{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 200.0, "global_step": 106182, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005650755082147852, "grad_norm": 2.5348994731903076, "learning_rate": 3.5781544256120527e-07, "loss": 6.771160888671875, "step": 20 }, { "epoch": 0.0011301510164295704, "grad_norm": 2.710658311843872, "learning_rate": 7.344632768361582e-07, "loss": 6.899335479736328, "step": 40 }, { "epoch": 0.0016952265246443555, "grad_norm": 3.642833709716797, "learning_rate": 1.1111111111111112e-06, "loss": 6.389015197753906, "step": 60 }, { "epoch": 0.002260302032859141, "grad_norm": 1.7288906574249268, "learning_rate": 1.487758945386064e-06, "loss": 6.72058334350586, "step": 80 }, { "epoch": 0.002825377541073926, "grad_norm": 2.6034772396087646, "learning_rate": 1.8644067796610171e-06, "loss": 6.788397216796875, "step": 100 }, { "epoch": 0.003390453049288711, "grad_norm": 4.211796760559082, "learning_rate": 2.2410546139359697e-06, "loss": 6.450605010986328, "step": 120 }, { "epoch": 0.003955528557503496, "grad_norm": 1.6516824960708618, "learning_rate": 2.617702448210923e-06, "loss": 6.290931701660156, "step": 140 }, { "epoch": 0.004520604065718282, "grad_norm": 2.9470319747924805, "learning_rate": 2.994350282485876e-06, "loss": 6.1667327880859375, "step": 160 }, { "epoch": 0.005085679573933067, "grad_norm": 4.560809135437012, "learning_rate": 3.370998116760829e-06, "loss": 6.25506362915039, "step": 180 }, { "epoch": 0.005650755082147852, "grad_norm": 2.6977131366729736, "learning_rate": 3.747645951035782e-06, "loss": 6.188862991333008, "step": 200 }, { "epoch": 0.0062158305903626376, "grad_norm": 1.961645483970642, "learning_rate": 4.124293785310734e-06, "loss": 6.0346923828125, "step": 220 }, { "epoch": 0.006780906098577422, "grad_norm": 4.568611145019531, "learning_rate": 4.5009416195856876e-06, "loss": 5.845339965820313, "step": 240 }, { "epoch": 0.007345981606792207, "grad_norm": 2.6742594242095947, "learning_rate": 4.877589453860641e-06, "loss": 6.141055297851563, "step": 260 }, { "epoch": 0.007911057115006993, "grad_norm": 4.060245037078857, "learning_rate": 5.254237288135593e-06, "loss": 6.006123352050781, "step": 280 }, { "epoch": 0.008476132623221779, "grad_norm": 2.6908962726593018, "learning_rate": 5.6308851224105465e-06, "loss": 5.51111946105957, "step": 300 }, { "epoch": 0.009041208131436563, "grad_norm": 3.6183221340179443, "learning_rate": 6.0075329566855e-06, "loss": 5.5268699645996096, "step": 320 }, { "epoch": 0.009606283639651348, "grad_norm": 4.2484893798828125, "learning_rate": 6.384180790960452e-06, "loss": 5.432608032226563, "step": 340 }, { "epoch": 0.010171359147866134, "grad_norm": 5.259164333343506, "learning_rate": 6.7608286252354045e-06, "loss": 4.913628387451172, "step": 360 }, { "epoch": 0.010736434656080918, "grad_norm": 5.480133533477783, "learning_rate": 7.137476459510359e-06, "loss": 4.758895492553711, "step": 380 }, { "epoch": 0.011301510164295704, "grad_norm": 2.874417304992676, "learning_rate": 7.514124293785312e-06, "loss": 4.842123031616211, "step": 400 }, { "epoch": 0.011866585672510489, "grad_norm": 4.560913562774658, "learning_rate": 7.890772128060264e-06, "loss": 4.649380493164062, "step": 420 }, { "epoch": 0.012431661180725275, "grad_norm": 3.4285426139831543, "learning_rate": 8.267419962335218e-06, "loss": 4.762957763671875, "step": 440 }, { "epoch": 0.01299673668894006, "grad_norm": 5.911031246185303, "learning_rate": 8.644067796610169e-06, "loss": 4.695363235473633, "step": 460 }, { "epoch": 0.013561812197154844, "grad_norm": 3.828498363494873, "learning_rate": 9.020715630885122e-06, "loss": 4.7244102478027346, "step": 480 }, { "epoch": 0.01412688770536963, "grad_norm": 4.166859149932861, "learning_rate": 9.397363465160076e-06, "loss": 4.481912612915039, "step": 500 }, { "epoch": 0.014691963213584415, "grad_norm": 3.163666009902954, "learning_rate": 9.774011299435029e-06, "loss": 4.499019622802734, "step": 520 }, { "epoch": 0.0152570387217992, "grad_norm": 3.8218350410461426, "learning_rate": 1.0150659133709982e-05, "loss": 4.4074150085449215, "step": 540 }, { "epoch": 0.015822114230013985, "grad_norm": 15.735069274902344, "learning_rate": 1.0527306967984935e-05, "loss": 4.315810775756836, "step": 560 }, { "epoch": 0.01638718973822877, "grad_norm": 7.921339988708496, "learning_rate": 1.0903954802259887e-05, "loss": 4.1778106689453125, "step": 580 }, { "epoch": 0.016952265246443558, "grad_norm": 6.871067523956299, "learning_rate": 1.128060263653484e-05, "loss": 3.988964080810547, "step": 600 }, { "epoch": 0.017517340754658342, "grad_norm": 13.242423057556152, "learning_rate": 1.1657250470809793e-05, "loss": 4.230078125, "step": 620 }, { "epoch": 0.018082416262873127, "grad_norm": 5.2831878662109375, "learning_rate": 1.2033898305084747e-05, "loss": 4.116972351074219, "step": 640 }, { "epoch": 0.01864749177108791, "grad_norm": 10.219537734985352, "learning_rate": 1.24105461393597e-05, "loss": 4.014706420898437, "step": 660 }, { "epoch": 0.019212567279302695, "grad_norm": 23.514415740966797, "learning_rate": 1.2787193973634653e-05, "loss": 4.076214981079102, "step": 680 }, { "epoch": 0.019777642787517483, "grad_norm": 6.436954975128174, "learning_rate": 1.3163841807909605e-05, "loss": 3.652445983886719, "step": 700 }, { "epoch": 0.020342718295732268, "grad_norm": 7.603453159332275, "learning_rate": 1.354048964218456e-05, "loss": 3.765607452392578, "step": 720 }, { "epoch": 0.020907793803947052, "grad_norm": 7.553692817687988, "learning_rate": 1.391713747645951e-05, "loss": 3.4925308227539062, "step": 740 }, { "epoch": 0.021472869312161837, "grad_norm": 7.251210689544678, "learning_rate": 1.4293785310734465e-05, "loss": 3.782305145263672, "step": 760 }, { "epoch": 0.022037944820376625, "grad_norm": 35.443756103515625, "learning_rate": 1.4670433145009416e-05, "loss": 3.4786941528320314, "step": 780 }, { "epoch": 0.02260302032859141, "grad_norm": 15.168000221252441, "learning_rate": 1.504708097928437e-05, "loss": 3.3081298828125, "step": 800 }, { "epoch": 0.023168095836806193, "grad_norm": 19.092775344848633, "learning_rate": 1.5423728813559323e-05, "loss": 3.412352752685547, "step": 820 }, { "epoch": 0.023733171345020978, "grad_norm": 15.211946487426758, "learning_rate": 1.5800376647834274e-05, "loss": 3.295152282714844, "step": 840 }, { "epoch": 0.024298246853235762, "grad_norm": 9.430453300476074, "learning_rate": 1.617702448210923e-05, "loss": 3.0562770843505858, "step": 860 }, { "epoch": 0.02486332236145055, "grad_norm": 9.709391593933105, "learning_rate": 1.655367231638418e-05, "loss": 3.1903926849365236, "step": 880 }, { "epoch": 0.025428397869665335, "grad_norm": 11.241543769836426, "learning_rate": 1.6930320150659136e-05, "loss": 3.0628828048706054, "step": 900 }, { "epoch": 0.02599347337788012, "grad_norm": 11.688015937805176, "learning_rate": 1.7306967984934087e-05, "loss": 3.1413501739501952, "step": 920 }, { "epoch": 0.026558548886094904, "grad_norm": 9.856255531311035, "learning_rate": 1.768361581920904e-05, "loss": 2.8844512939453124, "step": 940 }, { "epoch": 0.027123624394309688, "grad_norm": 12.113326072692871, "learning_rate": 1.8060263653483994e-05, "loss": 2.982631301879883, "step": 960 }, { "epoch": 0.027688699902524476, "grad_norm": 11.251745223999023, "learning_rate": 1.8436911487758945e-05, "loss": 2.833060455322266, "step": 980 }, { "epoch": 0.02825377541073926, "grad_norm": 23.89540672302246, "learning_rate": 1.88135593220339e-05, "loss": 2.973756790161133, "step": 1000 }, { "epoch": 0.028818850918954045, "grad_norm": 48.1312141418457, "learning_rate": 1.9190207156308852e-05, "loss": 2.9845380783081055, "step": 1020 }, { "epoch": 0.02938392642716883, "grad_norm": 35.40742874145508, "learning_rate": 1.9566854990583807e-05, "loss": 2.871182441711426, "step": 1040 }, { "epoch": 0.029949001935383617, "grad_norm": 9.615740776062012, "learning_rate": 1.9943502824858758e-05, "loss": 2.7468084335327148, "step": 1060 }, { "epoch": 0.0305140774435984, "grad_norm": 15.22346305847168, "learning_rate": 2.032015065913371e-05, "loss": 3.0032825469970703, "step": 1080 }, { "epoch": 0.031079152951813186, "grad_norm": 15.467687606811523, "learning_rate": 2.0696798493408665e-05, "loss": 2.9469884872436523, "step": 1100 }, { "epoch": 0.03164422846002797, "grad_norm": 15.997018814086914, "learning_rate": 2.1073446327683616e-05, "loss": 2.8002357482910156, "step": 1120 }, { "epoch": 0.03220930396824276, "grad_norm": 12.600042343139648, "learning_rate": 2.145009416195857e-05, "loss": 2.607904243469238, "step": 1140 }, { "epoch": 0.03277437947645754, "grad_norm": 10.291247367858887, "learning_rate": 2.1826741996233523e-05, "loss": 2.8464759826660155, "step": 1160 }, { "epoch": 0.03333945498467233, "grad_norm": 18.6491641998291, "learning_rate": 2.2203389830508474e-05, "loss": 2.6195499420166017, "step": 1180 }, { "epoch": 0.033904530492887115, "grad_norm": 12.737696647644043, "learning_rate": 2.258003766478343e-05, "loss": 2.678802490234375, "step": 1200 }, { "epoch": 0.034469606001101896, "grad_norm": 10.604427337646484, "learning_rate": 2.295668549905838e-05, "loss": 2.671494483947754, "step": 1220 }, { "epoch": 0.035034681509316684, "grad_norm": 14.397049903869629, "learning_rate": 2.3333333333333336e-05, "loss": 2.5984167098999023, "step": 1240 }, { "epoch": 0.035599757017531465, "grad_norm": 22.953359603881836, "learning_rate": 2.3709981167608287e-05, "loss": 2.5420406341552733, "step": 1260 }, { "epoch": 0.03616483252574625, "grad_norm": 11.855541229248047, "learning_rate": 2.408662900188324e-05, "loss": 2.5206804275512695, "step": 1280 }, { "epoch": 0.03672990803396104, "grad_norm": 19.627016067504883, "learning_rate": 2.4463276836158194e-05, "loss": 2.6552150726318358, "step": 1300 }, { "epoch": 0.03729498354217582, "grad_norm": 12.305405616760254, "learning_rate": 2.4839924670433145e-05, "loss": 2.743071746826172, "step": 1320 }, { "epoch": 0.03786005905039061, "grad_norm": 70.56048583984375, "learning_rate": 2.5216572504708097e-05, "loss": 2.520913505554199, "step": 1340 }, { "epoch": 0.03842513455860539, "grad_norm": 9.740160942077637, "learning_rate": 2.5593220338983055e-05, "loss": 2.6588504791259764, "step": 1360 }, { "epoch": 0.03899021006682018, "grad_norm": 6.7531867027282715, "learning_rate": 2.5969868173258003e-05, "loss": 2.518979072570801, "step": 1380 }, { "epoch": 0.03955528557503497, "grad_norm": 12.29990291595459, "learning_rate": 2.6346516007532955e-05, "loss": 2.485004997253418, "step": 1400 }, { "epoch": 0.04012036108324975, "grad_norm": 10.546372413635254, "learning_rate": 2.6723163841807913e-05, "loss": 2.5462961196899414, "step": 1420 }, { "epoch": 0.040685436591464536, "grad_norm": 9.226950645446777, "learning_rate": 2.7099811676082865e-05, "loss": 2.450338935852051, "step": 1440 }, { "epoch": 0.041250512099679316, "grad_norm": 15.990116119384766, "learning_rate": 2.7476459510357817e-05, "loss": 2.4865875244140625, "step": 1460 }, { "epoch": 0.041815587607894104, "grad_norm": 23.294763565063477, "learning_rate": 2.7853107344632768e-05, "loss": 2.5164947509765625, "step": 1480 }, { "epoch": 0.04238066311610889, "grad_norm": 12.847193717956543, "learning_rate": 2.8229755178907723e-05, "loss": 2.4457075119018556, "step": 1500 }, { "epoch": 0.04294573862432367, "grad_norm": 84.27172088623047, "learning_rate": 2.8606403013182675e-05, "loss": 2.413028907775879, "step": 1520 }, { "epoch": 0.04351081413253846, "grad_norm": 7.135191917419434, "learning_rate": 2.8983050847457626e-05, "loss": 2.393525314331055, "step": 1540 }, { "epoch": 0.04407588964075325, "grad_norm": 35.462921142578125, "learning_rate": 2.9359698681732584e-05, "loss": 2.5715663909912108, "step": 1560 }, { "epoch": 0.04464096514896803, "grad_norm": 13.541833877563477, "learning_rate": 2.9736346516007536e-05, "loss": 2.451706123352051, "step": 1580 }, { "epoch": 0.04520604065718282, "grad_norm": 7.69377326965332, "learning_rate": 3.0112994350282488e-05, "loss": 2.4393217086791994, "step": 1600 }, { "epoch": 0.0457711161653976, "grad_norm": 27.013948440551758, "learning_rate": 3.048964218455744e-05, "loss": 2.3585893630981447, "step": 1620 }, { "epoch": 0.04633619167361239, "grad_norm": 8.354761123657227, "learning_rate": 3.0866290018832394e-05, "loss": 2.4374061584472657, "step": 1640 }, { "epoch": 0.046901267181827175, "grad_norm": 8.501105308532715, "learning_rate": 3.1242937853107346e-05, "loss": 2.448665428161621, "step": 1660 }, { "epoch": 0.047466342690041956, "grad_norm": 8.308324813842773, "learning_rate": 3.16195856873823e-05, "loss": 2.265692138671875, "step": 1680 }, { "epoch": 0.048031418198256744, "grad_norm": 5.6145782470703125, "learning_rate": 3.1996233521657256e-05, "loss": 2.457777976989746, "step": 1700 }, { "epoch": 0.048596493706471525, "grad_norm": 11.986368179321289, "learning_rate": 3.237288135593221e-05, "loss": 2.1881938934326173, "step": 1720 }, { "epoch": 0.04916156921468631, "grad_norm": 9.634145736694336, "learning_rate": 3.274952919020716e-05, "loss": 2.4696332931518556, "step": 1740 }, { "epoch": 0.0497266447229011, "grad_norm": 6.8141937255859375, "learning_rate": 3.312617702448211e-05, "loss": 2.292523956298828, "step": 1760 }, { "epoch": 0.05029172023111588, "grad_norm": 6.704174518585205, "learning_rate": 3.350282485875706e-05, "loss": 2.2688667297363283, "step": 1780 }, { "epoch": 0.05085679573933067, "grad_norm": 8.178789138793945, "learning_rate": 3.387947269303201e-05, "loss": 2.2400474548339844, "step": 1800 }, { "epoch": 0.05142187124754545, "grad_norm": 9.825295448303223, "learning_rate": 3.4256120527306965e-05, "loss": 2.2677932739257813, "step": 1820 }, { "epoch": 0.05198694675576024, "grad_norm": 12.513734817504883, "learning_rate": 3.463276836158192e-05, "loss": 2.276126480102539, "step": 1840 }, { "epoch": 0.052552022263975026, "grad_norm": 10.533915519714355, "learning_rate": 3.5009416195856875e-05, "loss": 2.377655601501465, "step": 1860 }, { "epoch": 0.05311709777218981, "grad_norm": 7.917450428009033, "learning_rate": 3.5386064030131826e-05, "loss": 2.222239112854004, "step": 1880 }, { "epoch": 0.053682173280404595, "grad_norm": 5.9128007888793945, "learning_rate": 3.5762711864406785e-05, "loss": 2.418479156494141, "step": 1900 }, { "epoch": 0.054247248788619376, "grad_norm": 16.11314582824707, "learning_rate": 3.6139359698681736e-05, "loss": 2.321010780334473, "step": 1920 }, { "epoch": 0.054812324296834164, "grad_norm": 11.440580368041992, "learning_rate": 3.651600753295669e-05, "loss": 2.199978828430176, "step": 1940 }, { "epoch": 0.05537739980504895, "grad_norm": 8.03387451171875, "learning_rate": 3.689265536723164e-05, "loss": 2.280604934692383, "step": 1960 }, { "epoch": 0.05594247531326373, "grad_norm": 7.684676170349121, "learning_rate": 3.72693032015066e-05, "loss": 2.42786865234375, "step": 1980 }, { "epoch": 0.05650755082147852, "grad_norm": 9.443155288696289, "learning_rate": 3.764595103578155e-05, "loss": 2.2754934310913084, "step": 2000 }, { "epoch": 0.05707262632969331, "grad_norm": 8.508720397949219, "learning_rate": 3.8022598870056494e-05, "loss": 2.344216728210449, "step": 2020 }, { "epoch": 0.05763770183790809, "grad_norm": 7.905667304992676, "learning_rate": 3.839924670433145e-05, "loss": 2.1292818069458006, "step": 2040 }, { "epoch": 0.05820277734612288, "grad_norm": 7.576245307922363, "learning_rate": 3.8775894538606404e-05, "loss": 2.1796987533569334, "step": 2060 }, { "epoch": 0.05876785285433766, "grad_norm": 6.848289489746094, "learning_rate": 3.9152542372881355e-05, "loss": 2.144194412231445, "step": 2080 }, { "epoch": 0.059332928362552446, "grad_norm": 6.793764591217041, "learning_rate": 3.952919020715631e-05, "loss": 2.1435800552368165, "step": 2100 }, { "epoch": 0.059898003870767234, "grad_norm": 7.349837779998779, "learning_rate": 3.9905838041431265e-05, "loss": 2.413008689880371, "step": 2120 }, { "epoch": 0.060463079378982015, "grad_norm": 6.937588214874268, "learning_rate": 4.028248587570622e-05, "loss": 2.088386344909668, "step": 2140 }, { "epoch": 0.0610281548871968, "grad_norm": 9.590886116027832, "learning_rate": 4.065913370998117e-05, "loss": 2.236486625671387, "step": 2160 }, { "epoch": 0.061593230395411584, "grad_norm": 7.426961898803711, "learning_rate": 4.103578154425613e-05, "loss": 2.1759605407714844, "step": 2180 }, { "epoch": 0.06215830590362637, "grad_norm": 23.767013549804688, "learning_rate": 4.141242937853108e-05, "loss": 2.1913335800170897, "step": 2200 }, { "epoch": 0.06272338141184115, "grad_norm": 10.894024848937988, "learning_rate": 4.178907721280603e-05, "loss": 2.113474655151367, "step": 2220 }, { "epoch": 0.06328845692005594, "grad_norm": 7.4665727615356445, "learning_rate": 4.216572504708098e-05, "loss": 2.1279882431030273, "step": 2240 }, { "epoch": 0.06385353242827073, "grad_norm": 8.973069190979004, "learning_rate": 4.254237288135593e-05, "loss": 2.2613546371459963, "step": 2260 }, { "epoch": 0.06441860793648552, "grad_norm": 6.026763439178467, "learning_rate": 4.2919020715630885e-05, "loss": 2.2732559204101563, "step": 2280 }, { "epoch": 0.0649836834447003, "grad_norm": 5.70259952545166, "learning_rate": 4.3295668549905836e-05, "loss": 2.24715518951416, "step": 2300 }, { "epoch": 0.06554875895291508, "grad_norm": 10.004762649536133, "learning_rate": 4.3672316384180795e-05, "loss": 2.041566276550293, "step": 2320 }, { "epoch": 0.06611383446112987, "grad_norm": 4.231626510620117, "learning_rate": 4.4048964218455746e-05, "loss": 2.126857948303223, "step": 2340 }, { "epoch": 0.06667890996934465, "grad_norm": 5.539495468139648, "learning_rate": 4.44256120527307e-05, "loss": 2.133513641357422, "step": 2360 }, { "epoch": 0.06724398547755944, "grad_norm": 5.262454032897949, "learning_rate": 4.4802259887005656e-05, "loss": 2.270960235595703, "step": 2380 }, { "epoch": 0.06780906098577423, "grad_norm": 9.011143684387207, "learning_rate": 4.517890772128061e-05, "loss": 2.3362848281860353, "step": 2400 }, { "epoch": 0.068374136493989, "grad_norm": 12.048408508300781, "learning_rate": 4.555555555555556e-05, "loss": 2.108991241455078, "step": 2420 }, { "epoch": 0.06893921200220379, "grad_norm": 10.741975784301758, "learning_rate": 4.593220338983051e-05, "loss": 2.298171806335449, "step": 2440 }, { "epoch": 0.06950428751041858, "grad_norm": 4.850519180297852, "learning_rate": 4.630885122410546e-05, "loss": 2.107274627685547, "step": 2460 }, { "epoch": 0.07006936301863337, "grad_norm": 5.743119239807129, "learning_rate": 4.6685499058380414e-05, "loss": 2.202987289428711, "step": 2480 }, { "epoch": 0.07063443852684816, "grad_norm": 8.169608116149902, "learning_rate": 4.7062146892655365e-05, "loss": 2.1021163940429686, "step": 2500 }, { "epoch": 0.07119951403506293, "grad_norm": 6.864205837249756, "learning_rate": 4.7438794726930324e-05, "loss": 2.222420883178711, "step": 2520 }, { "epoch": 0.07176458954327772, "grad_norm": 4.863960266113281, "learning_rate": 4.7815442561205275e-05, "loss": 2.08400821685791, "step": 2540 }, { "epoch": 0.0723296650514925, "grad_norm": 6.309634208679199, "learning_rate": 4.819209039548023e-05, "loss": 1.9897686004638673, "step": 2560 }, { "epoch": 0.0728947405597073, "grad_norm": 3.6103248596191406, "learning_rate": 4.856873822975518e-05, "loss": 2.118903160095215, "step": 2580 }, { "epoch": 0.07345981606792208, "grad_norm": 6.141952037811279, "learning_rate": 4.894538606403014e-05, "loss": 2.0537273406982424, "step": 2600 }, { "epoch": 0.07402489157613686, "grad_norm": 6.1183247566223145, "learning_rate": 4.932203389830509e-05, "loss": 1.9865335464477538, "step": 2620 }, { "epoch": 0.07458996708435164, "grad_norm": 8.652756690979004, "learning_rate": 4.969868173258004e-05, "loss": 2.1147907257080076, "step": 2640 }, { "epoch": 0.07515504259256643, "grad_norm": 5.449613094329834, "learning_rate": 5.007532956685499e-05, "loss": 2.136873245239258, "step": 2660 }, { "epoch": 0.07572011810078122, "grad_norm": 8.185656547546387, "learning_rate": 5.045197740112994e-05, "loss": 2.1827388763427735, "step": 2680 }, { "epoch": 0.07628519360899601, "grad_norm": 7.5593180656433105, "learning_rate": 5.08286252354049e-05, "loss": 2.1354360580444336, "step": 2700 }, { "epoch": 0.07685026911721078, "grad_norm": 5.740236282348633, "learning_rate": 5.1205273069679846e-05, "loss": 2.1773427963256835, "step": 2720 }, { "epoch": 0.07741534462542557, "grad_norm": 6.934750556945801, "learning_rate": 5.1581920903954804e-05, "loss": 2.0418153762817384, "step": 2740 }, { "epoch": 0.07798042013364036, "grad_norm": 5.030130386352539, "learning_rate": 5.195856873822976e-05, "loss": 1.9715879440307618, "step": 2760 }, { "epoch": 0.07854549564185515, "grad_norm": 7.768702030181885, "learning_rate": 5.233521657250471e-05, "loss": 2.051305961608887, "step": 2780 }, { "epoch": 0.07911057115006993, "grad_norm": 6.015239715576172, "learning_rate": 5.2711864406779666e-05, "loss": 2.0351964950561525, "step": 2800 }, { "epoch": 0.07967564665828471, "grad_norm": 9.2662935256958, "learning_rate": 5.308851224105461e-05, "loss": 2.0389114379882813, "step": 2820 }, { "epoch": 0.0802407221664995, "grad_norm": 5.8817877769470215, "learning_rate": 5.346516007532957e-05, "loss": 2.0070566177368163, "step": 2840 }, { "epoch": 0.08080579767471428, "grad_norm": 4.711618900299072, "learning_rate": 5.384180790960453e-05, "loss": 1.9912302017211914, "step": 2860 }, { "epoch": 0.08137087318292907, "grad_norm": 5.703268051147461, "learning_rate": 5.421845574387947e-05, "loss": 2.064822959899902, "step": 2880 }, { "epoch": 0.08193594869114386, "grad_norm": 4.444399356842041, "learning_rate": 5.459510357815443e-05, "loss": 1.9847446441650392, "step": 2900 }, { "epoch": 0.08250102419935863, "grad_norm": 7.735978603363037, "learning_rate": 5.497175141242938e-05, "loss": 2.084360694885254, "step": 2920 }, { "epoch": 0.08306609970757342, "grad_norm": 5.43013334274292, "learning_rate": 5.534839924670433e-05, "loss": 2.0766372680664062, "step": 2940 }, { "epoch": 0.08363117521578821, "grad_norm": 8.789827346801758, "learning_rate": 5.5725047080979285e-05, "loss": 2.0992902755737304, "step": 2960 }, { "epoch": 0.084196250724003, "grad_norm": 6.058624744415283, "learning_rate": 5.6101694915254243e-05, "loss": 2.181283187866211, "step": 2980 }, { "epoch": 0.08476132623221778, "grad_norm": 6.472544193267822, "learning_rate": 5.647834274952919e-05, "loss": 2.147643280029297, "step": 3000 }, { "epoch": 0.08532640174043256, "grad_norm": 5.873350620269775, "learning_rate": 5.6854990583804147e-05, "loss": 2.011431121826172, "step": 3020 }, { "epoch": 0.08589147724864735, "grad_norm": 5.975162506103516, "learning_rate": 5.7231638418079105e-05, "loss": 1.9567214965820312, "step": 3040 }, { "epoch": 0.08645655275686213, "grad_norm": 6.757689476013184, "learning_rate": 5.760828625235405e-05, "loss": 2.096600341796875, "step": 3060 }, { "epoch": 0.08702162826507692, "grad_norm": 4.705783843994141, "learning_rate": 5.798493408662901e-05, "loss": 2.027924728393555, "step": 3080 }, { "epoch": 0.08758670377329171, "grad_norm": 3.6568050384521484, "learning_rate": 5.836158192090396e-05, "loss": 2.0183942794799803, "step": 3100 }, { "epoch": 0.0881517792815065, "grad_norm": 4.490758419036865, "learning_rate": 5.873822975517891e-05, "loss": 2.007257080078125, "step": 3120 }, { "epoch": 0.08871685478972127, "grad_norm": 6.200980186462402, "learning_rate": 5.911487758945386e-05, "loss": 2.2622964859008787, "step": 3140 }, { "epoch": 0.08928193029793606, "grad_norm": 5.600936412811279, "learning_rate": 5.9491525423728814e-05, "loss": 1.9009244918823243, "step": 3160 }, { "epoch": 0.08984700580615085, "grad_norm": 4.371004104614258, "learning_rate": 5.9868173258003766e-05, "loss": 2.104210090637207, "step": 3180 }, { "epoch": 0.09041208131436564, "grad_norm": 3.6765873432159424, "learning_rate": 6.0244821092278724e-05, "loss": 1.9316190719604491, "step": 3200 }, { "epoch": 0.09097715682258042, "grad_norm": 5.225037574768066, "learning_rate": 6.062146892655367e-05, "loss": 2.1051021575927735, "step": 3220 }, { "epoch": 0.0915422323307952, "grad_norm": 8.372456550598145, "learning_rate": 6.099811676082863e-05, "loss": 2.0639501571655274, "step": 3240 }, { "epoch": 0.09210730783900999, "grad_norm": 5.947038650512695, "learning_rate": 6.137476459510358e-05, "loss": 1.9681930541992188, "step": 3260 }, { "epoch": 0.09267238334722477, "grad_norm": 4.6870880126953125, "learning_rate": 6.175141242937853e-05, "loss": 1.9360456466674805, "step": 3280 }, { "epoch": 0.09323745885543956, "grad_norm": 4.321720600128174, "learning_rate": 6.212806026365348e-05, "loss": 2.0432321548461916, "step": 3300 }, { "epoch": 0.09380253436365435, "grad_norm": 6.564341068267822, "learning_rate": 6.250470809792845e-05, "loss": 2.0804996490478516, "step": 3320 }, { "epoch": 0.09436760987186912, "grad_norm": 3.54832124710083, "learning_rate": 6.288135593220339e-05, "loss": 1.8863061904907226, "step": 3340 }, { "epoch": 0.09493268538008391, "grad_norm": 6.095017910003662, "learning_rate": 6.325800376647835e-05, "loss": 2.096742630004883, "step": 3360 }, { "epoch": 0.0954977608882987, "grad_norm": 5.616430759429932, "learning_rate": 6.36346516007533e-05, "loss": 2.0388221740722656, "step": 3380 }, { "epoch": 0.09606283639651349, "grad_norm": 7.578696250915527, "learning_rate": 6.401129943502825e-05, "loss": 2.0521095275878904, "step": 3400 }, { "epoch": 0.09662791190472828, "grad_norm": 5.580594062805176, "learning_rate": 6.43879472693032e-05, "loss": 1.8615259170532226, "step": 3420 }, { "epoch": 0.09719298741294305, "grad_norm": 9.740531921386719, "learning_rate": 6.476459510357816e-05, "loss": 1.8675617218017577, "step": 3440 }, { "epoch": 0.09775806292115784, "grad_norm": 8.095703125, "learning_rate": 6.514124293785311e-05, "loss": 1.9741518020629882, "step": 3460 }, { "epoch": 0.09832313842937263, "grad_norm": 4.4668049812316895, "learning_rate": 6.551789077212806e-05, "loss": 1.920663833618164, "step": 3480 }, { "epoch": 0.09888821393758741, "grad_norm": 4.469295024871826, "learning_rate": 6.589453860640301e-05, "loss": 1.9629404067993164, "step": 3500 }, { "epoch": 0.0994532894458022, "grad_norm": 4.638205528259277, "learning_rate": 6.627118644067796e-05, "loss": 1.9741813659667968, "step": 3520 }, { "epoch": 0.10001836495401698, "grad_norm": 2.7434542179107666, "learning_rate": 6.664783427495293e-05, "loss": 1.9064939498901368, "step": 3540 }, { "epoch": 0.10058344046223176, "grad_norm": 4.171450614929199, "learning_rate": 6.702448210922787e-05, "loss": 1.9099546432495118, "step": 3560 }, { "epoch": 0.10114851597044655, "grad_norm": 3.5381393432617188, "learning_rate": 6.740112994350283e-05, "loss": 1.9966075897216797, "step": 3580 }, { "epoch": 0.10171359147866134, "grad_norm": 4.676222801208496, "learning_rate": 6.777777777777778e-05, "loss": 1.9074153900146484, "step": 3600 }, { "epoch": 0.10227866698687613, "grad_norm": 5.618529796600342, "learning_rate": 6.815442561205273e-05, "loss": 1.979163932800293, "step": 3620 }, { "epoch": 0.1028437424950909, "grad_norm": 4.353571891784668, "learning_rate": 6.853107344632769e-05, "loss": 1.906976318359375, "step": 3640 }, { "epoch": 0.10340881800330569, "grad_norm": 4.45463228225708, "learning_rate": 6.890772128060265e-05, "loss": 1.9817983627319335, "step": 3660 }, { "epoch": 0.10397389351152048, "grad_norm": 3.316889524459839, "learning_rate": 6.928436911487759e-05, "loss": 1.9464332580566406, "step": 3680 }, { "epoch": 0.10453896901973526, "grad_norm": 8.190747261047363, "learning_rate": 6.966101694915254e-05, "loss": 2.0487335205078123, "step": 3700 }, { "epoch": 0.10510404452795005, "grad_norm": 5.397557735443115, "learning_rate": 7.00376647834275e-05, "loss": 1.90808162689209, "step": 3720 }, { "epoch": 0.10566912003616483, "grad_norm": 4.314833164215088, "learning_rate": 7.041431261770244e-05, "loss": 1.8177675247192382, "step": 3740 }, { "epoch": 0.10623419554437961, "grad_norm": 4.32835578918457, "learning_rate": 7.079096045197741e-05, "loss": 2.114674949645996, "step": 3760 }, { "epoch": 0.1067992710525944, "grad_norm": 4.071811199188232, "learning_rate": 7.116760828625236e-05, "loss": 1.9522823333740233, "step": 3780 }, { "epoch": 0.10736434656080919, "grad_norm": 5.726691246032715, "learning_rate": 7.154425612052731e-05, "loss": 1.8772392272949219, "step": 3800 }, { "epoch": 0.10792942206902398, "grad_norm": 3.885040760040283, "learning_rate": 7.192090395480226e-05, "loss": 1.8595453262329102, "step": 3820 }, { "epoch": 0.10849449757723875, "grad_norm": 4.370023250579834, "learning_rate": 7.229755178907721e-05, "loss": 1.9419153213500977, "step": 3840 }, { "epoch": 0.10905957308545354, "grad_norm": 3.5817601680755615, "learning_rate": 7.267419962335217e-05, "loss": 2.0182563781738283, "step": 3860 }, { "epoch": 0.10962464859366833, "grad_norm": 17.77394676208496, "learning_rate": 7.305084745762713e-05, "loss": 1.9741798400878907, "step": 3880 }, { "epoch": 0.11018972410188312, "grad_norm": 2.4996237754821777, "learning_rate": 7.342749529190207e-05, "loss": 1.9621583938598632, "step": 3900 }, { "epoch": 0.1107547996100979, "grad_norm": 4.026330471038818, "learning_rate": 7.380414312617703e-05, "loss": 2.0365888595581056, "step": 3920 }, { "epoch": 0.11131987511831268, "grad_norm": 4.1621904373168945, "learning_rate": 7.418079096045199e-05, "loss": 2.012761878967285, "step": 3940 }, { "epoch": 0.11188495062652747, "grad_norm": 3.708510398864746, "learning_rate": 7.455743879472692e-05, "loss": 1.9612436294555664, "step": 3960 }, { "epoch": 0.11245002613474225, "grad_norm": 4.811985492706299, "learning_rate": 7.493408662900189e-05, "loss": 1.934931755065918, "step": 3980 }, { "epoch": 0.11301510164295704, "grad_norm": 5.438121795654297, "learning_rate": 7.531073446327684e-05, "loss": 1.9472091674804688, "step": 4000 }, { "epoch": 0.11358017715117183, "grad_norm": 4.534512519836426, "learning_rate": 7.568738229755179e-05, "loss": 1.8663358688354492, "step": 4020 }, { "epoch": 0.11414525265938662, "grad_norm": 4.073400497436523, "learning_rate": 7.606403013182674e-05, "loss": 2.064264488220215, "step": 4040 }, { "epoch": 0.11471032816760139, "grad_norm": 4.093326568603516, "learning_rate": 7.644067796610171e-05, "loss": 1.7538349151611328, "step": 4060 }, { "epoch": 0.11527540367581618, "grad_norm": 3.118818521499634, "learning_rate": 7.681732580037665e-05, "loss": 1.88787784576416, "step": 4080 }, { "epoch": 0.11584047918403097, "grad_norm": 4.602313041687012, "learning_rate": 7.719397363465161e-05, "loss": 1.765399169921875, "step": 4100 }, { "epoch": 0.11640555469224576, "grad_norm": 2.6856415271759033, "learning_rate": 7.757062146892655e-05, "loss": 1.7908483505249024, "step": 4120 }, { "epoch": 0.11697063020046054, "grad_norm": 3.2676968574523926, "learning_rate": 7.794726930320152e-05, "loss": 1.7829973220825195, "step": 4140 }, { "epoch": 0.11753570570867532, "grad_norm": 3.413709878921509, "learning_rate": 7.832391713747647e-05, "loss": 1.9091621398925782, "step": 4160 }, { "epoch": 0.1181007812168901, "grad_norm": 4.0047407150268555, "learning_rate": 7.870056497175142e-05, "loss": 1.8490144729614257, "step": 4180 }, { "epoch": 0.11866585672510489, "grad_norm": 3.5628678798675537, "learning_rate": 7.907721280602637e-05, "loss": 1.8700313568115234, "step": 4200 }, { "epoch": 0.11923093223331968, "grad_norm": 4.08143949508667, "learning_rate": 7.945386064030132e-05, "loss": 1.9351333618164062, "step": 4220 }, { "epoch": 0.11979600774153447, "grad_norm": 28.188674926757812, "learning_rate": 7.983050847457627e-05, "loss": 1.820303726196289, "step": 4240 }, { "epoch": 0.12036108324974924, "grad_norm": 7.127738952636719, "learning_rate": 8.020715630885122e-05, "loss": 1.7369560241699218, "step": 4260 }, { "epoch": 0.12092615875796403, "grad_norm": 3.724578619003296, "learning_rate": 8.058380414312619e-05, "loss": 1.838450813293457, "step": 4280 }, { "epoch": 0.12149123426617882, "grad_norm": 4.5588154792785645, "learning_rate": 8.096045197740113e-05, "loss": 1.887596893310547, "step": 4300 }, { "epoch": 0.1220563097743936, "grad_norm": 3.9761126041412354, "learning_rate": 8.133709981167609e-05, "loss": 1.815549087524414, "step": 4320 }, { "epoch": 0.1226213852826084, "grad_norm": 4.427428245544434, "learning_rate": 8.171374764595104e-05, "loss": 1.855613899230957, "step": 4340 }, { "epoch": 0.12318646079082317, "grad_norm": 2.857879400253296, "learning_rate": 8.2090395480226e-05, "loss": 1.8386844635009765, "step": 4360 }, { "epoch": 0.12375153629903796, "grad_norm": 2.5971412658691406, "learning_rate": 8.246704331450095e-05, "loss": 1.7507667541503906, "step": 4380 }, { "epoch": 0.12431661180725274, "grad_norm": 5.31064510345459, "learning_rate": 8.28436911487759e-05, "loss": 1.9002836227416993, "step": 4400 }, { "epoch": 0.12488168731546753, "grad_norm": 3.9003968238830566, "learning_rate": 8.322033898305085e-05, "loss": 1.797281265258789, "step": 4420 }, { "epoch": 0.1254467628236823, "grad_norm": 3.9475066661834717, "learning_rate": 8.35969868173258e-05, "loss": 1.7964210510253906, "step": 4440 }, { "epoch": 0.1260118383318971, "grad_norm": 4.653626918792725, "learning_rate": 8.397363465160075e-05, "loss": 1.8716123580932618, "step": 4460 }, { "epoch": 0.12657691384011188, "grad_norm": 4.7867045402526855, "learning_rate": 8.43502824858757e-05, "loss": 1.8020332336425782, "step": 4480 }, { "epoch": 0.12714198934832668, "grad_norm": 4.118474006652832, "learning_rate": 8.472693032015067e-05, "loss": 1.9140260696411133, "step": 4500 }, { "epoch": 0.12770706485654146, "grad_norm": 4.338505268096924, "learning_rate": 8.510357815442561e-05, "loss": 1.7305770874023438, "step": 4520 }, { "epoch": 0.12827214036475623, "grad_norm": 3.9260406494140625, "learning_rate": 8.548022598870057e-05, "loss": 1.8510927200317382, "step": 4540 }, { "epoch": 0.12883721587297103, "grad_norm": 4.884488582611084, "learning_rate": 8.585687382297552e-05, "loss": 1.9758781433105468, "step": 4560 }, { "epoch": 0.1294022913811858, "grad_norm": 3.203674077987671, "learning_rate": 8.623352165725048e-05, "loss": 1.837313461303711, "step": 4580 }, { "epoch": 0.1299673668894006, "grad_norm": 2.973176956176758, "learning_rate": 8.661016949152543e-05, "loss": 1.8492511749267577, "step": 4600 }, { "epoch": 0.13053244239761538, "grad_norm": 4.0425310134887695, "learning_rate": 8.698681732580038e-05, "loss": 1.7976297378540038, "step": 4620 }, { "epoch": 0.13109751790583016, "grad_norm": 4.731219291687012, "learning_rate": 8.736346516007533e-05, "loss": 1.928700828552246, "step": 4640 }, { "epoch": 0.13166259341404496, "grad_norm": 3.1372368335723877, "learning_rate": 8.774011299435028e-05, "loss": 1.9193445205688477, "step": 4660 }, { "epoch": 0.13222766892225973, "grad_norm": 4.307485103607178, "learning_rate": 8.811676082862525e-05, "loss": 1.8927040100097656, "step": 4680 }, { "epoch": 0.13279274443047454, "grad_norm": 3.8667550086975098, "learning_rate": 8.849340866290019e-05, "loss": 1.8032472610473633, "step": 4700 }, { "epoch": 0.1333578199386893, "grad_norm": 2.252525568008423, "learning_rate": 8.887005649717515e-05, "loss": 1.8621322631835937, "step": 4720 }, { "epoch": 0.13392289544690408, "grad_norm": 9.096452713012695, "learning_rate": 8.92467043314501e-05, "loss": 1.8222740173339844, "step": 4740 }, { "epoch": 0.13448797095511889, "grad_norm": 4.876845836639404, "learning_rate": 8.962335216572505e-05, "loss": 1.8211399078369142, "step": 4760 }, { "epoch": 0.13505304646333366, "grad_norm": 5.517350196838379, "learning_rate": 9e-05, "loss": 1.8328817367553711, "step": 4780 }, { "epoch": 0.13561812197154846, "grad_norm": 4.157557010650635, "learning_rate": 9.037664783427496e-05, "loss": 1.8134614944458007, "step": 4800 }, { "epoch": 0.13618319747976323, "grad_norm": 2.8596341609954834, "learning_rate": 9.075329566854991e-05, "loss": 1.816060447692871, "step": 4820 }, { "epoch": 0.136748272987978, "grad_norm": 3.9726505279541016, "learning_rate": 9.112994350282486e-05, "loss": 1.8071964263916016, "step": 4840 }, { "epoch": 0.1373133484961928, "grad_norm": 2.3504602909088135, "learning_rate": 9.150659133709981e-05, "loss": 1.8301094055175782, "step": 4860 }, { "epoch": 0.13787842400440758, "grad_norm": 5.258048057556152, "learning_rate": 9.188323917137476e-05, "loss": 1.7767465591430665, "step": 4880 }, { "epoch": 0.1384434995126224, "grad_norm": 3.822582721710205, "learning_rate": 9.225988700564973e-05, "loss": 1.851527214050293, "step": 4900 }, { "epoch": 0.13900857502083716, "grad_norm": 3.891725540161133, "learning_rate": 9.263653483992467e-05, "loss": 1.8236055374145508, "step": 4920 }, { "epoch": 0.13957365052905193, "grad_norm": 3.795771360397339, "learning_rate": 9.301318267419963e-05, "loss": 1.8394596099853515, "step": 4940 }, { "epoch": 0.14013872603726674, "grad_norm": 3.716705083847046, "learning_rate": 9.338983050847458e-05, "loss": 1.796240997314453, "step": 4960 }, { "epoch": 0.1407038015454815, "grad_norm": 4.8295392990112305, "learning_rate": 9.376647834274953e-05, "loss": 1.8437206268310546, "step": 4980 }, { "epoch": 0.1412688770536963, "grad_norm": 5.838343143463135, "learning_rate": 9.414312617702449e-05, "loss": 1.8345863342285156, "step": 5000 }, { "epoch": 0.1418339525619111, "grad_norm": 4.267309188842773, "learning_rate": 9.451977401129944e-05, "loss": 1.7434694290161132, "step": 5020 }, { "epoch": 0.14239902807012586, "grad_norm": 3.044116735458374, "learning_rate": 9.489642184557439e-05, "loss": 1.839921760559082, "step": 5040 }, { "epoch": 0.14296410357834066, "grad_norm": 4.3795857429504395, "learning_rate": 9.527306967984934e-05, "loss": 1.824784278869629, "step": 5060 }, { "epoch": 0.14352917908655544, "grad_norm": 3.2254183292388916, "learning_rate": 9.564971751412429e-05, "loss": 1.8027971267700196, "step": 5080 }, { "epoch": 0.14409425459477024, "grad_norm": 4.827868461608887, "learning_rate": 9.602636534839924e-05, "loss": 1.8502323150634765, "step": 5100 }, { "epoch": 0.144659330102985, "grad_norm": 3.796125888824463, "learning_rate": 9.640301318267421e-05, "loss": 1.8183721542358398, "step": 5120 }, { "epoch": 0.14522440561119979, "grad_norm": 3.3129069805145264, "learning_rate": 9.677966101694915e-05, "loss": 1.7893632888793944, "step": 5140 }, { "epoch": 0.1457894811194146, "grad_norm": 3.9063994884490967, "learning_rate": 9.715630885122411e-05, "loss": 1.7410701751708983, "step": 5160 }, { "epoch": 0.14635455662762936, "grad_norm": 3.0288302898406982, "learning_rate": 9.753295668549906e-05, "loss": 1.9110763549804688, "step": 5180 }, { "epoch": 0.14691963213584416, "grad_norm": 2.6014199256896973, "learning_rate": 9.790960451977402e-05, "loss": 1.7923595428466796, "step": 5200 }, { "epoch": 0.14748470764405894, "grad_norm": 4.532857418060303, "learning_rate": 9.828625235404897e-05, "loss": 1.7434818267822265, "step": 5220 }, { "epoch": 0.1480497831522737, "grad_norm": 3.6844284534454346, "learning_rate": 9.866290018832393e-05, "loss": 1.7726402282714844, "step": 5240 }, { "epoch": 0.1486148586604885, "grad_norm": 3.6164748668670654, "learning_rate": 9.903954802259887e-05, "loss": 1.7625114440917968, "step": 5260 }, { "epoch": 0.1491799341687033, "grad_norm": 5.871447563171387, "learning_rate": 9.941619585687382e-05, "loss": 1.731430435180664, "step": 5280 }, { "epoch": 0.1497450096769181, "grad_norm": 2.369749069213867, "learning_rate": 9.979284369114879e-05, "loss": 1.8822433471679687, "step": 5300 }, { "epoch": 0.15031008518513286, "grad_norm": 4.239933490753174, "learning_rate": 9.999999803580995e-05, "loss": 1.8096691131591798, "step": 5320 }, { "epoch": 0.15087516069334764, "grad_norm": 3.507423162460327, "learning_rate": 9.999997960637371e-05, "loss": 1.744801139831543, "step": 5340 }, { "epoch": 0.15144023620156244, "grad_norm": 4.114673614501953, "learning_rate": 9.999994177753797e-05, "loss": 1.79986629486084, "step": 5360 }, { "epoch": 0.1520053117097772, "grad_norm": 3.3639376163482666, "learning_rate": 9.999988454931741e-05, "loss": 1.887227439880371, "step": 5380 }, { "epoch": 0.15257038721799202, "grad_norm": 3.5731570720672607, "learning_rate": 9.999980792173426e-05, "loss": 1.7295488357543944, "step": 5400 }, { "epoch": 0.1531354627262068, "grad_norm": 3.293105363845825, "learning_rate": 9.999971189481824e-05, "loss": 1.7381031036376953, "step": 5420 }, { "epoch": 0.15370053823442156, "grad_norm": 3.6669375896453857, "learning_rate": 9.999959646860659e-05, "loss": 1.655379867553711, "step": 5440 }, { "epoch": 0.15426561374263636, "grad_norm": 3.472975254058838, "learning_rate": 9.999946164314411e-05, "loss": 1.7849767684936524, "step": 5460 }, { "epoch": 0.15483068925085114, "grad_norm": 4.797120571136475, "learning_rate": 9.999930741848311e-05, "loss": 1.6916629791259765, "step": 5480 }, { "epoch": 0.15539576475906594, "grad_norm": 3.1873271465301514, "learning_rate": 9.999913379468342e-05, "loss": 1.8157159805297851, "step": 5500 }, { "epoch": 0.15596084026728071, "grad_norm": 5.187962532043457, "learning_rate": 9.999894077181242e-05, "loss": 1.8383541107177734, "step": 5520 }, { "epoch": 0.1565259157754955, "grad_norm": 3.5466158390045166, "learning_rate": 9.999872834994497e-05, "loss": 1.7380748748779298, "step": 5540 }, { "epoch": 0.1570909912837103, "grad_norm": 3.8730380535125732, "learning_rate": 9.999849652916352e-05, "loss": 1.5584320068359374, "step": 5560 }, { "epoch": 0.15765606679192506, "grad_norm": 4.270564556121826, "learning_rate": 9.999824530955799e-05, "loss": 1.7561353683471679, "step": 5580 }, { "epoch": 0.15822114230013987, "grad_norm": 4.778900623321533, "learning_rate": 9.999797469122587e-05, "loss": 1.7723871231079102, "step": 5600 }, { "epoch": 0.15878621780835464, "grad_norm": 3.249751329421997, "learning_rate": 9.999768467427214e-05, "loss": 1.6327268600463867, "step": 5620 }, { "epoch": 0.15935129331656941, "grad_norm": 3.818366289138794, "learning_rate": 9.999737525880934e-05, "loss": 1.7093399047851563, "step": 5640 }, { "epoch": 0.15991636882478422, "grad_norm": 