64, "learning_rate": 9.060483964394799e-05, "loss": 0.1952, "step": 69430 }, { "epoch": 16.65, "learning_rate": 9.060222123493441e-05, "loss": 0.1416, "step": 69440 }, { "epoch": 16.65, "learning_rate": 9.059960249894553e-05, "loss": 0.1771, "step": 69450 }, { "epoch": 16.65, "learning_rate": 9.059698343600243e-05, "loss": 0.1939, "step": 69460 }, { "epoch": 16.65, "learning_rate": 9.059436404612623e-05, "loss": 0.2075, "step": 69470 }, { "epoch": 16.66, "learning_rate": 9.0591744329338e-05, "loss": 0.1954, "step": 69480 }, { "epoch": 16.66, "learning_rate": 9.058912428565887e-05, "loss": 0.1631, "step": 69490 }, { "epoch": 16.66, "learning_rate": 9.05865039151099e-05, "loss": 0.2132, "step": 69500 }, { "epoch": 16.66, "learning_rate": 9.058388321771223e-05, "loss": 0.2439, "step": 69510 }, { "epoch": 16.67, "learning_rate": 9.058126219348693e-05, "loss": 0.1423, "step": 69520 }, { "epoch": 16.67, "learning_rate": 9.057864084245514e-05, "loss": 0.1825, "step": 69530 }, { "epoch": 16.67, "learning_rate": 9.057601916463793e-05, "loss": 0.1689, "step": 69540 }, { "epoch": 16.67, "learning_rate": 9.057339716005644e-05, "loss": 0.2195, "step": 69550 }, { "epoch": 16.67, "learning_rate": 9.05707748287318e-05, "loss": 0.1682, "step": 69560 }, { "epoch": 16.68, "learning_rate": 9.056815217068509e-05, "loss": 0.1859, "step": 69570 }, { "epoch": 16.68, "learning_rate": 9.056552918593746e-05, "loss": 0.1738, "step": 69580 }, { "epoch": 16.68, "learning_rate": 9.056290587451001e-05, "loss": 0.1757, "step": 69590 }, { "epoch": 16.68, "learning_rate": 9.056028223642389e-05, "loss": 0.1757, "step": 69600 }, { "epoch": 16.69, "learning_rate": 9.055765827170022e-05, "loss": 0.1537, "step": 69610 }, { "epoch": 16.69, "learning_rate": 9.055503398036011e-05, "loss": 0.1582, "step": 69620 }, { "epoch": 16.69, "learning_rate": 9.055240936242473e-05, "loss": 0.1922, "step": 69630 }, { "epoch": 16.69, "learning_rate": 9.05497844179152e-05, "loss": 0.2232, "step": 69640 }, { "epoch": 16.7, "learning_rate": 9.054715914685265e-05, "loss": 0.1761, "step": 69650 }, { "epoch": 16.7, "learning_rate": 9.054453354925822e-05, "loss": 0.1559, "step": 69660 }, { "epoch": 16.7, "learning_rate": 9.05419076251531e-05, "loss": 0.1846, "step": 69670 }, { "epoch": 16.7, "learning_rate": 9.053928137455836e-05, "loss": 0.185, "step": 69680 }, { "epoch": 16.7, "learning_rate": 9.053665479749521e-05, "loss": 0.204, "step": 69690 }, { "epoch": 16.71, "learning_rate": 9.053402789398477e-05, "loss": 0.1838, "step": 69700 }, { "epoch": 16.71, "learning_rate": 9.053140066404822e-05, "loss": 0.15, "step": 69710 }, { "epoch": 16.71, "learning_rate": 9.052877310770672e-05, "loss": 0.2175, "step": 69720 }, { "epoch": 16.71, "learning_rate": 9.052614522498138e-05, "loss": 0.2185, "step": 69730 }, { "epoch": 16.72, "learning_rate": 9.052351701589341e-05, "loss": 0.131, "step": 69740 }, { "epoch": 16.72, "learning_rate": 9.052088848046399e-05, "loss": 0.149, "step": 69750 }, { "epoch": 16.72, "learning_rate": 9.051825961871423e-05, "loss": 0.1645, "step": 69760 }, { "epoch": 16.72, "learning_rate": 9.051563043066534e-05, "loss": 0.1812, "step": 69770 }, { "epoch": 16.72, "learning_rate": 9.051300091633848e-05, "loss": 0.1879, "step": 69780 }, { "epoch": 16.73, "learning_rate": 9.051037107575483e-05, "loss": 0.1647, "step": 69790 }, { "epoch": 16.73, "learning_rate": 9.050774090893557e-05, "loss": 0.1983, "step": 69800 }, { "epoch": 16.73, "learning_rate": 9.050511041590189e-05, "loss": 0.1758, "step": 69810 }, { "epoch": 16.73, "learning_rate": 9.050247959667495e-05, "loss": 0.1942, "step": 69820 }, { "epoch": 16.74, "learning_rate": 9.049984845127595e-05, "loss": 0.1879, "step": 69830 }, { "epoch": 16.74, "learning_rate": 9.04972169797261e-05, "loss": 0.194, "step": 69840 }, { "epoch": 16.74, "learning_rate": 9.049458518204654e-05, "loss": 0.1922, "step": 69850 }, { "epoch": 16.74, "learning_rate": 9.049195305825853e-05, "loss": 0.1565, "step": 69860 }, { "epoch": 16.75, "learning_rate": 9.048932060838319e-05, "loss": 0.2006, "step": 69870 }, { "epoch": 16.75, "learning_rate": 9.04866878324418e-05, "loss": 0.1614, "step": 69880 }, { "epoch": 16.75, "learning_rate": 9.048405473045552e-05, "loss": 0.1752, "step": 69890 }, { "epoch": 16.75, "learning_rate": 9.048142130244553e-05, "loss": 0.158, "step": 69900 }, { "epoch": 16.75, "learning_rate": 9.047878754843308e-05, "loss": 0.1986, "step": 69910 }, { "epoch": 16.76, "learning_rate": 9.047615346843938e-05, "loss": 0.205, "step": 69920 }, { "epoch": 16.76, "learning_rate": 9.04735190624856e-05, "loss": 0.1612, "step": 69930 }, { "epoch": 16.76, "learning_rate": 9.047088433059301e-05, "loss": 0.1757, "step": 69940 }, { "epoch": 16.76, "learning_rate": 9.04682492727828e-05, "loss": 0.1433, "step": 69950 }, { "epoch": 16.77, "learning_rate": 9.046561388907617e-05, "loss": 0.1782, "step": 69960 }, { "epoch": 16.77, "learning_rate": 9.046297817949436e-05, "loss": 0.2026, "step": 69970 }, { "epoch": 16.77, "learning_rate": 9.046034214405863e-05, "loss": 0.167, "step": 69980 }, { "epoch": 16.77, "learning_rate": 9.045770578279015e-05, "loss": 0.1833, "step": 69990 }, { "epoch": 16.78, "learning_rate": 9.045506909571019e-05, "loss": 0.193, "step": 70000 }, { "epoch": 16.78, "learning_rate": 9.045243208284e-05, "loss": 0.1589, "step": 70010 }, { "epoch": 16.78, "learning_rate": 9.044979474420076e-05, "loss": 0.1885, "step": 70020 }, { "epoch": 16.78, "learning_rate": 9.044715707981375e-05, "loss": 0.1956, "step": 70030 }, { "epoch": 16.78, "learning_rate": 9.04445190897002e-05, "loss": 0.1624, "step": 70040 }, { "epoch": 16.79, "learning_rate": 9.044188077388134e-05, "loss": 0.1536, "step": 70050 }, { "epoch": 16.79, "learning_rate": 9.043924213237844e-05, "loss": 0.1781, "step": 70060 }, { "epoch": 16.79, "learning_rate": 9.043660316521274e-05, "loss": 0.1654, "step": 70070 }, { "epoch": 16.79, "learning_rate": 9.043396387240551e-05, "loss": 0.1844, "step": 70080 }, { "epoch": 16.8, "learning_rate": 9.043132425397796e-05, "loss": 0.1884, "step": 70090 }, { "epoch": 16.8, "learning_rate": 9.042868430995138e-05, "loss": 0.1331, "step": 70100 }, { "epoch": 16.8, "learning_rate": 9.042604404034703e-05, "loss": 0.1397, "step": 70110 }, { "epoch": 16.8, "learning_rate": 9.042340344518617e-05, "loss": 0.1835, "step": 70120 }, { "epoch": 16.8, "learning_rate": 9.042076252449006e-05, "loss": 0.1621, "step": 70130 }, { "epoch": 16.81, "learning_rate": 9.041812127827995e-05, "loss": 0.1413, "step": 70140 }, { "epoch": 16.81, "learning_rate": 9.041547970657715e-05, "loss": 0.1703, "step": 70150 }, { "epoch": 16.81, "learning_rate": 9.04128378094029e-05, "loss": 0.1776, "step": 70160 }, { "epoch": 16.81, "learning_rate": 9.041019558677849e-05, "loss": 0.1745, "step": 70170 }, { "epoch": 16.82, "learning_rate": 9.04075530387252e-05, "loss": 0.2002, "step": 70180 }, { "epoch": 16.82, "learning_rate": 9.04049101652643e-05, "loss": 0.1771, "step": 70190 }, { "epoch": 16.82, "learning_rate": 9.040226696641709e-05, "loss": 0.1471, "step": 70200 }, { "epoch": 16.82, "learning_rate": 9.039962344220486e-05, "loss": 0.1955, "step": 70210 }, { "epoch": 16.83, "learning_rate": 9.039697959264885e-05, "loss": 0.2393, "step": 70220 }, { "epoch": 16.83, "learning_rate": 9.03943354177704e-05, "loss": 0.1677, "step": 70230 }, { "epoch": 16.83, "learning_rate": 9.03916909175908e-05, "loss": 0.1663, "step": 70240 }, { "epoch": 16.83, "learning_rate": 9.038904609213132e-05, "loss": 0.1713, "step": 70250 }, { "epoch": 16.83, "learning_rate": 9.03864009414133e-05, "loss": 0.2049, "step": 70260 }, { "epoch": 16.84, "learning_rate": 9.038375546545799e-05, "loss": 0.1941, "step": 70270 }, { "epoch": 16.84, "learning_rate": 9.038110966428674e-05, "loss": 0.1615, "step": 70280 }, { "epoch": 16.84, "learning_rate": 9.037846353792084e-05, "loss": 0.1566, "step": 70290 }, { "epoch": 16.84, "learning_rate": 9.037581708638159e-05, "loss": 0.1362, "step": 70300 }, { "epoch": 16.85, "learning_rate": 9.037317030969031e-05, "loss": 0.135, "step": 70310 }, { "epoch": 16.85, "learning_rate": 9.037052320786832e-05, "loss": 0.1495, "step": 70320 }, { "epoch": 16.85, "learning_rate": 9.036787578093693e-05, "loss": 0.1773, "step": 70330 }, { "epoch": 16.85, "learning_rate": 9.036522802891746e-05, "loss": 0.2175, "step": 70340 }, { "epoch": 16.86, "learning_rate": 9.036257995183126e-05, "loss": 0.1665, "step": 70350 }, { "epoch": 16.86, "learning_rate": 9.035993154969961e-05, "loss": 0.2245, "step": 70360 }, { "epoch": 16.86, "learning_rate": 9.035728282254386e-05, "loss": 0.1814, "step": 70370 }, { "epoch": 16.86, "learning_rate": 9.035463377038533e-05, "loss": 0.159, "step": 70380 }, { "epoch": 16.86, "learning_rate": 9.035198439324539e-05, "loss": 0.1495, "step": 70390 }, { "epoch": 16.87, "learning_rate": 9.034933469114532e-05, "loss": 0.1791, "step": 70400 }, { "epoch": 16.87, "learning_rate": 9.03466846641065e-05, "loss": 0.2164, "step": 70410 }, { "epoch": 16.87, "learning_rate": 9.034403431215026e-05, "loss": 0.1993, "step": 70420 }, { "epoch": 16.87, "learning_rate": 9.034138363529793e-05, "loss": 0.1553, "step": 70430 }, { "epoch": 16.88, "learning_rate": 9.033873263357089e-05, "loss": 0.1791, "step": 70440 }, { "epoch": 16.88, "learning_rate": 9.033608130699045e-05, "loss": 0.1919, "step": 70450 }, { "epoch": 16.88, "learning_rate": 9.033342965557799e-05, "loss": 0.1854, "step": 70460 }, { "epoch": 16.88, "learning_rate": 9.033077767935484e-05, "loss": 0.1699, "step": 70470 }, { "epoch": 16.88, "learning_rate": 9.032812537834239e-05, "loss": 0.197, "step": 70480 }, { "epoch": 16.89, "learning_rate": 9.032547275256195e-05, "loss": 0.1733, "step": 70490 }, { "epoch": 16.89, "learning_rate": 9.032281980203494e-05, "loss": 0.1374, "step": 70500 }, { "epoch": 16.89, "learning_rate": 9.032016652678268e-05, "loss": 0.1769, "step": 70510 }, { "epoch": 16.89, "learning_rate": 9.031751292682655e-05, "loss": 0.1911, "step": 70520 }, { "epoch": 16.9, "learning_rate": 9.031485900218792e-05, "loss": 0.1488, "step": 70530 }, { "epoch": 16.9, "learning_rate": 9.031220475288817e-05, "loss": 0.1617, "step": 70540 }, { "epoch": 16.9, "learning_rate": 9.030955017894867e-05, "loss": 0.1755, "step": 70550 }, { "epoch": 16.9, "learning_rate": 9.03068952803908e-05, "loss": 0.1924, "step": 70560 }, { "epoch": 16.91, "learning_rate": 9.030424005723594e-05, "loss": 0.1694, "step": 70570 }, { "epoch": 16.91, "learning_rate": 9.030158450950546e-05, "loss": 0.1445, "step": 70580 }, { "epoch": 16.91, "learning_rate": 9.029892863722076e-05, "loss": 0.1613, "step": 70590 }, { "epoch": 16.91, "learning_rate": 9.029627244040324e-05, "loss": 0.2158, "step": 70600 }, { "epoch": 16.91, "learning_rate": 9.029361591907424e-05, "loss": 0.1708, "step": 70610 }, { "epoch": 16.92, "learning_rate": 9.029095907325521e-05, "loss": 0.1571, "step": 70620 }, { "epoch": 16.92, "learning_rate": 9.028830190296754e-05, "loss": 0.1674, "step": 70630 }, { "epoch": 16.92, "learning_rate": 9.028564440823257e-05, "loss": 0.1674, "step": 70640 }, { "epoch": 16.92, "learning_rate": 9.028298658907178e-05, "loss": 0.1533, "step": 70650 }, { "epoch": 16.93, "learning_rate": 9.028032844550652e-05, "loss": 0.1709, "step": 70660 }, { "epoch": 16.93, "learning_rate": 9.027766997755822e-05, "loss": 0.1522, "step": 70670 }, { "epoch": 16.93, "learning_rate": 9.027501118524828e-05, "loss": 0.1203, "step": 70680 }, { "epoch": 16.93, "learning_rate": 9.027235206859812e-05, "loss": 0.1591, "step": 70690 }, { "epoch": 16.94, "learning_rate": 9.026969262762915e-05, "loss": 0.1611, "step": 70700 }, { "epoch": 16.94, "learning_rate": 9.026703286236278e-05, "loss": 0.1694, "step": 70710 }, { "epoch": 16.94, "learning_rate": 9.026437277282044e-05, "loss": 0.187, "step": 70720 }, { "epoch": 16.94, "learning_rate": 9.026171235902354e-05, "loss": 0.1686, "step": 70730 }, { "epoch": 16.94, "learning_rate": 9.025905162099354e-05, "loss": 0.2169, "step": 70740 }, { "epoch": 16.95, "learning_rate": 9.025639055875179e-05, "loss": 0.1841, "step": 70750 }, { "epoch": 16.95, "learning_rate": 9.02537291723198e-05, "loss": 0.1628, "step": 70760 }, { "epoch": 16.95, "learning_rate": 9.025106746171896e-05, "loss": 0.1682, "step": 70770 }, { "epoch": 17.0, "learning_rate": 9.024840542697073e-05, "loss": 0.1605, "step": 70780 }, { "epoch": 17.0, "learning_rate": 9.024574306809652e-05, "loss": 0.169, "step": 70790 }, { "epoch": 17.01, "learning_rate": 9.024308038511779e-05, "loss": 0.1255, "step": 70800 }, { "epoch": 17.01, "learning_rate": 9.0240417378056e-05, "loss": 0.1881, "step": 70810 }, { "epoch": 17.01, "learning_rate": 9.023775404693253e-05, "loss": 0.157, "step": 70820 }, { "epoch": 17.01, "learning_rate": 9.02350903917689e-05, "loss": 0.1602, "step": 70830 }, { "epoch": 17.02, "learning_rate": 9.023242641258654e-05, "loss": 0.1531, "step": 70840 }, { "epoch": 17.02, "learning_rate": 9.022976210940688e-05, "loss": 0.1519, "step": 70850 }, { "epoch": 17.02, "learning_rate": 9.02270974822514e-05, "loss": 0.1996, "step": 70860 }, { "epoch": 17.02, "learning_rate": 9.022443253114153e-05, "loss": 0.1775, "step": 70870 }, { "epoch": 17.02, "learning_rate": 9.022176725609877e-05, "loss": 0.1333, "step": 70880 }, { "epoch": 17.03, "learning_rate": 9.021910165714456e-05, "loss": 0.1423, "step": 70890 }, { "epoch": 17.03, "learning_rate": 9.021643573430037e-05, "loss": 0.2045, "step": 70900 }, { "epoch": 17.03, "learning_rate": 9.021376948758769e-05, "loss": 0.1697, "step": 70910 }, { "epoch": 17.03, "learning_rate": 9.021110291702795e-05, "loss": 0.1646, "step": 70920 }, { "epoch": 17.04, "learning_rate": 9.020843602264265e-05, "loss": 0.1503, "step": 70930 }, { "epoch": 17.04, "learning_rate": 9.020576880445327e-05, "loss": 0.1497, "step": 70940 }, { "epoch": 17.04, "learning_rate": 9.020310126248129e-05, "loss": 0.1514, "step": 70950 }, { "epoch": 17.04, "learning_rate": 9.020043339674816e-05, "loss": 0.1372, "step": 70960 }, { "epoch": 17.05, "learning_rate": 9.019776520727541e-05, "loss": 0.2041, "step": 70970 }, { "epoch": 17.05, "learning_rate": 9.01950966940845e-05, "loss": 0.1241, "step": 70980 }, { "epoch": 17.05, "learning_rate": 9.019242785719693e-05, "loss": 0.1674, "step": 70990 }, { "epoch": 17.05, "learning_rate": 9.018975869663419e-05, "loss": 0.1822, "step": 71000 }, { "epoch": 17.05, "learning_rate": 9.018708921241778e-05, "loss": 0.1263, "step": 71010 }, { "epoch": 17.06, "learning_rate": 9.018441940456918e-05, "loss": 0.1523, "step": 71020 }, { "epoch": 17.06, "learning_rate": 9.01817492731099e-05, "loss": 0.1866, "step": 71030 }, { "epoch": 17.06, "learning_rate": 9.017907881806146e-05, "loss": 0.1687, "step": 71040 }, { "epoch": 17.06, "learning_rate": 9.017640803944534e-05, "loss": 0.1724, "step": 71050 }, { "epoch": 17.07, "learning_rate": 9.017373693728307e-05, "loss": 0.1902, "step": 71060 }, { "epoch": 17.07, "learning_rate": 9.017106551159614e-05, "loss": 0.1177, "step": 71070 }, { "epoch": 17.07, "learning_rate": 9.016839376240607e-05, "loss": 0.1552, "step": 71080 }, { "epoch": 17.07, "learning_rate": 9.016572168973441e-05, "loss": 0.1497, "step": 71090 }, { "epoch": 17.08, "learning_rate": 9.016304929360262e-05, "loss": 0.1476, "step": 71100 }, { "epoch": 17.08, "learning_rate": 9.016037657403224e-05, "loss": 0.1353, "step": 71110 }, { "epoch": 17.08, "learning_rate": 9.015770353104482e-05, "loss": 0.1642, "step": 71120 }, { "epoch": 17.08, "learning_rate": 9.015503016466187e-05, "loss": 0.1676, "step": 71130 }, { "epoch": 17.08, "learning_rate": 9.015235647490492e-05, "loss": 0.1419, "step": 71140 }, { "epoch": 17.09, "learning_rate": 9.01496824617955e-05, "loss": 0.1561, "step": 71150 }, { "epoch": 17.09, "learning_rate": 9.014700812535514e-05, "loss": 0.1464, "step": 71160 }, { "epoch": 17.09, "learning_rate": 9.014433346560539e-05, "loss": 0.1413, "step": 71170 }, { "epoch": 17.09, "learning_rate": 9.014165848256776e-05, "loss": 0.1313, "step": 71180 }, { "epoch": 17.1, "learning_rate": 9.013898317626381e-05, "loss": 0.1695, "step": 71190 }, { "epoch": 17.1, "learning_rate": 9.013630754671511e-05, "loss": 0.1947, "step": 71200 }, { "epoch": 17.1, "learning_rate": 9.013363159394317e-05, "loss": 0.1629, "step": 71210 }, { "epoch": 17.1, "learning_rate": 9.013095531796955e-05, "loss": 0.1302, "step": 71220 }, { "epoch": 17.1, "learning_rate": 9.012827871881582e-05, "loss": 0.1291, "step": 71230 }, { "epoch": 17.11, "learning_rate": 9.012560179650352e-05, "loss": 0.1465, "step": 71240 }, { "epoch": 17.11, "learning_rate": 9.012292455105421e-05, "loss": 0.1682, "step": 71250 }, { "epoch": 17.11, "learning_rate": 9.012024698248944e-05, "loss": 0.1673, "step": 71260 }, { "epoch": 17.11, "learning_rate": 9.01175690908308e-05, "loss": 0.1489, "step": 71270 }, { "epoch": 17.12, "learning_rate": 9.011489087609982e-05, "loss": 0.1886, "step": 71280 }, { "epoch": 17.12, "learning_rate": 9.011221233831808e-05, "loss": 0.1565, "step": 71290 }, { "epoch": 17.12, "learning_rate": 9.010953347750717e-05, "loss": 0.1574, "step": 71300 }, { "epoch": 17.12, "learning_rate": 9.010685429368864e-05, "loss": 0.1305, "step": 71310 }, { "epoch": 17.13, "learning_rate": 9.01041747868841e-05, "loss": 0.1565, "step": 71320 }, { "epoch": 17.13, "learning_rate": 9.010149495711507e-05, "loss": 0.1464, "step": 71330 }, { "epoch": 17.13, "learning_rate": 9.009881480440319e-05, "loss": 0.1932, "step": 71340 }, { "epoch": 17.13, "learning_rate": 9.009613432877e-05, "loss": 0.1263, "step": 71350 }, { "epoch": 17.13, "learning_rate": 9.009345353023711e-05, "loss": 0.1496, "step": 71360 }, { "epoch": 17.14, "learning_rate": 9.009077240882611e-05, "loss": 0.1166, "step": 71370 }, { "epoch": 17.14, "learning_rate": 9.008809096455857e-05, "loss": 0.1538, "step": 71380 }, { "epoch": 17.14, "learning_rate": 9.008540919745611e-05, "loss": 0.1212, "step": 71390 }, { "epoch": 17.14, "learning_rate": 9.008272710754032e-05, "loss": 0.1778, "step": 71400 }, { "epoch": 17.15, "learning_rate": 9.008004469483279e-05, "loss": 0.1857, "step": 71410 }, { "epoch": 17.15, "learning_rate": 9.007736195935512e-05, "loss": 0.126, "step": 71420 }, { "epoch": 17.15, "learning_rate": 9.007467890112892e-05, "loss": 0.1742, "step": 71430 }, { "epoch": 17.15, "learning_rate": 9.007199552017583e-05, "loss": 0.1935, "step": 71440 }, { "epoch": 17.16, "learning_rate": 9.006931181651738e-05, "loss": 0.1477, "step": 71450 }, { "epoch": 17.16, "learning_rate": 9.006662779017527e-05, "loss": 0.1074, "step": 71460 }, { "epoch": 17.16, "learning_rate": 9.006394344117106e-05, "loss": 0.1426, "step": 71470 }, { "epoch": 17.16, "learning_rate": 9.006125876952639e-05, "loss": 0.1901, "step": 71480 }, { "epoch": 17.16, "learning_rate": 9.005857377526285e-05, "loss": 0.1666, "step": 71490 }, { "epoch": 17.17, "learning_rate": 9.00558884584021e-05, "loss": 0.1385, "step": 71500 }, { "epoch": 17.17, "learning_rate": 9.005320281896574e-05, "loss": 0.1472, "step": 71510 }, { "epoch": 17.17, "learning_rate": 9.005051685697543e-05, "loss": 0.1384, "step": 71520 }, { "epoch": 17.17, "learning_rate": 9.004783057245276e-05, "loss": 0.1366, "step": 71530 }, { "epoch": 17.18, "learning_rate": 9.004514396541939e-05, "loss": 0.1324, "step": 71540 }, { "epoch": 17.18, "learning_rate": 9.004245703589694e-05, "loss": 0.104, "step": 71550 }, { "epoch": 17.18, "learning_rate": 9.003976978390705e-05, "loss": 0.1647, "step": 71560 }, { "epoch": 17.18, "learning_rate": 9.003708220947137e-05, "loss": 0.1572, "step": 71570 }, { "epoch": 17.18, "learning_rate": 9.003439431261156e-05, "loss": 0.1512, "step": 71580 }, { "epoch": 17.19, "learning_rate": 9.003170609334923e-05, "loss": 0.2116, "step": 71590 }, { "epoch": 17.19, "learning_rate": 9.002901755170603e-05, "loss": 0.135, "step": 71600 }, { "epoch": 17.19, "learning_rate": 9.002632868770364e-05, "loss": 0.1556, "step": 71610 }, { "epoch": 17.19, "learning_rate": 9.00236395013637e-05, "loss": 0.1525, "step": 71620 }, { "epoch": 17.2, "learning_rate": 9.002094999270787e-05, "loss": 0.1065, "step": 71630 }, { "epoch": 17.2, "learning_rate": 9.001826016175781e-05, "loss": 0.1347, "step": 71640 }, { "epoch": 17.2, "learning_rate": 9.001557000853515e-05, "loss": 0.1395, "step": 71650 }, { "epoch": 17.2, "learning_rate": 9.00128795330616e-05, "loss": 0.1498, "step": 71660 }, { "epoch": 17.21, "learning_rate": 9.00101887353588e-05, "loss": 0.1368, "step": 71670 }, { "epoch": 17.21, "learning_rate": 9.000749761544842e-05, "loss": 0.1616, "step": 71680 }, { "epoch": 17.21, "learning_rate": 9.000480617335216e-05, "loss": 0.1633, "step": 71690 }, { "epoch": 17.21, "learning_rate": 9.000211440909165e-05, "loss": 0.1498, "step": 71700 }, { "epoch": 17.21, "learning_rate": 8.999942232268861e-05, "loss": 0.1489, "step": 71710 }, { "epoch": 17.22, "learning_rate": 8.999672991416468e-05, "loss": 0.1336, "step": 71720 }, { "epoch": 17.22, "learning_rate": 8.999403718354157e-05, "loss": 0.1222, "step": 71730 }, { "epoch": 17.22, "learning_rate": 8.999134413084096e-05, "loss": 0.1378, "step": 71740 }, { "epoch": 17.22, "learning_rate": 8.998865075608454e-05, "loss": 0.1179, "step": 71750 }, { "epoch": 17.23, "learning_rate": 8.998595705929398e-05, "loss": 0.1425, "step": 71760 }, { "epoch": 17.23, "learning_rate": 8.9983263040491e-05, "loss": 0.1454, "step": 71770 }, { "epoch": 17.23, "learning_rate": 8.998056869969727e-05, "loss": 0.1415, "step": 71780 }, { "epoch": 17.23, "learning_rate": 8.997787403693451e-05, "loss": 0.1628, "step": 71790 }, { "epoch": 17.24, "learning_rate": 8.997517905222441e-05, "loss": 0.1402, "step": 71800 }, { "epoch": 17.24, "learning_rate": 8.997248374558867e-05, "loss": 0.1612, "step": 71810 }, { "epoch": 17.24, "learning_rate": 8.9969788117049e-05, "loss": 0.1858, "step": 71820 }, { "epoch": 17.24, "learning_rate": 8.996709216662711e-05, "loss": 0.1297, "step": 71830 }, { "epoch": 17.24, "learning_rate": 8.996439589434471e-05, "loss": 0.1369, "step": 71840 }, { "epoch": 17.25, "learning_rate": 8.996169930022351e-05, "loss": 0.1275, "step": 71850 }, { "epoch": 17.25, "learning_rate": 8.995900238428524e-05, "loss": 0.1766, "step": 71860 }, { "epoch": 17.25, "learning_rate": 8.99563051465516e-05, "loss": 0.1581, "step": 71870 }, { "epoch": 17.25, "learning_rate": 8.995360758704431e-05, "loss": 0.1206, "step": 71880 }, { "epoch": 17.26, "learning_rate": 8.99509097057851e-05, "loss": 0.1799, "step": 71890 }, { "epoch": 17.26, "learning_rate": 8.99482115027957e-05, "loss": 0.1272, "step": 71900 }, { "epoch": 17.26, "learning_rate": 8.994551297809786e-05, "loss": 0.1482, "step": 71910 }, { "epoch": 17.26, "learning_rate": 8.994281413171328e-05, "loss": 0.1557, "step": 71920 }, { "epoch": 17.26, "learning_rate": 8.994011496366371e-05, "loss": 0.1694, "step": 71930 }, { "epoch": 17.27, "learning_rate": 8.993741547397085e-05, "loss": 0.1497, "step": 71940 }, { "epoch": 17.27, "learning_rate": 8.993471566265649e-05, "loss": 0.1372, "step": 71950 }, { "epoch": 17.27, "learning_rate": 8.993201552974235e-05, "loss": 0.1295, "step": 71960 }, { "epoch": 17.27, "learning_rate": 8.992931507525018e-05, "loss": 0.1302, "step": 71970 }, { "epoch": 17.28, "learning_rate": 8.992661429920171e-05, "loss": 0.1685, "step": 71980 }, { "epoch": 17.28, "learning_rate": 8.992391320161871e-05, "loss": 0.1563, "step": 71990 }, { "epoch": 17.28, "learning_rate": 8.992121178252292e-05, "loss": 0.1649, "step": 72000 }, { "epoch": 17.28, "learning_rate": 8.991851004193611e-05, "loss": 0.1592, "step": 72010 }, { "epoch": 17.29, "learning_rate": 8.991580797988002e-05, "loss": 0.1568, "step": 72020 }, { "epoch": 17.29, "learning_rate": 8.991310559637643e-05, "loss": 0.1318, "step": 72030 }, { "epoch": 17.29, "learning_rate": 8.991040289144708e-05, "loss": 0.1388, "step": 72040 }, { "epoch": 17.29, "learning_rate": 8.990769986511374e-05, "loss": 0.1719, "step": 72050 }, { "epoch": 17.29, "learning_rate": 8.99049965173982e-05, "loss": 0.1262, "step": 72060 }, { "epoch": 17.3, "learning_rate": 8.990229284832219e-05, "loss": 0.0916, "step": 72070 }, { "epoch": 17.3, "learning_rate": 8.989958885790752e-05, "loss": 0.1906, "step": 72080 }, { "epoch": 17.3, "learning_rate": 8.989688454617595e-05, "loss": 0.166, "step": 72090 }, { "epoch": 17.3, "learning_rate": 8.989417991314928e-05, "loss": 0.1268, "step": 72100 }, { "epoch": 17.31, "learning_rate": 8.989147495884924e-05, "loss": 0.1801, "step": 72110 }, { "epoch": 17.31, "learning_rate": 8.988876968329766e-05, "loss": 0.157, "step": 72120 }, { "epoch": 17.31, "learning_rate": 8.988606408651633e-05, "loss": 0.1108, "step": 72130 }, { "epoch": 17.31, "learning_rate": 8.988335816852699e-05, "loss": 0.1685, "step": 72140 }, { "epoch": 17.32, "learning_rate": 8.988065192935147e-05, "loss": 0.1191, "step": 72150 }, { "epoch": 17.32, "learning_rate": 8.987794536901156e-05, "loss": 0.1625, "step": 72160 }, { "epoch": 17.32, "learning_rate": 8.987523848752903e-05, "loss": 0.1526, "step": 72170 }, { "epoch": 17.32, "learning_rate": 8.987253128492572e-05, "loss": 0.1251, "step": 72180 }, { "epoch": 17.32, "learning_rate": 8.986982376122342e-05, "loss": 0.1373, "step": 72190 }, { "epoch": 17.33, "learning_rate": 8.98671159164439e-05, "loss": 0.1751, "step": 72200 }, { "epoch": 17.33, "learning_rate": 8.9864407750609e-05, "loss": 0.1529, "step": 72210 }, { "epoch": 17.33, "learning_rate": 8.986169926374051e-05, "loss": 0.1622, "step": 72220 }, { "epoch": 17.33, "learning_rate": 8.985899045586028e-05, "loss": 0.1432, "step": 72230 }, { "epoch": 17.34, "learning_rate": 8.985628132699008e-05, "loss": 0.1392, "step": 72240 }, { "epoch": 17.34, "learning_rate": 8.985357187715175e-05, "loss": 0.1479, "step": 72250 }, { "epoch": 17.34, "learning_rate": 8.985086210636709e-05, "loss": 0.1528, "step": 72260 }, { "epoch": 17.34, "learning_rate": 8.984815201465795e-05, "loss": 0.1156, "step": 72270 }, { "epoch": 17.34, "learning_rate": 8.984544160204613e-05, "loss": 0.1525, "step": 72280 }, { "epoch": 17.35, "learning_rate": 8.984273086855349e-05, "loss": 0.1205, "step": 72290 }, { "epoch": 17.35, "learning_rate": 8.98400198142018e-05, "loss": 0.1334, "step": 72300 }, { "epoch": 17.35, "learning_rate": 8.983730843901295e-05, "loss": 0.2003, "step": 72310 }, { "epoch": 17.35, "learning_rate": 8.983459674300876e-05, "loss": 0.1449, "step": 72320 }, { "epoch": 17.36, "learning_rate": 8.983188472621106e-05, "loss": 0.1495, "step": 72330 }, { "epoch": 17.36, "learning_rate": 8.982917238864169e-05, "loss": 0.1479, "step": 72340 }, { "epoch": 17.36, "learning_rate": 8.982645973032251e-05, "loss": 0.1558, "step": 72350 }, { "epoch": 17.36, "learning_rate": 8.982374675127534e-05, "loss": 0.1473, "step": 72360 }, { "epoch": 17.37, "learning_rate": 8.982103345152204e-05, "loss": 0.1806, "step": 72370 }, { "epoch": 17.37, "learning_rate": 8.981831983108445e-05, "loss": 0.1242, "step": 72380 }, { "epoch": 17.37, "learning_rate": 8.981560588998444e-05, "loss": 0.1161, "step": 72390 }, { "epoch": 17.37, "learning_rate": 8.981289162824387e-05, "loss": 0.1484, "step": 72400 }, { "epoch": 17.37, "learning_rate": 8.981017704588457e-05, "loss": 0.1425, "step": 72410 }, { "epoch": 17.38, "learning_rate": 8.980746214292843e-05, "loss": 0.171, "step": 72420 }, { "epoch": 17.38, "learning_rate": 8.980474691939731e-05, "loss": 0.1708, "step": 72430 }, { "epoch": 17.38, "learning_rate": 8.980203137531305e-05, "loss": 0.1919, "step": 72440 }, { "epoch": 17.38, "learning_rate": 8.979931551069754e-05, "loss": 0.15, "step": 72450 }, { "epoch": 17.39, "learning_rate": 8.979659932557266e-05, "loss": 0.1353, "step": 72460 }, { "epoch": 17.39, "learning_rate": 8.979388281996024e-05, "loss": 0.1323, "step": 72470 }, { "epoch": 17.39, "learning_rate": 8.979116599388222e-05, "loss": 0.142, "step": 72480 }, { "epoch": 17.39, "learning_rate": 8.978844884736044e-05, "loss": 0.1785, "step": 72490 }, { "epoch": 17.4, "learning_rate": 8.978573138041677e-05, "loss": 0.1278, "step": 72500 }, { "epoch": 17.4, "learning_rate": 8.978301359307312e-05, "loss": 0.1848, "step": 72510 }, { "epoch": 17.4, "learning_rate": 8.978029548535138e-05, "loss": 0.163, "step": 72520 }, { "epoch": 17.4, "learning_rate": 8.977757705727343e-05, "loss": 0.1265, "step": 72530 }, { "epoch": 17.4, "learning_rate": 8.977485830886117e-05, "loss": 0.1099, "step": 72540 }, { "epoch": 17.41, "learning_rate": 8.977213924013645e-05, "loss": 0.1271, "step": 72550 }, { "epoch": 17.41, "learning_rate": 8.976941985112122e-05, "loss": 0.1068, "step": 72560 }, { "epoch": 17.41, "learning_rate": 8.976670014183736e-05, "loss": 0.127, "step": 72570 }, { "epoch": 17.41, "learning_rate": 8.976398011230677e-05, "loss": 0.1797, "step": 72580 }, { "epoch": 17.42, "learning_rate": 8.976125976255139e-05, "loss": 0.1051, "step": 72590 }, { "epoch": 17.42, "learning_rate": 8.975853909259307e-05, "loss": 0.1111, "step": 72600 }, { "epoch": 17.42, "learning_rate": 8.975581810245374e-05, "loss": 0.1496, "step": 72610 }, { "epoch": 17.42, "learning_rate": 8.975309679215532e-05, "loss": 0.1124, "step": 72620 }, { "epoch": 17.42, "learning_rate": 8.975037516171972e-05, "loss": 0.1452, "step": 72630 }, { "epoch": 17.43, "learning_rate": 8.974765321116886e-05, "loss": 0.1265, "step": 72640 }, { "epoch": 17.43, "learning_rate": 8.974493094052469e-05, "loss": 0.1068, "step": 72650 }, { "epoch": 17.43, "learning_rate": 8.974220834980908e-05, "loss": 0.1433, "step": 72660 }, { "epoch": 17.43, "learning_rate": 8.973948543904399e-05, "loss": 0.1329, "step": 72670 }, { "epoch": 17.44, "learning_rate": 8.973676220825132e-05, "loss": 0.1723, "step": 72680 }, { "epoch": 17.44, "learning_rate": 8.973403865745302e-05, "loss": 0.1228, "step": 72690 }, { "epoch": 17.44, "learning_rate": 8.973131478667104e-05, "loss": 0.1315, "step": 72700 }, { "epoch": 17.44, "learning_rate": 8.972859059592729e-05, "loss": 0.1582, "step": 72710 }, { "epoch": 17.45, "learning_rate": 8.972586608524371e-05, "loss": 0.1419, "step": 72720 }, { "epoch": 17.45, "learning_rate": 8.972314125464224e-05, "loss": 0.1329, "step": 72730 }, { "epoch": 17.45, "learning_rate": 8.972041610414483e-05, "loss": 0.1305, "step": 72740 }, { "epoch": 17.45, "learning_rate": 8.971769063377345e-05, "loss": 0.1451, "step": 72750 }, { "epoch": 17.45, "learning_rate": 8.971496484355e-05, "loss": 0.1643, "step": 72760 }, { "epoch": 17.46, "learning_rate": 8.971223873349646e-05, "loss": 0.1222, "step": 72770 }, { "epoch": 17.46, "learning_rate": 8.970951230363478e-05, "loss": 0.1425, "step": 72780 }, { "epoch": 17.46, "learning_rate": 8.97067855539869e-05, "loss": 0.1141, "step": 72790 }, { "epoch": 17.46, "learning_rate": 8.970405848457482e-05, "loss": 0.1235, "step": 72800 }, { "epoch": 17.47, "learning_rate": 8.970133109542046e-05, "loss": 0.1218, "step": 72810 }, { "epoch": 17.47, "learning_rate": 8.969860338654581e-05, "loss": 0.1574, "step": 72820 }, { "epoch": 17.47, "learning_rate": 8.969587535797281e-05, "loss": 0.1261, "step": 72830 }, { "epoch": 17.47, "learning_rate": 8.969314700972347e-05, "loss": 0.148, "step": 72840 }, { "epoch": 17.48, "learning_rate": 8.969041834181971e-05, "loss": 0.1233, "step": 72850 }, { "epoch": 17.48, "learning_rate": 8.968768935428356e-05, "loss": 0.2164, "step": 72860 }, { "epoch": 17.48, "learning_rate": 8.968496004713694e-05, "loss": 0.1755, "step": 72870 }, { "epoch": 17.48, "learning_rate": 8.968223042040187e-05, "loss": 0.172, "step": 72880 }, { "epoch": 17.48, "learning_rate": 8.967950047410032e-05, "loss": 0.1568, "step": 72890 }, { "epoch": 17.49, "learning_rate": 8.967677020825428e-05, "loss": 0.1682, "step": 72900 }, { "epoch": 17.49, "learning_rate": 8.967403962288572e-05, "loss": 0.1166, "step": 72910 }, { "epoch": 17.49, "learning_rate": 8.967130871801666e-05, "loss": 0.1683, "step": 72920 }, { "epoch": 17.49, "learning_rate": 8.966857749366906e-05, "loss": 0.1437, "step": 72930 }, { "epoch": 17.5, "learning_rate": 8.966584594986493e-05, "loss": 0.1259, "step": 72940 }, { "epoch": 17.5, "learning_rate": 8.966311408662627e-05, "loss": 0.1731, "step": 72950 }, { "epoch": 17.5, "learning_rate": 8.966038190397508e-05, "loss": 0.149, "step": 72960 }, { "epoch": 17.5, "learning_rate": 8.965764940193334e-05, "loss": 0.1528, "step": 72970 }, { "epoch": 17.5, "learning_rate": 8.96549165805231e-05, "loss": 0.1332, "step": 72980 }, { "epoch": 17.51, "learning_rate": 8.965218343976631e-05, "loss": 0.1251, "step": 72990 }, { "epoch": 17.51, "learning_rate": 8.964944997968505e-05, "loss": 0.1301, "step": 73000 }, { "epoch": 17.51, "learning_rate": 8.964671620030127e-05, "loss": 0.1282, "step": 73010 }, { "epoch": 17.51, "learning_rate": 8.964398210163702e-05, "loss": 0.1421, "step": 73020 }, { "epoch": 17.52, "learning_rate": 8.964124768371431e-05, "loss": 0.1675, "step": 73030 }, { "epoch": 17.52, "learning_rate": 8.963851294655516e-05, "loss": 0.1519, "step": 73040 }, { "epoch": 17.52, "learning_rate": 8.963577789018158e-05, "loss": 0.1381, "step": 73050 }, { "epoch": 17.52, "learning_rate": 8.963304251461562e-05, "loss": 0.1229, "step": 73060 }, { "epoch": 17.53, "learning_rate": 8.96303068198793e-05, "loss": 0.1323, "step": 73070 }, { "epoch": 17.53, "learning_rate": 8.962757080599463e-05, "loss": 0.1794, "step": 73080 }, { "epoch": 17.53, "learning_rate": 8.962483447298368e-05, "loss": 0.1629, "step": 73090 }, { "epoch": 17.53, "learning_rate": 8.962209782086846e-05, "loss": 0.18, "step": 73100 }, { "epoch": 17.53, "learning_rate": 8.961936084967102e-05, "loss": 0.1848, "step": 73110 }, { "epoch": 17.54, "learning_rate": 8.961662355941339e-05, "loss": 0.1945, "step": 73120 }, { "epoch": 17.54, "learning_rate": 8.961388595011763e-05, "loss": 0.1812, "step": 73130 }, { "epoch": 17.54, "learning_rate": 8.961114802180577e-05, "loss": 0.1876, "step": 73140 }, { "epoch": 17.54, "learning_rate": 8.960840977449987e-05, "loss": 0.1898, "step": 73150 }, { "epoch": 17.55, "learning_rate": 8.960567120822199e-05, "loss": 0.1733, "step": 73160 }, { "epoch": 17.55, "learning_rate": 8.960293232299414e-05, "loss": 0.2108, "step": 73170 }, { "epoch": 17.55, "learning_rate": 8.960019311883844e-05, "loss": 0.2149, "step": 73180 }, { "epoch": 17.55, "learning_rate": 8.95974535957769e-05, "loss": 0.1791, "step": 73190 }, { "epoch": 17.56, "learning_rate": 8.95947137538316e-05, "loss": 0.1678, "step": 73200 }, { "epoch": 17.56, "learning_rate": 8.959197359302462e-05, "loss": 0.1915, "step": 73210 }, { "epoch": 17.56, "learning_rate": 8.958923311337799e-05, "loss": 0.2132, "step": 73220 }, { "epoch": 17.56, "learning_rate": 8.95864923149138e-05, "loss": 0.176, "step": 73230 }, { "epoch": 17.56, "learning_rate": 8.958375119765414e-05, "loss": 0.1993, "step": 73240 }, { "epoch": 17.57, "learning_rate": 8.958100976162107e-05, "loss": 0.1745, "step": 73250 }, { "epoch": 17.57, "learning_rate": 8.957826800683664e-05, "loss": 0.1429, "step": 73260 }, { "epoch": 17.57, "learning_rate": 8.957552593332297e-05, "loss": 0.168, "step": 73270 }, { "epoch": 17.57, "learning_rate": 8.957278354110212e-05, "loss": 0.1481, "step": 73280 }, { "epoch": 17.58, "learning_rate": 8.957004083019618e-05, "loss": 0.1855, "step": 73290 }, { "epoch": 17.58, "learning_rate": 8.956729780062725e-05, "loss": 0.1698, "step": 73300 }, { "epoch": 17.58, "learning_rate": 8.956455445241741e-05, "loss": 0.1814, "step": 73310 }, { "epoch": 17.58, "learning_rate": 8.956181078558872e-05, "loss": 0.1542, "step": 73320 }, { "epoch": 17.58, "learning_rate": 8.955906680016333e-05, "loss": 0.1597, "step": 73330 }, { "epoch": 17.59, "learning_rate": 8.955632249616331e-05, "loss": 0.1787, "step": 73340 }, { "epoch": 17.59, "learning_rate": 8.955357787361077e-05, "loss": 0.1876, "step": 73350 }, { "epoch": 17.59, "learning_rate": 8.95508329325278e-05, "loss": 0.1824, "step": 73360 }, { "epoch": 17.59, "learning_rate": 8.954808767293651e-05, "loss": 0.1663, "step": 73370 }, { "epoch": 17.6, "learning_rate": 8.9545342094859e-05, "loss": 0.1681, "step": 73380 }, { "epoch": 17.6, "learning_rate": 8.95425961983174e-05, "loss": 0.1714, "step": 73390 }, { "epoch": 17.6, "learning_rate": 8.953984998333382e-05, "loss": 0.1907, "step": 73400 }, { "epoch": 17.6, "learning_rate": 8.953710344993036e-05, "loss": 0.1998, "step": 73410 }, { "epoch": 17.61, "learning_rate": 8.953435659812916e-05, "loss": 0.1731, "step": 73420 }, { "epoch": 17.61, "learning_rate": 8.953160942795234e-05, "loss": 0.1692, "step": 73430 }, { "epoch": 17.61, "learning_rate": 8.952886193942198e-05, "loss": 0.1678, "step": 73440 }, { "epoch": 17.61, "learning_rate": 8.952611413256025e-05, "loss": 0.1949, "step": 73450 }, { "epoch": 17.61, "learning_rate": 8.952336600738926e-05, "loss": 0.1942, "step": 73460 }, { "epoch": 17.62, "learning_rate": 8.952061756393116e-05, "loss": 0.2001, "step": 73470 }, { "epoch": 17.62, "learning_rate": 8.951786880220806e-05, "loss": 0.1817, "step": 73480 }, { "epoch": 17.62, "learning_rate": 8.951511972224212e-05, "loss": 0.169, "step": 73490 }, { "epoch": 17.62, "learning_rate": 8.951237032405544e-05, "loss": 0.1984, "step": 73500 }, { "epoch": 17.63, "learning_rate": 8.950962060767021e-05, "loss": 0.2385, "step": 73510 }, { "epoch": 17.63, "learning_rate": 8.950687057310854e-05, "loss": 0.1885, "step": 73520 }, { "epoch": 17.63, "learning_rate": 8.950412022039259e-05, "loss": 0.2126, "step": 73530 }, { "epoch": 17.63, "learning_rate": 8.950136954954451e-05, "loss": 0.2139, "step": 73540 }, { "epoch": 17.64, "learning_rate": 8.949861856058645e-05, "loss": 0.1124, "step": 73550 }, { "epoch": 17.64, "learning_rate": 8.949586725354056e-05, "loss": 0.1579, "step": 73560 }, { "epoch": 17.64, "learning_rate": 8.9493115628429e-05, "loss": 0.1426, "step": 73570 }, { "epoch": 17.64, "learning_rate": 8.94903636852739e-05, "loss": 0.1432, "step": 73580 }, { "epoch": 17.64, "learning_rate": 8.948761142409747e-05, "loss": 0.176, "step": 73590 }, { "epoch": 17.65, "learning_rate": 8.948485884492186e-05, "loss": 0.1825, "step": 73600 }, { "epoch": 17.65, "learning_rate": 8.948210594776923e-05, "loss": 0.1312, "step": 73610 }, { "epoch": 17.65, "learning_rate": 8.947935273266174e-05, "loss": 0.1352, "step": 73620 }, { "epoch": 17.65, "learning_rate": 8.947659919962157e-05, "loss": 0.1389, "step": 73630 }, { "epoch": 17.66, "learning_rate": 8.947384534867092e-05, "loss": 0.178, "step": 73640 }, { "epoch": 17.66, "learning_rate": 8.947109117983191e-05, "loss": 0.1805, "step": 73650 }, { "epoch": 17.66, "learning_rate": 8.946833669312678e-05, "loss": 0.1851, "step": 73660 }, { "epoch": 17.66, "learning_rate": 8.946558188857767e-05, "loss": 0.144, "step": 73670 }, { "epoch": 17.66, "learning_rate": 8.946282676620678e-05, "loss": 0.1671, "step": 73680 }, { "epoch": 17.67, "learning_rate": 8.94600713260363e-05, "loss": 0.214, "step": 73690 }, { "epoch": 17.67, "learning_rate": 8.945731556808843e-05, "loss": 0.1775, "step": 73700 }, { "epoch": 17.67, "learning_rate": 8.945455949238535e-05, "loss": 0.1301, "step": 73710 }, { "epoch": 17.67, "learning_rate": 8.945180309894923e-05, "loss": 0.1662, "step": 73720 }, { "epoch": 17.68, "learning_rate": 8.944904638780232e-05, "loss": 0.1771, "step": 73730 }, { "epoch": 17.68, "learning_rate": 8.944628935896678e-05, "loss": 0.1346, "step": 73740 }, { "epoch": 17.68, "learning_rate": 8.944353201246483e-05, "loss": 0.1373, "step": 73750 }, { "epoch": 17.68, "learning_rate": 8.944077434831867e-05, "loss": 0.1576, "step": 73760 }, { "epoch": 17.69, "learning_rate": 8.943801636655051e-05, "loss": 0.1807, "step": 73770 }, { "epoch": 17.69, "learning_rate": 8.943525806718256e-05, "loss": 0.2134, "step": 73780 }, { "epoch": 17.69, "learning_rate": 8.943249945023703e-05, "loss": 0.1642, "step": 73790 }, { "epoch": 17.69, "learning_rate": 8.942974051573615e-05, "loss": 0.1716, "step": 73800 }, { "epoch": 17.69, "learning_rate": 8.942698126370211e-05, "loss": 0.1802, "step": 73810 }, { "epoch": 17.7, "learning_rate": 8.942422169415716e-05, "loss": 0.1199, "step": 73820 }, { "epoch": 17.7, "learning_rate": 8.942146180712349e-05, "loss": 0.1809, "step": 73830 }, { "epoch": 17.7, "learning_rate": 8.941870160262337e-05, "loss": 0.1567, "step": 73840 }, { "epoch": 17.7, "learning_rate": 8.941594108067898e-05, "loss": 0.1555, "step": 73850 }, { "epoch": 17.71, "learning_rate": 8.94131802413126e-05, "loss": 0.1885, "step": 73860 }, { "epoch": 17.71, "learning_rate": 8.941041908454642e-05, "loss": 0.1535, "step": 73870 }, { "epoch": 17.71, "learning_rate": 8.94076576104027e-05, "loss": 0.1593, "step": 73880 }, { "epoch": 17.71, "learning_rate": 8.940489581890366e-05, "loss": 0.1538, "step": 73890 }, { "epoch": 17.72, "learning_rate": 8.940213371007157e-05, "loss": 0.1539, "step": 73900 }, { "epoch": 17.72, "learning_rate": 8.939937128392865e-05, "loss": 0.1485, "step": 73910 }, { "epoch": 17.72, "learning_rate": 8.939660854049716e-05, "loss": 0.1308, "step": 73920 }, { "epoch": 17.72, "learning_rate": 8.939384547979935e-05, "loss": 0.1786, "step": 73930 }, { "epoch": 17.72, "learning_rate": 8.939108210185744e-05, "loss": 0.1545, "step": 73940 }, { "epoch": 17.73, "learning_rate": 8.938831840669373e-05, "loss": 0.1523, "step": 73950 }, { "epoch": 17.73, "learning_rate": 8.938555439433044e-05, "loss": 0.1763, "step": 73960 }, { "epoch": 17.73, "learning_rate": 8.938279006478984e-05, "loss": 0.141, "step": 73970 }, { "epoch": 17.73, "learning_rate": 8.93800254180942e-05, "loss": 0.1634, "step": 73980 }, { "epoch": 17.74, "learning_rate": 8.937726045426579e-05, "loss": 0.1621, "step": 73990 }, { "epoch": 17.74, "learning_rate": 8.937449517332685e-05, "loss": 0.1574, "step": 74000 }, { "epoch": 17.74, "learning_rate": 8.937172957529966e-05, "loss": 0.1445, "step": 74010 }, { "epoch": 17.74, "learning_rate": 8.936896366020651e-05, "loss": 0.1351, "step": 74020 }, { "epoch": 17.74, "learning_rate": 8.936619742806966e-05, "loss": 0.1652, "step": 74030 }, { "epoch": 17.75, "learning_rate": 8.936343087891139e-05, "loss": 0.1785, "step": 74040 }, { "epoch": 17.75, "learning_rate": 8.936066401275396e-05, "loss": 0.1645, "step": 74050 }, { "epoch": 17.75, "learning_rate": 8.935789682961967e-05, "loss": 0.1706, "step": 74060 }, { "epoch": 17.75, "learning_rate": 8.935512932953082e-05, "loss": 0.1695, "step": 74070 }, { "epoch": 17.76, "learning_rate": 8.935236151250967e-05, "loss": 0.1416, "step": 74080 }, { "epoch": 17.76, "learning_rate": 8.934959337857853e-05, "loss": 0.1726, "step": 74090 }, { "epoch": 17.76, "learning_rate": 8.934682492775968e-05, "loss": 0.1827, "step": 74100 }, { "epoch": 17.76, "learning_rate": 8.93440561600754e-05, "loss": 0.1639, "step": 74110 }, { "epoch": 17.77, "learning_rate": 8.934128707554802e-05, "loss": 0.1418, "step": 74120 }, { "epoch": 17.77, "learning_rate": 8.933851767419982e-05, "loss": 0.1794, "step": 74130 }, { "epoch": 17.77, "learning_rate": 8.93357479560531e-05, "loss": 0.1558, "step": 74140 }, { "epoch": 17.77, "learning_rate": 8.933297792113017e-05, "loss": 0.1703, "step": 74150 }, { "epoch": 17.77, "learning_rate": 8.933020756945335e-05, "loss": 0.1846, "step": 74160 }, { "epoch": 17.78, "learning_rate": 8.932743690104493e-05, "loss": 0.1504, "step": 74170 }, { "epoch": 17.78, "learning_rate": 8.932466591592723e-05, "loss": 0.1635, "step": 74180 }, { "epoch": 17.78, "learning_rate": 8.932189461412258e-05, "loss": 0.1304, "step": 74190 }, { "epoch": 17.78, "learning_rate": 8.931912299565327e-05, "loss": 0.1668, "step": 74200 }, { "epoch": 17.79, "learning_rate": 8.931635106054164e-05, "loss": 0.1494, "step": 74210 }, { "epoch": 17.79, "learning_rate": 8.931357880881001e-05, "loss": 0.1519, "step": 74220 }, { "epoch": 17.79, "learning_rate": 8.931080624048069e-05, "loss": 0.1193, "step": 74230 }, { "epoch": 17.79, "learning_rate": 8.930803335557602e-05, "loss": 0.1393, "step": 74240 }, { "epoch": 17.8, "learning_rate": 8.930526015411835e-05, "loss": 0.159, "step": 74250 }, { "epoch": 17.8, "learning_rate": 8.930248663612997e-05, "loss": 0.1649, "step": 74260 }, { "epoch": 17.8, "learning_rate": 8.929971280163326e-05, "loss": 0.1904, "step": 74270 }, { "epoch": 17.8, "learning_rate": 8.929693865065053e-05, "loss": 0.1658, "step": 74280 }, { "epoch": 17.8, "learning_rate": 8.929416418320413e-05, "loss": 0.1198, "step": 74290 }, { "epoch": 17.81, "learning_rate": 8.929138939931639e-05, "loss": 0.1067, "step": 74300 }, { "epoch": 17.81, "learning_rate": 8.928861429900968e-05, "loss": 0.2104, "step": 74310 }, { "epoch": 17.81, "learning_rate": 8.928583888230632e-05, "loss": 0.1587, "step": 74320 }, { "epoch": 17.81, "learning_rate": 8.928306314922869e-05, "loss": 0.149, "step": 74330 }, { "epoch": 17.82, "learning_rate": 8.928028709979912e-05, "loss": 0.1395, "step": 74340 }, { "epoch": 17.82, "learning_rate": 8.927751073403999e-05, "loss": 0.1808, "step": 74350 }, { "epoch": 17.82, "learning_rate": 8.927473405197362e-05, "loss": 0.1342, "step": 74360 }, { "epoch": 17.82, "learning_rate": 8.927195705362241e-05, "loss": 0.1527, "step": 74370 }, { "epoch": 17.82, "learning_rate": 8.92691797390087e-05, "loss": 0.1601, "step": 74380 }, { "epoch": 17.83, "learning_rate": 8.926640210815486e-05, "loss": 0.1531, "step": 74390 }, { "epoch": 17.83, "learning_rate": 8.926362416108327e-05, "loss": 0.1705, "step": 74400 }, { "epoch": 17.83, "learning_rate": 8.926084589781631e-05, "loss": 0.1374, "step": 74410 }, { "epoch": 17.83, "learning_rate": 8.925806731837632e-05, "loss": 0.1413, "step": 74420 }, { "epoch": 17.84, "learning_rate": 8.92552884227857e-05, "loss": 0.1463, "step": 74430 }, { "epoch": 17.84, "learning_rate": 8.92525092110668e-05, "loss": 0.1524, "step": 74440 }, { "epoch": 17.84, "learning_rate": 8.924972968324205e-05, "loss": 0.181, "step": 74450 }, { "epoch": 17.84, "learning_rate": 8.92469498393338e-05, "loss": 0.1498, "step": 74460 }, { "epoch": 17.85, "learning_rate": 8.924416967936445e-05, "loss": 0.168, "step": 74470 }, { "epoch": 17.85, "learning_rate": 8.924138920335639e-05, "loss": 0.1486, "step": 74480 }, { "epoch": 17.85, "learning_rate": 8.923860841133198e-05, "loss": 0.1581, "step": 74490 }, { "epoch": 17.85, "learning_rate": 8.923582730331366e-05, "loss": 0.11, "step": 74500 }, { "epoch": 17.85, "learning_rate": 8.92330458793238e-05, "loss": 0.1284, "step": 74510 }, { "epoch": 17.86, "learning_rate": 8.92302641393848e-05, "loss": 0.1443, "step": 74520 }, { "epoch": 17.86, "learning_rate": 8.922748208351908e-05, "loss": 0.1755, "step": 74530 }, { "epoch": 17.86, "learning_rate": 8.922469971174902e-05, "loss": 0.1359, "step": 74540 }, { "epoch": 17.86, "learning_rate": 8.922191702409703e-05, "loss": 0.1559, "step": 74550 }, { "epoch": 17.87, "learning_rate": 8.921913402058555e-05, "loss": 0.1417, "step": 74560 }, { "epoch": 17.87, "learning_rate": 8.921635070123695e-05, "loss": 0.131, "step": 74570 }, { "epoch": 17.87, "learning_rate": 8.921356706607366e-05, "loss": 0.1442, "step": 74580 }, { "epoch": 17.87, "learning_rate": 8.921078311511813e-05, "loss": 0.2011, "step": 74590 }, { "epoch": 17.88, "learning_rate": 8.920799884839272e-05, "loss": 0.1614, "step": 74600 }, { "epoch": 17.88, "learning_rate": 8.92052142659199e-05, "loss": 0.1411, "step": 74610 }, { "epoch": 17.88, "learning_rate": 8.920242936772207e-05, "loss": 0.1565, "step": 74620 }, { "epoch": 17.88, "learning_rate": 8.919964415382167e-05, "loss": 0.1262, "step": 74630 }, { "epoch": 17.88, "learning_rate": 8.919685862424112e-05, "loss": 0.1486, "step": 74640 }, { "epoch": 17.89, "learning_rate": 8.919407277900285e-05, "loss": 0.1482, "step": 74650 }, { "epoch": 17.89, "learning_rate": 8.91912866181293e-05, "loss": 0.1358, "step": 74660 }, { "epoch": 17.89, "learning_rate": 8.918850014164293e-05, "loss": 0.1448, "step": 74670 }, { "epoch": 17.89, "learning_rate": 8.918571334956614e-05, "loss": 0.1643, "step": 74680 }, { "epoch": 17.9, "learning_rate": 8.918292624192138e-05, "loss": 0.1595, "step": 74690 }, { "epoch": 17.9, "learning_rate": 8.918013881873112e-05, "loss": 0.1335, "step": 74700 }, { "epoch": 17.9, "learning_rate": 8.917735108001779e-05, "loss": 0.1494, "step": 74710 }, { "epoch": 17.9, "learning_rate": 8.917456302580385e-05, "loss": 0.1577, "step": 74720 }, { "epoch": 17.9, "learning_rate": 8.917177465611172e-05, "loss": 0.1212, "step": 74730 }, { "epoch": 17.91, "learning_rate": 8.916898597096392e-05, "loss": 0.1751, "step": 74740 }, { "epoch": 17.91, "learning_rate": 8.916619697038284e-05, "loss": 0.1337, "step": 74750 }, { "epoch": 17.91, "learning_rate": 8.916340765439097e-05, "loss": 0.1278, "step": 74760 }, { "epoch": 17.91, "learning_rate": 8.916061802301079e-05, "loss": 0.1279, "step": 74770 }, { "epoch": 17.92, "learning_rate": 8.915782807626473e-05, "loss": 0.1431, "step": 74780 }, { "epoch": 17.92, "learning_rate": 8.915503781417528e-05, "loss": 0.1467, "step": 74790 }, { "epoch": 17.92, "learning_rate": 8.915224723676489e-05, "loss": 0.1423, "step": 74800 }, { "epoch": 17.92, "learning_rate": 8.914945634405607e-05, "loss": 0.1106, "step": 74810 }, { "epoch": 17.93, "learning_rate": 8.914666513607128e-05, "loss": 0.1185, "step": 74820 }, { "epoch": 17.93, "learning_rate": 8.914387361283296e-05, "loss": 0.1245, "step": 74830 }, { "epoch": 17.93, "learning_rate": 8.914108177436364e-05, "loss": 0.145, "step": 74840 }, { "epoch": 17.93, "learning_rate": 8.913828962068579e-05, "loss": 0.1256, "step": 74850 }, { "epoch": 17.93, "learning_rate": 8.913549715182187e-05, "loss": 0.121, "step": 74860 }, { "epoch": 17.94, "learning_rate": 8.913270436779442e-05, "loss": 0.1506, "step": 74870 }, { "epoch": 17.94, "learning_rate": 8.912991126862586e-05, "loss": 0.1484, "step": 74880 }, { "epoch": 17.94, "learning_rate": 8.912711785433876e-05, "loss": 0.1486, "step": 74890 }, { "epoch": 17.94, "learning_rate": 8.912432412495555e-05, "loss": 0.2281, "step": 74900 }, { "epoch": 17.95, "learning_rate": 8.912153008049877e-05, "loss": 0.1683, "step": 74910 }, { "epoch": 17.95, "learning_rate": 8.91187357209909e-05, "loss": 0.1251, "step": 74920 }, { "epoch": 17.95, "learning_rate": 8.911594104645447e-05, "loss": 0.135, "step": 74930 }, { "epoch": 18.0, "learning_rate": 8.911314605691194e-05, "loss": 0.174, "step": 74940 }, { "epoch": 18.0, "learning_rate": 8.911035075238585e-05, "loss": 0.116, "step": 74950 }, { "epoch": 18.01, "learning_rate": 8.910755513289873e-05, "loss": 0.1264, "step": 74960 }, { "epoch": 18.01, "learning_rate": 8.910475919847304e-05, "loss": 0.1059, "step": 74970 }, { "epoch": 18.01, "learning_rate": 8.910196294913134e-05, "loss": 0.1484, "step": 74980 }, { "epoch": 18.01, "learning_rate": 8.909916638489613e-05, "loss": 0.0965, "step": 74990 }, { "epoch": 18.02, "learning_rate": 8.909636950578994e-05, "loss": 0.1641, "step": 75000 }, { "epoch": 18.02, "learning_rate": 8.909357231183529e-05, "loss": 0.1455, "step": 75010 }, { "epoch": 18.02, "learning_rate": 8.909077480305468e-05, "loss": 0.1274, "step": 75020 }, { "epoch": 18.02, "learning_rate": 8.90879769794707e-05, "loss": 0.1502, "step": 75030 }, { "epoch": 18.02, "learning_rate": 8.908517884110582e-05, "loss": 0.1596, "step": 75040 }, { "epoch": 18.03, "learning_rate": 8.90823803879826e-05, "loss": 0.1258, "step": 75050 }, { "epoch": 18.03, "learning_rate": 8.907958162012358e-05, "loss": 0.1379, "step": 75060 }, { "epoch": 18.03, "learning_rate": 8.90767825375513e-05, "loss": 0.1346, "step": 75070 }, { "epoch": 18.03, "learning_rate": 8.90739831402883e-05, "loss": 0.1331, "step": 75080 }, { "epoch": 18.04, "learning_rate": 8.907118342835711e-05, "loss": 0.1099, "step": 75090 }, { "epoch": 18.04, "learning_rate": 8.906838340178028e-05, "loss": 0.1197, "step": 75100 }, { "epoch": 18.04, "learning_rate": 8.906558306058037e-05, "loss": 0.1375, "step": 75110 }, { "epoch": 18.04, "learning_rate": 8.906278240477993e-05, "loss": 0.1221, "step": 75120 }, { "epoch": 18.04, "learning_rate": 8.905998143440151e-05, "loss": 0.1727, "step": 75130 }, { "epoch": 18.05, "learning_rate": 8.905718014946766e-05, "loss": 0.1535, "step": 75140 }, { "epoch": 18.05, "learning_rate": 8.905437855000096e-05, "loss": 0.1594, "step": 75150 }, { "epoch": 18.05, "learning_rate": 8.905157663602395e-05, "loss": 0.1515, "step": 75160 }, { "epoch": 18.05, "learning_rate": 8.904877440755919e-05, "loss": 0.1355, "step": 75170 }, { "epoch": 18.06, "learning_rate": 8.904597186462927e-05, "loss": 0.1602, "step": 75180 }, { "epoch": 18.06, "learning_rate": 8.904316900725675e-05, "loss": 0.1186, "step": 75190 }, { "epoch": 18.06, "learning_rate": 8.90403658354642e-05, "loss": 0.129, "step": 75200 }, { "epoch": 18.06, "learning_rate": 8.903756234927418e-05, "loss": 0.1629, "step": 75210 }, { "epoch": 18.07, "learning_rate": 8.903475854870931e-05, "loss": 0.1268, "step": 75220 }, { "epoch": 18.07, "learning_rate": 8.903195443379211e-05, "loss": 0.1118, "step": 75230 }, { "epoch": 18.07, "learning_rate": 8.902915000454521e-05, "loss": 0.1119, "step": 75240 }, { "epoch": 18.07, "learning_rate": 8.902634526099117e-05, "loss": 0.119, "step": 75250 }, { "epoch": 18.07, "learning_rate": 8.902354020315257e-05, "loss": 0.1279, "step": 75260 }, { "epoch": 18.08, "learning_rate": 8.902073483105204e-05, "loss": 0.1572, "step": 75270 }, { "epoch": 18.08, "learning_rate": 8.901792914471213e-05, "loss": 0.1297, "step": 75280 }, { "epoch": 18.08, "learning_rate": 8.901512314415545e-05, "loss": 0.1412, "step": 75290 }, { "epoch": 18.08, "learning_rate": 8.901231682940461e-05, "loss": 0.128, "step": 75300 }, { "epoch": 18.09, "learning_rate": 8.900951020048218e-05, "loss": 0.1241, "step": 75310 }, { "epoch": 18.09, "learning_rate": 8.900670325741078e-05, "loss": 0.1262, "step": 75320 }, { "epoch": 18.09, "learning_rate": 8.900389600021303e-05, "loss": 0.1443, "step": 75330 }, { "epoch": 18.09, "learning_rate": 8.90010884289115e-05, "loss": 0.1422, "step": 75340 }, { "epoch": 18.1, "learning_rate": 8.899828054352883e-05, "loss": 0.1255, "step": 75350 }, { "epoch": 18.1, "learning_rate": 8.899547234408763e-05, "loss": 0.098, "step": 75360 }, { "epoch": 18.1, "learning_rate": 8.89926638306105e-05, "loss": 0.0882, "step": 75370 }, { "epoch": 18.1, "learning_rate": 8.898985500312007e-05, "loss": 0.1433, "step": 75380 }, { "epoch": 18.1, "learning_rate": 8.898704586163896e-05, "loss": 0.1255, "step": 75390 }, { "epoch": 18.11, "learning_rate": 8.898423640618976e-05, "loss": 0.1506, "step": 75400 }, { "epoch": 18.11, "learning_rate": 8.898142663679514e-05, "loss": 0.1354, "step": 75410 }, { "epoch": 18.11, "learning_rate": 8.897861655347771e-05, "loss": 0.123, "step": 75420 }, { "epoch": 18.11, "learning_rate": 8.89758061562601e-05, "loss": 0.1284, "step": 75430 }, { "epoch": 18.12, "learning_rate": 8.897299544516494e-05, "loss": 0.1621, "step": 75440 }, { "epoch": 18.12, "learning_rate": 8.897018442021487e-05, "loss": 0.156, "step": 75450 }, { "epoch": 18.12, "learning_rate": 8.896737308143253e-05, "loss": 0.1479, "step": 75460 }, { "epoch": 18.12, "learning_rate": 8.896456142884054e-05, "loss": 0.1092, "step": 75470 }, { "epoch": 18.12, "learning_rate": 8.896174946246156e-05, "loss": 0.1072, "step": 75480 }, { "epoch": 18.13, "learning_rate": 8.895893718231825e-05, "loss": 0.116, "step": 75490 }, { "epoch": 18.13, "learning_rate": 8.89561245884332e-05, "loss": 0.1623, "step": 75500 }, { "epoch": 18.13, "learning_rate": 8.895331168082915e-05, "loss": 0.1271, "step": 75510 }, { "epoch": 18.13, "learning_rate": 8.895049845952868e-05, "loss": 0.1875, "step": 75520 }, { "epoch": 18.14, "learning_rate": 8.894768492455446e-05, "loss": 0.1213, "step": 75530 }, { "epoch": 18.14, "learning_rate": 8.894487107592917e-05, "loss": 0.1105, "step": 75540 }, { "epoch": 18.14, "learning_rate": 8.894205691367545e-05, "loss": 0.1401, "step": 75550 }, { "epoch": 18.14, "learning_rate": 8.893924243781597e-05, "loss": 0.1397, "step": 75560 }, { "epoch": 18.15, "learning_rate": 8.89364276483734e-05, "loss": 0.1315, "step": 75570 }, { "epoch": 18.15, "learning_rate": 8.893361254537041e-05, "loss": 0.0962, "step": 75580 }, { "epoch": 18.15, "learning_rate": 8.893079712882964e-05, "loss": 0.1043, "step": 75590 }, { "epoch": 18.15, "learning_rate": 8.89279813987738e-05, "loss": 0.1084, "step": 75600 }, { "epoch": 18.15, "learning_rate": 8.892516535522554e-05, "loss": 0.0931, "step": 75610 }, { "epoch": 18.16, "learning_rate": 8.892234899820757e-05, "loss": 0.1306, "step": 75620 }, { "epoch": 18.16, "learning_rate": 8.891953232774254e-05, "loss": 0.1478, "step": 75630 }, { "epoch": 18.16, "learning_rate": 8.891671534385314e-05, "loss": 0.1488, "step": 75640 }, { "epoch": 18.16, "learning_rate": 8.891389804656205e-05, "loss": 0.1655, "step": 75650 }, { "epoch": 18.17, "learning_rate": 8.891108043589199e-05, "loss": 0.1514, "step": 75660 }, { "epoch": 18.17, "learning_rate": 8.890826251186561e-05, "loss": 0.1032, "step": 75670 }, { "epoch": 18.17, "learning_rate": 8.890544427450563e-05, "loss": 0.1101, "step": 75680 }, { "epoch": 18.17, "learning_rate": 8.890262572383472e-05, "loss": 0.1439, "step": 75690 }, { "epoch": 18.18, "learning_rate": 8.889980685987562e-05, "loss": 0.1379, "step": 75700 }, { "epoch": 18.18, "learning_rate": 8.889698768265098e-05, "loss": 0.1297, "step": 75710 }, { "epoch": 18.18, "learning_rate": 8.889416819218354e-05, "loss": 0.0941, "step": 75720 }, { "epoch": 18.18, "learning_rate": 8.8891348388496e-05, "loss": 0.118, "step": 75730 }, { "epoch": 18.18, "learning_rate": 8.888852827161105e-05, "loss": 0.1457, "step": 75740 }, { "epoch": 18.19, "learning_rate": 8.888570784155142e-05, "loss": 0.1812, "step": 75750 }, { "epoch": 18.19, "learning_rate": 8.888288709833981e-05, "loss": 0.193, "step": 75760 }, { "epoch": 18.19, "learning_rate": 8.888006604199894e-05, "loss": 0.1443, "step": 75770 }, { "epoch": 18.19, "learning_rate": 8.887724467255154e-05, "loss": 0.1122, "step": 75780 }, { "epoch": 18.2, "learning_rate": 8.88744229900203e-05, "loss": 0.1605, "step": 75790 }, { "epoch": 18.2, "learning_rate": 8.8871600994428e-05, "loss": 0.0953, "step": 75800 }, { "epoch": 18.2, "learning_rate": 8.886877868579731e-05, "loss": 0.1377, "step": 75810 }, { "epoch": 18.2, "learning_rate": 8.886595606415098e-05, "loss": 0.1775, "step": 75820 }, { "epoch": 18.2, "learning_rate": 8.886313312951173e-05, "loss": 0.1597, "step": 75830 }, { "epoch": 18.21, "learning_rate": 8.886030988190232e-05, "loss": 0.1469, "step": 75840 }, { "epoch": 18.21, "learning_rate": 8.885748632134548e-05, "loss": 0.1115, "step": 75850 }, { "epoch": 18.21, "learning_rate": 8.885466244786391e-05, "loss": 0.1281, "step": 75860 }, { "epoch": 18.21, "learning_rate": 8.88518382614804e-05, "loss": 0.1345, "step": 75870 }, { "epoch": 18.22, "learning_rate": 8.884901376221766e-05, "loss": 0.1723, "step": 75880 }, { "epoch": 18.22, "learning_rate": 8.884618895009846e-05, "loss": 0.1411, "step": 75890 }, { "epoch": 18.22, "learning_rate": 8.884336382514552e-05, "loss": 0.1426, "step": 75900 }, { "epoch": 18.22, "learning_rate": 8.884053838738162e-05, "loss": 0.1636, "step": 75910 }, { "epoch": 18.23, "learning_rate": 8.88377126368295e-05, "loss": 0.1414, "step": 75920 }, { "epoch": 18.23, "learning_rate": 8.883488657351192e-05, "loss": 0.1235, "step": 75930 }, { "epoch": 18.23, "learning_rate": 8.883206019745164e-05, "loss": 0.113, "step": 75940 }, { "epoch": 18.23, "learning_rate": 8.882923350867141e-05, "loss": 0.1081, "step": 75950 }, { "epoch": 18.23, "learning_rate": 8.8826406507194e-05, "loss": 0.1465, "step": 75960 }, { "epoch": 18.24, "learning_rate": 8.882357919304219e-05, "loss": 0.1332, "step": 75970 }, { "epoch": 18.24, "learning_rate": 8.882075156623872e-05, "loss": 0.1175, "step": 75980 }, { "epoch": 18.24, "learning_rate": 8.881792362680641e-05, "loss": 0.1546, "step": 75990 }, { "epoch": 18.24, "learning_rate": 8.881509537476797e-05, "loss": 0.1235, "step": 76000 }, { "epoch": 18.25, "learning_rate": 8.881226681014623e-05, "loss": 0.1319, "step": 76010 }, { "epoch": 18.25, "learning_rate": 8.880943793296392e-05, "loss": 0.119, "step": 76020 }, { "epoch": 18.25, "learning_rate": 8.880660874324387e-05, "loss": 0.1128, "step": 76030 }, { "epoch": 18.25, "learning_rate": 8.880377924100885e-05, "loss": 0.1512, "step": 76040 }, { "epoch": 18.26, "learning_rate": 8.880094942628162e-05, "loss": 0.1385, "step": 76050 }, { "epoch": 18.26, "learning_rate": 8.879811929908499e-05, "loss": 0.1168, "step": 76060 }, { "epoch": 18.26, "learning_rate": 8.879528885944174e-05, "loss": 0.1484, "step": 76070 }, { "epoch": 18.26, "learning_rate": 8.879245810737469e-05, "loss": 0.1258, "step": 76080 }, { "epoch": 18.26, "learning_rate": 8.87896270429066e-05, "loss": 0.1479, "step": 76090 }, { "epoch": 18.27, "learning_rate": 8.878679566606031e-05, "loss": 0.1205, "step": 76100 }, { "epoch": 18.27, "learning_rate": 8.87839639768586e-05, "loss": 0.0947, "step": 76110 }, { "epoch": 18.27, "learning_rate": 8.878113197532427e-05, "loss": 0.1485, "step": 76120 }, { "epoch": 18.27, "learning_rate": 8.877829966148013e-05, "loss": 0.117, "step": 76130 }, { "epoch": 18.28, "learning_rate": 8.877546703534898e-05, "loss": 0.1549, "step": 76140 }, { "epoch": 18.28, "learning_rate": 8.877263409695364e-05, "loss": 0.1311, "step": 76150 }, { "epoch": 18.28, "learning_rate": 8.876980084631693e-05, "loss": 0.1131, "step": 76160 }, { "epoch": 18.28, "learning_rate": 8.876696728346166e-05, "loss": 0.1044, "step": 76170 }, { "epoch": 18.28, "learning_rate": 8.876413340841065e-05, "loss": 0.1532, "step": 76180 }, { "epoch": 18.29, "learning_rate": 8.876129922118673e-05, "loss": 0.163, "step": 76190 }, { "epoch": 18.29, "learning_rate": 8.87584647218127e-05, "loss": 0.1352, "step": 76200 }, { "epoch": 18.29, "learning_rate": 8.875562991031141e-05, "loss": 0.1054, "step": 76210 }, { "epoch": 18.29, "learning_rate": 8.875279478670568e-05, "loss": 0.1692, "step": 76220 }, { "epoch": 18.3, "learning_rate": 8.874995935101836e-05, "loss": 0.1532, "step": 76230 }, { "epoch": 18.3, "learning_rate": 8.874712360327225e-05, "loss": 0.1313, "step": 76240 }, { "epoch": 18.3, "learning_rate": 8.874428754349021e-05, "loss": 0.1082, "step": 76250 }, { "epoch": 18.3, "learning_rate": 8.874145117169508e-05, "loss": 0.1706, "step": 76260 }, { "epoch": 18.31, "learning_rate": 8.873861448790968e-05, "loss": 0.1433, "step": 76270 }, { "epoch": 18.31, "learning_rate": 8.873577749215687e-05, "loss": 0.102, "step": 76280 }, { "epoch": 18.31, "learning_rate": 8.873294018445952e-05, "loss": 0.1054, "step": 76290 }, { "epoch": 18.31, "learning_rate": 8.873010256484044e-05, "loss": 0.0897, "step": 76300 }, { "epoch": 18.31, "learning_rate": 8.872726463332248e-05, "loss": 0.1689, "step": 76310 }, { "epoch": 18.32, "learning_rate": 8.872442638992853e-05, "loss": 0.139, "step": 76320 }, { "epoch": 18.32, "learning_rate": 8.872158783468142e-05, "loss": 0.1179, "step": 76330 }, { "epoch": 18.32, "learning_rate": 8.871874896760404e-05, "loss": 0.1056, "step": 76340 }, { "epoch": 18.32, "learning_rate": 8.87159097887192e-05, "loss": 0.1407, "step": 76350 }, { "epoch": 18.33, "learning_rate": 8.87130702980498e-05, "loss": 0.1191, "step": 76360 }, { "epoch": 18.33, "learning_rate": 8.871023049561871e-05, "loss": 0.1399, "step": 76370 }, { "epoch": 18.33, "learning_rate": 8.870739038144878e-05, "loss": 0.0937, "step": 76380 }, { "epoch": 18.33, "learning_rate": 8.87045499555629e-05, "loss": 0.1399, "step": 76390 }, { "epoch": 18.34, "learning_rate": 8.870170921798393e-05, "loss": 0.1223, "step": 76400 }, { "epoch": 18.34, "learning_rate": 8.869886816873476e-05, "loss": 0.1321, "step": 76410 }, { "epoch": 18.34, "learning_rate": 8.869602680783825e-05, "loss": 0.1252, "step": 76420 }, { "epoch": 18.34, "learning_rate": 8.86931851353173e-05, "loss": 0.1063, "step": 76430 }, { "epoch": 18.34, "learning_rate": 8.869034315119479e-05, "loss": 0.1211, "step": 76440 }, { "epoch": 18.35, "learning_rate": 8.86875008554936e-05, "loss": 0.1348, "step": 76450 }, { "epoch": 18.35, "learning_rate": 8.868465824823663e-05, "loss": 0.1359, "step": 76460 }, { "epoch": 18.35, "learning_rate": 8.868181532944677e-05, "loss": 0.1096, "step": 76470 }, { "epoch": 18.35, "learning_rate": 8.86789720991469e-05, "loss": 0.1359, "step": 76480 }, { "epoch": 18.36, "learning_rate": 8.867612855735994e-05, "loss": 0.1333, "step": 76490 }, { "epoch": 18.36, "learning_rate": 8.867328470410875e-05, "loss": 0.1269, "step": 76500 }, { "epoch": 18.36, "learning_rate": 8.867044053941628e-05, "loss": 0.1468, "step": 76510 }, { "epoch": 18.36, "learning_rate": 8.866759606330541e-05, "loss": 0.1389, "step": 76520 }, { "epoch": 18.36, "learning_rate": 8.866475127579906e-05, "loss": 0.1052, "step": 76530 }, { "epoch": 18.37, "learning_rate": 8.866190617692013e-05, "loss": 0.144, "step": 76540 }, { "epoch": 18.37, "learning_rate": 8.865906076669153e-05, "loss": 0.1079, "step": 76550 }, { "epoch": 18.37, "learning_rate": 8.865621504513616e-05, "loss": 0.148, "step": 76560 }, { "epoch": 18.37, "learning_rate": 8.865336901227696e-05, "loss": 0.1438, "step": 76570 }, { "epoch": 18.38, "learning_rate": 8.865052266813685e-05, "loss": 0.1302, "step": 76580 }, { "epoch": 18.38, "learning_rate": 8.864767601273874e-05, "loss": 0.124, "step": 76590 }, { "epoch": 18.38, "learning_rate": 8.864482904610557e-05, "loss": 0.1397, "step": 76600 }, { "epoch": 18.38, "learning_rate": 8.864198176826024e-05, "loss": 0.1297, "step": 76610 }, { "epoch": 18.39, "learning_rate": 8.863913417922572e-05, "loss": 0.1326, "step": 76620 }, { "epoch": 18.39, "learning_rate": 8.86362862790249e-05, "loss": 0.0839, "step": 76630 }, { "epoch": 18.39, "learning_rate": 8.863343806768071e-05, "loss": 0.1161, "step": 76640 }, { "epoch": 18.39, "learning_rate": 8.863058954521615e-05, "loss": 0.1183, "step": 76650 }, { "epoch": 18.39, "learning_rate": 8.862774071165411e-05, "loss": 0.1371, "step": 76660 }, { "epoch": 18.4, "learning_rate": 8.862489156701752e-05, "loss": 0.1348, "step": 76670 }, { "epoch": 18.4, "learning_rate": 8.862204211132936e-05, "loss": 0.1154, "step": 76680 }, { "epoch": 18.4, "learning_rate": 8.861919234461257e-05, "loss": 0.1386, "step": 76690 }, { "epoch": 18.4, "learning_rate": 8.861634226689009e-05, "loss": 0.1111, "step": 76700 }, { "epoch": 18.41, "learning_rate": 8.861349187818486e-05, "loss": 0.1058, "step": 76710 }, { "epoch": 18.41, "learning_rate": 8.861064117851987e-05, "loss": 0.169, "step": 76720 }, { "epoch": 18.41, "learning_rate": 8.860779016791804e-05, "loss": 0.112, "step": 76730 }, { "epoch": 18.41, "learning_rate": 8.860493884640235e-05, "loss": 0.1201, "step": 76740 }, { "epoch": 18.41, "learning_rate": 8.860208721399575e-05, "loss": 0.1352, "step": 76750 }, { "epoch": 18.42, "learning_rate": 8.859923527072122e-05, "loss": 0.1186, "step": 76760 }, { "epoch": 18.42, "learning_rate": 8.859638301660173e-05, "loss": 0.1499, "step": 76770 }, { "epoch": 18.42, "learning_rate": 8.859353045166023e-05, "loss": 0.1379, "step": 76780 }, { "epoch": 18.42, "learning_rate": 8.85906775759197e-05, "loss": 0.1289, "step": 76790 }, { "epoch": 18.43, "learning_rate": 8.858782438940312e-05, "loss": 0.1059, "step": 76800 }, { "epoch": 18.43, "learning_rate": 8.858497089213344e-05, "loss": 0.1229, "step": 76810 }, { "epoch": 18.43, "learning_rate": 8.858211708413369e-05, "loss": 0.1064, "step": 76820 }, { "epoch": 18.43, "learning_rate": 8.857926296542683e-05, "loss": 0.1303, "step": 76830 }, { "epoch": 18.44, "learning_rate": 8.857640853603581e-05, "loss": 0.0951, "step": 76840 }, { "epoch": 18.44, "learning_rate": 8.857355379598366e-05, "loss": 0.1758, "step": 76850 }, { "epoch": 18.44, "learning_rate": 8.857069874529336e-05, "loss": 0.1143, "step": 76860 }, { "epoch": 18.44, "learning_rate": 8.856784338398789e-05, "loss": 0.1571, "step": 76870 }, { "epoch": 18.44, "learning_rate": 8.856498771209026e-05, "loss": 0.1115, "step": 76880 }, { "epoch": 18.45, "learning_rate": 8.856213172962345e-05, "loss": 0.1505, "step": 76890 }, { "epoch": 18.45, "learning_rate": 8.85592754366105e-05, "loss": 0.1285, "step": 76900 }, { "epoch": 18.45, "learning_rate": 8.855641883307435e-05, "loss": 0.1195, "step": 76910 }, { "epoch": 18.45, "learning_rate": 8.855356191903802e-05, "loss": 0.152, "step": 76920 }, { "epoch": 18.46, "learning_rate": 8.855070469452457e-05, "loss": 0.1333, "step": 76930 }, { "epoch": 18.46, "learning_rate": 8.854784715955696e-05, "loss": 0.1406, "step": 76940 }, { "epoch": 18.46, "learning_rate": 8.854498931415822e-05, "loss": 0.1508, "step": 76950 }, { "epoch": 18.46, "learning_rate": 8.854213115835134e-05, "loss": 0.1282, "step": 76960 }, { "epoch": 18.47, "learning_rate": 8.853927269215938e-05, "loss": 0.1028, "step": 76970 }, { "epoch": 18.47, "learning_rate": 8.853641391560532e-05, "loss": 0.1211, "step": 76980 }, { "epoch": 18.47, "learning_rate": 8.853355482871222e-05, "loss": 0.1195, "step": 76990 }, { "epoch": 18.47, "learning_rate": 8.853069543150307e-05, "loss": 0.1048, "step": 77000 }, { "epoch": 18.47, "learning_rate": 8.85278357240009e-05, "loss": 0.1204, "step": 77010 }, { "epoch": 18.48, "learning_rate": 8.852497570622877e-05, "loss": 0.1463, "step": 77020 }, { "epoch": 18.48, "learning_rate": 8.852211537820968e-05, "loss": 0.1352, "step": 77030 }, { "epoch": 18.48, "learning_rate": 8.851925473996667e-05, "loss": 0.1133, "step": 77040 }, { "epoch": 18.48, "learning_rate": 8.851639379152279e-05, "loss": 0.0736, "step": 77050 }, { "epoch": 18.49, "learning_rate": 8.851353253290107e-05, "loss": 0.1035, "step": 77060 }, { "epoch": 18.49, "learning_rate": 8.851067096412457e-05, "loss": 0.1158, "step": 77070 }, { "epoch": 18.49, "learning_rate": 8.85078090852163e-05, "loss": 0.1273, "step": 77080 }, { "epoch": 18.49, "learning_rate": 8.850494689619935e-05, "loss": 0.1266, "step": 77090 }, { "epoch": 18.49, "learning_rate": 8.850208439709673e-05, "loss": 0.1512, "step": 77100 }, { "epoch": 18.5, "learning_rate": 8.849922158793151e-05, "loss": 0.1582, "step": 77110 }, { "epoch": 18.5, "learning_rate": 8.849635846872675e-05, "loss": 0.0999, "step": 77120 }, { "epoch": 18.5, "learning_rate": 8.849349503950549e-05, "loss": 0.0995, "step": 77130 }, { "epoch": 18.5, "learning_rate": 8.84906313002908e-05, "loss": 0.1316, "step": 77140 }, { "epoch": 18.51, "learning_rate": 8.848776725110576e-05, "loss": 0.1688, "step": 77150 }, { "epoch": 18.51, "learning_rate": 8.84849028919734e-05, "loss": 0.1029, "step": 77160 }, { "epoch": 18.51, "learning_rate": 8.848203822291681e-05, "loss": 0.0884, "step": 77170 }, { "epoch": 18.51, "learning_rate": 8.847917324395906e-05, "loss": 0.1119, "step": 77180 }, { "epoch": 18.52, "learning_rate": 8.84763079551232e-05, "loss": 0.1284, "step": 77190 }, { "epoch": 18.52, "learning_rate": 8.847344235643233e-05, "loss": 0.1365, "step": 77200 }, { "epoch": 18.52, "learning_rate": 8.847057644790952e-05, "loss": 0.1293, "step": 77210 }, { "epoch": 18.52, "learning_rate": 8.846771022957783e-05, "loss": 0.1462, "step": 77220 }, { "epoch": 18.52, "learning_rate": 8.846484370146038e-05, "loss": 0.1318, "step": 77230 }, { "epoch": 18.53, "learning_rate": 8.846197686358023e-05, "loss": 0.1153, "step": 77240 }, { "epoch": 18.53, "learning_rate": 8.845910971596045e-05, "loss": 0.1326, "step": 77250 }, { "epoch": 18.53, "learning_rate": 8.845624225862417e-05, "loss": 0.1385, "step": 77260 }, { "epoch": 18.53, "learning_rate": 8.845337449159445e-05, "loss": 0.1292, "step": 77270 }, { "epoch": 18.54, "learning_rate": 8.84505064148944e-05, "loss": 0.1679, "step": 77280 }, { "epoch": 18.54, "learning_rate": 8.844763802854713e-05, "loss": 0.1647, "step": 77290 }, { "epoch": 18.54, "learning_rate": 8.844476933257571e-05, "loss": 0.1651, "step": 77300 }, { "epoch": 18.54, "learning_rate": 8.844190032700325e-05, "loss": 0.1729, "step": 77310 }, { "epoch": 18.55, "learning_rate": 8.843903101185287e-05, "loss": 0.1998, "step": 77320 }, { "epoch": 18.55, "learning_rate": 8.843616138714766e-05, "loss": 0.167, "step": 77330 }, { "epoch": 18.55, "learning_rate": 8.843329145291073e-05, "loss": 0.1717, "step": 77340 }, { "epoch": 18.55, "learning_rate": 8.843042120916521e-05, "loss": 0.2054, "step": 77350 }, { "epoch": 18.55, "learning_rate": 8.842755065593418e-05, "loss": 0.1563, "step": 77360 }, { "epoch": 18.56, "learning_rate": 8.84246797932408e-05, "loss": 0.1418, "step": 77370 }, { "epoch": 18.56, "learning_rate": 8.842180862110816e-05, "loss": 0.1505, "step": 77380 }, { "epoch": 18.56, "learning_rate": 8.84189371395594e-05, "loss": 0.1743, "step": 77390 }, { "epoch": 18.56, "learning_rate": 8.841606534861763e-05, "loss": 0.1612, "step": 77400 }, { "epoch": 18.57, "learning_rate": 8.841319324830597e-05, "loss": 0.1947, "step": 77410 }, { "epoch": 18.57, "learning_rate": 8.841032083864758e-05, "loss": 0.1506, "step": 77420 }, { "epoch": 18.57, "learning_rate": 8.840744811966557e-05, "loss": 0.177, "step": 77430 }, { "epoch": 18.57, "learning_rate": 8.840457509138307e-05, "loss": 0.1477, "step": 77440 }, { "epoch": 18.57, "learning_rate": 8.840170175382323e-05, "loss": 0.162, "step": 77450 }, { "epoch": 18.58, "learning_rate": 8.83988281070092e-05, "loss": 0.1643, "step": 77460 }, { "epoch": 18.58, "learning_rate": 8.839595415096407e-05, "loss": 0.1655, "step": 77470 }, { "epoch": 18.58, "learning_rate": 8.839307988571103e-05, "loss": 0.1104, "step": 77480 }, { "epoch": 18.58, "learning_rate": 8.839020531127324e-05, "loss": 0.1517, "step": 77490 }, { "epoch": 18.59, "learning_rate": 8.838733042767382e-05, "loss": 0.1661, "step": 77500 }, { "epoch": 18.59, "learning_rate": 8.838445523493593e-05, "loss": 0.1839, "step": 77510 }, { "epoch": 18.59, "learning_rate": 8.83815797330827e-05, "loss": 0.138, "step": 77520 }, { "epoch": 18.59, "learning_rate": 8.837870392213734e-05, "loss": 0.162, "step": 77530 }, { "epoch": 18.6, "learning_rate": 8.837582780212294e-05, "loss": 0.1578, "step": 77540 }, { "epoch": 18.6, "learning_rate": 8.837295137306273e-05, "loss": 0.1566, "step": 77550 }, { "epoch": 18.6, "learning_rate": 8.837007463497983e-05, "loss": 0.124, "step": 77560 }, { "epoch": 18.6, "learning_rate": 8.836719758789745e-05, "loss": 0.1448, "step": 77570 }, { "epoch": 18.6, "learning_rate": 8.83643202318387e-05, "loss": 0.1585, "step": 77580 }, { "epoch": 18.61, "learning_rate": 8.836144256682679e-05, "loss": 0.1418, "step": 77590 }, { "epoch": 18.61, "learning_rate": 8.835856459288489e-05, "loss": 0.16, "step": 77600 }, { "epoch": 18.61, "learning_rate": 8.835568631003618e-05, "loss": 0.1712, "step": 77610 }, { "epoch": 18.61, "learning_rate": 8.835280771830383e-05, "loss": 0.1293, "step": 77620 }, { "epoch": 18.62, "learning_rate": 8.834992881771102e-05, "loss": 0.1537, "step": 77630 }, { "epoch": 18.62, "learning_rate": 8.834704960828093e-05, "loss": 0.172, "step": 77640 }, { "epoch": 18.62, "learning_rate": 8.834417009003677e-05, "loss": 0.1742, "step": 77650 }, { "epoch": 18.62, "learning_rate": 8.83412902630017e-05, "loss": 0.1492, "step": 77660 }, { "epoch": 18.63, "learning_rate": 8.833841012719895e-05, "loss": 0.1227, "step": 77670 }, { "epoch": 18.63, "learning_rate": 8.833552968265168e-05, "loss": 0.1404, "step": 77680 }, { "epoch": 18.63, "learning_rate": 8.833264892938308e-05, "loss": 0.1286, "step": 77690 }, { "epoch": 18.63, "learning_rate": 8.832976786741638e-05, "loss": 0.1086, "step": 77700 }, { "epoch": 18.63, "learning_rate": 8.832688649677476e-05, "loss": 0.174, "step": 77710 }, { "epoch": 18.64, "learning_rate": 8.832400481748145e-05, "loss": 0.1634, "step": 77720 }, { "epoch": 18.64, "learning_rate": 8.832112282955962e-05, "loss": 0.1862, "step": 77730 }, { "epoch": 18.64, "learning_rate": 8.83182405330325e-05, "loss": 0.1143, "step": 77740 }, { "epoch": 18.64, "learning_rate": 8.831535792792331e-05, "loss": 0.1359, "step": 77750 }, { "epoch": 18.65, "learning_rate": 8.831247501425524e-05, "loss": 0.1228, "step": 77760 }, { "epoch": 18.65, "learning_rate": 8.830959179205153e-05, "loss": 0.1947, "step": 77770 }, { "epoch": 18.65, "learning_rate": 8.830670826133538e-05, "loss": 0.136, "step": 77780 }, { "epoch": 18.65, "learning_rate": 8.830382442213004e-05, "loss": 0.1287, "step": 77790 }, { "epoch": 18.65, "learning_rate": 8.830094027445868e-05, "loss": 0.1404, "step": 77800 }, { "epoch": 18.66, "learning_rate": 8.829805581834458e-05, "loss": 0.1377, "step": 77810 }, { "epoch": 18.66, "learning_rate": 8.829517105381095e-05, "loss": 0.1309, "step": 77820 }, { "epoch": 18.66, "learning_rate": 8.829228598088101e-05, "loss": 0.1175, "step": 77830 }, { "epoch": 18.66, "learning_rate": 8.828940059957803e-05, "loss": 0.1441, "step": 77840 }, { "epoch": 18.67, "learning_rate": 8.828651490992519e-05, "loss": 0.1759, "step": 77850 }, { "epoch": 18.67, "learning_rate": 8.828362891194576e-05, "loss": 0.1239, "step": 77860 }, { "epoch": 18.67, "learning_rate": 8.8280742605663e-05, "loss": 0.133, "step": 77870 }, { "epoch": 18.67, "learning_rate": 8.827785599110013e-05, "loss": 0.1293, "step": 77880 }, { "epoch": 18.68, "learning_rate": 8.82749690682804e-05, "loss": 0.1265, "step": 77890 }, { "epoch": 18.68, "learning_rate": 8.827208183722706e-05, "loss": 0.1398, "step": 77900 }, { "epoch": 18.68, "learning_rate": 8.826919429796337e-05, "loss": 0.1146, "step": 77910 }, { "epoch": 18.68, "learning_rate": 8.826630645051255e-05, "loss": 0.0947, "step": 77920 }, { "epoch": 18.68, "learning_rate": 8.82634182948979e-05, "loss": 0.1637, "step": 77930 }, { "epoch": 18.69, "learning_rate": 8.826052983114266e-05, "loss": 0.1343, "step": 77940 }, { "epoch": 18.69, "learning_rate": 8.825764105927009e-05, "loss": 0.1264, "step": 77950 }, { "epoch": 18.69, "learning_rate": 8.825475197930344e-05, "loss": 0.1796, "step": 77960 }, { "epoch": 18.69, "learning_rate": 8.825186259126601e-05, "loss": 0.1984, "step": 77970 }, { "epoch": 18.7, "learning_rate": 8.824897289518104e-05, "loss": 0.1712, "step": 77980 }, { "epoch": 18.7, "learning_rate": 8.824608289107181e-05, "loss": 0.1337, "step": 77990 }, { "epoch": 18.7, "learning_rate": 8.82431925789616e-05, "loss": 0.1495, "step": 78000 }, { "epoch": 18.7, "learning_rate": 8.824030195887367e-05, "loss": 0.1399, "step": 78010 }, { "epoch": 18.71, "learning_rate": 8.823741103083132e-05, "loss": 0.1474, "step": 78020 }, { "epoch": 18.71, "learning_rate": 8.823451979485781e-05, "loss": 0.149, "step": 78030 }, { "epoch": 18.71, "learning_rate": 8.823162825097645e-05, "loss": 0.1585, "step": 78040 }, { "epoch": 18.71, "learning_rate": 8.82287363992105e-05, "loss": 0.1816, "step": 78050 }, { "epoch": 18.71, "learning_rate": 8.822584423958325e-05, "loss": 0.1685, "step": 78060 }, { "epoch": 18.72, "learning_rate": 8.8222951772118e-05, "loss": 0.1472, "step": 78070 }, { "epoch": 18.72, "learning_rate": 8.822005899683805e-05, "loss": 0.1631, "step": 78080 }, { "epoch": 18.72, "learning_rate": 8.821716591376669e-05, "loss": 0.1729, "step": 78090 }, { "epoch": 18.72, "learning_rate": 8.821427252292722e-05, "loss": 0.1102, "step": 78100 }, { "epoch": 18.73, "learning_rate": 8.821137882434293e-05, "loss": 0.1443, "step": 78110 }, { "epoch": 18.73, "learning_rate": 8.820848481803712e-05, "loss": 0.1508, "step": 78120 }, { "epoch": 18.73, "learning_rate": 8.820559050403312e-05, "loss": 0.147, "step": 78130 }, { "epoch": 18.73, "learning_rate": 8.820269588235423e-05, "loss": 0.1511, "step": 78140 }, { "epoch": 18.73, "learning_rate": 8.819980095302375e-05, "loss": 0.1401, "step": 78150 }, { "epoch": 18.74, "learning_rate": 8.819690571606501e-05, "loss": 0.1286, "step": 78160 }, { "epoch": 18.74, "learning_rate": 8.819401017150129e-05, "loss": 0.142, "step": 78170 }, { "epoch": 18.74, "learning_rate": 8.819111431935594e-05, "loss": 0.1594, "step": 78180 }, { "epoch": 18.74, "learning_rate": 8.818821815965228e-05, "loss": 0.1055, "step": 78190 }, { "epoch": 18.75, "learning_rate": 8.818532169241363e-05, "loss": 0.1129, "step": 78200 }, { "epoch": 18.75, "learning_rate": 8.818242491766331e-05, "loss": 0.1591, "step": 78210 }, { "epoch": 18.75, "learning_rate": 8.817952783542464e-05, "loss": 0.1401, "step": 78220 }, { "epoch": 18.75, "learning_rate": 8.817663044572098e-05, "loss": 0.1363, "step": 78230 }, { "epoch": 18.76, "learning_rate": 8.817373274857564e-05, "loss": 0.1283, "step": 78240 }, { "epoch": 18.76, "learning_rate": 8.817083474401195e-05, "loss": 0.1358, "step": 78250 }, { "epoch": 18.76, "learning_rate": 8.816793643205328e-05, "loss": 0.1273, "step": 78260 }, { "epoch": 18.76, "learning_rate": 8.816503781272292e-05, "loss": 0.1473, "step": 78270 }, { "epoch": 18.76, "learning_rate": 8.816213888604425e-05, "loss": 0.1482, "step": 78280 }, { "epoch": 18.77, "learning_rate": 8.815923965204062e-05, "loss": 0.1062, "step": 78290 }, { "epoch": 18.77, "learning_rate": 8.815634011073535e-05, "loss": 0.1301, "step": 78300 }, { "epoch": 18.77, "learning_rate": 8.815344026215182e-05, "loss": 0.1366, "step": 78310 }, { "epoch": 18.77, "learning_rate": 8.815054010631337e-05, "loss": 0.1461, "step": 78320 }, { "epoch": 18.78, "learning_rate": 8.814763964324333e-05, "loss": 0.1281, "step": 78330 }, { "epoch": 18.78, "learning_rate": 8.814473887296509e-05, "loss": 0.1248, "step": 78340 }, { "epoch": 18.78, "learning_rate": 8.814183779550201e-05, "loss": 0.1217, "step": 78350 }, { "epoch": 18.78, "learning_rate": 8.813893641087744e-05, "loss": 0.1522, "step": 78360 }, { "epoch": 18.79, "learning_rate": 8.813603471911476e-05, "loss": 0.1215, "step": 78370 }, { "epoch": 18.79, "learning_rate": 8.813313272023731e-05, "loss": 0.1507, "step": 78380 }, { "epoch": 18.79, "learning_rate": 8.813023041426849e-05, "loss": 0.1622, "step": 78390 }, { "epoch": 18.79, "learning_rate": 8.812732780123165e-05, "loss": 0.1491, "step": 78400 }, { "epoch": 18.79, "learning_rate": 8.812442488115019e-05, "loss": 0.1261, "step": 78410 }, { "epoch": 18.8, "learning_rate": 8.812152165404745e-05, "loss": 0.1398, "step": 78420 }, { "epoch": 18.8, "learning_rate": 8.811861811994685e-05, "loss": 0.1464, "step": 78430 }, { "epoch": 18.8, "learning_rate": 8.811571427887175e-05, "loss": 0.1379, "step": 78440 }, { "epoch": 18.8, "learning_rate": 8.811281013084555e-05, "loss": 0.1359, "step": 78450 }, { "epoch": 18.81, "learning_rate": 8.810990567589162e-05, "loss": 0.1393, "step": 78460 }, { "epoch": 18.81, "learning_rate": 8.810700091403336e-05, "loss": 0.1526, "step": 78470 }, { "epoch": 18.81, "learning_rate": 8.810409584529415e-05, "loss": 0.1212, "step": 78480 }, { "epoch": 18.81, "learning_rate": 8.810119046969742e-05, "loss": 0.1477, "step": 78490 }, { "epoch": 18.81, "learning_rate": 8.809828478726652e-05, "loss": 0.1358, "step": 78500 }, { "epoch": 18.82, "learning_rate": 8.809537879802489e-05, "loss": 0.1285, "step": 78510 }, { "epoch": 18.82, "learning_rate": 8.80924725019959e-05, "loss": 0.1265, "step": 78520 }, { "epoch": 18.82, "learning_rate": 8.808956589920299e-05, "loss": 0.1065, "step": 78530 }, { "epoch": 18.82, "learning_rate": 8.808665898966952e-05, "loss": 0.1562, "step": 78540 }, { "epoch": 18.83, "learning_rate": 8.808375177341894e-05, "loss": 0.1809, "step": 78550 }, { "epoch": 18.83, "learning_rate": 8.808084425047465e-05, "loss": 0.1106, "step": 78560 }, { "epoch": 18.83, "learning_rate": 8.807793642086006e-05, "loss": 0.1553, "step": 78570 }, { "epoch": 18.83, "learning_rate": 8.807502828459861e-05, "loss": 0.1373, "step": 78580 }, { "epoch": 18.84, "learning_rate": 8.807211984171368e-05, "loss": 0.1057, "step": 78590 }, { "epoch": 18.84, "learning_rate": 8.806921109222873e-05, "loss": 0.1151, "step": 78600 }, { "epoch": 18.84, "learning_rate": 8.806630203616715e-05, "loss": 0.1415, "step": 78610 }, { "epoch": 18.84, "learning_rate": 8.806339267355238e-05, "loss": 0.1657, "step": 78620 }, { "epoch": 18.84, "learning_rate": 8.806048300440787e-05, "loss": 0.1516, "step": 78630 }, { "epoch": 18.85, "learning_rate": 8.805757302875704e-05, "loss": 0.1419, "step": 78640 }, { "epoch": 18.85, "learning_rate": 8.805466274662331e-05, "loss": 0.1381, "step": 78650 }, { "epoch": 18.85, "learning_rate": 8.805175215803012e-05, "loss": 0.1331, "step": 78660 }, { "epoch": 18.85, "learning_rate": 8.804884126300092e-05, "loss": 0.1381, "step": 78670 }, { "epoch": 18.86, "learning_rate": 8.804593006155914e-05, "loss": 0.1109, "step": 78680 }, { "epoch": 18.86, "learning_rate": 8.804301855372825e-05, "loss": 0.1443, "step": 78690 }, { "epoch": 18.86, "learning_rate": 8.804010673953169e-05, "loss": 0.1351, "step": 78700 }, { "epoch": 18.86, "learning_rate": 8.803719461899288e-05, "loss": 0.1426, "step": 78710 }, { "epoch": 18.87, "learning_rate": 8.803428219213528e-05, "loss": 0.1248, "step": 78720 }, { "epoch": 18.87, "learning_rate": 8.803136945898237e-05, "loss": 0.1618, "step": 78730 }, { "epoch": 18.87, "learning_rate": 8.802845641955759e-05, "loss": 0.1621, "step": 78740 }, { "epoch": 18.87, "learning_rate": 8.80255430738844e-05, "loss": 0.1247, "step": 78750 }, { "epoch": 18.87, "learning_rate": 8.802262942198626e-05, "loss": 0.1474, "step": 78760 }, { "epoch": 18.88, "learning_rate": 8.801971546388663e-05, "loss": 0.1425, "step": 78770 }, { "epoch": 18.88, "learning_rate": 8.8016801199609e-05, "loss": 0.1107, "step": 78780 }, { "epoch": 18.88, "learning_rate": 8.80138866291768e-05, "loss": 0.1316, "step": 78790 }, { "epoch": 18.88, "learning_rate": 8.801097175261354e-05, "loss": 0.1967, "step": 78800 }, { "epoch": 18.89, "learning_rate": 8.800805656994266e-05, "loss": 0.1683, "step": 78810 }, { "epoch": 18.89, "learning_rate": 8.800514108118768e-05, "loss": 0.1104, "step": 78820 }, { "epoch": 18.89, "learning_rate": 8.800222528637202e-05, "loss": 0.1231, "step": 78830 }, { "epoch": 18.89, "learning_rate": 8.799930918551922e-05, "loss": 0.1319, "step": 78840 }, { "epoch": 18.89, "learning_rate": 8.799639277865273e-05, "loss": 0.1328, "step": 78850 }, { "epoch": 18.9, "learning_rate": 8.799347606579602e-05, "loss": 0.1593, "step": 78860 }, { "epoch": 18.9, "learning_rate": 8.799055904697262e-05, "loss": 0.1556, "step": 78870 }, { "epoch": 18.9, "learning_rate": 8.798764172220601e-05, "loss": 0.0998, "step": 78880 }, { "epoch": 18.9, "learning_rate": 8.798472409151967e-05, "loss": 0.1088, "step": 78890 }, { "epoch": 18.91, "learning_rate": 8.798180615493711e-05, "loss": 0.1272, "step": 78900 }, { "epoch": 18.91, "learning_rate": 8.797888791248181e-05, "loss": 0.1085, "step": 78910 }, { "epoch": 18.91, "learning_rate": 8.797596936417729e-05, "loss": 0.1214, "step": 78920 }, { "epoch": 18.91, "learning_rate": 8.797305051004704e-05, "loss": 0.1326, "step": 78930 }, { "epoch": 18.92, "learning_rate": 8.797013135011458e-05, "loss": 0.1481, "step": 78940 }, { "epoch": 18.92, "learning_rate": 8.79672118844034e-05, "loss": 0.1239, "step": 78950 }, { "epoch": 18.92, "learning_rate": 8.796429211293702e-05, "loss": 0.1299, "step": 78960 }, { "epoch": 18.92, "learning_rate": 8.796137203573896e-05, "loss": 0.1274, "step": 78970 }, { "epoch": 18.92, "learning_rate": 8.795845165283274e-05, "loss": 0.1297, "step": 78980 }, { "epoch": 18.93, "learning_rate": 8.795553096424185e-05, "loss": 0.1275, "step": 78990 }, { "epoch": 18.93, "learning_rate": 8.795260996998984e-05, "loss": 0.0919, "step": 79000 }, { "epoch": 18.93, "learning_rate": 8.794968867010022e-05, "loss": 0.1233, "step": 79010 }, { "epoch": 18.93, "learning_rate": 8.794676706459652e-05, "loss": 0.1496, "step": 79020 }, { "epoch": 18.94, "learning_rate": 8.794384515350226e-05, "loss": 0.1015, "step": 79030 }, { "epoch": 18.94, "learning_rate": 8.794092293684098e-05, "loss": 0.1211, "step": 79040 }, { "epoch": 18.94, "learning_rate": 8.793800041463622e-05, "loss": 0.1462, "step": 79050 }, { "epoch": 18.94, "learning_rate": 8.793507758691148e-05, "loss": 0.1457, "step": 79060 }, { "epoch": 18.95, "learning_rate": 8.793215445369034e-05, "loss": 0.1246, "step": 79070 }, { "epoch": 18.95, "learning_rate": 8.792923101499632e-05, "loss": 0.1409, "step": 79080 }, { "epoch": 18.95, "learning_rate": 8.792630727085297e-05, "loss": 0.1115, "step": 79090 }, { "epoch": 19.0, "learning_rate": 8.792338322128381e-05, "loss": 0.123, "step": 79100 }, { "epoch": 19.0, "learning_rate": 8.792045886631245e-05, "loss": 0.1264, "step": 79110 }, { "epoch": 19.01, "learning_rate": 8.791753420596238e-05, "loss": 0.1214, "step": 79120 }, { "epoch": 19.01, "learning_rate": 8.791460924025716e-05, "loss": 0.1454, "step": 79130 }, { "epoch": 19.01, "learning_rate": 8.791168396922036e-05, "loss": 0.1463, "step": 79140 }, { "epoch": 19.01, "learning_rate": 8.790875839287554e-05, "loss": 0.0916, "step": 79150 }, { "epoch": 19.01, "learning_rate": 8.790583251124627e-05, "loss": 0.1309, "step": 79160 }, { "epoch": 19.02, "learning_rate": 8.790290632435607e-05, "loss": 0.1478, "step": 79170 }, { "epoch": 19.02, "learning_rate": 8.789997983222856e-05, "loss": 0.1168, "step": 79180 }, { "epoch": 19.02, "learning_rate": 8.789705303488726e-05, "loss": 0.1525, "step": 79190 }, { "epoch": 19.02, "learning_rate": 8.789412593235578e-05, "loss": 0.1017, "step": 79200 }, { "epoch": 19.03, "learning_rate": 8.789119852465765e-05, "loss": 0.1005, "step": 79210 }, { "epoch": 19.03, "learning_rate": 8.788827081181648e-05, "loss": 0.1136, "step": 79220 }, { "epoch": 19.03, "learning_rate": 8.788534279385583e-05, "loss": 0.1228, "step": 79230 }, { "epoch": 19.03, "learning_rate": 8.788241447079928e-05, "loss": 0.1201, "step": 79240 }, { "epoch": 19.03, "learning_rate": 8.787948584267042e-05, "loss": 0.1499, "step": 79250 }, { "epoch": 19.04, "learning_rate": 8.787655690949283e-05, "loss": 0.114, "step": 79260 }, { "epoch": 19.04, "learning_rate": 8.787362767129011e-05, "loss": 0.1145, "step": 79270 }, { "epoch": 19.04, "learning_rate": 8.787069812808582e-05, "loss": 0.1376, "step": 79280 }, { "epoch": 19.04, "learning_rate": 8.786776827990357e-05, "loss": 0.1153, "step": 79290 }, { "epoch": 19.05, "learning_rate": 8.786483812676696e-05, "loss": 0.1018, "step": 79300 }, { "epoch": 19.05, "learning_rate": 8.786190766869959e-05, "loss": 0.112, "step": 79310 }, { "epoch": 19.05, "learning_rate": 8.785897690572504e-05, "loss": 0.1373, "step": 79320 }, { "epoch": 19.05, "learning_rate": 8.785604583786693e-05, "loss": 0.1272, "step": 79330 }, { "epoch": 19.06, "learning_rate": 8.785311446514884e-05, "loss": 0.1209, "step": 79340 }, { "epoch": 19.06, "learning_rate": 8.785018278759441e-05, "loss": 0.1308, "step": 79350 }, { "epoch": 19.06, "learning_rate": 8.784725080522723e-05, "loss": 0.1166, "step": 79360 }, { "epoch": 19.06, "learning_rate": 8.784431851807091e-05, "loss": 0.094, "step": 79370 }, { "epoch": 19.06, "learning_rate": 8.784138592614907e-05, "loss": 0.1149, "step": 79380 }, { "epoch": 19.07, "learning_rate": 8.783845302948533e-05, "loss": 0.0966, "step": 79390 }, { "epoch": 19.07, "learning_rate": 8.783551982810328e-05, "loss": 0.1331, "step": 79400 }, { "epoch": 19.07, "learning_rate": 8.783258632202658e-05, "loss": 0.1406, "step": 79410 }, { "epoch": 19.07, "learning_rate": 8.782965251127884e-05, "loss": 0.1103, "step": 79420 }, { "epoch": 19.08, "learning_rate": 8.78267183958837e-05, "loss": 0.1342, "step": 79430 }, { "epoch": 19.08, "learning_rate": 8.782378397586477e-05, "loss": 0.1255, "step": 79440 }, { "epoch": 19.08, "learning_rate": 8.782084925124567e-05, "loss": 0.0988, "step": 79450 }, { "epoch": 19.08, "learning_rate": 8.781791422205006e-05, "loss": 0.132, "step": 79460 }, { "epoch": 19.09, "learning_rate": 8.781497888830156e-05, "loss": 0.1686, "step": 79470 }, { "epoch": 19.09, "learning_rate": 8.781204325002381e-05, "loss": 0.1307, "step": 79480 }, { "epoch": 19.09, "learning_rate": 8.780910730724047e-05, "loss": 0.0991, "step": 79490 }, { "epoch": 19.09, "learning_rate": 8.780617105997516e-05, "loss": 0.122, "step": 79500 }, { "epoch": 19.09, "learning_rate": 8.780323450825154e-05, "loss": 0.1119, "step": 79510 }, { "epoch": 19.1, "learning_rate": 8.780029765209325e-05, "loss": 0.1138, "step": 79520 }, { "epoch": 19.1, "learning_rate": 8.779736049152393e-05, "loss": 0.1291, "step": 79530 }, { "epoch": 19.1, "learning_rate": 8.779442302656727e-05, "loss": 0.1086, "step": 79540 }, { "epoch": 19.1, "learning_rate": 8.77914852572469e-05, "loss": 0.1278, "step": 79550 }, { "epoch": 19.11, "learning_rate": 8.77885471835865e-05, "loss": 0.1198, "step": 79560 }, { "epoch": 19.11, "learning_rate": 8.778560880560966e-05, "loss": 0.088, "step": 79570 }, { "epoch": 19.11, "learning_rate": 8.778267012334014e-05, "loss": 0.094, "step": 79580 }, { "epoch": 19.11, "learning_rate": 8.777973113680153e-05, "loss": 0.0802, "step": 79590 }, { "epoch": 19.11, "learning_rate": 8.777679184601756e-05, "loss": 0.1191, "step": 79600 }, { "epoch": 19.12, "learning_rate": 8.777385225101186e-05, "loss": 0.0958, "step": 79610 }, { "epoch": 19.12, "learning_rate": 8.77709123518081e-05, "loss": 0.0684, "step": 79620 }, { "epoch": 19.12, "learning_rate": 8.776797214842998e-05, "loss": 0.1353, "step": 79630 }, { "epoch": 19.12, "learning_rate": 8.776503164090117e-05, "loss": 0.129, "step": 79640 }, { "epoch": 19.13, "learning_rate": 8.776209082924533e-05, "loss": 0.1384, "step": 79650 }, { "epoch": 19.13, "learning_rate": 8.775914971348618e-05, "loss": 0.0964, "step": 79660 }, { "epoch": 19.13, "learning_rate": 8.775620829364736e-05, "loss": 0.1257, "step": 79670 }, { "epoch": 19.13, "learning_rate": 8.77532665697526e-05, "loss": 0.1277, "step": 79680 }, { "epoch": 19.14, "learning_rate": 8.775032454182556e-05, "loss": 0.1422, "step": 79690 }, { "epoch": 19.14, "learning_rate": 8.774738220988996e-05, "loss": 0.1438, "step": 79700 }, { "epoch": 19.14, "learning_rate": 8.774443957396947e-05, "loss": 0.1008, "step": 79710 }, { "epoch": 19.14, "learning_rate": 8.77414966340878e-05, "loss": 0.1259, "step": 79720 }, { "epoch": 19.14, "learning_rate": 8.773855339026865e-05, "loss": 0.127, "step": 79730 }, { "epoch": 19.15, "learning_rate": 8.773560984253572e-05, "loss": 0.1203, "step": 79740 }, { "epoch": 19.15, "learning_rate": 8.77326659909127e-05, "loss": 0.1535, "step": 79750 }, { "epoch": 19.15, "learning_rate": 8.772972183542333e-05, "loss": 0.1217, "step": 79760 }, { "epoch": 19.15, "learning_rate": 8.77267773760913e-05, "loss": 0.1165, "step": 79770 }, { "epoch": 19.16, "learning_rate": 8.77238326129403e-05, "loss": 0.1205, "step": 79780 }, { "epoch": 19.16, "learning_rate": 8.772088754599409e-05, "loss": 0.1349, "step": 79790 }, { "epoch": 19.16, "learning_rate": 8.771794217527636e-05, "loss": 0.0804, "step": 79800 }, { "epoch": 19.16, "learning_rate": 8.771499650081083e-05, "loss": 0.1118, "step": 79810 }, { "epoch": 19.17, "learning_rate": 8.771205052262123e-05, "loss": 0.1262, "step": 79820 }, { "epoch": 19.17, "learning_rate": 8.770910424073129e-05, "loss": 0.1346, "step": 79830 }, { "epoch": 19.17, "learning_rate": 8.770615765516471e-05, "loss": 0.1113, "step": 79840 }, { "epoch": 19.17, "learning_rate": 8.770321076594525e-05, "loss": 0.1043, "step": 79850 }, { "epoch": 19.17, "learning_rate": 8.770026357309662e-05, "loss": 0.1227, "step": 79860 }, { "epoch": 19.18, "learning_rate": 8.769731607664256e-05, "loss": 0.0948, "step": 79870 }, { "epoch": 19.18, "learning_rate": 8.769436827660682e-05, "loss": 0.1049, "step": 79880 }, { "epoch": 19.18, "learning_rate": 8.769142017301312e-05, "loss": 0.1558, "step": 79890 }, { "epoch": 19.18, "learning_rate": 8.768847176588522e-05, "loss": 0.1426, "step": 79900 }, { "epoch": 19.19, "learning_rate": 8.768552305524685e-05, "loss": 0.0928, "step": 79910 }, { "epoch": 19.19, "learning_rate": 8.768257404112174e-05, "loss": 0.1169, "step": 79920 }, { "epoch": 19.19, "learning_rate": 8.767962472353369e-05, "loss": 0.1439, "step": 79930 }, { "epoch": 19.19, "learning_rate": 8.767667510250639e-05, "loss": 0.0971, "step": 79940 }, { "epoch": 19.19, "learning_rate": 8.767372517806365e-05, "loss": 0.1144, "step": 79950 }, { "epoch": 19.2, "learning_rate": 8.767077495022918e-05, "loss": 0.1063, "step": 79960 }, { "epoch": 19.2, "learning_rate": 8.766782441902677e-05, "loss": 0.134, "step": 79970 }, { "epoch": 19.2, "learning_rate": 8.766487358448016e-05, "loss": 0.1209, "step": 79980 }, { "epoch": 19.2, "learning_rate": 8.766192244661313e-05, "loss": 0.0855, "step": 79990 }, { "epoch": 19.21, "learning_rate": 8.765897100544945e-05, "loss": 0.152, "step": 80000 }, { "epoch": 19.21, "learning_rate": 8.765601926101286e-05, "loss": 0.1053, "step": 80010 }, { "epoch": 19.21, "learning_rate": 8.765306721332716e-05, "loss": 0.0975, "step": 80020 }, { "epoch": 19.21, "learning_rate": 8.76501148624161e-05, "loss": 0.113, "step": 80030 }, { "epoch": 19.22, "learning_rate": 8.764716220830347e-05, "loss": 0.1302, "step": 80040 }, { "epoch": 19.22, "learning_rate": 8.764420925101306e-05, "loss": 0.112, "step": 80050 }, { "epoch": 19.22, "learning_rate": 8.764125599056861e-05, "loss": 0.1329, "step": 80060 }, { "epoch": 19.22, "learning_rate": 8.763830242699395e-05, "loss": 0.1182, "step": 80070 }, { "epoch": 19.22, "learning_rate": 8.763534856031284e-05, "loss": 0.1254, "step": 80080 }, { "epoch": 19.23, "learning_rate": 8.763239439054907e-05, "loss": 0.1183, "step": 80090 }, { "epoch": 19.23, "learning_rate": 8.762943991772643e-05, "loss": 0.1049, "step": 80100 }, { "epoch": 19.23, "learning_rate": 8.762648514186871e-05, "loss": 0.121, "step": 80110 }, { "epoch": 19.23, "learning_rate": 8.762353006299973e-05, "loss": 0.1045, "step": 80120 }, { "epoch": 19.24, "learning_rate": 8.762057468114324e-05, "loss": 0.1207, "step": 80130 }, { "epoch": 19.24, "learning_rate": 8.76176189963231e-05, "loss": 0.1283, "step": 80140 }, { "epoch": 19.24, "learning_rate": 8.761466300856305e-05, "loss": 0.142, "step": 80150 }, { "epoch": 19.24, "learning_rate": 8.761170671788694e-05, "loss": 0.1205, "step": 80160 }, { "epoch": 19.25, "learning_rate": 8.760875012431857e-05, "loss": 0.0968, "step": 80170 }, { "epoch": 19.25, "learning_rate": 8.760579322788173e-05, "loss": 0.1049, "step": 80180 }, { "epoch": 19.25, "learning_rate": 8.760283602860025e-05, "loss": 0.1085, "step": 80190 }, { "epoch": 19.25, "learning_rate": 8.759987852649795e-05, "loss": 0.1229, "step": 80200 }, { "epoch": 19.25, "learning_rate": 8.759692072159863e-05, "loss": 0.1812, "step": 80210 }, { "epoch": 19.26, "learning_rate": 8.759396261392612e-05, "loss": 0.1269, "step": 80220 }, { "epoch": 19.26, "learning_rate": 8.759100420350424e-05, "loss": 0.1365, "step": 80230 }, { "epoch": 19.26, "learning_rate": 8.758804549035679e-05, "loss": 0.1267, "step": 80240 }, { "epoch": 19.26, "learning_rate": 8.758508647450764e-05, "loss": 0.1184, "step": 80250 }, { "epoch": 19.27, "learning_rate": 8.758212715598061e-05, "loss": 0.1223, "step": 80260 }, { "epoch": 19.27, "learning_rate": 8.75791675347995e-05, "loss": 0.12, "step": 80270 }, { "epoch": 19.27, "learning_rate": 8.757620761098819e-05, "loss": 0.1267, "step": 80280 }, { "epoch": 19.27, "learning_rate": 8.757324738457047e-05, "loss": 0.1201, "step": 80290 }, { "epoch": 19.27, "learning_rate": 8.75702868555702e-05, "loss": 0.0945, "step": 80300 }, { "epoch": 19.28, "learning_rate": 8.756732602401124e-05, "loss": 0.1386, "step": 80310 }, { "epoch": 19.28, "learning_rate": 8.756436488991741e-05, "loss": 0.0951, "step": 80320 }, { "epoch": 19.28, "learning_rate": 8.756140345331256e-05, "loss": 0.1219, "step": 80330 }, { "epoch": 19.28, "learning_rate": 8.755844171422056e-05, "loss": 0.1141, "step": 80340 }, { "epoch": 19.29, "learning_rate": 8.755547967266522e-05, "loss": 0.1082, "step": 80350 }, { "epoch": 19.29, "learning_rate": 8.755251732867043e-05, "loss": 0.175, "step": 80360 }, { "epoch": 19.29, "learning_rate": 8.754955468226003e-05, "loss": 0.0826, "step": 80370 }, { "epoch": 19.29, "learning_rate": 8.754659173345788e-05, "loss": 0.1043, "step": 80380 }, { "epoch": 19.3, "learning_rate": 8.754362848228784e-05, "loss": 0.1107, "step": 80390 }, { "epoch": 19.3, "learning_rate": 8.754066492877379e-05, "loss": 0.1257, "step": 80400 }, { "epoch": 19.3, "learning_rate": 8.753770107293957e-05, "loss": 0.116, "step": 80410 }, { "epoch": 19.3, "learning_rate": 8.753473691480907e-05, "loss": 0.1103, "step": 80420 }, { "epoch": 19.3, "learning_rate": 8.753177245440613e-05, "loss": 0.1448, "step": 80430 }, { "epoch": 19.31, "learning_rate": 8.752880769175467e-05, "loss": 0.1374, "step": 80440 }, { "epoch": 19.31, "learning_rate": 8.752584262687852e-05, "loss": 0.1288, "step": 80450 }, { "epoch": 19.31, "learning_rate": 8.75228772598016e-05, "loss": 0.1217, "step": 80460 }, { "epoch": 19.31, "learning_rate": 8.751991159054777e-05, "loss": 0.1024, "step": 80470 }, { "epoch": 19.32, "learning_rate": 8.75169456191409e-05, "loss": 0.1032, "step": 80480 }, { "epoch": 19.32, "learning_rate": 8.751397934560488e-05, "loss": 0.1191, "step": 80490 }, { "epoch": 19.32, "learning_rate": 8.751101276996363e-05, "loss": 0.1361, "step": 80500 }, { "epoch": 19.32, "learning_rate": 8.750804589224099e-05, "loss": 0.1344, "step": 80510 }, { "epoch": 19.33, "learning_rate": 8.750507871246089e-05, "loss": 0.1228, "step": 80520 }, { "epoch": 19.33, "learning_rate": 8.750211123064721e-05, "loss": 0.1054, "step": 80530 }, { "epoch": 19.33, "learning_rate": 8.749914344682385e-05, "loss": 0.1612, "step": 80540 }, { "epoch": 19.33, "learning_rate": 8.749617536101471e-05, "loss": 0.1371, "step": 80550 }, { "epoch": 19.33, "learning_rate": 8.74932069732437e-05, "loss": 0.1166, "step": 80560 }, { "epoch": 19.34, "learning_rate": 8.749023828353471e-05, "loss": 0.1268, "step": 80570 }, { "epoch": 19.34, "learning_rate": 8.748726929191167e-05, "loss": 0.1022, "step": 80580 }, { "epoch": 19.34, "learning_rate": 8.748429999839846e-05, "loss": 0.119, "step": 80590 }, { "epoch": 19.34, "learning_rate": 8.7481330403019e-05, "loss": 0.1173, "step": 80600 }, { "epoch": 19.35, "learning_rate": 8.747836050579723e-05, "loss": 0.118, "step": 80610 }, { "epoch": 19.35, "learning_rate": 8.747539030675705e-05, "loss": 0.109, "step": 80620 }, { "epoch": 19.35, "learning_rate": 8.747241980592236e-05, "loss": 0.0995, "step": 80630 }, { "epoch": 19.35, "learning_rate": 8.746944900331711e-05, "loss": 0.1421, "step": 80640 }, { "epoch": 19.35, "learning_rate": 8.746647789896521e-05, "loss": 0.0852, "step": 80650 }, { "epoch": 19.36, "learning_rate": 8.74635064928906e-05, "loss": 0.1441, "step": 80660 }, { "epoch": 19.36, "learning_rate": 8.74605347851172e-05, "loss": 0.093, "step": 80670 }, { "epoch": 19.36, "learning_rate": 8.745756277566892e-05, "loss": 0.1017, "step": 80680 }, { "epoch": 19.36, "learning_rate": 8.745459046456974e-05, "loss": 0.1001, "step": 80690 }, { "epoch": 19.37, "learning_rate": 8.745161785184357e-05, "loss": 0.1375, "step": 80700 }, { "epoch": 19.37, "learning_rate": 8.744864493751434e-05, "loss": 0.0774, "step": 80710 }, { "epoch": 19.37, "learning_rate": 8.7445671721606e-05, "loss": 0.1035, "step": 80720 }, { "epoch": 19.37, "learning_rate": 8.74426982041425e-05, "loss": 0.1055, "step": 80730 }, { "epoch": 19.38, "learning_rate": 8.743972438514779e-05, "loss": 0.0835, "step": 80740 }, { "epoch": 19.38, "learning_rate": 8.743675026464581e-05, "loss": 0.1319, "step": 80750 }, { "epoch": 19.38, "learning_rate": 8.74337758426605e-05, "loss": 0.0828, "step": 80760 }, { "epoch": 19.38, "learning_rate": 8.743080111921584e-05, "loss": 0.099, "step": 80770 }, { "epoch": 19.38, "learning_rate": 8.742782609433576e-05, "loss": 0.0966, "step": 80780 }, { "epoch": 19.39, "learning_rate": 8.742485076804423e-05, "loss": 0.1282, "step": 80790 }, { "epoch": 19.39, "learning_rate": 8.742187514036522e-05, "loss": 0.096, "step": 80800 }, { "epoch": 19.39, "learning_rate": 8.741889921132267e-05, "loss": 0.1108, "step": 80810 }, { "epoch": 19.39, "learning_rate": 8.741592298094057e-05, "loss": 0.099, "step": 80820 }, { "epoch": 19.4, "learning_rate": 8.741294644924287e-05, "loss": 0.1273, "step": 80830 }, { "epoch": 19.4, "learning_rate": 8.740996961625354e-05, "loss": 0.1084, "step": 80840 }, { "epoch": 19.4, "learning_rate": 8.740699248199658e-05, "loss": 0.1466, "step": 80850 }, { "epoch": 19.4, "learning_rate": 8.740401504649593e-05, "loss": 0.1137, "step": 80860 }, { "epoch": 19.41, "learning_rate": 8.740103730977557e-05, "loss": 0.1479, "step": 80870 }, { "epoch": 19.41, "learning_rate": 8.739805927185952e-05, "loss": 0.1348, "step": 80880 }, { "epoch": 19.41, "learning_rate": 8.739508093277173e-05, "loss": 0.1193, "step": 80890 }, { "epoch": 19.41, "learning_rate": 8.739210229253618e-05, "loss": 0.1225, "step": 80900 }, { "epoch": 19.41, "learning_rate": 8.738912335117687e-05, "loss": 0.1243, "step": 80910 }, { "epoch": 19.42, "learning_rate": 8.738614410871779e-05, "loss": 0.0893, "step": 80920 }, { "epoch": 19.42, "learning_rate": 8.738316456518295e-05, "loss": 0.1318, "step": 80930 }, { "epoch": 19.42, "learning_rate": 8.738018472059629e-05, "loss": 0.1087, "step": 80940 }, { "epoch": 19.42, "learning_rate": 8.737720457498186e-05, "loss": 0.1311, "step": 80950 }, { "epoch": 19.43, "learning_rate": 8.737422412836364e-05, "loss": 0.1175, "step": 80960 }, { "epoch": 19.43, "learning_rate": 8.737124338076563e-05, "loss": 0.1219, "step": 80970 }, { "epoch": 19.43, "learning_rate": 8.736826233221184e-05, "loss": 0.1015, "step": 80980 }, { "epoch": 19.43, "learning_rate": 8.736528098272628e-05, "loss": 0.1192, "step": 80990 }, { "epoch": 19.43, "learning_rate": 8.736229933233294e-05, "loss": 0.0939, "step": 81000 }, { "epoch": 19.44, "learning_rate": 8.735931738105585e-05, "loss": 0.1022, "step": 81010 }, { "epoch": 19.44, "learning_rate": 8.735633512891904e-05, "loss": 0.1142, "step": 81020 }, { "epoch": 19.44, "learning_rate": 8.735335257594647e-05, "loss": 0.0955, "step": 81030 }, { "epoch": 19.44, "learning_rate": 8.735036972216222e-05, "loss": 0.12, "step": 81040 }, { "epoch": 19.45, "learning_rate": 8.734738656759028e-05, "loss": 0.1052, "step": 81050 }, { "epoch": 19.45, "learning_rate": 8.734440311225467e-05, "loss": 0.128, "step": 81060 }, { "epoch": 19.45, "learning_rate": 8.734141935617944e-05, "loss": 0.109, "step": 81070 }, { "epoch": 19.45, "learning_rate": 8.733843529938859e-05, "loss": 0.1061, "step": 81080 }, { "epoch": 19.46, "learning_rate": 8.733545094190619e-05, "loss": 0.1064, "step": 81090 }, { "epoch": 19.46, "learning_rate": 8.733246628375622e-05, "loss": 0.1092, "step": 81100 }, { "epoch": 19.46, "learning_rate": 8.732948132496277e-05, "loss": 0.1268, "step": 81110 }, { "epoch": 19.46, "learning_rate": 8.732649606554984e-05, "loss": 0.0947, "step": 81120 }, { "epoch": 19.46, "learning_rate": 8.732351050554149e-05, "loss": 0.1224, "step": 81130 }, { "epoch": 19.47, "learning_rate": 8.732052464496175e-05, "loss": 0.0903, "step": 81140 }, { "epoch": 19.47, "learning_rate": 8.731753848383468e-05, "loss": 0.0828, "step": 81150 }, { "epoch": 19.47, "learning_rate": 8.731455202218431e-05, "loss": 0.1376, "step": 81160 }, { "epoch": 19.47, "learning_rate": 8.73115652600347e-05, "loss": 0.1303, "step": 81170 }, { "epoch": 19.48, "learning_rate": 8.730857819740991e-05, "loss": 0.1264, "step": 81180 }, { "epoch": 19.48, "learning_rate": 8.7305590834334e-05, "loss": 0.1093, "step": 81190 }, { "epoch": 19.48, "learning_rate": 8.730260317083102e-05, "loss": 0.1092, "step": 81200 }, { "epoch": 19.48, "learning_rate": 8.7299615206925e-05, "loss": 0.0964, "step": 81210 }, { "epoch": 19.49, "learning_rate": 8.729662694264004e-05, "loss": 0.1285, "step": 81220 }, { "epoch": 19.49, "learning_rate": 8.72936383780002e-05, "loss": 0.1108, "step": 81230 }, { "epoch": 19.49, "learning_rate": 8.729064951302953e-05, "loss": 0.0955, "step": 81240 }, { "epoch": 19.49, "learning_rate": 8.728766034775213e-05, "loss": 0.1299, "step": 81250 }, { "epoch": 19.49, "learning_rate": 8.728467088219203e-05, "loss": 0.1054, "step": 81260 }, { "epoch": 19.5, "learning_rate": 8.728168111637335e-05, "loss": 0.1404, "step": 81270 }, { "epoch": 19.5, "learning_rate": 8.727869105032014e-05, "loss": 0.1037, "step": 81280 }, { "epoch": 19.5, "learning_rate": 8.727570068405648e-05, "loss": 0.0974, "step": 81290 }, { "epoch": 19.5, "learning_rate": 8.727271001760645e-05, "loss": 0.164, "step": 81300 }, { "epoch": 19.51, "learning_rate": 8.726971905099414e-05, "loss": 0.1064, "step": 81310 }, { "epoch": 19.51, "learning_rate": 8.726672778424365e-05, "loss": 0.0987, "step": 81320 }, { "epoch": 19.51, "learning_rate": 8.726373621737905e-05, "loss": 0.1083, "step": 81330 }, { "epoch": 19.51, "learning_rate": 8.726074435042444e-05, "loss": 0.1062, "step": 81340 }, { "epoch": 19.51, "learning_rate": 8.725775218340391e-05, "loss": 0.0769, "step": 81350 }, { "epoch": 19.52, "learning_rate": 8.725475971634156e-05, "loss": 0.0952, "step": 81360 }, { "epoch": 19.52, "learning_rate": 8.725176694926147e-05, "loss": 0.1211, "step": 81370 }, { "epoch": 19.52, "learning_rate": 8.724877388218777e-05, "loss": 0.1022, "step": 81380 }, { "epoch": 19.52, "learning_rate": 8.724578051514456e-05, "loss": 0.1213, "step": 81390 }, { "epoch": 19.53, "learning_rate": 8.724278684815593e-05, "loss": 0.136, "step": 81400 }, { "epoch": 19.53, "learning_rate": 8.723979288124599e-05, "loss": 0.1093, "step": 81410 }, { "epoch": 19.53, "learning_rate": 8.723679861443888e-05, "loss": 0.107, "step": 81420 }, { "epoch": 19.53, "learning_rate": 8.723380404775865e-05, "loss": 0.1562, "step": 81430 }, { "epoch": 19.54, "learning_rate": 8.72308091812295e-05, "loss": 0.1099, "step": 81440 }, { "epoch": 19.54, "learning_rate": 8.722781401487548e-05, "loss": 0.1407, "step": 81450 }, { "epoch": 19.54, "learning_rate": 8.722481854872074e-05, "loss": 0.1351, "step": 81460 }, { "epoch": 19.54, "learning_rate": 8.722182278278938e-05, "loss": 0.1317, "step": 81470 }, { "epoch": 19.54, "learning_rate": 8.721882671710556e-05, "loss": 0.1201, "step": 81480 }, { "epoch": 19.55, "learning_rate": 8.721583035169338e-05, "loss": 0.1618, "step": 81490 }, { "epoch": 19.55, "learning_rate": 8.721283368657699e-05, "loss": 0.139, "step": 81500 }, { "epoch": 19.55, "learning_rate": 8.720983672178051e-05, "loss": 0.1366, "step": 81510 }, { "epoch": 19.55, "learning_rate": 8.720683945732808e-05, "loss": 0.1697, "step": 81520 }, { "epoch": 19.56, "learning_rate": 8.720384189324382e-05, "loss": 0.1339, "step": 81530 }, { "epoch": 19.56, "learning_rate": 8.72008440295519e-05, "loss": 0.0977, "step": 81540 }, { "epoch": 19.56, "learning_rate": 8.719784586627643e-05, "loss": 0.178, "step": 81550 }, { "epoch": 19.56, "learning_rate": 8.71948474034416e-05, "loss": 0.14, "step": 81560 }, { "epoch": 19.57, "learning_rate": 8.719184864107152e-05, "loss": 0.1417, "step": 81570 }, { "epoch": 19.57, "learning_rate": 8.718884957919033e-05, "loss": 0.081, "step": 81580 }, { "epoch": 19.57, "learning_rate": 8.718585021782221e-05, "loss": 0.1447, "step": 81590 }, { "epoch": 19.57, "learning_rate": 8.718285055699131e-05, "loss": 0.1313, "step": 81600 }, { "epoch": 19.57, "learning_rate": 8.717985059672177e-05, "loss": 0.1777, "step": 81610 }, { "epoch": 19.58, "learning_rate": 8.717685033703778e-05, "loss": 0.1363, "step": 81620 }, { "epoch": 19.58, "learning_rate": 8.717384977796346e-05, "loss": 0.1854, "step": 81630 }, { "epoch": 19.58, "learning_rate": 8.717084891952301e-05, "loss": 0.1491, "step": 81640 }, { "epoch": 19.58, "learning_rate": 8.716784776174058e-05, "loss": 0.198, "step": 81650 }, { "epoch": 19.59, "learning_rate": 8.716484630464035e-05, "loss": 0.1463, "step": 81660 }, { "epoch": 19.59, "learning_rate": 8.716184454824646e-05, "loss": 0.1342, "step": 81670 }, { "epoch": 19.59, "learning_rate": 8.715884249258311e-05, "loss": 0.1132, "step": 81680 }, { "epoch": 19.59, "learning_rate": 8.715584013767448e-05, "loss": 0.1188, "step": 81690 }, { "epoch": 19.59, "learning_rate": 8.715283748354472e-05, "loss": 0.1284, "step": 81700 }, { "epoch": 19.6, "learning_rate": 8.714983453021806e-05, "loss": 0.1217, "step": 81710 }, { "epoch": 19.6, "learning_rate": 8.714683127771863e-05, "loss": 0.1562, "step": 81720 }, { "epoch": 19.6, "learning_rate": 8.714382772607066e-05, "loss": 0.1225, "step": 81730 }, { "epoch": 19.6, "learning_rate": 8.71408238752983e-05, "loss": 0.1613, "step": 81740 }, { "epoch": 19.61, "learning_rate": 8.713781972542577e-05, "loss": 0.1526, "step": 81750 }, { "epoch": 19.61, "learning_rate": 8.713481527647724e-05, "loss": 0.125, "step": 81760 }, { "epoch": 19.61, "learning_rate": 8.713181052847693e-05, "loss": 0.1405, "step": 81770 }, { "epoch": 19.61, "learning_rate": 8.712880548144902e-05, "loss": 0.1339, "step": 81780 }, { "epoch": 19.62, "learning_rate": 8.712580013541768e-05, "loss": 0.1225, "step": 81790 }, { "epoch": 19.62, "learning_rate": 8.712279449040719e-05, "loss": 0.1021, "step": 81800 }, { "epoch": 19.62, "learning_rate": 8.711978854644169e-05, "loss": 0.1628, "step": 81810 }, { "epoch": 19.62, "learning_rate": 8.711678230354541e-05, "loss": 0.1087, "step": 81820 }, { "epoch": 19.62, "learning_rate": 8.711377576174257e-05, "loss": 0.1299, "step": 81830 }, { "epoch": 19.63, "learning_rate": 8.711076892105736e-05, "loss": 0.1584, "step": 81840 }, { "epoch": 19.63, "learning_rate": 8.710776178151401e-05, "loss": 0.1543, "step": 81850 }, { "epoch": 19.63, "learning_rate": 8.710475434313671e-05, "loss": 0.117, "step": 81860 }, { "epoch": 19.63, "learning_rate": 8.710174660594972e-05, "loss": 0.1309, "step": 81870 }, { "epoch": 19.64, "learning_rate": 8.709873856997724e-05, "loss": 0.1542, "step": 81880 }, { "epoch": 19.64, "learning_rate": 8.70957302352435e-05, "loss": 0.1375, "step": 81890 }, { "epoch": 19.64, "learning_rate": 8.70927216017727e-05, "loss": 0.1198, "step": 81900 }, { "epoch": 19.64, "learning_rate": 8.708971266958912e-05, "loss": 0.1457, "step": 81910 }, { "epoch": 19.65, "learning_rate": 8.708670343871697e-05, "loss": 0.1687, "step": 81920 }, { "epoch": 19.65, "learning_rate": 8.708369390918045e-05, "loss": 0.0996, "step": 81930 }, { "epoch": 19.65, "learning_rate": 8.708068408100382e-05, "loss": 0.1463, "step": 81940 }, { "epoch": 19.65, "learning_rate": 8.707767395421136e-05, "loss": 0.1549, "step": 81950 }, { "epoch": 19.65, "learning_rate": 8.707466352882723e-05, "loss": 0.1225, "step": 81960 }, { "epoch": 19.66, "learning_rate": 8.707165280487574e-05, "loss": 0.1166, "step": 81970 }, { "epoch": 19.66, "learning_rate": 8.70686417823811e-05, "loss": 0.1118, "step": 81980 }, { "epoch": 19.66, "learning_rate": 8.706563046136758e-05, "loss": 0.1096, "step": 81990 }, { "epoch": 19.66, "learning_rate": 8.706261884185942e-05, "loss": 0.132, "step": 82000 }, { "epoch": 19.67, "learning_rate": 8.705960692388087e-05, "loss": 0.1245, "step": 82010 }, { "epoch": 19.67, "learning_rate": 8.70565947074562e-05, "loss": 0.1033, "step": 82020 }, { "epoch": 19.67, "learning_rate": 8.705358219260964e-05, "loss": 0.101, "step": 82030 }, { "epoch": 19.67, "learning_rate": 8.705056937936548e-05, "loss": 0.1901, "step": 82040 }, { "epoch": 19.67, "learning_rate": 8.704755626774796e-05, "loss": 0.1513, "step": 82050 }, { "epoch": 19.68, "learning_rate": 8.704454285778137e-05, "loss": 0.1586, "step": 82060 }, { "epoch": 19.68, "learning_rate": 8.704152914948993e-05, "loss": 0.0861, "step": 82070 }, { "epoch": 19.68, "learning_rate": 8.703851514289797e-05, "loss": 0.1421, "step": 82080 }, { "epoch": 19.68, "learning_rate": 8.703550083802972e-05, "loss": 0.1397, "step": 82090 }, { "epoch": 19.69, "learning_rate": 8.703248623490949e-05, "loss": 0.1275, "step": 82100 }, { "epoch": 19.69, "learning_rate": 8.702947133356152e-05, "loss": 0.113, "step": 82110 }, { "epoch": 19.69, "learning_rate": 8.702645613401011e-05, "loss": 0.1373, "step": 82120 }, { "epoch": 19.69, "learning_rate": 8.702344063627952e-05, "loss": 0.1293, "step": 82130 }, { "epoch": 19.7, "learning_rate": 8.702042484039407e-05, "loss": 0.136, "step": 82140 }, { "epoch": 19.7, "learning_rate": 8.701740874637801e-05, "loss": 0.117, "step": 82150 }, { "epoch": 19.7, "learning_rate": 8.701439235425566e-05, "loss": 0.1153, "step": 82160 }, { "epoch": 19.7, "learning_rate": 8.701137566405131e-05, "loss": 0.104, "step": 82170 }, { "epoch": 19.7, "learning_rate": 8.700835867578923e-05, "loss": 0.1303, "step": 82180 }, { "epoch": 19.71, "learning_rate": 8.700534138949373e-05, "loss": 0.1194, "step": 82190 }, { "epoch": 19.71, "learning_rate": 8.700232380518909e-05, "loss": 0.1141, "step": 82200 }, { "epoch": 19.71, "learning_rate": 8.699930592289964e-05, "loss": 0.1236, "step": 82210 }, { "epoch": 19.71, "learning_rate": 8.699628774264967e-05, "loss": 0.1112, "step": 82220 }, { "epoch": 19.72, "learning_rate": 8.69932692644635e-05, "loss": 0.15, "step": 82230 }, { "epoch": 19.72, "learning_rate": 8.699025048836541e-05, "loss": 0.1015, "step": 82240 }, { "epoch": 19.72, "learning_rate": 8.698723141437974e-05, "loss": 0.1392, "step": 82250 }, { "epoch": 19.72, "learning_rate": 8.698421204253078e-05, "loss": 0.14, "step": 82260 }, { "epoch": 19.73, "learning_rate": 8.698119237284285e-05, "loss": 0.1354, "step": 82270 }, { "epoch": 19.73, "learning_rate": 8.697817240534027e-05, "loss": 0.1371, "step": 82280 }, { "epoch": 19.73, "learning_rate": 8.697515214004737e-05, "loss": 0.1048, "step": 82290 }, { "epoch": 19.73, "learning_rate": 8.697213157698847e-05, "loss": 0.1118, "step": 82300 }, { "epoch": 19.73, "learning_rate": 8.696911071618787e-05, "loss": 0.1298, "step": 82310 }, { "epoch": 19.74, "learning_rate": 8.696608955766994e-05, "loss": 0.1379, "step": 82320 }, { "epoch": 19.74, "learning_rate": 8.696306810145898e-05, "loss": 0.1337, "step": 82330 }, { "epoch": 19.74, "learning_rate": 8.696004634757933e-05, "loss": 0.1326, "step": 82340 }, { "epoch": 19.74, "learning_rate": 8.695702429605532e-05, "loss": 0.1105, "step": 82350 }, { "epoch": 19.75, "learning_rate": 8.69540019469113e-05, "loss": 0.1412, "step": 82360 }, { "epoch": 19.75, "learning_rate": 8.69509793001716e-05, "loss": 0.1355, "step": 82370 }, { "epoch": 19.75, "learning_rate": 8.694795635586054e-05, "loss": 0.1149, "step": 82380 }, { "epoch": 19.75, "learning_rate": 8.694493311400252e-05, "loss": 0.1159, "step": 82390 }, { "epoch": 19.75, "learning_rate": 8.694190957462183e-05, "loss": 0.1567, "step": 82400 }, { "epoch": 19.76, "learning_rate": 8.693888573774285e-05, "loss": 0.0995, "step": 82410 }, { "epoch": 19.76, "learning_rate": 8.693586160338992e-05, "loss": 0.1346, "step": 82420 }, { "epoch": 19.76, "learning_rate": 8.69328371715874e-05, "loss": 0.0812, "step": 82430 }, { "epoch": 19.76, "learning_rate": 8.692981244235965e-05, "loss": 0.1294, "step": 82440 }, { "epoch": 19.77, "learning_rate": 8.692678741573101e-05, "loss": 0.1047, "step": 82450 }, { "epoch": 19.77, "learning_rate": 8.692376209172586e-05, "loss": 0.1357, "step": 82460 }, { "epoch": 19.77, "learning_rate": 8.692073647036856e-05, "loss": 0.1393, "step": 82470 }, { "epoch": 19.77, "learning_rate": 8.691771055168344e-05, "loss": 0.1397, "step": 82480 }, { "epoch": 19.78, "learning_rate": 8.691468433569494e-05, "loss": 0.1072, "step": 82490 }, { "epoch": 19.78, "learning_rate": 8.691165782242738e-05, "loss": 0.1092, "step": 82500 }, { "epoch": 19.78, "learning_rate": 8.690863101190514e-05, "loss": 0.1181, "step": 82510 }, { "epoch": 19.78, "learning_rate": 8.69056039041526e-05, "loss": 0.1326, "step": 82520 }, { "epoch": 19.78, "learning_rate": 8.690257649919413e-05, "loss": 0.1489, "step": 82530 }, { "epoch": 19.79, "learning_rate": 8.689954879705413e-05, "loss": 0.1569, "step": 82540 }, { "epoch": 19.79, "learning_rate": 8.689652079775696e-05, "loss": 0.0919, "step": 82550 }, { "epoch": 19.79, "learning_rate": 8.689349250132702e-05, "loss": 0.0989, "step": 82560 }, { "epoch": 19.79, "learning_rate": 8.689046390778868e-05, "loss": 0.1068, "step": 82570 }, { "epoch": 19.8, "learning_rate": 8.688743501716636e-05, "loss": 0.123, "step": 82580 }, { "epoch": 19.8, "learning_rate": 8.688440582948441e-05, "loss": 0.1206, "step": 82590 }, { "epoch": 19.8, "learning_rate": 8.688137634476726e-05, "loss": 0.1321, "step": 82600 }, { "epoch": 19.8, "learning_rate": 8.68783465630393e-05, "loss": 0.1078, "step": 82610 }, { "epoch": 19.81, "learning_rate": 8.687531648432491e-05, "loss": 0.1049, "step": 82620 }, { "epoch": 19.81, "learning_rate": 8.687228610864851e-05, "loss": 0.1204, "step": 82630 }, { "epoch": 19.81, "learning_rate": 8.68692554360345e-05, "loss": 0.117, "step": 82640 }, { "epoch": 19.81, "learning_rate": 8.686622446650729e-05, "loss": 0.0984, "step": 82650 }, { "epoch": 19.81, "learning_rate": 8.686319320009129e-05, "loss": 0.1629, "step": 82660 }, { "epoch": 19.82, "learning_rate": 8.68601616368109e-05, "loss": 0.1396, "step": 82670 }, { "epoch": 19.82, "learning_rate": 8.685712977669053e-05, "loss": 0.1422, "step": 82680 }, { "epoch": 19.82, "learning_rate": 8.685409761975461e-05, "loss": 0.152, "step": 82690 }, { "epoch": 19.82, "learning_rate": 8.685106516602756e-05, "loss": 0.1474, "step": 82700 }, { "epoch": 19.83, "learning_rate": 8.684803241553379e-05, "loss": 0.141, "step": 82710 }, { "epoch": 19.83, "learning_rate": 8.684499936829774e-05, "loss": 0.1157, "step": 82720 }, { "epoch": 19.83, "learning_rate": 8.684196602434381e-05, "loss": 0.1309, "step": 82730 }, { "epoch": 19.83, "learning_rate": 8.683893238369645e-05, "loss": 0.1313, "step": 82740 }, { "epoch": 19.83, "learning_rate": 8.683589844638007e-05, "loss": 0.1148, "step": 82750 }, { "epoch": 19.84, "learning_rate": 8.683286421241911e-05, "loss": 0.1324, "step": 82760 }, { "epoch": 19.84, "learning_rate": 8.682982968183804e-05, "loss": 0.1209, "step": 82770 }, { "epoch": 19.84, "learning_rate": 8.682679485466123e-05, "loss": 0.0956, "step": 82780 }, { "epoch": 19.84, "learning_rate": 8.682375973091318e-05, "loss": 0.1527, "step": 82790 }, { "epoch": 19.85, "learning_rate": 8.68207243106183e-05, "loss": 0.118, "step": 82800 }, { "epoch": 19.85, "learning_rate": 8.681768859380104e-05, "loss": 0.1199, "step": 82810 }, { "epoch": 19.85, "learning_rate": 8.681465258048586e-05, "loss": 0.1556, "step": 82820 }, { "epoch": 19.85, "learning_rate": 8.68116162706972e-05, "loss": 0.1228, "step": 82830 }, { "epoch": 19.86, "learning_rate": 8.680857966445951e-05, "loss": 0.1209, "step": 82840 }, { "epoch": 19.86, "learning_rate": 8.680554276179724e-05, "loss": 0.1339, "step": 82850 }, { "epoch": 19.86, "learning_rate": 8.680250556273486e-05, "loss": 0.1259, "step": 82860 }, { "epoch": 19.86, "learning_rate": 8.679946806729683e-05, "loss": 0.1334, "step": 82870 }, { "epoch": 19.86, "learning_rate": 8.67964302755076e-05, "loss": 0.119, "step": 82880 }, { "epoch": 19.87, "learning_rate": 8.679339218739162e-05, "loss": 0.0976, "step": 82890 }, { "epoch": 19.87, "learning_rate": 8.679035380297338e-05, "loss": 0.1128, "step": 82900 }, { "epoch": 19.87, "learning_rate": 8.678731512227735e-05, "loss": 0.1453, "step": 82910 }, { "epoch": 19.87, "learning_rate": 8.678427614532799e-05, "loss": 0.097, "step": 82920 }, { "epoch": 19.88, "learning_rate": 8.678123687214976e-05, "loss": 0.1335, "step": 82930 }, { "epoch": 19.88, "learning_rate": 8.677819730276717e-05, "loss": 0.1389, "step": 82940 }, { "epoch": 19.88, "learning_rate": 8.677515743720468e-05, "loss": 0.0985, "step": 82950 }, { "epoch": 19.88, "learning_rate": 8.677211727548675e-05, "loss": 0.1037, "step": 82960 }, { "epoch": 19.89, "learning_rate": 8.676907681763791e-05, "loss": 0.1416, "step": 82970 }, { "epoch": 19.89, "learning_rate": 8.67660360636826e-05, "loss": 0.1171, "step": 82980 }, { "epoch": 19.89, "learning_rate": 8.676299501364534e-05, "loss": 0.1021, "step": 82990 }, { "epoch": 19.89, "learning_rate": 8.675995366755058e-05, "loss": 0.1178, "step": 83000 }, { "epoch": 19.89, "learning_rate": 8.675691202542287e-05, "loss": 0.1095, "step": 83010 }, { "epoch": 19.9, "learning_rate": 8.675387008728666e-05, "loss": 0.1123, "step": 83020 }, { "epoch": 19.9, "learning_rate": 8.675082785316644e-05, "loss": 0.1038, "step": 83030 }, { "epoch": 19.9, "learning_rate": 8.674778532308677e-05, "loss": 0.1129, "step": 83040 }, { "epoch": 19.9, "learning_rate": 8.674474249707207e-05, "loss": 0.103, "step": 83050 }, { "epoch": 19.91, "learning_rate": 8.674169937514691e-05, "loss": 0.1166, "step": 83060 }, { "epoch": 19.91, "learning_rate": 8.673865595733577e-05, "loss": 0.1355, "step": 83070 }, { "epoch": 19.91, "learning_rate": 8.673561224366316e-05, "loss": 0.1291, "step": 83080 }, { "epoch": 19.91, "learning_rate": 8.673256823415359e-05, "loss": 0.1201, "step": 83090 }, { "epoch": 19.91, "learning_rate": 8.672952392883157e-05, "loss": 0.089, "step": 83100 }, { "epoch": 19.92, "learning_rate": 8.672647932772163e-05, "loss": 0.1135, "step": 83110 }, { "epoch": 19.92, "learning_rate": 8.67234344308483e-05, "loss": 0.1156, "step": 83120 }, { "epoch": 19.92, "learning_rate": 8.672038923823604e-05, "loss": 0.116, "step": 83130 }, { "epoch": 19.92, "learning_rate": 8.671734374990945e-05, "loss": 0.1342, "step": 83140 }, { "epoch": 19.93, "learning_rate": 8.6714297965893e-05, "loss": 0.1472, "step": 83150 }, { "epoch": 19.93, "learning_rate": 8.671125188621126e-05, "loss": 0.1206, "step": 83160 }, { "epoch": 19.93, "learning_rate": 8.670820551088874e-05, "loss": 0.1061, "step": 83170 }, { "epoch": 19.93, "learning_rate": 8.670515883994996e-05, "loss": 0.083, "step": 83180 }, { "epoch": 19.94, "learning_rate": 8.670211187341947e-05, "loss": 0.1028, "step": 83190 }, { "epoch": 19.94, "learning_rate": 8.669906461132182e-05, "loss": 0.1148, "step": 83200 }, { "epoch": 19.94, "learning_rate": 8.669601705368152e-05, "loss": 0.1125, "step": 83210 }, { "epoch": 19.94, "learning_rate": 8.669296920052313e-05, "loss": 0.1025, "step": 83220 }, { "epoch": 19.94, "learning_rate": 8.66899210518712e-05, "loss": 0.1041, "step": 83230 }, { "epoch": 19.95, "learning_rate": 8.668687260775028e-05, "loss": 0.1045, "step": 83240 }, { "epoch": 19.95, "learning_rate": 8.668382386818489e-05, "loss": 0.0779, "step": 83250 }, { "epoch": 19.95, "learning_rate": 8.668077483319961e-05, "loss": 0.098, "step": 83260 }, { "epoch": 20.0, "learning_rate": 8.667772550281899e-05, "loss": 0.1034, "step": 83270 }, { "epoch": 20.0, "learning_rate": 8.667467587706757e-05, "loss": 0.0958, "step": 83280 }, { "epoch": 20.01, "learning_rate": 8.667162595596994e-05, "loss": 0.1216, "step": 83290 }, { "epoch": 20.01, "learning_rate": 8.666857573955063e-05, "loss": 0.1212, "step": 83300 }, { "epoch": 20.01, "learning_rate": 8.666552522783422e-05, "loss": 0.094, "step": 83310 }, { "epoch": 20.01, "learning_rate": 8.666247442084528e-05, "loss": 0.119, "step": 83320 }, { "epoch": 20.02, "learning_rate": 8.665942331860837e-05, "loss": 0.1188, "step": 83330 }, { "epoch": 20.02, "learning_rate": 8.665637192114805e-05, "loss": 0.0837, "step": 83340 }, { "epoch": 20.02, "learning_rate": 8.665332022848892e-05, "loss": 0.149, "step": 83350 }, { "epoch": 20.02, "learning_rate": 8.665026824065554e-05, "loss": 0.1263, "step": 83360 }, { "epoch": 20.03, "learning_rate": 8.664721595767249e-05, "loss": 0.0903, "step": 83370 }, { "epoch": 20.03, "learning_rate": 8.664416337956433e-05, "loss": 0.086, "step": 83380 }, { "epoch": 20.03, "learning_rate": 8.664111050635569e-05, "loss": 0.123, "step": 83390 }, { "epoch": 20.03, "learning_rate": 8.663805733807113e-05, "loss": 0.0947, "step": 83400 }, { "epoch": 20.03, "learning_rate": 8.663500387473522e-05, "loss": 0.1237, "step": 83410 }, { "epoch": 20.04, "learning_rate": 8.663195011637257e-05, "loss": 0.104, "step": 83420 }, { "epoch": 20.04, "learning_rate": 8.662889606300777e-05, "loss": 0.095, "step": 83430 }, { "epoch": 20.04, "learning_rate": 8.66258417146654e-05, "loss": 0.1091, "step": 83440 }, { "epoch": 20.04, "learning_rate": 8.66227870713701e-05, "loss": 0.1099, "step": 83450 }, { "epoch": 20.05, "learning_rate": 8.661973213314643e-05, "loss": 0.0902, "step": 83460 }, { "epoch": 20.05, "learning_rate": 8.661667690001897e-05, "loss": 0.1182, "step": 83470 }, { "epoch": 20.05, "learning_rate": 8.66136213720124e-05, "loss": 0.1192, "step": 83480 }, { "epoch": 20.05, "learning_rate": 8.661056554915125e-05, "loss": 0.127, "step": 83490 }, { "epoch": 20.05, "learning_rate": 8.660750943146018e-05, "loss": 0.0808, "step": 83500 }, { "epoch": 20.06, "learning_rate": 8.660445301896379e-05, "loss": 0.1193, "step": 83510 }, { "epoch": 20.06, "learning_rate": 8.660139631168667e-05, "loss": 0.0864, "step": 83520 }, { "epoch": 20.06, "learning_rate": 8.659833930965344e-05, "loss": 0.1146, "step": 83530 }, { "epoch": 20.06, "learning_rate": 8.659528201288876e-05, "loss": 0.102, "step": 83540 }, { "epoch": 20.07, "learning_rate": 8.65922244214172e-05, "loss": 0.1229, "step": 83550 }, { "epoch": 20.07, "learning_rate": 8.658916653526341e-05, "loss": 0.0949, "step": 83560 }, { "epoch": 20.07, "learning_rate": 8.658610835445203e-05, "loss": 0.0954, "step": 83570 }, { "epoch": 20.07, "learning_rate": 8.658304987900764e-05, "loss": 0.1088, "step": 83580 }, { "epoch": 20.08, "learning_rate": 8.657999110895492e-05, "loss": 0.0998, "step": 83590 }, { "epoch": 20.08, "learning_rate": 8.657693204431845e-05, "loss": 0.1094, "step": 83600 }, { "epoch": 20.08, "learning_rate": 8.657387268512292e-05, "loss": 0.0986, "step": 83610 }, { "epoch": 20.08, "learning_rate": 8.657081303139295e-05, "loss": 0.0951, "step": 83620 }, { "epoch": 20.08, "learning_rate": 8.656775308315317e-05, "loss": 0.0964, "step": 83630 }, { "epoch": 20.09, "learning_rate": 8.656469284042821e-05, "loss": 0.0849, "step": 83640 }, { "epoch": 20.09, "learning_rate": 8.656163230324275e-05, "loss": 0.0972, "step": 83650 }, { "epoch": 20.09, "learning_rate": 8.65585714716214e-05, "loss": 0.1438, "step": 83660 }, { "epoch": 20.09, "learning_rate": 8.655551034558884e-05, "loss": 0.1139, "step": 83670 }, { "epoch": 20.1, "learning_rate": 8.655244892516971e-05, "loss": 0.1114, "step": 83680 }, { "epoch": 20.1, "learning_rate": 8.654938721038866e-05, "loss": 0.0738, "step": 83690 }, { "epoch": 20.1, "learning_rate": 8.654632520127034e-05, "loss": 0.0808, "step": 83700 }, { "epoch": 20.1, "learning_rate": 8.654326289783943e-05, "loss": 0.105, "step": 83710 }, { "epoch": 20.11, "learning_rate": 8.654020030012056e-05, "loss": 0.0983, "step": 83720 }, { "epoch": 20.11, "learning_rate": 8.653713740813843e-05, "loss": 0.0941, "step": 83730 }, { "epoch": 20.11, "learning_rate": 8.653407422191768e-05, "loss": 0.1038, "step": 83740 }, { "epoch": 20.11, "learning_rate": 8.653101074148298e-05, "loss": 0.0956, "step": 83750 }, { "epoch": 20.11, "learning_rate": 8.652794696685902e-05, "loss": 0.125, "step": 83760 }, { "epoch": 20.12, "learning_rate": 8.652488289807046e-05, "loss": 0.1066, "step": 83770 }, { "epoch": 20.12, "learning_rate": 8.652181853514198e-05, "loss": 0.1131, "step": 83780 }, { "epoch": 20.12, "learning_rate": 8.651875387809824e-05, "loss": 0.1264, "step": 83790 }, { "epoch": 20.12, "learning_rate": 8.651568892696393e-05, "loss": 0.1454, "step": 83800 }, { "epoch": 20.13, "learning_rate": 8.651262368176375e-05, "loss": 0.0976, "step": 83810 }, { "epoch": 20.13, "learning_rate": 8.650955814252236e-05, "loss": 0.1106, "step": 83820 }, { "epoch": 20.13, "learning_rate": 8.650649230926447e-05, "loss": 0.0936, "step": 83830 }, { "epoch": 20.13, "learning_rate": 8.650342618201475e-05, "loss": 0.0901, "step": 83840 }, { "epoch": 20.13, "learning_rate": 8.65003597607979e-05, "loss": 0.1138, "step": 83850 }, { "epoch": 20.14, "learning_rate": 8.64972930456386e-05, "loss": 0.1179, "step": 83860 }, { "epoch": 20.14, "learning_rate": 8.649422603656158e-05, "loss": 0.0741, "step": 83870 }, { "epoch": 20.14, "learning_rate": 8.64911587335915e-05, "loss": 0.0764, "step": 83880 }, { "epoch": 20.14, "learning_rate": 8.648809113675311e-05, "loss": 0.1078, "step": 83890 }, { "epoch": 20.15, "learning_rate": 8.648502324607107e-05, "loss": 0.1019, "step": 83900 }, { "epoch": 20.15, "learning_rate": 8.64819550615701e-05, "loss": 0.102, "step": 83910 }, { "epoch": 20.15, "learning_rate": 8.64788865832749e-05, "loss": 0.0973, "step": 83920 }, { "epoch": 20.15, "learning_rate": 8.647581781121019e-05, "loss": 0.093, "step": 83930 }, { "epoch": 20.16, "learning_rate": 8.64727487454007e-05, "loss": 0.1093, "step": 83940 }, { "epoch": 20.16, "learning_rate": 8.646967938587112e-05, "loss": 0.1051, "step": 83950 }, { "epoch": 20.16, "learning_rate": 8.646660973264618e-05, "loss": 0.0957, "step": 83960 }, { "epoch": 20.16, "learning_rate": 8.646353978575059e-05, "loss": 0.0848, "step": 83970 }, { "epoch": 20.16, "learning_rate": 8.646046954520909e-05, "loss": 0.1016, "step": 83980 }, { "epoch": 20.17, "learning_rate": 8.645739901104639e-05, "loss": 0.1069, "step": 83990 }, { "epoch": 20.17, "learning_rate": 8.645432818328721e-05, "loss": 0.1024, "step": 84000 }, { "epoch": 20.17, "learning_rate": 8.645125706195632e-05, "loss": 0.1255, "step": 84010 }, { "epoch": 20.17, "learning_rate": 8.64481856470784e-05, "loss": 0.128, "step": 84020 }, { "epoch": 20.18, "learning_rate": 8.644511393867822e-05, "loss": 0.1186, "step": 84030 }, { "epoch": 20.18, "learning_rate": 8.64420419367805e-05, "loss": 0.1076, "step": 84040 }, { "epoch": 20.18, "learning_rate": 8.643896964140999e-05, "loss": 0.1473, "step": 84050 }, { "epoch": 20.18, "learning_rate": 8.643589705259142e-05, "loss": 0.0728, "step": 84060 }, { "epoch": 20.19, "learning_rate": 8.643282417034955e-05, "loss": 0.0818, "step": 84070 }, { "epoch": 20.19, "learning_rate": 8.642975099470911e-05, "loss": 0.1295, "step": 84080 }, { "epoch": 20.19, "learning_rate": 8.642667752569487e-05, "loss": 0.0978, "step": 84090 }, { "epoch": 20.19, "learning_rate": 8.642360376333156e-05, "loss": 0.1423, "step": 84100 }, { "epoch": 20.19, "learning_rate": 8.642052970764392e-05, "loss": 0.0886, "step": 84110 }, { "epoch": 20.2, "learning_rate": 8.641745535865676e-05, "loss": 0.1118, "step": 84120 }, { "epoch": 20.2, "learning_rate": 8.641438071639479e-05, "loss": 0.0969, "step": 84130 }, { "epoch": 20.2, "learning_rate": 8.641130578088276e-05, "loss": 0.1382, "step": 84140 }, { "epoch": 20.2, "learning_rate": 8.640823055214548e-05, "loss": 0.1261, "step": 84150 }, { "epoch": 20.21, "learning_rate": 8.640515503020769e-05, "loss": 0.1021, "step": 84160 }, { "epoch": 20.21, "learning_rate": 8.640207921509418e-05, "loss": 0.094, "step": 84170 }, { "epoch": 20.21, "learning_rate": 8.639900310682968e-05, "loss": 0.1041, "step": 84180 }, { "epoch": 20.21, "learning_rate": 8.639592670543899e-05, "loss": 0.1023, "step": 84190 }, { "epoch": 20.21, "learning_rate": 8.639285001094685e-05, "loss": 0.1321, "step": 84200 }, { "epoch": 20.22, "learning_rate": 8.63897730233781e-05, "loss": 0.1274, "step": 84210 }, { "epoch": 20.22, "learning_rate": 8.638669574275748e-05, "loss": 0.084, "step": 84220 }, { "epoch": 20.22, "learning_rate": 8.638361816910976e-05, "loss": 0.1236, "step": 84230 }, { "epoch": 20.22, "learning_rate": 8.638054030245975e-05, "loss": 0.081, "step": 84240 }, { "epoch": 20.23, "learning_rate": 8.637746214283223e-05, "loss": 0.1019, "step": 84250 }, { "epoch": 20.23, "learning_rate": 8.637438369025197e-05, "loss": 0.0987, "step": 84260 }, { "epoch": 20.23, "learning_rate": 8.637130494474379e-05, "loss": 0.0939, "step": 84270 }, { "epoch": 20.23, "learning_rate": 8.636822590633247e-05, "loss": 0.1097, "step": 84280 }, { "epoch": 20.24, "learning_rate": 8.63651465750428e-05, "loss": 0.1033, "step": 84290 }, { "epoch": 20.24, "learning_rate": 8.636206695089957e-05, "loss": 0.121, "step": 84300 }, { "epoch": 20.24, "learning_rate": 8.635898703392762e-05, "loss": 0.0613, "step": 84310 }, { "epoch": 20.24, "learning_rate": 8.635590682415171e-05, "loss": 0.1026, "step": 84320 }, { "epoch": 20.24, "learning_rate": 8.635282632159667e-05, "loss": 0.1373, "step": 84330 }, { "epoch": 20.25, "learning_rate": 8.634974552628731e-05, "loss": 0.1158, "step": 84340 }, { "epoch": 20.25, "learning_rate": 8.634666443824842e-05, "loss": 0.0838, "step": 84350 }, { "epoch": 20.25, "learning_rate": 8.634358305750483e-05, "loss": 0.0859, "step": 84360 }, { "epoch": 20.25, "learning_rate": 8.634050138408134e-05, "loss": 0.0925, "step": 84370 }, { "epoch": 20.26, "learning_rate": 8.633741941800278e-05, "loss": 0.1367, "step": 84380 }, { "epoch": 20.26, "learning_rate": 8.633433715929395e-05, "loss": 0.1167, "step": 84390 }, { "epoch": 20.26, "learning_rate": 8.63312546079797e-05, "loss": 0.0897, "step": 84400 }, { "epoch": 20.26, "learning_rate": 8.632817176408485e-05, "loss": 0.1151, "step": 84410 }, { "epoch": 20.27, "learning_rate": 8.632508862763421e-05, "loss": 0.1238, "step": 84420 }, { "epoch": 20.27, "learning_rate": 8.632200519865262e-05, "loss": 0.0861, "step": 84430 }, { "epoch": 20.27, "learning_rate": 8.63189214771649e-05, "loss": 0.0947, "step": 84440 }, { "epoch": 20.27, "learning_rate": 8.63158374631959e-05, "loss": 0.1042, "step": 84450 }, { "epoch": 20.27, "learning_rate": 8.631275315677043e-05, "loss": 0.0999, "step": 84460 }, { "epoch": 20.28, "learning_rate": 8.630966855791337e-05, "loss": 0.1046, "step": 84470 }, { "epoch": 20.28, "learning_rate": 8.630658366664951e-05, "loss": 0.0855, "step": 84480 }, { "epoch": 20.28, "learning_rate": 8.630349848300373e-05, "loss": 0.124, "step": 84490 }, { "epoch": 20.28, "learning_rate": 8.630041300700087e-05, "loss": 0.1264, "step": 84500 }, { "epoch": 20.29, "learning_rate": 8.629732723866578e-05, "loss": 0.0999, "step": 84510 }, { "epoch": 20.29, "learning_rate": 8.629424117802328e-05, "loss": 0.1357, "step": 84520 }, { "epoch": 20.29, "learning_rate": 8.629115482509825e-05, "loss": 0.1294, "step": 84530 }, { "epoch": 20.29, "learning_rate": 8.628806817991555e-05, "loss": 0.1244, "step": 84540 }, { "epoch": 20.29, "learning_rate": 8.628498124250002e-05, "loss": 0.0916, "step": 84550 }, { "epoch": 20.3, "learning_rate": 8.628189401287654e-05, "loss": 0.1161, "step": 84560 }, { "epoch": 20.3, "learning_rate": 8.627880649106995e-05, "loss": 0.0951, "step": 84570 }, { "epoch": 20.3, "learning_rate": 8.627571867710511e-05, "loss": 0.1036, "step": 84580 }, { "epoch": 20.3, "learning_rate": 8.627263057100691e-05, "loss": 0.1062, "step": 84590 }, { "epoch": 20.31, "learning_rate": 8.626954217280021e-05, "loss": 0.0969, "step": 84600 }, { "epoch": 20.31, "learning_rate": 8.626645348250988e-05, "loss": 0.1015, "step": 84610 }, { "epoch": 20.31, "learning_rate": 8.626336450016079e-05, "loss": 0.1369, "step": 84620 }, { "epoch": 20.31, "learning_rate": 8.626027522577781e-05, "loss": 0.0893, "step": 84630 }, { "epoch": 20.32, "learning_rate": 8.625718565938585e-05, "loss": 0.0641, "step": 84640 }, { "epoch": 20.32, "learning_rate": 8.625409580100976e-05, "loss": 0.1136, "step": 84650 }, { "epoch": 20.32, "learning_rate": 8.625100565067444e-05, "loss": 0.1143, "step": 84660 }, { "epoch": 20.32, "learning_rate": 8.624791520840474e-05, "loss": 0.0839, "step": 84670 }, { "epoch": 20.32, "learning_rate": 8.62448244742256e-05, "loss": 0.0715, "step": 84680 }, { "epoch": 20.33, "learning_rate": 8.624173344816187e-05, "loss": 0.1027, "step": 84690 }, { "epoch": 20.33, "learning_rate": 8.623864213023845e-05, "loss": 0.0851, "step": 84700 }, { "epoch": 20.33, "learning_rate": 8.623555052048025e-05, "loss": 0.1135, "step": 84710 }, { "epoch": 20.33, "learning_rate": 8.623245861891217e-05, "loss": 0.0929, "step": 84720 }, { "epoch": 20.34, "learning_rate": 8.622936642555909e-05, "loss": 0.0856, "step": 84730 }, { "epoch": 20.34, "learning_rate": 8.622627394044593e-05, "loss": 0.0988, "step": 84740 }, { "epoch": 20.34, "learning_rate": 8.622318116359757e-05, "loss": 0.1006, "step": 84750 }, { "epoch": 20.34, "learning_rate": 8.622008809503894e-05, "loss": 0.1348, "step": 84760 }, { "epoch": 20.35, "learning_rate": 8.621699473479493e-05, "loss": 0.1079, "step": 84770 }, { "epoch": 20.35, "learning_rate": 8.621390108289047e-05, "loss": 0.115, "step": 84780 }, { "epoch": 20.35, "learning_rate": 8.621080713935046e-05, "loss": 0.0918, "step": 84790 }, { "epoch": 20.35, "learning_rate": 8.620771290419982e-05, "loss": 0.0791, "step": 84800 }, { "epoch": 20.35, "learning_rate": 8.620461837746347e-05, "loss": 0.1411, "step": 84810 }, { "epoch": 20.36, "learning_rate": 8.620152355916634e-05, "loss": 0.1063, "step": 84820 }, { "epoch": 20.36, "learning_rate": 8.619842844933333e-05, "loss": 0.0821, "step": 84830 }, { "epoch": 20.36, "learning_rate": 8.619533304798938e-05, "loss": 0.0833, "step": 84840 }, { "epoch": 20.36, "learning_rate": 8.619223735515943e-05, "loss": 0.0881, "step": 84850 }, { "epoch": 20.37, "learning_rate": 8.618914137086839e-05, "loss": 0.0862, "step": 84860 }, { "epoch": 20.37, "learning_rate": 8.61860450951412e-05, "loss": 0.0876, "step": 84870 }, { "epoch": 20.37, "learning_rate": 8.618294852800277e-05, "loss": 0.0769, "step": 84880 }, { "epoch": 20.37, "learning_rate": 8.617985166947808e-05, "loss": 0.0751, "step": 84890 }, { "epoch": 20.37, "learning_rate": 8.617675451959205e-05, "loss": 0.0938, "step": 84900 }, { "epoch": 20.38, "learning_rate": 8.617365707836962e-05, "loss": 0.0952, "step": 84910 }, { "epoch": 20.38, "learning_rate": 8.617055934583573e-05, "loss": 0.1269, "step": 84920 }, { "epoch": 20.38, "learning_rate": 8.616746132201534e-05, "loss": 0.1268, "step": 84930 }, { "epoch": 20.38, "learning_rate": 8.616436300693337e-05, "loss": 0.0921, "step": 84940 }, { "epoch": 20.39, "learning_rate": 8.616126440061482e-05, "loss": 0.1025, "step": 84950 }, { "epoch": 20.39, "learning_rate": 8.61581655030846e-05, "loss": 0.1199, "step": 84960 }, { "epoch": 20.39, "learning_rate": 8.61550663143677e-05, "loss": 0.0871, "step": 84970 }, { "epoch": 20.39, "learning_rate": 8.615196683448904e-05, "loss": 0.1175, "step": 84980 }, { "epoch": 20.4, "learning_rate": 8.614886706347361e-05, "loss": 0.0933, "step": 84990 }, { "epoch": 20.4, "learning_rate": 8.614576700134634e-05, "loss": 0.1224, "step": 85000 }, { "epoch": 20.4, "learning_rate": 8.614266664813225e-05, "loss": 0.1065, "step": 85010 }, { "epoch": 20.4, "learning_rate": 8.613956600385625e-05, "loss": 0.0729, "step": 85020 }, { "epoch": 20.4, "learning_rate": 8.613646506854334e-05, "loss": 0.0907, "step": 85030 }, { "epoch": 20.41, "learning_rate": 8.61333638422185e-05, "loss": 0.0832, "step": 85040 }, { "epoch": 20.41, "learning_rate": 8.613026232490669e-05, "loss": 0.0885, "step": 85050 }, { "epoch": 20.41, "learning_rate": 8.612716051663289e-05, "loss": 0.0996, "step": 85060 }, { "epoch": 20.41, "learning_rate": 8.612405841742207e-05, "loss": 0.0878, "step": 85070 }, { "epoch": 20.42, "learning_rate": 8.612095602729923e-05, "loss": 0.1121, "step": 85080 }, { "epoch": 20.42, "learning_rate": 8.611785334628933e-05, "loss": 0.0924, "step": 85090 }, { "epoch": 20.42, "learning_rate": 8.611475037441738e-05, "loss": 0.1087, "step": 85100 }, { "epoch": 20.42, "learning_rate": 8.611164711170836e-05, "loss": 0.1037, "step": 85110 }, { "epoch": 20.43, "learning_rate": 8.610854355818727e-05, "loss": 0.0979, "step": 85120 }, { "epoch": 20.43, "learning_rate": 8.610543971387908e-05, "loss": 0.1076, "step": 85130 }, { "epoch": 20.43, "learning_rate": 8.61023355788088e-05, "loss": 0.0858, "step": 85140 }, { "epoch": 20.43, "learning_rate": 8.609923115300142e-05, "loss": 0.0884, "step": 85150 }, { "epoch": 20.43, "learning_rate": 8.609612643648197e-05, "loss": 0.1179, "step": 85160 }, { "epoch": 20.44, "learning_rate": 8.609302142927542e-05, "loss": 0.1352, "step": 85170 }, { "epoch": 20.44, "learning_rate": 8.608991613140677e-05, "loss": 0.1175, "step": 85180 }, { "epoch": 20.44, "learning_rate": 8.608681054290107e-05, "loss": 0.0704, "step": 85190 }, { "epoch": 20.44, "learning_rate": 8.608370466378328e-05, "loss": 0.0847, "step": 85200 }, { "epoch": 20.45, "learning_rate": 8.608059849407846e-05, "loss": 0.1262, "step": 85210 }, { "epoch": 20.45, "learning_rate": 8.607749203381157e-05, "loss": 0.1048, "step": 85220 }, { "epoch": 20.45, "learning_rate": 8.607438528300768e-05, "loss": 0.0898, "step": 85230 }, { "epoch": 20.45, "learning_rate": 8.607127824169177e-05, "loss": 0.1254, "step": 85240 }, { "epoch": 20.45, "learning_rate": 8.606817090988888e-05, "loss": 0.0652, "step": 85250 }, { "epoch": 20.46, "learning_rate": 8.606506328762403e-05, "loss": 0.1702, "step": 85260 }, { "epoch": 20.46, "learning_rate": 8.606195537492224e-05, "loss": 0.0876, "step": 85270 }, { "epoch": 20.46, "learning_rate": 8.605884717180856e-05, "loss": 0.1095, "step": 85280 }, { "epoch": 20.46, "learning_rate": 8.605573867830799e-05, "loss": 0.0983, "step": 85290 }, { "epoch": 20.47, "learning_rate": 8.605262989444559e-05, "loss": 0.1124, "step": 85300 }, { "epoch": 20.47, "learning_rate": 8.604952082024638e-05, "loss": 0.0856, "step": 85310 }, { "epoch": 20.47, "learning_rate": 8.60464114557354e-05, "loss": 0.0997, "step": 85320 }, { "epoch": 20.47, "learning_rate": 8.604330180093769e-05, "loss": 0.1149, "step": 85330 }, { "epoch": 20.48, "learning_rate": 8.604019185587831e-05, "loss": 0.0638, "step": 85340 }, { "epoch": 20.48, "learning_rate": 8.603708162058226e-05, "loss": 0.0947, "step": 85350 }, { "epoch": 20.48, "learning_rate": 8.603397109507464e-05, "loss": 0.0689, "step": 85360 }, { "epoch": 20.48, "learning_rate": 8.603086027938046e-05, "loss": 0.0731, "step": 85370 }, { "epoch": 20.48, "learning_rate": 8.60277491735248e-05, "loss": 0.1174, "step": 85380 }, { "epoch": 20.49, "learning_rate": 8.60246377775327e-05, "loss": 0.0755, "step": 85390 }, { "epoch": 20.49, "learning_rate": 8.602152609142922e-05, "loss": 0.1059, "step": 85400 }, { "epoch": 20.49, "learning_rate": 8.601841411523942e-05, "loss": 0.0789, "step": 85410 }, { "epoch": 20.49, "learning_rate": 8.601530184898836e-05, "loss": 0.1259, "step": 85420 }, { "epoch": 20.5, "learning_rate": 8.601218929270109e-05, "loss": 0.0761, "step": 85430 }, { "epoch": 20.5, "learning_rate": 8.60090764464027e-05, "loss": 0.0852, "step": 85440 }, { "epoch": 20.5, "learning_rate": 8.600596331011823e-05, "loss": 0.0932, "step": 85450 }, { "epoch": 20.5, "learning_rate": 8.600284988387277e-05, "loss": 0.1314, "step": 85460 }, { "epoch": 20.51, "learning_rate": 8.59997361676914e-05, "loss": 0.1031, "step": 85470 }, { "epoch": 20.51, "learning_rate": 8.599662216159918e-05, "loss": 0.0716, "step": 85480 }, { "epoch": 20.51, "learning_rate": 8.59935078656212e-05, "loss": 0.0794, "step": 85490 }, { "epoch": 20.51, "learning_rate": 8.599039327978251e-05, "loss": 0.0866, "step": 85500 }, { "epoch": 20.51, "learning_rate": 8.598727840410823e-05, "loss": 0.0865, "step": 85510 }, { "epoch": 20.52, "learning_rate": 8.598416323862343e-05, "loss": 0.1117, "step": 85520 }, { "epoch": 20.52, "learning_rate": 8.598104778335319e-05, "loss": 0.1263, "step": 85530 }, { "epoch": 20.52, "learning_rate": 8.59779320383226e-05, "loss": 0.0753, "step": 85540 }, { "epoch": 20.52, "learning_rate": 8.597481600355677e-05, "loss": 0.0909, "step": 85550 }, { "epoch": 20.53, "learning_rate": 8.597169967908078e-05, "loss": 0.1281, "step": 85560 }, { "epoch": 20.53, "learning_rate": 8.596858306491971e-05, "loss": 0.1108, "step": 85570 }, { "epoch": 20.53, "learning_rate": 8.596546616109869e-05, "loss": 0.1132, "step": 85580 }, { "epoch": 20.53, "learning_rate": 8.59623489676428e-05, "loss": 0.1249, "step": 85590 }, { "epoch": 20.53, "learning_rate": 8.595923148457715e-05, "loss": 0.0968, "step": 85600 }, { "epoch": 20.54, "learning_rate": 8.595611371192684e-05, "loss": 0.0986, "step": 85610 }, { "epoch": 20.54, "learning_rate": 8.595299564971699e-05, "loss": 0.1617, "step": 85620 }, { "epoch": 20.54, "learning_rate": 8.59498772979727e-05, "loss": 0.1241, "step": 85630 }, { "epoch": 20.54, "learning_rate": 8.594675865671908e-05, "loss": 0.1274, "step": 85640 }, { "epoch": 20.55, "learning_rate": 8.594363972598125e-05, "loss": 0.1164, "step": 85650 }, { "epoch": 20.55, "learning_rate": 8.594052050578434e-05, "loss": 0.1356, "step": 85660 }, { "epoch": 20.55, "learning_rate": 8.593740099615344e-05, "loss": 0.1031, "step": 85670 }, { "epoch": 20.55, "learning_rate": 8.593428119711368e-05, "loss": 0.1438, "step": 85680 }, { "epoch": 20.56, "learning_rate": 8.593116110869022e-05, "loss": 0.1351, "step": 85690 }, { "epoch": 20.56, "learning_rate": 8.592804073090814e-05, "loss": 0.1174, "step": 85700 }, { "epoch": 20.56, "learning_rate": 8.592492006379261e-05, "loss": 0.1352, "step": 85710 }, { "epoch": 20.56, "learning_rate": 8.59217991073687e-05, "loss": 0.1376, "step": 85720 }, { "epoch": 20.56, "learning_rate": 8.591867786166162e-05, "loss": 0.123, "step": 85730 }, { "epoch": 20.57, "learning_rate": 8.591555632669645e-05, "loss": 0.112, "step": 85740 }, { "epoch": 20.57, "learning_rate": 8.591243450249835e-05, "loss": 0.1052, "step": 85750 }, { "epoch": 20.57, "learning_rate": 8.590931238909245e-05, "loss": 0.1241, "step": 85760 }, { "epoch": 20.57, "learning_rate": 8.590618998650392e-05, "loss": 0.1307, "step": 85770 }, { "epoch": 20.58, "learning_rate": 8.590306729475787e-05, "loss": 0.1496, "step": 85780 }, { "epoch": 20.58, "learning_rate": 8.589994431387946e-05, "loss": 0.1435, "step": 85790 }, { "epoch": 20.58, "learning_rate": 8.589682104389385e-05, "loss": 0.1307, "step": 85800 }, { "epoch": 20.58, "learning_rate": 8.589369748482617e-05, "loss": 0.1169, "step": 85810 }, { "epoch": 20.59, "learning_rate": 8.589057363670161e-05, "loss": 0.1356, "step": 85820 }, { "epoch": 20.59, "learning_rate": 8.588744949954529e-05, "loss": 0.1324, "step": 85830 }, { "epoch": 20.59, "learning_rate": 8.588432507338239e-05, "loss": 0.0919, "step": 85840 }, { "epoch": 20.59, "learning_rate": 8.588120035823806e-05, "loss": 0.1256, "step": 85850 }, { "epoch": 20.59, "learning_rate": 8.587807535413747e-05, "loss": 0.1459, "step": 85860 }, { "epoch": 20.6, "learning_rate": 8.58749500611058e-05, "loss": 0.1387, "step": 85870 }, { "epoch": 20.6, "learning_rate": 8.58718244791682e-05, "loss": 0.0995, "step": 85880 }, { "epoch": 20.6, "learning_rate": 8.586869860834982e-05, "loss": 0.1352, "step": 85890 }, { "epoch": 20.6, "learning_rate": 8.58655724486759e-05, "loss": 0.1526, "step": 85900 }, { "epoch": 20.61, "learning_rate": 8.586244600017155e-05, "loss": 0.1312, "step": 85910 }, { "epoch": 20.61, "learning_rate": 8.585931926286198e-05, "loss": 0.1403, "step": 85920 }, { "epoch": 20.61, "learning_rate": 8.585619223677233e-05, "loss": 0.1313, "step": 85930 }, { "epoch": 20.61, "learning_rate": 8.585306492192785e-05, "loss": 0.116, "step": 85940 }, { "epoch": 20.61, "learning_rate": 8.584993731835367e-05, "loss": 0.1023, "step": 85950 }, { "epoch": 20.62, "learning_rate": 8.584680942607501e-05, "loss": 0.0927, "step": 85960 }, { "epoch": 20.62, "learning_rate": 8.584368124511704e-05, "loss": 0.1183, "step": 85970 }, { "epoch": 20.62, "learning_rate": 8.584055277550494e-05, "loss": 0.1241, "step": 85980 }, { "epoch": 20.62, "learning_rate": 8.583742401726394e-05, "loss": 0.125, "step": 85990 }, { "epoch": 20.63, "learning_rate": 8.583429497041922e-05, "loss": 0.1035, "step": 86000 }, { "epoch": 20.63, "learning_rate": 8.583116563499595e-05, "loss": 0.1221, "step": 86010 }, { "epoch": 20.63, "learning_rate": 8.582803601101938e-05, "loss": 0.0941, "step": 86020 }, { "epoch": 20.63, "learning_rate": 8.582490609851468e-05, "loss": 0.1688, "step": 86030 }, { "epoch": 20.64, "learning_rate": 8.582177589750707e-05, "loss": 0.1229, "step": 86040 }, { "epoch": 20.64, "learning_rate": 8.581864540802174e-05, "loss": 0.1065, "step": 86050 }, { "epoch": 20.64, "learning_rate": 8.581551463008393e-05, "loss": 0.0943, "step": 86060 }, { "epoch": 20.64, "learning_rate": 8.581238356371883e-05, "loss": 0.1312, "step": 86070 }, { "epoch": 20.64, "learning_rate": 8.580925220895166e-05, "loss": 0.1275, "step": 86080 }, { "epoch": 20.65, "learning_rate": 8.580612056580763e-05, "loss": 0.1511, "step": 86090 }, { "epoch": 20.65, "learning_rate": 8.580298863431198e-05, "loss": 0.1069, "step": 86100 }, { "epoch": 20.65, "learning_rate": 8.579985641448991e-05, "loss": 0.124, "step": 86110 }, { "epoch": 20.65, "learning_rate": 8.579672390636666e-05, "loss": 0.1087, "step": 86120 }, { "epoch": 20.66, "learning_rate": 8.579359110996745e-05, "loss": 0.115, "step": 86130 }, { "epoch": 20.66, "learning_rate": 8.57904580253175e-05, "loss": 0.1816, "step": 86140 }, { "epoch": 20.66, "learning_rate": 8.578732465244208e-05, "loss": 0.1221, "step": 86150 }, { "epoch": 20.66, "learning_rate": 8.578419099136636e-05, "loss": 0.1013, "step": 86160 }, { "epoch": 20.66, "learning_rate": 8.578105704211563e-05, "loss": 0.1015, "step": 86170 }, { "epoch": 20.67, "learning_rate": 8.57779228047151e-05, "loss": 0.0974, "step": 86180 }, { "epoch": 20.67, "learning_rate": 8.577478827919002e-05, "loss": 0.1207, "step": 86190 }, { "epoch": 20.67, "learning_rate": 8.577165346556564e-05, "loss": 0.1474, "step": 86200 }, { "epoch": 20.67, "learning_rate": 8.576851836386718e-05, "loss": 0.1126, "step": 86210 }, { "epoch": 20.68, "learning_rate": 8.576538297411991e-05, "loss": 0.1055, "step": 86220 }, { "epoch": 20.68, "learning_rate": 8.576224729634907e-05, "loss": 0.1131, "step": 86230 }, { "epoch": 20.68, "learning_rate": 8.575911133057992e-05, "loss": 0.1117, "step": 86240 }, { "epoch": 20.68, "learning_rate": 8.575597507683771e-05, "loss": 0.0963, "step": 86250 }, { "epoch": 20.69, "learning_rate": 8.575283853514768e-05, "loss": 0.1172, "step": 86260 }, { "epoch": 20.69, "learning_rate": 8.574970170553513e-05, "loss": 0.1125, "step": 86270 }, { "epoch": 20.69, "learning_rate": 8.574656458802529e-05, "loss": 0.0848, "step": 86280 }, { "epoch": 20.69, "learning_rate": 8.574342718264342e-05, "loss": 0.1011, "step": 86290 }, { "epoch": 20.69, "learning_rate": 8.57402894894148e-05, "loss": 0.0813, "step": 86300 }, { "epoch": 20.7, "learning_rate": 8.57371515083647e-05, "loss": 0.0897, "step": 86310 }, { "epoch": 20.7, "learning_rate": 8.573401323951837e-05, "loss": 0.0895, "step": 86320 }, { "epoch": 20.7, "learning_rate": 8.573087468290112e-05, "loss": 0.1202, "step": 86330 }, { "epoch": 20.7, "learning_rate": 8.572773583853819e-05, "loss": 0.1337, "step": 86340 }, { "epoch": 20.71, "learning_rate": 8.572459670645487e-05, "loss": 0.0937, "step": 86350 }, { "epoch": 20.71, "learning_rate": 8.572145728667645e-05, "loss": 0.1101, "step": 86360 }, { "epoch": 20.71, "learning_rate": 8.57183175792282e-05, "loss": 0.113, "step": 86370 }, { "epoch": 20.71, "learning_rate": 8.57151775841354e-05, "loss": 0.1406, "step": 86380 }, { "epoch": 20.72, "learning_rate": 8.571203730142334e-05, "loss": 0.1105, "step": 86390 }, { "epoch": 20.72, "learning_rate": 8.570889673111733e-05, "loss": 0.1071, "step": 86400 }, { "epoch": 20.72, "learning_rate": 8.570575587324264e-05, "loss": 0.0948, "step": 86410 }, { "epoch": 20.72, "learning_rate": 8.570261472782457e-05, "loss": 0.1202, "step": 86420 }, { "epoch": 20.72, "learning_rate": 8.569947329488841e-05, "loss": 0.0865, "step": 86430 }, { "epoch": 20.73, "learning_rate": 8.569633157445946e-05, "loss": 0.1333, "step": 86440 }, { "epoch": 20.73, "learning_rate": 8.569318956656303e-05, "loss": 0.1118, "step": 86450 }, { "epoch": 20.73, "learning_rate": 8.569004727122441e-05, "loss": 0.134, "step": 86460 }, { "epoch": 20.73, "learning_rate": 8.568690468846891e-05, "loss": 0.1556, "step": 86470 }, { "epoch": 20.74, "learning_rate": 8.568376181832185e-05, "loss": 0.1134, "step": 86480 }, { "epoch": 20.74, "learning_rate": 8.568061866080852e-05, "loss": 0.1224, "step": 86490 }, { "epoch": 20.74, "learning_rate": 8.567747521595423e-05, "loss": 0.0998, "step": 86500 }, { "epoch": 20.74, "learning_rate": 8.567433148378434e-05, "loss": 0.1544, "step": 86510 }, { "epoch": 20.74, "learning_rate": 8.567118746432411e-05, "loss": 0.0825, "step": 86520 }, { "epoch": 20.75, "learning_rate": 8.56680431575989e-05, "loss": 0.1027, "step": 86530 }, { "epoch": 20.75, "learning_rate": 8.5664898563634e-05, "loss": 0.1124, "step": 86540 }, { "epoch": 20.75, "learning_rate": 8.566175368245475e-05, "loss": 0.1205, "step": 86550 }, { "epoch": 20.75, "learning_rate": 8.565860851408646e-05, "loss": 0.1157, "step": 86560 }, { "epoch": 20.76, "learning_rate": 8.565546305855449e-05, "loss": 0.0884, "step": 86570 }, { "epoch": 20.76, "learning_rate": 8.565231731588415e-05, "loss": 0.1624, "step": 86580 }, { "epoch": 20.76, "learning_rate": 8.564917128610079e-05, "loss": 0.1021, "step": 86590 }, { "epoch": 20.76, "learning_rate": 8.564602496922971e-05, "loss": 0.1208, "step": 86600 }, { "epoch": 20.77, "learning_rate": 8.564287836529627e-05, "loss": 0.0955, "step": 86610 }, { "epoch": 20.77, "learning_rate": 8.563973147432584e-05, "loss": 0.1202, "step": 86620 }, { "epoch": 20.77, "learning_rate": 8.563658429634371e-05, "loss": 0.1183, "step": 86630 }, { "epoch": 20.77, "learning_rate": 8.563343683137523e-05, "loss": 0.1155, "step": 86640 }, { "epoch": 20.77, "learning_rate": 8.56302890794458e-05, "loss": 0.1091, "step": 86650 }, { "epoch": 20.78, "learning_rate": 8.56271410405807e-05, "loss": 0.1135, "step": 86660 }, { "epoch": 20.78, "learning_rate": 8.562399271480534e-05, "loss": 0.1152, "step": 86670 }, { "epoch": 20.78, "learning_rate": 8.562084410214503e-05, "loss": 0.0851, "step": 86680 }, { "epoch": 20.78, "learning_rate": 8.561769520262515e-05, "loss": 0.1073, "step": 86690 }, { "epoch": 20.79, "learning_rate": 8.561454601627105e-05, "loss": 0.1257, "step": 86700 }, { "epoch": 20.79, "learning_rate": 8.56113965431081e-05, "loss": 0.1081, "step": 86710 }, { "epoch": 20.79, "learning_rate": 8.560824678316167e-05, "loss": 0.123, "step": 86720 }, { "epoch": 20.79, "learning_rate": 8.560509673645709e-05, "loss": 0.0946, "step": 86730 }, { "epoch": 20.8, "learning_rate": 8.560194640301978e-05, "loss": 0.1257, "step": 86740 }, { "epoch": 20.8, "learning_rate": 8.559879578287504e-05, "loss": 0.1002, "step": 86750 }, { "epoch": 20.8, "learning_rate": 8.559564487604831e-05, "loss": 0.094, "step": 86760 }, { "epoch": 20.8, "learning_rate": 8.559249368256492e-05, "loss": 0.0928, "step": 86770 }, { "epoch": 20.8, "learning_rate": 8.558934220245028e-05, "loss": 0.075, "step": 86780 }, { "epoch": 20.81, "learning_rate": 8.558619043572976e-05, "loss": 0.0884, "step": 86790 }, { "epoch": 20.81, "learning_rate": 8.558303838242872e-05, "loss": 0.0973, "step": 86800 }, { "epoch": 20.81, "learning_rate": 8.557988604257257e-05, "loss": 0.0881, "step": 86810 }, { "epoch": 20.81, "learning_rate": 8.557673341618668e-05, "loss": 0.085, "step": 86820 }, { "epoch": 20.82, "learning_rate": 8.557358050329642e-05, "loss": 0.1097, "step": 86830 }, { "epoch": 20.82, "learning_rate": 8.557042730392724e-05, "loss": 0.106, "step": 86840 }, { "epoch": 20.82, "learning_rate": 8.556727381810449e-05, "loss": 0.1115, "step": 86850 }, { "epoch": 20.82, "learning_rate": 8.556412004585357e-05, "loss": 0.1344, "step": 86860 }, { "epoch": 20.82, "learning_rate": 8.556096598719987e-05, "loss": 0.1107, "step": 86870 }, { "epoch": 20.83, "learning_rate": 8.555781164216883e-05, "loss": 0.0785, "step": 86880 }, { "epoch": 20.83, "learning_rate": 8.55546570107858e-05, "loss": 0.106, "step": 86890 }, { "epoch": 20.83, "learning_rate": 8.55515020930762e-05, "loss": 0.0985, "step": 86900 }, { "epoch": 20.83, "learning_rate": 8.554834688906547e-05, "loss": 0.1202, "step": 86910 }, { "epoch": 20.84, "learning_rate": 8.5545191398779e-05, "loss": 0.1161, "step": 86920 }, { "epoch": 20.84, "learning_rate": 8.554203562224216e-05, "loss": 0.0849, "step": 86930 }, { "epoch": 20.84, "learning_rate": 8.553887955948043e-05, "loss": 0.0883, "step": 86940 }, { "epoch": 20.84, "learning_rate": 8.55357232105192e-05, "loss": 0.1212, "step": 86950 }, { "epoch": 20.85, "learning_rate": 8.553256657538387e-05, "loss": 0.0795, "step": 86960 }, { "epoch": 20.85, "learning_rate": 8.552940965409987e-05, "loss": 0.0947, "step": 86970 }, { "epoch": 20.85, "learning_rate": 8.552625244669264e-05, "loss": 0.1022, "step": 86980 }, { "epoch": 20.85, "learning_rate": 8.55230949531876e-05, "loss": 0.1077, "step": 86990 }, { "epoch": 20.85, "learning_rate": 8.551993717361015e-05, "loss": 0.1328, "step": 87000 }, { "epoch": 20.86, "learning_rate": 8.551677910798577e-05, "loss": 0.0804, "step": 87010 }, { "epoch": 20.86, "learning_rate": 8.551362075633984e-05, "loss": 0.1361, "step": 87020 }, { "epoch": 20.86, "learning_rate": 8.551046211869783e-05, "loss": 0.0798, "step": 87030 }, { "epoch": 20.86, "learning_rate": 8.550730319508516e-05, "loss": 0.0949, "step": 87040 }, { "epoch": 20.87, "learning_rate": 8.550414398552729e-05, "loss": 0.0855, "step": 87050 }, { "epoch": 20.87, "learning_rate": 8.550098449004964e-05, "loss": 0.0875, "step": 87060 }, { "epoch": 20.87, "learning_rate": 8.549782470867765e-05, "loss": 0.128, "step": 87070 }, { "epoch": 20.87, "learning_rate": 8.549466464143678e-05, "loss": 0.1212, "step": 87080 }, { "epoch": 20.88, "learning_rate": 8.549150428835249e-05, "loss": 0.0952, "step": 87090 }, { "epoch": 20.88, "learning_rate": 8.548834364945021e-05, "loss": 0.1029, "step": 87100 }, { "epoch": 20.88, "learning_rate": 8.54851827247554e-05, "loss": 0.0983, "step": 87110 }, { "epoch": 20.88, "learning_rate": 8.548202151429351e-05, "loss": 0.1077, "step": 87120 }, { "epoch": 20.88, "learning_rate": 8.547886001809e-05, "loss": 0.0959, "step": 87130 }, { "epoch": 20.89, "learning_rate": 8.547569823617033e-05, "loss": 0.079, "step": 87140 }, { "epoch": 20.89, "learning_rate": 8.547253616855997e-05, "loss": 0.0981, "step": 87150 }, { "epoch": 20.89, "learning_rate": 8.546937381528438e-05, "loss": 0.1121, "step": 87160 }, { "epoch": 20.89, "learning_rate": 8.546621117636903e-05, "loss": 0.0968, "step": 87170 }, { "epoch": 20.9, "learning_rate": 8.546304825183938e-05, "loss": 0.0983, "step": 87180 }, { "epoch": 20.9, "learning_rate": 8.54598850417209e-05, "loss": 0.1172, "step": 87190 }, { "epoch": 20.9, "learning_rate": 8.545672154603908e-05, "loss": 0.121, "step": 87200 }, { "epoch": 20.9, "learning_rate": 8.545355776481938e-05, "loss": 0.0771, "step": 87210 }, { "epoch": 20.9, "learning_rate": 8.545039369808728e-05, "loss": 0.1406, "step": 87220 }, { "epoch": 20.91, "learning_rate": 8.544722934586828e-05, "loss": 0.1085, "step": 87230 }, { "epoch": 20.91, "learning_rate": 8.544406470818784e-05, "loss": 0.135, "step": 87240 }, { "epoch": 20.91, "learning_rate": 8.544089978507145e-05, "loss": 0.0913, "step": 87250 }, { "epoch": 20.91, "learning_rate": 8.54377345765446e-05, "loss": 0.1254, "step": 87260 }, { "epoch": 20.92, "learning_rate": 8.543456908263279e-05, "loss": 0.0741, "step": 87270 }, { "epoch": 20.92, "learning_rate": 8.543140330336151e-05, "loss": 0.1107, "step": 87280 }, { "epoch": 20.92, "learning_rate": 8.542823723875622e-05, "loss": 0.0953, "step": 87290 }, { "epoch": 20.92, "learning_rate": 8.542507088884246e-05, "loss": 0.08, "step": 87300 }, { "epoch": 20.93, "learning_rate": 8.542190425364572e-05, "loss": 0.1219, "step": 87310 }, { "epoch": 20.93, "learning_rate": 8.541873733319149e-05, "loss": 0.0999, "step": 87320 }, { "epoch": 20.93, "learning_rate": 8.541557012750527e-05, "loss": 0.1164, "step": 87330 }, { "epoch": 20.93, "learning_rate": 8.541240263661258e-05, "loss": 0.0866, "step": 87340 }, { "epoch": 20.93, "learning_rate": 8.540923486053893e-05, "loss": 0.0661, "step": 87350 }, { "epoch": 20.94, "learning_rate": 8.540606679930982e-05, "loss": 0.1174, "step": 87360 }, { "epoch": 20.94, "learning_rate": 8.540289845295077e-05, "loss": 0.112, "step": 87370 }, { "epoch": 20.94, "learning_rate": 8.539972982148727e-05, "loss": 0.0714, "step": 87380 }, { "epoch": 20.94, "learning_rate": 8.539656090494488e-05, "loss": 0.0962, "step": 87390 }, { "epoch": 20.95, "learning_rate": 8.53933917033491e-05, "loss": 0.1343, "step": 87400 }, { "epoch": 20.95, "learning_rate": 8.539022221672543e-05, "loss": 0.1038, "step": 87410 }, { "epoch": 20.95, "learning_rate": 8.538705244509944e-05, "loss": 0.08, "step": 87420 }, { "epoch": 21.0, "learning_rate": 8.53838823884966e-05, "loss": 0.1017, "step": 87430 }, { "epoch": 21.0, "learning_rate": 8.538071204694248e-05, "loss": 0.1039, "step": 87440 }, { "epoch": 21.01, "learning_rate": 8.537754142046261e-05, "loss": 0.0788, "step": 87450 }, { "epoch": 21.01, "learning_rate": 8.537437050908252e-05, "loss": 0.0836, "step": 87460 }, { "epoch": 21.01, "learning_rate": 8.537119931282774e-05, "loss": 0.0959, "step": 87470 }, { "epoch": 21.01, "learning_rate": 8.536802783172381e-05, "loss": 0.0957, "step": 87480 }, { "epoch": 21.02, "learning_rate": 8.536485606579624e-05, "loss": 0.0911, "step": 87490 }, { "epoch": 21.02, "learning_rate": 8.536168401507063e-05, "loss": 0.0589, "step": 87500 }, { "epoch": 21.02, "learning_rate": 8.53585116795725e-05, "loss": 0.1312, "step": 87510 }, { "epoch": 21.02, "learning_rate": 8.535533905932738e-05, "loss": 0.0743, "step": 87520 }, { "epoch": 21.02, "learning_rate": 8.535216615436084e-05, "loss": 0.1371, "step": 87530 }, { "epoch": 21.03, "learning_rate": 8.534899296469843e-05, "loss": 0.0708, "step": 87540 }, { "epoch": 21.03, "learning_rate": 8.534581949036568e-05, "loss": 0.0845, "step": 87550 }, { "epoch": 21.03, "learning_rate": 8.534264573138818e-05, "loss": 0.0857, "step": 87560 }, { "epoch": 21.03, "learning_rate": 8.533947168779148e-05, "loss": 0.0627, "step": 87570 }, { "epoch": 21.04, "learning_rate": 8.533629735960112e-05, "loss": 0.0789, "step": 87580 }, { "epoch": 21.04, "learning_rate": 8.533312274684268e-05, "loss": 0.0996, "step": 87590 }, { "epoch": 21.04, "learning_rate": 8.532994784954173e-05, "loss": 0.0961, "step": 87600 }, { "epoch": 21.04, "learning_rate": 8.532677266772385e-05, "loss": 0.0912, "step": 87610 }, { "epoch": 21.05, "learning_rate": 8.532359720141456e-05, "loss": 0.0814, "step": 87620 }, { "epoch": 21.05, "learning_rate": 8.53204214506395e-05, "loss": 0.0609, "step": 87630 }, { "epoch": 21.05, "learning_rate": 8.531724541542419e-05, "loss": 0.1046, "step": 87640 }, { "epoch": 21.05, "learning_rate": 8.531406909579422e-05, "loss": 0.0913, "step": 87650 }, { "epoch": 21.05, "learning_rate": 8.531089249177518e-05, "loss": 0.088, "step": 87660 }, { "epoch": 21.06, "learning_rate": 8.530771560339265e-05, "loss": 0.0733, "step": 87670 }, { "epoch": 21.06, "learning_rate": 8.530453843067222e-05, "loss": 0.1128, "step": 87680 }, { "epoch": 21.06, "learning_rate": 8.530136097363945e-05, "loss": 0.0819, "step": 87690 }, { "epoch": 21.06, "learning_rate": 8.529818323231998e-05, "loss": 0.0772, "step": 87700 }, { "epoch": 21.07, "learning_rate": 8.529500520673933e-05, "loss": 0.0743, "step": 87710 }, { "epoch": 21.07, "learning_rate": 8.529182689692315e-05, "loss": 0.1174, "step": 87720 }, { "epoch": 21.07, "learning_rate": 8.5288648302897e-05, "loss": 0.0732, "step": 87730 }, { "epoch": 21.07, "learning_rate": 8.528546942468652e-05, "loss": 0.1109, "step": 87740 }, { "epoch": 21.07, "learning_rate": 8.528229026231726e-05, "loss": 0.0893, "step": 87750 }, { "epoch": 21.08, "learning_rate": 8.527911081581485e-05, "loss": 0.0778, "step": 87760 }, { "epoch": 21.08, "learning_rate": 8.527593108520491e-05, "loss": 0.0903, "step": 87770 }, { "epoch": 21.08, "learning_rate": 8.5272751070513e-05, "loss": 0.1099, "step": 87780 }, { "epoch": 21.08, "learning_rate": 8.526957077176476e-05, "loss": 0.0726, "step": 87790 }, { "epoch": 21.09, "learning_rate": 8.526639018898581e-05, "loss": 0.0778, "step": 87800 }, { "epoch": 21.09, "learning_rate": 8.526320932220173e-05, "loss": 0.0787, "step": 87810 }, { "epoch": 21.09, "learning_rate": 8.526002817143818e-05, "loss": 0.1484, "step": 87820 }, { "epoch": 21.09, "learning_rate": 8.525684673672074e-05, "loss": 0.0721, "step": 87830 }, { "epoch": 21.1, "learning_rate": 8.525366501807506e-05, "loss": 0.0937, "step": 87840 }, { "epoch": 21.1, "learning_rate": 8.525048301552674e-05, "loss": 0.075, "step": 87850 }, { "epoch": 21.1, "learning_rate": 8.52473007291014e-05, "loss": 0.0891, "step": 87860 }, { "epoch": 21.1, "learning_rate": 8.524411815882471e-05, "loss": 0.0479, "step": 87870 }, { "epoch": 21.1, "learning_rate": 8.524093530472225e-05, "loss": 0.0837, "step": 87880 }, { "epoch": 21.11, "learning_rate": 8.523775216681968e-05, "loss": 0.0771, "step": 87890 }, { "epoch": 21.11, "learning_rate": 8.523456874514263e-05, "loss": 0.1282, "step": 87900 }, { "epoch": 21.11, "learning_rate": 8.523138503971673e-05, "loss": 0.079, "step": 87910 }, { "epoch": 21.11, "learning_rate": 8.522820105056761e-05, "loss": 0.1003, "step": 87920 }, { "epoch": 21.12, "learning_rate": 8.522501677772095e-05, "loss": 0.0848, "step": 87930 }, { "epoch": 21.12, "learning_rate": 8.522183222120234e-05, "loss": 0.0854, "step": 87940 }, { "epoch": 21.12, "learning_rate": 8.521864738103746e-05, "loss": 0.0728, "step": 87950 }, { "epoch": 21.12, "learning_rate": 8.521546225725197e-05, "loss": 0.1031, "step": 87960 }, { "epoch": 21.12, "learning_rate": 8.521227684987147e-05, "loss": 0.0984, "step": 87970 }, { "epoch": 21.13, "learning_rate": 8.520909115892166e-05, "loss": 0.0854, "step": 87980 }, { "epoch": 21.13, "learning_rate": 8.520590518442818e-05, "loss": 0.0982, "step": 87990 }, { "epoch": 21.13, "learning_rate": 8.520271892641668e-05, "loss": 0.0909, "step": 88000 }, { "epoch": 21.13, "learning_rate": 8.519953238491283e-05, "loss": 0.0685, "step": 88010 }, { "epoch": 21.14, "learning_rate": 8.519634555994228e-05, "loss": 0.1031, "step": 88020 }, { "epoch": 21.14, "learning_rate": 8.519315845153071e-05, "loss": 0.0972, "step": 88030 }, { "epoch": 21.14, "learning_rate": 8.518997105970377e-05, "loss": 0.0945, "step": 88040 }, { "epoch": 21.14, "learning_rate": 8.518678338448712e-05, "loss": 0.0762, "step": 88050 }, { "epoch": 21.15, "learning_rate": 8.518359542590646e-05, "loss": 0.094, "step": 88060 }, { "epoch": 21.15, "learning_rate": 8.518040718398745e-05, "loss": 0.0807, "step": 88070 }, { "epoch": 21.15, "learning_rate": 8.517721865875576e-05, "loss": 0.1084, "step": 88080 }, { "epoch": 21.15, "learning_rate": 8.517402985023708e-05, "loss": 0.1115, "step": 88090 }, { "epoch": 21.15, "learning_rate": 8.517084075845708e-05, "loss": 0.0734, "step": 88100 }, { "epoch": 21.16, "learning_rate": 8.516765138344143e-05, "loss": 0.0586, "step": 88110 }, { "epoch": 21.16, "learning_rate": 8.516446172521583e-05, "loss": 0.1076, "step": 88120 }, { "epoch": 21.16, "learning_rate": 8.516127178380597e-05, "loss": 0.1057, "step": 88130 }, { "epoch": 21.16, "learning_rate": 8.515808155923754e-05, "loss": 0.0834, "step": 88140 }, { "epoch": 21.17, "learning_rate": 8.515489105153622e-05, "loss": 0.0952, "step": 88150 }, { "epoch": 21.17, "learning_rate": 8.51517002607277e-05, "loss": 0.09, "step": 88160 }, { "epoch": 21.17, "learning_rate": 8.51485091868377e-05, "loss": 0.0738, "step": 88170 }, { "epoch": 21.17, "learning_rate": 8.51453178298919e-05, "loss": 0.0854, "step": 88180 }, { "epoch": 21.18, "learning_rate": 8.5142126189916e-05, "loss": 0.0969, "step": 88190 }, { "epoch": 21.18, "learning_rate": 8.513893426693572e-05, "loss": 0.0848, "step": 88200 }, { "epoch": 21.18, "learning_rate": 8.513574206097672e-05, "loss": 0.0771, "step": 88210 }, { "epoch": 21.18, "learning_rate": 8.513254957206476e-05, "loss": 0.0994, "step": 88220 }, { "epoch": 21.18, "learning_rate": 8.512935680022552e-05, "loss": 0.0843, "step": 88230 }, { "epoch": 21.19, "learning_rate": 8.512616374548473e-05, "loss": 0.1021, "step": 88240 }, { "epoch": 21.19, "learning_rate": 8.512297040786809e-05, "loss": 0.0748, "step": 88250 }, { "epoch": 21.19, "learning_rate": 8.511977678740131e-05, "loss": 0.0911, "step": 88260 }, { "epoch": 21.19, "learning_rate": 8.511658288411014e-05, "loss": 0.098, "step": 88270 }, { "epoch": 21.2, "learning_rate": 8.511338869802026e-05, "loss": 0.0774, "step": 88280 }, { "epoch": 21.2, "learning_rate": 8.511019422915742e-05, "loss": 0.1154, "step": 88290 }, { "epoch": 21.2, "learning_rate": 8.510699947754734e-05, "loss": 0.1049, "step": 88300 }, { "epoch": 21.2, "learning_rate": 8.510380444321575e-05, "loss": 0.0538, "step": 88310 }, { "epoch": 21.2, "learning_rate": 8.510060912618835e-05, "loss": 0.1038, "step": 88320 }, { "epoch": 21.21, "learning_rate": 8.509741352649094e-05, "loss": 0.0988, "step": 88330 }, { "epoch": 21.21, "learning_rate": 8.509421764414917e-05, "loss": 0.1043, "step": 88340 }, { "epoch": 21.21, "learning_rate": 8.509102147918886e-05, "loss": 0.0862, "step": 88350 }, { "epoch": 21.21, "learning_rate": 8.50878250316357e-05, "loss": 0.0991, "step": 88360 }, { "epoch": 21.22, "learning_rate": 8.508462830151543e-05, "loss": 0.0807, "step": 88370 }, { "epoch": 21.22, "learning_rate": 8.50814312888538e-05, "loss": 0.0809, "step": 88380 }, { "epoch": 21.22, "learning_rate": 8.507823399367658e-05, "loss": 0.0888, "step": 88390 }, { "epoch": 21.22, "learning_rate": 8.507503641600948e-05, "loss": 0.0892, "step": 88400 }, { "epoch": 21.23, "learning_rate": 8.507183855587829e-05, "loss": 0.0948, "step": 88410 }, { "epoch": 21.23, "learning_rate": 8.506864041330871e-05, "loss": 0.0714, "step": 88420 }, { "epoch": 21.23, "learning_rate": 8.506544198832655e-05, "loss": 0.0633, "step": 88430 }, { "epoch": 21.23, "learning_rate": 8.506224328095756e-05, "loss": 0.0597, "step": 88440 }, { "epoch": 21.23, "learning_rate": 8.505904429122744e-05, "loss": 0.1235, "step": 88450 }, { "epoch": 21.24, "learning_rate": 8.505584501916204e-05, "loss": 0.0637, "step": 88460 }, { "epoch": 21.24, "learning_rate": 8.505264546478705e-05, "loss": 0.0829, "step": 88470 }, { "epoch": 21.24, "learning_rate": 8.504944562812829e-05, "loss": 0.1074, "step": 88480 }, { "epoch": 21.24, "learning_rate": 8.504624550921148e-05, "loss": 0.0856, "step": 88490 }, { "epoch": 21.25, "learning_rate": 8.504304510806245e-05, "loss": 0.0958, "step": 88500 }, { "epoch": 21.25, "learning_rate": 8.503984442470691e-05, "loss": 0.0984, "step": 88510 }, { "epoch": 21.25, "learning_rate": 8.503664345917067e-05, "loss": 0.095, "step": 88520 }, { "epoch": 21.25, "learning_rate": 8.503344221147951e-05, "loss": 0.0866, "step": 88530 }, { "epoch": 21.26, "learning_rate": 8.50302406816592e-05, "loss": 0.0999, "step": 88540 }, { "epoch": 21.26, "learning_rate": 8.502703886973553e-05, "loss": 0.1002, "step": 88550 }, { "epoch": 21.26, "learning_rate": 8.502383677573428e-05, "loss": 0.0667, "step": 88560 }, { "epoch": 21.26, "learning_rate": 8.502063439968125e-05, "loss": 0.0758, "step": 88570 }, { "epoch": 21.26, "learning_rate": 8.501743174160219e-05, "loss": 0.0928, "step": 88580 }, { "epoch": 21.27, "learning_rate": 8.501422880152292e-05, "loss": 0.0903, "step": 88590 }, { "epoch": 21.27, "learning_rate": 8.501102557946925e-05, "loss": 0.0975, "step": 88600 }, { "epoch": 21.27, "learning_rate": 8.500782207546694e-05, "loss": 0.073, "step": 88610 }, { "epoch": 21.27, "learning_rate": 8.500461828954183e-05, "loss": 0.0801, "step": 88620 }, { "epoch": 21.28, "learning_rate": 8.500141422171966e-05, "loss": 0.1034, "step": 88630 }, { "epoch": 21.28, "learning_rate": 8.49982098720263e-05, "loss": 0.081, "step": 88640 }, { "epoch": 21.28, "learning_rate": 8.499500524048751e-05, "loss": 0.0909, "step": 88650 }, { "epoch": 21.28, "learning_rate": 8.49918003271291e-05, "loss": 0.0928, "step": 88660 }, { "epoch": 21.28, "learning_rate": 8.498859513197692e-05, "loss": 0.0866, "step": 88670 }, { "epoch": 21.29, "learning_rate": 8.498538965505673e-05, "loss": 0.088, "step": 88680 }, { "epoch": 21.29, "learning_rate": 8.498218389639439e-05, "loss": 0.1098, "step": 88690 }, { "epoch": 21.29, "learning_rate": 8.497897785601567e-05, "loss": 0.0621, "step": 88700 }, { "epoch": 21.29, "learning_rate": 8.497577153394642e-05, "loss": 0.0644, "step": 88710 }, { "epoch": 21.3, "learning_rate": 8.497256493021246e-05, "loss": 0.1275, "step": 88720 }, { "epoch": 21.3, "learning_rate": 8.496935804483959e-05, "loss": 0.0839, "step": 88730 }, { "epoch": 21.3, "learning_rate": 8.496615087785367e-05, "loss": 0.1313, "step": 88740 }, { "epoch": 21.3, "learning_rate": 8.496294342928049e-05, "loss": 0.0914, "step": 88750 }, { "epoch": 21.31, "learning_rate": 8.495973569914593e-05, "loss": 0.0981, "step": 88760 }, { "epoch": 21.31, "learning_rate": 8.495652768747576e-05, "loss": 0.0852, "step": 88770 }, { "epoch": 21.31, "learning_rate": 8.495331939429587e-05, "loss": 0.0958, "step": 88780 }, { "epoch": 21.31, "learning_rate": 8.495011081963205e-05, "loss": 0.074, "step": 88790 }, { "epoch": 21.31, "learning_rate": 8.494690196351018e-05, "loss": 0.0767, "step": 88800 }, { "epoch": 21.32, "learning_rate": 8.494369282595609e-05, "loss": 0.0684, "step": 88810 }, { "epoch": 21.32, "learning_rate": 8.49404834069956e-05, "loss": 0.1196, "step": 88820 }, { "epoch": 21.32, "learning_rate": 8.493727370665458e-05, "loss": 0.079, "step": 88830 }, { "epoch": 21.32, "learning_rate": 8.493406372495887e-05, "loss": 0.1004, "step": 88840 }, { "epoch": 21.33, "learning_rate": 8.493085346193432e-05, "loss": 0.107, "step": 88850 }, { "epoch": 21.33, "learning_rate": 8.49276429176068e-05, "loss": 0.0883, "step": 88860 }, { "epoch": 21.33, "learning_rate": 8.492443209200213e-05, "loss": 0.0721, "step": 88870 }, { "epoch": 21.33, "learning_rate": 8.492122098514619e-05, "loss": 0.0832, "step": 88880 }, { "epoch": 21.34, "learning_rate": 8.491800959706484e-05, "loss": 0.0752, "step": 88890 }, { "epoch": 21.34, "learning_rate": 8.491479792778394e-05, "loss": 0.061, "step": 88900 }, { "epoch": 21.34, "learning_rate": 8.491158597732935e-05, "loss": 0.1062, "step": 88910 }, { "epoch": 21.34, "learning_rate": 8.490837374572693e-05, "loss": 0.1083, "step": 88920 }, { "epoch": 21.34, "learning_rate": 8.490516123300259e-05, "loss": 0.1214, "step": 88930 }, { "epoch": 21.35, "learning_rate": 8.490194843918214e-05, "loss": 0.0775, "step": 88940 }, { "epoch": 21.35, "learning_rate": 8.489873536429147e-05, "loss": 0.0847, "step": 88950 }, { "epoch": 21.35, "learning_rate": 8.489552200835648e-05, "loss": 0.0868, "step": 88960 }, { "epoch": 21.35, "learning_rate": 8.489230837140302e-05, "loss": 0.0606, "step": 88970 }, { "epoch": 21.36, "learning_rate": 8.488909445345701e-05, "loss": 0.097, "step": 88980 }, { "epoch": 21.36, "learning_rate": 8.488588025454429e-05, "loss": 0.0694, "step": 88990 }, { "epoch": 21.36, "learning_rate": 8.488266577469077e-05, "loss": 0.105, "step": 89000 }, { "epoch": 21.36, "learning_rate": 8.487945101392232e-05, "loss": 0.1061, "step": 89010 }, { "epoch": 21.36, "learning_rate": 8.487623597226485e-05, "loss": 0.1085, "step": 89020 }, { "epoch": 21.37, "learning_rate": 8.48730206497442e-05, "loss": 0.0693, "step": 89030 }, { "epoch": 21.37, "learning_rate": 8.486980504638633e-05, "loss": 0.1039, "step": 89040 }, { "epoch": 21.37, "learning_rate": 8.48665891622171e-05, "loss": 0.0883, "step": 89050 }, { "epoch": 21.37, "learning_rate": 8.486337299726241e-05, "loss": 0.0834, "step": 89060 }, { "epoch": 21.38, "learning_rate": 8.486015655154817e-05, "loss": 0.0565, "step": 89070 }, { "epoch": 21.38, "learning_rate": 8.485693982510026e-05, "loss": 0.0771, "step": 89080 }, { "epoch": 21.38, "learning_rate": 8.485372281794461e-05, "loss": 0.0825, "step": 89090 }, { "epoch": 21.38, "learning_rate": 8.485050553010713e-05, "loss": 0.1097, "step": 89100 }, { "epoch": 21.39, "learning_rate": 8.484728796161371e-05, "loss": 0.0819, "step": 89110 }, { "epoch": 21.39, "learning_rate": 8.484407011249027e-05, "loss": 0.0882, "step": 89120 }, { "epoch": 21.39, "learning_rate": 8.484085198276271e-05, "loss": 0.0806, "step": 89130 }, { "epoch": 21.39, "learning_rate": 8.483763357245698e-05, "loss": 0.0976, "step": 89140 }, { "epoch": 21.39, "learning_rate": 8.483441488159897e-05, "loss": 0.1018, "step": 89150 }, { "epoch": 21.4, "learning_rate": 8.483119591021461e-05, "loss": 0.0881, "step": 89160 }, { "epoch": 21.4, "learning_rate": 8.48279766583298e-05, "loss": 0.103, "step": 89170 }, { "epoch": 21.4, "learning_rate": 8.48247571259705e-05, "loss": 0.0878, "step": 89180 }, { "epoch": 21.4, "learning_rate": 8.482153731316262e-05, "loss": 0.0902, "step": 89190 }, { "epoch": 21.41, "learning_rate": 8.481831721993211e-05, "loss": 0.0944, "step": 89200 }, { "epoch": 21.41, "learning_rate": 8.481509684630488e-05, "loss": 0.0895, "step": 89210 }, { "epoch": 21.41, "learning_rate": 8.481187619230684e-05, "loss": 0.1298, "step": 89220 }, { "epoch": 21.41, "learning_rate": 8.4808655257964e-05, "loss": 0.0891, "step": 89230 }, { "epoch": 21.42, "learning_rate": 8.480543404330221e-05, "loss": 0.0944, "step": 89240 }, { "epoch": 21.42, "learning_rate": 8.480221254834749e-05, "loss": 0.0845, "step": 89250 }, { "epoch": 21.42, "learning_rate": 8.479899077312572e-05, "loss": 0.0738, "step": 89260 }, { "epoch": 21.42, "learning_rate": 8.479576871766288e-05, "loss": 0.0694, "step": 89270 }, { "epoch": 21.42, "learning_rate": 8.479254638198493e-05, "loss": 0.0744, "step": 89280 }, { "epoch": 21.43, "learning_rate": 8.478932376611776e-05, "loss": 0.0676, "step": 89290 }, { "epoch": 21.43, "learning_rate": 8.47861008700874e-05, "loss": 0.1284, "step": 89300 }, { "epoch": 21.43, "learning_rate": 8.478287769391974e-05, "loss": 0.0879, "step": 89310 }, { "epoch": 21.43, "learning_rate": 8.477965423764078e-05, "loss": 0.0715, "step": 89320 }, { "epoch": 21.44, "learning_rate": 8.477643050127649e-05, "loss": 0.0862, "step": 89330 }, { "epoch": 21.44, "learning_rate": 8.477320648485276e-05, "loss": 0.0703, "step": 89340 }, { "epoch": 21.44, "learning_rate": 8.476998218839563e-05, "loss": 0.0802, "step": 89350 }, { "epoch": 21.44, "learning_rate": 8.4766757611931e-05, "loss": 0.0895, "step": 89360 }, { "epoch": 21.44, "learning_rate": 8.476353275548488e-05, "loss": 0.0799, "step": 89370 }, { "epoch": 21.45, "learning_rate": 8.476030761908325e-05, "loss": 0.115, "step": 89380 }, { "epoch": 21.45, "learning_rate": 8.475708220275205e-05, "loss": 0.0895, "step": 89390 }, { "epoch": 21.45, "learning_rate": 8.475385650651727e-05, "loss": 0.0775, "step": 89400 }, { "epoch": 21.45, "learning_rate": 8.475063053040488e-05, "loss": 0.1092, "step": 89410 }, { "epoch": 21.46, "learning_rate": 8.474740427444088e-05, "loss": 0.085, "step": 89420 }, { "epoch": 21.46, "learning_rate": 8.474417773865122e-05, "loss": 0.128, "step": 89430 }, { "epoch": 21.46, "learning_rate": 8.474095092306191e-05, "loss": 0.1027, "step": 89440 }, { "epoch": 21.46, "learning_rate": 8.473772382769892e-05, "loss": 0.0789, "step": 89450 }, { "epoch": 21.47, "learning_rate": 8.473449645258825e-05, "loss": 0.0708, "step": 89460 }, { "epoch": 21.47, "learning_rate": 8.473126879775588e-05, "loss": 0.0713, "step": 89470 }, { "epoch": 21.47, "learning_rate": 8.47280408632278e-05, "loss": 0.0723, "step": 89480 }, { "epoch": 21.47, "learning_rate": 8.472481264903003e-05, "loss": 0.0734, "step": 89490 }, { "epoch": 21.47, "learning_rate": 8.472158415518854e-05, "loss": 0.0575, "step": 89500 }, { "epoch": 21.48, "learning_rate": 8.471835538172935e-05, "loss": 0.1151, "step": 89510 }, { "epoch": 21.48, "learning_rate": 8.471512632867844e-05, "loss": 0.0962, "step": 89520 }, { "epoch": 21.48, "learning_rate": 8.471189699606183e-05, "loss": 0.0616, "step": 89530 }, { "epoch": 21.48, "learning_rate": 8.470866738390551e-05, "loss": 0.0877, "step": 89540 }, { "epoch": 21.49, "learning_rate": 8.470543749223551e-05, "loss": 0.0707, "step": 89550 }, { "epoch": 21.49, "learning_rate": 8.470220732107783e-05, "loss": 0.1011, "step": 89560 }, { "epoch": 21.49, "learning_rate": 8.469897687045847e-05, "loss": 0.0728, "step": 89570 }, { "epoch": 21.49, "learning_rate": 8.469574614040348e-05, "loss": 0.0765, "step": 89580 }, { "epoch": 21.5, "learning_rate": 8.469251513093885e-05, "loss": 0.0703, "step": 89590 }, { "epoch": 21.5, "learning_rate": 8.46892838420906e-05, "loss": 0.089, "step": 89600 }, { "epoch": 21.5, "learning_rate": 8.468605227388475e-05, "loss": 0.0763, "step": 89610 }, { "epoch": 21.5, "learning_rate": 8.468282042634734e-05, "loss": 0.0851, "step": 89620 }, { "epoch": 21.5, "learning_rate": 8.46795882995044e-05, "loss": 0.0812, "step": 89630 }, { "epoch": 21.51, "learning_rate": 8.467635589338194e-05, "loss": 0.0782, "step": 89640 }, { "epoch": 21.51, "learning_rate": 8.4673123208006e-05, "loss": 0.0659, "step": 89650 }, { "epoch": 21.51, "learning_rate": 8.466989024340262e-05, "loss": 0.097, "step": 89660 }, { "epoch": 21.51, "learning_rate": 8.466665699959781e-05, "loss": 0.076, "step": 89670 }, { "epoch": 21.52, "learning_rate": 8.466342347661764e-05, "loss": 0.086, "step": 89680 }, { "epoch": 21.52, "learning_rate": 8.466018967448812e-05, "loss": 0.1125, "step": 89690 }, { "epoch": 21.52, "learning_rate": 8.465695559323532e-05, "loss": 0.0836, "step": 89700 }, { "epoch": 21.52, "learning_rate": 8.465372123288527e-05, "loss": 0.1856, "step": 89710 }, { "epoch": 21.52, "learning_rate": 8.465048659346399e-05, "loss": 0.0654, "step": 89720 }, { "epoch": 21.53, "learning_rate": 8.464725167499759e-05, "loss": 0.0807, "step": 89730 }, { "epoch": 21.53, "learning_rate": 8.464401647751209e-05, "loss": 0.1112, "step": 89740 }, { "epoch": 21.53, "learning_rate": 8.464078100103354e-05, "loss": 0.1028, "step": 89750 }, { "epoch": 21.53, "learning_rate": 8.463754524558797e-05, "loss": 0.1303, "step": 89760 }, { "epoch": 21.54, "learning_rate": 8.46343092112015e-05, "loss": 0.1132, "step": 89770 }, { "epoch": 21.54, "learning_rate": 8.463107289790016e-05, "loss": 0.1225, "step": 89780 }, { "epoch": 21.54, "learning_rate": 8.462783630570999e-05, "loss": 0.1651, "step": 89790 }, { "epoch": 21.54, "learning_rate": 8.462459943465708e-05, "loss": 0.1419, "step": 89800 }, { "epoch": 21.55, "learning_rate": 8.462136228476748e-05, "loss": 0.142, "step": 89810 }, { "epoch": 21.55, "learning_rate": 8.461812485606728e-05, "loss": 0.1485, "step": 89820 }, { "epoch": 21.55, "learning_rate": 8.461488714858254e-05, "loss": 0.1051, "step": 89830 }, { "epoch": 21.55, "learning_rate": 8.461164916233933e-05, "loss": 0.1547, "step": 89840 }, { "epoch": 21.55, "learning_rate": 8.460841089736373e-05, "loss": 0.1117, "step": 89850 }, { "epoch": 21.56, "learning_rate": 8.460517235368183e-05, "loss": 0.0963, "step": 89860 }, { "epoch": 21.56, "learning_rate": 8.460193353131968e-05, "loss": 0.1283, "step": 89870 }, { "epoch": 21.56, "learning_rate": 8.459869443030341e-05, "loss": 0.1481, "step": 89880 }, { "epoch": 21.56, "learning_rate": 8.459545505065907e-05, "loss": 0.1564, "step": 89890 }, { "epoch": 21.57, "learning_rate": 8.459221539241275e-05, "loss": 0.1097, "step": 89900 }, { "epoch": 21.57, "learning_rate": 8.458897545559053e-05, "loss": 0.1063, "step": 89910 }, { "epoch": 21.57, "learning_rate": 8.458573524021854e-05, "loss": 0.1385, "step": 89920 }, { "epoch": 21.57, "learning_rate": 8.458249474632283e-05, "loss": 0.0919, "step": 89930 }, { "epoch": 21.58, "learning_rate": 8.457925397392951e-05, "loss": 0.1145, "step": 89940 }, { "epoch": 21.58, "learning_rate": 8.45760129230647e-05, "loss": 0.1391, "step": 89950 }, { "epoch": 21.58, "learning_rate": 8.457277159375447e-05, "loss": 0.1071, "step": 89960 }, { "epoch": 21.58, "learning_rate": 8.456952998602494e-05, "loss": 0.1, "step": 89970 }, { "epoch": 21.58, "learning_rate": 8.456628809990223e-05, "loss": 0.1206, "step": 89980 }, { "epoch": 21.59, "learning_rate": 8.456304593541243e-05, "loss": 0.1315, "step": 89990 }, { "epoch": 21.59, "learning_rate": 8.455980349258162e-05, "loss": 0.0934, "step": 90000 }, { "epoch": 21.59, "learning_rate": 8.455656077143597e-05, "loss": 0.1127, "step": 90010 }, { "epoch": 21.59, "learning_rate": 8.455331777200154e-05, "loss": 0.136, "step": 90020 }, { "epoch": 21.6, "learning_rate": 8.45500744943045e-05, "loss": 0.1243, "step": 90030 }, { "epoch": 21.6, "learning_rate": 8.454683093837093e-05, "loss": 0.1421, "step": 90040 }, { "epoch": 21.6, "learning_rate": 8.454358710422694e-05, "loss": 0.1214, "step": 90050 }, { "epoch": 21.6, "learning_rate": 8.45403429918987e-05, "loss": 0.1168, "step": 90060 }, { "epoch": 21.6, "learning_rate": 8.453709860141231e-05, "loss": 0.1063, "step": 90070 }, { "epoch": 21.61, "learning_rate": 8.453385393279387e-05, "loss": 0.1085, "step": 90080 }, { "epoch": 21.61, "learning_rate": 8.453060898606956e-05, "loss": 0.0964, "step": 90090 }, { "epoch": 21.61, "learning_rate": 8.452736376126548e-05, "loss": 0.1128, "step": 90100 }, { "epoch": 21.61, "learning_rate": 8.452411825840778e-05, "loss": 0.109, "step": 90110 }, { "epoch": 21.62, "learning_rate": 8.452087247752259e-05, "loss": 0.1091, "step": 90120 }, { "epoch": 21.62, "learning_rate": 8.451762641863603e-05, "loss": 0.0836, "step": 90130 }, { "epoch": 21.62, "learning_rate": 8.451438008177428e-05, "loss": 0.119, "step": 90140 }, { "epoch": 21.62, "learning_rate": 8.451113346696344e-05, "loss": 0.0862, "step": 90150 }, { "epoch": 21.63, "learning_rate": 8.45078865742297e-05, "loss": 0.0867, "step": 90160 }, { "epoch": 21.63, "learning_rate": 8.450463940359918e-05, "loss": 0.0786, "step": 90170 }, { "epoch": 21.63, "learning_rate": 8.450139195509803e-05, "loss": 0.0997, "step": 90180 }, { "epoch": 21.63, "learning_rate": 8.449814422875241e-05, "loss": 0.1267, "step": 90190 }, { "epoch": 21.63, "learning_rate": 8.449489622458847e-05, "loss": 0.123, "step": 90200 }, { "epoch": 21.64, "learning_rate": 8.449164794263237e-05, "loss": 0.0873, "step": 90210 }, { "epoch": 21.64, "learning_rate": 8.448839938291027e-05, "loss": 0.1367, "step": 90220 }, { "epoch": 21.64, "learning_rate": 8.448515054544832e-05, "loss": 0.1003, "step": 90230 }, { "epoch": 21.64, "learning_rate": 8.448190143027269e-05, "loss": 0.0895, "step": 90240 }, { "epoch": 21.65, "learning_rate": 8.447865203740957e-05, "loss": 0.1069, "step": 90250 }, { "epoch": 21.65, "learning_rate": 8.447540236688507e-05, "loss": 0.0972, "step": 90260 }, { "epoch": 21.65, "learning_rate": 8.447215241872543e-05, "loss": 0.1199, "step": 90270 }, { "epoch": 21.65, "learning_rate": 8.446890219295675e-05, "loss": 0.115, "step": 90280 }, { "epoch": 21.66, "learning_rate": 8.446565168960527e-05, "loss": 0.1357, "step": 90290 }, { "epoch": 21.66, "learning_rate": 8.446240090869714e-05, "loss": 0.0985, "step": 90300 }, { "epoch": 21.66, "learning_rate": 8.445914985025853e-05, "loss": 0.104, "step": 90310 }, { "epoch": 21.66, "learning_rate": 8.445589851431563e-05, "loss": 0.1397, "step": 90320 }, { "epoch": 21.66, "learning_rate": 8.445264690089461e-05, "loss": 0.1401, "step": 90330 }, { "epoch": 21.67, "learning_rate": 8.44493950100217e-05, "loss": 0.0711, "step": 90340 }, { "epoch": 21.67, "learning_rate": 8.444614284172303e-05, "loss": 0.1437, "step": 90350 }, { "epoch": 21.67, "learning_rate": 8.44428903960248e-05, "loss": 0.0921, "step": 90360 }, { "epoch": 21.67, "learning_rate": 8.443963767295325e-05, "loss": 0.1381, "step": 90370 }, { "epoch": 21.68, "learning_rate": 8.443638467253454e-05, "loss": 0.1072, "step": 90380 }, { "epoch": 21.68, "learning_rate": 8.443313139479485e-05, "loss": 0.0702, "step": 90390 }, { "epoch": 21.68, "learning_rate": 8.442987783976042e-05, "loss": 0.1143, "step": 90400 }, { "epoch": 21.68, "learning_rate": 8.442662400745742e-05, "loss": 0.0732, "step": 90410 }, { "epoch": 21.68, "learning_rate": 8.442336989791207e-05, "loss": 0.0964, "step": 90420 }, { "epoch": 21.69, "learning_rate": 8.442011551115057e-05, "loss": 0.1155, "step": 90430 }, { "epoch": 21.69, "learning_rate": 8.441686084719912e-05, "loss": 0.1048, "step": 90440 }, { "epoch": 21.69, "learning_rate": 8.441360590608394e-05, "loss": 0.1059, "step": 90450 }, { "epoch": 21.69, "learning_rate": 8.441035068783125e-05, "loss": 0.119, "step": 90460 }, { "epoch": 21.7, "learning_rate": 8.440709519246724e-05, "loss": 0.0788, "step": 90470 }, { "epoch": 21.7, "learning_rate": 8.440383942001815e-05, "loss": 0.0981, "step": 90480 }, { "epoch": 21.7, "learning_rate": 8.440058337051019e-05, "loss": 0.1087, "step": 90490 }, { "epoch": 21.7, "learning_rate": 8.439732704396958e-05, "loss": 0.1303, "step": 90500 }, { "epoch": 21.71, "learning_rate": 8.439407044042256e-05, "loss": 0.0929, "step": 90510 }, { "epoch": 21.71, "learning_rate": 8.439081355989532e-05, "loss": 0.0764, "step": 90520 }, { "epoch": 21.71, "learning_rate": 8.438755640241414e-05, "loss": 0.079, "step": 90530 }, { "epoch": 21.71, "learning_rate": 8.438429896800519e-05, "loss": 0.1096, "step": 90540 }, { "epoch": 21.71, "learning_rate": 8.438104125669475e-05, "loss": 0.1038, "step": 90550 }, { "epoch": 21.72, "learning_rate": 8.437778326850903e-05, "loss": 0.0883, "step": 90560 }, { "epoch": 21.72, "learning_rate": 8.437452500347429e-05, "loss": 0.1161, "step": 90570 }, { "epoch": 21.72, "learning_rate": 8.437126646161675e-05, "loss": 0.0965, "step": 90580 }, { "epoch": 21.72, "learning_rate": 8.436800764296264e-05, "loss": 0.1224, "step": 90590 }, { "epoch": 21.73, "learning_rate": 8.436474854753824e-05, "loss": 0.088, "step": 90600 }, { "epoch": 21.73, "learning_rate": 8.436148917536975e-05, "loss": 0.0812, "step": 90610 }, { "epoch": 21.73, "learning_rate": 8.435822952648347e-05, "loss": 0.1586, "step": 90620 }, { "epoch": 21.73, "learning_rate": 8.435496960090561e-05, "loss": 0.1162, "step": 90630 }, { "epoch": 21.74, "learning_rate": 8.435170939866243e-05, "loss": 0.1022, "step": 90640 }, { "epoch": 21.74, "learning_rate": 8.434844891978021e-05, "loss": 0.1012, "step": 90650 }, { "epoch": 21.74, "learning_rate": 8.434518816428518e-05, "loss": 0.1127, "step": 90660 }, { "epoch": 21.74, "learning_rate": 8.434192713220362e-05, "loss": 0.1044, "step": 90670 }, { "epoch": 21.74, "learning_rate": 8.433866582356176e-05, "loss": 0.092, "step": 90680 }, { "epoch": 21.75, "learning_rate": 8.43354042383859e-05, "loss": 0.0927, "step": 90690 }, { "epoch": 21.75, "learning_rate": 8.433214237670228e-05, "loss": 0.0708, "step": 90700 }, { "epoch": 21.75, "learning_rate": 8.432888023853718e-05, "loss": 0.1147, "step": 90710 }, { "epoch": 21.75, "learning_rate": 8.432561782391687e-05, "loss": 0.112, "step": 90720 }, { "epoch": 21.76, "learning_rate": 8.432235513286761e-05, "loss": 0.1295, "step": 90730 }, { "epoch": 21.76, "learning_rate": 8.431909216541571e-05, "loss": 0.1196, "step": 90740 }, { "epoch": 21.76, "learning_rate": 8.43158289215874e-05, "loss": 0.1263, "step": 90750 }, { "epoch": 21.76, "learning_rate": 8.431256540140899e-05, "loss": 0.0718, "step": 90760 }, { "epoch": 21.76, "learning_rate": 8.430930160490675e-05, "loss": 0.1272, "step": 90770 }, { "epoch": 21.77, "learning_rate": 8.430603753210697e-05, "loss": 0.0953, "step": 90780 }, { "epoch": 21.77, "learning_rate": 8.430277318303594e-05, "loss": 0.1145, "step": 90790 }, { "epoch": 21.77, "learning_rate": 8.429950855771993e-05, "loss": 0.079, "step": 90800 }, { "epoch": 21.77, "learning_rate": 8.429624365618524e-05, "loss": 0.0969, "step": 90810 }, { "epoch": 21.78, "learning_rate": 8.429297847845818e-05, "loss": 0.0903, "step": 90820 }, { "epoch": 21.78, "learning_rate": 8.428971302456502e-05, "loss": 0.1284, "step": 90830 }, { "epoch": 21.78, "learning_rate": 8.428644729453207e-05, "loss": 0.0938, "step": 90840 }, { "epoch": 21.78, "learning_rate": 8.428318128838561e-05, "loss": 0.0947, "step": 90850 }, { "epoch": 21.79, "learning_rate": 8.4279915006152e-05, "loss": 0.0746, "step": 90860 }, { "epoch": 21.79, "learning_rate": 8.427664844785747e-05, "loss": 0.1016, "step": 90870 }, { "epoch": 21.79, "learning_rate": 8.427338161352836e-05, "loss": 0.1297, "step": 90880 }, { "epoch": 21.79, "learning_rate": 8.427011450319098e-05, "loss": 0.0819, "step": 90890 }, { "epoch": 21.79, "learning_rate": 8.426684711687163e-05, "loss": 0.0923, "step": 90900 }, { "epoch": 21.8, "learning_rate": 8.426357945459664e-05, "loss": 0.0849, "step": 90910 }, { "epoch": 21.8, "learning_rate": 8.426031151639231e-05, "loss": 0.0967, "step": 90920 }, { "epoch": 21.8, "learning_rate": 8.425704330228497e-05, "loss": 0.1254, "step": 90930 }, { "epoch": 21.8, "learning_rate": 8.42537748123009e-05, "loss": 0.1103, "step": 90940 }, { "epoch": 21.81, "learning_rate": 8.425050604646648e-05, "loss": 0.0914, "step": 90950 }, { "epoch": 21.81, "learning_rate": 8.424723700480801e-05, "loss": 0.0803, "step": 90960 }, { "epoch": 21.81, "learning_rate": 8.42439676873518e-05, "loss": 0.067, "step": 90970 }, { "epoch": 21.81, "learning_rate": 8.42406980941242e-05, "loss": 0.1097, "step": 90980 }, { "epoch": 21.82, "learning_rate": 8.423742822515152e-05, "loss": 0.1029, "step": 90990 }, { "epoch": 21.82, "learning_rate": 8.42341580804601e-05, "loss": 0.1243, "step": 91000 }, { "epoch": 21.82, "learning_rate": 8.42308876600763e-05, "loss": 0.091, "step": 91010 }, { "epoch": 21.82, "learning_rate": 8.422761696402641e-05, "loss": 0.0779, "step": 91020 }, { "epoch": 21.82, "learning_rate": 8.422434599233682e-05, "loss": 0.1045, "step": 91030 }, { "epoch": 21.83, "learning_rate": 8.422107474503382e-05, "loss": 0.0945, "step": 91040 }, { "epoch": 21.83, "learning_rate": 8.421780322214381e-05, "loss": 0.0863, "step": 91050 }, { "epoch": 21.83, "learning_rate": 8.421453142369309e-05, "loss": 0.0954, "step": 91060 }, { "epoch": 21.83, "learning_rate": 8.421125934970802e-05, "loss": 0.0992, "step": 91070 }, { "epoch": 21.84, "learning_rate": 8.420798700021496e-05, "loss": 0.0702, "step": 91080 }, { "epoch": 21.84, "learning_rate": 8.420471437524026e-05, "loss": 0.0829, "step": 91090 }, { "epoch": 21.84, "learning_rate": 8.420144147481028e-05, "loss": 0.0771, "step": 91100 }, { "epoch": 21.84, "learning_rate": 8.419816829895135e-05, "loss": 0.1027, "step": 91110 }, { "epoch": 21.84, "learning_rate": 8.419489484768987e-05, "loss": 0.0737, "step": 91120 }, { "epoch": 21.85, "learning_rate": 8.419162112105217e-05, "loss": 0.1286, "step": 91130 }, { "epoch": 21.85, "learning_rate": 8.418834711906463e-05, "loss": 0.0854, "step": 91140 }, { "epoch": 21.85, "learning_rate": 8.41850728417536e-05, "loss": 0.1117, "step": 91150 }, { "epoch": 21.85, "learning_rate": 8.418179828914548e-05, "loss": 0.0711, "step": 91160 }, { "epoch": 21.86, "learning_rate": 8.41785234612666e-05, "loss": 0.1149, "step": 91170 }, { "epoch": 21.86, "learning_rate": 8.417524835814336e-05, "loss": 0.0727, "step": 91180 }, { "epoch": 21.86, "learning_rate": 8.417197297980213e-05, "loss": 0.0828, "step": 91190 }, { "epoch": 21.86, "learning_rate": 8.416869732626928e-05, "loss": 0.0952, "step": 91200 }, { "epoch": 21.87, "learning_rate": 8.41654213975712e-05, "loss": 0.1181, "step": 91210 }, { "epoch": 21.87, "learning_rate": 8.416214519373424e-05, "loss": 0.0991, "step": 91220 }, { "epoch": 21.87, "learning_rate": 8.415886871478482e-05, "loss": 0.099, "step": 91230 }, { "epoch": 21.87, "learning_rate": 8.415559196074932e-05, "loss": 0.1022, "step": 91240 }, { "epoch": 21.87, "learning_rate": 8.415231493165412e-05, "loss": 0.0699, "step": 91250 }, { "epoch": 21.88, "learning_rate": 8.414903762752563e-05, "loss": 0.075, "step": 91260 }, { "epoch": 21.88, "learning_rate": 8.41457600483902e-05, "loss": 0.0993, "step": 91270 }, { "epoch": 21.88, "learning_rate": 8.414248219427426e-05, "loss": 0.0947, "step": 91280 }, { "epoch": 21.88, "learning_rate": 8.41392040652042e-05, "loss": 0.1018, "step": 91290 }, { "epoch": 21.89, "learning_rate": 8.413592566120641e-05, "loss": 0.1183, "step": 91300 }, { "epoch": 21.89, "learning_rate": 8.413264698230731e-05, "loss": 0.1005, "step": 91310 }, { "epoch": 21.89, "learning_rate": 8.412936802853329e-05, "loss": 0.1072, "step": 91320 }, { "epoch": 21.89, "learning_rate": 8.412608879991076e-05, "loss": 0.0809, "step": 91330 }, { "epoch": 21.9, "learning_rate": 8.41228092964661e-05, "loss": 0.0958, "step": 91340 }, { "epoch": 21.9, "learning_rate": 8.411952951822576e-05, "loss": 0.0814, "step": 91350 }, { "epoch": 21.9, "learning_rate": 8.411624946521615e-05, "loss": 0.0708, "step": 91360 }, { "epoch": 21.9, "learning_rate": 8.411296913746365e-05, "loss": 0.0689, "step": 91370 }, { "epoch": 21.9, "learning_rate": 8.410968853499473e-05, "loss": 0.081, "step": 91380 }, { "epoch": 21.91, "learning_rate": 8.410640765783575e-05, "loss": 0.0814, "step": 91390 }, { "epoch": 21.91, "learning_rate": 8.410312650601318e-05, "loss": 0.1023, "step": 91400 }, { "epoch": 21.91, "learning_rate": 8.409984507955342e-05, "loss": 0.0992, "step": 91410 }, { "epoch": 21.91, "learning_rate": 8.409656337848288e-05, "loss": 0.1191, "step": 91420 }, { "epoch": 21.92, "learning_rate": 8.409328140282804e-05, "loss": 0.1148, "step": 91430 }, { "epoch": 21.92, "learning_rate": 8.408999915261527e-05, "loss": 0.0704, "step": 91440 }, { "epoch": 21.92, "learning_rate": 8.408671662787105e-05, "loss": 0.1423, "step": 91450 }, { "epoch": 21.92, "learning_rate": 8.408343382862178e-05, "loss": 0.0967, "step": 91460 }, { "epoch": 21.92, "learning_rate": 8.408015075489393e-05, "loss": 0.0672, "step": 91470 }, { "epoch": 21.93, "learning_rate": 8.40768674067139e-05, "loss": 0.0946, "step": 91480 }, { "epoch": 21.93, "learning_rate": 8.407358378410816e-05, "loss": 0.1526, "step": 91490 }, { "epoch": 21.93, "learning_rate": 8.407029988710316e-05, "loss": 0.1259, "step": 91500 }, { "epoch": 21.93, "learning_rate": 8.406701571572532e-05, "loss": 0.0968, "step": 91510 }, { "epoch": 21.94, "learning_rate": 8.40637312700011e-05, "loss": 0.1068, "step": 91520 }, { "epoch": 21.94, "learning_rate": 8.406044654995696e-05, "loss": 0.1331, "step": 91530 }, { "epoch": 21.94, "learning_rate": 8.405716155561932e-05, "loss": 0.1189, "step": 91540 }, { "epoch": 21.94, "learning_rate": 8.405387628701466e-05, "loss": 0.1441, "step": 91550 }, { "epoch": 21.95, "learning_rate": 8.405059074416944e-05, "loss": 0.0851, "step": 91560 }, { "epoch": 21.95, "learning_rate": 8.404730492711011e-05, "loss": 0.0688, "step": 91570 }, { "epoch": 21.95, "learning_rate": 8.404401883586314e-05, "loss": 0.0982, "step": 91580 }, { "epoch": 22.0, "learning_rate": 8.404073247045499e-05, "loss": 0.1087, "step": 91590 }, { "epoch": 22.0, "learning_rate": 8.40374458309121e-05, "loss": 0.1385, "step": 91600 }, { "epoch": 22.01, "learning_rate": 8.403415891726096e-05, "loss": 0.0755, "step": 91610 }, { "epoch": 22.01, "learning_rate": 8.403087172952806e-05, "loss": 0.1055, "step": 91620 }, { "epoch": 22.01, "learning_rate": 8.402758426773985e-05, "loss": 0.0774, "step": 91630 }, { "epoch": 22.01, "learning_rate": 8.40242965319228e-05, "loss": 0.0836, "step": 91640 }, { "epoch": 22.01, "learning_rate": 8.402100852210338e-05, "loss": 0.0799, "step": 91650 }, { "epoch": 22.02, "learning_rate": 8.40177202383081e-05, "loss": 0.0818, "step": 91660 }, { "epoch": 22.02, "learning_rate": 8.40144316805634e-05, "loss": 0.1043, "step": 91670 }, { "epoch": 22.02, "learning_rate": 8.40111428488958e-05, "loss": 0.1055, "step": 91680 }, { "epoch": 22.02, "learning_rate": 8.400785374333179e-05, "loss": 0.0873, "step": 91690 }, { "epoch": 22.03, "learning_rate": 8.400456436389781e-05, "loss": 0.0758, "step": 91700 }, { "epoch": 22.03, "learning_rate": 8.40012747106204e-05, "loss": 0.0834, "step": 91710 }, { "epoch": 22.03, "learning_rate": 8.399798478352602e-05, "loss": 0.0714, "step": 91720 }, { "epoch": 22.03, "learning_rate": 8.399469458264118e-05, "loss": 0.0757, "step": 91730 }, { "epoch": 22.04, "learning_rate": 8.399140410799235e-05, "loss": 0.0572, "step": 91740 }, { "epoch": 22.04, "learning_rate": 8.398811335960607e-05, "loss": 0.0964, "step": 91750 }, { "epoch": 22.04, "learning_rate": 8.398482233750881e-05, "loss": 0.0654, "step": 91760 }, { "epoch": 22.04, "learning_rate": 8.39815310417271e-05, "loss": 0.0985, "step": 91770 }, { "epoch": 22.04, "learning_rate": 8.397823947228742e-05, "loss": 0.0886, "step": 91780 }, { "epoch": 22.05, "learning_rate": 8.397494762921629e-05, "loss": 0.1065, "step": 91790 }, { "epoch": 22.05, "learning_rate": 8.39716555125402e-05, "loss": 0.1037, "step": 91800 }, { "epoch": 22.05, "learning_rate": 8.396836312228569e-05, "loss": 0.0793, "step": 91810 }, { "epoch": 22.05, "learning_rate": 8.396507045847926e-05, "loss": 0.0985, "step": 91820 }, { "epoch": 22.06, "learning_rate": 8.396177752114745e-05, "loss": 0.113, "step": 91830 }, { "epoch": 22.06, "learning_rate": 8.395848431031672e-05, "loss": 0.0758, "step": 91840 }, { "epoch": 22.06, "learning_rate": 8.395519082601366e-05, "loss": 0.0685, "step": 91850 }, { "epoch": 22.06, "learning_rate": 8.395189706826473e-05, "loss": 0.0632, "step": 91860 }, { "epoch": 22.06, "learning_rate": 8.394860303709651e-05, "loss": 0.0895, "step": 91870 }, { "epoch": 22.07, "learning_rate": 8.39453087325355e-05, "loss": 0.0975, "step": 91880 }, { "epoch": 22.07, "learning_rate": 8.394201415460823e-05, "loss": 0.0724, "step": 91890 }, { "epoch": 22.07, "learning_rate": 8.393871930334122e-05, "loss": 0.1066, "step": 91900 }, { "epoch": 22.07, "learning_rate": 8.393542417876103e-05, "loss": 0.0908, "step": 91910 }, { "epoch": 22.08, "learning_rate": 8.393212878089419e-05, "loss": 0.0965, "step": 91920 }, { "epoch": 22.08, "learning_rate": 8.392883310976722e-05, "loss": 0.1067, "step": 91930 }, { "epoch": 22.08, "learning_rate": 8.392553716540667e-05, "loss": 0.0742, "step": 91940 }, { "epoch": 22.08, "learning_rate": 8.39222409478391e-05, "loss": 0.0846, "step": 91950 }, { "epoch": 22.09, "learning_rate": 8.391894445709103e-05, "loss": 0.0732, "step": 91960 }, { "epoch": 22.09, "learning_rate": 8.391564769318902e-05, "loss": 0.0745, "step": 91970 }, { "epoch": 22.09, "learning_rate": 8.391235065615962e-05, "loss": 0.0769, "step": 91980 }, { "epoch": 22.09, "learning_rate": 8.390905334602939e-05, "loss": 0.0641, "step": 91990 }, { "epoch": 22.09, "learning_rate": 8.390575576282484e-05, "loss": 0.1022, "step": 92000 }, { "epoch": 22.1, "learning_rate": 8.390245790657259e-05, "loss": 0.0834, "step": 92010 }, { "epoch": 22.1, "learning_rate": 8.389915977729914e-05, "loss": 0.108, "step": 92020 }, { "epoch": 22.1, "learning_rate": 8.38958613750311e-05, "loss": 0.1097, "step": 92030 }, { "epoch": 22.1, "learning_rate": 8.389256269979499e-05, "loss": 0.1209, "step": 92040 }, { "epoch": 22.11, "learning_rate": 8.388926375161741e-05, "loss": 0.0858, "step": 92050 }, { "epoch": 22.11, "learning_rate": 8.38859645305249e-05, "loss": 0.0604, "step": 92060 }, { "epoch": 22.11, "learning_rate": 8.388266503654403e-05, "loss": 0.0805, "step": 92070 }, { "epoch": 22.11, "learning_rate": 8.38793652697014e-05, "loss": 0.0843, "step": 92080 }, { "epoch": 22.12, "learning_rate": 8.387606523002355e-05, "loss": 0.0788, "step": 92090 }, { "epoch": 22.12, "learning_rate": 8.387276491753708e-05, "loss": 0.0664, "step": 92100 }, { "epoch": 22.12, "learning_rate": 8.386946433226854e-05, "loss": 0.0851, "step": 92110 }, { "epoch": 22.12, "learning_rate": 8.386616347424454e-05, "loss": 0.0858, "step": 92120 }, { "epoch": 22.12, "learning_rate": 8.386286234349165e-05, "loss": 0.0857, "step": 92130 }, { "epoch": 22.13, "learning_rate": 8.385956094003647e-05, "loss": 0.076, "step": 92140 }, { "epoch": 22.13, "learning_rate": 8.385625926390554e-05, "loss": 0.0773, "step": 92150 }, { "epoch": 22.13, "learning_rate": 8.38529573151255e-05, "loss": 0.0745, "step": 92160 }, { "epoch": 22.13, "learning_rate": 8.384965509372291e-05, "loss": 0.0811, "step": 92170 }, { "epoch": 22.14, "learning_rate": 8.38463525997244e-05, "loss": 0.0955, "step": 92180 }, { "epoch": 22.14, "learning_rate": 8.384304983315651e-05, "loss": 0.0608, "step": 92190 }, { "epoch": 22.14, "learning_rate": 8.383974679404587e-05, "loss": 0.0917, "step": 92200 }, { "epoch": 22.14, "learning_rate": 8.38364434824191e-05, "loss": 0.0927, "step": 92210 }, { "epoch": 22.14, "learning_rate": 8.383313989830275e-05, "loss": 0.0902, "step": 92220 }, { "epoch": 22.15, "learning_rate": 8.382983604172348e-05, "loss": 0.0704, "step": 92230 }, { "epoch": 22.15, "learning_rate": 8.382653191270786e-05, "loss": 0.0775, "step": 92240 }, { "epoch": 22.15, "learning_rate": 8.38232275112825e-05, "loss": 0.0885, "step": 92250 }, { "epoch": 22.15, "learning_rate": 8.381992283747403e-05, "loss": 0.0478, "step": 92260 }, { "epoch": 22.16, "learning_rate": 8.381661789130904e-05, "loss": 0.0938, "step": 92270 }, { "epoch": 22.16, "learning_rate": 8.381331267281417e-05, "loss": 0.0684, "step": 92280 }, { "epoch": 22.16, "learning_rate": 8.381000718201602e-05, "loss": 0.0738, "step": 92290 }, { "epoch": 22.16, "learning_rate": 8.380670141894123e-05, "loss": 0.0909, "step": 92300 }, { "epoch": 22.17, "learning_rate": 8.380339538361637e-05, "loss": 0.0612, "step": 92310 }, { "epoch": 22.17, "learning_rate": 8.380008907606813e-05, "loss": 0.0622, "step": 92320 }, { "epoch": 22.17, "learning_rate": 8.37967824963231e-05, "loss": 0.0995, "step": 92330 }, { "epoch": 22.17, "learning_rate": 8.379347564440791e-05, "loss": 0.1038, "step": 92340 }, { "epoch": 22.17, "learning_rate": 8.37901685203492e-05, "loss": 0.077, "step": 92350 }, { "epoch": 22.18, "learning_rate": 8.378686112417358e-05, "loss": 0.064, "step": 92360 }, { "epoch": 22.18, "learning_rate": 8.378355345590774e-05, "loss": 0.0793, "step": 92370 }, { "epoch": 22.18, "learning_rate": 8.378024551557825e-05, "loss": 0.1014, "step": 92380 }, { "epoch": 22.18, "learning_rate": 8.377693730321179e-05, "loss": 0.1008, "step": 92390 }, { "epoch": 22.19, "learning_rate": 8.377362881883497e-05, "loss": 0.0724, "step": 92400 }, { "epoch": 22.19, "learning_rate": 8.377032006247447e-05, "loss": 0.1063, "step": 92410 }, { "epoch": 22.19, "learning_rate": 8.376701103415695e-05, "loss": 0.0695, "step": 92420 }, { "epoch": 22.19, "learning_rate": 8.376370173390898e-05, "loss": 0.0539, "step": 92430 }, { "epoch": 22.2, "learning_rate": 8.376039216175729e-05, "loss": 0.0722, "step": 92440 }, { "epoch": 22.2, "learning_rate": 8.375708231772847e-05, "loss": 0.0963, "step": 92450 }, { "epoch": 22.2, "learning_rate": 8.375377220184924e-05, "loss": 0.0646, "step": 92460 }, { "epoch": 22.2, "learning_rate": 8.375046181414621e-05, "loss": 0.0578, "step": 92470 }, { "epoch": 22.2, "learning_rate": 8.374715115464605e-05, "loss": 0.0833, "step": 92480 }, { "epoch": 22.21, "learning_rate": 8.374384022337543e-05, "loss": 0.0793, "step": 92490 }, { "epoch": 22.21, "learning_rate": 8.374052902036099e-05, "loss": 0.0875, "step": 92500 }, { "epoch": 22.21, "learning_rate": 8.373721754562942e-05, "loss": 0.0895, "step": 92510 }, { "epoch": 22.21, "learning_rate": 8.373390579920737e-05, "loss": 0.0825, "step": 92520 }, { "epoch": 22.22, "learning_rate": 8.373059378112153e-05, "loss": 0.0901, "step": 92530 }, { "epoch": 22.22, "learning_rate": 8.372728149139857e-05, "loss": 0.0787, "step": 92540 }, { "epoch": 22.22, "learning_rate": 8.372396893006513e-05, "loss": 0.0503, "step": 92550 }, { "epoch": 22.22, "learning_rate": 8.372065609714794e-05, "loss": 0.1232, "step": 92560 }, { "epoch": 22.22, "learning_rate": 8.371734299267364e-05, "loss": 0.1091, "step": 92570 }, { "epoch": 22.23, "learning_rate": 8.371402961666892e-05, "loss": 0.1201, "step": 92580 }, { "epoch": 22.23, "learning_rate": 8.371071596916047e-05, "loss": 0.0706, "step": 92590 }, { "epoch": 22.23, "learning_rate": 8.370740205017495e-05, "loss": 0.0814, "step": 92600 }, { "epoch": 22.23, "learning_rate": 8.37040878597391e-05, "loss": 0.0866, "step": 92610 }, { "epoch": 22.24, "learning_rate": 8.370077339787957e-05, "loss": 0.0724, "step": 92620 }, { "epoch": 22.24, "learning_rate": 8.369745866462304e-05, "loss": 0.0539, "step": 92630 }, { "epoch": 22.24, "learning_rate": 8.369414365999624e-05, "loss": 0.0598, "step": 92640 }, { "epoch": 22.24, "learning_rate": 8.369082838402584e-05, "loss": 0.0747, "step": 92650 }, { "epoch": 22.25, "learning_rate": 8.368751283673854e-05, "loss": 0.0738, "step": 92660 }, { "epoch": 22.25, "learning_rate": 8.368419701816106e-05, "loss": 0.1075, "step": 92670 }, { "epoch": 22.25, "learning_rate": 8.368088092832009e-05, "loss": 0.0927, "step": 92680 }, { "epoch": 22.25, "learning_rate": 8.367756456724234e-05, "loss": 0.0702, "step": 92690 }, { "epoch": 22.25, "learning_rate": 8.367424793495451e-05, "loss": 0.067, "step": 92700 }, { "epoch": 22.26, "learning_rate": 8.367093103148332e-05, "loss": 0.089, "step": 92710 }, { "epoch": 22.26, "learning_rate": 8.366761385685547e-05, "loss": 0.0751, "step": 92720 }, { "epoch": 22.26, "learning_rate": 8.366429641109767e-05, "loss": 0.1008, "step": 92730 }, { "epoch": 22.26, "learning_rate": 8.366097869423664e-05, "loss": 0.0743, "step": 92740 }, { "epoch": 22.27, "learning_rate": 8.36576607062991e-05, "loss": 0.0796, "step": 92750 }, { "epoch": 22.27, "learning_rate": 8.365434244731178e-05, "loss": 0.1093, "step": 92760 }, { "epoch": 22.27, "learning_rate": 8.36510239173014e-05, "loss": 0.0992, "step": 92770 }, { "epoch": 22.27, "learning_rate": 8.364770511629468e-05, "loss": 0.0673, "step": 92780 }, { "epoch": 22.28, "learning_rate": 8.364438604431834e-05, "loss": 0.0657, "step": 92790 }, { "epoch": 22.28, "learning_rate": 8.36410667013991e-05, "loss": 0.0941, "step": 92800 }, { "epoch": 22.28, "learning_rate": 8.363774708756371e-05, "loss": 0.0597, "step": 92810 }, { "epoch": 22.28, "learning_rate": 8.363442720283892e-05, "loss": 0.0667, "step": 92820 }, { "epoch": 22.28, "learning_rate": 8.363110704725142e-05, "loss": 0.0712, "step": 92830 }, { "epoch": 22.29, "learning_rate": 8.362778662082798e-05, "loss": 0.0791, "step": 92840 }, { "epoch": 22.29, "learning_rate": 8.362446592359534e-05, "loss": 0.102, "step": 92850 }, { "epoch": 22.29, "learning_rate": 8.362114495558022e-05, "loss": 0.0707, "step": 92860 }, { "epoch": 22.29, "learning_rate": 8.36178237168094e-05, "loss": 0.0802, "step": 92870 }, { "epoch": 22.3, "learning_rate": 8.361450220730958e-05, "loss": 0.0836, "step": 92880 }, { "epoch": 22.3, "learning_rate": 8.361118042710754e-05, "loss": 0.0767, "step": 92890 }, { "epoch": 22.3, "learning_rate": 8.360785837623001e-05, "loss": 0.075, "step": 92900 }, { "epoch": 22.3, "learning_rate": 8.36045360547038e-05, "loss": 0.071, "step": 92910 }, { "epoch": 22.3, "learning_rate": 8.360121346255559e-05, "loss": 0.0846, "step": 92920 }, { "epoch": 22.31, "learning_rate": 8.359789059981217e-05, "loss": 0.0811, "step": 92930 }, { "epoch": 22.31, "learning_rate": 8.359456746650029e-05, "loss": 0.0738, "step": 92940 }, { "epoch": 22.31, "learning_rate": 8.359124406264674e-05, "loss": 0.0729, "step": 92950 }, { "epoch": 22.31, "learning_rate": 8.358792038827826e-05, "loss": 0.086, "step": 92960 }, { "epoch": 22.32, "learning_rate": 8.358459644342162e-05, "loss": 0.0883, "step": 92970 }, { "epoch": 22.32, "learning_rate": 8.35812722281036e-05, "loss": 0.0794, "step": 92980 }, { "epoch": 22.32, "learning_rate": 8.357794774235092e-05, "loss": 0.0939, "step": 92990 }, { "epoch": 22.32, "learning_rate": 8.357462298619042e-05, "loss": 0.116, "step": 93000 }, { "epoch": 22.33, "learning_rate": 8.357129795964885e-05, "loss": 0.0747, "step": 93010 }, { "epoch": 22.33, "learning_rate": 8.356797266275296e-05, "loss": 0.101, "step": 93020 }, { "epoch": 22.33, "learning_rate": 8.356464709552957e-05, "loss": 0.0567, "step": 93030 }, { "epoch": 22.33, "learning_rate": 8.356132125800545e-05, "loss": 0.1236, "step": 93040 }, { "epoch": 22.33, "learning_rate": 8.355799515020734e-05, "loss": 0.0814, "step": 93050 }, { "epoch": 22.34, "learning_rate": 8.355466877216209e-05, "loss": 0.074, "step": 93060 }, { "epoch": 22.34, "learning_rate": 8.355134212389646e-05, "loss": 0.0864, "step": 93070 }, { "epoch": 22.34, "learning_rate": 8.354801520543724e-05, "loss": 0.0656, "step": 93080 }, { "epoch": 22.34, "learning_rate": 8.35446880168112e-05, "loss": 0.0908, "step": 93090 }, { "epoch": 22.35, "learning_rate": 8.35413605580452e-05, "loss": 0.0785, "step": 93100 }, { "epoch": 22.35, "learning_rate": 8.353803282916595e-05, "loss": 0.0598, "step": 93110 }, { "epoch": 22.35, "learning_rate": 8.353470483020031e-05, "loss": 0.0735, "step": 93120 }, { "epoch": 22.35, "learning_rate": 8.353137656117506e-05, "loss": 0.0559, "step": 93130 }, { "epoch": 22.36, "learning_rate": 8.3528048022117e-05, "loss": 0.0882, "step": 93140 }, { "epoch": 22.36, "learning_rate": 8.352471921305296e-05, "loss": 0.0949, "step": 93150 }, { "epoch": 22.36, "learning_rate": 8.352139013400971e-05, "loss": 0.081, "step": 93160 }, { "epoch": 22.36, "learning_rate": 8.351806078501409e-05, "loss": 0.0865, "step": 93170 }, { "epoch": 22.36, "learning_rate": 8.351473116609287e-05, "loss": 0.0566, "step": 93180 }, { "epoch": 22.37, "learning_rate": 8.351140127727293e-05, "loss": 0.0684, "step": 93190 }, { "epoch": 22.37, "learning_rate": 8.350807111858104e-05, "loss": 0.0946, "step": 93200 }, { "epoch": 22.37, "learning_rate": 8.350474069004401e-05, "loss": 0.1066, "step": 93210 }, { "epoch": 22.37, "learning_rate": 8.35014099916887e-05, "loss": 0.0644, "step": 93220 }, { "epoch": 22.38, "learning_rate": 8.349807902354188e-05, "loss": 0.0628, "step": 93230 }, { "epoch": 22.38, "learning_rate": 8.349474778563042e-05, "loss": 0.0493, "step": 93240 }, { "epoch": 22.38, "learning_rate": 8.349141627798114e-05, "loss": 0.0811, "step": 93250 }, { "epoch": 22.38, "learning_rate": 8.348808450062084e-05, "loss": 0.0778, "step": 93260 }, { "epoch": 22.38, "learning_rate": 8.34847524535764e-05, "loss": 0.0665, "step": 93270 }, { "epoch": 22.39, "learning_rate": 8.348142013687461e-05, "loss": 0.0508, "step": 93280 }, { "epoch": 22.39, "learning_rate": 8.347808755054233e-05, "loss": 0.1169, "step": 93290 }, { "epoch": 22.39, "learning_rate": 8.347475469460638e-05, "loss": 0.0736, "step": 93300 }, { "epoch": 22.39, "learning_rate": 8.347142156909363e-05, "loss": 0.0878, "step": 93310 }, { "epoch": 22.4, "learning_rate": 8.346808817403087e-05, "loss": 0.0659, "step": 93320 }, { "epoch": 22.4, "learning_rate": 8.346475450944499e-05, "loss": 0.064, "step": 93330 }, { "epoch": 22.4, "learning_rate": 8.346142057536282e-05, "loss": 0.0879, "step": 93340 }, { "epoch": 22.4, "learning_rate": 8.34580863718112e-05, "loss": 0.0756, "step": 93350 }, { "epoch": 22.41, "learning_rate": 8.345475189881702e-05, "loss": 0.0553, "step": 93360 }, { "epoch": 22.41, "learning_rate": 8.345141715640707e-05, "loss": 0.0527, "step": 93370 }, { "epoch": 22.41, "learning_rate": 8.344808214460826e-05, "loss": 0.0693, "step": 93380 }, { "epoch": 22.41, "learning_rate": 8.344474686344743e-05, "loss": 0.0706, "step": 93390 }, { "epoch": 22.41, "learning_rate": 8.344141131295142e-05, "loss": 0.0519, "step": 93400 }, { "epoch": 22.42, "learning_rate": 8.343807549314713e-05, "loss": 0.1002, "step": 93410 }, { "epoch": 22.42, "learning_rate": 8.343473940406136e-05, "loss": 0.0775, "step": 93420 }, { "epoch": 22.42, "learning_rate": 8.343140304572107e-05, "loss": 0.0733, "step": 93430 }, { "epoch": 22.42, "learning_rate": 8.342806641815304e-05, "loss": 0.0809, "step": 93440 }, { "epoch": 22.43, "learning_rate": 8.34247295213842e-05, "loss": 0.0767, "step": 93450 }, { "epoch": 22.43, "learning_rate": 8.342139235544138e-05, "loss": 0.0736, "step": 93460 }, { "epoch": 22.43, "learning_rate": 8.341805492035149e-05, "loss": 0.0884, "step": 93470 }, { "epoch": 22.43, "learning_rate": 8.341471721614137e-05, "loss": 0.0816, "step": 93480 }, { "epoch": 22.44, "learning_rate": 8.341137924283793e-05, "loss": 0.0811, "step": 93490 }, { "epoch": 22.44, "learning_rate": 8.340804100046803e-05, "loss": 0.0993, "step": 93500 }, { "epoch": 22.44, "learning_rate": 8.340470248905859e-05, "loss": 0.0835, "step": 93510 }, { "epoch": 22.44, "learning_rate": 8.340136370863643e-05, "loss": 0.0719, "step": 93520 }, { "epoch": 22.44, "learning_rate": 8.33980246592285e-05, "loss": 0.0971, "step": 93530 }, { "epoch": 22.45, "learning_rate": 8.339468534086168e-05, "loss": 0.076, "step": 93540 }, { "epoch": 22.45, "learning_rate": 8.339134575356283e-05, "loss": 0.0739, "step": 93550 }, { "epoch": 22.45, "learning_rate": 8.338800589735886e-05, "loss": 0.0824, "step": 93560 }, { "epoch": 22.45, "learning_rate": 8.338466577227668e-05, "loss": 0.0755, "step": 93570 }, { "epoch": 22.46, "learning_rate": 8.338132537834317e-05, "loss": 0.0664, "step": 93580 }, { "epoch": 22.46, "learning_rate": 8.337798471558525e-05, "loss": 0.0695, "step": 93590 }, { "epoch": 22.46, "learning_rate": 8.33746437840298e-05, "loss": 0.0495, "step": 93600 }, { "epoch": 22.46, "learning_rate": 8.337130258370372e-05, "loss": 0.0662, "step": 93610 }, { "epoch": 22.46, "learning_rate": 8.336796111463397e-05, "loss": 0.1026, "step": 93620 }, { "epoch": 22.47, "learning_rate": 8.336461937684739e-05, "loss": 0.0876, "step": 93630 }, { "epoch": 22.47, "learning_rate": 8.336127737037094e-05, "loss": 0.0794, "step": 93640 }, { "epoch": 22.47, "learning_rate": 8.335793509523151e-05, "loss": 0.0597, "step": 93650 }, { "epoch": 22.47, "learning_rate": 8.335459255145604e-05, "loss": 0.0608, "step": 93660 }, { "epoch": 22.48, "learning_rate": 8.335124973907142e-05, "loss": 0.1008, "step": 93670 }, { "epoch": 22.48, "learning_rate": 8.334790665810456e-05, "loss": 0.0671, "step": 93680 }, { "epoch": 22.48, "learning_rate": 8.334456330858244e-05, "loss": 0.0769, "step": 93690 }, { "epoch": 22.48, "learning_rate": 8.334121969053192e-05, "loss": 0.0582, "step": 93700 }, { "epoch": 22.49, "learning_rate": 8.333787580397998e-05, "loss": 0.0917, "step": 93710 }, { "epoch": 22.49, "learning_rate": 8.333453164895351e-05, "loss": 0.0852, "step": 93720 }, { "epoch": 22.49, "learning_rate": 8.333118722547946e-05, "loss": 0.0807, "step": 93730 }, { "epoch": 22.49, "learning_rate": 8.332784253358474e-05, "loss": 0.1035, "step": 93740 }, { "epoch": 22.49, "learning_rate": 8.332449757329632e-05, "loss": 0.0863, "step": 93750 }, { "epoch": 22.5, "learning_rate": 8.332115234464113e-05, "loss": 0.0832, "step": 93760 }, { "epoch": 22.5, "learning_rate": 8.331780684764607e-05, "loss": 0.0744, "step": 93770 }, { "epoch": 22.5, "learning_rate": 8.331446108233813e-05, "loss": 0.0725, "step": 93780 }, { "epoch": 22.5, "learning_rate": 8.331111504874423e-05, "loss": 0.0988, "step": 93790 }, { "epoch": 22.51, "learning_rate": 8.330776874689132e-05, "loss": 0.0816, "step": 93800 }, { "epoch": 22.51, "learning_rate": 8.330442217680636e-05, "loss": 0.0761, "step": 93810 }, { "epoch": 22.51, "learning_rate": 8.330107533851629e-05, "loss": 0.0636, "step": 93820 }, { "epoch": 22.51, "learning_rate": 8.329772823204805e-05, "loss": 0.0736, "step": 93830 }, { "epoch": 22.52, "learning_rate": 8.329438085742862e-05, "loss": 0.0718, "step": 93840 }, { "epoch": 22.52, "learning_rate": 8.329103321468495e-05, "loss": 0.1115, "step": 93850 }, { "epoch": 22.52, "learning_rate": 8.328768530384398e-05, "loss": 0.1239, "step": 93860 }, { "epoch": 22.52, "learning_rate": 8.328433712493269e-05, "loss": 0.085, "step": 93870 }, { "epoch": 22.52, "learning_rate": 8.328098867797803e-05, "loss": 0.0616, "step": 93880 }, { "epoch": 22.53, "learning_rate": 8.327763996300697e-05, "loss": 0.0939, "step": 93890 }, { "epoch": 22.53, "learning_rate": 8.32742909800465e-05, "loss": 0.0812, "step": 93900 }, { "epoch": 22.53, "learning_rate": 8.327094172912355e-05, "loss": 0.0826, "step": 93910 }, { "epoch": 22.53, "learning_rate": 8.326759221026512e-05, "loss": 0.081, "step": 93920 }, { "epoch": 22.54, "learning_rate": 8.32642424234982e-05, "loss": 0.0883, "step": 93930 }, { "epoch": 22.54, "learning_rate": 8.326089236884971e-05, "loss": 0.0978, "step": 93940 }, { "epoch": 22.54, "learning_rate": 8.325754204634668e-05, "loss": 0.0848, "step": 93950 }, { "epoch": 22.54, "learning_rate": 8.325419145601608e-05, "loss": 0.0926, "step": 93960 }, { "epoch": 22.54, "learning_rate": 8.325084059788486e-05, "loss": 0.0797, "step": 93970 }, { "epoch": 22.55, "learning_rate": 8.324748947198005e-05, "loss": 0.0974, "step": 93980 }, { "epoch": 22.55, "learning_rate": 8.32441380783286e-05, "loss": 0.0993, "step": 93990 }, { "epoch": 22.55, "learning_rate": 8.324078641695754e-05, "loss": 0.0865, "step": 94000 }, { "epoch": 22.55, "learning_rate": 8.323743448789383e-05, "loss": 0.1057, "step": 94010 }, { "epoch": 22.56, "learning_rate": 8.323408229116447e-05, "loss": 0.1164, "step": 94020 }, { "epoch": 22.56, "learning_rate": 8.323072982679645e-05, "loss": 0.1597, "step": 94030 }, { "epoch": 22.56, "learning_rate": 8.322737709481678e-05, "loss": 0.1546, "step": 94040 }, { "epoch": 22.56, "learning_rate": 8.322402409525245e-05, "loss": 0.1034, "step": 94050 }, { "epoch": 22.57, "learning_rate": 8.322067082813046e-05, "loss": 0.087, "step": 94060 }, { "epoch": 22.57, "learning_rate": 8.321731729347784e-05, "loss": 0.1245, "step": 94070 }, { "epoch": 22.57, "learning_rate": 8.321396349132156e-05, "loss": 0.0717, "step": 94080 }, { "epoch": 22.57, "learning_rate": 8.321060942168866e-05, "loss": 0.1296, "step": 94090 }, { "epoch": 22.57, "learning_rate": 8.320725508460614e-05, "loss": 0.0749, "step": 94100 }, { "epoch": 22.58, "learning_rate": 8.3203900480101e-05, "loss": 0.1293, "step": 94110 }, { "epoch": 22.58, "learning_rate": 8.320054560820028e-05, "loss": 0.0994, "step": 94120 }, { "epoch": 22.58, "learning_rate": 8.319719046893096e-05, "loss": 0.1007, "step": 94130 }, { "epoch": 22.58, "learning_rate": 8.31938350623201e-05, "loss": 0.1244, "step": 94140 }, { "epoch": 22.59, "learning_rate": 8.31904793883947e-05, "loss": 0.0918, "step": 94150 }, { "epoch": 22.59, "learning_rate": 8.318712344718179e-05, "loss": 0.0881, "step": 94160 }, { "epoch": 22.59, "learning_rate": 8.318376723870838e-05, "loss": 0.1242, "step": 94170 }, { "epoch": 22.59, "learning_rate": 8.318041076300152e-05, "loss": 0.0951, "step": 94180 }, { "epoch": 22.6, "learning_rate": 8.317705402008823e-05, "loss": 0.1168, "step": 94190 }, { "epoch": 22.6, "learning_rate": 8.317369700999555e-05, "loss": 0.0933, "step": 94200 }, { "epoch": 22.6, "learning_rate": 8.31703397327505e-05, "loss": 0.1179, "step": 94210 }, { "epoch": 22.6, "learning_rate": 8.316698218838013e-05, "loss": 0.0863, "step": 94220 }, { "epoch": 22.6, "learning_rate": 8.316362437691146e-05, "loss": 0.086, "step": 94230 }, { "epoch": 22.61, "learning_rate": 8.316026629837156e-05, "loss": 0.085, "step": 94240 }, { "epoch": 22.61, "learning_rate": 8.315690795278745e-05, "loss": 0.0777, "step": 94250 }, { "epoch": 22.61, "learning_rate": 8.315354934018618e-05, "loss": 0.0796, "step": 94260 }, { "epoch": 22.61, "learning_rate": 8.315019046059481e-05, "loss": 0.0911, "step": 94270 }, { "epoch": 22.62, "learning_rate": 8.314683131404037e-05, "loss": 0.1344, "step": 94280 }, { "epoch": 22.62, "learning_rate": 8.314347190054991e-05, "loss": 0.1318, "step": 94290 }, { "epoch": 22.62, "learning_rate": 8.314011222015054e-05, "loss": 0.0953, "step": 94300 }, { "epoch": 22.62, "learning_rate": 8.313675227286924e-05, "loss": 0.0834, "step": 94310 }, { "epoch": 22.62, "learning_rate": 8.31333920587331e-05, "loss": 0.0824, "step": 94320 }, { "epoch": 22.63, "learning_rate": 8.313003157776918e-05, "loss": 0.1014, "step": 94330 }, { "epoch": 22.63, "learning_rate": 8.312667083000453e-05, "loss": 0.0899, "step": 94340 }, { "epoch": 22.63, "learning_rate": 8.312330981546625e-05, "loss": 0.102, "step": 94350 }, { "epoch": 22.63, "learning_rate": 8.311994853418136e-05, "loss": 0.1162, "step": 94360 }, { "epoch": 22.64, "learning_rate": 8.311658698617697e-05, "loss": 0.0901, "step": 94370 }, { "epoch": 22.64, "learning_rate": 8.311322517148012e-05, "loss": 0.0776, "step": 94380 }, { "epoch": 22.64, "learning_rate": 8.31098630901179e-05, "loss": 0.0983, "step": 94390 }, { "epoch": 22.64, "learning_rate": 8.31065007421174e-05, "loss": 0.1002, "step": 94400 }, { "epoch": 22.65, "learning_rate": 8.310313812750566e-05, "loss": 0.0777, "step": 94410 }, { "epoch": 22.65, "learning_rate": 8.309977524630977e-05, "loss": 0.0766, "step": 94420 }, { "epoch": 22.65, "learning_rate": 8.309641209855684e-05, "loss": 0.1017, "step": 94430 }, { "epoch": 22.65, "learning_rate": 8.309304868427392e-05, "loss": 0.098, "step": 94440 }, { "epoch": 22.65, "learning_rate": 8.308968500348811e-05, "loss": 0.1224, "step": 94450 }, { "epoch": 22.66, "learning_rate": 8.308632105622651e-05, "loss": 0.1382, "step": 94460 }, { "epoch": 22.66, "learning_rate": 8.308295684251619e-05, "loss": 0.1094, "step": 94470 }, { "epoch": 22.66, "learning_rate": 8.307959236238425e-05, "loss": 0.0805, "step": 94480 }, { "epoch": 22.66, "learning_rate": 8.30762276158578e-05, "loss": 0.0932, "step": 94490 }, { "epoch": 22.67, "learning_rate": 8.30728626029639e-05, "loss": 0.0844, "step": 94500 }, { "epoch": 22.67, "learning_rate": 8.306949732372968e-05, "loss": 0.1211, "step": 94510 }, { "epoch": 22.67, "learning_rate": 8.306613177818226e-05, "loss": 0.0868, "step": 94520 }, { "epoch": 22.67, "learning_rate": 8.306276596634868e-05, "loss": 0.0543, "step": 94530 }, { "epoch": 22.68, "learning_rate": 8.30593998882561e-05, "loss": 0.1013, "step": 94540 }, { "epoch": 22.68, "learning_rate": 8.305603354393159e-05, "loss": 0.0757, "step": 94550 }, { "epoch": 22.68, "learning_rate": 8.305266693340231e-05, "loss": 0.0961, "step": 94560 }, { "epoch": 22.68, "learning_rate": 8.30493000566953e-05, "loss": 0.0713, "step": 94570 }, { "epoch": 22.68, "learning_rate": 8.304593291383774e-05, "loss": 0.0917, "step": 94580 }, { "epoch": 22.69, "learning_rate": 8.304256550485672e-05, "loss": 0.0691, "step": 94590 }, { "epoch": 22.69, "learning_rate": 8.303919782977933e-05, "loss": 0.1387, "step": 94600 }, { "epoch": 22.69, "learning_rate": 8.303582988863276e-05, "loss": 0.1002, "step": 94610 }, { "epoch": 22.69, "learning_rate": 8.303246168144407e-05, "loss": 0.0729, "step": 94620 }, { "epoch": 22.7, "learning_rate": 8.302909320824041e-05, "loss": 0.1165, "step": 94630 }, { "epoch": 22.7, "learning_rate": 8.302572446904888e-05, "loss": 0.0974, "step": 94640 }, { "epoch": 22.7, "learning_rate": 8.302235546389665e-05, "loss": 0.062, "step": 94650 }, { "epoch": 22.7, "learning_rate": 8.301898619281086e-05, "loss": 0.061, "step": 94660 }, { "epoch": 22.7, "learning_rate": 8.301561665581858e-05, "loss": 0.1164, "step": 94670 }, { "epoch": 22.71, "learning_rate": 8.301224685294699e-05, "loss": 0.0785, "step": 94680 }, { "epoch": 22.71, "learning_rate": 8.300887678422322e-05, "loss": 0.09, "step": 94690 }, { "epoch": 22.71, "learning_rate": 8.30055064496744e-05, "loss": 0.073, "step": 94700 }, { "epoch": 22.71, "learning_rate": 8.300213584932768e-05, "loss": 0.1116, "step": 94710 }, { "epoch": 22.72, "learning_rate": 8.299876498321022e-05, "loss": 0.0749, "step": 94720 }, { "epoch": 22.72, "learning_rate": 8.299539385134913e-05, "loss": 0.0707, "step": 94730 }, { "epoch": 22.72, "learning_rate": 8.29920224537716e-05, "loss": 0.0906, "step": 94740 }, { "epoch": 22.72, "learning_rate": 8.298865079050474e-05, "loss": 0.1105, "step": 94750 }, { "epoch": 22.73, "learning_rate": 8.298527886157572e-05, "loss": 0.0959, "step": 94760 }, { "epoch": 22.73, "learning_rate": 8.298190666701172e-05, "loss": 0.0818, "step": 94770 }, { "epoch": 22.73, "learning_rate": 8.297853420683985e-05, "loss": 0.1313, "step": 94780 }, { "epoch": 22.73, "learning_rate": 8.297516148108729e-05, "loss": 0.0739, "step": 94790 }, { "epoch": 22.73, "learning_rate": 8.297178848978121e-05, "loss": 0.1276, "step": 94800 }, { "epoch": 22.74, "learning_rate": 8.296841523294876e-05, "loss": 0.0894, "step": 94810 }, { "epoch": 22.74, "learning_rate": 8.296504171061711e-05, "loss": 0.09, "step": 94820 }, { "epoch": 22.74, "learning_rate": 8.296166792281343e-05, "loss": 0.0708, "step": 94830 }, { "epoch": 22.74, "learning_rate": 8.295829386956489e-05, "loss": 0.0721, "step": 94840 }, { "epoch": 22.75, "learning_rate": 8.295491955089867e-05, "loss": 0.0793, "step": 94850 }, { "epoch": 22.75, "learning_rate": 8.295154496684192e-05, "loss": 0.1051, "step": 94860 }, { "epoch": 22.75, "learning_rate": 8.294817011742182e-05, "loss": 0.0854, "step": 94870 }, { "epoch": 22.75, "learning_rate": 8.294479500266557e-05, "loss": 0.094, "step": 94880 }, { "epoch": 22.76, "learning_rate": 8.294141962260034e-05, "loss": 0.1134, "step": 94890 }, { "epoch": 22.76, "learning_rate": 8.293804397725331e-05, "loss": 0.0587, "step": 94900 }, { "epoch": 22.76, "learning_rate": 8.293466806665166e-05, "loss": 0.0923, "step": 94910 }, { "epoch": 22.76, "learning_rate": 8.293129189082258e-05, "loss": 0.1052, "step": 94920 }, { "epoch": 22.76, "learning_rate": 8.292791544979326e-05, "loss": 0.0751, "step": 94930 }, { "epoch": 22.77, "learning_rate": 8.29245387435909e-05, "loss": 0.0718, "step": 94940 }, { "epoch": 22.77, "learning_rate": 8.292116177224267e-05, "loss": 0.1001, "step": 94950 }, { "epoch": 22.77, "learning_rate": 8.291778453577579e-05, "loss": 0.1034, "step": 94960 }, { "epoch": 22.77, "learning_rate": 8.291440703421743e-05, "loss": 0.0721, "step": 94970 }, { "epoch": 22.78, "learning_rate": 8.291102926759482e-05, "loss": 0.0868, "step": 94980 }, { "epoch": 22.78, "learning_rate": 8.290765123593514e-05, "loss": 0.0975, "step": 94990 }, { "epoch": 22.78, "learning_rate": 8.290427293926562e-05, "loss": 0.0905, "step": 95000 }, { "epoch": 22.78, "learning_rate": 8.290089437761344e-05, "loss": 0.081, "step": 95010 }, { "epoch": 22.78, "learning_rate": 8.28975155510058e-05, "loss": 0.0808, "step": 95020 }, { "epoch": 22.79, "learning_rate": 8.289413645946994e-05, "loss": 0.0888, "step": 95030 }, { "epoch": 22.79, "learning_rate": 8.289075710303305e-05, "loss": 0.0712, "step": 95040 }, { "epoch": 22.79, "learning_rate": 8.288737748172235e-05, "loss": 0.0888, "step": 95050 }, { "epoch": 22.79, "learning_rate": 8.288399759556506e-05, "loss": 0.0952, "step": 95060 }, { "epoch": 22.8, "learning_rate": 8.288061744458841e-05, "loss": 0.0926, "step": 95070 }, { "epoch": 22.8, "learning_rate": 8.28772370288196e-05, "loss": 0.0825, "step": 95080 }, { "epoch": 22.8, "learning_rate": 8.287385634828587e-05, "loss": 0.0977, "step": 95090 }, { "epoch": 22.8, "learning_rate": 8.287047540301441e-05, "loss": 0.0805, "step": 95100 }, { "epoch": 22.81, "learning_rate": 8.286709419303249e-05, "loss": 0.0711, "step": 95110 }, { "epoch": 22.81, "learning_rate": 8.286371271836732e-05, "loss": 0.0616, "step": 95120 }, { "epoch": 22.81, "learning_rate": 8.286033097904615e-05, "loss": 0.085, "step": 95130 }, { "epoch": 22.81, "learning_rate": 8.285694897509618e-05, "loss": 0.0948, "step": 95140 }, { "epoch": 22.81, "learning_rate": 8.285356670654468e-05, "loss": 0.1079, "step": 95150 }, { "epoch": 22.82, "learning_rate": 8.285018417341886e-05, "loss": 0.0634, "step": 95160 }, { "epoch": 22.82, "learning_rate": 8.284680137574597e-05, "loss": 0.1013, "step": 95170 }, { "epoch": 22.82, "learning_rate": 8.284341831355325e-05, "loss": 0.101, "step": 95180 }, { "epoch": 22.82, "learning_rate": 8.284003498686795e-05, "loss": 0.0625, "step": 95190 }, { "epoch": 22.83, "learning_rate": 8.283665139571732e-05, "loss": 0.0808, "step": 95200 }, { "epoch": 22.83, "learning_rate": 8.283326754012861e-05, "loss": 0.0719, "step": 95210 }, { "epoch": 22.83, "learning_rate": 8.282988342012904e-05, "loss": 0.1057, "step": 95220 }, { "epoch": 22.83, "learning_rate": 8.282649903574591e-05, "loss": 0.1035, "step": 95230 }, { "epoch": 22.84, "learning_rate": 8.282311438700643e-05, "loss": 0.074, "step": 95240 }, { "epoch": 22.84, "learning_rate": 8.28197294739379e-05, "loss": 0.1144, "step": 95250 }, { "epoch": 22.84, "learning_rate": 8.281634429656755e-05, "loss": 0.0876, "step": 95260 }, { "epoch": 22.84, "learning_rate": 8.281295885492266e-05, "loss": 0.0677, "step": 95270 }, { "epoch": 22.84, "learning_rate": 8.280957314903046e-05, "loss": 0.0863, "step": 95280 }, { "epoch": 22.85, "learning_rate": 8.280618717891826e-05, "loss": 0.0717, "step": 95290 }, { "epoch": 22.85, "learning_rate": 8.280280094461328e-05, "loss": 0.0888, "step": 95300 }, { "epoch": 22.85, "learning_rate": 8.279941444614283e-05, "loss": 0.1077, "step": 95310 }, { "epoch": 22.85, "learning_rate": 8.279602768353417e-05, "loss": 0.0932, "step": 95320 }, { "epoch": 22.86, "learning_rate": 8.279264065681456e-05, "loss": 0.0853, "step": 95330 }, { "epoch": 22.86, "learning_rate": 8.27892533660113e-05, "loss": 0.1068, "step": 95340 }, { "epoch": 22.86, "learning_rate": 8.278586581115164e-05, "loss": 0.068, "step": 95350 }, { "epoch": 22.86, "learning_rate": 8.278247799226291e-05, "loss": 0.0847, "step": 95360 }, { "epoch": 22.86, "learning_rate": 8.277908990937232e-05, "loss": 0.0979, "step": 95370 }, { "epoch": 22.87, "learning_rate": 8.27757015625072e-05, "loss": 0.0873, "step": 95380 }, { "epoch": 22.87, "learning_rate": 8.277231295169486e-05, "loss": 0.0893, "step": 95390 }, { "epoch": 22.87, "learning_rate": 8.276892407696252e-05, "loss": 0.0638, "step": 95400 }, { "epoch": 22.87, "learning_rate": 8.276553493833755e-05, "loss": 0.0772, "step": 95410 }, { "epoch": 22.88, "learning_rate": 8.276214553584717e-05, "loss": 0.0676, "step": 95420 }, { "epoch": 22.88, "learning_rate": 8.27587558695187e-05, "loss": 0.0838, "step": 95430 }, { "epoch": 22.88, "learning_rate": 8.27553659393795e-05, "loss": 0.0939, "step": 95440 }, { "epoch": 22.88, "learning_rate": 8.275197574545677e-05, "loss": 0.075, "step": 95450 }, { "epoch": 22.89, "learning_rate": 8.274858528777788e-05, "loss": 0.0607, "step": 95460 }, { "epoch": 22.89, "learning_rate": 8.27451945663701e-05, "loss": 0.0717, "step": 95470 }, { "epoch": 22.89, "learning_rate": 8.274180358126076e-05, "loss": 0.071, "step": 95480 }, { "epoch": 22.89, "learning_rate": 8.273841233247713e-05, "loss": 0.0914, "step": 95490 }, { "epoch": 22.89, "learning_rate": 8.273502082004656e-05, "loss": 0.099, "step": 95500 }, { "epoch": 22.9, "learning_rate": 8.273162904399637e-05, "loss": 0.0733, "step": 95510 }, { "epoch": 22.9, "learning_rate": 8.272823700435382e-05, "loss": 0.0631, "step": 95520 }, { "epoch": 22.9, "learning_rate": 8.272484470114626e-05, "loss": 0.072, "step": 95530 }, { "epoch": 22.9, "learning_rate": 8.272145213440103e-05, "loss": 0.0811, "step": 95540 }, { "epoch": 22.91, "learning_rate": 8.27180593041454e-05, "loss": 0.108, "step": 95550 }, { "epoch": 22.91, "learning_rate": 8.271466621040675e-05, "loss": 0.1057, "step": 95560 }, { "epoch": 22.91, "learning_rate": 8.271127285321236e-05, "loss": 0.0835, "step": 95570 }, { "epoch": 22.91, "learning_rate": 8.270787923258959e-05, "loss": 0.0722, "step": 95580 }, { "epoch": 22.91, "learning_rate": 8.270448534856574e-05, "loss": 0.0966, "step": 95590 }, { "epoch": 22.92, "learning_rate": 8.270109120116815e-05, "loss": 0.0655, "step": 95600 }, { "epoch": 22.92, "learning_rate": 8.269769679042416e-05, "loss": 0.0994, "step": 95610 }, { "epoch": 22.92, "learning_rate": 8.269430211636111e-05, "loss": 0.0744, "step": 95620 }, { "epoch": 22.92, "learning_rate": 8.269090717900632e-05, "loss": 0.0597, "step": 95630 }, { "epoch": 22.93, "learning_rate": 8.268751197838715e-05, "loss": 0.0724, "step": 95640 }, { "epoch": 22.93, "learning_rate": 8.268411651453094e-05, "loss": 0.1021, "step": 95650 }, { "epoch": 22.93, "learning_rate": 8.268072078746502e-05, "loss": 0.0953, "step": 95660 }, { "epoch": 22.93, "learning_rate": 8.267732479721675e-05, "loss": 0.1053, "step": 95670 }, { "epoch": 22.94, "learning_rate": 8.267392854381347e-05, "loss": 0.0913, "step": 95680 }, { "epoch": 22.94, "learning_rate": 8.267053202728252e-05, "loss": 0.0826, "step": 95690 }, { "epoch": 22.94, "learning_rate": 8.266713524765127e-05, "loss": 0.096, "step": 95700 }, { "epoch": 22.94, "learning_rate": 8.266373820494709e-05, "loss": 0.1017, "step": 95710 }, { "epoch": 22.94, "learning_rate": 8.266034089919728e-05, "loss": 0.0854, "step": 95720 }, { "epoch": 22.95, "learning_rate": 8.265694333042926e-05, "loss": 0.0976, "step": 95730 }, { "epoch": 22.95, "learning_rate": 8.265354549867037e-05, "loss": 0.0864, "step": 95740 }, { "epoch": 23.0, "learning_rate": 8.265014740394796e-05, "loss": 0.0954, "step": 95750 }, { "epoch": 23.0, "learning_rate": 8.26467490462894e-05, "loss": 0.0793, "step": 95760 }, { "epoch": 23.0, "learning_rate": 8.264335042572208e-05, "loss": 0.1018, "step": 95770 }, { "epoch": 23.01, "learning_rate": 8.263995154227333e-05, "loss": 0.0662, "step": 95780 }, { "epoch": 23.01, "learning_rate": 8.263655239597057e-05, "loss": 0.07, "step": 95790 }, { "epoch": 23.01, "learning_rate": 8.263315298684114e-05, "loss": 0.0908, "step": 95800 }, { "epoch": 23.01, "learning_rate": 8.26297533149124e-05, "loss": 0.0903, "step": 95810 }, { "epoch": 23.02, "learning_rate": 8.262635338021179e-05, "loss": 0.0798, "step": 95820 }, { "epoch": 23.02, "learning_rate": 8.262295318276663e-05, "loss": 0.0762, "step": 95830 }, { "epoch": 23.02, "learning_rate": 8.261955272260432e-05, "loss": 0.062, "step": 95840 }, { "epoch": 23.02, "learning_rate": 8.261615199975226e-05, "loss": 0.0751, "step": 95850 }, { "epoch": 23.03, "learning_rate": 8.261275101423782e-05, "loss": 0.0789, "step": 95860 }, { "epoch": 23.03, "learning_rate": 8.260934976608839e-05, "loss": 0.0733, "step": 95870 }, { "epoch": 23.03, "learning_rate": 8.260594825533137e-05, "loss": 0.0693, "step": 95880 }, { "epoch": 23.03, "learning_rate": 8.260254648199414e-05, "loss": 0.0894, "step": 95890 }, { "epoch": 23.03, "learning_rate": 8.25991444461041e-05, "loss": 0.0928, "step": 95900 }, { "epoch": 23.04, "learning_rate": 8.259574214768866e-05, "loss": 0.0648, "step": 95910 }, { "epoch": 23.04, "learning_rate": 8.259233958677522e-05, "loss": 0.0689, "step": 95920 }, { "epoch": 23.04, "learning_rate": 8.258893676339114e-05, "loss": 0.1016, "step": 95930 }, { "epoch": 23.04, "learning_rate": 8.258553367756387e-05, "loss": 0.0729, "step": 95940 }, { "epoch": 23.05, "learning_rate": 8.25821303293208e-05, "loss": 0.095, "step": 95950 }, { "epoch": 23.05, "learning_rate": 8.257872671868933e-05, "loss": 0.0701, "step": 95960 }, { "epoch": 23.05, "learning_rate": 8.257532284569687e-05, "loss": 0.0678, "step": 95970 }, { "epoch": 23.05, "learning_rate": 8.257191871037086e-05, "loss": 0.0789, "step": 95980 }, { "epoch": 23.06, "learning_rate": 8.256851431273866e-05, "loss": 0.088, "step": 95990 }, { "epoch": 23.06, "learning_rate": 8.256510965282776e-05, "loss": 0.0879, "step": 96000 }, { "epoch": 23.06, "learning_rate": 8.25617047306655e-05, "loss": 0.0716, "step": 96010 }, { "epoch": 23.06, "learning_rate": 8.255829954627935e-05, "loss": 0.0776, "step": 96020 }, { "epoch": 23.06, "learning_rate": 8.255489409969671e-05, "loss": 0.0633, "step": 96030 }, { "epoch": 23.07, "learning_rate": 8.255148839094503e-05, "loss": 0.0769, "step": 96040 }, { "epoch": 23.07, "learning_rate": 8.25480824200517e-05, "loss": 0.0747, "step": 96050 }, { "epoch": 23.07, "learning_rate": 8.254467618704418e-05, "loss": 0.0882, "step": 96060 }, { "epoch": 23.07, "learning_rate": 8.254126969194988e-05, "loss": 0.069, "step": 96070 }, { "epoch": 23.08, "learning_rate": 8.253786293479626e-05, "loss": 0.0887, "step": 96080 }, { "epoch": 23.08, "learning_rate": 8.253445591561073e-05, "loss": 0.1065, "step": 96090 }, { "epoch": 23.08, "learning_rate": 8.253104863442074e-05, "loss": 0.0614, "step": 96100 }, { "epoch": 23.08, "learning_rate": 8.252764109125371e-05, "loss": 0.0769, "step": 96110 }, { "epoch": 23.08, "learning_rate": 8.252423328613711e-05, "loss": 0.0763, "step": 96120 }, { "epoch": 23.09, "learning_rate": 8.252082521909837e-05, "loss": 0.0664, "step": 96130 }, { "epoch": 23.09, "learning_rate": 8.251741689016492e-05, "loss": 0.0644, "step": 96140 }, { "epoch": 23.09, "learning_rate": 8.251400829936422e-05, "loss": 0.0937, "step": 96150 }, { "epoch": 23.09, "learning_rate": 8.251059944672373e-05, "loss": 0.0585, "step": 96160 }, { "epoch": 23.1, "learning_rate": 8.25071903322709e-05, "loss": 0.0689, "step": 96170 }, { "epoch": 23.1, "learning_rate": 8.250378095603318e-05, "loss": 0.115, "step": 96180 }, { "epoch": 23.1, "learning_rate": 8.250037131803802e-05, "loss": 0.0776, "step": 96190 }, { "epoch": 23.1, "learning_rate": 8.249696141831287e-05, "loss": 0.0787, "step": 96200 }, { "epoch": 23.11, "learning_rate": 8.249355125688523e-05, "loss": 0.0741, "step": 96210 }, { "epoch": 23.11, "learning_rate": 8.249014083378252e-05, "loss": 0.0694, "step": 96220 }, { "epoch": 23.11, "learning_rate": 8.248673014903221e-05, "loss": 0.0863, "step": 96230 }, { "epoch": 23.11, "learning_rate": 8.24833192026618e-05, "loss": 0.0481, "step": 96240 }, { "epoch": 23.11, "learning_rate": 8.247990799469871e-05, "loss": 0.072, "step": 96250 }, { "epoch": 23.12, "learning_rate": 8.247649652517047e-05, "loss": 0.0543, "step": 96260 }, { "epoch": 23.12, "learning_rate": 8.24730847941045e-05, "loss": 0.0809, "step": 96270 }, { "epoch": 23.12, "learning_rate": 8.246967280152829e-05, "loss": 0.0605, "step": 96280 }, { "epoch": 23.12, "learning_rate": 8.246626054746933e-05, "loss": 0.0833, "step": 96290 }, { "epoch": 23.13, "learning_rate": 8.246284803195508e-05, "loss": 0.0918, "step": 96300 }, { "epoch": 23.13, "learning_rate": 8.245943525501305e-05, "loss": 0.0592, "step": 96310 }, { "epoch": 23.13, "learning_rate": 8.24560222166707e-05, "loss": 0.0915, "step": 96320 }, { "epoch": 23.13, "learning_rate": 8.245260891695552e-05, "loss": 0.0936, "step": 96330 }, { "epoch": 23.14, "learning_rate": 8.244919535589499e-05, "loss": 0.0698, "step": 96340 }, { "epoch": 23.14, "learning_rate": 8.244578153351663e-05, "loss": 0.0691, "step": 96350 }, { "epoch": 23.14, "learning_rate": 8.24423674498479e-05, "loss": 0.0651, "step": 96360 }, { "epoch": 23.14, "learning_rate": 8.243895310491632e-05, "loss": 0.0578, "step": 96370 }, { "epoch": 23.14, "learning_rate": 8.243553849874935e-05, "loss": 0.0557, "step": 96380 }, { "epoch": 23.15, "learning_rate": 8.243212363137452e-05, "loss": 0.0616, "step": 96390 }, { "epoch": 23.15, "learning_rate": 8.242870850281932e-05, "loss": 0.0985, "step": 96400 }, { "epoch": 23.15, "learning_rate": 8.242529311311127e-05, "loss": 0.0607, "step": 96410 }, { "epoch": 23.15, "learning_rate": 8.242187746227783e-05, "loss": 0.0868, "step": 96420 }, { "epoch": 23.16, "learning_rate": 8.241846155034656e-05, "loss": 0.0993, "step": 96430 }, { "epoch": 23.16, "learning_rate": 8.241504537734492e-05, "loss": 0.0935, "step": 96440 }, { "epoch": 23.16, "learning_rate": 8.241162894330047e-05, "loss": 0.1002, "step": 96450 }, { "epoch": 23.16, "learning_rate": 8.240821224824067e-05, "loss": 0.0989, "step": 96460 }, { "epoch": 23.16, "learning_rate": 8.24047952921931e-05, "loss": 0.0683, "step": 96470 }, { "epoch": 23.17, "learning_rate": 8.24013780751852e-05, "loss": 0.0813, "step": 96480 }, { "epoch": 23.17, "learning_rate": 8.239796059724453e-05, "loss": 0.0705, "step": 96490 }, { "epoch": 23.17, "learning_rate": 8.239454285839865e-05, "loss": 0.078, "step": 96500 }, { "epoch": 23.17, "learning_rate": 8.239112485867501e-05, "loss": 0.102, "step": 96510 }, { "epoch": 23.18, "learning_rate": 8.238770659810118e-05, "loss": 0.0684, "step": 96520 }, { "epoch": 23.18, "learning_rate": 8.238428807670468e-05, "loss": 0.086, "step": 96530 }, { "epoch": 23.18, "learning_rate": 8.238086929451304e-05, "loss": 0.0588, "step": 96540 }, { "epoch": 23.18, "learning_rate": 8.237745025155377e-05, "loss": 0.0833, "step": 96550 }, { "epoch": 23.19, "learning_rate": 8.237403094785444e-05, "loss": 0.0875, "step": 96560 }, { "epoch": 23.19, "learning_rate": 8.237061138344257e-05, "loss": 0.0635, "step": 96570 }, { "epoch": 23.19, "learning_rate": 8.236719155834569e-05, "loss": 0.0572, "step": 96580 }, { "epoch": 23.19, "learning_rate": 8.236377147259136e-05, "loss": 0.0901, "step": 96590 }, { "epoch": 23.19, "learning_rate": 8.23603511262071e-05, "loss": 0.0671, "step": 96600 }, { "epoch": 23.2, "learning_rate": 8.235693051922047e-05, "loss": 0.0667, "step": 96610 }, { "epoch": 23.2, "learning_rate": 8.2353509651659e-05, "loss": 0.058, "step": 96620 }, { "epoch": 23.2, "learning_rate": 8.235008852355023e-05, "loss": 0.0578, "step": 96630 }, { "epoch": 23.2, "learning_rate": 8.234666713492178e-05, "loss": 0.087, "step": 96640 }, { "epoch": 23.21, "learning_rate": 8.234324548580113e-05, "loss": 0.0697, "step": 96650 }, { "epoch": 23.21, "learning_rate": 8.233982357621586e-05, "loss": 0.0902, "step": 96660 }, { "epoch": 23.21, "learning_rate": 8.233640140619353e-05, "loss": 0.072, "step": 96670 }, { "epoch": 23.21, "learning_rate": 8.233297897576169e-05, "loss": 0.0736, "step": 96680 }, { "epoch": 23.22, "learning_rate": 8.232955628494792e-05, "loss": 0.0768, "step": 96690 }, { "epoch": 23.22, "learning_rate": 8.232613333377974e-05, "loss": 0.0666, "step": 96700 }, { "epoch": 23.22, "learning_rate": 8.232271012228478e-05, "loss": 0.0509, "step": 96710 }, { "epoch": 23.22, "learning_rate": 8.231928665049056e-05, "loss": 0.0635, "step": 96720 }, { "epoch": 23.22, "learning_rate": 8.231586291842466e-05, "loss": 0.0617, "step": 96730 }, { "epoch": 23.23, "learning_rate": 8.231243892611465e-05, "loss": 0.0883, "step": 96740 }, { "epoch": 23.23, "learning_rate": 8.23090146735881e-05, "loss": 0.0563, "step": 96750 }, { "epoch": 23.23, "learning_rate": 8.23055901608726e-05, "loss": 0.1207, "step": 96760 }, { "epoch": 23.23, "learning_rate": 8.230216538799574e-05, "loss": 0.066, "step": 96770 }, { "epoch": 23.24, "learning_rate": 8.229874035498509e-05, "loss": 0.0616, "step": 96780 }, { "epoch": 23.24, "learning_rate": 8.229531506186818e-05, "loss": 0.0745, "step": 96790 }, { "epoch": 23.24, "learning_rate": 8.229188950867268e-05, "loss": 0.0741, "step": 96800 }, { "epoch": 23.24, "learning_rate": 8.228846369542611e-05, "loss": 0.0654, "step": 96810 }, { "epoch": 23.24, "learning_rate": 8.22850376221561e-05, "loss": 0.0788, "step": 96820 }, { "epoch": 23.25, "learning_rate": 8.228161128889023e-05, "loss": 0.0495, "step": 96830 }, { "epoch": 23.25, "learning_rate": 8.227818469565607e-05, "loss": 0.076, "step": 96840 }, { "epoch": 23.25, "learning_rate": 8.227475784248124e-05, "loss": 0.0829, "step": 96850 }, { "epoch": 23.25, "learning_rate": 8.227133072939332e-05, "loss": 0.0685, "step": 96860 }, { "epoch": 23.26, "learning_rate": 8.226790335641994e-05, "loss": 0.0483, "step": 96870 }, { "epoch": 23.26, "learning_rate": 8.226447572358867e-05, "loss": 0.0676, "step": 96880 }, { "epoch": 23.26, "learning_rate": 8.226104783092709e-05, "loss": 0.0448, "step": 96890 }, { "epoch": 23.26, "learning_rate": 8.225761967846289e-05, "loss": 0.1185, "step": 96900 }, { "epoch": 23.27, "learning_rate": 8.22541912662236e-05, "loss": 0.0948, "step": 96910 }, { "epoch": 23.27, "learning_rate": 8.225076259423686e-05, "loss": 0.0885, "step": 96920 }, { "epoch": 23.27, "learning_rate": 8.224733366253026e-05, "loss": 0.0541, "step": 96930 }, { "epoch": 23.27, "learning_rate": 8.224390447113146e-05, "loss": 0.0815, "step": 96940 }, { "epoch": 23.27, "learning_rate": 8.224047502006802e-05, "loss": 0.0605, "step": 96950 }, { "epoch": 23.28, "learning_rate": 8.22370453093676e-05, "loss": 0.0905, "step": 96960 }, { "epoch": 23.28, "learning_rate": 8.223361533905781e-05, "loss": 0.0629, "step": 96970 }, { "epoch": 23.28, "learning_rate": 8.223018510916624e-05, "loss": 0.0643, "step": 96980 }, { "epoch": 23.28, "learning_rate": 8.222675461972055e-05, "loss": 0.0573, "step": 96990 }, { "epoch": 23.29, "learning_rate": 8.222332387074836e-05, "loss": 0.1011, "step": 97000 }, { "epoch": 23.29, "learning_rate": 8.22198928622773e-05, "loss": 0.0938, "step": 97010 }, { "epoch": 23.29, "learning_rate": 8.221646159433497e-05, "loss": 0.0854, "step": 97020 }, { "epoch": 23.29, "learning_rate": 8.221303006694905e-05, "loss": 0.0841, "step": 97030 }, { "epoch": 23.3, "learning_rate": 8.220959828014714e-05, "loss": 0.0631, "step": 97040 }, { "epoch": 23.3, "learning_rate": 8.220616623395689e-05, "loss": 0.0761, "step": 97050 }, { "epoch": 23.3, "learning_rate": 8.220273392840593e-05, "loss": 0.0497, "step": 97060 }, { "epoch": 23.3, "learning_rate": 8.219930136352194e-05, "loss": 0.0724, "step": 97070 }, { "epoch": 23.3, "learning_rate": 8.21958685393325e-05, "loss": 0.0623, "step": 97080 }, { "epoch": 23.31, "learning_rate": 8.21924354558653e-05, "loss": 0.0831, "step": 97090 }, { "epoch": 23.31, "learning_rate": 8.218900211314796e-05, "loss": 0.0989, "step": 97100 }, { "epoch": 23.31, "learning_rate": 8.218556851120816e-05, "loss": 0.0629, "step": 97110 }, { "epoch": 23.31, "learning_rate": 8.218213465007351e-05, "loss": 0.0919, "step": 97120 }, { "epoch": 23.32, "learning_rate": 8.217870052977171e-05, "loss": 0.0603, "step": 97130 }, { "epoch": 23.32, "learning_rate": 8.217526615033038e-05, "loss": 0.0463, "step": 97140 }, { "epoch": 23.32, "learning_rate": 8.217183151177718e-05, "loss": 0.0754, "step": 97150 }, { "epoch": 23.32, "learning_rate": 8.21683966141398e-05, "loss": 0.0712, "step": 97160 }, { "epoch": 23.32, "learning_rate": 8.216496145744585e-05, "loss": 0.0626, "step": 97170 }, { "epoch": 23.33, "learning_rate": 8.216152604172307e-05, "loss": 0.0721, "step": 97180 }, { "epoch": 23.33, "learning_rate": 8.215809036699904e-05, "loss": 0.0779, "step": 97190 }, { "epoch": 23.33, "learning_rate": 8.215465443330151e-05, "loss": 0.0763, "step": 97200 }, { "epoch": 23.33, "learning_rate": 8.215121824065807e-05, "loss": 0.0746, "step": 97210 }, { "epoch": 23.34, "learning_rate": 8.214778178909643e-05, "loss": 0.0587, "step": 97220 }, { "epoch": 23.34, "learning_rate": 8.214434507864428e-05, "loss": 0.0784, "step": 97230 }, { "epoch": 23.34, "learning_rate": 8.214090810932928e-05, "loss": 0.0612, "step": 97240 }, { "epoch": 23.34, "learning_rate": 8.213747088117912e-05, "loss": 0.0544, "step": 97250 }, { "epoch": 23.35, "learning_rate": 8.213403339422145e-05, "loss": 0.0646, "step": 97260 }, { "epoch": 23.35, "learning_rate": 8.2130595648484e-05, "loss": 0.0741, "step": 97270 }, { "epoch": 23.35, "learning_rate": 8.212715764399441e-05, "loss": 0.1033, "step": 97280 }, { "epoch": 23.35, "learning_rate": 8.212371938078038e-05, "loss": 0.0853, "step": 97290 }, { "epoch": 23.35, "learning_rate": 8.21202808588696e-05, "loss": 0.08, "step": 97300 }, { "epoch": 23.36, "learning_rate": 8.211684207828979e-05, "loss": 0.0936, "step": 97310 }, { "epoch": 23.36, "learning_rate": 8.211340303906858e-05, "loss": 0.0421, "step": 97320 }, { "epoch": 23.36, "learning_rate": 8.210996374123372e-05, "loss": 0.0984, "step": 97330 }, { "epoch": 23.36, "learning_rate": 8.210652418481288e-05, "loss": 0.0976, "step": 97340 }, { "epoch": 23.37, "learning_rate": 8.210308436983379e-05, "loss": 0.0591, "step": 97350 }, { "epoch": 23.37, "learning_rate": 8.209964429632411e-05, "loss": 0.0587, "step": 97360 }, { "epoch": 23.37, "learning_rate": 8.209620396431157e-05, "loss": 0.0856, "step": 97370 }, { "epoch": 23.37, "learning_rate": 8.209276337382388e-05, "loss": 0.0682, "step": 97380 }, { "epoch": 23.38, "learning_rate": 8.208932252488872e-05, "loss": 0.0552, "step": 97390 }, { "epoch": 23.38, "learning_rate": 8.208588141753382e-05, "loss": 0.0616, "step": 97400 }, { "epoch": 23.38, "learning_rate": 8.208244005178688e-05, "loss": 0.0569, "step": 97410 }, { "epoch": 23.38, "learning_rate": 8.207899842767563e-05, "loss": 0.0748, "step": 97420 }, { "epoch": 23.38, "learning_rate": 8.207555654522777e-05, "loss": 0.0741, "step": 97430 }, { "epoch": 23.39, "learning_rate": 8.207211440447104e-05, "loss": 0.0655, "step": 97440 }, { "epoch": 23.39, "learning_rate": 8.206867200543313e-05, "loss": 0.0955, "step": 97450 }, { "epoch": 23.39, "learning_rate": 8.206522934814178e-05, "loss": 0.084, "step": 97460 }, { "epoch": 23.39, "learning_rate": 8.20617864326247e-05, "loss": 0.0882, "step": 97470 }, { "epoch": 23.4, "learning_rate": 8.205834325890964e-05, "loss": 0.111, "step": 97480 }, { "epoch": 23.4, "learning_rate": 8.205489982702432e-05, "loss": 0.0557, "step": 97490 }, { "epoch": 23.4, "learning_rate": 8.205145613699645e-05, "loss": 0.0694, "step": 97500 }, { "epoch": 23.4, "learning_rate": 8.20480121888538e-05, "loss": 0.0524, "step": 97510 }, { "epoch": 23.4, "learning_rate": 8.204456798262407e-05, "loss": 0.0767, "step": 97520 }, { "epoch": 23.41, "learning_rate": 8.204112351833501e-05, "loss": 0.056, "step": 97530 }, { "epoch": 23.41, "learning_rate": 8.203767879601437e-05, "loss": 0.0719, "step": 97540 }, { "epoch": 23.41, "learning_rate": 8.203423381568987e-05, "loss": 0.0733, "step": 97550 }, { "epoch": 23.41, "learning_rate": 8.203078857738926e-05, "loss": 0.0591, "step": 97560 }, { "epoch": 23.42, "learning_rate": 8.20273430811403e-05, "loss": 0.0651, "step": 97570 }, { "epoch": 23.42, "learning_rate": 8.202389732697071e-05, "loss": 0.0421, "step": 97580 }, { "epoch": 23.42, "learning_rate": 8.202045131490825e-05, "loss": 0.0872, "step": 97590 }, { "epoch": 23.42, "learning_rate": 8.20170050449807e-05, "loss": 0.0523, "step": 97600 }, { "epoch": 23.43, "learning_rate": 8.201355851721577e-05, "loss": 0.0851, "step": 97610 }, { "epoch": 23.43, "learning_rate": 8.201011173164124e-05, "loss": 0.0551, "step": 97620 }, { "epoch": 23.43, "learning_rate": 8.200666468828487e-05, "loss": 0.0929, "step": 97630 }, { "epoch": 23.43, "learning_rate": 8.200321738717438e-05, "loss": 0.0735, "step": 97640 }, { "epoch": 23.43, "learning_rate": 8.199976982833758e-05, "loss": 0.073, "step": 97650 }, { "epoch": 23.44, "learning_rate": 8.199632201180221e-05, "loss": 0.1117, "step": 97660 }, { "epoch": 23.44, "learning_rate": 8.199287393759605e-05, "loss": 0.0655, "step": 97670 }, { "epoch": 23.44, "learning_rate": 8.198942560574686e-05, "loss": 0.0482, "step": 97680 }, { "epoch": 23.44, "learning_rate": 8.198597701628241e-05, "loss": 0.0455, "step": 97690 }, { "epoch": 23.45, "learning_rate": 8.198252816923047e-05, "loss": 0.0546, "step": 97700 }, { "epoch": 23.45, "learning_rate": 8.197907906461881e-05, "loss": 0.0788, "step": 97710 }, { "epoch": 23.45, "learning_rate": 8.197562970247521e-05, "loss": 0.0557, "step": 97720 }, { "epoch": 23.45, "learning_rate": 8.197218008282746e-05, "loss": 0.0914, "step": 97730 }, { "epoch": 23.45, "learning_rate": 8.19687302057033e-05, "loss": 0.0794, "step": 97740 }, { "epoch": 23.46, "learning_rate": 8.196528007113057e-05, "loss": 0.0762, "step": 97750 }, { "epoch": 23.46, "learning_rate": 8.196182967913702e-05, "loss": 0.0721, "step": 97760 }, { "epoch": 23.46, "learning_rate": 8.195837902975046e-05, "loss": 0.1094, "step": 97770 }, { "epoch": 23.46, "learning_rate": 8.195492812299863e-05, "loss": 0.0731, "step": 97780 }, { "epoch": 23.47, "learning_rate": 8.195147695890938e-05, "loss": 0.0563, "step": 97790 }, { "epoch": 23.47, "learning_rate": 8.194802553751047e-05, "loss": 0.0688, "step": 97800 }, { "epoch": 23.47, "learning_rate": 8.194457385882968e-05, "loss": 0.0611, "step": 97810 }, { "epoch": 23.47, "learning_rate": 8.194112192289484e-05, "loss": 0.0901, "step": 97820 }, { "epoch": 23.48, "learning_rate": 8.193766972973373e-05, "loss": 0.0593, "step": 97830 }, { "epoch": 23.48, "learning_rate": 8.193421727937416e-05, "loss": 0.0638, "step": 97840 }, { "epoch": 23.48, "learning_rate": 8.193076457184393e-05, "loss": 0.0963, "step": 97850 }, { "epoch": 23.48, "learning_rate": 8.192731160717086e-05, "loss": 0.0835, "step": 97860 }, { "epoch": 23.48, "learning_rate": 8.19238583853827e-05, "loss": 0.0816, "step": 97870 }, { "epoch": 23.49, "learning_rate": 8.192040490650735e-05, "loss": 0.0583, "step": 97880 }, { "epoch": 23.49, "learning_rate": 8.191695117057254e-05, "loss": 0.0865, "step": 97890 }, { "epoch": 23.49, "learning_rate": 8.191349717760612e-05, "loss": 0.1169, "step": 97900 }, { "epoch": 23.49, "learning_rate": 8.191004292763591e-05, "loss": 0.0544, "step": 97910 }, { "epoch": 23.5, "learning_rate": 8.190658842068972e-05, "loss": 0.0926, "step": 97920 }, { "epoch": 23.5, "learning_rate": 8.190313365679537e-05, "loss": 0.0665, "step": 97930 }, { "epoch": 23.5, "learning_rate": 8.189967863598067e-05, "loss": 0.0476, "step": 97940 }, { "epoch": 23.5, "learning_rate": 8.189622335827345e-05, "loss": 0.0827, "step": 97950 }, { "epoch": 23.51, "learning_rate": 8.189276782370156e-05, "loss": 0.0893, "step": 97960 }, { "epoch": 23.51, "learning_rate": 8.188931203229279e-05, "loss": 0.0697, "step": 97970 }, { "epoch": 23.51, "learning_rate": 8.1885855984075e-05, "loss": 0.0541, "step": 97980 }, { "epoch": 23.51, "learning_rate": 8.188239967907601e-05, "loss": 0.0686, "step": 97990 }, { "epoch": 23.51, "learning_rate": 8.187894311732362e-05, "loss": 0.0781, "step": 98000 }, { "epoch": 23.52, "learning_rate": 8.187548629884574e-05, "loss": 0.0718, "step": 98010 }, { "epoch": 23.52, "learning_rate": 8.187202922367015e-05, "loss": 0.0734, "step": 98020 }, { "epoch": 23.52, "learning_rate": 8.186857189182472e-05, "loss": 0.0661, "step": 98030 }, { "epoch": 23.52, "learning_rate": 8.186511430333728e-05, "loss": 0.0542, "step": 98040 }, { "epoch": 23.53, "learning_rate": 8.186165645823567e-05, "loss": 0.142, "step": 98050 }, { "epoch": 23.53, "learning_rate": 8.185819835654773e-05, "loss": 0.074, "step": 98060 }, { "epoch": 23.53, "learning_rate": 8.185473999830133e-05, "loss": 0.0651, "step": 98070 }, { "epoch": 23.53, "learning_rate": 8.185128138352431e-05, "loss": 0.0816, "step": 98080 }, { "epoch": 23.53, "learning_rate": 8.184782251224453e-05, "loss": 0.1198, "step": 98090 }, { "epoch": 23.54, "learning_rate": 8.184436338448984e-05, "loss": 0.0857, "step": 98100 }, { "epoch": 23.54, "learning_rate": 8.184090400028808e-05, "loss": 0.0758, "step": 98110 }, { "epoch": 23.54, "learning_rate": 8.183744435966714e-05, "loss": 0.0822, "step": 98120 }, { "epoch": 23.54, "learning_rate": 8.183398446265486e-05, "loss": 0.1034, "step": 98130 }, { "epoch": 23.55, "learning_rate": 8.18305243092791e-05, "loss": 0.1105, "step": 98140 }, { "epoch": 23.55, "learning_rate": 8.182706389956774e-05, "loss": 0.0959, "step": 98150 }, { "epoch": 23.55, "learning_rate": 8.182360323354865e-05, "loss": 0.1085, "step": 98160 }, { "epoch": 23.55, "learning_rate": 8.182014231124968e-05, "loss": 0.1278, "step": 98170 }, { "epoch": 23.56, "learning_rate": 8.181668113269871e-05, "loss": 0.0823, "step": 98180 }, { "epoch": 23.56, "learning_rate": 8.181321969792362e-05, "loss": 0.1106, "step": 98190 }, { "epoch": 23.56, "learning_rate": 8.180975800695228e-05, "loss": 0.082, "step": 98200 }, { "epoch": 23.56, "learning_rate": 8.180629605981255e-05, "loss": 0.0733, "step": 98210 }, { "epoch": 23.56, "learning_rate": 8.180283385653234e-05, "loss": 0.0879, "step": 98220 }, { "epoch": 23.57, "learning_rate": 8.179937139713952e-05, "loss": 0.0722, "step": 98230 }, { "epoch": 23.57, "learning_rate": 8.179590868166196e-05, "loss": 0.0836, "step": 98240 }, { "epoch": 23.57, "learning_rate": 8.179244571012758e-05, "loss": 0.0886, "step": 98250 }, { "epoch": 23.57, "learning_rate": 8.178898248256424e-05, "loss": 0.0913, "step": 98260 }, { "epoch": 23.58, "learning_rate": 8.178551899899983e-05, "loss": 0.0987, "step": 98270 }, { "epoch": 23.58, "learning_rate": 8.178205525946223e-05, "loss": 0.1238, "step": 98280 }, { "epoch": 23.58, "learning_rate": 8.177859126397938e-05, "loss": 0.0634, "step": 98290 }, { "epoch": 23.58, "learning_rate": 8.177512701257912e-05, "loss": 0.0759, "step": 98300 }, { "epoch": 23.59, "learning_rate": 8.17716625052894e-05, "loss": 0.0875, "step": 98310 }, { "epoch": 23.59, "learning_rate": 8.176819774213807e-05, "loss": 0.118, "step": 98320 }, { "epoch": 23.59, "learning_rate": 8.176473272315308e-05, "loss": 0.0987, "step": 98330 }, { "epoch": 23.59, "learning_rate": 8.17612674483623e-05, "loss": 0.1116, "step": 98340 }, { "epoch": 23.59, "learning_rate": 8.175780191779365e-05, "loss": 0.0866, "step": 98350 }, { "epoch": 23.6, "learning_rate": 8.175433613147505e-05, "loss": 0.0624, "step": 98360 }, { "epoch": 23.6, "learning_rate": 8.175087008943439e-05, "loss": 0.0955, "step": 98370 }, { "epoch": 23.6, "learning_rate": 8.174740379169958e-05, "loss": 0.0622, "step": 98380 }, { "epoch": 23.6, "learning_rate": 8.174393723829855e-05, "loss": 0.097, "step": 98390 }, { "epoch": 23.61, "learning_rate": 8.174047042925921e-05, "loss": 0.0928, "step": 98400 }, { "epoch": 23.61, "learning_rate": 8.173700336460947e-05, "loss": 0.1104, "step": 98410 }, { "epoch": 23.61, "learning_rate": 8.173353604437727e-05, "loss": 0.1197, "step": 98420 }, { "epoch": 23.61, "learning_rate": 8.173006846859054e-05, "loss": 0.0908, "step": 98430 }, { "epoch": 23.61, "learning_rate": 8.172660063727718e-05, "loss": 0.1244, "step": 98440 }, { "epoch": 23.62, "learning_rate": 8.172313255046511e-05, "loss": 0.055, "step": 98450 }, { "epoch": 23.62, "learning_rate": 8.171966420818228e-05, "loss": 0.0949, "step": 98460 }, { "epoch": 23.62, "learning_rate": 8.171619561045661e-05, "loss": 0.0756, "step": 98470 }, { "epoch": 23.62, "learning_rate": 8.171272675731605e-05, "loss": 0.0722, "step": 98480 }, { "epoch": 23.63, "learning_rate": 8.170925764878852e-05, "loss": 0.079, "step": 98490 }, { "epoch": 23.63, "learning_rate": 8.170578828490196e-05, "loss": 0.0933, "step": 98500 }, { "epoch": 23.63, "learning_rate": 8.170231866568429e-05, "loss": 0.0643, "step": 98510 }, { "epoch": 23.63, "learning_rate": 8.169884879116351e-05, "loss": 0.0665, "step": 98520 }, { "epoch": 23.64, "learning_rate": 8.169537866136749e-05, "loss": 0.0713, "step": 98530 }, { "epoch": 23.64, "learning_rate": 8.169190827632423e-05, "loss": 0.0687, "step": 98540 }, { "epoch": 23.64, "learning_rate": 8.168843763606165e-05, "loss": 0.0998, "step": 98550 }, { "epoch": 23.64, "learning_rate": 8.16849667406077e-05, "loss": 0.0839, "step": 98560 }, { "epoch": 23.64, "learning_rate": 8.168149558999036e-05, "loss": 0.0884, "step": 98570 }, { "epoch": 23.65, "learning_rate": 8.167802418423754e-05, "loss": 0.0731, "step": 98580 }, { "epoch": 23.65, "learning_rate": 8.167455252337723e-05, "loss": 0.1089, "step": 98590 }, { "epoch": 23.65, "learning_rate": 8.167108060743736e-05, "loss": 0.1282, "step": 98600 }, { "epoch": 23.65, "learning_rate": 8.166760843644592e-05, "loss": 0.053, "step": 98610 }, { "epoch": 23.66, "learning_rate": 8.166413601043086e-05, "loss": 0.1049, "step": 98620 }, { "epoch": 23.66, "learning_rate": 8.166066332942013e-05, "loss": 0.0934, "step": 98630 }, { "epoch": 23.66, "learning_rate": 8.165719039344172e-05, "loss": 0.0612, "step": 98640 }, { "epoch": 23.66, "learning_rate": 8.165371720252357e-05, "loss": 0.088, "step": 98650 }, { "epoch": 23.67, "learning_rate": 8.165024375669367e-05, "loss": 0.0585, "step": 98660 }, { "epoch": 23.67, "learning_rate": 8.164677005598e-05, "loss": 0.1102, "step": 98670 }, { "epoch": 23.67, "learning_rate": 8.16432961004105e-05, "loss": 0.0744, "step": 98680 }, { "epoch": 23.67, "learning_rate": 8.163982189001318e-05, "loss": 0.0682, "step": 98690 }, { "epoch": 23.67, "learning_rate": 8.163634742481601e-05, "loss": 0.1136, "step": 98700 }, { "epoch": 23.68, "learning_rate": 8.163287270484697e-05, "loss": 0.1123, "step": 98710 }, { "epoch": 23.68, "learning_rate": 8.162939773013402e-05, "loss": 0.0923, "step": 98720 }, { "epoch": 23.68, "learning_rate": 8.162592250070517e-05, "loss": 0.0931, "step": 98730 }, { "epoch": 23.68, "learning_rate": 8.162244701658842e-05, "loss": 0.0409, "step": 98740 }, { "epoch": 23.69, "learning_rate": 8.161897127781171e-05, "loss": 0.0794, "step": 98750 }, { "epoch": 23.69, "learning_rate": 8.161549528440307e-05, "loss": 0.0866, "step": 98760 }, { "epoch": 23.69, "learning_rate": 8.161201903639048e-05, "loss": 0.0753, "step": 98770 }, { "epoch": 23.69, "learning_rate": 8.160854253380196e-05, "loss": 0.0901, "step": 98780 }, { "epoch": 23.69, "learning_rate": 8.160506577666546e-05, "loss": 0.0902, "step": 98790 }, { "epoch": 23.7, "learning_rate": 8.1601588765009e-05, "loss": 0.0614, "step": 98800 }, { "epoch": 23.7, "learning_rate": 8.159811149886059e-05, "loss": 0.06, "step": 98810 }, { "epoch": 23.7, "learning_rate": 8.159463397824823e-05, "loss": 0.1009, "step": 98820 }, { "epoch": 23.7, "learning_rate": 8.159115620319991e-05, "loss": 0.0855, "step": 98830 }, { "epoch": 23.71, "learning_rate": 8.158767817374365e-05, "loss": 0.0682, "step": 98840 }, { "epoch": 23.71, "learning_rate": 8.158419988990745e-05, "loss": 0.0766, "step": 98850 }, { "epoch": 23.71, "learning_rate": 8.158072135171935e-05, "loss": 0.0815, "step": 98860 }, { "epoch": 23.71, "learning_rate": 8.15772425592073e-05, "loss": 0.0747, "step": 98870 }, { "epoch": 23.72, "learning_rate": 8.157376351239941e-05, "loss": 0.0762, "step": 98880 }, { "epoch": 23.72, "learning_rate": 8.15702842113236e-05, "loss": 0.0594, "step": 98890 }, { "epoch": 23.72, "learning_rate": 8.156680465600796e-05, "loss": 0.1036, "step": 98900 }, { "epoch": 23.72, "learning_rate": 8.156332484648048e-05, "loss": 0.0819, "step": 98910 }, { "epoch": 23.72, "learning_rate": 8.155984478276917e-05, "loss": 0.1569, "step": 98920 }, { "epoch": 23.73, "learning_rate": 8.15563644649021e-05, "loss": 0.1093, "step": 98930 }, { "epoch": 23.73, "learning_rate": 8.155288389290724e-05, "loss": 0.0842, "step": 98940 }, { "epoch": 23.73, "learning_rate": 8.154940306681268e-05, "loss": 0.0722, "step": 98950 }, { "epoch": 23.73, "learning_rate": 8.154592198664639e-05, "loss": 0.0907, "step": 98960 }, { "epoch": 23.74, "learning_rate": 8.154244065243646e-05, "loss": 0.0472, "step": 98970 }, { "epoch": 23.74, "learning_rate": 8.153895906421088e-05, "loss": 0.0903, "step": 98980 }, { "epoch": 23.74, "learning_rate": 8.153547722199773e-05, "loss": 0.0827, "step": 98990 }, { "epoch": 23.74, "learning_rate": 8.153199512582501e-05, "loss": 0.0907, "step": 99000 }, { "epoch": 23.75, "learning_rate": 8.152851277572079e-05, "loss": 0.0601, "step": 99010 }, { "epoch": 23.75, "learning_rate": 8.15250301717131e-05, "loss": 0.0745, "step": 99020 }, { "epoch": 23.75, "learning_rate": 8.152154731383e-05, "loss": 0.0536, "step": 99030 }, { "epoch": 23.75, "learning_rate": 8.15180642020995e-05, "loss": 0.1206, "step": 99040 }, { "epoch": 23.75, "learning_rate": 8.151458083654971e-05, "loss": 0.0809, "step": 99050 }, { "epoch": 23.76, "learning_rate": 8.151109721720863e-05, "loss": 0.0581, "step": 99060 }, { "epoch": 23.76, "learning_rate": 8.150761334410435e-05, "loss": 0.0735, "step": 99070 }, { "epoch": 23.76, "learning_rate": 8.15041292172649e-05, "loss": 0.0566, "step": 99080 }, { "epoch": 23.76, "learning_rate": 8.150064483671834e-05, "loss": 0.1211, "step": 99090 }, { "epoch": 23.77, "learning_rate": 8.149716020249273e-05, "loss": 0.0828, "step": 99100 }, { "epoch": 23.77, "learning_rate": 8.149367531461619e-05, "loss": 0.058, "step": 99110 }, { "epoch": 23.77, "learning_rate": 8.149019017311668e-05, "loss": 0.1082, "step": 99120 }, { "epoch": 23.77, "learning_rate": 8.148670477802235e-05, "loss": 0.0829, "step": 99130 }, { "epoch": 23.77, "learning_rate": 8.148321912936123e-05, "loss": 0.0898, "step": 99140 }, { "epoch": 23.78, "learning_rate": 8.14797332271614e-05, "loss": 0.0594, "step": 99150 }, { "epoch": 23.78, "learning_rate": 8.147624707145094e-05, "loss": 0.0861, "step": 99160 }, { "epoch": 23.78, "learning_rate": 8.147276066225791e-05, "loss": 0.0908, "step": 99170 }, { "epoch": 23.78, "learning_rate": 8.14692739996104e-05, "loss": 0.061, "step": 99180 }, { "epoch": 23.79, "learning_rate": 8.146578708353647e-05, "loss": 0.0825, "step": 99190 }, { "epoch": 23.79, "learning_rate": 8.146229991406422e-05, "loss": 0.1108, "step": 99200 }, { "epoch": 23.79, "learning_rate": 8.145881249122173e-05, "loss": 0.0864, "step": 99210 }, { "epoch": 23.79, "learning_rate": 8.145532481503706e-05, "loss": 0.0854, "step": 99220 }, { "epoch": 23.8, "learning_rate": 8.145183688553833e-05, "loss": 0.0772, "step": 99230 }, { "epoch": 23.8, "learning_rate": 8.144834870275361e-05, "loss": 0.0752, "step": 99240 }, { "epoch": 23.8, "learning_rate": 8.1444860266711e-05, "loss": 0.0618, "step": 99250 }, { "epoch": 23.8, "learning_rate": 8.144137157743861e-05, "loss": 0.049, "step": 99260 }, { "epoch": 23.8, "learning_rate": 8.143788263496448e-05, "loss": 0.0799, "step": 99270 }, { "epoch": 23.81, "learning_rate": 8.143439343931676e-05, "loss": 0.0528, "step": 99280 }, { "epoch": 23.81, "learning_rate": 8.143090399052352e-05, "loss": 0.0645, "step": 99290 }, { "epoch": 23.81, "learning_rate": 8.142741428861289e-05, "loss": 0.0872, "step": 99300 }, { "epoch": 23.81, "learning_rate": 8.142392433361293e-05, "loss": 0.0626, "step": 99310 }, { "epoch": 23.82, "learning_rate": 8.142043412555178e-05, "loss": 0.0589, "step": 99320 }, { "epoch": 23.82, "learning_rate": 8.141694366445754e-05, "loss": 0.0583, "step": 99330 }, { "epoch": 23.82, "learning_rate": 8.141345295035832e-05, "loss": 0.0886, "step": 99340 }, { "epoch": 23.82, "learning_rate": 8.140996198328221e-05, "loss": 0.0599, "step": 99350 }, { "epoch": 23.83, "learning_rate": 8.140647076325734e-05, "loss": 0.0622, "step": 99360 }, { "epoch": 23.83, "learning_rate": 8.140297929031184e-05, "loss": 0.0857, "step": 99370 }, { "epoch": 23.83, "learning_rate": 8.139948756447379e-05, "loss": 0.0719, "step": 99380 }, { "epoch": 23.83, "learning_rate": 8.139599558577135e-05, "loss": 0.0665, "step": 99390 }, { "epoch": 23.83, "learning_rate": 8.139250335423261e-05, "loss": 0.0539, "step": 99400 }, { "epoch": 23.84, "learning_rate": 8.138901086988572e-05, "loss": 0.0466, "step": 99410 }, { "epoch": 23.84, "learning_rate": 8.138551813275879e-05, "loss": 0.1406, "step": 99420 }, { "epoch": 23.84, "learning_rate": 8.138202514287995e-05, "loss": 0.0902, "step": 99430 }, { "epoch": 23.84, "learning_rate": 8.137853190027733e-05, "loss": 0.0971, "step": 99440 }, { "epoch": 23.85, "learning_rate": 8.137503840497905e-05, "loss": 0.0623, "step": 99450 }, { "epoch": 23.85, "learning_rate": 8.137154465701326e-05, "loss": 0.0579, "step": 99460 }, { "epoch": 23.85, "learning_rate": 8.136805065640809e-05, "loss": 0.0535, "step": 99470 }, { "epoch": 23.85, "learning_rate": 8.136455640319167e-05, "loss": 0.087, "step": 99480 }, { "epoch": 23.85, "learning_rate": 8.136106189739217e-05, "loss": 0.0642, "step": 99490 }, { "epoch": 23.86, "learning_rate": 8.135756713903768e-05, "loss": 0.0734, "step": 99500 }, { "epoch": 23.86, "learning_rate": 8.13540721281564e-05, "loss": 0.0689, "step": 99510 }, { "epoch": 23.86, "learning_rate": 8.135057686477643e-05, "loss": 0.0649, "step": 99520 }, { "epoch": 23.86, "learning_rate": 8.134708134892593e-05, "loss": 0.1012, "step": 99530 }, { "epoch": 23.87, "learning_rate": 8.134358558063308e-05, "loss": 0.0943, "step": 99540 }, { "epoch": 23.87, "learning_rate": 8.1340089559926e-05, "loss": 0.0838, "step": 99550 }, { "epoch": 23.87, "learning_rate": 8.133659328683284e-05, "loss": 0.0684, "step": 99560 }, { "epoch": 23.87, "learning_rate": 8.133309676138177e-05, "loss": 0.0684, "step": 99570 }, { "epoch": 23.88, "learning_rate": 8.132959998360096e-05, "loss": 0.0757, "step": 99580 }, { "epoch": 23.88, "learning_rate": 8.132610295351854e-05, "loss": 0.0581, "step": 99590 }, { "epoch": 23.88, "learning_rate": 8.13226056711627e-05, "loss": 0.043, "step": 99600 }, { "epoch": 23.88, "learning_rate": 8.131910813656158e-05, "loss": 0.0584, "step": 99610 }, { "epoch": 23.88, "learning_rate": 8.131561034974338e-05, "loss": 0.0938, "step": 99620 }, { "epoch": 23.89, "learning_rate": 8.131211231073622e-05, "loss": 0.0534, "step": 99630 }, { "epoch": 23.89, "learning_rate": 8.13086140195683e-05, "loss": 0.075, "step": 99640 }, { "epoch": 23.89, "learning_rate": 8.13051154762678e-05, "loss": 0.0775, "step": 99650 }, { "epoch": 23.89, "learning_rate": 8.13016166808629e-05, "loss": 0.0576, "step": 99660 }, { "epoch": 23.9, "learning_rate": 8.129811763338173e-05, "loss": 0.0773, "step": 99670 }, { "epoch": 23.9, "learning_rate": 8.129461833385252e-05, "loss": 0.0789, "step": 99680 }, { "epoch": 23.9, "learning_rate": 8.12911187823034e-05, "loss": 0.0597, "step": 99690 }, { "epoch": 23.9, "learning_rate": 8.12876189787626e-05, "loss": 0.0724, "step": 99700 }, { "epoch": 23.91, "learning_rate": 8.128411892325827e-05, "loss": 0.0671, "step": 99710 }, { "epoch": 23.91, "learning_rate": 8.128061861581863e-05, "loss": 0.0682, "step": 99720 }, { "epoch": 23.91, "learning_rate": 8.127711805647184e-05, "loss": 0.0893, "step": 99730 }, { "epoch": 23.91, "learning_rate": 8.127361724524612e-05, "loss": 0.0735, "step": 99740 }, { "epoch": 23.91, "learning_rate": 8.127011618216962e-05, "loss": 0.0576, "step": 99750 }, { "epoch": 23.92, "learning_rate": 8.126661486727056e-05, "loss": 0.0739, "step": 99760 }, { "epoch": 23.92, "learning_rate": 8.126311330057714e-05, "loss": 0.0991, "step": 99770 }, { "epoch": 23.92, "learning_rate": 8.125961148211753e-05, "loss": 0.0828, "step": 99780 }, { "epoch": 23.92, "learning_rate": 8.125610941191998e-05, "loss": 0.111, "step": 99790 }, { "epoch": 23.93, "learning_rate": 8.125260709001266e-05, "loss": 0.0598, "step": 99800 }, { "epoch": 23.93, "learning_rate": 8.124910451642378e-05, "loss": 0.0759, "step": 99810 }, { "epoch": 23.93, "learning_rate": 8.124560169118154e-05, "loss": 0.0711, "step": 99820 }, { "epoch": 23.93, "learning_rate": 8.124209861431415e-05, "loss": 0.0517, "step": 99830 }, { "epoch": 23.93, "learning_rate": 8.123859528584985e-05, "loss": 0.0669, "step": 99840 }, { "epoch": 23.94, "learning_rate": 8.123509170581683e-05, "loss": 0.0521, "step": 99850 }, { "epoch": 23.94, "learning_rate": 8.123158787424327e-05, "loss": 0.0573, "step": 99860 }, { "epoch": 23.94, "learning_rate": 8.122808379115745e-05, "loss": 0.0798, "step": 99870 }, { "epoch": 23.94, "learning_rate": 8.122457945658755e-05, "loss": 0.0431, "step": 99880 }, { "epoch": 23.95, "learning_rate": 8.12210748705618e-05, "loss": 0.0685, "step": 99890 }, { "epoch": 23.95, "learning_rate": 8.121757003310844e-05, "loss": 0.058, "step": 99900 }, { "epoch": 23.95, "learning_rate": 8.121406494425565e-05, "loss": 0.0771, "step": 99910 }, { "epoch": 24.0, "learning_rate": 8.121055960403171e-05, "loss": 0.047, "step": 99920 }, { "epoch": 24.0, "learning_rate": 8.120705401246483e-05, "loss": 0.0699, "step": 99930 }, { "epoch": 24.01, "learning_rate": 8.120354816958321e-05, "loss": 0.0708, "step": 99940 }, { "epoch": 24.01, "learning_rate": 8.120004207541511e-05, "loss": 0.056, "step": 99950 }, { "epoch": 24.01, "learning_rate": 8.119653572998877e-05, "loss": 0.0776, "step": 99960 }, { "epoch": 24.01, "learning_rate": 8.119302913333244e-05, "loss": 0.0642, "step": 99970 }, { "epoch": 24.02, "learning_rate": 8.118952228547432e-05, "loss": 0.0671, "step": 99980 }, { "epoch": 24.02, "learning_rate": 8.118601518644267e-05, "loss": 0.0717, "step": 99990 }, { "epoch": 24.02, "learning_rate": 8.118250783626575e-05, "loss": 0.0653, "step": 100000 }, { "epoch": 24.02, "learning_rate": 8.117900023497178e-05, "loss": 0.0844, "step": 100010 }, { "epoch": 24.02, "learning_rate": 8.117549238258901e-05, "loss": 0.0553, "step": 100020 }, { "epoch": 24.03, "learning_rate": 8.117198427914571e-05, "loss": 0.0597, "step": 100030 }, { "epoch": 24.03, "learning_rate": 8.11684759246701e-05, "loss": 0.0626, "step": 100040 }, { "epoch": 24.03, "learning_rate": 8.116496731919046e-05, "loss": 0.0807, "step": 100050 }, { "epoch": 24.03, "learning_rate": 8.116145846273504e-05, "loss": 0.053, "step": 100060 }, { "epoch": 24.04, "learning_rate": 8.115794935533207e-05, "loss": 0.0603, "step": 100070 }, { "epoch": 24.04, "learning_rate": 8.115443999700987e-05, "loss": 0.0709, "step": 100080 }, { "epoch": 24.04, "learning_rate": 8.115093038779662e-05, "loss": 0.0719, "step": 100090 }, { "epoch": 24.04, "learning_rate": 8.114742052772067e-05, "loss": 0.0704, "step": 100100 }, { "epoch": 24.05, "learning_rate": 8.114391041681022e-05, "loss": 0.0586, "step": 100110 }, { "epoch": 24.05, "learning_rate": 8.114040005509356e-05, "loss": 0.0592, "step": 100120 }, { "epoch": 24.05, "learning_rate": 8.113688944259896e-05, "loss": 0.0528, "step": 100130 }, { "epoch": 24.05, "learning_rate": 8.113337857935468e-05, "loss": 0.088, "step": 100140 }, { "epoch": 24.05, "learning_rate": 8.112986746538903e-05, "loss": 0.0788, "step": 100150 }, { "epoch": 24.06, "learning_rate": 8.112635610073025e-05, "loss": 0.0627, "step": 100160 }, { "epoch": 24.06, "learning_rate": 8.112284448540661e-05, "loss": 0.0906, "step": 100170 }, { "epoch": 24.06, "learning_rate": 8.111933261944642e-05, "loss": 0.0864, "step": 100180 }, { "epoch": 24.06, "learning_rate": 8.111582050287796e-05, "loss": 0.0469, "step": 100190 }, { "epoch": 24.07, "learning_rate": 8.111230813572948e-05, "loss": 0.0524, "step": 100200 }, { "epoch": 24.07, "learning_rate": 8.11087955180293e-05, "loss": 0.0783, "step": 100210 }, { "epoch": 24.07, "learning_rate": 8.110528264980569e-05, "loss": 0.0901, "step": 100220 }, { "epoch": 24.07, "learning_rate": 8.110176953108695e-05, "loss": 0.0784, "step": 100230 }, { "epoch": 24.07, "learning_rate": 8.109825616190136e-05, "loss": 0.067, "step": 100240 }, { "epoch": 24.08, "learning_rate": 8.109474254227721e-05, "loss": 0.062, "step": 100250 }, { "epoch": 24.08, "learning_rate": 8.109122867224282e-05, "loss": 0.0519, "step": 100260 }, { "epoch": 24.08, "learning_rate": 8.108771455182647e-05, "loss": 0.0931, "step": 100270 }, { "epoch": 24.08, "learning_rate": 8.108420018105646e-05, "loss": 0.0658, "step": 100280 }, { "epoch": 24.09, "learning_rate": 8.108068555996111e-05, "loss": 0.0878, "step": 100290 }, { "epoch": 24.09, "learning_rate": 8.107717068856868e-05, "loss": 0.0626, "step": 100300 }, { "epoch": 24.09, "learning_rate": 8.107365556690752e-05, "loss": 0.0636, "step": 100310 }, { "epoch": 24.09, "learning_rate": 8.107014019500592e-05, "loss": 0.0664, "step": 100320 }, { "epoch": 24.1, "learning_rate": 8.10666245728922e-05, "loss": 0.0474, "step": 100330 }, { "epoch": 24.1, "learning_rate": 8.106310870059466e-05, "loss": 0.0705, "step": 100340 }, { "epoch": 24.1, "learning_rate": 8.105959257814161e-05, "loss": 0.0641, "step": 100350 }, { "epoch": 24.1, "learning_rate": 8.105607620556137e-05, "loss": 0.0639, "step": 100360 }, { "epoch": 24.1, "learning_rate": 8.105255958288227e-05, "loss": 0.0373, "step": 100370 }, { "epoch": 24.11, "learning_rate": 8.104904271013262e-05, "loss": 0.0786, "step": 100380 }, { "epoch": 24.11, "learning_rate": 8.104552558734075e-05, "loss": 0.051, "step": 100390 }, { "epoch": 24.11, "learning_rate": 8.104200821453496e-05, "loss": 0.062, "step": 100400 }, { "epoch": 24.11, "learning_rate": 8.10384905917436e-05, "loss": 0.0743, "step": 100410 }, { "epoch": 24.12, "learning_rate": 8.103497271899499e-05, "loss": 0.0665, "step": 100420 }, { "epoch": 24.12, "learning_rate": 8.103145459631745e-05, "loss": 0.0556, "step": 100430 }, { "epoch": 24.12, "learning_rate": 8.102793622373933e-05, "loss": 0.056, "step": 100440 }, { "epoch": 24.12, "learning_rate": 8.102441760128896e-05, "loss": 0.0606, "step": 100450 }, { "epoch": 24.13, "learning_rate": 8.102089872899467e-05, "loss": 0.0653, "step": 100460 }, { "epoch": 24.13, "learning_rate": 8.101737960688479e-05, "loss": 0.0533, "step": 100470 }, { "epoch": 24.13, "learning_rate": 8.101386023498769e-05, "loss": 0.0614, "step": 100480 }, { "epoch": 24.13, "learning_rate": 8.101034061333167e-05, "loss": 0.0622, "step": 100490 }, { "epoch": 24.13, "learning_rate": 8.100682074194511e-05, "loss": 0.0868, "step": 100500 }, { "epoch": 24.14, "learning_rate": 8.100330062085634e-05, "loss": 0.0527, "step": 100510 }, { "epoch": 24.14, "learning_rate": 8.099978025009369e-05, "loss": 0.0559, "step": 100520 }, { "epoch": 24.14, "learning_rate": 8.099625962968556e-05, "loss": 0.0682, "step": 100530 }, { "epoch": 24.14, "learning_rate": 8.099273875966026e-05, "loss": 0.0713, "step": 100540 }, { "epoch": 24.15, "learning_rate": 8.098921764004616e-05, "loss": 0.0932, "step": 100550 }, { "epoch": 24.15, "learning_rate": 8.09856962708716e-05, "loss": 0.059, "step": 100560 }, { "epoch": 24.15, "learning_rate": 8.098217465216495e-05, "loss": 0.089, "step": 100570 }, { "epoch": 24.15, "learning_rate": 8.097865278395457e-05, "loss": 0.0772, "step": 100580 }, { "epoch": 24.15, "learning_rate": 8.097513066626885e-05, "loss": 0.0797, "step": 100590 }, { "epoch": 24.16, "learning_rate": 8.09716082991361e-05, "loss": 0.0643, "step": 100600 }, { "epoch": 24.16, "learning_rate": 8.096808568258471e-05, "loss": 0.0963, "step": 100610 }, { "epoch": 24.16, "learning_rate": 8.096456281664307e-05, "loss": 0.0558, "step": 100620 }, { "epoch": 24.16, "learning_rate": 8.096103970133952e-05, "loss": 0.0671, "step": 100630 }, { "epoch": 24.17, "learning_rate": 8.095751633670243e-05, "loss": 0.0521, "step": 100640 }, { "epoch": 24.17, "learning_rate": 8.09539927227602e-05, "loss": 0.0443, "step": 100650 }, { "epoch": 24.17, "learning_rate": 8.09504688595412e-05, "loss": 0.0775, "step": 100660 }, { "epoch": 24.17, "learning_rate": 8.094694474707379e-05, "loss": 0.0407, "step": 100670 }, { "epoch": 24.18, "learning_rate": 8.094342038538636e-05, "loss": 0.0807, "step": 100680 }, { "epoch": 24.18, "learning_rate": 8.093989577450731e-05, "loss": 0.0835, "step": 100690 }, { "epoch": 24.18, "learning_rate": 8.0936370914465e-05, "loss": 0.0611, "step": 100700 }, { "epoch": 24.18, "learning_rate": 8.093284580528782e-05, "loss": 0.0908, "step": 100710 }, { "epoch": 24.18, "learning_rate": 8.092932044700416e-05, "loss": 0.0533, "step": 100720 }, { "epoch": 24.19, "learning_rate": 8.092579483964242e-05, "loss": 0.0713, "step": 100730 }, { "epoch": 24.19, "learning_rate": 8.092226898323097e-05, "loss": 0.052, "step": 100740 }, { "epoch": 24.19, "learning_rate": 8.091874287779823e-05, "loss": 0.0617, "step": 100750 }, { "epoch": 24.19, "learning_rate": 8.091521652337259e-05, "loss": 0.072, "step": 100760 }, { "epoch": 24.2, "learning_rate": 8.091168991998243e-05, "loss": 0.0887, "step": 100770 }, { "epoch": 24.2, "learning_rate": 8.090816306765617e-05, "loss": 0.0919, "step": 100780 }, { "epoch": 24.2, "learning_rate": 8.090463596642222e-05, "loss": 0.059, "step": 100790 }, { "epoch": 24.2, "learning_rate": 8.090110861630894e-05, "loss": 0.0752, "step": 100800 }, { "epoch": 24.21, "learning_rate": 8.089758101734479e-05, "loss": 0.0478, "step": 100810 }, { "epoch": 24.21, "learning_rate": 8.089405316955814e-05, "loss": 0.0771, "step": 100820 }, { "epoch": 24.21, "learning_rate": 8.089052507297743e-05, "loss": 0.0637, "step": 100830 }, { "epoch": 24.21, "learning_rate": 8.088699672763105e-05, "loss": 0.0562, "step": 100840 }, { "epoch": 24.21, "learning_rate": 8.088346813354741e-05, "loss": 0.0639, "step": 100850 }, { "epoch": 24.22, "learning_rate": 8.087993929075495e-05, "loss": 0.0649, "step": 100860 }, { "epoch": 24.22, "learning_rate": 8.087641019928207e-05, "loss": 0.076, "step": 100870 }, { "epoch": 24.22, "learning_rate": 8.08728808591572e-05, "loss": 0.066, "step": 100880 }, { "epoch": 24.22, "learning_rate": 8.086935127040876e-05, "loss": 0.0446, "step": 100890 }, { "epoch": 24.23, "learning_rate": 8.086582143306516e-05, "loss": 0.0809, "step": 100900 }, { "epoch": 24.23, "learning_rate": 8.086229134715486e-05, "loss": 0.0701, "step": 100910 }, { "epoch": 24.23, "learning_rate": 8.085876101270624e-05, "loss": 0.0795, "step": 100920 }, { "epoch": 24.23, "learning_rate": 8.085523042974779e-05, "loss": 0.0714, "step": 100930 }, { "epoch": 24.23, "learning_rate": 8.085169959830788e-05, "loss": 0.0668, "step": 100940 }, { "epoch": 24.24, "learning_rate": 8.084816851841498e-05, "loss": 0.0432, "step": 100950 }, { "epoch": 24.24, "learning_rate": 8.084463719009753e-05, "loss": 0.0919, "step": 100960 }, { "epoch": 24.24, "learning_rate": 8.084110561338394e-05, "loss": 0.0941, "step": 100970 }, { "epoch": 24.24, "learning_rate": 8.08375737883027e-05, "loss": 0.0473, "step": 100980 }, { "epoch": 24.25, "learning_rate": 8.08340417148822e-05, "loss": 0.0629, "step": 100990 }, { "epoch": 24.25, "learning_rate": 8.083050939315091e-05, "loss": 0.064, "step": 101000 }, { "epoch": 24.25, "learning_rate": 8.082697682313727e-05, "loss": 0.0383, "step": 101010 }, { "epoch": 24.25, "learning_rate": 8.082344400486972e-05, "loss": 0.0603, "step": 101020 }, { "epoch": 24.26, "learning_rate": 8.081991093837673e-05, "loss": 0.0505, "step": 101030 }, { "epoch": 24.26, "learning_rate": 8.081637762368675e-05, "loss": 0.0754, "step": 101040 }, { "epoch": 24.26, "learning_rate": 8.081284406082821e-05, "loss": 0.0662, "step": 101050 }, { "epoch": 24.26, "learning_rate": 8.080931024982959e-05, "loss": 0.0572, "step": 101060 }, { "epoch": 24.26, "learning_rate": 8.080577619071935e-05, "loss": 0.0786, "step": 101070 }, { "epoch": 24.27, "learning_rate": 8.080224188352593e-05, "loss": 0.0836, "step": 101080 }, { "epoch": 24.27, "learning_rate": 8.079870732827781e-05, "loss": 0.0975, "step": 101090 }, { "epoch": 24.27, "learning_rate": 8.079517252500344e-05, "loss": 0.0829, "step": 101100 }, { "epoch": 24.27, "learning_rate": 8.079163747373129e-05, "loss": 0.0582, "step": 101110 }, { "epoch": 24.28, "learning_rate": 8.078810217448986e-05, "loss": 0.0562, "step": 101120 }, { "epoch": 24.28, "learning_rate": 8.078456662730755e-05, "loss": 0.0698, "step": 101130 }, { "epoch": 24.28, "learning_rate": 8.07810308322129e-05, "loss": 0.0587, "step": 101140 }, { "epoch": 24.28, "learning_rate": 8.077749478923438e-05, "loss": 0.0594, "step": 101150 }, { "epoch": 24.29, "learning_rate": 8.077395849840042e-05, "loss": 0.0964, "step": 101160 }, { "epoch": 24.29, "learning_rate": 8.077042195973952e-05, "loss": 0.074, "step": 101170 }, { "epoch": 24.29, "learning_rate": 8.076688517328017e-05, "loss": 0.0734, "step": 101180 }, { "epoch": 24.29, "learning_rate": 8.076334813905084e-05, "loss": 0.0592, "step": 101190 }, { "epoch": 24.29, "learning_rate": 8.075981085708004e-05, "loss": 0.071, "step": 101200 }, { "epoch": 24.3, "learning_rate": 8.075627332739621e-05, "loss": 0.0563, "step": 101210 }, { "epoch": 24.3, "learning_rate": 8.07527355500279e-05, "loss": 0.0821, "step": 101220 }, { "epoch": 24.3, "learning_rate": 8.074919752500351e-05, "loss": 0.0556, "step": 101230 }, { "epoch": 24.3, "learning_rate": 8.074565925235164e-05, "loss": 0.0494, "step": 101240 }, { "epoch": 24.31, "learning_rate": 8.074212073210072e-05, "loss": 0.0691, "step": 101250 }, { "epoch": 24.31, "learning_rate": 8.073858196427924e-05, "loss": 0.0645, "step": 101260 }, { "epoch": 24.31, "learning_rate": 8.073504294891572e-05, "loss": 0.0811, "step": 101270 }, { "epoch": 24.31, "learning_rate": 8.073150368603866e-05, "loss": 0.0613, "step": 101280 }, { "epoch": 24.31, "learning_rate": 8.072796417567656e-05, "loss": 0.0506, "step": 101290 }, { "epoch": 24.32, "learning_rate": 8.072442441785792e-05, "loss": 0.0513, "step": 101300 }, { "epoch": 24.32, "learning_rate": 8.072088441261125e-05, "loss": 0.0572, "step": 101310 }, { "epoch": 24.32, "learning_rate": 8.071734415996506e-05, "loss": 0.0447, "step": 101320 }, { "epoch": 24.32, "learning_rate": 8.071380365994785e-05, "loss": 0.0788, "step": 101330 }, { "epoch": 24.33, "learning_rate": 8.071026291258814e-05, "loss": 0.0597, "step": 101340 }, { "epoch": 24.33, "learning_rate": 8.070672191791445e-05, "loss": 0.0431, "step": 101350 }, { "epoch": 24.33, "learning_rate": 8.070318067595528e-05, "loss": 0.076, "step": 101360 }, { "epoch": 24.33, "learning_rate": 8.069963918673916e-05, "loss": 0.0673, "step": 101370 }, { "epoch": 24.34, "learning_rate": 8.069609745029462e-05, "loss": 0.0749, "step": 101380 }, { "epoch": 24.34, "learning_rate": 8.069255546665015e-05, "loss": 0.0636, "step": 101390 }, { "epoch": 24.34, "learning_rate": 8.068901323583432e-05, "loss": 0.0736, "step": 101400 }, { "epoch": 24.34, "learning_rate": 8.06854707578756e-05, "loss": 0.0668, "step": 101410 }, { "epoch": 24.34, "learning_rate": 8.068192803280255e-05, "loss": 0.0492, "step": 101420 }, { "epoch": 24.35, "learning_rate": 8.067838506064372e-05, "loss": 0.0554, "step": 101430 }, { "epoch": 24.35, "learning_rate": 8.067484184142759e-05, "loss": 0.0537, "step": 101440 }, { "epoch": 24.35, "learning_rate": 8.067129837518273e-05, "loss": 0.0745, "step": 101450 }, { "epoch": 24.35, "learning_rate": 8.066775466193768e-05, "loss": 0.0369, "step": 101460 }, { "epoch": 24.36, "learning_rate": 8.066421070172098e-05, "loss": 0.0551, "step": 101470 }, { "epoch": 24.36, "learning_rate": 8.066066649456114e-05, "loss": 0.0671, "step": 101480 }, { "epoch": 24.36, "learning_rate": 8.065712204048672e-05, "loss": 0.0868, "step": 101490 }, { "epoch": 24.36, "learning_rate": 8.065357733952627e-05, "loss": 0.0551, "step": 101500 }, { "epoch": 24.37, "learning_rate": 8.065003239170832e-05, "loss": 0.0413, "step": 101510 }, { "epoch": 24.37, "learning_rate": 8.064648719706145e-05, "loss": 0.0728, "step": 101520 }, { "epoch": 24.37, "learning_rate": 8.064294175561417e-05, "loss": 0.0735, "step": 101530 }, { "epoch": 24.37, "learning_rate": 8.063939606739505e-05, "loss": 0.0936, "step": 101540 }, { "epoch": 24.37, "learning_rate": 8.063585013243265e-05, "loss": 0.0727, "step": 101550 }, { "epoch": 24.38, "learning_rate": 8.063230395075551e-05, "loss": 0.0881, "step": 101560 }, { "epoch": 24.38, "learning_rate": 8.06287575223922e-05, "loss": 0.0546, "step": 101570 }, { "epoch": 24.38, "learning_rate": 8.062521084737128e-05, "loss": 0.0948, "step": 101580 }, { "epoch": 24.38, "learning_rate": 8.06216639257213e-05, "loss": 0.0378, "step": 101590 }, { "epoch": 24.39, "learning_rate": 8.061811675747084e-05, "loss": 0.0796, "step": 101600 }, { "epoch": 24.39, "learning_rate": 8.061456934264848e-05, "loss": 0.0494, "step": 101610 }, { "epoch": 24.39, "learning_rate": 8.061102168128274e-05, "loss": 0.0672, "step": 101620 }, { "epoch": 24.39, "learning_rate": 8.06074737734022e-05, "loss": 0.0737, "step": 101630 }, { "epoch": 24.39, "learning_rate": 8.06039256190355e-05, "loss": 0.0519, "step": 101640 }, { "epoch": 24.4, "learning_rate": 8.060037721821112e-05, "loss": 0.0622, "step": 101650 }, { "epoch": 24.4, "learning_rate": 8.05968285709577e-05, "loss": 0.0733, "step": 101660 }, { "epoch": 24.4, "learning_rate": 8.059327967730377e-05, "loss": 0.0572, "step": 101670 }, { "epoch": 24.4, "learning_rate": 8.058973053727797e-05, "loss": 0.0466, "step": 101680 }, { "epoch": 24.41, "learning_rate": 8.058618115090881e-05, "loss": 0.0507, "step": 101690 }, { "epoch": 24.41, "learning_rate": 8.058263151822494e-05, "loss": 0.0443, "step": 101700 }, { "epoch": 24.41, "learning_rate": 8.057908163925489e-05, "loss": 0.0625, "step": 101710 }, { "epoch": 24.41, "learning_rate": 8.05755315140273e-05, "loss": 0.0637, "step": 101720 }, { "epoch": 24.42, "learning_rate": 8.057198114257072e-05, "loss": 0.0616, "step": 101730 }, { "epoch": 24.42, "learning_rate": 8.056843052491375e-05, "loss": 0.0654, "step": 101740 }, { "epoch": 24.42, "learning_rate": 8.056487966108499e-05, "loss": 0.0608, "step": 101750 }, { "epoch": 24.42, "learning_rate": 8.056132855111305e-05, "loss": 0.0442, "step": 101760 }, { "epoch": 24.42, "learning_rate": 8.05577771950265e-05, "loss": 0.0564, "step": 101770 }, { "epoch": 24.43, "learning_rate": 8.055422559285396e-05, "loss": 0.0644, "step": 101780 }, { "epoch": 24.43, "learning_rate": 8.055067374462401e-05, "loss": 0.076, "step": 101790 }, { "epoch": 24.43, "learning_rate": 8.054712165036528e-05, "loss": 0.0622, "step": 101800 }, { "epoch": 24.43, "learning_rate": 8.054356931010635e-05, "loss": 0.0791, "step": 101810 }, { "epoch": 24.44, "learning_rate": 8.054001672387585e-05, "loss": 0.0795, "step": 101820 }, { "epoch": 24.44, "learning_rate": 8.053646389170236e-05, "loss": 0.059, "step": 101830 }, { "epoch": 24.44, "learning_rate": 8.053291081361452e-05, "loss": 0.0751, "step": 101840 }, { "epoch": 24.44, "learning_rate": 8.052935748964095e-05, "loss": 0.0441, "step": 101850 }, { "epoch": 24.45, "learning_rate": 8.052580391981024e-05, "loss": 0.061, "step": 101860 }, { "epoch": 24.45, "learning_rate": 8.0522250104151e-05, "loss": 0.0541, "step": 101870 }, { "epoch": 24.45, "learning_rate": 8.051869604269188e-05, "loss": 0.0729, "step": 101880 }, { "epoch": 24.45, "learning_rate": 8.051514173546149e-05, "loss": 0.0676, "step": 101890 }, { "epoch": 24.45, "learning_rate": 8.051158718248845e-05, "loss": 0.0425, "step": 101900 }, { "epoch": 24.46, "learning_rate": 8.050803238380138e-05, "loss": 0.0533, "step": 101910 }, { "epoch": 24.46, "learning_rate": 8.050447733942892e-05, "loss": 0.0609, "step": 101920 }, { "epoch": 24.46, "learning_rate": 8.05009220493997e-05, "loss": 0.0504, "step": 101930 }, { "epoch": 24.46, "learning_rate": 8.049736651374233e-05, "loss": 0.093, "step": 101940 }, { "epoch": 24.47, "learning_rate": 8.049381073248545e-05, "loss": 0.0411, "step": 101950 }, { "epoch": 24.47, "learning_rate": 8.049025470565773e-05, "loss": 0.0657, "step": 101960 }, { "epoch": 24.47, "learning_rate": 8.048669843328776e-05, "loss": 0.0426, "step": 101970 }, { "epoch": 24.47, "learning_rate": 8.048314191540419e-05, "loss": 0.0645, "step": 101980 }, { "epoch": 24.47, "learning_rate": 8.047958515203569e-05, "loss": 0.0668, "step": 101990 }, { "epoch": 24.48, "learning_rate": 8.047602814321086e-05, "loss": 0.0804, "step": 102000 }, { "epoch": 24.48, "learning_rate": 8.04724708889584e-05, "loss": 0.0782, "step": 102010 }, { "epoch": 24.48, "learning_rate": 8.046891338930689e-05, "loss": 0.0736, "step": 102020 }, { "epoch": 24.48, "learning_rate": 8.046535564428504e-05, "loss": 0.0582, "step": 102030 }, { "epoch": 24.49, "learning_rate": 8.046179765392146e-05, "loss": 0.0652, "step": 102040 }, { "epoch": 24.49, "learning_rate": 8.045823941824481e-05, "loss": 0.0668, "step": 102050 }, { "epoch": 24.49, "learning_rate": 8.045468093728377e-05, "loss": 0.0749, "step": 102060 }, { "epoch": 24.49, "learning_rate": 8.045112221106697e-05, "loss": 0.0493, "step": 102070 }, { "epoch": 24.5, "learning_rate": 8.04475632396231e-05, "loss": 0.0657, "step": 102080 }, { "epoch": 24.5, "learning_rate": 8.044400402298078e-05, "loss": 0.0561, "step": 102090 }, { "epoch": 24.5, "learning_rate": 8.044044456116869e-05, "loss": 0.0702, "step": 102100 }, { "epoch": 24.5, "learning_rate": 8.043688485421552e-05, "loss": 0.0756, "step": 102110 }, { "epoch": 24.5, "learning_rate": 8.04333249021499e-05, "loss": 0.0599, "step": 102120 }, { "epoch": 24.51, "learning_rate": 8.042976470500049e-05, "loss": 0.0454, "step": 102130 }, { "epoch": 24.51, "learning_rate": 8.042620426279601e-05, "loss": 0.0693, "step": 102140 }, { "epoch": 24.51, "learning_rate": 8.042264357556511e-05, "loss": 0.0703, "step": 102150 }, { "epoch": 24.51, "learning_rate": 8.041908264333645e-05, "loss": 0.0505, "step": 102160 }, { "epoch": 24.52, "learning_rate": 8.041552146613872e-05, "loss": 0.0686, "step": 102170 }, { "epoch": 24.52, "learning_rate": 8.04119600440006e-05, "loss": 0.0409, "step": 102180 }, { "epoch": 24.52, "learning_rate": 8.040839837695075e-05, "loss": 0.0683, "step": 102190 }, { "epoch": 24.52, "learning_rate": 8.040483646501791e-05, "loss": 0.0877, "step": 102200 }, { "epoch": 24.53, "learning_rate": 8.040127430823068e-05, "loss": 0.1079, "step": 102210 }, { "epoch": 24.53, "learning_rate": 8.039771190661781e-05, "loss": 0.0587, "step": 102220 }, { "epoch": 24.53, "learning_rate": 8.039414926020797e-05, "loss": 0.0541, "step": 102230 }, { "epoch": 24.53, "learning_rate": 8.039058636902985e-05, "loss": 0.0742, "step": 102240 }, { "epoch": 24.53, "learning_rate": 8.038702323311214e-05, "loss": 0.0616, "step": 102250 }, { "epoch": 24.54, "learning_rate": 8.038345985248354e-05, "loss": 0.0794, "step": 102260 }, { "epoch": 24.54, "learning_rate": 8.037989622717274e-05, "loss": 0.1225, "step": 102270 }, { "epoch": 24.54, "learning_rate": 8.037633235720845e-05, "loss": 0.1009, "step": 102280 }, { "epoch": 24.54, "learning_rate": 8.037276824261935e-05, "loss": 0.0634, "step": 102290 }, { "epoch": 24.55, "learning_rate": 8.036920388343416e-05, "loss": 0.1059, "step": 102300 }, { "epoch": 24.55, "learning_rate": 8.036563927968157e-05, "loss": 0.073, "step": 102310 }, { "epoch": 24.55, "learning_rate": 8.03620744313903e-05, "loss": 0.0832, "step": 102320 }, { "epoch": 24.55, "learning_rate": 8.035850933858907e-05, "loss": 0.1102, "step": 102330 }, { "epoch": 24.55, "learning_rate": 8.035494400130654e-05, "loss": 0.0876, "step": 102340 }, { "epoch": 24.56, "learning_rate": 8.035137841957148e-05, "loss": 0.0633, "step": 102350 }, { "epoch": 24.56, "learning_rate": 8.034781259341257e-05, "loss": 0.0677, "step": 102360 }, { "epoch": 24.56, "learning_rate": 8.034424652285854e-05, "loss": 0.0639, "step": 102370 }, { "epoch": 24.56, "learning_rate": 8.034068020793809e-05, "loss": 0.1049, "step": 102380 }, { "epoch": 24.57, "learning_rate": 8.033711364867997e-05, "loss": 0.1312, "step": 102390 }, { "epoch": 24.57, "learning_rate": 8.033354684511287e-05, "loss": 0.0932, "step": 102400 }, { "epoch": 24.57, "learning_rate": 8.032997979726555e-05, "loss": 0.0852, "step": 102410 }, { "epoch": 24.57, "learning_rate": 8.03264125051667e-05, "loss": 0.0835, "step": 102420 }, { "epoch": 24.58, "learning_rate": 8.032284496884506e-05, "loss": 0.0846, "step": 102430 }, { "epoch": 24.58, "learning_rate": 8.031927718832938e-05, "loss": 0.0718, "step": 102440 }, { "epoch": 24.58, "learning_rate": 8.031570916364837e-05, "loss": 0.0539, "step": 102450 }, { "epoch": 24.58, "learning_rate": 8.031214089483077e-05, "loss": 0.07, "step": 102460 }, { "epoch": 24.58, "learning_rate": 8.03085723819053e-05, "loss": 0.0979, "step": 102470 }, { "epoch": 24.59, "learning_rate": 8.030500362490072e-05, "loss": 0.0762, "step": 102480 }, { "epoch": 24.59, "learning_rate": 8.030143462384576e-05, "loss": 0.0694, "step": 102490 }, { "epoch": 24.59, "learning_rate": 8.029786537876915e-05, "loss": 0.0913, "step": 102500 }, { "epoch": 24.59, "learning_rate": 8.029429588969968e-05, "loss": 0.0733, "step": 102510 }, { "epoch": 24.6, "learning_rate": 8.029072615666604e-05, "loss": 0.0807, "step": 102520 }, { "epoch": 24.6, "learning_rate": 8.028715617969702e-05, "loss": 0.0945, "step": 102530 }, { "epoch": 24.6, "learning_rate": 8.028358595882133e-05, "loss": 0.1037, "step": 102540 }, { "epoch": 24.6, "learning_rate": 8.028001549406774e-05, "loss": 0.0493, "step": 102550 }, { "epoch": 24.61, "learning_rate": 8.027644478546503e-05, "loss": 0.0667, "step": 102560 }, { "epoch": 24.61, "learning_rate": 8.027287383304189e-05, "loss": 0.0777, "step": 102570 }, { "epoch": 24.61, "learning_rate": 8.026930263682717e-05, "loss": 0.0809, "step": 102580 }, { "epoch": 24.61, "learning_rate": 8.026573119684953e-05, "loss": 0.0576, "step": 102590 }, { "epoch": 24.61, "learning_rate": 8.02621595131378e-05, "loss": 0.0798, "step": 102600 }, { "epoch": 24.62, "learning_rate": 8.025858758572071e-05, "loss": 0.0748, "step": 102610 }, { "epoch": 24.62, "learning_rate": 8.025501541462705e-05, "loss": 0.0819, "step": 102620 }, { "epoch": 24.62, "learning_rate": 8.025144299988557e-05, "loss": 0.0775, "step": 102630 }, { "epoch": 24.62, "learning_rate": 8.024787034152504e-05, "loss": 0.1004, "step": 102640 }, { "epoch": 24.63, "learning_rate": 8.024429743957424e-05, "loss": 0.0848, "step": 102650 }, { "epoch": 24.63, "learning_rate": 8.024072429406193e-05, "loss": 0.0698, "step": 102660 }, { "epoch": 24.63, "learning_rate": 8.023715090501689e-05, "loss": 0.0755, "step": 102670 }, { "epoch": 24.63, "learning_rate": 8.023357727246791e-05, "loss": 0.0786, "step": 102680 }, { "epoch": 24.63, "learning_rate": 8.023000339644375e-05, "loss": 0.0967, "step": 102690 }, { "epoch": 24.64, "learning_rate": 8.022642927697321e-05, "loss": 0.0724, "step": 102700 }, { "epoch": 24.64, "learning_rate": 8.022285491408505e-05, "loss": 0.088, "step": 102710 }, { "epoch": 24.64, "learning_rate": 8.021928030780806e-05, "loss": 0.0887, "step": 102720 }, { "epoch": 24.64, "learning_rate": 8.021570545817105e-05, "loss": 0.0776, "step": 102730 }, { "epoch": 24.65, "learning_rate": 8.021213036520279e-05, "loss": 0.0896, "step": 102740 }, { "epoch": 24.65, "learning_rate": 8.020855502893206e-05, "loss": 0.0962, "step": 102750 }, { "epoch": 24.65, "learning_rate": 8.020497944938768e-05, "loss": 0.0731, "step": 102760 }, { "epoch": 24.65, "learning_rate": 8.020140362659843e-05, "loss": 0.0677, "step": 102770 }, { "epoch": 24.66, "learning_rate": 8.01978275605931e-05, "loss": 0.0926, "step": 102780 }, { "epoch": 24.66, "learning_rate": 8.01942512514005e-05, "loss": 0.1053, "step": 102790 }, { "epoch": 24.66, "learning_rate": 8.019067469904941e-05, "loss": 0.0572, "step": 102800 }, { "epoch": 24.66, "learning_rate": 8.018709790356866e-05, "loss": 0.0758, "step": 102810 }, { "epoch": 24.66, "learning_rate": 8.018352086498706e-05, "loss": 0.1068, "step": 102820 }, { "epoch": 24.67, "learning_rate": 8.017994358333338e-05, "loss": 0.0836, "step": 102830 }, { "epoch": 24.67, "learning_rate": 8.017636605863646e-05, "loss": 0.0684, "step": 102840 }, { "epoch": 24.67, "learning_rate": 8.01727882909251e-05, "loss": 0.0511, "step": 102850 }, { "epoch": 24.67, "learning_rate": 8.01692102802281e-05, "loss": 0.0757, "step": 102860 }, { "epoch": 24.68, "learning_rate": 8.016563202657428e-05, "loss": 0.069, "step": 102870 }, { "epoch": 24.68, "learning_rate": 8.016205352999246e-05, "loss": 0.0669, "step": 102880 }, { "epoch": 24.68, "learning_rate": 8.015847479051147e-05, "loss": 0.0701, "step": 102890 }, { "epoch": 24.68, "learning_rate": 8.015489580816012e-05, "loss": 0.0732, "step": 102900 }, { "epoch": 24.69, "learning_rate": 8.015131658296722e-05, "loss": 0.0683, "step": 102910 }, { "epoch": 24.69, "learning_rate": 8.01477371149616e-05, "loss": 0.0546, "step": 102920 }, { "epoch": 24.69, "learning_rate": 8.014415740417212e-05, "loss": 0.0952, "step": 102930 }, { "epoch": 24.69, "learning_rate": 8.014057745062755e-05, "loss": 0.0765, "step": 102940 }, { "epoch": 24.69, "learning_rate": 8.013699725435675e-05, "loss": 0.0507, "step": 102950 }, { "epoch": 24.7, "learning_rate": 8.013341681538857e-05, "loss": 0.0593, "step": 102960 }, { "epoch": 24.7, "learning_rate": 8.012983613375181e-05, "loss": 0.0544, "step": 102970 }, { "epoch": 24.7, "learning_rate": 8.012625520947532e-05, "loss": 0.1046, "step": 102980 }, { "epoch": 24.7, "learning_rate": 8.012267404258794e-05, "loss": 0.0687, "step": 102990 }, { "epoch": 24.71, "learning_rate": 8.011909263311853e-05, "loss": 0.0642, "step": 103000 }, { "epoch": 24.71, "learning_rate": 8.011551098109587e-05, "loss": 0.0759, "step": 103010 }, { "epoch": 24.71, "learning_rate": 8.011192908654886e-05, "loss": 0.0745, "step": 103020 }, { "epoch": 24.71, "learning_rate": 8.010834694950633e-05, "loss": 0.0795, "step": 103030 }, { "epoch": 24.71, "learning_rate": 8.010476456999712e-05, "loss": 0.0605, "step": 103040 }, { "epoch": 24.72, "learning_rate": 8.010118194805009e-05, "loss": 0.0694, "step": 103050 }, { "epoch": 24.72, "learning_rate": 8.009759908369407e-05, "loss": 0.0583, "step": 103060 }, { "epoch": 24.72, "learning_rate": 8.009401597695795e-05, "loss": 0.0581, "step": 103070 }, { "epoch": 24.72, "learning_rate": 8.009043262787055e-05, "loss": 0.071, "step": 103080 }, { "epoch": 24.73, "learning_rate": 8.008684903646076e-05, "loss": 0.0833, "step": 103090 }, { "epoch": 24.73, "learning_rate": 8.008326520275739e-05, "loss": 0.0747, "step": 103100 }, { "epoch": 24.73, "learning_rate": 8.007968112678936e-05, "loss": 0.0566, "step": 103110 }, { "epoch": 24.73, "learning_rate": 8.00760968085855e-05, "loss": 0.0726, "step": 103120 }, { "epoch": 24.74, "learning_rate": 8.007251224817468e-05, "loss": 0.069, "step": 103130 }, { "epoch": 24.74, "learning_rate": 8.006892744558576e-05, "loss": 0.0905, "step": 103140 }, { "epoch": 24.74, "learning_rate": 8.006534240084762e-05, "loss": 0.0826, "step": 103150 }, { "epoch": 24.74, "learning_rate": 8.006175711398912e-05, "loss": 0.0922, "step": 103160 }, { "epoch": 24.74, "learning_rate": 8.005817158503916e-05, "loss": 0.0706, "step": 103170 }, { "epoch": 24.75, "learning_rate": 8.005458581402658e-05, "loss": 0.0894, "step": 103180 }, { "epoch": 24.75, "learning_rate": 8.005099980098028e-05, "loss": 0.0648, "step": 103190 }, { "epoch": 24.75, "learning_rate": 8.004741354592911e-05, "loss": 0.0524, "step": 103200 }, { "epoch": 24.75, "learning_rate": 8.004382704890199e-05, "loss": 0.0499, "step": 103210 }, { "epoch": 24.76, "learning_rate": 8.004024030992776e-05, "loss": 0.0922, "step": 103220 }, { "epoch": 24.76, "learning_rate": 8.003665332903535e-05, "loss": 0.0611, "step": 103230 }, { "epoch": 24.76, "learning_rate": 8.003306610625362e-05, "loss": 0.0696, "step": 103240 }, { "epoch": 24.76, "learning_rate": 8.002947864161146e-05, "loss": 0.0662, "step": 103250 }, { "epoch": 24.77, "learning_rate": 8.002589093513777e-05, "loss": 0.0936, "step": 103260 }, { "epoch": 24.77, "learning_rate": 8.002230298686142e-05, "loss": 0.0765, "step": 103270 }, { "epoch": 24.77, "learning_rate": 8.00187147968113e-05, "loss": 0.0928, "step": 103280 }, { "epoch": 24.77, "learning_rate": 8.001512636501638e-05, "loss": 0.0605, "step": 103290 }, { "epoch": 24.77, "learning_rate": 8.001153769150547e-05, "loss": 0.0696, "step": 103300 }, { "epoch": 24.78, "learning_rate": 8.00079487763075e-05, "loss": 0.0619, "step": 103310 }, { "epoch": 24.78, "learning_rate": 8.000435961945138e-05, "loss": 0.0711, "step": 103320 }, { "epoch": 24.78, "learning_rate": 8.000077022096602e-05, "loss": 0.0859, "step": 103330 }, { "epoch": 24.78, "learning_rate": 7.99971805808803e-05, "loss": 0.0978, "step": 103340 }, { "epoch": 24.79, "learning_rate": 7.999359069922317e-05, "loss": 0.0864, "step": 103350 }, { "epoch": 24.79, "learning_rate": 7.99900005760235e-05, "loss": 0.0573, "step": 103360 }, { "epoch": 24.79, "learning_rate": 7.998641021131021e-05, "loss": 0.0664, "step": 103370 }, { "epoch": 24.79, "learning_rate": 7.998281960511221e-05, "loss": 0.1167, "step": 103380 }, { "epoch": 24.79, "learning_rate": 7.997922875745843e-05, "loss": 0.0612, "step": 103390 }, { "epoch": 24.8, "learning_rate": 7.997563766837778e-05, "loss": 0.101, "step": 103400 }, { "epoch": 24.8, "learning_rate": 7.99720463378992e-05, "loss": 0.0926, "step": 103410 }, { "epoch": 24.8, "learning_rate": 7.996845476605158e-05, "loss": 0.0476, "step": 103420 }, { "epoch": 24.8, "learning_rate": 7.996486295286385e-05, "loss": 0.0693, "step": 103430 }, { "epoch": 24.81, "learning_rate": 7.996127089836495e-05, "loss": 0.0716, "step": 103440 }, { "epoch": 24.81, "learning_rate": 7.995767860258381e-05, "loss": 0.0765, "step": 103450 }, { "epoch": 24.81, "learning_rate": 7.995408606554933e-05, "loss": 0.0592, "step": 103460 }, { "epoch": 24.81, "learning_rate": 7.995049328729046e-05, "loss": 0.0784, "step": 103470 }, { "epoch": 24.82, "learning_rate": 7.994690026783613e-05, "loss": 0.0756, "step": 103480 }, { "epoch": 24.82, "learning_rate": 7.99433070072153e-05, "loss": 0.065, "step": 103490 }, { "epoch": 24.82, "learning_rate": 7.993971350545687e-05, "loss": 0.0475, "step": 103500 }, { "epoch": 24.82, "learning_rate": 7.99361197625898e-05, "loss": 0.0699, "step": 103510 }, { "epoch": 24.82, "learning_rate": 7.9932525778643e-05, "loss": 0.0686, "step": 103520 }, { "epoch": 24.83, "learning_rate": 7.992893155364547e-05, "loss": 0.0684, "step": 103530 }, { "epoch": 24.83, "learning_rate": 7.99253370876261e-05, "loss": 0.0769, "step": 103540 }, { "epoch": 24.83, "learning_rate": 7.992174238061387e-05, "loss": 0.0744, "step": 103550 }, { "epoch": 24.83, "learning_rate": 7.991814743263772e-05, "loss": 0.0789, "step": 103560 }, { "epoch": 24.84, "learning_rate": 7.991455224372659e-05, "loss": 0.0516, "step": 103570 }, { "epoch": 24.84, "learning_rate": 7.991095681390943e-05, "loss": 0.0707, "step": 103580 }, { "epoch": 24.84, "learning_rate": 7.990736114321525e-05, "loss": 0.0515, "step": 103590 }, { "epoch": 24.84, "learning_rate": 7.99037652316729e-05, "loss": 0.0687, "step": 103600 }, { "epoch": 24.85, "learning_rate": 7.990016907931144e-05, "loss": 0.0748, "step": 103610 }, { "epoch": 24.85, "learning_rate": 7.989657268615979e-05, "loss": 0.0737, "step": 103620 }, { "epoch": 24.85, "learning_rate": 7.98929760522469e-05, "loss": 0.105, "step": 103630 }, { "epoch": 24.85, "learning_rate": 7.988937917760176e-05, "loss": 0.0611, "step": 103640 }, { "epoch": 24.85, "learning_rate": 7.98857820622533e-05, "loss": 0.1081, "step": 103650 }, { "epoch": 24.86, "learning_rate": 7.988218470623054e-05, "loss": 0.0806, "step": 103660 }, { "epoch": 24.86, "learning_rate": 7.987858710956239e-05, "loss": 0.0417, "step": 103670 }, { "epoch": 24.86, "learning_rate": 7.987498927227788e-05, "loss": 0.0629, "step": 103680 }, { "epoch": 24.86, "learning_rate": 7.987139119440594e-05, "loss": 0.0328, "step": 103690 }, { "epoch": 24.87, "learning_rate": 7.986779287597557e-05, "loss": 0.0632, "step": 103700 }, { "epoch": 24.87, "learning_rate": 7.986419431701575e-05, "loss": 0.0761, "step": 103710 }, { "epoch": 24.87, "learning_rate": 7.986059551755543e-05, "loss": 0.0499, "step": 103720 }, { "epoch": 24.87, "learning_rate": 7.985699647762363e-05, "loss": 0.0478, "step": 103730 }, { "epoch": 24.87, "learning_rate": 7.98533971972493e-05, "loss": 0.0544, "step": 103740 }, { "epoch": 24.88, "learning_rate": 7.984979767646145e-05, "loss": 0.0887, "step": 103750 }, { "epoch": 24.88, "learning_rate": 7.984619791528905e-05, "loss": 0.0546, "step": 103760 }, { "epoch": 24.88, "learning_rate": 7.984259791376109e-05, "loss": 0.0578, "step": 103770 }, { "epoch": 24.88, "learning_rate": 7.98389976719066e-05, "loss": 0.0679, "step": 103780 }, { "epoch": 24.89, "learning_rate": 7.983539718975453e-05, "loss": 0.0636, "step": 103790 }, { "epoch": 24.89, "learning_rate": 7.983179646733387e-05, "loss": 0.0618, "step": 103800 }, { "epoch": 24.89, "learning_rate": 7.982819550467364e-05, "loss": 0.0811, "step": 103810 }, { "epoch": 24.89, "learning_rate": 7.982459430180285e-05, "loss": 0.0573, "step": 103820 }, { "epoch": 24.9, "learning_rate": 7.982099285875047e-05, "loss": 0.0574, "step": 103830 }, { "epoch": 24.9, "learning_rate": 7.981739117554551e-05, "loss": 0.0741, "step": 103840 }, { "epoch": 24.9, "learning_rate": 7.981378925221702e-05, "loss": 0.0589, "step": 103850 }, { "epoch": 24.9, "learning_rate": 7.981018708879393e-05, "loss": 0.0802, "step": 103860 }, { "epoch": 24.9, "learning_rate": 7.980658468530531e-05, "loss": 0.0605, "step": 103870 }, { "epoch": 24.91, "learning_rate": 7.980298204178014e-05, "loss": 0.051, "step": 103880 }, { "epoch": 24.91, "learning_rate": 7.979937915824743e-05, "loss": 0.083, "step": 103890 }, { "epoch": 24.91, "learning_rate": 7.979577603473622e-05, "loss": 0.0578, "step": 103900 }, { "epoch": 24.91, "learning_rate": 7.979217267127551e-05, "loss": 0.0504, "step": 103910 }, { "epoch": 24.92, "learning_rate": 7.978856906789433e-05, "loss": 0.0393, "step": 103920 }, { "epoch": 24.92, "learning_rate": 7.978496522462167e-05, "loss": 0.0796, "step": 103930 }, { "epoch": 24.92, "learning_rate": 7.978136114148658e-05, "loss": 0.0719, "step": 103940 }, { "epoch": 24.92, "learning_rate": 7.977775681851808e-05, "loss": 0.0841, "step": 103950 }, { "epoch": 24.93, "learning_rate": 7.977415225574519e-05, "loss": 0.0762, "step": 103960 }, { "epoch": 24.93, "learning_rate": 7.977054745319696e-05, "loss": 0.0564, "step": 103970 }, { "epoch": 24.93, "learning_rate": 7.976694241090238e-05, "loss": 0.0381, "step": 103980 }, { "epoch": 24.93, "learning_rate": 7.976333712889051e-05, "loss": 0.1092, "step": 103990 }, { "epoch": 24.93, "learning_rate": 7.975973160719036e-05, "loss": 0.0617, "step": 104000 }, { "epoch": 24.94, "learning_rate": 7.9756125845831e-05, "loss": 0.0457, "step": 104010 }, { "epoch": 24.94, "learning_rate": 7.975251984484147e-05, "loss": 0.0842, "step": 104020 }, { "epoch": 24.94, "learning_rate": 7.974891360425076e-05, "loss": 0.0466, "step": 104030 }, { "epoch": 24.94, "learning_rate": 7.974530712408795e-05, "loss": 0.0672, "step": 104040 }, { "epoch": 24.95, "learning_rate": 7.974170040438208e-05, "loss": 0.0691, "step": 104050 }, { "epoch": 24.95, "learning_rate": 7.973809344516219e-05, "loss": 0.06, "step": 104060 }, { "epoch": 24.95, "learning_rate": 7.973448624645732e-05, "loss": 0.0537, "step": 104070 }, { "epoch": 25.0, "learning_rate": 7.973087880829653e-05, "loss": 0.0697, "step": 104080 }, { "epoch": 25.0, "learning_rate": 7.972727113070889e-05, "loss": 0.0574, "step": 104090 }, { "epoch": 25.01, "learning_rate": 7.97236632137234e-05, "loss": 0.0693, "step": 104100 }, { "epoch": 25.01, "learning_rate": 7.972005505736915e-05, "loss": 0.0724, "step": 104110 }, { "epoch": 25.01, "learning_rate": 7.97164466616752e-05, "loss": 0.0609, "step": 104120 }, { "epoch": 25.01, "learning_rate": 7.97128380266706e-05, "loss": 0.0785, "step": 104130 }, { "epoch": 25.01, "learning_rate": 7.970922915238442e-05, "loss": 0.0599, "step": 104140 }, { "epoch": 25.02, "learning_rate": 7.970562003884572e-05, "loss": 0.0563, "step": 104150 }, { "epoch": 25.02, "learning_rate": 7.970201068608355e-05, "loss": 0.0506, "step": 104160 }, { "epoch": 25.02, "learning_rate": 7.969840109412698e-05, "loss": 0.0397, "step": 104170 }, { "epoch": 25.02, "learning_rate": 7.969479126300511e-05, "loss": 0.0718, "step": 104180 }, { "epoch": 25.03, "learning_rate": 7.969118119274697e-05, "loss": 0.0689, "step": 104190 }, { "epoch": 25.03, "learning_rate": 7.968757088338166e-05, "loss": 0.056, "step": 104200 }, { "epoch": 25.03, "learning_rate": 7.968396033493823e-05, "loss": 0.0558, "step": 104210 }, { "epoch": 25.03, "learning_rate": 7.968034954744577e-05, "loss": 0.0802, "step": 104220 }, { "epoch": 25.04, "learning_rate": 7.967673852093336e-05, "loss": 0.0648, "step": 104230 }, { "epoch": 25.04, "learning_rate": 7.967312725543008e-05, "loss": 0.06, "step": 104240 }, { "epoch": 25.04, "learning_rate": 7.966951575096502e-05, "loss": 0.0577, "step": 104250 }, { "epoch": 25.04, "learning_rate": 7.966590400756724e-05, "loss": 0.0664, "step": 104260 }, { "epoch": 25.04, "learning_rate": 7.966229202526582e-05, "loss": 0.0493, "step": 104270 }, { "epoch": 25.05, "learning_rate": 7.965867980408991e-05, "loss": 0.0549, "step": 104280 }, { "epoch": 25.05, "learning_rate": 7.965506734406854e-05, "loss": 0.0661, "step": 104290 }, { "epoch": 25.05, "learning_rate": 7.96514546452308e-05, "loss": 0.0775, "step": 104300 }, { "epoch": 25.05, "learning_rate": 7.964784170760581e-05, "loss": 0.0761, "step": 104310 }, { "epoch": 25.06, "learning_rate": 7.964422853122268e-05, "loss": 0.074, "step": 104320 }, { "epoch": 25.06, "learning_rate": 7.964061511611048e-05, "loss": 0.0513, "step": 104330 }, { "epoch": 25.06, "learning_rate": 7.963700146229828e-05, "loss": 0.037, "step": 104340 }, { "epoch": 25.06, "learning_rate": 7.963338756981526e-05, "loss": 0.0581, "step": 104350 }, { "epoch": 25.07, "learning_rate": 7.962977343869045e-05, "loss": 0.0395, "step": 104360 }, { "epoch": 25.07, "learning_rate": 7.962615906895298e-05, "loss": 0.0685, "step": 104370 }, { "epoch": 25.07, "learning_rate": 7.962254446063199e-05, "loss": 0.065, "step": 104380 }, { "epoch": 25.07, "learning_rate": 7.961892961375655e-05, "loss": 0.0494, "step": 104390 }, { "epoch": 25.07, "learning_rate": 7.961531452835576e-05, "loss": 0.0905, "step": 104400 }, { "epoch": 25.08, "learning_rate": 7.961169920445877e-05, "loss": 0.0484, "step": 104410 }, { "epoch": 25.08, "learning_rate": 7.960808364209466e-05, "loss": 0.0877, "step": 104420 }, { "epoch": 25.08, "learning_rate": 7.960446784129258e-05, "loss": 0.0911, "step": 104430 }, { "epoch": 25.08, "learning_rate": 7.960085180208165e-05, "loss": 0.0633, "step": 104440 }, { "epoch": 25.09, "learning_rate": 7.959723552449096e-05, "loss": 0.0564, "step": 104450 }, { "epoch": 25.09, "learning_rate": 7.959361900854963e-05, "loss": 0.067, "step": 104460 }, { "epoch": 25.09, "learning_rate": 7.959000225428682e-05, "loss": 0.0739, "step": 104470 }, { "epoch": 25.09, "learning_rate": 7.958638526173164e-05, "loss": 0.0719, "step": 104480 }, { "epoch": 25.09, "learning_rate": 7.95827680309132e-05, "loss": 0.0713, "step": 104490 }, { "epoch": 25.1, "learning_rate": 7.957915056186065e-05, "loss": 0.0505, "step": 104500 }, { "epoch": 25.1, "learning_rate": 7.95755328546031e-05, "loss": 0.055, "step": 104510 }, { "epoch": 25.1, "learning_rate": 7.957191490916973e-05, "loss": 0.0713, "step": 104520 }, { "epoch": 25.1, "learning_rate": 7.956829672558964e-05, "loss": 0.0566, "step": 104530 }, { "epoch": 25.11, "learning_rate": 7.956467830389196e-05, "loss": 0.0582, "step": 104540 }, { "epoch": 25.11, "learning_rate": 7.956105964410585e-05, "loss": 0.0539, "step": 104550 }, { "epoch": 25.11, "learning_rate": 7.955744074626046e-05, "loss": 0.0833, "step": 104560 }, { "epoch": 25.11, "learning_rate": 7.95538216103849e-05, "loss": 0.074, "step": 104570 }, { "epoch": 25.12, "learning_rate": 7.955020223650834e-05, "loss": 0.0518, "step": 104580 }, { "epoch": 25.12, "learning_rate": 7.954658262465993e-05, "loss": 0.0744, "step": 104590 }, { "epoch": 25.12, "learning_rate": 7.954296277486879e-05, "loss": 0.0574, "step": 104600 }, { "epoch": 25.12, "learning_rate": 7.953934268716413e-05, "loss": 0.0535, "step": 104610 }, { "epoch": 25.12, "learning_rate": 7.953572236157503e-05, "loss": 0.046, "step": 104620 }, { "epoch": 25.13, "learning_rate": 7.953210179813069e-05, "loss": 0.0481, "step": 104630 }, { "epoch": 25.13, "learning_rate": 7.952848099686025e-05, "loss": 0.0601, "step": 104640 }, { "epoch": 25.13, "learning_rate": 7.952485995779289e-05, "loss": 0.0428, "step": 104650 }, { "epoch": 25.13, "learning_rate": 7.952123868095776e-05, "loss": 0.0747, "step": 104660 }, { "epoch": 25.14, "learning_rate": 7.951761716638399e-05, "loss": 0.0701, "step": 104670 }, { "epoch": 25.14, "learning_rate": 7.95139954141008e-05, "loss": 0.0679, "step": 104680 }, { "epoch": 25.14, "learning_rate": 7.951037342413732e-05, "loss": 0.0613, "step": 104690 }, { "epoch": 25.14, "learning_rate": 7.950675119652275e-05, "loss": 0.0491, "step": 104700 }, { "epoch": 25.15, "learning_rate": 7.950312873128621e-05, "loss": 0.0638, "step": 104710 }, { "epoch": 25.15, "learning_rate": 7.949950602845692e-05, "loss": 0.0587, "step": 104720 }, { "epoch": 25.15, "learning_rate": 7.949588308806402e-05, "loss": 0.0593, "step": 104730 }, { "epoch": 25.15, "learning_rate": 7.949225991013671e-05, "loss": 0.0699, "step": 104740 }, { "epoch": 25.15, "learning_rate": 7.948863649470417e-05, "loss": 0.0788, "step": 104750 }, { "epoch": 25.16, "learning_rate": 7.948501284179554e-05, "loss": 0.0478, "step": 104760 }, { "epoch": 25.16, "learning_rate": 7.948138895144006e-05, "loss": 0.052, "step": 104770 }, { "epoch": 25.16, "learning_rate": 7.947776482366687e-05, "loss": 0.0623, "step": 104780 }, { "epoch": 25.16, "learning_rate": 7.947414045850517e-05, "loss": 0.0664, "step": 104790 }, { "epoch": 25.17, "learning_rate": 7.947051585598415e-05, "loss": 0.0804, "step": 104800 }, { "epoch": 25.17, "learning_rate": 7.9466891016133e-05, "loss": 0.0805, "step": 104810 }, { "epoch": 25.17, "learning_rate": 7.946326593898093e-05, "loss": 0.0654, "step": 104820 }, { "epoch": 25.17, "learning_rate": 7.945964062455708e-05, "loss": 0.0575, "step": 104830 }, { "epoch": 25.17, "learning_rate": 7.945601507289068e-05, "loss": 0.0421, "step": 104840 }, { "epoch": 25.18, "learning_rate": 7.945238928401093e-05, "loss": 0.0791, "step": 104850 }, { "epoch": 25.18, "learning_rate": 7.944876325794701e-05, "loss": 0.0842, "step": 104860 }, { "epoch": 25.18, "learning_rate": 7.944513699472815e-05, "loss": 0.0621, "step": 104870 }, { "epoch": 25.18, "learning_rate": 7.944151049438354e-05, "loss": 0.0404, "step": 104880 }, { "epoch": 25.19, "learning_rate": 7.943788375694237e-05, "loss": 0.0558, "step": 104890 }, { "epoch": 25.19, "learning_rate": 7.943425678243387e-05, "loss": 0.0801, "step": 104900 }, { "epoch": 25.19, "learning_rate": 7.943062957088722e-05, "loss": 0.0686, "step": 104910 }, { "epoch": 25.19, "learning_rate": 7.942700212233166e-05, "loss": 0.0471, "step": 104920 }, { "epoch": 25.2, "learning_rate": 7.942337443679639e-05, "loss": 0.0479, "step": 104930 }, { "epoch": 25.2, "learning_rate": 7.941974651431062e-05, "loss": 0.0575, "step": 104940 }, { "epoch": 25.2, "learning_rate": 7.941611835490357e-05, "loss": 0.0825, "step": 104950 }, { "epoch": 25.2, "learning_rate": 7.941248995860445e-05, "loss": 0.0816, "step": 104960 }, { "epoch": 25.2, "learning_rate": 7.94088613254425e-05, "loss": 0.0405, "step": 104970 }, { "epoch": 25.21, "learning_rate": 7.940523245544693e-05, "loss": 0.0624, "step": 104980 }, { "epoch": 25.21, "learning_rate": 7.940160334864694e-05, "loss": 0.0782, "step": 104990 }, { "epoch": 25.21, "learning_rate": 7.939797400507181e-05, "loss": 0.092, "step": 105000 }, { "epoch": 25.21, "learning_rate": 7.939434442475072e-05, "loss": 0.0875, "step": 105010 }, { "epoch": 25.22, "learning_rate": 7.939071460771291e-05, "loss": 0.0779, "step": 105020 }, { "epoch": 25.22, "learning_rate": 7.938708455398764e-05, "loss": 0.065, "step": 105030 }, { "epoch": 25.22, "learning_rate": 7.938345426360409e-05, "loss": 0.0927, "step": 105040 }, { "epoch": 25.22, "learning_rate": 7.937982373659157e-05, "loss": 0.0602, "step": 105050 }, { "epoch": 25.23, "learning_rate": 7.937619297297922e-05, "loss": 0.0624, "step": 105060 }, { "epoch": 25.23, "learning_rate": 7.937256197279637e-05, "loss": 0.0472, "step": 105070 }, { "epoch": 25.23, "learning_rate": 7.936893073607221e-05, "loss": 0.0577, "step": 105080 }, { "epoch": 25.23, "learning_rate": 7.9365299262836e-05, "loss": 0.0691, "step": 105090 }, { "epoch": 25.23, "learning_rate": 7.936166755311698e-05, "loss": 0.0967, "step": 105100 }, { "epoch": 25.24, "learning_rate": 7.935803560694439e-05, "loss": 0.0698, "step": 105110 }, { "epoch": 25.24, "learning_rate": 7.93544034243475e-05, "loss": 0.048, "step": 105120 }, { "epoch": 25.24, "learning_rate": 7.935077100535554e-05, "loss": 0.0645, "step": 105130 }, { "epoch": 25.24, "learning_rate": 7.934713834999776e-05, "loss": 0.0487, "step": 105140 }, { "epoch": 25.25, "learning_rate": 7.934350545830344e-05, "loss": 0.1064, "step": 105150 }, { "epoch": 25.25, "learning_rate": 7.93398723303018e-05, "loss": 0.0859, "step": 105160 }, { "epoch": 25.25, "learning_rate": 7.933623896602214e-05, "loss": 0.0857, "step": 105170 }, { "epoch": 25.25, "learning_rate": 7.93326053654937e-05, "loss": 0.0647, "step": 105180 }, { "epoch": 25.25, "learning_rate": 7.932897152874571e-05, "loss": 0.0765, "step": 105190 }, { "epoch": 25.26, "learning_rate": 7.932533745580748e-05, "loss": 0.0541, "step": 105200 }, { "epoch": 25.26, "learning_rate": 7.932170314670827e-05, "loss": 0.058, "step": 105210 }, { "epoch": 25.26, "learning_rate": 7.931806860147731e-05, "loss": 0.048, "step": 105220 }, { "epoch": 25.26, "learning_rate": 7.931443382014392e-05, "loss": 0.0794, "step": 105230 }, { "epoch": 25.27, "learning_rate": 7.931079880273733e-05, "loss": 0.0588, "step": 105240 }, { "epoch": 25.27, "learning_rate": 7.930716354928684e-05, "loss": 0.045, "step": 105250 }, { "epoch": 25.27, "learning_rate": 7.930352805982171e-05, "loss": 0.0411, "step": 105260 }, { "epoch": 25.27, "learning_rate": 7.929989233437123e-05, "loss": 0.0471, "step": 105270 }, { "epoch": 25.28, "learning_rate": 7.929625637296467e-05, "loss": 0.073, "step": 105280 }, { "epoch": 25.28, "learning_rate": 7.929262017563132e-05, "loss": 0.0588, "step": 105290 }, { "epoch": 25.28, "learning_rate": 7.928898374240044e-05, "loss": 0.0581, "step": 105300 }, { "epoch": 25.28, "learning_rate": 7.928534707330133e-05, "loss": 0.0519, "step": 105310 }, { "epoch": 25.28, "learning_rate": 7.928171016836329e-05, "loss": 0.0601, "step": 105320 }, { "epoch": 25.29, "learning_rate": 7.927807302761558e-05, "loss": 0.074, "step": 105330 }, { "epoch": 25.29, "learning_rate": 7.927443565108752e-05, "loss": 0.0744, "step": 105340 }, { "epoch": 25.29, "learning_rate": 7.92707980388084e-05, "loss": 0.0572, "step": 105350 }, { "epoch": 25.29, "learning_rate": 7.926716019080749e-05, "loss": 0.052, "step": 105360 }, { "epoch": 25.3, "learning_rate": 7.926352210711408e-05, "loss": 0.051, "step": 105370 }, { "epoch": 25.3, "learning_rate": 7.92598837877575e-05, "loss": 0.0527, "step": 105380 }, { "epoch": 25.3, "learning_rate": 7.925624523276705e-05, "loss": 0.0658, "step": 105390 }, { "epoch": 25.3, "learning_rate": 7.9252606442172e-05, "loss": 0.065, "step": 105400 }, { "epoch": 25.31, "learning_rate": 7.924896741600167e-05, "loss": 0.0852, "step": 105410 }, { "epoch": 25.31, "learning_rate": 7.924532815428538e-05, "loss": 0.0632, "step": 105420 }, { "epoch": 25.31, "learning_rate": 7.924168865705241e-05, "loss": 0.0571, "step": 105430 }, { "epoch": 25.31, "learning_rate": 7.92380489243321e-05, "loss": 0.0943, "step": 105440 }, { "epoch": 25.31, "learning_rate": 7.923440895615374e-05, "loss": 0.0666, "step": 105450 }, { "epoch": 25.32, "learning_rate": 7.923076875254665e-05, "loss": 0.042, "step": 105460 }, { "epoch": 25.32, "learning_rate": 7.922712831354014e-05, "loss": 0.0578, "step": 105470 }, { "epoch": 25.32, "learning_rate": 7.922348763916354e-05, "loss": 0.0508, "step": 105480 }, { "epoch": 25.32, "learning_rate": 7.921984672944615e-05, "loss": 0.0673, "step": 105490 }, { "epoch": 25.33, "learning_rate": 7.92162055844173e-05, "loss": 0.0485, "step": 105500 }, { "epoch": 25.33, "learning_rate": 7.921256420410631e-05, "loss": 0.0566, "step": 105510 }, { "epoch": 25.33, "learning_rate": 7.920892258854251e-05, "loss": 0.0459, "step": 105520 }, { "epoch": 25.33, "learning_rate": 7.920528073775523e-05, "loss": 0.0606, "step": 105530 }, { "epoch": 25.33, "learning_rate": 7.920163865177379e-05, "loss": 0.04, "step": 105540 }, { "epoch": 25.34, "learning_rate": 7.919799633062752e-05, "loss": 0.052, "step": 105550 }, { "epoch": 25.34, "learning_rate": 7.919435377434576e-05, "loss": 0.051, "step": 105560 }, { "epoch": 25.34, "learning_rate": 7.919071098295783e-05, "loss": 0.0564, "step": 105570 }, { "epoch": 25.34, "learning_rate": 7.918706795649307e-05, "loss": 0.0555, "step": 105580 }, { "epoch": 25.35, "learning_rate": 7.918342469498083e-05, "loss": 0.0427, "step": 105590 }, { "epoch": 25.35, "learning_rate": 7.917978119845045e-05, "loss": 0.0554, "step": 105600 }, { "epoch": 25.35, "learning_rate": 7.917613746693125e-05, "loss": 0.0364, "step": 105610 }, { "epoch": 25.35, "learning_rate": 7.917249350045259e-05, "loss": 0.0563, "step": 105620 }, { "epoch": 25.36, "learning_rate": 7.916884929904381e-05, "loss": 0.0579, "step": 105630 }, { "epoch": 25.36, "learning_rate": 7.916520486273427e-05, "loss": 0.0678, "step": 105640 }, { "epoch": 25.36, "learning_rate": 7.91615601915533e-05, "loss": 0.0555, "step": 105650 }, { "epoch": 25.36, "learning_rate": 7.915791528553027e-05, "loss": 0.0659, "step": 105660 }, { "epoch": 25.36, "learning_rate": 7.915427014469452e-05, "loss": 0.0628, "step": 105670 }, { "epoch": 25.37, "learning_rate": 7.91506247690754e-05, "loss": 0.0795, "step": 105680 }, { "epoch": 25.37, "learning_rate": 7.914697915870227e-05, "loss": 0.0587, "step": 105690 }, { "epoch": 25.37, "learning_rate": 7.914333331360451e-05, "loss": 0.0567, "step": 105700 }, { "epoch": 25.37, "learning_rate": 7.913968723381145e-05, "loss": 0.0351, "step": 105710 }, { "epoch": 25.38, "learning_rate": 7.913604091935247e-05, "loss": 0.0483, "step": 105720 }, { "epoch": 25.38, "learning_rate": 7.913239437025692e-05, "loss": 0.075, "step": 105730 }, { "epoch": 25.38, "learning_rate": 7.912874758655419e-05, "loss": 0.0457, "step": 105740 }, { "epoch": 25.38, "learning_rate": 7.912510056827362e-05, "loss": 0.0493, "step": 105750 }, { "epoch": 25.39, "learning_rate": 7.912145331544462e-05, "loss": 0.0813, "step": 105760 }, { "epoch": 25.39, "learning_rate": 7.911780582809652e-05, "loss": 0.0395, "step": 105770 }, { "epoch": 25.39, "learning_rate": 7.911415810625869e-05, "loss": 0.0502, "step": 105780 }, { "epoch": 25.39, "learning_rate": 7.911051014996056e-05, "loss": 0.0618, "step": 105790 }, { "epoch": 25.39, "learning_rate": 7.910686195923145e-05, "loss": 0.0627, "step": 105800 }, { "epoch": 25.4, "learning_rate": 7.910321353410078e-05, "loss": 0.0743, "step": 105810 }, { "epoch": 25.4, "learning_rate": 7.909956487459789e-05, "loss": 0.0513, "step": 105820 }, { "epoch": 25.4, "learning_rate": 7.909591598075221e-05, "loss": 0.09, "step": 105830 }, { "epoch": 25.4, "learning_rate": 7.909226685259309e-05, "loss": 0.0691, "step": 105840 }, { "epoch": 25.41, "learning_rate": 7.908861749014993e-05, "loss": 0.0383, "step": 105850 }, { "epoch": 25.41, "learning_rate": 7.908496789345212e-05, "loss": 0.0386, "step": 105860 }, { "epoch": 25.41, "learning_rate": 7.908131806252904e-05, "loss": 0.0469, "step": 105870 }, { "epoch": 25.41, "learning_rate": 7.90776679974101e-05, "loss": 0.0466, "step": 105880 }, { "epoch": 25.41, "learning_rate": 7.907401769812469e-05, "loss": 0.0592, "step": 105890 }, { "epoch": 25.42, "learning_rate": 7.907036716470218e-05, "loss": 0.0669, "step": 105900 }, { "epoch": 25.42, "learning_rate": 7.9066716397172e-05, "loss": 0.0803, "step": 105910 }, { "epoch": 25.42, "learning_rate": 7.906306539556354e-05, "loss": 0.099, "step": 105920 }, { "epoch": 25.42, "learning_rate": 7.90594141599062e-05, "loss": 0.0598, "step": 105930 }, { "epoch": 25.43, "learning_rate": 7.905576269022941e-05, "loss": 0.063, "step": 105940 }, { "epoch": 25.43, "learning_rate": 7.905211098656254e-05, "loss": 0.0395, "step": 105950 }, { "epoch": 25.43, "learning_rate": 7.904845904893499e-05, "loss": 0.0402, "step": 105960 }, { "epoch": 25.43, "learning_rate": 7.90448068773762e-05, "loss": 0.0717, "step": 105970 }, { "epoch": 25.44, "learning_rate": 7.904115447191558e-05, "loss": 0.0517, "step": 105980 }, { "epoch": 25.44, "learning_rate": 7.903750183258251e-05, "loss": 0.0387, "step": 105990 }, { "epoch": 25.44, "learning_rate": 7.903384895940644e-05, "loss": 0.0525, "step": 106000 }, { "epoch": 25.44, "learning_rate": 7.903019585241677e-05, "loss": 0.032, "step": 106010 }, { "epoch": 25.44, "learning_rate": 7.902654251164295e-05, "loss": 0.0335, "step": 106020 }, { "epoch": 25.45, "learning_rate": 7.902288893711436e-05, "loss": 0.0862, "step": 106030 }, { "epoch": 25.45, "learning_rate": 7.901923512886043e-05, "loss": 0.0413, "step": 106040 }, { "epoch": 25.45, "learning_rate": 7.90155810869106e-05, "loss": 0.0676, "step": 106050 }, { "epoch": 25.45, "learning_rate": 7.90119268112943e-05, "loss": 0.0497, "step": 106060 }, { "epoch": 25.46, "learning_rate": 7.900827230204094e-05, "loss": 0.0729, "step": 106070 }, { "epoch": 25.46, "learning_rate": 7.900461755917996e-05, "loss": 0.0589, "step": 106080 }, { "epoch": 25.46, "learning_rate": 7.900096258274079e-05, "loss": 0.0517, "step": 106090 }, { "epoch": 25.46, "learning_rate": 7.899730737275286e-05, "loss": 0.0363, "step": 106100 }, { "epoch": 25.47, "learning_rate": 7.899365192924562e-05, "loss": 0.056, "step": 106110 }, { "epoch": 25.47, "learning_rate": 7.898999625224849e-05, "loss": 0.0696, "step": 106120 }, { "epoch": 25.47, "learning_rate": 7.898634034179092e-05, "loss": 0.0564, "step": 106130 }, { "epoch": 25.47, "learning_rate": 7.898268419790235e-05, "loss": 0.0549, "step": 106140 }, { "epoch": 25.47, "learning_rate": 7.897902782061222e-05, "loss": 0.0451, "step": 106150 }, { "epoch": 25.48, "learning_rate": 7.897537120994998e-05, "loss": 0.0601, "step": 106160 }, { "epoch": 25.48, "learning_rate": 7.897171436594506e-05, "loss": 0.0578, "step": 106170 }, { "epoch": 25.48, "learning_rate": 7.896805728862695e-05, "loss": 0.0731, "step": 106180 }, { "epoch": 25.48, "learning_rate": 7.896439997802508e-05, "loss": 0.0454, "step": 106190 }, { "epoch": 25.49, "learning_rate": 7.896074243416886e-05, "loss": 0.064, "step": 106200 }, { "epoch": 25.49, "learning_rate": 7.895708465708781e-05, "loss": 0.0682, "step": 106210 }, { "epoch": 25.49, "learning_rate": 7.895342664681136e-05, "loss": 0.0545, "step": 106220 }, { "epoch": 25.49, "learning_rate": 7.894976840336896e-05, "loss": 0.0912, "step": 106230 }, { "epoch": 25.49, "learning_rate": 7.894610992679008e-05, "loss": 0.0794, "step": 106240 }, { "epoch": 25.5, "learning_rate": 7.894245121710417e-05, "loss": 0.0438, "step": 106250 }, { "epoch": 25.5, "learning_rate": 7.893879227434073e-05, "loss": 0.0676, "step": 106260 }, { "epoch": 25.5, "learning_rate": 7.893513309852918e-05, "loss": 0.0448, "step": 106270 }, { "epoch": 25.5, "learning_rate": 7.893147368969902e-05, "loss": 0.0609, "step": 106280 }, { "epoch": 25.51, "learning_rate": 7.89278140478797e-05, "loss": 0.0375, "step": 106290 }, { "epoch": 25.51, "learning_rate": 7.892415417310072e-05, "loss": 0.0667, "step": 106300 }, { "epoch": 25.51, "learning_rate": 7.89204940653915e-05, "loss": 0.049, "step": 106310 }, { "epoch": 25.51, "learning_rate": 7.891683372478157e-05, "loss": 0.0512, "step": 106320 }, { "epoch": 25.52, "learning_rate": 7.89131731513004e-05, "loss": 0.0675, "step": 106330 }, { "epoch": 25.52, "learning_rate": 7.890951234497742e-05, "loss": 0.05, "step": 106340 }, { "epoch": 25.52, "learning_rate": 7.890585130584216e-05, "loss": 0.0479, "step": 106350 }, { "epoch": 25.52, "learning_rate": 7.89021900339241e-05, "loss": 0.0521, "step": 106360 }, { "epoch": 25.52, "learning_rate": 7.889852852925269e-05, "loss": 0.0498, "step": 106370 }, { "epoch": 25.53, "learning_rate": 7.889486679185747e-05, "loss": 0.0886, "step": 106380 }, { "epoch": 25.53, "learning_rate": 7.889120482176788e-05, "loss": 0.0732, "step": 106390 }, { "epoch": 25.53, "learning_rate": 7.888754261901343e-05, "loss": 0.06, "step": 106400 }, { "epoch": 25.53, "learning_rate": 7.88838801836236e-05, "loss": 0.0702, "step": 106410 }, { "epoch": 25.54, "learning_rate": 7.888021751562792e-05, "loss": 0.0776, "step": 106420 }, { "epoch": 25.54, "learning_rate": 7.887655461505585e-05, "loss": 0.0804, "step": 106430 }, { "epoch": 25.54, "learning_rate": 7.887289148193688e-05, "loss": 0.081, "step": 106440 }, { "epoch": 25.54, "learning_rate": 7.886922811630057e-05, "loss": 0.0663, "step": 106450 }, { "epoch": 25.55, "learning_rate": 7.886556451817634e-05, "loss": 0.0728, "step": 106460 }, { "epoch": 25.55, "learning_rate": 7.886190068759377e-05, "loss": 0.0849, "step": 106470 }, { "epoch": 25.55, "learning_rate": 7.88582366245823e-05, "loss": 0.069, "step": 106480 }, { "epoch": 25.55, "learning_rate": 7.885457232917148e-05, "loss": 0.0945, "step": 106490 }, { "epoch": 25.55, "learning_rate": 7.88509078013908e-05, "loss": 0.0845, "step": 106500 }, { "epoch": 25.56, "learning_rate": 7.884724304126977e-05, "loss": 0.0725, "step": 106510 }, { "epoch": 25.56, "learning_rate": 7.884357804883793e-05, "loss": 0.0567, "step": 106520 }, { "epoch": 25.56, "learning_rate": 7.883991282412475e-05, "loss": 0.0539, "step": 106530 }, { "epoch": 25.56, "learning_rate": 7.883624736715978e-05, "loss": 0.0755, "step": 106540 }, { "epoch": 25.57, "learning_rate": 7.883258167797253e-05, "loss": 0.077, "step": 106550 }, { "epoch": 25.57, "learning_rate": 7.882891575659253e-05, "loss": 0.0382, "step": 106560 }, { "epoch": 25.57, "learning_rate": 7.882524960304928e-05, "loss": 0.0636, "step": 106570 }, { "epoch": 25.57, "learning_rate": 7.882158321737231e-05, "loss": 0.0694, "step": 106580 }, { "epoch": 25.57, "learning_rate": 7.881791659959116e-05, "loss": 0.073, "step": 106590 }, { "epoch": 25.58, "learning_rate": 7.881424974973535e-05, "loss": 0.0933, "step": 106600 }, { "epoch": 25.58, "learning_rate": 7.88105826678344e-05, "loss": 0.0809, "step": 106610 }, { "epoch": 25.58, "learning_rate": 7.880691535391787e-05, "loss": 0.088, "step": 106620 }, { "epoch": 25.58, "learning_rate": 7.880324780801525e-05, "loss": 0.0596, "step": 106630 }, { "epoch": 25.59, "learning_rate": 7.879958003015611e-05, "loss": 0.0471, "step": 106640 }, { "epoch": 25.59, "learning_rate": 7.879591202036997e-05, "loss": 0.0752, "step": 106650 }, { "epoch": 25.59, "learning_rate": 7.879224377868638e-05, "loss": 0.0791, "step": 106660 }, { "epoch": 25.59, "learning_rate": 7.878857530513488e-05, "loss": 0.0531, "step": 106670 }, { "epoch": 25.6, "learning_rate": 7.878490659974501e-05, "loss": 0.0983, "step": 106680 }, { "epoch": 25.6, "learning_rate": 7.87812376625463e-05, "loss": 0.0936, "step": 106690 }, { "epoch": 25.6, "learning_rate": 7.877756849356831e-05, "loss": 0.1048, "step": 106700 }, { "epoch": 25.6, "learning_rate": 7.877389909284058e-05, "loss": 0.0439, "step": 106710 }, { "epoch": 25.6, "learning_rate": 7.87702294603927e-05, "loss": 0.0606, "step": 106720 }, { "epoch": 25.61, "learning_rate": 7.876655959625418e-05, "loss": 0.088, "step": 106730 }, { "epoch": 25.61, "learning_rate": 7.876288950045456e-05, "loss": 0.0718, "step": 106740 }, { "epoch": 25.61, "learning_rate": 7.875921917302345e-05, "loss": 0.0615, "step": 106750 }, { "epoch": 25.61, "learning_rate": 7.875554861399036e-05, "loss": 0.0497, "step": 106760 }, { "epoch": 25.62, "learning_rate": 7.875187782338487e-05, "loss": 0.0686, "step": 106770 }, { "epoch": 25.62, "learning_rate": 7.874820680123653e-05, "loss": 0.068, "step": 106780 }, { "epoch": 25.62, "learning_rate": 7.874453554757493e-05, "loss": 0.0747, "step": 106790 }, { "epoch": 25.62, "learning_rate": 7.87408640624296e-05, "loss": 0.0911, "step": 106800 }, { "epoch": 25.62, "learning_rate": 7.873719234583014e-05, "loss": 0.0623, "step": 106810 }, { "epoch": 25.63, "learning_rate": 7.87335203978061e-05, "loss": 0.0657, "step": 106820 }, { "epoch": 25.63, "learning_rate": 7.872984821838705e-05, "loss": 0.0772, "step": 106830 }, { "epoch": 25.63, "learning_rate": 7.872617580760256e-05, "loss": 0.0851, "step": 106840 }, { "epoch": 25.63, "learning_rate": 7.87225031654822e-05, "loss": 0.0594, "step": 106850 }, { "epoch": 25.64, "learning_rate": 7.871883029205558e-05, "loss": 0.0603, "step": 106860 }, { "epoch": 25.64, "learning_rate": 7.871515718735225e-05, "loss": 0.0519, "step": 106870 }, { "epoch": 25.64, "learning_rate": 7.871148385140179e-05, "loss": 0.0621, "step": 106880 }, { "epoch": 25.64, "learning_rate": 7.870781028423378e-05, "loss": 0.0725, "step": 106890 }, { "epoch": 25.65, "learning_rate": 7.870413648587783e-05, "loss": 0.0822, "step": 106900 }, { "epoch": 25.65, "learning_rate": 7.870046245636348e-05, "loss": 0.0849, "step": 106910 }, { "epoch": 25.65, "learning_rate": 7.869678819572035e-05, "loss": 0.0636, "step": 106920 }, { "epoch": 25.65, "learning_rate": 7.869311370397804e-05, "loss": 0.0568, "step": 106930 }, { "epoch": 25.65, "learning_rate": 7.868943898116612e-05, "loss": 0.0612, "step": 106940 }, { "epoch": 25.66, "learning_rate": 7.868576402731418e-05, "loss": 0.0683, "step": 106950 }, { "epoch": 25.66, "learning_rate": 7.868208884245182e-05, "loss": 0.0878, "step": 106960 }, { "epoch": 25.66, "learning_rate": 7.867841342660864e-05, "loss": 0.0514, "step": 106970 }, { "epoch": 25.66, "learning_rate": 7.867473777981424e-05, "loss": 0.0731, "step": 106980 }, { "epoch": 25.67, "learning_rate": 7.867106190209821e-05, "loss": 0.0672, "step": 106990 }, { "epoch": 25.67, "learning_rate": 7.866738579349018e-05, "loss": 0.0755, "step": 107000 }, { "epoch": 25.67, "learning_rate": 7.86637094540197e-05, "loss": 0.0664, "step": 107010 }, { "epoch": 25.67, "learning_rate": 7.866003288371644e-05, "loss": 0.1013, "step": 107020 }, { "epoch": 25.68, "learning_rate": 7.865635608260997e-05, "loss": 0.0513, "step": 107030 }, { "epoch": 25.68, "learning_rate": 7.865267905072992e-05, "loss": 0.0486, "step": 107040 }, { "epoch": 25.68, "learning_rate": 7.864900178810586e-05, "loss": 0.0487, "step": 107050 }, { "epoch": 25.68, "learning_rate": 7.864532429476748e-05, "loss": 0.0651, "step": 107060 }, { "epoch": 25.68, "learning_rate": 7.864164657074431e-05, "loss": 0.0727, "step": 107070 }, { "epoch": 25.69, "learning_rate": 7.8637968616066e-05, "loss": 0.0734, "step": 107080 }, { "epoch": 25.69, "learning_rate": 7.86342904307622e-05, "loss": 0.0744, "step": 107090 }, { "epoch": 25.69, "learning_rate": 7.863061201486249e-05, "loss": 0.0786, "step": 107100 }, { "epoch": 25.69, "learning_rate": 7.862693336839653e-05, "loss": 0.0386, "step": 107110 }, { "epoch": 25.7, "learning_rate": 7.862325449139391e-05, "loss": 0.0676, "step": 107120 }, { "epoch": 25.7, "learning_rate": 7.861957538388427e-05, "loss": 0.0582, "step": 107130 }, { "epoch": 25.7, "learning_rate": 7.861589604589724e-05, "loss": 0.0574, "step": 107140 }, { "epoch": 25.7, "learning_rate": 7.861221647746245e-05, "loss": 0.0603, "step": 107150 }, { "epoch": 25.7, "learning_rate": 7.860853667860952e-05, "loss": 0.062, "step": 107160 }, { "epoch": 25.71, "learning_rate": 7.86048566493681e-05, "loss": 0.0901, "step": 107170 }, { "epoch": 25.71, "learning_rate": 7.860117638976782e-05, "loss": 0.0816, "step": 107180 }, { "epoch": 25.71, "learning_rate": 7.859749589983832e-05, "loss": 0.0535, "step": 107190 }, { "epoch": 25.71, "learning_rate": 7.859381517960924e-05, "loss": 0.0642, "step": 107200 }, { "epoch": 25.72, "learning_rate": 7.859013422911021e-05, "loss": 0.0803, "step": 107210 }, { "epoch": 25.72, "learning_rate": 7.85864530483709e-05, "loss": 0.0563, "step": 107220 }, { "epoch": 25.72, "learning_rate": 7.858277163742091e-05, "loss": 0.0662, "step": 107230 }, { "epoch": 25.72, "learning_rate": 7.857908999628993e-05, "loss": 0.0718, "step": 107240 }, { "epoch": 25.73, "learning_rate": 7.857540812500758e-05, "loss": 0.0519, "step": 107250 }, { "epoch": 25.73, "learning_rate": 7.857172602360355e-05, "loss": 0.0644, "step": 107260 }, { "epoch": 25.73, "learning_rate": 7.856804369210744e-05, "loss": 0.0745, "step": 107270 }, { "epoch": 25.73, "learning_rate": 7.856436113054894e-05, "loss": 0.067, "step": 107280 }, { "epoch": 25.73, "learning_rate": 7.856067833895771e-05, "loss": 0.0804, "step": 107290 }, { "epoch": 25.74, "learning_rate": 7.855699531736338e-05, "loss": 0.0363, "step": 107300 }, { "epoch": 25.74, "learning_rate": 7.855331206579561e-05, "loss": 0.0702, "step": 107310 }, { "epoch": 25.74, "learning_rate": 7.85496285842841e-05, "loss": 0.0677, "step": 107320 }, { "epoch": 25.74, "learning_rate": 7.854594487285846e-05, "loss": 0.0389, "step": 107330 }, { "epoch": 25.75, "learning_rate": 7.854226093154842e-05, "loss": 0.073, "step": 107340 }, { "epoch": 25.75, "learning_rate": 7.853857676038359e-05, "loss": 0.0892, "step": 107350 }, { "epoch": 25.75, "learning_rate": 7.853489235939367e-05, "loss": 0.0564, "step": 107360 }, { "epoch": 25.75, "learning_rate": 7.853120772860833e-05, "loss": 0.0585, "step": 107370 }, { "epoch": 25.76, "learning_rate": 7.852752286805723e-05, "loss": 0.0387, "step": 107380 }, { "epoch": 25.76, "learning_rate": 7.852383777777004e-05, "loss": 0.0598, "step": 107390 }, { "epoch": 25.76, "learning_rate": 7.852015245777645e-05, "loss": 0.1026, "step": 107400 }, { "epoch": 25.76, "learning_rate": 7.851646690810615e-05, "loss": 0.0704, "step": 107410 }, { "epoch": 25.76, "learning_rate": 7.851278112878878e-05, "loss": 0.0688, "step": 107420 }, { "epoch": 25.77, "learning_rate": 7.850909511985405e-05, "loss": 0.0526, "step": 107430 }, { "epoch": 25.77, "learning_rate": 7.850540888133166e-05, "loss": 0.066, "step": 107440 }, { "epoch": 25.77, "learning_rate": 7.850172241325126e-05, "loss": 0.07, "step": 107450 }, { "epoch": 25.77, "learning_rate": 7.849803571564257e-05, "loss": 0.0704, "step": 107460 }, { "epoch": 25.78, "learning_rate": 7.849434878853526e-05, "loss": 0.0633, "step": 107470 }, { "epoch": 25.78, "learning_rate": 7.849066163195902e-05, "loss": 0.0677, "step": 107480 }, { "epoch": 25.78, "learning_rate": 7.848697424594356e-05, "loss": 0.0647, "step": 107490 }, { "epoch": 25.78, "learning_rate": 7.848328663051854e-05, "loss": 0.0706, "step": 107500 }, { "epoch": 25.78, "learning_rate": 7.84795987857137e-05, "loss": 0.0602, "step": 107510 }, { "epoch": 25.79, "learning_rate": 7.847591071155871e-05, "loss": 0.0711, "step": 107520 }, { "epoch": 25.79, "learning_rate": 7.847222240808329e-05, "loss": 0.0482, "step": 107530 }, { "epoch": 25.79, "learning_rate": 7.846853387531712e-05, "loss": 0.0479, "step": 107540 }, { "epoch": 25.79, "learning_rate": 7.846484511328991e-05, "loss": 0.0491, "step": 107550 }, { "epoch": 25.8, "learning_rate": 7.846115612203139e-05, "loss": 0.0701, "step": 107560 }, { "epoch": 25.8, "learning_rate": 7.845746690157124e-05, "loss": 0.0662, "step": 107570 }, { "epoch": 25.8, "learning_rate": 7.845377745193919e-05, "loss": 0.0878, "step": 107580 }, { "epoch": 25.8, "learning_rate": 7.845008777316494e-05, "loss": 0.0435, "step": 107590 }, { "epoch": 25.81, "learning_rate": 7.84463978652782e-05, "loss": 0.0761, "step": 107600 }, { "epoch": 25.81, "learning_rate": 7.844270772830869e-05, "loss": 0.0824, "step": 107610 }, { "epoch": 25.81, "learning_rate": 7.843901736228613e-05, "loss": 0.0756, "step": 107620 }, { "epoch": 25.81, "learning_rate": 7.843532676724024e-05, "loss": 0.0595, "step": 107630 }, { "epoch": 25.81, "learning_rate": 7.843163594320074e-05, "loss": 0.0425, "step": 107640 }, { "epoch": 25.82, "learning_rate": 7.842794489019733e-05, "loss": 0.0501, "step": 107650 }, { "epoch": 25.82, "learning_rate": 7.842425360825978e-05, "loss": 0.0411, "step": 107660 }, { "epoch": 25.82, "learning_rate": 7.842056209741778e-05, "loss": 0.0669, "step": 107670 }, { "epoch": 25.82, "learning_rate": 7.841687035770106e-05, "loss": 0.0718, "step": 107680 }, { "epoch": 25.83, "learning_rate": 7.841317838913938e-05, "loss": 0.0351, "step": 107690 }, { "epoch": 25.83, "learning_rate": 7.840948619176246e-05, "loss": 0.0457, "step": 107700 }, { "epoch": 25.83, "learning_rate": 7.84057937656e-05, "loss": 0.0447, "step": 107710 }, { "epoch": 25.83, "learning_rate": 7.840210111068176e-05, "loss": 0.0655, "step": 107720 }, { "epoch": 25.84, "learning_rate": 7.839840822703749e-05, "loss": 0.0563, "step": 107730 }, { "epoch": 25.84, "learning_rate": 7.839471511469692e-05, "loss": 0.0658, "step": 107740 }, { "epoch": 25.84, "learning_rate": 7.839102177368977e-05, "loss": 0.0824, "step": 107750 }, { "epoch": 25.84, "learning_rate": 7.838732820404582e-05, "loss": 0.0442, "step": 107760 }, { "epoch": 25.84, "learning_rate": 7.838363440579481e-05, "loss": 0.0697, "step": 107770 }, { "epoch": 25.85, "learning_rate": 7.837994037896646e-05, "loss": 0.0593, "step": 107780 }, { "epoch": 25.85, "learning_rate": 7.837624612359053e-05, "loss": 0.0524, "step": 107790 }, { "epoch": 25.85, "learning_rate": 7.837255163969677e-05, "loss": 0.0518, "step": 107800 }, { "epoch": 25.85, "learning_rate": 7.836885692731492e-05, "loss": 0.0731, "step": 107810 }, { "epoch": 25.86, "learning_rate": 7.836516198647477e-05, "loss": 0.0701, "step": 107820 }, { "epoch": 25.86, "learning_rate": 7.836146681720604e-05, "loss": 0.0866, "step": 107830 }, { "epoch": 25.86, "learning_rate": 7.835777141953853e-05, "loss": 0.05, "step": 107840 }, { "epoch": 25.86, "learning_rate": 7.835407579350194e-05, "loss": 0.0656, "step": 107850 }, { "epoch": 25.86, "learning_rate": 7.835037993912608e-05, "loss": 0.0496, "step": 107860 }, { "epoch": 25.87, "learning_rate": 7.83466838564407e-05, "loss": 0.0598, "step": 107870 }, { "epoch": 25.87, "learning_rate": 7.834298754547556e-05, "loss": 0.0779, "step": 107880 }, { "epoch": 25.87, "learning_rate": 7.833929100626041e-05, "loss": 0.068, "step": 107890 }, { "epoch": 25.87, "learning_rate": 7.833559423882506e-05, "loss": 0.0599, "step": 107900 }, { "epoch": 25.88, "learning_rate": 7.833189724319925e-05, "loss": 0.0759, "step": 107910 }, { "epoch": 25.88, "learning_rate": 7.832820001941275e-05, "loss": 0.0601, "step": 107920 }, { "epoch": 25.88, "learning_rate": 7.832450256749536e-05, "loss": 0.0608, "step": 107930 }, { "epoch": 25.88, "learning_rate": 7.832080488747681e-05, "loss": 0.0409, "step": 107940 }, { "epoch": 25.89, "learning_rate": 7.831710697938694e-05, "loss": 0.0947, "step": 107950 }, { "epoch": 25.89, "learning_rate": 7.83134088432555e-05, "loss": 0.0784, "step": 107960 }, { "epoch": 25.89, "learning_rate": 7.830971047911225e-05, "loss": 0.0872, "step": 107970 }, { "epoch": 25.89, "learning_rate": 7.8306011886987e-05, "loss": 0.0407, "step": 107980 }, { "epoch": 25.89, "learning_rate": 7.830231306690954e-05, "loss": 0.0479, "step": 107990 }, { "epoch": 25.9, "learning_rate": 7.829861401890964e-05, "loss": 0.0598, "step": 108000 }, { "epoch": 25.9, "learning_rate": 7.829491474301708e-05, "loss": 0.0639, "step": 108010 }, { "epoch": 25.9, "learning_rate": 7.829121523926168e-05, "loss": 0.0482, "step": 108020 }, { "epoch": 25.9, "learning_rate": 7.828751550767322e-05, "loss": 0.0683, "step": 108030 }, { "epoch": 25.91, "learning_rate": 7.828381554828146e-05, "loss": 0.038, "step": 108040 }, { "epoch": 25.91, "learning_rate": 7.828011536111627e-05, "loss": 0.0511, "step": 108050 }, { "epoch": 25.91, "learning_rate": 7.827641494620739e-05, "loss": 0.0808, "step": 108060 }, { "epoch": 25.91, "learning_rate": 7.827271430358464e-05, "loss": 0.0797, "step": 108070 }, { "epoch": 25.92, "learning_rate": 7.826901343327781e-05, "loss": 0.0627, "step": 108080 }, { "epoch": 25.92, "learning_rate": 7.82653123353167e-05, "loss": 0.0488, "step": 108090 }, { "epoch": 25.92, "learning_rate": 7.826161100973116e-05, "loss": 0.0342, "step": 108100 }, { "epoch": 25.92, "learning_rate": 7.825790945655094e-05, "loss": 0.0535, "step": 108110 }, { "epoch": 25.92, "learning_rate": 7.825420767580589e-05, "loss": 0.0664, "step": 108120 }, { "epoch": 25.93, "learning_rate": 7.825050566752581e-05, "loss": 0.055, "step": 108130 }, { "epoch": 25.93, "learning_rate": 7.824680343174049e-05, "loss": 0.08, "step": 108140 }, { "epoch": 25.93, "learning_rate": 7.824310096847977e-05, "loss": 0.0634, "step": 108150 }, { "epoch": 25.93, "learning_rate": 7.823939827777344e-05, "loss": 0.053, "step": 108160 }, { "epoch": 25.94, "learning_rate": 7.823569535965137e-05, "loss": 0.0328, "step": 108170 }, { "epoch": 25.94, "learning_rate": 7.823199221414333e-05, "loss": 0.0896, "step": 108180 }, { "epoch": 25.94, "learning_rate": 7.822828884127917e-05, "loss": 0.0452, "step": 108190 }, { "epoch": 25.94, "learning_rate": 7.822458524108869e-05, "loss": 0.0782, "step": 108200 }, { "epoch": 25.94, "learning_rate": 7.822088141360173e-05, "loss": 0.053, "step": 108210 }, { "epoch": 25.95, "learning_rate": 7.821717735884812e-05, "loss": 0.0623, "step": 108220 }, { "epoch": 25.95, "learning_rate": 7.821347307685767e-05, "loss": 0.0522, "step": 108230 }, { "epoch": 26.0, "learning_rate": 7.820976856766025e-05, "loss": 0.0442, "step": 108240 }, { "epoch": 26.0, "learning_rate": 7.820606383128565e-05, "loss": 0.0592, "step": 108250 }, { "epoch": 26.01, "learning_rate": 7.820235886776373e-05, "loss": 0.0457, "step": 108260 }, { "epoch": 26.01, "learning_rate": 7.819865367712432e-05, "loss": 0.0401, "step": 108270 }, { "epoch": 26.01, "learning_rate": 7.819494825939726e-05, "loss": 0.0431, "step": 108280 }, { "epoch": 26.01, "learning_rate": 7.81912426146124e-05, "loss": 0.0588, "step": 108290 }, { "epoch": 26.01, "learning_rate": 7.818753674279955e-05, "loss": 0.0686, "step": 108300 }, { "epoch": 26.02, "learning_rate": 7.81838306439886e-05, "loss": 0.0633, "step": 108310 }, { "epoch": 26.02, "learning_rate": 7.818012431820935e-05, "loss": 0.043, "step": 108320 }, { "epoch": 26.02, "learning_rate": 7.817641776549167e-05, "loss": 0.0752, "step": 108330 }, { "epoch": 26.02, "learning_rate": 7.817271098586542e-05, "loss": 0.0676, "step": 108340 }, { "epoch": 26.03, "learning_rate": 7.816900397936042e-05, "loss": 0.0443, "step": 108350 }, { "epoch": 26.03, "learning_rate": 7.816529674600657e-05, "loss": 0.0454, "step": 108360 }, { "epoch": 26.03, "learning_rate": 7.816158928583367e-05, "loss": 0.077, "step": 108370 }, { "epoch": 26.03, "learning_rate": 7.815788159887161e-05, "loss": 0.0586, "step": 108380 }, { "epoch": 26.03, "learning_rate": 7.815417368515026e-05, "loss": 0.0442, "step": 108390 }, { "epoch": 26.04, "learning_rate": 7.815046554469945e-05, "loss": 0.109, "step": 108400 }, { "epoch": 26.04, "learning_rate": 7.814675717754905e-05, "loss": 0.0457, "step": 108410 }, { "epoch": 26.04, "learning_rate": 7.814304858372892e-05, "loss": 0.0579, "step": 108420 }, { "epoch": 26.04, "learning_rate": 7.813933976326894e-05, "loss": 0.0902, "step": 108430 }, { "epoch": 26.05, "learning_rate": 7.813563071619898e-05, "loss": 0.0809, "step": 108440 }, { "epoch": 26.05, "learning_rate": 7.813192144254892e-05, "loss": 0.0599, "step": 108450 }, { "epoch": 26.05, "learning_rate": 7.812821194234858e-05, "loss": 0.0614, "step": 108460 }, { "epoch": 26.05, "learning_rate": 7.812450221562788e-05, "loss": 0.0769, "step": 108470 }, { "epoch": 26.06, "learning_rate": 7.812079226241669e-05, "loss": 0.0499, "step": 108480 }, { "epoch": 26.06, "learning_rate": 7.811708208274487e-05, "loss": 0.0309, "step": 108490 }, { "epoch": 26.06, "learning_rate": 7.81133716766423e-05, "loss": 0.0454, "step": 108500 }, { "epoch": 26.06, "learning_rate": 7.810966104413885e-05, "loss": 0.0497, "step": 108510 }, { "epoch": 26.06, "learning_rate": 7.810595018526445e-05, "loss": 0.0723, "step": 108520 }, { "epoch": 26.07, "learning_rate": 7.810223910004894e-05, "loss": 0.0498, "step": 108530 }, { "epoch": 26.07, "learning_rate": 7.809852778852222e-05, "loss": 0.0452, "step": 108540 }, { "epoch": 26.07, "learning_rate": 7.809481625071417e-05, "loss": 0.0456, "step": 108550 }, { "epoch": 26.07, "learning_rate": 7.80911044866547e-05, "loss": 0.048, "step": 108560 }, { "epoch": 26.08, "learning_rate": 7.808739249637369e-05, "loss": 0.048, "step": 108570 }, { "epoch": 26.08, "learning_rate": 7.8083680279901e-05, "loss": 0.0681, "step": 108580 }, { "epoch": 26.08, "learning_rate": 7.807996783726658e-05, "loss": 0.0768, "step": 108590 }, { "epoch": 26.08, "learning_rate": 7.80762551685003e-05, "loss": 0.036, "step": 108600 }, { "epoch": 26.09, "learning_rate": 7.807254227363205e-05, "loss": 0.0689, "step": 108610 }, { "epoch": 26.09, "learning_rate": 7.806882915269176e-05, "loss": 0.0728, "step": 108620 }, { "epoch": 26.09, "learning_rate": 7.80651158057093e-05, "loss": 0.0555, "step": 108630 }, { "epoch": 26.09, "learning_rate": 7.806140223271461e-05, "loss": 0.0802, "step": 108640 }, { "epoch": 26.09, "learning_rate": 7.805768843373755e-05, "loss": 0.0313, "step": 108650 }, { "epoch": 26.1, "learning_rate": 7.805397440880806e-05, "loss": 0.05, "step": 108660 }, { "epoch": 26.1, "learning_rate": 7.805026015795604e-05, "loss": 0.0642, "step": 108670 }, { "epoch": 26.1, "learning_rate": 7.804654568121139e-05, "loss": 0.032, "step": 108680 }, { "epoch": 26.1, "learning_rate": 7.804283097860405e-05, "loss": 0.0368, "step": 108690 }, { "epoch": 26.11, "learning_rate": 7.803911605016392e-05, "loss": 0.0524, "step": 108700 }, { "epoch": 26.11, "learning_rate": 7.803540089592092e-05, "loss": 0.0394, "step": 108710 }, { "epoch": 26.11, "learning_rate": 7.803168551590495e-05, "loss": 0.0632, "step": 108720 }, { "epoch": 26.11, "learning_rate": 7.802796991014596e-05, "loss": 0.0723, "step": 108730 }, { "epoch": 26.11, "learning_rate": 7.802425407867386e-05, "loss": 0.0738, "step": 108740 }, { "epoch": 26.12, "learning_rate": 7.802053802151856e-05, "loss": 0.0437, "step": 108750 }, { "epoch": 26.12, "learning_rate": 7.801682173871002e-05, "loss": 0.0592, "step": 108760 }, { "epoch": 26.12, "learning_rate": 7.801310523027813e-05, "loss": 0.0521, "step": 108770 }, { "epoch": 26.12, "learning_rate": 7.800938849625283e-05, "loss": 0.0718, "step": 108780 }, { "epoch": 26.13, "learning_rate": 7.800567153666407e-05, "loss": 0.0511, "step": 108790 }, { "epoch": 26.13, "learning_rate": 7.800195435154178e-05, "loss": 0.0664, "step": 108800 }, { "epoch": 26.13, "learning_rate": 7.799823694091586e-05, "loss": 0.0778, "step": 108810 }, { "epoch": 26.13, "learning_rate": 7.79945193048163e-05, "loss": 0.0863, "step": 108820 }, { "epoch": 26.14, "learning_rate": 7.799080144327298e-05, "loss": 0.0524, "step": 108830 }, { "epoch": 26.14, "learning_rate": 7.798708335631589e-05, "loss": 0.0425, "step": 108840 }, { "epoch": 26.14, "learning_rate": 7.798336504397496e-05, "loss": 0.0601, "step": 108850 }, { "epoch": 26.14, "learning_rate": 7.797964650628012e-05, "loss": 0.0592, "step": 108860 }, { "epoch": 26.14, "learning_rate": 7.797592774326134e-05, "loss": 0.0419, "step": 108870 }, { "epoch": 26.15, "learning_rate": 7.797220875494853e-05, "loss": 0.0628, "step": 108880 }, { "epoch": 26.15, "learning_rate": 7.796848954137166e-05, "loss": 0.0708, "step": 108890 }, { "epoch": 26.15, "learning_rate": 7.796477010256069e-05, "loss": 0.0464, "step": 108900 }, { "epoch": 26.15, "learning_rate": 7.796105043854556e-05, "loss": 0.0561, "step": 108910 }, { "epoch": 26.16, "learning_rate": 7.795733054935625e-05, "loss": 0.0595, "step": 108920 }, { "epoch": 26.16, "learning_rate": 7.795361043502267e-05, "loss": 0.0616, "step": 108930 }, { "epoch": 26.16, "learning_rate": 7.794989009557482e-05, "loss": 0.0502, "step": 108940 }, { "epoch": 26.16, "learning_rate": 7.794616953104266e-05, "loss": 0.05, "step": 108950 }, { "epoch": 26.16, "learning_rate": 7.794244874145611e-05, "loss": 0.0465, "step": 108960 }, { "epoch": 26.17, "learning_rate": 7.793872772684519e-05, "loss": 0.0798, "step": 108970 }, { "epoch": 26.17, "learning_rate": 7.793500648723981e-05, "loss": 0.052, "step": 108980 }, { "epoch": 26.17, "learning_rate": 7.793128502267e-05, "loss": 0.0699, "step": 108990 }, { "epoch": 26.17, "learning_rate": 7.792756333316567e-05, "loss": 0.0762, "step": 109000 }, { "epoch": 26.18, "learning_rate": 7.792384141875682e-05, "loss": 0.0492, "step": 109010 }, { "epoch": 26.18, "learning_rate": 7.792011927947342e-05, "loss": 0.0736, "step": 109020 }, { "epoch": 26.18, "learning_rate": 7.791639691534544e-05, "loss": 0.0515, "step": 109030 }, { "epoch": 26.18, "learning_rate": 7.791267432640288e-05, "loss": 0.0495, "step": 109040 }, { "epoch": 26.19, "learning_rate": 7.79089515126757e-05, "loss": 0.0554, "step": 109050 }, { "epoch": 26.19, "learning_rate": 7.790522847419386e-05, "loss": 0.0425, "step": 109060 }, { "epoch": 26.19, "learning_rate": 7.790150521098738e-05, "loss": 0.0579, "step": 109070 }, { "epoch": 26.19, "learning_rate": 7.789778172308622e-05, "loss": 0.0403, "step": 109080 }, { "epoch": 26.19, "learning_rate": 7.789405801052036e-05, "loss": 0.0342, "step": 109090 }, { "epoch": 26.2, "learning_rate": 7.789033407331983e-05, "loss": 0.0405, "step": 109100 }, { "epoch": 26.2, "learning_rate": 7.788660991151457e-05, "loss": 0.0435, "step": 109110 }, { "epoch": 26.2, "learning_rate": 7.788288552513458e-05, "loss": 0.052, "step": 109120 }, { "epoch": 26.2, "learning_rate": 7.787916091420989e-05, "loss": 0.0777, "step": 109130 }, { "epoch": 26.21, "learning_rate": 7.787543607877043e-05, "loss": 0.0711, "step": 109140 }, { "epoch": 26.21, "learning_rate": 7.787171101884627e-05, "loss": 0.0546, "step": 109150 }, { "epoch": 26.21, "learning_rate": 7.786798573446736e-05, "loss": 0.0441, "step": 109160 }, { "epoch": 26.21, "learning_rate": 7.786426022566372e-05, "loss": 0.0412, "step": 109170 }, { "epoch": 26.22, "learning_rate": 7.786053449246533e-05, "loss": 0.0972, "step": 109180 }, { "epoch": 26.22, "learning_rate": 7.785680853490222e-05, "loss": 0.0822, "step": 109190 }, { "epoch": 26.22, "learning_rate": 7.78530823530044e-05, "loss": 0.038, "step": 109200 }, { "epoch": 26.22, "learning_rate": 7.784935594680184e-05, "loss": 0.0537, "step": 109210 }, { "epoch": 26.22, "learning_rate": 7.784562931632458e-05, "loss": 0.0375, "step": 109220 }, { "epoch": 26.23, "learning_rate": 7.784190246160262e-05, "loss": 0.0566, "step": 109230 }, { "epoch": 26.23, "learning_rate": 7.783817538266597e-05, "loss": 0.0469, "step": 109240 }, { "epoch": 26.23, "learning_rate": 7.783444807954465e-05, "loss": 0.074, "step": 109250 }, { "epoch": 26.23, "learning_rate": 7.78307205522687e-05, "loss": 0.0819, "step": 109260 }, { "epoch": 26.24, "learning_rate": 7.78269928008681e-05, "loss": 0.0475, "step": 109270 }, { "epoch": 26.24, "learning_rate": 7.782326482537287e-05, "loss": 0.0628, "step": 109280 }, { "epoch": 26.24, "learning_rate": 7.781953662581308e-05, "loss": 0.0566, "step": 109290 }, { "epoch": 26.24, "learning_rate": 7.78158082022187e-05, "loss": 0.0464, "step": 109300 }, { "epoch": 26.24, "learning_rate": 7.781207955461977e-05, "loss": 0.0617, "step": 109310 }, { "epoch": 26.25, "learning_rate": 7.780835068304633e-05, "loss": 0.0528, "step": 109320 }, { "epoch": 26.25, "learning_rate": 7.780462158752841e-05, "loss": 0.0296, "step": 109330 }, { "epoch": 26.25, "learning_rate": 7.780089226809602e-05, "loss": 0.0565, "step": 109340 }, { "epoch": 26.25, "learning_rate": 7.779716272477922e-05, "loss": 0.0358, "step": 109350 }, { "epoch": 26.26, "learning_rate": 7.779343295760803e-05, "loss": 0.0633, "step": 109360 }, { "epoch": 26.26, "learning_rate": 7.778970296661248e-05, "loss": 0.0523, "step": 109370 }, { "epoch": 26.26, "learning_rate": 7.778597275182262e-05, "loss": 0.0309, "step": 109380 }, { "epoch": 26.26, "learning_rate": 7.77822423132685e-05, "loss": 0.0355, "step": 109390 }, { "epoch": 26.27, "learning_rate": 7.777851165098012e-05, "loss": 0.0567, "step": 109400 }, { "epoch": 26.27, "learning_rate": 7.777478076498755e-05, "loss": 0.0432, "step": 109410 }, { "epoch": 26.27, "learning_rate": 7.777104965532086e-05, "loss": 0.0473, "step": 109420 }, { "epoch": 26.27, "learning_rate": 7.776731832201006e-05, "loss": 0.0399, "step": 109430 }, { "epoch": 26.27, "learning_rate": 7.776358676508522e-05, "loss": 0.0739, "step": 109440 }, { "epoch": 26.28, "learning_rate": 7.775985498457637e-05, "loss": 0.062, "step": 109450 }, { "epoch": 26.28, "learning_rate": 7.775612298051358e-05, "loss": 0.0554, "step": 109460 }, { "epoch": 26.28, "learning_rate": 7.77523907529269e-05, "loss": 0.044, "step": 109470 }, { "epoch": 26.28, "learning_rate": 7.774865830184639e-05, "loss": 0.0458, "step": 109480 }, { "epoch": 26.29, "learning_rate": 7.77449256273021e-05, "loss": 0.08, "step": 109490 }, { "epoch": 26.29, "learning_rate": 7.774119272932409e-05, "loss": 0.0572, "step": 109500 }, { "epoch": 26.29, "learning_rate": 7.773745960794243e-05, "loss": 0.0321, "step": 109510 }, { "epoch": 26.29, "learning_rate": 7.773372626318717e-05, "loss": 0.0373, "step": 109520 }, { "epoch": 26.3, "learning_rate": 7.77299926950884e-05, "loss": 0.0437, "step": 109530 }, { "epoch": 26.3, "learning_rate": 7.772625890367615e-05, "loss": 0.0503, "step": 109540 }, { "epoch": 26.3, "learning_rate": 7.772252488898053e-05, "loss": 0.0641, "step": 109550 }, { "epoch": 26.3, "learning_rate": 7.771879065103157e-05, "loss": 0.0529, "step": 109560 }, { "epoch": 26.3, "learning_rate": 7.771505618985938e-05, "loss": 0.0632, "step": 109570 }, { "epoch": 26.31, "learning_rate": 7.771132150549401e-05, "loss": 0.0736, "step": 109580 }, { "epoch": 26.31, "learning_rate": 7.770758659796553e-05, "loss": 0.0444, "step": 109590 }, { "epoch": 26.31, "learning_rate": 7.770385146730405e-05, "loss": 0.0582, "step": 109600 }, { "epoch": 26.31, "learning_rate": 7.770011611353962e-05, "loss": 0.03, "step": 109610 }, { "epoch": 26.32, "learning_rate": 7.769638053670232e-05, "loss": 0.0522, "step": 109620 }, { "epoch": 26.32, "learning_rate": 7.769264473682227e-05, "loss": 0.0643, "step": 109630 }, { "epoch": 26.32, "learning_rate": 7.768890871392951e-05, "loss": 0.0524, "step": 109640 }, { "epoch": 26.32, "learning_rate": 7.768517246805416e-05, "loss": 0.047, "step": 109650 }, { "epoch": 26.32, "learning_rate": 7.768143599922627e-05, "loss": 0.0696, "step": 109660 }, { "epoch": 26.33, "learning_rate": 7.767769930747598e-05, "loss": 0.0341, "step": 109670 }, { "epoch": 26.33, "learning_rate": 7.767396239283333e-05, "loss": 0.0472, "step": 109680 }, { "epoch": 26.33, "learning_rate": 7.767022525532845e-05, "loss": 0.0472, "step": 109690 }, { "epoch": 26.33, "learning_rate": 7.766648789499143e-05, "loss": 0.0445, "step": 109700 }, { "epoch": 26.34, "learning_rate": 7.766275031185237e-05, "loss": 0.0442, "step": 109710 }, { "epoch": 26.34, "learning_rate": 7.765901250594135e-05, "loss": 0.0814, "step": 109720 }, { "epoch": 26.34, "learning_rate": 7.765527447728849e-05, "loss": 0.0585, "step": 109730 }, { "epoch": 26.34, "learning_rate": 7.765153622592389e-05, "loss": 0.0336, "step": 109740 }, { "epoch": 26.35, "learning_rate": 7.764779775187764e-05, "loss": 0.0671, "step": 109750 }, { "epoch": 26.35, "learning_rate": 7.764405905517986e-05, "loss": 0.0536, "step": 109760 }, { "epoch": 26.35, "learning_rate": 7.764032013586067e-05, "loss": 0.0502, "step": 109770 }, { "epoch": 26.35, "learning_rate": 7.763658099395015e-05, "loss": 0.0425, "step": 109780 }, { "epoch": 26.35, "learning_rate": 7.763284162947844e-05, "loss": 0.0554, "step": 109790 }, { "epoch": 26.36, "learning_rate": 7.762910204247562e-05, "loss": 0.0609, "step": 109800 }, { "epoch": 26.36, "learning_rate": 7.762536223297185e-05, "loss": 0.0668, "step": 109810 }, { "epoch": 26.36, "learning_rate": 7.762162220099722e-05, "loss": 0.049, "step": 109820 }, { "epoch": 26.36, "learning_rate": 7.761788194658185e-05, "loss": 0.0426, "step": 109830 }, { "epoch": 26.37, "learning_rate": 7.761414146975586e-05, "loss": 0.0748, "step": 109840 }, { "epoch": 26.37, "learning_rate": 7.761040077054938e-05, "loss": 0.0486, "step": 109850 }, { "epoch": 26.37, "learning_rate": 7.760665984899253e-05, "loss": 0.0698, "step": 109860 }, { "epoch": 26.37, "learning_rate": 7.760291870511543e-05, "loss": 0.0891, "step": 109870 }, { "epoch": 26.38, "learning_rate": 7.759917733894823e-05, "loss": 0.0869, "step": 109880 }, { "epoch": 26.38, "learning_rate": 7.759543575052104e-05, "loss": 0.0548, "step": 109890 }, { "epoch": 26.38, "learning_rate": 7.759169393986398e-05, "loss": 0.06, "step": 109900 }, { "epoch": 26.38, "learning_rate": 7.758795190700723e-05, "loss": 0.047, "step": 109910 }, { "epoch": 26.38, "learning_rate": 7.758420965198087e-05, "loss": 0.0391, "step": 109920 }, { "epoch": 26.39, "learning_rate": 7.758046717481507e-05, "loss": 0.031, "step": 109930 }, { "epoch": 26.39, "learning_rate": 7.757672447553996e-05, "loss": 0.059, "step": 109940 }, { "epoch": 26.39, "learning_rate": 7.757298155418566e-05, "loss": 0.0364, "step": 109950 }, { "epoch": 26.39, "learning_rate": 7.756923841078237e-05, "loss": 0.0442, "step": 109960 }, { "epoch": 26.4, "learning_rate": 7.756549504536017e-05, "loss": 0.0563, "step": 109970 }, { "epoch": 26.4, "learning_rate": 7.756175145794925e-05, "loss": 0.041, "step": 109980 }, { "epoch": 26.4, "learning_rate": 7.755800764857972e-05, "loss": 0.0754, "step": 109990 }, { "epoch": 26.4, "learning_rate": 7.755426361728177e-05, "loss": 0.0396, "step": 110000 }, { "epoch": 26.4, "learning_rate": 7.755051936408553e-05, "loss": 0.0736, "step": 110010 }, { "epoch": 26.41, "learning_rate": 7.754677488902113e-05, "loss": 0.0633, "step": 110020 }, { "epoch": 26.41, "learning_rate": 7.754303019211877e-05, "loss": 0.0676, "step": 110030 }, { "epoch": 26.41, "learning_rate": 7.753928527340858e-05, "loss": 0.0513, "step": 110040 }, { "epoch": 26.41, "learning_rate": 7.753554013292073e-05, "loss": 0.043, "step": 110050 }, { "epoch": 26.42, "learning_rate": 7.753179477068537e-05, "loss": 0.062, "step": 110060 }, { "epoch": 26.42, "learning_rate": 7.752804918673266e-05, "loss": 0.0682, "step": 110070 }, { "epoch": 26.42, "learning_rate": 7.752430338109277e-05, "loss": 0.0612, "step": 110080 }, { "epoch": 26.42, "learning_rate": 7.752055735379586e-05, "loss": 0.0485, "step": 110090 }, { "epoch": 26.43, "learning_rate": 7.751681110487212e-05, "loss": 0.0534, "step": 110100 }, { "epoch": 26.43, "learning_rate": 7.751306463435168e-05, "loss": 0.0261, "step": 110110 }, { "epoch": 26.43, "learning_rate": 7.750931794226475e-05, "loss": 0.0374, "step": 110120 }, { "epoch": 26.43, "learning_rate": 7.750557102864148e-05, "loss": 0.0742, "step": 110130 }, { "epoch": 26.43, "learning_rate": 7.750182389351205e-05, "loss": 0.0507, "step": 110140 }, { "epoch": 26.44, "learning_rate": 7.749807653690664e-05, "loss": 0.0669, "step": 110150 }, { "epoch": 26.44, "learning_rate": 7.749432895885541e-05, "loss": 0.0588, "step": 110160 }, { "epoch": 26.44, "learning_rate": 7.749058115938856e-05, "loss": 0.0589, "step": 110170 }, { "epoch": 26.44, "learning_rate": 7.748683313853627e-05, "loss": 0.056, "step": 110180 }, { "epoch": 26.45, "learning_rate": 7.748308489632871e-05, "loss": 0.0867, "step": 110190 }, { "epoch": 26.45, "learning_rate": 7.747933643279607e-05, "loss": 0.0565, "step": 110200 }, { "epoch": 26.45, "learning_rate": 7.747558774796855e-05, "loss": 0.0502, "step": 110210 }, { "epoch": 26.45, "learning_rate": 7.747183884187632e-05, "loss": 0.0303, "step": 110220 }, { "epoch": 26.46, "learning_rate": 7.746808971454958e-05, "loss": 0.0422, "step": 110230 }, { "epoch": 26.46, "learning_rate": 7.746434036601853e-05, "loss": 0.0441, "step": 110240 }, { "epoch": 26.46, "learning_rate": 7.746059079631334e-05, "loss": 0.0443, "step": 110250 }, { "epoch": 26.46, "learning_rate": 7.745684100546423e-05, "loss": 0.0726, "step": 110260 }, { "epoch": 26.46, "learning_rate": 7.74530909935014e-05, "loss": 0.0785, "step": 110270 }, { "epoch": 26.47, "learning_rate": 7.744934076045502e-05, "loss": 0.0624, "step": 110280 }, { "epoch": 26.47, "learning_rate": 7.744559030635533e-05, "loss": 0.0797, "step": 110290 }, { "epoch": 26.47, "learning_rate": 7.744183963123248e-05, "loss": 0.0614, "step": 110300 }, { "epoch": 26.47, "learning_rate": 7.743808873511673e-05, "loss": 0.0428, "step": 110310 }, { "epoch": 26.48, "learning_rate": 7.743433761803825e-05, "loss": 0.0522, "step": 110320 }, { "epoch": 26.48, "learning_rate": 7.743058628002727e-05, "loss": 0.0724, "step": 110330 }, { "epoch": 26.48, "learning_rate": 7.742683472111401e-05, "loss": 0.0962, "step": 110340 }, { "epoch": 26.48, "learning_rate": 7.742308294132863e-05, "loss": 0.0419, "step": 110350 }, { "epoch": 26.48, "learning_rate": 7.74193309407014e-05, "loss": 0.0496, "step": 110360 }, { "epoch": 26.49, "learning_rate": 7.741557871926251e-05, "loss": 0.0777, "step": 110370 }, { "epoch": 26.49, "learning_rate": 7.741182627704217e-05, "loss": 0.0578, "step": 110380 }, { "epoch": 26.49, "learning_rate": 7.740807361407061e-05, "loss": 0.0361, "step": 110390 }, { "epoch": 26.49, "learning_rate": 7.740432073037804e-05, "loss": 0.0556, "step": 110400 }, { "epoch": 26.5, "learning_rate": 7.740056762599471e-05, "loss": 0.0574, "step": 110410 }, { "epoch": 26.5, "learning_rate": 7.739681430095082e-05, "loss": 0.0572, "step": 110420 }, { "epoch": 26.5, "learning_rate": 7.739306075527662e-05, "loss": 0.0486, "step": 110430 }, { "epoch": 26.5, "learning_rate": 7.738930698900228e-05, "loss": 0.0444, "step": 110440 }, { "epoch": 26.51, "learning_rate": 7.738555300215811e-05, "loss": 0.0566, "step": 110450 }, { "epoch": 26.51, "learning_rate": 7.738179879477427e-05, "loss": 0.0563, "step": 110460 }, { "epoch": 26.51, "learning_rate": 7.737804436688104e-05, "loss": 0.0421, "step": 110470 }, { "epoch": 26.51, "learning_rate": 7.737428971850865e-05, "loss": 0.0468, "step": 110480 }, { "epoch": 26.51, "learning_rate": 7.73705348496873e-05, "loss": 0.0564, "step": 110490 }, { "epoch": 26.52, "learning_rate": 7.736677976044726e-05, "loss": 0.0594, "step": 110500 }, { "epoch": 26.52, "learning_rate": 7.736302445081878e-05, "loss": 0.0698, "step": 110510 }, { "epoch": 26.52, "learning_rate": 7.735926892083207e-05, "loss": 0.0631, "step": 110520 }, { "epoch": 26.52, "learning_rate": 7.735551317051739e-05, "loss": 0.0411, "step": 110530 }, { "epoch": 26.53, "learning_rate": 7.735175719990499e-05, "loss": 0.0681, "step": 110540 }, { "epoch": 26.53, "learning_rate": 7.734800100902513e-05, "loss": 0.0612, "step": 110550 }, { "epoch": 26.53, "learning_rate": 7.7344244597908e-05, "loss": 0.0748, "step": 110560 }, { "epoch": 26.53, "learning_rate": 7.734048796658394e-05, "loss": 0.0467, "step": 110570 }, { "epoch": 26.54, "learning_rate": 7.733673111508313e-05, "loss": 0.0464, "step": 110580 }, { "epoch": 26.54, "learning_rate": 7.733297404343586e-05, "loss": 0.0533, "step": 110590 }, { "epoch": 26.54, "learning_rate": 7.732921675167237e-05, "loss": 0.0654, "step": 110600 }, { "epoch": 26.54, "learning_rate": 7.732545923982292e-05, "loss": 0.0574, "step": 110610 }, { "epoch": 26.54, "learning_rate": 7.73217015079178e-05, "loss": 0.0804, "step": 110620 }, { "epoch": 26.55, "learning_rate": 7.731794355598723e-05, "loss": 0.0962, "step": 110630 }, { "epoch": 26.55, "learning_rate": 7.731418538406148e-05, "loss": 0.0636, "step": 110640 }, { "epoch": 26.55, "learning_rate": 7.731042699217083e-05, "loss": 0.09, "step": 110650 }, { "epoch": 26.55, "learning_rate": 7.730666838034553e-05, "loss": 0.0646, "step": 110660 }, { "epoch": 26.56, "learning_rate": 7.730290954861588e-05, "loss": 0.0656, "step": 110670 }, { "epoch": 26.56, "learning_rate": 7.729915049701212e-05, "loss": 0.0744, "step": 110680 }, { "epoch": 26.56, "learning_rate": 7.729539122556454e-05, "loss": 0.0591, "step": 110690 }, { "epoch": 26.56, "learning_rate": 7.72916317343034e-05, "loss": 0.0589, "step": 110700 }, { "epoch": 26.56, "learning_rate": 7.728787202325898e-05, "loss": 0.0641, "step": 110710 }, { "epoch": 26.57, "learning_rate": 7.728411209246156e-05, "loss": 0.0528, "step": 110720 }, { "epoch": 26.57, "learning_rate": 7.728035194194142e-05, "loss": 0.0616, "step": 110730 }, { "epoch": 26.57, "learning_rate": 7.727659157172884e-05, "loss": 0.0557, "step": 110740 }, { "epoch": 26.57, "learning_rate": 7.727283098185409e-05, "loss": 0.0707, "step": 110750 }, { "epoch": 26.58, "learning_rate": 7.726907017234747e-05, "loss": 0.0456, "step": 110760 }, { "epoch": 26.58, "learning_rate": 7.726530914323929e-05, "loss": 0.0827, "step": 110770 }, { "epoch": 26.58, "learning_rate": 7.726154789455979e-05, "loss": 0.0866, "step": 110780 }, { "epoch": 26.58, "learning_rate": 7.725778642633927e-05, "loss": 0.0558, "step": 110790 }, { "epoch": 26.59, "learning_rate": 7.725402473860806e-05, "loss": 0.0558, "step": 110800 }, { "epoch": 26.59, "learning_rate": 7.725026283139641e-05, "loss": 0.0419, "step": 110810 }, { "epoch": 26.59, "learning_rate": 7.724650070473463e-05, "loss": 0.0923, "step": 110820 }, { "epoch": 26.59, "learning_rate": 7.724273835865303e-05, "loss": 0.0671, "step": 110830 }, { "epoch": 26.59, "learning_rate": 7.723897579318187e-05, "loss": 0.0459, "step": 110840 }, { "epoch": 26.6, "learning_rate": 7.72352130083515e-05, "loss": 0.0651, "step": 110850 }, { "epoch": 26.6, "learning_rate": 7.723145000419221e-05, "loss": 0.0402, "step": 110860 }, { "epoch": 26.6, "learning_rate": 7.722768678073426e-05, "loss": 0.0493, "step": 110870 }, { "epoch": 26.6, "learning_rate": 7.722392333800802e-05, "loss": 0.0593, "step": 110880 }, { "epoch": 26.61, "learning_rate": 7.722015967604375e-05, "loss": 0.0547, "step": 110890 }, { "epoch": 26.61, "learning_rate": 7.721639579487179e-05, "loss": 0.0648, "step": 110900 }, { "epoch": 26.61, "learning_rate": 7.721263169452242e-05, "loss": 0.0889, "step": 110910 }, { "epoch": 26.61, "learning_rate": 7.720886737502598e-05, "loss": 0.0328, "step": 110920 }, { "epoch": 26.62, "learning_rate": 7.720510283641278e-05, "loss": 0.0619, "step": 110930 }, { "epoch": 26.62, "learning_rate": 7.720133807871313e-05, "loss": 0.0571, "step": 110940 }, { "epoch": 26.62, "learning_rate": 7.719757310195734e-05, "loss": 0.0518, "step": 110950 }, { "epoch": 26.62, "learning_rate": 7.719380790617575e-05, "loss": 0.076, "step": 110960 }, { "epoch": 26.62, "learning_rate": 7.719004249139865e-05, "loss": 0.0579, "step": 110970 }, { "epoch": 26.63, "learning_rate": 7.71862768576564e-05, "loss": 0.1034, "step": 110980 }, { "epoch": 26.63, "learning_rate": 7.71825110049793e-05, "loss": 0.0958, "step": 110990 }, { "epoch": 26.63, "learning_rate": 7.71787449333977e-05, "loss": 0.0533, "step": 111000 }, { "epoch": 26.63, "learning_rate": 7.71749786429419e-05, "loss": 0.0778, "step": 111010 }, { "epoch": 26.64, "learning_rate": 7.717121213364226e-05, "loss": 0.0627, "step": 111020 }, { "epoch": 26.64, "learning_rate": 7.716744540552908e-05, "loss": 0.0639, "step": 111030 }, { "epoch": 26.64, "learning_rate": 7.716367845863273e-05, "loss": 0.0805, "step": 111040 }, { "epoch": 26.64, "learning_rate": 7.715991129298352e-05, "loss": 0.0481, "step": 111050 }, { "epoch": 26.64, "learning_rate": 7.715614390861178e-05, "loss": 0.0417, "step": 111060 }, { "epoch": 26.65, "learning_rate": 7.715237630554788e-05, "loss": 0.0585, "step": 111070 }, { "epoch": 26.65, "learning_rate": 7.714860848382215e-05, "loss": 0.0633, "step": 111080 }, { "epoch": 26.65, "learning_rate": 7.714484044346492e-05, "loss": 0.0682, "step": 111090 }, { "epoch": 26.65, "learning_rate": 7.714107218450654e-05, "loss": 0.0544, "step": 111100 }, { "epoch": 26.66, "learning_rate": 7.713730370697736e-05, "loss": 0.048, "step": 111110 }, { "epoch": 26.66, "learning_rate": 7.713353501090774e-05, "loss": 0.0704, "step": 111120 }, { "epoch": 26.66, "learning_rate": 7.712976609632799e-05, "loss": 0.0568, "step": 111130 }, { "epoch": 26.66, "learning_rate": 7.71259969632685e-05, "loss": 0.065, "step": 111140 }, { "epoch": 26.67, "learning_rate": 7.712222761175961e-05, "loss": 0.0824, "step": 111150 }, { "epoch": 26.67, "learning_rate": 7.71184580418317e-05, "loss": 0.0597, "step": 111160 }, { "epoch": 26.67, "learning_rate": 7.711468825351506e-05, "loss": 0.052, "step": 111170 }, { "epoch": 26.67, "learning_rate": 7.711091824684012e-05, "loss": 0.0706, "step": 111180 }, { "epoch": 26.67, "learning_rate": 7.710714802183721e-05, "loss": 0.0432, "step": 111190 }, { "epoch": 26.68, "learning_rate": 7.71033775785367e-05, "loss": 0.0582, "step": 111200 }, { "epoch": 26.68, "learning_rate": 7.709960691696894e-05, "loss": 0.0513, "step": 111210 }, { "epoch": 26.68, "learning_rate": 7.709583603716431e-05, "loss": 0.0695, "step": 111220 }, { "epoch": 26.68, "learning_rate": 7.709206493915316e-05, "loss": 0.0473, "step": 111230 }, { "epoch": 26.69, "learning_rate": 7.708829362296588e-05, "loss": 0.0592, "step": 111240 }, { "epoch": 26.69, "learning_rate": 7.708452208863282e-05, "loss": 0.0458, "step": 111250 }, { "epoch": 26.69, "learning_rate": 7.708075033618438e-05, "loss": 0.0564, "step": 111260 }, { "epoch": 26.69, "learning_rate": 7.707697836565091e-05, "loss": 0.0493, "step": 111270 }, { "epoch": 26.7, "learning_rate": 7.707320617706281e-05, "loss": 0.0383, "step": 111280 }, { "epoch": 26.7, "learning_rate": 7.706943377045042e-05, "loss": 0.0597, "step": 111290 }, { "epoch": 26.7, "learning_rate": 7.706566114584416e-05, "loss": 0.097, "step": 111300 }, { "epoch": 26.7, "learning_rate": 7.706188830327439e-05, "loss": 0.0581, "step": 111310 }, { "epoch": 26.7, "learning_rate": 7.70581152427715e-05, "loss": 0.0714, "step": 111320 }, { "epoch": 26.71, "learning_rate": 7.705434196436585e-05, "loss": 0.0621, "step": 111330 }, { "epoch": 26.71, "learning_rate": 7.705056846808787e-05, "loss": 0.0717, "step": 111340 }, { "epoch": 26.71, "learning_rate": 7.704679475396794e-05, "loss": 0.0558, "step": 111350 }, { "epoch": 26.71, "learning_rate": 7.704302082203641e-05, "loss": 0.0623, "step": 111360 }, { "epoch": 26.72, "learning_rate": 7.703924667232371e-05, "loss": 0.0534, "step": 111370 }, { "epoch": 26.72, "learning_rate": 7.703547230486022e-05, "loss": 0.0536, "step": 111380 }, { "epoch": 26.72, "learning_rate": 7.703169771967635e-05, "loss": 0.0584, "step": 111390 }, { "epoch": 26.72, "learning_rate": 7.702792291680248e-05, "loss": 0.051, "step": 111400 }, { "epoch": 26.72, "learning_rate": 7.702414789626902e-05, "loss": 0.0713, "step": 111410 }, { "epoch": 26.73, "learning_rate": 7.702037265810635e-05, "loss": 0.0859, "step": 111420 }, { "epoch": 26.73, "learning_rate": 7.70165972023449e-05, "loss": 0.0349, "step": 111430 }, { "epoch": 26.73, "learning_rate": 7.701282152901508e-05, "loss": 0.067, "step": 111440 }, { "epoch": 26.73, "learning_rate": 7.700904563814725e-05, "loss": 0.039, "step": 111450 }, { "epoch": 26.74, "learning_rate": 7.700526952977185e-05, "loss": 0.0941, "step": 111460 }, { "epoch": 26.74, "learning_rate": 7.70014932039193e-05, "loss": 0.0497, "step": 111470 }, { "epoch": 26.74, "learning_rate": 7.699771666061999e-05, "loss": 0.0761, "step": 111480 }, { "epoch": 26.74, "learning_rate": 7.699393989990435e-05, "loss": 0.066, "step": 111490 }, { "epoch": 26.75, "learning_rate": 7.699016292180279e-05, "loss": 0.0583, "step": 111500 }, { "epoch": 26.75, "learning_rate": 7.698638572634569e-05, "loss": 0.0535, "step": 111510 }, { "epoch": 26.75, "learning_rate": 7.698260831356352e-05, "loss": 0.0545, "step": 111520 }, { "epoch": 26.75, "learning_rate": 7.697883068348669e-05, "loss": 0.0597, "step": 111530 }, { "epoch": 26.75, "learning_rate": 7.69750528361456e-05, "loss": 0.0568, "step": 111540 }, { "epoch": 26.76, "learning_rate": 7.69712747715707e-05, "loss": 0.0582, "step": 111550 }, { "epoch": 26.76, "learning_rate": 7.696749648979238e-05, "loss": 0.07, "step": 111560 }, { "epoch": 26.76, "learning_rate": 7.69637179908411e-05, "loss": 0.0767, "step": 111570 }, { "epoch": 26.76, "learning_rate": 7.695993927474725e-05, "loss": 0.0651, "step": 111580 }, { "epoch": 26.77, "learning_rate": 7.695616034154131e-05, "loss": 0.0577, "step": 111590 }, { "epoch": 26.77, "learning_rate": 7.69523811912537e-05, "loss": 0.0389, "step": 111600 }, { "epoch": 26.77, "learning_rate": 7.694860182391484e-05, "loss": 0.0454, "step": 111610 }, { "epoch": 26.77, "learning_rate": 7.694482223955514e-05, "loss": 0.038, "step": 111620 }, { "epoch": 26.78, "learning_rate": 7.69410424382051e-05, "loss": 0.0438, "step": 111630 }, { "epoch": 26.78, "learning_rate": 7.693726241989511e-05, "loss": 0.0459, "step": 111640 }, { "epoch": 26.78, "learning_rate": 7.693348218465562e-05, "loss": 0.0582, "step": 111650 }, { "epoch": 26.78, "learning_rate": 7.69297017325171e-05, "loss": 0.0603, "step": 111660 }, { "epoch": 26.78, "learning_rate": 7.692592106350995e-05, "loss": 0.0324, "step": 111670 }, { "epoch": 26.79, "learning_rate": 7.692214017766466e-05, "loss": 0.0661, "step": 111680 }, { "epoch": 26.79, "learning_rate": 7.691835907501167e-05, "loss": 0.0448, "step": 111690 }, { "epoch": 26.79, "learning_rate": 7.69145777555814e-05, "loss": 0.0527, "step": 111700 }, { "epoch": 26.79, "learning_rate": 7.69107962194043e-05, "loss": 0.0791, "step": 111710 }, { "epoch": 26.8, "learning_rate": 7.690701446651088e-05, "loss": 0.0451, "step": 111720 }, { "epoch": 26.8, "learning_rate": 7.690323249693152e-05, "loss": 0.0366, "step": 111730 }, { "epoch": 26.8, "learning_rate": 7.689945031069674e-05, "loss": 0.0724, "step": 111740 }, { "epoch": 26.8, "learning_rate": 7.689566790783698e-05, "loss": 0.0747, "step": 111750 }, { "epoch": 26.8, "learning_rate": 7.689188528838267e-05, "loss": 0.0547, "step": 111760 }, { "epoch": 26.81, "learning_rate": 7.688810245236431e-05, "loss": 0.0408, "step": 111770 }, { "epoch": 26.81, "learning_rate": 7.688431939981233e-05, "loss": 0.047, "step": 111780 }, { "epoch": 26.81, "learning_rate": 7.688053613075724e-05, "loss": 0.0426, "step": 111790 }, { "epoch": 26.81, "learning_rate": 7.687675264522947e-05, "loss": 0.0703, "step": 111800 }, { "epoch": 26.82, "learning_rate": 7.687296894325951e-05, "loss": 0.0648, "step": 111810 }, { "epoch": 26.82, "learning_rate": 7.686918502487781e-05, "loss": 0.0587, "step": 111820 }, { "epoch": 26.82, "learning_rate": 7.686540089011485e-05, "loss": 0.0617, "step": 111830 }, { "epoch": 26.82, "learning_rate": 7.686161653900111e-05, "loss": 0.0489, "step": 111840 }, { "epoch": 26.83, "learning_rate": 7.685783197156706e-05, "loss": 0.044, "step": 111850 }, { "epoch": 26.83, "learning_rate": 7.68540471878432e-05, "loss": 0.0508, "step": 111860 }, { "epoch": 26.83, "learning_rate": 7.685026218785998e-05, "loss": 0.0504, "step": 111870 }, { "epoch": 26.83, "learning_rate": 7.684647697164789e-05, "loss": 0.0589, "step": 111880 }, { "epoch": 26.83, "learning_rate": 7.684269153923741e-05, "loss": 0.0435, "step": 111890 }, { "epoch": 26.84, "learning_rate": 7.683890589065903e-05, "loss": 0.0642, "step": 111900 }, { "epoch": 26.84, "learning_rate": 7.683512002594324e-05, "loss": 0.0689, "step": 111910 }, { "epoch": 26.84, "learning_rate": 7.683133394512052e-05, "loss": 0.0834, "step": 111920 }, { "epoch": 26.84, "learning_rate": 7.682754764822137e-05, "loss": 0.0719, "step": 111930 }, { "epoch": 26.85, "learning_rate": 7.682376113527627e-05, "loss": 0.0565, "step": 111940 }, { "epoch": 26.85, "learning_rate": 7.681997440631571e-05, "loss": 0.0408, "step": 111950 }, { "epoch": 26.85, "learning_rate": 7.681618746137022e-05, "loss": 0.0304, "step": 111960 }, { "epoch": 26.85, "learning_rate": 7.681240030047023e-05, "loss": 0.0987, "step": 111970 }, { "epoch": 26.86, "learning_rate": 7.680861292364631e-05, "loss": 0.0811, "step": 111980 }, { "epoch": 26.86, "learning_rate": 7.680482533092892e-05, "loss": 0.0795, "step": 111990 }, { "epoch": 26.86, "learning_rate": 7.680103752234858e-05, "loss": 0.0396, "step": 112000 }, { "epoch": 26.86, "learning_rate": 7.679724949793577e-05, "loss": 0.0623, "step": 112010 }, { "epoch": 26.86, "learning_rate": 7.679346125772102e-05, "loss": 0.0404, "step": 112020 }, { "epoch": 26.87, "learning_rate": 7.678967280173483e-05, "loss": 0.0438, "step": 112030 }, { "epoch": 26.87, "learning_rate": 7.67858841300077e-05, "loss": 0.0663, "step": 112040 }, { "epoch": 26.87, "learning_rate": 7.678209524257014e-05, "loss": 0.0581, "step": 112050 }, { "epoch": 26.87, "learning_rate": 7.677830613945267e-05, "loss": 0.0736, "step": 112060 }, { "epoch": 26.88, "learning_rate": 7.677451682068581e-05, "loss": 0.0399, "step": 112070 }, { "epoch": 26.88, "learning_rate": 7.677072728630008e-05, "loss": 0.0596, "step": 112080 }, { "epoch": 26.88, "learning_rate": 7.676693753632597e-05, "loss": 0.0713, "step": 112090 }, { "epoch": 26.88, "learning_rate": 7.676314757079404e-05, "loss": 0.0473, "step": 112100 }, { "epoch": 26.88, "learning_rate": 7.675935738973476e-05, "loss": 0.0762, "step": 112110 }, { "epoch": 26.89, "learning_rate": 7.675556699317869e-05, "loss": 0.0941, "step": 112120 }, { "epoch": 26.89, "learning_rate": 7.675177638115636e-05, "loss": 0.054, "step": 112130 }, { "epoch": 26.89, "learning_rate": 7.674798555369825e-05, "loss": 0.0634, "step": 112140 }, { "epoch": 26.89, "learning_rate": 7.674419451083495e-05, "loss": 0.0574, "step": 112150 }, { "epoch": 26.9, "learning_rate": 7.674040325259695e-05, "loss": 0.077, "step": 112160 }, { "epoch": 26.9, "learning_rate": 7.67366117790148e-05, "loss": 0.0607, "step": 112170 }, { "epoch": 26.9, "learning_rate": 7.673282009011899e-05, "loss": 0.0469, "step": 112180 }, { "epoch": 26.9, "learning_rate": 7.672902818594012e-05, "loss": 0.0684, "step": 112190 }, { "epoch": 26.91, "learning_rate": 7.67252360665087e-05, "loss": 0.0566, "step": 112200 }, { "epoch": 26.91, "learning_rate": 7.672144373185524e-05, "loss": 0.0756, "step": 112210 }, { "epoch": 26.91, "learning_rate": 7.671765118201034e-05, "loss": 0.0369, "step": 112220 }, { "epoch": 26.91, "learning_rate": 7.671385841700445e-05, "loss": 0.043, "step": 112230 }, { "epoch": 26.91, "learning_rate": 7.671006543686821e-05, "loss": 0.0564, "step": 112240 }, { "epoch": 26.92, "learning_rate": 7.670627224163212e-05, "loss": 0.0381, "step": 112250 }, { "epoch": 26.92, "learning_rate": 7.670247883132673e-05, "loss": 0.053, "step": 112260 }, { "epoch": 26.92, "learning_rate": 7.66986852059826e-05, "loss": 0.0759, "step": 112270 }, { "epoch": 26.92, "learning_rate": 7.669489136563027e-05, "loss": 0.0643, "step": 112280 }, { "epoch": 26.93, "learning_rate": 7.669109731030028e-05, "loss": 0.0549, "step": 112290 }, { "epoch": 26.93, "learning_rate": 7.66873030400232e-05, "loss": 0.0706, "step": 112300 }, { "epoch": 26.93, "learning_rate": 7.668350855482959e-05, "loss": 0.0495, "step": 112310 }, { "epoch": 26.93, "learning_rate": 7.667971385475001e-05, "loss": 0.0459, "step": 112320 }, { "epoch": 26.94, "learning_rate": 7.667591893981501e-05, "loss": 0.0638, "step": 112330 }, { "epoch": 26.94, "learning_rate": 7.667212381005516e-05, "loss": 0.0764, "step": 112340 }, { "epoch": 26.94, "learning_rate": 7.666832846550098e-05, "loss": 0.0559, "step": 112350 }, { "epoch": 26.94, "learning_rate": 7.66645329061831e-05, "loss": 0.0577, "step": 112360 }, { "epoch": 26.94, "learning_rate": 7.666073713213204e-05, "loss": 0.0501, "step": 112370 }, { "epoch": 26.95, "learning_rate": 7.665694114337838e-05, "loss": 0.0297, "step": 112380 }, { "epoch": 26.95, "learning_rate": 7.665314493995271e-05, "loss": 0.0516, "step": 112390 }, { "epoch": 26.95, "learning_rate": 7.664934852188556e-05, "loss": 0.0981, "step": 112400 }, { "epoch": 27.0, "learning_rate": 7.664555188920756e-05, "loss": 0.0632, "step": 112410 }, { "epoch": 27.0, "learning_rate": 7.664175504194924e-05, "loss": 0.0534, "step": 112420 }, { "epoch": 27.01, "learning_rate": 7.663795798014117e-05, "loss": 0.055, "step": 112430 }, { "epoch": 27.01, "learning_rate": 7.663416070381397e-05, "loss": 0.0353, "step": 112440 }, { "epoch": 27.01, "learning_rate": 7.663036321299817e-05, "loss": 0.0929, "step": 112450 }, { "epoch": 27.01, "learning_rate": 7.662656550772441e-05, "loss": 0.0425, "step": 112460 }, { "epoch": 27.02, "learning_rate": 7.662276758802323e-05, "loss": 0.0447, "step": 112470 }, { "epoch": 27.02, "learning_rate": 7.661896945392522e-05, "loss": 0.0412, "step": 112480 }, { "epoch": 27.02, "learning_rate": 7.661517110546097e-05, "loss": 0.0743, "step": 112490 }, { "epoch": 27.02, "learning_rate": 7.661137254266107e-05, "loss": 0.0392, "step": 112500 }, { "epoch": 27.02, "learning_rate": 7.660757376555614e-05, "loss": 0.0504, "step": 112510 }, { "epoch": 27.03, "learning_rate": 7.660377477417673e-05, "loss": 0.06, "step": 112520 }, { "epoch": 27.03, "learning_rate": 7.659997556855345e-05, "loss": 0.0442, "step": 112530 }, { "epoch": 27.03, "learning_rate": 7.659617614871688e-05, "loss": 0.0502, "step": 112540 }, { "epoch": 27.03, "learning_rate": 7.659237651469765e-05, "loss": 0.0445, "step": 112550 }, { "epoch": 27.04, "learning_rate": 7.658857666652633e-05, "loss": 0.0426, "step": 112560 }, { "epoch": 27.04, "learning_rate": 7.658477660423353e-05, "loss": 0.0874, "step": 112570 }, { "epoch": 27.04, "learning_rate": 7.658097632784987e-05, "loss": 0.054, "step": 112580 }, { "epoch": 27.04, "learning_rate": 7.657717583740592e-05, "loss": 0.0505, "step": 112590 }, { "epoch": 27.05, "learning_rate": 7.657337513293233e-05, "loss": 0.1082, "step": 112600 }, { "epoch": 27.05, "learning_rate": 7.656957421445965e-05, "loss": 0.0326, "step": 112610 }, { "epoch": 27.05, "learning_rate": 7.656577308201854e-05, "loss": 0.0466, "step": 112620 }, { "epoch": 27.05, "learning_rate": 7.656197173563959e-05, "loss": 0.0575, "step": 112630 }, { "epoch": 27.05, "learning_rate": 7.655817017535339e-05, "loss": 0.0562, "step": 112640 }, { "epoch": 27.06, "learning_rate": 7.655436840119062e-05, "loss": 0.0634, "step": 112650 }, { "epoch": 27.06, "learning_rate": 7.655056641318181e-05, "loss": 0.0549, "step": 112660 }, { "epoch": 27.06, "learning_rate": 7.654676421135766e-05, "loss": 0.0376, "step": 112670 }, { "epoch": 27.06, "learning_rate": 7.654296179574873e-05, "loss": 0.0664, "step": 112680 }, { "epoch": 27.07, "learning_rate": 7.653915916638567e-05, "loss": 0.0499, "step": 112690 }, { "epoch": 27.07, "learning_rate": 7.653535632329911e-05, "loss": 0.0354, "step": 112700 }, { "epoch": 27.07, "learning_rate": 7.653155326651965e-05, "loss": 0.0524, "step": 112710 }, { "epoch": 27.07, "learning_rate": 7.652774999607793e-05, "loss": 0.0555, "step": 112720 }, { "epoch": 27.08, "learning_rate": 7.652394651200458e-05, "loss": 0.0465, "step": 112730 }, { "epoch": 27.08, "learning_rate": 7.652014281433023e-05, "loss": 0.0317, "step": 112740 }, { "epoch": 27.08, "learning_rate": 7.651633890308551e-05, "loss": 0.0501, "step": 112750 }, { "epoch": 27.08, "learning_rate": 7.651253477830104e-05, "loss": 0.051, "step": 112760 }, { "epoch": 27.08, "learning_rate": 7.650873044000748e-05, "loss": 0.0751, "step": 112770 }, { "epoch": 27.09, "learning_rate": 7.650492588823544e-05, "loss": 0.0542, "step": 112780 }, { "epoch": 27.09, "learning_rate": 7.650112112301558e-05, "loss": 0.0437, "step": 112790 }, { "epoch": 27.09, "learning_rate": 7.649731614437854e-05, "loss": 0.0659, "step": 112800 }, { "epoch": 27.09, "learning_rate": 7.649351095235494e-05, "loss": 0.0641, "step": 112810 }, { "epoch": 27.1, "learning_rate": 7.648970554697545e-05, "loss": 0.0311, "step": 112820 }, { "epoch": 27.1, "learning_rate": 7.64858999282707e-05, "loss": 0.0584, "step": 112830 }, { "epoch": 27.1, "learning_rate": 7.648209409627133e-05, "loss": 0.0457, "step": 112840 }, { "epoch": 27.1, "learning_rate": 7.647828805100802e-05, "loss": 0.0652, "step": 112850 }, { "epoch": 27.1, "learning_rate": 7.64744817925114e-05, "loss": 0.0521, "step": 112860 }, { "epoch": 27.11, "learning_rate": 7.647067532081211e-05, "loss": 0.0425, "step": 112870 }, { "epoch": 27.11, "learning_rate": 7.646686863594083e-05, "loss": 0.0561, "step": 112880 }, { "epoch": 27.11, "learning_rate": 7.646306173792818e-05, "loss": 0.059, "step": 112890 }, { "epoch": 27.11, "learning_rate": 7.645925462680485e-05, "loss": 0.0416, "step": 112900 }, { "epoch": 27.12, "learning_rate": 7.64554473026015e-05, "loss": 0.0569, "step": 112910 }, { "epoch": 27.12, "learning_rate": 7.645163976534879e-05, "loss": 0.0535, "step": 112920 }, { "epoch": 27.12, "learning_rate": 7.644783201507735e-05, "loss": 0.0538, "step": 112930 }, { "epoch": 27.12, "learning_rate": 7.644402405181789e-05, "loss": 0.041, "step": 112940 }, { "epoch": 27.13, "learning_rate": 7.644021587560104e-05, "loss": 0.0372, "step": 112950 }, { "epoch": 27.13, "learning_rate": 7.643640748645748e-05, "loss": 0.0362, "step": 112960 }, { "epoch": 27.13, "learning_rate": 7.643259888441788e-05, "loss": 0.0552, "step": 112970 }, { "epoch": 27.13, "learning_rate": 7.642879006951291e-05, "loss": 0.0486, "step": 112980 }, { "epoch": 27.13, "learning_rate": 7.642498104177325e-05, "loss": 0.0403, "step": 112990 }, { "epoch": 27.14, "learning_rate": 7.642117180122957e-05, "loss": 0.0575, "step": 113000 }, { "epoch": 27.14, "learning_rate": 7.641736234791255e-05, "loss": 0.0636, "step": 113010 }, { "epoch": 27.14, "learning_rate": 7.641355268185287e-05, "loss": 0.0373, "step": 113020 }, { "epoch": 27.14, "learning_rate": 7.640974280308118e-05, "loss": 0.0517, "step": 113030 }, { "epoch": 27.15, "learning_rate": 7.640593271162819e-05, "loss": 0.0604, "step": 113040 }, { "epoch": 27.15, "learning_rate": 7.640212240752458e-05, "loss": 0.0417, "step": 113050 }, { "epoch": 27.15, "learning_rate": 7.639831189080105e-05, "loss": 0.0776, "step": 113060 }, { "epoch": 27.15, "learning_rate": 7.639450116148825e-05, "loss": 0.0466, "step": 113070 }, { "epoch": 27.16, "learning_rate": 7.63906902196169e-05, "loss": 0.038, "step": 113080 }, { "epoch": 27.16, "learning_rate": 7.638687906521767e-05, "loss": 0.0633, "step": 113090 }, { "epoch": 27.16, "learning_rate": 7.638306769832126e-05, "loss": 0.032, "step": 113100 }, { "epoch": 27.16, "learning_rate": 7.637925611895838e-05, "loss": 0.0473, "step": 113110 }, { "epoch": 27.16, "learning_rate": 7.637544432715969e-05, "loss": 0.0605, "step": 113120 }, { "epoch": 27.17, "learning_rate": 7.637163232295592e-05, "loss": 0.0554, "step": 113130 }, { "epoch": 27.17, "learning_rate": 7.636782010637774e-05, "loss": 0.0447, "step": 113140 }, { "epoch": 27.17, "learning_rate": 7.636400767745587e-05, "loss": 0.0436, "step": 113150 }, { "epoch": 27.17, "learning_rate": 7.6360195036221e-05, "loss": 0.0436, "step": 113160 }, { "epoch": 27.18, "learning_rate": 7.635638218270384e-05, "loss": 0.0393, "step": 113170 }, { "epoch": 27.18, "learning_rate": 7.635256911693511e-05, "loss": 0.0919, "step": 113180 }, { "epoch": 27.18, "learning_rate": 7.634875583894549e-05, "loss": 0.0985, "step": 113190 }, { "epoch": 27.18, "learning_rate": 7.634494234876572e-05, "loss": 0.0567, "step": 113200 }, { "epoch": 27.18, "learning_rate": 7.634112864642649e-05, "loss": 0.059, "step": 113210 }, { "epoch": 27.19, "learning_rate": 7.633731473195848e-05, "loss": 0.0492, "step": 113220 }, { "epoch": 27.19, "learning_rate": 7.633350060539246e-05, "loss": 0.0274, "step": 113230 }, { "epoch": 27.19, "learning_rate": 7.632968626675914e-05, "loss": 0.0484, "step": 113240 }, { "epoch": 27.19, "learning_rate": 7.63258717160892e-05, "loss": 0.0504, "step": 113250 }, { "epoch": 27.2, "learning_rate": 7.632205695341339e-05, "loss": 0.0481, "step": 113260 }, { "epoch": 27.2, "learning_rate": 7.631824197876242e-05, "loss": 0.0705, "step": 113270 }, { "epoch": 27.2, "learning_rate": 7.631442679216703e-05, "loss": 0.0464, "step": 113280 }, { "epoch": 27.2, "learning_rate": 7.631061139365789e-05, "loss": 0.0651, "step": 113290 }, { "epoch": 27.21, "learning_rate": 7.630679578326578e-05, "loss": 0.0591, "step": 113300 }, { "epoch": 27.21, "learning_rate": 7.630297996102143e-05, "loss": 0.0359, "step": 113310 }, { "epoch": 27.21, "learning_rate": 7.629916392695553e-05, "loss": 0.0452, "step": 113320 }, { "epoch": 27.21, "learning_rate": 7.629534768109885e-05, "loss": 0.0428, "step": 113330 }, { "epoch": 27.21, "learning_rate": 7.629153122348208e-05, "loss": 0.0437, "step": 113340 }, { "epoch": 27.22, "learning_rate": 7.628771455413602e-05, "loss": 0.0635, "step": 113350 }, { "epoch": 27.22, "learning_rate": 7.628389767309132e-05, "loss": 0.0468, "step": 113360 }, { "epoch": 27.22, "learning_rate": 7.628008058037879e-05, "loss": 0.0611, "step": 113370 }, { "epoch": 27.22, "learning_rate": 7.627626327602912e-05, "loss": 0.0457, "step": 113380 }, { "epoch": 27.23, "learning_rate": 7.62724457600731e-05, "loss": 0.0355, "step": 113390 }, { "epoch": 27.23, "learning_rate": 7.626862803254144e-05, "loss": 0.04, "step": 113400 }, { "epoch": 27.23, "learning_rate": 7.626481009346488e-05, "loss": 0.0589, "step": 113410 }, { "epoch": 27.23, "learning_rate": 7.62609919428742e-05, "loss": 0.0319, "step": 113420 }, { "epoch": 27.24, "learning_rate": 7.625717358080011e-05, "loss": 0.055, "step": 113430 }, { "epoch": 27.24, "learning_rate": 7.625335500727338e-05, "loss": 0.0545, "step": 113440 }, { "epoch": 27.24, "learning_rate": 7.624953622232476e-05, "loss": 0.0728, "step": 113450 }, { "epoch": 27.24, "learning_rate": 7.6245717225985e-05, "loss": 0.0412, "step": 113460 }, { "epoch": 27.24, "learning_rate": 7.624189801828485e-05, "loss": 0.0398, "step": 113470 }, { "epoch": 27.25, "learning_rate": 7.623807859925507e-05, "loss": 0.0647, "step": 113480 }, { "epoch": 27.25, "learning_rate": 7.623425896892642e-05, "loss": 0.0494, "step": 113490 }, { "epoch": 27.25, "learning_rate": 7.623043912732968e-05, "loss": 0.0594, "step": 113500 }, { "epoch": 27.25, "learning_rate": 7.622661907449558e-05, "loss": 0.0406, "step": 113510 }, { "epoch": 27.26, "learning_rate": 7.622279881045489e-05, "loss": 0.0426, "step": 113520 }, { "epoch": 27.26, "learning_rate": 7.621897833523839e-05, "loss": 0.0608, "step": 113530 }, { "epoch": 27.26, "learning_rate": 7.621515764887684e-05, "loss": 0.0626, "step": 113540 }, { "epoch": 27.26, "learning_rate": 7.6211336751401e-05, "loss": 0.0361, "step": 113550 }, { "epoch": 27.26, "learning_rate": 7.620751564284163e-05, "loss": 0.0367, "step": 113560 }, { "epoch": 27.27, "learning_rate": 7.620369432322954e-05, "loss": 0.0456, "step": 113570 }, { "epoch": 27.27, "learning_rate": 7.619987279259547e-05, "loss": 0.0514, "step": 113580 }, { "epoch": 27.27, "learning_rate": 7.619605105097023e-05, "loss": 0.0399, "step": 113590 }, { "epoch": 27.27, "learning_rate": 7.619222909838456e-05, "loss": 0.0348, "step": 113600 }, { "epoch": 27.28, "learning_rate": 7.618840693486926e-05, "loss": 0.0563, "step": 113610 }, { "epoch": 27.28, "learning_rate": 7.618458456045507e-05, "loss": 0.0588, "step": 113620 }, { "epoch": 27.28, "learning_rate": 7.618076197517284e-05, "loss": 0.0477, "step": 113630 }, { "epoch": 27.28, "learning_rate": 7.61769391790533e-05, "loss": 0.0391, "step": 113640 }, { "epoch": 27.29, "learning_rate": 7.617311617212727e-05, "loss": 0.0515, "step": 113650 }, { "epoch": 27.29, "learning_rate": 7.616929295442552e-05, "loss": 0.0509, "step": 113660 }, { "epoch": 27.29, "learning_rate": 7.616546952597883e-05, "loss": 0.0347, "step": 113670 }, { "epoch": 27.29, "learning_rate": 7.616164588681802e-05, "loss": 0.0436, "step": 113680 }, { "epoch": 27.29, "learning_rate": 7.615782203697386e-05, "loss": 0.0226, "step": 113690 }, { "epoch": 27.3, "learning_rate": 7.615399797647713e-05, "loss": 0.0482, "step": 113700 }, { "epoch": 27.3, "learning_rate": 7.615017370535866e-05, "loss": 0.038, "step": 113710 }, { "epoch": 27.3, "learning_rate": 7.614634922364922e-05, "loss": 0.0507, "step": 113720 }, { "epoch": 27.3, "learning_rate": 7.614252453137964e-05, "loss": 0.0375, "step": 113730 }, { "epoch": 27.31, "learning_rate": 7.613869962858066e-05, "loss": 0.0308, "step": 113740 }, { "epoch": 27.31, "learning_rate": 7.613487451528316e-05, "loss": 0.0421, "step": 113750 }, { "epoch": 27.31, "learning_rate": 7.61310491915179e-05, "loss": 0.0445, "step": 113760 }, { "epoch": 27.31, "learning_rate": 7.612722365731569e-05, "loss": 0.0369, "step": 113770 }, { "epoch": 27.32, "learning_rate": 7.612339791270734e-05, "loss": 0.0437, "step": 113780 }, { "epoch": 27.32, "learning_rate": 7.611957195772366e-05, "loss": 0.0555, "step": 113790 }, { "epoch": 27.32, "learning_rate": 7.611574579239548e-05, "loss": 0.0307, "step": 113800 }, { "epoch": 27.32, "learning_rate": 7.611191941675356e-05, "loss": 0.0571, "step": 113810 }, { "epoch": 27.32, "learning_rate": 7.610809283082876e-05, "loss": 0.0432, "step": 113820 }, { "epoch": 27.33, "learning_rate": 7.61042660346519e-05, "loss": 0.0628, "step": 113830 }, { "epoch": 27.33, "learning_rate": 7.610043902825375e-05, "loss": 0.0446, "step": 113840 }, { "epoch": 27.33, "learning_rate": 7.60966118116652e-05, "loss": 0.0586, "step": 113850 }, { "epoch": 27.33, "learning_rate": 7.6092784384917e-05, "loss": 0.0569, "step": 113860 }, { "epoch": 27.34, "learning_rate": 7.608895674804001e-05, "loss": 0.0682, "step": 113870 }, { "epoch": 27.34, "learning_rate": 7.608512890106507e-05, "loss": 0.0382, "step": 113880 }, { "epoch": 27.34, "learning_rate": 7.608130084402296e-05, "loss": 0.0362, "step": 113890 }, { "epoch": 27.34, "learning_rate": 7.607747257694456e-05, "loss": 0.0437, "step": 113900 }, { "epoch": 27.34, "learning_rate": 7.607364409986065e-05, "loss": 0.0439, "step": 113910 }, { "epoch": 27.35, "learning_rate": 7.606981541280212e-05, "loss": 0.0271, "step": 113920 }, { "epoch": 27.35, "learning_rate": 7.606598651579973e-05, "loss": 0.0477, "step": 113930 }, { "epoch": 27.35, "learning_rate": 7.606215740888437e-05, "loss": 0.0392, "step": 113940 }, { "epoch": 27.35, "learning_rate": 7.605832809208683e-05, "loss": 0.0338, "step": 113950 }, { "epoch": 27.36, "learning_rate": 7.6054498565438e-05, "loss": 0.0636, "step": 113960 }, { "epoch": 27.36, "learning_rate": 7.60506688289687e-05, "loss": 0.0629, "step": 113970 }, { "epoch": 27.36, "learning_rate": 7.604683888270975e-05, "loss": 0.0402, "step": 113980 }, { "epoch": 27.36, "learning_rate": 7.604300872669203e-05, "loss": 0.0451, "step": 113990 }, { "epoch": 27.37, "learning_rate": 7.603917836094635e-05, "loss": 0.0713, "step": 114000 }, { "epoch": 27.37, "learning_rate": 7.603534778550359e-05, "loss": 0.0597, "step": 114010 }, { "epoch": 27.37, "learning_rate": 7.603151700039457e-05, "loss": 0.0408, "step": 114020 }, { "epoch": 27.37, "learning_rate": 7.602768600565014e-05, "loss": 0.0407, "step": 114030 }, { "epoch": 27.37, "learning_rate": 7.602385480130118e-05, "loss": 0.0632, "step": 114040 }, { "epoch": 27.38, "learning_rate": 7.602002338737851e-05, "loss": 0.0414, "step": 114050 }, { "epoch": 27.38, "learning_rate": 7.601619176391299e-05, "loss": 0.0435, "step": 114060 }, { "epoch": 27.38, "learning_rate": 7.601235993093551e-05, "loss": 0.054, "step": 114070 }, { "epoch": 27.38, "learning_rate": 7.600852788847688e-05, "loss": 0.0503, "step": 114080 }, { "epoch": 27.39, "learning_rate": 7.600469563656802e-05, "loss": 0.0379, "step": 114090 }, { "epoch": 27.39, "learning_rate": 7.600086317523972e-05, "loss": 0.0373, "step": 114100 }, { "epoch": 27.39, "learning_rate": 7.59970305045229e-05, "loss": 0.0341, "step": 114110 }, { "epoch": 27.39, "learning_rate": 7.599319762444838e-05, "loss": 0.0368, "step": 114120 }, { "epoch": 27.4, "learning_rate": 7.598936453504708e-05, "loss": 0.0315, "step": 114130 }, { "epoch": 27.4, "learning_rate": 7.598553123634983e-05, "loss": 0.0229, "step": 114140 }, { "epoch": 27.4, "learning_rate": 7.598169772838751e-05, "loss": 0.0489, "step": 114150 }, { "epoch": 27.4, "learning_rate": 7.597786401119098e-05, "loss": 0.0362, "step": 114160 }, { "epoch": 27.4, "learning_rate": 7.597403008479113e-05, "loss": 0.046, "step": 114170 }, { "epoch": 27.41, "learning_rate": 7.597019594921884e-05, "loss": 0.0317, "step": 114180 }, { "epoch": 27.41, "learning_rate": 7.596636160450496e-05, "loss": 0.038, "step": 114190 }, { "epoch": 27.41, "learning_rate": 7.59625270506804e-05, "loss": 0.0407, "step": 114200 }, { "epoch": 27.41, "learning_rate": 7.595869228777602e-05, "loss": 0.0444, "step": 114210 }, { "epoch": 27.42, "learning_rate": 7.59548573158227e-05, "loss": 0.0474, "step": 114220 }, { "epoch": 27.42, "learning_rate": 7.595102213485134e-05, "loss": 0.0609, "step": 114230 }, { "epoch": 27.42, "learning_rate": 7.594718674489281e-05, "loss": 0.0306, "step": 114240 }, { "epoch": 27.42, "learning_rate": 7.594335114597802e-05, "loss": 0.092, "step": 114250 }, { "epoch": 27.42, "learning_rate": 7.593951533813781e-05, "loss": 0.0474, "step": 114260 }, { "epoch": 27.43, "learning_rate": 7.593567932140314e-05, "loss": 0.0545, "step": 114270 }, { "epoch": 27.43, "learning_rate": 7.593184309580483e-05, "loss": 0.0475, "step": 114280 }, { "epoch": 27.43, "learning_rate": 7.592800666137381e-05, "loss": 0.0499, "step": 114290 }, { "epoch": 27.43, "learning_rate": 7.592417001814099e-05, "loss": 0.0486, "step": 114300 }, { "epoch": 27.44, "learning_rate": 7.592033316613725e-05, "loss": 0.0451, "step": 114310 }, { "epoch": 27.44, "learning_rate": 7.591649610539348e-05, "loss": 0.0404, "step": 114320 }, { "epoch": 27.44, "learning_rate": 7.591265883594058e-05, "loss": 0.0311, "step": 114330 }, { "epoch": 27.44, "learning_rate": 7.590882135780948e-05, "loss": 0.0497, "step": 114340 }, { "epoch": 27.45, "learning_rate": 7.590498367103107e-05, "loss": 0.056, "step": 114350 }, { "epoch": 27.45, "learning_rate": 7.590114577563622e-05, "loss": 0.0524, "step": 114360 }, { "epoch": 27.45, "learning_rate": 7.589730767165588e-05, "loss": 0.0474, "step": 114370 }, { "epoch": 27.45, "learning_rate": 7.589346935912096e-05, "loss": 0.069, "step": 114380 }, { "epoch": 27.45, "learning_rate": 7.588963083806235e-05, "loss": 0.0513, "step": 114390 }, { "epoch": 27.46, "learning_rate": 7.588579210851097e-05, "loss": 0.0441, "step": 114400 }, { "epoch": 27.46, "learning_rate": 7.58819531704977e-05, "loss": 0.0424, "step": 114410 }, { "epoch": 27.46, "learning_rate": 7.587811402405353e-05, "loss": 0.0481, "step": 114420 }, { "epoch": 27.46, "learning_rate": 7.58742746692093e-05, "loss": 0.0576, "step": 114430 }, { "epoch": 27.47, "learning_rate": 7.587043510599601e-05, "loss": 0.0356, "step": 114440 }, { "epoch": 27.47, "learning_rate": 7.58665953344445e-05, "loss": 0.0311, "step": 114450 }, { "epoch": 27.47, "learning_rate": 7.586275535458574e-05, "loss": 0.0444, "step": 114460 }, { "epoch": 27.47, "learning_rate": 7.585891516645064e-05, "loss": 0.0412, "step": 114470 }, { "epoch": 27.48, "learning_rate": 7.585507477007011e-05, "loss": 0.037, "step": 114480 }, { "epoch": 27.48, "learning_rate": 7.58512341654751e-05, "loss": 0.0471, "step": 114490 }, { "epoch": 27.48, "learning_rate": 7.584739335269655e-05, "loss": 0.0357, "step": 114500 }, { "epoch": 27.48, "learning_rate": 7.584355233176535e-05, "loss": 0.0571, "step": 114510 }, { "epoch": 27.48, "learning_rate": 7.583971110271247e-05, "loss": 0.0461, "step": 114520 }, { "epoch": 27.49, "learning_rate": 7.583586966556884e-05, "loss": 0.0659, "step": 114530 }, { "epoch": 27.49, "learning_rate": 7.583202802036535e-05, "loss": 0.0478, "step": 114540 }, { "epoch": 27.49, "learning_rate": 7.582818616713299e-05, "loss": 0.0307, "step": 114550 }, { "epoch": 27.49, "learning_rate": 7.582434410590269e-05, "loss": 0.0304, "step": 114560 }, { "epoch": 27.5, "learning_rate": 7.582050183670537e-05, "loss": 0.0343, "step": 114570 }, { "epoch": 27.5, "learning_rate": 7.581665935957198e-05, "loss": 0.0673, "step": 114580 }, { "epoch": 27.5, "learning_rate": 7.581281667453349e-05, "loss": 0.0457, "step": 114590 }, { "epoch": 27.5, "learning_rate": 7.580897378162081e-05, "loss": 0.0498, "step": 114600 }, { "epoch": 27.5, "learning_rate": 7.580513068086489e-05, "loss": 0.0399, "step": 114610 }, { "epoch": 27.51, "learning_rate": 7.580128737229671e-05, "loss": 0.0423, "step": 114620 }, { "epoch": 27.51, "learning_rate": 7.579744385594719e-05, "loss": 0.0435, "step": 114630 }, { "epoch": 27.51, "learning_rate": 7.579360013184729e-05, "loss": 0.0442, "step": 114640 }, { "epoch": 27.51, "learning_rate": 7.578975620002797e-05, "loss": 0.0572, "step": 114650 }, { "epoch": 27.52, "learning_rate": 7.578591206052019e-05, "loss": 0.1108, "step": 114660 }, { "epoch": 27.52, "learning_rate": 7.57820677133549e-05, "loss": 0.0331, "step": 114670 }, { "epoch": 27.52, "learning_rate": 7.577822315856304e-05, "loss": 0.0777, "step": 114680 }, { "epoch": 27.52, "learning_rate": 7.577437839617561e-05, "loss": 0.0696, "step": 114690 }, { "epoch": 27.53, "learning_rate": 7.577053342622355e-05, "loss": 0.0579, "step": 114700 }, { "epoch": 27.53, "learning_rate": 7.576668824873782e-05, "loss": 0.0698, "step": 114710 }, { "epoch": 27.53, "learning_rate": 7.57628428637494e-05, "loss": 0.0401, "step": 114720 }, { "epoch": 27.53, "learning_rate": 7.575899727128923e-05, "loss": 0.0789, "step": 114730 }, { "epoch": 27.53, "learning_rate": 7.575515147138832e-05, "loss": 0.0516, "step": 114740 }, { "epoch": 27.54, "learning_rate": 7.57513054640776e-05, "loss": 0.0755, "step": 114750 }, { "epoch": 27.54, "learning_rate": 7.574745924938809e-05, "loss": 0.0637, "step": 114760 }, { "epoch": 27.54, "learning_rate": 7.574361282735072e-05, "loss": 0.0691, "step": 114770 }, { "epoch": 27.54, "learning_rate": 7.573976619799648e-05, "loss": 0.0504, "step": 114780 }, { "epoch": 27.55, "learning_rate": 7.573591936135635e-05, "loss": 0.066, "step": 114790 }, { "epoch": 27.55, "learning_rate": 7.57320723174613e-05, "loss": 0.0691, "step": 114800 }, { "epoch": 27.55, "learning_rate": 7.572822506634234e-05, "loss": 0.075, "step": 114810 }, { "epoch": 27.55, "learning_rate": 7.572437760803041e-05, "loss": 0.0638, "step": 114820 }, { "epoch": 27.56, "learning_rate": 7.572052994255654e-05, "loss": 0.0437, "step": 114830 }, { "epoch": 27.56, "learning_rate": 7.571668206995167e-05, "loss": 0.0462, "step": 114840 }, { "epoch": 27.56, "learning_rate": 7.57128339902468e-05, "loss": 0.0566, "step": 114850 }, { "epoch": 27.56, "learning_rate": 7.570898570347296e-05, "loss": 0.0568, "step": 114860 }, { "epoch": 27.56, "learning_rate": 7.570513720966108e-05, "loss": 0.0553, "step": 114870 }, { "epoch": 27.57, "learning_rate": 7.570128850884221e-05, "loss": 0.0787, "step": 114880 }, { "epoch": 27.57, "learning_rate": 7.56974396010473e-05, "loss": 0.0797, "step": 114890 }, { "epoch": 27.57, "learning_rate": 7.569359048630735e-05, "loss": 0.0515, "step": 114900 }, { "epoch": 27.57, "learning_rate": 7.56897411646534e-05, "loss": 0.057, "step": 114910 }, { "epoch": 27.58, "learning_rate": 7.568589163611639e-05, "loss": 0.0463, "step": 114920 }, { "epoch": 27.58, "learning_rate": 7.568204190072737e-05, "loss": 0.0705, "step": 114930 }, { "epoch": 27.58, "learning_rate": 7.567819195851728e-05, "loss": 0.0659, "step": 114940 }, { "epoch": 27.58, "learning_rate": 7.567434180951721e-05, "loss": 0.0473, "step": 114950 }, { "epoch": 27.58, "learning_rate": 7.567049145375809e-05, "loss": 0.0713, "step": 114960 }, { "epoch": 27.59, "learning_rate": 7.566664089127095e-05, "loss": 0.0804, "step": 114970 }, { "epoch": 27.59, "learning_rate": 7.566279012208685e-05, "loss": 0.0619, "step": 114980 }, { "epoch": 27.59, "learning_rate": 7.565893914623673e-05, "loss": 0.0785, "step": 114990 }, { "epoch": 27.59, "learning_rate": 7.565508796375165e-05, "loss": 0.0475, "step": 115000 }, { "epoch": 27.6, "learning_rate": 7.565123657466258e-05, "loss": 0.0388, "step": 115010 }, { "epoch": 27.6, "learning_rate": 7.564738497900057e-05, "loss": 0.0533, "step": 115020 }, { "epoch": 27.6, "learning_rate": 7.564353317679664e-05, "loss": 0.0714, "step": 115030 }, { "epoch": 27.6, "learning_rate": 7.563968116808178e-05, "loss": 0.0594, "step": 115040 }, { "epoch": 27.61, "learning_rate": 7.563582895288705e-05, "loss": 0.0762, "step": 115050 }, { "epoch": 27.61, "learning_rate": 7.563197653124342e-05, "loss": 0.0462, "step": 115060 }, { "epoch": 27.61, "learning_rate": 7.562812390318196e-05, "loss": 0.0659, "step": 115070 }, { "epoch": 27.61, "learning_rate": 7.562427106873368e-05, "loss": 0.0563, "step": 115080 }, { "epoch": 27.61, "learning_rate": 7.562041802792961e-05, "loss": 0.0611, "step": 115090 }, { "epoch": 27.62, "learning_rate": 7.561656478080077e-05, "loss": 0.054, "step": 115100 }, { "epoch": 27.62, "learning_rate": 7.561271132737819e-05, "loss": 0.0621, "step": 115110 }, { "epoch": 27.62, "learning_rate": 7.560885766769294e-05, "loss": 0.0593, "step": 115120 }, { "epoch": 27.62, "learning_rate": 7.5605003801776e-05, "loss": 0.0471, "step": 115130 }, { "epoch": 27.63, "learning_rate": 7.560114972965842e-05, "loss": 0.0628, "step": 115140 }, { "epoch": 27.63, "learning_rate": 7.559729545137127e-05, "loss": 0.0481, "step": 115150 }, { "epoch": 27.63, "learning_rate": 7.559344096694554e-05, "loss": 0.057, "step": 115160 }, { "epoch": 27.63, "learning_rate": 7.558958627641233e-05, "loss": 0.0496, "step": 115170 }, { "epoch": 27.64, "learning_rate": 7.558573137980263e-05, "loss": 0.0849, "step": 115180 }, { "epoch": 27.64, "learning_rate": 7.55818762771475e-05, "loss": 0.0474, "step": 115190 }, { "epoch": 27.64, "learning_rate": 7.557802096847799e-05, "loss": 0.0629, "step": 115200 }, { "epoch": 27.64, "learning_rate": 7.557416545382515e-05, "loss": 0.0556, "step": 115210 }, { "epoch": 27.64, "learning_rate": 7.557030973322004e-05, "loss": 0.076, "step": 115220 }, { "epoch": 27.65, "learning_rate": 7.556645380669365e-05, "loss": 0.0571, "step": 115230 }, { "epoch": 27.65, "learning_rate": 7.556259767427713e-05, "loss": 0.107, "step": 115240 }, { "epoch": 27.65, "learning_rate": 7.555874133600145e-05, "loss": 0.0601, "step": 115250 }, { "epoch": 27.65, "learning_rate": 7.55548847918977e-05, "loss": 0.0954, "step": 115260 }, { "epoch": 27.66, "learning_rate": 7.555102804199694e-05, "loss": 0.0338, "step": 115270 }, { "epoch": 27.66, "learning_rate": 7.554717108633023e-05, "loss": 0.0359, "step": 115280 }, { "epoch": 27.66, "learning_rate": 7.554331392492862e-05, "loss": 0.0486, "step": 115290 }, { "epoch": 27.66, "learning_rate": 7.553945655782317e-05, "loss": 0.0826, "step": 115300 }, { "epoch": 27.66, "learning_rate": 7.553559898504497e-05, "loss": 0.084, "step": 115310 }, { "epoch": 27.67, "learning_rate": 7.553174120662504e-05, "loss": 0.0577, "step": 115320 }, { "epoch": 27.67, "learning_rate": 7.552788322259448e-05, "loss": 0.0397, "step": 115330 }, { "epoch": 27.67, "learning_rate": 7.552402503298437e-05, "loss": 0.0655, "step": 115340 }, { "epoch": 27.67, "learning_rate": 7.552016663782573e-05, "loss": 0.0588, "step": 115350 }, { "epoch": 27.68, "learning_rate": 7.55163080371497e-05, "loss": 0.0481, "step": 115360 }, { "epoch": 27.68, "learning_rate": 7.55124492309873e-05, "loss": 0.0757, "step": 115370 }, { "epoch": 27.68, "learning_rate": 7.550859021936962e-05, "loss": 0.0816, "step": 115380 }, { "epoch": 27.68, "learning_rate": 7.550473100232776e-05, "loss": 0.0484, "step": 115390 }, { "epoch": 27.69, "learning_rate": 7.550087157989275e-05, "loss": 0.0763, "step": 115400 }, { "epoch": 27.69, "learning_rate": 7.549701195209572e-05, "loss": 0.0675, "step": 115410 }, { "epoch": 27.69, "learning_rate": 7.549315211896772e-05, "loss": 0.0497, "step": 115420 }, { "epoch": 27.69, "learning_rate": 7.548929208053987e-05, "loss": 0.0671, "step": 115430 }, { "epoch": 27.69, "learning_rate": 7.548543183684322e-05, "loss": 0.0688, "step": 115440 }, { "epoch": 27.7, "learning_rate": 7.548157138790888e-05, "loss": 0.0683, "step": 115450 }, { "epoch": 27.7, "learning_rate": 7.547771073376791e-05, "loss": 0.0475, "step": 115460 }, { "epoch": 27.7, "learning_rate": 7.547384987445141e-05, "loss": 0.0652, "step": 115470 }, { "epoch": 27.7, "learning_rate": 7.546998880999052e-05, "loss": 0.0817, "step": 115480 }, { "epoch": 27.71, "learning_rate": 7.546612754041626e-05, "loss": 0.0293, "step": 115490 }, { "epoch": 27.71, "learning_rate": 7.546226606575977e-05, "loss": 0.0523, "step": 115500 }, { "epoch": 27.71, "learning_rate": 7.545840438605212e-05, "loss": 0.0725, "step": 115510 }, { "epoch": 27.71, "learning_rate": 7.545454250132445e-05, "loss": 0.0584, "step": 115520 }, { "epoch": 27.72, "learning_rate": 7.545068041160783e-05, "loss": 0.0447, "step": 115530 }, { "epoch": 27.72, "learning_rate": 7.544681811693335e-05, "loss": 0.0447, "step": 115540 }, { "epoch": 27.72, "learning_rate": 7.544295561733215e-05, "loss": 0.0324, "step": 115550 }, { "epoch": 27.72, "learning_rate": 7.543909291283528e-05, "loss": 0.05, "step": 115560 }, { "epoch": 27.72, "learning_rate": 7.543523000347392e-05, "loss": 0.0604, "step": 115570 }, { "epoch": 27.73, "learning_rate": 7.543136688927913e-05, "loss": 0.0664, "step": 115580 }, { "epoch": 27.73, "learning_rate": 7.542750357028203e-05, "loss": 0.0766, "step": 115590 }, { "epoch": 27.73, "learning_rate": 7.542364004651374e-05, "loss": 0.0408, "step": 115600 }, { "epoch": 27.73, "learning_rate": 7.541977631800537e-05, "loss": 0.0474, "step": 115610 }, { "epoch": 27.74, "learning_rate": 7.541591238478802e-05, "loss": 0.0395, "step": 115620 }, { "epoch": 27.74, "learning_rate": 7.541204824689281e-05, "loss": 0.0583, "step": 115630 }, { "epoch": 27.74, "learning_rate": 7.540818390435089e-05, "loss": 0.0655, "step": 115640 }, { "epoch": 27.74, "learning_rate": 7.540431935719334e-05, "loss": 0.0418, "step": 115650 }, { "epoch": 27.74, "learning_rate": 7.540045460545131e-05, "loss": 0.068, "step": 115660 }, { "epoch": 27.75, "learning_rate": 7.53965896491559e-05, "loss": 0.0419, "step": 115670 }, { "epoch": 27.75, "learning_rate": 7.539272448833824e-05, "loss": 0.0493, "step": 115680 }, { "epoch": 27.75, "learning_rate": 7.53888591230295e-05, "loss": 0.041, "step": 115690 }, { "epoch": 27.75, "learning_rate": 7.538499355326075e-05, "loss": 0.0545, "step": 115700 }, { "epoch": 27.76, "learning_rate": 7.538112777906314e-05, "loss": 0.0677, "step": 115710 }, { "epoch": 27.76, "learning_rate": 7.537726180046781e-05, "loss": 0.07, "step": 115720 }, { "epoch": 27.76, "learning_rate": 7.537339561750588e-05, "loss": 0.0594, "step": 115730 }, { "epoch": 27.76, "learning_rate": 7.53695292302085e-05, "loss": 0.0701, "step": 115740 }, { "epoch": 27.77, "learning_rate": 7.536566263860681e-05, "loss": 0.0406, "step": 115750 }, { "epoch": 27.77, "learning_rate": 7.536179584273191e-05, "loss": 0.0553, "step": 115760 }, { "epoch": 27.77, "learning_rate": 7.5357928842615e-05, "loss": 0.0647, "step": 115770 }, { "epoch": 27.77, "learning_rate": 7.535406163828715e-05, "loss": 0.0523, "step": 115780 }, { "epoch": 27.77, "learning_rate": 7.535019422977956e-05, "loss": 0.0586, "step": 115790 }, { "epoch": 27.78, "learning_rate": 7.534632661712336e-05, "loss": 0.0393, "step": 115800 }, { "epoch": 27.78, "learning_rate": 7.534245880034967e-05, "loss": 0.0604, "step": 115810 }, { "epoch": 27.78, "learning_rate": 7.533859077948968e-05, "loss": 0.0561, "step": 115820 }, { "epoch": 27.78, "learning_rate": 7.533472255457452e-05, "loss": 0.0854, "step": 115830 }, { "epoch": 27.79, "learning_rate": 7.533085412563534e-05, "loss": 0.0443, "step": 115840 }, { "epoch": 27.79, "learning_rate": 7.532698549270329e-05, "loss": 0.0467, "step": 115850 }, { "epoch": 27.79, "learning_rate": 7.532311665580955e-05, "loss": 0.0752, "step": 115860 }, { "epoch": 27.79, "learning_rate": 7.531924761498524e-05, "loss": 0.0472, "step": 115870 }, { "epoch": 27.8, "learning_rate": 7.531537837026152e-05, "loss": 0.0588, "step": 115880 }, { "epoch": 27.8, "learning_rate": 7.531150892166959e-05, "loss": 0.0302, "step": 115890 }, { "epoch": 27.8, "learning_rate": 7.530763926924056e-05, "loss": 0.0483, "step": 115900 }, { "epoch": 27.8, "learning_rate": 7.530376941300563e-05, "loss": 0.0383, "step": 115910 }, { "epoch": 27.8, "learning_rate": 7.529989935299595e-05, "loss": 0.0417, "step": 115920 }, { "epoch": 27.81, "learning_rate": 7.529602908924267e-05, "loss": 0.0382, "step": 115930 }, { "epoch": 27.81, "learning_rate": 7.529215862177699e-05, "loss": 0.0633, "step": 115940 }, { "epoch": 27.81, "learning_rate": 7.528828795063007e-05, "loss": 0.0721, "step": 115950 }, { "epoch": 27.81, "learning_rate": 7.528441707583306e-05, "loss": 0.0785, "step": 115960 }, { "epoch": 27.82, "learning_rate": 7.528054599741717e-05, "loss": 0.0536, "step": 115970 }, { "epoch": 27.82, "learning_rate": 7.527667471541355e-05, "loss": 0.078, "step": 115980 }, { "epoch": 27.82, "learning_rate": 7.527280322985338e-05, "loss": 0.0626, "step": 115990 }, { "epoch": 27.82, "learning_rate": 7.526893154076782e-05, "loss": 0.0575, "step": 116000 }, { "epoch": 27.82, "learning_rate": 7.526505964818806e-05, "loss": 0.0653, "step": 116010 }, { "epoch": 27.83, "learning_rate": 7.52611875521453e-05, "loss": 0.033, "step": 116020 }, { "epoch": 27.83, "learning_rate": 7.525731525267072e-05, "loss": 0.0533, "step": 116030 }, { "epoch": 27.83, "learning_rate": 7.525344274979549e-05, "loss": 0.0691, "step": 116040 }, { "epoch": 27.83, "learning_rate": 7.524957004355077e-05, "loss": 0.0321, "step": 116050 }, { "epoch": 27.84, "learning_rate": 7.524569713396781e-05, "loss": 0.0718, "step": 116060 }, { "epoch": 27.84, "learning_rate": 7.524182402107775e-05, "loss": 0.0455, "step": 116070 }, { "epoch": 27.84, "learning_rate": 7.52379507049118e-05, "loss": 0.0543, "step": 116080 }, { "epoch": 27.84, "learning_rate": 7.523407718550115e-05, "loss": 0.0413, "step": 116090 }, { "epoch": 27.85, "learning_rate": 7.523020346287701e-05, "loss": 0.09, "step": 116100 }, { "epoch": 27.85, "learning_rate": 7.522632953707054e-05, "loss": 0.0555, "step": 116110 }, { "epoch": 27.85, "learning_rate": 7.522245540811295e-05, "loss": 0.045, "step": 116120 }, { "epoch": 27.85, "learning_rate": 7.521858107603544e-05, "loss": 0.036, "step": 116130 }, { "epoch": 27.85, "learning_rate": 7.521470654086923e-05, "loss": 0.0376, "step": 116140 }, { "epoch": 27.86, "learning_rate": 7.52108318026455e-05, "loss": 0.0363, "step": 116150 }, { "epoch": 27.86, "learning_rate": 7.520695686139547e-05, "loss": 0.0579, "step": 116160 }, { "epoch": 27.86, "learning_rate": 7.520308171715033e-05, "loss": 0.0783, "step": 116170 }, { "epoch": 27.86, "learning_rate": 7.519920636994129e-05, "loss": 0.063, "step": 116180 }, { "epoch": 27.87, "learning_rate": 7.519533081979956e-05, "loss": 0.0399, "step": 116190 }, { "epoch": 27.87, "learning_rate": 7.519145506675635e-05, "loss": 0.0333, "step": 116200 }, { "epoch": 27.87, "learning_rate": 7.518757911084288e-05, "loss": 0.0536, "step": 116210 }, { "epoch": 27.87, "learning_rate": 7.518370295209038e-05, "loss": 0.0499, "step": 116220 }, { "epoch": 27.88, "learning_rate": 7.517982659053002e-05, "loss": 0.0418, "step": 116230 }, { "epoch": 27.88, "learning_rate": 7.517595002619303e-05, "loss": 0.0572, "step": 116240 }, { "epoch": 27.88, "learning_rate": 7.517207325911067e-05, "loss": 0.0367, "step": 116250 }, { "epoch": 27.88, "learning_rate": 7.516819628931409e-05, "loss": 0.028, "step": 116260 }, { "epoch": 27.88, "learning_rate": 7.516431911683457e-05, "loss": 0.0546, "step": 116270 }, { "epoch": 27.89, "learning_rate": 7.516044174170333e-05, "loss": 0.0473, "step": 116280 }, { "epoch": 27.89, "learning_rate": 7.515656416395155e-05, "loss": 0.0511, "step": 116290 }, { "epoch": 27.89, "learning_rate": 7.515268638361051e-05, "loss": 0.0215, "step": 116300 }, { "epoch": 27.89, "learning_rate": 7.51488084007114e-05, "loss": 0.0532, "step": 116310 }, { "epoch": 27.9, "learning_rate": 7.514493021528548e-05, "loss": 0.0576, "step": 116320 }, { "epoch": 27.9, "learning_rate": 7.514105182736395e-05, "loss": 0.0613, "step": 116330 }, { "epoch": 27.9, "learning_rate": 7.513717323697806e-05, "loss": 0.0758, "step": 116340 }, { "epoch": 27.9, "learning_rate": 7.513329444415905e-05, "loss": 0.0706, "step": 116350 }, { "epoch": 27.9, "learning_rate": 7.512941544893814e-05, "loss": 0.0335, "step": 116360 }, { "epoch": 27.91, "learning_rate": 7.51255362513466e-05, "loss": 0.0377, "step": 116370 }, { "epoch": 27.91, "learning_rate": 7.512165685141561e-05, "loss": 0.0417, "step": 116380 }, { "epoch": 27.91, "learning_rate": 7.511777724917648e-05, "loss": 0.0462, "step": 116390 }, { "epoch": 27.91, "learning_rate": 7.511389744466041e-05, "loss": 0.0598, "step": 116400 }, { "epoch": 27.92, "learning_rate": 7.511001743789868e-05, "loss": 0.0518, "step": 116410 }, { "epoch": 27.92, "learning_rate": 7.510613722892248e-05, "loss": 0.0431, "step": 116420 }, { "epoch": 27.92, "learning_rate": 7.51022568177631e-05, "loss": 0.0378, "step": 116430 }, { "epoch": 27.92, "learning_rate": 7.509837620445179e-05, "loss": 0.0385, "step": 116440 }, { "epoch": 27.93, "learning_rate": 7.509449538901979e-05, "loss": 0.057, "step": 116450 }, { "epoch": 27.93, "learning_rate": 7.509061437149834e-05, "loss": 0.0414, "step": 116460 }, { "epoch": 27.93, "learning_rate": 7.508673315191872e-05, "loss": 0.0611, "step": 116470 }, { "epoch": 27.93, "learning_rate": 7.508285173031216e-05, "loss": 0.0707, "step": 116480 }, { "epoch": 27.93, "learning_rate": 7.507897010670996e-05, "loss": 0.0246, "step": 116490 }, { "epoch": 27.94, "learning_rate": 7.507508828114332e-05, "loss": 0.0644, "step": 116500 }, { "epoch": 27.94, "learning_rate": 7.507120625364357e-05, "loss": 0.0519, "step": 116510 }, { "epoch": 27.94, "learning_rate": 7.50673240242419e-05, "loss": 0.0651, "step": 116520 }, { "epoch": 27.94, "learning_rate": 7.506344159296963e-05, "loss": 0.0346, "step": 116530 }, { "epoch": 27.95, "learning_rate": 7.505955895985799e-05, "loss": 0.0384, "step": 116540 }, { "epoch": 27.95, "learning_rate": 7.505567612493826e-05, "loss": 0.0496, "step": 116550 }, { "epoch": 27.95, "learning_rate": 7.505179308824172e-05, "loss": 0.0604, "step": 116560 }, { "epoch": 28.0, "learning_rate": 7.504790984979963e-05, "loss": 0.0673, "step": 116570 }, { "epoch": 28.0, "learning_rate": 7.504402640964328e-05, "loss": 0.0495, "step": 116580 }, { "epoch": 28.01, "learning_rate": 7.50401427678039e-05, "loss": 0.0627, "step": 116590 }, { "epoch": 28.01, "learning_rate": 7.503625892431281e-05, "loss": 0.0846, "step": 116600 }, { "epoch": 28.01, "learning_rate": 7.503237487920126e-05, "loss": 0.0452, "step": 116610 }, { "epoch": 28.01, "learning_rate": 7.502849063250054e-05, "loss": 0.0483, "step": 116620 }, { "epoch": 28.02, "learning_rate": 7.502460618424194e-05, "loss": 0.0381, "step": 116630 }, { "epoch": 28.02, "learning_rate": 7.502072153445672e-05, "loss": 0.0415, "step": 116640 }, { "epoch": 28.02, "learning_rate": 7.501683668317618e-05, "loss": 0.0456, "step": 116650 }, { "epoch": 28.02, "learning_rate": 7.501295163043161e-05, "loss": 0.0388, "step": 116660 }, { "epoch": 28.02, "learning_rate": 7.500906637625426e-05, "loss": 0.0542, "step": 116670 }, { "epoch": 28.03, "learning_rate": 7.500518092067549e-05, "loss": 0.0308, "step": 116680 }, { "epoch": 28.03, "learning_rate": 7.500129526372651e-05, "loss": 0.0582, "step": 116690 }, { "epoch": 28.03, "learning_rate": 7.499740940543867e-05, "loss": 0.0433, "step": 116700 }, { "epoch": 28.03, "learning_rate": 7.499352334584322e-05, "loss": 0.0433, "step": 116710 }, { "epoch": 28.04, "learning_rate": 7.498963708497148e-05, "loss": 0.0552, "step": 116720 }, { "epoch": 28.04, "learning_rate": 7.498575062285475e-05, "loss": 0.0601, "step": 116730 }, { "epoch": 28.04, "learning_rate": 7.498186395952432e-05, "loss": 0.0503, "step": 116740 }, { "epoch": 28.04, "learning_rate": 7.497797709501149e-05, "loss": 0.0621, "step": 116750 }, { "epoch": 28.04, "learning_rate": 7.497409002934756e-05, "loss": 0.0398, "step": 116760 }, { "epoch": 28.05, "learning_rate": 7.497020276256383e-05, "loss": 0.0341, "step": 116770 }, { "epoch": 28.05, "learning_rate": 7.496631529469163e-05, "loss": 0.0781, "step": 116780 }, { "epoch": 28.05, "learning_rate": 7.496242762576223e-05, "loss": 0.0392, "step": 116790 }, { "epoch": 28.05, "learning_rate": 7.495853975580695e-05, "loss": 0.056, "step": 116800 }, { "epoch": 28.06, "learning_rate": 7.495465168485711e-05, "loss": 0.0639, "step": 116810 }, { "epoch": 28.06, "learning_rate": 7.495076341294403e-05, "loss": 0.0403, "step": 116820 }, { "epoch": 28.06, "learning_rate": 7.494687494009898e-05, "loss": 0.0817, "step": 116830 }, { "epoch": 28.06, "learning_rate": 7.494298626635332e-05, "loss": 0.0525, "step": 116840 }, { "epoch": 28.07, "learning_rate": 7.493909739173835e-05, "loss": 0.0499, "step": 116850 }, { "epoch": 28.07, "learning_rate": 7.493520831628535e-05, "loss": 0.0432, "step": 116860 }, { "epoch": 28.07, "learning_rate": 7.493131904002573e-05, "loss": 0.0627, "step": 116870 }, { "epoch": 28.07, "learning_rate": 7.492742956299071e-05, "loss": 0.0323, "step": 116880 }, { "epoch": 28.07, "learning_rate": 7.492353988521168e-05, "loss": 0.0501, "step": 116890 }, { "epoch": 28.08, "learning_rate": 7.491965000671995e-05, "loss": 0.0613, "step": 116900 }, { "epoch": 28.08, "learning_rate": 7.491575992754683e-05, "loss": 0.0598, "step": 116910 }, { "epoch": 28.08, "learning_rate": 7.491186964772364e-05, "loss": 0.0603, "step": 116920 }, { "epoch": 28.08, "learning_rate": 7.490797916728174e-05, "loss": 0.039, "step": 116930 }, { "epoch": 28.09, "learning_rate": 7.490408848625245e-05, "loss": 0.0435, "step": 116940 }, { "epoch": 28.09, "learning_rate": 7.490019760466708e-05, "loss": 0.0382, "step": 116950 }, { "epoch": 28.09, "learning_rate": 7.489630652255699e-05, "loss": 0.0547, "step": 116960 }, { "epoch": 28.09, "learning_rate": 7.48924152399535e-05, "loss": 0.0447, "step": 116970 }, { "epoch": 28.1, "learning_rate": 7.488852375688796e-05, "loss": 0.052, "step": 116980 }, { "epoch": 28.1, "learning_rate": 7.488463207339171e-05, "loss": 0.0496, "step": 116990 }, { "epoch": 28.1, "learning_rate": 7.488074018949607e-05, "loss": 0.0413, "step": 117000 }, { "epoch": 28.1, "learning_rate": 7.48768481052324e-05, "loss": 0.0532, "step": 117010 }, { "epoch": 28.1, "learning_rate": 7.487295582063204e-05, "loss": 0.0291, "step": 117020 }, { "epoch": 28.11, "learning_rate": 7.486906333572633e-05, "loss": 0.0479, "step": 117030 }, { "epoch": 28.11, "learning_rate": 7.486517065054663e-05, "loss": 0.0396, "step": 117040 }, { "epoch": 28.11, "learning_rate": 7.486127776512424e-05, "loss": 0.052, "step": 117050 }, { "epoch": 28.11, "learning_rate": 7.485738467949059e-05, "loss": 0.0492, "step": 117060 }, { "epoch": 28.12, "learning_rate": 7.485349139367697e-05, "loss": 0.0476, "step": 117070 }, { "epoch": 28.12, "learning_rate": 7.484959790771477e-05, "loss": 0.0379, "step": 117080 }, { "epoch": 28.12, "learning_rate": 7.48457042216353e-05, "loss": 0.0415, "step": 117090 }, { "epoch": 28.12, "learning_rate": 7.484181033546996e-05, "loss": 0.0417, "step": 117100 }, { "epoch": 28.12, "learning_rate": 7.48379162492501e-05, "loss": 0.0465, "step": 117110 }, { "epoch": 28.13, "learning_rate": 7.483402196300705e-05, "loss": 0.063, "step": 117120 }, { "epoch": 28.13, "learning_rate": 7.483012747677222e-05, "loss": 0.0376, "step": 117130 }, { "epoch": 28.13, "learning_rate": 7.482623279057693e-05, "loss": 0.0318, "step": 117140 }, { "epoch": 28.13, "learning_rate": 7.482233790445254e-05, "loss": 0.0474, "step": 117150 }, { "epoch": 28.14, "learning_rate": 7.481844281843047e-05, "loss": 0.0606, "step": 117160 }, { "epoch": 28.14, "learning_rate": 7.481454753254203e-05, "loss": 0.0651, "step": 117170 }, { "epoch": 28.14, "learning_rate": 7.481065204681864e-05, "loss": 0.0406, "step": 117180 }, { "epoch": 28.14, "learning_rate": 7.48067563612916e-05, "loss": 0.0452, "step": 117190 }, { "epoch": 28.15, "learning_rate": 7.480286047599236e-05, "loss": 0.0612, "step": 117200 }, { "epoch": 28.15, "learning_rate": 7.479896439095224e-05, "loss": 0.0493, "step": 117210 }, { "epoch": 28.15, "learning_rate": 7.479506810620266e-05, "loss": 0.05, "step": 117220 }, { "epoch": 28.15, "learning_rate": 7.479117162177496e-05, "loss": 0.0431, "step": 117230 }, { "epoch": 28.15, "learning_rate": 7.478727493770054e-05, "loss": 0.0409, "step": 117240 }, { "epoch": 28.16, "learning_rate": 7.478337805401076e-05, "loss": 0.0536, "step": 117250 }, { "epoch": 28.16, "learning_rate": 7.477948097073702e-05, "loss": 0.0306, "step": 117260 }, { "epoch": 28.16, "learning_rate": 7.47755836879107e-05, "loss": 0.0461, "step": 117270 }, { "epoch": 28.16, "learning_rate": 7.477168620556319e-05, "loss": 0.0356, "step": 117280 }, { "epoch": 28.17, "learning_rate": 7.476778852372586e-05, "loss": 0.0441, "step": 117290 }, { "epoch": 28.17, "learning_rate": 7.476389064243012e-05, "loss": 0.0463, "step": 117300 }, { "epoch": 28.17, "learning_rate": 7.475999256170734e-05, "loss": 0.0344, "step": 117310 }, { "epoch": 28.17, "learning_rate": 7.475609428158891e-05, "loss": 0.0379, "step": 117320 }, { "epoch": 28.18, "learning_rate": 7.475219580210626e-05, "loss": 0.0459, "step": 117330 }, { "epoch": 28.18, "learning_rate": 7.474829712329076e-05, "loss": 0.0503, "step": 117340 }, { "epoch": 28.18, "learning_rate": 7.474439824517379e-05, "loss": 0.0459, "step": 117350 }, { "epoch": 28.18, "learning_rate": 7.474049916778678e-05, "loss": 0.0414, "step": 117360 }, { "epoch": 28.18, "learning_rate": 7.47365998911611e-05, "loss": 0.0396, "step": 117370 }, { "epoch": 28.19, "learning_rate": 7.473270041532817e-05, "loss": 0.0508, "step": 117380 }, { "epoch": 28.19, "learning_rate": 7.47288007403194e-05, "loss": 0.0574, "step": 117390 }, { "epoch": 28.19, "learning_rate": 7.472490086616617e-05, "loss": 0.0531, "step": 117400 }, { "epoch": 28.19, "learning_rate": 7.47210007928999e-05, "loss": 0.0433, "step": 117410 }, { "epoch": 28.2, "learning_rate": 7.4717100520552e-05, "loss": 0.047, "step": 117420 }, { "epoch": 28.2, "learning_rate": 7.471320004915389e-05, "loss": 0.0614, "step": 117430 }, { "epoch": 28.2, "learning_rate": 7.470929937873695e-05, "loss": 0.0337, "step": 117440 }, { "epoch": 28.2, "learning_rate": 7.470539850933263e-05, "loss": 0.0458, "step": 117450 }, { "epoch": 28.2, "learning_rate": 7.470149744097231e-05, "loss": 0.0589, "step": 117460 }, { "epoch": 28.21, "learning_rate": 7.469759617368742e-05, "loss": 0.0609, "step": 117470 }, { "epoch": 28.21, "learning_rate": 7.469369470750939e-05, "loss": 0.0428, "step": 117480 }, { "epoch": 28.21, "learning_rate": 7.468979304246963e-05, "loss": 0.0271, "step": 117490 }, { "epoch": 28.21, "learning_rate": 7.468589117859954e-05, "loss": 0.0493, "step": 117500 }, { "epoch": 28.22, "learning_rate": 7.468198911593056e-05, "loss": 0.0544, "step": 117510 }, { "epoch": 28.22, "learning_rate": 7.467808685449413e-05, "loss": 0.082, "step": 117520 }, { "epoch": 28.22, "learning_rate": 7.467418439432165e-05, "loss": 0.0356, "step": 117530 }, { "epoch": 28.22, "learning_rate": 7.467028173544456e-05, "loss": 0.035, "step": 117540 }, { "epoch": 28.23, "learning_rate": 7.466637887789429e-05, "loss": 0.0214, "step": 117550 }, { "epoch": 28.23, "learning_rate": 7.466247582170225e-05, "loss": 0.0378, "step": 117560 }, { "epoch": 28.23, "learning_rate": 7.46585725668999e-05, "loss": 0.0522, "step": 117570 }, { "epoch": 28.23, "learning_rate": 7.465466911351865e-05, "loss": 0.0215, "step": 117580 }, { "epoch": 28.23, "learning_rate": 7.465076546158996e-05, "loss": 0.0479, "step": 117590 }, { "epoch": 28.24, "learning_rate": 7.464686161114524e-05, "loss": 0.0627, "step": 117600 }, { "epoch": 28.24, "learning_rate": 7.464295756221596e-05, "loss": 0.0289, "step": 117610 }, { "epoch": 28.24, "learning_rate": 7.463905331483352e-05, "loss": 0.0385, "step": 117620 }, { "epoch": 28.24, "learning_rate": 7.463514886902939e-05, "loss": 0.0542, "step": 117630 }, { "epoch": 28.25, "learning_rate": 7.4631244224835e-05, "loss": 0.0293, "step": 117640 }, { "epoch": 28.25, "learning_rate": 7.462733938228181e-05, "loss": 0.0442, "step": 117650 }, { "epoch": 28.25, "learning_rate": 7.462343434140124e-05, "loss": 0.0325, "step": 117660 }, { "epoch": 28.25, "learning_rate": 7.461952910222477e-05, "loss": 0.0429, "step": 117670 }, { "epoch": 28.26, "learning_rate": 7.461562366478383e-05, "loss": 0.0418, "step": 117680 }, { "epoch": 28.26, "learning_rate": 7.461171802910988e-05, "loss": 0.0513, "step": 117690 }, { "epoch": 28.26, "learning_rate": 7.460781219523434e-05, "loss": 0.0668, "step": 117700 }, { "epoch": 28.26, "learning_rate": 7.460390616318872e-05, "loss": 0.0267, "step": 117710 }, { "epoch": 28.26, "learning_rate": 7.459999993300443e-05, "loss": 0.0532, "step": 117720 }, { "epoch": 28.27, "learning_rate": 7.459609350471295e-05, "loss": 0.0422, "step": 117730 }, { "epoch": 28.27, "learning_rate": 7.459218687834573e-05, "loss": 0.0323, "step": 117740 }, { "epoch": 28.27, "learning_rate": 7.458828005393424e-05, "loss": 0.0593, "step": 117750 }, { "epoch": 28.27, "learning_rate": 7.458437303150994e-05, "loss": 0.0435, "step": 117760 }, { "epoch": 28.28, "learning_rate": 7.458046581110428e-05, "loss": 0.0418, "step": 117770 }, { "epoch": 28.28, "learning_rate": 7.457655839274875e-05, "loss": 0.0688, "step": 117780 }, { "epoch": 28.28, "learning_rate": 7.457265077647479e-05, "loss": 0.0503, "step": 117790 }, { "epoch": 28.28, "learning_rate": 7.456874296231387e-05, "loss": 0.0282, "step": 117800 }, { "epoch": 28.28, "learning_rate": 7.456483495029749e-05, "loss": 0.0431, "step": 117810 }, { "epoch": 28.29, "learning_rate": 7.45609267404571e-05, "loss": 0.0629, "step": 117820 }, { "epoch": 28.29, "learning_rate": 7.455701833282418e-05, "loss": 0.0614, "step": 117830 }, { "epoch": 28.29, "learning_rate": 7.455310972743017e-05, "loss": 0.041, "step": 117840 }, { "epoch": 28.29, "learning_rate": 7.45492009243066e-05, "loss": 0.0475, "step": 117850 }, { "epoch": 28.3, "learning_rate": 7.454529192348494e-05, "loss": 0.0759, "step": 117860 }, { "epoch": 28.3, "learning_rate": 7.454138272499664e-05, "loss": 0.0412, "step": 117870 }, { "epoch": 28.3, "learning_rate": 7.45374733288732e-05, "loss": 0.0353, "step": 117880 }, { "epoch": 28.3, "learning_rate": 7.453356373514609e-05, "loss": 0.0534, "step": 117890 }, { "epoch": 28.31, "learning_rate": 7.452965394384682e-05, "loss": 0.0414, "step": 117900 }, { "epoch": 28.31, "learning_rate": 7.452574395500685e-05, "loss": 0.0346, "step": 117910 }, { "epoch": 28.31, "learning_rate": 7.452183376865767e-05, "loss": 0.0534, "step": 117920 }, { "epoch": 28.31, "learning_rate": 7.45179233848308e-05, "loss": 0.0474, "step": 117930 }, { "epoch": 28.31, "learning_rate": 7.451401280355769e-05, "loss": 0.0416, "step": 117940 }, { "epoch": 28.32, "learning_rate": 7.451010202486987e-05, "loss": 0.029, "step": 117950 }, { "epoch": 28.32, "learning_rate": 7.450619104879879e-05, "loss": 0.0591, "step": 117960 }, { "epoch": 28.32, "learning_rate": 7.450227987537598e-05, "loss": 0.0579, "step": 117970 }, { "epoch": 28.32, "learning_rate": 7.449836850463293e-05, "loss": 0.0697, "step": 117980 }, { "epoch": 28.33, "learning_rate": 7.449445693660113e-05, "loss": 0.0558, "step": 117990 }, { "epoch": 28.33, "learning_rate": 7.449054517131209e-05, "loss": 0.0365, "step": 118000 }, { "epoch": 28.33, "learning_rate": 7.44866332087973e-05, "loss": 0.04, "step": 118010 }, { "epoch": 28.33, "learning_rate": 7.44827210490883e-05, "loss": 0.0429, "step": 118020 }, { "epoch": 28.34, "learning_rate": 7.447880869221655e-05, "loss": 0.0522, "step": 118030 }, { "epoch": 28.34, "learning_rate": 7.447489613821357e-05, "loss": 0.0475, "step": 118040 }, { "epoch": 28.34, "learning_rate": 7.447098338711087e-05, "loss": 0.0523, "step": 118050 }, { "epoch": 28.34, "learning_rate": 7.446707043893996e-05, "loss": 0.0303, "step": 118060 }, { "epoch": 28.34, "learning_rate": 7.446315729373238e-05, "loss": 0.0255, "step": 118070 }, { "epoch": 28.35, "learning_rate": 7.44592439515196e-05, "loss": 0.0604, "step": 118080 }, { "epoch": 28.35, "learning_rate": 7.445533041233315e-05, "loss": 0.0494, "step": 118090 }, { "epoch": 28.35, "learning_rate": 7.445141667620455e-05, "loss": 0.0285, "step": 118100 }, { "epoch": 28.35, "learning_rate": 7.444750274316531e-05, "loss": 0.0296, "step": 118110 }, { "epoch": 28.36, "learning_rate": 7.444358861324696e-05, "loss": 0.0284, "step": 118120 }, { "epoch": 28.36, "learning_rate": 7.4439674286481e-05, "loss": 0.0388, "step": 118130 }, { "epoch": 28.36, "learning_rate": 7.4435759762899e-05, "loss": 0.0338, "step": 118140 }, { "epoch": 28.36, "learning_rate": 7.443184504253243e-05, "loss": 0.0321, "step": 118150 }, { "epoch": 28.36, "learning_rate": 7.442793012541284e-05, "loss": 0.04, "step": 118160 }, { "epoch": 28.37, "learning_rate": 7.442401501157178e-05, "loss": 0.05, "step": 118170 }, { "epoch": 28.37, "learning_rate": 7.442009970104073e-05, "loss": 0.0434, "step": 118180 }, { "epoch": 28.37, "learning_rate": 7.441618419385125e-05, "loss": 0.0417, "step": 118190 }, { "epoch": 28.37, "learning_rate": 7.441226849003487e-05, "loss": 0.0453, "step": 118200 }, { "epoch": 28.38, "learning_rate": 7.440835258962314e-05, "loss": 0.0481, "step": 118210 }, { "epoch": 28.38, "learning_rate": 7.440443649264756e-05, "loss": 0.0483, "step": 118220 }, { "epoch": 28.38, "learning_rate": 7.440052019913968e-05, "loss": 0.0289, "step": 118230 }, { "epoch": 28.38, "learning_rate": 7.439660370913104e-05, "loss": 0.0312, "step": 118240 }, { "epoch": 28.39, "learning_rate": 7.439268702265318e-05, "loss": 0.0282, "step": 118250 }, { "epoch": 28.39, "learning_rate": 7.438877013973766e-05, "loss": 0.046, "step": 118260 }, { "epoch": 28.39, "learning_rate": 7.4384853060416e-05, "loss": 0.0502, "step": 118270 }, { "epoch": 28.39, "learning_rate": 7.438093578471975e-05, "loss": 0.0386, "step": 118280 }, { "epoch": 28.39, "learning_rate": 7.437701831268046e-05, "loss": 0.0455, "step": 118290 }, { "epoch": 28.4, "learning_rate": 7.437310064432966e-05, "loss": 0.0524, "step": 118300 }, { "epoch": 28.4, "learning_rate": 7.436918277969895e-05, "loss": 0.0428, "step": 118310 }, { "epoch": 28.4, "learning_rate": 7.436526471881982e-05, "loss": 0.032, "step": 118320 }, { "epoch": 28.4, "learning_rate": 7.436134646172385e-05, "loss": 0.0438, "step": 118330 }, { "epoch": 28.41, "learning_rate": 7.43574280084426e-05, "loss": 0.0384, "step": 118340 }, { "epoch": 28.41, "learning_rate": 7.435350935900762e-05, "loss": 0.0262, "step": 118350 }, { "epoch": 28.41, "learning_rate": 7.434959051345048e-05, "loss": 0.0562, "step": 118360 }, { "epoch": 28.41, "learning_rate": 7.43456714718027e-05, "loss": 0.0606, "step": 118370 }, { "epoch": 28.41, "learning_rate": 7.43417522340959e-05, "loss": 0.044, "step": 118380 }, { "epoch": 28.42, "learning_rate": 7.433783280036157e-05, "loss": 0.0399, "step": 118390 }, { "epoch": 28.42, "learning_rate": 7.433391317063134e-05, "loss": 0.0406, "step": 118400 }, { "epoch": 28.42, "learning_rate": 7.432999334493673e-05, "loss": 0.0327, "step": 118410 }, { "epoch": 28.42, "learning_rate": 7.432607332330933e-05, "loss": 0.047, "step": 118420 }, { "epoch": 28.43, "learning_rate": 7.432215310578071e-05, "loss": 0.0574, "step": 118430 }, { "epoch": 28.43, "learning_rate": 7.431823269238241e-05, "loss": 0.0227, "step": 118440 }, { "epoch": 28.43, "learning_rate": 7.431431208314606e-05, "loss": 0.0584, "step": 118450 }, { "epoch": 28.43, "learning_rate": 7.431039127810318e-05, "loss": 0.0687, "step": 118460 }, { "epoch": 28.44, "learning_rate": 7.430647027728537e-05, "loss": 0.0529, "step": 118470 }, { "epoch": 28.44, "learning_rate": 7.430254908072419e-05, "loss": 0.0547, "step": 118480 }, { "epoch": 28.44, "learning_rate": 7.429862768845122e-05, "loss": 0.0588, "step": 118490 }, { "epoch": 28.44, "learning_rate": 7.429470610049806e-05, "loss": 0.0428, "step": 118500 }, { "epoch": 28.44, "learning_rate": 7.429078431689628e-05, "loss": 0.0341, "step": 118510 }, { "epoch": 28.45, "learning_rate": 7.428686233767746e-05, "loss": 0.0248, "step": 118520 }, { "epoch": 28.45, "learning_rate": 7.428294016287318e-05, "loss": 0.0564, "step": 118530 }, { "epoch": 28.45, "learning_rate": 7.427901779251503e-05, "loss": 0.036, "step": 118540 }, { "epoch": 28.45, "learning_rate": 7.427509522663459e-05, "loss": 0.06, "step": 118550 }, { "epoch": 28.46, "learning_rate": 7.427117246526347e-05, "loss": 0.0302, "step": 118560 }, { "epoch": 28.46, "learning_rate": 7.426724950843324e-05, "loss": 0.0582, "step": 118570 }, { "epoch": 28.46, "learning_rate": 7.42633263561755e-05, "loss": 0.0638, "step": 118580 }, { "epoch": 28.46, "learning_rate": 7.425940300852184e-05, "loss": 0.0513, "step": 118590 }, { "epoch": 28.47, "learning_rate": 7.425547946550387e-05, "loss": 0.044, "step": 118600 }, { "epoch": 28.47, "learning_rate": 7.425155572715317e-05, "loss": 0.0443, "step": 118610 }, { "epoch": 28.47, "learning_rate": 7.424763179350134e-05, "loss": 0.0384, "step": 118620 }, { "epoch": 28.47, "learning_rate": 7.424370766457997e-05, "loss": 0.0492, "step": 118630 }, { "epoch": 28.47, "learning_rate": 7.42397833404207e-05, "loss": 0.0265, "step": 118640 }, { "epoch": 28.48, "learning_rate": 7.423585882105511e-05, "loss": 0.0316, "step": 118650 }, { "epoch": 28.48, "learning_rate": 7.423193410651478e-05, "loss": 0.0498, "step": 118660 }, { "epoch": 28.48, "learning_rate": 7.422800919683135e-05, "loss": 0.0525, "step": 118670 }, { "epoch": 28.48, "learning_rate": 7.422408409203643e-05, "loss": 0.044, "step": 118680 }, { "epoch": 28.49, "learning_rate": 7.42201587921616e-05, "loss": 0.0497, "step": 118690 }, { "epoch": 28.49, "learning_rate": 7.421623329723848e-05, "loss": 0.0679, "step": 118700 }, { "epoch": 28.49, "learning_rate": 7.421230760729871e-05, "loss": 0.0458, "step": 118710 }, { "epoch": 28.49, "learning_rate": 7.420838172237388e-05, "loss": 0.0327, "step": 118720 }, { "epoch": 28.49, "learning_rate": 7.42044556424956e-05, "loss": 0.0284, "step": 118730 }, { "epoch": 28.5, "learning_rate": 7.42005293676955e-05, "loss": 0.0322, "step": 118740 }, { "epoch": 28.5, "learning_rate": 7.419660289800521e-05, "loss": 0.0321, "step": 118750 }, { "epoch": 28.5, "learning_rate": 7.419267623345631e-05, "loss": 0.0526, "step": 118760 }, { "epoch": 28.5, "learning_rate": 7.418874937408046e-05, "loss": 0.0416, "step": 118770 }, { "epoch": 28.51, "learning_rate": 7.418482231990929e-05, "loss": 0.0506, "step": 118780 }, { "epoch": 28.51, "learning_rate": 7.41808950709744e-05, "loss": 0.0397, "step": 118790 }, { "epoch": 28.51, "learning_rate": 7.41769676273074e-05, "loss": 0.018, "step": 118800 }, { "epoch": 28.51, "learning_rate": 7.417303998893996e-05, "loss": 0.0605, "step": 118810 }, { "epoch": 28.52, "learning_rate": 7.416911215590369e-05, "loss": 0.0389, "step": 118820 }, { "epoch": 28.52, "learning_rate": 7.416518412823022e-05, "loss": 0.0531, "step": 118830 }, { "epoch": 28.52, "learning_rate": 7.416125590595117e-05, "loss": 0.0464, "step": 118840 }, { "epoch": 28.52, "learning_rate": 7.415732748909823e-05, "loss": 0.0513, "step": 118850 }, { "epoch": 28.52, "learning_rate": 7.415339887770297e-05, "loss": 0.0533, "step": 118860 }, { "epoch": 28.53, "learning_rate": 7.414947007179706e-05, "loss": 0.0457, "step": 118870 }, { "epoch": 28.53, "learning_rate": 7.414554107141214e-05, "loss": 0.0712, "step": 118880 }, { "epoch": 28.53, "learning_rate": 7.414161187657983e-05, "loss": 0.0687, "step": 118890 }, { "epoch": 28.53, "learning_rate": 7.41376824873318e-05, "loss": 0.0319, "step": 118900 }, { "epoch": 28.54, "learning_rate": 7.413375290369966e-05, "loss": 0.0746, "step": 118910 }, { "epoch": 28.54, "learning_rate": 7.41298231257151e-05, "loss": 0.0689, "step": 118920 }, { "epoch": 28.54, "learning_rate": 7.412589315340974e-05, "loss": 0.0515, "step": 118930 }, { "epoch": 28.54, "learning_rate": 7.412196298681521e-05, "loss": 0.0541, "step": 118940 }, { "epoch": 28.55, "learning_rate": 7.411803262596321e-05, "loss": 0.0592, "step": 118950 }, { "epoch": 28.55, "learning_rate": 7.411410207088534e-05, "loss": 0.0721, "step": 118960 }, { "epoch": 28.55, "learning_rate": 7.411017132161329e-05, "loss": 0.0275, "step": 118970 }, { "epoch": 28.55, "learning_rate": 7.41062403781787e-05, "loss": 0.0623, "step": 118980 }, { "epoch": 28.55, "learning_rate": 7.410230924061324e-05, "loss": 0.0508, "step": 118990 }, { "epoch": 28.56, "learning_rate": 7.409837790894854e-05, "loss": 0.0572, "step": 119000 }, { "epoch": 28.56, "learning_rate": 7.409444638321628e-05, "loss": 0.0449, "step": 119010 }, { "epoch": 28.56, "learning_rate": 7.40905146634481e-05, "loss": 0.0761, "step": 119020 }, { "epoch": 28.56, "learning_rate": 7.40865827496757e-05, "loss": 0.0354, "step": 119030 }, { "epoch": 28.57, "learning_rate": 7.408265064193071e-05, "loss": 0.0567, "step": 119040 }, { "epoch": 28.57, "learning_rate": 7.407871834024482e-05, "loss": 0.0773, "step": 119050 }, { "epoch": 28.57, "learning_rate": 7.40747858446497e-05, "loss": 0.0618, "step": 119060 }, { "epoch": 28.57, "learning_rate": 7.407085315517699e-05, "loss": 0.0448, "step": 119070 }, { "epoch": 28.57, "learning_rate": 7.406692027185837e-05, "loss": 0.0471, "step": 119080 }, { "epoch": 28.58, "learning_rate": 7.406298719472553e-05, "loss": 0.0367, "step": 119090 }, { "epoch": 28.58, "learning_rate": 7.405905392381012e-05, "loss": 0.0367, "step": 119100 }, { "epoch": 28.58, "learning_rate": 7.405512045914385e-05, "loss": 0.0349, "step": 119110 }, { "epoch": 28.58, "learning_rate": 7.405118680075836e-05, "loss": 0.0506, "step": 119120 }, { "epoch": 28.59, "learning_rate": 7.404725294868533e-05, "loss": 0.0356, "step": 119130 }, { "epoch": 28.59, "learning_rate": 7.404331890295646e-05, "loss": 0.0353, "step": 119140 }, { "epoch": 28.59, "learning_rate": 7.403938466360343e-05, "loss": 0.0453, "step": 119150 }, { "epoch": 28.59, "learning_rate": 7.403545023065791e-05, "loss": 0.0404, "step": 119160 }, { "epoch": 28.6, "learning_rate": 7.40315156041516e-05, "loss": 0.0493, "step": 119170 }, { "epoch": 28.6, "learning_rate": 7.402758078411617e-05, "loss": 0.0661, "step": 119180 }, { "epoch": 28.6, "learning_rate": 7.402364577058332e-05, "loss": 0.0339, "step": 119190 }, { "epoch": 28.6, "learning_rate": 7.401971056358473e-05, "loss": 0.0392, "step": 119200 }, { "epoch": 28.6, "learning_rate": 7.40157751631521e-05, "loss": 0.0366, "step": 119210 }, { "epoch": 28.61, "learning_rate": 7.40118395693171e-05, "loss": 0.0402, "step": 119220 }, { "epoch": 28.61, "learning_rate": 7.400790378211146e-05, "loss": 0.0651, "step": 119230 }, { "epoch": 28.61, "learning_rate": 7.400396780156685e-05, "loss": 0.0538, "step": 119240 }, { "epoch": 28.61, "learning_rate": 7.400003162771497e-05, "loss": 0.0474, "step": 119250 }, { "epoch": 28.62, "learning_rate": 7.399609526058752e-05, "loss": 0.0429, "step": 119260 }, { "epoch": 28.62, "learning_rate": 7.399215870021622e-05, "loss": 0.0429, "step": 119270 }, { "epoch": 28.62, "learning_rate": 7.398822194663273e-05, "loss": 0.0357, "step": 119280 }, { "epoch": 28.62, "learning_rate": 7.398428499986879e-05, "loss": 0.0465, "step": 119290 }, { "epoch": 28.63, "learning_rate": 7.398034785995608e-05, "loss": 0.0432, "step": 119300 }, { "epoch": 28.63, "learning_rate": 7.397641052692633e-05, "loss": 0.0382, "step": 119310 }, { "epoch": 28.63, "learning_rate": 7.397247300081124e-05, "loss": 0.0459, "step": 119320 }, { "epoch": 28.63, "learning_rate": 7.396853528164249e-05, "loss": 0.0493, "step": 119330 }, { "epoch": 28.63, "learning_rate": 7.396459736945185e-05, "loss": 0.0818, "step": 119340 }, { "epoch": 28.64, "learning_rate": 7.396065926427099e-05, "loss": 0.059, "step": 119350 }, { "epoch": 28.64, "learning_rate": 7.395672096613163e-05, "loss": 0.0531, "step": 119360 }, { "epoch": 28.64, "learning_rate": 7.395278247506547e-05, "loss": 0.0436, "step": 119370 }, { "epoch": 28.64, "learning_rate": 7.394884379110427e-05, "loss": 0.0416, "step": 119380 }, { "epoch": 28.65, "learning_rate": 7.394490491427971e-05, "loss": 0.0363, "step": 119390 }, { "epoch": 28.65, "learning_rate": 7.394096584462352e-05, "loss": 0.0689, "step": 119400 }, { "epoch": 28.65, "learning_rate": 7.393702658216745e-05, "loss": 0.0253, "step": 119410 }, { "epoch": 28.65, "learning_rate": 7.393308712694318e-05, "loss": 0.0628, "step": 119420 }, { "epoch": 28.65, "learning_rate": 7.392914747898247e-05, "loss": 0.0255, "step": 119430 }, { "epoch": 28.66, "learning_rate": 7.392520763831702e-05, "loss": 0.0495, "step": 119440 }, { "epoch": 28.66, "learning_rate": 7.392126760497857e-05, "loss": 0.0403, "step": 119450 }, { "epoch": 28.66, "learning_rate": 7.391732737899886e-05, "loss": 0.0647, "step": 119460 }, { "epoch": 28.66, "learning_rate": 7.391338696040959e-05, "loss": 0.0657, "step": 119470 }, { "epoch": 28.67, "learning_rate": 7.390944634924255e-05, "loss": 0.0812, "step": 119480 }, { "epoch": 28.67, "learning_rate": 7.39055055455294e-05, "loss": 0.0581, "step": 119490 }, { "epoch": 28.67, "learning_rate": 7.390156454930193e-05, "loss": 0.0448, "step": 119500 }, { "epoch": 28.67, "learning_rate": 7.389762336059186e-05, "loss": 0.0461, "step": 119510 }, { "epoch": 28.68, "learning_rate": 7.389368197943091e-05, "loss": 0.0537, "step": 119520 }, { "epoch": 28.68, "learning_rate": 7.388974040585088e-05, "loss": 0.0359, "step": 119530 }, { "epoch": 28.68, "learning_rate": 7.388579863988345e-05, "loss": 0.0976, "step": 119540 }, { "epoch": 28.68, "learning_rate": 7.388185668156037e-05, "loss": 0.0511, "step": 119550 }, { "epoch": 28.68, "learning_rate": 7.387791453091344e-05, "loss": 0.0355, "step": 119560 }, { "epoch": 28.69, "learning_rate": 7.387397218797433e-05, "loss": 0.0474, "step": 119570 }, { "epoch": 28.69, "learning_rate": 7.387002965277485e-05, "loss": 0.0447, "step": 119580 }, { "epoch": 28.69, "learning_rate": 7.386608692534671e-05, "loss": 0.062, "step": 119590 }, { "epoch": 28.69, "learning_rate": 7.38621440057217e-05, "loss": 0.0422, "step": 119600 }, { "epoch": 28.7, "learning_rate": 7.385820089393153e-05, "loss": 0.0238, "step": 119610 }, { "epoch": 28.7, "learning_rate": 7.385425759000799e-05, "loss": 0.0359, "step": 119620 }, { "epoch": 28.7, "learning_rate": 7.38503140939828e-05, "loss": 0.0616, "step": 119630 }, { "epoch": 28.7, "learning_rate": 7.384637040588775e-05, "loss": 0.093, "step": 119640 }, { "epoch": 28.71, "learning_rate": 7.384242652575459e-05, "loss": 0.0455, "step": 119650 }, { "epoch": 28.71, "learning_rate": 7.383848245361507e-05, "loss": 0.032, "step": 119660 }, { "epoch": 28.71, "learning_rate": 7.383453818950095e-05, "loss": 0.0542, "step": 119670 }, { "epoch": 28.71, "learning_rate": 7.383059373344402e-05, "loss": 0.0385, "step": 119680 }, { "epoch": 28.71, "learning_rate": 7.382664908547602e-05, "loss": 0.0541, "step": 119690 }, { "epoch": 28.72, "learning_rate": 7.382270424562873e-05, "loss": 0.0298, "step": 119700 }, { "epoch": 28.72, "learning_rate": 7.381875921393391e-05, "loss": 0.0555, "step": 119710 }, { "epoch": 28.72, "learning_rate": 7.381481399042335e-05, "loss": 0.0465, "step": 119720 }, { "epoch": 28.72, "learning_rate": 7.381086857512877e-05, "loss": 0.0476, "step": 119730 }, { "epoch": 28.73, "learning_rate": 7.380692296808201e-05, "loss": 0.0317, "step": 119740 }, { "epoch": 28.73, "learning_rate": 7.38029771693148e-05, "loss": 0.0426, "step": 119750 }, { "epoch": 28.73, "learning_rate": 7.379903117885894e-05, "loss": 0.0517, "step": 119760 }, { "epoch": 28.73, "learning_rate": 7.37950849967462e-05, "loss": 0.0453, "step": 119770 }, { "epoch": 28.73, "learning_rate": 7.379113862300832e-05, "loss": 0.0627, "step": 119780 }, { "epoch": 28.74, "learning_rate": 7.378719205767715e-05, "loss": 0.0522, "step": 119790 }, { "epoch": 28.74, "learning_rate": 7.378324530078443e-05, "loss": 0.041, "step": 119800 }, { "epoch": 28.74, "learning_rate": 7.377929835236195e-05, "loss": 0.049, "step": 119810 }, { "epoch": 28.74, "learning_rate": 7.37753512124415e-05, "loss": 0.0544, "step": 119820 }, { "epoch": 28.75, "learning_rate": 7.377140388105484e-05, "loss": 0.0539, "step": 119830 }, { "epoch": 28.75, "learning_rate": 7.376745635823382e-05, "loss": 0.0701, "step": 119840 }, { "epoch": 28.75, "learning_rate": 7.376350864401018e-05, "loss": 0.0499, "step": 119850 }, { "epoch": 28.75, "learning_rate": 7.375956073841571e-05, "loss": 0.0305, "step": 119860 }, { "epoch": 28.76, "learning_rate": 7.375561264148222e-05, "loss": 0.0355, "step": 119870 }, { "epoch": 28.76, "learning_rate": 7.37516643532415e-05, "loss": 0.0585, "step": 119880 }, { "epoch": 28.76, "learning_rate": 7.374771587372538e-05, "loss": 0.0587, "step": 119890 }, { "epoch": 28.76, "learning_rate": 7.37437672029656e-05, "loss": 0.0552, "step": 119900 }, { "epoch": 28.76, "learning_rate": 7.373981834099399e-05, "loss": 0.0641, "step": 119910 }, { "epoch": 28.77, "learning_rate": 7.373586928784234e-05, "loss": 0.0428, "step": 119920 }, { "epoch": 28.77, "learning_rate": 7.373192004354245e-05, "loss": 0.0592, "step": 119930 }, { "epoch": 28.77, "learning_rate": 7.372797060812615e-05, "loss": 0.0502, "step": 119940 }, { "epoch": 28.77, "learning_rate": 7.372402098162522e-05, "loss": 0.038, "step": 119950 }, { "epoch": 28.78, "learning_rate": 7.372007116407148e-05, "loss": 0.0447, "step": 119960 }, { "epoch": 28.78, "learning_rate": 7.371612115549672e-05, "loss": 0.0418, "step": 119970 }, { "epoch": 28.78, "learning_rate": 7.371217095593277e-05, "loss": 0.0614, "step": 119980 }, { "epoch": 28.78, "learning_rate": 7.370822056541143e-05, "loss": 0.0609, "step": 119990 }, { "epoch": 28.79, "learning_rate": 7.370426998396452e-05, "loss": 0.0711, "step": 120000 }, { "epoch": 28.79, "learning_rate": 7.370031921162385e-05, "loss": 0.065, "step": 120010 }, { "epoch": 28.79, "learning_rate": 7.369636824842122e-05, "loss": 0.0439, "step": 120020 }, { "epoch": 28.79, "learning_rate": 7.36924170943885e-05, "loss": 0.0495, "step": 120030 }, { "epoch": 28.79, "learning_rate": 7.368846574955744e-05, "loss": 0.0598, "step": 120040 }, { "epoch": 28.8, "learning_rate": 7.368451421395993e-05, "loss": 0.0342, "step": 120050 }, { "epoch": 28.8, "learning_rate": 7.368056248762772e-05, "loss": 0.0947, "step": 120060 }, { "epoch": 28.8, "learning_rate": 7.367661057059269e-05, "loss": 0.0266, "step": 120070 }, { "epoch": 28.8, "learning_rate": 7.367265846288664e-05, "loss": 0.0569, "step": 120080 }, { "epoch": 28.81, "learning_rate": 7.36687061645414e-05, "loss": 0.0419, "step": 120090 }, { "epoch": 28.81, "learning_rate": 7.366475367558882e-05, "loss": 0.0429, "step": 120100 }, { "epoch": 28.81, "learning_rate": 7.36608009960607e-05, "loss": 0.0422, "step": 120110 }, { "epoch": 28.81, "learning_rate": 7.365684812598889e-05, "loss": 0.0389, "step": 120120 }, { "epoch": 28.81, "learning_rate": 7.365289506540521e-05, "loss": 0.04, "step": 120130 }, { "epoch": 28.82, "learning_rate": 7.36489418143415e-05, "loss": 0.0698, "step": 120140 }, { "epoch": 28.82, "learning_rate": 7.36449883728296e-05, "loss": 0.0763, "step": 120150 }, { "epoch": 28.82, "learning_rate": 7.364103474090133e-05, "loss": 0.041, "step": 120160 }, { "epoch": 28.82, "learning_rate": 7.363708091858855e-05, "loss": 0.0457, "step": 120170 }, { "epoch": 28.83, "learning_rate": 7.36331269059231e-05, "loss": 0.0632, "step": 120180 }, { "epoch": 28.83, "learning_rate": 7.362917270293683e-05, "loss": 0.0912, "step": 120190 }, { "epoch": 28.83, "learning_rate": 7.362521830966155e-05, "loss": 0.0432, "step": 120200 }, { "epoch": 28.83, "learning_rate": 7.362126372612912e-05, "loss": 0.0612, "step": 120210 }, { "epoch": 28.84, "learning_rate": 7.36173089523714e-05, "loss": 0.0515, "step": 120220 }, { "epoch": 28.84, "learning_rate": 7.361335398842024e-05, "loss": 0.0485, "step": 120230 }, { "epoch": 28.84, "learning_rate": 7.360939883430748e-05, "loss": 0.0538, "step": 120240 }, { "epoch": 28.84, "learning_rate": 7.360544349006497e-05, "loss": 0.0349, "step": 120250 }, { "epoch": 28.84, "learning_rate": 7.360148795572455e-05, "loss": 0.0278, "step": 120260 }, { "epoch": 28.85, "learning_rate": 7.359753223131811e-05, "loss": 0.0583, "step": 120270 }, { "epoch": 28.85, "learning_rate": 7.359357631687745e-05, "loss": 0.0363, "step": 120280 }, { "epoch": 28.85, "learning_rate": 7.35896202124345e-05, "loss": 0.0683, "step": 120290 }, { "epoch": 28.85, "learning_rate": 7.358566391802106e-05, "loss": 0.0594, "step": 120300 }, { "epoch": 28.86, "learning_rate": 7.358170743366902e-05, "loss": 0.0308, "step": 120310 }, { "epoch": 28.86, "learning_rate": 7.357775075941025e-05, "loss": 0.0323, "step": 120320 }, { "epoch": 28.86, "learning_rate": 7.357379389527658e-05, "loss": 0.0535, "step": 120330 }, { "epoch": 28.86, "learning_rate": 7.35698368412999e-05, "loss": 0.031, "step": 120340 }, { "epoch": 28.87, "learning_rate": 7.356587959751205e-05, "loss": 0.0232, "step": 120350 }, { "epoch": 28.87, "learning_rate": 7.356192216394493e-05, "loss": 0.0309, "step": 120360 }, { "epoch": 28.87, "learning_rate": 7.35579645406304e-05, "loss": 0.0755, "step": 120370 }, { "epoch": 28.87, "learning_rate": 7.355400672760035e-05, "loss": 0.0394, "step": 120380 }, { "epoch": 28.87, "learning_rate": 7.35500487248866e-05, "loss": 0.0533, "step": 120390 }, { "epoch": 28.88, "learning_rate": 7.354609053252107e-05, "loss": 0.0262, "step": 120400 }, { "epoch": 28.88, "learning_rate": 7.354213215053563e-05, "loss": 0.0528, "step": 120410 }, { "epoch": 28.88, "learning_rate": 7.353817357896213e-05, "loss": 0.058, "step": 120420 }, { "epoch": 28.88, "learning_rate": 7.353421481783249e-05, "loss": 0.0348, "step": 120430 }, { "epoch": 28.89, "learning_rate": 7.353025586717856e-05, "loss": 0.0569, "step": 120440 }, { "epoch": 28.89, "learning_rate": 7.352629672703221e-05, "loss": 0.0382, "step": 120450 }, { "epoch": 28.89, "learning_rate": 7.352233739742538e-05, "loss": 0.0674, "step": 120460 }, { "epoch": 28.89, "learning_rate": 7.351837787838991e-05, "loss": 0.0547, "step": 120470 }, { "epoch": 28.89, "learning_rate": 7.351441816995767e-05, "loss": 0.0429, "step": 120480 }, { "epoch": 28.9, "learning_rate": 7.35104582721606e-05, "loss": 0.0432, "step": 120490 }, { "epoch": 28.9, "learning_rate": 7.350649818503057e-05, "loss": 0.0291, "step": 120500 }, { "epoch": 28.9, "learning_rate": 7.350253790859945e-05, "loss": 0.0582, "step": 120510 }, { "epoch": 28.9, "learning_rate": 7.349857744289914e-05, "loss": 0.0312, "step": 120520 }, { "epoch": 28.91, "learning_rate": 7.349461678796155e-05, "loss": 0.0374, "step": 120530 }, { "epoch": 28.91, "learning_rate": 7.349065594381857e-05, "loss": 0.0515, "step": 120540 }, { "epoch": 28.91, "learning_rate": 7.348669491050209e-05, "loss": 0.035, "step": 120550 }, { "epoch": 28.91, "learning_rate": 7.348273368804402e-05, "loss": 0.038, "step": 120560 }, { "epoch": 28.92, "learning_rate": 7.347877227647625e-05, "loss": 0.0348, "step": 120570 }, { "epoch": 28.92, "learning_rate": 7.347481067583069e-05, "loss": 0.0478, "step": 120580 }, { "epoch": 28.92, "learning_rate": 7.347084888613924e-05, "loss": 0.0722, "step": 120590 }, { "epoch": 28.92, "learning_rate": 7.346688690743378e-05, "loss": 0.0281, "step": 120600 }, { "epoch": 28.92, "learning_rate": 7.346292473974627e-05, "loss": 0.0604, "step": 120610 }, { "epoch": 28.93, "learning_rate": 7.345896238310856e-05, "loss": 0.0625, "step": 120620 }, { "epoch": 28.93, "learning_rate": 7.345499983755261e-05, "loss": 0.0481, "step": 120630 }, { "epoch": 28.93, "learning_rate": 7.345103710311031e-05, "loss": 0.0456, "step": 120640 }, { "epoch": 28.93, "learning_rate": 7.344707417981354e-05, "loss": 0.0389, "step": 120650 }, { "epoch": 28.94, "learning_rate": 7.344311106769428e-05, "loss": 0.033, "step": 120660 }, { "epoch": 28.94, "learning_rate": 7.34391477667844e-05, "loss": 0.0406, "step": 120670 }, { "epoch": 28.94, "learning_rate": 7.343518427711581e-05, "loss": 0.0409, "step": 120680 }, { "epoch": 28.94, "learning_rate": 7.343122059872048e-05, "loss": 0.0494, "step": 120690 }, { "epoch": 28.95, "learning_rate": 7.342725673163027e-05, "loss": 0.0472, "step": 120700 }, { "epoch": 28.95, "learning_rate": 7.342329267587714e-05, "loss": 0.0457, "step": 120710 }, { "epoch": 28.95, "learning_rate": 7.341932843149298e-05, "loss": 0.0391, "step": 120720 }, { "epoch": 29.0, "learning_rate": 7.341536399850975e-05, "loss": 0.0554, "step": 120730 }, { "epoch": 29.0, "learning_rate": 7.341139937695935e-05, "loss": 0.0566, "step": 120740 }, { "epoch": 29.01, "learning_rate": 7.340743456687373e-05, "loss": 0.0422, "step": 120750 }, { "epoch": 29.01, "learning_rate": 7.340346956828481e-05, "loss": 0.0485, "step": 120760 }, { "epoch": 29.01, "learning_rate": 7.33995043812245e-05, "loss": 0.0362, "step": 120770 }, { "epoch": 29.01, "learning_rate": 7.339553900572478e-05, "loss": 0.0761, "step": 120780 }, { "epoch": 29.01, "learning_rate": 7.339157344181753e-05, "loss": 0.0513, "step": 120790 }, { "epoch": 29.02, "learning_rate": 7.338760768953473e-05, "loss": 0.0632, "step": 120800 }, { "epoch": 29.02, "learning_rate": 7.338364174890827e-05, "loss": 0.0394, "step": 120810 }, { "epoch": 29.02, "learning_rate": 7.337967561997013e-05, "loss": 0.0468, "step": 120820 }, { "epoch": 29.02, "learning_rate": 7.337570930275224e-05, "loss": 0.0295, "step": 120830 }, { "epoch": 29.03, "learning_rate": 7.337174279728652e-05, "loss": 0.0374, "step": 120840 }, { "epoch": 29.03, "learning_rate": 7.336777610360494e-05, "loss": 0.0539, "step": 120850 }, { "epoch": 29.03, "learning_rate": 7.336380922173942e-05, "loss": 0.0324, "step": 120860 }, { "epoch": 29.03, "learning_rate": 7.335984215172193e-05, "loss": 0.0478, "step": 120870 }, { "epoch": 29.03, "learning_rate": 7.335587489358442e-05, "loss": 0.0488, "step": 120880 }, { "epoch": 29.04, "learning_rate": 7.33519074473588e-05, "loss": 0.0247, "step": 120890 }, { "epoch": 29.04, "learning_rate": 7.334793981307707e-05, "loss": 0.0411, "step": 120900 }, { "epoch": 29.04, "learning_rate": 7.334397199077112e-05, "loss": 0.0369, "step": 120910 }, { "epoch": 29.04, "learning_rate": 7.334000398047299e-05, "loss": 0.0445, "step": 120920 }, { "epoch": 29.05, "learning_rate": 7.333603578221454e-05, "loss": 0.0329, "step": 120930 }, { "epoch": 29.05, "learning_rate": 7.33320673960278e-05, "loss": 0.0519, "step": 120940 }, { "epoch": 29.05, "learning_rate": 7.332809882194469e-05, "loss": 0.0218, "step": 120950 }, { "epoch": 29.05, "learning_rate": 7.332413005999717e-05, "loss": 0.0392, "step": 120960 }, { "epoch": 29.06, "learning_rate": 7.332016111021723e-05, "loss": 0.0307, "step": 120970 }, { "epoch": 29.06, "learning_rate": 7.33161919726368e-05, "loss": 0.0513, "step": 120980 }, { "epoch": 29.06, "learning_rate": 7.331222264728787e-05, "loss": 0.0422, "step": 120990 }, { "epoch": 29.06, "learning_rate": 7.330825313420237e-05, "loss": 0.047, "step": 121000 }, { "epoch": 29.06, "learning_rate": 7.330428343341231e-05, "loss": 0.0413, "step": 121010 }, { "epoch": 29.07, "learning_rate": 7.330031354494964e-05, "loss": 0.0478, "step": 121020 }, { "epoch": 29.07, "learning_rate": 7.329634346884631e-05, "loss": 0.0345, "step": 121030 }, { "epoch": 29.07, "learning_rate": 7.329237320513433e-05, "loss": 0.0562, "step": 121040 }, { "epoch": 29.07, "learning_rate": 7.328840275384565e-05, "loss": 0.0234, "step": 121050 }, { "epoch": 29.08, "learning_rate": 7.328443211501224e-05, "loss": 0.0307, "step": 121060 }, { "epoch": 29.08, "learning_rate": 7.328046128866608e-05, "loss": 0.0484, "step": 121070 }, { "epoch": 29.08, "learning_rate": 7.327649027483914e-05, "loss": 0.0584, "step": 121080 }, { "epoch": 29.08, "learning_rate": 7.327251907356344e-05, "loss": 0.0384, "step": 121090 }, { "epoch": 29.09, "learning_rate": 7.32685476848709e-05, "loss": 0.0395, "step": 121100 }, { "epoch": 29.09, "learning_rate": 7.326457610879357e-05, "loss": 0.0348, "step": 121110 }, { "epoch": 29.09, "learning_rate": 7.326060434536337e-05, "loss": 0.045, "step": 121120 }, { "epoch": 29.09, "learning_rate": 7.325663239461231e-05, "loss": 0.0266, "step": 121130 }, { "epoch": 29.09, "learning_rate": 7.325266025657241e-05, "loss": 0.0524, "step": 121140 }, { "epoch": 29.1, "learning_rate": 7.324868793127558e-05, "loss": 0.0487, "step": 121150 }, { "epoch": 29.1, "learning_rate": 7.32447154187539e-05, "loss": 0.0271, "step": 121160 }, { "epoch": 29.1, "learning_rate": 7.324074271903928e-05, "loss": 0.0317, "step": 121170 }, { "epoch": 29.1, "learning_rate": 7.323676983216377e-05, "loss": 0.0594, "step": 121180 }, { "epoch": 29.11, "learning_rate": 7.323279675815935e-05, "loss": 0.0384, "step": 121190 }, { "epoch": 29.11, "learning_rate": 7.322882349705799e-05, "loss": 0.0551, "step": 121200 }, { "epoch": 29.11, "learning_rate": 7.322485004889173e-05, "loss": 0.0314, "step": 121210 }, { "epoch": 29.11, "learning_rate": 7.322087641369253e-05, "loss": 0.0387, "step": 121220 }, { "epoch": 29.11, "learning_rate": 7.321690259149242e-05, "loss": 0.0329, "step": 121230 }, { "epoch": 29.12, "learning_rate": 7.321292858232337e-05, "loss": 0.0493, "step": 121240 }, { "epoch": 29.12, "learning_rate": 7.320895438621742e-05, "loss": 0.0384, "step": 121250 }, { "epoch": 29.12, "learning_rate": 7.320498000320654e-05, "loss": 0.0436, "step": 121260 }, { "epoch": 29.12, "learning_rate": 7.320100543332276e-05, "loss": 0.0433, "step": 121270 }, { "epoch": 29.13, "learning_rate": 7.319703067659809e-05, "loss": 0.023, "step": 121280 }, { "epoch": 29.13, "learning_rate": 7.319305573306451e-05, "loss": 0.0698, "step": 121290 }, { "epoch": 29.13, "learning_rate": 7.318908060275407e-05, "loss": 0.0432, "step": 121300 }, { "epoch": 29.13, "learning_rate": 7.318510528569875e-05, "loss": 0.0478, "step": 121310 }, { "epoch": 29.14, "learning_rate": 7.318112978193058e-05, "loss": 0.0434, "step": 121320 }, { "epoch": 29.14, "learning_rate": 7.317715409148157e-05, "loss": 0.0418, "step": 121330 }, { "epoch": 29.14, "learning_rate": 7.317317821438373e-05, "loss": 0.0403, "step": 121340 }, { "epoch": 29.14, "learning_rate": 7.316920215066912e-05, "loss": 0.0221, "step": 121350 }, { "epoch": 29.14, "learning_rate": 7.316522590036968e-05, "loss": 0.0454, "step": 121360 }, { "epoch": 29.15, "learning_rate": 7.31612494635175e-05, "loss": 0.0452, "step": 121370 }, { "epoch": 29.15, "learning_rate": 7.315727284014459e-05, "loss": 0.0292, "step": 121380 }, { "epoch": 29.15, "learning_rate": 7.315329603028295e-05, "loss": 0.0699, "step": 121390 }, { "epoch": 29.15, "learning_rate": 7.314931903396463e-05, "loss": 0.0348, "step": 121400 }, { "epoch": 29.16, "learning_rate": 7.314534185122162e-05, "loss": 0.0404, "step": 121410 }, { "epoch": 29.16, "learning_rate": 7.314136448208602e-05, "loss": 0.036, "step": 121420 }, { "epoch": 29.16, "learning_rate": 7.31373869265898e-05, "loss": 0.0743, "step": 121430 }, { "epoch": 29.16, "learning_rate": 7.3133409184765e-05, "loss": 0.0257, "step": 121440 }, { "epoch": 29.17, "learning_rate": 7.312943125664366e-05, "loss": 0.0487, "step": 121450 }, { "epoch": 29.17, "learning_rate": 7.312545314225782e-05, "loss": 0.0241, "step": 121460 }, { "epoch": 29.17, "learning_rate": 7.312147484163954e-05, "loss": 0.0268, "step": 121470 }, { "epoch": 29.17, "learning_rate": 7.31174963548208e-05, "loss": 0.0376, "step": 121480 }, { "epoch": 29.17, "learning_rate": 7.311351768183368e-05, "loss": 0.0389, "step": 121490 }, { "epoch": 29.18, "learning_rate": 7.31095388227102e-05, "loss": 0.0606, "step": 121500 }, { "epoch": 29.18, "learning_rate": 7.310555977748242e-05, "loss": 0.0468, "step": 121510 }, { "epoch": 29.18, "learning_rate": 7.310158054618239e-05, "loss": 0.0414, "step": 121520 }, { "epoch": 29.18, "learning_rate": 7.309760112884212e-05, "loss": 0.0356, "step": 121530 }, { "epoch": 29.19, "learning_rate": 7.309362152549371e-05, "loss": 0.0531, "step": 121540 }, { "epoch": 29.19, "learning_rate": 7.308964173616915e-05, "loss": 0.0365, "step": 121550 }, { "epoch": 29.19, "learning_rate": 7.308566176090052e-05, "loss": 0.0352, "step": 121560 }, { "epoch": 29.19, "learning_rate": 7.308168159971989e-05, "loss": 0.0339, "step": 121570 }, { "epoch": 29.19, "learning_rate": 7.307770125265927e-05, "loss": 0.0524, "step": 121580 }, { "epoch": 29.2, "learning_rate": 7.307372071975075e-05, "loss": 0.0408, "step": 121590 }, { "epoch": 29.2, "learning_rate": 7.306974000102636e-05, "loss": 0.06, "step": 121600 }, { "epoch": 29.2, "learning_rate": 7.306575909651817e-05, "loss": 0.0353, "step": 121610 }, { "epoch": 29.2, "learning_rate": 7.306177800625824e-05, "loss": 0.0707, "step": 121620 }, { "epoch": 29.21, "learning_rate": 7.305779673027864e-05, "loss": 0.0364, "step": 121630 }, { "epoch": 29.21, "learning_rate": 7.30538152686114e-05, "loss": 0.0276, "step": 121640 }, { "epoch": 29.21, "learning_rate": 7.304983362128861e-05, "loss": 0.0378, "step": 121650 }, { "epoch": 29.21, "learning_rate": 7.304585178834234e-05, "loss": 0.0653, "step": 121660 }, { "epoch": 29.22, "learning_rate": 7.304186976980462e-05, "loss": 0.0468, "step": 121670 }, { "epoch": 29.22, "learning_rate": 7.303788756570755e-05, "loss": 0.0301, "step": 121680 }, { "epoch": 29.22, "learning_rate": 7.303390517608321e-05, "loss": 0.0376, "step": 121690 }, { "epoch": 29.22, "learning_rate": 7.302992260096363e-05, "loss": 0.0288, "step": 121700 }, { "epoch": 29.22, "learning_rate": 7.302593984038091e-05, "loss": 0.0445, "step": 121710 }, { "epoch": 29.23, "learning_rate": 7.302195689436713e-05, "loss": 0.0282, "step": 121720 }, { "epoch": 29.23, "learning_rate": 7.301797376295433e-05, "loss": 0.0406, "step": 121730 }, { "epoch": 29.23, "learning_rate": 7.301399044617462e-05, "loss": 0.0481, "step": 121740 }, { "epoch": 29.23, "learning_rate": 7.301000694406007e-05, "loss": 0.0396, "step": 121750 }, { "epoch": 29.24, "learning_rate": 7.300602325664276e-05, "loss": 0.0431, "step": 121760 }, { "epoch": 29.24, "learning_rate": 7.300203938395476e-05, "loss": 0.0376, "step": 121770 }, { "epoch": 29.24, "learning_rate": 7.299805532602816e-05, "loss": 0.0333, "step": 121780 }, { "epoch": 29.24, "learning_rate": 7.299407108289505e-05, "loss": 0.0414, "step": 121790 }, { "epoch": 29.25, "learning_rate": 7.299008665458751e-05, "loss": 0.057, "step": 121800 }, { "epoch": 29.25, "learning_rate": 7.298610204113763e-05, "loss": 0.0459, "step": 121810 }, { "epoch": 29.25, "learning_rate": 7.298211724257749e-05, "loss": 0.0536, "step": 121820 }, { "epoch": 29.25, "learning_rate": 7.29781322589392e-05, "loss": 0.0267, "step": 121830 }, { "epoch": 29.25, "learning_rate": 7.297414709025484e-05, "loss": 0.0386, "step": 121840 }, { "epoch": 29.26, "learning_rate": 7.29701617365565e-05, "loss": 0.0419, "step": 121850 }, { "epoch": 29.26, "learning_rate": 7.296617619787625e-05, "loss": 0.0254, "step": 121860 }, { "epoch": 29.26, "learning_rate": 7.296219047424624e-05, "loss": 0.0578, "step": 121870 }, { "epoch": 29.26, "learning_rate": 7.295820456569853e-05, "loss": 0.0379, "step": 121880 }, { "epoch": 29.27, "learning_rate": 7.295421847226523e-05, "loss": 0.0591, "step": 121890 }, { "epoch": 29.27, "learning_rate": 7.295023219397845e-05, "loss": 0.0314, "step": 121900 }, { "epoch": 29.27, "learning_rate": 7.294624573087028e-05, "loss": 0.0457, "step": 121910 }, { "epoch": 29.27, "learning_rate": 7.29422590829728e-05, "loss": 0.0323, "step": 121920 }, { "epoch": 29.27, "learning_rate": 7.293827225031817e-05, "loss": 0.0291, "step": 121930 }, { "epoch": 29.28, "learning_rate": 7.293428523293845e-05, "loss": 0.0367, "step": 121940 }, { "epoch": 29.28, "learning_rate": 7.293029803086577e-05, "loss": 0.045, "step": 121950 }, { "epoch": 29.28, "learning_rate": 7.292631064413223e-05, "loss": 0.0496, "step": 121960 }, { "epoch": 29.28, "learning_rate": 7.292232307276996e-05, "loss": 0.0435, "step": 121970 }, { "epoch": 29.29, "learning_rate": 7.291833531681104e-05, "loss": 0.0315, "step": 121980 }, { "epoch": 29.29, "learning_rate": 7.29143473762876e-05, "loss": 0.0278, "step": 121990 }, { "epoch": 29.29, "learning_rate": 7.291035925123177e-05, "loss": 0.047, "step": 122000 }, { "epoch": 29.29, "learning_rate": 7.290637094167565e-05, "loss": 0.0436, "step": 122010 }, { "epoch": 29.3, "learning_rate": 7.290238244765138e-05, "loss": 0.05, "step": 122020 }, { "epoch": 29.3, "learning_rate": 7.289839376919103e-05, "loss": 0.0537, "step": 122030 }, { "epoch": 29.3, "learning_rate": 7.289440490632677e-05, "loss": 0.0314, "step": 122040 }, { "epoch": 29.3, "learning_rate": 7.289041585909071e-05, "loss": 0.0392, "step": 122050 }, { "epoch": 29.3, "learning_rate": 7.288642662751497e-05, "loss": 0.0415, "step": 122060 }, { "epoch": 29.31, "learning_rate": 7.288243721163166e-05, "loss": 0.0291, "step": 122070 }, { "epoch": 29.31, "learning_rate": 7.287844761147293e-05, "loss": 0.0304, "step": 122080 }, { "epoch": 29.31, "learning_rate": 7.287445782707091e-05, "loss": 0.0397, "step": 122090 }, { "epoch": 29.31, "learning_rate": 7.287046785845773e-05, "loss": 0.0602, "step": 122100 }, { "epoch": 29.32, "learning_rate": 7.28664777056655e-05, "loss": 0.0387, "step": 122110 }, { "epoch": 29.32, "learning_rate": 7.286248736872637e-05, "loss": 0.0341, "step": 122120 }, { "epoch": 29.32, "learning_rate": 7.285849684767249e-05, "loss": 0.0347, "step": 122130 }, { "epoch": 29.32, "learning_rate": 7.285450614253595e-05, "loss": 0.033, "step": 122140 }, { "epoch": 29.33, "learning_rate": 7.285051525334895e-05, "loss": 0.0351, "step": 122150 }, { "epoch": 29.33, "learning_rate": 7.284652418014357e-05, "loss": 0.03, "step": 122160 }, { "epoch": 29.33, "learning_rate": 7.2842532922952e-05, "loss": 0.0409, "step": 122170 }, { "epoch": 29.33, "learning_rate": 7.283854148180633e-05, "loss": 0.0341, "step": 122180 }, { "epoch": 29.33, "learning_rate": 7.283454985673875e-05, "loss": 0.0403, "step": 122190 }, { "epoch": 29.34, "learning_rate": 7.283055804778138e-05, "loss": 0.0324, "step": 122200 }, { "epoch": 29.34, "learning_rate": 7.282656605496638e-05, "loss": 0.0564, "step": 122210 }, { "epoch": 29.34, "learning_rate": 7.28225738783259e-05, "loss": 0.0294, "step": 122220 }, { "epoch": 29.34, "learning_rate": 7.281858151789207e-05, "loss": 0.0386, "step": 122230 }, { "epoch": 29.35, "learning_rate": 7.281458897369707e-05, "loss": 0.025, "step": 122240 }, { "epoch": 29.35, "learning_rate": 7.2810596245773e-05, "loss": 0.0326, "step": 122250 }, { "epoch": 29.35, "learning_rate": 7.280660333415208e-05, "loss": 0.0255, "step": 122260 }, { "epoch": 29.35, "learning_rate": 7.280261023886642e-05, "loss": 0.0621, "step": 122270 }, { "epoch": 29.35, "learning_rate": 7.279861695994821e-05, "loss": 0.0374, "step": 122280 }, { "epoch": 29.36, "learning_rate": 7.279462349742957e-05, "loss": 0.0369, "step": 122290 }, { "epoch": 29.36, "learning_rate": 7.279062985134267e-05, "loss": 0.0259, "step": 122300 }, { "epoch": 29.36, "learning_rate": 7.278663602171971e-05, "loss": 0.0336, "step": 122310 }, { "epoch": 29.36, "learning_rate": 7.278264200859281e-05, "loss": 0.0591, "step": 122320 }, { "epoch": 29.37, "learning_rate": 7.277864781199415e-05, "loss": 0.0397, "step": 122330 }, { "epoch": 29.37, "learning_rate": 7.27746534319559e-05, "loss": 0.0492, "step": 122340 }, { "epoch": 29.37, "learning_rate": 7.27706588685102e-05, "loss": 0.0312, "step": 122350 }, { "epoch": 29.37, "learning_rate": 7.276666412168927e-05, "loss": 0.0301, "step": 122360 }, { "epoch": 29.38, "learning_rate": 7.276266919152524e-05, "loss": 0.0416, "step": 122370 }, { "epoch": 29.38, "learning_rate": 7.275867407805029e-05, "loss": 0.0508, "step": 122380 }, { "epoch": 29.38, "learning_rate": 7.27546787812966e-05, "loss": 0.0278, "step": 122390 }, { "epoch": 29.38, "learning_rate": 7.275068330129633e-05, "loss": 0.032, "step": 122400 }, { "epoch": 29.38, "learning_rate": 7.274668763808167e-05, "loss": 0.0247, "step": 122410 }, { "epoch": 29.39, "learning_rate": 7.27426917916848e-05, "loss": 0.0628, "step": 122420 }, { "epoch": 29.39, "learning_rate": 7.273869576213789e-05, "loss": 0.0536, "step": 122430 }, { "epoch": 29.39, "learning_rate": 7.273469954947312e-05, "loss": 0.0726, "step": 122440 }, { "epoch": 29.39, "learning_rate": 7.273070315372268e-05, "loss": 0.0279, "step": 122450 }, { "epoch": 29.4, "learning_rate": 7.272670657491874e-05, "loss": 0.0266, "step": 122460 }, { "epoch": 29.4, "learning_rate": 7.27227098130935e-05, "loss": 0.0472, "step": 122470 }, { "epoch": 29.4, "learning_rate": 7.271871286827915e-05, "loss": 0.0252, "step": 122480 }, { "epoch": 29.4, "learning_rate": 7.271471574050787e-05, "loss": 0.0259, "step": 122490 }, { "epoch": 29.41, "learning_rate": 7.271071842981186e-05, "loss": 0.0498, "step": 122500 }, { "epoch": 29.41, "learning_rate": 7.270672093622325e-05, "loss": 0.0303, "step": 122510 }, { "epoch": 29.41, "learning_rate": 7.270272325977432e-05, "loss": 0.0313, "step": 122520 }, { "epoch": 29.41, "learning_rate": 7.269872540049723e-05, "loss": 0.0399, "step": 122530 }, { "epoch": 29.41, "learning_rate": 7.269472735842413e-05, "loss": 0.0411, "step": 122540 }, { "epoch": 29.42, "learning_rate": 7.26907291335873e-05, "loss": 0.0648, "step": 122550 }, { "epoch": 29.42, "learning_rate": 7.268673072601888e-05, "loss": 0.0504, "step": 122560 }, { "epoch": 29.42, "learning_rate": 7.268273213575109e-05, "loss": 0.0653, "step": 122570 }, { "epoch": 29.42, "learning_rate": 7.267873336281612e-05, "loss": 0.0297, "step": 122580 }, { "epoch": 29.43, "learning_rate": 7.267473440724617e-05, "loss": 0.0338, "step": 122590 }, { "epoch": 29.43, "learning_rate": 7.267073526907347e-05, "loss": 0.0324, "step": 122600 }, { "epoch": 29.43, "learning_rate": 7.26667359483302e-05, "loss": 0.0381, "step": 122610 }, { "epoch": 29.43, "learning_rate": 7.26627364450486e-05, "loss": 0.0428, "step": 122620 }, { "epoch": 29.43, "learning_rate": 7.265873675926081e-05, "loss": 0.0348, "step": 122630 }, { "epoch": 29.44, "learning_rate": 7.265473689099912e-05, "loss": 0.0358, "step": 122640 }, { "epoch": 29.44, "learning_rate": 7.265073684029569e-05, "loss": 0.0413, "step": 122650 }, { "epoch": 29.44, "learning_rate": 7.264673660718276e-05, "loss": 0.0412, "step": 122660 }, { "epoch": 29.44, "learning_rate": 7.264273619169253e-05, "loss": 0.0358, "step": 122670 }, { "epoch": 29.45, "learning_rate": 7.263873559385721e-05, "loss": 0.0341, "step": 122680 }, { "epoch": 29.45, "learning_rate": 7.263473481370904e-05, "loss": 0.0429, "step": 122690 }, { "epoch": 29.45, "learning_rate": 7.263073385128021e-05, "loss": 0.0468, "step": 122700 }, { "epoch": 29.45, "learning_rate": 7.262673270660297e-05, "loss": 0.0702, "step": 122710 }, { "epoch": 29.46, "learning_rate": 7.262273137970953e-05, "loss": 0.0422, "step": 122720 }, { "epoch": 29.46, "learning_rate": 7.26187298706321e-05, "loss": 0.038, "step": 122730 }, { "epoch": 29.46, "learning_rate": 7.261472817940292e-05, "loss": 0.0325, "step": 122740 }, { "epoch": 29.46, "learning_rate": 7.261072630605421e-05, "loss": 0.044, "step": 122750 }, { "epoch": 29.46, "learning_rate": 7.26067242506182e-05, "loss": 0.0371, "step": 122760 }, { "epoch": 29.47, "learning_rate": 7.260272201312712e-05, "loss": 0.0344, "step": 122770 }, { "epoch": 29.47, "learning_rate": 7.25987195936132e-05, "loss": 0.0579, "step": 122780 }, { "epoch": 29.47, "learning_rate": 7.259471699210867e-05, "loss": 0.0478, "step": 122790 }, { "epoch": 29.47, "learning_rate": 7.259071420864576e-05, "loss": 0.0462, "step": 122800 }, { "epoch": 29.48, "learning_rate": 7.258671124325673e-05, "loss": 0.0542, "step": 122810 }, { "epoch": 29.48, "learning_rate": 7.258270809597376e-05, "loss": 0.0419, "step": 122820 }, { "epoch": 29.48, "learning_rate": 7.257870476682915e-05, "loss": 0.0264, "step": 122830 }, { "epoch": 29.48, "learning_rate": 7.257470125585512e-05, "loss": 0.0453, "step": 122840 }, { "epoch": 29.49, "learning_rate": 7.257069756308388e-05, "loss": 0.0372, "step": 122850 }, { "epoch": 29.49, "learning_rate": 7.256669368854772e-05, "loss": 0.0216, "step": 122860 }, { "epoch": 29.49, "learning_rate": 7.256268963227884e-05, "loss": 0.0378, "step": 122870 }, { "epoch": 29.49, "learning_rate": 7.255868539430951e-05, "loss": 0.0681, "step": 122880 }, { "epoch": 29.49, "learning_rate": 7.255468097467198e-05, "loss": 0.0509, "step": 122890 }, { "epoch": 29.5, "learning_rate": 7.255067637339848e-05, "loss": 0.0436, "step": 122900 }, { "epoch": 29.5, "learning_rate": 7.254667159052129e-05, "loss": 0.0479, "step": 122910 }, { "epoch": 29.5, "learning_rate": 7.25426666260726e-05, "loss": 0.0272, "step": 122920 }, { "epoch": 29.5, "learning_rate": 7.253866148008475e-05, "loss": 0.0468, "step": 122930 }, { "epoch": 29.51, "learning_rate": 7.253465615258992e-05, "loss": 0.0238, "step": 122940 }, { "epoch": 29.51, "learning_rate": 7.253065064362041e-05, "loss": 0.0365, "step": 122950 }, { "epoch": 29.51, "learning_rate": 7.252664495320845e-05, "loss": 0.0301, "step": 122960 }, { "epoch": 29.51, "learning_rate": 7.252263908138632e-05, "loss": 0.0467, "step": 122970 }, { "epoch": 29.51, "learning_rate": 7.251863302818624e-05, "loss": 0.0582, "step": 122980 }, { "epoch": 29.52, "learning_rate": 7.251462679364051e-05, "loss": 0.0142, "step": 122990 }, { "epoch": 29.52, "learning_rate": 7.25106203777814e-05, "loss": 0.0385, "step": 123000 }, { "epoch": 29.52, "learning_rate": 7.250661378064114e-05, "loss": 0.0522, "step": 123010 }, { "epoch": 29.52, "learning_rate": 7.250260700225202e-05, "loss": 0.0424, "step": 123020 }, { "epoch": 29.53, "learning_rate": 7.24986000426463e-05, "loss": 0.0589, "step": 123030 }, { "epoch": 29.53, "learning_rate": 7.249459290185623e-05, "loss": 0.0379, "step": 123040 }, { "epoch": 29.53, "learning_rate": 7.249058557991413e-05, "loss": 0.0546, "step": 123050 }, { "epoch": 29.53, "learning_rate": 7.248657807685221e-05, "loss": 0.0666, "step": 123060 }, { "epoch": 29.54, "learning_rate": 7.248257039270278e-05, "loss": 0.0476, "step": 123070 }, { "epoch": 29.54, "learning_rate": 7.247856252749811e-05, "loss": 0.0444, "step": 123080 }, { "epoch": 29.54, "learning_rate": 7.247455448127048e-05, "loss": 0.0719, "step": 123090 }, { "epoch": 29.54, "learning_rate": 7.247054625405215e-05, "loss": 0.0362, "step": 123100 }, { "epoch": 29.54, "learning_rate": 7.24665378458754e-05, "loss": 0.0682, "step": 123110 }, { "epoch": 29.55, "learning_rate": 7.246252925677252e-05, "loss": 0.0409, "step": 123120 }, { "epoch": 29.55, "learning_rate": 7.245852048677582e-05, "loss": 0.0692, "step": 123130 }, { "epoch": 29.55, "learning_rate": 7.245451153591754e-05, "loss": 0.0386, "step": 123140 }, { "epoch": 29.55, "learning_rate": 7.245050240422997e-05, "loss": 0.0707, "step": 123150 }, { "epoch": 29.56, "learning_rate": 7.24464930917454e-05, "loss": 0.0442, "step": 123160 }, { "epoch": 29.56, "learning_rate": 7.244248359849614e-05, "loss": 0.0476, "step": 123170 }, { "epoch": 29.56, "learning_rate": 7.243847392451443e-05, "loss": 0.0643, "step": 123180 }, { "epoch": 29.56, "learning_rate": 7.243446406983263e-05, "loss": 0.0579, "step": 123190 }, { "epoch": 29.57, "learning_rate": 7.243045403448298e-05, "loss": 0.0293, "step": 123200 }, { "epoch": 29.57, "learning_rate": 7.242644381849778e-05, "loss": 0.0398, "step": 123210 }, { "epoch": 29.57, "learning_rate": 7.242243342190933e-05, "loss": 0.067, "step": 123220 }, { "epoch": 29.57, "learning_rate": 7.241842284474993e-05, "loss": 0.0432, "step": 123230 }, { "epoch": 29.57, "learning_rate": 7.241441208705189e-05, "loss": 0.0536, "step": 123240 }, { "epoch": 29.58, "learning_rate": 7.241040114884748e-05, "loss": 0.0607, "step": 123250 }, { "epoch": 29.58, "learning_rate": 7.240639003016901e-05, "loss": 0.0657, "step": 123260 }, { "epoch": 29.58, "learning_rate": 7.24023787310488e-05, "loss": 0.0376, "step": 123270 }, { "epoch": 29.58, "learning_rate": 7.239836725151913e-05, "loss": 0.052, "step": 123280 }, { "epoch": 29.59, "learning_rate": 7.239435559161233e-05, "loss": 0.0613, "step": 123290 }, { "epoch": 29.59, "learning_rate": 7.23903437513607e-05, "loss": 0.0483, "step": 123300 }, { "epoch": 29.59, "learning_rate": 7.238633173079651e-05, "loss": 0.04, "step": 123310 }, { "epoch": 29.59, "learning_rate": 7.238231952995213e-05, "loss": 0.0426, "step": 123320 }, { "epoch": 29.59, "learning_rate": 7.237830714885983e-05, "loss": 0.0364, "step": 123330 }, { "epoch": 29.6, "learning_rate": 7.237429458755193e-05, "loss": 0.0363, "step": 123340 }, { "epoch": 29.6, "learning_rate": 7.237028184606075e-05, "loss": 0.0436, "step": 123350 }, { "epoch": 29.6, "learning_rate": 7.23662689244186e-05, "loss": 0.046, "step": 123360 }, { "epoch": 29.6, "learning_rate": 7.236225582265781e-05, "loss": 0.056, "step": 123370 }, { "epoch": 29.61, "learning_rate": 7.235824254081066e-05, "loss": 0.0594, "step": 123380 }, { "epoch": 29.61, "learning_rate": 7.235422907890952e-05, "loss": 0.0474, "step": 123390 }, { "epoch": 29.61, "learning_rate": 7.235021543698667e-05, "loss": 0.0395, "step": 123400 }, { "epoch": 29.61, "learning_rate": 7.234620161507446e-05, "loss": 0.0398, "step": 123410 }, { "epoch": 29.62, "learning_rate": 7.23421876132052e-05, "loss": 0.0426, "step": 123420 }, { "epoch": 29.62, "learning_rate": 7.233817343141121e-05, "loss": 0.0421, "step": 123430 }, { "epoch": 29.62, "learning_rate": 7.233415906972486e-05, "loss": 0.0361, "step": 123440 }, { "epoch": 29.62, "learning_rate": 7.23301445281784e-05, "loss": 0.0468, "step": 123450 }, { "epoch": 29.62, "learning_rate": 7.232612980680422e-05, "loss": 0.0855, "step": 123460 }, { "epoch": 29.63, "learning_rate": 7.232211490563464e-05, "loss": 0.0587, "step": 123470 }, { "epoch": 29.63, "learning_rate": 7.231809982470199e-05, "loss": 0.0629, "step": 123480 }, { "epoch": 29.63, "learning_rate": 7.231408456403859e-05, "loss": 0.0487, "step": 123490 }, { "epoch": 29.63, "learning_rate": 7.23100691236768e-05, "loss": 0.0751, "step": 123500 }, { "epoch": 29.64, "learning_rate": 7.230605350364892e-05, "loss": 0.0659, "step": 123510 }, { "epoch": 29.64, "learning_rate": 7.230203770398734e-05, "loss": 0.0523, "step": 123520 }, { "epoch": 29.64, "learning_rate": 7.229802172472435e-05, "loss": 0.0417, "step": 123530 }, { "epoch": 29.64, "learning_rate": 7.229400556589232e-05, "loss": 0.0401, "step": 123540 }, { "epoch": 29.65, "learning_rate": 7.228998922752357e-05, "loss": 0.0538, "step": 123550 }, { "epoch": 29.65, "learning_rate": 7.22859727096505e-05, "loss": 0.0789, "step": 123560 }, { "epoch": 29.65, "learning_rate": 7.228195601230538e-05, "loss": 0.0536, "step": 123570 }, { "epoch": 29.65, "learning_rate": 7.227793913552058e-05, "loss": 0.0365, "step": 123580 }, { "epoch": 29.65, "learning_rate": 7.22739220793285e-05, "loss": 0.0531, "step": 123590 }, { "epoch": 29.66, "learning_rate": 7.226990484376144e-05, "loss": 0.0702, "step": 123600 }, { "epoch": 29.66, "learning_rate": 7.226588742885174e-05, "loss": 0.0573, "step": 123610 }, { "epoch": 29.66, "learning_rate": 7.226186983463179e-05, "loss": 0.0379, "step": 123620 }, { "epoch": 29.66, "learning_rate": 7.225785206113394e-05, "loss": 0.0313, "step": 123630 }, { "epoch": 29.67, "learning_rate": 7.225383410839051e-05, "loss": 0.0345, "step": 123640 }, { "epoch": 29.67, "learning_rate": 7.22498159764339e-05, "loss": 0.0425, "step": 123650 }, { "epoch": 29.67, "learning_rate": 7.224579766529644e-05, "loss": 0.0467, "step": 123660 }, { "epoch": 29.67, "learning_rate": 7.22417791750105e-05, "loss": 0.052, "step": 123670 }, { "epoch": 29.67, "learning_rate": 7.223776050560845e-05, "loss": 0.046, "step": 123680 }, { "epoch": 29.68, "learning_rate": 7.223374165712264e-05, "loss": 0.058, "step": 123690 }, { "epoch": 29.68, "learning_rate": 7.222972262958545e-05, "loss": 0.0253, "step": 123700 }, { "epoch": 29.68, "learning_rate": 7.222570342302921e-05, "loss": 0.0509, "step": 123710 }, { "epoch": 29.68, "learning_rate": 7.222168403748632e-05, "loss": 0.0313, "step": 123720 }, { "epoch": 29.69, "learning_rate": 7.221766447298914e-05, "loss": 0.0418, "step": 123730 }, { "epoch": 29.69, "learning_rate": 7.221364472957005e-05, "loss": 0.0231, "step": 123740 }, { "epoch": 29.69, "learning_rate": 7.220962480726142e-05, "loss": 0.0502, "step": 123750 }, { "epoch": 29.69, "learning_rate": 7.220560470609559e-05, "loss": 0.0454, "step": 123760 }, { "epoch": 29.7, "learning_rate": 7.220158442610497e-05, "loss": 0.0345, "step": 123770 }, { "epoch": 29.7, "learning_rate": 7.219756396732194e-05, "loss": 0.0578, "step": 123780 }, { "epoch": 29.7, "learning_rate": 7.219354332977885e-05, "loss": 0.0438, "step": 123790 }, { "epoch": 29.7, "learning_rate": 7.21895225135081e-05, "loss": 0.0305, "step": 123800 }, { "epoch": 29.7, "learning_rate": 7.218550151854204e-05, "loss": 0.0418, "step": 123810 }, { "epoch": 29.71, "learning_rate": 7.21814803449131e-05, "loss": 0.0587, "step": 123820 }, { "epoch": 29.71, "learning_rate": 7.217745899265363e-05, "loss": 0.0429, "step": 123830 }, { "epoch": 29.71, "learning_rate": 7.217343746179601e-05, "loss": 0.0388, "step": 123840 }, { "epoch": 29.71, "learning_rate": 7.216941575237264e-05, "loss": 0.0367, "step": 123850 }, { "epoch": 29.72, "learning_rate": 7.216539386441589e-05, "loss": 0.0594, "step": 123860 }, { "epoch": 29.72, "learning_rate": 7.21613717979582e-05, "loss": 0.0513, "step": 123870 }, { "epoch": 29.72, "learning_rate": 7.21573495530319e-05, "loss": 0.0401, "step": 123880 }, { "epoch": 29.72, "learning_rate": 7.215332712966941e-05, "loss": 0.0471, "step": 123890 }, { "epoch": 29.73, "learning_rate": 7.214930452790311e-05, "loss": 0.075, "step": 123900 }, { "epoch": 29.73, "learning_rate": 7.214528174776541e-05, "loss": 0.0503, "step": 123910 }, { "epoch": 29.73, "learning_rate": 7.21412587892887e-05, "loss": 0.0761, "step": 123920 }, { "epoch": 29.73, "learning_rate": 7.213723565250537e-05, "loss": 0.0464, "step": 123930 }, { "epoch": 29.73, "learning_rate": 7.213321233744785e-05, "loss": 0.0497, "step": 123940 }, { "epoch": 29.74, "learning_rate": 7.212918884414848e-05, "loss": 0.0474, "step": 123950 }, { "epoch": 29.74, "learning_rate": 7.21251651726397e-05, "loss": 0.0414, "step": 123960 }, { "epoch": 29.74, "learning_rate": 7.212114132295393e-05, "loss": 0.0336, "step": 123970 }, { "epoch": 29.74, "learning_rate": 7.211711729512354e-05, "loss": 0.0464, "step": 123980 }, { "epoch": 29.75, "learning_rate": 7.211309308918097e-05, "loss": 0.0449, "step": 123990 }, { "epoch": 29.75, "learning_rate": 7.210906870515858e-05, "loss": 0.0446, "step": 124000 }, { "epoch": 29.75, "learning_rate": 7.210504414308884e-05, "loss": 0.0525, "step": 124010 }, { "epoch": 29.75, "learning_rate": 7.210101940300411e-05, "loss": 0.0372, "step": 124020 }, { "epoch": 29.75, "learning_rate": 7.209699448493682e-05, "loss": 0.0557, "step": 124030 }, { "epoch": 29.76, "learning_rate": 7.209296938891938e-05, "loss": 0.0334, "step": 124040 }, { "epoch": 29.76, "learning_rate": 7.208894411498421e-05, "loss": 0.0589, "step": 124050 }, { "epoch": 29.76, "learning_rate": 7.208491866316374e-05, "loss": 0.0731, "step": 124060 }, { "epoch": 29.76, "learning_rate": 7.208089303349034e-05, "loss": 0.0432, "step": 124070 }, { "epoch": 29.77, "learning_rate": 7.207686722599647e-05, "loss": 0.0494, "step": 124080 }, { "epoch": 29.77, "learning_rate": 7.207284124071455e-05, "loss": 0.0199, "step": 124090 }, { "epoch": 29.77, "learning_rate": 7.206881507767697e-05, "loss": 0.0735, "step": 124100 }, { "epoch": 29.77, "learning_rate": 7.206478873691623e-05, "loss": 0.0366, "step": 124110 }, { "epoch": 29.78, "learning_rate": 7.206076221846464e-05, "loss": 0.0379, "step": 124120 }, { "epoch": 29.78, "learning_rate": 7.205673552235472e-05, "loss": 0.0502, "step": 124130 }, { "epoch": 29.78, "learning_rate": 7.205270864861885e-05, "loss": 0.0504, "step": 124140 }, { "epoch": 29.78, "learning_rate": 7.204868159728949e-05, "loss": 0.0422, "step": 124150 }, { "epoch": 29.78, "learning_rate": 7.204465436839903e-05, "loss": 0.0364, "step": 124160 }, { "epoch": 29.79, "learning_rate": 7.204062696197991e-05, "loss": 0.0479, "step": 124170 }, { "epoch": 29.79, "learning_rate": 7.203659937806462e-05, "loss": 0.0492, "step": 124180 }, { "epoch": 29.79, "learning_rate": 7.203257161668554e-05, "loss": 0.0485, "step": 124190 }, { "epoch": 29.79, "learning_rate": 7.202854367787512e-05, "loss": 0.0447, "step": 124200 }, { "epoch": 29.8, "learning_rate": 7.202451556166579e-05, "loss": 0.0348, "step": 124210 }, { "epoch": 29.8, "learning_rate": 7.202048726808999e-05, "loss": 0.0248, "step": 124220 }, { "epoch": 29.8, "learning_rate": 7.201645879718018e-05, "loss": 0.0415, "step": 124230 }, { "epoch": 29.8, "learning_rate": 7.201243014896876e-05, "loss": 0.0372, "step": 124240 }, { "epoch": 29.81, "learning_rate": 7.200840132348823e-05, "loss": 0.0363, "step": 124250 }, { "epoch": 29.81, "learning_rate": 7.2004372320771e-05, "loss": 0.035, "step": 124260 }, { "epoch": 29.81, "learning_rate": 7.200034314084952e-05, "loss": 0.0434, "step": 124270 }, { "epoch": 29.81, "learning_rate": 7.199631378375623e-05, "loss": 0.04, "step": 124280 }, { "epoch": 29.81, "learning_rate": 7.19922842495236e-05, "loss": 0.0445, "step": 124290 }, { "epoch": 29.82, "learning_rate": 7.198825453818406e-05, "loss": 0.0433, "step": 124300 }, { "epoch": 29.82, "learning_rate": 7.198422464977007e-05, "loss": 0.0267, "step": 124310 }, { "epoch": 29.82, "learning_rate": 7.19801945843141e-05, "loss": 0.0323, "step": 124320 }, { "epoch": 29.82, "learning_rate": 7.197616434184858e-05, "loss": 0.04, "step": 124330 }, { "epoch": 29.83, "learning_rate": 7.197213392240596e-05, "loss": 0.0418, "step": 124340 }, { "epoch": 29.83, "learning_rate": 7.196810332601873e-05, "loss": 0.0447, "step": 124350 }, { "epoch": 29.83, "learning_rate": 7.196407255271933e-05, "loss": 0.0411, "step": 124360 }, { "epoch": 29.83, "learning_rate": 7.196004160254022e-05, "loss": 0.03, "step": 124370 }, { "epoch": 29.83, "learning_rate": 7.195601047551385e-05, "loss": 0.0381, "step": 124380 }, { "epoch": 29.84, "learning_rate": 7.19519791716727e-05, "loss": 0.0457, "step": 124390 }, { "epoch": 29.84, "learning_rate": 7.194794769104925e-05, "loss": 0.0375, "step": 124400 }, { "epoch": 29.84, "learning_rate": 7.194391603367593e-05, "loss": 0.0529, "step": 124410 }, { "epoch": 29.84, "learning_rate": 7.193988419958523e-05, "loss": 0.0354, "step": 124420 }, { "epoch": 29.85, "learning_rate": 7.19358521888096e-05, "loss": 0.0453, "step": 124430 }, { "epoch": 29.85, "learning_rate": 7.193182000138155e-05, "loss": 0.0348, "step": 124440 }, { "epoch": 29.85, "learning_rate": 7.19277876373335e-05, "loss": 0.0578, "step": 124450 }, { "epoch": 29.85, "learning_rate": 7.192375509669796e-05, "loss": 0.0339, "step": 124460 }, { "epoch": 29.86, "learning_rate": 7.19197223795074e-05, "loss": 0.0595, "step": 124470 }, { "epoch": 29.86, "learning_rate": 7.191568948579428e-05, "loss": 0.0605, "step": 124480 }, { "epoch": 29.86, "learning_rate": 7.19116564155911e-05, "loss": 0.0401, "step": 124490 }, { "epoch": 29.86, "learning_rate": 7.19076231689303e-05, "loss": 0.0464, "step": 124500 }, { "epoch": 29.86, "learning_rate": 7.190358974584441e-05, "loss": 0.0287, "step": 124510 }, { "epoch": 29.87, "learning_rate": 7.189955614636588e-05, "loss": 0.0352, "step": 124520 }, { "epoch": 29.87, "learning_rate": 7.189552237052721e-05, "loss": 0.0339, "step": 124530 }, { "epoch": 29.87, "learning_rate": 7.189148841836087e-05, "loss": 0.0333, "step": 124540 }, { "epoch": 29.87, "learning_rate": 7.188745428989933e-05, "loss": 0.0321, "step": 124550 }, { "epoch": 29.88, "learning_rate": 7.188341998517513e-05, "loss": 0.0346, "step": 124560 }, { "epoch": 29.88, "learning_rate": 7.18793855042207e-05, "loss": 0.0545, "step": 124570 }, { "epoch": 29.88, "learning_rate": 7.187535084706857e-05, "loss": 0.0329, "step": 124580 }, { "epoch": 29.88, "learning_rate": 7.187131601375124e-05, "loss": 0.0595, "step": 124590 }, { "epoch": 29.89, "learning_rate": 7.186728100430116e-05, "loss": 0.0319, "step": 124600 }, { "epoch": 29.89, "learning_rate": 7.186324581875085e-05, "loss": 0.0492, "step": 124610 }, { "epoch": 29.89, "learning_rate": 7.18592104571328e-05, "loss": 0.0386, "step": 124620 }, { "epoch": 29.89, "learning_rate": 7.185517491947953e-05, "loss": 0.0643, "step": 124630 }, { "epoch": 29.89, "learning_rate": 7.185113920582349e-05, "loss": 0.0554, "step": 124640 }, { "epoch": 29.9, "learning_rate": 7.184710331619722e-05, "loss": 0.0334, "step": 124650 }, { "epoch": 29.9, "learning_rate": 7.184306725063323e-05, "loss": 0.0294, "step": 124660 }, { "epoch": 29.9, "learning_rate": 7.183903100916399e-05, "loss": 0.0398, "step": 124670 }, { "epoch": 29.9, "learning_rate": 7.183499459182202e-05, "loss": 0.0344, "step": 124680 }, { "epoch": 29.91, "learning_rate": 7.18309579986398e-05, "loss": 0.0452, "step": 124690 }, { "epoch": 29.91, "learning_rate": 7.18269212296499e-05, "loss": 0.0424, "step": 124700 }, { "epoch": 29.91, "learning_rate": 7.182288428488476e-05, "loss": 0.0563, "step": 124710 }, { "epoch": 29.91, "learning_rate": 7.181884716437693e-05, "loss": 0.042, "step": 124720 }, { "epoch": 29.91, "learning_rate": 7.181480986815892e-05, "loss": 0.0586, "step": 124730 }, { "epoch": 29.92, "learning_rate": 7.181077239626322e-05, "loss": 0.0394, "step": 124740 }, { "epoch": 29.92, "learning_rate": 7.180673474872236e-05, "loss": 0.0564, "step": 124750 }, { "epoch": 29.92, "learning_rate": 7.180269692556886e-05, "loss": 0.0409, "step": 124760 }, { "epoch": 29.92, "learning_rate": 7.179865892683523e-05, "loss": 0.0388, "step": 124770 }, { "epoch": 29.93, "learning_rate": 7.179462075255401e-05, "loss": 0.0307, "step": 124780 }, { "epoch": 29.93, "learning_rate": 7.179058240275768e-05, "loss": 0.0269, "step": 124790 }, { "epoch": 29.93, "learning_rate": 7.178654387747879e-05, "loss": 0.0484, "step": 124800 }, { "epoch": 29.93, "learning_rate": 7.178250517674985e-05, "loss": 0.0447, "step": 124810 }, { "epoch": 29.94, "learning_rate": 7.177846630060337e-05, "loss": 0.0293, "step": 124820 }, { "epoch": 29.94, "learning_rate": 7.177442724907192e-05, "loss": 0.0454, "step": 124830 }, { "epoch": 29.94, "learning_rate": 7.1770388022188e-05, "loss": 0.0451, "step": 124840 }, { "epoch": 29.94, "learning_rate": 7.176634861998412e-05, "loss": 0.0378, "step": 124850 }, { "epoch": 29.94, "learning_rate": 7.176230904249284e-05, "loss": 0.0296, "step": 124860 }, { "epoch": 29.95, "learning_rate": 7.17582692897467e-05, "loss": 0.0391, "step": 124870 }, { "epoch": 29.95, "learning_rate": 7.175422936177819e-05, "loss": 0.0388, "step": 124880 }, { "epoch": 29.95, "learning_rate": 7.175018925861987e-05, "loss": 0.0368, "step": 124890 }, { "epoch": 30.0, "learning_rate": 7.174614898030428e-05, "loss": 0.0383, "step": 124900 }, { "epoch": 30.0, "learning_rate": 7.174210852686393e-05, "loss": 0.0412, "step": 124910 }, { "epoch": 30.01, "learning_rate": 7.17380678983314e-05, "loss": 0.0369, "step": 124920 }, { "epoch": 30.01, "learning_rate": 7.173402709473921e-05, "loss": 0.0603, "step": 124930 }, { "epoch": 30.01, "learning_rate": 7.172998611611989e-05, "loss": 0.0343, "step": 124940 }, { "epoch": 30.01, "learning_rate": 7.1725944962506e-05, "loss": 0.0429, "step": 124950 }, { "epoch": 30.02, "learning_rate": 7.172190363393007e-05, "loss": 0.0482, "step": 124960 }, { "epoch": 30.02, "learning_rate": 7.171786213042465e-05, "loss": 0.0301, "step": 124970 }, { "epoch": 30.02, "learning_rate": 7.171382045202229e-05, "loss": 0.0306, "step": 124980 }, { "epoch": 30.02, "learning_rate": 7.170977859875554e-05, "loss": 0.0398, "step": 124990 }, { "epoch": 30.03, "learning_rate": 7.170573657065693e-05, "loss": 0.0628, "step": 125000 }, { "epoch": 30.03, "learning_rate": 7.170169436775905e-05, "loss": 0.0582, "step": 125010 }, { "epoch": 30.03, "learning_rate": 7.16976519900944e-05, "loss": 0.0397, "step": 125020 }, { "epoch": 30.03, "learning_rate": 7.169360943769559e-05, "loss": 0.0325, "step": 125030 }, { "epoch": 30.03, "learning_rate": 7.168956671059513e-05, "loss": 0.028, "step": 125040 }, { "epoch": 30.04, "learning_rate": 7.168552380882561e-05, "loss": 0.0603, "step": 125050 }, { "epoch": 30.04, "learning_rate": 7.168148073241956e-05, "loss": 0.0374, "step": 125060 }, { "epoch": 30.04, "learning_rate": 7.167743748140958e-05, "loss": 0.0246, "step": 125070 }, { "epoch": 30.04, "learning_rate": 7.167339405582816e-05, "loss": 0.0288, "step": 125080 }, { "epoch": 30.05, "learning_rate": 7.166935045570793e-05, "loss": 0.0347, "step": 125090 }, { "epoch": 30.05, "learning_rate": 7.166530668108142e-05, "loss": 0.0373, "step": 125100 }, { "epoch": 30.05, "learning_rate": 7.166126273198122e-05, "loss": 0.0431, "step": 125110 }, { "epoch": 30.05, "learning_rate": 7.165721860843987e-05, "loss": 0.0355, "step": 125120 }, { "epoch": 30.05, "learning_rate": 7.165317431048995e-05, "loss": 0.0504, "step": 125130 }, { "epoch": 30.06, "learning_rate": 7.164912983816403e-05, "loss": 0.0379, "step": 125140 }, { "epoch": 30.06, "learning_rate": 7.164508519149467e-05, "loss": 0.0427, "step": 125150 }, { "epoch": 30.06, "learning_rate": 7.164104037051445e-05, "loss": 0.0634, "step": 125160 }, { "epoch": 30.06, "learning_rate": 7.163699537525595e-05, "loss": 0.0298, "step": 125170 }, { "epoch": 30.07, "learning_rate": 7.163295020575175e-05, "loss": 0.0322, "step": 125180 }, { "epoch": 30.07, "learning_rate": 7.162890486203441e-05, "loss": 0.0348, "step": 125190 }, { "epoch": 30.07, "learning_rate": 7.162485934413649e-05, "loss": 0.0377, "step": 125200 }, { "epoch": 30.07, "learning_rate": 7.162081365209062e-05, "loss": 0.038, "step": 125210 }, { "epoch": 30.08, "learning_rate": 7.161676778592934e-05, "loss": 0.0377, "step": 125220 }, { "epoch": 30.08, "learning_rate": 7.161272174568525e-05, "loss": 0.0426, "step": 125230 }, { "epoch": 30.08, "learning_rate": 7.160867553139093e-05, "loss": 0.0275, "step": 125240 }, { "epoch": 30.08, "learning_rate": 7.160462914307894e-05, "loss": 0.0453, "step": 125250 }, { "epoch": 30.08, "learning_rate": 7.160058258078192e-05, "loss": 0.0501, "step": 125260 }, { "epoch": 30.09, "learning_rate": 7.159653584453241e-05, "loss": 0.0397, "step": 125270 }, { "epoch": 30.09, "learning_rate": 7.159248893436304e-05, "loss": 0.0232, "step": 125280 }, { "epoch": 30.09, "learning_rate": 7.158844185030634e-05, "loss": 0.036, "step": 125290 }, { "epoch": 30.09, "learning_rate": 7.158439459239496e-05, "loss": 0.0329, "step": 125300 }, { "epoch": 30.1, "learning_rate": 7.158034716066145e-05, "loss": 0.0522, "step": 125310 }, { "epoch": 30.1, "learning_rate": 7.157629955513843e-05, "loss": 0.0294, "step": 125320 }, { "epoch": 30.1, "learning_rate": 7.157225177585852e-05, "loss": 0.0258, "step": 125330 }, { "epoch": 30.1, "learning_rate": 7.156820382285425e-05, "loss": 0.0472, "step": 125340 }, { "epoch": 30.11, "learning_rate": 7.156415569615827e-05, "loss": 0.0284, "step": 125350 }, { "epoch": 30.11, "learning_rate": 7.156010739580317e-05, "loss": 0.046, "step": 125360 }, { "epoch": 30.11, "learning_rate": 7.155605892182154e-05, "loss": 0.0387, "step": 125370 }, { "epoch": 30.11, "learning_rate": 7.155201027424602e-05, "loss": 0.0413, "step": 125380 }, { "epoch": 30.11, "learning_rate": 7.154796145310916e-05, "loss": 0.0444, "step": 125390 }, { "epoch": 30.12, "learning_rate": 7.15439124584436e-05, "loss": 0.0447, "step": 125400 }, { "epoch": 30.12, "learning_rate": 7.153986329028193e-05, "loss": 0.0466, "step": 125410 }, { "epoch": 30.12, "learning_rate": 7.153581394865678e-05, "loss": 0.0268, "step": 125420 }, { "epoch": 30.12, "learning_rate": 7.153176443360075e-05, "loss": 0.0299, "step": 125430 }, { "epoch": 30.13, "learning_rate": 7.152771474514642e-05, "loss": 0.0484, "step": 125440 }, { "epoch": 30.13, "learning_rate": 7.152366488332647e-05, "loss": 0.0697, "step": 125450 }, { "epoch": 30.13, "learning_rate": 7.151961484817345e-05, "loss": 0.0247, "step": 125460 }, { "epoch": 30.13, "learning_rate": 7.151556463972e-05, "loss": 0.0363, "step": 125470 }, { "epoch": 30.13, "learning_rate": 7.151151425799875e-05, "loss": 0.0496, "step": 125480 }, { "epoch": 30.14, "learning_rate": 7.150746370304229e-05, "loss": 0.0294, "step": 125490 }, { "epoch": 30.14, "learning_rate": 7.150341297488326e-05, "loss": 0.0572, "step": 125500 }, { "epoch": 30.14, "learning_rate": 7.149936207355427e-05, "loss": 0.0299, "step": 125510 }, { "epoch": 30.14, "learning_rate": 7.149531099908798e-05, "loss": 0.0425, "step": 125520 }, { "epoch": 30.15, "learning_rate": 7.149125975151696e-05, "loss": 0.03, "step": 125530 }, { "epoch": 30.15, "learning_rate": 7.148720833087386e-05, "loss": 0.0495, "step": 125540 }, { "epoch": 30.15, "learning_rate": 7.148315673719131e-05, "loss": 0.0283, "step": 125550 }, { "epoch": 30.15, "learning_rate": 7.147910497050192e-05, "loss": 0.0539, "step": 125560 }, { "epoch": 30.16, "learning_rate": 7.147505303083835e-05, "loss": 0.0397, "step": 125570 }, { "epoch": 30.16, "learning_rate": 7.14710009182332e-05, "loss": 0.0515, "step": 125580 }, { "epoch": 30.16, "learning_rate": 7.146694863271913e-05, "loss": 0.0301, "step": 125590 }, { "epoch": 30.16, "learning_rate": 7.146289617432874e-05, "loss": 0.0572, "step": 125600 }, { "epoch": 30.16, "learning_rate": 7.145884354309469e-05, "loss": 0.0347, "step": 125610 }, { "epoch": 30.17, "learning_rate": 7.145479073904962e-05, "loss": 0.0514, "step": 125620 }, { "epoch": 30.17, "learning_rate": 7.145073776222614e-05, "loss": 0.0352, "step": 125630 }, { "epoch": 30.17, "learning_rate": 7.144668461265694e-05, "loss": 0.0349, "step": 125640 }, { "epoch": 30.17, "learning_rate": 7.144263129037459e-05, "loss": 0.0675, "step": 125650 }, { "epoch": 30.18, "learning_rate": 7.143857779541179e-05, "loss": 0.0339, "step": 125660 }, { "epoch": 30.18, "learning_rate": 7.143452412780116e-05, "loss": 0.0222, "step": 125670 }, { "epoch": 30.18, "learning_rate": 7.143047028757533e-05, "loss": 0.0292, "step": 125680 }, { "epoch": 30.18, "learning_rate": 7.1426416274767e-05, "loss": 0.0302, "step": 125690 }, { "epoch": 30.19, "learning_rate": 7.142236208940876e-05, "loss": 0.0432, "step": 125700 }, { "epoch": 30.19, "learning_rate": 7.14183077315333e-05, "loss": 0.0367, "step": 125710 }, { "epoch": 30.19, "learning_rate": 7.141425320117322e-05, "loss": 0.0376, "step": 125720 }, { "epoch": 30.19, "learning_rate": 7.141019849836122e-05, "loss": 0.0317, "step": 125730 }, { "epoch": 30.19, "learning_rate": 7.140614362312994e-05, "loss": 0.0292, "step": 125740 }, { "epoch": 30.2, "learning_rate": 7.1402088575512e-05, "loss": 0.0327, "step": 125750 }, { "epoch": 30.2, "learning_rate": 7.139803335554013e-05, "loss": 0.0245, "step": 125760 }, { "epoch": 30.2, "learning_rate": 7.139397796324692e-05, "loss": 0.0374, "step": 125770 }, { "epoch": 30.2, "learning_rate": 7.138992239866505e-05, "loss": 0.024, "step": 125780 }, { "epoch": 30.21, "learning_rate": 7.138586666182718e-05, "loss": 0.0411, "step": 125790 }, { "epoch": 30.21, "learning_rate": 7.138181075276599e-05, "loss": 0.0367, "step": 125800 }, { "epoch": 30.21, "learning_rate": 7.137775467151411e-05, "loss": 0.0295, "step": 125810 }, { "epoch": 30.21, "learning_rate": 7.137369841810422e-05, "loss": 0.0436, "step": 125820 }, { "epoch": 30.21, "learning_rate": 7.1369641992569e-05, "loss": 0.0349, "step": 125830 }, { "epoch": 30.22, "learning_rate": 7.136558539494109e-05, "loss": 0.0253, "step": 125840 }, { "epoch": 30.22, "learning_rate": 7.136152862525317e-05, "loss": 0.051, "step": 125850 }, { "epoch": 30.22, "learning_rate": 7.135747168353792e-05, "loss": 0.0523, "step": 125860 }, { "epoch": 30.22, "learning_rate": 7.1353414569828e-05, "loss": 0.0447, "step": 125870 }, { "epoch": 30.23, "learning_rate": 7.134935728415609e-05, "loss": 0.0219, "step": 125880 }, { "epoch": 30.23, "learning_rate": 7.134529982655485e-05, "loss": 0.0433, "step": 125890 }, { "epoch": 30.23, "learning_rate": 7.134124219705696e-05, "loss": 0.0218, "step": 125900 }, { "epoch": 30.23, "learning_rate": 7.13371843956951e-05, "loss": 0.0294, "step": 125910 }, { "epoch": 30.24, "learning_rate": 7.133312642250196e-05, "loss": 0.0518, "step": 125920 }, { "epoch": 30.24, "learning_rate": 7.13290682775102e-05, "loss": 0.0356, "step": 125930 }, { "epoch": 30.24, "learning_rate": 7.13250099607525e-05, "loss": 0.0393, "step": 125940 }, { "epoch": 30.24, "learning_rate": 7.132095147226156e-05, "loss": 0.0404, "step": 125950 }, { "epoch": 30.24, "learning_rate": 7.131689281207006e-05, "loss": 0.0368, "step": 125960 }, { "epoch": 30.25, "learning_rate": 7.131283398021067e-05, "loss": 0.0336, "step": 125970 }, { "epoch": 30.25, "learning_rate": 7.130877497671609e-05, "loss": 0.0271, "step": 125980 }, { "epoch": 30.25, "learning_rate": 7.130471580161901e-05, "loss": 0.0305, "step": 125990 }, { "epoch": 30.25, "learning_rate": 7.13006564549521e-05, "loss": 0.0283, "step": 126000 }, { "epoch": 30.26, "learning_rate": 7.129659693674805e-05, "loss": 0.0263, "step": 126010 }, { "epoch": 30.26, "learning_rate": 7.129253724703959e-05, "loss": 0.0463, "step": 126020 }, { "epoch": 30.26, "learning_rate": 7.128847738585939e-05, "loss": 0.0234, "step": 126030 }, { "epoch": 30.26, "learning_rate": 7.128441735324013e-05, "loss": 0.0373, "step": 126040 }, { "epoch": 30.27, "learning_rate": 7.128035714921452e-05, "loss": 0.0493, "step": 126050 }, { "epoch": 30.27, "learning_rate": 7.127629677381527e-05, "loss": 0.0237, "step": 126060 }, { "epoch": 30.27, "learning_rate": 7.127223622707504e-05, "loss": 0.048, "step": 126070 }, { "epoch": 30.27, "learning_rate": 7.126817550902655e-05, "loss": 0.0411, "step": 126080 }, { "epoch": 30.27, "learning_rate": 7.126411461970254e-05, "loss": 0.0289, "step": 126090 }, { "epoch": 30.28, "learning_rate": 7.126005355913565e-05, "loss": 0.0301, "step": 126100 }, { "epoch": 30.28, "learning_rate": 7.125599232735864e-05, "loss": 0.0416, "step": 126110 }, { "epoch": 30.28, "learning_rate": 7.125193092440417e-05, "loss": 0.0343, "step": 126120 }, { "epoch": 30.28, "learning_rate": 7.124786935030498e-05, "loss": 0.0285, "step": 126130 }, { "epoch": 30.29, "learning_rate": 7.124380760509374e-05, "loss": 0.0334, "step": 126140 }, { "epoch": 30.29, "learning_rate": 7.12397456888032e-05, "loss": 0.0314, "step": 126150 }, { "epoch": 30.29, "learning_rate": 7.123568360146606e-05, "loss": 0.0409, "step": 126160 }, { "epoch": 30.29, "learning_rate": 7.123162134311503e-05, "loss": 0.0327, "step": 126170 }, { "epoch": 30.29, "learning_rate": 7.122755891378281e-05, "loss": 0.0611, "step": 126180 }, { "epoch": 30.3, "learning_rate": 7.122349631350213e-05, "loss": 0.0302, "step": 126190 }, { "epoch": 30.3, "learning_rate": 7.121943354230572e-05, "loss": 0.028, "step": 126200 }, { "epoch": 30.3, "learning_rate": 7.121537060022626e-05, "loss": 0.0304, "step": 126210 }, { "epoch": 30.3, "learning_rate": 7.12113074872965e-05, "loss": 0.0223, "step": 126220 }, { "epoch": 30.31, "learning_rate": 7.120724420354916e-05, "loss": 0.0267, "step": 126230 }, { "epoch": 30.31, "learning_rate": 7.120318074901695e-05, "loss": 0.0311, "step": 126240 }, { "epoch": 30.31, "learning_rate": 7.11991171237326e-05, "loss": 0.0312, "step": 126250 }, { "epoch": 30.31, "learning_rate": 7.119505332772883e-05, "loss": 0.036, "step": 126260 }, { "epoch": 30.32, "learning_rate": 7.119098936103837e-05, "loss": 0.0337, "step": 126270 }, { "epoch": 30.32, "learning_rate": 7.118692522369393e-05, "loss": 0.043, "step": 126280 }, { "epoch": 30.32, "learning_rate": 7.118286091572827e-05, "loss": 0.0293, "step": 126290 }, { "epoch": 30.32, "learning_rate": 7.117879643717412e-05, "loss": 0.0297, "step": 126300 }, { "epoch": 30.32, "learning_rate": 7.11747317880642e-05, "loss": 0.05, "step": 126310 }, { "epoch": 30.33, "learning_rate": 7.117066696843122e-05, "loss": 0.0426, "step": 126320 }, { "epoch": 30.33, "learning_rate": 7.116660197830793e-05, "loss": 0.0299, "step": 126330 }, { "epoch": 30.33, "learning_rate": 7.11625368177271e-05, "loss": 0.0543, "step": 126340 }, { "epoch": 30.33, "learning_rate": 7.115847148672142e-05, "loss": 0.0397, "step": 126350 }, { "epoch": 30.34, "learning_rate": 7.115440598532366e-05, "loss": 0.0627, "step": 126360 }, { "epoch": 30.34, "learning_rate": 7.115034031356655e-05, "loss": 0.0435, "step": 126370 }, { "epoch": 30.34, "learning_rate": 7.114627447148283e-05, "loss": 0.0413, "step": 126380 }, { "epoch": 30.34, "learning_rate": 7.114220845910522e-05, "loss": 0.04, "step": 126390 }, { "epoch": 30.35, "learning_rate": 7.11381422764665e-05, "loss": 0.0199, "step": 126400 }, { "epoch": 30.35, "learning_rate": 7.11340759235994e-05, "loss": 0.0348, "step": 126410 }, { "epoch": 30.35, "learning_rate": 7.113000940053667e-05, "loss": 0.0316, "step": 126420 }, { "epoch": 30.35, "learning_rate": 7.112594270731105e-05, "loss": 0.0334, "step": 126430 }, { "epoch": 30.35, "learning_rate": 7.112187584395532e-05, "loss": 0.0694, "step": 126440 }, { "epoch": 30.36, "learning_rate": 7.111780881050218e-05, "loss": 0.0304, "step": 126450 }, { "epoch": 30.36, "learning_rate": 7.111374160698444e-05, "loss": 0.0412, "step": 126460 }, { "epoch": 30.36, "learning_rate": 7.11096742334348e-05, "loss": 0.0496, "step": 126470 }, { "epoch": 30.36, "learning_rate": 7.110560668988604e-05, "loss": 0.0343, "step": 126480 }, { "epoch": 30.37, "learning_rate": 7.110153897637094e-05, "loss": 0.0433, "step": 126490 }, { "epoch": 30.37, "learning_rate": 7.10974710929222e-05, "loss": 0.0202, "step": 126500 }, { "epoch": 30.37, "learning_rate": 7.109340303957264e-05, "loss": 0.0283, "step": 126510 }, { "epoch": 30.37, "learning_rate": 7.108933481635496e-05, "loss": 0.0511, "step": 126520 }, { "epoch": 30.37, "learning_rate": 7.108526642330199e-05, "loss": 0.0364, "step": 126530 }, { "epoch": 30.38, "learning_rate": 7.108119786044643e-05, "loss": 0.0352, "step": 126540 }, { "epoch": 30.38, "learning_rate": 7.107712912782109e-05, "loss": 0.0475, "step": 126550 }, { "epoch": 30.38, "learning_rate": 7.107306022545872e-05, "loss": 0.035, "step": 126560 }, { "epoch": 30.38, "learning_rate": 7.10689911533921e-05, "loss": 0.0571, "step": 126570 }, { "epoch": 30.39, "learning_rate": 7.106492191165396e-05, "loss": 0.0386, "step": 126580 }, { "epoch": 30.39, "learning_rate": 7.106085250027709e-05, "loss": 0.0538, "step": 126590 }, { "epoch": 30.39, "learning_rate": 7.10567829192943e-05, "loss": 0.0281, "step": 126600 }, { "epoch": 30.39, "learning_rate": 7.105271316873831e-05, "loss": 0.0374, "step": 126610 }, { "epoch": 30.4, "learning_rate": 7.104864324864191e-05, "loss": 0.0326, "step": 126620 }, { "epoch": 30.4, "learning_rate": 7.10445731590379e-05, "loss": 0.0294, "step": 126630 }, { "epoch": 30.4, "learning_rate": 7.1040502899959e-05, "loss": 0.0541, "step": 126640 }, { "epoch": 30.4, "learning_rate": 7.103643247143806e-05, "loss": 0.0302, "step": 126650 }, { "epoch": 30.4, "learning_rate": 7.103236187350781e-05, "loss": 0.0435, "step": 126660 }, { "epoch": 30.41, "learning_rate": 7.102829110620105e-05, "loss": 0.0602, "step": 126670 }, { "epoch": 30.41, "learning_rate": 7.102422016955056e-05, "loss": 0.022, "step": 126680 }, { "epoch": 30.41, "learning_rate": 7.102014906358913e-05, "loss": 0.0297, "step": 126690 }, { "epoch": 30.41, "learning_rate": 7.101607778834952e-05, "loss": 0.028, "step": 126700 }, { "epoch": 30.42, "learning_rate": 7.101200634386454e-05, "loss": 0.0305, "step": 126710 }, { "epoch": 30.42, "learning_rate": 7.100793473016699e-05, "loss": 0.0554, "step": 126720 }, { "epoch": 30.42, "learning_rate": 7.10038629472896e-05, "loss": 0.0359, "step": 126730 }, { "epoch": 30.42, "learning_rate": 7.099979099526523e-05, "loss": 0.036, "step": 126740 }, { "epoch": 30.43, "learning_rate": 7.099571887412666e-05, "loss": 0.0272, "step": 126750 }, { "epoch": 30.43, "learning_rate": 7.099164658390664e-05, "loss": 0.0496, "step": 126760 }, { "epoch": 30.43, "learning_rate": 7.098757412463801e-05, "loss": 0.0179, "step": 126770 }, { "epoch": 30.43, "learning_rate": 7.098350149635353e-05, "loss": 0.0555, "step": 126780 }, { "epoch": 30.43, "learning_rate": 7.097942869908602e-05, "loss": 0.035, "step": 126790 }, { "epoch": 30.44, "learning_rate": 7.097535573286828e-05, "loss": 0.022, "step": 126800 }, { "epoch": 30.44, "learning_rate": 7.097128259773312e-05, "loss": 0.0417, "step": 126810 }, { "epoch": 30.44, "learning_rate": 7.09672092937133e-05, "loss": 0.0311, "step": 126820 }, { "epoch": 30.44, "learning_rate": 7.096313582084164e-05, "loss": 0.0525, "step": 126830 }, { "epoch": 30.45, "learning_rate": 7.0959062179151e-05, "loss": 0.0272, "step": 126840 }, { "epoch": 30.45, "learning_rate": 7.09549883686741e-05, "loss": 0.0392, "step": 126850 }, { "epoch": 30.45, "learning_rate": 7.095091438944379e-05, "loss": 0.0354, "step": 126860 }, { "epoch": 30.45, "learning_rate": 7.094684024149287e-05, "loss": 0.0407, "step": 126870 }, { "epoch": 30.45, "learning_rate": 7.094276592485417e-05, "loss": 0.0421, "step": 126880 }, { "epoch": 30.46, "learning_rate": 7.093869143956049e-05, "loss": 0.024, "step": 126890 }, { "epoch": 30.46, "learning_rate": 7.093461678564461e-05, "loss": 0.0278, "step": 126900 }, { "epoch": 30.46, "learning_rate": 7.093054196313939e-05, "loss": 0.0482, "step": 126910 }, { "epoch": 30.46, "learning_rate": 7.092646697207762e-05, "loss": 0.0336, "step": 126920 }, { "epoch": 30.47, "learning_rate": 7.092239181249213e-05, "loss": 0.0355, "step": 126930 }, { "epoch": 30.47, "learning_rate": 7.091831648441572e-05, "loss": 0.0198, "step": 126940 }, { "epoch": 30.47, "learning_rate": 7.091424098788121e-05, "loss": 0.0282, "step": 126950 }, { "epoch": 30.47, "learning_rate": 7.091016532292146e-05, "loss": 0.0528, "step": 126960 }, { "epoch": 30.48, "learning_rate": 7.090608948956924e-05, "loss": 0.0354, "step": 126970 }, { "epoch": 30.48, "learning_rate": 7.09020134878574e-05, "loss": 0.0332, "step": 126980 }, { "epoch": 30.48, "learning_rate": 7.089793731781876e-05, "loss": 0.0322, "step": 126990 }, { "epoch": 30.48, "learning_rate": 7.089386097948615e-05, "loss": 0.0354, "step": 127000 }, { "epoch": 30.48, "learning_rate": 7.088978447289239e-05, "loss": 0.0523, "step": 127010 }, { "epoch": 30.49, "learning_rate": 7.08857077980703e-05, "loss": 0.047, "step": 127020 }, { "epoch": 30.49, "learning_rate": 7.088163095505275e-05, "loss": 0.0497, "step": 127030 }, { "epoch": 30.49, "learning_rate": 7.087755394387251e-05, "loss": 0.0385, "step": 127040 }, { "epoch": 30.49, "learning_rate": 7.087347676456246e-05, "loss": 0.0262, "step": 127050 }, { "epoch": 30.5, "learning_rate": 7.086939941715543e-05, "loss": 0.0347, "step": 127060 }, { "epoch": 30.5, "learning_rate": 7.086532190168423e-05, "loss": 0.054, "step": 127070 }, { "epoch": 30.5, "learning_rate": 7.086124421818173e-05, "loss": 0.0344, "step": 127080 }, { "epoch": 30.5, "learning_rate": 7.085716636668072e-05, "loss": 0.0406, "step": 127090 }, { "epoch": 30.51, "learning_rate": 7.08530883472141e-05, "loss": 0.023, "step": 127100 }, { "epoch": 30.51, "learning_rate": 7.084901015981467e-05, "loss": 0.0478, "step": 127110 }, { "epoch": 30.51, "learning_rate": 7.084493180451528e-05, "loss": 0.0458, "step": 127120 }, { "epoch": 30.51, "learning_rate": 7.084085328134877e-05, "loss": 0.0356, "step": 127130 }, { "epoch": 30.51, "learning_rate": 7.083677459034798e-05, "loss": 0.0321, "step": 127140 }, { "epoch": 30.52, "learning_rate": 7.083269573154581e-05, "loss": 0.0262, "step": 127150 }, { "epoch": 30.52, "learning_rate": 7.082861670497503e-05, "loss": 0.0383, "step": 127160 }, { "epoch": 30.52, "learning_rate": 7.082453751066854e-05, "loss": 0.0359, "step": 127170 }, { "epoch": 30.52, "learning_rate": 7.082045814865918e-05, "loss": 0.0264, "step": 127180 }, { "epoch": 30.53, "learning_rate": 7.081637861897979e-05, "loss": 0.0422, "step": 127190 }, { "epoch": 30.53, "learning_rate": 7.08122989216632e-05, "loss": 0.0387, "step": 127200 }, { "epoch": 30.53, "learning_rate": 7.080821905674233e-05, "loss": 0.0321, "step": 127210 }, { "epoch": 30.53, "learning_rate": 7.080413902425e-05, "loss": 0.0355, "step": 127220 }, { "epoch": 30.53, "learning_rate": 7.080005882421906e-05, "loss": 0.0515, "step": 127230 }, { "epoch": 30.54, "learning_rate": 7.079597845668235e-05, "loss": 0.0569, "step": 127240 }, { "epoch": 30.54, "learning_rate": 7.079189792167277e-05, "loss": 0.037, "step": 127250 }, { "epoch": 30.54, "learning_rate": 7.078781721922317e-05, "loss": 0.0447, "step": 127260 }, { "epoch": 30.54, "learning_rate": 7.078373634936641e-05, "loss": 0.0611, "step": 127270 }, { "epoch": 30.55, "learning_rate": 7.077965531213535e-05, "loss": 0.0467, "step": 127280 }, { "epoch": 30.55, "learning_rate": 7.077557410756285e-05, "loss": 0.0444, "step": 127290 }, { "epoch": 30.55, "learning_rate": 7.07714927356818e-05, "loss": 0.0456, "step": 127300 }, { "epoch": 30.55, "learning_rate": 7.076741119652504e-05, "loss": 0.0874, "step": 127310 }, { "epoch": 30.56, "learning_rate": 7.076332949012545e-05, "loss": 0.0664, "step": 127320 }, { "epoch": 30.56, "learning_rate": 7.075924761651589e-05, "loss": 0.0621, "step": 127330 }, { "epoch": 30.56, "learning_rate": 7.075516557572927e-05, "loss": 0.0393, "step": 127340 }, { "epoch": 30.56, "learning_rate": 7.075108336779841e-05, "loss": 0.0359, "step": 127350 }, { "epoch": 30.56, "learning_rate": 7.074700099275623e-05, "loss": 0.0718, "step": 127360 }, { "epoch": 30.57, "learning_rate": 7.074291845063558e-05, "loss": 0.0557, "step": 127370 }, { "epoch": 30.57, "learning_rate": 7.073883574146934e-05, "loss": 0.04, "step": 127380 }, { "epoch": 30.57, "learning_rate": 7.07347528652904e-05, "loss": 0.0417, "step": 127390 }, { "epoch": 30.57, "learning_rate": 7.073066982213161e-05, "loss": 0.0618, "step": 127400 }, { "epoch": 30.58, "learning_rate": 7.072658661202591e-05, "loss": 0.0483, "step": 127410 }, { "epoch": 30.58, "learning_rate": 7.072250323500612e-05, "loss": 0.0579, "step": 127420 }, { "epoch": 30.58, "learning_rate": 7.071841969110515e-05, "loss": 0.0483, "step": 127430 }, { "epoch": 30.58, "learning_rate": 7.071433598035591e-05, "loss": 0.0383, "step": 127440 }, { "epoch": 30.59, "learning_rate": 7.071025210279124e-05, "loss": 0.0509, "step": 127450 }, { "epoch": 30.59, "learning_rate": 7.070616805844407e-05, "loss": 0.0345, "step": 127460 }, { "epoch": 30.59, "learning_rate": 7.070208384734724e-05, "loss": 0.0711, "step": 127470 }, { "epoch": 30.59, "learning_rate": 7.06979994695337e-05, "loss": 0.0568, "step": 127480 }, { "epoch": 30.59, "learning_rate": 7.06939149250363e-05, "loss": 0.0406, "step": 127490 }, { "epoch": 30.6, "learning_rate": 7.068983021388794e-05, "loss": 0.0259, "step": 127500 }, { "epoch": 30.6, "learning_rate": 7.068574533612153e-05, "loss": 0.0408, "step": 127510 }, { "epoch": 30.6, "learning_rate": 7.068166029176996e-05, "loss": 0.0563, "step": 127520 }, { "epoch": 30.6, "learning_rate": 7.067757508086612e-05, "loss": 0.037, "step": 127530 }, { "epoch": 30.61, "learning_rate": 7.067348970344291e-05, "loss": 0.0365, "step": 127540 }, { "epoch": 30.61, "learning_rate": 7.066940415953323e-05, "loss": 0.0305, "step": 127550 }, { "epoch": 30.61, "learning_rate": 7.066531844916999e-05, "loss": 0.0315, "step": 127560 }, { "epoch": 30.61, "learning_rate": 7.066123257238609e-05, "loss": 0.0347, "step": 127570 }, { "epoch": 30.61, "learning_rate": 7.065714652921443e-05, "loss": 0.0446, "step": 127580 }, { "epoch": 30.62, "learning_rate": 7.065306031968791e-05, "loss": 0.0254, "step": 127590 }, { "epoch": 30.62, "learning_rate": 7.064897394383946e-05, "loss": 0.0478, "step": 127600 }, { "epoch": 30.62, "learning_rate": 7.064488740170196e-05, "loss": 0.0507, "step": 127610 }, { "epoch": 30.62, "learning_rate": 7.064080069330834e-05, "loss": 0.0397, "step": 127620 }, { "epoch": 30.63, "learning_rate": 7.06367138186915e-05, "loss": 0.0448, "step": 127630 }, { "epoch": 30.63, "learning_rate": 7.063262677788435e-05, "loss": 0.0375, "step": 127640 }, { "epoch": 30.63, "learning_rate": 7.062853957091982e-05, "loss": 0.0223, "step": 127650 }, { "epoch": 30.63, "learning_rate": 7.062445219783078e-05, "loss": 0.0555, "step": 127660 }, { "epoch": 30.64, "learning_rate": 7.062036465865021e-05, "loss": 0.0396, "step": 127670 }, { "epoch": 30.64, "learning_rate": 7.061627695341099e-05, "loss": 0.055, "step": 127680 }, { "epoch": 30.64, "learning_rate": 7.061218908214604e-05, "loss": 0.0474, "step": 127690 }, { "epoch": 30.64, "learning_rate": 7.060810104488829e-05, "loss": 0.0739, "step": 127700 }, { "epoch": 30.64, "learning_rate": 7.060401284167067e-05, "loss": 0.0527, "step": 127710 }, { "epoch": 30.65, "learning_rate": 7.059992447252606e-05, "loss": 0.0655, "step": 127720 }, { "epoch": 30.65, "learning_rate": 7.059583593748743e-05, "loss": 0.0253, "step": 127730 }, { "epoch": 30.65, "learning_rate": 7.059174723658769e-05, "loss": 0.0472, "step": 127740 }, { "epoch": 30.65, "learning_rate": 7.058765836985976e-05, "loss": 0.0404, "step": 127750 }, { "epoch": 30.66, "learning_rate": 7.058356933733659e-05, "loss": 0.0268, "step": 127760 }, { "epoch": 30.66, "learning_rate": 7.057948013905109e-05, "loss": 0.0609, "step": 127770 }, { "epoch": 30.66, "learning_rate": 7.057539077503618e-05, "loss": 0.0553, "step": 127780 }, { "epoch": 30.66, "learning_rate": 7.057130124532483e-05, "loss": 0.0347, "step": 127790 }, { "epoch": 30.66, "learning_rate": 7.056721154994992e-05, "loss": 0.0334, "step": 127800 }, { "epoch": 30.67, "learning_rate": 7.056312168894445e-05, "loss": 0.0479, "step": 127810 }, { "epoch": 30.67, "learning_rate": 7.055903166234131e-05, "loss": 0.0274, "step": 127820 }, { "epoch": 30.67, "learning_rate": 7.055494147017346e-05, "loss": 0.0313, "step": 127830 }, { "epoch": 30.67, "learning_rate": 7.055085111247379e-05, "loss": 0.0232, "step": 127840 }, { "epoch": 30.68, "learning_rate": 7.054676058927532e-05, "loss": 0.0366, "step": 127850 }, { "epoch": 30.68, "learning_rate": 7.054266990061093e-05, "loss": 0.0487, "step": 127860 }, { "epoch": 30.68, "learning_rate": 7.053857904651359e-05, "loss": 0.0655, "step": 127870 }, { "epoch": 30.68, "learning_rate": 7.053448802701623e-05, "loss": 0.0321, "step": 127880 }, { "epoch": 30.69, "learning_rate": 7.053039684215181e-05, "loss": 0.0511, "step": 127890 }, { "epoch": 30.69, "learning_rate": 7.052630549195328e-05, "loss": 0.0404, "step": 127900 }, { "epoch": 30.69, "learning_rate": 7.052221397645355e-05, "loss": 0.0422, "step": 127910 }, { "epoch": 30.69, "learning_rate": 7.051812229568561e-05, "loss": 0.0316, "step": 127920 }, { "epoch": 30.69, "learning_rate": 7.051403044968242e-05, "loss": 0.0377, "step": 127930 }, { "epoch": 30.7, "learning_rate": 7.050993843847688e-05, "loss": 0.0659, "step": 127940 }, { "epoch": 30.7, "learning_rate": 7.0505846262102e-05, "loss": 0.0621, "step": 127950 }, { "epoch": 30.7, "learning_rate": 7.050175392059069e-05, "loss": 0.06, "step": 127960 }, { "epoch": 30.7, "learning_rate": 7.049766141397593e-05, "loss": 0.042, "step": 127970 }, { "epoch": 30.71, "learning_rate": 7.049356874229067e-05, "loss": 0.0455, "step": 127980 }, { "epoch": 30.71, "learning_rate": 7.048947590556788e-05, "loss": 0.0649, "step": 127990 }, { "epoch": 30.71, "learning_rate": 7.048538290384051e-05, "loss": 0.0309, "step": 128000 }, { "epoch": 30.71, "learning_rate": 7.048128973714152e-05, "loss": 0.033, "step": 128010 }, { "epoch": 30.72, "learning_rate": 7.047719640550389e-05, "loss": 0.0393, "step": 128020 }, { "epoch": 30.72, "learning_rate": 7.047310290896054e-05, "loss": 0.0283, "step": 128030 }, { "epoch": 30.72, "learning_rate": 7.04690092475445e-05, "loss": 0.056, "step": 128040 }, { "epoch": 30.72, "learning_rate": 7.046491542128868e-05, "loss": 0.0306, "step": 128050 }, { "epoch": 30.72, "learning_rate": 7.046082143022607e-05, "loss": 0.0423, "step": 128060 }, { "epoch": 30.73, "learning_rate": 7.045672727438966e-05, "loss": 0.032, "step": 128070 }, { "epoch": 30.73, "learning_rate": 7.045263295381238e-05, "loss": 0.053, "step": 128080 }, { "epoch": 30.73, "learning_rate": 7.044853846852724e-05, "loss": 0.0389, "step": 128090 }, { "epoch": 30.73, "learning_rate": 7.044444381856718e-05, "loss": 0.0628, "step": 128100 }, { "epoch": 30.74, "learning_rate": 7.04403490039652e-05, "loss": 0.0457, "step": 128110 }, { "epoch": 30.74, "learning_rate": 7.043625402475426e-05, "loss": 0.0393, "step": 128120 }, { "epoch": 30.74, "learning_rate": 7.043215888096736e-05, "loss": 0.0567, "step": 128130 }, { "epoch": 30.74, "learning_rate": 7.042806357263745e-05, "loss": 0.041, "step": 128140 }, { "epoch": 30.74, "learning_rate": 7.042396809979752e-05, "loss": 0.0411, "step": 128150 }, { "epoch": 30.75, "learning_rate": 7.041987246248058e-05, "loss": 0.0371, "step": 128160 }, { "epoch": 30.75, "learning_rate": 7.041577666071957e-05, "loss": 0.0465, "step": 128170 }, { "epoch": 30.75, "learning_rate": 7.04116806945475e-05, "loss": 0.0492, "step": 128180 }, { "epoch": 30.75, "learning_rate": 7.040758456399732e-05, "loss": 0.0234, "step": 128190 }, { "epoch": 30.76, "learning_rate": 7.040348826910208e-05, "loss": 0.0473, "step": 128200 }, { "epoch": 30.76, "learning_rate": 7.039939180989472e-05, "loss": 0.0609, "step": 128210 }, { "epoch": 30.76, "learning_rate": 7.039529518640823e-05, "loss": 0.0567, "step": 128220 }, { "epoch": 30.76, "learning_rate": 7.039119839867563e-05, "loss": 0.0321, "step": 128230 }, { "epoch": 30.77, "learning_rate": 7.038710144672987e-05, "loss": 0.0311, "step": 128240 }, { "epoch": 30.77, "learning_rate": 7.038300433060398e-05, "loss": 0.0387, "step": 128250 }, { "epoch": 30.77, "learning_rate": 7.037890705033096e-05, "loss": 0.0224, "step": 128260 }, { "epoch": 30.77, "learning_rate": 7.037480960594376e-05, "loss": 0.0407, "step": 128270 }, { "epoch": 30.77, "learning_rate": 7.037071199747544e-05, "loss": 0.0515, "step": 128280 }, { "epoch": 30.78, "learning_rate": 7.036661422495892e-05, "loss": 0.0604, "step": 128290 }, { "epoch": 30.78, "learning_rate": 7.036251628842728e-05, "loss": 0.0205, "step": 128300 }, { "epoch": 30.78, "learning_rate": 7.035841818791346e-05, "loss": 0.0314, "step": 128310 }, { "epoch": 30.78, "learning_rate": 7.035431992345051e-05, "loss": 0.0294, "step": 128320 }, { "epoch": 30.79, "learning_rate": 7.03502214950714e-05, "loss": 0.0367, "step": 128330 }, { "epoch": 30.79, "learning_rate": 7.034612290280913e-05, "loss": 0.0315, "step": 128340 }, { "epoch": 30.79, "learning_rate": 7.034202414669677e-05, "loss": 0.0593, "step": 128350 }, { "epoch": 30.79, "learning_rate": 7.033792522676723e-05, "loss": 0.0414, "step": 128360 }, { "epoch": 30.8, "learning_rate": 7.033382614305359e-05, "loss": 0.0421, "step": 128370 }, { "epoch": 30.8, "learning_rate": 7.032972689558886e-05, "loss": 0.0286, "step": 128380 }, { "epoch": 30.8, "learning_rate": 7.0325627484406e-05, "loss": 0.0289, "step": 128390 }, { "epoch": 30.8, "learning_rate": 7.032152790953807e-05, "loss": 0.0249, "step": 128400 }, { "epoch": 30.8, "learning_rate": 7.031742817101807e-05, "loss": 0.04, "step": 128410 }, { "epoch": 30.81, "learning_rate": 7.031332826887903e-05, "loss": 0.0191, "step": 128420 }, { "epoch": 30.81, "learning_rate": 7.030922820315393e-05, "loss": 0.042, "step": 128430 }, { "epoch": 30.81, "learning_rate": 7.030512797387583e-05, "loss": 0.0478, "step": 128440 }, { "epoch": 30.81, "learning_rate": 7.030102758107771e-05, "loss": 0.037, "step": 128450 }, { "epoch": 30.82, "learning_rate": 7.029692702479263e-05, "loss": 0.024, "step": 128460 }, { "epoch": 30.82, "learning_rate": 7.02928263050536e-05, "loss": 0.0265, "step": 128470 }, { "epoch": 30.82, "learning_rate": 7.028872542189362e-05, "loss": 0.0224, "step": 128480 }, { "epoch": 30.82, "learning_rate": 7.028462437534576e-05, "loss": 0.0465, "step": 128490 }, { "epoch": 30.82, "learning_rate": 7.028052316544299e-05, "loss": 0.0349, "step": 128500 }, { "epoch": 30.83, "learning_rate": 7.027642179221837e-05, "loss": 0.0412, "step": 128510 }, { "epoch": 30.83, "learning_rate": 7.027232025570494e-05, "loss": 0.0362, "step": 128520 }, { "epoch": 30.83, "learning_rate": 7.026821855593569e-05, "loss": 0.0432, "step": 128530 }, { "epoch": 30.83, "learning_rate": 7.026411669294371e-05, "loss": 0.0523, "step": 128540 }, { "epoch": 30.84, "learning_rate": 7.026001466676198e-05, "loss": 0.0549, "step": 128550 }, { "epoch": 30.84, "learning_rate": 7.025591247742357e-05, "loss": 0.0402, "step": 128560 }, { "epoch": 30.84, "learning_rate": 7.025181012496149e-05, "loss": 0.0253, "step": 128570 }, { "epoch": 30.84, "learning_rate": 7.024770760940879e-05, "loss": 0.0198, "step": 128580 }, { "epoch": 30.85, "learning_rate": 7.024360493079851e-05, "loss": 0.0452, "step": 128590 }, { "epoch": 30.85, "learning_rate": 7.023950208916368e-05, "loss": 0.0381, "step": 128600 }, { "epoch": 30.85, "learning_rate": 7.023539908453734e-05, "loss": 0.0518, "step": 128610 }, { "epoch": 30.85, "learning_rate": 7.023129591695255e-05, "loss": 0.0318, "step": 128620 }, { "epoch": 30.85, "learning_rate": 7.022719258644232e-05, "loss": 0.0456, "step": 128630 }, { "epoch": 30.86, "learning_rate": 7.022308909303974e-05, "loss": 0.0478, "step": 128640 }, { "epoch": 30.86, "learning_rate": 7.02189854367778e-05, "loss": 0.0335, "step": 128650 }, { "epoch": 30.86, "learning_rate": 7.021488161768962e-05, "loss": 0.038, "step": 128660 }, { "epoch": 30.86, "learning_rate": 7.021077763580818e-05, "loss": 0.0288, "step": 128670 }, { "epoch": 30.87, "learning_rate": 7.020667349116656e-05, "loss": 0.0443, "step": 128680 }, { "epoch": 30.87, "learning_rate": 7.020256918379783e-05, "loss": 0.0395, "step": 128690 }, { "epoch": 30.87, "learning_rate": 7.0198464713735e-05, "loss": 0.0249, "step": 128700 }, { "epoch": 30.87, "learning_rate": 7.019436008101115e-05, "loss": 0.0281, "step": 128710 }, { "epoch": 30.88, "learning_rate": 7.019025528565933e-05, "loss": 0.0412, "step": 128720 }, { "epoch": 30.88, "learning_rate": 7.018615032771261e-05, "loss": 0.0251, "step": 128730 }, { "epoch": 30.88, "learning_rate": 7.0182045207204e-05, "loss": 0.0291, "step": 128740 }, { "epoch": 30.88, "learning_rate": 7.017793992416662e-05, "loss": 0.0414, "step": 128750 }, { "epoch": 30.88, "learning_rate": 7.01738344786335e-05, "loss": 0.0301, "step": 128760 }, { "epoch": 30.89, "learning_rate": 7.016972887063771e-05, "loss": 0.0419, "step": 128770 }, { "epoch": 30.89, "learning_rate": 7.016562310021231e-05, "loss": 0.0402, "step": 128780 }, { "epoch": 30.89, "learning_rate": 7.016151716739034e-05, "loss": 0.0329, "step": 128790 }, { "epoch": 30.89, "learning_rate": 7.015741107220491e-05, "loss": 0.0512, "step": 128800 }, { "epoch": 30.9, "learning_rate": 7.015330481468906e-05, "loss": 0.0371, "step": 128810 }, { "epoch": 30.9, "learning_rate": 7.014919839487587e-05, "loss": 0.0359, "step": 128820 }, { "epoch": 30.9, "learning_rate": 7.01450918127984e-05, "loss": 0.0264, "step": 128830 }, { "epoch": 30.9, "learning_rate": 7.014098506848971e-05, "loss": 0.0411, "step": 128840 }, { "epoch": 30.9, "learning_rate": 7.013687816198292e-05, "loss": 0.0203, "step": 128850 }, { "epoch": 30.91, "learning_rate": 7.013277109331103e-05, "loss": 0.0213, "step": 128860 }, { "epoch": 30.91, "learning_rate": 7.012866386250718e-05, "loss": 0.0323, "step": 128870 }, { "epoch": 30.91, "learning_rate": 7.012455646960441e-05, "loss": 0.041, "step": 128880 }, { "epoch": 30.91, "learning_rate": 7.012044891463582e-05, "loss": 0.0357, "step": 128890 }, { "epoch": 30.92, "learning_rate": 7.011634119763448e-05, "loss": 0.033, "step": 128900 }, { "epoch": 30.92, "learning_rate": 7.011223331863345e-05, "loss": 0.0562, "step": 128910 }, { "epoch": 30.92, "learning_rate": 7.010812527766585e-05, "loss": 0.0293, "step": 128920 }, { "epoch": 30.92, "learning_rate": 7.010401707476472e-05, "loss": 0.0322, "step": 128930 }, { "epoch": 30.93, "learning_rate": 7.009990870996317e-05, "loss": 0.0315, "step": 128940 }, { "epoch": 30.93, "learning_rate": 7.009580018329428e-05, "loss": 0.0185, "step": 128950 }, { "epoch": 30.93, "learning_rate": 7.009169149479115e-05, "loss": 0.0376, "step": 128960 }, { "epoch": 30.93, "learning_rate": 7.008758264448684e-05, "loss": 0.0279, "step": 128970 }, { "epoch": 30.93, "learning_rate": 7.008347363241446e-05, "loss": 0.0387, "step": 128980 }, { "epoch": 30.94, "learning_rate": 7.007936445860708e-05, "loss": 0.047, "step": 128990 }, { "epoch": 30.94, "learning_rate": 7.007525512309783e-05, "loss": 0.0364, "step": 129000 }, { "epoch": 30.94, "learning_rate": 7.007114562591977e-05, "loss": 0.032, "step": 129010 }, { "epoch": 30.94, "learning_rate": 7.0067035967106e-05, "loss": 0.0342, "step": 129020 }, { "epoch": 30.95, "learning_rate": 7.006292614668961e-05, "loss": 0.0414, "step": 129030 }, { "epoch": 30.95, "learning_rate": 7.005881616470372e-05, "loss": 0.0392, "step": 129040 }, { "epoch": 30.95, "learning_rate": 7.005470602118141e-05, "loss": 0.0376, "step": 129050 }, { "epoch": 31.0, "learning_rate": 7.005059571615578e-05, "loss": 0.0313, "step": 129060 }, { "epoch": 31.0, "learning_rate": 7.004648524965994e-05, "loss": 0.035, "step": 129070 }, { "epoch": 31.01, "learning_rate": 7.004237462172698e-05, "loss": 0.0414, "step": 129080 }, { "epoch": 31.01, "learning_rate": 7.003826383239001e-05, "loss": 0.0429, "step": 129090 }, { "epoch": 31.01, "learning_rate": 7.003415288168214e-05, "loss": 0.0382, "step": 129100 }, { "epoch": 31.01, "learning_rate": 7.003004176963646e-05, "loss": 0.0386, "step": 129110 }, { "epoch": 31.02, "learning_rate": 7.002593049628611e-05, "loss": 0.0795, "step": 129120 }, { "epoch": 31.02, "learning_rate": 7.002181906166417e-05, "loss": 0.0442, "step": 129130 }, { "epoch": 31.02, "learning_rate": 7.001770746580374e-05, "loss": 0.0455, "step": 129140 }, { "epoch": 31.02, "learning_rate": 7.001359570873798e-05, "loss": 0.0232, "step": 129150 }, { "epoch": 31.02, "learning_rate": 7.000948379049994e-05, "loss": 0.0478, "step": 129160 }, { "epoch": 31.03, "learning_rate": 7.000537171112278e-05, "loss": 0.0319, "step": 129170 }, { "epoch": 31.03, "learning_rate": 7.000125947063959e-05, "loss": 0.0458, "step": 129180 }, { "epoch": 31.03, "learning_rate": 6.99971470690835e-05, "loss": 0.051, "step": 129190 }, { "epoch": 31.03, "learning_rate": 6.999303450648763e-05, "loss": 0.0263, "step": 129200 }, { "epoch": 31.04, "learning_rate": 6.998892178288508e-05, "loss": 0.0277, "step": 129210 }, { "epoch": 31.04, "learning_rate": 6.998480889830901e-05, "loss": 0.0595, "step": 129220 }, { "epoch": 31.04, "learning_rate": 6.998069585279248e-05, "loss": 0.0412, "step": 129230 }, { "epoch": 31.04, "learning_rate": 6.997658264636866e-05, "loss": 0.0384, "step": 129240 }, { "epoch": 31.05, "learning_rate": 6.997246927907067e-05, "loss": 0.018, "step": 129250 }, { "epoch": 31.05, "learning_rate": 6.996835575093163e-05, "loss": 0.0326, "step": 129260 }, { "epoch": 31.05, "learning_rate": 6.996424206198467e-05, "loss": 0.0309, "step": 129270 }, { "epoch": 31.05, "learning_rate": 6.996012821226288e-05, "loss": 0.035, "step": 129280 }, { "epoch": 31.05, "learning_rate": 6.995601420179946e-05, "loss": 0.0491, "step": 129290 }, { "epoch": 31.06, "learning_rate": 6.995190003062747e-05, "loss": 0.0224, "step": 129300 }, { "epoch": 31.06, "learning_rate": 6.994778569878008e-05, "loss": 0.0584, "step": 129310 }, { "epoch": 31.06, "learning_rate": 6.994367120629044e-05, "loss": 0.0335, "step": 129320 }, { "epoch": 31.06, "learning_rate": 6.993955655319166e-05, "loss": 0.0199, "step": 129330 }, { "epoch": 31.07, "learning_rate": 6.993544173951686e-05, "loss": 0.0301, "step": 129340 }, { "epoch": 31.07, "learning_rate": 6.99313267652992e-05, "loss": 0.0528, "step": 129350 }, { "epoch": 31.07, "learning_rate": 6.992721163057183e-05, "loss": 0.038, "step": 129360 }, { "epoch": 31.07, "learning_rate": 6.992309633536784e-05, "loss": 0.03, "step": 129370 }, { "epoch": 31.07, "learning_rate": 6.991898087972043e-05, "loss": 0.0303, "step": 129380 }, { "epoch": 31.08, "learning_rate": 6.991486526366272e-05, "loss": 0.0477, "step": 129390 }, { "epoch": 31.08, "learning_rate": 6.991074948722784e-05, "loss": 0.0366, "step": 129400 }, { "epoch": 31.08, "learning_rate": 6.990663355044895e-05, "loss": 0.0442, "step": 129410 }, { "epoch": 31.08, "learning_rate": 6.990251745335918e-05, "loss": 0.0223, "step": 129420 }, { "epoch": 31.09, "learning_rate": 6.989840119599171e-05, "loss": 0.0448, "step": 129430 }, { "epoch": 31.09, "learning_rate": 6.989428477837965e-05, "loss": 0.0406, "step": 129440 }, { "epoch": 31.09, "learning_rate": 6.989016820055618e-05, "loss": 0.0322, "step": 129450 }, { "epoch": 31.09, "learning_rate": 6.988605146255443e-05, "loss": 0.0168, "step": 129460 }, { "epoch": 31.1, "learning_rate": 6.988193456440758e-05, "loss": 0.0306, "step": 129470 }, { "epoch": 31.1, "learning_rate": 6.987781750614875e-05, "loss": 0.0275, "step": 129480 }, { "epoch": 31.1, "learning_rate": 6.987370028781111e-05, "loss": 0.0299, "step": 129490 }, { "epoch": 31.1, "learning_rate": 6.986958290942783e-05, "loss": 0.0427, "step": 129500 }, { "epoch": 31.1, "learning_rate": 6.986546537103204e-05, "loss": 0.0307, "step": 129510 }, { "epoch": 31.11, "learning_rate": 6.986134767265693e-05, "loss": 0.0266, "step": 129520 }, { "epoch": 31.11, "learning_rate": 6.985722981433563e-05, "loss": 0.0382, "step": 129530 }, { "epoch": 31.11, "learning_rate": 6.985311179610132e-05, "loss": 0.0418, "step": 129540 }, { "epoch": 31.11, "learning_rate": 6.984899361798718e-05, "loss": 0.027, "step": 129550 }, { "epoch": 31.12, "learning_rate": 6.984487528002632e-05, "loss": 0.0251, "step": 129560 }, { "epoch": 31.12, "learning_rate": 6.984075678225197e-05, "loss": 0.0633, "step": 129570 }, { "epoch": 31.12, "learning_rate": 6.983663812469725e-05, "loss": 0.0302, "step": 129580 }, { "epoch": 31.12, "learning_rate": 6.983251930739536e-05, "loss": 0.0211, "step": 129590 }, { "epoch": 31.12, "learning_rate": 6.982840033037944e-05, "loss": 0.054, "step": 129600 }, { "epoch": 31.13, "learning_rate": 6.982428119368268e-05, "loss": 0.0247, "step": 129610 }, { "epoch": 31.13, "learning_rate": 6.982016189733825e-05, "loss": 0.053, "step": 129620 }, { "epoch": 31.13, "learning_rate": 6.98160424413793e-05, "loss": 0.0382, "step": 129630 }, { "epoch": 31.13, "learning_rate": 6.981192282583903e-05, "loss": 0.0264, "step": 129640 }, { "epoch": 31.14, "learning_rate": 6.980780305075063e-05, "loss": 0.0437, "step": 129650 }, { "epoch": 31.14, "learning_rate": 6.980368311614725e-05, "loss": 0.027, "step": 129660 }, { "epoch": 31.14, "learning_rate": 6.979956302206208e-05, "loss": 0.0215, "step": 129670 }, { "epoch": 31.14, "learning_rate": 6.979544276852827e-05, "loss": 0.0204, "step": 129680 }, { "epoch": 31.15, "learning_rate": 6.979132235557906e-05, "loss": 0.027, "step": 129690 }, { "epoch": 31.15, "learning_rate": 6.978720178324758e-05, "loss": 0.0434, "step": 129700 }, { "epoch": 31.15, "learning_rate": 6.978308105156703e-05, "loss": 0.0352, "step": 129710 }, { "epoch": 31.15, "learning_rate": 6.977896016057061e-05, "loss": 0.0198, "step": 129720 }, { "epoch": 31.15, "learning_rate": 6.977483911029148e-05, "loss": 0.0305, "step": 129730 }, { "epoch": 31.16, "learning_rate": 6.977071790076286e-05, "loss": 0.0291, "step": 129740 }, { "epoch": 31.16, "learning_rate": 6.97665965320179e-05, "loss": 0.0152, "step": 129750 }, { "epoch": 31.16, "learning_rate": 6.976247500408981e-05, "loss": 0.0304, "step": 129760 }, { "epoch": 31.16, "learning_rate": 6.975835331701179e-05, "loss": 0.0278, "step": 129770 }, { "epoch": 31.17, "learning_rate": 6.9754231470817e-05, "loss": 0.0332, "step": 129780 }, { "epoch": 31.17, "learning_rate": 6.97501094655387e-05, "loss": 0.0411, "step": 129790 }, { "epoch": 31.17, "learning_rate": 6.974598730121e-05, "loss": 0.0353, "step": 129800 }, { "epoch": 31.17, "learning_rate": 6.974186497786416e-05, "loss": 0.0459, "step": 129810 }, { "epoch": 31.18, "learning_rate": 6.973774249553433e-05, "loss": 0.0431, "step": 129820 }, { "epoch": 31.18, "learning_rate": 6.973361985425377e-05, "loss": 0.0445, "step": 129830 }, { "epoch": 31.18, "learning_rate": 6.972949705405564e-05, "loss": 0.019, "step": 129840 }, { "epoch": 31.18, "learning_rate": 6.972537409497313e-05, "loss": 0.052, "step": 129850 }, { "epoch": 31.18, "learning_rate": 6.972125097703948e-05, "loss": 0.018, "step": 129860 }, { "epoch": 31.19, "learning_rate": 6.971712770028784e-05, "loss": 0.0407, "step": 129870 }, { "epoch": 31.19, "learning_rate": 6.971300426475148e-05, "loss": 0.0452, "step": 129880 }, { "epoch": 31.19, "learning_rate": 6.970888067046355e-05, "loss": 0.0399, "step": 129890 }, { "epoch": 31.19, "learning_rate": 6.970475691745731e-05, "loss": 0.039, "step": 129900 }, { "epoch": 31.2, "learning_rate": 6.970063300576593e-05, "loss": 0.0451, "step": 129910 }, { "epoch": 31.2, "learning_rate": 6.96965089354226e-05, "loss": 0.0329, "step": 129920 }, { "epoch": 31.2, "learning_rate": 6.969238470646063e-05, "loss": 0.0254, "step": 129930 }, { "epoch": 31.2, "learning_rate": 6.968826031891311e-05, "loss": 0.0327, "step": 129940 }, { "epoch": 31.2, "learning_rate": 6.968413577281333e-05, "loss": 0.0366, "step": 129950 }, { "epoch": 31.21, "learning_rate": 6.96800110681945e-05, "loss": 0.0237, "step": 129960 }, { "epoch": 31.21, "learning_rate": 6.967588620508981e-05, "loss": 0.0315, "step": 129970 }, { "epoch": 31.21, "learning_rate": 6.96717611835325e-05, "loss": 0.0393, "step": 129980 }, { "epoch": 31.21, "learning_rate": 6.966763600355577e-05, "loss": 0.0408, "step": 129990 }, { "epoch": 31.22, "learning_rate": 6.966351066519287e-05, "loss": 0.0294, "step": 130000 }, { "epoch": 31.22, "learning_rate": 6.965938516847699e-05, "loss": 0.0407, "step": 130010 }, { "epoch": 31.22, "learning_rate": 6.965525951344136e-05, "loss": 0.0263, "step": 130020 }, { "epoch": 31.22, "learning_rate": 6.965113370011923e-05, "loss": 0.0449, "step": 130030 }, { "epoch": 31.23, "learning_rate": 6.964700772854379e-05, "loss": 0.026, "step": 130040 }, { "epoch": 31.23, "learning_rate": 6.96428815987483e-05, "loss": 0.0261, "step": 130050 }, { "epoch": 31.23, "learning_rate": 6.963875531076596e-05, "loss": 0.0351, "step": 130060 }, { "epoch": 31.23, "learning_rate": 6.963462886463003e-05, "loss": 0.038, "step": 130070 }, { "epoch": 31.23, "learning_rate": 6.963050226037371e-05, "loss": 0.0317, "step": 130080 }, { "epoch": 31.24, "learning_rate": 6.962637549803024e-05, "loss": 0.0319, "step": 130090 }, { "epoch": 31.24, "learning_rate": 6.962224857763286e-05, "loss": 0.0515, "step": 130100 }, { "epoch": 31.24, "learning_rate": 6.96181214992148e-05, "loss": 0.0276, "step": 130110 }, { "epoch": 31.24, "learning_rate": 6.961399426280932e-05, "loss": 0.0461, "step": 130120 }, { "epoch": 31.25, "learning_rate": 6.960986686844963e-05, "loss": 0.0449, "step": 130130 }, { "epoch": 31.25, "learning_rate": 6.960573931616896e-05, "loss": 0.0314, "step": 130140 }, { "epoch": 31.25, "learning_rate": 6.960161160600059e-05, "loss": 0.0207, "step": 130150 }, { "epoch": 31.25, "learning_rate": 6.95974837379777e-05, "loss": 0.038, "step": 130160 }, { "epoch": 31.26, "learning_rate": 6.95933557121336e-05, "loss": 0.0347, "step": 130170 }, { "epoch": 31.26, "learning_rate": 6.958922752850148e-05, "loss": 0.0315, "step": 130180 }, { "epoch": 31.26, "learning_rate": 6.958509918711461e-05, "loss": 0.0444, "step": 130190 }, { "epoch": 31.26, "learning_rate": 6.958097068800625e-05, "loss": 0.0415, "step": 130200 }, { "epoch": 31.26, "learning_rate": 6.957684203120961e-05, "loss": 0.0392, "step": 130210 }, { "epoch": 31.27, "learning_rate": 6.957271321675797e-05, "loss": 0.0283, "step": 130220 }, { "epoch": 31.27, "learning_rate": 6.956858424468456e-05, "loss": 0.0285, "step": 130230 }, { "epoch": 31.27, "learning_rate": 6.956445511502264e-05, "loss": 0.0443, "step": 130240 }, { "epoch": 31.27, "learning_rate": 6.956032582780546e-05, "loss": 0.0337, "step": 130250 }, { "epoch": 31.28, "learning_rate": 6.955619638306627e-05, "loss": 0.0333, "step": 130260 }, { "epoch": 31.28, "learning_rate": 6.955206678083836e-05, "loss": 0.0492, "step": 130270 }, { "epoch": 31.28, "learning_rate": 6.954793702115493e-05, "loss": 0.0271, "step": 130280 }, { "epoch": 31.28, "learning_rate": 6.954380710404928e-05, "loss": 0.0492, "step": 130290 }, { "epoch": 31.28, "learning_rate": 6.953967702955462e-05, "loss": 0.0274, "step": 130300 }, { "epoch": 31.29, "learning_rate": 6.953554679770427e-05, "loss": 0.0334, "step": 130310 }, { "epoch": 31.29, "learning_rate": 6.953141640853147e-05, "loss": 0.0359, "step": 130320 }, { "epoch": 31.29, "learning_rate": 6.952728586206948e-05, "loss": 0.0409, "step": 130330 }, { "epoch": 31.29, "learning_rate": 6.952315515835154e-05, "loss": 0.029, "step": 130340 }, { "epoch": 31.3, "learning_rate": 6.951902429741096e-05, "loss": 0.0331, "step": 130350 }, { "epoch": 31.3, "learning_rate": 6.951489327928097e-05, "loss": 0.0255, "step": 130360 }, { "epoch": 31.3, "learning_rate": 6.951076210399484e-05, "loss": 0.056, "step": 130370 }, { "epoch": 31.3, "learning_rate": 6.950663077158585e-05, "loss": 0.0364, "step": 130380 }, { "epoch": 31.31, "learning_rate": 6.95024992820873e-05, "loss": 0.0283, "step": 130390 }, { "epoch": 31.31, "learning_rate": 6.94983676355324e-05, "loss": 0.0314, "step": 130400 }, { "epoch": 31.31, "learning_rate": 6.949423583195447e-05, "loss": 0.0342, "step": 130410 }, { "epoch": 31.31, "learning_rate": 6.949010387138675e-05, "loss": 0.0391, "step": 130420 }, { "epoch": 31.31, "learning_rate": 6.948597175386256e-05, "loss": 0.0293, "step": 130430 }, { "epoch": 31.32, "learning_rate": 6.948183947941511e-05, "loss": 0.0282, "step": 130440 }, { "epoch": 31.32, "learning_rate": 6.947770704807775e-05, "loss": 0.0184, "step": 130450 }, { "epoch": 31.32, "learning_rate": 6.947357445988372e-05, "loss": 0.027, "step": 130460 }, { "epoch": 31.32, "learning_rate": 6.94694417148663e-05, "loss": 0.0283, "step": 130470 }, { "epoch": 31.33, "learning_rate": 6.946530881305878e-05, "loss": 0.0369, "step": 130480 }, { "epoch": 31.33, "learning_rate": 6.946117575449443e-05, "loss": 0.0449, "step": 130490 }, { "epoch": 31.33, "learning_rate": 6.945704253920657e-05, "loss": 0.0225, "step": 130500 }, { "epoch": 31.33, "learning_rate": 6.945290916722844e-05, "loss": 0.0373, "step": 130510 }, { "epoch": 31.34, "learning_rate": 6.944877563859335e-05, "loss": 0.0212, "step": 130520 }, { "epoch": 31.34, "learning_rate": 6.944464195333459e-05, "loss": 0.0221, "step": 130530 }, { "epoch": 31.34, "learning_rate": 6.944050811148544e-05, "loss": 0.0371, "step": 130540 }, { "epoch": 31.34, "learning_rate": 6.94363741130792e-05, "loss": 0.026, "step": 130550 }, { "epoch": 31.34, "learning_rate": 6.943223995814913e-05, "loss": 0.0294, "step": 130560 }, { "epoch": 31.35, "learning_rate": 6.942810564672858e-05, "loss": 0.0544, "step": 130570 }, { "epoch": 31.35, "learning_rate": 6.942397117885082e-05, "loss": 0.0162, "step": 130580 }, { "epoch": 31.35, "learning_rate": 6.941983655454911e-05, "loss": 0.0717, "step": 130590 }, { "epoch": 31.35, "learning_rate": 6.941570177385678e-05, "loss": 0.0284, "step": 130600 }, { "epoch": 31.36, "learning_rate": 6.941156683680714e-05, "loss": 0.0229, "step": 130610 }, { "epoch": 31.36, "learning_rate": 6.940743174343345e-05, "loss": 0.0282, "step": 130620 }, { "epoch": 31.36, "learning_rate": 6.940329649376904e-05, "loss": 0.0354, "step": 130630 }, { "epoch": 31.36, "learning_rate": 6.939916108784722e-05, "loss": 0.0325, "step": 130640 }, { "epoch": 31.36, "learning_rate": 6.939502552570127e-05, "loss": 0.0255, "step": 130650 }, { "epoch": 31.37, "learning_rate": 6.939088980736451e-05, "loss": 0.0316, "step": 130660 }, { "epoch": 31.37, "learning_rate": 6.938675393287023e-05, "loss": 0.0173, "step": 130670 }, { "epoch": 31.37, "learning_rate": 6.938261790225174e-05, "loss": 0.0296, "step": 130680 }, { "epoch": 31.37, "learning_rate": 6.937848171554233e-05, "loss": 0.0283, "step": 130690 }, { "epoch": 31.38, "learning_rate": 6.937434537277536e-05, "loss": 0.0217, "step": 130700 }, { "epoch": 31.38, "learning_rate": 6.937020887398412e-05, "loss": 0.0313, "step": 130710 }, { "epoch": 31.38, "learning_rate": 6.936607221920188e-05, "loss": 0.031, "step": 130720 }, { "epoch": 31.38, "learning_rate": 6.936193540846201e-05, "loss": 0.0249, "step": 130730 }, { "epoch": 31.39, "learning_rate": 6.935779844179779e-05, "loss": 0.0288, "step": 130740 }, { "epoch": 31.39, "learning_rate": 6.935366131924257e-05, "loss": 0.055, "step": 130750 }, { "epoch": 31.39, "learning_rate": 6.934952404082961e-05, "loss": 0.0392, "step": 130760 }, { "epoch": 31.39, "learning_rate": 6.934538660659229e-05, "loss": 0.0249, "step": 130770 }, { "epoch": 31.39, "learning_rate": 6.934124901656389e-05, "loss": 0.037, "step": 130780 }, { "epoch": 31.4, "learning_rate": 6.933711127077774e-05, "loss": 0.0392, "step": 130790 }, { "epoch": 31.4, "learning_rate": 6.933297336926717e-05, "loss": 0.0247, "step": 130800 }, { "epoch": 31.4, "learning_rate": 6.932883531206547e-05, "loss": 0.0498, "step": 130810 }, { "epoch": 31.4, "learning_rate": 6.932469709920601e-05, "loss": 0.0394, "step": 130820 }, { "epoch": 31.41, "learning_rate": 6.932055873072211e-05, "loss": 0.0276, "step": 130830 }, { "epoch": 31.41, "learning_rate": 6.931642020664706e-05, "loss": 0.0464, "step": 130840 }, { "epoch": 31.41, "learning_rate": 6.931228152701423e-05, "loss": 0.0307, "step": 130850 }, { "epoch": 31.41, "learning_rate": 6.930814269185693e-05, "loss": 0.041, "step": 130860 }, { "epoch": 31.42, "learning_rate": 6.930400370120849e-05, "loss": 0.0292, "step": 130870 }, { "epoch": 31.42, "learning_rate": 6.929986455510222e-05, "loss": 0.0428, "step": 130880 }, { "epoch": 31.42, "learning_rate": 6.929572525357149e-05, "loss": 0.0573, "step": 130890 }, { "epoch": 31.42, "learning_rate": 6.929158579664964e-05, "loss": 0.0377, "step": 130900 }, { "epoch": 31.42, "learning_rate": 6.928744618436996e-05, "loss": 0.091, "step": 130910 }, { "epoch": 31.43, "learning_rate": 6.928330641676584e-05, "loss": 0.0286, "step": 130920 }, { "epoch": 31.43, "learning_rate": 6.927916649387057e-05, "loss": 0.0237, "step": 130930 }, { "epoch": 31.43, "learning_rate": 6.927502641571752e-05, "loss": 0.0378, "step": 130940 }, { "epoch": 31.43, "learning_rate": 6.927088618234e-05, "loss": 0.0321, "step": 130950 }, { "epoch": 31.44, "learning_rate": 6.92667457937714e-05, "loss": 0.0304, "step": 130960 }, { "epoch": 31.44, "learning_rate": 6.926260525004502e-05, "loss": 0.0314, "step": 130970 }, { "epoch": 31.44, "learning_rate": 6.925846455119422e-05, "loss": 0.0386, "step": 130980 }, { "epoch": 31.44, "learning_rate": 6.925432369725235e-05, "loss": 0.0315, "step": 130990 }, { "epoch": 31.44, "learning_rate": 6.925018268825277e-05, "loss": 0.0257, "step": 131000 }, { "epoch": 31.45, "learning_rate": 6.92460415242288e-05, "loss": 0.0355, "step": 131010 }, { "epoch": 31.45, "learning_rate": 6.924190020521378e-05, "loss": 0.0318, "step": 131020 }, { "epoch": 31.45, "learning_rate": 6.92377587312411e-05, "loss": 0.0107, "step": 131030 }, { "epoch": 31.45, "learning_rate": 6.92336171023441e-05, "loss": 0.0243, "step": 131040 }, { "epoch": 31.46, "learning_rate": 6.92294753185561e-05, "loss": 0.0582, "step": 131050 }, { "epoch": 31.46, "learning_rate": 6.922533337991051e-05, "loss": 0.0339, "step": 131060 }, { "epoch": 31.46, "learning_rate": 6.922119128644065e-05, "loss": 0.0403, "step": 131070 }, { "epoch": 31.46, "learning_rate": 6.921704903817989e-05, "loss": 0.0537, "step": 131080 }, { "epoch": 31.47, "learning_rate": 6.921290663516155e-05, "loss": 0.0648, "step": 131090 }, { "epoch": 31.47, "learning_rate": 6.920876407741903e-05, "loss": 0.0329, "step": 131100 }, { "epoch": 31.47, "learning_rate": 6.92046213649857e-05, "loss": 0.0242, "step": 131110 }, { "epoch": 31.47, "learning_rate": 6.920047849789489e-05, "loss": 0.0527, "step": 131120 }, { "epoch": 31.47, "learning_rate": 6.919633547617999e-05, "loss": 0.0317, "step": 131130 }, { "epoch": 31.48, "learning_rate": 6.919219229987433e-05, "loss": 0.0397, "step": 131140 }, { "epoch": 31.48, "learning_rate": 6.91880489690113e-05, "loss": 0.0307, "step": 131150 }, { "epoch": 31.48, "learning_rate": 6.918390548362426e-05, "loss": 0.0358, "step": 131160 }, { "epoch": 31.48, "learning_rate": 6.917976184374659e-05, "loss": 0.0201, "step": 131170 }, { "epoch": 31.49, "learning_rate": 6.917561804941164e-05, "loss": 0.0511, "step": 131180 }, { "epoch": 31.49, "learning_rate": 6.91714741006528e-05, "loss": 0.0298, "step": 131190 }, { "epoch": 31.49, "learning_rate": 6.916732999750344e-05, "loss": 0.0296, "step": 131200 }, { "epoch": 31.49, "learning_rate": 6.916318573999691e-05, "loss": 0.0227, "step": 131210 }, { "epoch": 31.5, "learning_rate": 6.915904132816659e-05, "loss": 0.0606, "step": 131220 }, { "epoch": 31.5, "learning_rate": 6.91548967620459e-05, "loss": 0.026, "step": 131230 }, { "epoch": 31.5, "learning_rate": 6.915075204166814e-05, "loss": 0.0317, "step": 131240 }, { "epoch": 31.5, "learning_rate": 6.914660716706676e-05, "loss": 0.0428, "step": 131250 }, { "epoch": 31.5, "learning_rate": 6.91424621382751e-05, "loss": 0.0386, "step": 131260 }, { "epoch": 31.51, "learning_rate": 6.913831695532656e-05, "loss": 0.0252, "step": 131270 }, { "epoch": 31.51, "learning_rate": 6.91341716182545e-05, "loss": 0.0558, "step": 131280 }, { "epoch": 31.51, "learning_rate": 6.913002612709232e-05, "loss": 0.0333, "step": 131290 }, { "epoch": 31.51, "learning_rate": 6.912588048187338e-05, "loss": 0.0314, "step": 131300 }, { "epoch": 31.52, "learning_rate": 6.91217346826311e-05, "loss": 0.0322, "step": 131310 }, { "epoch": 31.52, "learning_rate": 6.911758872939886e-05, "loss": 0.0558, "step": 131320 }, { "epoch": 31.52, "learning_rate": 6.911344262221002e-05, "loss": 0.0383, "step": 131330 }, { "epoch": 31.52, "learning_rate": 6.9109296361098e-05, "loss": 0.037, "step": 131340 }, { "epoch": 31.52, "learning_rate": 6.910514994609617e-05, "loss": 0.0275, "step": 131350 }, { "epoch": 31.53, "learning_rate": 6.910100337723793e-05, "loss": 0.036, "step": 131360 }, { "epoch": 31.53, "learning_rate": 6.909685665455668e-05, "loss": 0.0325, "step": 131370 }, { "epoch": 31.53, "learning_rate": 6.90927097780858e-05, "loss": 0.0447, "step": 131380 }, { "epoch": 31.53, "learning_rate": 6.90885627478587e-05, "loss": 0.0468, "step": 131390 }, { "epoch": 31.54, "learning_rate": 6.908441556390876e-05, "loss": 0.0538, "step": 131400 }, { "epoch": 31.54, "learning_rate": 6.908026822626938e-05, "loss": 0.0499, "step": 131410 }, { "epoch": 31.54, "learning_rate": 6.907612073497398e-05, "loss": 0.0213, "step": 131420 }, { "epoch": 31.54, "learning_rate": 6.907197309005594e-05, "loss": 0.0338, "step": 131430 }, { "epoch": 31.55, "learning_rate": 6.906782529154868e-05, "loss": 0.0482, "step": 131440 }, { "epoch": 31.55, "learning_rate": 6.906367733948558e-05, "loss": 0.0402, "step": 131450 }, { "epoch": 31.55, "learning_rate": 6.905952923390006e-05, "loss": 0.0354, "step": 131460 }, { "epoch": 31.55, "learning_rate": 6.905538097482551e-05, "loss": 0.04, "step": 131470 }, { "epoch": 31.55, "learning_rate": 6.905123256229535e-05, "loss": 0.0253, "step": 131480 }, { "epoch": 31.56, "learning_rate": 6.904708399634298e-05, "loss": 0.0347, "step": 131490 }, { "epoch": 31.56, "learning_rate": 6.904293527700182e-05, "loss": 0.0812, "step": 131500 }, { "epoch": 31.56, "learning_rate": 6.903878640430528e-05, "loss": 0.0362, "step": 131510 }, { "epoch": 31.56, "learning_rate": 6.903463737828675e-05, "loss": 0.0477, "step": 131520 }, { "epoch": 31.57, "learning_rate": 6.903048819897966e-05, "loss": 0.0531, "step": 131530 }, { "epoch": 31.57, "learning_rate": 6.902633886641743e-05, "loss": 0.0275, "step": 131540 }, { "epoch": 31.57, "learning_rate": 6.902218938063345e-05, "loss": 0.061, "step": 131550 }, { "epoch": 31.57, "learning_rate": 6.901803974166118e-05, "loss": 0.0236, "step": 131560 }, { "epoch": 31.58, "learning_rate": 6.901388994953399e-05, "loss": 0.0435, "step": 131570 }, { "epoch": 31.58, "learning_rate": 6.900974000428532e-05, "loss": 0.0284, "step": 131580 }, { "epoch": 31.58, "learning_rate": 6.900558990594859e-05, "loss": 0.0263, "step": 131590 }, { "epoch": 31.58, "learning_rate": 6.900143965455723e-05, "loss": 0.0223, "step": 131600 }, { "epoch": 31.58, "learning_rate": 6.899728925014465e-05, "loss": 0.0357, "step": 131610 }, { "epoch": 31.59, "learning_rate": 6.899313869274427e-05, "loss": 0.0465, "step": 131620 }, { "epoch": 31.59, "learning_rate": 6.898898798238953e-05, "loss": 0.0366, "step": 131630 }, { "epoch": 31.59, "learning_rate": 6.898483711911383e-05, "loss": 0.0383, "step": 131640 }, { "epoch": 31.59, "learning_rate": 6.898068610295064e-05, "loss": 0.0387, "step": 131650 }, { "epoch": 31.6, "learning_rate": 6.897653493393334e-05, "loss": 0.0309, "step": 131660 }, { "epoch": 31.6, "learning_rate": 6.897238361209541e-05, "loss": 0.0427, "step": 131670 }, { "epoch": 31.6, "learning_rate": 6.896823213747024e-05, "loss": 0.0351, "step": 131680 }, { "epoch": 31.6, "learning_rate": 6.896408051009127e-05, "loss": 0.0209, "step": 131690 }, { "epoch": 31.6, "learning_rate": 6.895992872999195e-05, "loss": 0.0535, "step": 131700 }, { "epoch": 31.61, "learning_rate": 6.895577679720572e-05, "loss": 0.0591, "step": 131710 }, { "epoch": 31.61, "learning_rate": 6.8951624711766e-05, "loss": 0.0257, "step": 131720 }, { "epoch": 31.61, "learning_rate": 6.894747247370621e-05, "loss": 0.0326, "step": 131730 }, { "epoch": 31.61, "learning_rate": 6.894332008305982e-05, "loss": 0.0464, "step": 131740 }, { "epoch": 31.62, "learning_rate": 6.893916753986027e-05, "loss": 0.0651, "step": 131750 }, { "epoch": 31.62, "learning_rate": 6.893501484414096e-05, "loss": 0.0391, "step": 131760 }, { "epoch": 31.62, "learning_rate": 6.893086199593538e-05, "loss": 0.0312, "step": 131770 }, { "epoch": 31.62, "learning_rate": 6.892670899527695e-05, "loss": 0.044, "step": 131780 }, { "epoch": 31.63, "learning_rate": 6.892255584219913e-05, "loss": 0.0481, "step": 131790 }, { "epoch": 31.63, "learning_rate": 6.891840253673536e-05, "loss": 0.0295, "step": 131800 }, { "epoch": 31.63, "learning_rate": 6.891424907891904e-05, "loss": 0.039, "step": 131810 }, { "epoch": 31.63, "learning_rate": 6.89100954687837e-05, "loss": 0.044, "step": 131820 }, { "epoch": 31.63, "learning_rate": 6.890594170636274e-05, "loss": 0.045, "step": 131830 }, { "epoch": 31.64, "learning_rate": 6.890178779168963e-05, "loss": 0.0164, "step": 131840 }, { "epoch": 31.64, "learning_rate": 6.88976337247978e-05, "loss": 0.0455, "step": 131850 }, { "epoch": 31.64, "learning_rate": 6.889347950572073e-05, "loss": 0.0499, "step": 131860 }, { "epoch": 31.64, "learning_rate": 6.888932513449185e-05, "loss": 0.0309, "step": 131870 }, { "epoch": 31.65, "learning_rate": 6.888517061114463e-05, "loss": 0.0344, "step": 131880 }, { "epoch": 31.65, "learning_rate": 6.888101593571253e-05, "loss": 0.0598, "step": 131890 }, { "epoch": 31.65, "learning_rate": 6.8876861108229e-05, "loss": 0.0478, "step": 131900 }, { "epoch": 31.65, "learning_rate": 6.88727061287275e-05, "loss": 0.0458, "step": 131910 }, { "epoch": 31.66, "learning_rate": 6.886855099724148e-05, "loss": 0.0409, "step": 131920 }, { "epoch": 31.66, "learning_rate": 6.886439571380443e-05, "loss": 0.0332, "step": 131930 }, { "epoch": 31.66, "learning_rate": 6.88602402784498e-05, "loss": 0.0159, "step": 131940 }, { "epoch": 31.66, "learning_rate": 6.885608469121101e-05, "loss": 0.0374, "step": 131950 }, { "epoch": 31.66, "learning_rate": 6.885192895212162e-05, "loss": 0.0407, "step": 131960 }, { "epoch": 31.67, "learning_rate": 6.884777306121502e-05, "loss": 0.0464, "step": 131970 }, { "epoch": 31.67, "learning_rate": 6.88436170185247e-05, "loss": 0.0339, "step": 131980 }, { "epoch": 31.67, "learning_rate": 6.883946082408413e-05, "loss": 0.0267, "step": 131990 }, { "epoch": 31.67, "learning_rate": 6.883530447792679e-05, "loss": 0.052, "step": 132000 }, { "epoch": 31.68, "learning_rate": 6.883114798008613e-05, "loss": 0.0399, "step": 132010 }, { "epoch": 31.68, "learning_rate": 6.882699133059565e-05, "loss": 0.0421, "step": 132020 }, { "epoch": 31.68, "learning_rate": 6.88228345294888e-05, "loss": 0.0602, "step": 132030 }, { "epoch": 31.68, "learning_rate": 6.881867757679908e-05, "loss": 0.0512, "step": 132040 }, { "epoch": 31.68, "learning_rate": 6.881452047255993e-05, "loss": 0.0336, "step": 132050 }, { "epoch": 31.69, "learning_rate": 6.881036321680486e-05, "loss": 0.0288, "step": 132060 }, { "epoch": 31.69, "learning_rate": 6.880620580956734e-05, "loss": 0.0394, "step": 132070 }, { "epoch": 31.69, "learning_rate": 6.880204825088084e-05, "loss": 0.0467, "step": 132080 }, { "epoch": 31.69, "learning_rate": 6.879789054077885e-05, "loss": 0.0572, "step": 132090 }, { "epoch": 31.7, "learning_rate": 6.879373267929486e-05, "loss": 0.0622, "step": 132100 }, { "epoch": 31.7, "learning_rate": 6.878957466646235e-05, "loss": 0.0395, "step": 132110 }, { "epoch": 31.7, "learning_rate": 6.878541650231479e-05, "loss": 0.041, "step": 132120 }, { "epoch": 31.7, "learning_rate": 6.878125818688568e-05, "loss": 0.0345, "step": 132130 }, { "epoch": 31.71, "learning_rate": 6.87770997202085e-05, "loss": 0.0409, "step": 132140 }, { "epoch": 31.71, "learning_rate": 6.877294110231676e-05, "loss": 0.0339, "step": 132150 }, { "epoch": 31.71, "learning_rate": 6.876878233324391e-05, "loss": 0.0323, "step": 132160 }, { "epoch": 31.71, "learning_rate": 6.876462341302348e-05, "loss": 0.0369, "step": 132170 }, { "epoch": 31.71, "learning_rate": 6.876046434168895e-05, "loss": 0.036, "step": 132180 }, { "epoch": 31.72, "learning_rate": 6.875630511927382e-05, "loss": 0.0207, "step": 132190 }, { "epoch": 31.72, "learning_rate": 6.875214574581155e-05, "loss": 0.0322, "step": 132200 }, { "epoch": 31.72, "learning_rate": 6.874798622133567e-05, "loss": 0.0322, "step": 132210 }, { "epoch": 31.72, "learning_rate": 6.874382654587966e-05, "loss": 0.0412, "step": 132220 }, { "epoch": 31.73, "learning_rate": 6.873966671947705e-05, "loss": 0.0296, "step": 132230 }, { "epoch": 31.73, "learning_rate": 6.87355067421613e-05, "loss": 0.0266, "step": 132240 }, { "epoch": 31.73, "learning_rate": 6.873134661396594e-05, "loss": 0.0442, "step": 132250 }, { "epoch": 31.73, "learning_rate": 6.872718633492445e-05, "loss": 0.0439, "step": 132260 }, { "epoch": 31.74, "learning_rate": 6.872302590507034e-05, "loss": 0.0407, "step": 132270 }, { "epoch": 31.74, "learning_rate": 6.871886532443712e-05, "loss": 0.0491, "step": 132280 }, { "epoch": 31.74, "learning_rate": 6.87147045930583e-05, "loss": 0.0372, "step": 132290 }, { "epoch": 31.74, "learning_rate": 6.871054371096737e-05, "loss": 0.0245, "step": 132300 }, { "epoch": 31.74, "learning_rate": 6.870638267819786e-05, "loss": 0.042, "step": 132310 }, { "epoch": 31.75, "learning_rate": 6.870222149478326e-05, "loss": 0.0305, "step": 132320 }, { "epoch": 31.75, "learning_rate": 6.86980601607571e-05, "loss": 0.0474, "step": 132330 }, { "epoch": 31.75, "learning_rate": 6.869389867615286e-05, "loss": 0.0362, "step": 132340 }, { "epoch": 31.75, "learning_rate": 6.868973704100408e-05, "loss": 0.0428, "step": 132350 }, { "epoch": 31.76, "learning_rate": 6.868557525534428e-05, "loss": 0.0267, "step": 132360 }, { "epoch": 31.76, "learning_rate": 6.868141331920696e-05, "loss": 0.0294, "step": 132370 }, { "epoch": 31.76, "learning_rate": 6.867725123262563e-05, "loss": 0.0371, "step": 132380 }, { "epoch": 31.76, "learning_rate": 6.86730889956338e-05, "loss": 0.0489, "step": 132390 }, { "epoch": 31.76, "learning_rate": 6.866892660826505e-05, "loss": 0.0493, "step": 132400 }, { "epoch": 31.77, "learning_rate": 6.866476407055282e-05, "loss": 0.0331, "step": 132410 }, { "epoch": 31.77, "learning_rate": 6.866060138253068e-05, "loss": 0.0234, "step": 132420 }, { "epoch": 31.77, "learning_rate": 6.865643854423215e-05, "loss": 0.0394, "step": 132430 }, { "epoch": 31.77, "learning_rate": 6.865227555569073e-05, "loss": 0.0213, "step": 132440 }, { "epoch": 31.78, "learning_rate": 6.864811241693998e-05, "loss": 0.0542, "step": 132450 }, { "epoch": 31.78, "learning_rate": 6.864394912801338e-05, "loss": 0.0246, "step": 132460 }, { "epoch": 31.78, "learning_rate": 6.86397856889445e-05, "loss": 0.0187, "step": 132470 }, { "epoch": 31.78, "learning_rate": 6.863562209976685e-05, "loss": 0.0505, "step": 132480 }, { "epoch": 31.79, "learning_rate": 6.863145836051397e-05, "loss": 0.0196, "step": 132490 }, { "epoch": 31.79, "learning_rate": 6.862729447121937e-05, "loss": 0.0486, "step": 132500 }, { "epoch": 31.79, "learning_rate": 6.86231304319166e-05, "loss": 0.0272, "step": 132510 }, { "epoch": 31.79, "learning_rate": 6.861896624263919e-05, "loss": 0.0342, "step": 132520 }, { "epoch": 31.79, "learning_rate": 6.861480190342068e-05, "loss": 0.0311, "step": 132530 }, { "epoch": 31.8, "learning_rate": 6.861063741429459e-05, "loss": 0.0386, "step": 132540 }, { "epoch": 31.8, "learning_rate": 6.860647277529447e-05, "loss": 0.0173, "step": 132550 }, { "epoch": 31.8, "learning_rate": 6.860230798645386e-05, "loss": 0.0309, "step": 132560 }, { "epoch": 31.8, "learning_rate": 6.859814304780629e-05, "loss": 0.052, "step": 132570 }, { "epoch": 31.81, "learning_rate": 6.859397795938532e-05, "loss": 0.0282, "step": 132580 }, { "epoch": 31.81, "learning_rate": 6.858981272122448e-05, "loss": 0.0453, "step": 132590 }, { "epoch": 31.81, "learning_rate": 6.858564733335728e-05, "loss": 0.0353, "step": 132600 }, { "epoch": 31.81, "learning_rate": 6.858148179581733e-05, "loss": 0.031, "step": 132610 }, { "epoch": 31.82, "learning_rate": 6.857731610863813e-05, "loss": 0.0333, "step": 132620 }, { "epoch": 31.82, "learning_rate": 6.857315027185322e-05, "loss": 0.0267, "step": 132630 }, { "epoch": 31.82, "learning_rate": 6.85689842854962e-05, "loss": 0.0364, "step": 132640 }, { "epoch": 31.82, "learning_rate": 6.856481814960056e-05, "loss": 0.0227, "step": 132650 }, { "epoch": 31.82, "learning_rate": 6.856065186419989e-05, "loss": 0.0367, "step": 132660 }, { "epoch": 31.83, "learning_rate": 6.855648542932773e-05, "loss": 0.0286, "step": 132670 }, { "epoch": 31.83, "learning_rate": 6.855231884501761e-05, "loss": 0.0253, "step": 132680 }, { "epoch": 31.83, "learning_rate": 6.854815211130315e-05, "loss": 0.0283, "step": 132690 }, { "epoch": 31.83, "learning_rate": 6.854398522821781e-05, "loss": 0.0637, "step": 132700 }, { "epoch": 31.84, "learning_rate": 6.853981819579523e-05, "loss": 0.0273, "step": 132710 }, { "epoch": 31.84, "learning_rate": 6.853565101406891e-05, "loss": 0.0615, "step": 132720 }, { "epoch": 31.84, "learning_rate": 6.853148368307245e-05, "loss": 0.0316, "step": 132730 }, { "epoch": 31.84, "learning_rate": 6.852731620283939e-05, "loss": 0.0337, "step": 132740 }, { "epoch": 31.84, "learning_rate": 6.852314857340329e-05, "loss": 0.0237, "step": 132750 }, { "epoch": 31.85, "learning_rate": 6.851898079479772e-05, "loss": 0.0406, "step": 132760 }, { "epoch": 31.85, "learning_rate": 6.851481286705625e-05, "loss": 0.0402, "step": 132770 }, { "epoch": 31.85, "learning_rate": 6.851064479021243e-05, "loss": 0.0434, "step": 132780 }, { "epoch": 31.85, "learning_rate": 6.850647656429982e-05, "loss": 0.0443, "step": 132790 }, { "epoch": 31.86, "learning_rate": 6.850230818935201e-05, "loss": 0.0257, "step": 132800 }, { "epoch": 31.86, "learning_rate": 6.849813966540255e-05, "loss": 0.0331, "step": 132810 }, { "epoch": 31.86, "learning_rate": 6.849397099248502e-05, "loss": 0.0406, "step": 132820 }, { "epoch": 31.86, "learning_rate": 6.8489802170633e-05, "loss": 0.0255, "step": 132830 }, { "epoch": 31.87, "learning_rate": 6.848563319988005e-05, "loss": 0.0189, "step": 132840 }, { "epoch": 31.87, "learning_rate": 6.848146408025973e-05, "loss": 0.0285, "step": 132850 }, { "epoch": 31.87, "learning_rate": 6.847729481180565e-05, "loss": 0.0411, "step": 132860 }, { "epoch": 31.87, "learning_rate": 6.847312539455133e-05, "loss": 0.0304, "step": 132870 }, { "epoch": 31.87, "learning_rate": 6.846895582853042e-05, "loss": 0.028, "step": 132880 }, { "epoch": 31.88, "learning_rate": 6.846478611377642e-05, "loss": 0.04, "step": 132890 }, { "epoch": 31.88, "learning_rate": 6.846061625032298e-05, "loss": 0.024, "step": 132900 }, { "epoch": 31.88, "learning_rate": 6.845644623820363e-05, "loss": 0.0197, "step": 132910 }, { "epoch": 31.88, "learning_rate": 6.845227607745198e-05, "loss": 0.026, "step": 132920 }, { "epoch": 31.89, "learning_rate": 6.84481057681016e-05, "loss": 0.0259, "step": 132930 }, { "epoch": 31.89, "learning_rate": 6.844393531018607e-05, "loss": 0.0298, "step": 132940 }, { "epoch": 31.89, "learning_rate": 6.8439764703739e-05, "loss": 0.0271, "step": 132950 }, { "epoch": 31.89, "learning_rate": 6.843559394879395e-05, "loss": 0.0184, "step": 132960 }, { "epoch": 31.9, "learning_rate": 6.84314230453845e-05, "loss": 0.044, "step": 132970 }, { "epoch": 31.9, "learning_rate": 6.842725199354428e-05, "loss": 0.0432, "step": 132980 }, { "epoch": 31.9, "learning_rate": 6.842308079330685e-05, "loss": 0.036, "step": 132990 }, { "epoch": 31.9, "learning_rate": 6.84189094447058e-05, "loss": 0.0395, "step": 133000 }, { "epoch": 31.9, "learning_rate": 6.841473794777472e-05, "loss": 0.0247, "step": 133010 }, { "epoch": 31.91, "learning_rate": 6.841056630254725e-05, "loss": 0.0522, "step": 133020 }, { "epoch": 31.91, "learning_rate": 6.84063945090569e-05, "loss": 0.0276, "step": 133030 }, { "epoch": 31.91, "learning_rate": 6.840222256733735e-05, "loss": 0.0445, "step": 133040 }, { "epoch": 31.91, "learning_rate": 6.839805047742213e-05, "loss": 0.0396, "step": 133050 }, { "epoch": 31.92, "learning_rate": 6.839387823934489e-05, "loss": 0.0389, "step": 133060 }, { "epoch": 31.92, "learning_rate": 6.838970585313922e-05, "loss": 0.0402, "step": 133070 }, { "epoch": 31.92, "learning_rate": 6.83855333188387e-05, "loss": 0.045, "step": 133080 }, { "epoch": 31.92, "learning_rate": 6.838136063647693e-05, "loss": 0.0319, "step": 133090 }, { "epoch": 31.92, "learning_rate": 6.837718780608753e-05, "loss": 0.0449, "step": 133100 }, { "epoch": 31.93, "learning_rate": 6.83730148277041e-05, "loss": 0.0299, "step": 133110 }, { "epoch": 31.93, "learning_rate": 6.836884170136027e-05, "loss": 0.0418, "step": 133120 }, { "epoch": 31.93, "learning_rate": 6.836466842708958e-05, "loss": 0.0434, "step": 133130 }, { "epoch": 31.93, "learning_rate": 6.836049500492572e-05, "loss": 0.0455, "step": 133140 }, { "epoch": 31.94, "learning_rate": 6.835632143490222e-05, "loss": 0.0431, "step": 133150 }, { "epoch": 31.94, "learning_rate": 6.835214771705275e-05, "loss": 0.0194, "step": 133160 }, { "epoch": 31.94, "learning_rate": 6.83479738514109e-05, "loss": 0.034, "step": 133170 }, { "epoch": 31.94, "learning_rate": 6.83437998380103e-05, "loss": 0.0247, "step": 133180 }, { "epoch": 31.95, "learning_rate": 6.833962567688453e-05, "loss": 0.0676, "step": 133190 }, { "epoch": 31.95, "learning_rate": 6.83354513680672e-05, "loss": 0.0352, "step": 133200 }, { "epoch": 31.95, "learning_rate": 6.833127691159198e-05, "loss": 0.0329, "step": 133210 }, { "epoch": 32.0, "learning_rate": 6.832710230749245e-05, "loss": 0.0435, "step": 133220 }, { "epoch": 32.0, "learning_rate": 6.832292755580223e-05, "loss": 0.0354, "step": 133230 }, { "epoch": 32.01, "learning_rate": 6.831875265655494e-05, "loss": 0.0338, "step": 133240 }, { "epoch": 32.01, "learning_rate": 6.831457760978422e-05, "loss": 0.0319, "step": 133250 }, { "epoch": 32.01, "learning_rate": 6.831040241552366e-05, "loss": 0.0395, "step": 133260 }, { "epoch": 32.01, "learning_rate": 6.830622707380692e-05, "loss": 0.0295, "step": 133270 }, { "epoch": 32.01, "learning_rate": 6.830205158466759e-05, "loss": 0.0279, "step": 133280 }, { "epoch": 32.02, "learning_rate": 6.829787594813933e-05, "loss": 0.0354, "step": 133290 }, { "epoch": 32.02, "learning_rate": 6.829370016425573e-05, "loss": 0.0596, "step": 133300 }, { "epoch": 32.02, "learning_rate": 6.828952423305047e-05, "loss": 0.0361, "step": 133310 }, { "epoch": 32.02, "learning_rate": 6.82853481545571e-05, "loss": 0.0225, "step": 133320 }, { "epoch": 32.03, "learning_rate": 6.828117192880933e-05, "loss": 0.0515, "step": 133330 }, { "epoch": 32.03, "learning_rate": 6.827699555584074e-05, "loss": 0.0353, "step": 133340 }, { "epoch": 32.03, "learning_rate": 6.827281903568499e-05, "loss": 0.02, "step": 133350 }, { "epoch": 32.03, "learning_rate": 6.82686423683757e-05, "loss": 0.0422, "step": 133360 }, { "epoch": 32.04, "learning_rate": 6.826446555394652e-05, "loss": 0.0321, "step": 133370 }, { "epoch": 32.04, "learning_rate": 6.826028859243108e-05, "loss": 0.027, "step": 133380 }, { "epoch": 32.04, "learning_rate": 6.8256111483863e-05, "loss": 0.0455, "step": 133390 }, { "epoch": 32.04, "learning_rate": 6.825193422827594e-05, "loss": 0.0285, "step": 133400 }, { "epoch": 32.04, "learning_rate": 6.824775682570353e-05, "loss": 0.04, "step": 133410 }, { "epoch": 32.05, "learning_rate": 6.824357927617942e-05, "loss": 0.042, "step": 133420 }, { "epoch": 32.05, "learning_rate": 6.823940157973725e-05, "loss": 0.0234, "step": 133430 }, { "epoch": 32.05, "learning_rate": 6.823522373641066e-05, "loss": 0.0312, "step": 133440 }, { "epoch": 32.05, "learning_rate": 6.82310457462333e-05, "loss": 0.0305, "step": 133450 }, { "epoch": 32.06, "learning_rate": 6.82268676092388e-05, "loss": 0.0174, "step": 133460 }, { "epoch": 32.06, "learning_rate": 6.822268932546083e-05, "loss": 0.0292, "step": 133470 }, { "epoch": 32.06, "learning_rate": 6.821851089493302e-05, "loss": 0.0389, "step": 133480 }, { "epoch": 32.06, "learning_rate": 6.821433231768903e-05, "loss": 0.0386, "step": 133490 }, { "epoch": 32.06, "learning_rate": 6.82101535937625e-05, "loss": 0.0271, "step": 133500 }, { "epoch": 32.07, "learning_rate": 6.820597472318711e-05, "loss": 0.0369, "step": 133510 }, { "epoch": 32.07, "learning_rate": 6.820179570599646e-05, "loss": 0.0495, "step": 133520 }, { "epoch": 32.07, "learning_rate": 6.819761654222425e-05, "loss": 0.0235, "step": 133530 }, { "epoch": 32.07, "learning_rate": 6.819343723190413e-05, "loss": 0.0199, "step": 133540 }, { "epoch": 32.08, "learning_rate": 6.818925777506974e-05, "loss": 0.0266, "step": 133550 }, { "epoch": 32.08, "learning_rate": 6.818507817175475e-05, "loss": 0.0498, "step": 133560 }, { "epoch": 32.08, "learning_rate": 6.818089842199282e-05, "loss": 0.0286, "step": 133570 }, { "epoch": 32.08, "learning_rate": 6.817671852581761e-05, "loss": 0.0536, "step": 133580 }, { "epoch": 32.09, "learning_rate": 6.817253848326275e-05, "loss": 0.0429, "step": 133590 }, { "epoch": 32.09, "learning_rate": 6.816835829436194e-05, "loss": 0.0366, "step": 133600 }, { "epoch": 32.09, "learning_rate": 6.816417795914885e-05, "loss": 0.04, "step": 133610 }, { "epoch": 32.09, "learning_rate": 6.815999747765711e-05, "loss": 0.0288, "step": 133620 }, { "epoch": 32.09, "learning_rate": 6.81558168499204e-05, "loss": 0.0245, "step": 133630 }, { "epoch": 32.1, "learning_rate": 6.815163607597239e-05, "loss": 0.0243, "step": 133640 }, { "epoch": 32.1, "learning_rate": 6.814745515584678e-05, "loss": 0.019, "step": 133650 }, { "epoch": 32.1, "learning_rate": 6.814327408957717e-05, "loss": 0.0331, "step": 133660 }, { "epoch": 32.1, "learning_rate": 6.813909287719729e-05, "loss": 0.0201, "step": 133670 }, { "epoch": 32.11, "learning_rate": 6.813491151874077e-05, "loss": 0.0408, "step": 133680 }, { "epoch": 32.11, "learning_rate": 6.813073001424133e-05, "loss": 0.0415, "step": 133690 }, { "epoch": 32.11, "learning_rate": 6.81265483637326e-05, "loss": 0.0249, "step": 133700 }, { "epoch": 32.11, "learning_rate": 6.812236656724827e-05, "loss": 0.0292, "step": 133710 }, { "epoch": 32.12, "learning_rate": 6.811818462482204e-05, "loss": 0.0307, "step": 133720 }, { "epoch": 32.12, "learning_rate": 6.811400253648756e-05, "loss": 0.0206, "step": 133730 }, { "epoch": 32.12, "learning_rate": 6.81098203022785e-05, "loss": 0.0238, "step": 133740 }, { "epoch": 32.12, "learning_rate": 6.810563792222858e-05, "loss": 0.0301, "step": 133750 }, { "epoch": 32.12, "learning_rate": 6.810145539637145e-05, "loss": 0.0554, "step": 133760 }, { "epoch": 32.13, "learning_rate": 6.80972727247408e-05, "loss": 0.0319, "step": 133770 }, { "epoch": 32.13, "learning_rate": 6.809308990737031e-05, "loss": 0.0223, "step": 133780 }, { "epoch": 32.13, "learning_rate": 6.808890694429368e-05, "loss": 0.0311, "step": 133790 }, { "epoch": 32.13, "learning_rate": 6.808472383554457e-05, "loss": 0.0526, "step": 133800 }, { "epoch": 32.14, "learning_rate": 6.808054058115669e-05, "loss": 0.0354, "step": 133810 }, { "epoch": 32.14, "learning_rate": 6.807635718116372e-05, "loss": 0.0473, "step": 133820 }, { "epoch": 32.14, "learning_rate": 6.807217363559934e-05, "loss": 0.049, "step": 133830 }, { "epoch": 32.14, "learning_rate": 6.806798994449728e-05, "loss": 0.0304, "step": 133840 }, { "epoch": 32.14, "learning_rate": 6.806380610789117e-05, "loss": 0.032, "step": 133850 }, { "epoch": 32.15, "learning_rate": 6.805962212581477e-05, "loss": 0.0286, "step": 133860 }, { "epoch": 32.15, "learning_rate": 6.80554379983017e-05, "loss": 0.0203, "step": 133870 }, { "epoch": 32.15, "learning_rate": 6.805125372538572e-05, "loss": 0.0399, "step": 133880 }, { "epoch": 32.15, "learning_rate": 6.80470693071005e-05, "loss": 0.0391, "step": 133890 }, { "epoch": 32.16, "learning_rate": 6.804288474347973e-05, "loss": 0.0248, "step": 133900 }, { "epoch": 32.16, "learning_rate": 6.803870003455712e-05, "loss": 0.0218, "step": 133910 }, { "epoch": 32.16, "learning_rate": 6.803451518036636e-05, "loss": 0.0199, "step": 133920 }, { "epoch": 32.16, "learning_rate": 6.803033018094118e-05, "loss": 0.036, "step": 133930 }, { "epoch": 32.17, "learning_rate": 6.802614503631526e-05, "loss": 0.0295, "step": 133940 }, { "epoch": 32.17, "learning_rate": 6.802195974652228e-05, "loss": 0.0228, "step": 133950 }, { "epoch": 32.17, "learning_rate": 6.801777431159601e-05, "loss": 0.0198, "step": 133960 }, { "epoch": 32.17, "learning_rate": 6.801358873157007e-05, "loss": 0.0228, "step": 133970 }, { "epoch": 32.17, "learning_rate": 6.800940300647825e-05, "loss": 0.0292, "step": 133980 }, { "epoch": 32.18, "learning_rate": 6.800521713635421e-05, "loss": 0.016, "step": 133990 }, { "epoch": 32.18, "learning_rate": 6.800103112123168e-05, "loss": 0.0255, "step": 134000 }, { "epoch": 32.18, "learning_rate": 6.799684496114435e-05, "loss": 0.0433, "step": 134010 }, { "epoch": 32.18, "learning_rate": 6.799265865612593e-05, "loss": 0.0342, "step": 134020 }, { "epoch": 32.19, "learning_rate": 6.798847220621017e-05, "loss": 0.0517, "step": 134030 }, { "epoch": 32.19, "learning_rate": 6.798428561143074e-05, "loss": 0.0518, "step": 134040 }, { "epoch": 32.19, "learning_rate": 6.798009887182138e-05, "loss": 0.0335, "step": 134050 }, { "epoch": 32.19, "learning_rate": 6.79759119874158e-05, "loss": 0.0321, "step": 134060 }, { "epoch": 32.2, "learning_rate": 6.797172495824773e-05, "loss": 0.0243, "step": 134070 }, { "epoch": 32.2, "learning_rate": 6.796753778435087e-05, "loss": 0.0234, "step": 134080 }, { "epoch": 32.2, "learning_rate": 6.796335046575895e-05, "loss": 0.035, "step": 134090 }, { "epoch": 32.2, "learning_rate": 6.79591630025057e-05, "loss": 0.0301, "step": 134100 }, { "epoch": 32.2, "learning_rate": 6.79549753946248e-05, "loss": 0.0247, "step": 134110 }, { "epoch": 32.21, "learning_rate": 6.795078764215004e-05, "loss": 0.027, "step": 134120 }, { "epoch": 32.21, "learning_rate": 6.794659974511509e-05, "loss": 0.0275, "step": 134130 }, { "epoch": 32.21, "learning_rate": 6.794241170355369e-05, "loss": 0.0254, "step": 134140 }, { "epoch": 32.21, "learning_rate": 6.793822351749959e-05, "loss": 0.0484, "step": 134150 }, { "epoch": 32.22, "learning_rate": 6.793403518698648e-05, "loss": 0.0246, "step": 134160 }, { "epoch": 32.22, "learning_rate": 6.792984671204812e-05, "loss": 0.0461, "step": 134170 }, { "epoch": 32.22, "learning_rate": 6.792565809271823e-05, "loss": 0.0263, "step": 134180 }, { "epoch": 32.22, "learning_rate": 6.792146932903053e-05, "loss": 0.0514, "step": 134190 }, { "epoch": 32.22, "learning_rate": 6.791728042101877e-05, "loss": 0.0255, "step": 134200 }, { "epoch": 32.23, "learning_rate": 6.791309136871667e-05, "loss": 0.0264, "step": 134210 }, { "epoch": 32.23, "learning_rate": 6.7908902172158e-05, "loss": 0.035, "step": 134220 }, { "epoch": 32.23, "learning_rate": 6.790471283137642e-05, "loss": 0.0209, "step": 134230 }, { "epoch": 32.23, "learning_rate": 6.790052334640576e-05, "loss": 0.044, "step": 134240 }, { "epoch": 32.24, "learning_rate": 6.78963337172797e-05, "loss": 0.0418, "step": 134250 }, { "epoch": 32.24, "learning_rate": 6.789214394403197e-05, "loss": 0.0268, "step": 134260 }, { "epoch": 32.24, "learning_rate": 6.788795402669637e-05, "loss": 0.022, "step": 134270 }, { "epoch": 32.24, "learning_rate": 6.788376396530658e-05, "loss": 0.0381, "step": 134280 }, { "epoch": 32.25, "learning_rate": 6.78795737598964e-05, "loss": 0.0596, "step": 134290 }, { "epoch": 32.25, "learning_rate": 6.787538341049951e-05, "loss": 0.0347, "step": 134300 }, { "epoch": 32.25, "learning_rate": 6.787119291714972e-05, "loss": 0.0241, "step": 134310 }, { "epoch": 32.25, "learning_rate": 6.786700227988072e-05, "loss": 0.0386, "step": 134320 }, { "epoch": 32.25, "learning_rate": 6.78628114987263e-05, "loss": 0.0359, "step": 134330 }, { "epoch": 32.26, "learning_rate": 6.785862057372019e-05, "loss": 0.0466, "step": 134340 }, { "epoch": 32.26, "learning_rate": 6.785442950489613e-05, "loss": 0.0511, "step": 134350 }, { "epoch": 32.26, "learning_rate": 6.78502382922879e-05, "loss": 0.0353, "step": 134360 }, { "epoch": 32.26, "learning_rate": 6.784604693592924e-05, "loss": 0.0338, "step": 134370 }, { "epoch": 32.27, "learning_rate": 6.784185543585388e-05, "loss": 0.0272, "step": 134380 }, { "epoch": 32.27, "learning_rate": 6.783766379209561e-05, "loss": 0.0452, "step": 134390 }, { "epoch": 32.27, "learning_rate": 6.783347200468817e-05, "loss": 0.025, "step": 134400 }, { "epoch": 32.27, "learning_rate": 6.782928007366534e-05, "loss": 0.032, "step": 134410 }, { "epoch": 32.28, "learning_rate": 6.78250879990608e-05, "loss": 0.0387, "step": 134420 }, { "epoch": 32.28, "learning_rate": 6.78208957809084e-05, "loss": 0.031, "step": 134430 }, { "epoch": 32.28, "learning_rate": 6.781670341924188e-05, "loss": 0.0324, "step": 134440 }, { "epoch": 32.28, "learning_rate": 6.781251091409496e-05, "loss": 0.0373, "step": 134450 }, { "epoch": 32.28, "learning_rate": 6.780831826550146e-05, "loss": 0.0346, "step": 134460 }, { "epoch": 32.29, "learning_rate": 6.780412547349508e-05, "loss": 0.0345, "step": 134470 }, { "epoch": 32.29, "learning_rate": 6.779993253810963e-05, "loss": 0.0399, "step": 134480 }, { "epoch": 32.29, "learning_rate": 6.779573945937889e-05, "loss": 0.0323, "step": 134490 }, { "epoch": 32.29, "learning_rate": 6.779154623733657e-05, "loss": 0.0162, "step": 134500 }, { "epoch": 32.3, "learning_rate": 6.77873528720165e-05, "loss": 0.0353, "step": 134510 }, { "epoch": 32.3, "learning_rate": 6.778315936345239e-05, "loss": 0.0368, "step": 134520 }, { "epoch": 32.3, "learning_rate": 6.777896571167808e-05, "loss": 0.0183, "step": 134530 }, { "epoch": 32.3, "learning_rate": 6.777477191672728e-05, "loss": 0.027, "step": 134540 }, { "epoch": 32.3, "learning_rate": 6.77705779786338e-05, "loss": 0.023, "step": 134550 }, { "epoch": 32.31, "learning_rate": 6.77663838974314e-05, "loss": 0.0313, "step": 134560 }, { "epoch": 32.31, "learning_rate": 6.776218967315384e-05, "loss": 0.0438, "step": 134570 }, { "epoch": 32.31, "learning_rate": 6.775799530583494e-05, "loss": 0.0245, "step": 134580 }, { "epoch": 32.31, "learning_rate": 6.775380079550842e-05, "loss": 0.0408, "step": 134590 }, { "epoch": 32.32, "learning_rate": 6.774960614220813e-05, "loss": 0.0326, "step": 134600 }, { "epoch": 32.32, "learning_rate": 6.774541134596778e-05, "loss": 0.042, "step": 134610 }, { "epoch": 32.32, "learning_rate": 6.77412164068212e-05, "loss": 0.0341, "step": 134620 }, { "epoch": 32.32, "learning_rate": 6.773702132480215e-05, "loss": 0.0248, "step": 134630 }, { "epoch": 32.33, "learning_rate": 6.773282609994443e-05, "loss": 0.0429, "step": 134640 }, { "epoch": 32.33, "learning_rate": 6.772863073228179e-05, "loss": 0.0151, "step": 134650 }, { "epoch": 32.33, "learning_rate": 6.772443522184804e-05, "loss": 0.0336, "step": 134660 }, { "epoch": 32.33, "learning_rate": 6.772023956867698e-05, "loss": 0.0354, "step": 134670 }, { "epoch": 32.33, "learning_rate": 6.771604377280239e-05, "loss": 0.0275, "step": 134680 }, { "epoch": 32.34, "learning_rate": 6.771184783425803e-05, "loss": 0.0239, "step": 134690 }, { "epoch": 32.34, "learning_rate": 6.770765175307774e-05, "loss": 0.028, "step": 134700 }, { "epoch": 32.34, "learning_rate": 6.770345552929527e-05, "loss": 0.0396, "step": 134710 }, { "epoch": 32.34, "learning_rate": 6.769925916294444e-05, "loss": 0.0201, "step": 134720 }, { "epoch": 32.35, "learning_rate": 6.769506265405902e-05, "loss": 0.0225, "step": 134730 }, { "epoch": 32.35, "learning_rate": 6.769086600267282e-05, "loss": 0.0243, "step": 134740 }, { "epoch": 32.35, "learning_rate": 6.768666920881964e-05, "loss": 0.0344, "step": 134750 }, { "epoch": 32.35, "learning_rate": 6.768247227253328e-05, "loss": 0.0306, "step": 134760 }, { "epoch": 32.36, "learning_rate": 6.767827519384751e-05, "loss": 0.0281, "step": 134770 }, { "epoch": 32.36, "learning_rate": 6.767407797279615e-05, "loss": 0.0268, "step": 134780 }, { "epoch": 32.36, "learning_rate": 6.7669880609413e-05, "loss": 0.0243, "step": 134790 }, { "epoch": 32.36, "learning_rate": 6.766568310373187e-05, "loss": 0.0309, "step": 134800 }, { "epoch": 32.36, "learning_rate": 6.766148545578656e-05, "loss": 0.0228, "step": 134810 }, { "epoch": 32.37, "learning_rate": 6.765728766561086e-05, "loss": 0.0518, "step": 134820 }, { "epoch": 32.37, "learning_rate": 6.765308973323859e-05, "loss": 0.0267, "step": 134830 }, { "epoch": 32.37, "learning_rate": 6.764889165870355e-05, "loss": 0.0372, "step": 134840 }, { "epoch": 32.37, "learning_rate": 6.764469344203954e-05, "loss": 0.0183, "step": 134850 }, { "epoch": 32.38, "learning_rate": 6.764049508328038e-05, "loss": 0.0387, "step": 134860 }, { "epoch": 32.38, "learning_rate": 6.763629658245989e-05, "loss": 0.0268, "step": 134870 }, { "epoch": 32.38, "learning_rate": 6.763209793961187e-05, "loss": 0.0257, "step": 134880 }, { "epoch": 32.38, "learning_rate": 6.762789915477013e-05, "loss": 0.0311, "step": 134890 }, { "epoch": 32.38, "learning_rate": 6.762370022796846e-05, "loss": 0.0252, "step": 134900 }, { "epoch": 32.39, "learning_rate": 6.761950115924071e-05, "loss": 0.0463, "step": 134910 }, { "epoch": 32.39, "learning_rate": 6.76153019486207e-05, "loss": 0.0322, "step": 134920 }, { "epoch": 32.39, "learning_rate": 6.761110259614223e-05, "loss": 0.0419, "step": 134930 }, { "epoch": 32.39, "learning_rate": 6.760690310183911e-05, "loss": 0.0263, "step": 134940 }, { "epoch": 32.4, "learning_rate": 6.760270346574516e-05, "loss": 0.0212, "step": 134950 }, { "epoch": 32.4, "learning_rate": 6.759850368789424e-05, "loss": 0.0709, "step": 134960 }, { "epoch": 32.4, "learning_rate": 6.759430376832011e-05, "loss": 0.0277, "step": 134970 }, { "epoch": 32.4, "learning_rate": 6.759010370705662e-05, "loss": 0.024, "step": 134980 }, { "epoch": 32.41, "learning_rate": 6.758590350413762e-05, "loss": 0.0312, "step": 134990 }, { "epoch": 32.41, "learning_rate": 6.758170315959689e-05, "loss": 0.0273, "step": 135000 }, { "epoch": 32.41, "learning_rate": 6.75775026734683e-05, "loss": 0.0249, "step": 135010 }, { "epoch": 32.41, "learning_rate": 6.757330204578564e-05, "loss": 0.0255, "step": 135020 }, { "epoch": 32.41, "learning_rate": 6.756910127658273e-05, "loss": 0.0238, "step": 135030 }, { "epoch": 32.42, "learning_rate": 6.756490036589346e-05, "loss": 0.0325, "step": 135040 }, { "epoch": 32.42, "learning_rate": 6.756069931375161e-05, "loss": 0.0454, "step": 135050 }, { "epoch": 32.42, "learning_rate": 6.755649812019102e-05, "loss": 0.0199, "step": 135060 }, { "epoch": 32.42, "learning_rate": 6.755229678524553e-05, "loss": 0.0441, "step": 135070 }, { "epoch": 32.43, "learning_rate": 6.754809530894896e-05, "loss": 0.0435, "step": 135080 }, { "epoch": 32.43, "learning_rate": 6.754389369133518e-05, "loss": 0.0195, "step": 135090 }, { "epoch": 32.43, "learning_rate": 6.753969193243797e-05, "loss": 0.027, "step": 135100 }, { "epoch": 32.43, "learning_rate": 6.753549003229123e-05, "loss": 0.0267, "step": 135110 }, { "epoch": 32.44, "learning_rate": 6.753128799092875e-05, "loss": 0.0188, "step": 135120 }, { "epoch": 32.44, "learning_rate": 6.75270858083844e-05, "loss": 0.0448, "step": 135130 }, { "epoch": 32.44, "learning_rate": 6.752288348469199e-05, "loss": 0.0296, "step": 135140 }, { "epoch": 32.44, "learning_rate": 6.751868101988538e-05, "loss": 0.0336, "step": 135150 }, { "epoch": 32.44, "learning_rate": 6.751447841399844e-05, "loss": 0.0241, "step": 135160 }, { "epoch": 32.45, "learning_rate": 6.751027566706496e-05, "loss": 0.0178, "step": 135170 }, { "epoch": 32.45, "learning_rate": 6.750607277911882e-05, "loss": 0.0456, "step": 135180 }, { "epoch": 32.45, "learning_rate": 6.750186975019387e-05, "loss": 0.0243, "step": 135190 }, { "epoch": 32.45, "learning_rate": 6.749766658032393e-05, "loss": 0.0234, "step": 135200 }, { "epoch": 32.46, "learning_rate": 6.749346326954288e-05, "loss": 0.0284, "step": 135210 }, { "epoch": 32.46, "learning_rate": 6.748925981788454e-05, "loss": 0.0269, "step": 135220 }, { "epoch": 32.46, "learning_rate": 6.74850562253828e-05, "loss": 0.0187, "step": 135230 }, { "epoch": 32.46, "learning_rate": 6.748085249207147e-05, "loss": 0.0347, "step": 135240 }, { "epoch": 32.46, "learning_rate": 6.747664861798443e-05, "loss": 0.0341, "step": 135250 }, { "epoch": 32.47, "learning_rate": 6.747244460315551e-05, "loss": 0.0311, "step": 135260 }, { "epoch": 32.47, "learning_rate": 6.74682404476186e-05, "loss": 0.0317, "step": 135270 }, { "epoch": 32.47, "learning_rate": 6.746403615140753e-05, "loss": 0.027, "step": 135280 }, { "epoch": 32.47, "learning_rate": 6.745983171455616e-05, "loss": 0.0327, "step": 135290 }, { "epoch": 32.48, "learning_rate": 6.745562713709838e-05, "loss": 0.0301, "step": 135300 }, { "epoch": 32.48, "learning_rate": 6.745142241906799e-05, "loss": 0.0186, "step": 135310 }, { "epoch": 32.48, "learning_rate": 6.744721756049889e-05, "loss": 0.0401, "step": 135320 }, { "epoch": 32.48, "learning_rate": 6.744301256142496e-05, "loss": 0.0179, "step": 135330 }, { "epoch": 32.49, "learning_rate": 6.743880742188002e-05, "loss": 0.0407, "step": 135340 }, { "epoch": 32.49, "learning_rate": 6.743460214189798e-05, "loss": 0.0273, "step": 135350 }, { "epoch": 32.49, "learning_rate": 6.743039672151267e-05, "loss": 0.038, "step": 135360 }, { "epoch": 32.49, "learning_rate": 6.742619116075797e-05, "loss": 0.0289, "step": 135370 }, { "epoch": 32.49, "learning_rate": 6.742198545966774e-05, "loss": 0.0468, "step": 135380 }, { "epoch": 32.5, "learning_rate": 6.741777961827587e-05, "loss": 0.0259, "step": 135390 }, { "epoch": 32.5, "learning_rate": 6.741357363661621e-05, "loss": 0.0319, "step": 135400 }, { "epoch": 32.5, "learning_rate": 6.740936751472263e-05, "loss": 0.035, "step": 135410 }, { "epoch": 32.5, "learning_rate": 6.740516125262903e-05, "loss": 0.0705, "step": 135420 }, { "epoch": 32.51, "learning_rate": 6.740095485036924e-05, "loss": 0.0241, "step": 135430 }, { "epoch": 32.51, "learning_rate": 6.739674830797715e-05, "loss": 0.0296, "step": 135440 }, { "epoch": 32.51, "learning_rate": 6.739254162548667e-05, "loss": 0.0439, "step": 135450 }, { "epoch": 32.51, "learning_rate": 6.738833480293163e-05, "loss": 0.0195, "step": 135460 }, { "epoch": 32.52, "learning_rate": 6.738412784034595e-05, "loss": 0.0659, "step": 135470 }, { "epoch": 32.52, "learning_rate": 6.737992073776348e-05, "loss": 0.0347, "step": 135480 }, { "epoch": 32.52, "learning_rate": 6.737571349521812e-05, "loss": 0.0276, "step": 135490 }, { "epoch": 32.52, "learning_rate": 6.737150611274372e-05, "loss": 0.0328, "step": 135500 }, { "epoch": 32.52, "learning_rate": 6.736729859037418e-05, "loss": 0.0291, "step": 135510 }, { "epoch": 32.53, "learning_rate": 6.736309092814342e-05, "loss": 0.0217, "step": 135520 }, { "epoch": 32.53, "learning_rate": 6.735888312608524e-05, "loss": 0.044, "step": 135530 }, { "epoch": 32.53, "learning_rate": 6.735467518423363e-05, "loss": 0.0463, "step": 135540 }, { "epoch": 32.53, "learning_rate": 6.73504671026224e-05, "loss": 0.0492, "step": 135550 }, { "epoch": 32.54, "learning_rate": 6.734625888128546e-05, "loss": 0.0331, "step": 135560 }, { "epoch": 32.54, "learning_rate": 6.73420505202567e-05, "loss": 0.0321, "step": 135570 }, { "epoch": 32.54, "learning_rate": 6.733784201957003e-05, "loss": 0.0237, "step": 135580 }, { "epoch": 32.54, "learning_rate": 6.733363337925932e-05, "loss": 0.0248, "step": 135590 }, { "epoch": 32.54, "learning_rate": 6.732942459935845e-05, "loss": 0.0319, "step": 135600 }, { "epoch": 32.55, "learning_rate": 6.732521567990136e-05, "loss": 0.0346, "step": 135610 }, { "epoch": 32.55, "learning_rate": 6.732100662092188e-05, "loss": 0.0568, "step": 135620 }, { "epoch": 32.55, "learning_rate": 6.731679742245397e-05, "loss": 0.0335, "step": 135630 }, { "epoch": 32.55, "learning_rate": 6.731258808453149e-05, "loss": 0.0306, "step": 135640 }, { "epoch": 32.56, "learning_rate": 6.730837860718835e-05, "loss": 0.0401, "step": 135650 }, { "epoch": 32.56, "learning_rate": 6.730416899045846e-05, "loss": 0.0896, "step": 135660 }, { "epoch": 32.56, "learning_rate": 6.729995923437568e-05, "loss": 0.0363, "step": 135670 }, { "epoch": 32.56, "learning_rate": 6.729574933897397e-05, "loss": 0.0482, "step": 135680 }, { "epoch": 32.57, "learning_rate": 6.729153930428717e-05, "loss": 0.025, "step": 135690 }, { "epoch": 32.57, "learning_rate": 6.728732913034926e-05, "loss": 0.0592, "step": 135700 }, { "epoch": 32.57, "learning_rate": 6.728311881719407e-05, "loss": 0.035, "step": 135710 }, { "epoch": 32.57, "learning_rate": 6.727890836485553e-05, "loss": 0.0283, "step": 135720 }, { "epoch": 32.57, "learning_rate": 6.727469777336759e-05, "loss": 0.0395, "step": 135730 }, { "epoch": 32.58, "learning_rate": 6.727048704276408e-05, "loss": 0.073, "step": 135740 }, { "epoch": 32.58, "learning_rate": 6.7266276173079e-05, "loss": 0.0466, "step": 135750 }, { "epoch": 32.58, "learning_rate": 6.726206516434619e-05, "loss": 0.0313, "step": 135760 }, { "epoch": 32.58, "learning_rate": 6.725785401659958e-05, "loss": 0.042, "step": 135770 }, { "epoch": 32.59, "learning_rate": 6.72536427298731e-05, "loss": 0.0298, "step": 135780 }, { "epoch": 32.59, "learning_rate": 6.724943130420064e-05, "loss": 0.0358, "step": 135790 }, { "epoch": 32.59, "learning_rate": 6.724521973961615e-05, "loss": 0.0438, "step": 135800 }, { "epoch": 32.59, "learning_rate": 6.72410080361535e-05, "loss": 0.0382, "step": 135810 }, { "epoch": 32.6, "learning_rate": 6.723679619384666e-05, "loss": 0.0338, "step": 135820 }, { "epoch": 32.6, "learning_rate": 