3.8721795082092285, "learning_rate": 9.99970464449575e-05, "loss": 1.6817913055419922, "step": 5660 }, { "epoch": 0.160481444332999, "grad_norm": 3.7059738636016846, "learning_rate": 9.99966982328442e-05, "loss": 1.6983339309692382, "step": 5680 }, { "epoch": 0.1610465198412138, "grad_norm": 3.4542179107666016, "learning_rate": 9.999633062260457e-05, "loss": 1.7293325424194337, "step": 5700 }, { "epoch": 0.16161159534942857, "grad_norm": 4.522738933563232, "learning_rate": 9.999594361438118e-05, "loss": 1.7532634735107422, "step": 5720 }, { "epoch": 0.16217667085764334, "grad_norm": 3.773507595062256, "learning_rate": 9.999553720832425e-05, "loss": 1.740022850036621, "step": 5740 }, { "epoch": 0.16274174636585814, "grad_norm": 4.690428256988525, "learning_rate": 9.999511140459142e-05, "loss": 1.723243522644043, "step": 5760 }, { "epoch": 0.16330682187407292, "grad_norm": 2.7016167640686035, "learning_rate": 9.999466620334792e-05, "loss": 1.601738166809082, "step": 5780 }, { "epoch": 0.16387189738228772, "grad_norm": 3.260730028152466, "learning_rate": 9.999420160476644e-05, "loss": 1.7013120651245117, "step": 5800 }, { "epoch": 0.1644369728905025, "grad_norm": 4.347034931182861, "learning_rate": 9.99937176090273e-05, "loss": 1.6394535064697267, "step": 5820 }, { "epoch": 0.16500204839871727, "grad_norm": 4.751648902893066, "learning_rate": 9.999321421631824e-05, "loss": 1.7439561843872071, "step": 5840 }, { "epoch": 0.16556712390693207, "grad_norm": 3.7309043407440186, "learning_rate": 9.999269142683461e-05, "loss": 1.8031402587890626, "step": 5860 }, { "epoch": 0.16613219941514684, "grad_norm": 2.1702988147735596, "learning_rate": 9.99921492407792e-05, "loss": 1.7759626388549805, "step": 5880 }, { "epoch": 0.16669727492336164, "grad_norm": 3.3647594451904297, "learning_rate": 9.999158765836239e-05, "loss": 1.687129592895508, "step": 5900 }, { "epoch": 0.16726235043157642, "grad_norm": 2.695375919342041, "learning_rate": 9.999100667980207e-05, "loss": 1.6380062103271484, "step": 5920 }, { "epoch": 0.1678274259397912, "grad_norm": 3.4938273429870605, "learning_rate": 9.999040630532366e-05, "loss": 1.7259305953979491, "step": 5940 }, { "epoch": 0.168392501448006, "grad_norm": 3.339653968811035, "learning_rate": 9.998978653516008e-05, "loss": 1.731085968017578, "step": 5960 }, { "epoch": 0.16895757695622077, "grad_norm": 3.847378969192505, "learning_rate": 9.99891473695518e-05, "loss": 1.7762832641601562, "step": 5980 }, { "epoch": 0.16952265246443557, "grad_norm": 4.453037738800049, "learning_rate": 9.998848880874682e-05, "loss": 1.6701471328735351, "step": 6000 }, { "epoch": 0.17008772797265034, "grad_norm": 2.9112942218780518, "learning_rate": 9.998781085300066e-05, "loss": 1.649435043334961, "step": 6020 }, { "epoch": 0.17065280348086512, "grad_norm": 3.5953285694122314, "learning_rate": 9.998711350257633e-05, "loss": 1.581785011291504, "step": 6040 }, { "epoch": 0.17121787898907992, "grad_norm": 3.191038131713867, "learning_rate": 9.998639675774442e-05, "loss": 1.6621814727783204, "step": 6060 }, { "epoch": 0.1717829544972947, "grad_norm": 2.8252031803131104, "learning_rate": 9.998566061878301e-05, "loss": 1.6870445251464843, "step": 6080 }, { "epoch": 0.1723480300055095, "grad_norm": 2.538952589035034, "learning_rate": 9.998490508597769e-05, "loss": 1.742706871032715, "step": 6100 }, { "epoch": 0.17291310551372427, "grad_norm": 2.5839216709136963, "learning_rate": 9.998413015962164e-05, "loss": 1.6041437149047852, "step": 6120 }, { "epoch": 0.17347818102193904, "grad_norm": 3.8392586708068848, "learning_rate": 9.998333584001549e-05, "loss": 1.5898491859436035, "step": 6140 }, { "epoch": 0.17404325653015384, "grad_norm": 3.6053872108459473, "learning_rate": 9.998252212746743e-05, "loss": 1.672309684753418, "step": 6160 }, { "epoch": 0.17460833203836862, "grad_norm": 2.380797863006592, "learning_rate": 9.998168902229322e-05, "loss": 1.640016746520996, "step": 6180 }, { "epoch": 0.17517340754658342, "grad_norm": 3.323632001876831, "learning_rate": 9.9980836524816e-05, "loss": 1.7160558700561523, "step": 6200 }, { "epoch": 0.1757384830547982, "grad_norm": 3.5054876804351807, "learning_rate": 9.99799646353666e-05, "loss": 1.6047046661376954, "step": 6220 }, { "epoch": 0.176303558563013, "grad_norm": 3.405008316040039, "learning_rate": 9.99790733542833e-05, "loss": 1.597256565093994, "step": 6240 }, { "epoch": 0.17686863407122777, "grad_norm": 2.2455461025238037, "learning_rate": 9.99781626819119e-05, "loss": 1.521227741241455, "step": 6260 }, { "epoch": 0.17743370957944254, "grad_norm": 3.103963613510132, "learning_rate": 9.997723261860569e-05, "loss": 1.6366498947143555, "step": 6280 }, { "epoch": 0.17799878508765735, "grad_norm": 3.5176007747650146, "learning_rate": 9.997628316472556e-05, "loss": 1.6851821899414063, "step": 6300 }, { "epoch": 0.17856386059587212, "grad_norm": 3.467879295349121, "learning_rate": 9.997531432063989e-05, "loss": 1.6566228866577148, "step": 6320 }, { "epoch": 0.17912893610408692, "grad_norm": 2.9246749877929688, "learning_rate": 9.997432608672457e-05, "loss": 1.780135726928711, "step": 6340 }, { "epoch": 0.1796940116123017, "grad_norm": 3.8608596324920654, "learning_rate": 9.997331846336303e-05, "loss": 1.5192646026611327, "step": 6360 }, { "epoch": 0.18025908712051647, "grad_norm": 2.612607479095459, "learning_rate": 9.99722914509462e-05, "loss": 1.5534283638000488, "step": 6380 }, { "epoch": 0.18082416262873127, "grad_norm": 5.072202205657959, "learning_rate": 9.997124504987257e-05, "loss": 1.5139975547790527, "step": 6400 }, { "epoch": 0.18138923813694605, "grad_norm": 2.4957308769226074, "learning_rate": 9.997017926054813e-05, "loss": 1.6800012588500977, "step": 6420 }, { "epoch": 0.18195431364516085, "grad_norm": 2.9175596237182617, "learning_rate": 9.996909408338638e-05, "loss": 1.6090965270996094, "step": 6440 }, { "epoch": 0.18251938915337562, "grad_norm": 5.236269474029541, "learning_rate": 9.996798951880835e-05, "loss": 1.5813274383544922, "step": 6460 }, { "epoch": 0.1830844646615904, "grad_norm": 5.763176918029785, "learning_rate": 9.99668655672426e-05, "loss": 1.6232755661010743, "step": 6480 }, { "epoch": 0.1836495401698052, "grad_norm": 2.7952699661254883, "learning_rate": 9.996572222912524e-05, "loss": 1.522822380065918, "step": 6500 }, { "epoch": 0.18421461567801997, "grad_norm": 2.32928466796875, "learning_rate": 9.996455950489983e-05, "loss": 1.603543472290039, "step": 6520 }, { "epoch": 0.18477969118623477, "grad_norm": 2.485456943511963, "learning_rate": 9.996337739501753e-05, "loss": 1.6117679595947265, "step": 6540 }, { "epoch": 0.18534476669444955, "grad_norm": 3.726656913757324, "learning_rate": 9.996217589993695e-05, "loss": 1.5750132560729981, "step": 6560 }, { "epoch": 0.18590984220266432, "grad_norm": 2.3639516830444336, "learning_rate": 9.996095502012429e-05, "loss": 1.583302879333496, "step": 6580 }, { "epoch": 0.18647491771087912, "grad_norm": 2.9316344261169434, "learning_rate": 9.995971475605321e-05, "loss": 1.468791675567627, "step": 6600 }, { "epoch": 0.1870399932190939, "grad_norm": 2.878023862838745, "learning_rate": 9.995845510820494e-05, "loss": 1.5254633903503418, "step": 6620 }, { "epoch": 0.1876050687273087, "grad_norm": 1.944187879562378, "learning_rate": 9.995717607706819e-05, "loss": 1.5603862762451173, "step": 6640 }, { "epoch": 0.18817014423552347, "grad_norm": 3.464034080505371, "learning_rate": 9.995587766313921e-05, "loss": 1.5716239929199218, "step": 6660 }, { "epoch": 0.18873521974373825, "grad_norm": 3.2853643894195557, "learning_rate": 9.995455986692177e-05, "loss": 1.4953444480895997, "step": 6680 }, { "epoch": 0.18930029525195305, "grad_norm": 2.832921028137207, "learning_rate": 9.995322268892718e-05, "loss": 1.527914047241211, "step": 6700 }, { "epoch": 0.18986537076016782, "grad_norm": 3.3305935859680176, "learning_rate": 9.995186612967423e-05, "loss": 1.655074119567871, "step": 6720 }, { "epoch": 0.19043044626838262, "grad_norm": 2.0372021198272705, "learning_rate": 9.995049018968924e-05, "loss": 1.647903823852539, "step": 6740 }, { "epoch": 0.1909955217765974, "grad_norm": 4.033935070037842, "learning_rate": 9.994909486950608e-05, "loss": 1.5634920120239257, "step": 6760 }, { "epoch": 0.19156059728481217, "grad_norm": 3.7114100456237793, "learning_rate": 9.994768016966611e-05, "loss": 1.650543212890625, "step": 6780 }, { "epoch": 0.19212567279302697, "grad_norm": 2.502955198287964, "learning_rate": 9.99462460907182e-05, "loss": 1.7147113800048828, "step": 6800 }, { "epoch": 0.19269074830124175, "grad_norm": 4.048702239990234, "learning_rate": 9.99447926332188e-05, "loss": 1.550778579711914, "step": 6820 }, { "epoch": 0.19325582380945655, "grad_norm": 3.73266339302063, "learning_rate": 9.994331979773178e-05, "loss": 1.4889442443847656, "step": 6840 }, { "epoch": 0.19382089931767132, "grad_norm": 2.587930679321289, "learning_rate": 9.994182758482861e-05, "loss": 1.505070686340332, "step": 6860 }, { "epoch": 0.1943859748258861, "grad_norm": 6.545445442199707, "learning_rate": 9.994031599508826e-05, "loss": 1.5851396560668944, "step": 6880 }, { "epoch": 0.1949510503341009, "grad_norm": 3.199765205383301, "learning_rate": 9.993878502909719e-05, "loss": 1.6734376907348634, "step": 6900 }, { "epoch": 0.19551612584231567, "grad_norm": 3.369762420654297, "learning_rate": 9.993723468744941e-05, "loss": 1.5366138458251952, "step": 6920 }, { "epoch": 0.19608120135053048, "grad_norm": 2.906684160232544, "learning_rate": 9.993566497074642e-05, "loss": 1.4348803520202638, "step": 6940 }, { "epoch": 0.19664627685874525, "grad_norm": 7.621368408203125, "learning_rate": 9.993407587959727e-05, "loss": 1.5359091758728027, "step": 6960 }, { "epoch": 0.19721135236696002, "grad_norm": 3.012256145477295, "learning_rate": 9.993246741461849e-05, "loss": 1.6068069458007812, "step": 6980 }, { "epoch": 0.19777642787517483, "grad_norm": 4.8597564697265625, "learning_rate": 9.993083957643416e-05, "loss": 1.5369335174560548, "step": 7000 }, { "epoch": 0.1983415033833896, "grad_norm": 3.584531307220459, "learning_rate": 9.992919236567585e-05, "loss": 1.4959622383117677, "step": 7020 }, { "epoch": 0.1989065788916044, "grad_norm": 3.015571355819702, "learning_rate": 9.992752578298267e-05, "loss": 1.5963862419128418, "step": 7040 }, { "epoch": 0.19947165439981918, "grad_norm": 2.365189552307129, "learning_rate": 9.992583982900123e-05, "loss": 1.630258560180664, "step": 7060 }, { "epoch": 0.20003672990803395, "grad_norm": 2.907792568206787, "learning_rate": 9.992413450438564e-05, "loss": 1.5121320724487304, "step": 7080 }, { "epoch": 0.20060180541624875, "grad_norm": 4.349268913269043, "learning_rate": 9.992240980979758e-05, "loss": 1.5213706016540527, "step": 7100 }, { "epoch": 0.20116688092446353, "grad_norm": 3.6801390647888184, "learning_rate": 9.992066574590619e-05, "loss": 1.6284637451171875, "step": 7120 }, { "epoch": 0.20173195643267833, "grad_norm": 3.5839486122131348, "learning_rate": 9.991890231338815e-05, "loss": 1.5508891105651856, "step": 7140 }, { "epoch": 0.2022970319408931, "grad_norm": 3.5347492694854736, "learning_rate": 9.991711951292766e-05, "loss": 1.550615406036377, "step": 7160 }, { "epoch": 0.20286210744910788, "grad_norm": 3.2091095447540283, "learning_rate": 9.991531734521642e-05, "loss": 1.5830965042114258, "step": 7180 }, { "epoch": 0.20342718295732268, "grad_norm": 2.6603503227233887, "learning_rate": 9.991349581095364e-05, "loss": 1.602536392211914, "step": 7200 }, { "epoch": 0.20399225846553745, "grad_norm": 2.4173378944396973, "learning_rate": 9.991165491084605e-05, "loss": 1.6049711227416992, "step": 7220 }, { "epoch": 0.20455733397375225, "grad_norm": 2.540335178375244, "learning_rate": 9.990979464560792e-05, "loss": 1.5395750999450684, "step": 7240 }, { "epoch": 0.20512240948196703, "grad_norm": 2.8932065963745117, "learning_rate": 9.9907915015961e-05, "loss": 1.6161941528320312, "step": 7260 }, { "epoch": 0.2056874849901818, "grad_norm": 2.637845039367676, "learning_rate": 9.990601602263457e-05, "loss": 1.4723081588745117, "step": 7280 }, { "epoch": 0.2062525604983966, "grad_norm": 3.191385269165039, "learning_rate": 9.990409766636539e-05, "loss": 1.5189269065856934, "step": 7300 }, { "epoch": 0.20681763600661138, "grad_norm": 3.409735918045044, "learning_rate": 9.99021599478978e-05, "loss": 1.5608896255493163, "step": 7320 }, { "epoch": 0.20738271151482618, "grad_norm": 4.243335247039795, "learning_rate": 9.990020286798358e-05, "loss": 1.4904934883117675, "step": 7340 }, { "epoch": 0.20794778702304095, "grad_norm": 3.317131519317627, "learning_rate": 9.989822642738206e-05, "loss": 1.5294264793395995, "step": 7360 }, { "epoch": 0.20851286253125573, "grad_norm": 3.0011403560638428, "learning_rate": 9.98962306268601e-05, "loss": 1.597621250152588, "step": 7380 }, { "epoch": 0.20907793803947053, "grad_norm": 3.506784677505493, "learning_rate": 9.989421546719202e-05, "loss": 1.5538950920104981, "step": 7400 }, { "epoch": 0.2096430135476853, "grad_norm": 3.0734570026397705, "learning_rate": 9.989218094915968e-05, "loss": 1.6493656158447265, "step": 7420 }, { "epoch": 0.2102080890559001, "grad_norm": 4.318345069885254, "learning_rate": 9.989012707355247e-05, "loss": 1.5690672874450684, "step": 7440 }, { "epoch": 0.21077316456411488, "grad_norm": 2.504631757736206, "learning_rate": 9.988805384116725e-05, "loss": 1.4677300453186035, "step": 7460 }, { "epoch": 0.21133824007232965, "grad_norm": 4.23356819152832, "learning_rate": 9.98859612528084e-05, "loss": 1.4287897109985352, "step": 7480 }, { "epoch": 0.21190331558054445, "grad_norm": 4.2903032302856445, "learning_rate": 9.988384930928783e-05, "loss": 1.5336151123046875, "step": 7500 }, { "epoch": 0.21246839108875923, "grad_norm": 2.8875417709350586, "learning_rate": 9.988171801142496e-05, "loss": 1.5250856399536132, "step": 7520 }, { "epoch": 0.21303346659697403, "grad_norm": 4.067424774169922, "learning_rate": 9.987956736004672e-05, "loss": 1.637319564819336, "step": 7540 }, { "epoch": 0.2135985421051888, "grad_norm": 3.686713933944702, "learning_rate": 9.987739735598749e-05, "loss": 1.527482509613037, "step": 7560 }, { "epoch": 0.21416361761340358, "grad_norm": 2.310617446899414, "learning_rate": 9.987520800008925e-05, "loss": 1.5049246788024901, "step": 7580 }, { "epoch": 0.21472869312161838, "grad_norm": 1.8799818754196167, "learning_rate": 9.987299929320142e-05, "loss": 1.4913151741027832, "step": 7600 }, { "epoch": 0.21529376862983315, "grad_norm": 3.85404109954834, "learning_rate": 9.987077123618096e-05, "loss": 1.6071218490600585, "step": 7620 }, { "epoch": 0.21585884413804796, "grad_norm": 4.748233318328857, "learning_rate": 9.986852382989233e-05, "loss": 1.4733720779418946, "step": 7640 }, { "epoch": 0.21642391964626273, "grad_norm": 3.188513994216919, "learning_rate": 9.986625707520751e-05, "loss": 1.6002666473388671, "step": 7660 }, { "epoch": 0.2169889951544775, "grad_norm": 3.6194546222686768, "learning_rate": 9.986397097300595e-05, "loss": 1.4800057411193848, "step": 7680 }, { "epoch": 0.2175540706626923, "grad_norm": 5.709437370300293, "learning_rate": 9.986166552417464e-05, "loss": 1.623441505432129, "step": 7700 }, { "epoch": 0.21811914617090708, "grad_norm": 2.8823442459106445, "learning_rate": 9.985934072960807e-05, "loss": 1.4898175239562987, "step": 7720 }, { "epoch": 0.21868422167912188, "grad_norm": 4.608748912811279, "learning_rate": 9.985699659020823e-05, "loss": 1.5173352241516114, "step": 7740 }, { "epoch": 0.21924929718733666, "grad_norm": 2.9797799587249756, "learning_rate": 9.985463310688461e-05, "loss": 1.5331196784973145, "step": 7760 }, { "epoch": 0.21981437269555143, "grad_norm": 3.305400848388672, "learning_rate": 9.985225028055424e-05, "loss": 1.5492683410644532, "step": 7780 }, { "epoch": 0.22037944820376623, "grad_norm": 2.804089069366455, "learning_rate": 9.984984811214159e-05, "loss": 1.5614015579223632, "step": 7800 }, { "epoch": 0.220944523711981, "grad_norm": 2.7313389778137207, "learning_rate": 9.984742660257872e-05, "loss": 1.517676544189453, "step": 7820 }, { "epoch": 0.2215095992201958, "grad_norm": 3.083650827407837, "learning_rate": 9.98449857528051e-05, "loss": 1.5262545585632323, "step": 7840 }, { "epoch": 0.22207467472841058, "grad_norm": 3.9882779121398926, "learning_rate": 9.984252556376778e-05, "loss": 1.4972553253173828, "step": 7860 }, { "epoch": 0.22263975023662536, "grad_norm": 2.981773853302002, "learning_rate": 9.984004603642128e-05, "loss": 1.581277084350586, "step": 7880 }, { "epoch": 0.22320482574484016, "grad_norm": 4.508055210113525, "learning_rate": 9.983754717172762e-05, "loss": 1.466499423980713, "step": 7900 }, { "epoch": 0.22376990125305493, "grad_norm": 3.901487350463867, "learning_rate": 9.983502897065633e-05, "loss": 1.4725102424621581, "step": 7920 }, { "epoch": 0.22433497676126973, "grad_norm": 2.8067219257354736, "learning_rate": 9.983249143418445e-05, "loss": 1.5024890899658203, "step": 7940 }, { "epoch": 0.2249000522694845, "grad_norm": 2.5243091583251953, "learning_rate": 9.98299345632965e-05, "loss": 1.3718006134033203, "step": 7960 }, { "epoch": 0.22546512777769928, "grad_norm": 3.112607717514038, "learning_rate": 9.982735835898454e-05, "loss": 1.4724305152893067, "step": 7980 }, { "epoch": 0.22603020328591408, "grad_norm": 4.4936041831970215, "learning_rate": 9.982476282224807e-05, "loss": 1.6108282089233399, "step": 8000 }, { "epoch": 0.22659527879412886, "grad_norm": 1.8047497272491455, "learning_rate": 9.982214795409417e-05, "loss": 1.6297479629516602, "step": 8020 }, { "epoch": 0.22716035430234366, "grad_norm": 4.698698997497559, "learning_rate": 9.981951375553734e-05, "loss": 1.4761458396911622, "step": 8040 }, { "epoch": 0.22772542981055843, "grad_norm": 3.601710796356201, "learning_rate": 9.981686022759964e-05, "loss": 1.6146076202392579, "step": 8060 }, { "epoch": 0.22829050531877323, "grad_norm": 2.85583758354187, "learning_rate": 9.981418737131061e-05, "loss": 1.6392879486083984, "step": 8080 }, { "epoch": 0.228855580826988, "grad_norm": 3.474112033843994, "learning_rate": 9.981149518770727e-05, "loss": 1.4751179695129395, "step": 8100 }, { "epoch": 0.22942065633520278, "grad_norm": 3.0534751415252686, "learning_rate": 9.980878367783418e-05, "loss": 1.5433760643005372, "step": 8120 }, { "epoch": 0.22998573184341758, "grad_norm": 6.867227554321289, "learning_rate": 9.980605284274334e-05, "loss": 1.5574782371520997, "step": 8140 }, { "epoch": 0.23055080735163236, "grad_norm": 2.432018995285034, "learning_rate": 9.98033026834943e-05, "loss": 1.5164669036865235, "step": 8160 }, { "epoch": 0.23111588285984716, "grad_norm": 6.398127555847168, "learning_rate": 9.980053320115409e-05, "loss": 1.4285327911376953, "step": 8180 }, { "epoch": 0.23168095836806193, "grad_norm": 3.225142002105713, "learning_rate": 9.979774439679723e-05, "loss": 1.5999547958374023, "step": 8200 }, { "epoch": 0.2322460338762767, "grad_norm": 3.1247947216033936, "learning_rate": 9.979493627150576e-05, "loss": 1.52624454498291, "step": 8220 }, { "epoch": 0.2328111093844915, "grad_norm": 3.0038416385650635, "learning_rate": 9.979210882636918e-05, "loss": 1.468205451965332, "step": 8240 }, { "epoch": 0.23337618489270628, "grad_norm": 3.6637372970581055, "learning_rate": 9.978926206248452e-05, "loss": 1.4372809410095215, "step": 8260 }, { "epoch": 0.23394126040092109, "grad_norm": 3.4569809436798096, "learning_rate": 9.978639598095627e-05, "loss": 1.497194194793701, "step": 8280 }, { "epoch": 0.23450633590913586, "grad_norm": 2.0911006927490234, "learning_rate": 9.978351058289647e-05, "loss": 1.472102737426758, "step": 8300 }, { "epoch": 0.23507141141735063, "grad_norm": 4.13979959487915, "learning_rate": 9.978060586942459e-05, "loss": 1.5041305541992187, "step": 8320 }, { "epoch": 0.23563648692556544, "grad_norm": 2.8084876537323, "learning_rate": 9.977768184166763e-05, "loss": 1.4558696746826172, "step": 8340 }, { "epoch": 0.2362015624337802, "grad_norm": 3.6686651706695557, "learning_rate": 9.977473850076007e-05, "loss": 1.4708217620849608, "step": 8360 }, { "epoch": 0.236766637941995, "grad_norm": 5.481020927429199, "learning_rate": 9.977177584784391e-05, "loss": 1.5245384216308593, "step": 8380 }, { "epoch": 0.23733171345020979, "grad_norm": 4.221948623657227, "learning_rate": 9.976879388406863e-05, "loss": 1.4552244186401366, "step": 8400 }, { "epoch": 0.23789678895842456, "grad_norm": 3.9234724044799805, "learning_rate": 9.976579261059117e-05, "loss": 1.4810986518859863, "step": 8420 }, { "epoch": 0.23846186446663936, "grad_norm": 3.6320295333862305, "learning_rate": 9.976277202857601e-05, "loss": 1.505628490447998, "step": 8440 }, { "epoch": 0.23902693997485414, "grad_norm": 3.922123670578003, "learning_rate": 9.975973213919509e-05, "loss": 1.5077163696289062, "step": 8460 }, { "epoch": 0.23959201548306894, "grad_norm": 3.059326410293579, "learning_rate": 9.975667294362785e-05, "loss": 1.5214643478393555, "step": 8480 }, { "epoch": 0.2401570909912837, "grad_norm": 2.640794277191162, "learning_rate": 9.975359444306123e-05, "loss": 1.4224232673645019, "step": 8500 }, { "epoch": 0.24072216649949849, "grad_norm": 4.52756929397583, "learning_rate": 9.975049663868964e-05, "loss": 1.4643077850341797, "step": 8520 }, { "epoch": 0.2412872420077133, "grad_norm": 2.8608968257904053, "learning_rate": 9.974737953171501e-05, "loss": 1.4336235046386718, "step": 8540 }, { "epoch": 0.24185231751592806, "grad_norm": 3.452813148498535, "learning_rate": 9.974424312334672e-05, "loss": 1.5331624031066895, "step": 8560 }, { "epoch": 0.24241739302414286, "grad_norm": 3.1944808959960938, "learning_rate": 9.974108741480165e-05, "loss": 1.3940090179443358, "step": 8580 }, { "epoch": 0.24298246853235764, "grad_norm": 2.6857619285583496, "learning_rate": 9.973791240730422e-05, "loss": 1.517318344116211, "step": 8600 }, { "epoch": 0.2435475440405724, "grad_norm": 4.703683853149414, "learning_rate": 9.973471810208626e-05, "loss": 1.497379970550537, "step": 8620 }, { "epoch": 0.2441126195487872, "grad_norm": 3.5125718116760254, "learning_rate": 9.973150450038714e-05, "loss": 1.6444799423217773, "step": 8640 }, { "epoch": 0.244677695057002, "grad_norm": 3.7760674953460693, "learning_rate": 9.97282716034537e-05, "loss": 1.4815176963806151, "step": 8660 }, { "epoch": 0.2452427705652168, "grad_norm": 3.7860376834869385, "learning_rate": 9.972501941254024e-05, "loss": 1.4777807235717773, "step": 8680 }, { "epoch": 0.24580784607343156, "grad_norm": 2.985360622406006, "learning_rate": 9.97217479289086e-05, "loss": 1.5328362464904786, "step": 8700 }, { "epoch": 0.24637292158164634, "grad_norm": 3.8311398029327393, "learning_rate": 9.971845715382805e-05, "loss": 1.5039958953857422, "step": 8720 }, { "epoch": 0.24693799708986114, "grad_norm": 3.819167375564575, "learning_rate": 9.971514708857541e-05, "loss": 1.4494909286499023, "step": 8740 }, { "epoch": 0.2475030725980759, "grad_norm": 3.904930353164673, "learning_rate": 9.971181773443492e-05, "loss": 1.5291725158691407, "step": 8760 }, { "epoch": 0.24806814810629071, "grad_norm": 2.622109889984131, "learning_rate": 9.970846909269833e-05, "loss": 1.4408511161804198, "step": 8780 }, { "epoch": 0.2486332236145055, "grad_norm": 3.159428834915161, "learning_rate": 9.97051011646649e-05, "loss": 1.4618435859680177, "step": 8800 }, { "epoch": 0.24919829912272026, "grad_norm": 3.1256961822509766, "learning_rate": 9.97017139516413e-05, "loss": 1.5392280578613282, "step": 8820 }, { "epoch": 0.24976337463093506, "grad_norm": 4.740623474121094, "learning_rate": 9.969830745494175e-05, "loss": 1.534083652496338, "step": 8840 }, { "epoch": 0.25032845013914984, "grad_norm": 3.7735416889190674, "learning_rate": 9.969488167588794e-05, "loss": 1.4521275520324708, "step": 8860 }, { "epoch": 0.2508935256473646, "grad_norm": 3.432828903198242, "learning_rate": 9.969143661580902e-05, "loss": 1.4822478294372559, "step": 8880 }, { "epoch": 0.25145860115557944, "grad_norm": 6.959384441375732, "learning_rate": 9.968797227604164e-05, "loss": 1.3712017059326171, "step": 8900 }, { "epoch": 0.2520236766637942, "grad_norm": 3.5942864418029785, "learning_rate": 9.968448865792992e-05, "loss": 1.4966981887817383, "step": 8920 }, { "epoch": 0.252588752172009, "grad_norm": 5.365052223205566, "learning_rate": 9.968098576282547e-05, "loss": 1.4796293258666993, "step": 8940 }, { "epoch": 0.25315382768022376, "grad_norm": 3.509723424911499, "learning_rate": 9.967746359208735e-05, "loss": 1.3775707244873048, "step": 8960 }, { "epoch": 0.25371890318843854, "grad_norm": 3.4826693534851074, "learning_rate": 9.967392214708214e-05, "loss": 1.5164043426513671, "step": 8980 }, { "epoch": 0.25428397869665337, "grad_norm": 4.035372734069824, "learning_rate": 9.967036142918388e-05, "loss": 1.4027980804443358, "step": 9000 }, { "epoch": 0.25484905420486814, "grad_norm": 4.701097011566162, "learning_rate": 9.966678143977407e-05, "loss": 1.4672224044799804, "step": 9020 }, { "epoch": 0.2554141297130829, "grad_norm": 2.890103340148926, "learning_rate": 9.966318218024172e-05, "loss": 1.5586235046386718, "step": 9040 }, { "epoch": 0.2559792052212977, "grad_norm": 3.167006015777588, "learning_rate": 9.965956365198328e-05, "loss": 1.5025809288024903, "step": 9060 }, { "epoch": 0.25654428072951246, "grad_norm": 2.3600714206695557, "learning_rate": 9.965592585640273e-05, "loss": 1.3761470794677735, "step": 9080 }, { "epoch": 0.2571093562377273, "grad_norm": 2.3867852687835693, "learning_rate": 9.965226879491145e-05, "loss": 1.4962313652038575, "step": 9100 }, { "epoch": 0.25767443174594207, "grad_norm": 4.837586879730225, "learning_rate": 9.964859246892837e-05, "loss": 1.4751188278198242, "step": 9120 }, { "epoch": 0.25823950725415684, "grad_norm": 3.7450876235961914, "learning_rate": 9.964489687987986e-05, "loss": 1.4468761444091798, "step": 9140 }, { "epoch": 0.2588045827623716, "grad_norm": 2.067190647125244, "learning_rate": 9.964118202919973e-05, "loss": 1.4388608932495117, "step": 9160 }, { "epoch": 0.2593696582705864, "grad_norm": 3.427778482437134, "learning_rate": 9.963744791832933e-05, "loss": 1.4020013809204102, "step": 9180 }, { "epoch": 0.2599347337788012, "grad_norm": 4.155083656311035, "learning_rate": 9.963369454871745e-05, "loss": 1.4994168281555176, "step": 9200 }, { "epoch": 0.260499809287016, "grad_norm": 2.949540615081787, "learning_rate": 9.962992192182033e-05, "loss": 1.3615249633789062, "step": 9220 }, { "epoch": 0.26106488479523077, "grad_norm": 3.314021587371826, "learning_rate": 9.962613003910173e-05, "loss": 1.4539411544799805, "step": 9240 }, { "epoch": 0.26162996030344554, "grad_norm": 3.22041654586792, "learning_rate": 9.962231890203284e-05, "loss": 1.4634221076965332, "step": 9260 }, { "epoch": 0.2621950358116603, "grad_norm": 2.301424503326416, "learning_rate": 9.961848851209232e-05, "loss": 1.487288761138916, "step": 9280 }, { "epoch": 0.26276011131987514, "grad_norm": 5.55551815032959, "learning_rate": 9.961463887076636e-05, "loss": 1.479696273803711, "step": 9300 }, { "epoch": 0.2633251868280899, "grad_norm": 3.263231039047241, "learning_rate": 9.961076997954856e-05, "loss": 1.3834248542785645, "step": 9320 }, { "epoch": 0.2638902623363047, "grad_norm": 3.6920855045318604, "learning_rate": 9.960688183993999e-05, "loss": 1.3883632659912108, "step": 9340 }, { "epoch": 0.26445533784451947, "grad_norm": 2.924807548522949, "learning_rate": 9.960297445344919e-05, "loss": 1.5071229934692383, "step": 9360 }, { "epoch": 0.26502041335273424, "grad_norm": 1.9747225046157837, "learning_rate": 9.959904782159222e-05, "loss": 1.479658317565918, "step": 9380 }, { "epoch": 0.26558548886094907, "grad_norm": 3.115691661834717, "learning_rate": 9.959510194589252e-05, "loss": 1.4547225952148437, "step": 9400 }, { "epoch": 0.26615056436916384, "grad_norm": 3.5717225074768066, "learning_rate": 9.959113682788109e-05, "loss": 1.4966227531433105, "step": 9420 }, { "epoch": 0.2667156398773786, "grad_norm": 3.1260085105895996, "learning_rate": 9.958715246909632e-05, "loss": 1.3492955207824706, "step": 9440 }, { "epoch": 0.2672807153855934, "grad_norm": 5.622844219207764, "learning_rate": 9.958314887108409e-05, "loss": 1.4332292556762696, "step": 9460 }, { "epoch": 0.26784579089380817, "grad_norm": 3.7068428993225098, "learning_rate": 9.957912603539777e-05, "loss": 1.5725144386291503, "step": 9480 }, { "epoch": 0.268410866402023, "grad_norm": 3.9180545806884766, "learning_rate": 9.957508396359815e-05, "loss": 1.5934465408325196, "step": 9500 }, { "epoch": 0.26897594191023777, "grad_norm": 3.9512922763824463, "learning_rate": 9.957102265725353e-05, "loss": 1.4474807739257813, "step": 9520 }, { "epoch": 0.26954101741845254, "grad_norm": 2.7494406700134277, "learning_rate": 9.956694211793963e-05, "loss": 1.4355390548706055, "step": 9540 }, { "epoch": 0.2701060929266673, "grad_norm": 2.2034802436828613, "learning_rate": 9.956284234723964e-05, "loss": 1.3926453590393066, "step": 9560 }, { "epoch": 0.2706711684348821, "grad_norm": 3.778809070587158, "learning_rate": 9.955872334674425e-05, "loss": 1.4509303092956543, "step": 9580 }, { "epoch": 0.2712362439430969, "grad_norm": 2.986057996749878, "learning_rate": 9.955458511805159e-05, "loss": 1.3687426567077636, "step": 9600 }, { "epoch": 0.2718013194513117, "grad_norm": 3.1556360721588135, "learning_rate": 9.955042766276721e-05, "loss": 1.352797794342041, "step": 9620 }, { "epoch": 0.27236639495952647, "grad_norm": 2.986804723739624, "learning_rate": 9.954625098250417e-05, "loss": 1.528203296661377, "step": 9640 }, { "epoch": 0.27293147046774124, "grad_norm": 3.069422960281372, "learning_rate": 9.954205507888297e-05, "loss": 1.4064407348632812, "step": 9660 }, { "epoch": 0.273496545975956, "grad_norm": 4.62985372543335, "learning_rate": 9.953783995353158e-05, "loss": 1.4253838539123536, "step": 9680 }, { "epoch": 0.27406162148417085, "grad_norm": 3.8808672428131104, "learning_rate": 9.95336056080854e-05, "loss": 1.3948532104492188, "step": 9700 }, { "epoch": 0.2746266969923856, "grad_norm": 2.7956416606903076, "learning_rate": 9.952935204418734e-05, "loss": 1.3664334297180176, "step": 9720 }, { "epoch": 0.2751917725006004, "grad_norm": 3.885554075241089, "learning_rate": 9.95250792634877e-05, "loss": 1.4629864692687988, "step": 9740 }, { "epoch": 0.27575684800881517, "grad_norm": 3.58119797706604, "learning_rate": 9.952078726764426e-05, "loss": 1.279677391052246, "step": 9760 }, { "epoch": 0.27632192351702994, "grad_norm": 3.861758232116699, "learning_rate": 9.951647605832231e-05, "loss": 1.426565170288086, "step": 9780 }, { "epoch": 0.2768869990252448, "grad_norm": 3.281649112701416, "learning_rate": 9.95121456371945e-05, "loss": 1.4375346183776856, "step": 9800 }, { "epoch": 0.27745207453345955, "grad_norm": 3.8040709495544434, "learning_rate": 9.9507796005941e-05, "loss": 1.3270833015441894, "step": 9820 }, { "epoch": 0.2780171500416743, "grad_norm": 3.5282747745513916, "learning_rate": 9.950342716624943e-05, "loss": 1.4425312995910644, "step": 9840 }, { "epoch": 0.2785822255498891, "grad_norm": 3.3337771892547607, "learning_rate": 9.949903911981481e-05, "loss": 1.4338923454284669, "step": 9860 }, { "epoch": 0.27914730105810387, "grad_norm": 2.9965240955352783, "learning_rate": 9.949463186833972e-05, "loss": 1.4724153518676757, "step": 9880 }, { "epoch": 0.2797123765663187, "grad_norm": 2.999136447906494, "learning_rate": 9.949020541353404e-05, "loss": 1.4008754730224608, "step": 9900 }, { "epoch": 0.2802774520745335, "grad_norm": 3.019803762435913, "learning_rate": 9.948575975711523e-05, "loss": 1.4446629524230956, "step": 9920 }, { "epoch": 0.28084252758274825, "grad_norm": 3.690021276473999, "learning_rate": 9.948129490080812e-05, "loss": 1.4665382385253907, "step": 9940 }, { "epoch": 0.281407603090963, "grad_norm": 2.8875932693481445, "learning_rate": 9.947681084634509e-05, "loss": 1.2947988510131836, "step": 9960 }, { "epoch": 0.2819726785991778, "grad_norm": 3.8129169940948486, "learning_rate": 9.947230759546582e-05, "loss": 1.3990684509277345, "step": 9980 }, { "epoch": 0.2825377541073926, "grad_norm": 3.002448558807373, "learning_rate": 9.946778514991755e-05, "loss": 1.436600685119629, "step": 10000 }, { "epoch": 0.2831028296156074, "grad_norm": 5.486516952514648, "learning_rate": 9.946324351145493e-05, "loss": 1.4774100303649902, "step": 10020 }, { "epoch": 0.2836679051238222, "grad_norm": 3.678013324737549, "learning_rate": 9.945868268184008e-05, "loss": 1.4960163116455079, "step": 10040 }, { "epoch": 0.28423298063203695, "grad_norm": 3.7813475131988525, "learning_rate": 9.945410266284251e-05, "loss": 1.4596543312072754, "step": 10060 }, { "epoch": 0.2847980561402517, "grad_norm": 3.665384292602539, "learning_rate": 9.944950345623927e-05, "loss": 1.3622060775756837, "step": 10080 }, { "epoch": 0.28536313164846655, "grad_norm": 3.519195795059204, "learning_rate": 9.944488506381475e-05, "loss": 1.435713291168213, "step": 10100 }, { "epoch": 0.2859282071566813, "grad_norm": 2.993570566177368, "learning_rate": 9.944024748736086e-05, "loss": 1.3990497589111328, "step": 10120 }, { "epoch": 0.2864932826648961, "grad_norm": 3.640380620956421, "learning_rate": 9.94355907286769e-05, "loss": 1.4263050079345703, "step": 10140 }, { "epoch": 0.2870583581731109, "grad_norm": 3.5600426197052, "learning_rate": 9.943091478956964e-05, "loss": 1.4787766456604003, "step": 10160 }, { "epoch": 0.28762343368132565, "grad_norm": 3.197493553161621, "learning_rate": 9.94262196718533e-05, "loss": 1.2981319427490234, "step": 10180 }, { "epoch": 0.2881885091895405, "grad_norm": 3.2794981002807617, "learning_rate": 9.942150537734954e-05, "loss": 1.3648351669311523, "step": 10200 }, { "epoch": 0.28875358469775525, "grad_norm": 3.254457712173462, "learning_rate": 9.941677190788743e-05, "loss": 1.504896354675293, "step": 10220 }, { "epoch": 0.28931866020597, "grad_norm": 2.4169812202453613, "learning_rate": 9.941201926530352e-05, "loss": 1.3792830467224122, "step": 10240 }, { "epoch": 0.2898837357141848, "grad_norm": 3.932124376296997, "learning_rate": 9.940724745144175e-05, "loss": 1.4540437698364257, "step": 10260 }, { "epoch": 0.29044881122239957, "grad_norm": 3.225214958190918, "learning_rate": 9.940245646815355e-05, "loss": 1.4326263427734376, "step": 10280 }, { "epoch": 0.2910138867306144, "grad_norm": 3.3328521251678467, "learning_rate": 9.939764631729777e-05, "loss": 1.2505900382995605, "step": 10300 }, { "epoch": 0.2915789622388292, "grad_norm": 4.805780410766602, "learning_rate": 9.939281700074067e-05, "loss": 1.4697511672973633, "step": 10320 }, { "epoch": 0.29214403774704395, "grad_norm": 3.9462342262268066, "learning_rate": 9.938796852035599e-05, "loss": 1.477389144897461, "step": 10340 }, { "epoch": 0.2927091132552587, "grad_norm": 4.051931381225586, "learning_rate": 9.938310087802485e-05, "loss": 1.4705601692199708, "step": 10360 }, { "epoch": 0.2932741887634735, "grad_norm": 3.4094955921173096, "learning_rate": 9.937821407563588e-05, "loss": 1.4268510818481446, "step": 10380 }, { "epoch": 0.2938392642716883, "grad_norm": 2.3119215965270996, "learning_rate": 9.937330811508507e-05, "loss": 1.3867673873901367, "step": 10400 }, { "epoch": 0.2944043397799031, "grad_norm": 3.579387664794922, "learning_rate": 9.936838299827589e-05, "loss": 1.4339710235595704, "step": 10420 }, { "epoch": 0.2949694152881179, "grad_norm": 3.2447400093078613, "learning_rate": 9.936343872711921e-05, "loss": 1.3774785995483398, "step": 10440 }, { "epoch": 0.29553449079633265, "grad_norm": 3.4663472175598145, "learning_rate": 9.935847530353337e-05, "loss": 1.3901395797729492, "step": 10460 }, { "epoch": 0.2960995663045474, "grad_norm": 2.9764745235443115, "learning_rate": 9.935349272944411e-05, "loss": 1.3585482597351075, "step": 10480 }, { "epoch": 0.29666464181276225, "grad_norm": 3.923532247543335, "learning_rate": 9.934849100678461e-05, "loss": 1.3290056228637694, "step": 10500 }, { "epoch": 0.297229717320977, "grad_norm": 3.738661050796509, "learning_rate": 9.934347013749548e-05, "loss": 1.4927763938903809, "step": 10520 }, { "epoch": 0.2977947928291918, "grad_norm": 3.4218671321868896, "learning_rate": 9.933843012352475e-05, "loss": 1.4275416374206542, "step": 10540 }, { "epoch": 0.2983598683374066, "grad_norm": 2.6508007049560547, "learning_rate": 9.93333709668279e-05, "loss": 1.2727023124694825, "step": 10560 }, { "epoch": 0.29892494384562135, "grad_norm": 3.761737108230591, "learning_rate": 9.932829266936781e-05, "loss": 1.4442283630371093, "step": 10580 }, { "epoch": 0.2994900193538362, "grad_norm": 3.547638416290283, "learning_rate": 9.93231952331148e-05, "loss": 1.406318473815918, "step": 10600 }, { "epoch": 0.30005509486205095, "grad_norm": 3.101388692855835, "learning_rate": 9.931807866004663e-05, "loss": 1.3972251892089844, "step": 10620 }, { "epoch": 0.3006201703702657, "grad_norm": 3.980935573577881, "learning_rate": 9.931294295214845e-05, "loss": 1.3440360069274901, "step": 10640 }, { "epoch": 0.3011852458784805, "grad_norm": 3.3692402839660645, "learning_rate": 9.930778811141286e-05, "loss": 1.4425088882446289, "step": 10660 }, { "epoch": 0.3017503213866953, "grad_norm": 2.5094501972198486, "learning_rate": 9.930261413983989e-05, "loss": 1.3363531112670899, "step": 10680 }, { "epoch": 0.3023153968949101, "grad_norm": 3.9614109992980957, "learning_rate": 9.929742103943697e-05, "loss": 1.3720932960510255, "step": 10700 }, { "epoch": 0.3028804724031249, "grad_norm": 3.4301693439483643, "learning_rate": 9.929220881221895e-05, "loss": 1.4090145111083985, "step": 10720 }, { "epoch": 0.30344554791133965, "grad_norm": 3.2446553707122803, "learning_rate": 9.928697746020812e-05, "loss": 1.400029468536377, "step": 10740 }, { "epoch": 0.3040106234195544, "grad_norm": 3.8217787742614746, "learning_rate": 9.92817269854342e-05, "loss": 1.2847588539123536, "step": 10760 }, { "epoch": 0.3045756989277692, "grad_norm": 3.033372163772583, "learning_rate": 9.92764573899343e-05, "loss": 1.3729937553405762, "step": 10780 }, { "epoch": 0.30514077443598403, "grad_norm": 2.631093740463257, "learning_rate": 9.927116867575295e-05, "loss": 1.3496780395507812, "step": 10800 }, { "epoch": 0.3057058499441988, "grad_norm": 2.423790693283081, "learning_rate": 9.92658608449421e-05, "loss": 1.4595003128051758, "step": 10820 }, { "epoch": 0.3062709254524136, "grad_norm": 2.4488139152526855, "learning_rate": 9.926053389956115e-05, "loss": 1.3925975799560546, "step": 10840 }, { "epoch": 0.30683600096062835, "grad_norm": 3.043842315673828, "learning_rate": 9.925518784167692e-05, "loss": 1.380905532836914, "step": 10860 }, { "epoch": 0.3074010764688431, "grad_norm": 1.9303349256515503, "learning_rate": 9.924982267336354e-05, "loss": 1.4065467834472656, "step": 10880 }, { "epoch": 0.30796615197705796, "grad_norm": 3.87882137298584, "learning_rate": 9.924443839670268e-05, "loss": 1.364522647857666, "step": 10900 }, { "epoch": 0.30853122748527273, "grad_norm": 2.0383667945861816, "learning_rate": 9.923903501378338e-05, "loss": 1.4105310440063477, "step": 10920 }, { "epoch": 0.3090963029934875, "grad_norm": 2.137739896774292, "learning_rate": 9.923361252670207e-05, "loss": 1.3584872245788575, "step": 10940 }, { "epoch": 0.3096613785017023, "grad_norm": 2.339095115661621, "learning_rate": 9.92281709375626e-05, "loss": 1.313783550262451, "step": 10960 }, { "epoch": 0.31022645400991705, "grad_norm": 2.874467611312866, "learning_rate": 9.922271024847629e-05, "loss": 1.31652774810791, "step": 10980 }, { "epoch": 0.3107915295181319, "grad_norm": 3.7711572647094727, "learning_rate": 9.921723046156178e-05, "loss": 1.3701645851135253, "step": 11000 }, { "epoch": 0.31135660502634666, "grad_norm": 2.451141834259033, "learning_rate": 9.921173157894517e-05, "loss": 1.3177138328552247, "step": 11020 }, { "epoch": 0.31192168053456143, "grad_norm": 3.097536563873291, "learning_rate": 9.920621360275996e-05, "loss": 1.3298568725585938, "step": 11040 }, { "epoch": 0.3124867560427762, "grad_norm": 3.2429821491241455, "learning_rate": 9.920067653514709e-05, "loss": 1.445188331604004, "step": 11060 }, { "epoch": 0.313051831550991, "grad_norm": 3.7782435417175293, "learning_rate": 9.919512037825482e-05, "loss": 1.3962956428527833, "step": 11080 }, { "epoch": 0.3136169070592058, "grad_norm": 3.1900830268859863, "learning_rate": 9.918954513423893e-05, "loss": 1.3816341400146483, "step": 11100 }, { "epoch": 0.3141819825674206, "grad_norm": 3.7284164428710938, "learning_rate": 9.918395080526251e-05, "loss": 1.4106752395629882, "step": 11120 }, { "epoch": 0.31474705807563536, "grad_norm": 3.1267714500427246, "learning_rate": 9.917833739349611e-05, "loss": 1.3085719108581544, "step": 11140 }, { "epoch": 0.31531213358385013, "grad_norm": 2.8309195041656494, "learning_rate": 9.917270490111768e-05, "loss": 1.2791126251220704, "step": 11160 }, { "epoch": 0.3158772090920649, "grad_norm": 2.995832681655884, "learning_rate": 9.91670533303125e-05, "loss": 1.3888248443603515, "step": 11180 }, { "epoch": 0.31644228460027973, "grad_norm": 2.6980929374694824, "learning_rate": 9.91613826832734e-05, "loss": 1.4429994583129884, "step": 11200 }, { "epoch": 0.3170073601084945, "grad_norm": 3.2667343616485596, "learning_rate": 9.915569296220046e-05, "loss": 1.3575071334838866, "step": 11220 }, { "epoch": 0.3175724356167093, "grad_norm": 4.016037464141846, "learning_rate": 9.914998416930125e-05, "loss": 1.4467103004455566, "step": 11240 }, { "epoch": 0.31813751112492406, "grad_norm": 2.8818068504333496, "learning_rate": 9.914425630679072e-05, "loss": 1.3493334770202636, "step": 11260 }, { "epoch": 0.31870258663313883, "grad_norm": 3.385948896408081, "learning_rate": 9.91385093768912e-05, "loss": 1.3773790359497071, "step": 11280 }, { "epoch": 0.31926766214135366, "grad_norm": 3.0898282527923584, "learning_rate": 9.913274338183242e-05, "loss": 1.3016839981079102, "step": 11300 }, { "epoch": 0.31983273764956843, "grad_norm": 4.008965969085693, "learning_rate": 9.912695832385152e-05, "loss": 1.4033706665039063, "step": 11320 }, { "epoch": 0.3203978131577832, "grad_norm": 3.0523576736450195, "learning_rate": 9.912115420519306e-05, "loss": 1.3279399871826172, "step": 11340 }, { "epoch": 0.320962888665998, "grad_norm": 4.400137901306152, "learning_rate": 9.911533102810897e-05, "loss": 1.3906796455383301, "step": 11360 }, { "epoch": 0.32152796417421275, "grad_norm": 3.015141487121582, "learning_rate": 9.910948879485853e-05, "loss": 1.5382843017578125, "step": 11380 }, { "epoch": 0.3220930396824276, "grad_norm": 3.084864854812622, "learning_rate": 9.910362750770849e-05, "loss": 1.4085588455200195, "step": 11400 }, { "epoch": 0.32265811519064236, "grad_norm": 3.251131534576416, "learning_rate": 9.909774716893296e-05, "loss": 1.3900931358337403, "step": 11420 }, { "epoch": 0.32322319069885713, "grad_norm": 3.2206332683563232, "learning_rate": 9.909184778081342e-05, "loss": 1.4664071083068848, "step": 11440 }, { "epoch": 0.3237882662070719, "grad_norm": 4.314970970153809, "learning_rate": 9.90859293456388e-05, "loss": 1.2837697982788085, "step": 11460 }, { "epoch": 0.3243533417152867, "grad_norm": 3.1601219177246094, "learning_rate": 9.907999186570536e-05, "loss": 1.3256165504455566, "step": 11480 }, { "epoch": 0.3249184172235015, "grad_norm": 2.844912052154541, "learning_rate": 9.907403534331677e-05, "loss": 1.444107723236084, "step": 11500 }, { "epoch": 0.3254834927317163, "grad_norm": 3.423476219177246, "learning_rate": 9.906805978078409e-05, "loss": 1.3204006195068358, "step": 11520 }, { "epoch": 0.32604856823993106, "grad_norm": 3.181091785430908, "learning_rate": 9.906206518042576e-05, "loss": 1.408633041381836, "step": 11540 }, { "epoch": 0.32661364374814583, "grad_norm": 2.682130813598633, "learning_rate": 9.905605154456763e-05, "loss": 1.3772898674011231, "step": 11560 }, { "epoch": 0.3271787192563606, "grad_norm": 3.340155601501465, "learning_rate": 9.905001887554292e-05, "loss": 1.3727995872497558, "step": 11580 }, { "epoch": 0.32774379476457544, "grad_norm": 2.9898293018341064, "learning_rate": 9.904396717569222e-05, "loss": 1.3759284019470215, "step": 11600 }, { "epoch": 0.3283088702727902, "grad_norm": 3.2928414344787598, "learning_rate": 9.903789644736355e-05, "loss": 1.4322185516357422, "step": 11620 }, { "epoch": 0.328873945781005, "grad_norm": 2.88627290725708, "learning_rate": 9.903180669291223e-05, "loss": 1.45438814163208, "step": 11640 }, { "epoch": 0.32943902128921976, "grad_norm": 3.570549726486206, "learning_rate": 9.902569791470104e-05, "loss": 1.3041391372680664, "step": 11660 }, { "epoch": 0.33000409679743453, "grad_norm": 2.231503486633301, "learning_rate": 9.901957011510013e-05, "loss": 1.3075013160705566, "step": 11680 }, { "epoch": 0.33056917230564936, "grad_norm": 4.236885070800781, "learning_rate": 9.901342329648697e-05, "loss": 1.3730362892150878, "step": 11700 }, { "epoch": 0.33113424781386414, "grad_norm": 3.6721575260162354, "learning_rate": 9.90072574612465e-05, "loss": 1.3328767776489259, "step": 11720 }, { "epoch": 0.3316993233220789, "grad_norm": 3.2962779998779297, "learning_rate": 9.900107261177096e-05, "loss": 1.4687552452087402, "step": 11740 }, { "epoch": 0.3322643988302937, "grad_norm": 3.932791233062744, "learning_rate": 9.899486875046002e-05, "loss": 1.377164936065674, "step": 11760 }, { "epoch": 0.33282947433850846, "grad_norm": 4.264441013336182, "learning_rate": 9.898864587972069e-05, "loss": 1.301496982574463, "step": 11780 }, { "epoch": 0.3333945498467233, "grad_norm": 2.1791441440582275, "learning_rate": 9.898240400196736e-05, "loss": 1.4380258560180663, "step": 11800 }, { "epoch": 0.33395962535493806, "grad_norm": 2.8227555751800537, "learning_rate": 9.897614311962184e-05, "loss": 1.284807300567627, "step": 11820 }, { "epoch": 0.33452470086315284, "grad_norm": 3.599065065383911, "learning_rate": 9.896986323511324e-05, "loss": 1.3105058670043945, "step": 11840 }, { "epoch": 0.3350897763713676, "grad_norm": 3.237373113632202, "learning_rate": 9.89635643508781e-05, "loss": 1.3528427124023437, "step": 11860 }, { "epoch": 0.3356548518795824, "grad_norm": 1.796560287475586, "learning_rate": 9.895724646936031e-05, "loss": 1.2341827392578124, "step": 11880 }, { "epoch": 0.3362199273877972, "grad_norm": 3.5483744144439697, "learning_rate": 9.895090959301112e-05, "loss": 1.3287677764892578, "step": 11900 }, { "epoch": 0.336785002896012, "grad_norm": 3.464115619659424, "learning_rate": 9.894455372428919e-05, "loss": 1.3549612998962401, "step": 11920 }, { "epoch": 0.33735007840422676, "grad_norm": 3.8752341270446777, "learning_rate": 9.89381788656605e-05, "loss": 1.324669647216797, "step": 11940 }, { "epoch": 0.33791515391244153, "grad_norm": 2.9223008155822754, "learning_rate": 9.893178501959843e-05, "loss": 1.2360296249389648, "step": 11960 }, { "epoch": 0.3384802294206563, "grad_norm": 3.784315824508667, "learning_rate": 9.892537218858371e-05, "loss": 1.3422329902648926, "step": 11980 }, { "epoch": 0.33904530492887114, "grad_norm": 2.6226794719696045, "learning_rate": 9.891894037510445e-05, "loss": 1.332267951965332, "step": 12000 }, { "epoch": 0.3396103804370859, "grad_norm": 4.173865795135498, "learning_rate": 9.89124895816561e-05, "loss": 1.3408495903015136, "step": 12020 }, { "epoch": 0.3401754559453007, "grad_norm": 3.483492374420166, "learning_rate": 9.890601981074153e-05, "loss": 1.3306877136230468, "step": 12040 }, { "epoch": 0.34074053145351546, "grad_norm": 3.9041860103607178, "learning_rate": 9.889953106487089e-05, "loss": 1.2655829429626464, "step": 12060 }, { "epoch": 0.34130560696173023, "grad_norm": 2.634760618209839, "learning_rate": 9.889302334656176e-05, "loss": 1.384559154510498, "step": 12080 }, { "epoch": 0.34187068246994506, "grad_norm": 3.1494524478912354, "learning_rate": 9.888649665833905e-05, "loss": 1.4107508659362793, "step": 12100 }, { "epoch": 0.34243575797815984, "grad_norm": 1.7548595666885376, "learning_rate": 9.887995100273504e-05, "loss": 1.3325700759887695, "step": 12120 }, { "epoch": 0.3430008334863746, "grad_norm": 3.071404457092285, "learning_rate": 9.887338638228936e-05, "loss": 1.3859013557434081, "step": 12140 }, { "epoch": 0.3435659089945894, "grad_norm": 3.6949093341827393, "learning_rate": 9.886680279954903e-05, "loss": 1.3090840339660645, "step": 12160 }, { "epoch": 0.34413098450280416, "grad_norm": 3.595059871673584, "learning_rate": 9.886020025706837e-05, "loss": 1.344700241088867, "step": 12180 }, { "epoch": 0.344696060011019, "grad_norm": 2.831061601638794, "learning_rate": 9.88535787574091e-05, "loss": 1.351454734802246, "step": 12200 }, { "epoch": 0.34526113551923376, "grad_norm": 3.295546054840088, "learning_rate": 9.884693830314029e-05, "loss": 1.4619136810302735, "step": 12220 }, { "epoch": 0.34582621102744854, "grad_norm": 4.220534801483154, "learning_rate": 9.884027889683836e-05, "loss": 1.3694972038269042, "step": 12240 }, { "epoch": 0.3463912865356633, "grad_norm": 3.6566596031188965, "learning_rate": 9.883360054108707e-05, "loss": 1.4314380645751954, "step": 12260 }, { "epoch": 0.3469563620438781, "grad_norm": 3.332871198654175, "learning_rate": 9.882690323847755e-05, "loss": 1.4168705940246582, "step": 12280 }, { "epoch": 0.3475214375520929, "grad_norm": 3.772921085357666, "learning_rate": 9.882018699160827e-05, "loss": 1.4146920204162599, "step": 12300 }, { "epoch": 0.3480865130603077, "grad_norm": 3.1218364238739014, "learning_rate": 9.881345180308503e-05, "loss": 1.2580613136291503, "step": 12320 }, { "epoch": 0.34865158856852246, "grad_norm": 3.7025327682495117, "learning_rate": 9.880669767552106e-05, "loss": 1.302113151550293, "step": 12340 }, { "epoch": 0.34921666407673724, "grad_norm": 2.1027255058288574, "learning_rate": 9.879992461153684e-05, "loss": 1.3284140586853028, "step": 12360 }, { "epoch": 0.349781739584952, "grad_norm": 2.412069797515869, "learning_rate": 9.879313261376024e-05, "loss": 1.3059186935424805, "step": 12380 }, { "epoch": 0.35034681509316684, "grad_norm": 4.921259880065918, "learning_rate": 9.87863216848265e-05, "loss": 1.373667335510254, "step": 12400 }, { "epoch": 0.3509118906013816, "grad_norm": 2.941230058670044, "learning_rate": 9.877949182737815e-05, "loss": 1.3878764152526855, "step": 12420 }, { "epoch": 0.3514769661095964, "grad_norm": 2.9702885150909424, "learning_rate": 9.877264304406512e-05, "loss": 1.300623607635498, "step": 12440 }, { "epoch": 0.35204204161781116, "grad_norm": 3.224139928817749, "learning_rate": 9.876577533754464e-05, "loss": 1.3183808326721191, "step": 12460 }, { "epoch": 0.352607117126026, "grad_norm": 4.9529948234558105, "learning_rate": 9.87588887104813e-05, "loss": 1.2616344451904298, "step": 12480 }, { "epoch": 0.35317219263424077, "grad_norm": 4.393898010253906, "learning_rate": 9.875198316554701e-05, "loss": 1.3790562629699707, "step": 12500 }, { "epoch": 0.35373726814245554, "grad_norm": 2.887641191482544, "learning_rate": 9.874505870542108e-05, "loss": 1.302402400970459, "step": 12520 }, { "epoch": 0.3543023436506703, "grad_norm": 5.124517917633057, "learning_rate": 9.873811533279009e-05, "loss": 1.3505962371826172, "step": 12540 }, { "epoch": 0.3548674191588851, "grad_norm": 1.8160479068756104, "learning_rate": 9.873115305034802e-05, "loss": 1.3695784568786622, "step": 12560 }, { "epoch": 0.3554324946670999, "grad_norm": 2.859093427658081, "learning_rate": 9.87241718607961e-05, "loss": 1.3509838104248046, "step": 12580 }, { "epoch": 0.3559975701753147, "grad_norm": 4.635830879211426, "learning_rate": 9.871717176684299e-05, "loss": 1.4030471801757813, "step": 12600 }, { "epoch": 0.35656264568352947, "grad_norm": 2.253551721572876, "learning_rate": 9.871015277120463e-05, "loss": 1.3508992195129395, "step": 12620 }, { "epoch": 0.35712772119174424, "grad_norm": 3.2245516777038574, "learning_rate": 9.870311487660432e-05, "loss": 1.3443380355834962, "step": 12640 }, { "epoch": 0.357692796699959, "grad_norm": 3.7038655281066895, "learning_rate": 9.869605808577265e-05, "loss": 1.4076719284057617, "step": 12660 }, { "epoch": 0.35825787220817384, "grad_norm": 4.042696475982666, "learning_rate": 9.86889824014476e-05, "loss": 1.3149115562438964, "step": 12680 }, { "epoch": 0.3588229477163886, "grad_norm": 4.1988606452941895, "learning_rate": 9.868188782637444e-05, "loss": 1.3053779602050781, "step": 12700 }, { "epoch": 0.3593880232246034, "grad_norm": 3.454131841659546, "learning_rate": 9.867477436330579e-05, "loss": 1.2693844795227052, "step": 12720 }, { "epoch": 0.35995309873281817, "grad_norm": 4.505631923675537, "learning_rate": 9.866764201500156e-05, "loss": 1.31962308883667, "step": 12740 }, { "epoch": 0.36051817424103294, "grad_norm": 4.493458271026611, "learning_rate": 9.866049078422906e-05, "loss": 1.2880475997924805, "step": 12760 }, { "epoch": 0.36108324974924777, "grad_norm": 3.3199048042297363, "learning_rate": 9.865332067376284e-05, "loss": 1.3379878044128417, "step": 12780 }, { "epoch": 0.36164832525746254, "grad_norm": 4.604355812072754, "learning_rate": 9.864613168638486e-05, "loss": 1.39208927154541, "step": 12800 }, { "epoch": 0.3622134007656773, "grad_norm": 3.227435827255249, "learning_rate": 9.863892382488433e-05, "loss": 1.4264691352844239, "step": 12820 }, { "epoch": 0.3627784762738921, "grad_norm": 2.5071003437042236, "learning_rate": 9.863169709205782e-05, "loss": 1.3667313575744628, "step": 12840 }, { "epoch": 0.36334355178210687, "grad_norm": 3.5558366775512695, "learning_rate": 9.862445149070924e-05, "loss": 1.4056679725646972, "step": 12860 }, { "epoch": 0.3639086272903217, "grad_norm": 4.003350734710693, "learning_rate": 9.861718702364976e-05, "loss": 1.372144603729248, "step": 12880 }, { "epoch": 0.36447370279853647, "grad_norm": 5.164278030395508, "learning_rate": 9.860990369369793e-05, "loss": 1.4750750541687012, "step": 12900 }, { "epoch": 0.36503877830675124, "grad_norm": 2.0444672107696533, "learning_rate": 9.86026015036796e-05, "loss": 1.3186439514160155, "step": 12920 }, { "epoch": 0.365603853814966, "grad_norm": 3.848510503768921, "learning_rate": 9.859528045642792e-05, "loss": 1.4566253662109374, "step": 12940 }, { "epoch": 0.3661689293231808, "grad_norm": 3.296499490737915, "learning_rate": 9.858794055478337e-05, "loss": 1.3018409729003906, "step": 12960 }, { "epoch": 0.3667340048313956, "grad_norm": 2.8423011302948, "learning_rate": 9.858058180159378e-05, "loss": 1.3571032524108886, "step": 12980 }, { "epoch": 0.3672990803396104, "grad_norm": 2.48158597946167, "learning_rate": 9.857320419971419e-05, "loss": 1.1846652984619142, "step": 13000 }, { "epoch": 0.36786415584782517, "grad_norm": 3.2550573348999023, "learning_rate": 9.856580775200708e-05, "loss": 1.2964235305786134, "step": 13020 }, { "epoch": 0.36842923135603994, "grad_norm": 3.312535524368286, "learning_rate": 9.855839246134217e-05, "loss": 1.2996530532836914, "step": 13040 }, { "epoch": 0.3689943068642547, "grad_norm": 3.0673134326934814, "learning_rate": 9.855095833059649e-05, "loss": 1.349312686920166, "step": 13060 }, { "epoch": 0.36955938237246955, "grad_norm": 4.399865627288818, "learning_rate": 9.85435053626544e-05, "loss": 1.2573426246643067, "step": 13080 }, { "epoch": 0.3701244578806843, "grad_norm": 3.0610721111297607, "learning_rate": 9.853603356040758e-05, "loss": 1.2525577545166016, "step": 13100 }, { "epoch": 0.3706895333888991, "grad_norm": 4.299171447753906, "learning_rate": 9.852854292675499e-05, "loss": 1.280881690979004, "step": 13120 }, { "epoch": 0.37125460889711387, "grad_norm": 3.2595460414886475, "learning_rate": 9.85210334646029e-05, "loss": 1.2076571464538575, "step": 13140 }, { "epoch": 0.37181968440532864, "grad_norm": 3.4049596786499023, "learning_rate": 9.851350517686488e-05, "loss": 1.3790071487426758, "step": 13160 }, { "epoch": 0.3723847599135435, "grad_norm": 3.7476561069488525, "learning_rate": 9.850595806646185e-05, "loss": 1.3527795791625976, "step": 13180 }, { "epoch": 0.37294983542175825, "grad_norm": 3.490649461746216, "learning_rate": 9.8498392136322e-05, "loss": 1.3115869522094727, "step": 13200 }, { "epoch": 0.373514910929973, "grad_norm": 3.168811321258545, "learning_rate": 9.849080738938079e-05, "loss": 1.3116622924804688, "step": 13220 }, { "epoch": 0.3740799864381878, "grad_norm": 3.0161426067352295, "learning_rate": 9.848320382858103e-05, "loss": 1.182014274597168, "step": 13240 }, { "epoch": 0.37464506194640257, "grad_norm": 4.628612995147705, "learning_rate": 9.84755814568728e-05, "loss": 1.3701236724853516, "step": 13260 }, { "epoch": 0.3752101374546174, "grad_norm": 3.4868128299713135, "learning_rate": 9.846794027721352e-05, "loss": 1.3069832801818848, "step": 13280 }, { "epoch": 0.3757752129628322, "grad_norm": 3.603566884994507, "learning_rate": 9.846028029256782e-05, "loss": 1.2874613761901856, "step": 13300 }, { "epoch": 0.37634028847104695, "grad_norm": 4.602649211883545, "learning_rate": 9.845260150590774e-05, "loss": 1.2997098922729493, "step": 13320 }, { "epoch": 0.3769053639792617, "grad_norm": 3.017279863357544, "learning_rate": 9.844490392021253e-05, "loss": 1.3114617347717286, "step": 13340 }, { "epoch": 0.3774704394874765, "grad_norm": 3.143261671066284, "learning_rate": 9.843718753846878e-05, "loss": 1.3852926254272462, "step": 13360 }, { "epoch": 0.3780355149956913, "grad_norm": 4.851656913757324, "learning_rate": 9.842945236367034e-05, "loss": 1.2884034156799316, "step": 13380 }, { "epoch": 0.3786005905039061, "grad_norm": 3.591752052307129, "learning_rate": 9.842169839881836e-05, "loss": 1.332421112060547, "step": 13400 }, { "epoch": 0.37916566601212087, "grad_norm": 3.641772747039795, "learning_rate": 9.841392564692132e-05, "loss": 1.339711856842041, "step": 13420 }, { "epoch": 0.37973074152033565, "grad_norm": 2.9617576599121094, "learning_rate": 9.840613411099491e-05, "loss": 1.356488037109375, "step": 13440 }, { "epoch": 0.3802958170285504, "grad_norm": 3.357184648513794, "learning_rate": 9.839832379406218e-05, "loss": 1.2448564529418946, "step": 13460 }, { "epoch": 0.38086089253676525, "grad_norm": 2.785212755203247, "learning_rate": 9.839049469915344e-05, "loss": 1.2590556144714355, "step": 13480 }, { "epoch": 0.38142596804498, "grad_norm": 4.261466026306152, "learning_rate": 9.838264682930627e-05, "loss": 1.401529312133789, "step": 13500 }, { "epoch": 0.3819910435531948, "grad_norm": 2.7355523109436035, "learning_rate": 9.837478018756557e-05, "loss": 1.36390962600708, "step": 13520 }, { "epoch": 0.38255611906140957, "grad_norm": 4.396437644958496, "learning_rate": 9.83668947769835e-05, "loss": 1.2710393905639648, "step": 13540 }, { "epoch": 0.38312119456962435, "grad_norm": 2.3943169116973877, "learning_rate": 9.83589906006195e-05, "loss": 1.2772363662719726, "step": 13560 }, { "epoch": 0.3836862700778392, "grad_norm": 3.710517168045044, "learning_rate": 9.835106766154029e-05, "loss": 1.2697209358215331, "step": 13580 }, { "epoch": 0.38425134558605395, "grad_norm": 3.1500580310821533, "learning_rate": 9.834312596281989e-05, "loss": 1.4340381622314453, "step": 13600 }, { "epoch": 0.3848164210942687, "grad_norm": 3.3638815879821777, "learning_rate": 9.833516550753958e-05, "loss": 1.3857770919799806, "step": 13620 }, { "epoch": 0.3853814966024835, "grad_norm": 2.3400707244873047, "learning_rate": 9.832718629878793e-05, "loss": 1.3197705268859863, "step": 13640 }, { "epoch": 0.38594657211069827, "grad_norm": 2.7391602993011475, "learning_rate": 9.831918833966077e-05, "loss": 1.3394137382507325, "step": 13660 }, { "epoch": 0.3865116476189131, "grad_norm": 2.829043388366699, "learning_rate": 9.831117163326121e-05, "loss": 1.364285373687744, "step": 13680 }, { "epoch": 0.3870767231271279, "grad_norm": 3.8550527095794678, "learning_rate": 9.830313618269964e-05, "loss": 1.3532725334167481, "step": 13700 }, { "epoch": 0.38764179863534265, "grad_norm": 2.653538703918457, "learning_rate": 9.829508199109372e-05, "loss": 1.215583610534668, "step": 13720 }, { "epoch": 0.3882068741435574, "grad_norm": 2.2524611949920654, "learning_rate": 9.828700906156838e-05, "loss": 1.2327509880065919, "step": 13740 }, { "epoch": 0.3887719496517722, "grad_norm": 4.26747989654541, "learning_rate": 9.827891739725583e-05, "loss": 1.3086332321166991, "step": 13760 }, { "epoch": 0.389337025159987, "grad_norm": 4.207830905914307, "learning_rate": 9.827080700129553e-05, "loss": 1.279616355895996, "step": 13780 }, { "epoch": 0.3899021006682018, "grad_norm": 4.055178642272949, "learning_rate": 9.826267787683422e-05, "loss": 1.2542346000671387, "step": 13800 }, { "epoch": 0.3904671761764166, "grad_norm": 4.174699783325195, "learning_rate": 9.825453002702589e-05, "loss": 1.2712906837463378, "step": 13820 }, { "epoch": 0.39103225168463135, "grad_norm": 2.9817311763763428, "learning_rate": 9.824636345503184e-05, "loss": 1.3601544380187989, "step": 13840 }, { "epoch": 0.3915973271928461, "grad_norm": 2.383310556411743, "learning_rate": 9.82381781640206e-05, "loss": 1.2825637817382813, "step": 13860 }, { "epoch": 0.39216240270106095, "grad_norm": 3.364361047744751, "learning_rate": 9.822997415716792e-05, "loss": 1.2228384017944336, "step": 13880 }, { "epoch": 0.3927274782092757, "grad_norm": 2.8250436782836914, "learning_rate": 9.822175143765691e-05, "loss": 1.3160369873046875, "step": 13900 }, { "epoch": 0.3932925537174905, "grad_norm": 2.110105514526367, "learning_rate": 9.821351000867786e-05, "loss": 1.2543886184692383, "step": 13920 }, { "epoch": 0.3938576292257053, "grad_norm": 3.4589829444885254, "learning_rate": 9.820524987342836e-05, "loss": 1.294994831085205, "step": 13940 }, { "epoch": 0.39442270473392005, "grad_norm": 2.8320279121398926, "learning_rate": 9.819697103511323e-05, "loss": 1.3610896110534667, "step": 13960 }, { "epoch": 0.3949877802421349, "grad_norm": 4.372771739959717, "learning_rate": 9.818867349694458e-05, "loss": 1.4134285926818848, "step": 13980 }, { "epoch": 0.39555285575034965, "grad_norm": 3.2427940368652344, "learning_rate": 9.818035726214173e-05, "loss": 1.2714646339416504, "step": 14000 }, { "epoch": 0.3961179312585644, "grad_norm": 2.3396334648132324, "learning_rate": 9.81720223339313e-05, "loss": 1.292407512664795, "step": 14020 }, { "epoch": 0.3966830067667792, "grad_norm": 3.6140732765197754, "learning_rate": 9.816366871554716e-05, "loss": 1.2359285354614258, "step": 14040 }, { "epoch": 0.397248082274994, "grad_norm": 4.783915042877197, "learning_rate": 9.815529641023038e-05, "loss": 1.2808999061584472, "step": 14060 }, { "epoch": 0.3978131577832088, "grad_norm": 3.3025972843170166, "learning_rate": 9.814690542122933e-05, "loss": 1.2642712593078613, "step": 14080 }, { "epoch": 0.3983782332914236, "grad_norm": 2.417799234390259, "learning_rate": 9.813849575179963e-05, "loss": 1.3871830940246581, "step": 14100 }, { "epoch": 0.39894330879963835, "grad_norm": 3.7398550510406494, "learning_rate": 9.81300674052041e-05, "loss": 1.2884698867797852, "step": 14120 }, { "epoch": 0.3995083843078531, "grad_norm": 2.7741222381591797, "learning_rate": 9.812162038471286e-05, "loss": 1.2246121406555175, "step": 14140 }, { "epoch": 0.4000734598160679, "grad_norm": 2.935237169265747, "learning_rate": 9.811315469360324e-05, "loss": 1.2907029151916505, "step": 14160 }, { "epoch": 0.40063853532428273, "grad_norm": 2.465486526489258, "learning_rate": 9.810467033515984e-05, "loss": 1.171745777130127, "step": 14180 }, { "epoch": 0.4012036108324975, "grad_norm": 4.840959548950195, "learning_rate": 9.80961673126745e-05, "loss": 1.228367233276367, "step": 14200 }, { "epoch": 0.4017686863407123, "grad_norm": 3.1314640045166016, "learning_rate": 9.808764562944627e-05, "loss": 1.2462671279907227, "step": 14220 }, { "epoch": 0.40233376184892705, "grad_norm": 3.9897749423980713, "learning_rate": 9.807910528878149e-05, "loss": 1.3728610038757325, "step": 14240 }, { "epoch": 0.4028988373571418, "grad_norm": 2.710853338241577, "learning_rate": 9.807054629399366e-05, "loss": 1.3809951782226562, "step": 14260 }, { "epoch": 0.40346391286535666, "grad_norm": 3.1410715579986572, "learning_rate": 9.806196864840363e-05, "loss": 1.329177188873291, "step": 14280 }, { "epoch": 0.40402898837357143, "grad_norm": 3.5955111980438232, "learning_rate": 9.805337235533937e-05, "loss": 1.3803080558776855, "step": 14300 }, { "epoch": 0.4045940638817862, "grad_norm": 2.750093936920166, "learning_rate": 9.804475741813618e-05, "loss": 1.2348065376281738, "step": 14320 }, { "epoch": 0.405159139390001, "grad_norm": 3.8573389053344727, "learning_rate": 9.803612384013654e-05, "loss": 1.238777256011963, "step": 14340 }, { "epoch": 0.40572421489821575, "grad_norm": 4.165417194366455, "learning_rate": 9.802747162469018e-05, "loss": 1.3833311080932618, "step": 14360 }, { "epoch": 0.4062892904064306, "grad_norm": 3.9659199714660645, "learning_rate": 9.801880077515403e-05, "loss": 1.3305070877075196, "step": 14380 }, { "epoch": 0.40685436591464536, "grad_norm": 4.473455429077148, "learning_rate": 9.801011129489232e-05, "loss": 1.2695226669311523, "step": 14400 }, { "epoch": 0.40741944142286013, "grad_norm": 3.969116687774658, "learning_rate": 9.800140318727644e-05, "loss": 1.2736468315124512, "step": 14420 }, { "epoch": 0.4079845169310749, "grad_norm": 4.9039812088012695, "learning_rate": 9.799267645568503e-05, "loss": 1.4142005920410157, "step": 14440 }, { "epoch": 0.4085495924392897, "grad_norm": 3.4023890495300293, "learning_rate": 9.798393110350396e-05, "loss": 1.2351613998413087, "step": 14460 }, { "epoch": 0.4091146679475045, "grad_norm": 5.210245609283447, "learning_rate": 9.797516713412636e-05, "loss": 1.2698805809020997, "step": 14480 }, { "epoch": 0.4096797434557193, "grad_norm": 4.264780044555664, "learning_rate": 9.796638455095249e-05, "loss": 1.3101717948913574, "step": 14500 }, { "epoch": 0.41024481896393405, "grad_norm": 3.334567070007324, "learning_rate": 9.795758335738991e-05, "loss": 1.1433403968811036, "step": 14520 }, { "epoch": 0.41080989447214883, "grad_norm": 3.4355204105377197, "learning_rate": 9.794876355685338e-05, "loss": 1.271192741394043, "step": 14540 }, { "epoch": 0.4113749699803636, "grad_norm": 2.6011500358581543, "learning_rate": 9.793992515276489e-05, "loss": 1.2261575698852538, "step": 14560 }, { "epoch": 0.41194004548857843, "grad_norm": 3.4026896953582764, "learning_rate": 9.793106814855364e-05, "loss": 1.2750940322875977, "step": 14580 }, { "epoch": 0.4125051209967932, "grad_norm": 2.9352524280548096, "learning_rate": 9.7922192547656e-05, "loss": 1.3186975479125977, "step": 14600 }, { "epoch": 0.413070196505008, "grad_norm": 2.5643136501312256, "learning_rate": 9.791329835351564e-05, "loss": 1.251546859741211, "step": 14620 }, { "epoch": 0.41363527201322275, "grad_norm": 3.0023791790008545, "learning_rate": 9.790438556958338e-05, "loss": 1.30363130569458, "step": 14640 }, { "epoch": 0.41420034752143753, "grad_norm": 3.289336681365967, "learning_rate": 9.789545419931729e-05, "loss": 1.3533214569091796, "step": 14660 }, { "epoch": 0.41476542302965236, "grad_norm": 2.909613609313965, "learning_rate": 9.788650424618261e-05, "loss": 1.2872384071350098, "step": 14680 }, { "epoch": 0.41533049853786713, "grad_norm": 4.771299839019775, "learning_rate": 9.787753571365186e-05, "loss": 1.3337624549865723, "step": 14700 }, { "epoch": 0.4158955740460819, "grad_norm": 2.933763027191162, "learning_rate": 9.786854860520469e-05, "loss": 1.2032249450683594, "step": 14720 }, { "epoch": 0.4164606495542967, "grad_norm": 4.346441745758057, "learning_rate": 9.785954292432801e-05, "loss": 1.2603441238403321, "step": 14740 }, { "epoch": 0.41702572506251145, "grad_norm": 2.390451431274414, "learning_rate": 9.785051867451589e-05, "loss": 1.2825172424316407, "step": 14760 }, { "epoch": 0.4175908005707263, "grad_norm": 3.2570769786834717, "learning_rate": 9.784147585926966e-05, "loss": 1.272130298614502, "step": 14780 }, { "epoch": 0.41815587607894106, "grad_norm": 3.1208977699279785, "learning_rate": 9.783241448209781e-05, "loss": 1.191380214691162, "step": 14800 }, { "epoch": 0.41872095158715583, "grad_norm": 3.6468722820281982, "learning_rate": 9.782333454651606e-05, "loss": 1.2473644256591796, "step": 14820 }, { "epoch": 0.4192860270953706, "grad_norm": 2.7104804515838623, "learning_rate": 9.781423605604729e-05, "loss": 1.3413784980773926, "step": 14840 }, { "epoch": 0.4198511026035854, "grad_norm": 2.537104845046997, "learning_rate": 9.780511901422164e-05, "loss": 1.325687789916992, "step": 14860 }, { "epoch": 0.4204161781118002, "grad_norm": 2.6235713958740234, "learning_rate": 9.779598342457641e-05, "loss": 1.2273995399475097, "step": 14880 }, { "epoch": 0.420981253620015, "grad_norm": 4.353083610534668, "learning_rate": 9.778682929065607e-05, "loss": 1.314941692352295, "step": 14900 }, { "epoch": 0.42154632912822976, "grad_norm": 4.0640740394592285, "learning_rate": 9.777765661601234e-05, "loss": 1.2816516876220703, "step": 14920 }, { "epoch": 0.42211140463644453, "grad_norm": 3.7273340225219727, "learning_rate": 9.776846540420411e-05, "loss": 1.2239627838134766, "step": 14940 }, { "epoch": 0.4226764801446593, "grad_norm": 3.673238754272461, "learning_rate": 9.775925565879746e-05, "loss": 1.2147732734680177, "step": 14960 }, { "epoch": 0.42324155565287414, "grad_norm": 2.2748360633850098, "learning_rate": 9.775002738336565e-05, "loss": 1.3185152053833007, "step": 14980 }, { "epoch": 0.4238066311610889, "grad_norm": 2.6280295848846436, "learning_rate": 9.774078058148914e-05, "loss": 1.2845267295837401, "step": 15000 }, { "epoch": 0.4243717066693037, "grad_norm": 3.7784769535064697, "learning_rate": 9.773151525675561e-05, "loss": 1.3060141563415528, "step": 15020 }, { "epoch": 0.42493678217751846, "grad_norm": 3.2269256114959717, "learning_rate": 9.772223141275987e-05, "loss": 1.1980603218078614, "step": 15040 }, { "epoch": 0.42550185768573323, "grad_norm": 3.536105155944824, "learning_rate": 9.771292905310394e-05, "loss": 1.2846307754516602, "step": 15060 }, { "epoch": 0.42606693319394806, "grad_norm": 2.666185140609741, "learning_rate": 9.770360818139703e-05, "loss": 1.2904624938964844, "step": 15080 }, { "epoch": 0.42663200870216283, "grad_norm": 2.688156843185425, "learning_rate": 9.769426880125554e-05, "loss": 1.3136631965637207, "step": 15100 }, { "epoch": 0.4271970842103776, "grad_norm": 3.1851730346679688, "learning_rate": 9.768491091630304e-05, "loss": 1.2985455513000488, "step": 15120 }, { "epoch": 0.4277621597185924, "grad_norm": 4.4763288497924805, "learning_rate": 9.767553453017024e-05, "loss": 1.2271142959594727, "step": 15140 }, { "epoch": 0.42832723522680716, "grad_norm": 3.187681198120117, "learning_rate": 9.766613964649509e-05, "loss": 1.3160374641418457, "step": 15160 }, { "epoch": 0.428892310735022, "grad_norm": 2.482314348220825, "learning_rate": 9.765672626892272e-05, "loss": 1.230980396270752, "step": 15180 }, { "epoch": 0.42945738624323676, "grad_norm": 1.961078405380249, "learning_rate": 9.764729440110538e-05, "loss": 1.2145679473876954, "step": 15200 }, { "epoch": 0.43002246175145153, "grad_norm": 3.4945173263549805, "learning_rate": 9.763784404670253e-05, "loss": 1.2812154769897461, "step": 15220 }, { "epoch": 0.4305875372596663, "grad_norm": 3.819425106048584, "learning_rate": 9.762837520938077e-05, "loss": 1.294482707977295, "step": 15240 }, { "epoch": 0.4311526127678811, "grad_norm": 3.0035974979400635, "learning_rate": 9.761888789281395e-05, "loss": 1.200248908996582, "step": 15260 }, { "epoch": 0.4317176882760959, "grad_norm": 2.7814438343048096, "learning_rate": 9.7609382100683e-05, "loss": 1.2912436485290528, "step": 15280 }, { "epoch": 0.4322827637843107, "grad_norm": 3.4022669792175293, "learning_rate": 9.759985783667607e-05, "loss": 1.2914501190185548, "step": 15300 }, { "epoch": 0.43284783929252546, "grad_norm": 2.567099094390869, "learning_rate": 9.759031510448843e-05, "loss": 1.2513360977172852, "step": 15320 }, { "epoch": 0.43341291480074023, "grad_norm": 3.593312978744507, "learning_rate": 9.75807539078226e-05, "loss": 1.2613862037658692, "step": 15340 }, { "epoch": 0.433977990308955, "grad_norm": 3.6640372276306152, "learning_rate": 9.757117425038816e-05, "loss": 1.1997286796569824, "step": 15360 }, { "epoch": 0.43454306581716984, "grad_norm": 2.955524444580078, "learning_rate": 9.756157613590194e-05, "loss": 1.292067527770996, "step": 15380 }, { "epoch": 0.4351081413253846, "grad_norm": 2.178025245666504, "learning_rate": 9.755195956808787e-05, "loss": 1.2893711090087892, "step": 15400 }, { "epoch": 0.4356732168335994, "grad_norm": 3.9908103942871094, "learning_rate": 9.754232455067707e-05, "loss": 1.2838824272155762, "step": 15420 }, { "epoch": 0.43623829234181416, "grad_norm": 2.7442851066589355, "learning_rate": 9.753267108740783e-05, "loss": 1.3255204200744628, "step": 15440 }, { "epoch": 0.43680336785002893, "grad_norm": 3.1883862018585205, "learning_rate": 9.752299918202556e-05, "loss": 1.2476465225219726, "step": 15460 }, { "epoch": 0.43736844335824376, "grad_norm": 3.788839101791382, "learning_rate": 9.751330883828284e-05, "loss": 1.283113384246826, "step": 15480 }, { "epoch": 0.43793351886645854, "grad_norm": 3.486377716064453, "learning_rate": 9.750360005993943e-05, "loss": 1.229874324798584, "step": 15500 }, { "epoch": 0.4384985943746733, "grad_norm": 3.180294990539551, "learning_rate": 9.749387285076222e-05, "loss": 1.269042682647705, "step": 15520 }, { "epoch": 0.4390636698828881, "grad_norm": 3.8481357097625732, "learning_rate": 9.748412721452524e-05, "loss": 1.2387628555297852, "step": 15540 }, { "epoch": 0.43962874539110286, "grad_norm": 3.430572748184204, "learning_rate": 9.747436315500967e-05, "loss": 1.2648953437805175, "step": 15560 }, { "epoch": 0.4401938208993177, "grad_norm": 4.467489719390869, "learning_rate": 9.746458067600388e-05, "loss": 1.239261531829834, "step": 15580 }, { "epoch": 0.44075889640753246, "grad_norm": 2.1983821392059326, "learning_rate": 9.745477978130332e-05, "loss": 1.193742275238037, "step": 15600 }, { "epoch": 0.44132397191574724, "grad_norm": 3.5689709186553955, "learning_rate": 9.744496047471065e-05, "loss": 1.2191571235656737, "step": 15620 }, { "epoch": 0.441889047423962, "grad_norm": 3.833233594894409, "learning_rate": 9.743512276003563e-05, "loss": 1.2310237884521484, "step": 15640 }, { "epoch": 0.4424541229321768, "grad_norm": 3.7587032318115234, "learning_rate": 9.742526664109519e-05, "loss": 1.2904047966003418, "step": 15660 }, { "epoch": 0.4430191984403916, "grad_norm": 2.8898046016693115, "learning_rate": 9.741539212171338e-05, "loss": 1.3116506576538085, "step": 15680 }, { "epoch": 0.4435842739486064, "grad_norm": 3.166142463684082, "learning_rate": 9.740549920572138e-05, "loss": 1.271690273284912, "step": 15700 }, { "epoch": 0.44414934945682116, "grad_norm": 3.5525355339050293, "learning_rate": 9.739558789695755e-05, "loss": 1.2730921745300292, "step": 15720 }, { "epoch": 0.44471442496503594, "grad_norm": 2.5789036750793457, "learning_rate": 9.738565819926734e-05, "loss": 1.269394588470459, "step": 15740 }, { "epoch": 0.4452795004732507, "grad_norm": 3.8229010105133057, "learning_rate": 9.737571011650337e-05, "loss": 1.2366049766540528, "step": 15760 }, { "epoch": 0.44584457598146554, "grad_norm": 3.8310325145721436, "learning_rate": 9.736574365252538e-05, "loss": 1.2392356872558594, "step": 15780 }, { "epoch": 0.4464096514896803, "grad_norm": 2.8123884201049805, "learning_rate": 9.735575881120023e-05, "loss": 1.3403023719787597, "step": 15800 }, { "epoch": 0.4469747269978951, "grad_norm": 3.946784019470215, "learning_rate": 9.73457555964019e-05, "loss": 1.2153889656066894, "step": 15820 }, { "epoch": 0.44753980250610986, "grad_norm": 2.4717257022857666, "learning_rate": 9.733573401201157e-05, "loss": 1.2733667373657227, "step": 15840 }, { "epoch": 0.44810487801432464, "grad_norm": 2.5757992267608643, "learning_rate": 9.732569406191744e-05, "loss": 1.2618145942687988, "step": 15860 }, { "epoch": 0.44866995352253947, "grad_norm": 3.967637538909912, "learning_rate": 9.731563575001494e-05, "loss": 1.257247543334961, "step": 15880 }, { "epoch": 0.44923502903075424, "grad_norm": 2.870833396911621, "learning_rate": 9.730555908020656e-05, "loss": 1.2662821769714356, "step": 15900 }, { "epoch": 0.449800104538969, "grad_norm": 2.7375147342681885, "learning_rate": 9.72954640564019e-05, "loss": 1.218651294708252, "step": 15920 }, { "epoch": 0.4503651800471838, "grad_norm": 4.815446376800537, "learning_rate": 9.728535068251776e-05, "loss": 1.2620469093322755, "step": 15940 }, { "epoch": 0.45093025555539856, "grad_norm": 3.0715110301971436, "learning_rate": 9.727521896247797e-05, "loss": 1.2828779220581055, "step": 15960 }, { "epoch": 0.4514953310636134, "grad_norm": 3.49069881439209, "learning_rate": 9.726506890021354e-05, "loss": 1.2878911972045899, "step": 15980 }, { "epoch": 0.45206040657182817, "grad_norm": 2.188021659851074, "learning_rate": 9.725490049966255e-05, "loss": 1.1968610763549805, "step": 16000 }, { "epoch": 0.45262548208004294, "grad_norm": 3.4583053588867188, "learning_rate": 9.724471376477022e-05, "loss": 1.2269221305847169, "step": 16020 }, { "epoch": 0.4531905575882577, "grad_norm": 2.7596089839935303, "learning_rate": 9.723450869948892e-05, "loss": 1.3168354988098145, "step": 16040 }, { "epoch": 0.45375563309647254, "grad_norm": 4.1324381828308105, "learning_rate": 9.722428530777806e-05, "loss": 1.2943413734436036, "step": 16060 }, { "epoch": 0.4543207086046873, "grad_norm": 4.210691928863525, "learning_rate": 9.72140435936042e-05, "loss": 1.2821020126342773, "step": 16080 }, { "epoch": 0.4548857841129021, "grad_norm": 3.1942200660705566, "learning_rate": 9.7203783560941e-05, "loss": 1.325893020629883, "step": 16100 }, { "epoch": 0.45545085962111687, "grad_norm": 3.8105156421661377, "learning_rate": 9.719350521376925e-05, "loss": 1.2634745597839356, "step": 16120 }, { "epoch": 0.45601593512933164, "grad_norm": 3.5012266635894775, "learning_rate": 9.718320855607681e-05, "loss": 1.329091453552246, "step": 16140 }, { "epoch": 0.45658101063754647, "grad_norm": 4.730634689331055, "learning_rate": 9.717289359185865e-05, "loss": 1.2312539100646973, "step": 16160 }, { "epoch": 0.45714608614576124, "grad_norm": 3.6029391288757324, "learning_rate": 9.71625603251169e-05, "loss": 1.3690411567687988, "step": 16180 }, { "epoch": 0.457711161653976, "grad_norm": 2.9954495429992676, "learning_rate": 9.715220875986071e-05, "loss": 1.2387349128723144, "step": 16200 }, { "epoch": 0.4582762371621908, "grad_norm": 3.305361747741699, "learning_rate": 9.714183890010637e-05, "loss": 1.170444393157959, "step": 16220 }, { "epoch": 0.45884131267040557, "grad_norm": 4.307089805603027, "learning_rate": 9.713145074987726e-05, "loss": 1.3016263008117677, "step": 16240 }, { "epoch": 0.4594063881786204, "grad_norm": 2.771280288696289, "learning_rate": 9.712104431320386e-05, "loss": 1.305325984954834, "step": 16260 }, { "epoch": 0.45997146368683517, "grad_norm": 3.312912940979004, "learning_rate": 9.711061959412374e-05, "loss": 1.2480890274047851, "step": 16280 }, { "epoch": 0.46053653919504994, "grad_norm": 3.306471347808838, "learning_rate": 9.710017659668158e-05, "loss": 1.2253501892089844, "step": 16300 }, { "epoch": 0.4611016147032647, "grad_norm": 3.7613229751586914, "learning_rate": 9.708971532492914e-05, "loss": 1.2549135208129882, "step": 16320 }, { "epoch": 0.4616666902114795, "grad_norm": 3.374439239501953, "learning_rate": 9.707923578292523e-05, "loss": 1.270406150817871, "step": 16340 }, { "epoch": 0.4622317657196943, "grad_norm": 2.4773597717285156, "learning_rate": 9.706873797473586e-05, "loss": 1.2945353507995605, "step": 16360 }, { "epoch": 0.4627968412279091, "grad_norm": 3.1473119258880615, "learning_rate": 9.7058221904434e-05, "loss": 1.2491276741027832, "step": 16380 }, { "epoch": 0.46336191673612387, "grad_norm": 2.6877024173736572, "learning_rate": 9.704768757609977e-05, "loss": 1.245185661315918, "step": 16400 }, { "epoch": 0.46392699224433864, "grad_norm": 3.714726209640503, "learning_rate": 9.703713499382037e-05, "loss": 1.1960647583007813, "step": 16420 }, { "epoch": 0.4644920677525534, "grad_norm": 5.110629558563232, "learning_rate": 9.702656416169009e-05, "loss": 1.4344608306884765, "step": 16440 }, { "epoch": 0.46505714326076825, "grad_norm": 2.6432230472564697, "learning_rate": 9.701597508381028e-05, "loss": 1.240312385559082, "step": 16460 }, { "epoch": 0.465622218768983, "grad_norm": 2.5265579223632812, "learning_rate": 9.700536776428934e-05, "loss": 1.2833788871765137, "step": 16480 }, { "epoch": 0.4661872942771978, "grad_norm": 2.898273468017578, "learning_rate": 9.699474220724285e-05, "loss": 1.168332290649414, "step": 16500 }, { "epoch": 0.46675236978541257, "grad_norm": 3.375255584716797, "learning_rate": 9.698409841679334e-05, "loss": 1.1570181846618652, "step": 16520 }, { "epoch": 0.46731744529362734, "grad_norm": 4.367380142211914, "learning_rate": 9.697343639707053e-05, "loss": 1.223070240020752, "step": 16540 }, { "epoch": 0.46788252080184217, "grad_norm": 3.4191150665283203, "learning_rate": 9.696275615221111e-05, "loss": 1.2715524673461913, "step": 16560 }, { "epoch": 0.46844759631005695, "grad_norm": 2.7711198329925537, "learning_rate": 9.695205768635891e-05, "loss": 1.2422677993774414, "step": 16580 }, { "epoch": 0.4690126718182717, "grad_norm": 3.2883529663085938, "learning_rate": 9.694134100366479e-05, "loss": 1.1535399436950684, "step": 16600 }, { "epoch": 0.4695777473264865, "grad_norm": 4.747228622436523, "learning_rate": 9.693060610828672e-05, "loss": 1.1827269554138184, "step": 16620 }, { "epoch": 0.47014282283470127, "grad_norm": 2.204164505004883, "learning_rate": 9.691985300438971e-05, "loss": 1.3353718757629394, "step": 16640 }, { "epoch": 0.4707078983429161, "grad_norm": 3.2344882488250732, "learning_rate": 9.690908169614584e-05, "loss": 1.2717167854309082, "step": 16660 }, { "epoch": 0.47127297385113087, "grad_norm": 4.406016826629639, "learning_rate": 9.68982921877342e-05, "loss": 1.2040563583374024, "step": 16680 }, { "epoch": 0.47183804935934565, "grad_norm": 3.7973155975341797, "learning_rate": 9.688748448334107e-05, "loss": 1.1245112419128418, "step": 16700 }, { "epoch": 0.4724031248675604, "grad_norm": 4.049899101257324, "learning_rate": 9.687665858715965e-05, "loss": 1.2314355850219727, "step": 16720 }, { "epoch": 0.4729682003757752, "grad_norm": 3.8144826889038086, "learning_rate": 9.68658145033903e-05, "loss": 1.2143760681152345, "step": 16740 }, { "epoch": 0.47353327588399, "grad_norm": 2.9467225074768066, "learning_rate": 9.685495223624034e-05, "loss": 1.1294649124145508, "step": 16760 }, { "epoch": 0.4740983513922048, "grad_norm": 2.6290979385375977, "learning_rate": 9.684407178992428e-05, "loss": 1.333787441253662, "step": 16780 }, { "epoch": 0.47466342690041957, "grad_norm": 3.2511675357818604, "learning_rate": 9.683317316866354e-05, "loss": 1.241569709777832, "step": 16800 }, { "epoch": 0.47522850240863435, "grad_norm": 3.7387659549713135, "learning_rate": 9.682225637668669e-05, "loss": 1.2259676933288575, "step": 16820 }, { "epoch": 0.4757935779168491, "grad_norm": 3.0385079383850098, "learning_rate": 9.681132141822928e-05, "loss": 1.3095315933227538, "step": 16840 }, { "epoch": 0.47635865342506395, "grad_norm": 3.5995264053344727, "learning_rate": 9.6800368297534e-05, "loss": 1.2977353096008302, "step": 16860 }, { "epoch": 0.4769237289332787, "grad_norm": 4.349273681640625, "learning_rate": 9.678939701885048e-05, "loss": 1.2792762756347655, "step": 16880 }, { "epoch": 0.4774888044414935, "grad_norm": 4.568493366241455, "learning_rate": 9.677840758643547e-05, "loss": 1.2920076370239257, "step": 16900 }, { "epoch": 0.47805387994970827, "grad_norm": 3.466804265975952, "learning_rate": 9.676740000455273e-05, "loss": 1.1900196075439453, "step": 16920 }, { "epoch": 0.47861895545792305, "grad_norm": 3.019913911819458, "learning_rate": 9.675637427747309e-05, "loss": 1.217353916168213, "step": 16940 }, { "epoch": 0.4791840309661379, "grad_norm": 3.532066822052002, "learning_rate": 9.674533040947438e-05, "loss": 