6.72325842127295e-05, "loss": 0.0563, "step": 135830 }, { "epoch": 32.6, "learning_rate": 6.722837209283595e-05, "loss": 0.0487, "step": 135840 }, { "epoch": 32.6, "learning_rate": 6.722415983419997e-05, "loss": 0.0289, "step": 135850 }, { "epoch": 32.6, "learning_rate": 6.721994743685543e-05, "loss": 0.0423, "step": 135860 }, { "epoch": 32.61, "learning_rate": 6.72157349008363e-05, "loss": 0.0243, "step": 135870 }, { "epoch": 32.61, "learning_rate": 6.721152222617646e-05, "loss": 0.0242, "step": 135880 }, { "epoch": 32.61, "learning_rate": 6.720730941290987e-05, "loss": 0.036, "step": 135890 }, { "epoch": 32.61, "learning_rate": 6.720309646107043e-05, "loss": 0.0415, "step": 135900 }, { "epoch": 32.62, "learning_rate": 6.719888337069207e-05, "loss": 0.0483, "step": 135910 }, { "epoch": 32.62, "learning_rate": 6.719467014180875e-05, "loss": 0.0442, "step": 135920 }, { "epoch": 32.62, "learning_rate": 6.719045677445436e-05, "loss": 0.0259, "step": 135930 }, { "epoch": 32.62, "learning_rate": 6.718624326866285e-05, "loss": 0.0389, "step": 135940 }, { "epoch": 32.62, "learning_rate": 6.718202962446817e-05, "loss": 0.0422, "step": 135950 }, { "epoch": 32.63, "learning_rate": 6.717781584190422e-05, "loss": 0.0222, "step": 135960 }, { "epoch": 32.63, "learning_rate": 6.717360192100494e-05, "loss": 0.0507, "step": 135970 }, { "epoch": 32.63, "learning_rate": 6.716938786180427e-05, "loss": 0.0224, "step": 135980 }, { "epoch": 32.63, "learning_rate": 6.716517366433616e-05, "loss": 0.0279, "step": 135990 }, { "epoch": 32.64, "learning_rate": 6.716095932863454e-05, "loss": 0.0306, "step": 136000 }, { "epoch": 32.64, "learning_rate": 6.715674485473334e-05, "loss": 0.0219, "step": 136010 }, { "epoch": 32.64, "learning_rate": 6.715253024266652e-05, "loss": 0.0375, "step": 136020 }, { "epoch": 32.64, "learning_rate": 6.714831549246797e-05, "loss": 0.0286, "step": 136030 }, { "epoch": 32.65, "learning_rate": 6.714410060417171e-05, "loss": 0.0309, "step": 136040 }, { "epoch": 32.65, "learning_rate": 6.713988557781161e-05, "loss": 0.034, "step": 136050 }, { "epoch": 32.65, "learning_rate": 6.713567041342166e-05, "loss": 0.0271, "step": 136060 }, { "epoch": 32.65, "learning_rate": 6.713145511103578e-05, "loss": 0.0267, "step": 136070 }, { "epoch": 32.65, "learning_rate": 6.712723967068794e-05, "loss": 0.0237, "step": 136080 }, { "epoch": 32.66, "learning_rate": 6.712302409241207e-05, "loss": 0.0375, "step": 136090 }, { "epoch": 32.66, "learning_rate": 6.71188083762421e-05, "loss": 0.0198, "step": 136100 }, { "epoch": 32.66, "learning_rate": 6.711459252221204e-05, "loss": 0.0518, "step": 136110 }, { "epoch": 32.66, "learning_rate": 6.711037653035578e-05, "loss": 0.037, "step": 136120 }, { "epoch": 32.67, "learning_rate": 6.71061604007073e-05, "loss": 0.0284, "step": 136130 }, { "epoch": 32.67, "learning_rate": 6.710194413330056e-05, "loss": 0.0234, "step": 136140 }, { "epoch": 32.67, "learning_rate": 6.709772772816948e-05, "loss": 0.037, "step": 136150 }, { "epoch": 32.67, "learning_rate": 6.709351118534806e-05, "loss": 0.0331, "step": 136160 }, { "epoch": 32.68, "learning_rate": 6.708929450487022e-05, "loss": 0.038, "step": 136170 }, { "epoch": 32.68, "learning_rate": 6.708507768676994e-05, "loss": 0.0492, "step": 136180 }, { "epoch": 32.68, "learning_rate": 6.708086073108116e-05, "loss": 0.0446, "step": 136190 }, { "epoch": 32.68, "learning_rate": 6.707664363783787e-05, "loss": 0.0419, "step": 136200 }, { "epoch": 32.68, "learning_rate": 6.7072426407074e-05, "loss": 0.0482, "step": 136210 }, { "epoch": 32.69, "learning_rate": 6.706820903882353e-05, "loss": 0.0474, "step": 136220 }, { "epoch": 32.69, "learning_rate": 6.706399153312041e-05, "loss": 0.0256, "step": 136230 }, { "epoch": 32.69, "learning_rate": 6.70597738899986e-05, "loss": 0.0356, "step": 136240 }, { "epoch": 32.69, "learning_rate": 6.705555610949207e-05, "loss": 0.0491, "step": 136250 }, { "epoch": 32.7, "learning_rate": 6.705133819163483e-05, "loss": 0.0361, "step": 136260 }, { "epoch": 32.7, "learning_rate": 6.704712013646078e-05, "loss": 0.0426, "step": 136270 }, { "epoch": 32.7, "learning_rate": 6.704290194400394e-05, "loss": 0.0394, "step": 136280 }, { "epoch": 32.7, "learning_rate": 6.703868361429823e-05, "loss": 0.0219, "step": 136290 }, { "epoch": 32.7, "learning_rate": 6.703446514737766e-05, "loss": 0.0242, "step": 136300 }, { "epoch": 32.71, "learning_rate": 6.703024654327619e-05, "loss": 0.0557, "step": 136310 }, { "epoch": 32.71, "learning_rate": 6.702602780202779e-05, "loss": 0.0307, "step": 136320 }, { "epoch": 32.71, "learning_rate": 6.702180892366645e-05, "loss": 0.0317, "step": 136330 }, { "epoch": 32.71, "learning_rate": 6.701758990822613e-05, "loss": 0.0386, "step": 136340 }, { "epoch": 32.72, "learning_rate": 6.70133707557408e-05, "loss": 0.0505, "step": 136350 }, { "epoch": 32.72, "learning_rate": 6.700915146624445e-05, "loss": 0.0464, "step": 136360 }, { "epoch": 32.72, "learning_rate": 6.700493203977106e-05, "loss": 0.0346, "step": 136370 }, { "epoch": 32.72, "learning_rate": 6.70007124763546e-05, "loss": 0.0378, "step": 136380 }, { "epoch": 32.73, "learning_rate": 6.699649277602905e-05, "loss": 0.0435, "step": 136390 }, { "epoch": 32.73, "learning_rate": 6.699227293882841e-05, "loss": 0.0383, "step": 136400 }, { "epoch": 32.73, "learning_rate": 6.698805296478664e-05, "loss": 0.0322, "step": 136410 }, { "epoch": 32.73, "learning_rate": 6.698383285393772e-05, "loss": 0.0261, "step": 136420 }, { "epoch": 32.73, "learning_rate": 6.697961260631567e-05, "loss": 0.0353, "step": 136430 }, { "epoch": 32.74, "learning_rate": 6.697539222195446e-05, "loss": 0.0557, "step": 136440 }, { "epoch": 32.74, "learning_rate": 6.697117170088807e-05, "loss": 0.0326, "step": 136450 }, { "epoch": 32.74, "learning_rate": 6.696695104315048e-05, "loss": 0.0563, "step": 136460 }, { "epoch": 32.74, "learning_rate": 6.69627302487757e-05, "loss": 0.0215, "step": 136470 }, { "epoch": 32.75, "learning_rate": 6.695850931779771e-05, "loss": 0.0313, "step": 136480 }, { "epoch": 32.75, "learning_rate": 6.69542882502505e-05, "loss": 0.0604, "step": 136490 }, { "epoch": 32.75, "learning_rate": 6.695006704616806e-05, "loss": 0.0279, "step": 136500 }, { "epoch": 32.75, "learning_rate": 6.69458457055844e-05, "loss": 0.0298, "step": 136510 }, { "epoch": 32.76, "learning_rate": 6.694162422853351e-05, "loss": 0.0227, "step": 136520 }, { "epoch": 32.76, "learning_rate": 6.693740261504937e-05, "loss": 0.026, "step": 136530 }, { "epoch": 32.76, "learning_rate": 6.6933180865166e-05, "loss": 0.0291, "step": 136540 }, { "epoch": 32.76, "learning_rate": 6.692895897891737e-05, "loss": 0.0459, "step": 136550 }, { "epoch": 32.76, "learning_rate": 6.692473695633749e-05, "loss": 0.0337, "step": 136560 }, { "epoch": 32.77, "learning_rate": 6.69205147974604e-05, "loss": 0.0258, "step": 136570 }, { "epoch": 32.77, "learning_rate": 6.691629250232005e-05, "loss": 0.0514, "step": 136580 }, { "epoch": 32.77, "learning_rate": 6.691207007095047e-05, "loss": 0.0468, "step": 136590 }, { "epoch": 32.77, "learning_rate": 6.690784750338563e-05, "loss": 0.0411, "step": 136600 }, { "epoch": 32.78, "learning_rate": 6.690362479965957e-05, "loss": 0.0525, "step": 136610 }, { "epoch": 32.78, "learning_rate": 6.68994019598063e-05, "loss": 0.0265, "step": 136620 }, { "epoch": 32.78, "learning_rate": 6.689517898385981e-05, "loss": 0.034, "step": 136630 }, { "epoch": 32.78, "learning_rate": 6.68909558718541e-05, "loss": 0.0286, "step": 136640 }, { "epoch": 32.78, "learning_rate": 6.68867326238232e-05, "loss": 0.0205, "step": 136650 }, { "epoch": 32.79, "learning_rate": 6.68825092398011e-05, "loss": 0.0486, "step": 136660 }, { "epoch": 32.79, "learning_rate": 6.687828571982184e-05, "loss": 0.0445, "step": 136670 }, { "epoch": 32.79, "learning_rate": 6.687406206391939e-05, "loss": 0.025, "step": 136680 }, { "epoch": 32.79, "learning_rate": 6.68698382721278e-05, "loss": 0.0239, "step": 136690 }, { "epoch": 32.8, "learning_rate": 6.686561434448108e-05, "loss": 0.0355, "step": 136700 }, { "epoch": 32.8, "learning_rate": 6.686139028101323e-05, "loss": 0.0421, "step": 136710 }, { "epoch": 32.8, "learning_rate": 6.685716608175829e-05, "loss": 0.0365, "step": 136720 }, { "epoch": 32.8, "learning_rate": 6.685294174675025e-05, "loss": 0.0336, "step": 136730 }, { "epoch": 32.81, "learning_rate": 6.684871727602317e-05, "loss": 0.0612, "step": 136740 }, { "epoch": 32.81, "learning_rate": 6.6844492669611e-05, "loss": 0.0679, "step": 136750 }, { "epoch": 32.81, "learning_rate": 6.684026792754783e-05, "loss": 0.0455, "step": 136760 }, { "epoch": 32.81, "learning_rate": 6.683604304986766e-05, "loss": 0.0269, "step": 136770 }, { "epoch": 32.81, "learning_rate": 6.68318180366045e-05, "loss": 0.0249, "step": 136780 }, { "epoch": 32.82, "learning_rate": 6.68275928877924e-05, "loss": 0.0664, "step": 136790 }, { "epoch": 32.82, "learning_rate": 6.682336760346536e-05, "loss": 0.0438, "step": 136800 }, { "epoch": 32.82, "learning_rate": 6.681914218365744e-05, "loss": 0.0358, "step": 136810 }, { "epoch": 32.82, "learning_rate": 6.68149166284026e-05, "loss": 0.0435, "step": 136820 }, { "epoch": 32.83, "learning_rate": 6.681069093773496e-05, "loss": 0.032, "step": 136830 }, { "epoch": 32.83, "learning_rate": 6.680646511168847e-05, "loss": 0.0375, "step": 136840 }, { "epoch": 32.83, "learning_rate": 6.680223915029722e-05, "loss": 0.0251, "step": 136850 }, { "epoch": 32.83, "learning_rate": 6.679801305359523e-05, "loss": 0.0247, "step": 136860 }, { "epoch": 32.84, "learning_rate": 6.679378682161648e-05, "loss": 0.0213, "step": 136870 }, { "epoch": 32.84, "learning_rate": 6.678956045439508e-05, "loss": 0.0406, "step": 136880 }, { "epoch": 32.84, "learning_rate": 6.678533395196502e-05, "loss": 0.0358, "step": 136890 }, { "epoch": 32.84, "learning_rate": 6.678110731436034e-05, "loss": 0.0399, "step": 136900 }, { "epoch": 32.84, "learning_rate": 6.67768805416151e-05, "loss": 0.031, "step": 136910 }, { "epoch": 32.85, "learning_rate": 6.677265363376332e-05, "loss": 0.0291, "step": 136920 }, { "epoch": 32.85, "learning_rate": 6.676842659083905e-05, "loss": 0.0335, "step": 136930 }, { "epoch": 32.85, "learning_rate": 6.676419941287632e-05, "loss": 0.0354, "step": 136940 }, { "epoch": 32.85, "learning_rate": 6.675997209990917e-05, "loss": 0.0369, "step": 136950 }, { "epoch": 32.86, "learning_rate": 6.675574465197167e-05, "loss": 0.032, "step": 136960 }, { "epoch": 32.86, "learning_rate": 6.675151706909784e-05, "loss": 0.0249, "step": 136970 }, { "epoch": 32.86, "learning_rate": 6.674728935132171e-05, "loss": 0.0438, "step": 136980 }, { "epoch": 32.86, "learning_rate": 6.674306149867736e-05, "loss": 0.0331, "step": 136990 }, { "epoch": 32.86, "learning_rate": 6.673883351119883e-05, "loss": 0.0194, "step": 137000 }, { "epoch": 32.87, "learning_rate": 6.673460538892016e-05, "loss": 0.0433, "step": 137010 }, { "epoch": 32.87, "learning_rate": 6.67303771318754e-05, "loss": 0.0546, "step": 137020 }, { "epoch": 32.87, "learning_rate": 6.67261487400986e-05, "loss": 0.0423, "step": 137030 }, { "epoch": 32.87, "learning_rate": 6.672192021362382e-05, "loss": 0.0393, "step": 137040 }, { "epoch": 32.88, "learning_rate": 6.671769155248512e-05, "loss": 0.0309, "step": 137050 }, { "epoch": 32.88, "learning_rate": 6.671346275671651e-05, "loss": 0.0221, "step": 137060 }, { "epoch": 32.88, "learning_rate": 6.670923382635211e-05, "loss": 0.048, "step": 137070 }, { "epoch": 32.88, "learning_rate": 6.670500476142593e-05, "loss": 0.0221, "step": 137080 }, { "epoch": 32.89, "learning_rate": 6.670077556197203e-05, "loss": 0.0273, "step": 137090 }, { "epoch": 32.89, "learning_rate": 6.66965462280245e-05, "loss": 0.0432, "step": 137100 }, { "epoch": 32.89, "learning_rate": 6.669231675961736e-05, "loss": 0.0305, "step": 137110 }, { "epoch": 32.89, "learning_rate": 6.66880871567847e-05, "loss": 0.0249, "step": 137120 }, { "epoch": 32.89, "learning_rate": 6.668385741956056e-05, "loss": 0.0446, "step": 137130 }, { "epoch": 32.9, "learning_rate": 6.667962754797901e-05, "loss": 0.0161, "step": 137140 }, { "epoch": 32.9, "learning_rate": 6.667539754207412e-05, "loss": 0.0304, "step": 137150 }, { "epoch": 32.9, "learning_rate": 6.667116740187995e-05, "loss": 0.029, "step": 137160 }, { "epoch": 32.9, "learning_rate": 6.666693712743059e-05, "loss": 0.0297, "step": 137170 }, { "epoch": 32.91, "learning_rate": 6.666270671876006e-05, "loss": 0.0253, "step": 137180 }, { "epoch": 32.91, "learning_rate": 6.665847617590247e-05, "loss": 0.0423, "step": 137190 }, { "epoch": 32.91, "learning_rate": 6.665424549889185e-05, "loss": 0.0234, "step": 137200 }, { "epoch": 32.91, "learning_rate": 6.665001468776231e-05, "loss": 0.0237, "step": 137210 }, { "epoch": 32.91, "learning_rate": 6.66457837425479e-05, "loss": 0.0298, "step": 137220 }, { "epoch": 32.92, "learning_rate": 6.664155266328268e-05, "loss": 0.0223, "step": 137230 }, { "epoch": 32.92, "learning_rate": 6.663732145000077e-05, "loss": 0.0153, "step": 137240 }, { "epoch": 32.92, "learning_rate": 6.663309010273617e-05, "loss": 0.0369, "step": 137250 }, { "epoch": 32.92, "learning_rate": 6.662885862152304e-05, "loss": 0.033, "step": 137260 }, { "epoch": 32.93, "learning_rate": 6.662462700639539e-05, "loss": 0.0404, "step": 137270 }, { "epoch": 32.93, "learning_rate": 6.662039525738732e-05, "loss": 0.0216, "step": 137280 }, { "epoch": 32.93, "learning_rate": 6.661616337453295e-05, "loss": 0.019, "step": 137290 }, { "epoch": 32.93, "learning_rate": 6.661193135786628e-05, "loss": 0.0243, "step": 137300 }, { "epoch": 32.94, "learning_rate": 6.660769920742148e-05, "loss": 0.0213, "step": 137310 }, { "epoch": 32.94, "learning_rate": 6.660346692323254e-05, "loss": 0.0321, "step": 137320 }, { "epoch": 32.94, "learning_rate": 6.65992345053336e-05, "loss": 0.0267, "step": 137330 }, { "epoch": 32.94, "learning_rate": 6.659500195375874e-05, "loss": 0.0391, "step": 137340 }, { "epoch": 32.94, "learning_rate": 6.659076926854203e-05, "loss": 0.0581, "step": 137350 }, { "epoch": 32.95, "learning_rate": 6.658653644971758e-05, "loss": 0.0522, "step": 137360 }, { "epoch": 32.95, "learning_rate": 6.658230349731945e-05, "loss": 0.0286, "step": 137370 }, { "epoch": 33.0, "learning_rate": 6.657807041138173e-05, "loss": 0.0337, "step": 137380 }, { "epoch": 33.0, "learning_rate": 6.657383719193854e-05, "loss": 0.043, "step": 137390 }, { "epoch": 33.0, "learning_rate": 6.656960383902394e-05, "loss": 0.0283, "step": 137400 }, { "epoch": 33.01, "learning_rate": 6.656537035267204e-05, "loss": 0.0407, "step": 137410 }, { "epoch": 33.01, "learning_rate": 6.656113673291692e-05, "loss": 0.0377, "step": 137420 }, { "epoch": 33.01, "learning_rate": 6.65569029797927e-05, "loss": 0.0165, "step": 137430 }, { "epoch": 33.01, "learning_rate": 6.655266909333341e-05, "loss": 0.0237, "step": 137440 }, { "epoch": 33.02, "learning_rate": 6.654843507357322e-05, "loss": 0.0324, "step": 137450 }, { "epoch": 33.02, "learning_rate": 6.65442009205462e-05, "loss": 0.055, "step": 137460 }, { "epoch": 33.02, "learning_rate": 6.653996663428644e-05, "loss": 0.0299, "step": 137470 }, { "epoch": 33.02, "learning_rate": 6.653573221482805e-05, "loss": 0.0218, "step": 137480 }, { "epoch": 33.03, "learning_rate": 6.653149766220511e-05, "loss": 0.0434, "step": 137490 }, { "epoch": 33.03, "learning_rate": 6.652726297645177e-05, "loss": 0.0311, "step": 137500 }, { "epoch": 33.03, "learning_rate": 6.652302815760206e-05, "loss": 0.0261, "step": 137510 }, { "epoch": 33.03, "learning_rate": 6.651879320569014e-05, "loss": 0.0461, "step": 137520 }, { "epoch": 33.03, "learning_rate": 6.65145581207501e-05, "loss": 0.0489, "step": 137530 }, { "epoch": 33.04, "learning_rate": 6.651032290281604e-05, "loss": 0.0343, "step": 137540 }, { "epoch": 33.04, "learning_rate": 6.650608755192208e-05, "loss": 0.0353, "step": 137550 }, { "epoch": 33.04, "learning_rate": 6.65018520681023e-05, "loss": 0.0429, "step": 137560 }, { "epoch": 33.04, "learning_rate": 6.649761645139084e-05, "loss": 0.0196, "step": 137570 }, { "epoch": 33.05, "learning_rate": 6.64933807018218e-05, "loss": 0.034, "step": 137580 }, { "epoch": 33.05, "learning_rate": 6.648914481942928e-05, "loss": 0.038, "step": 137590 }, { "epoch": 33.05, "learning_rate": 6.64849088042474e-05, "loss": 0.034, "step": 137600 }, { "epoch": 33.05, "learning_rate": 6.648067265631028e-05, "loss": 0.0219, "step": 137610 }, { "epoch": 33.06, "learning_rate": 6.647643637565204e-05, "loss": 0.0388, "step": 137620 }, { "epoch": 33.06, "learning_rate": 6.647219996230675e-05, "loss": 0.0234, "step": 137630 }, { "epoch": 33.06, "learning_rate": 6.646796341630858e-05, "loss": 0.0348, "step": 137640 }, { "epoch": 33.06, "learning_rate": 6.646372673769162e-05, "loss": 0.0289, "step": 137650 }, { "epoch": 33.06, "learning_rate": 6.645948992649e-05, "loss": 0.0346, "step": 137660 }, { "epoch": 33.07, "learning_rate": 6.645525298273784e-05, "loss": 0.0358, "step": 137670 }, { "epoch": 33.07, "learning_rate": 6.645101590646923e-05, "loss": 0.0259, "step": 137680 }, { "epoch": 33.07, "learning_rate": 6.644677869771836e-05, "loss": 0.0244, "step": 137690 }, { "epoch": 33.07, "learning_rate": 6.644254135651929e-05, "loss": 0.0387, "step": 137700 }, { "epoch": 33.08, "learning_rate": 6.643830388290616e-05, "loss": 0.0457, "step": 137710 }, { "epoch": 33.08, "learning_rate": 6.643406627691311e-05, "loss": 0.0298, "step": 137720 }, { "epoch": 33.08, "learning_rate": 6.642982853857424e-05, "loss": 0.0408, "step": 137730 }, { "epoch": 33.08, "learning_rate": 6.642559066792371e-05, "loss": 0.023, "step": 137740 }, { "epoch": 33.08, "learning_rate": 6.64213526649956e-05, "loss": 0.0375, "step": 137750 }, { "epoch": 33.09, "learning_rate": 6.64171145298241e-05, "loss": 0.0395, "step": 137760 }, { "epoch": 33.09, "learning_rate": 6.64128762624433e-05, "loss": 0.0192, "step": 137770 }, { "epoch": 33.09, "learning_rate": 6.640863786288735e-05, "loss": 0.0234, "step": 137780 }, { "epoch": 33.09, "learning_rate": 6.640439933119037e-05, "loss": 0.0281, "step": 137790 }, { "epoch": 33.1, "learning_rate": 6.640016066738649e-05, "loss": 0.0383, "step": 137800 }, { "epoch": 33.1, "learning_rate": 6.639592187150985e-05, "loss": 0.0169, "step": 137810 }, { "epoch": 33.1, "learning_rate": 6.639168294359459e-05, "loss": 0.0227, "step": 137820 }, { "epoch": 33.1, "learning_rate": 6.638744388367487e-05, "loss": 0.0288, "step": 137830 }, { "epoch": 33.11, "learning_rate": 6.638320469178477e-05, "loss": 0.0249, "step": 137840 }, { "epoch": 33.11, "learning_rate": 6.637896536795847e-05, "loss": 0.0258, "step": 137850 }, { "epoch": 33.11, "learning_rate": 6.63747259122301e-05, "loss": 0.0346, "step": 137860 }, { "epoch": 33.11, "learning_rate": 6.63704863246338e-05, "loss": 0.0371, "step": 137870 }, { "epoch": 33.11, "learning_rate": 6.636624660520371e-05, "loss": 0.029, "step": 137880 }, { "epoch": 33.12, "learning_rate": 6.6362006753974e-05, "loss": 0.0402, "step": 137890 }, { "epoch": 33.12, "learning_rate": 6.635776677097877e-05, "loss": 0.0309, "step": 137900 }, { "epoch": 33.12, "learning_rate": 6.635352665625218e-05, "loss": 0.0154, "step": 137910 }, { "epoch": 33.12, "learning_rate": 6.63492864098284e-05, "loss": 0.0235, "step": 137920 }, { "epoch": 33.13, "learning_rate": 6.634504603174155e-05, "loss": 0.0327, "step": 137930 }, { "epoch": 33.13, "learning_rate": 6.634080552202578e-05, "loss": 0.0189, "step": 137940 }, { "epoch": 33.13, "learning_rate": 6.633656488071527e-05, "loss": 0.0421, "step": 137950 }, { "epoch": 33.13, "learning_rate": 6.633232410784413e-05, "loss": 0.03, "step": 137960 }, { "epoch": 33.14, "learning_rate": 6.632808320344654e-05, "loss": 0.033, "step": 137970 }, { "epoch": 33.14, "learning_rate": 6.632384216755662e-05, "loss": 0.0175, "step": 137980 }, { "epoch": 33.14, "learning_rate": 6.631960100020857e-05, "loss": 0.0343, "step": 137990 }, { "epoch": 33.14, "learning_rate": 6.63153597014365e-05, "loss": 0.0206, "step": 138000 }, { "epoch": 33.14, "learning_rate": 6.631111827127459e-05, "loss": 0.0191, "step": 138010 }, { "epoch": 33.15, "learning_rate": 6.630687670975701e-05, "loss": 0.0596, "step": 138020 }, { "epoch": 33.15, "learning_rate": 6.630263501691789e-05, "loss": 0.0307, "step": 138030 }, { "epoch": 33.15, "learning_rate": 6.62983931927914e-05, "loss": 0.0275, "step": 138040 }, { "epoch": 33.15, "learning_rate": 6.62941512374117e-05, "loss": 0.0307, "step": 138050 }, { "epoch": 33.16, "learning_rate": 6.628990915081294e-05, "loss": 0.0245, "step": 138060 }, { "epoch": 33.16, "learning_rate": 6.62856669330293e-05, "loss": 0.0477, "step": 138070 }, { "epoch": 33.16, "learning_rate": 6.628142458409494e-05, "loss": 0.0272, "step": 138080 }, { "epoch": 33.16, "learning_rate": 6.627718210404402e-05, "loss": 0.0214, "step": 138090 }, { "epoch": 33.16, "learning_rate": 6.62729394929107e-05, "loss": 0.0266, "step": 138100 }, { "epoch": 33.17, "learning_rate": 6.626869675072917e-05, "loss": 0.0155, "step": 138110 }, { "epoch": 33.17, "learning_rate": 6.626445387753355e-05, "loss": 0.041, "step": 138120 }, { "epoch": 33.17, "learning_rate": 6.626021087335805e-05, "loss": 0.0336, "step": 138130 }, { "epoch": 33.17, "learning_rate": 6.625596773823682e-05, "loss": 0.0258, "step": 138140 }, { "epoch": 33.18, "learning_rate": 6.625172447220406e-05, "loss": 0.0261, "step": 138150 }, { "epoch": 33.18, "learning_rate": 6.62474810752939e-05, "loss": 0.0459, "step": 138160 }, { "epoch": 33.18, "learning_rate": 6.624323754754054e-05, "loss": 0.0361, "step": 138170 }, { "epoch": 33.18, "learning_rate": 6.623899388897814e-05, "loss": 0.0198, "step": 138180 }, { "epoch": 33.19, "learning_rate": 6.623475009964088e-05, "loss": 0.0372, "step": 138190 }, { "epoch": 33.19, "learning_rate": 6.623050617956294e-05, "loss": 0.0264, "step": 138200 }, { "epoch": 33.19, "learning_rate": 6.622626212877848e-05, "loss": 0.0379, "step": 138210 }, { "epoch": 33.19, "learning_rate": 6.62220179473217e-05, "loss": 0.0215, "step": 138220 }, { "epoch": 33.19, "learning_rate": 6.621777363522678e-05, "loss": 0.0276, "step": 138230 }, { "epoch": 33.2, "learning_rate": 6.621352919252788e-05, "loss": 0.0371, "step": 138240 }, { "epoch": 33.2, "learning_rate": 6.620928461925921e-05, "loss": 0.0233, "step": 138250 }, { "epoch": 33.2, "learning_rate": 6.62050399154549e-05, "loss": 0.0498, "step": 138260 }, { "epoch": 33.2, "learning_rate": 6.620079508114918e-05, "loss": 0.0202, "step": 138270 }, { "epoch": 33.21, "learning_rate": 6.619655011637623e-05, "loss": 0.0202, "step": 138280 }, { "epoch": 33.21, "learning_rate": 6.619230502117022e-05, "loss": 0.0235, "step": 138290 }, { "epoch": 33.21, "learning_rate": 6.618805979556533e-05, "loss": 0.0197, "step": 138300 }, { "epoch": 33.21, "learning_rate": 6.618381443959577e-05, "loss": 0.0135, "step": 138310 }, { "epoch": 33.22, "learning_rate": 6.617956895329574e-05, "loss": 0.0303, "step": 138320 }, { "epoch": 33.22, "learning_rate": 6.617532333669937e-05, "loss": 0.0415, "step": 138330 }, { "epoch": 33.22, "learning_rate": 6.61710775898409e-05, "loss": 0.0347, "step": 138340 }, { "epoch": 33.22, "learning_rate": 6.616683171275451e-05, "loss": 0.0325, "step": 138350 }, { "epoch": 33.22, "learning_rate": 6.61625857054744e-05, "loss": 0.0391, "step": 138360 }, { "epoch": 33.23, "learning_rate": 6.615833956803475e-05, "loss": 0.0442, "step": 138370 }, { "epoch": 33.23, "learning_rate": 6.615409330046976e-05, "loss": 0.0385, "step": 138380 }, { "epoch": 33.23, "learning_rate": 6.614984690281365e-05, "loss": 0.0531, "step": 138390 }, { "epoch": 33.23, "learning_rate": 6.614560037510056e-05, "loss": 0.0314, "step": 138400 }, { "epoch": 33.24, "learning_rate": 6.614135371736473e-05, "loss": 0.0162, "step": 138410 }, { "epoch": 33.24, "learning_rate": 6.613710692964036e-05, "loss": 0.0211, "step": 138420 }, { "epoch": 33.24, "learning_rate": 6.613286001196161e-05, "loss": 0.0239, "step": 138430 }, { "epoch": 33.24, "learning_rate": 6.612861296436275e-05, "loss": 0.0174, "step": 138440 }, { "epoch": 33.24, "learning_rate": 6.612436578687793e-05, "loss": 0.0229, "step": 138450 }, { "epoch": 33.25, "learning_rate": 6.612011847954137e-05, "loss": 0.0277, "step": 138460 }, { "epoch": 33.25, "learning_rate": 6.611587104238725e-05, "loss": 0.0268, "step": 138470 }, { "epoch": 33.25, "learning_rate": 6.611162347544981e-05, "loss": 0.0296, "step": 138480 }, { "epoch": 33.25, "learning_rate": 6.610737577876325e-05, "loss": 0.0337, "step": 138490 }, { "epoch": 33.26, "learning_rate": 6.610312795236176e-05, "loss": 0.013, "step": 138500 }, { "epoch": 33.26, "learning_rate": 6.609887999627956e-05, "loss": 0.0352, "step": 138510 }, { "epoch": 33.26, "learning_rate": 6.609463191055084e-05, "loss": 0.0233, "step": 138520 }, { "epoch": 33.26, "learning_rate": 6.609038369520984e-05, "loss": 0.021, "step": 138530 }, { "epoch": 33.27, "learning_rate": 6.608613535029077e-05, "loss": 0.0313, "step": 138540 }, { "epoch": 33.27, "learning_rate": 6.608188687582782e-05, "loss": 0.016, "step": 138550 }, { "epoch": 33.27, "learning_rate": 6.607763827185522e-05, "loss": 0.0311, "step": 138560 }, { "epoch": 33.27, "learning_rate": 6.607338953840718e-05, "loss": 0.0146, "step": 138570 }, { "epoch": 33.27, "learning_rate": 6.60691406755179e-05, "loss": 0.0222, "step": 138580 }, { "epoch": 33.28, "learning_rate": 6.606489168322163e-05, "loss": 0.0467, "step": 138590 }, { "epoch": 33.28, "learning_rate": 6.606064256155255e-05, "loss": 0.0289, "step": 138600 }, { "epoch": 33.28, "learning_rate": 6.605639331054492e-05, "loss": 0.0268, "step": 138610 }, { "epoch": 33.28, "learning_rate": 6.605214393023291e-05, "loss": 0.0309, "step": 138620 }, { "epoch": 33.29, "learning_rate": 6.60478944206508e-05, "loss": 0.0214, "step": 138630 }, { "epoch": 33.29, "learning_rate": 6.604364478183278e-05, "loss": 0.0345, "step": 138640 }, { "epoch": 33.29, "learning_rate": 6.603939501381304e-05, "loss": 0.0318, "step": 138650 }, { "epoch": 33.29, "learning_rate": 6.603514511662587e-05, "loss": 0.0367, "step": 138660 }, { "epoch": 33.3, "learning_rate": 6.603089509030544e-05, "loss": 0.0284, "step": 138670 }, { "epoch": 33.3, "learning_rate": 6.602664493488602e-05, "loss": 0.0376, "step": 138680 }, { "epoch": 33.3, "learning_rate": 6.60223946504018e-05, "loss": 0.0411, "step": 138690 }, { "epoch": 33.3, "learning_rate": 6.601814423688703e-05, "loss": 0.04, "step": 138700 }, { "epoch": 33.3, "learning_rate": 6.601389369437594e-05, "loss": 0.0236, "step": 138710 }, { "epoch": 33.31, "learning_rate": 6.600964302290274e-05, "loss": 0.036, "step": 138720 }, { "epoch": 33.31, "learning_rate": 6.600539222250169e-05, "loss": 0.0186, "step": 138730 }, { "epoch": 33.31, "learning_rate": 6.600114129320699e-05, "loss": 0.0236, "step": 138740 }, { "epoch": 33.31, "learning_rate": 6.59968902350529e-05, "loss": 0.0312, "step": 138750 }, { "epoch": 33.32, "learning_rate": 6.599263904807363e-05, "loss": 0.0291, "step": 138760 }, { "epoch": 33.32, "learning_rate": 6.598838773230345e-05, "loss": 0.0213, "step": 138770 }, { "epoch": 33.32, "learning_rate": 6.598413628777657e-05, "loss": 0.026, "step": 138780 }, { "epoch": 33.32, "learning_rate": 6.597988471452722e-05, "loss": 0.021, "step": 138790 }, { "epoch": 33.32, "learning_rate": 6.597563301258967e-05, "loss": 0.0292, "step": 138800 }, { "epoch": 33.33, "learning_rate": 6.597138118199813e-05, "loss": 0.0259, "step": 138810 }, { "epoch": 33.33, "learning_rate": 6.596712922278688e-05, "loss": 0.0268, "step": 138820 }, { "epoch": 33.33, "learning_rate": 6.596287713499009e-05, "loss": 0.0251, "step": 138830 }, { "epoch": 33.33, "learning_rate": 6.595862491864207e-05, "loss": 0.0331, "step": 138840 }, { "epoch": 33.34, "learning_rate": 6.595437257377703e-05, "loss": 0.0348, "step": 138850 }, { "epoch": 33.34, "learning_rate": 6.595012010042924e-05, "loss": 0.0247, "step": 138860 }, { "epoch": 33.34, "learning_rate": 6.594586749863293e-05, "loss": 0.0187, "step": 138870 }, { "epoch": 33.34, "learning_rate": 6.594161476842234e-05, "loss": 0.036, "step": 138880 }, { "epoch": 33.35, "learning_rate": 6.593736190983172e-05, "loss": 0.02, "step": 138890 }, { "epoch": 33.35, "learning_rate": 6.593310892289534e-05, "loss": 0.02, "step": 138900 }, { "epoch": 33.35, "learning_rate": 6.592885580764743e-05, "loss": 0.0313, "step": 138910 }, { "epoch": 33.35, "learning_rate": 6.592460256412223e-05, "loss": 0.0297, "step": 138920 }, { "epoch": 33.35, "learning_rate": 6.592034919235402e-05, "loss": 0.0252, "step": 138930 }, { "epoch": 33.36, "learning_rate": 6.591609569237705e-05, "loss": 0.0155, "step": 138940 }, { "epoch": 33.36, "learning_rate": 6.591184206422553e-05, "loss": 0.0346, "step": 138950 }, { "epoch": 33.36, "learning_rate": 6.590758830793377e-05, "loss": 0.0215, "step": 138960 }, { "epoch": 33.36, "learning_rate": 6.5903334423536e-05, "loss": 0.0283, "step": 138970 }, { "epoch": 33.37, "learning_rate": 6.58990804110665e-05, "loss": 0.0113, "step": 138980 }, { "epoch": 33.37, "learning_rate": 6.58948262705595e-05, "loss": 0.0296, "step": 138990 }, { "epoch": 33.37, "learning_rate": 6.589057200204926e-05, "loss": 0.0146, "step": 139000 }, { "epoch": 33.37, "learning_rate": 6.588631760557007e-05, "loss": 0.0335, "step": 139010 }, { "epoch": 33.38, "learning_rate": 6.588206308115615e-05, "loss": 0.0294, "step": 139020 }, { "epoch": 33.38, "learning_rate": 6.587780842884181e-05, "loss": 0.0281, "step": 139030 }, { "epoch": 33.38, "learning_rate": 6.587355364866126e-05, "loss": 0.0445, "step": 139040 }, { "epoch": 33.38, "learning_rate": 6.58692987406488e-05, "loss": 0.0172, "step": 139050 }, { "epoch": 33.38, "learning_rate": 6.586504370483869e-05, "loss": 0.0259, "step": 139060 }, { "epoch": 33.39, "learning_rate": 6.586078854126519e-05, "loss": 0.0305, "step": 139070 }, { "epoch": 33.39, "learning_rate": 6.585653324996257e-05, "loss": 0.0237, "step": 139080 }, { "epoch": 33.39, "learning_rate": 6.58522778309651e-05, "loss": 0.03, "step": 139090 }, { "epoch": 33.39, "learning_rate": 6.584802228430705e-05, "loss": 0.0334, "step": 139100 }, { "epoch": 33.4, "learning_rate": 6.584376661002267e-05, "loss": 0.0371, "step": 139110 }, { "epoch": 33.4, "learning_rate": 6.583951080814627e-05, "loss": 0.036, "step": 139120 }, { "epoch": 33.4, "learning_rate": 6.58352548787121e-05, "loss": 0.0468, "step": 139130 }, { "epoch": 33.4, "learning_rate": 6.583099882175443e-05, "loss": 0.0391, "step": 139140 }, { "epoch": 33.4, "learning_rate": 6.582674263730754e-05, "loss": 0.0404, "step": 139150 }, { "epoch": 33.41, "learning_rate": 6.582248632540572e-05, "loss": 0.0254, "step": 139160 }, { "epoch": 33.41, "learning_rate": 6.581822988608322e-05, "loss": 0.0246, "step": 139170 }, { "epoch": 33.41, "learning_rate": 6.581397331937433e-05, "loss": 0.0252, "step": 139180 }, { "epoch": 33.41, "learning_rate": 6.580971662531334e-05, "loss": 0.0172, "step": 139190 }, { "epoch": 33.42, "learning_rate": 6.580545980393451e-05, "loss": 0.0487, "step": 139200 }, { "epoch": 33.42, "learning_rate": 6.580120285527213e-05, "loss": 0.0327, "step": 139210 }, { "epoch": 33.42, "learning_rate": 6.57969457793605e-05, "loss": 0.0175, "step": 139220 }, { "epoch": 33.42, "learning_rate": 6.579268857623387e-05, "loss": 0.0246, "step": 139230 }, { "epoch": 33.43, "learning_rate": 6.578843124592654e-05, "loss": 0.0334, "step": 139240 }, { "epoch": 33.43, "learning_rate": 6.57841737884728e-05, "loss": 0.0493, "step": 139250 }, { "epoch": 33.43, "learning_rate": 6.577991620390691e-05, "loss": 0.0176, "step": 139260 }, { "epoch": 33.43, "learning_rate": 6.57756584922632e-05, "loss": 0.0348, "step": 139270 }, { "epoch": 33.43, "learning_rate": 6.577140065357591e-05, "loss": 0.0313, "step": 139280 }, { "epoch": 33.44, "learning_rate": 6.576714268787937e-05, "loss": 0.0177, "step": 139290 }, { "epoch": 33.44, "learning_rate": 6.576288459520785e-05, "loss": 0.0308, "step": 139300 }, { "epoch": 33.44, "learning_rate": 6.575862637559564e-05, "loss": 0.0221, "step": 139310 }, { "epoch": 33.44, "learning_rate": 6.575436802907704e-05, "loss": 0.025, "step": 139320 }, { "epoch": 33.45, "learning_rate": 6.575010955568634e-05, "loss": 0.0269, "step": 139330 }, { "epoch": 33.45, "learning_rate": 6.574585095545783e-05, "loss": 0.0446, "step": 139340 }, { "epoch": 33.45, "learning_rate": 6.574159222842581e-05, "loss": 0.0323, "step": 139350 }, { "epoch": 33.45, "learning_rate": 6.573733337462458e-05, "loss": 0.0362, "step": 139360 }, { "epoch": 33.45, "learning_rate": 6.573307439408843e-05, "loss": 0.0156, "step": 139370 }, { "epoch": 33.46, "learning_rate": 6.572881528685165e-05, "loss": 0.0171, "step": 139380 }, { "epoch": 33.46, "learning_rate": 6.572455605294856e-05, "loss": 0.0351, "step": 139390 }, { "epoch": 33.46, "learning_rate": 6.572029669241344e-05, "loss": 0.0348, "step": 139400 }, { "epoch": 33.46, "learning_rate": 6.57160372052806e-05, "loss": 0.0321, "step": 139410 }, { "epoch": 33.47, "learning_rate": 6.571177759158435e-05, "loss": 0.0166, "step": 139420 }, { "epoch": 33.47, "learning_rate": 6.570751785135899e-05, "loss": 0.037, "step": 139430 }, { "epoch": 33.47, "learning_rate": 6.570325798463881e-05, "loss": 0.0294, "step": 139440 }, { "epoch": 33.47, "learning_rate": 6.569899799145813e-05, "loss": 0.025, "step": 139450 }, { "epoch": 33.48, "learning_rate": 6.569473787185125e-05, "loss": 0.0189, "step": 139460 }, { "epoch": 33.48, "learning_rate": 6.569047762585247e-05, "loss": 0.0281, "step": 139470 }, { "epoch": 33.48, "learning_rate": 6.568621725349613e-05, "loss": 0.0226, "step": 139480 }, { "epoch": 33.48, "learning_rate": 6.56819567548165e-05, "loss": 0.0257, "step": 139490 }, { "epoch": 33.48, "learning_rate": 6.567769612984793e-05, "loss": 0.0309, "step": 139500 }, { "epoch": 33.49, "learning_rate": 6.567343537862467e-05, "loss": 0.0125, "step": 139510 }, { "epoch": 33.49, "learning_rate": 6.566917450118108e-05, "loss": 0.0363, "step": 139520 }, { "epoch": 33.49, "learning_rate": 6.566491349755149e-05, "loss": 0.0596, "step": 139530 }, { "epoch": 33.49, "learning_rate": 6.566065236777017e-05, "loss": 0.0349, "step": 139540 }, { "epoch": 33.5, "learning_rate": 6.565639111187147e-05, "loss": 0.0191, "step": 139550 }, { "epoch": 33.5, "learning_rate": 6.565212972988967e-05, "loss": 0.0219, "step": 139560 }, { "epoch": 33.5, "learning_rate": 6.564786822185913e-05, "loss": 0.0204, "step": 139570 }, { "epoch": 33.5, "learning_rate": 6.564360658781413e-05, "loss": 0.0384, "step": 139580 }, { "epoch": 33.51, "learning_rate": 6.5639344827789e-05, "loss": 0.0415, "step": 139590 }, { "epoch": 33.51, "learning_rate": 6.563508294181808e-05, "loss": 0.0286, "step": 139600 }, { "epoch": 33.51, "learning_rate": 6.563082092993569e-05, "loss": 0.0667, "step": 139610 }, { "epoch": 33.51, "learning_rate": 6.562655879217613e-05, "loss": 0.0248, "step": 139620 }, { "epoch": 33.51, "learning_rate": 6.562229652857373e-05, "loss": 0.0196, "step": 139630 }, { "epoch": 33.52, "learning_rate": 6.561803413916283e-05, "loss": 0.0396, "step": 139640 }, { "epoch": 33.52, "learning_rate": 6.561377162397772e-05, "loss": 0.0223, "step": 139650 }, { "epoch": 33.52, "learning_rate": 6.560950898305278e-05, "loss": 0.0115, "step": 139660 }, { "epoch": 33.52, "learning_rate": 6.56052462164223e-05, "loss": 0.0319, "step": 139670 }, { "epoch": 33.53, "learning_rate": 6.560098332412061e-05, "loss": 0.0368, "step": 139680 }, { "epoch": 33.53, "learning_rate": 6.559672030618206e-05, "loss": 0.0239, "step": 139690 }, { "epoch": 33.53, "learning_rate": 6.559245716264095e-05, "loss": 0.0231, "step": 139700 }, { "epoch": 33.53, "learning_rate": 6.558819389353165e-05, "loss": 0.0195, "step": 139710 }, { "epoch": 33.53, "learning_rate": 6.558393049888846e-05, "loss": 0.026, "step": 139720 }, { "epoch": 33.54, "learning_rate": 6.557966697874573e-05, "loss": 0.035, "step": 139730 }, { "epoch": 33.54, "learning_rate": 6.557540333313778e-05, "loss": 0.0425, "step": 139740 }, { "epoch": 33.54, "learning_rate": 6.557113956209896e-05, "loss": 0.0212, "step": 139750 }, { "epoch": 33.54, "learning_rate": 6.556687566566363e-05, "loss": 0.0237, "step": 139760 }, { "epoch": 33.55, "learning_rate": 6.556261164386607e-05, "loss": 0.025, "step": 139770 }, { "epoch": 33.55, "learning_rate": 6.555834749674068e-05, "loss": 0.0201, "step": 139780 }, { "epoch": 33.55, "learning_rate": 6.555408322432174e-05, "loss": 0.0345, "step": 139790 }, { "epoch": 33.55, "learning_rate": 6.554981882664363e-05, "loss": 0.0275, "step": 139800 }, { "epoch": 33.56, "learning_rate": 6.554555430374068e-05, "loss": 0.0277, "step": 139810 }, { "epoch": 33.56, "learning_rate": 6.554128965564723e-05, "loss": 0.0179, "step": 139820 }, { "epoch": 33.56, "learning_rate": 6.553702488239766e-05, "loss": 0.038, "step": 139830 }, { "epoch": 33.56, "learning_rate": 6.553275998402625e-05, "loss": 0.0382, "step": 139840 }, { "epoch": 33.56, "learning_rate": 6.552849496056739e-05, "loss": 0.0303, "step": 139850 }, { "epoch": 33.57, "learning_rate": 6.552422981205542e-05, "loss": 0.0381, "step": 139860 }, { "epoch": 33.57, "learning_rate": 6.551996453852469e-05, "loss": 0.0343, "step": 139870 }, { "epoch": 33.57, "learning_rate": 6.551569914000953e-05, "loss": 0.0216, "step": 139880 }, { "epoch": 33.57, "learning_rate": 6.55114336165443e-05, "loss": 0.036, "step": 139890 }, { "epoch": 33.58, "learning_rate": 6.550716796816337e-05, "loss": 0.0177, "step": 139900 }, { "epoch": 33.58, "learning_rate": 6.550290219490105e-05, "loss": 0.0369, "step": 139910 }, { "epoch": 33.58, "learning_rate": 6.549863629679173e-05, "loss": 0.0361, "step": 139920 }, { "epoch": 33.58, "learning_rate": 6.549437027386976e-05, "loss": 0.0555, "step": 139930 }, { "epoch": 33.59, "learning_rate": 6.549010412616948e-05, "loss": 0.0213, "step": 139940 }, { "epoch": 33.59, "learning_rate": 6.548583785372526e-05, "loss": 0.0319, "step": 139950 }, { "epoch": 33.59, "learning_rate": 6.548157145657144e-05, "loss": 0.0283, "step": 139960 }, { "epoch": 33.59, "learning_rate": 6.547730493474241e-05, "loss": 0.021, "step": 139970 }, { "epoch": 33.59, "learning_rate": 6.547303828827248e-05, "loss": 0.0492, "step": 139980 }, { "epoch": 33.6, "learning_rate": 6.546877151719605e-05, "loss": 0.024, "step": 139990 }, { "epoch": 33.6, "learning_rate": 6.546450462154748e-05, "loss": 0.042, "step": 140000 }, { "epoch": 33.6, "learning_rate": 6.546023760136109e-05, "loss": 0.0343, "step": 140010 }, { "epoch": 33.6, "learning_rate": 6.545597045667128e-05, "loss": 0.0235, "step": 140020 }, { "epoch": 33.61, "learning_rate": 6.545170318751242e-05, "loss": 0.0358, "step": 140030 }, { "epoch": 33.61, "learning_rate": 6.544743579391884e-05, "loss": 0.0273, "step": 140040 }, { "epoch": 33.61, "learning_rate": 6.544316827592495e-05, "loss": 0.0322, "step": 140050 }, { "epoch": 33.61, "learning_rate": 6.543890063356507e-05, "loss": 0.036, "step": 140060 }, { "epoch": 33.61, "learning_rate": 6.543463286687361e-05, "loss": 0.0572, "step": 140070 }, { "epoch": 33.62, "learning_rate": 6.543036497588491e-05, "loss": 0.0377, "step": 140080 }, { "epoch": 33.62, "learning_rate": 6.542609696063338e-05, "loss": 0.0409, "step": 140090 }, { "epoch": 33.62, "learning_rate": 6.542182882115332e-05, "loss": 0.0295, "step": 140100 }, { "epoch": 33.62, "learning_rate": 6.541756055747917e-05, "loss": 0.0547, "step": 140110 }, { "epoch": 33.63, "learning_rate": 6.541329216964527e-05, "loss": 0.0403, "step": 140120 }, { "epoch": 33.63, "learning_rate": 6.540902365768598e-05, "loss": 0.0341, "step": 140130 }, { "epoch": 33.63, "learning_rate": 6.540475502163572e-05, "loss": 0.0417, "step": 140140 }, { "epoch": 33.63, "learning_rate": 6.540048626152884e-05, "loss": 0.0337, "step": 140150 }, { "epoch": 33.64, "learning_rate": 6.53962173773997e-05, "loss": 0.0384, "step": 140160 }, { "epoch": 33.64, "learning_rate": 6.539194836928272e-05, "loss": 0.0251, "step": 140170 }, { "epoch": 33.64, "learning_rate": 6.538767923721223e-05, "loss": 0.0261, "step": 140180 }, { "epoch": 33.64, "learning_rate": 6.538340998122266e-05, "loss": 0.0464, "step": 140190 }, { "epoch": 33.64, "learning_rate": 6.537914060134834e-05, "loss": 0.0331, "step": 140200 }, { "epoch": 33.65, "learning_rate": 6.537487109762371e-05, "loss": 0.0187, "step": 140210 }, { "epoch": 33.65, "learning_rate": 6.537060147008308e-05, "loss": 0.0301, "step": 140220 }, { "epoch": 33.65, "learning_rate": 6.53663317187609e-05, "loss": 0.0441, "step": 140230 }, { "epoch": 33.65, "learning_rate": 6.536206184369152e-05, "loss": 0.0366, "step": 140240 }, { "epoch": 33.66, "learning_rate": 6.535779184490934e-05, "loss": 0.0293, "step": 140250 }, { "epoch": 33.66, "learning_rate": 6.535352172244875e-05, "loss": 0.0257, "step": 140260 }, { "epoch": 33.66, "learning_rate": 6.534925147634412e-05, "loss": 0.0338, "step": 140270 }, { "epoch": 33.66, "learning_rate": 6.534498110662985e-05, "loss": 0.0215, "step": 140280 }, { "epoch": 33.67, "learning_rate": 6.534071061334033e-05, "loss": 0.0318, "step": 140290 }, { "epoch": 33.67, "learning_rate": 6.533643999650994e-05, "loss": 0.0248, "step": 140300 }, { "epoch": 33.67, "learning_rate": 6.533216925617309e-05, "loss": 0.0267, "step": 140310 }, { "epoch": 33.67, "learning_rate": 6.532789839236416e-05, "loss": 0.0321, "step": 140320 }, { "epoch": 33.67, "learning_rate": 6.532362740511758e-05, "loss": 0.0527, "step": 140330 }, { "epoch": 33.68, "learning_rate": 6.531935629446766e-05, "loss": 0.0159, "step": 140340 }, { "epoch": 33.68, "learning_rate": 6.531508506044887e-05, "loss": 0.0388, "step": 140350 }, { "epoch": 33.68, "learning_rate": 6.53108137030956e-05, "loss": 0.0284, "step": 140360 }, { "epoch": 33.68, "learning_rate": 6.530654222244223e-05, "loss": 0.0589, "step": 140370 }, { "epoch": 33.69, "learning_rate": 6.530227061852315e-05, "loss": 0.0344, "step": 140380 }, { "epoch": 33.69, "learning_rate": 6.529799889137277e-05, "loss": 0.0364, "step": 140390 }, { "epoch": 33.69, "learning_rate": 6.529372704102551e-05, "loss": 0.0448, "step": 140400 }, { "epoch": 33.69, "learning_rate": 6.528945506751574e-05, "loss": 0.0217, "step": 140410 }, { "epoch": 33.69, "learning_rate": 6.528518297087788e-05, "loss": 0.0362, "step": 140420 }, { "epoch": 33.7, "learning_rate": 6.528091075114633e-05, "loss": 0.0192, "step": 140430 }, { "epoch": 33.7, "learning_rate": 6.527663840835551e-05, "loss": 0.0464, "step": 140440 }, { "epoch": 33.7, "learning_rate": 6.527236594253979e-05, "loss": 0.045, "step": 140450 }, { "epoch": 33.7, "learning_rate": 6.526809335373361e-05, "loss": 0.0228, "step": 140460 }, { "epoch": 33.71, "learning_rate": 6.526382064197136e-05, "loss": 0.0589, "step": 140470 }, { "epoch": 33.71, "learning_rate": 6.525954780728747e-05, "loss": 0.0232, "step": 140480 }, { "epoch": 33.71, "learning_rate": 6.525527484971633e-05, "loss": 0.0199, "step": 140490 }, { "epoch": 33.71, "learning_rate": 6.525100176929236e-05, "loss": 0.0147, "step": 140500 }, { "epoch": 33.72, "learning_rate": 6.524672856604994e-05, "loss": 0.0365, "step": 140510 }, { "epoch": 33.72, "learning_rate": 6.524245524002353e-05, "loss": 0.033, "step": 140520 }, { "epoch": 33.72, "learning_rate": 6.523818179124752e-05, "loss": 0.0245, "step": 140530 }, { "epoch": 33.72, "learning_rate": 6.523390821975634e-05, "loss": 0.0424, "step": 140540 }, { "epoch": 33.72, "learning_rate": 6.522963452558439e-05, "loss": 0.0317, "step": 140550 }, { "epoch": 33.73, "learning_rate": 6.522536070876608e-05, "loss": 0.0292, "step": 140560 }, { "epoch": 33.73, "learning_rate": 6.522108676933585e-05, "loss": 0.0278, "step": 140570 }, { "epoch": 33.73, "learning_rate": 6.521681270732809e-05, "loss": 0.0321, "step": 140580 }, { "epoch": 33.73, "learning_rate": 6.521253852277725e-05, "loss": 0.0371, "step": 140590 }, { "epoch": 33.74, "learning_rate": 6.520826421571773e-05, "loss": 0.0223, "step": 140600 }, { "epoch": 33.74, "learning_rate": 6.520398978618395e-05, "loss": 0.0395, "step": 140610 }, { "epoch": 33.74, "learning_rate": 6.519971523421037e-05, "loss": 0.0226, "step": 140620 }, { "epoch": 33.74, "learning_rate": 6.519544055983136e-05, "loss": 0.0205, "step": 140630 }, { "epoch": 33.75, "learning_rate": 6.519116576308138e-05, "loss": 0.0276, "step": 140640 }, { "epoch": 33.75, "learning_rate": 6.518689084399484e-05, "loss": 0.017, "step": 140650 }, { "epoch": 33.75, "learning_rate": 6.518261580260617e-05, "loss": 0.0366, "step": 140660 }, { "epoch": 33.75, "learning_rate": 6.51783406389498e-05, "loss": 0.0275, "step": 140670 }, { "epoch": 33.75, "learning_rate": 6.517406535306016e-05, "loss": 0.0374, "step": 140680 }, { "epoch": 33.76, "learning_rate": 6.51697899449717e-05, "loss": 0.0363, "step": 140690 }, { "epoch": 33.76, "learning_rate": 6.516551441471879e-05, "loss": 0.035, "step": 140700 }, { "epoch": 33.76, "learning_rate": 6.51612387623359e-05, "loss": 0.027, "step": 140710 }, { "epoch": 33.76, "learning_rate": 6.515696298785749e-05, "loss": 0.0239, "step": 140720 }, { "epoch": 33.77, "learning_rate": 6.515268709131794e-05, "loss": 0.0284, "step": 140730 }, { "epoch": 33.77, "learning_rate": 6.514841107275172e-05, "loss": 0.0246, "step": 140740 }, { "epoch": 33.77, "learning_rate": 6.514413493219325e-05, "loss": 0.042, "step": 140750 }, { "epoch": 33.77, "learning_rate": 6.513985866967698e-05, "loss": 0.0148, "step": 140760 }, { "epoch": 33.77, "learning_rate": 6.513558228523733e-05, "loss": 0.0454, "step": 140770 }, { "epoch": 33.78, "learning_rate": 6.513130577890874e-05, "loss": 0.0286, "step": 140780 }, { "epoch": 33.78, "learning_rate": 6.512702915072566e-05, "loss": 0.038, "step": 140790 }, { "epoch": 33.78, "learning_rate": 6.512275240072253e-05, "loss": 0.0312, "step": 140800 }, { "epoch": 33.78, "learning_rate": 6.511847552893378e-05, "loss": 0.0284, "step": 140810 }, { "epoch": 33.79, "learning_rate": 6.511419853539388e-05, "loss": 0.0317, "step": 140820 }, { "epoch": 33.79, "learning_rate": 6.510992142013723e-05, "loss": 0.0453, "step": 140830 }, { "epoch": 33.79, "learning_rate": 6.51056441831983e-05, "loss": 0.0424, "step": 140840 }, { "epoch": 33.79, "learning_rate": 6.510136682461154e-05, "loss": 0.0315, "step": 140850 }, { "epoch": 33.8, "learning_rate": 6.509708934441138e-05, "loss": 0.0343, "step": 140860 }, { "epoch": 33.8, "learning_rate": 6.509281174263229e-05, "loss": 0.0201, "step": 140870 }, { "epoch": 33.8, "learning_rate": 6.508853401930868e-05, "loss": 0.0245, "step": 140880 }, { "epoch": 33.8, "learning_rate": 6.508425617447504e-05, "loss": 0.0217, "step": 140890 }, { "epoch": 33.8, "learning_rate": 6.507997820816579e-05, "loss": 0.0187, "step": 140900 }, { "epoch": 33.81, "learning_rate": 6.50757001204154e-05, "loss": 0.0143, "step": 140910 }, { "epoch": 33.81, "learning_rate": 6.507142191125832e-05, "loss": 0.0192, "step": 140920 }, { "epoch": 33.81, "learning_rate": 6.506714358072899e-05, "loss": 0.0268, "step": 140930 }, { "epoch": 33.81, "learning_rate": 6.506286512886188e-05, "loss": 0.0222, "step": 140940 }, { "epoch": 33.82, "learning_rate": 6.505858655569144e-05, "loss": 0.0413, "step": 140950 }, { "epoch": 33.82, "learning_rate": 6.505430786125212e-05, "loss": 0.0164, "step": 140960 }, { "epoch": 33.82, "learning_rate": 6.505002904557837e-05, "loss": 0.0264, "step": 140970 }, { "epoch": 33.82, "learning_rate": 6.504575010870467e-05, "loss": 0.0259, "step": 140980 }, { "epoch": 33.83, "learning_rate": 6.504147105066546e-05, "loss": 0.0256, "step": 140990 }, { "epoch": 33.83, "learning_rate": 6.503719187149522e-05, "loss": 0.0281, "step": 141000 }, { "epoch": 33.83, "learning_rate": 6.503291257122839e-05, "loss": 0.0237, "step": 141010 }, { "epoch": 33.83, "learning_rate": 6.502863314989943e-05, "loss": 0.0168, "step": 141020 }, { "epoch": 33.83, "learning_rate": 6.502435360754283e-05, "loss": 0.0289, "step": 141030 }, { "epoch": 33.84, "learning_rate": 6.502007394419302e-05, "loss": 0.0302, "step": 141040 }, { "epoch": 33.84, "learning_rate": 6.501579415988449e-05, "loss": 0.0222, "step": 141050 }, { "epoch": 33.84, "learning_rate": 6.50115142546517e-05, "loss": 0.0229, "step": 141060 }, { "epoch": 33.84, "learning_rate": 6.50072342285291e-05, "loss": 0.0245, "step": 141070 }, { "epoch": 33.85, "learning_rate": 6.500295408155119e-05, "loss": 0.0349, "step": 141080 }, { "epoch": 33.85, "learning_rate": 6.49986738137524e-05, "loss": 0.024, "step": 141090 }, { "epoch": 33.85, "learning_rate": 6.499439342516722e-05, "loss": 0.051, "step": 141100 }, { "epoch": 33.85, "learning_rate": 6.499011291583014e-05, "loss": 0.0433, "step": 141110 }, { "epoch": 33.85, "learning_rate": 6.498583228577559e-05, "loss": 0.0296, "step": 141120 }, { "epoch": 33.86, "learning_rate": 6.498155153503808e-05, "loss": 0.0299, "step": 141130 }, { "epoch": 33.86, "learning_rate": 6.497727066365205e-05, "loss": 0.0248, "step": 141140 }, { "epoch": 33.86, "learning_rate": 6.497298967165202e-05, "loss": 0.0214, "step": 141150 }, { "epoch": 33.86, "learning_rate": 6.49687085590724e-05, "loss": 0.0387, "step": 141160 }, { "epoch": 33.87, "learning_rate": 6.496442732594772e-05, "loss": 0.032, "step": 141170 }, { "epoch": 33.87, "learning_rate": 6.496014597231245e-05, "loss": 0.0653, "step": 141180 }, { "epoch": 33.87, "learning_rate": 6.495586449820106e-05, "loss": 0.0377, "step": 141190 }, { "epoch": 33.87, "learning_rate": 6.495158290364801e-05, "loss": 0.0256, "step": 141200 }, { "epoch": 33.88, "learning_rate": 6.49473011886878e-05, "loss": 0.0326, "step": 141210 }, { "epoch": 33.88, "learning_rate": 6.494301935335494e-05, "loss": 0.0191, "step": 141220 }, { "epoch": 33.88, "learning_rate": 6.493873739768384e-05, "loss": 0.0215, "step": 141230 }, { "epoch": 33.88, "learning_rate": 6.493445532170906e-05, "loss": 0.0212, "step": 141240 }, { "epoch": 33.88, "learning_rate": 6.493017312546503e-05, "loss": 0.0192, "step": 141250 }, { "epoch": 33.89, "learning_rate": 6.492589080898626e-05, "loss": 0.0342, "step": 141260 }, { "epoch": 33.89, "learning_rate": 6.492160837230723e-05, "loss": 0.0243, "step": 141270 }, { "epoch": 33.89, "learning_rate": 6.491732581546242e-05, "loss": 0.0275, "step": 141280 }, { "epoch": 33.89, "learning_rate": 6.491304313848633e-05, "loss": 0.0561, "step": 141290 }, { "epoch": 33.9, "learning_rate": 6.490876034141346e-05, "loss": 0.0246, "step": 141300 }, { "epoch": 33.9, "learning_rate": 6.490447742427828e-05, "loss": 0.0451, "step": 141310 }, { "epoch": 33.9, "learning_rate": 6.490019438711528e-05, "loss": 0.024, "step": 141320 }, { "epoch": 33.9, "learning_rate": 6.489591122995894e-05, "loss": 0.0205, "step": 141330 }, { "epoch": 33.91, "learning_rate": 6.48916279528438e-05, "loss": 0.031, "step": 141340 }, { "epoch": 33.91, "learning_rate": 6.48873445558043e-05, "loss": 0.0364, "step": 141350 }, { "epoch": 33.91, "learning_rate": 6.488306103887499e-05, "loss": 0.0209, "step": 141360 }, { "epoch": 33.91, "learning_rate": 6.487877740209029e-05, "loss": 0.0325, "step": 141370 }, { "epoch": 33.91, "learning_rate": 6.487449364548476e-05, "loss": 0.022, "step": 141380 }, { "epoch": 33.92, "learning_rate": 6.48702097690929e-05, "loss": 0.0149, "step": 141390 }, { "epoch": 33.92, "learning_rate": 6.486592577294917e-05, "loss": 0.0329, "step": 141400 }, { "epoch": 33.92, "learning_rate": 6.48616416570881e-05, "loss": 0.0275, "step": 141410 }, { "epoch": 33.92, "learning_rate": 6.485735742154415e-05, "loss": 0.0253, "step": 141420 }, { "epoch": 33.93, "learning_rate": 6.485307306635188e-05, "loss": 0.0272, "step": 141430 }, { "epoch": 33.93, "learning_rate": 6.484878859154576e-05, "loss": 0.0224, "step": 141440 }, { "epoch": 33.93, "learning_rate": 6.484450399716027e-05, "loss": 0.0257, "step": 141450 }, { "epoch": 33.93, "learning_rate": 6.484021928322996e-05, "loss": 0.0314, "step": 141460 }, { "epoch": 33.93, "learning_rate": 6.48359344497893e-05, "loss": 0.0191, "step": 141470 }, { "epoch": 33.94, "learning_rate": 6.483164949687283e-05, "loss": 0.0393, "step": 141480 }, { "epoch": 33.94, "learning_rate": 6.482736442451503e-05, "loss": 0.0262, "step": 141490 }, { "epoch": 33.94, "learning_rate": 6.482307923275042e-05, "loss": 0.0222, "step": 141500 }, { "epoch": 33.94, "learning_rate": 6.481879392161351e-05, "loss": 0.069, "step": 141510 }, { "epoch": 33.95, "learning_rate": 6.48145084911388e-05, "loss": 0.0181, "step": 141520 }, { "epoch": 33.95, "learning_rate": 6.48102229413608e-05, "loss": 0.0184, "step": 141530 }, { "epoch": 33.95, "learning_rate": 6.480593727231404e-05, "loss": 0.0239, "step": 141540 }, { "epoch": 34.0, "learning_rate": 6.480165148403303e-05, "loss": 0.0368, "step": 141550 }, { "epoch": 34.0, "learning_rate": 6.479736557655228e-05, "loss": 0.0188, "step": 141560 }, { "epoch": 34.01, "learning_rate": 6.479307954990627e-05, "loss": 0.0241, "step": 141570 }, { "epoch": 34.01, "learning_rate": 6.478879340412958e-05, "loss": 0.0209, "step": 141580 }, { "epoch": 34.01, "learning_rate": 6.478450713925668e-05, "loss": 0.0313, "step": 141590 }, { "epoch": 34.01, "learning_rate": 6.478022075532212e-05, "loss": 0.038, "step": 141600 }, { "epoch": 34.02, "learning_rate": 6.477593425236037e-05, "loss": 0.028, "step": 141610 }, { "epoch": 34.02, "learning_rate": 6.4771647630406e-05, "loss": 0.0346, "step": 141620 }, { "epoch": 34.02, "learning_rate": 6.476736088949353e-05, "loss": 0.0355, "step": 141630 }, { "epoch": 34.02, "learning_rate": 6.476307402965743e-05, "loss": 0.0254, "step": 141640 }, { "epoch": 34.02, "learning_rate": 6.475878705093229e-05, "loss": 0.0355, "step": 141650 }, { "epoch": 34.03, "learning_rate": 6.475449995335256e-05, "loss": 0.0209, "step": 141660 }, { "epoch": 34.03, "learning_rate": 6.475021273695284e-05, "loss": 0.027, "step": 141670 }, { "epoch": 34.03, "learning_rate": 6.474592540176762e-05, "loss": 0.0273, "step": 141680 }, { "epoch": 34.03, "learning_rate": 6.474163794783141e-05, "loss": 0.0346, "step": 141690 }, { "epoch": 34.04, "learning_rate": 6.473735037517877e-05, "loss": 0.0284, "step": 141700 }, { "epoch": 34.04, "learning_rate": 6.473306268384418e-05, "loss": 0.0191, "step": 141710 }, { "epoch": 34.04, "learning_rate": 6.472877487386224e-05, "loss": 0.0198, "step": 141720 }, { "epoch": 34.04, "learning_rate": 6.472448694526743e-05, "loss": 0.0135, "step": 141730 }, { "epoch": 34.05, "learning_rate": 6.472019889809429e-05, "loss": 0.0351, "step": 141740 }, { "epoch": 34.05, "learning_rate": 6.471591073237736e-05, "loss": 0.0195, "step": 141750 }, { "epoch": 34.05, "learning_rate": 6.471162244815115e-05, "loss": 0.0392, "step": 141760 }, { "epoch": 34.05, "learning_rate": 6.470733404545025e-05, "loss": 0.0264, "step": 141770 }, { "epoch": 34.05, "learning_rate": 6.470304552430913e-05, "loss": 0.0296, "step": 141780 }, { "epoch": 34.06, "learning_rate": 6.469875688476237e-05, "loss": 0.0164, "step": 141790 }, { "epoch": 34.06, "learning_rate": 6.469446812684447e-05, "loss": 0.0213, "step": 141800 }, { "epoch": 34.06, "learning_rate": 6.469017925059002e-05, "loss": 0.0298, "step": 141810 }, { "epoch": 34.06, "learning_rate": 6.46858902560335e-05, "loss": 0.021, "step": 141820 }, { "epoch": 34.07, "learning_rate": 6.46816011432095e-05, "loss": 0.0559, "step": 141830 }, { "epoch": 34.07, "learning_rate": 6.467731191215254e-05, "loss": 0.0178, "step": 141840 }, { "epoch": 34.07, "learning_rate": 6.467302256289713e-05, "loss": 0.0313, "step": 141850 }, { "epoch": 34.07, "learning_rate": 6.466873309547788e-05, "loss": 0.0367, "step": 141860 }, { "epoch": 34.07, "learning_rate": 6.466444350992928e-05, "loss": 0.0249, "step": 141870 }, { "epoch": 34.08, "learning_rate": 6.46601538062859e-05, "loss": 0.0316, "step": 141880 }, { "epoch": 34.08, "learning_rate": 6.465586398458227e-05, "loss": 0.0538, "step": 141890 }, { "epoch": 34.08, "learning_rate": 6.465157404485294e-05, "loss": 0.0217, "step": 141900 }, { "epoch": 34.08, "learning_rate": 6.464728398713247e-05, "loss": 0.0362, "step": 141910 }, { "epoch": 34.09, "learning_rate": 6.46429938114554e-05, "loss": 0.0255, "step": 141920 }, { "epoch": 34.09, "learning_rate": 6.463870351785626e-05, "loss": 0.0363, "step": 141930 }, { "epoch": 34.09, "learning_rate": 6.463441310636965e-05, "loss": 0.0308, "step": 141940 }, { "epoch": 34.09, "learning_rate": 6.463012257703008e-05, "loss": 0.0204, "step": 141950 }, { "epoch": 34.1, "learning_rate": 6.46258319298721e-05, "loss": 0.0261, "step": 141960 }, { "epoch": 34.1, "learning_rate": 6.462154116493028e-05, "loss": 0.0415, "step": 141970 }, { "epoch": 34.1, "learning_rate": 6.461725028223917e-05, "loss": 0.0261, "step": 141980 }, { "epoch": 34.1, "learning_rate": 6.461295928183334e-05, "loss": 0.0189, "step": 141990 }, { "epoch": 34.1, "learning_rate": 6.460866816374733e-05, "loss": 0.0472, "step": 142000 }, { "epoch": 34.11, "learning_rate": 6.460437692801569e-05, "loss": 0.0179, "step": 142010 }, { "epoch": 34.11, "learning_rate": 6.460008557467298e-05, "loss": 0.0238, "step": 142020 }, { "epoch": 34.11, "learning_rate": 6.459579410375378e-05, "loss": 0.0333, "step": 142030 }, { "epoch": 34.11, "learning_rate": 6.459150251529261e-05, "loss": 0.0284, "step": 142040 }, { "epoch": 34.12, "learning_rate": 6.458721080932408e-05, "loss": 0.0338, "step": 142050 }, { "epoch": 34.12, "learning_rate": 6.458291898588273e-05, "loss": 0.0538, "step": 142060 }, { "epoch": 34.12, "learning_rate": 6.457862704500311e-05, "loss": 0.016, "step": 142070 }, { "epoch": 34.12, "learning_rate": 6.457433498671978e-05, "loss": 0.0222, "step": 142080 }, { "epoch": 34.13, "learning_rate": 6.457004281106733e-05, "loss": 0.0604, "step": 142090 }, { "epoch": 34.13, "learning_rate": 6.456575051808033e-05, "loss": 0.0324, "step": 142100 }, { "epoch": 34.13, "learning_rate": 6.456145810779331e-05, "loss": 0.0298, "step": 142110 }, { "epoch": 34.13, "learning_rate": 6.455716558024087e-05, "loss": 0.0243, "step": 142120 }, { "epoch": 34.13, "learning_rate": 6.455287293545756e-05, "loss": 0.0381, "step": 142130 }, { "epoch": 34.14, "learning_rate": 6.454858017347795e-05, "loss": 0.0287, "step": 142140 }, { "epoch": 34.14, "learning_rate": 6.454428729433663e-05, "loss": 0.0339, "step": 142150 }, { "epoch": 34.14, "learning_rate": 6.453999429806814e-05, "loss": 0.0226, "step": 142160 }, { "epoch": 34.14, "learning_rate": 6.453570118470708e-05, "loss": 0.0356, "step": 142170 }, { "epoch": 34.15, "learning_rate": 6.453140795428801e-05, "loss": 0.033, "step": 142180 }, { "epoch": 34.15, "learning_rate": 6.45271146068455e-05, "loss": 0.0124, "step": 142190 }, { "epoch": 34.15, "learning_rate": 6.452282114241413e-05, "loss": 0.0598, "step": 142200 }, { "epoch": 34.15, "learning_rate": 6.451852756102848e-05, "loss": 0.0159, "step": 142210 }, { "epoch": 34.15, "learning_rate": 6.451423386272312e-05, "loss": 0.0159, "step": 142220 }, { "epoch": 34.16, "learning_rate": 6.450994004753263e-05, "loss": 0.0211, "step": 142230 }, { "epoch": 34.16, "learning_rate": 6.45056461154916e-05, "loss": 0.027, "step": 142240 }, { "epoch": 34.16, "learning_rate": 6.450135206663459e-05, "loss": 0.0372, "step": 142250 }, { "epoch": 34.16, "learning_rate": 6.449705790099619e-05, "loss": 0.0271, "step": 142260 }, { "epoch": 34.17, "learning_rate": 6.449276361861099e-05, "loss": 0.0554, "step": 142270 }, { "epoch": 34.17, "learning_rate": 6.448846921951355e-05, "loss": 0.0259, "step": 142280 }, { "epoch": 34.17, "learning_rate": 6.448417470373847e-05, "loss": 0.0384, "step": 142290 }, { "epoch": 34.17, "learning_rate": 6.447988007132035e-05, "loss": 0.014, "step": 142300 }, { "epoch": 34.18, "learning_rate": 6.447558532229373e-05, "loss": 0.0215, "step": 142310 }, { "epoch": 34.18, "learning_rate": 6.447129045669324e-05, "loss": 0.0324, "step": 142320 }, { "epoch": 34.18, "learning_rate": 6.446699547455345e-05, "loss": 0.0215, "step": 142330 }, { "epoch": 34.18, "learning_rate": 6.446270037590894e-05, "loss": 0.0291, "step": 142340 }, { "epoch": 34.18, "learning_rate": 6.445840516079432e-05, "loss": 0.0144, "step": 142350 }, { "epoch": 34.19, "learning_rate": 6.445410982924415e-05, "loss": 0.0275, "step": 142360 }, { "epoch": 34.19, "learning_rate": 6.444981438129305e-05, "loss": 0.0192, "step": 142370 }, { "epoch": 34.19, "learning_rate": 6.44455188169756e-05, "loss": 0.0167, "step": 142380 }, { "epoch": 34.19, "learning_rate": 6.444122313632638e-05, "loss": 0.0324, "step": 142390 }, { "epoch": 34.2, "learning_rate": 6.443692733938e-05, "loss": 0.0266, "step": 142400 }, { "epoch": 34.2, "learning_rate": 6.443263142617106e-05, "loss": 0.0184, "step": 142410 }, { "epoch": 34.2, "learning_rate": 6.442833539673414e-05, "loss": 0.0306, "step": 142420 }, { "epoch": 34.2, "learning_rate": 6.442403925110385e-05, "loss": 0.0325, "step": 142430 }, { "epoch": 34.21, "learning_rate": 6.441974298931477e-05, "loss": 0.0143, "step": 142440 }, { "epoch": 34.21, "learning_rate": 6.441544661140152e-05, "loss": 0.0197, "step": 142450 }, { "epoch": 34.21, "learning_rate": 6.441115011739869e-05, "loss": 0.0379, "step": 142460 }, { "epoch": 34.21, "learning_rate": 6.440685350734087e-05, "loss": 0.0246, "step": 142470 }, { "epoch": 34.21, "learning_rate": 6.440255678126265e-05, "loss": 0.0309, "step": 142480 }, { "epoch": 34.22, "learning_rate": 6.439825993919868e-05, "loss": 0.0223, "step": 142490 }, { "epoch": 34.22, "learning_rate": 6.439396298118354e-05, "loss": 0.0291, "step": 142500 }, { "epoch": 34.22, "learning_rate": 6.438966590725182e-05, "loss": 0.0235, "step": 142510 }, { "epoch": 34.22, "learning_rate": 6.438536871743812e-05, "loss": 0.0188, "step": 142520 }, { "epoch": 34.23, "learning_rate": 6.438107141177708e-05, "loss": 0.0342, "step": 142530 }, { "epoch": 34.23, "learning_rate": 6.437677399030327e-05, "loss": 0.0322, "step": 142540 }, { "epoch": 34.23, "learning_rate": 6.437247645305133e-05, "loss": 0.0196, "step": 142550 }, { "epoch": 34.23, "learning_rate": 6.436817880005583e-05, "loss": 0.053, "step": 142560 }, { "epoch": 34.23, "learning_rate": 6.436388103135142e-05, "loss": 0.0177, "step": 142570 }, { "epoch": 34.24, "learning_rate": 6.43595831469727e-05, "loss": 0.0223, "step": 142580 }, { "epoch": 34.24, "learning_rate": 6.435528514695426e-05, "loss": 0.0278, "step": 142590 }, { "epoch": 34.24, "learning_rate": 6.435098703133072e-05, "loss": 0.0457, "step": 142600 }, { "epoch": 34.24, "learning_rate": 6.434668880013672e-05, "loss": 0.0319, "step": 142610 }, { "epoch": 34.25, "learning_rate": 6.434239045340685e-05, "loss": 0.0288, "step": 142620 }, { "epoch": 34.25, "learning_rate": 6.433809199117572e-05, "loss": 0.0203, "step": 142630 }, { "epoch": 34.25, "learning_rate": 6.433379341347797e-05, "loss": 0.0225, "step": 142640 }, { "epoch": 34.25, "learning_rate": 6.432949472034817e-05, "loss": 0.0483, "step": 142650 }, { "epoch": 34.26, "learning_rate": 6.432519591182102e-05, "loss": 0.0213, "step": 142660 }, { "epoch": 34.26, "learning_rate": 6.432089698793104e-05, "loss": 0.0268, "step": 142670 }, { "epoch": 34.26, "learning_rate": 6.431659794871294e-05, "loss": 0.0273, "step": 142680 }, { "epoch": 34.26, "learning_rate": 6.431229879420127e-05, "loss": 0.0259, "step": 142690 }, { "epoch": 34.26, "learning_rate": 6.43079995244307e-05, "loss": 0.0297, "step": 142700 }, { "epoch": 34.27, "learning_rate": 6.430370013943583e-05, "loss": 0.0104, "step": 142710 }, { "epoch": 34.27, "learning_rate": 6.429940063925128e-05, "loss": 0.0302, "step": 142720 }, { "epoch": 34.27, "learning_rate": 6.429510102391171e-05, "loss": 0.0216, "step": 142730 }, { "epoch": 34.27, "learning_rate": 6.429080129345169e-05, "loss": 0.0336, "step": 142740 }, { "epoch": 34.28, "learning_rate": 6.428650144790588e-05, "loss": 0.0161, "step": 142750 }, { "epoch": 34.28, "learning_rate": 6.42822014873089e-05, "loss": 0.029, "step": 142760 }, { "epoch": 34.28, "learning_rate": 6.427790141169539e-05, "loss": 0.0381, "step": 142770 }, { "epoch": 34.28, "learning_rate": 6.427360122109996e-05, "loss": 0.0188, "step": 142780 }, { "epoch": 34.29, "learning_rate": 6.426930091555725e-05, "loss": 0.0427, "step": 142790 }, { "epoch": 34.29, "learning_rate": 6.426500049510191e-05, "loss": 0.0375, "step": 142800 }, { "epoch": 34.29, "learning_rate": 6.426069995976852e-05, "loss": 0.0305, "step": 142810 }, { "epoch": 34.29, "learning_rate": 6.425639930959176e-05, "loss": 0.011, "step": 142820 }, { "epoch": 34.29, "learning_rate": 6.425209854460624e-05, "loss": 0.0296, "step": 142830 }, { "epoch": 34.3, "learning_rate": 6.424779766484659e-05, "loss": 0.0165, "step": 142840 }, { "epoch": 34.3, "learning_rate": 6.42434966703475e-05, "loss": 0.0257, "step": 142850 }, { "epoch": 34.3, "learning_rate": 6.423919556114352e-05, "loss": 0.0457, "step": 142860 }, { "epoch": 34.3, "learning_rate": 6.423489433726937e-05, "loss": 0.0359, "step": 142870 }, { "epoch": 34.31, "learning_rate": 6.423059299875963e-05, "loss": 0.026, "step": 142880 }, { "epoch": 34.31, "learning_rate": 6.422629154564897e-05, "loss": 0.0326, "step": 142890 }, { "epoch": 34.31, "learning_rate": 6.4221989977972e-05, "loss": 0.0163, "step": 142900 }, { "epoch": 34.31, "learning_rate": 6.42176882957634e-05, "loss": 0.0267, "step": 142910 }, { "epoch": 34.31, "learning_rate": 6.421338649905779e-05, "loss": 0.0244, "step": 142920 }, { "epoch": 34.32, "learning_rate": 6.420908458788981e-05, "loss": 0.0393, "step": 142930 }, { "epoch": 34.32, "learning_rate": 6.420478256229412e-05, "loss": 0.0289, "step": 142940 }, { "epoch": 34.32, "learning_rate": 6.420048042230535e-05, "loss": 0.018, "step": 142950 }, { "epoch": 34.32, "learning_rate": 6.419617816795815e-05, "loss": 0.0242, "step": 142960 }, { "epoch": 34.33, "learning_rate": 6.419187579928717e-05, "loss": 0.0244, "step": 142970 }, { "epoch": 34.33, "learning_rate": 6.418757331632704e-05, "loss": 0.0355, "step": 142980 }, { "epoch": 34.33, "learning_rate": 6.418327071911246e-05, "loss": 0.0201, "step": 142990 }, { "epoch": 34.33, "learning_rate": 6.417896800767801e-05, "loss": 0.0412, "step": 143000 }, { "epoch": 34.34, "learning_rate": 6.417466518205837e-05, "loss": 0.0261, "step": 143010 }, { "epoch": 34.34, "learning_rate": 6.417036224228821e-05, "loss": 0.0218, "step": 143020 }, { "epoch": 34.34, "learning_rate": 6.416605918840217e-05, "loss": 0.0271, "step": 143030 }, { "epoch": 34.34, "learning_rate": 6.416175602043489e-05, "loss": 0.0355, "step": 143040 }, { "epoch": 34.34, "learning_rate": 6.415745273842103e-05, "loss": 0.0323, "step": 143050 }, { "epoch": 34.35, "learning_rate": 6.415314934239526e-05, "loss": 0.0209, "step": 143060 }, { "epoch": 34.35, "learning_rate": 6.414884583239223e-05, "loss": 0.0287, "step": 143070 }, { "epoch": 34.35, "learning_rate": 6.414454220844656e-05, "loss": 0.0426, "step": 143080 }, { "epoch": 34.35, "learning_rate": 6.414023847059297e-05, "loss": 0.0153, "step": 143090 }, { "epoch": 34.36, "learning_rate": 6.413593461886607e-05, "loss": 0.0189, "step": 143100 }, { "epoch": 34.36, "learning_rate": 6.413163065330055e-05, "loss": 0.0316, "step": 143110 }, { "epoch": 34.36, "learning_rate": 6.412732657393104e-05, "loss": 0.0147, "step": 143120 }, { "epoch": 34.36, "learning_rate": 6.412302238079224e-05, "loss": 0.0311, "step": 143130 }, { "epoch": 34.37, "learning_rate": 6.411871807391878e-05, "loss": 0.0244, "step": 143140 }, { "epoch": 34.37, "learning_rate": 6.411441365334532e-05, "loss": 0.0228, "step": 143150 }, { "epoch": 34.37, "learning_rate": 6.411010911910657e-05, "loss": 0.0278, "step": 143160 }, { "epoch": 34.37, "learning_rate": 6.410580447123713e-05, "loss": 0.0144, "step": 143170 }, { "epoch": 34.37, "learning_rate": 6.410149970977173e-05, "loss": 0.0366, "step": 143180 }, { "epoch": 34.38, "learning_rate": 6.409719483474498e-05, "loss": 0.0308, "step": 143190 }, { "epoch": 34.38, "learning_rate": 6.40928898461916e-05, "loss": 0.0216, "step": 143200 }, { "epoch": 34.38, "learning_rate": 6.408858474414621e-05, "loss": 0.0295, "step": 143210 }, { "epoch": 34.38, "learning_rate": 6.40842795286435e-05, "loss": 0.0138, "step": 143220 }, { "epoch": 34.39, "learning_rate": 6.407997419971816e-05, "loss": 0.0324, "step": 143230 }, { "epoch": 34.39, "learning_rate": 6.407566875740483e-05, "loss": 0.0192, "step": 143240 }, { "epoch": 34.39, "learning_rate": 6.40713632017382e-05, "loss": 0.0336, "step": 143250 }, { "epoch": 34.39, "learning_rate": 6.406705753275294e-05, "loss": 0.0242, "step": 143260 }, { "epoch": 34.39, "learning_rate": 6.406275175048373e-05, "loss": 0.0178, "step": 143270 }, { "epoch": 34.4, "learning_rate": 6.405844585496524e-05, "loss": 0.0253, "step": 143280 }, { "epoch": 34.4, "learning_rate": 6.405413984623214e-05, "loss": 0.0283, "step": 143290 }, { "epoch": 34.4, "learning_rate": 6.404983372431911e-05, "loss": 0.0137, "step": 143300 }, { "epoch": 34.4, "learning_rate": 6.404552748926082e-05, "loss": 0.0382, "step": 143310 }, { "epoch": 34.41, "learning_rate": 6.404122114109196e-05, "loss": 0.0349, "step": 143320 }, { "epoch": 34.41, "learning_rate": 6.403691467984723e-05, "loss": 0.0298, "step": 143330 }, { "epoch": 34.41, "learning_rate": 6.403260810556128e-05, "loss": 0.0314, "step": 143340 }, { "epoch": 34.41, "learning_rate": 6.40283014182688e-05, "loss": 0.0186, "step": 143350 }, { "epoch": 34.42, "learning_rate": 6.402399461800443e-05, "loss": 0.0377, "step": 143360 }, { "epoch": 34.42, "learning_rate": 6.401968770480295e-05, "loss": 0.0271, "step": 143370 }, { "epoch": 34.42, "learning_rate": 6.401538067869896e-05, "loss": 0.0175, "step": 143380 }, { "epoch": 34.42, "learning_rate": 6.40110735397272e-05, "loss": 0.0225, "step": 143390 }, { "epoch": 34.42, "learning_rate": 6.40067662879223e-05, "loss": 0.0431, "step": 143400 }, { "epoch": 34.43, "learning_rate": 6.400245892331899e-05, "loss": 0.0307, "step": 143410 }, { "epoch": 34.43, "learning_rate": 6.399815144595196e-05, "loss": 0.0199, "step": 143420 }, { "epoch": 34.43, "learning_rate": 6.399384385585585e-05, "loss": 0.0174, "step": 143430 }, { "epoch": 34.43, "learning_rate": 6.398953615306541e-05, "loss": 0.0316, "step": 143440 }, { "epoch": 34.44, "learning_rate": 6.39852283376153e-05, "loss": 0.0262, "step": 143450 }, { "epoch": 34.44, "learning_rate": 6.398092040954022e-05, "loss": 0.0206, "step": 143460 }, { "epoch": 34.44, "learning_rate": 6.397661236887485e-05, "loss": 0.023, "step": 143470 }, { "epoch": 34.44, "learning_rate": 6.397230421565388e-05, "loss": 0.0302, "step": 143480 }, { "epoch": 34.45, "learning_rate": 6.396799594991203e-05, "loss": 0.0411, "step": 143490 }, { "epoch": 34.45, "learning_rate": 6.396368757168398e-05, "loss": 0.0255, "step": 143500 }, { "epoch": 34.45, "learning_rate": 6.395937908100442e-05, "loss": 0.0138, "step": 143510 }, { "epoch": 34.45, "learning_rate": 6.395507047790806e-05, "loss": 0.0126, "step": 143520 }, { "epoch": 34.45, "learning_rate": 6.39507617624296e-05, "loss": 0.0234, "step": 143530 }, { "epoch": 34.46, "learning_rate": 6.394645293460371e-05, "loss": 0.0498, "step": 143540 }, { "epoch": 34.46, "learning_rate": 6.39421439944651e-05, "loss": 0.0246, "step": 143550 }, { "epoch": 34.46, "learning_rate": 6.39378349420485e-05, "loss": 0.0239, "step": 143560 }, { "epoch": 34.46, "learning_rate": 6.393352577738859e-05, "loss": 0.0238, "step": 143570 }, { "epoch": 34.47, "learning_rate": 6.392921650052007e-05, "loss": 0.0271, "step": 143580 }, { "epoch": 34.47, "learning_rate": 6.392490711147765e-05, "loss": 0.0219, "step": 143590 }, { "epoch": 34.47, "learning_rate": 6.392059761029603e-05, "loss": 0.0223, "step": 143600 }, { "epoch": 34.47, "learning_rate": 6.391628799700991e-05, "loss": 0.0201, "step": 143610 }, { "epoch": 34.47, "learning_rate": 6.391197827165401e-05, "loss": 0.0517, "step": 143620 }, { "epoch": 34.48, "learning_rate": 6.390766843426301e-05, "loss": 0.036, "step": 143630 }, { "epoch": 34.48, "learning_rate": 6.390335848487166e-05, "loss": 0.0346, "step": 143640 }, { "epoch": 34.48, "learning_rate": 6.389904842351463e-05, "loss": 0.0179, "step": 143650 }, { "epoch": 34.48, "learning_rate": 6.389473825022665e-05, "loss": 0.0385, "step": 143660 }, { "epoch": 34.49, "learning_rate": 6.38904279650424e-05, "loss": 0.0237, "step": 143670 }, { "epoch": 34.49, "learning_rate": 6.388611756799666e-05, "loss": 0.0159, "step": 143680 }, { "epoch": 34.49, "learning_rate": 6.388180705912406e-05, "loss": 0.0248, "step": 143690 }, { "epoch": 34.49, "learning_rate": 6.387749643845938e-05, "loss": 0.0287, "step": 143700 }, { "epoch": 34.5, "learning_rate": 6.387318570603729e-05, "loss": 0.0313, "step": 143710 }, { "epoch": 34.5, "learning_rate": 6.386887486189253e-05, "loss": 0.0435, "step": 143720 }, { "epoch": 34.5, "learning_rate": 6.38645639060598e-05, "loss": 0.0279, "step": 143730 }, { "epoch": 34.5, "learning_rate": 6.38602528385738e-05, "loss": 0.0277, "step": 143740 }, { "epoch": 34.5, "learning_rate": 6.38559416594693e-05, "loss": 0.0363, "step": 143750 }, { "epoch": 34.51, "learning_rate": 6.385163036878097e-05, "loss": 0.0314, "step": 143760 }, { "epoch": 34.51, "learning_rate": 6.384731896654357e-05, "loss": 0.0239, "step": 143770 }, { "epoch": 34.51, "learning_rate": 6.38430074527918e-05, "loss": 0.0253, "step": 143780 }, { "epoch": 34.51, "learning_rate": 6.383869582756036e-05, "loss": 0.0305, "step": 143790 }, { "epoch": 34.52, "learning_rate": 6.383438409088398e-05, "loss": 0.0251, "step": 143800 }, { "epoch": 34.52, "learning_rate": 6.383007224279743e-05, "loss": 0.0367, "step": 143810 }, { "epoch": 34.52, "learning_rate": 6.382576028333537e-05, "loss": 0.0486, "step": 143820 }, { "epoch": 34.52, "learning_rate": 6.382144821253257e-05, "loss": 0.0289, "step": 143830 }, { "epoch": 34.53, "learning_rate": 6.381713603042374e-05, "loss": 0.0284, "step": 143840 }, { "epoch": 34.53, "learning_rate": 6.38128237370436e-05, "loss": 0.0399, "step": 143850 }, { "epoch": 34.53, "learning_rate": 6.380851133242689e-05, "loss": 0.0186, "step": 143860 }, { "epoch": 34.53, "learning_rate": 6.380419881660832e-05, "loss": 0.017, "step": 143870 }, { "epoch": 34.53, "learning_rate": 6.379988618962265e-05, "loss": 0.0502, "step": 143880 }, { "epoch": 34.54, "learning_rate": 6.379557345150458e-05, "loss": 0.0408, "step": 143890 }, { "epoch": 34.54, "learning_rate": 6.379126060228885e-05, "loss": 0.029, "step": 143900 }, { "epoch": 34.54, "learning_rate": 6.37869476420102e-05, "loss": 0.0283, "step": 143910 }, { "epoch": 34.54, "learning_rate": 6.378263457070334e-05, "loss": 0.027, "step": 143920 }, { "epoch": 34.55, "learning_rate": 6.377832138840304e-05, "loss": 0.0253, "step": 143930 }, { "epoch": 34.55, "learning_rate": 6.377400809514401e-05, "loss": 0.0461, "step": 143940 }, { "epoch": 34.55, "learning_rate": 6.376969469096098e-05, "loss": 0.0282, "step": 143950 }, { "epoch": 34.55, "learning_rate": 6.376538117588873e-05, "loss": 0.0251, "step": 143960 }, { "epoch": 34.55, "learning_rate": 6.376106754996194e-05, "loss": 0.0259, "step": 143970 }, { "epoch": 34.56, "learning_rate": 6.375675381321537e-05, "loss": 0.0199, "step": 143980 }, { "epoch": 34.56, "learning_rate": 6.375243996568377e-05, "loss": 0.0233, "step": 143990 }, { "epoch": 34.56, "learning_rate": 6.374812600740187e-05, "loss": 0.0577, "step": 144000 }, { "epoch": 34.56, "learning_rate": 6.374381193840441e-05, "loss": 0.0292, "step": 144010 }, { "epoch": 34.57, "learning_rate": 6.373949775872616e-05, "loss": 0.0318, "step": 144020 }, { "epoch": 34.57, "learning_rate": 6.373518346840182e-05, "loss": 0.0229, "step": 144030 }, { "epoch": 34.57, "learning_rate": 6.373086906746613e-05, "loss": 0.044, "step": 144040 }, { "epoch": 34.57, "learning_rate": 6.372655455595388e-05, "loss": 0.0351, "step": 144050 }, { "epoch": 34.58, "learning_rate": 6.372223993389979e-05, "loss": 0.0321, "step": 144060 }, { "epoch": 34.58, "learning_rate": 6.37179252013386e-05, "loss": 0.0287, "step": 144070 }, { "epoch": 34.58, "learning_rate": 6.371361035830507e-05, "loss": 0.0342, "step": 144080 }, { "epoch": 34.58, "learning_rate": 6.370929540483395e-05, "loss": 0.0229, "step": 144090 }, { "epoch": 34.58, "learning_rate": 6.370498034095997e-05, "loss": 0.0394, "step": 144100 }, { "epoch": 34.59, "learning_rate": 6.370066516671788e-05, "loss": 0.0446, "step": 144110 }, { "epoch": 34.59, "learning_rate": 6.369634988214246e-05, "loss": 0.0393, "step": 144120 }, { "epoch": 34.59, "learning_rate": 6.369203448726844e-05, "loss": 0.0201, "step": 144130 }, { "epoch": 34.59, "learning_rate": 6.368771898213057e-05, "loss": 0.0194, "step": 144140 }, { "epoch": 34.6, "learning_rate": 6.368340336676362e-05, "loss": 0.0411, "step": 144150 }, { "epoch": 34.6, "learning_rate": 6.367908764120232e-05, "loss": 0.0178, "step": 144160 }, { "epoch": 34.6, "learning_rate": 6.367477180548145e-05, "loss": 0.02, "step": 144170 }, { "epoch": 34.6, "learning_rate": 6.367045585963574e-05, "loss": 0.0287, "step": 144180 }, { "epoch": 34.61, "learning_rate": 6.366613980369999e-05, "loss": 0.0257, "step": 144190 }, { "epoch": 34.61, "learning_rate": 6.36618236377089e-05, "loss": 0.0225, "step": 144200 }, { "epoch": 34.61, "learning_rate": 6.365750736169727e-05, "loss": 0.0452, "step": 144210 }, { "epoch": 34.61, "learning_rate": 6.365319097569985e-05, "loss": 0.0403, "step": 144220 }, { "epoch": 34.61, "learning_rate": 6.364887447975139e-05, "loss": 0.0248, "step": 144230 }, { "epoch": 34.62, "learning_rate": 6.364455787388668e-05, "loss": 0.0319, "step": 144240 }, { "epoch": 34.62, "learning_rate": 6.364024115814043e-05, "loss": 0.0316, "step": 144250 }, { "epoch": 34.62, "learning_rate": 6.363592433254747e-05, "loss": 0.0267, "step": 144260 }, { "epoch": 34.62, "learning_rate": 6.36316073971425e-05, "loss": 0.0316, "step": 144270 }, { "epoch": 34.63, "learning_rate": 6.362729035196032e-05, "loss": 0.0276, "step": 144280 }, { "epoch": 34.63, "learning_rate": 6.362297319703569e-05, "loss": 0.0263, "step": 144290 }, { "epoch": 34.63, "learning_rate": 6.361865593240338e-05, "loss": 0.0259, "step": 144300 }, { "epoch": 34.63, "learning_rate": 6.361433855809816e-05, "loss": 0.0404, "step": 144310 }, { "epoch": 34.63, "learning_rate": 6.361002107415477e-05, "loss": 0.0323, "step": 144320 }, { "epoch": 34.64, "learning_rate": 6.360570348060803e-05, "loss": 0.0553, "step": 144330 }, { "epoch": 34.64, "learning_rate": 6.360138577749268e-05, "loss": 0.0299, "step": 144340 }, { "epoch": 34.64, "learning_rate": 6.359706796484346e-05, "loss": 0.0228, "step": 144350 }, { "epoch": 34.64, "learning_rate": 6.35927500426952e-05, "loss": 0.0344, "step": 144360 }, { "epoch": 34.65, "learning_rate": 6.358843201108264e-05, "loss": 0.0208, "step": 144370 }, { "epoch": 34.65, "learning_rate": 6.358411387004057e-05, "loss": 0.0149, "step": 144380 }, { "epoch": 34.65, "learning_rate": 6.357979561960374e-05, "loss": 0.0226, "step": 144390 }, { "epoch": 34.65, "learning_rate": 6.357547725980697e-05, "loss": 0.0406, "step": 144400 }, { "epoch": 34.66, "learning_rate": 6.357115879068498e-05, "loss": 0.0205, "step": 144410 }, { "epoch": 34.66, "learning_rate": 6.356684021227257e-05, "loss": 0.0274, "step": 144420 }, { "epoch": 34.66, "learning_rate": 6.356252152460455e-05, "loss": 0.0431, "step": 144430 }, { "epoch": 34.66, "learning_rate": 6.355820272771564e-05, "loss": 0.0464, "step": 144440 }, { "epoch": 34.66, "learning_rate": 6.355388382164066e-05, "loss": 0.028, "step": 144450 }, { "epoch": 34.67, "learning_rate": 6.35495648064144e-05, "loss": 0.0562, "step": 144460 }, { "epoch": 34.67, "learning_rate": 6.354524568207161e-05, "loss": 0.0424, "step": 144470 }, { "epoch": 34.67, "learning_rate": 6.35409264486471e-05, "loss": 0.0243, "step": 144480 }, { "epoch": 34.67, "learning_rate": 6.353660710617563e-05, "loss": 0.029, "step": 144490 }, { "epoch": 34.68, "learning_rate": 6.3532287654692e-05, "loss": 0.0357, "step": 144500 }, { "epoch": 34.68, "learning_rate": 6.352796809423098e-05, "loss": 0.0265, "step": 144510 }, { "epoch": 34.68, "learning_rate": 6.352364842482738e-05, "loss": 0.0198, "step": 144520 }, { "epoch": 34.68, "learning_rate": 6.351932864651595e-05, "loss": 0.0315, "step": 144530 }, { "epoch": 34.69, "learning_rate": 6.351500875933151e-05, "loss": 0.0239, "step": 144540 }, { "epoch": 34.69, "learning_rate": 6.351068876330886e-05, "loss": 0.0925, "step": 144550 }, { "epoch": 34.69, "learning_rate": 6.350636865848273e-05, "loss": 0.0357, "step": 144560 }, { "epoch": 34.69, "learning_rate": 6.350204844488796e-05, "loss": 0.0215, "step": 144570 }, { "epoch": 34.69, "learning_rate": 6.349772812255934e-05, "loss": 0.0298, "step": 144580 }, { "epoch": 34.7, "learning_rate": 6.349340769153165e-05, "loss": 0.0222, "step": 144590 }, { "epoch": 34.7, "learning_rate": 6.34890871518397e-05, "loss": 0.0207, "step": 144600 }, { "epoch": 34.7, "learning_rate": 6.348476650351824e-05, "loss": 0.033, "step": 144610 }, { "epoch": 34.7, "learning_rate": 6.348044574660211e-05, "loss": 0.0289, "step": 144620 }, { "epoch": 34.71, "learning_rate": 6.347612488112608e-05, "loss": 0.0119, "step": 144630 }, { "epoch": 34.71, "learning_rate": 6.347180390712497e-05, "loss": 0.0425, "step": 144640 }, { "epoch": 34.71, "learning_rate": 6.346748282463355e-05, "loss": 0.0663, "step": 144650 }, { "epoch": 34.71, "learning_rate": 6.346316163368663e-05, "loss": 0.0172, "step": 144660 }, { "epoch": 34.71, "learning_rate": 6.345884033431903e-05, "loss": 0.0273, "step": 144670 }, { "epoch": 34.72, "learning_rate": 6.345451892656552e-05, "loss": 0.0147, "step": 144680 }, { "epoch": 34.72, "learning_rate": 6.345019741046091e-05, "loss": 0.0415, "step": 144690 }, { "epoch": 34.72, "learning_rate": 6.344587578603999e-05, "loss": 0.0261, "step": 144700 }, { "epoch": 34.72, "learning_rate": 6.34415540533376e-05, "loss": 0.0282, "step": 144710 }, { "epoch": 34.73, "learning_rate": 6.34372322123885e-05, "loss": 0.025, "step": 144720 }, { "epoch": 34.73, "learning_rate": 6.34329102632275e-05, "loss": 0.0164, "step": 144730 }, { "epoch": 34.73, "learning_rate": 6.342858820588946e-05, "loss": 0.0145, "step": 144740 }, { "epoch": 34.73, "learning_rate": 6.342426604040913e-05, "loss": 0.0383, "step": 144750 }, { "epoch": 34.74, "learning_rate": 6.341994376682132e-05, "loss": 0.0286, "step": 144760 }, { "epoch": 34.74, "learning_rate": 6.341562138516086e-05, "loss": 0.0155, "step": 144770 }, { "epoch": 34.74, "learning_rate": 6.341129889546256e-05, "loss": 0.0307, "step": 144780 }, { "epoch": 34.74, "learning_rate": 6.34069762977612e-05, "loss": 0.0183, "step": 144790 }, { "epoch": 34.74, "learning_rate": 6.340265359209161e-05, "loss": 0.0302, "step": 144800 }, { "epoch": 34.75, "learning_rate": 6.339833077848862e-05, "loss": 0.0365, "step": 144810 }, { "epoch": 34.75, "learning_rate": 6.339400785698699e-05, "loss": 0.0215, "step": 144820 }, { "epoch": 34.75, "learning_rate": 6.338968482762158e-05, "loss": 0.0695, "step": 144830 }, { "epoch": 34.75, "learning_rate": 6.33853616904272e-05, "loss": 0.0279, "step": 144840 }, { "epoch": 34.76, "learning_rate": 6.338103844543864e-05, "loss": 0.0366, "step": 144850 }, { "epoch": 34.76, "learning_rate": 6.337671509269075e-05, "loss": 0.0245, "step": 144860 }, { "epoch": 34.76, "learning_rate": 6.33723916322183e-05, "loss": 0.0239, "step": 144870 }, { "epoch": 34.76, "learning_rate": 6.336806806405615e-05, "loss": 0.0242, "step": 144880 }, { "epoch": 34.77, "learning_rate": 6.33637443882391e-05, "loss": 0.0174, "step": 144890 }, { "epoch": 34.77, "learning_rate": 6.335942060480198e-05, "loss": 0.0252, "step": 144900 }, { "epoch": 34.77, "learning_rate": 6.33550967137796e-05, "loss": 0.0165, "step": 144910 }, { "epoch": 34.77, "learning_rate": 6.335077271520676e-05, "loss": 0.0353, "step": 144920 }, { "epoch": 34.77, "learning_rate": 6.334644860911833e-05, "loss": 0.0324, "step": 144930 }, { "epoch": 34.78, "learning_rate": 6.334212439554908e-05, "loss": 0.029, "step": 144940 }, { "epoch": 34.78, "learning_rate": 6.333780007453388e-05, "loss": 0.0185, "step": 144950 }, { "epoch": 34.78, "learning_rate": 6.333347564610753e-05, "loss": 0.024, "step": 144960 }, { "epoch": 34.78, "learning_rate": 6.332915111030487e-05, "loss": 0.03, "step": 144970 }, { "epoch": 34.79, "learning_rate": 6.33248264671607e-05, "loss": 0.0314, "step": 144980 }, { "epoch": 34.79, "learning_rate": 6.332050171670987e-05, "loss": 0.069, "step": 144990 }, { "epoch": 34.79, "learning_rate": 6.33161768589872e-05, "loss": 0.0546, "step": 145000 }, { "epoch": 34.79, "learning_rate": 6.331185189402752e-05, "loss": 0.0324, "step": 145010 }, { "epoch": 34.79, "learning_rate": 6.330752682186565e-05, "loss": 0.0177, "step": 145020 }, { "epoch": 34.8, "learning_rate": 6.330320164253645e-05, "loss": 0.0223, "step": 145030 }, { "epoch": 34.8, "learning_rate": 6.329887635607472e-05, "loss": 0.0243, "step": 145040 }, { "epoch": 34.8, "learning_rate": 6.32945509625153e-05, "loss": 0.0272, "step": 145050 }, { "epoch": 34.8, "learning_rate": 6.329022546189301e-05, "loss": 0.026, "step": 145060 }, { "epoch": 34.81, "learning_rate": 6.328589985424273e-05, "loss": 0.0285, "step": 145070 }, { "epoch": 34.81, "learning_rate": 6.328157413959925e-05, "loss": 0.0266, "step": 145080 }, { "epoch": 34.81, "learning_rate": 6.327724831799741e-05, "loss": 0.022, "step": 145090 }, { "epoch": 34.81, "learning_rate": 6.327292238947208e-05, "loss": 0.0377, "step": 145100 }, { "epoch": 34.82, "learning_rate": 6.326859635405806e-05, "loss": 0.0219, "step": 145110 }, { "epoch": 34.82, "learning_rate": 6.32642702117902e-05, "loss": 0.0216, "step": 145120 }, { "epoch": 34.82, "learning_rate": 6.325994396270334e-05, "loss": 0.0325, "step": 145130 }, { "epoch": 34.82, "learning_rate": 6.325561760683232e-05, "loss": 0.0396, "step": 145140 }, { "epoch": 34.82, "learning_rate": 6.325129114421198e-05, "loss": 0.0482, "step": 145150 }, { "epoch": 34.83, "learning_rate": 6.324696457487718e-05, "loss": 0.0515, "step": 145160 }, { "epoch": 34.83, "learning_rate": 6.324263789886274e-05, "loss": 0.0238, "step": 145170 }, { "epoch": 34.83, "learning_rate": 6.323831111620349e-05, "loss": 0.0205, "step": 145180 }, { "epoch": 34.83, "learning_rate": 6.32339842269343e-05, "loss": 0.0287, "step": 145190 }, { "epoch": 34.84, "learning_rate": 6.322965723109001e-05, "loss": 0.0206, "step": 145200 }, { "epoch": 34.84, "learning_rate": 6.322533012870547e-05, "loss": 0.0237, "step": 145210 }, { "epoch": 34.84, "learning_rate": 6.322100291981552e-05, "loss": 0.0172, "step": 145220 }, { "epoch": 34.84, "learning_rate": 6.3216675604455e-05, "loss": 0.0352, "step": 145230 }, { "epoch": 34.85, "learning_rate": 6.321234818265877e-05, "loss": 0.0441, "step": 145240 }, { "epoch": 34.85, "learning_rate": 6.320802065446168e-05, "loss": 0.0199, "step": 145250 }, { "epoch": 34.85, "learning_rate": 6.320369301989857e-05, "loss": 0.0394, "step": 145260 }, { "epoch": 34.85, "learning_rate": 6.31993652790043e-05, "loss": 0.0104, "step": 145270 }, { "epoch": 34.85, "learning_rate": 6.319503743181372e-05, "loss": 0.0179, "step": 145280 }, { "epoch": 34.86, "learning_rate": 6.319070947836169e-05, "loss": 0.028, "step": 145290 }, { "epoch": 34.86, "learning_rate": 6.318638141868304e-05, "loss": 0.0262, "step": 145300 }, { "epoch": 34.86, "learning_rate": 6.318205325281265e-05, "loss": 0.0225, "step": 145310 }, { "epoch": 34.86, "learning_rate": 6.317772498078536e-05, "loss": 0.0229, "step": 145320 }, { "epoch": 34.87, "learning_rate": 6.317339660263604e-05, "loss": 0.0438, "step": 145330 }, { "epoch": 34.87, "learning_rate": 6.316906811839953e-05, "loss": 0.0318, "step": 145340 }, { "epoch": 34.87, "learning_rate": 6.31647395281107e-05, "loss": 0.0301, "step": 145350 }, { "epoch": 34.87, "learning_rate": 6.31604108318044e-05, "loss": 0.0314, "step": 145360 }, { "epoch": 34.87, "learning_rate": 6.315608202951551e-05, "loss": 0.0283, "step": 145370 }, { "epoch": 34.88, "learning_rate": 6.315175312127886e-05, "loss": 0.0278, "step": 145380 }, { "epoch": 34.88, "learning_rate": 6.314742410712932e-05, "loss": 0.0221, "step": 145390 }, { "epoch": 34.88, "learning_rate": 6.314309498710178e-05, "loss": 0.0234, "step": 145400 }, { "epoch": 34.88, "learning_rate": 6.313876576123107e-05, "loss": 0.0171, "step": 145410 }, { "epoch": 34.89, "learning_rate": 6.313443642955205e-05, "loss": 0.0227, "step": 145420 }, { "epoch": 34.89, "learning_rate": 6.313010699209963e-05, "loss": 0.0194, "step": 145430 }, { "epoch": 34.89, "learning_rate": 6.312577744890864e-05, "loss": 0.015, "step": 145440 }, { "epoch": 34.89, "learning_rate": 6.312144780001393e-05, "loss": 0.0576, "step": 145450 }, { "epoch": 34.9, "learning_rate": 6.311711804545041e-05, "loss": 0.0201, "step": 145460 }, { "epoch": 34.9, "learning_rate": 6.311278818525292e-05, "loss": 0.0264, "step": 145470 }, { "epoch": 34.9, "learning_rate": 6.310845821945634e-05, "loss": 0.0437, "step": 145480 }, { "epoch": 34.9, "learning_rate": 6.310412814809553e-05, "loss": 0.0284, "step": 145490 }, { "epoch": 34.9, "learning_rate": 6.309979797120535e-05, "loss": 0.0301, "step": 145500 }, { "epoch": 34.91, "learning_rate": 6.309546768882073e-05, "loss": 0.0251, "step": 145510 }, { "epoch": 34.91, "learning_rate": 6.309113730097647e-05, "loss": 0.032, "step": 145520 }, { "epoch": 34.91, "learning_rate": 6.308680680770749e-05, "loss": 0.0259, "step": 145530 }, { "epoch": 34.91, "learning_rate": 6.308247620904864e-05, "loss": 0.0418, "step": 145540 }, { "epoch": 34.92, "learning_rate": 6.30781455050348e-05, "loss": 0.0178, "step": 145550 }, { "epoch": 34.92, "learning_rate": 6.307381469570086e-05, "loss": 0.0206, "step": 145560 }, { "epoch": 34.92, "learning_rate": 6.306948378108166e-05, "loss": 0.0366, "step": 145570 }, { "epoch": 34.92, "learning_rate": 6.306515276121215e-05, "loss": 0.017, "step": 145580 }, { "epoch": 34.93, "learning_rate": 6.30608216361271e-05, "loss": 0.0273, "step": 145590 }, { "epoch": 34.93, "learning_rate": 6.30564904058615e-05, "loss": 0.0171, "step": 145600 }, { "epoch": 34.93, "learning_rate": 6.305215907045016e-05, "loss": 0.0324, "step": 145610 }, { "epoch": 34.93, "learning_rate": 6.304782762992798e-05, "loss": 0.0209, "step": 145620 }, { "epoch": 34.93, "learning_rate": 6.304349608432985e-05, "loss": 0.0212, "step": 145630 }, { "epoch": 34.94, "learning_rate": 6.303916443369064e-05, "loss": 0.031, "step": 145640 }, { "epoch": 34.94, "learning_rate": 6.303483267804524e-05, "loss": 0.0292, "step": 145650 }, { "epoch": 34.94, "learning_rate": 6.303050081742853e-05, "loss": 0.0253, "step": 145660 }, { "epoch": 34.94, "learning_rate": 6.30261688518754e-05, "loss": 0.0305, "step": 145670 }, { "epoch": 34.95, "learning_rate": 6.302183678142074e-05, "loss": 0.0507, "step": 145680 }, { "epoch": 34.95, "learning_rate": 6.301750460609941e-05, "loss": 0.0141, "step": 145690 }, { "epoch": 34.95, "learning_rate": 6.301317232594636e-05, "loss": 0.0257, "step": 145700 }, { "epoch": 35.0, "learning_rate": 6.30088399409964e-05, "loss": 0.0182, "step": 145710 }, { "epoch": 35.0, "learning_rate": 6.300450745128445e-05, "loss": 0.0142, "step": 145720 }, { "epoch": 35.01, "learning_rate": 6.300017485684543e-05, "loss": 0.047, "step": 145730 }, { "epoch": 35.01, "learning_rate": 6.299584215771419e-05, "loss": 0.0217, "step": 145740 }, { "epoch": 35.01, "learning_rate": 6.299150935392568e-05, "loss": 0.0432, "step": 145750 }, { "epoch": 35.01, "learning_rate": 6.298717644551469e-05, "loss": 0.0163, "step": 145760 }, { "epoch": 35.01, "learning_rate": 6.298284343251623e-05, "loss": 0.0273, "step": 145770 }, { "epoch": 35.02, "learning_rate": 6.29785103149651e-05, "loss": 0.0299, "step": 145780 }, { "epoch": 35.02, "learning_rate": 6.297417709289625e-05, "loss": 0.0134, "step": 145790 }, { "epoch": 35.02, "learning_rate": 6.296984376634455e-05, "loss": 0.0166, "step": 145800 }, { "epoch": 35.02, "learning_rate": 6.296551033534492e-05, "loss": 0.03, "step": 145810 }, { "epoch": 35.03, "learning_rate": 6.296117679993225e-05, "loss": 0.0255, "step": 145820 }, { "epoch": 35.03, "learning_rate": 6.295684316014142e-05, "loss": 0.0304, "step": 145830 }, { "epoch": 35.03, "learning_rate": 6.295250941600736e-05, "loss": 0.0404, "step": 145840 }, { "epoch": 35.03, "learning_rate": 6.294817556756494e-05, "loss": 0.0349, "step": 145850 }, { "epoch": 35.04, "learning_rate": 6.294384161484906e-05, "loss": 0.0201, "step": 145860 }, { "epoch": 35.04, "learning_rate": 6.293950755789467e-05, "loss": 0.0247, "step": 145870 }, { "epoch": 35.04, "learning_rate": 6.293517339673662e-05, "loss": 0.0471, "step": 145880 }, { "epoch": 35.04, "learning_rate": 6.293083913140985e-05, "loss": 0.0205, "step": 145890 }, { "epoch": 35.04, "learning_rate": 6.292650476194923e-05, "loss": 0.0213, "step": 145900 }, { "epoch": 35.05, "learning_rate": 6.292217028838968e-05, "loss": 0.026, "step": 145910 }, { "epoch": 35.05, "learning_rate": 6.291783571076611e-05, "loss": 0.0278, "step": 145920 }, { "epoch": 35.05, "learning_rate": 6.291350102911342e-05, "loss": 0.0235, "step": 145930 }, { "epoch": 35.05, "learning_rate": 6.290916624346655e-05, "loss": 0.0358, "step": 145940 }, { "epoch": 35.06, "learning_rate": 6.290483135386037e-05, "loss": 0.0193, "step": 145950 }, { "epoch": 35.06, "learning_rate": 6.290049636032979e-05, "loss": 0.0228, "step": 145960 }, { "epoch": 35.06, "learning_rate": 6.289616126290974e-05, "loss": 0.0223, "step": 145970 }, { "epoch": 35.06, "learning_rate": 6.28918260616351e-05, "loss": 0.0227, "step": 145980 }, { "epoch": 35.07, "learning_rate": 6.288749075654084e-05, "loss": 0.0255, "step": 145990 }, { "epoch": 35.07, "learning_rate": 6.288315534766183e-05, "loss": 0.0266, "step": 146000 }, { "epoch": 35.07, "learning_rate": 6.287881983503298e-05, "loss": 0.0373, "step": 146010 }, { "epoch": 35.07, "learning_rate": 6.287448421868923e-05, "loss": 0.0434, "step": 146020 }, { "epoch": 35.07, "learning_rate": 6.287014849866547e-05, "loss": 0.0283, "step": 146030 }, { "epoch": 35.08, "learning_rate": 6.286581267499662e-05, "loss": 0.0274, "step": 146040 }, { "epoch": 35.08, "learning_rate": 6.286147674771762e-05, "loss": 0.0158, "step": 146050 }, { "epoch": 35.08, "learning_rate": 6.285714071686337e-05, "loss": 0.0211, "step": 146060 }, { "epoch": 35.08, "learning_rate": 6.285280458246878e-05, "loss": 0.0265, "step": 146070 }, { "epoch": 35.09, "learning_rate": 6.28484683445688e-05, "loss": 0.0294, "step": 146080 }, { "epoch": 35.09, "learning_rate": 6.284413200319831e-05, "loss": 0.0334, "step": 146090 }, { "epoch": 35.09, "learning_rate": 6.283979555839226e-05, "loss": 0.0366, "step": 146100 }, { "epoch": 35.09, "learning_rate": 6.283545901018558e-05, "loss": 0.0384, "step": 146110 }, { "epoch": 35.09, "learning_rate": 6.283112235861313e-05, "loss": 0.0158, "step": 146120 }, { "epoch": 35.1, "learning_rate": 6.282678560370993e-05, "loss": 0.0279, "step": 146130 }, { "epoch": 35.1, "learning_rate": 6.282244874551083e-05, "loss": 0.0329, "step": 146140 }, { "epoch": 35.1, "learning_rate": 6.281811178405079e-05, "loss": 0.0186, "step": 146150 }, { "epoch": 35.1, "learning_rate": 6.281377471936472e-05, "loss": 0.0143, "step": 146160 }, { "epoch": 35.11, "learning_rate": 6.280943755148754e-05, "loss": 0.0363, "step": 146170 }, { "epoch": 35.11, "learning_rate": 6.280510028045422e-05, "loss": 0.0195, "step": 146180 }, { "epoch": 35.11, "learning_rate": 6.280076290629964e-05, "loss": 0.0143, "step": 146190 }, { "epoch": 35.11, "learning_rate": 6.279642542905876e-05, "loss": 0.0429, "step": 146200 }, { "epoch": 35.12, "learning_rate": 6.279208784876649e-05, "loss": 0.055, "step": 146210 }, { "epoch": 35.12, "learning_rate": 6.278775016545777e-05, "loss": 0.0361, "step": 146220 }, { "epoch": 35.12, "learning_rate": 6.278341237916754e-05, "loss": 0.0331, "step": 146230 }, { "epoch": 35.12, "learning_rate": 6.277907448993072e-05, "loss": 0.0239, "step": 146240 }, { "epoch": 35.12, "learning_rate": 6.277473649778225e-05, "loss": 0.0172, "step": 146250 }, { "epoch": 35.13, "learning_rate": 6.277039840275706e-05, "loss": 0.018, "step": 146260 }, { "epoch": 35.13, "learning_rate": 6.276606020489009e-05, "loss": 0.0264, "step": 146270 }, { "epoch": 35.13, "learning_rate": 6.276172190421627e-05, "loss": 0.033, "step": 146280 }, { "epoch": 35.13, "learning_rate": 6.275738350077056e-05, "loss": 0.022, "step": 146290 }, { "epoch": 35.14, "learning_rate": 6.275304499458788e-05, "loss": 0.0162, "step": 146300 }, { "epoch": 35.14, "learning_rate": 6.274870638570313e-05, "loss": 0.0232, "step": 146310 }, { "epoch": 35.14, "learning_rate": 6.274436767415133e-05, "loss": 0.034, "step": 146320 }, { "epoch": 35.14, "learning_rate": 6.274002885996735e-05, "loss": 0.0226, "step": 146330 }, { "epoch": 35.15, "learning_rate": 6.273568994318618e-05, "loss": 0.011, "step": 146340 }, { "epoch": 35.15, "learning_rate": 6.273135092384273e-05, "loss": 0.0157, "step": 146350 }, { "epoch": 35.15, "learning_rate": 6.272701180197195e-05, "loss": 0.0204, "step": 146360 }, { "epoch": 35.15, "learning_rate": 6.27226725776088e-05, "loss": 0.0292, "step": 146370 }, { "epoch": 35.15, "learning_rate": 6.271833325078819e-05, "loss": 0.0169, "step": 146380 }, { "epoch": 35.16, "learning_rate": 6.27139938215451e-05, "loss": 0.017, "step": 146390 }, { "epoch": 35.16, "learning_rate": 6.270965428991447e-05, "loss": 0.0086, "step": 146400 }, { "epoch": 35.16, "learning_rate": 6.270531465593122e-05, "loss": 0.0402, "step": 146410 }, { "epoch": 35.16, "learning_rate": 6.270097491963033e-05, "loss": 0.0206, "step": 146420 }, { "epoch": 35.17, "learning_rate": 6.269663508104672e-05, "loss": 0.0146, "step": 146430 }, { "epoch": 35.17, "learning_rate": 6.269229514021538e-05, "loss": 0.0141, "step": 146440 }, { "epoch": 35.17, "learning_rate": 6.268795509717121e-05, "loss": 0.0232, "step": 146450 }, { "epoch": 35.17, "learning_rate": 6.268361495194921e-05, "loss": 0.0185, "step": 146460 }, { "epoch": 35.17, "learning_rate": 6.26792747045843e-05, "loss": 0.0213, "step": 146470 }, { "epoch": 35.18, "learning_rate": 6.267493435511143e-05, "loss": 0.0183, "step": 146480 }, { "epoch": 35.18, "learning_rate": 6.267059390356558e-05, "loss": 0.0258, "step": 146490 }, { "epoch": 35.18, "learning_rate": 6.266625334998167e-05, "loss": 0.0481, "step": 146500 }, { "epoch": 35.18, "learning_rate": 6.266191269439469e-05, "loss": 0.0237, "step": 146510 }, { "epoch": 35.19, "learning_rate": 6.265757193683956e-05, "loss": 0.03, "step": 146520 }, { "epoch": 35.19, "learning_rate": 6.265323107735126e-05, "loss": 0.018, "step": 146530 }, { "epoch": 35.19, "learning_rate": 6.264889011596476e-05, "loss": 0.0252, "step": 146540 }, { "epoch": 35.19, "learning_rate": 6.264454905271499e-05, "loss": 0.0441, "step": 146550 }, { "epoch": 35.2, "learning_rate": 6.264020788763691e-05, "loss": 0.0231, "step": 146560 }, { "epoch": 35.2, "learning_rate": 6.26358666207655e-05, "loss": 0.0333, "step": 146570 }, { "epoch": 35.2, "learning_rate": 6.263152525213571e-05, "loss": 0.0134, "step": 146580 }, { "epoch": 35.2, "learning_rate": 6.262718378178251e-05, "loss": 0.0135, "step": 146590 }, { "epoch": 35.2, "learning_rate": 6.262284220974086e-05, "loss": 0.0249, "step": 146600 }, { "epoch": 35.21, "learning_rate": 6.261850053604572e-05, "loss": 0.0224, "step": 146610 }, { "epoch": 35.21, "learning_rate": 6.261415876073204e-05, "loss": 0.0191, "step": 146620 }, { "epoch": 35.21, "learning_rate": 6.260981688383481e-05, "loss": 0.0324, "step": 146630 }, { "epoch": 35.21, "learning_rate": 6.260547490538897e-05, "loss": 0.0544, "step": 146640 }, { "epoch": 35.22, "learning_rate": 6.26011328254295e-05, "loss": 0.0298, "step": 146650 }, { "epoch": 35.22, "learning_rate": 6.259679064399138e-05, "loss": 0.0248, "step": 146660 }, { "epoch": 35.22, "learning_rate": 6.259244836110955e-05, "loss": 0.0204, "step": 146670 }, { "epoch": 35.22, "learning_rate": 6.258810597681903e-05, "loss": 0.0212, "step": 146680 }, { "epoch": 35.23, "learning_rate": 6.258376349115472e-05, "loss": 0.0193, "step": 146690 }, { "epoch": 35.23, "learning_rate": 6.257942090415163e-05, "loss": 0.0375, "step": 146700 }, { "epoch": 35.23, "learning_rate": 6.257507821584473e-05, "loss": 0.0291, "step": 146710 }, { "epoch": 35.23, "learning_rate": 6.257073542626899e-05, "loss": 0.0204, "step": 146720 }, { "epoch": 35.23, "learning_rate": 6.256639253545939e-05, "loss": 0.0311, "step": 146730 }, { "epoch": 35.24, "learning_rate": 6.256204954345089e-05, "loss": 0.0332, "step": 146740 }, { "epoch": 35.24, "learning_rate": 6.255770645027848e-05, "loss": 0.0272, "step": 146750 }, { "epoch": 35.24, "learning_rate": 6.255336325597712e-05, "loss": 0.0432, "step": 146760 }, { "epoch": 35.24, "learning_rate": 6.254901996058177e-05, "loss": 0.0214, "step": 146770 }, { "epoch": 35.25, "learning_rate": 6.254467656412745e-05, "loss": 0.0324, "step": 146780 }, { "epoch": 35.25, "learning_rate": 6.254033306664911e-05, "loss": 0.0327, "step": 146790 }, { "epoch": 35.25, "learning_rate": 6.253598946818176e-05, "loss": 0.0174, "step": 146800 }, { "epoch": 35.25, "learning_rate": 6.253164576876034e-05, "loss": 0.0267, "step": 146810 }, { "epoch": 35.25, "learning_rate": 6.252730196841983e-05, "loss": 0.0283, "step": 146820 }, { "epoch": 35.26, "learning_rate": 6.252295806719526e-05, "loss": 0.0312, "step": 146830 }, { "epoch": 35.26, "learning_rate": 6.251861406512155e-05, "loss": 0.0331, "step": 146840 }, { "epoch": 35.26, "learning_rate": 6.251426996223372e-05, "loss": 0.0346, "step": 146850 }, { "epoch": 35.26, "learning_rate": 6.250992575856675e-05, "loss": 0.0448, "step": 146860 }, { "epoch": 35.27, "learning_rate": 6.250558145415564e-05, "loss": 0.03, "step": 146870 }, { "epoch": 35.27, "learning_rate": 6.250123704903534e-05, "loss": 0.0163, "step": 146880 }, { "epoch": 35.27, "learning_rate": 6.249689254324083e-05, "loss": 0.0304, "step": 146890 }, { "epoch": 35.27, "learning_rate": 6.249254793680714e-05, "loss": 0.027, "step": 146900 }, { "epoch": 35.28, "learning_rate": 6.248820322976925e-05, "loss": 0.0201, "step": 146910 }, { "epoch": 35.28, "learning_rate": 6.248385842216212e-05, "loss": 0.0184, "step": 146920 }, { "epoch": 35.28, "learning_rate": 6.247951351402076e-05, "loss": 0.0233, "step": 146930 }, { "epoch": 35.28, "learning_rate": 6.247516850538013e-05, "loss": 0.0273, "step": 146940 }, { "epoch": 35.28, "learning_rate": 6.247082339627529e-05, "loss": 0.0242, "step": 146950 }, { "epoch": 35.29, "learning_rate": 6.246647818674115e-05, "loss": 0.0229, "step": 146960 }, { "epoch": 35.29, "learning_rate": 6.246213287681276e-05, "loss": 0.0524, "step": 146970 }, { "epoch": 35.29, "learning_rate": 6.245778746652508e-05, "loss": 0.0227, "step": 146980 }, { "epoch": 35.29, "learning_rate": 6.245344195591314e-05, "loss": 0.0296, "step": 146990 }, { "epoch": 35.3, "learning_rate": 6.24490963450119e-05, "loss": 0.0261, "step": 147000 }, { "epoch": 35.3, "learning_rate": 6.244475063385636e-05, "loss": 0.0296, "step": 147010 }, { "epoch": 35.3, "learning_rate": 6.244040482248153e-05, "loss": 0.0212, "step": 147020 }, { "epoch": 35.3, "learning_rate": 6.24360589109224e-05, "loss": 0.0351, "step": 147030 }, { "epoch": 35.31, "learning_rate": 6.243171289921399e-05, "loss": 0.0451, "step": 147040 }, { "epoch": 35.31, "learning_rate": 6.242736678739126e-05, "loss": 0.0223, "step": 147050 }, { "epoch": 35.31, "learning_rate": 6.242302057548924e-05, "loss": 0.0228, "step": 147060 }, { "epoch": 35.31, "learning_rate": 6.24186742635429e-05, "loss": 0.0363, "step": 147070 }, { "epoch": 35.31, "learning_rate": 6.241432785158727e-05, "loss": 0.0275, "step": 147080 }, { "epoch": 35.32, "learning_rate": 6.240998133965737e-05, "loss": 0.0177, "step": 147090 }, { "epoch": 35.32, "learning_rate": 6.240563472778815e-05, "loss": 0.022, "step": 147100 }, { "epoch": 35.32, "learning_rate": 6.240128801601464e-05, "loss": 0.0348, "step": 147110 }, { "epoch": 35.32, "learning_rate": 6.239694120437186e-05, "loss": 0.0234, "step": 147120 }, { "epoch": 35.33, "learning_rate": 6.239259429289478e-05, "loss": 0.0154, "step": 147130 }, { "epoch": 35.33, "learning_rate": 6.238824728161847e-05, "loss": 0.0218, "step": 147140 }, { "epoch": 35.33, "learning_rate": 6.238390017057785e-05, "loss": 0.0263, "step": 147150 }, { "epoch": 35.33, "learning_rate": 6.2379552959808e-05, "loss": 0.0122, "step": 147160 }, { "epoch": 35.33, "learning_rate": 6.237520564934387e-05, "loss": 0.0313, "step": 147170 }, { "epoch": 35.34, "learning_rate": 6.237085823922054e-05, "loss": 0.0206, "step": 147180 }, { "epoch": 35.34, "learning_rate": 6.236651072947295e-05, "loss": 0.0194, "step": 147190 }, { "epoch": 35.34, "learning_rate": 6.236216312013614e-05, "loss": 0.0295, "step": 147200 }, { "epoch": 35.34, "learning_rate": 6.235781541124514e-05, "loss": 0.0173, "step": 147210 }, { "epoch": 35.35, "learning_rate": 6.235346760283494e-05, "loss": 0.0241, "step": 147220 }, { "epoch": 35.35, "learning_rate": 6.234911969494057e-05, "loss": 0.0287, "step": 147230 }, { "epoch": 35.35, "learning_rate": 6.234477168759703e-05, "loss": 0.036, "step": 147240 }, { "epoch": 35.35, "learning_rate": 6.234042358083932e-05, "loss": 0.0317, "step": 147250 }, { "epoch": 35.36, "learning_rate": 6.233607537470251e-05, "loss": 0.0215, "step": 147260 }, { "epoch": 35.36, "learning_rate": 6.233172706922154e-05, "loss": 0.0234, "step": 147270 }, { "epoch": 35.36, "learning_rate": 6.232737866443152e-05, "loss": 0.0125, "step": 147280 }, { "epoch": 35.36, "learning_rate": 6.232303016036737e-05, "loss": 0.0277, "step": 147290 }, { "epoch": 35.36, "learning_rate": 6.231868155706417e-05, "loss": 0.0178, "step": 147300 }, { "epoch": 35.37, "learning_rate": 6.231433285455695e-05, "loss": 0.0122, "step": 147310 }, { "epoch": 35.37, "learning_rate": 6.230998405288067e-05, "loss": 0.0237, "step": 147320 }, { "epoch": 35.37, "learning_rate": 6.230563515207043e-05, "loss": 0.039, "step": 147330 }, { "epoch": 35.37, "learning_rate": 6.230128615216117e-05, "loss": 0.0188, "step": 147340 }, { "epoch": 35.38, "learning_rate": 6.229693705318799e-05, "loss": 0.0158, "step": 147350 }, { "epoch": 35.38, "learning_rate": 6.229258785518585e-05, "loss": 0.0374, "step": 147360 }, { "epoch": 35.38, "learning_rate": 6.228823855818981e-05, "loss": 0.0238, "step": 147370 }, { "epoch": 35.38, "learning_rate": 6.228388916223492e-05, "loss": 0.0239, "step": 147380 }, { "epoch": 35.39, "learning_rate": 6.227953966735614e-05, "loss": 0.0211, "step": 147390 }, { "epoch": 35.39, "learning_rate": 6.227519007358855e-05, "loss": 0.0229, "step": 147400 }, { "epoch": 35.39, "learning_rate": 6.227084038096714e-05, "loss": 0.0172, "step": 147410 }, { "epoch": 35.39, "learning_rate": 6.226649058952697e-05, "loss": 0.0304, "step": 147420 }, { "epoch": 35.39, "learning_rate": 6.226214069930306e-05, "loss": 0.0131, "step": 147430 }, { "epoch": 35.4, "learning_rate": 6.225779071033042e-05, "loss": 0.0117, "step": 147440 }, { "epoch": 35.4, "learning_rate": 6.225344062264413e-05, "loss": 0.0215, "step": 147450 }, { "epoch": 35.4, "learning_rate": 6.224909043627917e-05, "loss": 0.0153, "step": 147460 }, { "epoch": 35.4, "learning_rate": 6.224474015127059e-05, "loss": 0.0235, "step": 147470 }, { "epoch": 35.41, "learning_rate": 6.224038976765344e-05, "loss": 0.0134, "step": 147480 }, { "epoch": 35.41, "learning_rate": 6.223603928546275e-05, "loss": 0.0276, "step": 147490 }, { "epoch": 35.41, "learning_rate": 6.223168870473352e-05, "loss": 0.0459, "step": 147500 }, { "epoch": 35.41, "learning_rate": 6.222733802550083e-05, "loss": 0.0217, "step": 147510 }, { "epoch": 35.41, "learning_rate": 6.222298724779971e-05, "loss": 0.0305, "step": 147520 }, { "epoch": 35.42, "learning_rate": 6.221863637166515e-05, "loss": 0.0274, "step": 147530 }, { "epoch": 35.42, "learning_rate": 6.221428539713225e-05, "loss": 0.0298, "step": 147540 }, { "epoch": 35.42, "learning_rate": 6.220993432423602e-05, "loss": 0.014, "step": 147550 }, { "epoch": 35.42, "learning_rate": 6.22055831530115e-05, "loss": 0.0232, "step": 147560 }, { "epoch": 35.43, "learning_rate": 6.220123188349374e-05, "loss": 0.0172, "step": 147570 }, { "epoch": 35.43, "learning_rate": 6.219688051571776e-05, "loss": 0.0178, "step": 147580 }, { "epoch": 35.43, "learning_rate": 6.219252904971864e-05, "loss": 0.019, "step": 147590 }, { "epoch": 35.43, "learning_rate": 6.218817748553138e-05, "loss": 0.0256, "step": 147600 }, { "epoch": 35.44, "learning_rate": 6.218382582319104e-05, "loss": 0.0113, "step": 147610 }, { "epoch": 35.44, "learning_rate": 6.217947406273269e-05, "loss": 0.0302, "step": 147620 }, { "epoch": 35.44, "learning_rate": 6.217512220419134e-05, "loss": 0.0182, "step": 147630 }, { "epoch": 35.44, "learning_rate": 6.217077024760206e-05, "loss": 0.02, "step": 147640 }, { "epoch": 35.44, "learning_rate": 6.216641819299987e-05, "loss": 0.0231, "step": 147650 }, { "epoch": 35.45, "learning_rate": 6.216206604041986e-05, "loss": 0.0128, "step": 147660 }, { "epoch": 35.45, "learning_rate": 6.215771378989703e-05, "loss": 0.0192, "step": 147670 }, { "epoch": 35.45, "learning_rate": 6.215336144146646e-05, "loss": 0.0347, "step": 147680 }, { "epoch": 35.45, "learning_rate": 6.21490089951632e-05, "loss": 0.0257, "step": 147690 }, { "epoch": 35.46, "learning_rate": 6.214465645102228e-05, "loss": 0.0306, "step": 147700 }, { "epoch": 35.46, "learning_rate": 6.214030380907878e-05, "loss": 0.0233, "step": 147710 }, { "epoch": 35.46, "learning_rate": 6.213595106936772e-05, "loss": 0.0237, "step": 147720 }, { "epoch": 35.46, "learning_rate": 6.213159823192418e-05, "loss": 0.0568, "step": 147730 }, { "epoch": 35.47, "learning_rate": 6.212724529678321e-05, "loss": 0.0144, "step": 147740 }, { "epoch": 35.47, "learning_rate": 6.212289226397986e-05, "loss": 0.0476, "step": 147750 }, { "epoch": 35.47, "learning_rate": 6.211853913354918e-05, "loss": 0.0183, "step": 147760 }, { "epoch": 35.47, "learning_rate": 6.211418590552623e-05, "loss": 0.0581, "step": 147770 }, { "epoch": 35.47, "learning_rate": 6.210983257994606e-05, "loss": 0.0422, "step": 147780 }, { "epoch": 35.48, "learning_rate": 6.210547915684375e-05, "loss": 0.041, "step": 147790 }, { "epoch": 35.48, "learning_rate": 6.210112563625434e-05, "loss": 0.0343, "step": 147800 }, { "epoch": 35.48, "learning_rate": 6.209677201821289e-05, "loss": 0.0204, "step": 147810 }, { "epoch": 35.48, "learning_rate": 6.209241830275447e-05, "loss": 0.0184, "step": 147820 }, { "epoch": 35.49, "learning_rate": 6.208806448991415e-05, "loss": 0.0336, "step": 147830 }, { "epoch": 35.49, "learning_rate": 6.208371057972694e-05, "loss": 0.0328, "step": 147840 }, { "epoch": 35.49, "learning_rate": 6.207935657222797e-05, "loss": 0.0257, "step": 147850 }, { "epoch": 35.49, "learning_rate": 6.207500246745227e-05, "loss": 0.0164, "step": 147860 }, { "epoch": 35.49, "learning_rate": 6.207064826543491e-05, "loss": 0.0273, "step": 147870 }, { "epoch": 35.5, "learning_rate": 6.206629396621095e-05, "loss": 0.0204, "step": 147880 }, { "epoch": 35.5, "learning_rate": 6.206193956981545e-05, "loss": 0.0306, "step": 147890 }, { "epoch": 35.5, "learning_rate": 6.20575850762835e-05, "loss": 0.0263, "step": 147900 }, { "epoch": 35.5, "learning_rate": 6.205323048565013e-05, "loss": 0.02, "step": 147910 }, { "epoch": 35.51, "learning_rate": 6.204887579795045e-05, "loss": 0.0309, "step": 147920 }, { "epoch": 35.51, "learning_rate": 6.204452101321951e-05, "loss": 0.0153, "step": 147930 }, { "epoch": 35.51, "learning_rate": 6.204016613149239e-05, "loss": 0.0197, "step": 147940 }, { "epoch": 35.51, "learning_rate": 6.203581115280413e-05, "loss": 0.0375, "step": 147950 }, { "epoch": 35.52, "learning_rate": 6.203145607718982e-05, "loss": 0.0182, "step": 147960 }, { "epoch": 35.52, "learning_rate": 6.202710090468455e-05, "loss": 0.0316, "step": 147970 }, { "epoch": 35.52, "learning_rate": 6.202274563532335e-05, "loss": 0.0257, "step": 147980 }, { "epoch": 35.52, "learning_rate": 6.201839026914135e-05, "loss": 0.0165, "step": 147990 }, { "epoch": 35.52, "learning_rate": 6.201403480617357e-05, "loss": 0.0594, "step": 148000 }, { "epoch": 35.53, "learning_rate": 6.200967924645512e-05, "loss": 0.0219, "step": 148010 }, { "epoch": 35.53, "learning_rate": 6.200532359002107e-05, "loss": 0.0227, "step": 148020 }, { "epoch": 35.53, "learning_rate": 6.200096783690647e-05, "loss": 0.0303, "step": 148030 }, { "epoch": 35.53, "learning_rate": 6.199661198714643e-05, "loss": 0.0262, "step": 148040 }, { "epoch": 35.54, "learning_rate": 6.199225604077604e-05, "loss": 0.0221, "step": 148050 }, { "epoch": 35.54, "learning_rate": 6.198789999783033e-05, "loss": 0.0269, "step": 148060 }, { "epoch": 35.54, "learning_rate": 6.198354385834442e-05, "loss": 0.0368, "step": 148070 }, { "epoch": 35.54, "learning_rate": 6.197918762235337e-05, "loss": 0.0354, "step": 148080 }, { "epoch": 35.55, "learning_rate": 6.197483128989227e-05, "loss": 0.034, "step": 148090 }, { "epoch": 35.55, "learning_rate": 6.197047486099619e-05, "loss": 0.0267, "step": 148100 }, { "epoch": 35.55, "learning_rate": 6.196611833570024e-05, "loss": 0.0233, "step": 148110 }, { "epoch": 35.55, "learning_rate": 6.196176171403948e-05, "loss": 0.0334, "step": 148120 }, { "epoch": 35.55, "learning_rate": 6.1957404996049e-05, "loss": 0.0338, "step": 148130 }, { "epoch": 35.56, "learning_rate": 6.19530481817639e-05, "loss": 0.041, "step": 148140 }, { "epoch": 35.56, "learning_rate": 6.194869127121925e-05, "loss": 0.0444, "step": 148150 }, { "epoch": 35.56, "learning_rate": 6.19443342644501e-05, "loss": 0.0229, "step": 148160 }, { "epoch": 35.56, "learning_rate": 6.193997716149162e-05, "loss": 0.0248, "step": 148170 }, { "epoch": 35.57, "learning_rate": 6.193561996237885e-05, "loss": 0.0368, "step": 148180 }, { "epoch": 35.57, "learning_rate": 6.193126266714688e-05, "loss": 0.0184, "step": 148190 }, { "epoch": 35.57, "learning_rate": 6.192690527583081e-05, "loss": 0.0317, "step": 148200 }, { "epoch": 35.57, "learning_rate": 6.19225477884657e-05, "loss": 0.0303, "step": 148210 }, { "epoch": 35.57, "learning_rate": 6.191819020508668e-05, "loss": 0.0269, "step": 148220 }, { "epoch": 35.58, "learning_rate": 6.191383252572884e-05, "loss": 0.0352, "step": 148230 }, { "epoch": 35.58, "learning_rate": 6.190947475042725e-05, "loss": 0.0377, "step": 148240 }, { "epoch": 35.58, "learning_rate": 6.190511687921702e-05, "loss": 0.0193, "step": 148250 }, { "epoch": 35.58, "learning_rate": 6.190075891213325e-05, "loss": 0.0131, "step": 148260 }, { "epoch": 35.59, "learning_rate": 6.189640084921102e-05, "loss": 0.0416, "step": 148270 }, { "epoch": 35.59, "learning_rate": 6.189204269048542e-05, "loss": 0.0213, "step": 148280 }, { "epoch": 35.59, "learning_rate": 6.188768443599156e-05, "loss": 0.0255, "step": 148290 }, { "epoch": 35.59, "learning_rate": 6.188332608576455e-05, "loss": 0.0308, "step": 148300 }, { "epoch": 35.6, "learning_rate": 6.187896763983946e-05, "loss": 0.0206, "step": 148310 }, { "epoch": 35.6, "learning_rate": 6.187460909825142e-05, "loss": 0.0539, "step": 148320 }, { "epoch": 35.6, "learning_rate": 6.18702504610355e-05, "loss": 0.0278, "step": 148330 }, { "epoch": 35.6, "learning_rate": 6.186589172822683e-05, "loss": 0.0383, "step": 148340 }, { "epoch": 35.6, "learning_rate": 6.186153289986048e-05, "loss": 0.025, "step": 148350 }, { "epoch": 35.61, "learning_rate": 6.185717397597156e-05, "loss": 0.0358, "step": 148360 }, { "epoch": 35.61, "learning_rate": 6.18528149565952e-05, "loss": 0.0359, "step": 148370 }, { "epoch": 35.61, "learning_rate": 6.184845584176648e-05, "loss": 0.0272, "step": 148380 }, { "epoch": 35.61, "learning_rate": 6.18440966315205e-05, "loss": 0.0287, "step": 148390 }, { "epoch": 35.62, "learning_rate": 6.183973732589237e-05, "loss": 0.0321, "step": 148400 }, { "epoch": 35.62, "learning_rate": 6.183537792491724e-05, "loss": 0.0412, "step": 148410 }, { "epoch": 35.62, "learning_rate": 6.183101842863013e-05, "loss": 0.0224, "step": 148420 }, { "epoch": 35.62, "learning_rate": 6.182665883706622e-05, "loss": 0.026, "step": 148430 }, { "epoch": 35.62, "learning_rate": 6.18222991502606e-05, "loss": 0.0393, "step": 148440 }, { "epoch": 35.63, "learning_rate": 6.181793936824836e-05, "loss": 0.0242, "step": 148450 }, { "epoch": 35.63, "learning_rate": 6.181357949106462e-05, "loss": 0.0201, "step": 148460 }, { "epoch": 35.63, "learning_rate": 6.180921951874448e-05, "loss": 0.0256, "step": 148470 }, { "epoch": 35.63, "learning_rate": 6.18048594513231e-05, "loss": 0.0151, "step": 148480 }, { "epoch": 35.64, "learning_rate": 6.180049928883553e-05, "loss": 0.0418, "step": 148490 }, { "epoch": 35.64, "learning_rate": 6.179613903131694e-05, "loss": 0.0229, "step": 148500 }, { "epoch": 35.64, "learning_rate": 6.179177867880238e-05, "loss": 0.0342, "step": 148510 }, { "epoch": 35.64, "learning_rate": 6.178741823132701e-05, "loss": 0.0172, "step": 148520 }, { "epoch": 35.65, "learning_rate": 6.178305768892594e-05, "loss": 0.0386, "step": 148530 }, { "epoch": 35.65, "learning_rate": 6.177869705163427e-05, "loss": 0.0282, "step": 148540 }, { "epoch": 35.65, "learning_rate": 6.177433631948713e-05, "loss": 0.0262, "step": 148550 }, { "epoch": 35.65, "learning_rate": 6.176997549251964e-05, "loss": 0.0254, "step": 148560 }, { "epoch": 35.65, "learning_rate": 6.176561457076692e-05, "loss": 0.0195, "step": 148570 }, { "epoch": 35.66, "learning_rate": 6.176125355426406e-05, "loss": 0.0404, "step": 148580 }, { "epoch": 35.66, "learning_rate": 6.17568924430462e-05, "loss": 0.033, "step": 148590 }, { "epoch": 35.66, "learning_rate": 6.17525312371485e-05, "loss": 0.0315, "step": 148600 }, { "epoch": 35.66, "learning_rate": 6.1748169936606e-05, "loss": 0.022, "step": 148610 }, { "epoch": 35.67, "learning_rate": 6.174380854145389e-05, "loss": 0.0262, "step": 148620 }, { "epoch": 35.67, "learning_rate": 6.173944705172725e-05, "loss": 0.0309, "step": 148630 }, { "epoch": 35.67, "learning_rate": 6.173508546746122e-05, "loss": 0.0445, "step": 148640 }, { "epoch": 35.67, "learning_rate": 6.173072378869096e-05, "loss": 0.0338, "step": 148650 }, { "epoch": 35.68, "learning_rate": 6.172636201545154e-05, "loss": 0.0268, "step": 148660 }, { "epoch": 35.68, "learning_rate": 6.172200014777811e-05, "loss": 0.0112, "step": 148670 }, { "epoch": 35.68, "learning_rate": 6.171763818570578e-05, "loss": 0.0274, "step": 148680 }, { "epoch": 35.68, "learning_rate": 6.171327612926971e-05, "loss": 0.0366, "step": 148690 }, { "epoch": 35.68, "learning_rate": 6.170891397850501e-05, "loss": 0.0226, "step": 148700 }, { "epoch": 35.69, "learning_rate": 6.17045517334468e-05, "loss": 0.0333, "step": 148710 }, { "epoch": 35.69, "learning_rate": 6.170018939413023e-05, "loss": 0.0162, "step": 148720 }, { "epoch": 35.69, "learning_rate": 6.16958269605904e-05, "loss": 0.0333, "step": 148730 }, { "epoch": 35.69, "learning_rate": 6.169146443286249e-05, "loss": 0.0157, "step": 148740 }, { "epoch": 35.7, "learning_rate": 6.168710181098158e-05, "loss": 0.0367, "step": 148750 }, { "epoch": 35.7, "learning_rate": 6.168273909498282e-05, "loss": 0.0252, "step": 148760 }, { "epoch": 35.7, "learning_rate": 6.167837628490138e-05, "loss": 0.0413, "step": 148770 }, { "epoch": 35.7, "learning_rate": 6.167401338077233e-05, "loss": 0.0257, "step": 148780 }, { "epoch": 35.7, "learning_rate": 6.166965038263087e-05, "loss": 0.0275, "step": 148790 }, { "epoch": 35.71, "learning_rate": 6.166528729051209e-05, "loss": 0.0236, "step": 148800 }, { "epoch": 35.71, "learning_rate": 6.166092410445114e-05, "loss": 0.0291, "step": 148810 }, { "epoch": 35.71, "learning_rate": 6.165656082448315e-05, "loss": 0.0357, "step": 148820 }, { "epoch": 35.71, "learning_rate": 6.165219745064326e-05, "loss": 0.0223, "step": 148830 }, { "epoch": 35.72, "learning_rate": 6.164783398296666e-05, "loss": 0.042, "step": 148840 }, { "epoch": 35.72, "learning_rate": 6.164347042148839e-05, "loss": 0.0409, "step": 148850 }, { "epoch": 35.72, "learning_rate": 6.163910676624367e-05, "loss": 0.056, "step": 148860 }, { "epoch": 35.72, "learning_rate": 6.163474301726761e-05, "loss": 0.0109, "step": 148870 }, { "epoch": 35.73, "learning_rate": 6.163037917459537e-05, "loss": 0.0186, "step": 148880 }, { "epoch": 35.73, "learning_rate": 6.162601523826208e-05, "loss": 0.0267, "step": 148890 }, { "epoch": 35.73, "learning_rate": 6.162165120830287e-05, "loss": 0.0272, "step": 148900 }, { "epoch": 35.73, "learning_rate": 6.161728708475292e-05, "loss": 0.0238, "step": 148910 }, { "epoch": 35.73, "learning_rate": 6.161292286764732e-05, "loss": 0.0174, "step": 148920 }, { "epoch": 35.74, "learning_rate": 6.160855855702128e-05, "loss": 0.015, "step": 148930 }, { "epoch": 35.74, "learning_rate": 6.160419415290991e-05, "loss": 0.0251, "step": 148940 }, { "epoch": 35.74, "learning_rate": 6.159982965534835e-05, "loss": 0.0175, "step": 148950 }, { "epoch": 35.74, "learning_rate": 6.159546506437177e-05, "loss": 0.0321, "step": 148960 }, { "epoch": 35.75, "learning_rate": 6.15911003800153e-05, "loss": 0.0397, "step": 148970 }, { "epoch": 35.75, "learning_rate": 6.158673560231412e-05, "loss": 0.0252, "step": 148980 }, { "epoch": 35.75, "learning_rate": 6.158237073130333e-05, "loss": 0.0304, "step": 148990 }, { "epoch": 35.75, "learning_rate": 6.157800576701813e-05, "loss": 0.029, "step": 149000 }, { "epoch": 35.76, "learning_rate": 6.157364070949364e-05, "loss": 0.0152, "step": 149010 }, { "epoch": 35.76, "learning_rate": 6.156927555876502e-05, "loss": 0.0306, "step": 149020 }, { "epoch": 35.76, "learning_rate": 6.156491031486744e-05, "loss": 0.0308, "step": 149030 }, { "epoch": 35.76, "learning_rate": 6.156054497783604e-05, "loss": 0.044, "step": 149040 }, { "epoch": 35.76, "learning_rate": 6.155617954770596e-05, "loss": 0.0225, "step": 149050 }, { "epoch": 35.77, "learning_rate": 6.155181402451238e-05, "loss": 0.0095, "step": 149060 }, { "epoch": 35.77, "learning_rate": 6.154744840829045e-05, "loss": 0.0352, "step": 149070 }, { "epoch": 35.77, "learning_rate": 6.154308269907533e-05, "loss": 0.0242, "step": 149080 }, { "epoch": 35.77, "learning_rate": 6.153871689690215e-05, "loss": 0.0166, "step": 149090 }, { "epoch": 35.78, "learning_rate": 6.153435100180611e-05, "loss": 0.0305, "step": 149100 }, { "epoch": 35.78, "learning_rate": 6.152998501382234e-05, "loss": 0.0207, "step": 149110 }, { "epoch": 35.78, "learning_rate": 6.1525618932986e-05, "loss": 0.0137, "step": 149120 }, { "epoch": 35.78, "learning_rate": 6.152125275933229e-05, "loss": 0.0211, "step": 149130 }, { "epoch": 35.78, "learning_rate": 6.15168864928963e-05, "loss": 0.0212, "step": 149140 }, { "epoch": 35.79, "learning_rate": 6.151252013371327e-05, "loss": 0.0281, "step": 149150 }, { "epoch": 35.79, "learning_rate": 6.15081536818183e-05, "loss": 0.0251, "step": 149160 }, { "epoch": 35.79, "learning_rate": 6.150378713724659e-05, "loss": 0.0105, "step": 149170 }, { "epoch": 35.79, "learning_rate": 6.149942050003329e-05, "loss": 0.019, "step": 149180 }, { "epoch": 35.8, "learning_rate": 6.149505377021358e-05, "loss": 0.0161, "step": 149190 }, { "epoch": 35.8, "learning_rate": 6.149068694782261e-05, "loss": 0.0335, "step": 149200 }, { "epoch": 35.8, "learning_rate": 6.148632003289554e-05, "loss": 0.0306, "step": 149210 }, { "epoch": 35.8, "learning_rate": 6.148195302546756e-05, "loss": 0.0316, "step": 149220 }, { "epoch": 35.81, "learning_rate": 6.147758592557383e-05, "loss": 0.0203, "step": 149230 }, { "epoch": 35.81, "learning_rate": 6.14732187332495e-05, "loss": 0.0243, "step": 149240 }, { "epoch": 35.81, "learning_rate": 6.146885144852978e-05, "loss": 0.028, "step": 149250 }, { "epoch": 35.81, "learning_rate": 6.146448407144979e-05, "loss": 0.0229, "step": 149260 }, { "epoch": 35.81, "learning_rate": 6.146011660204475e-05, "loss": 0.0262, "step": 149270 }, { "epoch": 35.82, "learning_rate": 6.145574904034979e-05, "loss": 0.0236, "step": 149280 }, { "epoch": 35.82, "learning_rate": 6.145138138640011e-05, "loss": 0.0225, "step": 149290 }, { "epoch": 35.82, "learning_rate": 6.144701364023087e-05, "loss": 0.0536, "step": 149300 }, { "epoch": 35.82, "learning_rate": 6.144264580187725e-05, "loss": 0.0384, "step": 149310 }, { "epoch": 35.83, "learning_rate": 6.143827787137443e-05, "loss": 0.0324, "step": 149320 }, { "epoch": 35.83, "learning_rate": 6.14339098487576e-05, "loss": 0.0327, "step": 149330 }, { "epoch": 35.83, "learning_rate": 6.142954173406188e-05, "loss": 0.0216, "step": 149340 }, { "epoch": 35.83, "learning_rate": 6.142517352732248e-05, "loss": 0.0244, "step": 149350 }, { "epoch": 35.84, "learning_rate": 6.142080522857459e-05, "loss": 0.0378, "step": 149360 }, { "epoch": 35.84, "learning_rate": 6.141643683785339e-05, "loss": 0.0221, "step": 149370 }, { "epoch": 35.84, "learning_rate": 6.141206835519404e-05, "loss": 0.0128, "step": 149380 }, { "epoch": 35.84, "learning_rate": 6.140769978063173e-05, "loss": 0.0195, "step": 149390 }, { "epoch": 35.84, "learning_rate": 6.140333111420164e-05, "loss": 0.0191, "step": 149400 }, { "epoch": 35.85, "learning_rate": 6.139896235593895e-05, "loss": 0.0269, "step": 149410 }, { "epoch": 35.85, "learning_rate": 6.139459350587883e-05, "loss": 0.0505, "step": 149420 }, { "epoch": 35.85, "learning_rate": 6.139022456405648e-05, "loss": 0.0165, "step": 149430 }, { "epoch": 35.85, "learning_rate": 6.13858555305071e-05, "loss": 0.0336, "step": 149440 }, { "epoch": 35.86, "learning_rate": 6.138148640526584e-05, "loss": 0.0261, "step": 149450 }, { "epoch": 35.86, "learning_rate": 6.137711718836789e-05, "loss": 0.0094, "step": 149460 }, { "epoch": 35.86, "learning_rate": 6.137274787984844e-05, "loss": 0.0287, "step": 149470 }, { "epoch": 35.86, "learning_rate": 6.13683784797427e-05, "loss": 0.0329, "step": 149480 }, { "epoch": 35.86, "learning_rate": 6.136400898808583e-05, "loss": 0.0239, "step": 149490 }, { "epoch": 35.87, "learning_rate": 6.135963940491303e-05, "loss": 0.0277, "step": 149500 }, { "epoch": 35.87, "learning_rate": 6.135526973025949e-05, "loss": 0.0154, "step": 149510 }, { "epoch": 35.87, "learning_rate": 6.135089996416039e-05, "loss": 0.0344, "step": 149520 }, { "epoch": 35.87, "learning_rate": 6.134653010665092e-05, "loss": 0.0367, "step": 149530 }, { "epoch": 35.88, "learning_rate": 6.134216015776628e-05, "loss": 0.0288, "step": 149540 }, { "epoch": 35.88, "learning_rate": 6.133779011754166e-05, "loss": 0.037, "step": 149550 }, { "epoch": 35.88, "learning_rate": 6.133341998601225e-05, "loss": 0.0397, "step": 149560 }, { "epoch": 35.88, "learning_rate": 6.132904976321324e-05, "loss": 0.0236, "step": 149570 }, { "epoch": 35.89, "learning_rate": 6.132467944917983e-05, "loss": 0.0231, "step": 149580 }, { "epoch": 35.89, "learning_rate": 6.132030904394723e-05, "loss": 0.0145, "step": 149590 }, { "epoch": 35.89, "learning_rate": 6.13159385475506e-05, "loss": 0.0423, "step": 149600 }, { "epoch": 35.89, "learning_rate": 6.131156796002516e-05, "loss": 0.0164, "step": 149610 }, { "epoch": 35.89, "learning_rate": 6.13071972814061e-05, "loss": 0.0327, "step": 149620 }, { "epoch": 35.9, "learning_rate": 6.130282651172861e-05, "loss": 0.0191, "step": 149630 }, { "epoch": 35.9, "learning_rate": 6.12984556510279e-05, "loss": 0.0229, "step": 149640 }, { "epoch": 35.9, "learning_rate": 6.129408469933918e-05, "loss": 0.0301, "step": 149650 }, { "epoch": 35.9, "learning_rate": 6.128971365669764e-05, "loss": 0.0464, "step": 149660 }, { "epoch": 35.91, "learning_rate": 6.128534252313845e-05, "loss": 0.0147, "step": 149670 }, { "epoch": 35.91, "learning_rate": 6.128097129869686e-05, "loss": 0.0174, "step": 149680 }, { "epoch": 35.91, "learning_rate": 6.127659998340805e-05, "loss": 0.0107, "step": 149690 }, { "epoch": 35.91, "learning_rate": 6.127222857730722e-05, "loss": 0.0192, "step": 149700 }, { "epoch": 35.92, "learning_rate": 6.126785708042959e-05, "loss": 0.0194, "step": 149710 }, { "epoch": 35.92, "learning_rate": 6.126348549281033e-05, "loss": 0.0157, "step": 149720 }, { "epoch": 35.92, "learning_rate": 6.125911381448468e-05, "loss": 0.0272, "step": 149730 }, { "epoch": 35.92, "learning_rate": 6.125474204548781e-05, "loss": 0.0297, "step": 149740 }, { "epoch": 35.92, "learning_rate": 6.125037018585498e-05, "loss": 0.0236, "step": 149750 }, { "epoch": 35.93, "learning_rate": 6.124599823562135e-05, "loss": 0.0142, "step": 149760 }, { "epoch": 35.93, "learning_rate": 6.124162619482214e-05, "loss": 0.0243, "step": 149770 }, { "epoch": 35.93, "learning_rate": 6.123725406349257e-05, "loss": 0.0155, "step": 149780 }, { "epoch": 35.93, "learning_rate": 6.123288184166783e-05, "loss": 0.0365, "step": 149790 }, { "epoch": 35.94, "learning_rate": 6.122850952938315e-05, "loss": 0.0344, "step": 149800 }, { "epoch": 35.94, "learning_rate": 6.122413712667374e-05, "loss": 0.0261, "step": 149810 }, { "epoch": 35.94, "learning_rate": 6.12197646335748e-05, "loss": 0.0231, "step": 149820 }, { "epoch": 35.94, "learning_rate": 6.121539205012155e-05, "loss": 0.0283, "step": 149830 }, { "epoch": 35.94, "learning_rate": 6.121101937634919e-05, "loss": 0.0179, "step": 149840 }, { "epoch": 35.95, "learning_rate": 6.120664661229293e-05, "loss": 0.0141, "step": 149850 }, { "epoch": 35.95, "learning_rate": 6.120227375798801e-05, "loss": 0.0364, "step": 149860 }, { "epoch": 36.0, "learning_rate": 6.119790081346964e-05, "loss": 0.0362, "step": 149870 }, { "epoch": 36.0, "learning_rate": 6.119352777877303e-05, "loss": 0.0142, "step": 149880 }, { "epoch": 36.01, "learning_rate": 6.11891546539334e-05, "loss": 0.0473, "step": 149890 }, { "epoch": 36.01, "learning_rate": 6.118478143898595e-05, "loss": 0.0207, "step": 149900 }, { "epoch": 36.01, "learning_rate": 6.118040813396591e-05, "loss": 0.0206, "step": 149910 }, { "epoch": 36.01, "learning_rate": 6.117603473890851e-05, "loss": 0.0107, "step": 149920 }, { "epoch": 36.01, "learning_rate": 6.117166125384895e-05, "loss": 0.0137, "step": 149930 }, { "epoch": 36.02, "learning_rate": 6.116728767882246e-05, "loss": 0.0155, "step": 149940 }, { "epoch": 36.02, "learning_rate": 6.116291401386426e-05, "loss": 0.0159, "step": 149950 }, { "epoch": 36.02, "learning_rate": 6.11585402590096e-05, "loss": 0.025, "step": 149960 }, { "epoch": 36.02, "learning_rate": 6.115416641429363e-05, "loss": 0.018, "step": 149970 }, { "epoch": 36.03, "learning_rate": 6.114979247975163e-05, "loss": 0.0282, "step": 149980 }, { "epoch": 36.03, "learning_rate": 6.114541845541883e-05, "loss": 0.0138, "step": 149990 }, { "epoch": 36.03, "learning_rate": 6.114104434133043e-05, "loss": 0.0314, "step": 150000 }, { "epoch": 36.03, "learning_rate": 6.113667013752165e-05, "loss": 0.0235, "step": 150010 }, { "epoch": 36.03, "learning_rate": 6.113229584402775e-05, "loss": 0.0399, "step": 150020 }, { "epoch": 36.04, "learning_rate": 6.112792146088391e-05, "loss": 0.021, "step": 150030 }, { "epoch": 36.04, "learning_rate": 6.11235469881254e-05, "loss": 0.0173, "step": 150040 }, { "epoch": 36.04, "learning_rate": 6.111917242578742e-05, "loss": 0.0302, "step": 150050 }, { "epoch": 36.04, "learning_rate": 6.111479777390523e-05, "loss": 0.022, "step": 150060 }, { "epoch": 36.05, "learning_rate": 6.111042303251401e-05, "loss": 0.0199, "step": 150070 }, { "epoch": 36.05, "learning_rate": 6.110604820164903e-05, "loss": 0.0233, "step": 150080 }, { "epoch": 36.05, "learning_rate": 6.110167328134552e-05, "loss": 0.0129, "step": 150090 }, { "epoch": 36.05, "learning_rate": 6.109729827163869e-05, "loss": 0.0181, "step": 150100 }, { "epoch": 36.06, "learning_rate": 6.10929231725638e-05, "loss": 0.0305, "step": 150110 }, { "epoch": 36.06, "learning_rate": 6.108854798415604e-05, "loss": 0.0256, "step": 150120 }, { "epoch": 36.06, "learning_rate": 6.108417270645069e-05, "loss": 0.0299, "step": 150130 }, { "epoch": 36.06, "learning_rate": 6.107979733948297e-05, "loss": 0.0355, "step": 150140 }, { "epoch": 36.06, "learning_rate": 6.10754218832881e-05, "loss": 0.0209, "step": 150150 }, { "epoch": 36.07, "learning_rate": 6.107104633790136e-05, "loss": 0.0188, "step": 150160 }, { "epoch": 36.07, "learning_rate": 6.106667070335793e-05, "loss": 0.0235, "step": 150170 }, { "epoch": 36.07, "learning_rate": 6.106229497969308e-05, "loss": 0.02, "step": 150180 }, { "epoch": 36.07, "learning_rate": 6.105791916694202e-05, "loss": 0.0252, "step": 150190 }, { "epoch": 36.08, "learning_rate": 6.105354326514004e-05, "loss": 0.0279, "step": 150200 }, { "epoch": 36.08, "learning_rate": 6.104916727432234e-05, "loss": 0.0251, "step": 150210 }, { "epoch": 36.08, "learning_rate": 6.104479119452416e-05, "loss": 0.0261, "step": 150220 }, { "epoch": 36.08, "learning_rate": 6.104041502578078e-05, "loss": 0.0204, "step": 150230 }, { "epoch": 36.09, "learning_rate": 6.103603876812737e-05, "loss": 0.0216, "step": 150240 }, { "epoch": 36.09, "learning_rate": 6.103166242159925e-05, "loss": 0.0262, "step": 150250 }, { "epoch": 36.09, "learning_rate": 6.102728598623162e-05, "loss": 0.0173, "step": 150260 }, { "epoch": 36.09, "learning_rate": 6.102290946205972e-05, "loss": 0.0213, "step": 150270 }, { "epoch": 36.09, "learning_rate": 6.101853284911882e-05, "loss": 0.0274, "step": 150280 }, { "epoch": 36.1, "learning_rate": 6.101415614744416e-05, "loss": 0.0216, "step": 150290 }, { "epoch": 36.1, "learning_rate": 6.100977935707098e-05, "loss": 0.0224, "step": 150300 }, { "epoch": 36.1, "learning_rate": 6.100540247803451e-05, "loss": 0.0172, "step": 150310 }, { "epoch": 36.1, "learning_rate": 6.1001025510370035e-05, "loss": 0.0184, "step": 150320 }, { "epoch": 36.11, "learning_rate": 6.099664845411277e-05, "loss": 0.0349, "step": 150330 }, { "epoch": 36.11, "learning_rate": 6.099227130929798e-05, "loss": 0.0116, "step": 150340 }, { "epoch": 36.11, "learning_rate": 6.098789407596093e-05, "loss": 0.0156, "step": 150350 }, { "epoch": 36.11, "learning_rate": 6.098351675413682e-05, "loss": 0.0168, "step": 150360 }, { "epoch": 36.11, "learning_rate": 6.097913934386096e-05, "loss": 0.0145, "step": 150370 }, { "epoch": 36.12, "learning_rate": 6.097476184516855e-05, "loss": 0.0218, "step": 150380 }, { "epoch": 36.12, "learning_rate": 6.097038425809488e-05, "loss": 0.0235, "step": 150390 }, { "epoch": 36.12, "learning_rate": 6.096600658267519e-05, "loss": 0.0248, "step": 150400 }, { "epoch": 36.12, "learning_rate": 6.096162881894474e-05, "loss": 0.0106, "step": 150410 }, { "epoch": 36.13, "learning_rate": 6.0957250966938785e-05, "loss": 0.0193, "step": 150420 }, { "epoch": 36.13, "learning_rate": 6.095287302669256e-05, "loss": 0.0278, "step": 150430 }, { "epoch": 36.13, "learning_rate": 6.094849499824134e-05, "loss": 0.0235, "step": 150440 }, { "epoch": 36.13, "learning_rate": 6.094411688162038e-05, "loss": 0.0279, "step": 150450 }, { "epoch": 36.14, "learning_rate": 6.0939738676864935e-05, "loss": 0.0181, "step": 150460 }, { "epoch": 36.14, "learning_rate": 6.093536038401028e-05, "loss": 0.022, "step": 150470 }, { "epoch": 36.14, "learning_rate": 6.093098200309163e-05, "loss": 0.0207, "step": 150480 }, { "epoch": 36.14, "learning_rate": 6.09266035341443e-05, "loss": 0.0204, "step": 150490 }, { "epoch": 36.14, "learning_rate": 6.0922224977203503e-05, "loss": 0.0285, "step": 150500 }, { "epoch": 36.15, "learning_rate": 6.091784633230453e-05, "loss": 0.0267, "step": 150510 }, { "epoch": 36.15, "learning_rate": 6.0913467599482624e-05, "loss": 0.0173, "step": 150520 }, { "epoch": 36.15, "learning_rate": 6.090908877877306e-05, "loss": 0.0272, "step": 150530 }, { "epoch": 36.15, "learning_rate": 6.090470987021111e-05, "loss": 0.0137, "step": 150540 }, { "epoch": 36.16, "learning_rate": 6.090033087383201e-05, "loss": 0.0161, "step": 150550 }, { "epoch": 36.16, "learning_rate": 6.089595178967104e-05, "loss": 0.0178, "step": 150560 }, { "epoch": 36.16, "learning_rate": 6.089157261776348e-05, "loss": 0.0237, "step": 150570 }, { "epoch": 36.16, "learning_rate": 6.088719335814458e-05, "loss": 0.0111, "step": 150580 }, { "epoch": 36.16, "learning_rate": 6.088281401084961e-05, "loss": 0.0219, "step": 150590 }, { "epoch": 36.17, "learning_rate": 6.0878434575913824e-05, "loss": 0.0113, "step": 150600 }, { "epoch": 36.17, "learning_rate": 6.087405505337251e-05, "loss": 0.0259, "step": 150610 }, { "epoch": 36.17, "learning_rate": 6.086967544326093e-05, "loss": 0.0185, "step": 150620 }, { "epoch": 36.17, "learning_rate": 6.0865295745614346e-05, "loss": 0.0198, "step": 150630 }, { "epoch": 36.18, "learning_rate": 6.0860915960468046e-05, "loss": 0.0227, "step": 150640 }, { "epoch": 36.18, "learning_rate": 6.085653608785729e-05, "loss": 0.0293, "step": 150650 }, { "epoch": 36.18, "learning_rate": 6.085215612781735e-05, "loss": 0.0199, "step": 150660 }, { "epoch": 36.18, "learning_rate": 6.084777608038348e-05, "loss": 0.0204, "step": 150670 }, { "epoch": 36.19, "learning_rate": 6.0843395945590984e-05, "loss": 0.0226, "step": 150680 }, { "epoch": 36.19, "learning_rate": 6.083901572347513e-05, "loss": 0.0201, "step": 150690 }, { "epoch": 36.19, "learning_rate": 6.0834635414071187e-05, "loss": 0.0331, "step": 150700 }, { "epoch": 36.19, "learning_rate": 6.083025501741442e-05, "loss": 0.0228, "step": 150710 }, { "epoch": 36.19, "learning_rate": 6.0825874533540116e-05, "loss": 0.0142, "step": 150720 }, { "epoch": 36.2, "learning_rate": 6.082149396248355e-05, "loss": 0.0177, "step": 150730 }, { "epoch": 36.2, "learning_rate": 6.081711330427999e-05, "loss": 0.0232, "step": 150740 }, { "epoch": 36.2, "learning_rate": 6.081273255896475e-05, "loss": 0.0285, "step": 150750 }, { "epoch": 36.2, "learning_rate": 6.080835172657306e-05, "loss": 0.0311, "step": 150760 }, { "epoch": 36.21, "learning_rate": 6.080397080714023e-05, "loss": 0.0218, "step": 150770 }, { "epoch": 36.21, "learning_rate": 6.079958980070153e-05, "loss": 0.0156, "step": 150780 }, { "epoch": 36.21, "learning_rate": 6.079520870729223e-05, "loss": 0.0385, "step": 150790 }, { "epoch": 36.21, "learning_rate": 6.079082752694765e-05, "loss": 0.0379, "step": 150800 }, { "epoch": 36.22, "learning_rate": 6.078644625970302e-05, "loss": 0.0247, "step": 150810 }, { "epoch": 36.22, "learning_rate": 6.078206490559366e-05, "loss": 0.0269, "step": 150820 }, { "epoch": 36.22, "learning_rate": 6.0777683464654844e-05, "loss": 0.0231, "step": 150830 }, { "epoch": 36.22, "learning_rate": 6.077330193692186e-05, "loss": 0.0264, "step": 150840 }, { "epoch": 36.22, "learning_rate": 6.076892032242998e-05, "loss": 0.0257, "step": 150850 }, { "epoch": 36.23, "learning_rate": 6.0764538621214493e-05, "loss": 0.0185, "step": 150860 }, { "epoch": 36.23, "learning_rate": 6.07601568333107e-05, "loss": 0.0296, "step": 150870 }, { "epoch": 36.23, "learning_rate": 6.0755774958753877e-05, "loss": 0.0295, "step": 150880 }, { "epoch": 36.23, "learning_rate": 6.075139299757931e-05, "loss": 0.0313, "step": 150890 }, { "epoch": 36.24, "learning_rate": 6.074701094982229e-05, "loss": 0.032, "step": 150900 }, { "epoch": 36.24, "learning_rate": 6.074262881551811e-05, "loss": 0.021, "step": 150910 }, { "epoch": 36.24, "learning_rate": 6.073824659470206e-05, "loss": 0.0138, "step": 150920 }, { "epoch": 36.24, "learning_rate": 6.073386428740941e-05, "loss": 0.019, "step": 150930 }, { "epoch": 36.24, "learning_rate": 6.07294818936755e-05, "loss": 0.0312, "step": 150940 }, { "epoch": 36.25, "learning_rate": 6.072509941353557e-05, "loss": 0.0317, "step": 150950 }, { "epoch": 36.25, "learning_rate": 6.072071684702494e-05, "loss": 0.0231, "step": 150960 }, { "epoch": 36.25, "learning_rate": 6.07163341941789e-05, "loss": 0.0366, "step": 150970 }, { "epoch": 36.25, "learning_rate": 6.071195145503274e-05, "loss": 0.0162, "step": 150980 }, { "epoch": 36.26, "learning_rate": 6.0707568629621735e-05, "loss": 0.0223, "step": 150990 }, { "epoch": 36.26, "learning_rate": 6.070318571798123e-05, "loss": 0.0179, "step": 151000 }, { "epoch": 36.26, "learning_rate": 6.069880272014648e-05, "loss": 0.0234, "step": 151010 }, { "epoch": 36.26, "learning_rate": 6.06944196361528e-05, "loss": 0.0178, "step": 151020 }, { "epoch": 36.27, "learning_rate": 6.069003646603548e-05, "loss": 0.0243, "step": 151030 }, { "epoch": 36.27, "learning_rate": 6.068565320982982e-05, "loss": 0.0234, "step": 151040 }, { "epoch": 36.27, "learning_rate": 6.0681269867571124e-05, "loss": 0.019, "step": 151050 }, { "epoch": 36.27, "learning_rate": 6.067688643929467e-05, "loss": 0.0111, "step": 151060 }, { "epoch": 36.27, "learning_rate": 6.067250292503579e-05, "loss": 0.0347, "step": 151070 }, { "epoch": 36.28, "learning_rate": 6.0668119324829764e-05, "loss": 0.0339, "step": 151080 }, { "epoch": 36.28, "learning_rate": 6.0663735638711905e-05, "loss": 0.0169, "step": 151090 }, { "epoch": 36.28, "learning_rate": 6.0659351866717515e-05, "loss": 0.0118, "step": 151100 }, { "epoch": 36.28, "learning_rate": 6.0654968008881886e-05, "loss": 0.0141, "step": 151110 }, { "epoch": 36.29, "learning_rate": 6.065058406524032e-05, "loss": 0.031, "step": 151120 }, { "epoch": 36.29, "learning_rate": 6.064620003582815e-05, "loss": 0.0312, "step": 151130 }, { "epoch": 36.29, "learning_rate": 6.064181592068065e-05, "loss": 0.0198, "step": 151140 }, { "epoch": 36.29, "learning_rate": 6.063743171983314e-05, "loss": 0.0253, "step": 151150 }, { "epoch": 36.3, "learning_rate": 6.063304743332092e-05, "loss": 0.0295, "step": 151160 }, { "epoch": 36.3, "learning_rate": 6.0628663061179316e-05, "loss": 0.0187, "step": 151170 }, { "epoch": 36.3, "learning_rate": 6.062427860344359e-05, "loss": 0.023, "step": 151180 }, { "epoch": 36.3, "learning_rate": 6.0619894060149106e-05, "loss": 0.0222, "step": 151190 }, { "epoch": 36.3, "learning_rate": 6.061550943133114e-05, "loss": 0.0158, "step": 151200 }, { "epoch": 36.31, "learning_rate": 6.0611124717025023e-05, "loss": 0.0227, "step": 151210 }, { "epoch": 36.31, "learning_rate": 6.060673991726604e-05, "loss": 0.0131, "step": 151220 }, { "epoch": 36.31, "learning_rate": 6.060235503208952e-05, "loss": 0.0253, "step": 151230 }, { "epoch": 36.31, "learning_rate": 6.059797006153079e-05, "loss": 0.0198, "step": 151240 }, { "epoch": 36.32, "learning_rate": 6.0593585005625106e-05, "loss": 0.0282, "step": 151250 }, { "epoch": 36.32, "learning_rate": 6.058919986440784e-05, "loss": 0.023, "step": 151260 }, { "epoch": 36.32, "learning_rate": 6.058481463791429e-05, "loss": 0.0198, "step": 151270 }, { "epoch": 36.32, "learning_rate": 6.058042932617976e-05, "loss": 0.0213, "step": 151280 }, { "epoch": 36.32, "learning_rate": 6.057604392923958e-05, "loss": 0.0158, "step": 151290 }, { "epoch": 36.33, "learning_rate": 6.057165844712904e-05, "loss": 0.0302, "step": 151300 }, { "epoch": 36.33, "learning_rate": 6.0567272879883496e-05, "loss": 0.0374, "step": 151310 }, { "epoch": 36.33, "learning_rate": 6.056288722753824e-05, "loss": 0.0249, "step": 151320 }, { "epoch": 36.33, "learning_rate": 6.0558501490128584e-05, "loss": 0.0358, "step": 151330 }, { "epoch": 36.34, "learning_rate": 6.055411566768987e-05, "loss": 0.0188, "step": 151340 }, { "epoch": 36.34, "learning_rate": 6.054972976025739e-05, "loss": 0.0475, "step": 151350 }, { "epoch": 36.34, "learning_rate": 6.054534376786649e-05, "loss": 0.0114, "step": 151360 }, { "epoch": 36.34, "learning_rate": 6.054095769055248e-05, "loss": 0.0238, "step": 151370 }, { "epoch": 36.35, "learning_rate": 6.053657152835069e-05, "loss": 0.02, "step": 151380 }, { "epoch": 36.35, "learning_rate": 6.053218528129642e-05, "loss": 0.0199, "step": 151390 }, { "epoch": 36.35, "learning_rate": 6.0527798949425015e-05, "loss": 0.0364, "step": 151400 }, { "epoch": 36.35, "learning_rate": 6.0523412532771794e-05, "loss": 0.0195, "step": 151410 }, { "epoch": 36.35, "learning_rate": 6.051902603137207e-05, "loss": 0.0118, "step": 151420 }, { "epoch": 36.36, "learning_rate": 6.051463944526119e-05, "loss": 0.0184, "step": 151430 }, { "epoch": 36.36, "learning_rate": 6.051025277447445e-05, "loss": 0.0263, "step": 151440 }, { "epoch": 36.36, "learning_rate": 6.050586601904721e-05, "loss": 0.0231, "step": 151450 }, { "epoch": 36.36, "learning_rate": 6.0501479179014775e-05, "loss": 0.0303, "step": 151460 }, { "epoch": 36.37, "learning_rate": 6.049709225441248e-05, "loss": 0.0286, "step": 151470 }, { "epoch": 36.37, "learning_rate": 6.049270524527565e-05, "loss": 0.0175, "step": 151480 }, { "epoch": 36.37, "learning_rate": 6.048831815163961e-05, "loss": 0.0298, "step": 151490 }, { "epoch": 36.37, "learning_rate": 6.048393097353972e-05, "loss": 0.0101, "step": 151500 }, { "epoch": 36.38, "learning_rate": 6.0479543711011254e-05, "loss": 0.023, "step": 151510 }, { "epoch": 36.38, "learning_rate": 6.047515636408959e-05, "loss": 0.0285, "step": 151520 }, { "epoch": 36.38, "learning_rate": 6.047076893281005e-05, "loss": 0.014, "step": 151530 }, { "epoch": 36.38, "learning_rate": 6.046638141720795e-05, "loss": 0.0121, "step": 151540 }, { "epoch": 36.38, "learning_rate": 6.046199381731865e-05, "loss": 0.0215, "step": 151550 }, { "epoch": 36.39, "learning_rate": 6.045760613317746e-05, "loss": 0.0377, "step": 151560 }, { "epoch": 36.39, "learning_rate": 6.045321836481974e-05, "loss": 0.0601, "step": 151570 }, { "epoch": 36.39, "learning_rate": 6.044883051228079e-05, "loss": 0.0171, "step": 151580 }, { "epoch": 36.39, "learning_rate": 6.044444257559596e-05, "loss": 0.0257, "step": 151590 }, { "epoch": 36.4, "learning_rate": 6.044005455480061e-05, "loss": 0.0206, "step": 151600 }, { "epoch": 36.4, "learning_rate": 6.043566644993004e-05, "loss": 0.0122, "step": 151610 }, { "epoch": 36.4, "learning_rate": 6.043127826101964e-05, "loss": 0.0194, "step": 151620 }, { "epoch": 36.4, "learning_rate": 6.0426889988104684e-05, "loss": 0.0081, "step": 151630 }, { "epoch": 36.4, "learning_rate": 6.042250163122056e-05, "loss": 0.0417, "step": 151640 }, { "epoch": 36.41, "learning_rate": 6.0418113190402584e-05, "loss": 0.0244, "step": 151650 }, { "epoch": 36.41, "learning_rate": 6.04137246656861e-05, "loss": 0.0108, "step": 151660 }, { "epoch": 36.41, "learning_rate": 6.040933605710647e-05, "loss": 0.03, "step": 151670 }, { "epoch": 36.41, "learning_rate": 6.0404947364699004e-05, "loss": 0.0209, "step": 151680 }, { "epoch": 36.42, "learning_rate": 6.040055858849908e-05, "loss": 0.029, "step": 151690 }, { "epoch": 36.42, "learning_rate": 6.0396169728541994e-05, "loss": 0.0196, "step": 151700 }, { "epoch": 36.42, "learning_rate": 6.039178078486314e-05, "loss": 0.0328, "step": 151710 }, { "epoch": 36.42, "learning_rate": 6.038739175749784e-05, "loss": 0.0169, "step": 151720 }, { "epoch": 36.43, "learning_rate": 6.038300264648141e-05, "loss": 0.0148, "step": 151730 }, { "epoch": 36.43, "learning_rate": 6.0378613451849265e-05, "loss": 0.0353, "step": 151740 }, { "epoch": 36.43, "learning_rate": 6.0374224173636693e-05, "loss": 0.0117, "step": 151750 }, { "epoch": 36.43, "learning_rate": 6.036983481187908e-05, "loss": 0.0186, "step": 151760 }, { "epoch": 36.43, "learning_rate": 6.036544536661173e-05, "loss": 0.0221, "step": 151770 }, { "epoch": 36.44, "learning_rate": 6.036105583787003e-05, "loss": 0.0243, "step": 151780 }, { "epoch": 36.44, "learning_rate": 6.035666622568932e-05, "loss": 0.024, "step": 151790 }, { "epoch": 36.44, "learning_rate": 6.0352276530104934e-05, "loss": 0.0092, "step": 151800 }, { "epoch": 36.44, "learning_rate": 6.034788675115226e-05, "loss": 0.0157, "step": 151810 }, { "epoch": 36.45, "learning_rate": 6.03434968888666e-05, "loss": 0.0243, "step": 151820 }, { "epoch": 36.45, "learning_rate": 6.0339106943283344e-05, "loss": 0.0206, "step": 151830 }, { "epoch": 36.45, "learning_rate": 6.033471691443783e-05, "loss": 0.0269, "step": 151840 }, { "epoch": 36.45, "learning_rate": 6.03303268023654e-05, "loss": 0.0136, "step": 151850 }, { "epoch": 36.46, "learning_rate": 6.032593660710145e-05, "loss": 0.0173, "step": 151860 }, { "epoch": 36.46, "learning_rate": 6.032154632868128e-05, "loss": 0.0409, "step": 151870 }, { "epoch": 36.46, "learning_rate": 6.0317155967140304e-05, "loss": 0.0202, "step": 151880 }, { "epoch": 36.46, "learning_rate": 6.0312765522513816e-05, "loss": 0.0198, "step": 151890 }, { "epoch": 36.46, "learning_rate": 6.030837499483721e-05, "loss": 0.0233, "step": 151900 }, { "epoch": 36.47, "learning_rate": 6.0303984384145854e-05, "loss": 0.0215, "step": 151910 }, { "epoch": 36.47, "learning_rate": 6.0299593690475064e-05, "loss": 0.0167, "step": 151920 }, { "epoch": 36.47, "learning_rate": 6.029520291386025e-05, "loss": 0.0188, "step": 151930 }, { "epoch": 36.47, "learning_rate": 6.029081205433673e-05, "loss": 0.0146, "step": 151940 }, { "epoch": 36.48, "learning_rate": 6.0286421111939887e-05, "loss": 0.0156, "step": 151950 }, { "epoch": 36.48, "learning_rate": 6.028203008670506e-05, "loss": 0.0202, "step": 151960 }, { "epoch": 36.48, "learning_rate": 6.027763897866765e-05, "loss": 0.0296, "step": 151970 }, { "epoch": 36.48, "learning_rate": 6.027324778786297e-05, "loss": 0.0165, "step": 151980 }, { "epoch": 36.48, "learning_rate": 6.026885651432641e-05, "loss": 0.0173, "step": 151990 }, { "epoch": 36.49, "learning_rate": 6.026446515809335e-05, "loss": 0.0308, "step": 152000 }, { "epoch": 36.49, "learning_rate": 6.0260073719199116e-05, "loss": 0.0193, "step": 152010 }, { "epoch": 36.49, "learning_rate": 6.025568219767911e-05, "loss": 0.0342, "step": 152020 }, { "epoch": 36.49, "learning_rate": 6.025129059356867e-05, "loss": 0.0127, "step": 152030 }, { "epoch": 36.5, "learning_rate": 6.024689890690316e-05, "loss": 0.0377, "step": 152040 }, { "epoch": 36.5, "learning_rate": 6.024250713771797e-05, "loss": 0.0318, "step": 152050 }, { "epoch": 36.5, "learning_rate": 6.023811528604846e-05, "loss": 0.0224, "step": 152060 }, { "epoch": 36.5, "learning_rate": 6.023372335192998e-05, "loss": 0.0234, "step": 152070 }, { "epoch": 36.51, "learning_rate": 6.022933133539793e-05, "loss": 0.0358, "step": 152080 }, { "epoch": 36.51, "learning_rate": 6.0224939236487655e-05, "loss": 0.0196, "step": 152090 }, { "epoch": 36.51, "learning_rate": 6.022054705523453e-05, "loss": 0.03, "step": 152100 }, { "epoch": 36.51, "learning_rate": 6.021615479167393e-05, "loss": 0.0278, "step": 152110 }, { "epoch": 36.51, "learning_rate": 6.0211762445841234e-05, "loss": 0.0177, "step": 152120 }, { "epoch": 36.52, "learning_rate": 6.020737001777178e-05, "loss": 0.0208, "step": 152130 }, { "epoch": 36.52, "learning_rate": 6.020297750750099e-05, "loss": 0.0318, "step": 152140 }, { "epoch": 36.52, "learning_rate": 6.019858491506421e-05, "loss": 0.0241, "step": 152150 }, { "epoch": 36.52, "learning_rate": 6.0194192240496816e-05, "loss": 0.0201, "step": 152160 }, { "epoch": 36.53, "learning_rate": 6.0189799483834186e-05, "loss": 0.0158, "step": 152170 }, { "epoch": 36.53, "learning_rate": 6.0185406645111675e-05, "loss": 0.0161, "step": 152180 }, { "epoch": 36.53, "learning_rate": 6.01810137243647e-05, "loss": 0.02, "step": 152190 }, { "epoch": 36.53, "learning_rate": 6.0176620721628605e-05, "loss": 0.0343, "step": 152200 }, { "epoch": 36.54, "learning_rate": 6.0172227636938785e-05, "loss": 0.0386, "step": 152210 }, { "epoch": 36.54, "learning_rate": 6.0167834470330605e-05, "loss": 0.0366, "step": 152220 }, { "epoch": 36.54, "learning_rate": 6.0163441221839467e-05, "loss": 0.0201, "step": 152230 }, { "epoch": 36.54, "learning_rate": 6.015904789150072e-05, "loss": 0.0352, "step": 152240 }, { "epoch": 36.54, "learning_rate": 6.015465447934975e-05, "loss": 0.0196, "step": 152250 }, { "epoch": 36.55, "learning_rate": 6.015026098542196e-05, "loss": 0.0245, "step": 152260 }, { "epoch": 36.55, "learning_rate": 6.014586740975271e-05, "loss": 0.0208, "step": 152270 }, { "epoch": 36.55, "learning_rate": 6.014147375237739e-05, "loss": 0.0163, "step": 152280 }, { "epoch": 36.55, "learning_rate": 6.013708001333138e-05, "loss": 0.0228, "step": 152290 }, { "epoch": 36.56, "learning_rate": 6.0132686192650064e-05, "loss": 0.0325, "step": 152300 }, { "epoch": 36.56, "learning_rate": 6.012829229036884e-05, "loss": 0.0207, "step": 152310 }, { "epoch": 36.56, "learning_rate": 6.0123898306523067e-05, "loss": 0.0168, "step": 152320 }, { "epoch": 36.56, "learning_rate": 6.011950424114814e-05, "loss": 0.0153, "step": 152330 }, { "epoch": 36.56, "learning_rate": 6.011511009427946e-05, "loss": 0.0196, "step": 152340 }, { "epoch": 36.57, "learning_rate": 6.0110715865952405e-05, "loss": 0.0249, "step": 152350 }, { "epoch": 36.57, "learning_rate": 6.010632155620235e-05, "loss": 0.0211, "step": 152360 }, { "epoch": 36.57, "learning_rate": 6.010192716506469e-05, "loss": 0.0361, "step": 152370 }, { "epoch": 36.57, "learning_rate": 6.009753269257481e-05, "loss": 0.0257, "step": 152380 }, { "epoch": 36.58, "learning_rate": 6.009313813876811e-05, "loss": 0.0363, "step": 152390 }, { "epoch": 36.58, "learning_rate": 6.008874350367999e-05, "loss": 0.0488, "step": 152400 }, { "epoch": 36.58, "learning_rate": 6.008434878734581e-05, "loss": 0.0348, "step": 152410 }, { "epoch": 36.58, "learning_rate": 6.0079953989801e-05, "loss": 0.0331, "step": 152420 }, { "epoch": 36.59, "learning_rate": 6.00755591110809e-05, "loss": 0.0163, "step": 152430 }, { "epoch": 36.59, "learning_rate": 6.007116415122094e-05, "loss": 0.0363, "step": 152440 }, { "epoch": 36.59, "learning_rate": 6.0066769110256504e-05, "loss": 0.039, "step": 152450 }, { "epoch": 36.59, "learning_rate": 6.0062373988222994e-05, "loss": 0.043, "step": 152460 }, { "epoch": 36.59, "learning_rate": 6.00579787851558e-05, "loss": 0.0283, "step": 152470 }, { "epoch": 36.6, "learning_rate": 6.00535835010903e-05, "loss": 0.014, "step": 152480 }, { "epoch": 36.6, "learning_rate": 6.004918813606192e-05, "loss": 0.0244, "step": 152490 }, { "epoch": 36.6, "learning_rate": 6.004479269010602e-05, "loss": 0.0388, "step": 152500 }, { "epoch": 36.6, "learning_rate": 6.004039716325803e-05, "loss": 0.0579, "step": 152510 }, { "epoch": 36.61, "learning_rate": 6.0036001555553333e-05, "loss": 0.0255, "step": 152520 }, { "epoch": 36.61, "learning_rate": 6.003160586702734e-05, "loss": 0.0316, "step": 152530 }, { "epoch": 36.61, "learning_rate": 6.0027210097715436e-05, "loss": 0.0198, "step": 152540 }, { "epoch": 36.61, "learning_rate": 6.0022814247653015e-05, "loss": 0.0287, "step": 152550 }, { "epoch": 36.62, "learning_rate": 6.001841831687549e-05, "loss": 0.0162, "step": 152560 }, { "epoch": 36.62, "learning_rate": 6.001402230541826e-05, "loss": 0.0166, "step": 152570 }, { "epoch": 36.62, "learning_rate": 6.000962621331673e-05, "loss": 0.0307, "step": 152580 }, { "epoch": 36.62, "learning_rate": 6.00052300406063e-05, "loss": 0.0209, "step": 152590 }, { "epoch": 36.62, "learning_rate": 6.000083378732236e-05, "loss": 0.0208, "step": 152600 }, { "epoch": 36.63, "learning_rate": 5.9996437453500344e-05, "loss": 0.0276, "step": 152610 }, { "epoch": 36.63, "learning_rate": 5.9992041039175616e-05, "loss": 0.019, "step": 152620 }, { "epoch": 36.63, "learning_rate": 5.998764454438361e-05, "loss": 0.0183, "step": 152630 }, { "epoch": 36.63, "learning_rate": 5.998324796915973e-05, "loss": 0.0175, "step": 152640 }, { "epoch": 36.64, "learning_rate": 5.9978851313539364e-05, "loss": 0.0438, "step": 152650 }, { "epoch": 36.64, "learning_rate": 5.997445457755794e-05, "loss": 0.021, "step": 152660 }, { "epoch": 36.64, "learning_rate": 5.997005776125085e-05, "loss": 0.0288, "step": 152670 }, { "epoch": 36.64, "learning_rate": 5.9965660864653514e-05, "loss": 0.0329, "step": 152680 }, { "epoch": 36.64, "learning_rate": 5.996126388780133e-05, "loss": 0.0152, "step": 152690 }, { "epoch": 36.65, "learning_rate": 5.995686683072972e-05, "loss": 0.0276, "step": 152700 }, { "epoch": 36.65, "learning_rate": 5.995246969347408e-05, "loss": 0.035, "step": 152710 }, { "epoch": 36.65, "learning_rate": 5.994807247606984e-05, "loss": 0.0284, "step": 152720 }, { "epoch": 36.65, "learning_rate": 5.994367517855238e-05, "loss": 0.0162, "step": 152730 }, { "epoch": 36.66, "learning_rate": 5.993927780095715e-05, "loss": 0.0158, "step": 152740 }, { "epoch": 36.66, "learning_rate": 5.993488034331953e-05, "loss": 0.0386, "step": 152750 }, { "epoch": 36.66, "learning_rate": 5.9930482805674946e-05, "loss": 0.0258, "step": 152760 }, { "epoch": 36.66, "learning_rate": 5.992608518805881e-05, "loss": 0.0234, "step": 152770 }, { "epoch": 36.67, "learning_rate": 5.992168749050655e-05, "loss": 0.0416, "step": 152780 }, { "epoch": 36.67, "learning_rate": 5.991728971305357e-05, "loss": 0.0257, "step": 152790 }, { "epoch": 36.67, "learning_rate": 5.9912891855735285e-05, "loss": 0.0197, "step": 152800 }, { "epoch": 36.67, "learning_rate": 5.9908493918587104e-05, "loss": 0.0331, "step": 152810 }, { "epoch": 36.67, "learning_rate": 5.990409590164448e-05, "loss": 0.0368, "step": 152820 }, { "epoch": 36.68, "learning_rate": 5.989969780494278e-05, "loss": 0.0247, "step": 152830 }, { "epoch": 36.68, "learning_rate": 5.9895299628517454e-05, "loss": 0.0166, "step": 152840 }, { "epoch": 36.68, "learning_rate": 5.989090137240392e-05, "loss": 0.0215, "step": 152850 }, { "epoch": 36.68, "learning_rate": 5.988650303663759e-05, "loss": 0.0384, "step": 152860 }, { "epoch": 36.69, "learning_rate": 5.9882104621253874e-05, "loss": 0.0296, "step": 152870 }, { "epoch": 36.69, "learning_rate": 5.98777061262882e-05, "loss": 0.0285, "step": 152880 }, { "epoch": 36.69, "learning_rate": 5.9873307551776026e-05, "loss": 0.0428, "step": 152890 }, { "epoch": 36.69, "learning_rate": 5.986890889775272e-05, "loss": 0.023, "step": 152900 }, { "epoch": 36.7, "learning_rate": 5.9864510164253725e-05, "loss": 0.0216, "step": 152910 }, { "epoch": 36.7, "learning_rate": 5.986011135131449e-05, "loss": 0.0289, "step": 152920 }, { "epoch": 36.7, "learning_rate": 5.985571245897039e-05, "loss": 0.0245, "step": 152930 }, { "epoch": 36.7, "learning_rate": 5.98513134872569e-05, "loss": 0.0174, "step": 152940 }, { "epoch": 36.7, "learning_rate": 5.98469144362094e-05, "loss": 0.0225, "step": 152950 }, { "epoch": 36.71, "learning_rate": 5.984251530586337e-05, "loss": 0.0221, "step": 152960 }, { "epoch": 36.71, "learning_rate": 5.983811609625417e-05, "loss": 0.0392, "step": 152970 }, { "epoch": 36.71, "learning_rate": 5.9833716807417284e-05, "loss": 0.0209, "step": 152980 }, { "epoch": 36.71, "learning_rate": 5.982931743938811e-05, "loss": 0.0148, "step": 152990 }, { "epoch": 36.72, "learning_rate": 5.982491799220209e-05, "loss": 0.0274, "step": 153000 }, { "epoch": 36.72, "learning_rate": 5.982051846589466e-05, "loss": 0.0269, "step": 153010 }, { "epoch": 36.72, "learning_rate": 5.981611886050121e-05, "loss": 0.0354, "step": 153020 }, { "epoch": 36.72, "learning_rate": 5.981171917605722e-05, "loss": 0.0294, "step": 153030 }, { "epoch": 36.72, "learning_rate": 5.980731941259811e-05, "loss": 0.013, "step": 153040 }, { "epoch": 36.73, "learning_rate": 5.980291957015928e-05, "loss": 0.0283, "step": 153050 }, { "epoch": 36.73, "learning_rate": 5.979851964877621e-05, "loss": 0.0116, "step": 153060 }, { "epoch": 36.73, "learning_rate": 5.979411964848428e-05, "loss": 0.0223, "step": 153070 }, { "epoch": 36.73, "learning_rate": 5.978971956931898e-05, "loss": 0.0224, "step": 153080 }, { "epoch": 36.74, "learning_rate": 5.97853194113157e-05, "loss": 0.0242, "step": 153090 }, { "epoch": 36.74, "learning_rate": 5.9780919174509896e-05, "loss": 0.0234, "step": 153100 }, { "epoch": 36.74, "learning_rate": 5.9776518858937e-05, "loss": 0.0184, "step": 153110 }, { "epoch": 36.74, "learning_rate": 5.9772118464632435e-05, "loss": 0.009, "step": 153120 }, { "epoch": 36.75, "learning_rate": 5.9767717991631677e-05, "loss": 0.0255, "step": 153130 }, { "epoch": 36.75, "learning_rate": 5.976331743997011e-05, "loss": 0.022, "step": 153140 }, { "epoch": 36.75, "learning_rate": 5.975891680968322e-05, "loss": 0.021, "step": 153150 }, { "epoch": 36.75, "learning_rate": 5.9754516100806423e-05, "loss": 0.0231, "step": 153160 }, { "epoch": 36.75, "learning_rate": 5.975011531337516e-05, "loss": 0.0194, "step": 153170 }, { "epoch": 36.76, "learning_rate": 5.9745714447424864e-05, "loss": 0.0228, "step": 153180 }, { "epoch": 36.76, "learning_rate": 5.974131350299098e-05, "loss": 0.0081, "step": 153190 }, { "epoch": 36.76, "learning_rate": 5.9736912480108974e-05, "loss": 0.0265, "step": 153200 }, { "epoch": 36.76, "learning_rate": 5.973251137881425e-05, "loss": 0.0237, "step": 153210 }, { "epoch": 36.77, "learning_rate": 5.972811019914227e-05, "loss": 0.0135, "step": 153220 }, { "epoch": 36.77, "learning_rate": 5.972370894112849e-05, "loss": 0.0346, "step": 153230 }, { "epoch": 36.77, "learning_rate": 5.971930760480832e-05, "loss": 0.0175, "step": 153240 }, { "epoch": 36.77, "learning_rate": 5.971490619021724e-05, "loss": 0.0428, "step": 153250 }, { "epoch": 36.78, "learning_rate": 5.971050469739067e-05, "loss": 0.0099, "step": 153260 }, { "epoch": 36.78, "learning_rate": 5.970610312636408e-05, "loss": 0.0311, "step": 153270 }, { "epoch": 36.78, "learning_rate": 5.970170147717288e-05, "loss": 0.016, "step": 153280 }, { "epoch": 36.78, "learning_rate": 5.969729974985255e-05, "loss": 0.0142, "step": 153290 }, { "epoch": 36.78, "learning_rate": 5.969289794443853e-05, "loss": 0.027, "step": 153300 }, { "epoch": 36.79, "learning_rate": 5.9688496060966245e-05, "loss": 0.0268, "step": 153310 }, { "epoch": 36.79, "learning_rate": 5.968409409947119e-05, "loss": 0.0274, "step": 153320 }, { "epoch": 36.79, "learning_rate": 5.9679692059988766e-05, "loss": 0.0201, "step": 153330 }, { "epoch": 36.79, "learning_rate": 5.9675289942554456e-05, "loss": 0.0105, "step": 153340 }, { "epoch": 36.8, "learning_rate": 5.967088774720371e-05, "loss": 0.0194, "step": 153350 }, { "epoch": 36.8, "learning_rate": 5.9666485473971944e-05, "loss": 0.0222, "step": 153360 }, { "epoch": 36.8, "learning_rate": 5.966208312289466e-05, "loss": 0.0469, "step": 153370 }, { "epoch": 36.8, "learning_rate": 5.9657680694007265e-05, "loss": 0.0274, "step": 153380 }, { "epoch": 36.8, "learning_rate": 5.965327818734526e-05, "loss": 0.0095, "step": 153390 }, { "epoch": 36.81, "learning_rate": 5.9648875602944055e-05, "loss": 0.0275, "step": 153400 }, { "epoch": 36.81, "learning_rate": 5.9644472940839134e-05, "loss": 0.0191, "step": 153410 }, { "epoch": 36.81, "learning_rate": 5.964007020106593e-05, "loss": 0.0143, "step": 153420 }, { "epoch": 36.81, "learning_rate": 5.963566738365991e-05, "loss": 0.0429, "step": 153430 }, { "epoch": 36.82, "learning_rate": 5.963126448865655e-05, "loss": 0.0126, "step": 153440 }, { "epoch": 36.82, "learning_rate": 5.962686151609126e-05, "loss": 0.022, "step": 153450 }, { "epoch": 36.82, "learning_rate": 5.9622458465999546e-05, "loss": 0.0152, "step": 153460 }, { "epoch": 36.82, "learning_rate": 5.9618055338416836e-05, "loss": 0.0372, "step": 153470 }, { "epoch": 36.83, "learning_rate": 5.9613652133378595e-05, "loss": 0.0254, "step": 153480 }, { "epoch": 36.83, "learning_rate": 5.9609248850920296e-05, "loss": 0.0284, "step": 153490 }, { "epoch": 36.83, "learning_rate": 5.9604845491077365e-05, "loss": 0.0221, "step": 153500 }, { "epoch": 36.83, "learning_rate": 5.960044205388533e-05, "loss": 0.0246, "step": 153510 }, { "epoch": 36.83, "learning_rate": 5.959603853937957e-05, "loss": 0.0219, "step": 153520 }, { "epoch": 36.84, "learning_rate": 5.9591634947595606e-05, "loss": 0.0212, "step": 153530 }, { "epoch": 36.84, "learning_rate": 5.958723127856888e-05, "loss": 0.0238, "step": 153540 }, { "epoch": 36.84, "learning_rate": 5.958282753233486e-05, "loss": 0.0442, "step": 153550 }, { "epoch": 36.84, "learning_rate": 5.9578423708929e-05, "loss": 0.023, "step": 153560 }, { "epoch": 36.85, "learning_rate": 5.957401980838676e-05, "loss": 0.0212, "step": 153570 }, { "epoch": 36.85, "learning_rate": 5.956961583074363e-05, "loss": 0.0228, "step": 153580 }, { "epoch": 36.85, "learning_rate": 5.9565211776035066e-05, "loss": 0.0166, "step": 153590 }, { "epoch": 36.85, "learning_rate": 5.956080764429653e-05, "loss": 0.0293, "step": 153600 }, { "epoch": 36.86, "learning_rate": 5.955640343556349e-05, "loss": 0.0261, "step": 153610 }, { "epoch": 36.86, "learning_rate": 5.955199914987142e-05, "loss": 0.0349, "step": 153620 }, { "epoch": 36.86, "learning_rate": 5.954759478725578e-05, "loss": 0.0189, "step": 153630 }, { "epoch": 36.86, "learning_rate": 5.954319034775202e-05, "loss": 0.0134, "step": 153640 }, { "epoch": 36.86, "learning_rate": 5.953878583139565e-05, "loss": 0.0197, "step": 153650 }, { "epoch": 36.87, "learning_rate": 5.953438123822211e-05, "loss": 0.0205, "step": 153660 }, { "epoch": 36.87, "learning_rate": 5.9529976568266885e-05, "loss": 0.0192, "step": 153670 }, { "epoch": 36.87, "learning_rate": 5.952557182156545e-05, "loss": 0.0193, "step": 153680 }, { "epoch": 36.87, "learning_rate": 5.952116699815326e-05, "loss": 0.0181, "step": 153690 }, { "epoch": 36.88, "learning_rate": 5.951676209806582e-05, "loss": 0.0185, "step": 153700 }, { "epoch": 36.88, "learning_rate": 5.951235712133856e-05, "loss": 0.0313, "step": 153710 }, { "epoch": 36.88, "learning_rate": 5.9507952068006976e-05, "loss": 0.0149, "step": 153720 }, { "epoch": 36.88, "learning_rate": 5.950354693810655e-05, "loss": 0.0221, "step": 153730 }, { "epoch": 36.88, "learning_rate": 5.949914173167274e-05, "loss": 0.0128, "step": 153740 }, { "epoch": 36.89, "learning_rate": 5.949473644874103e-05, "loss": 0.0527, "step": 153750 }, { "epoch": 36.89, "learning_rate": 5.94903310893469e-05, "loss": 0.038, "step": 153760 }, { "epoch": 36.89, "learning_rate": 5.948592565352582e-05, "loss": 0.0189, "step": 153770 }, { "epoch": 36.89, "learning_rate": 5.9481520141313276e-05, "loss": 0.0201, "step": 153780 }, { "epoch": 36.9, "learning_rate": 5.947711455274474e-05, "loss": 0.0179, "step": 153790 }, { "epoch": 36.9, "learning_rate": 5.94727088878557e-05, "loss": 0.0178, "step": 153800 }, { "epoch": 36.9, "learning_rate": 5.946830314668161e-05, "loss": 0.0337, "step": 153810 }, { "epoch": 36.9, "learning_rate": 5.946389732925799e-05, "loss": 0.0303, "step": 153820 }, { "epoch": 36.91, "learning_rate": 5.9459491435620274e-05, "loss": 0.0135, "step": 153830 }, { "epoch": 36.91, "learning_rate": 5.9455085465803975e-05, "loss": 0.0459, "step": 153840 }, { "epoch": 36.91, "learning_rate": 5.945067941984457e-05, "loss": 0.0347, "step": 153850 }, { "epoch": 36.91, "learning_rate": 5.944627329777754e-05, "loss": 0.0336, "step": 153860 }, { "epoch": 36.91, "learning_rate": 5.944186709963837e-05, "loss": 0.0183, "step": 153870 }, { "epoch": 36.92, "learning_rate": 5.943746082546254e-05, "loss": 0.0343, "step": 153880 }, { "epoch": 36.92, "learning_rate": 5.9433054475285534e-05, "loss": 0.0153, "step": 153890 }, { "epoch": 36.92, "learning_rate": 5.942864804914283e-05, "loss": 0.0168, "step": 153900 }, { "epoch": 36.92, "learning_rate": 5.9424241547069936e-05, "loss": 0.0184, "step": 153910 }, { "epoch": 36.93, "learning_rate": 5.941983496910232e-05, "loss": 0.0191, "step": 153920 }, { "epoch": 36.93, "learning_rate": 5.9415428315275465e-05, "loss": 0.0212, "step": 153930 }, { "epoch": 36.93, "learning_rate": 5.941102158562487e-05, "loss": 0.0189, "step": 153940 }, { "epoch": 36.93, "learning_rate": 5.940661478018602e-05, "loss": 0.027, "step": 153950 }, { "epoch": 36.94, "learning_rate": 5.940220789899439e-05, "loss": 0.0282, "step": 153960 }, { "epoch": 36.94, "learning_rate": 5.939780094208549e-05, "loss": 0.0364, "step": 153970 }, { "epoch": 36.94, "learning_rate": 5.939339390949481e-05, "loss": 0.0164, "step": 153980 }, { "epoch": 36.94, "learning_rate": 5.938898680125783e-05, "loss": 0.0139, "step": 153990 }, { "epoch": 36.94, "learning_rate": 5.9384579617410043e-05, "loss": 0.0242, "step": 154000 }, { "epoch": 36.95, "learning_rate": 5.9380172357986916e-05, "loss": 0.02, "step": 154010 }, { "epoch": 36.95, "learning_rate": 5.9375765023024e-05, "loss": 0.0181, "step": 154020 }, { "epoch": 36.95, "learning_rate": 5.9371357612556746e-05, "loss": 0.0239, "step": 154030 }, { "epoch": 37.0, "learning_rate": 5.9366950126620644e-05, "loss": 0.0204, "step": 154040 }, { "epoch": 37.0, "learning_rate": 5.936254256525121e-05, "loss": 0.023, "step": 154050 }, { "epoch": 37.01, "learning_rate": 5.935813492848392e-05, "loss": 0.0128, "step": 154060 }, { "epoch": 37.01, "learning_rate": 5.935372721635428e-05, "loss": 0.0244, "step": 154070 }, { "epoch": 37.01, "learning_rate": 5.934931942889778e-05, "loss": 0.0285, "step": 154080 }, { "epoch": 37.01, "learning_rate": 5.934491156614993e-05, "loss": 0.0164, "step": 154090 }, { "epoch": 37.02, "learning_rate": 5.9340503628146203e-05, "loss": 0.0173, "step": 154100 }, { "epoch": 37.02, "learning_rate": 5.9336095614922124e-05, "loss": 0.0195, "step": 154110 }, { "epoch": 37.02, "learning_rate": 5.933168752651318e-05, "loss": 0.0266, "step": 154120 }, { "epoch": 37.02, "learning_rate": 5.932727936295486e-05, "loss": 0.0281, "step": 154130 }, { "epoch": 37.02, "learning_rate": 5.932287112428267e-05, "loss": 0.0117, "step": 154140 }, { "epoch": 37.03, "learning_rate": 5.93184628105321e-05, "loss": 0.0141, "step": 154150 }, { "epoch": 37.03, "learning_rate": 5.931405442173868e-05, "loss": 0.0257, "step": 154160 }, { "epoch": 37.03, "learning_rate": 5.93096459579379e-05, "loss": 0.0138, "step": 154170 }, { "epoch": 37.03, "learning_rate": 5.930523741916525e-05, "loss": 0.02, "step": 154180 }, { "epoch": 37.04, "learning_rate": 5.930082880545624e-05, "loss": 0.0218, "step": 154190 }, { "epoch": 37.04, "learning_rate": 5.929642011684635e-05, "loss": 0.0185, "step": 154200 }, { "epoch": 37.04, "learning_rate": 5.929201135337114e-05, "loss": 0.0099, "step": 154210 }, { "epoch": 37.04, "learning_rate": 5.9287602515066055e-05, "loss": 0.0189, "step": 154220 }, { "epoch": 37.05, "learning_rate": 5.928319360196663e-05, "loss": 0.0165, "step": 154230 }, { "epoch": 37.05, "learning_rate": 5.9278784614108375e-05, "loss": 0.0229, "step": 154240 }, { "epoch": 37.05, "learning_rate": 5.9274375551526775e-05, "loss": 0.027, "step": 154250 }, { "epoch": 37.05, "learning_rate": 5.926996641425735e-05, "loss": 0.0235, "step": 154260 }, { "epoch": 37.05, "learning_rate": 5.92655572023356e-05, "loss": 0.0177, "step": 154270 }, { "epoch": 37.06, "learning_rate": 5.9261147915797057e-05, "loss": 0.0295, "step": 154280 }, { "epoch": 37.06, "learning_rate": 5.9256738554677196e-05, "loss": 0.0197, "step": 154290 }, { "epoch": 37.06, "learning_rate": 5.925232911901154e-05, "loss": 0.0177, "step": 154300 }, { "epoch": 37.06, "learning_rate": 5.924791960883561e-05, "loss": 0.0206, "step": 154310 }, { "epoch": 37.07, "learning_rate": 5.924351002418489e-05, "loss": 0.0101, "step": 154320 }, { "epoch": 37.07, "learning_rate": 5.923910036509494e-05, "loss": 0.0217, "step": 154330 }, { "epoch": 37.07, "learning_rate": 5.9234690631601206e-05, "loss": 0.0184, "step": 154340 }, { "epoch": 37.07, "learning_rate": 5.923028082373925e-05, "loss": 0.0236, "step": 154350 }, { "epoch": 37.08, "learning_rate": 5.922587094154457e-05, "loss": 0.0256, "step": 154360 }, { "epoch": 37.08, "learning_rate": 5.922146098505267e-05, "loss": 0.0236, "step": 154370 }, { "epoch": 37.08, "learning_rate": 5.921705095429908e-05, "loss": 0.0265, "step": 154380 }, { "epoch": 37.08, "learning_rate": 5.921264084931929e-05, "loss": 0.0175, "step": 154390 }, { "epoch": 37.08, "learning_rate": 5.920823067014885e-05, "loss": 0.0177, "step": 154400 }, { "epoch": 37.09, "learning_rate": 5.920382041682324e-05, "loss": 0.0119, "step": 154410 }, { "epoch": 37.09, "learning_rate": 5.9199410089378004e-05, "loss": 0.0107, "step": 154420 }, { "epoch": 37.09, "learning_rate": 5.919499968784865e-05, "loss": 0.025, "step": 154430 }, { "epoch": 37.09, "learning_rate": 5.919058921227068e-05, "loss": 0.0164, "step": 154440 }, { "epoch": 37.1, "learning_rate": 5.918617866267965e-05, "loss": 0.0143, "step": 154450 }, { "epoch": 37.1, "learning_rate": 5.918176803911103e-05, "loss": 0.0167, "step": 154460 }, { "epoch": 37.1, "learning_rate": 5.9177357341600394e-05, "loss": 0.035, "step": 154470 }, { "epoch": 37.1, "learning_rate": 5.9172946570183206e-05, "loss": 0.0178, "step": 154480 }, { "epoch": 37.1, "learning_rate": 5.916853572489502e-05, "loss": 0.0215, "step": 154490 }, { "epoch": 37.11, "learning_rate": 5.916412480577136e-05, "loss": 0.027, "step": 154500 }, { "epoch": 37.11, "learning_rate": 5.915971381284772e-05, "loss": 0.0234, "step": 154510 }, { "epoch": 37.11, "learning_rate": 5.9155302746159656e-05, "loss": 0.0249, "step": 154520 }, { "epoch": 37.11, "learning_rate": 5.915089160574266e-05, "loss": 0.0108, "step": 154530 }, { "epoch": 37.12, "learning_rate": 5.914648039163229e-05, "loss": 0.0101, "step": 154540 }, { "epoch": 37.12, "learning_rate": 5.9142069103864026e-05, "loss": 0.0256, "step": 154550 }, { "epoch": 37.12, "learning_rate": 5.913765774247343e-05, "loss": 0.0202, "step": 154560 }, { "epoch": 37.12, "learning_rate": 5.9133246307496024e-05, "loss": 0.019, "step": 154570 }, { "epoch": 37.13, "learning_rate": 5.912883479896731e-05, "loss": 0.017, "step": 154580 }, { "epoch": 37.13, "learning_rate": 5.912442321692284e-05, "loss": 0.0323, "step": 154590 }, { "epoch": 37.13, "learning_rate": 5.912001156139812e-05, "loss": 0.0263, "step": 154600 }, { "epoch": 37.13, "learning_rate": 5.91155998324287e-05, "loss": 0.0137, "step": 154610 }, { "epoch": 37.13, "learning_rate": 5.911118803005009e-05, "loss": 0.0237, "step": 154620 }, { "epoch": 37.14, "learning_rate": 5.9106776154297814e-05, "loss": 0.0209, "step": 154630 }, { "epoch": 37.14, "learning_rate": 5.910236420520744e-05, "loss": 0.0206, "step": 154640 }, { "epoch": 37.14, "learning_rate": 5.909795218281444e-05, "loss": 0.0136, "step": 154650 }, { "epoch": 37.14, "learning_rate": 5.90935400871544e-05, "loss": 0.0163, "step": 154660 }, { "epoch": 37.15, "learning_rate": 5.908912791826281e-05, "loss": 0.0088, "step": 154670 }, { "epoch": 37.15, "learning_rate": 5.9084715676175216e-05, "loss": 0.0147, "step": 154680 }, { "epoch": 37.15, "learning_rate": 5.908030336092716e-05, "loss": 0.0189, "step": 154690 }, { "epoch": 37.15, "learning_rate": 5.907589097255416e-05, "loss": 0.0214, "step": 154700 }, { "epoch": 37.16, "learning_rate": 5.9071478511091784e-05, "loss": 0.0172, "step": 154710 }, { "epoch": 37.16, "learning_rate": 5.9067065976575496e-05, "loss": 0.0244, "step": 154720 }, { "epoch": 37.16, "learning_rate": 5.9062653369040896e-05, "loss": 0.0247, "step": 154730 }, { "epoch": 37.16, "learning_rate": 5.9058240688523504e-05, "loss": 0.0433, "step": 154740 }, { "epoch": 37.16, "learning_rate": 5.9053827935058835e-05, "loss": 0.0149, "step": 154750 }, { "epoch": 37.17, "learning_rate": 5.904941510868246e-05, "loss": 0.026, "step": 154760 }, { "epoch": 37.17, "learning_rate": 5.904500220942988e-05, "loss": 0.0261, "step": 154770 }, { "epoch": 37.17, "learning_rate": 5.904058923733666e-05, "loss": 0.0157, "step": 154780 }, { "epoch": 37.17, "learning_rate": 5.9036176192438306e-05, "loss": 0.0405, "step": 154790 }, { "epoch": 37.18, "learning_rate": 5.9031763074770395e-05, "loss": 0.0218, "step": 154800 }, { "epoch": 37.18, "learning_rate": 5.902734988436844e-05, "loss": 0.0146, "step": 154810 }, { "epoch": 37.18, "learning_rate": 5.902293662126799e-05, "loss": 0.0225, "step": 154820 }, { "epoch": 37.18, "learning_rate": 5.90185232855046e-05, "loss": 0.0193, "step": 154830 }, { "epoch": 37.18, "learning_rate": 5.901410987711378e-05, "loss": 0.0276, "step": 154840 }, { "epoch": 37.19, "learning_rate": 5.90096963961311e-05, "loss": 0.0425, "step": 154850 }, { "epoch": 37.19, "learning_rate": 5.900528284259208e-05, "loss": 0.0201, "step": 154860 }, { "epoch": 37.19, "learning_rate": 5.9000869216532285e-05, "loss": 0.0181, "step": 154870 }, { "epoch": 37.19, "learning_rate": 5.899645551798725e-05, "loss": 0.021, "step": 154880 }, { "epoch": 37.2, "learning_rate": 5.89920417469925e-05, "loss": 0.0226, "step": 154890 }, { "epoch": 37.2, "learning_rate": 5.898762790358361e-05, "loss": 0.0254, "step": 154900 }, { "epoch": 37.2, "learning_rate": 5.8983213987796105e-05, "loss": 0.0139, "step": 154910 }, { "epoch": 37.2, "learning_rate": 5.8978799999665536e-05, "loss": 0.0161, "step": 154920 }, { "epoch": 37.21, "learning_rate": 5.8974385939227464e-05, "loss": 0.0255, "step": 154930 }, { "epoch": 37.21, "learning_rate": 5.8969971806517396e-05, "loss": 0.0306, "step": 154940 }, { "epoch": 37.21, "learning_rate": 5.896555760157094e-05, "loss": 0.0224, "step": 154950 }, { "epoch": 37.21, "learning_rate": 5.8961143324423585e-05, "loss": 0.0302, "step": 154960 }, { "epoch": 37.21, "learning_rate": 5.895672897511092e-05, "loss": 0.0213, "step": 154970 }, { "epoch": 37.22, "learning_rate": 5.895231455366847e-05, "loss": 0.0265, "step": 154980 }, { "epoch": 37.22, "learning_rate": 5.894790006013181e-05, "loss": 0.0234, "step": 154990 }, { "epoch": 37.22, "learning_rate": 5.8943485494536474e-05, "loss": 0.0255, "step": 155000 }, { "epoch": 37.22, "learning_rate": 5.8939070856918e-05, "loss": 0.0189, "step": 155010 }, { "epoch": 37.23, "learning_rate": 5.8934656147311975e-05, "loss": 0.0432, "step": 155020 }, { "epoch": 37.23, "learning_rate": 5.89302413657539e-05, "loss": 0.031, "step": 155030 }, { "epoch": 37.23, "learning_rate": 5.892582651227938e-05, "loss": 0.0529, "step": 155040 }, { "epoch": 37.23, "learning_rate": 5.892141158692395e-05, "loss": 0.0128, "step": 155050 }, { "epoch": 37.24, "learning_rate": 5.891699658972315e-05, "loss": 0.0223, "step": 155060 }, { "epoch": 37.24, "learning_rate": 5.891258152071255e-05, "loss": 0.0267, "step": 155070 }, { "epoch": 37.24, "learning_rate": 5.890816637992769e-05, "loss": 0.018, "step": 155080 }, { "epoch": 37.24, "learning_rate": 5.8903751167404166e-05, "loss": 0.0168, "step": 155090 }, { "epoch": 37.24, "learning_rate": 5.8899335883177465e-05, "loss": 0.0248, "step": 155100 }, { "epoch": 37.25, "learning_rate": 5.8894920527283206e-05, "loss": 0.018, "step": 155110 }, { "epoch": 37.25, "learning_rate": 5.889050509975692e-05, "loss": 0.0168, "step": 155120 }, { "epoch": 37.25, "learning_rate": 5.8886089600634175e-05, "loss": 0.0162, "step": 155130 }, { "epoch": 37.25, "learning_rate": 5.888167402995052e-05, "loss": 0.011, "step": 155140 }, { "epoch": 37.26, "learning_rate": 5.8877258387741507e-05, "loss": 0.0216, "step": 155150 }, { "epoch": 37.26, "learning_rate": 5.8872842674042715e-05, "loss": 0.0154, "step": 155160 }, { "epoch": 37.26, "learning_rate": 5.8868426888889695e-05, "loss": 0.0212, "step": 155170 }, { "epoch": 37.26, "learning_rate": 5.886401103231802e-05, "loss": 0.0111, "step": 155180 }, { "epoch": 37.26, "learning_rate": 5.885959510436323e-05, "loss": 0.0112, "step": 155190 }, { "epoch": 37.27, "learning_rate": 5.88551791050609e-05, "loss": 0.0178, "step": 155200 }, { "epoch": 37.27, "learning_rate": 5.885076303444659e-05, "loss": 0.0232, "step": 155210 }, { "epoch": 37.27, "learning_rate": 5.884634689255585e-05, "loss": 0.0265, "step": 155220 }, { "epoch": 37.27, "learning_rate": 5.8841930679424275e-05, "loss": 0.0261, "step": 155230 }, { "epoch": 37.28, "learning_rate": 5.8837514395087404e-05, "loss": 0.021, "step": 155240 }, { "epoch": 37.28, "learning_rate": 5.883309803958081e-05, "loss": 0.0234, "step": 155250 }, { "epoch": 37.28, "learning_rate": 5.882868161294006e-05, "loss": 0.0236, "step": 155260 }, { "epoch": 37.28, "learning_rate": 5.882426511520072e-05, "loss": 0.0275, "step": 155270 }, { "epoch": 37.29, "learning_rate": 5.881984854639835e-05, "loss": 0.0175, "step": 155280 }, { "epoch": 37.29, "learning_rate": 5.881543190656852e-05, "loss": 0.0229, "step": 155290 }, { "epoch": 37.29, "learning_rate": 5.881101519574681e-05, "loss": 0.0247, "step": 155300 }, { "epoch": 37.29, "learning_rate": 5.8806598413968774e-05, "loss": 0.0169, "step": 155310 }, { "epoch": 37.29, "learning_rate": 5.880218156126999e-05, "loss": 0.0249, "step": 155320 }, { "epoch": 37.3, "learning_rate": 5.879776463768601e-05, "loss": 0.0158, "step": 155330 }, { "epoch": 37.3, "learning_rate": 5.879334764325242e-05, "loss": 0.0553, "step": 155340 }, { "epoch": 37.3, "learning_rate": 5.8788930578004784e-05, "loss": 0.0227, "step": 155350 }, { "epoch": 37.3, "learning_rate": 5.878451344197868e-05, "loss": 0.0153, "step": 155360 }, { "epoch": 37.31, "learning_rate": 5.878009623520969e-05, "loss": 0.016, "step": 155370 }, { "epoch": 37.31, "learning_rate": 5.877567895773336e-05, "loss": 0.0147, "step": 155380 }, { "epoch": 37.31, "learning_rate": 5.877126160958528e-05, "loss": 0.0135, "step": 155390 }, { "epoch": 37.31, "learning_rate": 5.876684419080101e-05, "loss": 0.008, "step": 155400 }, { "epoch": 37.32, "learning_rate": 5.876242670141614e-05, "loss": 0.0161, "step": 155410 }, { "epoch": 37.32, "learning_rate": 5.875800914146624e-05, "loss": 0.0121, "step": 155420 }, { "epoch": 37.32, "learning_rate": 5.8753591510986884e-05, "loss": 0.0223, "step": 155430 }, { "epoch": 37.32, "learning_rate": 5.8749173810013646e-05, "loss": 0.0158, "step": 155440 }, { "epoch": 37.32, "learning_rate": 5.874475603858211e-05, "loss": 0.0197, "step": 155450 }, { "epoch": 37.33, "learning_rate": 5.874033819672784e-05, "loss": 0.0192, "step": 155460 }, { "epoch": 37.33, "learning_rate": 5.87359202844864e-05, "loss": 0.023, "step": 155470 }, { "epoch": 37.33, "learning_rate": 5.8731502301893415e-05, "loss": 0.015, "step": 155480 }, { "epoch": 37.33, "learning_rate": 5.872708424898443e-05, "loss": 0.012, "step": 155490 }, { "epoch": 37.34, "learning_rate": 5.8722666125795024e-05, "loss": 0.0244, "step": 155500 }, { "epoch": 37.34, "learning_rate": 5.8718247932360795e-05, "loss": 0.016, "step": 155510 }, { "epoch": 37.34, "learning_rate": 5.871382966871729e-05, "loss": 0.0189, "step": 155520 }, { "epoch": 37.34, "learning_rate": 5.8709411334900145e-05, "loss": 0.0147, "step": 155530 }, { "epoch": 37.34, "learning_rate": 5.870499293094488e-05, "loss": 0.0247, "step": 155540 }, { "epoch": 37.35, "learning_rate": 5.870057445688711e-05, "loss": 0.014, "step": 155550 }, { "epoch": 37.35, "learning_rate": 5.869615591276242e-05, "loss": 0.0229, "step": 155560 }, { "epoch": 37.35, "learning_rate": 5.869173729860639e-05, "loss": 0.0116, "step": 155570 }, { "epoch": 37.35, "learning_rate": 5.868731861445459e-05, "loss": 0.0155, "step": 155580 }, { "epoch": 37.36, "learning_rate": 5.868289986034261e-05, "loss": 0.0198, "step": 155590 }, { "epoch": 37.36, "learning_rate": 5.867848103630605e-05, "loss": 0.0217, "step": 155600 }, { "epoch": 37.36, "learning_rate": 5.867406214238048e-05, "loss": 0.0263, "step": 155610 }, { "epoch": 37.36, "learning_rate": 5.866964317860149e-05, "loss": 0.0439, "step": 155620 }, { "epoch": 37.37, "learning_rate": 5.866522414500466e-05, "loss": 0.0175, "step": 155630 }, { "epoch": 37.37, "learning_rate": 5.86608050416256e-05, "loss": 0.0265, "step": 155640 }, { "epoch": 37.37, "learning_rate": 5.8656385868499874e-05, "loss": 0.0293, "step": 155650 }, { "epoch": 37.37, "learning_rate": 5.8651966625663055e-05, "loss": 0.0095, "step": 155660 }, { "epoch": 37.37, "learning_rate": 5.864754731315078e-05, "loss": 0.025, "step": 155670 }, { "epoch": 37.38, "learning_rate": 5.8643127930998607e-05, "loss": 0.0161, "step": 155680 }, { "epoch": 37.38, "learning_rate": 5.8638708479242134e-05, "loss": 0.0166, "step": 155690 }, { "epoch": 37.38, "learning_rate": 5.863428895791695e-05, "loss": 0.039, "step": 155700 }, { "epoch": 37.38, "learning_rate": 5.862986936705863e-05, "loss": 0.0396, "step": 155710 }, { "epoch": 37.39, "learning_rate": 5.862544970670281e-05, "loss": 0.0145, "step": 155720 }, { "epoch": 37.39, "learning_rate": 5.862102997688502e-05, "loss": 0.0166, "step": 155730 }, { "epoch": 37.39, "learning_rate": 5.861661017764089e-05, "loss": 0.0148, "step": 155740 }, { "epoch": 37.39, "learning_rate": 5.861219030900603e-05, "loss": 0.0199, "step": 155750 }, { "epoch": 37.4, "learning_rate": 5.8607770371016e-05, "loss": 0.0332, "step": 155760 }, { "epoch": 37.4, "learning_rate": 5.860335036370641e-05, "loss": 0.0198, "step": 155770 }, { "epoch": 37.4, "learning_rate": 5.8598930287112844e-05, "loss": 0.0223, "step": 155780 }, { "epoch": 37.4, "learning_rate": 5.8594510141270916e-05, "loss": 0.0158, "step": 155790 }, { "epoch": 37.4, "learning_rate": 5.85900899262162e-05, "loss": 0.0195, "step": 155800 }, { "epoch": 37.41, "learning_rate": 5.858566964198431e-05, "loss": 0.024, "step": 155810 }, { "epoch": 37.41, "learning_rate": 5.858124928861084e-05, "loss": 0.0169, "step": 155820 }, { "epoch": 37.41, "learning_rate": 5.857682886613137e-05, "loss": 0.0124, "step": 155830 }, { "epoch": 37.41, "learning_rate": 5.857240837458155e-05, "loss": 0.0236, "step": 155840 }, { "epoch": 37.42, "learning_rate": 5.85679878139969e-05, "loss": 0.0137, "step": 155850 }, { "epoch": 37.42, "learning_rate": 5.856356718441309e-05, "loss": 0.0288, "step": 155860 }, { "epoch": 37.42, "learning_rate": 5.8559146485865667e-05, "loss": 0.0165, "step": 155870 }, { "epoch": 37.42, "learning_rate": 5.855472571839027e-05, "loss": 0.0114, "step": 155880 }, { "epoch": 37.42, "learning_rate": 5.855030488202249e-05, "loss": 0.0509, "step": 155890 }, { "epoch": 37.43, "learning_rate": 5.85458839767979e-05, "loss": 0.0148, "step": 155900 }, { "epoch": 37.43, "learning_rate": 5.854146300275216e-05, "loss": 0.0095, "step": 155910 }, { "epoch": 37.43, "learning_rate": 5.8537041959920814e-05, "loss": 0.0136, "step": 155920 }, { "epoch": 37.43, "learning_rate": 5.85326208483395e-05, "loss": 0.0244, "step": 155930 }, { "epoch": 37.44, "learning_rate": 5.852819966804382e-05, "loss": 0.019, "step": 155940 }, { "epoch": 37.44, "learning_rate": 5.8523778419069344e-05, "loss": 0.0344, "step": 155950 }, { "epoch": 37.44, "learning_rate": 5.8519357101451735e-05, "loss": 0.0245, "step": 155960 }, { "epoch": 37.44, "learning_rate": 5.851493571522655e-05, "loss": 0.0174, "step": 155970 }, { "epoch": 37.45, "learning_rate": 5.851051426042943e-05, "loss": 0.0175, "step": 155980 }, { "epoch": 37.45, "learning_rate": 5.850609273709594e-05, "loss": 0.0129, "step": 155990 }, { "epoch": 37.45, "learning_rate": 5.8501671145261715e-05, "loss": 0.0194, "step": 156000 }, { "epoch": 37.45, "learning_rate": 5.849724948496237e-05, "loss": 0.0166, "step": 156010 }, { "epoch": 37.45, "learning_rate": 5.849282775623349e-05, "loss": 0.0489, "step": 156020 }, { "epoch": 37.46, "learning_rate": 5.8488405959110715e-05, "loss": 0.0105, "step": 156030 }, { "epoch": 37.46, "learning_rate": 5.8483984093629606e-05, "loss": 0.0145, "step": 156040 }, { "epoch": 37.46, "learning_rate": 5.847956215982584e-05, "loss": 0.0407, "step": 156050 }, { "epoch": 37.46, "learning_rate": 5.847514015773495e-05, "loss": 0.0182, "step": 156060 }, { "epoch": 37.47, "learning_rate": 5.847071808739261e-05, "loss": 0.0093, "step": 156070 }, { "epoch": 37.47, "learning_rate": 5.84662959488344e-05, "loss": 0.022, "step": 156080 }, { "epoch": 37.47, "learning_rate": 5.846187374209593e-05, "loss": 0.0269, "step": 156090 }, { "epoch": 37.47, "learning_rate": 5.845745146721284e-05, "loss": 0.0112, "step": 156100 }, { "epoch": 37.48, "learning_rate": 5.845302912422071e-05, "loss": 0.0087, "step": 156110 }, { "epoch": 37.48, "learning_rate": 5.8448606713155186e-05, "loss": 0.0234, "step": 156120 }, { "epoch": 37.48, "learning_rate": 5.8444184234051854e-05, "loss": 0.0309, "step": 156130 }, { "epoch": 37.48, "learning_rate": 5.843976168694634e-05, "loss": 0.0183, "step": 156140 }, { "epoch": 37.48, "learning_rate": 5.843533907187428e-05, "loss": 0.019, "step": 156150 }, { "epoch": 37.49, "learning_rate": 5.843091638887125e-05, "loss": 0.0399, "step": 156160 }, { "epoch": 37.49, "learning_rate": 5.84264936379729e-05, "loss": 0.0136, "step": 156170 }, { "epoch": 37.49, "learning_rate": 5.8422070819214815e-05, "loss": 0.0237, "step": 156180 }, { "epoch": 37.49, "learning_rate": 5.841764793263264e-05, "loss": 0.0167, "step": 156190 }, { "epoch": 37.5, "learning_rate": 5.8413224978261984e-05, "loss": 0.0236, "step": 156200 }, { "epoch": 37.5, "learning_rate": 5.840880195613846e-05, "loss": 0.0206, "step": 156210 }, { "epoch": 37.5, "learning_rate": 5.8404378866297715e-05, "loss": 0.0156, "step": 156220 }, { "epoch": 37.5, "learning_rate": 5.8399955708775324e-05, "loss": 0.0165, "step": 156230 }, { "epoch": 37.5, "learning_rate": 5.839553248360693e-05, "loss": 0.0153, "step": 156240 }, { "epoch": 37.51, "learning_rate": 5.839110919082816e-05, "loss": 0.0417, "step": 156250 }, { "epoch": 37.51, "learning_rate": 5.838668583047463e-05, "loss": 0.0172, "step": 156260 }, { "epoch": 37.51, "learning_rate": 5.838226240258197e-05, "loss": 0.0162, "step": 156270 }, { "epoch": 37.51, "learning_rate": 5.837783890718578e-05, "loss": 0.0305, "step": 156280 }, { "epoch": 37.52, "learning_rate": 5.837341534432171e-05, "loss": 0.0293, "step": 156290 }, { "epoch": 37.52, "learning_rate": 5.8368991714025354e-05, "loss": 0.0162, "step": 156300 }, { "epoch": 37.52, "learning_rate": 5.836456801633235e-05, "loss": 0.0142, "step": 156310 }, { "epoch": 37.52, "learning_rate": 5.8360144251278345e-05, "loss": 0.0143, "step": 156320 }, { "epoch": 37.53, "learning_rate": 5.835572041889893e-05, "loss": 0.02, "step": 156330 }, { "epoch": 37.53, "learning_rate": 5.835129651922976e-05, "loss": 0.0288, "step": 156340 }, { "epoch": 37.53, "learning_rate": 5.834687255230642e-05, "loss": 0.0133, "step": 156350 }, { "epoch": 37.53, "learning_rate": 5.834244851816458e-05, "loss": 0.0209, "step": 156360 }, { "epoch": 37.53, "learning_rate": 5.833802441683986e-05, "loss": 0.0229, "step": 156370 }, { "epoch": 37.54, "learning_rate": 5.833360024836786e-05, "loss": 0.0254, "step": 156380 }, { "epoch": 37.54, "learning_rate": 5.832917601278424e-05, "loss": 0.0216, "step": 156390 }, { "epoch": 37.54, "learning_rate": 5.832475171012459e-05, "loss": 0.0253, "step": 156400 }, { "epoch": 37.54, "learning_rate": 5.832032734042459e-05, "loss": 0.0136, "step": 156410 }, { "epoch": 37.55, "learning_rate": 5.831590290371984e-05, "loss": 0.0183, "step": 156420 }, { "epoch": 37.55, "learning_rate": 5.831147840004598e-05, "loss": 0.0218, "step": 156430 }, { "epoch": 37.55, "learning_rate": 5.830705382943863e-05, "loss": 0.0242, "step": 156440 }, { "epoch": 37.55, "learning_rate": 5.8302629191933437e-05, "loss": 0.0187, "step": 156450 }, { "epoch": 37.56, "learning_rate": 5.829820448756602e-05, "loss": 0.0282, "step": 156460 }, { "epoch": 37.56, "learning_rate": 5.8293779716372e-05, "loss": 0.0213, "step": 156470 }, { "epoch": 37.56, "learning_rate": 5.828935487838705e-05, "loss": 0.0274, "step": 156480 }, { "epoch": 37.56, "learning_rate": 5.8284929973646776e-05, "loss": 0.0091, "step": 156490 }, { "epoch": 37.56, "learning_rate": 5.8280505002186815e-05, "loss": 0.0138, "step": 156500 }, { "epoch": 37.57, "learning_rate": 5.827607996404281e-05, "loss": 0.0147, "step": 156510 }, { "epoch": 37.57, "learning_rate": 5.827165485925038e-05, "loss": 0.0304, "step": 156520 }, { "epoch": 37.57, "learning_rate": 5.826722968784517e-05, "loss": 0.0147, "step": 156530 }, { "epoch": 37.57, "learning_rate": 5.8262804449862815e-05, "loss": 0.0189, "step": 156540 }, { "epoch": 37.58, "learning_rate": 5.825837914533897e-05, "loss": 0.0164, "step": 156550 }, { "epoch": 37.58, "learning_rate": 5.8253953774309246e-05, "loss": 0.0245, "step": 156560 }, { "epoch": 37.58, "learning_rate": 5.82495283368093e-05, "loss": 0.0225, "step": 156570 }, { "epoch": 37.58, "learning_rate": 5.8245102832874766e-05, "loss": 0.0284, "step": 156580 }, { "epoch": 37.58, "learning_rate": 5.824067726254127e-05, "loss": 0.0256, "step": 156590 }, { "epoch": 37.59, "learning_rate": 5.823625162584447e-05, "loss": 0.0365, "step": 156600 }, { "epoch": 37.59, "learning_rate": 5.8231825922819996e-05, "loss": 0.0185, "step": 156610 }, { "epoch": 37.59, "learning_rate": 5.822740015350349e-05, "loss": 0.0364, "step": 156620 }, { "epoch": 37.59, "learning_rate": 5.82229743179306e-05, "loss": 0.0202, "step": 156630 }, { "epoch": 37.6, "learning_rate": 5.8218548416136956e-05, "loss": 0.0212, "step": 156640 }, { "epoch": 37.6, "learning_rate": 5.8214122448158216e-05, "loss": 0.028, "step": 156650 }, { "epoch": 37.6, "learning_rate": 5.820969641402999e-05, "loss": 0.0199, "step": 156660 }, { "epoch": 37.6, "learning_rate": 5.8205270313787964e-05, "loss": 0.0406, "step": 156670 }, { "epoch": 37.61, "learning_rate": 5.820084414746777e-05, "loss": 0.0165, "step": 156680 }, { "epoch": 37.61, "learning_rate": 5.819641791510504e-05, "loss": 0.0157, "step": 156690 }, { "epoch": 37.61, "learning_rate": 5.819199161673542e-05, "loss": 0.0172, "step": 156700 }, { "epoch": 37.61, "learning_rate": 5.818756525239457e-05, "loss": 0.0175, "step": 156710 }, { "epoch": 37.61, "learning_rate": 5.818313882211812e-05, "loss": 0.0237, "step": 156720 }, { "epoch": 37.62, "learning_rate": 5.817871232594172e-05, "loss": 0.0132, "step": 156730 }, { "epoch": 37.62, "learning_rate": 5.8174285763901016e-05, "loss": 0.0152, "step": 156740 }, { "epoch": 37.62, "learning_rate": 5.816985913603168e-05, "loss": 0.0213, "step": 156750 }, { "epoch": 37.62, "learning_rate": 5.8165432442369324e-05, "loss": 0.0285, "step": 156760 }, { "epoch": 37.63, "learning_rate": 5.816100568294962e-05, "loss": 0.0223, "step": 156770 }, { "epoch": 37.63, "learning_rate": 5.815657885780821e-05, "loss": 0.0197, "step": 156780 }, { "epoch": 37.63, "learning_rate": 5.815215196698074e-05, "loss": 0.0301, "step": 156790 }, { "epoch": 37.63, "learning_rate": 5.8147725010502864e-05, "loss": 0.0289, "step": 156800 }, { "epoch": 37.64, "learning_rate": 5.814329798841024e-05, "loss": 0.0309, "step": 156810 }, { "epoch": 37.64, "learning_rate": 5.813887090073851e-05, "loss": 0.0298, "step": 156820 }, { "epoch": 37.64, "learning_rate": 5.813444374752333e-05, "loss": 0.0199, "step": 156830 }, { "epoch": 37.64, "learning_rate": 5.8130016528800356e-05, "loss": 0.0591, "step": 156840 }, { "epoch": 37.64, "learning_rate": 5.812558924460523e-05, "loss": 0.0191, "step": 156850 }, { "epoch": 37.65, "learning_rate": 5.812116189497361e-05, "loss": 0.0286, "step": 156860 }, { "epoch": 37.65, "learning_rate": 5.811673447994115e-05, "loss": 0.0181, "step": 156870 }, { "epoch": 37.65, "learning_rate": 5.811230699954352e-05, "loss": 0.0137, "step": 156880 }, { "epoch": 37.65, "learning_rate": 5.810787945381635e-05, "loss": 0.0232, "step": 156890 }, { "epoch": 37.66, "learning_rate": 5.810345184279531e-05, "loss": 0.0308, "step": 156900 }, { "epoch": 37.66, "learning_rate": 5.8099024166516045e-05, "loss": 0.0114, "step": 156910 }, { "epoch": 37.66, "learning_rate": 5.809459642501424e-05, "loss": 0.0352, "step": 156920 }, { "epoch": 37.66, "learning_rate": 5.809016861832553e-05, "loss": 0.0151, "step": 156930 }, { "epoch": 37.66, "learning_rate": 5.8085740746485564e-05, "loss": 0.0211, "step": 156940 }, { "epoch": 37.67, "learning_rate": 5.808131280953001e-05, "loss": 0.0194, "step": 156950 }, { "epoch": 37.67, "learning_rate": 5.8076884807494536e-05, "loss": 0.0158, "step": 156960 }, { "epoch": 37.67, "learning_rate": 5.807245674041479e-05, "loss": 0.0282, "step": 156970 }, { "epoch": 37.67, "learning_rate": 5.806802860832643e-05, "loss": 0.0209, "step": 156980 }, { "epoch": 37.68, "learning_rate": 5.806360041126513e-05, "loss": 0.0251, "step": 156990 }, { "epoch": 37.68, "learning_rate": 5.8059172149266536e-05, "loss": 0.0158, "step": 157000 }, { "epoch": 37.68, "learning_rate": 5.8054743822366334e-05, "loss": 0.0079, "step": 157010 }, { "epoch": 37.68, "learning_rate": 5.805031543060015e-05, "loss": 0.0156, "step": 157020 }, { "epoch": 37.69, "learning_rate": 5.804588697400367e-05, "loss": 0.0296, "step": 157030 }, { "epoch": 37.69, "learning_rate": 5.804145845261255e-05, "loss": 0.0284, "step": 157040 }, { "epoch": 37.69, "learning_rate": 5.8037029866462446e-05, "loss": 0.0366, "step": 157050 }, { "epoch": 37.69, "learning_rate": 5.803260121558904e-05, "loss": 0.0419, "step": 157060 }, { "epoch": 37.69, "learning_rate": 5.8028172500028e-05, "loss": 0.031, "step": 157070 }, { "epoch": 37.7, "learning_rate": 5.802374371981496e-05, "loss": 0.0254, "step": 157080 }, { "epoch": 37.7, "learning_rate": 5.801931487498562e-05, "loss": 0.0231, "step": 157090 }, { "epoch": 37.7, "learning_rate": 5.8014885965575606e-05, "loss": 0.0208, "step": 157100 }, { "epoch": 37.7, "learning_rate": 5.801045699162064e-05, "loss": 0.017, "step": 157110 }, { "epoch": 37.71, "learning_rate": 5.800602795315633e-05, "loss": 0.0336, "step": 157120 }, { "epoch": 37.71, "learning_rate": 5.8001598850218386e-05, "loss": 0.0566, "step": 157130 }, { "epoch": 37.71, "learning_rate": 5.799716968284246e-05, "loss": 0.0153, "step": 157140 }, { "epoch": 37.71, "learning_rate": 5.799274045106422e-05, "loss": 0.0153, "step": 157150 }, { "epoch": 37.72, "learning_rate": 5.7988311154919336e-05, "loss": 0.0516, "step": 157160 }, { "epoch": 37.72, "learning_rate": 5.798388179444347e-05, "loss": 0.0133, "step": 157170 }, { "epoch": 37.72, "learning_rate": 5.7979452369672336e-05, "loss": 0.0218, "step": 157180 }, { "epoch": 37.72, "learning_rate": 5.797502288064154e-05, "loss": 0.0275, "step": 157190 }, { "epoch": 37.72, "learning_rate": 5.797059332738679e-05, "loss": 0.0234, "step": 157200 }, { "epoch": 37.73, "learning_rate": 5.7966163709943754e-05, "loss": 0.0153, "step": 157210 }, { "epoch": 37.73, "learning_rate": 5.796173402834809e-05, "loss": 0.0165, "step": 157220 }, { "epoch": 37.73, "learning_rate": 5.795730428263551e-05, "loss": 0.0267, "step": 157230 }, { "epoch": 37.73, "learning_rate": 5.7952874472841636e-05, "loss": 0.0182, "step": 157240 }, { "epoch": 37.74, "learning_rate": 5.7948444599002174e-05, "loss": 0.0148, "step": 157250 }, { "epoch": 37.74, "learning_rate": 5.794401466115279e-05, "loss": 0.0242, "step": 157260 }, { "epoch": 37.74, "learning_rate": 5.793958465932916e-05, "loss": 0.0286, "step": 157270 }, { "epoch": 37.74, "learning_rate": 5.7935154593566965e-05, "loss": 0.017, "step": 157280 }, { "epoch": 37.74, "learning_rate": 5.7930724463901856e-05, "loss": 0.0225, "step": 157290 }, { "epoch": 37.75, "learning_rate": 5.7926294270369554e-05, "loss": 0.0115, "step": 157300 }, { "epoch": 37.75, "learning_rate": 5.792186401300569e-05, "loss": 0.0154, "step": 157310 }, { "epoch": 37.75, "learning_rate": 5.7917433691845967e-05, "loss": 0.0146, "step": 157320 }, { "epoch": 37.75, "learning_rate": 5.791300330692606e-05, "loss": 0.0083, "step": 157330 }, { "epoch": 37.76, "learning_rate": 5.7908572858281626e-05, "loss": 0.0505, "step": 157340 }, { "epoch": 37.76, "learning_rate": 5.7904142345948396e-05, "loss": 0.0246, "step": 157350 }, { "epoch": 37.76, "learning_rate": 5.7899711769961996e-05, "loss": 0.0141, "step": 157360 }, { "epoch": 37.76, "learning_rate": 5.7895281130358136e-05, "loss": 0.0228, "step": 157370 }, { "epoch": 37.77, "learning_rate": 5.789085042717247e-05, "loss": 0.0181, "step": 157380 }, { "epoch": 37.77, "learning_rate": 5.788641966044072e-05, "loss": 0.0171, "step": 157390 }, { "epoch": 37.77, "learning_rate": 5.788198883019853e-05, "loss": 0.0212, "step": 157400 }, { "epoch": 37.77, "learning_rate": 5.7877557936481583e-05, "loss": 0.025, "step": 157410 }, { "epoch": 37.77, "learning_rate": 5.78731269793256e-05, "loss": 0.0187, "step": 157420 }, { "epoch": 37.78, "learning_rate": 5.786869595876622e-05, "loss": 0.0164, "step": 157430 }, { "epoch": 37.78, "learning_rate": 5.7864264874839144e-05, "loss": 0.0146, "step": 157440 }, { "epoch": 37.78, "learning_rate": 5.785983372758007e-05, "loss": 0.0246, "step": 157450 }, { "epoch": 37.78, "learning_rate": 5.785540251702467e-05, "loss": 0.0154, "step": 157460 }, { "epoch": 37.79, "learning_rate": 5.785097124320863e-05, "loss": 0.0172, "step": 157470 }, { "epoch": 37.79, "learning_rate": 5.784653990616762e-05, "loss": 0.0192, "step": 157480 }, { "epoch": 37.79, "learning_rate": 5.7842108505937355e-05, "loss": 0.024, "step": 157490 }, { "epoch": 37.79, "learning_rate": 5.783767704255349e-05, "loss": 0.0151, "step": 157500 }, { "epoch": 37.8, "learning_rate": 5.783324551605175e-05, "loss": 0.013, "step": 157510 }, { "epoch": 37.8, "learning_rate": 5.78288139264678e-05, "loss": 0.0232, "step": 157520 }, { "epoch": 37.8, "learning_rate": 5.782438227383731e-05, "loss": 0.0265, "step": 157530 }, { "epoch": 37.8, "learning_rate": 5.7819950558196015e-05, "loss": 0.0271, "step": 157540 }, { "epoch": 37.8, "learning_rate": 5.781551877957956e-05, "loss": 0.0264, "step": 157550 }, { "epoch": 37.81, "learning_rate": 5.7811086938023674e-05, "loss": 0.029, "step": 157560 }, { "epoch": 37.81, "learning_rate": 5.7806655033564006e-05, "loss": 0.033, "step": 157570 }, { "epoch": 37.81, "learning_rate": 5.780222306623627e-05, "loss": 0.0211, "step": 157580 }, { "epoch": 37.81, "learning_rate": 5.779779103607616e-05, "loss": 0.014, "step": 157590 }, { "epoch": 37.82, "learning_rate": 5.7793358943119355e-05, "loss": 0.0354, "step": 157600 }, { "epoch": 37.82, "learning_rate": 5.778892678740157e-05, "loss": 0.0267, "step": 157610 }, { "epoch": 37.82, "learning_rate": 5.778449456895847e-05, "loss": 0.0345, "step": 157620 }, { "epoch": 37.82, "learning_rate": 5.778006228782576e-05, "loss": 0.0228, "step": 157630 }, { "epoch": 37.82, "learning_rate": 5.777562994403915e-05, "loss": 0.0111, "step": 157640 }, { "epoch": 37.83, "learning_rate": 5.7771197537634294e-05, "loss": 0.0165, "step": 157650 }, { "epoch": 37.83, "learning_rate": 5.776676506864693e-05, "loss": 0.0245, "step": 157660 }, { "epoch": 37.83, "learning_rate": 5.7762332537112714e-05, "loss": 0.0284, "step": 157670 }, { "epoch": 37.83, "learning_rate": 5.77578999430674e-05, "loss": 0.0182, "step": 157680 }, { "epoch": 37.84, "learning_rate": 5.7753467286546616e-05, "loss": 0.0179, "step": 157690 }, { "epoch": 37.84, "learning_rate": 5.774903456758609e-05, "loss": 0.019, "step": 157700 }, { "epoch": 37.84, "learning_rate": 5.774460178622153e-05, "loss": 0.0157, "step": 157710 }, { "epoch": 37.84, "learning_rate": 5.774016894248861e-05, "loss": 0.0196, "step": 157720 }, { "epoch": 37.85, "learning_rate": 5.773573603642306e-05, "loss": 0.0174, "step": 157730 }, { "epoch": 37.85, "learning_rate": 5.7731303068060536e-05, "loss": 0.0223, "step": 157740 }, { "epoch": 37.85, "learning_rate": 5.7726870037436785e-05, "loss": 0.0178, "step": 157750 }, { "epoch": 37.85, "learning_rate": 5.772243694458748e-05, "loss": 0.0181, "step": 157760 }, { "epoch": 37.85, "learning_rate": 5.7718003789548304e-05, "loss": 0.0312, "step": 157770 }, { "epoch": 37.86, "learning_rate": 5.7713570572355e-05, "loss": 0.0176, "step": 157780 }, { "epoch": 37.86, "learning_rate": 5.7709137293043226e-05, "loss": 0.0292, "step": 157790 }, { "epoch": 37.86, "learning_rate": 5.770470395164873e-05, "loss": 0.0225, "step": 157800 }, { "epoch": 37.86, "learning_rate": 5.770027054820717e-05, "loss": 0.019, "step": 157810 }, { "epoch": 37.87, "learning_rate": 5.7695837082754264e-05, "loss": 0.0269, "step": 157820 }, { "epoch": 37.87, "learning_rate": 5.769140355532574e-05, "loss": 0.0143, "step": 157830 }, { "epoch": 37.87, "learning_rate": 5.768696996595726e-05, "loss": 0.0169, "step": 157840 }, { "epoch": 37.87, "learning_rate": 5.7682536314684565e-05, "loss": 0.0269, "step": 157850 }, { "epoch": 37.88, "learning_rate": 5.7678102601543336e-05, "loss": 0.0241, "step": 157860 }, { "epoch": 37.88, "learning_rate": 5.767366882656929e-05, "loss": 0.0094, "step": 157870 }, { "epoch": 37.88, "learning_rate": 5.7669234989798134e-05, "loss": 0.0226, "step": 157880 }, { "epoch": 37.88, "learning_rate": 5.7664801091265564e-05, "loss": 0.0226, "step": 157890 }, { "epoch": 37.88, "learning_rate": 5.76603671310073e-05, "loss": 0.0238, "step": 157900 }, { "epoch": 37.89, "learning_rate": 5.7655933109059024e-05, "loss": 0.0296, "step": 157910 }, { "epoch": 37.89, "learning_rate": 5.765149902545649e-05, "loss": 0.0116, "step": 157920 }, { "epoch": 37.89, "learning_rate": 5.7647064880235345e-05, "loss": 0.0168, "step": 157930 }, { "epoch": 37.89, "learning_rate": 5.7642630673431354e-05, "loss": 0.014, "step": 157940 }, { "epoch": 37.9, "learning_rate": 5.76381964050802e-05, "loss": 0.027, "step": 157950 }, { "epoch": 37.9, "learning_rate": 5.76337620752176e-05, "loss": 0.021, "step": 157960 }, { "epoch": 37.9, "learning_rate": 5.762932768387925e-05, "loss": 0.0164, "step": 157970 }, { "epoch": 37.9, "learning_rate": 5.762489323110086e-05, "loss": 0.0298, "step": 157980 }, { "epoch": 37.9, "learning_rate": 5.762045871691818e-05, "loss": 0.0346, "step": 157990 }, { "epoch": 37.91, "learning_rate": 5.7616024141366876e-05, "loss": 0.0231, "step": 158000 }, { "epoch": 37.91, "learning_rate": 5.761158950448268e-05, "loss": 0.0209, "step": 158010 }, { "epoch": 37.91, "learning_rate": 5.760715480630131e-05, "loss": 0.0109, "step": 158020 }, { "epoch": 37.91, "learning_rate": 5.760272004685847e-05, "loss": 0.0163, "step": 158030 }, { "epoch": 37.92, "learning_rate": 5.7598285226189875e-05, "loss": 0.0191, "step": 158040 }, { "epoch": 37.92, "learning_rate": 5.759385034433123e-05, "loss": 0.0267, "step": 158050 }, { "epoch": 37.92, "learning_rate": 5.7589415401318256e-05, "loss": 0.0257, "step": 158060 }, { "epoch": 37.92, "learning_rate": 5.7584980397186695e-05, "loss": 0.031, "step": 158070 }, { "epoch": 37.93, "learning_rate": 5.758054533197223e-05, "loss": 0.0176, "step": 158080 }, { "epoch": 37.93, "learning_rate": 5.7576110205710584e-05, "loss": 0.013, "step": 158090 }, { "epoch": 37.93, "learning_rate": 5.7571675018437476e-05, "loss": 0.022, "step": 158100 }, { "epoch": 37.93, "learning_rate": 5.756723977018863e-05, "loss": 0.0313, "step": 158110 }, { "epoch": 37.93, "learning_rate": 5.756280446099974e-05, "loss": 0.0161, "step": 158120 }, { "epoch": 37.94, "learning_rate": 5.755836909090656e-05, "loss": 0.0275, "step": 158130 }, { "epoch": 37.94, "learning_rate": 5.7553933659944784e-05, "loss": 0.0145, "step": 158140 }, { "epoch": 37.94, "learning_rate": 5.754949816815014e-05, "loss": 0.0112, "step": 158150 }, { "epoch": 37.94, "learning_rate": 5.754506261555834e-05, "loss": 0.0186, "step": 158160 }, { "epoch": 37.95, "learning_rate": 5.754062700220511e-05, "loss": 0.0303, "step": 158170 }, { "epoch": 37.95, "learning_rate": 5.753619132812618e-05, "loss": 0.0146, "step": 158180 }, { "epoch": 37.95, "learning_rate": 5.753175559335725e-05, "loss": 0.0344, "step": 158190 }, { "epoch": 38.0, "learning_rate": 5.752731979793405e-05, "loss": 0.016, "step": 158200 }, { "epoch": 38.0, "learning_rate": 5.7522883941892314e-05, "loss": 0.0078, "step": 158210 }, { "epoch": 38.01, "learning_rate": 5.751844802526776e-05, "loss": 0.0212, "step": 158220 }, { "epoch": 38.01, "learning_rate": 5.751401204809609e-05, "loss": 0.0145, "step": 158230 }, { "epoch": 38.01, "learning_rate": 5.750957601041305e-05, "loss": 0.0127, "step": 158240 }, { "epoch": 38.01, "learning_rate": 5.750513991225435e-05, "loss": 0.0175, "step": 158250 }, { "epoch": 38.02, "learning_rate": 5.750070375365573e-05, "loss": 0.0163, "step": 158260 }, { "epoch": 38.02, "learning_rate": 5.749626753465291e-05, "loss": 0.013, "step": 158270 }, { "epoch": 38.02, "learning_rate": 5.749183125528161e-05, "loss": 0.0207, "step": 158280 }, { "epoch": 38.02, "learning_rate": 5.748739491557756e-05, "loss": 0.0198, "step": 158290 }, { "epoch": 38.02, "learning_rate": 5.748295851557648e-05, "loss": 0.023, "step": 158300 }, { "epoch": 38.03, "learning_rate": 5.74785220553141e-05, "loss": 0.017, "step": 158310 }, { "epoch": 38.03, "learning_rate": 5.747408553482616e-05, "loss": 0.0154, "step": 158320 }, { "epoch": 38.03, "learning_rate": 5.746964895414837e-05, "loss": 0.0084, "step": 158330 }, { "epoch": 38.03, "learning_rate": 5.746521231331648e-05, "loss": 0.0163, "step": 158340 }, { "epoch": 38.04, "learning_rate": 5.746077561236618e-05, "loss": 0.027, "step": 158350 }, { "epoch": 38.04, "learning_rate": 5.7456338851333243e-05, "loss": 0.0138, "step": 158360 }, { "epoch": 38.04, "learning_rate": 5.745190203025337e-05, "loss": 0.0144, "step": 158370 }, { "epoch": 38.04, "learning_rate": 5.7447465149162305e-05, "loss": 0.0177, "step": 158380 }, { "epoch": 38.04, "learning_rate": 5.744302820809577e-05, "loss": 0.0223, "step": 158390 }, { "epoch": 38.05, "learning_rate": 5.743859120708951e-05, "loss": 0.0152, "step": 158400 }, { "epoch": 38.05, "learning_rate": 5.743415414617924e-05, "loss": 0.0267, "step": 158410 }, { "epoch": 38.05, "learning_rate": 5.742971702540071e-05, "loss": 0.008, "step": 158420 }, { "epoch": 38.05, "learning_rate": 5.7425279844789634e-05, "loss": 0.0173, "step": 158430 }, { "epoch": 38.06, "learning_rate": 5.742084260438175e-05, "loss": 0.0214, "step": 158440 }, { "epoch": 38.06, "learning_rate": 5.7416405304212806e-05, "loss": 0.0093, "step": 158450 }, { "epoch": 38.06, "learning_rate": 5.7411967944318525e-05, "loss": 0.0175, "step": 158460 }, { "epoch": 38.06, "learning_rate": 5.7407530524734645e-05, "loss": 0.0129, "step": 158470 }, { "epoch": 38.07, "learning_rate": 5.740309304549689e-05, "loss": 0.0207, "step": 158480 }, { "epoch": 38.07, "learning_rate": 5.739865550664101e-05, "loss": 0.0256, "step": 158490 }, { "epoch": 38.07, "learning_rate": 5.739421790820273e-05, "loss": 0.0236, "step": 158500 }, { "epoch": 38.07, "learning_rate": 5.73897802502178e-05, "loss": 0.0178, "step": 158510 }, { "epoch": 38.07, "learning_rate": 5.7385342532721954e-05, "loss": 0.0302, "step": 158520 }, { "epoch": 38.08, "learning_rate": 5.738090475575092e-05, "loss": 0.0225, "step": 158530 }, { "epoch": 38.08, "learning_rate": 5.737646691934043e-05, "loss": 0.0246, "step": 158540 }, { "epoch": 38.08, "learning_rate": 5.737202902352625e-05, "loss": 0.0291, "step": 158550 }, { "epoch": 38.08, "learning_rate": 5.7367591068344085e-05, "loss": 0.028, "step": 158560 }, { "epoch": 38.09, "learning_rate": 5.736315305382971e-05, "loss": 0.0265, "step": 158570 }, { "epoch": 38.09, "learning_rate": 5.7358714980018836e-05, "loss": 0.0139, "step": 158580 }, { "epoch": 38.09, "learning_rate": 5.735427684694722e-05, "loss": 0.0273, "step": 158590 }, { "epoch": 38.09, "learning_rate": 5.73498386546506e-05, "loss": 0.0283, "step": 158600 }, { "epoch": 38.1, "learning_rate": 5.734540040316469e-05, "loss": 0.0167, "step": 158610 }, { "epoch": 38.1, "learning_rate": 5.73409620925253e-05, "loss": 0.0139, "step": 158620 }, { "epoch": 38.1, "learning_rate": 5.733652372276809e-05, "loss": 0.0082, "step": 158630 }, { "epoch": 38.1, "learning_rate": 5.733208529392886e-05, "loss": 0.0123, "step": 158640 }, { "epoch": 38.1, "learning_rate": 5.732764680604333e-05, "loss": 0.0151, "step": 158650 }, { "epoch": 38.11, "learning_rate": 5.732320825914725e-05, "loss": 0.023, "step": 158660 }, { "epoch": 38.11, "learning_rate": 5.731876965327636e-05, "loss": 0.0156, "step": 158670 }, { "epoch": 38.11, "learning_rate": 5.7314330988466406e-05, "loss": 0.0181, "step": 158680 }, { "epoch": 38.11, "learning_rate": 5.7309892264753154e-05, "loss": 0.0208, "step": 158690 }, { "epoch": 38.12, "learning_rate": 5.730545348217231e-05, "loss": 0.0169, "step": 158700 }, { "epoch": 38.12, "learning_rate": 5.7301014640759646e-05, "loss": 0.0141, "step": 158710 }, { "epoch": 38.12, "learning_rate": 5.72965757405509e-05, "loss": 0.0284, "step": 158720 }, { "epoch": 38.12, "learning_rate": 5.7292136781581815e-05, "loss": 0.0219, "step": 158730 }, { "epoch": 38.12, "learning_rate": 5.728769776388817e-05, "loss": 0.0132, "step": 158740 }, { "epoch": 38.13, "learning_rate": 5.728325868750567e-05, "loss": 0.0132, "step": 158750 }, { "epoch": 38.13, "learning_rate": 5.72788195524701e-05, "loss": 0.0138, "step": 158760 }, { "epoch": 38.13, "learning_rate": 5.7274380358817157e-05, "loss": 0.0172, "step": 158770 }, { "epoch": 38.13, "learning_rate": 5.726994110658266e-05, "loss": 0.0216, "step": 158780 }, { "epoch": 38.14, "learning_rate": 5.72655017958023e-05, "loss": 0.0229, "step": 158790 }, { "epoch": 38.14, "learning_rate": 5.7261062426511856e-05, "loss": 0.013, "step": 158800 }, { "epoch": 38.14, "learning_rate": 5.725662299874709e-05, "loss": 0.0314, "step": 158810 }, { "epoch": 38.14, "learning_rate": 5.725218351254372e-05, "loss": 0.0119, "step": 158820 }, { "epoch": 38.15, "learning_rate": 5.724774396793752e-05, "loss": 0.0231, "step": 158830 }, { "epoch": 38.15, "learning_rate": 5.7243304364964236e-05, "loss": 0.0245, "step": 158840 }, { "epoch": 38.15, "learning_rate": 5.7238864703659624e-05, "loss": 0.0247, "step": 158850 }, { "epoch": 38.15, "learning_rate": 5.723442498405944e-05, "loss": 0.0135, "step": 158860 }, { "epoch": 38.15, "learning_rate": 5.722998520619942e-05, "loss": 0.0194, "step": 158870 }, { "epoch": 38.16, "learning_rate": 5.7225545370115355e-05, "loss": 0.028, "step": 158880 }, { "epoch": 38.16, "learning_rate": 5.722110547584294e-05, "loss": 0.0202, "step": 158890 }, { "epoch": 38.16, "learning_rate": 5.721666552341799e-05, "loss": 0.019, "step": 158900 }, { "epoch": 38.16, "learning_rate": 5.7212225512876236e-05, "loss": 0.0185, "step": 158910 }, { "epoch": 38.17, "learning_rate": 5.7207785444253416e-05, "loss": 0.016, "step": 158920 }, { "epoch": 38.17, "learning_rate": 5.720334531758533e-05, "loss": 0.0174, "step": 158930 }, { "epoch": 38.17, "learning_rate": 5.719890513290769e-05, "loss": 0.0264, "step": 158940 }, { "epoch": 38.17, "learning_rate": 5.71944648902563e-05, "loss": 0.0141, "step": 158950 }, { "epoch": 38.18, "learning_rate": 5.719002458966686e-05, "loss": 0.0094, "step": 158960 }, { "epoch": 38.18, "learning_rate": 5.718558423117517e-05, "loss": 0.0223, "step": 158970 }, { "epoch": 38.18, "learning_rate": 5.718114381481698e-05, "loss": 0.0459, "step": 158980 }, { "epoch": 38.18, "learning_rate": 5.717670334062804e-05, "loss": 0.0192, "step": 158990 }, { "epoch": 38.18, "learning_rate": 5.717226280864414e-05, "loss": 0.0141, "step": 159000 }, { "epoch": 38.19, "learning_rate": 5.716782221890098e-05, "loss": 0.0168, "step": 159010 }, { "epoch": 38.19, "learning_rate": 5.716338157143438e-05, "loss": 0.0166, "step": 159020 }, { "epoch": 38.19, "learning_rate": 5.7158940866280086e-05, "loss": 0.0103, "step": 159030 }, { "epoch": 38.19, "learning_rate": 5.715450010347384e-05, "loss": 0.0149, "step": 159040 }, { "epoch": 38.2, "learning_rate": 5.715005928305143e-05, "loss": 0.0173, "step": 159050 }, { "epoch": 38.2, "learning_rate": 5.7145618405048594e-05, "loss": 0.0093, "step": 159060 }, { "epoch": 38.2, "learning_rate": 5.714117746950112e-05, "loss": 0.0313, "step": 159070 }, { "epoch": 38.2, "learning_rate": 5.713673647644474e-05, "loss": 0.0212, "step": 159080 }, { "epoch": 38.2, "learning_rate": 5.713229542591524e-05, "loss": 0.0256, "step": 159090 }, { "epoch": 38.21, "learning_rate": 5.712785431794839e-05, "loss": 0.0201, "step": 159100 }, { "epoch": 38.21, "learning_rate": 5.712341315257993e-05, "loss": 0.0235, "step": 159110 }, { "epoch": 38.21, "learning_rate": 5.7118971929845665e-05, "loss": 0.0138, "step": 159120 }, { "epoch": 38.21, "learning_rate": 5.711453064978131e-05, "loss": 0.0218, "step": 159130 }, { "epoch": 38.22, "learning_rate": 5.7110089312422665e-05, "loss": 0.0143, "step": 159140 }, { "epoch": 38.22, "learning_rate": 5.710564791780549e-05, "loss": 0.0157, "step": 159150 }, { "epoch": 38.22, "learning_rate": 5.710120646596555e-05, "loss": 0.0279, "step": 159160 }, { "epoch": 38.22, "learning_rate": 5.709676495693863e-05, "loss": 0.0112, "step": 159170 }, { "epoch": 38.23, "learning_rate": 5.709232339076046e-05, "loss": 0.0295, "step": 159180 }, { "epoch": 38.23, "learning_rate": 5.7087881767466854e-05, "loss": 0.0207, "step": 159190 }, { "epoch": 38.23, "learning_rate": 5.708344008709354e-05, "loss": 0.0102, "step": 159200 }, { "epoch": 38.23, "learning_rate": 5.70789983496763e-05, "loss": 0.0205, "step": 159210 }, { "epoch": 38.23, "learning_rate": 5.7074556555250924e-05, "loss": 0.0102, "step": 159220 }, { "epoch": 38.24, "learning_rate": 5.707011470385316e-05, "loss": 0.0123, "step": 159230 }, { "epoch": 38.24, "learning_rate": 5.70656727955188e-05, "loss": 0.0193, "step": 159240 }, { "epoch": 38.24, "learning_rate": 5.706123083028357e-05, "loss": 0.0173, "step": 159250 }, { "epoch": 38.24, "learning_rate": 5.7056788808183306e-05, "loss": 0.0056, "step": 159260 }, { "epoch": 38.25, "learning_rate": 5.705234672925372e-05, "loss": 0.0281, "step": 159270 }, { "epoch": 38.25, "learning_rate": 5.704790459353064e-05, "loss": 0.0217, "step": 159280 }, { "epoch": 38.25, "learning_rate": 5.70434624010498e-05, "loss": 0.0145, "step": 159290 }, { "epoch": 38.25, "learning_rate": 5.703902015184697e-05, "loss": 0.0171, "step": 159300 }, { "epoch": 38.26, "learning_rate": 5.703457784595796e-05, "loss": 0.0295, "step": 159310 }, { "epoch": 38.26, "learning_rate": 5.703013548341851e-05, "loss": 0.0174, "step": 159320 }, { "epoch": 38.26, "learning_rate": 5.7025693064264416e-05, "loss": 0.0134, "step": 159330 }, { "epoch": 38.26, "learning_rate": 5.702125058853144e-05, "loss": 0.0191, "step": 159340 }, { "epoch": 38.26, "learning_rate": 5.701680805625537e-05, "loss": 0.0244, "step": 159350 }, { "epoch": 38.27, "learning_rate": 5.7012365467471975e-05, "loss": 0.0305, "step": 159360 }, { "epoch": 38.27, "learning_rate": 5.700792282221702e-05, "loss": 0.0237, "step": 159370 }, { "epoch": 38.27, "learning_rate": 5.700348012052632e-05, "loss": 0.0115, "step": 159380 }, { "epoch": 38.27, "learning_rate": 5.69990373624356e-05, "loss": 0.0246, "step": 159390 }, { "epoch": 38.28, "learning_rate": 5.699459454798068e-05, "loss": 0.021, "step": 159400 }, { "epoch": 38.28, "learning_rate": 5.699015167719732e-05, "loss": 0.0196, "step": 159410 }, { "epoch": 38.28, "learning_rate": 5.698570875012131e-05, "loss": 0.019, "step": 159420 }, { "epoch": 38.28, "learning_rate": 5.698126576678843e-05, "loss": 0.0196, "step": 159430 }, { "epoch": 38.28, "learning_rate": 5.6976822727234435e-05, "loss": 0.0263, "step": 159440 }, { "epoch": 38.29, "learning_rate": 5.6972379631495134e-05, "loss": 0.0242, "step": 159450 }, { "epoch": 38.29, "learning_rate": 5.696793647960629e-05, "loss": 0.0093, "step": 159460 }, { "epoch": 38.29, "learning_rate": 5.6963493271603695e-05, "loss": 0.0258, "step": 159470 }, { "epoch": 38.29, "learning_rate": 5.695905000752313e-05, "loss": 0.032, "step": 159480 }, { "epoch": 38.3, "learning_rate": 5.695460668740037e-05, "loss": 0.0197, "step": 159490 }, { "epoch": 38.3, "learning_rate": 5.695016331127121e-05, "loss": 0.0248, "step": 159500 }, { "epoch": 38.3, "learning_rate": 5.694571987917141e-05, "loss": 0.0255, "step": 159510 }, { "epoch": 38.3, "learning_rate": 5.694127639113679e-05, "loss": 0.0116, "step": 159520 }, { "epoch": 38.31, "learning_rate": 5.69368328472031e-05, "loss": 0.0247, "step": 159530 }, { "epoch": 38.31, "learning_rate": 5.6932389247406134e-05, "loss": 0.0222, "step": 159540 }, { "epoch": 38.31, "learning_rate": 5.6927945591781694e-05, "loss": 0.0212, "step": 159550 }, { "epoch": 38.31, "learning_rate": 5.692350188036554e-05, "loss": 0.0189, "step": 159560 }, { "epoch": 38.31, "learning_rate": 5.691905811319347e-05, "loss": 0.0159, "step": 159570 }, { "epoch": 38.32, "learning_rate": 5.691461429030127e-05, "loss": 0.0128, "step": 159580 }, { "epoch": 38.32, "learning_rate": 5.6910170411724725e-05, "loss": 0.0153, "step": 159590 }, { "epoch": 38.32, "learning_rate": 5.690572647749963e-05, "loss": 0.0198, "step": 159600 }, { "epoch": 38.32, "learning_rate": 5.690128248766178e-05, "loss": 0.0193, "step": 159610 }, { "epoch": 38.33, "learning_rate": 5.6896838442246924e-05, "loss": 0.0303, "step": 159620 }, { "epoch": 38.33, "learning_rate": 5.689239434129088e-05, "loss": 0.0341, "step": 159630 }, { "epoch": 38.33, "learning_rate": 5.6887950184829445e-05, "loss": 0.0224, "step": 159640 }, { "epoch": 38.33, "learning_rate": 5.688350597289839e-05, "loss": 0.0102, "step": 159650 }, { "epoch": 38.34, "learning_rate": 5.687906170553351e-05, "loss": 0.0141, "step": 159660 }, { "epoch": 38.34, "learning_rate": 5.68746173827706e-05, "loss": 0.0189, "step": 159670 }, { "epoch": 38.34, "learning_rate": 5.687017300464544e-05, "loss": 0.0107, "step": 159680 }, { "epoch": 38.34, "learning_rate": 5.686572857119382e-05, "loss": 0.0084, "step": 159690 }, { "epoch": 38.34, "learning_rate": 5.686128408245156e-05, "loss": 0.0218, "step": 159700 }, { "epoch": 38.35, "learning_rate": 5.685683953845442e-05, "loss": 0.0201, "step": 159710 }, { "epoch": 38.35, "learning_rate": 5.685239493923822e-05, "loss": 0.0282, "step": 159720 }, { "epoch": 38.35, "learning_rate": 5.684795028483873e-05, "loss": 0.0162, "step": 159730 }, { "epoch": 38.35, "learning_rate": 5.6843505575291746e-05, "loss": 0.0112, "step": 159740 }, { "epoch": 38.36, "learning_rate": 5.683906081063306e-05, "loss": 0.0163, "step": 159750 }, { "epoch": 38.36, "learning_rate": 5.683461599089848e-05, "loss": 0.0355, "step": 159760 }, { "epoch": 38.36, "learning_rate": 5.6830171116123796e-05, "loss": 0.0112, "step": 159770 }, { "epoch": 38.36, "learning_rate": 5.6825726186344794e-05, "loss": 0.0177, "step": 159780 }, { "epoch": 38.36, "learning_rate": 5.682128120159729e-05, "loss": 0.03, "step": 159790 }, { "epoch": 38.37, "learning_rate": 5.681683616191706e-05, "loss": 0.0199, "step": 159800 }, { "epoch": 38.37, "learning_rate": 5.68123910673399e-05, "loss": 0.0221, "step": 159810 }, { "epoch": 38.37, "learning_rate": 5.680794591790162e-05, "loss": 0.0189, "step": 159820 }, { "epoch": 38.37, "learning_rate": 5.680350071363802e-05, "loss": 0.0155, "step": 159830 }, { "epoch": 38.38, "learning_rate": 5.679905545458488e-05, "loss": 0.0101, "step": 159840 }, { "epoch": 38.38, "learning_rate": 5.6794610140778015e-05, "loss": 0.02, "step": 159850 }, { "epoch": 38.38, "learning_rate": 5.6790164772253205e-05, "loss": 0.0101, "step": 159860 }, { "epoch": 38.38, "learning_rate": 5.678571934904627e-05, "loss": 0.009, "step": 159870 }, { "epoch": 38.39, "learning_rate": 5.678127387119299e-05, "loss": 0.0127, "step": 159880 }, { "epoch": 38.39, "learning_rate": 5.6776828338729185e-05, "loss": 0.0326, "step": 159890 }, { "epoch": 38.39, "learning_rate": 5.6772382751690644e-05, "loss": 0.0233, "step": 159900 }, { "epoch": 38.39, "learning_rate": 5.676793711011317e-05, "loss": 0.0152, "step": 159910 }, { "epoch": 38.39, "learning_rate": 5.6763491414032566e-05, "loss": 0.0202, "step": 159920 }, { "epoch": 38.4, "learning_rate": 5.6759045663484634e-05, "loss": 0.0218, "step": 159930 }, { "epoch": 38.4, "learning_rate": 5.6754599858505166e-05, "loss": 0.0151, "step": 159940 }, { "epoch": 38.4, "learning_rate": 5.6750153999129974e-05, "loss": 0.013, "step": 159950 }, { "epoch": 38.4, "learning_rate": 5.6745708085394856e-05, "loss": 0.0193, "step": 159960 }, { "epoch": 38.41, "learning_rate": 5.6741262117335626e-05, "loss": 0.0219, "step": 159970 }, { "epoch": 38.41, "learning_rate": 5.673681609498809e-05, "loss": 0.0177, "step": 159980 }, { "epoch": 38.41, "learning_rate": 5.6732370018388025e-05, "loss": 0.009, "step": 159990 }, { "epoch": 38.41, "learning_rate": 5.6727923887571265e-05, "loss": 0.0155, "step": 160000 }, { "epoch": 38.41, "learning_rate": 5.6723477702573616e-05, "loss": 0.0125, "step": 160010 }, { "epoch": 38.42, "learning_rate": 5.671903146343085e-05, "loss": 0.0144, "step": 160020 }, { "epoch": 38.42, "learning_rate": 5.6714585170178805e-05, "loss": 0.0251, "step": 160030 }, { "epoch": 38.42, "learning_rate": 5.671013882285329e-05, "loss": 0.0295, "step": 160040 }, { "epoch": 38.42, "learning_rate": 5.6705692421490086e-05, "loss": 0.0161, "step": 160050 }, { "epoch": 38.43, "learning_rate": 5.670124596612503e-05, "loss": 0.0238, "step": 160060 }, { "epoch": 38.43, "learning_rate": 5.669679945679389e-05, "loss": 0.02, "step": 160070 }, { "epoch": 38.43, "learning_rate": 5.6692352893532517e-05, "loss": 0.0107, "step": 160080 }, { "epoch": 38.43, "learning_rate": 5.66879062763767e-05, "loss": 0.0136, "step": 160090 }, { "epoch": 38.44, "learning_rate": 5.668345960536225e-05, "loss": 0.0198, "step": 160100 }, { "epoch": 38.44, "learning_rate": 5.6679012880524986e-05, "loss": 0.0195, "step": 160110 }, { "epoch": 38.44, "learning_rate": 5.6674566101900694e-05, "loss": 0.0238, "step": 160120 }, { "epoch": 38.44, "learning_rate": 5.667011926952521e-05, "loss": 0.0314, "step": 160130 }, { "epoch": 38.44, "learning_rate": 5.666567238343433e-05, "loss": 0.0126, "step": 160140 }, { "epoch": 38.45, "learning_rate": 5.666122544366388e-05, "loss": 0.019, "step": 160150 }, { "epoch": 38.45, "learning_rate": 5.665677845024965e-05, "loss": 0.0203, "step": 160160 }, { "epoch": 38.45, "learning_rate": 5.6652331403227464e-05, "loss": 0.0205, "step": 160170 }, { "epoch": 38.45, "learning_rate": 5.664788430263315e-05, "loss": 0.0323, "step": 160180 }, { "epoch": 38.46, "learning_rate": 5.6643437148502475e-05, "loss": 0.0207, "step": 160190 }, { "epoch": 38.46, "learning_rate": 5.6638989940871324e-05, "loss": 0.0095, "step": 160200 }, { "epoch": 38.46, "learning_rate": 5.663454267977544e-05, "loss": 0.0116, "step": 160210 }, { "epoch": 38.46, "learning_rate": 5.663009536525068e-05, "loss": 0.014, "step": 160220 }, { "epoch": 38.47, "learning_rate": 5.662564799733284e-05, "loss": 0.0162, "step": 160230 }, { "epoch": 38.47, "learning_rate": 5.662120057605773e-05, "loss": 0.0204, "step": 160240 }, { "epoch": 38.47, "learning_rate": 5.661675310146122e-05, "loss": 0.0135, "step": 160250 }, { "epoch": 38.47, "learning_rate": 5.661230557357904e-05, "loss": 0.0273, "step": 160260 }, { "epoch": 38.47, "learning_rate": 5.660785799244708e-05, "loss": 0.0196, "step": 160270 }, { "epoch": 38.48, "learning_rate": 5.66034103581011e-05, "loss": 0.0135, "step": 160280 }, { "epoch": 38.48, "learning_rate": 5.659896267057696e-05, "loss": 0.015, "step": 160290 }, { "epoch": 38.48, "learning_rate": 5.659451492991047e-05, "loss": 0.0091, "step": 160300 }, { "epoch": 38.48, "learning_rate": 5.659006713613743e-05, "loss": 0.0177, "step": 160310 }, { "epoch": 38.49, "learning_rate": 5.6585619289293676e-05, "loss": 0.0438, "step": 160320 }, { "epoch": 38.49, "learning_rate": 5.658117138941501e-05, "loss": 0.0137, "step": 160330 }, { "epoch": 38.49, "learning_rate": 5.657672343653728e-05, "loss": 0.0258, "step": 160340 }, { "epoch": 38.49, "learning_rate": 5.6572275430696276e-05, "loss": 0.0197, "step": 160350 }, { "epoch": 38.49, "learning_rate": 5.656782737192783e-05, "loss": 0.018, "step": 160360 }, { "epoch": 38.5, "learning_rate": 5.656337926026777e-05, "loss": 0.022, "step": 160370 }, { "epoch": 38.5, "learning_rate": 5.655893109575189e-05, "loss": 0.0145, "step": 160380 }, { "epoch": 38.5, "learning_rate": 5.655448287841606e-05, "loss": 0.0311, "step": 160390 }, { "epoch": 38.5, "learning_rate": 5.655003460829605e-05, "loss": 0.0216, "step": 160400 }, { "epoch": 38.51, "learning_rate": 5.654558628542773e-05, "loss": 0.0156, "step": 160410 }, { "epoch": 38.51, "learning_rate": 5.6541137909846886e-05, "loss": 0.0128, "step": 160420 }, { "epoch": 38.51, "learning_rate": 5.653668948158936e-05, "loss": 0.0098, "step": 160430 }, { "epoch": 38.51, "learning_rate": 5.6532241000690975e-05, "loss": 0.0281, "step": 160440 }, { "epoch": 38.52, "learning_rate": 5.652779246718754e-05, "loss": 0.0094, "step": 160450 }, { "epoch": 38.52, "learning_rate": 5.652334388111491e-05, "loss": 0.0213, "step": 160460 }, { "epoch": 38.52, "learning_rate": 5.651889524250887e-05, "loss": 0.026, "step": 160470 }, { "epoch": 38.52, "learning_rate": 5.651444655140528e-05, "loss": 0.0361, "step": 160480 }, { "epoch": 38.52, "learning_rate": 5.6509997807839945e-05, "loss": 0.0271, "step": 160490 }, { "epoch": 38.53, "learning_rate": 5.65055490118487e-05, "loss": 0.0283, "step": 160500 }, { "epoch": 38.53, "learning_rate": 5.650110016346738e-05, "loss": 0.0209, "step": 160510 }, { "epoch": 38.53, "learning_rate": 5.6496651262731795e-05, "loss": 0.0187, "step": 160520 }, { "epoch": 38.53, "learning_rate": 5.649220230967778e-05, "loss": 0.0175, "step": 160530 }, { "epoch": 38.54, "learning_rate": 5.6487753304341164e-05, "loss": 0.0253, "step": 160540 }, { "epoch": 38.54, "learning_rate": 5.648330424675776e-05, "loss": 0.0132, "step": 160550 }, { "epoch": 38.54, "learning_rate": 5.647885513696345e-05, "loss": 0.0332, "step": 160560 }, { "epoch": 38.54, "learning_rate": 5.647440597499398e-05, "loss": 0.0118, "step": 160570 }, { "epoch": 38.55, "learning_rate": 5.6469956760885264e-05, "loss": 0.02, "step": 160580 }, { "epoch": 38.55, "learning_rate": 5.646550749467308e-05, "loss": 0.0197, "step": 160590 }, { "epoch": 38.55, "learning_rate": 5.6461058176393255e-05, "loss": 0.0225, "step": 160600 }, { "epoch": 38.55, "learning_rate": 5.6456608806081655e-05, "loss": 0.0267, "step": 160610 }, { "epoch": 38.55, "learning_rate": 5.645215938377408e-05, "loss": 0.0261, "step": 160620 }, { "epoch": 38.56, "learning_rate": 5.6447709909506394e-05, "loss": 0.0143, "step": 160630 }, { "epoch": 38.56, "learning_rate": 5.644326038331439e-05, "loss": 0.0327, "step": 160640 }, { "epoch": 38.56, "learning_rate": 5.643881080523393e-05, "loss": 0.0108, "step": 160650 }, { "epoch": 38.56, "learning_rate": 5.643436117530083e-05, "loss": 0.0191, "step": 160660 }, { "epoch": 38.57, "learning_rate": 5.642991149355094e-05, "loss": 0.0154, "step": 160670 }, { "epoch": 38.57, "learning_rate": 5.6425461760020096e-05, "loss": 0.0216, "step": 160680 }, { "epoch": 38.57, "learning_rate": 5.6421011974744087e-05, "loss": 0.032, "step": 160690 }, { "epoch": 38.57, "learning_rate": 5.6416562137758824e-05, "loss": 0.0244, "step": 160700 }, { "epoch": 38.57, "learning_rate": 5.641211224910007e-05, "loss": 0.0242, "step": 160710 }, { "epoch": 38.58, "learning_rate": 5.64076623088037e-05, "loss": 0.0265, "step": 160720 }, { "epoch": 38.58, "learning_rate": 5.640321231690554e-05, "loss": 0.0253, "step": 160730 }, { "epoch": 38.58, "learning_rate": 5.639876227344142e-05, "loss": 0.0217, "step": 160740 }, { "epoch": 38.58, "learning_rate": 5.6394312178447205e-05, "loss": 0.0223, "step": 160750 }, { "epoch": 38.59, "learning_rate": 5.6389862031958685e-05, "loss": 0.0316, "step": 160760 }, { "epoch": 38.59, "learning_rate": 5.6385411834011734e-05, "loss": 0.035, "step": 160770 }, { "epoch": 38.59, "learning_rate": 5.638096158464219e-05, "loss": 0.0141, "step": 160780 }, { "epoch": 38.59, "learning_rate": 5.637651128388588e-05, "loss": 0.0158, "step": 160790 }, { "epoch": 38.6, "learning_rate": 5.6372060931778633e-05, "loss": 0.0299, "step": 160800 }, { "epoch": 38.6, "learning_rate": 5.6367610528356296e-05, "loss": 0.0253, "step": 160810 }, { "epoch": 38.6, "learning_rate": 5.636316007365474e-05, "loss": 0.0226, "step": 160820 }, { "epoch": 38.6, "learning_rate": 5.635870956770974e-05, "loss": 0.0171, "step": 160830 }, { "epoch": 38.6, "learning_rate": 5.63542590105572e-05, "loss": 0.0281, "step": 160840 }, { "epoch": 38.61, "learning_rate": 5.634980840223293e-05, "loss": 0.0305, "step": 160850 }, { "epoch": 38.61, "learning_rate": 5.634535774277277e-05, "loss": 0.023, "step": 160860 }, { "epoch": 38.61, "learning_rate": 5.6340907032212575e-05, "loss": 0.0171, "step": 160870 }, { "epoch": 38.61, "learning_rate": 5.633645627058817e-05, "loss": 0.0227, "step": 160880 }, { "epoch": 38.62, "learning_rate": 5.633200545793543e-05, "loss": 0.037, "step": 160890 }, { "epoch": 38.62, "learning_rate": 5.6327554594290154e-05, "loss": 0.0306, "step": 160900 }, { "epoch": 38.62, "learning_rate": 5.632310367968822e-05, "loss": 0.0162, "step": 160910 }, { "epoch": 38.62, "learning_rate": 5.631865271416546e-05, "loss": 0.0267, "step": 160920 }, { "epoch": 38.63, "learning_rate": 5.631420169775771e-05, "loss": 0.0199, "step": 160930 }, { "epoch": 38.63, "learning_rate": 5.630975063050081e-05, "loss": 0.0241, "step": 160940 }, { "epoch": 38.63, "learning_rate": 5.630529951243063e-05, "loss": 0.0156, "step": 160950 }, { "epoch": 38.63, "learning_rate": 5.6300848343583004e-05, "loss": 0.016, "step": 160960 }, { "epoch": 38.63, "learning_rate": 5.629639712399377e-05, "loss": 0.0233, "step": 160970 }, { "epoch": 38.64, "learning_rate": 5.629194585369879e-05, "loss": 0.0139, "step": 160980 }, { "epoch": 38.64, "learning_rate": 5.62874945327339e-05, "loss": 0.0234, "step": 160990 }, { "epoch": 38.64, "learning_rate": 5.6283043161134954e-05, "loss": 0.0237, "step": 161000 }, { "epoch": 38.64, "learning_rate": 5.627859173893778e-05, "loss": 0.0139, "step": 161010 }, { "epoch": 38.65, "learning_rate": 5.627414026617823e-05, "loss": 0.0205, "step": 161020 }, { "epoch": 38.65, "learning_rate": 5.626968874289219e-05, "loss": 0.0111, "step": 161030 }, { "epoch": 38.65, "learning_rate": 5.626523716911547e-05, "loss": 0.0124, "step": 161040 }, { "epoch": 38.65, "learning_rate": 5.626078554488392e-05, "loss": 0.0283, "step": 161050 }, { "epoch": 38.65, "learning_rate": 5.625633387023341e-05, "loss": 0.0273, "step": 161060 }, { "epoch": 38.66, "learning_rate": 5.625188214519978e-05, "loss": 0.0251, "step": 161070 }, { "epoch": 38.66, "learning_rate": 5.6247430369818876e-05, "loss": 0.018, "step": 161080 }, { "epoch": 38.66, "learning_rate": 5.6242978544126555e-05, "loss": 0.0315, "step": 161090 }, { "epoch": 38.66, "learning_rate": 5.623852666815866e-05, "loss": 0.0168, "step": 161100 }, { "epoch": 38.67, "learning_rate": 5.623407474195106e-05, "loss": 0.0219, "step": 161110 }, { "epoch": 38.67, "learning_rate": 5.622962276553959e-05, "loss": 0.019, "step": 161120 }, { "epoch": 38.67, "learning_rate": 5.622517073896011e-05, "loss": 0.0158, "step": 161130 }, { "epoch": 38.67, "learning_rate": 5.622071866224846e-05, "loss": 0.0259, "step": 161140 }, { "epoch": 38.68, "learning_rate": 5.6216266535440506e-05, "loss": 0.0155, "step": 161150 }, { "epoch": 38.68, "learning_rate": 5.6211814358572114e-05, "loss": 0.0258, "step": 161160 }, { "epoch": 38.68, "learning_rate": 5.620736213167912e-05, "loss": 0.016, "step": 161170 }, { "epoch": 38.68, "learning_rate": 5.620290985479737e-05, "loss": 0.0121, "step": 161180 }, { "epoch": 38.68, "learning_rate": 5.619845752796275e-05, "loss": 0.0351, "step": 161190 }, { "epoch": 38.69, "learning_rate": 5.619400515121107e-05, "loss": 0.0261, "step": 161200 }, { "epoch": 38.69, "learning_rate": 5.618955272457822e-05, "loss": 0.012, "step": 161210 }, { "epoch": 38.69, "learning_rate": 5.6185100248100055e-05, "loss": 0.0157, "step": 161220 }, { "epoch": 38.69, "learning_rate": 5.618064772181242e-05, "loss": 0.068, "step": 161230 }, { "epoch": 38.7, "learning_rate": 5.6176195145751174e-05, "loss": 0.0213, "step": 161240 }, { "epoch": 38.7, "learning_rate": 5.617174251995219e-05, "loss": 0.0133, "step": 161250 }, { "epoch": 38.7, "learning_rate": 5.6167289844451296e-05, "loss": 0.0151, "step": 161260 }, { "epoch": 38.7, "learning_rate": 5.616283711928436e-05, "loss": 0.0148, "step": 161270 }, { "epoch": 38.71, "learning_rate": 5.615838434448726e-05, "loss": 0.0166, "step": 161280 }, { "epoch": 38.71, "learning_rate": 5.6153931520095823e-05, "loss": 0.0217, "step": 161290 }, { "epoch": 38.71, "learning_rate": 5.6149478646145946e-05, "loss": 0.0109, "step": 161300 }, { "epoch": 38.71, "learning_rate": 5.614502572267346e-05, "loss": 0.0149, "step": 161310 }, { "epoch": 38.71, "learning_rate": 5.6140572749714234e-05, "loss": 0.0162, "step": 161320 }, { "epoch": 38.72, "learning_rate": 5.613611972730413e-05, "loss": 0.0242, "step": 161330 }, { "epoch": 38.72, "learning_rate": 5.6131666655479e-05, "loss": 0.0181, "step": 161340 }, { "epoch": 38.72, "learning_rate": 5.6127213534274714e-05, "loss": 0.022, "step": 161350 }, { "epoch": 38.72, "learning_rate": 5.6122760363727137e-05, "loss": 0.0372, "step": 161360 }, { "epoch": 38.73, "learning_rate": 5.611830714387212e-05, "loss": 0.0209, "step": 161370 }, { "epoch": 38.73, "learning_rate": 5.611385387474554e-05, "loss": 0.0182, "step": 161380 }, { "epoch": 38.73, "learning_rate": 5.610940055638323e-05, "loss": 0.0088, "step": 161390 }, { "epoch": 38.73, "learning_rate": 5.610494718882109e-05, "loss": 0.0251, "step": 161400 }, { "epoch": 38.73, "learning_rate": 5.6100493772094963e-05, "loss": 0.0193, "step": 161410 }, { "epoch": 38.74, "learning_rate": 5.6096040306240726e-05, "loss": 0.0261, "step": 161420 }, { "epoch": 38.74, "learning_rate": 5.609158679129423e-05, "loss": 0.0365, "step": 161430 }, { "epoch": 38.74, "learning_rate": 5.608713322729134e-05, "loss": 0.0174, "step": 161440 }, { "epoch": 38.74, "learning_rate": 5.608267961426793e-05, "loss": 0.012, "step": 161450 }, { "epoch": 38.75, "learning_rate": 5.607822595225985e-05, "loss": 0.0304, "step": 161460 }, { "epoch": 38.75, "learning_rate": 5.607377224130299e-05, "loss": 0.0146, "step": 161470 }, { "epoch": 38.75, "learning_rate": 5.606931848143321e-05, "loss": 0.0226, "step": 161480 }, { "epoch": 38.75, "learning_rate": 5.6064864672686354e-05, "loss": 0.0091, "step": 161490 }, { "epoch": 38.76, "learning_rate": 5.606041081509832e-05, "loss": 0.0166, "step": 161500 }, { "epoch": 38.76, "learning_rate": 5.605595690870494e-05, "loss": 0.0171, "step": 161510 }, { "epoch": 38.76, "learning_rate": 5.605150295354213e-05, "loss": 0.0273, "step": 161520 }, { "epoch": 38.76, "learning_rate": 5.604704894964571e-05, "loss": 0.0259, "step": 161530 }, { "epoch": 38.76, "learning_rate": 5.604259489705158e-05, "loss": 0.0166, "step": 161540 }, { "epoch": 38.77, "learning_rate": 5.60381407957956e-05, "loss": 0.0238, "step": 161550 }, { "epoch": 38.77, "learning_rate": 5.603368664591363e-05, "loss": 0.0288, "step": 161560 }, { "epoch": 38.77, "learning_rate": 5.602923244744156e-05, "loss": 0.0278, "step": 161570 }, { "epoch": 38.77, "learning_rate": 5.602477820041523e-05, "loss": 0.0153, "step": 161580 }, { "epoch": 38.78, "learning_rate": 5.602032390487055e-05, "loss": 0.0265, "step": 161590 }, { "epoch": 38.78, "learning_rate": 5.601586956084336e-05, "loss": 0.0162, "step": 161600 }, { "epoch": 38.78, "learning_rate": 5.601141516836954e-05, "loss": 0.0124, "step": 161610 }, { "epoch": 38.78, "learning_rate": 5.600696072748497e-05, "loss": 0.0333, "step": 161620 }, { "epoch": 38.79, "learning_rate": 5.6002506238225503e-05, "loss": 0.016, "step": 161630 }, { "epoch": 38.79, "learning_rate": 5.599805170062705e-05, "loss": 0.0089, "step": 161640 }, { "epoch": 38.79, "learning_rate": 5.599359711472544e-05, "loss": 0.0224, "step": 161650 }, { "epoch": 38.79, "learning_rate": 5.598914248055658e-05, "loss": 0.0249, "step": 161660 }, { "epoch": 38.79, "learning_rate": 5.598468779815631e-05, "loss": 0.0266, "step": 161670 }, { "epoch": 38.8, "learning_rate": 5.598023306756053e-05, "loss": 0.0197, "step": 161680 }, { "epoch": 38.8, "learning_rate": 5.597577828880511e-05, "loss": 0.0194, "step": 161690 }, { "epoch": 38.8, "learning_rate": 5.5971323461925915e-05, "loss": 0.0186, "step": 161700 }, { "epoch": 38.8, "learning_rate": 5.596686858695884e-05, "loss": 0.0146, "step": 161710 }, { "epoch": 38.81, "learning_rate": 5.596241366393974e-05, "loss": 0.0307, "step": 161720 }, { "epoch": 38.81, "learning_rate": 5.59579586929045e-05, "loss": 0.0221, "step": 161730 }, { "epoch": 38.81, "learning_rate": 5.5953503673889e-05, "loss": 0.0146, "step": 161740 }, { "epoch": 38.81, "learning_rate": 5.594904860692911e-05, "loss": 0.0251, "step": 161750 }, { "epoch": 38.81, "learning_rate": 5.594459349206072e-05, "loss": 0.0212, "step": 161760 }, { "epoch": 38.82, "learning_rate": 5.594013832931967e-05, "loss": 0.0206, "step": 161770 }, { "epoch": 38.82, "learning_rate": 5.59356831187419e-05, "loss": 0.011, "step": 161780 }, { "epoch": 38.82, "learning_rate": 5.593122786036323e-05, "loss": 0.0194, "step": 161790 }, { "epoch": 38.82, "learning_rate": 5.592677255421958e-05, "loss": 0.0163, "step": 161800 }, { "epoch": 38.83, "learning_rate": 5.59223172003468e-05, "loss": 0.0173, "step": 161810 }, { "epoch": 38.83, "learning_rate": 5.591786179878078e-05, "loss": 0.0426, "step": 161820 }, { "epoch": 38.83, "learning_rate": 5.5913406349557415e-05, "loss": 0.0179, "step": 161830 }, { "epoch": 38.83, "learning_rate": 5.590895085271256e-05, "loss": 0.0215, "step": 161840 }, { "epoch": 38.84, "learning_rate": 5.5904495308282127e-05, "loss": 0.012, "step": 161850 }, { "epoch": 38.84, "learning_rate": 5.5900039716301953e-05, "loss": 0.0067, "step": 161860 }, { "epoch": 38.84, "learning_rate": 5.589558407680796e-05, "loss": 0.0116, "step": 161870 }, { "epoch": 38.84, "learning_rate": 5.589112838983601e-05, "loss": 0.0136, "step": 161880 }, { "epoch": 38.84, "learning_rate": 5.588667265542198e-05, "loss": 0.0237, "step": 161890 }, { "epoch": 38.85, "learning_rate": 5.588221687360179e-05, "loss": 0.016, "step": 161900 }, { "epoch": 38.85, "learning_rate": 5.587776104441127e-05, "loss": 0.0193, "step": 161910 }, { "epoch": 38.85, "learning_rate": 5.5873305167886334e-05, "loss": 0.029, "step": 161920 }, { "epoch": 38.85, "learning_rate": 5.586884924406287e-05, "loss": 0.0257, "step": 161930 }, { "epoch": 38.86, "learning_rate": 5.586439327297673e-05, "loss": 0.0131, "step": 161940 }, { "epoch": 38.86, "learning_rate": 5.5859937254663855e-05, "loss": 0.0094, "step": 161950 }, { "epoch": 38.86, "learning_rate": 5.585548118916008e-05, "loss": 0.0176, "step": 161960 }, { "epoch": 38.86, "learning_rate": 5.5851025076501305e-05, "loss": 0.0233, "step": 161970 }, { "epoch": 38.87, "learning_rate": 5.584656891672341e-05, "loss": 0.0315, "step": 161980 }, { "epoch": 38.87, "learning_rate": 5.58421127098623e-05, "loss": 0.0159, "step": 161990 }, { "epoch": 38.87, "learning_rate": 5.5837656455953846e-05, "loss": 0.0305, "step": 162000 }, { "epoch": 38.87, "learning_rate": 5.5833200155033924e-05, "loss": 0.0181, "step": 162010 }, { "epoch": 38.87, "learning_rate": 5.5828743807138475e-05, "loss": 0.0153, "step": 162020 }, { "epoch": 38.88, "learning_rate": 5.5824287412303314e-05, "loss": 0.0189, "step": 162030 }, { "epoch": 38.88, "learning_rate": 5.581983097056437e-05, "loss": 0.0105, "step": 162040 }, { "epoch": 38.88, "learning_rate": 5.581537448195753e-05, "loss": 0.0227, "step": 162050 }, { "epoch": 38.88, "learning_rate": 5.581091794651866e-05, "loss": 0.0122, "step": 162060 }, { "epoch": 38.89, "learning_rate": 5.580646136428369e-05, "loss": 0.0202, "step": 162070 }, { "epoch": 38.89, "learning_rate": 5.580200473528846e-05, "loss": 0.0231, "step": 162080 }, { "epoch": 38.89, "learning_rate": 5.5797548059568914e-05, "loss": 0.0166, "step": 162090 }, { "epoch": 38.89, "learning_rate": 5.5793091337160883e-05, "loss": 0.0346, "step": 162100 }, { "epoch": 38.89, "learning_rate": 5.5788634568100305e-05, "loss": 0.0209, "step": 162110 }, { "epoch": 38.9, "learning_rate": 5.578417775242305e-05, "loss": 0.0177, "step": 162120 }, { "epoch": 38.9, "learning_rate": 5.5779720890165e-05, "loss": 0.0137, "step": 162130 }, { "epoch": 38.9, "learning_rate": 5.577526398136209e-05, "loss": 0.0158, "step": 162140 }, { "epoch": 38.9, "learning_rate": 5.577080702605016e-05, "loss": 0.0179, "step": 162150 }, { "epoch": 38.91, "learning_rate": 5.576635002426512e-05, "loss": 0.0223, "step": 162160 }, { "epoch": 38.91, "learning_rate": 5.5761892976042886e-05, "loss": 0.0101, "step": 162170 }, { "epoch": 38.91, "learning_rate": 5.575743588141932e-05, "loss": 0.0087, "step": 162180 }, { "epoch": 38.91, "learning_rate": 5.575297874043033e-05, "loss": 0.0393, "step": 162190 }, { "epoch": 38.92, "learning_rate": 5.57485215531118e-05, "loss": 0.0215, "step": 162200 }, { "epoch": 38.92, "learning_rate": 5.574406431949966e-05, "loss": 0.0146, "step": 162210 }, { "epoch": 38.92, "learning_rate": 5.573960703962974e-05, "loss": 0.0298, "step": 162220 }, { "epoch": 38.92, "learning_rate": 5.5735149713537995e-05, "loss": 0.0254, "step": 162230 }, { "epoch": 38.92, "learning_rate": 5.5730692341260294e-05, "loss": 0.0178, "step": 162240 }, { "epoch": 38.93, "learning_rate": 5.572623492283253e-05, "loss": 0.0153, "step": 162250 }, { "epoch": 38.93, "learning_rate": 5.5721777458290615e-05, "loss": 0.0123, "step": 162260 }, { "epoch": 38.93, "learning_rate": 5.5717319947670424e-05, "loss": 0.0275, "step": 162270 }, { "epoch": 38.93, "learning_rate": 5.571286239100788e-05, "loss": 0.0122, "step": 162280 }, { "epoch": 38.94, "learning_rate": 5.570840478833885e-05, "loss": 0.0162, "step": 162290 }, { "epoch": 38.94, "learning_rate": 5.570394713969926e-05, "loss": 0.0252, "step": 162300 }, { "epoch": 38.94, "learning_rate": 5.5699489445124996e-05, "loss": 0.0153, "step": 162310 }, { "epoch": 38.94, "learning_rate": 5.569503170465196e-05, "loss": 0.0126, "step": 162320 }, { "epoch": 38.95, "learning_rate": 5.569057391831603e-05, "loss": 0.0178, "step": 162330 }, { "epoch": 38.95, "learning_rate": 5.568611608615313e-05, "loss": 0.0102, "step": 162340 }, { "epoch": 38.95, "learning_rate": 5.568165820819916e-05, "loss": 0.0261, "step": 162350 }, { "epoch": 39.0, "learning_rate": 5.567720028449002e-05, "loss": 0.0274, "step": 162360 }, { "epoch": 39.0, "learning_rate": 5.567274231506159e-05, "loss": 0.0106, "step": 162370 }, { "epoch": 39.01, "learning_rate": 5.566828429994978e-05, "loss": 0.0202, "step": 162380 }, { "epoch": 39.01, "learning_rate": 5.566382623919049e-05, "loss": 0.0189, "step": 162390 }, { "epoch": 39.01, "learning_rate": 5.565936813281964e-05, "loss": 0.0137, "step": 162400 }, { "epoch": 39.01, "learning_rate": 5.5654909980873104e-05, "loss": 0.01, "step": 162410 }, { "epoch": 39.01, "learning_rate": 5.5650451783386815e-05, "loss": 0.0236, "step": 162420 }, { "epoch": 39.02, "learning_rate": 5.564599354039665e-05, "loss": 0.0325, "step": 162430 }, { "epoch": 39.02, "learning_rate": 5.5641535251938513e-05, "loss": 0.0144, "step": 162440 }, { "epoch": 39.02, "learning_rate": 5.5637076918048316e-05, "loss": 0.0187, "step": 162450 }, { "epoch": 39.02, "learning_rate": 5.563261853876195e-05, "loss": 0.0102, "step": 162460 }, { "epoch": 39.03, "learning_rate": 5.562816011411535e-05, "loss": 0.0121, "step": 162470 }, { "epoch": 39.03, "learning_rate": 5.562370164414439e-05, "loss": 0.0255, "step": 162480 }, { "epoch": 39.03, "learning_rate": 5.561924312888498e-05, "loss": 0.0151, "step": 162490 }, { "epoch": 39.03, "learning_rate": 5.561478456837304e-05, "loss": 0.0239, "step": 162500 }, { "epoch": 39.03, "learning_rate": 5.561032596264446e-05, "loss": 0.0184, "step": 162510 }, { "epoch": 39.04, "learning_rate": 5.560586731173515e-05, "loss": 0.0146, "step": 162520 }, { "epoch": 39.04, "learning_rate": 5.5601408615681e-05, "loss": 0.0208, "step": 162530 }, { "epoch": 39.04, "learning_rate": 5.559694987451796e-05, "loss": 0.013, "step": 162540 }, { "epoch": 39.04, "learning_rate": 5.5592491088281896e-05, "loss": 0.0228, "step": 162550 }, { "epoch": 39.05, "learning_rate": 5.558803225700873e-05, "loss": 0.0331, "step": 162560 }, { "epoch": 39.05, "learning_rate": 5.5583573380734364e-05, "loss": 0.0156, "step": 162570 }, { "epoch": 39.05, "learning_rate": 5.557911445949473e-05, "loss": 0.0108, "step": 162580 }, { "epoch": 39.05, "learning_rate": 5.557465549332569e-05, "loss": 0.0537, "step": 162590 }, { "epoch": 39.06, "learning_rate": 5.557019648226319e-05, "loss": 0.0234, "step": 162600 }, { "epoch": 39.06, "learning_rate": 5.556573742634315e-05, "loss": 0.0165, "step": 162610 }, { "epoch": 39.06, "learning_rate": 5.556127832560143e-05, "loss": 0.0192, "step": 162620 }, { "epoch": 39.06, "learning_rate": 5.555681918007398e-05, "loss": 0.0139, "step": 162630 }, { "epoch": 39.06, "learning_rate": 5.55523599897967e-05, "loss": 0.021, "step": 162640 }, { "epoch": 39.07, "learning_rate": 5.554790075480549e-05, "loss": 0.0146, "step": 162650 }, { "epoch": 39.07, "learning_rate": 5.5543441475136274e-05, "loss": 0.0163, "step": 162660 }, { "epoch": 39.07, "learning_rate": 5.553898215082496e-05, "loss": 0.0107, "step": 162670 }, { "epoch": 39.07, "learning_rate": 5.553452278190746e-05, "loss": 0.0134, "step": 162680 }, { "epoch": 39.08, "learning_rate": 5.553006336841968e-05, "loss": 0.0162, "step": 162690 }, { "epoch": 39.08, "learning_rate": 5.552560391039754e-05, "loss": 0.0108, "step": 162700 }, { "epoch": 39.08, "learning_rate": 5.5521144407876945e-05, "loss": 0.0274, "step": 162710 }, { "epoch": 39.08, "learning_rate": 5.55166848608938e-05, "loss": 0.0139, "step": 162720 }, { "epoch": 39.09, "learning_rate": 5.551222526948404e-05, "loss": 0.0341, "step": 162730 }, { "epoch": 39.09, "learning_rate": 5.5507765633683584e-05, "loss": 0.0115, "step": 162740 }, { "epoch": 39.09, "learning_rate": 5.5503305953528314e-05, "loss": 0.0174, "step": 162750 }, { "epoch": 39.09, "learning_rate": 5.5498846229054166e-05, "loss": 0.0181, "step": 162760 }, { "epoch": 39.09, "learning_rate": 5.549438646029705e-05, "loss": 0.0172, "step": 162770 }, { "epoch": 39.1, "learning_rate": 5.548992664729288e-05, "loss": 0.0139, "step": 162780 }, { "epoch": 39.1, "learning_rate": 5.548546679007758e-05, "loss": 0.0267, "step": 162790 }, { "epoch": 39.1, "learning_rate": 5.548100688868705e-05, "loss": 0.0095, "step": 162800 }, { "epoch": 39.1, "learning_rate": 5.5476546943157217e-05, "loss": 0.0159, "step": 162810 }, { "epoch": 39.11, "learning_rate": 5.547208695352399e-05, "loss": 0.0131, "step": 162820 }, { "epoch": 39.11, "learning_rate": 5.54676269198233e-05, "loss": 0.0284, "step": 162830 }, { "epoch": 39.11, "learning_rate": 5.546316684209106e-05, "loss": 0.0156, "step": 162840 }, { "epoch": 39.11, "learning_rate": 5.545870672036316e-05, "loss": 0.0236, "step": 162850 }, { "epoch": 39.11, "learning_rate": 5.545424655467557e-05, "loss": 0.0187, "step": 162860 }, { "epoch": 39.12, "learning_rate": 5.544978634506417e-05, "loss": 0.0132, "step": 162870 }, { "epoch": 39.12, "learning_rate": 5.544532609156488e-05, "loss": 0.016, "step": 162880 }, { "epoch": 39.12, "learning_rate": 5.544086579421364e-05, "loss": 0.0177, "step": 162890 }, { "epoch": 39.12, "learning_rate": 5.5436405453046336e-05, "loss": 0.01, "step": 162900 }, { "epoch": 39.13, "learning_rate": 5.543194506809893e-05, "loss": 0.0139, "step": 162910 }, { "epoch": 39.13, "learning_rate": 5.54274846394073e-05, "loss": 0.0315, "step": 162920 }, { "epoch": 39.13, "learning_rate": 5.54230241670074e-05, "loss": 0.0197, "step": 162930 }, { "epoch": 39.13, "learning_rate": 5.541856365093514e-05, "loss": 0.0126, "step": 162940 }, { "epoch": 39.14, "learning_rate": 5.5414103091226434e-05, "loss": 0.0256, "step": 162950 }, { "epoch": 39.14, "learning_rate": 5.5409642487917216e-05, "loss": 0.0263, "step": 162960 }, { "epoch": 39.14, "learning_rate": 5.5405181841043385e-05, "loss": 0.0107, "step": 162970 }, { "epoch": 39.14, "learning_rate": 5.540072115064089e-05, "loss": 0.0141, "step": 162980 }, { "epoch": 39.14, "learning_rate": 5.539626041674564e-05, "loss": 0.0145, "step": 162990 }, { "epoch": 39.15, "learning_rate": 5.539179963939356e-05, "loss": 0.0151, "step": 163000 }, { "epoch": 39.15, "learning_rate": 5.538733881862057e-05, "loss": 0.0072, "step": 163010 }, { "epoch": 39.15, "learning_rate": 5.538287795446259e-05, "loss": 0.009, "step": 163020 }, { "epoch": 39.15, "learning_rate": 5.537841704695557e-05, "loss": 0.0039, "step": 163030 }, { "epoch": 39.16, "learning_rate": 5.5373956096135395e-05, "loss": 0.0244, "step": 163040 }, { "epoch": 39.16, "learning_rate": 5.536949510203802e-05, "loss": 0.0233, "step": 163050 }, { "epoch": 39.16, "learning_rate": 5.536503406469936e-05, "loss": 0.0231, "step": 163060 }, { "epoch": 39.16, "learning_rate": 5.536057298415535e-05, "loss": 0.0113, "step": 163070 }, { "epoch": 39.17, "learning_rate": 5.5356111860441886e-05, "loss": 0.0251, "step": 163080 }, { "epoch": 39.17, "learning_rate": 5.535165069359491e-05, "loss": 0.0096, "step": 163090 }, { "epoch": 39.17, "learning_rate": 5.534718948365037e-05, "loss": 0.009, "step": 163100 }, { "epoch": 39.17, "learning_rate": 5.534272823064417e-05, "loss": 0.0107, "step": 163110 }, { "epoch": 39.17, "learning_rate": 5.5338266934612236e-05, "loss": 0.027, "step": 163120 }, { "epoch": 39.18, "learning_rate": 5.5333805595590515e-05, "loss": 0.0256, "step": 163130 }, { "epoch": 39.18, "learning_rate": 5.532934421361491e-05, "loss": 0.0154, "step": 163140 }, { "epoch": 39.18, "learning_rate": 5.532488278872136e-05, "loss": 0.0196, "step": 163150 }, { "epoch": 39.18, "learning_rate": 5.5320421320945795e-05, "loss": 0.0233, "step": 163160 }, { "epoch": 39.19, "learning_rate": 5.531595981032416e-05, "loss": 0.0118, "step": 163170 }, { "epoch": 39.19, "learning_rate": 5.5311498256892335e-05, "loss": 0.0106, "step": 163180 }, { "epoch": 39.19, "learning_rate": 5.53070366606863e-05, "loss": 0.0251, "step": 163190 }, { "epoch": 39.19, "learning_rate": 5.5302575021741967e-05, "loss": 0.0203, "step": 163200 }, { "epoch": 39.19, "learning_rate": 5.529811334009525e-05, "loss": 0.0255, "step": 163210 }, { "epoch": 39.2, "learning_rate": 5.529365161578212e-05, "loss": 0.0134, "step": 163220 }, { "epoch": 39.2, "learning_rate": 5.5289189848838465e-05, "loss": 0.0288, "step": 163230 }, { "epoch": 39.2, "learning_rate": 5.5284728039300234e-05, "loss": 0.0293, "step": 163240 }, { "epoch": 39.2, "learning_rate": 5.528026618720337e-05, "loss": 0.0184, "step": 163250 }, { "epoch": 39.21, "learning_rate": 5.5275804292583775e-05, "loss": 0.0244, "step": 163260 }, { "epoch": 39.21, "learning_rate": 5.5271342355477416e-05, "loss": 0.0134, "step": 163270 }, { "epoch": 39.21, "learning_rate": 5.526688037592019e-05, "loss": 0.0111, "step": 163280 }, { "epoch": 39.21, "learning_rate": 5.5262418353948076e-05, "loss": 0.0141, "step": 163290 }, { "epoch": 39.22, "learning_rate": 5.525795628959696e-05, "loss": 0.0253, "step": 163300 }, { "epoch": 39.22, "learning_rate": 5.525349418290281e-05, "loss": 0.0107, "step": 163310 }, { "epoch": 39.22, "learning_rate": 5.524903203390154e-05, "loss": 0.0109, "step": 163320 }, { "epoch": 39.22, "learning_rate": 5.524456984262908e-05, "loss": 0.0266, "step": 163330 }, { "epoch": 39.22, "learning_rate": 5.5240107609121395e-05, "loss": 0.0105, "step": 163340 }, { "epoch": 39.23, "learning_rate": 5.5235645333414374e-05, "loss": 0.0077, "step": 163350 }, { "epoch": 39.23, "learning_rate": 5.523118301554401e-05, "loss": 0.0192, "step": 163360 }, { "epoch": 39.23, "learning_rate": 5.522672065554618e-05, "loss": 0.0174, "step": 163370 }, { "epoch": 39.23, "learning_rate": 5.522225825345686e-05, "loss": 0.0138, "step": 163380 }, { "epoch": 39.24, "learning_rate": 5.521779580931198e-05, "loss": 0.0112, "step": 163390 }, { "epoch": 39.24, "learning_rate": 5.5213333323147446e-05, "loss": 0.0058, "step": 163400 }, { "epoch": 39.24, "learning_rate": 5.520887079499924e-05, "loss": 0.0088, "step": 163410 }, { "epoch": 39.24, "learning_rate": 5.520440822490327e-05, "loss": 0.0117, "step": 163420 }, { "epoch": 39.25, "learning_rate": 5.5199945612895486e-05, "loss": 0.019, "step": 163430 }, { "epoch": 39.25, "learning_rate": 5.519548295901182e-05, "loss": 0.0094, "step": 163440 }, { "epoch": 39.25, "learning_rate": 5.5191020263288206e-05, "loss": 0.0125, "step": 163450 }, { "epoch": 39.25, "learning_rate": 5.518655752576061e-05, "loss": 0.0375, "step": 163460 }, { "epoch": 39.25, "learning_rate": 5.518209474646493e-05, "loss": 0.0207, "step": 163470 }, { "epoch": 39.26, "learning_rate": 5.5177631925437146e-05, "loss": 0.0248, "step": 163480 }, { "epoch": 39.26, "learning_rate": 5.517316906271315e-05, "loss": 0.0302, "step": 163490 }, { "epoch": 39.26, "learning_rate": 5.516870615832892e-05, "loss": 0.0191, "step": 163500 }, { "epoch": 39.26, "learning_rate": 5.5164243212320396e-05, "loss": 0.0129, "step": 163510 }, { "epoch": 39.27, "learning_rate": 5.515978022472349e-05, "loss": 0.0254, "step": 163520 }, { "epoch": 39.27, "learning_rate": 5.5155317195574185e-05, "loss": 0.0113, "step": 163530 }, { "epoch": 39.27, "learning_rate": 5.515085412490838e-05, "loss": 0.0209, "step": 163540 }, { "epoch": 39.27, "learning_rate": 5.514639101276204e-05, "loss": 0.0128, "step": 163550 }, { "epoch": 39.27, "learning_rate": 5.514192785917111e-05, "loss": 0.0174, "step": 163560 }, { "epoch": 39.28, "learning_rate": 5.5137464664171524e-05, "loss": 0.0133, "step": 163570 }, { "epoch": 39.28, "learning_rate": 5.513300142779921e-05, "loss": 0.0183, "step": 163580 }, { "epoch": 39.28, "learning_rate": 5.5128538150090135e-05, "loss": 0.0186, "step": 163590 }, { "epoch": 39.28, "learning_rate": 5.512407483108025e-05, "loss": 0.0178, "step": 163600 }, { "epoch": 39.29, "learning_rate": 5.5119611470805466e-05, "loss": 0.0296, "step": 163610 }, { "epoch": 39.29, "learning_rate": 5.511514806930175e-05, "loss": 0.0214, "step": 163620 }, { "epoch": 39.29, "learning_rate": 5.5110684626605034e-05, "loss": 0.0137, "step": 163630 }, { "epoch": 39.29, "learning_rate": 5.510622114275127e-05, "loss": 0.0313, "step": 163640 }, { "epoch": 39.3, "learning_rate": 5.5101757617776416e-05, "loss": 0.0261, "step": 163650 }, { "epoch": 39.3, "learning_rate": 5.5097294051716385e-05, "loss": 0.0271, "step": 163660 }, { "epoch": 39.3, "learning_rate": 5.509283044460716e-05, "loss": 0.0267, "step": 163670 }, { "epoch": 39.3, "learning_rate": 5.508836679648465e-05, "loss": 0.0103, "step": 163680 }, { "epoch": 39.3, "learning_rate": 5.508390310738483e-05, "loss": 0.0241, "step": 163690 }, { "epoch": 39.31, "learning_rate": 5.507943937734363e-05, "loss": 0.0173, "step": 163700 }, { "epoch": 39.31, "learning_rate": 5.507497560639701e-05, "loss": 0.0096, "step": 163710 }, { "epoch": 39.31, "learning_rate": 5.507051179458092e-05, "loss": 0.0243, "step": 163720 }, { "epoch": 39.31, "learning_rate": 5.506604794193128e-05, "loss": 0.01, "step": 163730 }, { "epoch": 39.32, "learning_rate": 5.506158404848406e-05, "loss": 0.0159, "step": 163740 }, { "epoch": 39.32, "learning_rate": 5.505712011427521e-05, "loss": 0.0253, "step": 163750 }, { "epoch": 39.32, "learning_rate": 5.5052656139340676e-05, "loss": 0.0156, "step": 163760 }, { "epoch": 39.32, "learning_rate": 5.50481921237164e-05, "loss": 0.0127, "step": 163770 }, { "epoch": 39.33, "learning_rate": 5.504372806743833e-05, "loss": 0.0162, "step": 163780 }, { "epoch": 39.33, "learning_rate": 5.5039263970542445e-05, "loss": 0.0212, "step": 163790 }, { "epoch": 39.33, "learning_rate": 5.503479983306464e-05, "loss": 0.0219, "step": 163800 }, { "epoch": 39.33, "learning_rate": 5.503033565504091e-05, "loss": 0.0139, "step": 163810 }, { "epoch": 39.33, "learning_rate": 5.502587143650719e-05, "loss": 0.0156, "step": 163820 }, { "epoch": 39.34, "learning_rate": 5.502140717749945e-05, "loss": 0.0186, "step": 163830 }, { "epoch": 39.34, "learning_rate": 5.501694287805361e-05, "loss": 0.0124, "step": 163840 }, { "epoch": 39.34, "learning_rate": 5.5012478538205624e-05, "loss": 0.0193, "step": 163850 }, { "epoch": 39.34, "learning_rate": 5.500801415799148e-05, "loss": 0.0218, "step": 163860 }, { "epoch": 39.35, "learning_rate": 5.50035497374471e-05, "loss": 0.0097, "step": 163870 }, { "epoch": 39.35, "learning_rate": 5.499908527660844e-05, "loss": 0.0082, "step": 163880 }, { "epoch": 39.35, "learning_rate": 5.499462077551145e-05, "loss": 0.0178, "step": 163890 }, { "epoch": 39.35, "learning_rate": 5.49901562341921e-05, "loss": 0.0128, "step": 163900 }, { "epoch": 39.35, "learning_rate": 5.498569165268633e-05, "loss": 0.0131, "step": 163910 }, { "epoch": 39.36, "learning_rate": 5.498122703103009e-05, "loss": 0.0104, "step": 163920 }, { "epoch": 39.36, "learning_rate": 5.497676236925935e-05, "loss": 0.0135, "step": 163930 }, { "epoch": 39.36, "learning_rate": 5.497229766741006e-05, "loss": 0.0117, "step": 163940 }, { "epoch": 39.36, "learning_rate": 5.496783292551816e-05, "loss": 0.0261, "step": 163950 }, { "epoch": 39.37, "learning_rate": 5.496336814361962e-05, "loss": 0.02, "step": 163960 }, { "epoch": 39.37, "learning_rate": 5.495890332175038e-05, "loss": 0.0184, "step": 163970 }, { "epoch": 39.37, "learning_rate": 5.495443845994641e-05, "loss": 0.0142, "step": 163980 }, { "epoch": 39.37, "learning_rate": 5.494997355824367e-05, "loss": 0.0159, "step": 163990 }, { "epoch": 39.38, "learning_rate": 5.494550861667812e-05, "loss": 0.0286, "step": 164000 }, { "epoch": 39.38, "learning_rate": 5.4941043635285694e-05, "loss": 0.0447, "step": 164010 }, { "epoch": 39.38, "learning_rate": 5.493657861410236e-05, "loss": 0.0258, "step": 164020 }, { "epoch": 39.38, "learning_rate": 5.4932113553164086e-05, "loss": 0.0235, "step": 164030 }, { "epoch": 39.38, "learning_rate": 5.492764845250681e-05, "loss": 0.0168, "step": 164040 }, { "epoch": 39.39, "learning_rate": 5.49231833121665e-05, "loss": 0.0184, "step": 164050 }, { "epoch": 39.39, "learning_rate": 5.491871813217913e-05, "loss": 0.0118, "step": 164060 }, { "epoch": 39.39, "learning_rate": 5.491425291258063e-05, "loss": 0.0207, "step": 164070 }, { "epoch": 39.39, "learning_rate": 5.4909787653406974e-05, "loss": 0.0277, "step": 164080 }, { "epoch": 39.4, "learning_rate": 5.4905322354694136e-05, "loss": 0.0266, "step": 164090 }, { "epoch": 39.4, "learning_rate": 5.490085701647805e-05, "loss": 0.0228, "step": 164100 }, { "epoch": 39.4, "learning_rate": 5.489639163879466e-05, "loss": 0.007, "step": 164110 }, { "epoch": 39.4, "learning_rate": 5.489192622167998e-05, "loss": 0.0217, "step": 164120 }, { "epoch": 39.41, "learning_rate": 5.488746076516994e-05, "loss": 0.0272, "step": 164130 }, { "epoch": 39.41, "learning_rate": 5.488299526930051e-05, "loss": 0.0191, "step": 164140 }, { "epoch": 39.41, "learning_rate": 5.487852973410763e-05, "loss": 0.0197, "step": 164150 }, { "epoch": 39.41, "learning_rate": 5.487406415962728e-05, "loss": 0.0726, "step": 164160 }, { "epoch": 39.41, "learning_rate": 5.4869598545895416e-05, "loss": 0.0178, "step": 164170 }, { "epoch": 39.42, "learning_rate": 5.486513289294801e-05, "loss": 0.0294, "step": 164180 }, { "epoch": 39.42, "learning_rate": 5.486066720082101e-05, "loss": 0.0215, "step": 164190 }, { "epoch": 39.42, "learning_rate": 5.485620146955039e-05, "loss": 0.0239, "step": 164200 }, { "epoch": 39.42, "learning_rate": 5.485173569917212e-05, "loss": 0.0084, "step": 164210 }, { "epoch": 39.43, "learning_rate": 5.484726988972214e-05, "loss": 0.0205, "step": 164220 }, { "epoch": 39.43, "learning_rate": 5.484280404123644e-05, "loss": 0.0328, "step": 164230 }, { "epoch": 39.43, "learning_rate": 5.4838338153750944e-05, "loss": 0.0138, "step": 164240 }, { "epoch": 39.43, "learning_rate": 5.4833872227301664e-05, "loss": 0.0124, "step": 164250 }, { "epoch": 39.43, "learning_rate": 5.4829406261924546e-05, "loss": 0.0309, "step": 164260 }, { "epoch": 39.44, "learning_rate": 5.482494025765553e-05, "loss": 0.0178, "step": 164270 }, { "epoch": 39.44, "learning_rate": 5.482047421453063e-05, "loss": 0.0077, "step": 164280 }, { "epoch": 39.44, "learning_rate": 5.481600813258576e-05, "loss": 0.0354, "step": 164290 }, { "epoch": 39.44, "learning_rate": 5.4811542011856933e-05, "loss": 0.0099, "step": 164300 }, { "epoch": 39.45, "learning_rate": 5.480707585238009e-05, "loss": 0.022, "step": 164310 }, { "epoch": 39.45, "learning_rate": 5.480260965419119e-05, "loss": 0.0176, "step": 164320 }, { "epoch": 39.45, "learning_rate": 5.479814341732623e-05, "loss": 0.0132, "step": 164330 }, { "epoch": 39.45, "learning_rate": 5.479367714182114e-05, "loss": 0.0136, "step": 164340 }, { "epoch": 39.46, "learning_rate": 5.4789210827711924e-05, "loss": 0.0194, "step": 164350 }, { "epoch": 39.46, "learning_rate": 5.478474447503451e-05, "loss": 0.0193, "step": 164360 }, { "epoch": 39.46, "learning_rate": 5.4780278083824896e-05, "loss": 0.0265, "step": 164370 }, { "epoch": 39.46, "learning_rate": 5.477581165411906e-05, "loss": 0.0204, "step": 164380 }, { "epoch": 39.46, "learning_rate": 5.4771345185952936e-05, "loss": 0.0095, "step": 164390 }, { "epoch": 39.47, "learning_rate": 5.4766878679362523e-05, "loss": 0.0245, "step": 164400 }, { "epoch": 39.47, "learning_rate": 5.476241213438376e-05, "loss": 0.0156, "step": 164410 }, { "epoch": 39.47, "learning_rate": 5.4757945551052655e-05, "loss": 0.0142, "step": 164420 }, { "epoch": 39.47, "learning_rate": 5.4753478929405136e-05, "loss": 0.0203, "step": 164430 }, { "epoch": 39.48, "learning_rate": 5.474901226947721e-05, "loss": 0.0089, "step": 164440 }, { "epoch": 39.48, "learning_rate": 5.474454557130483e-05, "loss": 0.0047, "step": 164450 }, { "epoch": 39.48, "learning_rate": 5.474007883492397e-05, "loss": 0.0468, "step": 164460 }, { "epoch": 39.48, "learning_rate": 5.47356120603706e-05, "loss": 0.0196, "step": 164470 }, { "epoch": 39.49, "learning_rate": 5.473114524768068e-05, "loss": 0.0213, "step": 164480 }, { "epoch": 39.49, "learning_rate": 5.4726678396890215e-05, "loss": 0.0211, "step": 164490 }, { "epoch": 39.49, "learning_rate": 5.4722211508035135e-05, "loss": 0.0103, "step": 164500 }, { "epoch": 39.49, "learning_rate": 5.471774458115145e-05, "loss": 0.016, "step": 164510 }, { "epoch": 39.49, "learning_rate": 5.471327761627512e-05, "loss": 0.0269, "step": 164520 }, { "epoch": 39.5, "learning_rate": 5.47088106134421e-05, "loss": 0.0171, "step": 164530 }, { "epoch": 39.5, "learning_rate": 5.470434357268839e-05, "loss": 0.0256, "step": 164540 }, { "epoch": 39.5, "learning_rate": 5.469987649404994e-05, "loss": 0.0185, "step": 164550 }, { "epoch": 39.5, "learning_rate": 5.469540937756276e-05, "loss": 0.0145, "step": 164560 }, { "epoch": 39.51, "learning_rate": 5.4690942223262764e-05, "loss": 0.0203, "step": 164570 }, { "epoch": 39.51, "learning_rate": 5.468647503118598e-05, "loss": 0.0196, "step": 164580 }, { "epoch": 39.51, "learning_rate": 5.468200780136837e-05, "loss": 0.0215, "step": 164590 }, { "epoch": 39.51, "learning_rate": 5.467754053384589e-05, "loss": 0.0138, "step": 164600 }, { "epoch": 39.51, "learning_rate": 5.467307322865456e-05, "loss": 0.0077, "step": 164610 }, { "epoch": 39.52, "learning_rate": 5.4668605885830296e-05, "loss": 0.0262, "step": 164620 }, { "epoch": 39.52, "learning_rate": 5.4664138505409125e-05, "loss": 0.0083, "step": 164630 }, { "epoch": 39.52, "learning_rate": 5.465967108742699e-05, "loss": 0.0086, "step": 164640 }, { "epoch": 39.52, "learning_rate": 5.4655203631919884e-05, "loss": 0.0229, "step": 164650 }, { "epoch": 39.53, "learning_rate": 5.4650736138923785e-05, "loss": 0.0101, "step": 164660 }, { "epoch": 39.53, "learning_rate": 5.464626860847465e-05, "loss": 0.0194, "step": 164670 }, { "epoch": 39.53, "learning_rate": 5.46418010406085e-05, "loss": 0.0157, "step": 164680 }, { "epoch": 39.53, "learning_rate": 5.463733343536126e-05, "loss": 0.0349, "step": 164690 }, { "epoch": 39.54, "learning_rate": 5.463286579276894e-05, "loss": 0.0102, "step": 164700 }, { "epoch": 39.54, "learning_rate": 5.462839811286752e-05, "loss": 0.0331, "step": 164710 }, { "epoch": 39.54, "learning_rate": 5.462393039569296e-05, "loss": 0.0308, "step": 164720 }, { "epoch": 39.54, "learning_rate": 5.461946264128126e-05, "loss": 0.0403, "step": 164730 }, { "epoch": 39.54, "learning_rate": 5.461499484966838e-05, "loss": 0.031, "step": 164740 }, { "epoch": 39.55, "learning_rate": 5.461052702089032e-05, "loss": 0.0316, "step": 164750 }, { "epoch": 39.55, "learning_rate": 5.4606059154983035e-05, "loss": 0.0123, "step": 164760 }, { "epoch": 39.55, "learning_rate": 5.460159125198253e-05, "loss": 0.0129, "step": 164770 }, { "epoch": 39.55, "learning_rate": 5.459712331192478e-05, "loss": 0.0227, "step": 164780 }, { "epoch": 39.56, "learning_rate": 5.4592655334845745e-05, "loss": 0.0201, "step": 164790 }, { "epoch": 39.56, "learning_rate": 5.4588187320781445e-05, "loss": 0.0329, "step": 164800 }, { "epoch": 39.56, "learning_rate": 5.458371926976782e-05, "loss": 0.0209, "step": 164810 }, { "epoch": 39.56, "learning_rate": 5.4579251181840884e-05, "loss": 0.0169, "step": 164820 }, { "epoch": 39.57, "learning_rate": 5.45747830570366e-05, "loss": 0.0316, "step": 164830 }, { "epoch": 39.57, "learning_rate": 5.457031489539095e-05, "loss": 0.0147, "step": 164840 }, { "epoch": 39.57, "learning_rate": 5.456584669693994e-05, "loss": 0.0214, "step": 164850 }, { "epoch": 39.57, "learning_rate": 5.456137846171951e-05, "loss": 0.0269, "step": 164860 }, { "epoch": 39.57, "learning_rate": 5.455691018976571e-05, "loss": 0.029, "step": 164870 }, { "epoch": 39.58, "learning_rate": 5.4552441881114445e-05, "loss": 0.025, "step": 164880 }, { "epoch": 39.58, "learning_rate": 5.4547973535801756e-05, "loss": 0.0169, "step": 164890 }, { "epoch": 39.58, "learning_rate": 5.454350515386359e-05, "loss": 0.0168, "step": 164900 }, { "epoch": 39.58, "learning_rate": 5.453903673533596e-05, "loss": 0.0255, "step": 164910 }, { "epoch": 39.59, "learning_rate": 5.453456828025486e-05, "loss": 0.0114, "step": 164920 }, { "epoch": 39.59, "learning_rate": 5.453009978865623e-05, "loss": 0.0167, "step": 164930 }, { "epoch": 39.59, "learning_rate": 5.4525631260576096e-05, "loss": 0.0178, "step": 164940 }, { "epoch": 39.59, "learning_rate": 5.452116269605042e-05, "loss": 0.0178, "step": 164950 }, { "epoch": 39.59, "learning_rate": 5.451669409511518e-05, "loss": 0.0149, "step": 164960 }, { "epoch": 39.6, "learning_rate": 5.451222545780642e-05, "loss": 0.0315, "step": 164970 }, { "epoch": 39.6, "learning_rate": 5.450775678416005e-05, "loss": 0.0194, "step": 164980 }, { "epoch": 39.6, "learning_rate": 5.4503288074212125e-05, "loss": 0.0104, "step": 164990 }, { "epoch": 39.6, "learning_rate": 5.449881932799856e-05, "loss": 0.0167, "step": 165000 }, { "epoch": 39.61, "learning_rate": 5.44943505455554e-05, "loss": 0.0255, "step": 165010 }, { "epoch": 39.61, "learning_rate": 5.448988172691862e-05, "loss": 0.0197, "step": 165020 }, { "epoch": 39.61, "learning_rate": 5.4485412872124196e-05, "loss": 0.0172, "step": 165030 }, { "epoch": 39.61, "learning_rate": 5.448094398120814e-05, "loss": 0.0179, "step": 165040 }, { "epoch": 39.62, "learning_rate": 5.44764750542064e-05, "loss": 0.0204, "step": 165050 }, { "epoch": 39.62, "learning_rate": 5.4472006091155e-05, "loss": 0.0126, "step": 165060 }, { "epoch": 39.62, "learning_rate": 5.446753709208992e-05, "loss": 0.009, "step": 165070 }, { "epoch": 39.62, "learning_rate": 5.4463068057047137e-05, "loss": 0.02, "step": 165080 }, { "epoch": 39.62, "learning_rate": 5.445859898606266e-05, "loss": 0.017, "step": 165090 }, { "epoch": 39.63, "learning_rate": 5.445412987917246e-05, "loss": 0.0415, "step": 165100 }, { "epoch": 39.63, "learning_rate": 5.444966073641256e-05, "loss": 0.0132, "step": 165110 }, { "epoch": 39.63, "learning_rate": 5.4445191557818894e-05, "loss": 0.0127, "step": 165120 }, { "epoch": 39.63, "learning_rate": 5.4440722343427505e-05, "loss": 0.0203, "step": 165130 }, { "epoch": 39.64, "learning_rate": 5.443625309327437e-05, "loss": 0.0161, "step": 165140 }, { "epoch": 39.64, "learning_rate": 5.443178380739547e-05, "loss": 0.0345, "step": 165150 }, { "epoch": 39.64, "learning_rate": 5.442731448582681e-05, "loss": 0.0161, "step": 165160 }, { "epoch": 39.64, "learning_rate": 5.442284512860436e-05, "loss": 0.0271, "step": 165170 }, { "epoch": 39.65, "learning_rate": 5.441837573576415e-05, "loss": 0.0149, "step": 165180 }, { "epoch": 39.65, "learning_rate": 5.4413906307342124e-05, "loss": 0.015, "step": 165190 }, { "epoch": 39.65, "learning_rate": 5.440943684337432e-05, "loss": 0.0239, "step": 165200 }, { "epoch": 39.65, "learning_rate": 5.4404967343896706e-05, "loss": 0.0107, "step": 165210 }, { "epoch": 39.65, "learning_rate": 5.4400497808945285e-05, "loss": 0.0106, "step": 165220 }, { "epoch": 39.66, "learning_rate": 5.439602823855604e-05, "loss": 0.0111, "step": 165230 }, { "epoch": 39.66, "learning_rate": 5.4391558632764973e-05, "loss": 0.0199, "step": 165240 }, { "epoch": 39.66, "learning_rate": 5.438708899160808e-05, "loss": 0.0213, "step": 165250 }, { "epoch": 39.66, "learning_rate": 5.4382619315121364e-05, "loss": 0.0174, "step": 165260 }, { "epoch": 39.67, "learning_rate": 5.43781496033408e-05, "loss": 0.0133, "step": 165270 }, { "epoch": 39.67, "learning_rate": 5.4373679856302395e-05, "loss": 0.0172, "step": 165280 }, { "epoch": 39.67, "learning_rate": 5.436921007404213e-05, "loss": 0.0142, "step": 165290 }, { "epoch": 39.67, "learning_rate": 5.4364740256596035e-05, "loss": 0.0185, "step": 165300 }, { "epoch": 39.67, "learning_rate": 5.436027040400007e-05, "loss": 0.0175, "step": 165310 }, { "epoch": 39.68, "learning_rate": 5.4355800516290256e-05, "loss": 0.0124, "step": 165320 }, { "epoch": 39.68, "learning_rate": 5.435133059350257e-05, "loss": 0.009, "step": 165330 }, { "epoch": 39.68, "learning_rate": 5.434686063567302e-05, "loss": 0.0207, "step": 165340 }, { "epoch": 39.68, "learning_rate": 5.4342390642837606e-05, "loss": 0.0285, "step": 165350 }, { "epoch": 39.69, "learning_rate": 5.433792061503231e-05, "loss": 0.0169, "step": 165360 }, { "epoch": 39.69, "learning_rate": 5.433345055229314e-05, "loss": 0.0233, "step": 165370 }, { "epoch": 39.69, "learning_rate": 5.432898045465611e-05, "loss": 0.0341, "step": 165380 }, { "epoch": 39.69, "learning_rate": 5.4324510322157196e-05, "loss": 0.0176, "step": 165390 }, { "epoch": 39.7, "learning_rate": 5.432004015483241e-05, "loss": 0.016, "step": 165400 }, { "epoch": 39.7, "learning_rate": 5.431556995271772e-05, "loss": 0.0127, "step": 165410 }, { "epoch": 39.7, "learning_rate": 5.431109971584918e-05, "loss": 0.0208, "step": 165420 }, { "epoch": 39.7, "learning_rate": 5.4306629444262735e-05, "loss": 0.0194, "step": 165430 }, { "epoch": 39.7, "learning_rate": 5.430215913799441e-05, "loss": 0.0119, "step": 165440 }, { "epoch": 39.71, "learning_rate": 5.429768879708022e-05, "loss": 0.0156, "step": 165450 }, { "epoch": 39.71, "learning_rate": 5.4293218421556134e-05, "loss": 0.0202, "step": 165460 }, { "epoch": 39.71, "learning_rate": 5.428874801145818e-05, "loss": 0.0169, "step": 165470 }, { "epoch": 39.71, "learning_rate": 5.428427756682234e-05, "loss": 0.0162, "step": 165480 }, { "epoch": 39.72, "learning_rate": 5.427980708768461e-05, "loss": 0.0238, "step": 165490 }, { "epoch": 39.72, "learning_rate": 5.4275336574081015e-05, "loss": 0.022, "step": 165500 }, { "epoch": 39.72, "learning_rate": 5.427086602604754e-05, "loss": 0.0106, "step": 165510 }, { "epoch": 39.72, "learning_rate": 5.4266395443620197e-05, "loss": 0.0084, "step": 165520 }, { "epoch": 39.73, "learning_rate": 5.426192482683499e-05, "loss": 0.02, "step": 165530 }, { "epoch": 39.73, "learning_rate": 5.4257454175727896e-05, "loss": 0.0133, "step": 165540 }, { "epoch": 39.73, "learning_rate": 5.425298349033494e-05, "loss": 0.007, "step": 165550 }, { "epoch": 39.73, "learning_rate": 5.424851277069212e-05, "loss": 0.0164, "step": 165560 }, { "epoch": 39.73, "learning_rate": 5.424404201683545e-05, "loss": 0.0192, "step": 165570 }, { "epoch": 39.74, "learning_rate": 5.423957122880092e-05, "loss": 0.0102, "step": 165580 }, { "epoch": 39.74, "learning_rate": 5.423510040662454e-05, "loss": 0.0172, "step": 165590 }, { "epoch": 39.74, "learning_rate": 5.4230629550342305e-05, "loss": 0.0152, "step": 165600 }, { "epoch": 39.74, "learning_rate": 5.422615865999022e-05, "loss": 0.0197, "step": 165610 }, { "epoch": 39.75, "learning_rate": 5.42216877356043e-05, "loss": 0.0094, "step": 165620 }, { "epoch": 39.75, "learning_rate": 5.4217216777220556e-05, "loss": 0.028, "step": 165630 }, { "epoch": 39.75, "learning_rate": 5.421274578487497e-05, "loss": 0.0215, "step": 165640 }, { "epoch": 39.75, "learning_rate": 5.420827475860357e-05, "loss": 0.0191, "step": 165650 }, { "epoch": 39.75, "learning_rate": 5.4203803698442354e-05, "loss": 0.0092, "step": 165660 }, { "epoch": 39.76, "learning_rate": 5.4199332604427324e-05, "loss": 0.012, "step": 165670 }, { "epoch": 39.76, "learning_rate": 5.4194861476594484e-05, "loss": 0.0167, "step": 165680 }, { "epoch": 39.76, "learning_rate": 5.419039031497984e-05, "loss": 0.0168, "step": 165690 }, { "epoch": 39.76, "learning_rate": 5.418591911961942e-05, "loss": 0.0358, "step": 165700 }, { "epoch": 39.77, "learning_rate": 5.418144789054921e-05, "loss": 0.0459, "step": 165710 }, { "epoch": 39.77, "learning_rate": 5.417697662780522e-05, "loss": 0.0179, "step": 165720 }, { "epoch": 39.77, "learning_rate": 5.4172505331423464e-05, "loss": 0.0202, "step": 165730 }, { "epoch": 39.77, "learning_rate": 5.416803400143995e-05, "loss": 0.015, "step": 165740 }, { "epoch": 39.78, "learning_rate": 5.416356263789066e-05, "loss": 0.0311, "step": 165750 }, { "epoch": 39.78, "learning_rate": 5.4159091240811646e-05, "loss": 0.022, "step": 165760 }, { "epoch": 39.78, "learning_rate": 5.41546198102389e-05, "loss": 0.0348, "step": 165770 }, { "epoch": 39.78, "learning_rate": 5.415014834620842e-05, "loss": 0.0181, "step": 165780 }, { "epoch": 39.78, "learning_rate": 5.414567684875622e-05, "loss": 0.0207, "step": 165790 }, { "epoch": 39.79, "learning_rate": 5.414120531791831e-05, "loss": 0.0174, "step": 165800 }, { "epoch": 39.79, "learning_rate": 5.4136733753730706e-05, "loss": 0.0316, "step": 165810 }, { "epoch": 39.79, "learning_rate": 5.4132262156229406e-05, "loss": 0.03, "step": 165820 }, { "epoch": 39.79, "learning_rate": 5.412779052545044e-05, "loss": 0.0211, "step": 165830 }, { "epoch": 39.8, "learning_rate": 5.4123318861429804e-05, "loss": 0.0206, "step": 165840 }, { "epoch": 39.8, "learning_rate": 5.411884716420351e-05, "loss": 0.011, "step": 165850 }, { "epoch": 39.8, "learning_rate": 5.4114375433807575e-05, "loss": 0.0231, "step": 165860 }, { "epoch": 39.8, "learning_rate": 5.4109903670278e-05, "loss": 0.0171, "step": 165870 }, { "epoch": 39.81, "learning_rate": 5.4105431873650805e-05, "loss": 0.0189, "step": 165880 }, { "epoch": 39.81, "learning_rate": 5.4100960043962e-05, "loss": 0.0149, "step": 165890 }, { "epoch": 39.81, "learning_rate": 5.409648818124761e-05, "loss": 0.0243, "step": 165900 }, { "epoch": 39.81, "learning_rate": 5.409201628554362e-05, "loss": 0.033, "step": 165910 }, { "epoch": 39.81, "learning_rate": 5.408754435688606e-05, "loss": 0.0286, "step": 165920 }, { "epoch": 39.82, "learning_rate": 5.4083072395310955e-05, "loss": 0.013, "step": 165930 }, { "epoch": 39.82, "learning_rate": 5.407860040085427e-05, "loss": 0.0104, "step": 165940 }, { "epoch": 39.82, "learning_rate": 5.407412837355209e-05, "loss": 0.0143, "step": 165950 }, { "epoch": 39.82, "learning_rate": 5.4069656313440376e-05, "loss": 0.0206, "step": 165960 }, { "epoch": 39.83, "learning_rate": 5.4065184220555163e-05, "loss": 0.0181, "step": 165970 }, { "epoch": 39.83, "learning_rate": 5.406071209493245e-05, "loss": 0.0178, "step": 165980 }, { "epoch": 39.83, "learning_rate": 5.4056239936608266e-05, "loss": 0.0105, "step": 165990 }, { "epoch": 39.83, "learning_rate": 5.4051767745618634e-05, "loss": 0.0206, "step": 166000 }, { "epoch": 39.83, "learning_rate": 5.4047295521999544e-05, "loss": 0.0208, "step": 166010 }, { "epoch": 39.84, "learning_rate": 5.4042823265787026e-05, "loss": 0.0121, "step": 166020 }, { "epoch": 39.84, "learning_rate": 5.4038350977017096e-05, "loss": 0.0068, "step": 166030 }, { "epoch": 39.84, "learning_rate": 5.403387865572577e-05, "loss": 0.014, "step": 166040 }, { "epoch": 39.84, "learning_rate": 5.4029406301949056e-05, "loss": 0.0181, "step": 166050 }, { "epoch": 39.85, "learning_rate": 5.402493391572298e-05, "loss": 0.0292, "step": 166060 }, { "epoch": 39.85, "learning_rate": 5.4020461497083564e-05, "loss": 0.0204, "step": 166070 }, { "epoch": 39.85, "learning_rate": 5.4015989046066804e-05, "loss": 0.0153, "step": 166080 }, { "epoch": 39.85, "learning_rate": 5.4011516562708734e-05, "loss": 0.0139, "step": 166090 }, { "epoch": 39.86, "learning_rate": 5.4007044047045376e-05, "loss": 0.0159, "step": 166100 }, { "epoch": 39.86, "learning_rate": 5.400257149911272e-05, "loss": 0.0219, "step": 166110 }, { "epoch": 39.86, "learning_rate": 5.3998098918946826e-05, "loss": 0.015, "step": 166120 }, { "epoch": 39.86, "learning_rate": 5.3993626306583665e-05, "loss": 0.0107, "step": 166130 }, { "epoch": 39.86, "learning_rate": 5.39891536620593e-05, "loss": 0.0231, "step": 166140 }, { "epoch": 39.87, "learning_rate": 5.398468098540972e-05, "loss": 0.0175, "step": 166150 }, { "epoch": 39.87, "learning_rate": 5.398020827667095e-05, "loss": 0.0208, "step": 166160 }, { "epoch": 39.87, "learning_rate": 5.397573553587902e-05, "loss": 0.0353, "step": 166170 }, { "epoch": 39.87, "learning_rate": 5.397126276306994e-05, "loss": 0.0172, "step": 166180 }, { "epoch": 39.88, "learning_rate": 5.396678995827975e-05, "loss": 0.0097, "step": 166190 }, { "epoch": 39.88, "learning_rate": 5.396231712154443e-05, "loss": 0.0143, "step": 166200 }, { "epoch": 39.88, "learning_rate": 5.3957844252900024e-05, "loss": 0.0232, "step": 166210 }, { "epoch": 39.88, "learning_rate": 5.3953371352382564e-05, "loss": 0.0138, "step": 166220 }, { "epoch": 39.89, "learning_rate": 5.394889842002805e-05, "loss": 0.0114, "step": 166230 }, { "epoch": 39.89, "learning_rate": 5.394442545587253e-05, "loss": 0.0234, "step": 166240 }, { "epoch": 39.89, "learning_rate": 5.393995245995198e-05, "loss": 0.0244, "step": 166250 }, { "epoch": 39.89, "learning_rate": 5.393547943230247e-05, "loss": 0.0086, "step": 166260 }, { "epoch": 39.89, "learning_rate": 5.393100637295998e-05, "loss": 0.0143, "step": 166270 }, { "epoch": 39.9, "learning_rate": 5.392653328196058e-05, "loss": 0.023, "step": 166280 }, { "epoch": 39.9, "learning_rate": 5.392206015934025e-05, "loss": 0.0099, "step": 166290 }, { "epoch": 39.9, "learning_rate": 5.391758700513502e-05, "loss": 0.0127, "step": 166300 }, { "epoch": 39.9, "learning_rate": 5.391311381938093e-05, "loss": 0.03, "step": 166310 }, { "epoch": 39.91, "learning_rate": 5.390864060211399e-05, "loss": 0.0131, "step": 166320 }, { "epoch": 39.91, "learning_rate": 5.390416735337024e-05, "loss": 0.0209, "step": 166330 }, { "epoch": 39.91, "learning_rate": 5.389969407318568e-05, "loss": 0.0189, "step": 166340 }, { "epoch": 39.91, "learning_rate": 5.3895220761596346e-05, "loss": 0.0189, "step": 166350 }, { "epoch": 39.91, "learning_rate": 5.3890747418638266e-05, "loss": 0.013, "step": 166360 }, { "epoch": 39.92, "learning_rate": 5.388627404434745e-05, "loss": 0.0231, "step": 166370 }, { "epoch": 39.92, "learning_rate": 5.388180063875995e-05, "loss": 0.0238, "step": 166380 }, { "epoch": 39.92, "learning_rate": 5.387732720191175e-05, "loss": 0.0103, "step": 166390 }, { "epoch": 39.92, "learning_rate": 5.387285373383892e-05, "loss": 0.0248, "step": 166400 }, { "epoch": 39.93, "learning_rate": 5.3868380234577466e-05, "loss": 0.0149, "step": 166410 }, { "epoch": 39.93, "learning_rate": 5.386390670416339e-05, "loss": 0.0185, "step": 166420 }, { "epoch": 39.93, "learning_rate": 5.3859433142632764e-05, "loss": 0.0106, "step": 166430 }, { "epoch": 39.93, "learning_rate": 5.385495955002157e-05, "loss": 0.0188, "step": 166440 }, { "epoch": 39.94, "learning_rate": 5.385048592636586e-05, "loss": 0.0402, "step": 166450 }, { "epoch": 39.94, "learning_rate": 5.384601227170166e-05, "loss": 0.0178, "step": 166460 }, { "epoch": 39.94, "learning_rate": 5.3841538586064996e-05, "loss": 0.0195, "step": 166470 }, { "epoch": 39.94, "learning_rate": 5.3837064869491885e-05, "loss": 0.0104, "step": 166480 }, { "epoch": 39.94, "learning_rate": 5.383259112201835e-05, "loss": 0.0174, "step": 166490 }, { "epoch": 39.95, "learning_rate": 5.382811734368046e-05, "loss": 0.0243, "step": 166500 }, { "epoch": 39.95, "learning_rate": 5.382364353451418e-05, "loss": 0.0115, "step": 166510 }, { "epoch": 39.95, "learning_rate": 5.381916969455558e-05, "loss": 0.0116, "step": 166520 }, { "epoch": 40.0, "learning_rate": 5.381469582384069e-05, "loss": 0.0083, "step": 166530 }, { "epoch": 40.0, "learning_rate": 5.381022192240551e-05, "loss": 0.019, "step": 166540 }, { "epoch": 40.01, "learning_rate": 5.3805747990286115e-05, "loss": 0.0307, "step": 166550 }, { "epoch": 40.01, "learning_rate": 5.380127402751848e-05, "loss": 0.0086, "step": 166560 }, { "epoch": 40.01, "learning_rate": 5.379680003413869e-05, "loss": 0.0194, "step": 166570 }, { "epoch": 40.01, "learning_rate": 5.379232601018271e-05, "loss": 0.0088, "step": 166580 }, { "epoch": 40.02, "learning_rate": 5.378785195568662e-05, "loss": 0.0252, "step": 166590 }, { "epoch": 40.02, "learning_rate": 5.378337787068644e-05, "loss": 0.0151, "step": 166600 }, { "epoch": 40.02, "learning_rate": 5.3778903755218177e-05, "loss": 0.0109, "step": 166610 }, { "epoch": 40.02, "learning_rate": 5.377442960931791e-05, "loss": 0.0131, "step": 166620 }, { "epoch": 40.03, "learning_rate": 5.376995543302161e-05, "loss": 0.0098, "step": 166630 }, { "epoch": 40.03, "learning_rate": 5.3765481226365354e-05, "loss": 0.0088, "step": 166640 }, { "epoch": 40.03, "learning_rate": 5.376100698938517e-05, "loss": 0.0157, "step": 166650 }, { "epoch": 40.03, "learning_rate": 5.375653272211706e-05, "loss": 0.007, "step": 166660 }, { "epoch": 40.03, "learning_rate": 5.3752058424597086e-05, "loss": 0.0089, "step": 166670 }, { "epoch": 40.04, "learning_rate": 5.374758409686125e-05, "loss": 0.027, "step": 166680 }, { "epoch": 40.04, "learning_rate": 5.3743109738945616e-05, "loss": 0.0137, "step": 166690 }, { "epoch": 40.04, "learning_rate": 5.3738635350886193e-05, "loss": 0.0191, "step": 166700 }, { "epoch": 40.04, "learning_rate": 5.3734160932719026e-05, "loss": 0.0232, "step": 166710 }, { "epoch": 40.05, "learning_rate": 5.372968648448015e-05, "loss": 0.0075, "step": 166720 }, { "epoch": 40.05, "learning_rate": 5.372521200620559e-05, "loss": 0.0093, "step": 166730 }, { "epoch": 40.05, "learning_rate": 5.3720737497931384e-05, "loss": 0.0102, "step": 166740 }, { "epoch": 40.05, "learning_rate": 5.371626295969356e-05, "loss": 0.0117, "step": 166750 }, { "epoch": 40.05, "learning_rate": 5.371178839152816e-05, "loss": 0.0113, "step": 166760 }, { "epoch": 40.06, "learning_rate": 5.370731379347123e-05, "loss": 0.0122, "step": 166770 }, { "epoch": 40.06, "learning_rate": 5.370283916555878e-05, "loss": 0.0142, "step": 166780 }, { "epoch": 40.06, "learning_rate": 5.369836450782686e-05, "loss": 0.0059, "step": 166790 }, { "epoch": 40.06, "learning_rate": 5.369388982031149e-05, "loss": 0.0074, "step": 166800 }, { "epoch": 40.07, "learning_rate": 5.368941510304872e-05, "loss": 0.0088, "step": 166810 }, { "epoch": 40.07, "learning_rate": 5.368494035607457e-05, "loss": 0.0166, "step": 166820 }, { "epoch": 40.07, "learning_rate": 5.36804655794251e-05, "loss": 0.0201, "step": 166830 }, { "epoch": 40.07, "learning_rate": 5.367599077313633e-05, "loss": 0.0218, "step": 166840 }, { "epoch": 40.08, "learning_rate": 5.36715159372443e-05, "loss": 0.0269, "step": 166850 }, { "epoch": 40.08, "learning_rate": 5.366704107178504e-05, "loss": 0.0238, "step": 166860 }, { "epoch": 40.08, "learning_rate": 5.366256617679459e-05, "loss": 0.0101, "step": 166870 }, { "epoch": 40.08, "learning_rate": 5.365809125230899e-05, "loss": 0.0064, "step": 166880 }, { "epoch": 40.08, "learning_rate": 5.3653616298364294e-05, "loss": 0.0108, "step": 166890 }, { "epoch": 40.09, "learning_rate": 5.364914131499651e-05, "loss": 0.0142, "step": 166900 }, { "epoch": 40.09, "learning_rate": 5.364466630224168e-05, "loss": 0.0072, "step": 166910 }, { "epoch": 40.09, "learning_rate": 5.3640191260135863e-05, "loss": 0.0258, "step": 166920 }, { "epoch": 40.09, "learning_rate": 5.363571618871507e-05, "loss": 0.011, "step": 166930 }, { "epoch": 40.1, "learning_rate": 5.363124108801535e-05, "loss": 0.0131, "step": 166940 }, { "epoch": 40.1, "learning_rate": 5.362676595807276e-05, "loss": 0.013, "step": 166950 }, { "epoch": 40.1, "learning_rate": 5.3622290798923315e-05, "loss": 0.0202, "step": 166960 }, { "epoch": 40.1, "learning_rate": 5.361781561060306e-05, "loss": 0.0186, "step": 166970 }, { "epoch": 40.11, "learning_rate": 5.361334039314804e-05, "loss": 0.0275, "step": 166980 }, { "epoch": 40.11, "learning_rate": 5.360886514659429e-05, "loss": 0.0157, "step": 166990 }, { "epoch": 40.11, "learning_rate": 5.3604389870977845e-05, "loss": 0.035, "step": 167000 }, { "epoch": 40.11, "learning_rate": 5.359991456633475e-05, "loss": 0.0155, "step": 167010 }, { "epoch": 40.11, "learning_rate": 5.359543923270105e-05, "loss": 0.0165, "step": 167020 }, { "epoch": 40.12, "learning_rate": 5.359096387011279e-05, "loss": 0.008, "step": 167030 }, { "epoch": 40.12, "learning_rate": 5.358648847860599e-05, "loss": 0.0253, "step": 167040 }, { "epoch": 40.12, "learning_rate": 5.3582013058216715e-05, "loss": 0.0139, "step": 167050 }, { "epoch": 40.12, "learning_rate": 5.3577537608980986e-05, "loss": 0.0583, "step": 167060 }, { "epoch": 40.13, "learning_rate": 5.357306213093485e-05, "loss": 0.0179, "step": 167070 }, { "epoch": 40.13, "learning_rate": 5.356858662411435e-05, "loss": 0.0217, "step": 167080 }, { "epoch": 40.13, "learning_rate": 5.3564111088555534e-05, "loss": 0.0168, "step": 167090 }, { "epoch": 40.13, "learning_rate": 5.355963552429445e-05, "loss": 0.0202, "step": 167100 }, { "epoch": 40.13, "learning_rate": 5.355515993136712e-05, "loss": 0.0167, "step": 167110 }, { "epoch": 40.14, "learning_rate": 5.35506843098096e-05, "loss": 0.0116, "step": 167120 }, { "epoch": 40.14, "learning_rate": 5.3546208659657924e-05, "loss": 0.0167, "step": 167130 }, { "epoch": 40.14, "learning_rate": 5.3541732980948135e-05, "loss": 0.0224, "step": 167140 }, { "epoch": 40.14, "learning_rate": 5.3537257273716294e-05, "loss": 0.0348, "step": 167150 }, { "epoch": 40.15, "learning_rate": 5.353278153799842e-05, "loss": 0.0177, "step": 167160 }, { "epoch": 40.15, "learning_rate": 5.352830577383058e-05, "loss": 0.0136, "step": 167170 }, { "epoch": 40.15, "learning_rate": 5.35238299812488e-05, "loss": 0.0166, "step": 167180 }, { "epoch": 40.15, "learning_rate": 5.3519354160289115e-05, "loss": 0.0214, "step": 167190 }, { "epoch": 40.16, "learning_rate": 5.35148783109876e-05, "loss": 0.0205, "step": 167200 }, { "epoch": 40.16, "learning_rate": 5.351040243338029e-05, "loss": 0.0068, "step": 167210 }, { "epoch": 40.16, "learning_rate": 5.350592652750322e-05, "loss": 0.014, "step": 167220 }, { "epoch": 40.16, "learning_rate": 5.350145059339244e-05, "loss": 0.0115, "step": 167230 }, { "epoch": 40.16, "learning_rate": 5.3496974631084007e-05, "loss": 0.0288, "step": 167240 }, { "epoch": 40.17, "learning_rate": 5.349249864061394e-05, "loss": 0.0224, "step": 167250 }, { "epoch": 40.17, "learning_rate": 5.34880226220183e-05, "loss": 0.0139, "step": 167260 }, { "epoch": 40.17, "learning_rate": 5.348354657533313e-05, "loss": 0.0187, "step": 167270 }, { "epoch": 40.17, "learning_rate": 5.3479070500594485e-05, "loss": 0.0111, "step": 167280 }, { "epoch": 40.18, "learning_rate": 5.347459439783841e-05, "loss": 0.0145, "step": 167290 }, { "epoch": 40.18, "learning_rate": 5.3470118267100934e-05, "loss": 0.0152, "step": 167300 }, { "epoch": 40.18, "learning_rate": 5.346564210841811e-05, "loss": 0.0137, "step": 167310 }, { "epoch": 40.18, "learning_rate": 5.346116592182602e-05, "loss": 0.0148, "step": 167320 }, { "epoch": 40.19, "learning_rate": 5.345668970736065e-05, "loss": 0.0143, "step": 167330 }, { "epoch": 40.19, "learning_rate": 5.34522134650581e-05, "loss": 0.0108, "step": 167340 }, { "epoch": 40.19, "learning_rate": 5.344773719495439e-05, "loss": 0.0219, "step": 167350 }, { "epoch": 40.19, "learning_rate": 5.344326089708559e-05, "loss": 0.0179, "step": 167360 }, { "epoch": 40.19, "learning_rate": 5.343878457148773e-05, "loss": 0.0134, "step": 167370 }, { "epoch": 40.2, "learning_rate": 5.343430821819685e-05, "loss": 0.0212, "step": 167380 }, { "epoch": 40.2, "learning_rate": 5.342983183724903e-05, "loss": 0.0292, "step": 167390 }, { "epoch": 40.2, "learning_rate": 5.3425355428680293e-05, "loss": 0.023, "step": 167400 }, { "epoch": 40.2, "learning_rate": 5.342087899252669e-05, "loss": 0.0133, "step": 167410 }, { "epoch": 40.21, "learning_rate": 5.341640252882428e-05, "loss": 0.0127, "step": 167420 }, { "epoch": 40.21, "learning_rate": 5.341192603760912e-05, "loss": 0.0202, "step": 167430 }, { "epoch": 40.21, "learning_rate": 5.340744951891723e-05, "loss": 0.0102, "step": 167440 }, { "epoch": 40.21, "learning_rate": 5.340297297278468e-05, "loss": 0.0198, "step": 167450 }, { "epoch": 40.21, "learning_rate": 5.3398496399247546e-05, "loss": 0.0381, "step": 167460 }, { "epoch": 40.22, "learning_rate": 5.339401979834181e-05, "loss": 0.0138, "step": 167470 }, { "epoch": 40.22, "learning_rate": 5.3389543170103595e-05, "loss": 0.0693, "step": 167480 }, { "epoch": 40.22, "learning_rate": 5.33850665145689e-05, "loss": 0.0084, "step": 167490 }, { "epoch": 40.22, "learning_rate": 5.338058983177381e-05, "loss": 0.0112, "step": 167500 }, { "epoch": 40.23, "learning_rate": 5.337611312175437e-05, "loss": 0.0142, "step": 167510 }, { "epoch": 40.23, "learning_rate": 5.337163638454661e-05, "loss": 0.0146, "step": 167520 }, { "epoch": 40.23, "learning_rate": 5.33671596201866e-05, "loss": 0.0111, "step": 167530 }, { "epoch": 40.23, "learning_rate": 5.33626828287104e-05, "loss": 0.0326, "step": 167540 }, { "epoch": 40.24, "learning_rate": 5.3358206010154045e-05, "loss": 0.0151, "step": 167550 }, { "epoch": 40.24, "learning_rate": 5.335372916455359e-05, "loss": 0.0198, "step": 167560 }, { "epoch": 40.24, "learning_rate": 5.334925229194509e-05, "loss": 0.0154, "step": 167570 }, { "epoch": 40.24, "learning_rate": 5.33447753923646e-05, "loss": 0.0145, "step": 167580 }, { "epoch": 40.24, "learning_rate": 5.334029846584817e-05, "loss": 0.0121, "step": 167590 }, { "epoch": 40.25, "learning_rate": 5.333582151243186e-05, "loss": 0.0082, "step": 167600 }, { "epoch": 40.25, "learning_rate": 5.333134453215172e-05, "loss": 0.019, "step": 167610 }, { "epoch": 40.25, "learning_rate": 5.332686752504379e-05, "loss": 0.0161, "step": 167620 }, { "epoch": 40.25, "learning_rate": 5.3322390491144156e-05, "loss": 0.0204, "step": 167630 }, { "epoch": 40.26, "learning_rate": 5.331791343048883e-05, "loss": 0.0205, "step": 167640 }, { "epoch": 40.26, "learning_rate": 5.331343634311392e-05, "loss": 0.0164, "step": 167650 }, { "epoch": 40.26, "learning_rate": 5.3308959229055424e-05, "loss": 0.0161, "step": 167660 }, { "epoch": 40.26, "learning_rate": 5.330448208834943e-05, "loss": 0.0277, "step": 167670 }, { "epoch": 40.27, "learning_rate": 5.3300004921031974e-05, "loss": 0.0366, "step": 167680 }, { "epoch": 40.27, "learning_rate": 5.3295527727139125e-05, "loss": 0.0084, "step": 167690 }, { "epoch": 40.27, "learning_rate": 5.3291050506706966e-05, "loss": 0.0086, "step": 167700 }, { "epoch": 40.27, "learning_rate": 5.328657325977149e-05, "loss": 0.0324, "step": 167710 }, { "epoch": 40.27, "learning_rate": 5.3282095986368806e-05, "loss": 0.0228, "step": 167720 }, { "epoch": 40.28, "learning_rate": 5.327761868653494e-05, "loss": 0.0102, "step": 167730 }, { "epoch": 40.28, "learning_rate": 5.327314136030596e-05, "loss": 0.021, "step": 167740 }, { "epoch": 40.28, "learning_rate": 5.326866400771793e-05, "loss": 0.0199, "step": 167750 }, { "epoch": 40.28, "learning_rate": 5.326418662880688e-05, "loss": 0.0104, "step": 167760 }, { "epoch": 40.29, "learning_rate": 5.32597092236089e-05, "loss": 0.0118, "step": 167770 }, { "epoch": 40.29, "learning_rate": 5.325523179216001e-05, "loss": 0.0098, "step": 167780 }, { "epoch": 40.29, "learning_rate": 5.325075433449631e-05, "loss": 0.0317, "step": 167790 }, { "epoch": 40.29, "learning_rate": 5.324627685065383e-05, "loss": 0.0111, "step": 167800 }, { "epoch": 40.29, "learning_rate": 5.324179934066863e-05, "loss": 0.0301, "step": 167810 }, { "epoch": 40.3, "learning_rate": 5.3237321804576786e-05, "loss": 0.0366, "step": 167820 }, { "epoch": 40.3, "learning_rate": 5.323284424241433e-05, "loss": 0.0152, "step": 167830 }, { "epoch": 40.3, "learning_rate": 5.322836665421733e-05, "loss": 0.0109, "step": 167840 }, { "epoch": 40.3, "learning_rate": 5.322388904002186e-05, "loss": 0.0284, "step": 167850 }, { "epoch": 40.31, "learning_rate": 5.321941139986395e-05, "loss": 0.0162, "step": 167860 }, { "epoch": 40.31, "learning_rate": 5.321493373377969e-05, "loss": 0.0214, "step": 167870 }, { "epoch": 40.31, "learning_rate": 5.321045604180512e-05, "loss": 0.0108, "step": 167880 }, { "epoch": 40.31, "learning_rate": 5.320597832397631e-05, "loss": 0.0142, "step": 167890 }, { "epoch": 40.32, "learning_rate": 5.320150058032931e-05, "loss": 0.0322, "step": 167900 }, { "epoch": 40.32, "learning_rate": 5.3197022810900174e-05, "loss": 0.0068, "step": 167910 }, { "epoch": 40.32, "learning_rate": 5.319254501572499e-05, "loss": 0.0135, "step": 167920 }, { "epoch": 40.32, "learning_rate": 5.318806719483977e-05, "loss": 0.0213, "step": 167930 }, { "epoch": 40.32, "learning_rate": 5.318358934828065e-05, "loss": 0.0139, "step": 167940 }, { "epoch": 40.33, "learning_rate": 5.3179111476083607e-05, "loss": 0.0138, "step": 167950 }, { "epoch": 40.33, "learning_rate": 5.317463357828477e-05, "loss": 0.0178, "step": 167960 }, { "epoch": 40.33, "learning_rate": 5.317015565492014e-05, "loss": 0.0125, "step": 167970 }, { "epoch": 40.33, "learning_rate": 5.316567770602583e-05, "loss": 0.0089, "step": 167980 }, { "epoch": 40.34, "learning_rate": 5.316119973163788e-05, "loss": 0.0113, "step": 167990 }, { "epoch": 40.34, "learning_rate": 5.3156721731792336e-05, "loss": 0.0092, "step": 168000 }, { "epoch": 40.34, "learning_rate": 5.315224370652529e-05, "loss": 0.0177, "step": 168010 }, { "epoch": 40.34, "learning_rate": 5.314776565587278e-05, "loss": 0.0174, "step": 168020 }, { "epoch": 40.35, "learning_rate": 5.3143287579870896e-05, "loss": 0.0125, "step": 168030 }, { "epoch": 40.35, "learning_rate": 5.3138809478555677e-05, "loss": 0.019, "step": 168040 }, { "epoch": 40.35, "learning_rate": 5.3134331351963184e-05, "loss": 0.008, "step": 168050 }, { "epoch": 40.35, "learning_rate": 5.312985320012949e-05, "loss": 0.0147, "step": 168060 }, { "epoch": 40.35, "learning_rate": 5.312537502309065e-05, "loss": 0.0159, "step": 168070 }, { "epoch": 40.36, "learning_rate": 5.312089682088275e-05, "loss": 0.0068, "step": 168080 }, { "epoch": 40.36, "learning_rate": 5.311641859354182e-05, "loss": 0.0217, "step": 168090 }, { "epoch": 40.36, "learning_rate": 5.311194034110395e-05, "loss": 0.0128, "step": 168100 }, { "epoch": 40.36, "learning_rate": 5.31074620636052e-05, "loss": 0.0391, "step": 168110 }, { "epoch": 40.37, "learning_rate": 5.310298376108162e-05, "loss": 0.018, "step": 168120 }, { "epoch": 40.37, "learning_rate": 5.309850543356929e-05, "loss": 0.0074, "step": 168130 }, { "epoch": 40.37, "learning_rate": 5.309402708110425e-05, "loss": 0.0087, "step": 168140 }, { "epoch": 40.37, "learning_rate": 5.30895487037226e-05, "loss": 0.0106, "step": 168150 }, { "epoch": 40.37, "learning_rate": 5.3085070301460384e-05, "loss": 0.039, "step": 168160 }, { "epoch": 40.38, "learning_rate": 5.3080591874353666e-05, "loss": 0.0105, "step": 168170 }, { "epoch": 40.38, "learning_rate": 5.307611342243853e-05, "loss": 0.0129, "step": 168180 }, { "epoch": 40.38, "learning_rate": 5.3071634945751014e-05, "loss": 0.0402, "step": 168190 }, { "epoch": 40.38, "learning_rate": 5.306715644432722e-05, "loss": 0.0177, "step": 168200 }, { "epoch": 40.39, "learning_rate": 5.306267791820316e-05, "loss": 0.0092, "step": 168210 }, { "epoch": 40.39, "learning_rate": 5.305819936741495e-05, "loss": 0.0147, "step": 168220 }, { "epoch": 40.39, "learning_rate": 5.3053720791998626e-05, "loss": 0.0156, "step": 168230 }, { "epoch": 40.39, "learning_rate": 5.304924219199029e-05, "loss": 0.0164, "step": 168240 }, { "epoch": 40.4, "learning_rate": 5.304476356742597e-05, "loss": 0.0125, "step": 168250 }, { "epoch": 40.4, "learning_rate": 5.304028491834174e-05, "loss": 0.0078, "step": 168260 }, { "epoch": 40.4, "learning_rate": 5.303580624477369e-05, "loss": 0.0245, "step": 168270 }, { "epoch": 40.4, "learning_rate": 5.303132754675787e-05, "loss": 0.0124, "step": 168280 }, { "epoch": 40.4, "learning_rate": 5.302684882433035e-05, "loss": 0.0105, "step": 168290 }, { "epoch": 40.41, "learning_rate": 5.30223700775272e-05, "loss": 0.0099, "step": 168300 }, { "epoch": 40.41, "learning_rate": 5.301789130638448e-05, "loss": 0.0115, "step": 168310 }, { "epoch": 40.41, "learning_rate": 5.301341251093828e-05, "loss": 0.0125, "step": 168320 }, { "epoch": 40.41, "learning_rate": 5.300893369122463e-05, "loss": 0.023, "step": 168330 }, { "epoch": 40.42, "learning_rate": 5.300445484727964e-05, "loss": 0.0248, "step": 168340 }, { "epoch": 40.42, "learning_rate": 5.299997597913935e-05, "loss": 0.0151, "step": 168350 }, { "epoch": 40.42, "learning_rate": 5.2995497086839854e-05, "loss": 0.0088, "step": 168360 }, { "epoch": 40.42, "learning_rate": 5.299101817041719e-05, "loss": 0.0093, "step": 168370 }, { "epoch": 40.43, "learning_rate": 5.298653922990745e-05, "loss": 0.0106, "step": 168380 }, { "epoch": 40.43, "learning_rate": 5.29820602653467e-05, "loss": 0.0085, "step": 168390 }, { "epoch": 40.43, "learning_rate": 5.2977581276771004e-05, "loss": 0.0216, "step": 168400 }, { "epoch": 40.43, "learning_rate": 5.297310226421643e-05, "loss": 0.0158, "step": 168410 }, { "epoch": 40.43, "learning_rate": 5.296862322771906e-05, "loss": 0.02, "step": 168420 }, { "epoch": 40.44, "learning_rate": 5.296414416731496e-05, "loss": 0.0105, "step": 168430 }, { "epoch": 40.44, "learning_rate": 5.295966508304019e-05, "loss": 0.024, "step": 168440 }, { "epoch": 40.44, "learning_rate": 5.295518597493082e-05, "loss": 0.0172, "step": 168450 }, { "epoch": 40.44, "learning_rate": 5.295070684302295e-05, "loss": 0.0077, "step": 168460 }, { "epoch": 40.45, "learning_rate": 5.2946227687352626e-05, "loss": 0.0112, "step": 168470 }, { "epoch": 40.45, "learning_rate": 5.2941748507955914e-05, "loss": 0.0116, "step": 168480 }, { "epoch": 40.45, "learning_rate": 5.293726930486891e-05, "loss": 0.0078, "step": 168490 }, { "epoch": 40.45, "learning_rate": 5.293279007812766e-05, "loss": 0.0146, "step": 168500 }, { "epoch": 40.45, "learning_rate": 5.292831082776825e-05, "loss": 0.0253, "step": 168510 }, { "epoch": 40.46, "learning_rate": 5.292383155382673e-05, "loss": 0.0151, "step": 168520 }, { "epoch": 40.46, "learning_rate": 5.2919352256339216e-05, "loss": 0.0184, "step": 168530 }, { "epoch": 40.46, "learning_rate": 5.291487293534174e-05, "loss": 0.0114, "step": 168540 }, { "epoch": 40.46, "learning_rate": 5.29103935908704e-05, "loss": 0.0186, "step": 168550 }, { "epoch": 40.47, "learning_rate": 5.290591422296126e-05, "loss": 0.0429, "step": 168560 }, { "epoch": 40.47, "learning_rate": 5.290143483165039e-05, "loss": 0.0147, "step": 168570 }, { "epoch": 40.47, "learning_rate": 5.289695541697385e-05, "loss": 0.0186, "step": 168580 }, { "epoch": 40.47, "learning_rate": 5.2892475978967735e-05, "loss": 0.0218, "step": 168590 }, { "epoch": 40.48, "learning_rate": 5.2887996517668124e-05, "loss": 0.0115, "step": 168600 }, { "epoch": 40.48, "learning_rate": 5.2883517033111076e-05, "loss": 0.0204, "step": 168610 }, { "epoch": 40.48, "learning_rate": 5.2879037525332654e-05, "loss": 0.0132, "step": 168620 }, { "epoch": 40.48, "learning_rate": 5.2874557994368954e-05, "loss": 0.0204, "step": 168630 }, { "epoch": 40.48, "learning_rate": 5.287007844025604e-05, "loss": 0.0117, "step": 168640 }, { "epoch": 40.49, "learning_rate": 5.286559886302998e-05, "loss": 0.0197, "step": 168650 }, { "epoch": 40.49, "learning_rate": 5.286111926272688e-05, "loss": 0.0156, "step": 168660 }, { "epoch": 40.49, "learning_rate": 5.2856639639382764e-05, "loss": 0.0171, "step": 168670 }, { "epoch": 40.49, "learning_rate": 5.2852159993033756e-05, "loss": 0.0238, "step": 168680 }, { "epoch": 40.5, "learning_rate": 5.28476803237159e-05, "loss": 0.0062, "step": 168690 }, { "epoch": 40.5, "learning_rate": 5.2843200631465274e-05, "loss": 0.0133, "step": 168700 }, { "epoch": 40.5, "learning_rate": 5.283872091631799e-05, "loss": 0.0169, "step": 168710 }, { "epoch": 40.5, "learning_rate": 5.283424117831006e-05, "loss": 0.0095, "step": 168720 }, { "epoch": 40.51, "learning_rate": 5.282976141747761e-05, "loss": 0.0309, "step": 168730 }, { "epoch": 40.51, "learning_rate": 5.2825281633856695e-05, "loss": 0.0107, "step": 168740 }, { "epoch": 40.51, "learning_rate": 5.28208018274834e-05, "loss": 0.01, "step": 168750 }, { "epoch": 40.51, "learning_rate": 5.28163219983938e-05, "loss": 0.0183, "step": 168760 }, { "epoch": 40.51, "learning_rate": 5.281184214662397e-05, "loss": 0.0165, "step": 168770 }, { "epoch": 40.52, "learning_rate": 5.2807362272209984e-05, "loss": 0.0119, "step": 168780 }, { "epoch": 40.52, "learning_rate": 