1.2658322334289551, "step": 16960 }, { "epoch": 0.47974910647435265, "grad_norm": 3.1002118587493896, "learning_rate": 9.67342684048415e-05, "loss": 1.1755453109741212, "step": 16980 }, { "epoch": 0.4803141819825674, "grad_norm": 3.6163063049316406, "learning_rate": 9.672318826786637e-05, "loss": 1.3406148910522462, "step": 17000 }, { "epoch": 0.4808792574907822, "grad_norm": 3.6704256534576416, "learning_rate": 9.671209000284795e-05, "loss": 1.3187335014343262, "step": 17020 }, { "epoch": 0.48144433299899697, "grad_norm": 2.76982045173645, "learning_rate": 9.670097361409225e-05, "loss": 1.1564640045166015, "step": 17040 }, { "epoch": 0.4820094085072118, "grad_norm": 4.0256123542785645, "learning_rate": 9.66898391059123e-05, "loss": 1.201673984527588, "step": 17060 }, { "epoch": 0.4825744840154266, "grad_norm": 2.581418752670288, "learning_rate": 9.667868648262812e-05, "loss": 1.2487850189208984, "step": 17080 }, { "epoch": 0.48313955952364135, "grad_norm": 3.314241409301758, "learning_rate": 9.666751574856685e-05, "loss": 1.2265445709228515, "step": 17100 }, { "epoch": 0.4837046350318561, "grad_norm": 4.340676307678223, "learning_rate": 9.665632690806254e-05, "loss": 1.245652675628662, "step": 17120 }, { "epoch": 0.4842697105400709, "grad_norm": 3.7944226264953613, "learning_rate": 9.66451199654564e-05, "loss": 1.2580971717834473, "step": 17140 }, { "epoch": 0.4848347860482857, "grad_norm": 3.1808533668518066, "learning_rate": 9.663389492509652e-05, "loss": 1.1617656707763673, "step": 17160 }, { "epoch": 0.4853998615565005, "grad_norm": 3.61660099029541, "learning_rate": 9.662265179133813e-05, "loss": 1.1919476509094238, "step": 17180 }, { "epoch": 0.4859649370647153, "grad_norm": 3.1014626026153564, "learning_rate": 9.661139056854342e-05, "loss": 1.175271987915039, "step": 17200 }, { "epoch": 0.48653001257293005, "grad_norm": 2.867961883544922, "learning_rate": 9.660011126108161e-05, "loss": 1.1889507293701171, "step": 17220 }, { "epoch": 0.4870950880811448, "grad_norm": 3.269253730773926, "learning_rate": 9.658881387332892e-05, "loss": 1.1679763793945312, "step": 17240 }, { "epoch": 0.48766016358935965, "grad_norm": 3.2208316326141357, "learning_rate": 9.657749840966863e-05, "loss": 1.1899333953857423, "step": 17260 }, { "epoch": 0.4882252390975744, "grad_norm": 2.2785634994506836, "learning_rate": 9.6566164874491e-05, "loss": 1.2997963905334473, "step": 17280 }, { "epoch": 0.4887903146057892, "grad_norm": 3.295969247817993, "learning_rate": 9.65548132721933e-05, "loss": 1.2790766716003419, "step": 17300 }, { "epoch": 0.489355390114004, "grad_norm": 2.8859469890594482, "learning_rate": 9.65434436071798e-05, "loss": 1.114296817779541, "step": 17320 }, { "epoch": 0.48992046562221875, "grad_norm": 4.054596900939941, "learning_rate": 9.653205588386183e-05, "loss": 1.240523624420166, "step": 17340 }, { "epoch": 0.4904855411304336, "grad_norm": 2.6683192253112793, "learning_rate": 9.652065010665768e-05, "loss": 1.2659207344055177, "step": 17360 }, { "epoch": 0.49105061663864835, "grad_norm": 3.6370174884796143, "learning_rate": 9.650922627999263e-05, "loss": 1.1715252876281739, "step": 17380 }, { "epoch": 0.4916156921468631, "grad_norm": 3.8434317111968994, "learning_rate": 9.649778440829904e-05, "loss": 1.1248855590820312, "step": 17400 }, { "epoch": 0.4921807676550779, "grad_norm": 2.875934362411499, "learning_rate": 9.648632449601618e-05, "loss": 1.2281975746154785, "step": 17420 }, { "epoch": 0.4927458431632927, "grad_norm": 2.515319347381592, "learning_rate": 9.647484654759037e-05, "loss": 1.1537465095520019, "step": 17440 }, { "epoch": 0.4933109186715075, "grad_norm": 3.060483932495117, "learning_rate": 9.646335056747493e-05, "loss": 1.2693918228149415, "step": 17460 }, { "epoch": 0.4938759941797223, "grad_norm": 3.832533359527588, "learning_rate": 9.645183656013014e-05, "loss": 1.1962859153747558, "step": 17480 }, { "epoch": 0.49444106968793705, "grad_norm": 3.941537857055664, "learning_rate": 9.644030453002333e-05, "loss": 1.2686962127685546, "step": 17500 }, { "epoch": 0.4950061451961518, "grad_norm": 1.9330395460128784, "learning_rate": 9.642875448162876e-05, "loss": 1.269239902496338, "step": 17520 }, { "epoch": 0.4955712207043666, "grad_norm": 3.7555932998657227, "learning_rate": 9.641718641942771e-05, "loss": 1.123356533050537, "step": 17540 }, { "epoch": 0.49613629621258143, "grad_norm": 3.7245335578918457, "learning_rate": 9.640560034790851e-05, "loss": 1.1523794174194335, "step": 17560 }, { "epoch": 0.4967013717207962, "grad_norm": 4.631481647491455, "learning_rate": 9.639399627156634e-05, "loss": 1.2245365142822267, "step": 17580 }, { "epoch": 0.497266447229011, "grad_norm": 2.5276436805725098, "learning_rate": 9.63823741949035e-05, "loss": 1.1816060066223144, "step": 17600 }, { "epoch": 0.49783152273722575, "grad_norm": 3.4966654777526855, "learning_rate": 9.637073412242919e-05, "loss": 1.1694398880004884, "step": 17620 }, { "epoch": 0.4983965982454405, "grad_norm": 2.7816946506500244, "learning_rate": 9.635907605865962e-05, "loss": 1.1661806106567383, "step": 17640 }, { "epoch": 0.49896167375365535, "grad_norm": 2.794555902481079, "learning_rate": 9.6347400008118e-05, "loss": 1.217679500579834, "step": 17660 }, { "epoch": 0.49952674926187013, "grad_norm": 3.2900919914245605, "learning_rate": 9.633570597533447e-05, "loss": 1.2726376533508301, "step": 17680 }, { "epoch": 0.5000918247700848, "grad_norm": 3.3712306022644043, "learning_rate": 9.63239939648462e-05, "loss": 1.1985581398010254, "step": 17700 }, { "epoch": 0.5006569002782997, "grad_norm": 4.10586404800415, "learning_rate": 9.63122639811973e-05, "loss": 1.2838337898254395, "step": 17720 }, { "epoch": 0.5012219757865145, "grad_norm": 2.7948012351989746, "learning_rate": 9.630051602893888e-05, "loss": 1.3111911773681642, "step": 17740 }, { "epoch": 0.5017870512947292, "grad_norm": 3.0208840370178223, "learning_rate": 9.628875011262899e-05, "loss": 1.3151878356933593, "step": 17760 }, { "epoch": 0.502352126802944, "grad_norm": 2.330130100250244, "learning_rate": 9.627696623683268e-05, "loss": 1.2046958923339843, "step": 17780 }, { "epoch": 0.5029172023111589, "grad_norm": 3.9373042583465576, "learning_rate": 9.626516440612195e-05, "loss": 1.2081060409545898, "step": 17800 }, { "epoch": 0.5034822778193736, "grad_norm": 3.0095319747924805, "learning_rate": 9.625334462507574e-05, "loss": 1.2024392127990722, "step": 17820 }, { "epoch": 0.5040473533275884, "grad_norm": 1.8494727611541748, "learning_rate": 9.624150689828003e-05, "loss": 1.246811866760254, "step": 17840 }, { "epoch": 0.5046124288358032, "grad_norm": 3.386075019836426, "learning_rate": 9.62296512303277e-05, "loss": 1.2340991020202636, "step": 17860 }, { "epoch": 0.505177504344018, "grad_norm": 2.9544334411621094, "learning_rate": 9.62177776258186e-05, "loss": 1.2436477661132812, "step": 17880 }, { "epoch": 0.5057425798522328, "grad_norm": 3.9816901683807373, "learning_rate": 9.620588608935955e-05, "loss": 1.186993408203125, "step": 17900 }, { "epoch": 0.5063076553604475, "grad_norm": 3.9075136184692383, "learning_rate": 9.619397662556435e-05, "loss": 1.2427995681762696, "step": 17920 }, { "epoch": 0.5068727308686624, "grad_norm": 3.232119083404541, "learning_rate": 9.618204923905369e-05, "loss": 1.2750746726989746, "step": 17940 }, { "epoch": 0.5074378063768771, "grad_norm": 2.6496012210845947, "learning_rate": 9.617010393445529e-05, "loss": 1.177126407623291, "step": 17960 }, { "epoch": 0.5080028818850919, "grad_norm": 3.1925899982452393, "learning_rate": 9.615814071640376e-05, "loss": 1.1604344367980957, "step": 17980 }, { "epoch": 0.5085679573933067, "grad_norm": 2.618422508239746, "learning_rate": 9.61461595895407e-05, "loss": 1.2498910903930665, "step": 18000 }, { "epoch": 0.5091330329015215, "grad_norm": 4.6840643882751465, "learning_rate": 9.613416055851467e-05, "loss": 1.2208030700683594, "step": 18020 }, { "epoch": 0.5096981084097363, "grad_norm": 2.5754997730255127, "learning_rate": 9.61221436279811e-05, "loss": 1.1995566368103028, "step": 18040 }, { "epoch": 0.510263183917951, "grad_norm": 2.52156662940979, "learning_rate": 9.611010880260245e-05, "loss": 1.3123780250549317, "step": 18060 }, { "epoch": 0.5108282594261658, "grad_norm": 3.202179193496704, "learning_rate": 9.609805608704808e-05, "loss": 1.241464614868164, "step": 18080 }, { "epoch": 0.5113933349343807, "grad_norm": 2.0307624340057373, "learning_rate": 9.60859854859943e-05, "loss": 1.1215895652770995, "step": 18100 }, { "epoch": 0.5119584104425954, "grad_norm": 3.44840669631958, "learning_rate": 9.607389700412437e-05, "loss": 1.2415206909179688, "step": 18120 }, { "epoch": 0.5125234859508102, "grad_norm": 4.489277362823486, "learning_rate": 9.606179064612848e-05, "loss": 1.131345844268799, "step": 18140 }, { "epoch": 0.5130885614590249, "grad_norm": 3.383732795715332, "learning_rate": 9.604966641670374e-05, "loss": 1.3431761741638184, "step": 18160 }, { "epoch": 0.5136536369672398, "grad_norm": 3.113757848739624, "learning_rate": 9.60375243205542e-05, "loss": 1.2513912200927735, "step": 18180 }, { "epoch": 0.5142187124754546, "grad_norm": 2.9718642234802246, "learning_rate": 9.602536436239088e-05, "loss": 1.323676872253418, "step": 18200 }, { "epoch": 0.5147837879836693, "grad_norm": 3.691070318222046, "learning_rate": 9.601318654693166e-05, "loss": 1.3025980949401856, "step": 18220 }, { "epoch": 0.5153488634918841, "grad_norm": 3.1577558517456055, "learning_rate": 9.600099087890142e-05, "loss": 1.3344097137451172, "step": 18240 }, { "epoch": 0.5159139390000989, "grad_norm": 4.084220886230469, "learning_rate": 9.598877736303191e-05, "loss": 1.1698972702026367, "step": 18260 }, { "epoch": 0.5164790145083137, "grad_norm": 2.6011476516723633, "learning_rate": 9.597654600406186e-05, "loss": 1.2280047416687012, "step": 18280 }, { "epoch": 0.5170440900165285, "grad_norm": 4.129403591156006, "learning_rate": 9.596429680673687e-05, "loss": 1.2616541862487793, "step": 18300 }, { "epoch": 0.5176091655247432, "grad_norm": 3.5026843547821045, "learning_rate": 9.595202977580948e-05, "loss": 1.223594570159912, "step": 18320 }, { "epoch": 0.5181742410329581, "grad_norm": 3.5131232738494873, "learning_rate": 9.593974491603919e-05, "loss": 1.2751783370971679, "step": 18340 }, { "epoch": 0.5187393165411728, "grad_norm": 3.9443981647491455, "learning_rate": 9.592744223219232e-05, "loss": 1.1823659896850587, "step": 18360 }, { "epoch": 0.5193043920493876, "grad_norm": 3.3995258808135986, "learning_rate": 9.59151217290422e-05, "loss": 1.1423355102539063, "step": 18380 }, { "epoch": 0.5198694675576024, "grad_norm": 3.3438987731933594, "learning_rate": 9.590278341136905e-05, "loss": 1.2273934364318848, "step": 18400 }, { "epoch": 0.5204345430658172, "grad_norm": 2.788196563720703, "learning_rate": 9.589042728395998e-05, "loss": 1.1871584892272948, "step": 18420 }, { "epoch": 0.520999618574032, "grad_norm": 2.2505476474761963, "learning_rate": 9.5878053351609e-05, "loss": 1.2482570648193358, "step": 18440 }, { "epoch": 0.5215646940822467, "grad_norm": 4.503807544708252, "learning_rate": 9.586566161911708e-05, "loss": 1.224743938446045, "step": 18460 }, { "epoch": 0.5221297695904615, "grad_norm": 2.7816600799560547, "learning_rate": 9.585325209129206e-05, "loss": 1.253301239013672, "step": 18480 }, { "epoch": 0.5226948450986764, "grad_norm": 3.496615409851074, "learning_rate": 9.584082477294867e-05, "loss": 1.1997184753417969, "step": 18500 }, { "epoch": 0.5232599206068911, "grad_norm": 4.120483875274658, "learning_rate": 9.582837966890857e-05, "loss": 1.2783429145812988, "step": 18520 }, { "epoch": 0.5238249961151059, "grad_norm": 3.3090462684631348, "learning_rate": 9.581591678400032e-05, "loss": 1.2437036514282227, "step": 18540 }, { "epoch": 0.5243900716233206, "grad_norm": 2.7644283771514893, "learning_rate": 9.580343612305937e-05, "loss": 1.1782882690429688, "step": 18560 }, { "epoch": 0.5249551471315355, "grad_norm": 5.121026515960693, "learning_rate": 9.579093769092807e-05, "loss": 1.1886838912963866, "step": 18580 }, { "epoch": 0.5255202226397503, "grad_norm": 2.7856662273406982, "learning_rate": 9.577842149245566e-05, "loss": 1.2862894058227539, "step": 18600 }, { "epoch": 0.526085298147965, "grad_norm": 3.082134246826172, "learning_rate": 9.576588753249829e-05, "loss": 1.2195878982543946, "step": 18620 }, { "epoch": 0.5266503736561798, "grad_norm": 3.5387699604034424, "learning_rate": 9.575333581591895e-05, "loss": 1.1442955017089844, "step": 18640 }, { "epoch": 0.5272154491643946, "grad_norm": 3.5842719078063965, "learning_rate": 9.574076634758759e-05, "loss": 1.116472053527832, "step": 18660 }, { "epoch": 0.5277805246726094, "grad_norm": 3.473313808441162, "learning_rate": 9.572817913238102e-05, "loss": 1.1014322280883788, "step": 18680 }, { "epoch": 0.5283456001808242, "grad_norm": 3.6462182998657227, "learning_rate": 9.57155741751829e-05, "loss": 1.1991455078125, "step": 18700 }, { "epoch": 0.5289106756890389, "grad_norm": 3.153022289276123, "learning_rate": 9.570295148088385e-05, "loss": 1.2149731636047363, "step": 18720 }, { "epoch": 0.5294757511972538, "grad_norm": 2.691715955734253, "learning_rate": 9.569031105438128e-05, "loss": 1.1600509643554688, "step": 18740 }, { "epoch": 0.5300408267054685, "grad_norm": 2.4938769340515137, "learning_rate": 9.567765290057955e-05, "loss": 1.1762652397155762, "step": 18760 }, { "epoch": 0.5306059022136833, "grad_norm": 4.289146900177002, "learning_rate": 9.566497702438986e-05, "loss": 1.2353937149047851, "step": 18780 }, { "epoch": 0.5311709777218981, "grad_norm": 2.272881269454956, "learning_rate": 9.56522834307303e-05, "loss": 1.1607087135314942, "step": 18800 }, { "epoch": 0.5317360532301129, "grad_norm": 2.923788547515869, "learning_rate": 9.563957212452585e-05, "loss": 1.1496057510375977, "step": 18820 }, { "epoch": 0.5323011287383277, "grad_norm": 3.896435022354126, "learning_rate": 9.562684311070835e-05, "loss": 1.2617059707641602, "step": 18840 }, { "epoch": 0.5328662042465424, "grad_norm": 2.373147964477539, "learning_rate": 9.561409639421648e-05, "loss": 1.1771658897399901, "step": 18860 }, { "epoch": 0.5334312797547572, "grad_norm": 4.17665433883667, "learning_rate": 9.560133197999582e-05, "loss": 1.1980083465576172, "step": 18880 }, { "epoch": 0.5339963552629721, "grad_norm": 5.028891086578369, "learning_rate": 9.558854987299884e-05, "loss": 1.1716548919677734, "step": 18900 }, { "epoch": 0.5345614307711868, "grad_norm": 5.628077983856201, "learning_rate": 9.55757500781848e-05, "loss": 1.304315948486328, "step": 18920 }, { "epoch": 0.5351265062794016, "grad_norm": 2.3474550247192383, "learning_rate": 9.556293260051991e-05, "loss": 1.1752639770507813, "step": 18940 }, { "epoch": 0.5356915817876163, "grad_norm": 2.90698504447937, "learning_rate": 9.555009744497718e-05, "loss": 1.2246301651000977, "step": 18960 }, { "epoch": 0.5362566572958312, "grad_norm": 2.075631618499756, "learning_rate": 9.55372446165365e-05, "loss": 1.1502445220947266, "step": 18980 }, { "epoch": 0.536821732804046, "grad_norm": 2.6070361137390137, "learning_rate": 9.552437412018462e-05, "loss": 1.126774215698242, "step": 19000 }, { "epoch": 0.5373868083122607, "grad_norm": 5.824568271636963, "learning_rate": 9.551148596091515e-05, "loss": 1.168462085723877, "step": 19020 }, { "epoch": 0.5379518838204755, "grad_norm": 2.939209461212158, "learning_rate": 9.54985801437285e-05, "loss": 1.2797561645507813, "step": 19040 }, { "epoch": 0.5385169593286903, "grad_norm": 3.5530006885528564, "learning_rate": 9.548565667363203e-05, "loss": 1.1072229385375976, "step": 19060 }, { "epoch": 0.5390820348369051, "grad_norm": 3.473444700241089, "learning_rate": 9.547271555563986e-05, "loss": 1.2285836219787598, "step": 19080 }, { "epoch": 0.5396471103451199, "grad_norm": 2.4528818130493164, "learning_rate": 9.545975679477299e-05, "loss": 1.2891817092895508, "step": 19100 }, { "epoch": 0.5402121858533346, "grad_norm": 2.8753151893615723, "learning_rate": 9.544678039605929e-05, "loss": 1.198719596862793, "step": 19120 }, { "epoch": 0.5407772613615495, "grad_norm": 3.545985460281372, "learning_rate": 9.543378636453342e-05, "loss": 1.1617219924926758, "step": 19140 }, { "epoch": 0.5413423368697642, "grad_norm": 2.9745137691497803, "learning_rate": 9.542077470523692e-05, "loss": 1.2461181640625, "step": 19160 }, { "epoch": 0.541907412377979, "grad_norm": 3.1850125789642334, "learning_rate": 9.540774542321818e-05, "loss": 1.3202067375183106, "step": 19180 }, { "epoch": 0.5424724878861938, "grad_norm": 2.1810343265533447, "learning_rate": 9.539469852353238e-05, "loss": 1.1525290489196778, "step": 19200 }, { "epoch": 0.5430375633944086, "grad_norm": 3.9647278785705566, "learning_rate": 9.538163401124157e-05, "loss": 1.1687252044677734, "step": 19220 }, { "epoch": 0.5436026389026234, "grad_norm": 2.7569851875305176, "learning_rate": 9.536855189141462e-05, "loss": 1.2666114807128905, "step": 19240 }, { "epoch": 0.5441677144108381, "grad_norm": 2.353311777114868, "learning_rate": 9.535545216912725e-05, "loss": 1.2489352226257324, "step": 19260 }, { "epoch": 0.5447327899190529, "grad_norm": 4.102557182312012, "learning_rate": 9.5342334849462e-05, "loss": 1.1653132438659668, "step": 19280 }, { "epoch": 0.5452978654272678, "grad_norm": 4.128636360168457, "learning_rate": 9.532919993750822e-05, "loss": 1.1863117218017578, "step": 19300 }, { "epoch": 0.5458629409354825, "grad_norm": 3.602524995803833, "learning_rate": 9.53160474383621e-05, "loss": 1.174619197845459, "step": 19320 }, { "epoch": 0.5464280164436973, "grad_norm": 4.0687761306762695, "learning_rate": 9.530287735712666e-05, "loss": 1.2289848327636719, "step": 19340 }, { "epoch": 0.546993091951912, "grad_norm": 7.809090614318848, "learning_rate": 9.528968969891175e-05, "loss": 1.195305347442627, "step": 19360 }, { "epoch": 0.5475581674601269, "grad_norm": 2.9584121704101562, "learning_rate": 9.527648446883401e-05, "loss": 1.2578271865844726, "step": 19380 }, { "epoch": 0.5481232429683417, "grad_norm": 3.1439614295959473, "learning_rate": 9.526326167201691e-05, "loss": 1.2232824325561524, "step": 19400 }, { "epoch": 0.5486883184765564, "grad_norm": 2.7544782161712646, "learning_rate": 9.525002131359073e-05, "loss": 1.2977683067321777, "step": 19420 }, { "epoch": 0.5492533939847712, "grad_norm": 2.95920729637146, "learning_rate": 9.52367633986926e-05, "loss": 1.1324356079101563, "step": 19440 }, { "epoch": 0.549818469492986, "grad_norm": 3.2000839710235596, "learning_rate": 9.522348793246642e-05, "loss": 1.215992546081543, "step": 19460 }, { "epoch": 0.5503835450012008, "grad_norm": 2.9644508361816406, "learning_rate": 9.521019492006291e-05, "loss": 1.256586456298828, "step": 19480 }, { "epoch": 0.5509486205094156, "grad_norm": 3.5153145790100098, "learning_rate": 9.51968843666396e-05, "loss": 1.1733203887939454, "step": 19500 }, { "epoch": 0.5515136960176303, "grad_norm": 2.4777965545654297, "learning_rate": 9.518355627736082e-05, "loss": 1.2266655921936036, "step": 19520 }, { "epoch": 0.5520787715258452, "grad_norm": 3.1227991580963135, "learning_rate": 9.517021065739773e-05, "loss": 1.1416260719299316, "step": 19540 }, { "epoch": 0.5526438470340599, "grad_norm": 3.101471424102783, "learning_rate": 9.515684751192825e-05, "loss": 1.2465381622314453, "step": 19560 }, { "epoch": 0.5532089225422747, "grad_norm": 3.800257682800293, "learning_rate": 9.514346684613717e-05, "loss": 1.225588035583496, "step": 19580 }, { "epoch": 0.5537739980504895, "grad_norm": 2.4604077339172363, "learning_rate": 9.513006866521596e-05, "loss": 1.2582746505737306, "step": 19600 }, { "epoch": 0.5543390735587043, "grad_norm": 2.0859262943267822, "learning_rate": 9.5116652974363e-05, "loss": 1.2096041679382323, "step": 19620 }, { "epoch": 0.5549041490669191, "grad_norm": 3.360607147216797, "learning_rate": 9.510321977878343e-05, "loss": 1.1664464950561524, "step": 19640 }, { "epoch": 0.5554692245751338, "grad_norm": 3.816218852996826, "learning_rate": 9.508976908368913e-05, "loss": 1.2132569313049317, "step": 19660 }, { "epoch": 0.5560343000833486, "grad_norm": 3.137006998062134, "learning_rate": 9.507630089429883e-05, "loss": 1.2466067314147948, "step": 19680 }, { "epoch": 0.5565993755915635, "grad_norm": 4.07546329498291, "learning_rate": 9.506281521583804e-05, "loss": 1.2053840637207032, "step": 19700 }, { "epoch": 0.5571644510997782, "grad_norm": 3.129518508911133, "learning_rate": 9.504931205353902e-05, "loss": 1.2193957328796388, "step": 19720 }, { "epoch": 0.557729526607993, "grad_norm": 2.417759895324707, "learning_rate": 9.503579141264085e-05, "loss": 1.214765739440918, "step": 19740 }, { "epoch": 0.5582946021162077, "grad_norm": 4.362947463989258, "learning_rate": 9.502225329838938e-05, "loss": 1.2385251998901368, "step": 19760 }, { "epoch": 0.5588596776244226, "grad_norm": 3.8807637691497803, "learning_rate": 9.500869771603723e-05, "loss": 1.2063585281372071, "step": 19780 }, { "epoch": 0.5594247531326374, "grad_norm": 2.928049087524414, "learning_rate": 9.499512467084382e-05, "loss": 1.2622265815734863, "step": 19800 }, { "epoch": 0.5599898286408521, "grad_norm": 2.4946300983428955, "learning_rate": 9.498153416807531e-05, "loss": 1.1370651245117187, "step": 19820 }, { "epoch": 0.560554904149067, "grad_norm": 2.4082553386688232, "learning_rate": 9.496792621300468e-05, "loss": 1.1811104774475099, "step": 19840 }, { "epoch": 0.5611199796572817, "grad_norm": 3.804753065109253, "learning_rate": 9.49543008109116e-05, "loss": 1.2121612548828125, "step": 19860 }, { "epoch": 0.5616850551654965, "grad_norm": 4.2251105308532715, "learning_rate": 9.494065796708264e-05, "loss": 1.0859783172607422, "step": 19880 }, { "epoch": 0.5622501306737113, "grad_norm": 4.3200764656066895, "learning_rate": 9.492699768681103e-05, "loss": 1.175265407562256, "step": 19900 }, { "epoch": 0.562815206181926, "grad_norm": 2.7406070232391357, "learning_rate": 9.491331997539678e-05, "loss": 1.3109883308410644, "step": 19920 }, { "epoch": 0.5633802816901409, "grad_norm": 2.768087148666382, "learning_rate": 9.48996248381467e-05, "loss": 1.0860713958740233, "step": 19940 }, { "epoch": 0.5639453571983556, "grad_norm": 2.3330392837524414, "learning_rate": 9.488591228037433e-05, "loss": 1.172123622894287, "step": 19960 }, { "epoch": 0.5645104327065704, "grad_norm": 4.181493759155273, "learning_rate": 9.487218230739998e-05, "loss": 1.25642671585083, "step": 19980 }, { "epoch": 0.5650755082147852, "grad_norm": 2.776735305786133, "learning_rate": 9.485843492455073e-05, "loss": 1.2310086250305177, "step": 20000 }, { "epoch": 0.565640583723, "grad_norm": 4.1007585525512695, "learning_rate": 9.484467013716038e-05, "loss": 1.2191880226135254, "step": 20020 }, { "epoch": 0.5662056592312148, "grad_norm": 2.89688777923584, "learning_rate": 9.483088795056953e-05, "loss": 1.2568633079528808, "step": 20040 }, { "epoch": 0.5667707347394295, "grad_norm": 2.92113995552063, "learning_rate": 9.481708837012548e-05, "loss": 1.1787038803100587, "step": 20060 }, { "epoch": 0.5673358102476443, "grad_norm": 3.451305389404297, "learning_rate": 9.480327140118234e-05, "loss": 1.153952693939209, "step": 20080 }, { "epoch": 0.5679008857558592, "grad_norm": 2.9119482040405273, "learning_rate": 9.478943704910088e-05, "loss": 1.169605827331543, "step": 20100 }, { "epoch": 0.5684659612640739, "grad_norm": 2.5545475482940674, "learning_rate": 9.47755853192487e-05, "loss": 1.0922025680541991, "step": 20120 }, { "epoch": 0.5690310367722887, "grad_norm": 3.3967671394348145, "learning_rate": 9.476171621700009e-05, "loss": 1.1670223236083985, "step": 20140 }, { "epoch": 0.5695961122805034, "grad_norm": 2.7272493839263916, "learning_rate": 9.47478297477361e-05, "loss": 1.253341007232666, "step": 20160 }, { "epoch": 0.5701611877887183, "grad_norm": 3.0371041297912598, "learning_rate": 9.473392591684453e-05, "loss": 1.1801952362060546, "step": 20180 }, { "epoch": 0.5707262632969331, "grad_norm": 3.0803933143615723, "learning_rate": 9.47200047297199e-05, "loss": 1.2164899826049804, "step": 20200 }, { "epoch": 0.5712913388051478, "grad_norm": 4.029707431793213, "learning_rate": 9.470606619176345e-05, "loss": 1.0791903495788575, "step": 20220 }, { "epoch": 0.5718564143133626, "grad_norm": 3.1499829292297363, "learning_rate": 9.469211030838318e-05, "loss": 1.2119596481323243, "step": 20240 }, { "epoch": 0.5724214898215774, "grad_norm": 4.196051120758057, "learning_rate": 9.467813708499379e-05, "loss": 1.1867735862731934, "step": 20260 }, { "epoch": 0.5729865653297922, "grad_norm": 3.28163480758667, "learning_rate": 9.466414652701674e-05, "loss": 1.1982367515563965, "step": 20280 }, { "epoch": 0.573551640838007, "grad_norm": 2.6130809783935547, "learning_rate": 9.46501386398802e-05, "loss": 1.0777320861816406, "step": 20300 }, { "epoch": 0.5741167163462217, "grad_norm": 3.1238811016082764, "learning_rate": 9.463611342901906e-05, "loss": 1.218849277496338, "step": 20320 }, { "epoch": 0.5746817918544366, "grad_norm": 2.7101659774780273, "learning_rate": 9.462207089987494e-05, "loss": 1.1641975402832032, "step": 20340 }, { "epoch": 0.5752468673626513, "grad_norm": 3.139448404312134, "learning_rate": 9.460801105789618e-05, "loss": 1.0932342529296875, "step": 20360 }, { "epoch": 0.5758119428708661, "grad_norm": 2.13826322555542, "learning_rate": 9.459393390853782e-05, "loss": 1.2350099563598633, "step": 20380 }, { "epoch": 0.576377018379081, "grad_norm": 2.5202629566192627, "learning_rate": 9.457983945726161e-05, "loss": 1.1942258834838868, "step": 20400 }, { "epoch": 0.5769420938872957, "grad_norm": 5.6507720947265625, "learning_rate": 9.456572770953608e-05, "loss": 1.182151985168457, "step": 20420 }, { "epoch": 0.5775071693955105, "grad_norm": 3.650641441345215, "learning_rate": 9.455159867083638e-05, "loss": 1.2093636512756347, "step": 20440 }, { "epoch": 0.5780722449037252, "grad_norm": 3.898087739944458, "learning_rate": 9.453745234664441e-05, "loss": 1.2593118667602539, "step": 20460 }, { "epoch": 0.57863732041194, "grad_norm": 3.6263763904571533, "learning_rate": 9.452328874244882e-05, "loss": 1.2204686164855958, "step": 20480 }, { "epoch": 0.5792023959201549, "grad_norm": 3.4286561012268066, "learning_rate": 9.450910786374487e-05, "loss": 1.1930355072021483, "step": 20500 }, { "epoch": 0.5797674714283696, "grad_norm": 3.0702483654022217, "learning_rate": 9.449490971603458e-05, "loss": 1.1562658309936524, "step": 20520 }, { "epoch": 0.5803325469365844, "grad_norm": 2.3471693992614746, "learning_rate": 9.44806943048267e-05, "loss": 1.1584287643432618, "step": 20540 }, { "epoch": 0.5808976224447991, "grad_norm": 3.99210524559021, "learning_rate": 9.44664616356366e-05, "loss": 1.1452105522155762, "step": 20560 }, { "epoch": 0.581462697953014, "grad_norm": 3.1825625896453857, "learning_rate": 9.445221171398641e-05, "loss": 1.3103062629699707, "step": 20580 }, { "epoch": 0.5820277734612288, "grad_norm": 2.2690036296844482, "learning_rate": 9.443794454540492e-05, "loss": 1.1678762435913086, "step": 20600 }, { "epoch": 0.5825928489694435, "grad_norm": 3.8695859909057617, "learning_rate": 9.442366013542763e-05, "loss": 1.0753920555114747, "step": 20620 }, { "epoch": 0.5831579244776584, "grad_norm": 3.560879707336426, "learning_rate": 9.440935848959672e-05, "loss": 1.1460871696472168, "step": 20640 }, { "epoch": 0.5837229999858731, "grad_norm": 3.242415189743042, "learning_rate": 9.439503961346104e-05, "loss": 1.136295986175537, "step": 20660 }, { "epoch": 0.5842880754940879, "grad_norm": 2.273049831390381, "learning_rate": 9.438070351257617e-05, "loss": 1.1783709526062012, "step": 20680 }, { "epoch": 0.5848531510023027, "grad_norm": 3.0741937160491943, "learning_rate": 9.436635019250435e-05, "loss": 1.1880499839782714, "step": 20700 }, { "epoch": 0.5854182265105174, "grad_norm": 2.201155185699463, "learning_rate": 9.435197965881446e-05, "loss": 1.17103910446167, "step": 20720 }, { "epoch": 0.5859833020187323, "grad_norm": 2.9975290298461914, "learning_rate": 9.433759191708215e-05, "loss": 1.1417083740234375, "step": 20740 }, { "epoch": 0.586548377526947, "grad_norm": 3.484038829803467, "learning_rate": 9.432318697288964e-05, "loss": 1.1842876434326173, "step": 20760 }, { "epoch": 0.5871134530351618, "grad_norm": 3.22068452835083, "learning_rate": 9.430876483182593e-05, "loss": 1.1908416748046875, "step": 20780 }, { "epoch": 0.5876785285433767, "grad_norm": 2.7793989181518555, "learning_rate": 9.42943254994866e-05, "loss": 1.242291259765625, "step": 20800 }, { "epoch": 0.5882436040515914, "grad_norm": 2.196828842163086, "learning_rate": 9.427986898147396e-05, "loss": 1.142988109588623, "step": 20820 }, { "epoch": 0.5888086795598062, "grad_norm": 4.067251205444336, "learning_rate": 9.426539528339695e-05, "loss": 1.2434355735778808, "step": 20840 }, { "epoch": 0.5893737550680209, "grad_norm": 2.948864221572876, "learning_rate": 9.425090441087121e-05, "loss": 1.2397734642028808, "step": 20860 }, { "epoch": 0.5899388305762358, "grad_norm": 2.5829100608825684, "learning_rate": 9.423639636951902e-05, "loss": 1.1714550018310548, "step": 20880 }, { "epoch": 0.5905039060844506, "grad_norm": 3.090205192565918, "learning_rate": 9.422187116496934e-05, "loss": 1.1613765716552735, "step": 20900 }, { "epoch": 0.5910689815926653, "grad_norm": 2.2054970264434814, "learning_rate": 9.420732880285776e-05, "loss": 1.1711240768432618, "step": 20920 }, { "epoch": 0.5916340571008801, "grad_norm": 3.616583824157715, "learning_rate": 9.419276928882654e-05, "loss": 1.153905200958252, "step": 20940 }, { "epoch": 0.5921991326090948, "grad_norm": 3.228001594543457, "learning_rate": 9.417819262852461e-05, "loss": 1.195093536376953, "step": 20960 }, { "epoch": 0.5927642081173097, "grad_norm": 3.690208911895752, "learning_rate": 9.416359882760756e-05, "loss": 1.2373431205749512, "step": 20980 }, { "epoch": 0.5933292836255245, "grad_norm": 3.822737216949463, "learning_rate": 9.414898789173758e-05, "loss": 1.233492946624756, "step": 21000 }, { "epoch": 0.5938943591337392, "grad_norm": 3.0884358882904053, "learning_rate": 9.413435982658354e-05, "loss": 1.2893274307250977, "step": 21020 }, { "epoch": 0.594459434641954, "grad_norm": 3.9946341514587402, "learning_rate": 9.411971463782099e-05, "loss": 1.1734413146972655, "step": 21040 }, { "epoch": 0.5950245101501688, "grad_norm": 2.510533094406128, "learning_rate": 9.410505233113207e-05, "loss": 1.279682731628418, "step": 21060 }, { "epoch": 0.5955895856583836, "grad_norm": 3.5866239070892334, "learning_rate": 9.409037291220557e-05, "loss": 1.2300843238830566, "step": 21080 }, { "epoch": 0.5961546611665984, "grad_norm": 3.2413828372955322, "learning_rate": 9.407567638673693e-05, "loss": 1.0502992630004884, "step": 21100 }, { "epoch": 0.5967197366748132, "grad_norm": 2.718778133392334, "learning_rate": 9.406096276042826e-05, "loss": 1.1942917823791503, "step": 21120 }, { "epoch": 0.597284812183028, "grad_norm": 3.911129951477051, "learning_rate": 9.404623203898823e-05, "loss": 1.0949110031127929, "step": 21140 }, { "epoch": 0.5978498876912427, "grad_norm": 3.776017427444458, "learning_rate": 9.403148422813222e-05, "loss": 1.3301783561706544, "step": 21160 }, { "epoch": 0.5984149631994575, "grad_norm": 4.868062973022461, "learning_rate": 9.401671933358218e-05, "loss": 1.2617758750915526, "step": 21180 }, { "epoch": 0.5989800387076724, "grad_norm": 1.8522148132324219, "learning_rate": 9.400193736106673e-05, "loss": 1.1084506034851074, "step": 21200 }, { "epoch": 0.5995451142158871, "grad_norm": 3.227789878845215, "learning_rate": 9.398713831632109e-05, "loss": 1.1331701278686523, "step": 21220 }, { "epoch": 0.6001101897241019, "grad_norm": 3.035306692123413, "learning_rate": 9.397232220508714e-05, "loss": 1.1767949104309081, "step": 21240 }, { "epoch": 0.6006752652323166, "grad_norm": 4.314642906188965, "learning_rate": 9.395748903311332e-05, "loss": 1.0673460960388184, "step": 21260 }, { "epoch": 0.6012403407405315, "grad_norm": 2.6369383335113525, "learning_rate": 9.394263880615473e-05, "loss": 1.1627432823181152, "step": 21280 }, { "epoch": 0.6018054162487463, "grad_norm": 3.2315428256988525, "learning_rate": 9.392777152997311e-05, "loss": 1.3029950141906739, "step": 21300 }, { "epoch": 0.602370491756961, "grad_norm": 3.747938632965088, "learning_rate": 9.391288721033676e-05, "loss": 1.1862641334533692, "step": 21320 }, { "epoch": 0.6029355672651758, "grad_norm": 3.2638907432556152, "learning_rate": 9.389798585302064e-05, "loss": 1.1876097679138184, "step": 21340 }, { "epoch": 0.6035006427733905, "grad_norm": 2.7325754165649414, "learning_rate": 9.388306746380628e-05, "loss": 1.1761985778808595, "step": 21360 }, { "epoch": 0.6040657182816054, "grad_norm": 2.989497661590576, "learning_rate": 9.386813204848184e-05, "loss": 1.1681604385375977, "step": 21380 }, { "epoch": 0.6046307937898202, "grad_norm": 2.7948145866394043, "learning_rate": 9.385317961284211e-05, "loss": 1.157413864135742, "step": 21400 }, { "epoch": 0.6051958692980349, "grad_norm": 3.902559995651245, "learning_rate": 9.383821016268842e-05, "loss": 1.1875669479370117, "step": 21420 }, { "epoch": 0.6057609448062498, "grad_norm": 3.381715774536133, "learning_rate": 9.382322370382876e-05, "loss": 1.2677498817443849, "step": 21440 }, { "epoch": 0.6063260203144645, "grad_norm": 4.555493354797363, "learning_rate": 9.380822024207772e-05, "loss": 1.236974334716797, "step": 21460 }, { "epoch": 0.6068910958226793, "grad_norm": 3.4268336296081543, "learning_rate": 9.379319978325641e-05, "loss": 1.2310321807861329, "step": 21480 }, { "epoch": 0.6074561713308941, "grad_norm": 4.593026638031006, "learning_rate": 9.377816233319263e-05, "loss": 1.2598967552185059, "step": 21500 }, { "epoch": 0.6080212468391089, "grad_norm": 2.884852409362793, "learning_rate": 9.376310789772074e-05, "loss": 1.132223129272461, "step": 21520 }, { "epoch": 0.6085863223473237, "grad_norm": 3.735715389251709, "learning_rate": 9.374803648268167e-05, "loss": 1.1465303421020507, "step": 21540 }, { "epoch": 0.6091513978555384, "grad_norm": 3.9315619468688965, "learning_rate": 9.373294809392293e-05, "loss": 1.196207046508789, "step": 21560 }, { "epoch": 0.6097164733637532, "grad_norm": 3.456834316253662, "learning_rate": 9.371784273729866e-05, "loss": 1.1939019203186034, "step": 21580 }, { "epoch": 0.6102815488719681, "grad_norm": 3.3253862857818604, "learning_rate": 9.370272041866955e-05, "loss": 1.2148083686828612, "step": 21600 }, { "epoch": 0.6108466243801828, "grad_norm": 2.3267695903778076, "learning_rate": 9.368758114390288e-05, "loss": 1.085935688018799, "step": 21620 }, { "epoch": 0.6114116998883976, "grad_norm": 3.0227832794189453, "learning_rate": 9.367242491887252e-05, "loss": 1.1549819946289062, "step": 21640 }, { "epoch": 0.6119767753966123, "grad_norm": 3.205632448196411, "learning_rate": 9.36572517494589e-05, "loss": 1.0893731117248535, "step": 21660 }, { "epoch": 0.6125418509048272, "grad_norm": 3.3289830684661865, "learning_rate": 9.364206164154901e-05, "loss": 1.1388432502746582, "step": 21680 }, { "epoch": 0.613106926413042, "grad_norm": 2.943690776824951, "learning_rate": 9.362685460103646e-05, "loss": 1.1759793281555175, "step": 21700 }, { "epoch": 0.6136720019212567, "grad_norm": 1.839065670967102, "learning_rate": 9.361163063382139e-05, "loss": 1.14395112991333, "step": 21720 }, { "epoch": 0.6142370774294715, "grad_norm": 3.240880012512207, "learning_rate": 9.359638974581053e-05, "loss": 1.2091687202453614, "step": 21740 }, { "epoch": 0.6148021529376863, "grad_norm": 3.822199583053589, "learning_rate": 9.358113194291715e-05, "loss": 1.1407074928283691, "step": 21760 }, { "epoch": 0.6153672284459011, "grad_norm": 3.0230154991149902, "learning_rate": 9.35658572310611e-05, "loss": 1.1391435623168946, "step": 21780 }, { "epoch": 0.6159323039541159, "grad_norm": 2.930220603942871, "learning_rate": 9.355056561616877e-05, "loss": 1.201925563812256, "step": 21800 }, { "epoch": 0.6164973794623306, "grad_norm": 4.001004695892334, "learning_rate": 9.353525710417317e-05, "loss": 1.0597633361816405, "step": 21820 }, { "epoch": 0.6170624549705455, "grad_norm": 3.290403366088867, "learning_rate": 9.351993170101377e-05, "loss": 1.1250479698181153, "step": 21840 }, { "epoch": 0.6176275304787602, "grad_norm": 2.904928207397461, "learning_rate": 9.350458941263669e-05, "loss": 1.230992317199707, "step": 21860 }, { "epoch": 0.618192605986975, "grad_norm": 2.355818271636963, "learning_rate": 9.348923024499452e-05, "loss": 1.2138873100280763, "step": 21880 }, { "epoch": 0.6187576814951898, "grad_norm": 3.4591782093048096, "learning_rate": 9.347385420404646e-05, "loss": 1.1205592155456543, "step": 21900 }, { "epoch": 0.6193227570034046, "grad_norm": 2.485274314880371, "learning_rate": 9.345846129575821e-05, "loss": 1.1265619277954102, "step": 21920 }, { "epoch": 0.6198878325116194, "grad_norm": 3.744344711303711, "learning_rate": 9.344305152610206e-05, "loss": 1.1201146125793457, "step": 21940 }, { "epoch": 0.6204529080198341, "grad_norm": 3.219454288482666, "learning_rate": 9.342762490105682e-05, "loss": 1.1275481224060058, "step": 21960 }, { "epoch": 0.6210179835280489, "grad_norm": 2.8198599815368652, "learning_rate": 9.341218142660779e-05, "loss": 1.2001996994018556, "step": 21980 }, { "epoch": 0.6215830590362638, "grad_norm": 3.725487232208252, "learning_rate": 9.33967211087469e-05, "loss": 1.266980266571045, "step": 22000 }, { "epoch": 0.6221481345444785, "grad_norm": 3.4252445697784424, "learning_rate": 9.338124395347257e-05, "loss": 1.1646670341491698, "step": 22020 }, { "epoch": 0.6227132100526933, "grad_norm": 3.124967336654663, "learning_rate": 9.336574996678973e-05, "loss": 1.2022172927856445, "step": 22040 }, { "epoch": 0.623278285560908, "grad_norm": 2.7689411640167236, "learning_rate": 9.335023915470989e-05, "loss": 1.187053108215332, "step": 22060 }, { "epoch": 0.6238433610691229, "grad_norm": 4.002249240875244, "learning_rate": 9.333471152325103e-05, "loss": 1.1218992233276368, "step": 22080 }, { "epoch": 0.6244084365773377, "grad_norm": 2.4110236167907715, "learning_rate": 9.33191670784377e-05, "loss": 1.1125144004821776, "step": 22100 }, { "epoch": 0.6249735120855524, "grad_norm": 1.807568907737732, "learning_rate": 9.330360582630097e-05, "loss": 1.1663103103637695, "step": 22120 }, { "epoch": 0.6255385875937672, "grad_norm": 2.390479564666748, "learning_rate": 9.328802777287842e-05, "loss": 1.1402843475341797, "step": 22140 }, { "epoch": 0.626103663101982, "grad_norm": 3.5968832969665527, "learning_rate": 9.327243292421415e-05, "loss": 1.1760102272033692, "step": 22160 }, { "epoch": 0.6266687386101968, "grad_norm": 2.6485958099365234, "learning_rate": 9.325682128635875e-05, "loss": 1.033609390258789, "step": 22180 }, { "epoch": 0.6272338141184116, "grad_norm": 2.852144956588745, "learning_rate": 9.324119286536938e-05, "loss": 1.1224122047424316, "step": 22200 }, { "epoch": 0.6277988896266263, "grad_norm": 2.8011486530303955, "learning_rate": 9.322554766730969e-05, "loss": 1.1269078254699707, "step": 22220 }, { "epoch": 0.6283639651348412, "grad_norm": 3.1025447845458984, "learning_rate": 9.32098856982498e-05, "loss": 1.0921232223510742, "step": 22240 }, { "epoch": 0.6289290406430559, "grad_norm": 3.1929562091827393, "learning_rate": 9.319420696426638e-05, "loss": 1.1999906539916991, "step": 22260 }, { "epoch": 0.6294941161512707, "grad_norm": 2.3112425804138184, "learning_rate": 9.31785114714426e-05, "loss": 1.204923725128174, "step": 22280 }, { "epoch": 0.6300591916594855, "grad_norm": 4.218932628631592, "learning_rate": 9.316279922586813e-05, "loss": 1.1443449974060058, "step": 22300 }, { "epoch": 0.6306242671677003, "grad_norm": 2.977776288986206, "learning_rate": 9.314707023363912e-05, "loss": 1.1640196800231934, "step": 22320 }, { "epoch": 0.6311893426759151, "grad_norm": 3.4345691204071045, "learning_rate": 9.313132450085823e-05, "loss": 1.2277626037597655, "step": 22340 }, { "epoch": 0.6317544181841298, "grad_norm": 3.1076278686523438, "learning_rate": 9.311556203363463e-05, "loss": 1.1314867973327636, "step": 22360 }, { "epoch": 0.6323194936923446, "grad_norm": 3.636561393737793, "learning_rate": 9.309978283808399e-05, "loss": 1.1071114540100098, "step": 22380 }, { "epoch": 0.6328845692005595, "grad_norm": 2.8774731159210205, "learning_rate": 9.308398692032841e-05, "loss": 1.1765236854553223, "step": 22400 }, { "epoch": 0.6334496447087742, "grad_norm": 3.8195817470550537, "learning_rate": 9.306817428649653e-05, "loss": 1.1971356391906738, "step": 22420 }, { "epoch": 0.634014720216989, "grad_norm": 3.0323376655578613, "learning_rate": 9.305234494272348e-05, "loss": 1.1234700202941894, "step": 22440 }, { "epoch": 0.6345797957252037, "grad_norm": 2.7886581420898438, "learning_rate": 9.303649889515085e-05, "loss": 1.0638008117675781, "step": 22460 }, { "epoch": 0.6351448712334186, "grad_norm": 3.6937508583068848, "learning_rate": 9.302063614992672e-05, "loss": 1.1237104415893555, "step": 22480 }, { "epoch": 0.6357099467416334, "grad_norm": 2.716778516769409, "learning_rate": 9.300475671320564e-05, "loss": 1.0928509712219239, "step": 22500 }, { "epoch": 0.6362750222498481, "grad_norm": 4.046789169311523, "learning_rate": 9.298886059114865e-05, "loss": 1.1093276977539062, "step": 22520 }, { "epoch": 0.6368400977580629, "grad_norm": 3.3688559532165527, "learning_rate": 9.297294778992326e-05, "loss": 1.1539340019226074, "step": 22540 }, { "epoch": 0.6374051732662777, "grad_norm": 3.445300579071045, "learning_rate": 9.295701831570344e-05, "loss": 1.2129650115966797, "step": 22560 }, { "epoch": 0.6379702487744925, "grad_norm": 3.0556209087371826, "learning_rate": 9.294107217466965e-05, "loss": 1.0455276489257812, "step": 22580 }, { "epoch": 0.6385353242827073, "grad_norm": 3.6190924644470215, "learning_rate": 9.292510937300877e-05, "loss": 1.1988415718078613, "step": 22600 }, { "epoch": 0.639100399790922, "grad_norm": 3.2846767902374268, "learning_rate": 9.290912991691422e-05, "loss": 1.1477157592773437, "step": 22620 }, { "epoch": 0.6396654752991369, "grad_norm": 3.9127936363220215, "learning_rate": 9.289313381258583e-05, "loss": 1.2086974143981934, "step": 22640 }, { "epoch": 0.6402305508073516, "grad_norm": 2.7484800815582275, "learning_rate": 9.287712106622988e-05, "loss": 1.2438410758972167, "step": 22660 }, { "epoch": 0.6407956263155664, "grad_norm": 2.7191851139068604, "learning_rate": 9.286109168405914e-05, "loss": 1.1545339584350587, "step": 22680 }, { "epoch": 0.6413607018237812, "grad_norm": 3.2638237476348877, "learning_rate": 9.284504567229282e-05, "loss": 1.1316978454589843, "step": 22700 }, { "epoch": 0.641925777331996, "grad_norm": 3.905663251876831, "learning_rate": 9.282898303715657e-05, "loss": 1.162180519104004, "step": 22720 }, { "epoch": 0.6424908528402108, "grad_norm": 3.951326847076416, "learning_rate": 9.281290378488252e-05, "loss": 1.2726449966430664, "step": 22740 }, { "epoch": 0.6430559283484255, "grad_norm": 3.5144364833831787, "learning_rate": 9.279680792170921e-05, "loss": 1.1757299423217773, "step": 22760 }, { "epoch": 0.6436210038566403, "grad_norm": 3.5135791301727295, "learning_rate": 9.278069545388167e-05, "loss": 1.1614282608032227, "step": 22780 }, { "epoch": 0.6441860793648552, "grad_norm": 3.074740409851074, "learning_rate": 9.276456638765132e-05, "loss": 1.1106781959533691, "step": 22800 }, { "epoch": 0.6447511548730699, "grad_norm": 2.7861766815185547, "learning_rate": 9.274842072927607e-05, "loss": 1.171926784515381, "step": 22820 }, { "epoch": 0.6453162303812847, "grad_norm": 3.2704389095306396, "learning_rate": 9.273225848502022e-05, "loss": 1.185202693939209, "step": 22840 }, { "epoch": 0.6458813058894994, "grad_norm": 2.695735454559326, "learning_rate": 9.271607966115454e-05, "loss": 1.1261791229248046, "step": 22860 }, { "epoch": 0.6464463813977143, "grad_norm": 3.190171957015991, "learning_rate": 9.269988426395624e-05, "loss": 1.2000380516052247, "step": 22880 }, { "epoch": 0.6470114569059291, "grad_norm": 3.323068380355835, "learning_rate": 9.268367229970891e-05, "loss": 1.1389333724975585, "step": 22900 }, { "epoch": 0.6475765324141438, "grad_norm": 2.4625186920166016, "learning_rate": 9.266744377470263e-05, "loss": 1.1608047485351562, "step": 22920 }, { "epoch": 0.6481416079223586, "grad_norm": 4.597689628601074, "learning_rate": 9.265119869523384e-05, "loss": 1.2487784385681153, "step": 22940 }, { "epoch": 0.6487066834305734, "grad_norm": 3.409426212310791, "learning_rate": 9.263493706760547e-05, "loss": 1.1774642944335938, "step": 22960 }, { "epoch": 0.6492717589387882, "grad_norm": 3.0845069885253906, "learning_rate": 9.261865889812683e-05, "loss": 1.0828008651733398, "step": 22980 }, { "epoch": 0.649836834447003, "grad_norm": 3.1442935466766357, "learning_rate": 9.260236419311366e-05, "loss": 1.0993816375732421, "step": 23000 }, { "epoch": 0.6504019099552177, "grad_norm": 3.155329942703247, "learning_rate": 9.258605295888809e-05, "loss": 1.1836557388305664, "step": 23020 }, { "epoch": 0.6509669854634326, "grad_norm": 3.3172168731689453, "learning_rate": 9.256972520177872e-05, "loss": 1.128534984588623, "step": 23040 }, { "epoch": 0.6515320609716473, "grad_norm": 2.4101226329803467, "learning_rate": 9.255338092812049e-05, "loss": 1.2471450805664062, "step": 23060 }, { "epoch": 0.6520971364798621, "grad_norm": 4.00584077835083, "learning_rate": 9.253702014425482e-05, "loss": 1.0682209968566894, "step": 23080 }, { "epoch": 0.652662211988077, "grad_norm": 3.4119246006011963, "learning_rate": 9.252064285652949e-05, "loss": 1.1900989532470703, "step": 23100 }, { "epoch": 0.6532272874962917, "grad_norm": 3.2326650619506836, "learning_rate": 9.250424907129867e-05, "loss": 1.1813941955566407, "step": 23120 }, { "epoch": 0.6537923630045065, "grad_norm": 4.475712776184082, "learning_rate": 9.248783879492298e-05, "loss": 1.175790023803711, "step": 23140 }, { "epoch": 0.6543574385127212, "grad_norm": 2.159485101699829, "learning_rate": 9.247141203376938e-05, "loss": 1.1438680648803712, "step": 23160 }, { "epoch": 0.654922514020936, "grad_norm": 3.4765639305114746, "learning_rate": 9.245496879421132e-05, "loss": 1.1883389472961425, "step": 23180 }, { "epoch": 0.6554875895291509, "grad_norm": 4.606746673583984, "learning_rate": 9.243850908262852e-05, "loss": 1.078860378265381, "step": 23200 }, { "epoch": 0.6560526650373656, "grad_norm": 2.750706195831299, "learning_rate": 9.242203290540719e-05, "loss": 1.1544534683227539, "step": 23220 }, { "epoch": 0.6566177405455804, "grad_norm": 3.0930261611938477, "learning_rate": 9.240554026893988e-05, "loss": 1.1746087074279785, "step": 23240 }, { "epoch": 0.6571828160537951, "grad_norm": 2.5582244396209717, "learning_rate": 9.238903117962553e-05, "loss": 1.0910493850708007, "step": 23260 }, { "epoch": 0.65774789156201, "grad_norm": 3.175555944442749, "learning_rate": 9.237250564386948e-05, "loss": 1.0961616516113282, "step": 23280 }, { "epoch": 0.6583129670702248, "grad_norm": 2.434067726135254, "learning_rate": 9.235596366808343e-05, "loss": 1.1253371238708496, "step": 23300 }, { "epoch": 0.6588780425784395, "grad_norm": 3.859502077102661, "learning_rate": 9.23394052586855e-05, "loss": 1.1911304473876954, "step": 23320 }, { "epoch": 0.6594431180866543, "grad_norm": 2.764928102493286, "learning_rate": 9.232283042210013e-05, "loss": 1.139876937866211, "step": 23340 }, { "epoch": 0.6600081935948691, "grad_norm": 4.049333572387695, "learning_rate": 9.230623916475817e-05, "loss": 1.1180710792541504, "step": 23360 }, { "epoch": 0.6605732691030839, "grad_norm": 2.5349347591400146, "learning_rate": 9.228963149309681e-05, "loss": 1.1190397262573242, "step": 23380 }, { "epoch": 0.6611383446112987, "grad_norm": 2.48097562789917, "learning_rate": 9.227300741355968e-05, "loss": 1.1513540267944335, "step": 23400 }, { "epoch": 0.6617034201195134, "grad_norm": 4.29408597946167, "learning_rate": 9.225636693259667e-05, "loss": 1.1354475975036622, "step": 23420 }, { "epoch": 0.6622684956277283, "grad_norm": 3.2476606369018555, "learning_rate": 9.223971005666412e-05, "loss": 1.2088683128356934, "step": 23440 }, { "epoch": 0.662833571135943, "grad_norm": 3.0969481468200684, "learning_rate": 9.22230367922247e-05, "loss": 1.150352668762207, "step": 23460 }, { "epoch": 0.6633986466441578, "grad_norm": 4.1526780128479, "learning_rate": 9.220634714574743e-05, "loss": 1.0730902671813964, "step": 23480 }, { "epoch": 0.6639637221523726, "grad_norm": 2.901805877685547, "learning_rate": 9.218964112370769e-05, "loss": 1.143744945526123, "step": 23500 }, { "epoch": 0.6645287976605874, "grad_norm": 2.920626401901245, "learning_rate": 9.217291873258722e-05, "loss": 1.0918846130371094, "step": 23520 }, { "epoch": 0.6650938731688022, "grad_norm": 3.8826637268066406, "learning_rate": 9.215617997887413e-05, "loss": 1.1995015144348145, "step": 23540 }, { "epoch": 0.6656589486770169, "grad_norm": 3.4034039974212646, "learning_rate": 9.213942486906286e-05, "loss": 1.3044843673706055, "step": 23560 }, { "epoch": 0.6662240241852317, "grad_norm": 3.7303988933563232, "learning_rate": 9.212265340965415e-05, "loss": 1.0424982070922852, "step": 23580 }, { "epoch": 0.6667890996934466, "grad_norm": 3.2776143550872803, "learning_rate": 9.210586560715517e-05, "loss": 1.1530545234680176, "step": 23600 }, { "epoch": 0.6673541752016613, "grad_norm": 3.3698747158050537, "learning_rate": 9.208906146807936e-05, "loss": 1.1131509780883788, "step": 23620 }, { "epoch": 0.6679192507098761, "grad_norm": 2.821808338165283, "learning_rate": 9.207224099894656e-05, "loss": 1.1431468963623046, "step": 23640 }, { "epoch": 0.6684843262180908, "grad_norm": 3.8925461769104004, "learning_rate": 9.205540420628286e-05, "loss": 1.0917351722717286, "step": 23660 }, { "epoch": 0.6690494017263057, "grad_norm": 2.839707612991333, "learning_rate": 9.20385510966208e-05, "loss": 1.2434934616088866, "step": 23680 }, { "epoch": 0.6696144772345205, "grad_norm": 3.4713175296783447, "learning_rate": 9.202168167649916e-05, "loss": 1.1335414886474608, "step": 23700 }, { "epoch": 0.6701795527427352, "grad_norm": 2.387789011001587, "learning_rate": 9.200479595246305e-05, "loss": 1.1175192832946776, "step": 23720 }, { "epoch": 0.67074462825095, "grad_norm": 3.968034029006958, "learning_rate": 9.198789393106398e-05, "loss": 1.1111875534057618, "step": 23740 }, { "epoch": 0.6713097037591648, "grad_norm": 2.670386552810669, "learning_rate": 9.197097561885968e-05, "loss": 1.1868657112121581, "step": 23760 }, { "epoch": 0.6718747792673796, "grad_norm": 3.297780752182007, "learning_rate": 9.195404102241429e-05, "loss": 1.1676377296447753, "step": 23780 }, { "epoch": 0.6724398547755944, "grad_norm": 2.866554021835327, "learning_rate": 9.193709014829821e-05, "loss": 1.1426793098449708, "step": 23800 }, { "epoch": 0.6730049302838091, "grad_norm": 3.1430962085723877, "learning_rate": 9.192012300308821e-05, "loss": 1.072834587097168, "step": 23820 }, { "epoch": 0.673570005792024, "grad_norm": 3.551058530807495, "learning_rate": 9.190313959336732e-05, "loss": 1.149318790435791, "step": 23840 }, { "epoch": 0.6741350813002387, "grad_norm": 3.779160261154175, "learning_rate": 9.18861399257249e-05, "loss": 1.1646828651428223, "step": 23860 }, { "epoch": 0.6747001568084535, "grad_norm": 2.796623945236206, "learning_rate": 9.186912400675663e-05, "loss": 1.060561180114746, "step": 23880 }, { "epoch": 0.6752652323166684, "grad_norm": 2.8023815155029297, "learning_rate": 9.185209184306447e-05, "loss": 1.1535423278808594, "step": 23900 }, { "epoch": 0.6758303078248831, "grad_norm": 2.894002914428711, "learning_rate": 9.183504344125671e-05, "loss": 1.2015538215637207, "step": 23920 }, { "epoch": 0.6763953833330979, "grad_norm": 4.230664253234863, "learning_rate": 9.181797880794792e-05, "loss": 1.1084952354431152, "step": 23940 }, { "epoch": 0.6769604588413126, "grad_norm": 3.36905574798584, "learning_rate": 9.180089794975899e-05, "loss": 1.1015642166137696, "step": 23960 }, { "epoch": 0.6775255343495274, "grad_norm": 3.7748265266418457, "learning_rate": 9.178380087331708e-05, "loss": 1.0246125221252442, "step": 23980 }, { "epoch": 0.6780906098577423, "grad_norm": 3.294590711593628, "learning_rate": 9.176668758525565e-05, "loss": 1.0894070625305177, "step": 24000 }, { "epoch": 0.678655685365957, "grad_norm": 2.466017007827759, "learning_rate": 9.174955809221446e-05, "loss": 1.1878242492675781, "step": 24020 }, { "epoch": 0.6792207608741718, "grad_norm": 3.404681444168091, "learning_rate": 9.173241240083953e-05, "loss": 1.147813606262207, "step": 24040 }, { "epoch": 0.6797858363823865, "grad_norm": 2.703373432159424, "learning_rate": 9.171525051778322e-05, "loss": 1.062798309326172, "step": 24060 }, { "epoch": 0.6803509118906014, "grad_norm": 3.6668248176574707, "learning_rate": 9.169807244970412e-05, "loss": 1.1634112358093263, "step": 24080 }, { "epoch": 0.6809159873988162, "grad_norm": 3.1652090549468994, "learning_rate": 9.168087820326712e-05, "loss": 1.1919386863708497, "step": 24100 }, { "epoch": 0.6814810629070309, "grad_norm": 3.264643669128418, "learning_rate": 9.166366778514336e-05, "loss": 1.2253900527954102, "step": 24120 }, { "epoch": 0.6820461384152458, "grad_norm": 3.0522520542144775, "learning_rate": 9.164644120201032e-05, "loss": 1.1352046966552733, "step": 24140 }, { "epoch": 0.6826112139234605, "grad_norm": 3.3705763816833496, "learning_rate": 9.162919846055166e-05, "loss": 1.0862237930297851, "step": 24160 }, { "epoch": 0.6831762894316753, "grad_norm": 3.8979878425598145, "learning_rate": 9.161193956745742e-05, "loss": 1.0587600708007812, "step": 24180 }, { "epoch": 0.6837413649398901, "grad_norm": 3.476851463317871, "learning_rate": 9.159466452942378e-05, "loss": 1.144219970703125, "step": 24200 }, { "epoch": 0.6843064404481048, "grad_norm": 2.482560396194458, "learning_rate": 9.15773733531533e-05, "loss": 1.1181410789489745, "step": 24220 }, { "epoch": 0.6848715159563197, "grad_norm": 3.4682400226593018, "learning_rate": 9.156006604535474e-05, "loss": 1.2258406639099122, "step": 24240 }, { "epoch": 0.6854365914645344, "grad_norm": 2.603708505630493, "learning_rate": 9.154274261274312e-05, "loss": 1.1638579368591309, "step": 24260 }, { "epoch": 0.6860016669727492, "grad_norm": 3.4911727905273438, "learning_rate": 9.152540306203973e-05, "loss": 1.1478788375854492, "step": 24280 }, { "epoch": 0.686566742480964, "grad_norm": 5.298600673675537, "learning_rate": 9.150804739997212e-05, "loss": 1.0601018905639648, "step": 24300 }, { "epoch": 0.6871318179891788, "grad_norm": 3.2789182662963867, "learning_rate": 9.149067563327405e-05, "loss": 1.0703045845031738, "step": 24320 }, { "epoch": 0.6876968934973936, "grad_norm": 3.698319911956787, "learning_rate": 9.147328776868561e-05, "loss": 1.1659321784973145, "step": 24340 }, { "epoch": 0.6882619690056083, "grad_norm": 3.057739496231079, "learning_rate": 9.145588381295305e-05, "loss": 1.1051502227783203, "step": 24360 }, { "epoch": 0.6888270445138232, "grad_norm": 3.608703136444092, "learning_rate": 9.14384637728289e-05, "loss": 1.1247699737548829, "step": 24380 }, { "epoch": 0.689392120022038, "grad_norm": 3.5643396377563477, "learning_rate": 9.142102765507195e-05, "loss": 1.1345785140991211, "step": 24400 }, { "epoch": 0.6899571955302527, "grad_norm": 3.2758729457855225, "learning_rate": 9.140357546644718e-05, "loss": 1.2251052856445312, "step": 24420 }, { "epoch": 0.6905222710384675, "grad_norm": 3.271719217300415, "learning_rate": 9.138610721372585e-05, "loss": 1.072391414642334, "step": 24440 }, { "epoch": 0.6910873465466822, "grad_norm": 2.458434820175171, "learning_rate": 9.136862290368542e-05, "loss": 1.023391342163086, "step": 24460 }, { "epoch": 0.6916524220548971, "grad_norm": 4.465213775634766, "learning_rate": 9.135112254310961e-05, "loss": 1.0889568328857422, "step": 24480 }, { "epoch": 0.6922174975631119, "grad_norm": 2.364516496658325, "learning_rate": 9.133360613878835e-05, "loss": 1.033189582824707, "step": 24500 }, { "epoch": 0.6927825730713266, "grad_norm": 2.9296765327453613, "learning_rate": 9.131607369751779e-05, "loss": 1.0581647872924804, "step": 24520 }, { "epoch": 0.6933476485795415, "grad_norm": 3.327918767929077, "learning_rate": 9.129852522610032e-05, "loss": 1.2115694999694824, "step": 24540 }, { "epoch": 0.6939127240877562, "grad_norm": 3.8117356300354004, "learning_rate": 9.128096073134453e-05, "loss": 1.177830410003662, "step": 24560 }, { "epoch": 0.694477799595971, "grad_norm": 2.66576886177063, "learning_rate": 9.126338022006524e-05, "loss": 1.1339356422424316, "step": 24580 }, { "epoch": 0.6950428751041858, "grad_norm": 2.575265407562256, "learning_rate": 9.124578369908348e-05, "loss": 1.1133891105651856, "step": 24600 }, { "epoch": 0.6956079506124005, "grad_norm": 4.748629093170166, "learning_rate": 9.12281711752265e-05, "loss": 1.0952016830444335, "step": 24620 }, { "epoch": 0.6961730261206154, "grad_norm": 3.2432973384857178, "learning_rate": 9.121054265532773e-05, "loss": 1.1256036758422852, "step": 24640 }, { "epoch": 0.6967381016288301, "grad_norm": 3.341963052749634, "learning_rate": 9.119289814622683e-05, "loss": 1.1621355056762694, "step": 24660 }, { "epoch": 0.6973031771370449, "grad_norm": 3.9619877338409424, "learning_rate": 9.117523765476969e-05, "loss": 1.1352086067199707, "step": 24680 }, { "epoch": 0.6978682526452598, "grad_norm": 3.9111855030059814, "learning_rate": 9.115756118780834e-05, "loss": 1.0775476455688477, "step": 24700 }, { "epoch": 0.6984333281534745, "grad_norm": 2.8584961891174316, "learning_rate": 9.113986875220105e-05, "loss": 1.0300395011901855, "step": 24720 }, { "epoch": 0.6989984036616893, "grad_norm": 2.4969000816345215, "learning_rate": 9.112216035481226e-05, "loss": 1.0966676712036132, "step": 24740 }, { "epoch": 0.699563479169904, "grad_norm": 2.967808246612549, "learning_rate": 9.110443600251265e-05, "loss": 1.147977066040039, "step": 24760 }, { "epoch": 0.7001285546781189, "grad_norm": 3.7299396991729736, "learning_rate": 9.108669570217903e-05, "loss": 1.1500679969787597, "step": 24780 }, { "epoch": 0.7006936301863337, "grad_norm": 3.1571438312530518, "learning_rate": 9.106893946069445e-05, "loss": 1.1157882690429688, "step": 24800 }, { "epoch": 0.7012587056945484, "grad_norm": 2.788517951965332, "learning_rate": 9.10511672849481e-05, "loss": 1.1277948379516602, "step": 24820 }, { "epoch": 0.7018237812027632, "grad_norm": 3.305920362472534, "learning_rate": 9.103337918183539e-05, "loss": 1.101285457611084, "step": 24840 }, { "epoch": 0.702388856710978, "grad_norm": 2.7898006439208984, "learning_rate": 9.101557515825788e-05, "loss": 1.1174089431762695, "step": 24860 }, { "epoch": 0.7029539322191928, "grad_norm": 2.1857411861419678, "learning_rate": 9.099775522112333e-05, "loss": 1.118039035797119, "step": 24880 }, { "epoch": 0.7035190077274076, "grad_norm": 3.340050458908081, "learning_rate": 9.097991937734564e-05, "loss": 1.108839225769043, "step": 24900 }, { "epoch": 0.7040840832356223, "grad_norm": 2.5567259788513184, "learning_rate": 9.096206763384496e-05, "loss": 1.2127989768981933, "step": 24920 }, { "epoch": 0.7046491587438372, "grad_norm": 3.233069658279419, "learning_rate": 9.094419999754751e-05, "loss": 1.0789197921752929, "step": 24940 }, { "epoch": 0.705214234252052, "grad_norm": 2.5852460861206055, "learning_rate": 9.092631647538572e-05, "loss": 1.095817756652832, "step": 24960 }, { "epoch": 0.7057793097602667, "grad_norm": 2.154024124145508, "learning_rate": 9.09084170742982e-05, "loss": 1.2088044166564942, "step": 24980 }, { "epoch": 0.7063443852684815, "grad_norm": 4.8553056716918945, "learning_rate": 9.089050180122971e-05, "loss": 1.0871821403503419, "step": 25000 }, { "epoch": 0.7069094607766963, "grad_norm": 3.174422025680542, "learning_rate": 9.087257066313115e-05, "loss": 1.2235529899597168, "step": 25020 }, { "epoch": 0.7074745362849111, "grad_norm": 3.3529131412506104, "learning_rate": 9.085462366695961e-05, "loss": 1.1147781372070313, "step": 25040 }, { "epoch": 0.7080396117931259, "grad_norm": 3.1814191341400146, "learning_rate": 9.083666081967827e-05, "loss": 1.155458927154541, "step": 25060 }, { "epoch": 0.7086046873013406, "grad_norm": 2.328770875930786, "learning_rate": 9.081868212825655e-05, "loss": 1.1527506828308105, "step": 25080 }, { "epoch": 0.7091697628095555, "grad_norm": 2.511568307876587, "learning_rate": 9.080068759966995e-05, "loss": 1.2134083747863769, "step": 25100 }, { "epoch": 0.7097348383177702, "grad_norm": 3.2014806270599365, "learning_rate": 9.078267724090013e-05, "loss": 1.0909175872802734, "step": 25120 }, { "epoch": 0.710299913825985, "grad_norm": 3.4517979621887207, "learning_rate": 9.076465105893487e-05, "loss": 1.0779218673706055, "step": 25140 }, { "epoch": 0.7108649893341998, "grad_norm": 4.268838405609131, "learning_rate": 9.074660906076817e-05, "loss": 1.1740532875061036, "step": 25160 }, { "epoch": 0.7114300648424146, "grad_norm": 3.7933621406555176, "learning_rate": 9.07285512534001e-05, "loss": 1.1202109336853028, "step": 25180 }, { "epoch": 0.7119951403506294, "grad_norm": 3.9100654125213623, "learning_rate": 9.071047764383683e-05, "loss": 1.0752214431762694, "step": 25200 }, { "epoch": 0.7125602158588441, "grad_norm": 4.161895275115967, "learning_rate": 9.069238823909074e-05, "loss": 1.1553067207336425, "step": 25220 }, { "epoch": 0.7131252913670589, "grad_norm": 3.7063863277435303, "learning_rate": 9.06742830461803e-05, "loss": 1.030357837677002, "step": 25240 }, { "epoch": 0.7136903668752738, "grad_norm": 3.4565446376800537, "learning_rate": 9.065616207213012e-05, "loss": 1.1057129859924317, "step": 25260 }, { "epoch": 0.7142554423834885, "grad_norm": 3.0091745853424072, "learning_rate": 9.063802532397092e-05, "loss": 1.1016512870788575, "step": 25280 }, { "epoch": 0.7148205178917033, "grad_norm": 2.8469901084899902, "learning_rate": 9.061987280873952e-05, "loss": 1.1149499893188477, "step": 25300 }, { "epoch": 0.715385593399918, "grad_norm": 2.5117664337158203, "learning_rate": 9.060170453347889e-05, "loss": 1.1018942832946776, "step": 25320 }, { "epoch": 0.7159506689081329, "grad_norm": 3.186263084411621, "learning_rate": 9.058352050523812e-05, "loss": 1.2010828018188477, "step": 25340 }, { "epoch": 0.7165157444163477, "grad_norm": 3.7037765979766846, "learning_rate": 9.056532073107241e-05, "loss": 1.206453800201416, "step": 25360 }, { "epoch": 0.7170808199245624, "grad_norm": 2.3383495807647705, "learning_rate": 9.054710521804303e-05, "loss": 1.0850662231445312, "step": 25380 }, { "epoch": 0.7176458954327772, "grad_norm": 3.1976473331451416, "learning_rate": 9.052887397321738e-05, "loss": 1.1461727142333984, "step": 25400 }, { "epoch": 0.718210970940992, "grad_norm": 3.33182954788208, "learning_rate": 9.051062700366898e-05, "loss": 1.1962703704833983, "step": 25420 }, { "epoch": 0.7187760464492068, "grad_norm": 3.027796983718872, "learning_rate": 9.049236431647744e-05, "loss": 1.1017403602600098, "step": 25440 }, { "epoch": 0.7193411219574216, "grad_norm": 2.0258736610412598, "learning_rate": 9.047408591872846e-05, "loss": 1.1290461540222168, "step": 25460 }, { "epoch": 0.7199061974656363, "grad_norm": 3.6550819873809814, "learning_rate": 9.045579181751383e-05, "loss": 1.1085844039916992, "step": 25480 }, { "epoch": 0.7204712729738512, "grad_norm": 2.796679973602295, "learning_rate": 9.043748201993147e-05, "loss": 1.1133931159973145, "step": 25500 }, { "epoch": 0.7210363484820659, "grad_norm": 3.1957154273986816, "learning_rate": 9.041915653308535e-05, "loss": 1.1263614654541017, "step": 25520 }, { "epoch": 0.7216014239902807, "grad_norm": 4.3786444664001465, "learning_rate": 9.040081536408555e-05, "loss": 1.1034400939941407, "step": 25540 }, { "epoch": 0.7221664994984955, "grad_norm": 2.2308905124664307, "learning_rate": 9.038245852004821e-05, "loss": 1.1757619857788086, "step": 25560 }, { "epoch": 0.7227315750067103, "grad_norm": 3.764890432357788, "learning_rate": 9.036408600809559e-05, "loss": 1.0954778671264649, "step": 25580 }, { "epoch": 0.7232966505149251, "grad_norm": 3.104037284851074, "learning_rate": 9.034569783535599e-05, "loss": 1.1328980445861816, "step": 25600 }, { "epoch": 0.7238617260231398, "grad_norm": 3.2161757946014404, "learning_rate": 9.03272940089638e-05, "loss": 1.125420093536377, "step": 25620 }, { "epoch": 0.7244268015313546, "grad_norm": 2.486701726913452, "learning_rate": 9.030887453605951e-05, "loss": 1.1737950325012207, "step": 25640 }, { "epoch": 0.7249918770395695, "grad_norm": 4.39532995223999, "learning_rate": 9.029043942378962e-05, "loss": 1.159797763824463, "step": 25660 }, { "epoch": 0.7255569525477842, "grad_norm": 3.7140300273895264, "learning_rate": 9.027198867930678e-05, "loss": 1.0819243431091308, "step": 25680 }, { "epoch": 0.726122028055999, "grad_norm": 2.81119441986084, "learning_rate": 9.025352230976962e-05, "loss": 1.0537238121032715, "step": 25700 }, { "epoch": 0.7266871035642137, "grad_norm": 4.694212913513184, "learning_rate": 9.02350403223429e-05, "loss": 1.0716522216796875, "step": 25720 }, { "epoch": 0.7272521790724286, "grad_norm": 3.7711539268493652, "learning_rate": 9.021654272419739e-05, "loss": 1.1237900733947754, "step": 25740 }, { "epoch": 0.7278172545806434, "grad_norm": 3.1208412647247314, "learning_rate": 9.019802952250996e-05, "loss": 1.0533141136169433, "step": 25760 }, { "epoch": 0.7283823300888581, "grad_norm": 3.4408364295959473, "learning_rate": 9.017950072446351e-05, "loss": 1.0949275970458985, "step": 25780 }, { "epoch": 0.7289474055970729, "grad_norm": 3.8668429851531982, "learning_rate": 9.016095633724697e-05, "loss": 1.1057689666748047, "step": 25800 }, { "epoch": 0.7295124811052877, "grad_norm": 3.238166570663452, "learning_rate": 9.014239636805535e-05, "loss": 1.1065932273864747, "step": 25820 }, { "epoch": 0.7300775566135025, "grad_norm": 2.4378061294555664, "learning_rate": 9.012382082408975e-05, "loss": 1.0917963981628418, "step": 25840 }, { "epoch": 0.7306426321217173, "grad_norm": 3.1363372802734375, "learning_rate": 9.010522971255718e-05, "loss": 1.0770783424377441, "step": 25860 }, { "epoch": 0.731207707629932, "grad_norm": 3.234349250793457, "learning_rate": 9.008662304067082e-05, "loss": 1.1191338539123534, "step": 25880 }, { "epoch": 0.7317727831381469, "grad_norm": 2.480846643447876, "learning_rate": 9.006800081564984e-05, "loss": 1.070312213897705, "step": 25900 }, { "epoch": 0.7323378586463616, "grad_norm": 3.69362735748291, "learning_rate": 9.00493630447194e-05, "loss": 1.1202000617980956, "step": 25920 }, { "epoch": 0.7329029341545764, "grad_norm": 2.373222589492798, "learning_rate": 9.00307097351108e-05, "loss": 1.1521299362182618, "step": 25940 }, { "epoch": 0.7334680096627912, "grad_norm": 3.542367935180664, "learning_rate": 9.001204089406125e-05, "loss": 1.0863287925720215, "step": 25960 }, { "epoch": 0.734033085171006, "grad_norm": 2.5048987865448, "learning_rate": 8.999335652881406e-05, "loss": 1.0637874603271484, "step": 25980 }, { "epoch": 0.7345981606792208, "grad_norm": 3.102785348892212, "learning_rate": 8.997465664661853e-05, "loss": 1.1275898933410644, "step": 26000 }, { "epoch": 0.7351632361874355, "grad_norm": 3.766702651977539, "learning_rate": 8.995594125473002e-05, "loss": 1.1065070152282714, "step": 26020 }, { "epoch": 0.7357283116956503, "grad_norm": 3.1698312759399414, "learning_rate": 8.993721036040985e-05, "loss": 1.0569238662719727, "step": 26040 }, { "epoch": 0.7362933872038652, "grad_norm": 3.986304998397827, "learning_rate": 8.991846397092539e-05, "loss": 0.9740676879882812, "step": 26060 }, { "epoch": 0.7368584627120799, "grad_norm": 2.7156169414520264, "learning_rate": 8.989970209355003e-05, "loss": 1.0835305213928224, "step": 26080 }, { "epoch": 0.7374235382202947, "grad_norm": 2.8956868648529053, "learning_rate": 8.988092473556315e-05, "loss": 1.1089884757995605, "step": 26100 }, { "epoch": 0.7379886137285094, "grad_norm": 2.942437171936035, "learning_rate": 8.986213190425015e-05, "loss": 1.1081379890441894, "step": 26120 }, { "epoch": 0.7385536892367243, "grad_norm": 3.7554469108581543, "learning_rate": 8.984332360690241e-05, "loss": 1.2204872131347657, "step": 26140 }, { "epoch": 0.7391187647449391, "grad_norm": 2.0293753147125244, "learning_rate": 8.982449985081734e-05, "loss": 1.0866355895996094, "step": 26160 }, { "epoch": 0.7396838402531538, "grad_norm": 3.2674052715301514, "learning_rate": 8.980566064329831e-05, "loss": 1.1830026626586914, "step": 26180 }, { "epoch": 0.7402489157613686, "grad_norm": 3.246258020401001, "learning_rate": 8.978680599165475e-05, "loss": 1.203585720062256, "step": 26200 }, { "epoch": 0.7408139912695834, "grad_norm": 3.3275668621063232, "learning_rate": 8.9767935903202e-05, "loss": 1.0904476165771484, "step": 26220 }, { "epoch": 0.7413790667777982, "grad_norm": 3.24656081199646, "learning_rate": 8.974905038526147e-05, "loss": 1.0320629119873046, "step": 26240 }, { "epoch": 0.741944142286013, "grad_norm": 2.6876187324523926, "learning_rate": 8.97301494451605e-05, "loss": 1.0517584800720214, "step": 26260 }, { "epoch": 0.7425092177942277, "grad_norm": 3.529951572418213, "learning_rate": 8.97112330902324e-05, "loss": 1.175868606567383, "step": 26280 }, { "epoch": 0.7430742933024426, "grad_norm": 5.308630466461182, "learning_rate": 8.969230132781655e-05, "loss": 1.0836967468261718, "step": 26300 }, { "epoch": 0.7436393688106573, "grad_norm": 3.578307867050171, "learning_rate": 8.967335416525819e-05, "loss": 1.1636499404907226, "step": 26320 }, { "epoch": 0.7442044443188721, "grad_norm": 3.6557257175445557, "learning_rate": 8.965439160990864e-05, "loss": 1.1199105262756348, "step": 26340 }, { "epoch": 0.744769519827087, "grad_norm": 3.06142258644104, "learning_rate": 8.963541366912512e-05, "loss": 1.0686775207519532, "step": 26360 }, { "epoch": 0.7453345953353017, "grad_norm": 2.6959304809570312, "learning_rate": 8.961642035027087e-05, "loss": 1.0159113883972168, "step": 26380 }, { "epoch": 0.7458996708435165, "grad_norm": 3.1058781147003174, "learning_rate": 8.959741166071504e-05, "loss": 1.2006366729736329, "step": 26400 }, { "epoch": 0.7464647463517312, "grad_norm": 3.9579720497131348, "learning_rate": 8.957838760783281e-05, "loss": 1.1796916007995606, "step": 26420 }, { "epoch": 0.747029821859946, "grad_norm": 2.6344432830810547, "learning_rate": 8.955934819900527e-05, "loss": 1.008646583557129, "step": 26440 }, { "epoch": 0.7475948973681609, "grad_norm": 5.23372220993042, "learning_rate": 8.95402934416195e-05, "loss": 1.095982837677002, "step": 26460 }, { "epoch": 0.7481599728763756, "grad_norm": 3.023026704788208, "learning_rate": 8.952122334306849e-05, "loss": 1.1059672355651855, "step": 26480 }, { "epoch": 0.7487250483845904, "grad_norm": 3.323911666870117, "learning_rate": 8.950213791075123e-05, "loss": 1.1316338539123536, "step": 26500 }, { "epoch": 0.7492901238928051, "grad_norm": 2.6978373527526855, "learning_rate": 8.948303715207263e-05, "loss": 1.083777904510498, "step": 26520 }, { "epoch": 0.74985519940102, "grad_norm": 4.186313152313232, "learning_rate": 8.946392107444358e-05, "loss": 1.1032967567443848, "step": 26540 }, { "epoch": 0.7504202749092348, "grad_norm": 2.714777946472168, "learning_rate": 8.944478968528089e-05, "loss": 1.101963710784912, "step": 26560 }, { "epoch": 0.7509853504174495, "grad_norm": 3.8887596130371094, "learning_rate": 8.94256429920073e-05, "loss": 1.078538417816162, "step": 26580 }, { "epoch": 0.7515504259256643, "grad_norm": 3.299804449081421, "learning_rate": 8.94064810020515e-05, "loss": 1.0986174583435058, "step": 26600 }, { "epoch": 0.7521155014338791, "grad_norm": 3.5499305725097656, "learning_rate": 8.93873037228481e-05, "loss": 1.1195365905761718, "step": 26620 }, { "epoch": 0.7526805769420939, "grad_norm": 3.528986692428589, "learning_rate": 8.93681111618377e-05, "loss": 1.202183723449707, "step": 26640 }, { "epoch": 0.7532456524503087, "grad_norm": 3.0467872619628906, "learning_rate": 8.934890332646675e-05, "loss": 1.0984074592590332, "step": 26660 }, { "epoch": 0.7538107279585234, "grad_norm": 3.4565603733062744, "learning_rate": 8.932968022418766e-05, "loss": 1.1445248603820801, "step": 26680 }, { "epoch": 0.7543758034667383, "grad_norm": 3.0519752502441406, "learning_rate": 8.931044186245881e-05, "loss": 1.1059165000915527, "step": 26700 }, { "epoch": 0.754940878974953, "grad_norm": 3.2753782272338867, "learning_rate": 8.92911882487444e-05, "loss": 1.134038543701172, "step": 26720 }, { "epoch": 0.7555059544831678, "grad_norm": 2.9366588592529297, "learning_rate": 8.927191939051464e-05, "loss": 1.0422195434570312, "step": 26740 }, { "epoch": 0.7560710299913826, "grad_norm": 2.7722127437591553, "learning_rate": 8.92526352952456e-05, "loss": 1.1105210304260253, "step": 26760 }, { "epoch": 0.7566361054995974, "grad_norm": 3.967958927154541, "learning_rate": 8.92333359704193e-05, "loss": 1.1463178634643554, "step": 26780 }, { "epoch": 0.7572011810078122, "grad_norm": 3.5653560161590576, "learning_rate": 8.921402142352362e-05, "loss": 1.0865794181823731, "step": 26800 }, { "epoch": 0.7577662565160269, "grad_norm": 3.3835384845733643, "learning_rate": 8.919469166205241e-05, "loss": 1.078042221069336, "step": 26820 }, { "epoch": 0.7583313320242417, "grad_norm": 3.846445322036743, "learning_rate": 8.917534669350535e-05, "loss": 1.1499770164489747, "step": 26840 }, { "epoch": 0.7588964075324566, "grad_norm": 2.523122549057007, "learning_rate": 8.915598652538811e-05, "loss": 1.0777621269226074, "step": 26860 }, { "epoch": 0.7594614830406713, "grad_norm": 3.8458850383758545, "learning_rate": 8.913661116521216e-05, "loss": 1.0690784454345703, "step": 26880 }, { "epoch": 0.7600265585488861, "grad_norm": 3.1697838306427, "learning_rate": 8.911722062049493e-05, "loss": 1.0667675018310547, "step": 26900 }, { "epoch": 0.7605916340571008, "grad_norm": 3.6572744846343994, "learning_rate": 8.909781489875971e-05, "loss": 1.109433364868164, "step": 26920 }, { "epoch": 0.7611567095653157, "grad_norm": 3.191014051437378, "learning_rate": 8.907839400753571e-05, "loss": 1.0898544311523437, "step": 26940 }, { "epoch": 0.7617217850735305, "grad_norm": 4.056923866271973, "learning_rate": 8.905895795435797e-05, "loss": 1.1110716819763184, "step": 26960 }, { "epoch": 0.7622868605817452, "grad_norm": 3.389963150024414, "learning_rate": 8.903950674676749e-05, "loss": 1.0589890480041504, "step": 26980 }, { "epoch": 0.76285193608996, "grad_norm": 3.182218551635742, "learning_rate": 8.902004039231109e-05, "loss": 1.1473590850830078, "step": 27000 }, { "epoch": 0.7634170115981748, "grad_norm": 2.987639904022217, "learning_rate": 8.900055889854148e-05, "loss": 1.1755850791931153, "step": 27020 }, { "epoch": 0.7639820871063896, "grad_norm": 3.774611711502075, "learning_rate": 8.898106227301725e-05, "loss": 1.1440903663635253, "step": 27040 }, { "epoch": 0.7645471626146044, "grad_norm": 3.160219430923462, "learning_rate": 8.896155052330287e-05, "loss": 1.1155387878417968, "step": 27060 }, { "epoch": 0.7651122381228191, "grad_norm": 4.191543102264404, "learning_rate": 8.894202365696864e-05, "loss": 1.0278716087341309, "step": 27080 }, { "epoch": 0.765677313631034, "grad_norm": 3.3442115783691406, "learning_rate": 8.89224816815908e-05, "loss": 1.1239681243896484, "step": 27100 }, { "epoch": 0.7662423891392487, "grad_norm": 3.0011911392211914, "learning_rate": 8.890292460475136e-05, "loss": 1.134052562713623, "step": 27120 }, { "epoch": 0.7668074646474635, "grad_norm": 2.9036436080932617, "learning_rate": 8.888335243403825e-05, "loss": 1.0694004058837892, "step": 27140 }, { "epoch": 0.7673725401556784, "grad_norm": 3.3571298122406006, "learning_rate": 8.886376517704525e-05, "loss": 1.0854718208312988, "step": 27160 }, { "epoch": 0.7679376156638931, "grad_norm": 2.90580415725708, "learning_rate": 8.884416284137198e-05, "loss": 1.1195537567138671, "step": 27180 }, { "epoch": 0.7685026911721079, "grad_norm": 2.545830011367798, "learning_rate": 8.88245454346239e-05, "loss": 1.1288962364196777, "step": 27200 }, { "epoch": 0.7690677666803226, "grad_norm": 5.382704257965088, "learning_rate": 8.880491296441235e-05, "loss": 1.0965164184570313, "step": 27220 }, { "epoch": 0.7696328421885374, "grad_norm": 3.504972457885742, "learning_rate": 8.878526543835448e-05, "loss": 1.1112503051757812, "step": 27240 }, { "epoch": 0.7701979176967523, "grad_norm": 3.1834542751312256, "learning_rate": 8.87656028640733e-05, "loss": 1.1254182815551759, "step": 27260 }, { "epoch": 0.770762993204967, "grad_norm": 4.0598931312561035, "learning_rate": 8.874592524919766e-05, "loss": 1.175435447692871, "step": 27280 }, { "epoch": 0.7713280687131818, "grad_norm": 3.96535325050354, "learning_rate": 8.872623260136223e-05, "loss": 1.129081916809082, "step": 27300 }, { "epoch": 0.7718931442213965, "grad_norm": 2.8693909645080566, "learning_rate": 8.870652492820756e-05, "loss": 1.1828269004821776, "step": 27320 }, { "epoch": 0.7724582197296114, "grad_norm": 3.349857807159424, "learning_rate": 8.868680223737996e-05, "loss": 1.0758611679077148, "step": 27340 }, { "epoch": 0.7730232952378262, "grad_norm": 3.5505616664886475, "learning_rate": 8.86670645365316e-05, "loss": 1.0911221504211426, "step": 27360 }, { "epoch": 0.7735883707460409, "grad_norm": 3.5946407318115234, "learning_rate": 8.864731183332048e-05, "loss": 1.0534512519836425, "step": 27380 }, { "epoch": 0.7741534462542558, "grad_norm": 2.7643659114837646, "learning_rate": 8.862754413541044e-05, "loss": 1.0063386917114259, "step": 27400 }, { "epoch": 0.7747185217624705, "grad_norm": 3.1449413299560547, "learning_rate": 8.860776145047108e-05, "loss": 1.1102384567260741, "step": 27420 }, { "epoch": 0.7752835972706853, "grad_norm": 2.5477139949798584, "learning_rate": 8.858796378617784e-05, "loss": 1.0392619132995606, "step": 27440 }, { "epoch": 0.7758486727789001, "grad_norm": 5.907681465148926, "learning_rate": 8.856815115021203e-05, "loss": 1.1191020011901855, "step": 27460 }, { "epoch": 0.7764137482871148, "grad_norm": 2.5616729259490967, "learning_rate": 8.854832355026065e-05, "loss": 1.127807903289795, "step": 27480 }, { "epoch": 0.7769788237953297, "grad_norm": 3.6543970108032227, "learning_rate": 8.852848099401662e-05, "loss": 1.0550318717956544, "step": 27500 }, { "epoch": 0.7775438993035444, "grad_norm": 2.9305942058563232, "learning_rate": 8.850862348917861e-05, "loss": 1.0615076065063476, "step": 27520 }, { "epoch": 0.7781089748117592, "grad_norm": 2.9650440216064453, "learning_rate": 8.848875104345107e-05, "loss": 1.1134916305541993, "step": 27540 }, { "epoch": 0.778674050319974, "grad_norm": 3.564627170562744, "learning_rate": 8.846886366454432e-05, "loss": 1.0726702690124512, "step": 27560 }, { "epoch": 0.7792391258281888, "grad_norm": 2.4005744457244873, "learning_rate": 8.84489613601744e-05, "loss": 1.08388090133667, "step": 27580 }, { "epoch": 0.7798042013364036, "grad_norm": 3.0752038955688477, "learning_rate": 8.842904413806315e-05, "loss": 1.0703536987304687, "step": 27600 }, { "epoch": 0.7803692768446183, "grad_norm": 5.142773628234863, "learning_rate": 8.840911200593826e-05, "loss": 1.047508716583252, "step": 27620 }, { "epoch": 0.7809343523528331, "grad_norm": 3.223515272140503, "learning_rate": 8.838916497153312e-05, "loss": 1.0789781570434571, "step": 27640 }, { "epoch": 0.781499427861048, "grad_norm": 2.707296848297119, "learning_rate": 8.836920304258697e-05, "loss": 1.0675657272338868, "step": 27660 }, { "epoch": 0.7820645033692627, "grad_norm": 3.6077399253845215, "learning_rate": 8.834922622684478e-05, "loss": 1.1921844482421875, "step": 27680 }, { "epoch": 0.7826295788774775, "grad_norm": 2.840285062789917, "learning_rate": 8.832923453205735e-05, "loss": 1.0945690155029297, "step": 27700 }, { "epoch": 0.7831946543856922, "grad_norm": 4.510866165161133, "learning_rate": 8.830922796598117e-05, "loss": 1.166372013092041, "step": 27720 }, { "epoch": 0.7837597298939071, "grad_norm": 4.209907531738281, "learning_rate": 8.828920653637861e-05, "loss": 1.0671940803527833, "step": 27740 }, { "epoch": 0.7843248054021219, "grad_norm": 2.6507694721221924, "learning_rate": 8.82691702510177e-05, "loss": 1.0889955520629884, "step": 27760 }, { "epoch": 0.7848898809103366, "grad_norm": 3.034451961517334, "learning_rate": 8.824911911767232e-05, "loss": 1.1203947067260742, "step": 27780 }, { "epoch": 0.7854549564185515, "grad_norm": 3.2755720615386963, "learning_rate": 8.822905314412204e-05, "loss": 1.0676383018493651, "step": 27800 }, { "epoch": 0.7860200319267662, "grad_norm": 3.201491117477417, "learning_rate": 8.820897233815223e-05, "loss": 1.0503196716308594, "step": 27820 }, { "epoch": 0.786585107434981, "grad_norm": 3.32824444770813, "learning_rate": 8.8188876707554e-05, "loss": 1.1150938987731933, "step": 27840 }, { "epoch": 0.7871501829431958, "grad_norm": 3.3613054752349854, "learning_rate": 8.816876626012424e-05, "loss": 1.135185146331787, "step": 27860 }, { "epoch": 0.7877152584514105, "grad_norm": 3.902157783508301, "learning_rate": 8.814864100366554e-05, "loss": 1.0600241661071776, "step": 27880 }, { "epoch": 0.7882803339596254, "grad_norm": 2.7802560329437256, "learning_rate": 8.812850094598627e-05, "loss": 1.0628619194030762, "step": 27900 }, { "epoch": 0.7888454094678401, "grad_norm": 3.6485178470611572, "learning_rate": 8.810834609490053e-05, "loss": 1.0838992118835449, "step": 27920 }, { "epoch": 0.7894104849760549, "grad_norm": 3.168376922607422, "learning_rate": 8.808817645822816e-05, "loss": 0.9916201591491699, "step": 27940 }, { "epoch": 0.7899755604842698, "grad_norm": 3.535024404525757, "learning_rate": 8.806799204379475e-05, "loss": 1.1887300491333008, "step": 27960 }, { "epoch": 0.7905406359924845, "grad_norm": 2.6720516681671143, "learning_rate": 8.804779285943161e-05, "loss": 1.112503719329834, "step": 27980 }, { "epoch": 0.7911057115006993, "grad_norm": 2.811310052871704, "learning_rate": 8.80275789129758e-05, "loss": 1.1238983154296875, "step": 28000 }, { "epoch": 0.791670787008914, "grad_norm": 3.157525062561035, "learning_rate": 8.800735021227004e-05, "loss": 1.0927964210510255, "step": 28020 }, { "epoch": 0.7922358625171289, "grad_norm": 4.264059066772461, "learning_rate": 8.798710676516288e-05, "loss": 1.097845458984375, "step": 28040 }, { "epoch": 0.7928009380253437, "grad_norm": 4.473461151123047, "learning_rate": 8.796684857950853e-05, "loss": 1.145701789855957, "step": 28060 }, { "epoch": 0.7933660135335584, "grad_norm": 4.4579386711120605, "learning_rate": 8.79465756631669e-05, "loss": 1.0756842613220214, "step": 28080 }, { "epoch": 0.7939310890417732, "grad_norm": 3.0825083255767822, "learning_rate": 8.792628802400367e-05, "loss": 1.1247604370117188, "step": 28100 }, { "epoch": 0.794496164549988, "grad_norm": 2.739305019378662, "learning_rate": 8.790598566989018e-05, "loss": 1.157236385345459, "step": 28120 }, { "epoch": 0.7950612400582028, "grad_norm": 2.937328577041626, "learning_rate": 8.788566860870351e-05, "loss": 1.0247296333312987, "step": 28140 }, { "epoch": 0.7956263155664176, "grad_norm": 4.008519649505615, "learning_rate": 8.786533684832645e-05, "loss": 1.1507199287414551, "step": 28160 }, { "epoch": 0.7961913910746323, "grad_norm": 3.268392324447632, "learning_rate": 8.784499039664746e-05, "loss": 1.1937284469604492, "step": 28180 }, { "epoch": 0.7967564665828472, "grad_norm": 3.1458945274353027, "learning_rate": 8.782462926156075e-05, "loss": 1.0627116203308105, "step": 28200 }, { "epoch": 0.7973215420910619, "grad_norm": 3.758347749710083, "learning_rate": 8.780425345096619e-05, "loss": 1.108817195892334, "step": 28220 }, { "epoch": 0.7978866175992767, "grad_norm": 2.7600786685943604, "learning_rate": 8.778386297276933e-05, "loss": 1.1406152725219727, "step": 28240 }, { "epoch": 0.7984516931074915, "grad_norm": 3.200824737548828, "learning_rate": 8.776345783488146e-05, "loss": 1.0372465133666993, "step": 28260 }, { "epoch": 0.7990167686157063, "grad_norm": 3.7274363040924072, "learning_rate": 