5.2802882375187924e-05, "loss": 0.0083, "step": 168790 }, { "epoch": 40.52, "learning_rate": 5.279840245559387e-05, "loss": 0.0322, "step": 168800 }, { "epoch": 40.52, "learning_rate": 5.279392251346389e-05, "loss": 0.0089, "step": 168810 }, { "epoch": 40.53, "learning_rate": 5.278944254883406e-05, "loss": 0.0256, "step": 168820 }, { "epoch": 40.53, "learning_rate": 5.278496256174048e-05, "loss": 0.0218, "step": 168830 }, { "epoch": 40.53, "learning_rate": 5.2780482552219204e-05, "loss": 0.017, "step": 168840 }, { "epoch": 40.53, "learning_rate": 5.277600252030631e-05, "loss": 0.0229, "step": 168850 }, { "epoch": 40.53, "learning_rate": 5.2771522466037895e-05, "loss": 0.0245, "step": 168860 }, { "epoch": 40.54, "learning_rate": 5.276704238945003e-05, "loss": 0.0182, "step": 168870 }, { "epoch": 40.54, "learning_rate": 5.276256229057878e-05, "loss": 0.0126, "step": 168880 }, { "epoch": 40.54, "learning_rate": 5.2758082169460233e-05, "loss": 0.0239, "step": 168890 }, { "epoch": 40.54, "learning_rate": 5.275360202613049e-05, "loss": 0.0315, "step": 168900 }, { "epoch": 40.55, "learning_rate": 5.274912186062558e-05, "loss": 0.0214, "step": 168910 }, { "epoch": 40.55, "learning_rate": 5.274464167298163e-05, "loss": 0.0197, "step": 168920 }, { "epoch": 40.55, "learning_rate": 5.2740161463234696e-05, "loss": 0.0145, "step": 168930 }, { "epoch": 40.55, "learning_rate": 5.2735681231420865e-05, "loss": 0.0176, "step": 168940 }, { "epoch": 40.56, "learning_rate": 5.273120097757622e-05, "loss": 0.0077, "step": 168950 }, { "epoch": 40.56, "learning_rate": 5.272672070173682e-05, "loss": 0.0105, "step": 168960 }, { "epoch": 40.56, "learning_rate": 5.2722240403938795e-05, "loss": 0.0113, "step": 168970 }, { "epoch": 40.56, "learning_rate": 5.271776008421816e-05, "loss": 0.0166, "step": 168980 }, { "epoch": 40.56, "learning_rate": 5.271327974261104e-05, "loss": 0.0457, "step": 168990 }, { "epoch": 40.57, "learning_rate": 5.2708799379153506e-05, "loss": 0.0311, "step": 169000 }, { "epoch": 40.57, "learning_rate": 5.270431899388162e-05, "loss": 0.0165, "step": 169010 }, { "epoch": 40.57, "learning_rate": 5.2699838586831504e-05, "loss": 0.0116, "step": 169020 }, { "epoch": 40.57, "learning_rate": 5.26953581580392e-05, "loss": 0.0129, "step": 169030 }, { "epoch": 40.58, "learning_rate": 5.269087770754082e-05, "loss": 0.025, "step": 169040 }, { "epoch": 40.58, "learning_rate": 5.268639723537241e-05, "loss": 0.0132, "step": 169050 }, { "epoch": 40.58, "learning_rate": 5.268191674157008e-05, "loss": 0.0295, "step": 169060 }, { "epoch": 40.58, "learning_rate": 5.2677436226169916e-05, "loss": 0.0196, "step": 169070 }, { "epoch": 40.59, "learning_rate": 5.267295568920797e-05, "loss": 0.0168, "step": 169080 }, { "epoch": 40.59, "learning_rate": 5.266847513072036e-05, "loss": 0.0225, "step": 169090 }, { "epoch": 40.59, "learning_rate": 5.266399455074313e-05, "loss": 0.0174, "step": 169100 }, { "epoch": 40.59, "learning_rate": 5.26595139493124e-05, "loss": 0.0173, "step": 169110 }, { "epoch": 40.59, "learning_rate": 5.2655033326464245e-05, "loss": 0.0207, "step": 169120 }, { "epoch": 40.6, "learning_rate": 5.265055268223471e-05, "loss": 0.01, "step": 169130 }, { "epoch": 40.6, "learning_rate": 5.264607201665994e-05, "loss": 0.0139, "step": 169140 }, { "epoch": 40.6, "learning_rate": 5.2641591329775964e-05, "loss": 0.0204, "step": 169150 }, { "epoch": 40.6, "learning_rate": 5.263711062161891e-05, "loss": 0.0273, "step": 169160 }, { "epoch": 40.61, "learning_rate": 5.263262989222482e-05, "loss": 0.0167, "step": 169170 }, { "epoch": 40.61, "learning_rate": 5.262814914162981e-05, "loss": 0.0192, "step": 169180 }, { "epoch": 40.61, "learning_rate": 5.262366836986995e-05, "loss": 0.0259, "step": 169190 }, { "epoch": 40.61, "learning_rate": 5.261918757698131e-05, "loss": 0.0097, "step": 169200 }, { "epoch": 40.61, "learning_rate": 5.261470676300002e-05, "loss": 0.0395, "step": 169210 }, { "epoch": 40.62, "learning_rate": 5.261022592796211e-05, "loss": 0.0203, "step": 169220 }, { "epoch": 40.62, "learning_rate": 5.260574507190371e-05, "loss": 0.0247, "step": 169230 }, { "epoch": 40.62, "learning_rate": 5.260126419486088e-05, "loss": 0.0283, "step": 169240 }, { "epoch": 40.62, "learning_rate": 5.259678329686969e-05, "loss": 0.0195, "step": 169250 }, { "epoch": 40.63, "learning_rate": 5.2592302377966274e-05, "loss": 0.0187, "step": 169260 }, { "epoch": 40.63, "learning_rate": 5.2587821438186667e-05, "loss": 0.013, "step": 169270 }, { "epoch": 40.63, "learning_rate": 5.2583340477567e-05, "loss": 0.0168, "step": 169280 }, { "epoch": 40.63, "learning_rate": 5.2578859496143315e-05, "loss": 0.0137, "step": 169290 }, { "epoch": 40.64, "learning_rate": 5.2574378493951724e-05, "loss": 0.0065, "step": 169300 }, { "epoch": 40.64, "learning_rate": 5.256989747102832e-05, "loss": 0.0164, "step": 169310 }, { "epoch": 40.64, "learning_rate": 5.256541642740915e-05, "loss": 0.0143, "step": 169320 }, { "epoch": 40.64, "learning_rate": 5.256093536313036e-05, "loss": 0.0158, "step": 169330 }, { "epoch": 40.64, "learning_rate": 5.255645427822799e-05, "loss": 0.0125, "step": 169340 }, { "epoch": 40.65, "learning_rate": 5.255197317273813e-05, "loss": 0.0098, "step": 169350 }, { "epoch": 40.65, "learning_rate": 5.254749204669689e-05, "loss": 0.0402, "step": 169360 }, { "epoch": 40.65, "learning_rate": 5.254301090014034e-05, "loss": 0.0218, "step": 169370 }, { "epoch": 40.65, "learning_rate": 5.253852973310458e-05, "loss": 0.0125, "step": 169380 }, { "epoch": 40.66, "learning_rate": 5.253404854562567e-05, "loss": 0.0128, "step": 169390 }, { "epoch": 40.66, "learning_rate": 5.252956733773974e-05, "loss": 0.0169, "step": 169400 }, { "epoch": 40.66, "learning_rate": 5.2525086109482835e-05, "loss": 0.0202, "step": 169410 }, { "epoch": 40.66, "learning_rate": 5.2520604860891075e-05, "loss": 0.014, "step": 169420 }, { "epoch": 40.66, "learning_rate": 5.251612359200054e-05, "loss": 0.0112, "step": 169430 }, { "epoch": 40.67, "learning_rate": 5.2511642302847295e-05, "loss": 0.0145, "step": 169440 }, { "epoch": 40.67, "learning_rate": 5.2507160993467476e-05, "loss": 0.0077, "step": 169450 }, { "epoch": 40.67, "learning_rate": 5.2502679663897116e-05, "loss": 0.0307, "step": 169460 }, { "epoch": 40.67, "learning_rate": 5.2498198314172366e-05, "loss": 0.0124, "step": 169470 }, { "epoch": 40.68, "learning_rate": 5.249371694432924e-05, "loss": 0.0205, "step": 169480 }, { "epoch": 40.68, "learning_rate": 5.2489235554403895e-05, "loss": 0.0156, "step": 169490 }, { "epoch": 40.68, "learning_rate": 5.248475414443238e-05, "loss": 0.0347, "step": 169500 }, { "epoch": 40.68, "learning_rate": 5.2480272714450786e-05, "loss": 0.0152, "step": 169510 }, { "epoch": 40.69, "learning_rate": 5.2475791264495245e-05, "loss": 0.0221, "step": 169520 }, { "epoch": 40.69, "learning_rate": 5.247130979460179e-05, "loss": 0.015, "step": 169530 }, { "epoch": 40.69, "learning_rate": 5.2466828304806534e-05, "loss": 0.0326, "step": 169540 }, { "epoch": 40.69, "learning_rate": 5.246234679514558e-05, "loss": 0.0124, "step": 169550 }, { "epoch": 40.69, "learning_rate": 5.245786526565501e-05, "loss": 0.0107, "step": 169560 }, { "epoch": 40.7, "learning_rate": 5.245338371637091e-05, "loss": 0.0163, "step": 169570 }, { "epoch": 40.7, "learning_rate": 5.244890214732936e-05, "loss": 0.0106, "step": 169580 }, { "epoch": 40.7, "learning_rate": 5.244442055856649e-05, "loss": 0.0109, "step": 169590 }, { "epoch": 40.7, "learning_rate": 5.243993895011833e-05, "loss": 0.027, "step": 169600 }, { "epoch": 40.71, "learning_rate": 5.243545732202102e-05, "loss": 0.009, "step": 169610 }, { "epoch": 40.71, "learning_rate": 5.243097567431064e-05, "loss": 0.0121, "step": 169620 }, { "epoch": 40.71, "learning_rate": 5.242649400702327e-05, "loss": 0.0156, "step": 169630 }, { "epoch": 40.71, "learning_rate": 5.242201232019502e-05, "loss": 0.0143, "step": 169640 }, { "epoch": 40.72, "learning_rate": 5.2417530613861954e-05, "loss": 0.0189, "step": 169650 }, { "epoch": 40.72, "learning_rate": 5.241304888806019e-05, "loss": 0.0176, "step": 169660 }, { "epoch": 40.72, "learning_rate": 5.2408567142825816e-05, "loss": 0.014, "step": 169670 }, { "epoch": 40.72, "learning_rate": 5.240408537819491e-05, "loss": 0.0235, "step": 169680 }, { "epoch": 40.72, "learning_rate": 5.2399603594203574e-05, "loss": 0.0185, "step": 169690 }, { "epoch": 40.73, "learning_rate": 5.2395121790887904e-05, "loss": 0.0167, "step": 169700 }, { "epoch": 40.73, "learning_rate": 5.2390639968283985e-05, "loss": 0.0253, "step": 169710 }, { "epoch": 40.73, "learning_rate": 5.2386158126427896e-05, "loss": 0.0165, "step": 169720 }, { "epoch": 40.73, "learning_rate": 5.238167626535576e-05, "loss": 0.0146, "step": 169730 }, { "epoch": 40.74, "learning_rate": 5.237719438510366e-05, "loss": 0.0106, "step": 169740 }, { "epoch": 40.74, "learning_rate": 5.2372712485707686e-05, "loss": 0.0251, "step": 169750 }, { "epoch": 40.74, "learning_rate": 5.2368230567203924e-05, "loss": 0.0128, "step": 169760 }, { "epoch": 40.74, "learning_rate": 5.2363748629628476e-05, "loss": 0.0145, "step": 169770 }, { "epoch": 40.74, "learning_rate": 5.235926667301743e-05, "loss": 0.0138, "step": 169780 }, { "epoch": 40.75, "learning_rate": 5.2354784697406886e-05, "loss": 0.0188, "step": 169790 }, { "epoch": 40.75, "learning_rate": 5.2350302702832945e-05, "loss": 0.0203, "step": 169800 }, { "epoch": 40.75, "learning_rate": 5.234582068933169e-05, "loss": 0.0137, "step": 169810 }, { "epoch": 40.75, "learning_rate": 5.234133865693921e-05, "loss": 0.0162, "step": 169820 }, { "epoch": 40.76, "learning_rate": 5.233685660569161e-05, "loss": 0.0353, "step": 169830 }, { "epoch": 40.76, "learning_rate": 5.233237453562497e-05, "loss": 0.0232, "step": 169840 }, { "epoch": 40.76, "learning_rate": 5.2327892446775404e-05, "loss": 0.018, "step": 169850 }, { "epoch": 40.76, "learning_rate": 5.232341033917901e-05, "loss": 0.0107, "step": 169860 }, { "epoch": 40.77, "learning_rate": 5.231892821287186e-05, "loss": 0.0146, "step": 169870 }, { "epoch": 40.77, "learning_rate": 5.2314446067890064e-05, "loss": 0.0185, "step": 169880 }, { "epoch": 40.77, "learning_rate": 5.230996390426972e-05, "loss": 0.0177, "step": 169890 }, { "epoch": 40.77, "learning_rate": 5.230548172204691e-05, "loss": 0.0093, "step": 169900 }, { "epoch": 40.77, "learning_rate": 5.230099952125773e-05, "loss": 0.0122, "step": 169910 }, { "epoch": 40.78, "learning_rate": 5.2296517301938294e-05, "loss": 0.0226, "step": 169920 }, { "epoch": 40.78, "learning_rate": 5.2292035064124686e-05, "loss": 0.021, "step": 169930 }, { "epoch": 40.78, "learning_rate": 5.2287552807853004e-05, "loss": 0.0132, "step": 169940 }, { "epoch": 40.78, "learning_rate": 5.228307053315934e-05, "loss": 0.018, "step": 169950 }, { "epoch": 40.79, "learning_rate": 5.2278588240079805e-05, "loss": 0.0094, "step": 169960 }, { "epoch": 40.79, "learning_rate": 5.227410592865046e-05, "loss": 0.017, "step": 169970 }, { "epoch": 40.79, "learning_rate": 5.226962359890745e-05, "loss": 0.0227, "step": 169980 }, { "epoch": 40.79, "learning_rate": 5.226514125088684e-05, "loss": 0.0178, "step": 169990 }, { "epoch": 40.8, "learning_rate": 5.226065888462473e-05, "loss": 0.0155, "step": 170000 }, { "epoch": 40.8, "learning_rate": 5.2256176500157225e-05, "loss": 0.027, "step": 170010 }, { "epoch": 40.8, "learning_rate": 5.225169409752042e-05, "loss": 0.0235, "step": 170020 }, { "epoch": 40.8, "learning_rate": 5.224721167675042e-05, "loss": 0.01, "step": 170030 }, { "epoch": 40.8, "learning_rate": 5.2242729237883294e-05, "loss": 0.0094, "step": 170040 }, { "epoch": 40.81, "learning_rate": 5.223824678095517e-05, "loss": 0.0229, "step": 170050 }, { "epoch": 40.81, "learning_rate": 5.223376430600214e-05, "loss": 0.0118, "step": 170060 }, { "epoch": 40.81, "learning_rate": 5.222928181306029e-05, "loss": 0.0137, "step": 170070 }, { "epoch": 40.81, "learning_rate": 5.222479930216574e-05, "loss": 0.0185, "step": 170080 }, { "epoch": 40.82, "learning_rate": 5.222031677335455e-05, "loss": 0.0165, "step": 170090 }, { "epoch": 40.82, "learning_rate": 5.221583422666286e-05, "loss": 0.0133, "step": 170100 }, { "epoch": 40.82, "learning_rate": 5.221135166212675e-05, "loss": 0.0227, "step": 170110 }, { "epoch": 40.82, "learning_rate": 5.2206869079782316e-05, "loss": 0.0114, "step": 170120 }, { "epoch": 40.82, "learning_rate": 5.2202386479665666e-05, "loss": 0.0135, "step": 170130 }, { "epoch": 40.83, "learning_rate": 5.219790386181289e-05, "loss": 0.0099, "step": 170140 }, { "epoch": 40.83, "learning_rate": 5.2193421226260096e-05, "loss": 0.0117, "step": 170150 }, { "epoch": 40.83, "learning_rate": 5.218893857304336e-05, "loss": 0.0133, "step": 170160 }, { "epoch": 40.83, "learning_rate": 5.218445590219881e-05, "loss": 0.0124, "step": 170170 }, { "epoch": 40.84, "learning_rate": 5.2179973213762545e-05, "loss": 0.0104, "step": 170180 }, { "epoch": 40.84, "learning_rate": 5.217549050777064e-05, "loss": 0.0183, "step": 170190 }, { "epoch": 40.84, "learning_rate": 5.217100778425923e-05, "loss": 0.0216, "step": 170200 }, { "epoch": 40.84, "learning_rate": 5.216652504326437e-05, "loss": 0.0115, "step": 170210 }, { "epoch": 40.85, "learning_rate": 5.21620422848222e-05, "loss": 0.0162, "step": 170220 }, { "epoch": 40.85, "learning_rate": 5.215755950896879e-05, "loss": 0.0139, "step": 170230 }, { "epoch": 40.85, "learning_rate": 5.215307671574027e-05, "loss": 0.0281, "step": 170240 }, { "epoch": 40.85, "learning_rate": 5.2148593905172725e-05, "loss": 0.0084, "step": 170250 }, { "epoch": 40.85, "learning_rate": 5.214411107730226e-05, "loss": 0.0136, "step": 170260 }, { "epoch": 40.86, "learning_rate": 5.213962823216496e-05, "loss": 0.0177, "step": 170270 }, { "epoch": 40.86, "learning_rate": 5.2135145369796944e-05, "loss": 0.0119, "step": 170280 }, { "epoch": 40.86, "learning_rate": 5.213066249023432e-05, "loss": 0.0058, "step": 170290 }, { "epoch": 40.86, "learning_rate": 5.2126179593513145e-05, "loss": 0.0151, "step": 170300 }, { "epoch": 40.87, "learning_rate": 5.2121696679669586e-05, "loss": 0.012, "step": 170310 }, { "epoch": 40.87, "learning_rate": 5.211721374873969e-05, "loss": 0.0253, "step": 170320 }, { "epoch": 40.87, "learning_rate": 5.2112730800759594e-05, "loss": 0.0384, "step": 170330 }, { "epoch": 40.87, "learning_rate": 5.2108247835765375e-05, "loss": 0.0185, "step": 170340 }, { "epoch": 40.88, "learning_rate": 5.210376485379313e-05, "loss": 0.0327, "step": 170350 }, { "epoch": 40.88, "learning_rate": 5.209928185487901e-05, "loss": 0.0103, "step": 170360 }, { "epoch": 40.88, "learning_rate": 5.209479883905907e-05, "loss": 0.0169, "step": 170370 }, { "epoch": 40.88, "learning_rate": 5.2090315806369416e-05, "loss": 0.0128, "step": 170380 }, { "epoch": 40.88, "learning_rate": 5.2085832756846174e-05, "loss": 0.0251, "step": 170390 }, { "epoch": 40.89, "learning_rate": 5.2081349690525416e-05, "loss": 0.0192, "step": 170400 }, { "epoch": 40.89, "learning_rate": 5.2076866607443284e-05, "loss": 0.0188, "step": 170410 }, { "epoch": 40.89, "learning_rate": 5.207238350763584e-05, "loss": 0.0094, "step": 170420 }, { "epoch": 40.89, "learning_rate": 5.206790039113921e-05, "loss": 0.0091, "step": 170430 }, { "epoch": 40.9, "learning_rate": 5.206341725798949e-05, "loss": 0.022, "step": 170440 }, { "epoch": 40.9, "learning_rate": 5.20589341082228e-05, "loss": 0.0118, "step": 170450 }, { "epoch": 40.9, "learning_rate": 5.2054450941875224e-05, "loss": 0.0134, "step": 170460 }, { "epoch": 40.9, "learning_rate": 5.204996775898286e-05, "loss": 0.0121, "step": 170470 }, { "epoch": 40.9, "learning_rate": 5.204548455958184e-05, "loss": 0.0177, "step": 170480 }, { "epoch": 40.91, "learning_rate": 5.204100134370822e-05, "loss": 0.0111, "step": 170490 }, { "epoch": 40.91, "learning_rate": 5.203651811139816e-05, "loss": 0.0323, "step": 170500 }, { "epoch": 40.91, "learning_rate": 5.203203486268773e-05, "loss": 0.0112, "step": 170510 }, { "epoch": 40.91, "learning_rate": 5.202755159761303e-05, "loss": 0.0162, "step": 170520 }, { "epoch": 40.92, "learning_rate": 5.202306831621021e-05, "loss": 0.0117, "step": 170530 }, { "epoch": 40.92, "learning_rate": 5.201858501851532e-05, "loss": 0.0142, "step": 170540 }, { "epoch": 40.92, "learning_rate": 5.20141017045645e-05, "loss": 0.0143, "step": 170550 }, { "epoch": 40.92, "learning_rate": 5.200961837439382e-05, "loss": 0.0175, "step": 170560 }, { "epoch": 40.93, "learning_rate": 5.2005135028039423e-05, "loss": 0.0095, "step": 170570 }, { "epoch": 40.93, "learning_rate": 5.200065166553739e-05, "loss": 0.0167, "step": 170580 }, { "epoch": 40.93, "learning_rate": 5.199616828692382e-05, "loss": 0.0123, "step": 170590 }, { "epoch": 40.93, "learning_rate": 5.199168489223486e-05, "loss": 0.0255, "step": 170600 }, { "epoch": 40.93, "learning_rate": 5.1987201481506564e-05, "loss": 0.0268, "step": 170610 }, { "epoch": 40.94, "learning_rate": 5.198271805477507e-05, "loss": 0.0227, "step": 170620 }, { "epoch": 40.94, "learning_rate": 5.197823461207647e-05, "loss": 0.0149, "step": 170630 }, { "epoch": 40.94, "learning_rate": 5.197375115344686e-05, "loss": 0.0248, "step": 170640 }, { "epoch": 40.94, "learning_rate": 5.196926767892239e-05, "loss": 0.0154, "step": 170650 }, { "epoch": 40.95, "learning_rate": 5.196478418853911e-05, "loss": 0.0302, "step": 170660 }, { "epoch": 40.95, "learning_rate": 5.1960300682333175e-05, "loss": 0.0164, "step": 170670 }, { "epoch": 40.95, "learning_rate": 5.195581716034065e-05, "loss": 0.027, "step": 170680 }, { "epoch": 41.0, "learning_rate": 5.1951333622597665e-05, "loss": 0.021, "step": 170690 }, { "epoch": 41.0, "learning_rate": 5.194685006914032e-05, "loss": 0.0108, "step": 170700 }, { "epoch": 41.01, "learning_rate": 5.1942366500004714e-05, "loss": 0.0236, "step": 170710 }, { "epoch": 41.01, "learning_rate": 5.1937882915226974e-05, "loss": 0.028, "step": 170720 }, { "epoch": 41.01, "learning_rate": 5.193339931484319e-05, "loss": 0.0282, "step": 170730 }, { "epoch": 41.01, "learning_rate": 5.192891569888948e-05, "loss": 0.0106, "step": 170740 }, { "epoch": 41.02, "learning_rate": 5.192443206740194e-05, "loss": 0.012, "step": 170750 }, { "epoch": 41.02, "learning_rate": 5.191994842041669e-05, "loss": 0.0132, "step": 170760 }, { "epoch": 41.02, "learning_rate": 5.191546475796982e-05, "loss": 0.016, "step": 170770 }, { "epoch": 41.02, "learning_rate": 5.191098108009744e-05, "loss": 0.0318, "step": 170780 }, { "epoch": 41.02, "learning_rate": 5.190649738683569e-05, "loss": 0.0165, "step": 170790 }, { "epoch": 41.03, "learning_rate": 5.190201367822064e-05, "loss": 0.0157, "step": 170800 }, { "epoch": 41.03, "learning_rate": 5.1897529954288415e-05, "loss": 0.0079, "step": 170810 }, { "epoch": 41.03, "learning_rate": 5.1893046215075115e-05, "loss": 0.0222, "step": 170820 }, { "epoch": 41.03, "learning_rate": 5.1888562460616855e-05, "loss": 0.0258, "step": 170830 }, { "epoch": 41.04, "learning_rate": 5.1884078690949746e-05, "loss": 0.0115, "step": 170840 }, { "epoch": 41.04, "learning_rate": 5.187959490610987e-05, "loss": 0.0171, "step": 170850 }, { "epoch": 41.04, "learning_rate": 5.187511110613339e-05, "loss": 0.0184, "step": 170860 }, { "epoch": 41.04, "learning_rate": 5.187062729105635e-05, "loss": 0.0112, "step": 170870 }, { "epoch": 41.05, "learning_rate": 5.186614346091491e-05, "loss": 0.0235, "step": 170880 }, { "epoch": 41.05, "learning_rate": 5.186165961574516e-05, "loss": 0.0231, "step": 170890 }, { "epoch": 41.05, "learning_rate": 5.1857175755583185e-05, "loss": 0.014, "step": 170900 }, { "epoch": 41.05, "learning_rate": 5.1852691880465156e-05, "loss": 0.0191, "step": 170910 }, { "epoch": 41.05, "learning_rate": 5.18482079904271e-05, "loss": 0.0114, "step": 170920 }, { "epoch": 41.06, "learning_rate": 5.1843724085505196e-05, "loss": 0.0177, "step": 170930 }, { "epoch": 41.06, "learning_rate": 5.183924016573553e-05, "loss": 0.0262, "step": 170940 }, { "epoch": 41.06, "learning_rate": 5.18347562311542e-05, "loss": 0.0119, "step": 170950 }, { "epoch": 41.06, "learning_rate": 5.183027228179732e-05, "loss": 0.0068, "step": 170960 }, { "epoch": 41.07, "learning_rate": 5.1825788317701006e-05, "loss": 0.0155, "step": 170970 }, { "epoch": 41.07, "learning_rate": 5.182130433890139e-05, "loss": 0.0204, "step": 170980 }, { "epoch": 41.07, "learning_rate": 5.181682034543453e-05, "loss": 0.0142, "step": 170990 }, { "epoch": 41.07, "learning_rate": 5.1812336337336574e-05, "loss": 0.0175, "step": 171000 }, { "epoch": 41.07, "learning_rate": 5.180785231464362e-05, "loss": 0.0137, "step": 171010 }, { "epoch": 41.08, "learning_rate": 5.180336827739178e-05, "loss": 0.0145, "step": 171020 }, { "epoch": 41.08, "learning_rate": 5.1798884225617186e-05, "loss": 0.0163, "step": 171030 }, { "epoch": 41.08, "learning_rate": 5.1794400159355907e-05, "loss": 0.0111, "step": 171040 }, { "epoch": 41.08, "learning_rate": 5.178991607864408e-05, "loss": 0.0072, "step": 171050 }, { "epoch": 41.09, "learning_rate": 5.178543198351782e-05, "loss": 0.0142, "step": 171060 }, { "epoch": 41.09, "learning_rate": 5.178094787401323e-05, "loss": 0.0149, "step": 171070 }, { "epoch": 41.09, "learning_rate": 5.1776463750166415e-05, "loss": 0.0183, "step": 171080 }, { "epoch": 41.09, "learning_rate": 5.1771979612013486e-05, "loss": 0.0126, "step": 171090 }, { "epoch": 41.1, "learning_rate": 5.176749545959058e-05, "loss": 0.0084, "step": 171100 }, { "epoch": 41.1, "learning_rate": 5.176301129293377e-05, "loss": 0.0069, "step": 171110 }, { "epoch": 41.1, "learning_rate": 5.175852711207919e-05, "loss": 0.0047, "step": 171120 }, { "epoch": 41.1, "learning_rate": 5.175404291706296e-05, "loss": 0.0253, "step": 171130 }, { "epoch": 41.1, "learning_rate": 5.174955870792118e-05, "loss": 0.0078, "step": 171140 }, { "epoch": 41.11, "learning_rate": 5.174507448468995e-05, "loss": 0.0095, "step": 171150 }, { "epoch": 41.11, "learning_rate": 5.1740590247405385e-05, "loss": 0.0218, "step": 171160 }, { "epoch": 41.11, "learning_rate": 5.1736105996103625e-05, "loss": 0.0186, "step": 171170 }, { "epoch": 41.11, "learning_rate": 5.1731621730820754e-05, "loss": 0.0261, "step": 171180 }, { "epoch": 41.12, "learning_rate": 5.172713745159291e-05, "loss": 0.0156, "step": 171190 }, { "epoch": 41.12, "learning_rate": 5.172265315845618e-05, "loss": 0.013, "step": 171200 }, { "epoch": 41.12, "learning_rate": 5.171816885144668e-05, "loss": 0.0273, "step": 171210 }, { "epoch": 41.12, "learning_rate": 5.1713684530600536e-05, "loss": 0.0188, "step": 171220 }, { "epoch": 41.12, "learning_rate": 5.1709200195953845e-05, "loss": 0.0195, "step": 171230 }, { "epoch": 41.13, "learning_rate": 5.170471584754274e-05, "loss": 0.0137, "step": 171240 }, { "epoch": 41.13, "learning_rate": 5.170023148540332e-05, "loss": 0.0301, "step": 171250 }, { "epoch": 41.13, "learning_rate": 5.16957471095717e-05, "loss": 0.0227, "step": 171260 }, { "epoch": 41.13, "learning_rate": 5.1691262720084e-05, "loss": 0.0159, "step": 171270 }, { "epoch": 41.14, "learning_rate": 5.1686778316976325e-05, "loss": 0.0154, "step": 171280 }, { "epoch": 41.14, "learning_rate": 5.168229390028478e-05, "loss": 0.0167, "step": 171290 }, { "epoch": 41.14, "learning_rate": 5.167780947004549e-05, "loss": 0.0099, "step": 171300 }, { "epoch": 41.14, "learning_rate": 5.1673325026294587e-05, "loss": 0.0162, "step": 171310 }, { "epoch": 41.15, "learning_rate": 5.1668840569068154e-05, "loss": 0.013, "step": 171320 }, { "epoch": 41.15, "learning_rate": 5.1664356098402324e-05, "loss": 0.0123, "step": 171330 }, { "epoch": 41.15, "learning_rate": 5.16598716143332e-05, "loss": 0.0139, "step": 171340 }, { "epoch": 41.15, "learning_rate": 5.1655387116896894e-05, "loss": 0.0167, "step": 171350 }, { "epoch": 41.15, "learning_rate": 5.1650902606129536e-05, "loss": 0.0169, "step": 171360 }, { "epoch": 41.16, "learning_rate": 5.164641808206723e-05, "loss": 0.0116, "step": 171370 }, { "epoch": 41.16, "learning_rate": 5.1641933544746094e-05, "loss": 0.0197, "step": 171380 }, { "epoch": 41.16, "learning_rate": 5.1637448994202244e-05, "loss": 0.0089, "step": 171390 }, { "epoch": 41.16, "learning_rate": 5.1632964430471786e-05, "loss": 0.0141, "step": 171400 }, { "epoch": 41.17, "learning_rate": 5.162847985359084e-05, "loss": 0.0114, "step": 171410 }, { "epoch": 41.17, "learning_rate": 5.162399526359551e-05, "loss": 0.0113, "step": 171420 }, { "epoch": 41.17, "learning_rate": 5.1619510660521934e-05, "loss": 0.0216, "step": 171430 }, { "epoch": 41.17, "learning_rate": 5.1615026044406215e-05, "loss": 0.0166, "step": 171440 }, { "epoch": 41.18, "learning_rate": 5.161054141528446e-05, "loss": 0.0106, "step": 171450 }, { "epoch": 41.18, "learning_rate": 5.160605677319281e-05, "loss": 0.0111, "step": 171460 }, { "epoch": 41.18, "learning_rate": 5.160157211816735e-05, "loss": 0.0255, "step": 171470 }, { "epoch": 41.18, "learning_rate": 5.15970874502442e-05, "loss": 0.0181, "step": 171480 }, { "epoch": 41.18, "learning_rate": 5.15926027694595e-05, "loss": 0.008, "step": 171490 }, { "epoch": 41.19, "learning_rate": 5.1588118075849345e-05, "loss": 0.0161, "step": 171500 }, { "epoch": 41.19, "learning_rate": 5.1583633369449855e-05, "loss": 0.0199, "step": 171510 }, { "epoch": 41.19, "learning_rate": 5.157914865029715e-05, "loss": 0.0211, "step": 171520 }, { "epoch": 41.19, "learning_rate": 5.157466391842735e-05, "loss": 0.0215, "step": 171530 }, { "epoch": 41.2, "learning_rate": 5.157017917387655e-05, "loss": 0.0117, "step": 171540 }, { "epoch": 41.2, "learning_rate": 5.1565694416680874e-05, "loss": 0.0274, "step": 171550 }, { "epoch": 41.2, "learning_rate": 5.156120964687646e-05, "loss": 0.0225, "step": 171560 }, { "epoch": 41.2, "learning_rate": 5.15567248644994e-05, "loss": 0.0208, "step": 171570 }, { "epoch": 41.2, "learning_rate": 5.155224006958583e-05, "loss": 0.0167, "step": 171580 }, { "epoch": 41.21, "learning_rate": 5.154775526217186e-05, "loss": 0.023, "step": 171590 }, { "epoch": 41.21, "learning_rate": 5.154327044229358e-05, "loss": 0.0203, "step": 171600 }, { "epoch": 41.21, "learning_rate": 5.153878560998716e-05, "loss": 0.0141, "step": 171610 }, { "epoch": 41.21, "learning_rate": 5.153430076528867e-05, "loss": 0.0116, "step": 171620 }, { "epoch": 41.22, "learning_rate": 5.152981590823424e-05, "loss": 0.0109, "step": 171630 }, { "epoch": 41.22, "learning_rate": 5.1525331038860006e-05, "loss": 0.0092, "step": 171640 }, { "epoch": 41.22, "learning_rate": 5.152084615720205e-05, "loss": 0.0206, "step": 171650 }, { "epoch": 41.22, "learning_rate": 5.151636126329653e-05, "loss": 0.0106, "step": 171660 }, { "epoch": 41.23, "learning_rate": 5.151187635717952e-05, "loss": 0.0162, "step": 171670 }, { "epoch": 41.23, "learning_rate": 5.1507391438887184e-05, "loss": 0.0143, "step": 171680 }, { "epoch": 41.23, "learning_rate": 5.1502906508455604e-05, "loss": 0.0148, "step": 171690 }, { "epoch": 41.23, "learning_rate": 5.149842156592092e-05, "loss": 0.0155, "step": 171700 }, { "epoch": 41.23, "learning_rate": 5.149393661131924e-05, "loss": 0.0209, "step": 171710 }, { "epoch": 41.24, "learning_rate": 5.1489451644686685e-05, "loss": 0.0127, "step": 171720 }, { "epoch": 41.24, "learning_rate": 5.148496666605935e-05, "loss": 0.0092, "step": 171730 }, { "epoch": 41.24, "learning_rate": 5.148048167547338e-05, "loss": 0.0103, "step": 171740 }, { "epoch": 41.24, "learning_rate": 5.14759966729649e-05, "loss": 0.016, "step": 171750 }, { "epoch": 41.25, "learning_rate": 5.147151165857001e-05, "loss": 0.0108, "step": 171760 }, { "epoch": 41.25, "learning_rate": 5.146702663232483e-05, "loss": 0.0046, "step": 171770 }, { "epoch": 41.25, "learning_rate": 5.146254159426548e-05, "loss": 0.0159, "step": 171780 }, { "epoch": 41.25, "learning_rate": 5.1458056544428076e-05, "loss": 0.0119, "step": 171790 }, { "epoch": 41.26, "learning_rate": 5.145357148284876e-05, "loss": 0.0107, "step": 171800 }, { "epoch": 41.26, "learning_rate": 5.1449086409563615e-05, "loss": 0.0144, "step": 171810 }, { "epoch": 41.26, "learning_rate": 5.144460132460879e-05, "loss": 0.0048, "step": 171820 }, { "epoch": 41.26, "learning_rate": 5.144011622802039e-05, "loss": 0.023, "step": 171830 }, { "epoch": 41.26, "learning_rate": 5.1435631119834526e-05, "loss": 0.0094, "step": 171840 }, { "epoch": 41.27, "learning_rate": 5.143114600008733e-05, "loss": 0.0105, "step": 171850 }, { "epoch": 41.27, "learning_rate": 5.142666086881491e-05, "loss": 0.0134, "step": 171860 }, { "epoch": 41.27, "learning_rate": 5.1422175726053415e-05, "loss": 0.0071, "step": 171870 }, { "epoch": 41.27, "learning_rate": 5.1417690571838915e-05, "loss": 0.013, "step": 171880 }, { "epoch": 41.28, "learning_rate": 5.141320540620758e-05, "loss": 0.0256, "step": 171890 }, { "epoch": 41.28, "learning_rate": 5.14087202291955e-05, "loss": 0.011, "step": 171900 }, { "epoch": 41.28, "learning_rate": 5.140423504083878e-05, "loss": 0.0158, "step": 171910 }, { "epoch": 41.28, "learning_rate": 5.1399749841173596e-05, "loss": 0.0422, "step": 171920 }, { "epoch": 41.28, "learning_rate": 5.1395264630236e-05, "loss": 0.0125, "step": 171930 }, { "epoch": 41.29, "learning_rate": 5.139077940806219e-05, "loss": 0.0219, "step": 171940 }, { "epoch": 41.29, "learning_rate": 5.1386294174688195e-05, "loss": 0.0079, "step": 171950 }, { "epoch": 41.29, "learning_rate": 5.13818089301502e-05, "loss": 0.0179, "step": 171960 }, { "epoch": 41.29, "learning_rate": 5.137732367448431e-05, "loss": 0.0152, "step": 171970 }, { "epoch": 41.3, "learning_rate": 5.137283840772663e-05, "loss": 0.0183, "step": 171980 }, { "epoch": 41.3, "learning_rate": 5.136835312991332e-05, "loss": 0.0223, "step": 171990 }, { "epoch": 41.3, "learning_rate": 5.136386784108045e-05, "loss": 0.0116, "step": 172000 }, { "epoch": 41.3, "learning_rate": 5.135938254126417e-05, "loss": 0.0331, "step": 172010 }, { "epoch": 41.31, "learning_rate": 5.13548972305006e-05, "loss": 0.0251, "step": 172020 }, { "epoch": 41.31, "learning_rate": 5.1350411908825836e-05, "loss": 0.0102, "step": 172030 }, { "epoch": 41.31, "learning_rate": 5.134592657627605e-05, "loss": 0.0157, "step": 172040 }, { "epoch": 41.31, "learning_rate": 5.13414412328873e-05, "loss": 0.0169, "step": 172050 }, { "epoch": 41.31, "learning_rate": 5.133695587869577e-05, "loss": 0.0152, "step": 172060 }, { "epoch": 41.32, "learning_rate": 5.133247051373752e-05, "loss": 0.015, "step": 172070 }, { "epoch": 41.32, "learning_rate": 5.132798513804872e-05, "loss": 0.0111, "step": 172080 }, { "epoch": 41.32, "learning_rate": 5.132349975166546e-05, "loss": 0.0144, "step": 172090 }, { "epoch": 41.32, "learning_rate": 5.1319014354623875e-05, "loss": 0.0227, "step": 172100 }, { "epoch": 41.33, "learning_rate": 5.1314528946960095e-05, "loss": 0.0189, "step": 172110 }, { "epoch": 41.33, "learning_rate": 5.131004352871022e-05, "loss": 0.0364, "step": 172120 }, { "epoch": 41.33, "learning_rate": 5.1305558099910386e-05, "loss": 0.0092, "step": 172130 }, { "epoch": 41.33, "learning_rate": 5.1301072660596726e-05, "loss": 0.0084, "step": 172140 }, { "epoch": 41.34, "learning_rate": 5.129658721080532e-05, "loss": 0.0201, "step": 172150 }, { "epoch": 41.34, "learning_rate": 5.129210175057236e-05, "loss": 0.0112, "step": 172160 }, { "epoch": 41.34, "learning_rate": 5.128761627993389e-05, "loss": 0.0199, "step": 172170 }, { "epoch": 41.34, "learning_rate": 5.1283130798926096e-05, "loss": 0.0131, "step": 172180 }, { "epoch": 41.34, "learning_rate": 5.127864530758505e-05, "loss": 0.013, "step": 172190 }, { "epoch": 41.35, "learning_rate": 5.127415980594691e-05, "loss": 0.0135, "step": 172200 }, { "epoch": 41.35, "learning_rate": 5.1269674294047776e-05, "loss": 0.0239, "step": 172210 }, { "epoch": 41.35, "learning_rate": 5.126518877192378e-05, "loss": 0.0138, "step": 172220 }, { "epoch": 41.35, "learning_rate": 5.126070323961106e-05, "loss": 0.0417, "step": 172230 }, { "epoch": 41.36, "learning_rate": 5.12562176971457e-05, "loss": 0.0165, "step": 172240 }, { "epoch": 41.36, "learning_rate": 5.125173214456387e-05, "loss": 0.0084, "step": 172250 }, { "epoch": 41.36, "learning_rate": 5.1247246581901645e-05, "loss": 0.0147, "step": 172260 }, { "epoch": 41.36, "learning_rate": 5.124276100919518e-05, "loss": 0.0185, "step": 172270 }, { "epoch": 41.36, "learning_rate": 5.12382754264806e-05, "loss": 0.0076, "step": 172280 }, { "epoch": 41.37, "learning_rate": 5.1233789833793985e-05, "loss": 0.0135, "step": 172290 }, { "epoch": 41.37, "learning_rate": 5.1229304231171526e-05, "loss": 0.0162, "step": 172300 }, { "epoch": 41.37, "learning_rate": 5.12248186186493e-05, "loss": 0.0185, "step": 172310 }, { "epoch": 41.37, "learning_rate": 5.122033299626343e-05, "loss": 0.0132, "step": 172320 }, { "epoch": 41.38, "learning_rate": 5.121584736405005e-05, "loss": 0.0291, "step": 172330 }, { "epoch": 41.38, "learning_rate": 5.121136172204528e-05, "loss": 0.0168, "step": 172340 }, { "epoch": 41.38, "learning_rate": 5.120687607028528e-05, "loss": 0.0105, "step": 172350 }, { "epoch": 41.38, "learning_rate": 5.12023904088061e-05, "loss": 0.0159, "step": 172360 }, { "epoch": 41.39, "learning_rate": 5.1197904737643945e-05, "loss": 0.0261, "step": 172370 }, { "epoch": 41.39, "learning_rate": 5.1193419056834856e-05, "loss": 0.011, "step": 172380 }, { "epoch": 41.39, "learning_rate": 5.118893336641501e-05, "loss": 0.014, "step": 172390 }, { "epoch": 41.39, "learning_rate": 5.118444766642053e-05, "loss": 0.01, "step": 172400 }, { "epoch": 41.39, "learning_rate": 5.1179961956887525e-05, "loss": 0.0156, "step": 172410 }, { "epoch": 41.4, "learning_rate": 5.1175476237852136e-05, "loss": 0.0226, "step": 172420 }, { "epoch": 41.4, "learning_rate": 5.117099050935045e-05, "loss": 0.0074, "step": 172430 }, { "epoch": 41.4, "learning_rate": 5.116650477141863e-05, "loss": 0.0215, "step": 172440 }, { "epoch": 41.4, "learning_rate": 5.116201902409279e-05, "loss": 0.011, "step": 172450 }, { "epoch": 41.41, "learning_rate": 5.115753326740904e-05, "loss": 0.01, "step": 172460 }, { "epoch": 41.41, "learning_rate": 5.115304750140353e-05, "loss": 0.0221, "step": 172470 }, { "epoch": 41.41, "learning_rate": 5.114856172611234e-05, "loss": 0.0111, "step": 172480 }, { "epoch": 41.41, "learning_rate": 5.114407594157166e-05, "loss": 0.0187, "step": 172490 }, { "epoch": 41.42, "learning_rate": 5.113959014781755e-05, "loss": 0.0172, "step": 172500 }, { "epoch": 41.42, "learning_rate": 5.113510434488618e-05, "loss": 0.0183, "step": 172510 }, { "epoch": 41.42, "learning_rate": 5.1130618532813645e-05, "loss": 0.0134, "step": 172520 }, { "epoch": 41.42, "learning_rate": 5.11261327116361e-05, "loss": 0.0288, "step": 172530 }, { "epoch": 41.42, "learning_rate": 5.112164688138964e-05, "loss": 0.0101, "step": 172540 }, { "epoch": 41.43, "learning_rate": 5.11171610421104e-05, "loss": 0.0206, "step": 172550 }, { "epoch": 41.43, "learning_rate": 5.111267519383451e-05, "loss": 0.0118, "step": 172560 }, { "epoch": 41.43, "learning_rate": 5.11081893365981e-05, "loss": 0.0123, "step": 172570 }, { "epoch": 41.43, "learning_rate": 5.110370347043729e-05, "loss": 0.0176, "step": 172580 }, { "epoch": 41.44, "learning_rate": 5.109921759538819e-05, "loss": 0.0105, "step": 172590 }, { "epoch": 41.44, "learning_rate": 5.1094731711486956e-05, "loss": 0.0076, "step": 172600 }, { "epoch": 41.44, "learning_rate": 5.109024581876969e-05, "loss": 0.021, "step": 172610 }, { "epoch": 41.44, "learning_rate": 5.108575991727251e-05, "loss": 0.0125, "step": 172620 }, { "epoch": 41.44, "learning_rate": 5.108127400703156e-05, "loss": 0.0106, "step": 172630 }, { "epoch": 41.45, "learning_rate": 5.107678808808298e-05, "loss": 0.0079, "step": 172640 }, { "epoch": 41.45, "learning_rate": 5.107230216046287e-05, "loss": 0.0157, "step": 172650 }, { "epoch": 41.45, "learning_rate": 5.1067816224207354e-05, "loss": 0.008, "step": 172660 }, { "epoch": 41.45, "learning_rate": 5.106333027935256e-05, "loss": 0.0093, "step": 172670 }, { "epoch": 41.46, "learning_rate": 5.105884432593465e-05, "loss": 0.0206, "step": 172680 }, { "epoch": 41.46, "learning_rate": 5.1054358363989684e-05, "loss": 0.0232, "step": 172690 }, { "epoch": 41.46, "learning_rate": 5.1049872393553846e-05, "loss": 0.0172, "step": 172700 }, { "epoch": 41.46, "learning_rate": 5.1045386414663244e-05, "loss": 0.0126, "step": 172710 }, { "epoch": 41.47, "learning_rate": 5.104090042735399e-05, "loss": 0.0107, "step": 172720 }, { "epoch": 41.47, "learning_rate": 5.103641443166223e-05, "loss": 0.0099, "step": 172730 }, { "epoch": 41.47, "learning_rate": 5.103192842762407e-05, "loss": 0.0119, "step": 172740 }, { "epoch": 41.47, "learning_rate": 5.102744241527565e-05, "loss": 0.0121, "step": 172750 }, { "epoch": 41.47, "learning_rate": 5.1022956394653096e-05, "loss": 0.0125, "step": 172760 }, { "epoch": 41.48, "learning_rate": 5.101847036579254e-05, "loss": 0.0128, "step": 172770 }, { "epoch": 41.48, "learning_rate": 5.1013984328730105e-05, "loss": 0.0191, "step": 172780 }, { "epoch": 41.48, "learning_rate": 5.10094982835019e-05, "loss": 0.0099, "step": 172790 }, { "epoch": 41.48, "learning_rate": 5.100501223014408e-05, "loss": 0.0094, "step": 172800 }, { "epoch": 41.49, "learning_rate": 5.100052616869274e-05, "loss": 0.0204, "step": 172810 }, { "epoch": 41.49, "learning_rate": 5.099604009918403e-05, "loss": 0.0113, "step": 172820 }, { "epoch": 41.49, "learning_rate": 5.0991554021654074e-05, "loss": 0.0301, "step": 172830 }, { "epoch": 41.49, "learning_rate": 5.098706793613901e-05, "loss": 0.0162, "step": 172840 }, { "epoch": 41.5, "learning_rate": 5.098258184267494e-05, "loss": 0.0063, "step": 172850 }, { "epoch": 41.5, "learning_rate": 5.0978095741298006e-05, "loss": 0.0197, "step": 172860 }, { "epoch": 41.5, "learning_rate": 5.097360963204432e-05, "loss": 0.0158, "step": 172870 }, { "epoch": 41.5, "learning_rate": 5.0969123514950024e-05, "loss": 0.0286, "step": 172880 }, { "epoch": 41.5, "learning_rate": 5.096463739005125e-05, "loss": 0.0111, "step": 172890 }, { "epoch": 41.51, "learning_rate": 5.096015125738413e-05, "loss": 0.015, "step": 172900 }, { "epoch": 41.51, "learning_rate": 5.0955665116984766e-05, "loss": 0.0102, "step": 172910 }, { "epoch": 41.51, "learning_rate": 5.095117896888929e-05, "loss": 0.0126, "step": 172920 }, { "epoch": 41.51, "learning_rate": 5.094669281313386e-05, "loss": 0.022, "step": 172930 }, { "epoch": 41.52, "learning_rate": 5.0942206649754554e-05, "loss": 0.0099, "step": 172940 }, { "epoch": 41.52, "learning_rate": 5.093772047878754e-05, "loss": 0.0483, "step": 172950 }, { "epoch": 41.52, "learning_rate": 5.093323430026894e-05, "loss": 0.0125, "step": 172960 }, { "epoch": 41.52, "learning_rate": 5.092874811423487e-05, "loss": 0.0117, "step": 172970 }, { "epoch": 41.52, "learning_rate": 5.092426192072147e-05, "loss": 0.0145, "step": 172980 }, { "epoch": 41.53, "learning_rate": 5.091977571976485e-05, "loss": 0.0159, "step": 172990 }, { "epoch": 41.53, "learning_rate": 5.0915289511401156e-05, "loss": 0.0183, "step": 173000 }, { "epoch": 41.53, "learning_rate": 5.091080329566651e-05, "loss": 0.0141, "step": 173010 }, { "epoch": 41.53, "learning_rate": 5.090631707259704e-05, "loss": 0.0139, "step": 173020 }, { "epoch": 41.54, "learning_rate": 5.090183084222887e-05, "loss": 0.0229, "step": 173030 }, { "epoch": 41.54, "learning_rate": 5.0897344604598143e-05, "loss": 0.0136, "step": 173040 }, { "epoch": 41.54, "learning_rate": 5.089285835974096e-05, "loss": 0.0166, "step": 173050 }, { "epoch": 41.54, "learning_rate": 5.088837210769346e-05, "loss": 0.0134, "step": 173060 }, { "epoch": 41.55, "learning_rate": 5.08838858484918e-05, "loss": 0.0148, "step": 173070 }, { "epoch": 41.55, "learning_rate": 5.087939958217207e-05, "loss": 0.0236, "step": 173080 }, { "epoch": 41.55, "learning_rate": 5.087491330877042e-05, "loss": 0.0062, "step": 173090 }, { "epoch": 41.55, "learning_rate": 5.0870427028322966e-05, "loss": 0.0083, "step": 173100 }, { "epoch": 41.55, "learning_rate": 5.086594074086584e-05, "loss": 0.0287, "step": 173110 }, { "epoch": 41.56, "learning_rate": 5.0861454446435195e-05, "loss": 0.0479, "step": 173120 }, { "epoch": 41.56, "learning_rate": 5.085696814506711e-05, "loss": 0.0182, "step": 173130 }, { "epoch": 41.56, "learning_rate": 5.085248183679776e-05, "loss": 0.015, "step": 173140 }, { "epoch": 41.56, "learning_rate": 5.084799552166325e-05, "loss": 0.0171, "step": 173150 }, { "epoch": 41.57, "learning_rate": 5.084350919969973e-05, "loss": 0.0148, "step": 173160 }, { "epoch": 41.57, "learning_rate": 5.08390228709433e-05, "loss": 0.0134, "step": 173170 }, { "epoch": 41.57, "learning_rate": 5.0834536535430086e-05, "loss": 0.0147, "step": 173180 }, { "epoch": 41.57, "learning_rate": 5.0830050193196265e-05, "loss": 0.0182, "step": 173190 }, { "epoch": 41.58, "learning_rate": 5.082556384427791e-05, "loss": 0.0211, "step": 173200 }, { "epoch": 41.58, "learning_rate": 5.08210774887112e-05, "loss": 0.0123, "step": 173210 }, { "epoch": 41.58, "learning_rate": 5.081659112653222e-05, "loss": 0.014, "step": 173220 }, { "epoch": 41.58, "learning_rate": 5.0812104757777134e-05, "loss": 0.022, "step": 173230 }, { "epoch": 41.58, "learning_rate": 5.0807618382482044e-05, "loss": 0.0195, "step": 173240 }, { "epoch": 41.59, "learning_rate": 5.08031320006831e-05, "loss": 0.0095, "step": 173250 }, { "epoch": 41.59, "learning_rate": 5.079864561241642e-05, "loss": 0.0119, "step": 173260 }, { "epoch": 41.59, "learning_rate": 5.079415921771813e-05, "loss": 0.0167, "step": 173270 }, { "epoch": 41.59, "learning_rate": 5.0789672816624366e-05, "loss": 0.0088, "step": 173280 }, { "epoch": 41.6, "learning_rate": 5.078518640917127e-05, "loss": 0.0093, "step": 173290 }, { "epoch": 41.6, "learning_rate": 5.078069999539494e-05, "loss": 0.0322, "step": 173300 }, { "epoch": 41.6, "learning_rate": 5.0776213575331557e-05, "loss": 0.0161, "step": 173310 }, { "epoch": 41.6, "learning_rate": 5.077172714901719e-05, "loss": 0.0167, "step": 173320 }, { "epoch": 41.6, "learning_rate": 5.0767240716488006e-05, "loss": 0.0171, "step": 173330 }, { "epoch": 41.61, "learning_rate": 5.0762754277780134e-05, "loss": 0.0185, "step": 173340 }, { "epoch": 41.61, "learning_rate": 5.0758267832929694e-05, "loss": 0.0292, "step": 173350 }, { "epoch": 41.61, "learning_rate": 5.075378138197282e-05, "loss": 0.022, "step": 173360 }, { "epoch": 41.61, "learning_rate": 5.074929492494562e-05, "loss": 0.0131, "step": 173370 }, { "epoch": 41.62, "learning_rate": 5.074480846188427e-05, "loss": 0.01, "step": 173380 }, { "epoch": 41.62, "learning_rate": 5.074032199282486e-05, "loss": 0.0137, "step": 173390 }, { "epoch": 41.62, "learning_rate": 5.0735835517803545e-05, "loss": 0.0207, "step": 173400 }, { "epoch": 41.62, "learning_rate": 5.073134903685644e-05, "loss": 0.0094, "step": 173410 }, { "epoch": 41.63, "learning_rate": 5.072686255001967e-05, "loss": 0.0149, "step": 173420 }, { "epoch": 41.63, "learning_rate": 5.07223760573294e-05, "loss": 0.0069, "step": 173430 }, { "epoch": 41.63, "learning_rate": 5.071788955882171e-05, "loss": 0.0303, "step": 173440 }, { "epoch": 41.63, "learning_rate": 5.0713403054532784e-05, "loss": 0.0031, "step": 173450 }, { "epoch": 41.63, "learning_rate": 5.07089165444987e-05, "loss": 0.0205, "step": 173460 }, { "epoch": 41.64, "learning_rate": 5.070443002875562e-05, "loss": 0.0255, "step": 173470 }, { "epoch": 41.64, "learning_rate": 5.069994350733968e-05, "loss": 0.0121, "step": 173480 }, { "epoch": 41.64, "learning_rate": 5.0695456980286974e-05, "loss": 0.0318, "step": 173490 }, { "epoch": 41.64, "learning_rate": 5.069097044763368e-05, "loss": 0.0365, "step": 173500 }, { "epoch": 41.65, "learning_rate": 5.0686483909415884e-05, "loss": 0.0142, "step": 173510 }, { "epoch": 41.65, "learning_rate": 5.068199736566975e-05, "loss": 0.0112, "step": 173520 }, { "epoch": 41.65, "learning_rate": 5.0677510816431407e-05, "loss": 0.0143, "step": 173530 }, { "epoch": 41.65, "learning_rate": 5.0673024261736955e-05, "loss": 0.0196, "step": 173540 }, { "epoch": 41.66, "learning_rate": 5.066853770162256e-05, "loss": 0.039, "step": 173550 }, { "epoch": 41.66, "learning_rate": 5.0664051136124335e-05, "loss": 0.0122, "step": 173560 }, { "epoch": 41.66, "learning_rate": 5.065956456527843e-05, "loss": 0.0172, "step": 173570 }, { "epoch": 41.66, "learning_rate": 5.0655077989120935e-05, "loss": 0.0188, "step": 173580 }, { "epoch": 41.66, "learning_rate": 5.065059140768802e-05, "loss": 0.0153, "step": 173590 }, { "epoch": 41.67, "learning_rate": 5.0646104821015795e-05, "loss": 0.0189, "step": 173600 }, { "epoch": 41.67, "learning_rate": 5.06416182291404e-05, "loss": 0.016, "step": 173610 }, { "epoch": 41.67, "learning_rate": 5.063713163209798e-05, "loss": 0.0282, "step": 173620 }, { "epoch": 41.67, "learning_rate": 5.063264502992463e-05, "loss": 0.0072, "step": 173630 }, { "epoch": 41.68, "learning_rate": 5.062815842265652e-05, "loss": 0.01, "step": 173640 }, { "epoch": 41.68, "learning_rate": 5.062367181032975e-05, "loss": 0.0157, "step": 173650 }, { "epoch": 41.68, "learning_rate": 5.061918519298047e-05, "loss": 0.0075, "step": 173660 }, { "epoch": 41.68, "learning_rate": 5.061469857064481e-05, "loss": 0.0148, "step": 173670 }, { "epoch": 41.68, "learning_rate": 5.0610211943358885e-05, "loss": 0.025, "step": 173680 }, { "epoch": 41.69, "learning_rate": 5.060572531115886e-05, "loss": 0.0099, "step": 173690 }, { "epoch": 41.69, "learning_rate": 5.060123867408082e-05, "loss": 0.0137, "step": 173700 }, { "epoch": 41.69, "learning_rate": 5.0596752032160945e-05, "loss": 0.0096, "step": 173710 }, { "epoch": 41.69, "learning_rate": 5.0592265385435334e-05, "loss": 0.0159, "step": 173720 }, { "epoch": 41.7, "learning_rate": 5.0587778733940114e-05, "loss": 0.0112, "step": 173730 }, { "epoch": 41.7, "learning_rate": 5.058329207771145e-05, "loss": 0.008, "step": 173740 }, { "epoch": 41.7, "learning_rate": 5.0578805416785446e-05, "loss": 0.0142, "step": 173750 }, { "epoch": 41.7, "learning_rate": 5.0574318751198254e-05, "loss": 0.0058, "step": 173760 }, { "epoch": 41.71, "learning_rate": 5.056983208098598e-05, "loss": 0.0198, "step": 173770 }, { "epoch": 41.71, "learning_rate": 5.0565345406184775e-05, "loss": 0.0124, "step": 173780 }, { "epoch": 41.71, "learning_rate": 5.0560858726830763e-05, "loss": 0.0085, "step": 173790 }, { "epoch": 41.71, "learning_rate": 5.0556372042960074e-05, "loss": 0.0166, "step": 173800 }, { "epoch": 41.71, "learning_rate": 5.0551885354608865e-05, "loss": 0.0201, "step": 173810 }, { "epoch": 41.72, "learning_rate": 5.054739866181322e-05, "loss": 0.0201, "step": 173820 }, { "epoch": 41.72, "learning_rate": 5.054291196460931e-05, "loss": 0.0162, "step": 173830 }, { "epoch": 41.72, "learning_rate": 5.053842526303326e-05, "loss": 0.0204, "step": 173840 }, { "epoch": 41.72, "learning_rate": 5.053393855712119e-05, "loss": 0.0249, "step": 173850 }, { "epoch": 41.73, "learning_rate": 5.052945184690925e-05, "loss": 0.0179, "step": 173860 }, { "epoch": 41.73, "learning_rate": 5.052496513243353e-05, "loss": 0.013, "step": 173870 }, { "epoch": 41.73, "learning_rate": 5.052047841373023e-05, "loss": 0.0252, "step": 173880 }, { "epoch": 41.73, "learning_rate": 5.051599169083543e-05, "loss": 0.0092, "step": 173890 }, { "epoch": 41.74, "learning_rate": 5.0511504963785275e-05, "loss": 0.023, "step": 173900 }, { "epoch": 41.74, "learning_rate": 5.0507018232615914e-05, "loss": 0.0273, "step": 173910 }, { "epoch": 41.74, "learning_rate": 5.050253149736344e-05, "loss": 0.0112, "step": 173920 }, { "epoch": 41.74, "learning_rate": 5.049804475806403e-05, "loss": 0.0395, "step": 173930 }, { "epoch": 41.74, "learning_rate": 5.049355801475378e-05, "loss": 0.012, "step": 173940 }, { "epoch": 41.75, "learning_rate": 5.048907126746886e-05, "loss": 0.0136, "step": 173950 }, { "epoch": 41.75, "learning_rate": 5.048458451624537e-05, "loss": 0.0485, "step": 173960 }, { "epoch": 41.75, "learning_rate": 5.048009776111946e-05, "loss": 0.0115, "step": 173970 }, { "epoch": 41.75, "learning_rate": 5.047561100212726e-05, "loss": 0.0176, "step": 173980 }, { "epoch": 41.76, "learning_rate": 5.047112423930488e-05, "loss": 0.0225, "step": 173990 }, { "epoch": 41.76, "learning_rate": 5.0466637472688495e-05, "loss": 0.0155, "step": 174000 }, { "epoch": 41.76, "learning_rate": 5.046215070231419e-05, "loss": 0.0224, "step": 174010 }, { "epoch": 41.76, "learning_rate": 5.045766392821814e-05, "loss": 0.0105, "step": 174020 }, { "epoch": 41.76, "learning_rate": 5.045317715043646e-05, "loss": 0.0118, "step": 174030 }, { "epoch": 41.77, "learning_rate": 5.044869036900527e-05, "loss": 0.0187, "step": 174040 }, { "epoch": 41.77, "learning_rate": 5.0444203583960725e-05, "loss": 0.0133, "step": 174050 }, { "epoch": 41.77, "learning_rate": 5.0439716795338934e-05, "loss": 0.0167, "step": 174060 }, { "epoch": 41.77, "learning_rate": 5.043523000317605e-05, "loss": 0.0198, "step": 174070 }, { "epoch": 41.78, "learning_rate": 5.04307432075082e-05, "loss": 0.0389, "step": 174080 }, { "epoch": 41.78, "learning_rate": 5.042625640837152e-05, "loss": 0.0234, "step": 174090 }, { "epoch": 41.78, "learning_rate": 5.042176960580214e-05, "loss": 0.0103, "step": 174100 }, { "epoch": 41.78, "learning_rate": 5.041728279983618e-05, "loss": 0.0171, "step": 174110 }, { "epoch": 41.79, "learning_rate": 5.0412795990509784e-05, "loss": 0.0115, "step": 174120 }, { "epoch": 41.79, "learning_rate": 5.040830917785909e-05, "loss": 0.0137, "step": 174130 }, { "epoch": 41.79, "learning_rate": 5.0403822361920224e-05, "loss": 0.0108, "step": 174140 }, { "epoch": 41.79, "learning_rate": 5.039933554272932e-05, "loss": 0.0103, "step": 174150 }, { "epoch": 41.79, "learning_rate": 5.0394848720322516e-05, "loss": 0.0421, "step": 174160 }, { "epoch": 41.8, "learning_rate": 5.0390361894735937e-05, "loss": 0.0201, "step": 174170 }, { "epoch": 41.8, "learning_rate": 5.0385875066005727e-05, "loss": 0.007, "step": 174180 }, { "epoch": 41.8, "learning_rate": 5.038138823416802e-05, "loss": 0.0122, "step": 174190 }, { "epoch": 41.8, "learning_rate": 5.0376901399258905e-05, "loss": 0.008, "step": 174200 }, { "epoch": 41.81, "learning_rate": 5.0372414561314576e-05, "loss": 0.0087, "step": 174210 }, { "epoch": 41.81, "learning_rate": 5.036792772037115e-05, "loss": 0.0227, "step": 174220 }, { "epoch": 41.81, "learning_rate": 5.036344087646473e-05, "loss": 0.0191, "step": 174230 }, { "epoch": 41.81, "learning_rate": 5.035895402963149e-05, "loss": 0.0165, "step": 174240 }, { "epoch": 41.82, "learning_rate": 5.035446717990752e-05, "loss": 0.0202, "step": 174250 }, { "epoch": 41.82, "learning_rate": 5.0349980327328994e-05, "loss": 0.0259, "step": 174260 }, { "epoch": 41.82, "learning_rate": 5.0345493471932025e-05, "loss": 0.0071, "step": 174270 }, { "epoch": 41.82, "learning_rate": 5.034100661375275e-05, "loss": 0.0143, "step": 174280 }, { "epoch": 41.82, "learning_rate": 5.0336519752827305e-05, "loss": 0.0189, "step": 174290 }, { "epoch": 41.83, "learning_rate": 5.0332032889191816e-05, "loss": 0.0121, "step": 174300 }, { "epoch": 41.83, "learning_rate": 5.032754602288242e-05, "loss": 0.0222, "step": 174310 }, { "epoch": 41.83, "learning_rate": 5.0323059153935235e-05, "loss": 0.01, "step": 174320 }, { "epoch": 41.83, "learning_rate": 5.031857228238643e-05, "loss": 0.0152, "step": 174330 }, { "epoch": 41.84, "learning_rate": 5.0314085408272116e-05, "loss": 0.0087, "step": 174340 }, { "epoch": 41.84, "learning_rate": 5.030959853162843e-05, "loss": 0.0202, "step": 174350 }, { "epoch": 41.84, "learning_rate": 5.03051116524915e-05, "loss": 0.0143, "step": 174360 }, { "epoch": 41.84, "learning_rate": 5.030062477089746e-05, "loss": 0.0062, "step": 174370 }, { "epoch": 41.84, "learning_rate": 5.029613788688244e-05, "loss": 0.0073, "step": 174380 }, { "epoch": 41.85, "learning_rate": 5.0291651000482596e-05, "loss": 0.0201, "step": 174390 }, { "epoch": 41.85, "learning_rate": 5.028716411173405e-05, "loss": 0.0111, "step": 174400 }, { "epoch": 41.85, "learning_rate": 5.028267722067292e-05, "loss": 0.0151, "step": 174410 }, { "epoch": 41.85, "learning_rate": 5.027819032733536e-05, "loss": 0.0152, "step": 174420 }, { "epoch": 41.86, "learning_rate": 5.02737034317575e-05, "loss": 0.0181, "step": 174430 }, { "epoch": 41.86, "learning_rate": 5.026921653397546e-05, "loss": 0.0118, "step": 174440 }, { "epoch": 41.86, "learning_rate": 5.026472963402538e-05, "loss": 0.0211, "step": 174450 }, { "epoch": 41.86, "learning_rate": 5.026024273194339e-05, "loss": 0.0281, "step": 174460 }, { "epoch": 41.87, "learning_rate": 5.0255755827765636e-05, "loss": 0.0177, "step": 174470 }, { "epoch": 41.87, "learning_rate": 5.025126892152825e-05, "loss": 0.0173, "step": 174480 }, { "epoch": 41.87, "learning_rate": 5.024678201326736e-05, "loss": 0.0161, "step": 174490 }, { "epoch": 41.87, "learning_rate": 5.0242295103019086e-05, "loss": 0.0227, "step": 174500 }, { "epoch": 41.87, "learning_rate": 5.02378081908196e-05, "loss": 0.0125, "step": 174510 }, { "epoch": 41.88, "learning_rate": 5.023332127670499e-05, "loss": 0.0166, "step": 174520 }, { "epoch": 41.88, "learning_rate": 5.0228834360711416e-05, "loss": 0.0066, "step": 174530 }, { "epoch": 41.88, "learning_rate": 5.022434744287502e-05, "loss": 0.0147, "step": 174540 }, { "epoch": 41.88, "learning_rate": 5.021986052323191e-05, "loss": 0.0163, "step": 174550 }, { "epoch": 41.89, "learning_rate": 5.021537360181824e-05, "loss": 0.0237, "step": 174560 }, { "epoch": 41.89, "learning_rate": 5.021088667867012e-05, "loss": 0.0264, "step": 174570 }, { "epoch": 41.89, "learning_rate": 5.020639975382372e-05, "loss": 0.0079, "step": 174580 }, { "epoch": 41.89, "learning_rate": 5.0201912827315156e-05, "loss": 0.0099, "step": 174590 }, { "epoch": 41.9, "learning_rate": 5.019742589918055e-05, "loss": 0.0128, "step": 174600 }, { "epoch": 41.9, "learning_rate": 5.019293896945605e-05, "loss": 0.0154, "step": 174610 }, { "epoch": 41.9, "learning_rate": 5.018845203817779e-05, "loss": 0.0129, "step": 174620 }, { "epoch": 41.9, "learning_rate": 5.018396510538189e-05, "loss": 0.0196, "step": 174630 }, { "epoch": 41.9, "learning_rate": 5.017947817110449e-05, "loss": 0.0097, "step": 174640 }, { "epoch": 41.91, "learning_rate": 5.0174991235381744e-05, "loss": 0.0235, "step": 174650 }, { "epoch": 41.91, "learning_rate": 5.0170504298249755e-05, "loss": 0.0098, "step": 174660 }, { "epoch": 41.91, "learning_rate": 5.016601735974468e-05, "loss": 0.0204, "step": 174670 }, { "epoch": 41.91, "learning_rate": 5.0161530419902644e-05, "loss": 0.0215, "step": 174680 }, { "epoch": 41.92, "learning_rate": 5.015704347875977e-05, "loss": 0.0107, "step": 174690 }, { "epoch": 41.92, "learning_rate": 5.0152556536352224e-05, "loss": 0.0171, "step": 174700 }, { "epoch": 41.92, "learning_rate": 5.014806959271609e-05, "loss": 0.0082, "step": 174710 }, { "epoch": 41.92, "learning_rate": 5.0143582647887556e-05, "loss": 0.037, "step": 174720 }, { "epoch": 41.92, "learning_rate": 5.013909570190273e-05, "loss": 0.0159, "step": 174730 }, { "epoch": 41.93, "learning_rate": 5.013460875479774e-05, "loss": 0.0196, "step": 174740 }, { "epoch": 41.93, "learning_rate": 5.013012180660872e-05, "loss": 0.0158, "step": 174750 }, { "epoch": 41.93, "learning_rate": 5.012563485737182e-05, "loss": 0.0089, "step": 174760 }, { "epoch": 41.93, "learning_rate": 5.0121147907123164e-05, "loss": 0.0233, "step": 174770 }, { "epoch": 41.94, "learning_rate": 5.0116660955898885e-05, "loss": 0.0146, "step": 174780 }, { "epoch": 41.94, "learning_rate": 5.0112174003735124e-05, "loss": 0.011, "step": 174790 }, { "epoch": 41.94, "learning_rate": 5.0107687050668006e-05, "loss": 0.0059, "step": 174800 }, { "epoch": 41.94, "learning_rate": 5.010320009673366e-05, "loss": 0.017, "step": 174810 }, { "epoch": 41.95, "learning_rate": 5.0098713141968256e-05, "loss": 0.0144, "step": 174820 }, { "epoch": 41.95, "learning_rate": 5.009422618640788e-05, "loss": 0.0152, "step": 174830 }, { "epoch": 41.95, "learning_rate": 5.00897392300887e-05, "loss": 0.0111, "step": 174840 }, { "epoch": 42.0, "learning_rate": 5.0085252273046825e-05, "loss": 0.0147, "step": 174850 }, { "epoch": 42.0, "learning_rate": 5.008076531531841e-05, "loss": 0.0217, "step": 174860 }, { "epoch": 42.01, "learning_rate": 5.0076278356939576e-05, "loss": 0.0148, "step": 174870 }, { "epoch": 42.01, "learning_rate": 5.007179139794645e-05, "loss": 0.0158, "step": 174880 }, { "epoch": 42.01, "learning_rate": 5.0067304438375205e-05, "loss": 0.0085, "step": 174890 }, { "epoch": 42.01, "learning_rate": 5.0062817478261925e-05, "loss": 0.0242, "step": 174900 }, { "epoch": 42.01, "learning_rate": 5.005833051764278e-05, "loss": 0.013, "step": 174910 }, { "epoch": 42.02, "learning_rate": 5.005384355655389e-05, "loss": 0.0218, "step": 174920 }, { "epoch": 42.02, "learning_rate": 5.0049356595031384e-05, "loss": 0.0137, "step": 174930 }, { "epoch": 42.02, "learning_rate": 5.004486963311142e-05, "loss": 0.0119, "step": 174940 }, { "epoch": 42.02, "learning_rate": 5.004038267083009e-05, "loss": 0.0119, "step": 174950 }, { "epoch": 42.03, "learning_rate": 5.003589570822358e-05, "loss": 0.0045, "step": 174960 }, { "epoch": 42.03, "learning_rate": 5.0031408745327965e-05, "loss": 0.0072, "step": 174970 }, { "epoch": 42.03, "learning_rate": 5.0026921782179434e-05, "loss": 0.0142, "step": 174980 }, { "epoch": 42.03, "learning_rate": 5.00224348188141e-05, "loss": 0.0046, "step": 174990 }, { "epoch": 42.04, "learning_rate": 5.0017947855268076e-05, "loss": 0.0097, "step": 175000 }, { "epoch": 42.04, "learning_rate": 5.001346089157754e-05, "loss": 0.0278, "step": 175010 }, { "epoch": 42.04, "learning_rate": 5.000897392777858e-05, "loss": 0.0113, "step": 175020 }, { "epoch": 42.04, "learning_rate": 5.000448696390736e-05, "loss": 0.0129, "step": 175030 }, { "epoch": 42.04, "learning_rate": 5e-05, "loss": 0.0074, "step": 175040 }, { "epoch": 42.05, "learning_rate": 4.999551303609265e-05, "loss": 0.0334, "step": 175050 }, { "epoch": 42.05, "learning_rate": 4.9991026072221425e-05, "loss": 0.0214, "step": 175060 }, { "epoch": 42.05, "learning_rate": 4.998653910842249e-05, "loss": 0.0071, "step": 175070 }, { "epoch": 42.05, "learning_rate": 4.9982052144731936e-05, "loss": 0.0205, "step": 175080 }, { "epoch": 42.06, "learning_rate": 4.9977565181185916e-05, "loss": 0.0191, "step": 175090 }, { "epoch": 42.06, "learning_rate": 4.997307821782057e-05, "loss": 0.0152, "step": 175100 }, { "epoch": 42.06, "learning_rate": 4.9968591254672026e-05, "loss": 0.0108, "step": 175110 }, { "epoch": 42.06, "learning_rate": 4.996410429177644e-05, "loss": 0.0088, "step": 175120 }, { "epoch": 42.06, "learning_rate": 4.9959617329169914e-05, "loss": 0.0421, "step": 175130 }, { "epoch": 42.07, "learning_rate": 4.9955130366888595e-05, "loss": 0.014, "step": 175140 }, { "epoch": 42.07, "learning_rate": 4.9950643404968614e-05, "loss": 0.0249, "step": 175150 }, { "epoch": 42.07, "learning_rate": 4.994615644344613e-05, "loss": 0.0239, "step": 175160 }, { "epoch": 42.07, "learning_rate": 4.994166948235723e-05, "loss": 0.013, "step": 175170 }, { "epoch": 42.08, "learning_rate": 4.993718252173808e-05, "loss": 0.0183, "step": 175180 }, { "epoch": 42.08, "learning_rate": 4.99326955616248e-05, "loss": 0.0071, "step": 175190 }, { "epoch": 42.08, "learning_rate": 4.9928208602053546e-05, "loss": 0.0079, "step": 175200 }, { "epoch": 42.08, "learning_rate": 4.992372164306044e-05, "loss": 0.0083, "step": 175210 }, { "epoch": 42.09, "learning_rate": 4.99192346846816e-05, "loss": 0.0076, "step": 175220 }, { "epoch": 42.09, "learning_rate": 4.9914747726953186e-05, "loss": 0.0132, "step": 175230 }, { "epoch": 42.09, "learning_rate": 4.991026076991131e-05, "loss": 0.0127, "step": 175240 }, { "epoch": 42.09, "learning_rate": 4.990577381359212e-05, "loss": 0.0209, "step": 175250 }, { "epoch": 42.09, "learning_rate": 4.990128685803176e-05, "loss": 0.0158, "step": 175260 }, { "epoch": 42.1, "learning_rate": 4.989679990326635e-05, "loss": 0.0135, "step": 175270 }, { "epoch": 42.1, "learning_rate": 4.9892312949332006e-05, "loss": 0.01, "step": 175280 }, { "epoch": 42.1, "learning_rate": 4.988782599626489e-05, "loss": 0.0223, "step": 175290 }, { "epoch": 42.1, "learning_rate": 4.9883339044101134e-05, "loss": 0.0162, "step": 175300 }, { "epoch": 42.11, "learning_rate": 4.987885209287685e-05, "loss": 0.0268, "step": 175310 }, { "epoch": 42.11, "learning_rate": 4.9874365142628194e-05, "loss": 0.0137, "step": 175320 }, { "epoch": 42.11, "learning_rate": 4.9869878193391284e-05, "loss": 0.0147, "step": 175330 }, { "epoch": 42.11, "learning_rate": 4.9865391245202276e-05, "loss": 0.0148, "step": 175340 }, { "epoch": 42.12, "learning_rate": 4.98609042980973e-05, "loss": 0.0114, "step": 175350 }, { "epoch": 42.12, "learning_rate": 4.9856417352112456e-05, "loss": 0.0103, "step": 175360 }, { "epoch": 42.12, "learning_rate": 4.985193040728391e-05, "loss": 0.0055, "step": 175370 }, { "epoch": 42.12, "learning_rate": 4.984744346364779e-05, "loss": 0.016, "step": 175380 }, { "epoch": 42.12, "learning_rate": 4.9842956521240233e-05, "loss": 0.0188, "step": 175390 }, { "epoch": 42.13, "learning_rate": 4.983846958009738e-05, "loss": 0.0104, "step": 175400 }, { "epoch": 42.13, "learning_rate": 4.9833982640255334e-05, "loss": 0.0215, "step": 175410 }, { "epoch": 42.13, "learning_rate": 4.982949570175026e-05, "loss": 0.0308, "step": 175420 }, { "epoch": 42.13, "learning_rate": 4.982500876461826e-05, "loss": 0.0104, "step": 175430 }, { "epoch": 42.14, "learning_rate": 4.982052182889551e-05, "loss": 0.0081, "step": 175440 }, { "epoch": 42.14, "learning_rate": 4.981603489461813e-05, "loss": 0.0248, "step": 175450 }, { "epoch": 42.14, "learning_rate": 4.9811547961822226e-05, "loss": 0.0189, "step": 175460 }, { "epoch": 42.14, "learning_rate": 4.980706103054396e-05, "loss": 0.0121, "step": 175470 }, { "epoch": 42.14, "learning_rate": 4.980257410081946e-05, "loss": 0.0112, "step": 175480 }, { "epoch": 42.15, "learning_rate": 4.979808717268487e-05, "loss": 0.0124, "step": 175490 }, { "epoch": 42.15, "learning_rate": 4.979360024617629e-05, "loss": 0.0123, "step": 175500 }, { "epoch": 42.15, "learning_rate": 4.9789113321329887e-05, "loss": 0.0118, "step": 175510 }, { "epoch": 42.15, "learning_rate": 4.9784626398181775e-05, "loss": 0.0113, "step": 175520 }, { "epoch": 42.16, "learning_rate": 4.97801394767681e-05, "loss": 0.0067, "step": 175530 }, { "epoch": 42.16, "learning_rate": 4.9775652557125005e-05, "loss": 0.0153, "step": 175540 }, { "epoch": 42.16, "learning_rate": 4.977116563928859e-05, "loss": 0.0263, "step": 175550 }, { "epoch": 42.16, "learning_rate": 4.9766678723295026e-05, "loss": 0.0097, "step": 175560 }, { "epoch": 42.17, "learning_rate": 4.976219180918041e-05, "loss": 0.0078, "step": 175570 }, { "epoch": 42.17, "learning_rate": 4.975770489698092e-05, "loss": 0.016, "step": 175580 }, { "epoch": 42.17, "learning_rate": 4.9753217986732665e-05, "loss": 0.0129, "step": 175590 }, { "epoch": 42.17, "learning_rate": 4.974873107847176e-05, "loss": 0.0225, "step": 175600 }, { "epoch": 42.17, "learning_rate": 4.974424417223437e-05, "loss": 0.0192, "step": 175610 }, { "epoch": 42.18, "learning_rate": 4.973975726805661e-05, "loss": 0.0087, "step": 175620 }, { "epoch": 42.18, "learning_rate": 4.973527036597464e-05, "loss": 0.0092, "step": 175630 }, { "epoch": 42.18, "learning_rate": 4.973078346602456e-05, "loss": 0.008, "step": 175640 }, { "epoch": 42.18, "learning_rate": 4.9726296568242516e-05, "loss": 0.0144, "step": 175650 }, { "epoch": 42.19, "learning_rate": 4.972180967266464e-05, "loss": 0.0112, "step": 175660 }, { "epoch": 42.19, "learning_rate": 4.971732277932707e-05, "loss": 0.0159, "step": 175670 }, { "epoch": 42.19, "learning_rate": 4.971283588826597e-05, "loss": 0.0096, "step": 175680 }, { "epoch": 42.19, "learning_rate": 4.970834899951741e-05, "loss": 0.0138, "step": 175690 }, { "epoch": 42.2, "learning_rate": 4.9703862113117563e-05, "loss": 0.0157, "step": 175700 }, { "epoch": 42.2, "learning_rate": 4.969937522910254e-05, "loss": 0.0086, "step": 175710 }, { "epoch": 42.2, "learning_rate": 4.969488834750851e-05, "loss": 0.0154, "step": 175720 }, { "epoch": 42.2, "learning_rate": 4.9690401468371595e-05, "loss": 0.0061, "step": 175730 }, { "epoch": 42.2, "learning_rate": 4.9685914591727896e-05, "loss": 0.0053, "step": 175740 }, { "epoch": 42.21, "learning_rate": 4.968142771761358e-05, "loss": 0.0161, "step": 175750 }, { "epoch": 42.21, "learning_rate": 4.967694084606476e-05, "loss": 0.0146, "step": 175760 }, { "epoch": 42.21, "learning_rate": 4.967245397711759e-05, "loss": 0.0134, "step": 175770 }, { "epoch": 42.21, "learning_rate": 4.966796711080821e-05, "loss": 0.0107, "step": 175780 }, { "epoch": 42.22, "learning_rate": 4.966348024717271e-05, "loss": 0.0053, "step": 175790 }, { "epoch": 42.22, "learning_rate": 4.965899338624727e-05, "loss": 0.0119, "step": 175800 }, { "epoch": 42.22, "learning_rate": 4.965450652806798e-05, "loss": 0.0119, "step": 175810 }, { "epoch": 42.22, "learning_rate": 4.9650019672671025e-05, "loss": 0.0108, "step": 175820 }, { "epoch": 42.22, "learning_rate": 4.9645532820092494e-05, "loss": 0.0116, "step": 175830 }, { "epoch": 42.23, "learning_rate": 4.9641045970368525e-05, "loss": 0.0162, "step": 175840 }, { "epoch": 42.23, "learning_rate": 4.963655912353528e-05, "loss": 0.0089, "step": 175850 }, { "epoch": 42.23, "learning_rate": 4.963207227962886e-05, "loss": 0.0139, "step": 175860 }, { "epoch": 42.23, "learning_rate": 4.962758543868543e-05, "loss": 0.0088, "step": 175870 }, { "epoch": 42.24, "learning_rate": 4.96230986007411e-05, "loss": 0.0126, "step": 175880 }, { "epoch": 42.24, "learning_rate": 4.9618611765832e-05, "loss": 0.0104, "step": 175890 }, { "epoch": 42.24, "learning_rate": 4.9614124933994285e-05, "loss": 0.0081, "step": 175900 }, { "epoch": 42.24, "learning_rate": 4.9609638105264055e-05, "loss": 0.0082, "step": 175910 }, { "epoch": 42.25, "learning_rate": 4.96051512796775e-05, "loss": 0.0054, "step": 175920 }, { "epoch": 42.25, "learning_rate": 4.9600664457270685e-05, "loss": 0.0109, "step": 175930 }, { "epoch": 42.25, "learning_rate": 4.959617763807979e-05, "loss": 0.0109, "step": 175940 }, { "epoch": 42.25, "learning_rate": 4.959169082214091e-05, "loss": 0.012, "step": 175950 }, { "epoch": 42.25, "learning_rate": 4.958720400949023e-05, "loss": 0.0121, "step": 175960 }, { "epoch": 42.26, "learning_rate": 4.958271720016384e-05, "loss": 0.0106, "step": 175970 }, { "epoch": 42.26, "learning_rate": 4.957823039419788e-05, "loss": 0.0147, "step": 175980 }, { "epoch": 42.26, "learning_rate": 4.957374359162849e-05, "loss": 0.033, "step": 175990 }, { "epoch": 42.26, "learning_rate": 4.95692567924918e-05, "loss": 0.0172, "step": 176000 }, { "epoch": 42.27, "learning_rate": 4.956476999682396e-05, "loss": 0.0117, "step": 176010 }, { "epoch": 42.27, "learning_rate": 4.956028320466108e-05, "loss": 0.0123, "step": 176020 }, { "epoch": 42.27, "learning_rate": 4.955579641603929e-05, "loss": 0.01, "step": 176030 }, { "epoch": 42.27, "learning_rate": 4.955130963099473e-05, "loss": 0.0074, "step": 176040 }, { "epoch": 42.28, "learning_rate": 4.954682284956354e-05, "loss": 0.0093, "step": 176050 }, { "epoch": 42.28, "learning_rate": 4.954233607178187e-05, "loss": 0.0215, "step": 176060 }, { "epoch": 42.28, "learning_rate": 4.953784929768581e-05, "loss": 0.0139, "step": 176070 }, { "epoch": 42.28, "learning_rate": 4.953336252731151e-05, "loss": 0.0159, "step": 176080 }, { "epoch": 42.28, "learning_rate": 4.952887576069512e-05, "loss": 0.0088, "step": 176090 }, { "epoch": 42.29, "learning_rate": 4.952438899787274e-05, "loss": 0.0086, "step": 176100 }, { "epoch": 42.29, "learning_rate": 4.9519902238880556e-05, "loss": 0.0084, "step": 176110 }, { "epoch": 42.29, "learning_rate": 4.9515415483754636e-05, "loss": 0.0217, "step": 176120 }, { "epoch": 42.29, "learning_rate": 4.9510928732531146e-05, "loss": 0.0108, "step": 176130 }, { "epoch": 42.3, "learning_rate": 4.950644198524621e-05, "loss": 0.0131, "step": 176140 }, { "epoch": 42.3, "learning_rate": 4.9501955241935986e-05, "loss": 0.013, "step": 176150 }, { "epoch": 42.3, "learning_rate": 4.949746850263657e-05, "loss": 0.0105, "step": 176160 }, { "epoch": 42.3, "learning_rate": 4.9492981767384105e-05, "loss": 0.0271, "step": 176170 }, { "epoch": 42.3, "learning_rate": 4.948849503621473e-05, "loss": 0.0184, "step": 176180 }, { "epoch": 42.31, "learning_rate": 4.948400830916458e-05, "loss": 0.011, "step": 176190 }, { "epoch": 42.31, "learning_rate": 4.947952158626979e-05, "loss": 0.0258, "step": 176200 }, { "epoch": 42.31, "learning_rate": 4.947503486756648e-05, "loss": 0.0069, "step": 176210 }, { "epoch": 42.31, "learning_rate": 4.947054815309077e-05, "loss": 0.018, "step": 176220 }, { "epoch": 42.32, "learning_rate": 4.946606144287882e-05, "loss": 0.0097, "step": 176230 }, { "epoch": 42.32, "learning_rate": 4.9461574736966745e-05, "loss": 0.0055, "step": 176240 }, { "epoch": 42.32, "learning_rate": 4.94570880353907e-05, "loss": 0.02, "step": 176250 }, { "epoch": 42.32, "learning_rate": 4.945260133818679e-05, "loss": 0.0133, "step": 176260 }, { "epoch": 42.33, "learning_rate": 4.9448114645391154e-05, "loss": 0.0058, "step": 176270 }, { "epoch": 42.33, "learning_rate": 4.944362795703993e-05, "loss": 0.0071, "step": 176280 }, { "epoch": 42.33, "learning_rate": 4.943914127316926e-05, "loss": 0.0069, "step": 176290 }, { "epoch": 42.33, "learning_rate": 4.9434654593815236e-05, "loss": 0.0072, "step": 176300 }, { "epoch": 42.33, "learning_rate": 4.9430167919014034e-05, "loss": 0.0205, "step": 176310 }, { "epoch": 42.34, "learning_rate": 4.942568124880175e-05, "loss": 0.0097, "step": 176320 }, { "epoch": 42.34, "learning_rate": 4.942119458321455e-05, "loss": 0.0288, "step": 176330 }, { "epoch": 42.34, "learning_rate": 4.941670792228856e-05, "loss": 0.0126, "step": 176340 }, { "epoch": 42.34, "learning_rate": 4.94122212660599e-05, "loss": 0.0192, "step": 176350 }, { "epoch": 42.35, "learning_rate": 4.9407734614564685e-05, "loss": 0.0183, "step": 176360 }, { "epoch": 42.35, "learning_rate": 4.940324796783907e-05, "loss": 0.0162, "step": 176370 }, { "epoch": 42.35, "learning_rate": 4.939876132591918e-05, "loss": 0.0148, "step": 176380 }, { "epoch": 42.35, "learning_rate": 4.939427468884116e-05, "loss": 0.0125, "step": 176390 }, { "epoch": 42.36, "learning_rate": 4.938978805664113e-05, "loss": 0.0055, "step": 176400 }, { "epoch": 42.36, "learning_rate": 4.93853014293552e-05, "loss": 0.0182, "step": 176410 }, { "epoch": 42.36, "learning_rate": 4.9380814807019536e-05, "loss": 0.0171, "step": 176420 }, { "epoch": 42.36, "learning_rate": 4.9376328189670254e-05, "loss": 0.0095, "step": 176430 }, { "epoch": 42.36, "learning_rate": 4.93718415773435e-05, "loss": 0.0135, "step": 176440 }, { "epoch": 42.37, "learning_rate": 4.936735497007538e-05, "loss": 0.01, "step": 176450 }, { "epoch": 42.37, "learning_rate": 4.936286836790203e-05, "loss": 0.0268, "step": 176460 }, { "epoch": 42.37, "learning_rate": 4.93583817708596e-05, "loss": 0.0064, "step": 176470 }, { "epoch": 42.37, "learning_rate": 4.935389517898422e-05, "loss": 0.0106, "step": 176480 }, { "epoch": 42.38, "learning_rate": 4.9349408592311994e-05, "loss": 0.0101, "step": 176490 }, { "epoch": 42.38, "learning_rate": 4.934492201087908e-05, "loss": 0.0176, "step": 176500 }, { "epoch": 42.38, "learning_rate": 4.934043543472158e-05, "loss": 0.0067, "step": 176510 }, { "epoch": 42.38, "learning_rate": 4.933594886387566e-05, "loss": 0.0199, "step": 176520 }, { "epoch": 42.38, "learning_rate": 4.933146229837745e-05, "loss": 0.0197, "step": 176530 }, { "epoch": 42.39, "learning_rate": 4.932697573826306e-05, "loss": 0.0272, "step": 176540 }, { "epoch": 42.39, "learning_rate": 4.932248918356861e-05, "loss": 0.0136, "step": 176550 }, { "epoch": 42.39, "learning_rate": 4.931800263433026e-05, "loss": 0.0166, "step": 176560 }, { "epoch": 42.39, "learning_rate": 4.9313516090584114e-05, "loss": 0.0137, "step": 176570 }, { "epoch": 42.4, "learning_rate": 4.9309029552366344e-05, "loss": 0.0088, "step": 176580 }, { "epoch": 42.4, "learning_rate": 4.930454301971304e-05, "loss": 0.0238, "step": 176590 }, { "epoch": 42.4, "learning_rate": 4.930005649266034e-05, "loss": 0.0098, "step": 176600 }, { "epoch": 42.4, "learning_rate": 4.929556997124439e-05, "loss": 0.0173, "step": 176610 }, { "epoch": 42.41, "learning_rate": 4.9291083455501325e-05, "loss": 0.0214, "step": 176620 }, { "epoch": 42.41, "learning_rate": 4.928659694546724e-05, "loss": 0.01, "step": 176630 }, { "epoch": 42.41, "learning_rate": 4.92821104411783e-05, "loss": 0.0087, "step": 176640 }, { "epoch": 42.41, "learning_rate": 4.927762394267062e-05, "loss": 0.005, "step": 176650 }, { "epoch": 42.41, "learning_rate": 4.9273137449980326e-05, "loss": 0.039, "step": 176660 }, { "epoch": 42.42, "learning_rate": 4.926865096314358e-05, "loss": 0.0152, "step": 176670 }, { "epoch": 42.42, "learning_rate": 4.9264164482196467e-05, "loss": 0.0112, "step": 176680 }, { "epoch": 42.42, "learning_rate": 4.925967800717515e-05, "loss": 0.0098, "step": 176690 }, { "epoch": 42.42, "learning_rate": 4.925519153811573e-05, "loss": 0.0124, "step": 176700 }, { "epoch": 42.43, "learning_rate": 4.9250705075054376e-05, "loss": 0.0175, "step": 176710 }, { "epoch": 42.43, "learning_rate": 4.924621861802721e-05, "loss": 0.0102, "step": 176720 }, { "epoch": 42.43, "learning_rate": 4.924173216707032e-05, "loss": 0.0108, "step": 176730 }, { "epoch": 42.43, "learning_rate": 4.923724572221988e-05, "loss": 0.0107, "step": 176740 }, { "epoch": 42.44, "learning_rate": 4.923275928351199e-05, "loss": 0.0246, "step": 176750 }, { "epoch": 42.44, "learning_rate": 4.922827285098281e-05, "loss": 0.0203, "step": 176760 }, { "epoch": 42.44, "learning_rate": 4.922378642466847e-05, "loss": 0.0081, "step": 176770 }, { "epoch": 42.44, "learning_rate": 4.9219300004605066e-05, "loss": 0.0143, "step": 176780 }, { "epoch": 42.44, "learning_rate": 4.921481359082874e-05, "loss": 0.0153, "step": 176790 }, { "epoch": 42.45, "learning_rate": 4.921032718337564e-05, "loss": 0.0163, "step": 176800 }, { "epoch": 42.45, "learning_rate": 4.920584078228189e-05, "loss": 0.0114, "step": 176810 }, { "epoch": 42.45, "learning_rate": 4.9201354387583595e-05, "loss": 0.0223, "step": 176820 }, { "epoch": 42.45, "learning_rate": 4.919686799931692e-05, "loss": 0.0189, "step": 176830 }, { "epoch": 42.46, "learning_rate": 4.919238161751796e-05, "loss": 0.0142, "step": 176840 }, { "epoch": 42.46, "learning_rate": 4.918789524222288e-05, "loss": 0.0161, "step": 176850 }, { "epoch": 42.46, "learning_rate": 4.91834088734678e-05, "loss": 0.013, "step": 176860 }, { "epoch": 42.46, "learning_rate": 4.917892251128882e-05, "loss": 0.0178, "step": 176870 }, { "epoch": 42.46, "learning_rate": 4.9174436155722094e-05, "loss": 0.0098, "step": 176880 }, { "epoch": 42.47, "learning_rate": 4.9169949806803747e-05, "loss": 0.0106, "step": 176890 }, { "epoch": 42.47, "learning_rate": 4.916546346456991e-05, "loss": 0.0044, "step": 176900 }, { "epoch": 42.47, "learning_rate": 4.916097712905673e-05, "loss": 0.0162, "step": 176910 }, { "epoch": 42.47, "learning_rate": 4.9156490800300285e-05, "loss": 0.0116, "step": 176920 }, { "epoch": 42.48, "learning_rate": 4.9152004478336755e-05, "loss": 0.0165, "step": 176930 }, { "epoch": 42.48, "learning_rate": 4.914751816320224e-05, "loss": 0.0107, "step": 176940 }, { "epoch": 42.48, "learning_rate": 4.91430318549329e-05, "loss": 0.0118, "step": 176950 }, { "epoch": 42.48, "learning_rate": 4.913854555356483e-05, "loss": 0.0133, "step": 176960 }, { "epoch": 42.49, "learning_rate": 4.913405925913417e-05, "loss": 0.016, "step": 176970 }, { "epoch": 42.49, "learning_rate": 4.912957297167704e-05, "loss": 0.0141, "step": 176980 }, { "epoch": 42.49, "learning_rate": 4.9125086691229595e-05, "loss": 0.0082, "step": 176990 }, { "epoch": 42.49, "learning_rate": 4.9120600417827955e-05, "loss": 0.0093, "step": 177000 }, { "epoch": 42.49, "learning_rate": 4.911611415150822e-05, "loss": 0.0205, "step": 177010 }, { "epoch": 42.5, "learning_rate": 4.9111627892306546e-05, "loss": 0.0095, "step": 177020 }, { "epoch": 42.5, "learning_rate": 4.910714164025905e-05, "loss": 0.013, "step": 177030 }, { "epoch": 42.5, "learning_rate": 4.9102655395401875e-05, "loss": 0.028, "step": 177040 }, { "epoch": 42.5, "learning_rate": 4.9098169157771154e-05, "loss": 0.0104, "step": 177050 }, { "epoch": 42.51, "learning_rate": 4.9093682927402975e-05, "loss": 0.0208, "step": 177060 }, { "epoch": 42.51, "learning_rate": 4.90891967043335e-05, "loss": 0.0172, "step": 177070 }, { "epoch": 42.51, "learning_rate": 4.908471048859885e-05, "loss": 0.025, "step": 177080 }, { "epoch": 42.51, "learning_rate": 4.9080224280235156e-05, "loss": 0.0146, "step": 177090 }, { "epoch": 42.52, "learning_rate": 4.907573807927855e-05, "loss": 0.0141, "step": 177100 }, { "epoch": 42.52, "learning_rate": 4.907125188576513e-05, "loss": 0.0134, "step": 177110 }, { "epoch": 42.52, "learning_rate": 4.906676569973107e-05, "loss": 0.0114, "step": 177120 }, { "epoch": 42.52, "learning_rate": 4.9062279521212456e-05, "loss": 0.0171, "step": 177130 }, { "epoch": 42.52, "learning_rate": 4.905779335024546e-05, "loss": 0.0059, "step": 177140 }, { "epoch": 42.53, "learning_rate": 4.9053307186866174e-05, "loss": 0.0207, "step": 177150 }, { "epoch": 42.53, "learning_rate": 4.904882103111072e-05, "loss": 0.0117, "step": 177160 }, { "epoch": 42.53, "learning_rate": 4.904433488301525e-05, "loss": 0.0145, "step": 177170 }, { "epoch": 42.53, "learning_rate": 4.903984874261588e-05, "loss": 0.0134, "step": 177180 }, { "epoch": 42.54, "learning_rate": 4.903536260994877e-05, "loss": 0.0095, "step": 177190 }, { "epoch": 42.54, "learning_rate": 4.903087648504998e-05, "loss": 0.0148, "step": 177200 }, { "epoch": 42.54, "learning_rate": 4.9026390367955694e-05, "loss": 0.0135, "step": 177210 }, { "epoch": 42.54, "learning_rate": 4.9021904258702005e-05, "loss": 0.0207, "step": 177220 }, { "epoch": 42.54, "learning_rate": 4.901741815732507e-05, "loss": 0.0112, "step": 177230 }, { "epoch": 42.55, "learning_rate": 4.901293206386102e-05, "loss": 0.046, "step": 177240 }, { "epoch": 42.55, "learning_rate": 4.900844597834593e-05, "loss": 0.0091, "step": 177250 }, { "epoch": 42.55, "learning_rate": 4.900395990081598e-05, "loss": 0.0131, "step": 177260 }, { "epoch": 42.55, "learning_rate": 4.899947383130726e-05, "loss": 0.0265, "step": 177270 }, { "epoch": 42.56, "learning_rate": 4.8994987769855946e-05, "loss": 0.0213, "step": 177280 }, { "epoch": 42.56, "learning_rate": 4.8990501716498123e-05, "loss": 0.0072, "step": 177290 }, { "epoch": 42.56, "learning_rate": 4.8986015671269914e-05, "loss": 0.0263, "step": 177300 }, { "epoch": 42.56, "learning_rate": 4.898152963420747e-05, "loss": 0.0224, "step": 177310 }, { "epoch": 42.57, "learning_rate": 4.89770436053469e-05, "loss": 0.0084, "step": 177320 }, { "epoch": 42.57, "learning_rate": 4.897255758472436e-05, "loss": 0.0172, "step": 177330 }, { "epoch": 42.57, "learning_rate": 4.8968071572375945e-05, "loss": 0.0121, "step": 177340 }, { "epoch": 42.57, "learning_rate": 4.896358556833778e-05, "loss": 0.0059, "step": 177350 }, { "epoch": 42.57, "learning_rate": 4.895909957264602e-05, "loss": 0.027, "step": 177360 }, { "epoch": 42.58, "learning_rate": 4.8954613585336754e-05, "loss": 0.0163, "step": 177370 }, { "epoch": 42.58, "learning_rate": 4.895012760644616e-05, "loss": 0.0141, "step": 177380 }, { "epoch": 42.58, "learning_rate": 4.894564163601032e-05, "loss": 0.0115, "step": 177390 }, { "epoch": 42.58, "learning_rate": 4.8941155674065365e-05, "loss": 0.0131, "step": 177400 }, { "epoch": 42.59, "learning_rate": 4.8936669720647436e-05, "loss": 0.0098, "step": 177410 }, { "epoch": 42.59, "learning_rate": 4.893218377579266e-05, "loss": 0.0098, "step": 177420 }, { "epoch": 42.59, "learning_rate": 4.8927697839537154e-05, "loss": 0.0312, "step": 177430 }, { "epoch": 42.59, "learning_rate": 4.8923211911917036e-05, "loss": 0.0149, "step": 177440 }, { "epoch": 42.6, "learning_rate": 4.891872599296844e-05, "loss": 0.0365, "step": 177450 }, { "epoch": 42.6, "learning_rate": 4.891424008272749e-05, "loss": 0.022, "step": 177460 }, { "epoch": 42.6, "learning_rate": 4.8909754181230334e-05, "loss": 0.0135, "step": 177470 }, { "epoch": 42.6, "learning_rate": 4.890526828851307e-05, "loss": 0.0191, "step": 177480 }, { "epoch": 42.6, "learning_rate": 4.890078240461181e-05, "loss": 0.0183, "step": 177490 }, { "epoch": 42.61, "learning_rate": 4.8896296529562726e-05, "loss": 0.0179, "step": 177500 }, { "epoch": 42.61, "learning_rate": 4.88918106634019e-05, "loss": 0.0162, "step": 177510 }, { "epoch": 42.61, "learning_rate": 4.88873248061655e-05, "loss": 0.0115, "step": 177520 }, { "epoch": 42.61, "learning_rate": 4.8882838957889614e-05, "loss": 0.0117, "step": 177530 }, { "epoch": 42.62, "learning_rate": 4.887835311861037e-05, "loss": 0.0089, "step": 177540 }, { "epoch": 42.62, "learning_rate": 4.887386728836392e-05, "loss": 0.0154, "step": 177550 }, { "epoch": 42.62, "learning_rate": 4.8869381467186346e-05, "loss": 0.0108, "step": 177560 }, { "epoch": 42.62, "learning_rate": 4.8864895655113835e-05, "loss": 0.0196, "step": 177570 }, { "epoch": 42.62, "learning_rate": 4.886040985218246e-05, "loss": 0.0299, "step": 177580 }, { "epoch": 42.63, "learning_rate": 4.885592405842835e-05, "loss": 0.0228, "step": 177590 }, { "epoch": 42.63, "learning_rate": 4.885143827388766e-05, "loss": 0.0112, "step": 177600 }, { "epoch": 42.63, "learning_rate": 4.88469524985965e-05, "loss": 0.0152, "step": 177610 }, { "epoch": 42.63, "learning_rate": 4.884246673259098e-05, "loss": 0.0164, "step": 177620 }, { "epoch": 42.64, "learning_rate": 4.883798097590722e-05, "loss": 0.0179, "step": 177630 }, { "epoch": 42.64, "learning_rate": 4.883349522858138e-05, "loss": 0.0093, "step": 177640 }, { "epoch": 42.64, "learning_rate": 4.882900949064955e-05, "loss": 0.0082, "step": 177650 }, { "epoch": 42.64, "learning_rate": 4.882452376214789e-05, "loss": 0.0173, "step": 177660 }, { "epoch": 42.65, "learning_rate": 4.882003804311249e-05, "loss": 0.017, "step": 177670 }, { "epoch": 42.65, "learning_rate": 4.8815552333579473e-05, "loss": 0.0193, "step": 177680 }, { "epoch": 42.65, "learning_rate": 4.881106663358499e-05, "loss": 0.015, "step": 177690 }, { "epoch": 42.65, "learning_rate": 4.880658094316514e-05, "loss": 0.019, "step": 177700 }, { "epoch": 42.65, "learning_rate": 4.8802095262356087e-05, "loss": 0.0105, "step": 177710 }, { "epoch": 42.66, "learning_rate": 4.87976095911939e-05, "loss": 0.0145, "step": 177720 }, { "epoch": 42.66, "learning_rate": 4.8793123929714735e-05, "loss": 0.018, "step": 177730 }, { "epoch": 42.66, "learning_rate": 4.8788638277954715e-05, "loss": 0.0118, "step": 177740 }, { "epoch": 42.66, "learning_rate": 4.878415263594994e-05, "loss": 0.009, "step": 177750 }, { "epoch": 42.67, "learning_rate": 4.877966700373659e-05, "loss": 0.0155, "step": 177760 }, { "epoch": 42.67, "learning_rate": 4.877518138135072e-05, "loss": 0.0147, "step": 177770 }, { "epoch": 42.67, "learning_rate": 4.8770695768828486e-05, "loss": 0.0232, "step": 177780 }, { "epoch": 42.67, "learning_rate": 4.876621016620601e-05, "loss": 0.0157, "step": 177790 }, { "epoch": 42.68, "learning_rate": 4.876172457351943e-05, "loss": 0.0069, "step": 177800 }, { "epoch": 42.68, "learning_rate": 4.8757238990804835e-05, "loss": 0.022, "step": 177810 }, { "epoch": 42.68, "learning_rate": 4.8752753418098366e-05, "loss": 0.0249, "step": 177820 }, { "epoch": 42.68, "learning_rate": 4.874826785543614e-05, "loss": 0.0148, "step": 177830 }, { "epoch": 42.68, "learning_rate": 4.87437823028543e-05, "loss": 0.0181, "step": 177840 }, { "epoch": 42.69, "learning_rate": 4.873929676038896e-05, "loss": 0.0127, "step": 177850 }, { "epoch": 42.69, "learning_rate": 4.8734811228076235e-05, "loss": 0.0139, "step": 177860 }, { "epoch": 42.69, "learning_rate": 4.8730325705952236e-05, "loss": 0.0096, "step": 177870 }, { "epoch": 42.69, "learning_rate": 4.87258401940531e-05, "loss": 0.0167, "step": 177880 }, { "epoch": 42.7, "learning_rate": 4.872135469241495e-05, "loss": 0.0253, "step": 177890 }, { "epoch": 42.7, "learning_rate": 4.871686920107392e-05, "loss": 0.0402, "step": 177900 }, { "epoch": 42.7, "learning_rate": 4.8712383720066115e-05, "loss": 0.0065, "step": 177910 }, { "epoch": 42.7, "learning_rate": 4.870789824942765e-05, "loss": 0.0086, "step": 177920 }, { "epoch": 42.7, "learning_rate": 4.870341278919467e-05, "loss": 0.0123, "step": 177930 }, { "epoch": 42.71, "learning_rate": 4.869892733940328e-05, "loss": 0.0212, "step": 177940 }, { "epoch": 42.71, "learning_rate": 4.869444190008962e-05, "loss": 0.0081, "step": 177950 }, { "epoch": 42.71, "learning_rate": 4.8689956471289785e-05, "loss": 0.0097, "step": 177960 }, { "epoch": 42.71, "learning_rate": 4.868547105303991e-05, "loss": 0.0094, "step": 177970 }, { "epoch": 42.72, "learning_rate": 4.868098564537613e-05, "loss": 0.0227, "step": 177980 }, { "epoch": 42.72, "learning_rate": 4.8676500248334563e-05, "loss": 0.0208, "step": 177990 }, { "epoch": 42.72, "learning_rate": 4.86720148619513e-05, "loss": 0.0121, "step": 178000 }, { "epoch": 42.72, "learning_rate": 4.866752948626249e-05, "loss": 0.0247, "step": 178010 }, { "epoch": 42.73, "learning_rate": 4.8663044121304244e-05, "loss": 0.0148, "step": 178020 }, { "epoch": 42.73, "learning_rate": 4.86585587671127e-05, "loss": 0.0126, "step": 178030 }, { "epoch": 42.73, "learning_rate": 4.865407342372398e-05, "loss": 0.0121, "step": 178040 }, { "epoch": 42.73, "learning_rate": 4.8649588091174176e-05, "loss": 0.0204, "step": 178050 }, { "epoch": 42.73, "learning_rate": 4.864510276949942e-05, "loss": 0.0101, "step": 178060 }, { "epoch": 42.74, "learning_rate": 4.864061745873584e-05, "loss": 0.0077, "step": 178070 }, { "epoch": 42.74, "learning_rate": 4.863613215891956e-05, "loss": 0.0132, "step": 178080 }, { "epoch": 42.74, "learning_rate": 4.863164687008671e-05, "loss": 0.0098, "step": 178090 }, { "epoch": 42.74, "learning_rate": 4.8627161592273376e-05, "loss": 0.0145, "step": 178100 }, { "epoch": 42.75, "learning_rate": 4.8622676325515696e-05, "loss": 0.0093, "step": 178110 }, { "epoch": 42.75, "learning_rate": 4.86181910698498e-05, "loss": 0.0121, "step": 178120 }, { "epoch": 42.75, "learning_rate": 4.861370582531183e-05, "loss": 0.0077, "step": 178130 }, { "epoch": 42.75, "learning_rate": 4.8609220591937845e-05, "loss": 0.0129, "step": 178140 }, { "epoch": 42.76, "learning_rate": 4.8604735369764e-05, "loss": 0.005, "step": 178150 }, { "epoch": 42.76, "learning_rate": 4.8600250158826416e-05, "loss": 0.0074, "step": 178160 }, { "epoch": 42.76, "learning_rate": 4.859576495916122e-05, "loss": 0.0198, "step": 178170 }, { "epoch": 42.76, "learning_rate": 4.8591279770804535e-05, "loss": 0.0174, "step": 178180 }, { "epoch": 42.76, "learning_rate": 4.858679459379244e-05, "loss": 0.0144, "step": 178190 }, { "epoch": 42.77, "learning_rate": 4.8582309428161096e-05, "loss": 0.0167, "step": 178200 }, { "epoch": 42.77, "learning_rate": 4.8577824273946596e-05, "loss": 0.009, "step": 178210 }, { "epoch": 42.77, "learning_rate": 4.857333913118509e-05, "loss": 0.0094, "step": 178220 }, { "epoch": 42.77, "learning_rate": 4.85688539999127e-05, "loss": 0.0178, "step": 178230 }, { "epoch": 42.78, "learning_rate": 4.856436888016549e-05, "loss": 0.0265, "step": 178240 }, { "epoch": 42.78, "learning_rate": 4.855988377197963e-05, "loss": 0.0194, "step": 178250 }, { "epoch": 42.78, "learning_rate": 4.8555398675391215e-05, "loss": 0.0191, "step": 178260 }, { "epoch": 42.78, "learning_rate": 4.855091359043638e-05, "loss": 0.0169, "step": 178270 }, { "epoch": 42.78, "learning_rate": 4.854642851715126e-05, "loss": 0.013, "step": 178280 }, { "epoch": 42.79, "learning_rate": 4.854194345557193e-05, "loss": 0.0046, "step": 178290 }, { "epoch": 42.79, "learning_rate": 4.853745840573453e-05, "loss": 0.0121, "step": 178300 }, { "epoch": 42.79, "learning_rate": 4.853297336767518e-05, "loss": 0.0094, "step": 178310 }, { "epoch": 42.79, "learning_rate": 4.852848834143002e-05, "loss": 0.0115, "step": 178320 }, { "epoch": 42.8, "learning_rate": 4.852400332703512e-05, "loss": 0.0137, "step": 178330 }, { "epoch": 42.8, "learning_rate": 4.851951832452663e-05, "loss": 0.0156, "step": 178340 }, { "epoch": 42.8, "learning_rate": 4.8515033333940655e-05, "loss": 0.0106, "step": 178350 }, { "epoch": 42.8, "learning_rate": 4.8510548355313334e-05, "loss": 0.0209, "step": 178360 }, { "epoch": 42.81, "learning_rate": 4.8506063388680785e-05, "loss": 0.0158, "step": 178370 }, { "epoch": 42.81, "learning_rate": 4.850157843407909e-05, "loss": 0.0156, "step": 178380 }, { "epoch": 42.81, "learning_rate": 4.84970934915444e-05, "loss": 0.0075, "step": 178390 }, { "epoch": 42.81, "learning_rate": 4.849260856111282e-05, "loss": 0.0143, "step": 178400 }, { "epoch": 42.81, "learning_rate": 4.848812364282048e-05, "loss": 0.0135, "step": 178410 }, { "epoch": 42.82, "learning_rate": 4.848363873670349e-05, "loss": 0.0119, "step": 178420 }, { "epoch": 42.82, "learning_rate": 4.847915384279795e-05, "loss": 0.0115, "step": 178430 }, { "epoch": 42.82, "learning_rate": 4.847466896114001e-05, "loss": 0.0112, "step": 178440 }, { "epoch": 42.82, "learning_rate": 4.847018409176576e-05, "loss": 0.014, "step": 178450 }, { "epoch": 42.83, "learning_rate": 4.846569923471136e-05, "loss": 0.0194, "step": 178460 }, { "epoch": 42.83, "learning_rate": 4.846121439001286e-05, "loss": 0.018, "step": 178470 }, { "epoch": 42.83, "learning_rate": 4.845672955770643e-05, "loss": 0.0143, "step": 178480 }, { "epoch": 42.83, "learning_rate": 4.845224473782815e-05, "loss": 0.0071, "step": 178490 }, { "epoch": 42.84, "learning_rate": 4.8447759930414174e-05, "loss": 0.0101, "step": 178500 }, { "epoch": 42.84, "learning_rate": 4.8443275135500615e-05, "loss": 0.019, "step": 178510 }, { "epoch": 42.84, "learning_rate": 4.843879035312355e-05, "loss": 0.0146, "step": 178520 }, { "epoch": 42.84, "learning_rate": 4.843430558331913e-05, "loss": 0.0091, "step": 178530 }, { "epoch": 42.84, "learning_rate": 4.8429820826123454e-05, "loss": 0.0144, "step": 178540 }, { "epoch": 42.85, "learning_rate": 4.8425336081572665e-05, "loss": 0.0171, "step": 178550 }, { "epoch": 42.85, "learning_rate": 4.842085134970287e-05, "loss": 0.0208, "step": 178560 }, { "epoch": 42.85, "learning_rate": 4.841636663055015e-05, "loss": 0.0229, "step": 178570 }, { "epoch": 42.85, "learning_rate": 4.841188192415067e-05, "loss": 0.0102, "step": 178580 }, { "epoch": 42.86, "learning_rate": 4.84073972305405e-05, "loss": 0.0152, "step": 178590 }, { "epoch": 42.86, "learning_rate": 4.8402912549755794e-05, "loss": 0.0108, "step": 178600 }, { "epoch": 42.86, "learning_rate": 4.839842788183267e-05, "loss": 0.0215, "step": 178610 }, { "epoch": 42.86, "learning_rate": 4.83939432268072e-05, "loss": 0.0104, "step": 178620 }, { "epoch": 42.86, "learning_rate": 4.8389458584715544e-05, "loss": 0.0114, "step": 178630 }, { "epoch": 42.87, "learning_rate": 4.838497395559379e-05, "loss": 0.0108, "step": 178640 }, { "epoch": 42.87, "learning_rate": 4.838048933947808e-05, "loss": 0.008, "step": 178650 }, { "epoch": 42.87, "learning_rate": 4.83760047364045e-05, "loss": 0.0078, "step": 178660 }, { "epoch": 42.87, "learning_rate": 4.8371520146409175e-05, "loss": 0.0064, "step": 178670 }, { "epoch": 42.88, "learning_rate": 4.836703556952823e-05, "loss": 0.0053, "step": 178680 }, { "epoch": 42.88, "learning_rate": 4.836255100579776e-05, "loss": 0.0254, "step": 178690 }, { "epoch": 42.88, "learning_rate": 4.835806645525393e-05, "loss": 0.0123, "step": 178700 }, { "epoch": 42.88, "learning_rate": 4.835358191793278e-05, "loss": 0.0187, "step": 178710 }, { "epoch": 42.89, "learning_rate": 4.834909739387048e-05, "loss": 0.0086, "step": 178720 }, { "epoch": 42.89, "learning_rate": 4.834461288310311e-05, "loss": 0.0099, "step": 178730 }, { "epoch": 42.89, "learning_rate": 4.834012838566681e-05, "loss": 0.0241, "step": 178740 }, { "epoch": 42.89, "learning_rate": 4.83356439015977e-05, "loss": 0.0156, "step": 178750 }, { "epoch": 42.89, "learning_rate": 4.833115943093186e-05, "loss": 0.0126, "step": 178760 }, { "epoch": 42.9, "learning_rate": 4.8326674973705425e-05, "loss": 0.024, "step": 178770 }, { "epoch": 42.9, "learning_rate": 4.832219052995451e-05, "loss": 0.0086, "step": 178780 }, { "epoch": 42.9, "learning_rate": 4.8317706099715236e-05, "loss": 0.0137, "step": 178790 }, { "epoch": 42.9, "learning_rate": 4.83132216830237e-05, "loss": 0.0128, "step": 178800 }, { "epoch": 42.91, "learning_rate": 4.830873727991602e-05, "loss": 0.0124, "step": 178810 }, { "epoch": 42.91, "learning_rate": 4.830425289042831e-05, "loss": 0.0085, "step": 178820 }, { "epoch": 42.91, "learning_rate": 4.829976851459668e-05, "loss": 0.006, "step": 178830 }, { "epoch": 42.91, "learning_rate": 4.829528415245727e-05, "loss": 0.0183, "step": 178840 }, { "epoch": 42.91, "learning_rate": 4.8290799804046167e-05, "loss": 0.0096, "step": 178850 }, { "epoch": 42.92, "learning_rate": 4.8286315469399476e-05, "loss": 0.0117, "step": 178860 }, { "epoch": 42.92, "learning_rate": 4.828183114855332e-05, "loss": 0.0152, "step": 178870 }, { "epoch": 42.92, "learning_rate": 4.827734684154383e-05, "loss": 0.0112, "step": 178880 }, { "epoch": 42.92, "learning_rate": 4.8272862548407104e-05, "loss": 0.0058, "step": 178890 }, { "epoch": 42.93, "learning_rate": 4.826837826917925e-05, "loss": 0.013, "step": 178900 }, { "epoch": 42.93, "learning_rate": 4.8263894003896386e-05, "loss": 0.0106, "step": 178910 }, { "epoch": 42.93, "learning_rate": 4.8259409752594613e-05, "loss": 0.0166, "step": 178920 }, { "epoch": 42.93, "learning_rate": 4.8254925515310064e-05, "loss": 0.01, "step": 178930 }, { "epoch": 42.94, "learning_rate": 4.8250441292078855e-05, "loss": 0.0094, "step": 178940 }, { "epoch": 42.94, "learning_rate": 4.8245957082937056e-05, "loss": 0.0103, "step": 178950 }, { "epoch": 42.94, "learning_rate": 4.824147288792082e-05, "loss": 0.0124, "step": 178960 }, { "epoch": 42.94, "learning_rate": 4.8236988707066234e-05, "loss": 0.0106, "step": 178970 }, { "epoch": 42.94, "learning_rate": 4.823250454040944e-05, "loss": 0.0185, "step": 178980 }, { "epoch": 42.95, "learning_rate": 4.8228020387986526e-05, "loss": 0.0338, "step": 178990 }, { "epoch": 42.95, "learning_rate": 4.8223536249833596e-05, "loss": 0.0065, "step": 179000 }, { "epoch": 43.0, "learning_rate": 4.821905212598678e-05, "loss": 0.0149, "step": 179010 }, { "epoch": 43.0, "learning_rate": 4.8214568016482174e-05, "loss": 0.0144, "step": 179020 }, { "epoch": 43.0, "learning_rate": 4.821008392135592e-05, "loss": 0.0141, "step": 179030 }, { "epoch": 43.01, "learning_rate": 4.8205599840644105e-05, "loss": 0.0109, "step": 179040 }, { "epoch": 43.01, "learning_rate": 4.8201115774382826e-05, "loss": 0.0105, "step": 179050 }, { "epoch": 43.01, "learning_rate": 4.819663172260822e-05, "loss": 0.0158, "step": 179060 }, { "epoch": 43.01, "learning_rate": 4.819214768535638e-05, "loss": 0.0097, "step": 179070 }, { "epoch": 43.02, "learning_rate": 4.818766366266344e-05, "loss": 0.0191, "step": 179080 }, { "epoch": 43.02, "learning_rate": 4.8183179654565485e-05, "loss": 0.0195, "step": 179090 }, { "epoch": 43.02, "learning_rate": 4.817869566109863e-05, "loss": 0.0145, "step": 179100 }, { "epoch": 43.02, "learning_rate": 4.817421168229899e-05, "loss": 0.0161, "step": 179110 }, { "epoch": 43.03, "learning_rate": 4.816972771820269e-05, "loss": 0.0142, "step": 179120 }, { "epoch": 43.03, "learning_rate": 4.8165243768845825e-05, "loss": 0.0102, "step": 179130 }, { "epoch": 43.03, "learning_rate": 4.8160759834264484e-05, "loss": 0.0125, "step": 179140 }, { "epoch": 43.03, "learning_rate": 4.8156275914494815e-05, "loss": 0.0165, "step": 179150 }, { "epoch": 43.03, "learning_rate": 4.8151792009572895e-05, "loss": 0.0095, "step": 179160 }, { "epoch": 43.04, "learning_rate": 4.8147308119534876e-05, "loss": 0.0406, "step": 179170 }, { "epoch": 43.04, "learning_rate": 4.814282424441682e-05, "loss": 0.0112, "step": 179180 }, { "epoch": 43.04, "learning_rate": 4.813834038425485e-05, "loss": 0.0067, "step": 179190 }, { "epoch": 43.04, "learning_rate": 4.8133856539085096e-05, "loss": 0.0131, "step": 179200 }, { "epoch": 43.05, "learning_rate": 4.812937270894364e-05, "loss": 0.0089, "step": 179210 }, { "epoch": 43.05, "learning_rate": 4.812488889386663e-05, "loss": 0.0151, "step": 179220 }, { "epoch": 43.05, "learning_rate": 4.8120405093890134e-05, "loss": 0.0127, "step": 179230 }, { "epoch": 43.05, "learning_rate": 4.8115921309050266e-05, "loss": 0.0199, "step": 179240 }, { "epoch": 43.06, "learning_rate": 4.811143753938315e-05, "loss": 0.0252, "step": 179250 }, { "epoch": 43.06, "learning_rate": 4.810695378492488e-05, "loss": 0.0112, "step": 179260 }, { "epoch": 43.06, "learning_rate": 4.8102470045711604e-05, "loss": 0.0113, "step": 179270 }, { "epoch": 43.06, "learning_rate": 4.809798632177937e-05, "loss": 0.018, "step": 179280 }, { "epoch": 43.06, "learning_rate": 4.809350261316431e-05, "loss": 0.0064, "step": 179290 }, { "epoch": 43.07, "learning_rate": 4.808901891990256e-05, "loss": 0.0094, "step": 179300 }, { "epoch": 43.07, "learning_rate": 4.80845352420302e-05, "loss": 0.0248, "step": 179310 }, { "epoch": 43.07, "learning_rate": 4.8080051579583324e-05, "loss": 0.0088, "step": 179320 }, { "epoch": 43.07, "learning_rate": 4.8075567932598075e-05, "loss": 0.0193, "step": 179330 }, { "epoch": 43.08, "learning_rate": 4.8071084301110534e-05, "loss": 0.0162, "step": 179340 }, { "epoch": 43.08, "learning_rate": 4.806660068515682e-05, "loss": 0.012, "step": 179350 }, { "epoch": 43.08, "learning_rate": 4.8062117084773044e-05, "loss": 0.0117, "step": 179360 }, { "epoch": 43.08, "learning_rate": 4.8057633499995304e-05, "loss": 0.0143, "step": 179370 }, { "epoch": 43.08, "learning_rate": 4.8053149930859695e-05, "loss": 0.0082, "step": 179380 }, { "epoch": 43.09, "learning_rate": 4.804866637740235e-05, "loss": 0.0169, "step": 179390 }, { "epoch": 43.09, "learning_rate": 4.804418283965936e-05, "loss": 0.0061, "step": 179400 }, { "epoch": 43.09, "learning_rate": 4.803969931766685e-05, "loss": 0.0144, "step": 179410 }, { "epoch": 43.09, "learning_rate": 4.8035215811460896e-05, "loss": 0.015, "step": 179420 }, { "epoch": 43.1, "learning_rate": 4.803073232107762e-05, "loss": 0.0228, "step": 179430 }, { "epoch": 43.1, "learning_rate": 4.8026248846553136e-05, "loss": 0.0195, "step": 179440 }, { "epoch": 43.1, "learning_rate": 4.802176538792355e-05, "loss": 0.0214, "step": 179450 }, { "epoch": 43.1, "learning_rate": 4.801728194522494e-05, "loss": 0.0091, "step": 179460 }, { "epoch": 43.11, "learning_rate": 4.8012798518493455e-05, "loss": 0.0214, "step": 179470 }, { "epoch": 43.11, "learning_rate": 4.800831510776515e-05, "loss": 0.0224, "step": 179480 }, { "epoch": 43.11, "learning_rate": 4.800383171307618e-05, "loss": 0.0176, "step": 179490 }, { "epoch": 43.11, "learning_rate": 4.799934833446263e-05, "loss": 0.0224, "step": 179500 }, { "epoch": 43.11, "learning_rate": 4.799486497196059e-05, "loss": 0.0133, "step": 179510 }, { "epoch": 43.12, "learning_rate": 4.799038162560619e-05, "loss": 0.0053, "step": 179520 }, { "epoch": 43.12, "learning_rate": 4.798589829543551e-05, "loss": 0.0139, "step": 179530 }, { "epoch": 43.12, "learning_rate": 4.798141498148468e-05, "loss": 0.0178, "step": 179540 }, { "epoch": 43.12, "learning_rate": 4.797693168378981e-05, "loss": 0.0144, "step": 179550 }, { "epoch": 43.13, "learning_rate": 4.797244840238697e-05, "loss": 0.043, "step": 179560 }, { "epoch": 43.13, "learning_rate": 4.796796513731228e-05, "loss": 0.0137, "step": 179570 }, { "epoch": 43.13, "learning_rate": 4.796348188860185e-05, "loss": 0.0083, "step": 179580 }, { "epoch": 43.13, "learning_rate": 4.7958998656291774e-05, "loss": 0.0171, "step": 179590 }, { "epoch": 43.14, "learning_rate": 4.7954515440418194e-05, "loss": 0.0076, "step": 179600 }, { "epoch": 43.14, "learning_rate": 4.795003224101716e-05, "loss": 0.0126, "step": 179610 }, { "epoch": 43.14, "learning_rate": 4.7945549058124794e-05, "loss": 0.0175, "step": 179620 }, { "epoch": 43.14, "learning_rate": 4.794106589177722e-05, "loss": 0.0073, "step": 179630 }, { "epoch": 43.14, "learning_rate": 4.793658274201053e-05, "loss": 0.0076, "step": 179640 }, { "epoch": 43.15, "learning_rate": 4.7932099608860807e-05, "loss": 0.0225, "step": 179650 }, { "epoch": 43.15, "learning_rate": 4.7927616492364174e-05, "loss": 0.0175, "step": 179660 }, { "epoch": 43.15, "learning_rate": 4.792313339255673e-05, "loss": 0.0057, "step": 179670 }, { "epoch": 43.15, "learning_rate": 4.791865030947458e-05, "loss": 0.0197, "step": 179680 }, { "epoch": 43.16, "learning_rate": 4.791416724315385e-05, "loss": 0.0215, "step": 179690 }, { "epoch": 43.16, "learning_rate": 4.7909684193630596e-05, "loss": 0.024, "step": 179700 }, { "epoch": 43.16, "learning_rate": 4.790520116094095e-05, "loss": 0.0103, "step": 179710 }, { "epoch": 43.16, "learning_rate": 4.790071814512099e-05, "loss": 0.0122, "step": 179720 }, { "epoch": 43.16, "learning_rate": 4.789623514620686e-05, "loss": 0.0096, "step": 179730 }, { "epoch": 43.17, "learning_rate": 4.789175216423464e-05, "loss": 0.0152, "step": 179740 }, { "epoch": 43.17, "learning_rate": 4.788726919924042e-05, "loss": 0.0114, "step": 179750 }, { "epoch": 43.17, "learning_rate": 4.788278625126031e-05, "loss": 0.0079, "step": 179760 }, { "epoch": 43.17, "learning_rate": 4.787830332033043e-05, "loss": 0.0083, "step": 179770 }, { "epoch": 43.18, "learning_rate": 4.7873820406486866e-05, "loss": 0.009, "step": 179780 }, { "epoch": 43.18, "learning_rate": 4.7869337509765706e-05, "loss": 0.016, "step": 179790 }, { "epoch": 43.18, "learning_rate": 4.7864854630203074e-05, "loss": 0.0052, "step": 179800 }, { "epoch": 43.18, "learning_rate": 4.786037176783504e-05, "loss": 0.0165, "step": 179810 }, { "epoch": 43.19, "learning_rate": 4.7855888922697754e-05, "loss": 0.0173, "step": 179820 }, { "epoch": 43.19, "learning_rate": 4.7851406094827294e-05, "loss": 0.0084, "step": 179830 }, { "epoch": 43.19, "learning_rate": 4.784692328425974e-05, "loss": 0.0142, "step": 179840 }, { "epoch": 43.19, "learning_rate": 4.784244049103122e-05, "loss": 0.0076, "step": 179850 }, { "epoch": 43.19, "learning_rate": 4.78379577151778e-05, "loss": 0.0081, "step": 179860 }, { "epoch": 43.2, "learning_rate": 4.783347495673564e-05, "loss": 0.0093, "step": 179870 }, { "epoch": 43.2, "learning_rate": 4.78289922157408e-05, "loss": 0.0077, "step": 179880 }, { "epoch": 43.2, "learning_rate": 4.7824509492229366e-05, "loss": 0.0073, "step": 179890 }, { "epoch": 43.2, "learning_rate": 4.782002678623747e-05, "loss": 0.0255, "step": 179900 }, { "epoch": 43.21, "learning_rate": 4.7815544097801186e-05, "loss": 0.0073, "step": 179910 }, { "epoch": 43.21, "learning_rate": 4.781106142695664e-05, "loss": 0.0127, "step": 179920 }, { "epoch": 43.21, "learning_rate": 4.780657877373993e-05, "loss": 0.0087, "step": 179930 }, { "epoch": 43.21, "learning_rate": 4.780209613818712e-05, "loss": 0.0059, "step": 179940 }, { "epoch": 43.22, "learning_rate": 4.7797613520334345e-05, "loss": 0.0081, "step": 179950 }, { "epoch": 43.22, "learning_rate": 4.779313092021768e-05, "loss": 0.008, "step": 179960 }, { "epoch": 43.22, "learning_rate": 4.7788648337873274e-05, "loss": 0.0111, "step": 179970 }, { "epoch": 43.22, "learning_rate": 4.778416577333715e-05, "loss": 0.0062, "step": 179980 }, { "epoch": 43.22, "learning_rate": 4.7779683226645464e-05, "loss": 0.0086, "step": 179990 }, { "epoch": 43.23, "learning_rate": 4.7775200697834277e-05, "loss": 0.0173, "step": 180000 }, { "epoch": 43.23, "learning_rate": 4.777071818693972e-05, "loss": 0.0083, "step": 180010 }, { "epoch": 43.23, "learning_rate": 4.7766235693997884e-05, "loss": 0.0172, "step": 180020 }, { "epoch": 43.23, "learning_rate": 4.776175321904484e-05, "loss": 0.0158, "step": 180030 }, { "epoch": 43.24, "learning_rate": 4.775727076211672e-05, "loss": 0.0102, "step": 180040 }, { "epoch": 43.24, "learning_rate": 4.77527883232496e-05, "loss": 0.0084, "step": 180050 }, { "epoch": 43.24, "learning_rate": 4.774830590247959e-05, "loss": 0.0058, "step": 180060 }, { "epoch": 43.24, "learning_rate": 4.7743823499842794e-05, "loss": 0.0278, "step": 180070 }, { "epoch": 43.24, "learning_rate": 4.773934111537528e-05, "loss": 0.0255, "step": 180080 }, { "epoch": 43.25, "learning_rate": 4.7734858749113175e-05, "loss": 0.0135, "step": 180090 }, { "epoch": 43.25, "learning_rate": 4.773037640109256e-05, "loss": 0.0056, "step": 180100 }, { "epoch": 43.25, "learning_rate": 4.772589407134955e-05, "loss": 0.0091, "step": 180110 }, { "epoch": 43.25, "learning_rate": 4.772141175992022e-05, "loss": 0.0164, "step": 180120 }, { "epoch": 43.26, "learning_rate": 4.771692946684067e-05, "loss": 0.0064, "step": 180130 }, { "epoch": 43.26, "learning_rate": 4.771244719214701e-05, "loss": 0.0044, "step": 180140 }, { "epoch": 43.26, "learning_rate": 4.770796493587532e-05, "loss": 0.0123, "step": 180150 }, { "epoch": 43.26, "learning_rate": 4.770348269806172e-05, "loss": 0.0111, "step": 180160 }, { "epoch": 43.27, "learning_rate": 4.769900047874228e-05, "loss": 0.0121, "step": 180170 }, { "epoch": 43.27, "learning_rate": 4.76945182779531e-05, "loss": 0.0142, "step": 180180 }, { "epoch": 43.27, "learning_rate": 4.769003609573029e-05, "loss": 0.0155, "step": 180190 }, { "epoch": 43.27, "learning_rate": 4.7685553932109934e-05, "loss": 0.0254, "step": 180200 }, { "epoch": 43.27, "learning_rate": 4.768107178712816e-05, "loss": 0.0083, "step": 180210 }, { "epoch": 43.28, "learning_rate": 4.7676589660821e-05, "loss": 0.0121, "step": 180220 }, { "epoch": 43.28, "learning_rate": 4.76721075532246e-05, "loss": 0.0051, "step": 180230 }, { "epoch": 43.28, "learning_rate": 4.7667625464375025e-05, "loss": 0.0081, "step": 180240 }, { "epoch": 43.28, "learning_rate": 4.7663143394308405e-05, "loss": 0.0134, "step": 180250 }, { "epoch": 43.29, "learning_rate": 4.765866134306081e-05, "loss": 0.0084, "step": 180260 }, { "epoch": 43.29, "learning_rate": 4.7654179310668325e-05, "loss": 0.0208, "step": 180270 }, { "epoch": 43.29, "learning_rate": 4.7649697297167067e-05, "loss": 0.013, "step": 180280 }, { "epoch": 43.29, "learning_rate": 4.764521530259311e-05, "loss": 0.0108, "step": 180290 }, { "epoch": 43.3, "learning_rate": 4.764073332698258e-05, "loss": 0.0167, "step": 180300 }, { "epoch": 43.3, "learning_rate": 4.763625137037154e-05, "loss": 0.007, "step": 180310 }, { "epoch": 43.3, "learning_rate": 4.763176943279609e-05, "loss": 0.0125, "step": 180320 }, { "epoch": 43.3, "learning_rate": 4.7627287514292325e-05, "loss": 0.0162, "step": 180330 }, { "epoch": 43.3, "learning_rate": 4.762280561489634e-05, "loss": 0.007, "step": 180340 }, { "epoch": 43.31, "learning_rate": 4.7618323734644246e-05, "loss": 0.0156, "step": 180350 }, { "epoch": 43.31, "learning_rate": 4.761384187357211e-05, "loss": 0.0141, "step": 180360 }, { "epoch": 43.31, "learning_rate": 4.7609360031716026e-05, "loss": 0.0102, "step": 180370 }, { "epoch": 43.31, "learning_rate": 4.760487820911211e-05, "loss": 0.0164, "step": 180380 }, { "epoch": 43.32, "learning_rate": 4.7600396405796424e-05, "loss": 0.0162, "step": 180390 }, { "epoch": 43.32, "learning_rate": 4.759591462180511e-05, "loss": 0.0118, "step": 180400 }, { "epoch": 43.32, "learning_rate": 4.75914328571742e-05, "loss": 0.0089, "step": 180410 }, { "epoch": 43.32, "learning_rate": 4.758695111193982e-05, "loss": 0.0221, "step": 180420 }, { "epoch": 43.32, "learning_rate": 4.7582469386138044e-05, "loss": 0.0116, "step": 180430 }, { "epoch": 43.33, "learning_rate": 4.7577987679805e-05, "loss": 0.0131, "step": 180440 }, { "epoch": 43.33, "learning_rate": 4.7573505992976746e-05, "loss": 0.0115, "step": 180450 }, { "epoch": 43.33, "learning_rate": 4.756902432568937e-05, "loss": 0.0218, "step": 180460 }, { "epoch": 43.33, "learning_rate": 4.756454267797899e-05, "loss": 0.0373, "step": 180470 }, { "epoch": 43.34, "learning_rate": 4.7560061049881674e-05, "loss": 0.0114, "step": 180480 }, { "epoch": 43.34, "learning_rate": 4.755557944143354e-05, "loss": 0.0135, "step": 180490 }, { "epoch": 43.34, "learning_rate": 4.755109785267065e-05, "loss": 0.0072, "step": 180500 }, { "epoch": 43.34, "learning_rate": 4.7546616283629105e-05, "loss": 0.0065, "step": 180510 }, { "epoch": 43.35, "learning_rate": 4.7542134734345e-05, "loss": 0.0166, "step": 180520 }, { "epoch": 43.35, "learning_rate": 4.753765320485441e-05, "loss": 0.0059, "step": 180530 }, { "epoch": 43.35, "learning_rate": 4.753317169519347e-05, "loss": 0.0061, "step": 180540 }, { "epoch": 43.35, "learning_rate": 4.752869020539823e-05, "loss": 0.012, "step": 180550 }, { "epoch": 43.35, "learning_rate": 4.752420873550477e-05, "loss": 0.0123, "step": 180560 }, { "epoch": 43.36, "learning_rate": 4.751972728554921e-05, "loss": 0.0056, "step": 180570 }, { "epoch": 43.36, "learning_rate": 4.751524585556762e-05, "loss": 0.0244, "step": 180580 }, { "epoch": 43.36, "learning_rate": 4.751076444559612e-05, "loss": 0.008, "step": 180590 }, { "epoch": 43.36, "learning_rate": 4.750628305567077e-05, "loss": 0.0216, "step": 180600 }, { "epoch": 43.37, "learning_rate": 4.750180168582765e-05, "loss": 0.0157, "step": 180610 }, { "epoch": 43.37, "learning_rate": 4.749732033610288e-05, "loss": 0.0141, "step": 180620 }, { "epoch": 43.37, "learning_rate": 4.749283900653255e-05, "loss": 0.008, "step": 180630 }, { "epoch": 43.37, "learning_rate": 4.748835769715271e-05, "loss": 0.0095, "step": 180640 }, { "epoch": 43.38, "learning_rate": 4.748387640799947e-05, "loss": 0.0047, "step": 180650 }, { "epoch": 43.38, "learning_rate": 4.747939513910894e-05, "loss": 0.0079, "step": 180660 }, { "epoch": 43.38, "learning_rate": 4.747491389051716e-05, "loss": 0.0105, "step": 180670 }, { "epoch": 43.38, "learning_rate": 4.747043266226028e-05, "loss": 0.0102, "step": 180680 }, { "epoch": 43.38, "learning_rate": 4.746595145437434e-05, "loss": 0.0143, "step": 180690 }, { "epoch": 43.39, "learning_rate": 4.746147026689544e-05, "loss": 0.0068, "step": 180700 }, { "epoch": 43.39, "learning_rate": 4.7456989099859675e-05, "loss": 0.0223, "step": 180710 }, { "epoch": 43.39, "learning_rate": 4.745250795330311e-05, "loss": 0.0167, "step": 180720 }, { "epoch": 43.39, "learning_rate": 4.7448026827261885e-05, "loss": 0.0244, "step": 180730 }, { "epoch": 43.4, "learning_rate": 4.744354572177203e-05, "loss": 0.021, "step": 180740 }, { "epoch": 43.4, "learning_rate": 4.743906463686965e-05, "loss": 0.0127, "step": 180750 }, { "epoch": 43.4, "learning_rate": 4.7434583572590845e-05, "loss": 0.0105, "step": 180760 }, { "epoch": 43.4, "learning_rate": 4.743010252897171e-05, "loss": 0.0147, "step": 180770 }, { "epoch": 43.4, "learning_rate": 4.742562150604828e-05, "loss": 0.0084, "step": 180780 }, { "epoch": 43.41, "learning_rate": 4.742114050385669e-05, "loss": 0.0224, "step": 180790 }, { "epoch": 43.41, "learning_rate": 4.7416659522433006e-05, "loss": 0.0101, "step": 180800 }, { "epoch": 43.41, "learning_rate": 4.7412178561813325e-05, "loss": 0.0103, "step": 180810 }, { "epoch": 43.41, "learning_rate": 4.7407697622033744e-05, "loss": 0.0094, "step": 180820 }, { "epoch": 43.42, "learning_rate": 4.7403216703130314e-05, "loss": 0.0152, "step": 180830 }, { "epoch": 43.42, "learning_rate": 4.739873580513914e-05, "loss": 0.0125, "step": 180840 }, { "epoch": 43.42, "learning_rate": 4.7394254928096306e-05, "loss": 0.011, "step": 180850 }, { "epoch": 43.42, "learning_rate": 4.738977407203788e-05, "loss": 0.0079, "step": 180860 }, { "epoch": 43.43, "learning_rate": 4.7385293237e-05, "loss": 0.0102, "step": 180870 }, { "epoch": 43.43, "learning_rate": 4.7380812423018694e-05, "loss": 0.0295, "step": 180880 }, { "epoch": 43.43, "learning_rate": 4.737633163013006e-05, "loss": 0.0096, "step": 180890 }, { "epoch": 43.43, "learning_rate": 4.73718508583702e-05, "loss": 0.0078, "step": 180900 }, { "epoch": 43.43, "learning_rate": 4.736737010777518e-05, "loss": 0.0083, "step": 180910 }, { "epoch": 43.44, "learning_rate": 4.736288937838111e-05, "loss": 0.0108, "step": 180920 }, { "epoch": 43.44, "learning_rate": 4.735840867022405e-05, "loss": 0.0126, "step": 180930 }, { "epoch": 43.44, "learning_rate": 4.7353927983340065e-05, "loss": 0.0169, "step": 180940 }, { "epoch": 43.44, "learning_rate": 4.734944731776529e-05, "loss": 0.0102, "step": 180950 }, { "epoch": 43.45, "learning_rate": 4.734496667353579e-05, "loss": 0.0081, "step": 180960 }, { "epoch": 43.45, "learning_rate": 4.734048605068761e-05, "loss": 0.0089, "step": 180970 }, { "epoch": 43.45, "learning_rate": 4.733600544925688e-05, "loss": 0.0116, "step": 180980 }, { "epoch": 43.45, "learning_rate": 4.7331524869279656e-05, "loss": 0.0216, "step": 180990 }, { "epoch": 43.45, "learning_rate": 4.732704431079204e-05, "loss": 0.0097, "step": 181000 }, { "epoch": 43.46, "learning_rate": 4.732256377383011e-05, "loss": 0.0134, "step": 181010 }, { "epoch": 43.46, "learning_rate": 4.7318083258429925e-05, "loss": 0.0209, "step": 181020 }, { "epoch": 43.46, "learning_rate": 4.73136027646276e-05, "loss": 0.0207, "step": 181030 }, { "epoch": 43.46, "learning_rate": 4.730912229245919e-05, "loss": 0.0137, "step": 181040 }, { "epoch": 43.47, "learning_rate": 4.73046418419608e-05, "loss": 0.0149, "step": 181050 }, { "epoch": 43.47, "learning_rate": 4.7300161413168514e-05, "loss": 0.0101, "step": 181060 }, { "epoch": 43.47, "learning_rate": 4.7295681006118387e-05, "loss": 0.0146, "step": 181070 }, { "epoch": 43.47, "learning_rate": 4.7291200620846506e-05, "loss": 0.0367, "step": 181080 }, { "epoch": 43.48, "learning_rate": 4.728672025738897e-05, "loss": 0.0138, "step": 181090 }, { "epoch": 43.48, "learning_rate": 4.728223991578186e-05, "loss": 0.0207, "step": 181100 }, { "epoch": 43.48, "learning_rate": 4.727775959606123e-05, "loss": 0.0088, "step": 181110 }, { "epoch": 43.48, "learning_rate": 4.727327929826319e-05, "loss": 0.0065, "step": 181120 }, { "epoch": 43.48, "learning_rate": 4.726879902242379e-05, "loss": 0.0238, "step": 181130 }, { "epoch": 43.49, "learning_rate": 4.726431876857914e-05, "loss": 0.0152, "step": 181140 }, { "epoch": 43.49, "learning_rate": 4.725983853676533e-05, "loss": 0.0106, "step": 181150 }, { "epoch": 43.49, "learning_rate": 4.725535832701839e-05, "loss": 0.0052, "step": 181160 }, { "epoch": 43.49, "learning_rate": 4.725087813937443e-05, "loss": 0.018, "step": 181170 }, { "epoch": 43.5, "learning_rate": 4.7246397973869525e-05, "loss": 0.0123, "step": 181180 }, { "epoch": 43.5, "learning_rate": 4.724191783053977e-05, "loss": 0.0185, "step": 181190 }, { "epoch": 43.5, "learning_rate": 4.723743770942124e-05, "loss": 0.0167, "step": 181200 }, { "epoch": 43.5, "learning_rate": 4.723295761054999e-05, "loss": 0.0077, "step": 181210 }, { "epoch": 43.51, "learning_rate": 4.722847753396212e-05, "loss": 0.0098, "step": 181220 }, { "epoch": 43.51, "learning_rate": 4.722399747969369e-05, "loss": 0.0112, "step": 181230 }, { "epoch": 43.51, "learning_rate": 4.72195174477808e-05, "loss": 0.0182, "step": 181240 }, { "epoch": 43.51, "learning_rate": 4.721503743825954e-05, "loss": 0.0155, "step": 181250 }, { "epoch": 43.51, "learning_rate": 4.721055745116595e-05, "loss": 0.0078, "step": 181260 }, { "epoch": 43.52, "learning_rate": 4.720607748653612e-05, "loss": 0.0116, "step": 181270 }, { "epoch": 43.52, "learning_rate": 4.720159754440614e-05, "loss": 0.0135, "step": 181280 }, { "epoch": 43.52, "learning_rate": 4.7197117624812094e-05, "loss": 0.0146, "step": 181290 }, { "epoch": 43.52, "learning_rate": 4.719263772779002e-05, "loss": 0.0045, "step": 181300 }, { "epoch": 43.53, "learning_rate": 4.7188157853376044e-05, "loss": 0.0083, "step": 181310 }, { "epoch": 43.53, "learning_rate": 4.7183678001606205e-05, "loss": 0.0102, "step": 181320 }, { "epoch": 43.53, "learning_rate": 4.71791981725166e-05, "loss": 0.012, "step": 181330 }, { "epoch": 43.53, "learning_rate": 4.7174718366143324e-05, "loss": 0.0135, "step": 181340 }, { "epoch": 43.53, "learning_rate": 4.71702385825224e-05, "loss": 0.0163, "step": 181350 }, { "epoch": 43.54, "learning_rate": 4.716575882168995e-05, "loss": 0.0313, "step": 181360 }, { "epoch": 43.54, "learning_rate": 4.7161279083682025e-05, "loss": 0.0123, "step": 181370 }, { "epoch": 43.54, "learning_rate": 4.7156799368534724e-05, "loss": 0.007, "step": 181380 }, { "epoch": 43.54, "learning_rate": 4.715231967628412e-05, "loss": 0.0094, "step": 181390 }, { "epoch": 43.55, "learning_rate": 4.7147840006966255e-05, "loss": 0.0135, "step": 181400 }, { "epoch": 43.55, "learning_rate": 4.714336036061724e-05, "loss": 0.0138, "step": 181410 }, { "epoch": 43.55, "learning_rate": 4.7138880737273126e-05, "loss": 0.0184, "step": 181420 }, { "epoch": 43.55, "learning_rate": 4.713440113697002e-05, "loss": 0.0078, "step": 181430 }, { "epoch": 43.56, "learning_rate": 4.712992155974397e-05, "loss": 0.0082, "step": 181440 }, { "epoch": 43.56, "learning_rate": 4.712544200563106e-05, "loss": 0.0103, "step": 181450 }, { "epoch": 43.56, "learning_rate": 4.712096247466735e-05, "loss": 0.0148, "step": 181460 }, { "epoch": 43.56, "learning_rate": 4.711648296688893e-05, "loss": 0.0146, "step": 181470 }, { "epoch": 43.56, "learning_rate": 4.71120034823319e-05, "loss": 0.0217, "step": 181480 }, { "epoch": 43.57, "learning_rate": 4.710752402103227e-05, "loss": 0.0085, "step": 181490 }, { "epoch": 43.57, "learning_rate": 4.710304458302616e-05, "loss": 0.0168, "step": 181500 }, { "epoch": 43.57, "learning_rate": 4.709856516834962e-05, "loss": 0.0077, "step": 181510 }, { "epoch": 43.57, "learning_rate": 4.709408577703875e-05, "loss": 0.0201, "step": 181520 }, { "epoch": 43.58, "learning_rate": 4.708960640912962e-05, "loss": 0.0172, "step": 181530 }, { "epoch": 43.58, "learning_rate": 4.708512706465826e-05, "loss": 0.0095, "step": 181540 }, { "epoch": 43.58, "learning_rate": 4.70806477436608e-05, "loss": 0.0205, "step": 181550 }, { "epoch": 43.58, "learning_rate": 4.7076168446173264e-05, "loss": 0.0062, "step": 181560 }, { "epoch": 43.59, "learning_rate": 4.7071689172231765e-05, "loss": 0.0098, "step": 181570 }, { "epoch": 43.59, "learning_rate": 4.706720992187236e-05, "loss": 0.0109, "step": 181580 }, { "epoch": 43.59, "learning_rate": 4.706273069513111e-05, "loss": 0.0137, "step": 181590 }, { "epoch": 43.59, "learning_rate": 4.705825149204409e-05, "loss": 0.024, "step": 181600 }, { "epoch": 43.59, "learning_rate": 4.705377231264738e-05, "loss": 0.0159, "step": 181610 }, { "epoch": 43.6, "learning_rate": 4.7049293156977056e-05, "loss": 0.0084, "step": 181620 }, { "epoch": 43.6, "learning_rate": 4.7044814025069186e-05, "loss": 0.018, "step": 181630 }, { "epoch": 43.6, "learning_rate": 4.704033491695982e-05, "loss": 0.0099, "step": 181640 }, { "epoch": 43.6, "learning_rate": 4.703585583268505e-05, "loss": 0.0222, "step": 181650 }, { "epoch": 43.61, "learning_rate": 4.703137677228094e-05, "loss": 0.018, "step": 181660 }, { "epoch": 43.61, "learning_rate": 4.702689773578358e-05, "loss": 0.0092, "step": 181670 }, { "epoch": 43.61, "learning_rate": 4.7022418723229014e-05, "loss": 0.0176, "step": 181680 }, { "epoch": 43.61, "learning_rate": 4.701793973465331e-05, "loss": 0.0185, "step": 181690 }, { "epoch": 43.61, "learning_rate": 4.701346077009256e-05, "loss": 0.0139, "step": 181700 }, { "epoch": 43.62, "learning_rate": 4.700898182958281e-05, "loss": 0.0146, "step": 181710 }, { "epoch": 43.62, "learning_rate": 4.700450291316017e-05, "loss": 0.0182, "step": 181720 }, { "epoch": 43.62, "learning_rate": 4.7000024020860656e-05, "loss": 0.0117, "step": 181730 }, { "epoch": 43.62, "learning_rate": 4.699554515272037e-05, "loss": 0.0169, "step": 181740 }, { "epoch": 43.63, "learning_rate": 4.699106630877537e-05, "loss": 0.0094, "step": 181750 }, { "epoch": 43.63, "learning_rate": 4.6986587489061746e-05, "loss": 0.0219, "step": 181760 }, { "epoch": 43.63, "learning_rate": 4.6982108693615535e-05, "loss": 0.0141, "step": 181770 }, { "epoch": 43.63, "learning_rate": 4.697762992247281e-05, "loss": 0.0072, "step": 181780 }, { "epoch": 43.64, "learning_rate": 4.697315117566966e-05, "loss": 0.0175, "step": 181790 }, { "epoch": 43.64, "learning_rate": 4.696867245324213e-05, "loss": 0.0096, "step": 181800 }, { "epoch": 43.64, "learning_rate": 4.696419375522632e-05, "loss": 0.01, "step": 181810 }, { "epoch": 43.64, "learning_rate": 4.695971508165827e-05, "loss": 0.014, "step": 181820 }, { "epoch": 43.64, "learning_rate": 4.695523643257404e-05, "loss": 0.0091, "step": 181830 }, { "epoch": 43.65, "learning_rate": 4.6950757808009726e-05, "loss": 0.0052, "step": 181840 }, { "epoch": 43.65, "learning_rate": 4.6946279208001365e-05, "loss": 0.0135, "step": 181850 }, { "epoch": 43.65, "learning_rate": 4.694180063258507e-05, "loss": 0.0129, "step": 181860 }, { "epoch": 43.65, "learning_rate": 4.6937322081796856e-05, "loss": 0.0126, "step": 181870 }, { "epoch": 43.66, "learning_rate": 4.6932843555672794e-05, "loss": 0.0182, "step": 181880 }, { "epoch": 43.66, "learning_rate": 4.692836505424899e-05, "loss": 0.013, "step": 181890 }, { "epoch": 43.66, "learning_rate": 4.692388657756147e-05, "loss": 0.014, "step": 181900 }, { "epoch": 43.66, "learning_rate": 4.6919408125646345e-05, "loss": 0.0088, "step": 181910 }, { "epoch": 43.67, "learning_rate": 4.691492969853963e-05, "loss": 0.005, "step": 181920 }, { "epoch": 43.67, "learning_rate": 4.691045129627741e-05, "loss": 0.013, "step": 181930 }, { "epoch": 43.67, "learning_rate": 4.690597291889575e-05, "loss": 0.0141, "step": 181940 }, { "epoch": 43.67, "learning_rate": 4.6901494566430734e-05, "loss": 0.0086, "step": 181950 }, { "epoch": 43.67, "learning_rate": 4.68970162389184e-05, "loss": 0.0045, "step": 181960 }, { "epoch": 43.68, "learning_rate": 4.6892537936394815e-05, "loss": 0.0183, "step": 181970 }, { "epoch": 43.68, "learning_rate": 4.688805965889606e-05, "loss": 0.0081, "step": 181980 }, { "epoch": 43.68, "learning_rate": 4.688358140645818e-05, "loss": 0.0098, "step": 181990 }, { "epoch": 43.68, "learning_rate": 4.687910317911727e-05, "loss": 0.0064, "step": 182000 }, { "epoch": 43.69, "learning_rate": 4.687462497690936e-05, "loss": 0.0134, "step": 182010 }, { "epoch": 43.69, "learning_rate": 4.6870146799870515e-05, "loss": 0.0097, "step": 182020 }, { "epoch": 43.69, "learning_rate": 4.6865668648036834e-05, "loss": 0.0067, "step": 182030 }, { "epoch": 43.69, "learning_rate": 4.686119052144433e-05, "loss": 0.0105, "step": 182040 }, { "epoch": 43.69, "learning_rate": 4.685671242012912e-05, "loss": 0.0206, "step": 182050 }, { "epoch": 43.7, "learning_rate": 4.6852234344127225e-05, "loss": 0.0095, "step": 182060 }, { "epoch": 43.7, "learning_rate": 4.684775629347471e-05, "loss": 0.0102, "step": 182070 }, { "epoch": 43.7, "learning_rate": 4.684327826820767e-05, "loss": 0.0061, "step": 182080 }, { "epoch": 43.7, "learning_rate": 4.6838800268362145e-05, "loss": 0.008, "step": 182090 }, { "epoch": 43.71, "learning_rate": 4.683432229397418e-05, "loss": 0.0158, "step": 182100 }, { "epoch": 43.71, "learning_rate": 4.6829844345079865e-05, "loss": 0.0137, "step": 182110 }, { "epoch": 43.71, "learning_rate": 4.682536642171524e-05, "loss": 0.0104, "step": 182120 }, { "epoch": 43.71, "learning_rate": 4.682088852391639e-05, "loss": 0.0132, "step": 182130 }, { "epoch": 43.72, "learning_rate": 4.681641065171937e-05, "loss": 0.0105, "step": 182140 }, { "epoch": 43.72, "learning_rate": 4.681193280516023e-05, "loss": 0.0127, "step": 182150 }, { "epoch": 43.72, "learning_rate": 4.680745498427502e-05, "loss": 0.0188, "step": 182160 }, { "epoch": 43.72, "learning_rate": 4.680297718909983e-05, "loss": 0.0121, "step": 182170 }, { "epoch": 43.72, "learning_rate": 4.679849941967069e-05, "loss": 0.0249, "step": 182180 }, { "epoch": 43.73, "learning_rate": 4.679402167602371e-05, "loss": 0.0155, "step": 182190 }, { "epoch": 43.73, "learning_rate": 4.6789543958194896e-05, "loss": 0.0043, "step": 182200 }, { "epoch": 43.73, "learning_rate": 4.6785066266220315e-05, "loss": 0.0199, "step": 182210 }, { "epoch": 43.73, "learning_rate": 4.678058860013605e-05, "loss": 0.0152, "step": 182220 }, { "epoch": 43.74, "learning_rate": 4.6776110959978145e-05, "loss": 0.0117, "step": 182230 }, { "epoch": 43.74, "learning_rate": 4.6771633345782676e-05, "loss": 0.0083, "step": 182240 }, { "epoch": 43.74, "learning_rate": 4.676715575758569e-05, "loss": 0.007, "step": 182250 }, { "epoch": 43.74, "learning_rate": 4.6762678195423225e-05, "loss": 0.0123, "step": 182260 }, { "epoch": 43.75, "learning_rate": 4.675820065933138e-05, "loss": 0.0112, "step": 182270 }, { "epoch": 43.75, "learning_rate": 4.675372314934619e-05, "loss": 0.013, "step": 182280 }, { "epoch": 43.75, "learning_rate": 4.6749245665503696e-05, "loss": 0.0105, "step": 182290 }, { "epoch": 43.75, "learning_rate": 4.674476820784e-05, "loss": 0.0204, "step": 182300 }, { "epoch": 43.75, "learning_rate": 4.674029077639111e-05, "loss": 0.0125, "step": 182310 }, { "epoch": 43.76, "learning_rate": 4.6735813371193124e-05, "loss": 0.0301, "step": 182320 }, { "epoch": 43.76, "learning_rate": 4.6731335992282096e-05, "loss": 0.0039, "step": 182330 }, { "epoch": 43.76, "learning_rate": 4.672685863969406e-05, "loss": 0.0239, "step": 182340 }, { "epoch": 43.76, "learning_rate": 4.672238131346507e-05, "loss": 0.0064, "step": 182350 }, { "epoch": 43.77, "learning_rate": 4.6717904013631206e-05, "loss": 0.0073, "step": 182360 }, { "epoch": 43.77, "learning_rate": 4.6713426740228506e-05, "loss": 0.0238, "step": 182370 }, { "epoch": 43.77, "learning_rate": 4.670894949329306e-05, "loss": 0.0159, "step": 182380 }, { "epoch": 43.77, "learning_rate": 4.670447227286088e-05, "loss": 0.0147, "step": 182390 }, { "epoch": 43.77, "learning_rate": 4.669999507896803e-05, "loss": 0.0089, "step": 182400 }, { "epoch": 43.78, "learning_rate": 4.669551791165059e-05, "loss": 0.0037, "step": 182410 }, { "epoch": 43.78, "learning_rate": 4.669104077094461e-05, "loss": 0.0114, "step": 182420 }, { "epoch": 43.78, "learning_rate": 4.6686563656886106e-05, "loss": 0.0035, "step": 182430 }, { "epoch": 43.78, "learning_rate": 4.668208656951118e-05, "loss": 0.0122, "step": 182440 }, { "epoch": 43.79, "learning_rate": 4.6677609508855856e-05, "loss": 0.01, "step": 182450 }, { "epoch": 43.79, "learning_rate": 4.6673132474956215e-05, "loss": 0.0103, "step": 182460 }, { "epoch": 43.79, "learning_rate": 4.666865546784831e-05, "loss": 0.0073, "step": 182470 }, { "epoch": 43.79, "learning_rate": 4.6664178487568156e-05, "loss": 0.0164, "step": 182480 }, { "epoch": 43.8, "learning_rate": 4.6659701534151844e-05, "loss": 0.0194, "step": 182490 }, { "epoch": 43.8, "learning_rate": 4.665522460763541e-05, "loss": 0.0051, "step": 182500 }, { "epoch": 43.8, "learning_rate": 4.665074770805492e-05, "loss": 0.0066, "step": 182510 }, { "epoch": 43.8, "learning_rate": 4.664627083544644e-05, "loss": 0.0081, "step": 182520 }, { "epoch": 43.8, "learning_rate": 4.6641793989845974e-05, "loss": 0.0229, "step": 182530 }, { "epoch": 43.81, "learning_rate": 4.663731717128961e-05, "loss": 0.0242, "step": 182540 }, { "epoch": 43.81, "learning_rate": 4.6632840379813397e-05, "loss": 0.0307, "step": 182550 }, { "epoch": 43.81, "learning_rate": 4.662836361545339e-05, "loss": 0.0093, "step": 182560 }, { "epoch": 43.81, "learning_rate": 4.662388687824565e-05, "loss": 0.0135, "step": 182570 }, { "epoch": 43.82, "learning_rate": 4.66194101682262e-05, "loss": 0.0114, "step": 182580 }, { "epoch": 43.82, "learning_rate": 4.66149334854311e-05, "loss": 0.0203, "step": 182590 }, { "epoch": 43.82, "learning_rate": 4.6610456829896424e-05, "loss": 0.0122, "step": 182600 }, { "epoch": 43.82, "learning_rate": 4.660598020165821e-05, "loss": 0.0144, "step": 182610 }, { "epoch": 43.83, "learning_rate": 4.6601503600752486e-05, "loss": 0.0299, "step": 182620 }, { "epoch": 43.83, "learning_rate": 4.6597027027215326e-05, "loss": 0.0105, "step": 182630 }, { "epoch": 43.83, "learning_rate": 4.659255048108277e-05, "loss": 0.0109, "step": 182640 }, { "epoch": 43.83, "learning_rate": 4.65880739623909e-05, "loss": 0.0051, "step": 182650 }, { "epoch": 43.83, "learning_rate": 4.6583597471175735e-05, "loss": 0.0122, "step": 182660 }, { "epoch": 43.84, "learning_rate": 4.657912100747332e-05, "loss": 0.0261, "step": 182670 }, { "epoch": 43.84, "learning_rate": 4.6574644571319725e-05, "loss": 0.0201, "step": 182680 }, { "epoch": 43.84, "learning_rate": 4.657016816275098e-05, "loss": 0.0114, "step": 182690 }, { "epoch": 43.84, "learning_rate": 4.656569178180315e-05, "loss": 0.0081, "step": 182700 }, { "epoch": 43.85, "learning_rate": 4.6561215428512286e-05, "loss": 0.0232, "step": 182710 }, { "epoch": 43.85, "learning_rate": 4.6556739102914416e-05, "loss": 0.015, "step": 182720 }, { "epoch": 43.85, "learning_rate": 4.655226280504561e-05, "loss": 0.0119, "step": 182730 }, { "epoch": 43.85, "learning_rate": 4.654778653494189e-05, "loss": 0.0109, "step": 182740 }, { "epoch": 43.85, "learning_rate": 4.654331029263937e-05, "loss": 0.0129, "step": 182750 }, { "epoch": 43.86, "learning_rate": 4.6538834078174e-05, "loss": 0.0175, "step": 182760 }, { "epoch": 43.86, "learning_rate": 4.6534357891581895e-05, "loss": 0.007, "step": 182770 }, { "epoch": 43.86, "learning_rate": 4.652988173289908e-05, "loss": 0.0136, "step": 182780 }, { "epoch": 43.86, "learning_rate": 4.652540560216161e-05, "loss": 0.0052, "step": 182790 }, { "epoch": 43.87, "learning_rate": 4.652092949940554e-05, "loss": 0.0153, "step": 182800 }, { "epoch": 43.87, "learning_rate": 4.6516453424666886e-05, "loss": 0.0107, "step": 182810 }, { "epoch": 43.87, "learning_rate": 4.651197737798172e-05, "loss": 0.0105, "step": 182820 }, { "epoch": 43.87, "learning_rate": 4.650750135938607e-05, "loss": 0.0114, "step": 182830 }, { "epoch": 43.88, "learning_rate": 4.650302536891601e-05, "loss": 0.0178, "step": 182840 }, { "epoch": 43.88, "learning_rate": 4.649854940660757e-05, "loss": 0.0099, "step": 182850 }, { "epoch": 43.88, "learning_rate": 4.649407347249678e-05, "loss": 0.0068, "step": 182860 }, { "epoch": 43.88, "learning_rate": 4.648959756661972e-05, "loss": 0.0072, "step": 182870 }, { "epoch": 43.88, "learning_rate": 4.6485121689012396e-05, "loss": 0.0112, "step": 182880 }, { "epoch": 43.89, "learning_rate": 4.6480645839710876e-05, "loss": 0.0071, "step": 182890 }, { "epoch": 43.89, "learning_rate": 4.647617001875123e-05, "loss": 0.0246, "step": 182900 }, { "epoch": 43.89, "learning_rate": 4.647169422616944e-05, "loss": 0.0075, "step": 182910 }, { "epoch": 43.89, "learning_rate": 4.6467218462001596e-05, "loss": 0.0115, "step": 182920 }, { "epoch": 43.9, "learning_rate": 4.646274272628371e-05, "loss": 0.0049, "step": 182930 }, { "epoch": 43.9, "learning_rate": 4.6458267019051884e-05, "loss": 0.0132, "step": 182940 }, { "epoch": 43.9, "learning_rate": 4.64537913403421e-05, "loss": 0.0125, "step": 182950 }, { "epoch": 43.9, "learning_rate": 4.6449315690190415e-05, "loss": 0.0061, "step": 182960 }, { "epoch": 43.91, "learning_rate": 4.6444840068632887e-05, "loss": 0.0132, "step": 182970 }, { "epoch": 43.91, "learning_rate": 4.644036447570555e-05, "loss": 0.0123, "step": 182980 }, { "epoch": 43.91, "learning_rate": 4.643588891144448e-05, "loss": 0.0118, "step": 182990 }, { "epoch": 43.91, "learning_rate": 4.6431413375885656e-05, "loss": 0.0126, "step": 183000 }, { "epoch": 43.91, "learning_rate": 4.642693786906517e-05, "loss": 0.0126, "step": 183010 }, { "epoch": 43.92, "learning_rate": 4.6422462391019025e-05, "loss": 0.0172, "step": 183020 }, { "epoch": 43.92, "learning_rate": 4.6417986941783296e-05, "loss": 0.0194, "step": 183030 }, { "epoch": 43.92, "learning_rate": 4.6413511521394026e-05, "loss": 0.0109, "step": 183040 }, { "epoch": 43.92, "learning_rate": 4.6409036129887225e-05, "loss": 0.0183, "step": 183050 }, { "epoch": 43.93, "learning_rate": 4.640456076729896e-05, "loss": 0.0077, "step": 183060 }, { "epoch": 43.93, "learning_rate": 4.640008543366525e-05, "loss": 0.0228, "step": 183070 }, { "epoch": 43.93, "learning_rate": 4.6395610129022174e-05, "loss": 0.0196, "step": 183080 }, { "epoch": 43.93, "learning_rate": 4.6391134853405735e-05, "loss": 0.0238, "step": 183090 }, { "epoch": 43.93, "learning_rate": 4.638665960685197e-05, "loss": 0.0133, "step": 183100 }, { "epoch": 43.94, "learning_rate": 4.638218438939696e-05, "loss": 0.0152, "step": 183110 }, { "epoch": 43.94, "learning_rate": 4.637770920107669e-05, "loss": 0.0094, "step": 183120 }, { "epoch": 43.94, "learning_rate": 4.637323404192726e-05, "loss": 0.0102, "step": 183130 }, { "epoch": 43.94, "learning_rate": 4.636875891198466e-05, "loss": 0.0071, "step": 183140 }, { "epoch": 43.95, "learning_rate": 4.636428381128494e-05, "loss": 0.0105, "step": 183150 }, { "epoch": 43.95, "learning_rate": 4.6359808739864155e-05, "loss": 0.0101, "step": 183160 }, { "epoch": 43.95, "learning_rate": 4.635533369775832e-05, "loss": 0.0256, "step": 183170 }, { "epoch": 44.0, "learning_rate": 4.6350858685003515e-05, "loss": 0.0054, "step": 183180 }, { "epoch": 44.0, "learning_rate": 4.634638370163572e-05, "loss": 0.0205, "step": 183190 }, { "epoch": 44.01, "learning_rate": 4.634190874769102e-05, "loss": 0.0103, "step": 183200 }, { "epoch": 44.01, "learning_rate": 4.633743382320541e-05, "loss": 0.0202, "step": 183210 }, { "epoch": 44.01, "learning_rate": 4.633295892821497e-05, "loss": 0.0099, "step": 183220 }, { "epoch": 44.01, "learning_rate": 4.632848406275572e-05, "loss": 0.0069, "step": 183230 }, { "epoch": 44.02, "learning_rate": 4.632400922686368e-05, "loss": 0.0078, "step": 183240 }, { "epoch": 44.02, "learning_rate": 4.6319534420574913e-05, "loss": 0.0095, "step": 183250 }, { "epoch": 44.02, "learning_rate": 4.631505964392543e-05, "loss": 0.0119, "step": 183260 }, { "epoch": 44.02, "learning_rate": 4.63105848969513e-05, "loss": 0.0128, "step": 183270 }, { "epoch": 44.02, "learning_rate": 4.6306110179688534e-05, "loss": 0.03, "step": 183280 }, { "epoch": 44.03, "learning_rate": 4.6301635492173156e-05, "loss": 0.0118, "step": 183290 }, { "epoch": 44.03, "learning_rate": 4.629716083444123e-05, "loss": 0.0087, "step": 183300 }, { "epoch": 44.03, "learning_rate": 4.629268620652877e-05, "loss": 0.0146, "step": 183310 }, { "epoch": 44.03, "learning_rate": 4.628821160847184e-05, "loss": 0.0066, "step": 183320 }, { "epoch": 44.04, "learning_rate": 4.628373704030645e-05, "loss": 0.0137, "step": 183330 }, { "epoch": 44.04, "learning_rate": 4.627926250206862e-05, "loss": 0.0095, "step": 183340 }, { "epoch": 44.04, "learning_rate": 4.627478799379441e-05, "loss": 0.011, "step": 183350 }, { "epoch": 44.04, "learning_rate": 4.627031351551985e-05, "loss": 0.0207, "step": 183360 }, { "epoch": 44.05, "learning_rate": 4.6265839067280986e-05, "loss": 0.0098, "step": 183370 }, { "epoch": 44.05, "learning_rate": 4.626136464911382e-05, "loss": 0.0091, "step": 183380 }, { "epoch": 44.05, "learning_rate": 4.625689026105439e-05, "loss": 0.0154, "step": 183390 }, { "epoch": 44.05, "learning_rate": 4.6252415903138755e-05, "loss": 0.0174, "step": 183400 }, { "epoch": 44.05, "learning_rate": 4.624794157540292e-05, "loss": 0.0245, "step": 183410 }, { "epoch": 44.06, "learning_rate": 4.624346727788296e-05, "loss": 0.0129, "step": 183420 }, { "epoch": 44.06, "learning_rate": 4.6238993010614844e-05, "loss": 0.0129, "step": 183430 }, { "epoch": 44.06, "learning_rate": 4.623451877363465e-05, "loss": 0.0264, "step": 183440 }, { "epoch": 44.06, "learning_rate": 4.6230044566978386e-05, "loss": 0.0274, "step": 183450 }, { "epoch": 44.07, "learning_rate": 4.6225570390682114e-05, "loss": 0.0116, "step": 183460 }, { "epoch": 44.07, "learning_rate": 4.622109624478183e-05, "loss": 0.0089, "step": 183470 }, { "epoch": 44.07, "learning_rate": 4.621662212931357e-05, "loss": 0.0151, "step": 183480 }, { "epoch": 44.07, "learning_rate": 4.621214804431339e-05, "loss": 0.0133, "step": 183490 }, { "epoch": 44.07, "learning_rate": 4.620767398981729e-05, "loss": 0.0086, "step": 183500 }, { "epoch": 44.08, "learning_rate": 4.620319996586134e-05, "loss": 0.0269, "step": 183510 }, { "epoch": 44.08, "learning_rate": 4.6198725972481526e-05, "loss": 0.0059, "step": 183520 }, { "epoch": 44.08, "learning_rate": 4.61942520097139e-05, "loss": 0.0109, "step": 183530 }, { "epoch": 44.08, "learning_rate": 4.618977807759449e-05, "loss": 0.0125, "step": 183540 }, { "epoch": 44.09, "learning_rate": 4.61853041761593e-05, "loss": 0.005, "step": 183550 }, { "epoch": 44.09, "learning_rate": 4.618083030544442e-05, "loss": 0.0128, "step": 183560 }, { "epoch": 44.09, "learning_rate": 4.617635646548583e-05, "loss": 0.0185, "step": 183570 }, { "epoch": 44.09, "learning_rate": 4.617188265631955e-05, "loss": 0.0067, "step": 183580 }, { "epoch": 44.1, "learning_rate": 4.6167408877981644e-05, "loss": 0.0104, "step": 183590 }, { "epoch": 44.1, "learning_rate": 4.616293513050813e-05, "loss": 0.0091, "step": 183600 }, { "epoch": 44.1, "learning_rate": 4.6158461413935015e-05, "loss": 0.0158, "step": 183610 }, { "epoch": 44.1, "learning_rate": 4.6153987728298345e-05, "loss": 0.0115, "step": 183620 }, { "epoch": 44.1, "learning_rate": 4.614951407363415e-05, "loss": 0.0105, "step": 183630 }, { "epoch": 44.11, "learning_rate": 4.6145040449978436e-05, "loss": 0.0214, "step": 183640 }, { "epoch": 44.11, "learning_rate": 4.614056685736726e-05, "loss": 0.0064, "step": 183650 }, { "epoch": 44.11, "learning_rate": 4.6136093295836626e-05, "loss": 0.016, "step": 183660 }, { "epoch": 44.11, "learning_rate": 4.613161976542255e-05, "loss": 0.0105, "step": 183670 }, { "epoch": 44.12, "learning_rate": 4.612714626616109e-05, "loss": 0.0062, "step": 183680 }, { "epoch": 44.12, "learning_rate": 4.612267279808824e-05, "loss": 0.0069, "step": 183690 }, { "epoch": 44.12, "learning_rate": 4.611819936124007e-05, "loss": 0.0125, "step": 183700 }, { "epoch": 44.12, "learning_rate": 4.6113725955652556e-05, "loss": 0.0075, "step": 183710 }, { "epoch": 44.13, "learning_rate": 4.610925258136174e-05, "loss": 0.0048, "step": 183720 }, { "epoch": 44.13, "learning_rate": 4.610477923840366e-05, "loss": 0.0103, "step": 183730 }, { "epoch": 44.13, "learning_rate": 4.610030592681432e-05, "loss": 0.0048, "step": 183740 }, { "epoch": 44.13, "learning_rate": 4.609583264662978e-05, "loss": 0.006, "step": 183750 }, { "epoch": 44.13, "learning_rate": 4.609135939788602e-05, "loss": 0.0119, "step": 183760 }, { "epoch": 44.14, "learning_rate": 4.608688618061907e-05, "loss": 0.0165, "step": 183770 }, { "epoch": 44.14, "learning_rate": 4.608241299486499e-05, "loss": 0.0046, "step": 183780 }, { "epoch": 44.14, "learning_rate": 4.607793984065978e-05, "loss": 0.0079, "step": 183790 }, { "epoch": 44.14, "learning_rate": 4.607346671803944e-05, "loss": 0.0101, "step": 183800 }, { "epoch": 44.15, "learning_rate": 4.606899362704002e-05, "loss": 0.0073, "step": 183810 }, { "epoch": 44.15, "learning_rate": 4.606452056769754e-05, "loss": 0.0212, "step": 183820 }, { "epoch": 44.15, "learning_rate": 4.6060047540048025e-05, "loss": 0.0085, "step": 183830 }, { "epoch": 44.15, "learning_rate": 4.60555745441275e-05, "loss": 0.0096, "step": 183840 }, { "epoch": 44.15, "learning_rate": 4.605110157997197e-05, "loss": 0.0152, "step": 183850 }, { "epoch": 44.16, "learning_rate": 4.604662864761745e-05, "loss": 0.0118, "step": 183860 }, { "epoch": 44.16, "learning_rate": 4.604215574709998e-05, "loss": 0.0101, "step": 183870 }, { "epoch": 44.16, "learning_rate": 4.603768287845557e-05, "loss": 0.0059, "step": 183880 }, { "epoch": 44.16, "learning_rate": 4.6033210041720275e-05, "loss": 0.0168, "step": 183890 }, { "epoch": 44.17, "learning_rate": 4.602873723693007e-05, "loss": 0.0113, "step": 183900 }, { "epoch": 44.17, "learning_rate": 4.6024264464120984e-05, "loss": 0.0135, "step": 183910 }, { "epoch": 44.17, "learning_rate": 4.6019791723329055e-05, "loss": 0.0118, "step": 183920 }, { "epoch": 44.17, "learning_rate": 4.6015319014590303e-05, "loss": 0.0147, "step": 183930 }, { "epoch": 44.18, "learning_rate": 4.601084633794072e-05, "loss": 0.0098, "step": 183940 }, { "epoch": 44.18, "learning_rate": 4.6006373693416346e-05, "loss": 0.0212, "step": 183950 }, { "epoch": 44.18, "learning_rate": 4.6001901081053186e-05, "loss": 0.0281, "step": 183960 }, { "epoch": 44.18, "learning_rate": 4.5997428500887286e-05, "loss": 0.0077, "step": 183970 }, { "epoch": 44.18, "learning_rate": 4.599295595295465e-05, "loss": 0.0079, "step": 183980 }, { "epoch": 44.19, "learning_rate": 4.598848343729127e-05, "loss": 0.0104, "step": 183990 }, { "epoch": 44.19, "learning_rate": 4.598401095393321e-05, "loss": 0.0091, "step": 184000 }, { "epoch": 44.19, "learning_rate": 4.597953850291644e-05, "loss": 0.0139, "step": 184010 }, { "epoch": 44.19, "learning_rate": 4.597506608427703e-05, "loss": 0.0083, "step": 184020 }, { "epoch": 44.2, "learning_rate": 4.597059369805096e-05, "loss": 0.006, "step": 184030 }, { "epoch": 44.2, "learning_rate": 4.5966121344274235e-05, "loss": 0.0141, "step": 184040 }, { "epoch": 44.2, "learning_rate": 4.596164902298291e-05, "loss": 0.0065, "step": 184050 }, { "epoch": 44.2, "learning_rate": 4.5957176734212985e-05, "loss": 0.0064, "step": 184060 }, { "epoch": 44.21, "learning_rate": 4.595270447800046e-05, "loss": 0.0097, "step": 184070 }, { "epoch": 44.21, "learning_rate": 4.5948232254381384e-05, "loss": 0.0195, "step": 184080 }, { "epoch": 44.21, "learning_rate": 4.5943760063391745e-05, "loss": 0.0183, "step": 184090 }, { "epoch": 44.21, "learning_rate": 4.593928790506756e-05, "loss": 0.0057, "step": 184100 }, { "epoch": 44.21, "learning_rate": 4.593481577944485e-05, "loss": 0.0154, "step": 184110 }, { "epoch": 44.22, "learning_rate": 4.593034368655965e-05, "loss": 0.006, "step": 184120 }, { "epoch": 44.22, "learning_rate": 4.592587162644792e-05, "loss": 0.0128, "step": 184130 }, { "epoch": 44.22, "learning_rate": 4.5921399599145734e-05, "loss": 0.026, "step": 184140 }, { "epoch": 44.22, "learning_rate": 4.5916927604689064e-05, "loss": 0.0219, "step": 184150 }, { "epoch": 44.23, "learning_rate": 4.591245564311394e-05, "loss": 0.013, "step": 184160 }, { "epoch": 44.23, "learning_rate": 4.59079837144564e-05, "loss": 0.0175, "step": 184170 }, { "epoch": 44.23, "learning_rate": 4.590351181875241e-05, "loss": 0.0143, "step": 184180 }, { "epoch": 44.23, "learning_rate": 4.589903995603801e-05, "loss": 0.014, "step": 184190 }, { "epoch": 44.23, "learning_rate": 4.58945681263492e-05, "loss": 0.0112, "step": 184200 }, { "epoch": 44.24, "learning_rate": 4.589009632972201e-05, "loss": 0.0076, "step": 184210 }, { "epoch": 44.24, "learning_rate": 4.588562456619245e-05, "loss": 0.0096, "step": 184220 }, { "epoch": 44.24, "learning_rate": 4.58811528357965e-05, "loss": 0.0136, "step": 184230 }, { "epoch": 44.24, "learning_rate": 4.58766811385702e-05, "loss": 0.0147, "step": 184240 }, { "epoch": 44.25, "learning_rate": 4.587220947454956e-05, "loss": 0.0191, "step": 184250 }, { "epoch": 44.25, "learning_rate": 4.586773784377061e-05, "loss": 0.0054, "step": 184260 }, { "epoch": 44.25, "learning_rate": 4.586326624626931e-05, "loss": 0.0094, "step": 184270 }, { "epoch": 44.25, "learning_rate": 4.585879468208171e-05, "loss": 0.0085, "step": 184280 }, { "epoch": 44.26, "learning_rate": 4.585432315124379e-05, "loss": 0.0119, "step": 184290 }, { "epoch": 44.26, "learning_rate": 4.58498516537916e-05, "loss": 0.0103, "step": 184300 }, { "epoch": 44.26, "learning_rate": 4.584538018976113e-05, "loss": 0.0182, "step": 184310 }, { "epoch": 44.26, "learning_rate": 4.584090875918836e-05, "loss": 0.0056, "step": 184320 }, { "epoch": 44.26, "learning_rate": 4.5836437362109345e-05, "loss": 0.0144, "step": 184330 }, { "epoch": 44.27, "learning_rate": 4.583196599856007e-05, "loss": 0.0064, "step": 184340 }, { "epoch": 44.27, "learning_rate": 4.582749466857655e-05, "loss": 0.0122, "step": 184350 }, { "epoch": 44.27, "learning_rate": 4.58230233721948e-05, "loss": 0.0055, "step": 184360 }, { "epoch": 44.27, "learning_rate": 4.58185521094508e-05, "loss": 0.0057, "step": 184370 }, { "epoch": 44.28, "learning_rate": 4.581408088038059e-05, "loss": 0.007, "step": 184380 }, { "epoch": 44.28, "learning_rate": 4.5809609685020156e-05, "loss": 0.0175, "step": 184390 }, { "epoch": 44.28, "learning_rate": 4.580513852340552e-05, "loss": 0.0125, "step": 184400 }, { "epoch": 44.28, "learning_rate": 4.5800667395572694e-05, "loss": 0.0056, "step": 184410 }, { "epoch": 44.29, "learning_rate": 4.579619630155765e-05, "loss": 0.006, "step": 184420 }, { "epoch": 44.29, "learning_rate": 4.579172524139644e-05, "loss": 0.0098, "step": 184430 }, { "epoch": 44.29, "learning_rate": 4.5787254215125025e-05, "loss": 0.0136, "step": 184440 }, { "epoch": 44.29, "learning_rate": 4.5782783222779455e-05, "loss": 0.011, "step": 184450 }, { "epoch": 44.29, "learning_rate": 4.5778312264395705e-05, "loss": 0.0119, "step": 184460 }, { "epoch": 44.3, "learning_rate": 4.577384134000978e-05, "loss": 0.014, "step": 184470 }, { "epoch": 44.3, "learning_rate": 4.576937044965771e-05, "loss": 0.0297, "step": 184480 }, { "epoch": 44.3, "learning_rate": 4.5764899593375464e-05, "loss": 0.0129, "step": 184490 }, { "epoch": 44.3, "learning_rate": 4.5760428771199104e-05, "loss": 0.0035, "step": 184500 }, { "epoch": 44.31, "learning_rate": 4.575595798316457e-05, "loss": 0.0195, "step": 184510 }, { "epoch": 44.31, "learning_rate": 4.575148722930789e-05, "loss": 0.0109, "step": 184520 }, { "epoch": 44.31, "learning_rate": 4.574701650966506e-05, "loss": 0.0195, "step": 184530 }, { "epoch": 44.31, "learning_rate": 4.574254582427211e-05, "loss": 0.0074, "step": 184540 }, { "epoch": 44.31, "learning_rate": 4.573807517316504e-05, "loss": 0.0147, "step": 184550 }, { "epoch": 44.32, "learning_rate": 4.573360455637981e-05, "loss": 0.0168, "step": 184560 }, { "epoch": 44.32, "learning_rate": 4.5729133973952465e-05, "loss": 0.0141, "step": 184570 }, { "epoch": 44.32, "learning_rate": 4.572466342591898e-05, "loss": 0.0104, "step": 184580 }, { "epoch": 44.32, "learning_rate": 4.5720192912315404e-05, "loss": 0.0113, "step": 184590 }, { "epoch": 44.33, "learning_rate": 4.5715722433177684e-05, "loss": 0.0058, "step": 184600 }, { "epoch": 44.33, "learning_rate": 4.571125198854183e-05, "loss": 0.008, "step": 184610 }, { "epoch": 44.33, "learning_rate": 4.570678157844387e-05, "loss": 0.0087, "step": 184620 }, { "epoch": 44.33, "learning_rate": 4.570231120291978e-05, "loss": 0.0046, "step": 184630 }, { "epoch": 44.34, "learning_rate": 4.56978408620056e-05, "loss": 0.0223, "step": 184640 }, { "epoch": 44.34, "learning_rate": 4.569337055573728e-05, "loss": 0.0081, "step": 184650 }, { "epoch": 44.34, "learning_rate": 4.568890028415084e-05, "loss": 0.0042, "step": 184660 }, { "epoch": 44.34, "learning_rate": 4.568443004728228e-05, "loss": 0.0041, "step": 184670 }, { "epoch": 44.34, "learning_rate": 4.5679959845167595e-05, "loss": 0.0077, "step": 184680 }, { "epoch": 44.35, "learning_rate": 4.567548967784282e-05, "loss": 0.0076, "step": 184690 }, { "epoch": 44.35, "learning_rate": 4.56710195453439e-05, "loss": 0.0072, "step": 184700 }, { "epoch": 44.35, "learning_rate": 4.566654944770686e-05, "loss": 0.0228, "step": 184710 }, { "epoch": 44.35, "learning_rate": 4.566207938496769e-05, "loss": 0.0251, "step": 184720 }, { "epoch": 44.36, "learning_rate": 4.5657609357162406e-05, "loss": 0.0091, "step": 184730 }, { "epoch": 44.36, "learning_rate": 4.5653139364326995e-05, "loss": 0.0114, "step": 184740 }, { "epoch": 44.36, "learning_rate": 4.564866940649744e-05, "loss": 0.0135, "step": 184750 }, { "epoch": 44.36, "learning_rate": 4.564419948370976e-05, "loss": 0.0063, "step": 184760 }, { "epoch": 44.37, "learning_rate": 4.563972959599993e-05, "loss": 0.0075, "step": 184770 }, { "epoch": 44.37, "learning_rate": 4.5635259743403976e-05, "loss": 0.0142, "step": 184780 }, { "epoch": 44.37, "learning_rate": 4.563078992595788e-05, "loss": 0.0251, "step": 184790 }, { "epoch": 44.37, "learning_rate": 4.562632014369762e-05, "loss": 0.0286, "step": 184800 }, { "epoch": 44.37, "learning_rate": 4.562185039665921e-05, "loss": 0.0145, "step": 184810 }, { "epoch": 44.38, "learning_rate": 4.561738068487864e-05, "loss": 0.0052, "step": 184820 }, { "epoch": 44.38, "learning_rate": 4.561291100839193e-05, "loss": 0.0096, "step": 184830 }, { "epoch": 44.38, "learning_rate": 4.560844136723504e-05, "loss": 0.0114, "step": 184840 }, { "epoch": 44.38, "learning_rate": 4.560397176144397e-05, "loss": 0.0109, "step": 184850 }, { "epoch": 44.39, "learning_rate": 4.5599502191054734e-05, "loss": 0.016, "step": 184860 }, { "epoch": 44.39, "learning_rate": 4.55950326561033e-05, "loss": 0.0054, "step": 184870 }, { "epoch": 44.39, "learning_rate": 4.55905631566257e-05, "loss": 0.0123, "step": 184880 }, { "epoch": 44.39, "learning_rate": 4.558609369265789e-05, "loss": 0.0058, "step": 184890 }, { "epoch": 44.39, "learning_rate": 4.558162426423587e-05, "loss": 0.0121, "step": 184900 }, { "epoch": 44.4, "learning_rate": 4.557715487139564e-05, "loss": 0.0157, "step": 184910 }, { "epoch": 44.4, "learning_rate": 4.557268551417322e-05, "loss": 0.0066, "step": 184920 }, { "epoch": 44.4, "learning_rate": 4.556821619260455e-05, "loss": 0.0047, "step": 184930 }, { "epoch": 44.4, "learning_rate": 4.556374690672565e-05, "loss": 0.0054, "step": 184940 }, { "epoch": 44.41, "learning_rate": 4.55592776565725e-05, "loss": 0.0144, "step": 184950 }, { "epoch": 44.41, "learning_rate": 4.555480844218111e-05, "loss": 0.0108, "step": 184960 }, { "epoch": 44.41, "learning_rate": 4.555033926358747e-05, "loss": 0.0142, "step": 184970 }, { "epoch": 44.41, "learning_rate": 4.5545870120827554e-05, "loss": 0.0062, "step": 184980 }, { "epoch": 44.42, "learning_rate": 4.554140101393735e-05, "loss": 0.0112, "step": 184990 }, { "epoch": 44.42, "learning_rate": 4.553693194295287e-05, "loss": 0.0208, "step": 185000 }, { "epoch": 44.42, "learning_rate": 4.553246290791009e-05, "loss": 0.0132, "step": 185010 }, { "epoch": 44.42, "learning_rate": 4.552799390884501e-05, "loss": 0.0066, "step": 185020 }, { "epoch": 44.42, "learning_rate": 4.552352494579361e-05, "loss": 0.0066, "step": 185030 }, { "epoch": 44.43, "learning_rate": 4.5519056018791875e-05, "loss": 0.0135, "step": 185040 }, { "epoch": 44.43, "learning_rate": 4.55145871278758e-05, "loss": 0.0069, "step": 185050 }, { "epoch": 44.43, "learning_rate": 4.551011827308137e-05, "loss": 0.011, "step": 185060 }, { "epoch": 44.43, "learning_rate": 4.55056494544446e-05, "loss": 0.0082, "step": 185070 }, { "epoch": 44.44, "learning_rate": 4.5501180672001445e-05, "loss": 0.008, "step": 185080 }, { "epoch": 44.44, "learning_rate": 4.549671192578789e-05, "loss": 0.0212, "step": 185090 }, { "epoch": 44.44, "learning_rate": 4.549224321583995e-05, "loss": 0.0078, "step": 185100 }, { "epoch": 44.44, "learning_rate": 4.5487774542193607e-05, "loss": 0.0218, "step": 185110 }, { "epoch": 44.45, "learning_rate": 4.548330590488482e-05, "loss": 0.009, "step": 185120 }, { "epoch": 44.45, "learning_rate": 4.54788373039496e-05, "loss": 0.0131, "step": 185130 }, { "epoch": 44.45, "learning_rate": 4.547436873942392e-05, "loss": 0.0154, "step": 185140 }, { "epoch": 44.45, "learning_rate": 4.546990021134378e-05, "loss": 0.0106, "step": 185150 }, { "epoch": 44.45, "learning_rate": 4.5465431719745164e-05, "loss": 0.0068, "step": 185160 }, { "epoch": 44.46, "learning_rate": 4.5460963264664046e-05, "loss": 0.0135, "step": 185170 }, { "epoch": 44.46, "learning_rate": 4.545649484613641e-05, "loss": 0.015, "step": 185180 }, { "epoch": 44.46, "learning_rate": 4.545202646419826e-05, "loss": 0.0294, "step": 185190 }, { "epoch": 44.46, "learning_rate": 4.544755811888556e-05, "loss": 0.0104, "step": 185200 }, { "epoch": 44.47, "learning_rate": 4.544308981023432e-05, "loss": 0.0122, "step": 185210 }, { "epoch": 44.47, "learning_rate": 4.543862153828049e-05, "loss": 0.013, "step": 185220 }, { "epoch": 44.47, "learning_rate": 4.543415330306007e-05, "loss": 0.0133, "step": 185230 }, { "epoch": 44.47, "learning_rate": 4.542968510460905e-05, "loss": 0.0067, "step": 185240 }, { "epoch": 44.47, "learning_rate": 4.5425216942963424e-05, "loss": 0.023, "step": 185250 }, { "epoch": 44.48, "learning_rate": 4.5420748818159134e-05, "loss": 0.008, "step": 185260 }, { "epoch": 44.48, "learning_rate": 4.541628073023219e-05, "loss": 0.01, "step": 185270 }, { "epoch": 44.48, "learning_rate": 4.541181267921856e-05, "loss": 0.0123, "step": 185280 }, { "epoch": 44.48, "learning_rate": 4.540734466515425e-05, "loss": 0.0159, "step": 185290 }, { "epoch": 44.49, "learning_rate": 4.540287668807524e-05, "loss": 0.0157, "step": 185300 }, { "epoch": 44.49, "learning_rate": 4.5398408748017477e-05, "loss": 0.0245, "step": 185310 }, { "epoch": 44.49, "learning_rate": 4.539394084501697e-05, "loss": 0.0051, "step": 185320 }, { "epoch": 44.49, "learning_rate": 4.538947297910969e-05, "loss": 0.0132, "step": 185330 }, { "epoch": 44.5, "learning_rate": 4.5385005150331625e-05, "loss": 0.0068, "step": 185340 }, { "epoch": 44.5, "learning_rate": 4.538053735871876e-05, "loss": 0.0043, "step": 185350 }, { "epoch": 44.5, "learning_rate": 4.537606960430706e-05, "loss": 0.0073, "step": 185360 }, { "epoch": 44.5, "learning_rate": 4.53716018871325e-05, "loss": 0.0119, "step": 185370 }, { "epoch": 44.5, "learning_rate": 4.536713420723107e-05, "loss": 0.0098, "step": 185380 }, { "epoch": 44.51, "learning_rate": 4.536266656463875e-05, "loss": 0.0144, "step": 185390 }, { "epoch": 44.51, "learning_rate": 4.535819895939153e-05, "loss": 0.0135, "step": 185400 }, { "epoch": 44.51, "learning_rate": 4.5353731391525365e-05, "loss": 0.011, "step": 185410 }, { "epoch": 44.51, "learning_rate": 4.534926386107623e-05, "loss": 0.0206, "step": 185420 }, { "epoch": 44.52, "learning_rate": 4.534479636808013e-05, "loss": 0.012, "step": 185430 }, { "epoch": 44.52, "learning_rate": 4.534032891257303e-05, "loss": 0.0178, "step": 185440 }, { "epoch": 44.52, "learning_rate": 4.5335861494590894e-05, "loss": 0.0111, "step": 185450 }, { "epoch": 44.52, "learning_rate": 4.533139411416971e-05, "loss": 0.0143, "step": 185460 }, { "epoch": 44.53, "learning_rate": 4.532692677134545e-05, "loss": 0.0113, "step": 185470 }, { "epoch": 44.53, "learning_rate": 4.5322459466154106e-05, "loss": 0.0099, "step": 185480 }, { "epoch": 44.53, "learning_rate": 4.5317992198631646e-05, "loss": 0.0131, "step": 185490 }, { "epoch": 44.53, "learning_rate": 4.531352496881402e-05, "loss": 0.0136, "step": 185500 }, { "epoch": 44.53, "learning_rate": 4.530905777673725e-05, "loss": 0.0128, "step": 185510 }, { "epoch": 44.54, "learning_rate": 4.530459062243726e-05, "loss": 0.0118, "step": 185520 }, { "epoch": 44.54, "learning_rate": 4.530012350595006e-05, "loss": 0.0108, "step": 185530 }, { "epoch": 44.54, "learning_rate": 4.529565642731163e-05, "loss": 0.0124, "step": 185540 }, { "epoch": 44.54, "learning_rate": 4.529118938655792e-05, "loss": 0.0185, "step": 185550 }, { "epoch": 44.55, "learning_rate": 4.528672238372489e-05, "loss": 0.0283, "step": 185560 }, { "epoch": 44.55, "learning_rate": 4.528225541884856e-05, "loss": 0.0211, "step": 185570 }, { "epoch": 44.55, "learning_rate": 4.527778849196488e-05, "loss": 0.014, "step": 185580 }, { "epoch": 44.55, "learning_rate": 4.52733216031098e-05, "loss": 0.0067, "step": 185590 }, { "epoch": 44.55, "learning_rate": 4.5268854752319326e-05, "loss": 0.0257, "step": 185600 }, { "epoch": 44.56, "learning_rate": 4.526438793962941e-05, "loss": 0.0142, "step": 185610 }, { "epoch": 44.56, "learning_rate": 4.525992116507604e-05, "loss": 0.0104, "step": 185620 }, { "epoch": 44.56, "learning_rate": 4.5255454428695194e-05, "loss": 0.012, "step": 185630 }, { "epoch": 44.56, "learning_rate": 4.52509877305228e-05, "loss": 0.0223, "step": 185640 }, { "epoch": 44.57, "learning_rate": 4.524652107059487e-05, "loss": 0.0206, "step": 185650 }, { "epoch": 44.57, "learning_rate": 4.5242054448947356e-05, "loss": 0.0136, "step": 185660 }, { "epoch": 44.57, "learning_rate": 4.523758786561624e-05, "loss": 0.0083, "step": 185670 }, { "epoch": 44.57, "learning_rate": 4.52331213206375e-05, "loss": 0.0361, "step": 185680 }, { "epoch": 44.58, "learning_rate": 4.5228654814047076e-05, "loss": 0.0152, "step": 185690 }, { "epoch": 44.58, "learning_rate": 4.522418834588095e-05, "loss": 0.0186, "step": 185700 }, { "epoch": 44.58, "learning_rate": 4.5219721916175096e-05, "loss": 0.0131, "step": 185710 }, { "epoch": 44.58, "learning_rate": 4.5215255524965485e-05, "loss": 0.0149, "step": 185720 }, { "epoch": 44.58, "learning_rate": 4.52107891722881e-05, "loss": 0.011, "step": 185730 }, { "epoch": 44.59, "learning_rate": 4.5206322858178865e-05, "loss": 0.0141, "step": 185740 }, { "epoch": 44.59, "learning_rate": 4.5201856582673786e-05, "loss": 0.0126, "step": 185750 }, { "epoch": 44.59, "learning_rate": 4.5197390345808805e-05, "loss": 0.0221, "step": 185760 }, { "epoch": 44.59, "learning_rate": 4.519292414761994e-05, "loss": 0.01, "step": 185770 }, { "epoch": 44.6, "learning_rate": 4.518845798814308e-05, "loss": 0.0257, "step": 185780 }, { "epoch": 44.6, "learning_rate": 4.518399186741425e-05, "loss": 0.0091, "step": 185790 }, { "epoch": 44.6, "learning_rate": 4.5179525785469385e-05, "loss": 0.0118, "step": 185800 }, { "epoch": 44.6, "learning_rate": 4.5175059742344474e-05, "loss": 0.0065, "step": 185810 }, { "epoch": 44.61, "learning_rate": 4.5170593738075486e-05, "loss": 0.0145, "step": 185820 }, { "epoch": 44.61, "learning_rate": 4.516612777269835e-05, "loss": 0.0239, "step": 185830 }, { "epoch": 44.61, "learning_rate": 4.516166184624907e-05, "loss": 0.0152, "step": 185840 }, { "epoch": 44.61, "learning_rate": 4.5157195958763574e-05, "loss": 0.0099, "step": 185850 }, { "epoch": 44.61, "learning_rate": 4.515273011027786e-05, "loss": 0.0149, "step": 185860 }, { "epoch": 44.62, "learning_rate": 4.51482643008279e-05, "loss": 0.022, "step": 185870 }, { "epoch": 44.62, "learning_rate": 4.5143798530449614e-05, "loss": 0.0186, "step": 185880 }, { "epoch": 44.62, "learning_rate": 4.5139332799179e-05, "loss": 0.0085, "step": 185890 }, { "epoch": 44.62, "learning_rate": 4.513486710705199e-05, "loss": 0.0117, "step": 185900 }, { "epoch": 44.63, "learning_rate": 4.5130401454104595e-05, "loss": 0.0067, "step": 185910 }, { "epoch": 44.63, "learning_rate": 4.512593584037274e-05, "loss": 0.0071, "step": 185920 }, { "epoch": 44.63, "learning_rate": 4.512147026589238e-05, "loss": 0.0178, "step": 185930 }, { "epoch": 44.63, "learning_rate": 4.511700473069951e-05, "loss": 0.0169, "step": 185940 }, { "epoch": 44.63, "learning_rate": 4.511253923483006e-05, "loss": 0.0154, "step": 185950 }, { "epoch": 44.64, "learning_rate": 4.510807377832003e-05, "loss": 0.0095, "step": 185960 }, { "epoch": 44.64, "learning_rate": 4.5103608361205343e-05, "loss": 0.0136, "step": 185970 }, { "epoch": 44.64, "learning_rate": 4.509914298352197e-05, "loss": 0.0156, "step": 185980 }, { "epoch": 44.64, "learning_rate": 4.509467764530588e-05, "loss": 0.0056, "step": 185990 }, { "epoch": 44.65, "learning_rate": 4.509021234659303e-05, "loss": 0.0099, "step": 186000 }, { "epoch": 44.65, "learning_rate": 4.5085747087419394e-05, "loss": 0.0131, "step": 186010 }, { "epoch": 44.65, "learning_rate": 4.5081281867820884e-05, "loss": 0.0128, "step": 186020 }, { "epoch": 44.65, "learning_rate": 4.5076816687833503e-05, "loss": 0.0089, "step": 186030 }, { "epoch": 44.66, "learning_rate": 4.5072351547493195e-05, "loss": 0.02, "step": 186040 }, { "epoch": 44.66, "learning_rate": 4.5067886446835925e-05, "loss": 0.0092, "step": 186050 }, { "epoch": 44.66, "learning_rate": 4.506342138589766e-05, "loss": 0.0117, "step": 186060 }, { "epoch": 44.66, "learning_rate": 4.505895636471432e-05, "loss": 0.0274, "step": 186070 }, { "epoch": 44.66, "learning_rate": 4.5054491383321896e-05, "loss": 0.0053, "step": 186080 }, { "epoch": 44.67, "learning_rate": 4.505002644175632e-05, "loss": 0.0098, "step": 186090 }, { "epoch": 44.67, "learning_rate": 4.504556154005359e-05, "loss": 0.0104, "step": 186100 }, { "epoch": 44.67, "learning_rate": 4.504109667824963e-05, "loss": 0.0033, "step": 186110 }, { "epoch": 44.67, "learning_rate": 4.503663185638039e-05, "loss": 0.0086, "step": 186120 }, { "epoch": 44.68, "learning_rate": 4.503216707448185e-05, "loss": 0.0052, "step": 186130 }, { "epoch": 44.68, "learning_rate": 4.502770233258994e-05, "loss": 0.0074, "step": 186140 }, { "epoch": 44.68, "learning_rate": 4.502323763074066e-05, "loss": 0.0133, "step": 186150 }, { "epoch": 44.68, "learning_rate": 4.501877296896992e-05, "loss": 0.0219, "step": 186160 }, { "epoch": 44.69, "learning_rate": 4.501430834731368e-05, "loss": 0.0096, "step": 186170 }, { "epoch": 44.69, "learning_rate": 4.500984376580791e-05, "loss": 0.0091, "step": 186180 }, { "epoch": 44.69, "learning_rate": 4.500537922448854e-05, "loss": 0.0208, "step": 186190 }, { "epoch": 44.69, "learning_rate": 4.5000914723391585e-05, "loss": 0.0165, "step": 186200 }, { "epoch": 44.69, "learning_rate": 4.499645026255291e-05, "loss": 0.0099, "step": 186210 }, { "epoch": 44.7, "learning_rate": 4.4991985842008535e-05, "loss": 0.0041, "step": 186220 }, { "epoch": 44.7, "learning_rate": 4.498752146179437e-05, "loss": 0.0112, "step": 186230 }, { "epoch": 44.7, "learning_rate": 4.4983057121946414e-05, "loss": 0.014, "step": 186240 }, { "epoch": 44.7, "learning_rate": 4.497859282250058e-05, "loss": 0.006, "step": 186250 }, { "epoch": 44.71, "learning_rate": 4.497412856349281e-05, "loss": 0.0256, "step": 186260 }, { "epoch": 44.71, "learning_rate": 4.49696643449591e-05, "loss": 0.0119, "step": 186270 }, { "epoch": 44.71, "learning_rate": 4.496520016693536e-05, "loss": 0.0063, "step": 186280 }, { "epoch": 44.71, "learning_rate": 4.4960736029457586e-05, "loss": 0.0153, "step": 186290 }, { "epoch": 44.71, "learning_rate": 4.495627193256168e-05, "loss": 0.0088, "step": 186300 }, { "epoch": 44.72, "learning_rate": 4.495180787628361e-05, "loss": 0.0082, "step": 186310 }, { "epoch": 44.72, "learning_rate": 4.4947343860659336e-05, "loss": 0.0154, "step": 186320 }, { "epoch": 44.72, "learning_rate": 4.4942879885724784e-05, "loss": 0.0119, "step": 186330 }, { "epoch": 44.72, "learning_rate": 4.493841595151595e-05, "loss": 0.0246, "step": 186340 }, { "epoch": 44.73, "learning_rate": 4.493395205806873e-05, "loss": 0.0185, "step": 186350 }, { "epoch": 44.73, "learning_rate": 4.492948820541909e-05, "loss": 0.0123, "step": 186360 }, { "epoch": 44.73, "learning_rate": 4.4925024393603e-05, "loss": 0.0039, "step": 186370 }, { "epoch": 44.73, "learning_rate": 4.492056062265636e-05, "loss": 0.0059, "step": 186380 }, { "epoch": 44.74, "learning_rate": 4.4916096892615176e-05, "loss": 0.011, "step": 186390 }, { "epoch": 44.74, "learning_rate": 4.4911633203515355e-05, "loss": 0.0118, "step": 186400 }, { "epoch": 44.74, "learning_rate": 4.490716955539285e-05, "loss": 0.0111, "step": 186410 }, { "epoch": 44.74, "learning_rate": 4.490270594828361e-05, "loss": 0.0171, "step": 186420 }, { "epoch": 44.74, "learning_rate": 4.48982423822236e-05, "loss": 0.0077, "step": 186430 }, { "epoch": 44.75, "learning_rate": 4.489377885724874e-05, "loss": 0.0224, "step": 186440 }, { "epoch": 44.75, "learning_rate": 4.488931537339498e-05, "loss": 0.0157, "step": 186450 }, { "epoch": 44.75, "learning_rate": 4.488485193069826e-05, "loss": 0.0075, "step": 186460 }, { "epoch": 44.75, "learning_rate": 4.488038852919454e-05, "loss": 0.0122, "step": 186470 }, { "epoch": 44.76, "learning_rate": 4.4875925168919766e-05, "loss": 0.0105, "step": 186480 }, { "epoch": 44.76, "learning_rate": 4.4871461849909877e-05, "loss": 0.0043, "step": 186490 }, { "epoch": 44.76, "learning_rate": 4.486699857220079e-05, "loss": 0.0078, "step": 186500 }, { "epoch": 44.76, "learning_rate": 4.4862535335828494e-05, "loss": 0.0174, "step": 186510 }, { "epoch": 44.77, "learning_rate": 4.48580721408289e-05, "loss": 0.0185, "step": 186520 }, { "epoch": 44.77, "learning_rate": 4.485360898723797e-05, "loss": 0.0079, "step": 186530 }, { "epoch": 44.77, "learning_rate": 4.484914587509163e-05, "loss": 0.0169, "step": 186540 }, { "epoch": 44.77, "learning_rate": 4.4844682804425826e-05, "loss": 0.0125, "step": 186550 }, { "epoch": 44.77, "learning_rate": 4.484021977527651e-05, "loss": 0.006, "step": 186560 }, { "epoch": 44.78, "learning_rate": 4.483575678767963e-05, "loss": 0.0244, "step": 186570 }, { "epoch": 44.78, "learning_rate": 4.4831293841671086e-05, "loss": 0.0091, "step": 186580 }, { "epoch": 44.78, "learning_rate": 4.4826830937286854e-05, "loss": 0.0065, "step": 186590 }, { "epoch": 44.78, "learning_rate": 4.482236807456287e-05, "loss": 0.0146, "step": 186600 }, { "epoch": 44.79, "learning_rate": 4.481790525353507e-05, "loss": 0.0122, "step": 186610 }, { "epoch": 44.79, "learning_rate": 4.481344247423941e-05, "loss": 0.0121, "step": 186620 }, { "epoch": 44.79, "learning_rate": 4.4808979736711805e-05, "loss": 0.0098, "step": 186630 }, { "epoch": 44.79, "learning_rate": 4.480451704098819e-05, "loss": 0.0086, "step": 186640 }, { "epoch": 44.79, "learning_rate": 4.4800054387104525e-05, "loss": 0.01, "step": 186650 }, { "epoch": 44.8, "learning_rate": 4.4795591775096727e-05, "loss": 0.007, "step": 186660 }, { "epoch": 44.8, "learning_rate": 4.479112920500077e-05, "loss": 0.0066, "step": 186670 }, { "epoch": 44.8, "learning_rate": 4.478666667685256e-05, "loss": 0.0183, "step": 186680 }, { "epoch": 44.8, "learning_rate": 4.478220419068804e-05, "loss": 0.0085, "step": 186690 }, { "epoch": 44.81, "learning_rate": 4.477774174654314e-05, "loss": 0.013, "step": 186700 }, { "epoch": 44.81, "learning_rate": 4.477327934445382e-05, "loss": 0.0158, "step": 186710 }, { "epoch": 44.81, "learning_rate": 4.476881698445601e-05, "loss": 0.0076, "step": 186720 }, { "epoch": 44.81, "learning_rate": 4.476435466658563e-05, "loss": 0.0069, "step": 186730 }, { "epoch": 44.82, "learning_rate": 4.475989239087862e-05, "loss": 0.011, "step": 186740 }, { "epoch": 44.82, "learning_rate": 4.4755430157370926e-05, "loss": 0.0124, "step": 186750 }, { "epoch": 44.82, "learning_rate": 4.475096796609849e-05, "loss": 0.0228, "step": 186760 }, { "epoch": 44.82, "learning_rate": 4.474650581709721e-05, "loss": 0.0129, "step": 186770 }, { "epoch": 44.82, "learning_rate": 4.474204371040305e-05, "loss": 0.0069, "step": 186780 }, { "epoch": 44.83, "learning_rate": 4.473758164605193e-05, "loss": 0.0157, "step": 186790 }, { "epoch": 44.83, "learning_rate": 4.473311962407981e-05, "loss": 0.0118, "step": 186800 }, { "epoch": 44.83, "learning_rate": 4.472865764452261e-05, "loss": 0.0112, "step": 186810 }, { "epoch": 44.83, "learning_rate": 4.4724195707416236e-05, "loss": 0.0123, "step": 186820 }, { "epoch": 44.84, "learning_rate": 4.471973381279665e-05, "loss": 0.0096, "step": 186830 }, { "epoch": 44.84, "learning_rate": 4.471527196069977e-05, "loss": 0.0116, "step": 186840 }, { "epoch": 44.84, "learning_rate": 4.471081015116154e-05, "loss": 0.0125, "step": 186850 }, { "epoch": 44.84, "learning_rate": 4.4706348384217906e-05, "loss": 0.0093, "step": 186860 }, { "epoch": 44.85, "learning_rate": 4.470188665990476e-05, "loss": 0.0079, "step": 186870 }, { "epoch": 44.85, "learning_rate": 4.4697424978258045e-05, "loss": 0.015, "step": 186880 }, { "epoch": 44.85, "learning_rate": 4.469296333931371e-05, "loss": 0.0073, "step": 186890 }, { "epoch": 44.85, "learning_rate": 4.468850174310768e-05, "loss": 0.0126, "step": 186900 }, { "epoch": 44.85, "learning_rate": 4.468404018967587e-05, "loss": 0.0203, "step": 186910 }, { "epoch": 44.86, "learning_rate": 4.4679578679054216e-05, "loss": 0.01, "step": 186920 }, { "epoch": 44.86, "learning_rate": 4.467511721127864e-05, "loss": 0.0106, "step": 186930 }, { "epoch": 44.86, "learning_rate": 4.467065578638509e-05, "loss": 0.0084, "step": 186940 }, { "epoch": 44.86, "learning_rate": 4.466619440440951e-05, "loss": 0.0083, "step": 186950 }, { "epoch": 44.87, "learning_rate": 4.466173306538777e-05, "loss": 0.0311, "step": 186960 }, { "epoch": 44.87, "learning_rate": 4.465727176935584e-05, "loss": 0.0105, "step": 186970 }, { "epoch": 44.87, "learning_rate": 4.465281051634963e-05, "loss": 0.0087, "step": 186980 }, { "epoch": 44.87, "learning_rate": 4.4648349306405087e-05, "loss": 0.0142, "step": 186990 }, { "epoch": 44.87, "learning_rate": 4.464388813955814e-05, "loss": 0.0067, "step": 187000 }, { "epoch": 44.88, "learning_rate": 4.463942701584467e-05, "loss": 0.0102, "step": 187010 }, { "epoch": 44.88, "learning_rate": 4.463496593530065e-05, "loss": 0.0122, "step": 187020 }, { "epoch": 44.88, "learning_rate": 4.463050489796198e-05, "loss": 0.0137, "step": 187030 }, { "epoch": 44.88, "learning_rate": 4.46260439038646e-05, "loss": 0.0096, "step": 187040 }, { "epoch": 44.89, "learning_rate": 4.462158295304445e-05, "loss": 0.0213, "step": 187050 }, { "epoch": 44.89, "learning_rate": 4.461712204553742e-05, "loss": 0.0118, "step": 187060 }, { "epoch": 44.89, "learning_rate": 4.461266118137944e-05, "loss": 0.0172, "step": 187070 }, { "epoch": 44.89, "learning_rate": 4.460820036060645e-05, "loss": 0.0072, "step": 187080 }, { "epoch": 44.9, "learning_rate": 4.4603739583254387e-05, "loss": 0.0041, "step": 187090 }, { "epoch": 44.9, "learning_rate": 4.459927884935913e-05, "loss": 0.0203, "step": 187100 }, { "epoch": 44.9, "learning_rate": 4.4594818158956633e-05, "loss": 0.0124, "step": 187110 }, { "epoch": 44.9, "learning_rate": 4.4590357512082796e-05, "loss": 0.0248, "step": 187120 }, { "epoch": 44.9, "learning_rate": 4.458589690877357e-05, "loss": 0.0109, "step": 187130 }, { "epoch": 44.91, "learning_rate": 4.458143634906488e-05, "loss": 0.0078, "step": 187140 }, { "epoch": 44.91, "learning_rate": 4.4576975832992606e-05, "loss": 0.011, "step": 187150 }, { "epoch": 44.91, "learning_rate": 4.457251536059271e-05, "loss": 0.0135, "step": 187160 }, { "epoch": 44.91, "learning_rate": 4.456805493190108e-05, "loss": 0.0116, "step": 187170 }, { "epoch": 44.92, "learning_rate": 4.456359454695367e-05, "loss": 0.0051, "step": 187180 }, { "epoch": 44.92, "learning_rate": 4.455913420578639e-05, "loss": 0.0047, "step": 187190 }, { "epoch": 44.92, "learning_rate": 4.4554673908435126e-05, "loss": 0.0255, "step": 187200 }, { "epoch": 44.92, "learning_rate": 4.4550213654935844e-05, "loss": 0.0105, "step": 187210 }, { "epoch": 44.93, "learning_rate": 4.4545753445324436e-05, "loss": 0.0162, "step": 187220 }, { "epoch": 44.93, "learning_rate": 4.454129327963684e-05, "loss": 0.0121, "step": 187230 }, { "epoch": 44.93, "learning_rate": 4.4536833157908965e-05, "loss": 0.0043, "step": 187240 }, { "epoch": 44.93, "learning_rate": 4.4532373080176703e-05, "loss": 0.012, "step": 187250 }, { "epoch": 44.93, "learning_rate": 4.452791304647601e-05, "loss": 0.01, "step": 187260 }, { "epoch": 44.94, "learning_rate": 4.452345305684278e-05, "loss": 0.007, "step": 187270 }, { "epoch": 44.94, "learning_rate": 4.4518993111312976e-05, "loss": 0.0107, "step": 187280 }, { "epoch": 44.94, "learning_rate": 4.451453320992244e-05, "loss": 0.0123, "step": 187290 }, { "epoch": 44.94, "learning_rate": 4.4510073352707134e-05, "loss": 0.009, "step": 187300 }, { "epoch": 44.95, "learning_rate": 4.450561353970296e-05, "loss": 0.0094, "step": 187310 }, { "epoch": 44.95, "learning_rate": 4.450115377094584e-05, "loss": 0.0082, "step": 187320 }, { "epoch": 44.95, "learning_rate": 4.4496694046471704e-05, "loss": 0.016, "step": 187330 }, { "epoch": 45.0, "learning_rate": 4.4492234366316434e-05, "loss": 0.0085, "step": 187340 }, { "epoch": 45.0, "learning_rate": 4.448777473051596e-05, "loss": 0.0216, "step": 187350 }, { "epoch": 45.01, "learning_rate": 4.44833151391062e-05, "loss": 0.0161, "step": 187360 }, { "epoch": 45.01, "learning_rate": 4.4478855592123066e-05, "loss": 0.0066, "step": 187370 }, { "epoch": 45.01, "learning_rate": 4.4474396089602484e-05, "loss": 0.0111, "step": 187380 }, { "epoch": 45.01, "learning_rate": 4.446993663158034e-05, "loss": 0.0105, "step": 187390 }, { "epoch": 45.01, "learning_rate": 4.446547721809255e-05, "loss": 0.0088, "step": 187400 }, { "epoch": 45.02, "learning_rate": 4.446101784917504e-05, "loss": 0.0078, "step": 187410 }, { "epoch": 45.02, "learning_rate": 4.445655852486374e-05, "loss": 0.0157, "step": 187420 }, { "epoch": 45.02, "learning_rate": 4.445209924519452e-05, "loss": 0.0181, "step": 187430 }, { "epoch": 45.02, "learning_rate": 4.444764001020331e-05, "loss": 0.0193, "step": 187440 }, { "epoch": 45.03, "learning_rate": 4.444318081992603e-05, "loss": 0.0106, "step": 187450 }, { "epoch": 45.03, "learning_rate": 4.443872167439856e-05, "loss": 0.0112, "step": 187460 }, { "epoch": 45.03, "learning_rate": 4.4434262573656884e-05, "loss": 0.0061, "step": 187470 }, { "epoch": 45.03, "learning_rate": 4.4429803517736815e-05, "loss": 0.0171, "step": 187480 }, { "epoch": 45.04, "learning_rate": 4.442534450667432e-05, "loss": 0.0214, "step": 187490 }, { "epoch": 45.04, "learning_rate": 4.442088554050529e-05, "loss": 0.0087, "step": 187500 }, { "epoch": 45.04, "learning_rate": 4.441642661926564e-05, "loss": 0.0153, "step": 187510 }, { "epoch": 45.04, "learning_rate": 4.441196774299129e-05, "loss": 0.0151, "step": 187520 }, { "epoch": 45.04, "learning_rate": 4.440750891171812e-05, "loss": 0.0058, "step": 187530 }, { "epoch": 45.05, "learning_rate": 4.440305012548206e-05, "loss": 0.0181, "step": 187540 }, { "epoch": 45.05, "learning_rate": 4.4398591384319e-05, "loss": 0.0094, "step": 187550 }, { "epoch": 45.05, "learning_rate": 4.439413268826488e-05, "loss": 0.0072, "step": 187560 }, { "epoch": 45.05, "learning_rate": 4.4389674037355564e-05, "loss": 0.0192, "step": 187570 }, { "epoch": 45.06, "learning_rate": 4.4385215431626974e-05, "loss": 0.0248, "step": 187580 }, { "epoch": 45.06, "learning_rate": 4.438075687111503e-05, "loss": 0.0227, "step": 187590 }, { "epoch": 45.06, "learning_rate": 4.4376298355855616e-05, "loss": 0.006, "step": 187600 }, { "epoch": 45.06, "learning_rate": 4.437183988588467e-05, "loss": 0.0062, "step": 187610 }, { "epoch": 45.07, "learning_rate": 4.436738146123806e-05, "loss": 0.011, "step": 187620 }, { "epoch": 45.07, "learning_rate": 4.4362923081951696e-05, "loss": 0.0155, "step": 187630 }, { "epoch": 45.07, "learning_rate": 4.43584647480615e-05, "loss": 0.0072, "step": 187640 }, { "epoch": 45.07, "learning_rate": 4.4354006459603356e-05, "loss": 0.0045, "step": 187650 }, { "epoch": 45.07, "learning_rate": 4.4349548216613203e-05, "loss": 0.012, "step": 187660 }, { "epoch": 45.08, "learning_rate": 4.43450900191269e-05, "loss": 0.0082, "step": 187670 }, { "epoch": 45.08, "learning_rate": 4.434063186718036e-05, "loss": 0.0175, "step": 187680 }, { "epoch": 45.08, "learning_rate": 4.433617376080951e-05, "loss": 0.0094, "step": 187690 }, { "epoch": 45.08, "learning_rate": 4.433171570005022e-05, "loss": 0.0108, "step": 187700 }, { "epoch": 45.09, "learning_rate": 4.4327257684938435e-05, "loss": 0.007, "step": 187710 }, { "epoch": 45.09, "learning_rate": 4.432279971551e-05, "loss": 0.0088, "step": 187720 }, { "epoch": 45.09, "learning_rate": 4.431834179180085e-05, "loss": 0.0105, "step": 187730 }, { "epoch": 45.09, "learning_rate": 4.431388391384687e-05, "loss": 0.0093, "step": 187740 }, { "epoch": 45.09, "learning_rate": 4.430942608168398e-05, "loss": 0.0059, "step": 187750 }, { "epoch": 45.1, "learning_rate": 4.4304968295348065e-05, "loss": 0.0075, "step": 187760 }, { "epoch": 45.1, "learning_rate": 4.430051055487502e-05, "loss": 0.0306, "step": 187770 }, { "epoch": 45.1, "learning_rate": 4.429605286030075e-05, "loss": 0.0055, "step": 187780 }, { "epoch": 45.1, "learning_rate": 4.4291595211661154e-05, "loss": 0.0159, "step": 187790 }, { "epoch": 45.11, "learning_rate": 4.428713760899214e-05, "loss": 0.0113, "step": 187800 }, { "epoch": 45.11, "learning_rate": 4.4282680052329595e-05, "loss": 0.0063, "step": 187810 }, { "epoch": 45.11, "learning_rate": 4.4278222541709404e-05, "loss": 0.0036, "step": 187820 }, { "epoch": 45.11, "learning_rate": 4.427376507716749e-05, "loss": 0.0086, "step": 187830 }, { "epoch": 45.12, "learning_rate": 4.426930765873971e-05, "loss": 0.0046, "step": 187840 }, { "epoch": 45.12, "learning_rate": 4.426485028646202e-05, "loss": 0.0104, "step": 187850 }, { "epoch": 45.12, "learning_rate": 4.426039296037027e-05, "loss": 0.0211, "step": 187860 }, { "epoch": 45.12, "learning_rate": 4.425593568050036e-05, "loss": 0.0095, "step": 187870 }, { "epoch": 45.12, "learning_rate": 4.42514784468882e-05, "loss": 0.0121, "step": 187880 }, { "epoch": 45.13, "learning_rate": 4.424702125956969e-05, "loss": 0.0073, "step": 187890 }, { "epoch": 45.13, "learning_rate": 4.424256411858069e-05, "loss": 0.0211, "step": 187900 }, { "epoch": 45.13, "learning_rate": 4.423810702395713e-05, "loss": 0.0092, "step": 187910 }, { "epoch": 45.13, "learning_rate": 4.4233649975734884e-05, "loss": 0.0146, "step": 187920 }, { "epoch": 45.14, "learning_rate": 4.422919297394985e-05, "loss": 0.0065, "step": 187930 }, { "epoch": 45.14, "learning_rate": 4.422473601863794e-05, "loss": 0.0223, "step": 187940 }, { "epoch": 45.14, "learning_rate": 4.4220279109835e-05, "loss": 0.0141, "step": 187950 }, { "epoch": 45.14, "learning_rate": 4.421582224757696e-05, "loss": 0.0103, "step": 187960 }, { "epoch": 45.15, "learning_rate": 4.421136543189971e-05, "loss": 0.0071, "step": 187970 }, { "epoch": 45.15, "learning_rate": 4.4206908662839115e-05, "loss": 0.0116, "step": 187980 }, { "epoch": 45.15, "learning_rate": 4.420245194043111e-05, "loss": 0.0083, "step": 187990 }, { "epoch": 45.15, "learning_rate": 4.419799526471155e-05, "loss": 0.0068, "step": 188000 }, { "epoch": 45.15, "learning_rate": 4.4193538635716327e-05, "loss": 0.0366, "step": 188010 }, { "epoch": 45.16, "learning_rate": 4.418908205348134e-05, "loss": 0.0187, "step": 188020 }, { "epoch": 45.16, "learning_rate": 4.418462551804247e-05, "loss": 0.007, "step": 188030 }, { "epoch": 45.16, "learning_rate": 4.4180169029435645e-05, "loss": 0.0081, "step": 188040 }, { "epoch": 45.16, "learning_rate": 4.41757125876967e-05, "loss": 0.0061, "step": 188050 }, { "epoch": 45.17, "learning_rate": 4.4171256192861536e-05, "loss": 0.0043, "step": 188060 }, { "epoch": 45.17, "learning_rate": 4.416679984496607e-05, "loss": 0.0138, "step": 188070 }, { "epoch": 45.17, "learning_rate": 4.416234354404617e-05, "loss": 0.0167, "step": 188080 }, { "epoch": 45.17, "learning_rate": 4.415788729013771e-05, "loss": 0.0061, "step": 188090 }, { "epoch": 45.17, "learning_rate": 4.4153431083276594e-05, "loss": 0.0052, "step": 188100 }, { "epoch": 45.18, "learning_rate": 4.414897492349871e-05, "loss": 0.0041, "step": 188110 }, { "epoch": 45.18, "learning_rate": 4.414451881083993e-05, "loss": 0.01, "step": 188120 }, { "epoch": 45.18, "learning_rate": 4.414006274533617e-05, "loss": 0.0154, "step": 188130 }, { "epoch": 45.18, "learning_rate": 4.4135606727023274e-05, "loss": 0.0159, "step": 188140 }, { "epoch": 45.19, "learning_rate": 4.413115075593715e-05, "loss": 0.0049, "step": 188150 }, { "epoch": 45.19, "learning_rate": 4.412669483211368e-05, "loss": 0.0074, "step": 188160 }, { "epoch": 45.19, "learning_rate": 4.412223895558874e-05, "loss": 0.0125, "step": 188170 }, { "epoch": 45.19, "learning_rate": 4.411778312639824e-05, "loss": 0.0079, "step": 188180 }, { "epoch": 45.2, "learning_rate": 4.4113327344578035e-05, "loss": 0.0114, "step": 188190 }, { "epoch": 45.2, "learning_rate": 4.4108871610164e-05, "loss": 0.0081, "step": 188200 }, { "epoch": 45.2, "learning_rate": 4.4104415923192056e-05, "loss": 0.0351, "step": 188210 }, { "epoch": 45.2, "learning_rate": 4.409996028369807e-05, "loss": 0.0129, "step": 188220 }, { "epoch": 45.2, "learning_rate": 4.40955046917179e-05, "loss": 0.0068, "step": 188230 }, { "epoch": 45.21, "learning_rate": 4.409104914728746e-05, "loss": 0.008, "step": 188240 }, { "epoch": 45.21, "learning_rate": 4.408659365044259e-05, "loss": 0.0123, "step": 188250 }, { "epoch": 45.21, "learning_rate": 4.408213820121922e-05, "loss": 0.0081, "step": 188260 }, { "epoch": 45.21, "learning_rate": 4.407768279965323e-05, "loss": 0.0116, "step": 188270 }, { "epoch": 45.22, "learning_rate": 4.407322744578044e-05, "loss": 0.0087, "step": 188280 }, { "epoch": 45.22, "learning_rate": 4.406877213963678e-05, "loss": 0.0141, "step": 188290 }, { "epoch": 45.22, "learning_rate": 4.406431688125811e-05, "loss": 0.0152, "step": 188300 }, { "epoch": 45.22, "learning_rate": 4.405986167068033e-05, "loss": 0.0079, "step": 188310 }, { "epoch": 45.23, "learning_rate": 4.4055406507939314e-05, "loss": 0.0058, "step": 188320 }, { "epoch": 45.23, "learning_rate": 4.40509513930709e-05, "loss": 0.0176, "step": 188330 }, { "epoch": 45.23, "learning_rate": 4.4046496326111013e-05, "loss": 0.0113, "step": 188340 }, { "epoch": 45.23, "learning_rate": 4.404204130709551e-05, "loss": 0.0079, "step": 188350 }, { "epoch": 45.23, "learning_rate": 4.403758633606026e-05, "loss": 0.0054, "step": 188360 }, { "epoch": 45.24, "learning_rate": 4.403313141304118e-05, "loss": 0.008, "step": 188370 }, { "epoch": 45.24, "learning_rate": 4.40286765380741e-05, "loss": 0.0118, "step": 188380 }, { "epoch": 45.24, "learning_rate": 4.40242217111949e-05, "loss": 0.0056, "step": 188390 }, { "epoch": 45.24, "learning_rate": 4.401976693243948e-05, "loss": 0.0036, "step": 188400 }, { "epoch": 45.25, "learning_rate": 4.4015312201843714e-05, "loss": 0.0118, "step": 188410 }, { "epoch": 45.25, "learning_rate": 4.401085751944344e-05, "loss": 0.0229, "step": 188420 }, { "epoch": 45.25, "learning_rate": 4.400640288527457e-05, "loss": 0.0144, "step": 188430 }, { "epoch": 45.25, "learning_rate": 4.400194829937296e-05, "loss": 0.0117, "step": 188440 }, { "epoch": 45.25, "learning_rate": 4.399749376177449e-05, "loss": 0.0149, "step": 188450 }, { "epoch": 45.26, "learning_rate": 4.399303927251505e-05, "loss": 0.0132, "step": 188460 }, { "epoch": 45.26, "learning_rate": 4.3988584831630463e-05, "loss": 0.0085, "step": 188470 }, { "epoch": 45.26, "learning_rate": 4.398413043915665e-05, "loss": 0.0166, "step": 188480 }, { "epoch": 45.26, "learning_rate": 4.397967609512945e-05, "loss": 0.0199, "step": 188490 }, { "epoch": 45.27, "learning_rate": 4.3975221799584767e-05, "loss": 0.0069, "step": 188500 }, { "epoch": 45.27, "learning_rate": 4.397076755255846e-05, "loss": 0.0108, "step": 188510 }, { "epoch": 45.27, "learning_rate": 4.396631335408638e-05, "loss": 0.006, "step": 188520 }, { "epoch": 45.27, "learning_rate": 4.3961859204204415e-05, "loss": 0.0065, "step": 188530 }, { "epoch": 45.28, "learning_rate": 4.3957405102948426e-05, "loss": 0.0051, "step": 188540 }, { "epoch": 45.28, "learning_rate": 4.395295105035431e-05, "loss": 0.0115, "step": 188550 }, { "epoch": 45.28, "learning_rate": 4.394849704645789e-05, "loss": 0.0132, "step": 188560 }, { "epoch": 45.28, "learning_rate": 4.394404309129507e-05, "loss": 0.0068, "step": 188570 }, { "epoch": 45.28, "learning_rate": 4.3939589184901694e-05, "loss": 0.0243, "step": 188580 }, { "epoch": 45.29, "learning_rate": 4.393513532731365e-05, "loss": 0.0095, "step": 188590 }, { "epoch": 45.29, "learning_rate": 4.3930681518566815e-05, "loss": 0.0124, "step": 188600 }, { "epoch": 45.29, "learning_rate": 4.392622775869702e-05, "loss": 0.0055, "step": 188610 }, { "epoch": 45.29, "learning_rate": 4.392177404774016e-05, "loss": 0.0137, "step": 188620 }, { "epoch": 45.3, "learning_rate": 4.391732038573208e-05, "loss": 0.0058, "step": 188630 }, { "epoch": 45.3, "learning_rate": 4.3912866772708664e-05, "loss": 0.0067, "step": 188640 }, { "epoch": 45.3, "learning_rate": 4.39084132087058e-05, "loss": 0.0117, "step": 188650 }, { "epoch": 45.3, "learning_rate": 4.3903959693759286e-05, "loss": 0.0042, "step": 188660 }, { "epoch": 45.31, "learning_rate": 4.389950622790505e-05, "loss": 0.0101, "step": 188670 }, { "epoch": 45.31, "learning_rate": 4.389505281117891e-05, "loss": 0.0087, "step": 188680 }, { "epoch": 45.31, "learning_rate": 4.389059944361677e-05, "loss": 0.0268, "step": 188690 }, { "epoch": 45.31, "learning_rate": 4.388614612525449e-05, "loss": 0.0185, "step": 188700 }, { "epoch": 45.31, "learning_rate": 4.388169285612789e-05, "loss": 0.0085, "step": 188710 }, { "epoch": 45.32, "learning_rate": 4.3877239636272875e-05, "loss": 0.0104, "step": 188720 }, { "epoch": 45.32, "learning_rate": 4.3872786465725284e-05, "loss": 0.0122, "step": 188730 }, { "epoch": 45.32, "learning_rate": 4.3868333344521014e-05, "loss": 0.0192, "step": 188740 }, { "epoch": 45.32, "learning_rate": 4.386388027269589e-05, "loss": 0.0149, "step": 188750 }, { "epoch": 45.33, "learning_rate": 4.385942725028577e-05, "loss": 0.0073, "step": 188760 }, { "epoch": 45.33, "learning_rate": 4.385497427732655e-05, "loss": 0.0195, "step": 188770 }, { "epoch": 45.33, "learning_rate": 4.385052135385406e-05, "loss": 0.0186, "step": 188780 }, { "epoch": 45.33, "learning_rate": 4.384606847990419e-05, "loss": 0.0183, "step": 188790 }, { "epoch": 45.33, "learning_rate": 4.384161565551276e-05, "loss": 0.013, "step": 188800 }, { "epoch": 45.34, "learning_rate": 4.383716288071566e-05, "loss": 0.0143, "step": 188810 }, { "epoch": 45.34, "learning_rate": 4.3832710155548716e-05, "loss": 0.0081, "step": 188820 }, { "epoch": 45.34, "learning_rate": 4.382825748004783e-05, "loss": 0.0103, "step": 188830 }, { "epoch": 45.34, "learning_rate": 4.3823804854248844e-05, "loss": 0.0112, "step": 188840 }, { "epoch": 45.35, "learning_rate": 4.381935227818759e-05, "loss": 0.0164, "step": 188850 }, { "epoch": 45.35, "learning_rate": 4.3814899751899956e-05, "loss": 0.0045, "step": 188860 }, { "epoch": 45.35, "learning_rate": 4.381044727542178e-05, "loss": 0.0075, "step": 188870 }, { "epoch": 45.35, "learning_rate": 4.380599484878893e-05, "loss": 0.0164, "step": 188880 }, { "epoch": 45.36, "learning_rate": 4.380154247203728e-05, "loss": 0.0197, "step": 188890 }, { "epoch": 45.36, "learning_rate": 4.379709014520264e-05, "loss": 0.0078, "step": 188900 }, { "epoch": 45.36, "learning_rate": 4.37926378683209e-05, "loss": 0.0126, "step": 188910 }, { "epoch": 45.36, "learning_rate": 4.3788185641427884e-05, "loss": 0.0123, "step": 188920 }, { "epoch": 45.36, "learning_rate": 4.37837334645595e-05, "loss": 0.0067, "step": 188930 }, { "epoch": 45.37, "learning_rate": 4.3779281337751546e-05, "loss": 0.0114, "step": 188940 }, { "epoch": 45.37, "learning_rate": 4.3774829261039893e-05, "loss": 0.0077, "step": 188950 }, { "epoch": 45.37, "learning_rate": 4.377037723446042e-05, "loss": 0.0103, "step": 188960 }, { "epoch": 45.37, "learning_rate": 4.376592525804894e-05, "loss": 0.0155, "step": 188970 }, { "epoch": 45.38, "learning_rate": 4.3761473331841356e-05, "loss": 0.0177, "step": 188980 }, { "epoch": 45.38, "learning_rate": 4.3757021455873456e-05, "loss": 0.0255, "step": 188990 }, { "epoch": 45.38, "learning_rate": 4.375256963018114e-05, "loss": 0.0124, "step": 189000 }, { "epoch": 45.38, "learning_rate": 4.374811785480023e-05, "loss": 0.007, "step": 189010 }, { "epoch": 45.39, "learning_rate": 4.374366612976659e-05, "loss": 0.0319, "step": 189020 }, { "epoch": 45.39, "learning_rate": 4.3739214455116096e-05, "loss": 0.0129, "step": 189030 }, { "epoch": 45.39, "learning_rate": 4.3734762830884545e-05, "loss": 0.0079, "step": 189040 }, { "epoch": 45.39, "learning_rate": 4.3730311257107826e-05, "loss": 0.0119, "step": 189050 }, { "epoch": 45.39, "learning_rate": 4.372585973382176e-05, "loss": 0.0093, "step": 189060 }, { "epoch": 45.4, "learning_rate": 4.372140826106224e-05, "loss": 0.0041, "step": 189070 }, { "epoch": 45.4, "learning_rate": 4.371695683886508e-05, "loss": 0.015, "step": 189080 }, { "epoch": 45.4, "learning_rate": 4.3712505467266104e-05, "loss": 0.0069, "step": 189090 }, { "epoch": 45.4, "learning_rate": 4.370805414630122e-05, "loss": 0.0088, "step": 189100 }, { "epoch": 45.41, "learning_rate": 4.370360287600622e-05, "loss": 0.0077, "step": 189110 }, { "epoch": 45.41, "learning_rate": 4.369915165641701e-05, "loss": 0.017, "step": 189120 }, { "epoch": 45.41, "learning_rate": 4.369470048756938e-05, "loss": 0.0061, "step": 189130 }, { "epoch": 45.41, "learning_rate": 4.3690249369499195e-05, "loss": 0.0185, "step": 189140 }, { "epoch": 45.41, "learning_rate": 4.368579830224231e-05, "loss": 0.0063, "step": 189150 }, { "epoch": 45.42, "learning_rate": 4.368134728583455e-05, "loss": 0.01, "step": 189160 }, { "epoch": 45.42, "learning_rate": 4.3676896320311795e-05, "loss": 0.0082, "step": 189170 }, { "epoch": 45.42, "learning_rate": 4.367244540570986e-05, "loss": 0.0147, "step": 189180 }, { "epoch": 45.42, "learning_rate": 4.366799454206458e-05, "loss": 0.0107, "step": 189190 }, { "epoch": 45.43, "learning_rate": 4.366354372941183e-05, "loss": 0.0227, "step": 189200 }, { "epoch": 45.43, "learning_rate": 4.3659092967787416e-05, "loss": 0.007, "step": 189210 }, { "epoch": 45.43, "learning_rate": 4.3654642257227245e-05, "loss": 0.0031, "step": 189220 }, { "epoch": 45.43, "learning_rate": 4.365019159776708e-05, "loss": 0.0063, "step": 189230 }, { "epoch": 45.44, "learning_rate": 4.3645740989442805e-05, "loss": 0.0058, "step": 189240 }, { "epoch": 45.44, "learning_rate": 4.3641290432290255e-05, "loss": 0.0046, "step": 189250 }, { "epoch": 45.44, "learning_rate": 4.3636839926345286e-05, "loss": 0.041, "step": 189260 }, { "epoch": 45.44, "learning_rate": 4.3632389471643716e-05, "loss": 0.0082, "step": 189270 }, { "epoch": 45.44, "learning_rate": 4.362793906822137e-05, "loss": 0.0132, "step": 189280 }, { "epoch": 45.45, "learning_rate": 4.362348871611413e-05, "loss": 0.0093, "step": 189290 }, { "epoch": 45.45, "learning_rate": 4.361903841535781e-05, "loss": 0.0171, "step": 189300 }, { "epoch": 45.45, "learning_rate": 4.361458816598827e-05, "loss": 0.0154, "step": 189310 }, { "epoch": 45.45, "learning_rate": 4.361013796804133e-05, "loss": 0.0066, "step": 189320 }, { "epoch": 45.46, "learning_rate": 4.3605687821552806e-05, "loss": 0.004, "step": 189330 }, { "epoch": 45.46, "learning_rate": 4.3601237726558584e-05, "loss": 0.0072, "step": 189340 }, { "epoch": 45.46, "learning_rate": 4.3596787683094464e-05, "loss": 0.0115, "step": 189350 }, { "epoch": 45.46, "learning_rate": 4.3592337691196314e-05, "loss": 0.0084, "step": 189360 }, { "epoch": 45.47, "learning_rate": 4.358788775089995e-05, "loss": 0.0081, "step": 189370 }, { "epoch": 45.47, "learning_rate": 4.3583437862241195e-05, "loss": 0.0066, "step": 189380 }, { "epoch": 45.47, "learning_rate": 4.3578988025255905e-05, "loss": 0.0037, "step": 189390 }, { "epoch": 45.47, "learning_rate": 4.3574538239979936e-05, "loss": 0.0436, "step": 189400 }, { "epoch": 45.47, "learning_rate": 4.357008850644908e-05, "loss": 0.0138, "step": 189410 }, { "epoch": 45.48, "learning_rate": 4.3565638824699174e-05, "loss": 0.015, "step": 189420 }, { "epoch": 45.48, "learning_rate": 4.356118919476608e-05, "loss": 0.0048, "step": 189430 }, { "epoch": 45.48, "learning_rate": 4.355673961668561e-05, "loss": 0.0236, "step": 189440 }, { "epoch": 45.48, "learning_rate": 4.355229009049363e-05, "loss": 0.0124, "step": 189450 }, { "epoch": 45.49, "learning_rate": 4.3547840616225935e-05, "loss": 0.0092, "step": 189460 }, { "epoch": 45.49, "learning_rate": 4.354339119391836e-05, "loss": 0.0086, "step": 189470 }, { "epoch": 45.49, "learning_rate": 4.353894182360675e-05, "loss": 0.0088, "step": 189480 }, { "epoch": 45.49, "learning_rate": 4.353449250532693e-05, "loss": 0.0062, "step": 189490 }, { "epoch": 45.49, "learning_rate": 4.3530043239114754e-05, "loss": 0.0069, "step": 189500 }, { "epoch": 45.5, "learning_rate": 4.3525594025006024e-05, "loss": 0.0096, "step": 189510 }, { "epoch": 45.5, "learning_rate": 4.352114486303657e-05, "loss": 0.0073, "step": 189520 }, { "epoch": 45.5, "learning_rate": 4.351669575324224e-05, "loss": 0.0141, "step": 189530 }, { "epoch": 45.5, "learning_rate": 4.3512246695658834e-05, "loss": 0.013, "step": 189540 }, { "epoch": 45.51, "learning_rate": 4.350779769032224e-05, "loss": 0.0158, "step": 189550 }, { "epoch": 45.51, "learning_rate": 4.350334873726822e-05, "loss": 0.0037, "step": 189560 }, { "epoch": 45.51, "learning_rate": 4.349889983653263e-05, "loss": 0.0146, "step": 189570 }, { "epoch": 45.51, "learning_rate": 4.3494450988151304e-05, "loss": 0.0086, "step": 189580 }, { "epoch": 45.52, "learning_rate": 4.3490002192160074e-05, "loss": 0.0041, "step": 189590 }, { "epoch": 45.52, "learning_rate": 4.3485553448594735e-05, "loss": 0.0087, "step": 189600 }, { "epoch": 45.52, "learning_rate": 4.348110475749114e-05, "loss": 0.0165, "step": 189610 }, { "epoch": 45.52, "learning_rate": 4.34766561188851e-05, "loss": 0.0126, "step": 189620 }, { "epoch": 45.52, "learning_rate": 4.347220753281246e-05, "loss": 0.0237, "step": 189630 }, { "epoch": 45.53, "learning_rate": 4.346775899930904e-05, "loss": 0.0191, "step": 189640 }, { "epoch": 45.53, "learning_rate": 4.3463310518410654e-05, "loss": 0.0117, "step": 189650 }, { "epoch": 45.53, "learning_rate": 4.345886209015312e-05, "loss": 0.0078, "step": 189660 }, { "epoch": 45.53, "learning_rate": 4.3454413714572286e-05, "loss": 0.0117, "step": 189670 }, { "epoch": 45.54, "learning_rate": 4.344996539170394e-05, "loss": 0.0142, "step": 189680 }, { "epoch": 45.54, "learning_rate": 4.344551712158396e-05, "loss": 0.0189, "step": 189690 }, { "epoch": 45.54, "learning_rate": 4.344106890424812e-05, "loss": 0.0168, "step": 189700 }, { "epoch": 45.54, "learning_rate": 4.343662073973225e-05, "loss": 0.0069, "step": 189710 }, { "epoch": 45.55, "learning_rate": 4.343217262807218e-05, "loss": 0.008, "step": 189720 }, { "epoch": 45.55, "learning_rate": 4.342772456930375e-05, "loss": 0.0096, "step": 189730 }, { "epoch": 45.55, "learning_rate": 4.342327656346274e-05, "loss": 0.0084, "step": 189740 }, { "epoch": 45.55, "learning_rate": 4.3418828610585e-05, "loss": 0.0098, "step": 189750 }, { "epoch": 45.55, "learning_rate": 4.341438071070633e-05, "loss": 0.0158, "step": 189760 }, { "epoch": 45.56, "learning_rate": 4.340993286386258e-05, "loss": 0.0112, "step": 189770 }, { "epoch": 45.56, "learning_rate": 4.340548507008955e-05, "loss": 0.0125, "step": 189780 }, { "epoch": 45.56, "learning_rate": 4.340103732942305e-05, "loss": 0.0125, "step": 189790 }, { "epoch": 45.56, "learning_rate": 4.33965896418989e-05, "loss": 0.0271, "step": 189800 }, { "epoch": 45.57, "learning_rate": 4.3392142007552934e-05, "loss": 0.0206, "step": 189810 }, { "epoch": 45.57, "learning_rate": 4.338769442642096e-05, "loss": 0.0121, "step": 189820 }, { "epoch": 45.57, "learning_rate": 4.338324689853881e-05, "loss": 0.0089, "step": 189830 }, { "epoch": 45.57, "learning_rate": 4.3378799423942276e-05, "loss": 0.0203, "step": 189840 }, { "epoch": 45.57, "learning_rate": 4.3374352002667176e-05, "loss": 0.011, "step": 189850 }, { "epoch": 45.58, "learning_rate": 4.336990463474934e-05, "loss": 0.005, "step": 189860 }, { "epoch": 45.58, "learning_rate": 4.3365457320224566e-05, "loss": 0.0104, "step": 189870 }, { "epoch": 45.58, "learning_rate": 4.33610100591287e-05, "loss": 0.017, "step": 189880 }, { "epoch": 45.58, "learning_rate": 4.335656285149753e-05, "loss": 0.0099, "step": 189890 }, { "epoch": 45.59, "learning_rate": 4.335211569736687e-05, "loss": 0.0141, "step": 189900 }, { "epoch": 45.59, "learning_rate": 4.334766859677255e-05, "loss": 0.0074, "step": 189910 }, { "epoch": 45.59, "learning_rate": 4.3343221549750376e-05, "loss": 0.0079, "step": 189920 }, { "epoch": 45.59, "learning_rate": 4.3338774556336134e-05, "loss": 0.006, "step": 189930 }, { "epoch": 45.6, "learning_rate": 4.333432761656568e-05, "loss": 0.0068, "step": 189940 }, { "epoch": 45.6, "learning_rate": 4.3329880730474795e-05, "loss": 0.0094, "step": 189950 }, { "epoch": 45.6, "learning_rate": 4.332543389809931e-05, "loss": 0.0072, "step": 189960 }, { "epoch": 45.6, "learning_rate": 4.332098711947504e-05, "loss": 0.0058, "step": 189970 }, { "epoch": 45.6, "learning_rate": 4.331654039463775e-05, "loss": 0.0076, "step": 189980 }, { "epoch": 45.61, "learning_rate": 4.3312093723623305e-05, "loss": 0.0158, "step": 189990 }, { "epoch": 45.61, "learning_rate": 4.330764710646748e-05, "loss": 0.0118, "step": 190000 }, { "epoch": 45.61, "learning_rate": 4.330320054320611e-05, "loss": 0.0098, "step": 190010 }, { "epoch": 45.61, "learning_rate": 4.3298754033875e-05, "loss": 0.0133, "step": 190020 }, { "epoch": 45.62, "learning_rate": 4.329430757850992e-05, "loss": 0.0281, "step": 190030 }, { "epoch": 45.62, "learning_rate": 4.328986117714672e-05, "loss": 0.0112, "step": 190040 }, { "epoch": 45.62, "learning_rate": 4.328541482982119e-05, "loss": 0.0225, "step": 190050 }, { "epoch": 45.62, "learning_rate": 4.328096853656917e-05, "loss": 0.0068, "step": 190060 }, { "epoch": 45.62, "learning_rate": 4.327652229742641e-05, "loss": 0.0101, "step": 190070 }, { "epoch": 45.63, "learning_rate": 4.327207611242875e-05, "loss": 0.0233, "step": 190080 }, { "epoch": 45.63, "learning_rate": 4.326762998161198e-05, "loss": 0.0216, "step": 190090 }, { "epoch": 45.63, "learning_rate": 4.326318390501193e-05, "loss": 0.0207, "step": 190100 }, { "epoch": 45.63, "learning_rate": 4.325873788266439e-05, "loss": 0.0158, "step": 190110 }, { "epoch": 45.64, "learning_rate": 4.3254291914605155e-05, "loss": 0.0228, "step": 190120 }, { "epoch": 45.64, "learning_rate": 4.3249846000870045e-05, "loss": 0.0062, "step": 190130 }, { "epoch": 45.64, "learning_rate": 4.324540014149484e-05, "loss": 0.0156, "step": 190140 }, { "epoch": 45.64, "learning_rate": 4.3240954336515384e-05, "loss": 0.0083, "step": 190150 }, { "epoch": 45.65, "learning_rate": 4.323650858596745e-05, "loss": 0.0057, "step": 190160 }, { "epoch": 45.65, "learning_rate": 4.3232062889886836e-05, "loss": 0.0131, "step": 190170 }, { "epoch": 45.65, "learning_rate": 4.322761724830937e-05, "loss": 0.0065, "step": 190180 }, { "epoch": 45.65, "learning_rate": 4.322317166127082e-05, "loss": 0.0105, "step": 190190 }, { "epoch": 45.65, "learning_rate": 4.321872612880701e-05, "loss": 0.0094, "step": 190200 }, { "epoch": 45.66, "learning_rate": 4.321428065095375e-05, "loss": 0.0155, "step": 190210 }, { "epoch": 45.66, "learning_rate": 4.32098352277468e-05, "loss": 0.0064, "step": 190220 }, { "epoch": 45.66, "learning_rate": 4.3205389859222003e-05, "loss": 0.0147, "step": 190230 }, { "epoch": 45.66, "learning_rate": 4.320094454541512e-05, "loss": 0.0118, "step": 190240 }, { "epoch": 45.67, "learning_rate": 4.3196499286361995e-05, "loss": 0.0055, "step": 190250 }, { "epoch": 45.67, "learning_rate": 4.319205408209839e-05, "loss": 0.0129, "step": 190260 }, { "epoch": 45.67, "learning_rate": 4.318760893266011e-05, "loss": 0.0058, "step": 190270 }, { "epoch": 45.67, "learning_rate": 4.318316383808295e-05, "loss": 0.0065, "step": 190280 }, { "epoch": 45.68, "learning_rate": 4.3178718798402715e-05, "loss": 0.0068, "step": 190290 }, { "epoch": 45.68, "learning_rate": 4.317427381365522e-05, "loss": 0.0176, "step": 190300 }, { "epoch": 45.68, "learning_rate": 4.3169828883876215e-05, "loss": 0.0124, "step": 190310 }, { "epoch": 45.68, "learning_rate": 4.316538400910153e-05, "loss": 0.0069, "step": 190320 }, { "epoch": 45.68, "learning_rate": 4.316093918936694e-05, "loss": 0.0143, "step": 190330 }, { "epoch": 45.69, "learning_rate": 4.315649442470827e-05, "loss": 0.0081, "step": 190340 }, { "epoch": 45.69, "learning_rate": 4.31520497151613e-05, "loss": 0.0145, "step": 190350 }, { "epoch": 45.69, "learning_rate": 4.31476050607618e-05, "loss": 0.0118, "step": 190360 }, { "epoch": 45.69, "learning_rate": 4.3143160461545584e-05, "loss": 0.0054, "step": 190370 }, { "epoch": 45.7, "learning_rate": 4.313871591754844e-05, "loss": 0.0186, "step": 190380 }, { "epoch": 45.7, "learning_rate": 4.3134271428806186e-05, "loss": 0.0092, "step": 190390 }, { "epoch": 45.7, "learning_rate": 4.3129826995354575e-05, "loss": 0.0063, "step": 190400 }, { "epoch": 45.7, "learning_rate": 4.3125382617229415e-05, "loss": 0.0122, "step": 190410 }, { "epoch": 45.7, "learning_rate": 4.31209382944665e-05, "loss": 0.0069, "step": 190420 }, { "epoch": 45.71, "learning_rate": 4.311649402710161e-05, "loss": 0.007, "step": 190430 }, { "epoch": 45.71, "learning_rate": 4.311204981517057e-05, "loss": 0.007, "step": 190440 }, { "epoch": 45.71, "learning_rate": 4.3107605658709125e-05, "loss": 0.0064, "step": 190450 }, { "epoch": 45.71, "learning_rate": 4.310316155775308e-05, "loss": 0.0103, "step": 190460 }, { "epoch": 45.72, "learning_rate": 4.309871751233824e-05, "loss": 0.006, "step": 190470 }, { "epoch": 45.72, "learning_rate": 4.309427352250036e-05, "loss": 0.0167, "step": 190480 }, { "epoch": 45.72, "learning_rate": 4.3089829588275286e-05, "loss": 0.0111, "step": 190490 }, { "epoch": 45.72, "learning_rate": 4.308538570969874e-05, "loss": 0.0035, "step": 190500 }, { "epoch": 45.73, "learning_rate": 4.308094188680654e-05, "loss": 0.0305, "step": 190510 }, { "epoch": 45.73, "learning_rate": 4.307649811963447e-05, "loss": 0.0113, "step": 190520 }, { "epoch": 45.73, "learning_rate": 4.307205440821832e-05, "loss": 0.0233, "step": 190530 }, { "epoch": 45.73, "learning_rate": 4.306761075259388e-05, "loss": 0.0081, "step": 190540 }, { "epoch": 45.73, "learning_rate": 4.306316715279691e-05, "loss": 0.013, "step": 190550 }, { "epoch": 45.74, "learning_rate": 4.3058723608863225e-05, "loss": 0.01, "step": 190560 }, { "epoch": 45.74, "learning_rate": 4.305428012082858e-05, "loss": 0.0072, "step": 190570 }, { "epoch": 45.74, "learning_rate": 4.3049836688728806e-05, "loss": 0.0174, "step": 190580 }, { "epoch": 45.74, "learning_rate": 4.3045393312599644e-05, "loss": 0.0081, "step": 190590 }, { "epoch": 45.75, "learning_rate": 4.304094999247688e-05, "loss": 0.021, "step": 190600 }, { "epoch": 45.75, "learning_rate": 4.303650672839632e-05, "loss": 0.0115, "step": 190610 }, { "epoch": 45.75, "learning_rate": 4.303206352039371e-05, "loss": 0.0125, "step": 190620 }, { "epoch": 45.75, "learning_rate": 4.3027620368504885e-05, "loss": 0.0146, "step": 190630 }, { "epoch": 45.76, "learning_rate": 4.302317727276558e-05, "loss": 0.0044, "step": 190640 }, { "epoch": 45.76, "learning_rate": 4.3018734233211584e-05, "loss": 0.0206, "step": 190650 }, { "epoch": 45.76, "learning_rate": 4.30142912498787e-05, "loss": 0.0086, "step": 190660 }, { "epoch": 45.76, "learning_rate": 4.300984832280267e-05, "loss": 0.0232, "step": 190670 }, { "epoch": 45.76, "learning_rate": 4.300540545201933e-05, "loss": 0.0129, "step": 190680 }, { "epoch": 45.77, "learning_rate": 4.300096263756441e-05, "loss": 0.02, "step": 190690 }, { "epoch": 45.77, "learning_rate": 4.299651987947369e-05, "loss": 0.0094, "step": 190700 }, { "epoch": 45.77, "learning_rate": 4.299207717778298e-05, "loss": 0.0074, "step": 190710 }, { "epoch": 45.77, "learning_rate": 4.298763453252805e-05, "loss": 0.0064, "step": 190720 }, { "epoch": 45.78, "learning_rate": 4.298319194374465e-05, "loss": 0.0151, "step": 190730 }, { "epoch": 45.78, "learning_rate": 4.2978749411468565e-05, "loss": 0.01, "step": 190740 }, { "epoch": 45.78, "learning_rate": 4.2974306935735595e-05, "loss": 0.0136, "step": 190750 }, { "epoch": 45.78, "learning_rate": 4.296986451658149e-05, "loss": 0.0189, "step": 190760 }, { "epoch": 45.78, "learning_rate": 4.2965422154042056e-05, "loss": 0.0094, "step": 190770 }, { "epoch": 45.79, "learning_rate": 4.2960979848153037e-05, "loss": 0.0096, "step": 190780 }, { "epoch": 45.79, "learning_rate": 4.295653759895021e-05, "loss": 0.0067, "step": 190790 }, { "epoch": 45.79, "learning_rate": 4.295209540646937e-05, "loss": 0.0093, "step": 190800 }, { "epoch": 45.79, "learning_rate": 4.294765327074627e-05, "loss": 0.0125, "step": 190810 }, { "epoch": 45.8, "learning_rate": 4.294321119181671e-05, "loss": 0.0288, "step": 190820 }, { "epoch": 45.8, "learning_rate": 4.293876916971643e-05, "loss": 0.0075, "step": 190830 }, { "epoch": 45.8, "learning_rate": 4.2934327204481215e-05, "loss": 0.0146, "step": 190840 }, { "epoch": 45.8, "learning_rate": 4.2929885296146845e-05, "loss": 0.0126, "step": 190850 }, { "epoch": 45.81, "learning_rate": 4.292544344474907e-05, "loss": 0.0197, "step": 190860 }, { "epoch": 45.81, "learning_rate": 4.29210016503237e-05, "loss": 0.0109, "step": 190870 }, { "epoch": 45.81, "learning_rate": 4.291655991290647e-05, "loss": 0.0125, "step": 190880 }, { "epoch": 45.81, "learning_rate": 4.291211823253316e-05, "loss": 0.0083, "step": 190890 }, { "epoch": 45.81, "learning_rate": 4.290767660923953e-05, "loss": 0.0152, "step": 190900 }, { "epoch": 45.82, "learning_rate": 4.290323504306139e-05, "loss": 0.0068, "step": 190910 }, { "epoch": 45.82, "learning_rate": 4.289879353403446e-05, "loss": 0.0047, "step": 190920 }, { "epoch": 45.82, "learning_rate": 4.2894352082194514e-05, "loss": 0.0063, "step": 190930 }, { "epoch": 45.82, "learning_rate": 4.288991068757734e-05, "loss": 0.0073, "step": 190940 }, { "epoch": 45.83, "learning_rate": 4.288546935021869e-05, "loss": 0.0094, "step": 190950 }, { "epoch": 45.83, "learning_rate": 4.288102807015436e-05, "loss": 0.0114, "step": 190960 }, { "epoch": 45.83, "learning_rate": 4.287658684742008e-05, "loss": 0.009, "step": 190970 }, { "epoch": 45.83, "learning_rate": 4.2872145682051626e-05, "loss": 0.0119, "step": 190980 }, { "epoch": 45.84, "learning_rate": 4.2867704574084766e-05, "loss": 0.0082, "step": 190990 }, { "epoch": 45.84, "learning_rate": 4.2863263523555265e-05, "loss": 0.0084, "step": 191000 }, { "epoch": 45.84, "learning_rate": 4.285882253049891e-05, "loss": 0.0224, "step": 191010 }, { "epoch": 45.84, "learning_rate": 4.285438159495142e-05, "loss": 0.0128, "step": 191020 }, { "epoch": 45.84, "learning_rate": 4.2849940716948575e-05, "loss": 0.0045, "step": 191030 }, { "epoch": 45.85, "learning_rate": 4.2845499896526165e-05, "loss": 0.0111, "step": 191040 }, { "epoch": 45.85, "learning_rate": 4.284105913371993e-05, "loss": 0.0053, "step": 191050 }, { "epoch": 45.85, "learning_rate": 4.283661842856562e-05, "loss": 0.0071, "step": 191060 }, { "epoch": 45.85, "learning_rate": 4.2832177781099025e-05, "loss": 0.0148, "step": 191070 }, { "epoch": 45.86, "learning_rate": 4.2827737191355874e-05, "loss": 0.018, "step": 191080 }, { "epoch": 45.86, "learning_rate": 4.282329665937197e-05, "loss": 0.0092, "step": 191090 }, { "epoch": 45.86, "learning_rate": 4.281885618518304e-05, "loss": 0.0136, "step": 191100 }, { "epoch": 45.86, "learning_rate": 4.2814415768824846e-05, "loss": 0.0184, "step": 191110 }, { "epoch": 45.86, "learning_rate": 4.2809975410333155e-05, "loss": 0.0116, "step": 191120 }, { "epoch": 45.87, "learning_rate": 4.2805535109743714e-05, "loss": 0.0114, "step": 191130 }, { "epoch": 45.87, "learning_rate": 4.28010948670923e-05, "loss": 0.008, "step": 191140 }, { "epoch": 45.87, "learning_rate": 4.2796654682414686e-05, "loss": 0.007, "step": 191150 }, { "epoch": 45.87, "learning_rate": 4.279221455574659e-05, "loss": 0.0119, "step": 191160 }, { "epoch": 45.88, "learning_rate": 4.2787774487123775e-05, "loss": 0.0058, "step": 191170 }, { "epoch": 45.88, "learning_rate": 4.278333447658202e-05, "loss": 0.0175, "step": 191180 }, { "epoch": 45.88, "learning_rate": 4.2778894524157054e-05, "loss": 0.0087, "step": 191190 }, { "epoch": 45.88, "learning_rate": 4.2774454629884677e-05, "loss": 0.0089, "step": 191200 }, { "epoch": 45.89, "learning_rate": 4.2770014793800596e-05, "loss": 0.0163, "step": 191210 }, { "epoch": 45.89, "learning_rate": 4.276557501594057e-05, "loss": 0.0065, "step": 191220 }, { "epoch": 45.89, "learning_rate": 4.276113529634038e-05, "loss": 0.0062, "step": 191230 }, { "epoch": 45.89, "learning_rate": 4.275669563503578e-05, "loss": 0.0135, "step": 191240 }, { "epoch": 45.89, "learning_rate": 4.275225603206249e-05, "loss": 0.0083, "step": 191250 }, { "epoch": 45.9, "learning_rate": 4.2747816487456295e-05, "loss": 0.0039, "step": 191260 }, { "epoch": 45.9, "learning_rate": 4.2743377001252916e-05, "loss": 0.0056, "step": 191270 }, { "epoch": 45.9, "learning_rate": 4.273893757348814e-05, "loss": 0.0175, "step": 191280 }, { "epoch": 45.9, "learning_rate": 4.273449820419771e-05, "loss": 0.0055, "step": 191290 }, { "epoch": 45.91, "learning_rate": 4.273005889341736e-05, "loss": 0.011, "step": 191300 }, { "epoch": 45.91, "learning_rate": 4.272561964118285e-05, "loss": 0.0087, "step": 191310 }, { "epoch": 45.91, "learning_rate": 4.272118044752992e-05, "loss": 0.0187, "step": 191320 }, { "epoch": 45.91, "learning_rate": 4.2716741312494336e-05, "loss": 0.0271, "step": 191330 }, { "epoch": 45.92, "learning_rate": 4.271230223611185e-05, "loss": 0.0089, "step": 191340 }, { "epoch": 45.92, "learning_rate": 4.270786321841819e-05, "loss": 0.0057, "step": 191350 }, { "epoch": 45.92, "learning_rate": 4.2703424259449106e-05, "loss": 0.0053, "step": 191360 }, { "epoch": 45.92, "learning_rate": 4.2698985359240366e-05, "loss": 0.0094, "step": 191370 }, { "epoch": 45.92, "learning_rate": 4.269454651782772e-05, "loss": 0.0046, "step": 191380 }, { "epoch": 45.93, "learning_rate": 4.269010773524687e-05, "loss": 0.0042, "step": 191390 }, { "epoch": 45.93, "learning_rate": 4.26856690115336e-05, "loss": 0.0055, "step": 191400 }, { "epoch": 45.93, "learning_rate": 4.268123034672364e-05, "loss": 0.0036, "step": 191410 }, { "epoch": 45.93, "learning_rate": 4.267679174085276e-05, "loss": 0.01, "step": 191420 }, { "epoch": 45.94, "learning_rate": 4.2672353193956694e-05, "loss": 0.0107, "step": 191430 }, { "epoch": 45.94, "learning_rate": 4.266791470607116e-05, "loss": 0.0096, "step": 191440 }, { "epoch": 45.94, "learning_rate": 4.2663476277231915e-05, "loss": 0.013, "step": 191450 }, { "epoch": 45.94, "learning_rate": 4.265903790747472e-05, "loss": 0.0056, "step": 191460 }, { "epoch": 45.94, "learning_rate": 4.2654599596835305e-05, "loss": 0.0112, "step": 191470 }, { "epoch": 45.95, "learning_rate": 4.265016134534943e-05, "loss": 0.0051, "step": 191480 }, { "epoch": 45.95, "learning_rate": 4.264572315305279e-05, "loss": 0.0104, "step": 191490 }, { "epoch": 46.0, "learning_rate": 4.2641285019981175e-05, "loss": 0.0047, "step": 191500 }, { "epoch": 46.0, "learning_rate": 4.26368469461703e-05, "loss": 0.0079, "step": 191510 }, { "epoch": 46.01, "learning_rate": 4.263240893165591e-05, "loss": 0.0074, "step": 191520 }, { "epoch": 46.01, "learning_rate": 4.262797097647377e-05, "loss": 0.0044, "step": 191530 }, { "epoch": 46.01, "learning_rate": 4.262353308065957e-05, "loss": 0.0073, "step": 191540 }, { "epoch": 46.01, "learning_rate": 4.26190952442491e-05, "loss": 0.0064, "step": 191550 }, { "epoch": 46.01, "learning_rate": 4.261465746727805e-05, "loss": 0.0084, "step": 191560 }, { "epoch": 46.02, "learning_rate": 4.261021974978222e-05, "loss": 0.0116, "step": 191570 }, { "epoch": 46.02, "learning_rate": 4.260578209179728e-05, "loss": 0.007, "step": 191580 }, { "epoch": 46.02, "learning_rate": 4.260134449335901e-05, "loss": 0.007, "step": 191590 }, { "epoch": 46.02, "learning_rate": 4.259690695450312e-05, "loss": 0.0085, "step": 191600 }, { "epoch": 46.03, "learning_rate": 4.2592469475265366e-05, "loss": 0.0106, "step": 191610 }, { "epoch": 46.03, "learning_rate": 4.25880320556815e-05, "loss": 0.0034, "step": 191620 }, { "epoch": 46.03, "learning_rate": 4.2583594695787205e-05, "loss": 0.0131, "step": 191630 }, { "epoch": 46.03, "learning_rate": 4.257915739561826e-05, "loss": 0.0119, "step": 191640 }, { "epoch": 46.03, "learning_rate": 4.257472015521037e-05, "loss": 0.0209, "step": 191650 }, { "epoch": 46.04, "learning_rate": 4.25702829745993e-05, "loss": 0.0042, "step": 191660 }, { "epoch": 46.04, "learning_rate": 4.256584585382078e-05, "loss": 0.0121, "step": 191670 }, { "epoch": 46.04, "learning_rate": 4.256140879291051e-05, "loss": 0.0112, "step": 191680 }, { "epoch": 46.04, "learning_rate": 4.255697179190424e-05, "loss": 0.0116, "step": 191690 }, { "epoch": 46.05, "learning_rate": 4.25525348508377e-05, "loss": 0.0173, "step": 191700 }, { "epoch": 46.05, "learning_rate": 4.254809796974665e-05, "loss": 0.0065, "step": 191710 }, { "epoch": 46.05, "learning_rate": 4.254366114866678e-05, "loss": 0.0118, "step": 191720 }, { "epoch": 46.05, "learning_rate": 4.253922438763383e-05, "loss": 0.0127, "step": 191730 }, { "epoch": 46.06, "learning_rate": 4.253478768668354e-05, "loss": 0.0078, "step": 191740 }, { "epoch": 46.06, "learning_rate": 4.253035104585163e-05, "loss": 0.0332, "step": 191750 }, { "epoch": 46.06, "learning_rate": 4.252591446517386e-05, "loss": 0.0062, "step": 191760 }, { "epoch": 46.06, "learning_rate": 4.252147794468591e-05, "loss": 0.0101, "step": 191770 }, { "epoch": 46.06, "learning_rate": 4.2517041484423535e-05, "loss": 0.0107, "step": 191780 }, { "epoch": 46.07, "learning_rate": 4.251260508442245e-05, "loss": 0.0127, "step": 191790 }, { "epoch": 46.07, "learning_rate": 4.25081687447184e-05, "loss": 0.0125, "step": 191800 }, { "epoch": 46.07, "learning_rate": 4.250373246534711e-05, "loss": 0.0089, "step": 191810 }, { "epoch": 46.07, "learning_rate": 4.2499296246344277e-05, "loss": 0.0096, "step": 191820 }, { "epoch": 46.08, "learning_rate": 4.249486008774566e-05, "loss": 0.0099, "step": 191830 }, { "epoch": 46.08, "learning_rate": 4.249042398958696e-05, "loss": 0.0056, "step": 191840 }, { "epoch": 46.08, "learning_rate": 4.2485987951903924e-05, "loss": 0.0083, "step": 191850 }, { "epoch": 46.08, "learning_rate": 4.248155197473227e-05, "loss": 0.0129, "step": 191860 }, { "epoch": 46.09, "learning_rate": 4.24771160581077e-05, "loss": 0.0142, "step": 191870 }, { "epoch": 46.09, "learning_rate": 4.247268020206595e-05, "loss": 0.0071, "step": 191880 }, { "epoch": 46.09, "learning_rate": 4.246824440664275e-05, "loss": 0.0119, "step": 191890 }, { "epoch": 46.09, "learning_rate": 4.246380867187384e-05, "loss": 0.0079, "step": 191900 }, { "epoch": 46.09, "learning_rate": 4.24593729977949e-05, "loss": 0.0044, "step": 191910 }, { "epoch": 46.1, "learning_rate": 4.2454937384441665e-05, "loss": 0.004, "step": 191920 }, { "epoch": 46.1, "learning_rate": 4.245050183184987e-05, "loss": 0.0086, "step": 191930 }, { "epoch": 46.1, "learning_rate": 4.2446066340055214e-05, "loss": 0.0282, "step": 191940 }, { "epoch": 46.1, "learning_rate": 4.244163090909345e-05, "loss": 0.006, "step": 191950 }, { "epoch": 46.11, "learning_rate": 4.243719553900027e-05, "loss": 0.0051, "step": 191960 }, { "epoch": 46.11, "learning_rate": 4.243276022981138e-05, "loss": 0.0066, "step": 191970 }, { "epoch": 46.11, "learning_rate": 4.2428324981562536e-05, "loss": 0.0141, "step": 191980 }, { "epoch": 46.11, "learning_rate": 4.242388979428942e-05, "loss": 0.0167, "step": 191990 }, { "epoch": 46.11, "learning_rate": 4.241945466802779e-05, "loss": 0.0107, "step": 192000 }, { "epoch": 46.12, "learning_rate": 4.241501960281332e-05, "loss": 0.0104, "step": 192010 }, { "epoch": 46.12, "learning_rate": 4.241058459868175e-05, "loss": 0.0076, "step": 192020 }, { "epoch": 46.12, "learning_rate": 4.240614965566878e-05, "loss": 0.0154, "step": 192030 }, { "epoch": 46.12, "learning_rate": 4.240171477381015e-05, "loss": 0.0079, "step": 192040 }, { "epoch": 46.13, "learning_rate": 4.2397279953141555e-05, "loss": 0.0079, "step": 192050 }, { "epoch": 46.13, "learning_rate": 4.23928451936987e-05, "loss": 0.0086, "step": 192060 }, { "epoch": 46.13, "learning_rate": 4.2388410495517326e-05, "loss": 0.0096, "step": 192070 }, { "epoch": 46.13, "learning_rate": 4.238397585863313e-05, "loss": 0.0053, "step": 192080 }, { "epoch": 46.14, "learning_rate": 4.2379541283081835e-05, "loss": 0.0104, "step": 192090 }, { "epoch": 46.14, "learning_rate": 4.237510676889915e-05, "loss": 0.0044, "step": 192100 }, { "epoch": 46.14, "learning_rate": 4.237067231612076e-05, "loss": 0.0099, "step": 192110 }, { "epoch": 46.14, "learning_rate": 4.2366237924782415e-05, "loss": 0.0084, "step": 192120 }, { "epoch": 46.14, "learning_rate": 4.23618035949198e-05, "loss": 0.0129, "step": 192130 }, { "epoch": 46.15, "learning_rate": 4.235736932656865e-05, "loss": 0.0082, "step": 192140 }, { "epoch": 46.15, "learning_rate": 4.235293511976466e-05, "loss": 0.0126, "step": 192150 }, { "epoch": 46.15, "learning_rate": 4.234850097454352e-05, "loss": 0.0054, "step": 192160 }, { "epoch": 46.15, "learning_rate": 4.234406689094097e-05, "loss": 0.0089, "step": 192170 }, { "epoch": 46.16, "learning_rate": 4.23396328689927e-05, "loss": 0.0181, "step": 192180 }, { "epoch": 46.16, "learning_rate": 4.233519890873444e-05, "loss": 0.0048, "step": 192190 }, { "epoch": 46.16, "learning_rate": 4.233076501020188e-05, "loss": 0.0078, "step": 192200 }, { "epoch": 46.16, "learning_rate": 4.2326331173430714e-05, "loss": 0.01, "step": 192210 }, { "epoch": 46.16, "learning_rate": 4.232189739845666e-05, "loss": 0.0104, "step": 192220 }, { "epoch": 46.17, "learning_rate": 4.231746368531545e-05, "loss": 0.0057, "step": 192230 }, { "epoch": 46.17, "learning_rate": 4.231303003404276e-05, "loss": 0.0085, "step": 192240 }, { "epoch": 46.17, "learning_rate": 4.230859644467428e-05, "loss": 0.009, "step": 192250 }, { "epoch": 46.17, "learning_rate": 4.230416291724574e-05, "loss": 0.0061, "step": 192260 }, { "epoch": 46.18, "learning_rate": 4.2299729451792836e-05, "loss": 0.0076, "step": 192270 }, { "epoch": 46.18, "learning_rate": 4.2295296048351294e-05, "loss": 0.0042, "step": 192280 }, { "epoch": 46.18, "learning_rate": 4.2290862706956786e-05, "loss": 0.005, "step": 192290 }, { "epoch": 46.18, "learning_rate": 4.2286429427645015e-05, "loss": 0.0044, "step": 192300 }, { "epoch": 46.19, "learning_rate": 4.22819962104517e-05, "loss": 0.0091, "step": 192310 }, { "epoch": 46.19, "learning_rate": 4.2277563055412525e-05, "loss": 0.0177, "step": 192320 }, { "epoch": 46.19, "learning_rate": 4.2273129962563226e-05, "loss": 0.0038, "step": 192330 }, { "epoch": 46.19, "learning_rate": 4.226869693193947e-05, "loss": 0.0072, "step": 192340 }, { "epoch": 46.19, "learning_rate": 4.226426396357695e-05, "loss": 0.0062, "step": 192350 }, { "epoch": 46.2, "learning_rate": 4.225983105751139e-05, "loss": 0.0054, "step": 192360 }, { "epoch": 46.2, "learning_rate": 4.225539821377849e-05, "loss": 0.0026, "step": 192370 }, { "epoch": 46.2, "learning_rate": 4.2250965432413914e-05, "loss": 0.0141, "step": 192380 }, { "epoch": 46.2, "learning_rate": 4.22465327134534e-05, "loss": 0.0051, "step": 192390 }, { "epoch": 46.21, "learning_rate": 4.2242100056932615e-05, "loss": 0.0061, "step": 192400 }, { "epoch": 46.21, "learning_rate": 4.223766746288728e-05, "loss": 0.0064, "step": 192410 }, { "epoch": 46.21, "learning_rate": 4.2233234931353085e-05, "loss": 0.006, "step": 192420 }, { "epoch": 46.21, "learning_rate": 4.2228802462365725e-05, "loss": 0.011, "step": 192430 }, { "epoch": 46.22, "learning_rate": 4.222437005596087e-05, "loss": 0.0061, "step": 192440 }, { "epoch": 46.22, "learning_rate": 4.221993771217424e-05, "loss": 0.0053, "step": 192450 }, { "epoch": 46.22, "learning_rate": 4.221550543104153e-05, "loss": 0.0101, "step": 192460 }, { "epoch": 46.22, "learning_rate": 4.2211073212598445e-05, "loss": 0.0095, "step": 192470 }, { "epoch": 46.22, "learning_rate": 4.220664105688066e-05, "loss": 0.0062, "step": 192480 }, { "epoch": 46.23, "learning_rate": 4.220220896392384e-05, "loss": 0.0138, "step": 192490 }, { "epoch": 46.23, "learning_rate": 4.219777693376374e-05, "loss": 0.0138, "step": 192500 }, { "epoch": 46.23, "learning_rate": 4.2193344966436e-05, "loss": 0.0088, "step": 192510 }, { "epoch": 46.23, "learning_rate": 4.218891306197635e-05, "loss": 0.0181, "step": 192520 }, { "epoch": 46.24, "learning_rate": 4.2184481220420454e-05, "loss": 0.0078, "step": 192530 }, { "epoch": 46.24, "learning_rate": 4.218004944180399e-05, "loss": 0.0055, "step": 192540 }, { "epoch": 46.24, "learning_rate": 4.217561772616269e-05, "loss": 0.0071, "step": 192550 }, { "epoch": 46.24, "learning_rate": 4.2171186073532227e-05, "loss": 0.0052, "step": 192560 }, { "epoch": 46.24, "learning_rate": 4.216675448394826e-05, "loss": 0.0121, "step": 192570 }, { "epoch": 46.25, "learning_rate": 4.216232295744651e-05, "loss": 0.0103, "step": 192580 }, { "epoch": 46.25, "learning_rate": 4.215789149406265e-05, "loss": 0.0079, "step": 192590 }, { "epoch": 46.25, "learning_rate": 4.2153460093832385e-05, "loss": 0.0096, "step": 192600 }, { "epoch": 46.25, "learning_rate": 4.2149028756791394e-05, "loss": 0.0039, "step": 192610 }, { "epoch": 46.26, "learning_rate": 4.214459748297534e-05, "loss": 0.0104, "step": 192620 }, { "epoch": 46.26, "learning_rate": 4.214016627241993e-05, "loss": 0.012, "step": 192630 }, { "epoch": 46.26, "learning_rate": 4.213573512516086e-05, "loss": 0.01, "step": 192640 }, { "epoch": 46.26, "learning_rate": 4.213130404123378e-05, "loss": 0.0161, "step": 192650 }, { "epoch": 46.27, "learning_rate": 4.2126873020674425e-05, "loss": 0.0026, "step": 192660 }, { "epoch": 46.27, "learning_rate": 4.212244206351843e-05, "loss": 0.0092, "step": 192670 }, { "epoch": 46.27, "learning_rate": 4.2118011169801485e-05, "loss": 0.0061, "step": 192680 }, { "epoch": 46.27, "learning_rate": 4.21135803395593e-05, "loss": 0.0086, "step": 192690 }, { "epoch": 46.27, "learning_rate": 4.210914957282755e-05, "loss": 0.0147, "step": 192700 }, { "epoch": 46.28, "learning_rate": 4.210471886964188e-05, "loss": 0.0044, "step": 192710 }, { "epoch": 46.28, "learning_rate": 4.210028823003802e-05, "loss": 0.0093, "step": 192720 }, { "epoch": 46.28, "learning_rate": 4.2095857654051615e-05, "loss": 0.0053, "step": 192730 }, { "epoch": 46.28, "learning_rate": 4.209142714171837e-05, "loss": 0.0112, "step": 192740 }, { "epoch": 46.29, "learning_rate": 4.208699669307396e-05, "loss": 0.0059, "step": 192750 }, { "epoch": 46.29, "learning_rate": 4.2082566308154045e-05, "loss": 0.0088, "step": 192760 }, { "epoch": 46.29, "learning_rate": 4.207813598699433e-05, "loss": 0.0065, "step": 192770 }, { "epoch": 46.29, "learning_rate": 4.207370572963046e-05, "loss": 0.007, "step": 192780 }, { "epoch": 46.3, "learning_rate": 4.206927553609814e-05, "loss": 0.0054, "step": 192790 }, { "epoch": 46.3, "learning_rate": 4.206484540643306e-05, "loss": 0.0069, "step": 192800 }, { "epoch": 46.3, "learning_rate": 4.2060415340670847e-05, "loss": 0.0104, "step": 192810 }, { "epoch": 46.3, "learning_rate": 4.2055985338847214e-05, "loss": 0.014, "step": 192820 }, { "epoch": 46.3, "learning_rate": 4.2051555400997824e-05, "loss": 0.0066, "step": 192830 }, { "epoch": 46.31, "learning_rate": 4.204712552715836e-05, "loss": 0.0104, "step": 192840 }, { "epoch": 46.31, "learning_rate": 4.204269571736451e-05, "loss": 0.0089, "step": 192850 }, { "epoch": 46.31, "learning_rate": 4.2038265971651915e-05, "loss": 0.0122, "step": 192860 }, { "epoch": 46.31, "learning_rate": 4.203383629005626e-05, "loss": 0.0062, "step": 192870 }, { "epoch": 46.32, "learning_rate": 4.202940667261322e-05, "loss": 0.0078, "step": 192880 }, { "epoch": 46.32, "learning_rate": 4.2024977119358484e-05, "loss": 0.009, "step": 192890 }, { "epoch": 46.32, "learning_rate": 4.202054763032769e-05, "loss": 0.0125, "step": 192900 }, { "epoch": 46.32, "learning_rate": 4.2016118205556534e-05, "loss": 0.0145, "step": 192910 }, { "epoch": 46.32, "learning_rate": 4.201168884508067e-05, "loss": 0.0053, "step": 192920 }, { "epoch": 46.33, "learning_rate": 4.200725954893579e-05, "loss": 0.0083, "step": 192930 }, { "epoch": 46.33, "learning_rate": 4.200283031715757e-05, "loss": 0.0176, "step": 192940 }, { "epoch": 46.33, "learning_rate": 4.199840114978163e-05, "loss": 0.0171, "step": 192950 }, { "epoch": 46.33, "learning_rate": 4.199397204684368e-05, "loss": 0.0237, "step": 192960 }, { "epoch": 46.34, "learning_rate": 4.198954300837937e-05, "loss": 0.0074, "step": 192970 }, { "epoch": 46.34, "learning_rate": 4.198511403442439e-05, "loss": 0.0072, "step": 192980 }, { "epoch": 46.34, "learning_rate": 4.198068512501441e-05, "loss": 0.0086, "step": 192990 }, { "epoch": 46.34, "learning_rate": 4.197625628018505e-05, "loss": 0.0102, "step": 193000 }, { "epoch": 46.35, "learning_rate": 4.1971827499972016e-05, "loss": 0.0118, "step": 193010 }, { "epoch": 46.35, "learning_rate": 4.1967398784410956e-05, "loss": 0.0138, "step": 193020 }, { "epoch": 46.35, "learning_rate": 4.196297013353756e-05, "loss": 0.009, "step": 193030 }, { "epoch": 46.35, "learning_rate": 4.195854154738747e-05, "loss": 0.0113, "step": 193040 }, { "epoch": 46.35, "learning_rate": 4.1954113025996337e-05, "loss": 0.0096, "step": 193050 }, { "epoch": 46.36, "learning_rate": 4.194968456939986e-05, "loss": 0.0098, "step": 193060 }, { "epoch": 46.36, "learning_rate": 4.1945256177633684e-05, "loss": 0.0062, "step": 193070 }, { "epoch": 46.36, "learning_rate": 4.1940827850733475e-05, "loss": 0.0106, "step": 193080 }, { "epoch": 46.36, "learning_rate": 4.193639958873488e-05, "loss": 0.0081, "step": 193090 }, { "epoch": 46.37, "learning_rate": 4.193197139167358e-05, "loss": 0.0044, "step": 193100 }, { "epoch": 46.37, "learning_rate": 4.192754325958522e-05, "loss": 0.0092, "step": 193110 }, { "epoch": 46.37, "learning_rate": 4.1923115192505476e-05, "loss": 0.0043, "step": 193120 }, { "epoch": 46.37, "learning_rate": 4.191868719047001e-05, "loss": 0.018, "step": 193130 }, { "epoch": 46.38, "learning_rate": 4.1914259253514455e-05, "loss": 0.0074, "step": 193140 }, { "epoch": 46.38, "learning_rate": 4.190983138167449e-05, "loss": 0.0083, "step": 193150 }, { "epoch": 46.38, "learning_rate": 4.190540357498576e-05, "loss": 0.0117, "step": 193160 }, { "epoch": 46.38, "learning_rate": 4.190097583348395e-05, "loss": 0.0038, "step": 193170 }, { "epoch": 46.38, "learning_rate": 4.1896548157204706e-05, "loss": 0.0223, "step": 193180 }, { "epoch": 46.39, "learning_rate": 4.189212054618366e-05, "loss": 0.0188, "step": 193190 }, { "epoch": 46.39, "learning_rate": 4.188769300045649e-05, "loss": 0.0212, "step": 193200 }, { "epoch": 46.39, "learning_rate": 4.1883265520058846e-05, "loss": 0.0042, "step": 193210 }, { "epoch": 46.39, "learning_rate": 4.187883810502641e-05, "loss": 0.0164, "step": 193220 }, { "epoch": 46.4, "learning_rate": 4.187441075539479e-05, "loss": 0.0258, "step": 193230 }, { "epoch": 46.4, "learning_rate": 4.1869983471199655e-05, "loss": 0.0056, "step": 193240 }, { "epoch": 46.4, "learning_rate": 4.186555625247668e-05, "loss": 0.003, "step": 193250 }, { "epoch": 46.4, "learning_rate": 4.1861129099261485e-05, "loss": 0.0128, "step": 193260 }, { "epoch": 46.4, "learning_rate": 4.185670201158978e-05, "loss": 0.0076, "step": 193270 }, { "epoch": 46.41, "learning_rate": 4.185227498949715e-05, "loss": 0.0032, "step": 193280 }, { "epoch": 46.41, "learning_rate": 4.1847848033019276e-05, "loss": 0.009, "step": 193290 }, { "epoch": 46.41, "learning_rate": 4.1843421142191804e-05, "loss": 0.0038, "step": 193300 }, { "epoch": 46.41, "learning_rate": 4.183899431705039e-05, "loss": 0.0082, "step": 193310 }, { "epoch": 46.42, "learning_rate": 4.18345675576307e-05, "loss": 0.0067, "step": 193320 }, { "epoch": 46.42, "learning_rate": 4.1830140863968335e-05, "loss": 0.0153, "step": 193330 }, { "epoch": 46.42, "learning_rate": 4.182571423609899e-05, "loss": 0.0081, "step": 193340 }, { "epoch": 46.42, "learning_rate": 4.1821287674058286e-05, "loss": 0.0071, "step": 193350 }, { "epoch": 46.43, "learning_rate": 4.18168611778819e-05, "loss": 0.011, "step": 193360 }, { "epoch": 46.43, "learning_rate": 4.1812434747605455e-05, "loss": 0.0062, "step": 193370 }, { "epoch": 46.43, "learning_rate": 4.1808008383264586e-05, "loss": 0.006, "step": 193380 }, { "epoch": 46.43, "learning_rate": 4.180358208489498e-05, "loss": 0.0152, "step": 193390 }, { "epoch": 46.43, "learning_rate": 4.179915585253223e-05, "loss": 0.0211, "step": 193400 }, { "epoch": 46.44, "learning_rate": 4.179472968621204e-05, "loss": 0.01, "step": 193410 }, { "epoch": 46.44, "learning_rate": 4.179030358597002e-05, "loss": 0.0071, "step": 193420 }, { "epoch": 46.44, "learning_rate": 4.17858775518418e-05, "loss": 0.0048, "step": 193430 }, { "epoch": 46.44, "learning_rate": 4.1781451583863055e-05, "loss": 0.0064, "step": 193440 }, { "epoch": 46.45, "learning_rate": 4.17770256820694e-05, "loss": 0.0049, "step": 193450 }, { "epoch": 46.45, "learning_rate": 4.177259984649652e-05, "loss": 0.0182, "step": 193460 }, { "epoch": 46.45, "learning_rate": 4.176817407718002e-05, "loss": 0.0338, "step": 193470 }, { "epoch": 46.45, "learning_rate": 4.176374837415554e-05, "loss": 0.0075, "step": 193480 }, { "epoch": 46.46, "learning_rate": 4.175932273745874e-05, "loss": 0.0094, "step": 193490 }, { "epoch": 46.46, "learning_rate": 4.175489716712524e-05, "loss": 0.0128, "step": 193500 }, { "epoch": 46.46, "learning_rate": 4.175047166319072e-05, "loss": 0.012, "step": 193510 }, { "epoch": 46.46, "learning_rate": 4.174604622569076e-05, "loss": 0.0058, "step": 193520 }, { "epoch": 46.46, "learning_rate": 4.174162085466104e-05, "loss": 0.016, "step": 193530 }, { "epoch": 46.47, "learning_rate": 4.173719555013719e-05, "loss": 0.0147, "step": 193540 }, { "epoch": 46.47, "learning_rate": 4.173277031215485e-05, "loss": 0.0076, "step": 193550 }, { "epoch": 46.47, "learning_rate": 4.172834514074965e-05, "loss": 0.0102, "step": 193560 }, { "epoch": 46.47, "learning_rate": 4.172392003595721e-05, "loss": 0.0082, "step": 193570 }, { "epoch": 46.48, "learning_rate": 4.1719494997813204e-05, "loss": 0.0051, "step": 193580 }, { "epoch": 46.48, "learning_rate": 4.171507002635323e-05, "loss": 0.0171, "step": 193590 }, { "epoch": 46.48, "learning_rate": 4.171064512161296e-05, "loss": 0.0109, "step": 193600 }, { "epoch": 46.48, "learning_rate": 4.1706220283628005e-05, "loss": 0.0107, "step": 193610 }, { "epoch": 46.48, "learning_rate": 4.1701795512433995e-05, "loss": 0.01, "step": 193620 }, { "epoch": 46.49, "learning_rate": 4.1697370808066575e-05, "loss": 0.0134, "step": 193630 }, { "epoch": 46.49, "learning_rate": 4.169294617056137e-05, "loss": 0.0184, "step": 193640 }, { "epoch": 46.49, "learning_rate": 4.1688521599954036e-05, "loss": 0.0189, "step": 193650 }, { "epoch": 46.49, "learning_rate": 4.168409709628017e-05, "loss": 0.0093, "step": 193660 }, { "epoch": 46.5, "learning_rate": 4.167967265957541e-05, "loss": 0.0234, "step": 193670 }, { "epoch": 46.5, "learning_rate": 4.1675248289875405e-05, "loss": 0.0105, "step": 193680 }, { "epoch": 46.5, "learning_rate": 4.167082398721579e-05, "loss": 0.0049, "step": 193690 }, { "epoch": 46.5, "learning_rate": 4.1666399751632164e-05, "loss": 0.0099, "step": 193700 }, { "epoch": 46.51, "learning_rate": 4.166197558316016e-05, "loss": 0.012, "step": 193710 }, { "epoch": 46.51, "learning_rate": 4.165755148183543e-05, "loss": 0.0117, "step": 193720 }, { "epoch": 46.51, "learning_rate": 4.165312744769358e-05, "loss": 0.0092, "step": 193730 }, { "epoch": 46.51, "learning_rate": 4.164870348077027e-05, "loss": 0.0042, "step": 193740 }, { "epoch": 46.51, "learning_rate": 4.1644279581101085e-05, "loss": 0.0051, "step": 193750 }, { "epoch": 46.52, "learning_rate": 4.1639855748721666e-05, "loss": 0.0054, "step": 193760 }, { "epoch": 46.52, "learning_rate": 4.163543198366765e-05, "loss": 0.0064, "step": 193770 }, { "epoch": 46.52, "learning_rate": 4.163100828597465e-05, "loss": 0.0039, "step": 193780 }, { "epoch": 46.52, "learning_rate": 4.162658465567831e-05, "loss": 0.0049, "step": 193790 }, { "epoch": 46.53, "learning_rate": 4.162216109281424e-05, "loss": 0.0081, "step": 193800 }, { "epoch": 46.53, "learning_rate": 4.161773759741804e-05, "loss": 0.0055, "step": 193810 }, { "epoch": 46.53, "learning_rate": 4.161331416952537e-05, "loss": 0.0055, "step": 193820 }, { "epoch": 46.53, "learning_rate": 4.1608890809171835e-05, "loss": 0.0083, "step": 193830 }, { "epoch": 46.54, "learning_rate": 4.1604467516393075e-05, "loss": 0.0201, "step": 193840 }, { "epoch": 46.54, "learning_rate": 4.1600044291224695e-05, "loss": 0.0109, "step": 193850 }, { "epoch": 46.54, "learning_rate": 4.1595621133702304e-05, "loss": 0.0099, "step": 193860 }, { "epoch": 46.54, "learning_rate": 4.159119804386154e-05, "loss": 0.0073, "step": 193870 }, { "epoch": 46.54, "learning_rate": 4.1586775021738035e-05, "loss": 0.0132, "step": 193880 }, { "epoch": 46.55, "learning_rate": 4.158235206736737e-05, "loss": 0.0183, "step": 193890 }, { "epoch": 46.55, "learning_rate": 4.1577929180785196e-05, "loss": 0.0115, "step": 193900 }, { "epoch": 46.55, "learning_rate": 4.157350636202711e-05, "loss": 0.0195, "step": 193910 }, { "epoch": 46.55, "learning_rate": 4.156908361112876e-05, "loss": 0.0059, "step": 193920 }, { "epoch": 46.56, "learning_rate": 4.156466092812574e-05, "loss": 0.0112, "step": 193930 }, { "epoch": 46.56, "learning_rate": 4.1560238313053666e-05, "loss": 0.0069, "step": 193940 }, { "epoch": 46.56, "learning_rate": 4.155581576594815e-05, "loss": 0.0153, "step": 193950 }, { "epoch": 46.56, "learning_rate": 4.155139328684482e-05, "loss": 0.0215, "step": 193960 }, { "epoch": 46.56, "learning_rate": 4.1546970875779286e-05, "loss": 0.0316, "step": 193970 }, { "epoch": 46.57, "learning_rate": 4.1542548532787175e-05, "loss": 0.0071, "step": 193980 }, { "epoch": 46.57, "learning_rate": 4.153812625790408e-05, "loss": 0.0132, "step": 193990 }, { "epoch": 46.57, "learning_rate": 4.153370405116561e-05, "loss": 0.0249, "step": 194000 }, { "epoch": 46.57, "learning_rate": 4.15292819126074e-05, "loss": 0.0075, "step": 194010 }, { "epoch": 46.58, "learning_rate": 4.152485984226507e-05, "loss": 0.0173, "step": 194020 }, { "epoch": 46.58, "learning_rate": 4.152043784017419e-05, "loss": 0.0166, "step": 194030 }, { "epoch": 46.58, "learning_rate": 4.15160159063704e-05, "loss": 0.0065, "step": 194040 }, { "epoch": 46.58, "learning_rate": 4.15115940408893e-05, "loss": 0.023, "step": 194050 }, { "epoch": 46.59, "learning_rate": 4.150717224376651e-05, "loss": 0.0136, "step": 194060 }, { "epoch": 46.59, "learning_rate": 4.150275051503765e-05, "loss": 0.0181, "step": 194070 }, { "epoch": 46.59, "learning_rate": 4.149832885473829e-05, "loss": 0.0101, "step": 194080 }, { "epoch": 46.59, "learning_rate": 4.149390726290408e-05, "loss": 0.006, "step": 194090 }, { "epoch": 46.59, "learning_rate": 4.1489485739570584e-05, "loss": 0.0088, "step": 194100 }, { "epoch": 46.6, "learning_rate": 4.148506428477345e-05, "loss": 0.0079, "step": 194110 }, { "epoch": 46.6, "learning_rate": 4.1480642898548284e-05, "loss": 0.0037, "step": 194120 }, { "epoch": 46.6, "learning_rate": 4.147622158093066e-05, "loss": 0.0099, "step": 194130 }, { "epoch": 46.6, "learning_rate": 4.14718003319562e-05, "loss": 0.0052, "step": 194140 }, { "epoch": 46.61, "learning_rate": 4.1467379151660515e-05, "loss": 0.0237, "step": 194150 }, { "epoch": 46.61, "learning_rate": 4.1462958040079184e-05, "loss": 0.0055, "step": 194160 }, { "epoch": 46.61, "learning_rate": 4.1458536997247865e-05, "loss": 0.0068, "step": 194170 }, { "epoch": 46.61, "learning_rate": 4.145411602320211e-05, "loss": 0.0058, "step": 194180 }, { "epoch": 46.62, "learning_rate": 4.1449695117977524e-05, "loss": 0.0243, "step": 194190 }, { "epoch": 46.62, "learning_rate": 4.144527428160974e-05, "loss": 0.0163, "step": 194200 }, { "epoch": 46.62, "learning_rate": 4.144085351413435e-05, "loss": 0.0251, "step": 194210 }, { "epoch": 46.62, "learning_rate": 4.143643281558693e-05, "loss": 0.0109, "step": 194220 }, { "epoch": 46.62, "learning_rate": 4.143201218600311e-05, "loss": 0.0085, "step": 194230 }, { "epoch": 46.63, "learning_rate": 4.142759162541847e-05, "loss": 0.0779, "step": 194240 }, { "epoch": 46.63, "learning_rate": 4.1423171133868625e-05, "loss": 0.0102, "step": 194250 }, { "epoch": 46.63, "learning_rate": 4.141875071138918e-05, "loss": 0.0044, "step": 194260 }, { "epoch": 46.63, "learning_rate": 4.14143303580157e-05, "loss": 0.0315, "step": 194270 }, { "epoch": 46.64, "learning_rate": 4.1409910073783805e-05, "loss": 0.004, "step": 194280 }, { "epoch": 46.64, "learning_rate": 4.140548985872909e-05, "loss": 0.017, "step": 194290 }, { "epoch": 46.64, "learning_rate": 4.140106971288716e-05, "loss": 0.0076, "step": 194300 }, { "epoch": 46.64, "learning_rate": 4.139664963629361e-05, "loss": 0.0133, "step": 194310 }, { "epoch": 46.64, "learning_rate": 4.1392229628984006e-05, "loss": 0.0092, "step": 194320 }, { "epoch": 46.65, "learning_rate": 4.1387809690993976e-05, "loss": 0.0065, "step": 194330 }, { "epoch": 46.65, "learning_rate": 4.13833898223591e-05, "loss": 0.0119, "step": 194340 }, { "epoch": 46.65, "learning_rate": 4.137897002311498e-05, "loss": 0.0113, "step": 194350 }, { "epoch": 46.65, "learning_rate": 4.137455029329722e-05, "loss": 0.0127, "step": 194360 }, { "epoch": 46.66, "learning_rate": 4.137013063294138e-05, "loss": 0.0091, "step": 194370 }, { "epoch": 46.66, "learning_rate": 4.136571104208306e-05, "loss": 0.0162, "step": 194380 }, { "epoch": 46.66, "learning_rate": 4.136129152075787e-05, "loss": 0.0096, "step": 194390 }, { "epoch": 46.66, "learning_rate": 4.135687206900141e-05, "loss": 0.0048, "step": 194400 }, { "epoch": 46.67, "learning_rate": 4.135245268684923e-05, "loss": 0.0118, "step": 194410 }, { "epoch": 46.67, "learning_rate": 4.134803337433695e-05, "loss": 0.0059, "step": 194420 }, { "epoch": 46.67, "learning_rate": 4.1343614131500144e-05, "loss": 0.0202, "step": 194430 }, { "epoch": 46.67, "learning_rate": 4.1339194958374414e-05, "loss": 0.0115, "step": 194440 }, { "epoch": 46.67, "learning_rate": 4.1334775854995356e-05, "loss": 0.0067, "step": 194450 }, { "epoch": 46.68, "learning_rate": 4.133035682139852e-05, "loss": 0.0105, "step": 194460 }, { "epoch": 46.68, "learning_rate": 4.1325937857619536e-05, "loss": 0.0073, "step": 194470 }, { "epoch": 46.68, "learning_rate": 4.132151896369395e-05, "loss": 0.0194, "step": 194480 }, { "epoch": 46.68, "learning_rate": 4.131710013965739e-05, "loss": 0.0159, "step": 194490 }, { "epoch": 46.69, "learning_rate": 4.1312681385545426e-05, "loss": 0.0065, "step": 194500 }, { "epoch": 46.69, "learning_rate": 4.130826270139362e-05, "loss": 0.022, "step": 194510 }, { "epoch": 46.69, "learning_rate": 4.1303844087237586e-05, "loss": 0.008, "step": 194520 }, { "epoch": 46.69, "learning_rate": 4.1299425543112885e-05, "loss": 0.0082, "step": 194530 }, { "epoch": 46.7, "learning_rate": 4.1295007069055136e-05, "loss": 0.023, "step": 194540 }, { "epoch": 46.7, "learning_rate": 4.129058866509988e-05, "loss": 0.0136, "step": 194550 }, { "epoch": 46.7, "learning_rate": 4.128617033128271e-05, "loss": 0.0046, "step": 194560 }, { "epoch": 46.7, "learning_rate": 4.128175206763922e-05, "loss": 0.0118, "step": 194570 }, { "epoch": 46.7, "learning_rate": 4.127733387420498e-05, "loss": 0.0095, "step": 194580 }, { "epoch": 46.71, "learning_rate": 4.127291575101559e-05, "loss": 0.0276, "step": 194590 }, { "epoch": 46.71, "learning_rate": 4.12684976981066e-05, "loss": 0.0087, "step": 194600 }, { "epoch": 46.71, "learning_rate": 4.1264079715513606e-05, "loss": 0.0084, "step": 194610 }, { "epoch": 46.71, "learning_rate": 4.1259661803272177e-05, "loss": 0.005, "step": 194620 }, { "epoch": 46.72, "learning_rate": 4.1255243961417905e-05, "loss": 0.0134, "step": 194630 }, { "epoch": 46.72, "learning_rate": 4.125082618998637e-05, "loss": 0.0083, "step": 194640 }, { "epoch": 46.72, "learning_rate": 4.124640848901313e-05, "loss": 0.0121, "step": 194650 }, { "epoch": 46.72, "learning_rate": 4.1241990858533766e-05, "loss": 0.0056, "step": 194660 }, { "epoch": 46.72, "learning_rate": 4.1237573298583856e-05, "loss": 0.007, "step": 194670 }, { "epoch": 46.73, "learning_rate": 4.1233155809198995e-05, "loss": 0.0094, "step": 194680 }, { "epoch": 46.73, "learning_rate": 4.122873839041474e-05, "loss": 0.0049, "step": 194690 }, { "epoch": 46.73, "learning_rate": 4.122432104226665e-05, "loss": 0.0087, "step": 194700 }, { "epoch": 46.73, "learning_rate": 4.121990376479033e-05, "loss": 0.0059, "step": 194710 }, { "epoch": 46.74, "learning_rate": 4.1215486558021315e-05, "loss": 0.0117, "step": 194720 }, { "epoch": 46.74, "learning_rate": 4.121106942199523e-05, "loss": 0.0078, "step": 194730 }, { "epoch": 46.74, "learning_rate": 4.12066523567476e-05, "loss": 0.013, "step": 194740 }, { "epoch": 46.74, "learning_rate": 4.1202235362314e-05, "loss": 0.02, "step": 194750 }, { "epoch": 46.75, "learning_rate": 4.119781843873003e-05, "loss": 0.0135, "step": 194760 }, { "epoch": 46.75, "learning_rate": 4.1193401586031224e-05, "loss": 0.0182, "step": 194770 }, { "epoch": 46.75, "learning_rate": 4.1188984804253214e-05, "loss": 0.0065, "step": 194780 }, { "epoch": 46.75, "learning_rate": 4.1184568093431486e-05, "loss": 0.0064, "step": 194790 }, { "epoch": 46.75, "learning_rate": 4.118015145360166e-05, "loss": 0.0033, "step": 194800 }, { "epoch": 46.76, "learning_rate": 4.1175734884799286e-05, "loss": 0.0214, "step": 194810 }, { "epoch": 46.76, "learning_rate": 4.1171318387059944e-05, "loss": 0.012, "step": 194820 }, { "epoch": 46.76, "learning_rate": 4.116690196041921e-05, "loss": 0.0276, "step": 194830 }, { "epoch": 46.76, "learning_rate": 4.11624856049126e-05, "loss": 0.0071, "step": 194840 }, { "epoch": 46.77, "learning_rate": 4.1158069320575736e-05, "loss": 0.0048, "step": 194850 }, { "epoch": 46.77, "learning_rate": 4.115365310744415e-05, "loss": 0.0117, "step": 194860 }, { "epoch": 46.77, "learning_rate": 4.114923696555343e-05, "loss": 0.0131, "step": 194870 }, { "epoch": 46.77, "learning_rate": 4.1144820894939126e-05, "loss": 0.0117, "step": 194880 }, { "epoch": 46.78, "learning_rate": 4.114040489563678e-05, "loss": 0.0062, "step": 194890 }, { "epoch": 46.78, "learning_rate": 4.113598896768199e-05, "loss": 0.0093, "step": 194900 }, { "epoch": 46.78, "learning_rate": 4.11315731111103e-05, "loss": 0.0067, "step": 194910 }, { "epoch": 46.78, "learning_rate": 4.1127157325957296e-05, "loss": 0.006, "step": 194920 }, { "epoch": 46.78, "learning_rate": 4.1122741612258505e-05, "loss": 0.0047, "step": 194930 }, { "epoch": 46.79, "learning_rate": 4.111832597004949e-05, "loss": 0.0075, "step": 194940 }, { "epoch": 46.79, "learning_rate": 4.1113910399365837e-05, "loss": 0.0106, "step": 194950 }, { "epoch": 46.79, "learning_rate": 4.1109494900243076e-05, "loss": 0.0041, "step": 194960 }, { "epoch": 46.79, "learning_rate": 4.11050794727168e-05, "loss": 0.006, "step": 194970 }, { "epoch": 46.8, "learning_rate": 4.110066411682254e-05, "loss": 0.0146, "step": 194980 }, { "epoch": 46.8, "learning_rate": 4.109624883259585e-05, "loss": 0.0069, "step": 194990 }, { "epoch": 46.8, "learning_rate": 4.109183362007231e-05, "loss": 0.0229, "step": 195000 }, { "epoch": 46.8, "learning_rate": 4.108741847928746e-05, "loss": 0.0052, "step": 195010 }, { "epoch": 46.8, "learning_rate": 4.108300341027687e-05, "loss": 0.0081, "step": 195020 }, { "epoch": 46.81, "learning_rate": 4.107858841307607e-05, "loss": 0.0075, "step": 195030 }, { "epoch": 46.81, "learning_rate": 4.107417348772063e-05, "loss": 0.0061, "step": 195040 }, { "epoch": 46.81, "learning_rate": 4.10697586342461e-05, "loss": 0.0128, "step": 195050 }, { "epoch": 46.81, "learning_rate": 4.106534385268806e-05, "loss": 0.0079, "step": 195060 }, { "epoch": 46.82, "learning_rate": 4.1060929143082016e-05, "loss": 0.0094, "step": 195070 }, { "epoch": 46.82, "learning_rate": 4.105651450546354e-05, "loss": 0.0115, "step": 195080 }, { "epoch": 46.82, "learning_rate": 4.10520999398682e-05, "loss": 0.0086, "step": 195090 }, { "epoch": 46.82, "learning_rate": 4.104768544633152e-05, "loss": 0.0115, "step": 195100 }, { "epoch": 46.83, "learning_rate": 4.104327102488908e-05, "loss": 0.0078, "step": 195110 }, { "epoch": 46.83, "learning_rate": 4.103885667557642e-05, "loss": 0.0086, "step": 195120 }, { "epoch": 46.83, "learning_rate": 4.103444239842907e-05, "loss": 0.0129, "step": 195130 }, { "epoch": 46.83, "learning_rate": 4.10300281934826e-05, "loss": 0.0099, "step": 195140 }, { "epoch": 46.83, "learning_rate": 4.102561406077254e-05, "loss": 0.0132, "step": 195150 }, { "epoch": 46.84, "learning_rate": 4.102120000033447e-05, "loss": 0.0085, "step": 195160 }, { "epoch": 46.84, "learning_rate": 4.1016786012203914e-05, "loss": 0.016, "step": 195170 }, { "epoch": 46.84, "learning_rate": 4.1012372096416396e-05, "loss": 0.0047, "step": 195180 }, { "epoch": 46.84, "learning_rate": 4.1007958253007504e-05, "loss": 0.0052, "step": 195190 }, { "epoch": 46.85, "learning_rate": 4.100354448201278e-05, "loss": 0.0098, "step": 195200 }, { "epoch": 46.85, "learning_rate": 4.099913078346774e-05, "loss": 0.0038, "step": 195210 }, { "epoch": 46.85, "learning_rate": 4.099471715740792e-05, "loss": 0.0068, "step": 195220 }, { "epoch": 46.85, "learning_rate": 4.099030360386892e-05, "loss": 0.0057, "step": 195230 }, { "epoch": 46.86, "learning_rate": 4.098589012288622e-05, "loss": 0.0062, "step": 195240 }, { "epoch": 46.86, "learning_rate": 4.098147671449542e-05, "loss": 0.0123, "step": 195250 }, { "epoch": 46.86, "learning_rate": 4.097706337873202e-05, "loss": 0.0088, "step": 195260 }, { "epoch": 46.86, "learning_rate": 4.097265011563157e-05, "loss": 0.0149, "step": 195270 }, { "epoch": 46.86, "learning_rate": 4.0968236925229616e-05, "loss": 0.0083, "step": 195280 }, { "epoch": 46.87, "learning_rate": 4.096382380756169e-05, "loss": 0.0292, "step": 195290 }, { "epoch": 46.87, "learning_rate": 4.0959410762663363e-05, "loss": 0.0051, "step": 195300 }, { "epoch": 46.87, "learning_rate": 4.095499779057014e-05, "loss": 0.0075, "step": 195310 }, { "epoch": 46.87, "learning_rate": 4.095058489131755e-05, "loss": 0.0084, "step": 195320 }, { "epoch": 46.88, "learning_rate": 4.0946172064941163e-05, "loss": 0.0047, "step": 195330 }, { "epoch": 46.88, "learning_rate": 4.094175931147649e-05, "loss": 0.0073, "step": 195340 }, { "epoch": 46.88, "learning_rate": 4.093734663095911e-05, "loss": 0.009, "step": 195350 }, { "epoch": 46.88, "learning_rate": 4.093293402342451e-05, "loss": 0.0056, "step": 195360 }, { "epoch": 46.88, "learning_rate": 4.0928521488908234e-05, "loss": 0.0096, "step": 195370 }, { "epoch": 46.89, "learning_rate": 4.092410902744584e-05, "loss": 0.0084, "step": 195380 }, { "epoch": 46.89, "learning_rate": 4.091969663907286e-05, "loss": 0.0182, "step": 195390 }, { "epoch": 46.89, "learning_rate": 4.0915284323824796e-05, "loss": 0.0179, "step": 195400 }, { "epoch": 46.89, "learning_rate": 4.091087208173721e-05, "loss": 0.0096, "step": 195410 }, { "epoch": 46.9, "learning_rate": 4.0906459912845605e-05, "loss": 0.0037, "step": 195420 }, { "epoch": 46.9, "learning_rate": 4.0902047817185564e-05, "loss": 0.0084, "step": 195430 }, { "epoch": 46.9, "learning_rate": 4.0897635794792585e-05, "loss": 0.0099, "step": 195440 }, { "epoch": 46.9, "learning_rate": 4.08932238457022e-05, "loss": 0.0056, "step": 195450 }, { "epoch": 46.91, "learning_rate": 4.088881196994992e-05, "loss": 0.0122, "step": 195460 }, { "epoch": 46.91, "learning_rate": 4.088440016757131e-05, "loss": 0.0108, "step": 195470 }, { "epoch": 46.91, "learning_rate": 4.087998843860188e-05, "loss": 0.0079, "step": 195480 }, { "epoch": 46.91, "learning_rate": 4.0875576783077175e-05, "loss": 0.0292, "step": 195490 }, { "epoch": 46.91, "learning_rate": 4.08711652010327e-05, "loss": 0.0047, "step": 195500 }, { "epoch": 46.92, "learning_rate": 4.086675369250398e-05, "loss": 0.0044, "step": 195510 }, { "epoch": 46.92, "learning_rate": 4.086234225752657e-05, "loss": 0.0055, "step": 195520 }, { "epoch": 46.92, "learning_rate": 4.0857930896135985e-05, "loss": 0.0042, "step": 195530 }, { "epoch": 46.92, "learning_rate": 4.085351960836773e-05, "loss": 0.0192, "step": 195540 }, { "epoch": 46.93, "learning_rate": 4.084910839425735e-05, "loss": 0.0049, "step": 195550 }, { "epoch": 46.93, "learning_rate": 4.0844697253840355e-05, "loss": 0.0078, "step": 195560 }, { "epoch": 46.93, "learning_rate": 4.0840286187152286e-05, "loss": 0.0064, "step": 195570 }, { "epoch": 46.93, "learning_rate": 4.0835875194228664e-05, "loss": 0.0167, "step": 195580 }, { "epoch": 46.94, "learning_rate": 4.083146427510499e-05, "loss": 0.0072, "step": 195590 }, { "epoch": 46.94, "learning_rate": 4.0827053429816805e-05, "loss": 0.0188, "step": 195600 }, { "epoch": 46.94, "learning_rate": 4.082264265839962e-05, "loss": 0.0058, "step": 195610 }, { "epoch": 46.94, "learning_rate": 4.081823196088896e-05, "loss": 0.0091, "step": 195620 }, { "epoch": 46.94, "learning_rate": 4.081382133732037e-05, "loss": 0.0193, "step": 195630 }, { "epoch": 46.95, "learning_rate": 4.080941078772933e-05, "loss": 0.0083, "step": 195640 }, { "epoch": 46.95, "learning_rate": 4.0805000312151367e-05, "loss": 0.0085, "step": 195650 }, { "epoch": 46.95, "learning_rate": 4.080058991062201e-05, "loss": 0.0085, "step": 195660 }, { "epoch": 47.0, "learning_rate": 4.079617958317676e-05, "loss": 0.0076, "step": 195670 }, { "epoch": 47.0, "learning_rate": 4.079176932985117e-05, "loss": 0.0049, "step": 195680 }, { "epoch": 47.01, "learning_rate": 4.078735915068073e-05, "loss": 0.0105, "step": 195690 }, { "epoch": 47.01, "learning_rate": 4.078294904570094e-05, "loss": 0.0108, "step": 195700 }, { "epoch": 47.01, "learning_rate": 4.077853901494734e-05, "loss": 0.0049, "step": 195710 }, { "epoch": 47.01, "learning_rate": 4.077412905845546e-05, "loss": 0.0041, "step": 195720 }, { "epoch": 47.02, "learning_rate": 4.076971917626076e-05, "loss": 0.0023, "step": 195730 }, { "epoch": 47.02, "learning_rate": 4.0765309368398805e-05, "loss": 0.0114, "step": 195740 }, { "epoch": 47.02, "learning_rate": 4.0760899634905074e-05, "loss": 0.007, "step": 195750 }, { "epoch": 47.02, "learning_rate": 4.07564899758151e-05, "loss": 0.0084, "step": 195760 }, { "epoch": 47.02, "learning_rate": 4.075208039116441e-05, "loss": 0.0055, "step": 195770 }, { "epoch": 47.03, "learning_rate": 4.0747670880988466e-05, "loss": 0.0139, "step": 195780 }, { "epoch": 47.03, "learning_rate": 4.0743261445322815e-05, "loss": 0.0143, "step": 195790 }, { "epoch": 47.03, "learning_rate": 4.073885208420295e-05, "loss": 0.0063, "step": 195800 }, { "epoch": 47.03, "learning_rate": 4.07344427976644e-05, "loss": 0.0153, "step": 195810 }, { "epoch": 47.04, "learning_rate": 4.0730033585742665e-05, "loss": 0.0259, "step": 195820 }, { "epoch": 47.04, "learning_rate": 4.0725624448473236e-05, "loss": 0.0119, "step": 195830 }, { "epoch": 47.04, "learning_rate": 4.072121538589164e-05, "loss": 0.0114, "step": 195840 }, { "epoch": 47.04, "learning_rate": 4.071680639803337e-05, "loss": 0.0069, "step": 195850 }, { "epoch": 47.05, "learning_rate": 4.071239748493397e-05, "loss": 0.0177, "step": 195860 }, { "epoch": 47.05, "learning_rate": 4.070798864662888e-05, "loss": 0.0071, "step": 195870 }, { "epoch": 47.05, "learning_rate": 4.0703579883153655e-05, "loss": 0.0286, "step": 195880 }, { "epoch": 47.05, "learning_rate": 4.0699171194543775e-05, "loss": 0.0076, "step": 195890 }, { "epoch": 47.05, "learning_rate": 4.069476258083476e-05, "loss": 0.0091, "step": 195900 }, { "epoch": 47.06, "learning_rate": 4.069035404206212e-05, "loss": 0.0056, "step": 195910 }, { "epoch": 47.06, "learning_rate": 4.068594557826132e-05, "loss": 0.0038, "step": 195920 }, { "epoch": 47.06, "learning_rate": 4.06815371894679e-05, "loss": 0.0075, "step": 195930 }, { "epoch": 47.06, "learning_rate": 4.067712887571733e-05, "loss": 0.0068, "step": 195940 }, { "epoch": 47.07, "learning_rate": 4.067272063704515e-05, "loss": 0.0101, "step": 195950 }, { "epoch": 47.07, "learning_rate": 4.066831247348684e-05, "loss": 0.0067, "step": 195960 }, { "epoch": 47.07, "learning_rate": 4.066390438507788e-05, "loss": 0.0167, "step": 195970 }, { "epoch": 47.07, "learning_rate": 4.06594963718538e-05, "loss": 0.0084, "step": 195980 }, { "epoch": 47.08, "learning_rate": 4.0655088433850076e-05, "loss": 0.0098, "step": 195990 }, { "epoch": 47.08, "learning_rate": 4.065068057110222e-05, "loss": 0.005, "step": 196000 }, { "epoch": 47.08, "learning_rate": 4.064627278364573e-05, "loss": 0.0051, "step": 196010 }, { "epoch": 47.08, "learning_rate": 4.064186507151609e-05, "loss": 0.0086, "step": 196020 }, { "epoch": 47.08, "learning_rate": 4.06374574347488e-05, "loss": 0.017, "step": 196030 }, { "epoch": 47.09, "learning_rate": 4.063304987337936e-05, "loss": 0.0116, "step": 196040 }, { "epoch": 47.09, "learning_rate": 4.0628642387443286e-05, "loss": 0.009, "step": 196050 }, { "epoch": 47.09, "learning_rate": 4.062423497697602e-05, "loss": 0.0065, "step": 196060 }, { "epoch": 47.09, "learning_rate": 4.061982764201309e-05, "loss": 0.0138, "step": 196070 }, { "epoch": 47.1, "learning_rate": 4.0615420382589975e-05, "loss": 0.0136, "step": 196080 }, { "epoch": 47.1, "learning_rate": 4.061101319874218e-05, "loss": 0.0037, "step": 196090 }, { "epoch": 47.1, "learning_rate": 4.0606606090505214e-05, "loss": 0.0117, "step": 196100 }, { "epoch": 47.1, "learning_rate": 4.0602199057914515e-05, "loss": 0.004, "step": 196110 }, { "epoch": 47.1, "learning_rate": 4.059779210100562e-05, "loss": 0.01, "step": 196120 }, { "epoch": 47.11, "learning_rate": 4.0593385219814e-05, "loss": 0.0068, "step": 196130 }, { "epoch": 47.11, "learning_rate": 4.0588978414375145e-05, "loss": 0.0116, "step": 196140 }, { "epoch": 47.11, "learning_rate": 4.058457168472456e-05, "loss": 0.0058, "step": 196150 }, { "epoch": 47.11, "learning_rate": 4.05801650308977e-05, "loss": 0.0045, "step": 196160 }, { "epoch": 47.12, "learning_rate": 4.0575758452930076e-05, "loss": 0.0066, "step": 196170 }, { "epoch": 47.12, "learning_rate": 4.057135195085717e-05, "loss": 0.0245, "step": 196180 }, { "epoch": 47.12, "learning_rate": 4.0566945524714484e-05, "loss": 0.0168, "step": 196190 }, { "epoch": 47.12, "learning_rate": 4.056253917453748e-05, "loss": 0.007, "step": 196200 }, { "epoch": 47.13, "learning_rate": 4.0558132900361635e-05, "loss": 0.0043, "step": 196210 }, { "epoch": 47.13, "learning_rate": 4.055372670222247e-05, "loss": 0.0146, "step": 196220 }, { "epoch": 47.13, "learning_rate": 4.054932058015543e-05, "loss": 0.0054, "step": 196230 }, { "epoch": 47.13, "learning_rate": 4.054491453419603e-05, "loss": 0.0057, "step": 196240 }, { "epoch": 47.13, "learning_rate": 4.0540508564379745e-05, "loss": 0.0062, "step": 196250 }, { "epoch": 47.14, "learning_rate": 4.0536102670742025e-05, "loss": 0.0113, "step": 196260 }, { "epoch": 47.14, "learning_rate": 4.05316968533184e-05, "loss": 0.0031, "step": 196270 }, { "epoch": 47.14, "learning_rate": 4.0527291112144305e-05, "loss": 0.0174, "step": 196280 }, { "epoch": 47.14, "learning_rate": 4.052288544725528e-05, "loss": 0.008, "step": 196290 }, { "epoch": 47.15, "learning_rate": 4.0518479858686736e-05, "loss": 0.0126, "step": 196300 }, { "epoch": 47.15, "learning_rate": 4.051407434647419e-05, "loss": 0.0083, "step": 196310 }, { "epoch": 47.15, "learning_rate": 4.0509668910653106e-05, "loss": 0.0083, "step": 196320 }, { "epoch": 47.15, "learning_rate": 4.0505263551258975e-05, "loss": 0.0131, "step": 196330 }, { "epoch": 47.16, "learning_rate": 4.050085826832729e-05, "loss": 0.0102, "step": 196340 }, { "epoch": 47.16, "learning_rate": 4.049645306189347e-05, "loss": 0.0151, "step": 196350 }, { "epoch": 47.16, "learning_rate": 4.0492047931993035e-05, "loss": 0.0142, "step": 196360 }, { "epoch": 47.16, "learning_rate": 4.0487642878661445e-05, "loss": 0.0085, "step": 196370 }, { "epoch": 47.16, "learning_rate": 4.048323790193421e-05, "loss": 0.0096, "step": 196380 }, { "epoch": 47.17, "learning_rate": 4.047883300184675e-05, "loss": 0.0115, "step": 196390 }, { "epoch": 47.17, "learning_rate": 4.0474428178434554e-05, "loss": 0.0101, "step": 196400 }, { "epoch": 47.17, "learning_rate": 4.047002343173312e-05, "loss": 0.0051, "step": 196410 }, { "epoch": 47.17, "learning_rate": 4.046561876177789e-05, "loss": 0.0065, "step": 196420 }, { "epoch": 47.18, "learning_rate": 4.0461214168604364e-05, "loss": 0.02, "step": 196430 }, { "epoch": 47.18, "learning_rate": 4.0456809652248e-05, "loss": 0.0093, "step": 196440 }, { "epoch": 47.18, "learning_rate": 4.045240521274424e-05, "loss": 0.0082, "step": 196450 }, { "epoch": 47.18, "learning_rate": 4.044800085012859e-05, "loss": 0.0093, "step": 196460 }, { "epoch": 47.18, "learning_rate": 4.04435965644365e-05, "loss": 0.0133, "step": 196470 }, { "epoch": 47.19, "learning_rate": 4.043919235570348e-05, "loss": 0.0144, "step": 196480 }, { "epoch": 47.19, "learning_rate": 4.043478822396494e-05, "loss": 0.0052, "step": 196490 }, { "epoch": 47.19, "learning_rate": 4.0430384169256375e-05, "loss": 0.0203, "step": 196500 }, { "epoch": 47.19, "learning_rate": 4.042598019161323e-05, "loss": 0.0054, "step": 196510 }, { "epoch": 47.2, "learning_rate": 4.042157629107102e-05, "loss": 0.0157, "step": 196520 }, { "epoch": 47.2, "learning_rate": 4.0417172467665166e-05, "loss": 0.0075, "step": 196530 }, { "epoch": 47.2, "learning_rate": 4.0412768721431134e-05, "loss": 0.0112, "step": 196540 }, { "epoch": 47.2, "learning_rate": 4.0408365052404406e-05, "loss": 0.0037, "step": 196550 }, { "epoch": 47.21, "learning_rate": 4.040396146062043e-05, "loss": 0.0039, "step": 196560 }, { "epoch": 47.21, "learning_rate": 4.0399557946114695e-05, "loss": 0.0059, "step": 196570 }, { "epoch": 47.21, "learning_rate": 4.039515450892264e-05, "loss": 0.0178, "step": 196580 }, { "epoch": 47.21, "learning_rate": 4.039075114907972e-05, "loss": 0.0074, "step": 196590 }, { "epoch": 47.21, "learning_rate": 4.0386347866621416e-05, "loss": 0.008, "step": 196600 }, { "epoch": 47.22, "learning_rate": 4.038194466158317e-05, "loss": 0.0038, "step": 196610 }, { "epoch": 47.22, "learning_rate": 4.037754153400047e-05, "loss": 0.0108, "step": 196620 }, { "epoch": 47.22, "learning_rate": 4.037313848390875e-05, "loss": 0.012, "step": 196630 }, { "epoch": 47.22, "learning_rate": 4.0368735511343464e-05, "loss": 0.0115, "step": 196640 }, { "epoch": 47.23, "learning_rate": 4.036433261634009e-05, "loss": 0.0044, "step": 196650 }, { "epoch": 47.23, "learning_rate": 4.0359929798934065e-05, "loss": 0.0095, "step": 196660 }, { "epoch": 47.23, "learning_rate": 4.035552705916088e-05, "loss": 0.0051, "step": 196670 }, { "epoch": 47.23, "learning_rate": 4.035112439705595e-05, "loss": 0.0079, "step": 196680 }, { "epoch": 47.24, "learning_rate": 4.034672181265474e-05, "loss": 0.008, "step": 196690 }, { "epoch": 47.24, "learning_rate": 4.0342319305992726e-05, "loss": 0.0112, "step": 196700 }, { "epoch": 47.24, "learning_rate": 4.033791687710536e-05, "loss": 0.0038, "step": 196710 }, { "epoch": 47.24, "learning_rate": 4.033351452602807e-05, "loss": 0.0063, "step": 196720 }, { "epoch": 47.24, "learning_rate": 4.032911225279631e-05, "loss": 0.0052, "step": 196730 }, { "epoch": 47.25, "learning_rate": 4.0324710057445555e-05, "loss": 0.0072, "step": 196740 }, { "epoch": 47.25, "learning_rate": 4.032030794001124e-05, "loss": 0.0067, "step": 196750 }, { "epoch": 47.25, "learning_rate": 4.0315905900528836e-05, "loss": 0.0061, "step": 196760 }, { "epoch": 47.25, "learning_rate": 4.0311503939033766e-05, "loss": 0.0092, "step": 196770 }, { "epoch": 47.26, "learning_rate": 4.030710205556148e-05, "loss": 0.0055, "step": 196780 }, { "epoch": 47.26, "learning_rate": 4.030270025014746e-05, "loss": 0.0086, "step": 196790 }, { "epoch": 47.26, "learning_rate": 4.0298298522827124e-05, "loss": 0.0396, "step": 196800 }, { "epoch": 47.26, "learning_rate": 4.029389687363595e-05, "loss": 0.0113, "step": 196810 }, { "epoch": 47.26, "learning_rate": 4.0289495302609345e-05, "loss": 0.0086, "step": 196820 }, { "epoch": 47.27, "learning_rate": 4.028509380978276e-05, "loss": 0.0037, "step": 196830 }, { "epoch": 47.27, "learning_rate": 4.0280692395191685e-05, "loss": 0.0104, "step": 196840 }, { "epoch": 47.27, "learning_rate": 4.0276291058871536e-05, "loss": 0.0164, "step": 196850 }, { "epoch": 47.27, "learning_rate": 4.027188980085773e-05, "loss": 0.0113, "step": 196860 }, { "epoch": 47.28, "learning_rate": 4.026748862118576e-05, "loss": 0.0148, "step": 196870 }, { "epoch": 47.28, "learning_rate": 4.026308751989104e-05, "loss": 0.0095, "step": 196880 }, { "epoch": 47.28, "learning_rate": 4.025868649700902e-05, "loss": 0.0107, "step": 196890 }, { "epoch": 47.28, "learning_rate": 4.0254285552575154e-05, "loss": 0.0059, "step": 196900 }, { "epoch": 47.29, "learning_rate": 4.0249884686624855e-05, "loss": 0.0037, "step": 196910 }, { "epoch": 47.29, "learning_rate": 4.0245483899193595e-05, "loss": 0.0084, "step": 196920 }, { "epoch": 47.29, "learning_rate": 4.0241083190316794e-05, "loss": 0.0181, "step": 196930 }, { "epoch": 47.29, "learning_rate": 4.0236682560029885e-05, "loss": 0.0127, "step": 196940 }, { "epoch": 47.29, "learning_rate": 4.023228200836834e-05, "loss": 0.0046, "step": 196950 }, { "epoch": 47.3, "learning_rate": 4.022788153536757e-05, "loss": 0.0114, "step": 196960 }, { "epoch": 47.3, "learning_rate": 4.022348114106301e-05, "loss": 0.0133, "step": 196970 }, { "epoch": 47.3, "learning_rate": 4.0219080825490116e-05, "loss": 0.0077, "step": 196980 }, { "epoch": 47.3, "learning_rate": 4.0214680588684305e-05, "loss": 0.0085, "step": 196990 }, { "epoch": 47.31, "learning_rate": 4.021028043068104e-05, "loss": 0.0085, "step": 197000 }, { "epoch": 47.31, "learning_rate": 4.020588035151573e-05, "loss": 0.0129, "step": 197010 }, { "epoch": 47.31, "learning_rate": 4.020148035122381e-05, "loss": 0.0064, "step": 197020 }, { "epoch": 47.31, "learning_rate": 4.019708042984072e-05, "loss": 0.013, "step": 197030 }, { "epoch": 47.32, "learning_rate": 4.019268058740192e-05, "loss": 0.0099, "step": 197040 }, { "epoch": 47.32, "learning_rate": 4.018828082394279e-05, "loss": 0.0093, "step": 197050 }, { "epoch": 47.32, "learning_rate": 4.018388113949879e-05, "loss": 0.0096, "step": 197060 }, { "epoch": 47.32, "learning_rate": 4.017948153410535e-05, "loss": 0.0084, "step": 197070 }, { "epoch": 47.32, "learning_rate": 4.017508200779791e-05, "loss": 0.0095, "step": 197080 }, { "epoch": 47.33, "learning_rate": 4.01706825606119e-05, "loss": 0.0051, "step": 197090 }, { "epoch": 47.33, "learning_rate": 4.016628319258273e-05, "loss": 0.0138, "step": 197100 }, { "epoch": 47.33, "learning_rate": 4.0161883903745834e-05, "loss": 0.0026, "step": 197110 }, { "epoch": 47.33, "learning_rate": 4.015748469413664e-05, "loss": 0.007, "step": 197120 }, { "epoch": 47.34, "learning_rate": 4.015308556379059e-05, "loss": 0.0064, "step": 197130 }, { "epoch": 47.34, "learning_rate": 4.014868651274312e-05, "loss": 0.0136, "step": 197140 }, { "epoch": 47.34, "learning_rate": 4.014428754102962e-05, "loss": 0.005, "step": 197150 }, { "epoch": 47.34, "learning_rate": 4.0139888648685524e-05, "loss": 0.0041, "step": 197160 }, { "epoch": 47.34, "learning_rate": 4.013548983574628e-05, "loss": 0.006, "step": 197170 }, { "epoch": 47.35, "learning_rate": 4.013109110224731e-05, "loss": 0.0028, "step": 197180 }, { "epoch": 47.35, "learning_rate": 4.0126692448224e-05, "loss": 0.0106, "step": 197190 }, { "epoch": 47.35, "learning_rate": 4.01222938737118e-05, "loss": 0.0068, "step": 197200 }, { "epoch": 47.35, "learning_rate": 4.011789537874613e-05, "loss": 0.0151, "step": 197210 }, { "epoch": 47.36, "learning_rate": 4.011349696336243e-05, "loss": 0.0109, "step": 197220 }, { "epoch": 47.36, "learning_rate": 4.0109098627596106e-05, "loss": 0.0087, "step": 197230 }, { "epoch": 47.36, "learning_rate": 4.010470037148256e-05, "loss": 0.0073, "step": 197240 }, { "epoch": 47.36, "learning_rate": 4.010030219505723e-05, "loss": 0.0124, "step": 197250 }, { "epoch": 47.37, "learning_rate": 4.009590409835553e-05, "loss": 0.0073, "step": 197260 }, { "epoch": 47.37, "learning_rate": 4.009150608141289e-05, "loss": 0.012, "step": 197270 }, { "epoch": 47.37, "learning_rate": 4.008710814426473e-05, "loss": 0.0073, "step": 197280 }, { "epoch": 47.37, "learning_rate": 4.008271028694643e-05, "loss": 0.0123, "step": 197290 }, { "epoch": 47.37, "learning_rate": 4.0078312509493453e-05, "loss": 0.0106, "step": 197300 }, { "epoch": 47.38, "learning_rate": 4.007391481194118e-05, "loss": 0.0061, "step": 197310 }, { "epoch": 47.38, "learning_rate": 4.006951719432506e-05, "loss": 0.0065, "step": 197320 }, { "epoch": 47.38, "learning_rate": 4.006511965668049e-05, "loss": 0.0095, "step": 197330 }, { "epoch": 47.38, "learning_rate": 4.0060722199042864e-05, "loss": 0.0076, "step": 197340 }, { "epoch": 47.39, "learning_rate": 4.005632482144763e-05, "loss": 0.0067, "step": 197350 }, { "epoch": 47.39, "learning_rate": 4.005192752393018e-05, "loss": 0.0177, "step": 197360 }, { "epoch": 47.39, "learning_rate": 4.004753030652594e-05, "loss": 0.0098, "step": 197370 }, { "epoch": 47.39, "learning_rate": 4.004313316927029e-05, "loss": 0.007, "step": 197380 }, { "epoch": 47.4, "learning_rate": 4.003873611219868e-05, "loss": 0.0087, "step": 197390 }, { "epoch": 47.4, "learning_rate": 4.003433913534649e-05, "loss": 0.0113, "step": 197400 }, { "epoch": 47.4, "learning_rate": 4.0029942238749154e-05, "loss": 0.0098, "step": 197410 }, { "epoch": 47.4, "learning_rate": 4.002554542244208e-05, "loss": 0.0064, "step": 197420 }, { "epoch": 47.4, "learning_rate": 4.002114868646064e-05, "loss": 0.0087, "step": 197430 }, { "epoch": 47.41, "learning_rate": 4.001675203084029e-05, "loss": 0.009, "step": 197440 }, { "epoch": 47.41, "learning_rate": 4.001235545561639e-05, "loss": 0.0219, "step": 197450 }, { "epoch": 47.41, "learning_rate": 4.000795896082439e-05, "loss": 0.0056, "step": 197460 }, { "epoch": 47.41, "learning_rate": 4.000356254649968e-05, "loss": 0.0144, "step": 197470 }, { "epoch": 47.42, "learning_rate": 3.999916621267765e-05, "loss": 0.0069, "step": 197480 }, { "epoch": 47.42, "learning_rate": 3.999476995939371e-05, "loss": 0.0085, "step": 197490 }, { "epoch": 47.42, "learning_rate": 3.9990373786683275e-05, "loss": 0.0073, "step": 197500 }, { "epoch": 47.42, "learning_rate": 3.998597769458175e-05, "loss": 0.0076, "step": 197510 }, { "epoch": 47.42, "learning_rate": 3.998158168312453e-05, "loss": 0.0047, "step": 197520 }, { "epoch": 47.43, "learning_rate": 3.997718575234699e-05, "loss": 0.0332, "step": 197530 }, { "epoch": 47.43, "learning_rate": 3.997278990228458e-05, "loss": 0.0072, "step": 197540 }, { "epoch": 47.43, "learning_rate": 3.9968394132972665e-05, "loss": 0.0066, "step": 197550 }, { "epoch": 47.43, "learning_rate": 3.9963998444446685e-05, "loss": 0.0087, "step": 197560 }, { "epoch": 47.44, "learning_rate": 3.995960283674198e-05, "loss": 0.0087, "step": 197570 }, { "epoch": 47.44, "learning_rate": 3.9955207309893996e-05, "loss": 0.0109, "step": 197580 }, { "epoch": 47.44, "learning_rate": 3.99508118639381e-05, "loss": 0.0145, "step": 197590 }, { "epoch": 47.44, "learning_rate": 3.994641649890971e-05, "loss": 0.005, "step": 197600 }, { "epoch": 47.45, "learning_rate": 3.994202121484423e-05, "loss": 0.0078, "step": 197610 }, { "epoch": 47.45, "learning_rate": 3.993762601177702e-05, "loss": 0.0083, "step": 197620 }, { "epoch": 47.45, "learning_rate": 3.993323088974351e-05, "loss": 0.0033, "step": 197630 }, { "epoch": 47.45, "learning_rate": 3.992883584877906e-05, "loss": 0.0059, "step": 197640 }, { "epoch": 47.45, "learning_rate": 3.992444088891911e-05, "loss": 0.0041, "step": 197650 }, { "epoch": 47.46, "learning_rate": 3.992004601019903e-05, "loss": 0.0133, "step": 197660 }, { "epoch": 47.46, "learning_rate": 3.9915651212654195e-05, "loss": 0.0077, "step": 197670 }, { "epoch": 47.46, "learning_rate": 3.991125649632002e-05, "loss": 0.0094, "step": 197680 }, { "epoch": 47.46, "learning_rate": 3.990686186123188e-05, "loss": 0.006, "step": 197690 }, { "epoch": 47.47, "learning_rate": 3.99024673074252e-05, "loss": 0.0073, "step": 197700 }, { "epoch": 47.47, "learning_rate": 3.989807283493533e-05, "loss": 0.0038, "step": 197710 }, { "epoch": 47.47, "learning_rate": 3.989367844379767e-05, "loss": 0.0059, "step": 197720 }, { "epoch": 47.47, "learning_rate": 3.988928413404761e-05, "loss": 0.0098, "step": 197730 }, { "epoch": 47.48, "learning_rate": 3.988488990572054e-05, "loss": 0.0063, "step": 197740 }, { "epoch": 47.48, "learning_rate": 3.988049575885186e-05, "loss": 0.0062, "step": 197750 }, { "epoch": 47.48, "learning_rate": 3.9876101693476945e-05, "loss": 0.0055, "step": 197760 }, { "epoch": 47.48, "learning_rate": 3.9871707709631165e-05, "loss": 0.0067, "step": 197770 }, { "epoch": 47.48, "learning_rate": 3.986731380734994e-05, "loss": 0.013, "step": 197780 }, { "epoch": 47.49, "learning_rate": 3.986291998666862e-05, "loss": 0.0079, "step": 197790 }, { "epoch": 47.49, "learning_rate": 3.985852624762263e-05, "loss": 0.0099, "step": 197800 }, { "epoch": 47.49, "learning_rate": 3.98541325902473e-05, "loss": 0.0112, "step": 197810 }, { "epoch": 47.49, "learning_rate": 3.984973901457806e-05, "loss": 0.0057, "step": 197820 }, { "epoch": 47.5, "learning_rate": 3.9845345520650254e-05, "loss": 0.0084, "step": 197830 }, { "epoch": 47.5, "learning_rate": 3.9840952108499305e-05, "loss": 0.0068, "step": 197840 }, { "epoch": 47.5, "learning_rate": 3.983655877816056e-05, "loss": 0.0046, "step": 197850 }, { "epoch": 47.5, "learning_rate": 3.98321655296694e-05, "loss": 0.0074, "step": 197860 }, { "epoch": 47.5, "learning_rate": 3.982777236306122e-05, "loss": 0.0036, "step": 197870 }, { "epoch": 47.51, "learning_rate": 3.982337927837139e-05, "loss": 0.0108, "step": 197880 }, { "epoch": 47.51, "learning_rate": 3.981898627563532e-05, "loss": 0.0082, "step": 197890 }, { "epoch": 47.51, "learning_rate": 3.981459335488834e-05, "loss": 0.0159, "step": 197900 }, { "epoch": 47.51, "learning_rate": 3.981020051616583e-05, "loss": 0.0075, "step": 197910 }, { "epoch": 47.52, "learning_rate": 3.98058077595032e-05, "loss": 0.0125, "step": 197920 }, { "epoch": 47.52, "learning_rate": 3.98014150849358e-05, "loss": 0.0061, "step": 197930 }, { "epoch": 47.52, "learning_rate": 3.979702249249902e-05, "loss": 0.0099, "step": 197940 }, { "epoch": 47.52, "learning_rate": 3.979262998222822e-05, "loss": 0.0089, "step": 197950 }, { "epoch": 47.53, "learning_rate": 3.978823755415878e-05, "loss": 0.0131, "step": 197960 }, { "epoch": 47.53, "learning_rate": 3.978384520832607e-05, "loss": 0.006, "step": 197970 }, { "epoch": 47.53, "learning_rate": 3.977945294476547e-05, "loss": 0.0208, "step": 197980 }, { "epoch": 47.53, "learning_rate": 3.977506076351237e-05, "loss": 0.0074, "step": 197990 }, { "epoch": 47.53, "learning_rate": 3.977066866460208e-05, "loss": 0.0055, "step": 198000 }, { "epoch": 47.54, "learning_rate": 3.976627664807003e-05, "loss": 0.0073, "step": 198010 }, { "epoch": 47.54, "learning_rate": 3.976188471395155e-05, "loss": 0.007, "step": 198020 }, { "epoch": 47.54, "learning_rate": 3.975749286228204e-05, "loss": 0.0109, "step": 198030 }, { "epoch": 47.54, "learning_rate": 3.9753101093096856e-05, "loss": 0.0112, "step": 198040 }, { "epoch": 47.55, "learning_rate": 3.9748709406431344e-05, "loss": 0.0095, "step": 198050 }, { "epoch": 47.55, "learning_rate": 3.974431780232091e-05, "loss": 0.0103, "step": 198060 }, { "epoch": 47.55, "learning_rate": 3.9739926280800875e-05, "loss": 0.0175, "step": 198070 }, { "epoch": 47.55, "learning_rate": 3.973553484190666e-05, "loss": 0.0057, "step": 198080 }, { "epoch": 47.56, "learning_rate": 3.9731143485673595e-05, "loss": 0.0162, "step": 198090 }, { "epoch": 47.56, "learning_rate": 3.972675221213703e-05, "loss": 0.0051, "step": 198100 }, { "epoch": 47.56, "learning_rate": 3.9722361021332367e-05, "loss": 0.0097, "step": 198110 }, { "epoch": 47.56, "learning_rate": 3.9717969913294935e-05, "loss": 0.0109, "step": 198120 }, { "epoch": 47.56, "learning_rate": 3.971357888806013e-05, "loss": 0.014, "step": 198130 }, { "epoch": 47.57, "learning_rate": 3.970918794566329e-05, "loss": 0.0079, "step": 198140 }, { "epoch": 47.57, "learning_rate": 3.970479708613975e-05, "loss": 0.0363, "step": 198150 }, { "epoch": 47.57, "learning_rate": 3.9700406309524934e-05, "loss": 0.0436, "step": 198160 }, { "epoch": 47.57, "learning_rate": 3.969601561585417e-05, "loss": 0.0087, "step": 198170 }, { "epoch": 47.58, "learning_rate": 3.9691625005162794e-05, "loss": 0.0139, "step": 198180 }, { "epoch": 47.58, "learning_rate": 3.9687234477486196e-05, "loss": 0.0203, "step": 198190 }, { "epoch": 47.58, "learning_rate": 3.9682844032859714e-05, "loss": 0.0064, "step": 198200 }, { "epoch": 47.58, "learning_rate": 3.9678453671318715e-05, "loss": 0.0068, "step": 198210 }, { "epoch": 47.58, "learning_rate": 3.9674063392898576e-05, "loss": 0.0114, "step": 198220 }, { "epoch": 47.59, "learning_rate": 3.966967319763461e-05, "loss": 0.0124, "step": 198230 }, { "epoch": 47.59, "learning_rate": 3.966528308556218e-05, "loss": 0.0129, "step": 198240 }, { "epoch": 47.59, "learning_rate": 3.9660893056716675e-05, "loss": 0.0105, "step": 198250 }, { "epoch": 47.59, "learning_rate": 3.96565031111334e-05, "loss": 0.0077, "step": 198260 }, { "epoch": 47.6, "learning_rate": 3.9652113248847765e-05, "loss": 0.0087, "step": 198270 }, { "epoch": 47.6, "learning_rate": 3.9647723469895084e-05, "loss": 0.006, "step": 198280 }, { "epoch": 47.6, "learning_rate": 3.9643333774310694e-05, "loss": 0.0046, "step": 198290 }, { "epoch": 47.6, "learning_rate": 3.9638944162129985e-05, "loss": 0.0119, "step": 198300 }, { "epoch": 47.61, "learning_rate": 3.963455463338827e-05, "loss": 0.0037, "step": 198310 }, { "epoch": 47.61, "learning_rate": 3.9630165188120945e-05, "loss": 0.0095, "step": 198320 }, { "epoch": 47.61, "learning_rate": 3.962577582636332e-05, "loss": 0.0085, "step": 198330 }, { "epoch": 47.61, "learning_rate": 3.962138654815074e-05, "loss": 0.0077, "step": 198340 }, { "epoch": 47.61, "learning_rate": 3.961699735351858e-05, "loss": 0.0045, "step": 198350 }, { "epoch": 47.62, "learning_rate": 3.9612608242502195e-05, "loss": 0.0099, "step": 198360 }, { "epoch": 47.62, "learning_rate": 3.960821921513687e-05, "loss": 0.0114, "step": 198370 }, { "epoch": 47.62, "learning_rate": 3.960383027145802e-05, "loss": 0.0119, "step": 198380 }, { "epoch": 47.62, "learning_rate": 3.959944141150093e-05, "loss": 0.0092, "step": 198390 }, { "epoch": 47.63, "learning_rate": 3.9595052635301e-05, "loss": 0.0054, "step": 198400 }, { "epoch": 47.63, "learning_rate": 3.959066394289355e-05, "loss": 0.003, "step": 198410 }, { "epoch": 47.63, "learning_rate": 3.958627533431391e-05, "loss": 0.0094, "step": 198420 }, { "epoch": 47.63, "learning_rate": 3.958188680959742e-05, "loss": 0.0113, "step": 198430 }, { "epoch": 47.64, "learning_rate": 3.9577498368779456e-05, "loss": 0.0098, "step": 198440 }, { "epoch": 47.64, "learning_rate": 3.9573110011895314e-05, "loss": 0.0111, "step": 198450 }, { "epoch": 47.64, "learning_rate": 3.9568721738980387e-05, "loss": 0.0038, "step": 198460 }, { "epoch": 47.64, "learning_rate": 3.9564333550069966e-05, "loss": 0.011, "step": 198470 }, { "epoch": 47.64, "learning_rate": 3.9559945445199396e-05, "loss": 0.0112, "step": 198480 }, { "epoch": 47.65, "learning_rate": 3.955555742440404e-05, "loss": 0.0116, "step": 198490 }, { "epoch": 47.65, "learning_rate": 3.9551169487719244e-05, "loss": 0.0028, "step": 198500 }, { "epoch": 47.65, "learning_rate": 3.9546781635180283e-05, "loss": 0.0085, "step": 198510 }, { "epoch": 47.65, "learning_rate": 3.9542393866822554e-05, "loss": 0.0167, "step": 198520 }, { "epoch": 47.66, "learning_rate": 3.953800618268136e-05, "loss": 0.0087, "step": 198530 }, { "epoch": 47.66, "learning_rate": 3.9533618582792054e-05, "loss": 0.0154, "step": 198540 }, { "epoch": 47.66, "learning_rate": 3.952923106718997e-05, "loss": 0.0097, "step": 198550 }, { "epoch": 47.66, "learning_rate": 3.952484363591042e-05, "loss": 0.0136, "step": 198560 }, { "epoch": 47.66, "learning_rate": 3.952045628898876e-05, "loss": 0.0061, "step": 198570 }, { "epoch": 47.67, "learning_rate": 3.9516069026460294e-05, "loss": 0.0114, "step": 198580 }, { "epoch": 47.67, "learning_rate": 3.951168184836039e-05, "loss": 0.0058, "step": 198590 }, { "epoch": 47.67, "learning_rate": 3.9507294754724365e-05, "loss": 0.0098, "step": 198600 }, { "epoch": 47.67, "learning_rate": 3.950290774558753e-05, "loss": 0.0071, "step": 198610 }, { "epoch": 47.68, "learning_rate": 3.949852082098523e-05, "loss": 0.0059, "step": 198620 }, { "epoch": 47.68, "learning_rate": 3.949413398095279e-05, "loss": 0.0067, "step": 198630 }, { "epoch": 47.68, "learning_rate": 3.948974722552554e-05, "loss": 0.0079, "step": 198640 }, { "epoch": 47.68, "learning_rate": 3.948536055473883e-05, "loss": 0.0171, "step": 198650 }, { "epoch": 47.69, "learning_rate": 3.9480973968627945e-05, "loss": 0.0062, "step": 198660 }, { "epoch": 47.69, "learning_rate": 3.947658746722822e-05, "loss": 0.0119, "step": 198670 }, { "epoch": 47.69, "learning_rate": 3.9472201050574996e-05, "loss": 0.0108, "step": 198680 }, { "epoch": 47.69, "learning_rate": 3.94678147187036e-05, "loss": 0.0076, "step": 198690 }, { "epoch": 47.69, "learning_rate": 3.946342847164933e-05, "loss": 0.0141, "step": 198700 }, { "epoch": 47.7, "learning_rate": 3.9459042309447534e-05, "loss": 0.0146, "step": 198710 }, { "epoch": 47.7, "learning_rate": 3.945465623213351e-05, "loss": 0.0162, "step": 198720 }, { "epoch": 47.7, "learning_rate": 3.9450270239742615e-05, "loss": 0.0119, "step": 198730 }, { "epoch": 47.7, "learning_rate": 3.944588433231016e-05, "loss": 0.0099, "step": 198740 }, { "epoch": 47.71, "learning_rate": 3.944149850987143e-05, "loss": 0.019, "step": 198750 }, { "epoch": 47.71, "learning_rate": 3.943711277246178e-05, "loss": 0.0066, "step": 198760 }, { "epoch": 47.71, "learning_rate": 3.943272712011651e-05, "loss": 0.0139, "step": 198770 }, { "epoch": 47.71, "learning_rate": 3.9428341552870956e-05, "loss": 0.0122, "step": 198780 }, { "epoch": 47.72, "learning_rate": 3.942395607076044e-05, "loss": 0.015, "step": 198790 }, { "epoch": 47.72, "learning_rate": 3.941957067382025e-05, "loss": 0.0152, "step": 198800 }, { "epoch": 47.72, "learning_rate": 3.941518536208572e-05, "loss": 0.0133, "step": 198810 }, { "epoch": 47.72, "learning_rate": 3.941080013559216e-05, "loss": 0.0082, "step": 198820 }, { "epoch": 47.72, "learning_rate": 3.94064149943749e-05, "loss": 0.0063, "step": 198830 }, { "epoch": 47.73, "learning_rate": 3.9402029938469245e-05, "loss": 0.0085, "step": 198840 }, { "epoch": 47.73, "learning_rate": 3.9397644967910496e-05, "loss": 0.0151, "step": 198850 }, { "epoch": 47.73, "learning_rate": 3.939326008273396e-05, "loss": 0.008, "step": 198860 }, { "epoch": 47.73, "learning_rate": 3.938887528297499e-05, "loss": 0.0108, "step": 198870 }, { "epoch": 47.74, "learning_rate": 3.938449056866887e-05, "loss": 0.0076, "step": 198880 }, { "epoch": 47.74, "learning_rate": 3.9380105939850905e-05, "loss": 0.0061, "step": 198890 }, { "epoch": 47.74, "learning_rate": 3.937572139655641e-05, "loss": 0.0094, "step": 198900 }, { "epoch": 47.74, "learning_rate": 3.93713369388207e-05, "loss": 0.0105, "step": 198910 }, { "epoch": 47.74, "learning_rate": 3.936695256667908e-05, "loss": 0.0091, "step": 198920 }, { "epoch": 47.75, "learning_rate": 3.936256828016688e-05, "loss": 0.0041, "step": 198930 }, { "epoch": 47.75, "learning_rate": 3.935818407931936e-05, "loss": 0.0104, "step": 198940 }, { "epoch": 47.75, "learning_rate": 3.9353799964171864e-05, "loss": 0.0054, "step": 198950 }, { "epoch": 47.75, "learning_rate": 3.9349415934759676e-05, "loss": 0.0046, "step": 198960 }, { "epoch": 47.76, "learning_rate": 3.934503199111812e-05, "loss": 0.0059, "step": 198970 }, { "epoch": 47.76, "learning_rate": 3.93406481332825e-05, "loss": 0.0105, "step": 198980 }, { "epoch": 47.76, "learning_rate": 3.93362643612881e-05, "loss": 0.0102, "step": 198990 }, { "epoch": 47.76, "learning_rate": 3.933188067517024e-05, "loss": 0.0046, "step": 199000 }, { "epoch": 47.77, "learning_rate": 3.9327497074964216e-05, "loss": 0.0048, "step": 199010 }, { "epoch": 47.77, "learning_rate": 3.9323113560705344e-05, "loss": 0.008, "step": 199020 }, { "epoch": 47.77, "learning_rate": 3.931873013242891e-05, "loss": 0.0093, "step": 199030 }, { "epoch": 47.77, "learning_rate": 3.931434679017019e-05, "loss": 0.017, "step": 199040 }, { "epoch": 47.77, "learning_rate": 3.9309963533964535e-05, "loss": 0.014, "step": 199050 }, { "epoch": 47.78, "learning_rate": 3.93055803638472e-05, "loss": 0.0126, "step": 199060 }, { "epoch": 47.78, "learning_rate": 3.930119727985354e-05, "loss": 0.0078, "step": 199070 }, { "epoch": 47.78, "learning_rate": 3.9296814282018784e-05, "loss": 0.0039, "step": 199080 }, { "epoch": 47.78, "learning_rate": 3.929243137037827e-05, "loss": 0.0056, "step": 199090 }, { "epoch": 47.79, "learning_rate": 3.928804854496727e-05, "loss": 0.0039, "step": 199100 }, { "epoch": 47.79, "learning_rate": 3.928366580582111e-05, "loss": 0.0038, "step": 199110 }, { "epoch": 47.79, "learning_rate": 3.9279283152975074e-05, "loss": 0.0177, "step": 199120 }, { "epoch": 47.79, "learning_rate": 3.9274900586464436e-05, "loss": 0.0108, "step": 199130 }, { "epoch": 47.8, "learning_rate": 3.9270518106324514e-05, "loss": 0.0035, "step": 199140 }, { "epoch": 47.8, "learning_rate": 3.926613571259058e-05, "loss": 0.0075, "step": 199150 }, { "epoch": 47.8, "learning_rate": 3.9261753405297956e-05, "loss": 0.018, "step": 199160 }, { "epoch": 47.8, "learning_rate": 3.925737118448191e-05, "loss": 0.014, "step": 199170 }, { "epoch": 47.8, "learning_rate": 3.925298905017771e-05, "loss": 0.0044, "step": 199180 }, { "epoch": 47.81, "learning_rate": 3.92486070024207e-05, "loss": 0.0062, "step": 199190 }, { "epoch": 47.81, "learning_rate": 3.924422504124612e-05, "loss": 0.0053, "step": 199200 }, { "epoch": 47.81, "learning_rate": 3.9239843166689315e-05, "loss": 0.0043, "step": 199210 }, { "epoch": 47.81, "learning_rate": 3.923546137878552e-05, "loss": 0.0075, "step": 199220 }, { "epoch": 47.82, "learning_rate": 3.9231079677570034e-05, "loss": 0.0103, "step": 199230 }, { "epoch": 47.82, "learning_rate": 3.9226698063078153e-05, "loss": 0.0055, "step": 199240 }, { "epoch": 47.82, "learning_rate": 3.9222316535345154e-05, "loss": 0.0073, "step": 199250 }, { "epoch": 47.82, "learning_rate": 3.921793509440635e-05, "loss": 0.0253, "step": 199260 }, { "epoch": 47.82, "learning_rate": 3.9213553740296996e-05, "loss": 0.0057, "step": 199270 }, { "epoch": 47.83, "learning_rate": 3.9209172473052364e-05, "loss": 0.0184, "step": 199280 }, { "epoch": 47.83, "learning_rate": 3.920479129270776e-05, "loss": 0.0179, "step": 199290 }, { "epoch": 47.83, "learning_rate": 3.920041019929848e-05, "loss": 0.0059, "step": 199300 }, { "epoch": 47.83, "learning_rate": 3.919602919285979e-05, "loss": 0.0046, "step": 199310 }, { "epoch": 47.84, "learning_rate": 3.919164827342695e-05, "loss": 0.0093, "step": 199320 }, { "epoch": 47.84, "learning_rate": 3.918726744103527e-05, "loss": 0.0096, "step": 199330 }, { "epoch": 47.84, "learning_rate": 3.918288669572e-05, "loss": 0.0051, "step": 199340 }, { "epoch": 47.84, "learning_rate": 3.917850603751646e-05, "loss": 0.0141, "step": 199350 }, { "epoch": 47.85, "learning_rate": 3.91741254664599e-05, "loss": 0.0055, "step": 199360 }, { "epoch": 47.85, "learning_rate": 3.916974498258559e-05, "loss": 0.0064, "step": 199370 }, { "epoch": 47.85, "learning_rate": 3.9165364585928825e-05, "loss": 0.004, "step": 199380 }, { "epoch": 47.85, "learning_rate": 3.916098427652487e-05, "loss": 0.0076, "step": 199390 }, { "epoch": 47.85, "learning_rate": 3.915660405440902e-05, "loss": 0.0047, "step": 199400 }, { "epoch": 47.86, "learning_rate": 3.9152223919616526e-05, "loss": 0.0113, "step": 199410 }, { "epoch": 47.86, "learning_rate": 3.9147843872182666e-05, "loss": 0.0035, "step": 199420 }, { "epoch": 47.86, "learning_rate": 3.914346391214272e-05, "loss": 0.0069, "step": 199430 }, { "epoch": 47.86, "learning_rate": 3.913908403953195e-05, "loss": 0.0036, "step": 199440 }, { "epoch": 47.87, "learning_rate": 3.913470425438566e-05, "loss": 0.0067, "step": 199450 }, { "epoch": 47.87, "learning_rate": 3.913032455673908e-05, "loss": 0.0049, "step": 199460 }, { "epoch": 47.87, "learning_rate": 3.912594494662749e-05, "loss": 0.0087, "step": 199470 }, { "epoch": 47.87, "learning_rate": 3.912156542408618e-05, "loss": 0.0113, "step": 199480 }, { "epoch": 47.88, "learning_rate": 3.911718598915041e-05, "loss": 0.0101, "step": 199490 }, { "epoch": 47.88, "learning_rate": 3.911280664185544e-05, "loss": 0.0098, "step": 199500 }, { "epoch": 47.88, "learning_rate": 3.9108427382236527e-05, "loss": 0.0101, "step": 199510 }, { "epoch": 47.88, "learning_rate": 3.910404821032896e-05, "loss": 0.0098, "step": 199520 }, { "epoch": 47.88, "learning_rate": 3.909966912616799e-05, "loss": 0.0051, "step": 199530 }, { "epoch": 47.89, "learning_rate": 3.909529012978891e-05, "loss": 0.0061, "step": 199540 }, { "epoch": 47.89, "learning_rate": 3.909091122122695e-05, "loss": 0.0037, "step": 199550 }, { "epoch": 47.89, "learning_rate": 3.908653240051738e-05, "loss": 0.0187, "step": 199560 }, { "epoch": 47.89, "learning_rate": 3.908215366769549e-05, "loss": 0.0093, "step": 199570 }, { "epoch": 47.9, "learning_rate": 3.90777750227965e-05, "loss": 0.0069, "step": 199580 }, { "epoch": 47.9, "learning_rate": 3.907339646585573e-05, "loss": 0.006, "step": 199590 }, { "epoch": 47.9, "learning_rate": 3.906901799690839e-05, "loss": 0.0149, "step": 199600 }, { "epoch": 47.9, "learning_rate": 3.906463961598974e-05, "loss": 0.0097, "step": 199610 }, { "epoch": 47.9, "learning_rate": 3.906026132313507e-05, "loss": 0.0039, "step": 199620 }, { "epoch": 47.91, "learning_rate": 3.9055883118379624e-05, "loss": 0.0074, "step": 199630 }, { "epoch": 47.91, "learning_rate": 3.905150500175867e-05, "loss": 0.0148, "step": 199640 }, { "epoch": 47.91, "learning_rate": 3.904712697330746e-05, "loss": 0.0109, "step": 199650 }, { "epoch": 47.91, "learning_rate": 3.9042749033061226e-05, "loss": 0.0097, "step": 199660 }, { "epoch": 47.92, "learning_rate": 3.903837118105527e-05, "loss": 0.0085, "step": 199670 }, { "epoch": 47.92, "learning_rate": 3.9033993417324826e-05, "loss": 0.0039, "step": 199680 }, { "epoch": 47.92, "learning_rate": 3.902961574190513e-05, "loss": 0.0176, "step": 199690 }, { "epoch": 47.92, "learning_rate": 3.902523815483146e-05, "loss": 0.0083, "step": 199700 }, { "epoch": 47.93, "learning_rate": 3.902086065613905e-05, "loss": 0.0066, "step": 199710 }, { "epoch": 47.93, "learning_rate": 3.901648324586319e-05, "loss": 0.0057, "step": 199720 }, { "epoch": 47.93, "learning_rate": 3.90121059240391e-05, "loss": 0.0078, "step": 199730 }, { "epoch": 47.93, "learning_rate": 3.900772869070203e-05, "loss": 0.0051, "step": 199740 }, { "epoch": 47.93, "learning_rate": 3.9003351545887235e-05, "loss": 0.0142, "step": 199750 }, { "epoch": 47.94, "learning_rate": 3.8998974489629976e-05, "loss": 0.0145, "step": 199760 }, { "epoch": 47.94, "learning_rate": 3.899459752196548e-05, "loss": 0.0048, "step": 199770 }, { "epoch": 47.94, "learning_rate": 3.8990220642929035e-05, "loss": 0.0051, "step": 199780 }, { "epoch": 47.94, "learning_rate": 3.898584385255585e-05, "loss": 0.0069, "step": 199790 }, { "epoch": 47.95, "learning_rate": 3.898146715088118e-05, "loss": 0.0086, "step": 199800 }, { "epoch": 47.95, "learning_rate": 3.897709053794028e-05, "loss": 0.0143, "step": 199810 }, { "epoch": 47.95, "learning_rate": 3.8972714013768384e-05, "loss": 0.0081, "step": 199820 }, { "epoch": 48.0, "learning_rate": 3.896833757840077e-05, "loss": 0.0045, "step": 199830 }, { "epoch": 48.0, "learning_rate": 3.8963961231872635e-05, "loss": 0.0031, "step": 199840 }, { "epoch": 48.01, "learning_rate": 3.895958497421924e-05, "loss": 0.0143, "step": 199850 }, { "epoch": 48.01, "learning_rate": 3.895520880547585e-05, "loss": 0.0082, "step": 199860 }, { "epoch": 48.01, "learning_rate": 3.895083272567769e-05, "loss": 0.0239, "step": 199870 }, { "epoch": 48.01, "learning_rate": 3.894645673485998e-05, "loss": 0.0065, "step": 199880 }, { "epoch": 48.02, "learning_rate": 3.894208083305799e-05, "loss": 0.0042, "step": 199890 }, { "epoch": 48.02, "learning_rate": 3.8937705020306936e-05, "loss": 0.0166, "step": 199900 }, { "epoch": 48.02, "learning_rate": 3.893332929664208e-05, "loss": 0.0065, "step": 199910 }, { "epoch": 48.02, "learning_rate": 3.892895366209867e-05, "loss": 0.003, "step": 199920 }, { "epoch": 48.02, "learning_rate": 3.892457811671191e-05, "loss": 0.0091, "step": 199930 }, { "epoch": 48.03, "learning_rate": 3.892020266051704e-05, "loss": 0.0117, "step": 199940 }, { "epoch": 48.03, "learning_rate": 3.8915827293549315e-05, "loss": 0.0088, "step": 199950 }, { "epoch": 48.03, "learning_rate": 3.891145201584396e-05, "loss": 0.015, "step": 199960 }, { "epoch": 48.03, "learning_rate": 3.890707682743623e-05, "loss": 0.006, "step": 199970 }, { "epoch": 48.04, "learning_rate": 3.8902701728361326e-05, "loss": 0.0066, "step": 199980 }, { "epoch": 48.04, "learning_rate": 3.889832671865449e-05, "loss": 0.0101, "step": 199990 }, { "epoch": 48.04, "learning_rate": 3.889395179835098e-05, "loss": 0.0192, "step": 200000 }, { "epoch": 48.04, "learning_rate": 3.8889576967486015e-05, "loss": 0.0101, "step": 200010 }, { "epoch": 48.04, "learning_rate": 3.8885202226094795e-05, "loss": 0.0077, "step": 200020 }, { "epoch": 48.05, "learning_rate": 3.888082757421259e-05, "loss": 0.0054, "step": 200030 }, { "epoch": 48.05, "learning_rate": 3.88764530118746e-05, "loss": 0.0055, "step": 200040 }, { "epoch": 48.05, "learning_rate": 3.887207853911609e-05, "loss": 0.0071, "step": 200050 }, { "epoch": 48.05, "learning_rate": 3.886770415597227e-05, "loss": 0.0066, "step": 200060 }, { "epoch": 48.06, "learning_rate": 3.8863329862478346e-05, "loss": 0.0069, "step": 200070 }, { "epoch": 48.06, "learning_rate": 3.885895565866958e-05, "loss": 0.0352, "step": 200080 }, { "epoch": 48.06, "learning_rate": 3.885458154458117e-05, "loss": 0.006, "step": 200090 }, { "epoch": 48.06, "learning_rate": 3.885020752024836e-05, "loss": 0.0052, "step": 200100 }, { "epoch": 48.07, "learning_rate": 3.884583358570638e-05, "loss": 0.0041, "step": 200110 }, { "epoch": 48.07, "learning_rate": 3.8841459740990425e-05, "loss": 0.0073, "step": 200120 }, { "epoch": 48.07, "learning_rate": 3.883708598613575e-05, "loss": 0.0038, "step": 200130 }, { "epoch": 48.07, "learning_rate": 3.883271232117754e-05, "loss": 0.0095, "step": 200140 }, { "epoch": 48.07, "learning_rate": 3.882833874615105e-05, "loss": 0.0077, "step": 200150 }, { "epoch": 48.08, "learning_rate": 3.882396526109151e-05, "loss": 0.0071, "step": 200160 }, { "epoch": 48.08, "learning_rate": 3.8819591866034104e-05, "loss": 0.004, "step": 200170 }, { "epoch": 48.08, "learning_rate": 3.881521856101406e-05, "loss": 0.0032, "step": 200180 }, { "epoch": 48.08, "learning_rate": 3.8810845346066614e-05, "loss": 0.0109, "step": 200190 }, { "epoch": 48.09, "learning_rate": 3.8806472221226986e-05, "loss": 0.004, "step": 200200 }, { "epoch": 48.09, "learning_rate": 3.8802099186530366e-05, "loss": 0.0052, "step": 200210 }, { "epoch": 48.09, "learning_rate": 3.879772624201199e-05, "loss": 0.0341, "step": 200220 }, { "epoch": 48.09, "learning_rate": 3.879335338770706e-05, "loss": 0.0093, "step": 200230 }, { "epoch": 48.1, "learning_rate": 3.8788980623650826e-05, "loss": 0.0141, "step": 200240 }, { "epoch": 48.1, "learning_rate": 3.878460794987848e-05, "loss": 0.0037, "step": 200250 }, { "epoch": 48.1, "learning_rate": 3.8780235366425214e-05, "loss": 0.0075, "step": 200260 }, { "epoch": 48.1, "learning_rate": 3.877586287332627e-05, "loss": 0.0174, "step": 200270 }, { "epoch": 48.1, "learning_rate": 3.8771490470616844e-05, "loss": 0.0121, "step": 200280 }, { "epoch": 48.11, "learning_rate": 3.8767118158332175e-05, "loss": 0.0069, "step": 200290 }, { "epoch": 48.11, "learning_rate": 3.876274593650745e-05, "loss": 0.0037, "step": 200300 }, { "epoch": 48.11, "learning_rate": 3.875837380517787e-05, "loss": 0.0041, "step": 200310 }, { "epoch": 48.11, "learning_rate": 3.8754001764378664e-05, "loss": 0.0048, "step": 200320 }, { "epoch": 48.12, "learning_rate": 3.874962981414503e-05, "loss": 0.0106, "step": 200330 }, { "epoch": 48.12, "learning_rate": 3.8745257954512205e-05, "loss": 0.0244, "step": 200340 }, { "epoch": 48.12, "learning_rate": 3.874088618551535e-05, "loss": 0.0048, "step": 200350 }, { "epoch": 48.12, "learning_rate": 3.873651450718969e-05, "loss": 0.0059, "step": 200360 }, { "epoch": 48.12, "learning_rate": 3.873214291957043e-05, "loss": 0.0059, "step": 200370 }, { "epoch": 48.13, "learning_rate": 3.872777142269279e-05, "loss": 0.0068, "step": 200380 }, { "epoch": 48.13, "learning_rate": 3.872340001659197e-05, "loss": 0.0129, "step": 200390 }, { "epoch": 48.13, "learning_rate": 3.871902870130315e-05, "loss": 0.0079, "step": 200400 }, { "epoch": 48.13, "learning_rate": 3.871465747686155e-05, "loss": 0.0061, "step": 200410 }, { "epoch": 48.14, "learning_rate": 3.871028634330237e-05, "loss": 0.0086, "step": 200420 }, { "epoch": 48.14, "learning_rate": 3.870591530066083e-05, "loss": 0.004, "step": 200430 }, { "epoch": 48.14, "learning_rate": 3.8701544348972115e-05, "loss": 0.0059, "step": 200440 }, { "epoch": 48.14, "learning_rate": 3.8697173488271396e-05, "loss": 0.0054, "step": 200450 }, { "epoch": 48.15, "learning_rate": 3.869280271859392e-05, "loss": 0.0174, "step": 200460 }, { "epoch": 48.15, "learning_rate": 3.8688432039974854e-05, "loss": 0.0053, "step": 200470 }, { "epoch": 48.15, "learning_rate": 3.868406145244941e-05, "loss": 0.0051, "step": 200480 }, { "epoch": 48.15, "learning_rate": 3.86796909560528e-05, "loss": 0.0098, "step": 200490 }, { "epoch": 48.15, "learning_rate": 3.867532055082017e-05, "loss": 0.0146, "step": 200500 }, { "epoch": 48.16, "learning_rate": 3.8670950236786766e-05, "loss": 0.0051, "step": 200510 }, { "epoch": 48.16, "learning_rate": 3.866658001398775e-05, "loss": 0.0155, "step": 200520 }, { "epoch": 48.16, "learning_rate": 3.8662209882458354e-05, "loss": 0.004, "step": 200530 }, { "epoch": 48.16, "learning_rate": 3.8657839842233734e-05, "loss": 0.009, "step": 200540 }, { "epoch": 48.17, "learning_rate": 3.865346989334909e-05, "loss": 0.0138, "step": 200550 }, { "epoch": 48.17, "learning_rate": 3.8649100035839627e-05, "loss": 0.0138, "step": 200560 }, { "epoch": 48.17, "learning_rate": 3.864473026974052e-05, "loss": 0.0104, "step": 200570 }, { "epoch": 48.17, "learning_rate": 3.864036059508699e-05, "loss": 0.0049, "step": 200580 }, { "epoch": 48.18, "learning_rate": 3.863599101191417e-05, "loss": 0.0066, "step": 200590 }, { "epoch": 48.18, "learning_rate": 3.863162152025731e-05, "loss": 0.0214, "step": 200600 }, { "epoch": 48.18, "learning_rate": 3.862725212015155e-05, "loss": 0.0045, "step": 200610 }, { "epoch": 48.18, "learning_rate": 3.8622882811632117e-05, "loss": 0.0097, "step": 200620 }, { "epoch": 48.18, "learning_rate": 3.861851359473419e-05, "loss": 0.0098, "step": 200630 }, { "epoch": 48.19, "learning_rate": 3.8614144469492914e-05, "loss": 0.0135, "step": 200640 }, { "epoch": 48.19, "learning_rate": 3.860977543594352e-05, "loss": 0.0094, "step": 200650 }, { "epoch": 48.19, "learning_rate": 3.860540649412117e-05, "loss": 0.0148, "step": 200660 }, { "epoch": 48.19, "learning_rate": 3.8601037644061064e-05, "loss": 0.0045, "step": 200670 }, { "epoch": 48.2, "learning_rate": 3.859666888579838e-05, "loss": 0.0089, "step": 200680 }, { "epoch": 48.2, "learning_rate": 3.859230021936828e-05, "loss": 0.0035, "step": 200690 }, { "epoch": 48.2, "learning_rate": 3.858793164480597e-05, "loss": 0.0042, "step": 200700 }, { "epoch": 48.2, "learning_rate": 3.858356316214661e-05, "loss": 0.005, "step": 200710 }, { "epoch": 48.2, "learning_rate": 3.857919477142541e-05, "loss": 0.0051, "step": 200720 }, { "epoch": 48.21, "learning_rate": 3.857482647267753e-05, "loss": 0.005, "step": 200730 }, { "epoch": 48.21, "learning_rate": 3.8570458265938135e-05, "loss": 0.0055, "step": 200740 }, { "epoch": 48.21, "learning_rate": 3.856609015124243e-05, "loss": 0.003, "step": 200750 }, { "epoch": 48.21, "learning_rate": 3.8561722128625565e-05, "loss": 0.0214, "step": 200760 }, { "epoch": 48.22, "learning_rate": 3.855735419812275e-05, "loss": 0.0086, "step": 200770 }, { "epoch": 48.22, "learning_rate": 3.8552986359769137e-05, "loss": 0.0083, "step": 200780 }, { "epoch": 48.22, "learning_rate": 3.8548618613599904e-05, "loss": 0.0128, "step": 200790 }, { "epoch": 48.22, "learning_rate": 3.854425095965021e-05, "loss": 0.006, "step": 200800 }, { "epoch": 48.23, "learning_rate": 3.853988339795527e-05, "loss": 0.0095, "step": 200810 }, { "epoch": 48.23, "learning_rate": 3.8535515928550224e-05, "loss": 0.0043, "step": 200820 }, { "epoch": 48.23, "learning_rate": 3.853114855147024e-05, "loss": 0.0057, "step": 200830 }, { "epoch": 48.23, "learning_rate": 3.852678126675051e-05, "loss": 0.0047, "step": 200840 }, { "epoch": 48.23, "learning_rate": 3.8522414074426184e-05, "loss": 0.0031, "step": 200850 }, { "epoch": 48.24, "learning_rate": 3.851804697453246e-05, "loss": 0.0039, "step": 200860 }, { "epoch": 48.24, "learning_rate": 3.8513679967104475e-05, "loss": 0.0348, "step": 200870 }, { "epoch": 48.24, "learning_rate": 3.850931305217741e-05, "loss": 0.0055, "step": 200880 }, { "epoch": 48.24, "learning_rate": 3.850494622978643e-05, "loss": 0.0084, "step": 200890 }, { "epoch": 48.25, "learning_rate": 3.8500579499966704e-05, "loss": 0.0037, "step": 200900 }, { "epoch": 48.25, "learning_rate": 3.849621286275342e-05, "loss": 0.0104, "step": 200910 }, { "epoch": 48.25, "learning_rate": 3.8491846318181715e-05, "loss": 0.0047, "step": 200920 }, { "epoch": 48.25, "learning_rate": 3.848747986628675e-05, "loss": 0.0046, "step": 200930 }, { "epoch": 48.26, "learning_rate": 3.84831135071037e-05, "loss": 0.0156, "step": 200940 }, { "epoch": 48.26, "learning_rate": 3.8478747240667725e-05, "loss": 0.0075, "step": 200950 }, { "epoch": 48.26, "learning_rate": 3.8474381067014e-05, "loss": 0.0033, "step": 200960 }, { "epoch": 48.26, "learning_rate": 3.847001498617767e-05, "loss": 0.0059, "step": 200970 }, { "epoch": 48.26, "learning_rate": 3.8465648998193896e-05, "loss": 0.0067, "step": 200980 }, { "epoch": 48.27, "learning_rate": 3.846128310309785e-05, "loss": 0.0115, "step": 200990 }, { "epoch": 48.27, "learning_rate": 3.845691730092469e-05, "loss": 0.0048, "step": 201000 }, { "epoch": 48.27, "learning_rate": 3.845255159170957e-05, "loss": 0.0168, "step": 201010 }, { "epoch": 48.27, "learning_rate": 3.844818597548763e-05, "loss": 0.004, "step": 201020 }, { "epoch": 48.28, "learning_rate": 3.8443820452294046e-05, "loss": 0.0072, "step": 201030 }, { "epoch": 48.28, "learning_rate": 3.8439455022163966e-05, "loss": 0.0048, "step": 201040 }, { "epoch": 48.28, "learning_rate": 3.843508968513258e-05, "loss": 0.006, "step": 201050 }, { "epoch": 48.28, "learning_rate": 3.843072444123499e-05, "loss": 0.0068, "step": 201060 }, { "epoch": 48.28, "learning_rate": 3.842635929050637e-05, "loss": 0.0094, "step": 201070 }, { "epoch": 48.29, "learning_rate": 3.842199423298188e-05, "loss": 0.0135, "step": 201080 }, { "epoch": 48.29, "learning_rate": 3.841762926869666e-05, "loss": 0.0072, "step": 201090 }, { "epoch": 48.29, "learning_rate": 3.84132643976859e-05, "loss": 0.0137, "step": 201100 }, { "epoch": 48.29, "learning_rate": 3.84088996199847e-05, "loss": 0.0074, "step": 201110 }, { "epoch": 48.3, "learning_rate": 3.840453493562823e-05, "loss": 0.0064, "step": 201120 }, { "epoch": 48.3, "learning_rate": 3.840017034465165e-05, "loss": 0.0126, "step": 201130 }, { "epoch": 48.3, "learning_rate": 3.8395805847090094e-05, "loss": 0.0101, "step": 201140 }, { "epoch": 48.3, "learning_rate": 3.839144144297873e-05, "loss": 0.0054, "step": 201150 }, { "epoch": 48.31, "learning_rate": 3.838707713235268e-05, "loss": 0.0067, "step": 201160 }, { "epoch": 48.31, "learning_rate": 3.838271291524709e-05, "loss": 0.0339, "step": 201170 }, { "epoch": 48.31, "learning_rate": 3.837834879169713e-05, "loss": 0.0027, "step": 201180 }, { "epoch": 48.31, "learning_rate": 3.837398476173794e-05, "loss": 0.0043, "step": 201190 }, { "epoch": 48.31, "learning_rate": 3.836962082540463e-05, "loss": 0.0064, "step": 201200 }, { "epoch": 48.32, "learning_rate": 3.836525698273239e-05, "loss": 0.0163, "step": 201210 }, { "epoch": 48.32, "learning_rate": 3.836089323375634e-05, "loss": 0.0092, "step": 201220 }, { "epoch": 48.32, "learning_rate": 3.835652957851161e-05, "loss": 0.0077, "step": 201230 }, { "epoch": 48.32, "learning_rate": 3.8352166017033374e-05, "loss": 0.004, "step": 201240 }, { "epoch": 48.33, "learning_rate": 3.834780254935675e-05, "loss": 0.0076, "step": 201250 }, { "epoch": 48.33, "learning_rate": 3.834343917551686e-05, "loss": 0.0066, "step": 201260 }, { "epoch": 48.33, "learning_rate": 3.833907589554888e-05, "loss": 0.0039, "step": 201270 }, { "epoch": 48.33, "learning_rate": 3.833471270948792e-05, "loss": 0.0116, "step": 201280 }, { "epoch": 48.34, "learning_rate": 3.833034961736915e-05, "loss": 0.0102, "step": 201290 }, { "epoch": 48.34, "learning_rate": 3.832598661922767e-05, "loss": 0.0101, "step": 201300 }, { "epoch": 48.34, "learning_rate": 3.832162371509863e-05, "loss": 0.0034, "step": 201310 }, { "epoch": 48.34, "learning_rate": 3.8317260905017174e-05, "loss": 0.0073, "step": 201320 }, { "epoch": 48.34, "learning_rate": 3.8312898189018436e-05, "loss": 0.0107, "step": 201330 }, { "epoch": 48.35, "learning_rate": 3.830853556713753e-05, "loss": 0.0069, "step": 201340 }, { "epoch": 48.35, "learning_rate": 3.83041730394096e-05, "loss": 0.0045, "step": 201350 }, { "epoch": 48.35, "learning_rate": 3.829981060586978e-05, "loss": 0.0072, "step": 201360 }, { "epoch": 48.35, "learning_rate": 3.82954482665532e-05, "loss": 0.0165, "step": 201370 }, { "epoch": 48.36, "learning_rate": 3.829108602149501e-05, "loss": 0.007, "step": 201380 }, { "epoch": 48.36, "learning_rate": 3.82867238707303e-05, "loss": 0.0055, "step": 201390 }, { "epoch": 48.36, "learning_rate": 3.828236181429422e-05, "loss": 0.0109, "step": 201400 }, { "epoch": 48.36, "learning_rate": 3.82779998522219e-05, "loss": 0.0087, "step": 201410 }, { "epoch": 48.36, "learning_rate": 3.827363798454847e-05, "loss": 0.0048, "step": 201420 }, { "epoch": 48.37, "learning_rate": 3.826927621130906e-05, "loss": 0.0098, "step": 201430 }, { "epoch": 48.37, "learning_rate": 3.826491453253878e-05, "loss": 0.0111, "step": 201440 }, { "epoch": 48.37, "learning_rate": 3.826055294827276e-05, "loss": 0.0088, "step": 201450 }, { "epoch": 48.37, "learning_rate": 3.8256191458546135e-05, "loss": 0.0162, "step": 201460 }, { "epoch": 48.38, "learning_rate": 3.8251830063394e-05, "loss": 0.014, "step": 201470 }, { "epoch": 48.38, "learning_rate": 3.824746876285153e-05, "loss": 0.0063, "step": 201480 }, { "epoch": 48.38, "learning_rate": 3.824310755695381e-05, "loss": 0.0099, "step": 201490 }, { "epoch": 48.38, "learning_rate": 3.8238746445735946e-05, "loss": 0.005, "step": 201500 }, { "epoch": 48.39, "learning_rate": 3.82343854292331e-05, "loss": 0.0187, "step": 201510 }, { "epoch": 48.39, "learning_rate": 3.823002450748038e-05, "loss": 0.0148, "step": 201520 }, { "epoch": 48.39, "learning_rate": 3.822566368051287e-05, "loss": 0.0048, "step": 201530 }, { "epoch": 48.39, "learning_rate": 3.822130294836574e-05, "loss": 0.009, "step": 201540 }, { "epoch": 48.39, "learning_rate": 3.821694231107407e-05, "loss": 0.0087, "step": 201550 }, { "epoch": 48.4, "learning_rate": 3.8212581768672996e-05, "loss": 0.0132, "step": 201560 }, { "epoch": 48.4, "learning_rate": 3.820822132119763e-05, "loss": 0.0097, "step": 201570 }, { "epoch": 48.4, "learning_rate": 3.820386096868308e-05, "loss": 0.006, "step": 201580 }, { "epoch": 48.4, "learning_rate": 3.819950071116447e-05, "loss": 0.0096, "step": 201590 }, { "epoch": 48.41, "learning_rate": 3.819514054867691e-05, "loss": 0.0039, "step": 201600 }, { "epoch": 48.41, "learning_rate": 3.8190780481255503e-05, "loss": 0.0102, "step": 201610 }, { "epoch": 48.41, "learning_rate": 3.81864205089354e-05, "loss": 0.0093, "step": 201620 }, { "epoch": 48.41, "learning_rate": 3.8182060631751655e-05, "loss": 0.0045, "step": 201630 }, { "epoch": 48.41, "learning_rate": 3.817770084973942e-05, "loss": 0.0122, "step": 201640 }, { "epoch": 48.42, "learning_rate": 3.817334116293378e-05, "loss": 0.0073, "step": 201650 }, { "epoch": 48.42, "learning_rate": 3.816898157136989e-05, "loss": 0.0082, "step": 201660 }, { "epoch": 48.42, "learning_rate": 3.816462207508279e-05, "loss": 0.0073, "step": 201670 }, { "epoch": 48.42, "learning_rate": 3.8160262674107624e-05, "loss": 0.0069, "step": 201680 }, { "epoch": 48.43, "learning_rate": 