8.774303804521953e-05, "loss": 1.1505254745483398, "step": 28280 }, { "epoch": 0.7995818441239211, "grad_norm": 4.011970043182373, "learning_rate": 8.772260361170616e-05, "loss": 1.085913848876953, "step": 28300 }, { "epoch": 0.8001469196321358, "grad_norm": 3.3213651180267334, "learning_rate": 8.770215454226968e-05, "loss": 1.1584247589111327, "step": 28320 }, { "epoch": 0.8007119951403506, "grad_norm": 3.248013496398926, "learning_rate": 8.768169084484408e-05, "loss": 1.0819347381591797, "step": 28340 }, { "epoch": 0.8012770706485655, "grad_norm": 3.2647759914398193, "learning_rate": 8.766121252736903e-05, "loss": 1.123091220855713, "step": 28360 }, { "epoch": 0.8018421461567802, "grad_norm": 3.2253313064575195, "learning_rate": 8.76407195977899e-05, "loss": 1.1285037994384766, "step": 28380 }, { "epoch": 0.802407221664995, "grad_norm": 3.6502013206481934, "learning_rate": 8.762021206405768e-05, "loss": 1.1166404724121093, "step": 28400 }, { "epoch": 0.8029722971732097, "grad_norm": 2.528191089630127, "learning_rate": 8.759968993412905e-05, "loss": 1.0810117721557617, "step": 28420 }, { "epoch": 0.8035373726814246, "grad_norm": 2.626555919647217, "learning_rate": 8.757915321596636e-05, "loss": 1.0534433364868163, "step": 28440 }, { "epoch": 0.8041024481896394, "grad_norm": 3.3075454235076904, "learning_rate": 8.755860191753761e-05, "loss": 1.0040666580200195, "step": 28460 }, { "epoch": 0.8046675236978541, "grad_norm": 3.56239652633667, "learning_rate": 8.753803604681645e-05, "loss": 1.1301284790039063, "step": 28480 }, { "epoch": 0.8052325992060689, "grad_norm": 4.463495254516602, "learning_rate": 8.751745561178221e-05, "loss": 1.0962712287902832, "step": 28500 }, { "epoch": 0.8057976747142837, "grad_norm": 3.790827512741089, "learning_rate": 8.749686062041988e-05, "loss": 1.0588294982910156, "step": 28520 }, { "epoch": 0.8063627502224985, "grad_norm": 4.226777076721191, "learning_rate": 8.747625108072002e-05, "loss": 1.1449335098266602, "step": 28540 }, { "epoch": 0.8069278257307133, "grad_norm": 2.948896884918213, "learning_rate": 8.745562700067891e-05, "loss": 1.1519246101379395, "step": 28560 }, { "epoch": 0.807492901238928, "grad_norm": 3.2483091354370117, "learning_rate": 8.743498838829844e-05, "loss": 1.143216323852539, "step": 28580 }, { "epoch": 0.8080579767471429, "grad_norm": 2.94240140914917, "learning_rate": 8.741433525158616e-05, "loss": 1.125504970550537, "step": 28600 }, { "epoch": 0.8086230522553576, "grad_norm": 5.188705921173096, "learning_rate": 8.739366759855525e-05, "loss": 1.1707324028015136, "step": 28620 }, { "epoch": 0.8091881277635724, "grad_norm": 3.747455596923828, "learning_rate": 8.737298543722449e-05, "loss": 1.1154777526855468, "step": 28640 }, { "epoch": 0.8097532032717872, "grad_norm": 2.6666717529296875, "learning_rate": 8.735228877561833e-05, "loss": 1.0394587516784668, "step": 28660 }, { "epoch": 0.810318278780002, "grad_norm": 3.7813594341278076, "learning_rate": 8.733157762176682e-05, "loss": 1.1291560173034667, "step": 28680 }, { "epoch": 0.8108833542882168, "grad_norm": 2.67195463180542, "learning_rate": 8.731085198370566e-05, "loss": 1.1597579002380372, "step": 28700 }, { "epoch": 0.8114484297964315, "grad_norm": 3.4042234420776367, "learning_rate": 8.729011186947613e-05, "loss": 1.1181085586547852, "step": 28720 }, { "epoch": 0.8120135053046463, "grad_norm": 4.097559452056885, "learning_rate": 8.726935728712516e-05, "loss": 1.1361172676086426, "step": 28740 }, { "epoch": 0.8125785808128612, "grad_norm": 3.9184999465942383, "learning_rate": 8.724858824470528e-05, "loss": 1.1804088592529296, "step": 28760 }, { "epoch": 0.8131436563210759, "grad_norm": 5.713576793670654, "learning_rate": 8.722780475027461e-05, "loss": 1.1544454574584961, "step": 28780 }, { "epoch": 0.8137087318292907, "grad_norm": 2.550511598587036, "learning_rate": 8.720700681189695e-05, "loss": 1.1171393394470215, "step": 28800 }, { "epoch": 0.8142738073375054, "grad_norm": 3.4125006198883057, "learning_rate": 8.718619443764162e-05, "loss": 1.0918364524841309, "step": 28820 }, { "epoch": 0.8148388828457203, "grad_norm": 2.5872457027435303, "learning_rate": 8.716536763558358e-05, "loss": 1.0183886528015136, "step": 28840 }, { "epoch": 0.8154039583539351, "grad_norm": 2.4287893772125244, "learning_rate": 8.714452641380337e-05, "loss": 1.0937705993652345, "step": 28860 }, { "epoch": 0.8159690338621498, "grad_norm": 3.6183319091796875, "learning_rate": 8.712367078038717e-05, "loss": 1.1363898277282716, "step": 28880 }, { "epoch": 0.8165341093703646, "grad_norm": 3.3154752254486084, "learning_rate": 8.710280074342668e-05, "loss": 1.1438787460327149, "step": 28900 }, { "epoch": 0.8170991848785794, "grad_norm": 2.934744358062744, "learning_rate": 8.708191631101925e-05, "loss": 0.9574949264526367, "step": 28920 }, { "epoch": 0.8176642603867942, "grad_norm": 4.737296104431152, "learning_rate": 8.706101749126778e-05, "loss": 1.1134632110595704, "step": 28940 }, { "epoch": 0.818229335895009, "grad_norm": 2.9953670501708984, "learning_rate": 8.704010429228078e-05, "loss": 1.19493408203125, "step": 28960 }, { "epoch": 0.8187944114032237, "grad_norm": 3.8331847190856934, "learning_rate": 8.701917672217232e-05, "loss": 1.111466121673584, "step": 28980 }, { "epoch": 0.8193594869114386, "grad_norm": 3.6679646968841553, "learning_rate": 8.699823478906204e-05, "loss": 1.1642550468444823, "step": 29000 }, { "epoch": 0.8199245624196533, "grad_norm": 3.1065564155578613, "learning_rate": 8.697727850107515e-05, "loss": 1.0823229789733886, "step": 29020 }, { "epoch": 0.8204896379278681, "grad_norm": 4.269775867462158, "learning_rate": 8.695630786634248e-05, "loss": 1.1230808258056642, "step": 29040 }, { "epoch": 0.8210547134360829, "grad_norm": 2.456606388092041, "learning_rate": 8.693532289300035e-05, "loss": 1.0863059997558593, "step": 29060 }, { "epoch": 0.8216197889442977, "grad_norm": 3.307974338531494, "learning_rate": 8.69143235891907e-05, "loss": 1.1092334747314454, "step": 29080 }, { "epoch": 0.8221848644525125, "grad_norm": 3.5139565467834473, "learning_rate": 8.6893309963061e-05, "loss": 1.1370591163635253, "step": 29100 }, { "epoch": 0.8227499399607272, "grad_norm": 3.127825975418091, "learning_rate": 8.687228202276432e-05, "loss": 1.0500480651855468, "step": 29120 }, { "epoch": 0.823315015468942, "grad_norm": 2.543907880783081, "learning_rate": 8.68512397764592e-05, "loss": 1.1380797386169434, "step": 29140 }, { "epoch": 0.8238800909771569, "grad_norm": 3.4047529697418213, "learning_rate": 8.683018323230981e-05, "loss": 1.0166851997375488, "step": 29160 }, { "epoch": 0.8244451664853716, "grad_norm": 2.33426570892334, "learning_rate": 8.680911239848585e-05, "loss": 1.0581501007080079, "step": 29180 }, { "epoch": 0.8250102419935864, "grad_norm": 3.682920455932617, "learning_rate": 8.678802728316253e-05, "loss": 1.0044283866882324, "step": 29200 }, { "epoch": 0.8255753175018011, "grad_norm": 3.220734119415283, "learning_rate": 8.676692789452065e-05, "loss": 1.0886527061462403, "step": 29220 }, { "epoch": 0.826140393010016, "grad_norm": 3.5878541469573975, "learning_rate": 8.67458142407465e-05, "loss": 1.0615223884582519, "step": 29240 }, { "epoch": 0.8267054685182308, "grad_norm": 2.9292328357696533, "learning_rate": 8.672468633003193e-05, "loss": 1.0329524040222169, "step": 29260 }, { "epoch": 0.8272705440264455, "grad_norm": 2.3202476501464844, "learning_rate": 8.670354417057434e-05, "loss": 1.1730237007141113, "step": 29280 }, { "epoch": 0.8278356195346603, "grad_norm": 3.5039172172546387, "learning_rate": 8.668238777057663e-05, "loss": 1.150660228729248, "step": 29300 }, { "epoch": 0.8284006950428751, "grad_norm": 3.333634376525879, "learning_rate": 8.666121713824719e-05, "loss": 1.1185750007629394, "step": 29320 }, { "epoch": 0.8289657705510899, "grad_norm": 2.813796043395996, "learning_rate": 8.664003228180005e-05, "loss": 1.1306690216064452, "step": 29340 }, { "epoch": 0.8295308460593047, "grad_norm": 3.111553430557251, "learning_rate": 8.661883320945461e-05, "loss": 1.005716037750244, "step": 29360 }, { "epoch": 0.8300959215675194, "grad_norm": 3.1924774646759033, "learning_rate": 8.659761992943591e-05, "loss": 1.0603718757629395, "step": 29380 }, { "epoch": 0.8306609970757343, "grad_norm": 3.7607345581054688, "learning_rate": 8.657639244997443e-05, "loss": 1.0378775596618652, "step": 29400 }, { "epoch": 0.831226072583949, "grad_norm": 3.1721696853637695, "learning_rate": 8.655515077930618e-05, "loss": 1.0000171661376953, "step": 29420 }, { "epoch": 0.8317911480921638, "grad_norm": 2.894254207611084, "learning_rate": 8.653389492567268e-05, "loss": 1.0674169540405274, "step": 29440 }, { "epoch": 0.8323562236003786, "grad_norm": 3.0401978492736816, "learning_rate": 8.651262489732096e-05, "loss": 1.0049406051635743, "step": 29460 }, { "epoch": 0.8329212991085934, "grad_norm": 4.039356708526611, "learning_rate": 8.649134070250352e-05, "loss": 1.1041462898254395, "step": 29480 }, { "epoch": 0.8334863746168082, "grad_norm": 4.038210391998291, "learning_rate": 8.647004234947838e-05, "loss": 1.0915896415710449, "step": 29500 }, { "epoch": 0.8340514501250229, "grad_norm": 3.3273491859436035, "learning_rate": 8.644872984650906e-05, "loss": 1.1733427047729492, "step": 29520 }, { "epoch": 0.8346165256332377, "grad_norm": 3.3766255378723145, "learning_rate": 8.642740320186455e-05, "loss": 1.2042576789855957, "step": 29540 }, { "epoch": 0.8351816011414526, "grad_norm": 2.859232187271118, "learning_rate": 8.640606242381933e-05, "loss": 1.0839661598205566, "step": 29560 }, { "epoch": 0.8357466766496673, "grad_norm": 3.794300079345703, "learning_rate": 8.638470752065337e-05, "loss": 1.0752289772033692, "step": 29580 }, { "epoch": 0.8363117521578821, "grad_norm": 1.921765923500061, "learning_rate": 8.636333850065214e-05, "loss": 1.0206874847412108, "step": 29600 }, { "epoch": 0.8368768276660968, "grad_norm": 3.134762763977051, "learning_rate": 8.634195537210655e-05, "loss": 1.092637538909912, "step": 29620 }, { "epoch": 0.8374419031743117, "grad_norm": 2.9508018493652344, "learning_rate": 8.6320558143313e-05, "loss": 1.0627373695373534, "step": 29640 }, { "epoch": 0.8380069786825265, "grad_norm": 4.301577091217041, "learning_rate": 8.629914682257334e-05, "loss": 1.02413969039917, "step": 29660 }, { "epoch": 0.8385720541907412, "grad_norm": 4.164079189300537, "learning_rate": 8.627772141819494e-05, "loss": 1.0478294372558594, "step": 29680 }, { "epoch": 0.839137129698956, "grad_norm": 3.2973828315734863, "learning_rate": 8.62562819384906e-05, "loss": 1.008784008026123, "step": 29700 }, { "epoch": 0.8397022052071708, "grad_norm": 3.219928741455078, "learning_rate": 8.623482839177858e-05, "loss": 0.9810276985168457, "step": 29720 }, { "epoch": 0.8402672807153856, "grad_norm": 3.9100217819213867, "learning_rate": 8.62133607863826e-05, "loss": 1.0656318664550781, "step": 29740 }, { "epoch": 0.8408323562236004, "grad_norm": 3.2150325775146484, "learning_rate": 8.619187913063185e-05, "loss": 1.1278412818908692, "step": 29760 }, { "epoch": 0.8413974317318151, "grad_norm": 3.3159232139587402, "learning_rate": 8.617038343286093e-05, "loss": 1.0497773170471192, "step": 29780 }, { "epoch": 0.84196250724003, "grad_norm": 3.8353378772735596, "learning_rate": 8.614887370140993e-05, "loss": 1.0542630195617675, "step": 29800 }, { "epoch": 0.8425275827482447, "grad_norm": 4.1637282371521, "learning_rate": 8.612734994462437e-05, "loss": 1.0841944694519043, "step": 29820 }, { "epoch": 0.8430926582564595, "grad_norm": 4.246404647827148, "learning_rate": 8.61058121708552e-05, "loss": 1.0152687072753905, "step": 29840 }, { "epoch": 0.8436577337646743, "grad_norm": 3.0257768630981445, "learning_rate": 8.608426038845885e-05, "loss": 1.1112980842590332, "step": 29860 }, { "epoch": 0.8442228092728891, "grad_norm": 2.8050572872161865, "learning_rate": 8.606269460579715e-05, "loss": 1.0705060958862305, "step": 29880 }, { "epoch": 0.8447878847811039, "grad_norm": 4.382151126861572, "learning_rate": 8.604111483123734e-05, "loss": 1.1225448608398438, "step": 29900 }, { "epoch": 0.8453529602893186, "grad_norm": 3.1844069957733154, "learning_rate": 8.601952107315216e-05, "loss": 1.0820062637329102, "step": 29920 }, { "epoch": 0.8459180357975334, "grad_norm": 2.5859670639038086, "learning_rate": 8.599791333991968e-05, "loss": 1.0717876434326172, "step": 29940 }, { "epoch": 0.8464831113057483, "grad_norm": 2.8566298484802246, "learning_rate": 8.597629163992349e-05, "loss": 1.027845859527588, "step": 29960 }, { "epoch": 0.847048186813963, "grad_norm": 2.4272563457489014, "learning_rate": 8.595465598155252e-05, "loss": 1.0005817413330078, "step": 29980 }, { "epoch": 0.8476132623221778, "grad_norm": 3.2604031562805176, "learning_rate": 8.593300637320118e-05, "loss": 1.0173312187194825, "step": 30000 }, { "epoch": 0.8481783378303925, "grad_norm": 2.988260507583618, "learning_rate": 8.591134282326924e-05, "loss": 1.0705063819885254, "step": 30020 }, { "epoch": 0.8487434133386074, "grad_norm": 3.4087233543395996, "learning_rate": 8.58896653401619e-05, "loss": 1.0854143142700194, "step": 30040 }, { "epoch": 0.8493084888468222, "grad_norm": 5.157528400421143, "learning_rate": 8.586797393228978e-05, "loss": 1.0003679275512696, "step": 30060 }, { "epoch": 0.8498735643550369, "grad_norm": 3.8187074661254883, "learning_rate": 8.584626860806888e-05, "loss": 1.0851680755615234, "step": 30080 }, { "epoch": 0.8504386398632517, "grad_norm": 2.504608392715454, "learning_rate": 8.582454937592062e-05, "loss": 1.015268611907959, "step": 30100 }, { "epoch": 0.8510037153714665, "grad_norm": 3.599480628967285, "learning_rate": 8.580281624427177e-05, "loss": 1.0390302658081054, "step": 30120 }, { "epoch": 0.8515687908796813, "grad_norm": 2.161545753479004, "learning_rate": 8.578106922155458e-05, "loss": 1.0862344741821288, "step": 30140 }, { "epoch": 0.8521338663878961, "grad_norm": 3.971409559249878, "learning_rate": 8.57593083162066e-05, "loss": 1.0791738510131836, "step": 30160 }, { "epoch": 0.8526989418961108, "grad_norm": 4.662937641143799, "learning_rate": 8.573753353667081e-05, "loss": 1.0108945846557618, "step": 30180 }, { "epoch": 0.8532640174043257, "grad_norm": 2.1990718841552734, "learning_rate": 8.571574489139558e-05, "loss": 1.0392091751098633, "step": 30200 }, { "epoch": 0.8538290929125404, "grad_norm": 2.990281581878662, "learning_rate": 8.569394238883462e-05, "loss": 1.0789323806762696, "step": 30220 }, { "epoch": 0.8543941684207552, "grad_norm": 3.633697748184204, "learning_rate": 8.567212603744707e-05, "loss": 1.149510669708252, "step": 30240 }, { "epoch": 0.85495924392897, "grad_norm": 3.2537105083465576, "learning_rate": 8.565029584569741e-05, "loss": 1.049192237854004, "step": 30260 }, { "epoch": 0.8555243194371848, "grad_norm": 3.8352086544036865, "learning_rate": 8.562845182205548e-05, "loss": 1.0777071952819823, "step": 30280 }, { "epoch": 0.8560893949453996, "grad_norm": 2.6013195514678955, "learning_rate": 8.560659397499651e-05, "loss": 1.1065954208374023, "step": 30300 }, { "epoch": 0.8566544704536143, "grad_norm": 4.142226696014404, "learning_rate": 8.55847223130011e-05, "loss": 0.9906035423278808, "step": 30320 }, { "epoch": 0.8572195459618291, "grad_norm": 3.258676052093506, "learning_rate": 8.556283684455518e-05, "loss": 1.1048202514648438, "step": 30340 }, { "epoch": 0.857784621470044, "grad_norm": 3.94787859916687, "learning_rate": 8.554093757815004e-05, "loss": 0.9553385734558105, "step": 30360 }, { "epoch": 0.8583496969782587, "grad_norm": 2.9086263179779053, "learning_rate": 8.551902452228235e-05, "loss": 1.0333238601684571, "step": 30380 }, { "epoch": 0.8589147724864735, "grad_norm": 4.452613353729248, "learning_rate": 8.549709768545412e-05, "loss": 1.0395953178405761, "step": 30400 }, { "epoch": 0.8594798479946882, "grad_norm": 3.6581575870513916, "learning_rate": 8.547515707617272e-05, "loss": 0.9492686271667481, "step": 30420 }, { "epoch": 0.8600449235029031, "grad_norm": 4.302663326263428, "learning_rate": 8.545320270295083e-05, "loss": 1.1019842147827148, "step": 30440 }, { "epoch": 0.8606099990111179, "grad_norm": 3.699313163757324, "learning_rate": 8.543123457430646e-05, "loss": 1.1284750938415526, "step": 30460 }, { "epoch": 0.8611750745193326, "grad_norm": 4.240027904510498, "learning_rate": 8.540925269876303e-05, "loss": 1.0821520805358886, "step": 30480 }, { "epoch": 0.8617401500275474, "grad_norm": 2.2717044353485107, "learning_rate": 8.53872570848492e-05, "loss": 1.1056451797485352, "step": 30500 }, { "epoch": 0.8623052255357622, "grad_norm": 3.3078932762145996, "learning_rate": 8.536524774109905e-05, "loss": 1.113498592376709, "step": 30520 }, { "epoch": 0.862870301043977, "grad_norm": 3.7862656116485596, "learning_rate": 8.534322467605192e-05, "loss": 1.0637806892395019, "step": 30540 }, { "epoch": 0.8634353765521918, "grad_norm": 3.438462734222412, "learning_rate": 8.532118789825249e-05, "loss": 1.015557098388672, "step": 30560 }, { "epoch": 0.8640004520604065, "grad_norm": 3.8059234619140625, "learning_rate": 8.52991374162508e-05, "loss": 1.1286267280578612, "step": 30580 }, { "epoch": 0.8645655275686214, "grad_norm": 3.5023508071899414, "learning_rate": 8.527707323860216e-05, "loss": 1.0403084754943848, "step": 30600 }, { "epoch": 0.8651306030768361, "grad_norm": 3.160161256790161, "learning_rate": 8.52549953738672e-05, "loss": 1.052511215209961, "step": 30620 }, { "epoch": 0.8656956785850509, "grad_norm": 3.7232048511505127, "learning_rate": 8.523290383061189e-05, "loss": 1.0782881736755372, "step": 30640 }, { "epoch": 0.8662607540932658, "grad_norm": 2.4176623821258545, "learning_rate": 8.521079861740747e-05, "loss": 1.0878229141235352, "step": 30660 }, { "epoch": 0.8668258296014805, "grad_norm": 2.8571598529815674, "learning_rate": 8.518867974283049e-05, "loss": 1.0998825073242187, "step": 30680 }, { "epoch": 0.8673909051096953, "grad_norm": 2.6383461952209473, "learning_rate": 8.516654721546283e-05, "loss": 1.068903636932373, "step": 30700 }, { "epoch": 0.86795598061791, "grad_norm": 3.3486111164093018, "learning_rate": 8.514440104389166e-05, "loss": 0.9738103866577148, "step": 30720 }, { "epoch": 0.8685210561261248, "grad_norm": 2.8780930042266846, "learning_rate": 8.51222412367094e-05, "loss": 1.061293888092041, "step": 30740 }, { "epoch": 0.8690861316343397, "grad_norm": 3.24096417427063, "learning_rate": 8.510006780251382e-05, "loss": 1.1666149139404296, "step": 30760 }, { "epoch": 0.8696512071425544, "grad_norm": 2.658208131790161, "learning_rate": 8.507788074990794e-05, "loss": 0.9861373901367188, "step": 30780 }, { "epoch": 0.8702162826507692, "grad_norm": 3.614746570587158, "learning_rate": 8.505568008750007e-05, "loss": 1.0639100074768066, "step": 30800 }, { "epoch": 0.8707813581589839, "grad_norm": 3.161921977996826, "learning_rate": 8.503346582390381e-05, "loss": 1.079721450805664, "step": 30820 }, { "epoch": 0.8713464336671988, "grad_norm": 3.3422632217407227, "learning_rate": 8.501123796773802e-05, "loss": 1.1124303817749024, "step": 30840 }, { "epoch": 0.8719115091754136, "grad_norm": 4.811054706573486, "learning_rate": 8.498899652762686e-05, "loss": 1.054161834716797, "step": 30860 }, { "epoch": 0.8724765846836283, "grad_norm": 3.525151014328003, "learning_rate": 8.496674151219972e-05, "loss": 1.123206615447998, "step": 30880 }, { "epoch": 0.8730416601918431, "grad_norm": 4.173394203186035, "learning_rate": 8.494447293009132e-05, "loss": 1.0860614776611328, "step": 30900 }, { "epoch": 0.8736067357000579, "grad_norm": 3.577860116958618, "learning_rate": 8.49221907899416e-05, "loss": 1.005933666229248, "step": 30920 }, { "epoch": 0.8741718112082727, "grad_norm": 2.970797061920166, "learning_rate": 8.489989510039571e-05, "loss": 1.0707304000854492, "step": 30940 }, { "epoch": 0.8747368867164875, "grad_norm": 3.3437700271606445, "learning_rate": 8.487758587010419e-05, "loss": 1.13539457321167, "step": 30960 }, { "epoch": 0.8753019622247022, "grad_norm": 3.458348035812378, "learning_rate": 8.485526310772272e-05, "loss": 1.0704459190368651, "step": 30980 }, { "epoch": 0.8758670377329171, "grad_norm": 3.9331226348876953, "learning_rate": 8.483292682191226e-05, "loss": 1.0865097045898438, "step": 31000 }, { "epoch": 0.8764321132411318, "grad_norm": 2.315441846847534, "learning_rate": 8.481057702133902e-05, "loss": 1.027235221862793, "step": 31020 }, { "epoch": 0.8769971887493466, "grad_norm": 3.8922910690307617, "learning_rate": 8.478821371467449e-05, "loss": 1.073345947265625, "step": 31040 }, { "epoch": 0.8775622642575615, "grad_norm": 3.1256251335144043, "learning_rate": 8.476583691059534e-05, "loss": 1.0230923652648927, "step": 31060 }, { "epoch": 0.8781273397657762, "grad_norm": 2.685415506362915, "learning_rate": 8.474344661778351e-05, "loss": 1.106724739074707, "step": 31080 }, { "epoch": 0.878692415273991, "grad_norm": 3.6417248249053955, "learning_rate": 8.472104284492619e-05, "loss": 1.017683506011963, "step": 31100 }, { "epoch": 0.8792574907822057, "grad_norm": 3.166614294052124, "learning_rate": 8.469862560071576e-05, "loss": 1.137916374206543, "step": 31120 }, { "epoch": 0.8798225662904205, "grad_norm": 3.31109619140625, "learning_rate": 8.467619489384982e-05, "loss": 1.052801513671875, "step": 31140 }, { "epoch": 0.8803876417986354, "grad_norm": 3.1824402809143066, "learning_rate": 8.465375073303127e-05, "loss": 1.0157474517822265, "step": 31160 }, { "epoch": 0.8809527173068501, "grad_norm": 3.369405508041382, "learning_rate": 8.463129312696814e-05, "loss": 1.059483528137207, "step": 31180 }, { "epoch": 0.8815177928150649, "grad_norm": 3.9994630813598633, "learning_rate": 8.460882208437373e-05, "loss": 1.077256202697754, "step": 31200 }, { "epoch": 0.8820828683232796, "grad_norm": 2.8279621601104736, "learning_rate": 8.458633761396652e-05, "loss": 1.112459659576416, "step": 31220 }, { "epoch": 0.8826479438314945, "grad_norm": 3.7829511165618896, "learning_rate": 8.456383972447027e-05, "loss": 1.0804228782653809, "step": 31240 }, { "epoch": 0.8832130193397093, "grad_norm": 4.608926296234131, "learning_rate": 8.454132842461383e-05, "loss": 1.0530016899108887, "step": 31260 }, { "epoch": 0.883778094847924, "grad_norm": 3.1780481338500977, "learning_rate": 8.451880372313136e-05, "loss": 1.0685062408447266, "step": 31280 }, { "epoch": 0.8843431703561389, "grad_norm": 3.4200377464294434, "learning_rate": 8.449626562876216e-05, "loss": 1.0001909255981445, "step": 31300 }, { "epoch": 0.8849082458643536, "grad_norm": 5.2423319816589355, "learning_rate": 8.447371415025074e-05, "loss": 1.1767945289611816, "step": 31320 }, { "epoch": 0.8854733213725684, "grad_norm": 3.7929720878601074, "learning_rate": 8.44511492963468e-05, "loss": 1.0855381965637207, "step": 31340 }, { "epoch": 0.8860383968807832, "grad_norm": 2.028491258621216, "learning_rate": 8.442857107580528e-05, "loss": 1.1263961791992188, "step": 31360 }, { "epoch": 0.886603472388998, "grad_norm": 2.678433656692505, "learning_rate": 8.440597949738621e-05, "loss": 1.028639316558838, "step": 31380 }, { "epoch": 0.8871685478972128, "grad_norm": 3.257988929748535, "learning_rate": 8.438337456985488e-05, "loss": 1.1092459678649902, "step": 31400 }, { "epoch": 0.8877336234054275, "grad_norm": 2.685262441635132, "learning_rate": 8.436075630198173e-05, "loss": 1.0934383392333984, "step": 31420 }, { "epoch": 0.8882986989136423, "grad_norm": 4.136645793914795, "learning_rate": 8.433812470254239e-05, "loss": 1.1058860778808595, "step": 31440 }, { "epoch": 0.8888637744218572, "grad_norm": 3.2653040885925293, "learning_rate": 8.431547978031762e-05, "loss": 1.0294376373291017, "step": 31460 }, { "epoch": 0.8894288499300719, "grad_norm": 3.0233688354492188, "learning_rate": 8.429282154409341e-05, "loss": 1.0908066749572753, "step": 31480 }, { "epoch": 0.8899939254382867, "grad_norm": 5.210518836975098, "learning_rate": 8.427015000266089e-05, "loss": 1.0371809005737305, "step": 31500 }, { "epoch": 0.8905590009465014, "grad_norm": 3.240288734436035, "learning_rate": 8.424746516481634e-05, "loss": 1.0842399597167969, "step": 31520 }, { "epoch": 0.8911240764547163, "grad_norm": 3.634692907333374, "learning_rate": 8.42247670393612e-05, "loss": 1.0956844329833983, "step": 31540 }, { "epoch": 0.8916891519629311, "grad_norm": 2.9561681747436523, "learning_rate": 8.420205563510208e-05, "loss": 1.0347770690917968, "step": 31560 }, { "epoch": 0.8922542274711458, "grad_norm": 6.052662372589111, "learning_rate": 8.417933096085073e-05, "loss": 0.9678061485290528, "step": 31580 }, { "epoch": 0.8928193029793606, "grad_norm": 3.2179296016693115, "learning_rate": 8.415659302542408e-05, "loss": 1.063118076324463, "step": 31600 }, { "epoch": 0.8933843784875753, "grad_norm": 3.058520793914795, "learning_rate": 8.413384183764414e-05, "loss": 1.0256499290466308, "step": 31620 }, { "epoch": 0.8939494539957902, "grad_norm": 2.895596981048584, "learning_rate": 8.411107740633814e-05, "loss": 1.0803390502929688, "step": 31640 }, { "epoch": 0.894514529504005, "grad_norm": 2.930050849914551, "learning_rate": 8.408829974033838e-05, "loss": 1.0190034866333009, "step": 31660 }, { "epoch": 0.8950796050122197, "grad_norm": 2.6700096130371094, "learning_rate": 8.406550884848235e-05, "loss": 1.0141725540161133, "step": 31680 }, { "epoch": 0.8956446805204346, "grad_norm": 4.454522132873535, "learning_rate": 8.404270473961262e-05, "loss": 0.9293667793273925, "step": 31700 }, { "epoch": 0.8962097560286493, "grad_norm": 2.8093461990356445, "learning_rate": 8.401988742257693e-05, "loss": 1.100390911102295, "step": 31720 }, { "epoch": 0.8967748315368641, "grad_norm": 2.3270421028137207, "learning_rate": 8.399705690622812e-05, "loss": 1.0962725639343263, "step": 31740 }, { "epoch": 0.8973399070450789, "grad_norm": 2.2276244163513184, "learning_rate": 8.397421319942419e-05, "loss": 1.0872962951660157, "step": 31760 }, { "epoch": 0.8979049825532937, "grad_norm": 3.713320016860962, "learning_rate": 8.395135631102816e-05, "loss": 1.120680332183838, "step": 31780 }, { "epoch": 0.8984700580615085, "grad_norm": 1.975902795791626, "learning_rate": 8.39284862499083e-05, "loss": 1.061628818511963, "step": 31800 }, { "epoch": 0.8990351335697232, "grad_norm": 2.9900074005126953, "learning_rate": 8.390560302493789e-05, "loss": 1.0766557693481444, "step": 31820 }, { "epoch": 0.899600209077938, "grad_norm": 3.8843839168548584, "learning_rate": 8.388270664499536e-05, "loss": 1.005502414703369, "step": 31840 }, { "epoch": 0.9001652845861529, "grad_norm": 3.6975300312042236, "learning_rate": 8.385979711896422e-05, "loss": 1.0039902687072755, "step": 31860 }, { "epoch": 0.9007303600943676, "grad_norm": 4.072999000549316, "learning_rate": 8.38368744557331e-05, "loss": 1.070166015625, "step": 31880 }, { "epoch": 0.9012954356025824, "grad_norm": 2.531663417816162, "learning_rate": 8.381393866419573e-05, "loss": 0.9538192749023438, "step": 31900 }, { "epoch": 0.9018605111107971, "grad_norm": 2.2098238468170166, "learning_rate": 8.379098975325094e-05, "loss": 1.0850214958190918, "step": 31920 }, { "epoch": 0.902425586619012, "grad_norm": 3.1375720500946045, "learning_rate": 8.37680277318026e-05, "loss": 1.0623967170715332, "step": 31940 }, { "epoch": 0.9029906621272268, "grad_norm": 4.253315448760986, "learning_rate": 8.374505260875973e-05, "loss": 1.02886962890625, "step": 31960 }, { "epoch": 0.9035557376354415, "grad_norm": 3.6786911487579346, "learning_rate": 8.372206439303638e-05, "loss": 1.0812843322753907, "step": 31980 }, { "epoch": 0.9041208131436563, "grad_norm": 3.843636989593506, "learning_rate": 8.369906309355173e-05, "loss": 1.026442813873291, "step": 32000 }, { "epoch": 0.9046858886518712, "grad_norm": 3.2090837955474854, "learning_rate": 8.367604871923e-05, "loss": 1.146535587310791, "step": 32020 }, { "epoch": 0.9052509641600859, "grad_norm": 3.067582607269287, "learning_rate": 8.36530212790005e-05, "loss": 0.9248588562011719, "step": 32040 }, { "epoch": 0.9058160396683007, "grad_norm": 3.0408852100372314, "learning_rate": 8.36299807817976e-05, "loss": 1.1338140487670898, "step": 32060 }, { "epoch": 0.9063811151765154, "grad_norm": 4.172349452972412, "learning_rate": 8.360692723656074e-05, "loss": 1.0622507095336915, "step": 32080 }, { "epoch": 0.9069461906847303, "grad_norm": 3.6865108013153076, "learning_rate": 8.358386065223442e-05, "loss": 0.985683822631836, "step": 32100 }, { "epoch": 0.9075112661929451, "grad_norm": 4.612514972686768, "learning_rate": 8.35607810377682e-05, "loss": 0.9995819091796875, "step": 32120 }, { "epoch": 0.9080763417011598, "grad_norm": 3.927459478378296, "learning_rate": 8.35376884021167e-05, "loss": 0.9926139831542968, "step": 32140 }, { "epoch": 0.9086414172093746, "grad_norm": 4.442288398742676, "learning_rate": 8.35145827542396e-05, "loss": 1.133796501159668, "step": 32160 }, { "epoch": 0.9092064927175894, "grad_norm": 5.570597171783447, "learning_rate": 8.34914641031016e-05, "loss": 1.1160712242126465, "step": 32180 }, { "epoch": 0.9097715682258042, "grad_norm": 2.712398052215576, "learning_rate": 8.346833245767244e-05, "loss": 1.0814056396484375, "step": 32200 }, { "epoch": 0.910336643734019, "grad_norm": 3.336122751235962, "learning_rate": 8.344518782692701e-05, "loss": 1.1120593070983886, "step": 32220 }, { "epoch": 0.9109017192422337, "grad_norm": 3.4792282581329346, "learning_rate": 8.342203021984506e-05, "loss": 1.1728772163391112, "step": 32240 }, { "epoch": 0.9114667947504486, "grad_norm": 3.2023017406463623, "learning_rate": 8.339885964541153e-05, "loss": 0.9935279846191406, "step": 32260 }, { "epoch": 0.9120318702586633, "grad_norm": 3.8574962615966797, "learning_rate": 8.337567611261627e-05, "loss": 1.1337944984436035, "step": 32280 }, { "epoch": 0.9125969457668781, "grad_norm": 3.310467481613159, "learning_rate": 8.335247963045426e-05, "loss": 1.0593778610229492, "step": 32300 }, { "epoch": 0.9131620212750929, "grad_norm": 3.05061936378479, "learning_rate": 8.332927020792545e-05, "loss": 1.0499587059020996, "step": 32320 }, { "epoch": 0.9137270967833077, "grad_norm": 4.070340156555176, "learning_rate": 8.330604785403481e-05, "loss": 1.1084916114807128, "step": 32340 }, { "epoch": 0.9142921722915225, "grad_norm": 3.2210934162139893, "learning_rate": 8.328281257779236e-05, "loss": 0.9946585655212402, "step": 32360 }, { "epoch": 0.9148572477997372, "grad_norm": 2.799654245376587, "learning_rate": 8.32595643882131e-05, "loss": 1.0503750801086427, "step": 32380 }, { "epoch": 0.915422323307952, "grad_norm": 2.857480049133301, "learning_rate": 8.323630329431703e-05, "loss": 1.0620717048645019, "step": 32400 }, { "epoch": 0.9159873988161669, "grad_norm": 3.717813014984131, "learning_rate": 8.321302930512922e-05, "loss": 1.075756549835205, "step": 32420 }, { "epoch": 0.9165524743243816, "grad_norm": 3.1162922382354736, "learning_rate": 8.318974242967967e-05, "loss": 0.9977462768554688, "step": 32440 }, { "epoch": 0.9171175498325964, "grad_norm": 3.432966947555542, "learning_rate": 8.316644267700342e-05, "loss": 1.0076152801513671, "step": 32460 }, { "epoch": 0.9176826253408111, "grad_norm": 3.3380937576293945, "learning_rate": 8.314313005614051e-05, "loss": 1.0871500968933105, "step": 32480 }, { "epoch": 0.918247700849026, "grad_norm": 4.450190544128418, "learning_rate": 8.311980457613596e-05, "loss": 1.1265153884887695, "step": 32500 }, { "epoch": 0.9188127763572408, "grad_norm": 5.270046234130859, "learning_rate": 8.309646624603975e-05, "loss": 0.9784567832946778, "step": 32520 }, { "epoch": 0.9193778518654555, "grad_norm": 3.0688328742980957, "learning_rate": 8.307311507490689e-05, "loss": 1.0461698532104493, "step": 32540 }, { "epoch": 0.9199429273736703, "grad_norm": 3.4346370697021484, "learning_rate": 8.304975107179738e-05, "loss": 0.9302179336547851, "step": 32560 }, { "epoch": 0.9205080028818851, "grad_norm": 3.9773478507995605, "learning_rate": 8.302637424577618e-05, "loss": 1.000300693511963, "step": 32580 }, { "epoch": 0.9210730783900999, "grad_norm": 2.5066230297088623, "learning_rate": 8.300298460591316e-05, "loss": 1.1088244438171386, "step": 32600 }, { "epoch": 0.9216381538983147, "grad_norm": 4.963232040405273, "learning_rate": 8.29795821612833e-05, "loss": 1.046929168701172, "step": 32620 }, { "epoch": 0.9222032294065294, "grad_norm": 2.6969218254089355, "learning_rate": 8.295616692096641e-05, "loss": 1.0742467880249023, "step": 32640 }, { "epoch": 0.9227683049147443, "grad_norm": 2.566805362701416, "learning_rate": 8.293273889404739e-05, "loss": 1.0391380310058593, "step": 32660 }, { "epoch": 0.923333380422959, "grad_norm": 4.655641078948975, "learning_rate": 8.290929808961597e-05, "loss": 1.0311264038085937, "step": 32680 }, { "epoch": 0.9238984559311738, "grad_norm": 2.99432110786438, "learning_rate": 8.28858445167669e-05, "loss": 0.9980253219604492, "step": 32700 }, { "epoch": 0.9244635314393886, "grad_norm": 2.868030309677124, "learning_rate": 8.286237818459996e-05, "loss": 1.062490749359131, "step": 32720 }, { "epoch": 0.9250286069476034, "grad_norm": 3.373154640197754, "learning_rate": 8.283889910221978e-05, "loss": 1.0122489929199219, "step": 32740 }, { "epoch": 0.9255936824558182, "grad_norm": 5.352921009063721, "learning_rate": 8.281540727873594e-05, "loss": 1.0783586502075195, "step": 32760 }, { "epoch": 0.9261587579640329, "grad_norm": 4.327433109283447, "learning_rate": 8.2791902723263e-05, "loss": 0.9881304740905762, "step": 32780 }, { "epoch": 0.9267238334722477, "grad_norm": 3.919686794281006, "learning_rate": 8.276838544492047e-05, "loss": 1.1359567642211914, "step": 32800 }, { "epoch": 0.9272889089804626, "grad_norm": 4.119050979614258, "learning_rate": 8.274485545283275e-05, "loss": 1.043861484527588, "step": 32820 }, { "epoch": 0.9278539844886773, "grad_norm": 3.214221239089966, "learning_rate": 8.27213127561292e-05, "loss": 1.116493320465088, "step": 32840 }, { "epoch": 0.9284190599968921, "grad_norm": 3.9319682121276855, "learning_rate": 8.269775736394411e-05, "loss": 1.0142326354980469, "step": 32860 }, { "epoch": 0.9289841355051068, "grad_norm": 3.1585190296173096, "learning_rate": 8.267418928541673e-05, "loss": 0.9775660514831543, "step": 32880 }, { "epoch": 0.9295492110133217, "grad_norm": 5.279801845550537, "learning_rate": 8.265060852969113e-05, "loss": 1.050508689880371, "step": 32900 }, { "epoch": 0.9301142865215365, "grad_norm": 2.626885175704956, "learning_rate": 8.26270151059164e-05, "loss": 1.0156359672546387, "step": 32920 }, { "epoch": 0.9306793620297512, "grad_norm": 3.0897722244262695, "learning_rate": 8.260340902324653e-05, "loss": 1.046427059173584, "step": 32940 }, { "epoch": 0.931244437537966, "grad_norm": 3.6115243434906006, "learning_rate": 8.257979029084035e-05, "loss": 1.0682629585266112, "step": 32960 }, { "epoch": 0.9318095130461808, "grad_norm": 3.473206043243408, "learning_rate": 8.255615891786169e-05, "loss": 0.9872307777404785, "step": 32980 }, { "epoch": 0.9323745885543956, "grad_norm": 2.1360342502593994, "learning_rate": 8.25325149134792e-05, "loss": 1.0695276260375977, "step": 33000 }, { "epoch": 0.9329396640626104, "grad_norm": 4.051977157592773, "learning_rate": 8.250885828686652e-05, "loss": 1.0566869735717774, "step": 33020 }, { "epoch": 0.9335047395708251, "grad_norm": 3.3902294635772705, "learning_rate": 8.248518904720211e-05, "loss": 0.9890046119689941, "step": 33040 }, { "epoch": 0.93406981507904, "grad_norm": 3.5924148559570312, "learning_rate": 8.246150720366937e-05, "loss": 1.0830095291137696, "step": 33060 }, { "epoch": 0.9346348905872547, "grad_norm": 2.938223123550415, "learning_rate": 8.243781276545656e-05, "loss": 1.0683791160583496, "step": 33080 }, { "epoch": 0.9351999660954695, "grad_norm": 3.061166524887085, "learning_rate": 8.241410574175688e-05, "loss": 1.1066121101379394, "step": 33100 }, { "epoch": 0.9357650416036843, "grad_norm": 3.5263140201568604, "learning_rate": 8.239038614176833e-05, "loss": 1.048383903503418, "step": 33120 }, { "epoch": 0.9363301171118991, "grad_norm": 2.80972957611084, "learning_rate": 8.236665397469383e-05, "loss": 1.016822624206543, "step": 33140 }, { "epoch": 0.9368951926201139, "grad_norm": 3.3791589736938477, "learning_rate": 8.234290924974122e-05, "loss": 1.065610122680664, "step": 33160 }, { "epoch": 0.9374602681283286, "grad_norm": 2.5459368228912354, "learning_rate": 8.231915197612314e-05, "loss": 1.0368969917297364, "step": 33180 }, { "epoch": 0.9380253436365434, "grad_norm": 3.4687767028808594, "learning_rate": 8.229538216305714e-05, "loss": 1.1671802520751953, "step": 33200 }, { "epoch": 0.9385904191447583, "grad_norm": 3.3530399799346924, "learning_rate": 8.227159981976562e-05, "loss": 1.170241641998291, "step": 33220 }, { "epoch": 0.939155494652973, "grad_norm": 2.8908212184906006, "learning_rate": 8.224780495547586e-05, "loss": 1.0234346389770508, "step": 33240 }, { "epoch": 0.9397205701611878, "grad_norm": 3.31349515914917, "learning_rate": 8.222399757941999e-05, "loss": 1.0962956428527832, "step": 33260 }, { "epoch": 0.9402856456694025, "grad_norm": 3.9144163131713867, "learning_rate": 8.220017770083497e-05, "loss": 1.0243528366088868, "step": 33280 }, { "epoch": 0.9408507211776174, "grad_norm": 2.4083542823791504, "learning_rate": 8.217634532896264e-05, "loss": 1.0728736877441407, "step": 33300 }, { "epoch": 0.9414157966858322, "grad_norm": 3.061699867248535, "learning_rate": 8.215250047304968e-05, "loss": 1.0368775367736816, "step": 33320 }, { "epoch": 0.9419808721940469, "grad_norm": 5.31147575378418, "learning_rate": 8.21286431423476e-05, "loss": 1.0501111030578614, "step": 33340 }, { "epoch": 0.9425459477022617, "grad_norm": 3.4810168743133545, "learning_rate": 8.210477334611277e-05, "loss": 0.9775117874145508, "step": 33360 }, { "epoch": 0.9431110232104765, "grad_norm": 2.19809889793396, "learning_rate": 8.208089109360639e-05, "loss": 1.0743818283081055, "step": 33380 }, { "epoch": 0.9436760987186913, "grad_norm": 4.29622220993042, "learning_rate": 8.20569963940945e-05, "loss": 1.0359272003173827, "step": 33400 }, { "epoch": 0.9442411742269061, "grad_norm": 3.035731315612793, "learning_rate": 8.203308925684794e-05, "loss": 1.0062774658203124, "step": 33420 }, { "epoch": 0.9448062497351208, "grad_norm": 3.003148078918457, "learning_rate": 8.200916969114241e-05, "loss": 1.0098413467407226, "step": 33440 }, { "epoch": 0.9453713252433357, "grad_norm": 3.844813108444214, "learning_rate": 8.198523770625841e-05, "loss": 1.0577139854431152, "step": 33460 }, { "epoch": 0.9459364007515504, "grad_norm": 3.0293021202087402, "learning_rate": 8.196129331148127e-05, "loss": 1.1258504867553711, "step": 33480 }, { "epoch": 0.9465014762597652, "grad_norm": 4.302636623382568, "learning_rate": 8.193733651610113e-05, "loss": 1.1170869827270509, "step": 33500 }, { "epoch": 0.94706655176798, "grad_norm": 4.006747722625732, "learning_rate": 8.191336732941294e-05, "loss": 1.0032535552978517, "step": 33520 }, { "epoch": 0.9476316272761948, "grad_norm": 2.8097896575927734, "learning_rate": 8.188938576071646e-05, "loss": 0.9896849632263184, "step": 33540 }, { "epoch": 0.9481967027844096, "grad_norm": 3.2382853031158447, "learning_rate": 8.186539181931627e-05, "loss": 1.059288501739502, "step": 33560 }, { "epoch": 0.9487617782926243, "grad_norm": 2.9022459983825684, "learning_rate": 8.184138551452172e-05, "loss": 0.9580639839172364, "step": 33580 }, { "epoch": 0.9493268538008391, "grad_norm": 3.811584949493408, "learning_rate": 8.181736685564698e-05, "loss": 1.0893707275390625, "step": 33600 }, { "epoch": 0.949891929309054, "grad_norm": 2.3645853996276855, "learning_rate": 8.179333585201099e-05, "loss": 1.1146355628967286, "step": 33620 }, { "epoch": 0.9504570048172687, "grad_norm": 2.688138484954834, "learning_rate": 8.17692925129375e-05, "loss": 1.137057113647461, "step": 33640 }, { "epoch": 0.9510220803254835, "grad_norm": 4.382174968719482, "learning_rate": 8.174523684775506e-05, "loss": 0.9970392227172852, "step": 33660 }, { "epoch": 0.9515871558336982, "grad_norm": 3.844996452331543, "learning_rate": 8.172116886579697e-05, "loss": 1.1160574913024903, "step": 33680 }, { "epoch": 0.9521522313419131, "grad_norm": 2.577012538909912, "learning_rate": 8.16970885764013e-05, "loss": 0.9822040557861328, "step": 33700 }, { "epoch": 0.9527173068501279, "grad_norm": 2.4089744091033936, "learning_rate": 8.167299598891096e-05, "loss": 1.0120923042297363, "step": 33720 }, { "epoch": 0.9532823823583426, "grad_norm": 4.288974285125732, "learning_rate": 8.164889111267355e-05, "loss": 1.036893081665039, "step": 33740 }, { "epoch": 0.9538474578665574, "grad_norm": 3.165203094482422, "learning_rate": 8.16247739570415e-05, "loss": 0.9759634017944336, "step": 33760 }, { "epoch": 0.9544125333747722, "grad_norm": 3.0956926345825195, "learning_rate": 8.160064453137198e-05, "loss": 1.0510124206542968, "step": 33780 }, { "epoch": 0.954977608882987, "grad_norm": 2.496335506439209, "learning_rate": 8.15765028450269e-05, "loss": 1.1016427993774414, "step": 33800 }, { "epoch": 0.9555426843912018, "grad_norm": 2.744908094406128, "learning_rate": 8.155234890737296e-05, "loss": 1.0495006561279296, "step": 33820 }, { "epoch": 0.9561077598994165, "grad_norm": 3.515721082687378, "learning_rate": 8.15281827277816e-05, "loss": 0.9818250656127929, "step": 33840 }, { "epoch": 0.9566728354076314, "grad_norm": 3.701280117034912, "learning_rate": 8.150400431562901e-05, "loss": 1.0064952850341797, "step": 33860 }, { "epoch": 0.9572379109158461, "grad_norm": 2.198913812637329, "learning_rate": 8.147981368029615e-05, "loss": 1.1159795761108398, "step": 33880 }, { "epoch": 0.9578029864240609, "grad_norm": 4.094174385070801, "learning_rate": 8.145561083116867e-05, "loss": 1.0556535720825195, "step": 33900 }, { "epoch": 0.9583680619322757, "grad_norm": 2.9766969680786133, "learning_rate": 8.143139577763701e-05, "loss": 1.028139877319336, "step": 33920 }, { "epoch": 0.9589331374404905, "grad_norm": 3.400768756866455, "learning_rate": 8.14071685290963e-05, "loss": 