3.81559033684795e-05, "loss": 0.0063, "step": 201690 }, { "epoch": 48.43, "learning_rate": 3.815154415823353e-05, "loss": 0.0139, "step": 201700 }, { "epoch": 48.43, "learning_rate": 3.814718504340482e-05, "loss": 0.0111, "step": 201710 }, { "epoch": 48.43, "learning_rate": 3.814282602402844e-05, "loss": 0.0178, "step": 201720 }, { "epoch": 48.44, "learning_rate": 3.813846710013954e-05, "loss": 0.0056, "step": 201730 }, { "epoch": 48.44, "learning_rate": 3.8134108271773184e-05, "loss": 0.0034, "step": 201740 }, { "epoch": 48.44, "learning_rate": 3.8129749538964506e-05, "loss": 0.0138, "step": 201750 }, { "epoch": 48.44, "learning_rate": 3.8125390901748604e-05, "loss": 0.0069, "step": 201760 }, { "epoch": 48.44, "learning_rate": 3.812103236016054e-05, "loss": 0.0082, "step": 201770 }, { "epoch": 48.45, "learning_rate": 3.8116673914235464e-05, "loss": 0.011, "step": 201780 }, { "epoch": 48.45, "learning_rate": 3.811231556400843e-05, "loss": 0.0042, "step": 201790 }, { "epoch": 48.45, "learning_rate": 3.8107957309514584e-05, "loss": 0.0209, "step": 201800 }, { "epoch": 48.45, "learning_rate": 3.8103599150789005e-05, "loss": 0.0049, "step": 201810 }, { "epoch": 48.46, "learning_rate": 3.809924108786676e-05, "loss": 0.0075, "step": 201820 }, { "epoch": 48.46, "learning_rate": 3.809488312078298e-05, "loss": 0.0164, "step": 201830 }, { "epoch": 48.46, "learning_rate": 3.809052524957275e-05, "loss": 0.007, "step": 201840 }, { "epoch": 48.46, "learning_rate": 3.808616747427119e-05, "loss": 0.007, "step": 201850 }, { "epoch": 48.47, "learning_rate": 3.8081809794913326e-05, "loss": 0.0065, "step": 201860 }, { "epoch": 48.47, "learning_rate": 3.807745221153431e-05, "loss": 0.0121, "step": 201870 }, { "epoch": 48.47, "learning_rate": 3.807309472416921e-05, "loss": 0.0134, "step": 201880 }, { "epoch": 48.47, "learning_rate": 3.806873733285314e-05, "loss": 0.0171, "step": 201890 }, { "epoch": 48.47, "learning_rate": 3.806438003762118e-05, "loss": 0.0078, "step": 201900 }, { "epoch": 48.48, "learning_rate": 3.806002283850839e-05, "loss": 0.0092, "step": 201910 }, { "epoch": 48.48, "learning_rate": 3.80556657355499e-05, "loss": 0.0079, "step": 201920 }, { "epoch": 48.48, "learning_rate": 3.805130872878077e-05, "loss": 0.0049, "step": 201930 }, { "epoch": 48.48, "learning_rate": 3.8046951818236113e-05, "loss": 0.0053, "step": 201940 }, { "epoch": 48.49, "learning_rate": 3.8042595003951016e-05, "loss": 0.0044, "step": 201950 }, { "epoch": 48.49, "learning_rate": 3.803823828596053e-05, "loss": 0.0052, "step": 201960 }, { "epoch": 48.49, "learning_rate": 3.803388166429977e-05, "loss": 0.0085, "step": 201970 }, { "epoch": 48.49, "learning_rate": 3.8029525139003806e-05, "loss": 0.0122, "step": 201980 }, { "epoch": 48.49, "learning_rate": 3.802516871010775e-05, "loss": 0.0053, "step": 201990 }, { "epoch": 48.5, "learning_rate": 3.8020812377646644e-05, "loss": 0.0062, "step": 202000 }, { "epoch": 48.5, "learning_rate": 3.8016456141655585e-05, "loss": 0.0033, "step": 202010 }, { "epoch": 48.5, "learning_rate": 3.801210000216967e-05, "loss": 0.0034, "step": 202020 }, { "epoch": 48.5, "learning_rate": 3.800774395922396e-05, "loss": 0.0127, "step": 202030 }, { "epoch": 48.51, "learning_rate": 3.800338801285357e-05, "loss": 0.0066, "step": 202040 }, { "epoch": 48.51, "learning_rate": 3.799903216309353e-05, "loss": 0.0108, "step": 202050 }, { "epoch": 48.51, "learning_rate": 3.799467640997894e-05, "loss": 0.0083, "step": 202060 }, { "epoch": 48.51, "learning_rate": 3.799032075354489e-05, "loss": 0.0087, "step": 202070 }, { "epoch": 48.52, "learning_rate": 3.7985965193826423e-05, "loss": 0.0096, "step": 202080 }, { "epoch": 48.52, "learning_rate": 3.798160973085868e-05, "loss": 0.0051, "step": 202090 }, { "epoch": 48.52, "learning_rate": 3.797725436467665e-05, "loss": 0.0043, "step": 202100 }, { "epoch": 48.52, "learning_rate": 3.797289909531547e-05, "loss": 0.0066, "step": 202110 }, { "epoch": 48.52, "learning_rate": 3.796854392281019e-05, "loss": 0.0069, "step": 202120 }, { "epoch": 48.53, "learning_rate": 3.796418884719588e-05, "loss": 0.0104, "step": 202130 }, { "epoch": 48.53, "learning_rate": 3.795983386850764e-05, "loss": 0.0028, "step": 202140 }, { "epoch": 48.53, "learning_rate": 3.7955478986780494e-05, "loss": 0.0126, "step": 202150 }, { "epoch": 48.53, "learning_rate": 3.7951124202049554e-05, "loss": 0.0095, "step": 202160 }, { "epoch": 48.54, "learning_rate": 3.7946769514349864e-05, "loss": 0.0092, "step": 202170 }, { "epoch": 48.54, "learning_rate": 3.7942414923716517e-05, "loss": 0.0075, "step": 202180 }, { "epoch": 48.54, "learning_rate": 3.793806043018456e-05, "loss": 0.0159, "step": 202190 }, { "epoch": 48.54, "learning_rate": 3.793370603378906e-05, "loss": 0.0052, "step": 202200 }, { "epoch": 48.55, "learning_rate": 3.79293517345651e-05, "loss": 0.0111, "step": 202210 }, { "epoch": 48.55, "learning_rate": 3.792499753254773e-05, "loss": 0.0286, "step": 202220 }, { "epoch": 48.55, "learning_rate": 3.7920643427772043e-05, "loss": 0.011, "step": 202230 }, { "epoch": 48.55, "learning_rate": 3.791628942027307e-05, "loss": 0.0128, "step": 202240 }, { "epoch": 48.55, "learning_rate": 3.7911935510085864e-05, "loss": 0.0071, "step": 202250 }, { "epoch": 48.56, "learning_rate": 3.7907581697245536e-05, "loss": 0.0089, "step": 202260 }, { "epoch": 48.56, "learning_rate": 3.79032279817871e-05, "loss": 0.0134, "step": 202270 }, { "epoch": 48.56, "learning_rate": 3.789887436374568e-05, "loss": 0.0032, "step": 202280 }, { "epoch": 48.56, "learning_rate": 3.789452084315627e-05, "loss": 0.0134, "step": 202290 }, { "epoch": 48.57, "learning_rate": 3.7890167420053954e-05, "loss": 0.0134, "step": 202300 }, { "epoch": 48.57, "learning_rate": 3.788581409447378e-05, "loss": 0.0099, "step": 202310 }, { "epoch": 48.57, "learning_rate": 3.788146086645084e-05, "loss": 0.0115, "step": 202320 }, { "epoch": 48.57, "learning_rate": 3.787710773602016e-05, "loss": 0.0045, "step": 202330 }, { "epoch": 48.57, "learning_rate": 3.78727547032168e-05, "loss": 0.0054, "step": 202340 }, { "epoch": 48.58, "learning_rate": 3.786840176807582e-05, "loss": 0.0144, "step": 202350 }, { "epoch": 48.58, "learning_rate": 3.7864048930632273e-05, "loss": 0.0065, "step": 202360 }, { "epoch": 48.58, "learning_rate": 3.7859696190921235e-05, "loss": 0.0061, "step": 202370 }, { "epoch": 48.58, "learning_rate": 3.785534354897773e-05, "loss": 0.0069, "step": 202380 }, { "epoch": 48.59, "learning_rate": 3.785099100483681e-05, "loss": 0.0123, "step": 202390 }, { "epoch": 48.59, "learning_rate": 3.784663855853354e-05, "loss": 0.0117, "step": 202400 }, { "epoch": 48.59, "learning_rate": 3.784228621010297e-05, "loss": 0.0134, "step": 202410 }, { "epoch": 48.59, "learning_rate": 3.7837933959580156e-05, "loss": 0.0059, "step": 202420 }, { "epoch": 48.6, "learning_rate": 3.7833581807000135e-05, "loss": 0.0198, "step": 202430 }, { "epoch": 48.6, "learning_rate": 3.782922975239795e-05, "loss": 0.0156, "step": 202440 }, { "epoch": 48.6, "learning_rate": 3.7824877795808665e-05, "loss": 0.0167, "step": 202450 }, { "epoch": 48.6, "learning_rate": 3.782052593726731e-05, "loss": 0.0045, "step": 202460 }, { "epoch": 48.6, "learning_rate": 3.781617417680896e-05, "loss": 0.0096, "step": 202470 }, { "epoch": 48.61, "learning_rate": 3.781182251446864e-05, "loss": 0.0112, "step": 202480 }, { "epoch": 48.61, "learning_rate": 3.7807470950281376e-05, "loss": 0.0113, "step": 202490 }, { "epoch": 48.61, "learning_rate": 3.780311948428225e-05, "loss": 0.0335, "step": 202500 }, { "epoch": 48.61, "learning_rate": 3.7798768116506286e-05, "loss": 0.0264, "step": 202510 }, { "epoch": 48.62, "learning_rate": 3.7794416846988524e-05, "loss": 0.0063, "step": 202520 }, { "epoch": 48.62, "learning_rate": 3.7790065675764e-05, "loss": 0.0142, "step": 202530 }, { "epoch": 48.62, "learning_rate": 3.778571460286777e-05, "loss": 0.004, "step": 202540 }, { "epoch": 48.62, "learning_rate": 3.778136362833485e-05, "loss": 0.007, "step": 202550 }, { "epoch": 48.63, "learning_rate": 3.7777012752200325e-05, "loss": 0.0097, "step": 202560 }, { "epoch": 48.63, "learning_rate": 3.777266197449919e-05, "loss": 0.01, "step": 202570 }, { "epoch": 48.63, "learning_rate": 3.776831129526648e-05, "loss": 0.0068, "step": 202580 }, { "epoch": 48.63, "learning_rate": 3.776396071453727e-05, "loss": 0.0046, "step": 202590 }, { "epoch": 48.63, "learning_rate": 3.775961023234656e-05, "loss": 0.0049, "step": 202600 }, { "epoch": 48.64, "learning_rate": 3.775525984872942e-05, "loss": 0.0058, "step": 202610 }, { "epoch": 48.64, "learning_rate": 3.7750909563720846e-05, "loss": 0.0059, "step": 202620 }, { "epoch": 48.64, "learning_rate": 3.7746559377355885e-05, "loss": 0.0029, "step": 202630 }, { "epoch": 48.64, "learning_rate": 3.774220928966958e-05, "loss": 0.0083, "step": 202640 }, { "epoch": 48.65, "learning_rate": 3.7737859300696965e-05, "loss": 0.0176, "step": 202650 }, { "epoch": 48.65, "learning_rate": 3.7733509410473046e-05, "loss": 0.0063, "step": 202660 }, { "epoch": 48.65, "learning_rate": 3.772915961903287e-05, "loss": 0.0115, "step": 202670 }, { "epoch": 48.65, "learning_rate": 3.772480992641147e-05, "loss": 0.0051, "step": 202680 }, { "epoch": 48.65, "learning_rate": 3.772046033264386e-05, "loss": 0.0065, "step": 202690 }, { "epoch": 48.66, "learning_rate": 3.771611083776511e-05, "loss": 0.0045, "step": 202700 }, { "epoch": 48.66, "learning_rate": 3.77117614418102e-05, "loss": 0.0066, "step": 202710 }, { "epoch": 48.66, "learning_rate": 3.770741214481415e-05, "loss": 0.0071, "step": 202720 }, { "epoch": 48.66, "learning_rate": 3.770306294681203e-05, "loss": 0.0056, "step": 202730 }, { "epoch": 48.67, "learning_rate": 3.769871384783882e-05, "loss": 0.0094, "step": 202740 }, { "epoch": 48.67, "learning_rate": 3.76943648479296e-05, "loss": 0.0063, "step": 202750 }, { "epoch": 48.67, "learning_rate": 3.769001594711933e-05, "loss": 0.0088, "step": 202760 }, { "epoch": 48.67, "learning_rate": 3.7685667145443066e-05, "loss": 0.005, "step": 202770 }, { "epoch": 48.68, "learning_rate": 3.768131844293583e-05, "loss": 0.0146, "step": 202780 }, { "epoch": 48.68, "learning_rate": 3.767696983963263e-05, "loss": 0.0067, "step": 202790 }, { "epoch": 48.68, "learning_rate": 3.7672621335568514e-05, "loss": 0.0164, "step": 202800 }, { "epoch": 48.68, "learning_rate": 3.766827293077846e-05, "loss": 0.0063, "step": 202810 }, { "epoch": 48.68, "learning_rate": 3.7663924625297505e-05, "loss": 0.0065, "step": 202820 }, { "epoch": 48.69, "learning_rate": 3.765957641916068e-05, "loss": 0.0139, "step": 202830 }, { "epoch": 48.69, "learning_rate": 3.7655228312403e-05, "loss": 0.0067, "step": 202840 }, { "epoch": 48.69, "learning_rate": 3.7650880305059445e-05, "loss": 0.009, "step": 202850 }, { "epoch": 48.69, "learning_rate": 3.764653239716507e-05, "loss": 0.0064, "step": 202860 }, { "epoch": 48.7, "learning_rate": 3.764218458875486e-05, "loss": 0.0043, "step": 202870 }, { "epoch": 48.7, "learning_rate": 3.7637836879863855e-05, "loss": 0.006, "step": 202880 }, { "epoch": 48.7, "learning_rate": 3.763348927052707e-05, "loss": 0.0063, "step": 202890 }, { "epoch": 48.7, "learning_rate": 3.762914176077949e-05, "loss": 0.0146, "step": 202900 }, { "epoch": 48.71, "learning_rate": 3.762479435065613e-05, "loss": 0.0074, "step": 202910 }, { "epoch": 48.71, "learning_rate": 3.762044704019202e-05, "loss": 0.0074, "step": 202920 }, { "epoch": 48.71, "learning_rate": 3.7616099829422154e-05, "loss": 0.0035, "step": 202930 }, { "epoch": 48.71, "learning_rate": 3.7611752718381565e-05, "loss": 0.0078, "step": 202940 }, { "epoch": 48.71, "learning_rate": 3.760740570710523e-05, "loss": 0.0057, "step": 202950 }, { "epoch": 48.72, "learning_rate": 3.760305879562815e-05, "loss": 0.011, "step": 202960 }, { "epoch": 48.72, "learning_rate": 3.759871198398537e-05, "loss": 0.0049, "step": 202970 }, { "epoch": 48.72, "learning_rate": 3.759436527221187e-05, "loss": 0.0129, "step": 202980 }, { "epoch": 48.72, "learning_rate": 3.759001866034265e-05, "loss": 0.0098, "step": 202990 }, { "epoch": 48.73, "learning_rate": 3.7585672148412734e-05, "loss": 0.0097, "step": 203000 }, { "epoch": 48.73, "learning_rate": 3.75813257364571e-05, "loss": 0.0081, "step": 203010 }, { "epoch": 48.73, "learning_rate": 3.757697942451078e-05, "loss": 0.005, "step": 203020 }, { "epoch": 48.73, "learning_rate": 3.757263321260876e-05, "loss": 0.0101, "step": 203030 }, { "epoch": 48.73, "learning_rate": 3.756828710078603e-05, "loss": 0.0076, "step": 203040 }, { "epoch": 48.74, "learning_rate": 3.75639410890776e-05, "loss": 0.0121, "step": 203050 }, { "epoch": 48.74, "learning_rate": 3.7559595177518466e-05, "loss": 0.0063, "step": 203060 }, { "epoch": 48.74, "learning_rate": 3.755524936614365e-05, "loss": 0.0069, "step": 203070 }, { "epoch": 48.74, "learning_rate": 3.755090365498812e-05, "loss": 0.0094, "step": 203080 }, { "epoch": 48.75, "learning_rate": 3.7546558044086875e-05, "loss": 0.0071, "step": 203090 }, { "epoch": 48.75, "learning_rate": 3.754221253347492e-05, "loss": 0.0176, "step": 203100 }, { "epoch": 48.75, "learning_rate": 3.753786712318724e-05, "loss": 0.0029, "step": 203110 }, { "epoch": 48.75, "learning_rate": 3.753352181325884e-05, "loss": 0.0128, "step": 203120 }, { "epoch": 48.76, "learning_rate": 3.752917660372473e-05, "loss": 0.0034, "step": 203130 }, { "epoch": 48.76, "learning_rate": 3.752483149461987e-05, "loss": 0.0065, "step": 203140 }, { "epoch": 48.76, "learning_rate": 3.7520486485979254e-05, "loss": 0.0106, "step": 203150 }, { "epoch": 48.76, "learning_rate": 3.751614157783789e-05, "loss": 0.0069, "step": 203160 }, { "epoch": 48.76, "learning_rate": 3.751179677023078e-05, "loss": 0.0051, "step": 203170 }, { "epoch": 48.77, "learning_rate": 3.750745206319287e-05, "loss": 0.0177, "step": 203180 }, { "epoch": 48.77, "learning_rate": 3.750310745675918e-05, "loss": 0.0101, "step": 203190 }, { "epoch": 48.77, "learning_rate": 3.749876295096468e-05, "loss": 0.0095, "step": 203200 }, { "epoch": 48.77, "learning_rate": 3.7494418545844376e-05, "loss": 0.0101, "step": 203210 }, { "epoch": 48.78, "learning_rate": 3.749007424143326e-05, "loss": 0.0084, "step": 203220 }, { "epoch": 48.78, "learning_rate": 3.748573003776629e-05, "loss": 0.0076, "step": 203230 }, { "epoch": 48.78, "learning_rate": 3.7481385934878465e-05, "loss": 0.0067, "step": 203240 }, { "epoch": 48.78, "learning_rate": 3.7477041932804756e-05, "loss": 0.0069, "step": 203250 }, { "epoch": 48.79, "learning_rate": 3.747269803158017e-05, "loss": 0.0075, "step": 203260 }, { "epoch": 48.79, "learning_rate": 3.7468354231239686e-05, "loss": 0.0168, "step": 203270 }, { "epoch": 48.79, "learning_rate": 3.746401053181826e-05, "loss": 0.0093, "step": 203280 }, { "epoch": 48.79, "learning_rate": 3.745966693335089e-05, "loss": 0.0074, "step": 203290 }, { "epoch": 48.79, "learning_rate": 3.7455323435872546e-05, "loss": 0.0072, "step": 203300 }, { "epoch": 48.8, "learning_rate": 3.745098003941824e-05, "loss": 0.0071, "step": 203310 }, { "epoch": 48.8, "learning_rate": 3.744663674402291e-05, "loss": 0.0033, "step": 203320 }, { "epoch": 48.8, "learning_rate": 3.744229354972154e-05, "loss": 0.0049, "step": 203330 }, { "epoch": 48.8, "learning_rate": 3.743795045654912e-05, "loss": 0.0036, "step": 203340 }, { "epoch": 48.81, "learning_rate": 3.743360746454061e-05, "loss": 0.0118, "step": 203350 }, { "epoch": 48.81, "learning_rate": 3.7429264573731024e-05, "loss": 0.0147, "step": 203360 }, { "epoch": 48.81, "learning_rate": 3.742492178415528e-05, "loss": 0.0043, "step": 203370 }, { "epoch": 48.81, "learning_rate": 3.7420579095848386e-05, "loss": 0.0059, "step": 203380 }, { "epoch": 48.81, "learning_rate": 3.741623650884529e-05, "loss": 0.0073, "step": 203390 }, { "epoch": 48.82, "learning_rate": 3.741189402318099e-05, "loss": 0.0049, "step": 203400 }, { "epoch": 48.82, "learning_rate": 3.740755163889046e-05, "loss": 0.0081, "step": 203410 }, { "epoch": 48.82, "learning_rate": 3.740320935600863e-05, "loss": 0.0039, "step": 203420 }, { "epoch": 48.82, "learning_rate": 3.7398867174570504e-05, "loss": 0.0175, "step": 203430 }, { "epoch": 48.83, "learning_rate": 3.739452509461103e-05, "loss": 0.0046, "step": 203440 }, { "epoch": 48.83, "learning_rate": 3.73901831161652e-05, "loss": 0.0082, "step": 203450 }, { "epoch": 48.83, "learning_rate": 3.738584123926798e-05, "loss": 0.0061, "step": 203460 }, { "epoch": 48.83, "learning_rate": 3.738149946395429e-05, "loss": 0.0094, "step": 203470 }, { "epoch": 48.84, "learning_rate": 3.737715779025915e-05, "loss": 0.0064, "step": 203480 }, { "epoch": 48.84, "learning_rate": 3.737281621821748e-05, "loss": 0.0104, "step": 203490 }, { "epoch": 48.84, "learning_rate": 3.736847474786429e-05, "loss": 0.0061, "step": 203500 }, { "epoch": 48.84, "learning_rate": 3.7364133379234506e-05, "loss": 0.0068, "step": 203510 }, { "epoch": 48.84, "learning_rate": 3.735979211236309e-05, "loss": 0.0098, "step": 203520 }, { "epoch": 48.85, "learning_rate": 3.735545094728502e-05, "loss": 0.0135, "step": 203530 }, { "epoch": 48.85, "learning_rate": 3.735110988403524e-05, "loss": 0.005, "step": 203540 }, { "epoch": 48.85, "learning_rate": 3.734676892264874e-05, "loss": 0.0116, "step": 203550 }, { "epoch": 48.85, "learning_rate": 3.734242806316045e-05, "loss": 0.0043, "step": 203560 }, { "epoch": 48.86, "learning_rate": 3.7338087305605325e-05, "loss": 0.0073, "step": 203570 }, { "epoch": 48.86, "learning_rate": 3.733374665001834e-05, "loss": 0.0102, "step": 203580 }, { "epoch": 48.86, "learning_rate": 3.7329406096434435e-05, "loss": 0.008, "step": 203590 }, { "epoch": 48.86, "learning_rate": 3.732506564488859e-05, "loss": 0.0051, "step": 203600 }, { "epoch": 48.87, "learning_rate": 3.7320725295415715e-05, "loss": 0.0064, "step": 203610 }, { "epoch": 48.87, "learning_rate": 3.73163850480508e-05, "loss": 0.0076, "step": 203620 }, { "epoch": 48.87, "learning_rate": 3.731204490282878e-05, "loss": 0.0048, "step": 203630 }, { "epoch": 48.87, "learning_rate": 3.7307704859784635e-05, "loss": 0.0048, "step": 203640 }, { "epoch": 48.87, "learning_rate": 3.730336491895329e-05, "loss": 0.0226, "step": 203650 }, { "epoch": 48.88, "learning_rate": 3.7299025080369676e-05, "loss": 0.0027, "step": 203660 }, { "epoch": 48.88, "learning_rate": 3.7294685344068794e-05, "loss": 0.0077, "step": 203670 }, { "epoch": 48.88, "learning_rate": 3.729034571008554e-05, "loss": 0.0107, "step": 203680 }, { "epoch": 48.88, "learning_rate": 3.728600617845491e-05, "loss": 0.0217, "step": 203690 }, { "epoch": 48.89, "learning_rate": 3.728166674921182e-05, "loss": 0.0071, "step": 203700 }, { "epoch": 48.89, "learning_rate": 3.727732742239122e-05, "loss": 0.0041, "step": 203710 }, { "epoch": 48.89, "learning_rate": 3.727298819802806e-05, "loss": 0.0088, "step": 203720 }, { "epoch": 48.89, "learning_rate": 3.726864907615727e-05, "loss": 0.0107, "step": 203730 }, { "epoch": 48.89, "learning_rate": 3.7264310056813836e-05, "loss": 0.015, "step": 203740 }, { "epoch": 48.9, "learning_rate": 3.725997114003266e-05, "loss": 0.0091, "step": 203750 }, { "epoch": 48.9, "learning_rate": 3.725563232584868e-05, "loss": 0.0129, "step": 203760 }, { "epoch": 48.9, "learning_rate": 3.725129361429687e-05, "loss": 0.0085, "step": 203770 }, { "epoch": 48.9, "learning_rate": 3.7246955005412135e-05, "loss": 0.006, "step": 203780 }, { "epoch": 48.91, "learning_rate": 3.724261649922946e-05, "loss": 0.005, "step": 203790 }, { "epoch": 48.91, "learning_rate": 3.723827809578373e-05, "loss": 0.0096, "step": 203800 }, { "epoch": 48.91, "learning_rate": 3.723393979510992e-05, "loss": 0.0091, "step": 203810 }, { "epoch": 48.91, "learning_rate": 3.722960159724294e-05, "loss": 0.0086, "step": 203820 }, { "epoch": 48.92, "learning_rate": 3.7225263502217764e-05, "loss": 0.0058, "step": 203830 }, { "epoch": 48.92, "learning_rate": 3.72209255100693e-05, "loss": 0.0099, "step": 203840 }, { "epoch": 48.92, "learning_rate": 3.721658762083247e-05, "loss": 0.0081, "step": 203850 }, { "epoch": 48.92, "learning_rate": 3.721224983454224e-05, "loss": 0.0141, "step": 203860 }, { "epoch": 48.92, "learning_rate": 3.720791215123352e-05, "loss": 0.0053, "step": 203870 }, { "epoch": 48.93, "learning_rate": 3.720357457094126e-05, "loss": 0.0045, "step": 203880 }, { "epoch": 48.93, "learning_rate": 3.719923709370038e-05, "loss": 0.0147, "step": 203890 }, { "epoch": 48.93, "learning_rate": 3.71948997195458e-05, "loss": 0.0151, "step": 203900 }, { "epoch": 48.93, "learning_rate": 3.7190562448512455e-05, "loss": 0.0072, "step": 203910 }, { "epoch": 48.94, "learning_rate": 3.7186225280635285e-05, "loss": 0.0066, "step": 203920 }, { "epoch": 48.94, "learning_rate": 3.7181888215949225e-05, "loss": 0.0073, "step": 203930 }, { "epoch": 48.94, "learning_rate": 3.7177551254489186e-05, "loss": 0.0142, "step": 203940 }, { "epoch": 48.94, "learning_rate": 3.717321439629008e-05, "loss": 0.0057, "step": 203950 }, { "epoch": 48.95, "learning_rate": 3.716887764138686e-05, "loss": 0.0171, "step": 203960 }, { "epoch": 48.95, "learning_rate": 3.7164540989814454e-05, "loss": 0.0127, "step": 203970 }, { "epoch": 48.95, "learning_rate": 3.716020444160775e-05, "loss": 0.006, "step": 203980 }, { "epoch": 49.0, "learning_rate": 3.71558679968017e-05, "loss": 0.0096, "step": 203990 }, { "epoch": 49.0, "learning_rate": 3.7151531655431204e-05, "loss": 0.0067, "step": 204000 }, { "epoch": 49.01, "learning_rate": 3.714719541753122e-05, "loss": 0.0159, "step": 204010 }, { "epoch": 49.01, "learning_rate": 3.714285928313665e-05, "loss": 0.0128, "step": 204020 }, { "epoch": 49.01, "learning_rate": 3.71385232522824e-05, "loss": 0.0079, "step": 204030 }, { "epoch": 49.01, "learning_rate": 3.7134187325003376e-05, "loss": 0.0039, "step": 204040 }, { "epoch": 49.01, "learning_rate": 3.712985150133455e-05, "loss": 0.0154, "step": 204050 }, { "epoch": 49.02, "learning_rate": 3.7125515781310776e-05, "loss": 0.003, "step": 204060 }, { "epoch": 49.02, "learning_rate": 3.712118016496703e-05, "loss": 0.0085, "step": 204070 }, { "epoch": 49.02, "learning_rate": 3.7116844652338186e-05, "loss": 0.0089, "step": 204080 }, { "epoch": 49.02, "learning_rate": 3.711250924345916e-05, "loss": 0.003, "step": 204090 }, { "epoch": 49.03, "learning_rate": 3.710817393836489e-05, "loss": 0.0067, "step": 204100 }, { "epoch": 49.03, "learning_rate": 3.7103838737090266e-05, "loss": 0.007, "step": 204110 }, { "epoch": 49.03, "learning_rate": 3.709950363967022e-05, "loss": 0.0058, "step": 204120 }, { "epoch": 49.03, "learning_rate": 3.709516864613965e-05, "loss": 0.005, "step": 204130 }, { "epoch": 49.03, "learning_rate": 3.709083375653346e-05, "loss": 0.0032, "step": 204140 }, { "epoch": 49.04, "learning_rate": 3.708649897088657e-05, "loss": 0.0082, "step": 204150 }, { "epoch": 49.04, "learning_rate": 3.708216428923391e-05, "loss": 0.0128, "step": 204160 }, { "epoch": 49.04, "learning_rate": 3.7077829711610335e-05, "loss": 0.0132, "step": 204170 }, { "epoch": 49.04, "learning_rate": 3.707349523805079e-05, "loss": 0.0047, "step": 204180 }, { "epoch": 49.05, "learning_rate": 3.7069160868590164e-05, "loss": 0.0096, "step": 204190 }, { "epoch": 49.05, "learning_rate": 3.706482660326338e-05, "loss": 0.0072, "step": 204200 }, { "epoch": 49.05, "learning_rate": 3.706049244210535e-05, "loss": 0.0103, "step": 204210 }, { "epoch": 49.05, "learning_rate": 3.705615838515094e-05, "loss": 0.0032, "step": 204220 }, { "epoch": 49.06, "learning_rate": 3.7051824432435076e-05, "loss": 0.004, "step": 204230 }, { "epoch": 49.06, "learning_rate": 3.704749058399266e-05, "loss": 0.007, "step": 204240 }, { "epoch": 49.06, "learning_rate": 3.7043156839858576e-05, "loss": 0.0083, "step": 204250 }, { "epoch": 49.06, "learning_rate": 3.7038823200067764e-05, "loss": 0.0144, "step": 204260 }, { "epoch": 49.06, "learning_rate": 3.7034489664655094e-05, "loss": 0.0106, "step": 204270 }, { "epoch": 49.07, "learning_rate": 3.703015623365545e-05, "loss": 0.0043, "step": 204280 }, { "epoch": 49.07, "learning_rate": 3.702582290710376e-05, "loss": 0.0063, "step": 204290 }, { "epoch": 49.07, "learning_rate": 3.702148968503492e-05, "loss": 0.0053, "step": 204300 }, { "epoch": 49.07, "learning_rate": 3.70171565674838e-05, "loss": 0.0101, "step": 204310 }, { "epoch": 49.08, "learning_rate": 3.701282355448531e-05, "loss": 0.0064, "step": 204320 }, { "epoch": 49.08, "learning_rate": 3.700849064607434e-05, "loss": 0.0084, "step": 204330 }, { "epoch": 49.08, "learning_rate": 3.7004157842285805e-05, "loss": 0.0049, "step": 204340 }, { "epoch": 49.08, "learning_rate": 3.6999825143154585e-05, "loss": 0.0089, "step": 204350 }, { "epoch": 49.09, "learning_rate": 3.6995492548715546e-05, "loss": 0.0065, "step": 204360 }, { "epoch": 49.09, "learning_rate": 3.6991160059003613e-05, "loss": 0.0058, "step": 204370 }, { "epoch": 49.09, "learning_rate": 3.698682767405366e-05, "loss": 0.007, "step": 204380 }, { "epoch": 49.09, "learning_rate": 3.698249539390058e-05, "loss": 0.0086, "step": 204390 }, { "epoch": 49.09, "learning_rate": 3.697816321857928e-05, "loss": 0.0078, "step": 204400 }, { "epoch": 49.1, "learning_rate": 3.69738311481246e-05, "loss": 0.0064, "step": 204410 }, { "epoch": 49.1, "learning_rate": 3.696949918257148e-05, "loss": 0.0055, "step": 204420 }, { "epoch": 49.1, "learning_rate": 3.696516732195476e-05, "loss": 0.007, "step": 204430 }, { "epoch": 49.1, "learning_rate": 3.6960835566309365e-05, "loss": 0.0094, "step": 204440 }, { "epoch": 49.11, "learning_rate": 3.6956503915670174e-05, "loss": 0.0042, "step": 204450 }, { "epoch": 49.11, "learning_rate": 3.6952172370072034e-05, "loss": 0.0084, "step": 204460 }, { "epoch": 49.11, "learning_rate": 3.694784092954985e-05, "loss": 0.009, "step": 204470 }, { "epoch": 49.11, "learning_rate": 3.6943509594138516e-05, "loss": 0.003, "step": 204480 }, { "epoch": 49.11, "learning_rate": 3.6939178363872906e-05, "loss": 0.0072, "step": 204490 }, { "epoch": 49.12, "learning_rate": 3.6934847238787884e-05, "loss": 0.0045, "step": 204500 }, { "epoch": 49.12, "learning_rate": 3.693051621891834e-05, "loss": 0.0045, "step": 204510 }, { "epoch": 49.12, "learning_rate": 3.692618530429915e-05, "loss": 0.0124, "step": 204520 }, { "epoch": 49.12, "learning_rate": 3.692185449496521e-05, "loss": 0.0158, "step": 204530 }, { "epoch": 49.13, "learning_rate": 3.691752379095138e-05, "loss": 0.0053, "step": 204540 }, { "epoch": 49.13, "learning_rate": 3.691319319229253e-05, "loss": 0.0049, "step": 204550 }, { "epoch": 49.13, "learning_rate": 3.690886269902354e-05, "loss": 0.0071, "step": 204560 }, { "epoch": 49.13, "learning_rate": 3.690453231117928e-05, "loss": 0.0101, "step": 204570 }, { "epoch": 49.14, "learning_rate": 3.6900202028794636e-05, "loss": 0.005, "step": 204580 }, { "epoch": 49.14, "learning_rate": 3.689587185190449e-05, "loss": 0.0076, "step": 204590 }, { "epoch": 49.14, "learning_rate": 3.6891541780543676e-05, "loss": 0.0064, "step": 204600 }, { "epoch": 49.14, "learning_rate": 3.688721181474709e-05, "loss": 0.0063, "step": 204610 }, { "epoch": 49.14, "learning_rate": 3.68828819545496e-05, "loss": 0.0105, "step": 204620 }, { "epoch": 49.15, "learning_rate": 3.68785521999861e-05, "loss": 0.006, "step": 204630 }, { "epoch": 49.15, "learning_rate": 3.6874222551091386e-05, "loss": 0.0165, "step": 204640 }, { "epoch": 49.15, "learning_rate": 3.686989300790039e-05, "loss": 0.0059, "step": 204650 }, { "epoch": 49.15, "learning_rate": 3.6865563570447945e-05, "loss": 0.0122, "step": 204660 }, { "epoch": 49.16, "learning_rate": 3.6861234238768944e-05, "loss": 0.0028, "step": 204670 }, { "epoch": 49.16, "learning_rate": 3.685690501289825e-05, "loss": 0.0062, "step": 204680 }, { "epoch": 49.16, "learning_rate": 3.685257589287069e-05, "loss": 0.0129, "step": 204690 }, { "epoch": 49.16, "learning_rate": 3.684824687872116e-05, "loss": 0.005, "step": 204700 }, { "epoch": 49.17, "learning_rate": 3.6843917970484504e-05, "loss": 0.0077, "step": 204710 }, { "epoch": 49.17, "learning_rate": 3.6839589168195605e-05, "loss": 0.0247, "step": 204720 }, { "epoch": 49.17, "learning_rate": 3.683526047188932e-05, "loss": 0.0092, "step": 204730 }, { "epoch": 49.17, "learning_rate": 3.683093188160048e-05, "loss": 0.0077, "step": 204740 }, { "epoch": 49.17, "learning_rate": 3.682660339736397e-05, "loss": 0.0031, "step": 204750 }, { "epoch": 49.18, "learning_rate": 3.682227501921464e-05, "loss": 0.0078, "step": 204760 }, { "epoch": 49.18, "learning_rate": 3.681794674718735e-05, "loss": 0.0055, "step": 204770 }, { "epoch": 49.18, "learning_rate": 3.6813618581316976e-05, "loss": 0.0103, "step": 204780 }, { "epoch": 49.18, "learning_rate": 3.680929052163832e-05, "loss": 0.0044, "step": 204790 }, { "epoch": 49.19, "learning_rate": 3.6804962568186286e-05, "loss": 0.0064, "step": 204800 }, { "epoch": 49.19, "learning_rate": 3.68006347209957e-05, "loss": 0.0054, "step": 204810 }, { "epoch": 49.19, "learning_rate": 3.679630698010144e-05, "loss": 0.006, "step": 204820 }, { "epoch": 49.19, "learning_rate": 3.6791979345538335e-05, "loss": 0.0049, "step": 204830 }, { "epoch": 49.19, "learning_rate": 3.678765181734124e-05, "loss": 0.0072, "step": 204840 }, { "epoch": 49.2, "learning_rate": 3.6783324395545e-05, "loss": 0.0071, "step": 204850 }, { "epoch": 49.2, "learning_rate": 3.677899708018448e-05, "loss": 0.0078, "step": 204860 }, { "epoch": 49.2, "learning_rate": 3.677466987129455e-05, "loss": 0.0067, "step": 204870 }, { "epoch": 49.2, "learning_rate": 3.6770342768910005e-05, "loss": 0.0168, "step": 204880 }, { "epoch": 49.21, "learning_rate": 3.6766015773065715e-05, "loss": 0.0046, "step": 204890 }, { "epoch": 49.21, "learning_rate": 3.676168888379652e-05, "loss": 0.0059, "step": 204900 }, { "epoch": 49.21, "learning_rate": 3.675736210113728e-05, "loss": 0.0061, "step": 204910 }, { "epoch": 49.21, "learning_rate": 3.675303542512285e-05, "loss": 0.0049, "step": 204920 }, { "epoch": 49.22, "learning_rate": 3.674870885578803e-05, "loss": 0.0195, "step": 204930 }, { "epoch": 49.22, "learning_rate": 3.6744382393167694e-05, "loss": 0.0023, "step": 204940 }, { "epoch": 49.22, "learning_rate": 3.674005603729667e-05, "loss": 0.0086, "step": 204950 }, { "epoch": 49.22, "learning_rate": 3.673572978820982e-05, "loss": 0.0091, "step": 204960 }, { "epoch": 49.22, "learning_rate": 3.6731403645941966e-05, "loss": 0.0092, "step": 204970 }, { "epoch": 49.23, "learning_rate": 3.672707761052794e-05, "loss": 0.0094, "step": 204980 }, { "epoch": 49.23, "learning_rate": 3.672275168200259e-05, "loss": 0.0032, "step": 204990 }, { "epoch": 49.23, "learning_rate": 3.671842586040075e-05, "loss": 0.0032, "step": 205000 }, { "epoch": 49.23, "learning_rate": 3.671410014575729e-05, "loss": 0.0035, "step": 205010 }, { "epoch": 49.24, "learning_rate": 3.6709774538106995e-05, "loss": 0.0074, "step": 205020 }, { "epoch": 49.24, "learning_rate": 3.6705449037484715e-05, "loss": 0.0038, "step": 205030 }, { "epoch": 49.24, "learning_rate": 3.670112364392529e-05, "loss": 0.008, "step": 205040 }, { "epoch": 49.24, "learning_rate": 3.6696798357463555e-05, "loss": 0.0065, "step": 205050 }, { "epoch": 49.25, "learning_rate": 3.669247317813437e-05, "loss": 0.0048, "step": 205060 }, { "epoch": 49.25, "learning_rate": 3.66881481059725e-05, "loss": 0.0056, "step": 205070 }, { "epoch": 49.25, "learning_rate": 3.668382314101282e-05, "loss": 0.003, "step": 205080 }, { "epoch": 49.25, "learning_rate": 3.667949828329014e-05, "loss": 0.0027, "step": 205090 }, { "epoch": 49.25, "learning_rate": 3.6675173532839306e-05, "loss": 0.006, "step": 205100 }, { "epoch": 49.26, "learning_rate": 3.667084888969515e-05, "loss": 0.0061, "step": 205110 }, { "epoch": 49.26, "learning_rate": 3.666652435389248e-05, "loss": 0.006, "step": 205120 }, { "epoch": 49.26, "learning_rate": 3.666219992546613e-05, "loss": 0.0129, "step": 205130 }, { "epoch": 49.26, "learning_rate": 3.665787560445092e-05, "loss": 0.0035, "step": 205140 }, { "epoch": 49.27, "learning_rate": 3.6653551390881694e-05, "loss": 0.0048, "step": 205150 }, { "epoch": 49.27, "learning_rate": 3.6649227284793255e-05, "loss": 0.0132, "step": 205160 }, { "epoch": 49.27, "learning_rate": 3.664490328622042e-05, "loss": 0.0069, "step": 205170 }, { "epoch": 49.27, "learning_rate": 3.664057939519804e-05, "loss": 0.0046, "step": 205180 }, { "epoch": 49.27, "learning_rate": 3.6636255611760903e-05, "loss": 0.0095, "step": 205190 }, { "epoch": 49.28, "learning_rate": 3.6631931935943863e-05, "loss": 0.0138, "step": 205200 }, { "epoch": 49.28, "learning_rate": 3.662760836778171e-05, "loss": 0.0043, "step": 205210 }, { "epoch": 49.28, "learning_rate": 3.6623284907309264e-05, "loss": 0.0079, "step": 205220 }, { "epoch": 49.28, "learning_rate": 3.661896155456136e-05, "loss": 0.0031, "step": 205230 }, { "epoch": 49.29, "learning_rate": 3.66146383095728e-05, "loss": 0.0075, "step": 205240 }, { "epoch": 49.29, "learning_rate": 3.661031517237843e-05, "loss": 0.0053, "step": 205250 }, { "epoch": 49.29, "learning_rate": 3.660599214301302e-05, "loss": 0.0077, "step": 205260 }, { "epoch": 49.29, "learning_rate": 3.6601669221511395e-05, "loss": 0.0104, "step": 205270 }, { "epoch": 49.3, "learning_rate": 3.6597346407908396e-05, "loss": 0.0031, "step": 205280 }, { "epoch": 49.3, "learning_rate": 3.659302370223881e-05, "loss": 0.0102, "step": 205290 }, { "epoch": 49.3, "learning_rate": 3.658870110453747e-05, "loss": 0.0058, "step": 205300 }, { "epoch": 49.3, "learning_rate": 3.658437861483915e-05, "loss": 0.0089, "step": 205310 }, { "epoch": 49.3, "learning_rate": 3.658005623317869e-05, "loss": 0.0032, "step": 205320 }, { "epoch": 49.31, "learning_rate": 3.657573395959087e-05, "loss": 0.0065, "step": 205330 }, { "epoch": 49.31, "learning_rate": 3.6571411794110556e-05, "loss": 0.0075, "step": 205340 }, { "epoch": 49.31, "learning_rate": 3.6567089736772494e-05, "loss": 0.0067, "step": 205350 }, { "epoch": 49.31, "learning_rate": 3.656276778761151e-05, "loss": 0.0104, "step": 205360 }, { "epoch": 49.32, "learning_rate": 3.655844594666242e-05, "loss": 0.0061, "step": 205370 }, { "epoch": 49.32, "learning_rate": 3.655412421396e-05, "loss": 0.0053, "step": 205380 }, { "epoch": 49.32, "learning_rate": 3.654980258953912e-05, "loss": 0.0059, "step": 205390 }, { "epoch": 49.32, "learning_rate": 3.654548107343451e-05, "loss": 0.0112, "step": 205400 }, { "epoch": 49.33, "learning_rate": 3.654115966568098e-05, "loss": 0.003, "step": 205410 }, { "epoch": 49.33, "learning_rate": 3.6536838366313374e-05, "loss": 0.0079, "step": 205420 }, { "epoch": 49.33, "learning_rate": 3.653251717536645e-05, "loss": 0.0059, "step": 205430 }, { "epoch": 49.33, "learning_rate": 3.6528196092875044e-05, "loss": 0.0062, "step": 205440 }, { "epoch": 49.33, "learning_rate": 3.652387511887393e-05, "loss": 0.0088, "step": 205450 }, { "epoch": 49.34, "learning_rate": 3.651955425339789e-05, "loss": 0.0027, "step": 205460 }, { "epoch": 49.34, "learning_rate": 3.651523349648176e-05, "loss": 0.0055, "step": 205470 }, { "epoch": 49.34, "learning_rate": 3.651091284816033e-05, "loss": 0.0043, "step": 205480 }, { "epoch": 49.34, "learning_rate": 3.650659230846836e-05, "loss": 0.0043, "step": 205490 }, { "epoch": 49.35, "learning_rate": 3.650227187744066e-05, "loss": 0.0074, "step": 205500 }, { "epoch": 49.35, "learning_rate": 3.649795155511204e-05, "loss": 0.003, "step": 205510 }, { "epoch": 49.35, "learning_rate": 3.649363134151727e-05, "loss": 0.0043, "step": 205520 }, { "epoch": 49.35, "learning_rate": 3.648931123669117e-05, "loss": 0.0038, "step": 205530 }, { "epoch": 49.35, "learning_rate": 3.6484991240668504e-05, "loss": 0.0107, "step": 205540 }, { "epoch": 49.36, "learning_rate": 3.648067135348405e-05, "loss": 0.0058, "step": 205550 }, { "epoch": 49.36, "learning_rate": 3.647635157517264e-05, "loss": 0.0065, "step": 205560 }, { "epoch": 49.36, "learning_rate": 3.647203190576902e-05, "loss": 0.0063, "step": 205570 }, { "epoch": 49.36, "learning_rate": 3.6467712345308013e-05, "loss": 0.0063, "step": 205580 }, { "epoch": 49.37, "learning_rate": 3.646339289382438e-05, "loss": 0.0177, "step": 205590 }, { "epoch": 49.37, "learning_rate": 3.6459073551352906e-05, "loss": 0.0068, "step": 205600 }, { "epoch": 49.37, "learning_rate": 3.6454754317928385e-05, "loss": 0.0067, "step": 205610 }, { "epoch": 49.37, "learning_rate": 3.6450435193585594e-05, "loss": 0.0055, "step": 205620 }, { "epoch": 49.38, "learning_rate": 3.6446116178359335e-05, "loss": 0.0129, "step": 205630 }, { "epoch": 49.38, "learning_rate": 3.6441797272284364e-05, "loss": 0.0163, "step": 205640 }, { "epoch": 49.38, "learning_rate": 3.643747847539546e-05, "loss": 0.0138, "step": 205650 }, { "epoch": 49.38, "learning_rate": 3.643315978772743e-05, "loss": 0.011, "step": 205660 }, { "epoch": 49.38, "learning_rate": 3.6428841209315046e-05, "loss": 0.0088, "step": 205670 }, { "epoch": 49.39, "learning_rate": 3.642452274019305e-05, "loss": 0.0076, "step": 205680 }, { "epoch": 49.39, "learning_rate": 3.642020438039626e-05, "loss": 0.0157, "step": 205690 }, { "epoch": 49.39, "learning_rate": 3.641588612995943e-05, "loss": 0.0101, "step": 205700 }, { "epoch": 49.39, "learning_rate": 3.641156798891736e-05, "loss": 0.0125, "step": 205710 }, { "epoch": 49.4, "learning_rate": 3.640724995730481e-05, "loss": 0.0225, "step": 205720 }, { "epoch": 49.4, "learning_rate": 3.640293203515655e-05, "loss": 0.0157, "step": 205730 }, { "epoch": 49.4, "learning_rate": 3.639861422250734e-05, "loss": 0.0089, "step": 205740 }, { "epoch": 49.4, "learning_rate": 3.639429651939198e-05, "loss": 0.01, "step": 205750 }, { "epoch": 49.41, "learning_rate": 3.638997892584522e-05, "loss": 0.0046, "step": 205760 }, { "epoch": 49.41, "learning_rate": 3.638566144190185e-05, "loss": 0.0079, "step": 205770 }, { "epoch": 49.41, "learning_rate": 3.6381344067596635e-05, "loss": 0.0031, "step": 205780 }, { "epoch": 49.41, "learning_rate": 3.637702680296431e-05, "loss": 0.0066, "step": 205790 }, { "epoch": 49.41, "learning_rate": 3.637270964803969e-05, "loss": 0.0038, "step": 205800 }, { "epoch": 49.42, "learning_rate": 3.636839260285753e-05, "loss": 0.0037, "step": 205810 }, { "epoch": 49.42, "learning_rate": 3.6364075667452555e-05, "loss": 0.0069, "step": 205820 }, { "epoch": 49.42, "learning_rate": 3.6359758841859584e-05, "loss": 0.0088, "step": 205830 }, { "epoch": 49.42, "learning_rate": 3.6355442126113335e-05, "loss": 0.0027, "step": 205840 }, { "epoch": 49.43, "learning_rate": 3.635112552024861e-05, "loss": 0.0087, "step": 205850 }, { "epoch": 49.43, "learning_rate": 3.634680902430017e-05, "loss": 0.0204, "step": 205860 }, { "epoch": 49.43, "learning_rate": 3.6342492638302736e-05, "loss": 0.0094, "step": 205870 }, { "epoch": 49.43, "learning_rate": 3.633817636229111e-05, "loss": 0.0037, "step": 205880 }, { "epoch": 49.43, "learning_rate": 3.6333860196300026e-05, "loss": 0.01, "step": 205890 }, { "epoch": 49.44, "learning_rate": 3.632954414036426e-05, "loss": 0.0201, "step": 205900 }, { "epoch": 49.44, "learning_rate": 3.632522819451857e-05, "loss": 0.0106, "step": 205910 }, { "epoch": 49.44, "learning_rate": 3.632091235879769e-05, "loss": 0.004, "step": 205920 }, { "epoch": 49.44, "learning_rate": 3.6316596633236396e-05, "loss": 0.0087, "step": 205930 }, { "epoch": 49.45, "learning_rate": 3.6312281017869443e-05, "loss": 0.009, "step": 205940 }, { "epoch": 49.45, "learning_rate": 3.630796551273157e-05, "loss": 0.0067, "step": 205950 }, { "epoch": 49.45, "learning_rate": 3.630365011785756e-05, "loss": 0.0026, "step": 205960 }, { "epoch": 49.45, "learning_rate": 3.629933483328213e-05, "loss": 0.0043, "step": 205970 }, { "epoch": 49.46, "learning_rate": 3.6295019659040045e-05, "loss": 0.0161, "step": 205980 }, { "epoch": 49.46, "learning_rate": 3.6290704595166066e-05, "loss": 0.0066, "step": 205990 }, { "epoch": 49.46, "learning_rate": 3.628638964169495e-05, "loss": 0.0047, "step": 206000 }, { "epoch": 49.46, "learning_rate": 3.6282074798661415e-05, "loss": 0.015, "step": 206010 }, { "epoch": 49.46, "learning_rate": 3.627776006610023e-05, "loss": 0.0051, "step": 206020 }, { "epoch": 49.47, "learning_rate": 3.627344544404613e-05, "loss": 0.004, "step": 206030 }, { "epoch": 49.47, "learning_rate": 3.6269130932533866e-05, "loss": 0.0168, "step": 206040 }, { "epoch": 49.47, "learning_rate": 3.626481653159821e-05, "loss": 0.0052, "step": 206050 }, { "epoch": 49.47, "learning_rate": 3.626050224127386e-05, "loss": 0.0062, "step": 206060 }, { "epoch": 49.48, "learning_rate": 3.625618806159559e-05, "loss": 0.0084, "step": 206070 }, { "epoch": 49.48, "learning_rate": 3.625187399259813e-05, "loss": 0.0037, "step": 206080 }, { "epoch": 49.48, "learning_rate": 3.624756003431623e-05, "loss": 0.0061, "step": 206090 }, { "epoch": 49.48, "learning_rate": 3.624324618678464e-05, "loss": 0.0043, "step": 206100 }, { "epoch": 49.49, "learning_rate": 3.6238932450038075e-05, "loss": 0.0042, "step": 206110 }, { "epoch": 49.49, "learning_rate": 3.623461882411129e-05, "loss": 0.0089, "step": 206120 }, { "epoch": 49.49, "learning_rate": 3.6230305309039007e-05, "loss": 0.0043, "step": 206130 }, { "epoch": 49.49, "learning_rate": 3.6225991904856014e-05, "loss": 0.0177, "step": 206140 }, { "epoch": 49.49, "learning_rate": 3.6221678611596974e-05, "loss": 0.0065, "step": 206150 }, { "epoch": 49.5, "learning_rate": 3.621736542929667e-05, "loss": 0.003, "step": 206160 }, { "epoch": 49.5, "learning_rate": 3.621305235798982e-05, "loss": 0.007, "step": 206170 }, { "epoch": 49.5, "learning_rate": 3.6208739397711165e-05, "loss": 0.0037, "step": 206180 }, { "epoch": 49.5, "learning_rate": 3.620442654849545e-05, "loss": 0.0111, "step": 206190 }, { "epoch": 49.51, "learning_rate": 3.620011381037737e-05, "loss": 0.0052, "step": 206200 }, { "epoch": 49.51, "learning_rate": 3.6195801183391686e-05, "loss": 0.0099, "step": 206210 }, { "epoch": 49.51, "learning_rate": 3.6191488667573115e-05, "loss": 0.0093, "step": 206220 }, { "epoch": 49.51, "learning_rate": 3.6187176262956404e-05, "loss": 0.0133, "step": 206230 }, { "epoch": 49.51, "learning_rate": 3.6182863969576274e-05, "loss": 0.0065, "step": 206240 }, { "epoch": 49.52, "learning_rate": 3.6178551787467434e-05, "loss": 0.0061, "step": 206250 }, { "epoch": 49.52, "learning_rate": 3.617423971666464e-05, "loss": 0.0161, "step": 206260 }, { "epoch": 49.52, "learning_rate": 3.616992775720258e-05, "loss": 0.0098, "step": 206270 }, { "epoch": 49.52, "learning_rate": 3.6165615909116016e-05, "loss": 0.0057, "step": 206280 }, { "epoch": 49.53, "learning_rate": 3.6161304172439665e-05, "loss": 0.0141, "step": 206290 }, { "epoch": 49.53, "learning_rate": 3.6156992547208225e-05, "loss": 0.0058, "step": 206300 }, { "epoch": 49.53, "learning_rate": 3.6152681033456444e-05, "loss": 0.008, "step": 206310 }, { "epoch": 49.53, "learning_rate": 3.614836963121902e-05, "loss": 0.0077, "step": 206320 }, { "epoch": 49.54, "learning_rate": 3.6144058340530715e-05, "loss": 0.0078, "step": 206330 }, { "epoch": 49.54, "learning_rate": 3.613974716142621e-05, "loss": 0.016, "step": 206340 }, { "epoch": 49.54, "learning_rate": 3.613543609394022e-05, "loss": 0.0093, "step": 206350 }, { "epoch": 49.54, "learning_rate": 3.6131125138107494e-05, "loss": 0.0156, "step": 206360 }, { "epoch": 49.54, "learning_rate": 3.6126814293962716e-05, "loss": 0.0062, "step": 206370 }, { "epoch": 49.55, "learning_rate": 3.612250356154064e-05, "loss": 0.0093, "step": 206380 }, { "epoch": 49.55, "learning_rate": 3.6118192940875945e-05, "loss": 0.0122, "step": 206390 }, { "epoch": 49.55, "learning_rate": 3.611388243200337e-05, "loss": 0.0116, "step": 206400 }, { "epoch": 49.55, "learning_rate": 3.610957203495759e-05, "loss": 0.0191, "step": 206410 }, { "epoch": 49.56, "learning_rate": 3.6105261749773366e-05, "loss": 0.0076, "step": 206420 }, { "epoch": 49.56, "learning_rate": 3.61009515764854e-05, "loss": 0.0076, "step": 206430 }, { "epoch": 49.56, "learning_rate": 3.609664151512836e-05, "loss": 0.0074, "step": 206440 }, { "epoch": 49.56, "learning_rate": 3.6092331565737e-05, "loss": 0.0139, "step": 206450 }, { "epoch": 49.57, "learning_rate": 3.6088021728346e-05, "loss": 0.0082, "step": 206460 }, { "epoch": 49.57, "learning_rate": 3.608371200299011e-05, "loss": 0.0072, "step": 206470 }, { "epoch": 49.57, "learning_rate": 3.6079402389703993e-05, "loss": 0.0095, "step": 206480 }, { "epoch": 49.57, "learning_rate": 3.607509288852236e-05, "loss": 0.0097, "step": 206490 }, { "epoch": 49.57, "learning_rate": 3.607078349947994e-05, "loss": 0.0079, "step": 206500 }, { "epoch": 49.58, "learning_rate": 3.6066474222611405e-05, "loss": 0.0068, "step": 206510 }, { "epoch": 49.58, "learning_rate": 3.60621650579515e-05, "loss": 0.0156, "step": 206520 }, { "epoch": 49.58, "learning_rate": 3.6057856005534905e-05, "loss": 0.0048, "step": 206530 }, { "epoch": 49.58, "learning_rate": 3.6053547065396295e-05, "loss": 0.0049, "step": 206540 }, { "epoch": 49.59, "learning_rate": 3.604923823757042e-05, "loss": 0.014, "step": 206550 }, { "epoch": 49.59, "learning_rate": 3.604492952209194e-05, "loss": 0.004, "step": 206560 }, { "epoch": 49.59, "learning_rate": 3.6040620918995596e-05, "loss": 0.0196, "step": 206570 }, { "epoch": 49.59, "learning_rate": 3.603631242831603e-05, "loss": 0.0081, "step": 206580 }, { "epoch": 49.59, "learning_rate": 3.603200405008798e-05, "loss": 0.0061, "step": 206590 }, { "epoch": 49.6, "learning_rate": 3.602769578434611e-05, "loss": 0.005, "step": 206600 }, { "epoch": 49.6, "learning_rate": 3.602338763112516e-05, "loss": 0.0173, "step": 206610 }, { "epoch": 49.6, "learning_rate": 3.60190795904598e-05, "loss": 0.0057, "step": 206620 }, { "epoch": 49.6, "learning_rate": 3.6014771662384705e-05, "loss": 0.014, "step": 206630 }, { "epoch": 49.61, "learning_rate": 3.601046384693459e-05, "loss": 0.0045, "step": 206640 }, { "epoch": 49.61, "learning_rate": 3.6006156144144144e-05, "loss": 0.0079, "step": 206650 }, { "epoch": 49.61, "learning_rate": 3.600184855404807e-05, "loss": 0.0047, "step": 206660 }, { "epoch": 49.61, "learning_rate": 3.5997541076681026e-05, "loss": 0.0055, "step": 206670 }, { "epoch": 49.62, "learning_rate": 3.5993233712077705e-05, "loss": 0.0045, "step": 206680 }, { "epoch": 49.62, "learning_rate": 3.598892646027282e-05, "loss": 0.0125, "step": 206690 }, { "epoch": 49.62, "learning_rate": 3.598461932130104e-05, "loss": 0.0037, "step": 206700 }, { "epoch": 49.62, "learning_rate": 3.598031229519707e-05, "loss": 0.0119, "step": 206710 }, { "epoch": 49.62, "learning_rate": 3.597600538199557e-05, "loss": 0.0065, "step": 206720 }, { "epoch": 49.63, "learning_rate": 3.597169858173123e-05, "loss": 0.0054, "step": 206730 }, { "epoch": 49.63, "learning_rate": 3.596739189443874e-05, "loss": 0.0049, "step": 206740 }, { "epoch": 49.63, "learning_rate": 3.596308532015277e-05, "loss": 0.0122, "step": 206750 }, { "epoch": 49.63, "learning_rate": 3.5958778858908036e-05, "loss": 0.0058, "step": 206760 }, { "epoch": 49.64, "learning_rate": 3.595447251073919e-05, "loss": 0.0026, "step": 206770 }, { "epoch": 49.64, "learning_rate": 3.595016627568089e-05, "loss": 0.0049, "step": 206780 }, { "epoch": 49.64, "learning_rate": 3.5945860153767876e-05, "loss": 0.005, "step": 206790 }, { "epoch": 49.64, "learning_rate": 3.5941554145034784e-05, "loss": 0.0066, "step": 206800 }, { "epoch": 49.65, "learning_rate": 3.5937248249516286e-05, "loss": 0.0121, "step": 206810 }, { "epoch": 49.65, "learning_rate": 3.593294246724707e-05, "loss": 0.0048, "step": 206820 }, { "epoch": 49.65, "learning_rate": 3.5928636798261805e-05, "loss": 0.0032, "step": 206830 }, { "epoch": 49.65, "learning_rate": 3.5924331242595165e-05, "loss": 0.0073, "step": 206840 }, { "epoch": 49.65, "learning_rate": 3.5920025800281855e-05, "loss": 0.0033, "step": 206850 }, { "epoch": 49.66, "learning_rate": 3.591572047135651e-05, "loss": 0.0055, "step": 206860 }, { "epoch": 49.66, "learning_rate": 3.59114152558538e-05, "loss": 0.0061, "step": 206870 }, { "epoch": 49.66, "learning_rate": 3.590711015380842e-05, "loss": 0.0113, "step": 206880 }, { "epoch": 49.66, "learning_rate": 3.5902805165255015e-05, "loss": 0.0066, "step": 206890 }, { "epoch": 49.67, "learning_rate": 3.5898500290228286e-05, "loss": 0.0083, "step": 206900 }, { "epoch": 49.67, "learning_rate": 3.589419552876288e-05, "loss": 0.0087, "step": 206910 }, { "epoch": 49.67, "learning_rate": 3.588989088089344e-05, "loss": 0.0082, "step": 206920 }, { "epoch": 49.67, "learning_rate": 3.5885586346654674e-05, "loss": 0.0082, "step": 206930 }, { "epoch": 49.67, "learning_rate": 3.5881281926081226e-05, "loss": 0.0124, "step": 206940 }, { "epoch": 49.68, "learning_rate": 3.5876977619207775e-05, "loss": 0.0106, "step": 206950 }, { "epoch": 49.68, "learning_rate": 3.587267342606896e-05, "loss": 0.0072, "step": 206960 }, { "epoch": 49.68, "learning_rate": 3.586836934669946e-05, "loss": 0.0122, "step": 206970 }, { "epoch": 49.68, "learning_rate": 3.586406538113393e-05, "loss": 0.0084, "step": 206980 }, { "epoch": 49.69, "learning_rate": 3.585976152940705e-05, "loss": 0.0103, "step": 206990 }, { "epoch": 49.69, "learning_rate": 3.5855457791553446e-05, "loss": 0.0141, "step": 207000 }, { "epoch": 49.69, "learning_rate": 3.585115416760779e-05, "loss": 0.0057, "step": 207010 }, { "epoch": 49.69, "learning_rate": 3.584685065760475e-05, "loss": 0.0044, "step": 207020 }, { "epoch": 49.7, "learning_rate": 3.584254726157897e-05, "loss": 0.0056, "step": 207030 }, { "epoch": 49.7, "learning_rate": 3.5838243979565126e-05, "loss": 0.0061, "step": 207040 }, { "epoch": 49.7, "learning_rate": 3.583394081159785e-05, "loss": 0.0029, "step": 207050 }, { "epoch": 49.7, "learning_rate": 3.58296377577118e-05, "loss": 0.0059, "step": 207060 }, { "epoch": 49.7, "learning_rate": 3.582533481794164e-05, "loss": 0.0051, "step": 207070 }, { "epoch": 49.71, "learning_rate": 3.5821031992321994e-05, "loss": 0.0028, "step": 207080 }, { "epoch": 49.71, "learning_rate": 3.581672928088756e-05, "loss": 0.0035, "step": 207090 }, { "epoch": 49.71, "learning_rate": 3.581242668367296e-05, "loss": 0.0055, "step": 207100 }, { "epoch": 49.71, "learning_rate": 3.580812420071283e-05, "loss": 0.003, "step": 207110 }, { "epoch": 49.72, "learning_rate": 3.5803821832041855e-05, "loss": 0.0053, "step": 207120 }, { "epoch": 49.72, "learning_rate": 3.579951957769467e-05, "loss": 0.0116, "step": 207130 }, { "epoch": 49.72, "learning_rate": 3.5795217437705894e-05, "loss": 0.0047, "step": 207140 }, { "epoch": 49.72, "learning_rate": 3.57909154121102e-05, "loss": 0.006, "step": 207150 }, { "epoch": 49.73, "learning_rate": 3.578661350094221e-05, "loss": 0.0191, "step": 207160 }, { "epoch": 49.73, "learning_rate": 3.5782311704236604e-05, "loss": 0.007, "step": 207170 }, { "epoch": 49.73, "learning_rate": 3.577801002202801e-05, "loss": 0.0037, "step": 207180 }, { "epoch": 49.73, "learning_rate": 3.577370845435105e-05, "loss": 0.0068, "step": 207190 }, { "epoch": 49.73, "learning_rate": 3.5769407001240384e-05, "loss": 0.01, "step": 207200 }, { "epoch": 49.74, "learning_rate": 3.5765105662730634e-05, "loss": 0.0044, "step": 207210 }, { "epoch": 49.74, "learning_rate": 3.576080443885647e-05, "loss": 0.0057, "step": 207220 }, { "epoch": 49.74, "learning_rate": 3.575650332965252e-05, "loss": 0.0097, "step": 207230 }, { "epoch": 49.74, "learning_rate": 3.575220233515341e-05, "loss": 0.0062, "step": 207240 }, { "epoch": 49.75, "learning_rate": 3.574790145539377e-05, "loss": 0.0086, "step": 207250 }, { "epoch": 49.75, "learning_rate": 3.5743600690408256e-05, "loss": 0.0031, "step": 207260 }, { "epoch": 49.75, "learning_rate": 3.573930004023148e-05, "loss": 0.0067, "step": 207270 }, { "epoch": 49.75, "learning_rate": 3.573499950489812e-05, "loss": 0.0045, "step": 207280 }, { "epoch": 49.75, "learning_rate": 3.5730699084442765e-05, "loss": 0.0078, "step": 207290 }, { "epoch": 49.76, "learning_rate": 3.572639877890004e-05, "loss": 0.0066, "step": 207300 }, { "epoch": 49.76, "learning_rate": 3.572209858830462e-05, "loss": 0.0115, "step": 207310 }, { "epoch": 49.76, "learning_rate": 3.571779851269111e-05, "loss": 0.0069, "step": 207320 }, { "epoch": 49.76, "learning_rate": 3.571349855209413e-05, "loss": 0.0078, "step": 207330 }, { "epoch": 49.77, "learning_rate": 3.5709198706548326e-05, "loss": 0.009, "step": 207340 }, { "epoch": 49.77, "learning_rate": 3.57048989760883e-05, "loss": 0.0261, "step": 207350 }, { "epoch": 49.77, "learning_rate": 3.5700599360748716e-05, "loss": 0.0038, "step": 207360 }, { "epoch": 49.77, "learning_rate": 3.5696299860564186e-05, "loss": 0.0068, "step": 207370 }, { "epoch": 49.78, "learning_rate": 3.569200047556931e-05, "loss": 0.0151, "step": 207380 }, { "epoch": 49.78, "learning_rate": 3.5687701205798726e-05, "loss": 0.0124, "step": 207390 }, { "epoch": 49.78, "learning_rate": 3.568340205128707e-05, "loss": 0.0171, "step": 207400 }, { "epoch": 49.78, "learning_rate": 3.567910301206895e-05, "loss": 0.0062, "step": 207410 }, { "epoch": 49.78, "learning_rate": 3.567480408817901e-05, "loss": 0.0073, "step": 207420 }, { "epoch": 49.79, "learning_rate": 3.5670505279651834e-05, "loss": 0.0162, "step": 207430 }, { "epoch": 49.79, "learning_rate": 3.566620658652205e-05, "loss": 0.0137, "step": 207440 }, { "epoch": 49.79, "learning_rate": 3.566190800882429e-05, "loss": 0.0089, "step": 207450 }, { "epoch": 49.79, "learning_rate": 3.565760954659318e-05, "loss": 0.0082, "step": 207460 }, { "epoch": 49.8, "learning_rate": 3.5653311199863295e-05, "loss": 0.0054, "step": 207470 }, { "epoch": 49.8, "learning_rate": 3.564901296866929e-05, "loss": 0.0046, "step": 207480 }, { "epoch": 49.8, "learning_rate": 3.564471485304575e-05, "loss": 0.018, "step": 207490 }, { "epoch": 49.8, "learning_rate": 3.5640416853027314e-05, "loss": 0.0082, "step": 207500 }, { "epoch": 49.81, "learning_rate": 3.5636118968648595e-05, "loss": 0.0041, "step": 207510 }, { "epoch": 49.81, "learning_rate": 3.563182119994417e-05, "loss": 0.005, "step": 207520 }, { "epoch": 49.81, "learning_rate": 3.56275235469487e-05, "loss": 0.0129, "step": 207530 }, { "epoch": 49.81, "learning_rate": 3.562322600969673e-05, "loss": 0.0048, "step": 207540 }, { "epoch": 49.81, "learning_rate": 3.5618928588222934e-05, "loss": 0.0103, "step": 207550 }, { "epoch": 49.82, "learning_rate": 3.561463128256189e-05, "loss": 0.0051, "step": 207560 }, { "epoch": 49.82, "learning_rate": 3.56103340927482e-05, "loss": 0.0057, "step": 207570 }, { "epoch": 49.82, "learning_rate": 3.5606037018816477e-05, "loss": 0.0082, "step": 207580 }, { "epoch": 49.82, "learning_rate": 3.560174006080132e-05, "loss": 0.0139, "step": 207590 }, { "epoch": 49.83, "learning_rate": 3.559744321873734e-05, "loss": 0.0054, "step": 207600 }, { "epoch": 49.83, "learning_rate": 3.559314649265915e-05, "loss": 0.0168, "step": 207610 }, { "epoch": 49.83, "learning_rate": 3.5588849882601326e-05, "loss": 0.0051, "step": 207620 }, { "epoch": 49.83, "learning_rate": 3.558455338859849e-05, "loss": 0.0065, "step": 207630 }, { "epoch": 49.83, "learning_rate": 3.5580257010685224e-05, "loss": 0.0073, "step": 207640 }, { "epoch": 49.84, "learning_rate": 3.5575960748896174e-05, "loss": 0.0072, "step": 207650 }, { "epoch": 49.84, "learning_rate": 3.5571664603265876e-05, "loss": 0.0033, "step": 207660 }, { "epoch": 49.84, "learning_rate": 3.5567368573828955e-05, "loss": 0.0057, "step": 207670 }, { "epoch": 49.84, "learning_rate": 3.556307266062e-05, "loss": 0.0063, "step": 207680 }, { "epoch": 49.85, "learning_rate": 3.5558776863673625e-05, "loss": 0.0057, "step": 207690 }, { "epoch": 49.85, "learning_rate": 3.555448118302443e-05, "loss": 0.0111, "step": 207700 }, { "epoch": 49.85, "learning_rate": 3.5550185618706966e-05, "loss": 0.0079, "step": 207710 }, { "epoch": 49.85, "learning_rate": 3.5545890170755866e-05, "loss": 0.0185, "step": 207720 }, { "epoch": 49.86, "learning_rate": 3.5541594839205694e-05, "loss": 0.0031, "step": 207730 }, { "epoch": 49.86, "learning_rate": 3.5537299624091063e-05, "loss": 0.0119, "step": 207740 }, { "epoch": 49.86, "learning_rate": 3.5533004525446566e-05, "loss": 0.0061, "step": 207750 }, { "epoch": 49.86, "learning_rate": 3.552870954330677e-05, "loss": 0.0094, "step": 207760 }, { "epoch": 49.86, "learning_rate": 3.552441467770628e-05, "loss": 0.0142, "step": 207770 }, { "epoch": 49.87, "learning_rate": 3.552011992867966e-05, "loss": 0.0115, "step": 207780 }, { "epoch": 49.87, "learning_rate": 3.5515825296261535e-05, "loss": 0.0052, "step": 207790 }, { "epoch": 49.87, "learning_rate": 3.551153078048646e-05, "loss": 0.0155, "step": 207800 }, { "epoch": 49.87, "learning_rate": 3.550723638138902e-05, "loss": 0.0069, "step": 207810 }, { "epoch": 49.88, "learning_rate": 3.550294209900381e-05, "loss": 0.0109, "step": 207820 }, { "epoch": 49.88, "learning_rate": 3.5498647933365406e-05, "loss": 0.0101, "step": 207830 }, { "epoch": 49.88, "learning_rate": 3.549435388450841e-05, "loss": 0.0048, "step": 207840 }, { "epoch": 49.88, "learning_rate": 3.549005995246738e-05, "loss": 0.0065, "step": 207850 }, { "epoch": 49.89, "learning_rate": 3.5485766137276894e-05, "loss": 0.0034, "step": 207860 }, { "epoch": 49.89, "learning_rate": 3.5481472438971524e-05, "loss": 0.009, "step": 207870 }, { "epoch": 49.89, "learning_rate": 3.547717885758588e-05, "loss": 0.007, "step": 207880 }, { "epoch": 49.89, "learning_rate": 3.547288539315452e-05, "loss": 0.0091, "step": 207890 }, { "epoch": 49.89, "learning_rate": 3.546859204571201e-05, "loss": 0.0065, "step": 207900 }, { "epoch": 49.9, "learning_rate": 3.5464298815292935e-05, "loss": 0.0073, "step": 207910 }, { "epoch": 49.9, "learning_rate": 3.546000570193186e-05, "loss": 0.0021, "step": 207920 }, { "epoch": 49.9, "learning_rate": 3.545571270566338e-05, "loss": 0.0061, "step": 207930 }, { "epoch": 49.9, "learning_rate": 3.545141982652207e-05, "loss": 0.0077, "step": 207940 }, { "epoch": 49.91, "learning_rate": 3.544712706454245e-05, "loss": 0.008, "step": 207950 }, { "epoch": 49.91, "learning_rate": 3.544283441975914e-05, "loss": 0.0066, "step": 207960 }, { "epoch": 49.91, "learning_rate": 3.5438541892206687e-05, "loss": 0.0046, "step": 207970 }, { "epoch": 49.91, "learning_rate": 3.543424948191969e-05, "loss": 0.003, "step": 207980 }, { "epoch": 49.91, "learning_rate": 3.542995718893267e-05, "loss": 0.0029, "step": 207990 }, { "epoch": 49.92, "learning_rate": 3.5425665013280216e-05, "loss": 0.0039, "step": 208000 }, { "epoch": 49.92, "learning_rate": 3.54213729549969e-05, "loss": 0.0043, "step": 208010 }, { "epoch": 49.92, "learning_rate": 3.541708101411727e-05, "loss": 0.0041, "step": 208020 }, { "epoch": 49.92, "learning_rate": 3.541278919067593e-05, "loss": 0.024, "step": 208030 }, { "epoch": 49.93, "learning_rate": 3.540849748470739e-05, "loss": 0.0051, "step": 208040 }, { "epoch": 49.93, "learning_rate": 3.5404205896246235e-05, "loss": 0.0034, "step": 208050 }, { "epoch": 49.93, "learning_rate": 3.539991442532703e-05, "loss": 0.005, "step": 208060 }, { "epoch": 49.93, "learning_rate": 3.5395623071984316e-05, "loss": 0.0196, "step": 208070 }, { "epoch": 49.94, "learning_rate": 3.53913318362527e-05, "loss": 0.009, "step": 208080 }, { "epoch": 49.94, "learning_rate": 3.538704071816668e-05, "loss": 0.0068, "step": 208090 }, { "epoch": 49.94, "learning_rate": 3.5382749717760835e-05, "loss": 0.0059, "step": 208100 }, { "epoch": 49.94, "learning_rate": 3.5378458835069724e-05, "loss": 0.003, "step": 208110 }, { "epoch": 49.94, "learning_rate": 3.537416807012792e-05, "loss": 0.0073, "step": 208120 }, { "epoch": 49.95, "learning_rate": 3.536987742296995e-05, "loss": 0.0143, "step": 208130 }, { "epoch": 49.95, "learning_rate": 3.5365586893630365e-05, "loss": 0.0037, "step": 208140 }, { "epoch": 49.95, "learning_rate": 3.536129648214375e-05, "loss": 0.0062, "step": 208150 }, { "epoch": 50.0, "learning_rate": 3.535700618854461e-05, "loss": 0.0104, "step": 208160 }, { "epoch": 50.0, "learning_rate": 3.535271601286755e-05, "loss": 0.0119, "step": 208170 }, { "epoch": 50.01, "learning_rate": 3.534842595514708e-05, "loss": 0.0144, "step": 208180 }, { "epoch": 50.01, "learning_rate": 3.5344136015417746e-05, "loss": 0.0049, "step": 208190 }, { "epoch": 50.01, "learning_rate": 3.533984619371412e-05, "loss": 0.008, "step": 208200 }, { "epoch": 50.01, "learning_rate": 3.533555649007072e-05, "loss": 0.0042, "step": 208210 }, { "epoch": 50.02, "learning_rate": 3.5331266904522136e-05, "loss": 0.0079, "step": 208220 }, { "epoch": 50.02, "learning_rate": 3.532697743710287e-05, "loss": 0.0136, "step": 208230 }, { "epoch": 50.02, "learning_rate": 3.5322688087847475e-05, "loss": 0.0042, "step": 208240 }, { "epoch": 50.02, "learning_rate": 3.531839885679051e-05, "loss": 0.0048, "step": 208250 }, { "epoch": 50.03, "learning_rate": 3.531410974396649e-05, "loss": 0.0073, "step": 208260 }, { "epoch": 50.03, "learning_rate": 3.5309820749409995e-05, "loss": 0.0048, "step": 208270 }, { "epoch": 50.03, "learning_rate": 3.5305531873155525e-05, "loss": 0.0136, "step": 208280 }, { "epoch": 50.03, "learning_rate": 3.530124311523764e-05, "loss": 0.0052, "step": 208290 }, { "epoch": 50.03, "learning_rate": 3.529695447569087e-05, "loss": 0.0058, "step": 208300 }, { "epoch": 50.04, "learning_rate": 3.529266595454977e-05, "loss": 0.0096, "step": 208310 }, { "epoch": 50.04, "learning_rate": 3.528837755184885e-05, "loss": 0.0035, "step": 208320 }, { "epoch": 50.04, "learning_rate": 3.5284089267622655e-05, "loss": 0.0048, "step": 208330 }, { "epoch": 50.04, "learning_rate": 3.5279801101905724e-05, "loss": 0.0043, "step": 208340 }, { "epoch": 50.05, "learning_rate": 3.527551305473258e-05, "loss": 0.0055, "step": 208350 }, { "epoch": 50.05, "learning_rate": 3.527122512613777e-05, "loss": 0.0025, "step": 208360 }, { "epoch": 50.05, "learning_rate": 3.526693731615582e-05, "loss": 0.0042, "step": 208370 }, { "epoch": 50.05, "learning_rate": 3.526264962482125e-05, "loss": 0.0028, "step": 208380 }, { "epoch": 50.05, "learning_rate": 3.52583620521686e-05, "loss": 0.0037, "step": 208390 }, { "epoch": 50.06, "learning_rate": 3.525407459823239e-05, "loss": 0.0051, "step": 208400 }, { "epoch": 50.06, "learning_rate": 3.5249787263047166e-05, "loss": 0.0032, "step": 208410 }, { "epoch": 50.06, "learning_rate": 3.524550004664744e-05, "loss": 0.0109, "step": 208420 }, { "epoch": 50.06, "learning_rate": 3.5241212949067725e-05, "loss": 0.0056, "step": 208430 }, { "epoch": 50.07, "learning_rate": 3.523692597034257e-05, "loss": 0.0117, "step": 208440 }, { "epoch": 50.07, "learning_rate": 3.52326391105065e-05, "loss": 0.0044, "step": 208450 }, { "epoch": 50.07, "learning_rate": 3.5228352369594e-05, "loss": 0.0039, "step": 208460 }, { "epoch": 50.07, "learning_rate": 3.522406574763963e-05, "loss": 0.0039, "step": 208470 }, { "epoch": 50.08, "learning_rate": 3.5219779244677895e-05, "loss": 0.0068, "step": 208480 }, { "epoch": 50.08, "learning_rate": 3.521549286074333e-05, "loss": 0.0045, "step": 208490 }, { "epoch": 50.08, "learning_rate": 3.5211206595870435e-05, "loss": 0.0031, "step": 208500 }, { "epoch": 50.08, "learning_rate": 3.5206920450093736e-05, "loss": 0.0075, "step": 208510 }, { "epoch": 50.08, "learning_rate": 3.520263442344774e-05, "loss": 0.0025, "step": 208520 }, { "epoch": 50.09, "learning_rate": 3.5198348515966985e-05, "loss": 0.0027, "step": 208530 }, { "epoch": 50.09, "learning_rate": 3.519406272768596e-05, "loss": 0.0064, "step": 208540 }, { "epoch": 50.09, "learning_rate": 3.5189777058639214e-05, "loss": 0.0061, "step": 208550 }, { "epoch": 50.09, "learning_rate": 3.518549150886122e-05, "loss": 0.0054, "step": 208560 }, { "epoch": 50.1, "learning_rate": 3.518120607838651e-05, "loss": 0.0121, "step": 208570 }, { "epoch": 50.1, "learning_rate": 3.5176920767249586e-05, "loss": 0.0098, "step": 208580 }, { "epoch": 50.1, "learning_rate": 3.517263557548497e-05, "loss": 0.0068, "step": 208590 }, { "epoch": 50.1, "learning_rate": 3.5168350503127186e-05, "loss": 0.0053, "step": 208600 }, { "epoch": 50.11, "learning_rate": 3.5164065550210704e-05, "loss": 0.0057, "step": 208610 }, { "epoch": 50.11, "learning_rate": 3.5159780716770055e-05, "loss": 0.0028, "step": 208620 }, { "epoch": 50.11, "learning_rate": 3.515549600283974e-05, "loss": 0.0099, "step": 208630 }, { "epoch": 50.11, "learning_rate": 3.5151211408454276e-05, "loss": 0.0044, "step": 208640 }, { "epoch": 50.11, "learning_rate": 3.5146926933648136e-05, "loss": 0.006, "step": 208650 }, { "epoch": 50.12, "learning_rate": 3.5142642578455855e-05, "loss": 0.0054, "step": 208660 }, { "epoch": 50.12, "learning_rate": 3.513835834291192e-05, "loss": 0.0078, "step": 208670 }, { "epoch": 50.12, "learning_rate": 3.5134074227050836e-05, "loss": 0.0108, "step": 208680 }, { "epoch": 50.12, "learning_rate": 3.512979023090712e-05, "loss": 0.0081, "step": 208690 }, { "epoch": 50.13, "learning_rate": 3.5125506354515236e-05, "loss": 0.0042, "step": 208700 }, { "epoch": 50.13, "learning_rate": 3.5121222597909714e-05, "loss": 0.0051, "step": 208710 }, { "epoch": 50.13, "learning_rate": 3.5116938961125026e-05, "loss": 0.0056, "step": 208720 }, { "epoch": 50.13, "learning_rate": 3.5112655444195696e-05, "loss": 0.0057, "step": 208730 }, { "epoch": 50.13, "learning_rate": 3.510837204715622e-05, "loss": 0.0075, "step": 208740 }, { "epoch": 50.14, "learning_rate": 3.510408877004107e-05, "loss": 0.0048, "step": 208750 }, { "epoch": 50.14, "learning_rate": 3.509980561288474e-05, "loss": 0.003, "step": 208760 }, { "epoch": 50.14, "learning_rate": 3.509552257572174e-05, "loss": 0.0072, "step": 208770 }, { "epoch": 50.14, "learning_rate": 3.509123965858657e-05, "loss": 0.005, "step": 208780 }, { "epoch": 50.15, "learning_rate": 3.508695686151368e-05, "loss": 0.0075, "step": 208790 }, { "epoch": 50.15, "learning_rate": 3.508267418453759e-05, "loss": 0.0035, "step": 208800 }, { "epoch": 50.15, "learning_rate": 3.507839162769278e-05, "loss": 0.023, "step": 208810 }, { "epoch": 50.15, "learning_rate": 3.507410919101375e-05, "loss": 0.0085, "step": 208820 }, { "epoch": 50.16, "learning_rate": 3.5069826874534994e-05, "loss": 0.0067, "step": 208830 }, { "epoch": 50.16, "learning_rate": 3.5065544678290966e-05, "loss": 0.0063, "step": 208840 }, { "epoch": 50.16, "learning_rate": 3.506126260231617e-05, "loss": 0.0074, "step": 208850 }, { "epoch": 50.16, "learning_rate": 3.5056980646645076e-05, "loss": 0.0087, "step": 208860 }, { "epoch": 50.16, "learning_rate": 3.5052698811312204e-05, "loss": 0.0027, "step": 208870 }, { "epoch": 50.17, "learning_rate": 3.504841709635201e-05, "loss": 0.0097, "step": 208880 }, { "epoch": 50.17, "learning_rate": 3.5044135501798955e-05, "loss": 0.0036, "step": 208890 }, { "epoch": 50.17, "learning_rate": 3.5039854027687566e-05, "loss": 0.0044, "step": 208900 }, { "epoch": 50.17, "learning_rate": 3.5035572674052276e-05, "loss": 0.0055, "step": 208910 }, { "epoch": 50.18, "learning_rate": 3.5031291440927595e-05, "loss": 0.008, "step": 208920 }, { "epoch": 50.18, "learning_rate": 3.502701032834801e-05, "loss": 0.0032, "step": 208930 }, { "epoch": 50.18, "learning_rate": 3.502272933634796e-05, "loss": 0.0049, "step": 208940 }, { "epoch": 50.18, "learning_rate": 3.5018448464961926e-05, "loss": 0.0058, "step": 208950 }, { "epoch": 50.19, "learning_rate": 3.501416771422441e-05, "loss": 0.0039, "step": 208960 }, { "epoch": 50.19, "learning_rate": 3.5009887084169884e-05, "loss": 0.0098, "step": 208970 }, { "epoch": 50.19, "learning_rate": 3.500560657483278e-05, "loss": 0.003, "step": 208980 }, { "epoch": 50.19, "learning_rate": 3.5001326186247615e-05, "loss": 0.0056, "step": 208990 }, { "epoch": 50.19, "learning_rate": 3.499704591844882e-05, "loss": 0.0082, "step": 209000 }, { "epoch": 50.2, "learning_rate": 3.4992765771470906e-05, "loss": 0.0041, "step": 209010 }, { "epoch": 50.2, "learning_rate": 3.498848574534832e-05, "loss": 0.0038, "step": 209020 }, { "epoch": 50.2, "learning_rate": 3.498420584011552e-05, "loss": 0.0046, "step": 209030 }, { "epoch": 50.2, "learning_rate": 3.497992605580699e-05, "loss": 0.0119, "step": 209040 }, { "epoch": 50.21, "learning_rate": 3.497564639245718e-05, "loss": 0.0047, "step": 209050 }, { "epoch": 50.21, "learning_rate": 3.497136685010057e-05, "loss": 0.0032, "step": 209060 }, { "epoch": 50.21, "learning_rate": 3.4967087428771626e-05, "loss": 0.0095, "step": 209070 }, { "epoch": 50.21, "learning_rate": 3.496280812850479e-05, "loss": 0.0034, "step": 209080 }, { "epoch": 50.21, "learning_rate": 3.495852894933455e-05, "loss": 0.0041, "step": 209090 }, { "epoch": 50.22, "learning_rate": 3.495424989129533e-05, "loss": 0.0048, "step": 209100 }, { "epoch": 50.22, "learning_rate": 3.494997095442164e-05, "loss": 0.0083, "step": 209110 }, { "epoch": 50.22, "learning_rate": 3.49456921387479e-05, "loss": 0.0041, "step": 209120 }, { "epoch": 50.22, "learning_rate": 3.494141344430857e-05, "loss": 0.0062, "step": 209130 }, { "epoch": 50.23, "learning_rate": 3.493713487113813e-05, "loss": 0.0083, "step": 209140 }, { "epoch": 50.23, "learning_rate": 3.4932856419271e-05, "loss": 0.008, "step": 209150 }, { "epoch": 50.23, "learning_rate": 3.492857808874171e-05, "loss": 0.0111, "step": 209160 }, { "epoch": 50.23, "learning_rate": 3.492429987958461e-05, "loss": 0.0036, "step": 209170 }, { "epoch": 50.24, "learning_rate": 3.4920021791834224e-05, "loss": 0.0119, "step": 209180 }, { "epoch": 50.24, "learning_rate": 3.491574382552497e-05, "loss": 0.0045, "step": 209190 }, { "epoch": 50.24, "learning_rate": 3.491146598069133e-05, "loss": 0.009, "step": 209200 }, { "epoch": 50.24, "learning_rate": 3.490718825736774e-05, "loss": 0.0029, "step": 209210 }, { "epoch": 50.24, "learning_rate": 3.490291065558863e-05, "loss": 0.0085, "step": 209220 }, { "epoch": 50.25, "learning_rate": 3.4898633175388474e-05, "loss": 0.0059, "step": 209230 }, { "epoch": 50.25, "learning_rate": 3.4894355816801704e-05, "loss": 0.0186, "step": 209240 }, { "epoch": 50.25, "learning_rate": 3.489007857986277e-05, "loss": 0.0076, "step": 209250 }, { "epoch": 50.25, "learning_rate": 3.488580146460615e-05, "loss": 0.0058, "step": 209260 }, { "epoch": 50.26, "learning_rate": 3.488152447106622e-05, "loss": 0.0175, "step": 209270 }, { "epoch": 50.26, "learning_rate": 3.487724759927747e-05, "loss": 0.0072, "step": 209280 }, { "epoch": 50.26, "learning_rate": 3.487297084927433e-05, "loss": 0.0034, "step": 209290 }, { "epoch": 50.26, "learning_rate": 3.486869422109127e-05, "loss": 0.0078, "step": 209300 }, { "epoch": 50.27, "learning_rate": 3.4864417714762685e-05, "loss": 0.0058, "step": 209310 }, { "epoch": 50.27, "learning_rate": 3.486014133032303e-05, "loss": 0.0065, "step": 209320 }, { "epoch": 50.27, "learning_rate": 3.485586506780675e-05, "loss": 0.0046, "step": 209330 }, { "epoch": 50.27, "learning_rate": 3.485158892724827e-05, "loss": 0.0051, "step": 209340 }, { "epoch": 50.27, "learning_rate": 3.484731290868207e-05, "loss": 0.0081, "step": 209350 }, { "epoch": 50.28, "learning_rate": 3.484303701214253e-05, "loss": 0.0104, "step": 209360 }, { "epoch": 50.28, "learning_rate": 3.48387612376641e-05, "loss": 0.0198, "step": 209370 }, { "epoch": 50.28, "learning_rate": 3.483448558528122e-05, "loss": 0.0057, "step": 209380 }, { "epoch": 50.28, "learning_rate": 3.483021005502832e-05, "loss": 0.0052, "step": 209390 }, { "epoch": 50.29, "learning_rate": 3.482593464693985e-05, "loss": 0.0069, "step": 209400 }, { "epoch": 50.29, "learning_rate": 3.48216593610502e-05, "loss": 0.017, "step": 209410 }, { "epoch": 50.29, "learning_rate": 3.481738419739383e-05, "loss": 0.0085, "step": 209420 }, { "epoch": 50.29, "learning_rate": 3.481310915600516e-05, "loss": 0.0039, "step": 209430 }, { "epoch": 50.29, "learning_rate": 3.480883423691863e-05, "loss": 0.0104, "step": 209440 }, { "epoch": 50.3, "learning_rate": 3.480455944016866e-05, "loss": 0.0045, "step": 209450 }, { "epoch": 50.3, "learning_rate": 3.480028476578964e-05, "loss": 0.0072, "step": 209460 }, { "epoch": 50.3, "learning_rate": 3.479601021381605e-05, "loss": 0.0042, "step": 209470 }, { "epoch": 50.3, "learning_rate": 3.479173578428228e-05, "loss": 0.0066, "step": 209480 }, { "epoch": 50.31, "learning_rate": 3.478746147722277e-05, "loss": 0.0204, "step": 209490 }, { "epoch": 50.31, "learning_rate": 3.478318729267193e-05, "loss": 0.0065, "step": 209500 }, { "epoch": 50.31, "learning_rate": 3.477891323066417e-05, "loss": 0.0064, "step": 209510 }, { "epoch": 50.31, "learning_rate": 3.477463929123393e-05, "loss": 0.0199, "step": 209520 }, { "epoch": 50.32, "learning_rate": 3.477036547441562e-05, "loss": 0.0047, "step": 209530 }, { "epoch": 50.32, "learning_rate": 3.4766091780243675e-05, "loss": 0.0065, "step": 209540 }, { "epoch": 50.32, "learning_rate": 3.476181820875248e-05, "loss": 0.0062, "step": 209550 }, { "epoch": 50.32, "learning_rate": 3.475754475997647e-05, "loss": 0.004, "step": 209560 }, { "epoch": 50.32, "learning_rate": 3.475327143395006e-05, "loss": 0.0043, "step": 209570 }, { "epoch": 50.33, "learning_rate": 3.4748998230707655e-05, "loss": 0.0029, "step": 209580 }, { "epoch": 50.33, "learning_rate": 3.47447251502837e-05, "loss": 0.0037, "step": 209590 }, { "epoch": 50.33, "learning_rate": 3.4740452192712544e-05, "loss": 0.0027, "step": 209600 }, { "epoch": 50.33, "learning_rate": 3.473617935802864e-05, "loss": 0.0123, "step": 209610 }, { "epoch": 50.34, "learning_rate": 3.4731906646266394e-05, "loss": 0.01, "step": 209620 }, { "epoch": 50.34, "learning_rate": 3.4727634057460224e-05, "loss": 0.0042, "step": 209630 }, { "epoch": 50.34, "learning_rate": 3.472336159164452e-05, "loss": 0.0054, "step": 209640 }, { "epoch": 50.34, "learning_rate": 3.471908924885367e-05, "loss": 0.0157, "step": 209650 }, { "epoch": 50.35, "learning_rate": 3.471481702912213e-05, "loss": 0.0128, "step": 209660 }, { "epoch": 50.35, "learning_rate": 3.4710544932484266e-05, "loss": 0.0052, "step": 209670 }, { "epoch": 50.35, "learning_rate": 3.470627295897452e-05, "loss": 0.0065, "step": 209680 }, { "epoch": 50.35, "learning_rate": 3.470200110862725e-05, "loss": 0.0024, "step": 209690 }, { "epoch": 50.35, "learning_rate": 3.4697729381476864e-05, "loss": 0.01, "step": 209700 }, { "epoch": 50.36, "learning_rate": 3.469345777755779e-05, "loss": 0.0049, "step": 209710 }, { "epoch": 50.36, "learning_rate": 3.46891862969044e-05, "loss": 0.004, "step": 209720 }, { "epoch": 50.36, "learning_rate": 3.468491493955114e-05, "loss": 0.0026, "step": 209730 }, { "epoch": 50.36, "learning_rate": 3.468064370553235e-05, "loss": 0.0066, "step": 209740 }, { "epoch": 50.37, "learning_rate": 3.467637259488244e-05, "loss": 0.0081, "step": 209750 }, { "epoch": 50.37, "learning_rate": 3.467210160763584e-05, "loss": 0.0028, "step": 209760 }, { "epoch": 50.37, "learning_rate": 3.4667830743826925e-05, "loss": 0.0038, "step": 209770 }, { "epoch": 50.37, "learning_rate": 3.466356000349006e-05, "loss": 0.0031, "step": 209780 }, { "epoch": 50.37, "learning_rate": 3.465928938665969e-05, "loss": 0.0023, "step": 209790 }, { "epoch": 50.38, "learning_rate": 3.4655018893370164e-05, "loss": 0.0033, "step": 209800 }, { "epoch": 50.38, "learning_rate": 3.465074852365589e-05, "loss": 0.0076, "step": 209810 }, { "epoch": 50.38, "learning_rate": 3.464647827755127e-05, "loss": 0.0047, "step": 209820 }, { "epoch": 50.38, "learning_rate": 3.464220815509067e-05, "loss": 0.0042, "step": 209830 }, { "epoch": 50.39, "learning_rate": 3.463793815630848e-05, "loss": 0.012, "step": 209840 }, { "epoch": 50.39, "learning_rate": 3.463366828123911e-05, "loss": 0.0073, "step": 209850 }, { "epoch": 50.39, "learning_rate": 3.462939852991691e-05, "loss": 0.0069, "step": 209860 }, { "epoch": 50.39, "learning_rate": 3.4625128902376316e-05, "loss": 0.0045, "step": 209870 }, { "epoch": 50.4, "learning_rate": 3.462085939865167e-05, "loss": 0.0074, "step": 209880 }, { "epoch": 50.4, "learning_rate": 3.461659001877735e-05, "loss": 0.0058, "step": 209890 }, { "epoch": 50.4, "learning_rate": 3.461232076278778e-05, "loss": 0.0024, "step": 209900 }, { "epoch": 50.4, "learning_rate": 3.4608051630717284e-05, "loss": 0.0058, "step": 209910 }, { "epoch": 50.4, "learning_rate": 3.4603782622600305e-05, "loss": 0.0043, "step": 209920 }, { "epoch": 50.41, "learning_rate": 3.4599513738471176e-05, "loss": 0.0084, "step": 209930 }, { "epoch": 50.41, "learning_rate": 3.4595244978364285e-05, "loss": 0.0079, "step": 209940 }, { "epoch": 50.41, "learning_rate": 3.4590976342314016e-05, "loss": 0.0062, "step": 209950 }, { "epoch": 50.41, "learning_rate": 3.458670783035476e-05, "loss": 0.0025, "step": 209960 }, { "epoch": 50.42, "learning_rate": 3.458243944252084e-05, "loss": 0.0054, "step": 209970 }, { "epoch": 50.42, "learning_rate": 3.4578171178846685e-05, "loss": 0.0096, "step": 209980 }, { "epoch": 50.42, "learning_rate": 3.457390303936664e-05, "loss": 0.0057, "step": 209990 }, { "epoch": 50.42, "learning_rate": 3.4569635024115087e-05, "loss": 0.0063, "step": 210000 }, { "epoch": 50.43, "learning_rate": 3.45653671331264e-05, "loss": 0.004, "step": 210010 }, { "epoch": 50.43, "learning_rate": 3.456109936643494e-05, "loss": 0.0045, "step": 210020 }, { "epoch": 50.43, "learning_rate": 3.455683172407507e-05, "loss": 0.0044, "step": 210030 }, { "epoch": 50.43, "learning_rate": 3.4552564206081165e-05, "loss": 0.0036, "step": 210040 }, { "epoch": 50.43, "learning_rate": 3.454829681248759e-05, "loss": 0.0069, "step": 210050 }, { "epoch": 50.44, "learning_rate": 3.4544029543328734e-05, "loss": 0.0038, "step": 210060 }, { "epoch": 50.44, "learning_rate": 3.453976239863893e-05, "loss": 0.0056, "step": 210070 }, { "epoch": 50.44, "learning_rate": 3.453549537845254e-05, "loss": 0.0024, "step": 210080 }, { "epoch": 50.44, "learning_rate": 3.453122848280396e-05, "loss": 0.0063, "step": 210090 }, { "epoch": 50.45, "learning_rate": 3.4526961711727535e-05, "loss": 0.0071, "step": 210100 }, { "epoch": 50.45, "learning_rate": 3.452269506525761e-05, "loss": 0.0124, "step": 210110 }, { "epoch": 50.45, "learning_rate": 3.4518428543428564e-05, "loss": 0.0037, "step": 210120 }, { "epoch": 50.45, "learning_rate": 3.451416214627474e-05, "loss": 0.01, "step": 210130 }, { "epoch": 50.45, "learning_rate": 3.450989587383052e-05, "loss": 0.0131, "step": 210140 }, { "epoch": 50.46, "learning_rate": 3.450562972613025e-05, "loss": 0.0057, "step": 210150 }, { "epoch": 50.46, "learning_rate": 3.450136370320827e-05, "loss": 0.0113, "step": 210160 }, { "epoch": 50.46, "learning_rate": 3.449709780509895e-05, "loss": 0.0037, "step": 210170 }, { "epoch": 50.46, "learning_rate": 3.449283203183664e-05, "loss": 0.0061, "step": 210180 }, { "epoch": 50.47, "learning_rate": 3.4488566383455706e-05, "loss": 0.0049, "step": 210190 }, { "epoch": 50.47, "learning_rate": 3.4484300859990496e-05, "loss": 0.0139, "step": 210200 }, { "epoch": 50.47, "learning_rate": 3.448003546147533e-05, "loss": 0.0063, "step": 210210 }, { "epoch": 50.47, "learning_rate": 3.447577018794459e-05, "loss": 0.0039, "step": 210220 }, { "epoch": 50.48, "learning_rate": 3.447150503943262e-05, "loss": 0.004, "step": 210230 }, { "epoch": 50.48, "learning_rate": 3.446724001597375e-05, "loss": 0.0037, "step": 210240 }, { "epoch": 50.48, "learning_rate": 3.446297511760236e-05, "loss": 0.0045, "step": 210250 }, { "epoch": 50.48, "learning_rate": 3.445871034435277e-05, "loss": 0.0036, "step": 210260 }, { "epoch": 50.48, "learning_rate": 3.4454445696259324e-05, "loss": 0.0055, "step": 210270 }, { "epoch": 50.49, "learning_rate": 3.445018117335638e-05, "loss": 0.0092, "step": 210280 }, { "epoch": 50.49, "learning_rate": 3.444591677567828e-05, "loss": 0.0085, "step": 210290 }, { "epoch": 50.49, "learning_rate": 3.444165250325935e-05, "loss": 0.0066, "step": 210300 }, { "epoch": 50.49, "learning_rate": 3.4437388356133936e-05, "loss": 0.0086, "step": 210310 }, { "epoch": 50.5, "learning_rate": 3.443312433433638e-05, "loss": 0.003, "step": 210320 }, { "epoch": 50.5, "learning_rate": 3.442886043790103e-05, "loss": 0.0084, "step": 210330 }, { "epoch": 50.5, "learning_rate": 3.442459666686223e-05, "loss": 0.0045, "step": 210340 }, { "epoch": 50.5, "learning_rate": 3.442033302125428e-05, "loss": 0.0138, "step": 210350 }, { "epoch": 50.51, "learning_rate": 3.441606950111156e-05, "loss": 0.0025, "step": 210360 }, { "epoch": 50.51, "learning_rate": 3.441180610646836e-05, "loss": 0.0036, "step": 210370 }, { "epoch": 50.51, "learning_rate": 3.440754283735905e-05, "loss": 0.0053, "step": 210380 }, { "epoch": 50.51, "learning_rate": 3.440327969381797e-05, "loss": 0.0112, "step": 210390 }, { "epoch": 50.51, "learning_rate": 3.43990166758794e-05, "loss": 0.0087, "step": 210400 }, { "epoch": 50.52, "learning_rate": 3.4394753783577714e-05, "loss": 0.0021, "step": 210410 }, { "epoch": 50.52, "learning_rate": 3.439049101694722e-05, "loss": 0.0055, "step": 210420 }, { "epoch": 50.52, "learning_rate": 3.43862283760223e-05, "loss": 0.0147, "step": 210430 }, { "epoch": 50.52, "learning_rate": 3.4381965860837194e-05, "loss": 0.0106, "step": 210440 }, { "epoch": 50.53, "learning_rate": 3.437770347142629e-05, "loss": 0.0085, "step": 210450 }, { "epoch": 50.53, "learning_rate": 3.437344120782389e-05, "loss": 0.0058, "step": 210460 }, { "epoch": 50.53, "learning_rate": 3.436917907006432e-05, "loss": 0.0031, "step": 210470 }, { "epoch": 50.53, "learning_rate": 3.4364917058181934e-05, "loss": 0.0057, "step": 210480 }, { "epoch": 50.53, "learning_rate": 3.4360655172211e-05, "loss": 0.0049, "step": 210490 }, { "epoch": 50.54, "learning_rate": 3.4356393412185886e-05, "loss": 0.0036, "step": 210500 }, { "epoch": 50.54, "learning_rate": 3.435213177814088e-05, "loss": 0.0052, "step": 210510 }, { "epoch": 50.54, "learning_rate": 3.434787027011033e-05, "loss": 0.0069, "step": 210520 }, { "epoch": 50.54, "learning_rate": 3.4343608888128556e-05, "loss": 0.0116, "step": 210530 }, { "epoch": 50.55, "learning_rate": 3.433934763222984e-05, "loss": 0.016, "step": 210540 }, { "epoch": 50.55, "learning_rate": 3.4335086502448524e-05, "loss": 0.0081, "step": 210550 }, { "epoch": 50.55, "learning_rate": 3.433082549881891e-05, "loss": 0.0034, "step": 210560 }, { "epoch": 50.55, "learning_rate": 3.432656462137533e-05, "loss": 0.0096, "step": 210570 }, { "epoch": 50.56, "learning_rate": 3.4322303870152105e-05, "loss": 0.0078, "step": 210580 }, { "epoch": 50.56, "learning_rate": 3.431804324518351e-05, "loss": 0.0027, "step": 210590 }, { "epoch": 50.56, "learning_rate": 3.4313782746503886e-05, "loss": 0.0057, "step": 210600 }, { "epoch": 50.56, "learning_rate": 3.430952237414752e-05, "loss": 0.0069, "step": 210610 }, { "epoch": 50.56, "learning_rate": 3.430526212814876e-05, "loss": 0.0063, "step": 210620 }, { "epoch": 50.57, "learning_rate": 3.430100200854188e-05, "loss": 0.0042, "step": 210630 }, { "epoch": 50.57, "learning_rate": 3.4296742015361195e-05, "loss": 0.0041, "step": 210640 }, { "epoch": 50.57, "learning_rate": 3.429248214864102e-05, "loss": 0.0062, "step": 210650 }, { "epoch": 50.57, "learning_rate": 3.4288222408415646e-05, "loss": 0.0031, "step": 210660 }, { "epoch": 50.58, "learning_rate": 3.4283962794719415e-05, "loss": 0.0162, "step": 210670 }, { "epoch": 50.58, "learning_rate": 3.4279703307586575e-05, "loss": 0.0092, "step": 210680 }, { "epoch": 50.58, "learning_rate": 3.427544394705146e-05, "loss": 0.0039, "step": 210690 }, { "epoch": 50.58, "learning_rate": 3.427118471314836e-05, "loss": 0.0047, "step": 210700 }, { "epoch": 50.59, "learning_rate": 3.426692560591158e-05, "loss": 0.0066, "step": 210710 }, { "epoch": 50.59, "learning_rate": 3.4262666625375436e-05, "loss": 0.006, "step": 210720 }, { "epoch": 50.59, "learning_rate": 3.42584077715742e-05, "loss": 0.0134, "step": 210730 }, { "epoch": 50.59, "learning_rate": 3.4254149044542185e-05, "loss": 0.0068, "step": 210740 }, { "epoch": 50.59, "learning_rate": 3.4249890444313665e-05, "loss": 0.0077, "step": 210750 }, { "epoch": 50.6, "learning_rate": 3.424563197092296e-05, "loss": 0.0137, "step": 210760 }, { "epoch": 50.6, "learning_rate": 3.424137362440438e-05, "loss": 0.0108, "step": 210770 }, { "epoch": 50.6, "learning_rate": 3.4237115404792165e-05, "loss": 0.0057, "step": 210780 }, { "epoch": 50.6, "learning_rate": 3.423285731212064e-05, "loss": 0.0124, "step": 210790 }, { "epoch": 50.61, "learning_rate": 3.422859934642409e-05, "loss": 0.0032, "step": 210800 }, { "epoch": 50.61, "learning_rate": 3.4224341507736827e-05, "loss": 0.0132, "step": 210810 }, { "epoch": 50.61, "learning_rate": 3.4220083796093105e-05, "loss": 0.0169, "step": 210820 }, { "epoch": 50.61, "learning_rate": 3.421582621152722e-05, "loss": 0.01, "step": 210830 }, { "epoch": 50.61, "learning_rate": 3.4211568754073475e-05, "loss": 0.0093, "step": 210840 }, { "epoch": 50.62, "learning_rate": 3.420731142376613e-05, "loss": 0.0074, "step": 210850 }, { "epoch": 50.62, "learning_rate": 3.420305422063953e-05, "loss": 0.0055, "step": 210860 }, { "epoch": 50.62, "learning_rate": 3.419879714472787e-05, "loss": 0.0065, "step": 210870 }, { "epoch": 50.62, "learning_rate": 3.41945401960655e-05, "loss": 0.0051, "step": 210880 }, { "epoch": 50.63, "learning_rate": 3.419028337468667e-05, "loss": 0.0075, "step": 210890 }, { "epoch": 50.63, "learning_rate": 3.418602668062567e-05, "loss": 0.0034, "step": 210900 }, { "epoch": 50.63, "learning_rate": 3.41817701139168e-05, "loss": 0.0068, "step": 210910 }, { "epoch": 50.63, "learning_rate": 3.4177513674594297e-05, "loss": 0.0039, "step": 210920 }, { "epoch": 50.64, "learning_rate": 3.417325736269247e-05, "loss": 0.0037, "step": 210930 }, { "epoch": 50.64, "learning_rate": 3.4169001178245575e-05, "loss": 0.0055, "step": 210940 }, { "epoch": 50.64, "learning_rate": 3.416474512128792e-05, "loss": 0.0095, "step": 210950 }, { "epoch": 50.64, "learning_rate": 3.416048919185375e-05, "loss": 0.0057, "step": 210960 }, { "epoch": 50.64, "learning_rate": 3.415623338997733e-05, "loss": 0.0061, "step": 210970 }, { "epoch": 50.65, "learning_rate": 3.415197771569297e-05, "loss": 0.0068, "step": 210980 }, { "epoch": 50.65, "learning_rate": 3.414772216903491e-05, "loss": 0.0074, "step": 210990 }, { "epoch": 50.65, "learning_rate": 3.4143466750037446e-05, "loss": 0.0075, "step": 211000 }, { "epoch": 50.65, "learning_rate": 3.413921145873483e-05, "loss": 0.0101, "step": 211010 }, { "epoch": 50.66, "learning_rate": 3.413495629516132e-05, "loss": 0.0059, "step": 211020 }, { "epoch": 50.66, "learning_rate": 3.4130701259351207e-05, "loss": 0.0026, "step": 211030 }, { "epoch": 50.66, "learning_rate": 3.4126446351338734e-05, "loss": 0.0043, "step": 211040 }, { "epoch": 50.66, "learning_rate": 3.412219157115821e-05, "loss": 0.0055, "step": 211050 }, { "epoch": 50.66, "learning_rate": 3.411793691884385e-05, "loss": 0.0055, "step": 211060 }, { "epoch": 50.67, "learning_rate": 3.4113682394429934e-05, "loss": 0.0046, "step": 211070 }, { "epoch": 50.67, "learning_rate": 3.4109427997950735e-05, "loss": 0.0075, "step": 211080 }, { "epoch": 50.67, "learning_rate": 3.41051737294405e-05, "loss": 0.0079, "step": 211090 }, { "epoch": 50.67, "learning_rate": 3.4100919588933514e-05, "loss": 0.0076, "step": 211100 }, { "epoch": 50.68, "learning_rate": 3.409666557646399e-05, "loss": 0.0033, "step": 211110 }, { "epoch": 50.68, "learning_rate": 3.4092411692066226e-05, "loss": 0.0065, "step": 211120 }, { "epoch": 50.68, "learning_rate": 3.408815793577447e-05, "loss": 0.0134, "step": 211130 }, { "epoch": 50.68, "learning_rate": 3.408390430762298e-05, "loss": 0.0113, "step": 211140 }, { "epoch": 50.69, "learning_rate": 3.4079650807646e-05, "loss": 0.0037, "step": 211150 }, { "epoch": 50.69, "learning_rate": 3.4075397435877775e-05, "loss": 0.01, "step": 211160 }, { "epoch": 50.69, "learning_rate": 3.407114419235259e-05, "loss": 0.0095, "step": 211170 }, { "epoch": 50.69, "learning_rate": 3.406689107710467e-05, "loss": 0.0059, "step": 211180 }, { "epoch": 50.69, "learning_rate": 3.406263809016829e-05, "loss": 0.0069, "step": 211190 }, { "epoch": 50.7, "learning_rate": 3.4058385231577674e-05, "loss": 0.0042, "step": 211200 }, { "epoch": 50.7, "learning_rate": 3.405413250136708e-05, "loss": 0.0054, "step": 211210 }, { "epoch": 50.7, "learning_rate": 3.404987989957077e-05, "loss": 0.0057, "step": 211220 }, { "epoch": 50.7, "learning_rate": 3.404562742622296e-05, "loss": 0.002, "step": 211230 }, { "epoch": 50.71, "learning_rate": 3.404137508135794e-05, "loss": 0.0022, "step": 211240 }, { "epoch": 50.71, "learning_rate": 3.403712286500992e-05, "loss": 0.0164, "step": 211250 }, { "epoch": 50.71, "learning_rate": 3.403287077721314e-05, "loss": 0.0122, "step": 211260 }, { "epoch": 50.71, "learning_rate": 3.402861881800187e-05, "loss": 0.0049, "step": 211270 }, { "epoch": 50.72, "learning_rate": 3.402436698741035e-05, "loss": 0.0041, "step": 211280 }, { "epoch": 50.72, "learning_rate": 3.40201152854728e-05, "loss": 0.0068, "step": 211290 }, { "epoch": 50.72, "learning_rate": 3.401586371222345e-05, "loss": 0.0061, "step": 211300 }, { "epoch": 50.72, "learning_rate": 3.401161226769657e-05, "loss": 0.0143, "step": 211310 }, { "epoch": 50.72, "learning_rate": 3.400736095192637e-05, "loss": 0.0055, "step": 211320 }, { "epoch": 50.73, "learning_rate": 3.4003109764947124e-05, "loss": 0.0148, "step": 211330 }, { "epoch": 50.73, "learning_rate": 3.399885870679303e-05, "loss": 0.0066, "step": 211340 }, { "epoch": 50.73, "learning_rate": 3.3994607777498326e-05, "loss": 0.0028, "step": 211350 }, { "epoch": 50.73, "learning_rate": 3.3990356977097274e-05, "loss": 0.0096, "step": 211360 }, { "epoch": 50.74, "learning_rate": 3.398610630562406e-05, "loss": 0.0051, "step": 211370 }, { "epoch": 50.74, "learning_rate": 3.398185576311298e-05, "loss": 0.0063, "step": 211380 }, { "epoch": 50.74, "learning_rate": 3.397760534959821e-05, "loss": 0.0045, "step": 211390 }, { "epoch": 50.74, "learning_rate": 3.397335506511399e-05, "loss": 0.0112, "step": 211400 }, { "epoch": 50.74, "learning_rate": 3.396910490969456e-05, "loss": 0.0075, "step": 211410 }, { "epoch": 50.75, "learning_rate": 3.396485488337413e-05, "loss": 0.005, "step": 211420 }, { "epoch": 50.75, "learning_rate": 3.396060498618696e-05, "loss": 0.0031, "step": 211430 }, { "epoch": 50.75, "learning_rate": 3.395635521816724e-05, "loss": 0.0111, "step": 211440 }, { "epoch": 50.75, "learning_rate": 3.39521055793492e-05, "loss": 0.0101, "step": 211450 }, { "epoch": 50.76, "learning_rate": 3.394785606976708e-05, "loss": 0.0111, "step": 211460 }, { "epoch": 50.76, "learning_rate": 3.39436066894551e-05, "loss": 0.0096, "step": 211470 }, { "epoch": 50.76, "learning_rate": 3.393935743844745e-05, "loss": 0.0053, "step": 211480 }, { "epoch": 50.76, "learning_rate": 3.3935108316778384e-05, "loss": 0.0074, "step": 211490 }, { "epoch": 50.77, "learning_rate": 3.39308593244821e-05, "loss": 0.0162, "step": 211500 }, { "epoch": 50.77, "learning_rate": 3.3926610461592836e-05, "loss": 0.0039, "step": 211510 }, { "epoch": 50.77, "learning_rate": 3.3922361728144804e-05, "loss": 0.0073, "step": 211520 }, { "epoch": 50.77, "learning_rate": 3.39181131241722e-05, "loss": 0.0059, "step": 211530 }, { "epoch": 50.77, "learning_rate": 3.391386464970924e-05, "loss": 0.0094, "step": 211540 }, { "epoch": 50.78, "learning_rate": 3.390961630479016e-05, "loss": 0.0097, "step": 211550 }, { "epoch": 50.78, "learning_rate": 3.3905368089449154e-05, "loss": 0.0061, "step": 211560 }, { "epoch": 50.78, "learning_rate": 3.390112000372047e-05, "loss": 0.011, "step": 211570 }, { "epoch": 50.78, "learning_rate": 3.389687204763826e-05, "loss": 0.0065, "step": 211580 }, { "epoch": 50.79, "learning_rate": 3.389262422123676e-05, "loss": 0.0031, "step": 211590 }, { "epoch": 50.79, "learning_rate": 3.38883765245502e-05, "loss": 0.0071, "step": 211600 }, { "epoch": 50.79, "learning_rate": 3.388412895761277e-05, "loss": 0.0059, "step": 211610 }, { "epoch": 50.79, "learning_rate": 3.387988152045866e-05, "loss": 0.0074, "step": 211620 }, { "epoch": 50.8, "learning_rate": 3.3875634213122086e-05, "loss": 0.0092, "step": 211630 }, { "epoch": 50.8, "learning_rate": 3.387138703563726e-05, "loss": 0.0071, "step": 211640 }, { "epoch": 50.8, "learning_rate": 3.386713998803838e-05, "loss": 0.0058, "step": 211650 }, { "epoch": 50.8, "learning_rate": 3.386289307035967e-05, "loss": 0.0104, "step": 211660 }, { "epoch": 50.8, "learning_rate": 3.3858646282635285e-05, "loss": 0.0061, "step": 211670 }, { "epoch": 50.81, "learning_rate": 3.385439962489946e-05, "loss": 0.0036, "step": 211680 }, { "epoch": 50.81, "learning_rate": 3.3850153097186366e-05, "loss": 0.0059, "step": 211690 }, { "epoch": 50.81, "learning_rate": 3.384590669953024e-05, "loss": 0.0105, "step": 211700 }, { "epoch": 50.81, "learning_rate": 3.3841660431965264e-05, "loss": 0.0033, "step": 211710 }, { "epoch": 50.82, "learning_rate": 3.3837414294525615e-05, "loss": 0.0084, "step": 211720 }, { "epoch": 50.82, "learning_rate": 3.38331682872455e-05, "loss": 0.0117, "step": 211730 }, { "epoch": 50.82, "learning_rate": 3.382892241015911e-05, "loss": 0.005, "step": 211740 }, { "epoch": 50.82, "learning_rate": 3.3824676663300634e-05, "loss": 0.0069, "step": 211750 }, { "epoch": 50.82, "learning_rate": 3.3820431046704296e-05, "loss": 0.0073, "step": 211760 }, { "epoch": 50.83, "learning_rate": 3.3816185560404244e-05, "loss": 0.0042, "step": 211770 }, { "epoch": 50.83, "learning_rate": 3.381194020443467e-05, "loss": 0.0036, "step": 211780 }, { "epoch": 50.83, "learning_rate": 3.38076949788298e-05, "loss": 0.0043, "step": 211790 }, { "epoch": 50.83, "learning_rate": 3.38034498836238e-05, "loss": 0.0045, "step": 211800 }, { "epoch": 50.84, "learning_rate": 3.379920491885083e-05, "loss": 0.0063, "step": 211810 }, { "epoch": 50.84, "learning_rate": 3.379496008454511e-05, "loss": 0.0109, "step": 211820 }, { "epoch": 50.84, "learning_rate": 3.379071538074081e-05, "loss": 0.0063, "step": 211830 }, { "epoch": 50.84, "learning_rate": 3.378647080747213e-05, "loss": 0.0118, "step": 211840 }, { "epoch": 50.85, "learning_rate": 3.378222636477324e-05, "loss": 0.0043, "step": 211850 }, { "epoch": 50.85, "learning_rate": 3.3777982052678305e-05, "loss": 0.0057, "step": 211860 }, { "epoch": 50.85, "learning_rate": 3.3773737871221524e-05, "loss": 0.0098, "step": 211870 }, { "epoch": 50.85, "learning_rate": 3.376949382043707e-05, "loss": 0.0062, "step": 211880 }, { "epoch": 50.85, "learning_rate": 3.3765249900359134e-05, "loss": 0.0077, "step": 211890 }, { "epoch": 50.86, "learning_rate": 3.376100611102188e-05, "loss": 0.0075, "step": 211900 }, { "epoch": 50.86, "learning_rate": 3.375676245245947e-05, "loss": 0.0224, "step": 211910 }, { "epoch": 50.86, "learning_rate": 3.3752518924706114e-05, "loss": 0.0108, "step": 211920 }, { "epoch": 50.86, "learning_rate": 3.374827552779595e-05, "loss": 0.0101, "step": 211930 }, { "epoch": 50.87, "learning_rate": 3.3744032261763194e-05, "loss": 0.0038, "step": 211940 }, { "epoch": 50.87, "learning_rate": 3.3739789126641964e-05, "loss": 0.018, "step": 211950 }, { "epoch": 50.87, "learning_rate": 3.3735546122466465e-05, "loss": 0.009, "step": 211960 }, { "epoch": 50.87, "learning_rate": 3.3731303249270854e-05, "loss": 0.0049, "step": 211970 }, { "epoch": 50.88, "learning_rate": 3.3727060507089306e-05, "loss": 0.0163, "step": 211980 }, { "epoch": 50.88, "learning_rate": 3.3722817895956e-05, "loss": 0.0022, "step": 211990 }, { "epoch": 50.88, "learning_rate": 3.371857541590507e-05, "loss": 0.0025, "step": 212000 }, { "epoch": 50.88, "learning_rate": 3.371433306697071e-05, "loss": 0.0123, "step": 212010 }, { "epoch": 50.88, "learning_rate": 3.371009084918706e-05, "loss": 0.0094, "step": 212020 }, { "epoch": 50.89, "learning_rate": 3.370584876258831e-05, "loss": 0.0068, "step": 212030 }, { "epoch": 50.89, "learning_rate": 3.370160680720862e-05, "loss": 0.005, "step": 212040 }, { "epoch": 50.89, "learning_rate": 3.369736498308212e-05, "loss": 0.0053, "step": 212050 }, { "epoch": 50.89, "learning_rate": 3.3693123290243e-05, "loss": 0.0063, "step": 212060 }, { "epoch": 50.9, "learning_rate": 3.36888817287254e-05, "loss": 0.0235, "step": 212070 }, { "epoch": 50.9, "learning_rate": 3.36846402985635e-05, "loss": 0.0048, "step": 212080 }, { "epoch": 50.9, "learning_rate": 3.3680398999791455e-05, "loss": 0.0029, "step": 212090 }, { "epoch": 50.9, "learning_rate": 3.367615783244338e-05, "loss": 0.0038, "step": 212100 }, { "epoch": 50.9, "learning_rate": 3.367191679655348e-05, "loss": 0.0057, "step": 212110 }, { "epoch": 50.91, "learning_rate": 3.366767589215587e-05, "loss": 0.0049, "step": 212120 }, { "epoch": 50.91, "learning_rate": 3.3663435119284746e-05, "loss": 0.0057, "step": 212130 }, { "epoch": 50.91, "learning_rate": 3.365919447797423e-05, "loss": 0.0076, "step": 212140 }, { "epoch": 50.91, "learning_rate": 3.365495396825846e-05, "loss": 0.0182, "step": 212150 }, { "epoch": 50.92, "learning_rate": 3.365071359017161e-05, "loss": 0.0033, "step": 212160 }, { "epoch": 50.92, "learning_rate": 3.364647334374782e-05, "loss": 0.0021, "step": 212170 }, { "epoch": 50.92, "learning_rate": 3.364223322902126e-05, "loss": 0.0031, "step": 212180 }, { "epoch": 50.92, "learning_rate": 3.3637993246026025e-05, "loss": 0.0053, "step": 212190 }, { "epoch": 50.93, "learning_rate": 3.36337533947963e-05, "loss": 0.005, "step": 212200 }, { "epoch": 50.93, "learning_rate": 3.3629513675366206e-05, "loss": 0.0077, "step": 212210 }, { "epoch": 50.93, "learning_rate": 3.362527408776991e-05, "loss": 0.0068, "step": 212220 }, { "epoch": 50.93, "learning_rate": 3.362103463204155e-05, "loss": 0.0027, "step": 212230 }, { "epoch": 50.93, "learning_rate": 3.3616795308215245e-05, "loss": 0.0029, "step": 212240 }, { "epoch": 50.94, "learning_rate": 3.361255611632515e-05, "loss": 0.0021, "step": 212250 }, { "epoch": 50.94, "learning_rate": 3.36083170564054e-05, "loss": 0.0029, "step": 212260 }, { "epoch": 50.94, "learning_rate": 3.360407812849016e-05, "loss": 0.0038, "step": 212270 }, { "epoch": 50.94, "learning_rate": 3.3599839332613524e-05, "loss": 0.0033, "step": 212280 }, { "epoch": 50.95, "learning_rate": 3.359560066880965e-05, "loss": 0.0089, "step": 212290 }, { "epoch": 50.95, "learning_rate": 3.359136213711266e-05, "loss": 0.0111, "step": 212300 }, { "epoch": 50.95, "learning_rate": 3.3587123737556695e-05, "loss": 0.0074, "step": 212310 }, { "epoch": 51.0, "learning_rate": 3.3582885470175906e-05, "loss": 0.0055, "step": 212320 }, { "epoch": 51.0, "learning_rate": 3.35786473350044e-05, "loss": 0.0096, "step": 212330 }, { "epoch": 51.01, "learning_rate": 3.3574409332076305e-05, "loss": 0.0053, "step": 212340 }, { "epoch": 51.01, "learning_rate": 3.357017146142577e-05, "loss": 0.0116, "step": 212350 }, { "epoch": 51.01, "learning_rate": 3.3565933723086894e-05, "loss": 0.0075, "step": 212360 }, { "epoch": 51.01, "learning_rate": 3.3561696117093865e-05, "loss": 0.0072, "step": 212370 }, { "epoch": 51.02, "learning_rate": 3.355745864348073e-05, "loss": 0.0023, "step": 212380 }, { "epoch": 51.02, "learning_rate": 3.355322130228166e-05, "loss": 0.0039, "step": 212390 }, { "epoch": 51.02, "learning_rate": 3.354898409353076e-05, "loss": 0.0052, "step": 212400 }, { "epoch": 51.02, "learning_rate": 3.3544747017262165e-05, "loss": 0.0059, "step": 212410 }, { "epoch": 51.02, "learning_rate": 3.3540510073510014e-05, "loss": 0.0076, "step": 212420 }, { "epoch": 51.03, "learning_rate": 3.353627326230839e-05, "loss": 0.0034, "step": 212430 }, { "epoch": 51.03, "learning_rate": 3.3532036583691436e-05, "loss": 0.0051, "step": 212440 }, { "epoch": 51.03, "learning_rate": 3.352780003769325e-05, "loss": 0.0057, "step": 212450 }, { "epoch": 51.03, "learning_rate": 3.352356362434799e-05, "loss": 0.0055, "step": 212460 }, { "epoch": 51.04, "learning_rate": 3.351932734368974e-05, "loss": 0.0073, "step": 212470 }, { "epoch": 51.04, "learning_rate": 3.35150911957526e-05, "loss": 0.008, "step": 212480 }, { "epoch": 51.04, "learning_rate": 3.3510855180570736e-05, "loss": 0.0096, "step": 212490 }, { "epoch": 51.04, "learning_rate": 3.3506619298178204e-05, "loss": 0.007, "step": 212500 }, { "epoch": 51.05, "learning_rate": 3.350238354860917e-05, "loss": 0.011, "step": 212510 }, { "epoch": 51.05, "learning_rate": 3.3498147931897706e-05, "loss": 0.006, "step": 212520 }, { "epoch": 51.05, "learning_rate": 3.349391244807793e-05, "loss": 0.0167, "step": 212530 }, { "epoch": 51.05, "learning_rate": 3.348967709718396e-05, "loss": 0.0043, "step": 212540 }, { "epoch": 51.05, "learning_rate": 3.34854418792499e-05, "loss": 0.0158, "step": 212550 }, { "epoch": 51.06, "learning_rate": 3.348120679430987e-05, "loss": 0.0052, "step": 212560 }, { "epoch": 51.06, "learning_rate": 3.3476971842397955e-05, "loss": 0.0055, "step": 212570 }, { "epoch": 51.06, "learning_rate": 3.347273702354825e-05, "loss": 0.0099, "step": 212580 }, { "epoch": 51.06, "learning_rate": 3.346850233779489e-05, "loss": 0.0073, "step": 212590 }, { "epoch": 51.07, "learning_rate": 3.346426778517197e-05, "loss": 0.0055, "step": 212600 }, { "epoch": 51.07, "learning_rate": 3.346003336571358e-05, "loss": 0.0034, "step": 212610 }, { "epoch": 51.07, "learning_rate": 3.345579907945381e-05, "loss": 0.0043, "step": 212620 }, { "epoch": 51.07, "learning_rate": 3.345156492642679e-05, "loss": 0.0045, "step": 212630 }, { "epoch": 51.07, "learning_rate": 3.3447330906666584e-05, "loss": 0.0051, "step": 212640 }, { "epoch": 51.08, "learning_rate": 3.3443097020207337e-05, "loss": 0.0113, "step": 212650 }, { "epoch": 51.08, "learning_rate": 3.3438863267083096e-05, "loss": 0.0071, "step": 212660 }, { "epoch": 51.08, "learning_rate": 3.343462964732797e-05, "loss": 0.0138, "step": 212670 }, { "epoch": 51.08, "learning_rate": 3.343039616097607e-05, "loss": 0.0065, "step": 212680 }, { "epoch": 51.09, "learning_rate": 3.342616280806146e-05, "loss": 0.0093, "step": 212690 }, { "epoch": 51.09, "learning_rate": 3.342192958861828e-05, "loss": 0.0043, "step": 212700 }, { "epoch": 51.09, "learning_rate": 3.341769650268057e-05, "loss": 0.0064, "step": 212710 }, { "epoch": 51.09, "learning_rate": 3.3413463550282435e-05, "loss": 0.0079, "step": 212720 }, { "epoch": 51.1, "learning_rate": 3.340923073145797e-05, "loss": 0.0163, "step": 212730 }, { "epoch": 51.1, "learning_rate": 3.340499804624127e-05, "loss": 0.0157, "step": 212740 }, { "epoch": 51.1, "learning_rate": 3.340076549466641e-05, "loss": 0.007, "step": 212750 }, { "epoch": 51.1, "learning_rate": 3.339653307676748e-05, "loss": 0.0098, "step": 212760 }, { "epoch": 51.1, "learning_rate": 3.339230079257854e-05, "loss": 0.0047, "step": 212770 }, { "epoch": 51.11, "learning_rate": 3.338806864213372e-05, "loss": 0.0133, "step": 212780 }, { "epoch": 51.11, "learning_rate": 3.338383662546708e-05, "loss": 0.008, "step": 212790 }, { "epoch": 51.11, "learning_rate": 3.337960474261268e-05, "loss": 0.0039, "step": 212800 }, { "epoch": 51.11, "learning_rate": 3.3375372993604615e-05, "loss": 0.003, "step": 212810 }, { "epoch": 51.12, "learning_rate": 3.3371141378476976e-05, "loss": 0.0058, "step": 212820 }, { "epoch": 51.12, "learning_rate": 3.336690989726382e-05, "loss": 0.003, "step": 212830 }, { "epoch": 51.12, "learning_rate": 3.336267854999926e-05, "loss": 0.0082, "step": 212840 }, { "epoch": 51.12, "learning_rate": 3.335844733671733e-05, "loss": 0.0162, "step": 212850 }, { "epoch": 51.12, "learning_rate": 3.335421625745211e-05, "loss": 0.0025, "step": 212860 }, { "epoch": 51.13, "learning_rate": 3.33499853122377e-05, "loss": 0.0052, "step": 212870 }, { "epoch": 51.13, "learning_rate": 3.3345754501108143e-05, "loss": 0.0036, "step": 212880 }, { "epoch": 51.13, "learning_rate": 3.334152382409755e-05, "loss": 0.0035, "step": 212890 }, { "epoch": 51.13, "learning_rate": 3.333729328123995e-05, "loss": 0.0042, "step": 212900 }, { "epoch": 51.14, "learning_rate": 3.333306287256942e-05, "loss": 0.0063, "step": 212910 }, { "epoch": 51.14, "learning_rate": 3.332883259812004e-05, "loss": 0.005, "step": 212920 }, { "epoch": 51.14, "learning_rate": 3.332460245792589e-05, "loss": 0.0038, "step": 212930 }, { "epoch": 51.14, "learning_rate": 3.3320372452021e-05, "loss": 0.0153, "step": 212940 }, { "epoch": 51.15, "learning_rate": 3.331614258043946e-05, "loss": 0.0063, "step": 212950 }, { "epoch": 51.15, "learning_rate": 3.331191284321531e-05, "loss": 0.0037, "step": 212960 }, { "epoch": 51.15, "learning_rate": 3.3307683240382644e-05, "loss": 0.0122, "step": 212970 }, { "epoch": 51.15, "learning_rate": 3.3303453771975523e-05, "loss": 0.004, "step": 212980 }, { "epoch": 51.15, "learning_rate": 3.329922443802798e-05, "loss": 0.0038, "step": 212990 }, { "epoch": 51.16, "learning_rate": 3.329499523857409e-05, "loss": 0.0037, "step": 213000 }, { "epoch": 51.16, "learning_rate": 3.32907661736479e-05, "loss": 0.0042, "step": 213010 }, { "epoch": 51.16, "learning_rate": 3.3286537243283484e-05, "loss": 0.0059, "step": 213020 }, { "epoch": 51.16, "learning_rate": 3.328230844751491e-05, "loss": 0.0033, "step": 213030 }, { "epoch": 51.17, "learning_rate": 3.327807978637619e-05, "loss": 0.0111, "step": 213040 }, { "epoch": 51.17, "learning_rate": 3.32738512599014e-05, "loss": 0.0168, "step": 213050 }, { "epoch": 51.17, "learning_rate": 3.326962286812461e-05, "loss": 0.0025, "step": 213060 }, { "epoch": 51.17, "learning_rate": 3.326539461107984e-05, "loss": 0.0076, "step": 213070 }, { "epoch": 51.18, "learning_rate": 3.3261166488801185e-05, "loss": 0.0065, "step": 213080 }, { "epoch": 51.18, "learning_rate": 3.325693850132265e-05, "loss": 0.0055, "step": 213090 }, { "epoch": 51.18, "learning_rate": 3.325271064867829e-05, "loss": 0.0057, "step": 213100 }, { "epoch": 51.18, "learning_rate": 3.324848293090218e-05, "loss": 0.0048, "step": 213110 }, { "epoch": 51.18, "learning_rate": 3.3244255348028355e-05, "loss": 0.0111, "step": 213120 }, { "epoch": 51.19, "learning_rate": 3.3240027900090834e-05, "loss": 0.0142, "step": 213130 }, { "epoch": 51.19, "learning_rate": 3.32358005871237e-05, "loss": 0.0031, "step": 213140 }, { "epoch": 51.19, "learning_rate": 3.3231573409160954e-05, "loss": 0.0041, "step": 213150 }, { "epoch": 51.19, "learning_rate": 3.322734636623668e-05, "loss": 0.0034, "step": 213160 }, { "epoch": 51.2, "learning_rate": 3.322311945838491e-05, "loss": 0.0097, "step": 213170 }, { "epoch": 51.2, "learning_rate": 3.321889268563966e-05, "loss": 0.0135, "step": 213180 }, { "epoch": 51.2, "learning_rate": 3.3214666048034994e-05, "loss": 0.0068, "step": 213190 }, { "epoch": 51.2, "learning_rate": 3.3210439545604926e-05, "loss": 0.0047, "step": 213200 }, { "epoch": 51.2, "learning_rate": 3.3206213178383515e-05, "loss": 0.0033, "step": 213210 }, { "epoch": 51.21, "learning_rate": 3.3201986946404806e-05, "loss": 0.0042, "step": 213220 }, { "epoch": 51.21, "learning_rate": 3.3197760849702795e-05, "loss": 0.0039, "step": 213230 }, { "epoch": 51.21, "learning_rate": 3.3193534888311525e-05, "loss": 0.018, "step": 213240 }, { "epoch": 51.21, "learning_rate": 3.318930906226506e-05, "loss": 0.0077, "step": 213250 }, { "epoch": 51.22, "learning_rate": 3.3185083371597415e-05, "loss": 0.0042, "step": 213260 }, { "epoch": 51.22, "learning_rate": 3.3180857816342594e-05, "loss": 0.0055, "step": 213270 }, { "epoch": 51.22, "learning_rate": 3.317663239653466e-05, "loss": 0.0056, "step": 213280 }, { "epoch": 51.22, "learning_rate": 3.317240711220761e-05, "loss": 0.003, "step": 213290 }, { "epoch": 51.23, "learning_rate": 3.31681819633955e-05, "loss": 0.006, "step": 213300 }, { "epoch": 51.23, "learning_rate": 3.316395695013236e-05, "loss": 0.0028, "step": 213310 }, { "epoch": 51.23, "learning_rate": 3.315973207245218e-05, "loss": 0.0038, "step": 213320 }, { "epoch": 51.23, "learning_rate": 3.3155507330389e-05, "loss": 0.0069, "step": 213330 }, { "epoch": 51.23, "learning_rate": 3.3151282723976854e-05, "loss": 0.0108, "step": 213340 }, { "epoch": 51.24, "learning_rate": 3.314705825324975e-05, "loss": 0.0037, "step": 213350 }, { "epoch": 51.24, "learning_rate": 3.314283391824173e-05, "loss": 0.0042, "step": 213360 }, { "epoch": 51.24, "learning_rate": 3.3138609718986766e-05, "loss": 0.0053, "step": 213370 }, { "epoch": 51.24, "learning_rate": 3.313438565551893e-05, "loss": 0.0074, "step": 213380 }, { "epoch": 51.25, "learning_rate": 3.313016172787219e-05, "loss": 0.0077, "step": 213390 }, { "epoch": 51.25, "learning_rate": 3.312593793608061e-05, "loss": 0.0198, "step": 213400 }, { "epoch": 51.25, "learning_rate": 3.312171428017819e-05, "loss": 0.0097, "step": 213410 }, { "epoch": 51.25, "learning_rate": 3.3117490760198906e-05, "loss": 0.0034, "step": 213420 }, { "epoch": 51.26, "learning_rate": 3.3113267376176815e-05, "loss": 0.0035, "step": 213430 }, { "epoch": 51.26, "learning_rate": 3.31090441281459e-05, "loss": 0.0073, "step": 213440 }, { "epoch": 51.26, "learning_rate": 3.310482101614022e-05, "loss": 0.0056, "step": 213450 }, { "epoch": 51.26, "learning_rate": 3.3100598040193706e-05, "loss": 0.0031, "step": 213460 }, { "epoch": 51.26, "learning_rate": 3.309637520034044e-05, "loss": 0.0019, "step": 213470 }, { "epoch": 51.27, "learning_rate": 3.309215249661437e-05, "loss": 0.0105, "step": 213480 }, { "epoch": 51.27, "learning_rate": 3.3087929929049546e-05, "loss": 0.0038, "step": 213490 }, { "epoch": 51.27, "learning_rate": 3.308370749767997e-05, "loss": 0.0044, "step": 213500 }, { "epoch": 51.27, "learning_rate": 3.307948520253962e-05, "loss": 0.0105, "step": 213510 }, { "epoch": 51.28, "learning_rate": 3.3075263043662506e-05, "loss": 0.007, "step": 213520 }, { "epoch": 51.28, "learning_rate": 3.307104102108263e-05, "loss": 0.0034, "step": 213530 }, { "epoch": 51.28, "learning_rate": 3.306681913483402e-05, "loss": 0.0083, "step": 213540 }, { "epoch": 51.28, "learning_rate": 3.3062597384950646e-05, "loss": 0.0033, "step": 213550 }, { "epoch": 51.28, "learning_rate": 3.30583757714665e-05, "loss": 0.0025, "step": 213560 }, { "epoch": 51.29, "learning_rate": 3.305415429441561e-05, "loss": 0.0255, "step": 213570 }, { "epoch": 51.29, "learning_rate": 3.3049932953831934e-05, "loss": 0.0029, "step": 213580 }, { "epoch": 51.29, "learning_rate": 3.304571174974952e-05, "loss": 0.0055, "step": 213590 }, { "epoch": 51.29, "learning_rate": 3.3041490682202306e-05, "loss": 0.0065, "step": 213600 }, { "epoch": 51.3, "learning_rate": 3.303726975122431e-05, "loss": 0.0028, "step": 213610 }, { "epoch": 51.3, "learning_rate": 3.303304895684953e-05, "loss": 0.0031, "step": 213620 }, { "epoch": 51.3, "learning_rate": 3.302882829911193e-05, "loss": 0.0034, "step": 213630 }, { "epoch": 51.3, "learning_rate": 3.302460777804556e-05, "loss": 0.0071, "step": 213640 }, { "epoch": 51.31, "learning_rate": 3.302038739368434e-05, "loss": 0.0042, "step": 213650 }, { "epoch": 51.31, "learning_rate": 3.301616714606228e-05, "loss": 0.0065, "step": 213660 }, { "epoch": 51.31, "learning_rate": 3.301194703521337e-05, "loss": 0.0021, "step": 213670 }, { "epoch": 51.31, "learning_rate": 3.300772706117161e-05, "loss": 0.0125, "step": 213680 }, { "epoch": 51.31, "learning_rate": 3.300350722397097e-05, "loss": 0.0089, "step": 213690 }, { "epoch": 51.32, "learning_rate": 3.2999287523645416e-05, "loss": 0.0064, "step": 213700 }, { "epoch": 51.32, "learning_rate": 3.299506796022896e-05, "loss": 0.004, "step": 213710 }, { "epoch": 51.32, "learning_rate": 3.2990848533755556e-05, "loss": 0.0043, "step": 213720 }, { "epoch": 51.32, "learning_rate": 3.298662924425921e-05, "loss": 0.0101, "step": 213730 }, { "epoch": 51.33, "learning_rate": 3.29824100917739e-05, "loss": 0.0038, "step": 213740 }, { "epoch": 51.33, "learning_rate": 3.297819107633356e-05, "loss": 0.0087, "step": 213750 }, { "epoch": 51.33, "learning_rate": 3.2973972197972216e-05, "loss": 0.0026, "step": 213760 }, { "epoch": 51.33, "learning_rate": 3.296975345672381e-05, "loss": 0.0026, "step": 213770 }, { "epoch": 51.34, "learning_rate": 3.296553485262236e-05, "loss": 0.0039, "step": 213780 }, { "epoch": 51.34, "learning_rate": 3.296131638570179e-05, "loss": 0.0029, "step": 213790 }, { "epoch": 51.34, "learning_rate": 3.2957098055996086e-05, "loss": 0.0043, "step": 213800 }, { "epoch": 51.34, "learning_rate": 3.295287986353923e-05, "loss": 0.0045, "step": 213810 }, { "epoch": 51.34, "learning_rate": 3.294866180836518e-05, "loss": 0.0041, "step": 213820 }, { "epoch": 51.35, "learning_rate": 3.294444389050792e-05, "loss": 0.0075, "step": 213830 }, { "epoch": 51.35, "learning_rate": 3.2940226110001416e-05, "loss": 0.0028, "step": 213840 }, { "epoch": 51.35, "learning_rate": 3.293600846687961e-05, "loss": 0.0058, "step": 213850 }, { "epoch": 51.35, "learning_rate": 3.293179096117649e-05, "loss": 0.0059, "step": 213860 }, { "epoch": 51.36, "learning_rate": 3.2927573592925996e-05, "loss": 0.0054, "step": 213870 }, { "epoch": 51.36, "learning_rate": 3.292335636216215e-05, "loss": 0.0083, "step": 213880 }, { "epoch": 51.36, "learning_rate": 3.291913926891884e-05, "loss": 0.0071, "step": 213890 }, { "epoch": 51.36, "learning_rate": 3.291492231323007e-05, "loss": 0.0028, "step": 213900 }, { "epoch": 51.36, "learning_rate": 3.2910705495129786e-05, "loss": 0.003, "step": 213910 }, { "epoch": 51.37, "learning_rate": 3.2906488814651956e-05, "loss": 0.0029, "step": 213920 }, { "epoch": 51.37, "learning_rate": 3.2902272271830534e-05, "loss": 0.0033, "step": 213930 }, { "epoch": 51.37, "learning_rate": 3.289805586669946e-05, "loss": 0.0063, "step": 213940 }, { "epoch": 51.37, "learning_rate": 3.289383959929271e-05, "loss": 0.0156, "step": 213950 }, { "epoch": 51.38, "learning_rate": 3.288962346964423e-05, "loss": 0.0066, "step": 213960 }, { "epoch": 51.38, "learning_rate": 3.288540747778798e-05, "loss": 0.0054, "step": 213970 }, { "epoch": 51.38, "learning_rate": 3.28811916237579e-05, "loss": 0.0047, "step": 213980 }, { "epoch": 51.38, "learning_rate": 3.2876975907587945e-05, "loss": 0.0082, "step": 213990 }, { "epoch": 51.39, "learning_rate": 3.287276032931208e-05, "loss": 0.0025, "step": 214000 }, { "epoch": 51.39, "learning_rate": 3.286854488896422e-05, "loss": 0.0036, "step": 214010 }, { "epoch": 51.39, "learning_rate": 3.2864329586578355e-05, "loss": 0.004, "step": 214020 }, { "epoch": 51.39, "learning_rate": 3.2860114422188406e-05, "loss": 0.0089, "step": 214030 }, { "epoch": 51.39, "learning_rate": 3.2855899395828304e-05, "loss": 0.0055, "step": 214040 }, { "epoch": 51.4, "learning_rate": 3.2851684507532024e-05, "loss": 0.0085, "step": 214050 }, { "epoch": 51.4, "learning_rate": 3.2847469757333495e-05, "loss": 0.0125, "step": 214060 }, { "epoch": 51.4, "learning_rate": 3.284325514526667e-05, "loss": 0.0039, "step": 214070 }, { "epoch": 51.4, "learning_rate": 3.2839040671365474e-05, "loss": 0.0057, "step": 214080 }, { "epoch": 51.41, "learning_rate": 3.2834826335663847e-05, "loss": 0.0024, "step": 214090 }, { "epoch": 51.41, "learning_rate": 3.2830612138195726e-05, "loss": 0.0041, "step": 214100 }, { "epoch": 51.41, "learning_rate": 3.282639807899508e-05, "loss": 0.0048, "step": 214110 }, { "epoch": 51.41, "learning_rate": 3.28221841580958e-05, "loss": 0.0019, "step": 214120 }, { "epoch": 51.42, "learning_rate": 3.281797037553185e-05, "loss": 0.004, "step": 214130 }, { "epoch": 51.42, "learning_rate": 3.281375673133715e-05, "loss": 0.004, "step": 214140 }, { "epoch": 51.42, "learning_rate": 3.280954322554564e-05, "loss": 0.0035, "step": 214150 }, { "epoch": 51.42, "learning_rate": 3.2805329858191266e-05, "loss": 0.0051, "step": 214160 }, { "epoch": 51.42, "learning_rate": 3.2801116629307936e-05, "loss": 0.0038, "step": 214170 }, { "epoch": 51.43, "learning_rate": 3.279690353892958e-05, "loss": 0.0031, "step": 214180 }, { "epoch": 51.43, "learning_rate": 3.2792690587090145e-05, "loss": 0.0045, "step": 214190 }, { "epoch": 51.43, "learning_rate": 3.278847777382354e-05, "loss": 0.0048, "step": 214200 }, { "epoch": 51.43, "learning_rate": 3.2784265099163714e-05, "loss": 0.0032, "step": 214210 }, { "epoch": 51.44, "learning_rate": 3.278005256314457e-05, "loss": 0.0058, "step": 214220 }, { "epoch": 51.44, "learning_rate": 3.277584016580003e-05, "loss": 0.0104, "step": 214230 }, { "epoch": 51.44, "learning_rate": 3.2771627907164043e-05, "loss": 0.0092, "step": 214240 }, { "epoch": 51.44, "learning_rate": 3.276741578727052e-05, "loss": 0.0065, "step": 214250 }, { "epoch": 51.44, "learning_rate": 3.276320380615336e-05, "loss": 0.0029, "step": 214260 }, { "epoch": 51.45, "learning_rate": 3.275899196384651e-05, "loss": 0.0051, "step": 214270 }, { "epoch": 51.45, "learning_rate": 3.2754780260383856e-05, "loss": 0.0104, "step": 214280 }, { "epoch": 51.45, "learning_rate": 3.275056869579936e-05, "loss": 0.0044, "step": 214290 }, { "epoch": 51.45, "learning_rate": 3.274635727012692e-05, "loss": 0.0265, "step": 214300 }, { "epoch": 51.46, "learning_rate": 3.274214598340044e-05, "loss": 0.0027, "step": 214310 }, { "epoch": 51.46, "learning_rate": 3.273793483565383e-05, "loss": 0.0049, "step": 214320 }, { "epoch": 51.46, "learning_rate": 3.273372382692103e-05, "loss": 0.0034, "step": 214330 }, { "epoch": 51.46, "learning_rate": 3.272951295723591e-05, "loss": 0.0069, "step": 214340 }, { "epoch": 51.47, "learning_rate": 3.2725302226632436e-05, "loss": 0.0101, "step": 214350 }, { "epoch": 51.47, "learning_rate": 3.272109163514448e-05, "loss": 0.0023, "step": 214360 }, { "epoch": 51.47, "learning_rate": 3.2716881182805946e-05, "loss": 0.0119, "step": 214370 }, { "epoch": 51.47, "learning_rate": 3.271267086965076e-05, "loss": 0.0073, "step": 214380 }, { "epoch": 51.47, "learning_rate": 3.270846069571282e-05, "loss": 0.0099, "step": 214390 }, { "epoch": 51.48, "learning_rate": 3.2704250661026045e-05, "loss": 0.0066, "step": 214400 }, { "epoch": 51.48, "learning_rate": 3.270004076562433e-05, "loss": 0.0024, "step": 214410 }, { "epoch": 51.48, "learning_rate": 3.269583100954155e-05, "loss": 0.0102, "step": 214420 }, { "epoch": 51.48, "learning_rate": 3.269162139281165e-05, "loss": 0.0091, "step": 214430 }, { "epoch": 51.49, "learning_rate": 3.2687411915468525e-05, "loss": 0.0057, "step": 214440 }, { "epoch": 51.49, "learning_rate": 3.268320257754603e-05, "loss": 0.0066, "step": 214450 }, { "epoch": 51.49, "learning_rate": 3.267899337907813e-05, "loss": 0.0051, "step": 214460 }, { "epoch": 51.49, "learning_rate": 3.267478432009865e-05, "loss": 0.0062, "step": 214470 }, { "epoch": 51.5, "learning_rate": 3.2670575400641546e-05, "loss": 0.0037, "step": 214480 }, { "epoch": 51.5, "learning_rate": 3.2666366620740706e-05, "loss": 0.0084, "step": 214490 }, { "epoch": 51.5, "learning_rate": 3.266215798042998e-05, "loss": 0.0115, "step": 214500 }, { "epoch": 51.5, "learning_rate": 3.26579494797433e-05, "loss": 0.0043, "step": 214510 }, { "epoch": 51.5, "learning_rate": 3.2653741118714555e-05, "loss": 0.003, "step": 214520 }, { "epoch": 51.51, "learning_rate": 3.264953289737761e-05, "loss": 0.0094, "step": 214530 }, { "epoch": 51.51, "learning_rate": 3.2645324815766396e-05, "loss": 0.0097, "step": 214540 }, { "epoch": 51.51, "learning_rate": 3.264111687391476e-05, "loss": 0.0067, "step": 214550 }, { "epoch": 51.51, "learning_rate": 3.26369090718566e-05, "loss": 0.0077, "step": 214560 }, { "epoch": 51.52, "learning_rate": 3.2632701409625824e-05, "loss": 0.018, "step": 214570 }, { "epoch": 51.52, "learning_rate": 3.262849388725631e-05, "loss": 0.0074, "step": 214580 }, { "epoch": 51.52, "learning_rate": 3.2624286504781906e-05, "loss": 0.0174, "step": 214590 }, { "epoch": 51.52, "learning_rate": 3.2620079262236534e-05, "loss": 0.0033, "step": 214600 }, { "epoch": 51.52, "learning_rate": 3.261587215965405e-05, "loss": 0.0059, "step": 214610 }, { "epoch": 51.53, "learning_rate": 3.2611665197068364e-05, "loss": 0.0059, "step": 214620 }, { "epoch": 51.53, "learning_rate": 3.260745837451335e-05, "loss": 0.0095, "step": 214630 }, { "epoch": 51.53, "learning_rate": 3.2603251692022854e-05, "loss": 0.0046, "step": 214640 }, { "epoch": 51.53, "learning_rate": 3.259904514963078e-05, "loss": 0.0119, "step": 214650 }, { "epoch": 51.54, "learning_rate": 3.2594838747370995e-05, "loss": 0.0033, "step": 214660 }, { "epoch": 51.54, "learning_rate": 3.259063248527737e-05, "loss": 0.0076, "step": 214670 }, { "epoch": 51.54, "learning_rate": 3.258642636338382e-05, "loss": 0.0061, "step": 214680 }, { "epoch": 51.54, "learning_rate": 3.2582220381724135e-05, "loss": 0.0122, "step": 214690 }, { "epoch": 51.55, "learning_rate": 3.257801454033226e-05, "loss": 0.0087, "step": 214700 }, { "epoch": 51.55, "learning_rate": 3.257380883924203e-05, "loss": 0.0075, "step": 214710 }, { "epoch": 51.55, "learning_rate": 3.256960327848733e-05, "loss": 0.0167, "step": 214720 }, { "epoch": 51.55, "learning_rate": 3.256539785810203e-05, "loss": 0.0277, "step": 214730 }, { "epoch": 51.55, "learning_rate": 3.2561192578119984e-05, "loss": 0.0067, "step": 214740 }, { "epoch": 51.56, "learning_rate": 3.255698743857505e-05, "loss": 0.007, "step": 214750 }, { "epoch": 51.56, "learning_rate": 3.2552782439501105e-05, "loss": 0.0058, "step": 214760 }, { "epoch": 51.56, "learning_rate": 3.254857758093203e-05, "loss": 0.0053, "step": 214770 }, { "epoch": 51.56, "learning_rate": 3.254437286290165e-05, "loss": 0.0035, "step": 214780 }, { "epoch": 51.57, "learning_rate": 3.254016828544385e-05, "loss": 0.0032, "step": 214790 }, { "epoch": 51.57, "learning_rate": 3.253596384859248e-05, "loss": 0.0066, "step": 214800 }, { "epoch": 51.57, "learning_rate": 3.253175955238141e-05, "loss": 0.003, "step": 214810 }, { "epoch": 51.57, "learning_rate": 3.25275553968445e-05, "loss": 0.0038, "step": 214820 }, { "epoch": 51.58, "learning_rate": 3.2523351382015586e-05, "loss": 0.0186, "step": 214830 }, { "epoch": 51.58, "learning_rate": 3.2519147507928545e-05, "loss": 0.0039, "step": 214840 }, { "epoch": 51.58, "learning_rate": 3.251494377461721e-05, "loss": 0.0157, "step": 214850 }, { "epoch": 51.58, "learning_rate": 3.251074018211545e-05, "loss": 0.0147, "step": 214860 }, { "epoch": 51.58, "learning_rate": 3.250653673045714e-05, "loss": 0.0046, "step": 214870 }, { "epoch": 51.59, "learning_rate": 3.2502333419676066e-05, "loss": 0.0072, "step": 214880 }, { "epoch": 51.59, "learning_rate": 3.249813024980614e-05, "loss": 0.0028, "step": 214890 }, { "epoch": 51.59, "learning_rate": 3.249392722088117e-05, "loss": 0.0038, "step": 214900 }, { "epoch": 51.59, "learning_rate": 3.248972433293505e-05, "loss": 0.017, "step": 214910 }, { "epoch": 51.6, "learning_rate": 3.248552158600158e-05, "loss": 0.011, "step": 214920 }, { "epoch": 51.6, "learning_rate": 3.2481318980114616e-05, "loss": 0.0089, "step": 214930 }, { "epoch": 51.6, "learning_rate": 3.2477116515308016e-05, "loss": 0.0074, "step": 214940 }, { "epoch": 51.6, "learning_rate": 3.247291419161562e-05, "loss": 0.0082, "step": 214950 }, { "epoch": 51.6, "learning_rate": 3.246871200907127e-05, "loss": 0.0156, "step": 214960 }, { "epoch": 51.61, "learning_rate": 3.246450996770879e-05, "loss": 0.0042, "step": 214970 }, { "epoch": 51.61, "learning_rate": 3.246030806756204e-05, "loss": 0.0093, "step": 214980 }, { "epoch": 51.61, "learning_rate": 3.2456106308664836e-05, "loss": 0.01, "step": 214990 }, { "epoch": 51.61, "learning_rate": 3.2451904691051035e-05, "loss": 0.0114, "step": 215000 }, { "epoch": 51.62, "learning_rate": 3.244770321475449e-05, "loss": 0.0028, "step": 215010 }, { "epoch": 51.62, "learning_rate": 3.2443501879808994e-05, "loss": 0.0284, "step": 215020 }, { "epoch": 51.62, "learning_rate": 3.243930068624841e-05, "loss": 0.0427, "step": 215030 }, { "epoch": 51.62, "learning_rate": 3.2435099634106545e-05, "loss": 0.0022, "step": 215040 }, { "epoch": 51.63, "learning_rate": 3.243089872341726e-05, "loss": 0.0154, "step": 215050 }, { "epoch": 51.63, "learning_rate": 3.2426697954214386e-05, "loss": 0.0035, "step": 215060 }, { "epoch": 51.63, "learning_rate": 3.242249732653172e-05, "loss": 0.0055, "step": 215070 }, { "epoch": 51.63, "learning_rate": 3.2418296840403115e-05, "loss": 0.0038, "step": 215080 }, { "epoch": 51.63, "learning_rate": 3.241409649586239e-05, "loss": 0.0049, "step": 215090 }, { "epoch": 51.64, "learning_rate": 3.240989629294339e-05, "loss": 0.0049, "step": 215100 }, { "epoch": 51.64, "learning_rate": 3.240569623167991e-05, "loss": 0.0111, "step": 215110 }, { "epoch": 51.64, "learning_rate": 3.240149631210578e-05, "loss": 0.0042, "step": 215120 }, { "epoch": 51.64, "learning_rate": 3.239729653425484e-05, "loss": 0.0036, "step": 215130 }, { "epoch": 51.65, "learning_rate": 3.239309689816089e-05, "loss": 0.0059, "step": 215140 }, { "epoch": 51.65, "learning_rate": 3.23888974038578e-05, "loss": 0.0278, "step": 215150 }, { "epoch": 51.65, "learning_rate": 3.2384698051379314e-05, "loss": 0.0122, "step": 215160 }, { "epoch": 51.65, "learning_rate": 3.238049884075929e-05, "loss": 0.006, "step": 215170 }, { "epoch": 51.66, "learning_rate": 3.2376299772031535e-05, "loss": 0.0057, "step": 215180 }, { "epoch": 51.66, "learning_rate": 3.237210084522989e-05, "loss": 0.0063, "step": 215190 }, { "epoch": 51.66, "learning_rate": 3.2367902060388155e-05, "loss": 0.0104, "step": 215200 }, { "epoch": 51.66, "learning_rate": 3.236370341754011e-05, "loss": 0.0046, "step": 215210 }, { "epoch": 51.66, "learning_rate": 3.235950491671962e-05, "loss": 0.0054, "step": 215220 }, { "epoch": 51.67, "learning_rate": 3.235530655796046e-05, "loss": 0.0044, "step": 215230 }, { "epoch": 51.67, "learning_rate": 3.235110834129647e-05, "loss": 0.0111, "step": 215240 }, { "epoch": 51.67, "learning_rate": 3.2346910266761434e-05, "loss": 0.0076, "step": 215250 }, { "epoch": 51.67, "learning_rate": 3.234271233438915e-05, "loss": 0.0073, "step": 215260 }, { "epoch": 51.68, "learning_rate": 3.233851454421345e-05, "loss": 0.0031, "step": 215270 }, { "epoch": 51.68, "learning_rate": 3.233431689626812e-05, "loss": 0.005, "step": 215280 }, { "epoch": 51.68, "learning_rate": 3.2330119390587013e-05, "loss": 0.0036, "step": 215290 }, { "epoch": 51.68, "learning_rate": 3.232592202720387e-05, "loss": 0.0049, "step": 215300 }, { "epoch": 51.68, "learning_rate": 3.2321724806152506e-05, "loss": 0.0057, "step": 215310 }, { "epoch": 51.69, "learning_rate": 3.231752772746674e-05, "loss": 0.0037, "step": 215320 }, { "epoch": 51.69, "learning_rate": 3.2313330791180364e-05, "loss": 0.0073, "step": 215330 }, { "epoch": 51.69, "learning_rate": 3.230913399732719e-05, "loss": 0.0155, "step": 215340 }, { "epoch": 51.69, "learning_rate": 3.2304937345940986e-05, "loss": 0.0067, "step": 215350 }, { "epoch": 51.7, "learning_rate": 3.2300740837055567e-05, "loss": 0.0072, "step": 215360 }, { "epoch": 51.7, "learning_rate": 3.229654447070474e-05, "loss": 0.0164, "step": 215370 }, { "epoch": 51.7, "learning_rate": 3.229234824692226e-05, "loss": 0.0047, "step": 215380 }, { "epoch": 51.7, "learning_rate": 3.228815216574198e-05, "loss": 0.0039, "step": 215390 }, { "epoch": 51.71, "learning_rate": 3.2283956227197626e-05, "loss": 0.0043, "step": 215400 }, { "epoch": 51.71, "learning_rate": 3.227976043132303e-05, "loss": 0.0067, "step": 215410 }, { "epoch": 51.71, "learning_rate": 3.227556477815196e-05, "loss": 0.006, "step": 215420 }, { "epoch": 51.71, "learning_rate": 3.2271369267718233e-05, "loss": 0.0113, "step": 215430 }, { "epoch": 51.71, "learning_rate": 3.2267173900055605e-05, "loss": 0.0047, "step": 215440 }, { "epoch": 51.72, "learning_rate": 3.2262978675197866e-05, "loss": 0.0087, "step": 215450 }, { "epoch": 51.72, "learning_rate": 3.225878359317881e-05, "loss": 0.0022, "step": 215460 }, { "epoch": 51.72, "learning_rate": 3.225458865403222e-05, "loss": 0.0046, "step": 215470 }, { "epoch": 51.72, "learning_rate": 3.225039385779189e-05, "loss": 0.0065, "step": 215480 }, { "epoch": 51.73, "learning_rate": 3.224619920449158e-05, "loss": 0.0114, "step": 215490 }, { "epoch": 51.73, "learning_rate": 3.2242004694165074e-05, "loss": 0.0048, "step": 215500 }, { "epoch": 51.73, "learning_rate": 3.223781032684616e-05, "loss": 0.0057, "step": 215510 }, { "epoch": 51.73, "learning_rate": 3.223361610256861e-05, "loss": 0.0109, "step": 215520 }, { "epoch": 51.74, "learning_rate": 3.222942202136622e-05, "loss": 0.0053, "step": 215530 }, { "epoch": 51.74, "learning_rate": 3.222522808327273e-05, "loss": 0.0064, "step": 215540 }, { "epoch": 51.74, "learning_rate": 3.2221034288321926e-05, "loss": 0.0029, "step": 215550 }, { "epoch": 51.74, "learning_rate": 3.22168406365476e-05, "loss": 0.0151, "step": 215560 }, { "epoch": 51.74, "learning_rate": 3.221264712798352e-05, "loss": 0.0118, "step": 215570 }, { "epoch": 51.75, "learning_rate": 3.220845376266344e-05, "loss": 0.0083, "step": 215580 }, { "epoch": 51.75, "learning_rate": 3.220426054062112e-05, "loss": 0.0038, "step": 215590 }, { "epoch": 51.75, "learning_rate": 3.220006746189037e-05, "loss": 0.0034, "step": 215600 }, { "epoch": 51.75, "learning_rate": 3.2195874526504916e-05, "loss": 0.0055, "step": 215610 }, { "epoch": 51.76, "learning_rate": 3.219168173449857e-05, "loss": 0.0037, "step": 215620 }, { "epoch": 51.76, "learning_rate": 3.218748908590505e-05, "loss": 0.0034, "step": 215630 }, { "epoch": 51.76, "learning_rate": 3.2183296580758135e-05, "loss": 0.0079, "step": 215640 }, { "epoch": 51.76, "learning_rate": 3.217910421909159e-05, "loss": 0.0073, "step": 215650 }, { "epoch": 51.76, "learning_rate": 3.2174912000939185e-05, "loss": 0.0043, "step": 215660 }, { "epoch": 51.77, "learning_rate": 3.217071992633469e-05, "loss": 0.003, "step": 215670 }, { "epoch": 51.77, "learning_rate": 3.2166527995311836e-05, "loss": 0.0072, "step": 215680 }, { "epoch": 51.77, "learning_rate": 3.2162336207904386e-05, "loss": 0.0059, "step": 215690 }, { "epoch": 51.77, "learning_rate": 3.215814456414612e-05, "loss": 0.0046, "step": 215700 }, { "epoch": 51.78, "learning_rate": 3.215395306407076e-05, "loss": 0.0052, "step": 215710 }, { "epoch": 51.78, "learning_rate": 3.214976170771211e-05, "loss": 0.004, "step": 215720 }, { "epoch": 51.78, "learning_rate": 3.2145570495103874e-05, "loss": 0.0043, "step": 215730 }, { "epoch": 51.78, "learning_rate": 3.214137942627981e-05, "loss": 0.0059, "step": 215740 }, { "epoch": 51.79, "learning_rate": 3.213718850127371e-05, "loss": 0.0056, "step": 215750 }, { "epoch": 51.79, "learning_rate": 3.2132997720119294e-05, "loss": 0.0055, "step": 215760 }, { "epoch": 51.79, "learning_rate": 3.21288070828503e-05, "loss": 0.0034, "step": 215770 }, { "epoch": 51.79, "learning_rate": 3.212461658950049e-05, "loss": 0.0268, "step": 215780 }, { "epoch": 51.79, "learning_rate": 3.212042624010361e-05, "loss": 0.0024, "step": 215790 }, { "epoch": 51.8, "learning_rate": 3.2116236034693413e-05, "loss": 0.0071, "step": 215800 }, { "epoch": 51.8, "learning_rate": 3.211204597330365e-05, "loss": 0.0113, "step": 215810 }, { "epoch": 51.8, "learning_rate": 3.210785605596803e-05, "loss": 0.0074, "step": 215820 }, { "epoch": 51.8, "learning_rate": 3.2103666282720315e-05, "loss": 0.0097, "step": 215830 }, { "epoch": 51.81, "learning_rate": 3.209947665359426e-05, "loss": 0.016, "step": 215840 }, { "epoch": 51.81, "learning_rate": 3.209528716862357e-05, "loss": 0.0032, "step": 215850 }, { "epoch": 51.81, "learning_rate": 3.2091097827842034e-05, "loss": 0.006, "step": 215860 }, { "epoch": 51.81, "learning_rate": 3.2086908631283343e-05, "loss": 0.0162, "step": 215870 }, { "epoch": 51.82, "learning_rate": 3.2082719578981235e-05, "loss": 0.0027, "step": 215880 }, { "epoch": 51.82, "learning_rate": 3.2078530670969475e-05, "loss": 0.0077, "step": 215890 }, { "epoch": 51.82, "learning_rate": 3.20743419072818e-05, "loss": 0.0055, "step": 215900 }, { "epoch": 51.82, "learning_rate": 3.20701532879519e-05, "loss": 0.0077, "step": 215910 }, { "epoch": 51.82, "learning_rate": 3.206596481301353e-05, "loss": 0.0044, "step": 215920 }, { "epoch": 51.83, "learning_rate": 3.206177648250042e-05, "loss": 0.0043, "step": 215930 }, { "epoch": 51.83, "learning_rate": 3.205758829644631e-05, "loss": 0.0062, "step": 215940 }, { "epoch": 51.83, "learning_rate": 3.205340025488493e-05, "loss": 0.0053, "step": 215950 }, { "epoch": 51.83, "learning_rate": 3.204921235784998e-05, "loss": 0.0059, "step": 215960 }, { "epoch": 51.84, "learning_rate": 3.20450246053752e-05, "loss": 0.0053, "step": 215970 }, { "epoch": 51.84, "learning_rate": 3.204083699749431e-05, "loss": 0.009, "step": 215980 }, { "epoch": 51.84, "learning_rate": 3.2036649534241046e-05, "loss": 0.0075, "step": 215990 }, { "epoch": 51.84, "learning_rate": 3.203246221564914e-05, "loss": 0.0075, "step": 216000 }, { "epoch": 51.84, "learning_rate": 3.2028275041752285e-05, "loss": 0.0089, "step": 216010 }, { "epoch": 51.85, "learning_rate": 3.2024088012584204e-05, "loss": 0.006, "step": 216020 }, { "epoch": 51.85, "learning_rate": 3.2019901128178634e-05, "loss": 0.0024, "step": 216030 }, { "epoch": 51.85, "learning_rate": 3.201571438856926e-05, "loss": 0.0032, "step": 216040 }, { "epoch": 51.85, "learning_rate": 3.2011527793789856e-05, "loss": 0.0036, "step": 216050 }, { "epoch": 51.86, "learning_rate": 3.2007341343874085e-05, "loss": 0.0086, "step": 216060 }, { "epoch": 51.86, "learning_rate": 3.200315503885567e-05, "loss": 0.0152, "step": 216070 }, { "epoch": 51.86, "learning_rate": 3.199896887876834e-05, "loss": 0.0032, "step": 216080 }, { "epoch": 51.86, "learning_rate": 3.199478286364581e-05, "loss": 0.0027, "step": 216090 }, { "epoch": 51.87, "learning_rate": 3.199059699352176e-05, "loss": 0.004, "step": 216100 }, { "epoch": 51.87, "learning_rate": 3.198641126842993e-05, "loss": 0.0049, "step": 216110 }, { "epoch": 51.87, "learning_rate": 3.198222568840401e-05, "loss": 0.0034, "step": 216120 }, { "epoch": 51.87, "learning_rate": 3.1978040253477714e-05, "loss": 0.0059, "step": 216130 }, { "epoch": 51.87, "learning_rate": 3.197385496368476e-05, "loss": 0.0037, "step": 216140 }, { "epoch": 51.88, "learning_rate": 3.1969669819058825e-05, "loss": 0.0039, "step": 216150 }, { "epoch": 51.88, "learning_rate": 3.196548481963364e-05, "loss": 0.0019, "step": 216160 }, { "epoch": 51.88, "learning_rate": 3.196129996544288e-05, "loss": 0.0036, "step": 216170 }, { "epoch": 51.88, "learning_rate": 3.1957115256520276e-05, "loss": 0.0046, "step": 216180 }, { "epoch": 51.89, "learning_rate": 3.1952930692899526e-05, "loss": 0.0042, "step": 216190 }, { "epoch": 51.89, "learning_rate": 3.1948746274614296e-05, "loss": 0.0051, "step": 216200 }, { "epoch": 51.89, "learning_rate": 3.194456200169831e-05, "loss": 0.0069, "step": 216210 }, { "epoch": 51.89, "learning_rate": 3.1940377874185246e-05, "loss": 0.0109, "step": 216220 }, { "epoch": 51.9, "learning_rate": 3.193619389210883e-05, "loss": 0.0024, "step": 216230 }, { "epoch": 51.9, "learning_rate": 3.193201005550275e-05, "loss": 0.0059, "step": 216240 }, { "epoch": 51.9, "learning_rate": 3.192782636440067e-05, "loss": 0.005, "step": 216250 }, { "epoch": 51.9, "learning_rate": 3.1923642818836286e-05, "loss": 0.0061, "step": 216260 }, { "epoch": 51.9, "learning_rate": 3.1919459418843325e-05, "loss": 0.0052, "step": 216270 }, { "epoch": 51.91, "learning_rate": 3.1915276164455455e-05, "loss": 0.0102, "step": 216280 }, { "epoch": 51.91, "learning_rate": 3.191109305570634e-05, "loss": 0.0046, "step": 216290 }, { "epoch": 51.91, "learning_rate": 3.1906910092629705e-05, "loss": 0.0042, "step": 216300 }, { "epoch": 51.91, "learning_rate": 3.1902727275259215e-05, "loss": 0.0157, "step": 216310 }, { "epoch": 51.92, "learning_rate": 3.1898544603628563e-05, "loss": 0.0033, "step": 216320 }, { "epoch": 51.92, "learning_rate": 3.189436207777144e-05, "loss": 0.0115, "step": 216330 }, { "epoch": 51.92, "learning_rate": 3.18901796977215e-05, "loss": 0.0057, "step": 216340 }, { "epoch": 51.92, "learning_rate": 3.1885997463512466e-05, "loss": 0.0084, "step": 216350 }, { "epoch": 51.92, "learning_rate": 3.188181537517797e-05, "loss": 0.0106, "step": 216360 }, { "epoch": 51.93, "learning_rate": 3.187763343275173e-05, "loss": 0.0027, "step": 216370 }, { "epoch": 51.93, "learning_rate": 3.187345163626742e-05, "loss": 0.0089, "step": 216380 }, { "epoch": 51.93, "learning_rate": 3.186926998575869e-05, "loss": 0.011, "step": 216390 }, { "epoch": 51.93, "learning_rate": 3.186508848125923e-05, "loss": 0.005, "step": 216400 }, { "epoch": 51.94, "learning_rate": 3.186090712280272e-05, "loss": 0.0089, "step": 216410 }, { "epoch": 51.94, "learning_rate": 3.1856725910422844e-05, "loss": 0.0032, "step": 216420 }, { "epoch": 51.94, "learning_rate": 3.1852544844153246e-05, "loss": 0.0132, "step": 216430 }, { "epoch": 51.94, "learning_rate": 3.1848363924027616e-05, "loss": 0.005, "step": 216440 }, { "epoch": 51.95, "learning_rate": 3.1844183150079604e-05, "loss": 0.0034, "step": 216450 }, { "epoch": 51.95, "learning_rate": 3.18400025223429e-05, "loss": 0.004, "step": 216460 }, { "epoch": 51.95, "learning_rate": 3.183582204085118e-05, "loss": 0.0127, "step": 216470 }, { "epoch": 52.0, "learning_rate": 3.183164170563806e-05, "loss": 0.0037, "step": 216480 }, { "epoch": 52.0, "learning_rate": 3.1827461516737254e-05, "loss": 0.0057, "step": 216490 }, { "epoch": 52.01, "learning_rate": 3.182328147418241e-05, "loss": 0.0042, "step": 216500 }, { "epoch": 52.01, "learning_rate": 3.181910157800718e-05, "loss": 0.0025, "step": 216510 }, { "epoch": 52.01, "learning_rate": 3.181492182824526e-05, "loss": 0.0041, "step": 216520 }, { "epoch": 52.01, "learning_rate": 3.181074222493026e-05, "loss": 0.0036, "step": 216530 }, { "epoch": 52.01, "learning_rate": 3.180656276809588e-05, "loss": 0.0063, "step": 216540 }, { "epoch": 52.02, "learning_rate": 3.1802383457775744e-05, "loss": 0.0023, "step": 216550 }, { "epoch": 52.02, "learning_rate": 3.179820429400354e-05, "loss": 0.0153, "step": 216560 }, { "epoch": 52.02, "learning_rate": 3.179402527681292e-05, "loss": 0.0074, "step": 216570 }, { "epoch": 52.02, "learning_rate": 3.17898464062375e-05, "loss": 0.0208, "step": 216580 }, { "epoch": 52.03, "learning_rate": 3.1785667682310985e-05, "loss": 0.0056, "step": 216590 }, { "epoch": 52.03, "learning_rate": 3.178148910506698e-05, "loss": 0.0092, "step": 216600 }, { "epoch": 52.03, "learning_rate": 3.1777310674539186e-05, "loss": 0.0029, "step": 216610 }, { "epoch": 52.03, "learning_rate": 3.1773132390761205e-05, "loss": 0.0033, "step": 216620 }, { "epoch": 52.04, "learning_rate": 3.176895425376671e-05, "loss": 0.0092, "step": 216630 }, { "epoch": 52.04, "learning_rate": 3.176477626358935e-05, "loss": 0.0083, "step": 216640 }, { "epoch": 52.04, "learning_rate": 3.1760598420262746e-05, "loss": 0.0041, "step": 216650 }, { "epoch": 52.04, "learning_rate": 3.175642072382059e-05, "loss": 0.0027, "step": 216660 }, { "epoch": 52.04, "learning_rate": 3.175224317429648e-05, "loss": 0.0023, "step": 216670 }, { "epoch": 52.05, "learning_rate": 3.1748065771724074e-05, "loss": 0.0067, "step": 216680 }, { "epoch": 52.05, "learning_rate": 3.1743888516137006e-05, "loss": 0.0044, "step": 216690 }, { "epoch": 52.05, "learning_rate": 3.173971140756893e-05, "loss": 0.0061, "step": 216700 }, { "epoch": 52.05, "learning_rate": 3.17355344460535e-05, "loss": 0.007, "step": 216710 }, { "epoch": 52.06, "learning_rate": 3.1731357631624305e-05, "loss": 0.0025, "step": 216720 }, { "epoch": 52.06, "learning_rate": 3.172718096431502e-05, "loss": 0.0044, "step": 216730 }, { "epoch": 52.06, "learning_rate": 3.172300444415927e-05, "loss": 0.0082, "step": 216740 }, { "epoch": 52.06, "learning_rate": 3.1718828071190695e-05, "loss": 0.0074, "step": 216750 }, { "epoch": 52.06, "learning_rate": 3.171465184544291e-05, "loss": 0.0053, "step": 216760 }, { "epoch": 52.07, "learning_rate": 3.171047576694955e-05, "loss": 0.0028, "step": 216770 }, { "epoch": 52.07, "learning_rate": 3.170629983574427e-05, "loss": 0.0037, "step": 216780 }, { "epoch": 52.07, "learning_rate": 3.170212405186067e-05, "loss": 0.0084, "step": 216790 }, { "epoch": 52.07, "learning_rate": 3.169794841533241e-05, "loss": 0.0055, "step": 216800 }, { "epoch": 52.08, "learning_rate": 3.169377292619309e-05, "loss": 0.0027, "step": 216810 }, { "epoch": 52.08, "learning_rate": 3.1689597584476336e-05, "loss": 0.0049, "step": 216820 }, { "epoch": 52.08, "learning_rate": 3.1685422390215794e-05, "loss": 0.0093, "step": 216830 }, { "epoch": 52.08, "learning_rate": 3.168124734344505e-05, "loss": 0.0033, "step": 216840 }, { "epoch": 52.09, "learning_rate": 3.1677072444197785e-05, "loss": 0.0042, "step": 216850 }, { "epoch": 52.09, "learning_rate": 3.1672897692507566e-05, "loss": 0.0052, "step": 216860 }, { "epoch": 52.09, "learning_rate": 3.166872308840803e-05, "loss": 0.0075, "step": 216870 }, { "epoch": 52.09, "learning_rate": 3.16645486319328e-05, "loss": 0.004, "step": 216880 }, { "epoch": 52.09, "learning_rate": 3.166037432311549e-05, "loss": 0.0026, "step": 216890 }, { "epoch": 52.1, "learning_rate": 3.1656200161989735e-05, "loss": 0.0034, "step": 216900 }, { "epoch": 52.1, "learning_rate": 3.165202614858911e-05, "loss": 0.0045, "step": 216910 }, { "epoch": 52.1, "learning_rate": 3.164785228294726e-05, "loss": 0.003, "step": 216920 }, { "epoch": 52.1, "learning_rate": 3.1643678565097776e-05, "loss": 0.0055, "step": 216930 }, { "epoch": 52.11, "learning_rate": 3.163950499507431e-05, "loss": 0.0041, "step": 216940 }, { "epoch": 52.11, "learning_rate": 3.163533157291043e-05, "loss": 0.0062, "step": 216950 }, { "epoch": 52.11, "learning_rate": 3.163115829863975e-05, "loss": 0.0082, "step": 216960 }, { "epoch": 52.11, "learning_rate": 3.16269851722959e-05, "loss": 0.0151, "step": 216970 }, { "epoch": 52.12, "learning_rate": 3.162281219391246e-05, "loss": 0.0052, "step": 216980 }, { "epoch": 52.12, "learning_rate": 3.1618639363523084e-05, "loss": 0.0174, "step": 216990 }, { "epoch": 52.12, "learning_rate": 3.161446668116132e-05, "loss": 0.0056, "step": 217000 }, { "epoch": 52.12, "learning_rate": 3.161029414686078e-05, "loss": 0.004, "step": 217010 }, { "epoch": 52.12, "learning_rate": 3.16061217606551e-05, "loss": 0.006, "step": 217020 }, { "epoch": 52.13, "learning_rate": 3.160194952257786e-05, "loss": 0.0051, "step": 217030 }, { "epoch": 52.13, "learning_rate": 3.159777743266267e-05, "loss": 0.0043, "step": 217040 }, { "epoch": 52.13, "learning_rate": 3.1593605490943104e-05, "loss": 0.0034, "step": 217050 }, { "epoch": 52.13, "learning_rate": 3.1589433697452766e-05, "loss": 0.0038, "step": 217060 }, { "epoch": 52.14, "learning_rate": 3.158526205222527e-05, "loss": 0.0045, "step": 217070 }, { "epoch": 52.14, "learning_rate": 3.158109055529422e-05, "loss": 0.0102, "step": 217080 }, { "epoch": 52.14, "learning_rate": 3.157691920669318e-05, "loss": 0.0091, "step": 217090 }, { "epoch": 52.14, "learning_rate": 3.1572748006455734e-05, "loss": 0.0022, "step": 217100 }, { "epoch": 52.14, "learning_rate": 3.1568576954615505e-05, "loss": 0.01, "step": 217110 }, { "epoch": 52.15, "learning_rate": 3.1564406051206064e-05, "loss": 0.0037, "step": 217120 }, { "epoch": 52.15, "learning_rate": 3.156023529626102e-05, "loss": 0.0054, "step": 217130 }, { "epoch": 52.15, "learning_rate": 3.1556064689813945e-05, "loss": 0.004, "step": 217140 }, { "epoch": 52.15, "learning_rate": 3.155189423189841e-05, "loss": 0.0032, "step": 217150 }, { "epoch": 52.16, "learning_rate": 3.1547723922548034e-05, "loss": 0.0117, "step": 217160 }, { "epoch": 52.16, "learning_rate": 3.1543553761796366e-05, "loss": 0.0036, "step": 217170 }, { "epoch": 52.16, "learning_rate": 3.153938374967704e-05, "loss": 0.0051, "step": 217180 }, { "epoch": 52.16, "learning_rate": 3.153521388622359e-05, "loss": 0.0048, "step": 217190 }, { "epoch": 52.17, "learning_rate": 3.153104417146959e-05, "loss": 0.0046, "step": 217200 }, { "epoch": 52.17, "learning_rate": 3.152687460544866e-05, "loss": 0.0044, "step": 217210 }, { "epoch": 52.17, "learning_rate": 3.152270518819436e-05, "loss": 0.0038, "step": 217220 }, { "epoch": 52.17, "learning_rate": 3.151853591974028e-05, "loss": 0.009, "step": 217230 }, { "epoch": 52.17, "learning_rate": 3.1514366800119964e-05, "loss": 0.0038, "step": 217240 }, { "epoch": 52.18, "learning_rate": 3.151019782936699e-05, "loss": 0.0058, "step": 217250 }, { "epoch": 52.18, "learning_rate": 3.150602900751497e-05, "loss": 0.0039, "step": 217260 }, { "epoch": 52.18, "learning_rate": 3.1501860334597457e-05, "loss": 0.0041, "step": 217270 }, { "epoch": 52.18, "learning_rate": 3.1497691810647993e-05, "loss": 0.0077, "step": 217280 }, { "epoch": 52.19, "learning_rate": 3.149352343570019e-05, "loss": 0.0064, "step": 217290 }, { "epoch": 52.19, "learning_rate": 3.148935520978757e-05, "loss": 0.0053, "step": 217300 }, { "epoch": 52.19, "learning_rate": 3.148518713294376e-05, "loss": 0.0029, "step": 217310 }, { "epoch": 52.19, "learning_rate": 3.148101920520229e-05, "loss": 0.0085, "step": 217320 }, { "epoch": 52.2, "learning_rate": 3.147685142659672e-05, "loss": 0.0056, "step": 217330 }, { "epoch": 52.2, "learning_rate": 3.147268379716062e-05, "loss": 0.0053, "step": 217340 }, { "epoch": 52.2, "learning_rate": 3.146851631692756e-05, "loss": 0.005, "step": 217350 }, { "epoch": 52.2, "learning_rate": 3.1464348985931085e-05, "loss": 0.0052, "step": 217360 }, { "epoch": 52.2, "learning_rate": 3.146018180420479e-05, "loss": 0.0027, "step": 217370 }, { "epoch": 52.21, "learning_rate": 3.14560147717822e-05, "loss": 0.009, "step": 217380 }, { "epoch": 52.21, "learning_rate": 3.145184788869687e-05, "loss": 0.0051, "step": 217390 }, { "epoch": 52.21, "learning_rate": 3.1447681154982386e-05, "loss": 0.0027, "step": 217400 }, { "epoch": 52.21, "learning_rate": 3.14435145706723e-05, "loss": 0.0041, "step": 217410 }, { "epoch": 52.22, "learning_rate": 3.143934813580012e-05, "loss": 0.0034, "step": 217420 }, { "epoch": 52.22, "learning_rate": 3.143518185039945e-05, "loss": 0.0062, "step": 217430 }, { "epoch": 52.22, "learning_rate": 3.1431015714503806e-05, "loss": 0.0046, "step": 217440 }, { "epoch": 52.22, "learning_rate": 3.142684972814677e-05, "loss": 0.006, "step": 217450 }, { "epoch": 52.22, "learning_rate": 3.1422683891361895e-05, "loss": 0.0021, "step": 217460 }, { "epoch": 52.23, "learning_rate": 3.1418518204182686e-05, "loss": 0.0058, "step": 217470 }, { "epoch": 52.23, "learning_rate": 3.141435266664272e-05, "loss": 0.0064, "step": 217480 }, { "epoch": 52.23, "learning_rate": 3.1410187278775535e-05, "loss": 0.0267, "step": 217490 }, { "epoch": 52.23, "learning_rate": 3.1406022040614685e-05, "loss": 0.0087, "step": 217500 }, { "epoch": 52.24, "learning_rate": 3.140185695219372e-05, "loss": 0.0027, "step": 217510 }, { "epoch": 52.24, "learning_rate": 3.1397692013546155e-05, "loss": 0.0054, "step": 217520 }, { "epoch": 52.24, "learning_rate": 3.139352722470553e-05, "loss": 0.0053, "step": 217530 }, { "epoch": 52.24, "learning_rate": 3.138936258570542e-05, "loss": 0.0071, "step": 217540 }, { "epoch": 52.25, "learning_rate": 3.138519809657933e-05, "loss": 0.0047, "step": 217550 }, { "epoch": 52.25, "learning_rate": 3.138103375736082e-05, "loss": 0.0027, "step": 217560 }, { "epoch": 52.25, "learning_rate": 3.137686956808342e-05, "loss": 0.0091, "step": 217570 }, { "epoch": 52.25, "learning_rate": 3.137270552878064e-05, "loss": 0.0028, "step": 217580 }, { "epoch": 52.25, "learning_rate": 3.136854163948605e-05, "loss": 0.0056, "step": 217590 }, { "epoch": 52.26, "learning_rate": 3.136437790023317e-05, "loss": 0.0026, "step": 217600 }, { "epoch": 52.26, "learning_rate": 3.1360214311055506e-05, "loss": 0.0095, "step": 217610 }, { "epoch": 52.26, "learning_rate": 3.135605087198663e-05, "loss": 0.0072, "step": 217620 }, { "epoch": 52.26, "learning_rate": 3.1351887583060033e-05, "loss": 0.0036, "step": 217630 }, { "epoch": 52.27, "learning_rate": 3.1347724444309266e-05, "loss": 0.0039, "step": 217640 }, { "epoch": 52.27, "learning_rate": 3.1343561455767866e-05, "loss": 0.0051, "step": 217650 }, { "epoch": 52.27, "learning_rate": 3.133939861746932e-05, "loss": 0.004, "step": 217660 }, { "epoch": 52.27, "learning_rate": 3.1335235929447186e-05, "loss": 0.0049, "step": 217670 }, { "epoch": 52.28, "learning_rate": 3.133107339173496e-05, "loss": 0.0083, "step": 217680 }, { "epoch": 52.28, "learning_rate": 3.132691100436619e-05, "loss": 0.0047, "step": 217690 }, { "epoch": 52.28, "learning_rate": 3.1322748767374386e-05, "loss": 0.0041, "step": 217700 }, { "epoch": 52.28, "learning_rate": 3.131858668079305e-05, "loss": 0.0082, "step": 217710 }, { "epoch": 52.28, "learning_rate": 3.131442474465573e-05, "loss": 0.0067, "step": 217720 }, { "epoch": 52.29, "learning_rate": 3.131026295899592e-05, "loss": 0.0041, "step": 217730 }, { "epoch": 52.29, "learning_rate": 3.130610132384716e-05, "loss": 0.0096, "step": 217740 }, { "epoch": 52.29, "learning_rate": 3.130193983924292e-05, "loss": 0.0102, "step": 217750 }, { "epoch": 52.29, "learning_rate": 3.1297778505216756e-05, "loss": 0.0051, "step": 217760 }, { "epoch": 52.3, "learning_rate": 3.129361732180215e-05, "loss": 0.0047, "step": 217770 }, { "epoch": 52.3, "learning_rate": 3.128945628903264e-05, "loss": 0.0049, "step": 217780 }, { "epoch": 52.3, "learning_rate": 3.128529540694172e-05, "loss": 0.0072, "step": 217790 }, { "epoch": 52.3, "learning_rate": 3.128113467556289e-05, "loss": 0.0043, "step": 217800 }, { "epoch": 52.3, "learning_rate": 3.1276974094929674e-05, "loss": 0.0086, "step": 217810 }, { "epoch": 52.31, "learning_rate": 3.1272813665075564e-05, "loss": 0.0112, "step": 217820 }, { "epoch": 52.31, "learning_rate": 3.126865338603407e-05, "loss": 0.003, "step": 217830 }, { "epoch": 52.31, "learning_rate": 3.126449325783872e-05, "loss": 0.0021, "step": 217840 }, { "epoch": 52.31, "learning_rate": 3.126033328052296e-05, "loss": 0.0063, "step": 217850 }, { "epoch": 52.32, "learning_rate": 3.125617345412034e-05, "loss": 0.0032, "step": 217860 }, { "epoch": 52.32, "learning_rate": 3.125201377866434e-05, "loss": 0.0041, "step": 217870 }, { "epoch": 52.32, "learning_rate": 3.124785425418846e-05, "loss": 0.0036, "step": 217880 }, { "epoch": 52.32, "learning_rate": 3.1243694880726214e-05, "loss": 0.0054, "step": 217890 }, { "epoch": 52.33, "learning_rate": 3.123953565831106e-05, "loss": 0.0022, "step": 217900 }, { "epoch": 52.33, "learning_rate": 3.123537658697653e-05, "loss": 0.0035, "step": 217910 }, { "epoch": 52.33, "learning_rate": 3.1231217666756086e-05, "loss": 0.0115, "step": 217920 }, { "epoch": 52.33, "learning_rate": 3.122705889768327e-05, "loss": 0.0024, "step": 217930 }, { "epoch": 52.33, "learning_rate": 3.122290027979151e-05, "loss": 0.0094, "step": 217940 }, { "epoch": 52.34, "learning_rate": 3.121874181311434e-05, "loss": 0.0102, "step": 217950 }, { "epoch": 52.34, "learning_rate": 3.1214583497685224e-05, "loss": 0.0164, "step": 217960 }, { "epoch": 52.34, "learning_rate": 3.121042533353767e-05, "loss": 0.0057, "step": 217970 }, { "epoch": 52.34, "learning_rate": 3.120626732070516e-05, "loss": 0.0113, "step": 217980 }, { "epoch": 52.35, "learning_rate": 3.1202109459221164e-05, "loss": 0.0055, "step": 217990 }, { "epoch": 52.35, "learning_rate": 3.119795174911917e-05, "loss": 0.0041, "step": 218000 }, { "epoch": 52.35, "learning_rate": 3.119379419043267e-05, "loss": 0.0037, "step": 218010 }, { "epoch": 52.35, "learning_rate": 3.118963678319515e-05, "loss": 0.0033, "step": 218020 }, { "epoch": 52.36, "learning_rate": 3.118547952744009e-05, "loss": 0.0037, "step": 218030 }, { "epoch": 52.36, "learning_rate": 3.118132242320094e-05, "loss": 0.004, "step": 218040 }, { "epoch": 52.36, "learning_rate": 3.117716547051121e-05, "loss": 0.003, "step": 218050 }, { "epoch": 52.36, "learning_rate": 3.1173008669404354e-05, "loss": 0.0039, "step": 218060 }, { "epoch": 52.36, "learning_rate": 3.116885201991388e-05, "loss": 0.0029, "step": 218070 }, { "epoch": 52.37, "learning_rate": 3.1164695522073226e-05, "loss": 0.0061, "step": 218080 }, { "epoch": 52.37, "learning_rate": 3.1160539175915876e-05, "loss": 0.0054, "step": 218090 }, { "epoch": 52.37, "learning_rate": 3.115638298147531e-05, "loss": 0.0033, "step": 218100 }, { "epoch": 52.37, "learning_rate": 3.115222693878499e-05, "loss": 0.0066, "step": 218110 }, { "epoch": 52.38, "learning_rate": 3.11480710478784e-05, "loss": 0.0023, "step": 218120 }, { "epoch": 52.38, "learning_rate": 3.114391530878899e-05, "loss": 0.0033, "step": 218130 }, { "epoch": 52.38, "learning_rate": 3.1139759721550224e-05, "loss": 0.0048, "step": 218140 }, { "epoch": 52.38, "learning_rate": 3.1135604286195585e-05, "loss": 0.0067, "step": 218150 }, { "epoch": 52.38, "learning_rate": 3.1131449002758514e-05, "loss": 0.0045, "step": 218160 }, { "epoch": 52.39, "learning_rate": 3.112729387127253e-05, "loss": 0.0027, "step": 218170 }, { "epoch": 52.39, "learning_rate": 3.112313889177102e-05, "loss": 0.006, "step": 218180 }, { "epoch": 52.39, "learning_rate": 3.1118984064287484e-05, "loss": 0.0078, "step": 218190 }, { "epoch": 52.39, "learning_rate": 3.111482938885537e-05, "loss": 0.0049, "step": 218200 }, { "epoch": 52.4, "learning_rate": 3.111067486550816e-05, "loss": 0.0054, "step": 218210 }, { "epoch": 52.4, "learning_rate": 3.110652049427929e-05, "loss": 0.0055, "step": 218220 }, { "epoch": 52.4, "learning_rate": 3.1102366275202207e-05, "loss": 0.0026, "step": 218230 }, { "epoch": 52.4, "learning_rate": 3.1098212208310385e-05, "loss": 0.0051, "step": 218240 }, { "epoch": 52.41, "learning_rate": 3.1094058293637255e-05, "loss": 0.0029, "step": 218250 }, { "epoch": 52.41, "learning_rate": 3.1089904531216306e-05, "loss": 0.0053, "step": 218260 }, { "epoch": 52.41, "learning_rate": 3.1085750921080964e-05, "loss": 0.0081, "step": 218270 }, { "epoch": 52.41, "learning_rate": 3.108159746326467e-05, "loss": 0.0032, "step": 218280 }, { "epoch": 52.41, "learning_rate": 3.1077444157800885e-05, "loss": 0.0081, "step": 218290 }, { "epoch": 52.42, "learning_rate": 3.107329100472305e-05, "loss": 0.0042, "step": 218300 }, { "epoch": 52.42, "learning_rate": 3.1069138004064634e-05, "loss": 0.0033, "step": 218310 }, { "epoch": 52.42, "learning_rate": 3.106498515585905e-05, "loss": 0.0055, "step": 218320 }, { "epoch": 52.42, "learning_rate": 3.106083246013975e-05, "loss": 0.0026, "step": 218330 }, { "epoch": 52.43, "learning_rate": 3.105667991694019e-05, "loss": 0.0028, "step": 218340 }, { "epoch": 52.43, "learning_rate": 3.1052527526293786e-05, "loss": 0.0017, "step": 218350 }, { "epoch": 52.43, "learning_rate": 3.104837528823402e-05, "loss": 0.0029, "step": 218360 }, { "epoch": 52.43, "learning_rate": 3.104422320279429e-05, "loss": 0.0088, "step": 218370 }, { "epoch": 52.44, "learning_rate": 3.104007127000805e-05, "loss": 0.0036, "step": 218380 }, { "epoch": 52.44, "learning_rate": 3.103591948990873e-05, "loss": 0.0046, "step": 218390 }, { "epoch": 52.44, "learning_rate": 3.103176786252978e-05, "loss": 0.009, "step": 218400 }, { "epoch": 52.44, "learning_rate": 3.102761638790461e-05, "loss": 0.006, "step": 218410 }, { "epoch": 52.44, "learning_rate": 3.102346506606666e-05, "loss": 0.0028, "step": 218420 }, { "epoch": 52.45, "learning_rate": 3.101931389704938e-05, "loss": 0.0274, "step": 218430 }, { "epoch": 52.45, "learning_rate": 3.1015162880886174e-05, "loss": 0.0042, "step": 218440 }, { "epoch": 52.45, "learning_rate": 3.10110120176105e-05, "loss": 0.0031, "step": 218450 }, { "epoch": 52.45, "learning_rate": 3.100686130725575e-05, "loss": 0.0075, "step": 218460 }, { "epoch": 52.46, "learning_rate": 3.1002710749855366e-05, "loss": 0.0046, "step": 218470 }, { "epoch": 52.46, "learning_rate": 3.0998560345442786e-05, "loss": 0.0023, "step": 218480 }, { "epoch": 52.46, "learning_rate": 3.0994410094051404e-05, "loss": 0.0023, "step": 218490 }, { "epoch": 52.46, "learning_rate": 3.0990259995714695e-05, "loss": 0.0019, "step": 218500 }, { "epoch": 52.46, "learning_rate": 3.0986110050466025e-05, "loss": 0.0046, "step": 218510 }, { "epoch": 52.47, "learning_rate": 3.0981960258338835e-05, "loss": 0.003, "step": 218520 }, { "epoch": 52.47, "learning_rate": 3.097781061936655e-05, "loss": 0.0022, "step": 218530 }, { "epoch": 52.47, "learning_rate": 3.097366113358257e-05, "loss": 0.0084, "step": 218540 }, { "epoch": 52.47, "learning_rate": 3.096951180102035e-05, "loss": 0.0029, "step": 218550 }, { "epoch": 52.48, "learning_rate": 3.096536262171326e-05, "loss": 0.0022, "step": 218560 }, { "epoch": 52.48, "learning_rate": 3.0961213595694724e-05, "loss": 0.0049, "step": 218570 }, { "epoch": 52.48, "learning_rate": 3.095706472299818e-05, "loss": 0.0022, "step": 218580 }, { "epoch": 52.48, "learning_rate": 3.095291600365703e-05, "loss": 0.0051, "step": 218590 }, { "epoch": 52.49, "learning_rate": 3.094876743770467e-05, "loss": 0.0088, "step": 218600 }, { "epoch": 52.49, "learning_rate": 3.0944619025174504e-05, "loss": 0.0084, "step": 218610 }, { "epoch": 52.49, "learning_rate": 3.094047076609996e-05, "loss": 0.0035, "step": 218620 }, { "epoch": 52.49, "learning_rate": 3.0936322660514426e-05, "loss": 0.0074, "step": 218630 }, { "epoch": 52.49, "learning_rate": 3.0932174708451334e-05, "loss": 0.0104, "step": 218640 }, { "epoch": 52.5, "learning_rate": 3.092802690994407e-05, "loss": 0.0036, "step": 218650 }, { "epoch": 52.5, "learning_rate": 3.0923879265026024e-05, "loss": 0.0027, "step": 218660 }, { "epoch": 52.5, "learning_rate": 3.091973177373062e-05, "loss": 0.0023, "step": 218670 }, { "epoch": 52.5, "learning_rate": 3.0915584436091236e-05, "loss": 0.0046, "step": 218680 }, { "epoch": 52.51, "learning_rate": 3.091143725214132e-05, "loss": 0.0051, "step": 218690 }, { "epoch": 52.51, "learning_rate": 3.090729022191422e-05, "loss": 0.0178, "step": 218700 }, { "epoch": 52.51, "learning_rate": 3.090314334544333e-05, "loss": 0.002, "step": 218710 }, { "epoch": 52.51, "learning_rate": 3.0898996622762075e-05, "loss": 0.0048, "step": 218720 }, { "epoch": 52.52, "learning_rate": 3.089485005390385e-05, "loss": 0.0064, "step": 218730 }, { "epoch": 52.52, "learning_rate": 3.089070363890202e-05, "loss": 0.0028, "step": 218740 }, { "epoch": 52.52, "learning_rate": 3.0886557377789995e-05, "loss": 0.0033, "step": 218750 }, { "epoch": 52.52, "learning_rate": 3.088241127060115e-05, "loss": 0.0091, "step": 218760 }, { "epoch": 52.52, "learning_rate": 3.08782653173689e-05, "loss": 0.0063, "step": 218770 }, { "epoch": 52.53, "learning_rate": 3.0874119518126634e-05, "loss": 0.0069, "step": 218780 }, { "epoch": 52.53, "learning_rate": 3.08699738729077e-05, "loss": 0.0036, "step": 218790 }, { "epoch": 52.53, "learning_rate": 3.086582838174551e-05, "loss": 0.0285, "step": 218800 }, { "epoch": 52.53, "learning_rate": 3.086168304467346e-05, "loss": 0.0058, "step": 218810 }, { "epoch": 52.54, "learning_rate": 3.08575378617249e-05, "loss": 0.0162, "step": 218820 }, { "epoch": 52.54, "learning_rate": 3.0853392832933254e-05, "loss": 0.0048, "step": 218830 }, { "epoch": 52.54, "learning_rate": 3.084924795833187e-05, "loss": 0.0057, "step": 218840 }, { "epoch": 52.54, "learning_rate": 3.084510323795412e-05, "loss": 0.0024, "step": 218850 }, { "epoch": 52.54, "learning_rate": 3.084095867183341e-05, "loss": 0.0031, "step": 218860 }, { "epoch": 52.55, "learning_rate": 3.08368142600031e-05, "loss": 0.0042, "step": 218870 }, { "epoch": 52.55, "learning_rate": 3.0832670002496584e-05, "loss": 0.0053, "step": 218880 }, { "epoch": 52.55, "learning_rate": 3.082852589934721e-05, "loss": 0.0064, "step": 218890 }, { "epoch": 52.55, "learning_rate": 3.082438195058837e-05, "loss": 0.0043, "step": 218900 }, { "epoch": 52.56, "learning_rate": 3.0820238156253426e-05, "loss": 0.014, "step": 218910 }, { "epoch": 52.56, "learning_rate": 3.081609451637576e-05, "loss": 0.0021, "step": 218920 }, { "epoch": 52.56, "learning_rate": 3.0811951030988716e-05, "loss": 0.0131, "step": 218930 }, { "epoch": 52.56, "learning_rate": 3.080780770012569e-05, "loss": 0.0114, "step": 218940 }, { "epoch": 52.57, "learning_rate": 3.080366452382003e-05, "loss": 0.0136, "step": 218950 }, { "epoch": 52.57, "learning_rate": 3.0799521502105125e-05, "loss": 0.0063, "step": 218960 }, { "epoch": 52.57, "learning_rate": 3.0795378635014326e-05, "loss": 0.0089, "step": 218970 }, { "epoch": 52.57, "learning_rate": 3.0791235922580975e-05, "loss": 0.0057, "step": 218980 }, { "epoch": 52.57, "learning_rate": 3.078709336483846e-05, "loss": 0.0056, "step": 218990 }, { "epoch": 52.58, "learning_rate": 3.078295096182013e-05, "loss": 0.0039, "step": 219000 }, { "epoch": 52.58, "learning_rate": 3.077880871355936e-05, "loss": 0.0045, "step": 219010 }, { "epoch": 52.58, "learning_rate": 3.077466662008951e-05, "loss": 0.0075, "step": 219020 }, { "epoch": 52.58, "learning_rate": 3.07705246814439e-05, "loss": 0.0097, "step": 219030 }, { "epoch": 52.59, "learning_rate": 3.076638289765591e-05, "loss": 0.0047, "step": 219040 }, { "epoch": 52.59, "learning_rate": 3.0762241268758906e-05, "loss": 0.0056, "step": 219050 }, { "epoch": 52.59, "learning_rate": 3.075809979478623e-05, "loss": 0.0064, "step": 219060 }, { "epoch": 52.59, "learning_rate": 3.0753958475771226e-05, "loss": 0.0043, "step": 219070 }, { "epoch": 52.6, "learning_rate": 3.074981731174725e-05, "loss": 0.0128, "step": 219080 }, { "epoch": 52.6, "learning_rate": 3.074567630274765e-05, "loss": 0.004, "step": 219090 }, { "epoch": 52.6, "learning_rate": 3.074153544880578e-05, "loss": 0.008, "step": 219100 }, { "epoch": 52.6, "learning_rate": 3.0737394749955e-05, "loss": 0.0029, "step": 219110 }, { "epoch": 52.6, "learning_rate": 3.0733254206228616e-05, "loss": 0.0053, "step": 219120 }, { "epoch": 52.61, "learning_rate": 3.0729113817660005e-05, "loss": 0.0018, "step": 219130 }, { "epoch": 52.61, "learning_rate": 3.0724973584282494e-05, "loss": 0.0046, "step": 219140 }, { "epoch": 52.61, "learning_rate": 3.072083350612944e-05, "loss": 0.0036, "step": 219150 }, { "epoch": 52.61, "learning_rate": 3.071669358323419e-05, "loss": 0.0082, "step": 219160 }, { "epoch": 52.62, "learning_rate": 3.071255381563004e-05, "loss": 0.005, "step": 219170 }, { "epoch": 52.62, "learning_rate": 3.0708414203350375e-05, "loss": 0.0046, "step": 219180 }, { "epoch": 52.62, "learning_rate": 3.0704274746428505e-05, "loss": 0.0068, "step": 219190 }, { "epoch": 52.62, "learning_rate": 3.070013544489778e-05, "loss": 0.0045, "step": 219200 }, { "epoch": 52.62, "learning_rate": 3.069599629879154e-05, "loss": 0.0069, "step": 219210 }, { "epoch": 52.63, "learning_rate": 3.069185730814308e-05, "loss": 0.0047, "step": 219220 }, { "epoch": 52.63, "learning_rate": 3.068771847298577e-05, "loss": 0.003, "step": 219230 }, { "epoch": 52.63, "learning_rate": 3.0683579793352934e-05, "loss": 0.0099, "step": 219240 }, { "epoch": 52.63, "learning_rate": 3.067944126927791e-05, "loss": 0.0022, "step": 219250 }, { "epoch": 52.64, "learning_rate": 3.067530290079399e-05, "loss": 0.0039, "step": 219260 }, { "epoch": 52.64, "learning_rate": 3.067116468793453e-05, "loss": 0.004, "step": 219270 }, { "epoch": 52.64, "learning_rate": 3.066702663073284e-05, "loss": 0.0048, "step": 219280 }, { "epoch": 52.64, "learning_rate": 3.066288872922227e-05, "loss": 0.0028, "step": 219290 }, { "epoch": 52.65, "learning_rate": 3.065875098343613e-05, "loss": 0.005, "step": 219300 }, { "epoch": 52.65, "learning_rate": 3.065461339340773e-05, "loss": 0.0085, "step": 219310 }, { "epoch": 52.65, "learning_rate": 3.065047595917039e-05, "loss": 0.0116, "step": 219320 }, { "epoch": 52.65, "learning_rate": 3.064633868075745e-05, "loss": 0.0051, "step": 219330 }, { "epoch": 52.65, "learning_rate": 3.064220155820221e-05, "loss": 0.0044, "step": 219340 }, { "epoch": 52.66, "learning_rate": 3.0638064591538004e-05, "loss": 0.0026, "step": 219350 }, { "epoch": 52.66, "learning_rate": 3.063392778079812e-05, "loss": 0.0031, "step": 219360 }, { "epoch": 52.66, "learning_rate": 3.062979112601591e-05, "loss": 0.0069, "step": 219370 }, { "epoch": 52.66, "learning_rate": 3.062565462722464e-05, "loss": 0.0035, "step": 219380 }, { "epoch": 52.67, "learning_rate": 3.062151828445768e-05, "loss": 0.0043, "step": 219390 }, { "epoch": 52.67, "learning_rate": 3.061738209774829e-05, "loss": 0.0045, "step": 219400 }, { "epoch": 52.67, "learning_rate": 3.06132460671298e-05, "loss": 0.0053, "step": 219410 }, { "epoch": 52.67, "learning_rate": 3.060911019263552e-05, "loss": 0.0094, "step": 219420 }, { "epoch": 52.68, "learning_rate": 3.060497447429873e-05, "loss": 0.0027, "step": 219430 }, { "epoch": 52.68, "learning_rate": 3.06008389121528e-05, "loss": 0.0127, "step": 219440 }, { "epoch": 52.68, "learning_rate": 3.059670350623096e-05, "loss": 0.0035, "step": 219450 }, { "epoch": 52.68, "learning_rate": 3.059256825656656e-05, "loss": 0.0119, "step": 219460 }, { "epoch": 52.68, "learning_rate": 3.058843316319287e-05, "loss": 0.0027, "step": 219470 }, { "epoch": 52.69, "learning_rate": 3.058429822614322e-05, "loss": 0.0057, "step": 219480 }, { "epoch": 52.69, "learning_rate": 3.058016344545091e-05, "loss": 0.0026, "step": 219490 }, { "epoch": 52.69, "learning_rate": 3.05760288211492e-05, "loss": 0.0037, "step": 219500 }, { "epoch": 52.69, "learning_rate": 3.057189435327142e-05, "loss": 0.0102, "step": 219510 }, { "epoch": 52.7, "learning_rate": 3.0567760041850854e-05, "loss": 0.0142, "step": 219520 }, { "epoch": 52.7, "learning_rate": 3.056362588692081e-05, "loss": 0.0064, "step": 219530 }, { "epoch": 52.7, "learning_rate": 3.055949188851458e-05, "loss": 0.0039, "step": 219540 }, { "epoch": 52.7, "learning_rate": 3.0555358046665424e-05, "loss": 0.0032, "step": 219550 }, { "epoch": 52.7, "learning_rate": 3.0551224361406663e-05, "loss": 0.0037, "step": 219560 }, { "epoch": 52.71, "learning_rate": 3.0547090832771566e-05, "loss": 0.003, "step": 219570 }, { "epoch": 52.71, "learning_rate": 3.0542957460793456e-05, "loss": 0.0033, "step": 219580 }, { "epoch": 52.71, "learning_rate": 3.053882424550558e-05, "loss": 0.003, "step": 219590 }, { "epoch": 52.71, "learning_rate": 3.0534691186941235e-05, "loss": 0.0116, "step": 219600 }, { "epoch": 52.72, "learning_rate": 3.053055828513371e-05, "loss": 0.0131, "step": 219610 }, { "epoch": 52.72, "learning_rate": 3.0526425540116286e-05, "loss": 0.0026, "step": 219620 }, { "epoch": 52.72, "learning_rate": 3.052229295192226e-05, "loss": 0.0039, "step": 219630 }, { "epoch": 52.72, "learning_rate": 3.051816052058489e-05, "loss": 0.0026, "step": 219640 }, { "epoch": 52.73, "learning_rate": 3.051402824613746e-05, "loss": 0.0024, "step": 219650 }, { "epoch": 52.73, "learning_rate": 3.0509896128613252e-05, "loss": 0.006, "step": 219660 }, { "epoch": 52.73, "learning_rate": 3.0505764168045536e-05, "loss": 0.0093, "step": 219670 }, { "epoch": 52.73, "learning_rate": 3.050163236446762e-05, "loss": 0.0035, "step": 219680 }, { "epoch": 52.73, "learning_rate": 3.049750071791272e-05, "loss": 0.0287, "step": 219690 }, { "epoch": 52.74, "learning_rate": 3.0493369228414147e-05, "loss": 0.005, "step": 219700 }, { "epoch": 52.74, "learning_rate": 3.0489237896005164e-05, "loss": 0.0062, "step": 219710 }, { "epoch": 52.74, "learning_rate": 3.0485106720719047e-05, "loss": 0.0064, "step": 219720 }, { "epoch": 52.74, "learning_rate": 3.0480975702589066e-05, "loss": 0.0029, "step": 219730 }, { "epoch": 52.75, "learning_rate": 3.047684484164846e-05, "loss": 0.0031, "step": 219740 }, { "epoch": 52.75, "learning_rate": 3.0472714137930536e-05, "loss": 0.0141, "step": 219750 }, { "epoch": 52.75, "learning_rate": 3.0468583591468526e-05, "loss": 0.0043, "step": 219760 }, { "epoch": 52.75, "learning_rate": 3.0464453202295728e-05, "loss": 0.0036, "step": 219770 }, { "epoch": 52.76, "learning_rate": 3.0460322970445377e-05, "loss": 0.0054, "step": 219780 }, { "epoch": 52.76, "learning_rate": 3.0456192895950736e-05, "loss": 0.0075, "step": 219790 }, { "epoch": 52.76, "learning_rate": 3.045206297884508e-05, "loss": 0.0079, "step": 219800 }, { "epoch": 52.76, "learning_rate": 3.044793321916165e-05, "loss": 0.0204, "step": 219810 }, { "epoch": 52.76, "learning_rate": 3.044380361693373e-05, "loss": 0.0027, "step": 219820 }, { "epoch": 52.77, "learning_rate": 3.0439674172194556e-05, "loss": 0.0023, "step": 219830 }, { "epoch": 52.77, "learning_rate": 3.0435544884977368e-05, "loss": 0.0104, "step": 219840 }, { "epoch": 52.77, "learning_rate": 3.043141575531545e-05, "loss": 0.006, "step": 219850 }, { "epoch": 52.77, "learning_rate": 3.0427286783242036e-05, "loss": 0.0031, "step": 219860 }, { "epoch": 52.78, "learning_rate": 3.0423157968790416e-05, "loss": 0.0052, "step": 219870 }, { "epoch": 52.78, "learning_rate": 3.0419029311993775e-05, "loss": 0.0031, "step": 219880 }, { "epoch": 52.78, "learning_rate": 3.04149008128854e-05, "loss": 0.0025, "step": 219890 }, { "epoch": 52.78, "learning_rate": 3.041077247149853e-05, "loss": 0.0066, "step": 219900 }, { "epoch": 52.78, "learning_rate": 3.0406644287866426e-05, "loss": 0.0041, "step": 219910 }, { "epoch": 52.79, "learning_rate": 3.0402516262022313e-05, "loss": 0.0048, "step": 219920 }, { "epoch": 52.79, "learning_rate": 3.0398388393999433e-05, "loss": 0.008, "step": 219930 }, { "epoch": 52.79, "learning_rate": 3.0394260683831046e-05, "loss": 0.013, "step": 219940 }, { "epoch": 52.79, "learning_rate": 3.0390133131550376e-05, "loss": 0.0024, "step": 219950 }, { "epoch": 52.8, "learning_rate": 3.038600573719069e-05, "loss": 0.0049, "step": 219960 }, { "epoch": 52.8, "learning_rate": 3.03818785007852e-05, "loss": 0.0043, "step": 219970 }, { "epoch": 52.8, "learning_rate": 3.037775142236714e-05, "loss": 0.006, "step": 219980 }, { "epoch": 52.8, "learning_rate": 3.0373624501969765e-05, "loss": 0.0088, "step": 219990 }, { "epoch": 52.81, "learning_rate": 3.0369497739626296e-05, "loss": 0.0128, "step": 220000 }, { "epoch": 52.81, "learning_rate": 3.036537113536999e-05, "loss": 0.0047, "step": 220010 }, { "epoch": 52.81, "learning_rate": 3.0361244689234047e-05, "loss": 0.0053, "step": 220020 }, { "epoch": 52.81, "learning_rate": 3.0357118401251705e-05, "loss": 0.0103, "step": 220030 }, { "epoch": 52.81, "learning_rate": 3.035299227145621e-05, "loss": 0.011, "step": 220040 }, { "epoch": 52.82, "learning_rate": 3.034886629988079e-05, "loss": 0.0062, "step": 220050 }, { "epoch": 52.82, "learning_rate": 3.0344740486558643e-05, "loss": 0.0046, "step": 220060 }, { "epoch": 52.82, "learning_rate": 3.034061483152303e-05, "loss": 0.0089, "step": 220070 }, { "epoch": 52.82, "learning_rate": 3.033648933480714e-05, "loss": 0.0092, "step": 220080 }, { "epoch": 52.83, "learning_rate": 3.0332363996444236e-05, "loss": 0.0037, "step": 220090 }, { "epoch": 52.83, "learning_rate": 3.0328238816467526e-05, "loss": 0.0056, "step": 220100 }, { "epoch": 52.83, "learning_rate": 3.0324113794910208e-05, "loss": 0.0074, "step": 220110 }, { "epoch": 52.83, "learning_rate": 3.0319988931805514e-05, "loss": 0.0051, "step": 220120 }, { "epoch": 52.84, "learning_rate": 3.0315864227186675e-05, "loss": 0.0036, "step": 220130 }, { "epoch": 52.84, "learning_rate": 3.0311739681086894e-05, "loss": 0.013, "step": 220140 }, { "epoch": 52.84, "learning_rate": 3.0307615293539405e-05, "loss": 0.0027, "step": 220150 }, { "epoch": 52.84, "learning_rate": 3.03034910645774e-05, "loss": 0.0071, "step": 220160 }, { "epoch": 52.84, "learning_rate": 3.029936699423409e-05, "loss": 0.0028, "step": 220170 }, { "epoch": 52.85, "learning_rate": 3.0295243082542712e-05, "loss": 0.0051, "step": 220180 }, { "epoch": 52.85, "learning_rate": 3.0291119329536444e-05, "loss": 0.004, "step": 220190 }, { "epoch": 52.85, "learning_rate": 3.028699573524854e-05, "loss": 0.0051, "step": 220200 }, { "epoch": 52.85, "learning_rate": 3.0282872299712174e-05, "loss": 0.003, "step": 220210 }, { "epoch": 52.86, "learning_rate": 3.027874902296054e-05, "loss": 0.003, "step": 220220 }, { "epoch": 52.86, "learning_rate": 3.0274625905026876e-05, "loss": 0.0064, "step": 220230 }, { "epoch": 52.86, "learning_rate": 3.027050294594439e-05, "loss": 0.0094, "step": 220240 }, { "epoch": 52.86, "learning_rate": 3.0266380145746236e-05, "loss": 0.0203, "step": 220250 }, { "epoch": 52.86, "learning_rate": 3.0262257504465663e-05, "loss": 0.005, "step": 220260 }, { "epoch": 52.87, "learning_rate": 3.0258135022135847e-05, "loss": 0.0035, "step": 220270 }, { "epoch": 52.87, "learning_rate": 3.0254012698790003e-05, "loss": 0.0061, "step": 220280 }, { "epoch": 52.87, "learning_rate": 3.0249890534461333e-05, "loss": 0.0052, "step": 220290 }, { "epoch": 52.87, "learning_rate": 3.0245768529183004e-05, "loss": 0.0066, "step": 220300 }, { "epoch": 52.88, "learning_rate": 3.0241646682988223e-05, "loss": 0.0065, "step": 220310 }, { "epoch": 52.88, "learning_rate": 3.0237524995910205e-05, "loss": 0.0059, "step": 220320 }, { "epoch": 52.88, "learning_rate": 3.0233403467982114e-05, "loss": 0.0119, "step": 220330 }, { "epoch": 52.88, "learning_rate": 3.0229282099237167e-05, "loss": 0.0026, "step": 220340 }, { "epoch": 52.89, "learning_rate": 3.0225160889708538e-05, "loss": 0.0043, "step": 220350 }, { "epoch": 52.89, "learning_rate": 3.0221039839429398e-05, "loss": 0.0098, "step": 220360 }, { "epoch": 52.89, "learning_rate": 3.0216918948432977e-05, "loss": 0.0043, "step": 220370 }, { "epoch": 52.89, "learning_rate": 3.0212798216752442e-05, "loss": 0.0042, "step": 220380 }, { "epoch": 52.89, "learning_rate": 3.0208677644420957e-05, "loss": 0.0138, "step": 220390 }, { "epoch": 52.9, "learning_rate": 3.020455723147173e-05, "loss": 0.0046, "step": 220400 }, { "epoch": 52.9, "learning_rate": 3.020043697793793e-05, "loss": 0.014, "step": 220410 }, { "epoch": 52.9, "learning_rate": 3.019631688385276e-05, "loss": 0.0043, "step": 220420 }, { "epoch": 52.9, "learning_rate": 3.0192196949249385e-05, "loss": 0.0086, "step": 220430 }, { "epoch": 52.91, "learning_rate": 3.0188077174160965e-05, "loss": 0.0053, "step": 220440 }, { "epoch": 52.91, "learning_rate": 3.0183957558620705e-05, "loss": 0.0066, "step": 220450 }, { "epoch": 52.91, "learning_rate": 3.017983810266176e-05, "loss": 0.0096, "step": 220460 }, { "epoch": 52.91, "learning_rate": 3.0175718806317333e-05, "loss": 0.0115, "step": 220470 }, { "epoch": 52.91, "learning_rate": 3.0171599669620577e-05, "loss": 0.0042, "step": 220480 }, { "epoch": 52.92, "learning_rate": 3.0167480692604656e-05, "loss": 0.0038, "step": 220490 }, { "epoch": 52.92, "learning_rate": 3.0163361875302753e-05, "loss": 0.0076, "step": 220500 }, { "epoch": 52.92, "learning_rate": 3.0159243217748036e-05, "loss": 0.0033, "step": 220510 }, { "epoch": 52.92, "learning_rate": 3.015512471997367e-05, "loss": 0.011, "step": 220520 }, { "epoch": 52.93, "learning_rate": 3.015100638201284e-05, "loss": 0.0019, "step": 220530 }, { "epoch": 52.93, "learning_rate": 3.0146888203898687e-05, "loss": 0.0018, "step": 220540 }, { "epoch": 52.93, "learning_rate": 3.014277018566437e-05, "loss": 0.0085, "step": 220550 }, { "epoch": 52.93, "learning_rate": 3.0138652327343088e-05, "loss": 0.0078, "step": 220560 }, { "epoch": 52.94, "learning_rate": 3.013453462896798e-05, "loss": 0.0048, "step": 220570 }, { "epoch": 52.94, "learning_rate": 3.0130417090572188e-05, "loss": 0.0104, "step": 220580 }, { "epoch": 52.94, "learning_rate": 3.0126299712188897e-05, "loss": 0.0032, "step": 220590 }, { "epoch": 52.94, "learning_rate": 3.012218249385126e-05, "loss": 0.004, "step": 220600 }, { "epoch": 52.94, "learning_rate": 3.0118065435592436e-05, "loss": 0.003, "step": 220610 }, { "epoch": 52.95, "learning_rate": 3.011394853744558e-05, "loss": 0.0076, "step": 220620 }, { "epoch": 52.95, "learning_rate": 3.0109831799443827e-05, "loss": 0.0058, "step": 220630 }, { "epoch": 53.0, "learning_rate": 3.0105715221620356e-05, "loss": 0.0026, "step": 220640 }, { "epoch": 53.0, "learning_rate": 3.010159880400829e-05, "loss": 0.0147, "step": 220650 }, { "epoch": 53.0, "learning_rate": 3.0097482546640815e-05, "loss": 0.0032, "step": 220660 }, { "epoch": 53.01, "learning_rate": 3.0093366449551064e-05, "loss": 0.003, "step": 220670 }, { "epoch": 53.01, "learning_rate": 3.008925051277217e-05, "loss": 0.0049, "step": 220680 }, { "epoch": 53.01, "learning_rate": 3.0085134736337295e-05, "loss": 0.0068, "step": 220690 }, { "epoch": 53.01, "learning_rate": 3.0081019120279564e-05, "loss": 0.0099, "step": 220700 }, { "epoch": 53.02, "learning_rate": 3.0076903664632162e-05, "loss": 0.0026, "step": 220710 }, { "epoch": 53.02, "learning_rate": 3.0072788369428194e-05, "loss": 0.004, "step": 220720 }, { "epoch": 53.02, "learning_rate": 3.0068673234700817e-05, "loss": 0.0022, "step": 220730 }, { "epoch": 53.02, "learning_rate": 3.006455826048315e-05, "loss": 0.0086, "step": 220740 }, { "epoch": 53.03, "learning_rate": 3.006044344680836e-05, "loss": 0.0049, "step": 220750 }, { "epoch": 53.03, "learning_rate": 3.0056328793709576e-05, "loss": 0.0111, "step": 220760 }, { "epoch": 53.03, "learning_rate": 3.0052214301219917e-05, "loss": 0.0041, "step": 220770 }, { "epoch": 53.03, "learning_rate": 3.004809996937254e-05, "loss": 0.0057, "step": 220780 }, { "epoch": 53.03, "learning_rate": 3.0043985798200557e-05, "loss": 0.0036, "step": 220790 }, { "epoch": 53.04, "learning_rate": 3.0039871787737118e-05, "loss": 0.0123, "step": 220800 }, { "epoch": 53.04, "learning_rate": 3.0035757938015362e-05, "loss": 0.0066, "step": 220810 }, { "epoch": 53.04, "learning_rate": 3.003164424906838e-05, "loss": 0.0043, "step": 220820 }, { "epoch": 53.04, "learning_rate": 3.0027530720929337e-05, "loss": 0.0108, "step": 220830 }, { "epoch": 53.05, "learning_rate": 3.0023417353631334e-05, "loss": 0.0026, "step": 220840 }, { "epoch": 53.05, "learning_rate": 3.0019304147207516e-05, "loss": 0.0037, "step": 220850 }, { "epoch": 53.05, "learning_rate": 3.001519110169102e-05, "loss": 0.0042, "step": 220860 }, { "epoch": 53.05, "learning_rate": 3.001107821711492e-05, "loss": 0.003, "step": 220870 }, { "epoch": 53.06, "learning_rate": 3.0006965493512383e-05, "loss": 0.0089, "step": 220880 }, { "epoch": 53.06, "learning_rate": 3.0002852930916496e-05, "loss": 0.004, "step": 220890 }, { "epoch": 53.06, "learning_rate": 2.9998740529360424e-05, "loss": 0.0044, "step": 220900 }, { "epoch": 53.06, "learning_rate": 2.9994628288877235e-05, "loss": 0.005, "step": 220910 }, { "epoch": 53.06, "learning_rate": 2.9990516209500065e-05, "loss": 0.0022, "step": 220920 }, { "epoch": 53.07, "learning_rate": 2.998640429126204e-05, "loss": 0.0074, "step": 220930 }, { "epoch": 53.07, "learning_rate": 2.998229253419625e-05, "loss": 0.0055, "step": 220940 }, { "epoch": 53.07, "learning_rate": 2.9978180938335854e-05, "loss": 0.0051, "step": 220950 }, { "epoch": 53.07, "learning_rate": 2.99740695037139e-05, "loss": 0.0057, "step": 220960 }, { "epoch": 53.08, "learning_rate": 2.9969958230363537e-05, "loss": 0.0033, "step": 220970 }, { "epoch": 53.08, "learning_rate": 2.9965847118317864e-05, "loss": 0.0073, "step": 220980 }, { "epoch": 53.08, "learning_rate": 2.9961736167609995e-05, "loss": 0.0031, "step": 220990 }, { "epoch": 53.08, "learning_rate": 2.9957625378273036e-05, "loss": 0.0029, "step": 221000 }, { "epoch": 53.08, "learning_rate": 2.9953514750340073e-05, "loss": 0.0064, "step": 221010 }, { "epoch": 53.09, "learning_rate": 2.9949404283844233e-05, "loss": 0.0036, "step": 221020 }, { "epoch": 53.09, "learning_rate": 2.99452939788186e-05, "loss": 0.0032, "step": 221030 }, { "epoch": 53.09, "learning_rate": 2.99411838352963e-05, "loss": 0.01, "step": 221040 }, { "epoch": 53.09, "learning_rate": 2.9937073853310405e-05, "loss": 0.005, "step": 221050 }, { "epoch": 53.1, "learning_rate": 2.9932964032894017e-05, "loss": 0.0033, "step": 221060 }, { "epoch": 53.1, "learning_rate": 2.992885437408025e-05, "loss": 0.0022, "step": 221070 }, { "epoch": 53.1, "learning_rate": 2.9924744876902177e-05, "loss": 0.0332, "step": 221080 }, { "epoch": 53.1, "learning_rate": 2.9920635541392928e-05, "loss": 0.0026, "step": 221090 }, { "epoch": 53.11, "learning_rate": 2.9916526367585562e-05, "loss": 0.0062, "step": 221100 }, { "epoch": 53.11, "learning_rate": 2.9912417355513167e-05, "loss": 0.0026, "step": 221110 }, { "epoch": 53.11, "learning_rate": 2.9908308505208866e-05, "loss": 0.0051, "step": 221120 }, { "epoch": 53.11, "learning_rate": 2.9904199816705713e-05, "loss": 0.0034, "step": 221130 }, { "epoch": 53.11, "learning_rate": 2.990009129003684e-05, "loss": 0.0049, "step": 221140 }, { "epoch": 53.12, "learning_rate": 2.9895982925235295e-05, "loss": 0.0048, "step": 221150 }, { "epoch": 53.12, "learning_rate": 2.989187472233417e-05, "loss": 0.0017, "step": 221160 }, { "epoch": 53.12, "learning_rate": 2.9887766681366553e-05, "loss": 0.0036, "step": 221170 }, { "epoch": 53.12, "learning_rate": 2.9883658802365534e-05, "loss": 0.0023, "step": 221180 }, { "epoch": 53.13, "learning_rate": 2.9879551085364198e-05, "loss": 0.006, "step": 221190 }, { "epoch": 53.13, "learning_rate": 2.9875443530395592e-05, "loss": 0.0076, "step": 221200 }, { "epoch": 53.13, "learning_rate": 2.987133613749283e-05, "loss": 0.0018, "step": 221210 }, { "epoch": 53.13, "learning_rate": 2.9867228906688967e-05, "loss": 0.0036, "step": 221220 }, { "epoch": 53.14, "learning_rate": 2.9863121838017104e-05, "loss": 0.0073, "step": 221230 }, { "epoch": 53.14, "learning_rate": 2.98590149315103e-05, "loss": 0.0029, "step": 221240 }, { "epoch": 53.14, "learning_rate": 2.9854908187201613e-05, "loss": 0.0077, "step": 221250 }, { "epoch": 53.14, "learning_rate": 2.9850801605124144e-05, "loss": 0.0026, "step": 221260 }, { "epoch": 53.14, "learning_rate": 2.9846695185310937e-05, "loss": 0.003, "step": 221270 }, { "epoch": 53.15, "learning_rate": 2.98425889277951e-05, "loss": 0.0031, "step": 221280 }, { "epoch": 53.15, "learning_rate": 2.983848283260967e-05, "loss": 0.0055, "step": 221290 }, { "epoch": 53.15, "learning_rate": 2.983437689978771e-05, "loss": 0.0071, "step": 221300 }, { "epoch": 53.15, "learning_rate": 2.9830271129362303e-05, "loss": 0.0145, "step": 221310 }, { "epoch": 53.16, "learning_rate": 2.98261655213665e-05, "loss": 0.0023, "step": 221320 }, { "epoch": 53.16, "learning_rate": 2.982206007583339e-05, "loss": 0.0033, "step": 221330 }, { "epoch": 53.16, "learning_rate": 2.9817954792796004e-05, "loss": 0.0057, "step": 221340 }, { "epoch": 53.16, "learning_rate": 2.9813849672287407e-05, "loss": 0.008, "step": 221350 }, { "epoch": 53.16, "learning_rate": 2.9809744714340676e-05, "loss": 0.0047, "step": 221360 }, { "epoch": 53.17, "learning_rate": 2.9805639918988872e-05, "loss": 0.0044, "step": 221370 }, { "epoch": 53.17, "learning_rate": 2.980153528626502e-05, "loss": 0.0122, "step": 221380 }, { "epoch": 53.17, "learning_rate": 2.9797430816202187e-05, "loss": 0.0106, "step": 221390 }, { "epoch": 53.17, "learning_rate": 2.979332650883344e-05, "loss": 0.0103, "step": 221400 }, { "epoch": 53.18, "learning_rate": 2.9789222364191817e-05, "loss": 0.0107, "step": 221410 }, { "epoch": 53.18, "learning_rate": 2.9785118382310394e-05, "loss": 0.0056, "step": 221420 }, { "epoch": 53.18, "learning_rate": 2.97810145632222e-05, "loss": 0.007, "step": 221430 }, { "epoch": 53.18, "learning_rate": 2.977691090696027e-05, "loss": 0.0106, "step": 221440 }, { "epoch": 53.19, "learning_rate": 2.977280741355768e-05, "loss": 0.0045, "step": 221450 }, { "epoch": 53.19, "learning_rate": 2.976870408304746e-05, "loss": 0.0063, "step": 221460 }, { "epoch": 53.19, "learning_rate": 2.9764600915462672e-05, "loss": 0.003, "step": 221470 }, { "epoch": 53.19, "learning_rate": 2.9760497910836337e-05, "loss": 0.0053, "step": 221480 }, { "epoch": 53.19, "learning_rate": 2.9756395069201502e-05, "loss": 0.0078, "step": 221490 }, { "epoch": 53.2, "learning_rate": 2.975229239059122e-05, "loss": 0.0079, "step": 221500 }, { "epoch": 53.2, "learning_rate": 2.9748189875038507e-05, "loss": 0.0175, "step": 221510 }, { "epoch": 53.2, "learning_rate": 2.974408752257644e-05, "loss": 0.0185, "step": 221520 }, { "epoch": 53.2, "learning_rate": 2.973998533323803e-05, "loss": 0.0037, "step": 221530 }, { "epoch": 53.21, "learning_rate": 2.97358833070563e-05, "loss": 0.0032, "step": 221540 }, { "epoch": 53.21, "learning_rate": 2.9731781444064304e-05, "loss": 0.0046, "step": 221550 }, { "epoch": 53.21, "learning_rate": 2.972767974429509e-05, "loss": 0.002, "step": 221560 }, { "epoch": 53.21, "learning_rate": 2.9723578207781645e-05, "loss": 0.0063, "step": 221570 }, { "epoch": 53.22, "learning_rate": 2.971947683455703e-05, "loss": 0.0024, "step": 221580 }, { "epoch": 53.22, "learning_rate": 2.9715375624654264e-05, "loss": 0.0127, "step": 221590 }, { "epoch": 53.22, "learning_rate": 2.9711274578106383e-05, "loss": 0.0023, "step": 221600 }, { "epoch": 53.22, "learning_rate": 2.970717369494642e-05, "loss": 0.0023, "step": 221610 }, { "epoch": 53.22, "learning_rate": 2.970307297520738e-05, "loss": 0.0034, "step": 221620 }, { "epoch": 53.23, "learning_rate": 2.9698972418922287e-05, "loss": 0.0034, "step": 221630 }, { "epoch": 53.23, "learning_rate": 2.9694872026124186e-05, "loss": 0.0128, "step": 221640 }, { "epoch": 53.23, "learning_rate": 2.9690771796846067e-05, "loss": 0.0073, "step": 221650 }, { "epoch": 53.23, "learning_rate": 2.968667173112099e-05, "loss": 0.0057, "step": 221660 }, { "epoch": 53.24, "learning_rate": 2.9682571828981943e-05, "loss": 0.0034, "step": 221670 }, { "epoch": 53.24, "learning_rate": 2.9678472090461927e-05, "loss": 0.0038, "step": 221680 }, { "epoch": 53.24, "learning_rate": 2.9674372515594005e-05, "loss": 0.0048, "step": 221690 }, { "epoch": 53.24, "learning_rate": 2.967027310441115e-05, "loss": 0.0025, "step": 221700 }, { "epoch": 53.24, "learning_rate": 2.9666173856946418e-05, "loss": 0.0033, "step": 221710 }, { "epoch": 53.25, "learning_rate": 2.966207477323278e-05, "loss": 0.0066, "step": 221720 }, { "epoch": 53.25, "learning_rate": 2.9657975853303256e-05, "loss": 0.004, "step": 221730 }, { "epoch": 53.25, "learning_rate": 2.9653877097190862e-05, "loss": 0.0074, "step": 221740 }, { "epoch": 53.25, "learning_rate": 2.964977850492862e-05, "loss": 0.0017, "step": 221750 }, { "epoch": 53.26, "learning_rate": 2.9645680076549503e-05, "loss": 0.0063, "step": 221760 }, { "epoch": 53.26, "learning_rate": 2.9641581812086545e-05, "loss": 0.0042, "step": 221770 }, { "epoch": 53.26, "learning_rate": 2.9637483711572727e-05, "loss": 0.0024, "step": 221780 }, { "epoch": 53.26, "learning_rate": 2.9633385775041078e-05, "loss": 0.0034, "step": 221790 }, { "epoch": 53.27, "learning_rate": 2.962928800252459e-05, "loss": 0.004, "step": 221800 }, { "epoch": 53.27, "learning_rate": 2.9625190394056246e-05, "loss": 0.0022, "step": 221810 }, { "epoch": 53.27, "learning_rate": 2.962109294966905e-05, "loss": 0.0097, "step": 221820 }, { "epoch": 53.27, "learning_rate": 2.961699566939602e-05, "loss": 0.0023, "step": 221830 }, { "epoch": 53.27, "learning_rate": 2.9612898553270124e-05, "loss": 0.0035, "step": 221840 }, { "epoch": 53.28, "learning_rate": 2.9608801601324386e-05, "loss": 0.013, "step": 221850 }, { "epoch": 53.28, "learning_rate": 2.9604704813591784e-05, "loss": 0.0038, "step": 221860 }, { "epoch": 53.28, "learning_rate": 2.9600608190105294e-05, "loss": 0.0064, "step": 221870 }, { "epoch": 53.28, "learning_rate": 2.9596511730897934e-05, "loss": 0.0026, "step": 221880 }, { "epoch": 53.29, "learning_rate": 2.959241543600269e-05, "loss": 0.0068, "step": 221890 }, { "epoch": 53.29, "learning_rate": 2.9588319305452523e-05, "loss": 0.0044, "step": 221900 }, { "epoch": 53.29, "learning_rate": 2.9584223339280446e-05, "loss": 0.0034, "step": 221910 }, { "epoch": 53.29, "learning_rate": 2.958012753751943e-05, "loss": 0.0026, "step": 221920 }, { "epoch": 53.3, "learning_rate": 2.9576031900202477e-05, "loss": 0.0043, "step": 221930 }, { "epoch": 53.3, "learning_rate": 2.9571936427362568e-05, "loss": 0.0078, "step": 221940 }, { "epoch": 53.3, "learning_rate": 2.9567841119032656e-05, "loss": 0.0039, "step": 221950 }, { "epoch": 53.3, "learning_rate": 2.956374597524575e-05, "loss": 0.0052, "step": 221960 }, { "epoch": 53.3, "learning_rate": 2.9559650996034805e-05, "loss": 0.003, "step": 221970 }, { "epoch": 53.31, "learning_rate": 2.955555618143283e-05, "loss": 0.005, "step": 221980 }, { "epoch": 53.31, "learning_rate": 2.955146153147279e-05, "loss": 0.0046, "step": 221990 }, { "epoch": 53.31, "learning_rate": 2.954736704618763e-05, "loss": 0.0043, "step": 222000 }, { "epoch": 53.31, "learning_rate": 2.954327272561036e-05, "loss": 0.0052, "step": 222010 }, { "epoch": 53.32, "learning_rate": 2.953917856977393e-05, "loss": 0.0028, "step": 222020 }, { "epoch": 53.32, "learning_rate": 2.9535084578711325e-05, "loss": 0.0041, "step": 222030 }, { "epoch": 53.32, "learning_rate": 2.9530990752455523e-05, "loss": 0.0084, "step": 222040 }, { "epoch": 53.32, "learning_rate": 2.952689709103947e-05, "loss": 0.0031, "step": 222050 }, { "epoch": 53.32, "learning_rate": 2.9522803594496128e-05, "loss": 0.0036, "step": 222060 }, { "epoch": 53.33, "learning_rate": 2.9518710262858484e-05, "loss": 0.0071, "step": 222070 }, { "epoch": 53.33, "learning_rate": 2.9514617096159507e-05, "loss": 0.0031, "step": 222080 }, { "epoch": 53.33, "learning_rate": 2.951052409443213e-05, "loss": 0.0016, "step": 222090 }, { "epoch": 53.33, "learning_rate": 2.950643125770933e-05, "loss": 0.0023, "step": 222100 }, { "epoch": 53.34, "learning_rate": 2.950233858602407e-05, "loss": 0.0033, "step": 222110 }, { "epoch": 53.34, "learning_rate": 2.9498246079409312e-05, "loss": 0.0067, "step": 222120 }, { "epoch": 53.34, "learning_rate": 2.949415373789802e-05, "loss": 0.0076, "step": 222130 }, { "epoch": 53.34, "learning_rate": 2.949006156152312e-05, "loss": 0.0122, "step": 222140 }, { "epoch": 53.35, "learning_rate": 2.9485969550317594e-05, "loss": 0.0114, "step": 222150 }, { "epoch": 53.35, "learning_rate": 2.948187770431438e-05, "loss": 0.0098, "step": 222160 }, { "epoch": 53.35, "learning_rate": 2.947778602354645e-05, "loss": 0.0071, "step": 222170 }, { "epoch": 53.35, "learning_rate": 2.9473694508046746e-05, "loss": 0.0034, "step": 222180 }, { "epoch": 53.35, "learning_rate": 2.9469603157848193e-05, "loss": 0.007, "step": 222190 }, { "epoch": 53.36, "learning_rate": 2.9465511972983773e-05, "loss": 0.0046, "step": 222200 }, { "epoch": 53.36, "learning_rate": 2.9461420953486412e-05, "loss": 0.0046, "step": 222210 }, { "epoch": 53.36, "learning_rate": 2.945733009938909e-05, "loss": 0.0033, "step": 222220 }, { "epoch": 53.36, "learning_rate": 2.94532394107247e-05, "loss": 0.0064, "step": 222230 }, { "epoch": 53.37, "learning_rate": 2.944914888752621e-05, "loss": 0.0056, "step": 222240 }, { "epoch": 53.37, "learning_rate": 2.9445058529826565e-05, "loss": 0.0026, "step": 222250 }, { "epoch": 53.37, "learning_rate": 2.9440968337658704e-05, "loss": 0.0033, "step": 222260 }, { "epoch": 53.37, "learning_rate": 2.9436878311055573e-05, "loss": 0.0035, "step": 222270 }, { "epoch": 53.38, "learning_rate": 2.9432788450050076e-05, "loss": 0.0114, "step": 222280 }, { "epoch": 53.38, "learning_rate": 2.9428698754675188e-05, "loss": 0.0041, "step": 222290 }, { "epoch": 53.38, "learning_rate": 2.9424609224963817e-05, "loss": 0.0021, "step": 222300 }, { "epoch": 53.38, "learning_rate": 2.9420519860948925e-05, "loss": 0.0137, "step": 222310 }, { "epoch": 53.38, "learning_rate": 2.941643066266343e-05, "loss": 0.0045, "step": 222320 }, { "epoch": 53.39, "learning_rate": 2.941234163014024e-05, "loss": 0.0037, "step": 222330 }, { "epoch": 53.39, "learning_rate": 2.9408252763412326e-05, "loss": 0.0088, "step": 222340 }, { "epoch": 53.39, "learning_rate": 2.9404164062512573e-05, "loss": 0.0044, "step": 222350 }, { "epoch": 53.39, "learning_rate": 2.9400075527473947e-05, "loss": 0.018, "step": 222360 }, { "epoch": 53.4, "learning_rate": 2.9395987158329362e-05, "loss": 0.0059, "step": 222370 }, { "epoch": 53.4, "learning_rate": 2.939189895511172e-05, "loss": 0.003, "step": 222380 }, { "epoch": 53.4, "learning_rate": 2.938781091785397e-05, "loss": 0.0021, "step": 222390 }, { "epoch": 53.4, "learning_rate": 2.938372304658902e-05, "loss": 0.0045, "step": 222400 }, { "epoch": 53.4, "learning_rate": 2.9379635341349804e-05, "loss": 0.0043, "step": 222410 }, { "epoch": 53.41, "learning_rate": 2.937554780216923e-05, "loss": 0.0135, "step": 222420 }, { "epoch": 53.41, "learning_rate": 2.9371460429080198e-05, "loss": 0.0026, "step": 222430 }, { "epoch": 53.41, "learning_rate": 2.9367373222115663e-05, "loss": 0.0021, "step": 222440 }, { "epoch": 53.41, "learning_rate": 2.9363286181308502e-05, "loss": 0.0033, "step": 222450 }, { "epoch": 53.42, "learning_rate": 2.9359199306691686e-05, "loss": 0.0047, "step": 222460 }, { "epoch": 53.42, "learning_rate": 2.9355112598298052e-05, "loss": 0.0077, "step": 222470 }, { "epoch": 53.42, "learning_rate": 2.9351026056160553e-05, "loss": 0.0139, "step": 222480 }, { "epoch": 53.42, "learning_rate": 2.9346939680312084e-05, "loss": 0.0337, "step": 222490 }, { "epoch": 53.43, "learning_rate": 2.9342853470785575e-05, "loss": 0.0156, "step": 222500 }, { "epoch": 53.43, "learning_rate": 2.9338767427613922e-05, "loss": 0.0059, "step": 222510 }, { "epoch": 53.43, "learning_rate": 2.9334681550830012e-05, "loss": 0.0036, "step": 222520 }, { "epoch": 53.43, "learning_rate": 2.9330595840466778e-05, "loss": 0.0027, "step": 222530 }, { "epoch": 53.43, "learning_rate": 2.9326510296557096e-05, "loss": 0.0174, "step": 222540 }, { "epoch": 53.44, "learning_rate": 2.9322424919133894e-05, "loss": 0.007, "step": 222550 }, { "epoch": 53.44, "learning_rate": 2.9318339708230058e-05, "loss": 0.0047, "step": 222560 }, { "epoch": 53.44, "learning_rate": 2.9314254663878477e-05, "loss": 0.0063, "step": 222570 }, { "epoch": 53.44, "learning_rate": 2.9310169786112062e-05, "loss": 0.0024, "step": 222580 }, { "epoch": 53.45, "learning_rate": 2.9306085074963706e-05, "loss": 0.0068, "step": 222590 }, { "epoch": 53.45, "learning_rate": 2.9302000530466318e-05, "loss": 0.007, "step": 222600 }, { "epoch": 53.45, "learning_rate": 2.9297916152652772e-05, "loss": 0.006, "step": 222610 }, { "epoch": 53.45, "learning_rate": 2.9293831941555948e-05, "loss": 0.0057, "step": 222620 }, { "epoch": 53.45, "learning_rate": 2.9289747897208764e-05, "loss": 0.0136, "step": 222630 }, { "epoch": 53.46, "learning_rate": 2.9285664019644095e-05, "loss": 0.0051, "step": 222640 }, { "epoch": 53.46, "learning_rate": 2.928158030889485e-05, "loss": 0.0038, "step": 222650 }, { "epoch": 53.46, "learning_rate": 2.927749676499389e-05, "loss": 0.0044, "step": 222660 }, { "epoch": 53.46, "learning_rate": 2.9273413387974113e-05, "loss": 0.0028, "step": 222670 }, { "epoch": 53.47, "learning_rate": 2.926933017786838e-05, "loss": 0.0035, "step": 222680 }, { "epoch": 53.47, "learning_rate": 2.926524713470961e-05, "loss": 0.0021, "step": 222690 }, { "epoch": 53.47, "learning_rate": 2.9261164258530683e-05, "loss": 0.0026, "step": 222700 }, { "epoch": 53.47, "learning_rate": 2.9257081549364434e-05, "loss": 0.0023, "step": 222710 }, { "epoch": 53.48, "learning_rate": 2.9252999007243785e-05, "loss": 0.0022, "step": 222720 }, { "epoch": 53.48, "learning_rate": 2.9248916632201584e-05, "loss": 0.0047, "step": 222730 }, { "epoch": 53.48, "learning_rate": 2.924483442427075e-05, "loss": 0.0055, "step": 222740 }, { "epoch": 53.48, "learning_rate": 2.9240752383484116e-05, "loss": 0.0043, "step": 222750 }, { "epoch": 53.48, "learning_rate": 2.9236670509874558e-05, "loss": 0.0034, "step": 222760 }, { "epoch": 53.49, "learning_rate": 2.9232588803474968e-05, "loss": 0.0034, "step": 222770 }, { "epoch": 53.49, "learning_rate": 2.9228507264318206e-05, "loss": 0.003, "step": 222780 }, { "epoch": 53.49, "learning_rate": 2.922442589243716e-05, "loss": 0.0051, "step": 222790 }, { "epoch": 53.49, "learning_rate": 2.9220344687864664e-05, "loss": 0.0054, "step": 222800 }, { "epoch": 53.5, "learning_rate": 2.9216263650633592e-05, "loss": 0.0054, "step": 222810 }, { "epoch": 53.5, "learning_rate": 2.9212182780776833e-05, "loss": 0.0164, "step": 222820 }, { "epoch": 53.5, "learning_rate": 2.920810207832722e-05, "loss": 0.0026, "step": 222830 }, { "epoch": 53.5, "learning_rate": 2.9204021543317657e-05, "loss": 0.0057, "step": 222840 }, { "epoch": 53.51, "learning_rate": 2.9199941175780963e-05, "loss": 0.0043, "step": 222850 }, { "epoch": 53.51, "learning_rate": 2.9195860975750012e-05, "loss": 0.0104, "step": 222860 }, { "epoch": 53.51, "learning_rate": 2.919178094325766e-05, "loss": 0.0023, "step": 222870 }, { "epoch": 53.51, "learning_rate": 2.9187701078336803e-05, "loss": 0.0085, "step": 222880 }, { "epoch": 53.51, "learning_rate": 2.918362138102024e-05, "loss": 0.0096, "step": 222890 }, { "epoch": 53.52, "learning_rate": 2.9179541851340848e-05, "loss": 0.0057, "step": 222900 }, { "epoch": 53.52, "learning_rate": 2.9175462489331464e-05, "loss": 0.0039, "step": 222910 }, { "epoch": 53.52, "learning_rate": 2.9171383295024967e-05, "loss": 0.0062, "step": 222920 }, { "epoch": 53.52, "learning_rate": 2.916730426845422e-05, "loss": 0.0029, "step": 222930 }, { "epoch": 53.53, "learning_rate": 2.9163225409652005e-05, "loss": 0.002, "step": 222940 }, { "epoch": 53.53, "learning_rate": 2.9159146718651236e-05, "loss": 0.0021, "step": 222950 }, { "epoch": 53.53, "learning_rate": 2.9155068195484735e-05, "loss": 0.0064, "step": 222960 }, { "epoch": 53.53, "learning_rate": 2.915098984018535e-05, "loss": 0.0064, "step": 222970 }, { "epoch": 53.53, "learning_rate": 2.9146911652785918e-05, "loss": 0.0041, "step": 222980 }, { "epoch": 53.54, "learning_rate": 2.914283363331929e-05, "loss": 0.003, "step": 222990 }, { "epoch": 53.54, "learning_rate": 2.9138755781818298e-05, "loss": 0.0051, "step": 223000 }, { "epoch": 53.54, "learning_rate": 2.9134678098315772e-05, "loss": 0.0025, "step": 223010 }, { "epoch": 53.54, "learning_rate": 2.9130600582844576e-05, "loss": 0.004, "step": 223020 }, { "epoch": 53.55, "learning_rate": 2.9126523235437557e-05, "loss": 0.0037, "step": 223030 }, { "epoch": 53.55, "learning_rate": 2.912244605612749e-05, "loss": 0.0045, "step": 223040 }, { "epoch": 53.55, "learning_rate": 2.911836904494727e-05, "loss": 0.0091, "step": 223050 }, { "epoch": 53.55, "learning_rate": 2.91142922019297e-05, "loss": 0.0053, "step": 223060 }, { "epoch": 53.56, "learning_rate": 2.911021552710762e-05, "loss": 0.006, "step": 223070 }, { "epoch": 53.56, "learning_rate": 2.9106139020513863e-05, "loss": 0.0032, "step": 223080 }, { "epoch": 53.56, "learning_rate": 2.9102062682181254e-05, "loss": 0.0032, "step": 223090 }, { "epoch": 53.56, "learning_rate": 2.909798651214261e-05, "loss": 0.0043, "step": 223100 }, { "epoch": 53.56, "learning_rate": 2.9093910510430772e-05, "loss": 0.0048, "step": 223110 }, { "epoch": 53.57, "learning_rate": 2.9089834677078558e-05, "loss": 0.0058, "step": 223120 }, { "epoch": 53.57, "learning_rate": 2.9085759012118795e-05, "loss": 0.004, "step": 223130 }, { "epoch": 53.57, "learning_rate": 2.9081683515584303e-05, "loss": 0.0076, "step": 223140 }, { "epoch": 53.57, "learning_rate": 2.9077608187507876e-05, "loss": 0.0229, "step": 223150 }, { "epoch": 53.58, "learning_rate": 2.9073533027922382e-05, "loss": 0.0049, "step": 223160 }, { "epoch": 53.58, "learning_rate": 2.906945803686063e-05, "loss": 0.0056, "step": 223170 }, { "epoch": 53.58, "learning_rate": 2.906538321435539e-05, "loss": 0.0042, "step": 223180 }, { "epoch": 53.58, "learning_rate": 2.9061308560439527e-05, "loss": 0.0093, "step": 223190 }, { "epoch": 53.59, "learning_rate": 2.9057234075145832e-05, "loss": 0.007, "step": 223200 }, { "epoch": 53.59, "learning_rate": 2.905315975850713e-05, "loss": 0.005, "step": 223210 }, { "epoch": 53.59, "learning_rate": 2.9049085610556227e-05, "loss": 0.0049, "step": 223220 }, { "epoch": 53.59, "learning_rate": 2.9045011631325918e-05, "loss": 0.009, "step": 223230 }, { "epoch": 53.59, "learning_rate": 2.904093782084903e-05, "loss": 0.0036, "step": 223240 }, { "epoch": 53.6, "learning_rate": 2.9036864179158342e-05, "loss": 0.0044, "step": 223250 }, { "epoch": 53.6, "learning_rate": 2.903279070628672e-05, "loss": 0.0175, "step": 223260 }, { "epoch": 53.6, "learning_rate": 2.9028717402266913e-05, "loss": 0.0065, "step": 223270 }, { "epoch": 53.6, "learning_rate": 2.902464426713172e-05, "loss": 0.0039, "step": 223280 }, { "epoch": 53.61, "learning_rate": 2.902057130091398e-05, "loss": 0.0054, "step": 223290 }, { "epoch": 53.61, "learning_rate": 2.9016498503646472e-05, "loss": 0.0079, "step": 223300 }, { "epoch": 53.61, "learning_rate": 2.9012425875362027e-05, "loss": 0.0025, "step": 223310 }, { "epoch": 53.61, "learning_rate": 2.900835341609337e-05, "loss": 0.0035, "step": 223320 }, { "epoch": 53.61, "learning_rate": 2.9004281125873356e-05, "loss": 0.0146, "step": 223330 }, { "epoch": 53.62, "learning_rate": 2.9000209004734767e-05, "loss": 0.0038, "step": 223340 }, { "epoch": 53.62, "learning_rate": 2.89961370527104e-05, "loss": 0.0061, "step": 223350 }, { "epoch": 53.62, "learning_rate": 2.8992065269833036e-05, "loss": 0.0031, "step": 223360 }, { "epoch": 53.62, "learning_rate": 2.898799365613547e-05, "loss": 0.0058, "step": 223370 }, { "epoch": 53.63, "learning_rate": 2.8983922211650493e-05, "loss": 0.0048, "step": 223380 }, { "epoch": 53.63, "learning_rate": 2.8979850936410878e-05, "loss": 0.005, "step": 223390 }, { "epoch": 53.63, "learning_rate": 2.8975779830449456e-05, "loss": 0.0027, "step": 223400 }, { "epoch": 53.63, "learning_rate": 2.8971708893798965e-05, "loss": 0.004, "step": 223410 }, { "epoch": 53.64, "learning_rate": 2.896763812649219e-05, "loss": 0.0034, "step": 223420 }, { "epoch": 53.64, "learning_rate": 2.896356752856194e-05, "loss": 0.0039, "step": 223430 }, { "epoch": 53.64, "learning_rate": 2.8959497100040996e-05, "loss": 0.003, "step": 223440 }, { "epoch": 53.64, "learning_rate": 2.8955426840962118e-05, "loss": 0.0041, "step": 223450 }, { "epoch": 53.64, "learning_rate": 2.8951356751358094e-05, "loss": 0.012, "step": 223460 }, { "epoch": 53.65, "learning_rate": 2.8947286831261704e-05, "loss": 0.0043, "step": 223470 }, { "epoch": 53.65, "learning_rate": 2.894321708070572e-05, "loss": 0.0048, "step": 223480 }, { "epoch": 53.65, "learning_rate": 2.8939147499722897e-05, "loss": 0.0044, "step": 223490 }, { "epoch": 53.65, "learning_rate": 2.8935078088346058e-05, "loss": 0.0058, "step": 223500 }, { "epoch": 53.66, "learning_rate": 2.8931008846607933e-05, "loss": 0.0077, "step": 223510 }, { "epoch": 53.66, "learning_rate": 2.892693977454127e-05, "loss": 0.0035, "step": 223520 }, { "epoch": 53.66, "learning_rate": 2.8922870872178904e-05, "loss": 0.0052, "step": 223530 }, { "epoch": 53.66, "learning_rate": 2.891880213955358e-05, "loss": 0.0045, "step": 223540 }, { "epoch": 53.67, "learning_rate": 2.891473357669804e-05, "loss": 0.0043, "step": 223550 }, { "epoch": 53.67, "learning_rate": 2.8910665183645036e-05, "loss": 0.0027, "step": 223560 }, { "epoch": 53.67, "learning_rate": 2.890659696042738e-05, "loss": 0.0027, "step": 223570 }, { "epoch": 53.67, "learning_rate": 2.8902528907077808e-05, "loss": 0.0067, "step": 223580 }, { "epoch": 53.67, "learning_rate": 2.8898461023629086e-05, "loss": 0.0087, "step": 223590 }, { "epoch": 53.68, "learning_rate": 2.8894393310113964e-05, "loss": 0.0074, "step": 223600 }, { "epoch": 53.68, "learning_rate": 2.889032576656522e-05, "loss": 0.0025, "step": 223610 }, { "epoch": 53.68, "learning_rate": 2.8886258393015586e-05, "loss": 0.0078, "step": 223620 }, { "epoch": 53.68, "learning_rate": 2.888219118949781e-05, "loss": 0.0058, "step": 223630 }, { "epoch": 53.69, "learning_rate": 2.8878124156044705e-05, "loss": 0.0069, "step": 223640 }, { "epoch": 53.69, "learning_rate": 2.887405729268896e-05, "loss": 0.0065, "step": 223650 }, { "epoch": 53.69, "learning_rate": 2.8869990599463325e-05, "loss": 0.0098, "step": 223660 }, { "epoch": 53.69, "learning_rate": 2.8865924076400603e-05, "loss": 0.0105, "step": 223670 }, { "epoch": 53.69, "learning_rate": 2.8861857723533502e-05, "loss": 0.0066, "step": 223680 }, { "epoch": 53.7, "learning_rate": 2.8857791540894785e-05, "loss": 0.0036, "step": 223690 }, { "epoch": 53.7, "learning_rate": 2.8853725528517195e-05, "loss": 0.0103, "step": 223700 }, { "epoch": 53.7, "learning_rate": 2.8849659686433468e-05, "loss": 0.0118, "step": 223710 }, { "epoch": 53.7, "learning_rate": 2.8845594014676347e-05, "loss": 0.0037, "step": 223720 }, { "epoch": 53.71, "learning_rate": 2.8841528513278586e-05, "loss": 0.0063, "step": 223730 }, { "epoch": 53.71, "learning_rate": 2.8837463182272917e-05, "loss": 0.0071, "step": 223740 }, { "epoch": 53.71, "learning_rate": 2.8833398021692072e-05, "loss": 0.0033, "step": 223750 }, { "epoch": 53.71, "learning_rate": 2.88293330315688e-05, "loss": 0.0151, "step": 223760 }, { "epoch": 53.72, "learning_rate": 2.8825268211935808e-05, "loss": 0.0031, "step": 223770 }, { "epoch": 53.72, "learning_rate": 2.8821203562825898e-05, "loss": 0.0059, "step": 223780 }, { "epoch": 53.72, "learning_rate": 2.8817139084271737e-05, "loss": 0.006, "step": 223790 }, { "epoch": 53.72, "learning_rate": 2.8813074776306058e-05, "loss": 0.0029, "step": 223800 }, { "epoch": 53.72, "learning_rate": 2.8809010638961644e-05, "loss": 0.0045, "step": 223810 }, { "epoch": 53.73, "learning_rate": 2.8804946672271184e-05, "loss": 0.0059, "step": 223820 }, { "epoch": 53.73, "learning_rate": 2.880088287626741e-05, "loss": 0.0045, "step": 223830 }, { "epoch": 53.73, "learning_rate": 2.8796819250983066e-05, "loss": 0.0076, "step": 223840 }, { "epoch": 53.73, "learning_rate": 2.8792755796450854e-05, "loss": 0.0073, "step": 223850 }, { "epoch": 53.74, "learning_rate": 2.878869251270351e-05, "loss": 0.0029, "step": 223860 }, { "epoch": 53.74, "learning_rate": 2.878462939977375e-05, "loss": 0.0057, "step": 223870 }, { "epoch": 53.74, "learning_rate": 2.87805664576943e-05, "loss": 0.0029, "step": 223880 }, { "epoch": 53.74, "learning_rate": 2.877650368649788e-05, "loss": 0.0026, "step": 223890 }, { "epoch": 53.75, "learning_rate": 2.8772441086217185e-05, "loss": 0.003, "step": 223900 }, { "epoch": 53.75, "learning_rate": 2.8768378656884974e-05, "loss": 0.0021, "step": 223910 }, { "epoch": 53.75, "learning_rate": 2.8764316398533957e-05, "loss": 0.0028, "step": 223920 }, { "epoch": 53.75, "learning_rate": 2.87602543111968e-05, "loss": 0.0061, "step": 223930 }, { "epoch": 53.75, "learning_rate": 2.8756192394906258e-05, "loss": 0.0017, "step": 223940 }, { "epoch": 53.76, "learning_rate": 2.8752130649695037e-05, "loss": 0.0033, "step": 223950 }, { "epoch": 53.76, "learning_rate": 2.874806907559584e-05, "loss": 0.0089, "step": 223960 }, { "epoch": 53.76, "learning_rate": 2.874400767264137e-05, "loss": 0.0034, "step": 223970 }, { "epoch": 53.76, "learning_rate": 2.873994644086435e-05, "loss": 0.0022, "step": 223980 }, { "epoch": 53.77, "learning_rate": 2.8735885380297477e-05, "loss": 0.0021, "step": 223990 }, { "epoch": 53.77, "learning_rate": 2.8731824490973446e-05, "loss": 0.0027, "step": 224000 }, { "epoch": 53.77, "learning_rate": 2.872776377292496e-05, "loss": 0.0047, "step": 224010 }, { "epoch": 53.77, "learning_rate": 2.8723703226184762e-05, "loss": 0.003, "step": 224020 }, { "epoch": 53.77, "learning_rate": 2.87196428507855e-05, "loss": 0.0024, "step": 224030 }, { "epoch": 53.78, "learning_rate": 2.8715582646759875e-05, "loss": 0.0075, "step": 224040 }, { "epoch": 53.78, "learning_rate": 2.8711522614140616e-05, "loss": 0.004, "step": 224050 }, { "epoch": 53.78, "learning_rate": 2.870746275296043e-05, "loss": 0.0031, "step": 224060 }, { "epoch": 53.78, "learning_rate": 2.8703403063251943e-05, "loss": 0.0033, "step": 224070 }, { "epoch": 53.79, "learning_rate": 2.8699343545047906e-05, "loss": 0.0061, "step": 224080 }, { "epoch": 53.79, "learning_rate": 2.8695284198381007e-05, "loss": 0.0062, "step": 224090 }, { "epoch": 53.79, "learning_rate": 2.869122502328392e-05, "loss": 0.0042, "step": 224100 }, { "epoch": 53.79, "learning_rate": 2.868716601978934e-05, "loss": 0.003, "step": 224110 }, { "epoch": 53.8, "learning_rate": 2.868310718792996e-05, "loss": 0.006, "step": 224120 }, { "epoch": 53.8, "learning_rate": 2.867904852773845e-05, "loss": 0.0027, "step": 224130 }, { "epoch": 53.8, "learning_rate": 2.8674990039247497e-05, "loss": 0.0068, "step": 224140 }, { "epoch": 53.8, "learning_rate": 2.8670931722489802e-05, "loss": 0.0035, "step": 224150 }, { "epoch": 53.8, "learning_rate": 2.8666873577498066e-05, "loss": 0.0022, "step": 224160 }, { "epoch": 53.81, "learning_rate": 2.8662815604304916e-05, "loss": 0.0047, "step": 224170 }, { "epoch": 53.81, "learning_rate": 2.865875780294305e-05, "loss": 0.0029, "step": 224180 }, { "epoch": 53.81, "learning_rate": 2.865470017344516e-05, "loss": 0.0037, "step": 224190 }, { "epoch": 53.81, "learning_rate": 2.8650642715843944e-05, "loss": 0.0039, "step": 224200 }, { "epoch": 53.82, "learning_rate": 2.8646585430172008e-05, "loss": 0.0023, "step": 224210 }, { "epoch": 53.82, "learning_rate": 2.8642528316462092e-05, "loss": 0.0035, "step": 224220 }, { "epoch": 53.82, "learning_rate": 2.8638471374746835e-05, "loss": 0.0045, "step": 224230 }, { "epoch": 53.82, "learning_rate": 2.8634414605058924e-05, "loss": 0.0055, "step": 224240 }, { "epoch": 53.83, "learning_rate": 2.8630358007431018e-05, "loss": 0.0033, "step": 224250 }, { "epoch": 53.83, "learning_rate": 2.862630158189579e-05, "loss": 0.0057, "step": 224260 }, { "epoch": 53.83, "learning_rate": 2.8622245328485907e-05, "loss": 0.0029, "step": 224270 }, { "epoch": 53.83, "learning_rate": 2.8618189247234016e-05, "loss": 0.002, "step": 224280 }, { "epoch": 53.83, "learning_rate": 2.8614133338172817e-05, "loss": 0.0038, "step": 224290 }, { "epoch": 53.84, "learning_rate": 2.8610077601334974e-05, "loss": 0.0061, "step": 224300 }, { "epoch": 53.84, "learning_rate": 2.860602203675309e-05, "loss": 0.0076, "step": 224310 }, { "epoch": 53.84, "learning_rate": 2.8601966644459883e-05, "loss": 0.0031, "step": 224320 }, { "epoch": 53.84, "learning_rate": 2.8597911424487993e-05, "loss": 0.0026, "step": 224330 }, { "epoch": 53.85, "learning_rate": 2.8593856376870075e-05, "loss": 0.0049, "step": 224340 }, { "epoch": 53.85, "learning_rate": 2.858980150163879e-05, "loss": 0.0031, "step": 224350 }, { "epoch": 53.85, "learning_rate": 2.858574679882679e-05, "loss": 0.0039, "step": 224360 }, { "epoch": 53.85, "learning_rate": 2.858169226846673e-05, "loss": 0.0045, "step": 224370 }, { "epoch": 53.85, "learning_rate": 2.857763791059123e-05, "loss": 0.0031, "step": 224380 }, { "epoch": 53.86, "learning_rate": 2.8573583725233022e-05, "loss": 0.0019, "step": 224390 }, { "epoch": 53.86, "learning_rate": 2.856952971242467e-05, "loss": 0.0108, "step": 224400 }, { "epoch": 53.86, "learning_rate": 2.856547587219886e-05, "loss": 0.0035, "step": 224410 }, { "epoch": 53.86, "learning_rate": 2.8561422204588212e-05, "loss": 0.0055, "step": 224420 }, { "epoch": 53.87, "learning_rate": 2.855736870962541e-05, "loss": 0.003, "step": 224430 }, { "epoch": 53.87, "learning_rate": 2.85533153873431e-05, "loss": 0.0044, "step": 224440 }, { "epoch": 53.87, "learning_rate": 2.8549262237773855e-05, "loss": 0.0071, "step": 224450 }, { "epoch": 53.87, "learning_rate": 2.854520926095039e-05, "loss": 0.0031, "step": 224460 }, { "epoch": 53.88, "learning_rate": 2.8541156456905316e-05, "loss": 0.0025, "step": 224470 }, { "epoch": 53.88, "learning_rate": 2.8537103825671267e-05, "loss": 0.0151, "step": 224480 }, { "epoch": 53.88, "learning_rate": 2.8533051367280895e-05, "loss": 0.0042, "step": 224490 }, { "epoch": 53.88, "learning_rate": 2.852899908176681e-05, "loss": 0.004, "step": 224500 }, { "epoch": 53.88, "learning_rate": 2.852494696916167e-05, "loss": 0.0103, "step": 224510 }, { "epoch": 53.89, "learning_rate": 2.8520895029498074e-05, "loss": 0.0034, "step": 224520 }, { "epoch": 53.89, "learning_rate": 2.851684326280871e-05, "loss": 0.0039, "step": 224530 }, { "epoch": 53.89, "learning_rate": 2.851279166912616e-05, "loss": 0.0089, "step": 224540 }, { "epoch": 53.89, "learning_rate": 2.8508740248483044e-05, "loss": 0.0081, "step": 224550 }, { "epoch": 53.9, "learning_rate": 2.8504689000912026e-05, "loss": 0.0031, "step": 224560 }, { "epoch": 53.9, "learning_rate": 2.8500637926445716e-05, "loss": 0.0019, "step": 224570 }, { "epoch": 53.9, "learning_rate": 2.849658702511676e-05, "loss": 0.0079, "step": 224580 }, { "epoch": 53.9, "learning_rate": 2.8492536296957717e-05, "loss": 0.0028, "step": 224590 }, { "epoch": 53.91, "learning_rate": 2.848848574200127e-05, "loss": 0.0055, "step": 224600 }, { "epoch": 53.91, "learning_rate": 2.8484435360280016e-05, "loss": 0.0079, "step": 224610 }, { "epoch": 53.91, "learning_rate": 2.848038515182657e-05, "loss": 0.0073, "step": 224620 }, { "epoch": 53.91, "learning_rate": 2.8476335116673557e-05, "loss": 0.0037, "step": 224630 }, { "epoch": 53.91, "learning_rate": 2.8472285254853593e-05, "loss": 0.005, "step": 224640 }, { "epoch": 53.92, "learning_rate": 2.8468235566399282e-05, "loss": 0.0056, "step": 224650 }, { "epoch": 53.92, "learning_rate": 2.8464186051343223e-05, "loss": 0.0088, "step": 224660 }, { "epoch": 53.92, "learning_rate": 2.8460136709718065e-05, "loss": 0.0047, "step": 224670 }, { "epoch": 53.92, "learning_rate": 2.8456087541556418e-05, "loss": 0.0049, "step": 224680 }, { "epoch": 53.93, "learning_rate": 2.8452038546890846e-05, "loss": 0.0051, "step": 224690 }, { "epoch": 53.93, "learning_rate": 2.8447989725753986e-05, "loss": 0.0046, "step": 224700 }, { "epoch": 53.93, "learning_rate": 2.844394107817845e-05, "loss": 0.0031, "step": 224710 }, { "epoch": 53.93, "learning_rate": 2.8439892604196834e-05, "loss": 0.0083, "step": 224720 }, { "epoch": 53.93, "learning_rate": 2.8435844303841736e-05, "loss": 0.0098, "step": 224730 }, { "epoch": 53.94, "learning_rate": 2.843179617714576e-05, "loss": 0.0027, "step": 224740 }, { "epoch": 53.94, "learning_rate": 2.8427748224141503e-05, "loss": 0.0027, "step": 224750 }, { "epoch": 53.94, "learning_rate": 2.8423700444861555e-05, "loss": 0.0122, "step": 224760 }, { "epoch": 53.94, "learning_rate": 2.841965283933856e-05, "loss": 0.0057, "step": 224770 }, { "epoch": 53.95, "learning_rate": 2.841560540760507e-05, "loss": 0.0033, "step": 224780 }, { "epoch": 53.95, "learning_rate": 2.8411558149693662e-05, "loss": 0.0021, "step": 224790 }, { "epoch": 53.95, "learning_rate": 2.8407511065636978e-05, "loss": 0.0022, "step": 224800 }, { "epoch": 54.0, "learning_rate": 2.8403464155467586e-05, "loss": 0.0064, "step": 224810 }, { "epoch": 54.0, "learning_rate": 2.83994174192181e-05, "loss": 0.0057, "step": 224820 }, { "epoch": 54.01, "learning_rate": 2.8395370856921055e-05, "loss": 0.0156, "step": 224830 }, { "epoch": 54.01, "learning_rate": 2.8391324468609082e-05, "loss": 0.0045, "step": 224840 }, { "epoch": 54.01, "learning_rate": 2.838727825431476e-05, "loss": 0.0031, "step": 224850 }, { "epoch": 54.01, "learning_rate": 2.8383232214070664e-05, "loss": 0.0065, "step": 224860 }, { "epoch": 54.02, "learning_rate": 2.8379186347909394e-05, "loss": 0.0061, "step": 224870 }, { "epoch": 54.02, "learning_rate": 2.8375140655863518e-05, "loss": 0.003, "step": 224880 }, { "epoch": 54.02, "learning_rate": 2.8371095137965614e-05, "loss": 0.0024, "step": 224890 }, { "epoch": 54.02, "learning_rate": 2.836704979424825e-05, "loss": 0.0052, "step": 224900 }, { "epoch": 54.02, "learning_rate": 2.8363004624744062e-05, "loss": 0.0028, "step": 224910 }, { "epoch": 54.03, "learning_rate": 2.8358959629485564e-05, "loss": 0.0056, "step": 224920 }, { "epoch": 54.03, "learning_rate": 2.8354914808505335e-05, "loss": 0.0047, "step": 224930 }, { "epoch": 54.03, "learning_rate": 2.835087016183598e-05, "loss": 0.008, "step": 224940 }, { "epoch": 54.03, "learning_rate": 2.834682568951006e-05, "loss": 0.0042, "step": 224950 }, { "epoch": 54.04, "learning_rate": 2.834278139156014e-05, "loss": 0.0096, "step": 224960 }, { "epoch": 54.04, "learning_rate": 2.833873726801879e-05, "loss": 0.0022, "step": 224970 }, { "epoch": 54.04, "learning_rate": 2.8334693318918583e-05, "loss": 0.0028, "step": 224980 }, { "epoch": 54.04, "learning_rate": 2.8330649544292083e-05, "loss": 0.0036, "step": 224990 }, { "epoch": 54.05, "learning_rate": 2.832660594417183e-05, "loss": 0.0093, "step": 225000 }, { "epoch": 54.05, "learning_rate": 2.8322562518590455e-05, "loss": 0.0028, "step": 225010 }, { "epoch": 54.05, "learning_rate": 2.831851926758045e-05, "loss": 0.0025, "step": 225020 }, { "epoch": 54.05, "learning_rate": 2.831447619117441e-05, "loss": 0.0036, "step": 225030 }, { "epoch": 54.05, "learning_rate": 2.8310433289404866e-05, "loss": 0.0118, "step": 225040 }, { "epoch": 54.06, "learning_rate": 2.830639056230443e-05, "loss": 0.0022, "step": 225050 }, { "epoch": 54.06, "learning_rate": 2.8302348009905616e-05, "loss": 0.0089, "step": 225060 }, { "epoch": 54.06, "learning_rate": 2.8298305632240964e-05, "loss": 0.0032, "step": 225070 }, { "epoch": 54.06, "learning_rate": 2.829426342934307e-05, "loss": 0.0027, "step": 225080 }, { "epoch": 54.07, "learning_rate": 2.8290221401244477e-05, "loss": 0.0064, "step": 225090 }, { "epoch": 54.07, "learning_rate": 2.828617954797772e-05, "loss": 0.0015, "step": 225100 }, { "epoch": 54.07, "learning_rate": 2.8282137869575363e-05, "loss": 0.0047, "step": 225110 }, { "epoch": 54.07, "learning_rate": 2.8278096366069946e-05, "loss": 0.0033, "step": 225120 }, { "epoch": 54.07, "learning_rate": 2.827405503749402e-05, "loss": 0.0051, "step": 225130 }, { "epoch": 54.08, "learning_rate": 2.8270013883880105e-05, "loss": 0.004, "step": 225140 }, { "epoch": 54.08, "learning_rate": 2.8265972905260808e-05, "loss": 0.0042, "step": 225150 }, { "epoch": 54.08, "learning_rate": 2.8261932101668608e-05, "loss": 0.0048, "step": 225160 }, { "epoch": 54.08, "learning_rate": 2.8257891473136055e-05, "loss": 0.0033, "step": 225170 }, { "epoch": 54.09, "learning_rate": 2.8253851019695725e-05, "loss": 0.0038, "step": 225180 }, { "epoch": 54.09, "learning_rate": 2.8249810741380155e-05, "loss": 0.0031, "step": 225190 }, { "epoch": 54.09, "learning_rate": 2.824577063822182e-05, "loss": 0.0035, "step": 225200 }, { "epoch": 54.09, "learning_rate": 2.8241730710253318e-05, "loss": 0.0058, "step": 225210 }, { "epoch": 54.1, "learning_rate": 2.8237690957507157e-05, "loss": 0.0027, "step": 225220 }, { "epoch": 54.1, "learning_rate": 2.8233651380015887e-05, "loss": 0.0103, "step": 225230 }, { "epoch": 54.1, "learning_rate": 2.822961197781202e-05, "loss": 0.0065, "step": 225240 }, { "epoch": 54.1, "learning_rate": 2.822557275092809e-05, "loss": 0.0043, "step": 225250 }, { "epoch": 54.1, "learning_rate": 2.8221533699396634e-05, "loss": 0.0029, "step": 225260 }, { "epoch": 54.11, "learning_rate": 2.8217494823250172e-05, "loss": 0.0087, "step": 225270 }, { "epoch": 54.11, "learning_rate": 2.8213456122521215e-05, "loss": 0.0037, "step": 225280 }, { "epoch": 54.11, "learning_rate": 2.820941759724234e-05, "loss": 0.0022, "step": 225290 }, { "epoch": 54.11, "learning_rate": 2.8205379247446017e-05, "loss": 0.005, "step": 225300 }, { "epoch": 54.12, "learning_rate": 2.8201341073164754e-05, "loss": 0.0022, "step": 225310 }, { "epoch": 54.12, "learning_rate": 2.819730307443113e-05, "loss": 0.0091, "step": 225320 }, { "epoch": 54.12, "learning_rate": 2.8193265251277634e-05, "loss": 0.0046, "step": 225330 }, { "epoch": 54.12, "learning_rate": 2.818922760373678e-05, "loss": 0.004, "step": 225340 }, { "epoch": 54.13, "learning_rate": 2.8185190131841087e-05, "loss": 0.0034, "step": 225350 }, { "epoch": 54.13, "learning_rate": 2.8181152835623077e-05, "loss": 0.008, "step": 225360 }, { "epoch": 54.13, "learning_rate": 2.817711571511525e-05, "loss": 0.0093, "step": 225370 }, { "epoch": 54.13, "learning_rate": 2.8173078770350126e-05, "loss": 0.0036, "step": 225380 }, { "epoch": 54.13, "learning_rate": 2.8169042001360202e-05, "loss": 0.007, "step": 225390 }, { "epoch": 54.14, "learning_rate": 2.8165005408178007e-05, "loss": 0.0052, "step": 225400 }, { "epoch": 54.14, "learning_rate": 2.816096899083601e-05, "loss": 0.0036, "step": 225410 }, { "epoch": 54.14, "learning_rate": 2.8156932749366778e-05, "loss": 0.002, "step": 225420 }, { "epoch": 54.14, "learning_rate": 2.815289668380279e-05, "loss": 0.0022, "step": 225430 }, { "epoch": 54.15, "learning_rate": 2.8148860794176507e-05, "loss": 0.0025, "step": 225440 }, { "epoch": 54.15, "learning_rate": 2.814482508052048e-05, "loss": 0.0107, "step": 225450 }, { "epoch": 54.15, "learning_rate": 2.8140789542867197e-05, "loss": 0.0059, "step": 225460 }, { "epoch": 54.15, "learning_rate": 2.813675418124916e-05, "loss": 0.0036, "step": 225470 }, { "epoch": 54.15, "learning_rate": 2.813271899569885e-05, "loss": 0.0185, "step": 225480 }, { "epoch": 54.16, "learning_rate": 2.8128683986248773e-05, "loss": 0.0081, "step": 225490 }, { "epoch": 54.16, "learning_rate": 2.8124649152931425e-05, "loss": 0.0099, "step": 225500 }, { "epoch": 54.16, "learning_rate": 2.812061449577931e-05, "loss": 0.0027, "step": 225510 }, { "epoch": 54.16, "learning_rate": 2.811658001482489e-05, "loss": 0.0041, "step": 225520 }, { "epoch": 54.17, "learning_rate": 2.8112545710100678e-05, "loss": 0.006, "step": 225530 }, { "epoch": 54.17, "learning_rate": 2.8108511581639158e-05, "loss": 0.0136, "step": 225540 }, { "epoch": 54.17, "learning_rate": 2.8104477629472798e-05, "loss": 0.0064, "step": 225550 }, { "epoch": 54.17, "learning_rate": 2.8100443853634116e-05, "loss": 0.0021, "step": 225560 }, { "epoch": 54.18, "learning_rate": 2.8096410254155615e-05, "loss": 0.0026, "step": 225570 }, { "epoch": 54.18, "learning_rate": 2.8092376831069693e-05, "loss": 0.0045, "step": 225580 }, { "epoch": 54.18, "learning_rate": 2.8088343584408916e-05, "loss": 0.0023, "step": 225590 }, { "epoch": 54.18, "learning_rate": 2.8084310514205725e-05, "loss": 0.0022, "step": 225600 }, { "epoch": 54.18, "learning_rate": 2.8080277620492613e-05, "loss": 0.0053, "step": 225610 }, { "epoch": 54.19, "learning_rate": 2.8076244903302045e-05, "loss": 0.0045, "step": 225620 }, { "epoch": 54.19, "learning_rate": 2.8072212362666506e-05, "loss": 0.0112, "step": 225630 }, { "epoch": 54.19, "learning_rate": 2.806817999861847e-05, "loss": 0.0104, "step": 225640 }, { "epoch": 54.19, "learning_rate": 2.806414781119039e-05, "loss": 0.0054, "step": 225650 }, { "epoch": 54.2, "learning_rate": 2.8060115800414778e-05, "loss": 0.0043, "step": 225660 }, { "epoch": 54.2, "learning_rate": 2.8056083966324098e-05, "loss": 0.011, "step": 225670 }, { "epoch": 54.2, "learning_rate": 2.8052052308950782e-05, "loss": 0.0027, "step": 225680 }, { "epoch": 54.2, "learning_rate": 2.80480208283273e-05, "loss": 0.0031, "step": 225690 }, { "epoch": 54.21, "learning_rate": 2.804398952448616e-05, "loss": 0.0055, "step": 225700 }, { "epoch": 54.21, "learning_rate": 2.803995839745982e-05, "loss": 0.0037, "step": 225710 }, { "epoch": 54.21, "learning_rate": 2.8035927447280685e-05, "loss": 0.004, "step": 225720 }, { "epoch": 54.21, "learning_rate": 2.8031896673981284e-05, "loss": 0.0106, "step": 225730 }, { "epoch": 54.21, "learning_rate": 2.8027866077594046e-05, "loss": 0.0093, "step": 225740 }, { "epoch": 54.22, "learning_rate": 2.8023835658151444e-05, "loss": 0.0021, "step": 225750 }, { "epoch": 54.22, "learning_rate": 2.8019805415685918e-05, "loss": 0.0069, "step": 225760 }, { "epoch": 54.22, "learning_rate": 2.8015775350229945e-05, "loss": 0.0031, "step": 225770 }, { "epoch": 54.22, "learning_rate": 2.8011745461815957e-05, "loss": 0.0066, "step": 225780 }, { "epoch": 54.23, "learning_rate": 2.8007715750476403e-05, "loss": 0.0016, "step": 225790 }, { "epoch": 54.23, "learning_rate": 2.8003686216243774e-05, "loss": 0.0065, "step": 225800 }, { "epoch": 54.23, "learning_rate": 2.7999656859150514e-05, "loss": 0.0059, "step": 225810 }, { "epoch": 54.23, "learning_rate": 2.799562767922901e-05, "loss": 0.0069, "step": 225820 }, { "epoch": 54.23, "learning_rate": 2.7991598676511777e-05, "loss": 0.0027, "step": 225830 }, { "epoch": 54.24, "learning_rate": 2.7987569851031236e-05, "loss": 0.0021, "step": 225840 }, { "epoch": 54.24, "learning_rate": 2.798354120281984e-05, "loss": 0.0035, "step": 225850 }, { "epoch": 54.24, "learning_rate": 2.7979512731910024e-05, "loss": 0.0038, "step": 225860 }, { "epoch": 54.24, "learning_rate": 2.797548443833423e-05, "loss": 0.0066, "step": 225870 }, { "epoch": 54.25, "learning_rate": 2.79714563221249e-05, "loss": 0.0028, "step": 225880 }, { "epoch": 54.25, "learning_rate": 2.7967428383314476e-05, "loss": 0.0037, "step": 225890 }, { "epoch": 54.25, "learning_rate": 2.79634006219354e-05, "loss": 0.0065, "step": 225900 }, { "epoch": 54.25, "learning_rate": 2.795937303802009e-05, "loss": 0.0027, "step": 225910 }, { "epoch": 54.26, "learning_rate": 2.7955345631600993e-05, "loss": 0.0022, "step": 225920 }, { "epoch": 54.26, "learning_rate": 2.7951318402710526e-05, "loss": 0.0043, "step": 225930 }, { "epoch": 54.26, "learning_rate": 2.7947291351381154e-05, "loss": 0.0028, "step": 225940 }, { "epoch": 54.26, "learning_rate": 2.794326447764531e-05, "loss": 0.0032, "step": 225950 }, { "epoch": 54.26, "learning_rate": 2.793923778153536e-05, "loss": 0.0031, "step": 225960 }, { "epoch": 54.27, "learning_rate": 2.7935211263083795e-05, "loss": 0.0034, "step": 225970 }, { "epoch": 54.27, "learning_rate": 2.7931184922323017e-05, "loss": 0.002, "step": 225980 }, { "epoch": 54.27, "learning_rate": 2.7927158759285454e-05, "loss": 0.0025, "step": 225990 }, { "epoch": 54.27, "learning_rate": 2.7923132774003536e-05, "loss": 0.0029, "step": 226000 }, { "epoch": 54.28, "learning_rate": 2.7919106966509673e-05, "loss": 0.0043, "step": 226010 }, { "epoch": 54.28, "learning_rate": 2.791508133683629e-05, "loss": 0.0063, "step": 226020 }, { "epoch": 54.28, "learning_rate": 2.7911055885015786e-05, "loss": 0.0038, "step": 226030 }, { "epoch": 54.28, "learning_rate": 2.790703061108064e-05, "loss": 0.0033, "step": 226040 }, { "epoch": 54.29, "learning_rate": 2.7903005515063202e-05, "loss": 0.0042, "step": 226050 }, { "epoch": 54.29, "learning_rate": 2.7898980596995893e-05, "loss": 0.0074, "step": 226060 }, { "epoch": 54.29, "learning_rate": 2.7894955856911164e-05, "loss": 0.0024, "step": 226070 }, { "epoch": 54.29, "learning_rate": 2.7890931294841417e-05, "loss": 0.0034, "step": 226080 }, { "epoch": 54.29, "learning_rate": 2.788690691081906e-05, "loss": 0.0022, "step": 226090 }, { "epoch": 54.3, "learning_rate": 2.7882882704876463e-05, "loss": 0.0031, "step": 226100 }, { "epoch": 54.3, "learning_rate": 2.7878858677046083e-05, "loss": 0.003, "step": 226110 }, { "epoch": 54.3, "learning_rate": 2.78748348273603e-05, "loss": 0.0034, "step": 226120 }, { "epoch": 54.3, "learning_rate": 2.787081115585154e-05, "loss": 0.0029, "step": 226130 }, { "epoch": 54.31, "learning_rate": 2.7866787662552183e-05, "loss": 0.0032, "step": 226140 }, { "epoch": 54.31, "learning_rate": 2.786276434749464e-05, "loss": 0.0057, "step": 226150 }, { "epoch": 54.31, "learning_rate": 2.7858741210711315e-05, "loss": 0.0067, "step": 226160 }, { "epoch": 54.31, "learning_rate": 2.785471825223459e-05, "loss": 0.0053, "step": 226170 }, { "epoch": 54.31, "learning_rate": 2.785069547209691e-05, "loss": 0.0058, "step": 226180 }, { "epoch": 54.32, "learning_rate": 2.7846672870330615e-05, "loss": 0.0036, "step": 226190 }, { "epoch": 54.32, "learning_rate": 2.784265044696811e-05, "loss": 0.0024, "step": 226200 }, { "epoch": 54.32, "learning_rate": 2.783862820204181e-05, "loss": 0.0056, "step": 226210 }, { "epoch": 54.32, "learning_rate": 2.7834606135584102e-05, "loss": 0.0082, "step": 226220 }, { "epoch": 54.33, "learning_rate": 2.783058424762737e-05, "loss": 0.0037, "step": 226230 }, { "epoch": 54.33, "learning_rate": 2.7826562538204004e-05, "loss": 0.0059, "step": 226240 }, { "epoch": 54.33, "learning_rate": 2.7822541007346393e-05, "loss": 0.0041, "step": 226250 }, { "epoch": 54.33, "learning_rate": 2.7818519655086916e-05, "loss": 0.0025, "step": 226260 }, { "epoch": 54.34, "learning_rate": 2.7814498481457953e-05, "loss": 0.0083, "step": 226270 }, { "epoch": 54.34, "learning_rate": 2.7810477486491924e-05, "loss": 0.005, "step": 226280 }, { "epoch": 54.34, "learning_rate": 2.780645667022117e-05, "loss": 0.0033, "step": 226290 }, { "epoch": 54.34, "learning_rate": 2.7802436032678065e-05, "loss": 0.0076, "step": 226300 }, { "epoch": 54.34, "learning_rate": 2.779841557389502e-05, "loss": 0.0028, "step": 226310 }, { "epoch": 54.35, "learning_rate": 2.7794395293904406e-05, "loss": 0.0025, "step": 226320 }, { "epoch": 54.35, "learning_rate": 2.7790375192738616e-05, "loss": 0.0024, "step": 226330 }, { "epoch": 54.35, "learning_rate": 2.7786355270429955e-05, "loss": 0.0069, "step": 226340 }, { "epoch": 54.35, "learning_rate": 2.778233552701086e-05, "loss": 0.0026, "step": 226350 }, { "epoch": 54.36, "learning_rate": 2.777831596251369e-05, "loss": 0.0029, "step": 226360 }, { "epoch": 54.36, "learning_rate": 2.7774296576970805e-05, "loss": 0.0035, "step": 226370 }, { "epoch": 54.36, "learning_rate": 2.7770277370414577e-05, "loss": 0.0029, "step": 226380 }, { "epoch": 54.36, "learning_rate": 2.7766258342877382e-05, "loss": 0.0026, "step": 226390 }, { "epoch": 54.37, "learning_rate": 2.7762239494391573e-05, "loss": 0.0085, "step": 226400 }, { "epoch": 54.37, "learning_rate": 2.77582208249895e-05, "loss": 0.0027, "step": 226410 }, { "epoch": 54.37, "learning_rate": 2.7754202334703583e-05, "loss": 0.0036, "step": 226420 }, { "epoch": 54.37, "learning_rate": 2.7750184023566127e-05, "loss": 0.0022, "step": 226430 }, { "epoch": 54.37, "learning_rate": 2.7746165891609492e-05, "loss": 0.0048, "step": 226440 }, { "epoch": 54.38, "learning_rate": 2.7742147938866076e-05, "loss": 0.0084, "step": 226450 }, { "epoch": 54.38, "learning_rate": 2.7738130165368214e-05, "loss": 0.0048, "step": 226460 }, { "epoch": 54.38, "learning_rate": 2.7734112571148264e-05, "loss": 0.0068, "step": 226470 }, { "epoch": 54.38, "learning_rate": 2.773009515623858e-05, "loss": 0.0067, "step": 226480 }, { "epoch": 54.39, "learning_rate": 2.772607792067151e-05, "loss": 0.0067, "step": 226490 }, { "epoch": 54.39, "learning_rate": 2.7722060864479414e-05, "loss": 0.005, "step": 226500 }, { "epoch": 54.39, "learning_rate": 2.7718043987694642e-05, "loss": 0.0037, "step": 226510 }, { "epoch": 54.39, "learning_rate": 2.771402729034953e-05, "loss": 0.0055, "step": 226520 }, { "epoch": 54.39, "learning_rate": 2.7710010772476434e-05, "loss": 0.0025, "step": 226530 }, { "epoch": 54.4, "learning_rate": 2.77059944341077e-05, "loss": 0.0072, "step": 226540 }, { "epoch": 54.4, "learning_rate": 2.7701978275275652e-05, "loss": 0.0057, "step": 226550 }, { "epoch": 54.4, "learning_rate": 2.7697962296012693e-05, "loss": 0.0031, "step": 226560 }, { "epoch": 54.4, "learning_rate": 2.7693946496351097e-05, "loss": 0.008, "step": 226570 }, { "epoch": 54.41, "learning_rate": 2.768993087632321e-05, "loss": 0.0042, "step": 226580 }, { "epoch": 54.41, "learning_rate": 2.7685915435961417e-05, "loss": 0.005, "step": 226590 }, { "epoch": 54.41, "learning_rate": 2.768190017529802e-05, "loss": 0.0054, "step": 226600 }, { "epoch": 54.41, "learning_rate": 2.7677885094365363e-05, "loss": 0.0059, "step": 226610 }, { "epoch": 54.42, "learning_rate": 2.7673870193195785e-05, "loss": 0.0046, "step": 226620 }, { "epoch": 54.42, "learning_rate": 2.7669855471821605e-05, "loss": 0.0025, "step": 226630 }, { "epoch": 54.42, "learning_rate": 2.7665840930275166e-05, "loss": 0.0016, "step": 226640 }, { "epoch": 54.42, "learning_rate": 2.7661826568588777e-05, "loss": 0.0087, "step": 226650 }, { "epoch": 54.42, "learning_rate": 2.765781238679481e-05, "loss": 0.0068, "step": 226660 }, { "epoch": 54.43, "learning_rate": 2.7653798384925555e-05, "loss": 0.0027, "step": 226670 }, { "epoch": 54.43, "learning_rate": 2.7649784563013327e-05, "loss": 0.0094, "step": 226680 }, { "epoch": 54.43, "learning_rate": 2.7645770921090485e-05, "loss": 0.0058, "step": 226690 }, { "epoch": 54.43, "learning_rate": 2.764175745918936e-05, "loss": 0.0071, "step": 226700 }, { "epoch": 54.44, "learning_rate": 2.7637744177342206e-05, "loss": 0.0131, "step": 226710 }, { "epoch": 54.44, "learning_rate": 2.7633731075581405e-05, "loss": 0.0105, "step": 226720 }, { "epoch": 54.44, "learning_rate": 2.762971815393926e-05, "loss": 0.0047, "step": 226730 }, { "epoch": 54.44, "learning_rate": 2.7625705412448076e-05, "loss": 0.003, "step": 226740 }, { "epoch": 54.45, "learning_rate": 2.762169285114018e-05, "loss": 0.0052, "step": 226750 }, { "epoch": 54.45, "learning_rate": 2.761768047004788e-05, "loss": 0.0058, "step": 226760 }, { "epoch": 54.45, "learning_rate": 2.761366826920349e-05, "loss": 0.0036, "step": 226770 }, { "epoch": 54.45, "learning_rate": 2.760965624863932e-05, "loss": 0.0108, "step": 226780 }, { "epoch": 54.45, "learning_rate": 2.760564440838766e-05, "loss": 0.0032, "step": 226790 }, { "epoch": 54.46, "learning_rate": 2.760163274848088e-05, "loss": 0.003, "step": 226800 }, { "epoch": 54.46, "learning_rate": 2.759762126895121e-05, "loss": 0.003, "step": 226810 }, { "epoch": 54.46, "learning_rate": 2.7593609969830987e-05, "loss": 0.0023, "step": 226820 }, { "epoch": 54.46, "learning_rate": 2.7589598851152525e-05, "loss": 0.0046, "step": 226830 }, { "epoch": 54.47, "learning_rate": 2.758558791294814e-05, "loss": 0.011, "step": 226840 }, { "epoch": 54.47, "learning_rate": 2.758157715525007e-05, "loss": 0.0119, "step": 226850 }, { "epoch": 54.47, "learning_rate": 2.7577566578090675e-05, "loss": 0.0074, "step": 226860 }, { "epoch": 54.47, "learning_rate": 2.7573556181502236e-05, "loss": 0.0035, "step": 226870 }, { "epoch": 54.47, "learning_rate": 2.756954596551704e-05, "loss": 0.0034, "step": 226880 }, { "epoch": 54.48, "learning_rate": 2.7565535930167386e-05, "loss": 0.0074, "step": 226890 }, { "epoch": 54.48, "learning_rate": 2.7561526075485572e-05, "loss": 0.0071, "step": 226900 }, { "epoch": 54.48, "learning_rate": 2.755751640150388e-05, "loss": 0.0059, "step": 226910 }, { "epoch": 54.48, "learning_rate": 2.7553506908254594e-05, "loss": 0.0049, "step": 226920 }, { "epoch": 54.49, "learning_rate": 2.7549497595770035e-05, "loss": 0.0025, "step": 226930 }, { "epoch": 54.49, "learning_rate": 2.754548846408249e-05, "loss": 0.0025, "step": 226940 }, { "epoch": 54.49, "learning_rate": 2.7541479513224205e-05, "loss": 0.0026, "step": 226950 }, { "epoch": 54.49, "learning_rate": 2.7537470743227467e-05, "loss": 0.0053, "step": 226960 }, { "epoch": 54.5, "learning_rate": 2.75334621541246e-05, "loss": 0.0025, "step": 226970 }, { "epoch": 54.5, "learning_rate": 2.7529453745947865e-05, "loss": 0.0053, "step": 226980 }, { "epoch": 54.5, "learning_rate": 2.7525445518729532e-05, "loss": 0.0046, "step": 226990 }, { "epoch": 54.5, "learning_rate": 2.75214374725019e-05, "loss": 0.0054, "step": 227000 }, { "epoch": 54.5, "learning_rate": 2.751742960729723e-05, "loss": 0.0044, "step": 227010 }, { "epoch": 54.51, "learning_rate": 2.7513421923147803e-05, "loss": 0.0057, "step": 227020 }, { "epoch": 54.51, "learning_rate": 2.7509414420085898e-05, "loss": 0.0055, "step": 227030 }, { "epoch": 54.51, "learning_rate": 2.7505407098143775e-05, "loss": 0.0047, "step": 227040 }, { "epoch": 54.51, "learning_rate": 2.7501399957353725e-05, "loss": 0.0023, "step": 227050 }, { "epoch": 54.52, "learning_rate": 2.7497392997747983e-05, "loss": 0.0026, "step": 227060 }, { "epoch": 54.52, "learning_rate": 2.7493386219358862e-05, "loss": 0.0035, "step": 227070 }, { "epoch": 54.52, "learning_rate": 2.7489379622218627e-05, "loss": 0.0051, "step": 227080 }, { "epoch": 54.52, "learning_rate": 2.7485373206359488e-05, "loss": 0.0032, "step": 227090 }, { "epoch": 54.53, "learning_rate": 2.748136697181376e-05, "loss": 0.0037, "step": 227100 }, { "epoch": 54.53, "learning_rate": 2.7477360918613702e-05, "loss": 0.0057, "step": 227110 }, { "epoch": 54.53, "learning_rate": 2.747335504679156e-05, "loss": 0.008, "step": 227120 }, { "epoch": 54.53, "learning_rate": 2.7469349356379604e-05, "loss": 0.0106, "step": 227130 }, { "epoch": 54.53, "learning_rate": 2.7465343847410084e-05, "loss": 0.0097, "step": 227140 }, { "epoch": 54.54, "learning_rate": 2.746133851991527e-05, "loss": 0.009, "step": 227150 }, { "epoch": 54.54, "learning_rate": 2.7457333373927373e-05, "loss": 0.0054, "step": 227160 }, { "epoch": 54.54, "learning_rate": 2.745332840947872e-05, "loss": 0.0025, "step": 227170 }, { "epoch": 54.54, "learning_rate": 2.744932362660153e-05, "loss": 0.0032, "step": 227180 }, { "epoch": 54.55, "learning_rate": 2.7445319025328042e-05, "loss": 0.0074, "step": 227190 }, { "epoch": 54.55, "learning_rate": 2.7441314605690488e-05, "loss": 0.0069, "step": 227200 }, { "epoch": 54.55, "learning_rate": 2.7437310367721163e-05, "loss": 0.0041, "step": 227210 }, { "epoch": 54.55, "learning_rate": 2.743330631145231e-05, "loss": 0.0053, "step": 227220 }, { "epoch": 54.55, "learning_rate": 2.7429302436916125e-05, "loss": 0.0036, "step": 227230 }, { "epoch": 54.56, "learning_rate": 2.74252987441449e-05, "loss": 0.0032, "step": 227240 }, { "epoch": 54.56, "learning_rate": 2.7421295233170858e-05, "loss": 0.0023, "step": 227250 }, { "epoch": 54.56, "learning_rate": 2.7417291904026245e-05, "loss": 0.0025, "step": 227260 }, { "epoch": 54.56, "learning_rate": 2.7413288756743295e-05, "loss": 0.003, "step": 227270 }, { "epoch": 54.57, "learning_rate": 2.740928579135425e-05, "loss": 0.0044, "step": 227280 }, { "epoch": 54.57, "learning_rate": 2.7405283007891345e-05, "loss": 0.0026, "step": 227290 }, { "epoch": 54.57, "learning_rate": 2.7401280406386798e-05, "loss": 0.0018, "step": 227300 }, { "epoch": 54.57, "learning_rate": 2.7397277986872883e-05, "loss": 0.0057, "step": 227310 }, { "epoch": 54.58, "learning_rate": 2.7393275749381818e-05, "loss": 0.0034, "step": 227320 }, { "epoch": 54.58, "learning_rate": 2.7389273693945794e-05, "loss": 0.0079, "step": 227330 }, { "epoch": 54.58, "learning_rate": 2.7385271820597087e-05, "loss": 0.0023, "step": 227340 }, { "epoch": 54.58, "learning_rate": 2.7381270129367907e-05, "loss": 0.0029, "step": 227350 }, { "epoch": 54.58, "learning_rate": 2.7377268620290486e-05, "loss": 0.0091, "step": 227360 }, { "epoch": 54.59, "learning_rate": 2.7373267293397038e-05, "loss": 0.0042, "step": 227370 }, { "epoch": 54.59, "learning_rate": 2.7369266148719798e-05, "loss": 0.0027, "step": 227380 }, { "epoch": 54.59, "learning_rate": 2.736526518629098e-05, "loss": 0.0115, "step": 227390 }, { "epoch": 54.59, "learning_rate": 2.73612644061428e-05, "loss": 0.0051, "step": 227400 }, { "epoch": 54.6, "learning_rate": 2.7357263808307487e-05, "loss": 0.0019, "step": 227410 }, { "epoch": 54.6, "learning_rate": 2.7353263392817262e-05, "loss": 0.0067, "step": 227420 }, { "epoch": 54.6, "learning_rate": 2.7349263159704323e-05, "loss": 0.0025, "step": 227430 }, { "epoch": 54.6, "learning_rate": 2.7345263109000885e-05, "loss": 0.0018, "step": 227440 }, { "epoch": 54.61, "learning_rate": 2.734126324073918e-05, "loss": 0.0035, "step": 227450 }, { "epoch": 54.61, "learning_rate": 2.7337263554951442e-05, "loss": 0.0041, "step": 227460 }, { "epoch": 54.61, "learning_rate": 2.73332640516698e-05, "loss": 0.0033, "step": 227470 }, { "epoch": 54.61, "learning_rate": 2.7329264730926534e-05, "loss": 0.0028, "step": 227480 }, { "epoch": 54.61, "learning_rate": 2.7325265592753834e-05, "loss": 0.0023, "step": 227490 }, { "epoch": 54.62, "learning_rate": 2.7321266637183895e-05, "loss": 0.0056, "step": 227500 }, { "epoch": 54.62, "learning_rate": 2.731726786424893e-05, "loss": 0.0043, "step": 227510 }, { "epoch": 54.62, "learning_rate": 2.7313269273981135e-05, "loss": 0.0023, "step": 227520 }, { "epoch": 54.62, "learning_rate": 2.7309270866412716e-05, "loss": 0.0044, "step": 227530 }, { "epoch": 54.63, "learning_rate": 2.730527264157585e-05, "loss": 0.002, "step": 227540 }, { "epoch": 54.63, "learning_rate": 2.7301274599502803e-05, "loss": 0.0053, "step": 227550 }, { "epoch": 54.63, "learning_rate": 2.7297276740225696e-05, "loss": 0.0049, "step": 227560 }, { "epoch": 54.63, "learning_rate": 2.7293279063776744e-05, "loss": 0.0088, "step": 227570 }, { "epoch": 54.63, "learning_rate": 2.7289281570188165e-05, "loss": 0.0043, "step": 227580 }, { "epoch": 54.64, "learning_rate": 2.728528425949214e-05, "loss": 0.0054, "step": 227590 }, { "epoch": 54.64, "learning_rate": 2.7281287131720867e-05, "loss": 0.0024, "step": 227600 }, { "epoch": 54.64, "learning_rate": 2.7277290186906497e-05, "loss": 0.0049, "step": 227610 }, { "epoch": 54.64, "learning_rate": 2.7273293425081258e-05, "loss": 0.0035, "step": 227620 }, { "epoch": 54.65, "learning_rate": 2.7269296846277332e-05, "loss": 0.0067, "step": 227630 }, { "epoch": 54.65, "learning_rate": 2.726530045052689e-05, "loss": 0.0158, "step": 227640 }, { "epoch": 54.65, "learning_rate": 2.726130423786213e-05, "loss": 0.0038, "step": 227650 }, { "epoch": 54.65, "learning_rate": 2.725730820831522e-05, "loss": 0.0045, "step": 227660 }, { "epoch": 54.66, "learning_rate": 2.725331236191835e-05, "loss": 0.0055, "step": 227670 }, { "epoch": 54.66, "learning_rate": 2.724931669870367e-05, "loss": 0.0059, "step": 227680 }, { "epoch": 54.66, "learning_rate": 2.7245321218703425e-05, "loss": 0.0034, "step": 227690 }, { "epoch": 54.66, "learning_rate": 2.7241325921949733e-05, "loss": 0.0039, "step": 227700 }, { "epoch": 54.66, "learning_rate": 2.723733080847477e-05, "loss": 0.0026, "step": 227710 }, { "epoch": 54.67, "learning_rate": 2.7233335878310738e-05, "loss": 0.0036, "step": 227720 }, { "epoch": 54.67, "learning_rate": 2.7229341131489792e-05, "loss": 0.0051, "step": 227730 }, { "epoch": 54.67, "learning_rate": 2.7225346568044114e-05, "loss": 0.0021, "step": 227740 }, { "epoch": 54.67, "learning_rate": 2.7221352188005856e-05, "loss": 0.0033, "step": 227750 }, { "epoch": 54.68, "learning_rate": 2.72173579914072e-05, "loss": 0.0049, "step": 227760 }, { "epoch": 54.68, "learning_rate": 2.7213363978280304e-05, "loss": 0.0085, "step": 227770 }, { "epoch": 54.68, "learning_rate": 2.7209370148657313e-05, "loss": 0.0073, "step": 227780 }, { "epoch": 54.68, "learning_rate": 2.720537650257045e-05, "loss": 0.0035, "step": 227790 }, { "epoch": 54.69, "learning_rate": 2.720138304005182e-05, "loss": 0.0105, "step": 227800 }, { "epoch": 54.69, "learning_rate": 2.7197389761133572e-05, "loss": 0.0034, "step": 227810 }, { "epoch": 54.69, "learning_rate": 2.7193396665847926e-05, "loss": 0.0028, "step": 227820 }, { "epoch": 54.69, "learning_rate": 2.7189403754226995e-05, "loss": 0.0076, "step": 227830 }, { "epoch": 54.69, "learning_rate": 2.7185411026302964e-05, "loss": 0.0021, "step": 227840 }, { "epoch": 54.7, "learning_rate": 2.7181418482107934e-05, "loss": 0.0052, "step": 227850 }, { "epoch": 54.7, "learning_rate": 2.717742612167411e-05, "loss": 0.0036, "step": 227860 }, { "epoch": 54.7, "learning_rate": 2.7173433945033622e-05, "loss": 0.0033, "step": 227870 }, { "epoch": 54.7, "learning_rate": 2.716944195221862e-05, "loss": 0.0144, "step": 227880 }, { "epoch": 54.71, "learning_rate": 2.7165450143261263e-05, "loss": 0.0023, "step": 227890 }, { "epoch": 54.71, "learning_rate": 2.716145851819368e-05, "loss": 0.0096, "step": 227900 }, { "epoch": 54.71, "learning_rate": 2.7157467077048026e-05, "loss": 0.0042, "step": 227910 }, { "epoch": 54.71, "learning_rate": 2.7153475819856422e-05, "loss": 0.0087, "step": 227920 }, { "epoch": 54.71, "learning_rate": 2.714948474665107e-05, "loss": 0.0067, "step": 227930 }, { "epoch": 54.72, "learning_rate": 2.7145493857464053e-05, "loss": 0.0054, "step": 227940 }, { "epoch": 54.72, "learning_rate": 2.7141503152327518e-05, "loss": 0.0067, "step": 227950 }, { "epoch": 54.72, "learning_rate": 2.7137512631273627e-05, "loss": 0.0041, "step": 227960 }, { "epoch": 54.72, "learning_rate": 2.71335222943345e-05, "loss": 0.0063, "step": 227970 }, { "epoch": 54.73, "learning_rate": 2.712953214154228e-05, "loss": 0.0044, "step": 227980 }, { "epoch": 54.73, "learning_rate": 2.7125542172929096e-05, "loss": 0.0094, "step": 227990 }, { "epoch": 54.73, "learning_rate": 2.712155238852707e-05, "loss": 0.0048, "step": 228000 }, { "epoch": 54.73, "learning_rate": 2.711756278836835e-05, "loss": 0.0025, "step": 228010 }, { "epoch": 54.74, "learning_rate": 2.7113573372485056e-05, "loss": 0.0035, "step": 228020 }, { "epoch": 54.74, "learning_rate": 2.710958414090931e-05, "loss": 0.0048, "step": 228030 }, { "epoch": 54.74, "learning_rate": 2.7105595093673248e-05, "loss": 0.0032, "step": 228040 }, { "epoch": 54.74, "learning_rate": 2.7101606230808985e-05, "loss": 0.0078, "step": 228050 }, { "epoch": 54.74, "learning_rate": 2.7097617552348633e-05, "loss": 0.0051, "step": 228060 }, { "epoch": 54.75, "learning_rate": 2.7093629058324365e-05, "loss": 0.0031, "step": 228070 }, { "epoch": 54.75, "learning_rate": 2.7089640748768247e-05, "loss": 0.004, "step": 228080 }, { "epoch": 54.75, "learning_rate": 2.708565262371239e-05, "loss": 0.0041, "step": 228090 }, { "epoch": 54.75, "learning_rate": 2.708166468318897e-05, "loss": 0.0033, "step": 228100 }, { "epoch": 54.76, "learning_rate": 2.7077676927230055e-05, "loss": 0.0312, "step": 228110 }, { "epoch": 54.76, "learning_rate": 2.7073689355867772e-05, "loss": 0.0031, "step": 228120 }, { "epoch": 54.76, "learning_rate": 2.7069701969134243e-05, "loss": 0.0038, "step": 228130 }, { "epoch": 54.76, "learning_rate": 2.7065714767061557e-05, "loss": 0.0124, "step": 228140 }, { "epoch": 54.77, "learning_rate": 2.7061727749681847e-05, "loss": 0.0035, "step": 228150 }, { "epoch": 54.77, "learning_rate": 2.7057740917027186e-05, "loss": 0.0158, "step": 228160 }, { "epoch": 54.77, "learning_rate": 2.705375426912975e-05, "loss": 0.0094, "step": 228170 }, { "epoch": 54.77, "learning_rate": 2.704976780602157e-05, "loss": 0.0021, "step": 228180 }, { "epoch": 54.77, "learning_rate": 2.7045781527734766e-05, "loss": 0.0046, "step": 228190 }, { "epoch": 54.78, "learning_rate": 2.7041795434301465e-05, "loss": 0.0039, "step": 228200 }, { "epoch": 54.78, "learning_rate": 2.7037809525753776e-05, "loss": 0.0027, "step": 228210 }, { "epoch": 54.78, "learning_rate": 2.7033823802123746e-05, "loss": 0.0034, "step": 228220 }, { "epoch": 54.78, "learning_rate": 2.702983826344352e-05, "loss": 0.0026, "step": 228230 }, { "epoch": 54.79, "learning_rate": 2.7025852909745176e-05, "loss": 0.0024, "step": 228240 }, { "epoch": 54.79, "learning_rate": 2.7021867741060804e-05, "loss": 0.0074, "step": 228250 }, { "epoch": 54.79, "learning_rate": 2.7017882757422508e-05, "loss": 0.0038, "step": 228260 }, { "epoch": 54.79, "learning_rate": 2.7013897958862378e-05, "loss": 0.0032, "step": 228270 }, { "epoch": 54.79, "learning_rate": 2.7009913345412497e-05, "loss": 0.0029, "step": 228280 }, { "epoch": 54.8, "learning_rate": 2.7005928917104962e-05, "loss": 0.0042, "step": 228290 }, { "epoch": 54.8, "learning_rate": 2.7001944673971834e-05, "loss": 0.0042, "step": 228300 }, { "epoch": 54.8, "learning_rate": 2.699796061604526e-05, "loss": 0.0106, "step": 228310 }, { "epoch": 54.8, "learning_rate": 2.6993976743357264e-05, "loss": 0.0034, "step": 228320 }, { "epoch": 54.81, "learning_rate": 2.698999305593993e-05, "loss": 0.0029, "step": 228330 }, { "epoch": 54.81, "learning_rate": 2.6986009553825388e-05, "loss": 0.0094, "step": 228340 }, { "epoch": 54.81, "learning_rate": 2.69820262370457e-05, "loss": 0.0052, "step": 228350 }, { "epoch": 54.81, "learning_rate": 2.697804310563289e-05, "loss": 0.0029, "step": 228360 }, { "epoch": 54.82, "learning_rate": 2.6974060159619097e-05, "loss": 0.0087, "step": 228370 }, { "epoch": 54.82, "learning_rate": 2.6970077399036376e-05, "loss": 0.005, "step": 228380 }, { "epoch": 54.82, "learning_rate": 2.696609482391681e-05, "loss": 0.0071, "step": 228390 }, { "epoch": 54.82, "learning_rate": 2.6962112434292454e-05, "loss": 0.0021, "step": 228400 }, { "epoch": 54.82, "learning_rate": 2.695813023019539e-05, "loss": 0.0118, "step": 228410 }, { "epoch": 54.83, "learning_rate": 2.6954148211657682e-05, "loss": 0.0038, "step": 228420 }, { "epoch": 54.83, "learning_rate": 2.6950166378711384e-05, "loss": 0.0041, "step": 228430 }, { "epoch": 54.83, "learning_rate": 2.6946184731388602e-05, "loss": 0.0031, "step": 228440 }, { "epoch": 54.83, "learning_rate": 2.694220326972139e-05, "loss": 0.007, "step": 228450 }, { "epoch": 54.84, "learning_rate": 2.6938221993741774e-05, "loss": 0.0053, "step": 228460 }, { "epoch": 54.84, "learning_rate": 2.6934240903481835e-05, "loss": 0.0031, "step": 228470 }, { "epoch": 54.84, "learning_rate": 2.6930259998973646e-05, "loss": 0.0031, "step": 228480 }, { "epoch": 54.84, "learning_rate": 2.6926279280249263e-05, "loss": 0.0025, "step": 228490 }, { "epoch": 54.85, "learning_rate": 2.6922298747340736e-05, "loss": 0.003, "step": 228500 }, { "epoch": 54.85, "learning_rate": 2.6918318400280122e-05, "loss": 0.0026, "step": 228510 }, { "epoch": 54.85, "learning_rate": 2.691433823909948e-05, "loss": 0.0052, "step": 228520 }, { "epoch": 54.85, "learning_rate": 2.691035826383086e-05, "loss": 0.015, "step": 228530 }, { "epoch": 54.85, "learning_rate": 2.6906378474506312e-05, "loss": 0.0026, "step": 228540 }, { "epoch": 54.86, "learning_rate": 2.6902398871157885e-05, "loss": 0.0022, "step": 228550 }, { "epoch": 54.86, "learning_rate": 2.689841945381763e-05, "loss": 0.0025, "step": 228560 }, { "epoch": 54.86, "learning_rate": 2.689444022251757e-05, "loss": 0.0026, "step": 228570 }, { "epoch": 54.86, "learning_rate": 2.6890461177289796e-05, "loss": 0.0044, "step": 228580 }, { "epoch": 54.87, "learning_rate": 2.688648231816635e-05, "loss": 0.0037, "step": 228590 }, { "epoch": 54.87, "learning_rate": 2.688250364517921e-05, "loss": 0.0029, "step": 228600 }, { "epoch": 54.87, "learning_rate": 2.687852515836048e-05, "loss": 0.0042, "step": 228610 }, { "epoch": 54.87, "learning_rate": 2.687454685774218e-05, "loss": 0.0112, "step": 228620 }, { "epoch": 54.87, "learning_rate": 2.6870568743356344e-05, "loss": 0.0027, "step": 228630 }, { "epoch": 54.88, "learning_rate": 2.6866590815235016e-05, "loss": 0.0021, "step": 228640 }, { "epoch": 54.88, "learning_rate": 2.686261307341022e-05, "loss": 0.0026, "step": 228650 }, { "epoch": 54.88, "learning_rate": 2.6858635517914e-05, "loss": 0.0044, "step": 228660 }, { "epoch": 54.88, "learning_rate": 2.6854658148778356e-05, "loss": 0.0018, "step": 228670 }, { "epoch": 54.89, "learning_rate": 2.685068096603539e-05, "loss": 0.0033, "step": 228680 }, { "epoch": 54.89, "learning_rate": 2.6846703969717067e-05, "loss": 0.0032, "step": 228690 }, { "epoch": 54.89, "learning_rate": 2.6842727159855436e-05, "loss": 0.0014, "step": 228700 }, { "epoch": 54.89, "learning_rate": 2.6838750536482498e-05, "loss": 0.0048, "step": 228710 }, { "epoch": 54.9, "learning_rate": 2.683477409963032e-05, "loss": 0.0034, "step": 228720 }, { "epoch": 54.9, "learning_rate": 2.6830797849330923e-05, "loss": 0.0023, "step": 228730 }, { "epoch": 54.9, "learning_rate": 2.6826821785616268e-05, "loss": 0.0109, "step": 228740 }, { "epoch": 54.9, "learning_rate": 2.6822845908518442e-05, "loss": 0.0112, "step": 228750 }, { "epoch": 54.9, "learning_rate": 2.681887021806943e-05, "loss": 0.0048, "step": 228760 }, { "epoch": 54.91, "learning_rate": 2.6814894714301265e-05, "loss": 0.0037, "step": 228770 }, { "epoch": 54.91, "learning_rate": 2.681091939724595e-05, "loss": 0.0028, "step": 228780 }, { "epoch": 54.91, "learning_rate": 2.6806944266935497e-05, "loss": 0.0034, "step": 228790 }, { "epoch": 54.91, "learning_rate": 2.680296932340193e-05, "loss": 0.0078, "step": 228800 }, { "epoch": 54.92, "learning_rate": 2.679899456667723e-05, "loss": 0.0083, "step": 228810 }, { "epoch": 54.92, "learning_rate": 2.6795019996793453e-05, "loss": 0.0016, "step": 228820 }, { "epoch": 54.92, "learning_rate": 2.6791045613782606e-05, "loss": 0.0061, "step": 228830 }, { "epoch": 54.92, "learning_rate": 2.6787071417676622e-05, "loss": 0.0082, "step": 228840 }, { "epoch": 54.93, "learning_rate": 2.6783097408507585e-05, "loss": 0.002, "step": 228850 }, { "epoch": 54.93, "learning_rate": 2.6779123586307474e-05, "loss": 0.003, "step": 228860 }, { "epoch": 54.93, "learning_rate": 2.6775149951108303e-05, "loss": 0.0084, "step": 228870 }, { "epoch": 54.93, "learning_rate": 2.6771176502942007e-05, "loss": 0.0158, "step": 228880 }, { "epoch": 54.93, "learning_rate": 2.6767203241840664e-05, "loss": 0.004, "step": 228890 }, { "epoch": 54.94, "learning_rate": 2.6763230167836238e-05, "loss": 0.0044, "step": 228900 }, { "epoch": 54.94, "learning_rate": 2.6759257280960726e-05, "loss": 0.0041, "step": 228910 }, { "epoch": 54.94, "learning_rate": 2.6755284581246132e-05, "loss": 0.0027, "step": 228920 }, { "epoch": 54.94, "learning_rate": 2.6751312068724434e-05, "loss": 0.0045, "step": 228930 }, { "epoch": 54.95, "learning_rate": 2.6747339743427625e-05, "loss": 0.0049, "step": 228940 }, { "epoch": 54.95, "learning_rate": 2.674336760538768e-05, "loss": 0.0049, "step": 228950 }, { "epoch": 54.95, "learning_rate": 2.6739395654636633e-05, "loss": 0.0023, "step": 228960 }, { "epoch": 55.0, "learning_rate": 2.673542389120646e-05, "loss": 0.0021, "step": 228970 }, { "epoch": 55.0, "learning_rate": 2.673145231512909e-05, "loss": 0.0065, "step": 228980 }, { "epoch": 55.01, "learning_rate": 2.6727480926436567e-05, "loss": 0.0051, "step": 228990 }, { "epoch": 55.01, "learning_rate": 2.6723509725160855e-05, "loss": 0.0026, "step": 229000 }, { "epoch": 55.01, "learning_rate": 2.6719538711333937e-05, "loss": 0.0019, "step": 229010 }, { "epoch": 55.01, "learning_rate": 2.671556788498778e-05, "loss": 0.0082, "step": 229020 }, { "epoch": 55.01, "learning_rate": 2.6711597246154373e-05, "loss": 0.0029, "step": 229030 }, { "epoch": 55.02, "learning_rate": 2.670762679486568e-05, "loss": 0.0027, "step": 229040 }, { "epoch": 55.02, "learning_rate": 2.6703656531153676e-05, "loss": 0.0051, "step": 229050 }, { "epoch": 55.02, "learning_rate": 2.6699686455050378e-05, "loss": 0.002, "step": 229060 }, { "epoch": 55.02, "learning_rate": 2.6695716566587704e-05, "loss": 0.002, "step": 229070 }, { "epoch": 55.03, "learning_rate": 2.6691746865797617e-05, "loss": 0.0034, "step": 229080 }, { "epoch": 55.03, "learning_rate": 2.6687777352712135e-05, "loss": 0.0037, "step": 229090 }, { "epoch": 55.03, "learning_rate": 2.6683808027363198e-05, "loss": 0.003, "step": 229100 }, { "epoch": 55.03, "learning_rate": 2.6679838889782794e-05, "loss": 0.0028, "step": 229110 }, { "epoch": 55.04, "learning_rate": 2.6675869940002828e-05, "loss": 0.0017, "step": 229120 }, { "epoch": 55.04, "learning_rate": 2.6671901178055318e-05, "loss": 0.0041, "step": 229130 }, { "epoch": 55.04, "learning_rate": 2.666793260397221e-05, "loss": 0.0033, "step": 229140 }, { "epoch": 55.04, "learning_rate": 2.6663964217785465e-05, "loss": 0.0052, "step": 229150 }, { "epoch": 55.04, "learning_rate": 2.6659996019527035e-05, "loss": 0.0025, "step": 229160 }, { "epoch": 55.05, "learning_rate": 2.6656028009228885e-05, "loss": 0.0156, "step": 229170 }, { "epoch": 55.05, "learning_rate": 2.6652060186922955e-05, "loss": 0.0032, "step": 229180 }, { "epoch": 55.05, "learning_rate": 2.6648092552641196e-05, "loss": 0.0079, "step": 229190 }, { "epoch": 55.05, "learning_rate": 2.664412510641561e-05, "loss": 0.0064, "step": 229200 }, { "epoch": 55.06, "learning_rate": 2.664015784827808e-05, "loss": 0.0043, "step": 229210 }, { "epoch": 55.06, "learning_rate": 2.6636190778260574e-05, "loss": 0.0029, "step": 229220 }, { "epoch": 55.06, "learning_rate": 2.663222389639507e-05, "loss": 0.0071, "step": 229230 }, { "epoch": 55.06, "learning_rate": 2.6628257202713486e-05, "loss": 0.0081, "step": 229240 }, { "epoch": 55.07, "learning_rate": 2.662429069724778e-05, "loss": 0.009, "step": 229250 }, { "epoch": 55.07, "learning_rate": 2.6620324380029882e-05, "loss": 0.0026, "step": 229260 }, { "epoch": 55.07, "learning_rate": 2.6616358251091743e-05, "loss": 0.0026, "step": 229270 }, { "epoch": 55.07, "learning_rate": 2.6612392310465294e-05, "loss": 0.0045, "step": 229280 }, { "epoch": 55.07, "learning_rate": 2.6608426558182463e-05, "loss": 0.0026, "step": 229290 }, { "epoch": 55.08, "learning_rate": 2.660446099427525e-05, "loss": 0.0027, "step": 229300 }, { "epoch": 55.08, "learning_rate": 2.660049561877551e-05, "loss": 0.0023, "step": 229310 }, { "epoch": 55.08, "learning_rate": 2.6596530431715218e-05, "loss": 0.005, "step": 229320 }, { "epoch": 55.08, "learning_rate": 2.659256543312627e-05, "loss": 0.006, "step": 229330 }, { "epoch": 55.09, "learning_rate": 2.6588600623040673e-05, "loss": 0.0023, "step": 229340 }, { "epoch": 55.09, "learning_rate": 2.658463600149028e-05, "loss": 0.0061, "step": 229350 }, { "epoch": 55.09, "learning_rate": 2.6580671568507032e-05, "loss": 0.011, "step": 229360 }, { "epoch": 55.09, "learning_rate": 2.6576707324122885e-05, "loss": 0.0028, "step": 229370 }, { "epoch": 55.09, "learning_rate": 2.6572743268369743e-05, "loss": 0.004, "step": 229380 }, { "epoch": 55.1, "learning_rate": 2.6568779401279543e-05, "loss": 0.0067, "step": 229390 }, { "epoch": 55.1, "learning_rate": 2.656481572288419e-05, "loss": 0.0022, "step": 229400 }, { "epoch": 55.1, "learning_rate": 2.6560852233215615e-05, "loss": 0.0036, "step": 229410 }, { "epoch": 55.1, "learning_rate": 2.6556888932305733e-05, "loss": 0.002, "step": 229420 }, { "epoch": 55.11, "learning_rate": 2.655292582018644e-05, "loss": 0.0022, "step": 229430 }, { "epoch": 55.11, "learning_rate": 2.654896289688972e-05, "loss": 0.0028, "step": 229440 }, { "epoch": 55.11, "learning_rate": 2.6545000162447408e-05, "loss": 0.0099, "step": 229450 }, { "epoch": 55.11, "learning_rate": 2.654103761689143e-05, "loss": 0.0048, "step": 229460 }, { "epoch": 55.12, "learning_rate": 2.653707526025374e-05, "loss": 0.0042, "step": 229470 }, { "epoch": 55.12, "learning_rate": 2.653311309256622e-05, "loss": 0.0016, "step": 229480 }, { "epoch": 55.12, "learning_rate": 2.6529151113860774e-05, "loss": 0.0054, "step": 229490 }, { "epoch": 55.12, "learning_rate": 2.652518932416932e-05, "loss": 0.0087, "step": 229500 }, { "epoch": 55.12, "learning_rate": 2.6521227723523756e-05, "loss": 0.0138, "step": 229510 }, { "epoch": 55.13, "learning_rate": 2.651726631195599e-05, "loss": 0.0069, "step": 229520 }, { "epoch": 55.13, "learning_rate": 2.651330508949792e-05, "loss": 0.0031, "step": 229530 }, { "epoch": 55.13, "learning_rate": 2.650934405618144e-05, "loss": 0.0017, "step": 229540 }, { "epoch": 55.13, "learning_rate": 2.6505383212038465e-05, "loss": 0.0156, "step": 229550 }, { "epoch": 55.14, "learning_rate": 2.6501422557100874e-05, "loss": 0.0034, "step": 229560 }, { "epoch": 55.14, "learning_rate": 2.649746209140056e-05, "loss": 0.0051, "step": 229570 }, { "epoch": 55.14, "learning_rate": 2.6493501814969463e-05, "loss": 0.003, "step": 229580 }, { "epoch": 55.14, "learning_rate": 2.6489541727839416e-05, "loss": 0.0056, "step": 229590 }, { "epoch": 55.15, "learning_rate": 2.6485581830042328e-05, "loss": 0.0059, "step": 229600 }, { "epoch": 55.15, "learning_rate": 2.6481622121610107e-05, "loss": 0.0034, "step": 229610 }, { "epoch": 55.15, "learning_rate": 2.6477662602574633e-05, "loss": 0.0018, "step": 229620 }, { "epoch": 55.15, "learning_rate": 2.6473703272967787e-05, "loss": 0.0072, "step": 229630 }, { "epoch": 55.15, "learning_rate": 2.646974413282146e-05, "loss": 0.0049, "step": 229640 }, { "epoch": 55.16, "learning_rate": 2.6465785182167523e-05, "loss": 0.0021, "step": 229650 }, { "epoch": 55.16, "learning_rate": 2.6461826421037878e-05, "loss": 0.0033, "step": 229660 }, { "epoch": 55.16, "learning_rate": 2.6457867849464392e-05, "loss": 0.0028, "step": 229670 }, { "epoch": 55.16, "learning_rate": 2.6453909467478943e-05, "loss": 0.0088, "step": 229680 }, { "epoch": 55.17, "learning_rate": 2.6449951275113416e-05, "loss": 0.007, "step": 229690 }, { "epoch": 55.17, "learning_rate": 2.644599327239966e-05, "loss": 0.003, "step": 229700 }, { "epoch": 55.17, "learning_rate": 2.644203545936959e-05, "loss": 0.0061, "step": 229710 }, { "epoch": 55.17, "learning_rate": 2.6438077836055086e-05, "loss": 0.0042, "step": 229720 }, { "epoch": 55.17, "learning_rate": 2.643412040248795e-05, "loss": 0.009, "step": 229730 }, { "epoch": 55.18, "learning_rate": 2.6430163158700115e-05, "loss": 0.0077, "step": 229740 }, { "epoch": 55.18, "learning_rate": 2.6426206104723438e-05, "loss": 0.0028, "step": 229750 }, { "epoch": 55.18, "learning_rate": 2.6422249240589768e-05, "loss": 0.003, "step": 229760 }, { "epoch": 55.18, "learning_rate": 2.641829256633098e-05, "loss": 0.0038, "step": 229770 }, { "epoch": 55.19, "learning_rate": 2.6414336081978946e-05, "loss": 0.0035, "step": 229780 }, { "epoch": 55.19, "learning_rate": 2.641037978756552e-05, "loss": 0.0029, "step": 229790 }, { "epoch": 55.19, "learning_rate": 2.640642368312255e-05, "loss": 0.0034, "step": 229800 }, { "epoch": 55.19, "learning_rate": 2.6402467768681898e-05, "loss": 0.0074, "step": 229810 }, { "epoch": 55.2, "learning_rate": 2.639851204427547e-05, "loss": 0.0057, "step": 229820 }, { "epoch": 55.2, "learning_rate": 2.639455650993506e-05, "loss": 0.0031, "step": 229830 }, { "epoch": 55.2, "learning_rate": 2.639060116569253e-05, "loss": 0.0044, "step": 229840 }, { "epoch": 55.2, "learning_rate": 2.6386646011579762e-05, "loss": 0.0037, "step": 229850 }, { "epoch": 55.2, "learning_rate": 2.6382691047628615e-05, "loss": 0.0037, "step": 229860 }, { "epoch": 55.21, "learning_rate": 2.637873627387088e-05, "loss": 0.0055, "step": 229870 }, { "epoch": 55.21, "learning_rate": 2.6374781690338457e-05, "loss": 0.0024, "step": 229880 }, { "epoch": 55.21, "learning_rate": 2.6370827297063185e-05, "loss": 0.0039, "step": 229890 }, { "epoch": 55.21, "learning_rate": 2.6366873094076906e-05, "loss": 0.0026, "step": 229900 }, { "epoch": 55.22, "learning_rate": 2.6362919081411454e-05, "loss": 0.0031, "step": 229910 }, { "epoch": 55.22, "learning_rate": 2.635896525909868e-05, "loss": 0.0074, "step": 229920 }, { "epoch": 55.22, "learning_rate": 2.6355011627170422e-05, "loss": 0.0029, "step": 229930 }, { "epoch": 55.22, "learning_rate": 2.63510581856585e-05, "loss": 0.0027, "step": 229940 }, { "epoch": 55.23, "learning_rate": 2.634710493459479e-05, "loss": 0.0053, "step": 229950 }, { "epoch": 55.23, "learning_rate": 2.6343151874011134e-05, "loss": 0.0019, "step": 229960 }, { "epoch": 55.23, "learning_rate": 2.6339199003939317e-05, "loss": 0.0025, "step": 229970 }, { "epoch": 55.23, "learning_rate": 2.6335246324411177e-05, "loss": 0.0057, "step": 229980 }, { "epoch": 55.23, "learning_rate": 2.633129383545859e-05, "loss": 0.0126, "step": 229990 }, { "epoch": 55.24, "learning_rate": 2.632734153711338e-05, "loss": 0.0023, "step": 230000 }, { "epoch": 55.24, "learning_rate": 2.632338942940732e-05, "loss": 0.0036, "step": 230010 }, { "epoch": 55.24, "learning_rate": 2.6319437512372292e-05, "loss": 0.0023, "step": 230020 }, { "epoch": 55.24, "learning_rate": 2.6315485786040095e-05, "loss": 0.0066, "step": 230030 }, { "epoch": 55.25, "learning_rate": 2.631153425044257e-05, "loss": 0.0043, "step": 230040 }, { "epoch": 55.25, "learning_rate": 2.6307582905611526e-05, "loss": 0.0047, "step": 230050 }, { "epoch": 55.25, "learning_rate": 2.6303631751578783e-05, "loss": 0.0091, "step": 230060 }, { "epoch": 55.25, "learning_rate": 2.6299680788376173e-05, "loss": 0.0032, "step": 230070 }, { "epoch": 55.25, "learning_rate": 2.629573001603548e-05, "loss": 0.0038, "step": 230080 }, { "epoch": 55.26, "learning_rate": 2.629177943458857e-05, "loss": 0.0021, "step": 230090 }, { "epoch": 55.26, "learning_rate": 2.6287829044067257e-05, "loss": 0.0042, "step": 230100 }, { "epoch": 55.26, "learning_rate": 2.6283878844503284e-05, "loss": 0.0022, "step": 230110 }, { "epoch": 55.26, "learning_rate": 2.627992883592853e-05, "loss": 0.0074, "step": 230120 }, { "epoch": 55.27, "learning_rate": 2.6275979018374787e-05, "loss": 0.0047, "step": 230130 }, { "epoch": 55.27, "learning_rate": 2.6272029391873855e-05, "loss": 0.0027, "step": 230140 }, { "epoch": 55.27, "learning_rate": 2.626807995645755e-05, "loss": 0.0022, "step": 230150 }, { "epoch": 55.27, "learning_rate": 2.626413071215767e-05, "loss": 0.009, "step": 230160 }, { "epoch": 55.28, "learning_rate": 2.6260181659006023e-05, "loss": 0.0138, "step": 230170 }, { "epoch": 55.28, "learning_rate": 2.6256232797034414e-05, "loss": 0.0065, "step": 230180 }, { "epoch": 55.28, "learning_rate": 2.625228412627464e-05, "loss": 0.0031, "step": 230190 }, { "epoch": 55.28, "learning_rate": 2.624833564675849e-05, "loss": 0.0057, "step": 230200 }, { "epoch": 55.28, "learning_rate": 2.6244387358517784e-05, "loss": 0.0027, "step": 230210 }, { "epoch": 55.29, "learning_rate": 2.6240439261584286e-05, "loss": 0.0033, "step": 230220 }, { "epoch": 55.29, "learning_rate": 2.623649135598983e-05, "loss": 0.0031, "step": 230230 }, { "epoch": 55.29, "learning_rate": 2.6232543641766206e-05, "loss": 0.0272, "step": 230240 }, { "epoch": 55.29, "learning_rate": 2.6228596118945155e-05, "loss": 0.0046, "step": 230250 }, { "epoch": 55.3, "learning_rate": 2.6224648787558513e-05, "loss": 0.0037, "step": 230260 }, { "epoch": 55.3, "learning_rate": 2.622070164763806e-05, "loss": 0.0047, "step": 230270 }, { "epoch": 55.3, "learning_rate": 2.6216754699215585e-05, "loss": 0.003, "step": 230280 }, { "epoch": 55.3, "learning_rate": 2.6212807942322863e-05, "loss": 0.0089, "step": 230290 }, { "epoch": 55.31, "learning_rate": 2.6208861376991684e-05, "loss": 0.0039, "step": 230300 }, { "epoch": 55.31, "learning_rate": 2.6204915003253828e-05, "loss": 0.004, "step": 230310 }, { "epoch": 55.31, "learning_rate": 2.620096882114106e-05, "loss": 0.0027, "step": 230320 }, { "epoch": 55.31, "learning_rate": 2.6197022830685215e-05, "loss": 0.0033, "step": 230330 }, { "epoch": 55.31, "learning_rate": 2.6193077031918e-05, "loss": 0.0047, "step": 230340 }, { "epoch": 55.32, "learning_rate": 2.6189131424871216e-05, "loss": 0.0034, "step": 230350 }, { "epoch": 55.32, "learning_rate": 2.6185186009576656e-05, "loss": 0.0042, "step": 230360 }, { "epoch": 55.32, "learning_rate": 2.6181240786066086e-05, "loss": 0.003, "step": 230370 }, { "epoch": 55.32, "learning_rate": 2.617729575437129e-05, "loss": 0.0176, "step": 230380 }, { "epoch": 55.33, "learning_rate": 2.6173350914523986e-05, "loss": 0.0018, "step": 230390 }, { "epoch": 55.33, "learning_rate": 2.6169406266555983e-05, "loss": 0.0025, "step": 230400 }, { "epoch": 55.33, "learning_rate": 2.616546181049906e-05, "loss": 0.0023, "step": 230410 }, { "epoch": 55.33, "learning_rate": 2.6161517546384952e-05, "loss": 0.0022, "step": 230420 }, { "epoch": 55.33, "learning_rate": 2.6157573474245434e-05, "loss": 0.0055, "step": 230430 }, { "epoch": 55.34, "learning_rate": 2.6153629594112273e-05, "loss": 0.004, "step": 230440 }, { "epoch": 55.34, "learning_rate": 2.614968590601722e-05, "loss": 0.006, "step": 230450 }, { "epoch": 55.34, "learning_rate": 2.6145742409992018e-05, "loss": 0.0023, "step": 230460 }, { "epoch": 55.34, "learning_rate": 2.614179910606847e-05, "loss": 0.0251, "step": 230470 }, { "epoch": 55.35, "learning_rate": 2.6137855994278325e-05, "loss": 0.0031, "step": 230480 }, { "epoch": 55.35, "learning_rate": 2.6133913074653282e-05, "loss": 0.0035, "step": 230490 }, { "epoch": 55.35, "learning_rate": 2.612997034722515e-05, "loss": 0.0043, "step": 230500 }, { "epoch": 55.35, "learning_rate": 2.6126027812025666e-05, "loss": 0.0074, "step": 230510 }, { "epoch": 55.36, "learning_rate": 2.6122085469086576e-05, "loss": 0.0039, "step": 230520 }, { "epoch": 55.36, "learning_rate": 2.6118143318439625e-05, "loss": 0.0045, "step": 230530 }, { "epoch": 55.36, "learning_rate": 2.6114201360116563e-05, "loss": 0.0018, "step": 230540 }, { "epoch": 55.36, "learning_rate": 2.6110259594149134e-05, "loss": 0.0021, "step": 230550 }, { "epoch": 55.36, "learning_rate": 2.6106318020569064e-05, "loss": 0.0046, "step": 230560 }, { "epoch": 55.37, "learning_rate": 2.6102376639408154e-05, "loss": 0.0036, "step": 230570 }, { "epoch": 55.37, "learning_rate": 2.609843545069809e-05, "loss": 0.0031, "step": 230580 }, { "epoch": 55.37, "learning_rate": 2.6094494454470597e-05, "loss": 0.0038, "step": 230590 }, { "epoch": 55.37, "learning_rate": 2.6090553650757465e-05, "loss": 0.003, "step": 230600 }, { "epoch": 55.38, "learning_rate": 2.6086613039590402e-05, "loss": 0.0032, "step": 230610 }, { "epoch": 55.38, "learning_rate": 2.608267262100117e-05, "loss": 0.0025, "step": 230620 }, { "epoch": 55.38, "learning_rate": 2.6078732395021434e-05, "loss": 0.0071, "step": 230630 }, { "epoch": 55.38, "learning_rate": 2.607479236168299e-05, "loss": 0.0019, "step": 230640 }, { "epoch": 55.39, "learning_rate": 2.607085252101755e-05, "loss": 0.0028, "step": 230650 }, { "epoch": 55.39, "learning_rate": 2.6066912873056827e-05, "loss": 0.0027, "step": 230660 }, { "epoch": 55.39, "learning_rate": 2.606297341783257e-05, "loss": 0.0027, "step": 230670 }, { "epoch": 55.39, "learning_rate": 2.6059034155376483e-05, "loss": 0.0052, "step": 230680 }, { "epoch": 55.39, "learning_rate": 2.6055095085720304e-05, "loss": 0.0075, "step": 230690 }, { "epoch": 55.4, "learning_rate": 2.605115620889573e-05, "loss": 0.0035, "step": 230700 }, { "epoch": 55.4, "learning_rate": 2.6047217524934547e-05, "loss": 0.005, "step": 230710 }, { "epoch": 55.4, "learning_rate": 2.6043279033868407e-05, "loss": 0.0084, "step": 230720 }, { "epoch": 55.4, "learning_rate": 2.6039340735729023e-05, "loss": 0.0073, "step": 230730 }, { "epoch": 55.41, "learning_rate": 2.6035402630548155e-05, "loss": 0.0039, "step": 230740 }, { "epoch": 55.41, "learning_rate": 2.60314647183575e-05, "loss": 0.0031, "step": 230750 }, { "epoch": 55.41, "learning_rate": 2.6027526999188768e-05, "loss": 0.0056, "step": 230760 }, { "epoch": 55.41, "learning_rate": 2.6023589473073674e-05, "loss": 0.009, "step": 230770 }, { "epoch": 55.41, "learning_rate": 2.6019652140043928e-05, "loss": 0.0055, "step": 230780 }, { "epoch": 55.42, "learning_rate": 2.6015715000131226e-05, "loss": 0.0031, "step": 230790 }, { "epoch": 55.42, "learning_rate": 2.6011778053367264e-05, "loss": 0.0018, "step": 230800 }, { "epoch": 55.42, "learning_rate": 2.6007841299783802e-05, "loss": 0.0017, "step": 230810 }, { "epoch": 55.42, "learning_rate": 2.6003904739412493e-05, "loss": 0.0023, "step": 230820 }, { "epoch": 55.43, "learning_rate": 2.599996837228505e-05, "loss": 0.0108, "step": 230830 }, { "epoch": 55.43, "learning_rate": 2.5996032198433152e-05, "loss": 0.0025, "step": 230840 }, { "epoch": 55.43, "learning_rate": 2.599209621788856e-05, "loss": 0.008, "step": 230850 }, { "epoch": 55.43, "learning_rate": 2.5988160430682918e-05, "loss": 0.0028, "step": 230860 }, { "epoch": 55.44, "learning_rate": 2.5984224836847915e-05, "loss": 0.0042, "step": 230870 }, { "epoch": 55.44, "learning_rate": 2.5980289436415277e-05, "loss": 0.0022, "step": 230880 }, { "epoch": 55.44, "learning_rate": 2.5976354229416687e-05, "loss": 0.0022, "step": 230890 }, { "epoch": 55.44, "learning_rate": 2.5972419215883837e-05, "loss": 0.0032, "step": 230900 }, { "epoch": 55.44, "learning_rate": 2.5968484395848413e-05, "loss": 0.0026, "step": 230910 }, { "epoch": 55.45, "learning_rate": 2.5964549769342095e-05, "loss": 0.0046, "step": 230920 }, { "epoch": 55.45, "learning_rate": 2.596061533639658e-05, "loss": 0.002, "step": 230930 }, { "epoch": 55.45, "learning_rate": 2.5956681097043534e-05, "loss": 0.0021, "step": 230940 }, { "epoch": 55.45, "learning_rate": 2.5952747051314684e-05, "loss": 0.0017, "step": 230950 }, { "epoch": 55.46, "learning_rate": 2.5948813199241672e-05, "loss": 0.0067, "step": 230960 }, { "epoch": 55.46, "learning_rate": 2.594487954085616e-05, "loss": 0.0018, "step": 230970 }, { "epoch": 55.46, "learning_rate": 2.5940946076189875e-05, "loss": 0.0028, "step": 230980 }, { "epoch": 55.46, "learning_rate": 2.5937012805274496e-05, "loss": 0.0026, "step": 230990 }, { "epoch": 55.47, "learning_rate": 2.5933079728141634e-05, "loss": 0.0021, "step": 231000 }, { "epoch": 55.47, "learning_rate": 2.5929146844823026e-05, "loss": 0.0026, "step": 231010 }, { "epoch": 55.47, "learning_rate": 2.592521415535032e-05, "loss": 0.0044, "step": 231020 }, { "epoch": 55.47, "learning_rate": 2.5921281659755182e-05, "loss": 0.003, "step": 231030 }, { "epoch": 55.47, "learning_rate": 2.591734935806929e-05, "loss": 0.0052, "step": 231040 }, { "epoch": 55.48, "learning_rate": 2.5913417250324312e-05, "loss": 0.0025, "step": 231050 }, { "epoch": 55.48, "learning_rate": 2.5909485336551908e-05, "loss": 0.0158, "step": 231060 }, { "epoch": 55.48, "learning_rate": 2.590555361678375e-05, "loss": 0.0037, "step": 231070 }, { "epoch": 55.48, "learning_rate": 2.590162209105147e-05, "loss": 0.0033, "step": 231080 }, { "epoch": 55.49, "learning_rate": 2.5897690759386796e-05, "loss": 0.0035, "step": 231090 }, { "epoch": 55.49, "learning_rate": 2.5893759621821324e-05, "loss": 0.0049, "step": 231100 }, { "epoch": 55.49, "learning_rate": 2.5889828678386713e-05, "loss": 0.0024, "step": 231110 }, { "epoch": 55.49, "learning_rate": 2.5885897929114662e-05, "loss": 0.0032, "step": 231120 }, { "epoch": 55.49, "learning_rate": 2.5881967374036804e-05, "loss": 0.011, "step": 231130 }, { "epoch": 55.5, "learning_rate": 2.5878037013184793e-05, "loss": 0.01, "step": 231140 }, { "epoch": 55.5, "learning_rate": 2.5874106846590278e-05, "loss": 0.0021, "step": 231150 }, { "epoch": 55.5, "learning_rate": 2.5870176874284914e-05, "loss": 0.0027, "step": 231160 }, { "epoch": 55.5, "learning_rate": 2.5866247096300343e-05, "loss": 0.0051, "step": 231170 }, { "epoch": 55.51, "learning_rate": 2.586231751266822e-05, "loss": 0.0059, "step": 231180 }, { "epoch": 55.51, "learning_rate": 2.5858388123420185e-05, "loss": 0.0048, "step": 231190 }, { "epoch": 55.51, "learning_rate": 2.5854458928587888e-05, "loss": 0.0021, "step": 231200 }, { "epoch": 55.51, "learning_rate": 2.5850529928202937e-05, "loss": 0.0024, "step": 231210 }, { "epoch": 55.52, "learning_rate": 2.5846601122297033e-05, "loss": 0.0038, "step": 231220 }, { "epoch": 55.52, "learning_rate": 2.58426725109018e-05, "loss": 0.0025, "step": 231230 }, { "epoch": 55.52, "learning_rate": 2.583874409404884e-05, "loss": 0.0019, "step": 231240 }, { "epoch": 55.52, "learning_rate": 2.5834815871769792e-05, "loss": 0.0026, "step": 231250 }, { "epoch": 55.52, "learning_rate": 2.583088784409632e-05, "loss": 0.003, "step": 231260 }, { "epoch": 55.53, "learning_rate": 2.5826960011060054e-05, "loss": 0.0073, "step": 231270 }, { "epoch": 55.53, "learning_rate": 2.5823032372692614e-05, "loss": 0.0032, "step": 231280 }, { "epoch": 55.53, "learning_rate": 2.5819104929025627e-05, "loss": 0.0044, "step": 231290 }, { "epoch": 55.53, "learning_rate": 2.581517768009073e-05, "loss": 0.0042, "step": 231300 }, { "epoch": 55.54, "learning_rate": 2.5811250625919548e-05, "loss": 0.005, "step": 231310 }, { "epoch": 55.54, "learning_rate": 2.58073237665437e-05, "loss": 0.0102, "step": 231320 }, { "epoch": 55.54, "learning_rate": 2.5803397101994818e-05, "loss": 0.0077, "step": 231330 }, { "epoch": 55.54, "learning_rate": 2.579947063230452e-05, "loss": 0.0026, "step": 231340 }, { "epoch": 55.55, "learning_rate": 2.5795544357504402e-05, "loss": 0.0092, "step": 231350 }, { "epoch": 55.55, "learning_rate": 2.579161827762613e-05, "loss": 0.0055, "step": 231360 }, { "epoch": 55.55, "learning_rate": 2.5787692392701312e-05, "loss": 0.0028, "step": 231370 }, { "epoch": 55.55, "learning_rate": 2.578376670276152e-05, "loss": 0.0037, "step": 231380 }, { "epoch": 55.55, "learning_rate": 2.577984120783841e-05, "loss": 0.0054, "step": 231390 }, { "epoch": 55.56, "learning_rate": 2.5775915907963587e-05, "loss": 0.0051, "step": 231400 }, { "epoch": 55.56, "learning_rate": 2.5771990803168654e-05, "loss": 0.0033, "step": 231410 }, { "epoch": 55.56, "learning_rate": 2.5768065893485226e-05, "loss": 0.0108, "step": 231420 }, { "epoch": 55.56, "learning_rate": 2.576414117894491e-05, "loss": 0.008, "step": 231430 }, { "epoch": 55.57, "learning_rate": 2.5760216659579313e-05, "loss": 0.0028, "step": 231440 }, { "epoch": 55.57, "learning_rate": 2.5756292335420017e-05, "loss": 0.0029, "step": 231450 }, { "epoch": 55.57, "learning_rate": 2.575236820649866e-05, "loss": 0.0054, "step": 231460 }, { "epoch": 55.57, "learning_rate": 2.574844427284685e-05, "loss": 0.0046, "step": 231470 }, { "epoch": 55.57, "learning_rate": 2.5744520534496152e-05, "loss": 0.0079, "step": 231480 }, { "epoch": 55.58, "learning_rate": 2.574059699147816e-05, "loss": 0.002, "step": 231490 }, { "epoch": 55.58, "learning_rate": 2.5736673643824505e-05, "loss": 0.0028, "step": 231500 }, { "epoch": 55.58, "learning_rate": 2.573275049156678e-05, "loss": 0.0024, "step": 231510 }, { "epoch": 55.58, "learning_rate": 2.572882753473654e-05, "loss": 0.0073, "step": 231520 }, { "epoch": 55.59, "learning_rate": 2.5724904773365417e-05, "loss": 0.0079, "step": 231530 }, { "epoch": 55.59, "learning_rate": 2.5720982207484983e-05, "loss": 0.0023, "step": 231540 }, { "epoch": 55.59, "learning_rate": 2.5717059837126832e-05, "loss": 0.0029, "step": 231550 }, { "epoch": 55.59, "learning_rate": 2.5713137662322557e-05, "loss": 0.0046, "step": 231560 }, { "epoch": 55.6, "learning_rate": 2.570921568310374e-05, "loss": 0.0089, "step": 231570 }, { "epoch": 55.6, "learning_rate": 2.5705293899501946e-05, "loss": 0.0029, "step": 231580 }, { "epoch": 55.6, "learning_rate": 2.5701372311548765e-05, "loss": 0.0074, "step": 231590 }, { "epoch": 55.6, "learning_rate": 2.569745091927581e-05, "loss": 0.0024, "step": 231600 }, { "epoch": 55.6, "learning_rate": 2.5693529722714653e-05, "loss": 0.0031, "step": 231610 }, { "epoch": 55.61, "learning_rate": 2.568960872189682e-05, "loss": 0.0022, "step": 231620 }, { "epoch": 55.61, "learning_rate": 2.5685687916853946e-05, "loss": 0.005, "step": 231630 }, { "epoch": 55.61, "learning_rate": 2.5681767307617577e-05, "loss": 0.0025, "step": 231640 }, { "epoch": 55.61, "learning_rate": 2.56778468942193e-05, "loss": 0.0019, "step": 231650 }, { "epoch": 55.62, "learning_rate": 2.5673926676690674e-05, "loss": 0.0026, "step": 231660 }, { "epoch": 55.62, "learning_rate": 2.5670006655063283e-05, "loss": 0.0057, "step": 231670 }, { "epoch": 55.62, "learning_rate": 2.5666086829368678e-05, "loss": 0.002, "step": 231680 }, { "epoch": 55.62, "learning_rate": 2.566216719963844e-05, "loss": 0.0039, "step": 231690 }, { "epoch": 55.62, "learning_rate": 2.565824776590413e-05, "loss": 0.004, "step": 231700 }, { "epoch": 55.63, "learning_rate": 2.5654328528197314e-05, "loss": 0.0092, "step": 231710 }, { "epoch": 55.63, "learning_rate": 2.5650409486549544e-05, "loss": 0.002, "step": 231720 }, { "epoch": 55.63, "learning_rate": 2.564649064099237e-05, "loss": 0.0025, "step": 231730 }, { "epoch": 55.63, "learning_rate": 2.5642571991557396e-05, "loss": 0.0076, "step": 231740 }, { "epoch": 55.64, "learning_rate": 2.5638653538276164e-05, "loss": 0.0045, "step": 231750 }, { "epoch": 55.64, "learning_rate": 2.5634735281180182e-05, "loss": 0.0027, "step": 231760 }, { "epoch": 55.64, "learning_rate": 2.563081722030106e-05, "loss": 0.0069, "step": 231770 }, { "epoch": 55.64, "learning_rate": 2.562689935567033e-05, "loss": 0.002, "step": 231780 }, { "epoch": 55.65, "learning_rate": 2.562298168731955e-05, "loss": 0.005, "step": 231790 }, { "epoch": 55.65, "learning_rate": 2.5619064215280262e-05, "loss": 0.0118, "step": 231800 }, { "epoch": 55.65, "learning_rate": 2.5615146939584013e-05, "loss": 0.0144, "step": 231810 }, { "epoch": 55.65, "learning_rate": 2.5611229860262354e-05, "loss": 0.0035, "step": 231820 }, { "epoch": 55.65, "learning_rate": 2.560731297734681e-05, "loss": 0.0017, "step": 231830 }, { "epoch": 55.66, "learning_rate": 2.5603396290868975e-05, "loss": 0.002, "step": 231840 }, { "epoch": 55.66, "learning_rate": 2.5599479800860345e-05, "loss": 0.0033, "step": 231850 }, { "epoch": 55.66, "learning_rate": 2.559556350735245e-05, "loss": 0.0062, "step": 231860 }, { "epoch": 55.66, "learning_rate": 2.5591647410376874e-05, "loss": 0.0103, "step": 231870 }, { "epoch": 55.67, "learning_rate": 2.5587731509965124e-05, "loss": 0.016, "step": 231880 }, { "epoch": 55.67, "learning_rate": 2.558381580614877e-05, "loss": 0.0029, "step": 231890 }, { "epoch": 55.67, "learning_rate": 2.5579900298959268e-05, "loss": 0.004, "step": 231900 }, { "epoch": 55.67, "learning_rate": 2.5575984988428235e-05, "loss": 0.0053, "step": 231910 }, { "epoch": 55.68, "learning_rate": 2.5572069874587157e-05, "loss": 0.0114, "step": 231920 }, { "epoch": 55.68, "learning_rate": 2.5568154957467576e-05, "loss": 0.004, "step": 231930 }, { "epoch": 55.68, "learning_rate": 2.5564240237101013e-05, "loss": 0.0034, "step": 231940 }, { "epoch": 55.68, "learning_rate": 2.5560325713519e-05, "loss": 0.0044, "step": 231950 }, { "epoch": 55.68, "learning_rate": 2.555641138675306e-05, "loss": 0.0141, "step": 231960 }, { "epoch": 55.69, "learning_rate": 2.555249725683469e-05, "loss": 0.0042, "step": 231970 }, { "epoch": 55.69, "learning_rate": 2.5548583323795476e-05, "loss": 0.0027, "step": 231980 }, { "epoch": 55.69, "learning_rate": 2.554466958766688e-05, "loss": 0.0027, "step": 231990 }, { "epoch": 55.69, "learning_rate": 2.554075604848041e-05, "loss": 0.0016, "step": 232000 }, { "epoch": 55.7, "learning_rate": 2.553684270626763e-05, "loss": 0.0032, "step": 232010 }, { "epoch": 55.7, "learning_rate": 2.553292956106004e-05, "loss": 0.0028, "step": 232020 }, { "epoch": 55.7, "learning_rate": 2.5529016612889133e-05, "loss": 0.004, "step": 232030 }, { "epoch": 55.7, "learning_rate": 2.5525103861786444e-05, "loss": 0.0185, "step": 232040 }, { "epoch": 55.7, "learning_rate": 2.5521191307783466e-05, "loss": 0.0036, "step": 232050 }, { "epoch": 55.71, "learning_rate": 2.5517278950911716e-05, "loss": 0.0047, "step": 232060 }, { "epoch": 55.71, "learning_rate": 2.551336679120268e-05, "loss": 0.0061, "step": 232070 }, { "epoch": 55.71, "learning_rate": 2.5509454828687922e-05, "loss": 0.0018, "step": 232080 }, { "epoch": 55.71, "learning_rate": 2.5505543063398884e-05, "loss": 0.0034, "step": 232090 }, { "epoch": 55.72, "learning_rate": 2.5501631495367075e-05, "loss": 0.0018, "step": 232100 }, { "epoch": 55.72, "learning_rate": 2.5497720124624025e-05, "loss": 0.0092, "step": 232110 }, { "epoch": 55.72, "learning_rate": 2.5493808951201213e-05, "loss": 0.0041, "step": 232120 }, { "epoch": 55.72, "learning_rate": 2.5489897975130167e-05, "loss": 0.0032, "step": 232130 }, { "epoch": 55.73, "learning_rate": 2.5485987196442317e-05, "loss": 0.0178, "step": 232140 }, { "epoch": 55.73, "learning_rate": 2.5482076615169213e-05, "loss": 0.0023, "step": 232150 }, { "epoch": 55.73, "learning_rate": 2.5478166231342333e-05, "loss": 0.0023, "step": 232160 }, { "epoch": 55.73, "learning_rate": 2.547425604499316e-05, "loss": 0.002, "step": 232170 }, { "epoch": 55.73, "learning_rate": 2.5470346056153194e-05, "loss": 0.0023, "step": 232180 }, { "epoch": 55.74, "learning_rate": 2.546643626485392e-05, "loss": 0.0026, "step": 232190 }, { "epoch": 55.74, "learning_rate": 2.546252667112682e-05, "loss": 0.0068, "step": 232200 }, { "epoch": 55.74, "learning_rate": 2.545861727500336e-05, "loss": 0.004, "step": 232210 }, { "epoch": 55.74, "learning_rate": 2.5454708076515082e-05, "loss": 0.0038, "step": 232220 }, { "epoch": 55.75, "learning_rate": 2.545079907569341e-05, "loss": 0.0045, "step": 232230 }, { "epoch": 55.75, "learning_rate": 2.5446890272569823e-05, "loss": 0.0059, "step": 232240 }, { "epoch": 55.75, "learning_rate": 2.5442981667175836e-05, "loss": 0.0016, "step": 232250 }, { "epoch": 55.75, "learning_rate": 2.543907325954291e-05, "loss": 0.006, "step": 232260 }, { "epoch": 55.76, "learning_rate": 2.543516504970252e-05, "loss": 0.0137, "step": 232270 }, { "epoch": 55.76, "learning_rate": 2.5431257037686136e-05, "loss": 0.0035, "step": 232280 }, { "epoch": 55.76, "learning_rate": 2.5427349223525226e-05, "loss": 0.0046, "step": 232290 }, { "epoch": 55.76, "learning_rate": 2.542344160725127e-05, "loss": 0.0019, "step": 232300 }, { "epoch": 55.76, "learning_rate": 2.5419534188895733e-05, "loss": 0.0059, "step": 232310 }, { "epoch": 55.77, "learning_rate": 2.5415626968490074e-05, "loss": 0.0044, "step": 232320 }, { "epoch": 55.77, "learning_rate": 2.541171994606577e-05, "loss": 0.0051, "step": 232330 }, { "epoch": 55.77, "learning_rate": 2.5407813121654277e-05, "loss": 0.0018, "step": 232340 }, { "epoch": 55.77, "learning_rate": 2.5403906495287045e-05, "loss": 0.0037, "step": 232350 }, { "epoch": 55.78, "learning_rate": 2.5400000066995587e-05, "loss": 0.0245, "step": 232360 }, { "epoch": 55.78, "learning_rate": 2.539609383681131e-05, "loss": 0.0028, "step": 232370 }, { "epoch": 55.78, "learning_rate": 2.5392187804765656e-05, "loss": 0.0165, "step": 232380 }, { "epoch": 55.78, "learning_rate": 2.5388281970890137e-05, "loss": 0.0023, "step": 232390 }, { "epoch": 55.78, "learning_rate": 2.5384376335216177e-05, "loss": 0.0071, "step": 232400 }, { "epoch": 55.79, "learning_rate": 2.5380470897775232e-05, "loss": 0.0045, "step": 232410 }, { "epoch": 55.79, "learning_rate": 2.537656565859876e-05, "loss": 0.0023, "step": 232420 }, { "epoch": 55.79, "learning_rate": 2.5372660617718203e-05, "loss": 0.0049, "step": 232430 }, { "epoch": 55.79, "learning_rate": 2.536875577516501e-05, "loss": 0.0019, "step": 232440 }, { "epoch": 55.8, "learning_rate": 2.53648511309706e-05, "loss": 0.0017, "step": 232450 }, { "epoch": 55.8, "learning_rate": 2.5360946685166498e-05, "loss": 0.0066, "step": 232460 }, { "epoch": 55.8, "learning_rate": 2.5357042437784062e-05, "loss": 0.0026, "step": 232470 }, { "epoch": 55.8, "learning_rate": 2.5353138388854754e-05, "loss": 0.0025, "step": 232480 }, { "epoch": 55.81, "learning_rate": 2.534923453841004e-05, "loss": 0.0034, "step": 232490 }, { "epoch": 55.81, "learning_rate": 2.5345330886481367e-05, "loss": 0.0029, "step": 232500 }, { "epoch": 55.81, "learning_rate": 2.5341427433100107e-05, "loss": 0.0087, "step": 232510 }, { "epoch": 55.81, "learning_rate": 2.5337524178297757e-05, "loss": 0.0037, "step": 232520 }, { "epoch": 55.81, "learning_rate": 2.5333621122105723e-05, "loss": 0.0071, "step": 232530 }, { "epoch": 55.82, "learning_rate": 2.5329718264555445e-05, "loss": 0.0057, "step": 232540 }, { "epoch": 55.82, "learning_rate": 2.532581560567836e-05, "loss": 0.0018, "step": 232550 }, { "epoch": 55.82, "learning_rate": 2.5321913145505882e-05, "loss": 0.0028, "step": 232560 }, { "epoch": 55.82, "learning_rate": 2.5318010884069447e-05, "loss": 0.005, "step": 232570 }, { "epoch": 55.83, "learning_rate": 2.5314108821400477e-05, "loss": 0.0041, "step": 232580 }, { "epoch": 55.83, "learning_rate": 2.531020695753038e-05, "loss": 0.0063, "step": 232590 }, { "epoch": 55.83, "learning_rate": 2.530630529249063e-05, "loss": 0.0034, "step": 232600 }, { "epoch": 55.83, "learning_rate": 2.5302403826312592e-05, "loss": 0.0024, "step": 232610 }, { "epoch": 55.84, "learning_rate": 2.5298502559027692e-05, "loss": 0.0035, "step": 232620 }, { "epoch": 55.84, "learning_rate": 2.529460149066738e-05, "loss": 0.0061, "step": 232630 }, { "epoch": 55.84, "learning_rate": 2.5290700621263046e-05, "loss": 0.0039, "step": 232640 }, { "epoch": 55.84, "learning_rate": 2.528679995084612e-05, "loss": 0.0022, "step": 232650 }, { "epoch": 55.84, "learning_rate": 2.5282899479447996e-05, "loss": 0.0109, "step": 232660 }, { "epoch": 55.85, "learning_rate": 2.5278999207100108e-05, "loss": 0.0069, "step": 232670 }, { "epoch": 55.85, "learning_rate": 2.527509913383384e-05, "loss": 0.0144, "step": 232680 }, { "epoch": 55.85, "learning_rate": 2.5271199259680617e-05, "loss": 0.0032, "step": 232690 }, { "epoch": 55.85, "learning_rate": 2.5267299584671842e-05, "loss": 0.0033, "step": 232700 }, { "epoch": 55.86, "learning_rate": 2.5263400108838915e-05, "loss": 0.0033, "step": 232710 }, { "epoch": 55.86, "learning_rate": 2.5259500832213223e-05, "loss": 0.0019, "step": 232720 }, { "epoch": 55.86, "learning_rate": 2.5255601754826206e-05, "loss": 0.0028, "step": 232730 }, { "epoch": 55.86, "learning_rate": 2.5251702876709265e-05, "loss": 0.0057, "step": 232740 }, { "epoch": 55.86, "learning_rate": 2.5247804197893754e-05, "loss": 0.002, "step": 232750 }, { "epoch": 55.87, "learning_rate": 2.5243905718411083e-05, "loss": 0.0042, "step": 232760 }, { "epoch": 55.87, "learning_rate": 2.5240007438292667e-05, "loss": 0.0022, "step": 232770 }, { "epoch": 55.87, "learning_rate": 2.5236109357569892e-05, "loss": 0.0027, "step": 232780 }, { "epoch": 55.87, "learning_rate": 2.5232211476274147e-05, "loss": 0.0021, "step": 232790 }, { "epoch": 55.88, "learning_rate": 2.5228313794436832e-05, "loss": 0.0023, "step": 232800 }, { "epoch": 55.88, "learning_rate": 2.5224416312089316e-05, "loss": 0.0027, "step": 232810 }, { "epoch": 55.88, "learning_rate": 2.522051902926299e-05, "loss": 0.0053, "step": 232820 }, { "epoch": 55.88, "learning_rate": 2.521662194598926e-05, "loss": 0.0031, "step": 232830 }, { "epoch": 55.89, "learning_rate": 2.5212725062299482e-05, "loss": 0.0026, "step": 232840 }, { "epoch": 55.89, "learning_rate": 2.5208828378225058e-05, "loss": 0.0031, "step": 232850 }, { "epoch": 55.89, "learning_rate": 2.5204931893797346e-05, "loss": 0.0728, "step": 232860 }, { "epoch": 55.89, "learning_rate": 2.5201035609047752e-05, "loss": 0.0032, "step": 232870 }, { "epoch": 55.89, "learning_rate": 2.5197139524007663e-05, "loss": 0.0022, "step": 232880 }, { "epoch": 55.9, "learning_rate": 2.5193243638708398e-05, "loss": 0.0058, "step": 232890 }, { "epoch": 55.9, "learning_rate": 2.5189347953181386e-05, "loss": 0.003, "step": 232900 }, { "epoch": 55.9, "learning_rate": 2.5185452467457975e-05, "loss": 0.007, "step": 232910 }, { "epoch": 55.9, "learning_rate": 2.5181557181569548e-05, "loss": 0.002, "step": 232920 }, { "epoch": 55.91, "learning_rate": 2.5177662095547462e-05, "loss": 0.0165, "step": 232930 }, { "epoch": 55.91, "learning_rate": 2.5173767209423095e-05, "loss": 0.0026, "step": 232940 }, { "epoch": 55.91, "learning_rate": 2.5169872523227804e-05, "loss": 0.0026, "step": 232950 }, { "epoch": 55.91, "learning_rate": 2.5165978036992943e-05, "loss": 0.0024, "step": 232960 }, { "epoch": 55.92, "learning_rate": 2.5162083750749903e-05, "loss": 0.0085, "step": 232970 }, { "epoch": 55.92, "learning_rate": 2.5158189664530052e-05, "loss": 0.0035, "step": 232980 }, { "epoch": 55.92, "learning_rate": 2.515429577836471e-05, "loss": 0.0046, "step": 232990 }, { "epoch": 55.92, "learning_rate": 2.515040209228524e-05, "loss": 0.0038, "step": 233000 }, { "epoch": 55.92, "learning_rate": 2.514650860632303e-05, "loss": 0.0014, "step": 233010 }, { "epoch": 55.93, "learning_rate": 2.5142615320509434e-05, "loss": 0.0846, "step": 233020 }, { "epoch": 55.93, "learning_rate": 2.513872223487575e-05, "loss": 0.0032, "step": 233030 }, { "epoch": 55.93, "learning_rate": 2.513482934945339e-05, "loss": 0.0022, "step": 233040 }, { "epoch": 55.93, "learning_rate": 2.5130936664273678e-05, "loss": 0.0026, "step": 233050 }, { "epoch": 55.94, "learning_rate": 2.512704417936797e-05, "loss": 0.0038, "step": 233060 }, { "epoch": 55.94, "learning_rate": 2.512315189476761e-05, "loss": 0.0034, "step": 233070 }, { "epoch": 55.94, "learning_rate": 2.5119259810503936e-05, "loss": 0.0043, "step": 233080 }, { "epoch": 55.94, "learning_rate": 2.51153679266083e-05, "loss": 0.0031, "step": 233090 }, { "epoch": 55.94, "learning_rate": 2.511147624311203e-05, "loss": 0.0025, "step": 233100 }, { "epoch": 55.95, "learning_rate": 2.510758476004649e-05, "loss": 0.0021, "step": 233110 }, { "epoch": 55.95, "learning_rate": 2.510369347744303e-05, "loss": 0.0035, "step": 233120 }, { "epoch": 56.0, "learning_rate": 2.509980239533292e-05, "loss": 0.0192, "step": 233130 }, { "epoch": 56.0, "learning_rate": 2.509591151374756e-05, "loss": 0.0035, "step": 233140 }, { "epoch": 56.01, "learning_rate": 2.5092020832718268e-05, "loss": 0.0038, "step": 233150 }, { "epoch": 56.01, "learning_rate": 2.5088130352276385e-05, "loss": 0.0043, "step": 233160 }, { "epoch": 56.01, "learning_rate": 2.508424007245319e-05, "loss": 0.0035, "step": 233170 }, { "epoch": 56.01, "learning_rate": 2.5080349993280072e-05, "loss": 0.0038, "step": 233180 }, { "epoch": 56.01, "learning_rate": 2.507646011478833e-05, "loss": 0.002, "step": 233190 }, { "epoch": 56.02, "learning_rate": 2.50725704370093e-05, "loss": 0.0026, "step": 233200 }, { "epoch": 56.02, "learning_rate": 2.50686809599743e-05, "loss": 0.0035, "step": 233210 }, { "epoch": 56.02, "learning_rate": 2.506479168371465e-05, "loss": 0.0022, "step": 233220 }, { "epoch": 56.02, "learning_rate": 2.5060902608261683e-05, "loss": 0.0051, "step": 233230 }, { "epoch": 56.03, "learning_rate": 2.5057013733646684e-05, "loss": 0.0046, "step": 233240 }, { "epoch": 56.03, "learning_rate": 2.5053125059901022e-05, "loss": 0.0031, "step": 233250 }, { "epoch": 56.03, "learning_rate": 2.5049236587056e-05, "loss": 0.0076, "step": 233260 }, { "epoch": 56.03, "learning_rate": 2.504534831514289e-05, "loss": 0.0024, "step": 233270 }, { "epoch": 56.03, "learning_rate": 2.5041460244193047e-05, "loss": 0.0037, "step": 233280 }, { "epoch": 56.04, "learning_rate": 2.5037572374237783e-05, "loss": 0.0017, "step": 233290 }, { "epoch": 56.04, "learning_rate": 2.503368470530838e-05, "loss": 0.0098, "step": 233300 }, { "epoch": 56.04, "learning_rate": 2.502979723743617e-05, "loss": 0.0041, "step": 233310 }, { "epoch": 56.04, "learning_rate": 2.502590997065245e-05, "loss": 0.0049, "step": 233320 }, { "epoch": 56.05, "learning_rate": 2.502202290498852e-05, "loss": 0.002, "step": 233330 }, { "epoch": 56.05, "learning_rate": 2.501813604047567e-05, "loss": 0.0045, "step": 233340 }, { "epoch": 56.05, "learning_rate": 2.501424937714526e-05, "loss": 0.002, "step": 233350 }, { "epoch": 56.05, "learning_rate": 2.501036291502853e-05, "loss": 0.0022, "step": 233360 }, { "epoch": 56.06, "learning_rate": 2.500647665415678e-05, "loss": 0.0034, "step": 233370 }, { "epoch": 56.06, "learning_rate": 2.5002590594561336e-05, "loss": 0.0065, "step": 233380 }, { "epoch": 56.06, "learning_rate": 2.499870473627349e-05, "loss": 0.0029, "step": 233390 }, { "epoch": 56.06, "learning_rate": 2.4994819079324543e-05, "loss": 0.003, "step": 233400 }, { "epoch": 56.06, "learning_rate": 2.4990933623745727e-05, "loss": 0.009, "step": 233410 }, { "epoch": 56.07, "learning_rate": 2.49870483695684e-05, "loss": 0.003, "step": 233420 }, { "epoch": 56.07, "learning_rate": 2.498316331682382e-05, "loss": 0.0021, "step": 233430 }, { "epoch": 56.07, "learning_rate": 2.4979278465543287e-05, "loss": 0.0024, "step": 233440 }, { "epoch": 56.07, "learning_rate": 2.4975393815758074e-05, "loss": 0.0047, "step": 233450 }, { "epoch": 56.08, "learning_rate": 2.497150936749947e-05, "loss": 0.009, "step": 233460 }, { "epoch": 56.08, "learning_rate": 2.4967625120798753e-05, "loss": 0.0039, "step": 233470 }, { "epoch": 56.08, "learning_rate": 2.4963741075687197e-05, "loss": 0.003, "step": 233480 }, { "epoch": 56.08, "learning_rate": 2.4959857232196122e-05, "loss": 0.005, "step": 233490 }, { "epoch": 56.09, "learning_rate": 2.4955973590356756e-05, "loss": 0.0069, "step": 233500 }, { "epoch": 56.09, "learning_rate": 2.4952090150200375e-05, "loss": 0.0026, "step": 233510 }, { "epoch": 56.09, "learning_rate": 2.494820691175828e-05, "loss": 0.0048, "step": 233520 }, { "epoch": 56.09, "learning_rate": 2.4944323875061742e-05, "loss": 0.0048, "step": 233530 }, { "epoch": 56.09, "learning_rate": 2.4940441040142028e-05, "loss": 0.0028, "step": 233540 }, { "epoch": 56.1, "learning_rate": 2.4936558407030393e-05, "loss": 0.0029, "step": 233550 }, { "epoch": 56.1, "learning_rate": 2.4932675975758114e-05, "loss": 0.0048, "step": 233560 }, { "epoch": 56.1, "learning_rate": 2.492879374635646e-05, "loss": 0.0119, "step": 233570 }, { "epoch": 56.1, "learning_rate": 2.492491171885667e-05, "loss": 0.0054, "step": 233580 }, { "epoch": 56.11, "learning_rate": 2.4921029893290067e-05, "loss": 0.0054, "step": 233590 }, { "epoch": 56.11, "learning_rate": 2.491714826968785e-05, "loss": 0.0058, "step": 233600 }, { "epoch": 56.11, "learning_rate": 2.4913266848081308e-05, "loss": 0.0056, "step": 233610 }, { "epoch": 56.11, "learning_rate": 2.4909385628501664e-05, "loss": 0.0073, "step": 233620 }, { "epoch": 56.11, "learning_rate": 2.4905504610980225e-05, "loss": 0.0056, "step": 233630 }, { "epoch": 56.12, "learning_rate": 2.490162379554824e-05, "loss": 0.0024, "step": 233640 }, { "epoch": 56.12, "learning_rate": 2.4897743182236904e-05, "loss": 0.0034, "step": 233650 }, { "epoch": 56.12, "learning_rate": 2.489386277107753e-05, "loss": 0.0031, "step": 233660 }, { "epoch": 56.12, "learning_rate": 2.4889982562101345e-05, "loss": 0.0031, "step": 233670 }, { "epoch": 56.13, "learning_rate": 2.4886102555339596e-05, "loss": 0.0069, "step": 233680 }, { "epoch": 56.13, "learning_rate": 2.488222275082353e-05, "loss": 0.0016, "step": 233690 }, { "epoch": 56.13, "learning_rate": 2.4878343148584395e-05, "loss": 0.0024, "step": 233700 }, { "epoch": 56.13, "learning_rate": 2.4874463748653427e-05, "loss": 0.0076, "step": 233710 }, { "epoch": 56.14, "learning_rate": 2.4870584551061853e-05, "loss": 0.0022, "step": 233720 }, { "epoch": 56.14, "learning_rate": 2.4866705555840968e-05, "loss": 0.0025, "step": 233730 }, { "epoch": 56.14, "learning_rate": 2.4862826763021956e-05, "loss": 0.0029, "step": 233740 }, { "epoch": 56.14, "learning_rate": 2.4858948172636053e-05, "loss": 0.0016, "step": 233750 }, { "epoch": 56.14, "learning_rate": 2.4855069784714528e-05, "loss": 0.0019, "step": 233760 }, { "epoch": 56.15, "learning_rate": 2.48511915992886e-05, "loss": 0.0031, "step": 233770 }, { "epoch": 56.15, "learning_rate": 2.4847313616389495e-05, "loss": 0.0035, "step": 233780 }, { "epoch": 56.15, "learning_rate": 2.4843435836048447e-05, "loss": 0.003, "step": 233790 }, { "epoch": 56.15, "learning_rate": 2.483955825829668e-05, "loss": 0.0037, "step": 233800 }, { "epoch": 56.16, "learning_rate": 2.483568088316543e-05, "loss": 0.0043, "step": 233810 }, { "epoch": 56.16, "learning_rate": 2.4831803710685908e-05, "loss": 0.0034, "step": 233820 }, { "epoch": 56.16, "learning_rate": 2.4827926740889352e-05, "loss": 0.0067, "step": 233830 }, { "epoch": 56.16, "learning_rate": 2.4824049973806978e-05, "loss": 0.0028, "step": 233840 }, { "epoch": 56.16, "learning_rate": 2.4820173409470004e-05, "loss": 0.0031, "step": 233850 }, { "epoch": 56.17, "learning_rate": 2.4816297047909627e-05, "loss": 0.0097, "step": 233860 }, { "epoch": 56.17, "learning_rate": 2.481242088915713e-05, "loss": 0.0082, "step": 233870 }, { "epoch": 56.17, "learning_rate": 2.480854493324366e-05, "loss": 0.0044, "step": 233880 }, { "epoch": 56.17, "learning_rate": 2.480466918020044e-05, "loss": 0.0066, "step": 233890 }, { "epoch": 56.18, "learning_rate": 2.4800793630058718e-05, "loss": 0.0016, "step": 233900 }, { "epoch": 56.18, "learning_rate": 2.479691828284968e-05, "loss": 0.0055, "step": 233910 }, { "epoch": 56.18, "learning_rate": 2.4793043138604544e-05, "loss": 0.0091, "step": 233920 }, { "epoch": 56.18, "learning_rate": 2.4789168197354505e-05, "loss": 0.011, "step": 233930 }, { "epoch": 56.19, "learning_rate": 2.4785293459130783e-05, "loss": 0.0057, "step": 233940 }, { "epoch": 56.19, "learning_rate": 2.4781418923964568e-05, "loss": 0.0029, "step": 233950 }, { "epoch": 56.19, "learning_rate": 2.477754459188705e-05, "loss": 0.0023, "step": 233960 }, { "epoch": 56.19, "learning_rate": 2.4773670462929487e-05, "loss": 0.0041, "step": 233970 }, { "epoch": 56.19, "learning_rate": 2.476979653712302e-05, "loss": 0.0041, "step": 233980 }, { "epoch": 56.2, "learning_rate": 2.4765922814498842e-05, "loss": 0.002, "step": 233990 }, { "epoch": 56.2, "learning_rate": 2.476204929508819e-05, "loss": 0.0019, "step": 234000 }, { "epoch": 56.2, "learning_rate": 2.4758175978922267e-05, "loss": 0.0027, "step": 234010 }, { "epoch": 56.2, "learning_rate": 2.475430286603219e-05, "loss": 0.0016, "step": 234020 }, { "epoch": 56.21, "learning_rate": 2.4750429956449223e-05, "loss": 0.0031, "step": 234030 }, { "epoch": 56.21, "learning_rate": 2.474655725020452e-05, "loss": 0.002, "step": 234040 }, { "epoch": 56.21, "learning_rate": 2.4742684747329288e-05, "loss": 0.002, "step": 234050 }, { "epoch": 56.21, "learning_rate": 2.47388124478547e-05, "loss": 0.0024, "step": 234060 }, { "epoch": 56.22, "learning_rate": 2.4734940351811942e-05, "loss": 0.0052, "step": 234070 }, { "epoch": 56.22, "learning_rate": 2.4731068459232197e-05, "loss": 0.0035, "step": 234080 }, { "epoch": 56.22, "learning_rate": 2.472719677014665e-05, "loss": 0.0028, "step": 234090 }, { "epoch": 56.22, "learning_rate": 2.472332528458645e-05, "loss": 0.0021, "step": 234100 }, { "epoch": 56.22, "learning_rate": 2.471945400258284e-05, "loss": 0.0024, "step": 234110 }, { "epoch": 56.23, "learning_rate": 2.4715582924166947e-05, "loss": 0.0091, "step": 234120 }, { "epoch": 56.23, "learning_rate": 2.4711712049369927e-05, "loss": 0.0028, "step": 234130 }, { "epoch": 56.23, "learning_rate": 2.4707841378223006e-05, "loss": 0.0037, "step": 234140 }, { "epoch": 56.23, "learning_rate": 2.470397091075735e-05, "loss": 0.0052, "step": 234150 }, { "epoch": 56.24, "learning_rate": 2.4700100647004064e-05, "loss": 0.0029, "step": 234160 }, { "epoch": 56.24, "learning_rate": 2.4696230586994386e-05, "loss": 0.0084, "step": 234170 }, { "epoch": 56.24, "learning_rate": 2.4692360730759455e-05, "loss": 0.0047, "step": 234180 }, { "epoch": 56.24, "learning_rate": 2.4688491078330434e-05, "loss": 0.002, "step": 234190 }, { "epoch": 56.24, "learning_rate": 2.468462162973849e-05, "loss": 0.0059, "step": 234200 }, { "epoch": 56.25, "learning_rate": 2.4680752385014782e-05, "loss": 0.0045, "step": 234210 }, { "epoch": 56.25, "learning_rate": 2.4676883344190477e-05, "loss": 0.0038, "step": 234220 }, { "epoch": 56.25, "learning_rate": 2.46730145072967e-05, "loss": 0.0023, "step": 234230 }, { "epoch": 56.25, "learning_rate": 2.4669145874364658e-05, "loss": 0.003, "step": 234240 }, { "epoch": 56.26, "learning_rate": 2.4665277445425495e-05, "loss": 0.0037, "step": 234250 }, { "epoch": 56.26, "learning_rate": 2.4661409220510336e-05, "loss": 0.004, "step": 234260 }, { "epoch": 56.26, "learning_rate": 2.4657541199650326e-05, "loss": 0.0019, "step": 234270 }, { "epoch": 56.26, "learning_rate": 2.4653673382876653e-05, "loss": 0.0032, "step": 234280 }, { "epoch": 56.27, "learning_rate": 2.464980577022045e-05, "loss": 0.0022, "step": 234290 }, { "epoch": 56.27, "learning_rate": 2.464593836171286e-05, "loss": 0.0023, "step": 234300 }, { "epoch": 56.27, "learning_rate": 2.4642071157385027e-05, "loss": 0.0036, "step": 234310 }, { "epoch": 56.27, "learning_rate": 2.4638204157268097e-05, "loss": 0.0023, "step": 234320 }, { "epoch": 56.27, "learning_rate": 2.463433736139321e-05, "loss": 0.0048, "step": 234330 }, { "epoch": 56.28, "learning_rate": 2.4630470769791507e-05, "loss": 0.0133, "step": 234340 }, { "epoch": 56.28, "learning_rate": 2.462660438249413e-05, "loss": 0.0023, "step": 234350 }, { "epoch": 56.28, "learning_rate": 2.4622738199532202e-05, "loss": 0.0028, "step": 234360 }, { "epoch": 56.28, "learning_rate": 2.4618872220936858e-05, "loss": 0.0018, "step": 234370 }, { "epoch": 56.29, "learning_rate": 2.461500644673925e-05, "loss": 0.0037, "step": 234380 }, { "epoch": 56.29, "learning_rate": 2.4611140876970522e-05, "loss": 0.0037, "step": 234390 }, { "epoch": 56.29, "learning_rate": 2.4607275511661743e-05, "loss": 0.0046, "step": 234400 }, { "epoch": 56.29, "learning_rate": 2.4603410350844102e-05, "loss": 0.0037, "step": 234410 }, { "epoch": 56.3, "learning_rate": 2.45995453945487e-05, "loss": 0.0023, "step": 234420 }, { "epoch": 56.3, "learning_rate": 2.4595680642806667e-05, "loss": 0.0033, "step": 234430 }, { "epoch": 56.3, "learning_rate": 2.4591816095649123e-05, "loss": 0.0038, "step": 234440 }, { "epoch": 56.3, "learning_rate": 2.4587951753107197e-05, "loss": 0.0033, "step": 234450 }, { "epoch": 56.3, "learning_rate": 2.4584087615211998e-05, "loss": 0.0024, "step": 234460 }, { "epoch": 56.31, "learning_rate": 2.458022368199465e-05, "loss": 0.0052, "step": 234470 }, { "epoch": 56.31, "learning_rate": 2.4576359953486278e-05, "loss": 0.0082, "step": 234480 }, { "epoch": 56.31, "learning_rate": 2.4572496429717983e-05, "loss": 0.0029, "step": 234490 }, { "epoch": 56.31, "learning_rate": 2.4568633110720885e-05, "loss": 0.002, "step": 234500 }, { "epoch": 56.32, "learning_rate": 2.4564769996526078e-05, "loss": 0.0039, "step": 234510 }, { "epoch": 56.32, "learning_rate": 