0.9883931159973145, "step": 33940 }, { "epoch": 0.9594982129487053, "grad_norm": 5.596562385559082, "learning_rate": 8.138292909494645e-05, "loss": 1.134099006652832, "step": 33960 }, { "epoch": 0.96006328845692, "grad_norm": 3.108863115310669, "learning_rate": 8.135867748459206e-05, "loss": 1.082033348083496, "step": 33980 }, { "epoch": 0.9606283639651348, "grad_norm": 3.7871334552764893, "learning_rate": 8.133441370744247e-05, "loss": 1.000310230255127, "step": 34000 }, { "epoch": 0.9611934394733497, "grad_norm": 4.0850396156311035, "learning_rate": 8.131013777291174e-05, "loss": 1.044931411743164, "step": 34020 }, { "epoch": 0.9617585149815644, "grad_norm": 2.2532436847686768, "learning_rate": 8.128584969041863e-05, "loss": 1.1701183319091797, "step": 34040 }, { "epoch": 0.9623235904897792, "grad_norm": 4.074802875518799, "learning_rate": 8.126154946938665e-05, "loss": 1.0061016082763672, "step": 34060 }, { "epoch": 0.9628886659979939, "grad_norm": 2.9255881309509277, "learning_rate": 8.123723711924398e-05, "loss": 1.0393710136413574, "step": 34080 }, { "epoch": 0.9634537415062088, "grad_norm": 3.177457332611084, "learning_rate": 8.121291264942354e-05, "loss": 1.0118690490722657, "step": 34100 }, { "epoch": 0.9640188170144236, "grad_norm": 4.339822769165039, "learning_rate": 8.118857606936294e-05, "loss": 1.0544870376586915, "step": 34120 }, { "epoch": 0.9645838925226383, "grad_norm": 3.6965723037719727, "learning_rate": 8.116422738850445e-05, "loss": 1.093789768218994, "step": 34140 }, { "epoch": 0.9651489680308531, "grad_norm": 2.932140350341797, "learning_rate": 8.113986661629511e-05, "loss": 1.0367231369018555, "step": 34160 }, { "epoch": 0.9657140435390679, "grad_norm": 2.8732266426086426, "learning_rate": 8.111549376218659e-05, "loss": 0.9920144081115723, "step": 34180 }, { "epoch": 0.9662791190472827, "grad_norm": 3.55737566947937, "learning_rate": 8.109110883563526e-05, "loss": 1.0446369171142578, "step": 34200 }, { "epoch": 0.9668441945554975, "grad_norm": 2.391197919845581, "learning_rate": 8.10667118461022e-05, "loss": 0.9519875526428223, "step": 34220 }, { "epoch": 0.9674092700637122, "grad_norm": 3.350170135498047, "learning_rate": 8.104230280305315e-05, "loss": 1.1588502883911134, "step": 34240 }, { "epoch": 0.9679743455719271, "grad_norm": 3.2149291038513184, "learning_rate": 8.101788171595852e-05, "loss": 1.0202189445495606, "step": 34260 }, { "epoch": 0.9685394210801418, "grad_norm": 2.376772403717041, "learning_rate": 8.099344859429341e-05, "loss": 1.099555206298828, "step": 34280 }, { "epoch": 0.9691044965883566, "grad_norm": 2.980938196182251, "learning_rate": 8.09690034475376e-05, "loss": 1.1283910751342774, "step": 34300 }, { "epoch": 0.9696695720965715, "grad_norm": 3.8482229709625244, "learning_rate": 8.094454628517546e-05, "loss": 1.027400302886963, "step": 34320 }, { "epoch": 0.9702346476047862, "grad_norm": 3.947050094604492, "learning_rate": 8.092007711669616e-05, "loss": 1.0797614097595214, "step": 34340 }, { "epoch": 0.970799723113001, "grad_norm": 3.527249813079834, "learning_rate": 8.089559595159338e-05, "loss": 1.021073341369629, "step": 34360 }, { "epoch": 0.9713647986212157, "grad_norm": 2.9085805416107178, "learning_rate": 8.087110279936554e-05, "loss": 1.0776378631591796, "step": 34380 }, { "epoch": 0.9719298741294305, "grad_norm": 1.7273950576782227, "learning_rate": 8.084659766951572e-05, "loss": 0.9870974540710449, "step": 34400 }, { "epoch": 0.9724949496376454, "grad_norm": 3.6517412662506104, "learning_rate": 8.082208057155158e-05, "loss": 0.9998081207275391, "step": 34420 }, { "epoch": 0.9730600251458601, "grad_norm": 2.672924041748047, "learning_rate": 8.079755151498549e-05, "loss": 1.0289227485656738, "step": 34440 }, { "epoch": 0.9736251006540749, "grad_norm": 2.4110591411590576, "learning_rate": 8.077301050933442e-05, "loss": 1.0067402839660644, "step": 34460 }, { "epoch": 0.9741901761622896, "grad_norm": 3.2630701065063477, "learning_rate": 8.074845756412e-05, "loss": 0.9884803771972657, "step": 34480 }, { "epoch": 0.9747552516705045, "grad_norm": 3.5743911266326904, "learning_rate": 8.072389268886847e-05, "loss": 1.050501823425293, "step": 34500 }, { "epoch": 0.9753203271787193, "grad_norm": 3.144683599472046, "learning_rate": 8.069931589311072e-05, "loss": 0.9827048301696777, "step": 34520 }, { "epoch": 0.975885402686934, "grad_norm": 3.880499839782715, "learning_rate": 8.067472718638224e-05, "loss": 1.0884591102600099, "step": 34540 }, { "epoch": 0.9764504781951489, "grad_norm": 2.6867403984069824, "learning_rate": 8.06501265782232e-05, "loss": 1.0421825408935548, "step": 34560 }, { "epoch": 0.9770155537033636, "grad_norm": 3.512033462524414, "learning_rate": 8.062551407817828e-05, "loss": 0.9974565505981445, "step": 34580 }, { "epoch": 0.9775806292115784, "grad_norm": 4.703131198883057, "learning_rate": 8.060088969579691e-05, "loss": 1.0571335792541503, "step": 34600 }, { "epoch": 0.9781457047197932, "grad_norm": 4.173259735107422, "learning_rate": 8.0576253440633e-05, "loss": 1.021451187133789, "step": 34620 }, { "epoch": 0.978710780228008, "grad_norm": 2.9028353691101074, "learning_rate": 8.055160532224514e-05, "loss": 0.9920223236083985, "step": 34640 }, { "epoch": 0.9792758557362228, "grad_norm": 3.4421300888061523, "learning_rate": 8.052694535019652e-05, "loss": 1.028670310974121, "step": 34660 }, { "epoch": 0.9798409312444375, "grad_norm": 4.611041069030762, "learning_rate": 8.05022735340549e-05, "loss": 1.0148138999938965, "step": 34680 }, { "epoch": 0.9804060067526523, "grad_norm": 3.0942234992980957, "learning_rate": 8.047758988339267e-05, "loss": 1.019493579864502, "step": 34700 }, { "epoch": 0.9809710822608672, "grad_norm": 2.8560047149658203, "learning_rate": 8.045289440778679e-05, "loss": 1.0201313972473145, "step": 34720 }, { "epoch": 0.9815361577690819, "grad_norm": 4.483311176300049, "learning_rate": 8.04281871168188e-05, "loss": 0.9656545639038085, "step": 34740 }, { "epoch": 0.9821012332772967, "grad_norm": 3.9120585918426514, "learning_rate": 8.040346802007484e-05, "loss": 1.0306537628173829, "step": 34760 }, { "epoch": 0.9826663087855114, "grad_norm": 3.3289647102355957, "learning_rate": 8.037873712714565e-05, "loss": 1.0537991523742676, "step": 34780 }, { "epoch": 0.9832313842937263, "grad_norm": 3.2281296253204346, "learning_rate": 8.03539944476265e-05, "loss": 0.974820899963379, "step": 34800 }, { "epoch": 0.9837964598019411, "grad_norm": 3.4282588958740234, "learning_rate": 8.032923999111724e-05, "loss": 0.9929211616516114, "step": 34820 }, { "epoch": 0.9843615353101558, "grad_norm": 3.7503273487091064, "learning_rate": 8.030447376722235e-05, "loss": 0.9213528633117676, "step": 34840 }, { "epoch": 0.9849266108183706, "grad_norm": 2.8744895458221436, "learning_rate": 8.027969578555079e-05, "loss": 1.0485945701599122, "step": 34860 }, { "epoch": 0.9854916863265853, "grad_norm": 3.2659809589385986, "learning_rate": 8.025490605571615e-05, "loss": 1.0863960266113282, "step": 34880 }, { "epoch": 0.9860567618348002, "grad_norm": 3.217285633087158, "learning_rate": 8.023010458733654e-05, "loss": 1.033207321166992, "step": 34900 }, { "epoch": 0.986621837343015, "grad_norm": 4.329658031463623, "learning_rate": 8.020529139003463e-05, "loss": 0.9921257019042968, "step": 34920 }, { "epoch": 0.9871869128512297, "grad_norm": 3.9736850261688232, "learning_rate": 8.018046647343767e-05, "loss": 1.039882755279541, "step": 34940 }, { "epoch": 0.9877519883594446, "grad_norm": 3.256330728530884, "learning_rate": 8.015562984717742e-05, "loss": 1.0324663162231444, "step": 34960 }, { "epoch": 0.9883170638676593, "grad_norm": 3.8504481315612793, "learning_rate": 8.013078152089018e-05, "loss": 0.9813628196716309, "step": 34980 }, { "epoch": 0.9888821393758741, "grad_norm": 3.2075369358062744, "learning_rate": 8.010592150421683e-05, "loss": 1.0186269760131836, "step": 35000 }, { "epoch": 0.9894472148840889, "grad_norm": 3.6467390060424805, "learning_rate": 8.008104980680273e-05, "loss": 1.034533405303955, "step": 35020 }, { "epoch": 0.9900122903923037, "grad_norm": 3.24259877204895, "learning_rate": 8.005616643829786e-05, "loss": 1.1291983604431153, "step": 35040 }, { "epoch": 0.9905773659005185, "grad_norm": 4.077826499938965, "learning_rate": 8.003127140835661e-05, "loss": 0.9932223320007324, "step": 35060 }, { "epoch": 0.9911424414087332, "grad_norm": 4.114977836608887, "learning_rate": 8.000636472663799e-05, "loss": 1.121729850769043, "step": 35080 }, { "epoch": 0.991707516916948, "grad_norm": 3.0445706844329834, "learning_rate": 7.99814464028055e-05, "loss": 0.9895510673522949, "step": 35100 }, { "epoch": 0.9922725924251629, "grad_norm": 2.6428301334381104, "learning_rate": 7.995651644652715e-05, "loss": 0.9932331085205078, "step": 35120 }, { "epoch": 0.9928376679333776, "grad_norm": 4.296855926513672, "learning_rate": 7.993157486747547e-05, "loss": 0.9998556137084961, "step": 35140 }, { "epoch": 0.9934027434415924, "grad_norm": 3.5239815711975098, "learning_rate": 7.990662167532747e-05, "loss": 1.0867359161376953, "step": 35160 }, { "epoch": 0.9939678189498071, "grad_norm": 4.02960205078125, "learning_rate": 7.988165687976472e-05, "loss": 1.0063796997070313, "step": 35180 }, { "epoch": 0.994532894458022, "grad_norm": 5.246978759765625, "learning_rate": 7.985668049047326e-05, "loss": 1.0074823379516602, "step": 35200 }, { "epoch": 0.9950979699662368, "grad_norm": 3.2165677547454834, "learning_rate": 7.983169251714363e-05, "loss": 1.0805810928344726, "step": 35220 }, { "epoch": 0.9956630454744515, "grad_norm": 3.4071261882781982, "learning_rate": 7.980669296947087e-05, "loss": 0.9878376007080079, "step": 35240 }, { "epoch": 0.9962281209826663, "grad_norm": 3.380387306213379, "learning_rate": 7.978168185715452e-05, "loss": 0.9783706665039062, "step": 35260 }, { "epoch": 0.996793196490881, "grad_norm": 2.713130235671997, "learning_rate": 7.975665918989858e-05, "loss": 1.0363734245300293, "step": 35280 }, { "epoch": 0.9973582719990959, "grad_norm": 2.8075716495513916, "learning_rate": 7.973162497741154e-05, "loss": 0.93017578125, "step": 35300 }, { "epoch": 0.9979233475073107, "grad_norm": 4.118582248687744, "learning_rate": 7.970657922940638e-05, "loss": 0.9896899223327636, "step": 35320 }, { "epoch": 0.9984884230155254, "grad_norm": 3.213505268096924, "learning_rate": 7.968152195560058e-05, "loss": 1.0313511848449708, "step": 35340 }, { "epoch": 0.9990534985237403, "grad_norm": 3.461583137512207, "learning_rate": 7.965645316571604e-05, "loss": 1.01361141204834, "step": 35360 }, { "epoch": 0.999618574031955, "grad_norm": 2.7539703845977783, "learning_rate": 7.963137286947917e-05, "loss": 1.0382539749145507, "step": 35380 }, { "epoch": 1.0001695226524645, "grad_norm": 2.6645798683166504, "learning_rate": 7.960628107662081e-05, "loss": 1.0966405868530273, "step": 35400 }, { "epoch": 1.0007345981606792, "grad_norm": 2.5845940113067627, "learning_rate": 7.958117779687628e-05, "loss": 1.043269443511963, "step": 35420 }, { "epoch": 1.001299673668894, "grad_norm": 2.4287054538726807, "learning_rate": 7.955606303998538e-05, "loss": 1.070742130279541, "step": 35440 }, { "epoch": 1.0018647491771089, "grad_norm": 3.520873546600342, "learning_rate": 7.95309368156923e-05, "loss": 1.0203206062316894, "step": 35460 }, { "epoch": 1.0024298246853236, "grad_norm": 3.1280152797698975, "learning_rate": 7.950579913374574e-05, "loss": 0.9812895774841308, "step": 35480 }, { "epoch": 1.0029949001935383, "grad_norm": 3.967653274536133, "learning_rate": 7.948065000389883e-05, "loss": 0.9973193168640136, "step": 35500 }, { "epoch": 1.003559975701753, "grad_norm": 2.9306893348693848, "learning_rate": 7.945548943590911e-05, "loss": 0.955479907989502, "step": 35520 }, { "epoch": 1.004125051209968, "grad_norm": 4.495151519775391, "learning_rate": 7.943031743953862e-05, "loss": 1.0700550079345703, "step": 35540 }, { "epoch": 1.0046901267181827, "grad_norm": 2.7156877517700195, "learning_rate": 7.940513402455375e-05, "loss": 1.1119354248046875, "step": 35560 }, { "epoch": 1.0052552022263974, "grad_norm": 3.5798113346099854, "learning_rate": 7.93799392007254e-05, "loss": 1.043719482421875, "step": 35580 }, { "epoch": 1.0058202777346124, "grad_norm": 4.367880821228027, "learning_rate": 7.935473297782882e-05, "loss": 1.0765525817871093, "step": 35600 }, { "epoch": 1.006385353242827, "grad_norm": 3.4893970489501953, "learning_rate": 7.932951536564381e-05, "loss": 1.0661635398864746, "step": 35620 }, { "epoch": 1.0069504287510418, "grad_norm": 3.6043622493743896, "learning_rate": 7.930428637395441e-05, "loss": 0.9220877647399902, "step": 35640 }, { "epoch": 1.0075155042592567, "grad_norm": 2.973532199859619, "learning_rate": 7.927904601254922e-05, "loss": 0.9873416900634766, "step": 35660 }, { "epoch": 1.0080805797674715, "grad_norm": 4.117000102996826, "learning_rate": 7.925379429122122e-05, "loss": 1.0272786140441894, "step": 35680 }, { "epoch": 1.0086456552756862, "grad_norm": 3.253077507019043, "learning_rate": 7.922853121976773e-05, "loss": 0.9787684440612793, "step": 35700 }, { "epoch": 1.0092107307839009, "grad_norm": 4.943368434906006, "learning_rate": 7.920325680799054e-05, "loss": 1.057875633239746, "step": 35720 }, { "epoch": 1.0097758062921158, "grad_norm": 2.2440297603607178, "learning_rate": 7.917797106569584e-05, "loss": 1.0108392715454102, "step": 35740 }, { "epoch": 1.0103408818003305, "grad_norm": 3.5851352214813232, "learning_rate": 7.915267400269417e-05, "loss": 1.0274591445922852, "step": 35760 }, { "epoch": 1.0109059573085453, "grad_norm": 3.5708460807800293, "learning_rate": 7.912736562880051e-05, "loss": 1.1284276962280273, "step": 35780 }, { "epoch": 1.0114710328167602, "grad_norm": 3.1800076961517334, "learning_rate": 7.910204595383422e-05, "loss": 1.0145906448364257, "step": 35800 }, { "epoch": 1.012036108324975, "grad_norm": 3.6094822883605957, "learning_rate": 7.9076714987619e-05, "loss": 1.0245924949645997, "step": 35820 }, { "epoch": 1.0126011838331896, "grad_norm": 3.017374038696289, "learning_rate": 7.905137273998298e-05, "loss": 1.033819580078125, "step": 35840 }, { "epoch": 1.0131662593414046, "grad_norm": 3.182204484939575, "learning_rate": 7.902601922075865e-05, "loss": 1.097272777557373, "step": 35860 }, { "epoch": 1.0137313348496193, "grad_norm": 3.2183709144592285, "learning_rate": 7.900065443978289e-05, "loss": 1.0386072158813477, "step": 35880 }, { "epoch": 1.014296410357834, "grad_norm": 2.921468496322632, "learning_rate": 7.897527840689694e-05, "loss": 1.1016776084899902, "step": 35900 }, { "epoch": 1.014861485866049, "grad_norm": 3.0249359607696533, "learning_rate": 7.894989113194636e-05, "loss": 0.997373104095459, "step": 35920 }, { "epoch": 1.0154265613742637, "grad_norm": 2.579667091369629, "learning_rate": 7.892449262478114e-05, "loss": 0.9493831634521485, "step": 35940 }, { "epoch": 1.0159916368824784, "grad_norm": 3.6140055656433105, "learning_rate": 7.88990828952556e-05, "loss": 0.9997329711914062, "step": 35960 }, { "epoch": 1.0165567123906931, "grad_norm": 4.659737586975098, "learning_rate": 7.887366195322841e-05, "loss": 0.9792832374572754, "step": 35980 }, { "epoch": 1.017121787898908, "grad_norm": 3.4436721801757812, "learning_rate": 7.884822980856258e-05, "loss": 0.9482085227966308, "step": 36000 }, { "epoch": 1.0176868634071228, "grad_norm": 3.155625581741333, "learning_rate": 7.882278647112551e-05, "loss": 1.0225546836853028, "step": 36020 }, { "epoch": 1.0182519389153375, "grad_norm": 2.744189977645874, "learning_rate": 7.879733195078889e-05, "loss": 0.995599365234375, "step": 36040 }, { "epoch": 1.0188170144235524, "grad_norm": 4.326786041259766, "learning_rate": 7.877186625742878e-05, "loss": 1.063971996307373, "step": 36060 }, { "epoch": 1.0193820899317672, "grad_norm": 3.218402862548828, "learning_rate": 7.874638940092558e-05, "loss": 1.0141793251037599, "step": 36080 }, { "epoch": 1.0199471654399819, "grad_norm": 2.870032548904419, "learning_rate": 7.872090139116397e-05, "loss": 0.9390565872192382, "step": 36100 }, { "epoch": 1.0205122409481966, "grad_norm": 3.3262715339660645, "learning_rate": 7.869540223803305e-05, "loss": 1.0259352684020997, "step": 36120 }, { "epoch": 1.0210773164564115, "grad_norm": 3.0518434047698975, "learning_rate": 7.866989195142613e-05, "loss": 0.953184986114502, "step": 36140 }, { "epoch": 1.0216423919646263, "grad_norm": 3.6384975910186768, "learning_rate": 7.864437054124095e-05, "loss": 1.022252368927002, "step": 36160 }, { "epoch": 1.022207467472841, "grad_norm": 2.8831958770751953, "learning_rate": 7.861883801737949e-05, "loss": 0.9457832336425781, "step": 36180 }, { "epoch": 1.022772542981056, "grad_norm": 2.926820755004883, "learning_rate": 7.859329438974806e-05, "loss": 1.0301363945007325, "step": 36200 }, { "epoch": 1.0233376184892706, "grad_norm": 3.52085280418396, "learning_rate": 7.85677396682573e-05, "loss": 0.9964058876037598, "step": 36220 }, { "epoch": 1.0239026939974853, "grad_norm": 2.2316744327545166, "learning_rate": 7.854217386282214e-05, "loss": 0.9434114456176758, "step": 36240 }, { "epoch": 1.0244677695057003, "grad_norm": 3.9454541206359863, "learning_rate": 7.85165969833618e-05, "loss": 1.0525879859924316, "step": 36260 }, { "epoch": 1.025032845013915, "grad_norm": 4.263220310211182, "learning_rate": 7.849100903979982e-05, "loss": 0.8940347671508789, "step": 36280 }, { "epoch": 1.0255979205221297, "grad_norm": 2.7737269401550293, "learning_rate": 7.846541004206398e-05, "loss": 1.0823739051818848, "step": 36300 }, { "epoch": 1.0261629960303447, "grad_norm": 2.16831636428833, "learning_rate": 7.843980000008644e-05, "loss": 1.042854404449463, "step": 36320 }, { "epoch": 1.0267280715385594, "grad_norm": 2.51747465133667, "learning_rate": 7.841417892380356e-05, "loss": 1.0135300636291504, "step": 36340 }, { "epoch": 1.027293147046774, "grad_norm": 3.7291035652160645, "learning_rate": 7.838854682315603e-05, "loss": 1.027707576751709, "step": 36360 }, { "epoch": 1.0278582225549888, "grad_norm": 3.910061836242676, "learning_rate": 7.83629037080888e-05, "loss": 1.0097346305847168, "step": 36380 }, { "epoch": 1.0284232980632038, "grad_norm": 3.4454612731933594, "learning_rate": 7.833724958855107e-05, "loss": 1.0945045471191406, "step": 36400 }, { "epoch": 1.0289883735714185, "grad_norm": 3.437300443649292, "learning_rate": 7.831158447449636e-05, "loss": 1.0523623466491698, "step": 36420 }, { "epoch": 1.0295534490796332, "grad_norm": 4.624603271484375, "learning_rate": 7.828590837588243e-05, "loss": 1.0528903007507324, "step": 36440 }, { "epoch": 1.0301185245878481, "grad_norm": 4.598104953765869, "learning_rate": 7.82602213026713e-05, "loss": 1.01107759475708, "step": 36460 }, { "epoch": 1.0306836000960629, "grad_norm": 2.8743412494659424, "learning_rate": 7.823452326482924e-05, "loss": 0.9418943405151368, "step": 36480 }, { "epoch": 1.0312486756042776, "grad_norm": 3.1517512798309326, "learning_rate": 7.820881427232678e-05, "loss": 1.0286005973815917, "step": 36500 }, { "epoch": 1.0318137511124923, "grad_norm": 3.083379030227661, "learning_rate": 7.818309433513872e-05, "loss": 1.0058283805847168, "step": 36520 }, { "epoch": 1.0323788266207072, "grad_norm": 3.586552619934082, "learning_rate": 7.815736346324408e-05, "loss": 1.026031494140625, "step": 36540 }, { "epoch": 1.032943902128922, "grad_norm": 3.5721700191497803, "learning_rate": 7.813162166662615e-05, "loss": 0.9348162651062012, "step": 36560 }, { "epoch": 1.0335089776371367, "grad_norm": 4.156050682067871, "learning_rate": 7.810586895527243e-05, "loss": 1.0261350631713868, "step": 36580 }, { "epoch": 1.0340740531453516, "grad_norm": 3.539520263671875, "learning_rate": 7.808010533917465e-05, "loss": 1.005007266998291, "step": 36600 }, { "epoch": 1.0346391286535663, "grad_norm": 4.613826274871826, "learning_rate": 7.805433082832881e-05, "loss": 0.9451485633850097, "step": 36620 }, { "epoch": 1.035204204161781, "grad_norm": 2.4773387908935547, "learning_rate": 7.802854543273513e-05, "loss": 0.9840297698974609, "step": 36640 }, { "epoch": 1.035769279669996, "grad_norm": 2.714794397354126, "learning_rate": 7.800274916239799e-05, "loss": 1.0059064865112304, "step": 36660 }, { "epoch": 1.0363343551782107, "grad_norm": 3.8713414669036865, "learning_rate": 7.797694202732606e-05, "loss": 1.0361931800842286, "step": 36680 }, { "epoch": 1.0368994306864254, "grad_norm": 3.2229137420654297, "learning_rate": 7.795112403753223e-05, "loss": 1.0630895614624023, "step": 36700 }, { "epoch": 1.0374645061946404, "grad_norm": 3.0496420860290527, "learning_rate": 7.792529520303354e-05, "loss": 1.062628173828125, "step": 36720 }, { "epoch": 1.038029581702855, "grad_norm": 3.209571599960327, "learning_rate": 7.789945553385129e-05, "loss": 1.0250632286071777, "step": 36740 }, { "epoch": 1.0385946572110698, "grad_norm": 3.9881699085235596, "learning_rate": 7.787360504001095e-05, "loss": 1.0545418739318848, "step": 36760 }, { "epoch": 1.0391597327192845, "grad_norm": 4.679169654846191, "learning_rate": 7.784774373154221e-05, "loss": 0.9450247764587403, "step": 36780 }, { "epoch": 1.0397248082274995, "grad_norm": 3.869781970977783, "learning_rate": 7.782187161847896e-05, "loss": 1.0260717391967773, "step": 36800 }, { "epoch": 1.0402898837357142, "grad_norm": 3.465588092803955, "learning_rate": 7.779598871085927e-05, "loss": 1.0129141807556152, "step": 36820 }, { "epoch": 1.040854959243929, "grad_norm": 3.9356508255004883, "learning_rate": 7.777009501872539e-05, "loss": 0.992302417755127, "step": 36840 }, { "epoch": 1.0414200347521438, "grad_norm": 3.2696540355682373, "learning_rate": 7.774419055212378e-05, "loss": 1.0370529174804688, "step": 36860 }, { "epoch": 1.0419851102603586, "grad_norm": 2.3645951747894287, "learning_rate": 7.771827532110506e-05, "loss": 0.958516788482666, "step": 36880 }, { "epoch": 1.0425501857685733, "grad_norm": 3.885277271270752, "learning_rate": 7.769234933572402e-05, "loss": 0.99581298828125, "step": 36900 }, { "epoch": 1.043115261276788, "grad_norm": 2.7306292057037354, "learning_rate": 7.766641260603968e-05, "loss": 1.0862607955932617, "step": 36920 }, { "epoch": 1.043680336785003, "grad_norm": 3.2010533809661865, "learning_rate": 7.764046514211513e-05, "loss": 1.0638650894165038, "step": 36940 }, { "epoch": 1.0442454122932177, "grad_norm": 3.0042712688446045, "learning_rate": 7.761450695401771e-05, "loss": 1.0093273162841796, "step": 36960 }, { "epoch": 1.0448104878014324, "grad_norm": 3.0316407680511475, "learning_rate": 7.758853805181885e-05, "loss": 0.9892303466796875, "step": 36980 }, { "epoch": 1.0453755633096473, "grad_norm": 3.701916217803955, "learning_rate": 7.756255844559424e-05, "loss": 0.9748375892639161, "step": 37000 }, { "epoch": 1.045940638817862, "grad_norm": 3.6943769454956055, "learning_rate": 7.753656814542361e-05, "loss": 0.9974026679992676, "step": 37020 }, { "epoch": 1.0465057143260768, "grad_norm": 3.044861316680908, "learning_rate": 7.75105671613909e-05, "loss": 1.0428666114807128, "step": 37040 }, { "epoch": 1.0470707898342917, "grad_norm": 3.0455431938171387, "learning_rate": 7.74845555035842e-05, "loss": 0.9061004638671875, "step": 37060 }, { "epoch": 1.0476358653425064, "grad_norm": 3.579181432723999, "learning_rate": 7.74585331820957e-05, "loss": 0.9505236625671387, "step": 37080 }, { "epoch": 1.0482009408507211, "grad_norm": 3.1453375816345215, "learning_rate": 7.743250020702177e-05, "loss": 0.9817140579223633, "step": 37100 }, { "epoch": 1.048766016358936, "grad_norm": 4.414900779724121, "learning_rate": 7.740645658846289e-05, "loss": 1.111452007293701, "step": 37120 }, { "epoch": 1.0493310918671508, "grad_norm": 4.189448833465576, "learning_rate": 7.738040233652368e-05, "loss": 1.1119712829589843, "step": 37140 }, { "epoch": 1.0498961673753655, "grad_norm": 1.8605804443359375, "learning_rate": 7.735433746131286e-05, "loss": 0.9873733520507812, "step": 37160 }, { "epoch": 1.0504612428835802, "grad_norm": 4.371017932891846, "learning_rate": 7.732826197294333e-05, "loss": 0.9915799140930176, "step": 37180 }, { "epoch": 1.0510263183917952, "grad_norm": 2.7777950763702393, "learning_rate": 7.730217588153203e-05, "loss": 1.0976120948791503, "step": 37200 }, { "epoch": 1.0515913939000099, "grad_norm": 3.676513433456421, "learning_rate": 7.72760791972001e-05, "loss": 1.0536310195922851, "step": 37220 }, { "epoch": 1.0521564694082246, "grad_norm": 2.909881114959717, "learning_rate": 7.724997193007271e-05, "loss": 0.9881084442138672, "step": 37240 }, { "epoch": 1.0527215449164395, "grad_norm": 3.292722702026367, "learning_rate": 7.722385409027916e-05, "loss": 0.9809577941894532, "step": 37260 }, { "epoch": 1.0532866204246543, "grad_norm": 3.4193742275238037, "learning_rate": 7.71977256879529e-05, "loss": 0.9418270111083984, "step": 37280 }, { "epoch": 1.053851695932869, "grad_norm": 3.3358235359191895, "learning_rate": 7.717158673323141e-05, "loss": 0.9766009330749512, "step": 37300 }, { "epoch": 1.054416771441084, "grad_norm": 3.0045948028564453, "learning_rate": 7.71454372362563e-05, "loss": 0.9127391815185547, "step": 37320 }, { "epoch": 1.0549818469492986, "grad_norm": 3.2479794025421143, "learning_rate": 7.711927720717328e-05, "loss": 1.0760738372802734, "step": 37340 }, { "epoch": 1.0555469224575134, "grad_norm": 4.874820232391357, "learning_rate": 7.709310665613212e-05, "loss": 0.9848008155822754, "step": 37360 }, { "epoch": 1.056111997965728, "grad_norm": 3.374083995819092, "learning_rate": 7.706692559328669e-05, "loss": 1.0602412223815918, "step": 37380 }, { "epoch": 1.056677073473943, "grad_norm": 3.1550185680389404, "learning_rate": 7.704073402879492e-05, "loss": 0.9944801330566406, "step": 37400 }, { "epoch": 1.0572421489821577, "grad_norm": 5.687960624694824, "learning_rate": 7.701453197281886e-05, "loss": 1.1032236099243165, "step": 37420 }, { "epoch": 1.0578072244903725, "grad_norm": 3.3948657512664795, "learning_rate": 7.698831943552454e-05, "loss": 1.0117280960083008, "step": 37440 }, { "epoch": 1.0583722999985874, "grad_norm": 3.2456846237182617, "learning_rate": 7.696209642708215e-05, "loss": 0.9824016571044922, "step": 37460 }, { "epoch": 1.0589373755068021, "grad_norm": 3.6634957790374756, "learning_rate": 7.693586295766589e-05, "loss": 1.0338809967041016, "step": 37480 }, { "epoch": 1.0595024510150168, "grad_norm": 2.816347360610962, "learning_rate": 7.690961903745407e-05, "loss": 0.9590750694274902, "step": 37500 }, { "epoch": 1.0600675265232318, "grad_norm": 2.2498703002929688, "learning_rate": 7.688336467662898e-05, "loss": 1.068280029296875, "step": 37520 }, { "epoch": 1.0606326020314465, "grad_norm": 4.095190525054932, "learning_rate": 7.685709988537704e-05, "loss": 1.013416576385498, "step": 37540 }, { "epoch": 1.0611976775396612, "grad_norm": 2.990638017654419, "learning_rate": 7.683082467388865e-05, "loss": 1.0123505592346191, "step": 37560 }, { "epoch": 1.061762753047876, "grad_norm": 2.3509294986724854, "learning_rate": 7.680453905235827e-05, "loss": 0.9682796478271485, "step": 37580 }, { "epoch": 1.0623278285560909, "grad_norm": 2.3181443214416504, "learning_rate": 7.677824303098445e-05, "loss": 1.077847671508789, "step": 37600 }, { "epoch": 1.0628929040643056, "grad_norm": 3.3609800338745117, "learning_rate": 7.675193661996969e-05, "loss": 0.9299765586853027, "step": 37620 }, { "epoch": 1.0634579795725203, "grad_norm": 2.730232000350952, "learning_rate": 7.672561982952058e-05, "loss": 0.9903326988220215, "step": 37640 }, { "epoch": 1.0640230550807352, "grad_norm": 2.957343816757202, "learning_rate": 7.669929266984774e-05, "loss": 1.0299121856689453, "step": 37660 }, { "epoch": 1.06458813058895, "grad_norm": 3.958765983581543, "learning_rate": 7.667295515116578e-05, "loss": 0.9813870429992676, "step": 37680 }, { "epoch": 1.0651532060971647, "grad_norm": 2.257554769515991, "learning_rate": 7.664660728369336e-05, "loss": 1.0445417404174804, "step": 37700 }, { "epoch": 1.0657182816053794, "grad_norm": 3.757505178451538, "learning_rate": 7.662024907765311e-05, "loss": 0.9283598899841309, "step": 37720 }, { "epoch": 1.0662833571135943, "grad_norm": 3.3665008544921875, "learning_rate": 7.659388054327175e-05, "loss": 1.052276611328125, "step": 37740 }, { "epoch": 1.066848432621809, "grad_norm": 4.430465221405029, "learning_rate": 7.65675016907799e-05, "loss": 0.976078987121582, "step": 37760 }, { "epoch": 1.0674135081300238, "grad_norm": 3.597287654876709, "learning_rate": 7.65411125304123e-05, "loss": 1.005323600769043, "step": 37780 }, { "epoch": 1.0679785836382387, "grad_norm": 2.356074333190918, "learning_rate": 7.651471307240758e-05, "loss": 0.9555392265319824, "step": 37800 }, { "epoch": 1.0685436591464534, "grad_norm": 3.281590700149536, "learning_rate": 7.648830332700847e-05, "loss": 1.020794677734375, "step": 37820 }, { "epoch": 1.0691087346546682, "grad_norm": 3.552771806716919, "learning_rate": 7.64618833044616e-05, "loss": 0.947942066192627, "step": 37840 }, { "epoch": 1.069673810162883, "grad_norm": 3.1750590801239014, "learning_rate": 7.643545301501761e-05, "loss": 0.9960015296936036, "step": 37860 }, { "epoch": 1.0702388856710978, "grad_norm": 3.695340156555176, "learning_rate": 7.640901246893118e-05, "loss": 1.0002212524414062, "step": 37880 }, { "epoch": 1.0708039611793125, "grad_norm": 4.182821750640869, "learning_rate": 7.638256167646092e-05, "loss": 1.064292049407959, "step": 37900 }, { "epoch": 1.0713690366875275, "grad_norm": 3.578566312789917, "learning_rate": 7.63561006478694e-05, "loss": 1.0975576400756837, "step": 37920 }, { "epoch": 1.0719341121957422, "grad_norm": 3.11191725730896, "learning_rate": 7.632962939342322e-05, "loss": 0.8735363006591796, "step": 37940 }, { "epoch": 1.072499187703957, "grad_norm": 3.747098922729492, "learning_rate": 7.630314792339289e-05, "loss": 1.0742524147033692, "step": 37960 }, { "epoch": 1.0730642632121716, "grad_norm": 3.8836636543273926, "learning_rate": 7.627665624805289e-05, "loss": 1.0547511100769043, "step": 37980 }, { "epoch": 1.0736293387203866, "grad_norm": 4.584456443786621, "learning_rate": 7.625015437768172e-05, "loss": 0.9821951866149903, "step": 38000 }, { "epoch": 1.0741944142286013, "grad_norm": 3.0709187984466553, "learning_rate": 7.622364232256176e-05, "loss": 0.9887774467468262, "step": 38020 }, { "epoch": 1.074759489736816, "grad_norm": 2.9176084995269775, "learning_rate": 7.619712009297939e-05, "loss": 0.9828864097595215, "step": 38040 }, { "epoch": 1.075324565245031, "grad_norm": 2.8616206645965576, "learning_rate": 7.61705876992249e-05, "loss": 1.0319249153137207, "step": 38060 }, { "epoch": 1.0758896407532457, "grad_norm": 4.729869365692139, "learning_rate": 7.614404515159257e-05, "loss": 1.0004973411560059, "step": 38080 }, { "epoch": 1.0764547162614604, "grad_norm": 2.7095203399658203, "learning_rate": 7.611749246038057e-05, "loss": 1.0226366996765137, "step": 38100 }, { "epoch": 1.077019791769675, "grad_norm": 2.6719799041748047, "learning_rate": 7.609092963589105e-05, "loss": 0.946403694152832, "step": 38120 }, { "epoch": 1.07758486727789, "grad_norm": 3.373988628387451, "learning_rate": 7.606435668843004e-05, "loss": 1.0431665420532226, "step": 38140 }, { "epoch": 1.0781499427861048, "grad_norm": 3.011425495147705, "learning_rate": 7.603777362830758e-05, "loss": 1.0137031555175782, "step": 38160 }, { "epoch": 1.0787150182943195, "grad_norm": 4.285366058349609, "learning_rate": 7.601118046583753e-05, "loss": 1.0053319931030273, "step": 38180 }, { "epoch": 1.0792800938025344, "grad_norm": 3.150245428085327, "learning_rate": 7.598457721133776e-05, "loss": 1.075758457183838, "step": 38200 }, { "epoch": 1.0798451693107491, "grad_norm": 3.577394962310791, "learning_rate": 7.595796387512998e-05, "loss": 0.9223601341247558, "step": 38220 }, { "epoch": 1.0804102448189639, "grad_norm": 3.3337976932525635, "learning_rate": 7.59313404675399e-05, "loss": 0.9814525604248047, "step": 38240 }, { "epoch": 1.0809753203271788, "grad_norm": 5.65709114074707, "learning_rate": 7.590470699889705e-05, "loss": 1.0533529281616212, "step": 38260 }, { "epoch": 1.0815403958353935, "grad_norm": 4.029707431793213, "learning_rate": 7.58780634795349e-05, "loss": 1.0616660118103027, "step": 38280 }, { "epoch": 1.0821054713436082, "grad_norm": 3.8891441822052, "learning_rate": 7.585140991979082e-05, "loss": 0.9986467361450195, "step": 38300 }, { "epoch": 1.0826705468518232, "grad_norm": 3.0334935188293457, "learning_rate": 7.58247463300061e-05, "loss": 1.0696510314941405, "step": 38320 }, { "epoch": 1.083235622360038, "grad_norm": 3.231855630874634, "learning_rate": 7.579807272052586e-05, "loss": 0.9616587638854981, "step": 38340 }, { "epoch": 1.0838006978682526, "grad_norm": 3.2324750423431396, "learning_rate": 7.577138910169917e-05, "loss": 0.9868988037109375, "step": 38360 }, { "epoch": 1.0843657733764673, "grad_norm": 3.235443115234375, "learning_rate": 7.574469548387894e-05, "loss": 1.092817497253418, "step": 38380 }, { "epoch": 1.0849308488846823, "grad_norm": 2.5955774784088135, "learning_rate": 7.571799187742203e-05, "loss": 0.9642186164855957, "step": 38400 }, { "epoch": 1.085495924392897, "grad_norm": 3.2308621406555176, "learning_rate": 7.569127829268905e-05, "loss": 0.986728286743164, "step": 38420 }, { "epoch": 1.0860609999011117, "grad_norm": 2.7046401500701904, "learning_rate": 7.566455474004459e-05, "loss": 1.0324913024902345, "step": 38440 }, { "epoch": 1.0866260754093267, "grad_norm": 4.038181304931641, "learning_rate": 7.563782122985707e-05, "loss": 1.0304251670837403, "step": 38460 }, { "epoch": 1.0871911509175414, "grad_norm": 2.171196460723877, "learning_rate": 7.561107777249876e-05, "loss": 0.9551874160766601, "step": 38480 }, { "epoch": 1.087756226425756, "grad_norm": 3.209562301635742, "learning_rate": 7.558432437834584e-05, "loss": 0.9460545539855957, "step": 38500 }, { "epoch": 1.088321301933971, "grad_norm": 3.3433640003204346, "learning_rate": 7.555756105777828e-05, "loss": 1.0097060203552246, "step": 38520 }, { "epoch": 1.0888863774421857, "grad_norm": 3.8380792140960693, "learning_rate": 7.553078782117993e-05, "loss": 0.9857352256774903, "step": 38540 }, { "epoch": 1.0894514529504005, "grad_norm": 3.527937889099121, "learning_rate": 7.55040046789385e-05, "loss": 0.9689837455749511, "step": 38560 }, { "epoch": 1.0900165284586152, "grad_norm": 3.122807502746582, "learning_rate": 7.547721164144555e-05, "loss": 0.957269287109375, "step": 38580 }, { "epoch": 1.0905816039668301, "grad_norm": 3.9181103706359863, "learning_rate": 7.545040871909641e-05, "loss": 0.9448162078857422, "step": 38600 }, { "epoch": 1.0911466794750448, "grad_norm": 3.6518185138702393, "learning_rate": 7.542359592229034e-05, "loss": 1.0325135231018066, "step": 38620 }, { "epoch": 1.0917117549832596, "grad_norm": 3.9976868629455566, "learning_rate": 7.539677326143036e-05, "loss": 0.9809359550476074, "step": 38640 }, { "epoch": 1.0922768304914745, "grad_norm": 4.115107536315918, "learning_rate": 7.536994074692336e-05, "loss": 1.0013399124145508, "step": 38660 }, { "epoch": 1.0928419059996892, "grad_norm": 3.7361724376678467, "learning_rate": 7.534309838918004e-05, "loss": 0.9042531967163085, "step": 38680 }, { "epoch": 1.093406981507904, "grad_norm": 4.8505778312683105, "learning_rate": 7.531624619861492e-05, "loss": 1.0462935447692872, "step": 38700 }, { "epoch": 1.0939720570161189, "grad_norm": 3.121140718460083, "learning_rate": 7.52893841856463e-05, "loss": 0.9046999931335449, "step": 38720 }, { "epoch": 1.0945371325243336, "grad_norm": 2.956285238265991, "learning_rate": 7.526251236069638e-05, "loss": 1.02199125289917, "step": 38740 }, { "epoch": 1.0951022080325483, "grad_norm": 4.285277366638184, "learning_rate": 7.523563073419105e-05, "loss": 1.0980982780456543, "step": 38760 }, { "epoch": 1.095667283540763, "grad_norm": 3.0363309383392334, "learning_rate": 7.520873931656011e-05, "loss": 0.9910536766052246, "step": 38780 }, { "epoch": 1.096232359048978, "grad_norm": 3.5675604343414307, "learning_rate": 7.518183811823705e-05, "loss": 1.0305127143859862, "step": 38800 }, { "epoch": 1.0967974345571927, "grad_norm": 3.447075366973877, "learning_rate": 7.51549271496593e-05, "loss": 1.0000317573547364, "step": 38820 }, { "epoch": 1.0973625100654074, "grad_norm": 2.9256322383880615, "learning_rate": 7.512800642126793e-05, "loss": 0.9970251083374023, "step": 38840 }, { "epoch": 1.0979275855736224, "grad_norm": 3.5962791442871094, "learning_rate": 7.51010759435079e-05, "loss": 0.9266630172729492, "step": 38860 }, { "epoch": 1.098492661081837, "grad_norm": 4.0508928298950195, "learning_rate": 7.507413572682788e-05, "loss": 1.1220334053039551, "step": 38880 }, { "epoch": 1.0990577365900518, "grad_norm": 4.453197479248047, "learning_rate": 7.504718578168039e-05, "loss": 0.9784603118896484, "step": 38900 }, { "epoch": 1.0996228120982667, "grad_norm": 3.246107339859009, "learning_rate": 7.502022611852169e-05, "loss": 1.0426286697387694, "step": 38920 }, { "epoch": 1.1001878876064815, "grad_norm": 3.6366589069366455, "learning_rate": 7.499325674781178e-05, "loss": 0.9759272575378418, "step": 38940 }, { "epoch": 1.1007529631146962, "grad_norm": 3.0705862045288086, "learning_rate": 7.496627768001448e-05, "loss": 0.9425864219665527, "step": 38960 }, { "epoch": 1.1013180386229109, "grad_norm": 3.7813518047332764, "learning_rate": 7.493928892559732e-05, "loss": 1.035243606567383, "step": 38980 }, { "epoch": 1.1018831141311258, "grad_norm": 2.9251856803894043, "learning_rate": 7.491229049503165e-05, "loss": 1.0084763526916505, "step": 39000 }, { "epoch": 1.1024481896393405, "grad_norm": 2.5450832843780518, "learning_rate": 7.488528239879254e-05, "loss": 0.9894542694091797, "step": 39020 }, { "epoch": 1.1030132651475553, "grad_norm": 2.479038953781128, "learning_rate": 7.48582646473588e-05, "loss": 1.0387421607971192, "step": 39040 }, { "epoch": 1.1035783406557702, "grad_norm": 2.7803544998168945, "learning_rate": 7.4831237251213e-05, "loss": 1.0197016716003418, "step": 39060 }, { "epoch": 1.104143416163985, "grad_norm": 1.8725892305374146, "learning_rate": 7.480420022084142e-05, "loss": 0.9741215705871582, "step": 39080 }, { "epoch": 1.1047084916721996, "grad_norm": 3.427762985229492, "learning_rate": 7.477715356673416e-05, "loss": 0.9360231399536133, "step": 39100 }, { "epoch": 1.1052735671804146, "grad_norm": 3.0507216453552246, "learning_rate": 7.475009729938497e-05, "loss": 0.9731344223022461, "step": 39120 }, { "epoch": 1.1058386426886293, "grad_norm": 2.86191725730896, "learning_rate": 7.472303142929136e-05, "loss": 0.9515190124511719, "step": 39140 }, { "epoch": 1.106403718196844, "grad_norm": 3.567106246948242, "learning_rate": 7.469595596695458e-05, "loss": 0.9897695541381836, "step": 39160 }, { "epoch": 1.1069687937050587, "grad_norm": 2.9512012004852295, "learning_rate": 7.466887092287957e-05, "loss": 0.9246237754821778, "step": 39180 }, { "epoch": 1.1075338692132737, "grad_norm": 2.214522123336792, "learning_rate": 7.464177630757505e-05, "loss": 0.9668663024902344, "step": 39200 }, { "epoch": 1.1080989447214884, "grad_norm": 1.824751853942871, "learning_rate": 7.461467213155334e-05, "loss": 0.940573787689209, "step": 39220 }, { "epoch": 1.1086640202297031, "grad_norm": 3.555077314376831, "learning_rate": 7.458755840533061e-05, "loss": 0.9876265525817871, "step": 39240 }, { "epoch": 1.109229095737918, "grad_norm": 2.85247540473938, "learning_rate": 7.45604351394266e-05, "loss": 0.937257194519043, "step": 39260 }, { "epoch": 1.1097941712461328, "grad_norm": 2.2302401065826416, "learning_rate": 7.453330234436486e-05, "loss": 0.9301839828491211, "step": 39280 }, { "epoch": 1.1103592467543475, "grad_norm": 3.039275646209717, "learning_rate": 7.450616003067257e-05, "loss": 0.9951457023620606, "step": 39300 }, { "epoch": 1.1109243222625624, "grad_norm": 3.1131131649017334, "learning_rate": 7.447900820888064e-05, "loss": 0.9106276512145997, "step": 39320 }, { "epoch": 1.1114893977707772, "grad_norm": 2.6450917720794678, "learning_rate": 7.445184688952366e-05, "loss": 1.0687979698181151, "step": 39340 }, { "epoch": 1.1120544732789919, "grad_norm": 3.395517587661743, "learning_rate": 7.442467608313989e-05, "loss": 1.0391197204589844, "step": 39360 }, { "epoch": 1.1126195487872066, "grad_norm": 4.5002617835998535, "learning_rate": 7.439749580027127e-05, "loss": 1.0108400344848634, "step": 39380 }, { "epoch": 1.1131846242954215, "grad_norm": 2.5805296897888184, "learning_rate": 7.437030605146345e-05, "loss": 0.9714832305908203, "step": 39400 }, { "epoch": 1.1137496998036363, "grad_norm": 2.5576300621032715, "learning_rate": 7.434310684726571e-05, "loss": 1.035959815979004, "step": 39420 }, { "epoch": 1.114314775311851, "grad_norm": 3.5160157680511475, "learning_rate": 7.431589819823104e-05, "loss": 0.986048698425293, "step": 39440 }, { "epoch": 1.114879850820066, "grad_norm": 5.055524826049805, "learning_rate": 7.428868011491604e-05, "loss": 1.0224514961242677, "step": 39460 }, { "epoch": 1.1154449263282806, "grad_norm": 3.6031031608581543, "learning_rate": 7.426145260788104e-05, "loss": 0.9938475608825683, "step": 39480 }, { "epoch": 1.1160100018364953, "grad_norm": 3.537644624710083, "learning_rate": 7.423421568768998e-05, "loss": 0.962064552307129, "step": 39500 }, { "epoch": 1.1165750773447103, "grad_norm": 3.941310405731201, "learning_rate": 7.420696936491044e-05, "loss": 0.9145100593566895, "step": 39520 }, { "epoch": 1.117140152852925, "grad_norm": 2.952526807785034, "learning_rate": 7.417971365011372e-05, "loss": 1.0088155746459961, "step": 39540 }, { "epoch": 1.1177052283611397, "grad_norm": 3.49980092048645, "learning_rate": 7.415244855387467e-05, "loss": 0.9496548652648926, "step": 39560 }, { "epoch": 1.1182703038693544, "grad_norm": 5.35536003112793, "learning_rate": 7.412517408677183e-05, "loss": 1.0410245895385741, "step": 39580 }, { "epoch": 1.1188353793775694, "grad_norm": 3.5255072116851807, "learning_rate": 7.409789025938737e-05, "loss": 1.034751033782959, "step": 