2.4560907087164708e-05, "loss": 0.0035, "step": 234520 }, { "epoch": 56.32, "learning_rate": 2.455704438266789e-05, "loss": 0.0118, "step": 234530 }, { "epoch": 56.32, "learning_rate": 2.4553181883066663e-05, "loss": 0.0025, "step": 234540 }, { "epoch": 56.32, "learning_rate": 2.454931958839219e-05, "loss": 0.0025, "step": 234550 }, { "epoch": 56.33, "learning_rate": 2.4545457498675567e-05, "loss": 0.0021, "step": 234560 }, { "epoch": 56.33, "learning_rate": 2.4541595613947886e-05, "loss": 0.0067, "step": 234570 }, { "epoch": 56.33, "learning_rate": 2.453773393424025e-05, "loss": 0.0035, "step": 234580 }, { "epoch": 56.33, "learning_rate": 2.4533872459583756e-05, "loss": 0.0025, "step": 234590 }, { "epoch": 56.34, "learning_rate": 2.4530011190009504e-05, "loss": 0.0111, "step": 234600 }, { "epoch": 56.34, "learning_rate": 2.4526150125548574e-05, "loss": 0.0061, "step": 234610 }, { "epoch": 56.34, "learning_rate": 2.4522289266232092e-05, "loss": 0.0034, "step": 234620 }, { "epoch": 56.34, "learning_rate": 2.451842861209115e-05, "loss": 0.0045, "step": 234630 }, { "epoch": 56.35, "learning_rate": 2.4514568163156777e-05, "loss": 0.0034, "step": 234640 }, { "epoch": 56.35, "learning_rate": 2.451070791946013e-05, "loss": 0.002, "step": 234650 }, { "epoch": 56.35, "learning_rate": 2.450684788103227e-05, "loss": 0.002, "step": 234660 }, { "epoch": 56.35, "learning_rate": 2.45029880479043e-05, "loss": 0.0016, "step": 234670 }, { "epoch": 56.35, "learning_rate": 2.4499128420107255e-05, "loss": 0.003, "step": 234680 }, { "epoch": 56.36, "learning_rate": 2.449526899767226e-05, "loss": 0.005, "step": 234690 }, { "epoch": 56.36, "learning_rate": 2.449140978063039e-05, "loss": 0.0042, "step": 234700 }, { "epoch": 56.36, "learning_rate": 2.4487550769012718e-05, "loss": 0.003, "step": 234710 }, { "epoch": 56.36, "learning_rate": 2.4483691962850326e-05, "loss": 0.0021, "step": 234720 }, { "epoch": 56.37, "learning_rate": 2.4479833362174276e-05, "loss": 0.0028, "step": 234730 }, { "epoch": 56.37, "learning_rate": 2.447597496701566e-05, "loss": 0.0036, "step": 234740 }, { "epoch": 56.37, "learning_rate": 2.4472116777405517e-05, "loss": 0.0038, "step": 234750 }, { "epoch": 56.37, "learning_rate": 2.4468258793374964e-05, "loss": 0.0088, "step": 234760 }, { "epoch": 56.38, "learning_rate": 2.4464401014955063e-05, "loss": 0.0064, "step": 234770 }, { "epoch": 56.38, "learning_rate": 2.446054344217683e-05, "loss": 0.0022, "step": 234780 }, { "epoch": 56.38, "learning_rate": 2.445668607507139e-05, "loss": 0.0046, "step": 234790 }, { "epoch": 56.38, "learning_rate": 2.445282891366978e-05, "loss": 0.0078, "step": 234800 }, { "epoch": 56.38, "learning_rate": 2.4448971958003066e-05, "loss": 0.0028, "step": 234810 }, { "epoch": 56.39, "learning_rate": 2.444511520810231e-05, "loss": 0.0051, "step": 234820 }, { "epoch": 56.39, "learning_rate": 2.444125866399856e-05, "loss": 0.0021, "step": 234830 }, { "epoch": 56.39, "learning_rate": 2.443740232572289e-05, "loss": 0.0039, "step": 234840 }, { "epoch": 56.39, "learning_rate": 2.4433546193306334e-05, "loss": 0.0074, "step": 234850 }, { "epoch": 56.4, "learning_rate": 2.4429690266779993e-05, "loss": 0.0031, "step": 234860 }, { "epoch": 56.4, "learning_rate": 2.442583454617487e-05, "loss": 0.0052, "step": 234870 }, { "epoch": 56.4, "learning_rate": 2.4421979031522006e-05, "loss": 0.0045, "step": 234880 }, { "epoch": 56.4, "learning_rate": 2.4418123722852505e-05, "loss": 0.003, "step": 234890 }, { "epoch": 56.4, "learning_rate": 2.441426862019738e-05, "loss": 0.0026, "step": 234900 }, { "epoch": 56.41, "learning_rate": 2.44104137235877e-05, "loss": 0.0019, "step": 234910 }, { "epoch": 56.41, "learning_rate": 2.4406559033054453e-05, "loss": 0.0082, "step": 234920 }, { "epoch": 56.41, "learning_rate": 2.4402704548628743e-05, "loss": 0.0039, "step": 234930 }, { "epoch": 56.41, "learning_rate": 2.4398850270341584e-05, "loss": 0.0015, "step": 234940 }, { "epoch": 56.42, "learning_rate": 2.4394996198224018e-05, "loss": 0.0044, "step": 234950 }, { "epoch": 56.42, "learning_rate": 2.439114233230708e-05, "loss": 0.0019, "step": 234960 }, { "epoch": 56.42, "learning_rate": 2.4387288672621816e-05, "loss": 0.0019, "step": 234970 }, { "epoch": 56.42, "learning_rate": 2.4383435219199245e-05, "loss": 0.0031, "step": 234980 }, { "epoch": 56.43, "learning_rate": 2.4379581972070393e-05, "loss": 0.0061, "step": 234990 }, { "epoch": 56.43, "learning_rate": 2.437572893126634e-05, "loss": 0.0025, "step": 235000 }, { "epoch": 56.43, "learning_rate": 2.437187609681806e-05, "loss": 0.0028, "step": 235010 }, { "epoch": 56.43, "learning_rate": 2.4368023468756585e-05, "loss": 0.0018, "step": 235020 }, { "epoch": 56.43, "learning_rate": 2.4364171047112966e-05, "loss": 0.0028, "step": 235030 }, { "epoch": 56.44, "learning_rate": 2.4360318831918228e-05, "loss": 0.0022, "step": 235040 }, { "epoch": 56.44, "learning_rate": 2.4356466823203373e-05, "loss": 0.0059, "step": 235050 }, { "epoch": 56.44, "learning_rate": 2.4352615020999436e-05, "loss": 0.0031, "step": 235060 }, { "epoch": 56.44, "learning_rate": 2.4348763425337427e-05, "loss": 0.002, "step": 235070 }, { "epoch": 56.45, "learning_rate": 2.4344912036248373e-05, "loss": 0.0025, "step": 235080 }, { "epoch": 56.45, "learning_rate": 2.4341060853763258e-05, "loss": 0.0026, "step": 235090 }, { "epoch": 56.45, "learning_rate": 2.433720987791317e-05, "loss": 0.0015, "step": 235100 }, { "epoch": 56.45, "learning_rate": 2.4333359108729046e-05, "loss": 0.0019, "step": 235110 }, { "epoch": 56.46, "learning_rate": 2.432950854624193e-05, "loss": 0.0017, "step": 235120 }, { "epoch": 56.46, "learning_rate": 2.4325658190482804e-05, "loss": 0.0023, "step": 235130 }, { "epoch": 56.46, "learning_rate": 2.4321808041482734e-05, "loss": 0.0026, "step": 235140 }, { "epoch": 56.46, "learning_rate": 2.4317958099272677e-05, "loss": 0.0024, "step": 235150 }, { "epoch": 56.46, "learning_rate": 2.431410836388362e-05, "loss": 0.0017, "step": 235160 }, { "epoch": 56.47, "learning_rate": 2.4310258835346622e-05, "loss": 0.004, "step": 235170 }, { "epoch": 56.47, "learning_rate": 2.430640951369265e-05, "loss": 0.0055, "step": 235180 }, { "epoch": 56.47, "learning_rate": 2.4302560398952712e-05, "loss": 0.0106, "step": 235190 }, { "epoch": 56.47, "learning_rate": 2.4298711491157806e-05, "loss": 0.0028, "step": 235200 }, { "epoch": 56.48, "learning_rate": 2.4294862790338917e-05, "loss": 0.0039, "step": 235210 }, { "epoch": 56.48, "learning_rate": 2.4291014296527055e-05, "loss": 0.0023, "step": 235220 }, { "epoch": 56.48, "learning_rate": 2.4287166009753182e-05, "loss": 0.0038, "step": 235230 }, { "epoch": 56.48, "learning_rate": 2.428331793004835e-05, "loss": 0.0048, "step": 235240 }, { "epoch": 56.48, "learning_rate": 2.427947005744349e-05, "loss": 0.0074, "step": 235250 }, { "epoch": 56.49, "learning_rate": 2.4275622391969587e-05, "loss": 0.0029, "step": 235260 }, { "epoch": 56.49, "learning_rate": 2.4271774933657664e-05, "loss": 0.0026, "step": 235270 }, { "epoch": 56.49, "learning_rate": 2.42679276825387e-05, "loss": 0.0033, "step": 235280 }, { "epoch": 56.49, "learning_rate": 2.426408063864366e-05, "loss": 0.0026, "step": 235290 }, { "epoch": 56.5, "learning_rate": 2.426023380200353e-05, "loss": 0.0045, "step": 235300 }, { "epoch": 56.5, "learning_rate": 2.4256387172649297e-05, "loss": 0.0016, "step": 235310 }, { "epoch": 56.5, "learning_rate": 2.425254075061193e-05, "loss": 0.0072, "step": 235320 }, { "epoch": 56.5, "learning_rate": 2.4248694535922402e-05, "loss": 0.0058, "step": 235330 }, { "epoch": 56.51, "learning_rate": 2.4244848528611697e-05, "loss": 0.002, "step": 235340 }, { "epoch": 56.51, "learning_rate": 2.4241002728710782e-05, "loss": 0.0047, "step": 235350 }, { "epoch": 56.51, "learning_rate": 2.4237157136250628e-05, "loss": 0.0018, "step": 235360 }, { "epoch": 56.51, "learning_rate": 2.4233311751262182e-05, "loss": 0.003, "step": 235370 }, { "epoch": 56.51, "learning_rate": 2.4229466573776476e-05, "loss": 0.0037, "step": 235380 }, { "epoch": 56.52, "learning_rate": 2.4225621603824416e-05, "loss": 0.0105, "step": 235390 }, { "epoch": 56.52, "learning_rate": 2.422177684143696e-05, "loss": 0.006, "step": 235400 }, { "epoch": 56.52, "learning_rate": 2.4217932286645116e-05, "loss": 0.0031, "step": 235410 }, { "epoch": 56.52, "learning_rate": 2.4214087939479817e-05, "loss": 0.0184, "step": 235420 }, { "epoch": 56.53, "learning_rate": 2.421024379997204e-05, "loss": 0.0028, "step": 235430 }, { "epoch": 56.53, "learning_rate": 2.4206399868152717e-05, "loss": 0.0085, "step": 235440 }, { "epoch": 56.53, "learning_rate": 2.4202556144052824e-05, "loss": 0.0032, "step": 235450 }, { "epoch": 56.53, "learning_rate": 2.419871262770331e-05, "loss": 0.0025, "step": 235460 }, { "epoch": 56.54, "learning_rate": 2.4194869319135116e-05, "loss": 0.0029, "step": 235470 }, { "epoch": 56.54, "learning_rate": 2.419102621837921e-05, "loss": 0.0054, "step": 235480 }, { "epoch": 56.54, "learning_rate": 2.4187183325466533e-05, "loss": 0.0041, "step": 235490 }, { "epoch": 56.54, "learning_rate": 2.418334064042801e-05, "loss": 0.002, "step": 235500 }, { "epoch": 56.54, "learning_rate": 2.417949816329463e-05, "loss": 0.0036, "step": 235510 }, { "epoch": 56.55, "learning_rate": 2.4175655894097333e-05, "loss": 0.0044, "step": 235520 }, { "epoch": 56.55, "learning_rate": 2.4171813832867023e-05, "loss": 0.0047, "step": 235530 }, { "epoch": 56.55, "learning_rate": 2.416797197963465e-05, "loss": 0.0098, "step": 235540 }, { "epoch": 56.55, "learning_rate": 2.416413033443118e-05, "loss": 0.0097, "step": 235550 }, { "epoch": 56.56, "learning_rate": 2.4160288897287538e-05, "loss": 0.0036, "step": 235560 }, { "epoch": 56.56, "learning_rate": 2.4156447668234656e-05, "loss": 0.0033, "step": 235570 }, { "epoch": 56.56, "learning_rate": 2.4152606647303466e-05, "loss": 0.0042, "step": 235580 }, { "epoch": 56.56, "learning_rate": 2.4148765834524906e-05, "loss": 0.0041, "step": 235590 }, { "epoch": 56.56, "learning_rate": 2.41449252299299e-05, "loss": 0.0025, "step": 235600 }, { "epoch": 56.57, "learning_rate": 2.4141084833549366e-05, "loss": 0.0042, "step": 235610 }, { "epoch": 56.57, "learning_rate": 2.413724464541428e-05, "loss": 0.0023, "step": 235620 }, { "epoch": 56.57, "learning_rate": 2.4133404665555514e-05, "loss": 0.002, "step": 235630 }, { "epoch": 56.57, "learning_rate": 2.4129564894004e-05, "loss": 0.0047, "step": 235640 }, { "epoch": 56.58, "learning_rate": 2.4125725330790683e-05, "loss": 0.0068, "step": 235650 }, { "epoch": 56.58, "learning_rate": 2.412188597594649e-05, "loss": 0.0039, "step": 235660 }, { "epoch": 56.58, "learning_rate": 2.411804682950229e-05, "loss": 0.0067, "step": 235670 }, { "epoch": 56.58, "learning_rate": 2.4114207891489047e-05, "loss": 0.0137, "step": 235680 }, { "epoch": 56.59, "learning_rate": 2.4110369161937664e-05, "loss": 0.0071, "step": 235690 }, { "epoch": 56.59, "learning_rate": 2.410653064087905e-05, "loss": 0.0038, "step": 235700 }, { "epoch": 56.59, "learning_rate": 2.4102692328344123e-05, "loss": 0.0157, "step": 235710 }, { "epoch": 56.59, "learning_rate": 2.4098854224363786e-05, "loss": 0.0048, "step": 235720 }, { "epoch": 56.59, "learning_rate": 2.4095016328968955e-05, "loss": 0.0023, "step": 235730 }, { "epoch": 56.6, "learning_rate": 2.4091178642190515e-05, "loss": 0.0021, "step": 235740 }, { "epoch": 56.6, "learning_rate": 2.4087341164059407e-05, "loss": 0.0021, "step": 235750 }, { "epoch": 56.6, "learning_rate": 2.408350389460654e-05, "loss": 0.0048, "step": 235760 }, { "epoch": 56.6, "learning_rate": 2.4079666833862774e-05, "loss": 0.0037, "step": 235770 }, { "epoch": 56.61, "learning_rate": 2.4075829981859003e-05, "loss": 0.0221, "step": 235780 }, { "epoch": 56.61, "learning_rate": 2.407199333862618e-05, "loss": 0.0032, "step": 235790 }, { "epoch": 56.61, "learning_rate": 2.4068156904195193e-05, "loss": 0.0059, "step": 235800 }, { "epoch": 56.61, "learning_rate": 2.406432067859688e-05, "loss": 0.0035, "step": 235810 }, { "epoch": 56.62, "learning_rate": 2.406048466186219e-05, "loss": 0.0054, "step": 235820 }, { "epoch": 56.62, "learning_rate": 2.4056648854022e-05, "loss": 0.0018, "step": 235830 }, { "epoch": 56.62, "learning_rate": 2.4052813255107198e-05, "loss": 0.0063, "step": 235840 }, { "epoch": 56.62, "learning_rate": 2.404897786514867e-05, "loss": 0.0037, "step": 235850 }, { "epoch": 56.62, "learning_rate": 2.4045142684177313e-05, "loss": 0.0034, "step": 235860 }, { "epoch": 56.63, "learning_rate": 2.4041307712223997e-05, "loss": 0.0072, "step": 235870 }, { "epoch": 56.63, "learning_rate": 2.40374729493196e-05, "loss": 0.002, "step": 235880 }, { "epoch": 56.63, "learning_rate": 2.4033638395495035e-05, "loss": 0.0015, "step": 235890 }, { "epoch": 56.63, "learning_rate": 2.4029804050781186e-05, "loss": 0.0026, "step": 235900 }, { "epoch": 56.64, "learning_rate": 2.402596991520887e-05, "loss": 0.0019, "step": 235910 }, { "epoch": 56.64, "learning_rate": 2.4022135988809025e-05, "loss": 0.0055, "step": 235920 }, { "epoch": 56.64, "learning_rate": 2.4018302271612504e-05, "loss": 0.0039, "step": 235930 }, { "epoch": 56.64, "learning_rate": 2.4014468763650185e-05, "loss": 0.0037, "step": 235940 }, { "epoch": 56.64, "learning_rate": 2.4010635464952928e-05, "loss": 0.0085, "step": 235950 }, { "epoch": 56.65, "learning_rate": 2.4006802375551618e-05, "loss": 0.005, "step": 235960 }, { "epoch": 56.65, "learning_rate": 2.400296949547712e-05, "loss": 0.0075, "step": 235970 }, { "epoch": 56.65, "learning_rate": 2.3999136824760294e-05, "loss": 0.0044, "step": 235980 }, { "epoch": 56.65, "learning_rate": 2.399530436343201e-05, "loss": 0.0046, "step": 235990 }, { "epoch": 56.66, "learning_rate": 2.399147211152313e-05, "loss": 0.0049, "step": 236000 }, { "epoch": 56.66, "learning_rate": 2.398764006906451e-05, "loss": 0.004, "step": 236010 }, { "epoch": 56.66, "learning_rate": 2.3983808236087003e-05, "loss": 0.0031, "step": 236020 }, { "epoch": 56.66, "learning_rate": 2.3979976612621497e-05, "loss": 0.0048, "step": 236030 }, { "epoch": 56.67, "learning_rate": 2.397614519869885e-05, "loss": 0.0065, "step": 236040 }, { "epoch": 56.67, "learning_rate": 2.3972313994349866e-05, "loss": 0.0029, "step": 236050 }, { "epoch": 56.67, "learning_rate": 2.396848299960544e-05, "loss": 0.0034, "step": 236060 }, { "epoch": 56.67, "learning_rate": 2.3964652214496423e-05, "loss": 0.0026, "step": 236070 }, { "epoch": 56.67, "learning_rate": 2.3960821639053653e-05, "loss": 0.0025, "step": 236080 }, { "epoch": 56.68, "learning_rate": 2.3956991273307984e-05, "loss": 0.0112, "step": 236090 }, { "epoch": 56.68, "learning_rate": 2.3953161117290258e-05, "loss": 0.0032, "step": 236100 }, { "epoch": 56.68, "learning_rate": 2.394933117103132e-05, "loss": 0.0027, "step": 236110 }, { "epoch": 56.68, "learning_rate": 2.3945501434561996e-05, "loss": 0.0024, "step": 236120 }, { "epoch": 56.69, "learning_rate": 2.394167190791318e-05, "loss": 0.0064, "step": 236130 }, { "epoch": 56.69, "learning_rate": 2.3937842591115662e-05, "loss": 0.0039, "step": 236140 }, { "epoch": 56.69, "learning_rate": 2.393401348420028e-05, "loss": 0.0091, "step": 236150 }, { "epoch": 56.69, "learning_rate": 2.3930184587197903e-05, "loss": 0.0019, "step": 236160 }, { "epoch": 56.7, "learning_rate": 2.3926355900139347e-05, "loss": 0.0027, "step": 236170 }, { "epoch": 56.7, "learning_rate": 2.3922527423055468e-05, "loss": 0.0087, "step": 236180 }, { "epoch": 56.7, "learning_rate": 2.3918699155977037e-05, "loss": 0.006, "step": 236190 }, { "epoch": 56.7, "learning_rate": 2.3914871098934937e-05, "loss": 0.0025, "step": 236200 }, { "epoch": 56.7, "learning_rate": 2.3911043251959985e-05, "loss": 0.0026, "step": 236210 }, { "epoch": 56.71, "learning_rate": 2.3907215615083005e-05, "loss": 0.0075, "step": 236220 }, { "epoch": 56.71, "learning_rate": 2.3903388188334824e-05, "loss": 0.003, "step": 236230 }, { "epoch": 56.71, "learning_rate": 2.3899560971746254e-05, "loss": 0.0026, "step": 236240 }, { "epoch": 56.71, "learning_rate": 2.389573396534812e-05, "loss": 0.0034, "step": 236250 }, { "epoch": 56.72, "learning_rate": 2.3891907169171236e-05, "loss": 0.0024, "step": 236260 }, { "epoch": 56.72, "learning_rate": 2.388808058324644e-05, "loss": 0.0017, "step": 236270 }, { "epoch": 56.72, "learning_rate": 2.3884254207604555e-05, "loss": 0.0027, "step": 236280 }, { "epoch": 56.72, "learning_rate": 2.388042804227634e-05, "loss": 0.0035, "step": 236290 }, { "epoch": 56.72, "learning_rate": 2.387660208729266e-05, "loss": 0.0022, "step": 236300 }, { "epoch": 56.73, "learning_rate": 2.3872776342684317e-05, "loss": 0.0078, "step": 236310 }, { "epoch": 56.73, "learning_rate": 2.3868950808482104e-05, "loss": 0.0049, "step": 236320 }, { "epoch": 56.73, "learning_rate": 2.3865125484716845e-05, "loss": 0.0087, "step": 236330 }, { "epoch": 56.73, "learning_rate": 2.3861300371419338e-05, "loss": 0.0045, "step": 236340 }, { "epoch": 56.74, "learning_rate": 2.3857475468620383e-05, "loss": 0.0026, "step": 236350 }, { "epoch": 56.74, "learning_rate": 2.3853650776350773e-05, "loss": 0.0096, "step": 236360 }, { "epoch": 56.74, "learning_rate": 2.3849826294641357e-05, "loss": 0.0032, "step": 236370 }, { "epoch": 56.74, "learning_rate": 2.3846002023522885e-05, "loss": 0.0067, "step": 236380 }, { "epoch": 56.75, "learning_rate": 2.3842177963026148e-05, "loss": 0.003, "step": 236390 }, { "epoch": 56.75, "learning_rate": 2.3838354113181982e-05, "loss": 0.004, "step": 236400 }, { "epoch": 56.75, "learning_rate": 2.383453047402116e-05, "loss": 0.0021, "step": 236410 }, { "epoch": 56.75, "learning_rate": 2.38307070455745e-05, "loss": 0.0055, "step": 236420 }, { "epoch": 56.75, "learning_rate": 2.382688382787273e-05, "loss": 0.0027, "step": 236430 }, { "epoch": 56.76, "learning_rate": 2.3823060820946697e-05, "loss": 0.003, "step": 236440 }, { "epoch": 56.76, "learning_rate": 2.3819238024827167e-05, "loss": 0.0052, "step": 236450 }, { "epoch": 56.76, "learning_rate": 2.381541543954493e-05, "loss": 0.0028, "step": 236460 }, { "epoch": 56.76, "learning_rate": 2.3811593065130767e-05, "loss": 0.003, "step": 236470 }, { "epoch": 56.77, "learning_rate": 2.3807770901615463e-05, "loss": 0.0022, "step": 236480 }, { "epoch": 56.77, "learning_rate": 2.380394894902979e-05, "loss": 0.0015, "step": 236490 }, { "epoch": 56.77, "learning_rate": 2.3800127207404514e-05, "loss": 0.0041, "step": 236500 }, { "epoch": 56.77, "learning_rate": 2.3796305676770477e-05, "loss": 0.0052, "step": 236510 }, { "epoch": 56.78, "learning_rate": 2.379248435715838e-05, "loss": 0.0032, "step": 236520 }, { "epoch": 56.78, "learning_rate": 2.3788663248599007e-05, "loss": 0.0036, "step": 236530 }, { "epoch": 56.78, "learning_rate": 2.378484235112317e-05, "loss": 0.0022, "step": 236540 }, { "epoch": 56.78, "learning_rate": 2.3781021664761617e-05, "loss": 0.0037, "step": 236550 }, { "epoch": 56.78, "learning_rate": 2.377720118954512e-05, "loss": 0.0034, "step": 236560 }, { "epoch": 56.79, "learning_rate": 2.3773380925504435e-05, "loss": 0.0049, "step": 236570 }, { "epoch": 56.79, "learning_rate": 2.376956087267033e-05, "loss": 0.0044, "step": 236580 }, { "epoch": 56.79, "learning_rate": 2.3765741031073584e-05, "loss": 0.0034, "step": 236590 }, { "epoch": 56.79, "learning_rate": 2.3761921400744926e-05, "loss": 0.002, "step": 236600 }, { "epoch": 56.8, "learning_rate": 2.375810198171517e-05, "loss": 0.0035, "step": 236610 }, { "epoch": 56.8, "learning_rate": 2.3754282774015026e-05, "loss": 0.0031, "step": 236620 }, { "epoch": 56.8, "learning_rate": 2.3750463777675265e-05, "loss": 0.003, "step": 236630 }, { "epoch": 56.8, "learning_rate": 2.3746644992726623e-05, "loss": 0.0029, "step": 236640 }, { "epoch": 56.8, "learning_rate": 2.3742826419199916e-05, "loss": 0.0026, "step": 236650 }, { "epoch": 56.81, "learning_rate": 2.373900805712583e-05, "loss": 0.0021, "step": 236660 }, { "epoch": 56.81, "learning_rate": 2.3735189906535117e-05, "loss": 0.0092, "step": 236670 }, { "epoch": 56.81, "learning_rate": 2.3731371967458564e-05, "loss": 0.0022, "step": 236680 }, { "epoch": 56.81, "learning_rate": 2.3727554239926907e-05, "loss": 0.0024, "step": 236690 }, { "epoch": 56.82, "learning_rate": 2.372373672397088e-05, "loss": 0.002, "step": 236700 }, { "epoch": 56.82, "learning_rate": 2.371991941962122e-05, "loss": 0.002, "step": 236710 }, { "epoch": 56.82, "learning_rate": 2.371610232690869e-05, "loss": 0.0087, "step": 236720 }, { "epoch": 56.82, "learning_rate": 2.3712285445864007e-05, "loss": 0.0019, "step": 236730 }, { "epoch": 56.83, "learning_rate": 2.3708468776517906e-05, "loss": 0.0083, "step": 236740 }, { "epoch": 56.83, "learning_rate": 2.370465231890117e-05, "loss": 0.0023, "step": 236750 }, { "epoch": 56.83, "learning_rate": 2.3700836073044486e-05, "loss": 0.0034, "step": 236760 }, { "epoch": 56.83, "learning_rate": 2.3697020038978574e-05, "loss": 0.004, "step": 236770 }, { "epoch": 56.83, "learning_rate": 2.369320421673421e-05, "loss": 0.003, "step": 236780 }, { "epoch": 56.84, "learning_rate": 2.368938860634213e-05, "loss": 0.0036, "step": 236790 }, { "epoch": 56.84, "learning_rate": 2.368557320783299e-05, "loss": 0.0037, "step": 236800 }, { "epoch": 56.84, "learning_rate": 2.368175802123759e-05, "loss": 0.0037, "step": 236810 }, { "epoch": 56.84, "learning_rate": 2.3677943046586616e-05, "loss": 0.0058, "step": 236820 }, { "epoch": 56.85, "learning_rate": 2.3674128283910808e-05, "loss": 0.0016, "step": 236830 }, { "epoch": 56.85, "learning_rate": 2.3670313733240872e-05, "loss": 0.0027, "step": 236840 }, { "epoch": 56.85, "learning_rate": 2.3666499394607546e-05, "loss": 0.0027, "step": 236850 }, { "epoch": 56.85, "learning_rate": 2.3662685268041525e-05, "loss": 0.002, "step": 236860 }, { "epoch": 56.86, "learning_rate": 2.3658871353573543e-05, "loss": 0.0052, "step": 236870 }, { "epoch": 56.86, "learning_rate": 2.365505765123428e-05, "loss": 0.0015, "step": 236880 }, { "epoch": 56.86, "learning_rate": 2.365124416105452e-05, "loss": 0.0014, "step": 236890 }, { "epoch": 56.86, "learning_rate": 2.3647430883064904e-05, "loss": 0.0028, "step": 236900 }, { "epoch": 56.86, "learning_rate": 2.364361781729615e-05, "loss": 0.0093, "step": 236910 }, { "epoch": 56.87, "learning_rate": 2.3639804963778998e-05, "loss": 0.0021, "step": 236920 }, { "epoch": 56.87, "learning_rate": 2.3635992322544136e-05, "loss": 0.0028, "step": 236930 }, { "epoch": 56.87, "learning_rate": 2.363217989362227e-05, "loss": 0.0016, "step": 236940 }, { "epoch": 56.87, "learning_rate": 2.3628367677044096e-05, "loss": 0.0098, "step": 236950 }, { "epoch": 56.88, "learning_rate": 2.362455567284032e-05, "loss": 0.0028, "step": 236960 }, { "epoch": 56.88, "learning_rate": 2.3620743881041642e-05, "loss": 0.003, "step": 236970 }, { "epoch": 56.88, "learning_rate": 2.3616932301678745e-05, "loss": 0.003, "step": 236980 }, { "epoch": 56.88, "learning_rate": 2.3613120934782346e-05, "loss": 0.0091, "step": 236990 }, { "epoch": 56.88, "learning_rate": 2.3609309780383122e-05, "loss": 0.0027, "step": 237000 }, { "epoch": 56.89, "learning_rate": 2.3605498838511746e-05, "loss": 0.005, "step": 237010 }, { "epoch": 56.89, "learning_rate": 2.3601688109198954e-05, "loss": 0.0119, "step": 237020 }, { "epoch": 56.89, "learning_rate": 2.3597877592475437e-05, "loss": 0.0026, "step": 237030 }, { "epoch": 56.89, "learning_rate": 2.3594067288371836e-05, "loss": 0.0027, "step": 237040 }, { "epoch": 56.9, "learning_rate": 2.359025719691883e-05, "loss": 0.0048, "step": 237050 }, { "epoch": 56.9, "learning_rate": 2.3586447318147154e-05, "loss": 0.0024, "step": 237060 }, { "epoch": 56.9, "learning_rate": 2.3582637652087462e-05, "loss": 0.0021, "step": 237070 }, { "epoch": 56.9, "learning_rate": 2.3578828198770442e-05, "loss": 0.0058, "step": 237080 }, { "epoch": 56.91, "learning_rate": 2.3575018958226763e-05, "loss": 0.0026, "step": 237090 }, { "epoch": 56.91, "learning_rate": 2.3571209930487102e-05, "loss": 0.0042, "step": 237100 }, { "epoch": 56.91, "learning_rate": 2.356740111558214e-05, "loss": 0.0069, "step": 237110 }, { "epoch": 56.91, "learning_rate": 2.3563592513542544e-05, "loss": 0.0024, "step": 237120 }, { "epoch": 56.91, "learning_rate": 2.3559784124398983e-05, "loss": 0.0015, "step": 237130 }, { "epoch": 56.92, "learning_rate": 2.3555975948182137e-05, "loss": 0.0064, "step": 237140 }, { "epoch": 56.92, "learning_rate": 2.3552167984922645e-05, "loss": 0.0033, "step": 237150 }, { "epoch": 56.92, "learning_rate": 2.3548360234651217e-05, "loss": 0.006, "step": 237160 }, { "epoch": 56.92, "learning_rate": 2.3544552697398513e-05, "loss": 0.0025, "step": 237170 }, { "epoch": 56.93, "learning_rate": 2.354074537319514e-05, "loss": 0.0077, "step": 237180 }, { "epoch": 56.93, "learning_rate": 2.3536938262071817e-05, "loss": 0.0022, "step": 237190 }, { "epoch": 56.93, "learning_rate": 2.3533131364059187e-05, "loss": 0.0068, "step": 237200 }, { "epoch": 56.93, "learning_rate": 2.3529324679187898e-05, "loss": 0.0024, "step": 237210 }, { "epoch": 56.94, "learning_rate": 2.3525518207488618e-05, "loss": 0.0408, "step": 237220 }, { "epoch": 56.94, "learning_rate": 2.3521711948991993e-05, "loss": 0.0032, "step": 237230 }, { "epoch": 56.94, "learning_rate": 2.351790590372867e-05, "loss": 0.0016, "step": 237240 }, { "epoch": 56.94, "learning_rate": 2.35141000717293e-05, "loss": 0.0077, "step": 237250 }, { "epoch": 56.94, "learning_rate": 2.351029445302455e-05, "loss": 0.0018, "step": 237260 }, { "epoch": 56.95, "learning_rate": 2.3506489047645074e-05, "loss": 0.0046, "step": 237270 }, { "epoch": 56.95, "learning_rate": 2.3502683855621487e-05, "loss": 0.0086, "step": 237280 }, { "epoch": 56.95, "learning_rate": 2.349887887698442e-05, "loss": 0.0108, "step": 237290 }, { "epoch": 57.0, "learning_rate": 2.3495074111764564e-05, "loss": 0.0024, "step": 237300 }, { "epoch": 57.0, "learning_rate": 2.349126955999255e-05, "loss": 0.0016, "step": 237310 }, { "epoch": 57.01, "learning_rate": 2.3487465221698967e-05, "loss": 0.0026, "step": 237320 }, { "epoch": 57.01, "learning_rate": 2.3483661096914505e-05, "loss": 0.0017, "step": 237330 }, { "epoch": 57.01, "learning_rate": 2.347985718566978e-05, "loss": 0.0054, "step": 237340 }, { "epoch": 57.01, "learning_rate": 2.3476053487995425e-05, "loss": 0.0031, "step": 237350 }, { "epoch": 57.02, "learning_rate": 2.3472250003922076e-05, "loss": 0.0025, "step": 237360 }, { "epoch": 57.02, "learning_rate": 2.346844673348036e-05, "loss": 0.0046, "step": 237370 }, { "epoch": 57.02, "learning_rate": 2.3464643676700903e-05, "loss": 0.0046, "step": 237380 }, { "epoch": 57.02, "learning_rate": 2.3460840833614316e-05, "loss": 0.0033, "step": 237390 }, { "epoch": 57.02, "learning_rate": 2.3457038204251265e-05, "loss": 0.0062, "step": 237400 }, { "epoch": 57.03, "learning_rate": 2.3453235788642365e-05, "loss": 0.0114, "step": 237410 }, { "epoch": 57.03, "learning_rate": 2.344943358681818e-05, "loss": 0.0025, "step": 237420 }, { "epoch": 57.03, "learning_rate": 2.34456315988094e-05, "loss": 0.0017, "step": 237430 }, { "epoch": 57.03, "learning_rate": 2.3441829824646604e-05, "loss": 0.0052, "step": 237440 }, { "epoch": 57.04, "learning_rate": 2.3438028264360445e-05, "loss": 0.0021, "step": 237450 }, { "epoch": 57.04, "learning_rate": 2.343422691798147e-05, "loss": 0.0022, "step": 237460 }, { "epoch": 57.04, "learning_rate": 2.343042578554036e-05, "loss": 0.0045, "step": 237470 }, { "epoch": 57.04, "learning_rate": 2.342662486706769e-05, "loss": 0.004, "step": 237480 }, { "epoch": 57.05, "learning_rate": 2.3422824162594088e-05, "loss": 0.0023, "step": 237490 }, { "epoch": 57.05, "learning_rate": 2.341902367215014e-05, "loss": 0.002, "step": 237500 }, { "epoch": 57.05, "learning_rate": 2.3415223395766477e-05, "loss": 0.0038, "step": 237510 }, { "epoch": 57.05, "learning_rate": 2.341142333347368e-05, "loss": 0.0026, "step": 237520 }, { "epoch": 57.05, "learning_rate": 2.340762348530235e-05, "loss": 0.0039, "step": 237530 }, { "epoch": 57.06, "learning_rate": 2.3403823851283112e-05, "loss": 0.0093, "step": 237540 }, { "epoch": 57.06, "learning_rate": 2.3400024431446578e-05, "loss": 0.0036, "step": 237550 }, { "epoch": 57.06, "learning_rate": 2.3396225225823276e-05, "loss": 0.0018, "step": 237560 }, { "epoch": 57.06, "learning_rate": 2.3392426234443864e-05, "loss": 0.0028, "step": 237570 }, { "epoch": 57.07, "learning_rate": 2.3388627457338925e-05, "loss": 0.0025, "step": 237580 }, { "epoch": 57.07, "learning_rate": 2.3384828894539034e-05, "loss": 0.0017, "step": 237590 }, { "epoch": 57.07, "learning_rate": 2.3381030546074796e-05, "loss": 0.0088, "step": 237600 }, { "epoch": 57.07, "learning_rate": 2.337723241197679e-05, "loss": 0.0037, "step": 237610 }, { "epoch": 57.08, "learning_rate": 2.3373434492275608e-05, "loss": 0.002, "step": 237620 }, { "epoch": 57.08, "learning_rate": 2.3369636787001814e-05, "loss": 0.0021, "step": 237630 }, { "epoch": 57.08, "learning_rate": 2.3365839296186055e-05, "loss": 0.0024, "step": 237640 }, { "epoch": 57.08, "learning_rate": 2.3362042019858842e-05, "loss": 0.0023, "step": 237650 }, { "epoch": 57.08, "learning_rate": 2.3358244958050774e-05, "loss": 0.0014, "step": 237660 }, { "epoch": 57.09, "learning_rate": 2.3354448110792447e-05, "loss": 0.0036, "step": 237670 }, { "epoch": 57.09, "learning_rate": 2.335065147811443e-05, "loss": 0.0018, "step": 237680 }, { "epoch": 57.09, "learning_rate": 2.334685506004732e-05, "loss": 0.002, "step": 237690 }, { "epoch": 57.09, "learning_rate": 2.334305885662162e-05, "loss": 0.0016, "step": 237700 }, { "epoch": 57.1, "learning_rate": 2.3339262867867974e-05, "loss": 0.0057, "step": 237710 }, { "epoch": 57.1, "learning_rate": 2.3335467093816915e-05, "loss": 0.0045, "step": 237720 }, { "epoch": 57.1, "learning_rate": 2.3331671534499026e-05, "loss": 0.0023, "step": 237730 }, { "epoch": 57.1, "learning_rate": 2.332787618994487e-05, "loss": 0.0069, "step": 237740 }, { "epoch": 57.1, "learning_rate": 2.3324081060185012e-05, "loss": 0.0025, "step": 237750 }, { "epoch": 57.11, "learning_rate": 2.3320286145250002e-05, "loss": 0.0046, "step": 237760 }, { "epoch": 57.11, "learning_rate": 2.33164914451704e-05, "loss": 0.0055, "step": 237770 }, { "epoch": 57.11, "learning_rate": 2.3312696959976815e-05, "loss": 0.0092, "step": 237780 }, { "epoch": 57.11, "learning_rate": 2.330890268969974e-05, "loss": 0.0026, "step": 237790 }, { "epoch": 57.12, "learning_rate": 2.3305108634369744e-05, "loss": 0.0052, "step": 237800 }, { "epoch": 57.12, "learning_rate": 2.330131479401741e-05, "loss": 0.0038, "step": 237810 }, { "epoch": 57.12, "learning_rate": 2.3297521168673275e-05, "loss": 0.0054, "step": 237820 }, { "epoch": 57.12, "learning_rate": 2.329372775836789e-05, "loss": 0.004, "step": 237830 }, { "epoch": 57.13, "learning_rate": 2.3289934563131798e-05, "loss": 0.0029, "step": 237840 }, { "epoch": 57.13, "learning_rate": 2.328614158299555e-05, "loss": 0.0029, "step": 237850 }, { "epoch": 57.13, "learning_rate": 2.3282348817989696e-05, "loss": 0.0031, "step": 237860 }, { "epoch": 57.13, "learning_rate": 2.3278556268144757e-05, "loss": 0.0019, "step": 237870 }, { "epoch": 57.13, "learning_rate": 2.327476393349133e-05, "loss": 0.0122, "step": 237880 }, { "epoch": 57.14, "learning_rate": 2.32709718140599e-05, "loss": 0.0021, "step": 237890 }, { "epoch": 57.14, "learning_rate": 2.326717990988102e-05, "loss": 0.0021, "step": 237900 }, { "epoch": 57.14, "learning_rate": 2.3263388220985216e-05, "loss": 0.0024, "step": 237910 }, { "epoch": 57.14, "learning_rate": 2.3259596747403057e-05, "loss": 0.0018, "step": 237920 }, { "epoch": 57.15, "learning_rate": 2.3255805489165073e-05, "loss": 0.0065, "step": 237930 }, { "epoch": 57.15, "learning_rate": 2.3252014446301747e-05, "loss": 0.0021, "step": 237940 }, { "epoch": 57.15, "learning_rate": 2.3248223618843655e-05, "loss": 0.0059, "step": 237950 }, { "epoch": 57.15, "learning_rate": 2.3244433006821313e-05, "loss": 0.0095, "step": 237960 }, { "epoch": 57.16, "learning_rate": 2.324064261026525e-05, "loss": 0.0037, "step": 237970 }, { "epoch": 57.16, "learning_rate": 2.323685242920598e-05, "loss": 0.0017, "step": 237980 }, { "epoch": 57.16, "learning_rate": 2.3233062463674037e-05, "loss": 0.0047, "step": 237990 }, { "epoch": 57.16, "learning_rate": 2.3229272713699934e-05, "loss": 0.0023, "step": 238000 }, { "epoch": 57.16, "learning_rate": 2.3225483179314178e-05, "loss": 0.0018, "step": 238010 }, { "epoch": 57.17, "learning_rate": 2.322169386054734e-05, "loss": 0.0086, "step": 238020 }, { "epoch": 57.17, "learning_rate": 2.321790475742988e-05, "loss": 0.0032, "step": 238030 }, { "epoch": 57.17, "learning_rate": 2.321411586999231e-05, "loss": 0.0035, "step": 238040 }, { "epoch": 57.17, "learning_rate": 2.321032719826518e-05, "loss": 0.0058, "step": 238050 }, { "epoch": 57.18, "learning_rate": 2.320653874227899e-05, "loss": 0.0094, "step": 238060 }, { "epoch": 57.18, "learning_rate": 2.3202750502064235e-05, "loss": 0.0034, "step": 238070 }, { "epoch": 57.18, "learning_rate": 2.3198962477651432e-05, "loss": 0.0038, "step": 238080 }, { "epoch": 57.18, "learning_rate": 2.3195174669071084e-05, "loss": 0.0131, "step": 238090 }, { "epoch": 57.18, "learning_rate": 2.31913870763537e-05, "loss": 0.0025, "step": 238100 }, { "epoch": 57.19, "learning_rate": 2.318759969952975e-05, "loss": 0.0023, "step": 238110 }, { "epoch": 57.19, "learning_rate": 2.3183812538629806e-05, "loss": 0.005, "step": 238120 }, { "epoch": 57.19, "learning_rate": 2.3180025593684295e-05, "loss": 0.0024, "step": 238130 }, { "epoch": 57.19, "learning_rate": 2.317623886472375e-05, "loss": 0.0025, "step": 238140 }, { "epoch": 57.2, "learning_rate": 2.3172452351778635e-05, "loss": 0.0063, "step": 238150 }, { "epoch": 57.2, "learning_rate": 2.31686660548795e-05, "loss": 0.0015, "step": 238160 }, { "epoch": 57.2, "learning_rate": 2.3164879974056785e-05, "loss": 0.002, "step": 238170 }, { "epoch": 57.2, "learning_rate": 2.3161094109340974e-05, "loss": 0.0035, "step": 238180 }, { "epoch": 57.21, "learning_rate": 2.31573084607626e-05, "loss": 0.0049, "step": 238190 }, { "epoch": 57.21, "learning_rate": 2.3153523028352125e-05, "loss": 0.0016, "step": 238200 }, { "epoch": 57.21, "learning_rate": 2.314973781214004e-05, "loss": 0.0043, "step": 238210 }, { "epoch": 57.21, "learning_rate": 2.3145952812156817e-05, "loss": 0.0032, "step": 238220 }, { "epoch": 57.21, "learning_rate": 2.3142168028432947e-05, "loss": 0.0033, "step": 238230 }, { "epoch": 57.22, "learning_rate": 2.3138383460998903e-05, "loss": 0.0044, "step": 238240 }, { "epoch": 57.22, "learning_rate": 2.3134599109885148e-05, "loss": 0.0073, "step": 238250 }, { "epoch": 57.22, "learning_rate": 2.3130814975122212e-05, "loss": 0.0023, "step": 238260 }, { "epoch": 57.22, "learning_rate": 2.3127031056740517e-05, "loss": 0.0032, "step": 238270 }, { "epoch": 57.23, "learning_rate": 2.3123247354770532e-05, "loss": 0.003, "step": 238280 }, { "epoch": 57.23, "learning_rate": 2.3119463869242764e-05, "loss": 0.0049, "step": 238290 }, { "epoch": 57.23, "learning_rate": 2.3115680600187683e-05, "loss": 0.0023, "step": 238300 }, { "epoch": 57.23, "learning_rate": 2.3111897547635698e-05, "loss": 0.0027, "step": 238310 }, { "epoch": 57.24, "learning_rate": 2.3108114711617334e-05, "loss": 0.0032, "step": 238320 }, { "epoch": 57.24, "learning_rate": 2.310433209216304e-05, "loss": 0.0022, "step": 238330 }, { "epoch": 57.24, "learning_rate": 2.3100549689303264e-05, "loss": 0.0021, "step": 238340 }, { "epoch": 57.24, "learning_rate": 2.3096767503068485e-05, "loss": 0.0027, "step": 238350 }, { "epoch": 57.24, "learning_rate": 2.3092985533489143e-05, "loss": 0.0065, "step": 238360 }, { "epoch": 57.25, "learning_rate": 2.308920378059571e-05, "loss": 0.0049, "step": 238370 }, { "epoch": 57.25, "learning_rate": 2.3085422244418632e-05, "loss": 0.0027, "step": 238380 }, { "epoch": 57.25, "learning_rate": 2.308164092498834e-05, "loss": 0.009, "step": 238390 }, { "epoch": 57.25, "learning_rate": 2.3077859822335353e-05, "loss": 0.003, "step": 238400 }, { "epoch": 57.26, "learning_rate": 2.3074078936490058e-05, "loss": 0.0041, "step": 238410 }, { "epoch": 57.26, "learning_rate": 2.3070298267482904e-05, "loss": 0.0017, "step": 238420 }, { "epoch": 57.26, "learning_rate": 2.3066517815344374e-05, "loss": 0.002, "step": 238430 }, { "epoch": 57.26, "learning_rate": 2.3062737580104893e-05, "loss": 0.0034, "step": 238440 }, { "epoch": 57.26, "learning_rate": 2.3058957561794907e-05, "loss": 0.0045, "step": 238450 }, { "epoch": 57.27, "learning_rate": 2.3055177760444858e-05, "loss": 0.0029, "step": 238460 }, { "epoch": 57.27, "learning_rate": 2.3051398176085182e-05, "loss": 0.0019, "step": 238470 }, { "epoch": 57.27, "learning_rate": 2.3047618808746315e-05, "loss": 0.0017, "step": 238480 }, { "epoch": 57.27, "learning_rate": 2.3043839658458695e-05, "loss": 0.0031, "step": 238490 }, { "epoch": 57.28, "learning_rate": 2.3040060725252754e-05, "loss": 0.0101, "step": 238500 }, { "epoch": 57.28, "learning_rate": 2.3036282009158926e-05, "loss": 0.0083, "step": 238510 }, { "epoch": 57.28, "learning_rate": 2.3032503510207624e-05, "loss": 0.013, "step": 238520 }, { "epoch": 57.28, "learning_rate": 2.3028725228429316e-05, "loss": 0.0016, "step": 238530 }, { "epoch": 57.29, "learning_rate": 2.302494716385442e-05, "loss": 0.0098, "step": 238540 }, { "epoch": 57.29, "learning_rate": 2.3021169316513337e-05, "loss": 0.0022, "step": 238550 }, { "epoch": 57.29, "learning_rate": 2.301739168643648e-05, "loss": 0.0044, "step": 238560 }, { "epoch": 57.29, "learning_rate": 2.301361427365431e-05, "loss": 0.0051, "step": 238570 }, { "epoch": 57.29, "learning_rate": 2.3009837078197227e-05, "loss": 0.0032, "step": 238580 }, { "epoch": 57.3, "learning_rate": 2.3006060100095663e-05, "loss": 0.0035, "step": 238590 }, { "epoch": 57.3, "learning_rate": 2.3002283339380015e-05, "loss": 0.0018, "step": 238600 }, { "epoch": 57.3, "learning_rate": 2.2998506796080703e-05, "loss": 0.0026, "step": 238610 }, { "epoch": 57.3, "learning_rate": 2.2994730470228153e-05, "loss": 0.0025, "step": 238620 }, { "epoch": 57.31, "learning_rate": 2.299095436185276e-05, "loss": 0.0028, "step": 238630 }, { "epoch": 57.31, "learning_rate": 2.2987178470984948e-05, "loss": 0.0023, "step": 238640 }, { "epoch": 57.31, "learning_rate": 2.2983402797655114e-05, "loss": 0.0024, "step": 238650 }, { "epoch": 57.31, "learning_rate": 2.2979627341893644e-05, "loss": 0.0026, "step": 238660 }, { "epoch": 57.32, "learning_rate": 2.297585210373099e-05, "loss": 0.0077, "step": 238670 }, { "epoch": 57.32, "learning_rate": 2.297207708319754e-05, "loss": 0.0018, "step": 238680 }, { "epoch": 57.32, "learning_rate": 2.2968302280323657e-05, "loss": 0.0079, "step": 238690 }, { "epoch": 57.32, "learning_rate": 2.296452769513978e-05, "loss": 0.0047, "step": 238700 }, { "epoch": 57.32, "learning_rate": 2.29607533276763e-05, "loss": 0.0027, "step": 238710 }, { "epoch": 57.33, "learning_rate": 2.29569791779636e-05, "loss": 0.005, "step": 238720 }, { "epoch": 57.33, "learning_rate": 2.2953205246032083e-05, "loss": 0.0019, "step": 238730 }, { "epoch": 57.33, "learning_rate": 2.294943153191214e-05, "loss": 0.01, "step": 238740 }, { "epoch": 57.33, "learning_rate": 2.294565803563416e-05, "loss": 0.0081, "step": 238750 }, { "epoch": 57.34, "learning_rate": 2.2941884757228526e-05, "loss": 0.003, "step": 238760 }, { "epoch": 57.34, "learning_rate": 2.2938111696725612e-05, "loss": 0.0036, "step": 238770 }, { "epoch": 57.34, "learning_rate": 2.2934338854155863e-05, "loss": 0.0018, "step": 238780 }, { "epoch": 57.34, "learning_rate": 2.2930566229549595e-05, "loss": 0.0022, "step": 238790 }, { "epoch": 57.34, "learning_rate": 2.2926793822937197e-05, "loss": 0.0028, "step": 238800 }, { "epoch": 57.35, "learning_rate": 2.292302163434909e-05, "loss": 0.0038, "step": 238810 }, { "epoch": 57.35, "learning_rate": 2.291924966381564e-05, "loss": 0.0034, "step": 238820 }, { "epoch": 57.35, "learning_rate": 2.2915477911367178e-05, "loss": 0.002, "step": 238830 }, { "epoch": 57.35, "learning_rate": 2.291170637703413e-05, "loss": 0.002, "step": 238840 }, { "epoch": 57.36, "learning_rate": 2.2907935060846846e-05, "loss": 0.0049, "step": 238850 }, { "epoch": 57.36, "learning_rate": 2.2904163962835706e-05, "loss": 0.0036, "step": 238860 }, { "epoch": 57.36, "learning_rate": 2.2900393083031075e-05, "loss": 0.0018, "step": 238870 }, { "epoch": 57.36, "learning_rate": 2.2896622421463314e-05, "loss": 0.005, "step": 238880 }, { "epoch": 57.37, "learning_rate": 2.28928519781628e-05, "loss": 0.0022, "step": 238890 }, { "epoch": 57.37, "learning_rate": 2.2889081753159876e-05, "loss": 0.0039, "step": 238900 }, { "epoch": 57.37, "learning_rate": 2.2885311746484928e-05, "loss": 0.0017, "step": 238910 }, { "epoch": 57.37, "learning_rate": 2.2881541958168335e-05, "loss": 0.0014, "step": 238920 }, { "epoch": 57.37, "learning_rate": 2.2877772388240387e-05, "loss": 0.0124, "step": 238930 }, { "epoch": 57.38, "learning_rate": 2.2874003036731502e-05, "loss": 0.0033, "step": 238940 }, { "epoch": 57.38, "learning_rate": 2.2870233903672018e-05, "loss": 0.0038, "step": 238950 }, { "epoch": 57.38, "learning_rate": 2.2866464989092302e-05, "loss": 0.0022, "step": 238960 }, { "epoch": 57.38, "learning_rate": 2.2862696293022652e-05, "loss": 0.0045, "step": 238970 }, { "epoch": 57.39, "learning_rate": 2.2858927815493468e-05, "loss": 0.0027, "step": 238980 }, { "epoch": 57.39, "learning_rate": 2.2855159556535096e-05, "loss": 0.0041, "step": 238990 }, { "epoch": 57.39, "learning_rate": 2.2851391516177868e-05, "loss": 0.0022, "step": 239000 }, { "epoch": 57.39, "learning_rate": 2.284762369445213e-05, "loss": 0.0027, "step": 239010 }, { "epoch": 57.4, "learning_rate": 2.2843856091388227e-05, "loss": 0.0037, "step": 239020 }, { "epoch": 57.4, "learning_rate": 2.2840088707016506e-05, "loss": 0.002, "step": 239030 }, { "epoch": 57.4, "learning_rate": 2.2836321541367272e-05, "loss": 0.0029, "step": 239040 }, { "epoch": 57.4, "learning_rate": 2.2832554594470917e-05, "loss": 0.0061, "step": 239050 }, { "epoch": 57.4, "learning_rate": 2.2828787866357765e-05, "loss": 0.0021, "step": 239060 }, { "epoch": 57.41, "learning_rate": 2.2825021357058103e-05, "loss": 0.0021, "step": 239070 }, { "epoch": 57.41, "learning_rate": 2.282125506660231e-05, "loss": 0.0037, "step": 239080 }, { "epoch": 57.41, "learning_rate": 2.2817488995020703e-05, "loss": 0.0019, "step": 239090 }, { "epoch": 57.41, "learning_rate": 2.2813723142343613e-05, "loss": 0.0027, "step": 239100 }, { "epoch": 57.42, "learning_rate": 2.280995750860136e-05, "loss": 0.0023, "step": 239110 }, { "epoch": 57.42, "learning_rate": 2.2806192093824274e-05, "loss": 0.0066, "step": 239120 }, { "epoch": 57.42, "learning_rate": 2.280242689804268e-05, "loss": 0.0034, "step": 239130 }, { "epoch": 57.42, "learning_rate": 2.2798661921286873e-05, "loss": 0.0056, "step": 239140 }, { "epoch": 57.42, "learning_rate": 2.2794897163587235e-05, "loss": 0.0039, "step": 239150 }, { "epoch": 57.43, "learning_rate": 2.279113262497403e-05, "loss": 0.0019, "step": 239160 }, { "epoch": 57.43, "learning_rate": 2.2787368305477574e-05, "loss": 0.0025, "step": 239170 }, { "epoch": 57.43, "learning_rate": 2.2783604205128216e-05, "loss": 0.0016, "step": 239180 }, { "epoch": 57.43, "learning_rate": 2.2779840323956246e-05, "loss": 0.0017, "step": 239190 }, { "epoch": 57.44, "learning_rate": 2.2776076661992e-05, "loss": 0.002, "step": 239200 }, { "epoch": 57.44, "learning_rate": 2.2772313219265735e-05, "loss": 0.002, "step": 239210 }, { "epoch": 57.44, "learning_rate": 2.2768549995807804e-05, "loss": 0.0044, "step": 239220 }, { "epoch": 57.44, "learning_rate": 2.2764786991648503e-05, "loss": 0.0029, "step": 239230 }, { "epoch": 57.45, "learning_rate": 2.276102420681813e-05, "loss": 0.0034, "step": 239240 }, { "epoch": 57.45, "learning_rate": 2.2757261641346988e-05, "loss": 0.0024, "step": 239250 }, { "epoch": 57.45, "learning_rate": 2.2753499295265384e-05, "loss": 0.0026, "step": 239260 }, { "epoch": 57.45, "learning_rate": 2.2749737168603607e-05, "loss": 0.0016, "step": 239270 }, { "epoch": 57.45, "learning_rate": 2.2745975261391945e-05, "loss": 0.0022, "step": 239280 }, { "epoch": 57.46, "learning_rate": 2.2742213573660737e-05, "loss": 0.0027, "step": 239290 }, { "epoch": 57.46, "learning_rate": 2.2738452105440235e-05, "loss": 0.0038, "step": 239300 }, { "epoch": 57.46, "learning_rate": 2.273469085676072e-05, "loss": 0.0037, "step": 239310 }, { "epoch": 57.46, "learning_rate": 2.273092982765252e-05, "loss": 0.0059, "step": 239320 }, { "epoch": 57.47, "learning_rate": 2.2727169018145912e-05, "loss": 0.004, "step": 239330 }, { "epoch": 57.47, "learning_rate": 2.2723408428271176e-05, "loss": 0.0099, "step": 239340 }, { "epoch": 57.47, "learning_rate": 2.2719648058058596e-05, "loss": 0.0019, "step": 239350 }, { "epoch": 57.47, "learning_rate": 2.2715887907538454e-05, "loss": 0.0014, "step": 239360 }, { "epoch": 57.48, "learning_rate": 2.2712127976741037e-05, "loss": 0.0058, "step": 239370 }, { "epoch": 57.48, "learning_rate": 2.27083682656966e-05, "loss": 0.0029, "step": 239380 }, { "epoch": 57.48, "learning_rate": 2.2704608774435483e-05, "loss": 0.0044, "step": 239390 }, { "epoch": 57.48, "learning_rate": 2.2700849502987892e-05, "loss": 0.013, "step": 239400 }, { "epoch": 57.48, "learning_rate": 2.269709045138414e-05, "loss": 0.0038, "step": 239410 }, { "epoch": 57.49, "learning_rate": 2.269333161965446e-05, "loss": 0.0052, "step": 239420 }, { "epoch": 57.49, "learning_rate": 2.2689573007829173e-05, "loss": 0.0036, "step": 239430 }, { "epoch": 57.49, "learning_rate": 2.2685814615938545e-05, "loss": 0.0024, "step": 239440 }, { "epoch": 57.49, "learning_rate": 2.2682056444012784e-05, "loss": 0.0022, "step": 239450 }, { "epoch": 57.5, "learning_rate": 2.2678298492082212e-05, "loss": 0.0054, "step": 239460 }, { "epoch": 57.5, "learning_rate": 2.2674540760177078e-05, "loss": 0.0027, "step": 239470 }, { "epoch": 57.5, "learning_rate": 2.2670783248327637e-05, "loss": 0.0018, "step": 239480 }, { "epoch": 57.5, "learning_rate": 2.2667025956564147e-05, "loss": 0.0015, "step": 239490 }, { "epoch": 57.5, "learning_rate": 2.2663268884916878e-05, "loss": 0.0016, "step": 239500 }, { "epoch": 57.51, "learning_rate": 2.2659512033416075e-05, "loss": 0.006, "step": 239510 }, { "epoch": 57.51, "learning_rate": 2.2655755402091976e-05, "loss": 0.0016, "step": 239520 }, { "epoch": 57.51, "learning_rate": 2.2651998990974898e-05, "loss": 0.0025, "step": 239530 }, { "epoch": 57.51, "learning_rate": 2.2648242800095022e-05, "loss": 0.0029, "step": 239540 }, { "epoch": 57.52, "learning_rate": 2.264448682948261e-05, "loss": 0.0058, "step": 239550 }, { "epoch": 57.52, "learning_rate": 2.2640731079167938e-05, "loss": 0.002, "step": 239560 }, { "epoch": 57.52, "learning_rate": 2.2636975549181233e-05, "loss": 0.0055, "step": 239570 }, { "epoch": 57.52, "learning_rate": 2.2633220239552742e-05, "loss": 0.002, "step": 239580 }, { "epoch": 57.53, "learning_rate": 2.2629465150312713e-05, "loss": 0.0063, "step": 239590 }, { "epoch": 57.53, "learning_rate": 2.2625710281491376e-05, "loss": 0.0119, "step": 239600 }, { "epoch": 57.53, "learning_rate": 2.262195563311897e-05, "loss": 0.0053, "step": 239610 }, { "epoch": 57.53, "learning_rate": 2.2618201205225735e-05, "loss": 0.0101, "step": 239620 }, { "epoch": 57.53, "learning_rate": 2.261444699784191e-05, "loss": 0.0032, "step": 239630 }, { "epoch": 57.54, "learning_rate": 2.2610693010997724e-05, "loss": 0.0036, "step": 239640 }, { "epoch": 57.54, "learning_rate": 2.2606939244723406e-05, "loss": 0.0018, "step": 239650 }, { "epoch": 57.54, "learning_rate": 2.2603185699049173e-05, "loss": 0.0039, "step": 239660 }, { "epoch": 57.54, "learning_rate": 2.2599432374005304e-05, "loss": 0.0021, "step": 239670 }, { "epoch": 57.55, "learning_rate": 2.2595679269621968e-05, "loss": 0.0027, "step": 239680 }, { "epoch": 57.55, "learning_rate": 2.2591926385929398e-05, "loss": 0.0022, "step": 239690 }, { "epoch": 57.55, "learning_rate": 2.2588173722957838e-05, "loss": 0.0028, "step": 239700 }, { "epoch": 57.55, "learning_rate": 2.2584421280737504e-05, "loss": 0.003, "step": 239710 }, { "epoch": 57.56, "learning_rate": 2.258066905929861e-05, "loss": 0.0022, "step": 239720 }, { "epoch": 57.56, "learning_rate": 2.2576917058671377e-05, "loss": 0.008, "step": 239730 }, { "epoch": 57.56, "learning_rate": 2.257316527888601e-05, "loss": 0.0024, "step": 239740 }, { "epoch": 57.56, "learning_rate": 2.2569413719972737e-05, "loss": 0.0055, "step": 239750 }, { "epoch": 57.56, "learning_rate": 2.2565662381961738e-05, "loss": 0.0027, "step": 239760 }, { "epoch": 57.57, "learning_rate": 2.2561911264883284e-05, "loss": 0.0041, "step": 239770 }, { "epoch": 57.57, "learning_rate": 2.2558160368767534e-05, "loss": 0.0017, "step": 239780 }, { "epoch": 57.57, "learning_rate": 2.2554409693644686e-05, "loss": 0.0149, "step": 239790 }, { "epoch": 57.57, "learning_rate": 2.255065923954498e-05, "loss": 0.0043, "step": 239800 }, { "epoch": 57.58, "learning_rate": 2.254690900649863e-05, "loss": 0.0039, "step": 239810 }, { "epoch": 57.58, "learning_rate": 2.254315899453579e-05, "loss": 0.0048, "step": 239820 }, { "epoch": 57.58, "learning_rate": 2.253940920368666e-05, "loss": 0.0105, "step": 239830 }, { "epoch": 57.58, "learning_rate": 2.253565963398148e-05, "loss": 0.0019, "step": 239840 }, { "epoch": 57.58, "learning_rate": 2.253191028545043e-05, "loss": 0.0041, "step": 239850 }, { "epoch": 57.59, "learning_rate": 2.2528161158123696e-05, "loss": 0.0015, "step": 239860 }, { "epoch": 57.59, "learning_rate": 2.252441225203147e-05, "loss": 0.0026, "step": 239870 }, { "epoch": 57.59, "learning_rate": 2.2520663567203943e-05, "loss": 0.0035, "step": 239880 }, { "epoch": 57.59, "learning_rate": 2.251691510367131e-05, "loss": 0.0017, "step": 239890 }, { "epoch": 57.6, "learning_rate": 2.2513166861463736e-05, "loss": 0.0054, "step": 239900 }, { "epoch": 57.6, "learning_rate": 2.2509418840611456e-05, "loss": 0.0017, "step": 239910 }, { "epoch": 57.6, "learning_rate": 2.250567104114461e-05, "loss": 0.0036, "step": 239920 }, { "epoch": 57.6, "learning_rate": 2.2501923463093365e-05, "loss": 0.0032, "step": 239930 }, { "epoch": 57.61, "learning_rate": 2.249817610648795e-05, "loss": 0.0052, "step": 239940 }, { "epoch": 57.61, "learning_rate": 2.249442897135854e-05, "loss": 0.0047, "step": 239950 }, { "epoch": 57.61, "learning_rate": 2.2490682057735252e-05, "loss": 0.0026, "step": 239960 }, { "epoch": 57.61, "learning_rate": 2.2486935365648317e-05, "loss": 0.0023, "step": 239970 }, { "epoch": 57.61, "learning_rate": 2.2483188895127887e-05, "loss": 0.0097, "step": 239980 }, { "epoch": 57.62, "learning_rate": 2.247944264620414e-05, "loss": 0.0018, "step": 239990 }, { "epoch": 57.62, "learning_rate": 2.2475696618907237e-05, "loss": 0.0067, "step": 240000 }, { "epoch": 57.62, "learning_rate": 2.2471950813267355e-05, "loss": 0.0034, "step": 240010 }, { "epoch": 57.62, "learning_rate": 2.2468205229314648e-05, "loss": 0.0043, "step": 240020 }, { "epoch": 57.63, "learning_rate": 2.246445986707927e-05, "loss": 0.0018, "step": 240030 }, { "epoch": 57.63, "learning_rate": 2.2460714726591413e-05, "loss": 0.008, "step": 240040 }, { "epoch": 57.63, "learning_rate": 2.2456969807881245e-05, "loss": 0.0067, "step": 240050 }, { "epoch": 57.63, "learning_rate": 2.2453225110978882e-05, "loss": 0.0023, "step": 240060 }, { "epoch": 57.64, "learning_rate": 2.2449480635914482e-05, "loss": 0.0018, "step": 240070 }, { "epoch": 57.64, "learning_rate": 2.2445736382718237e-05, "loss": 0.0076, "step": 240080 }, { "epoch": 57.64, "learning_rate": 2.2441992351420276e-05, "loss": 0.0096, "step": 240090 }, { "epoch": 57.64, "learning_rate": 2.243824854205076e-05, "loss": 0.0038, "step": 240100 }, { "epoch": 57.64, "learning_rate": 2.2434504954639834e-05, "loss": 0.0034, "step": 240110 }, { "epoch": 57.65, "learning_rate": 2.243076158921765e-05, "loss": 0.019, "step": 240120 }, { "epoch": 57.65, "learning_rate": 2.242701844581434e-05, "loss": 0.0137, "step": 240130 }, { "epoch": 57.65, "learning_rate": 2.2423275524460057e-05, "loss": 0.0041, "step": 240140 }, { "epoch": 57.65, "learning_rate": 2.2419532825184947e-05, "loss": 0.003, "step": 240150 }, { "epoch": 57.66, "learning_rate": 2.241579034801915e-05, "loss": 0.002, "step": 240160 }, { "epoch": 57.66, "learning_rate": 2.2412048092992775e-05, "loss": 0.0058, "step": 240170 }, { "epoch": 57.66, "learning_rate": 2.2408306060136015e-05, "loss": 0.0033, "step": 240180 }, { "epoch": 57.66, "learning_rate": 2.2404564249478983e-05, "loss": 0.0022, "step": 240190 }, { "epoch": 57.66, "learning_rate": 2.2400822661051774e-05, "loss": 0.0025, "step": 240200 }, { "epoch": 57.67, "learning_rate": 2.239708129488457e-05, "loss": 0.0047, "step": 240210 }, { "epoch": 57.67, "learning_rate": 2.2393340151007476e-05, "loss": 0.0033, "step": 240220 }, { "epoch": 57.67, "learning_rate": 2.238959922945063e-05, "loss": 0.0031, "step": 240230 }, { "epoch": 57.67, "learning_rate": 2.2385858530244147e-05, "loss": 0.0041, "step": 240240 }, { "epoch": 57.68, "learning_rate": 2.2382118053418166e-05, "loss": 0.0049, "step": 240250 }, { "epoch": 57.68, "learning_rate": 2.237837779900279e-05, "loss": 0.0022, "step": 240260 }, { "epoch": 57.68, "learning_rate": 2.237463776702816e-05, "loss": 0.0017, "step": 240270 }, { "epoch": 57.68, "learning_rate": 2.2370897957524385e-05, "loss": 0.0038, "step": 240280 }, { "epoch": 57.69, "learning_rate": 2.2367158370521586e-05, "loss": 0.0025, "step": 240290 }, { "epoch": 57.69, "learning_rate": 2.2363419006049867e-05, "loss": 0.0031, "step": 240300 }, { "epoch": 57.69, "learning_rate": 2.2359679864139338e-05, "loss": 0.0162, "step": 240310 }, { "epoch": 57.69, "learning_rate": 2.2355940944820143e-05, "loss": 0.0023, "step": 240320 }, { "epoch": 57.69, "learning_rate": 2.2352202248122382e-05, "loss": 0.005, "step": 240330 }, { "epoch": 57.7, "learning_rate": 2.2348463774076123e-05, "loss": 0.0029, "step": 240340 }, { "epoch": 57.7, "learning_rate": 2.2344725522711518e-05, "loss": 0.0134, "step": 240350 }, { "epoch": 57.7, "learning_rate": 2.234098749405866e-05, "loss": 0.0023, "step": 240360 }, { "epoch": 57.7, "learning_rate": 2.233724968814765e-05, "loss": 0.0064, "step": 240370 }, { "epoch": 57.71, "learning_rate": 2.233351210500858e-05, "loss": 0.0041, "step": 240380 }, { "epoch": 57.71, "learning_rate": 2.232977474467156e-05, "loss": 0.0018, "step": 240390 }, { "epoch": 57.71, "learning_rate": 2.232603760716669e-05, "loss": 0.0043, "step": 240400 }, { "epoch": 57.71, "learning_rate": 2.2322300692524036e-05, "loss": 0.0015, "step": 240410 }, { "epoch": 57.72, "learning_rate": 2.2318564000773732e-05, "loss": 0.0056, "step": 240420 }, { "epoch": 57.72, "learning_rate": 2.2314827531945875e-05, "loss": 0.0071, "step": 240430 }, { "epoch": 57.72, "learning_rate": 2.2311091286070497e-05, "loss": 0.0018, "step": 240440 }, { "epoch": 57.72, "learning_rate": 2.2307355263177737e-05, "loss": 0.0023, "step": 240450 }, { "epoch": 57.72, "learning_rate": 2.2303619463297677e-05, "loss": 0.0029, "step": 240460 }, { "epoch": 57.73, "learning_rate": 2.2299883886460403e-05, "loss": 0.0044, "step": 240470 }, { "epoch": 57.73, "learning_rate": 2.229614853269596e-05, "loss": 0.0024, "step": 240480 }, { "epoch": 57.73, "learning_rate": 2.2292413402034474e-05, "loss": 0.0032, "step": 240490 }, { "epoch": 57.73, "learning_rate": 2.2288678494506005e-05, "loss": 0.0022, "step": 240500 }, { "epoch": 57.74, "learning_rate": 2.2284943810140636e-05, "loss": 0.006, "step": 240510 }, { "epoch": 57.74, "learning_rate": 2.2281209348968434e-05, "loss": 0.002, "step": 240520 }, { "epoch": 57.74, "learning_rate": 2.2277475111019487e-05, "loss": 0.0023, "step": 240530 }, { "epoch": 57.74, "learning_rate": 2.2273741096323857e-05, "loss": 0.0028, "step": 240540 }, { "epoch": 57.74, "learning_rate": 2.2270007304911604e-05, "loss": 0.0032, "step": 240550 }, { "epoch": 57.75, "learning_rate": 2.2266273736812826e-05, "loss": 0.0029, "step": 240560 }, { "epoch": 57.75, "learning_rate": 2.2262540392057597e-05, "loss": 0.0031, "step": 240570 }, { "epoch": 57.75, "learning_rate": 2.2258807270675914e-05, "loss": 0.0038, "step": 240580 }, { "epoch": 57.75, "learning_rate": 2.225507437269791e-05, "loss": 0.0085, "step": 240590 }, { "epoch": 57.76, "learning_rate": 2.2251341698153622e-05, "loss": 0.0019, "step": 240600 }, { "epoch": 57.76, "learning_rate": 2.224760924707311e-05, "loss": 0.0022, "step": 240610 }, { "epoch": 57.76, "learning_rate": 2.224387701948643e-05, "loss": 0.0036, "step": 240620 }, { "epoch": 57.76, "learning_rate": 2.2240145015423647e-05, "loss": 0.005, "step": 240630 }, { "epoch": 57.77, "learning_rate": 2.2236413234914805e-05, "loss": 0.0024, "step": 240640 }, { "epoch": 57.77, "learning_rate": 2.223268167798994e-05, "loss": 0.0043, "step": 240650 }, { "epoch": 57.77, "learning_rate": 2.222895034467916e-05, "loss": 0.0023, "step": 240660 }, { "epoch": 57.77, "learning_rate": 2.2225219235012456e-05, "loss": 0.0042, "step": 240670 }, { "epoch": 57.77, "learning_rate": 2.2221488349019903e-05, "loss": 0.0018, "step": 240680 }, { "epoch": 57.78, "learning_rate": 2.2217757686731516e-05, "loss": 0.0016, "step": 240690 }, { "epoch": 57.78, "learning_rate": 2.2214027248177382e-05, "loss": 0.0039, "step": 240700 }, { "epoch": 57.78, "learning_rate": 2.221029703338754e-05, "loss": 0.0082, "step": 240710 }, { "epoch": 57.78, "learning_rate": 2.2206567042391978e-05, "loss": 0.0035, "step": 240720 }, { "epoch": 57.79, "learning_rate": 2.2202837275220783e-05, "loss": 0.0035, "step": 240730 }, { "epoch": 57.79, "learning_rate": 2.2199107731903983e-05, "loss": 0.0039, "step": 240740 }, { "epoch": 57.79, "learning_rate": 2.2195378412471602e-05, "loss": 0.002, "step": 240750 }, { "epoch": 57.79, "learning_rate": 2.2191649316953678e-05, "loss": 0.0019, "step": 240760 }, { "epoch": 57.8, "learning_rate": 2.2187920445380243e-05, "loss": 0.0022, "step": 240770 }, { "epoch": 57.8, "learning_rate": 2.2184191797781324e-05, "loss": 0.0037, "step": 240780 }, { "epoch": 57.8, "learning_rate": 2.2180463374186926e-05, "loss": 0.0079, "step": 240790 }, { "epoch": 57.8, "learning_rate": 2.2176735174627138e-05, "loss": 0.007, "step": 240800 }, { "epoch": 57.8, "learning_rate": 2.217300719913193e-05, "loss": 0.0027, "step": 240810 }, { "epoch": 57.81, "learning_rate": 2.2169279447731306e-05, "loss": 0.0037, "step": 240820 }, { "epoch": 57.81, "learning_rate": 2.2165551920455345e-05, "loss": 0.0094, "step": 240830 }, { "epoch": 57.81, "learning_rate": 2.216182461733403e-05, "loss": 0.0027, "step": 240840 }, { "epoch": 57.81, "learning_rate": 2.2158097538397393e-05, "loss": 0.0024, "step": 240850 }, { "epoch": 57.82, "learning_rate": 2.2154370683675434e-05, "loss": 0.0025, "step": 240860 }, { "epoch": 57.82, "learning_rate": 2.2150644053198173e-05, "loss": 0.0067, "step": 240870 }, { "epoch": 57.82, "learning_rate": 2.2146917646995623e-05, "loss": 0.0016, "step": 240880 }, { "epoch": 57.82, "learning_rate": 2.214319146509777e-05, "loss": 0.0029, "step": 240890 }, { "epoch": 57.82, "learning_rate": 2.213946550753468e-05, "loss": 0.0038, "step": 240900 }, { "epoch": 57.83, "learning_rate": 2.21357397743363e-05, "loss": 0.0076, "step": 240910 }, { "epoch": 57.83, "learning_rate": 2.2132014265532658e-05, "loss": 0.003, "step": 240920 }, { "epoch": 57.83, "learning_rate": 2.2128288981153733e-05, "loss": 0.0021, "step": 240930 }, { "epoch": 57.83, "learning_rate": 2.212456392122958e-05, "loss": 0.0047, "step": 240940 }, { "epoch": 57.84, "learning_rate": 2.212083908579014e-05, "loss": 0.0016, "step": 240950 }, { "epoch": 57.84, "learning_rate": 2.211711447486542e-05, "loss": 0.0048, "step": 240960 }, { "epoch": 57.84, "learning_rate": 2.2113390088485443e-05, "loss": 0.0025, "step": 240970 }, { "epoch": 57.84, "learning_rate": 2.2109665926680184e-05, "loss": 0.0018, "step": 240980 }, { "epoch": 57.85, "learning_rate": 2.210594198947964e-05, "loss": 0.0109, "step": 240990 }, { "epoch": 57.85, "learning_rate": 2.2102218276913796e-05, "loss": 0.0027, "step": 241000 }, { "epoch": 57.85, "learning_rate": 2.2098494789012636e-05, "loss": 0.0035, "step": 241010 }, { "epoch": 57.85, "learning_rate": 2.2094771525806146e-05, "loss": 0.0033, "step": 241020 }, { "epoch": 57.85, "learning_rate": 2.20910484873243e-05, "loss": 0.0022, "step": 241030 }, { "epoch": 57.86, "learning_rate": 2.208732567359713e-05, "loss": 0.0028, "step": 241040 }, { "epoch": 57.86, "learning_rate": 2.2083603084654565e-05, "loss": 0.0023, "step": 241050 }, { "epoch": 57.86, "learning_rate": 2.2079880720526575e-05, "loss": 0.0067, "step": 241060 }, { "epoch": 57.86, "learning_rate": 2.207615858124318e-05, "loss": 0.0044, "step": 241070 }, { "epoch": 57.87, "learning_rate": 2.2072436666834336e-05, "loss": 0.0029, "step": 241080 }, { "epoch": 57.87, "learning_rate": 2.2068714977330012e-05, "loss": 0.0029, "step": 241090 }, { "epoch": 57.87, "learning_rate": 2.2064993512760184e-05, "loss": 0.0054, "step": 241100 }, { "epoch": 57.87, "learning_rate": 2.2061272273154825e-05, "loss": 0.0022, "step": 241110 }, { "epoch": 57.88, "learning_rate": 2.205755125854389e-05, "loss": 0.0028, "step": 241120 }, { "epoch": 57.88, "learning_rate": 2.205383046895736e-05, "loss": 0.0032, "step": 241130 }, { "epoch": 57.88, "learning_rate": 2.2050109904425188e-05, "loss": 0.0078, "step": 241140 }, { "epoch": 57.88, "learning_rate": 2.2046389564977338e-05, "loss": 0.0017, "step": 241150 }, { "epoch": 57.88, "learning_rate": 2.204266945064377e-05, "loss": 0.0079, "step": 241160 }, { "epoch": 57.89, "learning_rate": 2.203894956145443e-05, "loss": 0.0082, "step": 241170 }, { "epoch": 57.89, "learning_rate": 2.2035229897439324e-05, "loss": 0.0023, "step": 241180 }, { "epoch": 57.89, "learning_rate": 2.2031510458628356e-05, "loss": 0.0023, "step": 241190 }, { "epoch": 57.89, "learning_rate": 2.2027791245051478e-05, "loss": 0.0046, "step": 241200 }, { "epoch": 57.9, "learning_rate": 2.2024072256738676e-05, "loss": 0.0031, "step": 241210 }, { "epoch": 57.9, "learning_rate": 2.202035349371988e-05, "loss": 0.0028, "step": 241220 }, { "epoch": 57.9, "learning_rate": 2.2016634956025045e-05, "loss": 0.0026, "step": 241230 }, { "epoch": 57.9, "learning_rate": 2.2012916643684112e-05, "loss": 0.0027, "step": 241240 }, { "epoch": 57.9, "learning_rate": 2.200919855672702e-05, "loss": 0.0022, "step": 241250 }, { "epoch": 57.91, "learning_rate": 2.200548069518372e-05, "loss": 0.0094, "step": 241260 }, { "epoch": 57.91, "learning_rate": 2.2001763059084145e-05, "loss": 0.0021, "step": 241270 }, { "epoch": 57.91, "learning_rate": 2.1998045648458245e-05, "loss": 0.0028, "step": 241280 }, { "epoch": 57.91, "learning_rate": 2.1994328463335944e-05, "loss": 0.0085, "step": 241290 }, { "epoch": 57.92, "learning_rate": 2.1990611503747166e-05, "loss": 0.0037, "step": 241300 }, { "epoch": 57.92, "learning_rate": 2.1986894769721877e-05, "loss": 0.0019, "step": 241310 }, { "epoch": 57.92, "learning_rate": 2.198317826129001e-05, "loss": 0.0025, "step": 241320 }, { "epoch": 57.92, "learning_rate": 2.1979461978481458e-05, "loss": 0.0023, "step": 241330 }, { "epoch": 57.93, "learning_rate": 2.1975745921326153e-05, "loss": 0.0022, "step": 241340 }, { "epoch": 57.93, "learning_rate": 2.1972030089854046e-05, "loss": 0.0023, "step": 241350 }, { "epoch": 57.93, "learning_rate": 2.1968314484095053e-05, "loss": 0.0016, "step": 241360 }, { "epoch": 57.93, "learning_rate": 2.19645991040791e-05, "loss": 0.0031, "step": 241370 }, { "epoch": 57.93, "learning_rate": 2.196088394983609e-05, "loss": 0.0022, "step": 241380 }, { "epoch": 57.94, "learning_rate": 2.1957169021395963e-05, "loss": 0.005, "step": 241390 }, { "epoch": 57.94, "learning_rate": 2.195345431878862e-05, "loss": 0.0066, "step": 241400 }, { "epoch": 57.94, "learning_rate": 2.1949739842043965e-05, "loss": 0.0024, "step": 241410 }, { "epoch": 57.94, "learning_rate": 2.194602559119196e-05, "loss": 0.0097, "step": 241420 }, { "epoch": 57.95, "learning_rate": 2.194231156626247e-05, "loss": 0.0057, "step": 241430 }, { "epoch": 57.95, "learning_rate": 2.1938597767285397e-05, "loss": 0.0047, "step": 241440 }, { "epoch": 57.95, "learning_rate": 2.1934884194290695e-05, "loss": 0.0048, "step": 241450 }, { "epoch": 58.0, "learning_rate": 2.193117084730826e-05, "loss": 0.0032, "step": 241460 }, { "epoch": 58.0, "learning_rate": 2.192745772636794e-05, "loss": 0.0039, "step": 241470 }, { "epoch": 58.01, "learning_rate": 2.19237448314997e-05, "loss": 0.0094, "step": 241480 }, { "epoch": 58.01, "learning_rate": 2.192003216273342e-05, "loss": 0.0112, "step": 241490 }, { "epoch": 58.01, "learning_rate": 2.1916319720099e-05, "loss": 0.0141, "step": 241500 }, { "epoch": 58.01, "learning_rate": 2.1912607503626332e-05, "loss": 0.0018, "step": 241510 }, { "epoch": 58.02, "learning_rate": 2.1908895513345313e-05, "loss": 0.0057, "step": 241520 }, { "epoch": 58.02, "learning_rate": 2.1905183749285835e-05, "loss": 0.0036, "step": 241530 }, { "epoch": 58.02, "learning_rate": 2.1901472211477774e-05, "loss": 0.0021, "step": 241540 }, { "epoch": 58.02, "learning_rate": 2.189776089995106e-05, "loss": 0.0019, "step": 241550 }, { "epoch": 58.02, "learning_rate": 2.189404981473557e-05, "loss": 0.0032, "step": 241560 }, { "epoch": 58.03, "learning_rate": 2.1890338955861157e-05, "loss": 0.0036, "step": 241570 }, { "epoch": 58.03, "learning_rate": 2.1886628323357712e-05, "loss": 0.0017, "step": 241580 }, { "epoch": 58.03, "learning_rate": 2.1882917917255146e-05, "loss": 0.0072, "step": 241590 }, { "epoch": 58.03, "learning_rate": 2.187920773758334e-05, "loss": 0.0014, "step": 241600 }, { "epoch": 58.04, "learning_rate": 2.1875497784372122e-05, "loss": 0.0047, "step": 241610 }, { "epoch": 58.04, "learning_rate": 2.1871788057651427e-05, "loss": 0.0031, "step": 241620 }, { "epoch": 58.04, "learning_rate": 2.18680785574511e-05, "loss": 0.0024, "step": 241630 }, { "epoch": 58.04, "learning_rate": 2.1864369283801017e-05, "loss": 0.0048, "step": 241640 }, { "epoch": 58.04, "learning_rate": 2.186066023673106e-05, "loss": 0.0104, "step": 241650 }, { "epoch": 58.05, "learning_rate": 2.1856951416271086e-05, "loss": 0.0037, "step": 241660 }, { "epoch": 58.05, "learning_rate": 2.185324282245097e-05, "loss": 0.0018, "step": 241670 }, { "epoch": 58.05, "learning_rate": 2.1849534455300556e-05, "loss": 0.0071, "step": 241680 }, { "epoch": 58.05, "learning_rate": 2.1845826314849747e-05, "loss": 0.0082, "step": 241690 }, { "epoch": 58.06, "learning_rate": 2.18421184011284e-05, "loss": 0.0116, "step": 241700 }, { "epoch": 58.06, "learning_rate": 2.183841071416633e-05, "loss": 0.0034, "step": 241710 }, { "epoch": 58.06, "learning_rate": 2.1834703253993445e-05, "loss": 0.0047, "step": 241720 }, { "epoch": 58.06, "learning_rate": 2.1830996020639578e-05, "loss": 0.0054, "step": 241730 }, { "epoch": 58.07, "learning_rate": 2.1827289014134595e-05, "loss": 0.002, "step": 241740 }, { "epoch": 58.07, "learning_rate": 2.182358223450834e-05, "loss": 0.0017, "step": 241750 }, { "epoch": 58.07, "learning_rate": 2.1819875681790662e-05, "loss": 0.0079, "step": 241760 }, { "epoch": 58.07, "learning_rate": 2.1816169356011422e-05, "loss": 0.0057, "step": 241770 }, { "epoch": 58.07, "learning_rate": 2.181246325720046e-05, "loss": 0.0015, "step": 241780 }, { "epoch": 58.08, "learning_rate": 2.1808757385387624e-05, "loss": 0.0036, "step": 241790 }, { "epoch": 58.08, "learning_rate": 2.1805051740602754e-05, "loss": 0.0027, "step": 241800 }, { "epoch": 58.08, "learning_rate": 2.1801346322875698e-05, "loss": 0.0016, "step": 241810 }, { "epoch": 58.08, "learning_rate": 2.1797641132236275e-05, "loss": 0.0021, "step": 241820 }, { "epoch": 58.09, "learning_rate": 2.179393616871435e-05, "loss": 0.0045, "step": 241830 }, { "epoch": 58.09, "learning_rate": 2.179023143233978e-05, "loss": 0.0022, "step": 241840 }, { "epoch": 58.09, "learning_rate": 2.178652692314233e-05, "loss": 0.0028, "step": 241850 }, { "epoch": 58.09, "learning_rate": 2.1782822641151897e-05, "loss": 0.0023, "step": 241860 }, { "epoch": 58.1, "learning_rate": 2.1779118586398282e-05, "loss": 0.0021, "step": 241870 }, { "epoch": 58.1, "learning_rate": 2.177541475891133e-05, "loss": 0.0015, "step": 241880 }, { "epoch": 58.1, "learning_rate": 2.1771711158720852e-05, "loss": 0.0016, "step": 241890 }, { "epoch": 58.1, "learning_rate": 2.1768007785856685e-05, "loss": 0.0015, "step": 241900 }, { "epoch": 58.1, "learning_rate": 2.176430464034865e-05, "loss": 0.002, "step": 241910 }, { "epoch": 58.11, "learning_rate": 2.176060172222654e-05, "loss": 0.0015, "step": 241920 }, { "epoch": 58.11, "learning_rate": 2.175689903152025e-05, "loss": 0.006, "step": 241930 }, { "epoch": 58.11, "learning_rate": 2.1753196568259533e-05, "loss": 0.0046, "step": 241940 }, { "epoch": 58.11, "learning_rate": 2.17494943324742e-05, "loss": 0.0028, "step": 241950 }, { "epoch": 58.12, "learning_rate": 2.1745792324194108e-05, "loss": 0.0023, "step": 241960 }, { "epoch": 58.12, "learning_rate": 2.1742090543449057e-05, "loss": 0.008, "step": 241970 }, { "epoch": 58.12, "learning_rate": 2.1738388990268864e-05, "loss": 0.0016, "step": 241980 }, { "epoch": 58.12, "learning_rate": 2.173468766468329e-05, "loss": 0.002, "step": 241990 }, { "epoch": 58.12, "learning_rate": 2.17309865667222e-05, "loss": 0.0018, "step": 242000 }, { "epoch": 58.13, "learning_rate": 2.1727285696415378e-05, "loss": 0.0025, "step": 242010 }, { "epoch": 58.13, "learning_rate": 2.172358505379263e-05, "loss": 0.0103, "step": 242020 }, { "epoch": 58.13, "learning_rate": 2.1719884638883746e-05, "loss": 0.0018, "step": 242030 }, { "epoch": 58.13, "learning_rate": 2.171618445171854e-05, "loss": 0.0017, "step": 242040 }, { "epoch": 58.14, "learning_rate": 2.1712484492326813e-05, "loss": 0.0021, "step": 242050 }, { "epoch": 58.14, "learning_rate": 2.1708784760738326e-05, "loss": 0.0022, "step": 242060 }, { "epoch": 58.14, "learning_rate": 2.170508525698292e-05, "loss": 0.0033, "step": 242070 }, { "epoch": 58.14, "learning_rate": 2.1701385981090393e-05, "loss": 0.0077, "step": 242080 }, { "epoch": 58.15, "learning_rate": 2.169768693309047e-05, "loss": 0.002, "step": 242090 }, { "epoch": 58.15, "learning_rate": 2.1693988113013003e-05, "loss": 0.0155, "step": 242100 }, { "epoch": 58.15, "learning_rate": 2.169028952088775e-05, "loss": 0.0031, "step": 242110 }, { "epoch": 58.15, "learning_rate": 2.1686591156744513e-05, "loss": 0.0018, "step": 242120 }, { "epoch": 58.15, "learning_rate": 2.1682893020613065e-05, "loss": 0.0019, "step": 242130 }, { "epoch": 58.16, "learning_rate": 2.1679195112523188e-05, "loss": 0.0018, "step": 242140 }, { "epoch": 58.16, "learning_rate": 2.167549743250466e-05, "loss": 0.0094, "step": 242150 }, { "epoch": 58.16, "learning_rate": 2.1671799980587243e-05, "loss": 0.0017, "step": 242160 }, { "epoch": 58.16, "learning_rate": 2.1668102756800773e-05, "loss": 0.0027, "step": 242170 }, { "epoch": 58.17, "learning_rate": 2.166440576117496e-05, "loss": 0.015, "step": 242180 }, { "epoch": 58.17, "learning_rate": 2.1660708993739602e-05, "loss": 0.0075, "step": 242190 }, { "epoch": 58.17, "learning_rate": 2.165701245452445e-05, "loss": 0.0059, "step": 242200 }, { "epoch": 58.17, "learning_rate": 2.1653316143559303e-05, "loss": 0.0053, "step": 242210 }, { "epoch": 58.18, "learning_rate": 2.164962006087394e-05, "loss": 0.0016, "step": 242220 }, { "epoch": 58.18, "learning_rate": 2.164592420649806e-05, "loss": 0.0095, "step": 242230 }, { "epoch": 58.18, "learning_rate": 2.164222858046148e-05, "loss": 0.0031, "step": 242240 }, { "epoch": 58.18, "learning_rate": 2.163853318279396e-05, "loss": 0.0019, "step": 242250 }, { "epoch": 58.18, "learning_rate": 2.1634838013525238e-05, "loss": 0.0071, "step": 242260 }, { "epoch": 58.19, "learning_rate": 2.1631143072685084e-05, "loss": 0.0075, "step": 242270 }, { "epoch": 58.19, "learning_rate": 2.1627448360303255e-05, "loss": 0.0035, "step": 242280 }, { "epoch": 58.19, "learning_rate": 2.1623753876409496e-05, "loss": 0.0024, "step": 242290 }, { "epoch": 58.19, "learning_rate": 2.162005962103355e-05, "loss": 0.0026, "step": 242300 }, { "epoch": 58.2, "learning_rate": 2.1616365594205216e-05, "loss": 0.0046, "step": 242310 }, { "epoch": 58.2, "learning_rate": 2.1612671795954192e-05, "loss": 0.0017, "step": 242320 }, { "epoch": 58.2, "learning_rate": 2.160897822631022e-05, "loss": 0.0026, "step": 242330 }, { "epoch": 58.2, "learning_rate": 2.160528488530309e-05, "loss": 0.0021, "step": 242340 }, { "epoch": 58.2, "learning_rate": 2.1601591772962513e-05, "loss": 0.003, "step": 242350 }, { "epoch": 58.21, "learning_rate": 2.1597898889318248e-05, "loss": 0.002, "step": 242360 }, { "epoch": 58.21, "learning_rate": 2.1594206234400017e-05, "loss": 0.0026, "step": 242370 }, { "epoch": 58.21, "learning_rate": 2.1590513808237566e-05, "loss": 0.0024, "step": 242380 }, { "epoch": 58.21, "learning_rate": 2.158682161086063e-05, "loss": 0.0016, "step": 242390 }, { "epoch": 58.22, "learning_rate": 2.1583129642298927e-05, "loss": 0.0039, "step": 242400 }, { "epoch": 58.22, "learning_rate": 2.157943790258224e-05, "loss": 0.0027, "step": 242410 }, { "epoch": 58.22, "learning_rate": 2.1575746391740243e-05, "loss": 0.008, "step": 242420 }, { "epoch": 58.22, "learning_rate": 2.1572055109802687e-05, "loss": 0.0026, "step": 242430 }, { "epoch": 58.23, "learning_rate": 2.156836405679927e-05, "loss": 0.0021, "step": 242440 }, { "epoch": 58.23, "learning_rate": 2.1564673232759785e-05, "loss": 0.0018, "step": 242450 }, { "epoch": 58.23, "learning_rate": 2.1560982637713894e-05, "loss": 0.0039, "step": 242460 }, { "epoch": 58.23, "learning_rate": 2.155729227169132e-05, "loss": 0.0026, "step": 242470 }, { "epoch": 58.23, "learning_rate": 2.1553602134721812e-05, "loss": 0.0061, "step": 242480 }, { "epoch": 58.24, "learning_rate": 2.1549912226835072e-05, "loss": 0.0124, "step": 242490 }, { "epoch": 58.24, "learning_rate": 2.1546222548060824e-05, "loss": 0.0037, "step": 242500 }, { "epoch": 58.24, "learning_rate": 2.154253309842877e-05, "loss": 0.0014, "step": 242510 }, { "epoch": 58.24, "learning_rate": 2.1538843877968622e-05, "loss": 0.0025, "step": 242520 }, { "epoch": 58.25, "learning_rate": 2.1535154886710096e-05, "loss": 0.0021, "step": 242530 }, { "epoch": 58.25, "learning_rate": 2.153146612468288e-05, "loss": 0.0039, "step": 242540 }, { "epoch": 58.25, "learning_rate": 2.152777759191674e-05, "loss": 0.0021, "step": 242550 }, { "epoch": 58.25, "learning_rate": 2.152408928844131e-05, "loss": 0.002, "step": 242560 }, { "epoch": 58.26, "learning_rate": 2.1520401214286306e-05, "loss": 0.0027, "step": 242570 }, { "epoch": 58.26, "learning_rate": 2.1516713369481463e-05, "loss": 0.0016, "step": 242580 }, { "epoch": 58.26, "learning_rate": 2.1513025754056476e-05, "loss": 0.0032, "step": 242590 }, { "epoch": 58.26, "learning_rate": 2.1509338368040987e-05, "loss": 0.0019, "step": 242600 }, { "epoch": 58.26, "learning_rate": 2.150565121146475e-05, "loss": 0.0024, "step": 242610 }, { "epoch": 58.27, "learning_rate": 2.1501964284357434e-05, "loss": 0.0021, "step": 242620 }, { "epoch": 58.27, "learning_rate": 2.149827758674874e-05, "loss": 0.0048, "step": 242630 }, { "epoch": 58.27, "learning_rate": 2.149459111866835e-05, "loss": 0.0029, "step": 242640 }, { "epoch": 58.27, "learning_rate": 2.149090488014595e-05, "loss": 0.0019, "step": 242650 }, { "epoch": 58.28, "learning_rate": 2.1487218871211234e-05, "loss": 0.0019, "step": 242660 }, { "epoch": 58.28, "learning_rate": 2.1483533091893875e-05, "loss": 0.0013, "step": 242670 }, { "epoch": 58.28, "learning_rate": 2.1479847542223546e-05, "loss": 0.0015, "step": 242680 }, { "epoch": 58.28, "learning_rate": 2.147616222222998e-05, "loss": 0.0021, "step": 242690 }, { "epoch": 58.28, "learning_rate": 2.14724771319428e-05, "loss": 0.0023, "step": 242700 }, { "epoch": 58.29, "learning_rate": 2.1468792271391675e-05, "loss": 0.0017, "step": 242710 }, { "epoch": 58.29, "learning_rate": 2.146510764060633e-05, "loss": 0.0031, "step": 242720 }, { "epoch": 58.29, "learning_rate": 2.1461423239616406e-05, "loss": 0.0024, "step": 242730 }, { "epoch": 58.29, "learning_rate": 2.1457739068451588e-05, "loss": 0.0032, "step": 242740 }, { "epoch": 58.3, "learning_rate": 2.145405512714153e-05, "loss": 0.0021, "step": 242750 }, { "epoch": 58.3, "learning_rate": 2.1450371415715915e-05, "loss": 0.0021, "step": 242760 }, { "epoch": 58.3, "learning_rate": 2.1446687934204395e-05, "loss": 0.002, "step": 242770 }, { "epoch": 58.3, "learning_rate": 2.144300468263664e-05, "loss": 0.0031, "step": 242780 }, { "epoch": 58.31, "learning_rate": 2.1439321661042317e-05, "loss": 0.0028, "step": 242790 }, { "epoch": 58.31, "learning_rate": 2.1435638869451076e-05, "loss": 0.0025, "step": 242800 }, { "epoch": 58.31, "learning_rate": 2.1431956307892553e-05, "loss": 0.0033, "step": 242810 }, { "epoch": 58.31, "learning_rate": 2.1428273976396456e-05, "loss": 0.0016, "step": 242820 }, { "epoch": 58.31, "learning_rate": 2.1424591874992434e-05, "loss": 0.0023, "step": 242830 }, { "epoch": 58.32, "learning_rate": 2.1420910003710093e-05, "loss": 0.0024, "step": 242840 }, { "epoch": 58.32, "learning_rate": 2.1417228362579096e-05, "loss": 0.0051, "step": 242850 }, { "epoch": 58.32, "learning_rate": 2.1413546951629122e-05, "loss": 0.0022, "step": 242860 }, { "epoch": 58.32, "learning_rate": 2.14098657708898e-05, "loss": 0.0017, "step": 242870 }, { "epoch": 58.33, "learning_rate": 2.1406184820390774e-05, "loss": 0.0029, "step": 242880 }, { "epoch": 58.33, "learning_rate": 2.1402504100161698e-05, "loss": 0.0027, "step": 242890 }, { "epoch": 58.33, "learning_rate": 2.1398823610232194e-05, "loss": 0.0054, "step": 242900 }, { "epoch": 58.33, "learning_rate": 2.139514335063192e-05, "loss": 0.0019, "step": 242910 }, { "epoch": 58.34, "learning_rate": 2.13914633213905e-05, "loss": 0.0043, "step": 242920 }, { "epoch": 58.34, "learning_rate": 2.138778352253758e-05, "loss": 0.0014, "step": 242930 }, { "epoch": 58.34, "learning_rate": 2.1384103954102786e-05, "loss": 0.0014, "step": 242940 }, { "epoch": 58.34, "learning_rate": 2.1380424616115735e-05, "loss": 0.0054, "step": 242950 }, { "epoch": 58.34, "learning_rate": 2.13767455086061e-05, "loss": 0.0067, "step": 242960 }, { "epoch": 58.35, "learning_rate": 2.1373066631603494e-05, "loss": 0.0019, "step": 242970 }, { "epoch": 58.35, "learning_rate": 2.1369387985137505e-05, "loss": 0.002, "step": 242980 }, { "epoch": 58.35, "learning_rate": 2.136570956923781e-05, "loss": 0.0053, "step": 242990 }, { "epoch": 58.35, "learning_rate": 2.1362031383934002e-05, "loss": 0.0012, "step": 243000 }, { "epoch": 58.36, "learning_rate": 2.1358353429255705e-05, "loss": 0.0028, "step": 243010 }, { "epoch": 58.36, "learning_rate": 2.1354675705232546e-05, "loss": 0.0018, "step": 243020 }, { "epoch": 58.36, "learning_rate": 2.1350998211894142e-05, "loss": 0.0024, "step": 243030 }, { "epoch": 58.36, "learning_rate": 2.13473209492701e-05, "loss": 0.0027, "step": 243040 }, { "epoch": 58.36, "learning_rate": 2.134364391739004e-05, "loss": 0.0018, "step": 243050 }, { "epoch": 58.37, "learning_rate": 2.1339967116283555e-05, "loss": 0.0033, "step": 243060 }, { "epoch": 58.37, "learning_rate": 2.1336290545980304e-05, "loss": 0.0039, "step": 243070 }, { "epoch": 58.37, "learning_rate": 2.133261420650985e-05, "loss": 0.0031, "step": 243080 }, { "epoch": 58.37, "learning_rate": 2.132893809790179e-05, "loss": 0.0017, "step": 243090 }, { "epoch": 58.38, "learning_rate": 2.1325262220185764e-05, "loss": 0.0049, "step": 243100 }, { "epoch": 58.38, "learning_rate": 2.1321586573391382e-05, "loss": 0.0022, "step": 243110 }, { "epoch": 58.38, "learning_rate": 2.1317911157548187e-05, "loss": 0.0031, "step": 243120 }, { "epoch": 58.38, "learning_rate": 2.1314235972685832e-05, "loss": 0.0033, "step": 243130 }, { "epoch": 58.39, "learning_rate": 2.1310561018833895e-05, "loss": 0.002, "step": 243140 }, { "epoch": 58.39, "learning_rate": 2.130688629602197e-05, "loss": 0.0025, "step": 243150 }, { "epoch": 58.39, "learning_rate": 2.1303211804279653e-05, "loss": 0.0026, "step": 243160 }, { "epoch": 58.39, "learning_rate": 2.1299537543636533e-05, "loss": 0.0024, "step": 243170 }, { "epoch": 58.39, "learning_rate": 2.1295863514122195e-05, "loss": 0.0079, "step": 243180 }, { "epoch": 58.4, "learning_rate": 2.1292189715766214e-05, "loss": 0.0022, "step": 243190 }, { "epoch": 58.4, "learning_rate": 2.1288516148598214e-05, "loss": 0.0062, "step": 243200 }, { "epoch": 58.4, "learning_rate": 2.1284842812647775e-05, "loss": 0.0044, "step": 243210 }, { "epoch": 58.4, "learning_rate": 2.1281169707944422e-05, "loss": 0.0022, "step": 243220 }, { "epoch": 58.41, "learning_rate": 2.1277496834517795e-05, "loss": 0.0057, "step": 243230 }, { "epoch": 58.41, "learning_rate": 2.127382419239745e-05, "loss": 0.002, "step": 243240 }, { "epoch": 58.41, "learning_rate": 2.1270151781612985e-05, "loss": 0.0037, "step": 243250 }, { "epoch": 58.41, "learning_rate": 2.1266479602193916e-05, "loss": 0.0025, "step": 243260 }, { "epoch": 58.41, "learning_rate": 2.126280765416987e-05, "loss": 0.0021, "step": 243270 }, { "epoch": 58.42, "learning_rate": 2.1259135937570402e-05, "loss": 0.0017, "step": 243280 }, { "epoch": 58.42, "learning_rate": 2.1255464452425083e-05, "loss": 0.0075, "step": 243290 }, { "epoch": 58.42, "learning_rate": 2.1251793198763477e-05, "loss": 0.0018, "step": 243300 }, { "epoch": 58.42, "learning_rate": 2.124812217661515e-05, "loss": 0.0018, "step": 243310 }, { "epoch": 58.43, "learning_rate": 2.124445138600966e-05, "loss": 0.0071, "step": 243320 }, { "epoch": 58.43, "learning_rate": 2.124078082697656e-05, "loss": 0.002, "step": 243330 }, { "epoch": 58.43, "learning_rate": 2.1237110499545437e-05, "loss": 0.0024, "step": 243340 }, { "epoch": 58.43, "learning_rate": 2.1233440403745852e-05, "loss": 0.0055, "step": 243350 }, { "epoch": 58.44, "learning_rate": 2.122977053960731e-05, "loss": 0.0026, "step": 243360 }, { "epoch": 58.44, "learning_rate": 2.122610090715941e-05, "loss": 0.0013, "step": 243370 }, { "epoch": 58.44, "learning_rate": 2.1222431506431695e-05, "loss": 0.0021, "step": 243380 }, { "epoch": 58.44, "learning_rate": 2.121876233745371e-05, "loss": 0.0028, "step": 243390 }, { "epoch": 58.44, "learning_rate": 2.1215093400255015e-05, "loss": 0.0022, "step": 243400 }, { "epoch": 58.45, "learning_rate": 2.121142469486514e-05, "loss": 0.0075, "step": 243410 }, { "epoch": 58.45, "learning_rate": 2.1207756221313636e-05, "loss": 0.0055, "step": 243420 }, { "epoch": 58.45, "learning_rate": 2.1204087979630026e-05, "loss": 0.0021, "step": 243430 }, { "epoch": 58.45, "learning_rate": 2.120041996984391e-05, "loss": 0.0019, "step": 243440 }, { "epoch": 58.46, "learning_rate": 2.119675219198477e-05, "loss": 0.0069, "step": 243450 }, { "epoch": 58.46, "learning_rate": 2.119308464608214e-05, "loss": 0.002, "step": 243460 }, { "epoch": 58.46, "learning_rate": 2.11894173321656e-05, "loss": 0.0033, "step": 243470 }, { "epoch": 58.46, "learning_rate": 2.118575025026466e-05, "loss": 0.0027, "step": 243480 }, { "epoch": 58.47, "learning_rate": 2.1182083400408864e-05, "loss": 0.0033, "step": 243490 }, { "epoch": 58.47, "learning_rate": 2.117841678262769e-05, "loss": 0.0022, "step": 243500 }, { "epoch": 58.47, "learning_rate": 2.117475039695073e-05, "loss": 0.0031, "step": 243510 }, { "epoch": 58.47, "learning_rate": 2.1171084243407485e-05, "loss": 0.0017, "step": 243520 }, { "epoch": 58.47, "learning_rate": 2.1167418322027475e-05, "loss": 0.0036, "step": 243530 }, { "epoch": 58.48, "learning_rate": 2.1163752632840227e-05, "loss": 0.0019, "step": 243540 }, { "epoch": 58.48, "learning_rate": 2.116008717587526e-05, "loss": 0.004, "step": 243550 }, { "epoch": 58.48, "learning_rate": 2.1156421951162093e-05, "loss": 0.0045, "step": 243560 }, { "epoch": 58.48, "learning_rate": 2.1152756958730225e-05, "loss": 0.0014, "step": 243570 }, { "epoch": 58.49, "learning_rate": 2.1149092198609204e-05, "loss": 0.0024, "step": 243580 }, { "epoch": 58.49, "learning_rate": 2.1145427670828542e-05, "loss": 0.0032, "step": 243590 }, { "epoch": 58.49, "learning_rate": 2.1141763375417705e-05, "loss": 0.0022, "step": 243600 }, { "epoch": 58.49, "learning_rate": 2.1138099312406246e-05, "loss": 0.006, "step": 243610 }, { "epoch": 58.49, "learning_rate": 2.113443548182366e-05, "loss": 0.0031, "step": 243620 }, { "epoch": 58.5, "learning_rate": 2.1130771883699447e-05, "loss": 0.0023, "step": 243630 }, { "epoch": 58.5, "learning_rate": 2.1127108518063116e-05, "loss": 0.0091, "step": 243640 }, { "epoch": 58.5, "learning_rate": 2.1123445384944163e-05, "loss": 0.0024, "step": 243650 }, { "epoch": 58.5, "learning_rate": 2.1119782484372096e-05, "loss": 0.0038, "step": 243660 }, { "epoch": 58.51, "learning_rate": 2.111611981637639e-05, "loss": 0.0029, "step": 243670 }, { "epoch": 58.51, "learning_rate": 2.1112457380986587e-05, "loss": 0.0196, "step": 243680 }, { "epoch": 58.51, "learning_rate": 2.1108795178232144e-05, "loss": 0.002, "step": 243690 }, { "epoch": 58.51, "learning_rate": 2.1105133208142557e-05, "loss": 0.0024, "step": 243700 }, { "epoch": 58.52, "learning_rate": 2.1101471470747304e-05, "loss": 0.0127, "step": 243710 }, { "epoch": 58.52, "learning_rate": 2.109780996607591e-05, "loss": 0.0015, "step": 243720 }, { "epoch": 58.52, "learning_rate": 2.1094148694157862e-05, "loss": 0.0029, "step": 243730 }, { "epoch": 58.52, "learning_rate": 2.1090487655022584e-05, "loss": 0.0039, "step": 243740 }, { "epoch": 58.52, "learning_rate": 2.108682684869962e-05, "loss": 0.0069, "step": 243750 }, { "epoch": 58.53, "learning_rate": 2.1083166275218435e-05, "loss": 0.0019, "step": 243760 }, { "epoch": 58.53, "learning_rate": 2.10795059346085e-05, "loss": 0.0023, "step": 243770 }, { "epoch": 58.53, "learning_rate": 2.1075845826899298e-05, "loss": 0.004, "step": 243780 }, { "epoch": 58.53, "learning_rate": 2.1072185952120304e-05, "loss": 0.0016, "step": 243790 }, { "epoch": 58.54, "learning_rate": 2.106852631030099e-05, "loss": 0.0043, "step": 243800 }, { "epoch": 58.54, "learning_rate": 2.106486690147081e-05, "loss": 0.0038, "step": 243810 }, { "epoch": 58.54, "learning_rate": 2.106120772565929e-05, "loss": 0.0064, "step": 243820 }, { "epoch": 58.54, "learning_rate": 2.1057548782895837e-05, "loss": 0.0019, "step": 243830 }, { "epoch": 58.55, "learning_rate": 2.105389007320992e-05, "loss": 0.0086, "step": 243840 }, { "epoch": 58.55, "learning_rate": 2.1050231596631043e-05, "loss": 0.0036, "step": 243850 }, { "epoch": 58.55, "learning_rate": 2.1046573353188648e-05, "loss": 0.0026, "step": 243860 }, { "epoch": 58.55, "learning_rate": 2.1042915342912194e-05, "loss": 0.0035, "step": 243870 }, { "epoch": 58.55, "learning_rate": 2.1039257565831137e-05, "loss": 0.0016, "step": 243880 }, { "epoch": 58.56, "learning_rate": 2.1035600021974944e-05, "loss": 0.0027, "step": 243890 }, { "epoch": 58.56, "learning_rate": 2.103194271137306e-05, "loss": 0.0059, "step": 243900 }, { "epoch": 58.56, "learning_rate": 2.1028285634054924e-05, "loss": 0.0023, "step": 243910 }, { "epoch": 58.56, "learning_rate": 2.1024628790050038e-05, "loss": 0.0064, "step": 243920 }, { "epoch": 58.57, "learning_rate": 2.10209721793878e-05, "loss": 0.0032, "step": 243930 }, { "epoch": 58.57, "learning_rate": 2.101731580209767e-05, "loss": 0.0017, "step": 243940 }, { "epoch": 58.57, "learning_rate": 2.1013659658209083e-05, "loss": 0.0018, "step": 243950 }, { "epoch": 58.57, "learning_rate": 2.1010003747751533e-05, "loss": 0.0038, "step": 243960 }, { "epoch": 58.57, "learning_rate": 2.1006348070754407e-05, "loss": 0.0023, "step": 243970 }, { "epoch": 58.58, "learning_rate": 2.1002692627247145e-05, "loss": 0.0046, "step": 243980 }, { "epoch": 58.58, "learning_rate": 2.0999037417259216e-05, "loss": 0.0013, "step": 243990 }, { "epoch": 58.58, "learning_rate": 2.0995382440820045e-05, "loss": 0.0028, "step": 244000 }, { "epoch": 58.58, "learning_rate": 2.0991727697959067e-05, "loss": 0.0015, "step": 244010 }, { "epoch": 58.59, "learning_rate": 2.098807318870571e-05, "loss": 0.0028, "step": 244020 }, { "epoch": 58.59, "learning_rate": 2.09844189130894e-05, "loss": 0.0037, "step": 244030 }, { "epoch": 58.59, "learning_rate": 2.0980764871139575e-05, "loss": 0.0023, "step": 244040 }, { "epoch": 58.59, "learning_rate": 2.0977111062885636e-05, "loss": 0.0016, "step": 244050 }, { "epoch": 58.6, "learning_rate": 2.0973457488357063e-05, "loss": 0.0017, "step": 244060 }, { "epoch": 58.6, "learning_rate": 2.0969804147583227e-05, "loss": 0.0018, "step": 244070 }, { "epoch": 58.6, "learning_rate": 2.096615104059355e-05, "loss": 0.003, "step": 244080 }, { "epoch": 58.6, "learning_rate": 2.0962498167417488e-05, "loss": 0.005, "step": 244090 }, { "epoch": 58.6, "learning_rate": 2.0958845528084453e-05, "loss": 0.0013, "step": 244100 }, { "epoch": 58.61, "learning_rate": 2.0955193122623824e-05, "loss": 0.0022, "step": 244110 }, { "epoch": 58.61, "learning_rate": 2.095154095106502e-05, "loss": 0.003, "step": 244120 }, { "epoch": 58.61, "learning_rate": 2.0947889013437483e-05, "loss": 0.0089, "step": 244130 }, { "epoch": 58.61, "learning_rate": 2.0944237309770604e-05, "loss": 0.0049, "step": 244140 }, { "epoch": 58.62, "learning_rate": 2.0940585840093796e-05, "loss": 0.0047, "step": 244150 }, { "epoch": 58.62, "learning_rate": 2.0936934604436466e-05, "loss": 0.003, "step": 244160 }, { "epoch": 58.62, "learning_rate": 2.0933283602828007e-05, "loss": 0.0015, "step": 244170 }, { "epoch": 58.62, "learning_rate": 2.092963283529783e-05, "loss": 0.0069, "step": 244180 }, { "epoch": 58.63, "learning_rate": 2.092598230187532e-05, "loss": 0.0029, "step": 244190 }, { "epoch": 58.63, "learning_rate": 2.0922332002589917e-05, "loss": 0.0015, "step": 244200 }, { "epoch": 58.63, "learning_rate": 2.091868193747098e-05, "loss": 0.0041, "step": 244210 }, { "epoch": 58.63, "learning_rate": 2.0915032106547888e-05, "loss": 0.0027, "step": 244220 }, { "epoch": 58.63, "learning_rate": 2.0911382509850075e-05, "loss": 0.0027, "step": 244230 }, { "epoch": 58.64, "learning_rate": 2.0907733147406914e-05, "loss": 0.0044, "step": 244240 }, { "epoch": 58.64, "learning_rate": 2.09040840192478e-05, "loss": 0.0026, "step": 244250 }, { "epoch": 58.64, "learning_rate": 2.0900435125402113e-05, "loss": 0.0017, "step": 244260 }, { "epoch": 58.64, "learning_rate": 2.089678646589924e-05, "loss": 0.0074, "step": 244270 }, { "epoch": 58.65, "learning_rate": 2.0893138040768555e-05, "loss": 0.0043, "step": 244280 }, { "epoch": 58.65, "learning_rate": 2.0889489850039457e-05, "loss": 0.0019, "step": 244290 }, { "epoch": 58.65, "learning_rate": 2.088584189374131e-05, "loss": 0.0028, "step": 244300 }, { "epoch": 58.65, "learning_rate": 2.0882194171903502e-05, "loss": 0.0021, "step": 244310 }, { "epoch": 58.65, "learning_rate": 2.0878546684555385e-05, "loss": 0.002, "step": 244320 }, { "epoch": 58.66, "learning_rate": 2.087489943172637e-05, "loss": 0.0031, "step": 244330 }, { "epoch": 58.66, "learning_rate": 2.087125241344583e-05, "loss": 0.0028, "step": 244340 }, { "epoch": 58.66, "learning_rate": 2.0867605629743098e-05, "loss": 0.0018, "step": 244350 }, { "epoch": 58.66, "learning_rate": 2.086395908064754e-05, "loss": 0.0019, "step": 244360 }, { "epoch": 58.67, "learning_rate": 2.0860312766188562e-05, "loss": 0.0029, "step": 244370 }, { "epoch": 58.67, "learning_rate": 2.0856666686395504e-05, "loss": 0.0023, "step": 244380 }, { "epoch": 58.67, "learning_rate": 2.0853020841297738e-05, "loss": 0.0059, "step": 244390 }, { "epoch": 58.67, "learning_rate": 2.0849375230924616e-05, "loss": 0.0018, "step": 244400 }, { "epoch": 58.68, "learning_rate": 2.08457298553055e-05, "loss": 0.0029, "step": 244410 }, { "epoch": 58.68, "learning_rate": 2.0842084714469744e-05, "loss": 0.002, "step": 244420 }, { "epoch": 58.68, "learning_rate": 2.0838439808446707e-05, "loss": 0.0038, "step": 244430 }, { "epoch": 58.68, "learning_rate": 2.0834795137265743e-05, "loss": 0.002, "step": 244440 }, { "epoch": 58.68, "learning_rate": 2.0831150700956205e-05, "loss": 0.0021, "step": 244450 }, { "epoch": 58.69, "learning_rate": 2.082750649954741e-05, "loss": 0.0018, "step": 244460 }, { "epoch": 58.69, "learning_rate": 2.0823862533068756e-05, "loss": 0.0018, "step": 244470 }, { "epoch": 58.69, "learning_rate": 2.082021880154958e-05, "loss": 0.002, "step": 244480 }, { "epoch": 58.69, "learning_rate": 2.0816575305019175e-05, "loss": 0.0106, "step": 244490 }, { "epoch": 58.7, "learning_rate": 2.0812932043506932e-05, "loss": 0.0018, "step": 244500 }, { "epoch": 58.7, "learning_rate": 2.080928901704218e-05, "loss": 0.0022, "step": 244510 }, { "epoch": 58.7, "learning_rate": 2.0805646225654258e-05, "loss": 0.0023, "step": 244520 }, { "epoch": 58.7, "learning_rate": 2.0802003669372493e-05, "loss": 0.0015, "step": 244530 }, { "epoch": 58.71, "learning_rate": 2.0798361348226226e-05, "loss": 0.0035, "step": 244540 }, { "epoch": 58.71, "learning_rate": 2.079471926224479e-05, "loss": 0.002, "step": 244550 }, { "epoch": 58.71, "learning_rate": 2.0791077411457505e-05, "loss": 0.0014, "step": 244560 }, { "epoch": 58.71, "learning_rate": 2.0787435795893688e-05, "loss": 0.01, "step": 244570 }, { "epoch": 58.71, "learning_rate": 2.0783794415582725e-05, "loss": 0.0018, "step": 244580 }, { "epoch": 58.72, "learning_rate": 2.0780153270553876e-05, "loss": 0.0139, "step": 244590 }, { "epoch": 58.72, "learning_rate": 2.077651236083647e-05, "loss": 0.0021, "step": 244600 }, { "epoch": 58.72, "learning_rate": 2.0772871686459868e-05, "loss": 0.0022, "step": 244610 }, { "epoch": 58.72, "learning_rate": 2.0769231247453373e-05, "loss": 0.0024, "step": 244620 }, { "epoch": 58.73, "learning_rate": 2.0765591043846266e-05, "loss": 0.004, "step": 244630 }, { "epoch": 58.73, "learning_rate": 2.0761951075667908e-05, "loss": 0.0033, "step": 244640 }, { "epoch": 58.73, "learning_rate": 2.0758311342947588e-05, "loss": 0.0023, "step": 244650 }, { "epoch": 58.73, "learning_rate": 2.075467184571463e-05, "loss": 0.0025, "step": 244660 }, { "epoch": 58.73, "learning_rate": 2.0751032583998337e-05, "loss": 0.0048, "step": 244670 }, { "epoch": 58.74, "learning_rate": 2.0747393557828016e-05, "loss": 0.0019, "step": 244680 }, { "epoch": 58.74, "learning_rate": 2.0743754767232974e-05, "loss": 0.0023, "step": 244690 }, { "epoch": 58.74, "learning_rate": 2.0740116212242494e-05, "loss": 0.0023, "step": 244700 }, { "epoch": 58.74, "learning_rate": 2.0736477892885918e-05, "loss": 0.0021, "step": 244710 }, { "epoch": 58.75, "learning_rate": 2.073283980919254e-05, "loss": 0.0018, "step": 244720 }, { "epoch": 58.75, "learning_rate": 2.0729201961191614e-05, "loss": 0.0039, "step": 244730 }, { "epoch": 58.75, "learning_rate": 2.0725564348912473e-05, "loss": 0.0031, "step": 244740 }, { "epoch": 58.75, "learning_rate": 2.0721926972384415e-05, "loss": 0.0036, "step": 244750 }, { "epoch": 58.76, "learning_rate": 2.0718289831636732e-05, "loss": 0.0015, "step": 244760 }, { "epoch": 58.76, "learning_rate": 2.0714652926698668e-05, "loss": 0.0016, "step": 244770 }, { "epoch": 58.76, "learning_rate": 2.0711016257599568e-05, "loss": 0.0036, "step": 244780 }, { "epoch": 58.76, "learning_rate": 2.07073798243687e-05, "loss": 0.003, "step": 244790 }, { "epoch": 58.76, "learning_rate": 2.0703743627035344e-05, "loss": 0.0021, "step": 244800 }, { "epoch": 58.77, "learning_rate": 2.070010766562878e-05, "loss": 0.0049, "step": 244810 }, { "epoch": 58.77, "learning_rate": 2.0696471940178302e-05, "loss": 0.0059, "step": 244820 }, { "epoch": 58.77, "learning_rate": 2.0692836450713178e-05, "loss": 0.0033, "step": 244830 }, { "epoch": 58.77, "learning_rate": 2.068920119726267e-05, "loss": 0.0018, "step": 244840 }, { "epoch": 58.78, "learning_rate": 2.0685566179856087e-05, "loss": 0.002, "step": 244850 }, { "epoch": 58.78, "learning_rate": 2.0681931398522707e-05, "loss": 0.0044, "step": 244860 }, { "epoch": 58.78, "learning_rate": 2.0678296853291745e-05, "loss": 0.0026, "step": 244870 }, { "epoch": 58.78, "learning_rate": 2.0674662544192526e-05, "loss": 0.0041, "step": 244880 }, { "epoch": 58.79, "learning_rate": 2.0671028471254294e-05, "loss": 0.0092, "step": 244890 }, { "epoch": 58.79, "learning_rate": 2.066739463450632e-05, "loss": 0.002, "step": 244900 }, { "epoch": 58.79, "learning_rate": 2.066376103397787e-05, "loss": 0.0021, "step": 244910 }, { "epoch": 58.79, "learning_rate": 2.0660127669698197e-05, "loss": 0.0031, "step": 244920 }, { "epoch": 58.79, "learning_rate": 2.0656494541696575e-05, "loss": 0.0028, "step": 244930 }, { "epoch": 58.8, "learning_rate": 2.065286165000223e-05, "loss": 0.0024, "step": 244940 }, { "epoch": 58.8, "learning_rate": 2.0649228994644476e-05, "loss": 0.0014, "step": 244950 }, { "epoch": 58.8, "learning_rate": 2.0645596575652522e-05, "loss": 0.005, "step": 244960 }, { "epoch": 58.8, "learning_rate": 2.0641964393055625e-05, "loss": 0.0016, "step": 244970 }, { "epoch": 58.81, "learning_rate": 2.0638332446883025e-05, "loss": 0.0028, "step": 244980 }, { "epoch": 58.81, "learning_rate": 2.0634700737164003e-05, "loss": 0.0038, "step": 244990 }, { "epoch": 58.81, "learning_rate": 2.063106926392781e-05, "loss": 0.0025, "step": 245000 }, { "epoch": 58.81, "learning_rate": 2.0627438027203638e-05, "loss": 0.0031, "step": 245010 }, { "epoch": 58.81, "learning_rate": 2.062380702702078e-05, "loss": 0.0047, "step": 245020 }, { "epoch": 58.82, "learning_rate": 2.062017626340846e-05, "loss": 0.0026, "step": 245030 }, { "epoch": 58.82, "learning_rate": 2.0616545736395914e-05, "loss": 0.0021, "step": 245040 }, { "epoch": 58.82, "learning_rate": 2.0612915446012383e-05, "loss": 0.0078, "step": 245050 }, { "epoch": 58.82, "learning_rate": 2.06092853922871e-05, "loss": 0.0012, "step": 245060 }, { "epoch": 58.83, "learning_rate": 2.06056555752493e-05, "loss": 0.0026, "step": 245070 }, { "epoch": 58.83, "learning_rate": 2.06020259949282e-05, "loss": 0.0028, "step": 245080 }, { "epoch": 58.83, "learning_rate": 2.0598396651353068e-05, "loss": 0.0019, "step": 245090 }, { "epoch": 58.83, "learning_rate": 2.0594767544553102e-05, "loss": 0.0014, "step": 245100 }, { "epoch": 58.84, "learning_rate": 2.0591138674557507e-05, "loss": 0.0018, "step": 245110 }, { "epoch": 58.84, "learning_rate": 2.0587510041395554e-05, "loss": 0.0049, "step": 245120 }, { "epoch": 58.84, "learning_rate": 2.0583881645096436e-05, "loss": 0.003, "step": 245130 }, { "epoch": 58.84, "learning_rate": 2.0580253485689388e-05, "loss": 0.0015, "step": 245140 }, { "epoch": 58.84, "learning_rate": 2.0576625563203615e-05, "loss": 0.0056, "step": 245150 }, { "epoch": 58.85, "learning_rate": 2.057299787766835e-05, "loss": 0.0023, "step": 245160 }, { "epoch": 58.85, "learning_rate": 2.0569370429112784e-05, "loss": 0.0055, "step": 245170 }, { "epoch": 58.85, "learning_rate": 2.0565743217566124e-05, "loss": 0.009, "step": 245180 }, { "epoch": 58.85, "learning_rate": 2.0562116243057637e-05, "loss": 0.0019, "step": 245190 }, { "epoch": 58.86, "learning_rate": 2.0558489505616473e-05, "loss": 0.0082, "step": 245200 }, { "epoch": 58.86, "learning_rate": 2.0554863005271856e-05, "loss": 0.004, "step": 245210 }, { "epoch": 58.86, "learning_rate": 2.0551236742052977e-05, "loss": 0.003, "step": 245220 }, { "epoch": 58.86, "learning_rate": 2.0547610715989073e-05, "loss": 0.0023, "step": 245230 }, { "epoch": 58.87, "learning_rate": 2.0543984927109343e-05, "loss": 0.0018, "step": 245240 }, { "epoch": 58.87, "learning_rate": 2.054035937544293e-05, "loss": 0.0033, "step": 245250 }, { "epoch": 58.87, "learning_rate": 2.053673406101909e-05, "loss": 0.0021, "step": 245260 }, { "epoch": 58.87, "learning_rate": 2.0533108983867e-05, "loss": 0.0035, "step": 245270 }, { "epoch": 58.87, "learning_rate": 2.052948414401585e-05, "loss": 0.0013, "step": 245280 }, { "epoch": 58.88, "learning_rate": 2.0525859541494835e-05, "loss": 0.0109, "step": 245290 }, { "epoch": 58.88, "learning_rate": 2.0522235176333138e-05, "loss": 0.006, "step": 245300 }, { "epoch": 58.88, "learning_rate": 2.0518611048559955e-05, "loss": 0.0021, "step": 245310 }, { "epoch": 58.88, "learning_rate": 2.0514987158204447e-05, "loss": 0.0023, "step": 245320 }, { "epoch": 58.89, "learning_rate": 2.0511363505295855e-05, "loss": 0.0034, "step": 245330 }, { "epoch": 58.89, "learning_rate": 2.0507740089863304e-05, "loss": 0.0025, "step": 245340 }, { "epoch": 58.89, "learning_rate": 2.050411691193598e-05, "loss": 0.0026, "step": 245350 }, { "epoch": 58.89, "learning_rate": 2.050049397154309e-05, "loss": 0.0016, "step": 245360 }, { "epoch": 58.89, "learning_rate": 2.049687126871379e-05, "loss": 0.0053, "step": 245370 }, { "epoch": 58.9, "learning_rate": 2.0493248803477266e-05, "loss": 0.0099, "step": 245380 }, { "epoch": 58.9, "learning_rate": 2.048962657586268e-05, "loss": 0.0014, "step": 245390 }, { "epoch": 58.9, "learning_rate": 2.0486004585899206e-05, "loss": 0.0019, "step": 245400 }, { "epoch": 58.9, "learning_rate": 2.048238283361601e-05, "loss": 0.0043, "step": 245410 }, { "epoch": 58.91, "learning_rate": 2.0478761319042262e-05, "loss": 0.0029, "step": 245420 }, { "epoch": 58.91, "learning_rate": 2.0475140042207126e-05, "loss": 0.0025, "step": 245430 }, { "epoch": 58.91, "learning_rate": 2.0471519003139762e-05, "loss": 0.0023, "step": 245440 }, { "epoch": 58.91, "learning_rate": 2.046789820186933e-05, "loss": 0.0029, "step": 245450 }, { "epoch": 58.92, "learning_rate": 2.046427763842498e-05, "loss": 0.0019, "step": 245460 }, { "epoch": 58.92, "learning_rate": 2.0460657312835906e-05, "loss": 0.0048, "step": 245470 }, { "epoch": 58.92, "learning_rate": 2.0457037225131226e-05, "loss": 0.002, "step": 245480 }, { "epoch": 58.92, "learning_rate": 2.0453417375340085e-05, "loss": 0.0031, "step": 245490 }, { "epoch": 58.92, "learning_rate": 2.0449797763491667e-05, "loss": 0.0034, "step": 245500 }, { "epoch": 58.93, "learning_rate": 2.0446178389615105e-05, "loss": 0.0078, "step": 245510 }, { "epoch": 58.93, "learning_rate": 2.0442559253739556e-05, "loss": 0.002, "step": 245520 }, { "epoch": 58.93, "learning_rate": 2.0438940355894155e-05, "loss": 0.0017, "step": 245530 }, { "epoch": 58.93, "learning_rate": 2.0435321696108052e-05, "loss": 0.0018, "step": 245540 }, { "epoch": 58.94, "learning_rate": 2.043170327441038e-05, "loss": 0.0054, "step": 245550 }, { "epoch": 58.94, "learning_rate": 2.0428085090830268e-05, "loss": 0.0044, "step": 245560 }, { "epoch": 58.94, "learning_rate": 2.0424467145396902e-05, "loss": 0.0032, "step": 245570 }, { "epoch": 58.94, "learning_rate": 2.0420849438139373e-05, "loss": 0.0031, "step": 245580 }, { "epoch": 58.95, "learning_rate": 2.0417231969086803e-05, "loss": 0.0027, "step": 245590 }, { "epoch": 58.95, "learning_rate": 2.0413614738268373e-05, "loss": 0.0015, "step": 245600 }, { "epoch": 58.95, "learning_rate": 2.04099977457132e-05, "loss": 0.0034, "step": 245610 }, { "epoch": 59.0, "learning_rate": 2.0406380991450385e-05, "loss": 0.0038, "step": 245620 }, { "epoch": 59.0, "learning_rate": 2.0402764475509052e-05, "loss": 0.0024, "step": 245630 }, { "epoch": 59.01, "learning_rate": 2.039914819791836e-05, "loss": 0.0034, "step": 245640 }, { "epoch": 59.01, "learning_rate": 2.0395532158707414e-05, "loss": 0.0021, "step": 245650 }, { "epoch": 59.01, "learning_rate": 2.039191635790534e-05, "loss": 0.0033, "step": 245660 }, { "epoch": 59.01, "learning_rate": 2.0388300795541244e-05, "loss": 0.0037, "step": 245670 }, { "epoch": 59.01, "learning_rate": 2.038468547164425e-05, "loss": 0.0021, "step": 245680 }, { "epoch": 59.02, "learning_rate": 2.0381070386243478e-05, "loss": 0.002, "step": 245690 }, { "epoch": 59.02, "learning_rate": 2.0377455539368012e-05, "loss": 0.0036, "step": 245700 }, { "epoch": 59.02, "learning_rate": 2.0373840931047022e-05, "loss": 0.0017, "step": 245710 }, { "epoch": 59.02, "learning_rate": 2.037022656130957e-05, "loss": 0.0015, "step": 245720 }, { "epoch": 59.03, "learning_rate": 2.036661243018475e-05, "loss": 0.0036, "step": 245730 }, { "epoch": 59.03, "learning_rate": 2.036299853770171e-05, "loss": 0.0044, "step": 245740 }, { "epoch": 59.03, "learning_rate": 2.0359384883889553e-05, "loss": 0.0025, "step": 245750 }, { "epoch": 59.03, "learning_rate": 2.0355771468777323e-05, "loss": 0.0021, "step": 245760 }, { "epoch": 59.03, "learning_rate": 2.035215829239418e-05, "loss": 0.0032, "step": 245770 }, { "epoch": 59.04, "learning_rate": 2.03485453547692e-05, "loss": 0.0022, "step": 245780 }, { "epoch": 59.04, "learning_rate": 2.0344932655931476e-05, "loss": 0.0023, "step": 245790 }, { "epoch": 59.04, "learning_rate": 2.03413201959101e-05, "loss": 0.0016, "step": 245800 }, { "epoch": 59.04, "learning_rate": 2.033770797473417e-05, "loss": 0.0038, "step": 245810 }, { "epoch": 59.05, "learning_rate": 2.033409599243278e-05, "loss": 0.0016, "step": 245820 }, { "epoch": 59.05, "learning_rate": 2.0330484249034985e-05, "loss": 0.0029, "step": 245830 }, { "epoch": 59.05, "learning_rate": 2.0326872744569913e-05, "loss": 0.006, "step": 245840 }, { "epoch": 59.05, "learning_rate": 2.0323261479066652e-05, "loss": 0.0038, "step": 245850 }, { "epoch": 59.06, "learning_rate": 2.0319650452554245e-05, "loss": 0.0021, "step": 245860 }, { "epoch": 59.06, "learning_rate": 2.0316039665061776e-05, "loss": 0.0019, "step": 245870 }, { "epoch": 59.06, "learning_rate": 2.0312429116618353e-05, "loss": 0.0018, "step": 245880 }, { "epoch": 59.06, "learning_rate": 2.030881880725303e-05, "loss": 0.0028, "step": 245890 }, { "epoch": 59.06, "learning_rate": 2.0305208736994902e-05, "loss": 0.0031, "step": 245900 }, { "epoch": 59.07, "learning_rate": 2.030159890587302e-05, "loss": 0.0042, "step": 245910 }, { "epoch": 59.07, "learning_rate": 2.029798931391646e-05, "loss": 0.0022, "step": 245920 }, { "epoch": 59.07, "learning_rate": 2.02943799611543e-05, "loss": 0.0038, "step": 245930 }, { "epoch": 59.07, "learning_rate": 2.029077084761559e-05, "loss": 0.0034, "step": 245940 }, { "epoch": 59.08, "learning_rate": 2.028716197332941e-05, "loss": 0.0023, "step": 245950 }, { "epoch": 59.08, "learning_rate": 2.028355333832482e-05, "loss": 0.0028, "step": 245960 }, { "epoch": 59.08, "learning_rate": 2.0279944942630853e-05, "loss": 0.0016, "step": 245970 }, { "epoch": 59.08, "learning_rate": 2.0276336786276612e-05, "loss": 0.0024, "step": 245980 }, { "epoch": 59.09, "learning_rate": 2.0272728869291153e-05, "loss": 0.0018, "step": 245990 }, { "epoch": 59.09, "learning_rate": 2.026912119170347e-05, "loss": 0.0015, "step": 246000 }, { "epoch": 59.09, "learning_rate": 2.0265513753542685e-05, "loss": 0.0016, "step": 246010 }, { "epoch": 59.09, "learning_rate": 2.0261906554837822e-05, "loss": 0.0023, "step": 246020 }, { "epoch": 59.09, "learning_rate": 2.0258299595617932e-05, "loss": 0.0025, "step": 246030 }, { "epoch": 59.1, "learning_rate": 2.0254692875912057e-05, "loss": 0.002, "step": 246040 }, { "epoch": 59.1, "learning_rate": 2.025108639574925e-05, "loss": 0.0021, "step": 246050 }, { "epoch": 59.1, "learning_rate": 2.0247480155158547e-05, "loss": 0.003, "step": 246060 }, { "epoch": 59.1, "learning_rate": 2.0243874154169002e-05, "loss": 0.0069, "step": 246070 }, { "epoch": 59.11, "learning_rate": 2.024026839280964e-05, "loss": 0.0099, "step": 246080 }, { "epoch": 59.11, "learning_rate": 2.0236662871109508e-05, "loss": 0.0016, "step": 246090 }, { "epoch": 59.11, "learning_rate": 2.0233057589097642e-05, "loss": 0.0018, "step": 246100 }, { "epoch": 59.11, "learning_rate": 2.0229452546803053e-05, "loss": 0.0045, "step": 246110 }, { "epoch": 59.11, "learning_rate": 2.0225847744254807e-05, "loss": 0.0052, "step": 246120 }, { "epoch": 59.12, "learning_rate": 2.0222243181481937e-05, "loss": 0.0019, "step": 246130 }, { "epoch": 59.12, "learning_rate": 2.0218638858513422e-05, "loss": 0.005, "step": 246140 }, { "epoch": 59.12, "learning_rate": 2.0215034775378332e-05, "loss": 0.0027, "step": 246150 }, { "epoch": 59.12, "learning_rate": 2.0211430932105684e-05, "loss": 0.0032, "step": 246160 }, { "epoch": 59.13, "learning_rate": 2.02078273287245e-05, "loss": 0.0029, "step": 246170 }, { "epoch": 59.13, "learning_rate": 2.0204223965263786e-05, "loss": 0.0038, "step": 246180 }, { "epoch": 59.13, "learning_rate": 2.0200620841752577e-05, "loss": 0.0039, "step": 246190 }, { "epoch": 59.13, "learning_rate": 2.0197017958219875e-05, "loss": 0.0018, "step": 246200 }, { "epoch": 59.14, "learning_rate": 2.019341531469469e-05, "loss": 0.0042, "step": 246210 }, { "epoch": 59.14, "learning_rate": 2.0189812911206065e-05, "loss": 0.006, "step": 246220 }, { "epoch": 59.14, "learning_rate": 2.0186210747783008e-05, "loss": 0.0021, "step": 246230 }, { "epoch": 59.14, "learning_rate": 2.0182608824454475e-05, "loss": 0.0027, "step": 246240 }, { "epoch": 59.14, "learning_rate": 2.0179007141249527e-05, "loss": 0.0055, "step": 246250 }, { "epoch": 59.15, "learning_rate": 2.0175405698197153e-05, "loss": 0.003, "step": 246260 }, { "epoch": 59.15, "learning_rate": 2.0171804495326375e-05, "loss": 0.0013, "step": 246270 }, { "epoch": 59.15, "learning_rate": 2.0168203532666135e-05, "loss": 0.0031, "step": 246280 }, { "epoch": 59.15, "learning_rate": 2.0164602810245485e-05, "loss": 0.0019, "step": 246290 }, { "epoch": 59.16, "learning_rate": 2.0161002328093416e-05, "loss": 0.0019, "step": 246300 }, { "epoch": 59.16, "learning_rate": 2.0157402086238908e-05, "loss": 0.0036, "step": 246310 }, { "epoch": 59.16, "learning_rate": 2.015380208471096e-05, "loss": 0.0018, "step": 246320 }, { "epoch": 59.16, "learning_rate": 2.015020232353857e-05, "loss": 0.0022, "step": 246330 }, { "epoch": 59.17, "learning_rate": 2.014660280275072e-05, "loss": 0.0044, "step": 246340 }, { "epoch": 59.17, "learning_rate": 2.014300352237638e-05, "loss": 0.002, "step": 246350 }, { "epoch": 59.17, "learning_rate": 2.0139404482444573e-05, "loss": 0.0016, "step": 246360 }, { "epoch": 59.17, "learning_rate": 2.0135805682984283e-05, "loss": 0.0025, "step": 246370 }, { "epoch": 59.17, "learning_rate": 2.0132207124024434e-05, "loss": 0.0027, "step": 246380 }, { "epoch": 59.18, "learning_rate": 2.0128608805594064e-05, "loss": 0.0023, "step": 246390 }, { "epoch": 59.18, "learning_rate": 2.012501072772213e-05, "loss": 0.003, "step": 246400 }, { "epoch": 59.18, "learning_rate": 2.0121412890437612e-05, "loss": 0.0016, "step": 246410 }, { "epoch": 59.18, "learning_rate": 2.011781529376948e-05, "loss": 0.002, "step": 246420 }, { "epoch": 59.19, "learning_rate": 2.0114217937746704e-05, "loss": 0.0032, "step": 246430 }, { "epoch": 59.19, "learning_rate": 2.0110620822398263e-05, "loss": 0.0061, "step": 246440 }, { "epoch": 59.19, "learning_rate": 2.0107023947753095e-05, "loss": 0.0024, "step": 246450 }, { "epoch": 59.19, "learning_rate": 2.0103427313840227e-05, "loss": 0.0023, "step": 246460 }, { "epoch": 59.19, "learning_rate": 2.0099830920688573e-05, "loss": 0.0014, "step": 246470 }, { "epoch": 59.2, "learning_rate": 2.0096234768327105e-05, "loss": 0.0051, "step": 246480 }, { "epoch": 59.2, "learning_rate": 2.0092638856784772e-05, "loss": 0.0015, "step": 246490 }, { "epoch": 59.2, "learning_rate": 2.008904318609056e-05, "loss": 0.002, "step": 246500 }, { "epoch": 59.2, "learning_rate": 2.0085447756273436e-05, "loss": 0.0019, "step": 246510 }, { "epoch": 59.21, "learning_rate": 2.0081852567362292e-05, "loss": 0.0024, "step": 246520 }, { "epoch": 59.21, "learning_rate": 2.0078257619386137e-05, "loss": 0.0017, "step": 246530 }, { "epoch": 59.21, "learning_rate": 2.0074662912373908e-05, "loss": 0.0062, "step": 246540 }, { "epoch": 59.21, "learning_rate": 2.0071068446354546e-05, "loss": 0.0025, "step": 246550 }, { "epoch": 59.22, "learning_rate": 2.0067474221357003e-05, "loss": 0.0019, "step": 246560 }, { "epoch": 59.22, "learning_rate": 2.0063880237410228e-05, "loss": 0.0034, "step": 246570 }, { "epoch": 59.22, "learning_rate": 2.006028649454315e-05, "loss": 0.0017, "step": 246580 }, { "epoch": 59.22, "learning_rate": 2.0056692992784704e-05, "loss": 0.0025, "step": 246590 }, { "epoch": 59.22, "learning_rate": 2.0053099732163875e-05, "loss": 0.0015, "step": 246600 }, { "epoch": 59.23, "learning_rate": 2.004950671270956e-05, "loss": 0.0021, "step": 246610 }, { "epoch": 59.23, "learning_rate": 2.0045913934450677e-05, "loss": 0.0023, "step": 246620 }, { "epoch": 59.23, "learning_rate": 2.0042321397416204e-05, "loss": 0.0022, "step": 246630 }, { "epoch": 59.23, "learning_rate": 2.003872910163505e-05, "loss": 0.0014, "step": 246640 }, { "epoch": 59.24, "learning_rate": 2.0035137047136156e-05, "loss": 0.0064, "step": 246650 }, { "epoch": 59.24, "learning_rate": 2.003154523394843e-05, "loss": 0.0047, "step": 246660 }, { "epoch": 59.24, "learning_rate": 2.0027953662100813e-05, "loss": 0.0014, "step": 246670 }, { "epoch": 59.24, "learning_rate": 2.0024362331622222e-05, "loss": 0.0023, "step": 246680 }, { "epoch": 59.25, "learning_rate": 2.002077124254156e-05, "loss": 0.004, "step": 246690 }, { "epoch": 59.25, "learning_rate": 2.00171803948878e-05, "loss": 0.0058, "step": 246700 }, { "epoch": 59.25, "learning_rate": 2.0013589788689813e-05, "loss": 0.0083, "step": 246710 }, { "epoch": 59.25, "learning_rate": 2.0009999423976528e-05, "loss": 0.0019, "step": 246720 }, { "epoch": 59.25, "learning_rate": 2.0006409300776836e-05, "loss": 0.0034, "step": 246730 }, { "epoch": 59.26, "learning_rate": 2.0002819419119705e-05, "loss": 0.0018, "step": 246740 }, { "epoch": 59.26, "learning_rate": 1.9999229779033995e-05, "loss": 0.0023, "step": 246750 }, { "epoch": 59.26, "learning_rate": 1.9995640380548615e-05, "loss": 0.0025, "step": 246760 }, { "epoch": 59.26, "learning_rate": 1.9992051223692498e-05, "loss": 0.0019, "step": 246770 }, { "epoch": 59.27, "learning_rate": 1.9988462308494542e-05, "loss": 0.0021, "step": 246780 }, { "epoch": 59.27, "learning_rate": 1.9984873634983638e-05, "loss": 0.0017, "step": 246790 }, { "epoch": 59.27, "learning_rate": 1.9981285203188686e-05, "loss": 0.0026, "step": 246800 }, { "epoch": 59.27, "learning_rate": 1.9977697013138598e-05, "loss": 0.003, "step": 246810 }, { "epoch": 59.27, "learning_rate": 1.9974109064862256e-05, "loss": 0.0023, "step": 246820 }, { "epoch": 59.28, "learning_rate": 1.997052135838854e-05, "loss": 0.0026, "step": 246830 }, { "epoch": 59.28, "learning_rate": 1.9966933893746398e-05, "loss": 0.0017, "step": 246840 }, { "epoch": 59.28, "learning_rate": 1.9963346670964666e-05, "loss": 0.0026, "step": 246850 }, { "epoch": 59.28, "learning_rate": 1.9959759690072232e-05, "loss": 0.0019, "step": 246860 }, { "epoch": 59.29, "learning_rate": 1.9956172951098016e-05, "loss": 0.0018, "step": 246870 }, { "epoch": 59.29, "learning_rate": 1.9952586454070895e-05, "loss": 0.002, "step": 246880 }, { "epoch": 59.29, "learning_rate": 1.9949000199019734e-05, "loss": 0.0032, "step": 246890 }, { "epoch": 59.29, "learning_rate": 1.994541418597343e-05, "loss": 0.005, "step": 246900 }, { "epoch": 59.3, "learning_rate": 1.994182841496085e-05, "loss": 0.0027, "step": 246910 }, { "epoch": 59.3, "learning_rate": 1.9938242886010883e-05, "loss": 0.0121, "step": 246920 }, { "epoch": 59.3, "learning_rate": 1.993465759915239e-05, "loss": 0.0036, "step": 246930 }, { "epoch": 59.3, "learning_rate": 1.9931072554414248e-05, "loss": 0.0019, "step": 246940 }, { "epoch": 59.3, "learning_rate": 1.9927487751825336e-05, "loss": 0.0023, "step": 246950 }, { "epoch": 59.31, "learning_rate": 1.9923903191414517e-05, "loss": 0.0019, "step": 246960 }, { "epoch": 59.31, "learning_rate": 1.9920318873210635e-05, "loss": 0.002, "step": 246970 }, { "epoch": 59.31, "learning_rate": 1.9916734797242614e-05, "loss": 0.0049, "step": 246980 }, { "epoch": 59.31, "learning_rate": 1.9913150963539267e-05, "loss": 0.0019, "step": 246990 }, { "epoch": 59.32, "learning_rate": 1.990956737212945e-05, "loss": 0.0046, "step": 247000 }, { "epoch": 59.32, "learning_rate": 1.9905984023042056e-05, "loss": 0.0016, "step": 247010 }, { "epoch": 59.32, "learning_rate": 1.990240091630593e-05, "loss": 0.0021, "step": 247020 }, { "epoch": 59.32, "learning_rate": 1.9898818051949926e-05, "loss": 0.0048, "step": 247030 }, { "epoch": 59.33, "learning_rate": 1.9895235430002894e-05, "loss": 0.0015, "step": 247040 }, { "epoch": 59.33, "learning_rate": 1.9891653050493687e-05, "loss": 0.0015, "step": 247050 }, { "epoch": 59.33, "learning_rate": 1.9888070913451157e-05, "loss": 0.0035, "step": 247060 }, { "epoch": 59.33, "learning_rate": 1.9884489018904145e-05, "loss": 0.0063, "step": 247070 }, { "epoch": 59.33, "learning_rate": 1.98809073668815e-05, "loss": 0.0013, "step": 247080 }, { "epoch": 59.34, "learning_rate": 1.9877325957412072e-05, "loss": 0.0045, "step": 247090 }, { "epoch": 59.34, "learning_rate": 1.987374479052468e-05, "loss": 0.0083, "step": 247100 }, { "epoch": 59.34, "learning_rate": 1.987016386624819e-05, "loss": 0.0014, "step": 247110 }, { "epoch": 59.34, "learning_rate": 1.9866583184611455e-05, "loss": 0.0033, "step": 247120 }, { "epoch": 59.35, "learning_rate": 1.986300274564326e-05, "loss": 0.0036, "step": 247130 }, { "epoch": 59.35, "learning_rate": 1.9859422549372453e-05, "loss": 0.0034, "step": 247140 }, { "epoch": 59.35, "learning_rate": 1.9855842595827894e-05, "loss": 0.0022, "step": 247150 }, { "epoch": 59.35, "learning_rate": 1.9852262885038396e-05, "loss": 0.0015, "step": 247160 }, { "epoch": 59.35, "learning_rate": 1.9848683417032787e-05, "loss": 0.004, "step": 247170 }, { "epoch": 59.36, "learning_rate": 1.9845104191839896e-05, "loss": 0.0028, "step": 247180 }, { "epoch": 59.36, "learning_rate": 1.9841525209488542e-05, "loss": 0.0028, "step": 247190 }, { "epoch": 59.36, "learning_rate": 1.9837946470007552e-05, "loss": 0.002, "step": 247200 }, { "epoch": 59.36, "learning_rate": 1.983436797342572e-05, "loss": 0.0016, "step": 247210 }, { "epoch": 59.37, "learning_rate": 1.9830789719771925e-05, "loss": 0.0047, "step": 247220 }, { "epoch": 59.37, "learning_rate": 1.9827211709074928e-05, "loss": 0.0057, "step": 247230 }, { "epoch": 59.37, "learning_rate": 1.982363394136354e-05, "loss": 0.0045, "step": 247240 }, { "epoch": 59.37, "learning_rate": 1.9820056416666616e-05, "loss": 0.0016, "step": 247250 }, { "epoch": 59.38, "learning_rate": 1.981647913501296e-05, "loss": 0.0034, "step": 247260 }, { "epoch": 59.38, "learning_rate": 1.981290209643133e-05, "loss": 0.0026, "step": 247270 }, { "epoch": 59.38, "learning_rate": 1.9809325300950588e-05, "loss": 0.0024, "step": 247280 }, { "epoch": 59.38, "learning_rate": 1.9805748748599513e-05, "loss": 0.0017, "step": 247290 }, { "epoch": 59.38, "learning_rate": 1.980217243940691e-05, "loss": 0.0072, "step": 247300 }, { "epoch": 59.39, "learning_rate": 1.9798596373401586e-05, "loss": 0.0033, "step": 247310 }, { "epoch": 59.39, "learning_rate": 1.979502055061233e-05, "loss": 0.0088, "step": 247320 }, { "epoch": 59.39, "learning_rate": 1.9791444971067948e-05, "loss": 0.0026, "step": 247330 }, { "epoch": 59.39, "learning_rate": 1.978786963479723e-05, "loss": 0.005, "step": 247340 }, { "epoch": 59.4, "learning_rate": 1.978429454182895e-05, "loss": 0.0024, "step": 247350 }, { "epoch": 59.4, "learning_rate": 1.978071969219195e-05, "loss": 0.002, "step": 247360 }, { "epoch": 59.4, "learning_rate": 1.9777145085914972e-05, "loss": 0.0056, "step": 247370 }, { "epoch": 59.4, "learning_rate": 1.9773570723026803e-05, "loss": 0.0029, "step": 247380 }, { "epoch": 59.41, "learning_rate": 1.9769996603556255e-05, "loss": 0.0014, "step": 247390 }, { "epoch": 59.41, "learning_rate": 1.9766422727532114e-05, "loss": 0.0022, "step": 247400 }, { "epoch": 59.41, "learning_rate": 1.9762849094983114e-05, "loss": 0.0055, "step": 247410 }, { "epoch": 59.41, "learning_rate": 1.975927570593808e-05, "loss": 0.0019, "step": 247420 }, { "epoch": 59.41, "learning_rate": 1.9755702560425777e-05, "loss": 0.0058, "step": 247430 }, { "epoch": 59.42, "learning_rate": 1.9752129658474973e-05, "loss": 0.0017, "step": 247440 }, { "epoch": 59.42, "learning_rate": 1.9748557000114443e-05, "loss": 0.0021, "step": 247450 }, { "epoch": 59.42, "learning_rate": 1.974498458537296e-05, "loss": 0.0036, "step": 247460 }, { "epoch": 59.42, "learning_rate": 1.9741412414279298e-05, "loss": 0.0066, "step": 247470 }, { "epoch": 59.43, "learning_rate": 1.9737840486862197e-05, "loss": 0.0021, "step": 247480 }, { "epoch": 59.43, "learning_rate": 1.973426880315047e-05, "loss": 0.0043, "step": 247490 }, { "epoch": 59.43, "learning_rate": 1.9730697363172863e-05, "loss": 0.0018, "step": 247500 }, { "epoch": 59.43, "learning_rate": 1.97271261669581e-05, "loss": 0.002, "step": 247510 }, { "epoch": 59.43, "learning_rate": 1.9723555214534983e-05, "loss": 0.0045, "step": 247520 }, { "epoch": 59.44, "learning_rate": 1.9719984505932258e-05, "loss": 0.0059, "step": 247530 }, { "epoch": 59.44, "learning_rate": 1.9716414041178678e-05, "loss": 0.0064, "step": 247540 }, { "epoch": 59.44, "learning_rate": 1.9712843820302996e-05, "loss": 0.0042, "step": 247550 }, { "epoch": 59.44, "learning_rate": 1.9709273843333965e-05, "loss": 0.0022, "step": 247560 }, { "epoch": 59.45, "learning_rate": 1.9705704110300333e-05, "loss": 0.0037, "step": 247570 }, { "epoch": 59.45, "learning_rate": 1.9702134621230845e-05, "loss": 0.0013, "step": 247580 }, { "epoch": 59.45, "learning_rate": 1.9698565376154253e-05, "loss": 0.0021, "step": 247590 }, { "epoch": 59.45, "learning_rate": 1.96949963750993e-05, "loss": 0.0015, "step": 247600 }, { "epoch": 59.46, "learning_rate": 1.969142761809472e-05, "loss": 0.0029, "step": 247610 }, { "epoch": 59.46, "learning_rate": 1.9687859105169243e-05, "loss": 0.0036, "step": 247620 }, { "epoch": 59.46, "learning_rate": 1.9684290836351638e-05, "loss": 0.0059, "step": 247630 }, { "epoch": 59.46, "learning_rate": 1.9680722811670643e-05, "loss": 0.0022, "step": 247640 }, { "epoch": 59.46, "learning_rate": 1.9677155031154938e-05, "loss": 0.0065, "step": 247650 }, { "epoch": 59.47, "learning_rate": 1.9673587494833306e-05, "loss": 0.002, "step": 247660 }, { "epoch": 59.47, "learning_rate": 1.9670020202734464e-05, "loss": 0.0014, "step": 247670 }, { "epoch": 59.47, "learning_rate": 1.9666453154887134e-05, "loss": 0.0015, "step": 247680 }, { "epoch": 59.47, "learning_rate": 1.9662886351320043e-05, "loss": 0.0016, "step": 247690 }, { "epoch": 59.48, "learning_rate": 1.965931979206192e-05, "loss": 0.0016, "step": 247700 }, { "epoch": 59.48, "learning_rate": 1.965575347714148e-05, "loss": 0.0023, "step": 247710 }, { "epoch": 59.48, "learning_rate": 1.965218740658743e-05, "loss": 0.003, "step": 247720 }, { "epoch": 59.48, "learning_rate": 1.9648621580428545e-05, "loss": 0.0016, "step": 247730 }, { "epoch": 59.49, "learning_rate": 1.9645055998693474e-05, "loss": 0.0046, "step": 247740 }, { "epoch": 59.49, "learning_rate": 1.9641490661410943e-05, "loss": 0.0018, "step": 247750 }, { "epoch": 59.49, "learning_rate": 1.96379255686097e-05, "loss": 0.0079, "step": 247760 }, { "epoch": 59.49, "learning_rate": 1.9634360720318435e-05, "loss": 0.0027, "step": 247770 }, { "epoch": 59.49, "learning_rate": 1.963079611656587e-05, "loss": 0.0023, "step": 247780 }, { "epoch": 59.5, "learning_rate": 1.9627231757380658e-05, "loss": 0.0015, "step": 247790 }, { "epoch": 59.5, "learning_rate": 1.9623667642791565e-05, "loss": 0.0018, "step": 247800 }, { "epoch": 59.5, "learning_rate": 1.962010377282727e-05, "loss": 0.0088, "step": 247810 }, { "epoch": 59.5, "learning_rate": 1.961654014751647e-05, "loss": 0.002, "step": 247820 }, { "epoch": 59.51, "learning_rate": 1.961297676688787e-05, "loss": 0.0027, "step": 247830 }, { "epoch": 59.51, "learning_rate": 1.9609413630970165e-05, "loss": 0.0047, "step": 247840 }, { "epoch": 59.51, "learning_rate": 1.9605850739792042e-05, "loss": 0.0049, "step": 247850 }, { "epoch": 59.51, "learning_rate": 1.960228809338218e-05, "loss": 0.0106, "step": 247860 }, { "epoch": 59.51, "learning_rate": 1.9598725691769315e-05, "loss": 0.0048, "step": 247870 }, { "epoch": 59.52, "learning_rate": 1.9595163534982124e-05, "loss": 0.0016, "step": 247880 }, { "epoch": 59.52, "learning_rate": 1.959160162304924e-05, "loss": 0.0015, "step": 247890 }, { "epoch": 59.52, "learning_rate": 1.9588039955999405e-05, "loss": 0.0032, "step": 247900 }, { "epoch": 59.52, "learning_rate": 1.9584478533861284e-05, "loss": 0.0014, "step": 247910 }, { "epoch": 59.53, "learning_rate": 1.958091735666356e-05, "loss": 0.0033, "step": 247920 }, { "epoch": 59.53, "learning_rate": 1.95773564244349e-05, "loss": 0.0048, "step": 247930 }, { "epoch": 59.53, "learning_rate": 1.9573795737203994e-05, "loss": 0.0028, "step": 247940 }, { "epoch": 59.53, "learning_rate": 1.9570235294999512e-05, "loss": 0.0068, "step": 247950 }, { "epoch": 59.54, "learning_rate": 1.9566675097850105e-05, "loss": 0.0024, "step": 247960 }, { "epoch": 59.54, "learning_rate": 1.9563115145784504e-05, "loss": 0.0084, "step": 247970 }, { "epoch": 59.54, "learning_rate": 1.955955543883132e-05, "loss": 0.0038, "step": 247980 }, { "epoch": 59.54, "learning_rate": 1.9555995977019237e-05, "loss": 0.0027, "step": 247990 }, { "epoch": 59.54, "learning_rate": 1.9552436760376907e-05, "loss": 0.0021, "step": 248000 }, { "epoch": 59.55, "learning_rate": 1.954887778893302e-05, "loss": 0.0015, "step": 248010 }, { "epoch": 59.55, "learning_rate": 1.954531906271625e-05, "loss": 0.0033, "step": 248020 }, { "epoch": 59.55, "learning_rate": 1.9541760581755185e-05, "loss": 0.0023, "step": 248030 }, { "epoch": 59.55, "learning_rate": 1.953820234607855e-05, "loss": 0.0043, "step": 248040 }, { "epoch": 59.56, "learning_rate": 1.9534644355714977e-05, "loss": 0.0053, "step": 248050 }, { "epoch": 59.56, "learning_rate": 1.9531086610693118e-05, "loss": 0.0023, "step": 248060 }, { "epoch": 59.56, "learning_rate": 1.9527529111041627e-05, "loss": 0.0067, "step": 248070 }, { "epoch": 59.56, "learning_rate": 1.9523971856789146e-05, "loss": 0.0019, "step": 248080 }, { "epoch": 59.57, "learning_rate": 1.9520414847964337e-05, "loss": 0.0019, "step": 248090 }, { "epoch": 59.57, "learning_rate": 1.9516858084595807e-05, "loss": 0.0021, "step": 248100 }, { "epoch": 59.57, "learning_rate": 1.9513301566712267e-05, "loss": 0.003, "step": 248110 }, { "epoch": 59.57, "learning_rate": 1.9509745294342303e-05, "loss": 0.0047, "step": 248120 }, { "epoch": 59.57, "learning_rate": 1.9506189267514546e-05, "loss": 0.006, "step": 248130 }, { "epoch": 59.58, "learning_rate": 1.9502633486257683e-05, "loss": 0.0032, "step": 248140 }, { "epoch": 59.58, "learning_rate": 1.9499077950600314e-05, "loss": 0.0024, "step": 248150 }, { "epoch": 59.58, "learning_rate": 1.9495522660571085e-05, "loss": 0.0031, "step": 248160 }, { "epoch": 59.58, "learning_rate": 1.9491967616198626e-05, "loss": 0.0017, "step": 248170 }, { "epoch": 59.59, "learning_rate": 1.948841281751156e-05, "loss": 0.0154, "step": 248180 }, { "epoch": 59.59, "learning_rate": 1.948485826453852e-05, "loss": 0.0018, "step": 248190 }, { "epoch": 59.59, "learning_rate": 1.948130395730811e-05, "loss": 0.0021, "step": 248200 }, { "epoch": 59.59, "learning_rate": 1.9477749895849007e-05, "loss": 0.0081, "step": 248210 }, { "epoch": 59.59, "learning_rate": 1.947419608018978e-05, "loss": 0.0015, "step": 248220 }, { "epoch": 59.6, "learning_rate": 1.9470642510359073e-05, "loss": 0.0017, "step": 248230 }, { "epoch": 59.6, "learning_rate": 1.9467089186385472e-05, "loss": 0.0023, "step": 248240 }, { "epoch": 59.6, "learning_rate": 1.9463536108297658e-05, "loss": 0.0036, "step": 248250 }, { "epoch": 59.6, "learning_rate": 1.9459983276124183e-05, "loss": 0.0032, "step": 248260 }, { "epoch": 59.61, "learning_rate": 1.9456430689893656e-05, "loss": 0.0023, "step": 248270 }, { "epoch": 59.61, "learning_rate": 1.9452878349634734e-05, "loss": 0.0014, "step": 248280 }, { "epoch": 59.61, "learning_rate": 1.9449326255376e-05, "loss": 0.0032, "step": 248290 }, { "epoch": 59.61, "learning_rate": 1.9445774407146056e-05, "loss": 0.0019, "step": 248300 }, { "epoch": 59.62, "learning_rate": 1.9442222804973508e-05, "loss": 0.0025, "step": 248310 }, { "epoch": 59.62, "learning_rate": 1.9438671448886965e-05, "loss": 0.0121, "step": 248320 }, { "epoch": 59.62, "learning_rate": 1.9435120338915014e-05, "loss": 0.0019, "step": 248330 }, { "epoch": 59.62, "learning_rate": 1.9431569475086242e-05, "loss": 0.0049, "step": 248340 }, { "epoch": 59.62, "learning_rate": 1.9428018857429298e-05, "loss": 0.0018, "step": 248350 }, { "epoch": 59.63, "learning_rate": 1.9424468485972725e-05, "loss": 0.0022, "step": 248360 }, { "epoch": 59.63, "learning_rate": 1.9420918360745106e-05, "loss": 0.0033, "step": 248370 }, { "epoch": 59.63, "learning_rate": 1.941736848177507e-05, "loss": 0.0022, "step": 248380 }, { "epoch": 59.63, "learning_rate": 1.941381884909121e-05, "loss": 0.0042, "step": 248390 }, { "epoch": 59.64, "learning_rate": 1.9410269462722062e-05, "loss": 0.006, "step": 248400 }, { "epoch": 59.64, "learning_rate": 1.9406720322696232e-05, "loss": 0.0025, "step": 248410 }, { "epoch": 59.64, "learning_rate": 1.9403171429042315e-05, "loss": 0.0049, "step": 248420 }, { "epoch": 59.64, "learning_rate": 1.939962278178889e-05, "loss": 0.0062, "step": 248430 }, { "epoch": 59.65, "learning_rate": 1.9396074380964524e-05, "loss": 0.0019, "step": 248440 }, { "epoch": 59.65, "learning_rate": 1.9392526226597796e-05, "loss": 0.0028, "step": 248450 }, { "epoch": 59.65, "learning_rate": 1.9388978318717278e-05, "loss": 0.0021, "step": 248460 }, { "epoch": 59.65, "learning_rate": 1.9385430657351545e-05, "loss": 0.0041, "step": 248470 }, { "epoch": 59.65, "learning_rate": 1.9381883242529146e-05, "loss": 0.0029, "step": 248480 }, { "epoch": 59.66, "learning_rate": 1.9378336074278707e-05, "loss": 0.0049, "step": 248490 }, { "epoch": 59.66, "learning_rate": 1.9374789152628736e-05, "loss": 0.0023, "step": 248500 }, { "epoch": 59.66, "learning_rate": 1.9371242477607805e-05, "loss": 0.0023, "step": 248510 }, { "epoch": 59.66, "learning_rate": 1.9367696049244493e-05, "loss": 0.0018, "step": 248520 }, { "epoch": 59.67, "learning_rate": 1.936414986756736e-05, "loss": 0.0219, "step": 248530 }, { "epoch": 59.67, "learning_rate": 1.936060393260496e-05, "loss": 0.0042, "step": 248540 }, { "epoch": 59.67, "learning_rate": 1.9357058244385844e-05, "loss": 0.0017, "step": 248550 }, { "epoch": 59.67, "learning_rate": 1.9353512802938567e-05, "loss": 0.012, "step": 248560 }, { "epoch": 59.67, "learning_rate": 1.9349967608291686e-05, "loss": 0.0012, "step": 248570 }, { "epoch": 59.68, "learning_rate": 1.934642266047374e-05, "loss": 0.0019, "step": 248580 }, { "epoch": 59.68, "learning_rate": 1.934287795951329e-05, "loss": 0.0019, "step": 248590 }, { "epoch": 59.68, "learning_rate": 1.9339333505438878e-05, "loss": 0.0039, "step": 248600 }, { "epoch": 59.68, "learning_rate": 1.9335789298279022e-05, "loss": 0.0024, "step": 248610 }, { "epoch": 59.69, "learning_rate": 1.933224533806231e-05, "loss": 0.0017, "step": 248620 }, { "epoch": 59.69, "learning_rate": 1.9328701624817282e-05, "loss": 0.01, "step": 248630 }, { "epoch": 59.69, "learning_rate": 1.9325158158572433e-05, "loss": 0.0018, "step": 248640 }, { "epoch": 59.69, "learning_rate": 1.9321614939356296e-05, "loss": 0.0016, "step": 248650 }, { "epoch": 59.7, "learning_rate": 1.9318071967197454e-05, "loss": 0.0019, "step": 248660 }, { "epoch": 59.7, "learning_rate": 1.9314529242124418e-05, "loss": 0.0031, "step": 248670 }, { "epoch": 59.7, "learning_rate": 1.9310986764165705e-05, "loss": 0.0019, "step": 248680 }, { "epoch": 59.7, "learning_rate": 1.930744453334986e-05, "loss": 0.0019, "step": 248690 }, { "epoch": 59.7, "learning_rate": 1.9303902549705398e-05, "loss": 0.0048, "step": 248700 }, { "epoch": 59.71, "learning_rate": 1.930036081326085e-05, "loss": 0.0016, "step": 248710 }, { "epoch": 59.71, "learning_rate": 1.929681932404473e-05, "loss": 0.0014, "step": 248720 }, { "epoch": 59.71, "learning_rate": 1.9293278082085563e-05, "loss": 0.0045, "step": 248730 }, { "epoch": 59.71, "learning_rate": 1.928973708741187e-05, "loss": 0.0046, "step": 248740 }, { "epoch": 59.72, "learning_rate": 1.928619634005215e-05, "loss": 0.0031, "step": 248750 }, { "epoch": 59.72, "learning_rate": 1.9282655840034942e-05, "loss": 0.0019, "step": 248760 }, { "epoch": 59.72, "learning_rate": 1.9279115587388764e-05, "loss": 0.0015, "step": 248770 }, { "epoch": 59.72, "learning_rate": 1.927557558214208e-05, "loss": 0.0038, "step": 248780 }, { "epoch": 59.73, "learning_rate": 1.9272035824323442e-05, "loss": 0.0024, "step": 248790 }, { "epoch": 59.73, "learning_rate": 1.9268496313961343e-05, "loss": 0.0042, "step": 248800 }, { "epoch": 59.73, "learning_rate": 1.926495705108428e-05, "loss": 0.0014, "step": 248810 }, { "epoch": 59.73, "learning_rate": 1.926141803572077e-05, "loss": 0.0027, "step": 248820 }, { "epoch": 59.73, "learning_rate": 1.92578792678993e-05, "loss": 0.0015, "step": 248830 }, { "epoch": 59.74, "learning_rate": 1.9254340747648375e-05, "loss": 0.0073, "step": 248840 }, { "epoch": 59.74, "learning_rate": 1.925080247499648e-05, "loss": 0.0017, "step": 248850 }, { "epoch": 59.74, "learning_rate": 1.9247264449972114e-05, "loss": 0.0026, "step": 248860 }, { "epoch": 59.74, "learning_rate": 1.9243726672603803e-05, "loss": 0.0074, "step": 248870 }, { "epoch": 59.75, "learning_rate": 1.9240189142919983e-05, "loss": 0.0076, "step": 248880 }, { "epoch": 59.75, "learning_rate": 1.9236651860949157e-05, "loss": 0.0019, "step": 248890 }, { "epoch": 59.75, "learning_rate": 1.9233114826719832e-05, "loss": 0.0025, "step": 248900 }, { "epoch": 59.75, "learning_rate": 1.9229578040260505e-05, "loss": 0.002, "step": 248910 }, { "epoch": 59.75, "learning_rate": 1.9226041501599597e-05, "loss": 0.0013, "step": 248920 }, { "epoch": 59.76, "learning_rate": 1.9222505210765634e-05, "loss": 0.0032, "step": 248930 }, { "epoch": 59.76, "learning_rate": 1.92189691677871e-05, "loss": 0.002, "step": 248940 }, { "epoch": 59.76, "learning_rate": 1.921543337269245e-05, "loss": 0.0025, "step": 248950 }, { "epoch": 59.76, "learning_rate": 1.9211897825510162e-05, "loss": 0.0027, "step": 248960 }, { "epoch": 59.77, "learning_rate": 1.9208362526268712e-05, "loss": 0.0041, "step": 248970 }, { "epoch": 59.77, "learning_rate": 1.920482747499657e-05, "loss": 0.0022, "step": 248980 }, { "epoch": 59.77, "learning_rate": 1.9201292671722193e-05, "loss": 0.0037, "step": 248990 }, { "epoch": 59.77, "learning_rate": 1.9197758116474067e-05, "loss": 0.0129, "step": 249000 }, { "epoch": 59.78, "learning_rate": 1.919422380928067e-05, "loss": 0.0025, "step": 249010 }, { "epoch": 59.78, "learning_rate": 1.919068975017041e-05, "loss": 0.0021, "step": 249020 }, { "epoch": 59.78, "learning_rate": 1.918715593917179e-05, "loss": 0.0033, "step": 249030 }, { "epoch": 59.78, "learning_rate": 1.918362237631326e-05, "loss": 0.0013, "step": 249040 }, { "epoch": 59.78, "learning_rate": 1.9180089061623273e-05, "loss": 0.0051, "step": 249050 }, { "epoch": 59.79, "learning_rate": 1.9176555995130284e-05, "loss": 0.0019, "step": 249060 }, { "epoch": 59.79, "learning_rate": 1.9173023176862743e-05, "loss": 0.0041, "step": 249070 }, { "epoch": 59.79, "learning_rate": 1.9169490606849104e-05, "loss": 0.0016, "step": 249080 }, { "epoch": 59.79, "learning_rate": 1.9165958285117813e-05, "loss": 0.0056, "step": 249090 }, { "epoch": 59.8, "learning_rate": 1.916242621169732e-05, "loss": 0.0037, "step": 249100 }, { "epoch": 59.8, "learning_rate": 1.915889438661606e-05, "loss": 0.0024, "step": 249110 }, { "epoch": 59.8, "learning_rate": 1.9155362809902488e-05, "loss": 0.004, "step": 249120 }, { "epoch": 59.8, "learning_rate": 1.9151831481585014e-05, "loss": 0.0017, "step": 249130 }, { "epoch": 59.81, "learning_rate": 1.9148300401692122e-05, "loss": 0.0024, "step": 249140 }, { "epoch": 59.81, "learning_rate": 1.9144769570252242e-05, "loss": 0.0051, "step": 249150 }, { "epoch": 59.81, "learning_rate": 1.914123898729376e-05, "loss": 0.0022, "step": 249160 }, { "epoch": 59.81, "learning_rate": 1.9137708652845155e-05, "loss": 0.0028, "step": 249170 }, { "epoch": 59.81, "learning_rate": 1.913417856693484e-05, "loss": 0.002, "step": 249180 }, { "epoch": 59.82, "learning_rate": 1.9130648729591254e-05, "loss": 0.0024, "step": 249190 }, { "epoch": 59.82, "learning_rate": 1.912711914084281e-05, "loss": 0.0026, "step": 249200 }, { "epoch": 59.82, "learning_rate": 1.912358980071794e-05, "loss": 0.0023, "step": 249210 }, { "epoch": 59.82, "learning_rate": 1.9120060709245065e-05, "loss": 0.0014, "step": 249220 }, { "epoch": 59.83, "learning_rate": 1.9116531866452588e-05, "loss": 0.0018, "step": 249230 }, { "epoch": 59.83, "learning_rate": 1.9113003272368973e-05, "loss": 0.0014, "step": 249240 }, { "epoch": 59.83, "learning_rate": 1.910947492702259e-05, "loss": 0.0019, "step": 249250 }, { "epoch": 59.83, "learning_rate": 1.9105946830441874e-05, "loss": 0.0017, "step": 249260 }, { "epoch": 59.83, "learning_rate": 1.9102418982655212e-05, "loss": 0.0094, "step": 249270 }, { "epoch": 59.84, "learning_rate": 1.9098891383691058e-05, "loss": 0.0024, "step": 249280 }, { "epoch": 59.84, "learning_rate": 1.909536403357781e-05, "loss": 0.0027, "step": 249290 }, { "epoch": 59.84, "learning_rate": 1.9091836932343833e-05, "loss": 0.003, "step": 249300 }, { "epoch": 59.84, "learning_rate": 1.9088310080017575e-05, "loss": 0.0021, "step": 249310 }, { "epoch": 59.85, "learning_rate": 1.9084783476627422e-05, "loss": 0.0026, "step": 249320 }, { "epoch": 59.85, "learning_rate": 1.9081257122201777e-05, "loss": 0.0039, "step": 249330 }, { "epoch": 59.85, "learning_rate": 1.907773101676904e-05, "loss": 0.0025, "step": 249340 }, { "epoch": 59.85, "learning_rate": 1.90742051603576e-05, "loss": 0.0021, "step": 249350 }, { "epoch": 59.86, "learning_rate": 1.9070679552995857e-05, "loss": 0.0052, "step": 249360 }, { "epoch": 59.86, "learning_rate": 1.9067154194712183e-05, "loss": 0.0083, "step": 249370 }, { "epoch": 59.86, "learning_rate": 1.9063629085535007e-05, "loss": 0.0027, "step": 249380 }, { "epoch": 59.86, "learning_rate": 1.9060104225492708e-05, "loss": 0.0047, "step": 249390 }, { "epoch": 59.86, "learning_rate": 1.9056579614613634e-05, "loss": 0.0055, "step": 249400 }, { "epoch": 59.87, "learning_rate": 1.9053055252926212e-05, "loss": 0.0029, "step": 249410 }, { "epoch": 59.87, "learning_rate": 1.9049531140458804e-05, "loss": 0.0025, "step": 249420 }, { "epoch": 59.87, "learning_rate": 1.9046007277239795e-05, "loss": 0.0023, "step": 249430 }, { "epoch": 59.87, "learning_rate": 1.9042483663297572e-05, "loss": 0.0025, "step": 249440 }, { "epoch": 59.88, "learning_rate": 1.9038960298660496e-05, "loss": 0.0034, "step": 249450 }, { "epoch": 59.88, "learning_rate": 1.9035437183356946e-05, "loss": 0.0036, "step": 249460 }, { "epoch": 59.88, "learning_rate": 1.9031914317415278e-05, "loss": 0.0044, "step": 249470 }, { "epoch": 59.88, "learning_rate": 1.902839170086391e-05, "loss": 0.0019, "step": 249480 }, { "epoch": 59.89, "learning_rate": 1.902486933373117e-05, "loss": 0.002, "step": 249490 }, { "epoch": 59.89, "learning_rate": 1.9021347216045432e-05, "loss": 0.0021, "step": 249500 }, { "epoch": 59.89, "learning_rate": 1.9017825347835043e-05, "loss": 0.003, "step": 249510 }, { "epoch": 59.89, "learning_rate": 1.90143037291284e-05, "loss": 0.0012, "step": 249520 }, { "epoch": 59.89, "learning_rate": 1.9010782359953866e-05, "loss": 0.0022, "step": 249530 }, { "epoch": 59.9, "learning_rate": 1.9007261240339748e-05, "loss": 0.0012, "step": 249540 }, { "epoch": 59.9, "learning_rate": 1.9003740370314448e-05, "loss": 0.0016, "step": 249550 }, { "epoch": 59.9, "learning_rate": 1.9000219749906305e-05, "loss": 0.0016, "step": 249560 }, { "epoch": 59.9, "learning_rate": 1.8996699379143675e-05, "loss": 0.0081, "step": 249570 }, { "epoch": 59.91, "learning_rate": 1.8993179258054905e-05, "loss": 0.0017, "step": 249580 }, { "epoch": 59.91, "learning_rate": 1.898965938666834e-05, "loss": 0.0025, "step": 249590 }, { "epoch": 59.91, "learning_rate": 1.898613976501233e-05, "loss": 0.0015, "step": 249600 }, { "epoch": 59.91, "learning_rate": 1.8982620393115202e-05, "loss": 0.0046, "step": 249610 }, { "epoch": 59.91, "learning_rate": 1.897910127100535e-05, "loss": 0.0017, "step": 249620 }, { "epoch": 59.92, "learning_rate": 1.8975582398711062e-05, "loss": 0.0025, "step": 249630 }, { "epoch": 59.92, "learning_rate": 1.8972063776260668e-05, "loss": 0.0014, "step": 249640 }, { "epoch": 59.92, "learning_rate": 1.8968545403682553e-05, "loss": 0.0026, "step": 249650 }, { "epoch": 59.92, "learning_rate": 1.8965027281005023e-05, "loss": 0.003, "step": 249660 }, { "epoch": 59.93, "learning_rate": 1.8961509408256412e-05, "loss": 0.0028, "step": 249670 }, { "epoch": 59.93, "learning_rate": 1.8957991785465052e-05, "loss": 0.0014, "step": 249680 }, { "epoch": 59.93, "learning_rate": 1.8954474412659268e-05, "loss": 0.0042, "step": 249690 }, { "epoch": 59.93, "learning_rate": 1.8950957289867388e-05, "loss": 0.0014, "step": 249700 }, { "epoch": 59.94, "learning_rate": 1.894744041711774e-05, "loss": 0.0029, "step": 249710 }, { "epoch": 59.94, "learning_rate": 1.8943923794438635e-05, "loss": 0.0015, "step": 249720 }, { "epoch": 59.94, "learning_rate": 1.89404074218584e-05, "loss": 0.0015, "step": 249730 }, { "epoch": 59.94, "learning_rate": 1.8936891299405358e-05, "loss": 0.0074, "step": 249740 }, { "epoch": 59.94, "learning_rate": 1.8933375427107797e-05, "loss": 0.003, "step": 249750 }, { "epoch": 59.95, "learning_rate": 1.8929859804994086e-05, "loss": 0.0027, "step": 249760 }, { "epoch": 59.95, "learning_rate": 1.8926344433092492e-05, "loss": 0.002, "step": 249770 }, { "epoch": 59.95, "learning_rate": 1.8922829311431318e-05, "loss": 0.0024, "step": 249780 }, { "epoch": 60.0, "learning_rate": 1.8919314440038904e-05, "loss": 0.0034, "step": 249790 }, { "epoch": 60.0, "learning_rate": 1.8915799818943542e-05, "loss": 0.0015, "step": 249800 }, { "epoch": 60.01, "learning_rate": 1.8912285448173532e-05, "loss": 0.0035, "step": 249810 }, { "epoch": 60.01, "learning_rate": 1.8908771327757185e-05, "loss": 0.0031, "step": 249820 }, { "epoch": 60.01, "learning_rate": 1.890525745772279e-05, "loss": 0.0017, "step": 249830 }, { "epoch": 60.01, "learning_rate": 1.8901743838098657e-05, "loss": 0.0018, "step": 249840 }, { "epoch": 60.02, "learning_rate": 1.8898230468913052e-05, "loss": 0.0023, "step": 249850 }, { "epoch": 60.02, "learning_rate": 1.8894717350194324e-05, "loss": 0.002, "step": 249860 }, { "epoch": 60.02, "learning_rate": 1.889120448197072e-05, "loss": 0.0024, "step": 249870 }, { "epoch": 60.02, "learning_rate": 1.888769186427052e-05, "loss": 0.0021, "step": 249880 }, { "epoch": 60.03, "learning_rate": 1.888417949712205e-05, "loss": 0.003, "step": 249890 }, { "epoch": 60.03, "learning_rate": 1.8880667380553597e-05, "loss": 0.0021, "step": 249900 }, { "epoch": 60.03, "learning_rate": 1.8877155514593403e-05, "loss": 0.0024, "step": 249910 }, { "epoch": 60.03, "learning_rate": 1.887364389926976e-05, "loss": 0.0018, "step": 249920 }, { "epoch": 60.03, "learning_rate": 1.887013253461098e-05, "loss": 0.004, "step": 249930 }, { "epoch": 60.04, "learning_rate": 1.8866621420645314e-05, "loss": 0.0021, "step": 249940 }, { "epoch": 60.04, "learning_rate": 1.886311055740105e-05, "loss": 0.0032, "step": 249950 }, { "epoch": 60.04, "learning_rate": 1.8859599944906454e-05, "loss": 0.0092, "step": 249960 }, { "epoch": 60.04, "learning_rate": 1.8856089583189794e-05, "loss": 0.0052, "step": 249970 }, { "epoch": 60.05, "learning_rate": 1.8852579472279346e-05, "loss": 0.0016, "step": 249980 }, { "epoch": 60.05, "learning_rate": 1.8849069612203363e-05, "loss": 0.0021, "step": 249990 }, { "epoch": 60.05, "learning_rate": 1.8845560002990154e-05, "loss": 0.0107, "step": 250000 }, { "epoch": 60.05, "learning_rate": 1.8842050644667937e-05, "loss": 0.0013, "step": 250010 }, { "epoch": 60.05, "learning_rate": 1.883854153726497e-05, "loss": 0.0042, "step": 250020 }, { "epoch": 60.06, "learning_rate": 1.8835032680809544e-05, "loss": 0.0017, "step": 250030 }, { "epoch": 60.06, "learning_rate": 1.8831524075329903e-05, "loss": 0.0026, "step": 250040 }, { "epoch": 60.06, "learning_rate": 1.8828015720854302e-05, "loss": 0.0017, "step": 250050 }, { "epoch": 60.06, "learning_rate": 1.8824507617410997e-05, "loss": 0.0013, "step": 250060 }, { "epoch": 60.07, "learning_rate": 1.8820999765028234e-05, "loss": 0.0013, "step": 250070 }, { "epoch": 60.07, "learning_rate": 1.8817492163734263e-05, "loss": 0.0015, "step": 250080 }, { "epoch": 60.07, "learning_rate": 1.8813984813557334e-05, "loss": 0.0015, "step": 250090 }, { "epoch": 60.07, "learning_rate": 1.8810477714525694e-05, "loss": 0.0062, "step": 250100 }, { "epoch": 60.08, "learning_rate": 1.8806970866667577e-05, "loss": 0.0026, "step": 250110 }, { "epoch": 60.08, "learning_rate": 1.880346427001122e-05, "loss": 0.0015, "step": 250120 }, { "epoch": 60.08, "learning_rate": 1.8799957924584884e-05, "loss": 0.0017, "step": 250130 }, { "epoch": 60.08, "learning_rate": 1.879645183041681e-05, "loss": 0.0025, "step": 250140 }, { "epoch": 60.08, "learning_rate": 1.8792945987535206e-05, "loss": 0.0031, "step": 250150 }, { "epoch": 60.09, "learning_rate": 1.8789440395968295e-05, "loss": 0.0013, "step": 250160 }, { "epoch": 60.09, "learning_rate": 1.8785935055744348e-05, "loss": 0.0039, "step": 250170 }, { "epoch": 60.09, "learning_rate": 1.8782429966891573e-05, "loss": 0.0019, "step": 250180 }, { "epoch": 60.09, "learning_rate": 1.87789251294382e-05, "loss": 0.0041, "step": 250190 }, { "epoch": 60.1, "learning_rate": 1.8775420543412454e-05, "loss": 0.0032, "step": 250200 }, { "epoch": 60.1, "learning_rate": 1.877191620884256e-05, "loss": 0.0014, "step": 250210 }, { "epoch": 60.1, "learning_rate": 1.876841212575673e-05, "loss": 0.0015, "step": 250220 }, { "epoch": 60.1, "learning_rate": 1.876490829418319e-05, "loss": 0.0038, "step": 250230 }, { "epoch": 60.11, "learning_rate": 1.876140471415016e-05, "loss": 0.0022, "step": 250240 }, { "epoch": 60.11, "learning_rate": 1.875790138568585e-05, "loss": 0.0041, "step": 250250 }, { "epoch": 60.11, "learning_rate": 1.8754398308818454e-05, "loss": 0.0017, "step": 250260 }, { "epoch": 60.11, "learning_rate": 1.8750895483576226e-05, "loss": 0.0025, "step": 250270 }, { "epoch": 60.11, "learning_rate": 1.874739290998736e-05, "loss": 0.0033, "step": 250280 }, { "epoch": 60.12, "learning_rate": 1.874389058808002e-05, "loss": 0.0021, "step": 250290 }, { "epoch": 60.12, "learning_rate": 1.874038851788246e-05, "loss": 0.007, "step": 250300 }, { "epoch": 60.12, "learning_rate": 1.8736886699422872e-05, "loss": 0.0027, "step": 250310 }, { "epoch": 60.12, "learning_rate": 1.8733385132729455e-05, "loss": 0.0032, "step": 250320 }, { "epoch": 60.13, "learning_rate": 1.8729883817830397e-05, "loss": 0.0014, "step": 250330 }, { "epoch": 60.13, "learning_rate": 1.8726382754753903e-05, "loss": 0.0019, "step": 250340 }, { "epoch": 60.13, "learning_rate": 1.8722881943528165e-05, "loss": 0.0044, "step": 250350 }, { "epoch": 60.13, "learning_rate": 1.871938138418138e-05, "loss": 0.0028, "step": 250360 }, { "epoch": 60.13, "learning_rate": 1.8715881076741713e-05, "loss": 0.0015, "step": 250370 }, { "epoch": 60.14, "learning_rate": 1.871238102123742e-05, "loss": 0.0035, "step": 250380 }, { "epoch": 60.14, "learning_rate": 1.8708881217696616e-05, "loss": 0.0019, "step": 250390 }, { "epoch": 60.14, "learning_rate": 1.8705381666147493e-05, "loss": 0.0026, "step": 250400 }, { "epoch": 60.14, "learning_rate": 1.8701882366618274e-05, "loss": 0.0081, "step": 250410 }, { "epoch": 60.15, "learning_rate": 1.869838331913713e-05, "loss": 0.0014, "step": 250420 }, { "epoch": 60.15, "learning_rate": 1.8694884523732197e-05, "loss": 0.0021, "step": 250430 }, { "epoch": 60.15, "learning_rate": 1.8691385980431696e-05, "loss": 0.0014, "step": 250440 }, { "epoch": 60.15, "learning_rate": 1.868788768926379e-05, "loss": 0.0059, "step": 250450 }, { "epoch": 60.16, "learning_rate": 1.868438965025664e-05, "loss": 0.0085, "step": 250460 }, { "epoch": 60.16, "learning_rate": 1.8680891863438425e-05, "loss": 0.0014, "step": 250470 }, { "epoch": 60.16, "learning_rate": 1.8677394328837318e-05, "loss": 0.0071, "step": 250480 }, { "epoch": 60.16, "learning_rate": 1.867389704648147e-05, "loss": 0.0023, "step": 250490 }, { "epoch": 60.16, "learning_rate": 1.8670400016399042e-05, "loss": 0.0039, "step": 250500 }, { "epoch": 60.17, "learning_rate": 1.8666903238618228e-05, "loss": 0.0264, "step": 250510 }, { "epoch": 60.17, "learning_rate": 1.866340671316718e-05, "loss": 0.0013, "step": 250520 }, { "epoch": 60.17, "learning_rate": 1.8659910440074014e-05, "loss": 0.0045, "step": 250530 }, { "epoch": 60.17, "learning_rate": 1.865641441936693e-05, "loss": 0.002, "step": 250540 }, { "epoch": 60.18, "learning_rate": 1.8652918651074065e-05, "loss": 0.0026, "step": 250550 }, { "epoch": 60.18, "learning_rate": 1.8649423135223593e-05, "loss": 0.0016, "step": 250560 }, { "epoch": 60.18, "learning_rate": 1.8645927871843617e-05, "loss": 0.0025, "step": 250570 }, { "epoch": 60.18, "learning_rate": 1.8642432860962323e-05, "loss": 0.0023, "step": 250580 }, { "epoch": 60.19, "learning_rate": 1.8638938102607846e-05, "loss": 0.0022, "step": 250590 }, { "epoch": 60.19, "learning_rate": 1.8635443596808334e-05, "loss": 0.0066, "step": 250600 }, { "epoch": 60.19, "learning_rate": 1.863194934359192e-05, "loss": 0.0147, "step": 250610 }, { "epoch": 60.19, "learning_rate": 1.862845534298675e-05, "loss": 0.002, "step": 250620 }, { "epoch": 60.19, "learning_rate": 1.8624961595020962e-05, "loss": 0.0014, "step": 250630 }, { "epoch": 60.2, "learning_rate": 1.8621468099722673e-05, "loss": 0.0113, "step": 250640 }, { "epoch": 60.2, "learning_rate": 1.8617974857120052e-05, "loss": 0.0046, "step": 250650 }, { "epoch": 60.2, "learning_rate": 1.8614481867241223e-05, "loss": 0.0063, "step": 250660 }, { "epoch": 60.2, "learning_rate": 1.8610989130114274e-05, "loss": 0.0013, "step": 250670 }, { "epoch": 60.21, "learning_rate": 1.8607496645767385e-05, "loss": 0.0032, "step": 250680 }, { "epoch": 60.21, "learning_rate": 1.8604004414228653e-05, "loss": 0.0023, "step": 250690 }, { "epoch": 60.21, "learning_rate": 1.8600512435526214e-05, "loss": 0.0023, "step": 250700 }, { "epoch": 60.21, "learning_rate": 1.8597020709688177e-05, "loss": 0.0023, "step": 250710 }, { "epoch": 60.21, "learning_rate": 1.859352923674267e-05, "loss": 0.0128, "step": 250720 }, { "epoch": 60.22, "learning_rate": 1.859003801671781e-05, "loss": 0.0039, "step": 250730 }, { "epoch": 60.22, "learning_rate": 1.8586547049641688e-05, "loss": 0.0086, "step": 250740 }, { "epoch": 60.22, "learning_rate": 1.8583056335542474e-05, "loss": 0.0055, "step": 250750 }, { "epoch": 60.22, "learning_rate": 1.8579565874448234e-05, "loss": 0.0023, "step": 250760 }, { "epoch": 60.23, "learning_rate": 1.8576075666387083e-05, "loss": 0.002, "step": 250770 }, { "epoch": 60.23, "learning_rate": 1.857258571138712e-05, "loss": 0.0019, "step": 250780 }, { "epoch": 60.23, "learning_rate": 1.8569096009476476e-05, "loss": 0.0027, "step": 250790 }, { "epoch": 60.23, "learning_rate": 1.856560656068326e-05, "loss": 0.0018, "step": 250800 }, { "epoch": 60.24, "learning_rate": 1.856211736503552e-05, "loss": 0.0027, "step": 250810 }, { "epoch": 60.24, "learning_rate": 1.855862842256141e-05, "loss": 0.0017, "step": 250820 }, { "epoch": 60.24, "learning_rate": 1.8555139733288994e-05, "loss": 0.0017, "step": 250830 }, { "epoch": 60.24, "learning_rate": 1.8551651297246392e-05, "loss": 0.0016, "step": 250840 }, { "epoch": 60.24, "learning_rate": 1.8548163114461675e-05, "loss": 0.0051, "step": 250850 }, { "epoch": 60.25, "learning_rate": 1.854467518496295e-05, "loss": 0.0025, "step": 250860 }, { "epoch": 60.25, "learning_rate": 1.8541187508778298e-05, "loss": 0.0014, "step": 250870 }, { "epoch": 60.25, "learning_rate": 1.8537700085935782e-05, "loss": 0.0028, "step": 250880 }, { "epoch": 60.25, "learning_rate": 1.853421291646355e-05, "loss": 0.0072, "step": 250890 }, { "epoch": 60.26, "learning_rate": 1.8530726000389625e-05, "loss": 0.0017, "step": 250900 }, { "epoch": 60.26, "learning_rate": 1.8527239337742093e-05, "loss": 0.0027, "step": 250910 }, { "epoch": 60.26, "learning_rate": 1.8523752928549066e-05, "loss": 0.0016, "step": 250920 }, { "epoch": 60.26, "learning_rate": 1.85202667728386e-05, "loss": 0.0025, "step": 250930 }, { "epoch": 60.27, "learning_rate": 1.8516780870638774e-05, "loss": 0.0034, "step": 250940 }, { "epoch": 60.27, "learning_rate": 1.8513295221977656e-05, "loss": 0.0033, "step": 250950 }, { "epoch": 60.27, "learning_rate": 1.8509809826883322e-05, "loss": 0.005, "step": 250960 }, { "epoch": 60.27, "learning_rate": 1.8506324685383836e-05, "loss": 0.002, "step": 250970 }, { "epoch": 60.27, "learning_rate": 1.8502839797507244e-05, "loss": 0.0015, "step": 250980 }, { "epoch": 60.28, "learning_rate": 1.8499355163281672e-05, "loss": 0.0014, "step": 250990 }, { "epoch": 60.28, "learning_rate": 1.8495870782735118e-05, "loss": 0.0014, "step": 251000 }, { "epoch": 60.28, "learning_rate": 1.849238665589567e-05, "loss": 0.0041, "step": 251010 }, { "epoch": 60.28, "learning_rate": 1.8488902782791367e-05, "loss": 0.0021, "step": 251020 }, { "epoch": 60.29, "learning_rate": 1.8485419163450297e-05, "loss": 0.003, "step": 251030 }, { "epoch": 60.29, "learning_rate": 1.8481935797900505e-05, "loss": 0.0015, "step": 251040 }, { "epoch": 60.29, "learning_rate": 1.847845268617001e-05, "loss": 0.0021, "step": 251050 }, { "epoch": 60.29, "learning_rate": 1.8474969828286902e-05, "loss": 0.0056, "step": 251060 }, { "epoch": 60.29, "learning_rate": 1.8471487224279215e-05, "loss": 0.0027, "step": 251070 }, { "epoch": 60.3, "learning_rate": 1.8468004874174998e-05, "loss": 0.0017, "step": 251080 }, { "epoch": 60.3, "learning_rate": 1.8464522778002286e-05, "loss": 0.0016, "step": 251090 }, { "epoch": 60.3, "learning_rate": 1.846104093578913e-05, "loss": 0.0022, "step": 251100 }, { "epoch": 60.3, "learning_rate": 1.8457559347563563e-05, "loss": 0.0051, "step": 251110 }, { "epoch": 60.31, "learning_rate": 1.8454078013353603e-05, "loss": 0.0018, "step": 251120 }, { "epoch": 60.31, "learning_rate": 1.8450596933187353e-05, "loss": 0.0015, "step": 251130 }, { "epoch": 60.31, "learning_rate": 1.8447116107092776e-05, "loss": 0.0017, "step": 251140 }, { "epoch": 60.31, "learning_rate": 1.8443635535097913e-05, "loss": 0.0025, "step": 251150 }, { "epoch": 60.32, "learning_rate": 1.8440155217230832e-05, "loss": 0.0032, "step": 251160 }, { "epoch": 60.32, "learning_rate": 1.8436675153519535e-05, "loss": 0.0025, "step": 251170 }, { "epoch": 60.32, "learning_rate": 1.8433195343992048e-05, "loss": 0.0032, "step": 251180 }, { "epoch": 60.32, "learning_rate": 1.84297157886764e-05, "loss": 0.005, "step": 251190 }, { "epoch": 60.32, "learning_rate": 1.8426236487600606e-05, "loss": 0.0015, "step": 251200 }, { "epoch": 60.33, "learning_rate": 1.842275744079269e-05, "loss": 0.0016, "step": 251210 }, { "epoch": 60.33, "learning_rate": 1.841927864828067e-05, "loss": 0.0024, "step": 251220 }, { "epoch": 60.33, "learning_rate": 1.8415800110092556e-05, "loss": 0.0021, "step": 251230 }, { "epoch": 60.33, "learning_rate": 1.8412321826256368e-05, "loss": 0.0038, "step": 251240 }, { "epoch": 60.34, "learning_rate": 1.8408843796800112e-05, "loss": 0.0116, "step": 251250 }, { "epoch": 60.34, "learning_rate": 1.840536602175178e-05, "loss": 0.0016, "step": 251260 }, { "epoch": 60.34, "learning_rate": 1.840188850113943e-05, "loss": 0.0027, "step": 251270 }, { "epoch": 60.34, "learning_rate": 1.839841123499102e-05, "loss": 0.0028, "step": 251280 }, { "epoch": 60.35, "learning_rate": 1.8394934223334547e-05, "loss": 0.0014, "step": 251290 }, { "epoch": 60.35, "learning_rate": 1.8391457466198055e-05, "loss": 0.0094, "step": 251300 }, { "epoch": 60.35, "learning_rate": 1.8387980963609512e-05, "loss": 0.0017, "step": 251310 }, { "epoch": 60.35, "learning_rate": 1.8384504715596928e-05, "loss": 0.0028, "step": 251320 }, { "epoch": 60.35, "learning_rate": 1.8381028722188293e-05, "loss": 0.0025, "step": 251330 }, { "epoch": 60.36, "learning_rate": 1.83775529834116e-05, "loss": 0.0021, "step": 251340 }, { "epoch": 60.36, "learning_rate": 1.8374077499294834e-05, "loss": 0.007, "step": 251350 }, { "epoch": 60.36, "learning_rate": 1.8370602269865973e-05, "loss": 0.0011, "step": 251360 }, { "epoch": 60.36, "learning_rate": 1.836712729515305e-05, "loss": 0.0029, "step": 251370 }, { "epoch": 60.37, "learning_rate": 1.8363652575184005e-05, "loss": 0.0061, "step": 251380 }, { "epoch": 60.37, "learning_rate": 1.8360178109986816e-05, "loss": 0.0018, "step": 251390 }, { "epoch": 60.37, "learning_rate": 1.8356703899589493e-05, "loss": 0.0014, "step": 251400 }, { "epoch": 60.37, "learning_rate": 1.8353229944020027e-05, "loss": 0.0025, "step": 251410 }, { "epoch": 60.37, "learning_rate": 1.834975624330635e-05, "loss": 0.0026, "step": 251420 }, { "epoch": 60.38, "learning_rate": 1.8346282797476432e-05, "loss": 0.0021, "step": 251430 }, { "epoch": 60.38, "learning_rate": 1.8342809606558292e-05, "loss": 0.0018, "step": 251440 }, { "epoch": 60.38, "learning_rate": 1.8339336670579878e-05, "loss": 0.0021, "step": 251450 }, { "epoch": 60.38, "learning_rate": 1.8335863989569152e-05, "loss": 0.0067, "step": 251460 }, { "epoch": 60.39, "learning_rate": 1.8332391563554093e-05, "loss": 0.0018, "step": 251470 }, { "epoch": 60.39, "learning_rate": 1.832891939256265e-05, "loss": 0.0029, "step": 251480 }, { "epoch": 60.39, "learning_rate": 1.8325447476622788e-05, "loss": 0.0017, "step": 251490 }, { "epoch": 60.39, "learning_rate": 1.832197581576246e-05, "loss": 0.0032, "step": 251500 }, { "epoch": 60.4, "learning_rate": 1.831850441000966e-05, "loss": 0.0023, "step": 251510 }, { "epoch": 60.4, "learning_rate": 1.831503325939231e-05, "loss": 0.002, "step": 251520 }, { "epoch": 60.4, "learning_rate": 1.831156236393835e-05, "loss": 0.0092, "step": 251530 }, { "epoch": 60.4, "learning_rate": 1.8308091723675775e-05, "loss": 0.0027, "step": 251540 }, { "epoch": 60.4, "learning_rate": 1.830462133863253e-05, "loss": 0.0017, "step": 251550 }, { "epoch": 60.41, "learning_rate": 1.8301151208836505e-05, "loss": 0.0023, "step": 251560 }, { "epoch": 60.41, "learning_rate": 1.8297681334315702e-05, "loss": 0.0014, "step": 251570 }, { "epoch": 60.41, "learning_rate": 1.8294211715098054e-05, "loss": 0.0051, "step": 251580 }, { "epoch": 60.41, "learning_rate": 1.8290742351211494e-05, "loss": 0.0021, "step": 251590 }, { "epoch": 60.42, "learning_rate": 1.828727324268396e-05, "loss": 0.0018, "step": 251600 }, { "epoch": 60.42, "learning_rate": 1.8283804389543395e-05, "loss": 0.0028, "step": 251610 }, { "epoch": 60.42, "learning_rate": 1.8280335791817733e-05, "loss": 0.0023, "step": 251620 }, { "epoch": 60.42, "learning_rate": 1.8276867449534908e-05, "loss": 0.0015, "step": 251630 }, { "epoch": 60.43, "learning_rate": 1.8273399362722826e-05, "loss": 0.0013, "step": 251640 }, { "epoch": 60.43, "learning_rate": 1.8269931531409478e-05, "loss": 0.0017, "step": 251650 }, { "epoch": 60.43, "learning_rate": 1.8266463955622738e-05, "loss": 0.0027, "step": 251660 }, { "epoch": 60.43, "learning_rate": 1.8262996635390524e-05, "loss": 0.0017, "step": 251670 }, { "epoch": 60.43, "learning_rate": 1.825952957074079e-05, "loss": 0.0027, "step": 251680 }, { "epoch": 60.44, "learning_rate": 1.8256062761701455e-05, "loss": 0.0016, "step": 251690 }, { "epoch": 60.44, "learning_rate": 1.8252596208300426e-05, "loss": 0.0029, "step": 251700 }, { "epoch": 60.44, "learning_rate": 1.8249129910565626e-05, "loss": 0.0013, "step": 251710 }, { "epoch": 60.44, "learning_rate": 1.8245663868524964e-05, "loss": 0.0042, "step": 251720 }, { "epoch": 60.45, "learning_rate": 1.824219808220635e-05, "loss": 0.0018, "step": 251730 }, { "epoch": 60.45, "learning_rate": 1.8238732551637704e-05, "loss": 0.0028, "step": 251740 }, { "epoch": 60.45, "learning_rate": 1.8235267276846933e-05, "loss": 0.0023, "step": 251750 }, { "epoch": 60.45, "learning_rate": 1.8231802257861934e-05, "loss": 0.0141, "step": 251760 }, { "epoch": 60.45, "learning_rate": 1.8228337494710607e-05, "loss": 0.0014, "step": 251770 }, { "epoch": 60.46, "learning_rate": 1.8224872987420878e-05, "loss": 0.0029, "step": 251780 }, { "epoch": 60.46, "learning_rate": 1.822140873602065e-05, "loss": 0.0014, "step": 251790 }, { "epoch": 60.46, "learning_rate": 1.821794474053777e-05, "loss": 0.0017, "step": 251800 }, { "epoch": 60.46, "learning_rate": 1.8214481001000188e-05, "loss": 0.0027, "step": 251810 }, { "epoch": 60.47, "learning_rate": 1.8211017517435774e-05, "loss": 0.0018, "step": 251820 }, { "epoch": 60.47, "learning_rate": 1.820755428987243e-05, "loss": 0.0063, "step": 251830 }, { "epoch": 60.47, "learning_rate": 1.820409131833804e-05, "loss": 0.0017, "step": 251840 }, { "epoch": 60.47, "learning_rate": 1.8200628602860487e-05, "loss": 0.0056, "step": 251850 }, { "epoch": 60.48, "learning_rate": 1.819716614346767e-05, "loss": 0.0053, "step": 251860 }, { "epoch": 60.48, "learning_rate": 1.8193703940187455e-05, "loss": 0.0017, "step": 251870 }, { "epoch": 60.48, "learning_rate": 1.8190241993047742e-05, "loss": 0.0018, "step": 251880 }, { "epoch": 60.48, "learning_rate": 1.81867803020764e-05, "loss": 0.0014, "step": 251890 }, { "epoch": 60.48, "learning_rate": 1.818331886730131e-05, "loss": 0.0062, "step": 251900 }, { "epoch": 60.49, "learning_rate": 1.8179857688750324e-05, "loss": 0.0035, "step": 251910 }, { "epoch": 60.49, "learning_rate": 1.8176396766451352e-05, "loss": 0.0015, "step": 251920 }, { "epoch": 60.49, "learning_rate": 1.8172936100432275e-05, "loss": 0.0031, "step": 251930 }, { "epoch": 60.49, "learning_rate": 1.81694756907209e-05, "loss": 0.0022, "step": 251940 }, { "epoch": 60.5, "learning_rate": 1.8166015537345148e-05, "loss": 0.0017, "step": 251950 }, { "epoch": 60.5, "learning_rate": 1.8162555640332867e-05, "loss": 0.0015, "step": 251960 }, { "epoch": 60.5, "learning_rate": 1.8159095999711923e-05, "loss": 0.0049, "step": 251970 }, { "epoch": 60.5, "learning_rate": 1.8155636615510174e-05, "loss": 0.0023, "step": 251980 }, { "epoch": 60.51, "learning_rate": 1.815217748775548e-05, "loss": 0.0031, "step": 251990 }, { "epoch": 60.51, "learning_rate": 1.8148718616475696e-05, "loss": 0.0014, "step": 252000 }, { "epoch": 60.51, "learning_rate": 1.8145260001698665e-05, "loss": 0.0036, "step": 252010 }, { "epoch": 60.51, "learning_rate": 1.8141801643452267e-05, "loss": 0.0019, "step": 252020 }, { "epoch": 60.51, "learning_rate": 1.8138343541764357e-05, "loss": 0.002, "step": 252030 }, { "epoch": 60.52, "learning_rate": 1.813488569666273e-05, "loss": 0.0036, "step": 252040 }, { "epoch": 60.52, "learning_rate": 1.8131428108175286e-05, "loss": 0.004, "step": 252050 }, { "epoch": 60.52, "learning_rate": 1.812797077632985e-05, "loss": 0.0031, "step": 252060 }, { "epoch": 60.52, "learning_rate": 1.8124513701154285e-05, "loss": 0.0024, "step": 252070 }, { "epoch": 60.53, "learning_rate": 1.8121056882676373e-05, "loss": 0.0235, "step": 252080 }, { "epoch": 60.53, "learning_rate": 1.811760032092401e-05, "loss": 0.0055, "step": 252090 }, { "epoch": 60.53, "learning_rate": 1.8114144015925016e-05, "loss": 0.0094, "step": 252100 }, { "epoch": 60.53, "learning_rate": 1.8110687967707224e-05, "loss": 0.0022, "step": 252110 }, { "epoch": 60.53, "learning_rate": 1.8107232176298462e-05, "loss": 0.005, "step": 252120 }, { "epoch": 60.54, "learning_rate": 1.8103776641726562e-05, "loss": 0.002, "step": 252130 }, { "epoch": 60.54, "learning_rate": 1.8100321364019346e-05, "loss": 0.003, "step": 252140 }, { "epoch": 60.54, "learning_rate": 1.8096866343204638e-05, "loss": 0.0158, "step": 252150 }, { "epoch": 60.54, "learning_rate": 1.8093411579310283e-05, "loss": 0.0029, "step": 252160 }, { "epoch": 60.55, "learning_rate": 1.8089957072364105e-05, "loss": 0.0028, "step": 252170 }, { "epoch": 60.55, "learning_rate": 1.8086502822393876e-05, "loss": 0.0104, "step": 252180 }, { "epoch": 60.55, "learning_rate": 1.8083048829427463e-05, "loss": 0.0036, "step": 252190 }, { "epoch": 60.55, "learning_rate": 1.807959509349267e-05, "loss": 0.0023, "step": 252200 }, { "epoch": 60.56, "learning_rate": 1.807614161461729e-05, "loss": 0.0034, "step": 252210 }, { "epoch": 60.56, "learning_rate": 1.8072688392829162e-05, "loss": 0.0042, "step": 252220 }, { "epoch": 60.56, "learning_rate": 1.806923542815608e-05, "loss": 0.0026, "step": 252230 }, { "epoch": 60.56, "learning_rate": 1.806578272062585e-05, "loss": 0.0032, "step": 252240 }, { "epoch": 60.56, "learning_rate": 1.8062330270266265e-05, "loss": 0.0062, "step": 252250 }, { "epoch": 60.57, "learning_rate": 1.805887807710518e-05, "loss": 0.002, "step": 252260 }, { "epoch": 60.57, "learning_rate": 1.8055426141170334e-05, "loss": 0.0034, "step": 252270 }, { "epoch": 60.57, "learning_rate": 1.8051974462489562e-05, "loss": 0.0027, "step": 252280 }, { "epoch": 60.57, "learning_rate": 1.8048523041090627e-05, "loss": 0.0109, "step": 252290 }, { "epoch": 60.58, "learning_rate": 1.8045071877001368e-05, "loss": 0.0017, "step": 252300 }, { "epoch": 60.58, "learning_rate": 1.8041620970249568e-05, "loss": 0.0043, "step": 252310 }, { "epoch": 60.58, "learning_rate": 1.803817032086298e-05, "loss": 0.0089, "step": 252320 }, { "epoch": 60.58, "learning_rate": 1.8034719928869432e-05, "loss": 0.0042, "step": 252330 }, { "epoch": 60.59, "learning_rate": 1.8031269794296696e-05, "loss": 0.0039, "step": 252340 }, { "epoch": 60.59, "learning_rate": 1.802781991717256e-05, "loss": 0.0063, "step": 252350 }, { "epoch": 60.59, "learning_rate": 1.8024370297524806e-05, "loss": 0.0027, "step": 252360 }, { "epoch": 60.59, "learning_rate": 1.8020920935381208e-05, "loss": 0.0016, "step": 252370 }, { "epoch": 60.59, "learning_rate": 1.801747183076955e-05, "loss": 0.003, "step": 252380 }, { "epoch": 60.6, "learning_rate": 1.8014022983717594e-05, "loss": 0.0014, "step": 252390 }, { "epoch": 60.6, "learning_rate": 1.8010574394253154e-05, "loss": 0.002, "step": 252400 }, { "epoch": 60.6, "learning_rate": 1.8007126062403967e-05, "loss": 0.0063, "step": 252410 }, { "epoch": 60.6, "learning_rate": 1.8003677988197787e-05, "loss": 0.0025, "step": 252420 }, { "epoch": 60.61, "learning_rate": 1.8000230171662424e-05, "loss": 0.0054, "step": 252430 }, { "epoch": 60.61, "learning_rate": 1.7996782612825624e-05, "loss": 0.002, "step": 252440 }, { "epoch": 60.61, "learning_rate": 1.7993335311715153e-05, "loss": 0.0039, "step": 252450 }, { "epoch": 60.61, "learning_rate": 1.7989888268358773e-05, "loss": 0.0027, "step": 252460 }, { "epoch": 60.61, "learning_rate": 1.798644148278424e-05, "loss": 0.0016, "step": 252470 }, { "epoch": 60.62, "learning_rate": 1.798299495501931e-05, "loss": 0.0046, "step": 252480 }, { "epoch": 60.62, "learning_rate": 1.7979548685091734e-05, "loss": 0.0017, "step": 252490 }, { "epoch": 60.62, "learning_rate": 1.7976102673029298e-05, "loss": 0.0035, "step": 252500 }, { "epoch": 60.62, "learning_rate": 1.797265691885972e-05, "loss": 0.0019, "step": 252510 }, { "epoch": 60.63, "learning_rate": 1.796921142261075e-05, "loss": 0.0015, "step": 252520 }, { "epoch": 60.63, "learning_rate": 1.7965766184310128e-05, "loss": 0.0034, "step": 252530 }, { "epoch": 60.63, "learning_rate": 1.796232120398565e-05, "loss": 0.0016, "step": 252540 }, { "epoch": 60.63, "learning_rate": 1.7958876481665004e-05, "loss": 0.0034, "step": 252550 }, { "epoch": 60.64, "learning_rate": 1.7955432017375927e-05, "loss": 0.0032, "step": 252560 }, { "epoch": 60.64, "learning_rate": 1.7951987811146202e-05, "loss": 0.0023, "step": 252570 }, { "epoch": 60.64, "learning_rate": 1.7948543863003547e-05, "loss": 0.0026, "step": 252580 }, { "epoch": 60.64, "learning_rate": 1.7945100172975687e-05, "loss": 0.0023, "step": 252590 }, { "epoch": 60.64, "learning_rate": 1.7941656741090367e-05, "loss": 0.0034, "step": 252600 }, { "epoch": 60.65, "learning_rate": 1.7938213567375305e-05, "loss": 0.0015, "step": 252610 }, { "epoch": 60.65, "learning_rate": 1.793477065185824e-05, "loss": 0.002, "step": 252620 }, { "epoch": 60.65, "learning_rate": 1.7931327994566875e-05, "loss": 0.002, "step": 252630 }, { "epoch": 60.65, "learning_rate": 1.7927885595528988e-05, "loss": 0.003, "step": 252640 }, { "epoch": 60.66, "learning_rate": 1.7924443454772245e-05, "loss": 0.0028, "step": 252650 }, { "epoch": 60.66, "learning_rate": 1.7921001572324377e-05, "loss": 0.0016, "step": 252660 }, { "epoch": 60.66, "learning_rate": 1.7917559948213124e-05, "loss": 0.0037, "step": 252670 }, { "epoch": 60.66, "learning_rate": 1.7914118582466188e-05, "loss": 0.0081, "step": 252680 }, { "epoch": 60.66, "learning_rate": 1.791067747511131e-05, "loss": 0.0021, "step": 252690 }, { "epoch": 60.67, "learning_rate": 1.7907236626176132e-05, "loss": 0.0014, "step": 252700 }, { "epoch": 60.67, "learning_rate": 1.7903796035688438e-05, "loss": 0.0021, "step": 252710 }, { "epoch": 60.67, "learning_rate": 1.7900355703675893e-05, "loss": 0.002, "step": 252720 }, { "epoch": 60.67, "learning_rate": 1.7896915630166223e-05, "loss": 0.0037, "step": 252730 }, { "epoch": 60.68, "learning_rate": 1.7893475815187123e-05, "loss": 0.0017, "step": 252740 }, { "epoch": 60.68, "learning_rate": 1.789003625876629e-05, "loss": 0.0064, "step": 252750 }, { "epoch": 60.68, "learning_rate": 1.788659696093143e-05, "loss": 0.0023, "step": 252760 }, { "epoch": 60.68, "learning_rate": 1.7883157921710226e-05, "loss": 0.0019, "step": 252770 }, { "epoch": 60.69, "learning_rate": 1.7879719141130413e-05, "loss": 0.0023, "step": 252780 }, { "epoch": 60.69, "learning_rate": 1.7876280619219644e-05, "loss": 0.0014, "step": 252790 }, { "epoch": 60.69, "learning_rate": 1.7872842356005597e-05, "loss": 0.0013, "step": 252800 }, { "epoch": 60.69, "learning_rate": 1.7869404351516013e-05, "loss": 0.0015, "step": 252810 }, { "epoch": 60.69, "learning_rate": 1.7865966605778545e-05, "loss": 0.003, "step": 252820 }, { "epoch": 60.7, "learning_rate": 1.7862529118820887e-05, "loss": 0.002, "step": 252830 }, { "epoch": 60.7, "learning_rate": 1.785909189067072e-05, "loss": 0.0065, "step": 252840 }, { "epoch": 60.7, "learning_rate": 1.7855654921355718e-05, "loss": 0.002, "step": 252850 }, { "epoch": 60.7, "learning_rate": 1.785221821090357e-05, "loss": 0.007, "step": 252860 }, { "epoch": 60.71, "learning_rate": 1.784878175934195e-05, "loss": 0.0016, "step": 252870 }, { "epoch": 60.71, "learning_rate": 1.7845345566698523e-05, "loss": 0.0057, "step": 252880 }, { "epoch": 60.71, "learning_rate": 1.784190963300097e-05, "loss": 0.0021, "step": 252890 }, { "epoch": 60.71, "learning_rate": 1.783847395827694e-05, "loss": 0.0035, "step": 252900 }, { "epoch": 60.72, "learning_rate": 1.783503854255414e-05, "loss": 0.0021, "step": 252910 }, { "epoch": 60.72, "learning_rate": 1.7831603385860223e-05, "loss": 0.002, "step": 252920 }, { "epoch": 60.72, "learning_rate": 1.782816848822284e-05, "loss": 0.0023, "step": 252930 }, { "epoch": 60.72, "learning_rate": 1.7824733849669635e-05, "loss": 0.0026, "step": 252940 }, { "epoch": 60.72, "learning_rate": 1.7821299470228303e-05, "loss": 0.0023, "step": 252950 }, { "epoch": 60.73, "learning_rate": 1.7817865349926494e-05, "loss": 0.0015, "step": 252960 }, { "epoch": 60.73, "learning_rate": 1.781443148879186e-05, "loss": 0.0035, "step": 252970 }, { "epoch": 60.73, "learning_rate": 1.781099788685205e-05, "loss": 0.002, "step": 252980 }, { "epoch": 60.73, "learning_rate": 1.7807564544134718e-05, "loss": 0.0013, "step": 252990 }, { "epoch": 60.74, "learning_rate": 1.7804131460667518e-05, "loss": 0.0011, "step": 253000 }, { "epoch": 60.74, "learning_rate": 1.7800698636478068e-05, "loss": 0.0022, "step": 253010 }, { "epoch": 60.74, "learning_rate": 1.7797266071594078e-05, "loss": 0.005, "step": 253020 }, { "epoch": 60.74, "learning_rate": 1.779383376604313e-05, "loss": 0.0019, "step": 253030 }, { "epoch": 60.74, "learning_rate": 1.7790401719852862e-05, "loss": 0.0025, "step": 253040 }, { "epoch": 60.75, "learning_rate": 1.7786969933050955e-05, "loss": 0.0014, "step": 253050 }, { "epoch": 60.75, "learning_rate": 1.778353840566505e-05, "loss": 0.0034, "step": 253060 }, { "epoch": 60.75, "learning_rate": 1.7780107137722724e-05, "loss": 0.0018, "step": 253070 }, { "epoch": 60.75, "learning_rate": 1.7776676129251657e-05, "loss": 0.0021, "step": 253080 }, { "epoch": 60.76, "learning_rate": 1.7773245380279464e-05, "loss": 0.005, "step": 253090 }, { "epoch": 60.76, "learning_rate": 1.7769814890833775e-05, "loss": 0.0055, "step": 253100 }, { "epoch": 60.76, "learning_rate": 1.776638466094222e-05, "loss": 0.0018, "step": 253110 }, { "epoch": 60.76, "learning_rate": 1.7762954690632417e-05, "loss": 0.0017, "step": 253120 }, { "epoch": 60.77, "learning_rate": 1.775952497993199e-05, "loss": 0.0035, "step": 253130 }, { "epoch": 60.77, "learning_rate": 1.7756095528868562e-05, "loss": 0.0044, "step": 253140 }, { "epoch": 60.77, "learning_rate": 1.775266633746973e-05, "loss": 0.0026, "step": 253150 }, { "epoch": 60.77, "learning_rate": 1.7749237405763165e-05, "loss": 0.0025, "step": 253160 }, { "epoch": 60.77, "learning_rate": 1.774580873377642e-05, "loss": 0.0017, "step": 253170 }, { "epoch": 60.78, "learning_rate": 1.7742380321537115e-05, "loss": 0.0016, "step": 253180 }, { "epoch": 60.78, "learning_rate": 1.77389521690729e-05, "loss": 0.0019, "step": 253190 }, { "epoch": 60.78, "learning_rate": 1.7735524276411363e-05, "loss": 0.0022, "step": 253200 }, { "epoch": 60.78, "learning_rate": 1.7732096643580077e-05, "loss": 0.0037, "step": 253210 }, { "epoch": 60.79, "learning_rate": 1.7728669270606685e-05, "loss": 0.0013, "step": 253220 }, { "epoch": 60.79, "learning_rate": 1.7725242157518773e-05, "loss": 0.0029, "step": 253230 }, { "epoch": 60.79, "learning_rate": 1.7721815304343947e-05, "loss": 0.0083, "step": 253240 }, { "epoch": 60.79, "learning_rate": 1.7718388711109797e-05, "loss": 0.0022, "step": 253250 }, { "epoch": 60.8, "learning_rate": 1.7714962377843913e-05, "loss": 0.0017, "step": 253260 }, { "epoch": 60.8, "learning_rate": 1.77115363045739e-05, "loss": 0.0017, "step": 253270 }, { "epoch": 60.8, "learning_rate": 1.7708110491327327e-05, "loss": 0.0021, "step": 253280 }, { "epoch": 60.8, "learning_rate": 1.7704684938131815e-05, "loss": 0.0015, "step": 253290 }, { "epoch": 60.8, "learning_rate": 1.770125964501495e-05, "loss": 0.0015, "step": 253300 }, { "epoch": 60.81, "learning_rate": 1.7697834612004267e-05, "loss": 0.0015, "step": 253310 }, { "epoch": 60.81, "learning_rate": 1.7694409839127395e-05, "loss": 0.0018, "step": 253320 }, { "epoch": 60.81, "learning_rate": 1.76909853264119e-05, "loss": 0.0016, "step": 253330 }, { "epoch": 60.81, "learning_rate": 1.7687561073885366e-05, "loss": 0.0016, "step": 253340 }, { "epoch": 60.82, "learning_rate": 1.7684137081575358e-05, "loss": 0.0013, "step": 253350 }, { "epoch": 60.82, "learning_rate": 1.768071334950946e-05, "loss": 0.0016, "step": 253360 }, { "epoch": 60.82, "learning_rate": 1.7677289877715236e-05, "loss": 0.0015, "step": 253370 }, { "epoch": 60.82, "learning_rate": 1.7673866666220264e-05, "loss": 0.0018, "step": 253380 }, { "epoch": 60.82, "learning_rate": 1.7670443715052102e-05, "loss": 0.0018, "step": 253390 }, { "epoch": 60.83, "learning_rate": 1.766702102423832e-05, "loss": 0.0015, "step": 253400 }, { "epoch": 60.83, "learning_rate": 1.7663598593806484e-05, "loss": 0.0017, "step": 253410 }, { "epoch": 60.83, "learning_rate": 1.7660176423784134e-05, "loss": 0.0023, "step": 253420 }, { "epoch": 60.83, "learning_rate": 1.765675451419887e-05, "loss": 0.0016, "step": 253430 }, { "epoch": 60.84, "learning_rate": 1.7653332865078242e-05, "loss": 0.0085, "step": 253440 }, { "epoch": 60.84, "learning_rate": 1.7649911476449753e-05, "loss": 0.0014, "step": 253450 }, { "epoch": 60.84, "learning_rate": 1.764649034834101e-05, "loss": 0.0025, "step": 253460 }, { "epoch": 60.84, "learning_rate": 1.764306948077955e-05, "loss": 0.0017, "step": 253470 }, { "epoch": 60.85, "learning_rate": 1.7639648873792918e-05, "loss": 0.0015, "step": 253480 }, { "epoch": 60.85, "learning_rate": 1.763622852740866e-05, "loss": 0.002, "step": 253490 }, { "epoch": 60.85, "learning_rate": 1.7632808441654326e-05, "loss": 0.0013, "step": 253500 }, { "epoch": 60.85, "learning_rate": 1.7629388616557445e-05, "loss": 0.0017, "step": 253510 }, { "epoch": 60.85, "learning_rate": 1.762596905214556e-05, "loss": 0.0016, "step": 253520 }, { "epoch": 60.86, "learning_rate": 1.7622549748446244e-05, "loss": 0.0037, "step": 253530 }, { "epoch": 60.86, "learning_rate": 1.7619130705486987e-05, "loss": 0.003, "step": 253540 }, { "epoch": 60.86, "learning_rate": 1.761571192329534e-05, "loss": 0.0051, "step": 253550 }, { "epoch": 60.86, "learning_rate": 1.7612293401898822e-05, "loss": 0.0021, "step": 253560 }, { "epoch": 60.87, "learning_rate": 1.7608875141324993e-05, "loss": 0.0016, "step": 253570 }, { "epoch": 60.87, "learning_rate": 1.7605457141601383e-05, "loss": 0.0016, "step": 253580 }, { "epoch": 60.87, "learning_rate": 1.760203940275546e-05, "loss": 0.0036, "step": 253590 }, { "epoch": 60.87, "learning_rate": 1.7598621924814806e-05, "loss": 0.0021, "step": 253600 }, { "epoch": 60.88, "learning_rate": 1.759520470780693e-05, "loss": 0.0056, "step": 253610 }, { "epoch": 60.88, "learning_rate": 1.759178775175933e-05, "loss": 0.0017, "step": 253620 }, { "epoch": 60.88, "learning_rate": 1.758837105669955e-05, "loss": 0.0016, "step": 253630 }, { "epoch": 60.88, "learning_rate": 1.7584954622655088e-05, "loss": 0.003, "step": 253640 }, { "epoch": 60.88, "learning_rate": 1.7581538449653462e-05, "loss": 0.0015, "step": 253650 }, { "epoch": 60.89, "learning_rate": 1.7578122537722164e-05, "loss": 0.0027, "step": 253660 }, { "epoch": 60.89, "learning_rate": 1.7574706886888737e-05, "loss": 0.0042, "step": 253670 }, { "epoch": 60.89, "learning_rate": 1.757129149718069e-05, "loss": 0.0018, "step": 253680 }, { "epoch": 60.89, "learning_rate": 1.756787636862548e-05, "loss": 0.0015, "step": 253690 }, { "epoch": 60.9, "learning_rate": 1.756446150125065e-05, "loss": 0.0016, "step": 253700 }, { "epoch": 60.9, "learning_rate": 1.7561046895083692e-05, "loss": 0.0023, "step": 253710 }, { "epoch": 60.9, "learning_rate": 1.7557632550152108e-05, "loss": 0.0022, "step": 253720 }, { "epoch": 60.9, "learning_rate": 1.755421846648338e-05, "loss": 0.002, "step": 253730 }, { "epoch": 60.9, "learning_rate": 1.755080464410501e-05, "loss": 0.0012, "step": 253740 }, { "epoch": 60.91, "learning_rate": 1.7547391083044495e-05, "loss": 0.0047, "step": 253750 }, { "epoch": 60.91, "learning_rate": 1.75439777833293e-05, "loss": 0.0031, "step": 253760 }, { "epoch": 60.91, "learning_rate": 1.754056474498697e-05, "loss": 0.0032, "step": 253770 }, { "epoch": 60.91, "learning_rate": 1.7537151968044934e-05, "loss": 0.0018, "step": 253780 }, { "epoch": 60.92, "learning_rate": 1.7533739452530694e-05, "loss": 0.0022, "step": 253790 }, { "epoch": 60.92, "learning_rate": 1.753032719847172e-05, "loss": 0.0016, "step": 253800 }, { "epoch": 60.92, "learning_rate": 1.7526915205895513e-05, "loss": 0.0035, "step": 253810 }, { "epoch": 60.92, "learning_rate": 1.752350347482956e-05, "loss": 0.003, "step": 253820 }, { "epoch": 60.93, "learning_rate": 1.7520092005301288e-05, "loss": 0.0019, "step": 253830 }, { "epoch": 60.93, "learning_rate": 1.7516680797338215e-05, "loss": 0.0027, "step": 253840 }, { "epoch": 60.93, "learning_rate": 1.7513269850967794e-05, "loss": 0.0027, "step": 253850 }, { "epoch": 60.93, "learning_rate": 1.7509859166217495e-05, "loss": 0.0013, "step": 253860 }, { "epoch": 60.93, "learning_rate": 1.750644874311479e-05, "loss": 0.0084, "step": 253870 }, { "epoch": 60.94, "learning_rate": 1.7503038581687136e-05, "loss": 0.0021, "step": 253880 }, { "epoch": 60.94, "learning_rate": 1.7499628681962e-05, "loss": 0.0028, "step": 253890 }, { "epoch": 60.94, "learning_rate": 1.7496219043966823e-05, "loss": 0.0016, "step": 253900 }, { "epoch": 60.94, "learning_rate": 1.7492809667729114e-05, "loss": 0.0022, "step": 253910 }, { "epoch": 60.95, "learning_rate": 1.7489400553276282e-05, "loss": 0.0025, "step": 253920 }, { "epoch": 60.95, "learning_rate": 1.7485991700635778e-05, "loss": 0.0024, "step": 253930 }, { "epoch": 60.95, "learning_rate": 1.748258310983509e-05, "loss": 0.0016, "step": 253940 }, { "epoch": 61.0, "learning_rate": 1.747917478090165e-05, "loss": 0.0025, "step": 253950 }, { "epoch": 61.0, "learning_rate": 1.74757667138629e-05, "loss": 0.0012, "step": 253960 }, { "epoch": 61.01, "learning_rate": 1.7472358908746295e-05, "loss": 0.0056, "step": 253970 }, { "epoch": 61.01, "learning_rate": 1.7468951365579272e-05, "loss": 0.0023, "step": 253980 }, { "epoch": 61.01, "learning_rate": 1.746554408438928e-05, "loss": 0.0046, "step": 253990 }, { "epoch": 61.01, "learning_rate": 1.7462137065203747e-05, "loss": 0.002, "step": 254000 }, { "epoch": 61.02, "learning_rate": 1.7458730308050126e-05, "loss": 0.0023, "step": 254010 }, { "epoch": 61.02, "learning_rate": 1.745532381295583e-05, "loss": 0.0078, "step": 254020 }, { "epoch": 61.02, "learning_rate": 1.7451917579948312e-05, "loss": 0.0033, "step": 254030 }, { "epoch": 61.02, "learning_rate": 1.744851160905498e-05, "loss": 0.0034, "step": 254040 }, { "epoch": 61.02, "learning_rate": 1.7445105900303304e-05, "loss": 0.0025, "step": 254050 }, { "epoch": 61.03, "learning_rate": 1.7441700453720672e-05, "loss": 0.0075, "step": 254060 }, { "epoch": 61.03, "learning_rate": 1.743829526933451e-05, "loss": 0.0021, "step": 254070 }, { "epoch": 61.03, "learning_rate": 1.743489034717226e-05, "loss": 0.0019, "step": 254080 }, { "epoch": 61.03, "learning_rate": 1.7431485687261334e-05, "loss": 0.0023, "step": 254090 }, { "epoch": 61.04, "learning_rate": 1.7428081289629155e-05, "loss": 0.0016, "step": 254100 }, { "epoch": 61.04, "learning_rate": 1.742467715430313e-05, "loss": 0.0021, "step": 254110 }, { "epoch": 61.04, "learning_rate": 1.7421273281310685e-05, "loss": 0.0015, "step": 254120 }, { "epoch": 61.04, "learning_rate": 1.7417869670679217e-05, "loss": 0.0014, "step": 254130 }, { "epoch": 61.05, "learning_rate": 1.741446632243613e-05, "loss": 0.003, "step": 254140 }, { "epoch": 61.05, "learning_rate": 1.741106323660887e-05, "loss": 0.0021, "step": 254150 }, { "epoch": 61.05, "learning_rate": 1.7407660413224806e-05, "loss": 0.0019, "step": 254160 }, { "epoch": 61.05, "learning_rate": 1.740425785231134e-05, "loss": 0.0014, "step": 254170 }, { "epoch": 61.05, "learning_rate": 1.7400855553895896e-05, "loss": 0.0141, "step": 254180 }, { "epoch": 61.06, "learning_rate": 1.739745351800588e-05, "loss": 0.0039, "step": 254190 }, { "epoch": 61.06, "learning_rate": 1.7394051744668656e-05, "loss": 0.0013, "step": 254200 }, { "epoch": 61.06, "learning_rate": 1.739065023391162e-05, "loss": 0.0017, "step": 254210 }, { "epoch": 61.06, "learning_rate": 1.7387248985762195e-05, "loss": 0.0015, "step": 254220 }, { "epoch": 61.07, "learning_rate": 1.7383848000247753e-05, "loss": 0.0036, "step": 254230 }, { "epoch": 61.07, "learning_rate": 1.738044727739569e-05, "loss": 0.0016, "step": 254240 }, { "epoch": 61.07, "learning_rate": 1.737704681723339e-05, "loss": 0.0019, "step": 254250 }, { "epoch": 61.07, "learning_rate": 1.737364661978823e-05, "loss": 0.0015, "step": 254260 }, { "epoch": 61.07, "learning_rate": 1.7370246685087604e-05, "loss": 0.0041, "step": 254270 }, { "epoch": 61.08, "learning_rate": 1.7366847013158867e-05, "loss": 0.0016, "step": 254280 }, { "epoch": 61.08, "learning_rate": 1.736344760402945e-05, "loss": 0.0018, "step": 254290 }, { "epoch": 61.08, "learning_rate": 1.736004845772668e-05, "loss": 0.0016, "step": 254300 }, { "epoch": 61.08, "learning_rate": 1.7356649574277926e-05, "loss": 0.0019, "step": 254310 }, { "epoch": 61.09, "learning_rate": 1.73532509537106e-05, "loss": 0.0029, "step": 254320 }, { "epoch": 61.09, "learning_rate": 1.7349852596052047e-05, "loss": 0.0057, "step": 254330 }, { "epoch": 61.09, "learning_rate": 1.734645450132964e-05, "loss": 0.0015, "step": 254340 }, { "epoch": 61.09, "learning_rate": 1.7343056669570745e-05, "loss": 0.0015, "step": 254350 }, { "epoch": 61.1, "learning_rate": 1.7339659100802725e-05, "loss": 0.0025, "step": 254360 }, { "epoch": 61.1, "learning_rate": 1.7336261795052933e-05, "loss": 0.0016, "step": 254370 }, { "epoch": 61.1, "learning_rate": 1.7332864752348738e-05, "loss": 0.0151, "step": 254380 }, { "epoch": 61.1, "learning_rate": 1.7329467972717495e-05, "loss": 0.003, "step": 254390 }, { "epoch": 61.1, "learning_rate": 1.7326071456186555e-05, "loss": 0.0013, "step": 254400 }, { "epoch": 61.11, "learning_rate": 1.7322675202783256e-05, "loss": 0.002, "step": 254410 }, { "epoch": 61.11, "learning_rate": 1.7319279212534977e-05, "loss": 0.0017, "step": 254420 }, { "epoch": 61.11, "learning_rate": 1.7315883485469075e-05, "loss": 0.0024, "step": 254430 }, { "epoch": 61.11, "learning_rate": 1.731248802161286e-05, "loss": 0.006, "step": 254440 }, { "epoch": 61.12, "learning_rate": 1.730909282099368e-05, "loss": 0.0021, "step": 254450 }, { "epoch": 61.12, "learning_rate": 1.7305697883638893e-05, "loss": 0.0013, "step": 254460 }, { "epoch": 61.12, "learning_rate": 1.7302303209575843e-05, "loss": 0.0042, "step": 254470 }, { "epoch": 61.12, "learning_rate": 1.729890879883186e-05, "loss": 0.0032, "step": 254480 }, { "epoch": 61.12, "learning_rate": 1.7295514651434275e-05, "loss": 0.0108, "step": 254490 }, { "epoch": 61.13, "learning_rate": 1.729212076741043e-05, "loss": 0.0012, "step": 254500 }, { "epoch": 61.13, "learning_rate": 1.728872714678765e-05, "loss": 0.002, "step": 254510 }, { "epoch": 61.13, "learning_rate": 1.728533378959325e-05, "loss": 0.003, "step": 254520 }, { "epoch": 61.13, "learning_rate": 1.7281940695854602e-05, "loss": 0.0015, "step": 254530 }, { "epoch": 61.14, "learning_rate": 1.7278547865598994e-05, "loss": 0.003, "step": 254540 }, { "epoch": 61.14, "learning_rate": 1.7275155298853736e-05, "loss": 0.0034, "step": 254550 }, { "epoch": 61.14, "learning_rate": 1.7271762995646185e-05, "loss": 0.002, "step": 254560 }, { "epoch": 61.14, "learning_rate": 1.7268370956003665e-05, "loss": 0.0023, "step": 254570 }, { "epoch": 61.15, "learning_rate": 1.7264979179953438e-05, "loss": 0.0019, "step": 254580 }, { "epoch": 61.15, "learning_rate": 1.7261587667522873e-05, "loss": 0.0068, "step": 254590 }, { "epoch": 61.15, "learning_rate": 1.7258196418739258e-05, "loss": 0.0016, "step": 254600 }, { "epoch": 61.15, "learning_rate": 1.725480543362991e-05, "loss": 0.0022, "step": 254610 }, { "epoch": 61.15, "learning_rate": 1.7251414712222135e-05, "loss": 0.004, "step": 254620 }, { "epoch": 61.16, "learning_rate": 1.7248024254543237e-05, "loss": 0.0015, "step": 254630 }, { "epoch": 61.16, "learning_rate": 1.7244634060620522e-05, "loss": 0.0062, "step": 254640 }, { "epoch": 61.16, "learning_rate": 1.7241244130481293e-05, "loss": 0.0014, "step": 254650 }, { "epoch": 61.16, "learning_rate": 1.723785446415283e-05, "loss": 0.0019, "step": 254660 }, { "epoch": 61.17, "learning_rate": 1.723446506166248e-05, "loss": 0.0017, "step": 254670 }, { "epoch": 61.17, "learning_rate": 1.7231075923037488e-05, "loss": 0.0021, "step": 254680 }, { "epoch": 61.17, "learning_rate": 1.7227687048305153e-05, "loss": 0.0012, "step": 254690 }, { "epoch": 61.17, "learning_rate": 1.7224298437492793e-05, "loss": 0.0226, "step": 254700 }, { "epoch": 61.18, "learning_rate": 1.72209100906277e-05, "loss": 0.0012, "step": 254710 }, { "epoch": 61.18, "learning_rate": 1.7217522007737106e-05, "loss": 0.0023, "step": 254720 }, { "epoch": 61.18, "learning_rate": 1.721413418884836e-05, "loss": 0.0013, "step": 254730 }, { "epoch": 61.18, "learning_rate": 1.721074663398871e-05, "loss": 0.0014, "step": 254740 }, { "epoch": 61.18, "learning_rate": 1.7207359343185446e-05, "loss": 0.0017, "step": 254750 }, { "epoch": 61.19, "learning_rate": 1.7203972316465844e-05, "loss": 0.0045, "step": 254760 }, { "epoch": 61.19, "learning_rate": 1.720058555385718e-05, "loss": 0.0021, "step": 254770 }, { "epoch": 61.19, "learning_rate": 1.719719905538673e-05, "loss": 0.0088, "step": 254780 }, { "epoch": 61.19, "learning_rate": 1.7193812821081746e-05, "loss": 0.0016, "step": 254790 }, { "epoch": 61.2, "learning_rate": 1.7190426850969538e-05, "loss": 0.0018, "step": 254800 }, { "epoch": 61.2, "learning_rate": 1.7187041145077366e-05, "loss": 0.0027, "step": 254810 }, { "epoch": 61.2, "learning_rate": 1.7183655703432443e-05, "loss": 0.0016, "step": 254820 }, { "epoch": 61.2, "learning_rate": 1.7180270526062097e-05, "loss": 0.0016, "step": 254830 }, { "epoch": 61.2, "learning_rate": 1.717688561299356e-05, "loss": 0.0012, "step": 254840 }, { "epoch": 61.21, "learning_rate": 1.7173500964254092e-05, "loss": 0.0035, "step": 254850 }, { "epoch": 61.21, "learning_rate": 1.7170116579870953e-05, "loss": 0.0022, "step": 254860 }, { "epoch": 61.21, "learning_rate": 1.7166732459871403e-05, "loss": 0.0035, "step": 254870 }, { "epoch": 61.21, "learning_rate": 1.7163348604282686e-05, "loss": 0.0089, "step": 254880 }, { "epoch": 61.22, "learning_rate": 1.7159965013132056e-05, "loss": 0.0018, "step": 254890 }, { "epoch": 61.22, "learning_rate": 1.7156581686446758e-05, "loss": 0.0016, "step": 254900 }, { "epoch": 61.22, "learning_rate": 1.715319862425405e-05, "loss": 0.002, "step": 254910 }, { "epoch": 61.22, "learning_rate": 1.714981582658116e-05, "loss": 0.0021, "step": 254920 }, { "epoch": 61.23, "learning_rate": 1.7146433293455326e-05, "loss": 0.0037, "step": 254930 }, { "epoch": 61.23, "learning_rate": 1.7143051024903824e-05, "loss": 0.0119, "step": 254940 }, { "epoch": 61.23, "learning_rate": 1.7139669020953874e-05, "loss": 0.0075, "step": 254950 }, { "epoch": 61.23, "learning_rate": 1.713628728163268e-05, "loss": 0.0017, "step": 254960 }, { "epoch": 61.23, "learning_rate": 1.7132905806967513e-05, "loss": 0.0027, "step": 254970 }, { "epoch": 61.24, "learning_rate": 1.712952459698559e-05, "loss": 0.0016, "step": 254980 }, { "epoch": 61.24, "learning_rate": 1.712614365171415e-05, "loss": 0.0033, "step": 254990 }, { "epoch": 61.24, "learning_rate": 1.7122762971180412e-05, "loss": 0.0024, "step": 255000 }, { "epoch": 61.24, "learning_rate": 1.7119382555411607e-05, "loss": 0.0026, "step": 255010 }, { "epoch": 61.25, "learning_rate": 1.711600240443495e-05, "loss": 0.0056, "step": 255020 }, { "epoch": 61.25, "learning_rate": 1.7112622518277644e-05, "loss": 0.0064, "step": 255030 }, { "epoch": 61.25, "learning_rate": 1.710924289696697e-05, "loss": 0.0018, "step": 255040 }, { "epoch": 61.25, "learning_rate": 1.710586354053008e-05, "loss": 0.0021, "step": 255050 }, { "epoch": 61.26, "learning_rate": 1.7102484448994222e-05, "loss": 0.0015, "step": 255060 }, { "epoch": 61.26, "learning_rate": 1.7099105622386573e-05, "loss": 0.002, "step": 255070 }, { "epoch": 61.26, "learning_rate": 1.709572706073439e-05, "loss": 0.0027, "step": 255080 }, { "epoch": 61.26, "learning_rate": 1.7092348764064874e-05, "loss": 0.002, "step": 255090 }, { "epoch": 61.26, "learning_rate": 1.7088970732405184e-05, "loss": 0.0029, "step": 255100 }, { "epoch": 61.27, "learning_rate": 1.708559296578257e-05, "loss": 0.0035, "step": 255110 }, { "epoch": 61.27, "learning_rate": 1.7082215464224228e-05, "loss": 0.0037, "step": 255120 }, { "epoch": 61.27, "learning_rate": 1.7078838227757345e-05, "loss": 0.002, "step": 255130 }, { "epoch": 61.27, "learning_rate": 1.707546125640912e-05, "loss": 0.0024, "step": 255140 }, { "epoch": 61.28, "learning_rate": 1.7072084550206753e-05, "loss": 0.0042, "step": 255150 }, { "epoch": 61.28, "learning_rate": 1.7068708109177438e-05, "loss": 0.0014, "step": 255160 }, { "epoch": 61.28, "learning_rate": 1.7065331933348344e-05, "loss": 0.0044, "step": 255170 }, { "epoch": 61.28, "learning_rate": 1.7061956022746694e-05, "loss": 0.0034, "step": 255180 }, { "epoch": 61.28, "learning_rate": 1.705858037739968e-05, "loss": 0.0017, "step": 255190 }, { "epoch": 61.29, "learning_rate": 1.7055204997334427e-05, "loss": 0.0037, "step": 255200 }, { "epoch": 61.29, "learning_rate": 1.705182988257818e-05, "loss": 0.0031, "step": 255210 }, { "epoch": 61.29, "learning_rate": 1.704845503315809e-05, "loss": 0.0012, "step": 255220 }, { "epoch": 61.29, "learning_rate": 1.704508044910134e-05, "loss": 0.0019, "step": 255230 }, { "epoch": 61.3, "learning_rate": 1.7041706130435115e-05, "loss": 0.0018, "step": 255240 }, { "epoch": 61.3, "learning_rate": 1.7038332077186575e-05, "loss": 0.0017, "step": 255250 }, { "epoch": 61.3, "learning_rate": 1.7034958289382895e-05, "loss": 0.0015, "step": 255260 }, { "epoch": 61.3, "learning_rate": 1.7031584767051235e-05, "loss": 0.0038, "step": 255270 }, { "epoch": 61.31, "learning_rate": 1.7028211510218804e-05, "loss": 0.0024, "step": 255280 }, { "epoch": 61.31, "learning_rate": 1.7024838518912723e-05, "loss": 0.002, "step": 255290 }, { "epoch": 61.31, "learning_rate": 1.7021465793160175e-05, "loss": 0.0019, "step": 255300 }, { "epoch": 61.31, "learning_rate": 1.7018093332988296e-05, "loss": 0.002, "step": 255310 }, { "epoch": 61.31, "learning_rate": 1.7014721138424278e-05, "loss": 0.0027, "step": 255320 }, { "epoch": 61.32, "learning_rate": 1.701134920949528e-05, "loss": 0.0013, "step": 255330 }, { "epoch": 61.32, "learning_rate": 1.700797754622841e-05, "loss": 0.0012, "step": 255340 }, { "epoch": 61.32, "learning_rate": 1.700460614865087e-05, "loss": 0.0037, "step": 255350 }, { "epoch": 61.32, "learning_rate": 1.700123501678979e-05, "loss": 0.0013, "step": 255360 }, { "epoch": 61.33, "learning_rate": 1.699786415067232e-05, "loss": 0.0018, "step": 255370 }, { "epoch": 61.33, "learning_rate": 1.6994493550325612e-05, "loss": 0.0016, "step": 255380 }, { "epoch": 61.33, "learning_rate": 1.69911232157768e-05, "loss": 0.0015, "step": 255390 }, { "epoch": 61.33, "learning_rate": 1.6987753147053033e-05, "loss": 0.0012, "step": 255400 }, { "epoch": 61.34, "learning_rate": 1.6984383344181426e-05, "loss": 0.0019, "step": 255410 }, { "epoch": 61.34, "learning_rate": 1.6981013807189172e-05, "loss": 0.0018, "step": 255420 }, { "epoch": 61.34, "learning_rate": 1.6977644536103353e-05, "loss": 0.0028, "step": 255430 }, { "epoch": 61.34, "learning_rate": 1.697427553095111e-05, "loss": 0.0018, "step": 255440 }, { "epoch": 61.34, "learning_rate": 1.69709067917596e-05, "loss": 0.0017, "step": 255450 }, { "epoch": 61.35, "learning_rate": 1.6967538318555943e-05, "loss": 0.0027, "step": 255460 }, { "epoch": 61.35, "learning_rate": 1.6964170111367256e-05, "loss": 0.0016, "step": 255470 }, { "epoch": 61.35, "learning_rate": 1.6960802170220663e-05, "loss": 0.0012, "step": 255480 }, { "epoch": 61.35, "learning_rate": 1.69574344951433e-05, "loss": 0.0016, "step": 255490 }, { "epoch": 61.36, "learning_rate": 1.6954067086162272e-05, "loss": 0.0038, "step": 255500 }, { "epoch": 61.36, "learning_rate": 1.695069994330471e-05, "loss": 0.0048, "step": 255510 }, { "epoch": 61.36, "learning_rate": 1.694733306659772e-05, "loss": 0.0015, "step": 255520 }, { "epoch": 61.36, "learning_rate": 1.6943966456068424e-05, "loss": 0.0011, "step": 255530 }, { "epoch": 61.36, "learning_rate": 1.6940600111743922e-05, "loss": 0.0023, "step": 255540 }, { "epoch": 61.37, "learning_rate": 1.6937234033651322e-05, "loss": 0.0043, "step": 255550 }, { "epoch": 61.37, "learning_rate": 1.6933868221817773e-05, "loss": 0.0014, "step": 255560 }, { "epoch": 61.37, "learning_rate": 1.6930502676270328e-05, "loss": 0.0022, "step": 255570 }, { "epoch": 61.37, "learning_rate": 1.6927137397036096e-05, "loss": 0.0014, "step": 255580 }, { "epoch": 61.38, "learning_rate": 1.692377238414221e-05, "loss": 0.0014, "step": 255590 }, { "epoch": 61.38, "learning_rate": 1.6920407637615754e-05, "loss": 0.0015, "step": 255600 }, { "epoch": 61.38, "learning_rate": 1.691704315748382e-05, "loss": 0.0015, "step": 255610 }, { "epoch": 61.38, "learning_rate": 1.6913678943773502e-05, "loss": 0.0013, "step": 255620 }, { "epoch": 61.39, "learning_rate": 1.6910314996511895e-05, "loss": 0.0047, "step": 255630 }, { "epoch": 61.39, "learning_rate": 1.6906951315726095e-05, "loss": 0.0019, "step": 255640 }, { "epoch": 61.39, "learning_rate": 1.6903587901443162e-05, "loss": 0.0019, "step": 255650 }, { "epoch": 61.39, "learning_rate": 1.6900224753690242e-05, "loss": 0.0013, "step": 255660 }, { "epoch": 61.39, "learning_rate": 1.6896861872494362e-05, "loss": 0.0019, "step": 255670 }, { "epoch": 61.4, "learning_rate": 1.689349925788261e-05, "loss": 0.0021, "step": 255680 }, { "epoch": 61.4, "learning_rate": 1.68901369098821e-05, "loss": 0.0028, "step": 255690 }, { "epoch": 61.4, "learning_rate": 1.6886774828519898e-05, "loss": 0.0015, "step": 255700 }, { "epoch": 61.4, "learning_rate": 1.6883413013823056e-05, "loss": 0.0012, "step": 255710 }, { "epoch": 61.41, "learning_rate": 1.688005146581864e-05, "loss": 0.0016, "step": 255720 }, { "epoch": 61.41, "learning_rate": 1.6876690184533768e-05, "loss": 0.0039, "step": 255730 }, { "epoch": 61.41, "learning_rate": 1.6873329169995476e-05, "loss": 0.0048, "step": 255740 }, { "epoch": 61.41, "learning_rate": 1.6869968422230842e-05, "loss": 0.0017, "step": 255750 }, { "epoch": 61.42, "learning_rate": 1.6866607941266922e-05, "loss": 0.0013, "step": 255760 }, { "epoch": 61.42, "learning_rate": 1.686324772713078e-05, "loss": 0.0023, "step": 255770 }, { "epoch": 61.42, "learning_rate": 1.6859887779849488e-05, "loss": 0.0027, "step": 255780 }, { "epoch": 61.42, "learning_rate": 1.685652809945007e-05, "loss": 0.0023, "step": 255790 }, { "epoch": 61.42, "learning_rate": 1.6853168685959643e-05, "loss": 0.0013, "step": 255800 }, { "epoch": 61.43, "learning_rate": 1.6849809539405208e-05, "loss": 0.0017, "step": 255810 }, { "epoch": 61.43, "learning_rate": 1.6846450659813816e-05, "loss": 0.0019, "step": 255820 }, { "epoch": 61.43, "learning_rate": 1.6843092047212555e-05, "loss": 0.0023, "step": 255830 }, { "epoch": 61.43, "learning_rate": 1.6839733701628447e-05, "loss": 0.0102, "step": 255840 }, { "epoch": 61.44, "learning_rate": 1.6836375623088548e-05, "loss": 0.0014, "step": 255850 }, { "epoch": 61.44, "learning_rate": 1.6833017811619885e-05, "loss": 0.0013, "step": 255860 }, { "epoch": 61.44, "learning_rate": 1.6829660267249513e-05, "loss": 0.0021, "step": 255870 }, { "epoch": 61.44, "learning_rate": 1.6826302990004466e-05, "loss": 0.0011, "step": 255880 }, { "epoch": 61.44, "learning_rate": 1.682294597991178e-05, "loss": 0.0018, "step": 255890 }, { "epoch": 61.45, "learning_rate": 1.6819589236998495e-05, "loss": 0.007, "step": 255900 }, { "epoch": 61.45, "learning_rate": 1.6816232761291635e-05, "loss": 0.0013, "step": 255910 }, { "epoch": 61.45, "learning_rate": 1.6812876552818236e-05, "loss": 0.0015, "step": 255920 }, { "epoch": 61.45, "learning_rate": 1.68095206116053e-05, "loss": 0.0044, "step": 255930 }, { "epoch": 61.46, "learning_rate": 1.680616493767992e-05, "loss": 0.0026, "step": 255940 }, { "epoch": 61.46, "learning_rate": 1.6802809531069054e-05, "loss": 0.0013, "step": 255950 }, { "epoch": 61.46, "learning_rate": 1.679945439179973e-05, "loss": 0.0022, "step": 255960 }, { "epoch": 61.46, "learning_rate": 1.6796099519899e-05, "loss": 0.0015, "step": 255970 }, { "epoch": 61.47, "learning_rate": 1.6792744915393866e-05, "loss": 0.002, "step": 255980 }, { "epoch": 61.47, "learning_rate": 1.6789390578311343e-05, "loss": 0.0022, "step": 255990 }, { "epoch": 61.47, "learning_rate": 1.6786036508678437e-05, "loss": 0.0023, "step": 256000 }, { "epoch": 61.47, "learning_rate": 1.6782682706522174e-05, "loss": 0.0019, "step": 256010 }, { "epoch": 61.47, "learning_rate": 1.6779329171869544e-05, "loss": 0.002, "step": 256020 }, { "epoch": 61.48, "learning_rate": 1.6775975904747565e-05, "loss": 0.0014, "step": 256030 }, { "epoch": 61.48, "learning_rate": 1.6772622905183243e-05, "loss": 0.0015, "step": 256040 }, { "epoch": 61.48, "learning_rate": 1.676927017320357e-05, "loss": 0.0015, "step": 256050 }, { "epoch": 61.48, "learning_rate": 1.676591770883554e-05, "loss": 0.0064, "step": 256060 }, { "epoch": 61.49, "learning_rate": 1.6762565512106178e-05, "loss": 0.0039, "step": 256070 }, { "epoch": 61.49, "learning_rate": 1.6759213583042484e-05, "loss": 0.0054, "step": 256080 }, { "epoch": 61.49, "learning_rate": 1.6755861921671397e-05, "loss": 0.0028, "step": 256090 }, { "epoch": 61.49, "learning_rate": 1.6752510528019953e-05, "loss": 0.0023, "step": 256100 }, { "epoch": 61.5, "learning_rate": 1.674915940211514e-05, "loss": 0.0079, "step": 256110 }, { "epoch": 61.5, "learning_rate": 1.674580854398394e-05, "loss": 0.0018, "step": 256120 }, { "epoch": 61.5, "learning_rate": 1.6742457953653325e-05, "loss": 0.003, "step": 256130 }, { "epoch": 61.5, "learning_rate": 1.6739107631150293e-05, "loss": 0.0015, "step": 256140 }, { "epoch": 61.5, "learning_rate": 1.673575757650182e-05, "loss": 0.0015, "step": 256150 }, { "epoch": 61.51, "learning_rate": 1.6732407789734884e-05, "loss": 0.0016, "step": 256160 }, { "epoch": 61.51, "learning_rate": 1.672905827087644e-05, "loss": 0.0032, "step": 256170 }, { "epoch": 61.51, "learning_rate": 1.6725709019953517e-05, "loss": 0.0014, "step": 256180 }, { "epoch": 61.51, "learning_rate": 1.672236003699304e-05, "loss": 0.0023, "step": 256190 }, { "epoch": 61.52, "learning_rate": 1.6719011322021978e-05, "loss": 0.0019, "step": 256200 }, { "epoch": 61.52, "learning_rate": 1.671566287506732e-05, "loss": 0.0037, "step": 256210 }, { "epoch": 61.52, "learning_rate": 1.6712314696156045e-05, "loss": 0.0032, "step": 256220 }, { "epoch": 61.52, "learning_rate": 1.6708966785315066e-05, "loss": 0.0015, "step": 256230 }, { "epoch": 61.52, "learning_rate": 1.670561914257139e-05, "loss": 0.0022, "step": 256240 }, { "epoch": 61.53, "learning_rate": 1.6702271767951954e-05, "loss": 0.0013, "step": 256250 }, { "epoch": 61.53, "learning_rate": 1.6698924661483722e-05, "loss": 0.0014, "step": 256260 }, { "epoch": 61.53, "learning_rate": 1.669557782319365e-05, "loss": 0.0028, "step": 256270 }, { "epoch": 61.53, "learning_rate": 1.6692231253108682e-05, "loss": 0.0029, "step": 256280 }, { "epoch": 61.54, "learning_rate": 1.668888495125578e-05, "loss": 0.0065, "step": 256290 }, { "epoch": 61.54, "learning_rate": 1.668553891766187e-05, "loss": 0.0017, "step": 256300 }, { "epoch": 61.54, "learning_rate": 1.6682193152353924e-05, "loss": 0.0077, "step": 256310 }, { "epoch": 61.54, "learning_rate": 1.6678847655358897e-05, "loss": 0.0018, "step": 256320 }, { "epoch": 61.55, "learning_rate": 1.667550242670368e-05, "loss": 0.0037, "step": 256330 }, { "epoch": 61.55, "learning_rate": 1.6672157466415255e-05, "loss": 0.0021, "step": 256340 }, { "epoch": 61.55, "learning_rate": 1.6668812774520552e-05, "loss": 0.0015, "step": 256350 }, { "epoch": 61.55, "learning_rate": 1.6665468351046514e-05, "loss": 0.0027, "step": 256360 }, { "epoch": 61.55, "learning_rate": 1.666212419602003e-05, "loss": 0.0039, "step": 256370 }, { "epoch": 61.56, "learning_rate": 1.665878030946808e-05, "loss": 0.0019, "step": 256380 }, { "epoch": 61.56, "learning_rate": 1.6655436691417574e-05, "loss": 0.0073, "step": 256390 }, { "epoch": 61.56, "learning_rate": 1.6652093341895437e-05, "loss": 0.0016, "step": 256400 }, { "epoch": 61.56, "learning_rate": 1.6648750260928603e-05, "loss": 0.0017, "step": 256410 }, { "epoch": 61.57, "learning_rate": 1.664540744854398e-05, "loss": 0.0064, "step": 256420 }, { "epoch": 61.57, "learning_rate": 1.66420649047685e-05, "loss": 0.0054, "step": 256430 }, { "epoch": 61.57, "learning_rate": 1.663872262962906e-05, "loss": 0.0015, "step": 256440 }, { "epoch": 61.57, "learning_rate": 1.6635380623152607e-05, "loss": 0.0018, "step": 256450 }, { "epoch": 61.58, "learning_rate": 1.6632038885366057e-05, "loss": 0.0027, "step": 256460 }, { "epoch": 61.58, "learning_rate": 1.6628697416296274e-05, "loss": 0.0024, "step": 256470 }, { "epoch": 61.58, "learning_rate": 1.662535621597021e-05, "loss": 0.0024, "step": 256480 }, { "epoch": 61.58, "learning_rate": 1.6622015284414767e-05, "loss": 0.0016, "step": 256490 }, { "epoch": 61.58, "learning_rate": 1.661867462165684e-05, "loss": 0.0033, "step": 256500 }, { "epoch": 61.59, "learning_rate": 1.6615334227723334e-05, "loss": 0.0119, "step": 256510 }, { "epoch": 61.59, "learning_rate": 1.661199410264115e-05, "loss": 0.0055, "step": 256520 }, { "epoch": 61.59, "learning_rate": 1.6608654246437182e-05, "loss": 0.0053, "step": 256530 }, { "epoch": 61.59, "learning_rate": 1.6605314659138322e-05, "loss": 0.0103, "step": 256540 }, { "epoch": 61.6, "learning_rate": 1.660197534077151e-05, "loss": 0.0015, "step": 256550 }, { "epoch": 61.6, "learning_rate": 1.659863629136357e-05, "loss": 0.0025, "step": 256560 }, { "epoch": 61.6, "learning_rate": 1.6595297510941436e-05, "loss": 0.0021, "step": 256570 }, { "epoch": 61.6, "learning_rate": 1.6591958999531964e-05, "loss": 0.003, "step": 256580 }, { "epoch": 61.6, "learning_rate": 1.6588620757162078e-05, "loss": 0.0069, "step": 256590 }, { "epoch": 61.61, "learning_rate": 1.658528278385865e-05, "loss": 0.0029, "step": 256600 }, { "epoch": 61.61, "learning_rate": 1.6581945079648525e-05, "loss": 0.0049, "step": 256610 }, { "epoch": 61.61, "learning_rate": 1.6578607644558625e-05, "loss": 0.0022, "step": 256620 }, { "epoch": 61.61, "learning_rate": 1.6575270478615816e-05, "loss": 0.0043, "step": 256630 }, { "epoch": 61.62, "learning_rate": 1.6571933581846965e-05, "loss": 0.0026, "step": 256640 }, { "epoch": 61.62, "learning_rate": 1.6568596954278948e-05, "loss": 0.0022, "step": 256650 }, { "epoch": 61.62, "learning_rate": 1.6565260595938635e-05, "loss": 0.0034, "step": 256660 }, { "epoch": 61.62, "learning_rate": 1.6561924506852895e-05, "loss": 0.0017, "step": 256670 }, { "epoch": 61.63, "learning_rate": 1.6558588687048578e-05, "loss": 0.0025, "step": 256680 }, { "epoch": 61.63, "learning_rate": 1.655525313655259e-05, "loss": 0.0019, "step": 256690 }, { "epoch": 61.63, "learning_rate": 1.6551917855391756e-05, "loss": 0.0019, "step": 256700 }, { "epoch": 61.63, "learning_rate": 1.6548582843592923e-05, "loss": 0.0028, "step": 256710 }, { "epoch": 61.63, "learning_rate": 1.654524810118299e-05, "loss": 0.0014, "step": 256720 }, { "epoch": 61.64, "learning_rate": 1.65419136281888e-05, "loss": 0.0018, "step": 256730 }, { "epoch": 61.64, "learning_rate": 1.653857942463719e-05, "loss": 0.0019, "step": 256740 }, { "epoch": 61.64, "learning_rate": 1.6535245490555025e-05, "loss": 0.0014, "step": 256750 }, { "epoch": 61.64, "learning_rate": 1.6531911825969142e-05, "loss": 0.0024, "step": 256760 }, { "epoch": 61.65, "learning_rate": 1.6528578430906395e-05, "loss": 0.0016, "step": 256770 }, { "epoch": 61.65, "learning_rate": 1.652524530539361e-05, "loss": 0.0023, "step": 256780 }, { "epoch": 61.65, "learning_rate": 1.6521912449457682e-05, "loss": 0.0015, "step": 256790 }, { "epoch": 61.65, "learning_rate": 1.6518579863125398e-05, "loss": 0.0016, "step": 256800 }, { "epoch": 61.66, "learning_rate": 1.6515247546423613e-05, "loss": 0.0019, "step": 256810 }, { "epoch": 61.66, "learning_rate": 1.6511915499379144e-05, "loss": 0.0024, "step": 256820 }, { "epoch": 61.66, "learning_rate": 1.650858372201886e-05, "loss": 0.0029, "step": 256830 }, { "epoch": 61.66, "learning_rate": 1.6505252214369593e-05, "loss": 0.0036, "step": 256840 }, { "epoch": 61.66, "learning_rate": 1.6501920976458118e-05, "loss": 0.0016, "step": 256850 }, { "epoch": 61.67, "learning_rate": 1.6498590008311322e-05, "loss": 0.0045, "step": 256860 }, { "epoch": 61.67, "learning_rate": 1.6495259309955995e-05, "loss": 0.0016, "step": 256870 }, { "epoch": 61.67, "learning_rate": 1.649192888141898e-05, "loss": 0.0055, "step": 256880 }, { "epoch": 61.67, "learning_rate": 1.6488598722727082e-05, "loss": 0.0013, "step": 256890 }, { "epoch": 61.68, "learning_rate": 1.6485268833907123e-05, "loss": 0.004, "step": 256900 }, { "epoch": 61.68, "learning_rate": 1.648193921498593e-05, "loss": 0.0041, "step": 256910 }, { "epoch": 61.68, "learning_rate": 1.6478609865990286e-05, "loss": 0.0029, "step": 256920 }, { "epoch": 61.68, "learning_rate": 1.6475280786947056e-05, "loss": 0.0016, "step": 256930 }, { "epoch": 61.68, "learning_rate": 1.6471951977883004e-05, "loss": 0.0028, "step": 256940 }, { "epoch": 61.69, "learning_rate": 1.6468623438824937e-05, "loss": 0.0018, "step": 256950 }, { "epoch": 61.69, "learning_rate": 1.6465295169799687e-05, "loss": 0.005, "step": 256960 }, { "epoch": 61.69, "learning_rate": 1.6461967170834046e-05, "loss": 0.0017, "step": 256970 }, { "epoch": 61.69, "learning_rate": 1.645863944195483e-05, "loss": 0.0052, "step": 256980 }, { "epoch": 61.7, "learning_rate": 1.6455311983188792e-05, "loss": 0.0033, "step": 256990 }, { "epoch": 61.7, "learning_rate": 1.645198479456277e-05, "loss": 0.0017, "step": 257000 }, { "epoch": 61.7, "learning_rate": 1.6448657876103545e-05, "loss": 0.0023, "step": 257010 }, { "epoch": 61.7, "learning_rate": 1.6445331227837912e-05, "loss": 0.0014, "step": 257020 }, { "epoch": 61.71, "learning_rate": 1.6442004849792662e-05, "loss": 0.0012, "step": 257030 }, { "epoch": 61.71, "learning_rate": 1.643867874199458e-05, "loss": 0.0013, "step": 257040 }, { "epoch": 61.71, "learning_rate": 1.643535290447045e-05, "loss": 0.0037, "step": 257050 }, { "epoch": 61.71, "learning_rate": 1.6432027337247037e-05, "loss": 0.0017, "step": 257060 }, { "epoch": 61.71, "learning_rate": 1.642870204035118e-05, "loss": 0.0022, "step": 257070 }, { "epoch": 61.72, "learning_rate": 1.6425377013809602e-05, "loss": 0.0017, "step": 257080 }, { "epoch": 61.72, "learning_rate": 1.6422052257649078e-05, "loss": 0.0015, "step": 257090 }, { "epoch": 61.72, "learning_rate": 1.6418727771896425e-05, "loss": 0.0015, "step": 257100 }, { "epoch": 61.72, "learning_rate": 1.641540355657839e-05, "loss": 0.0049, "step": 257110 }, { "epoch": 61.73, "learning_rate": 1.6412079611721747e-05, "loss": 0.0027, "step": 257120 }, { "epoch": 61.73, "learning_rate": 1.6408755937353264e-05, "loss": 0.0089, "step": 257130 }, { "epoch": 61.73, "learning_rate": 1.640543253349971e-05, "loss": 0.0018, "step": 257140 }, { "epoch": 61.73, "learning_rate": 1.6402109400187843e-05, "loss": 0.0041, "step": 257150 }, { "epoch": 61.74, "learning_rate": 1.6398786537444412e-05, "loss": 0.0017, "step": 257160 }, { "epoch": 61.74, "learning_rate": 1.6395463945296224e-05, "loss": 0.0013, "step": 257170 }, { "epoch": 61.74, "learning_rate": 1.6392141623769984e-05, "loss": 0.0023, "step": 257180 }, { "epoch": 61.74, "learning_rate": 1.6388819572892455e-05, "loss": 0.0034, "step": 257190 }, { "epoch": 61.74, "learning_rate": 1.6385497792690423e-05, "loss": 0.0012, "step": 257200 }, { "epoch": 61.75, "learning_rate": 1.638217628319063e-05, "loss": 0.002, "step": 257210 }, { "epoch": 61.75, "learning_rate": 1.6378855044419794e-05, "loss": 0.0019, "step": 257220 }, { "epoch": 61.75, "learning_rate": 1.6375534076404668e-05, "loss": 0.0013, "step": 257230 }, { "epoch": 61.75, "learning_rate": 1.6372213379172023e-05, "loss": 0.0016, "step": 257240 }, { "epoch": 61.76, "learning_rate": 1.636889295274858e-05, "loss": 0.0016, "step": 257250 }, { "epoch": 61.76, "learning_rate": 1.6365572797161095e-05, "loss": 0.0019, "step": 257260 }, { "epoch": 61.76, "learning_rate": 1.6362252912436294e-05, "loss": 0.0011, "step": 257270 }, { "epoch": 61.76, "learning_rate": 1.635893329860091e-05, "loss": 0.0024, "step": 257280 }, { "epoch": 61.76, "learning_rate": 1.6355613955681686e-05, "loss": 0.0043, "step": 257290 }, { "epoch": 61.77, "learning_rate": 1.6352294883705326e-05, "loss": 0.0034, "step": 257300 }, { "epoch": 61.77, "learning_rate": 1.6348976082698615e-05, "loss": 0.0017, "step": 257310 }, { "epoch": 61.77, "learning_rate": 1.6345657552688233e-05, "loss": 0.0041, "step": 257320 }, { "epoch": 61.77, "learning_rate": 1.6342339293700893e-05, "loss": 0.0042, "step": 257330 }, { "epoch": 61.78, "learning_rate": 1.6339021305763364e-05, "loss": 0.0023, "step": 257340 }, { "epoch": 61.78, "learning_rate": 1.6335703588902355e-05, "loss": 0.0018, "step": 257350 }, { "epoch": 61.78, "learning_rate": 1.6332386143144544e-05, "loss": 0.0025, "step": 257360 }, { "epoch": 61.78, "learning_rate": 1.632906896851669e-05, "loss": 0.0026, "step": 257370 }, { "epoch": 61.79, "learning_rate": 1.6325752065045497e-05, "loss": 0.0018, "step": 257380 }, { "epoch": 61.79, "learning_rate": 1.6322435432757665e-05, "loss": 0.0015, "step": 257390 }, { "epoch": 61.79, "learning_rate": 1.6319119071679912e-05, "loss": 0.0016, "step": 257400 }, { "epoch": 61.79, "learning_rate": 1.6315802981838945e-05, "loss": 0.0014, "step": 257410 }, { "epoch": 61.79, "learning_rate": 1.6312487163261465e-05, "loss": 0.0016, "step": 257420 }, { "epoch": 61.8, "learning_rate": 1.6309171615974177e-05, "loss": 0.0027, "step": 257430 }, { "epoch": 61.8, "learning_rate": 1.6305856340003767e-05, "loss": 0.0017, "step": 257440 }, { "epoch": 61.8, "learning_rate": 1.6302541335376974e-05, "loss": 0.0012, "step": 257450 }, { "epoch": 61.8, "learning_rate": 1.629922660212046e-05, "loss": 0.0036, "step": 257460 }, { "epoch": 61.81, "learning_rate": 1.6295912140260904e-05, "loss": 0.0022, "step": 257470 }, { "epoch": 61.81, "learning_rate": 1.629259794982504e-05, "loss": 0.0014, "step": 257480 }, { "epoch": 61.81, "learning_rate": 1.628928403083954e-05, "loss": 0.0014, "step": 257490 }, { "epoch": 61.81, "learning_rate": 1.6285970383331083e-05, "loss": 0.0016, "step": 257500 }, { "epoch": 61.82, "learning_rate": 1.628265700732637e-05, "loss": 0.0074, "step": 257510 }, { "epoch": 61.82, "learning_rate": 1.627934390285207e-05, "loss": 0.0014, "step": 257520 }, { "epoch": 61.82, "learning_rate": 1.627603106993487e-05, "loss": 0.0014, "step": 257530 }, { "epoch": 61.82, "learning_rate": 1.627271850860145e-05, "loss": 0.0013, "step": 257540 }, { "epoch": 61.82, "learning_rate": 1.626940621887848e-05, "loss": 0.0015, "step": 257550 }, { "epoch": 61.83, "learning_rate": 1.6266094200792637e-05, "loss": 0.0077, "step": 257560 }, { "epoch": 61.83, "learning_rate": 1.6262782454370584e-05, "loss": 0.0023, "step": 257570 }, { "epoch": 61.83, "learning_rate": 1.625947097963901e-05, "loss": 0.0014, "step": 257580 }, { "epoch": 61.83, "learning_rate": 1.62561597766246e-05, "loss": 0.0018, "step": 257590 }, { "epoch": 61.84, "learning_rate": 1.6252848845353958e-05, "loss": 0.0012, "step": 257600 }, { "epoch": 61.84, "learning_rate": 1.6249538185853796e-05, "loss": 0.0015, "step": 257610 }, { "epoch": 61.84, "learning_rate": 1.6246227798150765e-05, "loss": 0.004, "step": 257620 }, { "epoch": 61.84, "learning_rate": 1.6242917682271524e-05, "loss": 0.0039, "step": 257630 }, { "epoch": 61.84, "learning_rate": 1.6239607838242726e-05, "loss": 0.0072, "step": 257640 }, { "epoch": 61.85, "learning_rate": 1.6236298266091027e-05, "loss": 0.005, "step": 257650 }, { "epoch": 61.85, "learning_rate": 1.6232988965843076e-05, "loss": 0.0018, "step": 257660 }, { "epoch": 61.85, "learning_rate": 1.6229679937525533e-05, "loss": 0.0013, "step": 257670 }, { "epoch": 61.85, "learning_rate": 1.6226371181165035e-05, "loss": 0.0014, "step": 257680 }, { "epoch": 61.86, "learning_rate": 1.6223062696788232e-05, "loss": 0.0017, "step": 257690 }, { "epoch": 61.86, "learning_rate": 1.6219754484421772e-05, "loss": 0.0014, "step": 257700 }, { "epoch": 61.86, "learning_rate": 1.6216446544092273e-05, "loss": 0.003, "step": 257710 }, { "epoch": 61.86, "learning_rate": 1.6213138875826412e-05, "loss": 0.0023, "step": 257720 }, { "epoch": 61.87, "learning_rate": 1.6209831479650828e-05, "loss": 0.0014, "step": 257730 }, { "epoch": 61.87, "learning_rate": 1.6206524355592096e-05, "loss": 0.0021, "step": 257740 }, { "epoch": 61.87, "learning_rate": 1.620321750367691e-05, "loss": 0.0024, "step": 257750 }, { "epoch": 61.87, "learning_rate": 1.6199910923931878e-05, "loss": 0.0026, "step": 257760 }, { "epoch": 61.87, "learning_rate": 1.619660461638363e-05, "loss": 0.0016, "step": 257770 }, { "epoch": 61.88, "learning_rate": 1.6193298581058795e-05, "loss": 0.0087, "step": 257780 }, { "epoch": 61.88, "learning_rate": 1.618999281798399e-05, "loss": 0.0016, "step": 257790 }, { "epoch": 61.88, "learning_rate": 1.618668732718584e-05, "loss": 0.0016, "step": 257800 }, { "epoch": 61.88, "learning_rate": 1.6183382108690952e-05, "loss": 0.0044, "step": 257810 }, { "epoch": 61.89, "learning_rate": 1.618007716252597e-05, "loss": 0.0014, "step": 257820 }, { "epoch": 61.89, "learning_rate": 1.6176772488717513e-05, "loss": 0.0041, "step": 257830 }, { "epoch": 61.89, "learning_rate": 1.6173468087292166e-05, "loss": 0.0027, "step": 257840 }, { "epoch": 61.89, "learning_rate": 1.6170163958276524e-05, "loss": 0.003, "step": 257850 }, { "epoch": 61.9, "learning_rate": 1.6166860101697246e-05, "loss": 0.0013, "step": 257860 }, { "epoch": 61.9, "learning_rate": 1.616355651758093e-05, "loss": 0.0045, "step": 257870 }, { "epoch": 61.9, "learning_rate": 1.616025320595413e-05, "loss": 0.0035, "step": 257880 }, { "epoch": 61.9, "learning_rate": 1.61569501668435e-05, "loss": 0.0044, "step": 257890 }, { "epoch": 61.9, "learning_rate": 1.6153647400275617e-05, "loss": 0.003, "step": 257900 }, { "epoch": 61.91, "learning_rate": 1.6150344906277092e-05, "loss": 0.0013, "step": 257910 }, { "epoch": 61.91, "learning_rate": 1.6147042684874508e-05, "loss": 0.0017, "step": 257920 }, { "epoch": 61.91, "learning_rate": 1.6143740736094466e-05, "loss": 0.0013, "step": 257930 }, { "epoch": 61.91, "learning_rate": 1.614043905996355e-05, "loss": 0.0016, "step": 257940 }, { "epoch": 61.92, "learning_rate": 1.6137137656508345e-05, "loss": 0.0021, "step": 257950 }, { "epoch": 61.92, "learning_rate": 1.6133836525755458e-05, "loss": 0.003, "step": 257960 }, { "epoch": 61.92, "learning_rate": 1.613053566773147e-05, "loss": 0.0017, "step": 257970 }, { "epoch": 61.92, "learning_rate": 1.6127235082462933e-05, "loss": 0.0013, "step": 257980 }, { "epoch": 61.92, "learning_rate": 1.6123934769976455e-05, "loss": 0.0013, "step": 257990 }, { "epoch": 61.93, "learning_rate": 1.6120634730298613e-05, "loss": 0.0017, "step": 258000 }, { "epoch": 61.93, "learning_rate": 1.6117334963455978e-05, "loss": 0.0041, "step": 258010 }, { "epoch": 61.93, "learning_rate": 1.611403546947512e-05, "loss": 0.0017, "step": 258020 }, { "epoch": 61.93, "learning_rate": 1.6110736248382606e-05, "loss": 0.0045, "step": 258030 }, { "epoch": 61.94, "learning_rate": 1.610743730020502e-05, "loss": 0.0027, "step": 258040 }, { "epoch": 61.94, "learning_rate": 1.6104138624968902e-05, "loss": 0.0026, "step": 258050 }, { "epoch": 61.94, "learning_rate": 1.610084022270087e-05, "loss": 0.0023, "step": 258060 }, { "epoch": 61.94, "learning_rate": 1.609754209342743e-05, "loss": 0.0014, "step": 258070 }, { "epoch": 61.95, "learning_rate": 1.609424423717517e-05, "loss": 0.0033, "step": 258080 }, { "epoch": 61.95, "learning_rate": 1.6090946653970623e-05, "loss": 0.0021, "step": 258090 }, { "epoch": 61.95, "learning_rate": 1.6087649343840376e-05, "loss": 0.0023, "step": 258100 }, { "epoch": 62.0, "learning_rate": 1.6084352306810997e-05, "loss": 0.0016, "step": 258110 }, { "epoch": 62.0, "learning_rate": 1.6081055542908974e-05, "loss": 0.0014, "step": 258120 }, { "epoch": 62.01, "learning_rate": 1.6077759052160907e-05, "loss": 0.0033, "step": 258130 }, { "epoch": 62.01, "learning_rate": 1.607446283459333e-05, "loss": 0.0023, "step": 258140 }, { "epoch": 62.01, "learning_rate": 1.6071166890232793e-05, "loss": 0.005, "step": 258150 }, { "epoch": 62.01, "learning_rate": 1.6067871219105824e-05, "loss": 0.0196, "step": 258160 }, { "epoch": 62.01, "learning_rate": 1.606457582123898e-05, "loss": 0.0019, "step": 258170 }, { "epoch": 62.02, "learning_rate": 1.6061280696658792e-05, "loss": 0.0085, "step": 258180 }, { "epoch": 62.02, "learning_rate": 1.6057985845391777e-05, "loss": 0.0019, "step": 258190 }, { "epoch": 62.02, "learning_rate": 1.6054691267464523e-05, "loss": 0.0063, "step": 258200 }, { "epoch": 62.02, "learning_rate": 1.6051396962903503e-05, "loss": 0.0029, "step": 258210 }, { "epoch": 62.03, "learning_rate": 1.6048102931735265e-05, "loss": 0.0018, "step": 258220 }, { "epoch": 62.03, "learning_rate": 1.6044809173986348e-05, "loss": 0.0019, "step": 258230 }, { "epoch": 62.03, "learning_rate": 1.604151568968328e-05, "loss": 0.0027, "step": 258240 }, { "epoch": 62.03, "learning_rate": 1.6038222478852565e-05, "loss": 0.0021, "step": 258250 }, { "epoch": 62.04, "learning_rate": 1.6034929541520737e-05, "loss": 0.0034, "step": 258260 }, { "epoch": 62.04, "learning_rate": 1.6031636877714313e-05, "loss": 0.0014, "step": 258270 }, { "epoch": 62.04, "learning_rate": 1.60283444874598e-05, "loss": 0.0026, "step": 258280 }, { "epoch": 62.04, "learning_rate": 1.6025052370783728e-05, "loss": 0.0035, "step": 258290 }, { "epoch": 62.04, "learning_rate": 1.6021760527712592e-05, "loss": 0.0018, "step": 258300 }, { "epoch": 62.05, "learning_rate": 1.6018468958272915e-05, "loss": 0.0014, "step": 258310 }, { "epoch": 62.05, "learning_rate": 1.60151776624912e-05, "loss": 0.0014, "step": 258320 }, { "epoch": 62.05, "learning_rate": 1.601188664039393e-05, "loss": 0.0032, "step": 258330 }, { "epoch": 62.05, "learning_rate": 1.600859589200766e-05, "loss": 0.0027, "step": 258340 }, { "epoch": 62.06, "learning_rate": 1.600530541735885e-05, "loss": 0.0014, "step": 258350 }, { "epoch": 62.06, "learning_rate": 1.6002015216473992e-05, "loss": 0.0014, "step": 258360 }, { "epoch": 62.06, "learning_rate": 1.5998725289379613e-05, "loss": 0.0055, "step": 258370 }, { "epoch": 62.06, "learning_rate": 1.5995435636102192e-05, "loss": 0.0018, "step": 258380 }, { "epoch": 62.06, "learning_rate": 1.5992146256668223e-05, "loss": 0.0015, "step": 258390 }, { "epoch": 62.07, "learning_rate": 1.5988857151104197e-05, "loss": 0.0015, "step": 258400 }, { "epoch": 62.07, "learning_rate": 1.59855683194366e-05, "loss": 0.0074, "step": 258410 }, { "epoch": 62.07, "learning_rate": 1.5982279761691915e-05, "loss": 0.017, "step": 258420 }, { "epoch": 62.07, "learning_rate": 1.5978991477896615e-05, "loss": 0.0029, "step": 258430 }, { "epoch": 62.08, "learning_rate": 1.5975703468077225e-05, "loss": 0.0015, "step": 258440 }, { "epoch": 62.08, "learning_rate": 1.597241573226017e-05, "loss": 0.0024, "step": 258450 }, { "epoch": 62.08, "learning_rate": 1.5969128270471938e-05, "loss": 0.0018, "step": 258460 }, { "epoch": 62.08, "learning_rate": 1.596584108273903e-05, "loss": 0.0019, "step": 258470 }, { "epoch": 62.09, "learning_rate": 1.5962554169087908e-05, "loss": 0.0034, "step": 258480 }, { "epoch": 62.09, "learning_rate": 1.595926752954504e-05, "loss": 0.0067, "step": 258490 }, { "epoch": 62.09, "learning_rate": 1.5955981164136868e-05, "loss": 0.0039, "step": 258500 }, { "epoch": 62.09, "learning_rate": 1.5952695072889896e-05, "loss": 0.013, "step": 258510 }, { "epoch": 62.09, "learning_rate": 1.5949409255830565e-05, "loss": 0.0026, "step": 258520 }, { "epoch": 62.1, "learning_rate": 1.5946123712985344e-05, "loss": 0.0126, "step": 258530 }, { "epoch": 62.1, "learning_rate": 1.594283844438069e-05, "loss": 0.0022, "step": 258540 }, { "epoch": 62.1, "learning_rate": 1.5939553450043066e-05, "loss": 0.006, "step": 258550 }, { "epoch": 62.1, "learning_rate": 1.5936268729998914e-05, "loss": 0.0021, "step": 258560 }, { "epoch": 62.11, "learning_rate": 1.5932984284274677e-05, "loss": 0.0017, "step": 258570 }, { "epoch": 62.11, "learning_rate": 1.5929700112896855e-05, "loss": 0.002, "step": 258580 }, { "epoch": 62.11, "learning_rate": 1.592641621589185e-05, "loss": 0.0014, "step": 258590 }, { "epoch": 62.11, "learning_rate": 1.5923132593286096e-05, "loss": 0.0015, "step": 258600 }, { "epoch": 62.12, "learning_rate": 1.5919849245106077e-05, "loss": 0.002, "step": 258610 }, { "epoch": 62.12, "learning_rate": 1.5916566171378218e-05, "loss": 0.0017, "step": 258620 }, { "epoch": 62.12, "learning_rate": 1.5913283372128956e-05, "loss": 0.0014, "step": 258630 }, { "epoch": 62.12, "learning_rate": 1.5910000847384732e-05, "loss": 0.0022, "step": 258640 }, { "epoch": 62.12, "learning_rate": 1.5906718597171977e-05, "loss": 0.0015, "step": 258650 }, { "epoch": 62.13, "learning_rate": 1.590343662151712e-05, "loss": 0.0019, "step": 258660 }, { "epoch": 62.13, "learning_rate": 1.59001549204466e-05, "loss": 0.0014, "step": 258670 }, { "epoch": 62.13, "learning_rate": 1.5896873493986836e-05, "loss": 0.0022, "step": 258680 }, { "epoch": 62.13, "learning_rate": 1.589359234216426e-05, "loss": 0.002, "step": 258690 }, { "epoch": 62.14, "learning_rate": 1.5890311465005282e-05, "loss": 0.0015, "step": 258700 }, { "epoch": 62.14, "learning_rate": 1.5887030862536345e-05, "loss": 0.0017, "step": 258710 }, { "epoch": 62.14, "learning_rate": 1.5883750534783875e-05, "loss": 0.0014, "step": 258720 }, { "epoch": 62.14, "learning_rate": 1.5880470481774257e-05, "loss": 0.0031, "step": 258730 }, { "epoch": 62.14, "learning_rate": 1.5877190703533908e-05, "loss": 0.0014, "step": 258740 }, { "epoch": 62.15, "learning_rate": 1.5873911200089264e-05, "loss": 0.0014, "step": 258750 }, { "epoch": 62.15, "learning_rate": 1.5870631971466727e-05, "loss": 0.0045, "step": 258760 }, { "epoch": 62.15, "learning_rate": 1.58673530176927e-05, "loss": 0.0046, "step": 258770 }, { "epoch": 62.15, "learning_rate": 1.5864074338793594e-05, "loss": 0.0013, "step": 258780 }, { "epoch": 62.16, "learning_rate": 1.586079593479581e-05, "loss": 0.0022, "step": 258790 }, { "epoch": 62.16, "learning_rate": 1.5857517805725747e-05, "loss": 0.0027, "step": 258800 }, { "epoch": 62.16, "learning_rate": 1.5854239951609795e-05, "loss": 0.0015, "step": 258810 }, { "epoch": 62.16, "learning_rate": 1.5850962372474394e-05, "loss": 0.0018, "step": 258820 }, { "epoch": 62.17, "learning_rate": 1.5847685068345885e-05, "loss": 0.0019, "step": 258830 }, { "epoch": 62.17, "learning_rate": 1.5844408039250676e-05, "loss": 0.0036, "step": 258840 }, { "epoch": 62.17, "learning_rate": 1.5841131285215178e-05, "loss": 0.0039, "step": 258850 }, { "epoch": 62.17, "learning_rate": 1.5837854806265777e-05, "loss": 0.0016, "step": 258860 }, { "epoch": 62.17, "learning_rate": 1.5834578602428818e-05, "loss": 0.0021, "step": 258870 }, { "epoch": 62.18, "learning_rate": 1.583130267373073e-05, "loss": 0.0021, "step": 258880 }, { "epoch": 62.18, "learning_rate": 1.5828027020197882e-05, "loss": 0.0015, "step": 258890 }, { "epoch": 62.18, "learning_rate": 1.582475164185665e-05, "loss": 0.0043, "step": 258900 }, { "epoch": 62.18, "learning_rate": 1.582147653873341e-05, "loss": 0.0022, "step": 258910 }, { "epoch": 62.19, "learning_rate": 1.5818201710854535e-05, "loss": 0.0022, "step": 258920 }, { "epoch": 62.19, "learning_rate": 1.5814927158246406e-05, "loss": 0.0042, "step": 258930 }, { "epoch": 62.19, "learning_rate": 1.5811652880935385e-05, "loss": 0.0017, "step": 258940 }, { "epoch": 62.19, "learning_rate": 1.5808378878947826e-05, "loss": 0.0011, "step": 258950 }, { "epoch": 62.2, "learning_rate": 1.5805105152310147e-05, "loss": 0.0031, "step": 258960 }, { "epoch": 62.2, "learning_rate": 1.580183170104866e-05, "loss": 0.0034, "step": 258970 }, { "epoch": 62.2, "learning_rate": 1.5798558525189728e-05, "loss": 0.0022, "step": 258980 }, { "epoch": 62.2, "learning_rate": 1.579528562475974e-05, "loss": 0.0014, "step": 258990 }, { "epoch": 62.2, "learning_rate": 1.579201299978506e-05, "loss": 0.0015, "step": 259000 }, { "epoch": 62.21, "learning_rate": 1.5788740650291987e-05, "loss": 0.0025, "step": 259010 }, { "epoch": 62.21, "learning_rate": 1.5785468576306922e-05, "loss": 0.0013, "step": 259020 }, { "epoch": 62.21, "learning_rate": 1.5782196777856205e-05, "loss": 0.0018, "step": 259030 }, { "epoch": 62.21, "learning_rate": 1.577892525496618e-05, "loss": 0.0047, "step": 259040 }, { "epoch": 62.22, "learning_rate": 1.5775654007663198e-05, "loss": 0.0018, "step": 259050 }, { "epoch": 62.22, "learning_rate": 1.57723830359736e-05, "loss": 0.0014, "step": 259060 }, { "epoch": 62.22, "learning_rate": 1.5769112339923724e-05, "loss": 0.0019, "step": 259070 }, { "epoch": 62.22, "learning_rate": 1.57658419195399e-05, "loss": 0.0019, "step": 259080 }, { "epoch": 62.22, "learning_rate": 1.5762571774848482e-05, "loss": 0.0017, "step": 259090 }, { "epoch": 62.23, "learning_rate": 1.5759301905875827e-05, "loss": 0.0019, "step": 259100 }, { "epoch": 62.23, "learning_rate": 1.5756032312648206e-05, "loss": 0.0022, "step": 259110 }, { "epoch": 62.23, "learning_rate": 1.5752762995192e-05, "loss": 0.0014, "step": 259120 }, { "epoch": 62.23, "learning_rate": 1.5749493953533523e-05, "loss": 0.0037, "step": 259130 }, { "epoch": 62.24, "learning_rate": 1.57462251876991e-05, "loss": 0.0019, "step": 259140 }, { "epoch": 62.24, "learning_rate": 1.574295669771505e-05, "loss": 0.0056, "step": 259150 }, { "epoch": 62.24, "learning_rate": 1.57396884836077e-05, "loss": 0.0038, "step": 259160 }, { "epoch": 62.24, "learning_rate": 1.5736420545403375e-05, "loss": 0.0024, "step": 259170 }, { "epoch": 62.25, "learning_rate": 1.5733152883128378e-05, "loss": 0.0014, "step": 259180 }, { "epoch": 62.25, "learning_rate": 1.5729885496809037e-05, "loss": 0.002, "step": 259190 }, { "epoch": 62.25, "learning_rate": 1.572661838647166e-05, "loss": 0.0045, "step": 259200 }, { "epoch": 62.25, "learning_rate": 1.5723351552142552e-05, "loss": 0.0017, "step": 259210 }, { "epoch": 62.25, "learning_rate": 1.572008499384801e-05, "loss": 0.0012, "step": 259220 }, { "epoch": 62.26, "learning_rate": 1.571681871161438e-05, "loss": 0.0028, "step": 259230 }, { "epoch": 62.26, "learning_rate": 1.5713552705467948e-05, "loss": 0.0053, "step": 259240 }, { "epoch": 62.26, "learning_rate": 1.5710286975434986e-05, "loss": 0.0015, "step": 259250 }, { "epoch": 62.26, "learning_rate": 1.5707021521541833e-05, "loss": 0.0026, "step": 259260 }, { "epoch": 62.27, "learning_rate": 1.5703756343814763e-05, "loss": 0.0061, "step": 259270 }, { "epoch": 62.27, "learning_rate": 1.5700491442280078e-05, "loss": 0.0038, "step": 259280 }, { "epoch": 62.27, "learning_rate": 1.5697226816964078e-05, "loss": 0.0018, "step": 259290 }, { "epoch": 62.27, "learning_rate": 1.5693962467893043e-05, "loss": 0.0026, "step": 259300 }, { "epoch": 62.28, "learning_rate": 1.5690698395093263e-05, "loss": 0.002, "step": 259310 }, { "epoch": 62.28, "learning_rate": 1.5687434598591012e-05, "loss": 0.0036, "step": 259320 }, { "epoch": 62.28, "learning_rate": 1.5684171078412617e-05, "loss": 0.0027, "step": 259330 }, { "epoch": 62.28, "learning_rate": 1.5680907834584314e-05, "loss": 0.0054, "step": 259340 }, { "epoch": 62.28, "learning_rate": 1.5677644867132403e-05, "loss": 0.004, "step": 259350 }, { "epoch": 62.29, "learning_rate": 1.5674382176083135e-05, "loss": 0.0025, "step": 259360 }, { "epoch": 62.29, "learning_rate": 1.567111976146282e-05, "loss": 0.0027, "step": 259370 }, { "epoch": 62.29, "learning_rate": 1.5667857623297738e-05, "loss": 0.0019, "step": 259380 }, { "epoch": 62.29, "learning_rate": 1.5664595761614108e-05, "loss": 0.002, "step": 259390 }, { "epoch": 62.3, "learning_rate": 1.5661334176438242e-05, "loss": 0.0016, "step": 259400 }, { "epoch": 62.3, "learning_rate": 1.5658072867796393e-05, "loss": 0.0015, "step": 259410 }, { "epoch": 62.3, "learning_rate": 1.5654811835714823e-05, "loss": 0.0014, "step": 259420 }, { "epoch": 62.3, "learning_rate": 1.5651551080219794e-05, "loss": 0.0015, "step": 259430 }, { "epoch": 62.3, "learning_rate": 1.5648290601337566e-05, "loss": 0.0016, "step": 259440 }, { "epoch": 62.31, "learning_rate": 1.5645030399094402e-05, "loss": 0.003, "step": 259450 }, { "epoch": 62.31, "learning_rate": 1.564177047351653e-05, "loss": 0.0016, "step": 259460 }, { "epoch": 62.31, "learning_rate": 1.5638510824630244e-05, "loss": 0.0019, "step": 259470 }, { "epoch": 62.31, "learning_rate": 1.5635251452461787e-05, "loss": 0.0015, "step": 259480 }, { "epoch": 62.32, "learning_rate": 1.563199235703736e-05, "loss": 0.0013, "step": 259490 }, { "epoch": 62.32, "learning_rate": 1.562873353838326e-05, "loss": 0.0015, "step": 259500 }, { "epoch": 62.32, "learning_rate": 1.5625474996525718e-05, "loss": 0.0047, "step": 259510 }, { "epoch": 62.32, "learning_rate": 1.5622216731490973e-05, "loss": 0.003, "step": 259520 }, { "epoch": 62.33, "learning_rate": 1.5618958743305258e-05, "loss": 0.0027, "step": 259530 }, { "epoch": 62.33, "learning_rate": 1.5615701031994816e-05, "loss": 0.0022, "step": 259540 }, { "epoch": 62.33, "learning_rate": 1.5612443597585885e-05, "loss": 0.0025, "step": 259550 }, { "epoch": 62.33, "learning_rate": 1.5609186440104673e-05, "loss": 0.0019, "step": 259560 }, { "epoch": 62.33, "learning_rate": 1.5605929559577458e-05, "loss": 0.0013, "step": 259570 }, { "epoch": 62.34, "learning_rate": 1.5602672956030433e-05, "loss": 0.0013, "step": 259580 }, { "epoch": 62.34, "learning_rate": 1.5599416629489827e-05, "loss": 0.0016, "step": 259590 }, { "epoch": 62.34, "learning_rate": 1.5596160579981855e-05, "loss": 0.0013, "step": 259600 }, { "epoch": 62.34, "learning_rate": 1.5592904807532764e-05, "loss": 0.0037, "step": 259610 }, { "epoch": 62.35, "learning_rate": 1.558964931216878e-05, "loss": 0.0033, "step": 259620 }, { "epoch": 62.35, "learning_rate": 1.558639409391607e-05, "loss": 0.0014, "step": 259630 }, { "epoch": 62.35, "learning_rate": 1.558313915280089e-05, "loss": 0.0014, "step": 259640 }, { "epoch": 62.35, "learning_rate": 1.5579884488849445e-05, "loss": 0.0013, "step": 259650 }, { "epoch": 62.36, "learning_rate": 1.5576630102087943e-05, "loss": 0.0024, "step": 259660 }, { "epoch": 62.36, "learning_rate": 1.557337599254259e-05, "loss": 0.0017, "step": 259670 }, { "epoch": 62.36, "learning_rate": 1.557012216023959e-05, "loss": 0.0014, "step": 259680 }, { "epoch": 62.36, "learning_rate": 1.5566868605205153e-05, "loss": 0.0017, "step": 259690 }, { "epoch": 62.36, "learning_rate": 1.5563615327465464e-05, "loss": 0.009, "step": 259700 }, { "epoch": 62.37, "learning_rate": 1.5560362327046763e-05, "loss": 0.0029, "step": 259710 }, { "epoch": 62.37, "learning_rate": 1.5557109603975205e-05, "loss": 0.0011, "step": 259720 }, { "epoch": 62.37, "learning_rate": 1.555385715827698e-05, "loss": 0.009, "step": 259730 }, { "epoch": 62.37, "learning_rate": 1.5550604989978316e-05, "loss": 0.0025, "step": 259740 }, { "epoch": 62.38, "learning_rate": 1.5547353099105387e-05, "loss": 0.004, "step": 259750 }, { "epoch": 62.38, "learning_rate": 1.554410148568439e-05, "loss": 0.0053, "step": 259760 }, { "epoch": 62.38, "learning_rate": 1.5540850149741475e-05, "loss": 0.0014, "step": 259770 }, { "epoch": 62.38, "learning_rate": 1.5537599091302866e-05, "loss": 0.0021, "step": 259780 }, { "epoch": 62.38, "learning_rate": 1.553434831039473e-05, "loss": 0.0043, "step": 259790 }, { "epoch": 62.39, "learning_rate": 1.5531097807043247e-05, "loss": 0.0024, "step": 259800 }, { "epoch": 62.39, "learning_rate": 1.552784758127459e-05, "loss": 0.0014, "step": 259810 }, { "epoch": 62.39, "learning_rate": 1.5524597633114935e-05, "loss": 0.0011, "step": 259820 }, { "epoch": 62.39, "learning_rate": 1.5521347962590456e-05, "loss": 0.0017, "step": 259830 }, { "epoch": 62.4, "learning_rate": 1.55180985697273e-05, "loss": 0.0018, "step": 259840 }, { "epoch": 62.4, "learning_rate": 1.55148494545517e-05, "loss": 0.0015, "step": 259850 }, { "epoch": 62.4, "learning_rate": 1.5511600617089756e-05, "loss": 0.0017, "step": 259860 }, { "epoch": 62.4, "learning_rate": 1.5508352057367638e-05, "loss": 0.0014, "step": 259870 }, { "epoch": 62.41, "learning_rate": 1.5505103775411538e-05, "loss": 0.0022, "step": 259880 }, { "epoch": 62.41, "learning_rate": 1.5501855771247597e-05, "loss": 0.0017, "step": 259890 }, { "epoch": 62.41, "learning_rate": 1.549860804490198e-05, "loss": 0.002, "step": 259900 }, { "epoch": 62.41, "learning_rate": 1.5495360596400833e-05, "loss": 0.0057, "step": 259910 }, { "epoch": 62.41, "learning_rate": 1.549211342577031e-05, "loss": 0.0036, "step": 259920 }, { "epoch": 62.42, "learning_rate": 1.548886653303656e-05, "loss": 0.0019, "step": 259930 }, { "epoch": 62.42, "learning_rate": 1.548561991822572e-05, "loss": 0.0021, "step": 259940 }, { "epoch": 62.42, "learning_rate": 1.548237358136398e-05, "loss": 0.0022, "step": 259950 }, { "epoch": 62.42, "learning_rate": 1.5479127522477433e-05, "loss": 0.002, "step": 259960 }, { "epoch": 62.43, "learning_rate": 1.5475881741592223e-05, "loss": 0.0017, "step": 259970 }, { "epoch": 62.43, "learning_rate": 1.547263623873452e-05, "loss": 0.0023, "step": 259980 }, { "epoch": 62.43, "learning_rate": 1.5469391013930446e-05, "loss": 0.0014, "step": 259990 }, { "epoch": 62.43, "learning_rate": 1.5466146067206145e-05, "loss": 0.0014, "step": 260000 }, { "epoch": 62.44, "learning_rate": 1.5462901398587704e-05, "loss": 0.0012, "step": 260010 }, { "epoch": 62.44, "learning_rate": 1.5459657008101307e-05, "loss": 0.0019, "step": 260020 }, { "epoch": 62.44, "learning_rate": 1.545641289577306e-05, "loss": 0.009, "step": 260030 }, { "epoch": 62.44, "learning_rate": 1.5453169061629085e-05, "loss": 0.0018, "step": 260040 }, { "epoch": 62.44, "learning_rate": 1.5449925505695516e-05, "loss": 0.0014, "step": 260050 }, { "epoch": 62.45, "learning_rate": 1.544668222799846e-05, "loss": 0.0013, "step": 260060 }, { "epoch": 62.45, "learning_rate": 1.544343922856405e-05, "loss": 0.0022, "step": 260070 }, { "epoch": 62.45, "learning_rate": 1.544019650741837e-05, "loss": 0.0014, "step": 260080 }, { "epoch": 62.45, "learning_rate": 1.54369540645876e-05, "loss": 0.0018, "step": 260090 }, { "epoch": 62.46, "learning_rate": 1.5433711900097787e-05, "loss": 0.0023, "step": 260100 }, { "epoch": 62.46, "learning_rate": 1.5430470013975053e-05, "loss": 0.0013, "step": 260110 }, { "epoch": 62.46, "learning_rate": 1.5427228406245526e-05, "loss": 0.0012, "step": 260120 }, { "epoch": 62.46, "learning_rate": 1.542398707693531e-05, "loss": 0.0026, "step": 260130 }, { "epoch": 62.46, "learning_rate": 1.5420746026070494e-05, "loss": 0.002, "step": 260140 }, { "epoch": 62.47, "learning_rate": 1.5417505253677182e-05, "loss": 0.0018, "step": 260150 }, { "epoch": 62.47, "learning_rate": 1.5414264759781483e-05, "loss": 0.0015, "step": 260160 }, { "epoch": 62.47, "learning_rate": 1.541102454440948e-05, "loss": 0.0015, "step": 260170 }, { "epoch": 62.47, "learning_rate": 1.540778460758727e-05, "loss": 0.0025, "step": 260180 }, { "epoch": 62.48, "learning_rate": 1.540454494934095e-05, "loss": 0.0017, "step": 260190 }, { "epoch": 62.48, "learning_rate": 1.5401305569696605e-05, "loss": 0.0019, "step": 260200 }, { "epoch": 62.48, "learning_rate": 1.5398066468680322e-05, "loss": 0.0017, "step": 260210 }, { "epoch": 62.48, "learning_rate": 1.539482764631817e-05, "loss": 0.004, "step": 260220 }, { "epoch": 62.49, "learning_rate": 1.5391589102636283e-05, "loss": 0.0018, "step": 260230 }, { "epoch": 62.49, "learning_rate": 1.5388350837660687e-05, "loss": 0.0036, "step": 260240 }, { "epoch": 62.49, "learning_rate": 1.5385112851417467e-05, "loss": 0.002, "step": 260250 }, { "epoch": 62.49, "learning_rate": 1.538187514393273e-05, "loss": 0.0037, "step": 260260 }, { "epoch": 62.49, "learning_rate": 1.5378637715232523e-05, "loss": 0.0017, "step": 260270 }, { "epoch": 62.5, "learning_rate": 1.5375400565342934e-05, "loss": 0.0018, "step": 260280 }, { "epoch": 62.5, "learning_rate": 1.5372163694290027e-05, "loss": 0.0022, "step": 260290 }, { "epoch": 62.5, "learning_rate": 1.5368927102099862e-05, "loss": 0.0021, "step": 260300 }, { "epoch": 62.5, "learning_rate": 1.5365690788798504e-05, "loss": 0.0016, "step": 260310 }, { "epoch": 62.51, "learning_rate": 1.536245475441201e-05, "loss": 0.0019, "step": 260320 }, { "epoch": 62.51, "learning_rate": 1.535921899896648e-05, "loss": 0.0038, "step": 260330 }, { "epoch": 62.51, "learning_rate": 1.5355983522487927e-05, "loss": 0.0012, "step": 260340 }, { "epoch": 62.51, "learning_rate": 1.5352748325002402e-05, "loss": 0.0013, "step": 260350 }, { "epoch": 62.52, "learning_rate": 1.5349513406536e-05, "loss": 0.0019, "step": 260360 }, { "epoch": 62.52, "learning_rate": 1.5346278767114764e-05, "loss": 0.0016, "step": 260370 }, { "epoch": 62.52, "learning_rate": 1.5343044406764695e-05, "loss": 0.0098, "step": 260380 }, { "epoch": 62.52, "learning_rate": 1.5339810325511888e-05, "loss": 0.0066, "step": 260390 }, { "epoch": 62.52, "learning_rate": 1.533657652338238e-05, "loss": 0.0021, "step": 260400 }, { "epoch": 62.53, "learning_rate": 1.53333430004022e-05, "loss": 0.007, "step": 260410 }, { "epoch": 62.53, "learning_rate": 1.53301097565974e-05, "loss": 0.0013, "step": 260420 }, { "epoch": 62.53, "learning_rate": 1.5326876791994012e-05, "loss": 0.0018, "step": 260430 }, { "epoch": 62.53, "learning_rate": 1.5323644106618074e-05, "loss": 0.006, "step": 260440 }, { "epoch": 62.54, "learning_rate": 1.5320411700495614e-05, "loss": 0.0032, "step": 260450 }, { "epoch": 62.54, "learning_rate": 1.5317179573652652e-05, "loss": 0.0028, "step": 260460 }, { "epoch": 62.54, "learning_rate": 1.5313947726115258e-05, "loss": 0.0044, "step": 260470 }, { "epoch": 62.54, "learning_rate": 1.531071615790942e-05, "loss": 0.0056, "step": 260480 }, { "epoch": 62.54, "learning_rate": 1.5307484869061162e-05, "loss": 0.0025, "step": 260490 }, { "epoch": 62.55, "learning_rate": 1.530425385959653e-05, "loss": 0.0012, "step": 260500 }, { "epoch": 62.55, "learning_rate": 1.530102312954154e-05, "loss": 0.0018, "step": 260510 }, { "epoch": 62.55, "learning_rate": 1.529779267892218e-05, "loss": 0.0052, "step": 260520 }, { "epoch": 62.55, "learning_rate": 1.52945625077645e-05, "loss": 0.0013, "step": 260530 }, { "epoch": 62.56, "learning_rate": 1.52913326160945e-05, "loss": 0.0055, "step": 260540 }, { "epoch": 62.56, "learning_rate": 1.5288103003938187e-05, "loss": 0.0015, "step": 260550 }, { "epoch": 62.56, "learning_rate": 1.5284873671321576e-05, "loss": 0.0028, "step": 260560 }, { "epoch": 62.56, "learning_rate": 1.528164461827067e-05, "loss": 0.0059, "step": 260570 }, { "epoch": 62.57, "learning_rate": 1.527841584481147e-05, "loss": 0.0023, "step": 260580 }, { "epoch": 62.57, "learning_rate": 1.5275187350969965e-05, "loss": 0.0021, "step": 260590 }, { "epoch": 62.57, "learning_rate": 1.527195913677219e-05, "loss": 0.0028, "step": 260600 }, { "epoch": 62.57, "learning_rate": 1.5268731202244136e-05, "loss": 0.0024, "step": 260610 }, { "epoch": 62.57, "learning_rate": 1.5265503547411752e-05, "loss": 0.0016, "step": 260620 }, { "epoch": 62.58, "learning_rate": 1.5262276172301083e-05, "loss": 0.002, "step": 260630 }, { "epoch": 62.58, "learning_rate": 1.5259049076938098e-05, "loss": 0.0024, "step": 260640 }, { "epoch": 62.58, "learning_rate": 1.5255822261348784e-05, "loss": 0.0017, "step": 260650 }, { "epoch": 62.58, "learning_rate": 1.5252595725559132e-05, "loss": 0.0025, "step": 260660 }, { "epoch": 62.59, "learning_rate": 1.5249369469595126e-05, "loss": 0.0049, "step": 260670 }, { "epoch": 62.59, "learning_rate": 1.5246143493482746e-05, "loss": 0.0016, "step": 260680 }, { "epoch": 62.59, "learning_rate": 1.5242917797247963e-05, "loss": 0.0033, "step": 260690 }, { "epoch": 62.59, "learning_rate": 1.523969238091677e-05, "loss": 0.0019, "step": 260700 }, { "epoch": 62.6, "learning_rate": 1.5236467244515129e-05, "loss": 0.0017, "step": 260710 }, { "epoch": 62.6, "learning_rate": 1.5233242388069019e-05, "loss": 0.0013, "step": 260720 }, { "epoch": 62.6, "learning_rate": 1.5230017811604386e-05, "loss": 0.0015, "step": 260730 }, { "epoch": 62.6, "learning_rate": 1.5226793515147241e-05, "loss": 0.0017, "step": 260740 }, { "epoch": 62.6, "learning_rate": 1.5223569498723544e-05, "loss": 0.0027, "step": 260750 }, { "epoch": 62.61, "learning_rate": 1.5220345762359211e-05, "loss": 0.0053, "step": 260760 }, { "epoch": 62.61, "learning_rate": 1.521712230608025e-05, "loss": 0.0015, "step": 260770 }, { "epoch": 62.61, "learning_rate": 1.5213899129912607e-05, "loss": 0.0016, "step": 260780 }, { "epoch": 62.61, "learning_rate": 1.5210676233882237e-05, "loss": 0.0016, "step": 260790 }, { "epoch": 62.62, "learning_rate": 1.5207453618015094e-05, "loss": 0.0033, "step": 260800 }, { "epoch": 62.62, "learning_rate": 1.5204231282337127e-05, "loss": 0.0031, "step": 260810 }, { "epoch": 62.62, "learning_rate": 1.5201009226874297e-05, "loss": 0.0014, "step": 260820 }, { "epoch": 62.62, "learning_rate": 1.5197787451652518e-05, "loss": 0.002, "step": 260830 }, { "epoch": 62.62, "learning_rate": 1.5194565956697798e-05, "loss": 0.0015, "step": 260840 }, { "epoch": 62.63, "learning_rate": 1.5191344742036029e-05, "loss": 0.0013, "step": 260850 }, { "epoch": 62.63, "learning_rate": 1.5188123807693167e-05, "loss": 0.0032, "step": 260860 }, { "epoch": 62.63, "learning_rate": 1.5184903153695129e-05, "loss": 0.0014, "step": 260870 }, { "epoch": 62.63, "learning_rate": 1.5181682780067896e-05, "loss": 0.0014, "step": 260880 }, { "epoch": 62.64, "learning_rate": 1.5178462686837392e-05, "loss": 0.0023, "step": 260890 }, { "epoch": 62.64, "learning_rate": 1.51752428740295e-05, "loss": 0.0012, "step": 260900 }, { "epoch": 62.64, "learning_rate": 1.51720233416702e-05, "loss": 0.0079, "step": 260910 }, { "epoch": 62.64, "learning_rate": 1.516880408978541e-05, "loss": 0.0016, "step": 260920 }, { "epoch": 62.65, "learning_rate": 1.5165585118401044e-05, "loss": 0.0043, "step": 260930 }, { "epoch": 62.65, "learning_rate": 1.5162366427543034e-05, "loss": 0.0023, "step": 260940 }, { "epoch": 62.65, "learning_rate": 1.5159148017237297e-05, "loss": 0.0019, "step": 260950 }, { "epoch": 62.65, "learning_rate": 1.5155929887509746e-05, "loss": 0.0024, "step": 260960 }, { "epoch": 62.65, "learning_rate": 1.515271203838629e-05, "loss": 0.0016, "step": 260970 }, { "epoch": 62.66, "learning_rate": 1.5149494469892872e-05, "loss": 0.0012, "step": 260980 }, { "epoch": 62.66, "learning_rate": 1.5146277182055402e-05, "loss": 0.0018, "step": 260990 }, { "epoch": 62.66, "learning_rate": 1.5143060174899742e-05, "loss": 0.0019, "step": 261000 }, { "epoch": 62.66, "learning_rate": 1.5139843448451846e-05, "loss": 0.0045, "step": 261010 }, { "epoch": 62.67, "learning_rate": 1.5136627002737603e-05, "loss": 0.0016, "step": 261020 }, { "epoch": 62.67, "learning_rate": 1.5133410837782913e-05, "loss": 0.0017, "step": 261030 }, { "epoch": 62.67, "learning_rate": 1.513019495361368e-05, "loss": 0.0026, "step": 261040 }, { "epoch": 62.67, "learning_rate": 1.5126979350255805e-05, "loss": 0.0025, "step": 261050 }, { "epoch": 62.68, "learning_rate": 1.5123764027735176e-05, "loss": 0.0017, "step": 261060 }, { "epoch": 62.68, "learning_rate": 1.5120548986077676e-05, "loss": 0.0013, "step": 261070 }, { "epoch": 62.68, "learning_rate": 1.5117334225309242e-05, "loss": 0.0014, "step": 261080 }, { "epoch": 62.68, "learning_rate": 1.5114119745455718e-05, "loss": 0.0013, "step": 261090 }, { "epoch": 62.68, "learning_rate": 1.5110905546543003e-05, "loss": 0.0016, "step": 261100 }, { "epoch": 62.69, "learning_rate": 1.5107691628596965e-05, "loss": 0.002, "step": 261110 }, { "epoch": 62.69, "learning_rate": 1.5104477991643517e-05, "loss": 0.0014, "step": 261120 }, { "epoch": 62.69, "learning_rate": 1.5101264635708546e-05, "loss": 0.0028, "step": 261130 }, { "epoch": 62.69, "learning_rate": 1.5098051560817878e-05, "loss": 0.0014, "step": 261140 }, { "epoch": 62.7, "learning_rate": 1.5094838766997433e-05, "loss": 0.0021, "step": 261150 }, { "epoch": 62.7, "learning_rate": 1.5091626254273068e-05, "loss": 0.0012, "step": 261160 }, { "epoch": 62.7, "learning_rate": 1.508841402267066e-05, "loss": 0.0015, "step": 261170 }, { "epoch": 62.7, "learning_rate": 1.508520207221607e-05, "loss": 0.0028, "step": 261180 }, { "epoch": 62.7, "learning_rate": 1.508199040293517e-05, "loss": 0.0047, "step": 261190 }, { "epoch": 62.71, "learning_rate": 1.5078779014853822e-05, "loss": 0.006, "step": 261200 }, { "epoch": 62.71, "learning_rate": 1.5075567907997872e-05, "loss": 0.0014, "step": 261210 }, { "epoch": 62.71, "learning_rate": 1.5072357082393223e-05, "loss": 0.0019, "step": 261220 }, { "epoch": 62.71, "learning_rate": 1.5069146538065693e-05, "loss": 0.0041, "step": 261230 }, { "epoch": 62.72, "learning_rate": 1.5065936275041132e-05, "loss": 0.0013, "step": 261240 }, { "epoch": 62.72, "learning_rate": 1.5062726293345424e-05, "loss": 0.0012, "step": 261250 }, { "epoch": 62.72, "learning_rate": 1.5059516593004408e-05, "loss": 0.0016, "step": 261260 }, { "epoch": 62.72, "learning_rate": 1.5056307174043943e-05, "loss": 0.0027, "step": 261270 }, { "epoch": 62.73, "learning_rate": 1.5053098036489826e-05, "loss": 0.0026, "step": 261280 }, { "epoch": 62.73, "learning_rate": 1.5049889180367954e-05, "loss": 0.0021, "step": 261290 }, { "epoch": 62.73, "learning_rate": 1.5046680605704145e-05, "loss": 0.0019, "step": 261300 }, { "epoch": 62.73, "learning_rate": 1.5043472312524249e-05, "loss": 0.0024, "step": 261310 }, { "epoch": 62.73, "learning_rate": 1.5040264300854096e-05, "loss": 0.0015, "step": 261320 }, { "epoch": 62.74, "learning_rate": 1.5037056570719516e-05, "loss": 0.0021, "step": 261330 }, { "epoch": 62.74, "learning_rate": 1.5033849122146348e-05, "loss": 0.0047, "step": 261340 }, { "epoch": 62.74, "learning_rate": 1.5030641955160406e-05, "loss": 0.0025, "step": 261350 }, { "epoch": 62.74, "learning_rate": 1.5027435069787565e-05, "loss": 0.0014, "step": 261360 }, { "epoch": 62.75, "learning_rate": 1.5024228466053597e-05, "loss": 0.0012, "step": 261370 }, { "epoch": 62.75, "learning_rate": 1.5021022143984336e-05, "loss": 0.0012, "step": 261380 }, { "epoch": 62.75, "learning_rate": 1.5017816103605625e-05, "loss": 0.0014, "step": 261390 }, { "epoch": 62.75, "learning_rate": 1.5014610344943269e-05, "loss": 0.0014, "step": 261400 }, { "epoch": 62.76, "learning_rate": 1.5011404868023094e-05, "loss": 0.0018, "step": 261410 }, { "epoch": 62.76, "learning_rate": 1.5008199672870898e-05, "loss": 0.0014, "step": 261420 }, { "epoch": 62.76, "learning_rate": 1.5004994759512504e-05, "loss": 0.003, "step": 261430 }, { "epoch": 62.76, "learning_rate": 1.5001790127973719e-05, "loss": 0.0012, "step": 261440 }, { "epoch": 62.76, "learning_rate": 1.4998585778280333e-05, "loss": 0.0026, "step": 261450 }, { "epoch": 62.77, "learning_rate": 1.49953817104582e-05, "loss": 0.0012, "step": 261460 }, { "epoch": 62.77, "learning_rate": 1.4992177924533074e-05, "loss": 0.0017, "step": 261470 }, { "epoch": 62.77, "learning_rate": 1.4988974420530754e-05, "loss": 0.0023, "step": 261480 }, { "epoch": 62.77, "learning_rate": 1.4985771198477077e-05, "loss": 0.0026, "step": 261490 }, { "epoch": 62.78, "learning_rate": 1.4982568258397833e-05, "loss": 0.0019, "step": 261500 }, { "epoch": 62.78, "learning_rate": 1.4979365600318784e-05, "loss": 0.0048, "step": 261510 }, { "epoch": 62.78, "learning_rate": 1.4976163224265726e-05, "loss": 0.0019, "step": 261520 }, { "epoch": 62.78, "learning_rate": 1.4972961130264474e-05, "loss": 0.0017, "step": 261530 }, { "epoch": 62.78, "learning_rate": 1.4969759318340804e-05, "loss": 0.002, "step": 261540 }, { "epoch": 62.79, "learning_rate": 1.4966557788520496e-05, "loss": 0.0149, "step": 261550 }, { "epoch": 62.79, "learning_rate": 1.4963356540829337e-05, "loss": 0.0025, "step": 261560 }, { "epoch": 62.79, "learning_rate": 1.4960155575293105e-05, "loss": 0.0019, "step": 261570 }, { "epoch": 62.79, "learning_rate": 1.4956954891937574e-05, "loss": 0.0017, "step": 261580 }, { "epoch": 62.8, "learning_rate": 1.4953754490788513e-05, "loss": 0.0019, "step": 261590 }, { "epoch": 62.8, "learning_rate": 1.4950554371871733e-05, "loss": 0.0018, "step": 261600 }, { "epoch": 62.8, "learning_rate": 1.494735453521296e-05, "loss": 0.0016, "step": 261610 }, { "epoch": 62.8, "learning_rate": 1.494415498083797e-05, "loss": 0.0015, "step": 261620 }, { "epoch": 62.81, "learning_rate": 1.4940955708772552e-05, "loss": 0.0014, "step": 261630 }, { "epoch": 62.81, "learning_rate": 1.4937756719042462e-05, "loss": 0.0024, "step": 261640 }, { "epoch": 62.81, "learning_rate": 1.493455801167345e-05, "loss": 0.0015, "step": 261650 }, { "epoch": 62.81, "learning_rate": 1.4931359586691291e-05, "loss": 0.0016, "step": 261660 }, { "epoch": 62.81, "learning_rate": 1.492816144412173e-05, "loss": 0.0023, "step": 261670 }, { "epoch": 62.82, "learning_rate": 1.492496358399053e-05, "loss": 0.0014, "step": 261680 }, { "epoch": 62.82, "learning_rate": 1.492176600632344e-05, "loss": 0.0014, "step": 261690 }, { "epoch": 62.82, "learning_rate": 1.4918568711146208e-05, "loss": 0.006, "step": 261700 }, { "epoch": 62.82, "learning_rate": 1.4915371698484587e-05, "loss": 0.0027, "step": 261710 }, { "epoch": 62.83, "learning_rate": 1.4912174968364323e-05, "loss": 0.0037, "step": 261720 }, { "epoch": 62.83, "learning_rate": 1.490897852081114e-05, "loss": 0.0032, "step": 261730 }, { "epoch": 62.83, "learning_rate": 1.4905782355850833e-05, "loss": 0.012, "step": 261740 }, { "epoch": 62.83, "learning_rate": 1.4902586473509089e-05, "loss": 0.0023, "step": 261750 }, { "epoch": 62.84, "learning_rate": 1.4899390873811642e-05, "loss": 0.0017, "step": 261760 }, { "epoch": 62.84, "learning_rate": 1.4896195556784265e-05, "loss": 0.0043, "step": 261770 }, { "epoch": 62.84, "learning_rate": 1.4893000522452671e-05, "loss": 0.0019, "step": 261780 }, { "epoch": 62.84, "learning_rate": 1.488980577084259e-05, "loss": 0.0019, "step": 261790 }, { "epoch": 62.84, "learning_rate": 1.4886611301979752e-05, "loss": 0.0017, "step": 261800 }, { "epoch": 62.85, "learning_rate": 1.4883417115889881e-05, "loss": 0.0018, "step": 261810 }, { "epoch": 62.85, "learning_rate": 1.4880223212598698e-05, "loss": 0.0013, "step": 261820 }, { "epoch": 62.85, "learning_rate": 1.487702959213193e-05, "loss": 0.0017, "step": 261830 }, { "epoch": 62.85, "learning_rate": 1.487383625451529e-05, "loss": 0.0016, "step": 261840 }, { "epoch": 62.86, "learning_rate": 1.4870643199774491e-05, "loss": 0.0013, "step": 261850 }, { "epoch": 62.86, "learning_rate": 1.4867450427935242e-05, "loss": 0.0011, "step": 261860 }, { "epoch": 62.86, "learning_rate": 1.486425793902328e-05, "loss": 0.0019, "step": 261870 }, { "epoch": 62.86, "learning_rate": 1.4861065733064317e-05, "loss": 0.0014, "step": 261880 }, { "epoch": 62.86, "learning_rate": 1.4857873810084005e-05, "loss": 0.0022, "step": 261890 }, { "epoch": 62.87, "learning_rate": 1.4854682170108108e-05, "loss": 0.0025, "step": 261900 }, { "epoch": 62.87, "learning_rate": 1.4851490813162305e-05, "loss": 0.0019, "step": 261910 }, { "epoch": 62.87, "learning_rate": 1.4848299739272303e-05, "loss": 0.0023, "step": 261920 }, { "epoch": 62.87, "learning_rate": 1.4845108948463792e-05, "loss": 0.0014, "step": 261930 }, { "epoch": 62.88, "learning_rate": 1.4841918440762476e-05, "loss": 0.004, "step": 261940 }, { "epoch": 62.88, "learning_rate": 1.4838728216194042e-05, "loss": 0.0016, "step": 261950 }, { "epoch": 62.88, "learning_rate": 1.4835538274784182e-05, "loss": 0.0022, "step": 261960 }, { "epoch": 62.88, "learning_rate": 1.4832348616558572e-05, "loss": 0.0025, "step": 261970 }, { "epoch": 62.89, "learning_rate": 1.482915924154295e-05, "loss": 0.0015, "step": 261980 }, { "epoch": 62.89, "learning_rate": 1.4825970149762946e-05, "loss": 0.0028, "step": 261990 }, { "epoch": 62.89, "learning_rate": 1.4822781341244241e-05, "loss": 0.0014, "step": 262000 }, { "epoch": 62.89, "learning_rate": 1.4819592816012557e-05, "loss": 0.0021, "step": 262010 }, { "epoch": 62.89, "learning_rate": 1.4816404574093556e-05, "loss": 0.0012, "step": 262020 }, { "epoch": 62.9, "learning_rate": 1.481321661551288e-05, "loss": 0.0039, "step": 262030 }, { "epoch": 62.9, "learning_rate": 1.4810028940296244e-05, "loss": 0.0016, "step": 262040 }, { "epoch": 62.9, "learning_rate": 1.4806841548469308e-05, "loss": 0.0014, "step": 262050 }, { "epoch": 62.9, "learning_rate": 1.4803654440057729e-05, "loss": 0.0013, "step": 262060 }, { "epoch": 62.91, "learning_rate": 1.4800467615087183e-05, "loss": 0.0017, "step": 262070 }, { "epoch": 62.91, "learning_rate": 1.479728107358333e-05, "loss": 0.0024, "step": 262080 }, { "epoch": 62.91, "learning_rate": 1.479409481557183e-05, "loss": 0.0018, "step": 262090 }, { "epoch": 62.91, "learning_rate": 1.4790908841078332e-05, "loss": 0.0016, "step": 262100 }, { "epoch": 62.91, "learning_rate": 1.4787723150128525e-05, "loss": 0.0014, "step": 262110 }, { "epoch": 62.92, "learning_rate": 1.4784537742748055e-05, "loss": 0.0027, "step": 262120 }, { "epoch": 62.92, "learning_rate": 1.4781352618962552e-05, "loss": 0.0019, "step": 262130 }, { "epoch": 62.92, "learning_rate": 1.4778167778797659e-05, "loss": 0.0015, "step": 262140 }, { "epoch": 62.92, "learning_rate": 1.477498322227906e-05, "loss": 0.0071, "step": 262150 }, { "epoch": 62.93, "learning_rate": 1.4771798949432403e-05, "loss": 0.0016, "step": 262160 }, { "epoch": 62.93, "learning_rate": 1.4768614960283278e-05, "loss": 0.0021, "step": 262170 }, { "epoch": 62.93, "learning_rate": 1.4765431254857381e-05, "loss": 0.003, "step": 262180 }, { "epoch": 62.93, "learning_rate": 1.4762247833180326e-05, "loss": 0.0014, "step": 262190 }, { "epoch": 62.94, "learning_rate": 1.4759064695277758e-05, "loss": 0.0042, "step": 262200 }, { "epoch": 62.94, "learning_rate": 1.4755881841175306e-05, "loss": 0.0017, "step": 262210 }, { "epoch": 62.94, "learning_rate": 1.4752699270898601e-05, "loss": 0.0018, "step": 262220 }, { "epoch": 62.94, "learning_rate": 1.4749516984473278e-05, "loss": 0.0027, "step": 262230 }, { "epoch": 62.94, "learning_rate": 1.4746334981924943e-05, "loss": 0.0017, "step": 262240 }, { "epoch": 62.95, "learning_rate": 1.4743153263279252e-05, "loss": 0.0019, "step": 262250 }, { "epoch": 62.95, "learning_rate": 1.4739971828561839e-05, "loss": 0.0014, "step": 262260 }, { "epoch": 63.0, "learning_rate": 1.4736790677798262e-05, "loss": 0.0014, "step": 262270 }, { "epoch": 63.0, "learning_rate": 1.4733609811014198e-05, "loss": 0.0023, "step": 262280 }, { "epoch": 63.0, "learning_rate": 1.4730429228235243e-05, "loss": 0.0013, "step": 262290 }, { "epoch": 63.01, "learning_rate": 1.4727248929487009e-05, "loss": 0.0016, "step": 262300 }, { "epoch": 63.01, "learning_rate": 1.4724068914795113e-05, "loss": 0.0051, "step": 262310 }, { "epoch": 63.01, "learning_rate": 1.4720889184185154e-05, "loss": 0.0016, "step": 262320 }, { "epoch": 63.01, "learning_rate": 1.471770973768275e-05, "loss": 0.0021, "step": 262330 }, { "epoch": 63.02, "learning_rate": 1.4714530575313485e-05, "loss": 0.0013, "step": 262340 }, { "epoch": 63.02, "learning_rate": 1.4711351697103003e-05, "loss": 0.0018, "step": 262350 }, { "epoch": 63.02, "learning_rate": 1.4708173103076866e-05, "loss": 0.0028, "step": 262360 }, { "epoch": 63.02, "learning_rate": 1.4704994793260684e-05, "loss": 0.0054, "step": 262370 }, { "epoch": 63.03, "learning_rate": 1.4701816767680032e-05, "loss": 0.0018, "step": 262380 }, { "epoch": 63.03, "learning_rate": 1.4698639026360545e-05, "loss": 0.0021, "step": 262390 }, { "epoch": 63.03, "learning_rate": 1.46954615693278e-05, "loss": 0.0013, "step": 262400 }, { "epoch": 63.03, "learning_rate": 1.4692284396607353e-05, "loss": 0.0013, "step": 262410 }, { "epoch": 63.03, "learning_rate": 1.4689107508224826e-05, "loss": 0.0015, "step": 262420 }, { "epoch": 63.04, "learning_rate": 1.468593090420579e-05, "loss": 0.0022, "step": 262430 }, { "epoch": 63.04, "learning_rate": 1.4682754584575831e-05, "loss": 0.0033, "step": 262440 }, { "epoch": 63.04, "learning_rate": 1.4679578549360524e-05, "loss": 0.0028, "step": 262450 }, { "epoch": 63.04, "learning_rate": 1.4676402798585442e-05, "loss": 0.0015, "step": 262460 }, { "epoch": 63.05, "learning_rate": 1.4673227332276167e-05, "loss": 0.0017, "step": 262470 }, { "epoch": 63.05, "learning_rate": 1.4670052150458258e-05, "loss": 0.0038, "step": 262480 }, { "epoch": 63.05, "learning_rate": 1.466687725315733e-05, "loss": 0.0019, "step": 262490 }, { "epoch": 63.05, "learning_rate": 1.4663702640398896e-05, "loss": 0.0012, "step": 262500 }, { "epoch": 63.06, "learning_rate": 1.4660528312208533e-05, "loss": 0.0011, "step": 262510 }, { "epoch": 63.06, "learning_rate": 1.4657354268611822e-05, "loss": 0.0014, "step": 262520 }, { "epoch": 63.06, "learning_rate": 1.4654180509634325e-05, "loss": 0.0013, "step": 262530 }, { "epoch": 63.06, "learning_rate": 1.4651007035301584e-05, "loss": 0.0034, "step": 262540 }, { "epoch": 63.06, "learning_rate": 1.4647833845639169e-05, "loss": 0.003, "step": 262550 }, { "epoch": 63.07, "learning_rate": 1.4644660940672627e-05, "loss": 0.0026, "step": 262560 }, { "epoch": 63.07, "learning_rate": 1.4641488320427515e-05, "loss": 0.0029, "step": 262570 }, { "epoch": 63.07, "learning_rate": 1.4638315984929374e-05, "loss": 0.004, "step": 262580 }, { "epoch": 63.07, "learning_rate": 1.463514393420376e-05, "loss": 0.0016, "step": 262590 }, { "epoch": 63.08, "learning_rate": 1.4631972168276209e-05, "loss": 0.0022, "step": 262600 }, { "epoch": 63.08, "learning_rate": 1.4628800687172273e-05, "loss": 0.0016, "step": 262610 }, { "epoch": 63.08, "learning_rate": 1.4625629490917476e-05, "loss": 0.0013, "step": 262620 }, { "epoch": 63.08, "learning_rate": 1.4622458579537379e-05, "loss": 0.0045, "step": 262630 }, { "epoch": 63.08, "learning_rate": 1.4619287953057525e-05, "loss": 0.0034, "step": 262640 }, { "epoch": 63.09, "learning_rate": 1.4616117611503399e-05, "loss": 0.0021, "step": 262650 }, { "epoch": 63.09, "learning_rate": 1.4612947554900575e-05, "loss": 0.0034, "step": 262660 }, { "epoch": 63.09, "learning_rate": 1.4609777783274576e-05, "loss": 0.0027, "step": 262670 }, { "epoch": 63.09, "learning_rate": 1.4606608296650915e-05, "loss": 0.0021, "step": 262680 }, { "epoch": 63.1, "learning_rate": 1.4603439095055126e-05, "loss": 0.0014, "step": 262690 }, { "epoch": 63.1, "learning_rate": 1.4600270178512732e-05, "loss": 0.0014, "step": 262700 }, { "epoch": 63.1, "learning_rate": 1.4597101547049247e-05, "loss": 0.0018, "step": 262710 }, { "epoch": 63.1, "learning_rate": 1.4593933200690179e-05, "loss": 0.0012, "step": 262720 }, { "epoch": 63.11, "learning_rate": 1.4590765139461082e-05, "loss": 0.0014, "step": 262730 }, { "epoch": 63.11, "learning_rate": 1.4587597363387428e-05, "loss": 0.0031, "step": 262740 }, { "epoch": 63.11, "learning_rate": 1.4584429872494725e-05, "loss": 0.0013, "step": 262750 }, { "epoch": 63.11, "learning_rate": 1.4581262666808515e-05, "loss": 0.0014, "step": 262760 }, { "epoch": 63.11, "learning_rate": 1.457809574635428e-05, "loss": 0.0024, "step": 262770 }, { "epoch": 63.12, "learning_rate": 1.4574929111157554e-05, "loss": 0.0142, "step": 262780 }, { "epoch": 63.12, "learning_rate": 1.457176276124378e-05, "loss": 0.0015, "step": 262790 }, { "epoch": 63.12, "learning_rate": 1.4568596696638509e-05, "loss": 0.0015, "step": 262800 }, { "epoch": 63.12, "learning_rate": 1.4565430917367217e-05, "loss": 0.0019, "step": 262810 }, { "epoch": 63.13, "learning_rate": 1.4562265423455406e-05, "loss": 0.0013, "step": 262820 }, { "epoch": 63.13, "learning_rate": 1.4559100214928562e-05, "loss": 0.0013, "step": 262830 }, { "epoch": 63.13, "learning_rate": 1.4555935291812178e-05, "loss": 0.0013, "step": 262840 }, { "epoch": 63.13, "learning_rate": 1.4552770654131736e-05, "loss": 0.0018, "step": 262850 }, { "epoch": 63.14, "learning_rate": 1.4549606301912716e-05, "loss": 0.0015, "step": 262860 }, { "epoch": 63.14, "learning_rate": 1.4546442235180641e-05, "loss": 0.0012, "step": 262870 }, { "epoch": 63.14, "learning_rate": 1.454327845396094e-05, "loss": 0.0025, "step": 262880 }, { "epoch": 63.14, "learning_rate": 1.4540114958279105e-05, "loss": 0.0017, "step": 262890 }, { "epoch": 63.14, "learning_rate": 1.4536951748160632e-05, "loss": 0.0026, "step": 262900 }, { "epoch": 63.15, "learning_rate": 1.4533788823630979e-05, "loss": 0.0015, "step": 262910 }, { "epoch": 63.15, "learning_rate": 1.4530626184715623e-05, "loss": 0.0013, "step": 262920 }, { "epoch": 63.15, "learning_rate": 1.4527463831440036e-05, "loss": 0.0024, "step": 262930 }, { "epoch": 63.15, "learning_rate": 1.4524301763829674e-05, "loss": 0.002, "step": 262940 }, { "epoch": 63.16, "learning_rate": 1.4521139981910009e-05, "loss": 0.0063, "step": 262950 }, { "epoch": 63.16, "learning_rate": 1.451797848570649e-05, "loss": 0.0038, "step": 262960 }, { "epoch": 63.16, "learning_rate": 1.4514817275244618e-05, "loss": 0.0014, "step": 262970 }, { "epoch": 63.16, "learning_rate": 1.4511656350549806e-05, "loss": 0.0012, "step": 262980 }, { "epoch": 63.16, "learning_rate": 1.4508495711647507e-05, "loss": 0.0019, "step": 262990 }, { "epoch": 63.17, "learning_rate": 1.450533535856321e-05, "loss": 0.0014, "step": 263000 }, { "epoch": 63.17, "learning_rate": 1.4502175291322362e-05, "loss": 0.003, "step": 263010 }, { "epoch": 63.17, "learning_rate": 1.4499015509950381e-05, "loss": 0.0014, "step": 263020 }, { "epoch": 63.17, "learning_rate": 1.4495856014472714e-05, "loss": 0.0023, "step": 263030 }, { "epoch": 63.18, "learning_rate": 1.449269680491484e-05, "loss": 0.0026, "step": 263040 }, { "epoch": 63.18, "learning_rate": 1.4489537881302173e-05, "loss": 0.0013, "step": 263050 }, { "epoch": 63.18, "learning_rate": 1.4486379243660164e-05, "loss": 0.0013, "step": 263060 }, { "epoch": 63.18, "learning_rate": 1.448322089201425e-05, "loss": 0.0043, "step": 263070 }, { "epoch": 63.19, "learning_rate": 1.4480062826389856e-05, "loss": 0.0036, "step": 263080 }, { "epoch": 63.19, "learning_rate": 1.4476905046812422e-05, "loss": 0.0019, "step": 263090 }, { "epoch": 63.19, "learning_rate": 1.447374755330736e-05, "loss": 0.0026, "step": 263100 }, { "epoch": 63.19, "learning_rate": 1.4470590345900142e-05, "loss": 0.0019, "step": 263110 }, { "epoch": 63.19, "learning_rate": 1.4467433424616156e-05, "loss": 0.0019, "step": 263120 }, { "epoch": 63.2, "learning_rate": 1.4464276789480813e-05, "loss": 0.0013, "step": 263130 }, { "epoch": 63.2, "learning_rate": 1.4461120440519572e-05, "loss": 0.0017, "step": 263140 }, { "epoch": 63.2, "learning_rate": 1.4457964377757849e-05, "loss": 0.0015, "step": 263150 }, { "epoch": 63.2, "learning_rate": 1.445480860122102e-05, "loss": 0.0055, "step": 263160 }, { "epoch": 63.21, "learning_rate": 1.4451653110934537e-05, "loss": 0.0015, "step": 263170 }, { "epoch": 63.21, "learning_rate": 1.4448497906923797e-05, "loss": 0.0057, "step": 263180 }, { "epoch": 63.21, "learning_rate": 1.444534298921421e-05, "loss": 0.0019, "step": 263190 }, { "epoch": 63.21, "learning_rate": 1.4442188357831187e-05, "loss": 0.0014, "step": 263200 }, { "epoch": 63.22, "learning_rate": 1.4439034012800135e-05, "loss": 0.0018, "step": 263210 }, { "epoch": 63.22, "learning_rate": 1.4435879954146448e-05, "loss": 0.0013, "step": 263220 }, { "epoch": 63.22, "learning_rate": 1.4432726181895529e-05, "loss": 0.0012, "step": 263230 }, { "epoch": 63.22, "learning_rate": 1.4429572696072757e-05, "loss": 0.003, "step": 263240 }, { "epoch": 63.22, "learning_rate": 1.4426419496703586e-05, "loss": 0.0013, "step": 263250 }, { "epoch": 63.23, "learning_rate": 1.4423266583813349e-05, "loss": 0.002, "step": 263260 }, { "epoch": 63.23, "learning_rate": 1.4420113957427444e-05, "loss": 0.0026, "step": 263270 }, { "epoch": 63.23, "learning_rate": 1.441696161757129e-05, "loss": 0.0017, "step": 263280 }, { "epoch": 63.23, "learning_rate": 1.4413809564270253e-05, "loss": 0.0018, "step": 263290 }, { "epoch": 63.24, "learning_rate": 1.4410657797549726e-05, "loss": 0.0019, "step": 263300 }, { "epoch": 63.24, "learning_rate": 1.4407506317435082e-05, "loss": 0.0017, "step": 263310 }, { "epoch": 63.24, "learning_rate": 1.4404355123951702e-05, "loss": 0.0017, "step": 263320 }, { "epoch": 63.24, "learning_rate": 1.4401204217124964e-05, "loss": 0.0015, "step": 263330 }, { "epoch": 63.24, "learning_rate": 1.439805359698025e-05, "loss": 0.0033, "step": 263340 }, { "epoch": 63.25, "learning_rate": 1.4394903263542919e-05, "loss": 0.0041, "step": 263350 }, { "epoch": 63.25, "learning_rate": 1.4391753216838349e-05, "loss": 0.0021, "step": 263360 }, { "epoch": 63.25, "learning_rate": 1.4388603456891892e-05, "loss": 0.0014, "step": 263370 }, { "epoch": 63.25, "learning_rate": 1.4385453983728942e-05, "loss": 0.0026, "step": 263380 }, { "epoch": 63.26, "learning_rate": 1.4382304797374862e-05, "loss": 0.0026, "step": 263390 }, { "epoch": 63.26, "learning_rate": 1.4379155897854973e-05, "loss": 0.0026, "step": 263400 }, { "epoch": 63.26, "learning_rate": 1.437600728519467e-05, "loss": 0.0013, "step": 263410 }, { "epoch": 63.26, "learning_rate": 1.4372858959419299e-05, "loss": 0.0022, "step": 263420 }, { "epoch": 63.27, "learning_rate": 1.4369710920554214e-05, "loss": 0.0024, "step": 263430 }, { "epoch": 63.27, "learning_rate": 1.4366563168624769e-05, "loss": 0.0014, "step": 263440 }, { "epoch": 63.27, "learning_rate": 1.4363415703656309e-05, "loss": 0.0017, "step": 263450 }, { "epoch": 63.27, "learning_rate": 1.4360268525674181e-05, "loss": 0.0026, "step": 263460 }, { "epoch": 63.27, "learning_rate": 1.435712163470373e-05, "loss": 0.0038, "step": 263470 }, { "epoch": 63.28, "learning_rate": 1.43539750307703e-05, "loss": 0.0014, "step": 263480 }, { "epoch": 63.28, "learning_rate": 1.4350828713899234e-05, "loss": 0.0034, "step": 263490 }, { "epoch": 63.28, "learning_rate": 1.4347682684115859e-05, "loss": 0.0017, "step": 263500 }, { "epoch": 63.28, "learning_rate": 1.4344536941445508e-05, "loss": 0.0029, "step": 263510 }, { "epoch": 63.29, "learning_rate": 1.4341391485913535e-05, "loss": 0.0012, "step": 263520 }, { "epoch": 63.29, "learning_rate": 1.4338246317545278e-05, "loss": 0.0021, "step": 263530 }, { "epoch": 63.29, "learning_rate": 1.4335101436366011e-05, "loss": 0.0057, "step": 263540 }, { "epoch": 63.29, "learning_rate": 1.4331956842401118e-05, "loss": 0.0029, "step": 263550 }, { "epoch": 63.3, "learning_rate": 1.4328812535675894e-05, "loss": 0.0023, "step": 263560 }, { "epoch": 63.3, "learning_rate": 1.4325668516215673e-05, "loss": 0.0021, "step": 263570 }, { "epoch": 63.3, "learning_rate": 1.4322524784045766e-05, "loss": 0.0015, "step": 263580 }, { "epoch": 63.3, "learning_rate": 1.4319381339191496e-05, "loss": 0.0012, "step": 263590 }, { "epoch": 63.3, "learning_rate": 1.4316238181678172e-05, "loss": 0.0016, "step": 263600 }, { "epoch": 63.31, "learning_rate": 1.4313095311531088e-05, "loss": 0.0032, "step": 263610 }, { "epoch": 63.31, "learning_rate": 1.4309952728775595e-05, "loss": 0.0013, "step": 263620 }, { "epoch": 63.31, "learning_rate": 1.4306810433436995e-05, "loss": 0.0063, "step": 263630 }, { "epoch": 63.31, "learning_rate": 1.4303668425540561e-05, "loss": 0.0011, "step": 263640 }, { "epoch": 63.32, "learning_rate": 1.43005267051116e-05, "loss": 0.0012, "step": 263650 }, { "epoch": 63.32, "learning_rate": 1.429738527217544e-05, "loss": 0.0029, "step": 263660 }, { "epoch": 63.32, "learning_rate": 1.4294244126757383e-05, "loss": 0.0013, "step": 263670 }, { "epoch": 63.32, "learning_rate": 1.4291103268882677e-05, "loss": 0.0015, "step": 263680 }, { "epoch": 63.32, "learning_rate": 1.4287962698576656e-05, "loss": 0.0018, "step": 263690 }, { "epoch": 63.33, "learning_rate": 1.4284822415864608e-05, "loss": 0.0014, "step": 263700 }, { "epoch": 63.33, "learning_rate": 1.4281682420771814e-05, "loss": 0.0017, "step": 263710 }, { "epoch": 63.33, "learning_rate": 1.4278542713323562e-05, "loss": 0.0012, "step": 263720 }, { "epoch": 63.33, "learning_rate": 1.4275403293545137e-05, "loss": 0.0024, "step": 263730 }, { "epoch": 63.34, "learning_rate": 1.4272264161461824e-05, "loss": 0.0015, "step": 263740 }, { "epoch": 63.34, "learning_rate": 1.426912531709888e-05, "loss": 0.0015, "step": 263750 }, { "epoch": 63.34, "learning_rate": 1.4265986760481625e-05, "loss": 0.0016, "step": 263760 }, { "epoch": 63.34, "learning_rate": 1.4262848491635322e-05, "loss": 0.0013, "step": 263770 }, { "epoch": 63.35, "learning_rate": 1.4259710510585205e-05, "loss": 0.0014, "step": 263780 }, { "epoch": 63.35, "learning_rate": 1.4256572817356589e-05, "loss": 0.0019, "step": 263790 }, { "epoch": 63.35, "learning_rate": 1.4253435411974725e-05, "loss": 0.0014, "step": 263800 }, { "epoch": 63.35, "learning_rate": 1.4250298294464881e-05, "loss": 0.003, "step": 263810 }, { "epoch": 63.35, "learning_rate": 1.4247161464852322e-05, "loss": 0.0055, "step": 263820 }, { "epoch": 63.36, "learning_rate": 1.4244024923162309e-05, "loss": 0.0059, "step": 263830 }, { "epoch": 63.36, "learning_rate": 1.4240888669420094e-05, "loss": 0.0014, "step": 263840 }, { "epoch": 63.36, "learning_rate": 1.423775270365093e-05, "loss": 0.0015, "step": 263850 }, { "epoch": 63.36, "learning_rate": 1.423461702588011e-05, "loss": 0.0023, "step": 263860 }, { "epoch": 63.37, "learning_rate": 1.4231481636132837e-05, "loss": 0.0064, "step": 263870 }, { "epoch": 63.37, "learning_rate": 1.4228346534434384e-05, "loss": 0.0012, "step": 263880 }, { "epoch": 63.37, "learning_rate": 1.4225211720809984e-05, "loss": 0.0055, "step": 263890 }, { "epoch": 63.37, "learning_rate": 1.42220771952849e-05, "loss": 0.0025, "step": 263900 }, { "epoch": 63.38, "learning_rate": 1.421894295788439e-05, "loss": 0.001, "step": 263910 }, { "epoch": 63.38, "learning_rate": 1.4215809008633636e-05, "loss": 0.0021, "step": 263920 }, { "epoch": 63.38, "learning_rate": 1.421267534755793e-05, "loss": 0.0016, "step": 263930 }, { "epoch": 63.38, "learning_rate": 1.4209541974682493e-05, "loss": 0.0016, "step": 263940 }, { "epoch": 63.38, "learning_rate": 1.4206408890032551e-05, "loss": 0.0023, "step": 263950 }, { "epoch": 63.39, "learning_rate": 1.4203276093633344e-05, "loss": 0.0011, "step": 263960 }, { "epoch": 63.39, "learning_rate": 1.4200143585510096e-05, "loss": 0.0024, "step": 263970 }, { "epoch": 63.39, "learning_rate": 1.4197011365688035e-05, "loss": 0.0011, "step": 263980 }, { "epoch": 63.39, "learning_rate": 1.4193879434192364e-05, "loss": 0.0037, "step": 263990 }, { "epoch": 63.4, "learning_rate": 1.4190747791048359e-05, "loss": 0.0025, "step": 264000 }, { "epoch": 63.4, "learning_rate": 1.4187616436281192e-05, "loss": 0.0016, "step": 264010 }, { "epoch": 63.4, "learning_rate": 1.4184485369916073e-05, "loss": 0.0061, "step": 264020 }, { "epoch": 63.4, "learning_rate": 1.4181354591978257e-05, "loss": 0.0019, "step": 264030 }, { "epoch": 63.4, "learning_rate": 1.4178224102492943e-05, "loss": 0.0011, "step": 264040 }, { "epoch": 63.41, "learning_rate": 1.4175093901485343e-05, "loss": 0.0013, "step": 264050 }, { "epoch": 63.41, "learning_rate": 1.417196398898063e-05, "loss": 0.0031, "step": 264060 }, { "epoch": 63.41, "learning_rate": 1.4168834365004053e-05, "loss": 0.0025, "step": 264070 }, { "epoch": 63.41, "learning_rate": 1.41657050295808e-05, "loss": 0.0017, "step": 264080 }, { "epoch": 63.42, "learning_rate": 1.416257598273607e-05, "loss": 0.0045, "step": 264090 }, { "epoch": 63.42, "learning_rate": 1.4159447224495065e-05, "loss": 0.0029, "step": 264100 }, { "epoch": 63.42, "learning_rate": 1.415631875488298e-05, "loss": 0.0017, "step": 264110 }, { "epoch": 63.42, "learning_rate": 1.4153190573925006e-05, "loss": 0.0024, "step": 264120 }, { "epoch": 63.43, "learning_rate": 1.4150062681646325e-05, "loss": 0.0013, "step": 264130 }, { "epoch": 63.43, "learning_rate": 1.4146935078072171e-05, "loss": 0.0012, "step": 264140 }, { "epoch": 63.43, "learning_rate": 1.414380776322768e-05, "loss": 0.0014, "step": 264150 }, { "epoch": 63.43, "learning_rate": 1.414068073713804e-05, "loss": 0.0079, "step": 264160 }, { "epoch": 63.43, "learning_rate": 1.4137553999828463e-05, "loss": 0.0014, "step": 264170 }, { "epoch": 63.44, "learning_rate": 1.4134427551324115e-05, "loss": 0.0018, "step": 264180 }, { "epoch": 63.44, "learning_rate": 1.4131301391650175e-05, "loss": 0.0015, "step": 264190 }, { "epoch": 63.44, "learning_rate": 1.4128175520831816e-05, "loss": 0.0014, "step": 264200 }, { "epoch": 63.44, "learning_rate": 1.4125049938894214e-05, "loss": 0.0013, "step": 264210 }, { "epoch": 63.45, "learning_rate": 1.4121924645862533e-05, "loss": 0.0013, "step": 264220 }, { "epoch": 63.45, "learning_rate": 1.4118799641761938e-05, "loss": 0.0019, "step": 264230 }, { "epoch": 63.45, "learning_rate": 1.4115674926617629e-05, "loss": 0.0014, "step": 264240 }, { "epoch": 63.45, "learning_rate": 1.411255050045473e-05, "loss": 0.0019, "step": 264250 }, { "epoch": 63.45, "learning_rate": 1.4109426363298394e-05, "loss": 0.0016, "step": 264260 }, { "epoch": 63.46, "learning_rate": 1.4106302515173825e-05, "loss": 0.0012, "step": 264270 }, { "epoch": 63.46, "learning_rate": 1.4103178956106161e-05, "loss": 0.0017, "step": 264280 }, { "epoch": 63.46, "learning_rate": 1.4100055686120561e-05, "loss": 0.0033, "step": 264290 }, { "epoch": 63.46, "learning_rate": 1.4096932705242139e-05, "loss": 0.0013, "step": 264300 }, { "epoch": 63.47, "learning_rate": 1.4093810013496096e-05, "loss": 0.0015, "step": 264310 }, { "epoch": 63.47, "learning_rate": 1.409068761090755e-05, "loss": 0.0021, "step": 264320 }, { "epoch": 63.47, "learning_rate": 1.4087565497501659e-05, "loss": 0.0013, "step": 264330 }, { "epoch": 63.47, "learning_rate": 1.408444367330356e-05, "loss": 0.0013, "step": 264340 }, { "epoch": 63.48, "learning_rate": 1.4081322138338394e-05, "loss": 0.0014, "step": 264350 }, { "epoch": 63.48, "learning_rate": 1.40782008926313e-05, "loss": 0.0023, "step": 264360 }, { "epoch": 63.48, "learning_rate": 1.4075079936207403e-05, "loss": 0.0029, "step": 264370 }, { "epoch": 63.48, "learning_rate": 1.4071959269091872e-05, "loss": 0.0015, "step": 264380 }, { "epoch": 63.48, "learning_rate": 1.40688388913098e-05, "loss": 0.0024, "step": 264390 }, { "epoch": 63.49, "learning_rate": 1.4065718802886307e-05, "loss": 0.0049, "step": 264400 }, { "epoch": 63.49, "learning_rate": 1.4062599003846567e-05, "loss": 0.0012, "step": 264410 }, { "epoch": 63.49, "learning_rate": 1.4059479494215672e-05, "loss": 0.0011, "step": 264420 }, { "epoch": 63.49, "learning_rate": 1.4056360274018754e-05, "loss": 0.0027, "step": 264430 }, { "epoch": 63.5, "learning_rate": 1.4053241343280927e-05, "loss": 0.0013, "step": 264440 }, { "epoch": 63.5, "learning_rate": 1.4050122702027313e-05, "loss": 0.002, "step": 264450 }, { "epoch": 63.5, "learning_rate": 1.4047004350283022e-05, "loss": 0.0019, "step": 264460 }, { "epoch": 63.5, "learning_rate": 1.4043886288073166e-05, "loss": 0.0061, "step": 264470 }, { "epoch": 63.51, "learning_rate": 1.4040768515422864e-05, "loss": 0.0014, "step": 264480 }, { "epoch": 63.51, "learning_rate": 1.4037651032357213e-05, "loss": 0.0025, "step": 264490 }, { "epoch": 63.51, "learning_rate": 1.4034533838901325e-05, "loss": 0.0013, "step": 264500 }, { "epoch": 63.51, "learning_rate": 1.4031416935080282e-05, "loss": 0.0026, "step": 264510 }, { "epoch": 63.51, "learning_rate": 1.4028300320919241e-05, "loss": 0.0015, "step": 264520 }, { "epoch": 63.52, "learning_rate": 1.4025183996443241e-05, "loss": 0.0013, "step": 264530 }, { "epoch": 63.52, "learning_rate": 1.4022067961677394e-05, "loss": 0.002, "step": 264540 }, { "epoch": 63.52, "learning_rate": 1.4018952216646814e-05, "loss": 0.0059, "step": 264550 }, { "epoch": 63.52, "learning_rate": 1.4015836761376577e-05, "loss": 0.0016, "step": 264560 }, { "epoch": 63.53, "learning_rate": 1.4012721595891776e-05, "loss": 0.0014, "step": 264570 }, { "epoch": 63.53, "learning_rate": 1.4009606720217494e-05, "loss": 0.0013, "step": 264580 }, { "epoch": 63.53, "learning_rate": 1.4006492134378818e-05, "loss": 0.0013, "step": 264590 }, { "epoch": 63.53, "learning_rate": 1.4003377838400834e-05, "loss": 0.0021, "step": 264600 }, { "epoch": 63.53, "learning_rate": 1.4000263832308597e-05, "loss": 0.0013, "step": 264610 }, { "epoch": 63.54, "learning_rate": 1.3997150116127238e-05, "loss": 0.0014, "step": 264620 }, { "epoch": 63.54, "learning_rate": 1.3994036689881785e-05, "loss": 0.0029, "step": 264630 }, { "epoch": 63.54, "learning_rate": 1.3990923553597312e-05, "loss": 0.0023, "step": 264640 }, { "epoch": 63.54, "learning_rate": 1.3987810707298916e-05, "loss": 0.0012, "step": 264650 }, { "epoch": 63.55, "learning_rate": 1.3984698151011666e-05, "loss": 0.0017, "step": 264660 }, { "epoch": 63.55, "learning_rate": 1.398158588476059e-05, "loss": 0.0127, "step": 264670 }, { "epoch": 63.55, "learning_rate": 1.3978473908570783e-05, "loss": 0.0061, "step": 264680 }, { "epoch": 63.55, "learning_rate": 1.3975362222467303e-05, "loss": 0.0014, "step": 264690 }, { "epoch": 63.56, "learning_rate": 1.3972250826475203e-05, "loss": 0.002, "step": 264700 }, { "epoch": 63.56, "learning_rate": 1.396913972061954e-05, "loss": 0.0011, "step": 264710 }, { "epoch": 63.56, "learning_rate": 1.396602890492537e-05, "loss": 0.0057, "step": 264720 }, { "epoch": 63.56, "learning_rate": 1.396291837941775e-05, "loss": 0.0036, "step": 264730 }, { "epoch": 63.56, "learning_rate": 1.3959808144121716e-05, "loss": 0.0096, "step": 264740 }, { "epoch": 63.57, "learning_rate": 1.3956698199062307e-05, "loss": 0.0023, "step": 264750 }, { "epoch": 63.57, "learning_rate": 1.3953588544264617e-05, "loss": 0.0023, "step": 264760 }, { "epoch": 63.57, "learning_rate": 1.395047917975364e-05, "loss": 0.0022, "step": 264770 }, { "epoch": 63.57, "learning_rate": 1.394737010555442e-05, "loss": 0.0021, "step": 264780 }, { "epoch": 63.58, "learning_rate": 1.3944261321692015e-05, "loss": 0.0016, "step": 264790 }, { "epoch": 63.58, "learning_rate": 1.3941152828191467e-05, "loss": 0.0019, "step": 264800 }, { "epoch": 63.58, "learning_rate": 1.3938044625077762e-05, "loss": 0.0025, "step": 264810 }, { "epoch": 63.58, "learning_rate": 1.3934936712375979e-05, "loss": 0.0043, "step": 264820 }, { "epoch": 63.59, "learning_rate": 1.3931829090111131e-05, "loss": 0.0014, "step": 264830 }, { "epoch": 63.59, "learning_rate": 1.3928721758308243e-05, "loss": 0.0014, "step": 264840 }, { "epoch": 63.59, "learning_rate": 1.3925614716992342e-05, "loss": 0.0017, "step": 264850 }, { "epoch": 63.59, "learning_rate": 1.3922507966188436e-05, "loss": 0.0014, "step": 264860 }, { "epoch": 63.59, "learning_rate": 1.3919401505921565e-05, "loss": 0.003, "step": 264870 }, { "epoch": 63.6, "learning_rate": 1.3916295336216712e-05, "loss": 0.0063, "step": 264880 }, { "epoch": 63.6, "learning_rate": 1.3913189457098935e-05, "loss": 0.0165, "step": 264890 }, { "epoch": 63.6, "learning_rate": 1.3910083868593239e-05, "loss": 0.0026, "step": 264900 }, { "epoch": 63.6, "learning_rate": 1.3906978570724588e-05, "loss": 0.0032, "step": 264910 }, { "epoch": 63.61, "learning_rate": 1.3903873563518033e-05, "loss": 0.0017, "step": 264920 }, { "epoch": 63.61, "learning_rate": 1.3900768846998575e-05, "loss": 0.0012, "step": 264930 }, { "epoch": 63.61, "learning_rate": 1.3897664421191203e-05, "loss": 0.0033, "step": 264940 }, { "epoch": 63.61, "learning_rate": 1.3894560286120928e-05, "loss": 0.0023, "step": 264950 }, { "epoch": 63.61, "learning_rate": 1.3891456441812745e-05, "loss": 0.0016, "step": 264960 }, { "epoch": 63.62, "learning_rate": 1.3888352888291645e-05, "loss": 0.0018, "step": 264970 }, { "epoch": 63.62, "learning_rate": 1.3885249625582625e-05, "loss": 0.0014, "step": 264980 }, { "epoch": 63.62, "learning_rate": 1.3882146653710675e-05, "loss": 0.0027, "step": 264990 }, { "epoch": 63.62, "learning_rate": 1.387904397270079e-05, "loss": 0.0018, "step": 265000 }, { "epoch": 63.63, "learning_rate": 1.3875941582577946e-05, "loss": 0.0014, "step": 265010 }, { "epoch": 63.63, "learning_rate": 1.3872839483367117e-05, "loss": 0.0018, "step": 265020 }, { "epoch": 63.63, "learning_rate": 1.3869737675093314e-05, "loss": 0.0017, "step": 265030 }, { "epoch": 63.63, "learning_rate": 1.3866636157781515e-05, "loss": 0.0014, "step": 265040 }, { "epoch": 63.64, "learning_rate": 1.3863534931456657e-05, "loss": 0.0017, "step": 265050 }, { "epoch": 63.64, "learning_rate": 1.3860433996143752e-05, "loss": 0.0029, "step": 265060 }, { "epoch": 63.64, "learning_rate": 1.3857333351867768e-05, "loss": 0.0024, "step": 265070 }, { "epoch": 63.64, "learning_rate": 1.385423299865366e-05, "loss": 0.0022, "step": 265080 }, { "epoch": 63.64, "learning_rate": 1.3851132936526413e-05, "loss": 0.0073, "step": 265090 }, { "epoch": 63.65, "learning_rate": 1.3848033165510977e-05, "loss": 0.0014, "step": 265100 }, { "epoch": 63.65, "learning_rate": 1.3844933685632322e-05, "loss": 0.0018, "step": 265110 }, { "epoch": 63.65, "learning_rate": 1.384183449691539e-05, "loss": 0.0028, "step": 265120 }, { "epoch": 63.65, "learning_rate": 1.3838735599385194e-05, "loss": 0.0013, "step": 265130 }, { "epoch": 63.66, "learning_rate": 1.383563699306663e-05, "loss": 0.0014, "step": 265140 }, { "epoch": 63.66, "learning_rate": 1.383253867798468e-05, "loss": 0.0016, "step": 265150 }, { "epoch": 63.66, "learning_rate": 1.3829440654164271e-05, "loss": 0.0022, "step": 265160 }, { "epoch": 63.66, "learning_rate": 1.3826342921630387e-05, "loss": 0.0021, "step": 265170 }, { "epoch": 63.67, "learning_rate": 1.382324548040797e-05, "loss": 0.0018, "step": 265180 }, { "epoch": 63.67, "learning_rate": 1.382014833052192e-05, "loss": 0.0016, "step": 265190 }, { "epoch": 63.67, "learning_rate": 1.3817051471997234e-05, "loss": 0.0021, "step": 265200 }, { "epoch": 63.67, "learning_rate": 1.3813954904858817e-05, "loss": 0.0016, "step": 265210 }, { "epoch": 63.67, "learning_rate": 1.3810858629131623e-05, "loss": 0.0016, "step": 265220 }, { "epoch": 63.68, "learning_rate": 1.3807762644840583e-05, "loss": 0.0016, "step": 265230 }, { "epoch": 63.68, "learning_rate": 1.380466695201062e-05, "loss": 0.0044, "step": 265240 }, { "epoch": 63.68, "learning_rate": 1.3801571550666676e-05, "loss": 0.0042, "step": 265250 }, { "epoch": 63.68, "learning_rate": 1.3798476440833657e-05, "loss": 0.0031, "step": 265260 }, { "epoch": 63.69, "learning_rate": 1.3795381622536524e-05, "loss": 0.0018, "step": 265270 }, { "epoch": 63.69, "learning_rate": 1.3792287095800193e-05, "loss": 0.0014, "step": 265280 }, { "epoch": 63.69, "learning_rate": 1.3789192860649542e-05, "loss": 0.0014, "step": 265290 }, { "epoch": 63.69, "learning_rate": 1.3786098917109536e-05, "loss": 0.002, "step": 265300 }, { "epoch": 63.69, "learning_rate": 1.3783005265205074e-05, "loss": 0.0016, "step": 265310 }, { "epoch": 63.7, "learning_rate": 1.3779911904961073e-05, "loss": 0.0013, "step": 265320 }, { "epoch": 63.7, "learning_rate": 1.3776818836402439e-05, "loss": 0.0015, "step": 265330 }, { "epoch": 63.7, "learning_rate": 1.3773726059554088e-05, "loss": 0.0022, "step": 265340 }, { "epoch": 63.7, "learning_rate": 1.3770633574440916e-05, "loss": 0.0012, "step": 265350 }, { "epoch": 63.71, "learning_rate": 1.3767541381087823e-05, "loss": 0.0017, "step": 265360 }, { "epoch": 63.71, "learning_rate": 1.3764449479519753e-05, "loss": 0.0014, "step": 265370 }, { "epoch": 63.71, "learning_rate": 1.376135786976156e-05, "loss": 0.0016, "step": 265380 }, { "epoch": 63.71, "learning_rate": 1.375826655183815e-05, "loss": 0.0013, "step": 265390 }, { "epoch": 63.72, "learning_rate": 1.3755175525774411e-05, "loss": 0.0012, "step": 265400 }, { "epoch": 63.72, "learning_rate": 1.375208479159526e-05, "loss": 0.0013, "step": 265410 }, { "epoch": 63.72, "learning_rate": 1.374899434932559e-05, "loss": 0.0044, "step": 265420 }, { "epoch": 63.72, "learning_rate": 1.3745904198990244e-05, "loss": 0.0013, "step": 265430 }, { "epoch": 63.72, "learning_rate": 1.3742814340614152e-05, "loss": 0.002, "step": 265440 }, { "epoch": 63.73, "learning_rate": 1.3739724774222185e-05, "loss": 0.0012, "step": 265450 }, { "epoch": 63.73, "learning_rate": 1.3736635499839211e-05, "loss": 0.0019, "step": 265460 }, { "epoch": 63.73, "learning_rate": 1.3733546517490126e-05, "loss": 0.0018, "step": 265470 }, { "epoch": 63.73, "learning_rate": 1.37304578271998e-05, "loss": 0.0023, "step": 265480 }, { "epoch": 63.74, "learning_rate": 1.3727369428993098e-05, "loss": 0.0022, "step": 265490 }, { "epoch": 63.74, "learning_rate": 1.3724281322894883e-05, "loss": 0.0018, "step": 265500 }, { "epoch": 63.74, "learning_rate": 1.3721193508930069e-05, "loss": 0.0015, "step": 265510 }, { "epoch": 63.74, "learning_rate": 1.3718105987123481e-05, "loss": 0.0013, "step": 265520 }, { "epoch": 63.75, "learning_rate": 1.3715018757499975e-05, "loss": 0.0012, "step": 265530 }, { "epoch": 63.75, "learning_rate": 1.371193182008445e-05, "loss": 0.0012, "step": 265540 }, { "epoch": 63.75, "learning_rate": 1.3708845174901753e-05, "loss": 0.0025, "step": 265550 }, { "epoch": 63.75, "learning_rate": 1.3705758821976744e-05, "loss": 0.0021, "step": 265560 }, { "epoch": 63.75, "learning_rate": 1.370267276133424e-05, "loss": 0.002, "step": 265570 }, { "epoch": 63.76, "learning_rate": 1.3699586992999142e-05, "loss": 0.0013, "step": 265580 }, { "epoch": 63.76, "learning_rate": 1.369650151699628e-05, "loss": 0.0017, "step": 265590 }, { "epoch": 63.76, "learning_rate": 1.3693416333350501e-05, "loss": 0.0058, "step": 265600 }, { "epoch": 63.76, "learning_rate": 1.3690331442086656e-05, "loss": 0.0015, "step": 265610 }, { "epoch": 63.77, "learning_rate": 1.3687246843229584e-05, "loss": 0.0095, "step": 265620 }, { "epoch": 63.77, "learning_rate": 1.3684162536804123e-05, "loss": 0.0013, "step": 265630 }, { "epoch": 63.77, "learning_rate": 1.36810785228351e-05, "loss": 0.0014, "step": 265640 }, { "epoch": 63.77, "learning_rate": 1.3677994801347399e-05, "loss": 0.0026, "step": 265650 }, { "epoch": 63.77, "learning_rate": 1.3674911372365806e-05, "loss": 0.0084, "step": 265660 }, { "epoch": 63.78, "learning_rate": 1.3671828235915152e-05, "loss": 0.0014, "step": 265670 }, { "epoch": 63.78, "learning_rate": 1.3668745392020294e-05, "loss": 0.0017, "step": 265680 }, { "epoch": 63.78, "learning_rate": 1.3665662840706044e-05, "loss": 0.002, "step": 265690 }, { "epoch": 63.78, "learning_rate": 1.3662580581997231e-05, "loss": 0.0017, "step": 265700 }, { "epoch": 63.79, "learning_rate": 1.365949861591867e-05, "loss": 0.0054, "step": 265710 }, { "epoch": 63.79, "learning_rate": 1.3656416942495187e-05, "loss": 0.0044, "step": 265720 }, { "epoch": 63.79, "learning_rate": 1.3653335561751591e-05, "loss": 0.0019, "step": 265730 }, { "epoch": 63.79, "learning_rate": 1.3650254473712693e-05, "loss": 0.0014, "step": 265740 }, { "epoch": 63.8, "learning_rate": 1.3647173678403336e-05, "loss": 0.0036, "step": 265750 }, { "epoch": 63.8, "learning_rate": 1.36440931758483e-05, "loss": 0.0013, "step": 265760 }, { "epoch": 63.8, "learning_rate": 1.364101296607238e-05, "loss": 0.0014, "step": 265770 }, { "epoch": 63.8, "learning_rate": 1.363793304910042e-05, "loss": 0.0016, "step": 265780 }, { "epoch": 63.8, "learning_rate": 1.3634853424957211e-05, "loss": 0.0015, "step": 265790 }, { "epoch": 63.81, "learning_rate": 1.3631774093667554e-05, "loss": 0.0015, "step": 265800 }, { "epoch": 63.81, "learning_rate": 1.3628695055256218e-05, "loss": 0.0028, "step": 265810 }, { "epoch": 63.81, "learning_rate": 1.3625616309748035e-05, "loss": 0.0015, "step": 265820 }, { "epoch": 63.81, "learning_rate": 1.3622537857167783e-05, "loss": 0.0026, "step": 265830 }, { "epoch": 63.82, "learning_rate": 1.361945969754026e-05, "loss": 0.0022, "step": 265840 }, { "epoch": 63.82, "learning_rate": 1.3616381830890246e-05, "loss": 0.0019, "step": 265850 }, { "epoch": 63.82, "learning_rate": 1.3613304257242537e-05, "loss": 0.0019, "step": 265860 }, { "epoch": 63.82, "learning_rate": 1.3610226976621909e-05, "loss": 0.0012, "step": 265870 }, { "epoch": 63.83, "learning_rate": 1.360714998905313e-05, "loss": 0.0017, "step": 265880 }, { "epoch": 63.83, "learning_rate": 1.3604073294561032e-05, "loss": 0.0057, "step": 265890 }, { "epoch": 63.83, "learning_rate": 1.3600996893170337e-05, "loss": 0.0015, "step": 265900 }, { "epoch": 63.83, "learning_rate": 1.3597920784905827e-05, "loss": 0.0014, "step": 265910 }, { "epoch": 63.83, "learning_rate": 1.3594844969792303e-05, "loss": 0.0027, "step": 265920 }, { "epoch": 63.84, "learning_rate": 1.3591769447854513e-05, "loss": 0.0017, "step": 265930 }, { "epoch": 63.84, "learning_rate": 1.3588694219117236e-05, "loss": 0.0014, "step": 265940 }, { "epoch": 63.84, "learning_rate": 1.3585619283605228e-05, "loss": 0.0022, "step": 265950 }, { "epoch": 63.84, "learning_rate": 1.3582544641343259e-05, "loss": 0.0017, "step": 265960 }, { "epoch": 63.85, "learning_rate": 1.3579470292356084e-05, "loss": 0.0026, "step": 265970 }, { "epoch": 63.85, "learning_rate": 1.357639623666846e-05, "loss": 0.0055, "step": 265980 }, { "epoch": 63.85, "learning_rate": 1.3573322474305145e-05, "loss": 0.0012, "step": 265990 }, { "epoch": 63.85, "learning_rate": 1.3570249005290896e-05, "loss": 0.0043, "step": 266000 }, { "epoch": 63.85, "learning_rate": 1.3567175829650463e-05, "loss": 0.0014, "step": 266010 }, { "epoch": 63.86, "learning_rate": 1.3564102947408574e-05, "loss": 0.0016, "step": 266020 }, { "epoch": 63.86, "learning_rate": 1.3561030358590026e-05, "loss": 0.0014, "step": 266030 }, { "epoch": 63.86, "learning_rate": 1.3557958063219517e-05, "loss": 0.0015, "step": 266040 }, { "epoch": 63.86, "learning_rate": 1.3554886061321787e-05, "loss": 0.0038, "step": 266050 }, { "epoch": 63.87, "learning_rate": 1.3551814352921605e-05, "loss": 0.0015, "step": 266060 }, { "epoch": 63.87, "learning_rate": 1.3548742938043696e-05, "loss": 0.0045, "step": 266070 }, { "epoch": 63.87, "learning_rate": 1.354567181671279e-05, "loss": 0.0012, "step": 266080 }, { "epoch": 63.87, "learning_rate": 1.3542600988953624e-05, "loss": 0.0014, "step": 266090 }, { "epoch": 63.88, "learning_rate": 1.3539530454790922e-05, "loss": 0.0014, "step": 266100 }, { "epoch": 63.88, "learning_rate": 1.3536460214249419e-05, "loss": 0.0017, "step": 266110 }, { "epoch": 63.88, "learning_rate": 1.3533390267353818e-05, "loss": 0.0012, "step": 266120 }, { "epoch": 63.88, "learning_rate": 1.3530320614128893e-05, "loss": 0.0024, "step": 266130 }, { "epoch": 63.88, "learning_rate": 1.3527251254599316e-05, "loss": 0.0015, "step": 266140 }, { "epoch": 63.89, "learning_rate": 1.3524182188789803e-05, "loss": 0.0043, "step": 266150 }, { "epoch": 63.89, "learning_rate": 1.3521113416725101e-05, "loss": 0.0057, "step": 266160 }, { "epoch": 63.89, "learning_rate": 1.3518044938429925e-05, "loss": 0.0024, "step": 266170 }, { "epoch": 63.89, "learning_rate": 1.3514976753928937e-05, "loss": 0.0048, "step": 266180 }, { "epoch": 63.9, "learning_rate": 1.3511908863246896e-05, "loss": 0.0016, "step": 266190 }, { "epoch": 63.9, "learning_rate": 1.3508841266408495e-05, "loss": 0.0015, "step": 266200 }, { "epoch": 63.9, "learning_rate": 1.3505773963438429e-05, "loss": 0.0019, "step": 266210 }, { "epoch": 63.9, "learning_rate": 1.35027069543614e-05, "loss": 0.0013, "step": 266220 }, { "epoch": 63.91, "learning_rate": 1.3499640239202116e-05, "loss": 0.0012, "step": 266230 }, { "epoch": 63.91, "learning_rate": 1.3496573817985264e-05, "loss": 0.0016, "step": 266240 }, { "epoch": 63.91, "learning_rate": 1.3493507690735546e-05, "loss": 0.0013, "step": 266250 }, { "epoch": 63.91, "learning_rate": 1.3490441857477632e-05, "loss": 0.0012, "step": 266260 }, { "epoch": 63.91, "learning_rate": 1.3487376318236267e-05, "loss": 0.0014, "step": 266270 }, { "epoch": 63.92, "learning_rate": 1.3484311073036082e-05, "loss": 0.0013, "step": 266280 }, { "epoch": 63.92, "learning_rate": 1.3481246121901765e-05, "loss": 0.0014, "step": 266290 }, { "epoch": 63.92, "learning_rate": 1.3478181464858031e-05, "loss": 0.0013, "step": 266300 }, { "epoch": 63.92, "learning_rate": 1.3475117101929557e-05, "loss": 0.0095, "step": 266310 }, { "epoch": 63.93, "learning_rate": 1.347205303314098e-05, "loss": 0.0014, "step": 266320 }, { "epoch": 63.93, "learning_rate": 1.3468989258517018e-05, "loss": 0.0069, "step": 266330 }, { "epoch": 63.93, "learning_rate": 1.3465925778082328e-05, "loss": 0.0012, "step": 266340 }, { "epoch": 63.93, "learning_rate": 1.346286259186158e-05, "loss": 0.0012, "step": 266350 }, { "epoch": 63.93, "learning_rate": 1.345979969987945e-05, "loss": 0.0018, "step": 266360 }, { "epoch": 63.94, "learning_rate": 1.3456737102160589e-05, "loss": 0.0014, "step": 266370 }, { "epoch": 63.94, "learning_rate": 1.3453674798729676e-05, "loss": 0.0012, "step": 266380 }, { "epoch": 63.94, "learning_rate": 1.3450612789611344e-05, "loss": 0.0022, "step": 266390 }, { "epoch": 63.94, "learning_rate": 1.3447551074830295e-05, "loss": 0.0012, "step": 266400 }, { "epoch": 63.95, "learning_rate": 1.3444489654411175e-05, "loss": 0.0014, "step": 266410 }, { "epoch": 63.95, "learning_rate": 1.3441428528378613e-05, "loss": 0.0016, "step": 266420 }, { "epoch": 63.95, "learning_rate": 1.3438367696757259e-05, "loss": 0.0016, "step": 266430 }, { "epoch": 64.0, "learning_rate": 1.3435307159571792e-05, "loss": 0.0018, "step": 266440 }, { "epoch": 64.0, "learning_rate": 1.3432246916846842e-05, "loss": 0.0013, "step": 266450 }, { "epoch": 64.01, "learning_rate": 1.3429186968607061e-05, "loss": 0.0016, "step": 266460 }, { "epoch": 64.01, "learning_rate": 1.3426127314877086e-05, "loss": 0.0013, "step": 266470 }, { "epoch": 64.01, "learning_rate": 1.342306795568155e-05, "loss": 0.0017, "step": 266480 }, { "epoch": 64.01, "learning_rate": 1.3420008891045105e-05, "loss": 0.0016, "step": 266490 }, { "epoch": 64.02, "learning_rate": 1.3416950120992377e-05, "loss": 0.0013, "step": 266500 }, { "epoch": 64.02, "learning_rate": 1.3413891645548e-05, "loss": 0.0013, "step": 266510 }, { "epoch": 64.02, "learning_rate": 1.34108334647366e-05, "loss": 0.0023, "step": 266520 }, { "epoch": 64.02, "learning_rate": 1.34077755785828e-05, "loss": 0.0013, "step": 266530 }, { "epoch": 64.02, "learning_rate": 1.3404717987111248e-05, "loss": 0.0016, "step": 266540 }, { "epoch": 64.03, "learning_rate": 1.3401660690346573e-05, "loss": 0.0016, "step": 266550 }, { "epoch": 64.03, "learning_rate": 1.3398603688313344e-05, "loss": 0.0037, "step": 266560 }, { "epoch": 64.03, "learning_rate": 1.3395546981036228e-05, "loss": 0.0033, "step": 266570 }, { "epoch": 64.03, "learning_rate": 1.3392490568539822e-05, "loss": 0.0012, "step": 266580 }, { "epoch": 64.04, "learning_rate": 1.3389434450848749e-05, "loss": 0.0023, "step": 266590 }, { "epoch": 64.04, "learning_rate": 1.338637862798761e-05, "loss": 0.0015, "step": 266600 }, { "epoch": 64.04, "learning_rate": 1.338332309998102e-05, "loss": 0.0022, "step": 266610 }, { "epoch": 64.04, "learning_rate": 1.338026786685359e-05, "loss": 0.0018, "step": 266620 }, { "epoch": 64.05, "learning_rate": 1.33772129286299e-05, "loss": 0.0013, "step": 266630 }, { "epoch": 64.05, "learning_rate": 1.3374158285334598e-05, "loss": 0.0024, "step": 266640 }, { "epoch": 64.05, "learning_rate": 1.337110393699224e-05, "loss": 0.0078, "step": 266650 }, { "epoch": 64.05, "learning_rate": 1.3368049883627443e-05, "loss": 0.0014, "step": 266660 }, { "epoch": 64.05, "learning_rate": 1.3364996125264784e-05, "loss": 0.0034, "step": 266670 }, { "epoch": 64.06, "learning_rate": 1.3361942661928877e-05, "loss": 0.0012, "step": 266680 }, { "epoch": 64.06, "learning_rate": 1.3358889493644327e-05, "loss": 0.0021, "step": 266690 }, { "epoch": 64.06, "learning_rate": 1.3355836620435664e-05, "loss": 0.0032, "step": 266700 }, { "epoch": 64.06, "learning_rate": 1.335278404232752e-05, "loss": 0.0011, "step": 266710 }, { "epoch": 64.07, "learning_rate": 1.334973175934447e-05, "loss": 0.0019, "step": 266720 }, { "epoch": 64.07, "learning_rate": 1.334667977151109e-05, "loss": 0.0015, "step": 266730 }, { "epoch": 64.07, "learning_rate": 1.3343628078851956e-05, "loss": 0.0011, "step": 266740 }, { "epoch": 64.07, "learning_rate": 1.3340576681391648e-05, "loss": 0.0014, "step": 266750 }, { "epoch": 64.07, "learning_rate": 1.3337525579154736e-05, "loss": 0.0015, "step": 266760 }, { "epoch": 64.08, "learning_rate": 1.3334474772165778e-05, "loss": 0.0019, "step": 266770 }, { "epoch": 64.08, "learning_rate": 1.3331424260449372e-05, "loss": 0.0024, "step": 266780 }, { "epoch": 64.08, "learning_rate": 1.3328374044030079e-05, "loss": 0.0016, "step": 266790 }, { "epoch": 64.08, "learning_rate": 1.3325324122932426e-05, "loss": 0.002, "step": 266800 }, { "epoch": 64.09, "learning_rate": 1.332227449718102e-05, "loss": 0.01, "step": 266810 }, { "epoch": 64.09, "learning_rate": 1.3319225166800392e-05, "loss": 0.0013, "step": 266820 }, { "epoch": 64.09, "learning_rate": 1.3316176131815117e-05, "loss": 0.0012, "step": 266830 }, { "epoch": 64.09, "learning_rate": 1.3313127392249735e-05, "loss": 0.0124, "step": 266840 }, { "epoch": 64.1, "learning_rate": 1.3310078948128808e-05, "loss": 0.0014, "step": 266850 }, { "epoch": 64.1, "learning_rate": 1.3307030799476872e-05, "loss": 0.0025, "step": 266860 }, { "epoch": 64.1, "learning_rate": 1.330398294631849e-05, "loss": 0.0037, "step": 266870 }, { "epoch": 64.1, "learning_rate": 1.3300935388678199e-05, "loss": 0.0023, "step": 266880 }, { "epoch": 64.1, "learning_rate": 1.3297888126580538e-05, "loss": 0.0013, "step": 266890 }, { "epoch": 64.11, "learning_rate": 1.3294841160050054e-05, "loss": 0.0011, "step": 266900 }, { "epoch": 64.11, "learning_rate": 1.3291794489111265e-05, "loss": 0.0018, "step": 266910 }, { "epoch": 64.11, "learning_rate": 1.3288748113788741e-05, "loss": 0.0012, "step": 266920 }, { "epoch": 64.11, "learning_rate": 1.3285702034107006e-05, "loss": 0.0025, "step": 266930 }, { "epoch": 64.12, "learning_rate": 1.3282656250090552e-05, "loss": 0.0011, "step": 266940 }, { "epoch": 64.12, "learning_rate": 1.3279610761763955e-05, "loss": 0.0019, "step": 266950 }, { "epoch": 64.12, "learning_rate": 1.3276565569151722e-05, "loss": 0.0015, "step": 266960 }, { "epoch": 64.12, "learning_rate": 1.3273520672278377e-05, "loss": 0.0033, "step": 266970 }, { "epoch": 64.13, "learning_rate": 1.3270476071168435e-05, "loss": 0.0014, "step": 266980 }, { "epoch": 64.13, "learning_rate": 1.3267431765846427e-05, "loss": 0.0019, "step": 266990 }, { "epoch": 64.13, "learning_rate": 1.326438775633686e-05, "loss": 0.002, "step": 267000 }, { "epoch": 64.13, "learning_rate": 1.3261344042664236e-05, "loss": 0.0021, "step": 267010 }, { "epoch": 64.13, "learning_rate": 1.325830062485311e-05, "loss": 0.0014, "step": 267020 }, { "epoch": 64.14, "learning_rate": 1.3255257502927943e-05, "loss": 0.0011, "step": 267030 }, { "epoch": 64.14, "learning_rate": 1.3252214676913249e-05, "loss": 0.0012, "step": 267040 }, { "epoch": 64.14, "learning_rate": 1.3249172146833555e-05, "loss": 0.002, "step": 267050 }, { "epoch": 64.14, "learning_rate": 1.324612991271335e-05, "loss": 0.0027, "step": 267060 }, { "epoch": 64.15, "learning_rate": 1.3243087974577156e-05, "loss": 0.0204, "step": 267070 }, { "epoch": 64.15, "learning_rate": 1.3240046332449418e-05, "loss": 0.0016, "step": 267080 }, { "epoch": 64.15, "learning_rate": 1.3237004986354673e-05, "loss": 0.0018, "step": 267090 }, { "epoch": 64.15, "learning_rate": 1.3233963936317406e-05, "loss": 0.0014, "step": 267100 }, { "epoch": 64.15, "learning_rate": 1.3230923182362104e-05, "loss": 0.002, "step": 267110 }, { "epoch": 64.16, "learning_rate": 1.3227882724513252e-05, "loss": 0.0013, "step": 267120 }, { "epoch": 64.16, "learning_rate": 1.3224842562795337e-05, "loss": 0.0021, "step": 267130 }, { "epoch": 64.16, "learning_rate": 1.3221802697232843e-05, "loss": 0.0021, "step": 267140 }, { "epoch": 64.16, "learning_rate": 1.3218763127850231e-05, "loss": 0.0016, "step": 267150 }, { "epoch": 64.17, "learning_rate": 1.3215723854672035e-05, "loss": 0.0088, "step": 267160 }, { "epoch": 64.17, "learning_rate": 1.321268487772267e-05, "loss": 0.0014, "step": 267170 }, { "epoch": 64.17, "learning_rate": 1.320964619702662e-05, "loss": 0.0009, "step": 267180 }, { "epoch": 64.17, "learning_rate": 1.3206607812608386e-05, "loss": 0.0015, "step": 267190 }, { "epoch": 64.18, "learning_rate": 1.3203569724492415e-05, "loss": 0.0025, "step": 267200 }, { "epoch": 64.18, "learning_rate": 1.320053193270318e-05, "loss": 0.0011, "step": 267210 }, { "epoch": 64.18, "learning_rate": 1.319749443726514e-05, "loss": 0.0013, "step": 267220 }, { "epoch": 64.18, "learning_rate": 1.3194457238202762e-05, "loss": 0.0013, "step": 267230 }, { "epoch": 64.18, "learning_rate": 1.31914203355405e-05, "loss": 0.0014, "step": 267240 }, { "epoch": 64.19, "learning_rate": 1.3188383729302795e-05, "loss": 0.0012, "step": 267250 }, { "epoch": 64.19, "learning_rate": 1.3185347419514149e-05, "loss": 0.0023, "step": 267260 }, { "epoch": 64.19, "learning_rate": 1.3182311406198966e-05, "loss": 0.0063, "step": 267270 }, { "epoch": 64.19, "learning_rate": 1.3179275689381699e-05, "loss": 0.0026, "step": 267280 }, { "epoch": 64.2, "learning_rate": 1.317624026908682e-05, "loss": 0.0021, "step": 267290 }, { "epoch": 64.2, "learning_rate": 1.317320514533878e-05, "loss": 0.0027, "step": 267300 }, { "epoch": 64.2, "learning_rate": 1.317017031816199e-05, "loss": 0.0015, "step": 267310 }, { "epoch": 64.2, "learning_rate": 1.3167135787580886e-05, "loss": 0.002, "step": 267320 }, { "epoch": 64.21, "learning_rate": 1.3164101553619934e-05, "loss": 0.0014, "step": 267330 }, { "epoch": 64.21, "learning_rate": 1.3161067616303563e-05, "loss": 0.0014, "step": 267340 }, { "epoch": 64.21, "learning_rate": 1.3158033975656198e-05, "loss": 0.0012, "step": 267350 }, { "epoch": 64.21, "learning_rate": 1.3155000631702275e-05, "loss": 0.0011, "step": 267360 }, { "epoch": 64.21, "learning_rate": 1.3151967584466213e-05, "loss": 0.0021, "step": 267370 }, { "epoch": 64.22, "learning_rate": 1.3148934833972448e-05, "loss": 0.0022, "step": 267380 }, { "epoch": 64.22, "learning_rate": 1.3145902380245378e-05, "loss": 0.0029, "step": 267390 }, { "epoch": 64.22, "learning_rate": 1.3142870223309478e-05, "loss": 0.0019, "step": 267400 }, { "epoch": 64.22, "learning_rate": 1.3139838363189117e-05, "loss": 0.0014, "step": 267410 }, { "epoch": 64.23, "learning_rate": 1.3136806799908714e-05, "loss": 0.0034, "step": 267420 }, { "epoch": 64.23, "learning_rate": 1.3133775533492708e-05, "loss": 0.0014, "step": 267430 }, { "epoch": 64.23, "learning_rate": 1.3130744563965497e-05, "loss": 0.0021, "step": 267440 }, { "epoch": 64.23, "learning_rate": 1.312771389135149e-05, "loss": 0.0012, "step": 267450 }, { "epoch": 64.23, "learning_rate": 1.3124683515675097e-05, "loss": 0.001, "step": 267460 }, { "epoch": 64.24, "learning_rate": 1.3121653436960713e-05, "loss": 0.0018, "step": 267470 }, { "epoch": 64.24, "learning_rate": 1.3118623655232748e-05, "loss": 0.0029, "step": 267480 }, { "epoch": 64.24, "learning_rate": 1.31155941705156e-05, "loss": 0.0012, "step": 267490 }, { "epoch": 64.24, "learning_rate": 1.3112564982833659e-05, "loss": 0.0013, "step": 267500 }, { "epoch": 64.25, "learning_rate": 1.3109536092211328e-05, "loss": 0.0018, "step": 267510 }, { "epoch": 64.25, "learning_rate": 1.3106507498672999e-05, "loss": 0.0016, "step": 267520 }, { "epoch": 64.25, "learning_rate": 1.3103479202243041e-05, "loss": 0.0013, "step": 267530 }, { "epoch": 64.25, "learning_rate": 1.3100451202945891e-05, "loss": 0.0014, "step": 267540 }, { "epoch": 64.26, "learning_rate": 1.3097423500805883e-05, "loss": 0.0027, "step": 267550 }, { "epoch": 64.26, "learning_rate": 1.3094396095847406e-05, "loss": 0.0052, "step": 267560 }, { "epoch": 64.26, "learning_rate": 1.3091368988094865e-05, "loss": 0.0038, "step": 267570 }, { "epoch": 64.26, "learning_rate": 1.3088342177572627e-05, "loss": 0.0018, "step": 267580 }, { "epoch": 64.26, "learning_rate": 1.3085315664305065e-05, "loss": 0.0015, "step": 267590 }, { "epoch": 64.27, "learning_rate": 1.3082289448316548e-05, "loss": 0.0012, "step": 267600 }, { "epoch": 64.27, "learning_rate": 1.3079263529631458e-05, "loss": 0.0106, "step": 267610 }, { "epoch": 64.27, "learning_rate": 1.3076237908274153e-05, "loss": 0.0016, "step": 267620 }, { "epoch": 64.27, "learning_rate": 1.3073212584269002e-05, "loss": 0.0014, "step": 267630 }, { "epoch": 64.28, "learning_rate": 1.3070187557640368e-05, "loss": 0.0046, "step": 267640 }, { "epoch": 64.28, "learning_rate": 1.306716282841261e-05, "loss": 0.0041, "step": 267650 }, { "epoch": 64.28, "learning_rate": 1.3064138396610075e-05, "loss": 0.0022, "step": 267660 }, { "epoch": 64.28, "learning_rate": 1.3061114262257151e-05, "loss": 0.0031, "step": 267670 }, { "epoch": 64.29, "learning_rate": 1.3058090425378183e-05, "loss": 0.0014, "step": 267680 }, { "epoch": 64.29, "learning_rate": 1.3055066885997486e-05, "loss": 0.0039, "step": 267690 }, { "epoch": 64.29, "learning_rate": 1.305204364413945e-05, "loss": 0.0013, "step": 267700 }, { "epoch": 64.29, "learning_rate": 1.3049020699828412e-05, "loss": 0.0011, "step": 267710 }, { "epoch": 64.29, "learning_rate": 1.3045998053088704e-05, "loss": 0.0031, "step": 267720 }, { "epoch": 64.3, "learning_rate": 1.3042975703944681e-05, "loss": 0.0011, "step": 267730 }, { "epoch": 64.3, "learning_rate": 1.3039953652420679e-05, "loss": 0.0014, "step": 267740 }, { "epoch": 64.3, "learning_rate": 1.3036931898541028e-05, "loss": 0.0028, "step": 267750 }, { "epoch": 64.3, "learning_rate": 1.3033910442330066e-05, "loss": 0.0012, "step": 267760 }, { "epoch": 64.31, "learning_rate": 1.3030889283812115e-05, "loss": 0.0025, "step": 267770 }, { "epoch": 64.31, "learning_rate": 1.3027868423011547e-05, "loss": 0.0019, "step": 267780 }, { "epoch": 64.31, "learning_rate": 1.3024847859952644e-05, "loss": 0.0115, "step": 267790 }, { "epoch": 64.31, "learning_rate": 1.302182759465973e-05, "loss": 0.0017, "step": 267800 }, { "epoch": 64.31, "learning_rate": 1.3018807627157159e-05, "loss": 0.0018, "step": 267810 }, { "epoch": 64.32, "learning_rate": 1.301578795746925e-05, "loss": 0.0012, "step": 267820 }, { "epoch": 64.32, "learning_rate": 1.3012768585620278e-05, "loss": 0.0038, "step": 267830 }, { "epoch": 64.32, "learning_rate": 1.30097495116346e-05, "loss": 0.0014, "step": 267840 }, { "epoch": 64.32, "learning_rate": 1.3006730735536515e-05, "loss": 0.0013, "step": 267850 }, { "epoch": 64.33, "learning_rate": 1.3003712257350337e-05, "loss": 0.0024, "step": 267860 }, { "epoch": 64.33, "learning_rate": 1.3000694077100367e-05, "loss": 0.0012, "step": 267870 }, { "epoch": 64.33, "learning_rate": 1.299767619481092e-05, "loss": 0.0032, "step": 267880 }, { "epoch": 64.33, "learning_rate": 1.29946586105063e-05, "loss": 0.0057, "step": 267890 }, { "epoch": 64.34, "learning_rate": 1.299164132421078e-05, "loss": 0.0023, "step": 267900 }, { "epoch": 64.34, "learning_rate": 1.2988624335948702e-05, "loss": 0.0012, "step": 267910 }, { "epoch": 64.34, "learning_rate": 1.2985607645744352e-05, "loss": 0.0015, "step": 267920 }, { "epoch": 64.34, "learning_rate": 1.2982591253622e-05, "loss": 0.0019, "step": 267930 }, { "epoch": 64.34, "learning_rate": 1.2979575159605939e-05, "loss": 0.0012, "step": 267940 }, { "epoch": 64.35, "learning_rate": 1.2976559363720486e-05, "loss": 0.002, "step": 267950 }, { "epoch": 64.35, "learning_rate": 1.2973543865989924e-05, "loss": 0.0014, "step": 267960 }, { "epoch": 64.35, "learning_rate": 1.2970528666438498e-05, "loss": 0.004, "step": 267970 }, { "epoch": 64.35, "learning_rate": 1.2967513765090527e-05, "loss": 0.0049, "step": 267980 }, { "epoch": 64.36, "learning_rate": 1.2964499161970284e-05, "loss": 0.0012, "step": 267990 }, { "epoch": 64.36, "learning_rate": 1.296148485710204e-05, "loss": 0.0016, "step": 268000 }, { "epoch": 64.36, "learning_rate": 1.2958470850510074e-05, "loss": 0.0028, "step": 268010 }, { "epoch": 64.36, "learning_rate": 1.2955457142218657e-05, "loss": 0.0029, "step": 268020 }, { "epoch": 64.37, "learning_rate": 1.2952443732252057e-05, "loss": 0.0013, "step": 268030 }, { "epoch": 64.37, "learning_rate": 1.2949430620634522e-05, "loss": 0.0017, "step": 268040 }, { "epoch": 64.37, "learning_rate": 1.294641780739036e-05, "loss": 0.0012, "step": 268050 }, { "epoch": 64.37, "learning_rate": 1.2943405292543825e-05, "loss": 0.0011, "step": 268060 }, { "epoch": 64.37, "learning_rate": 1.2940393076119129e-05, "loss": 0.0017, "step": 268070 }, { "epoch": 64.38, "learning_rate": 1.2937381158140583e-05, "loss": 0.0018, "step": 268080 }, { "epoch": 64.38, "learning_rate": 1.2934369538632418e-05, "loss": 0.0014, "step": 268090 }, { "epoch": 64.38, "learning_rate": 1.29313582176189e-05, "loss": 0.0048, "step": 268100 }, { "epoch": 64.38, "learning_rate": 1.2928347195124263e-05, "loss": 0.0021, "step": 268110 }, { "epoch": 64.39, "learning_rate": 1.2925336471172771e-05, "loss": 0.0071, "step": 268120 }, { "epoch": 64.39, "learning_rate": 1.2922326045788662e-05, "loss": 0.0017, "step": 268130 }, { "epoch": 64.39, "learning_rate": 1.2919315918996161e-05, "loss": 0.0015, "step": 268140 }, { "epoch": 64.39, "learning_rate": 1.2916306090819564e-05, "loss": 0.001, "step": 268150 }, { "epoch": 64.39, "learning_rate": 1.2913296561283057e-05, "loss": 0.0024, "step": 268160 }, { "epoch": 64.4, "learning_rate": 1.2910287330410892e-05, "loss": 0.003, "step": 268170 }, { "epoch": 64.4, "learning_rate": 1.2907278398227284e-05, "loss": 0.0014, "step": 268180 }, { "epoch": 64.4, "learning_rate": 1.2904269764756505e-05, "loss": 0.0013, "step": 268190 }, { "epoch": 64.4, "learning_rate": 1.2901261430022776e-05, "loss": 0.0014, "step": 268200 }, { "epoch": 64.41, "learning_rate": 1.289825339405028e-05, "loss": 0.0013, "step": 268210 }, { "epoch": 64.41, "learning_rate": 1.2895245656863291e-05, "loss": 0.0011, "step": 268220 }, { "epoch": 64.41, "learning_rate": 1.2892238218486008e-05, "loss": 0.0023, "step": 268230 }, { "epoch": 64.41, "learning_rate": 1.2889231078942654e-05, "loss": 0.0011, "step": 268240 }, { "epoch": 64.42, "learning_rate": 1.2886224238257443e-05, "loss": 0.0011, "step": 268250 }, { "epoch": 64.42, "learning_rate": 1.2883217696454596e-05, "loss": 0.0022, "step": 268260 }, { "epoch": 64.42, "learning_rate": 1.2880211453558322e-05, "loss": 0.0012, "step": 268270 }, { "epoch": 64.42, "learning_rate": 1.287720550959281e-05, "loss": 0.0017, "step": 268280 }, { "epoch": 64.42, "learning_rate": 1.287419986458232e-05, "loss": 0.0011, "step": 268290 }, { "epoch": 64.43, "learning_rate": 1.2871194518551005e-05, "loss": 0.002, "step": 268300 }, { "epoch": 64.43, "learning_rate": 1.2868189471523079e-05, "loss": 0.0012, "step": 268310 }, { "epoch": 64.43, "learning_rate": 1.2865184723522761e-05, "loss": 0.0024, "step": 268320 }, { "epoch": 64.43, "learning_rate": 1.2862180274574236e-05, "loss": 0.0012, "step": 268330 }, { "epoch": 64.44, "learning_rate": 1.2859176124701717e-05, "loss": 0.0015, "step": 268340 }, { "epoch": 64.44, "learning_rate": 1.2856172273929351e-05, "loss": 0.0017, "step": 268350 }, { "epoch": 64.44, "learning_rate": 1.2853168722281367e-05, "loss": 0.0018, "step": 268360 }, { "epoch": 64.44, "learning_rate": 1.2850165469781949e-05, "loss": 0.0012, "step": 268370 }, { "epoch": 64.45, "learning_rate": 1.2847162516455274e-05, "loss": 0.0023, "step": 268380 }, { "epoch": 64.45, "learning_rate": 1.2844159862325533e-05, "loss": 0.0021, "step": 268390 }, { "epoch": 64.45, "learning_rate": 1.28411575074169e-05, "loss": 0.0027, "step": 268400 }, { "epoch": 64.45, "learning_rate": 1.2838155451753559e-05, "loss": 0.003, "step": 268410 }, { "epoch": 64.45, "learning_rate": 1.2835153695359664e-05, "loss": 0.0014, "step": 268420 }, { "epoch": 64.46, "learning_rate": 1.283215223825942e-05, "loss": 0.001, "step": 268430 }, { "epoch": 64.46, "learning_rate": 1.2829151080477004e-05, "loss": 0.0014, "step": 268440 }, { "epoch": 64.46, "learning_rate": 1.2826150222036537e-05, "loss": 0.0018, "step": 268450 }, { "epoch": 64.46, "learning_rate": 1.2823149662962225e-05, "loss": 0.0022, "step": 268460 }, { "epoch": 64.47, "learning_rate": 1.2820149403278226e-05, "loss": 0.0012, "step": 268470 }, { "epoch": 64.47, "learning_rate": 1.2817149443008691e-05, "loss": 0.0023, "step": 268480 }, { "epoch": 64.47, "learning_rate": 1.2814149782177792e-05, "loss": 0.0051, "step": 268490 }, { "epoch": 64.47, "learning_rate": 1.2811150420809675e-05, "loss": 0.0017, "step": 268500 }, { "epoch": 64.47, "learning_rate": 1.28081513589285e-05, "loss": 0.0015, "step": 268510 }, { "epoch": 64.48, "learning_rate": 1.28051525965584e-05, "loss": 0.0014, "step": 268520 }, { "epoch": 64.48, "learning_rate": 1.280215413372357e-05, "loss": 0.0012, "step": 268530 }, { "epoch": 64.48, "learning_rate": 1.2799155970448112e-05, "loss": 0.0013, "step": 268540 }, { "epoch": 64.48, "learning_rate": 1.2796158106756178e-05, "loss": 0.0014, "step": 268550 }, { "epoch": 64.49, "learning_rate": 1.2793160542671928e-05, "loss": 0.0011, "step": 268560 }, { "epoch": 64.49, "learning_rate": 1.2790163278219497e-05, "loss": 0.0017, "step": 268570 }, { "epoch": 64.49, "learning_rate": 1.2787166313423033e-05, "loss": 0.0021, "step": 268580 }, { "epoch": 64.49, "learning_rate": 1.2784169648306621e-05, "loss": 0.0027, "step": 268590 }, { "epoch": 64.5, "learning_rate": 1.2781173282894449e-05, "loss": 0.0011, "step": 268600 }, { "epoch": 64.5, "learning_rate": 1.2778177217210625e-05, "loss": 0.0014, "step": 268610 }, { "epoch": 64.5, "learning_rate": 1.2775181451279278e-05, "loss": 0.0012, "step": 268620 }, { "epoch": 64.5, "learning_rate": 1.2772185985124536e-05, "loss": 0.0013, "step": 268630 }, { "epoch": 64.5, "learning_rate": 1.2769190818770521e-05, "loss": 0.0018, "step": 268640 }, { "epoch": 64.51, "learning_rate": 1.276619595224135e-05, "loss": 0.0015, "step": 268650 }, { "epoch": 64.51, "learning_rate": 1.276320138556113e-05, "loss": 0.0014, "step": 268660 }, { "epoch": 64.51, "learning_rate": 1.276020711875402e-05, "loss": 0.0015, "step": 268670 }, { "epoch": 64.51, "learning_rate": 1.2757213151844082e-05, "loss": 0.0015, "step": 268680 }, { "epoch": 64.52, "learning_rate": 1.275421948485544e-05, "loss": 0.0013, "step": 268690 }, { "epoch": 64.52, "learning_rate": 1.2751226117812226e-05, "loss": 0.0012, "step": 268700 }, { "epoch": 64.52, "learning_rate": 1.2748233050738528e-05, "loss": 0.002, "step": 268710 }, { "epoch": 64.52, "learning_rate": 1.2745240283658455e-05, "loss": 0.0012, "step": 268720 }, { "epoch": 64.53, "learning_rate": 1.2742247816596104e-05, "loss": 0.001, "step": 268730 }, { "epoch": 64.53, "learning_rate": 1.2739255649575571e-05, "loss": 0.0013, "step": 268740 }, { "epoch": 64.53, "learning_rate": 1.2736263782620961e-05, "loss": 0.0019, "step": 268750 }, { "epoch": 64.53, "learning_rate": 1.2733272215756348e-05, "loss": 0.0023, "step": 268760 }, { "epoch": 64.53, "learning_rate": 1.2730280949005868e-05, "loss": 0.002, "step": 268770 }, { "epoch": 64.54, "learning_rate": 1.2727289982393565e-05, "loss": 0.0015, "step": 268780 }, { "epoch": 64.54, "learning_rate": 1.2724299315943538e-05, "loss": 0.0024, "step": 268790 }, { "epoch": 64.54, "learning_rate": 1.2721308949679866e-05, "loss": 0.0022, "step": 268800 }, { "epoch": 64.54, "learning_rate": 1.2718318883626667e-05, "loss": 0.0016, "step": 268810 }, { "epoch": 64.55, "learning_rate": 1.2715329117807978e-05, "loss": 0.0018, "step": 268820 }, { "epoch": 64.55, "learning_rate": 1.2712339652247879e-05, "loss": 0.0012, "step": 268830 }, { "epoch": 64.55, "learning_rate": 1.2709350486970472e-05, "loss": 0.0016, "step": 268840 }, { "epoch": 64.55, "learning_rate": 1.2706361621999808e-05, "loss": 0.0013, "step": 268850 }, { "epoch": 64.55, "learning_rate": 1.2703373057359969e-05, "loss": 0.0015, "step": 268860 }, { "epoch": 64.56, "learning_rate": 1.270038479307501e-05, "loss": 0.0015, "step": 268870 }, { "epoch": 64.56, "learning_rate": 1.2697396829169006e-05, "loss": 0.0015, "step": 268880 }, { "epoch": 64.56, "learning_rate": 1.2694409165666015e-05, "loss": 0.0018, "step": 268890 }, { "epoch": 64.56, "learning_rate": 1.2691421802590082e-05, "loss": 0.0023, "step": 268900 }, { "epoch": 64.57, "learning_rate": 1.268843473996531e-05, "loss": 0.0022, "step": 268910 }, { "epoch": 64.57, "learning_rate": 1.2685447977815706e-05, "loss": 0.002, "step": 268920 }, { "epoch": 64.57, "learning_rate": 1.2682461516165328e-05, "loss": 0.0015, "step": 268930 }, { "epoch": 64.57, "learning_rate": 1.2679475355038255e-05, "loss": 0.0032, "step": 268940 }, { "epoch": 64.58, "learning_rate": 1.2676489494458537e-05, "loss": 0.0012, "step": 268950 }, { "epoch": 64.58, "learning_rate": 1.2673503934450171e-05, "loss": 0.001, "step": 268960 }, { "epoch": 64.58, "learning_rate": 1.267051867503724e-05, "loss": 0.0012, "step": 268970 }, { "epoch": 64.58, "learning_rate": 1.2667533716243785e-05, "loss": 0.0014, "step": 268980 }, { "epoch": 64.58, "learning_rate": 1.2664549058093827e-05, "loss": 0.0014, "step": 268990 }, { "epoch": 64.59, "learning_rate": 1.266156470061141e-05, "loss": 0.0012, "step": 269000 }, { "epoch": 64.59, "learning_rate": 1.2658580643820573e-05, "loss": 0.0014, "step": 269010 }, { "epoch": 64.59, "learning_rate": 1.265559688774534e-05, "loss": 0.0016, "step": 269020 }, { "epoch": 64.59, "learning_rate": 1.2652613432409737e-05, "loss": 0.0043, "step": 269030 }, { "epoch": 64.6, "learning_rate": 1.2649630277837788e-05, "loss": 0.0012, "step": 269040 }, { "epoch": 64.6, "learning_rate": 1.2646647424053542e-05, "loss": 0.0023, "step": 269050 }, { "epoch": 64.6, "learning_rate": 1.264366487108099e-05, "loss": 0.0014, "step": 269060 }, { "epoch": 64.6, "learning_rate": 1.2640682618944149e-05, "loss": 0.0025, "step": 269070 }, { "epoch": 64.61, "learning_rate": 1.2637700667667062e-05, "loss": 0.0012, "step": 269080 }, { "epoch": 64.61, "learning_rate": 1.2634719017273732e-05, "loss": 0.0014, "step": 269090 }, { "epoch": 64.61, "learning_rate": 1.2631737667788168e-05, "loss": 0.0024, "step": 269100 }, { "epoch": 64.61, "learning_rate": 1.2628756619234378e-05, "loss": 0.0014, "step": 269110 }, { "epoch": 64.61, "learning_rate": 1.2625775871636375e-05, "loss": 0.0013, "step": 269120 }, { "epoch": 64.62, "learning_rate": 1.2622795425018153e-05, "loss": 0.0025, "step": 269130 }, { "epoch": 64.62, "learning_rate": 1.2619815279403718e-05, "loss": 0.0019, "step": 269140 }, { "epoch": 64.62, "learning_rate": 1.2616835434817076e-05, "loss": 0.0026, "step": 269150 }, { "epoch": 64.62, "learning_rate": 1.2613855891282218e-05, "loss": 0.0014, "step": 269160 }, { "epoch": 64.63, "learning_rate": 1.2610876648823129e-05, "loss": 0.0023, "step": 269170 }, { "epoch": 64.63, "learning_rate": 1.2607897707463822e-05, "loss": 0.0023, "step": 269180 }, { "epoch": 64.63, "learning_rate": 1.2604919067228294e-05, "loss": 0.0025, "step": 269190 }, { "epoch": 64.63, "learning_rate": 1.2601940728140482e-05, "loss": 0.0017, "step": 269200 }, { "epoch": 64.63, "learning_rate": 1.259896269022442e-05, "loss": 0.0033, "step": 269210 }, { "epoch": 64.64, "learning_rate": 1.2595984953504081e-05, "loss": 0.0032, "step": 269220 }, { "epoch": 64.64, "learning_rate": 1.2593007518003436e-05, "loss": 0.0015, "step": 269230 }, { "epoch": 64.64, "learning_rate": 1.259003038374646e-05, "loss": 0.0022, "step": 269240 }, { "epoch": 64.64, "learning_rate": 1.2587053550757138e-05, "loss": 0.0018, "step": 269250 }, { "epoch": 64.65, "learning_rate": 1.2584077019059443e-05, "loss": 0.0015, "step": 269260 }, { "epoch": 64.65, "learning_rate": 1.2581100788677341e-05, "loss": 0.0029, "step": 269270 }, { "epoch": 64.65, "learning_rate": 1.2578124859634793e-05, "loss": 0.0028, "step": 269280 }, { "epoch": 64.65, "learning_rate": 1.257514923195578e-05, "loss": 0.0023, "step": 269290 }, { "epoch": 64.66, "learning_rate": 1.2572173905664254e-05, "loss": 0.0013, "step": 269300 }, { "epoch": 64.66, "learning_rate": 1.256919888078416e-05, "loss": 0.0044, "step": 269310 }, { "epoch": 64.66, "learning_rate": 1.2566224157339496e-05, "loss": 0.0036, "step": 269320 }, { "epoch": 64.66, "learning_rate": 1.256324973535421e-05, "loss": 0.0022, "step": 269330 }, { "epoch": 64.66, "learning_rate": 1.2560275614852213e-05, "loss": 0.0018, "step": 269340 }, { "epoch": 64.67, "learning_rate": 1.2557301795857495e-05, "loss": 0.0014, "step": 269350 }, { "epoch": 64.67, "learning_rate": 1.2554328278394001e-05, "loss": 0.0026, "step": 269360 }, { "epoch": 64.67, "learning_rate": 1.255135506248567e-05, "loss": 0.0015, "step": 269370 }, { "epoch": 64.67, "learning_rate": 1.2548382148156446e-05, "loss": 0.0037, "step": 269380 }, { "epoch": 64.68, "learning_rate": 1.254540953543027e-05, "loss": 0.0045, "step": 269390 }, { "epoch": 64.68, "learning_rate": 1.2542437224331082e-05, "loss": 0.0018, "step": 269400 }, { "epoch": 64.68, "learning_rate": 1.2539465214882806e-05, "loss": 0.0013, "step": 269410 }, { "epoch": 64.68, "learning_rate": 1.2536493507109403e-05, "loss": 0.0017, "step": 269420 }, { "epoch": 64.69, "learning_rate": 1.25335221010348e-05, "loss": 0.002, "step": 269430 }, { "epoch": 64.69, "learning_rate": 1.2530550996682905e-05, "loss": 0.0014, "step": 269440 }, { "epoch": 64.69, "learning_rate": 1.2527580194077642e-05, "loss": 0.0018, "step": 269450 }, { "epoch": 64.69, "learning_rate": 1.2524609693242962e-05, "loss": 0.0031, "step": 269460 }, { "epoch": 64.69, "learning_rate": 1.2521639494202792e-05, "loss": 0.0019, "step": 269470 }, { "epoch": 64.7, "learning_rate": 1.2518669596980997e-05, "loss": 0.0014, "step": 269480 }, { "epoch": 64.7, "learning_rate": 1.2515700001601549e-05, "loss": 0.0034, "step": 269490 }, { "epoch": 64.7, "learning_rate": 1.2512730708088344e-05, "loss": 0.0102, "step": 269500 }, { "epoch": 64.7, "learning_rate": 1.2509761716465295e-05, "loss": 0.0041, "step": 269510 }, { "epoch": 64.71, "learning_rate": 1.2506793026756313e-05, "loss": 0.0016, "step": 269520 }, { "epoch": 64.71, "learning_rate": 1.25038246389853e-05, "loss": 0.0016, "step": 269530 }, { "epoch": 64.71, "learning_rate": 1.250085655317616e-05, "loss": 0.0029, "step": 269540 }, { "epoch": 64.71, "learning_rate": 1.2497888769352789e-05, "loss": 0.0023, "step": 269550 }, { "epoch": 64.71, "learning_rate": 1.2494921287539114e-05, "loss": 0.0016, "step": 269560 }, { "epoch": 64.72, "learning_rate": 1.2491954107759024e-05, "loss": 0.0013, "step": 269570 }, { "epoch": 64.72, "learning_rate": 1.248898723003638e-05, "loss": 0.0017, "step": 269580 }, { "epoch": 64.72, "learning_rate": 1.2486020654395119e-05, "loss": 0.0013, "step": 269590 }, { "epoch": 64.72, "learning_rate": 1.248305438085911e-05, "loss": 0.0024, "step": 269600 }, { "epoch": 64.73, "learning_rate": 1.248008840945224e-05, "loss": 0.0017, "step": 269610 }, { "epoch": 64.73, "learning_rate": 1.2477122740198404e-05, "loss": 0.0022, "step": 269620 }, { "epoch": 64.73, "learning_rate": 1.2474157373121475e-05, "loss": 0.0018, "step": 269630 }, { "epoch": 64.73, "learning_rate": 1.2471192308245339e-05, "loss": 0.002, "step": 269640 }, { "epoch": 64.74, "learning_rate": 1.246822754559387e-05, "loss": 0.0039, "step": 269650 }, { "epoch": 64.74, "learning_rate": 1.2465263085190948e-05, "loss": 0.0015, "step": 269660 }, { "epoch": 64.74, "learning_rate": 1.2462298927060444e-05, "loss": 0.002, "step": 269670 }, { "epoch": 64.74, "learning_rate": 1.245933507122623e-05, "loss": 0.0044, "step": 269680 }, { "epoch": 64.74, "learning_rate": 1.2456371517712157e-05, "loss": 0.0015, "step": 269690 }, { "epoch": 64.75, "learning_rate": 1.2453408266542128e-05, "loss": 0.0017, "step": 269700 }, { "epoch": 64.75, "learning_rate": 1.2450445317739995e-05, "loss": 0.0014, "step": 269710 }, { "epoch": 64.75, "learning_rate": 1.244748267132958e-05, "loss": 0.0012, "step": 269720 }, { "epoch": 64.75, "learning_rate": 1.2444520327334785e-05, "loss": 0.0045, "step": 269730 }, { "epoch": 64.76, "learning_rate": 1.2441558285779458e-05, "loss": 0.0014, "step": 269740 }, { "epoch": 64.76, "learning_rate": 1.2438596546687442e-05, "loss": 0.0016, "step": 269750 }, { "epoch": 64.76, "learning_rate": 1.24356351100826e-05, "loss": 0.0118, "step": 269760 }, { "epoch": 64.76, "learning_rate": 1.2432673975988768e-05, "loss": 0.0019, "step": 269770 }, { "epoch": 64.77, "learning_rate": 1.24297131444298e-05, "loss": 0.0012, "step": 269780 }, { "epoch": 64.77, "learning_rate": 1.2426752615429526e-05, "loss": 0.0057, "step": 269790 }, { "epoch": 64.77, "learning_rate": 1.2423792389011835e-05, "loss": 0.0013, "step": 269800 }, { "epoch": 64.77, "learning_rate": 1.242083246520051e-05, "loss": 0.0012, "step": 269810 }, { "epoch": 64.77, "learning_rate": 1.2417872844019396e-05, "loss": 0.0026, "step": 269820 }, { "epoch": 64.78, "learning_rate": 1.2414913525492355e-05, "loss": 0.0013, "step": 269830 }, { "epoch": 64.78, "learning_rate": 1.2411954509643204e-05, "loss": 0.0013, "step": 269840 }, { "epoch": 64.78, "learning_rate": 1.2408995796495788e-05, "loss": 0.0047, "step": 269850 }, { "epoch": 64.78, "learning_rate": 1.2406037386073893e-05, "loss": 0.0012, "step": 269860 }, { "epoch": 64.79, "learning_rate": 1.240307927840138e-05, "loss": 0.0013, "step": 269870 }, { "epoch": 64.79, "learning_rate": 1.2400121473502057e-05, "loss": 0.0014, "step": 269880 }, { "epoch": 64.79, "learning_rate": 1.239716397139975e-05, "loss": 0.0019, "step": 269890 }, { "epoch": 64.79, "learning_rate": 1.2394206772118277e-05, "loss": 0.0014, "step": 269900 }, { "epoch": 64.79, "learning_rate": 1.2391249875681443e-05, "loss": 0.0011, "step": 269910 }, { "epoch": 64.8, "learning_rate": 1.2388293282113067e-05, "loss": 0.0017, "step": 269920 }, { "epoch": 64.8, "learning_rate": 1.2385336991436947e-05, "loss": 0.0018, "step": 269930 }, { "epoch": 64.8, "learning_rate": 1.2382381003676924e-05, "loss": 0.0014, "step": 269940 }, { "epoch": 64.8, "learning_rate": 1.2379425318856768e-05, "loss": 0.0012, "step": 269950 }, { "epoch": 64.81, "learning_rate": 1.2376469937000285e-05, "loss": 0.002, "step": 269960 }, { "epoch": 64.81, "learning_rate": 1.237351485813129e-05, "loss": 0.0025, "step": 269970 }, { "epoch": 64.81, "learning_rate": 1.237056008227358e-05, "loss": 0.0012, "step": 269980 }, { "epoch": 64.81, "learning_rate": 1.2367605609450945e-05, "loss": 0.0047, "step": 269990 }, { "epoch": 64.82, "learning_rate": 1.2364651439687174e-05, "loss": 0.0014, "step": 270000 }, { "epoch": 64.82, "learning_rate": 1.236169757300606e-05, "loss": 0.0024, "step": 270010 }, { "epoch": 64.82, "learning_rate": 1.2358744009431395e-05, "loss": 0.0015, "step": 270020 }, { "epoch": 64.82, "learning_rate": 1.2355790748986944e-05, "loss": 0.0011, "step": 270030 }, { "epoch": 64.82, "learning_rate": 1.2352837791696542e-05, "loss": 0.0015, "step": 270040 }, { "epoch": 64.83, "learning_rate": 1.2349885137583916e-05, "loss": 0.0049, "step": 270050 }, { "epoch": 64.83, "learning_rate": 1.2346932786672844e-05, "loss": 0.0014, "step": 270060 }, { "epoch": 64.83, "learning_rate": 1.2343980738987143e-05, "loss": 0.0012, "step": 270070 }, { "epoch": 64.83, "learning_rate": 1.2341028994550558e-05, "loss": 0.0015, "step": 270080 }, { "epoch": 64.84, "learning_rate": 1.2338077553386884e-05, "loss": 0.0019, "step": 270090 }, { "epoch": 64.84, "learning_rate": 1.2335126415519843e-05, "loss": 0.0016, "step": 270100 }, { "epoch": 64.84, "learning_rate": 1.2332175580973238e-05, "loss": 0.0111, "step": 270110 }, { "epoch": 64.84, "learning_rate": 1.2329225049770826e-05, "loss": 0.0017, "step": 270120 }, { "epoch": 64.85, "learning_rate": 1.2326274821936367e-05, "loss": 0.0012, "step": 270130 }, { "epoch": 64.85, "learning_rate": 1.2323324897493615e-05, "loss": 0.0013, "step": 270140 }, { "epoch": 64.85, "learning_rate": 1.2320375276466334e-05, "loss": 0.0013, "step": 270150 }, { "epoch": 64.85, "learning_rate": 1.2317425958878271e-05, "loss": 0.0023, "step": 270160 }, { "epoch": 64.85, "learning_rate": 1.2314476944753161e-05, "loss": 0.002, "step": 270170 }, { "epoch": 64.86, "learning_rate": 1.2311528234114805e-05, "loss": 0.0013, "step": 270180 }, { "epoch": 64.86, "learning_rate": 1.23085798269869e-05, "loss": 0.0018, "step": 270190 }, { "epoch": 64.86, "learning_rate": 1.2305631723393185e-05, "loss": 0.0011, "step": 270200 }, { "epoch": 64.86, "learning_rate": 1.2302683923357445e-05, "loss": 0.0015, "step": 270210 }, { "epoch": 64.87, "learning_rate": 1.2299736426903391e-05, "loss": 0.0014, "step": 270220 }, { "epoch": 64.87, "learning_rate": 1.2296789234054762e-05, "loss": 0.0013, "step": 270230 }, { "epoch": 64.87, "learning_rate": 1.22938423448353e-05, "loss": 0.0011, "step": 270240 }, { "epoch": 64.87, "learning_rate": 1.2290895759268729e-05, "loss": 0.0021, "step": 270250 }, { "epoch": 64.87, "learning_rate": 1.2287949477378779e-05, "loss": 0.0018, "step": 270260 }, { "epoch": 64.88, "learning_rate": 1.2285003499189179e-05, "loss": 0.0021, "step": 270270 }, { "epoch": 64.88, "learning_rate": 1.2282057824723652e-05, "loss": 0.0012, "step": 270280 }, { "epoch": 64.88, "learning_rate": 1.227911245400592e-05, "loss": 0.0032, "step": 270290 }, { "epoch": 64.88, "learning_rate": 1.2276167387059706e-05, "loss": 0.0013, "step": 270300 }, { "epoch": 64.89, "learning_rate": 1.2273222623908709e-05, "loss": 0.0016, "step": 270310 }, { "epoch": 64.89, "learning_rate": 1.2270278164576687e-05, "loss": 0.0013, "step": 270320 }, { "epoch": 64.89, "learning_rate": 1.2267334009087312e-05, "loss": 0.0073, "step": 270330 }, { "epoch": 64.89, "learning_rate": 1.2264390157464289e-05, "loss": 0.0017, "step": 270340 }, { "epoch": 64.9, "learning_rate": 1.2261446609731353e-05, "loss": 0.0013, "step": 270350 }, { "epoch": 64.9, "learning_rate": 1.22585033659122e-05, "loss": 0.0013, "step": 270360 }, { "epoch": 64.9, "learning_rate": 1.2255560426030532e-05, "loss": 0.0018, "step": 270370 }, { "epoch": 64.9, "learning_rate": 1.2252617790110043e-05, "loss": 0.0011, "step": 270380 }, { "epoch": 64.9, "learning_rate": 1.2249675458174437e-05, "loss": 0.0016, "step": 270390 }, { "epoch": 64.91, "learning_rate": 1.2246733430247409e-05, "loss": 0.0015, "step": 270400 }, { "epoch": 64.91, "learning_rate": 1.2243791706352631e-05, "loss": 0.0022, "step": 270410 }, { "epoch": 64.91, "learning_rate": 1.224085028651384e-05, "loss": 0.0014, "step": 270420 }, { "epoch": 64.91, "learning_rate": 1.223790917075468e-05, "loss": 0.0016, "step": 270430 }, { "epoch": 64.92, "learning_rate": 1.2234968359098837e-05, "loss": 0.0015, "step": 270440 }, { "epoch": 64.92, "learning_rate": 1.2232027851570021e-05, "loss": 0.0019, "step": 270450 }, { "epoch": 64.92, "learning_rate": 1.2229087648191911e-05, "loss": 0.0029, "step": 270460 }, { "epoch": 64.92, "learning_rate": 1.2226147748988148e-05, "loss": 0.0019, "step": 270470 }, { "epoch": 64.93, "learning_rate": 1.2223208153982447e-05, "loss": 0.0011, "step": 270480 }, { "epoch": 64.93, "learning_rate": 1.2220268863198464e-05, "loss": 0.0012, "step": 270490 }, { "epoch": 64.93, "learning_rate": 1.2217329876659873e-05, "loss": 0.0014, "step": 270500 }, { "epoch": 64.93, "learning_rate": 1.221439119439034e-05, "loss": 0.002, "step": 270510 }, { "epoch": 64.93, "learning_rate": 1.2211452816413531e-05, "loss": 0.0013, "step": 270520 }, { "epoch": 64.94, "learning_rate": 1.2208514742753108e-05, "loss": 0.0013, "step": 270530 }, { "epoch": 64.94, "learning_rate": 1.2205576973432736e-05, "loss": 0.0013, "step": 270540 }, { "epoch": 64.94, "learning_rate": 1.2202639508476054e-05, "loss": 0.0013, "step": 270550 }, { "epoch": 64.94, "learning_rate": 1.2199702347906767e-05, "loss": 0.0018, "step": 270560 }, { "epoch": 64.95, "learning_rate": 1.219676549174848e-05, "loss": 0.0098, "step": 270570 }, { "epoch": 64.95, "learning_rate": 1.2193828940024842e-05, "loss": 0.0027, "step": 270580 }, { "epoch": 64.95, "learning_rate": 1.2190892692759537e-05, "loss": 0.0011, "step": 270590 }, { "epoch": 65.0, "learning_rate": 1.2187956749976204e-05, "loss": 0.0018, "step": 270600 }, { "epoch": 65.0, "learning_rate": 1.2185021111698447e-05, "loss": 0.001, "step": 270610 }, { "epoch": 65.01, "learning_rate": 1.2182085777949954e-05, "loss": 0.0012, "step": 270620 }, { "epoch": 65.01, "learning_rate": 1.2179150748754342e-05, "loss": 0.0028, "step": 270630 }, { "epoch": 65.01, "learning_rate": 1.2176216024135251e-05, "loss": 0.0021, "step": 270640 }, { "epoch": 65.01, "learning_rate": 1.2173281604116316e-05, "loss": 0.002, "step": 270650 }, { "epoch": 65.01, "learning_rate": 1.2170347488721163e-05, "loss": 0.0016, "step": 270660 }, { "epoch": 65.02, "learning_rate": 1.2167413677973426e-05, "loss": 0.0025, "step": 270670 }, { "epoch": 65.02, "learning_rate": 1.2164480171896714e-05, "loss": 0.0012, "step": 270680 }, { "epoch": 65.02, "learning_rate": 1.216154697051468e-05, "loss": 0.0012, "step": 270690 }, { "epoch": 65.02, "learning_rate": 1.2158614073850955e-05, "loss": 0.0014, "step": 270700 }, { "epoch": 65.03, "learning_rate": 1.2155681481929115e-05, "loss": 0.0012, "step": 270710 }, { "epoch": 65.03, "learning_rate": 1.2152749194772784e-05, "loss": 0.0024, "step": 270720 }, { "epoch": 65.03, "learning_rate": 1.21498172124056e-05, "loss": 0.0015, "step": 270730 }, { "epoch": 65.03, "learning_rate": 1.2146885534851166e-05, "loss": 0.0012, "step": 270740 }, { "epoch": 65.04, "learning_rate": 1.2143954162133087e-05, "loss": 0.0035, "step": 270750 }, { "epoch": 65.04, "learning_rate": 1.2141023094274973e-05, "loss": 0.0014, "step": 270760 }, { "epoch": 65.04, "learning_rate": 1.2138092331300427e-05, "loss": 0.0016, "step": 270770 }, { "epoch": 65.04, "learning_rate": 1.2135161873233047e-05, "loss": 0.0015, "step": 270780 }, { "epoch": 65.04, "learning_rate": 1.2132231720096438e-05, "loss": 0.0023, "step": 270790 }, { "epoch": 65.05, "learning_rate": 1.21293018719142e-05, "loss": 0.0013, "step": 270800 }, { "epoch": 65.05, "learning_rate": 1.2126372328709917e-05, "loss": 0.0013, "step": 270810 }, { "epoch": 65.05, "learning_rate": 1.2123443090507175e-05, "loss": 0.0014, "step": 270820 }, { "epoch": 65.05, "learning_rate": 1.2120514157329582e-05, "loss": 0.0022, "step": 270830 }, { "epoch": 65.06, "learning_rate": 1.2117585529200742e-05, "loss": 0.0015, "step": 270840 }, { "epoch": 65.06, "learning_rate": 1.211465720614418e-05, "loss": 0.0011, "step": 270850 }, { "epoch": 65.06, "learning_rate": 1.2111729188183535e-05, "loss": 0.0016, "step": 270860 }, { "epoch": 65.06, "learning_rate": 1.2108801475342363e-05, "loss": 0.0032, "step": 270870 }, { "epoch": 65.07, "learning_rate": 1.210587406764424e-05, "loss": 0.0017, "step": 270880 }, { "epoch": 65.07, "learning_rate": 1.2102946965112748e-05, "loss": 0.0028, "step": 270890 }, { "epoch": 65.07, "learning_rate": 1.210002016777146e-05, "loss": 0.0011, "step": 270900 }, { "epoch": 65.07, "learning_rate": 1.2097093675643934e-05, "loss": 0.0019, "step": 270910 }, { "epoch": 65.07, "learning_rate": 1.2094167488753733e-05, "loss": 0.0033, "step": 270920 }, { "epoch": 65.08, "learning_rate": 1.2091241607124454e-05, "loss": 0.0014, "step": 270930 }, { "epoch": 65.08, "learning_rate": 1.208831603077965e-05, "loss": 0.0027, "step": 270940 }, { "epoch": 65.08, "learning_rate": 1.208539075974286e-05, "loss": 0.0013, "step": 270950 }, { "epoch": 65.08, "learning_rate": 1.2082465794037634e-05, "loss": 0.0029, "step": 270960 }, { "epoch": 65.09, "learning_rate": 1.2079541133687561e-05, "loss": 0.0022, "step": 270970 }, { "epoch": 65.09, "learning_rate": 1.2076616778716194e-05, "loss": 0.002, "step": 270980 }, { "epoch": 65.09, "learning_rate": 1.2073692729147041e-05, "loss": 0.0015, "step": 270990 }, { "epoch": 65.09, "learning_rate": 1.2070768985003688e-05, "loss": 0.0012, "step": 271000 }, { "epoch": 65.09, "learning_rate": 1.2067845546309669e-05, "loss": 0.0014, "step": 271010 }, { "epoch": 65.1, "learning_rate": 1.2064922413088524e-05, "loss": 0.0037, "step": 271020 }, { "epoch": 65.1, "learning_rate": 1.2061999585363804e-05, "loss": 0.0015, "step": 271030 }, { "epoch": 65.1, "learning_rate": 1.2059077063159035e-05, "loss": 0.0012, "step": 271040 }, { "epoch": 65.1, "learning_rate": 1.2056154846497752e-05, "loss": 0.0014, "step": 271050 }, { "epoch": 65.11, "learning_rate": 1.2053232935403486e-05, "loss": 0.0029, "step": 271060 }, { "epoch": 65.11, "learning_rate": 1.2050311329899782e-05, "loss": 0.0033, "step": 271070 }, { "epoch": 65.11, "learning_rate": 1.2047390030010174e-05, "loss": 0.0016, "step": 271080 }, { "epoch": 65.11, "learning_rate": 1.204446903575815e-05, "loss": 0.0022, "step": 271090 }, { "epoch": 65.12, "learning_rate": 1.204154834716727e-05, "loss": 0.0013, "step": 271100 }, { "epoch": 65.12, "learning_rate": 1.203862796426104e-05, "loss": 0.002, "step": 271110 }, { "epoch": 65.12, "learning_rate": 1.203570788706298e-05, "loss": 0.0013, "step": 271120 }, { "epoch": 65.12, "learning_rate": 1.203278811559661e-05, "loss": 0.0015, "step": 271130 }, { "epoch": 65.12, "learning_rate": 1.2029868649885435e-05, "loss": 0.003, "step": 271140 }, { "epoch": 65.13, "learning_rate": 1.2026949489952972e-05, "loss": 0.0018, "step": 271150 }, { "epoch": 65.13, "learning_rate": 1.2024030635822725e-05, "loss": 0.0034, "step": 271160 }, { "epoch": 65.13, "learning_rate": 1.2021112087518199e-05, "loss": 0.0013, "step": 271170 }, { "epoch": 65.13, "learning_rate": 1.2018193845062908e-05, "loss": 0.0049, "step": 271180 }, { "epoch": 65.14, "learning_rate": 1.2015275908480339e-05, "loss": 0.0015, "step": 271190 }, { "epoch": 65.14, "learning_rate": 1.201235827779399e-05, "loss": 0.0041, "step": 271200 }, { "epoch": 65.14, "learning_rate": 1.2009440953027374e-05, "loss": 0.0015, "step": 271210 }, { "epoch": 65.14, "learning_rate": 1.200652393420399e-05, "loss": 0.001, "step": 271220 }, { "epoch": 65.15, "learning_rate": 1.2003607221347286e-05, "loss": 0.0016, "step": 271230 }, { "epoch": 65.15, "learning_rate": 1.2000690814480791e-05, "loss": 0.0011, "step": 271240 }, { "epoch": 65.15, "learning_rate": 1.199777471362798e-05, "loss": 0.0043, "step": 271250 }, { "epoch": 65.15, "learning_rate": 1.1994858918812335e-05, "loss": 0.0013, "step": 271260 }, { "epoch": 65.15, "learning_rate": 1.199194343005734e-05, "loss": 0.0016, "step": 271270 }, { "epoch": 65.16, "learning_rate": 1.1989028247386475e-05, "loss": 0.0013, "step": 271280 }, { "epoch": 65.16, "learning_rate": 1.198611337082321e-05, "loss": 0.0013, "step": 271290 }, { "epoch": 65.16, "learning_rate": 1.1983198800391004e-05, "loss": 0.0015, "step": 271300 }, { "epoch": 65.16, "learning_rate": 1.1980284536113379e-05, "loss": 0.0014, "step": 271310 }, { "epoch": 65.17, "learning_rate": 1.1977370578013758e-05, "loss": 0.0011, "step": 271320 }, { "epoch": 65.17, "learning_rate": 1.1974456926115607e-05, "loss": 0.0027, "step": 271330 }, { "epoch": 65.17, "learning_rate": 1.1971543580442412e-05, "loss": 0.0015, "step": 271340 }, { "epoch": 65.17, "learning_rate": 1.1968630541017634e-05, "loss": 0.0012, "step": 271350 }, { "epoch": 65.17, "learning_rate": 1.196571780786474e-05, "loss": 0.0029, "step": 271360 }, { "epoch": 65.18, "learning_rate": 1.1962805381007136e-05, "loss": 0.0014, "step": 271370 }, { "epoch": 65.18, "learning_rate": 1.195989326046833e-05, "loss": 0.0012, "step": 271380 }, { "epoch": 65.18, "learning_rate": 1.1956981446271753e-05, "loss": 0.0024, "step": 271390 }, { "epoch": 65.18, "learning_rate": 1.195406993844086e-05, "loss": 0.0014, "step": 271400 }, { "epoch": 65.19, "learning_rate": 1.1951158736999097e-05, "loss": 0.0013, "step": 271410 }, { "epoch": 65.19, "learning_rate": 1.1948247841969901e-05, "loss": 0.0042, "step": 271420 }, { "epoch": 65.19, "learning_rate": 1.1945337253376715e-05, "loss": 0.004, "step": 271430 }, { "epoch": 65.19, "learning_rate": 1.1942426971242976e-05, "loss": 0.0015, "step": 271440 }, { "epoch": 65.2, "learning_rate": 1.1939516995592149e-05, "loss": 0.0014, "step": 271450 }, { "epoch": 65.2, "learning_rate": 1.1936607326447636e-05, "loss": 0.0013, "step": 271460 }, { "epoch": 65.2, "learning_rate": 1.1933697963832862e-05, "loss": 0.0012, "step": 271470 }, { "epoch": 65.2, "learning_rate": 1.193078890777129e-05, "loss": 0.0014, "step": 271480 }, { "epoch": 65.2, "learning_rate": 1.1927880158286326e-05, "loss": 0.0022, "step": 271490 }, { "epoch": 65.21, "learning_rate": 1.1924971715401406e-05, "loss": 0.0023, "step": 271500 }, { "epoch": 65.21, "learning_rate": 1.192206357913994e-05, "loss": 0.0021, "step": 271510 }, { "epoch": 65.21, "learning_rate": 1.1919155749525357e-05, "loss": 0.0012, "step": 271520 }, { "epoch": 65.21, "learning_rate": 1.1916248226581067e-05, "loss": 0.004, "step": 271530 }, { "epoch": 65.22, "learning_rate": 1.1913341010330475e-05, "loss": 0.0017, "step": 271540 }, { "epoch": 65.22, "learning_rate": 1.1910434100797036e-05, "loss": 0.0013, "step": 271550 }, { "epoch": 65.22, "learning_rate": 1.1907527498004112e-05, "loss": 0.0015, "step": 271560 }, { "epoch": 65.22, "learning_rate": 1.1904621201975113e-05, "loss": 0.0013, "step": 271570 }, { "epoch": 65.23, "learning_rate": 1.1901715212733478e-05, "loss": 0.0016, "step": 271580 }, { "epoch": 65.23, "learning_rate": 1.189880953030259e-05, "loss": 0.0011, "step": 271590 }, { "epoch": 65.23, "learning_rate": 1.1895904154705862e-05, "loss": 0.0018, "step": 271600 }, { "epoch": 65.23, "learning_rate": 1.1892999085966644e-05, "loss": 0.0012, "step": 271610 }, { "epoch": 65.23, "learning_rate": 1.1890094324108386e-05, "loss": 0.0013, "step": 271620 }, { "epoch": 65.24, "learning_rate": 1.1887189869154458e-05, "loss": 0.0018, "step": 271630 }, { "epoch": 65.24, "learning_rate": 1.1884285721128252e-05, "loss": 0.0013, "step": 271640 }, { "epoch": 65.24, "learning_rate": 1.188138188005316e-05, "loss": 0.0012, "step": 271650 }, { "epoch": 65.24, "learning_rate": 1.1878478345952553e-05, "loss": 0.0016, "step": 271660 }, { "epoch": 65.25, "learning_rate": 1.187557511884983e-05, "loss": 0.001, "step": 271670 }, { "epoch": 65.25, "learning_rate": 1.1872672198768347e-05, "loss": 0.0026, "step": 271680 }, { "epoch": 65.25, "learning_rate": 1.1869769585731528e-05, "loss": 0.0013, "step": 271690 }, { "epoch": 65.25, "learning_rate": 1.1866867279762705e-05, "loss": 0.0025, "step": 271700 }, { "epoch": 65.25, "learning_rate": 1.1863965280885247e-05, "loss": 0.0013, "step": 271710 }, { "epoch": 65.26, "learning_rate": 1.1861063589122561e-05, "loss": 0.0017, "step": 271720 }, { "epoch": 65.26, "learning_rate": 1.1858162204497991e-05, "loss": 0.0016, "step": 271730 }, { "epoch": 65.26, "learning_rate": 1.1855261127034911e-05, "loss": 0.0012, "step": 271740 }, { "epoch": 65.26, "learning_rate": 1.1852360356756675e-05, "loss": 0.0011, "step": 271750 }, { "epoch": 65.27, "learning_rate": 1.1849459893686648e-05, "loss": 0.0011, "step": 271760 }, { "epoch": 65.27, "learning_rate": 1.184655973784819e-05, "loss": 0.0072, "step": 271770 }, { "epoch": 65.27, "learning_rate": 1.1843659889264652e-05, "loss": 0.0011, "step": 271780 }, { "epoch": 65.27, "learning_rate": 1.184076034795939e-05, "loss": 0.0014, "step": 271790 }, { "epoch": 65.28, "learning_rate": 1.1837861113955751e-05, "loss": 0.0016, "step": 271800 }, { "epoch": 65.28, "learning_rate": 1.1834962187277088e-05, "loss": 0.0016, "step": 271810 }, { "epoch": 65.28, "learning_rate": 1.1832063567946728e-05, "loss": 0.0015, "step": 271820 }, { "epoch": 65.28, "learning_rate": 1.1829165255988055e-05, "loss": 0.0011, "step": 271830 }, { "epoch": 65.28, "learning_rate": 1.1826267251424372e-05, "loss": 0.001, "step": 271840 }, { "epoch": 65.29, "learning_rate": 1.1823369554279017e-05, "loss": 0.0015, "step": 271850 }, { "epoch": 65.29, "learning_rate": 1.1820472164575352e-05, "loss": 0.0026, "step": 271860 }, { "epoch": 65.29, "learning_rate": 1.181757508233669e-05, "loss": 0.0011, "step": 271870 }, { "epoch": 65.29, "learning_rate": 1.1814678307586375e-05, "loss": 0.0014, "step": 271880 }, { "epoch": 65.3, "learning_rate": 1.1811781840347718e-05, "loss": 0.0027, "step": 271890 }, { "epoch": 65.3, "learning_rate": 1.180888568064406e-05, "loss": 0.0011, "step": 271900 }, { "epoch": 65.3, "learning_rate": 1.180598982849872e-05, "loss": 0.0013, "step": 271910 }, { "epoch": 65.3, "learning_rate": 1.1803094283935001e-05, "loss": 0.0013, "step": 271920 }, { "epoch": 65.31, "learning_rate": 1.1800199046976262e-05, "loss": 0.0025, "step": 271930 }, { "epoch": 65.31, "learning_rate": 1.1797304117645786e-05, "loss": 0.0017, "step": 271940 }, { "epoch": 65.31, "learning_rate": 1.1794409495966874e-05, "loss": 0.0011, "step": 271950 }, { "epoch": 65.31, "learning_rate": 1.1791515181962875e-05, "loss": 0.0014, "step": 271960 }, { "epoch": 65.31, "learning_rate": 1.1788621175657095e-05, "loss": 0.002, "step": 271970 }, { "epoch": 65.32, "learning_rate": 1.1785727477072788e-05, "loss": 0.0129, "step": 271980 }, { "epoch": 65.32, "learning_rate": 1.1782834086233314e-05, "loss": 0.0013, "step": 271990 }, { "epoch": 65.32, "learning_rate": 1.1779941003161955e-05, "loss": 0.0015, "step": 272000 }, { "epoch": 65.32, "learning_rate": 1.1777048227882004e-05, "loss": 0.0098, "step": 272010 }, { "epoch": 65.33, "learning_rate": 1.1774155760416761e-05, "loss": 0.0013, "step": 272020 }, { "epoch": 65.33, "learning_rate": 1.1771263600789516e-05, "loss": 0.0015, "step": 272030 }, { "epoch": 65.33, "learning_rate": 1.1768371749023566e-05, "loss": 0.0015, "step": 272040 }, { "epoch": 65.33, "learning_rate": 1.17654802051422e-05, "loss": 0.0011, "step": 272050 }, { "epoch": 65.33, "learning_rate": 1.1762588969168681e-05, "loss": 0.0016, "step": 272060 }, { "epoch": 65.34, "learning_rate": 1.1759698041126343e-05, "loss": 0.0027, "step": 272070 }, { "epoch": 65.34, "learning_rate": 1.1756807421038418e-05, "loss": 0.0033, "step": 272080 }, { "epoch": 65.34, "learning_rate": 1.1753917108928192e-05, "loss": 0.0014, "step": 272090 }, { "epoch": 65.34, "learning_rate": 1.1751027104818967e-05, "loss": 0.0014, "step": 272100 }, { "epoch": 65.35, "learning_rate": 1.1748137408734017e-05, "loss": 0.0013, "step": 272110 }, { "epoch": 65.35, "learning_rate": 1.1745248020696564e-05, "loss": 0.0015, "step": 272120 }, { "epoch": 65.35, "learning_rate": 1.1742358940729926e-05, "loss": 0.0015, "step": 272130 }, { "epoch": 65.35, "learning_rate": 1.1739470168857353e-05, "loss": 0.0011, "step": 272140 }, { "epoch": 65.36, "learning_rate": 1.1736581705102113e-05, "loss": 0.0065, "step": 272150 }, { "epoch": 65.36, "learning_rate": 1.1733693549487457e-05, "loss": 0.0013, "step": 272160 }, { "epoch": 65.36, "learning_rate": 1.1730805702036651e-05, "loss": 0.004, "step": 272170 }, { "epoch": 65.36, "learning_rate": 1.1727918162772955e-05, "loss": 0.0014, "step": 272180 }, { "epoch": 65.36, "learning_rate": 1.17250309317196e-05, "loss": 0.0011, "step": 272190 }, { "epoch": 65.37, "learning_rate": 1.1722144008899871e-05, "loss": 0.0013, "step": 272200 }, { "epoch": 65.37, "learning_rate": 1.1719257394337012e-05, "loss": 0.0016, "step": 272210 }, { "epoch": 65.37, "learning_rate": 1.1716371088054246e-05, "loss": 0.0015, "step": 272220 }, { "epoch": 65.37, "learning_rate": 1.1713485090074816e-05, "loss": 0.0022, "step": 272230 }, { "epoch": 65.38, "learning_rate": 1.1710599400421985e-05, "loss": 0.0014, "step": 272240 }, { "epoch": 65.38, "learning_rate": 1.1707714019118987e-05, "loss": 0.0018, "step": 272250 }, { "epoch": 65.38, "learning_rate": 1.1704828946189055e-05, "loss": 0.0014, "step": 272260 }, { "epoch": 65.38, "learning_rate": 1.1701944181655422e-05, "loss": 0.0012, "step": 272270 }, { "epoch": 65.39, "learning_rate": 1.1699059725541323e-05, "loss": 0.0021, "step": 272280 }, { "epoch": 65.39, "learning_rate": 1.1696175577869983e-05, "loss": 0.0018, "step": 272290 }, { "epoch": 65.39, "learning_rate": 1.1693291738664625e-05, "loss": 0.0012, "step": 272300 }, { "epoch": 65.39, "learning_rate": 1.1690408207948478e-05, "loss": 0.0011, "step": 272310 }, { "epoch": 65.39, "learning_rate": 1.1687524985744764e-05, "loss": 0.0011, "step": 272320 }, { "epoch": 65.4, "learning_rate": 1.168464207207669e-05, "loss": 0.0011, "step": 272330 }, { "epoch": 65.4, "learning_rate": 1.168175946696749e-05, "loss": 0.0014, "step": 272340 }, { "epoch": 65.4, "learning_rate": 1.167887717044039e-05, "loss": 0.0013, "step": 272350 }, { "epoch": 65.4, "learning_rate": 1.1675995182518557e-05, "loss": 0.0012, "step": 272360 }, { "epoch": 65.41, "learning_rate": 1.1673113503225236e-05, "loss": 0.0034, "step": 272370 }, { "epoch": 65.41, "learning_rate": 1.1670232132583619e-05, "loss": 0.0012, "step": 272380 }, { "epoch": 65.41, "learning_rate": 1.1667351070616922e-05, "loss": 0.0016, "step": 272390 }, { "epoch": 65.41, "learning_rate": 1.1664470317348337e-05, "loss": 0.0014, "step": 272400 }, { "epoch": 65.41, "learning_rate": 1.1661589872801065e-05, "loss": 0.0016, "step": 272410 }, { "epoch": 65.42, "learning_rate": 1.1658709736998302e-05, "loss": 0.0013, "step": 272420 }, { "epoch": 65.42, "learning_rate": 1.1655829909963228e-05, "loss": 0.0013, "step": 272430 }, { "epoch": 65.42, "learning_rate": 1.165295039171908e-05, "loss": 0.0011, "step": 272440 }, { "epoch": 65.42, "learning_rate": 1.1650071182289001e-05, "loss": 0.0054, "step": 272450 }, { "epoch": 65.43, "learning_rate": 1.164719228169619e-05, "loss": 0.0137, "step": 272460 }, { "epoch": 65.43, "learning_rate": 1.1644313689963827e-05, "loss": 0.0012, "step": 272470 }, { "epoch": 65.43, "learning_rate": 1.164143540711511e-05, "loss": 0.0018, "step": 272480 }, { "epoch": 65.43, "learning_rate": 1.1638557433173225e-05, "loss": 0.0015, "step": 272490 }, { "epoch": 65.44, "learning_rate": 1.1635679768161305e-05, "loss": 0.0013, "step": 272500 }, { "epoch": 65.44, "learning_rate": 1.1632802412102568e-05, "loss": 0.0018, "step": 272510 }, { "epoch": 65.44, "learning_rate": 1.1629925365020167e-05, "loss": 0.0015, "step": 272520 }, { "epoch": 65.44, "learning_rate": 1.1627048626937276e-05, "loss": 0.0012, "step": 272530 }, { "epoch": 65.44, "learning_rate": 1.1624172197877064e-05, "loss": 0.0013, "step": 272540 }, { "epoch": 65.45, "learning_rate": 1.1621296077862686e-05, "loss": 0.0011, "step": 272550 }, { "epoch": 65.45, "learning_rate": 1.1618420266917312e-05, "loss": 0.0022, "step": 272560 }, { "epoch": 65.45, "learning_rate": 1.1615544765064084e-05, "loss": 0.0016, "step": 272570 }, { "epoch": 65.45, "learning_rate": 1.1612669572326185e-05, "loss": 0.001, "step": 272580 }, { "epoch": 65.46, "learning_rate": 1.1609794688726772e-05, "loss": 0.0015, "step": 272590 }, { "epoch": 65.46, "learning_rate": 1.1606920114288955e-05, "loss": 0.0019, "step": 272600 }, { "epoch": 65.46, "learning_rate": 1.1604045849035927e-05, "loss": 0.0013, "step": 272610 }, { "epoch": 65.46, "learning_rate": 1.160117189299082e-05, "loss": 0.0011, "step": 272620 }, { "epoch": 65.47, "learning_rate": 1.1598298246176787e-05, "loss": 0.0015, "step": 272630 }, { "epoch": 65.47, "learning_rate": 1.1595424908616931e-05, "loss": 0.001, "step": 272640 }, { "epoch": 65.47, "learning_rate": 1.159255188033444e-05, "loss": 0.0012, "step": 272650 }, { "epoch": 65.47, "learning_rate": 1.1589679161352424e-05, "loss": 0.0013, "step": 272660 }, { "epoch": 65.47, "learning_rate": 1.158680675169403e-05, "loss": 0.0016, "step": 272670 }, { "epoch": 65.48, "learning_rate": 1.1583934651382383e-05, "loss": 0.002, "step": 272680 }, { "epoch": 65.48, "learning_rate": 1.1581062860440618e-05, "loss": 0.0064, "step": 272690 }, { "epoch": 65.48, "learning_rate": 1.1578191378891851e-05, "loss": 0.0011, "step": 272700 }, { "epoch": 65.48, "learning_rate": 1.15753202067592e-05, "loss": 0.0035, "step": 272710 }, { "epoch": 65.49, "learning_rate": 1.1572449344065817e-05, "loss": 0.0009, "step": 272720 }, { "epoch": 65.49, "learning_rate": 1.1569578790834817e-05, "loss": 0.0021, "step": 272730 }, { "epoch": 65.49, "learning_rate": 1.1566708547089278e-05, "loss": 0.0026, "step": 272740 }, { "epoch": 65.49, "learning_rate": 1.1563838612852357e-05, "loss": 0.0011, "step": 272750 }, { "epoch": 65.49, "learning_rate": 1.1560968988147148e-05, "loss": 0.0013, "step": 272760 }, { "epoch": 65.5, "learning_rate": 1.1558099672996758e-05, "loss": 0.0011, "step": 272770 }, { "epoch": 65.5, "learning_rate": 1.1555230667424305e-05, "loss": 0.0017, "step": 272780 }, { "epoch": 65.5, "learning_rate": 1.1552361971452885e-05, "loss": 0.0012, "step": 272790 }, { "epoch": 65.5, "learning_rate": 1.1549493585105602e-05, "loss": 0.002, "step": 272800 }, { "epoch": 65.51, "learning_rate": 1.154662550840554e-05, "loss": 0.0015, "step": 272810 }, { "epoch": 65.51, "learning_rate": 1.1543757741375843e-05, "loss": 0.0011, "step": 272820 }, { "epoch": 65.51, "learning_rate": 1.1540890284039557e-05, "loss": 0.0011, "step": 272830 }, { "epoch": 65.51, "learning_rate": 1.1538023136419779e-05, "loss": 0.0013, "step": 272840 }, { "epoch": 65.52, "learning_rate": 1.1535156298539624e-05, "loss": 0.0035, "step": 272850 }, { "epoch": 65.52, "learning_rate": 1.1532289770422166e-05, "loss": 0.0012, "step": 272860 }, { "epoch": 65.52, "learning_rate": 1.1529423552090501e-05, "loss": 0.0012, "step": 272870 }, { "epoch": 65.52, "learning_rate": 1.1526557643567676e-05, "loss": 0.0016, "step": 272880 }, { "epoch": 65.52, "learning_rate": 1.1523692044876804e-05, "loss": 0.0015, "step": 272890 }, { "epoch": 65.53, "learning_rate": 1.1520826756040954e-05, "loss": 0.0014, "step": 272900 }, { "epoch": 65.53, "learning_rate": 1.1517961777083197e-05, "loss": 0.001, "step": 272910 }, { "epoch": 65.53, "learning_rate": 1.1515097108026607e-05, "loss": 0.0021, "step": 272920 }, { "epoch": 65.53, "learning_rate": 1.1512232748894252e-05, "loss": 0.0011, "step": 272930 }, { "epoch": 65.54, "learning_rate": 1.1509368699709206e-05, "loss": 0.0015, "step": 272940 }, { "epoch": 65.54, "learning_rate": 1.1506504960494508e-05, "loss": 0.0022, "step": 272950 }, { "epoch": 65.54, "learning_rate": 1.1503641531273267e-05, "loss": 0.0017, "step": 272960 }, { "epoch": 65.54, "learning_rate": 1.1500778412068508e-05, "loss": 0.0012, "step": 272970 }, { "epoch": 65.55, "learning_rate": 1.1497915602903276e-05, "loss": 0.0018, "step": 272980 }, { "epoch": 65.55, "learning_rate": 1.1495053103800663e-05, "loss": 0.0015, "step": 272990 }, { "epoch": 65.55, "learning_rate": 1.1492190914783702e-05, "loss": 0.0034, "step": 273000 }, { "epoch": 65.55, "learning_rate": 1.148932903587544e-05, "loss": 0.0017, "step": 273010 }, { "epoch": 65.55, "learning_rate": 1.1486467467098933e-05, "loss": 0.0013, "step": 273020 }, { "epoch": 65.56, "learning_rate": 1.1483606208477215e-05, "loss": 0.0015, "step": 273030 }, { "epoch": 65.56, "learning_rate": 1.1480745260033338e-05, "loss": 0.0013, "step": 273040 }, { "epoch": 65.56, "learning_rate": 1.1477884621790324e-05, "loss": 0.0019, "step": 273050 }, { "epoch": 65.56, "learning_rate": 1.1475024293771247e-05, "loss": 0.0033, "step": 273060 }, { "epoch": 65.57, "learning_rate": 1.147216427599911e-05, "loss": 0.0011, "step": 273070 }, { "epoch": 65.57, "learning_rate": 1.1469304568496952e-05, "loss": 0.0015, "step": 273080 }, { "epoch": 65.57, "learning_rate": 1.1466445171287788e-05, "loss": 0.0012, "step": 273090 }, { "epoch": 65.57, "learning_rate": 1.146358608439469e-05, "loss": 0.0012, "step": 273100 }, { "epoch": 65.57, "learning_rate": 1.1460727307840636e-05, "loss": 0.0015, "step": 273110 }, { "epoch": 65.58, "learning_rate": 1.1457868841648655e-05, "loss": 0.0012, "step": 273120 }, { "epoch": 65.58, "learning_rate": 1.1455010685841788e-05, "loss": 0.001, "step": 273130 }, { "epoch": 65.58, "learning_rate": 1.1452152840443048e-05, "loss": 0.0039, "step": 273140 }, { "epoch": 65.58, "learning_rate": 1.1449295305475438e-05, "loss": 0.0012, "step": 273150 }, { "epoch": 65.59, "learning_rate": 1.1446438080961974e-05, "loss": 0.0014, "step": 273160 }, { "epoch": 65.59, "learning_rate": 1.144358116692567e-05, "loss": 0.0014, "step": 273170 }, { "epoch": 65.59, "learning_rate": 1.1440724563389527e-05, "loss": 0.0013, "step": 273180 }, { "epoch": 65.59, "learning_rate": 1.1437868270376539e-05, "loss": 0.0015, "step": 273190 }, { "epoch": 65.6, "learning_rate": 1.1435012287909752e-05, "loss": 0.0013, "step": 273200 }, { "epoch": 65.6, "learning_rate": 1.1432156616012124e-05, "loss": 0.0012, "step": 273210 }, { "epoch": 65.6, "learning_rate": 1.1429301254706643e-05, "loss": 0.0011, "step": 273220 }, { "epoch": 65.6, "learning_rate": 1.1426446204016344e-05, "loss": 0.0011, "step": 273230 }, { "epoch": 65.6, "learning_rate": 1.1423591463964195e-05, "loss": 0.001, "step": 273240 }, { "epoch": 65.61, "learning_rate": 1.1420737034573186e-05, "loss": 0.0011, "step": 273250 }, { "epoch": 65.61, "learning_rate": 1.1417882915866318e-05, "loss": 0.001, "step": 273260 }, { "epoch": 65.61, "learning_rate": 1.141502910786656e-05, "loss": 0.0043, "step": 273270 }, { "epoch": 65.61, "learning_rate": 1.1412175610596897e-05, "loss": 0.0012, "step": 273280 }, { "epoch": 65.62, "learning_rate": 1.1409322424080316e-05, "loss": 0.009, "step": 273290 }, { "epoch": 65.62, "learning_rate": 1.1406469548339787e-05, "loss": 0.001, "step": 273300 }, { "epoch": 65.62, "learning_rate": 1.1403616983398285e-05, "loss": 0.0099, "step": 273310 }, { "epoch": 65.62, "learning_rate": 1.1400764729278785e-05, "loss": 0.0011, "step": 273320 }, { "epoch": 65.62, "learning_rate": 1.1397912786004245e-05, "loss": 0.0014, "step": 273330 }, { "epoch": 65.63, "learning_rate": 1.1395061153597663e-05, "loss": 0.0013, "step": 273340 }, { "epoch": 65.63, "learning_rate": 1.139220983208198e-05, "loss": 0.0013, "step": 273350 }, { "epoch": 65.63, "learning_rate": 1.138935882148014e-05, "loss": 0.0019, "step": 273360 }, { "epoch": 65.63, "learning_rate": 1.1386508121815137e-05, "loss": 0.0021, "step": 273370 }, { "epoch": 65.64, "learning_rate": 1.1383657733109921e-05, "loss": 0.0015, "step": 273380 }, { "epoch": 65.64, "learning_rate": 1.1380807655387437e-05, "loss": 0.0013, "step": 273390 }, { "epoch": 65.64, "learning_rate": 1.1377957888670643e-05, "loss": 0.0035, "step": 273400 }, { "epoch": 65.64, "learning_rate": 1.1375108432982484e-05, "loss": 0.0013, "step": 273410 }, { "epoch": 65.65, "learning_rate": 1.1372259288345905e-05, "loss": 0.0016, "step": 273420 }, { "epoch": 65.65, "learning_rate": 1.1369410454783864e-05, "loss": 0.002, "step": 273430 }, { "epoch": 65.65, "learning_rate": 1.1366561932319286e-05, "loss": 0.0012, "step": 273440 }, { "epoch": 65.65, "learning_rate": 1.1363713720975122e-05, "loss": 0.0015, "step": 273450 }, { "epoch": 65.65, "learning_rate": 1.1360865820774291e-05, "loss": 0.0014, "step": 273460 }, { "epoch": 65.66, "learning_rate": 1.1358018231739759e-05, "loss": 0.0055, "step": 273470 }, { "epoch": 65.66, "learning_rate": 1.135517095389445e-05, "loss": 0.0017, "step": 273480 }, { "epoch": 65.66, "learning_rate": 1.135232398726126e-05, "loss": 0.0015, "step": 273490 }, { "epoch": 65.66, "learning_rate": 1.134947733186315e-05, "loss": 0.0014, "step": 273500 }, { "epoch": 65.67, "learning_rate": 1.1346630987723039e-05, "loss": 0.0013, "step": 273510 }, { "epoch": 65.67, "learning_rate": 1.1343784954863846e-05, "loss": 0.0017, "step": 273520 }, { "epoch": 65.67, "learning_rate": 1.134093923330849e-05, "loss": 0.0023, "step": 273530 }, { "epoch": 65.67, "learning_rate": 1.1338093823079882e-05, "loss": 0.0021, "step": 273540 }, { "epoch": 65.68, "learning_rate": 1.1335248724200948e-05, "loss": 0.0015, "step": 273550 }, { "epoch": 65.68, "learning_rate": 1.1332403936694592e-05, "loss": 0.003, "step": 273560 }, { "epoch": 65.68, "learning_rate": 1.1329559460583711e-05, "loss": 0.0018, "step": 273570 }, { "epoch": 65.68, "learning_rate": 1.1326715295891255e-05, "loss": 0.001, "step": 273580 }, { "epoch": 65.68, "learning_rate": 1.1323871442640083e-05, "loss": 0.0016, "step": 273590 }, { "epoch": 65.69, "learning_rate": 1.1321027900853103e-05, "loss": 0.0013, "step": 273600 }, { "epoch": 65.69, "learning_rate": 1.1318184670553239e-05, "loss": 0.0013, "step": 273610 }, { "epoch": 65.69, "learning_rate": 1.1315341751763386e-05, "loss": 0.0012, "step": 273620 }, { "epoch": 65.69, "learning_rate": 1.1312499144506405e-05, "loss": 0.002, "step": 273630 }, { "epoch": 65.7, "learning_rate": 1.1309656848805217e-05, "loss": 0.003, "step": 273640 }, { "epoch": 65.7, "learning_rate": 1.1306814864682708e-05, "loss": 0.0012, "step": 273650 }, { "epoch": 65.7, "learning_rate": 1.1303973192161753e-05, "loss": 0.0012, "step": 273660 }, { "epoch": 65.7, "learning_rate": 1.1301131831265255e-05, "loss": 0.0012, "step": 273670 }, { "epoch": 65.7, "learning_rate": 1.129829078201608e-05, "loss": 0.0012, "step": 273680 }, { "epoch": 65.71, "learning_rate": 1.129545004443711e-05, "loss": 0.0015, "step": 273690 }, { "epoch": 65.71, "learning_rate": 1.1292609618551214e-05, "loss": 0.0028, "step": 273700 }, { "epoch": 65.71, "learning_rate": 1.1289769504381293e-05, "loss": 0.0011, "step": 273710 }, { "epoch": 65.71, "learning_rate": 1.1286929701950211e-05, "loss": 0.0049, "step": 273720 }, { "epoch": 65.72, "learning_rate": 1.1284090211280817e-05, "loss": 0.0022, "step": 273730 }, { "epoch": 65.72, "learning_rate": 1.1281251032395974e-05, "loss": 0.0015, "step": 273740 }, { "epoch": 65.72, "learning_rate": 1.1278412165318574e-05, "loss": 0.002, "step": 273750 }, { "epoch": 65.72, "learning_rate": 1.1275573610071488e-05, "loss": 0.0015, "step": 273760 }, { "epoch": 65.73, "learning_rate": 1.1272735366677522e-05, "loss": 0.0015, "step": 273770 }, { "epoch": 65.73, "learning_rate": 1.1269897435159577e-05, "loss": 0.0055, "step": 273780 }, { "epoch": 65.73, "learning_rate": 1.1267059815540498e-05, "loss": 0.0013, "step": 273790 }, { "epoch": 65.73, "learning_rate": 1.126422250784313e-05, "loss": 0.0021, "step": 273800 }, { "epoch": 65.73, "learning_rate": 1.1261385512090327e-05, "loss": 0.0011, "step": 273810 }, { "epoch": 65.74, "learning_rate": 1.1258548828304937e-05, "loss": 0.0012, "step": 273820 }, { "epoch": 65.74, "learning_rate": 1.1255712456509804e-05, "loss": 0.0011, "step": 273830 }, { "epoch": 65.74, "learning_rate": 1.1252876396727747e-05, "loss": 0.0016, "step": 273840 }, { "epoch": 65.74, "learning_rate": 1.1250040648981642e-05, "loss": 0.0033, "step": 273850 }, { "epoch": 65.75, "learning_rate": 1.1247205213294326e-05, "loss": 0.0026, "step": 273860 }, { "epoch": 65.75, "learning_rate": 1.1244370089688588e-05, "loss": 0.0023, "step": 273870 }, { "epoch": 65.75, "learning_rate": 1.1241535278187299e-05, "loss": 0.0017, "step": 273880 }, { "epoch": 65.75, "learning_rate": 1.1238700778813283e-05, "loss": 0.0025, "step": 273890 }, { "epoch": 65.76, "learning_rate": 1.1235866591589356e-05, "loss": 0.0074, "step": 273900 }, { "epoch": 65.76, "learning_rate": 1.123303271653835e-05, "loss": 0.0038, "step": 273910 }, { "epoch": 65.76, "learning_rate": 1.123019915368308e-05, "loss": 0.0016, "step": 273920 }, { "epoch": 65.76, "learning_rate": 1.1227365903046372e-05, "loss": 0.0014, "step": 273930 }, { "epoch": 65.76, "learning_rate": 1.1224532964651036e-05, "loss": 0.0016, "step": 273940 }, { "epoch": 65.77, "learning_rate": 1.1221700338519892e-05, "loss": 0.0015, "step": 273950 }, { "epoch": 65.77, "learning_rate": 1.121886802467575e-05, "loss": 0.0012, "step": 273960 }, { "epoch": 65.77, "learning_rate": 1.1216036023141414e-05, "loss": 0.0017, "step": 273970 }, { "epoch": 65.77, "learning_rate": 1.1213204333939686e-05, "loss": 0.0014, "step": 273980 }, { "epoch": 65.78, "learning_rate": 1.1210372957093385e-05, "loss": 0.0013, "step": 273990 }, { "epoch": 65.78, "learning_rate": 1.1207541892625329e-05, "loss": 0.0028, "step": 274000 }, { "epoch": 65.78, "learning_rate": 1.1204711140558255e-05, "loss": 0.0013, "step": 274010 }, { "epoch": 65.78, "learning_rate": 1.1201880700915018e-05, "loss": 0.0013, "step": 274020 }, { "epoch": 65.78, "learning_rate": 1.1199050573718394e-05, "loss": 0.0034, "step": 274030 }, { "epoch": 65.79, "learning_rate": 1.1196220758991171e-05, "loss": 0.0012, "step": 274040 }, { "epoch": 65.79, "learning_rate": 1.1193391256756136e-05, "loss": 0.0014, "step": 274050 }, { "epoch": 65.79, "learning_rate": 1.1190562067036087e-05, "loss": 0.0033, "step": 274060 }, { "epoch": 65.79, "learning_rate": 1.1187733189853794e-05, "loss": 0.0014, "step": 274070 }, { "epoch": 65.8, "learning_rate": 1.1184904625232028e-05, "loss": 0.0027, "step": 274080 }, { "epoch": 65.8, "learning_rate": 1.1182076373193611e-05, "loss": 0.0052, "step": 274090 }, { "epoch": 65.8, "learning_rate": 1.1179248433761286e-05, "loss": 0.0018, "step": 274100 }, { "epoch": 65.8, "learning_rate": 1.1176420806957811e-05, "loss": 0.0012, "step": 274110 }, { "epoch": 65.81, "learning_rate": 1.1173593492805995e-05, "loss": 0.0012, "step": 274120 }, { "epoch": 65.81, "learning_rate": 1.1170766491328593e-05, "loss": 0.0017, "step": 274130 }, { "epoch": 65.81, "learning_rate": 1.1167939802548383e-05, "loss": 0.0012, "step": 274140 }, { "epoch": 65.81, "learning_rate": 1.1165113426488089e-05, "loss": 0.0019, "step": 274150 }, { "epoch": 65.81, "learning_rate": 1.116228736317051e-05, "loss": 0.0018, "step": 274160 }, { "epoch": 65.82, "learning_rate": 1.1159461612618389e-05, "loss": 0.0012, "step": 274170 }, { "epoch": 65.82, "learning_rate": 1.115663617485449e-05, "loss": 0.0012, "step": 274180 }, { "epoch": 65.82, "learning_rate": 1.1153811049901564e-05, "loss": 0.0012, "step": 274190 }, { "epoch": 65.82, "learning_rate": 1.1150986237782357e-05, "loss": 0.0011, "step": 274200 }, { "epoch": 65.83, "learning_rate": 1.1148161738519618e-05, "loss": 0.0014, "step": 274210 }, { "epoch": 65.83, "learning_rate": 1.1145337552136087e-05, "loss": 0.0022, "step": 274220 }, { "epoch": 65.83, "learning_rate": 1.1142513678654531e-05, "loss": 0.0011, "step": 274230 }, { "epoch": 65.83, "learning_rate": 1.113969011809769e-05, "loss": 0.0017, "step": 274240 }, { "epoch": 65.84, "learning_rate": 1.1136866870488266e-05, "loss": 0.0012, "step": 274250 }, { "epoch": 65.84, "learning_rate": 1.1134043935849025e-05, "loss": 0.0013, "step": 274260 }, { "epoch": 65.84, "learning_rate": 1.11312213142027e-05, "loss": 0.0012, "step": 274270 }, { "epoch": 65.84, "learning_rate": 1.1128399005572015e-05, "loss": 0.0044, "step": 274280 }, { "epoch": 65.84, "learning_rate": 1.11255770099797e-05, "loss": 0.0014, "step": 274290 }, { "epoch": 65.85, "learning_rate": 1.1122755327448475e-05, "loss": 0.0074, "step": 274300 }, { "epoch": 65.85, "learning_rate": 1.1119933958001072e-05, "loss": 0.0017, "step": 274310 }, { "epoch": 65.85, "learning_rate": 1.1117112901660193e-05, "loss": 0.0017, "step": 274320 }, { "epoch": 65.85, "learning_rate": 1.1114292158448603e-05, "loss": 0.0021, "step": 274330 }, { "epoch": 65.86, "learning_rate": 1.1111471728388972e-05, "loss": 0.0013, "step": 274340 }, { "epoch": 65.86, "learning_rate": 1.1108651611504012e-05, "loss": 0.0011, "step": 274350 }, { "epoch": 65.86, "learning_rate": 1.1105831807816463e-05, "loss": 0.0012, "step": 274360 }, { "epoch": 65.86, "learning_rate": 1.1103012317349022e-05, "loss": 0.0013, "step": 274370 }, { "epoch": 65.86, "learning_rate": 1.110019314012441e-05, "loss": 0.003, "step": 274380 }, { "epoch": 65.87, "learning_rate": 1.1097374276165279e-05, "loss": 0.0013, "step": 274390 }, { "epoch": 65.87, "learning_rate": 1.1094555725494382e-05, "loss": 0.0017, "step": 274400 }, { "epoch": 65.87, "learning_rate": 1.1091737488134397e-05, "loss": 0.0013, "step": 274410 }, { "epoch": 65.87, "learning_rate": 1.1088919564108024e-05, "loss": 0.0012, "step": 274420 }, { "epoch": 65.88, "learning_rate": 1.108610195343795e-05, "loss": 0.0017, "step": 274430 }, { "epoch": 65.88, "learning_rate": 1.1083284656146875e-05, "loss": 0.0021, "step": 274440 }, { "epoch": 65.88, "learning_rate": 1.1080467672257478e-05, "loss": 0.0016, "step": 274450 }, { "epoch": 65.88, "learning_rate": 1.1077651001792433e-05, "loss": 0.0013, "step": 274460 }, { "epoch": 65.89, "learning_rate": 1.1074834644774467e-05, "loss": 0.001, "step": 274470 }, { "epoch": 65.89, "learning_rate": 1.1072018601226215e-05, "loss": 0.0025, "step": 274480 }, { "epoch": 65.89, "learning_rate": 1.1069202871170365e-05, "loss": 0.0011, "step": 274490 }, { "epoch": 65.89, "learning_rate": 1.1066387454629607e-05, "loss": 0.0018, "step": 274500 }, { "epoch": 65.89, "learning_rate": 1.1063572351626606e-05, "loss": 0.0011, "step": 274510 }, { "epoch": 65.9, "learning_rate": 1.1060757562184032e-05, "loss": 0.0022, "step": 274520 }, { "epoch": 65.9, "learning_rate": 1.1057943086324557e-05, "loss": 0.0011, "step": 274530 }, { "epoch": 65.9, "learning_rate": 1.105512892407084e-05, "loss": 0.0024, "step": 274540 }, { "epoch": 65.9, "learning_rate": 1.1052315075445547e-05, "loss": 0.0014, "step": 274550 }, { "epoch": 65.91, "learning_rate": 1.1049501540471325e-05, "loss": 0.0015, "step": 274560 }, { "epoch": 65.91, "learning_rate": 1.1046688319170867e-05, "loss": 0.0021, "step": 274570 }, { "epoch": 65.91, "learning_rate": 1.1043875411566795e-05, "loss": 0.0013, "step": 274580 }, { "epoch": 65.91, "learning_rate": 1.1041062817681774e-05, "loss": 0.003, "step": 274590 }, { "epoch": 65.92, "learning_rate": 1.1038250537538442e-05, "loss": 0.0013, "step": 274600 }, { "epoch": 65.92, "learning_rate": 1.1035438571159478e-05, "loss": 0.0043, "step": 274610 }, { "epoch": 65.92, "learning_rate": 1.1032626918567496e-05, "loss": 0.0019, "step": 274620 }, { "epoch": 65.92, "learning_rate": 1.1029815579785135e-05, "loss": 0.0014, "step": 274630 }, { "epoch": 65.92, "learning_rate": 1.1027004554835068e-05, "loss": 0.0014, "step": 274640 }, { "epoch": 65.93, "learning_rate": 1.1024193843739905e-05, "loss": 0.0065, "step": 274650 }, { "epoch": 65.93, "learning_rate": 1.10213834465223e-05, "loss": 0.0014, "step": 274660 }, { "epoch": 65.93, "learning_rate": 1.1018573363204864e-05, "loss": 0.0013, "step": 274670 }, { "epoch": 65.93, "learning_rate": 1.1015763593810246e-05, "loss": 0.0012, "step": 274680 }, { "epoch": 65.94, "learning_rate": 1.1012954138361065e-05, "loss": 0.0032, "step": 274690 }, { "epoch": 65.94, "learning_rate": 1.1010144996879933e-05, "loss": 0.0014, "step": 274700 }, { "epoch": 65.94, "learning_rate": 1.1007336169389516e-05, "loss": 0.0015, "step": 274710 }, { "epoch": 65.94, "learning_rate": 1.1004527655912384e-05, "loss": 0.0011, "step": 274720 }, { "epoch": 65.94, "learning_rate": 1.1001719456471165e-05, "loss": 0.0014, "step": 274730 }, { "epoch": 65.95, "learning_rate": 1.0998911571088494e-05, "loss": 0.0038, "step": 274740 }, { "epoch": 65.95, "learning_rate": 1.0996103999786989e-05, "loss": 0.0014, "step": 274750 }, { "epoch": 66.0, "learning_rate": 1.0993296742589215e-05, "loss": 0.002, "step": 274760 }, { "epoch": 66.0, "learning_rate": 1.0990489799517822e-05, "loss": 0.0033, "step": 274770 }, { "epoch": 66.01, "learning_rate": 1.0987683170595397e-05, "loss": 0.0017, "step": 274780 }, { "epoch": 66.01, "learning_rate": 1.098487685584455e-05, "loss": 0.0019, "step": 274790 }, { "epoch": 66.01, "learning_rate": 1.0982070855287874e-05, "loss": 0.0012, "step": 274800 }, { "epoch": 66.01, "learning_rate": 1.0979265168947971e-05, "loss": 0.0025, "step": 274810 }, { "epoch": 66.01, "learning_rate": 1.0976459796847428e-05, "loss": 0.0028, "step": 274820 }, { "epoch": 66.02, "learning_rate": 1.0973654739008842e-05, "loss": 0.0013, "step": 274830 }, { "epoch": 66.02, "learning_rate": 1.0970849995454796e-05, "loss": 0.0026, "step": 274840 }, { "epoch": 66.02, "learning_rate": 1.0968045566207902e-05, "loss": 0.0037, "step": 274850 }, { "epoch": 66.02, "learning_rate": 1.0965241451290715e-05, "loss": 0.001, "step": 274860 }, { "epoch": 66.03, "learning_rate": 1.0962437650725816e-05, "loss": 0.0043, "step": 274870 }, { "epoch": 66.03, "learning_rate": 1.0959634164535808e-05, "loss": 0.001, "step": 274880 }, { "epoch": 66.03, "learning_rate": 1.0956830992743255e-05, "loss": 0.0017, "step": 274890 }, { "epoch": 66.03, "learning_rate": 1.095402813537073e-05, "loss": 0.0031, "step": 274900 }, { "epoch": 66.03, "learning_rate": 1.0951225592440811e-05, "loss": 0.0016, "step": 274910 }, { "epoch": 66.04, "learning_rate": 1.0948423363976063e-05, "loss": 0.0015, "step": 274920 }, { "epoch": 66.04, "learning_rate": 1.0945621449999055e-05, "loss": 0.0012, "step": 274930 }, { "epoch": 66.04, "learning_rate": 1.0942819850532349e-05, "loss": 0.0033, "step": 274940 }, { "epoch": 66.04, "learning_rate": 1.0940018565598503e-05, "loss": 0.0022, "step": 274950 }, { "epoch": 66.05, "learning_rate": 1.0937217595220083e-05, "loss": 0.0012, "step": 274960 }, { "epoch": 66.05, "learning_rate": 1.0934416939419629e-05, "loss": 0.003, "step": 274970 }, { "epoch": 66.05, "learning_rate": 1.0931616598219719e-05, "loss": 0.0013, "step": 274980 }, { "epoch": 66.05, "learning_rate": 1.0928816571642909e-05, "loss": 0.0011, "step": 274990 }, { "epoch": 66.06, "learning_rate": 1.0926016859711725e-05, "loss": 0.0017, "step": 275000 }, { "epoch": 66.06, "learning_rate": 1.0923217462448699e-05, "loss": 0.0019, "step": 275010 }, { "epoch": 66.06, "learning_rate": 1.0920418379876419e-05, "loss": 0.0011, "step": 275020 }, { "epoch": 66.06, "learning_rate": 1.0917619612017399e-05, "loss": 0.0012, "step": 275030 }, { "epoch": 66.06, "learning_rate": 1.0914821158894189e-05, "loss": 0.0012, "step": 275040 }, { "epoch": 66.07, "learning_rate": 1.0912023020529317e-05, "loss": 0.0009, "step": 275050 }, { "epoch": 66.07, "learning_rate": 1.0909225196945322e-05, "loss": 0.0017, "step": 275060 }, { "epoch": 66.07, "learning_rate": 1.0906427688164733e-05, "loss": 0.0011, "step": 275070 }, { "epoch": 66.07, "learning_rate": 1.0903630494210076e-05, "loss": 0.0011, "step": 275080 }, { "epoch": 66.08, "learning_rate": 1.0900833615103884e-05, "loss": 0.0012, "step": 275090 }, { "epoch": 66.08, "learning_rate": 1.0898037050868676e-05, "loss": 0.0025, "step": 275100 }, { "epoch": 66.08, "learning_rate": 1.0895240801526962e-05, "loss": 0.0071, "step": 275110 }, { "epoch": 66.08, "learning_rate": 1.0892444867101287e-05, "loss": 0.0065, "step": 275120 }, { "epoch": 66.09, "learning_rate": 1.0889649247614159e-05, "loss": 0.0038, "step": 275130 }, { "epoch": 66.09, "learning_rate": 1.0886853943088066e-05, "loss": 0.0011, "step": 275140 }, { "epoch": 66.09, "learning_rate": 1.0884058953545544e-05, "loss": 0.0012, "step": 275150 }, { "epoch": 66.09, "learning_rate": 1.08812642790091e-05, "loss": 0.0028, "step": 275160 }, { "epoch": 66.09, "learning_rate": 1.0878469919501238e-05, "loss": 0.0012, "step": 275170 }, { "epoch": 66.1, "learning_rate": 1.0875675875044455e-05, "loss": 0.0017, "step": 275180 }, { "epoch": 66.1, "learning_rate": 1.0872882145661255e-05, "loss": 0.0011, "step": 275190 }, { "epoch": 66.1, "learning_rate": 1.0870088731374139e-05, "loss": 0.0032, "step": 275200 }, { "epoch": 66.1, "learning_rate": 1.0867295632205588e-05, "loss": 0.0013, "step": 275210 }, { "epoch": 66.11, "learning_rate": 1.086450284817812e-05, "loss": 0.0017, "step": 275220 }, { "epoch": 66.11, "learning_rate": 1.0861710379314227e-05, "loss": 0.0012, "step": 275230 }, { "epoch": 66.11, "learning_rate": 1.0858918225636371e-05, "loss": 0.001, "step": 275240 }, { "epoch": 66.11, "learning_rate": 1.0856126387167038e-05, "loss": 0.0102, "step": 275250 }, { "epoch": 66.11, "learning_rate": 1.0853334863928732e-05, "loss": 0.0013, "step": 275260 }, { "epoch": 66.12, "learning_rate": 1.0850543655943946e-05, "loss": 0.0014, "step": 275270 }, { "epoch": 66.12, "learning_rate": 1.0847752763235102e-05, "loss": 0.0012, "step": 275280 }, { "epoch": 66.12, "learning_rate": 1.0844962185824725e-05, "loss": 0.0014, "step": 275290 }, { "epoch": 66.12, "learning_rate": 1.0842171923735279e-05, "loss": 0.0012, "step": 275300 }, { "epoch": 66.13, "learning_rate": 1.083938197698922e-05, "loss": 0.0012, "step": 275310 }, { "epoch": 66.13, "learning_rate": 1.0836592345609031e-05, "loss": 0.0013, "step": 275320 }, { "epoch": 66.13, "learning_rate": 1.0833803029617167e-05, "loss": 0.0011, "step": 275330 }, { "epoch": 66.13, "learning_rate": 1.0831014029036101e-05, "loss": 0.0011, "step": 275340 }, { "epoch": 66.14, "learning_rate": 1.0828225343888266e-05, "loss": 0.0018, "step": 275350 }, { "epoch": 66.14, "learning_rate": 1.0825436974196157e-05, "loss": 0.003, "step": 275360 }, { "epoch": 66.14, "learning_rate": 1.0822648919982225e-05, "loss": 0.0022, "step": 275370 }, { "epoch": 66.14, "learning_rate": 1.081986118126888e-05, "loss": 0.0012, "step": 275380 }, { "epoch": 66.14, "learning_rate": 1.0817073758078622e-05, "loss": 0.0018, "step": 275390 }, { "epoch": 66.15, "learning_rate": 1.0814286650433875e-05, "loss": 0.0027, "step": 275400 }, { "epoch": 66.15, "learning_rate": 1.0811499858357089e-05, "loss": 0.0023, "step": 275410 }, { "epoch": 66.15, "learning_rate": 1.0808713381870706e-05, "loss": 0.0018, "step": 275420 }, { "epoch": 66.15, "learning_rate": 1.0805927220997159e-05, "loss": 0.0039, "step": 275430 }, { "epoch": 66.16, "learning_rate": 1.0803141375758896e-05, "loss": 0.0022, "step": 275440 }, { "epoch": 66.16, "learning_rate": 1.0800355846178345e-05, "loss": 0.0011, "step": 275450 }, { "epoch": 66.16, "learning_rate": 1.0797570632277943e-05, "loss": 0.0014, "step": 275460 }, { "epoch": 66.16, "learning_rate": 1.0794785734080115e-05, "loss": 0.0012, "step": 275470 }, { "epoch": 66.16, "learning_rate": 1.079200115160729e-05, "loss": 0.0018, "step": 275480 }, { "epoch": 66.17, "learning_rate": 1.0789216884881875e-05, "loss": 0.002, "step": 275490 }, { "epoch": 66.17, "learning_rate": 1.0786432933926332e-05, "loss": 0.0022, "step": 275500 }, { "epoch": 66.17, "learning_rate": 1.0783649298763066e-05, "loss": 0.0011, "step": 275510 }, { "epoch": 66.17, "learning_rate": 1.0780865979414462e-05, "loss": 0.0011, "step": 275520 }, { "epoch": 66.18, "learning_rate": 1.077808297590297e-05, "loss": 0.0011, "step": 275530 }, { "epoch": 66.18, "learning_rate": 1.0775300288250989e-05, "loss": 0.0012, "step": 275540 }, { "epoch": 66.18, "learning_rate": 1.0772517916480933e-05, "loss": 0.0022, "step": 275550 }, { "epoch": 66.18, "learning_rate": 1.076973586061521e-05, "loss": 0.0026, "step": 275560 }, { "epoch": 66.19, "learning_rate": 1.0766954120676214e-05, "loss": 0.0016, "step": 275570 }, { "epoch": 66.19, "learning_rate": 1.0764172696686354e-05, "loss": 0.0014, "step": 275580 }, { "epoch": 66.19, "learning_rate": 1.0761391588668019e-05, "loss": 0.0015, "step": 275590 }, { "epoch": 66.19, "learning_rate": 1.0758610796643636e-05, "loss": 0.002, "step": 275600 }, { "epoch": 66.19, "learning_rate": 1.0755830320635569e-05, "loss": 0.0324, "step": 275610 }, { "epoch": 66.2, "learning_rate": 1.07530501606662e-05, "loss": 0.0011, "step": 275620 }, { "epoch": 66.2, "learning_rate": 1.0750270316757954e-05, "loss": 0.0013, "step": 275630 }, { "epoch": 66.2, "learning_rate": 1.0747490788933195e-05, "loss": 0.0014, "step": 275640 }, { "epoch": 66.2, "learning_rate": 1.0744711577214328e-05, "loss": 0.0019, "step": 275650 }, { "epoch": 66.21, "learning_rate": 1.0741932681623695e-05, "loss": 0.0012, "step": 275660 }, { "epoch": 66.21, "learning_rate": 1.0739154102183706e-05, "loss": 0.0032, "step": 275670 }, { "epoch": 66.21, "learning_rate": 1.0736375838916734e-05, "loss": 0.0011, "step": 275680 }, { "epoch": 66.21, "learning_rate": 1.0733597891845142e-05, "loss": 0.0018, "step": 275690 }, { "epoch": 66.22, "learning_rate": 1.0730820260991314e-05, "loss": 0.0013, "step": 275700 }, { "epoch": 66.22, "learning_rate": 1.072804294637761e-05, "loss": 0.0018, "step": 275710 }, { "epoch": 66.22, "learning_rate": 1.0725265948026398e-05, "loss": 0.0014, "step": 275720 }, { "epoch": 66.22, "learning_rate": 1.0722489265960024e-05, "loss": 0.0011, "step": 275730 }, { "epoch": 66.22, "learning_rate": 1.0719712900200895e-05, "loss": 0.0047, "step": 275740 }, { "epoch": 66.23, "learning_rate": 1.0716936850771331e-05, "loss": 0.0012, "step": 275750 }, { "epoch": 66.23, "learning_rate": 1.0714161117693683e-05, "loss": 0.0012, "step": 275760 }, { "epoch": 66.23, "learning_rate": 1.0711385700990335e-05, "loss": 0.0015, "step": 275770 }, { "epoch": 66.23, "learning_rate": 1.0708610600683616e-05, "loss": 0.003, "step": 275780 }, { "epoch": 66.24, "learning_rate": 1.0705835816795884e-05, "loss": 0.0014, "step": 275790 }, { "epoch": 66.24, "learning_rate": 1.070306134934948e-05, "loss": 0.002, "step": 275800 }, { "epoch": 66.24, "learning_rate": 1.0700287198366749e-05, "loss": 0.0013, "step": 275810 }, { "epoch": 66.24, "learning_rate": 1.0697513363870032e-05, "loss": 0.0012, "step": 275820 }, { "epoch": 66.24, "learning_rate": 1.0694739845881651e-05, "loss": 0.0012, "step": 275830 }, { "epoch": 66.25, "learning_rate": 1.0691966644423985e-05, "loss": 0.0022, "step": 275840 }, { "epoch": 66.25, "learning_rate": 1.0689193759519323e-05, "loss": 0.0029, "step": 275850 }, { "epoch": 66.25, "learning_rate": 1.0686421191189999e-05, "loss": 0.0014, "step": 275860 }, { "epoch": 66.25, "learning_rate": 1.0683648939458362e-05, "loss": 0.0024, "step": 275870 }, { "epoch": 66.26, "learning_rate": 1.0680877004346734e-05, "loss": 0.001, "step": 275880 }, { "epoch": 66.26, "learning_rate": 1.067810538587744e-05, "loss": 0.0013, "step": 275890 }, { "epoch": 66.26, "learning_rate": 1.0675334084072769e-05, "loss": 0.0016, "step": 275900 }, { "epoch": 66.26, "learning_rate": 1.0672563098955074e-05, "loss": 0.0012, "step": 275910 }, { "epoch": 66.27, "learning_rate": 1.0669792430546654e-05, "loss": 0.0036, "step": 275920 }, { "epoch": 66.27, "learning_rate": 1.0667022078869831e-05, "loss": 0.0014, "step": 275930 }, { "epoch": 66.27, "learning_rate": 1.066425204394691e-05, "loss": 0.002, "step": 275940 }, { "epoch": 66.27, "learning_rate": 1.0661482325800193e-05, "loss": 0.0013, "step": 275950 }, { "epoch": 66.27, "learning_rate": 1.0658712924451992e-05, "loss": 0.0018, "step": 275960 }, { "epoch": 66.28, "learning_rate": 1.0655943839924593e-05, "loss": 0.0019, "step": 275970 }, { "epoch": 66.28, "learning_rate": 1.065317507224034e-05, "loss": 0.0012, "step": 275980 }, { "epoch": 66.28, "learning_rate": 1.0650406621421482e-05, "loss": 0.0012, "step": 275990 }, { "epoch": 66.28, "learning_rate": 1.0647638487490324e-05, "loss": 0.0011, "step": 276000 }, { "epoch": 66.29, "learning_rate": 1.0644870670469177e-05, "loss": 0.0013, "step": 276010 }, { "epoch": 66.29, "learning_rate": 1.0642103170380319e-05, "loss": 0.0014, "step": 276020 }, { "epoch": 66.29, "learning_rate": 1.063933598724604e-05, "loss": 0.0012, "step": 276030 }, { "epoch": 66.29, "learning_rate": 1.063656912108862e-05, "loss": 0.0036, "step": 276040 }, { "epoch": 66.3, "learning_rate": 1.0633802571930346e-05, "loss": 0.0018, "step": 276050 }, { "epoch": 66.3, "learning_rate": 1.0631036339793493e-05, "loss": 0.0011, "step": 276060 }, { "epoch": 66.3, "learning_rate": 1.0628270424700337e-05, "loss": 0.0019, "step": 276070 }, { "epoch": 66.3, "learning_rate": 1.0625504826673161e-05, "loss": 0.0011, "step": 276080 }, { "epoch": 66.3, "learning_rate": 1.0622739545734228e-05, "loss": 0.0016, "step": 276090 }, { "epoch": 66.31, "learning_rate": 1.0619974581905806e-05, "loss": 0.0015, "step": 276100 }, { "epoch": 66.31, "learning_rate": 1.0617209935210155e-05, "loss": 0.0012, "step": 276110 }, { "epoch": 66.31, "learning_rate": 1.0614445605669577e-05, "loss": 0.0014, "step": 276120 }, { "epoch": 66.31, "learning_rate": 1.0611681593306295e-05, "loss": 0.0017, "step": 276130 }, { "epoch": 66.32, "learning_rate": 1.0608917898142562e-05, "loss": 0.0101, "step": 276140 }, { "epoch": 66.32, "learning_rate": 1.0606154520200662e-05, "loss": 0.0018, "step": 276150 }, { "epoch": 66.32, "learning_rate": 1.0603391459502842e-05, "loss": 0.0019, "step": 276160 }, { "epoch": 66.32, "learning_rate": 1.0600628716071348e-05, "loss": 0.007, "step": 276170 }, { "epoch": 66.32, "learning_rate": 1.0597866289928432e-05, "loss": 0.0022, "step": 276180 }, { "epoch": 66.33, "learning_rate": 1.0595104181096338e-05, "loss": 0.0053, "step": 276190 }, { "epoch": 66.33, "learning_rate": 1.0592342389597315e-05, "loss": 0.0013, "step": 276200 }, { "epoch": 66.33, "learning_rate": 1.0589580915453578e-05, "loss": 0.0017, "step": 276210 }, { "epoch": 66.33, "learning_rate": 1.0586819758687416e-05, "loss": 0.0018, "step": 276220 }, { "epoch": 66.34, "learning_rate": 1.0584058919321027e-05, "loss": 0.0012, "step": 276230 }, { "epoch": 66.34, "learning_rate": 1.0581298397376638e-05, "loss": 0.0014, "step": 276240 }, { "epoch": 66.34, "learning_rate": 1.0578538192876503e-05, "loss": 0.0011, "step": 276250 }, { "epoch": 66.34, "learning_rate": 1.057577830584286e-05, "loss": 0.0016, "step": 276260 }, { "epoch": 66.35, "learning_rate": 1.057301873629789e-05, "loss": 0.0013, "step": 276270 }, { "epoch": 66.35, "learning_rate": 1.0570259484263856e-05, "loss": 0.0012, "step": 276280 }, { "epoch": 66.35, "learning_rate": 1.056750054976297e-05, "loss": 0.0013, "step": 276290 }, { "epoch": 66.35, "learning_rate": 1.056474193281744e-05, "loss": 0.0012, "step": 276300 }, { "epoch": 66.35, "learning_rate": 1.056198363344949e-05, "loss": 0.0016, "step": 276310 }, { "epoch": 66.36, "learning_rate": 1.0559225651681331e-05, "loss": 0.0014, "step": 276320 }, { "epoch": 66.36, "learning_rate": 1.0556467987535174e-05, "loss": 0.0025, "step": 276330 }, { "epoch": 66.36, "learning_rate": 1.0553710641033226e-05, "loss": 0.0012, "step": 276340 }, { "epoch": 66.36, "learning_rate": 1.0550953612197678e-05, "loss": 0.0024, "step": 276350 }, { "epoch": 66.37, "learning_rate": 1.0548196901050772e-05, "loss": 0.0053, "step": 276360 }, { "epoch": 66.37, "learning_rate": 1.0545440507614674e-05, "loss": 0.0024, "step": 276370 }, { "epoch": 66.37, "learning_rate": 1.054268443191157e-05, "loss": 0.0027, "step": 276380 }, { "epoch": 66.37, "learning_rate": 1.0539928673963695e-05, "loss": 0.0055, "step": 276390 }, { "epoch": 66.38, "learning_rate": 1.0537173233793219e-05, "loss": 0.0013, "step": 276400 }, { "epoch": 66.38, "learning_rate": 1.0534418111422334e-05, "loss": 0.0013, "step": 276410 }, { "epoch": 66.38, "learning_rate": 1.0531663306873235e-05, "loss": 0.0012, "step": 276420 }, { "epoch": 66.38, "learning_rate": 1.0528908820168093e-05, "loss": 0.0025, "step": 276430 }, { "epoch": 66.38, "learning_rate": 1.05261546513291e-05, "loss": 0.0026, "step": 276440 }, { "epoch": 66.39, "learning_rate": 1.0523400800378435e-05, "loss": 0.0034, "step": 276450 }, { "epoch": 66.39, "learning_rate": 1.0520647267338275e-05, "loss": 0.0015, "step": 276460 }, { "epoch": 66.39, "learning_rate": 1.0517894052230787e-05, "loss": 0.0054, "step": 276470 }, { "epoch": 66.39, "learning_rate": 1.051514115507814e-05, "loss": 0.0014, "step": 276480 }, { "epoch": 66.4, "learning_rate": 1.0512388575902527e-05, "loss": 0.0011, "step": 276490 }, { "epoch": 66.4, "learning_rate": 1.0509636314726112e-05, "loss": 0.0037, "step": 276500 }, { "epoch": 66.4, "learning_rate": 1.0506884371571035e-05, "loss": 0.0011, "step": 276510 }, { "epoch": 66.4, "learning_rate": 1.0504132746459456e-05, "loss": 0.0016, "step": 276520 }, { "epoch": 66.4, "learning_rate": 1.050138143941356e-05, "loss": 0.0015, "step": 276530 }, { "epoch": 66.41, "learning_rate": 1.04986304504555e-05, "loss": 0.0011, "step": 276540 }, { "epoch": 66.41, "learning_rate": 1.0495879779607415e-05, "loss": 0.0012, "step": 276550 }, { "epoch": 66.41, "learning_rate": 1.0493129426891463e-05, "loss": 0.0013, "step": 276560 }, { "epoch": 66.41, "learning_rate": 1.0490379392329796e-05, "loss": 0.0011, "step": 276570 }, { "epoch": 66.42, "learning_rate": 1.0487629675944566e-05, "loss": 0.0012, "step": 276580 }, { "epoch": 66.42, "learning_rate": 1.0484880277757903e-05, "loss": 0.0015, "step": 276590 }, { "epoch": 66.42, "learning_rate": 1.048213119779195e-05, "loss": 0.0019, "step": 276600 }, { "epoch": 66.42, "learning_rate": 1.0479382436068857e-05, "loss": 0.0009, "step": 276610 }, { "epoch": 66.43, "learning_rate": 1.0476633992610736e-05, "loss": 0.0012, "step": 276620 }, { "epoch": 66.43, "learning_rate": 1.0473885867439754e-05, "loss": 0.0011, "step": 276630 }, { "epoch": 66.43, "learning_rate": 1.0471138060578039e-05, "loss": 0.0011, "step": 276640 }, { "epoch": 66.43, "learning_rate": 1.0468390572047681e-05, "loss": 0.0012, "step": 276650 }, { "epoch": 66.43, "learning_rate": 1.046564340187084e-05, "loss": 0.0011, "step": 276660 }, { "epoch": 66.44, "learning_rate": 1.0462896550069634e-05, "loss": 0.0061, "step": 276670 }, { "epoch": 66.44, "learning_rate": 1.0460150016666181e-05, "loss": 0.0042, "step": 276680 }, { "epoch": 66.44, "learning_rate": 1.0457403801682597e-05, "loss": 0.004, "step": 276690 }, { "epoch": 66.44, "learning_rate": 1.0454657905141002e-05, "loss": 0.0012, "step": 276700 }, { "epoch": 66.45, "learning_rate": 1.0451912327063507e-05, "loss": 0.0012, "step": 276710 }, { "epoch": 66.45, "learning_rate": 1.0449167067472205e-05, "loss": 0.0011, "step": 276720 }, { "epoch": 66.45, "learning_rate": 1.0446422126389232e-05, "loss": 0.0014, "step": 276730 }, { "epoch": 66.45, "learning_rate": 1.0443677503836702e-05, "loss": 0.0031, "step": 276740 }, { "epoch": 66.46, "learning_rate": 1.0440933199836684e-05, "loss": 0.001, "step": 276750 }, { "epoch": 66.46, "learning_rate": 1.0438189214411275e-05, "loss": 0.0012, "step": 276760 }, { "epoch": 66.46, "learning_rate": 1.0435445547582606e-05, "loss": 0.001, "step": 276770 }, { "epoch": 66.46, "learning_rate": 1.0432702199372773e-05, "loss": 0.0054, "step": 276780 }, { "epoch": 66.46, "learning_rate": 1.0429959169803822e-05, "loss": 0.0012, "step": 276790 }, { "epoch": 66.47, "learning_rate": 1.0427216458897881e-05, "loss": 0.0012, "step": 276800 }, { "epoch": 66.47, "learning_rate": 1.0424474066677036e-05, "loss": 0.0012, "step": 276810 }, { "epoch": 66.47, "learning_rate": 1.0421731993163365e-05, "loss": 0.0012, "step": 276820 }, { "epoch": 66.47, "learning_rate": 1.0418990238378945e-05, "loss": 0.0011, "step": 276830 }, { "epoch": 66.48, "learning_rate": 1.0416248802345867e-05, "loss": 0.0013, "step": 276840 }, { "epoch": 66.48, "learning_rate": 1.04135076850862e-05, "loss": 0.0014, "step": 276850 }, { "epoch": 66.48, "learning_rate": 1.0410766886622002e-05, "loss": 0.0013, "step": 276860 }, { "epoch": 66.48, "learning_rate": 1.0408026406975386e-05, "loss": 0.0013, "step": 276870 }, { "epoch": 66.48, "learning_rate": 1.040528624616841e-05, "loss": 0.0013, "step": 276880 }, { "epoch": 66.49, "learning_rate": 1.0402546404223101e-05, "loss": 0.0014, "step": 276890 }, { "epoch": 66.49, "learning_rate": 1.0399806881161566e-05, "loss": 0.0011, "step": 276900 }, { "epoch": 66.49, "learning_rate": 1.0397067677005856e-05, "loss": 0.0014, "step": 276910 }, { "epoch": 66.49, "learning_rate": 1.039432879177804e-05, "loss": 0.0011, "step": 276920 }, { "epoch": 66.5, "learning_rate": 1.0391590225500137e-05, "loss": 0.0018, "step": 276930 }, { "epoch": 66.5, "learning_rate": 1.0388851978194236e-05, "loss": 0.0012, "step": 276940 }, { "epoch": 66.5, "learning_rate": 1.0386114049882384e-05, "loss": 0.0011, "step": 276950 }, { "epoch": 66.5, "learning_rate": 1.0383376440586617e-05, "loss": 0.0022, "step": 276960 }, { "epoch": 66.51, "learning_rate": 1.0380639150328997e-05, "loss": 0.0019, "step": 276970 }, { "epoch": 66.51, "learning_rate": 1.0377902179131554e-05, "loss": 0.0022, "step": 276980 }, { "epoch": 66.51, "learning_rate": 1.0375165527016334e-05, "loss": 0.0015, "step": 276990 }, { "epoch": 66.51, "learning_rate": 1.0372429194005368e-05, "loss": 0.0015, "step": 277000 }, { "epoch": 66.51, "learning_rate": 1.036969318012071e-05, "loss": 0.0016, "step": 277010 }, { "epoch": 66.52, "learning_rate": 1.0366957485384404e-05, "loss": 0.0012, "step": 277020 }, { "epoch": 66.52, "learning_rate": 1.0364222109818428e-05, "loss": 0.0012, "step": 277030 }, { "epoch": 66.52, "learning_rate": 1.0361487053444857e-05, "loss": 0.0012, "step": 277040 }, { "epoch": 66.52, "learning_rate": 1.0358752316285703e-05, "loss": 0.0018, "step": 277050 }, { "epoch": 66.53, "learning_rate": 1.035601789836299e-05, "loss": 0.004, "step": 277060 }, { "epoch": 66.53, "learning_rate": 1.0353283799698744e-05, "loss": 0.0022, "step": 277070 }, { "epoch": 66.53, "learning_rate": 1.035055002031497e-05, "loss": 0.0015, "step": 277080 }, { "epoch": 66.53, "learning_rate": 1.0347816560233692e-05, "loss": 0.0013, "step": 277090 }, { "epoch": 66.54, "learning_rate": 1.0345083419476908e-05, "loss": 0.0011, "step": 277100 }, { "epoch": 66.54, "learning_rate": 1.0342350598066675e-05, "loss": 0.003, "step": 277110 }, { "epoch": 66.54, "learning_rate": 1.0339618096024945e-05, "loss": 0.0012, "step": 277120 }, { "epoch": 66.54, "learning_rate": 1.033688591337374e-05, "loss": 0.0023, "step": 277130 }, { "epoch": 66.54, "learning_rate": 1.0334154050135075e-05, "loss": 0.0068, "step": 277140 }, { "epoch": 66.55, "learning_rate": 1.0331422506330952e-05, "loss": 0.0021, "step": 277150 }, { "epoch": 66.55, "learning_rate": 1.0328691281983365e-05, "loss": 0.0015, "step": 277160 }, { "epoch": 66.55, "learning_rate": 1.032596037711428e-05, "loss": 0.0011, "step": 277170 }, { "epoch": 66.55, "learning_rate": 1.032322979174573e-05, "loss": 0.0012, "step": 277180 }, { "epoch": 66.56, "learning_rate": 1.0320499525899685e-05, "loss": 0.002, "step": 277190 }, { "epoch": 66.56, "learning_rate": 1.0317769579598135e-05, "loss": 0.002, "step": 277200 }, { "epoch": 66.56, "learning_rate": 1.031503995286307e-05, "loss": 0.0018, "step": 277210 }, { "epoch": 66.56, "learning_rate": 1.031231064571646e-05, "loss": 0.0017, "step": 277220 }, { "epoch": 66.56, "learning_rate": 1.0309581658180296e-05, "loss": 0.0016, "step": 277230 }, { "epoch": 66.57, "learning_rate": 1.0306852990276539e-05, "loss": 0.0012, "step": 277240 }, { "epoch": 66.57, "learning_rate": 1.0304124642027197e-05, "loss": 0.0014, "step": 277250 }, { "epoch": 66.57, "learning_rate": 1.0301396613454207e-05, "loss": 0.0015, "step": 277260 }, { "epoch": 66.57, "learning_rate": 1.029866890457954e-05, "loss": 0.0021, "step": 277270 }, { "epoch": 66.58, "learning_rate": 1.0295941515425184e-05, "loss": 0.0015, "step": 277280 }, { "epoch": 66.58, "learning_rate": 1.0293214446013094e-05, "loss": 0.0011, "step": 277290 }, { "epoch": 66.58, "learning_rate": 1.029048769636523e-05, "loss": 0.0011, "step": 277300 }, { "epoch": 66.58, "learning_rate": 1.0287761266503553e-05, "loss": 0.002, "step": 277310 }, { "epoch": 66.59, "learning_rate": 1.0285035156450012e-05, "loss": 0.0017, "step": 277320 }, { "epoch": 66.59, "learning_rate": 1.0282309366226573e-05, "loss": 0.018, "step": 277330 }, { "epoch": 66.59, "learning_rate": 1.027958389585516e-05, "loss": 0.0038, "step": 277340 }, { "epoch": 66.59, "learning_rate": 1.027685874535777e-05, "loss": 0.0012, "step": 277350 }, { "epoch": 66.59, "learning_rate": 1.0274133914756307e-05, "loss": 0.0013, "step": 277360 }, { "epoch": 66.6, "learning_rate": 1.027140940407273e-05, "loss": 0.0014, "step": 277370 }, { "epoch": 66.6, "learning_rate": 1.0268685213328966e-05, "loss": 0.0015, "step": 277380 }, { "epoch": 66.6, "learning_rate": 1.0265961342546976e-05, "loss": 0.0014, "step": 277390 }, { "epoch": 66.6, "learning_rate": 1.0263237791748697e-05, "loss": 0.0013, "step": 277400 }, { "epoch": 66.61, "learning_rate": 1.0260514560956025e-05, "loss": 0.0012, "step": 277410 }, { "epoch": 66.61, "learning_rate": 1.0257791650190929e-05, "loss": 0.0012, "step": 277420 }, { "epoch": 66.61, "learning_rate": 1.0255069059475324e-05, "loss": 0.0015, "step": 277430 }, { "epoch": 66.61, "learning_rate": 1.0252346788831136e-05, "loss": 0.0014, "step": 277440 }, { "epoch": 66.62, "learning_rate": 1.0249624838280281e-05, "loss": 0.0012, "step": 277450 }, { "epoch": 66.62, "learning_rate": 1.0246903207844694e-05, "loss": 0.0079, "step": 277460 }, { "epoch": 66.62, "learning_rate": 1.0244181897546273e-05, "loss": 0.0012, "step": 277470 }, { "epoch": 66.62, "learning_rate": 1.024146090740694e-05, "loss": 0.0017, "step": 277480 }, { "epoch": 66.62, "learning_rate": 1.0238740237448634e-05, "loss": 0.0026, "step": 277490 }, { "epoch": 66.63, "learning_rate": 1.0236019887693226e-05, "loss": 0.0039, "step": 277500 }, { "epoch": 66.63, "learning_rate": 1.0233299858162631e-05, "loss": 0.0012, "step": 277510 }, { "epoch": 66.63, "learning_rate": 1.0230580148878777e-05, "loss": 0.0017, "step": 277520 }, { "epoch": 66.63, "learning_rate": 1.022786075986355e-05, "loss": 0.0011, "step": 277530 }, { "epoch": 66.64, "learning_rate": 1.0225141691138851e-05, "loss": 0.0046, "step": 277540 }, { "epoch": 66.64, "learning_rate": 1.0222422942726573e-05, "loss": 0.0015, "step": 277550 }, { "epoch": 66.64, "learning_rate": 1.021970451464862e-05, "loss": 0.0021, "step": 277560 }, { "epoch": 66.64, "learning_rate": 1.0216986406926877e-05, "loss": 0.001, "step": 277570 }, { "epoch": 66.64, "learning_rate": 1.0214268619583234e-05, "loss": 0.001, "step": 277580 }, { "epoch": 66.65, "learning_rate": 1.0211551152639576e-05, "loss": 0.0061, "step": 277590 }, { "epoch": 66.65, "learning_rate": 1.0208834006117796e-05, "loss": 0.0014, "step": 277600 }, { "epoch": 66.65, "learning_rate": 1.0206117180039765e-05, "loss": 0.001, "step": 277610 }, { "epoch": 66.65, "learning_rate": 1.0203400674427355e-05, "loss": 0.0019, "step": 277620 }, { "epoch": 66.66, "learning_rate": 1.0200684489302475e-05, "loss": 0.0011, "step": 277630 }, { "epoch": 66.66, "learning_rate": 1.0197968624686972e-05, "loss": 0.0014, "step": 277640 }, { "epoch": 66.66, "learning_rate": 1.0195253080602707e-05, "loss": 0.0051, "step": 277650 }, { "epoch": 66.66, "learning_rate": 1.019253785707157e-05, "loss": 0.0016, "step": 277660 }, { "epoch": 66.67, "learning_rate": 1.018982295411543e-05, "loss": 0.0025, "step": 277670 }, { "epoch": 66.67, "learning_rate": 1.0187108371756143e-05, "loss": 0.0019, "step": 277680 }, { "epoch": 66.67, "learning_rate": 1.018439411001556e-05, "loss": 0.0013, "step": 277690 }, { "epoch": 66.67, "learning_rate": 1.0181680168915559e-05, "loss": 0.0013, "step": 277700 }, { "epoch": 66.67, "learning_rate": 1.0178966548477974e-05, "loss": 0.0019, "step": 277710 }, { "epoch": 66.68, "learning_rate": 1.0176253248724665e-05, "loss": 0.0026, "step": 277720 }, { "epoch": 66.68, "learning_rate": 1.0173540269677506e-05, "loss": 0.0057, "step": 277730 }, { "epoch": 66.68, "learning_rate": 1.0170827611358318e-05, "loss": 0.0012, "step": 277740 }, { "epoch": 66.68, "learning_rate": 1.0168115273788936e-05, "loss": 0.0012, "step": 277750 }, { "epoch": 66.69, "learning_rate": 1.016540325699124e-05, "loss": 0.0051, "step": 277760 }, { "epoch": 66.69, "learning_rate": 1.0162691560987059e-05, "loss": 0.0012, "step": 277770 }, { "epoch": 66.69, "learning_rate": 1.0159980185798196e-05, "loss": 0.002, "step": 277780 }, { "epoch": 66.69, "learning_rate": 1.0157269131446529e-05, "loss": 0.0017, "step": 277790 }, { "epoch": 66.7, "learning_rate": 1.0154558397953873e-05, "loss": 0.001, "step": 277800 }, { "epoch": 66.7, "learning_rate": 1.015184798534206e-05, "loss": 0.0013, "step": 277810 }, { "epoch": 66.7, "learning_rate": 1.0149137893632916e-05, "loss": 0.0013, "step": 277820 }, { "epoch": 66.7, "learning_rate": 1.0146428122848266e-05, "loss": 0.0009, "step": 277830 }, { "epoch": 66.7, "learning_rate": 1.0143718673009933e-05, "loss": 0.0011, "step": 277840 }, { "epoch": 66.71, "learning_rate": 1.0141009544139735e-05, "loss": 0.0013, "step": 277850 }, { "epoch": 66.71, "learning_rate": 1.0138300736259482e-05, "loss": 0.0013, "step": 277860 }, { "epoch": 66.71, "learning_rate": 1.0135592249391018e-05, "loss": 0.0014, "step": 277870 }, { "epoch": 66.71, "learning_rate": 1.0132884083556121e-05, "loss": 0.0016, "step": 277880 }, { "epoch": 66.72, "learning_rate": 1.0130176238776595e-05, "loss": 0.001, "step": 277890 }, { "epoch": 66.72, "learning_rate": 1.0127468715074284e-05, "loss": 0.0011, "step": 277900 }, { "epoch": 66.72, "learning_rate": 1.0124761512470981e-05, "loss": 0.0015, "step": 277910 }, { "epoch": 66.72, "learning_rate": 1.0122054630988453e-05, "loss": 0.0022, "step": 277920 }, { "epoch": 66.72, "learning_rate": 1.0119348070648537e-05, "loss": 0.0045, "step": 277930 }, { "epoch": 66.73, "learning_rate": 1.0116641831473023e-05, "loss": 0.0014, "step": 277940 }, { "epoch": 66.73, "learning_rate": 1.011393591348369e-05, "loss": 0.0027, "step": 277950 }, { "epoch": 66.73, "learning_rate": 1.0111230316702342e-05, "loss": 0.0011, "step": 277960 }, { "epoch": 66.73, "learning_rate": 1.0108525041150763e-05, "loss": 0.0013, "step": 277970 }, { "epoch": 66.74, "learning_rate": 1.0105820086850742e-05, "loss": 0.0013, "step": 277980 }, { "epoch": 66.74, "learning_rate": 1.0103115453824042e-05, "loss": 0.0096, "step": 277990 }, { "epoch": 66.74, "learning_rate": 1.0100411142092475e-05, "loss": 0.0021, "step": 278000 }, { "epoch": 66.74, "learning_rate": 1.0097707151677821e-05, "loss": 0.0015, "step": 278010 }, { "epoch": 66.75, "learning_rate": 1.0095003482601828e-05, "loss": 0.0015, "step": 278020 }, { "epoch": 66.75, "learning_rate": 1.0092300134886263e-05, "loss": 0.0015, "step": 278030 }, { "epoch": 66.75, "learning_rate": 1.0089597108552928e-05, "loss": 0.0021, "step": 278040 }, { "epoch": 66.75, "learning_rate": 1.0086894403623581e-05, "loss": 0.0039, "step": 278050 }, { "epoch": 66.75, "learning_rate": 1.0084192020119988e-05, "loss": 0.0017, "step": 278060 }, { "epoch": 66.76, "learning_rate": 1.00814899580639e-05, "loss": 0.0011, "step": 278070 }, { "epoch": 66.76, "learning_rate": 1.0078788217477086e-05, "loss": 0.0012, "step": 278080 }, { "epoch": 66.76, "learning_rate": 1.0076086798381301e-05, "loss": 0.0012, "step": 278090 }, { "epoch": 66.76, "learning_rate": 1.0073385700798304e-05, "loss": 0.0013, "step": 278100 }, { "epoch": 66.77, "learning_rate": 1.0070684924749841e-05, "loss": 0.0012, "step": 278110 }, { "epoch": 66.77, "learning_rate": 1.0067984470257668e-05, "loss": 0.0013, "step": 278120 }, { "epoch": 66.77, "learning_rate": 1.0065284337343512e-05, "loss": 0.0013, "step": 278130 }, { "epoch": 66.77, "learning_rate": 1.0062584526029151e-05, "loss": 0.0012, "step": 278140 }, { "epoch": 66.78, "learning_rate": 1.0059885036336325e-05, "loss": 0.0019, "step": 278150 }, { "epoch": 66.78, "learning_rate": 1.0057185868286728e-05, "loss": 0.0014, "step": 278160 }, { "epoch": 66.78, "learning_rate": 1.0054487021902142e-05, "loss": 0.0012, "step": 278170 }, { "epoch": 66.78, "learning_rate": 1.005178849720429e-05, "loss": 0.0016, "step": 278180 }, { "epoch": 66.78, "learning_rate": 1.0049090294214896e-05, "loss": 0.0014, "step": 278190 }, { "epoch": 66.79, "learning_rate": 1.0046392412955696e-05, "loss": 0.0018, "step": 278200 }, { "epoch": 66.79, "learning_rate": 1.0043694853448416e-05, "loss": 0.0009, "step": 278210 }, { "epoch": 66.79, "learning_rate": 1.0040997615714776e-05, "loss": 0.0013, "step": 278220 }, { "epoch": 66.79, "learning_rate": 1.0038300699776498e-05, "loss": 0.0012, "step": 278230 }, { "epoch": 66.8, "learning_rate": 1.00356041056553e-05, "loss": 0.0013, "step": 278240 }, { "epoch": 66.8, "learning_rate": 1.00329078333729e-05, "loss": 0.0013, "step": 278250 }, { "epoch": 66.8, "learning_rate": 1.0030211882951013e-05, "loss": 0.002, "step": 278260 }, { "epoch": 66.8, "learning_rate": 1.0027516254411334e-05, "loss": 0.0066, "step": 278270 }, { "epoch": 66.8, "learning_rate": 1.0024820947775598e-05, "loss": 0.003, "step": 278280 }, { "epoch": 66.81, "learning_rate": 1.0022125963065509e-05, "loss": 0.0016, "step": 278290 }, { "epoch": 66.81, "learning_rate": 1.001943130030274e-05, "loss": 0.0014, "step": 278300 }, { "epoch": 66.81, "learning_rate": 1.0016736959509016e-05, "loss": 0.0013, "step": 278310 }, { "epoch": 66.81, "learning_rate": 1.001404294070603e-05, "loss": 0.0013, "step": 278320 }, { "epoch": 66.82, "learning_rate": 1.001134924391548e-05, "loss": 0.0014, "step": 278330 }, { "epoch": 66.82, "learning_rate": 1.0008655869159055e-05, "loss": 0.0012, "step": 278340 }, { "epoch": 66.82, "learning_rate": 1.0005962816458442e-05, "loss": 0.003, "step": 278350 }, { "epoch": 66.82, "learning_rate": 1.0003270085835336e-05, "loss": 0.0013, "step": 278360 }, { "epoch": 66.83, "learning_rate": 1.0000577677311401e-05, "loss": 0.0015, "step": 278370 }, { "epoch": 66.83, "learning_rate": 9.997885590908351e-06, "loss": 0.0012, "step": 278380 }, { "epoch": 66.83, "learning_rate": 9.995193826647864e-06, "loss": 0.0011, "step": 278390 }, { "epoch": 66.83, "learning_rate": 9.992502384551577e-06, "loss": 0.0012, "step": 278400 }, { "epoch": 66.83, "learning_rate": 9.989811264641208e-06, "loss": 0.0011, "step": 278410 }, { "epoch": 66.84, "learning_rate": 9.987120466938409e-06, "loss": 0.0012, "step": 278420 }, { "epoch": 66.84, "learning_rate": 9.984429991464867e-06, "loss": 0.0019, "step": 278430 }, { "epoch": 66.84, "learning_rate": 9.98173983824221e-06, "loss": 0.0016, "step": 278440 }, { "epoch": 66.84, "learning_rate": 9.97905000729214e-06, "loss": 0.0014, "step": 278450 }, { "epoch": 66.85, "learning_rate": 9.976360498636306e-06, "loss": 0.0011, "step": 278460 }, { "epoch": 66.85, "learning_rate": 9.973671312296362e-06, "loss": 0.0012, "step": 278470 }, { "epoch": 66.85, "learning_rate": 9.970982448293975e-06, "loss": 0.0012, "step": 278480 }, { "epoch": 66.85, "learning_rate": 9.968293906650789e-06, "loss": 0.0014, "step": 278490 }, { "epoch": 66.86, "learning_rate": 9.965605687388457e-06, "loss": 0.0034, "step": 278500 }, { "epoch": 66.86, "learning_rate": 9.96291779052862e-06, "loss": 0.0014, "step": 278510 }, { "epoch": 66.86, "learning_rate": 9.960230216092947e-06, "loss": 0.0042, "step": 278520 }, { "epoch": 66.86, "learning_rate": 9.957542964103078e-06, "loss": 0.0011, "step": 278530 }, { "epoch": 66.86, "learning_rate": 9.954856034580623e-06, "loss": 0.0011, "step": 278540 }, { "epoch": 66.87, "learning_rate": 9.952169427547247e-06, "loss": 0.0009, "step": 278550 }, { "epoch": 66.87, "learning_rate": 9.949483143024585e-06, "loss": 0.0014, "step": 278560 }, { "epoch": 66.87, "learning_rate": 9.946797181034263e-06, "loss": 0.0011, "step": 278570 }, { "epoch": 66.87, "learning_rate": 9.944111541597912e-06, "loss": 0.0013, "step": 278580 }, { "epoch": 66.88, "learning_rate": 9.94142622473716e-06, "loss": 0.001, "step": 278590 }, { "epoch": 66.88, "learning_rate": 9.938741230473635e-06, "loss": 0.0013, "step": 278600 }, { "epoch": 66.88, "learning_rate": 9.936056558828943e-06, "loss": 0.0014, "step": 278610 }, { "epoch": 66.88, "learning_rate": 9.933372209824742e-06, "loss": 0.0016, "step": 278620 }, { "epoch": 66.88, "learning_rate": 9.930688183482622e-06, "loss": 0.0013, "step": 278630 }, { "epoch": 66.89, "learning_rate": 9.928004479824183e-06, "loss": 0.0023, "step": 278640 }, { "epoch": 66.89, "learning_rate": 9.925321098871071e-06, "loss": 0.0013, "step": 278650 }, { "epoch": 66.89, "learning_rate": 9.922638040644877e-06, "loss": 0.0028, "step": 278660 }, { "epoch": 66.89, "learning_rate": 9.919955305167228e-06, "loss": 0.0011, "step": 278670 }, { "epoch": 66.9, "learning_rate": 9.917272892459684e-06, "loss": 0.0014, "step": 278680 }, { "epoch": 66.9, "learning_rate": 9.914590802543894e-06, "loss": 0.0014, "step": 278690 }, { "epoch": 66.9, "learning_rate": 9.91190903544143e-06, "loss": 0.0011, "step": 278700 }, { "epoch": 66.9, "learning_rate": 9.909227591173903e-06, "loss": 0.0021, "step": 278710 }, { "epoch": 66.91, "learning_rate": 9.9065464697629e-06, "loss": 0.0012, "step": 278720 }, { "epoch": 66.91, "learning_rate": 9.903865671230012e-06, "loss": 0.0012, "step": 278730 }, { "epoch": 66.91, "learning_rate": 9.901185195596835e-06, "loss": 0.0021, "step": 278740 }, { "epoch": 66.91, "learning_rate": 9.898505042884931e-06, "loss": 0.0012, "step": 278750 }, { "epoch": 66.91, "learning_rate": 9.895825213115928e-06, "loss": 0.0013, "step": 278760 }, { "epoch": 66.92, "learning_rate": 9.893145706311369e-06, "loss": 0.0014, "step": 278770 }, { "epoch": 66.92, "learning_rate": 9.89046652249283e-06, "loss": 0.0013, "step": 278780 }, { "epoch": 66.92, "learning_rate": 9.887787661681918e-06, "loss": 0.0012, "step": 278790 }, { "epoch": 66.92, "learning_rate": 9.885109123900187e-06, "loss": 0.0026, "step": 278800 }, { "epoch": 66.93, "learning_rate": 9.882430909169215e-06, "loss": 0.0013, "step": 278810 }, { "epoch": 66.93, "learning_rate": 9.879753017510563e-06, "loss": 0.0014, "step": 278820 }, { "epoch": 66.93, "learning_rate": 9.8770754489458e-06, "loss": 0.0016, "step": 278830 }, { "epoch": 66.93, "learning_rate": 9.874398203496487e-06, "loss": 0.0011, "step": 278840 }, { "epoch": 66.94, "learning_rate": 9.87172128118417e-06, "loss": 0.0014, "step": 278850 }, { "epoch": 66.94, "learning_rate": 9.869044682030448e-06, "loss": 0.0022, "step": 278860 }, { "epoch": 66.94, "learning_rate": 9.866368406056836e-06, "loss": 0.0057, "step": 278870 }, { "epoch": 66.94, "learning_rate": 9.863692453284901e-06, "loss": 0.0014, "step": 278880 }, { "epoch": 66.94, "learning_rate": 9.86101682373618e-06, "loss": 0.001, "step": 278890 }, { "epoch": 66.95, "learning_rate": 9.858341517432257e-06, "loss": 0.0011, "step": 278900 }, { "epoch": 66.95, "learning_rate": 9.855666534394641e-06, "loss": 0.0019, "step": 278910 }, { "epoch": 66.95, "learning_rate": 9.852991874644869e-06, "loss": 0.0013, "step": 278920 }, { "epoch": 67.0, "learning_rate": 9.850317538204507e-06, "loss": 0.0055, "step": 278930 }, { "epoch": 67.0, "learning_rate": 9.847643525095085e-06, "loss": 0.0052, "step": 278940 }, { "epoch": 67.01, "learning_rate": 9.844969835338131e-06, "loss": 0.0026, "step": 278950 }, { "epoch": 67.01, "learning_rate": 9.842296468955181e-06, "loss": 0.0011, "step": 278960 }, { "epoch": 67.01, "learning_rate": 9.83962342596776e-06, "loss": 0.0013, "step": 278970 }, { "epoch": 67.01, "learning_rate": 9.836950706397396e-06, "loss": 0.002, "step": 278980 }, { "epoch": 67.02, "learning_rate": 9.834278310265599e-06, "loss": 0.0018, "step": 278990 }, { "epoch": 67.02, "learning_rate": 9.831606237593932e-06, "loss": 0.0037, "step": 279000 }, { "epoch": 67.02, "learning_rate": 9.828934488403868e-06, "loss": 0.0026, "step": 279010 }, { "epoch": 67.02, "learning_rate": 9.826263062716933e-06, "loss": 0.0012, "step": 279020 }, { "epoch": 67.02, "learning_rate": 9.823591960554657e-06, "loss": 0.0013, "step": 279030 }, { "epoch": 67.03, "learning_rate": 9.820921181938547e-06, "loss": 0.0009, "step": 279040 }, { "epoch": 67.03, "learning_rate": 9.8182507268901e-06, "loss": 0.0013, "step": 279050 }, { "epoch": 67.03, "learning_rate": 9.81558059543083e-06, "loss": 0.0015, "step": 279060 }, { "epoch": 67.03, "learning_rate": 9.812910787582235e-06, "loss": 0.001, "step": 279070 }, { "epoch": 67.04, "learning_rate": 9.81024130336582e-06, "loss": 0.0014, "step": 279080 }, { "epoch": 67.04, "learning_rate": 9.80757214280308e-06, "loss": 0.0012, "step": 279090 }, { "epoch": 67.04, "learning_rate": 9.804903305915508e-06, "loss": 0.0015, "step": 279100 }, { "epoch": 67.04, "learning_rate": 9.802234792724602e-06, "loss": 0.0059, "step": 279110 }, { "epoch": 67.05, "learning_rate": 9.799566603251848e-06, "loss": 0.0011, "step": 279120 }, { "epoch": 67.05, "learning_rate": 9.796898737518723e-06, "loss": 0.0021, "step": 279130 }, { "epoch": 67.05, "learning_rate": 9.79423119554675e-06, "loss": 0.0012, "step": 279140 }, { "epoch": 67.05, "learning_rate": 9.791563977357365e-06, "loss": 0.0014, "step": 279150 }, { "epoch": 67.05, "learning_rate": 9.788897082972053e-06, "loss": 0.0034, "step": 279160 }, { "epoch": 67.06, "learning_rate": 9.786230512412326e-06, "loss": 0.0013, "step": 279170 }, { "epoch": 67.06, "learning_rate": 9.78356426569963e-06, "loss": 0.0015, "step": 279180 }, { "epoch": 67.06, "learning_rate": 9.780898342855443e-06, "loss": 0.0021, "step": 279190 }, { "epoch": 67.06, "learning_rate": 9.778232743901233e-06, "loss": 0.0011, "step": 279200 }, { "epoch": 67.07, "learning_rate": 9.77556746885847e-06, "loss": 0.0022, "step": 279210 }, { "epoch": 67.07, "learning_rate": 9.772902517748616e-06, "loss": 0.0014, "step": 279220 }, { "epoch": 67.07, "learning_rate": 9.77023789059313e-06, "loss": 0.0014, "step": 279230 }, { "epoch": 67.07, "learning_rate": 9.767573587413475e-06, "loss": 0.0017, "step": 279240 }, { "epoch": 67.08, "learning_rate": 9.764909608231105e-06, "loss": 0.0019, "step": 279250 }, { "epoch": 67.08, "learning_rate": 9.762245953067456e-06, "loss": 0.0037, "step": 279260 }, { "epoch": 67.08, "learning_rate": 9.759582621944014e-06, "loss": 0.0011, "step": 279270 }, { "epoch": 67.08, "learning_rate": 9.756919614882214e-06, "loss": 0.0011, "step": 279280 }, { "epoch": 67.08, "learning_rate": 9.754256931903489e-06, "loss": 0.001, "step": 279290 }, { "epoch": 67.09, "learning_rate": 9.751594573029276e-06, "loss": 0.0022, "step": 279300 }, { "epoch": 67.09, "learning_rate": 9.748932538281042e-06, "loss": 0.001, "step": 279310 }, { "epoch": 67.09, "learning_rate": 9.746270827680204e-06, "loss": 0.0015, "step": 279320 }, { "epoch": 67.09, "learning_rate": 9.743609441248215e-06, "loss": 0.0048, "step": 279330 }, { "epoch": 67.1, "learning_rate": 9.740948379006488e-06, "loss": 0.0021, "step": 279340 }, { "epoch": 67.1, "learning_rate": 9.738287640976468e-06, "loss": 0.0015, "step": 279350 }, { "epoch": 67.1, "learning_rate": 9.735627227179572e-06, "loss": 0.0013, "step": 279360 }, { "epoch": 67.1, "learning_rate": 9.732967137637217e-06, "loss": 0.0021, "step": 279370 }, { "epoch": 67.1, "learning_rate": 9.730307372370862e-06, "loss": 0.0012, "step": 279380 }, { "epoch": 67.11, "learning_rate": 9.72764793140189e-06, "loss": 0.0011, "step": 279390 }, { "epoch": 67.11, "learning_rate": 9.724988814751718e-06, "loss": 0.0011, "step": 279400 }, { "epoch": 67.11, "learning_rate": 9.722330022441778e-06, "loss": 0.0017, "step": 279410 }, { "epoch": 67.11, "learning_rate": 9.719671554493492e-06, "loss": 0.0012, "step": 279420 }, { "epoch": 67.12, "learning_rate": 9.717013410928227e-06, "loss": 0.0028, "step": 279430 }, { "epoch": 67.12, "learning_rate": 9.714355591767427e-06, "loss": 0.0013, "step": 279440 }, { "epoch": 67.12, "learning_rate": 9.711698097032484e-06, "loss": 0.0012, "step": 279450 }, { "epoch": 67.12, "learning_rate": 9.709040926744795e-06, "loss": 0.0011, "step": 279460 }, { "epoch": 67.13, "learning_rate": 9.706384080925762e-06, "loss": 0.0125, "step": 279470 }, { "epoch": 67.13, "learning_rate": 9.703727559596788e-06, "loss": 0.0017, "step": 279480 }, { "epoch": 67.13, "learning_rate": 9.701071362779251e-06, "loss": 0.0017, "step": 279490 }, { "epoch": 67.13, "learning_rate": 9.69841549049454e-06, "loss": 0.0011, "step": 279500 }, { "epoch": 67.13, "learning_rate": 9.695759942764066e-06, "loss": 0.0012, "step": 279510 }, { "epoch": 67.14, "learning_rate": 9.693104719609213e-06, "loss": 0.0021, "step": 279520 }, { "epoch": 67.14, "learning_rate": 9.690449821051345e-06, "loss": 0.0018, "step": 279530 }, { "epoch": 67.14, "learning_rate": 9.68779524711183e-06, "loss": 0.0022, "step": 279540 }, { "epoch": 67.14, "learning_rate": 9.68514099781208e-06, "loss": 0.0011, "step": 279550 }, { "epoch": 67.15, "learning_rate": 9.682487073173469e-06, "loss": 0.0019, "step": 279560 }, { "epoch": 67.15, "learning_rate": 9.679833473217332e-06, "loss": 0.0011, "step": 279570 }, { "epoch": 67.15, "learning_rate": 9.677180197965074e-06, "loss": 0.0018, "step": 279580 }, { "epoch": 67.15, "learning_rate": 9.674527247438047e-06, "loss": 0.0032, "step": 279590 }, { "epoch": 67.16, "learning_rate": 9.671874621657623e-06, "loss": 0.0016, "step": 279600 }, { "epoch": 67.16, "learning_rate": 9.66922232064516e-06, "loss": 0.0033, "step": 279610 }, { "epoch": 67.16, "learning_rate": 9.66657034442202e-06, "loss": 0.001, "step": 279620 }, { "epoch": 67.16, "learning_rate": 9.663918693009555e-06, "loss": 0.001, "step": 279630 }, { "epoch": 67.16, "learning_rate": 9.661267366429106e-06, "loss": 0.0019, "step": 279640 }, { "epoch": 67.17, "learning_rate": 9.658616364702056e-06, "loss": 0.0044, "step": 279650 }, { "epoch": 67.17, "learning_rate": 9.65596568784975e-06, "loss": 0.0013, "step": 279660 }, { "epoch": 67.17, "learning_rate": 9.653315335893498e-06, "loss": 0.0013, "step": 279670 }, { "epoch": 67.17, "learning_rate": 9.650665308854679e-06, "loss": 0.0015, "step": 279680 }, { "epoch": 67.18, "learning_rate": 9.648015606754624e-06, "loss": 0.0016, "step": 279690 }, { "epoch": 67.18, "learning_rate": 9.645366229614672e-06, "loss": 0.0054, "step": 279700 }, { "epoch": 67.18, "learning_rate": 9.64271717745615e-06, "loss": 0.0018, "step": 279710 }, { "epoch": 67.18, "learning_rate": 9.640068450300404e-06, "loss": 0.0012, "step": 279720 }, { "epoch": 67.18, "learning_rate": 9.63742004816876e-06, "loss": 0.0014, "step": 279730 }, { "epoch": 67.19, "learning_rate": 9.63477197108254e-06, "loss": 0.0011, "step": 279740 }, { "epoch": 67.19, "learning_rate": 9.632124219063077e-06, "loss": 0.0013, "step": 279750 }, { "epoch": 67.19, "learning_rate": 9.629476792131691e-06, "loss": 0.0019, "step": 279760 }, { "epoch": 67.19, "learning_rate": 9.626829690309702e-06, "loss": 0.0026, "step": 279770 }, { "epoch": 67.2, "learning_rate": 9.624182913618413e-06, "loss": 0.0013, "step": 279780 }, { "epoch": 67.2, "learning_rate": 9.621536462079168e-06, "loss": 0.0014, "step": 279790 }, { "epoch": 67.2, "learning_rate": 9.618890335713277e-06, "loss": 0.001, "step": 279800 }, { "epoch": 67.2, "learning_rate": 9.616244534542007e-06, "loss": 0.0013, "step": 279810 }, { "epoch": 67.21, "learning_rate": 9.613599058586714e-06, "loss": 0.0112, "step": 279820 }, { "epoch": 67.21, "learning_rate": 9.610953907868681e-06, "loss": 0.0012, "step": 279830 }, { "epoch": 67.21, "learning_rate": 9.608309082409211e-06, "loss": 0.0014, "step": 279840 }, { "epoch": 67.21, "learning_rate": 9.605664582229606e-06, "loss": 0.0018, "step": 279850 }, { "epoch": 67.21, "learning_rate": 9.60302040735116e-06, "loss": 0.0013, "step": 279860 }, { "epoch": 67.22, "learning_rate": 9.600376557795165e-06, "loss": 0.0011, "step": 279870 }, { "epoch": 67.22, "learning_rate": 9.597733033582906e-06, "loss": 0.0016, "step": 279880 }, { "epoch": 67.22, "learning_rate": 9.59508983473571e-06, "loss": 0.0015, "step": 279890 }, { "epoch": 67.22, "learning_rate": 9.592446961274814e-06, "loss": 0.001, "step": 279900 }, { "epoch": 67.23, "learning_rate": 9.58980441322151e-06, "loss": 0.0016, "step": 279910 }, { "epoch": 67.23, "learning_rate": 9.587162190597104e-06, "loss": 0.001, "step": 279920 }, { "epoch": 67.23, "learning_rate": 9.584520293422861e-06, "loss": 0.0013, "step": 279930 }, { "epoch": 67.23, "learning_rate": 9.581878721720066e-06, "loss": 0.0031, "step": 279940 }, { "epoch": 67.24, "learning_rate": 9.57923747550996e-06, "loss": 0.0019, "step": 279950 }, { "epoch": 67.24, "learning_rate": 9.57659655481385e-06, "loss": 0.0014, "step": 279960 }, { "epoch": 67.24, "learning_rate": 9.573955959652981e-06, "loss": 0.0156, "step": 279970 }, { "epoch": 67.24, "learning_rate": 9.571315690048627e-06, "loss": 0.0012, "step": 279980 }, { "epoch": 67.24, "learning_rate": 9.568675746022054e-06, "loss": 0.0017, "step": 279990 }, { "epoch": 67.25, "learning_rate": 9.566036127594514e-06, "loss": 0.0018, "step": 280000 }, { "epoch": 67.25, "learning_rate": 9.56339683478727e-06, "loss": 0.0019, "step": 280010 }, { "epoch": 67.25, "learning_rate": 9.560757867621556e-06, "loss": 0.0013, "step": 280020 }, { "epoch": 67.25, "learning_rate": 9.558119226118662e-06, "loss": 0.0012, "step": 280030 }, { "epoch": 67.26, "learning_rate": 9.555480910299824e-06, "loss": 0.0017, "step": 280040 }, { "epoch": 67.26, "learning_rate": 9.552842920186256e-06, "loss": 0.0011, "step": 280050 }, { "epoch": 67.26, "learning_rate": 9.550205255799243e-06, "loss": 0.0014, "step": 280060 }, { "epoch": 67.26, "learning_rate": 9.547567917160016e-06, "loss": 0.0012, "step": 280070 }, { "epoch": 67.26, "learning_rate": 9.5449309042898e-06, "loss": 0.001, "step": 280080 }, { "epoch": 67.27, "learning_rate": 9.542294217209846e-06, "loss": 0.0011, "step": 280090 }, { "epoch": 67.27, "learning_rate": 9.539657855941386e-06, "loss": 0.0012, "step": 280100 }, { "epoch": 67.27, "learning_rate": 9.537021820505643e-06, "loss": 0.0028, "step": 280110 }, { "epoch": 67.27, "learning_rate": 9.534386110923838e-06, "loss": 0.0011, "step": 280120 }, { "epoch": 67.28, "learning_rate": 9.53175072721723e-06, "loss": 0.0013, "step": 280130 }, { "epoch": 67.28, "learning_rate": 9.529115669407007e-06, "loss": 0.0012, "step": 280140 }, { "epoch": 67.28, "learning_rate": 9.526480937514399e-06, "loss": 0.0022, "step": 280150 }, { "epoch": 67.28, "learning_rate": 9.523846531560631e-06, "loss": 0.0015, "step": 280160 }, { "epoch": 67.29, "learning_rate": 9.521212451566919e-06, "loss": 0.0028, "step": 280170 }, { "epoch": 67.29, "learning_rate": 9.518578697554487e-06, "loss": 0.0015, "step": 280180 }, { "epoch": 67.29, "learning_rate": 9.515945269544496e-06, "loss": 0.0016, "step": 280190 }, { "epoch": 67.29, "learning_rate": 9.513312167558208e-06, "loss": 0.0013, "step": 280200 }, { "epoch": 67.29, "learning_rate": 9.5106793916168e-06, "loss": 0.0016, "step": 280210 }, { "epoch": 67.3, "learning_rate": 9.508046941741489e-06, "loss": 0.0012, "step": 280220 }, { "epoch": 67.3, "learning_rate": 9.505414817953461e-06, "loss": 0.0023, "step": 280230 }, { "epoch": 67.3, "learning_rate": 9.502783020273915e-06, "loss": 0.0012, "step": 280240 }, { "epoch": 67.3, "learning_rate": 9.50015154872405e-06, "loss": 0.002, "step": 280250 }, { "epoch": 67.31, "learning_rate": 9.49752040332505e-06, "loss": 0.001, "step": 280260 }, { "epoch": 67.31, "learning_rate": 9.494889584098126e-06, "loss": 0.0013, "step": 280270 }, { "epoch": 67.31, "learning_rate": 9.492259091064443e-06, "loss": 0.0012, "step": 280280 }, { "epoch": 67.31, "learning_rate": 9.489628924245175e-06, "loss": 0.0012, "step": 280290 }, { "epoch": 67.32, "learning_rate": 9.48699908366153e-06, "loss": 0.001, "step": 280300 }, { "epoch": 67.32, "learning_rate": 9.484369569334673e-06, "loss": 0.0012, "step": 280310 }, { "epoch": 67.32, "learning_rate": 9.481740381285781e-06, "loss": 0.0017, "step": 280320 }, { "epoch": 67.32, "learning_rate": 9.479111519536032e-06, "loss": 0.0016, "step": 280330 }, { "epoch": 67.32, "learning_rate": 9.476482984106589e-06, "loss": 0.0015, "step": 280340 }, { "epoch": 67.33, "learning_rate": 9.473854775018626e-06, "loss": 0.001, "step": 280350 }, { "epoch": 67.33, "learning_rate": 9.471226892293288e-06, "loss": 0.0032, "step": 280360 }, { "epoch": 67.33, "learning_rate": 9.468599335951783e-06, "loss": 0.001, "step": 280370 }, { "epoch": 67.33, "learning_rate": 9.46597210601523e-06, "loss": 0.0012, "step": 280380 }, { "epoch": 67.34, "learning_rate": 9.463345202504803e-06, "loss": 0.0013, "step": 280390 }, { "epoch": 67.34, "learning_rate": 9.460718625441639e-06, "loss": 0.0061, "step": 280400 }, { "epoch": 67.34, "learning_rate": 9.458092374846928e-06, "loss": 0.0014, "step": 280410 }, { "epoch": 67.34, "learning_rate": 9.455466450741784e-06, "loss": 0.001, "step": 280420 }, { "epoch": 67.34, "learning_rate": 9.452840853147354e-06, "loss": 0.0012, "step": 280430 }, { "epoch": 67.35, "learning_rate": 9.45021558208481e-06, "loss": 0.001, "step": 280440 }, { "epoch": 67.35, "learning_rate": 9.447590637575276e-06, "loss": 0.0013, "step": 280450 }, { "epoch": 67.35, "learning_rate": 9.44496601963989e-06, "loss": 0.0014, "step": 280460 }, { "epoch": 67.35, "learning_rate": 9.442341728299797e-06, "loss": 0.0015, "step": 280470 }, { "epoch": 67.36, "learning_rate": 9.439717763576123e-06, "loss": 0.001, "step": 280480 }, { "epoch": 67.36, "learning_rate": 9.437094125489998e-06, "loss": 0.0014, "step": 280490 }, { "epoch": 67.36, "learning_rate": 9.434470814062546e-06, "loss": 0.0011, "step": 280500 }, { "epoch": 67.36, "learning_rate": 9.431847829314928e-06, "loss": 0.0014, "step": 280510 }, { "epoch": 67.37, "learning_rate": 9.429225171268225e-06, "loss": 0.0032, "step": 280520 }, { "epoch": 67.37, "learning_rate": 9.42660283994356e-06, "loss": 0.0012, "step": 280530 }, { "epoch": 67.37, "learning_rate": 9.423980835362073e-06, "loss": 0.0019, "step": 280540 }, { "epoch": 67.37, "learning_rate": 9.42135915754489e-06, "loss": 0.0018, "step": 280550 }, { "epoch": 67.37, "learning_rate": 9.418737806513073e-06, "loss": 0.0013, "step": 280560 }, { "epoch": 67.38, "learning_rate": 9.416116782287777e-06, "loss": 0.0081, "step": 280570 }, { "epoch": 67.38, "learning_rate": 9.413496084890094e-06, "loss": 0.0016, "step": 280580 }, { "epoch": 67.38, "learning_rate": 9.410875714341133e-06, "loss": 0.0086, "step": 280590 }, { "epoch": 67.38, "learning_rate": 9.408255670661997e-06, "loss": 0.0012, "step": 280600 }, { "epoch": 67.39, "learning_rate": 9.405635953873776e-06, "loss": 0.0036, "step": 280610 }, { "epoch": 67.39, "learning_rate": 9.403016563997574e-06, "loss": 0.0042, "step": 280620 }, { "epoch": 67.39, "learning_rate": 9.400397501054487e-06, "loss": 0.0014, "step": 280630 }, { "epoch": 67.39, "learning_rate": 9.39777876506559e-06, "loss": 0.0011, "step": 280640 }, { "epoch": 67.4, "learning_rate": 9.395160356052014e-06, "loss": 0.0014, "step": 280650 }, { "epoch": 67.4, "learning_rate": 9.3925422740348e-06, "loss": 0.0013, "step": 280660 }, { "epoch": 67.4, "learning_rate": 9.389924519035038e-06, "loss": 0.0054, "step": 280670 }, { "epoch": 67.4, "learning_rate": 9.387307091073833e-06, "loss": 0.0021, "step": 280680 }, { "epoch": 67.4, "learning_rate": 9.384689990172252e-06, "loss": 0.0012, "step": 280690 }, { "epoch": 67.41, "learning_rate": 9.382073216351372e-06, "loss": 0.0021, "step": 280700 }, { "epoch": 67.41, "learning_rate": 9.379456769632261e-06, "loss": 0.0014, "step": 280710 }, { "epoch": 67.41, "learning_rate": 9.376840650035995e-06, "loss": 0.0013, "step": 280720 }, { "epoch": 67.41, "learning_rate": 9.374224857583635e-06, "loss": 0.0013, "step": 280730 }, { "epoch": 67.42, "learning_rate": 9.371609392296255e-06, "loss": 0.0032, "step": 280740 }, { "epoch": 67.42, "learning_rate": 9.368994254194913e-06, "loss": 0.0012, "step": 280750 }, { "epoch": 67.42, "learning_rate": 9.366379443300671e-06, "loss": 0.001, "step": 280760 }, { "epoch": 67.42, "learning_rate": 9.36376495963457e-06, "loss": 0.0013, "step": 280770 }, { "epoch": 67.42, "learning_rate": 9.361150803217694e-06, "loss": 0.0013, "step": 280780 }, { "epoch": 67.43, "learning_rate": 9.358536974071091e-06, "loss": 0.0012, "step": 280790 }, { "epoch": 67.43, "learning_rate": 9.355923472215789e-06, "loss": 0.0021, "step": 280800 }, { "epoch": 67.43, "learning_rate": 9.353310297672834e-06, "loss": 0.0013, "step": 280810 }, { "epoch": 67.43, "learning_rate": 9.350697450463297e-06, "loss": 0.0021, "step": 280820 }, { "epoch": 67.44, "learning_rate": 9.348084930608208e-06, "loss": 0.0013, "step": 280830 }, { "epoch": 67.44, "learning_rate": 9.345472738128597e-06, "loss": 0.0026, "step": 280840 }, { "epoch": 67.44, "learning_rate": 9.342860873045511e-06, "loss": 0.0011, "step": 280850 }, { "epoch": 67.44, "learning_rate": 9.34024933537998e-06, "loss": 0.0014, "step": 280860 }, { "epoch": 67.45, "learning_rate": 9.33763812515303e-06, "loss": 0.0014, "step": 280870 }, { "epoch": 67.45, "learning_rate": 9.335027242385701e-06, "loss": 0.001, "step": 280880 }, { "epoch": 67.45, "learning_rate": 9.332416687099004e-06, "loss": 0.0016, "step": 280890 }, { "epoch": 67.45, "learning_rate": 9.329806459313978e-06, "loss": 0.003, "step": 280900 }, { "epoch": 67.45, "learning_rate": 9.327196559051615e-06, "loss": 0.002, "step": 280910 }, { "epoch": 67.46, "learning_rate": 9.324586986332973e-06, "loss": 0.0013, "step": 280920 }, { "epoch": 67.46, "learning_rate": 9.321977741179055e-06, "loss": 0.0018, "step": 280930 }, { "epoch": 67.46, "learning_rate": 9.319368823610841e-06, "loss": 0.0016, "step": 280940 }, { "epoch": 67.46, "learning_rate": 9.316760233649379e-06, "loss": 0.0014, "step": 280950 }, { "epoch": 67.47, "learning_rate": 9.314151971315666e-06, "loss": 0.0013, "step": 280960 }, { "epoch": 67.47, "learning_rate": 9.311544036630703e-06, "loss": 0.0011, "step": 280970 }, { "epoch": 67.47, "learning_rate": 9.308936429615494e-06, "loss": 0.0009, "step": 280980 }, { "epoch": 67.47, "learning_rate": 9.306329150291038e-06, "loss": 0.0081, "step": 280990 }, { "epoch": 67.48, "learning_rate": 9.303722198678333e-06, "loss": 0.001, "step": 281000 }, { "epoch": 67.48, "learning_rate": 9.301115574798353e-06, "loss": 0.002, "step": 281010 }, { "epoch": 67.48, "learning_rate": 9.298509278672124e-06, "loss": 0.0014, "step": 281020 }, { "epoch": 67.48, "learning_rate": 9.295903310320636e-06, "loss": 0.0012, "step": 281030 }, { "epoch": 67.48, "learning_rate": 9.293297669764838e-06, "loss": 0.0014, "step": 281040 }, { "epoch": 67.49, "learning_rate": 9.290692357025726e-06, "loss": 0.0011, "step": 281050 }, { "epoch": 67.49, "learning_rate": 9.288087372124299e-06, "loss": 0.0011, "step": 281060 }, { "epoch": 67.49, "learning_rate": 9.28548271508154e-06, "loss": 0.0014, "step": 281070 }, { "epoch": 67.49, "learning_rate": 9.28287838591838e-06, "loss": 0.0011, "step": 281080 }, { "epoch": 67.5, "learning_rate": 9.28027438465584e-06, "loss": 0.0013, "step": 281090 }, { "epoch": 67.5, "learning_rate": 9.277670711314868e-06, "loss": 0.0011, "step": 281100 }, { "epoch": 67.5, "learning_rate": 9.27506736591644e-06, "loss": 0.0017, "step": 281110 }, { "epoch": 67.5, "learning_rate": 9.272464348481512e-06, "loss": 0.0063, "step": 281120 }, { "epoch": 67.5, "learning_rate": 9.269861659031055e-06, "loss": 0.0013, "step": 281130 }, { "epoch": 67.51, "learning_rate": 9.267259297586023e-06, "loss": 0.0014, "step": 281140 }, { "epoch": 67.51, "learning_rate": 9.264657264167364e-06, "loss": 0.0011, "step": 281150 }, { "epoch": 67.51, "learning_rate": 9.262055558796057e-06, "loss": 0.0021, "step": 281160 }, { "epoch": 67.51, "learning_rate": 9.259454181493049e-06, "loss": 0.0021, "step": 281170 }, { "epoch": 67.52, "learning_rate": 9.256853132279264e-06, "loss": 0.001, "step": 281180 }, { "epoch": 67.52, "learning_rate": 9.254252411175674e-06, "loss": 0.0012, "step": 281190 }, { "epoch": 67.52, "learning_rate": 9.251652018203211e-06, "loss": 0.0017, "step": 281200 }, { "epoch": 67.52, "learning_rate": 9.249051953382837e-06, "loss": 0.0011, "step": 281210 }, { "epoch": 67.53, "learning_rate": 9.246452216735445e-06, "loss": 0.0009, "step": 281220 }, { "epoch": 67.53, "learning_rate": 9.243852808282017e-06, "loss": 0.0013, "step": 281230 }, { "epoch": 67.53, "learning_rate": 9.241253728043464e-06, "loss": 0.0014, "step": 281240 }, { "epoch": 67.53, "learning_rate": 9.238654976040728e-06, "loss": 0.0021, "step": 281250 }, { "epoch": 67.53, "learning_rate": 9.236056552294725e-06, "loss": 0.0012, "step": 281260 }, { "epoch": 67.54, "learning_rate": 9.233458456826389e-06, "loss": 0.0026, "step": 281270 }, { "epoch": 67.54, "learning_rate": 9.23086068965664e-06, "loss": 0.0017, "step": 281280 }, { "epoch": 67.54, "learning_rate": 9.228263250806384e-06, "loss": 0.0014, "step": 281290 }, { "epoch": 67.54, "learning_rate": 9.225666140296568e-06, "loss": 0.0033, "step": 281300 }, { "epoch": 67.55, "learning_rate": 9.223069358148107e-06, "loss": 0.0018, "step": 281310 }, { "epoch": 67.55, "learning_rate": 9.220472904381866e-06, "loss": 0.0019, "step": 281320 }, { "epoch": 67.55, "learning_rate": 9.217876779018803e-06, "loss": 0.0012, "step": 281330 }, { "epoch": 67.55, "learning_rate": 9.21528098207981e-06, "loss": 0.0012, "step": 281340 }, { "epoch": 67.56, "learning_rate": 9.21268551358579e-06, "loss": 0.0017, "step": 281350 }, { "epoch": 67.56, "learning_rate": 9.21009037355764e-06, "loss": 0.0026, "step": 281360 }, { "epoch": 67.56, "learning_rate": 9.207495562016267e-06, "loss": 0.0012, "step": 281370 }, { "epoch": 67.56, "learning_rate": 9.204901078982565e-06, "loss": 0.0013, "step": 281380 }, { "epoch": 67.56, "learning_rate": 9.20230692447741e-06, "loss": 0.0018, "step": 281390 }, { "epoch": 67.57, "learning_rate": 9.19971309852174e-06, "loss": 0.0013, "step": 281400 }, { "epoch": 67.57, "learning_rate": 9.1971196011364e-06, "loss": 0.0018, "step": 281410 }, { "epoch": 67.57, "learning_rate": 9.194526432342272e-06, "loss": 0.0014, "step": 281420 }, { "epoch": 67.57, "learning_rate": 9.191933592160274e-06, "loss": 0.0017, "step": 281430 }, { "epoch": 67.58, "learning_rate": 9.189341080611264e-06, "loss": 0.0024, "step": 281440 }, { "epoch": 67.58, "learning_rate": 9.18674889771614e-06, "loss": 0.0012, "step": 281450 }, { "epoch": 67.58, "learning_rate": 9.18415704349574e-06, "loss": 0.0013, "step": 281460 }, { "epoch": 67.58, "learning_rate": 9.181565517970964e-06, "loss": 0.0024, "step": 281470 }, { "epoch": 67.58, "learning_rate": 9.178974321162681e-06, "loss": 0.0013, "step": 281480 }, { "epoch": 67.59, "learning_rate": 9.176383453091746e-06, "loss": 0.0013, "step": 281490 }, { "epoch": 67.59, "learning_rate": 9.173792913779038e-06, "loss": 0.0015, "step": 281500 }, { "epoch": 67.59, "learning_rate": 9.171202703245413e-06, "loss": 0.0024, "step": 281510 }, { "epoch": 67.59, "learning_rate": 9.16861282151173e-06, "loss": 0.0026, "step": 281520 }, { "epoch": 67.6, "learning_rate": 9.166023268598828e-06, "loss": 0.0014, "step": 281530 }, { "epoch": 67.6, "learning_rate": 9.163434044527603e-06, "loss": 0.0011, "step": 281540 }, { "epoch": 67.6, "learning_rate": 9.16084514931887e-06, "loss": 0.0014, "step": 281550 }, { "epoch": 67.6, "learning_rate": 9.15825658299348e-06, "loss": 0.0014, "step": 281560 }, { "epoch": 67.61, "learning_rate": 9.155668345572299e-06, "loss": 0.0011, "step": 281570 }, { "epoch": 67.61, "learning_rate": 9.153080437076156e-06, "loss": 0.0018, "step": 281580 }, { "epoch": 67.61, "learning_rate": 9.1504928575259e-06, "loss": 0.0016, "step": 281590 }, { "epoch": 67.61, "learning_rate": 9.147905606942364e-06, "loss": 0.0014, "step": 281600 }, { "epoch": 67.61, "learning_rate": 9.145318685346382e-06, "loss": 0.007, "step": 281610 }, { "epoch": 67.62, "learning_rate": 9.142732092758787e-06, "loss": 0.0015, "step": 281620 }, { "epoch": 67.62, "learning_rate": 9.140145829200402e-06, "loss": 0.0024, "step": 281630 }, { "epoch": 67.62, "learning_rate": 9.137559894692094e-06, "loss": 0.0011, "step": 281640 }, { "epoch": 67.62, "learning_rate": 9.134974289254638e-06, "loss": 0.0011, "step": 281650 }, { "epoch": 67.63, "learning_rate": 9.132389012908876e-06, "loss": 0.0022, "step": 281660 }, { "epoch": 67.63, "learning_rate": 9.129804065675617e-06, "loss": 0.001, "step": 281670 }, { "epoch": 67.63, "learning_rate": 9.127219447575702e-06, "loss": 0.0013, "step": 281680 }, { "epoch": 67.63, "learning_rate": 9.12463515862994e-06, "loss": 0.0025, "step": 281690 }, { "epoch": 67.64, "learning_rate": 9.12205119885911e-06, "loss": 0.0012, "step": 281700 }, { "epoch": 67.64, "learning_rate": 9.119467568284063e-06, "loss": 0.0023, "step": 281710 }, { "epoch": 67.64, "learning_rate": 9.116884266925584e-06, "loss": 0.0028, "step": 281720 }, { "epoch": 67.64, "learning_rate": 9.114301294804479e-06, "loss": 0.0013, "step": 281730 }, { "epoch": 67.64, "learning_rate": 9.111718651941553e-06, "loss": 0.0015, "step": 281740 }, { "epoch": 67.65, "learning_rate": 9.1091363383576e-06, "loss": 0.0011, "step": 281750 }, { "epoch": 67.65, "learning_rate": 9.106554354073415e-06, "loss": 0.0013, "step": 281760 }, { "epoch": 67.65, "learning_rate": 9.103972699109786e-06, "loss": 0.0023, "step": 281770 }, { "epoch": 67.65, "learning_rate": 9.101391373487534e-06, "loss": 0.0012, "step": 281780 }, { "epoch": 67.66, "learning_rate": 9.098810377227406e-06, "loss": 0.0012, "step": 281790 }, { "epoch": 67.66, "learning_rate": 9.096229710350202e-06, "loss": 0.0023, "step": 281800 }, { "epoch": 67.66, "learning_rate": 9.093649372876712e-06, "loss": 0.0026, "step": 281810 }, { "epoch": 67.66, "learning_rate": 9.091069364827714e-06, "loss": 0.0013, "step": 281820 }, { "epoch": 67.66, "learning_rate": 9.088489686223984e-06, "loss": 0.0012, "step": 281830 }, { "epoch": 67.67, "learning_rate": 9.08591033708629e-06, "loss": 0.002, "step": 281840 }, { "epoch": 67.67, "learning_rate": 9.083331317435412e-06, "loss": 0.0013, "step": 281850 }, { "epoch": 67.67, "learning_rate": 9.080752627292116e-06, "loss": 0.0058, "step": 281860 }, { "epoch": 67.67, "learning_rate": 9.078174266677152e-06, "loss": 0.0021, "step": 281870 }, { "epoch": 67.68, "learning_rate": 9.075596235611334e-06, "loss": 0.0014, "step": 281880 }, { "epoch": 67.68, "learning_rate": 9.073018534115368e-06, "loss": 0.0011, "step": 281890 }, { "epoch": 67.68, "learning_rate": 9.070441162210036e-06, "loss": 0.001, "step": 281900 }, { "epoch": 67.68, "learning_rate": 9.06786411991608e-06, "loss": 0.0019, "step": 281910 }, { "epoch": 67.69, "learning_rate": 9.065287407254292e-06, "loss": 0.0011, "step": 281920 }, { "epoch": 67.69, "learning_rate": 9.062711024245385e-06, "loss": 0.0014, "step": 281930 }, { "epoch": 67.69, "learning_rate": 9.0601349709101e-06, "loss": 0.0012, "step": 281940 }, { "epoch": 67.69, "learning_rate": 9.057559247269215e-06, "loss": 0.0015, "step": 281950 }, { "epoch": 67.69, "learning_rate": 9.054983853343462e-06, "loss": 0.0014, "step": 281960 }, { "epoch": 67.7, "learning_rate": 9.052408789153572e-06, "loss": 0.0024, "step": 281970 }, { "epoch": 67.7, "learning_rate": 9.049834054720286e-06, "loss": 0.0014, "step": 281980 }, { "epoch": 67.7, "learning_rate": 9.047259650064343e-06, "loss": 0.0013, "step": 281990 }, { "epoch": 67.7, "learning_rate": 9.044685575206473e-06, "loss": 0.0014, "step": 282000 }, { "epoch": 67.71, "learning_rate": 9.042111830167387e-06, "loss": 0.0032, "step": 282010 }, { "epoch": 67.71, "learning_rate": 9.039538414967857e-06, "loss": 0.0013, "step": 282020 }, { "epoch": 67.71, "learning_rate": 9.036965329628566e-06, "loss": 0.0015, "step": 282030 }, { "epoch": 67.71, "learning_rate": 9.034392574170236e-06, "loss": 0.0016, "step": 282040 }, { "epoch": 67.72, "learning_rate": 9.031820148613613e-06, "loss": 0.0011, "step": 282050 }, { "epoch": 67.72, "learning_rate": 9.029248052979412e-06, "loss": 0.0014, "step": 282060 }, { "epoch": 67.72, "learning_rate": 9.026676287288304e-06, "loss": 0.001, "step": 282070 }, { "epoch": 67.72, "learning_rate": 9.024104851561045e-06, "loss": 0.0012, "step": 282080 }, { "epoch": 67.72, "learning_rate": 9.021533745818323e-06, "loss": 0.0009, "step": 282090 }, { "epoch": 67.73, "learning_rate": 9.018962970080846e-06, "loss": 0.001, "step": 282100 }, { "epoch": 67.73, "learning_rate": 9.016392524369321e-06, "loss": 0.0024, "step": 282110 }, { "epoch": 67.73, "learning_rate": 9.013822408704443e-06, "loss": 0.0013, "step": 282120 }, { "epoch": 67.73, "learning_rate": 9.011252623106914e-06, "loss": 0.0011, "step": 282130 }, { "epoch": 67.74, "learning_rate": 9.008683167597421e-06, "loss": 0.0012, "step": 282140 }, { "epoch": 67.74, "learning_rate": 9.006114042196656e-06, "loss": 0.0017, "step": 282150 }, { "epoch": 67.74, "learning_rate": 9.003545246925338e-06, "loss": 0.0011, "step": 282160 }, { "epoch": 67.74, "learning_rate": 9.000976781804116e-06, "loss": 0.0011, "step": 282170 }, { "epoch": 67.74, "learning_rate": 8.998408646853673e-06, "loss": 0.001, "step": 282180 }, { "epoch": 67.75, "learning_rate": 8.995840842094722e-06, "loss": 0.0012, "step": 282190 }, { "epoch": 67.75, "learning_rate": 8.993273367547921e-06, "loss": 0.0013, "step": 282200 }, { "epoch": 67.75, "learning_rate": 8.990706223233958e-06, "loss": 0.001, "step": 282210 }, { "epoch": 67.75, "learning_rate": 8.988139409173497e-06, "loss": 0.0047, "step": 282220 }, { "epoch": 67.76, "learning_rate": 8.98557292538721e-06, "loss": 0.0021, "step": 282230 }, { "epoch": 67.76, "learning_rate": 8.983006771895763e-06, "loss": 0.0014, "step": 282240 }, { "epoch": 67.76, "learning_rate": 8.980440948719831e-06, "loss": 0.0015, "step": 282250 }, { "epoch": 67.76, "learning_rate": 8.977875455880069e-06, "loss": 0.0011, "step": 282260 }, { "epoch": 67.77, "learning_rate": 8.975310293397143e-06, "loss": 0.0097, "step": 282270 }, { "epoch": 67.77, "learning_rate": 8.972745461291688e-06, "loss": 0.0034, "step": 282280 }, { "epoch": 67.77, "learning_rate": 8.970180959584396e-06, "loss": 0.0011, "step": 282290 }, { "epoch": 67.77, "learning_rate": 8.967616788295912e-06, "loss": 0.0015, "step": 282300 }, { "epoch": 67.77, "learning_rate": 8.965052947446862e-06, "loss": 0.0014, "step": 282310 }, { "epoch": 67.78, "learning_rate": 8.962489437057892e-06, "loss": 0.0014, "step": 282320 }, { "epoch": 67.78, "learning_rate": 8.959926257149675e-06, "loss": 0.0011, "step": 282330 }, { "epoch": 67.78, "learning_rate": 8.957363407742835e-06, "loss": 0.001, "step": 282340 }, { "epoch": 67.78, "learning_rate": 8.954800888858017e-06, "loss": 0.0015, "step": 282350 }, { "epoch": 67.79, "learning_rate": 8.952238700515852e-06, "loss": 0.0024, "step": 282360 }, { "epoch": 67.79, "learning_rate": 8.949676842736975e-06, "loss": 0.0011, "step": 282370 }, { "epoch": 67.79, "learning_rate": 8.94711531554202e-06, "loss": 0.0013, "step": 282380 }, { "epoch": 67.79, "learning_rate": 8.944554118951615e-06, "loss": 0.0009, "step": 282390 }, { "epoch": 67.8, "learning_rate": 8.94199325298638e-06, "loss": 0.0013, "step": 282400 }, { "epoch": 67.8, "learning_rate": 8.93943271766694e-06, "loss": 0.0012, "step": 282410 }, { "epoch": 67.8, "learning_rate": 8.936872513013905e-06, "loss": 0.0013, "step": 282420 }, { "epoch": 67.8, "learning_rate": 8.93431263904792e-06, "loss": 0.0013, "step": 282430 }, { "epoch": 67.8, "learning_rate": 8.931753095789597e-06, "loss": 0.0013, "step": 282440 }, { "epoch": 67.81, "learning_rate": 8.929193883259513e-06, "loss": 0.0015, "step": 282450 }, { "epoch": 67.81, "learning_rate": 8.926635001478312e-06, "loss": 0.0029, "step": 282460 }, { "epoch": 67.81, "learning_rate": 8.92407645046659e-06, "loss": 0.0012, "step": 282470 }, { "epoch": 67.81, "learning_rate": 8.921518230244946e-06, "loss": 0.0014, "step": 282480 }, { "epoch": 67.82, "learning_rate": 8.918960340833992e-06, "loss": 0.001, "step": 282490 }, { "epoch": 67.82, "learning_rate": 8.916402782254324e-06, "loss": 0.0017, "step": 282500 }, { "epoch": 67.82, "learning_rate": 8.913845554526533e-06, "loss": 0.0013, "step": 282510 }, { "epoch": 67.82, "learning_rate": 8.911288657671218e-06, "loss": 0.0012, "step": 282520 }, { "epoch": 67.82, "learning_rate": 8.908732091708954e-06, "loss": 0.0013, "step": 282530 }, { "epoch": 67.83, "learning_rate": 8.906175856660366e-06, "loss": 0.0011, "step": 282540 }, { "epoch": 67.83, "learning_rate": 8.903619952546011e-06, "loss": 0.0011, "step": 282550 }, { "epoch": 67.83, "learning_rate": 8.901064379386459e-06, "loss": 0.0012, "step": 282560 }, { "epoch": 67.83, "learning_rate": 8.898509137202327e-06, "loss": 0.0012, "step": 282570 }, { "epoch": 67.84, "learning_rate": 8.895954226014186e-06, "loss": 0.0034, "step": 282580 }, { "epoch": 67.84, "learning_rate": 8.893399645842576e-06, "loss": 0.0025, "step": 282590 }, { "epoch": 67.84, "learning_rate": 8.890845396708102e-06, "loss": 0.0017, "step": 282600 }, { "epoch": 67.84, "learning_rate": 8.888291478631333e-06, "loss": 0.0018, "step": 282610 }, { "epoch": 67.85, "learning_rate": 8.885737891632823e-06, "loss": 0.0012, "step": 282620 }, { "epoch": 67.85, "learning_rate": 8.883184635733144e-06, "loss": 0.001, "step": 282630 }, { "epoch": 67.85, "learning_rate": 8.880631710952853e-06, "loss": 0.0033, "step": 282640 }, { "epoch": 67.85, "learning_rate": 8.878079117312516e-06, "loss": 0.0011, "step": 282650 }, { "epoch": 67.85, "learning_rate": 8.875526854832672e-06, "loss": 0.0014, "step": 282660 }, { "epoch": 67.86, "learning_rate": 8.872974923533894e-06, "loss": 0.0011, "step": 282670 }, { "epoch": 67.86, "learning_rate": 8.87042332343675e-06, "loss": 0.0013, "step": 282680 }, { "epoch": 67.86, "learning_rate": 8.867872054561733e-06, "loss": 0.0017, "step": 282690 }, { "epoch": 67.86, "learning_rate": 8.865321116929431e-06, "loss": 0.0012, "step": 282700 }, { "epoch": 67.87, "learning_rate": 8.86277051056038e-06, "loss": 0.0027, "step": 282710 }, { "epoch": 67.87, "learning_rate": 8.860220235475136e-06, "loss": 0.0032, "step": 282720 }, { "epoch": 67.87, "learning_rate": 8.857670291694187e-06, "loss": 0.0028, "step": 282730 }, { "epoch": 67.87, "learning_rate": 8.85512067923811e-06, "loss": 0.001, "step": 282740 }, { "epoch": 67.88, "learning_rate": 8.85257139812743e-06, "loss": 0.0047, "step": 282750 }, { "epoch": 67.88, "learning_rate": 8.850022448382673e-06, "loss": 0.0023, "step": 282760 }, { "epoch": 67.88, "learning_rate": 8.847473830024367e-06, "loss": 0.0012, "step": 282770 }, { "epoch": 67.88, "learning_rate": 8.844925543073035e-06, "loss": 0.0013, "step": 282780 }, { "epoch": 67.88, "learning_rate": 8.8423775875492e-06, "loss": 0.0021, "step": 282790 }, { "epoch": 67.89, "learning_rate": 8.839829963473368e-06, "loss": 0.0013, "step": 282800 }, { "epoch": 67.89, "learning_rate": 8.837282670866076e-06, "loss": 0.0024, "step": 282810 }, { "epoch": 67.89, "learning_rate": 8.834735709747849e-06, "loss": 0.0015, "step": 282820 }, { "epoch": 67.89, "learning_rate": 8.832189080139147e-06, "loss": 0.0021, "step": 282830 }, { "epoch": 67.9, "learning_rate": 8.829642782060527e-06, "loss": 0.0012, "step": 282840 }, { "epoch": 67.9, "learning_rate": 8.827096815532476e-06, "loss": 0.0029, "step": 282850 }, { "epoch": 67.9, "learning_rate": 8.824551180575496e-06, "loss": 0.0019, "step": 282860 }, { "epoch": 67.9, "learning_rate": 8.822005877210093e-06, "loss": 0.001, "step": 282870 }, { "epoch": 67.9, "learning_rate": 8.819460905456762e-06, "loss": 0.0029, "step": 282880 }, { "epoch": 67.91, "learning_rate": 8.816916265336e-06, "loss": 0.001, "step": 282890 }, { "epoch": 67.91, "learning_rate": 8.814371956868278e-06, "loss": 0.002, "step": 282900 }, { "epoch": 67.91, "learning_rate": 8.811827980074134e-06, "loss": 0.0011, "step": 282910 }, { "epoch": 67.91, "learning_rate": 8.80928433497401e-06, "loss": 0.0042, "step": 282920 }, { "epoch": 67.92, "learning_rate": 8.8067410215884e-06, "loss": 0.0017, "step": 282930 }, { "epoch": 67.92, "learning_rate": 8.8041980399378e-06, "loss": 0.0018, "step": 282940 }, { "epoch": 67.92, "learning_rate": 8.80165539004268e-06, "loss": 0.0012, "step": 282950 }, { "epoch": 67.92, "learning_rate": 8.799113071923527e-06, "loss": 0.0027, "step": 282960 }, { "epoch": 67.93, "learning_rate": 8.796571085600786e-06, "loss": 0.0011, "step": 282970 }, { "epoch": 67.93, "learning_rate": 8.794029431094952e-06, "loss": 0.0021, "step": 282980 }, { "epoch": 67.93, "learning_rate": 8.791488108426493e-06, "loss": 0.0017, "step": 282990 }, { "epoch": 67.93, "learning_rate": 8.78894711761587e-06, "loss": 0.0013, "step": 283000 }, { "epoch": 67.93, "learning_rate": 8.786406458683538e-06, "loss": 0.0015, "step": 283010 }, { "epoch": 67.94, "learning_rate": 8.78386613164997e-06, "loss": 0.0013, "step": 283020 }, { "epoch": 67.94, "learning_rate": 8.781326136535622e-06, "loss": 0.0056, "step": 283030 }, { "epoch": 67.94, "learning_rate": 8.778786473360928e-06, "loss": 0.0014, "step": 283040 }, { "epoch": 67.94, "learning_rate": 8.776247142146382e-06, "loss": 0.0023, "step": 283050 }, { "epoch": 67.95, "learning_rate": 8.773708142912396e-06, "loss": 0.001, "step": 283060 }, { "epoch": 67.95, "learning_rate": 8.771169475679419e-06, "loss": 0.0011, "step": 283070 }, { "epoch": 67.95, "learning_rate": 8.76863114046792e-06, "loss": 0.0029, "step": 283080 }, { "epoch": 68.0, "learning_rate": 8.766093137298326e-06, "loss": 0.0012, "step": 283090 }, { "epoch": 68.0, "learning_rate": 8.763555466191077e-06, "loss": 0.0012, "step": 283100 }, { "epoch": 68.01, "learning_rate": 8.761018127166609e-06, "loss": 0.0012, "step": 283110 }, { "epoch": 68.01, "learning_rate": 8.758481120245353e-06, "loss": 0.0013, "step": 283120 }, { "epoch": 68.01, "learning_rate": 8.755944445447745e-06, "loss": 0.0025, "step": 283130 }, { "epoch": 68.01, "learning_rate": 8.753408102794197e-06, "loss": 0.0016, "step": 283140 }, { "epoch": 68.02, "learning_rate": 8.750872092305173e-06, "loss": 0.0012, "step": 283150 }, { "epoch": 68.02, "learning_rate": 8.748336414001057e-06, "loss": 0.0013, "step": 283160 }, { "epoch": 68.02, "learning_rate": 8.745801067902287e-06, "loss": 0.0013, "step": 283170 }, { "epoch": 68.02, "learning_rate": 8.743266054029259e-06, "loss": 0.0012, "step": 283180 }, { "epoch": 68.02, "learning_rate": 8.740731372402422e-06, "loss": 0.0012, "step": 283190 }, { "epoch": 68.03, "learning_rate": 8.738197023042183e-06, "loss": 0.0015, "step": 283200 }, { "epoch": 68.03, "learning_rate": 8.735663005968913e-06, "loss": 0.0012, "step": 283210 }, { "epoch": 68.03, "learning_rate": 8.73312932120306e-06, "loss": 0.0013, "step": 283220 }, { "epoch": 68.03, "learning_rate": 8.73059596876501e-06, "loss": 0.0014, "step": 283230 }, { "epoch": 68.04, "learning_rate": 8.728062948675176e-06, "loss": 0.0011, "step": 283240 }, { "epoch": 68.04, "learning_rate": 8.725530260953941e-06, "loss": 0.0019, "step": 283250 }, { "epoch": 68.04, "learning_rate": 8.722997905621716e-06, "loss": 0.0013, "step": 283260 }, { "epoch": 68.04, "learning_rate": 8.72046588269888e-06, "loss": 0.0013, "step": 283270 }, { "epoch": 68.04, "learning_rate": 8.717934192205823e-06, "loss": 0.0013, "step": 283280 }, { "epoch": 68.05, "learning_rate": 8.715402834162966e-06, "loss": 0.0011, "step": 283290 }, { "epoch": 68.05, "learning_rate": 8.712871808590655e-06, "loss": 0.0013, "step": 283300 }, { "epoch": 68.05, "learning_rate": 8.710341115509279e-06, "loss": 0.0011, "step": 283310 }, { "epoch": 68.05, "learning_rate": 8.707810754939238e-06, "loss": 0.001, "step": 283320 }, { "epoch": 68.06, "learning_rate": 8.705280726900893e-06, "loss": 0.0016, "step": 283330 }, { "epoch": 68.06, "learning_rate": 8.70275103141463e-06, "loss": 0.0011, "step": 283340 }, { "epoch": 68.06, "learning_rate": 8.700221668500814e-06, "loss": 0.001, "step": 283350 }, { "epoch": 68.06, "learning_rate": 8.697692638179811e-06, "loss": 0.0011, "step": 283360 }, { "epoch": 68.07, "learning_rate": 8.695163940471989e-06, "loss": 0.001, "step": 283370 }, { "epoch": 68.07, "learning_rate": 8.692635575397717e-06, "loss": 0.001, "step": 283380 }, { "epoch": 68.07, "learning_rate": 8.690107542977355e-06, "loss": 0.0018, "step": 283390 }, { "epoch": 68.07, "learning_rate": 8.687579843231264e-06, "loss": 0.001, "step": 283400 }, { "epoch": 68.07, "learning_rate": 8.68505247617979e-06, "loss": 0.001, "step": 283410 }, { "epoch": 68.08, "learning_rate": 8.68252544184328e-06, "loss": 0.0011, "step": 283420 }, { "epoch": 68.08, "learning_rate": 8.679998740242123e-06, "loss": 0.0011, "step": 283430 }, { "epoch": 68.08, "learning_rate": 8.677472371396628e-06, "loss": 0.0014, "step": 283440 }, { "epoch": 68.08, "learning_rate": 8.674946335327138e-06, "loss": 0.0013, "step": 283450 }, { "epoch": 68.09, "learning_rate": 8.672420632054028e-06, "loss": 0.0011, "step": 283460 }, { "epoch": 68.09, "learning_rate": 8.669895261597621e-06, "loss": 0.0015, "step": 283470 }, { "epoch": 68.09, "learning_rate": 8.66737022397825e-06, "loss": 0.0029, "step": 283480 }, { "epoch": 68.09, "learning_rate": 8.664845519216252e-06, "loss": 0.001, "step": 283490 }, { "epoch": 68.1, "learning_rate": 8.662321147331958e-06, "loss": 0.0015, "step": 283500 }, { "epoch": 68.1, "learning_rate": 8.659797108345702e-06, "loss": 0.0014, "step": 283510 }, { "epoch": 68.1, "learning_rate": 8.657273402277799e-06, "loss": 0.0016, "step": 283520 }, { "epoch": 68.1, "learning_rate": 8.654750029148601e-06, "loss": 0.0009, "step": 283530 }, { "epoch": 68.1, "learning_rate": 8.652226988978396e-06, "loss": 0.0013, "step": 283540 }, { "epoch": 68.11, "learning_rate": 8.649704281787501e-06, "loss": 0.0011, "step": 283550 }, { "epoch": 68.11, "learning_rate": 8.647181907596264e-06, "loss": 0.0016, "step": 283560 }, { "epoch": 68.11, "learning_rate": 8.644659866424992e-06, "loss": 0.0014, "step": 283570 }, { "epoch": 68.11, "learning_rate": 8.642138158293967e-06, "loss": 0.0012, "step": 283580 }, { "epoch": 68.12, "learning_rate": 8.639616783223504e-06, "loss": 0.0013, "step": 283590 }, { "epoch": 68.12, "learning_rate": 8.63709574123393e-06, "loss": 0.0011, "step": 283600 }, { "epoch": 68.12, "learning_rate": 8.634575032345532e-06, "loss": 0.0011, "step": 283610 }, { "epoch": 68.12, "learning_rate": 8.632054656578615e-06, "loss": 0.0013, "step": 283620 }, { "epoch": 68.12, "learning_rate": 8.629534613953472e-06, "loss": 0.0012, "step": 283630 }, { "epoch": 68.13, "learning_rate": 8.6270149044904e-06, "loss": 0.0013, "step": 283640 }, { "epoch": 68.13, "learning_rate": 8.624495528209686e-06, "loss": 0.003, "step": 283650 }, { "epoch": 68.13, "learning_rate": 8.621976485131611e-06, "loss": 0.0042, "step": 283660 }, { "epoch": 68.13, "learning_rate": 8.619457775276495e-06, "loss": 0.0012, "step": 283670 }, { "epoch": 68.14, "learning_rate": 8.616939398664587e-06, "loss": 0.0012, "step": 283680 }, { "epoch": 68.14, "learning_rate": 8.614421355316165e-06, "loss": 0.001, "step": 283690 }, { "epoch": 68.14, "learning_rate": 8.611903645251535e-06, "loss": 0.0025, "step": 283700 }, { "epoch": 68.14, "learning_rate": 8.609386268490971e-06, "loss": 0.0015, "step": 283710 }, { "epoch": 68.15, "learning_rate": 8.606869225054715e-06, "loss": 0.0049, "step": 283720 }, { "epoch": 68.15, "learning_rate": 8.60435251496306e-06, "loss": 0.0012, "step": 283730 }, { "epoch": 68.15, "learning_rate": 8.601836138236275e-06, "loss": 0.0031, "step": 283740 }, { "epoch": 68.15, "learning_rate": 8.599320094894614e-06, "loss": 0.0011, "step": 283750 }, { "epoch": 68.15, "learning_rate": 8.596804384958346e-06, "loss": 0.0013, "step": 283760 }, { "epoch": 68.16, "learning_rate": 8.59428900844773e-06, "loss": 0.0012, "step": 283770 }, { "epoch": 68.16, "learning_rate": 8.59177396538302e-06, "loss": 0.0015, "step": 283780 }, { "epoch": 68.16, "learning_rate": 8.58925925578446e-06, "loss": 0.0013, "step": 283790 }, { "epoch": 68.16, "learning_rate": 8.58674487967232e-06, "loss": 0.0017, "step": 283800 }, { "epoch": 68.17, "learning_rate": 8.58423083706686e-06, "loss": 0.0018, "step": 283810 }, { "epoch": 68.17, "learning_rate": 8.581717127988287e-06, "loss": 0.001, "step": 283820 }, { "epoch": 68.17, "learning_rate": 8.579203752456854e-06, "loss": 0.0014, "step": 283830 }, { "epoch": 68.17, "learning_rate": 8.57669071049283e-06, "loss": 0.0013, "step": 283840 }, { "epoch": 68.18, "learning_rate": 8.574178002116429e-06, "loss": 0.001, "step": 283850 }, { "epoch": 68.18, "learning_rate": 8.571665627347892e-06, "loss": 0.0016, "step": 283860 }, { "epoch": 68.18, "learning_rate": 8.569153586207451e-06, "loss": 0.0013, "step": 283870 }, { "epoch": 68.18, "learning_rate": 8.566641878715336e-06, "loss": 0.0011, "step": 283880 }, { "epoch": 68.18, "learning_rate": 8.564130504891776e-06, "loss": 0.0011, "step": 283890 }, { "epoch": 68.19, "learning_rate": 8.561619464756998e-06, "loss": 0.0012, "step": 283900 }, { "epoch": 68.19, "learning_rate": 8.559108758331214e-06, "loss": 0.0011, "step": 283910 }, { "epoch": 68.19, "learning_rate": 8.556598385634646e-06, "loss": 0.0012, "step": 283920 }, { "epoch": 68.19, "learning_rate": 8.554088346687506e-06, "loss": 0.0051, "step": 283930 }, { "epoch": 68.2, "learning_rate": 8.551578641510023e-06, "loss": 0.004, "step": 283940 }, { "epoch": 68.2, "learning_rate": 8.549069270122411e-06, "loss": 0.001, "step": 283950 }, { "epoch": 68.2, "learning_rate": 8.546560232544848e-06, "loss": 0.0011, "step": 283960 }, { "epoch": 68.2, "learning_rate": 8.544051528797564e-06, "loss": 0.002, "step": 283970 }, { "epoch": 68.2, "learning_rate": 8.54154315890076e-06, "loss": 0.0034, "step": 283980 }, { "epoch": 68.21, "learning_rate": 8.539035122874633e-06, "loss": 0.0015, "step": 283990 }, { "epoch": 68.21, "learning_rate": 8.536527420739377e-06, "loss": 0.0011, "step": 284000 }, { "epoch": 68.21, "learning_rate": 8.534020052515195e-06, "loss": 0.0013, "step": 284010 }, { "epoch": 68.21, "learning_rate": 8.53151301822227e-06, "loss": 0.0012, "step": 284020 }, { "epoch": 68.22, "learning_rate": 8.5290063178808e-06, "loss": 0.0018, "step": 284030 }, { "epoch": 68.22, "learning_rate": 8.526499951510964e-06, "loss": 0.0011, "step": 284040 }, { "epoch": 68.22, "learning_rate": 8.52399391913295e-06, "loss": 0.0016, "step": 284050 }, { "epoch": 68.22, "learning_rate": 8.521488220766937e-06, "loss": 0.0015, "step": 284060 }, { "epoch": 68.23, "learning_rate": 8.5189828564331e-06, "loss": 0.0037, "step": 284070 }, { "epoch": 68.23, "learning_rate": 8.516477826151626e-06, "loss": 0.0014, "step": 284080 }, { "epoch": 68.23, "learning_rate": 8.513973129942699e-06, "loss": 0.001, "step": 284090 }, { "epoch": 68.23, "learning_rate": 8.511468767826446e-06, "loss": 0.001, "step": 284100 }, { "epoch": 68.23, "learning_rate": 8.508964739823083e-06, "loss": 0.0019, "step": 284110 }, { "epoch": 68.24, "learning_rate": 8.506461045952751e-06, "loss": 0.0011, "step": 284120 }, { "epoch": 68.24, "learning_rate": 8.503957686235613e-06, "loss": 0.0017, "step": 284130 }, { "epoch": 68.24, "learning_rate": 8.501454660691837e-06, "loss": 0.0023, "step": 284140 }, { "epoch": 68.24, "learning_rate": 8.498951969341573e-06, "loss": 0.0017, "step": 284150 }, { "epoch": 68.25, "learning_rate": 8.496449612204982e-06, "loss": 0.0027, "step": 284160 }, { "epoch": 68.25, "learning_rate": 8.493947589302197e-06, "loss": 0.001, "step": 284170 }, { "epoch": 68.25, "learning_rate": 8.491445900653393e-06, "loss": 0.0015, "step": 284180 }, { "epoch": 68.25, "learning_rate": 8.48894454627872e-06, "loss": 0.0015, "step": 284190 }, { "epoch": 68.26, "learning_rate": 8.486443526198285e-06, "loss": 0.0012, "step": 284200 }, { "epoch": 68.26, "learning_rate": 8.483942840432264e-06, "loss": 0.0038, "step": 284210 }, { "epoch": 68.26, "learning_rate": 8.481442489000779e-06, "loss": 0.001, "step": 284220 }, { "epoch": 68.26, "learning_rate": 8.478942471923989e-06, "loss": 0.0011, "step": 284230 }, { "epoch": 68.26, "learning_rate": 8.476442789221978e-06, "loss": 0.0012, "step": 284240 }, { "epoch": 68.27, "learning_rate": 8.473943440914916e-06, "loss": 0.0023, "step": 284250 }, { "epoch": 68.27, "learning_rate": 8.471444427022923e-06, "loss": 0.0011, "step": 284260 }, { "epoch": 68.27, "learning_rate": 8.46894574756612e-06, "loss": 0.0041, "step": 284270 }, { "epoch": 68.27, "learning_rate": 8.466447402564637e-06, "loss": 0.0021, "step": 284280 }, { "epoch": 68.28, "learning_rate": 8.463949392038579e-06, "loss": 0.001, "step": 284290 }, { "epoch": 68.28, "learning_rate": 8.461451716008073e-06, "loss": 0.0011, "step": 284300 }, { "epoch": 68.28, "learning_rate": 8.458954374493223e-06, "loss": 0.0013, "step": 284310 }, { "epoch": 68.28, "learning_rate": 8.456457367514154e-06, "loss": 0.0013, "step": 284320 }, { "epoch": 68.28, "learning_rate": 8.45396069509099e-06, "loss": 0.0011, "step": 284330 }, { "epoch": 68.29, "learning_rate": 8.451464357243783e-06, "loss": 0.0016, "step": 284340 }, { "epoch": 68.29, "learning_rate": 8.448968353992686e-06, "loss": 0.0009, "step": 284350 }, { "epoch": 68.29, "learning_rate": 8.446472685357786e-06, "loss": 0.0011, "step": 284360 }, { "epoch": 68.29, "learning_rate": 8.443977351359173e-06, "loss": 0.0012, "step": 284370 }, { "epoch": 68.3, "learning_rate": 8.44148235201695e-06, "loss": 0.001, "step": 284380 }, { "epoch": 68.3, "learning_rate": 8.438987687351207e-06, "loss": 0.0013, "step": 284390 }, { "epoch": 68.3, "learning_rate": 8.436493357382036e-06, "loss": 0.0013, "step": 284400 }, { "epoch": 68.3, "learning_rate": 8.433999362129507e-06, "loss": 0.0012, "step": 284410 }, { "epoch": 68.31, "learning_rate": 8.431505701613746e-06, "loss": 0.0013, "step": 284420 }, { "epoch": 68.31, "learning_rate": 8.429012375854795e-06, "loss": 0.0013, "step": 284430 }, { "epoch": 68.31, "learning_rate": 8.426519384872733e-06, "loss": 0.0011, "step": 284440 }, { "epoch": 68.31, "learning_rate": 8.424026728687668e-06, "loss": 0.0012, "step": 284450 }, { "epoch": 68.31, "learning_rate": 8.421534407319647e-06, "loss": 0.0012, "step": 284460 }, { "epoch": 68.32, "learning_rate": 8.41904242078877e-06, "loss": 0.0012, "step": 284470 }, { "epoch": 68.32, "learning_rate": 8.416550769115056e-06, "loss": 0.0011, "step": 284480 }, { "epoch": 68.32, "learning_rate": 8.414059452318612e-06, "loss": 0.0033, "step": 284490 }, { "epoch": 68.32, "learning_rate": 8.41156847041949e-06, "loss": 0.0018, "step": 284500 }, { "epoch": 68.33, "learning_rate": 8.40907782343775e-06, "loss": 0.0016, "step": 284510 }, { "epoch": 68.33, "learning_rate": 8.40658751139345e-06, "loss": 0.001, "step": 284520 }, { "epoch": 68.33, "learning_rate": 8.404097534306638e-06, "loss": 0.0013, "step": 284530 }, { "epoch": 68.33, "learning_rate": 8.401607892197371e-06, "loss": 0.0013, "step": 284540 }, { "epoch": 68.34, "learning_rate": 8.399118585085686e-06, "loss": 0.0011, "step": 284550 }, { "epoch": 68.34, "learning_rate": 8.396629612991669e-06, "loss": 0.0011, "step": 284560 }, { "epoch": 68.34, "learning_rate": 8.394140975935327e-06, "loss": 0.002, "step": 284570 }, { "epoch": 68.34, "learning_rate": 8.391652673936701e-06, "loss": 0.0019, "step": 284580 }, { "epoch": 68.34, "learning_rate": 8.389164707015846e-06, "loss": 0.0033, "step": 284590 }, { "epoch": 68.35, "learning_rate": 8.386677075192794e-06, "loss": 0.0014, "step": 284600 }, { "epoch": 68.35, "learning_rate": 8.384189778487584e-06, "loss": 0.0012, "step": 284610 }, { "epoch": 68.35, "learning_rate": 8.381702816920233e-06, "loss": 0.0024, "step": 284620 }, { "epoch": 68.35, "learning_rate": 8.379216190510774e-06, "loss": 0.0012, "step": 284630 }, { "epoch": 68.36, "learning_rate": 8.376729899279234e-06, "loss": 0.001, "step": 284640 }, { "epoch": 68.36, "learning_rate": 8.374243943245624e-06, "loss": 0.0014, "step": 284650 }, { "epoch": 68.36, "learning_rate": 8.371758322429995e-06, "loss": 0.0012, "step": 284660 }, { "epoch": 68.36, "learning_rate": 8.369273036852338e-06, "loss": 0.0012, "step": 284670 }, { "epoch": 68.36, "learning_rate": 8.366788086532667e-06, "loss": 0.0011, "step": 284680 }, { "epoch": 68.37, "learning_rate": 8.364303471490992e-06, "loss": 0.0011, "step": 284690 }, { "epoch": 68.37, "learning_rate": 8.36181919174735e-06, "loss": 0.0014, "step": 284700 }, { "epoch": 68.37, "learning_rate": 8.359335247321715e-06, "loss": 0.0014, "step": 284710 }, { "epoch": 68.37, "learning_rate": 8.356851638234087e-06, "loss": 0.0027, "step": 284720 }, { "epoch": 68.38, "learning_rate": 8.3543683645045e-06, "loss": 0.0016, "step": 284730 }, { "epoch": 68.38, "learning_rate": 8.351885426152927e-06, "loss": 0.0013, "step": 284740 }, { "epoch": 68.38, "learning_rate": 8.349402823199375e-06, "loss": 0.0022, "step": 284750 }, { "epoch": 68.38, "learning_rate": 8.346920555663835e-06, "loss": 0.001, "step": 284760 }, { "epoch": 68.39, "learning_rate": 8.344438623566292e-06, "loss": 0.0017, "step": 284770 }, { "epoch": 68.39, "learning_rate": 8.341957026926733e-06, "loss": 0.0014, "step": 284780 }, { "epoch": 68.39, "learning_rate": 8.339475765765137e-06, "loss": 0.0011, "step": 284790 }, { "epoch": 68.39, "learning_rate": 8.336994840101514e-06, "loss": 0.0012, "step": 284800 }, { "epoch": 68.39, "learning_rate": 8.334514249955816e-06, "loss": 0.0014, "step": 284810 }, { "epoch": 68.4, "learning_rate": 8.33203399534801e-06, "loss": 0.0011, "step": 284820 }, { "epoch": 68.4, "learning_rate": 8.329554076298102e-06, "loss": 0.0013, "step": 284830 }, { "epoch": 68.4, "learning_rate": 8.327074492826048e-06, "loss": 0.0014, "step": 284840 }, { "epoch": 68.4, "learning_rate": 8.324595244951816e-06, "loss": 0.0012, "step": 284850 }, { "epoch": 68.41, "learning_rate": 8.322116332695373e-06, "loss": 0.0012, "step": 284860 }, { "epoch": 68.41, "learning_rate": 8.319637756076681e-06, "loss": 0.0012, "step": 284870 }, { "epoch": 68.41, "learning_rate": 8.317159515115703e-06, "loss": 0.0013, "step": 284880 }, { "epoch": 68.41, "learning_rate": 8.314681609832387e-06, "loss": 0.0011, "step": 284890 }, { "epoch": 68.41, "learning_rate": 8.312204040246702e-06, "loss": 0.0012, "step": 284900 }, { "epoch": 68.42, "learning_rate": 8.309726806378587e-06, "loss": 0.001, "step": 284910 }, { "epoch": 68.42, "learning_rate": 8.307249908248005e-06, "loss": 0.0011, "step": 284920 }, { "epoch": 68.42, "learning_rate": 8.304773345874877e-06, "loss": 0.0011, "step": 284930 }, { "epoch": 68.42, "learning_rate": 8.30229711927919e-06, "loss": 0.0012, "step": 284940 }, { "epoch": 68.43, "learning_rate": 8.299821228480853e-06, "loss": 0.0012, "step": 284950 }, { "epoch": 68.43, "learning_rate": 8.2973456734998e-06, "loss": 0.0011, "step": 284960 }, { "epoch": 68.43, "learning_rate": 8.294870454355992e-06, "loss": 0.001, "step": 284970 }, { "epoch": 68.43, "learning_rate": 8.292395571069345e-06, "loss": 0.0011, "step": 284980 }, { "epoch": 68.44, "learning_rate": 8.289921023659803e-06, "loss": 0.0021, "step": 284990 }, { "epoch": 68.44, "learning_rate": 8.287446812147276e-06, "loss": 0.0014, "step": 285000 }, { "epoch": 68.44, "learning_rate": 8.284972936551705e-06, "loss": 0.0011, "step": 285010 }, { "epoch": 68.44, "learning_rate": 8.282499396893006e-06, "loss": 0.001, "step": 285020 }, { "epoch": 68.44, "learning_rate": 8.280026193191093e-06, "loss": 0.0012, "step": 285030 }, { "epoch": 68.45, "learning_rate": 8.277553325465898e-06, "loss": 0.0013, "step": 285040 }, { "epoch": 68.45, "learning_rate": 8.275080793737316e-06, "loss": 0.0014, "step": 285050 }, { "epoch": 68.45, "learning_rate": 8.272608598025267e-06, "loss": 0.0011, "step": 285060 }, { "epoch": 68.45, "learning_rate": 8.270136738349666e-06, "loss": 0.0064, "step": 285070 }, { "epoch": 68.46, "learning_rate": 8.26766521473043e-06, "loss": 0.0011, "step": 285080 }, { "epoch": 68.46, "learning_rate": 8.265194027187434e-06, "loss": 0.0027, "step": 285090 }, { "epoch": 68.46, "learning_rate": 8.262723175740583e-06, "loss": 0.0015, "step": 285100 }, { "epoch": 68.46, "learning_rate": 8.260252660409795e-06, "loss": 0.0011, "step": 285110 }, { "epoch": 68.47, "learning_rate": 8.257782481214953e-06, "loss": 0.0014, "step": 285120 }, { "epoch": 68.47, "learning_rate": 8.255312638175956e-06, "loss": 0.0012, "step": 285130 }, { "epoch": 68.47, "learning_rate": 8.252843131312688e-06, "loss": 0.0016, "step": 285140 }, { "epoch": 68.47, "learning_rate": 8.250373960645035e-06, "loss": 0.0039, "step": 285150 }, { "epoch": 68.47, "learning_rate": 8.24790512619289e-06, "loss": 0.0017, "step": 285160 }, { "epoch": 68.48, "learning_rate": 8.245436627976111e-06, "loss": 0.0017, "step": 285170 }, { "epoch": 68.48, "learning_rate": 8.242968466014622e-06, "loss": 0.0017, "step": 285180 }, { "epoch": 68.48, "learning_rate": 8.240500640328258e-06, "loss": 0.0012, "step": 285190 }, { "epoch": 68.48, "learning_rate": 8.238033150936902e-06, "loss": 0.0027, "step": 285200 }, { "epoch": 68.49, "learning_rate": 8.235565997860439e-06, "loss": 0.0022, "step": 285210 }, { "epoch": 68.49, "learning_rate": 8.233099181118742e-06, "loss": 0.0012, "step": 285220 }, { "epoch": 68.49, "learning_rate": 8.23063270073164e-06, "loss": 0.001, "step": 285230 }, { "epoch": 68.49, "learning_rate": 8.228166556719024e-06, "loss": 0.0013, "step": 285240 }, { "epoch": 68.49, "learning_rate": 8.225700749100756e-06, "loss": 0.0014, "step": 285250 }, { "epoch": 68.5, "learning_rate": 8.22323527789669e-06, "loss": 0.0017, "step": 285260 }, { "epoch": 68.5, "learning_rate": 8.220770143126671e-06, "loss": 0.0012, "step": 285270 }, { "epoch": 68.5, "learning_rate": 8.218305344810568e-06, "loss": 0.0013, "step": 285280 }, { "epoch": 68.5, "learning_rate": 8.215840882968213e-06, "loss": 0.001, "step": 285290 }, { "epoch": 68.51, "learning_rate": 8.213376757619446e-06, "loss": 0.001, "step": 285300 }, { "epoch": 68.51, "learning_rate": 8.21091296878414e-06, "loss": 0.0011, "step": 285310 }, { "epoch": 68.51, "learning_rate": 8.208449516482136e-06, "loss": 0.0049, "step": 285320 }, { "epoch": 68.51, "learning_rate": 8.20598640073324e-06, "loss": 0.0011, "step": 285330 }, { "epoch": 68.52, "learning_rate": 8.203523621557301e-06, "loss": 0.0013, "step": 285340 }, { "epoch": 68.52, "learning_rate": 8.201061178974162e-06, "loss": 0.0011, "step": 285350 }, { "epoch": 68.52, "learning_rate": 8.198599073003666e-06, "loss": 0.0011, "step": 285360 }, { "epoch": 68.52, "learning_rate": 8.196137303665591e-06, "loss": 0.0011, "step": 285370 }, { "epoch": 68.52, "learning_rate": 8.193675870979811e-06, "loss": 0.0012, "step": 285380 }, { "epoch": 68.53, "learning_rate": 8.191214774966128e-06, "loss": 0.001, "step": 285390 }, { "epoch": 68.53, "learning_rate": 8.188754015644368e-06, "loss": 0.0009, "step": 285400 }, { "epoch": 68.53, "learning_rate": 8.186293593034344e-06, "loss": 0.0012, "step": 285410 }, { "epoch": 68.53, "learning_rate": 8.18383350715587e-06, "loss": 0.001, "step": 285420 }, { "epoch": 68.54, "learning_rate": 8.181373758028753e-06, "loss": 0.0011, "step": 285430 }, { "epoch": 68.54, "learning_rate": 8.1789143456728e-06, "loss": 0.0012, "step": 285440 }, { "epoch": 68.54, "learning_rate": 8.176455270107835e-06, "loss": 0.0018, "step": 285450 }, { "epoch": 68.54, "learning_rate": 8.173996531353662e-06, "loss": 0.0011, "step": 285460 }, { "epoch": 68.55, "learning_rate": 8.17153812943004e-06, "loss": 0.0012, "step": 285470 }, { "epoch": 68.55, "learning_rate": 8.169080064356816e-06, "loss": 0.0016, "step": 285480 }, { "epoch": 68.55, "learning_rate": 8.166622336153756e-06, "loss": 0.0012, "step": 285490 }, { "epoch": 68.55, "learning_rate": 8.164164944840669e-06, "loss": 0.0013, "step": 285500 }, { "epoch": 68.55, "learning_rate": 8.161707890437337e-06, "loss": 0.0012, "step": 285510 }, { "epoch": 68.56, "learning_rate": 8.159251172963544e-06, "loss": 0.0018, "step": 285520 }, { "epoch": 68.56, "learning_rate": 8.156794792439082e-06, "loss": 0.0011, "step": 285530 }, { "epoch": 68.56, "learning_rate": 8.154338748883728e-06, "loss": 0.0016, "step": 285540 }, { "epoch": 68.56, "learning_rate": 8.15188304231726e-06, "loss": 0.0023, "step": 285550 }, { "epoch": 68.57, "learning_rate": 8.149427672759451e-06, "loss": 0.0011, "step": 285560 }, { "epoch": 68.57, "learning_rate": 8.146972640230089e-06, "loss": 0.0013, "step": 285570 }, { "epoch": 68.57, "learning_rate": 8.144517944748914e-06, "loss": 0.001, "step": 285580 }, { "epoch": 68.57, "learning_rate": 8.14206358633573e-06, "loss": 0.0014, "step": 285590 }, { "epoch": 68.57, "learning_rate": 8.139609565010297e-06, "loss": 0.0011, "step": 285600 }, { "epoch": 68.58, "learning_rate": 8.13715588079234e-06, "loss": 0.0013, "step": 285610 }, { "epoch": 68.58, "learning_rate": 8.134702533701666e-06, "loss": 0.0012, "step": 285620 }, { "epoch": 68.58, "learning_rate": 8.132249523758007e-06, "loss": 0.0011, "step": 285630 }, { "epoch": 68.58, "learning_rate": 8.129796850981126e-06, "loss": 0.001, "step": 285640 }, { "epoch": 68.59, "learning_rate": 8.127344515390768e-06, "loss": 0.0014, "step": 285650 }, { "epoch": 68.59, "learning_rate": 8.124892517006689e-06, "loss": 0.0011, "step": 285660 }, { "epoch": 68.59, "learning_rate": 8.122440855848629e-06, "loss": 0.0012, "step": 285670 }, { "epoch": 68.59, "learning_rate": 8.119989531936323e-06, "loss": 0.0011, "step": 285680 }, { "epoch": 68.6, "learning_rate": 8.117538545289549e-06, "loss": 0.0015, "step": 285690 }, { "epoch": 68.6, "learning_rate": 8.115087895928008e-06, "loss": 0.0011, "step": 285700 }, { "epoch": 68.6, "learning_rate": 8.112637583871429e-06, "loss": 0.0013, "step": 285710 }, { "epoch": 68.6, "learning_rate": 8.11018760913958e-06, "loss": 0.0012, "step": 285720 }, { "epoch": 68.6, "learning_rate": 8.107737971752172e-06, "loss": 0.0012, "step": 285730 }, { "epoch": 68.61, "learning_rate": 8.105288671728944e-06, "loss": 0.0011, "step": 285740 }, { "epoch": 68.61, "learning_rate": 8.102839709089588e-06, "loss": 0.0012, "step": 285750 }, { "epoch": 68.61, "learning_rate": 8.10039108385386e-06, "loss": 0.0031, "step": 285760 }, { "epoch": 68.61, "learning_rate": 8.09794279604147e-06, "loss": 0.0019, "step": 285770 }, { "epoch": 68.62, "learning_rate": 8.095494845672125e-06, "loss": 0.0016, "step": 285780 }, { "epoch": 68.62, "learning_rate": 8.093047232765549e-06, "loss": 0.0015, "step": 285790 }, { "epoch": 68.62, "learning_rate": 8.090599957341449e-06, "loss": 0.0017, "step": 285800 }, { "epoch": 68.62, "learning_rate": 8.088153019419531e-06, "loss": 0.0011, "step": 285810 }, { "epoch": 68.63, "learning_rate": 8.085706419019495e-06, "loss": 0.0013, "step": 285820 }, { "epoch": 68.63, "learning_rate": 8.083260156161066e-06, "loss": 0.002, "step": 285830 }, { "epoch": 68.63, "learning_rate": 8.080814230863936e-06, "loss": 0.0013, "step": 285840 }, { "epoch": 68.63, "learning_rate": 8.078368643147776e-06, "loss": 0.0013, "step": 285850 }, { "epoch": 68.63, "learning_rate": 8.075923393032308e-06, "loss": 0.001, "step": 285860 }, { "epoch": 68.64, "learning_rate": 8.073478480537222e-06, "loss": 0.001, "step": 285870 }, { "epoch": 68.64, "learning_rate": 8.071033905682201e-06, "loss": 0.0012, "step": 285880 }, { "epoch": 68.64, "learning_rate": 8.06858966848693e-06, "loss": 0.002, "step": 285890 }, { "epoch": 68.64, "learning_rate": 8.066145768971101e-06, "loss": 0.0012, "step": 285900 }, { "epoch": 68.65, "learning_rate": 8.063702207154383e-06, "loss": 0.0056, "step": 285910 }, { "epoch": 68.65, "learning_rate": 8.061258983056452e-06, "loss": 0.0011, "step": 285920 }, { "epoch": 68.65, "learning_rate": 8.058816096697019e-06, "loss": 0.0013, "step": 285930 }, { "epoch": 68.65, "learning_rate": 8.056373548095714e-06, "loss": 0.0011, "step": 285940 }, { "epoch": 68.65, "learning_rate": 8.053931337272225e-06, "loss": 0.001, "step": 285950 }, { "epoch": 68.66, "learning_rate": 8.051489464246204e-06, "loss": 0.004, "step": 285960 }, { "epoch": 68.66, "learning_rate": 8.049047929037345e-06, "loss": 0.0013, "step": 285970 }, { "epoch": 68.66, "learning_rate": 8.046606731665306e-06, "loss": 0.001, "step": 285980 }, { "epoch": 68.66, "learning_rate": 8.044165872149711e-06, "loss": 0.0009, "step": 285990 }, { "epoch": 68.67, "learning_rate": 8.041725350510255e-06, "loss": 0.0015, "step": 286000 }, { "epoch": 68.67, "learning_rate": 8.039285166766569e-06, "loss": 0.0011, "step": 286010 }, { "epoch": 68.67, "learning_rate": 8.03684532093832e-06, "loss": 0.0012, "step": 286020 }, { "epoch": 68.67, "learning_rate": 8.034405813045148e-06, "loss": 0.0026, "step": 286030 }, { "epoch": 68.68, "learning_rate": 8.031966643106698e-06, "loss": 0.0012, "step": 286040 }, { "epoch": 68.68, "learning_rate": 8.029527811142617e-06, "loss": 0.0013, "step": 286050 }, { "epoch": 68.68, "learning_rate": 8.027089317172525e-06, "loss": 0.0017, "step": 286060 }, { "epoch": 68.68, "learning_rate": 8.024651161216107e-06, "loss": 0.0132, "step": 286070 }, { "epoch": 68.68, "learning_rate": 8.022213343292956e-06, "loss": 0.004, "step": 286080 }, { "epoch": 68.69, "learning_rate": 8.019775863422702e-06, "loss": 0.0011, "step": 286090 }, { "epoch": 68.69, "learning_rate": 8.017338721625006e-06, "loss": 0.0022, "step": 286100 }, { "epoch": 68.69, "learning_rate": 8.01490191791947e-06, "loss": 0.0015, "step": 286110 }, { "epoch": 68.69, "learning_rate": 8.012465452325729e-06, "loss": 0.0012, "step": 286120 }, { "epoch": 68.7, "learning_rate": 8.010029324863399e-06, "loss": 0.0016, "step": 286130 }, { "epoch": 68.7, "learning_rate": 8.007593535552106e-06, "loss": 0.0011, "step": 286140 }, { "epoch": 68.7, "learning_rate": 8.005158084411452e-06, "loss": 0.0014, "step": 286150 }, { "epoch": 68.7, "learning_rate": 8.002722971461046e-06, "loss": 0.0069, "step": 286160 }, { "epoch": 68.71, "learning_rate": 8.00028819672054e-06, "loss": 0.0011, "step": 286170 }, { "epoch": 68.71, "learning_rate": 7.997853760209495e-06, "loss": 0.001, "step": 286180 }, { "epoch": 68.71, "learning_rate": 7.995419661947534e-06, "loss": 0.0013, "step": 286190 }, { "epoch": 68.71, "learning_rate": 7.992985901954242e-06, "loss": 0.0032, "step": 286200 }, { "epoch": 68.71, "learning_rate": 7.990552480249263e-06, "loss": 0.0013, "step": 286210 }, { "epoch": 68.72, "learning_rate": 7.98811939685215e-06, "loss": 0.001, "step": 286220 }, { "epoch": 68.72, "learning_rate": 7.985686651782504e-06, "loss": 0.0014, "step": 286230 }, { "epoch": 68.72, "learning_rate": 7.98325424505993e-06, "loss": 0.0017, "step": 286240 }, { "epoch": 68.72, "learning_rate": 7.980822176704012e-06, "loss": 0.0014, "step": 286250 }, { "epoch": 68.73, "learning_rate": 7.978390446734335e-06, "loss": 0.0017, "step": 286260 }, { "epoch": 68.73, "learning_rate": 7.975959055170479e-06, "loss": 0.001, "step": 286270 }, { "epoch": 68.73, "learning_rate": 7.973528002032028e-06, "loss": 0.0039, "step": 286280 }, { "epoch": 68.73, "learning_rate": 7.971097287338559e-06, "loss": 0.0026, "step": 286290 }, { "epoch": 68.73, "learning_rate": 7.968666911109635e-06, "loss": 0.0016, "step": 286300 }, { "epoch": 68.74, "learning_rate": 7.966236873364857e-06, "loss": 0.0011, "step": 286310 }, { "epoch": 68.74, "learning_rate": 7.963807174123773e-06, "loss": 0.0048, "step": 286320 }, { "epoch": 68.74, "learning_rate": 7.961377813405934e-06, "loss": 0.0012, "step": 286330 }, { "epoch": 68.74, "learning_rate": 7.95894879123094e-06, "loss": 0.0015, "step": 286340 }, { "epoch": 68.75, "learning_rate": 7.956520107618349e-06, "loss": 0.0011, "step": 286350 }, { "epoch": 68.75, "learning_rate": 7.954091762587678e-06, "loss": 0.0024, "step": 286360 }, { "epoch": 68.75, "learning_rate": 7.951663756158522e-06, "loss": 0.0014, "step": 286370 }, { "epoch": 68.75, "learning_rate": 7.949236088350426e-06, "loss": 0.001, "step": 286380 }, { "epoch": 68.76, "learning_rate": 7.946808759182934e-06, "loss": 0.0009, "step": 286390 }, { "epoch": 68.76, "learning_rate": 7.944381768675602e-06, "loss": 0.0011, "step": 286400 }, { "epoch": 68.76, "learning_rate": 7.941955116847966e-06, "loss": 0.0013, "step": 286410 }, { "epoch": 68.76, "learning_rate": 7.939528803719571e-06, "loss": 0.001, "step": 286420 }, { "epoch": 68.76, "learning_rate": 7.937102829309961e-06, "loss": 0.0086, "step": 286430 }, { "epoch": 68.77, "learning_rate": 7.934677193638651e-06, "loss": 0.0013, "step": 286440 }, { "epoch": 68.77, "learning_rate": 7.932251896725224e-06, "loss": 0.0014, "step": 286450 }, { "epoch": 68.77, "learning_rate": 7.929826938589163e-06, "loss": 0.0013, "step": 286460 }, { "epoch": 68.77, "learning_rate": 7.927402319250004e-06, "loss": 0.001, "step": 286470 }, { "epoch": 68.78, "learning_rate": 7.9249780387273e-06, "loss": 0.0013, "step": 286480 }, { "epoch": 68.78, "learning_rate": 7.922554097040547e-06, "loss": 0.0013, "step": 286490 }, { "epoch": 68.78, "learning_rate": 7.920130494209282e-06, "loss": 0.0012, "step": 286500 }, { "epoch": 68.78, "learning_rate": 7.917707230253013e-06, "loss": 0.0015, "step": 286510 }, { "epoch": 68.79, "learning_rate": 7.915284305191256e-06, "loss": 0.0014, "step": 286520 }, { "epoch": 68.79, "learning_rate": 7.912861719043525e-06, "loss": 0.0114, "step": 286530 }, { "epoch": 68.79, "learning_rate": 7.910439471829329e-06, "loss": 0.0012, "step": 286540 }, { "epoch": 68.79, "learning_rate": 7.908017563568177e-06, "loss": 0.0012, "step": 286550 }, { "epoch": 68.79, "learning_rate": 7.905595994279568e-06, "loss": 0.0011, "step": 286560 }, { "epoch": 68.8, "learning_rate": 7.903174763983001e-06, "loss": 0.0012, "step": 286570 }, { "epoch": 68.8, "learning_rate": 7.900753872697985e-06, "loss": 0.001, "step": 286580 }, { "epoch": 68.8, "learning_rate": 7.898333320444023e-06, "loss": 0.0086, "step": 286590 }, { "epoch": 68.8, "learning_rate": 7.895913107240582e-06, "loss": 0.0013, "step": 286600 }, { "epoch": 68.81, "learning_rate": 7.893493233107158e-06, "loss": 0.001, "step": 286610 }, { "epoch": 68.81, "learning_rate": 7.891073698063251e-06, "loss": 0.0013, "step": 286620 }, { "epoch": 68.81, "learning_rate": 7.888654502128345e-06, "loss": 0.0011, "step": 286630 }, { "epoch": 68.81, "learning_rate": 7.88623564532192e-06, "loss": 0.002, "step": 286640 }, { "epoch": 68.81, "learning_rate": 7.883817127663451e-06, "loss": 0.0024, "step": 286650 }, { "epoch": 68.82, "learning_rate": 7.881398949172419e-06, "loss": 0.0011, "step": 286660 }, { "epoch": 68.82, "learning_rate": 7.878981109868295e-06, "loss": 0.0026, "step": 286670 }, { "epoch": 68.82, "learning_rate": 7.876563609770554e-06, "loss": 0.0011, "step": 286680 }, { "epoch": 68.82, "learning_rate": 7.874146448898657e-06, "loss": 0.0012, "step": 286690 }, { "epoch": 68.83, "learning_rate": 7.87172962727208e-06, "loss": 0.0018, "step": 286700 }, { "epoch": 68.83, "learning_rate": 7.869313144910263e-06, "loss": 0.0022, "step": 286710 }, { "epoch": 68.83, "learning_rate": 7.866897001832696e-06, "loss": 0.0011, "step": 286720 }, { "epoch": 68.83, "learning_rate": 7.864481198058843e-06, "loss": 0.0011, "step": 286730 }, { "epoch": 68.84, "learning_rate": 7.86206573360811e-06, "loss": 0.0013, "step": 286740 }, { "epoch": 68.84, "learning_rate": 7.85965060849999e-06, "loss": 0.001, "step": 286750 }, { "epoch": 68.84, "learning_rate": 7.857235822753928e-06, "loss": 0.0027, "step": 286760 }, { "epoch": 68.84, "learning_rate": 7.85482137638936e-06, "loss": 0.0012, "step": 286770 }, { "epoch": 68.84, "learning_rate": 7.852407269425733e-06, "loss": 0.0024, "step": 286780 }, { "epoch": 68.85, "learning_rate": 7.849993501882492e-06, "loss": 0.0009, "step": 286790 }, { "epoch": 68.85, "learning_rate": 7.847580073779071e-06, "loss": 0.001, "step": 286800 }, { "epoch": 68.85, "learning_rate": 7.845166985134906e-06, "loss": 0.001, "step": 286810 }, { "epoch": 68.85, "learning_rate": 7.842754235969418e-06, "loss": 0.0011, "step": 286820 }, { "epoch": 68.86, "learning_rate": 7.840341826302077e-06, "loss": 0.001, "step": 286830 }, { "epoch": 68.86, "learning_rate": 7.837929756152268e-06, "loss": 0.0011, "step": 286840 }, { "epoch": 68.86, "learning_rate": 7.835518025539423e-06, "loss": 0.0042, "step": 286850 }, { "epoch": 68.86, "learning_rate": 7.833106634482985e-06, "loss": 0.0009, "step": 286860 }, { "epoch": 68.87, "learning_rate": 7.830695583002373e-06, "loss": 0.0012, "step": 286870 }, { "epoch": 68.87, "learning_rate": 7.828284871116964e-06, "loss": 0.0017, "step": 286880 }, { "epoch": 68.87, "learning_rate": 7.825874498846213e-06, "loss": 0.0012, "step": 286890 }, { "epoch": 68.87, "learning_rate": 7.823464466209518e-06, "loss": 0.0019, "step": 286900 }, { "epoch": 68.87, "learning_rate": 7.821054773226289e-06, "loss": 0.0011, "step": 286910 }, { "epoch": 68.88, "learning_rate": 7.818645419915926e-06, "loss": 0.0013, "step": 286920 }, { "epoch": 68.88, "learning_rate": 7.816236406297834e-06, "loss": 0.0029, "step": 286930 }, { "epoch": 68.88, "learning_rate": 7.813827732391415e-06, "loss": 0.0012, "step": 286940 }, { "epoch": 68.88, "learning_rate": 7.811419398216052e-06, "loss": 0.0011, "step": 286950 }, { "epoch": 68.89, "learning_rate": 7.809011403791166e-06, "loss": 0.0016, "step": 286960 }, { "epoch": 68.89, "learning_rate": 7.80660374913615e-06, "loss": 0.0011, "step": 286970 }, { "epoch": 68.89, "learning_rate": 7.80419643427035e-06, "loss": 0.0013, "step": 286980 }, { "epoch": 68.89, "learning_rate": 7.801789459213199e-06, "loss": 0.0011, "step": 286990 }, { "epoch": 68.89, "learning_rate": 7.799382823984064e-06, "loss": 0.001, "step": 287000 }, { "epoch": 68.9, "learning_rate": 7.796976528602335e-06, "loss": 0.0013, "step": 287010 }, { "epoch": 68.9, "learning_rate": 7.794570573087357e-06, "loss": 0.0011, "step": 287020 }, { "epoch": 68.9, "learning_rate": 7.792164957458537e-06, "loss": 0.0013, "step": 287030 }, { "epoch": 68.9, "learning_rate": 7.789759681735242e-06, "loss": 0.0011, "step": 287040 }, { "epoch": 68.91, "learning_rate": 7.787354745936843e-06, "loss": 0.001, "step": 287050 }, { "epoch": 68.91, "learning_rate": 7.784950150082704e-06, "loss": 0.0011, "step": 287060 }, { "epoch": 68.91, "learning_rate": 7.782545894192184e-06, "loss": 0.0012, "step": 287070 }, { "epoch": 68.91, "learning_rate": 7.780141978284655e-06, "loss": 0.0016, "step": 287080 }, { "epoch": 68.92, "learning_rate": 7.777738402379458e-06, "loss": 0.001, "step": 287090 }, { "epoch": 68.92, "learning_rate": 7.775335166495973e-06, "loss": 0.0013, "step": 287100 }, { "epoch": 68.92, "learning_rate": 7.77293227065356e-06, "loss": 0.0011, "step": 287110 }, { "epoch": 68.92, "learning_rate": 7.770529714871527e-06, "loss": 0.0009, "step": 287120 }, { "epoch": 68.92, "learning_rate": 7.768127499169258e-06, "loss": 0.0019, "step": 287130 }, { "epoch": 68.93, "learning_rate": 7.765725623566095e-06, "loss": 0.0012, "step": 287140 }, { "epoch": 68.93, "learning_rate": 7.76332408808137e-06, "loss": 0.0012, "step": 287150 }, { "epoch": 68.93, "learning_rate": 7.760922892734424e-06, "loss": 0.0014, "step": 287160 }, { "epoch": 68.93, "learning_rate": 7.758522037544602e-06, "loss": 0.0011, "step": 287170 }, { "epoch": 68.94, "learning_rate": 7.756121522531235e-06, "loss": 0.0011, "step": 287180 }, { "epoch": 68.94, "learning_rate": 7.753721347713638e-06, "loss": 0.0011, "step": 287190 }, { "epoch": 68.94, "learning_rate": 7.751321513111176e-06, "loss": 0.0013, "step": 287200 }, { "epoch": 68.94, "learning_rate": 7.748922018743148e-06, "loss": 0.0014, "step": 287210 }, { "epoch": 68.95, "learning_rate": 7.746522864628874e-06, "loss": 0.0017, "step": 287220 }, { "epoch": 68.95, "learning_rate": 7.744124050787694e-06, "loss": 0.0013, "step": 287230 }, { "epoch": 68.95, "learning_rate": 7.741725577238917e-06, "loss": 0.0011, "step": 287240 }, { "epoch": 69.0, "learning_rate": 7.73932744400187e-06, "loss": 0.0013, "step": 287250 }, { "epoch": 69.0, "learning_rate": 7.73692965109583e-06, "loss": 0.0029, "step": 287260 }, { "epoch": 69.01, "learning_rate": 7.73453219854014e-06, "loss": 0.0019, "step": 287270 }, { "epoch": 69.01, "learning_rate": 7.732135086354098e-06, "loss": 0.0019, "step": 287280 }, { "epoch": 69.01, "learning_rate": 7.729738314557012e-06, "loss": 0.0012, "step": 287290 }, { "epoch": 69.01, "learning_rate": 7.727341883168176e-06, "loss": 0.001, "step": 287300 }, { "epoch": 69.01, "learning_rate": 7.724945792206889e-06, "loss": 0.0021, "step": 287310 }, { "epoch": 69.02, "learning_rate": 7.722550041692455e-06, "loss": 0.0021, "step": 287320 }, { "epoch": 69.02, "learning_rate": 7.72015463164415e-06, "loss": 0.0033, "step": 287330 }, { "epoch": 69.02, "learning_rate": 7.717759562081284e-06, "loss": 0.0011, "step": 287340 }, { "epoch": 69.02, "learning_rate": 7.715364833023153e-06, "loss": 0.0011, "step": 287350 }, { "epoch": 69.03, "learning_rate": 7.712970444489004e-06, "loss": 0.0012, "step": 287360 }, { "epoch": 69.03, "learning_rate": 7.710576396498148e-06, "loss": 0.0045, "step": 287370 }, { "epoch": 69.03, "learning_rate": 7.708182689069865e-06, "loss": 0.0015, "step": 287380 }, { "epoch": 69.03, "learning_rate": 7.705789322223422e-06, "loss": 0.0013, "step": 287390 }, { "epoch": 69.03, "learning_rate": 7.7033962959781e-06, "loss": 0.0011, "step": 287400 }, { "epoch": 69.04, "learning_rate": 7.701003610353164e-06, "loss": 0.0015, "step": 287410 }, { "epoch": 69.04, "learning_rate": 7.698611265367888e-06, "loss": 0.0017, "step": 287420 }, { "epoch": 69.04, "learning_rate": 7.696219261041527e-06, "loss": 0.0012, "step": 287430 }, { "epoch": 69.04, "learning_rate": 7.693827597393372e-06, "loss": 0.0012, "step": 287440 }, { "epoch": 69.05, "learning_rate": 7.691436274442648e-06, "loss": 0.0016, "step": 287450 }, { "epoch": 69.05, "learning_rate": 7.689045292208635e-06, "loss": 0.0014, "step": 287460 }, { "epoch": 69.05, "learning_rate": 7.686654650710568e-06, "loss": 0.0011, "step": 287470 }, { "epoch": 69.05, "learning_rate": 7.684264349967724e-06, "loss": 0.003, "step": 287480 }, { "epoch": 69.06, "learning_rate": 7.681874389999355e-06, "loss": 0.0015, "step": 287490 }, { "epoch": 69.06, "learning_rate": 7.679484770824669e-06, "loss": 0.0029, "step": 287500 }, { "epoch": 69.06, "learning_rate": 7.677095492462944e-06, "loss": 0.0011, "step": 287510 }, { "epoch": 69.06, "learning_rate": 7.674706554933414e-06, "loss": 0.001, "step": 287520 }, { "epoch": 69.06, "learning_rate": 7.67231795825532e-06, "loss": 0.0024, "step": 287530 }, { "epoch": 69.07, "learning_rate": 7.669929702447886e-06, "loss": 0.0025, "step": 287540 }, { "epoch": 69.07, "learning_rate": 7.667541787530358e-06, "loss": 0.001, "step": 287550 }, { "epoch": 69.07, "learning_rate": 7.665154213521958e-06, "loss": 0.0012, "step": 287560 }, { "epoch": 69.07, "learning_rate": 7.662766980441905e-06, "loss": 0.0028, "step": 287570 }, { "epoch": 69.08, "learning_rate": 7.660380088309455e-06, "loss": 0.002, "step": 287580 }, { "epoch": 69.08, "learning_rate": 7.657993537143798e-06, "loss": 0.0011, "step": 287590 }, { "epoch": 69.08, "learning_rate": 7.655607326964154e-06, "loss": 0.0012, "step": 287600 }, { "epoch": 69.08, "learning_rate": 7.653221457789762e-06, "loss": 0.001, "step": 287610 }, { "epoch": 69.09, "learning_rate": 7.650835929639827e-06, "loss": 0.0012, "step": 287620 }, { "epoch": 69.09, "learning_rate": 7.648450742533552e-06, "loss": 0.001, "step": 287630 }, { "epoch": 69.09, "learning_rate": 7.646065896490156e-06, "loss": 0.0062, "step": 287640 }, { "epoch": 69.09, "learning_rate": 7.643681391528834e-06, "loss": 0.001, "step": 287650 }, { "epoch": 69.09, "learning_rate": 7.641297227668793e-06, "loss": 0.001, "step": 287660 }, { "epoch": 69.1, "learning_rate": 7.638913404929226e-06, "loss": 0.0014, "step": 287670 }, { "epoch": 69.1, "learning_rate": 7.636529923329355e-06, "loss": 0.0011, "step": 287680 }, { "epoch": 69.1, "learning_rate": 7.634146782888351e-06, "loss": 0.0034, "step": 287690 }, { "epoch": 69.1, "learning_rate": 7.631763983625412e-06, "loss": 0.0012, "step": 287700 }, { "epoch": 69.11, "learning_rate": 7.629381525559709e-06, "loss": 0.001, "step": 287710 }, { "epoch": 69.11, "learning_rate": 7.626999408710472e-06, "loss": 0.0012, "step": 287720 }, { "epoch": 69.11, "learning_rate": 7.624617633096854e-06, "loss": 0.0018, "step": 287730 }, { "epoch": 69.11, "learning_rate": 7.62223619873802e-06, "loss": 0.001, "step": 287740 }, { "epoch": 69.11, "learning_rate": 7.619855105653184e-06, "loss": 0.0012, "step": 287750 }, { "epoch": 69.12, "learning_rate": 7.617474353861504e-06, "loss": 0.0015, "step": 287760 }, { "epoch": 69.12, "learning_rate": 7.615093943382157e-06, "loss": 0.0021, "step": 287770 }, { "epoch": 69.12, "learning_rate": 7.6127138742343115e-06, "loss": 0.002, "step": 287780 }, { "epoch": 69.12, "learning_rate": 7.6103341464371255e-06, "loss": 0.0014, "step": 287790 }, { "epoch": 69.13, "learning_rate": 7.607954760009778e-06, "loss": 0.0013, "step": 287800 }, { "epoch": 69.13, "learning_rate": 7.605575714971408e-06, "loss": 0.001, "step": 287810 }, { "epoch": 69.13, "learning_rate": 7.603197011341218e-06, "loss": 0.0012, "step": 287820 }, { "epoch": 69.13, "learning_rate": 7.600818649138319e-06, "loss": 0.0055, "step": 287830 }, { "epoch": 69.14, "learning_rate": 7.59844062838187e-06, "loss": 0.0039, "step": 287840 }, { "epoch": 69.14, "learning_rate": 7.596062949091043e-06, "loss": 0.0011, "step": 287850 }, { "epoch": 69.14, "learning_rate": 7.5936856112849896e-06, "loss": 0.0014, "step": 287860 }, { "epoch": 69.14, "learning_rate": 7.591308614982828e-06, "loss": 0.001, "step": 287870 }, { "epoch": 69.14, "learning_rate": 7.588931960203705e-06, "loss": 0.0011, "step": 287880 }, { "epoch": 69.15, "learning_rate": 7.586555646966775e-06, "loss": 0.0014, "step": 287890 }, { "epoch": 69.15, "learning_rate": 7.5841796752911695e-06, "loss": 0.001, "step": 287900 }, { "epoch": 69.15, "learning_rate": 7.581804045196022e-06, "loss": 0.0019, "step": 287910 }, { "epoch": 69.15, "learning_rate": 7.579428756700463e-06, "loss": 0.0018, "step": 287920 }, { "epoch": 69.16, "learning_rate": 7.5770538098236145e-06, "loss": 0.0053, "step": 287930 }, { "epoch": 69.16, "learning_rate": 7.574679204584617e-06, "loss": 0.0019, "step": 287940 }, { "epoch": 69.16, "learning_rate": 7.572304941002567e-06, "loss": 0.0009, "step": 287950 }, { "epoch": 69.16, "learning_rate": 7.569931019096632e-06, "loss": 0.0019, "step": 287960 }, { "epoch": 69.17, "learning_rate": 7.567557438885881e-06, "loss": 0.0012, "step": 287970 }, { "epoch": 69.17, "learning_rate": 7.5651842003894415e-06, "loss": 0.0012, "step": 287980 }, { "epoch": 69.17, "learning_rate": 7.562811303626443e-06, "loss": 0.0019, "step": 287990 }, { "epoch": 69.17, "learning_rate": 7.5604387486159836e-06, "loss": 0.0017, "step": 288000 }, { "epoch": 69.17, "learning_rate": 7.558066535377173e-06, "loss": 0.001, "step": 288010 }, { "epoch": 69.18, "learning_rate": 7.555694663929108e-06, "loss": 0.0011, "step": 288020 }, { "epoch": 69.18, "learning_rate": 7.553323134290896e-06, "loss": 0.0025, "step": 288030 }, { "epoch": 69.18, "learning_rate": 7.550951946481632e-06, "loss": 0.0009, "step": 288040 }, { "epoch": 69.18, "learning_rate": 7.548581100520413e-06, "loss": 0.0011, "step": 288050 }, { "epoch": 69.19, "learning_rate": 7.546210596426328e-06, "loss": 0.0011, "step": 288060 }, { "epoch": 69.19, "learning_rate": 7.543840434218474e-06, "loss": 0.0021, "step": 288070 }, { "epoch": 69.19, "learning_rate": 7.541470613915924e-06, "loss": 0.0014, "step": 288080 }, { "epoch": 69.19, "learning_rate": 7.5391011355377845e-06, "loss": 0.0014, "step": 288090 }, { "epoch": 69.19, "learning_rate": 7.53673199910313e-06, "loss": 0.0011, "step": 288100 }, { "epoch": 69.2, "learning_rate": 7.534363204631034e-06, "loss": 0.0019, "step": 288110 }, { "epoch": 69.2, "learning_rate": 7.531994752140553e-06, "loss": 0.0018, "step": 288120 }, { "epoch": 69.2, "learning_rate": 7.5296266416508e-06, "loss": 0.0012, "step": 288130 }, { "epoch": 69.2, "learning_rate": 7.5272588731808205e-06, "loss": 0.0011, "step": 288140 }, { "epoch": 69.21, "learning_rate": 7.524891446749693e-06, "loss": 0.0015, "step": 288150 }, { "epoch": 69.21, "learning_rate": 7.522524362376482e-06, "loss": 0.0011, "step": 288160 }, { "epoch": 69.21, "learning_rate": 7.520157620080242e-06, "loss": 0.0011, "step": 288170 }, { "epoch": 69.21, "learning_rate": 7.517791219880038e-06, "loss": 0.0015, "step": 288180 }, { "epoch": 69.22, "learning_rate": 7.515425161794925e-06, "loss": 0.0013, "step": 288190 }, { "epoch": 69.22, "learning_rate": 7.513059445843962e-06, "loss": 0.0013, "step": 288200 }, { "epoch": 69.22, "learning_rate": 7.5106940720461925e-06, "loss": 0.0011, "step": 288210 }, { "epoch": 69.22, "learning_rate": 7.508329040420659e-06, "loss": 0.0015, "step": 288220 }, { "epoch": 69.22, "learning_rate": 7.505964350986433e-06, "loss": 0.0021, "step": 288230 }, { "epoch": 69.23, "learning_rate": 7.503600003762551e-06, "loss": 0.001, "step": 288240 }, { "epoch": 69.23, "learning_rate": 7.501235998768025e-06, "loss": 0.0011, "step": 288250 }, { "epoch": 69.23, "learning_rate": 7.498872336021923e-06, "loss": 0.0011, "step": 288260 }, { "epoch": 69.23, "learning_rate": 7.496509015543269e-06, "loss": 0.0012, "step": 288270 }, { "epoch": 69.24, "learning_rate": 7.494146037351096e-06, "loss": 0.0013, "step": 288280 }, { "epoch": 69.24, "learning_rate": 7.491783401464436e-06, "loss": 0.0012, "step": 288290 }, { "epoch": 69.24, "learning_rate": 7.489421107902311e-06, "loss": 0.0015, "step": 288300 }, { "epoch": 69.24, "learning_rate": 7.487059156683746e-06, "loss": 0.0013, "step": 288310 }, { "epoch": 69.25, "learning_rate": 7.484697547827762e-06, "loss": 0.0011, "step": 288320 }, { "epoch": 69.25, "learning_rate": 7.4823362813533696e-06, "loss": 0.0012, "step": 288330 }, { "epoch": 69.25, "learning_rate": 7.479975357279611e-06, "loss": 0.0015, "step": 288340 }, { "epoch": 69.25, "learning_rate": 7.477614775625475e-06, "loss": 0.0015, "step": 288350 }, { "epoch": 69.25, "learning_rate": 7.4752545364099644e-06, "loss": 0.0014, "step": 288360 }, { "epoch": 69.26, "learning_rate": 7.472894639652112e-06, "loss": 0.0026, "step": 288370 }, { "epoch": 69.26, "learning_rate": 7.4705350853709225e-06, "loss": 0.0013, "step": 288380 }, { "epoch": 69.26, "learning_rate": 7.468175873585359e-06, "loss": 0.0009, "step": 288390 }, { "epoch": 69.26, "learning_rate": 7.465817004314463e-06, "loss": 0.001, "step": 288400 }, { "epoch": 69.27, "learning_rate": 7.463458477577212e-06, "loss": 0.0011, "step": 288410 }, { "epoch": 69.27, "learning_rate": 7.461100293392604e-06, "loss": 0.0022, "step": 288420 }, { "epoch": 69.27, "learning_rate": 7.458742451779627e-06, "loss": 0.0016, "step": 288430 }, { "epoch": 69.27, "learning_rate": 7.456384952757273e-06, "loss": 0.0012, "step": 288440 }, { "epoch": 69.27, "learning_rate": 7.45402779634452e-06, "loss": 0.0012, "step": 288450 }, { "epoch": 69.28, "learning_rate": 7.451670982560344e-06, "loss": 0.0012, "step": 288460 }, { "epoch": 69.28, "learning_rate": 7.449314511423749e-06, "loss": 0.0056, "step": 288470 }, { "epoch": 69.28, "learning_rate": 7.446958382953712e-06, "loss": 0.001, "step": 288480 }, { "epoch": 69.28, "learning_rate": 7.44460259716917e-06, "loss": 0.0011, "step": 288490 }, { "epoch": 69.29, "learning_rate": 7.442247154089127e-06, "loss": 0.001, "step": 288500 }, { "epoch": 69.29, "learning_rate": 7.439892053732544e-06, "loss": 0.001, "step": 288510 }, { "epoch": 69.29, "learning_rate": 7.437537296118402e-06, "loss": 0.0016, "step": 288520 }, { "epoch": 69.29, "learning_rate": 7.435182881265617e-06, "loss": 0.0009, "step": 288530 }, { "epoch": 69.3, "learning_rate": 7.432828809193199e-06, "loss": 0.0019, "step": 288540 }, { "epoch": 69.3, "learning_rate": 7.4304750799200855e-06, "loss": 0.001, "step": 288550 }, { "epoch": 69.3, "learning_rate": 7.4281216934652344e-06, "loss": 0.0013, "step": 288560 }, { "epoch": 69.3, "learning_rate": 7.425768649847597e-06, "loss": 0.001, "step": 288570 }, { "epoch": 69.3, "learning_rate": 7.423415949086121e-06, "loss": 0.0016, "step": 288580 }, { "epoch": 69.31, "learning_rate": 7.4210635911997504e-06, "loss": 0.001, "step": 288590 }, { "epoch": 69.31, "learning_rate": 7.418711576207427e-06, "loss": 0.0011, "step": 288600 }, { "epoch": 69.31, "learning_rate": 7.416359904128106e-06, "loss": 0.001, "step": 288610 }, { "epoch": 69.31, "learning_rate": 7.414008574980735e-06, "loss": 0.0009, "step": 288620 }, { "epoch": 69.32, "learning_rate": 7.411657588784205e-06, "loss": 0.0011, "step": 288630 }, { "epoch": 69.32, "learning_rate": 7.409306945557487e-06, "loss": 0.0011, "step": 288640 }, { "epoch": 69.32, "learning_rate": 7.406956645319501e-06, "loss": 0.0011, "step": 288650 }, { "epoch": 69.32, "learning_rate": 7.404606688089177e-06, "loss": 0.0011, "step": 288660 }, { "epoch": 69.33, "learning_rate": 7.402257073885432e-06, "loss": 0.0012, "step": 288670 }, { "epoch": 69.33, "learning_rate": 7.399907802727191e-06, "loss": 0.0013, "step": 288680 }, { "epoch": 69.33, "learning_rate": 7.3975588746333755e-06, "loss": 0.0011, "step": 288690 }, { "epoch": 69.33, "learning_rate": 7.395210289622889e-06, "loss": 0.0013, "step": 288700 }, { "epoch": 69.33, "learning_rate": 7.392862047714677e-06, "loss": 0.0011, "step": 288710 }, { "epoch": 69.34, "learning_rate": 7.390514148927619e-06, "loss": 0.0011, "step": 288720 }, { "epoch": 69.34, "learning_rate": 7.388166593280632e-06, "loss": 0.0011, "step": 288730 }, { "epoch": 69.34, "learning_rate": 7.385819380792614e-06, "loss": 0.0009, "step": 288740 }, { "epoch": 69.34, "learning_rate": 7.3834725114824865e-06, "loss": 0.0011, "step": 288750 }, { "epoch": 69.35, "learning_rate": 7.381125985369147e-06, "loss": 0.0014, "step": 288760 }, { "epoch": 69.35, "learning_rate": 7.378779802471464e-06, "loss": 0.0011, "step": 288770 }, { "epoch": 69.35, "learning_rate": 7.37643396280836e-06, "loss": 0.0009, "step": 288780 }, { "epoch": 69.35, "learning_rate": 7.374088466398721e-06, "loss": 0.0012, "step": 288790 }, { "epoch": 69.35, "learning_rate": 7.371743313261431e-06, "loss": 0.0041, "step": 288800 }, { "epoch": 69.36, "learning_rate": 7.369398503415376e-06, "loss": 0.0012, "step": 288810 }, { "epoch": 69.36, "learning_rate": 7.367054036879445e-06, "loss": 0.0011, "step": 288820 }, { "epoch": 69.36, "learning_rate": 7.3647099136725076e-06, "loss": 0.001, "step": 288830 }, { "epoch": 69.36, "learning_rate": 7.362366133813442e-06, "loss": 0.0022, "step": 288840 }, { "epoch": 69.37, "learning_rate": 7.360022697321145e-06, "loss": 0.0011, "step": 288850 }, { "epoch": 69.37, "learning_rate": 7.357679604214463e-06, "loss": 0.0024, "step": 288860 }, { "epoch": 69.37, "learning_rate": 7.355336854512262e-06, "loss": 0.001, "step": 288870 }, { "epoch": 69.37, "learning_rate": 7.3529944482334354e-06, "loss": 0.002, "step": 288880 }, { "epoch": 69.38, "learning_rate": 7.350652385396833e-06, "loss": 0.0011, "step": 288890 }, { "epoch": 69.38, "learning_rate": 7.348310666021313e-06, "loss": 0.0011, "step": 288900 }, { "epoch": 69.38, "learning_rate": 7.345969290125732e-06, "loss": 0.0012, "step": 288910 }, { "epoch": 69.38, "learning_rate": 7.343628257728952e-06, "loss": 0.0017, "step": 288920 }, { "epoch": 69.38, "learning_rate": 7.341287568849825e-06, "loss": 0.0009, "step": 288930 }, { "epoch": 69.39, "learning_rate": 7.3389472235071864e-06, "loss": 0.0011, "step": 288940 }, { "epoch": 69.39, "learning_rate": 7.336607221719915e-06, "loss": 0.0011, "step": 288950 }, { "epoch": 69.39, "learning_rate": 7.334267563506825e-06, "loss": 0.0012, "step": 288960 }, { "epoch": 69.39, "learning_rate": 7.3319282488867715e-06, "loss": 0.0012, "step": 288970 }, { "epoch": 69.4, "learning_rate": 7.329589277878579e-06, "loss": 0.0012, "step": 288980 }, { "epoch": 69.4, "learning_rate": 7.327250650501105e-06, "loss": 0.0011, "step": 288990 }, { "epoch": 69.4, "learning_rate": 7.3249123667731845e-06, "loss": 0.001, "step": 289000 }, { "epoch": 69.4, "learning_rate": 7.322574426713613e-06, "loss": 0.0012, "step": 289010 }, { "epoch": 69.41, "learning_rate": 7.320236830341254e-06, "loss": 0.0015, "step": 289020 }, { "epoch": 69.41, "learning_rate": 7.3178995776749196e-06, "loss": 0.0011, "step": 289030 }, { "epoch": 69.41, "learning_rate": 7.3155626687334335e-06, "loss": 0.0015, "step": 289040 }, { "epoch": 69.41, "learning_rate": 7.3132261035356146e-06, "loss": 0.001, "step": 289050 }, { "epoch": 69.41, "learning_rate": 7.310889882100274e-06, "loss": 0.0011, "step": 289060 }, { "epoch": 69.42, "learning_rate": 7.308554004446233e-06, "loss": 0.0017, "step": 289070 }, { "epoch": 69.42, "learning_rate": 7.306218470592291e-06, "loss": 0.0016, "step": 289080 }, { "epoch": 69.42, "learning_rate": 7.303883280557288e-06, "loss": 0.0027, "step": 289090 }, { "epoch": 69.42, "learning_rate": 7.3015484343600005e-06, "loss": 0.0023, "step": 289100 }, { "epoch": 69.43, "learning_rate": 7.299213932019222e-06, "loss": 0.0011, "step": 289110 }, { "epoch": 69.43, "learning_rate": 7.296879773553783e-06, "loss": 0.0011, "step": 289120 }, { "epoch": 69.43, "learning_rate": 7.294545958982463e-06, "loss": 0.001, "step": 289130 }, { "epoch": 69.43, "learning_rate": 7.292212488324063e-06, "loss": 0.001, "step": 289140 }, { "epoch": 69.43, "learning_rate": 7.2898793615973686e-06, "loss": 0.001, "step": 289150 }, { "epoch": 69.44, "learning_rate": 7.287546578821175e-06, "loss": 0.001, "step": 289160 }, { "epoch": 69.44, "learning_rate": 7.2852141400142685e-06, "loss": 0.001, "step": 289170 }, { "epoch": 69.44, "learning_rate": 7.282882045195427e-06, "loss": 0.0011, "step": 289180 }, { "epoch": 69.44, "learning_rate": 7.280550294383431e-06, "loss": 0.001, "step": 289190 }, { "epoch": 69.45, "learning_rate": 7.2782188875970655e-06, "loss": 0.002, "step": 289200 }, { "epoch": 69.45, "learning_rate": 7.275887824855099e-06, "loss": 0.001, "step": 289210 }, { "epoch": 69.45, "learning_rate": 7.273557106176293e-06, "loss": 0.0035, "step": 289220 }, { "epoch": 69.45, "learning_rate": 7.271226731579456e-06, "loss": 0.001, "step": 289230 }, { "epoch": 69.46, "learning_rate": 7.268896701083322e-06, "loss": 0.001, "step": 289240 }, { "epoch": 69.46, "learning_rate": 7.266567014706643e-06, "loss": 0.002, "step": 289250 }, { "epoch": 69.46, "learning_rate": 7.264237672468216e-06, "loss": 0.0058, "step": 289260 }, { "epoch": 69.46, "learning_rate": 7.2619086743867804e-06, "loss": 0.0016, "step": 289270 }, { "epoch": 69.46, "learning_rate": 7.259580020481093e-06, "loss": 0.0011, "step": 289280 }, { "epoch": 69.47, "learning_rate": 7.2572517107699135e-06, "loss": 0.0011, "step": 289290 }, { "epoch": 69.47, "learning_rate": 7.2549237452719855e-06, "loss": 0.0013, "step": 289300 }, { "epoch": 69.47, "learning_rate": 7.252596124006056e-06, "loss": 0.0011, "step": 289310 }, { "epoch": 69.47, "learning_rate": 7.25026884699086e-06, "loss": 0.0011, "step": 289320 }, { "epoch": 69.48, "learning_rate": 7.247941914245177e-06, "loss": 0.0011, "step": 289330 }, { "epoch": 69.48, "learning_rate": 7.245615325787708e-06, "loss": 0.001, "step": 289340 }, { "epoch": 69.48, "learning_rate": 7.243289081637183e-06, "loss": 0.0017, "step": 289350 }, { "epoch": 69.48, "learning_rate": 7.2409631818123715e-06, "loss": 0.0038, "step": 289360 }, { "epoch": 69.49, "learning_rate": 7.238637626332001e-06, "loss": 0.0011, "step": 289370 }, { "epoch": 69.49, "learning_rate": 7.236312415214769e-06, "loss": 0.0013, "step": 289380 }, { "epoch": 69.49, "learning_rate": 7.2339875484794035e-06, "loss": 0.001, "step": 289390 }, { "epoch": 69.49, "learning_rate": 7.231663026144658e-06, "loss": 0.0013, "step": 289400 }, { "epoch": 69.49, "learning_rate": 7.229338848229233e-06, "loss": 0.0026, "step": 289410 }, { "epoch": 69.5, "learning_rate": 7.227015014751848e-06, "loss": 0.0011, "step": 289420 }, { "epoch": 69.5, "learning_rate": 7.224691525731214e-06, "loss": 0.001, "step": 289430 }, { "epoch": 69.5, "learning_rate": 7.22236838118604e-06, "loss": 0.0011, "step": 289440 }, { "epoch": 69.5, "learning_rate": 7.220045581135049e-06, "loss": 0.0014, "step": 289450 }, { "epoch": 69.51, "learning_rate": 7.2177231255969205e-06, "loss": 0.0011, "step": 289460 }, { "epoch": 69.51, "learning_rate": 7.215401014590395e-06, "loss": 0.0014, "step": 289470 }, { "epoch": 69.51, "learning_rate": 7.213079248134142e-06, "loss": 0.0009, "step": 289480 }, { "epoch": 69.51, "learning_rate": 7.210757826246861e-06, "loss": 0.0011, "step": 289490 }, { "epoch": 69.51, "learning_rate": 7.208436748947262e-06, "loss": 0.001, "step": 289500 }, { "epoch": 69.52, "learning_rate": 7.206116016254044e-06, "loss": 0.0009, "step": 289510 }, { "epoch": 69.52, "learning_rate": 7.203795628185855e-06, "loss": 0.001, "step": 289520 }, { "epoch": 69.52, "learning_rate": 7.201475584761425e-06, "loss": 0.0011, "step": 289530 }, { "epoch": 69.52, "learning_rate": 7.199155885999415e-06, "loss": 0.0014, "step": 289540 }, { "epoch": 69.53, "learning_rate": 7.196836531918516e-06, "loss": 0.0012, "step": 289550 }, { "epoch": 69.53, "learning_rate": 7.194517522537398e-06, "loss": 0.001, "step": 289560 }, { "epoch": 69.53, "learning_rate": 7.1921988578747435e-06, "loss": 0.0013, "step": 289570 }, { "epoch": 69.53, "learning_rate": 7.189880537949223e-06, "loss": 0.0015, "step": 289580 }, { "epoch": 69.54, "learning_rate": 7.187562562779487e-06, "loss": 0.0017, "step": 289590 }, { "epoch": 69.54, "learning_rate": 7.185244932384239e-06, "loss": 0.0011, "step": 289600 }, { "epoch": 69.54, "learning_rate": 7.182927646782128e-06, "loss": 0.0011, "step": 289610 }, { "epoch": 69.54, "learning_rate": 7.180610705991808e-06, "loss": 0.0015, "step": 289620 }, { "epoch": 69.54, "learning_rate": 7.178294110031924e-06, "loss": 0.0025, "step": 289630 }, { "epoch": 69.55, "learning_rate": 7.175977858921168e-06, "loss": 0.0014, "step": 289640 }, { "epoch": 69.55, "learning_rate": 7.173661952678168e-06, "loss": 0.0011, "step": 289650 }, { "epoch": 69.55, "learning_rate": 7.171346391321582e-06, "loss": 0.0027, "step": 289660 }, { "epoch": 69.55, "learning_rate": 7.169031174870061e-06, "loss": 0.0032, "step": 289670 }, { "epoch": 69.56, "learning_rate": 7.166716303342241e-06, "loss": 0.0017, "step": 289680 }, { "epoch": 69.56, "learning_rate": 7.164401776756768e-06, "loss": 0.0013, "step": 289690 }, { "epoch": 69.56, "learning_rate": 7.162087595132283e-06, "loss": 0.0011, "step": 289700 }, { "epoch": 69.56, "learning_rate": 7.15977375848742e-06, "loss": 0.0012, "step": 289710 }, { "epoch": 69.57, "learning_rate": 7.157460266840815e-06, "loss": 0.0013, "step": 289720 }, { "epoch": 69.57, "learning_rate": 7.155147120211081e-06, "loss": 0.0012, "step": 289730 }, { "epoch": 69.57, "learning_rate": 7.15283431861688e-06, "loss": 0.001, "step": 289740 }, { "epoch": 69.57, "learning_rate": 7.150521862076825e-06, "loss": 0.0011, "step": 289750 }, { "epoch": 69.57, "learning_rate": 7.1482097506095135e-06, "loss": 0.0011, "step": 289760 }, { "epoch": 69.58, "learning_rate": 7.145897984233596e-06, "loss": 0.0015, "step": 289770 }, { "epoch": 69.58, "learning_rate": 7.14358656296768e-06, "loss": 0.0011, "step": 289780 }, { "epoch": 69.58, "learning_rate": 7.1412754868303785e-06, "loss": 0.0012, "step": 289790 }, { "epoch": 69.58, "learning_rate": 7.1389647558403e-06, "loss": 0.0011, "step": 289800 }, { "epoch": 69.59, "learning_rate": 7.136654370016055e-06, "loss": 0.0074, "step": 289810 }, { "epoch": 69.59, "learning_rate": 7.134344329376253e-06, "loss": 0.0012, "step": 289820 }, { "epoch": 69.59, "learning_rate": 7.1320346339394885e-06, "loss": 0.0022, "step": 289830 }, { "epoch": 69.59, "learning_rate": 7.129725283724376e-06, "loss": 0.0011, "step": 289840 }, { "epoch": 69.59, "learning_rate": 7.127416278749499e-06, "loss": 0.0024, "step": 289850 }, { "epoch": 69.6, "learning_rate": 7.125107619033456e-06, "loss": 0.0012, "step": 289860 }, { "epoch": 69.6, "learning_rate": 7.122799304594835e-06, "loss": 0.0015, "step": 289870 }, { "epoch": 69.6, "learning_rate": 7.120491335452234e-06, "loss": 0.0018, "step": 289880 }, { "epoch": 69.6, "learning_rate": 7.118183711624255e-06, "loss": 0.001, "step": 289890 }, { "epoch": 69.61, "learning_rate": 7.115876433129437e-06, "loss": 0.0018, "step": 289900 }, { "epoch": 69.61, "learning_rate": 7.1135694999864e-06, "loss": 0.0015, "step": 289910 }, { "epoch": 69.61, "learning_rate": 7.1112629122137066e-06, "loss": 0.0013, "step": 289920 }, { "epoch": 69.61, "learning_rate": 7.10895666982993e-06, "loss": 0.001, "step": 289930 }, { "epoch": 69.62, "learning_rate": 7.1066507728536565e-06, "loss": 0.0021, "step": 289940 }, { "epoch": 69.62, "learning_rate": 7.104345221303438e-06, "loss": 0.0011, "step": 289950 }, { "epoch": 69.62, "learning_rate": 7.1020400151978524e-06, "loss": 0.002, "step": 289960 }, { "epoch": 69.62, "learning_rate": 7.099735154555448e-06, "loss": 0.0025, "step": 289970 }, { "epoch": 69.62, "learning_rate": 7.097430639394815e-06, "loss": 0.0092, "step": 289980 }, { "epoch": 69.63, "learning_rate": 7.095126469734503e-06, "loss": 0.0019, "step": 289990 }, { "epoch": 69.63, "learning_rate": 7.092822645593039e-06, "loss": 0.0014, "step": 290000 }, { "epoch": 69.63, "learning_rate": 7.090519166989012e-06, "loss": 0.0011, "step": 290010 }, { "epoch": 69.63, "learning_rate": 7.088216033940959e-06, "loss": 0.0012, "step": 290020 }, { "epoch": 69.64, "learning_rate": 7.085913246467435e-06, "loss": 0.0016, "step": 290030 }, { "epoch": 69.64, "learning_rate": 7.083610804586954e-06, "loss": 0.0012, "step": 290040 }, { "epoch": 69.64, "learning_rate": 7.081308708318091e-06, "loss": 0.001, "step": 290050 }, { "epoch": 69.64, "learning_rate": 7.079006957679374e-06, "loss": 0.0016, "step": 290060 }, { "epoch": 69.65, "learning_rate": 7.0767055526893385e-06, "loss": 0.0012, "step": 290070 }, { "epoch": 69.65, "learning_rate": 7.074404493366521e-06, "loss": 0.0011, "step": 290080 }, { "epoch": 69.65, "learning_rate": 7.07210377972945e-06, "loss": 0.001, "step": 290090 }, { "epoch": 69.65, "learning_rate": 7.069803411796655e-06, "loss": 0.0014, "step": 290100 }, { "epoch": 69.65, "learning_rate": 7.067503389586649e-06, "loss": 0.0023, "step": 290110 }, { "epoch": 69.66, "learning_rate": 7.065203713117974e-06, "loss": 0.0011, "step": 290120 }, { "epoch": 69.66, "learning_rate": 7.062904382409152e-06, "loss": 0.0011, "step": 290130 }, { "epoch": 69.66, "learning_rate": 7.06060539747867e-06, "loss": 0.0011, "step": 290140 }, { "epoch": 69.66, "learning_rate": 7.058306758345068e-06, "loss": 0.0022, "step": 290150 }, { "epoch": 69.67, "learning_rate": 7.056008465026853e-06, "loss": 0.0013, "step": 290160 }, { "epoch": 69.67, "learning_rate": 7.053710517542533e-06, "loss": 0.0012, "step": 290170 }, { "epoch": 69.67, "learning_rate": 7.051412915910605e-06, "loss": 0.0011, "step": 290180 }, { "epoch": 69.67, "learning_rate": 7.049115660149586e-06, "loss": 0.0012, "step": 290190 }, { "epoch": 69.67, "learning_rate": 7.046818750277961e-06, "loss": 0.0012, "step": 290200 }, { "epoch": 69.68, "learning_rate": 7.044522186314229e-06, "loss": 0.0012, "step": 290210 }, { "epoch": 69.68, "learning_rate": 7.0422259682769055e-06, "loss": 0.0011, "step": 290220 }, { "epoch": 69.68, "learning_rate": 7.039930096184461e-06, "loss": 0.0028, "step": 290230 }, { "epoch": 69.68, "learning_rate": 7.03763457005539e-06, "loss": 0.003, "step": 290240 }, { "epoch": 69.69, "learning_rate": 7.035339389908169e-06, "loss": 0.0011, "step": 290250 }, { "epoch": 69.69, "learning_rate": 7.033044555761298e-06, "loss": 0.001, "step": 290260 }, { "epoch": 69.69, "learning_rate": 7.030750067633268e-06, "loss": 0.0011, "step": 290270 }, { "epoch": 69.69, "learning_rate": 7.028455925542515e-06, "loss": 0.0013, "step": 290280 }, { "epoch": 69.7, "learning_rate": 7.026162129507552e-06, "loss": 0.0012, "step": 290290 }, { "epoch": 69.7, "learning_rate": 7.023868679546835e-06, "loss": 0.0011, "step": 290300 }, { "epoch": 69.7, "learning_rate": 7.02157557567884e-06, "loss": 0.0013, "step": 290310 }, { "epoch": 69.7, "learning_rate": 7.01928281792203e-06, "loss": 0.0012, "step": 290320 }, { "epoch": 69.7, "learning_rate": 7.016990406294866e-06, "loss": 0.0018, "step": 290330 }, { "epoch": 69.71, "learning_rate": 7.014698340815812e-06, "loss": 0.0011, "step": 290340 }, { "epoch": 69.71, "learning_rate": 7.01240662150332e-06, "loss": 0.0011, "step": 290350 }, { "epoch": 69.71, "learning_rate": 7.010115248375876e-06, "loss": 0.0009, "step": 290360 }, { "epoch": 69.71, "learning_rate": 7.007824221451892e-06, "loss": 0.001, "step": 290370 }, { "epoch": 69.72, "learning_rate": 7.005533540749826e-06, "loss": 0.0014, "step": 290380 }, { "epoch": 69.72, "learning_rate": 7.003243206288146e-06, "loss": 0.0012, "step": 290390 }, { "epoch": 69.72, "learning_rate": 7.0009532180852826e-06, "loss": 0.0101, "step": 290400 }, { "epoch": 69.72, "learning_rate": 6.9986635761596806e-06, "loss": 0.0011, "step": 290410 }, { "epoch": 69.73, "learning_rate": 6.996374280529783e-06, "loss": 0.0012, "step": 290420 }, { "epoch": 69.73, "learning_rate": 6.994085331214012e-06, "loss": 0.0011, "step": 290430 }, { "epoch": 69.73, "learning_rate": 6.991796728230815e-06, "loss": 0.0011, "step": 290440 }, { "epoch": 69.73, "learning_rate": 6.9895084715985995e-06, "loss": 0.0011, "step": 290450 }, { "epoch": 69.73, "learning_rate": 6.9872205613358385e-06, "loss": 0.002, "step": 290460 }, { "epoch": 69.74, "learning_rate": 6.984932997460914e-06, "loss": 0.0012, "step": 290470 }, { "epoch": 69.74, "learning_rate": 6.982645779992264e-06, "loss": 0.0015, "step": 290480 }, { "epoch": 69.74, "learning_rate": 6.980358908948292e-06, "loss": 0.0014, "step": 290490 }, { "epoch": 69.74, "learning_rate": 6.978072384347456e-06, "loss": 0.002, "step": 290500 }, { "epoch": 69.75, "learning_rate": 6.975786206208129e-06, "loss": 0.0032, "step": 290510 }, { "epoch": 69.75, "learning_rate": 6.973500374548725e-06, "loss": 0.0012, "step": 290520 }, { "epoch": 69.75, "learning_rate": 6.971214889387673e-06, "loss": 0.001, "step": 290530 }, { "epoch": 69.75, "learning_rate": 6.96892975074337e-06, "loss": 0.0013, "step": 290540 }, { "epoch": 69.75, "learning_rate": 6.966644958634216e-06, "loss": 0.0022, "step": 290550 }, { "epoch": 69.76, "learning_rate": 6.9643605130786106e-06, "loss": 0.0015, "step": 290560 }, { "epoch": 69.76, "learning_rate": 6.962076414094953e-06, "loss": 0.0011, "step": 290570 }, { "epoch": 69.76, "learning_rate": 6.959792661701631e-06, "loss": 0.0033, "step": 290580 }, { "epoch": 69.76, "learning_rate": 6.957509255917033e-06, "loss": 0.0011, "step": 290590 }, { "epoch": 69.77, "learning_rate": 6.955226196759579e-06, "loss": 0.0027, "step": 290600 }, { "epoch": 69.77, "learning_rate": 6.9529434842476205e-06, "loss": 0.0017, "step": 290610 }, { "epoch": 69.77, "learning_rate": 6.950661118399537e-06, "loss": 0.0024, "step": 290620 }, { "epoch": 69.77, "learning_rate": 6.948379099233732e-06, "loss": 0.0011, "step": 290630 }, { "epoch": 69.78, "learning_rate": 6.9460974267685774e-06, "loss": 0.0017, "step": 290640 }, { "epoch": 69.78, "learning_rate": 6.943816101022443e-06, "loss": 0.0014, "step": 290650 }, { "epoch": 69.78, "learning_rate": 6.941535122013704e-06, "loss": 0.001, "step": 290660 }, { "epoch": 69.78, "learning_rate": 6.939254489760727e-06, "loss": 0.0011, "step": 290670 }, { "epoch": 69.78, "learning_rate": 6.936974204281876e-06, "loss": 0.001, "step": 290680 }, { "epoch": 69.79, "learning_rate": 6.934694265595515e-06, "loss": 0.001, "step": 290690 }, { "epoch": 69.79, "learning_rate": 6.932414673720011e-06, "loss": 0.0011, "step": 290700 }, { "epoch": 69.79, "learning_rate": 6.9301354286737174e-06, "loss": 0.0012, "step": 290710 }, { "epoch": 69.79, "learning_rate": 6.9278565304749854e-06, "loss": 0.0033, "step": 290720 }, { "epoch": 69.8, "learning_rate": 6.925577979142167e-06, "loss": 0.0031, "step": 290730 }, { "epoch": 69.8, "learning_rate": 6.9232997746936316e-06, "loss": 0.001, "step": 290740 }, { "epoch": 69.8, "learning_rate": 6.921021917147702e-06, "loss": 0.001, "step": 290750 }, { "epoch": 69.8, "learning_rate": 6.91874440652272e-06, "loss": 0.0035, "step": 290760 }, { "epoch": 69.81, "learning_rate": 6.916467242837043e-06, "loss": 0.0013, "step": 290770 }, { "epoch": 69.81, "learning_rate": 6.914190426109008e-06, "loss": 0.001, "step": 290780 }, { "epoch": 69.81, "learning_rate": 6.9119139563569465e-06, "loss": 0.0009, "step": 290790 }, { "epoch": 69.81, "learning_rate": 6.909637833599192e-06, "loss": 0.001, "step": 290800 }, { "epoch": 69.81, "learning_rate": 6.907362057854067e-06, "loss": 0.001, "step": 290810 }, { "epoch": 69.82, "learning_rate": 6.905086629139906e-06, "loss": 0.0021, "step": 290820 }, { "epoch": 69.82, "learning_rate": 6.902811547475035e-06, "loss": 0.001, "step": 290830 }, { "epoch": 69.82, "learning_rate": 6.900536812877772e-06, "loss": 0.001, "step": 290840 }, { "epoch": 69.82, "learning_rate": 6.898262425366437e-06, "loss": 0.0012, "step": 290850 }, { "epoch": 69.83, "learning_rate": 6.895988384959329e-06, "loss": 0.001, "step": 290860 }, { "epoch": 69.83, "learning_rate": 6.893714691674796e-06, "loss": 0.0013, "step": 290870 }, { "epoch": 69.83, "learning_rate": 6.8914413455311356e-06, "loss": 0.001, "step": 290880 }, { "epoch": 69.83, "learning_rate": 6.889168346546643e-06, "loss": 0.0014, "step": 290890 }, { "epoch": 69.83, "learning_rate": 6.886895694739615e-06, "loss": 0.0013, "step": 290900 }, { "epoch": 69.84, "learning_rate": 6.884623390128375e-06, "loss": 0.0011, "step": 290910 }, { "epoch": 69.84, "learning_rate": 6.882351432731221e-06, "loss": 0.0012, "step": 290920 }, { "epoch": 69.84, "learning_rate": 6.880079822566443e-06, "loss": 0.0017, "step": 290930 }, { "epoch": 69.84, "learning_rate": 6.877808559652338e-06, "loss": 0.001, "step": 290940 }, { "epoch": 69.85, "learning_rate": 6.875537644007191e-06, "loss": 0.0011, "step": 290950 }, { "epoch": 69.85, "learning_rate": 6.873267075649292e-06, "loss": 0.001, "step": 290960 }, { "epoch": 69.85, "learning_rate": 6.8709968545969174e-06, "loss": 0.0013, "step": 290970 }, { "epoch": 69.85, "learning_rate": 6.868726980868378e-06, "loss": 0.0017, "step": 290980 }, { "epoch": 69.86, "learning_rate": 6.866457454481928e-06, "loss": 0.0018, "step": 290990 }, { "epoch": 69.86, "learning_rate": 6.86418827545584e-06, "loss": 0.001, "step": 291000 }, { "epoch": 69.86, "learning_rate": 6.861919443808406e-06, "loss": 0.0012, "step": 291010 }, { "epoch": 69.86, "learning_rate": 6.859650959557906e-06, "loss": 0.0011, "step": 291020 }, { "epoch": 69.86, "learning_rate": 6.857382822722569e-06, "loss": 0.0016, "step": 291030 }, { "epoch": 69.87, "learning_rate": 6.855115033320697e-06, "loss": 0.0012, "step": 291040 }, { "epoch": 69.87, "learning_rate": 6.852847591370542e-06, "loss": 0.001, "step": 291050 }, { "epoch": 69.87, "learning_rate": 6.8505804968903575e-06, "loss": 0.0012, "step": 291060 }, { "epoch": 69.87, "learning_rate": 6.8483137498984054e-06, "loss": 0.001, "step": 291070 }, { "epoch": 69.88, "learning_rate": 6.846047350412943e-06, "loss": 0.0014, "step": 291080 }, { "epoch": 69.88, "learning_rate": 6.8437812984522175e-06, "loss": 0.001, "step": 291090 }, { "epoch": 69.88, "learning_rate": 6.841515594034481e-06, "loss": 0.0018, "step": 291100 }, { "epoch": 69.88, "learning_rate": 6.839250237177963e-06, "loss": 0.0017, "step": 291110 }, { "epoch": 69.89, "learning_rate": 6.836985227900944e-06, "loss": 0.0011, "step": 291120 }, { "epoch": 69.89, "learning_rate": 6.834720566221637e-06, "loss": 0.0013, "step": 291130 }, { "epoch": 69.89, "learning_rate": 6.83245625215827e-06, "loss": 0.0011, "step": 291140 }, { "epoch": 69.89, "learning_rate": 6.830192285729098e-06, "loss": 0.0014, "step": 291150 }, { "epoch": 69.89, "learning_rate": 6.827928666952366e-06, "loss": 0.001, "step": 291160 }, { "epoch": 69.9, "learning_rate": 6.825665395846259e-06, "loss": 0.0011, "step": 291170 }, { "epoch": 69.9, "learning_rate": 6.823402472429041e-06, "loss": 0.0011, "step": 291180 }, { "epoch": 69.9, "learning_rate": 6.821139896718926e-06, "loss": 0.0036, "step": 291190 }, { "epoch": 69.9, "learning_rate": 6.81887766873413e-06, "loss": 0.0014, "step": 291200 }, { "epoch": 69.91, "learning_rate": 6.816615788492875e-06, "loss": 0.001, "step": 291210 }, { "epoch": 69.91, "learning_rate": 6.8143542560133725e-06, "loss": 0.0013, "step": 291220 }, { "epoch": 69.91, "learning_rate": 6.812093071313841e-06, "loss": 0.001, "step": 291230 }, { "epoch": 69.91, "learning_rate": 6.809832234412472e-06, "loss": 0.0011, "step": 291240 }, { "epoch": 69.91, "learning_rate": 6.807571745327501e-06, "loss": 0.0014, "step": 291250 }, { "epoch": 69.92, "learning_rate": 6.805311604077125e-06, "loss": 0.001, "step": 291260 }, { "epoch": 69.92, "learning_rate": 6.803051810679517e-06, "loss": 0.0009, "step": 291270 }, { "epoch": 69.92, "learning_rate": 6.800792365152908e-06, "loss": 0.0013, "step": 291280 }, { "epoch": 69.92, "learning_rate": 6.798533267515483e-06, "loss": 0.0012, "step": 291290 }, { "epoch": 69.93, "learning_rate": 6.796274517785434e-06, "loss": 0.0012, "step": 291300 }, { "epoch": 69.93, "learning_rate": 6.794016115980955e-06, "loss": 0.001, "step": 291310 }, { "epoch": 69.93, "learning_rate": 6.791758062120224e-06, "loss": 0.0014, "step": 291320 }, { "epoch": 69.93, "learning_rate": 6.789500356221429e-06, "loss": 0.0009, "step": 291330 }, { "epoch": 69.94, "learning_rate": 6.787242998302756e-06, "loss": 0.0011, "step": 291340 }, { "epoch": 69.94, "learning_rate": 6.784985988382381e-06, "loss": 0.0012, "step": 291350 }, { "epoch": 69.94, "learning_rate": 6.782729326478482e-06, "loss": 0.001, "step": 291360 }, { "epoch": 69.94, "learning_rate": 6.780473012609229e-06, "loss": 0.0009, "step": 291370 }, { "epoch": 69.94, "learning_rate": 6.778217046792779e-06, "loss": 0.0011, "step": 291380 }, { "epoch": 69.95, "learning_rate": 6.7759614290473286e-06, "loss": 0.0011, "step": 291390 }, { "epoch": 69.95, "learning_rate": 6.773706159391035e-06, "loss": 0.0024, "step": 291400 }, { "epoch": 69.95, "learning_rate": 6.771451237842036e-06, "loss": 0.0012, "step": 291410 }, { "epoch": 70.0, "learning_rate": 6.76919666441852e-06, "loss": 0.001, "step": 291420 }, { "epoch": 70.0, "learning_rate": 6.7669424391386295e-06, "loss": 0.0014, "step": 291430 }, { "epoch": 70.01, "learning_rate": 6.7646885620205215e-06, "loss": 0.0012, "step": 291440 }, { "epoch": 70.01, "learning_rate": 6.762435033082343e-06, "loss": 0.0012, "step": 291450 }, { "epoch": 70.01, "learning_rate": 6.760181852342245e-06, "loss": 0.001, "step": 291460 }, { "epoch": 70.01, "learning_rate": 6.757929019818377e-06, "loss": 0.001, "step": 291470 }, { "epoch": 70.02, "learning_rate": 6.75567653552886e-06, "loss": 0.0012, "step": 291480 }, { "epoch": 70.02, "learning_rate": 6.753424399491876e-06, "loss": 0.001, "step": 291490 }, { "epoch": 70.02, "learning_rate": 6.751172611725521e-06, "loss": 0.0011, "step": 291500 }, { "epoch": 70.02, "learning_rate": 6.748921172247935e-06, "loss": 0.0027, "step": 291510 }, { "epoch": 70.03, "learning_rate": 6.746670081077267e-06, "loss": 0.0015, "step": 291520 }, { "epoch": 70.03, "learning_rate": 6.744419338231639e-06, "loss": 0.001, "step": 291530 }, { "epoch": 70.03, "learning_rate": 6.742168943729182e-06, "loss": 0.0009, "step": 291540 }, { "epoch": 70.03, "learning_rate": 6.739918897587993e-06, "loss": 0.0011, "step": 291550 }, { "epoch": 70.03, "learning_rate": 6.7376691998262184e-06, "loss": 0.0008, "step": 291560 }, { "epoch": 70.04, "learning_rate": 6.7354198504619656e-06, "loss": 0.0011, "step": 291570 }, { "epoch": 70.04, "learning_rate": 6.733170849513348e-06, "loss": 0.0018, "step": 291580 }, { "epoch": 70.04, "learning_rate": 6.730922196998485e-06, "loss": 0.0011, "step": 291590 }, { "epoch": 70.04, "learning_rate": 6.728673892935472e-06, "loss": 0.0016, "step": 291600 }, { "epoch": 70.05, "learning_rate": 6.726425937342428e-06, "loss": 0.001, "step": 291610 }, { "epoch": 70.05, "learning_rate": 6.724178330237435e-06, "loss": 0.0011, "step": 291620 }, { "epoch": 70.05, "learning_rate": 6.721931071638621e-06, "loss": 0.0009, "step": 291630 }, { "epoch": 70.05, "learning_rate": 6.719684161564082e-06, "loss": 0.0008, "step": 291640 }, { "epoch": 70.05, "learning_rate": 6.717437600031878e-06, "loss": 0.001, "step": 291650 }, { "epoch": 70.06, "learning_rate": 6.715191387060138e-06, "loss": 0.001, "step": 291660 }, { "epoch": 70.06, "learning_rate": 6.712945522666935e-06, "loss": 0.0011, "step": 291670 }, { "epoch": 70.06, "learning_rate": 6.710700006870363e-06, "loss": 0.0012, "step": 291680 }, { "epoch": 70.06, "learning_rate": 6.708454839688499e-06, "loss": 0.0011, "step": 291690 }, { "epoch": 70.07, "learning_rate": 6.70621002113942e-06, "loss": 0.0011, "step": 291700 }, { "epoch": 70.07, "learning_rate": 6.703965551241214e-06, "loss": 0.0019, "step": 291710 }, { "epoch": 70.07, "learning_rate": 6.701721430011937e-06, "loss": 0.0016, "step": 291720 }, { "epoch": 70.07, "learning_rate": 6.699477657469699e-06, "loss": 0.0013, "step": 291730 }, { "epoch": 70.08, "learning_rate": 6.697234233632532e-06, "loss": 0.0011, "step": 291740 }, { "epoch": 70.08, "learning_rate": 6.694991158518515e-06, "loss": 0.0017, "step": 291750 }, { "epoch": 70.08, "learning_rate": 6.6927484321457064e-06, "loss": 0.0011, "step": 291760 }, { "epoch": 70.08, "learning_rate": 6.6905060545321805e-06, "loss": 0.0013, "step": 291770 }, { "epoch": 70.08, "learning_rate": 6.6882640256960004e-06, "loss": 0.0014, "step": 291780 }, { "epoch": 70.09, "learning_rate": 6.686022345655191e-06, "loss": 0.001, "step": 291790 }, { "epoch": 70.09, "learning_rate": 6.6837810144278315e-06, "loss": 0.0012, "step": 291800 }, { "epoch": 70.09, "learning_rate": 6.6815400320319635e-06, "loss": 0.0012, "step": 291810 }, { "epoch": 70.09, "learning_rate": 6.679299398485633e-06, "loss": 0.0012, "step": 291820 }, { "epoch": 70.1, "learning_rate": 6.677059113806888e-06, "loss": 0.0017, "step": 291830 }, { "epoch": 70.1, "learning_rate": 6.674819178013769e-06, "loss": 0.0013, "step": 291840 }, { "epoch": 70.1, "learning_rate": 6.672579591124306e-06, "loss": 0.0014, "step": 291850 }, { "epoch": 70.1, "learning_rate": 6.670340353156535e-06, "loss": 0.0013, "step": 291860 }, { "epoch": 70.11, "learning_rate": 6.668101464128518e-06, "loss": 0.0011, "step": 291870 }, { "epoch": 70.11, "learning_rate": 6.665862924058247e-06, "loss": 0.0016, "step": 291880 }, { "epoch": 70.11, "learning_rate": 6.663624732963758e-06, "loss": 0.0011, "step": 291890 }, { "epoch": 70.11, "learning_rate": 6.661386890863092e-06, "loss": 0.001, "step": 291900 }, { "epoch": 70.11, "learning_rate": 6.659149397774256e-06, "loss": 0.0017, "step": 291910 }, { "epoch": 70.12, "learning_rate": 6.65691225371528e-06, "loss": 0.0011, "step": 291920 }, { "epoch": 70.12, "learning_rate": 6.654675458704168e-06, "loss": 0.0011, "step": 291930 }, { "epoch": 70.12, "learning_rate": 6.652439012758943e-06, "loss": 0.0012, "step": 291940 }, { "epoch": 70.12, "learning_rate": 6.6502029158976076e-06, "loss": 0.0011, "step": 291950 }, { "epoch": 70.13, "learning_rate": 6.647967168138164e-06, "loss": 0.0035, "step": 291960 }, { "epoch": 70.13, "learning_rate": 6.6457317694986476e-06, "loss": 0.001, "step": 291970 }, { "epoch": 70.13, "learning_rate": 6.643496719997028e-06, "loss": 0.0023, "step": 291980 }, { "epoch": 70.13, "learning_rate": 6.641262019651317e-06, "loss": 0.0025, "step": 291990 }, { "epoch": 70.13, "learning_rate": 6.639027668479497e-06, "loss": 0.001, "step": 292000 }, { "epoch": 70.14, "learning_rate": 6.636793666499591e-06, "loss": 0.002, "step": 292010 }, { "epoch": 70.14, "learning_rate": 6.634560013729569e-06, "loss": 0.001, "step": 292020 }, { "epoch": 70.14, "learning_rate": 6.632326710187403e-06, "loss": 0.0012, "step": 292030 }, { "epoch": 70.14, "learning_rate": 6.630093755891115e-06, "loss": 0.0023, "step": 292040 }, { "epoch": 70.15, "learning_rate": 6.6278611508586665e-06, "loss": 0.001, "step": 292050 }, { "epoch": 70.15, "learning_rate": 6.625628895108038e-06, "loss": 0.0013, "step": 292060 }, { "epoch": 70.15, "learning_rate": 6.62339698865721e-06, "loss": 0.001, "step": 292070 }, { "epoch": 70.15, "learning_rate": 6.6211654315241566e-06, "loss": 0.0012, "step": 292080 }, { "epoch": 70.16, "learning_rate": 6.618934223726841e-06, "loss": 0.001, "step": 292090 }, { "epoch": 70.16, "learning_rate": 6.616703365283233e-06, "loss": 0.0022, "step": 292100 }, { "epoch": 70.16, "learning_rate": 6.6144728562113234e-06, "loss": 0.0009, "step": 292110 }, { "epoch": 70.16, "learning_rate": 6.612242696529036e-06, "loss": 0.001, "step": 292120 }, { "epoch": 70.16, "learning_rate": 6.610012886254347e-06, "loss": 0.0012, "step": 292130 }, { "epoch": 70.17, "learning_rate": 6.607783425405217e-06, "loss": 0.0012, "step": 292140 }, { "epoch": 70.17, "learning_rate": 6.605554313999612e-06, "loss": 0.0024, "step": 292150 }, { "epoch": 70.17, "learning_rate": 6.6033255520554615e-06, "loss": 0.0009, "step": 292160 }, { "epoch": 70.17, "learning_rate": 6.6010971395907065e-06, "loss": 0.0027, "step": 292170 }, { "epoch": 70.18, "learning_rate": 6.598869076623321e-06, "loss": 0.0011, "step": 292180 }, { "epoch": 70.18, "learning_rate": 6.59664136317123e-06, "loss": 0.0039, "step": 292190 }, { "epoch": 70.18, "learning_rate": 6.594413999252386e-06, "loss": 0.0026, "step": 292200 }, { "epoch": 70.18, "learning_rate": 6.592186984884713e-06, "loss": 0.002, "step": 292210 }, { "epoch": 70.19, "learning_rate": 6.589960320086152e-06, "loss": 0.0011, "step": 292220 }, { "epoch": 70.19, "learning_rate": 6.587734004874635e-06, "loss": 0.0024, "step": 292230 }, { "epoch": 70.19, "learning_rate": 6.585508039268079e-06, "loss": 0.0025, "step": 292240 }, { "epoch": 70.19, "learning_rate": 6.583282423284437e-06, "loss": 0.0011, "step": 292250 }, { "epoch": 70.19, "learning_rate": 6.581057156941611e-06, "loss": 0.0012, "step": 292260 }, { "epoch": 70.2, "learning_rate": 6.5788322402575155e-06, "loss": 0.0034, "step": 292270 }, { "epoch": 70.2, "learning_rate": 6.576607673250085e-06, "loss": 0.0011, "step": 292280 }, { "epoch": 70.2, "learning_rate": 6.5743834559372275e-06, "loss": 0.0012, "step": 292290 }, { "epoch": 70.2, "learning_rate": 6.572159588336862e-06, "loss": 0.0011, "step": 292300 }, { "epoch": 70.21, "learning_rate": 6.5699360704668864e-06, "loss": 0.0017, "step": 292310 }, { "epoch": 70.21, "learning_rate": 6.567712902345208e-06, "loss": 0.0015, "step": 292320 }, { "epoch": 70.21, "learning_rate": 6.565490083989739e-06, "loss": 0.0018, "step": 292330 }, { "epoch": 70.21, "learning_rate": 6.563267615418373e-06, "loss": 0.0013, "step": 292340 }, { "epoch": 70.21, "learning_rate": 6.56104549664901e-06, "loss": 0.001, "step": 292350 }, { "epoch": 70.22, "learning_rate": 6.5588237276995476e-06, "loss": 0.0017, "step": 292360 }, { "epoch": 70.22, "learning_rate": 6.5566023085878616e-06, "loss": 0.0012, "step": 292370 }, { "epoch": 70.22, "learning_rate": 6.554381239331864e-06, "loss": 0.0013, "step": 292380 }, { "epoch": 70.22, "learning_rate": 6.552160519949446e-06, "loss": 0.0013, "step": 292390 }, { "epoch": 70.23, "learning_rate": 6.549940150458467e-06, "loss": 0.0034, "step": 292400 }, { "epoch": 70.23, "learning_rate": 6.547720130876805e-06, "loss": 0.001, "step": 292410 }, { "epoch": 70.23, "learning_rate": 6.545500461222365e-06, "loss": 0.0014, "step": 292420 }, { "epoch": 70.23, "learning_rate": 6.543281141513008e-06, "loss": 0.003, "step": 292430 }, { "epoch": 70.24, "learning_rate": 6.541062171766605e-06, "loss": 0.0011, "step": 292440 }, { "epoch": 70.24, "learning_rate": 6.538843552001034e-06, "loss": 0.0021, "step": 292450 }, { "epoch": 70.24, "learning_rate": 6.536625282234155e-06, "loss": 0.0011, "step": 292460 }, { "epoch": 70.24, "learning_rate": 6.53440736248383e-06, "loss": 0.0011, "step": 292470 }, { "epoch": 70.24, "learning_rate": 6.532189792767924e-06, "loss": 0.0014, "step": 292480 }, { "epoch": 70.25, "learning_rate": 6.529972573104292e-06, "loss": 0.0016, "step": 292490 }, { "epoch": 70.25, "learning_rate": 6.527755703510796e-06, "loss": 0.001, "step": 292500 }, { "epoch": 70.25, "learning_rate": 6.525539184005275e-06, "loss": 0.001, "step": 292510 }, { "epoch": 70.25, "learning_rate": 6.523323014605598e-06, "loss": 0.0012, "step": 292520 }, { "epoch": 70.26, "learning_rate": 6.521107195329612e-06, "loss": 0.0015, "step": 292530 }, { "epoch": 70.26, "learning_rate": 6.518891726195136e-06, "loss": 0.0014, "step": 292540 }, { "epoch": 70.26, "learning_rate": 6.516676607220035e-06, "loss": 0.0013, "step": 292550 }, { "epoch": 70.26, "learning_rate": 6.5144618384221425e-06, "loss": 0.001, "step": 292560 }, { "epoch": 70.27, "learning_rate": 6.5122474198192895e-06, "loss": 0.0025, "step": 292570 }, { "epoch": 70.27, "learning_rate": 6.510033351429312e-06, "loss": 0.0011, "step": 292580 }, { "epoch": 70.27, "learning_rate": 6.507819633270046e-06, "loss": 0.0015, "step": 292590 }, { "epoch": 70.27, "learning_rate": 6.505606265359304e-06, "loss": 0.0012, "step": 292600 }, { "epoch": 70.27, "learning_rate": 6.503393247714928e-06, "loss": 0.0009, "step": 292610 }, { "epoch": 70.28, "learning_rate": 6.501180580354715e-06, "loss": 0.0012, "step": 292620 }, { "epoch": 70.28, "learning_rate": 6.498968263296523e-06, "loss": 0.001, "step": 292630 }, { "epoch": 70.28, "learning_rate": 6.496756296558137e-06, "loss": 0.0011, "step": 292640 }, { "epoch": 70.28, "learning_rate": 6.4945446801573666e-06, "loss": 0.0012, "step": 292650 }, { "epoch": 70.29, "learning_rate": 6.4923334141120395e-06, "loss": 0.0009, "step": 292660 }, { "epoch": 70.29, "learning_rate": 6.490122498439977e-06, "loss": 0.0012, "step": 292670 }, { "epoch": 70.29, "learning_rate": 6.487911933158936e-06, "loss": 0.0015, "step": 292680 }, { "epoch": 70.29, "learning_rate": 6.485701718286763e-06, "loss": 0.001, "step": 292690 }, { "epoch": 70.29, "learning_rate": 6.483491853841239e-06, "loss": 0.0012, "step": 292700 }, { "epoch": 70.3, "learning_rate": 6.4812823398401666e-06, "loss": 0.0019, "step": 292710 }, { "epoch": 70.3, "learning_rate": 6.479073176301332e-06, "loss": 0.0009, "step": 292720 }, { "epoch": 70.3, "learning_rate": 6.4768643632425294e-06, "loss": 0.0014, "step": 292730 }, { "epoch": 70.3, "learning_rate": 6.474655900681548e-06, "loss": 0.0017, "step": 292740 }, { "epoch": 70.31, "learning_rate": 6.472447788636166e-06, "loss": 0.0014, "step": 292750 }, { "epoch": 70.31, "learning_rate": 6.470240027124175e-06, "loss": 0.0017, "step": 292760 }, { "epoch": 70.31, "learning_rate": 6.468032616163367e-06, "loss": 0.0014, "step": 292770 }, { "epoch": 70.31, "learning_rate": 6.465825555771476e-06, "loss": 0.0012, "step": 292780 }, { "epoch": 70.32, "learning_rate": 6.463618845966313e-06, "loss": 0.001, "step": 292790 }, { "epoch": 70.32, "learning_rate": 6.461412486765639e-06, "loss": 0.0009, "step": 292800 }, { "epoch": 70.32, "learning_rate": 6.459206478187224e-06, "loss": 0.0013, "step": 292810 }, { "epoch": 70.32, "learning_rate": 6.457000820248826e-06, "loss": 0.001, "step": 292820 }, { "epoch": 70.32, "learning_rate": 6.454795512968215e-06, "loss": 0.001, "step": 292830 }, { "epoch": 70.33, "learning_rate": 6.4525905563631475e-06, "loss": 0.0013, "step": 292840 }, { "epoch": 70.33, "learning_rate": 6.450385950451376e-06, "loss": 0.001, "step": 292850 }, { "epoch": 70.33, "learning_rate": 6.4481816952506605e-06, "loss": 0.0012, "step": 292860 }, { "epoch": 70.33, "learning_rate": 6.445977790778757e-06, "loss": 0.0015, "step": 292870 }, { "epoch": 70.34, "learning_rate": 6.443774237053402e-06, "loss": 0.0012, "step": 292880 }, { "epoch": 70.34, "learning_rate": 6.441571034092331e-06, "loss": 0.0039, "step": 292890 }, { "epoch": 70.34, "learning_rate": 6.439368181913319e-06, "loss": 0.0011, "step": 292900 }, { "epoch": 70.34, "learning_rate": 6.437165680534102e-06, "loss": 0.001, "step": 292910 }, { "epoch": 70.35, "learning_rate": 6.434963529972376e-06, "loss": 0.0012, "step": 292920 }, { "epoch": 70.35, "learning_rate": 6.432761730245918e-06, "loss": 0.001, "step": 292930 }, { "epoch": 70.35, "learning_rate": 6.430560281372444e-06, "loss": 0.0011, "step": 292940 }, { "epoch": 70.35, "learning_rate": 6.428359183369681e-06, "loss": 0.0025, "step": 292950 }, { "epoch": 70.35, "learning_rate": 6.426158436255358e-06, "loss": 0.001, "step": 292960 }, { "epoch": 70.36, "learning_rate": 6.423958040047201e-06, "loss": 0.001, "step": 292970 }, { "epoch": 70.36, "learning_rate": 6.4217579947629225e-06, "loss": 0.0011, "step": 292980 }, { "epoch": 70.36, "learning_rate": 6.419558300420231e-06, "loss": 0.0011, "step": 292990 }, { "epoch": 70.36, "learning_rate": 6.417358957036879e-06, "loss": 0.0013, "step": 293000 }, { "epoch": 70.37, "learning_rate": 6.415159964630535e-06, "loss": 0.0013, "step": 293010 }, { "epoch": 70.37, "learning_rate": 6.41296132321893e-06, "loss": 0.0009, "step": 293020 }, { "epoch": 70.37, "learning_rate": 6.410763032819755e-06, "loss": 0.0013, "step": 293030 }, { "epoch": 70.37, "learning_rate": 6.40856509345073e-06, "loss": 0.0009, "step": 293040 }, { "epoch": 70.37, "learning_rate": 6.4063675051295625e-06, "loss": 0.001, "step": 293050 }, { "epoch": 70.38, "learning_rate": 6.40417026787391e-06, "loss": 0.0011, "step": 293060 }, { "epoch": 70.38, "learning_rate": 6.401973381701509e-06, "loss": 0.0009, "step": 293070 }, { "epoch": 70.38, "learning_rate": 6.399776846630034e-06, "loss": 0.001, "step": 293080 }, { "epoch": 70.38, "learning_rate": 6.397580662677171e-06, "loss": 0.0013, "step": 293090 }, { "epoch": 70.39, "learning_rate": 6.395384829860618e-06, "loss": 0.0011, "step": 293100 }, { "epoch": 70.39, "learning_rate": 6.393189348198047e-06, "loss": 0.0012, "step": 293110 }, { "epoch": 70.39, "learning_rate": 6.390994217707141e-06, "loss": 0.0021, "step": 293120 }, { "epoch": 70.39, "learning_rate": 6.388799438405574e-06, "loss": 0.0011, "step": 293130 }, { "epoch": 70.4, "learning_rate": 6.386605010311031e-06, "loss": 0.0009, "step": 293140 }, { "epoch": 70.4, "learning_rate": 6.384410933441193e-06, "loss": 0.0012, "step": 293150 }, { "epoch": 70.4, "learning_rate": 6.38221720781369e-06, "loss": 0.0011, "step": 293160 }, { "epoch": 70.4, "learning_rate": 6.38002383344623e-06, "loss": 0.0021, "step": 293170 }, { "epoch": 70.4, "learning_rate": 6.377830810356455e-06, "loss": 0.0009, "step": 293180 }, { "epoch": 70.41, "learning_rate": 6.375638138562035e-06, "loss": 0.0009, "step": 293190 }, { "epoch": 70.41, "learning_rate": 6.37344581808062e-06, "loss": 0.001, "step": 293200 }, { "epoch": 70.41, "learning_rate": 6.37125384892987e-06, "loss": 0.0012, "step": 293210 }, { "epoch": 70.41, "learning_rate": 6.369062231127437e-06, "loss": 0.0017, "step": 293220 }, { "epoch": 70.42, "learning_rate": 6.366870964690963e-06, "loss": 0.0012, "step": 293230 }, { "epoch": 70.42, "learning_rate": 6.364680049638117e-06, "loss": 0.0011, "step": 293240 }, { "epoch": 70.42, "learning_rate": 6.362489485986517e-06, "loss": 0.0012, "step": 293250 }, { "epoch": 70.42, "learning_rate": 6.360299273753811e-06, "loss": 0.0011, "step": 293260 }, { "epoch": 70.43, "learning_rate": 6.358109412957636e-06, "loss": 0.001, "step": 293270 }, { "epoch": 70.43, "learning_rate": 6.3559199036156366e-06, "loss": 0.0013, "step": 293280 }, { "epoch": 70.43, "learning_rate": 6.353730745745451e-06, "loss": 0.0016, "step": 293290 }, { "epoch": 70.43, "learning_rate": 6.351541939364675e-06, "loss": 0.0011, "step": 293300 }, { "epoch": 70.43, "learning_rate": 6.349353484490972e-06, "loss": 0.0011, "step": 293310 }, { "epoch": 70.44, "learning_rate": 6.3471653811419505e-06, "loss": 0.0011, "step": 293320 }, { "epoch": 70.44, "learning_rate": 6.3449776293352305e-06, "loss": 0.002, "step": 293330 }, { "epoch": 70.44, "learning_rate": 6.342790229088436e-06, "loss": 0.0012, "step": 293340 }, { "epoch": 70.44, "learning_rate": 6.340603180419175e-06, "loss": 0.0027, "step": 293350 }, { "epoch": 70.45, "learning_rate": 6.338416483345067e-06, "loss": 0.001, "step": 293360 }, { "epoch": 70.45, "learning_rate": 6.3362301378837086e-06, "loss": 0.0012, "step": 293370 }, { "epoch": 70.45, "learning_rate": 6.334044144052736e-06, "loss": 0.0012, "step": 293380 }, { "epoch": 70.45, "learning_rate": 6.331858501869725e-06, "loss": 0.0009, "step": 293390 }, { "epoch": 70.45, "learning_rate": 6.329673211352277e-06, "loss": 0.0018, "step": 293400 }, { "epoch": 70.46, "learning_rate": 6.327488272518006e-06, "loss": 0.0011, "step": 293410 }, { "epoch": 70.46, "learning_rate": 6.325303685384504e-06, "loss": 0.0024, "step": 293420 }, { "epoch": 70.46, "learning_rate": 6.323119449969362e-06, "loss": 0.0024, "step": 293430 }, { "epoch": 70.46, "learning_rate": 6.32093556629017e-06, "loss": 0.0009, "step": 293440 }, { "epoch": 70.47, "learning_rate": 6.318752034364511e-06, "loss": 0.0023, "step": 293450 }, { "epoch": 70.47, "learning_rate": 6.316568854209976e-06, "loss": 0.0014, "step": 293460 }, { "epoch": 70.47, "learning_rate": 6.3143860258441374e-06, "loss": 0.0012, "step": 293470 }, { "epoch": 70.47, "learning_rate": 6.312203549284584e-06, "loss": 0.0013, "step": 293480 }, { "epoch": 70.48, "learning_rate": 6.3100214245488896e-06, "loss": 0.0011, "step": 293490 }, { "epoch": 70.48, "learning_rate": 6.3078396516546175e-06, "loss": 0.005, "step": 293500 }, { "epoch": 70.48, "learning_rate": 6.305658230619338e-06, "loss": 0.0126, "step": 293510 }, { "epoch": 70.48, "learning_rate": 6.3034771614606465e-06, "loss": 0.001, "step": 293520 }, { "epoch": 70.48, "learning_rate": 6.301296444196075e-06, "loss": 0.0043, "step": 293530 }, { "epoch": 70.49, "learning_rate": 6.299116078843181e-06, "loss": 0.003, "step": 293540 }, { "epoch": 70.49, "learning_rate": 6.296936065419556e-06, "loss": 0.0011, "step": 293550 }, { "epoch": 70.49, "learning_rate": 6.2947564039427364e-06, "loss": 0.0017, "step": 293560 }, { "epoch": 70.49, "learning_rate": 6.292577094430274e-06, "loss": 0.0013, "step": 293570 }, { "epoch": 70.5, "learning_rate": 6.290398136899728e-06, "loss": 0.0012, "step": 293580 }, { "epoch": 70.5, "learning_rate": 6.288219531368639e-06, "loss": 0.001, "step": 293590 }, { "epoch": 70.5, "learning_rate": 6.286041277854549e-06, "loss": 0.0044, "step": 293600 }, { "epoch": 70.5, "learning_rate": 6.2838633763749936e-06, "loss": 0.0018, "step": 293610 }, { "epoch": 70.51, "learning_rate": 6.281685826947547e-06, "loss": 0.0016, "step": 293620 }, { "epoch": 70.51, "learning_rate": 6.279508629589709e-06, "loss": 0.001, "step": 293630 }, { "epoch": 70.51, "learning_rate": 6.277331784319007e-06, "loss": 0.0059, "step": 293640 }, { "epoch": 70.51, "learning_rate": 6.2751552911530065e-06, "loss": 0.0013, "step": 293650 }, { "epoch": 70.51, "learning_rate": 6.2729791501092265e-06, "loss": 0.0011, "step": 293660 }, { "epoch": 70.52, "learning_rate": 6.270803361205168e-06, "loss": 0.0011, "step": 293670 }, { "epoch": 70.52, "learning_rate": 6.268627924458359e-06, "loss": 0.0011, "step": 293680 }, { "epoch": 70.52, "learning_rate": 6.2664528398863384e-06, "loss": 0.0025, "step": 293690 }, { "epoch": 70.52, "learning_rate": 6.26427810750661e-06, "loss": 0.0012, "step": 293700 }, { "epoch": 70.53, "learning_rate": 6.262103727336688e-06, "loss": 0.0081, "step": 293710 }, { "epoch": 70.53, "learning_rate": 6.259929699394079e-06, "loss": 0.0018, "step": 293720 }, { "epoch": 70.53, "learning_rate": 6.257756023696298e-06, "loss": 0.0012, "step": 293730 }, { "epoch": 70.53, "learning_rate": 6.255582700260848e-06, "loss": 0.0011, "step": 293740 }, { "epoch": 70.53, "learning_rate": 6.2534097291052194e-06, "loss": 0.0134, "step": 293750 }, { "epoch": 70.54, "learning_rate": 6.251237110246944e-06, "loss": 0.0027, "step": 293760 }, { "epoch": 70.54, "learning_rate": 6.249064843703483e-06, "loss": 0.0014, "step": 293770 }, { "epoch": 70.54, "learning_rate": 6.2468929294923315e-06, "loss": 0.0012, "step": 293780 }, { "epoch": 70.54, "learning_rate": 6.244721367631007e-06, "loss": 0.0011, "step": 293790 }, { "epoch": 70.55, "learning_rate": 6.242550158136978e-06, "loss": 0.0019, "step": 293800 }, { "epoch": 70.55, "learning_rate": 6.2403793010277325e-06, "loss": 0.0015, "step": 293810 }, { "epoch": 70.55, "learning_rate": 6.238208796320754e-06, "loss": 0.0012, "step": 293820 }, { "epoch": 70.55, "learning_rate": 6.2360386440335265e-06, "loss": 0.0013, "step": 293830 }, { "epoch": 70.56, "learning_rate": 6.233868844183521e-06, "loss": 0.0069, "step": 293840 }, { "epoch": 70.56, "learning_rate": 6.23169939678821e-06, "loss": 0.0038, "step": 293850 }, { "epoch": 70.56, "learning_rate": 6.229530301865066e-06, "loss": 0.0009, "step": 293860 }, { "epoch": 70.56, "learning_rate": 6.227361559431555e-06, "loss": 0.001, "step": 293870 }, { "epoch": 70.56, "learning_rate": 6.225193169505139e-06, "loss": 0.0011, "step": 293880 }, { "epoch": 70.57, "learning_rate": 6.223025132103294e-06, "loss": 0.001, "step": 293890 }, { "epoch": 70.57, "learning_rate": 6.220857447243483e-06, "loss": 0.0011, "step": 293900 }, { "epoch": 70.57, "learning_rate": 6.218690114943138e-06, "loss": 0.0014, "step": 293910 }, { "epoch": 70.57, "learning_rate": 6.216523135219715e-06, "loss": 0.0013, "step": 293920 }, { "epoch": 70.58, "learning_rate": 6.2143565080906905e-06, "loss": 0.0011, "step": 293930 }, { "epoch": 70.58, "learning_rate": 6.212190233573495e-06, "loss": 0.0015, "step": 293940 }, { "epoch": 70.58, "learning_rate": 6.2100243116855805e-06, "loss": 0.0011, "step": 293950 }, { "epoch": 70.58, "learning_rate": 6.207858742444383e-06, "loss": 0.0015, "step": 293960 }, { "epoch": 70.59, "learning_rate": 6.2056935258673455e-06, "loss": 0.001, "step": 293970 }, { "epoch": 70.59, "learning_rate": 6.203528661971902e-06, "loss": 0.0057, "step": 293980 }, { "epoch": 70.59, "learning_rate": 6.20136415077549e-06, "loss": 0.001, "step": 293990 }, { "epoch": 70.59, "learning_rate": 6.19919999229554e-06, "loss": 0.0017, "step": 294000 }, { "epoch": 70.59, "learning_rate": 6.197036186549482e-06, "loss": 0.0016, "step": 294010 }, { "epoch": 70.6, "learning_rate": 6.194872733554724e-06, "loss": 0.0035, "step": 294020 }, { "epoch": 70.6, "learning_rate": 6.192709633328714e-06, "loss": 0.0032, "step": 294030 }, { "epoch": 70.6, "learning_rate": 6.190546885888876e-06, "loss": 0.0011, "step": 294040 }, { "epoch": 70.6, "learning_rate": 6.188384491252586e-06, "loss": 0.001, "step": 294050 }, { "epoch": 70.61, "learning_rate": 6.186222449437301e-06, "loss": 0.0024, "step": 294060 }, { "epoch": 70.61, "learning_rate": 6.184060760460409e-06, "loss": 0.0014, "step": 294070 }, { "epoch": 70.61, "learning_rate": 6.181899424339327e-06, "loss": 0.001, "step": 294080 }, { "epoch": 70.61, "learning_rate": 6.1797384410914595e-06, "loss": 0.0017, "step": 294090 }, { "epoch": 70.61, "learning_rate": 6.177577810734209e-06, "loss": 0.0013, "step": 294100 }, { "epoch": 70.62, "learning_rate": 6.175417533284972e-06, "loss": 0.001, "step": 294110 }, { "epoch": 70.62, "learning_rate": 6.173257608761152e-06, "loss": 0.0012, "step": 294120 }, { "epoch": 70.62, "learning_rate": 6.171098037180123e-06, "loss": 0.0009, "step": 294130 }, { "epoch": 70.62, "learning_rate": 6.1689388185593165e-06, "loss": 0.0011, "step": 294140 }, { "epoch": 70.63, "learning_rate": 6.166779952916085e-06, "loss": 0.001, "step": 294150 }, { "epoch": 70.63, "learning_rate": 6.16462144026782e-06, "loss": 0.0011, "step": 294160 }, { "epoch": 70.63, "learning_rate": 6.162463280631919e-06, "loss": 0.0014, "step": 294170 }, { "epoch": 70.63, "learning_rate": 6.160305474025763e-06, "loss": 0.001, "step": 294180 }, { "epoch": 70.64, "learning_rate": 6.158148020466698e-06, "loss": 0.0009, "step": 294190 }, { "epoch": 70.64, "learning_rate": 6.155990919972127e-06, "loss": 0.0011, "step": 294200 }, { "epoch": 70.64, "learning_rate": 6.15383417255942e-06, "loss": 0.0013, "step": 294210 }, { "epoch": 70.64, "learning_rate": 6.151677778245935e-06, "loss": 0.0013, "step": 294220 }, { "epoch": 70.64, "learning_rate": 6.149521737049046e-06, "loss": 0.0011, "step": 294230 }, { "epoch": 70.65, "learning_rate": 6.1473660489861084e-06, "loss": 0.0014, "step": 294240 }, { "epoch": 70.65, "learning_rate": 6.1452107140744895e-06, "loss": 0.0009, "step": 294250 }, { "epoch": 70.65, "learning_rate": 6.143055732331532e-06, "loss": 0.0011, "step": 294260 }, { "epoch": 70.65, "learning_rate": 6.140901103774615e-06, "loss": 0.0047, "step": 294270 }, { "epoch": 70.66, "learning_rate": 6.138746828421082e-06, "loss": 0.0011, "step": 294280 }, { "epoch": 70.66, "learning_rate": 6.136592906288257e-06, "loss": 0.001, "step": 294290 }, { "epoch": 70.66, "learning_rate": 6.134439337393516e-06, "loss": 0.0011, "step": 294300 }, { "epoch": 70.66, "learning_rate": 6.1322861217541936e-06, "loss": 0.001, "step": 294310 }, { "epoch": 70.66, "learning_rate": 6.130133259387632e-06, "loss": 0.0012, "step": 294320 }, { "epoch": 70.67, "learning_rate": 6.127980750311146e-06, "loss": 0.0012, "step": 294330 }, { "epoch": 70.67, "learning_rate": 6.1258285945420994e-06, "loss": 0.0011, "step": 294340 }, { "epoch": 70.67, "learning_rate": 6.123676792097815e-06, "loss": 0.0013, "step": 294350 }, { "epoch": 70.67, "learning_rate": 6.121525342995616e-06, "loss": 0.0018, "step": 294360 }, { "epoch": 70.68, "learning_rate": 6.11937424725283e-06, "loss": 0.0012, "step": 294370 }, { "epoch": 70.68, "learning_rate": 6.117223504886782e-06, "loss": 0.0011, "step": 294380 }, { "epoch": 70.68, "learning_rate": 6.115073115914788e-06, "loss": 0.0009, "step": 294390 }, { "epoch": 70.68, "learning_rate": 6.112923080354166e-06, "loss": 0.0011, "step": 294400 }, { "epoch": 70.69, "learning_rate": 6.110773398222236e-06, "loss": 0.0011, "step": 294410 }, { "epoch": 70.69, "learning_rate": 6.108624069536323e-06, "loss": 0.0012, "step": 294420 }, { "epoch": 70.69, "learning_rate": 6.1064750943136965e-06, "loss": 0.001, "step": 294430 }, { "epoch": 70.69, "learning_rate": 6.104326472571698e-06, "loss": 0.001, "step": 294440 }, { "epoch": 70.69, "learning_rate": 6.102178204327619e-06, "loss": 0.0011, "step": 294450 }, { "epoch": 70.7, "learning_rate": 6.100030289598757e-06, "loss": 0.0012, "step": 294460 }, { "epoch": 70.7, "learning_rate": 6.09788272840241e-06, "loss": 0.0013, "step": 294470 }, { "epoch": 70.7, "learning_rate": 6.0957355207558795e-06, "loss": 0.0015, "step": 294480 }, { "epoch": 70.7, "learning_rate": 6.093588666676453e-06, "loss": 0.001, "step": 294490 }, { "epoch": 70.71, "learning_rate": 6.0914421661814045e-06, "loss": 0.0015, "step": 294500 }, { "epoch": 70.71, "learning_rate": 6.089296019288054e-06, "loss": 0.0015, "step": 294510 }, { "epoch": 70.71, "learning_rate": 6.087150226013655e-06, "loss": 0.0009, "step": 294520 }, { "epoch": 70.71, "learning_rate": 6.085004786375504e-06, "loss": 0.0011, "step": 294530 }, { "epoch": 70.72, "learning_rate": 6.082859700390853e-06, "loss": 0.0018, "step": 294540 }, { "epoch": 70.72, "learning_rate": 6.0807149680770115e-06, "loss": 0.0012, "step": 294550 }, { "epoch": 70.72, "learning_rate": 6.078570589451244e-06, "loss": 0.0012, "step": 294560 }, { "epoch": 70.72, "learning_rate": 6.076426564530791e-06, "loss": 0.001, "step": 294570 }, { "epoch": 70.72, "learning_rate": 6.07428289333295e-06, "loss": 0.0012, "step": 294580 }, { "epoch": 70.73, "learning_rate": 6.072139575874975e-06, "loss": 0.001, "step": 294590 }, { "epoch": 70.73, "learning_rate": 6.069996612174122e-06, "loss": 0.0013, "step": 294600 }, { "epoch": 70.73, "learning_rate": 6.067854002247653e-06, "loss": 0.0013, "step": 294610 }, { "epoch": 70.73, "learning_rate": 6.0657117461128174e-06, "loss": 0.001, "step": 294620 }, { "epoch": 70.74, "learning_rate": 6.063569843786876e-06, "loss": 0.001, "step": 294630 }, { "epoch": 70.74, "learning_rate": 6.0614282952870586e-06, "loss": 0.0011, "step": 294640 }, { "epoch": 70.74, "learning_rate": 6.059287100630645e-06, "loss": 0.0014, "step": 294650 }, { "epoch": 70.74, "learning_rate": 6.05714625983485e-06, "loss": 0.0009, "step": 294660 }, { "epoch": 70.74, "learning_rate": 6.055005772916916e-06, "loss": 0.0014, "step": 294670 }, { "epoch": 70.75, "learning_rate": 6.0528656398940895e-06, "loss": 0.0011, "step": 294680 }, { "epoch": 70.75, "learning_rate": 6.050725860783613e-06, "loss": 0.0023, "step": 294690 }, { "epoch": 70.75, "learning_rate": 6.048586435602699e-06, "loss": 0.0024, "step": 294700 }, { "epoch": 70.75, "learning_rate": 6.046447364368596e-06, "loss": 0.0026, "step": 294710 }, { "epoch": 70.76, "learning_rate": 6.044308647098512e-06, "loss": 0.0012, "step": 294720 }, { "epoch": 70.76, "learning_rate": 6.042170283809684e-06, "loss": 0.0012, "step": 294730 }, { "epoch": 70.76, "learning_rate": 6.040032274519314e-06, "loss": 0.003, "step": 294740 }, { "epoch": 70.76, "learning_rate": 6.037894619244655e-06, "loss": 0.0014, "step": 294750 }, { "epoch": 70.77, "learning_rate": 6.035757318002894e-06, "loss": 0.0026, "step": 294760 }, { "epoch": 70.77, "learning_rate": 6.033620370811243e-06, "loss": 0.001, "step": 294770 }, { "epoch": 70.77, "learning_rate": 6.031483777686908e-06, "loss": 0.0012, "step": 294780 }, { "epoch": 70.77, "learning_rate": 6.029347538647117e-06, "loss": 0.003, "step": 294790 }, { "epoch": 70.77, "learning_rate": 6.027211653709069e-06, "loss": 0.0021, "step": 294800 }, { "epoch": 70.78, "learning_rate": 6.025076122889939e-06, "loss": 0.0009, "step": 294810 }, { "epoch": 70.78, "learning_rate": 6.022940946206945e-06, "loss": 0.0051, "step": 294820 }, { "epoch": 70.78, "learning_rate": 6.020806123677286e-06, "loss": 0.0011, "step": 294830 }, { "epoch": 70.78, "learning_rate": 6.018671655318148e-06, "loss": 0.0031, "step": 294840 }, { "epoch": 70.79, "learning_rate": 6.016537541146711e-06, "loss": 0.001, "step": 294850 }, { "epoch": 70.79, "learning_rate": 6.014403781180178e-06, "loss": 0.0012, "step": 294860 }, { "epoch": 70.79, "learning_rate": 6.012270375435719e-06, "loss": 0.0012, "step": 294870 }, { "epoch": 70.79, "learning_rate": 6.010137323930509e-06, "loss": 0.001, "step": 294880 }, { "epoch": 70.8, "learning_rate": 6.008004626681763e-06, "loss": 0.0012, "step": 294890 }, { "epoch": 70.8, "learning_rate": 6.005872283706609e-06, "loss": 0.0018, "step": 294900 }, { "epoch": 70.8, "learning_rate": 6.003740295022236e-06, "loss": 0.0012, "step": 294910 }, { "epoch": 70.8, "learning_rate": 6.0016086606458244e-06, "loss": 0.0011, "step": 294920 }, { "epoch": 70.8, "learning_rate": 5.999477380594537e-06, "loss": 0.001, "step": 294930 }, { "epoch": 70.81, "learning_rate": 5.9973464548855275e-06, "loss": 0.0013, "step": 294940 }, { "epoch": 70.81, "learning_rate": 5.995215883535965e-06, "loss": 0.0015, "step": 294950 }, { "epoch": 70.81, "learning_rate": 5.993085666563003e-06, "loss": 0.0011, "step": 294960 }, { "epoch": 70.81, "learning_rate": 5.990955803983795e-06, "loss": 0.0011, "step": 294970 }, { "epoch": 70.82, "learning_rate": 5.988826295815497e-06, "loss": 0.001, "step": 294980 }, { "epoch": 70.82, "learning_rate": 5.9866971420752595e-06, "loss": 0.0011, "step": 294990 }, { "epoch": 70.82, "learning_rate": 5.984568342780228e-06, "loss": 0.0011, "step": 295000 }, { "epoch": 70.82, "learning_rate": 5.982439897947539e-06, "loss": 0.0018, "step": 295010 }, { "epoch": 70.82, "learning_rate": 5.9803118075943295e-06, "loss": 0.0011, "step": 295020 }, { "epoch": 70.83, "learning_rate": 5.978184071737769e-06, "loss": 0.0014, "step": 295030 }, { "epoch": 70.83, "learning_rate": 5.97605669039496e-06, "loss": 0.0027, "step": 295040 }, { "epoch": 70.83, "learning_rate": 5.973929663583033e-06, "loss": 0.0011, "step": 295050 }, { "epoch": 70.83, "learning_rate": 5.971802991319136e-06, "loss": 0.001, "step": 295060 }, { "epoch": 70.84, "learning_rate": 5.969676673620389e-06, "loss": 0.0014, "step": 295070 }, { "epoch": 70.84, "learning_rate": 5.967550710503916e-06, "loss": 0.0012, "step": 295080 }, { "epoch": 70.84, "learning_rate": 5.965425101986838e-06, "loss": 0.0012, "step": 295090 }, { "epoch": 70.84, "learning_rate": 5.963299848086268e-06, "loss": 0.0008, "step": 295100 }, { "epoch": 70.85, "learning_rate": 5.961174948819326e-06, "loss": 0.0016, "step": 295110 }, { "epoch": 70.85, "learning_rate": 5.9590504042031095e-06, "loss": 0.0012, "step": 295120 }, { "epoch": 70.85, "learning_rate": 5.956926214254766e-06, "loss": 0.0014, "step": 295130 }, { "epoch": 70.85, "learning_rate": 5.954802378991359e-06, "loss": 0.001, "step": 295140 }, { "epoch": 70.85, "learning_rate": 5.952678898430003e-06, "loss": 0.0011, "step": 295150 }, { "epoch": 70.86, "learning_rate": 5.950555772587818e-06, "loss": 0.001, "step": 295160 }, { "epoch": 70.86, "learning_rate": 5.948433001481896e-06, "loss": 0.0012, "step": 295170 }, { "epoch": 70.86, "learning_rate": 5.946310585129311e-06, "loss": 0.0013, "step": 295180 }, { "epoch": 70.86, "learning_rate": 5.944188523547162e-06, "loss": 0.0013, "step": 295190 }, { "epoch": 70.87, "learning_rate": 5.942066816752556e-06, "loss": 0.0028, "step": 295200 }, { "epoch": 70.87, "learning_rate": 5.939945464762564e-06, "loss": 0.0011, "step": 295210 }, { "epoch": 70.87, "learning_rate": 5.9378244675942775e-06, "loss": 0.001, "step": 295220 }, { "epoch": 70.87, "learning_rate": 5.935703825264777e-06, "loss": 0.0025, "step": 295230 }, { "epoch": 70.88, "learning_rate": 5.933583537791132e-06, "loss": 0.0014, "step": 295240 }, { "epoch": 70.88, "learning_rate": 5.931463605190424e-06, "loss": 0.001, "step": 295250 }, { "epoch": 70.88, "learning_rate": 5.929344027479716e-06, "loss": 0.001, "step": 295260 }, { "epoch": 70.88, "learning_rate": 5.927224804676101e-06, "loss": 0.0012, "step": 295270 }, { "epoch": 70.88, "learning_rate": 5.925105936796621e-06, "loss": 0.001, "step": 295280 }, { "epoch": 70.89, "learning_rate": 5.92298742385834e-06, "loss": 0.0015, "step": 295290 }, { "epoch": 70.89, "learning_rate": 5.920869265878332e-06, "loss": 0.0014, "step": 295300 }, { "epoch": 70.89, "learning_rate": 5.9187514628736614e-06, "loss": 0.0012, "step": 295310 }, { "epoch": 70.89, "learning_rate": 5.91663401486135e-06, "loss": 0.001, "step": 295320 }, { "epoch": 70.9, "learning_rate": 5.914516921858482e-06, "loss": 0.0011, "step": 295330 }, { "epoch": 70.9, "learning_rate": 5.9124001838821e-06, "loss": 0.0011, "step": 295340 }, { "epoch": 70.9, "learning_rate": 5.91028380094924e-06, "loss": 0.001, "step": 295350 }, { "epoch": 70.9, "learning_rate": 5.90816777307695e-06, "loss": 0.0036, "step": 295360 }, { "epoch": 70.9, "learning_rate": 5.9060521002822775e-06, "loss": 0.0009, "step": 295370 }, { "epoch": 70.91, "learning_rate": 5.903936782582253e-06, "loss": 0.0011, "step": 295380 }, { "epoch": 70.91, "learning_rate": 5.901821819993913e-06, "loss": 0.0009, "step": 295390 }, { "epoch": 70.91, "learning_rate": 5.899707212534284e-06, "loss": 0.0013, "step": 295400 }, { "epoch": 70.91, "learning_rate": 5.897592960220416e-06, "loss": 0.0014, "step": 295410 }, { "epoch": 70.92, "learning_rate": 5.895479063069309e-06, "loss": 0.0012, "step": 295420 }, { "epoch": 70.92, "learning_rate": 5.893365521097993e-06, "loss": 0.0013, "step": 295430 }, { "epoch": 70.92, "learning_rate": 5.891252334323505e-06, "loss": 0.0011, "step": 295440 }, { "epoch": 70.92, "learning_rate": 5.889139502762847e-06, "loss": 0.001, "step": 295450 }, { "epoch": 70.93, "learning_rate": 5.88702702643304e-06, "loss": 0.001, "step": 295460 }, { "epoch": 70.93, "learning_rate": 5.884914905351096e-06, "loss": 0.0013, "step": 295470 }, { "epoch": 70.93, "learning_rate": 5.882803139534021e-06, "loss": 0.0015, "step": 295480 }, { "epoch": 70.93, "learning_rate": 5.880691728998822e-06, "loss": 0.001, "step": 295490 }, { "epoch": 70.93, "learning_rate": 5.878580673762507e-06, "loss": 0.0012, "step": 295500 }, { "epoch": 70.94, "learning_rate": 5.876469973842069e-06, "loss": 0.001, "step": 295510 }, { "epoch": 70.94, "learning_rate": 5.874359629254511e-06, "loss": 0.0018, "step": 295520 }, { "epoch": 70.94, "learning_rate": 5.8722496400168195e-06, "loss": 0.0025, "step": 295530 }, { "epoch": 70.94, "learning_rate": 5.870140006146002e-06, "loss": 0.0011, "step": 295540 }, { "epoch": 70.95, "learning_rate": 5.8680307276590515e-06, "loss": 0.0011, "step": 295550 }, { "epoch": 70.95, "learning_rate": 5.865921804572921e-06, "loss": 0.001, "step": 295560 }, { "epoch": 70.95, "learning_rate": 5.863813236904625e-06, "loss": 0.0012, "step": 295570 }, { "epoch": 71.0, "learning_rate": 5.861705024671133e-06, "loss": 0.0021, "step": 295580 }, { "epoch": 71.0, "learning_rate": 5.859597167889425e-06, "loss": 0.0009, "step": 295590 }, { "epoch": 71.01, "learning_rate": 5.857489666576477e-06, "loss": 0.0013, "step": 295600 }, { "epoch": 71.01, "learning_rate": 5.855382520749258e-06, "loss": 0.001, "step": 295610 }, { "epoch": 71.01, "learning_rate": 5.853275730424735e-06, "loss": 0.0011, "step": 295620 }, { "epoch": 71.01, "learning_rate": 5.851169295619879e-06, "loss": 0.0016, "step": 295630 }, { "epoch": 71.02, "learning_rate": 5.849063216351658e-06, "loss": 0.0014, "step": 295640 }, { "epoch": 71.02, "learning_rate": 5.8469574926370175e-06, "loss": 0.001, "step": 295650 }, { "epoch": 71.02, "learning_rate": 5.8448521244929276e-06, "loss": 0.0009, "step": 295660 }, { "epoch": 71.02, "learning_rate": 5.842747111936331e-06, "loss": 0.0013, "step": 295670 }, { "epoch": 71.02, "learning_rate": 5.840642454984197e-06, "loss": 0.0012, "step": 295680 }, { "epoch": 71.03, "learning_rate": 5.838538153653472e-06, "loss": 0.001, "step": 295690 }, { "epoch": 71.03, "learning_rate": 5.836434207961083e-06, "loss": 0.0012, "step": 295700 }, { "epoch": 71.03, "learning_rate": 5.834330617923994e-06, "loss": 0.001, "step": 295710 }, { "epoch": 71.03, "learning_rate": 5.8322273835591355e-06, "loss": 0.0011, "step": 295720 }, { "epoch": 71.04, "learning_rate": 5.83012450488345e-06, "loss": 0.0038, "step": 295730 }, { "epoch": 71.04, "learning_rate": 5.828021981913867e-06, "loss": 0.001, "step": 295740 }, { "epoch": 71.04, "learning_rate": 5.825919814667324e-06, "loss": 0.001, "step": 295750 }, { "epoch": 71.04, "learning_rate": 5.823818003160747e-06, "loss": 0.0016, "step": 295760 }, { "epoch": 71.05, "learning_rate": 5.821716547411055e-06, "loss": 0.0021, "step": 295770 }, { "epoch": 71.05, "learning_rate": 5.8196154474351835e-06, "loss": 0.0009, "step": 295780 }, { "epoch": 71.05, "learning_rate": 5.81751470325006e-06, "loss": 0.0011, "step": 295790 }, { "epoch": 71.05, "learning_rate": 5.815414314872575e-06, "loss": 0.0011, "step": 295800 }, { "epoch": 71.05, "learning_rate": 5.813314282319665e-06, "loss": 0.0017, "step": 295810 }, { "epoch": 71.06, "learning_rate": 5.811214605608234e-06, "loss": 0.0011, "step": 295820 }, { "epoch": 71.06, "learning_rate": 5.809115284755201e-06, "loss": 0.0009, "step": 295830 }, { "epoch": 71.06, "learning_rate": 5.8070163197774476e-06, "loss": 0.0011, "step": 295840 }, { "epoch": 71.06, "learning_rate": 5.804917710691904e-06, "loss": 0.001, "step": 295850 }, { "epoch": 71.07, "learning_rate": 5.802819457515457e-06, "loss": 0.0011, "step": 295860 }, { "epoch": 71.07, "learning_rate": 5.800721560265004e-06, "loss": 0.0017, "step": 295870 }, { "epoch": 71.07, "learning_rate": 5.798624018957449e-06, "loss": 0.0009, "step": 295880 }, { "epoch": 71.07, "learning_rate": 5.796526833609672e-06, "loss": 0.0012, "step": 295890 }, { "epoch": 71.07, "learning_rate": 5.794430004238566e-06, "loss": 0.0095, "step": 295900 }, { "epoch": 71.08, "learning_rate": 5.7923335308610106e-06, "loss": 0.0012, "step": 295910 }, { "epoch": 71.08, "learning_rate": 5.790237413493909e-06, "loss": 0.0011, "step": 295920 }, { "epoch": 71.08, "learning_rate": 5.788141652154138e-06, "loss": 0.0011, "step": 295930 }, { "epoch": 71.08, "learning_rate": 5.786046246858545e-06, "loss": 0.001, "step": 295940 }, { "epoch": 71.09, "learning_rate": 5.783951197624032e-06, "loss": 0.0019, "step": 295950 }, { "epoch": 71.09, "learning_rate": 5.78185650446747e-06, "loss": 0.0013, "step": 295960 }, { "epoch": 71.09, "learning_rate": 5.779762167405723e-06, "loss": 0.0015, "step": 295970 }, { "epoch": 71.09, "learning_rate": 5.777668186455648e-06, "loss": 0.0014, "step": 295980 }, { "epoch": 71.1, "learning_rate": 5.7755745616341225e-06, "loss": 0.0012, "step": 295990 }, { "epoch": 71.1, "learning_rate": 5.7734812929579995e-06, "loss": 0.0025, "step": 296000 }, { "epoch": 71.1, "learning_rate": 5.771388380444132e-06, "loss": 0.0086, "step": 296010 }, { "epoch": 71.1, "learning_rate": 5.769295824109394e-06, "loss": 0.0009, "step": 296020 }, { "epoch": 71.1, "learning_rate": 5.767203623970613e-06, "loss": 0.0012, "step": 296030 }, { "epoch": 71.11, "learning_rate": 5.765111780044652e-06, "loss": 0.0012, "step": 296040 }, { "epoch": 71.11, "learning_rate": 5.763020292348342e-06, "loss": 0.001, "step": 296050 }, { "epoch": 71.11, "learning_rate": 5.760929160898543e-06, "loss": 0.001, "step": 296060 }, { "epoch": 71.11, "learning_rate": 5.758838385712106e-06, "loss": 0.0012, "step": 296070 }, { "epoch": 71.12, "learning_rate": 5.756747966805826e-06, "loss": 0.0011, "step": 296080 }, { "epoch": 71.12, "learning_rate": 5.75465790419657e-06, "loss": 0.001, "step": 296090 }, { "epoch": 71.12, "learning_rate": 5.7525681979011706e-06, "loss": 0.0009, "step": 296100 }, { "epoch": 71.12, "learning_rate": 5.750478847936441e-06, "loss": 0.0009, "step": 296110 }, { "epoch": 71.12, "learning_rate": 5.748389854319219e-06, "loss": 0.0009, "step": 296120 }, { "epoch": 71.13, "learning_rate": 5.7463012170663185e-06, "loss": 0.0009, "step": 296130 }, { "epoch": 71.13, "learning_rate": 5.7442129361945706e-06, "loss": 0.0011, "step": 296140 }, { "epoch": 71.13, "learning_rate": 5.742125011720767e-06, "loss": 0.0011, "step": 296150 }, { "epoch": 71.13, "learning_rate": 5.740037443661766e-06, "loss": 0.0014, "step": 296160 }, { "epoch": 71.14, "learning_rate": 5.7379502320343445e-06, "loss": 0.001, "step": 296170 }, { "epoch": 71.14, "learning_rate": 5.735863376855311e-06, "loss": 0.0011, "step": 296180 }, { "epoch": 71.14, "learning_rate": 5.7337768781414895e-06, "loss": 0.001, "step": 296190 }, { "epoch": 71.14, "learning_rate": 5.731690735909672e-06, "loss": 0.0012, "step": 296200 }, { "epoch": 71.15, "learning_rate": 5.7296049501766645e-06, "loss": 0.0012, "step": 296210 }, { "epoch": 71.15, "learning_rate": 5.727519520959257e-06, "loss": 0.0011, "step": 296220 }, { "epoch": 71.15, "learning_rate": 5.725434448274247e-06, "loss": 0.0011, "step": 296230 }, { "epoch": 71.15, "learning_rate": 5.7233497321384275e-06, "loss": 0.0057, "step": 296240 }, { "epoch": 71.15, "learning_rate": 5.721265372568574e-06, "loss": 0.0015, "step": 296250 }, { "epoch": 71.16, "learning_rate": 5.719181369581506e-06, "loss": 0.0009, "step": 296260 }, { "epoch": 71.16, "learning_rate": 5.717097723193971e-06, "loss": 0.001, "step": 296270 }, { "epoch": 71.16, "learning_rate": 5.7150144334227665e-06, "loss": 0.0012, "step": 296280 }, { "epoch": 71.16, "learning_rate": 5.712931500284647e-06, "loss": 0.0013, "step": 296290 }, { "epoch": 71.17, "learning_rate": 5.7108489237964305e-06, "loss": 0.001, "step": 296300 }, { "epoch": 71.17, "learning_rate": 5.70876670397485e-06, "loss": 0.0012, "step": 296310 }, { "epoch": 71.17, "learning_rate": 5.706684840836674e-06, "loss": 0.001, "step": 296320 }, { "epoch": 71.17, "learning_rate": 5.704603334398695e-06, "loss": 0.001, "step": 296330 }, { "epoch": 71.18, "learning_rate": 5.702522184677655e-06, "loss": 0.002, "step": 296340 }, { "epoch": 71.18, "learning_rate": 5.7004413916903255e-06, "loss": 0.0013, "step": 296350 }, { "epoch": 71.18, "learning_rate": 5.698360955453453e-06, "loss": 0.001, "step": 296360 }, { "epoch": 71.18, "learning_rate": 5.696280875983795e-06, "loss": 0.0012, "step": 296370 }, { "epoch": 71.18, "learning_rate": 5.694201153298106e-06, "loss": 0.001, "step": 296380 }, { "epoch": 71.19, "learning_rate": 5.692121787413124e-06, "loss": 0.001, "step": 296390 }, { "epoch": 71.19, "learning_rate": 5.690042778345617e-06, "loss": 0.0026, "step": 296400 }, { "epoch": 71.19, "learning_rate": 5.687964126112305e-06, "loss": 0.0009, "step": 296410 }, { "epoch": 71.19, "learning_rate": 5.685885830729931e-06, "loss": 0.0013, "step": 296420 }, { "epoch": 71.2, "learning_rate": 5.683807892215237e-06, "loss": 0.0009, "step": 296430 }, { "epoch": 71.2, "learning_rate": 5.681730310584965e-06, "loss": 0.001, "step": 296440 }, { "epoch": 71.2, "learning_rate": 5.67965308585584e-06, "loss": 0.001, "step": 296450 }, { "epoch": 71.2, "learning_rate": 5.677576218044572e-06, "loss": 0.001, "step": 296460 }, { "epoch": 71.2, "learning_rate": 5.675499707167914e-06, "loss": 0.001, "step": 296470 }, { "epoch": 71.21, "learning_rate": 5.673423553242568e-06, "loss": 0.0012, "step": 296480 }, { "epoch": 71.21, "learning_rate": 5.6713477562852665e-06, "loss": 0.0011, "step": 296490 }, { "epoch": 71.21, "learning_rate": 5.669272316312724e-06, "loss": 0.0012, "step": 296500 }, { "epoch": 71.21, "learning_rate": 5.6671972333416475e-06, "loss": 0.0008, "step": 296510 }, { "epoch": 71.22, "learning_rate": 5.665122507388759e-06, "loss": 0.0012, "step": 296520 }, { "epoch": 71.22, "learning_rate": 5.663048138470744e-06, "loss": 0.0014, "step": 296530 }, { "epoch": 71.22, "learning_rate": 5.660974126604346e-06, "loss": 0.0011, "step": 296540 }, { "epoch": 71.22, "learning_rate": 5.658900471806228e-06, "loss": 0.0011, "step": 296550 }, { "epoch": 71.23, "learning_rate": 5.6568271740931045e-06, "loss": 0.0008, "step": 296560 }, { "epoch": 71.23, "learning_rate": 5.65475423348168e-06, "loss": 0.001, "step": 296570 }, { "epoch": 71.23, "learning_rate": 5.652681649988639e-06, "loss": 0.0013, "step": 296580 }, { "epoch": 71.23, "learning_rate": 5.650609423630682e-06, "loss": 0.0009, "step": 296590 }, { "epoch": 71.23, "learning_rate": 5.648537554424488e-06, "loss": 0.0011, "step": 296600 }, { "epoch": 71.24, "learning_rate": 5.646466042386739e-06, "loss": 0.0013, "step": 296610 }, { "epoch": 71.24, "learning_rate": 5.644394887534127e-06, "loss": 0.0009, "step": 296620 }, { "epoch": 71.24, "learning_rate": 5.642324089883327e-06, "loss": 0.001, "step": 296630 }, { "epoch": 71.24, "learning_rate": 5.640253649451016e-06, "loss": 0.0019, "step": 296640 }, { "epoch": 71.25, "learning_rate": 5.638183566253863e-06, "loss": 0.001, "step": 296650 }, { "epoch": 71.25, "learning_rate": 5.636113840308532e-06, "loss": 0.001, "step": 296660 }, { "epoch": 71.25, "learning_rate": 5.634044471631716e-06, "loss": 0.0011, "step": 296670 }, { "epoch": 71.25, "learning_rate": 5.6319754602400686e-06, "loss": 0.0011, "step": 296680 }, { "epoch": 71.26, "learning_rate": 5.629906806150242e-06, "loss": 0.0014, "step": 296690 }, { "epoch": 71.26, "learning_rate": 5.627838509378891e-06, "loss": 0.0009, "step": 296700 }, { "epoch": 71.26, "learning_rate": 5.625770569942696e-06, "loss": 0.0012, "step": 296710 }, { "epoch": 71.26, "learning_rate": 5.6237029878582925e-06, "loss": 0.001, "step": 296720 }, { "epoch": 71.26, "learning_rate": 5.621635763142335e-06, "loss": 0.001, "step": 296730 }, { "epoch": 71.27, "learning_rate": 5.619568895811473e-06, "loss": 0.0013, "step": 296740 }, { "epoch": 71.27, "learning_rate": 5.6175023858823505e-06, "loss": 0.0035, "step": 296750 }, { "epoch": 71.27, "learning_rate": 5.615436233371607e-06, "loss": 0.001, "step": 296760 }, { "epoch": 71.27, "learning_rate": 5.613370438295873e-06, "loss": 0.001, "step": 296770 }, { "epoch": 71.28, "learning_rate": 5.611305000671813e-06, "loss": 0.0011, "step": 296780 }, { "epoch": 71.28, "learning_rate": 5.609239920516035e-06, "loss": 0.0015, "step": 296790 }, { "epoch": 71.28, "learning_rate": 5.607175197845166e-06, "loss": 0.0011, "step": 296800 }, { "epoch": 71.28, "learning_rate": 5.605110832675858e-06, "loss": 0.001, "step": 296810 }, { "epoch": 71.28, "learning_rate": 5.603046825024727e-06, "loss": 0.0009, "step": 296820 }, { "epoch": 71.29, "learning_rate": 5.6009831749083696e-06, "loss": 0.0012, "step": 296830 }, { "epoch": 71.29, "learning_rate": 5.598919882343434e-06, "loss": 0.001, "step": 296840 }, { "epoch": 71.29, "learning_rate": 5.596856947346529e-06, "loss": 0.001, "step": 296850 }, { "epoch": 71.29, "learning_rate": 5.594794369934258e-06, "loss": 0.0011, "step": 296860 }, { "epoch": 71.3, "learning_rate": 5.592732150123247e-06, "loss": 0.0028, "step": 296870 }, { "epoch": 71.3, "learning_rate": 5.590670287930095e-06, "loss": 0.0009, "step": 296880 }, { "epoch": 71.3, "learning_rate": 5.5886087833714014e-06, "loss": 0.0012, "step": 296890 }, { "epoch": 71.3, "learning_rate": 5.586547636463774e-06, "loss": 0.0017, "step": 296900 }, { "epoch": 71.31, "learning_rate": 5.584486847223796e-06, "loss": 0.0023, "step": 296910 }, { "epoch": 71.31, "learning_rate": 5.582426415668107e-06, "loss": 0.0037, "step": 296920 }, { "epoch": 71.31, "learning_rate": 5.580366341813254e-06, "loss": 0.0011, "step": 296930 }, { "epoch": 71.31, "learning_rate": 5.578306625675833e-06, "loss": 0.0011, "step": 296940 }, { "epoch": 71.31, "learning_rate": 5.5762472672724555e-06, "loss": 0.001, "step": 296950 }, { "epoch": 71.32, "learning_rate": 5.574188266619696e-06, "loss": 0.001, "step": 296960 }, { "epoch": 71.32, "learning_rate": 5.572129623734118e-06, "loss": 0.001, "step": 296970 }, { "epoch": 71.32, "learning_rate": 5.570071338632321e-06, "loss": 0.0016, "step": 296980 }, { "epoch": 71.32, "learning_rate": 5.568013411330869e-06, "loss": 0.001, "step": 296990 }, { "epoch": 71.33, "learning_rate": 5.565955841846343e-06, "loss": 0.0017, "step": 297000 }, { "epoch": 71.33, "learning_rate": 5.563898630195314e-06, "loss": 0.0059, "step": 297010 }, { "epoch": 71.33, "learning_rate": 5.5618417763943385e-06, "loss": 0.001, "step": 297020 }, { "epoch": 71.33, "learning_rate": 5.559785280459989e-06, "loss": 0.0011, "step": 297030 }, { "epoch": 71.34, "learning_rate": 5.557729142408807e-06, "loss": 0.0009, "step": 297040 }, { "epoch": 71.34, "learning_rate": 5.555673362257385e-06, "loss": 0.0011, "step": 297050 }, { "epoch": 71.34, "learning_rate": 5.553617940022271e-06, "loss": 0.0028, "step": 297060 }, { "epoch": 71.34, "learning_rate": 5.551562875719984e-06, "loss": 0.001, "step": 297070 }, { "epoch": 71.34, "learning_rate": 5.549508169367113e-06, "loss": 0.0011, "step": 297080 }, { "epoch": 71.35, "learning_rate": 5.547453820980186e-06, "loss": 0.001, "step": 297090 }, { "epoch": 71.35, "learning_rate": 5.545399830575754e-06, "loss": 0.001, "step": 297100 }, { "epoch": 71.35, "learning_rate": 5.543346198170352e-06, "loss": 0.0012, "step": 297110 }, { "epoch": 71.35, "learning_rate": 5.541292923780517e-06, "loss": 0.0009, "step": 297120 }, { "epoch": 71.36, "learning_rate": 5.539240007422792e-06, "loss": 0.0011, "step": 297130 }, { "epoch": 71.36, "learning_rate": 5.537187449113706e-06, "loss": 0.0029, "step": 297140 }, { "epoch": 71.36, "learning_rate": 5.535135248869783e-06, "loss": 0.0012, "step": 297150 }, { "epoch": 71.36, "learning_rate": 5.533083406707562e-06, "loss": 0.0012, "step": 297160 }, { "epoch": 71.36, "learning_rate": 5.531031922643553e-06, "loss": 0.0008, "step": 297170 }, { "epoch": 71.37, "learning_rate": 5.5289807966942775e-06, "loss": 0.0019, "step": 297180 }, { "epoch": 71.37, "learning_rate": 5.5269300288762645e-06, "loss": 0.0011, "step": 297190 }, { "epoch": 71.37, "learning_rate": 5.524879619206042e-06, "loss": 0.001, "step": 297200 }, { "epoch": 71.37, "learning_rate": 5.522829567700077e-06, "loss": 0.0011, "step": 297210 }, { "epoch": 71.38, "learning_rate": 5.520779874374915e-06, "loss": 0.0011, "step": 297220 }, { "epoch": 71.38, "learning_rate": 5.518730539247058e-06, "loss": 0.001, "step": 297230 }, { "epoch": 71.38, "learning_rate": 5.516681562333004e-06, "loss": 0.0009, "step": 297240 }, { "epoch": 71.38, "learning_rate": 5.514632943649256e-06, "loss": 0.0009, "step": 297250 }, { "epoch": 71.39, "learning_rate": 5.512584683212307e-06, "loss": 0.0011, "step": 297260 }, { "epoch": 71.39, "learning_rate": 5.5105367810386555e-06, "loss": 0.0013, "step": 297270 }, { "epoch": 71.39, "learning_rate": 5.508489237144787e-06, "loss": 0.0012, "step": 297280 }, { "epoch": 71.39, "learning_rate": 5.506442051547217e-06, "loss": 0.001, "step": 297290 }, { "epoch": 71.39, "learning_rate": 5.504395224262399e-06, "loss": 0.001, "step": 297300 }, { "epoch": 71.4, "learning_rate": 5.50234875530683e-06, "loss": 0.001, "step": 297310 }, { "epoch": 71.4, "learning_rate": 5.500302644696981e-06, "loss": 0.0018, "step": 297320 }, { "epoch": 71.4, "learning_rate": 5.498256892449344e-06, "loss": 0.0015, "step": 297330 }, { "epoch": 71.4, "learning_rate": 5.4962114985804005e-06, "loss": 0.001, "step": 297340 }, { "epoch": 71.41, "learning_rate": 5.494166463106592e-06, "loss": 0.0015, "step": 297350 }, { "epoch": 71.41, "learning_rate": 5.492121786044413e-06, "loss": 0.001, "step": 297360 }, { "epoch": 71.41, "learning_rate": 5.490077467410326e-06, "loss": 0.0013, "step": 297370 }, { "epoch": 71.41, "learning_rate": 5.488033507220785e-06, "loss": 0.0011, "step": 297380 }, { "epoch": 71.42, "learning_rate": 5.4859899054922614e-06, "loss": 0.008, "step": 297390 }, { "epoch": 71.42, "learning_rate": 5.483946662241201e-06, "loss": 0.0012, "step": 297400 }, { "epoch": 71.42, "learning_rate": 5.481903777484065e-06, "loss": 0.0011, "step": 297410 }, { "epoch": 71.42, "learning_rate": 5.4798612512372946e-06, "loss": 0.0009, "step": 297420 }, { "epoch": 71.42, "learning_rate": 5.47781908351736e-06, "loss": 0.0017, "step": 297430 }, { "epoch": 71.43, "learning_rate": 5.475777274340704e-06, "loss": 0.0012, "step": 297440 }, { "epoch": 71.43, "learning_rate": 5.473735823723736e-06, "loss": 0.002, "step": 297450 }, { "epoch": 71.43, "learning_rate": 5.471694731682936e-06, "loss": 0.001, "step": 297460 }, { "epoch": 71.43, "learning_rate": 5.469653998234725e-06, "loss": 0.0047, "step": 297470 }, { "epoch": 71.44, "learning_rate": 5.467613623395535e-06, "loss": 0.0011, "step": 297480 }, { "epoch": 71.44, "learning_rate": 5.465573607181807e-06, "loss": 0.0011, "step": 297490 }, { "epoch": 71.44, "learning_rate": 5.463533949609956e-06, "loss": 0.0014, "step": 297500 }, { "epoch": 71.44, "learning_rate": 5.4614946506964195e-06, "loss": 0.0013, "step": 297510 }, { "epoch": 71.44, "learning_rate": 5.459455710457601e-06, "loss": 0.0016, "step": 297520 }, { "epoch": 71.45, "learning_rate": 5.457417128909958e-06, "loss": 0.001, "step": 297530 }, { "epoch": 71.45, "learning_rate": 5.455378906069875e-06, "loss": 0.0011, "step": 297540 }, { "epoch": 71.45, "learning_rate": 5.453341041953774e-06, "loss": 0.0015, "step": 297550 }, { "epoch": 71.45, "learning_rate": 5.451303536578062e-06, "loss": 0.0013, "step": 297560 }, { "epoch": 71.46, "learning_rate": 5.449266389959157e-06, "loss": 0.004, "step": 297570 }, { "epoch": 71.46, "learning_rate": 5.447229602113474e-06, "loss": 0.001, "step": 297580 }, { "epoch": 71.46, "learning_rate": 5.445193173057378e-06, "loss": 0.0012, "step": 297590 }, { "epoch": 71.46, "learning_rate": 5.443157102807306e-06, "loss": 0.0021, "step": 297600 }, { "epoch": 71.47, "learning_rate": 5.441121391379639e-06, "loss": 0.001, "step": 297610 }, { "epoch": 71.47, "learning_rate": 5.439086038790775e-06, "loss": 0.001, "step": 297620 }, { "epoch": 71.47, "learning_rate": 5.437051045057101e-06, "loss": 0.001, "step": 297630 }, { "epoch": 71.47, "learning_rate": 5.4350164101950095e-06, "loss": 0.0009, "step": 297640 }, { "epoch": 71.47, "learning_rate": 5.432982134220882e-06, "loss": 0.0012, "step": 297650 }, { "epoch": 71.48, "learning_rate": 5.430948217151094e-06, "loss": 0.0016, "step": 297660 }, { "epoch": 71.48, "learning_rate": 5.428914659002055e-06, "loss": 0.001, "step": 297670 }, { "epoch": 71.48, "learning_rate": 5.426881459790107e-06, "loss": 0.0011, "step": 297680 }, { "epoch": 71.48, "learning_rate": 5.424848619531625e-06, "loss": 0.0011, "step": 297690 }, { "epoch": 71.49, "learning_rate": 5.4228161382429975e-06, "loss": 0.0009, "step": 297700 }, { "epoch": 71.49, "learning_rate": 5.4207840159405945e-06, "loss": 0.0013, "step": 297710 }, { "epoch": 71.49, "learning_rate": 5.418752252640768e-06, "loss": 0.0011, "step": 297720 }, { "epoch": 71.49, "learning_rate": 5.416720848359885e-06, "loss": 0.0017, "step": 297730 }, { "epoch": 71.5, "learning_rate": 5.414689803114303e-06, "loss": 0.0009, "step": 297740 }, { "epoch": 71.5, "learning_rate": 5.412659116920382e-06, "loss": 0.0009, "step": 297750 }, { "epoch": 71.5, "learning_rate": 5.41062878979447e-06, "loss": 0.0011, "step": 297760 }, { "epoch": 71.5, "learning_rate": 5.408598821752919e-06, "loss": 0.0039, "step": 297770 }, { "epoch": 71.5, "learning_rate": 5.406569212812079e-06, "loss": 0.0012, "step": 297780 }, { "epoch": 71.51, "learning_rate": 5.404539962988297e-06, "loss": 0.0011, "step": 297790 }, { "epoch": 71.51, "learning_rate": 5.4025110722979e-06, "loss": 0.0011, "step": 297800 }, { "epoch": 71.51, "learning_rate": 5.400482540757257e-06, "loss": 0.0009, "step": 297810 }, { "epoch": 71.51, "learning_rate": 5.398454368382677e-06, "loss": 0.0033, "step": 297820 }, { "epoch": 71.52, "learning_rate": 5.396426555190492e-06, "loss": 0.0011, "step": 297830 }, { "epoch": 71.52, "learning_rate": 5.394399101197051e-06, "loss": 0.0013, "step": 297840 }, { "epoch": 71.52, "learning_rate": 5.392372006418672e-06, "loss": 0.0008, "step": 297850 }, { "epoch": 71.52, "learning_rate": 5.390345270871677e-06, "loss": 0.0013, "step": 297860 }, { "epoch": 71.52, "learning_rate": 5.388318894572392e-06, "loss": 0.001, "step": 297870 }, { "epoch": 71.53, "learning_rate": 5.386292877537136e-06, "loss": 0.0015, "step": 297880 }, { "epoch": 71.53, "learning_rate": 5.384267219782224e-06, "loss": 0.0011, "step": 297890 }, { "epoch": 71.53, "learning_rate": 5.382241921323955e-06, "loss": 0.0015, "step": 297900 }, { "epoch": 71.53, "learning_rate": 5.380216982178671e-06, "loss": 0.0011, "step": 297910 }, { "epoch": 71.54, "learning_rate": 5.378192402362653e-06, "loss": 0.0017, "step": 297920 }, { "epoch": 71.54, "learning_rate": 5.376168181892199e-06, "loss": 0.0012, "step": 297930 }, { "epoch": 71.54, "learning_rate": 5.374144320783631e-06, "loss": 0.0009, "step": 297940 }, { "epoch": 71.54, "learning_rate": 5.3721208190532555e-06, "loss": 0.0021, "step": 297950 }, { "epoch": 71.55, "learning_rate": 5.37009767671734e-06, "loss": 0.0011, "step": 297960 }, { "epoch": 71.55, "learning_rate": 5.36807489379218e-06, "loss": 0.001, "step": 297970 }, { "epoch": 71.55, "learning_rate": 5.3660524702940804e-06, "loss": 0.0012, "step": 297980 }, { "epoch": 71.55, "learning_rate": 5.3640304062393285e-06, "loss": 0.001, "step": 297990 }, { "epoch": 71.55, "learning_rate": 5.3620087016442e-06, "loss": 0.0013, "step": 298000 }, { "epoch": 71.56, "learning_rate": 5.3599873565249756e-06, "loss": 0.0012, "step": 298010 }, { "epoch": 71.56, "learning_rate": 5.357966370897938e-06, "loss": 0.0015, "step": 298020 }, { "epoch": 71.56, "learning_rate": 5.3559457447793615e-06, "loss": 0.0015, "step": 298030 }, { "epoch": 71.56, "learning_rate": 5.353925478185506e-06, "loss": 0.0016, "step": 298040 }, { "epoch": 71.57, "learning_rate": 5.35190557113267e-06, "loss": 0.0009, "step": 298050 }, { "epoch": 71.57, "learning_rate": 5.349886023637096e-06, "loss": 0.0014, "step": 298060 }, { "epoch": 71.57, "learning_rate": 5.347866835715043e-06, "loss": 0.0015, "step": 298070 }, { "epoch": 71.57, "learning_rate": 5.345848007382792e-06, "loss": 0.0025, "step": 298080 }, { "epoch": 71.58, "learning_rate": 5.343829538656592e-06, "loss": 0.0012, "step": 298090 }, { "epoch": 71.58, "learning_rate": 5.341811429552701e-06, "loss": 0.001, "step": 298100 }, { "epoch": 71.58, "learning_rate": 5.339793680087368e-06, "loss": 0.006, "step": 298110 }, { "epoch": 71.58, "learning_rate": 5.337776290276836e-06, "loss": 0.0012, "step": 298120 }, { "epoch": 71.58, "learning_rate": 5.335759260137363e-06, "loss": 0.0011, "step": 298130 }, { "epoch": 71.59, "learning_rate": 5.333742589685187e-06, "loss": 0.0012, "step": 298140 }, { "epoch": 71.59, "learning_rate": 5.33172627893655e-06, "loss": 0.0011, "step": 298150 }, { "epoch": 71.59, "learning_rate": 5.329710327907683e-06, "loss": 0.0009, "step": 298160 }, { "epoch": 71.59, "learning_rate": 5.327694736614819e-06, "loss": 0.0013, "step": 298170 }, { "epoch": 71.6, "learning_rate": 5.3256795050742045e-06, "loss": 0.0011, "step": 298180 }, { "epoch": 71.6, "learning_rate": 5.323664633302073e-06, "loss": 0.0013, "step": 298190 }, { "epoch": 71.6, "learning_rate": 5.321650121314625e-06, "loss": 0.0022, "step": 298200 }, { "epoch": 71.6, "learning_rate": 5.319635969128089e-06, "loss": 0.0011, "step": 298210 }, { "epoch": 71.6, "learning_rate": 5.317622176758702e-06, "loss": 0.001, "step": 298220 }, { "epoch": 71.61, "learning_rate": 5.315608744222677e-06, "loss": 0.0011, "step": 298230 }, { "epoch": 71.61, "learning_rate": 5.3135956715362205e-06, "loss": 0.001, "step": 298240 }, { "epoch": 71.61, "learning_rate": 5.311582958715544e-06, "loss": 0.0009, "step": 298250 }, { "epoch": 71.61, "learning_rate": 5.309570605776865e-06, "loss": 0.001, "step": 298260 }, { "epoch": 71.62, "learning_rate": 5.30755861273638e-06, "loss": 0.0009, "step": 298270 }, { "epoch": 71.62, "learning_rate": 5.305546979610288e-06, "loss": 0.001, "step": 298280 }, { "epoch": 71.62, "learning_rate": 5.303535706414814e-06, "loss": 0.001, "step": 298290 }, { "epoch": 71.62, "learning_rate": 5.301524793166129e-06, "loss": 0.0008, "step": 298300 }, { "epoch": 71.63, "learning_rate": 5.299514239880427e-06, "loss": 0.0012, "step": 298310 }, { "epoch": 71.63, "learning_rate": 5.29750404657392e-06, "loss": 0.001, "step": 298320 }, { "epoch": 71.63, "learning_rate": 5.295494213262792e-06, "loss": 0.001, "step": 298330 }, { "epoch": 71.63, "learning_rate": 5.2934847399632e-06, "loss": 0.0011, "step": 298340 }, { "epoch": 71.63, "learning_rate": 5.2914756266913555e-06, "loss": 0.0011, "step": 298350 }, { "epoch": 71.64, "learning_rate": 5.289466873463433e-06, "loss": 0.0012, "step": 298360 }, { "epoch": 71.64, "learning_rate": 5.287458480295609e-06, "loss": 0.001, "step": 298370 }, { "epoch": 71.64, "learning_rate": 5.2854504472040485e-06, "loss": 0.0011, "step": 298380 }, { "epoch": 71.64, "learning_rate": 5.283442774204933e-06, "loss": 0.0009, "step": 298390 }, { "epoch": 71.65, "learning_rate": 5.281435461314427e-06, "loss": 0.0013, "step": 298400 }, { "epoch": 71.65, "learning_rate": 5.279428508548695e-06, "loss": 0.001, "step": 298410 }, { "epoch": 71.65, "learning_rate": 5.2774219159238856e-06, "loss": 0.0015, "step": 298420 }, { "epoch": 71.65, "learning_rate": 5.275415683456197e-06, "loss": 0.0017, "step": 298430 }, { "epoch": 71.66, "learning_rate": 5.2734098111617506e-06, "loss": 0.0011, "step": 298440 }, { "epoch": 71.66, "learning_rate": 5.271404299056692e-06, "loss": 0.0012, "step": 298450 }, { "epoch": 71.66, "learning_rate": 5.269399147157205e-06, "loss": 0.0027, "step": 298460 }, { "epoch": 71.66, "learning_rate": 5.267394355479432e-06, "loss": 0.0022, "step": 298470 }, { "epoch": 71.66, "learning_rate": 5.265389924039494e-06, "loss": 0.0012, "step": 298480 }, { "epoch": 71.67, "learning_rate": 5.263385852853548e-06, "loss": 0.001, "step": 298490 }, { "epoch": 71.67, "learning_rate": 5.261382141937732e-06, "loss": 0.001, "step": 298500 }, { "epoch": 71.67, "learning_rate": 5.259378791308189e-06, "loss": 0.0009, "step": 298510 }, { "epoch": 71.67, "learning_rate": 5.2573758009810405e-06, "loss": 0.0011, "step": 298520 }, { "epoch": 71.68, "learning_rate": 5.255373170972422e-06, "loss": 0.0013, "step": 298530 }, { "epoch": 71.68, "learning_rate": 5.25337090129846e-06, "loss": 0.0012, "step": 298540 }, { "epoch": 71.68, "learning_rate": 5.2513689919752755e-06, "loss": 0.0011, "step": 298550 }, { "epoch": 71.68, "learning_rate": 5.249367443018999e-06, "loss": 0.0011, "step": 298560 }, { "epoch": 71.68, "learning_rate": 5.247366254445757e-06, "loss": 0.001, "step": 298570 }, { "epoch": 71.69, "learning_rate": 5.245365426271631e-06, "loss": 0.0018, "step": 298580 }, { "epoch": 71.69, "learning_rate": 5.243364958512764e-06, "loss": 0.0012, "step": 298590 }, { "epoch": 71.69, "learning_rate": 5.241364851185266e-06, "loss": 0.001, "step": 298600 }, { "epoch": 71.69, "learning_rate": 5.239365104305227e-06, "loss": 0.0011, "step": 298610 }, { "epoch": 71.7, "learning_rate": 5.237365717888765e-06, "loss": 0.001, "step": 298620 }, { "epoch": 71.7, "learning_rate": 5.235366691951976e-06, "loss": 0.0013, "step": 298630 }, { "epoch": 71.7, "learning_rate": 5.2333680265109595e-06, "loss": 0.0013, "step": 298640 }, { "epoch": 71.7, "learning_rate": 5.2313697215818136e-06, "loss": 0.001, "step": 298650 }, { "epoch": 71.71, "learning_rate": 5.229371777180625e-06, "loss": 0.0024, "step": 298660 }, { "epoch": 71.71, "learning_rate": 5.227374193323486e-06, "loss": 0.0011, "step": 298670 }, { "epoch": 71.71, "learning_rate": 5.225376970026485e-06, "loss": 0.0011, "step": 298680 }, { "epoch": 71.71, "learning_rate": 5.223380107305692e-06, "loss": 0.009, "step": 298690 }, { "epoch": 71.71, "learning_rate": 5.221383605177216e-06, "loss": 0.0011, "step": 298700 }, { "epoch": 71.72, "learning_rate": 5.219387463657127e-06, "loss": 0.0012, "step": 298710 }, { "epoch": 71.72, "learning_rate": 5.2173916827614686e-06, "loss": 0.001, "step": 298720 }, { "epoch": 71.72, "learning_rate": 5.215396262506356e-06, "loss": 0.0012, "step": 298730 }, { "epoch": 71.72, "learning_rate": 5.213401202907836e-06, "loss": 0.0012, "step": 298740 }, { "epoch": 71.73, "learning_rate": 5.211406503981981e-06, "loss": 0.0015, "step": 298750 }, { "epoch": 71.73, "learning_rate": 5.209412165744848e-06, "loss": 0.0008, "step": 298760 }, { "epoch": 71.73, "learning_rate": 5.207418188212504e-06, "loss": 0.001, "step": 298770 }, { "epoch": 71.73, "learning_rate": 5.205424571401008e-06, "loss": 0.0019, "step": 298780 }, { "epoch": 71.74, "learning_rate": 5.203431315326401e-06, "loss": 0.0009, "step": 298790 }, { "epoch": 71.74, "learning_rate": 5.201438420004767e-06, "loss": 0.0011, "step": 298800 }, { "epoch": 71.74, "learning_rate": 5.199445885452126e-06, "loss": 0.0009, "step": 298810 }, { "epoch": 71.74, "learning_rate": 5.19745371168453e-06, "loss": 0.0013, "step": 298820 }, { "epoch": 71.74, "learning_rate": 5.195461898718012e-06, "loss": 0.0017, "step": 298830 }, { "epoch": 71.75, "learning_rate": 5.193470446568638e-06, "loss": 0.0011, "step": 298840 }, { "epoch": 71.75, "learning_rate": 5.191479355252443e-06, "loss": 0.0015, "step": 298850 }, { "epoch": 71.75, "learning_rate": 5.189488624785433e-06, "loss": 0.0014, "step": 298860 }, { "epoch": 71.75, "learning_rate": 5.187498255183665e-06, "loss": 0.001, "step": 298870 }, { "epoch": 71.76, "learning_rate": 5.185508246463161e-06, "loss": 0.0011, "step": 298880 }, { "epoch": 71.76, "learning_rate": 5.183518598639941e-06, "loss": 0.001, "step": 298890 }, { "epoch": 71.76, "learning_rate": 5.181529311730038e-06, "loss": 0.0012, "step": 298900 }, { "epoch": 71.76, "learning_rate": 5.179540385749465e-06, "loss": 0.0011, "step": 298910 }, { "epoch": 71.76, "learning_rate": 5.177551820714244e-06, "loss": 0.0011, "step": 298920 }, { "epoch": 71.77, "learning_rate": 5.1755636166403774e-06, "loss": 0.0013, "step": 298930 }, { "epoch": 71.77, "learning_rate": 5.1735757735438926e-06, "loss": 0.002, "step": 298940 }, { "epoch": 71.77, "learning_rate": 5.171588291440799e-06, "loss": 0.0011, "step": 298950 }, { "epoch": 71.77, "learning_rate": 5.169601170347077e-06, "loss": 0.0015, "step": 298960 }, { "epoch": 71.78, "learning_rate": 5.167614410278754e-06, "loss": 0.0011, "step": 298970 }, { "epoch": 71.78, "learning_rate": 5.165628011251821e-06, "loss": 0.0012, "step": 298980 }, { "epoch": 71.78, "learning_rate": 5.163641973282279e-06, "loss": 0.0009, "step": 298990 }, { "epoch": 71.78, "learning_rate": 5.161656296386114e-06, "loss": 0.0011, "step": 299000 }, { "epoch": 71.79, "learning_rate": 5.159670980579323e-06, "loss": 0.0012, "step": 299010 }, { "epoch": 71.79, "learning_rate": 5.157686025877895e-06, "loss": 0.0013, "step": 299020 }, { "epoch": 71.79, "learning_rate": 5.1557014322977996e-06, "loss": 0.0034, "step": 299030 }, { "epoch": 71.79, "learning_rate": 5.1537171998550515e-06, "loss": 0.0013, "step": 299040 }, { "epoch": 71.79, "learning_rate": 5.1517333285656e-06, "loss": 0.0012, "step": 299050 }, { "epoch": 71.8, "learning_rate": 5.149749818445432e-06, "loss": 0.0009, "step": 299060 }, { "epoch": 71.8, "learning_rate": 5.147766669510512e-06, "loss": 0.0009, "step": 299070 }, { "epoch": 71.8, "learning_rate": 5.145783881776828e-06, "loss": 0.001, "step": 299080 }, { "epoch": 71.8, "learning_rate": 5.1438014552603445e-06, "loss": 0.0017, "step": 299090 }, { "epoch": 71.81, "learning_rate": 5.14181938997701e-06, "loss": 0.001, "step": 299100 }, { "epoch": 71.81, "learning_rate": 5.1398376859428e-06, "loss": 0.0011, "step": 299110 }, { "epoch": 71.81, "learning_rate": 5.137856343173675e-06, "loss": 0.001, "step": 299120 }, { "epoch": 71.81, "learning_rate": 5.135875361685583e-06, "loss": 0.0011, "step": 299130 }, { "epoch": 71.82, "learning_rate": 5.133894741494477e-06, "loss": 0.001, "step": 299140 }, { "epoch": 71.82, "learning_rate": 5.131914482616318e-06, "loss": 0.0027, "step": 299150 }, { "epoch": 71.82, "learning_rate": 5.129934585067042e-06, "loss": 0.0011, "step": 299160 }, { "epoch": 71.82, "learning_rate": 5.127955048862592e-06, "loss": 0.0035, "step": 299170 }, { "epoch": 71.82, "learning_rate": 5.125975874018929e-06, "loss": 0.0013, "step": 299180 }, { "epoch": 71.83, "learning_rate": 5.123997060551972e-06, "loss": 0.0011, "step": 299190 }, { "epoch": 71.83, "learning_rate": 5.122018608477652e-06, "loss": 0.001, "step": 299200 }, { "epoch": 71.83, "learning_rate": 5.12004051781192e-06, "loss": 0.0012, "step": 299210 }, { "epoch": 71.83, "learning_rate": 5.118062788570699e-06, "loss": 0.0015, "step": 299220 }, { "epoch": 71.84, "learning_rate": 5.1160854207699115e-06, "loss": 0.0011, "step": 299230 }, { "epoch": 71.84, "learning_rate": 5.114108414425489e-06, "loss": 0.0015, "step": 299240 }, { "epoch": 71.84, "learning_rate": 5.112131769553346e-06, "loss": 0.0012, "step": 299250 }, { "epoch": 71.84, "learning_rate": 5.110155486169404e-06, "loss": 0.0013, "step": 299260 }, { "epoch": 71.84, "learning_rate": 5.108179564289578e-06, "loss": 0.001, "step": 299270 }, { "epoch": 71.85, "learning_rate": 5.106204003929777e-06, "loss": 0.0058, "step": 299280 }, { "epoch": 71.85, "learning_rate": 5.104228805105915e-06, "loss": 0.0013, "step": 299290 }, { "epoch": 71.85, "learning_rate": 5.102253967833898e-06, "loss": 0.001, "step": 299300 }, { "epoch": 71.85, "learning_rate": 5.100279492129617e-06, "loss": 0.0015, "step": 299310 }, { "epoch": 71.86, "learning_rate": 5.0983053780090054e-06, "loss": 0.001, "step": 299320 }, { "epoch": 71.86, "learning_rate": 5.096331625487927e-06, "loss": 0.0012, "step": 299330 }, { "epoch": 71.86, "learning_rate": 5.094358234582281e-06, "loss": 0.0009, "step": 299340 }, { "epoch": 71.86, "learning_rate": 5.092385205307975e-06, "loss": 0.0014, "step": 299350 }, { "epoch": 71.87, "learning_rate": 5.090412537680894e-06, "loss": 0.0009, "step": 299360 }, { "epoch": 71.87, "learning_rate": 5.088440231716918e-06, "loss": 0.0009, "step": 299370 }, { "epoch": 71.87, "learning_rate": 5.086468287431934e-06, "loss": 0.0009, "step": 299380 }, { "epoch": 71.87, "learning_rate": 5.084496704841824e-06, "loss": 0.0015, "step": 299390 }, { "epoch": 71.87, "learning_rate": 5.0825254839624635e-06, "loss": 0.0011, "step": 299400 }, { "epoch": 71.88, "learning_rate": 5.080554624809713e-06, "loss": 0.0009, "step": 299410 }, { "epoch": 71.88, "learning_rate": 5.0785841273994824e-06, "loss": 0.0012, "step": 299420 }, { "epoch": 71.88, "learning_rate": 5.076613991747603e-06, "loss": 0.0013, "step": 299430 }, { "epoch": 71.88, "learning_rate": 5.0746442178699395e-06, "loss": 0.0011, "step": 299440 }, { "epoch": 71.89, "learning_rate": 5.0726748057823846e-06, "loss": 0.0015, "step": 299450 }, { "epoch": 71.89, "learning_rate": 5.070705755500787e-06, "loss": 0.0009, "step": 299460 }, { "epoch": 71.89, "learning_rate": 5.068737067040991e-06, "loss": 0.0012, "step": 299470 }, { "epoch": 71.89, "learning_rate": 5.066768740418848e-06, "loss": 0.001, "step": 299480 }, { "epoch": 71.9, "learning_rate": 5.06480077565023e-06, "loss": 0.0013, "step": 299490 }, { "epoch": 71.9, "learning_rate": 5.062833172750975e-06, "loss": 0.001, "step": 299500 }, { "epoch": 71.9, "learning_rate": 5.06086593173693e-06, "loss": 0.0011, "step": 299510 }, { "epoch": 71.9, "learning_rate": 5.058899052623933e-06, "loss": 0.0011, "step": 299520 }, { "epoch": 71.9, "learning_rate": 5.056932535427833e-06, "loss": 0.0011, "step": 299530 }, { "epoch": 71.91, "learning_rate": 5.05496638016445e-06, "loss": 0.001, "step": 299540 }, { "epoch": 71.91, "learning_rate": 5.0530005868496265e-06, "loss": 0.0021, "step": 299550 }, { "epoch": 71.91, "learning_rate": 5.051035155499212e-06, "loss": 0.0014, "step": 299560 }, { "epoch": 71.91, "learning_rate": 5.049070086129004e-06, "loss": 0.0011, "step": 299570 }, { "epoch": 71.92, "learning_rate": 5.047105378754835e-06, "loss": 0.001, "step": 299580 }, { "epoch": 71.92, "learning_rate": 5.0451410333925365e-06, "loss": 0.0018, "step": 299590 }, { "epoch": 71.92, "learning_rate": 5.043177050057929e-06, "loss": 0.0012, "step": 299600 }, { "epoch": 71.92, "learning_rate": 5.0412134287668224e-06, "loss": 0.0014, "step": 299610 }, { "epoch": 71.92, "learning_rate": 5.039250169535031e-06, "loss": 0.0015, "step": 299620 }, { "epoch": 71.93, "learning_rate": 5.037287272378361e-06, "loss": 0.0009, "step": 299630 }, { "epoch": 71.93, "learning_rate": 5.03532473731263e-06, "loss": 0.0012, "step": 299640 }, { "epoch": 71.93, "learning_rate": 5.033362564353633e-06, "loss": 0.001, "step": 299650 }, { "epoch": 71.93, "learning_rate": 5.031400753517174e-06, "loss": 0.0011, "step": 299660 }, { "epoch": 71.94, "learning_rate": 5.029439304819055e-06, "loss": 0.0018, "step": 299670 }, { "epoch": 71.94, "learning_rate": 5.027478218275072e-06, "loss": 0.0046, "step": 299680 }, { "epoch": 71.94, "learning_rate": 5.025517493901005e-06, "loss": 0.001, "step": 299690 }, { "epoch": 71.94, "learning_rate": 5.023557131712675e-06, "loss": 0.0011, "step": 299700 }, { "epoch": 71.95, "learning_rate": 5.021597131725836e-06, "loss": 0.0013, "step": 299710 }, { "epoch": 71.95, "learning_rate": 5.019637493956275e-06, "loss": 0.0009, "step": 299720 }, { "epoch": 71.95, "learning_rate": 5.017678218419797e-06, "loss": 0.003, "step": 299730 }, { "epoch": 72.0, "learning_rate": 5.015719305132166e-06, "loss": 0.0015, "step": 299740 }, { "epoch": 72.0, "learning_rate": 5.013760754109154e-06, "loss": 0.0016, "step": 299750 }, { "epoch": 72.01, "learning_rate": 5.0118025653665416e-06, "loss": 0.0013, "step": 299760 }, { "epoch": 72.01, "learning_rate": 5.009844738920089e-06, "loss": 0.0011, "step": 299770 }, { "epoch": 72.01, "learning_rate": 5.007887274785572e-06, "loss": 0.0015, "step": 299780 }, { "epoch": 72.01, "learning_rate": 5.005930172978751e-06, "loss": 0.0012, "step": 299790 }, { "epoch": 72.01, "learning_rate": 5.003973433515385e-06, "loss": 0.0014, "step": 299800 }, { "epoch": 72.02, "learning_rate": 5.002017056411229e-06, "loss": 0.0029, "step": 299810 }, { "epoch": 72.02, "learning_rate": 5.000061041682036e-06, "loss": 0.0011, "step": 299820 }, { "epoch": 72.02, "learning_rate": 4.998105389343577e-06, "loss": 0.0011, "step": 299830 }, { "epoch": 72.02, "learning_rate": 4.996150099411595e-06, "loss": 0.0013, "step": 299840 }, { "epoch": 72.03, "learning_rate": 4.994195171901805e-06, "loss": 0.0011, "step": 299850 }, { "epoch": 72.03, "learning_rate": 4.99224060682999e-06, "loss": 0.001, "step": 299860 }, { "epoch": 72.03, "learning_rate": 4.990286404211875e-06, "loss": 0.0011, "step": 299870 }, { "epoch": 72.03, "learning_rate": 4.988332564063197e-06, "loss": 0.0011, "step": 299880 }, { "epoch": 72.04, "learning_rate": 4.986379086399689e-06, "loss": 0.0009, "step": 299890 }, { "epoch": 72.04, "learning_rate": 4.984425971237089e-06, "loss": 0.0009, "step": 299900 }, { "epoch": 72.04, "learning_rate": 4.982473218591116e-06, "loss": 0.0012, "step": 299910 }, { "epoch": 72.04, "learning_rate": 4.980520828477509e-06, "loss": 0.0011, "step": 299920 }, { "epoch": 72.04, "learning_rate": 4.978568800911964e-06, "loss": 0.0009, "step": 299930 }, { "epoch": 72.05, "learning_rate": 4.976617135910244e-06, "loss": 0.001, "step": 299940 }, { "epoch": 72.05, "learning_rate": 4.974665833488035e-06, "loss": 0.001, "step": 299950 }, { "epoch": 72.05, "learning_rate": 4.972714893661046e-06, "loss": 0.0015, "step": 299960 }, { "epoch": 72.05, "learning_rate": 4.970764316445009e-06, "loss": 0.0009, "step": 299970 }, { "epoch": 72.06, "learning_rate": 4.9688141018556345e-06, "loss": 0.001, "step": 299980 }, { "epoch": 72.06, "learning_rate": 4.966864249908598e-06, "loss": 0.0011, "step": 299990 }, { "epoch": 72.06, "learning_rate": 4.9649147606196265e-06, "loss": 0.0012, "step": 300000 }, { "epoch": 72.06, "learning_rate": 4.962965634004418e-06, "loss": 0.0011, "step": 300010 }, { "epoch": 72.06, "learning_rate": 4.9610168700786665e-06, "loss": 0.0011, "step": 300020 }, { "epoch": 72.07, "learning_rate": 4.959068468858064e-06, "loss": 0.0012, "step": 300030 }, { "epoch": 72.07, "learning_rate": 4.957120430358298e-06, "loss": 0.0022, "step": 300040 }, { "epoch": 72.07, "learning_rate": 4.955172754595061e-06, "loss": 0.006, "step": 300050 }, { "epoch": 72.07, "learning_rate": 4.9532254415840255e-06, "loss": 0.0016, "step": 300060 }, { "epoch": 72.08, "learning_rate": 4.951278491340894e-06, "loss": 0.001, "step": 300070 }, { "epoch": 72.08, "learning_rate": 4.949331903881349e-06, "loss": 0.0012, "step": 300080 }, { "epoch": 72.08, "learning_rate": 4.947385679221034e-06, "loss": 0.0009, "step": 300090 }, { "epoch": 72.08, "learning_rate": 4.945439817375652e-06, "loss": 0.0012, "step": 300100 }, { "epoch": 72.09, "learning_rate": 4.943494318360858e-06, "loss": 0.0009, "step": 300110 }, { "epoch": 72.09, "learning_rate": 4.94154918219234e-06, "loss": 0.0013, "step": 300120 }, { "epoch": 72.09, "learning_rate": 4.939604408885729e-06, "loss": 0.0011, "step": 300130 }, { "epoch": 72.09, "learning_rate": 4.937659998456712e-06, "loss": 0.001, "step": 300140 }, { "epoch": 72.09, "learning_rate": 4.935715950920938e-06, "loss": 0.001, "step": 300150 }, { "epoch": 72.1, "learning_rate": 4.933772266294068e-06, "loss": 0.0015, "step": 300160 }, { "epoch": 72.1, "learning_rate": 4.931828944591749e-06, "loss": 0.0012, "step": 300170 }, { "epoch": 72.1, "learning_rate": 4.929885985829635e-06, "loss": 0.0012, "step": 300180 }, { "epoch": 72.1, "learning_rate": 4.92794339002337e-06, "loss": 0.0012, "step": 300190 }, { "epoch": 72.11, "learning_rate": 4.9260011571885925e-06, "loss": 0.001, "step": 300200 }, { "epoch": 72.11, "learning_rate": 4.92405928734096e-06, "loss": 0.0018, "step": 300210 }, { "epoch": 72.11, "learning_rate": 4.92211778049611e-06, "loss": 0.001, "step": 300220 }, { "epoch": 72.11, "learning_rate": 4.920176636669649e-06, "loss": 0.001, "step": 300230 }, { "epoch": 72.12, "learning_rate": 4.91823585587724e-06, "loss": 0.001, "step": 300240 }, { "epoch": 72.12, "learning_rate": 4.916295438134499e-06, "loss": 0.0012, "step": 300250 }, { "epoch": 72.12, "learning_rate": 4.9143553834570585e-06, "loss": 0.001, "step": 300260 }, { "epoch": 72.12, "learning_rate": 4.912415691860539e-06, "loss": 0.001, "step": 300270 }, { "epoch": 72.12, "learning_rate": 4.910476363360555e-06, "loss": 0.0011, "step": 300280 }, { "epoch": 72.13, "learning_rate": 4.908537397972735e-06, "loss": 0.0011, "step": 300290 }, { "epoch": 72.13, "learning_rate": 4.9065987957126805e-06, "loss": 0.0011, "step": 300300 }, { "epoch": 72.13, "learning_rate": 4.904660556596024e-06, "loss": 0.0013, "step": 300310 }, { "epoch": 72.13, "learning_rate": 4.902722680638355e-06, "loss": 0.0011, "step": 300320 }, { "epoch": 72.14, "learning_rate": 4.900785167855287e-06, "loss": 0.0011, "step": 300330 }, { "epoch": 72.14, "learning_rate": 4.898848018262414e-06, "loss": 0.0012, "step": 300340 }, { "epoch": 72.14, "learning_rate": 4.896911231875356e-06, "loss": 0.001, "step": 300350 }, { "epoch": 72.14, "learning_rate": 4.894974808709707e-06, "loss": 0.0013, "step": 300360 }, { "epoch": 72.14, "learning_rate": 4.893038748781031e-06, "loss": 0.0031, "step": 300370 }, { "epoch": 72.15, "learning_rate": 4.891103052104951e-06, "loss": 0.0013, "step": 300380 }, { "epoch": 72.15, "learning_rate": 4.889167718697046e-06, "loss": 0.0009, "step": 300390 }, { "epoch": 72.15, "learning_rate": 4.887232748572901e-06, "loss": 0.0009, "step": 300400 }, { "epoch": 72.15, "learning_rate": 4.885298141748102e-06, "loss": 0.0061, "step": 300410 }, { "epoch": 72.16, "learning_rate": 4.8833638982382244e-06, "loss": 0.0011, "step": 300420 }, { "epoch": 72.16, "learning_rate": 4.8814300180588466e-06, "loss": 0.0011, "step": 300430 }, { "epoch": 72.16, "learning_rate": 4.879496501225528e-06, "loss": 0.001, "step": 300440 }, { "epoch": 72.16, "learning_rate": 4.877563347753878e-06, "loss": 0.001, "step": 300450 }, { "epoch": 72.17, "learning_rate": 4.875630557659427e-06, "loss": 0.0009, "step": 300460 }, { "epoch": 72.17, "learning_rate": 4.873698130957744e-06, "loss": 0.0012, "step": 300470 }, { "epoch": 72.17, "learning_rate": 4.871766067664413e-06, "loss": 0.0011, "step": 300480 }, { "epoch": 72.17, "learning_rate": 4.869834367794973e-06, "loss": 0.0011, "step": 300490 }, { "epoch": 72.17, "learning_rate": 4.867903031364995e-06, "loss": 0.0011, "step": 300500 }, { "epoch": 72.18, "learning_rate": 4.865972058390017e-06, "loss": 0.0009, "step": 300510 }, { "epoch": 72.18, "learning_rate": 4.864041448885603e-06, "loss": 0.0011, "step": 300520 }, { "epoch": 72.18, "learning_rate": 4.8621112028672925e-06, "loss": 0.0015, "step": 300530 }, { "epoch": 72.18, "learning_rate": 4.860181320350626e-06, "loss": 0.001, "step": 300540 }, { "epoch": 72.19, "learning_rate": 4.858251801351166e-06, "loss": 0.0011, "step": 300550 }, { "epoch": 72.19, "learning_rate": 4.8563226458844255e-06, "loss": 0.0009, "step": 300560 }, { "epoch": 72.19, "learning_rate": 4.854393853965955e-06, "loss": 0.0016, "step": 300570 }, { "epoch": 72.19, "learning_rate": 4.852465425611275e-06, "loss": 0.0012, "step": 300580 }, { "epoch": 72.2, "learning_rate": 4.850537360835933e-06, "loss": 0.0009, "step": 300590 }, { "epoch": 72.2, "learning_rate": 4.848609659655451e-06, "loss": 0.0034, "step": 300600 }, { "epoch": 72.2, "learning_rate": 4.846682322085338e-06, "loss": 0.0013, "step": 300610 }, { "epoch": 72.2, "learning_rate": 4.8447553481411275e-06, "loss": 0.0009, "step": 300620 }, { "epoch": 72.2, "learning_rate": 4.84282873783834e-06, "loss": 0.0009, "step": 300630 }, { "epoch": 72.21, "learning_rate": 4.8409024911924894e-06, "loss": 0.0012, "step": 300640 }, { "epoch": 72.21, "learning_rate": 4.838976608219081e-06, "loss": 0.001, "step": 300650 }, { "epoch": 72.21, "learning_rate": 4.837051088933636e-06, "loss": 0.0017, "step": 300660 }, { "epoch": 72.21, "learning_rate": 4.835125933351647e-06, "loss": 0.0014, "step": 300670 }, { "epoch": 72.22, "learning_rate": 4.833201141488619e-06, "loss": 0.001, "step": 300680 }, { "epoch": 72.22, "learning_rate": 4.831276713360072e-06, "loss": 0.001, "step": 300690 }, { "epoch": 72.22, "learning_rate": 4.829352648981483e-06, "loss": 0.0013, "step": 300700 }, { "epoch": 72.22, "learning_rate": 4.827428948368345e-06, "loss": 0.0011, "step": 300710 }, { "epoch": 72.22, "learning_rate": 4.825505611536163e-06, "loss": 0.0011, "step": 300720 }, { "epoch": 72.23, "learning_rate": 4.8235826385004235e-06, "loss": 0.001, "step": 300730 }, { "epoch": 72.23, "learning_rate": 4.82166002927662e-06, "loss": 0.0009, "step": 300740 }, { "epoch": 72.23, "learning_rate": 4.819737783880207e-06, "loss": 0.0071, "step": 300750 }, { "epoch": 72.23, "learning_rate": 4.817815902326695e-06, "loss": 0.0029, "step": 300760 }, { "epoch": 72.24, "learning_rate": 4.815894384631548e-06, "loss": 0.001, "step": 300770 }, { "epoch": 72.24, "learning_rate": 4.813973230810237e-06, "loss": 0.001, "step": 300780 }, { "epoch": 72.24, "learning_rate": 4.812052440878246e-06, "loss": 0.001, "step": 300790 }, { "epoch": 72.24, "learning_rate": 4.810132014851027e-06, "loss": 0.001, "step": 300800 }, { "epoch": 72.25, "learning_rate": 4.808211952744058e-06, "loss": 0.001, "step": 300810 }, { "epoch": 72.25, "learning_rate": 4.806292254572786e-06, "loss": 0.0011, "step": 300820 }, { "epoch": 72.25, "learning_rate": 4.804372920352701e-06, "loss": 0.0018, "step": 300830 }, { "epoch": 72.25, "learning_rate": 4.8024539500992335e-06, "loss": 0.0011, "step": 300840 }, { "epoch": 72.25, "learning_rate": 4.800535343827833e-06, "loss": 0.0013, "step": 300850 }, { "epoch": 72.26, "learning_rate": 4.798617101553971e-06, "loss": 0.0009, "step": 300860 }, { "epoch": 72.26, "learning_rate": 4.796699223293083e-06, "loss": 0.0013, "step": 300870 }, { "epoch": 72.26, "learning_rate": 4.794781709060625e-06, "loss": 0.0011, "step": 300880 }, { "epoch": 72.26, "learning_rate": 4.792864558872024e-06, "loss": 0.0029, "step": 300890 }, { "epoch": 72.27, "learning_rate": 4.790947772742726e-06, "loss": 0.001, "step": 300900 }, { "epoch": 72.27, "learning_rate": 4.7890313506881726e-06, "loss": 0.0014, "step": 300910 }, { "epoch": 72.27, "learning_rate": 4.787115292723776e-06, "loss": 0.001, "step": 300920 }, { "epoch": 72.27, "learning_rate": 4.7851995988650036e-06, "loss": 0.0029, "step": 300930 }, { "epoch": 72.28, "learning_rate": 4.783284269127247e-06, "loss": 0.001, "step": 300940 }, { "epoch": 72.28, "learning_rate": 4.78136930352594e-06, "loss": 0.0009, "step": 300950 }, { "epoch": 72.28, "learning_rate": 4.779454702076519e-06, "loss": 0.0011, "step": 300960 }, { "epoch": 72.28, "learning_rate": 4.7775404647944e-06, "loss": 0.001, "step": 300970 }, { "epoch": 72.28, "learning_rate": 4.775626591694981e-06, "loss": 0.0011, "step": 300980 }, { "epoch": 72.29, "learning_rate": 4.7737130827936796e-06, "loss": 0.0008, "step": 300990 }, { "epoch": 72.29, "learning_rate": 4.771799938105914e-06, "loss": 0.0012, "step": 301000 }, { "epoch": 72.29, "learning_rate": 4.7698871576470906e-06, "loss": 0.0013, "step": 301010 }, { "epoch": 72.29, "learning_rate": 4.7679747414326124e-06, "loss": 0.0009, "step": 301020 }, { "epoch": 72.3, "learning_rate": 4.766062689477874e-06, "loss": 0.0011, "step": 301030 }, { "epoch": 72.3, "learning_rate": 4.764151001798284e-06, "loss": 0.0009, "step": 301040 }, { "epoch": 72.3, "learning_rate": 4.7622396784092245e-06, "loss": 0.0011, "step": 301050 }, { "epoch": 72.3, "learning_rate": 4.7603287193260845e-06, "loss": 0.001, "step": 301060 }, { "epoch": 72.3, "learning_rate": 4.758418124564284e-06, "loss": 0.0016, "step": 301070 }, { "epoch": 72.31, "learning_rate": 4.756507894139184e-06, "loss": 0.0026, "step": 301080 }, { "epoch": 72.31, "learning_rate": 4.7545980280661594e-06, "loss": 0.0011, "step": 301090 }, { "epoch": 72.31, "learning_rate": 4.75268852636061e-06, "loss": 0.001, "step": 301100 }, { "epoch": 72.31, "learning_rate": 4.750779389037918e-06, "loss": 0.001, "step": 301110 }, { "epoch": 72.32, "learning_rate": 4.748870616113427e-06, "loss": 0.0012, "step": 301120 }, { "epoch": 72.32, "learning_rate": 4.74696220760254e-06, "loss": 0.0011, "step": 301130 }, { "epoch": 72.32, "learning_rate": 4.745054163520612e-06, "loss": 0.0011, "step": 301140 }, { "epoch": 72.32, "learning_rate": 4.7431464838830095e-06, "loss": 0.0031, "step": 301150 }, { "epoch": 72.33, "learning_rate": 4.7412391687050976e-06, "loss": 0.001, "step": 301160 }, { "epoch": 72.33, "learning_rate": 4.739332218002235e-06, "loss": 0.001, "step": 301170 }, { "epoch": 72.33, "learning_rate": 4.737425631789777e-06, "loss": 0.0011, "step": 301180 }, { "epoch": 72.33, "learning_rate": 4.7355194100830835e-06, "loss": 0.0015, "step": 301190 }, { "epoch": 72.33, "learning_rate": 4.733613552897486e-06, "loss": 0.0008, "step": 301200 }, { "epoch": 72.34, "learning_rate": 4.731708060248375e-06, "loss": 0.0012, "step": 301210 }, { "epoch": 72.34, "learning_rate": 4.7298029321510565e-06, "loss": 0.0013, "step": 301220 }, { "epoch": 72.34, "learning_rate": 4.72789816862087e-06, "loss": 0.0051, "step": 301230 }, { "epoch": 72.34, "learning_rate": 4.725993769673182e-06, "loss": 0.0011, "step": 301240 }, { "epoch": 72.35, "learning_rate": 4.7240897353233175e-06, "loss": 0.0032, "step": 301250 }, { "epoch": 72.35, "learning_rate": 4.722186065586609e-06, "loss": 0.0016, "step": 301260 }, { "epoch": 72.35, "learning_rate": 4.7202827604783895e-06, "loss": 0.002, "step": 301270 }, { "epoch": 72.35, "learning_rate": 4.718379820013979e-06, "loss": 0.001, "step": 301280 }, { "epoch": 72.36, "learning_rate": 4.716477244208711e-06, "loss": 0.0013, "step": 301290 }, { "epoch": 72.36, "learning_rate": 4.714575033077906e-06, "loss": 0.002, "step": 301300 }, { "epoch": 72.36, "learning_rate": 4.712673186636874e-06, "loss": 0.0012, "step": 301310 }, { "epoch": 72.36, "learning_rate": 4.71077170490094e-06, "loss": 0.0011, "step": 301320 }, { "epoch": 72.36, "learning_rate": 4.708870587885405e-06, "loss": 0.0011, "step": 301330 }, { "epoch": 72.37, "learning_rate": 4.7069698356055955e-06, "loss": 0.0012, "step": 301340 }, { "epoch": 72.37, "learning_rate": 4.705069448076826e-06, "loss": 0.0013, "step": 301350 }, { "epoch": 72.37, "learning_rate": 4.703169425314363e-06, "loss": 0.0012, "step": 301360 }, { "epoch": 72.37, "learning_rate": 4.701269767333538e-06, "loss": 0.0046, "step": 301370 }, { "epoch": 72.38, "learning_rate": 4.699370474149645e-06, "loss": 0.0009, "step": 301380 }, { "epoch": 72.38, "learning_rate": 4.697471545777971e-06, "loss": 0.0009, "step": 301390 }, { "epoch": 72.38, "learning_rate": 4.695572982233815e-06, "loss": 0.0013, "step": 301400 }, { "epoch": 72.38, "learning_rate": 4.6936747835324646e-06, "loss": 0.001, "step": 301410 }, { "epoch": 72.38, "learning_rate": 4.6917769496892085e-06, "loss": 0.0012, "step": 301420 }, { "epoch": 72.39, "learning_rate": 4.689879480719328e-06, "loss": 0.0011, "step": 301430 }, { "epoch": 72.39, "learning_rate": 4.687982376638101e-06, "loss": 0.001, "step": 301440 }, { "epoch": 72.39, "learning_rate": 4.686085637460807e-06, "loss": 0.001, "step": 301450 }, { "epoch": 72.39, "learning_rate": 4.684189263202721e-06, "loss": 0.0011, "step": 301460 }, { "epoch": 72.4, "learning_rate": 4.682293253879105e-06, "loss": 0.0009, "step": 301470 }, { "epoch": 72.4, "learning_rate": 4.6803976095052545e-06, "loss": 0.001, "step": 301480 }, { "epoch": 72.4, "learning_rate": 4.678502330096424e-06, "loss": 0.0011, "step": 301490 }, { "epoch": 72.4, "learning_rate": 4.67660741566785e-06, "loss": 0.0012, "step": 301500 }, { "epoch": 72.41, "learning_rate": 4.674712866234826e-06, "loss": 0.0012, "step": 301510 }, { "epoch": 72.41, "learning_rate": 4.672818681812591e-06, "loss": 0.0011, "step": 301520 }, { "epoch": 72.41, "learning_rate": 4.670924862416409e-06, "loss": 0.0014, "step": 301530 }, { "epoch": 72.41, "learning_rate": 4.66903140806153e-06, "loss": 0.001, "step": 301540 }, { "epoch": 72.41, "learning_rate": 4.667138318763198e-06, "loss": 0.0017, "step": 301550 }, { "epoch": 72.42, "learning_rate": 4.66524559453666e-06, "loss": 0.0011, "step": 301560 }, { "epoch": 72.42, "learning_rate": 4.663353235397144e-06, "loss": 0.0009, "step": 301570 }, { "epoch": 72.42, "learning_rate": 4.661461241359916e-06, "loss": 0.0011, "step": 301580 }, { "epoch": 72.42, "learning_rate": 4.659569612440212e-06, "loss": 0.003, "step": 301590 }, { "epoch": 72.43, "learning_rate": 4.657678348653244e-06, "loss": 0.0019, "step": 301600 }, { "epoch": 72.43, "learning_rate": 4.655787450014237e-06, "loss": 0.0013, "step": 301610 }, { "epoch": 72.43, "learning_rate": 4.653896916538447e-06, "loss": 0.001, "step": 301620 }, { "epoch": 72.43, "learning_rate": 4.652006748241094e-06, "loss": 0.001, "step": 301630 }, { "epoch": 72.44, "learning_rate": 4.650116945137378e-06, "loss": 0.0015, "step": 301640 }, { "epoch": 72.44, "learning_rate": 4.648227507242537e-06, "loss": 0.0012, "step": 301650 }, { "epoch": 72.44, "learning_rate": 4.646338434571779e-06, "loss": 0.0009, "step": 301660 }, { "epoch": 72.44, "learning_rate": 4.644449727140316e-06, "loss": 0.0017, "step": 301670 }, { "epoch": 72.44, "learning_rate": 4.642561384963368e-06, "loss": 0.0012, "step": 301680 }, { "epoch": 72.45, "learning_rate": 4.640673408056129e-06, "loss": 0.0014, "step": 301690 }, { "epoch": 72.45, "learning_rate": 4.638785796433815e-06, "loss": 0.0014, "step": 301700 }, { "epoch": 72.45, "learning_rate": 4.636898550111607e-06, "loss": 0.0015, "step": 301710 }, { "epoch": 72.45, "learning_rate": 4.635011669104733e-06, "loss": 0.001, "step": 301720 }, { "epoch": 72.46, "learning_rate": 4.633125153428381e-06, "loss": 0.0009, "step": 301730 }, { "epoch": 72.46, "learning_rate": 4.6312390030977145e-06, "loss": 0.0011, "step": 301740 }, { "epoch": 72.46, "learning_rate": 4.629353218127952e-06, "loss": 0.0011, "step": 301750 }, { "epoch": 72.46, "learning_rate": 4.627467798534274e-06, "loss": 0.0011, "step": 301760 }, { "epoch": 72.46, "learning_rate": 4.625582744331864e-06, "loss": 0.0013, "step": 301770 }, { "epoch": 72.47, "learning_rate": 4.623698055535896e-06, "loss": 0.0011, "step": 301780 }, { "epoch": 72.47, "learning_rate": 4.621813732161551e-06, "loss": 0.0011, "step": 301790 }, { "epoch": 72.47, "learning_rate": 4.619929774224007e-06, "loss": 0.001, "step": 301800 }, { "epoch": 72.47, "learning_rate": 4.618046181738428e-06, "loss": 0.0008, "step": 301810 }, { "epoch": 72.48, "learning_rate": 4.616162954720004e-06, "loss": 0.0026, "step": 301820 }, { "epoch": 72.48, "learning_rate": 4.614280093183876e-06, "loss": 0.0011, "step": 301830 }, { "epoch": 72.48, "learning_rate": 4.6123975971452185e-06, "loss": 0.0013, "step": 301840 }, { "epoch": 72.48, "learning_rate": 4.610515466619175e-06, "loss": 0.001, "step": 301850 }, { "epoch": 72.49, "learning_rate": 4.608633701620929e-06, "loss": 0.001, "step": 301860 }, { "epoch": 72.49, "learning_rate": 4.606752302165634e-06, "loss": 0.0012, "step": 301870 }, { "epoch": 72.49, "learning_rate": 4.604871268268407e-06, "loss": 0.0011, "step": 301880 }, { "epoch": 72.49, "learning_rate": 4.602990599944434e-06, "loss": 0.0011, "step": 301890 }, { "epoch": 72.49, "learning_rate": 4.601110297208838e-06, "loss": 0.0014, "step": 301900 }, { "epoch": 72.5, "learning_rate": 4.5992303600767725e-06, "loss": 0.0012, "step": 301910 }, { "epoch": 72.5, "learning_rate": 4.597350788563376e-06, "loss": 0.001, "step": 301920 }, { "epoch": 72.5, "learning_rate": 4.595471582683775e-06, "loss": 0.001, "step": 301930 }, { "epoch": 72.5, "learning_rate": 4.593592742453112e-06, "loss": 0.0029, "step": 301940 }, { "epoch": 72.51, "learning_rate": 4.5917142678865095e-06, "loss": 0.0011, "step": 301950 }, { "epoch": 72.51, "learning_rate": 4.589836158999117e-06, "loss": 0.0011, "step": 301960 }, { "epoch": 72.51, "learning_rate": 4.587958415806032e-06, "loss": 0.0011, "step": 301970 }, { "epoch": 72.51, "learning_rate": 4.586081038322382e-06, "loss": 0.0011, "step": 301980 }, { "epoch": 72.52, "learning_rate": 4.584204026563299e-06, "loss": 0.0011, "step": 301990 }, { "epoch": 72.52, "learning_rate": 4.582327380543888e-06, "loss": 0.0012, "step": 302000 }, { "epoch": 72.52, "learning_rate": 4.580451100279271e-06, "loss": 0.0034, "step": 302010 }, { "epoch": 72.52, "learning_rate": 4.5785751857845445e-06, "loss": 0.0009, "step": 302020 }, { "epoch": 72.52, "learning_rate": 4.576699637074827e-06, "loss": 0.0009, "step": 302030 }, { "epoch": 72.53, "learning_rate": 4.574824454165222e-06, "loss": 0.0028, "step": 302040 }, { "epoch": 72.53, "learning_rate": 4.572949637070822e-06, "loss": 0.0016, "step": 302050 }, { "epoch": 72.53, "learning_rate": 4.571075185806728e-06, "loss": 0.0011, "step": 302060 }, { "epoch": 72.53, "learning_rate": 4.569201100388043e-06, "loss": 0.0064, "step": 302070 }, { "epoch": 72.54, "learning_rate": 4.56732738082985e-06, "loss": 0.0012, "step": 302080 }, { "epoch": 72.54, "learning_rate": 4.565454027147237e-06, "loss": 0.001, "step": 302090 }, { "epoch": 72.54, "learning_rate": 4.563581039355308e-06, "loss": 0.0011, "step": 302100 }, { "epoch": 72.54, "learning_rate": 4.5617084174691294e-06, "loss": 0.001, "step": 302110 }, { "epoch": 72.54, "learning_rate": 4.559836161503772e-06, "loss": 0.0011, "step": 302120 }, { "epoch": 72.55, "learning_rate": 4.557964271474341e-06, "loss": 0.0013, "step": 302130 }, { "epoch": 72.55, "learning_rate": 4.556092747395896e-06, "loss": 0.0011, "step": 302140 }, { "epoch": 72.55, "learning_rate": 4.5542215892835085e-06, "loss": 0.001, "step": 302150 }, { "epoch": 72.55, "learning_rate": 4.552350797152249e-06, "loss": 0.0023, "step": 302160 }, { "epoch": 72.56, "learning_rate": 4.550480371017185e-06, "loss": 0.001, "step": 302170 }, { "epoch": 72.56, "learning_rate": 4.548610310893375e-06, "loss": 0.0011, "step": 302180 }, { "epoch": 72.56, "learning_rate": 4.546740616795875e-06, "loss": 0.001, "step": 302190 }, { "epoch": 72.56, "learning_rate": 4.544871288739766e-06, "loss": 0.001, "step": 302200 }, { "epoch": 72.57, "learning_rate": 4.543002326740075e-06, "loss": 0.001, "step": 302210 }, { "epoch": 72.57, "learning_rate": 4.541133730811847e-06, "loss": 0.0009, "step": 302220 }, { "epoch": 72.57, "learning_rate": 4.539265500970158e-06, "loss": 0.0019, "step": 302230 }, { "epoch": 72.57, "learning_rate": 4.5373976372300454e-06, "loss": 0.001, "step": 302240 }, { "epoch": 72.57, "learning_rate": 4.535530139606548e-06, "loss": 0.0009, "step": 302250 }, { "epoch": 72.58, "learning_rate": 4.533663008114686e-06, "loss": 0.0011, "step": 302260 }, { "epoch": 72.58, "learning_rate": 4.531796242769526e-06, "loss": 0.0021, "step": 302270 }, { "epoch": 72.58, "learning_rate": 4.529929843586084e-06, "loss": 0.0018, "step": 302280 }, { "epoch": 72.58, "learning_rate": 4.528063810579397e-06, "loss": 0.0011, "step": 302290 }, { "epoch": 72.59, "learning_rate": 4.526198143764488e-06, "loss": 0.0011, "step": 302300 }, { "epoch": 72.59, "learning_rate": 4.524332843156387e-06, "loss": 0.001, "step": 302310 }, { "epoch": 72.59, "learning_rate": 4.522467908770106e-06, "loss": 0.0057, "step": 302320 }, { "epoch": 72.59, "learning_rate": 4.520603340620666e-06, "loss": 0.0011, "step": 302330 }, { "epoch": 72.6, "learning_rate": 4.518739138723099e-06, "loss": 0.001, "step": 302340 }, { "epoch": 72.6, "learning_rate": 4.516875303092399e-06, "loss": 0.0008, "step": 302350 }, { "epoch": 72.6, "learning_rate": 4.515011833743571e-06, "loss": 0.0009, "step": 302360 }, { "epoch": 72.6, "learning_rate": 4.513148730691647e-06, "loss": 0.0011, "step": 302370 }, { "epoch": 72.6, "learning_rate": 4.511285993951608e-06, "loss": 0.002, "step": 302380 }, { "epoch": 72.61, "learning_rate": 4.509423623538467e-06, "loss": 0.0014, "step": 302390 }, { "epoch": 72.61, "learning_rate": 4.507561619467215e-06, "loss": 0.0011, "step": 302400 }, { "epoch": 72.61, "learning_rate": 4.505699981752854e-06, "loss": 0.001, "step": 302410 }, { "epoch": 72.61, "learning_rate": 4.503838710410374e-06, "loss": 0.0009, "step": 302420 }, { "epoch": 72.62, "learning_rate": 4.501977805454754e-06, "loss": 0.0012, "step": 302430 }, { "epoch": 72.62, "learning_rate": 4.500117266900994e-06, "loss": 0.0011, "step": 302440 }, { "epoch": 72.62, "learning_rate": 4.498257094764069e-06, "loss": 0.0009, "step": 302450 }, { "epoch": 72.62, "learning_rate": 4.4963972890589514e-06, "loss": 0.0014, "step": 302460 }, { "epoch": 72.62, "learning_rate": 4.4945378498006396e-06, "loss": 0.001, "step": 302470 }, { "epoch": 72.63, "learning_rate": 4.492678777004105e-06, "loss": 0.0012, "step": 302480 }, { "epoch": 72.63, "learning_rate": 4.490820070684304e-06, "loss": 0.0009, "step": 302490 }, { "epoch": 72.63, "learning_rate": 4.488961730856206e-06, "loss": 0.011, "step": 302500 }, { "epoch": 72.63, "learning_rate": 4.487103757534783e-06, "loss": 0.0009, "step": 302510 }, { "epoch": 72.64, "learning_rate": 4.485246150735001e-06, "loss": 0.0027, "step": 302520 }, { "epoch": 72.64, "learning_rate": 4.483388910471814e-06, "loss": 0.0034, "step": 302530 }, { "epoch": 72.64, "learning_rate": 4.481532036760183e-06, "loss": 0.0063, "step": 302540 }, { "epoch": 72.64, "learning_rate": 4.479675529615057e-06, "loss": 0.0014, "step": 302550 }, { "epoch": 72.65, "learning_rate": 4.477819389051391e-06, "loss": 0.0011, "step": 302560 }, { "epoch": 72.65, "learning_rate": 4.475963615084117e-06, "loss": 0.0011, "step": 302570 }, { "epoch": 72.65, "learning_rate": 4.474108207728212e-06, "loss": 0.0012, "step": 302580 }, { "epoch": 72.65, "learning_rate": 4.472253166998591e-06, "loss": 0.0022, "step": 302590 }, { "epoch": 72.65, "learning_rate": 4.470398492910188e-06, "loss": 0.0012, "step": 302600 }, { "epoch": 72.66, "learning_rate": 4.468544185477969e-06, "loss": 0.001, "step": 302610 }, { "epoch": 72.66, "learning_rate": 4.466690244716854e-06, "loss": 0.001, "step": 302620 }, { "epoch": 72.66, "learning_rate": 4.464836670641748e-06, "loss": 0.0011, "step": 302630 }, { "epoch": 72.66, "learning_rate": 4.462983463267612e-06, "loss": 0.0009, "step": 302640 }, { "epoch": 72.67, "learning_rate": 4.461130622609355e-06, "loss": 0.001, "step": 302650 }, { "epoch": 72.67, "learning_rate": 4.4592781486819e-06, "loss": 0.0009, "step": 302660 }, { "epoch": 72.67, "learning_rate": 4.457426041500163e-06, "loss": 0.001, "step": 302670 }, { "epoch": 72.67, "learning_rate": 4.455574301079063e-06, "loss": 0.001, "step": 302680 }, { "epoch": 72.68, "learning_rate": 4.453722927433512e-06, "loss": 0.001, "step": 302690 }, { "epoch": 72.68, "learning_rate": 4.451871920578421e-06, "loss": 0.0011, "step": 302700 }, { "epoch": 72.68, "learning_rate": 4.450021280528682e-06, "loss": 0.001, "step": 302710 }, { "epoch": 72.68, "learning_rate": 4.448171007299229e-06, "loss": 0.0012, "step": 302720 }, { "epoch": 72.68, "learning_rate": 4.446321100904932e-06, "loss": 0.001, "step": 302730 }, { "epoch": 72.69, "learning_rate": 4.444471561360691e-06, "loss": 0.001, "step": 302740 }, { "epoch": 72.69, "learning_rate": 4.442622388681422e-06, "loss": 0.0011, "step": 302750 }, { "epoch": 72.69, "learning_rate": 4.440773582882013e-06, "loss": 0.0011, "step": 302760 }, { "epoch": 72.69, "learning_rate": 4.43892514397733e-06, "loss": 0.0012, "step": 302770 }, { "epoch": 72.7, "learning_rate": 4.437077071982276e-06, "loss": 0.0011, "step": 302780 }, { "epoch": 72.7, "learning_rate": 4.4352293669117305e-06, "loss": 0.0009, "step": 302790 }, { "epoch": 72.7, "learning_rate": 4.433382028780575e-06, "loss": 0.0009, "step": 302800 }, { "epoch": 72.7, "learning_rate": 4.431535057603687e-06, "loss": 0.0013, "step": 302810 }, { "epoch": 72.7, "learning_rate": 4.429688453395936e-06, "loss": 0.0011, "step": 302820 }, { "epoch": 72.71, "learning_rate": 4.427842216172196e-06, "loss": 0.001, "step": 302830 }, { "epoch": 72.71, "learning_rate": 4.425996345947325e-06, "loss": 0.0017, "step": 302840 }, { "epoch": 72.71, "learning_rate": 4.424150842736208e-06, "loss": 0.0012, "step": 302850 }, { "epoch": 72.71, "learning_rate": 4.422305706553703e-06, "loss": 0.0011, "step": 302860 }, { "epoch": 72.72, "learning_rate": 4.420460937414644e-06, "loss": 0.001, "step": 302870 }, { "epoch": 72.72, "learning_rate": 4.418616535333919e-06, "loss": 0.0013, "step": 302880 }, { "epoch": 72.72, "learning_rate": 4.4167725003263664e-06, "loss": 0.0035, "step": 302890 }, { "epoch": 72.72, "learning_rate": 4.414928832406834e-06, "loss": 0.0058, "step": 302900 }, { "epoch": 72.73, "learning_rate": 4.413085531590177e-06, "loss": 0.0009, "step": 302910 }, { "epoch": 72.73, "learning_rate": 4.411242597891235e-06, "loss": 0.0011, "step": 302920 }, { "epoch": 72.73, "learning_rate": 4.409400031324851e-06, "loss": 0.0015, "step": 302930 }, { "epoch": 72.73, "learning_rate": 4.407557831905856e-06, "loss": 0.0012, "step": 302940 }, { "epoch": 72.73, "learning_rate": 4.405715999649102e-06, "loss": 0.0009, "step": 302950 }, { "epoch": 72.74, "learning_rate": 4.403874534569407e-06, "loss": 0.0009, "step": 302960 }, { "epoch": 72.74, "learning_rate": 4.4020334366816075e-06, "loss": 0.0011, "step": 302970 }, { "epoch": 72.74, "learning_rate": 4.400192706000517e-06, "loss": 0.0021, "step": 302980 }, { "epoch": 72.74, "learning_rate": 4.398352342540979e-06, "loss": 0.0021, "step": 302990 }, { "epoch": 72.75, "learning_rate": 4.396512346317816e-06, "loss": 0.0012, "step": 303000 }, { "epoch": 72.75, "learning_rate": 4.39467271734581e-06, "loss": 0.0011, "step": 303010 }, { "epoch": 72.75, "learning_rate": 4.392833455639816e-06, "loss": 0.0024, "step": 303020 }, { "epoch": 72.75, "learning_rate": 4.390994561214634e-06, "loss": 0.001, "step": 303030 }, { "epoch": 72.76, "learning_rate": 4.389156034085062e-06, "loss": 0.001, "step": 303040 }, { "epoch": 72.76, "learning_rate": 4.387317874265917e-06, "loss": 0.0009, "step": 303050 }, { "epoch": 72.76, "learning_rate": 4.3854800817720034e-06, "loss": 0.0011, "step": 303060 }, { "epoch": 72.76, "learning_rate": 4.383642656618109e-06, "loss": 0.0012, "step": 303070 }, { "epoch": 72.76, "learning_rate": 4.381805598819033e-06, "loss": 0.0011, "step": 303080 }, { "epoch": 72.77, "learning_rate": 4.379968908389587e-06, "loss": 0.0012, "step": 303090 }, { "epoch": 72.77, "learning_rate": 4.378132585344546e-06, "loss": 0.0033, "step": 303100 }, { "epoch": 72.77, "learning_rate": 4.376296629698701e-06, "loss": 0.0011, "step": 303110 }, { "epoch": 72.77, "learning_rate": 4.374461041466826e-06, "loss": 0.0014, "step": 303120 }, { "epoch": 72.78, "learning_rate": 4.372625820663729e-06, "loss": 0.0012, "step": 303130 }, { "epoch": 72.78, "learning_rate": 4.370790967304184e-06, "loss": 0.0011, "step": 303140 }, { "epoch": 72.78, "learning_rate": 4.368956481402936e-06, "loss": 0.0017, "step": 303150 }, { "epoch": 72.78, "learning_rate": 4.367122362974791e-06, "loss": 0.001, "step": 303160 }, { "epoch": 72.78, "learning_rate": 4.3652886120345125e-06, "loss": 0.0011, "step": 303170 }, { "epoch": 72.79, "learning_rate": 4.363455228596863e-06, "loss": 0.0011, "step": 303180 }, { "epoch": 72.79, "learning_rate": 4.361622212676614e-06, "loss": 0.0015, "step": 303190 }, { "epoch": 72.79, "learning_rate": 4.359789564288519e-06, "loss": 0.0015, "step": 303200 }, { "epoch": 72.79, "learning_rate": 4.357957283447339e-06, "loss": 0.0019, "step": 303210 }, { "epoch": 72.8, "learning_rate": 4.356125370167818e-06, "loss": 0.0012, "step": 303220 }, { "epoch": 72.8, "learning_rate": 4.3542938244647335e-06, "loss": 0.0014, "step": 303230 }, { "epoch": 72.8, "learning_rate": 4.352462646352834e-06, "loss": 0.001, "step": 303240 }, { "epoch": 72.8, "learning_rate": 4.35063183584683e-06, "loss": 0.0011, "step": 303250 }, { "epoch": 72.81, "learning_rate": 4.348801392961505e-06, "loss": 0.0012, "step": 303260 }, { "epoch": 72.81, "learning_rate": 4.346971317711585e-06, "loss": 0.001, "step": 303270 }, { "epoch": 72.81, "learning_rate": 4.3451416101118025e-06, "loss": 0.001, "step": 303280 }, { "epoch": 72.81, "learning_rate": 4.343312270176902e-06, "loss": 0.001, "step": 303290 }, { "epoch": 72.81, "learning_rate": 4.341483297921611e-06, "loss": 0.0009, "step": 303300 }, { "epoch": 72.82, "learning_rate": 4.3396546933606565e-06, "loss": 0.001, "step": 303310 }, { "epoch": 72.82, "learning_rate": 4.337826456508759e-06, "loss": 0.0012, "step": 303320 }, { "epoch": 72.82, "learning_rate": 4.335998587380668e-06, "loss": 0.0011, "step": 303330 }, { "epoch": 72.82, "learning_rate": 4.334171085991073e-06, "loss": 0.0014, "step": 303340 }, { "epoch": 72.83, "learning_rate": 4.332343952354706e-06, "loss": 0.001, "step": 303350 }, { "epoch": 72.83, "learning_rate": 4.330517186486266e-06, "loss": 0.001, "step": 303360 }, { "epoch": 72.83, "learning_rate": 4.3286907884004854e-06, "loss": 0.001, "step": 303370 }, { "epoch": 72.83, "learning_rate": 4.3268647581120755e-06, "loss": 0.001, "step": 303380 }, { "epoch": 72.84, "learning_rate": 4.325039095635708e-06, "loss": 0.001, "step": 303390 }, { "epoch": 72.84, "learning_rate": 4.3232138009861205e-06, "loss": 0.0013, "step": 303400 }, { "epoch": 72.84, "learning_rate": 4.3213888741779895e-06, "loss": 0.0011, "step": 303410 }, { "epoch": 72.84, "learning_rate": 4.319564315226027e-06, "loss": 0.0012, "step": 303420 }, { "epoch": 72.84, "learning_rate": 4.31774012414492e-06, "loss": 0.001, "step": 303430 }, { "epoch": 72.85, "learning_rate": 4.315916300949352e-06, "loss": 0.0014, "step": 303440 }, { "epoch": 72.85, "learning_rate": 4.314092845654022e-06, "loss": 0.0009, "step": 303450 }, { "epoch": 72.85, "learning_rate": 4.312269758273602e-06, "loss": 0.001, "step": 303460 }, { "epoch": 72.85, "learning_rate": 4.310447038822796e-06, "loss": 0.0026, "step": 303470 }, { "epoch": 72.86, "learning_rate": 4.308624687316259e-06, "loss": 0.0011, "step": 303480 }, { "epoch": 72.86, "learning_rate": 4.30680270376867e-06, "loss": 0.001, "step": 303490 }, { "epoch": 72.86, "learning_rate": 4.304981088194715e-06, "loss": 0.0014, "step": 303500 }, { "epoch": 72.86, "learning_rate": 4.303159840609055e-06, "loss": 0.001, "step": 303510 }, { "epoch": 72.86, "learning_rate": 4.301338961026363e-06, "loss": 0.001, "step": 303520 }, { "epoch": 72.87, "learning_rate": 4.299518449461287e-06, "loss": 0.001, "step": 303530 }, { "epoch": 72.87, "learning_rate": 4.297698305928499e-06, "loss": 0.0021, "step": 303540 }, { "epoch": 72.87, "learning_rate": 4.29587853044266e-06, "loss": 0.0013, "step": 303550 }, { "epoch": 72.87, "learning_rate": 4.294059123018423e-06, "loss": 0.001, "step": 303560 }, { "epoch": 72.88, "learning_rate": 4.292240083670435e-06, "loss": 0.0012, "step": 303570 }, { "epoch": 72.88, "learning_rate": 4.290421412413348e-06, "loss": 0.0011, "step": 303580 }, { "epoch": 72.88, "learning_rate": 4.288603109261813e-06, "loss": 0.001, "step": 303590 }, { "epoch": 72.88, "learning_rate": 4.286785174230451e-06, "loss": 0.001, "step": 303600 }, { "epoch": 72.89, "learning_rate": 4.284967607333945e-06, "loss": 0.0042, "step": 303610 }, { "epoch": 72.89, "learning_rate": 4.283150408586894e-06, "loss": 0.0009, "step": 303620 }, { "epoch": 72.89, "learning_rate": 4.281333578003932e-06, "loss": 0.0011, "step": 303630 }, { "epoch": 72.89, "learning_rate": 4.279517115599719e-06, "loss": 0.0011, "step": 303640 }, { "epoch": 72.89, "learning_rate": 4.277701021388858e-06, "loss": 0.0013, "step": 303650 }, { "epoch": 72.9, "learning_rate": 4.275885295385989e-06, "loss": 0.0021, "step": 303660 }, { "epoch": 72.9, "learning_rate": 4.274069937605723e-06, "loss": 0.001, "step": 303670 }, { "epoch": 72.9, "learning_rate": 4.2722549480626925e-06, "loss": 0.0009, "step": 303680 }, { "epoch": 72.9, "learning_rate": 4.270440326771502e-06, "loss": 0.001, "step": 303690 }, { "epoch": 72.91, "learning_rate": 4.268626073746756e-06, "loss": 0.0163, "step": 303700 }, { "epoch": 72.91, "learning_rate": 4.2668121890031e-06, "loss": 0.0042, "step": 303710 }, { "epoch": 72.91, "learning_rate": 4.264998672555109e-06, "loss": 0.0036, "step": 303720 }, { "epoch": 72.91, "learning_rate": 4.26318552441739e-06, "loss": 0.0015, "step": 303730 }, { "epoch": 72.91, "learning_rate": 4.261372744604564e-06, "loss": 0.0013, "step": 303740 }, { "epoch": 72.92, "learning_rate": 4.259560333131213e-06, "loss": 0.0022, "step": 303750 }, { "epoch": 72.92, "learning_rate": 4.257748290011948e-06, "loss": 0.0011, "step": 303760 }, { "epoch": 72.92, "learning_rate": 4.25593661526133e-06, "loss": 0.0027, "step": 303770 }, { "epoch": 72.92, "learning_rate": 4.254125308893986e-06, "loss": 0.0011, "step": 303780 }, { "epoch": 72.93, "learning_rate": 4.252314370924482e-06, "loss": 0.0014, "step": 303790 }, { "epoch": 72.93, "learning_rate": 4.2505038013674055e-06, "loss": 0.001, "step": 303800 }, { "epoch": 72.93, "learning_rate": 4.248693600237341e-06, "loss": 0.0011, "step": 303810 }, { "epoch": 72.93, "learning_rate": 4.24688376754886e-06, "loss": 0.0011, "step": 303820 }, { "epoch": 72.94, "learning_rate": 4.245074303316543e-06, "loss": 0.0014, "step": 303830 }, { "epoch": 72.94, "learning_rate": 4.243265207554947e-06, "loss": 0.0009, "step": 303840 }, { "epoch": 72.94, "learning_rate": 4.241456480278677e-06, "loss": 0.0011, "step": 303850 }, { "epoch": 72.94, "learning_rate": 4.2396481215022655e-06, "loss": 0.0011, "step": 303860 }, { "epoch": 72.94, "learning_rate": 4.237840131240273e-06, "loss": 0.0011, "step": 303870 }, { "epoch": 72.95, "learning_rate": 4.236032509507282e-06, "loss": 0.0012, "step": 303880 }, { "epoch": 72.95, "learning_rate": 4.234225256317837e-06, "loss": 0.0011, "step": 303890 }, { "epoch": 73.0, "learning_rate": 4.2324183716864975e-06, "loss": 0.001, "step": 303900 }, { "epoch": 73.0, "learning_rate": 4.230611855627814e-06, "loss": 0.0011, "step": 303910 }, { "epoch": 73.0, "learning_rate": 4.228805708156325e-06, "loss": 0.001, "step": 303920 }, { "epoch": 73.01, "learning_rate": 4.226999929286591e-06, "loss": 0.0011, "step": 303930 }, { "epoch": 73.01, "learning_rate": 4.2251945190331375e-06, "loss": 0.0009, "step": 303940 }, { "epoch": 73.01, "learning_rate": 4.223389477410516e-06, "loss": 0.0012, "step": 303950 }, { "epoch": 73.01, "learning_rate": 4.22158480443326e-06, "loss": 0.001, "step": 303960 }, { "epoch": 73.02, "learning_rate": 4.219780500115899e-06, "loss": 0.0009, "step": 303970 }, { "epoch": 73.02, "learning_rate": 4.217976564472959e-06, "loss": 0.001, "step": 303980 }, { "epoch": 73.02, "learning_rate": 4.216172997518991e-06, "loss": 0.001, "step": 303990 }, { "epoch": 73.02, "learning_rate": 4.214369799268497e-06, "loss": 0.0009, "step": 304000 }, { "epoch": 73.03, "learning_rate": 4.212566969735993e-06, "loss": 0.0062, "step": 304010 }, { "epoch": 73.03, "learning_rate": 4.210764508936016e-06, "loss": 0.0011, "step": 304020 }, { "epoch": 73.03, "learning_rate": 4.2089624168830775e-06, "loss": 0.002, "step": 304030 }, { "epoch": 73.03, "learning_rate": 4.207160693591683e-06, "loss": 0.001, "step": 304040 }, { "epoch": 73.03, "learning_rate": 4.205359339076348e-06, "loss": 0.0008, "step": 304050 }, { "epoch": 73.04, "learning_rate": 4.203558353351572e-06, "loss": 0.001, "step": 304060 }, { "epoch": 73.04, "learning_rate": 4.201757736431866e-06, "loss": 0.0011, "step": 304070 }, { "epoch": 73.04, "learning_rate": 4.199957488331724e-06, "loss": 0.0013, "step": 304080 }, { "epoch": 73.04, "learning_rate": 4.198157609065662e-06, "loss": 0.001, "step": 304090 }, { "epoch": 73.05, "learning_rate": 4.196358098648146e-06, "loss": 0.0011, "step": 304100 }, { "epoch": 73.05, "learning_rate": 4.194558957093681e-06, "loss": 0.0013, "step": 304110 }, { "epoch": 73.05, "learning_rate": 4.192760184416761e-06, "loss": 0.0032, "step": 304120 }, { "epoch": 73.05, "learning_rate": 4.190961780631875e-06, "loss": 0.001, "step": 304130 }, { "epoch": 73.06, "learning_rate": 4.189163745753483e-06, "loss": 0.0012, "step": 304140 }, { "epoch": 73.06, "learning_rate": 4.187366079796084e-06, "loss": 0.0018, "step": 304150 }, { "epoch": 73.06, "learning_rate": 4.1855687827741575e-06, "loss": 0.0009, "step": 304160 }, { "epoch": 73.06, "learning_rate": 4.183771854702168e-06, "loss": 0.001, "step": 304170 }, { "epoch": 73.06, "learning_rate": 4.1819752955945864e-06, "loss": 0.0009, "step": 304180 }, { "epoch": 73.07, "learning_rate": 4.180179105465887e-06, "loss": 0.001, "step": 304190 }, { "epoch": 73.07, "learning_rate": 4.178383284330528e-06, "loss": 0.0012, "step": 304200 }, { "epoch": 73.07, "learning_rate": 4.176587832202977e-06, "loss": 0.001, "step": 304210 }, { "epoch": 73.07, "learning_rate": 4.174792749097678e-06, "loss": 0.0012, "step": 304220 }, { "epoch": 73.08, "learning_rate": 4.172998035029124e-06, "loss": 0.001, "step": 304230 }, { "epoch": 73.08, "learning_rate": 4.171203690011727e-06, "loss": 0.0013, "step": 304240 }, { "epoch": 73.08, "learning_rate": 4.169409714059952e-06, "loss": 0.001, "step": 304250 }, { "epoch": 73.08, "learning_rate": 4.1676161071882546e-06, "loss": 0.0011, "step": 304260 }, { "epoch": 73.08, "learning_rate": 4.165822869411079e-06, "loss": 0.001, "step": 304270 }, { "epoch": 73.09, "learning_rate": 4.164030000742841e-06, "loss": 0.0011, "step": 304280 }, { "epoch": 73.09, "learning_rate": 4.162237501198008e-06, "loss": 0.0009, "step": 304290 }, { "epoch": 73.09, "learning_rate": 4.160445370791005e-06, "loss": 0.0012, "step": 304300 }, { "epoch": 73.09, "learning_rate": 4.158653609536267e-06, "loss": 0.001, "step": 304310 }, { "epoch": 73.1, "learning_rate": 4.1568622174482155e-06, "loss": 0.001, "step": 304320 }, { "epoch": 73.1, "learning_rate": 4.155071194541283e-06, "loss": 0.0016, "step": 304330 }, { "epoch": 73.1, "learning_rate": 4.1532805408298905e-06, "loss": 0.001, "step": 304340 }, { "epoch": 73.1, "learning_rate": 4.15149025632845e-06, "loss": 0.001, "step": 304350 }, { "epoch": 73.11, "learning_rate": 4.149700341051399e-06, "loss": 0.001, "step": 304360 }, { "epoch": 73.11, "learning_rate": 4.1479107950131544e-06, "loss": 0.001, "step": 304370 }, { "epoch": 73.11, "learning_rate": 4.1461216182280885e-06, "loss": 0.0013, "step": 304380 }, { "epoch": 73.11, "learning_rate": 4.144332810710649e-06, "loss": 0.0012, "step": 304390 }, { "epoch": 73.11, "learning_rate": 4.142544372475226e-06, "loss": 0.001, "step": 304400 }, { "epoch": 73.12, "learning_rate": 4.140756303536225e-06, "loss": 0.0011, "step": 304410 }, { "epoch": 73.12, "learning_rate": 4.13896860390805e-06, "loss": 0.001, "step": 304420 }, { "epoch": 73.12, "learning_rate": 4.137181273605084e-06, "loss": 0.001, "step": 304430 }, { "epoch": 73.12, "learning_rate": 4.1353943126417324e-06, "loss": 0.0016, "step": 304440 }, { "epoch": 73.13, "learning_rate": 4.133607721032384e-06, "loss": 0.0012, "step": 304450 }, { "epoch": 73.13, "learning_rate": 4.131821498791422e-06, "loss": 0.0024, "step": 304460 }, { "epoch": 73.13, "learning_rate": 4.130035645933239e-06, "loss": 0.001, "step": 304470 }, { "epoch": 73.13, "learning_rate": 4.128250162472208e-06, "loss": 0.0021, "step": 304480 }, { "epoch": 73.14, "learning_rate": 4.1264650484227e-06, "loss": 0.0011, "step": 304490 }, { "epoch": 73.14, "learning_rate": 4.124680303799117e-06, "loss": 0.0011, "step": 304500 }, { "epoch": 73.14, "learning_rate": 4.122895928615822e-06, "loss": 0.0011, "step": 304510 }, { "epoch": 73.14, "learning_rate": 4.121111922887161e-06, "loss": 0.0009, "step": 304520 }, { "epoch": 73.14, "learning_rate": 4.119328286627533e-06, "loss": 0.0011, "step": 304530 }, { "epoch": 73.15, "learning_rate": 4.117545019851282e-06, "loss": 0.0009, "step": 304540 }, { "epoch": 73.15, "learning_rate": 4.115762122572781e-06, "loss": 0.0009, "step": 304550 }, { "epoch": 73.15, "learning_rate": 4.113979594806377e-06, "loss": 0.001, "step": 304560 }, { "epoch": 73.15, "learning_rate": 4.112197436566434e-06, "loss": 0.0009, "step": 304570 }, { "epoch": 73.16, "learning_rate": 4.110415647867305e-06, "loss": 0.0011, "step": 304580 }, { "epoch": 73.16, "learning_rate": 4.108634228723318e-06, "loss": 0.001, "step": 304590 }, { "epoch": 73.16, "learning_rate": 4.106853179148856e-06, "loss": 0.0013, "step": 304600 }, { "epoch": 73.16, "learning_rate": 4.10507249915823e-06, "loss": 0.001, "step": 304610 }, { "epoch": 73.16, "learning_rate": 4.103292188765795e-06, "loss": 0.0011, "step": 304620 }, { "epoch": 73.17, "learning_rate": 4.101512247985872e-06, "loss": 0.0009, "step": 304630 }, { "epoch": 73.17, "learning_rate": 4.099732676832818e-06, "loss": 0.0009, "step": 304640 }, { "epoch": 73.17, "learning_rate": 4.097953475320965e-06, "loss": 0.0008, "step": 304650 }, { "epoch": 73.17, "learning_rate": 4.096174643464606e-06, "loss": 0.0013, "step": 304660 }, { "epoch": 73.18, "learning_rate": 4.094396181278104e-06, "loss": 0.001, "step": 304670 }, { "epoch": 73.18, "learning_rate": 4.092618088775768e-06, "loss": 0.001, "step": 304680 }, { "epoch": 73.18, "learning_rate": 4.090840365971915e-06, "loss": 0.0013, "step": 304690 }, { "epoch": 73.18, "learning_rate": 4.089063012880861e-06, "loss": 0.0032, "step": 304700 }, { "epoch": 73.19, "learning_rate": 4.087286029516924e-06, "loss": 0.0011, "step": 304710 }, { "epoch": 73.19, "learning_rate": 4.085509415894406e-06, "loss": 0.001, "step": 304720 }, { "epoch": 73.19, "learning_rate": 4.083733172027615e-06, "loss": 0.0009, "step": 304730 }, { "epoch": 73.19, "learning_rate": 4.081957297930866e-06, "loss": 0.0011, "step": 304740 }, { "epoch": 73.19, "learning_rate": 4.080181793618465e-06, "loss": 0.001, "step": 304750 }, { "epoch": 73.2, "learning_rate": 4.0784066591046834e-06, "loss": 0.0012, "step": 304760 }, { "epoch": 73.2, "learning_rate": 4.076631894403843e-06, "loss": 0.0011, "step": 304770 }, { "epoch": 73.2, "learning_rate": 4.074857499530221e-06, "loss": 0.001, "step": 304780 }, { "epoch": 73.2, "learning_rate": 4.073083474498113e-06, "loss": 0.0011, "step": 304790 }, { "epoch": 73.21, "learning_rate": 4.071309819321806e-06, "loss": 0.0012, "step": 304800 }, { "epoch": 73.21, "learning_rate": 4.069536534015583e-06, "loss": 0.001, "step": 304810 }, { "epoch": 73.21, "learning_rate": 4.067763618593717e-06, "loss": 0.001, "step": 304820 }, { "epoch": 73.21, "learning_rate": 4.065991073070491e-06, "loss": 0.001, "step": 304830 }, { "epoch": 73.22, "learning_rate": 4.064218897460192e-06, "loss": 0.001, "step": 304840 }, { "epoch": 73.22, "learning_rate": 4.0624470917770774e-06, "loss": 0.001, "step": 304850 }, { "epoch": 73.22, "learning_rate": 4.060675656035412e-06, "loss": 0.001, "step": 304860 }, { "epoch": 73.22, "learning_rate": 4.058904590249462e-06, "loss": 0.001, "step": 304870 }, { "epoch": 73.22, "learning_rate": 4.057133894433507e-06, "loss": 0.001, "step": 304880 }, { "epoch": 73.23, "learning_rate": 4.0553635686018e-06, "loss": 0.0021, "step": 304890 }, { "epoch": 73.23, "learning_rate": 4.0535936127685805e-06, "loss": 0.0016, "step": 304900 }, { "epoch": 73.23, "learning_rate": 4.05182402694812e-06, "loss": 0.0019, "step": 304910 }, { "epoch": 73.23, "learning_rate": 4.050054811154669e-06, "loss": 0.002, "step": 304920 }, { "epoch": 73.24, "learning_rate": 4.048285965402465e-06, "loss": 0.001, "step": 304930 }, { "epoch": 73.24, "learning_rate": 4.046517489705759e-06, "loss": 0.0009, "step": 304940 }, { "epoch": 73.24, "learning_rate": 4.044749384078794e-06, "loss": 0.0011, "step": 304950 }, { "epoch": 73.24, "learning_rate": 4.042981648535804e-06, "loss": 0.001, "step": 304960 }, { "epoch": 73.24, "learning_rate": 4.041214283091022e-06, "loss": 0.0011, "step": 304970 }, { "epoch": 73.25, "learning_rate": 4.039447287758702e-06, "loss": 0.0037, "step": 304980 }, { "epoch": 73.25, "learning_rate": 4.0376806625530505e-06, "loss": 0.0009, "step": 304990 }, { "epoch": 73.25, "learning_rate": 4.035914407488289e-06, "loss": 0.0009, "step": 305000 }, { "epoch": 73.25, "learning_rate": 4.034148522578668e-06, "loss": 0.0011, "step": 305010 }, { "epoch": 73.26, "learning_rate": 4.032383007838392e-06, "loss": 0.001, "step": 305020 }, { "epoch": 73.26, "learning_rate": 4.030617863281694e-06, "loss": 0.0012, "step": 305030 }, { "epoch": 73.26, "learning_rate": 4.0288530889227574e-06, "loss": 0.001, "step": 305040 }, { "epoch": 73.26, "learning_rate": 4.02708868477582e-06, "loss": 0.0009, "step": 305050 }, { "epoch": 73.27, "learning_rate": 4.025324650855089e-06, "loss": 0.0009, "step": 305060 }, { "epoch": 73.27, "learning_rate": 4.023560987174762e-06, "loss": 0.0012, "step": 305070 }, { "epoch": 73.27, "learning_rate": 4.021797693749052e-06, "loss": 0.001, "step": 305080 }, { "epoch": 73.27, "learning_rate": 4.020034770592146e-06, "loss": 0.001, "step": 305090 }, { "epoch": 73.27, "learning_rate": 4.01827221771825e-06, "loss": 0.001, "step": 305100 }, { "epoch": 73.28, "learning_rate": 4.0165100351415465e-06, "loss": 0.0009, "step": 305110 }, { "epoch": 73.28, "learning_rate": 4.014748222876258e-06, "loss": 0.0048, "step": 305120 }, { "epoch": 73.28, "learning_rate": 4.012986780936539e-06, "loss": 0.0013, "step": 305130 }, { "epoch": 73.28, "learning_rate": 4.011225709336574e-06, "loss": 0.001, "step": 305140 }, { "epoch": 73.29, "learning_rate": 4.009465008090569e-06, "loss": 0.0012, "step": 305150 }, { "epoch": 73.29, "learning_rate": 4.007704677212692e-06, "loss": 0.0012, "step": 305160 }, { "epoch": 73.29, "learning_rate": 4.005944716717119e-06, "loss": 0.001, "step": 305170 }, { "epoch": 73.29, "learning_rate": 4.004185126618027e-06, "loss": 0.002, "step": 305180 }, { "epoch": 73.3, "learning_rate": 4.002425906929574e-06, "loss": 0.001, "step": 305190 }, { "epoch": 73.3, "learning_rate": 4.0006670576659414e-06, "loss": 0.001, "step": 305200 }, { "epoch": 73.3, "learning_rate": 3.998908578841276e-06, "loss": 0.0012, "step": 305210 }, { "epoch": 73.3, "learning_rate": 3.9971504704697735e-06, "loss": 0.0009, "step": 305220 }, { "epoch": 73.3, "learning_rate": 3.995392732565556e-06, "loss": 0.0012, "step": 305230 }, { "epoch": 73.31, "learning_rate": 3.993635365142784e-06, "loss": 0.0009, "step": 305240 }, { "epoch": 73.31, "learning_rate": 3.991878368215623e-06, "loss": 0.0022, "step": 305250 }, { "epoch": 73.31, "learning_rate": 3.99012174179823e-06, "loss": 0.0008, "step": 305260 }, { "epoch": 73.31, "learning_rate": 3.988365485904733e-06, "loss": 0.0014, "step": 305270 }, { "epoch": 73.32, "learning_rate": 3.986609600549268e-06, "loss": 0.0018, "step": 305280 }, { "epoch": 73.32, "learning_rate": 3.984854085745998e-06, "loss": 0.0011, "step": 305290 }, { "epoch": 73.32, "learning_rate": 3.98309894150905e-06, "loss": 0.001, "step": 305300 }, { "epoch": 73.32, "learning_rate": 3.981344167852563e-06, "loss": 0.0018, "step": 305310 }, { "epoch": 73.32, "learning_rate": 3.979589764790659e-06, "loss": 0.0016, "step": 305320 }, { "epoch": 73.33, "learning_rate": 3.977835732337476e-06, "loss": 0.0011, "step": 305330 }, { "epoch": 73.33, "learning_rate": 3.976082070507137e-06, "loss": 0.0009, "step": 305340 }, { "epoch": 73.33, "learning_rate": 3.974328779313752e-06, "loss": 0.001, "step": 305350 }, { "epoch": 73.33, "learning_rate": 3.972575858771466e-06, "loss": 0.0011, "step": 305360 }, { "epoch": 73.34, "learning_rate": 3.970823308894378e-06, "loss": 0.001, "step": 305370 }, { "epoch": 73.34, "learning_rate": 3.969071129696594e-06, "loss": 0.0011, "step": 305380 }, { "epoch": 73.34, "learning_rate": 3.967319321192242e-06, "loss": 0.0031, "step": 305390 }, { "epoch": 73.34, "learning_rate": 3.9655678833954215e-06, "loss": 0.0011, "step": 305400 }, { "epoch": 73.35, "learning_rate": 3.963816816320243e-06, "loss": 0.0012, "step": 305410 }, { "epoch": 73.35, "learning_rate": 3.962066119980801e-06, "loss": 0.001, "step": 305420 }, { "epoch": 73.35, "learning_rate": 3.960315794391195e-06, "loss": 0.0009, "step": 305430 }, { "epoch": 73.35, "learning_rate": 3.958565839565526e-06, "loss": 0.0009, "step": 305440 }, { "epoch": 73.35, "learning_rate": 3.956816255517881e-06, "loss": 0.0012, "step": 305450 }, { "epoch": 73.36, "learning_rate": 3.95506704226235e-06, "loss": 0.0009, "step": 305460 }, { "epoch": 73.36, "learning_rate": 3.9533181998130216e-06, "loss": 0.0017, "step": 305470 }, { "epoch": 73.36, "learning_rate": 3.951569728183979e-06, "loss": 0.001, "step": 305480 }, { "epoch": 73.36, "learning_rate": 3.949821627389294e-06, "loss": 0.0011, "step": 305490 }, { "epoch": 73.37, "learning_rate": 3.948073897443072e-06, "loss": 0.0073, "step": 305500 }, { "epoch": 73.37, "learning_rate": 3.946326538359357e-06, "loss": 0.0009, "step": 305510 }, { "epoch": 73.37, "learning_rate": 3.944579550152228e-06, "loss": 0.0009, "step": 305520 }, { "epoch": 73.37, "learning_rate": 3.942832932835761e-06, "loss": 0.0011, "step": 305530 }, { "epoch": 73.38, "learning_rate": 3.941086686424023e-06, "loss": 0.001, "step": 305540 }, { "epoch": 73.38, "learning_rate": 3.939340810931069e-06, "loss": 0.0029, "step": 305550 }, { "epoch": 73.38, "learning_rate": 3.937595306370967e-06, "loss": 0.0013, "step": 305560 }, { "epoch": 73.38, "learning_rate": 3.935850172757771e-06, "loss": 0.0011, "step": 305570 }, { "epoch": 73.38, "learning_rate": 3.934105410105526e-06, "loss": 0.0009, "step": 305580 }, { "epoch": 73.39, "learning_rate": 3.9323610184282985e-06, "loss": 0.001, "step": 305590 }, { "epoch": 73.39, "learning_rate": 3.930616997740122e-06, "loss": 0.001, "step": 305600 }, { "epoch": 73.39, "learning_rate": 3.928873348055045e-06, "loss": 0.001, "step": 305610 }, { "epoch": 73.39, "learning_rate": 3.927130069387108e-06, "loss": 0.0012, "step": 305620 }, { "epoch": 73.4, "learning_rate": 3.92538716175036e-06, "loss": 0.0013, "step": 305630 }, { "epoch": 73.4, "learning_rate": 3.92364462515884e-06, "loss": 0.0012, "step": 305640 }, { "epoch": 73.4, "learning_rate": 3.921902459626553e-06, "loss": 0.0035, "step": 305650 }, { "epoch": 73.4, "learning_rate": 3.920160665167555e-06, "loss": 0.0011, "step": 305660 }, { "epoch": 73.4, "learning_rate": 3.918419241795862e-06, "loss": 0.0012, "step": 305670 }, { "epoch": 73.41, "learning_rate": 3.916678189525507e-06, "loss": 0.0016, "step": 305680 }, { "epoch": 73.41, "learning_rate": 3.914937508370498e-06, "loss": 0.0011, "step": 305690 }, { "epoch": 73.41, "learning_rate": 3.913197198344865e-06, "loss": 0.0013, "step": 305700 }, { "epoch": 73.41, "learning_rate": 3.9114572594626145e-06, "loss": 0.0012, "step": 305710 }, { "epoch": 73.42, "learning_rate": 3.909717691737763e-06, "loss": 0.0011, "step": 305720 }, { "epoch": 73.42, "learning_rate": 3.907978495184311e-06, "loss": 0.0011, "step": 305730 }, { "epoch": 73.42, "learning_rate": 3.906239669816286e-06, "loss": 0.0011, "step": 305740 }, { "epoch": 73.42, "learning_rate": 3.904501215647671e-06, "loss": 0.001, "step": 305750 }, { "epoch": 73.43, "learning_rate": 3.902763132692461e-06, "loss": 0.001, "step": 305760 }, { "epoch": 73.43, "learning_rate": 3.901025420964671e-06, "loss": 0.001, "step": 305770 }, { "epoch": 73.43, "learning_rate": 3.8992880804782975e-06, "loss": 0.0016, "step": 305780 }, { "epoch": 73.43, "learning_rate": 3.897551111247305e-06, "loss": 0.001, "step": 305790 }, { "epoch": 73.43, "learning_rate": 3.895814513285706e-06, "loss": 0.0011, "step": 305800 }, { "epoch": 73.44, "learning_rate": 3.8940782866074835e-06, "loss": 0.0011, "step": 305810 }, { "epoch": 73.44, "learning_rate": 3.892342431226604e-06, "loss": 0.0008, "step": 305820 }, { "epoch": 73.44, "learning_rate": 3.890606947157061e-06, "loss": 0.0011, "step": 305830 }, { "epoch": 73.44, "learning_rate": 3.888871834412827e-06, "loss": 0.0011, "step": 305840 }, { "epoch": 73.45, "learning_rate": 3.887137093007875e-06, "loss": 0.0011, "step": 305850 }, { "epoch": 73.45, "learning_rate": 3.885402722956166e-06, "loss": 0.0017, "step": 305860 }, { "epoch": 73.45, "learning_rate": 3.883668724271678e-06, "loss": 0.0009, "step": 305870 }, { "epoch": 73.45, "learning_rate": 3.881935096968387e-06, "loss": 0.0011, "step": 305880 }, { "epoch": 73.45, "learning_rate": 3.880201841060227e-06, "loss": 0.0011, "step": 305890 }, { "epoch": 73.46, "learning_rate": 3.878468956561165e-06, "loss": 0.0008, "step": 305900 }, { "epoch": 73.46, "learning_rate": 3.8767364434851625e-06, "loss": 0.001, "step": 305910 }, { "epoch": 73.46, "learning_rate": 3.8750043018461855e-06, "loss": 0.0009, "step": 305920 }, { "epoch": 73.46, "learning_rate": 3.873272531658146e-06, "loss": 0.0026, "step": 305930 }, { "epoch": 73.47, "learning_rate": 3.871541132935019e-06, "loss": 0.001, "step": 305940 }, { "epoch": 73.47, "learning_rate": 3.869810105690735e-06, "loss": 0.0009, "step": 305950 }, { "epoch": 73.47, "learning_rate": 3.868079449939243e-06, "loss": 0.001, "step": 305960 }, { "epoch": 73.47, "learning_rate": 3.866349165694477e-06, "loss": 0.0011, "step": 305970 }, { "epoch": 73.48, "learning_rate": 3.864619252970375e-06, "loss": 0.0017, "step": 305980 }, { "epoch": 73.48, "learning_rate": 3.862889711780854e-06, "loss": 0.0017, "step": 305990 }, { "epoch": 73.48, "learning_rate": 3.8611605421398525e-06, "loss": 0.0011, "step": 306000 }, { "epoch": 73.48, "learning_rate": 3.859431744061298e-06, "loss": 0.0012, "step": 306010 }, { "epoch": 73.48, "learning_rate": 3.857703317559119e-06, "loss": 0.001, "step": 306020 }, { "epoch": 73.49, "learning_rate": 3.855975262647205e-06, "loss": 0.0034, "step": 306030 }, { "epoch": 73.49, "learning_rate": 3.854247579339504e-06, "loss": 0.0009, "step": 306040 }, { "epoch": 73.49, "learning_rate": 3.852520267649923e-06, "loss": 0.001, "step": 306050 }, { "epoch": 73.49, "learning_rate": 3.850793327592361e-06, "loss": 0.0015, "step": 306060 }, { "epoch": 73.5, "learning_rate": 3.849066759180736e-06, "loss": 0.0013, "step": 306070 }, { "epoch": 73.5, "learning_rate": 3.847340562428942e-06, "loss": 0.0012, "step": 306080 }, { "epoch": 73.5, "learning_rate": 3.845614737350894e-06, "loss": 0.0012, "step": 306090 }, { "epoch": 73.5, "learning_rate": 3.843889283960467e-06, "loss": 0.0009, "step": 306100 }, { "epoch": 73.51, "learning_rate": 3.842164202271592e-06, "loss": 0.0009, "step": 306110 }, { "epoch": 73.51, "learning_rate": 3.840439492298131e-06, "loss": 0.0012, "step": 306120 }, { "epoch": 73.51, "learning_rate": 3.838715154053985e-06, "loss": 0.001, "step": 306130 }, { "epoch": 73.51, "learning_rate": 3.836991187553035e-06, "loss": 0.0009, "step": 306140 }, { "epoch": 73.51, "learning_rate": 3.835267592809172e-06, "loss": 0.0008, "step": 306150 }, { "epoch": 73.52, "learning_rate": 3.833544369836278e-06, "loss": 0.0011, "step": 306160 }, { "epoch": 73.52, "learning_rate": 3.8318215186482096e-06, "loss": 0.001, "step": 306170 }, { "epoch": 73.52, "learning_rate": 3.830099039258866e-06, "loss": 0.0014, "step": 306180 }, { "epoch": 73.52, "learning_rate": 3.82837693168211e-06, "loss": 0.0012, "step": 306190 }, { "epoch": 73.53, "learning_rate": 3.826655195931811e-06, "loss": 0.0012, "step": 306200 }, { "epoch": 73.53, "learning_rate": 3.824933832021827e-06, "loss": 0.0012, "step": 306210 }, { "epoch": 73.53, "learning_rate": 3.823212839966028e-06, "loss": 0.0013, "step": 306220 }, { "epoch": 73.53, "learning_rate": 3.821492219778272e-06, "loss": 0.0012, "step": 306230 }, { "epoch": 73.53, "learning_rate": 3.8197719714724075e-06, "loss": 0.0009, "step": 306240 }, { "epoch": 73.54, "learning_rate": 3.818052095062308e-06, "loss": 0.0011, "step": 306250 }, { "epoch": 73.54, "learning_rate": 3.816332590561806e-06, "loss": 0.0012, "step": 306260 }, { "epoch": 73.54, "learning_rate": 3.814613457984739e-06, "loss": 0.001, "step": 306270 }, { "epoch": 73.54, "learning_rate": 3.8128946973449818e-06, "loss": 0.001, "step": 306280 }, { "epoch": 73.55, "learning_rate": 3.8111763086563557e-06, "loss": 0.002, "step": 306290 }, { "epoch": 73.55, "learning_rate": 3.809458291932705e-06, "loss": 0.001, "step": 306300 }, { "epoch": 73.55, "learning_rate": 3.8077406471878627e-06, "loss": 0.0009, "step": 306310 }, { "epoch": 73.55, "learning_rate": 3.8060233744356633e-06, "loss": 0.001, "step": 306320 }, { "epoch": 73.56, "learning_rate": 3.8043064736899336e-06, "loss": 0.0009, "step": 306330 }, { "epoch": 73.56, "learning_rate": 3.8025899449645073e-06, "loss": 0.001, "step": 306340 }, { "epoch": 73.56, "learning_rate": 3.8008737882731958e-06, "loss": 0.0011, "step": 306350 }, { "epoch": 73.56, "learning_rate": 3.799158003629827e-06, "loss": 0.001, "step": 306360 }, { "epoch": 73.56, "learning_rate": 3.797442591048217e-06, "loss": 0.0012, "step": 306370 }, { "epoch": 73.57, "learning_rate": 3.7957275505421774e-06, "loss": 0.0014, "step": 306380 }, { "epoch": 73.57, "learning_rate": 3.794012882125525e-06, "loss": 0.005, "step": 306390 }, { "epoch": 73.57, "learning_rate": 3.7922985858120763e-06, "loss": 0.0011, "step": 306400 }, { "epoch": 73.57, "learning_rate": 3.7905846616156095e-06, "loss": 0.001, "step": 306410 }, { "epoch": 73.58, "learning_rate": 3.7888711095499518e-06, "loss": 0.0009, "step": 306420 }, { "epoch": 73.58, "learning_rate": 3.7871579296288983e-06, "loss": 0.001, "step": 306430 }, { "epoch": 73.58, "learning_rate": 3.785445121866238e-06, "loss": 0.0012, "step": 306440 }, { "epoch": 73.58, "learning_rate": 3.7837326862757703e-06, "loss": 0.0011, "step": 306450 }, { "epoch": 73.59, "learning_rate": 3.7820206228712797e-06, "loss": 0.0011, "step": 306460 }, { "epoch": 73.59, "learning_rate": 3.7803089316665653e-06, "loss": 0.001, "step": 306470 }, { "epoch": 73.59, "learning_rate": 3.7785976126753884e-06, "loss": 0.0014, "step": 306480 }, { "epoch": 73.59, "learning_rate": 3.7768866659115663e-06, "loss": 0.001, "step": 306490 }, { "epoch": 73.59, "learning_rate": 3.775176091388849e-06, "loss": 0.0011, "step": 306500 }, { "epoch": 73.6, "learning_rate": 3.773465889121014e-06, "loss": 0.0066, "step": 306510 }, { "epoch": 73.6, "learning_rate": 3.771756059121845e-06, "loss": 0.001, "step": 306520 }, { "epoch": 73.6, "learning_rate": 3.770046601405108e-06, "loss": 0.001, "step": 306530 }, { "epoch": 73.6, "learning_rate": 3.768337515984577e-06, "loss": 0.001, "step": 306540 }, { "epoch": 73.61, "learning_rate": 3.766628802873995e-06, "loss": 0.001, "step": 306550 }, { "epoch": 73.61, "learning_rate": 3.7649204620871348e-06, "loss": 0.0011, "step": 306560 }, { "epoch": 73.61, "learning_rate": 3.763212493637758e-06, "loss": 0.0009, "step": 306570 }, { "epoch": 73.61, "learning_rate": 3.7615048975396085e-06, "loss": 0.001, "step": 306580 }, { "epoch": 73.61, "learning_rate": 3.7597976738064477e-06, "loss": 0.0013, "step": 306590 }, { "epoch": 73.62, "learning_rate": 3.7580908224520204e-06, "loss": 0.0011, "step": 306600 }, { "epoch": 73.62, "learning_rate": 3.7563843434900715e-06, "loss": 0.0009, "step": 306610 }, { "epoch": 73.62, "learning_rate": 3.7546782369343337e-06, "loss": 0.0009, "step": 306620 }, { "epoch": 73.62, "learning_rate": 3.752972502798574e-06, "loss": 0.001, "step": 306630 }, { "epoch": 73.63, "learning_rate": 3.751267141096504e-06, "loss": 0.0011, "step": 306640 }, { "epoch": 73.63, "learning_rate": 3.749562151841857e-06, "loss": 0.0011, "step": 306650 }, { "epoch": 73.63, "learning_rate": 3.7478575350483825e-06, "loss": 0.001, "step": 306660 }, { "epoch": 73.63, "learning_rate": 3.7461532907297926e-06, "loss": 0.0013, "step": 306670 }, { "epoch": 73.64, "learning_rate": 3.7444494188998145e-06, "loss": 0.0014, "step": 306680 }, { "epoch": 73.64, "learning_rate": 3.7427459195721716e-06, "loss": 0.0011, "step": 306690 }, { "epoch": 73.64, "learning_rate": 3.7410427927605853e-06, "loss": 0.002, "step": 306700 }, { "epoch": 73.64, "learning_rate": 3.739340038478767e-06, "loss": 0.0012, "step": 306710 }, { "epoch": 73.64, "learning_rate": 3.7376376567404227e-06, "loss": 0.0018, "step": 306720 }, { "epoch": 73.65, "learning_rate": 3.73593564755928e-06, "loss": 0.0011, "step": 306730 }, { "epoch": 73.65, "learning_rate": 3.7342340109490336e-06, "loss": 0.0017, "step": 306740 }, { "epoch": 73.65, "learning_rate": 3.7325327469233784e-06, "loss": 0.0014, "step": 306750 }, { "epoch": 73.65, "learning_rate": 3.730831855496031e-06, "loss": 0.0009, "step": 306760 }, { "epoch": 73.66, "learning_rate": 3.729131336680691e-06, "loss": 0.0009, "step": 306770 }, { "epoch": 73.66, "learning_rate": 3.727431190491032e-06, "loss": 0.0011, "step": 306780 }, { "epoch": 73.66, "learning_rate": 3.725731416940753e-06, "loss": 0.001, "step": 306790 }, { "epoch": 73.66, "learning_rate": 3.7240320160435603e-06, "loss": 0.0013, "step": 306800 }, { "epoch": 73.67, "learning_rate": 3.722332987813121e-06, "loss": 0.0009, "step": 306810 }, { "epoch": 73.67, "learning_rate": 3.7206343322631287e-06, "loss": 0.001, "step": 306820 }, { "epoch": 73.67, "learning_rate": 3.718936049407251e-06, "loss": 0.0011, "step": 306830 }, { "epoch": 73.67, "learning_rate": 3.7172381392591715e-06, "loss": 0.001, "step": 306840 }, { "epoch": 73.67, "learning_rate": 3.715540601832568e-06, "loss": 0.0009, "step": 306850 }, { "epoch": 73.68, "learning_rate": 3.7138434371410956e-06, "loss": 0.001, "step": 306860 }, { "epoch": 73.68, "learning_rate": 3.7121466451984443e-06, "loss": 0.0019, "step": 306870 }, { "epoch": 73.68, "learning_rate": 3.7104502260182637e-06, "loss": 0.0011, "step": 306880 }, { "epoch": 73.68, "learning_rate": 3.70875417961421e-06, "loss": 0.0011, "step": 306890 }, { "epoch": 73.69, "learning_rate": 3.707058505999955e-06, "loss": 0.001, "step": 306900 }, { "epoch": 73.69, "learning_rate": 3.705363205189155e-06, "loss": 0.0021, "step": 306910 }, { "epoch": 73.69, "learning_rate": 3.7036682771954433e-06, "loss": 0.001, "step": 306920 }, { "epoch": 73.69, "learning_rate": 3.7019737220324922e-06, "loss": 0.0009, "step": 306930 }, { "epoch": 73.69, "learning_rate": 3.7002795397139357e-06, "loss": 0.001, "step": 306940 }, { "epoch": 73.7, "learning_rate": 3.698585730253423e-06, "loss": 0.001, "step": 306950 }, { "epoch": 73.7, "learning_rate": 3.696892293664589e-06, "loss": 0.0009, "step": 306960 }, { "epoch": 73.7, "learning_rate": 3.6951992299610773e-06, "loss": 0.0013, "step": 306970 }, { "epoch": 73.7, "learning_rate": 3.693506539156516e-06, "loss": 0.0013, "step": 306980 }, { "epoch": 73.71, "learning_rate": 3.691814221264539e-06, "loss": 0.0014, "step": 306990 }, { "epoch": 73.71, "learning_rate": 3.690122276298769e-06, "loss": 0.0012, "step": 307000 }, { "epoch": 73.71, "learning_rate": 3.688430704272855e-06, "loss": 0.0044, "step": 307010 }, { "epoch": 73.71, "learning_rate": 3.6867395052003926e-06, "loss": 0.0014, "step": 307020 }, { "epoch": 73.72, "learning_rate": 3.6850486790950044e-06, "loss": 0.0009, "step": 307030 }, { "epoch": 73.72, "learning_rate": 3.683358225970318e-06, "loss": 0.0033, "step": 307040 }, { "epoch": 73.72, "learning_rate": 3.6816681458399448e-06, "loss": 0.0024, "step": 307050 }, { "epoch": 73.72, "learning_rate": 3.6799784387174905e-06, "loss": 0.0009, "step": 307060 }, { "epoch": 73.72, "learning_rate": 3.678289104616567e-06, "loss": 0.0008, "step": 307070 }, { "epoch": 73.73, "learning_rate": 3.6766001435507792e-06, "loss": 0.0009, "step": 307080 }, { "epoch": 73.73, "learning_rate": 3.674911555533722e-06, "loss": 0.001, "step": 307090 }, { "epoch": 73.73, "learning_rate": 3.6732233405789964e-06, "loss": 0.0011, "step": 307100 }, { "epoch": 73.73, "learning_rate": 3.6715354987002016e-06, "loss": 0.0018, "step": 307110 }, { "epoch": 73.74, "learning_rate": 3.6698480299109272e-06, "loss": 0.001, "step": 307120 }, { "epoch": 73.74, "learning_rate": 3.6681609342247516e-06, "loss": 0.0009, "step": 307130 }, { "epoch": 73.74, "learning_rate": 3.666474211655285e-06, "loss": 0.001, "step": 307140 }, { "epoch": 73.74, "learning_rate": 3.6647878622161012e-06, "loss": 0.0011, "step": 307150 }, { "epoch": 73.75, "learning_rate": 3.663101885920767e-06, "loss": 0.0011, "step": 307160 }, { "epoch": 73.75, "learning_rate": 3.661416282782876e-06, "loss": 0.001, "step": 307170 }, { "epoch": 73.75, "learning_rate": 3.6597310528159954e-06, "loss": 0.0023, "step": 307180 }, { "epoch": 73.75, "learning_rate": 3.658046196033704e-06, "loss": 0.0009, "step": 307190 }, { "epoch": 73.75, "learning_rate": 3.6563617124495575e-06, "loss": 0.001, "step": 307200 }, { "epoch": 73.76, "learning_rate": 3.6546776020771336e-06, "loss": 0.0013, "step": 307210 }, { "epoch": 73.76, "learning_rate": 3.6529938649299877e-06, "loss": 0.001, "step": 307220 }, { "epoch": 73.76, "learning_rate": 3.651310501021682e-06, "loss": 0.001, "step": 307230 }, { "epoch": 73.76, "learning_rate": 3.6496275103657664e-06, "loss": 0.0009, "step": 307240 }, { "epoch": 73.77, "learning_rate": 3.6479448929758074e-06, "loss": 0.0013, "step": 307250 }, { "epoch": 73.77, "learning_rate": 3.6462626488653396e-06, "loss": 0.0009, "step": 307260 }, { "epoch": 73.77, "learning_rate": 3.644580778047918e-06, "loss": 0.001, "step": 307270 }, { "epoch": 73.77, "learning_rate": 3.6428992805370877e-06, "loss": 0.0009, "step": 307280 }, { "epoch": 73.77, "learning_rate": 3.6412181563464045e-06, "loss": 0.0009, "step": 307290 }, { "epoch": 73.78, "learning_rate": 3.6395374054893683e-06, "loss": 0.001, "step": 307300 }, { "epoch": 73.78, "learning_rate": 3.637857027979552e-06, "loss": 0.001, "step": 307310 }, { "epoch": 73.78, "learning_rate": 3.636177023830473e-06, "loss": 0.0012, "step": 307320 }, { "epoch": 73.78, "learning_rate": 3.634497393055658e-06, "loss": 0.0009, "step": 307330 }, { "epoch": 73.79, "learning_rate": 3.6328181356686364e-06, "loss": 0.0015, "step": 307340 }, { "epoch": 73.79, "learning_rate": 3.6311392516829356e-06, "loss": 0.0034, "step": 307350 }, { "epoch": 73.79, "learning_rate": 3.629460741112073e-06, "loss": 0.0012, "step": 307360 }, { "epoch": 73.79, "learning_rate": 3.627782603969554e-06, "loss": 0.0011, "step": 307370 }, { "epoch": 73.8, "learning_rate": 3.6261048402689068e-06, "loss": 0.0033, "step": 307380 }, { "epoch": 73.8, "learning_rate": 3.624427450023654e-06, "loss": 0.001, "step": 307390 }, { "epoch": 73.8, "learning_rate": 3.6227504332472794e-06, "loss": 0.0009, "step": 307400 }, { "epoch": 73.8, "learning_rate": 3.621073789953294e-06, "loss": 0.0011, "step": 307410 }, { "epoch": 73.8, "learning_rate": 3.61939752015521e-06, "loss": 0.0082, "step": 307420 }, { "epoch": 73.81, "learning_rate": 3.617721623866527e-06, "loss": 0.001, "step": 307430 }, { "epoch": 73.81, "learning_rate": 3.616046101100723e-06, "loss": 0.001, "step": 307440 }, { "epoch": 73.81, "learning_rate": 3.61437095187131e-06, "loss": 0.0009, "step": 307450 }, { "epoch": 73.81, "learning_rate": 3.612696176191771e-06, "loss": 0.0009, "step": 307460 }, { "epoch": 73.82, "learning_rate": 3.6110217740755903e-06, "loss": 0.0011, "step": 307470 }, { "epoch": 73.82, "learning_rate": 3.6093477455362623e-06, "loss": 0.0013, "step": 307480 }, { "epoch": 73.82, "learning_rate": 3.6076740905872543e-06, "loss": 0.001, "step": 307490 }, { "epoch": 73.82, "learning_rate": 3.606000809242055e-06, "loss": 0.0028, "step": 307500 }, { "epoch": 73.83, "learning_rate": 3.604327901514132e-06, "loss": 0.0013, "step": 307510 }, { "epoch": 73.83, "learning_rate": 3.6026553674169683e-06, "loss": 0.0011, "step": 307520 }, { "epoch": 73.83, "learning_rate": 3.6009832069640313e-06, "loss": 0.0013, "step": 307530 }, { "epoch": 73.83, "learning_rate": 3.599311420168766e-06, "loss": 0.001, "step": 307540 }, { "epoch": 73.83, "learning_rate": 3.5976400070446616e-06, "loss": 0.0012, "step": 307550 }, { "epoch": 73.84, "learning_rate": 3.595968967605168e-06, "loss": 0.0011, "step": 307560 }, { "epoch": 73.84, "learning_rate": 3.5942983018637467e-06, "loss": 0.0009, "step": 307570 }, { "epoch": 73.84, "learning_rate": 3.592628009833843e-06, "loss": 0.001, "step": 307580 }, { "epoch": 73.84, "learning_rate": 3.5909580915289176e-06, "loss": 0.0011, "step": 307590 }, { "epoch": 73.85, "learning_rate": 3.5892885469624105e-06, "loss": 0.0012, "step": 307600 }, { "epoch": 73.85, "learning_rate": 3.5876193761477604e-06, "loss": 0.0012, "step": 307610 }, { "epoch": 73.85, "learning_rate": 3.585950579098435e-06, "loss": 0.001, "step": 307620 }, { "epoch": 73.85, "learning_rate": 3.5842821558278505e-06, "loss": 0.001, "step": 307630 }, { "epoch": 73.85, "learning_rate": 3.5826141063494523e-06, "loss": 0.001, "step": 307640 }, { "epoch": 73.86, "learning_rate": 3.580946430676663e-06, "loss": 0.0011, "step": 307650 }, { "epoch": 73.86, "learning_rate": 3.5792791288229267e-06, "loss": 0.001, "step": 307660 }, { "epoch": 73.86, "learning_rate": 3.5776122008016723e-06, "loss": 0.001, "step": 307670 }, { "epoch": 73.86, "learning_rate": 3.5759456466262997e-06, "loss": 0.0043, "step": 307680 }, { "epoch": 73.87, "learning_rate": 3.5742794663102543e-06, "loss": 0.001, "step": 307690 }, { "epoch": 73.87, "learning_rate": 3.5726136598669467e-06, "loss": 0.0013, "step": 307700 }, { "epoch": 73.87, "learning_rate": 3.570948227309795e-06, "loss": 0.001, "step": 307710 }, { "epoch": 73.87, "learning_rate": 3.5692831686521986e-06, "loss": 0.001, "step": 307720 }, { "epoch": 73.88, "learning_rate": 3.567618483907581e-06, "loss": 0.0028, "step": 307730 }, { "epoch": 73.88, "learning_rate": 3.565954173089342e-06, "loss": 0.0026, "step": 307740 }, { "epoch": 73.88, "learning_rate": 3.564290236210871e-06, "loss": 0.0012, "step": 307750 }, { "epoch": 73.88, "learning_rate": 3.562626673285602e-06, "loss": 0.001, "step": 307760 }, { "epoch": 73.88, "learning_rate": 3.560963484326907e-06, "loss": 0.0009, "step": 307770 }, { "epoch": 73.89, "learning_rate": 3.55930066934817e-06, "loss": 0.0008, "step": 307780 }, { "epoch": 73.89, "learning_rate": 3.5576382283628086e-06, "loss": 0.0015, "step": 307790 }, { "epoch": 73.89, "learning_rate": 3.555976161384195e-06, "loss": 0.0008, "step": 307800 }, { "epoch": 73.89, "learning_rate": 3.554314468425729e-06, "loss": 0.001, "step": 307810 }, { "epoch": 73.9, "learning_rate": 3.552653149500762e-06, "loss": 0.0012, "step": 307820 }, { "epoch": 73.9, "learning_rate": 3.5509922046226997e-06, "loss": 0.001, "step": 307830 }, { "epoch": 73.9, "learning_rate": 3.5493316338049086e-06, "loss": 0.0009, "step": 307840 }, { "epoch": 73.9, "learning_rate": 3.5476714370607623e-06, "loss": 0.0011, "step": 307850 }, { "epoch": 73.91, "learning_rate": 3.546011614403633e-06, "loss": 0.0009, "step": 307860 }, { "epoch": 73.91, "learning_rate": 3.544352165846887e-06, "loss": 0.001, "step": 307870 }, { "epoch": 73.91, "learning_rate": 3.542693091403887e-06, "loss": 0.0016, "step": 307880 }, { "epoch": 73.91, "learning_rate": 3.541034391087983e-06, "loss": 0.0017, "step": 307890 }, { "epoch": 73.91, "learning_rate": 3.5393760649125585e-06, "loss": 0.0024, "step": 307900 }, { "epoch": 73.92, "learning_rate": 3.5377181128909475e-06, "loss": 0.0011, "step": 307910 }, { "epoch": 73.92, "learning_rate": 3.5360605350365008e-06, "loss": 0.0012, "step": 307920 }, { "epoch": 73.92, "learning_rate": 3.5344033313625736e-06, "loss": 0.0028, "step": 307930 }, { "epoch": 73.92, "learning_rate": 3.532746501882517e-06, "loss": 0.0009, "step": 307940 }, { "epoch": 73.93, "learning_rate": 3.53109004660967e-06, "loss": 0.0009, "step": 307950 }, { "epoch": 73.93, "learning_rate": 3.529433965557366e-06, "loss": 0.0009, "step": 307960 }, { "epoch": 73.93, "learning_rate": 3.5277782587389452e-06, "loss": 0.0012, "step": 307970 }, { "epoch": 73.93, "learning_rate": 3.5261229261677464e-06, "loss": 0.0009, "step": 307980 }, { "epoch": 73.93, "learning_rate": 3.524467967857087e-06, "loss": 0.0011, "step": 307990 }, { "epoch": 73.94, "learning_rate": 3.522813383820317e-06, "loss": 0.0015, "step": 308000 }, { "epoch": 73.94, "learning_rate": 3.521159174070737e-06, "loss": 0.001, "step": 308010 }, { "epoch": 73.94, "learning_rate": 3.519505338621676e-06, "loss": 0.001, "step": 308020 }, { "epoch": 73.94, "learning_rate": 3.5178518774864612e-06, "loss": 0.0011, "step": 308030 }, { "epoch": 73.95, "learning_rate": 3.5161987906784043e-06, "loss": 0.0012, "step": 308040 }, { "epoch": 73.95, "learning_rate": 3.514546078210823e-06, "loss": 0.0011, "step": 308050 }, { "epoch": 73.95, "learning_rate": 3.512893740097001e-06, "loss": 0.0012, "step": 308060 }, { "epoch": 74.0, "learning_rate": 3.5112417763502768e-06, "loss": 0.0009, "step": 308070 }, { "epoch": 74.0, "learning_rate": 3.5095901869839355e-06, "loss": 0.0009, "step": 308080 }, { "epoch": 74.01, "learning_rate": 3.507938972011288e-06, "loss": 0.0037, "step": 308090 }, { "epoch": 74.01, "learning_rate": 3.5062881314456232e-06, "loss": 0.0009, "step": 308100 }, { "epoch": 74.01, "learning_rate": 3.5046376653002423e-06, "loss": 0.0009, "step": 308110 }, { "epoch": 74.01, "learning_rate": 3.5029875735884286e-06, "loss": 0.001, "step": 308120 }, { "epoch": 74.02, "learning_rate": 3.501337856323472e-06, "loss": 0.0012, "step": 308130 }, { "epoch": 74.02, "learning_rate": 3.499688513518673e-06, "loss": 0.0008, "step": 308140 }, { "epoch": 74.02, "learning_rate": 3.4980395451872985e-06, "loss": 0.0013, "step": 308150 }, { "epoch": 74.02, "learning_rate": 3.4963909513426206e-06, "loss": 0.0013, "step": 308160 }, { "epoch": 74.02, "learning_rate": 3.4947427319979355e-06, "loss": 0.0009, "step": 308170 }, { "epoch": 74.03, "learning_rate": 3.4930948871665036e-06, "loss": 0.0014, "step": 308180 }, { "epoch": 74.03, "learning_rate": 3.4914474168616042e-06, "loss": 0.001, "step": 308190 }, { "epoch": 74.03, "learning_rate": 3.489800321096498e-06, "loss": 0.0011, "step": 308200 }, { "epoch": 74.03, "learning_rate": 3.4881535998844526e-06, "loss": 0.0011, "step": 308210 }, { "epoch": 74.04, "learning_rate": 3.4865072532387243e-06, "loss": 0.0012, "step": 308220 }, { "epoch": 74.04, "learning_rate": 3.48486128117258e-06, "loss": 0.0011, "step": 308230 }, { "epoch": 74.04, "learning_rate": 3.483215683699265e-06, "loss": 0.0009, "step": 308240 }, { "epoch": 74.04, "learning_rate": 3.4815704608320344e-06, "loss": 0.0012, "step": 308250 }, { "epoch": 74.05, "learning_rate": 3.479925612584145e-06, "loss": 0.0009, "step": 308260 }, { "epoch": 74.05, "learning_rate": 3.478281138968825e-06, "loss": 0.0008, "step": 308270 }, { "epoch": 74.05, "learning_rate": 3.4766370399993474e-06, "loss": 0.0014, "step": 308280 }, { "epoch": 74.05, "learning_rate": 3.4749933156889234e-06, "loss": 0.001, "step": 308290 }, { "epoch": 74.05, "learning_rate": 3.4733499660507983e-06, "loss": 0.0011, "step": 308300 }, { "epoch": 74.06, "learning_rate": 3.471706991098217e-06, "loss": 0.001, "step": 308310 }, { "epoch": 74.06, "learning_rate": 3.470064390844402e-06, "loss": 0.001, "step": 308320 }, { "epoch": 74.06, "learning_rate": 3.4684221653025817e-06, "loss": 0.0071, "step": 308330 }, { "epoch": 74.06, "learning_rate": 3.4667803144859787e-06, "loss": 0.001, "step": 308340 }, { "epoch": 74.07, "learning_rate": 3.465138838407822e-06, "loss": 0.0012, "step": 308350 }, { "epoch": 74.07, "learning_rate": 3.4634977370813225e-06, "loss": 0.001, "step": 308360 }, { "epoch": 74.07, "learning_rate": 3.461857010519698e-06, "loss": 0.001, "step": 308370 }, { "epoch": 74.07, "learning_rate": 3.4602166587361762e-06, "loss": 0.0017, "step": 308380 }, { "epoch": 74.07, "learning_rate": 3.4585766817439522e-06, "loss": 0.002, "step": 308390 }, { "epoch": 74.08, "learning_rate": 3.456937079556222e-06, "loss": 0.0016, "step": 308400 }, { "epoch": 74.08, "learning_rate": 3.455297852186212e-06, "loss": 0.0011, "step": 308410 }, { "epoch": 74.08, "learning_rate": 3.453658999647125e-06, "loss": 0.001, "step": 308420 }, { "epoch": 74.08, "learning_rate": 3.452020521952132e-06, "loss": 0.0015, "step": 308430 }, { "epoch": 74.09, "learning_rate": 3.4503824191144506e-06, "loss": 0.0011, "step": 308440 }, { "epoch": 74.09, "learning_rate": 3.4487446911472653e-06, "loss": 0.001, "step": 308450 }, { "epoch": 74.09, "learning_rate": 3.447107338063765e-06, "loss": 0.001, "step": 308460 }, { "epoch": 74.09, "learning_rate": 3.44547035987714e-06, "loss": 0.0024, "step": 308470 }, { "epoch": 74.1, "learning_rate": 3.4438337566005675e-06, "loss": 0.0009, "step": 308480 }, { "epoch": 74.1, "learning_rate": 3.4421975282472262e-06, "loss": 0.0009, "step": 308490 }, { "epoch": 74.1, "learning_rate": 3.4405616748303005e-06, "loss": 0.0009, "step": 308500 }, { "epoch": 74.1, "learning_rate": 3.4389261963629515e-06, "loss": 0.0011, "step": 308510 }, { "epoch": 74.1, "learning_rate": 3.437291092858369e-06, "loss": 0.0009, "step": 308520 }, { "epoch": 74.11, "learning_rate": 3.435656364329709e-06, "loss": 0.001, "step": 308530 }, { "epoch": 74.11, "learning_rate": 3.434022010790122e-06, "loss": 0.0009, "step": 308540 }, { "epoch": 74.11, "learning_rate": 3.432388032252798e-06, "loss": 0.001, "step": 308550 }, { "epoch": 74.11, "learning_rate": 3.4307544287308866e-06, "loss": 0.001, "step": 308560 }, { "epoch": 74.12, "learning_rate": 3.429121200237523e-06, "loss": 0.0011, "step": 308570 }, { "epoch": 74.12, "learning_rate": 3.4274883467858845e-06, "loss": 0.0009, "step": 308580 }, { "epoch": 74.12, "learning_rate": 3.425855868389116e-06, "loss": 0.001, "step": 308590 }, { "epoch": 74.12, "learning_rate": 3.4242237650603527e-06, "loss": 0.0013, "step": 308600 }, { "epoch": 74.13, "learning_rate": 3.422592036812755e-06, "loss": 0.001, "step": 308610 }, { "epoch": 74.13, "learning_rate": 3.4209606836594466e-06, "loss": 0.0012, "step": 308620 }, { "epoch": 74.13, "learning_rate": 3.419329705613572e-06, "loss": 0.001, "step": 308630 }, { "epoch": 74.13, "learning_rate": 3.4176991026882653e-06, "loss": 0.001, "step": 308640 }, { "epoch": 74.13, "learning_rate": 3.4160688748966608e-06, "loss": 0.0009, "step": 308650 }, { "epoch": 74.14, "learning_rate": 3.4144390222518917e-06, "loss": 0.0008, "step": 308660 }, { "epoch": 74.14, "learning_rate": 3.412809544767065e-06, "loss": 0.0011, "step": 308670 }, { "epoch": 74.14, "learning_rate": 3.4111804424553196e-06, "loss": 0.0009, "step": 308680 }, { "epoch": 74.14, "learning_rate": 3.409551715329773e-06, "loss": 0.0011, "step": 308690 }, { "epoch": 74.15, "learning_rate": 3.407923363403537e-06, "loss": 0.0011, "step": 308700 }, { "epoch": 74.15, "learning_rate": 3.4062953866897287e-06, "loss": 0.001, "step": 308710 }, { "epoch": 74.15, "learning_rate": 3.404667785201454e-06, "loss": 0.0009, "step": 308720 }, { "epoch": 74.15, "learning_rate": 3.4030405589518256e-06, "loss": 0.0011, "step": 308730 }, { "epoch": 74.15, "learning_rate": 3.4014137079539433e-06, "loss": 0.0008, "step": 308740 }, { "epoch": 74.16, "learning_rate": 3.3997872322209078e-06, "loss": 0.0011, "step": 308750 }, { "epoch": 74.16, "learning_rate": 3.3981611317658203e-06, "loss": 0.0018, "step": 308760 }, { "epoch": 74.16, "learning_rate": 3.3965354066017753e-06, "loss": 0.0012, "step": 308770 }, { "epoch": 74.16, "learning_rate": 3.3949100567418513e-06, "loss": 0.0039, "step": 308780 }, { "epoch": 74.17, "learning_rate": 3.393285082199166e-06, "loss": 0.001, "step": 308790 }, { "epoch": 74.17, "learning_rate": 3.391660482986797e-06, "loss": 0.001, "step": 308800 }, { "epoch": 74.17, "learning_rate": 3.3900362591178016e-06, "loss": 0.0008, "step": 308810 }, { "epoch": 74.17, "learning_rate": 3.3884124106052905e-06, "loss": 0.001, "step": 308820 }, { "epoch": 74.18, "learning_rate": 3.3867889374623317e-06, "loss": 0.0009, "step": 308830 }, { "epoch": 74.18, "learning_rate": 3.3851658397019926e-06, "loss": 0.001, "step": 308840 }, { "epoch": 74.18, "learning_rate": 3.383543117337351e-06, "loss": 0.001, "step": 308850 }, { "epoch": 74.18, "learning_rate": 3.3819207703814693e-06, "loss": 0.001, "step": 308860 }, { "epoch": 74.18, "learning_rate": 3.3802987988474143e-06, "loss": 0.0017, "step": 308870 }, { "epoch": 74.19, "learning_rate": 3.378677202748248e-06, "loss": 0.0018, "step": 308880 }, { "epoch": 74.19, "learning_rate": 3.3770559820970437e-06, "loss": 0.0009, "step": 308890 }, { "epoch": 74.19, "learning_rate": 3.375435136906835e-06, "loss": 0.0019, "step": 308900 }, { "epoch": 74.19, "learning_rate": 3.3738146671906834e-06, "loss": 0.0047, "step": 308910 }, { "epoch": 74.2, "learning_rate": 3.3721945729616343e-06, "loss": 0.0009, "step": 308920 }, { "epoch": 74.2, "learning_rate": 3.3705748542327443e-06, "loss": 0.001, "step": 308930 }, { "epoch": 74.2, "learning_rate": 3.3689555110170634e-06, "loss": 0.0011, "step": 308940 }, { "epoch": 74.2, "learning_rate": 3.367336543327604e-06, "loss": 0.0022, "step": 308950 }, { "epoch": 74.21, "learning_rate": 3.365717951177433e-06, "loss": 0.0012, "step": 308960 }, { "epoch": 74.21, "learning_rate": 3.3640997345795677e-06, "loss": 0.0011, "step": 308970 }, { "epoch": 74.21, "learning_rate": 3.362481893547048e-06, "loss": 0.0011, "step": 308980 }, { "epoch": 74.21, "learning_rate": 3.3608644280929026e-06, "loss": 0.001, "step": 308990 }, { "epoch": 74.21, "learning_rate": 3.3592473382301536e-06, "loss": 0.0009, "step": 309000 }, { "epoch": 74.22, "learning_rate": 3.3576306239718247e-06, "loss": 0.0013, "step": 309010 }, { "epoch": 74.22, "learning_rate": 3.3560142853309275e-06, "loss": 0.0012, "step": 309020 }, { "epoch": 74.22, "learning_rate": 3.3543983223204957e-06, "loss": 0.001, "step": 309030 }, { "epoch": 74.22, "learning_rate": 3.352782734953541e-06, "loss": 0.0009, "step": 309040 }, { "epoch": 74.23, "learning_rate": 3.3511675232430483e-06, "loss": 0.0009, "step": 309050 }, { "epoch": 74.23, "learning_rate": 3.3495526872020564e-06, "loss": 0.0009, "step": 309060 }, { "epoch": 74.23, "learning_rate": 3.3479382268435556e-06, "loss": 0.0011, "step": 309070 }, { "epoch": 74.23, "learning_rate": 3.346324142180551e-06, "loss": 0.002, "step": 309080 }, { "epoch": 74.23, "learning_rate": 3.3447104332260337e-06, "loss": 0.0009, "step": 309090 }, { "epoch": 74.24, "learning_rate": 3.343097099993009e-06, "loss": 0.0009, "step": 309100 }, { "epoch": 74.24, "learning_rate": 3.3414841424944665e-06, "loss": 0.0009, "step": 309110 }, { "epoch": 74.24, "learning_rate": 3.3398715607433796e-06, "loss": 0.0009, "step": 309120 }, { "epoch": 74.24, "learning_rate": 3.338259354752771e-06, "loss": 0.0011, "step": 309130 }, { "epoch": 74.25, "learning_rate": 3.336647524535591e-06, "loss": 0.0011, "step": 309140 }, { "epoch": 74.25, "learning_rate": 3.33503607010483e-06, "loss": 0.001, "step": 309150 }, { "epoch": 74.25, "learning_rate": 3.3334249914734603e-06, "loss": 0.0029, "step": 309160 }, { "epoch": 74.25, "learning_rate": 3.331814288654467e-06, "loss": 0.0009, "step": 309170 }, { "epoch": 74.26, "learning_rate": 3.3302039616608273e-06, "loss": 0.0033, "step": 309180 }, { "epoch": 74.26, "learning_rate": 3.328594010505481e-06, "loss": 0.0009, "step": 309190 }, { "epoch": 74.26, "learning_rate": 3.3269844352014135e-06, "loss": 0.0009, "step": 309200 }, { "epoch": 74.26, "learning_rate": 3.3253752357615906e-06, "loss": 0.0009, "step": 309210 }, { "epoch": 74.26, "learning_rate": 3.323766412198964e-06, "loss": 0.001, "step": 309220 }, { "epoch": 74.27, "learning_rate": 3.32215796452649e-06, "loss": 0.0009, "step": 309230 }, { "epoch": 74.27, "learning_rate": 3.3205498927571186e-06, "loss": 0.0015, "step": 309240 }, { "epoch": 74.27, "learning_rate": 3.318942196903807e-06, "loss": 0.001, "step": 309250 }, { "epoch": 74.27, "learning_rate": 3.317334876979489e-06, "loss": 0.0012, "step": 309260 }, { "epoch": 74.28, "learning_rate": 3.315727932997137e-06, "loss": 0.0011, "step": 309270 }, { "epoch": 74.28, "learning_rate": 3.3141213649696636e-06, "loss": 0.0011, "step": 309280 }, { "epoch": 74.28, "learning_rate": 3.3125151729100078e-06, "loss": 0.0029, "step": 309290 }, { "epoch": 74.28, "learning_rate": 3.310909356831121e-06, "loss": 0.0009, "step": 309300 }, { "epoch": 74.29, "learning_rate": 3.309303916745926e-06, "loss": 0.0011, "step": 309310 }, { "epoch": 74.29, "learning_rate": 3.3076988526673626e-06, "loss": 0.0009, "step": 309320 }, { "epoch": 74.29, "learning_rate": 3.3060941646083255e-06, "loss": 0.0014, "step": 309330 }, { "epoch": 74.29, "learning_rate": 3.3044898525817714e-06, "loss": 0.0024, "step": 309340 }, { "epoch": 74.29, "learning_rate": 3.3028859166006064e-06, "loss": 0.0012, "step": 309350 }, { "epoch": 74.3, "learning_rate": 3.3012823566777483e-06, "loss": 0.0012, "step": 309360 }, { "epoch": 74.3, "learning_rate": 3.299679172826109e-06, "loss": 0.0009, "step": 309370 }, { "epoch": 74.3, "learning_rate": 3.2980763650586053e-06, "loss": 0.0016, "step": 309380 }, { "epoch": 74.3, "learning_rate": 3.2964739333881333e-06, "loss": 0.0009, "step": 309390 }, { "epoch": 74.31, "learning_rate": 3.2948718778276045e-06, "loss": 0.0011, "step": 309400 }, { "epoch": 74.31, "learning_rate": 3.2932701983899307e-06, "loss": 0.001, "step": 309410 }, { "epoch": 74.31, "learning_rate": 3.2916688950879903e-06, "loss": 0.0009, "step": 309420 }, { "epoch": 74.31, "learning_rate": 3.2900679679346848e-06, "loss": 0.001, "step": 309430 }, { "epoch": 74.31, "learning_rate": 3.2884674169429195e-06, "loss": 0.0009, "step": 309440 }, { "epoch": 74.32, "learning_rate": 3.286867242125574e-06, "loss": 0.0013, "step": 309450 }, { "epoch": 74.32, "learning_rate": 3.285267443495538e-06, "loss": 0.001, "step": 309460 }, { "epoch": 74.32, "learning_rate": 3.283668021065689e-06, "loss": 0.0008, "step": 309470 }, { "epoch": 74.32, "learning_rate": 3.282068974848912e-06, "loss": 0.0013, "step": 309480 }, { "epoch": 74.33, "learning_rate": 3.28047030485808e-06, "loss": 0.0013, "step": 309490 }, { "epoch": 74.33, "learning_rate": 3.2788720111060658e-06, "loss": 0.0041, "step": 309500 }, { "epoch": 74.33, "learning_rate": 3.2772740936057644e-06, "loss": 0.0011, "step": 309510 }, { "epoch": 74.33, "learning_rate": 3.275676552370016e-06, "loss": 0.0009, "step": 309520 }, { "epoch": 74.34, "learning_rate": 3.2740793874116826e-06, "loss": 0.0011, "step": 309530 }, { "epoch": 74.34, "learning_rate": 3.272482598743648e-06, "loss": 0.0008, "step": 309540 }, { "epoch": 74.34, "learning_rate": 3.270886186378769e-06, "loss": 0.0012, "step": 309550 }, { "epoch": 74.34, "learning_rate": 3.2692901503298954e-06, "loss": 0.001, "step": 309560 }, { "epoch": 74.34, "learning_rate": 3.267694490609868e-06, "loss": 0.0009, "step": 309570 }, { "epoch": 74.35, "learning_rate": 3.2660992072315544e-06, "loss": 0.0011, "step": 309580 }, { "epoch": 74.35, "learning_rate": 3.2645043002077935e-06, "loss": 0.0012, "step": 309590 }, { "epoch": 74.35, "learning_rate": 3.2629097695514365e-06, "loss": 0.001, "step": 309600 }, { "epoch": 74.35, "learning_rate": 3.261315615275318e-06, "loss": 0.0011, "step": 309610 }, { "epoch": 74.36, "learning_rate": 3.259721837392277e-06, "loss": 0.001, "step": 309620 }, { "epoch": 74.36, "learning_rate": 3.2581284359151476e-06, "loss": 0.0029, "step": 309630 }, { "epoch": 74.36, "learning_rate": 3.256535410856759e-06, "loss": 0.0009, "step": 309640 }, { "epoch": 74.36, "learning_rate": 3.2549427622299566e-06, "loss": 0.001, "step": 309650 }, { "epoch": 74.37, "learning_rate": 3.2533504900475463e-06, "loss": 0.0011, "step": 309660 }, { "epoch": 74.37, "learning_rate": 3.251758594322352e-06, "loss": 0.0011, "step": 309670 }, { "epoch": 74.37, "learning_rate": 3.2501670750672065e-06, "loss": 0.0011, "step": 309680 }, { "epoch": 74.37, "learning_rate": 3.248575932294917e-06, "loss": 0.001, "step": 309690 }, { "epoch": 74.37, "learning_rate": 3.2469851660183016e-06, "loss": 0.001, "step": 309700 }, { "epoch": 74.38, "learning_rate": 3.245394776250171e-06, "loss": 0.001, "step": 309710 }, { "epoch": 74.38, "learning_rate": 3.243804763003333e-06, "loss": 0.0009, "step": 309720 }, { "epoch": 74.38, "learning_rate": 3.2422151262905874e-06, "loss": 0.0013, "step": 309730 }, { "epoch": 74.38, "learning_rate": 3.2406258661247412e-06, "loss": 0.001, "step": 309740 }, { "epoch": 74.39, "learning_rate": 3.239036982518584e-06, "loss": 0.0011, "step": 309750 }, { "epoch": 74.39, "learning_rate": 3.237448475484922e-06, "loss": 0.001, "step": 309760 }, { "epoch": 74.39, "learning_rate": 3.2358603450365455e-06, "loss": 0.0009, "step": 309770 }, { "epoch": 74.39, "learning_rate": 3.2342725911862328e-06, "loss": 0.001, "step": 309780 }, { "epoch": 74.39, "learning_rate": 3.2326852139467957e-06, "loss": 0.0012, "step": 309790 }, { "epoch": 74.4, "learning_rate": 3.231098213330991e-06, "loss": 0.001, "step": 309800 }, { "epoch": 74.4, "learning_rate": 3.2295115893516027e-06, "loss": 0.0027, "step": 309810 }, { "epoch": 74.4, "learning_rate": 3.2279253420214205e-06, "loss": 0.0011, "step": 309820 }, { "epoch": 74.4, "learning_rate": 3.2263394713532124e-06, "loss": 0.0011, "step": 309830 }, { "epoch": 74.41, "learning_rate": 3.2247539773597512e-06, "loss": 0.0031, "step": 309840 }, { "epoch": 74.41, "learning_rate": 3.2231688600538044e-06, "loss": 0.0009, "step": 309850 }, { "epoch": 74.41, "learning_rate": 3.22158411944814e-06, "loss": 0.0012, "step": 309860 }, { "epoch": 74.41, "learning_rate": 3.219999755555514e-06, "loss": 0.0009, "step": 309870 }, { "epoch": 74.42, "learning_rate": 3.2184157683886827e-06, "loss": 0.0011, "step": 309880 }, { "epoch": 74.42, "learning_rate": 3.21683215796042e-06, "loss": 0.0022, "step": 309890 }, { "epoch": 74.42, "learning_rate": 3.2152489242834593e-06, "loss": 0.001, "step": 309900 }, { "epoch": 74.42, "learning_rate": 3.213666067370552e-06, "loss": 0.001, "step": 309910 }, { "epoch": 74.42, "learning_rate": 3.2120835872344545e-06, "loss": 0.0011, "step": 309920 }, { "epoch": 74.43, "learning_rate": 3.2105014838879235e-06, "loss": 0.001, "step": 309930 }, { "epoch": 74.43, "learning_rate": 3.208919757343659e-06, "loss": 0.001, "step": 309940 }, { "epoch": 74.43, "learning_rate": 3.2073384076144354e-06, "loss": 0.0009, "step": 309950 }, { "epoch": 74.43, "learning_rate": 3.205757434712975e-06, "loss": 0.0013, "step": 309960 }, { "epoch": 74.44, "learning_rate": 3.2041768386520123e-06, "loss": 0.0013, "step": 309970 }, { "epoch": 74.44, "learning_rate": 3.2025966194442757e-06, "loss": 0.0009, "step": 309980 }, { "epoch": 74.44, "learning_rate": 3.2010167771024835e-06, "loss": 0.0011, "step": 309990 }, { "epoch": 74.44, "learning_rate": 3.1994373116393694e-06, "loss": 0.001, "step": 310000 }, { "epoch": 74.45, "learning_rate": 3.197858223067646e-06, "loss": 0.0011, "step": 310010 }, { "epoch": 74.45, "learning_rate": 3.1962795114000245e-06, "loss": 0.0014, "step": 310020 }, { "epoch": 74.45, "learning_rate": 3.1947011766492394e-06, "loss": 0.001, "step": 310030 }, { "epoch": 74.45, "learning_rate": 3.193123218827981e-06, "loss": 0.0011, "step": 310040 }, { "epoch": 74.45, "learning_rate": 3.191545637948956e-06, "loss": 0.0014, "step": 310050 }, { "epoch": 74.46, "learning_rate": 3.1899684340248816e-06, "loss": 0.0012, "step": 310060 }, { "epoch": 74.46, "learning_rate": 3.188391607068464e-06, "loss": 0.001, "step": 310070 }, { "epoch": 74.46, "learning_rate": 3.1868151570923765e-06, "loss": 0.001, "step": 310080 }, { "epoch": 74.46, "learning_rate": 3.185239084109337e-06, "loss": 0.0009, "step": 310090 }, { "epoch": 74.47, "learning_rate": 3.18366338813203e-06, "loss": 0.0011, "step": 310100 }, { "epoch": 74.47, "learning_rate": 3.1820880691731448e-06, "loss": 0.0017, "step": 310110 }, { "epoch": 74.47, "learning_rate": 3.1805131272453716e-06, "loss": 0.0011, "step": 310120 }, { "epoch": 74.47, "learning_rate": 3.1789385623613833e-06, "loss": 0.001, "step": 310130 }, { "epoch": 74.47, "learning_rate": 3.17736437453387e-06, "loss": 0.0017, "step": 310140 }, { "epoch": 74.48, "learning_rate": 3.1757905637754992e-06, "loss": 0.0009, "step": 310150 }, { "epoch": 74.48, "learning_rate": 3.174217130098961e-06, "loss": 0.0019, "step": 310160 }, { "epoch": 74.48, "learning_rate": 3.172644073516917e-06, "loss": 0.0017, "step": 310170 }, { "epoch": 74.48, "learning_rate": 3.1710713940420355e-06, "loss": 0.0011, "step": 310180 }, { "epoch": 74.49, "learning_rate": 3.169499091686967e-06, "loss": 0.0019, "step": 310190 }, { "epoch": 74.49, "learning_rate": 3.1679271664644018e-06, "loss": 0.0019, "step": 310200 }, { "epoch": 74.49, "learning_rate": 3.1663556183869793e-06, "loss": 0.0012, "step": 310210 }, { "epoch": 74.49, "learning_rate": 3.164784447467367e-06, "loss": 0.0009, "step": 310220 }, { "epoch": 74.5, "learning_rate": 3.1632136537182055e-06, "loss": 0.0009, "step": 310230 }, { "epoch": 74.5, "learning_rate": 3.161643237152151e-06, "loss": 0.0033, "step": 310240 }, { "epoch": 74.5, "learning_rate": 3.1600731977818543e-06, "loss": 0.001, "step": 310250 }, { "epoch": 74.5, "learning_rate": 3.15850353561995e-06, "loss": 0.001, "step": 310260 }, { "epoch": 74.5, "learning_rate": 3.156934250679089e-06, "loss": 0.001, "step": 310270 }, { "epoch": 74.51, "learning_rate": 3.1553653429718997e-06, "loss": 0.001, "step": 310280 }, { "epoch": 74.51, "learning_rate": 3.1537968125110117e-06, "loss": 0.0011, "step": 310290 }, { "epoch": 74.51, "learning_rate": 3.1522286593090755e-06, "loss": 0.001, "step": 310300 }, { "epoch": 74.51, "learning_rate": 3.150660883378714e-06, "loss": 0.0009, "step": 310310 }, { "epoch": 74.52, "learning_rate": 3.1490934847325405e-06, "loss": 0.0012, "step": 310320 }, { "epoch": 74.52, "learning_rate": 3.147526463383188e-06, "loss": 0.0009, "step": 310330 }, { "epoch": 74.52, "learning_rate": 3.1459598193432695e-06, "loss": 0.0009, "step": 310340 }, { "epoch": 74.52, "learning_rate": 3.144393552625413e-06, "loss": 0.0009, "step": 310350 }, { "epoch": 74.53, "learning_rate": 3.1428276632422204e-06, "loss": 0.001, "step": 310360 }, { "epoch": 74.53, "learning_rate": 3.1412621512063033e-06, "loss": 0.0012, "step": 310370 }, { "epoch": 74.53, "learning_rate": 3.1396970165302743e-06, "loss": 0.001, "step": 310380 }, { "epoch": 74.53, "learning_rate": 3.138132259226728e-06, "loss": 0.0011, "step": 310390 }, { "epoch": 74.53, "learning_rate": 3.136567879308283e-06, "loss": 0.001, "step": 310400 }, { "epoch": 74.54, "learning_rate": 3.1350038767875235e-06, "loss": 0.0017, "step": 310410 }, { "epoch": 74.54, "learning_rate": 3.1334402516770444e-06, "loss": 0.0012, "step": 310420 }, { "epoch": 74.54, "learning_rate": 3.1318770039894363e-06, "loss": 0.0012, "step": 310430 }, { "epoch": 74.54, "learning_rate": 3.1303141337373e-06, "loss": 0.0016, "step": 310440 }, { "epoch": 74.55, "learning_rate": 3.1287516409332252e-06, "loss": 0.001, "step": 310450 }, { "epoch": 74.55, "learning_rate": 3.1271895255897686e-06, "loss": 0.0011, "step": 310460 }, { "epoch": 74.55, "learning_rate": 3.1256277877195315e-06, "loss": 0.001, "step": 310470 }, { "epoch": 74.55, "learning_rate": 3.1240664273350817e-06, "loss": 0.0009, "step": 310480 }, { "epoch": 74.55, "learning_rate": 3.1225054444490033e-06, "loss": 0.001, "step": 310490 }, { "epoch": 74.56, "learning_rate": 3.120944839073858e-06, "loss": 0.0008, "step": 310500 }, { "epoch": 74.56, "learning_rate": 3.1193846112222148e-06, "loss": 0.0012, "step": 310510 }, { "epoch": 74.56, "learning_rate": 3.1178247609066404e-06, "loss": 0.0009, "step": 310520 }, { "epoch": 74.56, "learning_rate": 3.116265288139686e-06, "loss": 0.001, "step": 310530 }, { "epoch": 74.57, "learning_rate": 3.1147061929339305e-06, "loss": 0.0011, "step": 310540 }, { "epoch": 74.57, "learning_rate": 3.113147475301925e-06, "loss": 0.0016, "step": 310550 }, { "epoch": 74.57, "learning_rate": 3.1115891352561987e-06, "loss": 0.0011, "step": 310560 }, { "epoch": 74.57, "learning_rate": 3.11003117280933e-06, "loss": 0.0009, "step": 310570 }, { "epoch": 74.58, "learning_rate": 3.1084735879738537e-06, "loss": 0.0009, "step": 310580 }, { "epoch": 74.58, "learning_rate": 3.1069163807623093e-06, "loss": 0.001, "step": 310590 }, { "epoch": 74.58, "learning_rate": 3.1053595511872424e-06, "loss": 0.001, "step": 310600 }, { "epoch": 74.58, "learning_rate": 3.1038030992611934e-06, "loss": 0.0012, "step": 310610 }, { "epoch": 74.58, "learning_rate": 3.1022470249966906e-06, "loss": 0.001, "step": 310620 }, { "epoch": 74.59, "learning_rate": 3.1006913284062634e-06, "loss": 0.0012, "step": 310630 }, { "epoch": 74.59, "learning_rate": 3.0991360095024512e-06, "loss": 0.0018, "step": 310640 }, { "epoch": 74.59, "learning_rate": 3.097581068297767e-06, "loss": 0.0008, "step": 310650 }, { "epoch": 74.59, "learning_rate": 3.0960265048047386e-06, "loss": 0.001, "step": 310660 }, { "epoch": 74.6, "learning_rate": 3.094472319035874e-06, "loss": 0.0009, "step": 310670 }, { "epoch": 74.6, "learning_rate": 3.0929185110037117e-06, "loss": 0.0029, "step": 310680 }, { "epoch": 74.6, "learning_rate": 3.091365080720754e-06, "loss": 0.0011, "step": 310690 }, { "epoch": 74.6, "learning_rate": 3.0898120281995013e-06, "loss": 0.001, "step": 310700 }, { "epoch": 74.61, "learning_rate": 3.088259353452472e-06, "loss": 0.0009, "step": 310710 }, { "epoch": 74.61, "learning_rate": 3.086707056492166e-06, "loss": 0.001, "step": 310720 }, { "epoch": 74.61, "learning_rate": 3.085155137331086e-06, "loss": 0.0011, "step": 310730 }, { "epoch": 74.61, "learning_rate": 3.0836035959817324e-06, "loss": 0.001, "step": 310740 }, { "epoch": 74.61, "learning_rate": 3.0820524324565892e-06, "loss": 0.0012, "step": 310750 }, { "epoch": 74.62, "learning_rate": 3.0805016467681634e-06, "loss": 0.0009, "step": 310760 }, { "epoch": 74.62, "learning_rate": 3.0789512389289233e-06, "loss": 0.0011, "step": 310770 }, { "epoch": 74.62, "learning_rate": 3.0774012089513803e-06, "loss": 0.0009, "step": 310780 }, { "epoch": 74.62, "learning_rate": 3.0758515568479974e-06, "loss": 0.0015, "step": 310790 }, { "epoch": 74.63, "learning_rate": 3.074302282631253e-06, "loss": 0.0009, "step": 310800 }, { "epoch": 74.63, "learning_rate": 3.072753386313637e-06, "loss": 0.001, "step": 310810 }, { "epoch": 74.63, "learning_rate": 3.0712048679076177e-06, "loss": 0.0011, "step": 310820 }, { "epoch": 74.63, "learning_rate": 3.0696567274256737e-06, "loss": 0.0009, "step": 310830 }, { "epoch": 74.63, "learning_rate": 3.0681089648802453e-06, "loss": 0.0009, "step": 310840 }, { "epoch": 74.64, "learning_rate": 3.0665615802838276e-06, "loss": 0.0012, "step": 310850 }, { "epoch": 74.64, "learning_rate": 3.0650145736488612e-06, "loss": 0.0025, "step": 310860 }, { "epoch": 74.64, "learning_rate": 3.063467944987819e-06, "loss": 0.0011, "step": 310870 }, { "epoch": 74.64, "learning_rate": 3.061921694313147e-06, "loss": 0.0013, "step": 310880 }, { "epoch": 74.65, "learning_rate": 3.0603758216373015e-06, "loss": 0.0011, "step": 310890 }, { "epoch": 74.65, "learning_rate": 3.058830326972728e-06, "loss": 0.001, "step": 310900 }, { "epoch": 74.65, "learning_rate": 3.057285210331862e-06, "loss": 0.001, "step": 310910 }, { "epoch": 74.65, "learning_rate": 3.055740471727181e-06, "loss": 0.001, "step": 310920 }, { "epoch": 74.66, "learning_rate": 3.0541961111710925e-06, "loss": 0.0012, "step": 310930 }, { "epoch": 74.66, "learning_rate": 3.052652128676037e-06, "loss": 0.0011, "step": 310940 }, { "epoch": 74.66, "learning_rate": 3.0511085242544647e-06, "loss": 0.0011, "step": 310950 }, { "epoch": 74.66, "learning_rate": 3.0495652979187938e-06, "loss": 0.0011, "step": 310960 }, { "epoch": 74.66, "learning_rate": 3.048022449681459e-06, "loss": 0.0008, "step": 310970 }, { "epoch": 74.67, "learning_rate": 3.0464799795548835e-06, "loss": 0.0011, "step": 310980 }, { "epoch": 74.67, "learning_rate": 3.04493788755148e-06, "loss": 0.001, "step": 310990 }, { "epoch": 74.67, "learning_rate": 3.043396173683677e-06, "loss": 0.0011, "step": 311000 }, { "epoch": 74.67, "learning_rate": 3.041854837963881e-06, "loss": 0.0009, "step": 311010 }, { "epoch": 74.68, "learning_rate": 3.040313880404527e-06, "loss": 0.0012, "step": 311020 }, { "epoch": 74.68, "learning_rate": 3.038773301018e-06, "loss": 0.0011, "step": 311030 }, { "epoch": 74.68, "learning_rate": 3.037233099816705e-06, "loss": 0.0009, "step": 311040 }, { "epoch": 74.68, "learning_rate": 3.0356932768130675e-06, "loss": 0.0011, "step": 311050 }, { "epoch": 74.69, "learning_rate": 3.0341538320194817e-06, "loss": 0.001, "step": 311060 }, { "epoch": 74.69, "learning_rate": 3.032614765448333e-06, "loss": 0.0011, "step": 311070 }, { "epoch": 74.69, "learning_rate": 3.0310760771120104e-06, "loss": 0.0009, "step": 311080 }, { "epoch": 74.69, "learning_rate": 3.0295377670229273e-06, "loss": 0.0014, "step": 311090 }, { "epoch": 74.69, "learning_rate": 3.027999835193457e-06, "loss": 0.001, "step": 311100 }, { "epoch": 74.7, "learning_rate": 3.0264622816359943e-06, "loss": 0.0011, "step": 311110 }, { "epoch": 74.7, "learning_rate": 3.0249251063629137e-06, "loss": 0.0012, "step": 311120 }, { "epoch": 74.7, "learning_rate": 3.0233883093865934e-06, "loss": 0.001, "step": 311130 }, { "epoch": 74.7, "learning_rate": 3.021851890719418e-06, "loss": 0.0012, "step": 311140 }, { "epoch": 74.71, "learning_rate": 3.020315850373745e-06, "loss": 0.001, "step": 311150 }, { "epoch": 74.71, "learning_rate": 3.0187801883619693e-06, "loss": 0.0014, "step": 311160 }, { "epoch": 74.71, "learning_rate": 3.0172449046964368e-06, "loss": 0.0013, "step": 311170 }, { "epoch": 74.71, "learning_rate": 3.0157099993895044e-06, "loss": 0.0009, "step": 311180 }, { "epoch": 74.71, "learning_rate": 3.014175472453562e-06, "loss": 0.0013, "step": 311190 }, { "epoch": 74.72, "learning_rate": 3.0126413239009443e-06, "loss": 0.0009, "step": 311200 }, { "epoch": 74.72, "learning_rate": 3.0111075537440194e-06, "loss": 0.0032, "step": 311210 }, { "epoch": 74.72, "learning_rate": 3.0095741619951266e-06, "loss": 0.0012, "step": 311220 }, { "epoch": 74.72, "learning_rate": 3.008041148666624e-06, "loss": 0.0011, "step": 311230 }, { "epoch": 74.73, "learning_rate": 3.0065085137708506e-06, "loss": 0.0033, "step": 311240 }, { "epoch": 74.73, "learning_rate": 3.0049762573201524e-06, "loss": 0.0011, "step": 311250 }, { "epoch": 74.73, "learning_rate": 3.0034443793268697e-06, "loss": 0.0029, "step": 311260 }, { "epoch": 74.73, "learning_rate": 3.0019128798033424e-06, "loss": 0.0011, "step": 311270 }, { "epoch": 74.74, "learning_rate": 3.0003817587618945e-06, "loss": 0.0027, "step": 311280 }, { "epoch": 74.74, "learning_rate": 2.998851016214854e-06, "loss": 0.0009, "step": 311290 }, { "epoch": 74.74, "learning_rate": 2.997320652174568e-06, "loss": 0.0013, "step": 311300 }, { "epoch": 74.74, "learning_rate": 2.995790666653342e-06, "loss": 0.001, "step": 311310 }, { "epoch": 74.74, "learning_rate": 2.9942610596634946e-06, "loss": 0.0015, "step": 311320 }, { "epoch": 74.75, "learning_rate": 2.9927318312173657e-06, "loss": 0.001, "step": 311330 }, { "epoch": 74.75, "learning_rate": 2.991202981327251e-06, "loss": 0.001, "step": 311340 }, { "epoch": 74.75, "learning_rate": 2.989674510005469e-06, "loss": 0.001, "step": 311350 }, { "epoch": 74.75, "learning_rate": 2.9881464172643314e-06, "loss": 0.001, "step": 311360 }, { "epoch": 74.76, "learning_rate": 2.9866187031161398e-06, "loss": 0.001, "step": 311370 }, { "epoch": 74.76, "learning_rate": 2.985091367573195e-06, "loss": 0.0014, "step": 311380 }, { "epoch": 74.76, "learning_rate": 2.9835644106478044e-06, "loss": 0.0009, "step": 311390 }, { "epoch": 74.76, "learning_rate": 2.982037832352258e-06, "loss": 0.001, "step": 311400 }, { "epoch": 74.77, "learning_rate": 2.9805116326988568e-06, "loss": 0.0012, "step": 311410 }, { "epoch": 74.77, "learning_rate": 2.9789858116998746e-06, "loss": 0.0011, "step": 311420 }, { "epoch": 74.77, "learning_rate": 2.977460369367624e-06, "loss": 0.0009, "step": 311430 }, { "epoch": 74.77, "learning_rate": 2.975935305714378e-06, "loss": 0.0011, "step": 311440 }, { "epoch": 74.77, "learning_rate": 2.974410620752405e-06, "loss": 0.0012, "step": 311450 }, { "epoch": 74.78, "learning_rate": 2.9728863144940058e-06, "loss": 0.0012, "step": 311460 }, { "epoch": 74.78, "learning_rate": 2.971362386951437e-06, "loss": 0.001, "step": 311470 }, { "epoch": 74.78, "learning_rate": 2.96983883813699e-06, "loss": 0.001, "step": 311480 }, { "epoch": 74.78, "learning_rate": 2.9683156680629156e-06, "loss": 0.0009, "step": 311490 }, { "epoch": 74.79, "learning_rate": 2.966792876741492e-06, "loss": 0.001, "step": 311500 }, { "epoch": 74.79, "learning_rate": 2.9652704641849825e-06, "loss": 0.001, "step": 311510 }, { "epoch": 74.79, "learning_rate": 2.9637484304056384e-06, "loss": 0.001, "step": 311520 }, { "epoch": 74.79, "learning_rate": 2.962226775415716e-06, "loss": 0.0038, "step": 311530 }, { "epoch": 74.79, "learning_rate": 2.9607054992274898e-06, "loss": 0.0011, "step": 311540 }, { "epoch": 74.8, "learning_rate": 2.959184601853188e-06, "loss": 0.0009, "step": 311550 }, { "epoch": 74.8, "learning_rate": 2.957664083305062e-06, "loss": 0.0009, "step": 311560 }, { "epoch": 74.8, "learning_rate": 2.956143943595363e-06, "loss": 0.0017, "step": 311570 }, { "epoch": 74.8, "learning_rate": 2.9546241827363485e-06, "loss": 0.0011, "step": 311580 }, { "epoch": 74.81, "learning_rate": 2.9531048007402198e-06, "loss": 0.0011, "step": 311590 }, { "epoch": 74.81, "learning_rate": 2.9515857976192386e-06, "loss": 0.0012, "step": 311600 }, { "epoch": 74.81, "learning_rate": 2.95006717338564e-06, "loss": 0.0012, "step": 311610 }, { "epoch": 74.81, "learning_rate": 2.948548928051642e-06, "loss": 0.001, "step": 311620 }, { "epoch": 74.82, "learning_rate": 2.947031061629474e-06, "loss": 0.0008, "step": 311630 }, { "epoch": 74.82, "learning_rate": 2.945513574131359e-06, "loss": 0.0008, "step": 311640 }, { "epoch": 74.82, "learning_rate": 2.943996465569526e-06, "loss": 0.001, "step": 311650 }, { "epoch": 74.82, "learning_rate": 2.942479735956172e-06, "loss": 0.0053, "step": 311660 }, { "epoch": 74.82, "learning_rate": 2.9409633853035355e-06, "loss": 0.0011, "step": 311670 }, { "epoch": 74.83, "learning_rate": 2.9394474136238246e-06, "loss": 0.0009, "step": 311680 }, { "epoch": 74.83, "learning_rate": 2.937931820929235e-06, "loss": 0.0012, "step": 311690 }, { "epoch": 74.83, "learning_rate": 2.9364166072319733e-06, "loss": 0.0013, "step": 311700 }, { "epoch": 74.83, "learning_rate": 2.9349017725442463e-06, "loss": 0.0012, "step": 311710 }, { "epoch": 74.84, "learning_rate": 2.9333873168782667e-06, "loss": 0.0017, "step": 311720 }, { "epoch": 74.84, "learning_rate": 2.9318732402461966e-06, "loss": 0.0028, "step": 311730 }, { "epoch": 74.84, "learning_rate": 2.9303595426602604e-06, "loss": 0.0015, "step": 311740 }, { "epoch": 74.84, "learning_rate": 2.9288462241326362e-06, "loss": 0.001, "step": 311750 }, { "epoch": 74.85, "learning_rate": 2.927333284675515e-06, "loss": 0.0013, "step": 311760 }, { "epoch": 74.85, "learning_rate": 2.925820724301076e-06, "loss": 0.0012, "step": 311770 }, { "epoch": 74.85, "learning_rate": 2.924308543021498e-06, "loss": 0.001, "step": 311780 }, { "epoch": 74.85, "learning_rate": 2.9227967408489653e-06, "loss": 0.001, "step": 311790 }, { "epoch": 74.85, "learning_rate": 2.9212853177956412e-06, "loss": 0.001, "step": 311800 }, { "epoch": 74.86, "learning_rate": 2.9197742738737155e-06, "loss": 0.001, "step": 311810 }, { "epoch": 74.86, "learning_rate": 2.9182636090953565e-06, "loss": 0.0012, "step": 311820 }, { "epoch": 74.86, "learning_rate": 2.916753323472704e-06, "loss": 0.0009, "step": 311830 }, { "epoch": 74.86, "learning_rate": 2.9152434170179434e-06, "loss": 0.0015, "step": 311840 }, { "epoch": 74.87, "learning_rate": 2.9137338897432254e-06, "loss": 0.0011, "step": 311850 }, { "epoch": 74.87, "learning_rate": 2.912224741660713e-06, "loss": 0.0009, "step": 311860 }, { "epoch": 74.87, "learning_rate": 2.910715972782557e-06, "loss": 0.001, "step": 311870 }, { "epoch": 74.87, "learning_rate": 2.9092075831209043e-06, "loss": 0.0011, "step": 311880 }, { "epoch": 74.87, "learning_rate": 2.9076995726879e-06, "loss": 0.0012, "step": 311890 }, { "epoch": 74.88, "learning_rate": 2.9061919414956897e-06, "loss": 0.0009, "step": 311900 }, { "epoch": 74.88, "learning_rate": 2.904684689556436e-06, "loss": 0.0012, "step": 311910 }, { "epoch": 74.88, "learning_rate": 2.9031778168822466e-06, "loss": 0.0016, "step": 311920 }, { "epoch": 74.88, "learning_rate": 2.9016713234852664e-06, "loss": 0.0022, "step": 311930 }, { "epoch": 74.89, "learning_rate": 2.9001652093776256e-06, "loss": 0.0011, "step": 311940 }, { "epoch": 74.89, "learning_rate": 2.8986594745714635e-06, "loss": 0.0011, "step": 311950 }, { "epoch": 74.89, "learning_rate": 2.897154119078904e-06, "loss": 0.0011, "step": 311960 }, { "epoch": 74.89, "learning_rate": 2.8956491429120546e-06, "loss": 0.0009, "step": 311970 }, { "epoch": 74.9, "learning_rate": 2.8941445460830494e-06, "loss": 0.0008, "step": 311980 }, { "epoch": 74.9, "learning_rate": 2.8926403286040016e-06, "loss": 0.0012, "step": 311990 }, { "epoch": 74.9, "learning_rate": 2.8911364904870284e-06, "loss": 0.0024, "step": 312000 }, { "epoch": 74.9, "learning_rate": 2.8896330317442323e-06, "loss": 0.001, "step": 312010 }, { "epoch": 74.9, "learning_rate": 2.8881299523877303e-06, "loss": 0.0017, "step": 312020 }, { "epoch": 74.91, "learning_rate": 2.886627252429619e-06, "loss": 0.0014, "step": 312030 }, { "epoch": 74.91, "learning_rate": 2.885124931881994e-06, "loss": 0.0009, "step": 312040 }, { "epoch": 74.91, "learning_rate": 2.8836229907569844e-06, "loss": 0.0011, "step": 312050 }, { "epoch": 74.91, "learning_rate": 2.8821214290666475e-06, "loss": 0.001, "step": 312060 }, { "epoch": 74.92, "learning_rate": 2.8806202468230903e-06, "loss": 0.0009, "step": 312070 }, { "epoch": 74.92, "learning_rate": 2.879119444038408e-06, "loss": 0.0012, "step": 312080 }, { "epoch": 74.92, "learning_rate": 2.8776190207246813e-06, "loss": 0.001, "step": 312090 }, { "epoch": 74.92, "learning_rate": 2.8761189768940044e-06, "loss": 0.001, "step": 312100 }, { "epoch": 74.93, "learning_rate": 2.8746193125584354e-06, "loss": 0.0013, "step": 312110 }, { "epoch": 74.93, "learning_rate": 2.873120027730064e-06, "loss": 0.0012, "step": 312120 }, { "epoch": 74.93, "learning_rate": 2.8716211224209643e-06, "loss": 0.0009, "step": 312130 }, { "epoch": 74.93, "learning_rate": 2.87012259664321e-06, "loss": 0.0009, "step": 312140 }, { "epoch": 74.93, "learning_rate": 2.868624450408863e-06, "loss": 0.0011, "step": 312150 }, { "epoch": 74.94, "learning_rate": 2.867126683729987e-06, "loss": 0.0011, "step": 312160 }, { "epoch": 74.94, "learning_rate": 2.8656292966186548e-06, "loss": 0.001, "step": 312170 }, { "epoch": 74.94, "learning_rate": 2.8641322890869017e-06, "loss": 0.0009, "step": 312180 }, { "epoch": 74.94, "learning_rate": 2.862635661146812e-06, "loss": 0.0011, "step": 312190 }, { "epoch": 74.95, "learning_rate": 2.861139412810426e-06, "loss": 0.001, "step": 312200 }, { "epoch": 74.95, "learning_rate": 2.859643544089785e-06, "loss": 0.001, "step": 312210 }, { "epoch": 74.95, "learning_rate": 2.8581480549969453e-06, "loss": 0.001, "step": 312220 }, { "epoch": 75.0, "learning_rate": 2.856652945543947e-06, "loss": 0.0013, "step": 312230 }, { "epoch": 75.0, "learning_rate": 2.855158215742837e-06, "loss": 0.0011, "step": 312240 }, { "epoch": 75.01, "learning_rate": 2.853663865605638e-06, "loss": 0.0013, "step": 312250 }, { "epoch": 75.01, "learning_rate": 2.852169895144402e-06, "loss": 0.0011, "step": 312260 }, { "epoch": 75.01, "learning_rate": 2.8506763043711416e-06, "loss": 0.0008, "step": 312270 }, { "epoch": 75.01, "learning_rate": 2.8491830932978915e-06, "loss": 0.001, "step": 312280 }, { "epoch": 75.01, "learning_rate": 2.8476902619366973e-06, "loss": 0.0012, "step": 312290 }, { "epoch": 75.02, "learning_rate": 2.84619781029955e-06, "loss": 0.0012, "step": 312300 }, { "epoch": 75.02, "learning_rate": 2.844705738398479e-06, "loss": 0.0012, "step": 312310 }, { "epoch": 75.02, "learning_rate": 2.843214046245507e-06, "loss": 0.0017, "step": 312320 }, { "epoch": 75.02, "learning_rate": 2.8417227338526475e-06, "loss": 0.001, "step": 312330 }, { "epoch": 75.03, "learning_rate": 2.8402318012319074e-06, "loss": 0.0012, "step": 312340 }, { "epoch": 75.03, "learning_rate": 2.8387412483952825e-06, "loss": 0.0015, "step": 312350 }, { "epoch": 75.03, "learning_rate": 2.8372510753547853e-06, "loss": 0.001, "step": 312360 }, { "epoch": 75.03, "learning_rate": 2.8357612821224233e-06, "loss": 0.0009, "step": 312370 }, { "epoch": 75.04, "learning_rate": 2.834271868710181e-06, "loss": 0.001, "step": 312380 }, { "epoch": 75.04, "learning_rate": 2.83278283513006e-06, "loss": 0.0009, "step": 312390 }, { "epoch": 75.04, "learning_rate": 2.8312941813940565e-06, "loss": 0.001, "step": 312400 }, { "epoch": 75.04, "learning_rate": 2.8298059075141494e-06, "loss": 0.001, "step": 312410 }, { "epoch": 75.04, "learning_rate": 2.8283180135023178e-06, "loss": 0.0011, "step": 312420 }, { "epoch": 75.05, "learning_rate": 2.8268304993705697e-06, "loss": 0.0009, "step": 312430 }, { "epoch": 75.05, "learning_rate": 2.8253433651308615e-06, "loss": 0.0011, "step": 312440 }, { "epoch": 75.05, "learning_rate": 2.8238566107951726e-06, "loss": 0.001, "step": 312450 }, { "epoch": 75.05, "learning_rate": 2.8223702363754824e-06, "loss": 0.0013, "step": 312460 }, { "epoch": 75.06, "learning_rate": 2.820884241883759e-06, "loss": 0.0017, "step": 312470 }, { "epoch": 75.06, "learning_rate": 2.819398627331965e-06, "loss": 0.0094, "step": 312480 }, { "epoch": 75.06, "learning_rate": 2.8179133927320745e-06, "loss": 0.0009, "step": 312490 }, { "epoch": 75.06, "learning_rate": 2.816428538096033e-06, "loss": 0.001, "step": 312500 }, { "epoch": 75.07, "learning_rate": 2.8149440634358148e-06, "loss": 0.0009, "step": 312510 }, { "epoch": 75.07, "learning_rate": 2.8134599687633544e-06, "loss": 0.001, "step": 312520 }, { "epoch": 75.07, "learning_rate": 2.8119762540906312e-06, "loss": 0.001, "step": 312530 }, { "epoch": 75.07, "learning_rate": 2.8104929194295692e-06, "loss": 0.0009, "step": 312540 }, { "epoch": 75.07, "learning_rate": 2.809009964792125e-06, "loss": 0.0009, "step": 312550 }, { "epoch": 75.08, "learning_rate": 2.8075273901902286e-06, "loss": 0.001, "step": 312560 }, { "epoch": 75.08, "learning_rate": 2.8060451956358423e-06, "loss": 0.0025, "step": 312570 }, { "epoch": 75.08, "learning_rate": 2.8045633811408902e-06, "loss": 0.001, "step": 312580 }, { "epoch": 75.08, "learning_rate": 2.8030819467172898e-06, "loss": 0.0012, "step": 312590 }, { "epoch": 75.09, "learning_rate": 2.8016008923769985e-06, "loss": 0.0016, "step": 312600 }, { "epoch": 75.09, "learning_rate": 2.8001202181319296e-06, "loss": 0.001, "step": 312610 }, { "epoch": 75.09, "learning_rate": 2.7986399239940066e-06, "loss": 0.0011, "step": 312620 }, { "epoch": 75.09, "learning_rate": 2.7971600099751583e-06, "loss": 0.0008, "step": 312630 }, { "epoch": 75.09, "learning_rate": 2.7956804760872923e-06, "loss": 0.0012, "step": 312640 }, { "epoch": 75.1, "learning_rate": 2.7942013223423324e-06, "loss": 0.001, "step": 312650 }, { "epoch": 75.1, "learning_rate": 2.7927225487521746e-06, "loss": 0.0028, "step": 312660 }, { "epoch": 75.1, "learning_rate": 2.7912441553287596e-06, "loss": 0.0011, "step": 312670 }, { "epoch": 75.1, "learning_rate": 2.7897661420839606e-06, "loss": 0.0011, "step": 312680 }, { "epoch": 75.11, "learning_rate": 2.788288509029685e-06, "loss": 0.0011, "step": 312690 }, { "epoch": 75.11, "learning_rate": 2.7868112561778514e-06, "loss": 0.0012, "step": 312700 }, { "epoch": 75.11, "learning_rate": 2.78533438354035e-06, "loss": 0.001, "step": 312710 }, { "epoch": 75.11, "learning_rate": 2.7838578911290548e-06, "loss": 0.0011, "step": 312720 }, { "epoch": 75.12, "learning_rate": 2.782381778955878e-06, "loss": 0.0012, "step": 312730 }, { "epoch": 75.12, "learning_rate": 2.7809060470326996e-06, "loss": 0.001, "step": 312740 }, { "epoch": 75.12, "learning_rate": 2.7794306953714046e-06, "loss": 0.0039, "step": 312750 }, { "epoch": 75.12, "learning_rate": 2.7779557239838715e-06, "loss": 0.0009, "step": 312760 }, { "epoch": 75.12, "learning_rate": 2.7764811328819804e-06, "loss": 0.0015, "step": 312770 }, { "epoch": 75.13, "learning_rate": 2.775006922077611e-06, "loss": 0.0009, "step": 312780 }, { "epoch": 75.13, "learning_rate": 2.7735330915826253e-06, "loss": 0.0009, "step": 312790 }, { "epoch": 75.13, "learning_rate": 2.7720596414088917e-06, "loss": 0.001, "step": 312800 }, { "epoch": 75.13, "learning_rate": 2.7705865715682955e-06, "loss": 0.0012, "step": 312810 }, { "epoch": 75.14, "learning_rate": 2.7691138820726827e-06, "loss": 0.0011, "step": 312820 }, { "epoch": 75.14, "learning_rate": 2.7676415729339047e-06, "loss": 0.0028, "step": 312830 }, { "epoch": 75.14, "learning_rate": 2.7661696441638406e-06, "loss": 0.001, "step": 312840 }, { "epoch": 75.14, "learning_rate": 2.7646980957743316e-06, "loss": 0.0012, "step": 312850 }, { "epoch": 75.15, "learning_rate": 2.763226927777235e-06, "loss": 0.001, "step": 312860 }, { "epoch": 75.15, "learning_rate": 2.761756140184385e-06, "loss": 0.0011, "step": 312870 }, { "epoch": 75.15, "learning_rate": 2.7602857330076393e-06, "loss": 0.001, "step": 312880 }, { "epoch": 75.15, "learning_rate": 2.7588157062588327e-06, "loss": 0.0009, "step": 312890 }, { "epoch": 75.15, "learning_rate": 2.7573460599498057e-06, "loss": 0.001, "step": 312900 }, { "epoch": 75.16, "learning_rate": 2.7558767940923936e-06, "loss": 0.0015, "step": 312910 }, { "epoch": 75.16, "learning_rate": 2.754407908698431e-06, "loss": 0.0009, "step": 312920 }, { "epoch": 75.16, "learning_rate": 2.7529394037797305e-06, "loss": 0.0009, "step": 312930 }, { "epoch": 75.16, "learning_rate": 2.7514712793481445e-06, "loss": 0.0011, "step": 312940 }, { "epoch": 75.17, "learning_rate": 2.7500035354154906e-06, "loss": 0.001, "step": 312950 }, { "epoch": 75.17, "learning_rate": 2.7485361719935655e-06, "loss": 0.0015, "step": 312960 }, { "epoch": 75.17, "learning_rate": 2.747069189094209e-06, "loss": 0.0009, "step": 312970 }, { "epoch": 75.17, "learning_rate": 2.7456025867292232e-06, "loss": 0.0009, "step": 312980 }, { "epoch": 75.17, "learning_rate": 2.7441363649104324e-06, "loss": 0.0011, "step": 312990 }, { "epoch": 75.18, "learning_rate": 2.742670523649632e-06, "loss": 0.0008, "step": 313000 }, { "epoch": 75.18, "learning_rate": 2.7412050629586296e-06, "loss": 0.0009, "step": 313010 }, { "epoch": 75.18, "learning_rate": 2.7397399828492265e-06, "loss": 0.001, "step": 313020 }, { "epoch": 75.18, "learning_rate": 2.738275283333225e-06, "loss": 0.0009, "step": 313030 }, { "epoch": 75.19, "learning_rate": 2.736810964422415e-06, "loss": 0.0023, "step": 313040 }, { "epoch": 75.19, "learning_rate": 2.7353470261285872e-06, "loss": 0.0012, "step": 313050 }, { "epoch": 75.19, "learning_rate": 2.733883468463544e-06, "loss": 0.001, "step": 313060 }, { "epoch": 75.19, "learning_rate": 2.732420291439047e-06, "loss": 0.0036, "step": 313070 }, { "epoch": 75.2, "learning_rate": 2.7309574950669104e-06, "loss": 0.0011, "step": 313080 }, { "epoch": 75.2, "learning_rate": 2.7294950793589013e-06, "loss": 0.0009, "step": 313090 }, { "epoch": 75.2, "learning_rate": 2.7280330443267777e-06, "loss": 0.0011, "step": 313100 }, { "epoch": 75.2, "learning_rate": 2.7265713899823407e-06, "loss": 0.001, "step": 313110 }, { "epoch": 75.2, "learning_rate": 2.725110116337354e-06, "loss": 0.001, "step": 313120 }, { "epoch": 75.21, "learning_rate": 2.7236492234035794e-06, "loss": 0.001, "step": 313130 }, { "epoch": 75.21, "learning_rate": 2.7221887111927857e-06, "loss": 0.0008, "step": 313140 }, { "epoch": 75.21, "learning_rate": 2.7207285797167306e-06, "loss": 0.0039, "step": 313150 }, { "epoch": 75.21, "learning_rate": 2.7192688289871758e-06, "loss": 0.001, "step": 313160 }, { "epoch": 75.22, "learning_rate": 2.717809459015869e-06, "loss": 0.0011, "step": 313170 }, { "epoch": 75.22, "learning_rate": 2.7163504698145824e-06, "loss": 0.0009, "step": 313180 }, { "epoch": 75.22, "learning_rate": 2.714891861395058e-06, "loss": 0.0009, "step": 313190 }, { "epoch": 75.22, "learning_rate": 2.7134336337690247e-06, "loss": 0.0012, "step": 313200 }, { "epoch": 75.23, "learning_rate": 2.71197578694824e-06, "loss": 0.0011, "step": 313210 }, { "epoch": 75.23, "learning_rate": 2.710518320944444e-06, "loss": 0.001, "step": 313220 }, { "epoch": 75.23, "learning_rate": 2.7090612357693834e-06, "loss": 0.001, "step": 313230 }, { "epoch": 75.23, "learning_rate": 2.7076045314347652e-06, "loss": 0.0008, "step": 313240 }, { "epoch": 75.23, "learning_rate": 2.706148207952347e-06, "loss": 0.001, "step": 313250 }, { "epoch": 75.24, "learning_rate": 2.7046922653338414e-06, "loss": 0.001, "step": 313260 }, { "epoch": 75.24, "learning_rate": 2.7032367035909834e-06, "loss": 0.001, "step": 313270 }, { "epoch": 75.24, "learning_rate": 2.7017815227354857e-06, "loss": 0.0009, "step": 313280 }, { "epoch": 75.24, "learning_rate": 2.7003267227790784e-06, "loss": 0.0012, "step": 313290 }, { "epoch": 75.25, "learning_rate": 2.698872303733463e-06, "loss": 0.001, "step": 313300 }, { "epoch": 75.25, "learning_rate": 2.6974182656103574e-06, "loss": 0.0009, "step": 313310 }, { "epoch": 75.25, "learning_rate": 2.695964608421475e-06, "loss": 0.001, "step": 313320 }, { "epoch": 75.25, "learning_rate": 2.6945113321785285e-06, "loss": 0.0016, "step": 313330 }, { "epoch": 75.25, "learning_rate": 2.693058436893203e-06, "loss": 0.0066, "step": 313340 }, { "epoch": 75.26, "learning_rate": 2.6916059225772117e-06, "loss": 0.0011, "step": 313350 }, { "epoch": 75.26, "learning_rate": 2.6901537892422502e-06, "loss": 0.001, "step": 313360 }, { "epoch": 75.26, "learning_rate": 2.688702036900015e-06, "loss": 0.0011, "step": 313370 }, { "epoch": 75.26, "learning_rate": 2.6872506655621908e-06, "loss": 0.0009, "step": 313380 }, { "epoch": 75.27, "learning_rate": 2.6857996752404692e-06, "loss": 0.0012, "step": 313390 }, { "epoch": 75.27, "learning_rate": 2.684349065946534e-06, "loss": 0.0009, "step": 313400 }, { "epoch": 75.27, "learning_rate": 2.6828988376920717e-06, "loss": 0.0012, "step": 313410 }, { "epoch": 75.27, "learning_rate": 2.6814489904887553e-06, "loss": 0.0008, "step": 313420 }, { "epoch": 75.28, "learning_rate": 2.6799995243482645e-06, "loss": 0.0008, "step": 313430 }, { "epoch": 75.28, "learning_rate": 2.678550439282268e-06, "loss": 0.0011, "step": 313440 }, { "epoch": 75.28, "learning_rate": 2.6771017353024287e-06, "loss": 0.0011, "step": 313450 }, { "epoch": 75.28, "learning_rate": 2.6756534124204367e-06, "loss": 0.001, "step": 313460 }, { "epoch": 75.28, "learning_rate": 2.6742054706479445e-06, "loss": 0.0009, "step": 313470 }, { "epoch": 75.29, "learning_rate": 2.672757909996593e-06, "loss": 0.001, "step": 313480 }, { "epoch": 75.29, "learning_rate": 2.671310730478066e-06, "loss": 0.001, "step": 313490 }, { "epoch": 75.29, "learning_rate": 2.669863932104005e-06, "loss": 0.001, "step": 313500 }, { "epoch": 75.29, "learning_rate": 2.668417514886068e-06, "loss": 0.0015, "step": 313510 }, { "epoch": 75.3, "learning_rate": 2.6669714788358946e-06, "loss": 0.0009, "step": 313520 }, { "epoch": 75.3, "learning_rate": 2.665525823965137e-06, "loss": 0.0014, "step": 313530 }, { "epoch": 75.3, "learning_rate": 2.664080550285436e-06, "loss": 0.0023, "step": 313540 }, { "epoch": 75.3, "learning_rate": 2.662635657808421e-06, "loss": 0.0009, "step": 313550 }, { "epoch": 75.31, "learning_rate": 2.661191146545755e-06, "loss": 0.001, "step": 313560 }, { "epoch": 75.31, "learning_rate": 2.6597470165090397e-06, "loss": 0.0009, "step": 313570 }, { "epoch": 75.31, "learning_rate": 2.6583032677099107e-06, "loss": 0.001, "step": 313580 }, { "epoch": 75.31, "learning_rate": 2.6568599001600136e-06, "loss": 0.001, "step": 313590 }, { "epoch": 75.31, "learning_rate": 2.655416913870956e-06, "loss": 0.0013, "step": 313600 }, { "epoch": 75.32, "learning_rate": 2.6539743088543677e-06, "loss": 0.0013, "step": 313610 }, { "epoch": 75.32, "learning_rate": 2.652532085121845e-06, "loss": 0.0008, "step": 313620 }, { "epoch": 75.32, "learning_rate": 2.6510902426850335e-06, "loss": 0.0009, "step": 313630 }, { "epoch": 75.32, "learning_rate": 2.649648781555519e-06, "loss": 0.0009, "step": 313640 }, { "epoch": 75.33, "learning_rate": 2.648207701744926e-06, "loss": 0.0009, "step": 313650 }, { "epoch": 75.33, "learning_rate": 2.646767003264855e-06, "loss": 0.0009, "step": 313660 }, { "epoch": 75.33, "learning_rate": 2.6453266861269033e-06, "loss": 0.0009, "step": 313670 }, { "epoch": 75.33, "learning_rate": 2.643886750342678e-06, "loss": 0.0009, "step": 313680 }, { "epoch": 75.33, "learning_rate": 2.6424471959237586e-06, "loss": 0.001, "step": 313690 }, { "epoch": 75.34, "learning_rate": 2.6410080228817692e-06, "loss": 0.0012, "step": 313700 }, { "epoch": 75.34, "learning_rate": 2.6395692312282673e-06, "loss": 0.0009, "step": 313710 }, { "epoch": 75.34, "learning_rate": 2.638130820974849e-06, "loss": 0.0023, "step": 313720 }, { "epoch": 75.34, "learning_rate": 2.636692792133111e-06, "loss": 0.0009, "step": 313730 }, { "epoch": 75.35, "learning_rate": 2.6352551447146213e-06, "loss": 0.001, "step": 313740 }, { "epoch": 75.35, "learning_rate": 2.6338178787309597e-06, "loss": 0.001, "step": 313750 }, { "epoch": 75.35, "learning_rate": 2.632380994193706e-06, "loss": 0.0011, "step": 313760 }, { "epoch": 75.35, "learning_rate": 2.630944491114429e-06, "loss": 0.0009, "step": 313770 }, { "epoch": 75.36, "learning_rate": 2.6295083695046908e-06, "loss": 0.0009, "step": 313780 }, { "epoch": 75.36, "learning_rate": 2.628072629376055e-06, "loss": 0.0012, "step": 313790 }, { "epoch": 75.36, "learning_rate": 2.6266372707401068e-06, "loss": 0.0012, "step": 313800 }, { "epoch": 75.36, "learning_rate": 2.625202293608381e-06, "loss": 0.0011, "step": 313810 }, { "epoch": 75.36, "learning_rate": 2.6237676979924353e-06, "loss": 0.0011, "step": 313820 }, { "epoch": 75.37, "learning_rate": 2.6223334839038382e-06, "loss": 0.001, "step": 313830 }, { "epoch": 75.37, "learning_rate": 2.620899651354131e-06, "loss": 0.0009, "step": 313840 }, { "epoch": 75.37, "learning_rate": 2.619466200354859e-06, "loss": 0.0009, "step": 313850 }, { "epoch": 75.37, "learning_rate": 2.6180331309175576e-06, "loss": 0.001, "step": 313860 }, { "epoch": 75.38, "learning_rate": 2.616600443053785e-06, "loss": 0.0012, "step": 313870 }, { "epoch": 75.38, "learning_rate": 2.6151681367750703e-06, "loss": 0.001, "step": 313880 }, { "epoch": 75.38, "learning_rate": 2.613736212092949e-06, "loss": 0.0014, "step": 313890 }, { "epoch": 75.38, "learning_rate": 2.61230466901895e-06, "loss": 0.0012, "step": 313900 }, { "epoch": 75.39, "learning_rate": 2.6108735075646097e-06, "loss": 0.001, "step": 313910 }, { "epoch": 75.39, "learning_rate": 2.60944272774144e-06, "loss": 0.0011, "step": 313920 }, { "epoch": 75.39, "learning_rate": 2.6080123295609658e-06, "loss": 0.0017, "step": 313930 }, { "epoch": 75.39, "learning_rate": 2.6065823130347278e-06, "loss": 0.0015, "step": 313940 }, { "epoch": 75.39, "learning_rate": 2.605152678174216e-06, "loss": 0.0011, "step": 313950 }, { "epoch": 75.4, "learning_rate": 2.6037234249909447e-06, "loss": 0.0008, "step": 313960 }, { "epoch": 75.4, "learning_rate": 2.6022945534964427e-06, "loss": 0.001, "step": 313970 }, { "epoch": 75.4, "learning_rate": 2.6008660637022066e-06, "loss": 0.001, "step": 313980 }, { "epoch": 75.4, "learning_rate": 2.5994379556197378e-06, "loss": 0.0009, "step": 313990 }, { "epoch": 75.41, "learning_rate": 2.598010229260539e-06, "loss": 0.0013, "step": 314000 }, { "epoch": 75.41, "learning_rate": 2.596582884636106e-06, "loss": 0.001, "step": 314010 }, { "epoch": 75.41, "learning_rate": 2.5951559217579414e-06, "loss": 0.0011, "step": 314020 }, { "epoch": 75.41, "learning_rate": 2.593729340637524e-06, "loss": 0.0009, "step": 314030 }, { "epoch": 75.41, "learning_rate": 2.5923031412863564e-06, "loss": 0.0008, "step": 314040 }, { "epoch": 75.42, "learning_rate": 2.5908773237159123e-06, "loss": 0.0008, "step": 314050 }, { "epoch": 75.42, "learning_rate": 2.5894518879376773e-06, "loss": 0.0008, "step": 314060 }, { "epoch": 75.42, "learning_rate": 2.5880268339631255e-06, "loss": 0.0011, "step": 314070 }, { "epoch": 75.42, "learning_rate": 2.586602161803753e-06, "loss": 0.001, "step": 314080 }, { "epoch": 75.43, "learning_rate": 2.585177871471012e-06, "loss": 0.001, "step": 314090 }, { "epoch": 75.43, "learning_rate": 2.5837539629763764e-06, "loss": 0.0028, "step": 314100 }, { "epoch": 75.43, "learning_rate": 2.5823304363313204e-06, "loss": 0.0009, "step": 314110 }, { "epoch": 75.43, "learning_rate": 2.580907291547302e-06, "loss": 0.0012, "step": 314120 }, { "epoch": 75.44, "learning_rate": 2.5794845286357895e-06, "loss": 0.0011, "step": 314130 }, { "epoch": 75.44, "learning_rate": 2.578062147608229e-06, "loss": 0.0009, "step": 314140 }, { "epoch": 75.44, "learning_rate": 2.5766401484760837e-06, "loss": 0.0017, "step": 314150 }, { "epoch": 75.44, "learning_rate": 2.5752185312508004e-06, "loss": 0.0009, "step": 314160 }, { "epoch": 75.44, "learning_rate": 2.573797295943825e-06, "loss": 0.001, "step": 314170 }, { "epoch": 75.45, "learning_rate": 2.5723764425666206e-06, "loss": 0.0011, "step": 314180 }, { "epoch": 75.45, "learning_rate": 2.5709559711306117e-06, "loss": 0.0012, "step": 314190 }, { "epoch": 75.45, "learning_rate": 2.5695358816472337e-06, "loss": 0.0009, "step": 314200 }, { "epoch": 75.45, "learning_rate": 2.568116174127938e-06, "loss": 0.0018, "step": 314210 }, { "epoch": 75.46, "learning_rate": 2.5666968485841545e-06, "loss": 0.0013, "step": 314220 }, { "epoch": 75.46, "learning_rate": 2.5652779050273024e-06, "loss": 0.001, "step": 314230 }, { "epoch": 75.46, "learning_rate": 2.563859343468822e-06, "loss": 0.0012, "step": 314240 }, { "epoch": 75.46, "learning_rate": 2.562441163920126e-06, "loss": 0.0011, "step": 314250 }, { "epoch": 75.47, "learning_rate": 2.5610233663926455e-06, "loss": 0.0018, "step": 314260 }, { "epoch": 75.47, "learning_rate": 2.559605950897792e-06, "loss": 0.0011, "step": 314270 }, { "epoch": 75.47, "learning_rate": 2.5581889174469796e-06, "loss": 0.001, "step": 314280 }, { "epoch": 75.47, "learning_rate": 2.5567722660516214e-06, "loss": 0.001, "step": 314290 }, { "epoch": 75.47, "learning_rate": 2.55535599672313e-06, "loss": 0.0011, "step": 314300 }, { "epoch": 75.48, "learning_rate": 2.5539401094728967e-06, "loss": 0.0022, "step": 314310 }, { "epoch": 75.48, "learning_rate": 2.5525246043123506e-06, "loss": 0.0008, "step": 314320 }, { "epoch": 75.48, "learning_rate": 2.551109481252867e-06, "loss": 0.0011, "step": 314330 }, { "epoch": 75.48, "learning_rate": 2.5496947403058415e-06, "loss": 0.0009, "step": 314340 }, { "epoch": 75.49, "learning_rate": 2.548280381482682e-06, "loss": 0.0011, "step": 314350 }, { "epoch": 75.49, "learning_rate": 2.5468664047947734e-06, "loss": 0.0009, "step": 314360 }, { "epoch": 75.49, "learning_rate": 2.545452810253496e-06, "loss": 0.0008, "step": 314370 }, { "epoch": 75.49, "learning_rate": 2.5440395978702405e-06, "loss": 0.0009, "step": 314380 }, { "epoch": 75.49, "learning_rate": 2.5426267676563864e-06, "loss": 0.0009, "step": 314390 }, { "epoch": 75.5, "learning_rate": 2.541214319623314e-06, "loss": 0.0009, "step": 314400 }, { "epoch": 75.5, "learning_rate": 2.539802253782392e-06, "loss": 0.001, "step": 314410 }, { "epoch": 75.5, "learning_rate": 2.538390570144994e-06, "loss": 0.0009, "step": 314420 }, { "epoch": 75.5, "learning_rate": 2.5369792687224892e-06, "loss": 0.0011, "step": 314430 }, { "epoch": 75.51, "learning_rate": 2.535568349526235e-06, "loss": 0.0009, "step": 314440 }, { "epoch": 75.51, "learning_rate": 2.5341578125676113e-06, "loss": 0.001, "step": 314450 }, { "epoch": 75.51, "learning_rate": 2.5327476578579756e-06, "loss": 0.0012, "step": 314460 }, { "epoch": 75.51, "learning_rate": 2.5313378854086687e-06, "loss": 0.0011, "step": 314470 }, { "epoch": 75.52, "learning_rate": 2.5299284952310433e-06, "loss": 0.0011, "step": 314480 }, { "epoch": 75.52, "learning_rate": 2.528519487336467e-06, "loss": 0.001, "step": 314490 }, { "epoch": 75.52, "learning_rate": 2.5271108617362705e-06, "loss": 0.001, "step": 314500 }, { "epoch": 75.52, "learning_rate": 2.525702618441811e-06, "loss": 0.001, "step": 314510 }, { "epoch": 75.52, "learning_rate": 2.524294757464418e-06, "loss": 0.0014, "step": 314520 }, { "epoch": 75.53, "learning_rate": 2.522887278815439e-06, "loss": 0.001, "step": 314530 }, { "epoch": 75.53, "learning_rate": 2.5214801825061973e-06, "loss": 0.0008, "step": 314540 }, { "epoch": 75.53, "learning_rate": 2.5200734685480343e-06, "loss": 0.0011, "step": 314550 }, { "epoch": 75.53, "learning_rate": 2.518667136952274e-06, "loss": 0.0015, "step": 314560 }, { "epoch": 75.54, "learning_rate": 2.517261187730241e-06, "loss": 0.0012, "step": 314570 }, { "epoch": 75.54, "learning_rate": 2.5158556208932537e-06, "loss": 0.001, "step": 314580 }, { "epoch": 75.54, "learning_rate": 2.514450436452642e-06, "loss": 0.0009, "step": 314590 }, { "epoch": 75.54, "learning_rate": 2.5130456344197252e-06, "loss": 0.0012, "step": 314600 }, { "epoch": 75.55, "learning_rate": 2.5116412148057935e-06, "loss": 0.001, "step": 314610 }, { "epoch": 75.55, "learning_rate": 2.5102371776221823e-06, "loss": 0.0014, "step": 314620 }, { "epoch": 75.55, "learning_rate": 2.5088335228801827e-06, "loss": 0.0009, "step": 314630 }, { "epoch": 75.55, "learning_rate": 2.507430250591103e-06, "loss": 0.0046, "step": 314640 }, { "epoch": 75.55, "learning_rate": 2.506027360766244e-06, "loss": 0.0009, "step": 314650 }, { "epoch": 75.56, "learning_rate": 2.504624853416909e-06, "loss": 0.0011, "step": 314660 }, { "epoch": 75.56, "learning_rate": 2.503222728554383e-06, "loss": 0.0014, "step": 314670 }, { "epoch": 75.56, "learning_rate": 2.501820986189951e-06, "loss": 0.0012, "step": 314680 }, { "epoch": 75.56, "learning_rate": 2.5004196263349266e-06, "loss": 0.0009, "step": 314690 }, { "epoch": 75.57, "learning_rate": 2.499018649000584e-06, "loss": 0.0011, "step": 314700 }, { "epoch": 75.57, "learning_rate": 2.497618054198192e-06, "loss": 0.001, "step": 314710 }, { "epoch": 75.57, "learning_rate": 2.4962178419390357e-06, "loss": 0.0008, "step": 314720 }, { "epoch": 75.57, "learning_rate": 2.4948180122344066e-06, "loss": 0.0011, "step": 314730 }, { "epoch": 75.57, "learning_rate": 2.493418565095568e-06, "loss": 0.0009, "step": 314740 }, { "epoch": 75.58, "learning_rate": 2.4920195005337765e-06, "loss": 0.0009, "step": 314750 }, { "epoch": 75.58, "learning_rate": 2.4906208185603185e-06, "loss": 0.001, "step": 314760 }, { "epoch": 75.58, "learning_rate": 2.4892225191864517e-06, "loss": 0.001, "step": 314770 }, { "epoch": 75.58, "learning_rate": 2.4878246024234273e-06, "loss": 0.0012, "step": 314780 }, { "epoch": 75.59, "learning_rate": 2.4864270682825206e-06, "loss": 0.0021, "step": 314790 }, { "epoch": 75.59, "learning_rate": 2.4850299167749725e-06, "loss": 0.0013, "step": 314800 }, { "epoch": 75.59, "learning_rate": 2.4836331479120346e-06, "loss": 0.0012, "step": 314810 }, { "epoch": 75.59, "learning_rate": 2.4822367617049592e-06, "loss": 0.001, "step": 314820 }, { "epoch": 75.6, "learning_rate": 2.480840758164993e-06, "loss": 0.001, "step": 314830 }, { "epoch": 75.6, "learning_rate": 2.4794451373033823e-06, "loss": 0.0011, "step": 314840 }, { "epoch": 75.6, "learning_rate": 2.4780498991313516e-06, "loss": 0.001, "step": 314850 }, { "epoch": 75.6, "learning_rate": 2.4766550436601534e-06, "loss": 0.0011, "step": 314860 }, { "epoch": 75.6, "learning_rate": 2.4752605709010056e-06, "loss": 0.0011, "step": 314870 }, { "epoch": 75.61, "learning_rate": 2.4738664808651502e-06, "loss": 0.0008, "step": 314880 }, { "epoch": 75.61, "learning_rate": 2.472472773563811e-06, "loss": 0.001, "step": 314890 }, { "epoch": 75.61, "learning_rate": 2.4710794490082067e-06, "loss": 0.0012, "step": 314900 }, { "epoch": 75.61, "learning_rate": 2.4696865072095675e-06, "loss": 0.0009, "step": 314910 }, { "epoch": 75.62, "learning_rate": 2.468293948179101e-06, "loss": 0.0009, "step": 314920 }, { "epoch": 75.62, "learning_rate": 2.4669017719280265e-06, "loss": 0.002, "step": 314930 }, { "epoch": 75.62, "learning_rate": 2.4655099784675507e-06, "loss": 0.001, "step": 314940 }, { "epoch": 75.62, "learning_rate": 2.464118567808887e-06, "loss": 0.001, "step": 314950 }, { "epoch": 75.62, "learning_rate": 2.4627275399632334e-06, "loss": 0.001, "step": 314960 }, { "epoch": 75.63, "learning_rate": 2.461336894941807e-06, "loss": 0.0027, "step": 314970 }, { "epoch": 75.63, "learning_rate": 2.4599466327557996e-06, "loss": 0.0009, "step": 314980 }, { "epoch": 75.63, "learning_rate": 2.4585567534163965e-06, "loss": 0.001, "step": 314990 }, { "epoch": 75.63, "learning_rate": 2.4571672569348e-06, "loss": 0.0012, "step": 315000 }, { "epoch": 75.64, "learning_rate": 2.455778143322207e-06, "loss": 0.0008, "step": 315010 }, { "epoch": 75.64, "learning_rate": 2.4543894125897915e-06, "loss": 0.0009, "step": 315020 }, { "epoch": 75.64, "learning_rate": 2.4530010647487446e-06, "loss": 0.001, "step": 315030 }, { "epoch": 75.64, "learning_rate": 2.4516130998102405e-06, "loss": 0.001, "step": 315040 }, { "epoch": 75.65, "learning_rate": 2.450225517785465e-06, "loss": 0.001, "step": 315050 }, { "epoch": 75.65, "learning_rate": 2.4488383186855813e-06, "loss": 0.0009, "step": 315060 }, { "epoch": 75.65, "learning_rate": 2.4474515025217747e-06, "loss": 0.0011, "step": 315070 }, { "epoch": 75.65, "learning_rate": 2.4460650693052033e-06, "loss": 0.0064, "step": 315080 }, { "epoch": 75.65, "learning_rate": 2.4446790190470305e-06, "loss": 0.0012, "step": 315090 }, { "epoch": 75.66, "learning_rate": 2.44329335175843e-06, "loss": 0.0009, "step": 315100 }, { "epoch": 75.66, "learning_rate": 2.441908067450549e-06, "loss": 0.0008, "step": 315110 }, { "epoch": 75.66, "learning_rate": 2.440523166134562e-06, "loss": 0.0008, "step": 315120 }, { "epoch": 75.66, "learning_rate": 2.439138647821587e-06, "loss": 0.0011, "step": 315130 }, { "epoch": 75.67, "learning_rate": 2.437754512522805e-06, "loss": 0.001, "step": 315140 }, { "epoch": 75.67, "learning_rate": 2.436370760249351e-06, "loss": 0.001, "step": 315150 }, { "epoch": 75.67, "learning_rate": 2.4349873910123723e-06, "loss": 0.0009, "step": 315160 }, { "epoch": 75.67, "learning_rate": 2.4336044048230032e-06, "loss": 0.0012, "step": 315170 }, { "epoch": 75.68, "learning_rate": 2.4322218016923914e-06, "loss": 0.0015, "step": 315180 }, { "epoch": 75.68, "learning_rate": 2.4308395816316553e-06, "loss": 0.0013, "step": 315190 }, { "epoch": 75.68, "learning_rate": 2.429457744651936e-06, "loss": 0.001, "step": 315200 }, { "epoch": 75.68, "learning_rate": 2.4280762907643696e-06, "loss": 0.0009, "step": 315210 }, { "epoch": 75.68, "learning_rate": 2.4266952199800685e-06, "loss": 0.0011, "step": 315220 }, { "epoch": 75.69, "learning_rate": 2.425314532310152e-06, "loss": 0.001, "step": 315230 }, { "epoch": 75.69, "learning_rate": 2.4239342277657563e-06, "loss": 0.001, "step": 315240 }, { "epoch": 75.69, "learning_rate": 2.4225543063579823e-06, "loss": 0.001, "step": 315250 }, { "epoch": 75.69, "learning_rate": 2.4211747680979447e-06, "loss": 0.0024, "step": 315260 }, { "epoch": 75.7, "learning_rate": 2.4197956129967556e-06, "loss": 0.001, "step": 315270 }, { "epoch": 75.7, "learning_rate": 2.418416841065524e-06, "loss": 0.001, "step": 315280 }, { "epoch": 75.7, "learning_rate": 2.4170384523153513e-06, "loss": 0.0011, "step": 315290 }, { "epoch": 75.7, "learning_rate": 2.4156604467573287e-06, "loss": 0.0011, "step": 315300 }, { "epoch": 75.7, "learning_rate": 2.414282824402575e-06, "loss": 0.001, "step": 315310 }, { "epoch": 75.71, "learning_rate": 2.4129055852621652e-06, "loss": 0.0013, "step": 315320 }, { "epoch": 75.71, "learning_rate": 2.41152872934719e-06, "loss": 0.001, "step": 315330 }, { "epoch": 75.71, "learning_rate": 2.410152256668752e-06, "loss": 0.0011, "step": 315340 }, { "epoch": 75.71, "learning_rate": 2.408776167237925e-06, "loss": 0.0025, "step": 315350 }, { "epoch": 75.72, "learning_rate": 2.407400461065801e-06, "loss": 0.0009, "step": 315360 }, { "epoch": 75.72, "learning_rate": 2.4060251381634425e-06, "loss": 0.0009, "step": 315370 }, { "epoch": 75.72, "learning_rate": 2.4046501985419355e-06, "loss": 0.001, "step": 315380 }, { "epoch": 75.72, "learning_rate": 2.403275642212355e-06, "loss": 0.001, "step": 315390 }, { "epoch": 75.73, "learning_rate": 2.4019014691857687e-06, "loss": 0.001, "step": 315400 }, { "epoch": 75.73, "learning_rate": 2.4005276794732355e-06, "loss": 0.0009, "step": 315410 }, { "epoch": 75.73, "learning_rate": 2.3991542730858297e-06, "loss": 0.0011, "step": 315420 }, { "epoch": 75.73, "learning_rate": 2.397781250034603e-06, "loss": 0.0009, "step": 315430 }, { "epoch": 75.73, "learning_rate": 2.396408610330608e-06, "loss": 0.001, "step": 315440 }, { "epoch": 75.74, "learning_rate": 2.3950363539849252e-06, "loss": 0.0012, "step": 315450 }, { "epoch": 75.74, "learning_rate": 2.3936644810085727e-06, "loss": 0.0011, "step": 315460 }, { "epoch": 75.74, "learning_rate": 2.3922929914126093e-06, "loss": 0.0009, "step": 315470 }, { "epoch": 75.74, "learning_rate": 2.3909218852080918e-06, "loss": 0.0009, "step": 315480 }, { "epoch": 75.75, "learning_rate": 2.3895511624060507e-06, "loss": 0.0009, "step": 315490 }, { "epoch": 75.75, "learning_rate": 2.388180823017533e-06, "loss": 0.0009, "step": 315500 }, { "epoch": 75.75, "learning_rate": 2.386810867053563e-06, "loss": 0.0012, "step": 315510 }, { "epoch": 75.75, "learning_rate": 2.385441294525176e-06, "loss": 0.0009, "step": 315520 }, { "epoch": 75.76, "learning_rate": 2.384072105443408e-06, "loss": 0.0031, "step": 315530 }, { "epoch": 75.76, "learning_rate": 2.382703299819283e-06, "loss": 0.0036, "step": 315540 }, { "epoch": 75.76, "learning_rate": 2.3813348776638157e-06, "loss": 0.0009, "step": 315550 }, { "epoch": 75.76, "learning_rate": 2.3799668389880405e-06, "loss": 0.001, "step": 315560 }, { "epoch": 75.76, "learning_rate": 2.37859918380296e-06, "loss": 0.003, "step": 315570 }, { "epoch": 75.77, "learning_rate": 2.377231912119593e-06, "loss": 0.001, "step": 315580 }, { "epoch": 75.77, "learning_rate": 2.375865023948959e-06, "loss": 0.0011, "step": 315590 }, { "epoch": 75.77, "learning_rate": 2.3744985193020597e-06, "loss": 0.0012, "step": 315600 }, { "epoch": 75.77, "learning_rate": 2.3731323981898868e-06, "loss": 0.001, "step": 315610 }, { "epoch": 75.78, "learning_rate": 2.3717666606234646e-06, "loss": 0.0011, "step": 315620 }, { "epoch": 75.78, "learning_rate": 2.3704013066137788e-06, "loss": 0.0012, "step": 315630 }, { "epoch": 75.78, "learning_rate": 2.369036336171826e-06, "loss": 0.003, "step": 315640 }, { "epoch": 75.78, "learning_rate": 2.367671749308603e-06, "loss": 0.0009, "step": 315650 }, { "epoch": 75.78, "learning_rate": 2.3663075460350957e-06, "loss": 0.0011, "step": 315660 }, { "epoch": 75.79, "learning_rate": 2.364943726362284e-06, "loss": 0.0012, "step": 315670 }, { "epoch": 75.79, "learning_rate": 2.363580290301154e-06, "loss": 0.0013, "step": 315680 }, { "epoch": 75.79, "learning_rate": 2.3622172378627015e-06, "loss": 0.001, "step": 315690 }, { "epoch": 75.79, "learning_rate": 2.3608545690578854e-06, "loss": 0.0008, "step": 315700 }, { "epoch": 75.8, "learning_rate": 2.3594922838976797e-06, "loss": 0.0011, "step": 315710 }, { "epoch": 75.8, "learning_rate": 2.358130382393059e-06, "loss": 0.0028, "step": 315720 }, { "epoch": 75.8, "learning_rate": 2.3567688645550033e-06, "loss": 0.001, "step": 315730 }, { "epoch": 75.8, "learning_rate": 2.3554077303944546e-06, "loss": 0.0042, "step": 315740 }, { "epoch": 75.81, "learning_rate": 2.3540469799223864e-06, "loss": 0.0009, "step": 315750 }, { "epoch": 75.81, "learning_rate": 2.352686613149757e-06, "loss": 0.0033, "step": 315760 }, { "epoch": 75.81, "learning_rate": 2.351326630087525e-06, "loss": 0.0012, "step": 315770 }, { "epoch": 75.81, "learning_rate": 2.3499670307466303e-06, "loss": 0.0011, "step": 315780 }, { "epoch": 75.81, "learning_rate": 2.3486078151380375e-06, "loss": 0.0013, "step": 315790 }, { "epoch": 75.82, "learning_rate": 2.347248983272676e-06, "loss": 0.0009, "step": 315800 }, { "epoch": 75.82, "learning_rate": 2.3458905351615045e-06, "loss": 0.0009, "step": 315810 }, { "epoch": 75.82, "learning_rate": 2.344532470815447e-06, "loss": 0.0013, "step": 315820 }, { "epoch": 75.82, "learning_rate": 2.3431747902454614e-06, "loss": 0.001, "step": 315830 }, { "epoch": 75.83, "learning_rate": 2.3418174934624614e-06, "loss": 0.0009, "step": 315840 }, { "epoch": 75.83, "learning_rate": 2.3404605804773827e-06, "loss": 0.0009, "step": 315850 }, { "epoch": 75.83, "learning_rate": 2.339104051301155e-06, "loss": 0.0011, "step": 315860 }, { "epoch": 75.83, "learning_rate": 2.337747905944715e-06, "loss": 0.0009, "step": 315870 }, { "epoch": 75.84, "learning_rate": 2.3363921444189527e-06, "loss": 0.0009, "step": 315880 }, { "epoch": 75.84, "learning_rate": 2.3350367667348107e-06, "loss": 0.001, "step": 315890 }, { "epoch": 75.84, "learning_rate": 2.333681772903201e-06, "loss": 0.001, "step": 315900 }, { "epoch": 75.84, "learning_rate": 2.332327162935033e-06, "loss": 0.0008, "step": 315910 }, { "epoch": 75.84, "learning_rate": 2.330972936841219e-06, "loss": 0.0011, "step": 315920 }, { "epoch": 75.85, "learning_rate": 2.3296190946326567e-06, "loss": 0.0012, "step": 315930 }, { "epoch": 75.85, "learning_rate": 2.328265636320254e-06, "loss": 0.0009, "step": 315940 }, { "epoch": 75.85, "learning_rate": 2.3269125619149013e-06, "loss": 0.0011, "step": 315950 }, { "epoch": 75.85, "learning_rate": 2.3255598714275073e-06, "loss": 0.001, "step": 315960 }, { "epoch": 75.86, "learning_rate": 2.324207564868974e-06, "loss": 0.0011, "step": 315970 }, { "epoch": 75.86, "learning_rate": 2.3228556422501712e-06, "loss": 0.001, "step": 315980 }, { "epoch": 75.86, "learning_rate": 2.3215041035819894e-06, "loss": 0.0009, "step": 315990 }, { "epoch": 75.86, "learning_rate": 2.3201529488753203e-06, "loss": 0.001, "step": 316000 }, { "epoch": 75.86, "learning_rate": 2.318802178141044e-06, "loss": 0.001, "step": 316010 }, { "epoch": 75.87, "learning_rate": 2.317451791390035e-06, "loss": 0.001, "step": 316020 }, { "epoch": 75.87, "learning_rate": 2.316101788633168e-06, "loss": 0.0013, "step": 316030 }, { "epoch": 75.87, "learning_rate": 2.3147521698813237e-06, "loss": 0.0014, "step": 316040 }, { "epoch": 75.87, "learning_rate": 2.313402935145359e-06, "loss": 0.0022, "step": 316050 }, { "epoch": 75.88, "learning_rate": 2.3120540844361438e-06, "loss": 0.001, "step": 316060 }, { "epoch": 75.88, "learning_rate": 2.3107056177645414e-06, "loss": 0.0011, "step": 316070 }, { "epoch": 75.88, "learning_rate": 2.3093575351414097e-06, "loss": 0.0011, "step": 316080 }, { "epoch": 75.88, "learning_rate": 2.308009836577596e-06, "loss": 0.001, "step": 316090 }, { "epoch": 75.89, "learning_rate": 2.3066625220839745e-06, "loss": 0.001, "step": 316100 }, { "epoch": 75.89, "learning_rate": 2.305315591671392e-06, "loss": 0.0009, "step": 316110 }, { "epoch": 75.89, "learning_rate": 2.3039690453506735e-06, "loss": 0.0011, "step": 316120 }, { "epoch": 75.89, "learning_rate": 2.3026228831326825e-06, "loss": 0.0013, "step": 316130 }, { "epoch": 75.89, "learning_rate": 2.3012771050282546e-06, "loss": 0.0009, "step": 316140 }, { "epoch": 75.9, "learning_rate": 2.2999317110482255e-06, "loss": 0.0009, "step": 316150 }, { "epoch": 75.9, "learning_rate": 2.298586701203437e-06, "loss": 0.0009, "step": 316160 }, { "epoch": 75.9, "learning_rate": 2.297242075504713e-06, "loss": 0.001, "step": 316170 }, { "epoch": 75.9, "learning_rate": 2.295897833962879e-06, "loss": 0.0009, "step": 316180 }, { "epoch": 75.91, "learning_rate": 2.2945539765887645e-06, "loss": 0.001, "step": 316190 }, { "epoch": 75.91, "learning_rate": 2.2932105033932063e-06, "loss": 0.0011, "step": 316200 }, { "epoch": 75.91, "learning_rate": 2.2918674143870002e-06, "loss": 0.0011, "step": 316210 }, { "epoch": 75.91, "learning_rate": 2.2905247095809766e-06, "loss": 0.0012, "step": 316220 }, { "epoch": 75.92, "learning_rate": 2.289182388985939e-06, "loss": 0.001, "step": 316230 }, { "epoch": 75.92, "learning_rate": 2.2878404526127052e-06, "loss": 0.001, "step": 316240 }, { "epoch": 75.92, "learning_rate": 2.286498900472084e-06, "loss": 0.0011, "step": 316250 }, { "epoch": 75.92, "learning_rate": 2.285157732574866e-06, "loss": 0.001, "step": 316260 }, { "epoch": 75.92, "learning_rate": 2.2838169489318605e-06, "loss": 0.0013, "step": 316270 }, { "epoch": 75.93, "learning_rate": 2.282476549553869e-06, "loss": 0.0011, "step": 316280 }, { "epoch": 75.93, "learning_rate": 2.281136534451683e-06, "loss": 0.0011, "step": 316290 }, { "epoch": 75.93, "learning_rate": 2.2797969036360943e-06, "loss": 0.0029, "step": 316300 }, { "epoch": 75.93, "learning_rate": 2.2784576571178827e-06, "loss": 0.0009, "step": 316310 }, { "epoch": 75.94, "learning_rate": 2.2771187949078452e-06, "loss": 0.001, "step": 316320 }, { "epoch": 75.94, "learning_rate": 2.2757803170167513e-06, "loss": 0.001, "step": 316330 }, { "epoch": 75.94, "learning_rate": 2.2744422234553917e-06, "loss": 0.001, "step": 316340 }, { "epoch": 75.94, "learning_rate": 2.273104514234542e-06, "loss": 0.001, "step": 316350 }, { "epoch": 75.94, "learning_rate": 2.271767189364965e-06, "loss": 0.0012, "step": 316360 }, { "epoch": 75.95, "learning_rate": 2.2704302488574357e-06, "loss": 0.0021, "step": 316370 }, { "epoch": 75.95, "learning_rate": 2.2690936927227237e-06, "loss": 0.001, "step": 316380 }, { "epoch": 76.0, "learning_rate": 2.2677575209715974e-06, "loss": 0.0009, "step": 316390 }, { "epoch": 76.0, "learning_rate": 2.2664217336147985e-06, "loss": 0.0009, "step": 316400 }, { "epoch": 76.01, "learning_rate": 2.2650863306630967e-06, "loss": 0.0009, "step": 316410 }, { "epoch": 76.01, "learning_rate": 2.263751312127249e-06, "loss": 0.0015, "step": 316420 }, { "epoch": 76.01, "learning_rate": 2.262416678017998e-06, "loss": 0.0008, "step": 316430 }, { "epoch": 76.01, "learning_rate": 2.2610824283461007e-06, "loss": 0.0009, "step": 316440 }, { "epoch": 76.01, "learning_rate": 2.2597485631222936e-06, "loss": 0.0009, "step": 316450 }, { "epoch": 76.02, "learning_rate": 2.2584150823573235e-06, "loss": 0.0009, "step": 316460 }, { "epoch": 76.02, "learning_rate": 2.257081986061926e-06, "loss": 0.0009, "step": 316470 }, { "epoch": 76.02, "learning_rate": 2.2557492742468378e-06, "loss": 0.0017, "step": 316480 }, { "epoch": 76.02, "learning_rate": 2.254416946922805e-06, "loss": 0.0008, "step": 316490 }, { "epoch": 76.03, "learning_rate": 2.2530850041005304e-06, "loss": 0.001, "step": 316500 }, { "epoch": 76.03, "learning_rate": 2.251753445790755e-06, "loss": 0.0012, "step": 316510 }, { "epoch": 76.03, "learning_rate": 2.2504222720042047e-06, "loss": 0.0009, "step": 316520 }, { "epoch": 76.03, "learning_rate": 2.2490914827515973e-06, "loss": 0.001, "step": 316530 }, { "epoch": 76.03, "learning_rate": 2.2477610780436476e-06, "loss": 0.0009, "step": 316540 }, { "epoch": 76.04, "learning_rate": 2.2464310578910686e-06, "loss": 0.0009, "step": 316550 }, { "epoch": 76.04, "learning_rate": 2.245101422304574e-06, "loss": 0.0009, "step": 316560 }, { "epoch": 76.04, "learning_rate": 2.2437721712948665e-06, "loss": 0.0013, "step": 316570 }, { "epoch": 76.04, "learning_rate": 2.2424433048726657e-06, "loss": 0.001, "step": 316580 }, { "epoch": 76.05, "learning_rate": 2.2411148230486567e-06, "loss": 0.001, "step": 316590 }, { "epoch": 76.05, "learning_rate": 2.239786725833537e-06, "loss": 0.001, "step": 316600 }, { "epoch": 76.05, "learning_rate": 2.2384590132380147e-06, "loss": 0.0012, "step": 316610 }, { "epoch": 76.05, "learning_rate": 2.2371316852727753e-06, "loss": 0.0009, "step": 316620 }, { "epoch": 76.06, "learning_rate": 2.2358047419485164e-06, "loss": 0.0009, "step": 316630 }, { "epoch": 76.06, "learning_rate": 2.2344781832759008e-06, "loss": 0.001, "step": 316640 }, { "epoch": 76.06, "learning_rate": 2.2331520092656375e-06, "loss": 0.0008, "step": 316650 }, { "epoch": 76.06, "learning_rate": 2.2318262199283903e-06, "loss": 0.002, "step": 316660 }, { "epoch": 76.06, "learning_rate": 2.230500815274844e-06, "loss": 0.0011, "step": 316670 }, { "epoch": 76.07, "learning_rate": 2.2291757953156745e-06, "loss": 0.001, "step": 316680 }, { "epoch": 76.07, "learning_rate": 2.2278511600615392e-06, "loss": 0.001, "step": 316690 }, { "epoch": 76.07, "learning_rate": 2.226526909523119e-06, "loss": 0.001, "step": 316700 }, { "epoch": 76.07, "learning_rate": 2.225203043711066e-06, "loss": 0.001, "step": 316710 }, { "epoch": 76.08, "learning_rate": 2.223879562636061e-06, "loss": 0.001, "step": 316720 }, { "epoch": 76.08, "learning_rate": 2.2225564663087397e-06, "loss": 0.0014, "step": 316730 }, { "epoch": 76.08, "learning_rate": 2.2212337547397654e-06, "loss": 0.0009, "step": 316740 }, { "epoch": 76.08, "learning_rate": 2.219911427939797e-06, "loss": 0.0011, "step": 316750 }, { "epoch": 76.09, "learning_rate": 2.218589485919481e-06, "loss": 0.0011, "step": 316760 }, { "epoch": 76.09, "learning_rate": 2.217267928689454e-06, "loss": 0.0011, "step": 316770 }, { "epoch": 76.09, "learning_rate": 2.215946756260373e-06, "loss": 0.0009, "step": 316780 }, { "epoch": 76.09, "learning_rate": 2.214625968642864e-06, "loss": 0.0023, "step": 316790 }, { "epoch": 76.09, "learning_rate": 2.213305565847573e-06, "loss": 0.0008, "step": 316800 }, { "epoch": 76.1, "learning_rate": 2.2119855478851206e-06, "loss": 0.0009, "step": 316810 }, { "epoch": 76.1, "learning_rate": 2.210665914766158e-06, "loss": 0.0009, "step": 316820 }, { "epoch": 76.1, "learning_rate": 2.2093466665012998e-06, "loss": 0.0009, "step": 316830 }, { "epoch": 76.1, "learning_rate": 2.2080278031011646e-06, "loss": 0.0008, "step": 316840 }, { "epoch": 76.11, "learning_rate": 2.2067093245763724e-06, "loss": 0.0009, "step": 316850 }, { "epoch": 76.11, "learning_rate": 2.2053912309375645e-06, "loss": 0.0009, "step": 316860 }, { "epoch": 76.11, "learning_rate": 2.2040735221953322e-06, "loss": 0.0012, "step": 316870 }, { "epoch": 76.11, "learning_rate": 2.2027561983602897e-06, "loss": 0.0009, "step": 316880 }, { "epoch": 76.11, "learning_rate": 2.2014392594430554e-06, "loss": 0.0011, "step": 316890 }, { "epoch": 76.12, "learning_rate": 2.200122705454233e-06, "loss": 0.0013, "step": 316900 }, { "epoch": 76.12, "learning_rate": 2.1988065364044184e-06, "loss": 0.0013, "step": 316910 }, { "epoch": 76.12, "learning_rate": 2.1974907523042153e-06, "loss": 0.001, "step": 316920 }, { "epoch": 76.12, "learning_rate": 2.196175353164215e-06, "loss": 0.0014, "step": 316930 }, { "epoch": 76.13, "learning_rate": 2.1948603389950196e-06, "loss": 0.0009, "step": 316940 }, { "epoch": 76.13, "learning_rate": 2.193545709807204e-06, "loss": 0.0009, "step": 316950 }, { "epoch": 76.13, "learning_rate": 2.1922314656113774e-06, "loss": 0.0009, "step": 316960 }, { "epoch": 76.13, "learning_rate": 2.190917606418108e-06, "loss": 0.0012, "step": 316970 }, { "epoch": 76.14, "learning_rate": 2.1896041322379658e-06, "loss": 0.001, "step": 316980 }, { "epoch": 76.14, "learning_rate": 2.1882910430815584e-06, "loss": 0.0009, "step": 316990 }, { "epoch": 76.14, "learning_rate": 2.186978338959439e-06, "loss": 0.0016, "step": 317000 }, { "epoch": 76.14, "learning_rate": 2.185666019882182e-06, "loss": 0.0009, "step": 317010 }, { "epoch": 76.14, "learning_rate": 2.1843540858603627e-06, "loss": 0.0023, "step": 317020 }, { "epoch": 76.15, "learning_rate": 2.183042536904539e-06, "loss": 0.0009, "step": 317030 }, { "epoch": 76.15, "learning_rate": 2.1817313730252755e-06, "loss": 0.0015, "step": 317040 }, { "epoch": 76.15, "learning_rate": 2.180420594233129e-06, "loss": 0.001, "step": 317050 }, { "epoch": 76.15, "learning_rate": 2.179110200538659e-06, "loss": 0.0011, "step": 317060 }, { "epoch": 76.16, "learning_rate": 2.177800191952417e-06, "loss": 0.0015, "step": 317070 }, { "epoch": 76.16, "learning_rate": 2.1764905684849513e-06, "loss": 0.0016, "step": 317080 }, { "epoch": 76.16, "learning_rate": 2.175181330146803e-06, "loss": 0.0011, "step": 317090 }, { "epoch": 76.16, "learning_rate": 2.173872476948535e-06, "loss": 0.0074, "step": 317100 }, { "epoch": 76.16, "learning_rate": 2.1725640089006684e-06, "loss": 0.0008, "step": 317110 }, { "epoch": 76.17, "learning_rate": 2.1712559260137434e-06, "loss": 0.001, "step": 317120 }, { "epoch": 76.17, "learning_rate": 2.1699482282982964e-06, "loss": 0.0009, "step": 317130 }, { "epoch": 76.17, "learning_rate": 2.1686409157648692e-06, "loss": 0.001, "step": 317140 }, { "epoch": 76.17, "learning_rate": 2.167333988423975e-06, "loss": 0.0011, "step": 317150 }, { "epoch": 76.18, "learning_rate": 2.166027446286145e-06, "loss": 0.0025, "step": 317160 }, { "epoch": 76.18, "learning_rate": 2.1647212893618985e-06, "loss": 0.001, "step": 317170 }, { "epoch": 76.18, "learning_rate": 2.1634155176617544e-06, "loss": 0.001, "step": 317180 }, { "epoch": 76.18, "learning_rate": 2.162110131196232e-06, "loss": 0.0009, "step": 317190 }, { "epoch": 76.19, "learning_rate": 2.1608051299758404e-06, "loss": 0.0011, "step": 317200 }, { "epoch": 76.19, "learning_rate": 2.1595005140110925e-06, "loss": 0.001, "step": 317210 }, { "epoch": 76.19, "learning_rate": 2.1581962833124803e-06, "loss": 0.0011, "step": 317220 }, { "epoch": 76.19, "learning_rate": 2.1568924378905286e-06, "loss": 0.0011, "step": 317230 }, { "epoch": 76.19, "learning_rate": 2.155588977755735e-06, "loss": 0.0009, "step": 317240 }, { "epoch": 76.2, "learning_rate": 2.1542859029185735e-06, "loss": 0.0028, "step": 317250 }, { "epoch": 76.2, "learning_rate": 2.152983213389559e-06, "loss": 0.0009, "step": 317260 }, { "epoch": 76.2, "learning_rate": 2.151680909179177e-06, "loss": 0.0009, "step": 317270 }, { "epoch": 76.2, "learning_rate": 2.1503789902979134e-06, "loss": 0.0013, "step": 317280 }, { "epoch": 76.21, "learning_rate": 2.1490774567562546e-06, "loss": 0.0009, "step": 317290 }, { "epoch": 76.21, "learning_rate": 2.147776308564681e-06, "loss": 0.0009, "step": 317300 }, { "epoch": 76.21, "learning_rate": 2.1464755457336726e-06, "loss": 0.001, "step": 317310 }, { "epoch": 76.21, "learning_rate": 2.1451751682737e-06, "loss": 0.001, "step": 317320 }, { "epoch": 76.22, "learning_rate": 2.1438751761952314e-06, "loss": 0.0009, "step": 317330 }, { "epoch": 76.22, "learning_rate": 2.142575569508759e-06, "loss": 0.0012, "step": 317340 }, { "epoch": 76.22, "learning_rate": 2.14127634822473e-06, "loss": 0.0013, "step": 317350 }, { "epoch": 76.22, "learning_rate": 2.139977512353597e-06, "loss": 0.0024, "step": 317360 }, { "epoch": 76.22, "learning_rate": 2.1386790619058405e-06, "loss": 0.0008, "step": 317370 }, { "epoch": 76.23, "learning_rate": 2.137380996891919e-06, "loss": 0.0009, "step": 317380 }, { "epoch": 76.23, "learning_rate": 2.136083317322257e-06, "loss": 0.0009, "step": 317390 }, { "epoch": 76.23, "learning_rate": 2.134786023207336e-06, "loss": 0.0009, "step": 317400 }, { "epoch": 76.23, "learning_rate": 2.133489114557591e-06, "loss": 0.0011, "step": 317410 }, { "epoch": 76.24, "learning_rate": 2.132192591383464e-06, "loss": 0.0014, "step": 317420 }, { "epoch": 76.24, "learning_rate": 2.1308964536954026e-06, "loss": 0.001, "step": 317430 }, { "epoch": 76.24, "learning_rate": 2.1296007015038366e-06, "loss": 0.001, "step": 317440 }, { "epoch": 76.24, "learning_rate": 2.128305334819203e-06, "loss": 0.001, "step": 317450 }, { "epoch": 76.24, "learning_rate": 2.127010353651937e-06, "loss": 0.0009, "step": 317460 }, { "epoch": 76.25, "learning_rate": 2.125715758012464e-06, "loss": 0.0009, "step": 317470 }, { "epoch": 76.25, "learning_rate": 2.124421547911226e-06, "loss": 0.001, "step": 317480 }, { "epoch": 76.25, "learning_rate": 2.12312772335862e-06, "loss": 0.001, "step": 317490 }, { "epoch": 76.25, "learning_rate": 2.121834284365071e-06, "loss": 0.001, "step": 317500 }, { "epoch": 76.26, "learning_rate": 2.1205412309410033e-06, "loss": 0.001, "step": 317510 }, { "epoch": 76.26, "learning_rate": 2.119248563096837e-06, "loss": 0.001, "step": 317520 }, { "epoch": 76.26, "learning_rate": 2.117956280842959e-06, "loss": 0.001, "step": 317530 }, { "epoch": 76.26, "learning_rate": 2.116664384189798e-06, "loss": 0.0009, "step": 317540 }, { "epoch": 76.27, "learning_rate": 2.1153728731477474e-06, "loss": 0.0009, "step": 317550 }, { "epoch": 76.27, "learning_rate": 2.114081747727209e-06, "loss": 0.001, "step": 317560 }, { "epoch": 76.27, "learning_rate": 2.1127910079385803e-06, "loss": 0.0009, "step": 317570 }, { "epoch": 76.27, "learning_rate": 2.111500653792259e-06, "loss": 0.0009, "step": 317580 }, { "epoch": 76.27, "learning_rate": 2.1102106852986357e-06, "loss": 0.001, "step": 317590 }, { "epoch": 76.28, "learning_rate": 2.1089211024680864e-06, "loss": 0.0009, "step": 317600 }, { "epoch": 76.28, "learning_rate": 2.1076319053110194e-06, "loss": 0.0015, "step": 317610 }, { "epoch": 76.28, "learning_rate": 2.106343093837809e-06, "loss": 0.0009, "step": 317620 }, { "epoch": 76.28, "learning_rate": 2.1050546680588144e-06, "loss": 0.0009, "step": 317630 }, { "epoch": 76.29, "learning_rate": 2.103766627984438e-06, "loss": 0.0011, "step": 317640 }, { "epoch": 76.29, "learning_rate": 2.1024789736250384e-06, "loss": 0.0011, "step": 317650 }, { "epoch": 76.29, "learning_rate": 2.101191704990985e-06, "loss": 0.0008, "step": 317660 }, { "epoch": 76.29, "learning_rate": 2.099904822092652e-06, "loss": 0.0012, "step": 317670 }, { "epoch": 76.3, "learning_rate": 2.098618324940399e-06, "loss": 0.001, "step": 317680 }, { "epoch": 76.3, "learning_rate": 2.097332213544584e-06, "loss": 0.0009, "step": 317690 }, { "epoch": 76.3, "learning_rate": 2.0960464879155652e-06, "loss": 0.001, "step": 317700 }, { "epoch": 76.3, "learning_rate": 2.094761148063701e-06, "loss": 0.0009, "step": 317710 }, { "epoch": 76.3, "learning_rate": 2.0934761939993387e-06, "loss": 0.0012, "step": 317720 }, { "epoch": 76.31, "learning_rate": 2.09219162573282e-06, "loss": 0.0009, "step": 317730 }, { "epoch": 76.31, "learning_rate": 2.090907443274498e-06, "loss": 0.0009, "step": 317740 }, { "epoch": 76.31, "learning_rate": 2.0896236466347143e-06, "loss": 0.001, "step": 317750 }, { "epoch": 76.31, "learning_rate": 2.0883402358238157e-06, "loss": 0.0009, "step": 317760 }, { "epoch": 76.32, "learning_rate": 2.0870572108521112e-06, "loss": 0.0009, "step": 317770 }, { "epoch": 76.32, "learning_rate": 2.085774571729959e-06, "loss": 0.0009, "step": 317780 }, { "epoch": 76.32, "learning_rate": 2.0844923184676736e-06, "loss": 0.0009, "step": 317790 }, { "epoch": 76.32, "learning_rate": 2.0832104510755957e-06, "loss": 0.0008, "step": 317800 }, { "epoch": 76.32, "learning_rate": 2.0819289695640344e-06, "loss": 0.001, "step": 317810 }, { "epoch": 76.33, "learning_rate": 2.0806478739433143e-06, "loss": 0.0012, "step": 317820 }, { "epoch": 76.33, "learning_rate": 2.07936716422375e-06, "loss": 0.0009, "step": 317830 }, { "epoch": 76.33, "learning_rate": 2.078086840415655e-06, "loss": 0.001, "step": 317840 }, { "epoch": 76.33, "learning_rate": 2.0768069025293545e-06, "loss": 0.0012, "step": 317850 }, { "epoch": 76.34, "learning_rate": 2.0755273505751406e-06, "loss": 0.0011, "step": 317860 }, { "epoch": 76.34, "learning_rate": 2.07424818456331e-06, "loss": 0.0008, "step": 317870 }, { "epoch": 76.34, "learning_rate": 2.072969404504188e-06, "loss": 0.001, "step": 317880 }, { "epoch": 76.34, "learning_rate": 2.0716910104080554e-06, "loss": 0.0009, "step": 317890 }, { "epoch": 76.35, "learning_rate": 2.070413002285221e-06, "loss": 0.0009, "step": 317900 }, { "epoch": 76.35, "learning_rate": 2.0691353801459533e-06, "loss": 0.0008, "step": 317910 }, { "epoch": 76.35, "learning_rate": 2.067858144000562e-06, "loss": 0.0022, "step": 317920 }, { "epoch": 76.35, "learning_rate": 2.0665812938593264e-06, "loss": 0.0013, "step": 317930 }, { "epoch": 76.35, "learning_rate": 2.0653048297325285e-06, "loss": 0.0011, "step": 317940 }, { "epoch": 76.36, "learning_rate": 2.0640287516304477e-06, "loss": 0.0011, "step": 317950 }, { "epoch": 76.36, "learning_rate": 2.062753059563366e-06, "loss": 0.001, "step": 317960 }, { "epoch": 76.36, "learning_rate": 2.0614777535415464e-06, "loss": 0.0009, "step": 317970 }, { "epoch": 76.36, "learning_rate": 2.0602028335752643e-06, "loss": 0.0008, "step": 317980 }, { "epoch": 76.37, "learning_rate": 2.0589282996747894e-06, "loss": 0.0009, "step": 317990 }, { "epoch": 76.37, "learning_rate": 2.057654151850391e-06, "loss": 0.001, "step": 318000 }, { "epoch": 76.37, "learning_rate": 2.056380390112311e-06, "loss": 0.0016, "step": 318010 }, { "epoch": 76.37, "learning_rate": 2.0551070144708252e-06, "loss": 0.001, "step": 318020 }, { "epoch": 76.38, "learning_rate": 2.0538340249361797e-06, "loss": 0.0008, "step": 318030 }, { "epoch": 76.38, "learning_rate": 2.0525614215186283e-06, "loss": 0.001, "step": 318040 }, { "epoch": 76.38, "learning_rate": 2.0512892042284236e-06, "loss": 0.0009, "step": 318050 }, { "epoch": 76.38, "learning_rate": 2.050017373075802e-06, "loss": 0.0009, "step": 318060 }, { "epoch": 76.38, "learning_rate": 2.0487459280710107e-06, "loss": 0.0011, "step": 318070 }, { "epoch": 76.39, "learning_rate": 2.0474748692242864e-06, "loss": 0.0009, "step": 318080 }, { "epoch": 76.39, "learning_rate": 2.0462041965458754e-06, "loss": 0.001, "step": 318090 }, { "epoch": 76.39, "learning_rate": 2.0449339100459986e-06, "loss": 0.0011, "step": 318100 }, { "epoch": 76.39, "learning_rate": 2.04366400973488e-06, "loss": 0.001, "step": 318110 }, { "epoch": 76.4, "learning_rate": 2.0423944956227625e-06, "loss": 0.0011, "step": 318120 }, { "epoch": 76.4, "learning_rate": 2.041125367719865e-06, "loss": 0.0026, "step": 318130 }, { "epoch": 76.4, "learning_rate": 2.039856626036413e-06, "loss": 0.001, "step": 318140 }, { "epoch": 76.4, "learning_rate": 2.038588270582603e-06, "loss": 0.0011, "step": 318150 }, { "epoch": 76.4, "learning_rate": 2.0373203013686726e-06, "loss": 0.0008, "step": 318160 }, { "epoch": 76.41, "learning_rate": 2.0360527184048183e-06, "loss": 0.0009, "step": 318170 }, { "epoch": 76.41, "learning_rate": 2.03478552170126e-06, "loss": 0.0013, "step": 318180 }, { "epoch": 76.41, "learning_rate": 2.0335187112681896e-06, "loss": 0.0009, "step": 318190 }, { "epoch": 76.41, "learning_rate": 2.032252287115821e-06, "loss": 0.0009, "step": 318200 }, { "epoch": 76.42, "learning_rate": 2.030986249254341e-06, "loss": 0.0012, "step": 318210 }, { "epoch": 76.42, "learning_rate": 2.029720597693946e-06, "loss": 0.0012, "step": 318220 }, { "epoch": 76.42, "learning_rate": 2.0284553324448506e-06, "loss": 0.001, "step": 318230 }, { "epoch": 76.42, "learning_rate": 2.0271904535172193e-06, "loss": 0.0009, "step": 318240 }, { "epoch": 76.43, "learning_rate": 2.025925960921238e-06, "loss": 0.0009, "step": 318250 }, { "epoch": 76.43, "learning_rate": 2.024661854667104e-06, "loss": 0.0011, "step": 318260 }, { "epoch": 76.43, "learning_rate": 2.023398134764992e-06, "loss": 0.0009, "step": 318270 }, { "epoch": 76.43, "learning_rate": 2.0221348012250783e-06, "loss": 0.0009, "step": 318280 }, { "epoch": 76.43, "learning_rate": 2.020871854057538e-06, "loss": 0.0011, "step": 318290 }, { "epoch": 76.44, "learning_rate": 2.0196092932725454e-06, "loss": 0.001, "step": 318300 }, { "epoch": 76.44, "learning_rate": 2.018347118880254e-06, "loss": 0.0013, "step": 318310 }, { "epoch": 76.44, "learning_rate": 2.017085330890839e-06, "loss": 0.0015, "step": 318320 }, { "epoch": 76.44, "learning_rate": 2.01582392931447e-06, "loss": 0.001, "step": 318330 }, { "epoch": 76.45, "learning_rate": 2.0145629141612887e-06, "loss": 0.0009, "step": 318340 }, { "epoch": 76.45, "learning_rate": 2.013302285441454e-06, "loss": 0.001, "step": 318350 }, { "epoch": 76.45, "learning_rate": 2.0120420431651186e-06, "loss": 0.001, "step": 318360 }, { "epoch": 76.45, "learning_rate": 2.010782187342447e-06, "loss": 0.001, "step": 318370 }, { "epoch": 76.46, "learning_rate": 2.009522717983564e-06, "loss": 0.0009, "step": 318380 }, { "epoch": 76.46, "learning_rate": 2.008263635098612e-06, "loss": 0.0009, "step": 318390 }, { "epoch": 76.46, "learning_rate": 2.0070049386977484e-06, "loss": 0.0008, "step": 318400 }, { "epoch": 76.46, "learning_rate": 2.0057466287910943e-06, "loss": 0.0008, "step": 318410 }, { "epoch": 76.46, "learning_rate": 2.004488705388796e-06, "loss": 0.0012, "step": 318420 }, { "epoch": 76.47, "learning_rate": 2.003231168500974e-06, "loss": 0.001, "step": 318430 }, { "epoch": 76.47, "learning_rate": 2.0019740181377534e-06, "loss": 0.0009, "step": 318440 }, { "epoch": 76.47, "learning_rate": 2.0007172543092643e-06, "loss": 0.0009, "step": 318450 }, { "epoch": 76.47, "learning_rate": 1.999460877025622e-06, "loss": 0.0008, "step": 318460 }, { "epoch": 76.48, "learning_rate": 1.9982048862969616e-06, "loss": 0.001, "step": 318470 }, { "epoch": 76.48, "learning_rate": 1.9969492821333756e-06, "loss": 0.001, "step": 318480 }, { "epoch": 76.48, "learning_rate": 1.9956940645449783e-06, "loss": 0.0009, "step": 318490 }, { "epoch": 76.48, "learning_rate": 1.994439233541889e-06, "loss": 0.0009, "step": 318500 }, { "epoch": 76.48, "learning_rate": 1.993184789134217e-06, "loss": 0.001, "step": 318510 }, { "epoch": 76.49, "learning_rate": 1.991930731332042e-06, "loss": 0.002, "step": 318520 }, { "epoch": 76.49, "learning_rate": 1.9906770601454847e-06, "loss": 0.001, "step": 318530 }, { "epoch": 76.49, "learning_rate": 1.9894237755846314e-06, "loss": 0.001, "step": 318540 }, { "epoch": 76.49, "learning_rate": 1.988170877659573e-06, "loss": 0.0009, "step": 318550 }, { "epoch": 76.5, "learning_rate": 1.986918366380408e-06, "loss": 0.0011, "step": 318560 }, { "epoch": 76.5, "learning_rate": 1.985666241757217e-06, "loss": 0.0013, "step": 318570 }, { "epoch": 76.5, "learning_rate": 1.984414503800086e-06, "loss": 0.0009, "step": 318580 }, { "epoch": 76.5, "learning_rate": 1.9831631525190907e-06, "loss": 0.001, "step": 318590 }, { "epoch": 76.51, "learning_rate": 1.9819121879243064e-06, "loss": 0.001, "step": 318600 }, { "epoch": 76.51, "learning_rate": 1.98066161002583e-06, "loss": 0.0014, "step": 318610 }, { "epoch": 76.51, "learning_rate": 1.9794114188337042e-06, "loss": 0.0016, "step": 318620 }, { "epoch": 76.51, "learning_rate": 1.9781616143579983e-06, "loss": 0.001, "step": 318630 }, { "epoch": 76.51, "learning_rate": 1.976912196608799e-06, "loss": 0.001, "step": 318640 }, { "epoch": 76.52, "learning_rate": 1.9756631655961533e-06, "loss": 0.0009, "step": 318650 }, { "epoch": 76.52, "learning_rate": 1.9744145213301202e-06, "loss": 0.0009, "step": 318660 }, { "epoch": 76.52, "learning_rate": 1.9731662638207636e-06, "loss": 0.001, "step": 318670 }, { "epoch": 76.52, "learning_rate": 1.971918393078126e-06, "loss": 0.0009, "step": 318680 }, { "epoch": 76.53, "learning_rate": 1.97067090911226e-06, "loss": 0.0009, "step": 318690 }, { "epoch": 76.53, "learning_rate": 1.9694238119332078e-06, "loss": 0.0015, "step": 318700 }, { "epoch": 76.53, "learning_rate": 1.968177101551022e-06, "loss": 0.0035, "step": 318710 }, { "epoch": 76.53, "learning_rate": 1.966930777975734e-06, "loss": 0.001, "step": 318720 }, { "epoch": 76.54, "learning_rate": 1.96568484121738e-06, "loss": 0.0011, "step": 318730 }, { "epoch": 76.54, "learning_rate": 1.9644392912860076e-06, "loss": 0.0011, "step": 318740 }, { "epoch": 76.54, "learning_rate": 1.9631941281916365e-06, "loss": 0.0009, "step": 318750 }, { "epoch": 76.54, "learning_rate": 1.961949351944292e-06, "loss": 0.0017, "step": 318760 }, { "epoch": 76.54, "learning_rate": 1.960704962553994e-06, "loss": 0.001, "step": 318770 }, { "epoch": 76.55, "learning_rate": 1.959460960030779e-06, "loss": 0.0009, "step": 318780 }, { "epoch": 76.55, "learning_rate": 1.958217344384655e-06, "loss": 0.0011, "step": 318790 }, { "epoch": 76.55, "learning_rate": 1.9569741156256425e-06, "loss": 0.0019, "step": 318800 }, { "epoch": 76.55, "learning_rate": 1.95573127376375e-06, "loss": 0.001, "step": 318810 }, { "epoch": 76.56, "learning_rate": 1.9544888188089804e-06, "loss": 0.0009, "step": 318820 }, { "epoch": 76.56, "learning_rate": 1.9532467507713537e-06, "loss": 0.0011, "step": 318830 }, { "epoch": 76.56, "learning_rate": 1.9520050696608616e-06, "loss": 0.0011, "step": 318840 }, { "epoch": 76.56, "learning_rate": 1.9507637754875018e-06, "loss": 0.0011, "step": 318850 }, { "epoch": 76.56, "learning_rate": 1.9495228682612776e-06, "loss": 0.0009, "step": 318860 }, { "epoch": 76.57, "learning_rate": 1.948282347992175e-06, "loss": 0.0012, "step": 318870 }, { "epoch": 76.57, "learning_rate": 1.9470422146901923e-06, "loss": 0.001, "step": 318880 }, { "epoch": 76.57, "learning_rate": 1.9458024683653208e-06, "loss": 0.0016, "step": 318890 }, { "epoch": 76.57, "learning_rate": 1.944563109027525e-06, "loss": 0.0015, "step": 318900 }, { "epoch": 76.58, "learning_rate": 1.9433241366868027e-06, "loss": 0.0011, "step": 318910 }, { "epoch": 76.58, "learning_rate": 1.942085551353123e-06, "loss": 0.0011, "step": 318920 }, { "epoch": 76.58, "learning_rate": 1.9408473530364625e-06, "loss": 0.0008, "step": 318930 }, { "epoch": 76.58, "learning_rate": 1.9396095417467953e-06, "loss": 0.0008, "step": 318940 }, { "epoch": 76.59, "learning_rate": 1.9383721174940916e-06, "loss": 0.0011, "step": 318950 }, { "epoch": 76.59, "learning_rate": 1.937135080288305e-06, "loss": 0.0011, "step": 318960 }, { "epoch": 76.59, "learning_rate": 1.9358984301394047e-06, "loss": 0.0012, "step": 318970 }, { "epoch": 76.59, "learning_rate": 1.934662167057355e-06, "loss": 0.0012, "step": 318980 }, { "epoch": 76.59, "learning_rate": 1.9334262910521096e-06, "loss": 0.001, "step": 318990 }, { "epoch": 76.6, "learning_rate": 1.9321908021336154e-06, "loss": 0.0066, "step": 319000 }, { "epoch": 76.6, "learning_rate": 1.9309557003118204e-06, "loss": 0.0011, "step": 319010 }, { "epoch": 76.6, "learning_rate": 1.929720985596678e-06, "loss": 0.001, "step": 319020 }, { "epoch": 76.6, "learning_rate": 1.928486657998135e-06, "loss": 0.001, "step": 319030 }, { "epoch": 76.61, "learning_rate": 1.927252717526118e-06, "loss": 0.0017, "step": 319040 }, { "epoch": 76.61, "learning_rate": 1.9260191641905734e-06, "loss": 0.0011, "step": 319050 }, { "epoch": 76.61, "learning_rate": 1.9247859980014328e-06, "loss": 0.0011, "step": 319060 }, { "epoch": 76.61, "learning_rate": 1.9235532189686267e-06, "loss": 0.0015, "step": 319070 }, { "epoch": 76.62, "learning_rate": 1.922320827102092e-06, "loss": 0.0008, "step": 319080 }, { "epoch": 76.62, "learning_rate": 1.9210888224117372e-06, "loss": 0.0097, "step": 319090 }, { "epoch": 76.62, "learning_rate": 1.9198572049074935e-06, "loss": 0.0014, "step": 319100 }, { "epoch": 76.62, "learning_rate": 1.918625974599275e-06, "loss": 0.0009, "step": 319110 }, { "epoch": 76.62, "learning_rate": 1.917395131497002e-06, "loss": 0.0008, "step": 319120 }, { "epoch": 76.63, "learning_rate": 1.9161646756105933e-06, "loss": 0.001, "step": 319130 }, { "epoch": 76.63, "learning_rate": 1.914934606949931e-06, "loss": 0.0009, "step": 319140 }, { "epoch": 76.63, "learning_rate": 1.9137049255249507e-06, "loss": 0.001, "step": 319150 }, { "epoch": 76.63, "learning_rate": 1.9124756313455396e-06, "loss": 0.0009, "step": 319160 }, { "epoch": 76.64, "learning_rate": 1.911246724421606e-06, "loss": 0.001, "step": 319170 }, { "epoch": 76.64, "learning_rate": 1.910018204763037e-06, "loss": 0.0012, "step": 319180 }, { "epoch": 76.64, "learning_rate": 1.908790072379735e-06, "loss": 0.0016, "step": 319190 }, { "epoch": 76.64, "learning_rate": 1.9075623272815813e-06, "loss": 0.0011, "step": 319200 }, { "epoch": 76.64, "learning_rate": 1.9063349694784681e-06, "loss": 0.0009, "step": 319210 }, { "epoch": 76.65, "learning_rate": 1.9051079989802822e-06, "loss": 0.001, "step": 319220 }, { "epoch": 76.65, "learning_rate": 1.9038814157968987e-06, "loss": 0.0009, "step": 319230 }, { "epoch": 76.65, "learning_rate": 1.9026552199381986e-06, "loss": 0.001, "step": 319240 }, { "epoch": 76.65, "learning_rate": 1.901429411414052e-06, "loss": 0.0025, "step": 319250 }, { "epoch": 76.66, "learning_rate": 1.9002039902343394e-06, "loss": 0.001, "step": 319260 }, { "epoch": 76.66, "learning_rate": 1.898978956408931e-06, "loss": 0.001, "step": 319270 }, { "epoch": 76.66, "learning_rate": 1.8977543099476747e-06, "loss": 0.0012, "step": 319280 }, { "epoch": 76.66, "learning_rate": 1.8965300508604511e-06, "loss": 0.0007, "step": 319290 }, { "epoch": 76.67, "learning_rate": 1.895306179157108e-06, "loss": 0.0009, "step": 319300 }, { "epoch": 76.67, "learning_rate": 1.89408269484751e-06, "loss": 0.0014, "step": 319310 }, { "epoch": 76.67, "learning_rate": 1.8928595979415042e-06, "loss": 0.0009, "step": 319320 }, { "epoch": 76.67, "learning_rate": 1.891636888448939e-06, "loss": 0.0008, "step": 319330 }, { "epoch": 76.67, "learning_rate": 1.8904145663796669e-06, "loss": 0.0009, "step": 319340 }, { "epoch": 76.68, "learning_rate": 1.8891926317435193e-06, "loss": 0.0009, "step": 319350 }, { "epoch": 76.68, "learning_rate": 1.8879710845503606e-06, "loss": 0.0009, "step": 319360 }, { "epoch": 76.68, "learning_rate": 1.886749924810005e-06, "loss": 0.0012, "step": 319370 }, { "epoch": 76.68, "learning_rate": 1.8855291525322893e-06, "loss": 0.0008, "step": 319380 }, { "epoch": 76.69, "learning_rate": 1.8843087677270554e-06, "loss": 0.0009, "step": 319390 }, { "epoch": 76.69, "learning_rate": 1.8830887704041234e-06, "loss": 0.001, "step": 319400 }, { "epoch": 76.69, "learning_rate": 1.8818691605733296e-06, "loss": 0.001, "step": 319410 }, { "epoch": 76.69, "learning_rate": 1.880649938244472e-06, "loss": 0.001, "step": 319420 }, { "epoch": 76.7, "learning_rate": 1.8794311034273925e-06, "loss": 0.0012, "step": 319430 }, { "epoch": 76.7, "learning_rate": 1.8782126561319002e-06, "loss": 0.0009, "step": 319440 }, { "epoch": 76.7, "learning_rate": 1.876994596367798e-06, "loss": 0.0009, "step": 319450 }, { "epoch": 76.7, "learning_rate": 1.8757769241449064e-06, "loss": 0.0009, "step": 319460 }, { "epoch": 76.7, "learning_rate": 1.8745596394730281e-06, "loss": 0.001, "step": 319470 }, { "epoch": 76.71, "learning_rate": 1.8733427423619666e-06, "loss": 0.001, "step": 319480 }, { "epoch": 76.71, "learning_rate": 1.8721262328215084e-06, "loss": 0.0009, "step": 319490 }, { "epoch": 76.71, "learning_rate": 1.870910110861479e-06, "loss": 0.0009, "step": 319500 }, { "epoch": 76.71, "learning_rate": 1.8696943764916486e-06, "loss": 0.001, "step": 319510 }, { "epoch": 76.72, "learning_rate": 1.8684790297218036e-06, "loss": 0.001, "step": 319520 }, { "epoch": 76.72, "learning_rate": 1.8672640705617529e-06, "loss": 0.0017, "step": 319530 }, { "epoch": 76.72, "learning_rate": 1.8660494990212718e-06, "loss": 0.0009, "step": 319540 }, { "epoch": 76.72, "learning_rate": 1.8648353151101306e-06, "loss": 0.0011, "step": 319550 }, { "epoch": 76.72, "learning_rate": 1.8636215188381213e-06, "loss": 0.0009, "step": 319560 }, { "epoch": 76.73, "learning_rate": 1.8624081102150137e-06, "loss": 0.0009, "step": 319570 }, { "epoch": 76.73, "learning_rate": 1.8611950892505836e-06, "loss": 0.001, "step": 319580 }, { "epoch": 76.73, "learning_rate": 1.8599824559545843e-06, "loss": 0.0011, "step": 319590 }, { "epoch": 76.73, "learning_rate": 1.8587702103368021e-06, "loss": 0.0008, "step": 319600 }, { "epoch": 76.74, "learning_rate": 1.8575583524069906e-06, "loss": 0.001, "step": 319610 }, { "epoch": 76.74, "learning_rate": 1.8563468821748974e-06, "loss": 0.0012, "step": 319620 }, { "epoch": 76.74, "learning_rate": 1.8551357996502983e-06, "loss": 0.0011, "step": 319630 }, { "epoch": 76.74, "learning_rate": 1.8539251048429352e-06, "loss": 0.0015, "step": 319640 }, { "epoch": 76.75, "learning_rate": 1.8527147977625614e-06, "loss": 0.0012, "step": 319650 }, { "epoch": 76.75, "learning_rate": 1.8515048784189193e-06, "loss": 0.0025, "step": 319660 }, { "epoch": 76.75, "learning_rate": 1.8502953468217566e-06, "loss": 0.001, "step": 319670 }, { "epoch": 76.75, "learning_rate": 1.8490862029808154e-06, "loss": 0.0015, "step": 319680 }, { "epoch": 76.75, "learning_rate": 1.8478774469058268e-06, "loss": 0.001, "step": 319690 }, { "epoch": 76.76, "learning_rate": 1.8466690786065333e-06, "loss": 0.0027, "step": 319700 }, { "epoch": 76.76, "learning_rate": 1.8454610980926602e-06, "loss": 0.0079, "step": 319710 }, { "epoch": 76.76, "learning_rate": 1.8442535053739384e-06, "loss": 0.001, "step": 319720 }, { "epoch": 76.76, "learning_rate": 1.8430463004600829e-06, "loss": 0.0009, "step": 319730 }, { "epoch": 76.77, "learning_rate": 1.8418394833608355e-06, "loss": 0.0009, "step": 319740 }, { "epoch": 76.77, "learning_rate": 1.8406330540858996e-06, "loss": 0.001, "step": 319750 }, { "epoch": 76.77, "learning_rate": 1.8394270126449898e-06, "loss": 0.0008, "step": 319760 }, { "epoch": 76.77, "learning_rate": 1.838221359047826e-06, "loss": 0.0009, "step": 319770 }, { "epoch": 76.78, "learning_rate": 1.837016093304117e-06, "loss": 0.0011, "step": 319780 }, { "epoch": 76.78, "learning_rate": 1.8358112154235662e-06, "loss": 0.0012, "step": 319790 }, { "epoch": 76.78, "learning_rate": 1.8346067254158772e-06, "loss": 0.0012, "step": 319800 }, { "epoch": 76.78, "learning_rate": 1.8334026232907474e-06, "loss": 0.001, "step": 319810 }, { "epoch": 76.78, "learning_rate": 1.8321989090578807e-06, "loss": 0.0012, "step": 319820 }, { "epoch": 76.79, "learning_rate": 1.830995582726963e-06, "loss": 0.001, "step": 319830 }, { "epoch": 76.79, "learning_rate": 1.8297926443076873e-06, "loss": 0.0011, "step": 319840 }, { "epoch": 76.79, "learning_rate": 1.8285900938097456e-06, "loss": 0.0014, "step": 319850 }, { "epoch": 76.79, "learning_rate": 1.8273879312428132e-06, "loss": 0.001, "step": 319860 }, { "epoch": 76.8, "learning_rate": 1.8261861566165717e-06, "loss": 0.0008, "step": 319870 }, { "epoch": 76.8, "learning_rate": 1.8249847699407186e-06, "loss": 0.0011, "step": 319880 }, { "epoch": 76.8, "learning_rate": 1.8237837712249073e-06, "loss": 0.001, "step": 319890 }, { "epoch": 76.8, "learning_rate": 1.8225831604788079e-06, "loss": 0.0008, "step": 319900 }, { "epoch": 76.8, "learning_rate": 1.8213829377121073e-06, "loss": 0.0009, "step": 319910 }, { "epoch": 76.81, "learning_rate": 1.8201831029344585e-06, "loss": 0.0068, "step": 319920 }, { "epoch": 76.81, "learning_rate": 1.8189836561555318e-06, "loss": 0.001, "step": 319930 }, { "epoch": 76.81, "learning_rate": 1.817784597384975e-06, "loss": 0.0008, "step": 319940 }, { "epoch": 76.81, "learning_rate": 1.8165859266324525e-06, "loss": 0.001, "step": 319950 }, { "epoch": 76.82, "learning_rate": 1.8153876439076178e-06, "loss": 0.0009, "step": 319960 }, { "epoch": 76.82, "learning_rate": 1.8141897492201133e-06, "loss": 0.0009, "step": 319970 }, { "epoch": 76.82, "learning_rate": 1.8129922425796031e-06, "loss": 0.0012, "step": 319980 }, { "epoch": 76.82, "learning_rate": 1.8117951239957075e-06, "loss": 0.0012, "step": 319990 }, { "epoch": 76.83, "learning_rate": 1.81059839347808e-06, "loss": 0.0009, "step": 320000 }, { "epoch": 76.83, "learning_rate": 1.8094020510363573e-06, "loss": 0.001, "step": 320010 }, { "epoch": 76.83, "learning_rate": 1.8082060966801816e-06, "loss": 0.0016, "step": 320020 }, { "epoch": 76.83, "learning_rate": 1.807010530419162e-06, "loss": 0.0011, "step": 320030 }, { "epoch": 76.83, "learning_rate": 1.8058153522629463e-06, "loss": 0.0021, "step": 320040 }, { "epoch": 76.84, "learning_rate": 1.8046205622211543e-06, "loss": 0.001, "step": 320050 }, { "epoch": 76.84, "learning_rate": 1.8034261603034063e-06, "loss": 0.0009, "step": 320060 }, { "epoch": 76.84, "learning_rate": 1.8022321465193227e-06, "loss": 0.001, "step": 320070 }, { "epoch": 76.84, "learning_rate": 1.8010385208785118e-06, "loss": 0.001, "step": 320080 }, { "epoch": 76.85, "learning_rate": 1.7998452833905999e-06, "loss": 0.0011, "step": 320090 }, { "epoch": 76.85, "learning_rate": 1.7986524340651845e-06, "loss": 0.0009, "step": 320100 }, { "epoch": 76.85, "learning_rate": 1.797459972911869e-06, "loss": 0.0011, "step": 320110 }, { "epoch": 76.85, "learning_rate": 1.7962678999402737e-06, "loss": 0.0018, "step": 320120 }, { "epoch": 76.86, "learning_rate": 1.7950762151599855e-06, "loss": 0.0018, "step": 320130 }, { "epoch": 76.86, "learning_rate": 1.7938849185805962e-06, "loss": 0.0009, "step": 320140 }, { "epoch": 76.86, "learning_rate": 1.7926940102117151e-06, "loss": 0.0011, "step": 320150 }, { "epoch": 76.86, "learning_rate": 1.7915034900629234e-06, "loss": 0.001, "step": 320160 }, { "epoch": 76.86, "learning_rate": 1.790313358143808e-06, "loss": 0.0014, "step": 320170 }, { "epoch": 76.87, "learning_rate": 1.7891236144639556e-06, "loss": 0.0008, "step": 320180 }, { "epoch": 76.87, "learning_rate": 1.7879342590329474e-06, "loss": 0.0011, "step": 320190 }, { "epoch": 76.87, "learning_rate": 1.786745291860359e-06, "loss": 0.0011, "step": 320200 }, { "epoch": 76.87, "learning_rate": 1.785556712955766e-06, "loss": 0.0011, "step": 320210 }, { "epoch": 76.88, "learning_rate": 1.7843685223287443e-06, "loss": 0.0009, "step": 320220 }, { "epoch": 76.88, "learning_rate": 1.7831807199888584e-06, "loss": 0.0012, "step": 320230 }, { "epoch": 76.88, "learning_rate": 1.781993305945673e-06, "loss": 0.001, "step": 320240 }, { "epoch": 76.88, "learning_rate": 1.7808062802087522e-06, "loss": 0.0009, "step": 320250 }, { "epoch": 76.88, "learning_rate": 1.779619642787661e-06, "loss": 0.0041, "step": 320260 }, { "epoch": 76.89, "learning_rate": 1.7784333936919472e-06, "loss": 0.0009, "step": 320270 }, { "epoch": 76.89, "learning_rate": 1.7772475329311644e-06, "loss": 0.001, "step": 320280 }, { "epoch": 76.89, "learning_rate": 1.7760620605148658e-06, "loss": 0.0009, "step": 320290 }, { "epoch": 76.89, "learning_rate": 1.7748769764525996e-06, "loss": 0.0011, "step": 320300 }, { "epoch": 76.9, "learning_rate": 1.7736922807539025e-06, "loss": 0.0011, "step": 320310 }, { "epoch": 76.9, "learning_rate": 1.7725079734283223e-06, "loss": 0.0014, "step": 320320 }, { "epoch": 76.9, "learning_rate": 1.771324054485396e-06, "loss": 0.001, "step": 320330 }, { "epoch": 76.9, "learning_rate": 1.7701405239346546e-06, "loss": 0.0009, "step": 320340 }, { "epoch": 76.91, "learning_rate": 1.7689573817856241e-06, "loss": 0.0019, "step": 320350 }, { "epoch": 76.91, "learning_rate": 1.7677746280478469e-06, "loss": 0.0009, "step": 320360 }, { "epoch": 76.91, "learning_rate": 1.7665922627308317e-06, "loss": 0.001, "step": 320370 }, { "epoch": 76.91, "learning_rate": 1.7654102858441103e-06, "loss": 0.0012, "step": 320380 }, { "epoch": 76.91, "learning_rate": 1.7642286973971966e-06, "loss": 0.0009, "step": 320390 }, { "epoch": 76.92, "learning_rate": 1.7630474973996224e-06, "loss": 0.0009, "step": 320400 }, { "epoch": 76.92, "learning_rate": 1.761866685860869e-06, "loss": 0.0013, "step": 320410 }, { "epoch": 76.92, "learning_rate": 1.760686262790473e-06, "loss": 0.0009, "step": 320420 }, { "epoch": 76.92, "learning_rate": 1.7595062281979268e-06, "loss": 0.0012, "step": 320430 }, { "epoch": 76.93, "learning_rate": 1.7583265820927398e-06, "loss": 0.001, "step": 320440 }, { "epoch": 76.93, "learning_rate": 1.757147324484404e-06, "loss": 0.0024, "step": 320450 }, { "epoch": 76.93, "learning_rate": 1.755968455382423e-06, "loss": 0.001, "step": 320460 }, { "epoch": 76.93, "learning_rate": 1.7547899747962948e-06, "loss": 0.0009, "step": 320470 }, { "epoch": 76.94, "learning_rate": 1.7536118827354897e-06, "loss": 0.001, "step": 320480 }, { "epoch": 76.94, "learning_rate": 1.7524341792095167e-06, "loss": 0.0014, "step": 320490 }, { "epoch": 76.94, "learning_rate": 1.7512568642278625e-06, "loss": 0.001, "step": 320500 }, { "epoch": 76.94, "learning_rate": 1.7500799377999866e-06, "loss": 0.0013, "step": 320510 }, { "epoch": 76.94, "learning_rate": 1.7489033999353754e-06, "loss": 0.001, "step": 320520 }, { "epoch": 76.95, "learning_rate": 1.7477272506435106e-06, "loss": 0.001, "step": 320530 }, { "epoch": 76.95, "learning_rate": 1.7465514899338676e-06, "loss": 0.0008, "step": 320540 }, { "epoch": 76.95, "learning_rate": 1.7453761178158945e-06, "loss": 0.0009, "step": 320550 }, { "epoch": 77.0, "learning_rate": 1.7442011342990783e-06, "loss": 0.001, "step": 320560 }, { "epoch": 77.0, "learning_rate": 1.743026539392867e-06, "loss": 0.0032, "step": 320570 }, { "epoch": 77.01, "learning_rate": 1.7418523331067304e-06, "loss": 0.001, "step": 320580 }, { "epoch": 77.01, "learning_rate": 1.7406785154501171e-06, "loss": 0.0009, "step": 320590 }, { "epoch": 77.01, "learning_rate": 1.7395050864324803e-06, "loss": 0.001, "step": 320600 }, { "epoch": 77.01, "learning_rate": 1.7383320460632735e-06, "loss": 0.0009, "step": 320610 }, { "epoch": 77.02, "learning_rate": 1.7371593943519394e-06, "loss": 0.0011, "step": 320620 }, { "epoch": 77.02, "learning_rate": 1.7359871313079257e-06, "loss": 0.0009, "step": 320630 }, { "epoch": 77.02, "learning_rate": 1.734815256940675e-06, "loss": 0.001, "step": 320640 }, { "epoch": 77.02, "learning_rate": 1.7336437712596131e-06, "loss": 0.0014, "step": 320650 }, { "epoch": 77.02, "learning_rate": 1.732472674274188e-06, "loss": 0.0011, "step": 320660 }, { "epoch": 77.03, "learning_rate": 1.73130196599382e-06, "loss": 0.001, "step": 320670 }, { "epoch": 77.03, "learning_rate": 1.7301316464279515e-06, "loss": 0.0012, "step": 320680 }, { "epoch": 77.03, "learning_rate": 1.7289617155859806e-06, "loss": 0.001, "step": 320690 }, { "epoch": 77.03, "learning_rate": 1.727792173477355e-06, "loss": 0.001, "step": 320700 }, { "epoch": 77.04, "learning_rate": 1.7266230201114786e-06, "loss": 0.001, "step": 320710 }, { "epoch": 77.04, "learning_rate": 1.7254542554977771e-06, "loss": 0.0011, "step": 320720 }, { "epoch": 77.04, "learning_rate": 1.7242858796456541e-06, "loss": 0.001, "step": 320730 }, { "epoch": 77.04, "learning_rate": 1.7231178925645186e-06, "loss": 0.0011, "step": 320740 }, { "epoch": 77.05, "learning_rate": 1.7219502942637854e-06, "loss": 0.0009, "step": 320750 }, { "epoch": 77.05, "learning_rate": 1.7207830847528418e-06, "loss": 0.001, "step": 320760 }, { "epoch": 77.05, "learning_rate": 1.7196162640411073e-06, "loss": 0.0009, "step": 320770 }, { "epoch": 77.05, "learning_rate": 1.7184498321379694e-06, "loss": 0.0009, "step": 320780 }, { "epoch": 77.05, "learning_rate": 1.7172837890528148e-06, "loss": 0.0019, "step": 320790 }, { "epoch": 77.06, "learning_rate": 1.7161181347950417e-06, "loss": 0.0009, "step": 320800 }, { "epoch": 77.06, "learning_rate": 1.714952869374037e-06, "loss": 0.0009, "step": 320810 }, { "epoch": 77.06, "learning_rate": 1.7137879927991818e-06, "loss": 0.0009, "step": 320820 }, { "epoch": 77.06, "learning_rate": 1.7126235050798578e-06, "loss": 0.0017, "step": 320830 }, { "epoch": 77.07, "learning_rate": 1.7114594062254463e-06, "loss": 0.0008, "step": 320840 }, { "epoch": 77.07, "learning_rate": 1.710295696245312e-06, "loss": 0.001, "step": 320850 }, { "epoch": 77.07, "learning_rate": 1.7091323751488365e-06, "loss": 0.0022, "step": 320860 }, { "epoch": 77.07, "learning_rate": 1.7079694429453897e-06, "loss": 0.001, "step": 320870 }, { "epoch": 77.08, "learning_rate": 1.706806899644331e-06, "loss": 0.0009, "step": 320880 }, { "epoch": 77.08, "learning_rate": 1.705644745255014e-06, "loss": 0.001, "step": 320890 }, { "epoch": 77.08, "learning_rate": 1.7044829797868145e-06, "loss": 0.001, "step": 320900 }, { "epoch": 77.08, "learning_rate": 1.7033216032490806e-06, "loss": 0.0008, "step": 320910 }, { "epoch": 77.08, "learning_rate": 1.7021606156511716e-06, "loss": 0.0012, "step": 320920 }, { "epoch": 77.09, "learning_rate": 1.7010000170024188e-06, "loss": 0.0009, "step": 320930 }, { "epoch": 77.09, "learning_rate": 1.6998398073121923e-06, "loss": 0.0009, "step": 320940 }, { "epoch": 77.09, "learning_rate": 1.6986799865898184e-06, "loss": 0.0011, "step": 320950 }, { "epoch": 77.09, "learning_rate": 1.6975205548446448e-06, "loss": 0.0009, "step": 320960 }, { "epoch": 77.1, "learning_rate": 1.6963615120860032e-06, "loss": 0.001, "step": 320970 }, { "epoch": 77.1, "learning_rate": 1.695202858323236e-06, "loss": 0.0014, "step": 320980 }, { "epoch": 77.1, "learning_rate": 1.694044593565669e-06, "loss": 0.0011, "step": 320990 }, { "epoch": 77.1, "learning_rate": 1.6928867178226226e-06, "loss": 0.0009, "step": 321000 }, { "epoch": 77.1, "learning_rate": 1.6917292311034393e-06, "loss": 0.0009, "step": 321010 }, { "epoch": 77.11, "learning_rate": 1.690572133417423e-06, "loss": 0.0051, "step": 321020 }, { "epoch": 77.11, "learning_rate": 1.6894154247738937e-06, "loss": 0.0009, "step": 321030 }, { "epoch": 77.11, "learning_rate": 1.6882591051821773e-06, "loss": 0.0016, "step": 321040 }, { "epoch": 77.11, "learning_rate": 1.687103174651583e-06, "loss": 0.001, "step": 321050 }, { "epoch": 77.12, "learning_rate": 1.6859476331914148e-06, "loss": 0.001, "step": 321060 }, { "epoch": 77.12, "learning_rate": 1.6847924808109817e-06, "loss": 0.001, "step": 321070 }, { "epoch": 77.12, "learning_rate": 1.6836377175195871e-06, "loss": 0.0009, "step": 321080 }, { "epoch": 77.12, "learning_rate": 1.6824833433265242e-06, "loss": 0.0009, "step": 321090 }, { "epoch": 77.13, "learning_rate": 1.6813293582410904e-06, "loss": 0.0009, "step": 321100 }, { "epoch": 77.13, "learning_rate": 1.68017576227259e-06, "loss": 0.0009, "step": 321110 }, { "epoch": 77.13, "learning_rate": 1.679022555430304e-06, "loss": 0.001, "step": 321120 }, { "epoch": 77.13, "learning_rate": 1.6778697377235197e-06, "loss": 0.001, "step": 321130 }, { "epoch": 77.13, "learning_rate": 1.6767173091615129e-06, "loss": 0.001, "step": 321140 }, { "epoch": 77.14, "learning_rate": 1.6755652697535817e-06, "loss": 0.001, "step": 321150 }, { "epoch": 77.14, "learning_rate": 1.6744136195089965e-06, "loss": 0.0009, "step": 321160 }, { "epoch": 77.14, "learning_rate": 1.6732623584370222e-06, "loss": 0.0011, "step": 321170 }, { "epoch": 77.14, "learning_rate": 1.6721114865469457e-06, "loss": 0.001, "step": 321180 }, { "epoch": 77.15, "learning_rate": 1.6709610038480262e-06, "loss": 0.001, "step": 321190 }, { "epoch": 77.15, "learning_rate": 1.6698109103495284e-06, "loss": 0.0009, "step": 321200 }, { "epoch": 77.15, "learning_rate": 1.668661206060712e-06, "loss": 0.0019, "step": 321210 }, { "epoch": 77.15, "learning_rate": 1.6675118909908471e-06, "loss": 0.0008, "step": 321220 }, { "epoch": 77.16, "learning_rate": 1.6663629651491763e-06, "loss": 0.001, "step": 321230 }, { "epoch": 77.16, "learning_rate": 1.6652144285449535e-06, "loss": 0.001, "step": 321240 }, { "epoch": 77.16, "learning_rate": 1.664066281187443e-06, "loss": 0.0022, "step": 321250 }, { "epoch": 77.16, "learning_rate": 1.6629185230858768e-06, "loss": 0.0009, "step": 321260 }, { "epoch": 77.16, "learning_rate": 1.6617711542494917e-06, "loss": 0.0011, "step": 321270 }, { "epoch": 77.17, "learning_rate": 1.6606241746875473e-06, "loss": 0.001, "step": 321280 }, { "epoch": 77.17, "learning_rate": 1.6594775844092636e-06, "loss": 0.0008, "step": 321290 }, { "epoch": 77.17, "learning_rate": 1.6583313834238833e-06, "loss": 0.001, "step": 321300 }, { "epoch": 77.17, "learning_rate": 1.6571855717406383e-06, "loss": 0.0008, "step": 321310 }, { "epoch": 77.18, "learning_rate": 1.6560401493687483e-06, "loss": 0.001, "step": 321320 }, { "epoch": 77.18, "learning_rate": 1.6548951163174397e-06, "loss": 0.0008, "step": 321330 }, { "epoch": 77.18, "learning_rate": 1.6537504725959386e-06, "loss": 0.001, "step": 321340 }, { "epoch": 77.18, "learning_rate": 1.6526062182134595e-06, "loss": 0.0011, "step": 321350 }, { "epoch": 77.18, "learning_rate": 1.6514623531792172e-06, "loss": 0.0011, "step": 321360 }, { "epoch": 77.19, "learning_rate": 1.6503188775024215e-06, "loss": 0.001, "step": 321370 }, { "epoch": 77.19, "learning_rate": 1.6491757911922811e-06, "loss": 0.0011, "step": 321380 }, { "epoch": 77.19, "learning_rate": 1.6480330942580112e-06, "loss": 0.0013, "step": 321390 }, { "epoch": 77.19, "learning_rate": 1.646890786708799e-06, "loss": 0.0017, "step": 321400 }, { "epoch": 77.2, "learning_rate": 1.645748868553848e-06, "loss": 0.0009, "step": 321410 }, { "epoch": 77.2, "learning_rate": 1.644607339802362e-06, "loss": 0.0009, "step": 321420 }, { "epoch": 77.2, "learning_rate": 1.6434662004635282e-06, "loss": 0.0011, "step": 321430 }, { "epoch": 77.2, "learning_rate": 1.642325450546539e-06, "loss": 0.0025, "step": 321440 }, { "epoch": 77.21, "learning_rate": 1.6411850900605764e-06, "loss": 0.0009, "step": 321450 }, { "epoch": 77.21, "learning_rate": 1.6400451190148324e-06, "loss": 0.0011, "step": 321460 }, { "epoch": 77.21, "learning_rate": 1.638905537418478e-06, "loss": 0.0013, "step": 321470 }, { "epoch": 77.21, "learning_rate": 1.6377663452806834e-06, "loss": 0.0011, "step": 321480 }, { "epoch": 77.21, "learning_rate": 1.6366275426106526e-06, "loss": 0.0009, "step": 321490 }, { "epoch": 77.22, "learning_rate": 1.6354891294175279e-06, "loss": 0.0013, "step": 321500 }, { "epoch": 77.22, "learning_rate": 1.63435110571048e-06, "loss": 0.007, "step": 321510 }, { "epoch": 77.22, "learning_rate": 1.6332134714986847e-06, "loss": 0.0011, "step": 321520 }, { "epoch": 77.22, "learning_rate": 1.632076226791307e-06, "loss": 0.0009, "step": 321530 }, { "epoch": 77.23, "learning_rate": 1.630939371597484e-06, "loss": 0.001, "step": 321540 }, { "epoch": 77.23, "learning_rate": 1.629802905926392e-06, "loss": 0.0009, "step": 321550 }, { "epoch": 77.23, "learning_rate": 1.6286668297871732e-06, "loss": 0.0009, "step": 321560 }, { "epoch": 77.23, "learning_rate": 1.627531143188976e-06, "loss": 0.001, "step": 321570 }, { "epoch": 77.24, "learning_rate": 1.6263958461409545e-06, "loss": 0.0014, "step": 321580 }, { "epoch": 77.24, "learning_rate": 1.6252609386522455e-06, "loss": 0.0008, "step": 321590 }, { "epoch": 77.24, "learning_rate": 1.6241264207319806e-06, "loss": 0.001, "step": 321600 }, { "epoch": 77.24, "learning_rate": 1.6229922923893137e-06, "loss": 0.0011, "step": 321610 }, { "epoch": 77.24, "learning_rate": 1.6218585536333598e-06, "loss": 0.0011, "step": 321620 }, { "epoch": 77.25, "learning_rate": 1.620725204473267e-06, "loss": 0.0011, "step": 321630 }, { "epoch": 77.25, "learning_rate": 1.61959224491815e-06, "loss": 0.0009, "step": 321640 }, { "epoch": 77.25, "learning_rate": 1.6184596749771297e-06, "loss": 0.0012, "step": 321650 }, { "epoch": 77.25, "learning_rate": 1.6173274946593376e-06, "loss": 0.001, "step": 321660 }, { "epoch": 77.26, "learning_rate": 1.616195703973894e-06, "loss": 0.0008, "step": 321670 }, { "epoch": 77.26, "learning_rate": 1.6150643029298917e-06, "loss": 0.0009, "step": 321680 }, { "epoch": 77.26, "learning_rate": 1.613933291536468e-06, "loss": 0.0031, "step": 321690 }, { "epoch": 77.26, "learning_rate": 1.6128026698027154e-06, "loss": 0.0011, "step": 321700 }, { "epoch": 77.26, "learning_rate": 1.6116724377377435e-06, "loss": 0.0043, "step": 321710 }, { "epoch": 77.27, "learning_rate": 1.6105425953506559e-06, "loss": 0.0009, "step": 321720 }, { "epoch": 77.27, "learning_rate": 1.6094131426505455e-06, "loss": 0.0011, "step": 321730 }, { "epoch": 77.27, "learning_rate": 1.608284079646516e-06, "loss": 0.0009, "step": 321740 }, { "epoch": 77.27, "learning_rate": 1.607155406347649e-06, "loss": 0.0011, "step": 321750 }, { "epoch": 77.28, "learning_rate": 1.6060271227630487e-06, "loss": 0.0009, "step": 321760 }, { "epoch": 77.28, "learning_rate": 1.6048992289017905e-06, "loss": 0.0012, "step": 321770 }, { "epoch": 77.28, "learning_rate": 1.6037717247729622e-06, "loss": 0.001, "step": 321780 }, { "epoch": 77.28, "learning_rate": 1.6026446103856341e-06, "loss": 0.0009, "step": 321790 }, { "epoch": 77.29, "learning_rate": 1.6015178857488932e-06, "loss": 0.0008, "step": 321800 }, { "epoch": 77.29, "learning_rate": 1.6003915508718159e-06, "loss": 0.0013, "step": 321810 }, { "epoch": 77.29, "learning_rate": 1.599265605763467e-06, "loss": 0.0009, "step": 321820 }, { "epoch": 77.29, "learning_rate": 1.5981400504329114e-06, "loss": 0.001, "step": 321830 }, { "epoch": 77.29, "learning_rate": 1.597014884889214e-06, "loss": 0.001, "step": 321840 }, { "epoch": 77.3, "learning_rate": 1.5958901091414402e-06, "loss": 0.0009, "step": 321850 }, { "epoch": 77.3, "learning_rate": 1.594765723198649e-06, "loss": 0.0012, "step": 321860 }, { "epoch": 77.3, "learning_rate": 1.5936417270698888e-06, "loss": 0.001, "step": 321870 }, { "epoch": 77.3, "learning_rate": 1.5925181207642193e-06, "loss": 0.0028, "step": 321880 }, { "epoch": 77.31, "learning_rate": 1.5913949042906717e-06, "loss": 0.001, "step": 321890 }, { "epoch": 77.31, "learning_rate": 1.5902720776583168e-06, "loss": 0.0012, "step": 321900 }, { "epoch": 77.31, "learning_rate": 1.5891496408761864e-06, "loss": 0.0008, "step": 321910 }, { "epoch": 77.31, "learning_rate": 1.5880275939533063e-06, "loss": 0.0044, "step": 321920 }, { "epoch": 77.32, "learning_rate": 1.5869059368987305e-06, "loss": 0.0012, "step": 321930 }, { "epoch": 77.32, "learning_rate": 1.5857846697214795e-06, "loss": 0.0022, "step": 321940 }, { "epoch": 77.32, "learning_rate": 1.5846637924305962e-06, "loss": 0.0009, "step": 321950 }, { "epoch": 77.32, "learning_rate": 1.5835433050350956e-06, "loss": 0.0032, "step": 321960 }, { "epoch": 77.32, "learning_rate": 1.5824232075440038e-06, "loss": 0.001, "step": 321970 }, { "epoch": 77.33, "learning_rate": 1.5813034999663467e-06, "loss": 0.0076, "step": 321980 }, { "epoch": 77.33, "learning_rate": 1.580184182311134e-06, "loss": 0.001, "step": 321990 }, { "epoch": 77.33, "learning_rate": 1.5790652545873862e-06, "loss": 0.001, "step": 322000 }, { "epoch": 77.33, "learning_rate": 1.5779467168041072e-06, "loss": 0.0009, "step": 322010 }, { "epoch": 77.34, "learning_rate": 1.5768285689703067e-06, "loss": 0.0009, "step": 322020 }, { "epoch": 77.34, "learning_rate": 1.5757108110949881e-06, "loss": 0.0015, "step": 322030 }, { "epoch": 77.34, "learning_rate": 1.5745934431871612e-06, "loss": 0.001, "step": 322040 }, { "epoch": 77.34, "learning_rate": 1.5734764652558242e-06, "loss": 0.0009, "step": 322050 }, { "epoch": 77.34, "learning_rate": 1.572359877309959e-06, "loss": 0.0012, "step": 322060 }, { "epoch": 77.35, "learning_rate": 1.5712436793585694e-06, "loss": 0.0011, "step": 322070 }, { "epoch": 77.35, "learning_rate": 1.5701278714106371e-06, "loss": 0.0016, "step": 322080 }, { "epoch": 77.35, "learning_rate": 1.5690124534751549e-06, "loss": 0.001, "step": 322090 }, { "epoch": 77.35, "learning_rate": 1.567897425561099e-06, "loss": 0.0021, "step": 322100 }, { "epoch": 77.36, "learning_rate": 1.566782787677451e-06, "loss": 0.0009, "step": 322110 }, { "epoch": 77.36, "learning_rate": 1.5656685398331927e-06, "loss": 0.001, "step": 322120 }, { "epoch": 77.36, "learning_rate": 1.5645546820372836e-06, "loss": 0.0009, "step": 322130 }, { "epoch": 77.36, "learning_rate": 1.563441214298711e-06, "loss": 0.0058, "step": 322140 }, { "epoch": 77.37, "learning_rate": 1.5623281366264343e-06, "loss": 0.0009, "step": 322150 }, { "epoch": 77.37, "learning_rate": 1.5612154490294073e-06, "loss": 0.001, "step": 322160 }, { "epoch": 77.37, "learning_rate": 1.5601031515166064e-06, "loss": 0.0009, "step": 322170 }, { "epoch": 77.37, "learning_rate": 1.55899124409698e-06, "loss": 0.0009, "step": 322180 }, { "epoch": 77.37, "learning_rate": 1.5578797267794932e-06, "loss": 0.001, "step": 322190 }, { "epoch": 77.38, "learning_rate": 1.5567685995730718e-06, "loss": 0.0008, "step": 322200 }, { "epoch": 77.38, "learning_rate": 1.5556578624866924e-06, "loss": 0.0008, "step": 322210 }, { "epoch": 77.38, "learning_rate": 1.5545475155292865e-06, "loss": 0.0011, "step": 322220 }, { "epoch": 77.38, "learning_rate": 1.5534375587097972e-06, "loss": 0.0013, "step": 322230 }, { "epoch": 77.39, "learning_rate": 1.552327992037167e-06, "loss": 0.001, "step": 322240 }, { "epoch": 77.39, "learning_rate": 1.5512188155203222e-06, "loss": 0.0011, "step": 322250 }, { "epoch": 77.39, "learning_rate": 1.5501100291682058e-06, "loss": 0.001, "step": 322260 }, { "epoch": 77.39, "learning_rate": 1.5490016329897384e-06, "loss": 0.001, "step": 322270 }, { "epoch": 77.4, "learning_rate": 1.5478936269938515e-06, "loss": 0.0009, "step": 322280 }, { "epoch": 77.4, "learning_rate": 1.5467860111894717e-06, "loss": 0.001, "step": 322290 }, { "epoch": 77.4, "learning_rate": 1.5456787855855025e-06, "loss": 0.0009, "step": 322300 }, { "epoch": 77.4, "learning_rate": 1.5445719501908762e-06, "loss": 0.0009, "step": 322310 }, { "epoch": 77.4, "learning_rate": 1.5434655050145074e-06, "loss": 0.0016, "step": 322320 }, { "epoch": 77.41, "learning_rate": 1.542359450065295e-06, "loss": 0.0011, "step": 322330 }, { "epoch": 77.41, "learning_rate": 1.5412537853521537e-06, "loss": 0.0015, "step": 322340 }, { "epoch": 77.41, "learning_rate": 1.5401485108839874e-06, "loss": 0.0009, "step": 322350 }, { "epoch": 77.41, "learning_rate": 1.539043626669695e-06, "loss": 0.0015, "step": 322360 }, { "epoch": 77.42, "learning_rate": 1.5379391327181692e-06, "loss": 0.0009, "step": 322370 }, { "epoch": 77.42, "learning_rate": 1.5368350290383193e-06, "loss": 0.0009, "step": 322380 }, { "epoch": 77.42, "learning_rate": 1.535731315639022e-06, "loss": 0.0014, "step": 322390 }, { "epoch": 77.42, "learning_rate": 1.5346279925291696e-06, "loss": 0.001, "step": 322400 }, { "epoch": 77.42, "learning_rate": 1.53352505971765e-06, "loss": 0.0009, "step": 322410 }, { "epoch": 77.43, "learning_rate": 1.5324225172133445e-06, "loss": 0.0009, "step": 322420 }, { "epoch": 77.43, "learning_rate": 1.5313203650251407e-06, "loss": 0.0012, "step": 322430 }, { "epoch": 77.43, "learning_rate": 1.5302186031618926e-06, "loss": 0.001, "step": 322440 }, { "epoch": 77.43, "learning_rate": 1.529117231632493e-06, "loss": 0.0008, "step": 322450 }, { "epoch": 77.44, "learning_rate": 1.5280162504458018e-06, "loss": 0.0021, "step": 322460 }, { "epoch": 77.44, "learning_rate": 1.5269156596106893e-06, "loss": 0.0008, "step": 322470 }, { "epoch": 77.44, "learning_rate": 1.5258154591360152e-06, "loss": 0.0009, "step": 322480 }, { "epoch": 77.44, "learning_rate": 1.5247156490306447e-06, "loss": 0.001, "step": 322490 }, { "epoch": 77.45, "learning_rate": 1.5236162293034263e-06, "loss": 0.0008, "step": 322500 }, { "epoch": 77.45, "learning_rate": 1.5225171999632192e-06, "loss": 0.0009, "step": 322510 }, { "epoch": 77.45, "learning_rate": 1.5214185610188836e-06, "loss": 0.0009, "step": 322520 }, { "epoch": 77.45, "learning_rate": 1.5203203124792454e-06, "loss": 0.001, "step": 322530 }, { "epoch": 77.45, "learning_rate": 1.5192224543531642e-06, "loss": 0.0008, "step": 322540 }, { "epoch": 77.46, "learning_rate": 1.5181249866494773e-06, "loss": 0.0011, "step": 322550 }, { "epoch": 77.46, "learning_rate": 1.5170279093770279e-06, "loss": 0.0009, "step": 322560 }, { "epoch": 77.46, "learning_rate": 1.5159312225446421e-06, "loss": 0.0009, "step": 322570 }, { "epoch": 77.46, "learning_rate": 1.5148349261611573e-06, "loss": 0.0009, "step": 322580 }, { "epoch": 77.47, "learning_rate": 1.5137390202353997e-06, "loss": 0.001, "step": 322590 }, { "epoch": 77.47, "learning_rate": 1.5126435047761956e-06, "loss": 0.001, "step": 322600 }, { "epoch": 77.47, "learning_rate": 1.5115483797923658e-06, "loss": 0.0009, "step": 322610 }, { "epoch": 77.47, "learning_rate": 1.5104536452927366e-06, "loss": 0.001, "step": 322620 }, { "epoch": 77.48, "learning_rate": 1.5093593012861173e-06, "loss": 0.0018, "step": 322630 }, { "epoch": 77.48, "learning_rate": 1.5082653477813235e-06, "loss": 0.0009, "step": 322640 }, { "epoch": 77.48, "learning_rate": 1.5071717847871535e-06, "loss": 0.0022, "step": 322650 }, { "epoch": 77.48, "learning_rate": 1.5060786123124338e-06, "loss": 0.0009, "step": 322660 }, { "epoch": 77.48, "learning_rate": 1.504985830365957e-06, "loss": 0.0015, "step": 322670 }, { "epoch": 77.49, "learning_rate": 1.5038934389565162e-06, "loss": 0.0049, "step": 322680 }, { "epoch": 77.49, "learning_rate": 1.5028014380929267e-06, "loss": 0.001, "step": 322690 }, { "epoch": 77.49, "learning_rate": 1.5017098277839702e-06, "loss": 0.0009, "step": 322700 }, { "epoch": 77.49, "learning_rate": 1.5006186080384399e-06, "loss": 0.0008, "step": 322710 }, { "epoch": 77.5, "learning_rate": 1.499527778865123e-06, "loss": 0.0011, "step": 322720 }, { "epoch": 77.5, "learning_rate": 1.4984373402728014e-06, "loss": 0.001, "step": 322730 }, { "epoch": 77.5, "learning_rate": 1.4973472922702625e-06, "loss": 0.001, "step": 322740 }, { "epoch": 77.5, "learning_rate": 1.4962576348662771e-06, "loss": 0.0013, "step": 322750 }, { "epoch": 77.5, "learning_rate": 1.4951683680696383e-06, "loss": 0.001, "step": 322760 }, { "epoch": 77.51, "learning_rate": 1.4940794918890998e-06, "loss": 0.0016, "step": 322770 }, { "epoch": 77.51, "learning_rate": 1.4929910063334275e-06, "loss": 0.0011, "step": 322780 }, { "epoch": 77.51, "learning_rate": 1.4919029114114026e-06, "loss": 0.0008, "step": 322790 }, { "epoch": 77.51, "learning_rate": 1.4908152071317795e-06, "loss": 0.0009, "step": 322800 }, { "epoch": 77.52, "learning_rate": 1.4897278935033177e-06, "loss": 0.0011, "step": 322810 }, { "epoch": 77.52, "learning_rate": 1.488640970534777e-06, "loss": 0.0011, "step": 322820 }, { "epoch": 77.52, "learning_rate": 1.487554438234906e-06, "loss": 0.0009, "step": 322830 }, { "epoch": 77.52, "learning_rate": 1.4864682966124589e-06, "loss": 0.001, "step": 322840 }, { "epoch": 77.53, "learning_rate": 1.4853825456761782e-06, "loss": 0.0013, "step": 322850 }, { "epoch": 77.53, "learning_rate": 1.4842971854348131e-06, "loss": 0.0009, "step": 322860 }, { "epoch": 77.53, "learning_rate": 1.4832122158970951e-06, "loss": 0.0009, "step": 322870 }, { "epoch": 77.53, "learning_rate": 1.4821276370717729e-06, "loss": 0.0011, "step": 322880 }, { "epoch": 77.53, "learning_rate": 1.4810434489675674e-06, "loss": 0.0011, "step": 322890 }, { "epoch": 77.54, "learning_rate": 1.4799596515932268e-06, "loss": 0.0009, "step": 322900 }, { "epoch": 77.54, "learning_rate": 1.4788762449574667e-06, "loss": 0.001, "step": 322910 }, { "epoch": 77.54, "learning_rate": 1.4777932290690077e-06, "loss": 0.001, "step": 322920 }, { "epoch": 77.54, "learning_rate": 1.476710603936582e-06, "loss": 0.0009, "step": 322930 }, { "epoch": 77.55, "learning_rate": 1.4756283695689099e-06, "loss": 0.0008, "step": 322940 }, { "epoch": 77.55, "learning_rate": 1.4745465259747015e-06, "loss": 0.0014, "step": 322950 }, { "epoch": 77.55, "learning_rate": 1.4734650731626665e-06, "loss": 0.0009, "step": 322960 }, { "epoch": 77.55, "learning_rate": 1.4723840111415144e-06, "loss": 0.0009, "step": 322970 }, { "epoch": 77.56, "learning_rate": 1.4713033399199605e-06, "loss": 0.001, "step": 322980 }, { "epoch": 77.56, "learning_rate": 1.4702230595066924e-06, "loss": 0.0009, "step": 322990 }, { "epoch": 77.56, "learning_rate": 1.4691431699104252e-06, "loss": 0.0009, "step": 323000 }, { "epoch": 77.56, "learning_rate": 1.4680636711398466e-06, "loss": 0.0011, "step": 323010 }, { "epoch": 77.56, "learning_rate": 1.4669845632036438e-06, "loss": 0.0009, "step": 323020 }, { "epoch": 77.57, "learning_rate": 1.4659058461105213e-06, "loss": 0.0009, "step": 323030 }, { "epoch": 77.57, "learning_rate": 1.4648275198691663e-06, "loss": 0.0014, "step": 323040 }, { "epoch": 77.57, "learning_rate": 1.4637495844882443e-06, "loss": 0.001, "step": 323050 }, { "epoch": 77.57, "learning_rate": 1.4626720399764482e-06, "loss": 0.0065, "step": 323060 }, { "epoch": 77.58, "learning_rate": 1.46159488634246e-06, "loss": 0.0011, "step": 323070 }, { "epoch": 77.58, "learning_rate": 1.4605181235949505e-06, "loss": 0.0009, "step": 323080 }, { "epoch": 77.58, "learning_rate": 1.4594417517425852e-06, "loss": 0.001, "step": 323090 }, { "epoch": 77.58, "learning_rate": 1.45836577079404e-06, "loss": 0.0009, "step": 323100 }, { "epoch": 77.58, "learning_rate": 1.457290180757981e-06, "loss": 0.001, "step": 323110 }, { "epoch": 77.59, "learning_rate": 1.4562149816430614e-06, "loss": 0.001, "step": 323120 }, { "epoch": 77.59, "learning_rate": 1.4551401734579363e-06, "loss": 0.001, "step": 323130 }, { "epoch": 77.59, "learning_rate": 1.454065756211287e-06, "loss": 0.0012, "step": 323140 }, { "epoch": 77.59, "learning_rate": 1.4529917299117347e-06, "loss": 0.001, "step": 323150 }, { "epoch": 77.6, "learning_rate": 1.4519180945679445e-06, "loss": 0.0017, "step": 323160 }, { "epoch": 77.6, "learning_rate": 1.4508448501885597e-06, "loss": 0.001, "step": 323170 }, { "epoch": 77.6, "learning_rate": 1.4497719967822342e-06, "loss": 0.0009, "step": 323180 }, { "epoch": 77.6, "learning_rate": 1.4486995343575839e-06, "loss": 0.0009, "step": 323190 }, { "epoch": 77.61, "learning_rate": 1.4476274629232678e-06, "loss": 0.0011, "step": 323200 }, { "epoch": 77.61, "learning_rate": 1.4465557824879072e-06, "loss": 0.001, "step": 323210 }, { "epoch": 77.61, "learning_rate": 1.4454844930601397e-06, "loss": 0.0009, "step": 323220 }, { "epoch": 77.61, "learning_rate": 1.444413594648586e-06, "loss": 0.001, "step": 323230 }, { "epoch": 77.61, "learning_rate": 1.4433430872618724e-06, "loss": 0.001, "step": 323240 }, { "epoch": 77.62, "learning_rate": 1.4422729709086202e-06, "loss": 0.0011, "step": 323250 }, { "epoch": 77.62, "learning_rate": 1.4412032455974444e-06, "loss": 0.0012, "step": 323260 }, { "epoch": 77.62, "learning_rate": 1.440133911336966e-06, "loss": 0.001, "step": 323270 }, { "epoch": 77.62, "learning_rate": 1.4390649681358004e-06, "loss": 0.0014, "step": 323280 }, { "epoch": 77.63, "learning_rate": 1.4379964160025461e-06, "loss": 0.0009, "step": 323290 }, { "epoch": 77.63, "learning_rate": 1.4369282549458018e-06, "loss": 0.0011, "step": 323300 }, { "epoch": 77.63, "learning_rate": 1.4358604849741886e-06, "loss": 0.0011, "step": 323310 }, { "epoch": 77.63, "learning_rate": 1.4347931060962939e-06, "loss": 0.001, "step": 323320 }, { "epoch": 77.64, "learning_rate": 1.4337261183207106e-06, "loss": 0.0011, "step": 323330 }, { "epoch": 77.64, "learning_rate": 1.432659521656038e-06, "loss": 0.001, "step": 323340 }, { "epoch": 77.64, "learning_rate": 1.4315933161108687e-06, "loss": 0.0009, "step": 323350 }, { "epoch": 77.64, "learning_rate": 1.430527501693779e-06, "loss": 0.0009, "step": 323360 }, { "epoch": 77.64, "learning_rate": 1.4294620784133573e-06, "loss": 0.0009, "step": 323370 }, { "epoch": 77.65, "learning_rate": 1.4283970462781792e-06, "loss": 0.0012, "step": 323380 }, { "epoch": 77.65, "learning_rate": 1.427332405296833e-06, "loss": 0.001, "step": 323390 }, { "epoch": 77.65, "learning_rate": 1.4262681554778723e-06, "loss": 0.0017, "step": 323400 }, { "epoch": 77.65, "learning_rate": 1.4252042968298907e-06, "loss": 0.0009, "step": 323410 }, { "epoch": 77.66, "learning_rate": 1.4241408293614478e-06, "loss": 0.0009, "step": 323420 }, { "epoch": 77.66, "learning_rate": 1.423077753081098e-06, "loss": 0.0009, "step": 323430 }, { "epoch": 77.66, "learning_rate": 1.422015067997412e-06, "loss": 0.0009, "step": 323440 }, { "epoch": 77.66, "learning_rate": 1.4209527741189444e-06, "loss": 0.001, "step": 323450 }, { "epoch": 77.66, "learning_rate": 1.4198908714542491e-06, "loss": 0.001, "step": 323460 }, { "epoch": 77.67, "learning_rate": 1.4188293600118808e-06, "loss": 0.0012, "step": 323470 }, { "epoch": 77.67, "learning_rate": 1.4177682398003933e-06, "loss": 0.0009, "step": 323480 }, { "epoch": 77.67, "learning_rate": 1.416707510828319e-06, "loss": 0.001, "step": 323490 }, { "epoch": 77.67, "learning_rate": 1.4156471731042064e-06, "loss": 0.001, "step": 323500 }, { "epoch": 77.68, "learning_rate": 1.4145872266365933e-06, "loss": 0.0009, "step": 323510 }, { "epoch": 77.68, "learning_rate": 1.4135276714340229e-06, "loss": 0.0011, "step": 323520 }, { "epoch": 77.68, "learning_rate": 1.412468507505016e-06, "loss": 0.0015, "step": 323530 }, { "epoch": 77.68, "learning_rate": 1.4114097348581046e-06, "loss": 0.001, "step": 323540 }, { "epoch": 77.69, "learning_rate": 1.4103513535018265e-06, "loss": 0.0043, "step": 323550 }, { "epoch": 77.69, "learning_rate": 1.4092933634447026e-06, "loss": 0.001, "step": 323560 }, { "epoch": 77.69, "learning_rate": 1.4082357646952316e-06, "loss": 0.0009, "step": 323570 }, { "epoch": 77.69, "learning_rate": 1.4071785572619567e-06, "loss": 0.0032, "step": 323580 }, { "epoch": 77.69, "learning_rate": 1.4061217411533822e-06, "loss": 0.001, "step": 323590 }, { "epoch": 77.7, "learning_rate": 1.4050653163780125e-06, "loss": 0.0009, "step": 323600 }, { "epoch": 77.7, "learning_rate": 1.4040092829443685e-06, "loss": 0.0008, "step": 323610 }, { "epoch": 77.7, "learning_rate": 1.4029536408609378e-06, "loss": 0.0011, "step": 323620 }, { "epoch": 77.7, "learning_rate": 1.4018983901362359e-06, "loss": 0.0009, "step": 323630 }, { "epoch": 77.71, "learning_rate": 1.4008435307787504e-06, "loss": 0.001, "step": 323640 }, { "epoch": 77.71, "learning_rate": 1.3997890627969911e-06, "loss": 0.001, "step": 323650 }, { "epoch": 77.71, "learning_rate": 1.3987349861994404e-06, "loss": 0.0009, "step": 323660 }, { "epoch": 77.71, "learning_rate": 1.3976813009945743e-06, "loss": 0.0009, "step": 323670 }, { "epoch": 77.72, "learning_rate": 1.3966280071908977e-06, "loss": 0.0009, "step": 323680 }, { "epoch": 77.72, "learning_rate": 1.3955751047968868e-06, "loss": 0.0009, "step": 323690 }, { "epoch": 77.72, "learning_rate": 1.3945225938210238e-06, "loss": 0.0011, "step": 323700 }, { "epoch": 77.72, "learning_rate": 1.3934704742717685e-06, "loss": 0.001, "step": 323710 }, { "epoch": 77.72, "learning_rate": 1.3924187461576144e-06, "loss": 0.0009, "step": 323720 }, { "epoch": 77.73, "learning_rate": 1.391367409487021e-06, "loss": 0.0016, "step": 323730 }, { "epoch": 77.73, "learning_rate": 1.3903164642684595e-06, "loss": 0.0008, "step": 323740 }, { "epoch": 77.73, "learning_rate": 1.38926591051039e-06, "loss": 0.0021, "step": 323750 }, { "epoch": 77.73, "learning_rate": 1.3882157482212722e-06, "loss": 0.0014, "step": 323760 }, { "epoch": 77.74, "learning_rate": 1.3871659774095658e-06, "loss": 0.0009, "step": 323770 }, { "epoch": 77.74, "learning_rate": 1.3861165980837144e-06, "loss": 0.0011, "step": 323780 }, { "epoch": 77.74, "learning_rate": 1.3850676102521832e-06, "loss": 0.001, "step": 323790 }, { "epoch": 77.74, "learning_rate": 1.384019013923421e-06, "loss": 0.0009, "step": 323800 }, { "epoch": 77.74, "learning_rate": 1.3829708091058546e-06, "loss": 0.0009, "step": 323810 }, { "epoch": 77.75, "learning_rate": 1.3819229958079438e-06, "loss": 0.0011, "step": 323820 }, { "epoch": 77.75, "learning_rate": 1.380875574038115e-06, "loss": 0.0009, "step": 323830 }, { "epoch": 77.75, "learning_rate": 1.379828543804812e-06, "loss": 0.001, "step": 323840 }, { "epoch": 77.75, "learning_rate": 1.3787819051164608e-06, "loss": 0.0011, "step": 323850 }, { "epoch": 77.76, "learning_rate": 1.3777356579814882e-06, "loss": 0.0011, "step": 323860 }, { "epoch": 77.76, "learning_rate": 1.3766898024083264e-06, "loss": 0.0009, "step": 323870 }, { "epoch": 77.76, "learning_rate": 1.3756443384053907e-06, "loss": 0.001, "step": 323880 }, { "epoch": 77.76, "learning_rate": 1.3745992659811135e-06, "loss": 0.001, "step": 323890 }, { "epoch": 77.77, "learning_rate": 1.3735545851438935e-06, "loss": 0.0012, "step": 323900 }, { "epoch": 77.77, "learning_rate": 1.3725102959021464e-06, "loss": 0.001, "step": 323910 }, { "epoch": 77.77, "learning_rate": 1.3714663982642984e-06, "loss": 0.0019, "step": 323920 }, { "epoch": 77.77, "learning_rate": 1.3704228922387374e-06, "loss": 0.0009, "step": 323930 }, { "epoch": 77.77, "learning_rate": 1.3693797778338846e-06, "loss": 0.001, "step": 323940 }, { "epoch": 77.78, "learning_rate": 1.3683370550581166e-06, "loss": 0.001, "step": 323950 }, { "epoch": 77.78, "learning_rate": 1.3672947239198541e-06, "loss": 0.001, "step": 323960 }, { "epoch": 77.78, "learning_rate": 1.3662527844274797e-06, "loss": 0.001, "step": 323970 }, { "epoch": 77.78, "learning_rate": 1.3652112365893865e-06, "loss": 0.001, "step": 323980 }, { "epoch": 77.79, "learning_rate": 1.3641700804139567e-06, "loss": 0.001, "step": 323990 }, { "epoch": 77.79, "learning_rate": 1.3631293159095836e-06, "loss": 0.001, "step": 324000 }, { "epoch": 77.79, "learning_rate": 1.3620889430846439e-06, "loss": 0.0009, "step": 324010 }, { "epoch": 77.79, "learning_rate": 1.3610489619475142e-06, "loss": 0.0013, "step": 324020 }, { "epoch": 77.8, "learning_rate": 1.360009372506582e-06, "loss": 0.001, "step": 324030 }, { "epoch": 77.8, "learning_rate": 1.3589701747702022e-06, "loss": 0.001, "step": 324040 }, { "epoch": 77.8, "learning_rate": 1.3579313687467453e-06, "loss": 0.001, "step": 324050 }, { "epoch": 77.8, "learning_rate": 1.3568929544445885e-06, "loss": 0.0029, "step": 324060 }, { "epoch": 77.8, "learning_rate": 1.3558549318720915e-06, "loss": 0.001, "step": 324070 }, { "epoch": 77.81, "learning_rate": 1.3548173010376086e-06, "loss": 0.0009, "step": 324080 }, { "epoch": 77.81, "learning_rate": 1.3537800619494946e-06, "loss": 0.0008, "step": 324090 }, { "epoch": 77.81, "learning_rate": 1.352743214616109e-06, "loss": 0.001, "step": 324100 }, { "epoch": 77.81, "learning_rate": 1.351706759045801e-06, "loss": 0.0013, "step": 324110 }, { "epoch": 77.82, "learning_rate": 1.3506706952469028e-06, "loss": 0.001, "step": 324120 }, { "epoch": 77.82, "learning_rate": 1.3496350232277854e-06, "loss": 0.001, "step": 324130 }, { "epoch": 77.82, "learning_rate": 1.3485997429967645e-06, "loss": 0.0008, "step": 324140 }, { "epoch": 77.82, "learning_rate": 1.347564854562189e-06, "loss": 0.001, "step": 324150 }, { "epoch": 77.82, "learning_rate": 1.3465303579323906e-06, "loss": 0.0009, "step": 324160 }, { "epoch": 77.83, "learning_rate": 1.3454962531157023e-06, "loss": 0.001, "step": 324170 }, { "epoch": 77.83, "learning_rate": 1.3444625401204503e-06, "loss": 0.0009, "step": 324180 }, { "epoch": 77.83, "learning_rate": 1.3434292189549503e-06, "loss": 0.0008, "step": 324190 }, { "epoch": 77.83, "learning_rate": 1.3423962896275399e-06, "loss": 0.0011, "step": 324200 }, { "epoch": 77.84, "learning_rate": 1.3413637521465238e-06, "loss": 0.0009, "step": 324210 }, { "epoch": 77.84, "learning_rate": 1.3403316065202288e-06, "loss": 0.0015, "step": 324220 }, { "epoch": 77.84, "learning_rate": 1.3392998527569645e-06, "loss": 0.001, "step": 324230 }, { "epoch": 77.84, "learning_rate": 1.33826849086503e-06, "loss": 0.0012, "step": 324240 }, { "epoch": 77.85, "learning_rate": 1.337237520852741e-06, "loss": 0.001, "step": 324250 }, { "epoch": 77.85, "learning_rate": 1.3362069427283907e-06, "loss": 0.0009, "step": 324260 }, { "epoch": 77.85, "learning_rate": 1.3351767565002893e-06, "loss": 0.0014, "step": 324270 }, { "epoch": 77.85, "learning_rate": 1.33414696217673e-06, "loss": 0.001, "step": 324280 }, { "epoch": 77.85, "learning_rate": 1.333117559765995e-06, "loss": 0.001, "step": 324290 }, { "epoch": 77.86, "learning_rate": 1.332088549276389e-06, "loss": 0.001, "step": 324300 }, { "epoch": 77.86, "learning_rate": 1.3310599307161998e-06, "loss": 0.0031, "step": 324310 }, { "epoch": 77.86, "learning_rate": 1.3300317040936926e-06, "loss": 0.0009, "step": 324320 }, { "epoch": 77.86, "learning_rate": 1.329003869417167e-06, "loss": 0.0013, "step": 324330 }, { "epoch": 77.87, "learning_rate": 1.327976426694888e-06, "loss": 0.0016, "step": 324340 }, { "epoch": 77.87, "learning_rate": 1.3269493759351382e-06, "loss": 0.001, "step": 324350 }, { "epoch": 77.87, "learning_rate": 1.325922717146183e-06, "loss": 0.0009, "step": 324360 }, { "epoch": 77.87, "learning_rate": 1.3248964503362937e-06, "loss": 0.001, "step": 324370 }, { "epoch": 77.88, "learning_rate": 1.3238705755137304e-06, "loss": 0.001, "step": 324380 }, { "epoch": 77.88, "learning_rate": 1.3228450926867586e-06, "loss": 0.0014, "step": 324390 }, { "epoch": 77.88, "learning_rate": 1.321820001863633e-06, "loss": 0.0019, "step": 324400 }, { "epoch": 77.88, "learning_rate": 1.3207953030526189e-06, "loss": 0.0009, "step": 324410 }, { "epoch": 77.88, "learning_rate": 1.3197709962619598e-06, "loss": 0.0011, "step": 324420 }, { "epoch": 77.89, "learning_rate": 1.3187470814998936e-06, "loss": 0.0008, "step": 324430 }, { "epoch": 77.89, "learning_rate": 1.3177235587746862e-06, "loss": 0.0016, "step": 324440 }, { "epoch": 77.89, "learning_rate": 1.316700428094575e-06, "loss": 0.0009, "step": 324450 }, { "epoch": 77.89, "learning_rate": 1.3156776894677924e-06, "loss": 0.0009, "step": 324460 }, { "epoch": 77.9, "learning_rate": 1.314655342902582e-06, "loss": 0.0011, "step": 324470 }, { "epoch": 77.9, "learning_rate": 1.3136333884071706e-06, "loss": 0.0009, "step": 324480 }, { "epoch": 77.9, "learning_rate": 1.3126118259897956e-06, "loss": 0.0008, "step": 324490 }, { "epoch": 77.9, "learning_rate": 1.3115906556586733e-06, "loss": 0.0009, "step": 324500 }, { "epoch": 77.9, "learning_rate": 1.3105698774220353e-06, "loss": 0.0009, "step": 324510 }, { "epoch": 77.91, "learning_rate": 1.3095494912881034e-06, "loss": 0.0009, "step": 324520 }, { "epoch": 77.91, "learning_rate": 1.308529497265082e-06, "loss": 0.0009, "step": 324530 }, { "epoch": 77.91, "learning_rate": 1.307509895361203e-06, "loss": 0.0009, "step": 324540 }, { "epoch": 77.91, "learning_rate": 1.3064906855846714e-06, "loss": 0.0057, "step": 324550 }, { "epoch": 77.92, "learning_rate": 1.3054718679436916e-06, "loss": 0.001, "step": 324560 }, { "epoch": 77.92, "learning_rate": 1.3044534424464627e-06, "loss": 0.0009, "step": 324570 }, { "epoch": 77.92, "learning_rate": 1.3034354091011947e-06, "loss": 0.0011, "step": 324580 }, { "epoch": 77.92, "learning_rate": 1.3024177679160864e-06, "loss": 0.001, "step": 324590 }, { "epoch": 77.93, "learning_rate": 1.3014005188993316e-06, "loss": 0.001, "step": 324600 }, { "epoch": 77.93, "learning_rate": 1.3003836620591236e-06, "loss": 0.0008, "step": 324610 }, { "epoch": 77.93, "learning_rate": 1.2993671974036503e-06, "loss": 0.0011, "step": 324620 }, { "epoch": 77.93, "learning_rate": 1.298351124941094e-06, "loss": 0.0009, "step": 324630 }, { "epoch": 77.93, "learning_rate": 1.297335444679637e-06, "loss": 0.001, "step": 324640 }, { "epoch": 77.94, "learning_rate": 1.296320156627462e-06, "loss": 0.001, "step": 324650 }, { "epoch": 77.94, "learning_rate": 1.2953052607927508e-06, "loss": 0.0009, "step": 324660 }, { "epoch": 77.94, "learning_rate": 1.2942907571836582e-06, "loss": 0.001, "step": 324670 }, { "epoch": 77.94, "learning_rate": 1.2932766458083778e-06, "loss": 0.0011, "step": 324680 }, { "epoch": 77.95, "learning_rate": 1.2922629266750642e-06, "loss": 0.0012, "step": 324690 }, { "epoch": 77.95, "learning_rate": 1.2912495997918772e-06, "loss": 0.0009, "step": 324700 }, { "epoch": 77.95, "learning_rate": 1.2902366651669829e-06, "loss": 0.0018, "step": 324710 }, { "epoch": 78.0, "learning_rate": 1.2892241228085356e-06, "loss": 0.0008, "step": 324720 }, { "epoch": 78.0, "learning_rate": 1.2882119727246956e-06, "loss": 0.0015, "step": 324730 }, { "epoch": 78.01, "learning_rate": 1.2872002149236118e-06, "loss": 0.001, "step": 324740 }, { "epoch": 78.01, "learning_rate": 1.2861888494134221e-06, "loss": 0.0009, "step": 324750 }, { "epoch": 78.01, "learning_rate": 1.285177876202287e-06, "loss": 0.0012, "step": 324760 }, { "epoch": 78.01, "learning_rate": 1.284167295298333e-06, "loss": 0.001, "step": 324770 }, { "epoch": 78.02, "learning_rate": 1.2831571067097093e-06, "loss": 0.0009, "step": 324780 }, { "epoch": 78.02, "learning_rate": 1.2821473104445482e-06, "loss": 0.0009, "step": 324790 }, { "epoch": 78.02, "learning_rate": 1.281137906510982e-06, "loss": 0.0009, "step": 324800 }, { "epoch": 78.02, "learning_rate": 1.2801288949171264e-06, "loss": 0.0012, "step": 324810 }, { "epoch": 78.02, "learning_rate": 1.2791202756711306e-06, "loss": 0.001, "step": 324820 }, { "epoch": 78.03, "learning_rate": 1.2781120487811105e-06, "loss": 0.001, "step": 324830 }, { "epoch": 78.03, "learning_rate": 1.2771042142551647e-06, "loss": 0.0008, "step": 324840 }, { "epoch": 78.03, "learning_rate": 1.2760967721014372e-06, "loss": 0.001, "step": 324850 }, { "epoch": 78.03, "learning_rate": 1.2750897223280212e-06, "loss": 0.0008, "step": 324860 }, { "epoch": 78.04, "learning_rate": 1.2740830649430435e-06, "loss": 0.0009, "step": 324870 }, { "epoch": 78.04, "learning_rate": 1.2730767999545978e-06, "loss": 0.0035, "step": 324880 }, { "epoch": 78.04, "learning_rate": 1.2720709273707886e-06, "loss": 0.001, "step": 324890 }, { "epoch": 78.04, "learning_rate": 1.2710654471997207e-06, "loss": 0.0009, "step": 324900 }, { "epoch": 78.04, "learning_rate": 1.2700603594494876e-06, "loss": 0.0009, "step": 324910 }, { "epoch": 78.05, "learning_rate": 1.2690556641281937e-06, "loss": 0.0022, "step": 324920 }, { "epoch": 78.05, "learning_rate": 1.2680513612439216e-06, "loss": 0.001, "step": 324930 }, { "epoch": 78.05, "learning_rate": 1.2670474508047536e-06, "loss": 0.0009, "step": 324940 }, { "epoch": 78.05, "learning_rate": 1.2660439328187835e-06, "loss": 0.0011, "step": 324950 }, { "epoch": 78.06, "learning_rate": 1.2650408072940878e-06, "loss": 0.001, "step": 324960 }, { "epoch": 78.06, "learning_rate": 1.2640380742387548e-06, "loss": 0.0008, "step": 324970 }, { "epoch": 78.06, "learning_rate": 1.2630357336608445e-06, "loss": 0.0023, "step": 324980 }, { "epoch": 78.06, "learning_rate": 1.2620337855684339e-06, "loss": 0.0009, "step": 324990 }, { "epoch": 78.07, "learning_rate": 1.2610322299695999e-06, "loss": 0.0012, "step": 325000 }, { "epoch": 78.07, "learning_rate": 1.260031066872397e-06, "loss": 0.0009, "step": 325010 }, { "epoch": 78.07, "learning_rate": 1.2590302962848965e-06, "loss": 0.0009, "step": 325020 }, { "epoch": 78.07, "learning_rate": 1.2580299182151533e-06, "loss": 0.0009, "step": 325030 }, { "epoch": 78.07, "learning_rate": 1.257029932671222e-06, "loss": 0.0009, "step": 325040 }, { "epoch": 78.08, "learning_rate": 1.2560303396611572e-06, "loss": 0.0008, "step": 325050 }, { "epoch": 78.08, "learning_rate": 1.2550311391930136e-06, "loss": 0.001, "step": 325060 }, { "epoch": 78.08, "learning_rate": 1.2540323312748402e-06, "loss": 0.0011, "step": 325070 }, { "epoch": 78.08, "learning_rate": 1.2530339159146586e-06, "loss": 0.0008, "step": 325080 }, { "epoch": 78.09, "learning_rate": 1.2520358931205344e-06, "loss": 0.0009, "step": 325090 }, { "epoch": 78.09, "learning_rate": 1.2510382629004945e-06, "loss": 0.0009, "step": 325100 }, { "epoch": 78.09, "learning_rate": 1.2500410252625717e-06, "loss": 0.0016, "step": 325110 }, { "epoch": 78.09, "learning_rate": 1.2490441802148033e-06, "loss": 0.0008, "step": 325120 }, { "epoch": 78.1, "learning_rate": 1.248047727765206e-06, "loss": 0.0009, "step": 325130 }, { "epoch": 78.1, "learning_rate": 1.2470516679218168e-06, "loss": 0.0009, "step": 325140 }, { "epoch": 78.1, "learning_rate": 1.2460560006926469e-06, "loss": 0.001, "step": 325150 }, { "epoch": 78.1, "learning_rate": 1.2450607260857227e-06, "loss": 0.0011, "step": 325160 }, { "epoch": 78.1, "learning_rate": 1.2440658441090547e-06, "loss": 0.0009, "step": 325170 }, { "epoch": 78.11, "learning_rate": 1.2430713547706529e-06, "loss": 0.0008, "step": 325180 }, { "epoch": 78.11, "learning_rate": 1.2420772580785278e-06, "loss": 0.001, "step": 325190 }, { "epoch": 78.11, "learning_rate": 1.2410835540406895e-06, "loss": 0.0028, "step": 325200 }, { "epoch": 78.11, "learning_rate": 1.2400902426651427e-06, "loss": 0.0009, "step": 325210 }, { "epoch": 78.12, "learning_rate": 1.2390973239598703e-06, "loss": 0.001, "step": 325220 }, { "epoch": 78.12, "learning_rate": 1.2381047979328818e-06, "loss": 0.0016, "step": 325230 }, { "epoch": 78.12, "learning_rate": 1.2371126645921715e-06, "loss": 0.001, "step": 325240 }, { "epoch": 78.12, "learning_rate": 1.2361209239457217e-06, "loss": 0.0011, "step": 325250 }, { "epoch": 78.12, "learning_rate": 1.2351295760015202e-06, "loss": 0.0009, "step": 325260 }, { "epoch": 78.13, "learning_rate": 1.2341386207675553e-06, "loss": 0.001, "step": 325270 }, { "epoch": 78.13, "learning_rate": 1.2331480582518095e-06, "loss": 0.001, "step": 325280 }, { "epoch": 78.13, "learning_rate": 1.2321578884622432e-06, "loss": 0.001, "step": 325290 }, { "epoch": 78.13, "learning_rate": 1.2311681114068551e-06, "loss": 0.001, "step": 325300 }, { "epoch": 78.14, "learning_rate": 1.230178727093595e-06, "loss": 0.001, "step": 325310 }, { "epoch": 78.14, "learning_rate": 1.2291897355304393e-06, "loss": 0.0008, "step": 325320 }, { "epoch": 78.14, "learning_rate": 1.2282011367253544e-06, "loss": 0.0012, "step": 325330 }, { "epoch": 78.14, "learning_rate": 1.2272129306863e-06, "loss": 0.0016, "step": 325340 }, { "epoch": 78.15, "learning_rate": 1.2262251174212313e-06, "loss": 0.0008, "step": 325350 }, { "epoch": 78.15, "learning_rate": 1.225237696938103e-06, "loss": 0.0009, "step": 325360 }, { "epoch": 78.15, "learning_rate": 1.2242506692448753e-06, "loss": 0.0008, "step": 325370 }, { "epoch": 78.15, "learning_rate": 1.2232640343494862e-06, "loss": 0.0008, "step": 325380 }, { "epoch": 78.15, "learning_rate": 1.222277792259885e-06, "loss": 0.0011, "step": 325390 }, { "epoch": 78.16, "learning_rate": 1.2212919429840209e-06, "loss": 0.0009, "step": 325400 }, { "epoch": 78.16, "learning_rate": 1.2203064865298263e-06, "loss": 0.0009, "step": 325410 }, { "epoch": 78.16, "learning_rate": 1.2193214229052342e-06, "loss": 0.0019, "step": 325420 }, { "epoch": 78.16, "learning_rate": 1.2183367521181765e-06, "loss": 0.0009, "step": 325430 }, { "epoch": 78.17, "learning_rate": 1.2173524741765917e-06, "loss": 0.0009, "step": 325440 }, { "epoch": 78.17, "learning_rate": 1.2163685890884124e-06, "loss": 0.0008, "step": 325450 }, { "epoch": 78.17, "learning_rate": 1.2153850968615377e-06, "loss": 0.001, "step": 325460 }, { "epoch": 78.17, "learning_rate": 1.2144019975039055e-06, "loss": 0.0011, "step": 325470 }, { "epoch": 78.18, "learning_rate": 1.2134192910234322e-06, "loss": 0.001, "step": 325480 }, { "epoch": 78.18, "learning_rate": 1.212436977428033e-06, "loss": 0.0011, "step": 325490 }, { "epoch": 78.18, "learning_rate": 1.2114550567256078e-06, "loss": 0.0011, "step": 325500 }, { "epoch": 78.18, "learning_rate": 1.210473528924072e-06, "loss": 0.0008, "step": 325510 }, { "epoch": 78.18, "learning_rate": 1.2094923940313307e-06, "loss": 0.0022, "step": 325520 }, { "epoch": 78.19, "learning_rate": 1.2085116520552774e-06, "loss": 0.0009, "step": 325530 }, { "epoch": 78.19, "learning_rate": 1.2075313030038227e-06, "loss": 0.0014, "step": 325540 }, { "epoch": 78.19, "learning_rate": 1.2065513468848544e-06, "loss": 0.0009, "step": 325550 }, { "epoch": 78.19, "learning_rate": 1.2055717837062552e-06, "loss": 0.0009, "step": 325560 }, { "epoch": 78.2, "learning_rate": 1.20459261347593e-06, "loss": 0.0009, "step": 325570 }, { "epoch": 78.2, "learning_rate": 1.2036138362017556e-06, "loss": 0.0011, "step": 325580 }, { "epoch": 78.2, "learning_rate": 1.2026354518916204e-06, "loss": 0.001, "step": 325590 }, { "epoch": 78.2, "learning_rate": 1.201657460553396e-06, "loss": 0.002, "step": 325600 }, { "epoch": 78.2, "learning_rate": 1.2006798621949588e-06, "loss": 0.0009, "step": 325610 }, { "epoch": 78.21, "learning_rate": 1.1997026568241864e-06, "loss": 0.001, "step": 325620 }, { "epoch": 78.21, "learning_rate": 1.1987258444489391e-06, "loss": 0.0027, "step": 325630 }, { "epoch": 78.21, "learning_rate": 1.1977494250770993e-06, "loss": 0.0009, "step": 325640 }, { "epoch": 78.21, "learning_rate": 1.1967733987165164e-06, "loss": 0.0011, "step": 325650 }, { "epoch": 78.22, "learning_rate": 1.1957977653750563e-06, "loss": 0.0009, "step": 325660 }, { "epoch": 78.22, "learning_rate": 1.1948225250605737e-06, "loss": 0.0013, "step": 325670 }, { "epoch": 78.22, "learning_rate": 1.1938476777809294e-06, "loss": 0.001, "step": 325680 }, { "epoch": 78.22, "learning_rate": 1.192873223543961e-06, "loss": 0.0009, "step": 325690 }, { "epoch": 78.23, "learning_rate": 1.191899162357518e-06, "loss": 0.0014, "step": 325700 }, { "epoch": 78.23, "learning_rate": 1.1909254942294556e-06, "loss": 0.0032, "step": 325710 }, { "epoch": 78.23, "learning_rate": 1.1899522191676116e-06, "loss": 0.0009, "step": 325720 }, { "epoch": 78.23, "learning_rate": 1.1889793371798186e-06, "loss": 0.0011, "step": 325730 }, { "epoch": 78.23, "learning_rate": 1.1880068482739092e-06, "loss": 0.0009, "step": 325740 }, { "epoch": 78.24, "learning_rate": 1.1870347524577274e-06, "loss": 0.001, "step": 325750 }, { "epoch": 78.24, "learning_rate": 1.186063049739089e-06, "loss": 0.0013, "step": 325760 }, { "epoch": 78.24, "learning_rate": 1.185091740125821e-06, "loss": 0.001, "step": 325770 }, { "epoch": 78.24, "learning_rate": 1.1841208236257562e-06, "loss": 0.0012, "step": 325780 }, { "epoch": 78.25, "learning_rate": 1.1831503002467048e-06, "loss": 0.0008, "step": 325790 }, { "epoch": 78.25, "learning_rate": 1.1821801699964773e-06, "loss": 0.001, "step": 325800 }, { "epoch": 78.25, "learning_rate": 1.1812104328828954e-06, "loss": 0.0011, "step": 325810 }, { "epoch": 78.25, "learning_rate": 1.1802410889137693e-06, "loss": 0.001, "step": 325820 }, { "epoch": 78.26, "learning_rate": 1.1792721380968985e-06, "loss": 0.0011, "step": 325830 }, { "epoch": 78.26, "learning_rate": 1.1783035804400877e-06, "loss": 0.001, "step": 325840 }, { "epoch": 78.26, "learning_rate": 1.1773354159511417e-06, "loss": 0.0009, "step": 325850 }, { "epoch": 78.26, "learning_rate": 1.1763676446378546e-06, "loss": 0.0011, "step": 325860 }, { "epoch": 78.26, "learning_rate": 1.1754002665080145e-06, "loss": 0.0011, "step": 325870 }, { "epoch": 78.27, "learning_rate": 1.1744332815694203e-06, "loss": 0.0013, "step": 325880 }, { "epoch": 78.27, "learning_rate": 1.1734666898298552e-06, "loss": 0.0009, "step": 325890 }, { "epoch": 78.27, "learning_rate": 1.1725004912971072e-06, "loss": 0.0009, "step": 325900 }, { "epoch": 78.27, "learning_rate": 1.1715346859789423e-06, "loss": 0.001, "step": 325910 }, { "epoch": 78.28, "learning_rate": 1.1705692738831654e-06, "loss": 0.001, "step": 325920 }, { "epoch": 78.28, "learning_rate": 1.1696042550175256e-06, "loss": 0.0008, "step": 325930 }, { "epoch": 78.28, "learning_rate": 1.168639629389806e-06, "loss": 0.0012, "step": 325940 }, { "epoch": 78.28, "learning_rate": 1.1676753970077724e-06, "loss": 0.0009, "step": 325950 }, { "epoch": 78.28, "learning_rate": 1.1667115578791909e-06, "loss": 0.001, "step": 325960 }, { "epoch": 78.29, "learning_rate": 1.1657481120118275e-06, "loss": 0.0009, "step": 325970 }, { "epoch": 78.29, "learning_rate": 1.1647850594134312e-06, "loss": 0.0009, "step": 325980 }, { "epoch": 78.29, "learning_rate": 1.163822400091763e-06, "loss": 0.0009, "step": 325990 }, { "epoch": 78.29, "learning_rate": 1.1628601340545774e-06, "loss": 0.001, "step": 326000 }, { "epoch": 78.3, "learning_rate": 1.161898261309624e-06, "loss": 0.0009, "step": 326010 }, { "epoch": 78.3, "learning_rate": 1.160936781864641e-06, "loss": 0.001, "step": 326020 }, { "epoch": 78.3, "learning_rate": 1.1599756957273833e-06, "loss": 0.0009, "step": 326030 }, { "epoch": 78.3, "learning_rate": 1.1590150029055725e-06, "loss": 0.001, "step": 326040 }, { "epoch": 78.31, "learning_rate": 1.1580547034069632e-06, "loss": 0.0009, "step": 326050 }, { "epoch": 78.31, "learning_rate": 1.1570947972392887e-06, "loss": 0.0009, "step": 326060 }, { "epoch": 78.31, "learning_rate": 1.1561352844102703e-06, "loss": 0.001, "step": 326070 }, { "epoch": 78.31, "learning_rate": 1.1551761649276293e-06, "loss": 0.001, "step": 326080 }, { "epoch": 78.31, "learning_rate": 1.1542174387991045e-06, "loss": 0.0024, "step": 326090 }, { "epoch": 78.32, "learning_rate": 1.1532591060324116e-06, "loss": 0.0011, "step": 326100 }, { "epoch": 78.32, "learning_rate": 1.1523011666352668e-06, "loss": 0.0011, "step": 326110 }, { "epoch": 78.32, "learning_rate": 1.1513436206153804e-06, "loss": 0.0011, "step": 326120 }, { "epoch": 78.32, "learning_rate": 1.1503864679804688e-06, "loss": 0.0009, "step": 326130 }, { "epoch": 78.33, "learning_rate": 1.149429708738242e-06, "loss": 0.0021, "step": 326140 }, { "epoch": 78.33, "learning_rate": 1.1484733428964e-06, "loss": 0.0013, "step": 326150 }, { "epoch": 78.33, "learning_rate": 1.1475173704626474e-06, "loss": 0.0011, "step": 326160 }, { "epoch": 78.33, "learning_rate": 1.1465617914446836e-06, "loss": 0.0014, "step": 326170 }, { "epoch": 78.34, "learning_rate": 1.1456066058501968e-06, "loss": 0.0009, "step": 326180 }, { "epoch": 78.34, "learning_rate": 1.1446518136868866e-06, "loss": 0.0009, "step": 326190 }, { "epoch": 78.34, "learning_rate": 1.1436974149624468e-06, "loss": 0.0009, "step": 326200 }, { "epoch": 78.34, "learning_rate": 1.142743409684549e-06, "loss": 0.0019, "step": 326210 }, { "epoch": 78.34, "learning_rate": 1.1417897978608872e-06, "loss": 0.0009, "step": 326220 }, { "epoch": 78.35, "learning_rate": 1.1408365794991383e-06, "loss": 0.0011, "step": 326230 }, { "epoch": 78.35, "learning_rate": 1.139883754606974e-06, "loss": 0.0009, "step": 326240 }, { "epoch": 78.35, "learning_rate": 1.1389313231920717e-06, "loss": 0.002, "step": 326250 }, { "epoch": 78.35, "learning_rate": 1.137979285262103e-06, "loss": 0.0008, "step": 326260 }, { "epoch": 78.36, "learning_rate": 1.1370276408247337e-06, "loss": 0.0011, "step": 326270 }, { "epoch": 78.36, "learning_rate": 1.1360763898876304e-06, "loss": 0.0011, "step": 326280 }, { "epoch": 78.36, "learning_rate": 1.135125532458442e-06, "loss": 0.0009, "step": 326290 }, { "epoch": 78.36, "learning_rate": 1.1341750685448405e-06, "loss": 0.0009, "step": 326300 }, { "epoch": 78.36, "learning_rate": 1.1332249981544696e-06, "loss": 0.0009, "step": 326310 }, { "epoch": 78.37, "learning_rate": 1.1322753212949844e-06, "loss": 0.0009, "step": 326320 }, { "epoch": 78.37, "learning_rate": 1.1313260379740343e-06, "loss": 0.0012, "step": 326330 }, { "epoch": 78.37, "learning_rate": 1.1303771481992631e-06, "loss": 0.0014, "step": 326340 }, { "epoch": 78.37, "learning_rate": 1.1294286519783093e-06, "loss": 0.001, "step": 326350 }, { "epoch": 78.38, "learning_rate": 1.128480549318811e-06, "loss": 0.001, "step": 326360 }, { "epoch": 78.38, "learning_rate": 1.1275328402284125e-06, "loss": 0.001, "step": 326370 }, { "epoch": 78.38, "learning_rate": 1.126585524714735e-06, "loss": 0.0042, "step": 326380 }, { "epoch": 78.38, "learning_rate": 1.1256386027854116e-06, "loss": 0.0009, "step": 326390 }, { "epoch": 78.39, "learning_rate": 1.1246920744480693e-06, "loss": 0.0009, "step": 326400 }, { "epoch": 78.39, "learning_rate": 1.1237459397103301e-06, "loss": 0.0018, "step": 326410 }, { "epoch": 78.39, "learning_rate": 1.1228001985798099e-06, "loss": 0.0015, "step": 326420 }, { "epoch": 78.39, "learning_rate": 1.1218548510641302e-06, "loss": 0.0008, "step": 326430 }, { "epoch": 78.39, "learning_rate": 1.120909897170902e-06, "loss": 0.001, "step": 326440 }, { "epoch": 78.4, "learning_rate": 1.1199653369077302e-06, "loss": 0.0075, "step": 326450 }, { "epoch": 78.4, "learning_rate": 1.1190211702822307e-06, "loss": 0.0009, "step": 326460 }, { "epoch": 78.4, "learning_rate": 1.1180773973019975e-06, "loss": 0.0011, "step": 326470 }, { "epoch": 78.4, "learning_rate": 1.117134017974647e-06, "loss": 0.001, "step": 326480 }, { "epoch": 78.41, "learning_rate": 1.1161910323077507e-06, "loss": 0.0009, "step": 326490 }, { "epoch": 78.41, "learning_rate": 1.1152484403089247e-06, "loss": 0.0008, "step": 326500 }, { "epoch": 78.41, "learning_rate": 1.114306241985752e-06, "loss": 0.0011, "step": 326510 }, { "epoch": 78.41, "learning_rate": 1.1133644373458152e-06, "loss": 0.0008, "step": 326520 }, { "epoch": 78.41, "learning_rate": 1.1124230263967083e-06, "loss": 0.001, "step": 326530 }, { "epoch": 78.42, "learning_rate": 1.1114820091460087e-06, "loss": 0.0009, "step": 326540 }, { "epoch": 78.42, "learning_rate": 1.110541385601288e-06, "loss": 0.0009, "step": 326550 }, { "epoch": 78.42, "learning_rate": 1.1096011557701291e-06, "loss": 0.0009, "step": 326560 }, { "epoch": 78.42, "learning_rate": 1.1086613196601036e-06, "loss": 0.0009, "step": 326570 }, { "epoch": 78.43, "learning_rate": 1.1077218772787834e-06, "loss": 0.0013, "step": 326580 }, { "epoch": 78.43, "learning_rate": 1.1067828286337178e-06, "loss": 0.0009, "step": 326590 }, { "epoch": 78.43, "learning_rate": 1.1058441737324899e-06, "loss": 0.0009, "step": 326600 }, { "epoch": 78.43, "learning_rate": 1.1049059125826433e-06, "loss": 0.0014, "step": 326610 }, { "epoch": 78.44, "learning_rate": 1.1039680451917445e-06, "loss": 0.0011, "step": 326620 }, { "epoch": 78.44, "learning_rate": 1.1030305715673373e-06, "loss": 0.001, "step": 326630 }, { "epoch": 78.44, "learning_rate": 1.1020934917169768e-06, "loss": 0.0009, "step": 326640 }, { "epoch": 78.44, "learning_rate": 1.1011568056482123e-06, "loss": 0.0011, "step": 326650 }, { "epoch": 78.44, "learning_rate": 1.1002205133685716e-06, "loss": 0.0009, "step": 326660 }, { "epoch": 78.45, "learning_rate": 1.0992846148856207e-06, "loss": 0.0008, "step": 326670 }, { "epoch": 78.45, "learning_rate": 1.0983491102068755e-06, "loss": 0.0009, "step": 326680 }, { "epoch": 78.45, "learning_rate": 1.0974139993398746e-06, "loss": 0.001, "step": 326690 }, { "epoch": 78.45, "learning_rate": 1.096479282292151e-06, "loss": 0.001, "step": 326700 }, { "epoch": 78.46, "learning_rate": 1.095544959071232e-06, "loss": 0.0008, "step": 326710 }, { "epoch": 78.46, "learning_rate": 1.0946110296846446e-06, "loss": 0.0008, "step": 326720 }, { "epoch": 78.46, "learning_rate": 1.0936774941398997e-06, "loss": 0.0011, "step": 326730 }, { "epoch": 78.46, "learning_rate": 1.0927443524445247e-06, "loss": 0.0012, "step": 326740 }, { "epoch": 78.47, "learning_rate": 1.09181160460603e-06, "loss": 0.0009, "step": 326750 }, { "epoch": 78.47, "learning_rate": 1.090879250631932e-06, "loss": 0.0008, "step": 326760 }, { "epoch": 78.47, "learning_rate": 1.0899472905297358e-06, "loss": 0.001, "step": 326770 }, { "epoch": 78.47, "learning_rate": 1.0890157243069465e-06, "loss": 0.0009, "step": 326780 }, { "epoch": 78.47, "learning_rate": 1.0880845519710635e-06, "loss": 0.0009, "step": 326790 }, { "epoch": 78.48, "learning_rate": 1.0871537735295812e-06, "loss": 0.0012, "step": 326800 }, { "epoch": 78.48, "learning_rate": 1.0862233889900153e-06, "loss": 0.0009, "step": 326810 }, { "epoch": 78.48, "learning_rate": 1.0852933983598435e-06, "loss": 0.001, "step": 326820 }, { "epoch": 78.48, "learning_rate": 1.0843638016465485e-06, "loss": 0.0011, "step": 326830 }, { "epoch": 78.49, "learning_rate": 1.08343459885763e-06, "loss": 0.001, "step": 326840 }, { "epoch": 78.49, "learning_rate": 1.0825057900005707e-06, "loss": 0.0009, "step": 326850 }, { "epoch": 78.49, "learning_rate": 1.081577375082843e-06, "loss": 0.0011, "step": 326860 }, { "epoch": 78.49, "learning_rate": 1.0806493541119233e-06, "loss": 0.001, "step": 326870 }, { "epoch": 78.49, "learning_rate": 1.0797217270952897e-06, "loss": 0.0009, "step": 326880 }, { "epoch": 78.5, "learning_rate": 1.0787944940404137e-06, "loss": 0.0009, "step": 326890 }, { "epoch": 78.5, "learning_rate": 1.0778676549547506e-06, "loss": 0.0009, "step": 326900 }, { "epoch": 78.5, "learning_rate": 1.0769412098457833e-06, "loss": 0.0009, "step": 326910 }, { "epoch": 78.5, "learning_rate": 1.076015158720961e-06, "loss": 0.0009, "step": 326920 }, { "epoch": 78.51, "learning_rate": 1.0750895015877394e-06, "loss": 0.0008, "step": 326930 }, { "epoch": 78.51, "learning_rate": 1.0741642384535733e-06, "loss": 0.001, "step": 326940 }, { "epoch": 78.51, "learning_rate": 1.0732393693259236e-06, "loss": 0.0009, "step": 326950 }, { "epoch": 78.51, "learning_rate": 1.0723148942122342e-06, "loss": 0.0009, "step": 326960 }, { "epoch": 78.52, "learning_rate": 1.0713908131199435e-06, "loss": 0.0022, "step": 326970 }, { "epoch": 78.52, "learning_rate": 1.0704671260564958e-06, "loss": 0.0009, "step": 326980 }, { "epoch": 78.52, "learning_rate": 1.069543833029335e-06, "loss": 0.0042, "step": 326990 }, { "epoch": 78.52, "learning_rate": 1.068620934045894e-06, "loss": 0.001, "step": 327000 }, { "epoch": 78.52, "learning_rate": 1.0676984291136005e-06, "loss": 0.0009, "step": 327010 }, { "epoch": 78.53, "learning_rate": 1.0667763182398926e-06, "loss": 0.0011, "step": 327020 }, { "epoch": 78.53, "learning_rate": 1.065854601432187e-06, "loss": 0.001, "step": 327030 }, { "epoch": 78.53, "learning_rate": 1.064933278697905e-06, "loss": 0.001, "step": 327040 }, { "epoch": 78.53, "learning_rate": 1.0640123500444798e-06, "loss": 0.001, "step": 327050 }, { "epoch": 78.54, "learning_rate": 1.0630918154793168e-06, "loss": 0.0011, "step": 327060 }, { "epoch": 78.54, "learning_rate": 1.062171675009821e-06, "loss": 0.001, "step": 327070 }, { "epoch": 78.54, "learning_rate": 1.0612519286434253e-06, "loss": 0.0013, "step": 327080 }, { "epoch": 78.54, "learning_rate": 1.0603325763875238e-06, "loss": 0.0011, "step": 327090 }, { "epoch": 78.55, "learning_rate": 1.0594136182495162e-06, "loss": 0.0009, "step": 327100 }, { "epoch": 78.55, "learning_rate": 1.0584950542368077e-06, "loss": 0.0008, "step": 327110 }, { "epoch": 78.55, "learning_rate": 1.0575768843567979e-06, "loss": 0.0009, "step": 327120 }, { "epoch": 78.55, "learning_rate": 1.0566591086168753e-06, "loss": 0.0015, "step": 327130 }, { "epoch": 78.55, "learning_rate": 1.0557417270244396e-06, "loss": 0.001, "step": 327140 }, { "epoch": 78.56, "learning_rate": 1.0548247395868682e-06, "loss": 0.0009, "step": 327150 }, { "epoch": 78.56, "learning_rate": 1.0539081463115496e-06, "loss": 0.0009, "step": 327160 }, { "epoch": 78.56, "learning_rate": 1.0529919472058724e-06, "loss": 0.0012, "step": 327170 }, { "epoch": 78.56, "learning_rate": 1.0520761422771974e-06, "loss": 0.001, "step": 327180 }, { "epoch": 78.57, "learning_rate": 1.051160731532924e-06, "loss": 0.0013, "step": 327190 }, { "epoch": 78.57, "learning_rate": 1.0502457149804025e-06, "loss": 0.001, "step": 327200 }, { "epoch": 78.57, "learning_rate": 1.0493310926270096e-06, "loss": 0.0012, "step": 327210 }, { "epoch": 78.57, "learning_rate": 1.0484168644801118e-06, "loss": 0.001, "step": 327220 }, { "epoch": 78.57, "learning_rate": 1.0475030305470756e-06, "loss": 0.0009, "step": 327230 }, { "epoch": 78.58, "learning_rate": 1.0465895908352562e-06, "loss": 0.0009, "step": 327240 }, { "epoch": 78.58, "learning_rate": 1.0456765453520035e-06, "loss": 0.001, "step": 327250 }, { "epoch": 78.58, "learning_rate": 1.0447638941046834e-06, "loss": 0.0047, "step": 327260 }, { "epoch": 78.58, "learning_rate": 1.0438516371006346e-06, "loss": 0.0029, "step": 327270 }, { "epoch": 78.59, "learning_rate": 1.0429397743472014e-06, "loss": 0.0009, "step": 327280 }, { "epoch": 78.59, "learning_rate": 1.0420283058517444e-06, "loss": 0.001, "step": 327290 }, { "epoch": 78.59, "learning_rate": 1.0411172316215856e-06, "loss": 0.0009, "step": 327300 }, { "epoch": 78.59, "learning_rate": 1.0402065516640691e-06, "loss": 0.001, "step": 327310 }, { "epoch": 78.6, "learning_rate": 1.0392962659865279e-06, "loss": 0.0009, "step": 327320 }, { "epoch": 78.6, "learning_rate": 1.0383863745963008e-06, "loss": 0.001, "step": 327330 }, { "epoch": 78.6, "learning_rate": 1.0374768775007037e-06, "loss": 0.0011, "step": 327340 }, { "epoch": 78.6, "learning_rate": 1.036567774707059e-06, "loss": 0.0008, "step": 327350 }, { "epoch": 78.6, "learning_rate": 1.0356590662226994e-06, "loss": 0.001, "step": 327360 }, { "epoch": 78.61, "learning_rate": 1.034750752054936e-06, "loss": 0.001, "step": 327370 }, { "epoch": 78.61, "learning_rate": 1.033842832211085e-06, "loss": 0.0009, "step": 327380 }, { "epoch": 78.61, "learning_rate": 1.032935306698457e-06, "loss": 0.0013, "step": 327390 }, { "epoch": 78.61, "learning_rate": 1.0320281755243632e-06, "loss": 0.0009, "step": 327400 }, { "epoch": 78.62, "learning_rate": 1.0311214386961088e-06, "loss": 0.001, "step": 327410 }, { "epoch": 78.62, "learning_rate": 1.0302150962209877e-06, "loss": 0.0008, "step": 327420 }, { "epoch": 78.62, "learning_rate": 1.029309148106311e-06, "loss": 0.0011, "step": 327430 }, { "epoch": 78.62, "learning_rate": 1.0284035943593674e-06, "loss": 0.0009, "step": 327440 }, { "epoch": 78.63, "learning_rate": 1.0274984349874451e-06, "loss": 0.0024, "step": 327450 }, { "epoch": 78.63, "learning_rate": 1.026593669997844e-06, "loss": 0.001, "step": 327460 }, { "epoch": 78.63, "learning_rate": 1.0256892993978474e-06, "loss": 0.001, "step": 327470 }, { "epoch": 78.63, "learning_rate": 1.0247853231947324e-06, "loss": 0.0009, "step": 327480 }, { "epoch": 78.63, "learning_rate": 1.0238817413957825e-06, "loss": 0.001, "step": 327490 }, { "epoch": 78.64, "learning_rate": 1.0229785540082748e-06, "loss": 0.0022, "step": 327500 }, { "epoch": 78.64, "learning_rate": 1.0220757610394872e-06, "loss": 0.001, "step": 327510 }, { "epoch": 78.64, "learning_rate": 1.0211733624966802e-06, "loss": 0.0011, "step": 327520 }, { "epoch": 78.64, "learning_rate": 1.0202713583871259e-06, "loss": 0.0009, "step": 327530 }, { "epoch": 78.65, "learning_rate": 1.019369748718091e-06, "loss": 0.001, "step": 327540 }, { "epoch": 78.65, "learning_rate": 1.0184685334968303e-06, "loss": 0.0009, "step": 327550 }, { "epoch": 78.65, "learning_rate": 1.0175677127306049e-06, "loss": 0.001, "step": 327560 }, { "epoch": 78.65, "learning_rate": 1.0166672864266758e-06, "loss": 0.0012, "step": 327570 }, { "epoch": 78.65, "learning_rate": 1.015767254592287e-06, "loss": 0.0014, "step": 327580 }, { "epoch": 78.66, "learning_rate": 1.0148676172346772e-06, "loss": 0.0008, "step": 327590 }, { "epoch": 78.66, "learning_rate": 1.0139683743611073e-06, "loss": 0.001, "step": 327600 }, { "epoch": 78.66, "learning_rate": 1.0130695259788158e-06, "loss": 0.0011, "step": 327610 }, { "epoch": 78.66, "learning_rate": 1.0121710720950362e-06, "loss": 0.0011, "step": 327620 }, { "epoch": 78.67, "learning_rate": 1.0112730127170067e-06, "loss": 0.0009, "step": 327630 }, { "epoch": 78.67, "learning_rate": 1.010375347851955e-06, "loss": 0.0013, "step": 327640 }, { "epoch": 78.67, "learning_rate": 1.00947807750712e-06, "loss": 0.001, "step": 327650 }, { "epoch": 78.67, "learning_rate": 1.0085812016897178e-06, "loss": 0.0008, "step": 327660 }, { "epoch": 78.68, "learning_rate": 1.0076847204069762e-06, "loss": 0.0009, "step": 327670 }, { "epoch": 78.68, "learning_rate": 1.0067886336661114e-06, "loss": 0.0009, "step": 327680 }, { "epoch": 78.68, "learning_rate": 1.00589294147434e-06, "loss": 0.0011, "step": 327690 }, { "epoch": 78.68, "learning_rate": 1.0049976438388787e-06, "loss": 0.0011, "step": 327700 }, { "epoch": 78.68, "learning_rate": 1.0041027407669435e-06, "loss": 0.0009, "step": 327710 }, { "epoch": 78.69, "learning_rate": 1.0032082322657233e-06, "loss": 0.0009, "step": 327720 }, { "epoch": 78.69, "learning_rate": 1.0023141183424346e-06, "loss": 0.0011, "step": 327730 }, { "epoch": 78.69, "learning_rate": 1.001420399004277e-06, "loss": 0.0009, "step": 327740 }, { "epoch": 78.69, "learning_rate": 1.000527074258445e-06, "loss": 0.0038, "step": 327750 }, { "epoch": 78.7, "learning_rate": 9.996341441121327e-07, "loss": 0.001, "step": 327760 }, { "epoch": 78.7, "learning_rate": 9.987416085725286e-07, "loss": 0.0009, "step": 327770 }, { "epoch": 78.7, "learning_rate": 9.978494676468276e-07, "loss": 0.0009, "step": 327780 }, { "epoch": 78.7, "learning_rate": 9.969577213422066e-07, "loss": 0.0009, "step": 327790 }, { "epoch": 78.71, "learning_rate": 9.960663696658545e-07, "loss": 0.0012, "step": 327800 }, { "epoch": 78.71, "learning_rate": 9.95175412624938e-07, "loss": 0.0009, "step": 327810 }, { "epoch": 78.71, "learning_rate": 9.942848502266455e-07, "loss": 0.0013, "step": 327820 }, { "epoch": 78.71, "learning_rate": 9.93394682478138e-07, "loss": 0.001, "step": 327830 }, { "epoch": 78.71, "learning_rate": 9.925049093865934e-07, "loss": 0.001, "step": 327840 }, { "epoch": 78.72, "learning_rate": 9.91615530959178e-07, "loss": 0.0009, "step": 327850 }, { "epoch": 78.72, "learning_rate": 9.907265472030359e-07, "loss": 0.0009, "step": 327860 }, { "epoch": 78.72, "learning_rate": 9.898379581253447e-07, "loss": 0.0011, "step": 327870 }, { "epoch": 78.72, "learning_rate": 9.8894976373326e-07, "loss": 0.001, "step": 327880 }, { "epoch": 78.73, "learning_rate": 9.880619640339205e-07, "loss": 0.001, "step": 327890 }, { "epoch": 78.73, "learning_rate": 9.871745590344926e-07, "loss": 0.001, "step": 327900 }, { "epoch": 78.73, "learning_rate": 9.862875487421096e-07, "loss": 0.0011, "step": 327910 }, { "epoch": 78.73, "learning_rate": 9.854009331639214e-07, "loss": 0.0012, "step": 327920 }, { "epoch": 78.73, "learning_rate": 9.845147123070607e-07, "loss": 0.0012, "step": 327930 }, { "epoch": 78.74, "learning_rate": 9.83628886178678e-07, "loss": 0.0011, "step": 327940 }, { "epoch": 78.74, "learning_rate": 9.827434547859005e-07, "loss": 0.001, "step": 327950 }, { "epoch": 78.74, "learning_rate": 9.818584181358503e-07, "loss": 0.0009, "step": 327960 }, { "epoch": 78.74, "learning_rate": 9.809737762356608e-07, "loss": 0.0008, "step": 327970 }, { "epoch": 78.75, "learning_rate": 9.800895290924593e-07, "loss": 0.001, "step": 327980 }, { "epoch": 78.75, "learning_rate": 9.79205676713374e-07, "loss": 0.0009, "step": 327990 }, { "epoch": 78.75, "learning_rate": 9.783222191054986e-07, "loss": 0.0009, "step": 328000 }, { "epoch": 78.75, "learning_rate": 9.774391562759721e-07, "loss": 0.001, "step": 328010 }, { "epoch": 78.76, "learning_rate": 9.765564882318888e-07, "loss": 0.0009, "step": 328020 }, { "epoch": 78.76, "learning_rate": 9.75674214980371e-07, "loss": 0.0047, "step": 328030 }, { "epoch": 78.76, "learning_rate": 9.747923365285127e-07, "loss": 0.001, "step": 328040 }, { "epoch": 78.76, "learning_rate": 9.739108528834195e-07, "loss": 0.001, "step": 328050 }, { "epoch": 78.76, "learning_rate": 9.730297640521912e-07, "loss": 0.0009, "step": 328060 }, { "epoch": 78.77, "learning_rate": 9.721490700419223e-07, "loss": 0.004, "step": 328070 }, { "epoch": 78.77, "learning_rate": 9.712687708597068e-07, "loss": 0.0009, "step": 328080 }, { "epoch": 78.77, "learning_rate": 9.703888665126393e-07, "loss": 0.0009, "step": 328090 }, { "epoch": 78.77, "learning_rate": 9.695093570077863e-07, "loss": 0.0008, "step": 328100 }, { "epoch": 78.78, "learning_rate": 9.68630242352253e-07, "loss": 0.0008, "step": 328110 }, { "epoch": 78.78, "learning_rate": 9.677515225531064e-07, "loss": 0.0009, "step": 328120 }, { "epoch": 78.78, "learning_rate": 9.668731976174295e-07, "loss": 0.001, "step": 328130 }, { "epoch": 78.78, "learning_rate": 9.659952675522888e-07, "loss": 0.0009, "step": 328140 }, { "epoch": 78.79, "learning_rate": 9.651177323647563e-07, "loss": 0.001, "step": 328150 }, { "epoch": 78.79, "learning_rate": 9.642405920619046e-07, "loss": 0.001, "step": 328160 }, { "epoch": 78.79, "learning_rate": 9.633638466507833e-07, "loss": 0.0009, "step": 328170 }, { "epoch": 78.79, "learning_rate": 9.624874961384755e-07, "loss": 0.001, "step": 328180 }, { "epoch": 78.79, "learning_rate": 9.616115405320203e-07, "loss": 0.0011, "step": 328190 }, { "epoch": 78.8, "learning_rate": 9.607359798384785e-07, "loss": 0.0009, "step": 328200 }, { "epoch": 78.8, "learning_rate": 9.598608140649001e-07, "loss": 0.001, "step": 328210 }, { "epoch": 78.8, "learning_rate": 9.589860432183294e-07, "loss": 0.0008, "step": 328220 }, { "epoch": 78.8, "learning_rate": 9.581116673058222e-07, "loss": 0.0009, "step": 328230 }, { "epoch": 78.81, "learning_rate": 9.572376863344057e-07, "loss": 0.0009, "step": 328240 }, { "epoch": 78.81, "learning_rate": 9.5636410031113e-07, "loss": 0.0009, "step": 328250 }, { "epoch": 78.81, "learning_rate": 9.55490909243023e-07, "loss": 0.001, "step": 328260 }, { "epoch": 78.81, "learning_rate": 9.54618113137118e-07, "loss": 0.001, "step": 328270 }, { "epoch": 78.81, "learning_rate": 9.537457120004422e-07, "loss": 0.0011, "step": 328280 }, { "epoch": 78.82, "learning_rate": 9.528737058400239e-07, "loss": 0.0013, "step": 328290 }, { "epoch": 78.82, "learning_rate": 9.520020946628904e-07, "loss": 0.0009, "step": 328300 }, { "epoch": 78.82, "learning_rate": 9.511308784760475e-07, "loss": 0.0009, "step": 328310 }, { "epoch": 78.82, "learning_rate": 9.502600572865284e-07, "loss": 0.001, "step": 328320 }, { "epoch": 78.83, "learning_rate": 9.493896311013328e-07, "loss": 0.0009, "step": 328330 }, { "epoch": 78.83, "learning_rate": 9.485195999274721e-07, "loss": 0.0009, "step": 328340 }, { "epoch": 78.83, "learning_rate": 9.476499637719515e-07, "loss": 0.001, "step": 328350 }, { "epoch": 78.83, "learning_rate": 9.46780722641788e-07, "loss": 0.0009, "step": 328360 }, { "epoch": 78.84, "learning_rate": 9.459118765439646e-07, "loss": 0.0009, "step": 328370 }, { "epoch": 78.84, "learning_rate": 9.450434254854867e-07, "loss": 0.0013, "step": 328380 }, { "epoch": 78.84, "learning_rate": 9.44175369473349e-07, "loss": 0.0009, "step": 328390 }, { "epoch": 78.84, "learning_rate": 9.433077085145348e-07, "loss": 0.001, "step": 328400 }, { "epoch": 78.84, "learning_rate": 9.424404426160383e-07, "loss": 0.0009, "step": 328410 }, { "epoch": 78.85, "learning_rate": 9.415735717848484e-07, "loss": 0.0009, "step": 328420 }, { "epoch": 78.85, "learning_rate": 9.407070960279318e-07, "loss": 0.001, "step": 328430 }, { "epoch": 78.85, "learning_rate": 9.398410153522774e-07, "loss": 0.0011, "step": 328440 }, { "epoch": 78.85, "learning_rate": 9.389753297648518e-07, "loss": 0.0011, "step": 328450 }, { "epoch": 78.86, "learning_rate": 9.381100392726383e-07, "loss": 0.0009, "step": 328460 }, { "epoch": 78.86, "learning_rate": 9.372451438825924e-07, "loss": 0.0015, "step": 328470 }, { "epoch": 78.86, "learning_rate": 9.363806436016809e-07, "loss": 0.0009, "step": 328480 }, { "epoch": 78.86, "learning_rate": 9.355165384368758e-07, "loss": 0.0008, "step": 328490 }, { "epoch": 78.87, "learning_rate": 9.346528283951328e-07, "loss": 0.0017, "step": 328500 }, { "epoch": 78.87, "learning_rate": 9.337895134834018e-07, "loss": 0.0011, "step": 328510 }, { "epoch": 78.87, "learning_rate": 9.329265937086385e-07, "loss": 0.0009, "step": 328520 }, { "epoch": 78.87, "learning_rate": 9.320640690777871e-07, "loss": 0.0031, "step": 328530 }, { "epoch": 78.87, "learning_rate": 9.312019395978034e-07, "loss": 0.001, "step": 328540 }, { "epoch": 78.88, "learning_rate": 9.303402052756149e-07, "loss": 0.0009, "step": 328550 }, { "epoch": 78.88, "learning_rate": 9.294788661181886e-07, "loss": 0.0011, "step": 328560 }, { "epoch": 78.88, "learning_rate": 9.286179221324298e-07, "loss": 0.0011, "step": 328570 }, { "epoch": 78.88, "learning_rate": 9.277573733252887e-07, "loss": 0.001, "step": 328580 }, { "epoch": 78.89, "learning_rate": 9.268972197036929e-07, "loss": 0.001, "step": 328590 }, { "epoch": 78.89, "learning_rate": 9.260374612745703e-07, "loss": 0.0009, "step": 328600 }, { "epoch": 78.89, "learning_rate": 9.251780980448377e-07, "loss": 0.0009, "step": 328610 }, { "epoch": 78.89, "learning_rate": 9.243191300214283e-07, "loss": 0.0011, "step": 328620 }, { "epoch": 78.89, "learning_rate": 9.234605572112476e-07, "loss": 0.0009, "step": 328630 }, { "epoch": 78.9, "learning_rate": 9.22602379621218e-07, "loss": 0.001, "step": 328640 }, { "epoch": 78.9, "learning_rate": 9.21744597258245e-07, "loss": 0.0011, "step": 328650 }, { "epoch": 78.9, "learning_rate": 9.208872101292399e-07, "loss": 0.0012, "step": 328660 }, { "epoch": 78.9, "learning_rate": 9.200302182411024e-07, "loss": 0.0009, "step": 328670 }, { "epoch": 78.91, "learning_rate": 9.191736216007385e-07, "loss": 0.0009, "step": 328680 }, { "epoch": 78.91, "learning_rate": 9.183174202150424e-07, "loss": 0.0021, "step": 328690 }, { "epoch": 78.91, "learning_rate": 9.174616140909254e-07, "loss": 0.0009, "step": 328700 }, { "epoch": 78.91, "learning_rate": 9.166062032352541e-07, "loss": 0.0011, "step": 328710 }, { "epoch": 78.92, "learning_rate": 9.157511876549285e-07, "loss": 0.0009, "step": 328720 }, { "epoch": 78.92, "learning_rate": 9.148965673568433e-07, "loss": 0.001, "step": 328730 }, { "epoch": 78.92, "learning_rate": 9.14042342347865e-07, "loss": 0.001, "step": 328740 }, { "epoch": 78.92, "learning_rate": 9.131885126348883e-07, "loss": 0.001, "step": 328750 }, { "epoch": 78.92, "learning_rate": 9.123350782247742e-07, "loss": 0.001, "step": 328760 }, { "epoch": 78.93, "learning_rate": 9.114820391244061e-07, "loss": 0.001, "step": 328770 }, { "epoch": 78.93, "learning_rate": 9.106293953406508e-07, "loss": 0.001, "step": 328780 }, { "epoch": 78.93, "learning_rate": 9.097771468803751e-07, "loss": 0.0009, "step": 328790 }, { "epoch": 78.93, "learning_rate": 9.0892529375044e-07, "loss": 0.0009, "step": 328800 }, { "epoch": 78.94, "learning_rate": 9.080738359577012e-07, "loss": 0.0014, "step": 328810 }, { "epoch": 78.94, "learning_rate": 9.072227735090255e-07, "loss": 0.0011, "step": 328820 }, { "epoch": 78.94, "learning_rate": 9.063721064112629e-07, "loss": 0.0009, "step": 328830 }, { "epoch": 78.94, "learning_rate": 9.05521834671269e-07, "loss": 0.0014, "step": 328840 }, { "epoch": 78.95, "learning_rate": 9.046719582958829e-07, "loss": 0.0028, "step": 328850 }, { "epoch": 78.95, "learning_rate": 9.038224772919435e-07, "loss": 0.001, "step": 328860 }, { "epoch": 78.95, "learning_rate": 9.029733916663063e-07, "loss": 0.001, "step": 328870 }, { "epoch": 79.0, "learning_rate": 9.021247014257994e-07, "loss": 0.001, "step": 328880 }, { "epoch": 79.0, "learning_rate": 9.012764065772672e-07, "loss": 0.0009, "step": 328890 }, { "epoch": 79.01, "learning_rate": 9.00428507127532e-07, "loss": 0.0008, "step": 328900 }, { "epoch": 79.01, "learning_rate": 8.995810030834218e-07, "loss": 0.0009, "step": 328910 }, { "epoch": 79.01, "learning_rate": 8.987338944517643e-07, "loss": 0.001, "step": 328920 }, { "epoch": 79.01, "learning_rate": 8.978871812393819e-07, "loss": 0.0011, "step": 328930 }, { "epoch": 79.01, "learning_rate": 8.970408634530969e-07, "loss": 0.0009, "step": 328940 }, { "epoch": 79.02, "learning_rate": 8.961949410997206e-07, "loss": 0.0008, "step": 328950 }, { "epoch": 79.02, "learning_rate": 8.953494141860585e-07, "loss": 0.0008, "step": 328960 }, { "epoch": 79.02, "learning_rate": 8.945042827189331e-07, "loss": 0.0009, "step": 328970 }, { "epoch": 79.02, "learning_rate": 8.936595467051445e-07, "loss": 0.0009, "step": 328980 }, { "epoch": 79.03, "learning_rate": 8.928152061514927e-07, "loss": 0.0009, "step": 328990 }, { "epoch": 79.03, "learning_rate": 8.919712610647779e-07, "loss": 0.001, "step": 329000 }, { "epoch": 79.03, "learning_rate": 8.911277114518058e-07, "loss": 0.001, "step": 329010 }, { "epoch": 79.03, "learning_rate": 8.902845573193541e-07, "loss": 0.0031, "step": 329020 }, { "epoch": 79.03, "learning_rate": 8.894417986742232e-07, "loss": 0.0009, "step": 329030 }, { "epoch": 79.04, "learning_rate": 8.885994355232019e-07, "loss": 0.0009, "step": 329040 }, { "epoch": 79.04, "learning_rate": 8.877574678730683e-07, "loss": 0.001, "step": 329050 }, { "epoch": 79.04, "learning_rate": 8.869158957305945e-07, "loss": 0.0009, "step": 329060 }, { "epoch": 79.04, "learning_rate": 8.860747191025753e-07, "loss": 0.0008, "step": 329070 }, { "epoch": 79.05, "learning_rate": 8.85233937995783e-07, "loss": 0.0009, "step": 329080 }, { "epoch": 79.05, "learning_rate": 8.843935524169733e-07, "loss": 0.0011, "step": 329090 }, { "epoch": 79.05, "learning_rate": 8.83553562372924e-07, "loss": 0.0018, "step": 329100 }, { "epoch": 79.05, "learning_rate": 8.827139678704021e-07, "loss": 0.0014, "step": 329110 }, { "epoch": 79.06, "learning_rate": 8.818747689161689e-07, "loss": 0.0009, "step": 329120 }, { "epoch": 79.06, "learning_rate": 8.810359655169687e-07, "loss": 0.0011, "step": 329130 }, { "epoch": 79.06, "learning_rate": 8.80197557679574e-07, "loss": 0.0009, "step": 329140 }, { "epoch": 79.06, "learning_rate": 8.793595454107296e-07, "loss": 0.0008, "step": 329150 }, { "epoch": 79.06, "learning_rate": 8.785219287171853e-07, "loss": 0.0009, "step": 329160 }, { "epoch": 79.07, "learning_rate": 8.77684707605686e-07, "loss": 0.0009, "step": 329170 }, { "epoch": 79.07, "learning_rate": 8.768478820829706e-07, "loss": 0.0008, "step": 329180 }, { "epoch": 79.07, "learning_rate": 8.760114521557839e-07, "loss": 0.0009, "step": 329190 }, { "epoch": 79.07, "learning_rate": 8.751754178308535e-07, "loss": 0.0011, "step": 329200 }, { "epoch": 79.08, "learning_rate": 8.743397791149188e-07, "loss": 0.0009, "step": 329210 }, { "epoch": 79.08, "learning_rate": 8.735045360147187e-07, "loss": 0.0009, "step": 329220 }, { "epoch": 79.08, "learning_rate": 8.726696885369534e-07, "loss": 0.0012, "step": 329230 }, { "epoch": 79.08, "learning_rate": 8.718352366883731e-07, "loss": 0.0009, "step": 329240 }, { "epoch": 79.09, "learning_rate": 8.710011804756779e-07, "loss": 0.0036, "step": 329250 }, { "epoch": 79.09, "learning_rate": 8.701675199056014e-07, "loss": 0.0013, "step": 329260 }, { "epoch": 79.09, "learning_rate": 8.693342549848438e-07, "loss": 0.0009, "step": 329270 }, { "epoch": 79.09, "learning_rate": 8.685013857201219e-07, "loss": 0.0011, "step": 329280 }, { "epoch": 79.09, "learning_rate": 8.676689121181359e-07, "loss": 0.0013, "step": 329290 }, { "epoch": 79.1, "learning_rate": 8.668368341856026e-07, "loss": 0.0012, "step": 329300 }, { "epoch": 79.1, "learning_rate": 8.660051519292111e-07, "loss": 0.0011, "step": 329310 }, { "epoch": 79.1, "learning_rate": 8.651738653556674e-07, "loss": 0.0008, "step": 329320 }, { "epoch": 79.1, "learning_rate": 8.643429744716602e-07, "loss": 0.0008, "step": 329330 }, { "epoch": 79.11, "learning_rate": 8.635124792838789e-07, "loss": 0.0008, "step": 329340 }, { "epoch": 79.11, "learning_rate": 8.62682379799018e-07, "loss": 0.0008, "step": 329350 }, { "epoch": 79.11, "learning_rate": 8.618526760237611e-07, "loss": 0.0011, "step": 329360 }, { "epoch": 79.11, "learning_rate": 8.610233679647861e-07, "loss": 0.0013, "step": 329370 }, { "epoch": 79.11, "learning_rate": 8.601944556287766e-07, "loss": 0.0009, "step": 329380 }, { "epoch": 79.12, "learning_rate": 8.593659390224052e-07, "loss": 0.0008, "step": 329390 }, { "epoch": 79.12, "learning_rate": 8.58537818152344e-07, "loss": 0.001, "step": 329400 }, { "epoch": 79.12, "learning_rate": 8.577100930252602e-07, "loss": 0.0009, "step": 329410 }, { "epoch": 79.12, "learning_rate": 8.568827636478205e-07, "loss": 0.0009, "step": 329420 }, { "epoch": 79.13, "learning_rate": 8.560558300266918e-07, "loss": 0.001, "step": 329430 }, { "epoch": 79.13, "learning_rate": 8.552292921685246e-07, "loss": 0.001, "step": 329440 }, { "epoch": 79.13, "learning_rate": 8.54403150079991e-07, "loss": 0.0009, "step": 329450 }, { "epoch": 79.13, "learning_rate": 8.535774037677302e-07, "loss": 0.001, "step": 329460 }, { "epoch": 79.14, "learning_rate": 8.52752053238387e-07, "loss": 0.0011, "step": 329470 }, { "epoch": 79.14, "learning_rate": 8.519270984986228e-07, "loss": 0.0009, "step": 329480 }, { "epoch": 79.14, "learning_rate": 8.511025395550765e-07, "loss": 0.0009, "step": 329490 }, { "epoch": 79.14, "learning_rate": 8.502783764143929e-07, "loss": 0.0008, "step": 329500 }, { "epoch": 79.14, "learning_rate": 8.49454609083189e-07, "loss": 0.0014, "step": 329510 }, { "epoch": 79.15, "learning_rate": 8.486312375681205e-07, "loss": 0.0008, "step": 329520 }, { "epoch": 79.15, "learning_rate": 8.478082618758099e-07, "loss": 0.001, "step": 329530 }, { "epoch": 79.15, "learning_rate": 8.469856820128852e-07, "loss": 0.001, "step": 329540 }, { "epoch": 79.15, "learning_rate": 8.461634979859745e-07, "loss": 0.0017, "step": 329550 }, { "epoch": 79.16, "learning_rate": 8.453417098016891e-07, "loss": 0.001, "step": 329560 }, { "epoch": 79.16, "learning_rate": 8.445203174666572e-07, "loss": 0.0008, "step": 329570 }, { "epoch": 79.16, "learning_rate": 8.436993209874844e-07, "loss": 0.0009, "step": 329580 }, { "epoch": 79.16, "learning_rate": 8.428787203707877e-07, "loss": 0.0012, "step": 329590 }, { "epoch": 79.17, "learning_rate": 8.420585156231842e-07, "loss": 0.0008, "step": 329600 }, { "epoch": 79.17, "learning_rate": 8.412387067512628e-07, "loss": 0.0014, "step": 329610 }, { "epoch": 79.17, "learning_rate": 8.404192937616351e-07, "loss": 0.001, "step": 329620 }, { "epoch": 79.17, "learning_rate": 8.396002766608957e-07, "loss": 0.001, "step": 329630 }, { "epoch": 79.17, "learning_rate": 8.387816554556449e-07, "loss": 0.0009, "step": 329640 }, { "epoch": 79.18, "learning_rate": 8.379634301524719e-07, "loss": 0.0009, "step": 329650 }, { "epoch": 79.18, "learning_rate": 8.371456007579659e-07, "loss": 0.001, "step": 329660 }, { "epoch": 79.18, "learning_rate": 8.363281672787104e-07, "loss": 0.0015, "step": 329670 }, { "epoch": 79.18, "learning_rate": 8.355111297212947e-07, "loss": 0.0012, "step": 329680 }, { "epoch": 79.19, "learning_rate": 8.346944880922969e-07, "loss": 0.0009, "step": 329690 }, { "epoch": 79.19, "learning_rate": 8.338782423982949e-07, "loss": 0.0016, "step": 329700 }, { "epoch": 79.19, "learning_rate": 8.330623926458558e-07, "loss": 0.0013, "step": 329710 }, { "epoch": 79.19, "learning_rate": 8.322469388415466e-07, "loss": 0.0013, "step": 329720 }, { "epoch": 79.19, "learning_rate": 8.314318809919453e-07, "loss": 0.001, "step": 329730 }, { "epoch": 79.2, "learning_rate": 8.306172191036187e-07, "loss": 0.0012, "step": 329740 }, { "epoch": 79.2, "learning_rate": 8.29802953183112e-07, "loss": 0.001, "step": 329750 }, { "epoch": 79.2, "learning_rate": 8.289890832369918e-07, "loss": 0.0009, "step": 329760 }, { "epoch": 79.2, "learning_rate": 8.28175609271814e-07, "loss": 0.001, "step": 329770 }, { "epoch": 79.21, "learning_rate": 8.273625312941235e-07, "loss": 0.0009, "step": 329780 }, { "epoch": 79.21, "learning_rate": 8.265498493104706e-07, "loss": 0.0031, "step": 329790 }, { "epoch": 79.21, "learning_rate": 8.257375633274e-07, "loss": 0.0009, "step": 329800 }, { "epoch": 79.21, "learning_rate": 8.249256733514565e-07, "loss": 0.0008, "step": 329810 }, { "epoch": 79.22, "learning_rate": 8.241141793891738e-07, "loss": 0.0019, "step": 329820 }, { "epoch": 79.22, "learning_rate": 8.23303081447091e-07, "loss": 0.001, "step": 329830 }, { "epoch": 79.22, "learning_rate": 8.224923795317418e-07, "loss": 0.0009, "step": 329840 }, { "epoch": 79.22, "learning_rate": 8.216820736496378e-07, "loss": 0.0017, "step": 329850 }, { "epoch": 79.22, "learning_rate": 8.208721638073291e-07, "loss": 0.0009, "step": 329860 }, { "epoch": 79.23, "learning_rate": 8.200626500113218e-07, "loss": 0.0011, "step": 329870 }, { "epoch": 79.23, "learning_rate": 8.192535322681383e-07, "loss": 0.0018, "step": 329880 }, { "epoch": 79.23, "learning_rate": 8.184448105843012e-07, "loss": 0.0009, "step": 329890 }, { "epoch": 79.23, "learning_rate": 8.176364849663165e-07, "loss": 0.0009, "step": 329900 }, { "epoch": 79.24, "learning_rate": 8.1682855542069e-07, "loss": 0.0009, "step": 329910 }, { "epoch": 79.24, "learning_rate": 8.160210219539333e-07, "loss": 0.0009, "step": 329920 }, { "epoch": 79.24, "learning_rate": 8.152138845725577e-07, "loss": 0.0009, "step": 329930 }, { "epoch": 79.24, "learning_rate": 8.144071432830524e-07, "loss": 0.001, "step": 329940 }, { "epoch": 79.25, "learning_rate": 8.136007980919181e-07, "loss": 0.001, "step": 329950 }, { "epoch": 79.25, "learning_rate": 8.127948490056381e-07, "loss": 0.0018, "step": 329960 }, { "epoch": 79.25, "learning_rate": 8.11989296030724e-07, "loss": 0.0012, "step": 329970 }, { "epoch": 79.25, "learning_rate": 8.11184139173643e-07, "loss": 0.0009, "step": 329980 }, { "epoch": 79.25, "learning_rate": 8.103793784408842e-07, "loss": 0.001, "step": 329990 }, { "epoch": 79.26, "learning_rate": 8.095750138389368e-07, "loss": 0.0011, "step": 330000 }, { "epoch": 79.26, "learning_rate": 8.087710453742736e-07, "loss": 0.0009, "step": 330010 }, { "epoch": 79.26, "learning_rate": 8.079674730533671e-07, "loss": 0.0011, "step": 330020 }, { "epoch": 79.26, "learning_rate": 8.071642968826898e-07, "loss": 0.0009, "step": 330030 }, { "epoch": 79.27, "learning_rate": 8.063615168687089e-07, "loss": 0.0012, "step": 330040 }, { "epoch": 79.27, "learning_rate": 8.055591330178913e-07, "loss": 0.0022, "step": 330050 }, { "epoch": 79.27, "learning_rate": 8.047571453366986e-07, "loss": 0.0008, "step": 330060 }, { "epoch": 79.27, "learning_rate": 8.039555538315924e-07, "loss": 0.0009, "step": 330070 }, { "epoch": 79.27, "learning_rate": 8.031543585090173e-07, "loss": 0.0038, "step": 330080 }, { "epoch": 79.28, "learning_rate": 8.023535593754295e-07, "loss": 0.0008, "step": 330090 }, { "epoch": 79.28, "learning_rate": 8.015531564372847e-07, "loss": 0.001, "step": 330100 }, { "epoch": 79.28, "learning_rate": 8.007531497010335e-07, "loss": 0.001, "step": 330110 }, { "epoch": 79.28, "learning_rate": 7.999535391730984e-07, "loss": 0.0008, "step": 330120 }, { "epoch": 79.29, "learning_rate": 7.991543248599298e-07, "loss": 0.0012, "step": 330130 }, { "epoch": 79.29, "learning_rate": 7.983555067679671e-07, "loss": 0.0013, "step": 330140 }, { "epoch": 79.29, "learning_rate": 7.97557084903644e-07, "loss": 0.0011, "step": 330150 }, { "epoch": 79.29, "learning_rate": 7.967590592733831e-07, "loss": 0.0009, "step": 330160 }, { "epoch": 79.3, "learning_rate": 7.959614298836126e-07, "loss": 0.0009, "step": 330170 }, { "epoch": 79.3, "learning_rate": 7.951641967407608e-07, "loss": 0.0009, "step": 330180 }, { "epoch": 79.3, "learning_rate": 7.943673598512391e-07, "loss": 0.0009, "step": 330190 }, { "epoch": 79.3, "learning_rate": 7.935709192214758e-07, "loss": 0.0009, "step": 330200 }, { "epoch": 79.3, "learning_rate": 7.927748748578822e-07, "loss": 0.0009, "step": 330210 }, { "epoch": 79.31, "learning_rate": 7.919792267668591e-07, "loss": 0.0009, "step": 330220 }, { "epoch": 79.31, "learning_rate": 7.911839749548178e-07, "loss": 0.0009, "step": 330230 }, { "epoch": 79.31, "learning_rate": 7.903891194281754e-07, "loss": 0.0009, "step": 330240 }, { "epoch": 79.31, "learning_rate": 7.895946601933157e-07, "loss": 0.001, "step": 330250 }, { "epoch": 79.32, "learning_rate": 7.888005972566504e-07, "loss": 0.0009, "step": 330260 }, { "epoch": 79.32, "learning_rate": 7.88006930624563e-07, "loss": 0.001, "step": 330270 }, { "epoch": 79.32, "learning_rate": 7.872136603034542e-07, "loss": 0.0009, "step": 330280 }, { "epoch": 79.32, "learning_rate": 7.864207862997075e-07, "loss": 0.001, "step": 330290 }, { "epoch": 79.33, "learning_rate": 7.856283086197069e-07, "loss": 0.0018, "step": 330300 }, { "epoch": 79.33, "learning_rate": 7.848362272698362e-07, "loss": 0.0063, "step": 330310 }, { "epoch": 79.33, "learning_rate": 7.840445422564735e-07, "loss": 0.001, "step": 330320 }, { "epoch": 79.33, "learning_rate": 7.832532535859916e-07, "loss": 0.0009, "step": 330330 }, { "epoch": 79.33, "learning_rate": 7.824623612647686e-07, "loss": 0.001, "step": 330340 }, { "epoch": 79.34, "learning_rate": 7.816718652991772e-07, "loss": 0.001, "step": 330350 }, { "epoch": 79.34, "learning_rate": 7.808817656955735e-07, "loss": 0.0011, "step": 330360 }, { "epoch": 79.34, "learning_rate": 7.800920624603192e-07, "loss": 0.0009, "step": 330370 }, { "epoch": 79.34, "learning_rate": 7.793027555997812e-07, "loss": 0.0009, "step": 330380 }, { "epoch": 79.35, "learning_rate": 7.785138451203156e-07, "loss": 0.001, "step": 330390 }, { "epoch": 79.35, "learning_rate": 7.777253310282729e-07, "loss": 0.001, "step": 330400 }, { "epoch": 79.35, "learning_rate": 7.769372133300034e-07, "loss": 0.0011, "step": 330410 }, { "epoch": 79.35, "learning_rate": 7.761494920318524e-07, "loss": 0.0011, "step": 330420 }, { "epoch": 79.35, "learning_rate": 7.753621671401701e-07, "loss": 0.0009, "step": 330430 }, { "epoch": 79.36, "learning_rate": 7.745752386612903e-07, "loss": 0.0014, "step": 330440 }, { "epoch": 79.36, "learning_rate": 7.73788706601547e-07, "loss": 0.0011, "step": 330450 }, { "epoch": 79.36, "learning_rate": 7.73002570967285e-07, "loss": 0.001, "step": 330460 }, { "epoch": 79.36, "learning_rate": 7.722168317648215e-07, "loss": 0.0008, "step": 330470 }, { "epoch": 79.37, "learning_rate": 7.714314890005015e-07, "loss": 0.0011, "step": 330480 }, { "epoch": 79.37, "learning_rate": 7.706465426806419e-07, "loss": 0.001, "step": 330490 }, { "epoch": 79.37, "learning_rate": 7.698619928115492e-07, "loss": 0.001, "step": 330500 }, { "epoch": 79.37, "learning_rate": 7.690778393995679e-07, "loss": 0.0013, "step": 330510 }, { "epoch": 79.38, "learning_rate": 7.682940824509932e-07, "loss": 0.0008, "step": 330520 }, { "epoch": 79.38, "learning_rate": 7.675107219721422e-07, "loss": 0.0009, "step": 330530 }, { "epoch": 79.38, "learning_rate": 7.667277579693266e-07, "loss": 0.0009, "step": 330540 }, { "epoch": 79.38, "learning_rate": 7.659451904488524e-07, "loss": 0.0009, "step": 330550 }, { "epoch": 79.38, "learning_rate": 7.651630194170145e-07, "loss": 0.001, "step": 330560 }, { "epoch": 79.39, "learning_rate": 7.643812448801136e-07, "loss": 0.0009, "step": 330570 }, { "epoch": 79.39, "learning_rate": 7.635998668444499e-07, "loss": 0.001, "step": 330580 }, { "epoch": 79.39, "learning_rate": 7.628188853163188e-07, "loss": 0.001, "step": 330590 }, { "epoch": 79.39, "learning_rate": 7.620383003020038e-07, "loss": 0.001, "step": 330600 }, { "epoch": 79.4, "learning_rate": 7.612581118077832e-07, "loss": 0.001, "step": 330610 }, { "epoch": 79.4, "learning_rate": 7.604783198399579e-07, "loss": 0.001, "step": 330620 }, { "epoch": 79.4, "learning_rate": 7.596989244048002e-07, "loss": 0.0009, "step": 330630 }, { "epoch": 79.4, "learning_rate": 7.589199255085778e-07, "loss": 0.0008, "step": 330640 }, { "epoch": 79.41, "learning_rate": 7.58141323157574e-07, "loss": 0.0009, "step": 330650 }, { "epoch": 79.41, "learning_rate": 7.573631173580565e-07, "loss": 0.0009, "step": 330660 }, { "epoch": 79.41, "learning_rate": 7.565853081162922e-07, "loss": 0.0009, "step": 330670 }, { "epoch": 79.41, "learning_rate": 7.558078954385483e-07, "loss": 0.0009, "step": 330680 }, { "epoch": 79.41, "learning_rate": 7.550308793310756e-07, "loss": 0.001, "step": 330690 }, { "epoch": 79.42, "learning_rate": 7.542542598001412e-07, "loss": 0.001, "step": 330700 }, { "epoch": 79.42, "learning_rate": 7.534780368519956e-07, "loss": 0.0011, "step": 330710 }, { "epoch": 79.42, "learning_rate": 7.527022104928894e-07, "loss": 0.001, "step": 330720 }, { "epoch": 79.42, "learning_rate": 7.519267807290786e-07, "loss": 0.0011, "step": 330730 }, { "epoch": 79.43, "learning_rate": 7.511517475667918e-07, "loss": 0.0008, "step": 330740 }, { "epoch": 79.43, "learning_rate": 7.503771110122793e-07, "loss": 0.0011, "step": 330750 }, { "epoch": 79.43, "learning_rate": 7.496028710717862e-07, "loss": 0.0012, "step": 330760 }, { "epoch": 79.43, "learning_rate": 7.488290277515409e-07, "loss": 0.0009, "step": 330770 }, { "epoch": 79.43, "learning_rate": 7.480555810577661e-07, "loss": 0.0009, "step": 330780 }, { "epoch": 79.44, "learning_rate": 7.472825309967013e-07, "loss": 0.0009, "step": 330790 }, { "epoch": 79.44, "learning_rate": 7.46509877574575e-07, "loss": 0.0009, "step": 330800 }, { "epoch": 79.44, "learning_rate": 7.457376207975985e-07, "loss": 0.0015, "step": 330810 }, { "epoch": 79.44, "learning_rate": 7.449657606720061e-07, "loss": 0.0019, "step": 330820 }, { "epoch": 79.45, "learning_rate": 7.441942972039983e-07, "loss": 0.0009, "step": 330830 }, { "epoch": 79.45, "learning_rate": 7.434232303997923e-07, "loss": 0.0012, "step": 330840 }, { "epoch": 79.45, "learning_rate": 7.426525602655999e-07, "loss": 0.0012, "step": 330850 }, { "epoch": 79.45, "learning_rate": 7.418822868076269e-07, "loss": 0.0011, "step": 330860 }, { "epoch": 79.46, "learning_rate": 7.411124100320854e-07, "loss": 0.0012, "step": 330870 }, { "epoch": 79.46, "learning_rate": 7.403429299451537e-07, "loss": 0.0009, "step": 330880 }, { "epoch": 79.46, "learning_rate": 7.395738465530432e-07, "loss": 0.0011, "step": 330890 }, { "epoch": 79.46, "learning_rate": 7.388051598619494e-07, "loss": 0.0027, "step": 330900 }, { "epoch": 79.46, "learning_rate": 7.380368698780615e-07, "loss": 0.0018, "step": 330910 }, { "epoch": 79.47, "learning_rate": 7.37268976607558e-07, "loss": 0.0009, "step": 330920 }, { "epoch": 79.47, "learning_rate": 7.365014800566339e-07, "loss": 0.0011, "step": 330930 }, { "epoch": 79.47, "learning_rate": 7.357343802314565e-07, "loss": 0.0009, "step": 330940 }, { "epoch": 79.47, "learning_rate": 7.349676771382152e-07, "loss": 0.001, "step": 330950 }, { "epoch": 79.48, "learning_rate": 7.34201370783083e-07, "loss": 0.0009, "step": 330960 }, { "epoch": 79.48, "learning_rate": 7.334354611722271e-07, "loss": 0.002, "step": 330970 }, { "epoch": 79.48, "learning_rate": 7.326699483118149e-07, "loss": 0.001, "step": 330980 }, { "epoch": 79.48, "learning_rate": 7.319048322080191e-07, "loss": 0.0015, "step": 330990 }, { "epoch": 79.49, "learning_rate": 7.311401128669903e-07, "loss": 0.0009, "step": 331000 }, { "epoch": 79.49, "learning_rate": 7.303757902949016e-07, "loss": 0.0017, "step": 331010 }, { "epoch": 79.49, "learning_rate": 7.296118644978866e-07, "loss": 0.0009, "step": 331020 }, { "epoch": 79.49, "learning_rate": 7.28848335482113e-07, "loss": 0.0016, "step": 331030 }, { "epoch": 79.49, "learning_rate": 7.280852032537255e-07, "loss": 0.0009, "step": 331040 }, { "epoch": 79.5, "learning_rate": 7.27322467818875e-07, "loss": 0.0009, "step": 331050 }, { "epoch": 79.5, "learning_rate": 7.265601291836955e-07, "loss": 0.001, "step": 331060 }, { "epoch": 79.5, "learning_rate": 7.257981873543318e-07, "loss": 0.001, "step": 331070 }, { "epoch": 79.5, "learning_rate": 7.250366423369181e-07, "loss": 0.0009, "step": 331080 }, { "epoch": 79.51, "learning_rate": 7.242754941375829e-07, "loss": 0.001, "step": 331090 }, { "epoch": 79.51, "learning_rate": 7.2351474276246e-07, "loss": 0.001, "step": 331100 }, { "epoch": 79.51, "learning_rate": 7.227543882176835e-07, "loss": 0.0009, "step": 331110 }, { "epoch": 79.51, "learning_rate": 7.219944305093595e-07, "loss": 0.001, "step": 331120 }, { "epoch": 79.51, "learning_rate": 7.212348696436222e-07, "loss": 0.0009, "step": 331130 }, { "epoch": 79.52, "learning_rate": 7.204757056265887e-07, "loss": 0.0017, "step": 331140 }, { "epoch": 79.52, "learning_rate": 7.197169384643599e-07, "loss": 0.0008, "step": 331150 }, { "epoch": 79.52, "learning_rate": 7.189585681630584e-07, "loss": 0.001, "step": 331160 }, { "epoch": 79.52, "learning_rate": 7.182005947287906e-07, "loss": 0.0014, "step": 331170 }, { "epoch": 79.53, "learning_rate": 7.174430181676517e-07, "loss": 0.001, "step": 331180 }, { "epoch": 79.53, "learning_rate": 7.166858384857478e-07, "loss": 0.001, "step": 331190 }, { "epoch": 79.53, "learning_rate": 7.159290556891796e-07, "loss": 0.0008, "step": 331200 }, { "epoch": 79.53, "learning_rate": 7.151726697840367e-07, "loss": 0.0009, "step": 331210 }, { "epoch": 79.54, "learning_rate": 7.144166807764142e-07, "loss": 0.0009, "step": 331220 }, { "epoch": 79.54, "learning_rate": 7.13661088672396e-07, "loss": 0.0011, "step": 331230 }, { "epoch": 79.54, "learning_rate": 7.129058934780719e-07, "loss": 0.0009, "step": 331240 }, { "epoch": 79.54, "learning_rate": 7.121510951995203e-07, "loss": 0.0011, "step": 331250 }, { "epoch": 79.54, "learning_rate": 7.113966938428196e-07, "loss": 0.0009, "step": 331260 }, { "epoch": 79.55, "learning_rate": 7.106426894140483e-07, "loss": 0.0009, "step": 331270 }, { "epoch": 79.55, "learning_rate": 7.098890819192738e-07, "loss": 0.001, "step": 331280 }, { "epoch": 79.55, "learning_rate": 7.09135871364569e-07, "loss": 0.0009, "step": 331290 }, { "epoch": 79.55, "learning_rate": 7.083830577559958e-07, "loss": 0.0008, "step": 331300 }, { "epoch": 79.56, "learning_rate": 7.076306410996214e-07, "loss": 0.0011, "step": 331310 }, { "epoch": 79.56, "learning_rate": 7.068786214015022e-07, "loss": 0.001, "step": 331320 }, { "epoch": 79.56, "learning_rate": 7.061269986676944e-07, "loss": 0.0018, "step": 331330 }, { "epoch": 79.56, "learning_rate": 7.053757729042543e-07, "loss": 0.0013, "step": 331340 }, { "epoch": 79.57, "learning_rate": 7.04624944117227e-07, "loss": 0.0047, "step": 331350 }, { "epoch": 79.57, "learning_rate": 7.038745123126578e-07, "loss": 0.001, "step": 331360 }, { "epoch": 79.57, "learning_rate": 7.031244774965918e-07, "loss": 0.0009, "step": 331370 }, { "epoch": 79.57, "learning_rate": 7.02374839675074e-07, "loss": 0.0009, "step": 331380 }, { "epoch": 79.57, "learning_rate": 7.016255988541387e-07, "loss": 0.001, "step": 331390 }, { "epoch": 79.58, "learning_rate": 7.008767550398144e-07, "loss": 0.0009, "step": 331400 }, { "epoch": 79.58, "learning_rate": 7.001283082381404e-07, "loss": 0.001, "step": 331410 }, { "epoch": 79.58, "learning_rate": 6.993802584551345e-07, "loss": 0.001, "step": 331420 }, { "epoch": 79.58, "learning_rate": 6.986326056968251e-07, "loss": 0.0009, "step": 331430 }, { "epoch": 79.59, "learning_rate": 6.978853499692406e-07, "loss": 0.0008, "step": 331440 }, { "epoch": 79.59, "learning_rate": 6.971384912783929e-07, "loss": 0.0009, "step": 331450 }, { "epoch": 79.59, "learning_rate": 6.963920296302883e-07, "loss": 0.0008, "step": 331460 }, { "epoch": 79.59, "learning_rate": 6.956459650309444e-07, "loss": 0.0009, "step": 331470 }, { "epoch": 79.59, "learning_rate": 6.949002974863783e-07, "loss": 0.0009, "step": 331480 }, { "epoch": 79.6, "learning_rate": 6.941550270025854e-07, "loss": 0.0012, "step": 331490 }, { "epoch": 79.6, "learning_rate": 6.934101535855609e-07, "loss": 0.0014, "step": 331500 }, { "epoch": 79.6, "learning_rate": 6.926656772413165e-07, "loss": 0.001, "step": 331510 }, { "epoch": 79.6, "learning_rate": 6.919215979758476e-07, "loss": 0.0009, "step": 331520 }, { "epoch": 79.61, "learning_rate": 6.911779157951382e-07, "loss": 0.0017, "step": 331530 }, { "epoch": 79.61, "learning_rate": 6.904346307051779e-07, "loss": 0.0008, "step": 331540 }, { "epoch": 79.61, "learning_rate": 6.896917427119564e-07, "loss": 0.001, "step": 331550 }, { "epoch": 79.61, "learning_rate": 6.88949251821458e-07, "loss": 0.001, "step": 331560 }, { "epoch": 79.62, "learning_rate": 6.882071580396499e-07, "loss": 0.0009, "step": 331570 }, { "epoch": 79.62, "learning_rate": 6.874654613725329e-07, "loss": 0.0009, "step": 331580 }, { "epoch": 79.62, "learning_rate": 6.867241618260523e-07, "loss": 0.0011, "step": 331590 }, { "epoch": 79.62, "learning_rate": 6.859832594061921e-07, "loss": 0.0008, "step": 331600 }, { "epoch": 79.62, "learning_rate": 6.852427541189199e-07, "loss": 0.001, "step": 331610 }, { "epoch": 79.63, "learning_rate": 6.845026459701975e-07, "loss": 0.001, "step": 331620 }, { "epoch": 79.63, "learning_rate": 6.837629349659813e-07, "loss": 0.001, "step": 331630 }, { "epoch": 79.63, "learning_rate": 6.830236211122276e-07, "loss": 0.0008, "step": 331640 }, { "epoch": 79.63, "learning_rate": 6.822847044148983e-07, "loss": 0.0009, "step": 331650 }, { "epoch": 79.64, "learning_rate": 6.815461848799387e-07, "loss": 0.0009, "step": 331660 }, { "epoch": 79.64, "learning_rate": 6.80808062513294e-07, "loss": 0.0019, "step": 331670 }, { "epoch": 79.64, "learning_rate": 6.800703373209094e-07, "loss": 0.001, "step": 331680 }, { "epoch": 79.64, "learning_rate": 6.793330093087303e-07, "loss": 0.0013, "step": 331690 }, { "epoch": 79.65, "learning_rate": 6.785960784826905e-07, "loss": 0.001, "step": 331700 }, { "epoch": 79.65, "learning_rate": 6.778595448487246e-07, "loss": 0.0009, "step": 331710 }, { "epoch": 79.65, "learning_rate": 6.77123408412772e-07, "loss": 0.001, "step": 331720 }, { "epoch": 79.65, "learning_rate": 6.763876691807502e-07, "loss": 0.0009, "step": 331730 }, { "epoch": 79.65, "learning_rate": 6.756523271585824e-07, "loss": 0.0008, "step": 331740 }, { "epoch": 79.66, "learning_rate": 6.749173823521971e-07, "loss": 0.0009, "step": 331750 }, { "epoch": 79.66, "learning_rate": 6.741828347675172e-07, "loss": 0.0008, "step": 331760 }, { "epoch": 79.66, "learning_rate": 6.734486844104493e-07, "loss": 0.0009, "step": 331770 }, { "epoch": 79.66, "learning_rate": 6.727149312869108e-07, "loss": 0.0013, "step": 331780 }, { "epoch": 79.67, "learning_rate": 6.719815754028081e-07, "loss": 0.0011, "step": 331790 }, { "epoch": 79.67, "learning_rate": 6.71248616764053e-07, "loss": 0.001, "step": 331800 }, { "epoch": 79.67, "learning_rate": 6.705160553765355e-07, "loss": 0.0008, "step": 331810 }, { "epoch": 79.67, "learning_rate": 6.697838912461674e-07, "loss": 0.001, "step": 331820 }, { "epoch": 79.67, "learning_rate": 6.690521243788384e-07, "loss": 0.0009, "step": 331830 }, { "epoch": 79.68, "learning_rate": 6.683207547804382e-07, "loss": 0.0009, "step": 331840 }, { "epoch": 79.68, "learning_rate": 6.675897824568677e-07, "loss": 0.0014, "step": 331850 }, { "epoch": 79.68, "learning_rate": 6.668592074140112e-07, "loss": 0.0008, "step": 331860 }, { "epoch": 79.68, "learning_rate": 6.661290296577416e-07, "loss": 0.0009, "step": 331870 }, { "epoch": 79.69, "learning_rate": 6.653992491939487e-07, "loss": 0.0009, "step": 331880 }, { "epoch": 79.69, "learning_rate": 6.646698660285055e-07, "loss": 0.0009, "step": 331890 }, { "epoch": 79.69, "learning_rate": 6.639408801672853e-07, "loss": 0.0011, "step": 331900 }, { "epoch": 79.69, "learning_rate": 6.63212291616161e-07, "loss": 0.0008, "step": 331910 }, { "epoch": 79.7, "learning_rate": 6.624841003810056e-07, "loss": 0.0009, "step": 331920 }, { "epoch": 79.7, "learning_rate": 6.617563064676701e-07, "loss": 0.001, "step": 331930 }, { "epoch": 79.7, "learning_rate": 6.610289098820277e-07, "loss": 0.0008, "step": 331940 }, { "epoch": 79.7, "learning_rate": 6.603019106299291e-07, "loss": 0.0009, "step": 331950 }, { "epoch": 79.7, "learning_rate": 6.595753087172308e-07, "loss": 0.001, "step": 331960 }, { "epoch": 79.71, "learning_rate": 6.588491041497835e-07, "loss": 0.001, "step": 331970 }, { "epoch": 79.71, "learning_rate": 6.581232969334328e-07, "loss": 0.0047, "step": 331980 }, { "epoch": 79.71, "learning_rate": 6.573978870740294e-07, "loss": 0.0008, "step": 331990 }, { "epoch": 79.71, "learning_rate": 6.566728745774186e-07, "loss": 0.0009, "step": 332000 }, { "epoch": 79.72, "learning_rate": 6.559482594494293e-07, "loss": 0.0009, "step": 332010 }, { "epoch": 79.72, "learning_rate": 6.55224041695901e-07, "loss": 0.0009, "step": 332020 }, { "epoch": 79.72, "learning_rate": 6.545002213226681e-07, "loss": 0.0009, "step": 332030 }, { "epoch": 79.72, "learning_rate": 6.537767983355536e-07, "loss": 0.0009, "step": 332040 }, { "epoch": 79.73, "learning_rate": 6.530537727403918e-07, "loss": 0.0008, "step": 332050 }, { "epoch": 79.73, "learning_rate": 6.523311445429947e-07, "loss": 0.0009, "step": 332060 }, { "epoch": 79.73, "learning_rate": 6.516089137491965e-07, "loss": 0.001, "step": 332070 }, { "epoch": 79.73, "learning_rate": 6.508870803647982e-07, "loss": 0.0009, "step": 332080 }, { "epoch": 79.73, "learning_rate": 6.501656443956173e-07, "loss": 0.0009, "step": 332090 }, { "epoch": 79.74, "learning_rate": 6.494446058474713e-07, "loss": 0.0009, "step": 332100 }, { "epoch": 79.74, "learning_rate": 6.487239647261612e-07, "loss": 0.0012, "step": 332110 }, { "epoch": 79.74, "learning_rate": 6.480037210374823e-07, "loss": 0.001, "step": 332120 }, { "epoch": 79.74, "learning_rate": 6.472838747872523e-07, "loss": 0.001, "step": 332130 }, { "epoch": 79.75, "learning_rate": 6.465644259812554e-07, "loss": 0.0008, "step": 332140 }, { "epoch": 79.75, "learning_rate": 6.458453746252868e-07, "loss": 0.001, "step": 332150 }, { "epoch": 79.75, "learning_rate": 6.451267207251422e-07, "loss": 0.0009, "step": 332160 }, { "epoch": 79.75, "learning_rate": 6.444084642866055e-07, "loss": 0.02, "step": 332170 }, { "epoch": 79.75, "learning_rate": 6.436906053154612e-07, "loss": 0.0009, "step": 332180 }, { "epoch": 79.76, "learning_rate": 6.429731438174879e-07, "loss": 0.001, "step": 332190 }, { "epoch": 79.76, "learning_rate": 6.4225607979847e-07, "loss": 0.0009, "step": 332200 }, { "epoch": 79.76, "learning_rate": 6.41539413264175e-07, "loss": 0.0009, "step": 332210 }, { "epoch": 79.76, "learning_rate": 6.40823144220376e-07, "loss": 0.0009, "step": 332220 }, { "epoch": 79.77, "learning_rate": 6.401072726728463e-07, "loss": 0.0008, "step": 332230 }, { "epoch": 79.77, "learning_rate": 6.393917986273479e-07, "loss": 0.0009, "step": 332240 }, { "epoch": 79.77, "learning_rate": 6.386767220896372e-07, "loss": 0.0009, "step": 332250 }, { "epoch": 79.77, "learning_rate": 6.37962043065482e-07, "loss": 0.001, "step": 332260 }, { "epoch": 79.78, "learning_rate": 6.372477615606332e-07, "loss": 0.0011, "step": 332270 }, { "epoch": 79.78, "learning_rate": 6.365338775808472e-07, "loss": 0.0012, "step": 332280 }, { "epoch": 79.78, "learning_rate": 6.358203911318583e-07, "loss": 0.001, "step": 332290 }, { "epoch": 79.78, "learning_rate": 6.351073022194287e-07, "loss": 0.0008, "step": 332300 }, { "epoch": 79.78, "learning_rate": 6.343946108492982e-07, "loss": 0.0009, "step": 332310 }, { "epoch": 79.79, "learning_rate": 6.336823170272011e-07, "loss": 0.0025, "step": 332320 }, { "epoch": 79.79, "learning_rate": 6.329704207588716e-07, "loss": 0.0009, "step": 332330 }, { "epoch": 79.79, "learning_rate": 6.322589220500496e-07, "loss": 0.0009, "step": 332340 }, { "epoch": 79.79, "learning_rate": 6.31547820906464e-07, "loss": 0.0011, "step": 332350 }, { "epoch": 79.8, "learning_rate": 6.308371173338378e-07, "loss": 0.0009, "step": 332360 }, { "epoch": 79.8, "learning_rate": 6.301268113378944e-07, "loss": 0.0014, "step": 332370 }, { "epoch": 79.8, "learning_rate": 6.294169029243624e-07, "loss": 0.0013, "step": 332380 }, { "epoch": 79.8, "learning_rate": 6.287073920989428e-07, "loss": 0.0008, "step": 332390 }, { "epoch": 79.81, "learning_rate": 6.279982788673645e-07, "loss": 0.001, "step": 332400 }, { "epoch": 79.81, "learning_rate": 6.272895632353281e-07, "loss": 0.001, "step": 332410 }, { "epoch": 79.81, "learning_rate": 6.265812452085518e-07, "loss": 0.0011, "step": 332420 }, { "epoch": 79.81, "learning_rate": 6.258733247927306e-07, "loss": 0.0008, "step": 332430 }, { "epoch": 79.81, "learning_rate": 6.251658019935658e-07, "loss": 0.0009, "step": 332440 }, { "epoch": 79.82, "learning_rate": 6.244586768167582e-07, "loss": 0.0013, "step": 332450 }, { "epoch": 79.82, "learning_rate": 6.237519492679978e-07, "loss": 0.0008, "step": 332460 }, { "epoch": 79.82, "learning_rate": 6.23045619352991e-07, "loss": 0.0011, "step": 332470 }, { "epoch": 79.82, "learning_rate": 6.223396870774056e-07, "loss": 0.001, "step": 332480 }, { "epoch": 79.83, "learning_rate": 6.216341524469372e-07, "loss": 0.001, "step": 332490 }, { "epoch": 79.83, "learning_rate": 6.209290154672642e-07, "loss": 0.0011, "step": 332500 }, { "epoch": 79.83, "learning_rate": 6.202242761440713e-07, "loss": 0.0009, "step": 332510 }, { "epoch": 79.83, "learning_rate": 6.195199344830316e-07, "loss": 0.0009, "step": 332520 }, { "epoch": 79.83, "learning_rate": 6.188159904898072e-07, "loss": 0.0011, "step": 332530 }, { "epoch": 79.84, "learning_rate": 6.181124441700825e-07, "loss": 0.002, "step": 332540 }, { "epoch": 79.84, "learning_rate": 6.174092955295085e-07, "loss": 0.0012, "step": 332550 }, { "epoch": 79.84, "learning_rate": 6.167065445737641e-07, "loss": 0.0012, "step": 332560 }, { "epoch": 79.84, "learning_rate": 6.160041913084947e-07, "loss": 0.001, "step": 332570 }, { "epoch": 79.85, "learning_rate": 6.153022357393623e-07, "loss": 0.0009, "step": 332580 }, { "epoch": 79.85, "learning_rate": 6.146006778720181e-07, "loss": 0.0009, "step": 332590 }, { "epoch": 79.85, "learning_rate": 6.138995177121076e-07, "loss": 0.0011, "step": 332600 }, { "epoch": 79.85, "learning_rate": 6.131987552652929e-07, "loss": 0.0008, "step": 332610 }, { "epoch": 79.86, "learning_rate": 6.124983905372028e-07, "loss": 0.0008, "step": 332620 }, { "epoch": 79.86, "learning_rate": 6.117984235334772e-07, "loss": 0.0009, "step": 332630 }, { "epoch": 79.86, "learning_rate": 6.110988542597617e-07, "loss": 0.0009, "step": 332640 }, { "epoch": 79.86, "learning_rate": 6.103996827216851e-07, "loss": 0.0008, "step": 332650 }, { "epoch": 79.86, "learning_rate": 6.097009089248762e-07, "loss": 0.0016, "step": 332660 }, { "epoch": 79.87, "learning_rate": 6.090025328749694e-07, "loss": 0.0008, "step": 332670 }, { "epoch": 79.87, "learning_rate": 6.083045545775823e-07, "loss": 0.0009, "step": 332680 }, { "epoch": 79.87, "learning_rate": 6.076069740383328e-07, "loss": 0.001, "step": 332690 }, { "epoch": 79.87, "learning_rate": 6.069097912628441e-07, "loss": 0.0009, "step": 332700 }, { "epoch": 79.88, "learning_rate": 6.062130062567395e-07, "loss": 0.0009, "step": 332710 }, { "epoch": 79.88, "learning_rate": 6.055166190256145e-07, "loss": 0.0009, "step": 332720 }, { "epoch": 79.88, "learning_rate": 6.048206295750814e-07, "loss": 0.0008, "step": 332730 }, { "epoch": 79.88, "learning_rate": 6.041250379107466e-07, "loss": 0.001, "step": 332740 }, { "epoch": 79.89, "learning_rate": 6.034298440382169e-07, "loss": 0.001, "step": 332750 }, { "epoch": 79.89, "learning_rate": 6.027350479630877e-07, "loss": 0.0009, "step": 332760 }, { "epoch": 79.89, "learning_rate": 6.020406496909436e-07, "loss": 0.0023, "step": 332770 }, { "epoch": 79.89, "learning_rate": 6.013466492273912e-07, "loss": 0.001, "step": 332780 }, { "epoch": 79.89, "learning_rate": 6.006530465780202e-07, "loss": 0.001, "step": 332790 }, { "epoch": 79.9, "learning_rate": 5.999598417484042e-07, "loss": 0.001, "step": 332800 }, { "epoch": 79.9, "learning_rate": 5.992670347441331e-07, "loss": 0.0031, "step": 332810 }, { "epoch": 79.9, "learning_rate": 5.985746255707803e-07, "loss": 0.0009, "step": 332820 }, { "epoch": 79.9, "learning_rate": 5.9788261423393e-07, "loss": 0.0009, "step": 332830 }, { "epoch": 79.91, "learning_rate": 5.971910007391501e-07, "loss": 0.0012, "step": 332840 }, { "epoch": 79.91, "learning_rate": 5.96499785092014e-07, "loss": 0.001, "step": 332850 }, { "epoch": 79.91, "learning_rate": 5.958089672980893e-07, "loss": 0.0013, "step": 332860 }, { "epoch": 79.91, "learning_rate": 5.951185473629272e-07, "loss": 0.0027, "step": 332870 }, { "epoch": 79.91, "learning_rate": 5.944285252921011e-07, "loss": 0.0008, "step": 332880 }, { "epoch": 79.92, "learning_rate": 5.93738901091162e-07, "loss": 0.001, "step": 332890 }, { "epoch": 79.92, "learning_rate": 5.930496747656611e-07, "loss": 0.001, "step": 332900 }, { "epoch": 79.92, "learning_rate": 5.92360846321155e-07, "loss": 0.001, "step": 332910 }, { "epoch": 79.92, "learning_rate": 5.916724157631893e-07, "loss": 0.0009, "step": 332920 }, { "epoch": 79.93, "learning_rate": 5.909843830973094e-07, "loss": 0.0014, "step": 332930 }, { "epoch": 79.93, "learning_rate": 5.9029674832905e-07, "loss": 0.0009, "step": 332940 }, { "epoch": 79.93, "learning_rate": 5.896095114639511e-07, "loss": 0.001, "step": 332950 }, { "epoch": 79.93, "learning_rate": 5.889226725075525e-07, "loss": 0.001, "step": 332960 }, { "epoch": 79.94, "learning_rate": 5.882362314653778e-07, "loss": 0.0009, "step": 332970 }, { "epoch": 79.94, "learning_rate": 5.875501883429557e-07, "loss": 0.0044, "step": 332980 }, { "epoch": 79.94, "learning_rate": 5.868645431458208e-07, "loss": 0.001, "step": 332990 }, { "epoch": 79.94, "learning_rate": 5.861792958794854e-07, "loss": 0.001, "step": 333000 }, { "epoch": 79.94, "learning_rate": 5.854944465494616e-07, "loss": 0.001, "step": 333010 }, { "epoch": 79.95, "learning_rate": 5.84809995161284e-07, "loss": 0.0009, "step": 333020 }, { "epoch": 79.95, "learning_rate": 5.841259417204481e-07, "loss": 0.0012, "step": 333030 }, { "epoch": 79.95, "learning_rate": 5.834422862324718e-07, "loss": 0.0011, "step": 333040 } ], "max_steps": 350080, "num_train_epochs": 80, "total_flos": 0.0, "trial_name": null, "trial_params": null }