39600 }, { "epoch": 1.119400454885784, "grad_norm": 2.268267869949341, "learning_rate": 7.40705970823071e-05, "loss": 1.0458937644958497, "step": 39620 }, { "epoch": 1.1199655303939988, "grad_norm": 3.2840707302093506, "learning_rate": 7.404329456612045e-05, "loss": 0.9389744758605957, "step": 39640 }, { "epoch": 1.1205306059022138, "grad_norm": 3.7053115367889404, "learning_rate": 7.401598272142046e-05, "loss": 0.9937764167785644, "step": 39660 }, { "epoch": 1.1210956814104285, "grad_norm": 3.4996321201324463, "learning_rate": 7.398866155880383e-05, "loss": 0.977287769317627, "step": 39680 }, { "epoch": 1.1216607569186432, "grad_norm": 3.020050287246704, "learning_rate": 7.396133108887082e-05, "loss": 1.0430419921875, "step": 39700 }, { "epoch": 1.1222258324268581, "grad_norm": 3.2564847469329834, "learning_rate": 7.393399132222534e-05, "loss": 0.9901755332946778, "step": 39720 }, { "epoch": 1.1227909079350729, "grad_norm": 3.8846778869628906, "learning_rate": 7.39066422694749e-05, "loss": 0.9850189208984375, "step": 39740 }, { "epoch": 1.1233559834432876, "grad_norm": 4.010267734527588, "learning_rate": 7.38792839412306e-05, "loss": 0.9676102638244629, "step": 39760 }, { "epoch": 1.1239210589515023, "grad_norm": 2.8525407314300537, "learning_rate": 7.385191634810713e-05, "loss": 0.9498796463012695, "step": 39780 }, { "epoch": 1.1244861344597172, "grad_norm": 3.7136757373809814, "learning_rate": 7.382453950072283e-05, "loss": 0.9258368492126465, "step": 39800 }, { "epoch": 1.125051209967932, "grad_norm": 2.9115145206451416, "learning_rate": 7.379715340969957e-05, "loss": 0.8899179458618164, "step": 39820 }, { "epoch": 1.1256162854761467, "grad_norm": 4.365438938140869, "learning_rate": 7.376975808566283e-05, "loss": 1.0306708335876464, "step": 39840 }, { "epoch": 1.1261813609843616, "grad_norm": 3.4748384952545166, "learning_rate": 7.374235353924166e-05, "loss": 0.930443286895752, "step": 39860 }, { "epoch": 1.1267464364925763, "grad_norm": 3.9178454875946045, "learning_rate": 7.371493978106873e-05, "loss": 0.9666380882263184, "step": 39880 }, { "epoch": 1.127311512000791, "grad_norm": 3.6745266914367676, "learning_rate": 7.368751682178022e-05, "loss": 1.025641918182373, "step": 39900 }, { "epoch": 1.127876587509006, "grad_norm": 3.866604804992676, "learning_rate": 7.366008467201592e-05, "loss": 0.971822452545166, "step": 39920 }, { "epoch": 1.1284416630172207, "grad_norm": 3.9229509830474854, "learning_rate": 7.363264334241922e-05, "loss": 0.9079953193664551, "step": 39940 }, { "epoch": 1.1290067385254354, "grad_norm": 4.084726333618164, "learning_rate": 7.360519284363696e-05, "loss": 0.9517134666442871, "step": 39960 }, { "epoch": 1.1295718140336501, "grad_norm": 2.8604753017425537, "learning_rate": 7.357773318631967e-05, "loss": 1.0081687927246095, "step": 39980 }, { "epoch": 1.130136889541865, "grad_norm": 4.622387409210205, "learning_rate": 7.355026438112135e-05, "loss": 1.0104637145996094, "step": 40000 }, { "epoch": 1.1307019650500798, "grad_norm": 2.41206431388855, "learning_rate": 7.352278643869957e-05, "loss": 0.960197925567627, "step": 40020 }, { "epoch": 1.1312670405582945, "grad_norm": 2.8949437141418457, "learning_rate": 7.349529936971542e-05, "loss": 0.9187137603759765, "step": 40040 }, { "epoch": 1.1318321160665095, "grad_norm": 3.486335277557373, "learning_rate": 7.34678031848336e-05, "loss": 1.002600860595703, "step": 40060 }, { "epoch": 1.1323971915747242, "grad_norm": 2.9603567123413086, "learning_rate": 7.344029789472229e-05, "loss": 1.0120462417602538, "step": 40080 }, { "epoch": 1.132962267082939, "grad_norm": 3.0191047191619873, "learning_rate": 7.34127835100532e-05, "loss": 1.032017707824707, "step": 40100 }, { "epoch": 1.1335273425911536, "grad_norm": 3.1739988327026367, "learning_rate": 7.338526004150159e-05, "loss": 0.9982571601867676, "step": 40120 }, { "epoch": 1.1340924180993686, "grad_norm": 3.016977548599243, "learning_rate": 7.335772749974626e-05, "loss": 0.9890530586242676, "step": 40140 }, { "epoch": 1.1346574936075833, "grad_norm": 2.6039364337921143, "learning_rate": 7.33301858954695e-05, "loss": 0.9235279083251953, "step": 40160 }, { "epoch": 1.1352225691157982, "grad_norm": 4.427135467529297, "learning_rate": 7.330263523935711e-05, "loss": 1.0039868354797363, "step": 40180 }, { "epoch": 1.135787644624013, "grad_norm": 3.602623701095581, "learning_rate": 7.327507554209842e-05, "loss": 1.01530179977417, "step": 40200 }, { "epoch": 1.1363527201322277, "grad_norm": 3.281710624694824, "learning_rate": 7.324750681438631e-05, "loss": 1.0043405532836913, "step": 40220 }, { "epoch": 1.1369177956404424, "grad_norm": 3.53810977935791, "learning_rate": 7.321992906691706e-05, "loss": 0.9305203437805176, "step": 40240 }, { "epoch": 1.1374828711486573, "grad_norm": 3.818917989730835, "learning_rate": 7.319234231039055e-05, "loss": 0.8687261581420899, "step": 40260 }, { "epoch": 1.138047946656872, "grad_norm": 2.3714332580566406, "learning_rate": 7.316474655551009e-05, "loss": 1.0290888786315917, "step": 40280 }, { "epoch": 1.1386130221650868, "grad_norm": 3.1780307292938232, "learning_rate": 7.313714181298251e-05, "loss": 1.039842700958252, "step": 40300 }, { "epoch": 1.1391780976733017, "grad_norm": 3.156935453414917, "learning_rate": 7.310952809351814e-05, "loss": 1.0897717475891113, "step": 40320 }, { "epoch": 1.1397431731815164, "grad_norm": 4.719325065612793, "learning_rate": 7.308190540783077e-05, "loss": 0.9434550285339356, "step": 40340 }, { "epoch": 1.1403082486897311, "grad_norm": 3.203748941421509, "learning_rate": 7.305427376663765e-05, "loss": 0.9243838310241699, "step": 40360 }, { "epoch": 1.1408733241979458, "grad_norm": 2.6112987995147705, "learning_rate": 7.302663318065957e-05, "loss": 1.0020133018493653, "step": 40380 }, { "epoch": 1.1414383997061608, "grad_norm": 3.6264994144439697, "learning_rate": 7.29989836606207e-05, "loss": 1.0153682708740235, "step": 40400 }, { "epoch": 1.1420034752143755, "grad_norm": 2.026503086090088, "learning_rate": 7.297132521724879e-05, "loss": 0.9738908767700195, "step": 40420 }, { "epoch": 1.1425685507225902, "grad_norm": 2.2209041118621826, "learning_rate": 7.294365786127492e-05, "loss": 1.0434295654296875, "step": 40440 }, { "epoch": 1.1431336262308052, "grad_norm": 3.254075050354004, "learning_rate": 7.291598160343374e-05, "loss": 0.9867978096008301, "step": 40460 }, { "epoch": 1.1436987017390199, "grad_norm": 3.126763343811035, "learning_rate": 7.28882964544633e-05, "loss": 0.9538382530212403, "step": 40480 }, { "epoch": 1.1442637772472346, "grad_norm": 3.45296311378479, "learning_rate": 7.286060242510511e-05, "loss": 1.0341562271118163, "step": 40500 }, { "epoch": 1.1448288527554493, "grad_norm": 4.90656042098999, "learning_rate": 7.283289952610413e-05, "loss": 0.9654019355773926, "step": 40520 }, { "epoch": 1.1453939282636643, "grad_norm": 3.4902851581573486, "learning_rate": 7.280518776820873e-05, "loss": 1.0463635444641113, "step": 40540 }, { "epoch": 1.145959003771879, "grad_norm": 3.1861989498138428, "learning_rate": 7.277746716217078e-05, "loss": 0.9837077140808106, "step": 40560 }, { "epoch": 1.146524079280094, "grad_norm": 3.169517993927002, "learning_rate": 7.274973771874551e-05, "loss": 1.0663311004638671, "step": 40580 }, { "epoch": 1.1470891547883086, "grad_norm": 5.334332466125488, "learning_rate": 7.272199944869166e-05, "loss": 1.0383809089660645, "step": 40600 }, { "epoch": 1.1476542302965234, "grad_norm": 2.6692075729370117, "learning_rate": 7.269425236277131e-05, "loss": 1.0165957450866698, "step": 40620 }, { "epoch": 1.148219305804738, "grad_norm": 2.449788808822632, "learning_rate": 7.266649647175002e-05, "loss": 0.9428220748901367, "step": 40640 }, { "epoch": 1.148784381312953, "grad_norm": 3.6668343544006348, "learning_rate": 7.263873178639674e-05, "loss": 0.9522214889526367, "step": 40660 }, { "epoch": 1.1493494568211677, "grad_norm": 3.711829423904419, "learning_rate": 7.261095831748385e-05, "loss": 0.9757204055786133, "step": 40680 }, { "epoch": 1.1499145323293825, "grad_norm": 2.881753921508789, "learning_rate": 7.258317607578712e-05, "loss": 1.0032281875610352, "step": 40700 }, { "epoch": 1.1504796078375974, "grad_norm": 2.6527554988861084, "learning_rate": 7.255538507208572e-05, "loss": 0.9165940284729004, "step": 40720 }, { "epoch": 1.1510446833458121, "grad_norm": 1.7820593118667603, "learning_rate": 7.252758531716224e-05, "loss": 0.9245631217956543, "step": 40740 }, { "epoch": 1.1516097588540268, "grad_norm": 3.434022903442383, "learning_rate": 7.249977682180267e-05, "loss": 0.9202312469482422, "step": 40760 }, { "epoch": 1.1521748343622416, "grad_norm": 2.8139631748199463, "learning_rate": 7.247195959679633e-05, "loss": 0.9153024673461914, "step": 40780 }, { "epoch": 1.1527399098704565, "grad_norm": 3.24583101272583, "learning_rate": 7.244413365293602e-05, "loss": 0.9374222755432129, "step": 40800 }, { "epoch": 1.1533049853786712, "grad_norm": 3.3017771244049072, "learning_rate": 7.241629900101787e-05, "loss": 1.0517590522766114, "step": 40820 }, { "epoch": 1.153870060886886, "grad_norm": 2.849412679672241, "learning_rate": 7.238845565184138e-05, "loss": 0.9340386390686035, "step": 40840 }, { "epoch": 1.1544351363951009, "grad_norm": 2.6533405780792236, "learning_rate": 7.236060361620943e-05, "loss": 0.9927674293518066, "step": 40860 }, { "epoch": 1.1550002119033156, "grad_norm": 4.917448043823242, "learning_rate": 7.233274290492831e-05, "loss": 1.032853889465332, "step": 40880 }, { "epoch": 1.1555652874115303, "grad_norm": 2.827329635620117, "learning_rate": 7.230487352880764e-05, "loss": 0.9310075759887695, "step": 40900 }, { "epoch": 1.1561303629197452, "grad_norm": 5.985076904296875, "learning_rate": 7.227699549866039e-05, "loss": 1.0022696495056151, "step": 40920 }, { "epoch": 1.15669543842796, "grad_norm": 5.3773393630981445, "learning_rate": 7.224910882530291e-05, "loss": 1.0477584838867187, "step": 40940 }, { "epoch": 1.1572605139361747, "grad_norm": 4.644030570983887, "learning_rate": 7.22212135195549e-05, "loss": 1.0527449607849122, "step": 40960 }, { "epoch": 1.1578255894443896, "grad_norm": 4.562978267669678, "learning_rate": 7.219330959223942e-05, "loss": 1.0028143882751466, "step": 40980 }, { "epoch": 1.1583906649526043, "grad_norm": 4.370436668395996, "learning_rate": 7.216539705418285e-05, "loss": 1.0466809272766113, "step": 41000 }, { "epoch": 1.158955740460819, "grad_norm": 3.171311616897583, "learning_rate": 7.213747591621494e-05, "loss": 1.003654670715332, "step": 41020 }, { "epoch": 1.1595208159690338, "grad_norm": 3.672703742980957, "learning_rate": 7.210954618916872e-05, "loss": 0.8550037384033203, "step": 41040 }, { "epoch": 1.1600858914772487, "grad_norm": 3.7311651706695557, "learning_rate": 7.208160788388063e-05, "loss": 0.9909395217895508, "step": 41060 }, { "epoch": 1.1606509669854634, "grad_norm": 2.6322712898254395, "learning_rate": 7.205366101119041e-05, "loss": 0.9471710205078125, "step": 41080 }, { "epoch": 1.1612160424936782, "grad_norm": 4.170153617858887, "learning_rate": 7.202570558194109e-05, "loss": 0.9716561317443848, "step": 41100 }, { "epoch": 1.161781118001893, "grad_norm": 4.172550201416016, "learning_rate": 7.199774160697904e-05, "loss": 1.0019102096557617, "step": 41120 }, { "epoch": 1.1623461935101078, "grad_norm": 2.994306802749634, "learning_rate": 7.196976909715398e-05, "loss": 0.9406082153320312, "step": 41140 }, { "epoch": 1.1629112690183225, "grad_norm": 4.011320114135742, "learning_rate": 7.194178806331889e-05, "loss": 1.0596253395080566, "step": 41160 }, { "epoch": 1.1634763445265373, "grad_norm": 2.2342312335968018, "learning_rate": 7.19137985163301e-05, "loss": 0.9797558784484863, "step": 41180 }, { "epoch": 1.1640414200347522, "grad_norm": 4.260128021240234, "learning_rate": 7.188580046704719e-05, "loss": 0.9562772750854492, "step": 41200 }, { "epoch": 1.164606495542967, "grad_norm": 4.709749221801758, "learning_rate": 7.18577939263331e-05, "loss": 1.002968978881836, "step": 41220 }, { "epoch": 1.1651715710511816, "grad_norm": 2.7687911987304688, "learning_rate": 7.182977890505403e-05, "loss": 0.9549610137939453, "step": 41240 }, { "epoch": 1.1657366465593966, "grad_norm": 3.8644495010375977, "learning_rate": 7.180175541407945e-05, "loss": 1.0054792404174804, "step": 41260 }, { "epoch": 1.1663017220676113, "grad_norm": 3.78314208984375, "learning_rate": 7.177372346428217e-05, "loss": 0.9281045913696289, "step": 41280 }, { "epoch": 1.166866797575826, "grad_norm": 3.6080751419067383, "learning_rate": 7.174568306653827e-05, "loss": 0.9450751304626465, "step": 41300 }, { "epoch": 1.167431873084041, "grad_norm": 4.454312801361084, "learning_rate": 7.171763423172704e-05, "loss": 0.9955292701721191, "step": 41320 }, { "epoch": 1.1679969485922557, "grad_norm": 4.076744556427002, "learning_rate": 7.168957697073116e-05, "loss": 0.988197135925293, "step": 41340 }, { "epoch": 1.1685620241004704, "grad_norm": 4.084256649017334, "learning_rate": 7.166151129443645e-05, "loss": 1.006606674194336, "step": 41360 }, { "epoch": 1.1691270996086853, "grad_norm": 2.2976818084716797, "learning_rate": 7.163343721373211e-05, "loss": 1.0187065124511718, "step": 41380 }, { "epoch": 1.1696921751169, "grad_norm": 4.179684162139893, "learning_rate": 7.160535473951052e-05, "loss": 1.046697998046875, "step": 41400 }, { "epoch": 1.1702572506251148, "grad_norm": 3.5276846885681152, "learning_rate": 7.157726388266737e-05, "loss": 0.8954370498657227, "step": 41420 }, { "epoch": 1.1708223261333295, "grad_norm": 3.503056049346924, "learning_rate": 7.154916465410154e-05, "loss": 0.920037841796875, "step": 41440 }, { "epoch": 1.1713874016415444, "grad_norm": 3.114919424057007, "learning_rate": 7.152105706471525e-05, "loss": 1.025162696838379, "step": 41460 }, { "epoch": 1.1719524771497591, "grad_norm": 3.1017520427703857, "learning_rate": 7.149294112541389e-05, "loss": 0.9296031951904297, "step": 41480 }, { "epoch": 1.1725175526579739, "grad_norm": 4.167130947113037, "learning_rate": 7.14648168471061e-05, "loss": 0.9692682266235352, "step": 41500 }, { "epoch": 1.1730826281661888, "grad_norm": 3.8499555587768555, "learning_rate": 7.143668424070378e-05, "loss": 1.0032439231872559, "step": 41520 }, { "epoch": 1.1736477036744035, "grad_norm": 5.106756210327148, "learning_rate": 7.140854331712204e-05, "loss": 0.9168381690979004, "step": 41540 }, { "epoch": 1.1742127791826182, "grad_norm": 3.2325942516326904, "learning_rate": 7.13803940872792e-05, "loss": 0.9723670005798339, "step": 41560 }, { "epoch": 1.174777854690833, "grad_norm": 4.900974750518799, "learning_rate": 7.135223656209691e-05, "loss": 0.9983840942382812, "step": 41580 }, { "epoch": 1.175342930199048, "grad_norm": 1.7374796867370605, "learning_rate": 7.132407075249986e-05, "loss": 1.0033929824829102, "step": 41600 }, { "epoch": 1.1759080057072626, "grad_norm": 4.223545074462891, "learning_rate": 7.12958966694161e-05, "loss": 0.9482881546020507, "step": 41620 }, { "epoch": 1.1764730812154773, "grad_norm": 2.455798387527466, "learning_rate": 7.126771432377684e-05, "loss": 0.9168926239013672, "step": 41640 }, { "epoch": 1.1770381567236923, "grad_norm": 3.5213093757629395, "learning_rate": 7.123952372651647e-05, "loss": 1.0319154739379883, "step": 41660 }, { "epoch": 1.177603232231907, "grad_norm": 3.845303773880005, "learning_rate": 7.121132488857265e-05, "loss": 0.969057559967041, "step": 41680 }, { "epoch": 1.1781683077401217, "grad_norm": 12.960716247558594, "learning_rate": 7.118311782088616e-05, "loss": 0.9286074638366699, "step": 41700 }, { "epoch": 1.1787333832483367, "grad_norm": 2.321202516555786, "learning_rate": 7.115490253440102e-05, "loss": 0.9720599174499511, "step": 41720 }, { "epoch": 1.1792984587565514, "grad_norm": 3.297739028930664, "learning_rate": 7.112667904006441e-05, "loss": 1.0396841049194336, "step": 41740 }, { "epoch": 1.179863534264766, "grad_norm": 2.5518031120300293, "learning_rate": 7.109844734882674e-05, "loss": 0.9237482070922851, "step": 41760 }, { "epoch": 1.180428609772981, "grad_norm": 6.210986137390137, "learning_rate": 7.107020747164155e-05, "loss": 0.9765764236450195, "step": 41780 }, { "epoch": 1.1809936852811957, "grad_norm": 3.0324244499206543, "learning_rate": 7.104195941946559e-05, "loss": 1.0920475959777831, "step": 41800 }, { "epoch": 1.1815587607894105, "grad_norm": 3.016444444656372, "learning_rate": 7.101370320325876e-05, "loss": 0.9779364585876464, "step": 41820 }, { "epoch": 1.1821238362976252, "grad_norm": 4.572189807891846, "learning_rate": 7.098543883398415e-05, "loss": 0.9755793571472168, "step": 41840 }, { "epoch": 1.1826889118058401, "grad_norm": 3.2712550163269043, "learning_rate": 7.0957166322608e-05, "loss": 0.9513459205627441, "step": 41860 }, { "epoch": 1.1832539873140548, "grad_norm": 3.3413219451904297, "learning_rate": 7.092888568009969e-05, "loss": 0.9637693405151367, "step": 41880 }, { "epoch": 1.1838190628222696, "grad_norm": 5.126760959625244, "learning_rate": 7.090059691743179e-05, "loss": 0.9833624839782715, "step": 41900 }, { "epoch": 1.1843841383304845, "grad_norm": 4.233065128326416, "learning_rate": 7.087230004557998e-05, "loss": 1.0281741142272949, "step": 41920 }, { "epoch": 1.1849492138386992, "grad_norm": 4.20395040512085, "learning_rate": 7.084399507552315e-05, "loss": 0.9657058715820312, "step": 41940 }, { "epoch": 1.185514289346914, "grad_norm": 2.621782064437866, "learning_rate": 7.081568201824328e-05, "loss": 1.0044838905334472, "step": 41960 }, { "epoch": 1.1860793648551287, "grad_norm": 3.663151979446411, "learning_rate": 7.078736088472549e-05, "loss": 1.0369064331054687, "step": 41980 }, { "epoch": 1.1866444403633436, "grad_norm": 4.342393398284912, "learning_rate": 7.075903168595805e-05, "loss": 0.9985282897949219, "step": 42000 }, { "epoch": 1.1872095158715583, "grad_norm": 3.3087732791900635, "learning_rate": 7.073069443293234e-05, "loss": 0.96693115234375, "step": 42020 }, { "epoch": 1.187774591379773, "grad_norm": 1.9579049348831177, "learning_rate": 7.07023491366429e-05, "loss": 0.9472528457641601, "step": 42040 }, { "epoch": 1.188339666887988, "grad_norm": 4.410978317260742, "learning_rate": 7.067399580808736e-05, "loss": 0.9675934791564942, "step": 42060 }, { "epoch": 1.1889047423962027, "grad_norm": 2.5502262115478516, "learning_rate": 7.064563445826647e-05, "loss": 0.9987469673156738, "step": 42080 }, { "epoch": 1.1894698179044174, "grad_norm": 4.7998833656311035, "learning_rate": 7.061726509818409e-05, "loss": 1.0348161697387694, "step": 42100 }, { "epoch": 1.1900348934126324, "grad_norm": 3.4670517444610596, "learning_rate": 7.058888773884725e-05, "loss": 0.9974884986877441, "step": 42120 }, { "epoch": 1.190599968920847, "grad_norm": 4.1834235191345215, "learning_rate": 7.056050239126595e-05, "loss": 0.9928597450256348, "step": 42140 }, { "epoch": 1.1911650444290618, "grad_norm": 3.7092180252075195, "learning_rate": 7.053210906645343e-05, "loss": 0.9162272453308106, "step": 42160 }, { "epoch": 1.1917301199372767, "grad_norm": 2.1599373817443848, "learning_rate": 7.050370777542591e-05, "loss": 0.9756618499755859, "step": 42180 }, { "epoch": 1.1922951954454915, "grad_norm": 2.710677146911621, "learning_rate": 7.04752985292028e-05, "loss": 0.995166015625, "step": 42200 }, { "epoch": 1.1928602709537062, "grad_norm": 3.892855644226074, "learning_rate": 7.044688133880654e-05, "loss": 0.9713832855224609, "step": 42220 }, { "epoch": 1.1934253464619209, "grad_norm": 3.8507139682769775, "learning_rate": 7.041845621526266e-05, "loss": 0.9590770721435546, "step": 42240 }, { "epoch": 1.1939904219701358, "grad_norm": 3.201751708984375, "learning_rate": 7.039002316959975e-05, "loss": 0.9096245765686035, "step": 42260 }, { "epoch": 1.1945554974783505, "grad_norm": 1.8810429573059082, "learning_rate": 7.036158221284952e-05, "loss": 0.9329017639160156, "step": 42280 }, { "epoch": 1.1951205729865653, "grad_norm": 3.162292957305908, "learning_rate": 7.033313335604674e-05, "loss": 0.974876880645752, "step": 42300 }, { "epoch": 1.1956856484947802, "grad_norm": 2.6763134002685547, "learning_rate": 7.030467661022917e-05, "loss": 1.0283337593078614, "step": 42320 }, { "epoch": 1.196250724002995, "grad_norm": 3.8335790634155273, "learning_rate": 7.027621198643775e-05, "loss": 0.9715145111083985, "step": 42340 }, { "epoch": 1.1968157995112096, "grad_norm": 3.2456297874450684, "learning_rate": 7.024773949571638e-05, "loss": 0.926666259765625, "step": 42360 }, { "epoch": 1.1973808750194244, "grad_norm": 3.7177951335906982, "learning_rate": 7.021925914911208e-05, "loss": 0.9311967849731445, "step": 42380 }, { "epoch": 1.1979459505276393, "grad_norm": 3.7379579544067383, "learning_rate": 7.019077095767486e-05, "loss": 0.975798225402832, "step": 42400 }, { "epoch": 1.198511026035854, "grad_norm": 3.229977607727051, "learning_rate": 7.016227493245779e-05, "loss": 0.973870849609375, "step": 42420 }, { "epoch": 1.1990761015440687, "grad_norm": 3.6295814514160156, "learning_rate": 7.013377108451703e-05, "loss": 0.9090520858764648, "step": 42440 }, { "epoch": 1.1996411770522837, "grad_norm": 5.08201789855957, "learning_rate": 7.010525942491172e-05, "loss": 0.9970768928527832, "step": 42460 }, { "epoch": 1.2002062525604984, "grad_norm": 2.5229010581970215, "learning_rate": 7.007673996470402e-05, "loss": 0.931947135925293, "step": 42480 }, { "epoch": 1.2007713280687131, "grad_norm": 4.1211981773376465, "learning_rate": 7.004821271495919e-05, "loss": 0.9418460845947265, "step": 42500 }, { "epoch": 1.201336403576928, "grad_norm": 2.9932730197906494, "learning_rate": 7.001967768674543e-05, "loss": 1.0177278518676758, "step": 42520 }, { "epoch": 1.2019014790851428, "grad_norm": 3.0229861736297607, "learning_rate": 6.9991134891134e-05, "loss": 1.0012431144714355, "step": 42540 }, { "epoch": 1.2024665545933575, "grad_norm": 2.6930785179138184, "learning_rate": 6.996258433919917e-05, "loss": 1.0690831184387206, "step": 42560 }, { "epoch": 1.2030316301015724, "grad_norm": 3.0498225688934326, "learning_rate": 6.99340260420182e-05, "loss": 1.0152033805847167, "step": 42580 }, { "epoch": 1.2035967056097872, "grad_norm": 4.2454962730407715, "learning_rate": 6.990546001067139e-05, "loss": 0.9908872604370117, "step": 42600 }, { "epoch": 1.2041617811180019, "grad_norm": 2.724360466003418, "learning_rate": 6.987688625624203e-05, "loss": 0.9550628662109375, "step": 42620 }, { "epoch": 1.2047268566262166, "grad_norm": 3.3541789054870605, "learning_rate": 6.984830478981636e-05, "loss": 0.9618684768676757, "step": 42640 }, { "epoch": 1.2052919321344315, "grad_norm": 3.7161288261413574, "learning_rate": 6.981971562248369e-05, "loss": 0.9236983299255371, "step": 42660 }, { "epoch": 1.2058570076426463, "grad_norm": 4.218156337738037, "learning_rate": 6.979111876533627e-05, "loss": 0.9442918777465821, "step": 42680 }, { "epoch": 1.206422083150861, "grad_norm": 2.293588399887085, "learning_rate": 6.976251422946931e-05, "loss": 1.0101681709289552, "step": 42700 }, { "epoch": 1.206987158659076, "grad_norm": 3.3304402828216553, "learning_rate": 6.973390202598107e-05, "loss": 0.9437599182128906, "step": 42720 }, { "epoch": 1.2075522341672906, "grad_norm": 3.904642343521118, "learning_rate": 6.970528216597273e-05, "loss": 0.8733310699462891, "step": 42740 }, { "epoch": 1.2081173096755053, "grad_norm": 4.940030574798584, "learning_rate": 6.967665466054844e-05, "loss": 0.9309611320495605, "step": 42760 }, { "epoch": 1.20868238518372, "grad_norm": 4.4413299560546875, "learning_rate": 6.964801952081537e-05, "loss": 0.993918514251709, "step": 42780 }, { "epoch": 1.209247460691935, "grad_norm": 2.38938307762146, "learning_rate": 6.96193767578836e-05, "loss": 0.9347169876098633, "step": 42800 }, { "epoch": 1.2098125362001497, "grad_norm": 3.3973145484924316, "learning_rate": 6.959072638286616e-05, "loss": 0.9439720153808594, "step": 42820 }, { "epoch": 1.2103776117083644, "grad_norm": 2.9822123050689697, "learning_rate": 6.956206840687906e-05, "loss": 0.890068244934082, "step": 42840 }, { "epoch": 1.2109426872165794, "grad_norm": 3.0699079036712646, "learning_rate": 6.95334028410413e-05, "loss": 0.9998027801513671, "step": 42860 }, { "epoch": 1.211507762724794, "grad_norm": 4.394340991973877, "learning_rate": 6.950472969647473e-05, "loss": 0.9931649208068848, "step": 42880 }, { "epoch": 1.2120728382330088, "grad_norm": 3.6600685119628906, "learning_rate": 6.947604898430423e-05, "loss": 1.038508129119873, "step": 42900 }, { "epoch": 1.2126379137412238, "grad_norm": 2.9354639053344727, "learning_rate": 6.944736071565753e-05, "loss": 0.9525836944580078, "step": 42920 }, { "epoch": 1.2132029892494385, "grad_norm": 3.0852160453796387, "learning_rate": 6.941866490166536e-05, "loss": 1.0459837913513184, "step": 42940 }, { "epoch": 1.2137680647576532, "grad_norm": 3.504690408706665, "learning_rate": 6.938996155346137e-05, "loss": 0.9989568710327148, "step": 42960 }, { "epoch": 1.2143331402658681, "grad_norm": 2.917940378189087, "learning_rate": 6.936125068218211e-05, "loss": 1.0036410331726073, "step": 42980 }, { "epoch": 1.2148982157740829, "grad_norm": 4.3950371742248535, "learning_rate": 6.933253229896706e-05, "loss": 1.0237505912780762, "step": 43000 }, { "epoch": 1.2154632912822976, "grad_norm": 5.363417625427246, "learning_rate": 6.93038064149586e-05, "loss": 0.910644245147705, "step": 43020 }, { "epoch": 1.2160283667905123, "grad_norm": 4.389266014099121, "learning_rate": 6.927507304130204e-05, "loss": 0.9843008041381835, "step": 43040 }, { "epoch": 1.2165934422987272, "grad_norm": 4.751115798950195, "learning_rate": 6.92463321891456e-05, "loss": 0.9315640449523925, "step": 43060 }, { "epoch": 1.217158517806942, "grad_norm": 2.833263874053955, "learning_rate": 6.921758386964036e-05, "loss": 0.9754644393920898, "step": 43080 }, { "epoch": 1.2177235933151567, "grad_norm": 3.187377452850342, "learning_rate": 6.918882809394035e-05, "loss": 1.0203474044799805, "step": 43100 }, { "epoch": 1.2182886688233716, "grad_norm": 3.3716249465942383, "learning_rate": 6.916006487320247e-05, "loss": 0.9750003814697266, "step": 43120 }, { "epoch": 1.2188537443315863, "grad_norm": 2.353433609008789, "learning_rate": 6.913129421858649e-05, "loss": 0.9522801399230957, "step": 43140 }, { "epoch": 1.219418819839801, "grad_norm": 5.130143642425537, "learning_rate": 6.910251614125512e-05, "loss": 1.0652427673339844, "step": 43160 }, { "epoch": 1.2199838953480158, "grad_norm": 2.7160484790802, "learning_rate": 6.907373065237388e-05, "loss": 0.9656452178955078, "step": 43180 }, { "epoch": 1.2205489708562307, "grad_norm": 3.9822094440460205, "learning_rate": 6.904493776311122e-05, "loss": 0.9575413703918457, "step": 43200 }, { "epoch": 1.2211140463644454, "grad_norm": 3.5308876037597656, "learning_rate": 6.901613748463841e-05, "loss": 0.989326000213623, "step": 43220 }, { "epoch": 1.2216791218726601, "grad_norm": 3.848480701446533, "learning_rate": 6.898732982812966e-05, "loss": 0.9589388847351075, "step": 43240 }, { "epoch": 1.222244197380875, "grad_norm": 2.8888635635375977, "learning_rate": 6.895851480476194e-05, "loss": 1.0103403091430665, "step": 43260 }, { "epoch": 1.2228092728890898, "grad_norm": 3.987316608428955, "learning_rate": 6.89296924257152e-05, "loss": 0.9313543319702149, "step": 43280 }, { "epoch": 1.2233743483973045, "grad_norm": 3.3276426792144775, "learning_rate": 6.890086270217213e-05, "loss": 0.9708652496337891, "step": 43300 }, { "epoch": 1.2239394239055195, "grad_norm": 3.594454288482666, "learning_rate": 6.887202564531838e-05, "loss": 0.9684059143066406, "step": 43320 }, { "epoch": 1.2245044994137342, "grad_norm": 3.3977153301239014, "learning_rate": 6.884318126634233e-05, "loss": 0.9694732666015625, "step": 43340 }, { "epoch": 1.225069574921949, "grad_norm": 3.3195407390594482, "learning_rate": 6.881432957643527e-05, "loss": 1.0601467132568358, "step": 43360 }, { "epoch": 1.2256346504301638, "grad_norm": 3.018970489501953, "learning_rate": 6.878547058679134e-05, "loss": 0.924806785583496, "step": 43380 }, { "epoch": 1.2261997259383786, "grad_norm": 2.6761536598205566, "learning_rate": 6.875660430860746e-05, "loss": 0.9576136589050293, "step": 43400 }, { "epoch": 1.2267648014465933, "grad_norm": 2.8889822959899902, "learning_rate": 6.87277307530834e-05, "loss": 0.9608955383300781, "step": 43420 }, { "epoch": 1.227329876954808, "grad_norm": 4.549287796020508, "learning_rate": 6.869884993142179e-05, "loss": 0.9138278961181641, "step": 43440 }, { "epoch": 1.227894952463023, "grad_norm": 4.5117597579956055, "learning_rate": 6.8669961854828e-05, "loss": 0.9999268531799317, "step": 43460 }, { "epoch": 1.2284600279712377, "grad_norm": 3.9682109355926514, "learning_rate": 6.864106653451032e-05, "loss": 0.8926235198974609, "step": 43480 }, { "epoch": 1.2290251034794524, "grad_norm": 3.6427860260009766, "learning_rate": 6.861216398167974e-05, "loss": 0.9802837371826172, "step": 43500 }, { "epoch": 1.2295901789876673, "grad_norm": 3.873497486114502, "learning_rate": 6.858325420755014e-05, "loss": 0.8964035987854004, "step": 43520 }, { "epoch": 1.230155254495882, "grad_norm": 2.7759206295013428, "learning_rate": 6.855433722333816e-05, "loss": 0.9988300323486328, "step": 43540 }, { "epoch": 1.2307203300040968, "grad_norm": 4.278314113616943, "learning_rate": 6.852541304026322e-05, "loss": 0.9730152130126953, "step": 43560 }, { "epoch": 1.2312854055123115, "grad_norm": 3.38670015335083, "learning_rate": 6.84964816695476e-05, "loss": 1.0392081260681152, "step": 43580 }, { "epoch": 1.2318504810205264, "grad_norm": 2.8148937225341797, "learning_rate": 6.84675431224163e-05, "loss": 0.9886189460754394, "step": 43600 }, { "epoch": 1.2324155565287411, "grad_norm": 5.028697967529297, "learning_rate": 6.843859741009717e-05, "loss": 0.9616106033325196, "step": 43620 }, { "epoch": 1.2329806320369558, "grad_norm": 2.2992002964019775, "learning_rate": 6.840964454382076e-05, "loss": 1.0219496726989745, "step": 43640 }, { "epoch": 1.2335457075451708, "grad_norm": 3.0311601161956787, "learning_rate": 6.838068453482045e-05, "loss": 0.939143180847168, "step": 43660 }, { "epoch": 1.2341107830533855, "grad_norm": 2.478555202484131, "learning_rate": 6.83517173943324e-05, "loss": 0.939762020111084, "step": 43680 }, { "epoch": 1.2346758585616002, "grad_norm": 2.354318857192993, "learning_rate": 6.832274313359551e-05, "loss": 0.9469493865966797, "step": 43700 }, { "epoch": 1.2352409340698152, "grad_norm": 3.7769877910614014, "learning_rate": 6.829376176385144e-05, "loss": 0.9528867721557617, "step": 43720 }, { "epoch": 1.2358060095780299, "grad_norm": 3.2887954711914062, "learning_rate": 6.826477329634462e-05, "loss": 1.006704044342041, "step": 43740 }, { "epoch": 1.2363710850862446, "grad_norm": 5.070285320281982, "learning_rate": 6.823577774232223e-05, "loss": 0.9966574668884277, "step": 43760 }, { "epoch": 1.2369361605944595, "grad_norm": 2.738293170928955, "learning_rate": 6.820677511303424e-05, "loss": 0.8869481086730957, "step": 43780 }, { "epoch": 1.2375012361026743, "grad_norm": 3.8985986709594727, "learning_rate": 6.817776541973326e-05, "loss": 0.8858503341674805, "step": 43800 }, { "epoch": 1.238066311610889, "grad_norm": 4.761708736419678, "learning_rate": 6.814874867367476e-05, "loss": 0.9320609092712402, "step": 43820 }, { "epoch": 1.2386313871191037, "grad_norm": 3.5121195316314697, "learning_rate": 6.811972488611686e-05, "loss": 0.8837522506713867, "step": 43840 }, { "epoch": 1.2391964626273186, "grad_norm": 2.4500274658203125, "learning_rate": 6.809069406832047e-05, "loss": 0.9836021423339844, "step": 43860 }, { "epoch": 1.2397615381355334, "grad_norm": 6.064455032348633, "learning_rate": 6.806165623154919e-05, "loss": 0.9712398529052735, "step": 43880 }, { "epoch": 1.240326613643748, "grad_norm": 3.559877634048462, "learning_rate": 6.803261138706935e-05, "loss": 1.031619930267334, "step": 43900 }, { "epoch": 1.240891689151963, "grad_norm": 2.694277763366699, "learning_rate": 6.800355954615002e-05, "loss": 0.9864907264709473, "step": 43920 }, { "epoch": 1.2414567646601777, "grad_norm": 2.963761568069458, "learning_rate": 6.797450072006297e-05, "loss": 0.9261929512023925, "step": 43940 }, { "epoch": 1.2420218401683925, "grad_norm": 2.9365837574005127, "learning_rate": 6.794543492008266e-05, "loss": 1.0146425247192383, "step": 43960 }, { "epoch": 1.2425869156766072, "grad_norm": 2.889147996902466, "learning_rate": 6.791636215748631e-05, "loss": 1.0222529411315917, "step": 43980 }, { "epoch": 1.2431519911848221, "grad_norm": 3.201814651489258, "learning_rate": 6.788728244355378e-05, "loss": 1.0143423080444336, "step": 44000 }, { "epoch": 1.2437170666930368, "grad_norm": 3.1302778720855713, "learning_rate": 6.785819578956766e-05, "loss": 1.0144203186035157, "step": 44020 }, { "epoch": 1.2442821422012516, "grad_norm": 3.213663101196289, "learning_rate": 6.782910220681323e-05, "loss": 0.9917882919311524, "step": 44040 }, { "epoch": 1.2448472177094665, "grad_norm": 4.5132856369018555, "learning_rate": 6.780000170657846e-05, "loss": 0.9190305709838867, "step": 44060 }, { "epoch": 1.2454122932176812, "grad_norm": 1.601010799407959, "learning_rate": 6.777089430015399e-05, "loss": 0.8899415969848633, "step": 44080 }, { "epoch": 1.245977368725896, "grad_norm": 4.86775541305542, "learning_rate": 6.774177999883316e-05, "loss": 1.023551845550537, "step": 44100 }, { "epoch": 1.2465424442341109, "grad_norm": 5.531378269195557, "learning_rate": 6.771265881391194e-05, "loss": 0.9679471969604492, "step": 44120 }, { "epoch": 1.2471075197423256, "grad_norm": 2.6171059608459473, "learning_rate": 6.768353075668906e-05, "loss": 0.9155619621276856, "step": 44140 }, { "epoch": 1.2476725952505403, "grad_norm": 3.059351682662964, "learning_rate": 6.765439583846582e-05, "loss": 0.9761107444763184, "step": 44160 }, { "epoch": 1.2482376707587552, "grad_norm": 3.4885480403900146, "learning_rate": 6.762525407054624e-05, "loss": 1.0671459197998048, "step": 44180 }, { "epoch": 1.24880274626697, "grad_norm": 3.0216708183288574, "learning_rate": 6.759610546423697e-05, "loss": 0.9355131149291992, "step": 44200 }, { "epoch": 1.2493678217751847, "grad_norm": 2.1557185649871826, "learning_rate": 6.756695003084734e-05, "loss": 0.9455679893493653, "step": 44220 }, { "epoch": 1.2499328972833994, "grad_norm": 3.5249392986297607, "learning_rate": 6.753778778168929e-05, "loss": 1.0366140365600587, "step": 44240 }, { "epoch": 1.2504979727916143, "grad_norm": 3.1694624423980713, "learning_rate": 6.750861872807743e-05, "loss": 0.9456661224365235, "step": 44260 }, { "epoch": 1.251063048299829, "grad_norm": 3.592705726623535, "learning_rate": 6.747944288132903e-05, "loss": 0.8147476196289063, "step": 44280 }, { "epoch": 1.2516281238080438, "grad_norm": 3.0480713844299316, "learning_rate": 6.745026025276396e-05, "loss": 0.8763651847839355, "step": 44300 }, { "epoch": 1.2521931993162587, "grad_norm": 2.8567817211151123, "learning_rate": 6.742107085370474e-05, "loss": 0.9094325065612793, "step": 44320 }, { "epoch": 1.2527582748244734, "grad_norm": 4.238839149475098, "learning_rate": 6.739187469547648e-05, "loss": 0.9724370956420898, "step": 44340 }, { "epoch": 1.2533233503326882, "grad_norm": 3.7442026138305664, "learning_rate": 6.736267178940699e-05, "loss": 0.9977827072143555, "step": 44360 }, { "epoch": 1.2538884258409029, "grad_norm": 3.5377211570739746, "learning_rate": 6.733346214682663e-05, "loss": 1.0021103858947753, "step": 44380 }, { "epoch": 1.2544535013491178, "grad_norm": 2.7872419357299805, "learning_rate": 6.730424577906838e-05, "loss": 0.9013642311096192, "step": 44400 }, { "epoch": 1.2550185768573325, "grad_norm": 3.8819661140441895, "learning_rate": 6.727502269746784e-05, "loss": 0.9864592552185059, "step": 44420 }, { "epoch": 1.2555836523655475, "grad_norm": 4.437226295471191, "learning_rate": 6.724579291336326e-05, "loss": 0.9238091468811035, "step": 44440 }, { "epoch": 1.2561487278737622, "grad_norm": 3.1164498329162598, "learning_rate": 6.721655643809542e-05, "loss": 0.9895762443542481, "step": 44460 }, { "epoch": 1.256713803381977, "grad_norm": 3.5623903274536133, "learning_rate": 6.718731328300775e-05, "loss": 0.9766133308410645, "step": 44480 }, { "epoch": 1.2572788788901916, "grad_norm": 4.225927829742432, "learning_rate": 6.715806345944622e-05, "loss": 1.0070857048034667, "step": 44500 }, { "epoch": 1.2578439543984063, "grad_norm": 3.383732557296753, "learning_rate": 6.712880697875944e-05, "loss": 0.9850083351135254, "step": 44520 }, { "epoch": 1.2584090299066213, "grad_norm": 3.5430827140808105, "learning_rate": 6.709954385229853e-05, "loss": 0.9473774909973145, "step": 44540 }, { "epoch": 1.258974105414836, "grad_norm": 3.3927385807037354, "learning_rate": 6.707027409141728e-05, "loss": 0.9378454208374023, "step": 44560 }, { "epoch": 1.259539180923051, "grad_norm": 2.987241506576538, "learning_rate": 6.7040997707472e-05, "loss": 0.9049558639526367, "step": 44580 }, { "epoch": 1.2601042564312657, "grad_norm": 3.745975971221924, "learning_rate": 6.70117147118216e-05, "loss": 1.0272096633911132, "step": 44600 }, { "epoch": 1.2606693319394804, "grad_norm": 2.6512327194213867, "learning_rate": 6.698242511582749e-05, "loss": 0.9781678199768067, "step": 44620 }, { "epoch": 1.261234407447695, "grad_norm": 2.9339330196380615, "learning_rate": 6.695312893085373e-05, "loss": 0.9775496482849121, "step": 44640 }, { "epoch": 1.26179948295591, "grad_norm": 3.9532291889190674, "learning_rate": 6.692382616826685e-05, "loss": 0.9561431884765625, "step": 44660 }, { "epoch": 1.2623645584641248, "grad_norm": 4.048150539398193, "learning_rate": 6.689451683943602e-05, "loss": 1.0386130332946777, "step": 44680 }, { "epoch": 1.2629296339723395, "grad_norm": 3.904625654220581, "learning_rate": 6.68652009557329e-05, "loss": 0.9607810020446778, "step": 44700 }, { "epoch": 1.2634947094805544, "grad_norm": 3.020026683807373, "learning_rate": 6.683587852853167e-05, "loss": 0.9728908538818359, "step": 44720 }, { "epoch": 1.2640597849887691, "grad_norm": 4.056398868560791, "learning_rate": 6.680654956920912e-05, "loss": 0.9157353401184082, "step": 44740 }, { "epoch": 1.2646248604969839, "grad_norm": 3.5403189659118652, "learning_rate": 6.677721408914453e-05, "loss": 0.9254315376281739, "step": 44760 }, { "epoch": 1.2651899360051986, "grad_norm": 3.7588789463043213, "learning_rate": 6.674787209971971e-05, "loss": 0.9739804267883301, "step": 44780 }, { "epoch": 1.2657550115134135, "grad_norm": 3.2851734161376953, "learning_rate": 6.671852361231901e-05, "loss": 0.9236293792724609, "step": 44800 }, { "epoch": 1.2663200870216282, "grad_norm": 3.696600914001465, "learning_rate": 6.668916863832932e-05, "loss": 1.013681983947754, "step": 44820 }, { "epoch": 1.2668851625298432, "grad_norm": 3.4231247901916504, "learning_rate": 6.665980718913998e-05, "loss": 0.9893285751342773, "step": 44840 }, { "epoch": 1.267450238038058, "grad_norm": 3.670863151550293, "learning_rate": 6.66304392761429e-05, "loss": 1.0315462112426759, "step": 44860 }, { "epoch": 1.2680153135462726, "grad_norm": 4.452688217163086, "learning_rate": 6.66010649107325e-05, "loss": 0.9846841812133789, "step": 44880 }, { "epoch": 1.2685803890544873, "grad_norm": 5.464673042297363, "learning_rate": 6.657168410430566e-05, "loss": 0.9616164207458496, "step": 44900 }, { "epoch": 1.269145464562702, "grad_norm": 5.463602542877197, "learning_rate": 6.654229686826179e-05, "loss": 0.9777281761169434, "step": 44920 }, { "epoch": 1.269710540070917, "grad_norm": 3.1292316913604736, "learning_rate": 6.65129032140028e-05, "loss": 1.023378849029541, "step": 44940 }, { "epoch": 1.2702756155791317, "grad_norm": 3.7472124099731445, "learning_rate": 6.648350315293308e-05, "loss": 0.9664993286132812, "step": 44960 }, { "epoch": 1.2708406910873467, "grad_norm": 3.4354848861694336, "learning_rate": 6.64540966964595e-05, "loss": 0.9341713905334472, "step": 44980 }, { "epoch": 1.2714057665955614, "grad_norm": 3.00938081741333, "learning_rate": 6.64246838559914e-05, "loss": 0.9218344688415527, "step": 45000 }, { "epoch": 1.271970842103776, "grad_norm": 3.7615725994110107, "learning_rate": 6.639526464294066e-05, "loss": 0.9908437728881836, "step": 45020 }, { "epoch": 1.2725359176119908, "grad_norm": 4.52711820602417, "learning_rate": 6.636583906872152e-05, "loss": 0.9661357879638672, "step": 45040 }, { "epoch": 1.2731009931202057, "grad_norm": 3.163069248199463, "learning_rate": 6.633640714475083e-05, "loss": 0.9139115333557128, "step": 45060 }, { "epoch": 1.2736660686284205, "grad_norm": 2.5313827991485596, "learning_rate": 6.630696888244774e-05, "loss": 0.9293172836303711, "step": 45080 }, { "epoch": 1.2742311441366352, "grad_norm": 3.3572399616241455, "learning_rate": 6.627752429323402e-05, "loss": 0.8906723022460937, "step": 45100 }, { "epoch": 1.2747962196448501, "grad_norm": 2.35066819190979, "learning_rate": 6.62480733885338e-05, "loss": 0.9372478485107422, "step": 45120 }, { "epoch": 1.2753612951530648, "grad_norm": 3.8946456909179688, "learning_rate": 6.621861617977368e-05, "loss": 1.0058881759643554, "step": 45140 }, { "epoch": 1.2759263706612796, "grad_norm": 3.4268124103546143, "learning_rate": 6.618915267838269e-05, "loss": 0.9882014274597168, "step": 45160 }, { "epoch": 1.2764914461694943, "grad_norm": 4.099332809448242, "learning_rate": 6.615968289579234e-05, "loss": 0.946574592590332, "step": 45180 }, { "epoch": 1.2770565216777092, "grad_norm": 3.529794931411743, "learning_rate": 6.613020684343655e-05, "loss": 0.9326141357421875, "step": 45200 }, { "epoch": 1.277621597185924, "grad_norm": 2.453465461730957, "learning_rate": 6.610072453275169e-05, "loss": 0.9339262008666992, "step": 45220 }, { "epoch": 1.2781866726941389, "grad_norm": 2.9213500022888184, "learning_rate": 6.607123597517652e-05, "loss": 0.9108413696289063, "step": 45240 }, { "epoch": 1.2787517482023536, "grad_norm": 3.0220088958740234, "learning_rate": 6.604174118215229e-05, "loss": 1.0270286560058595, "step": 45260 }, { "epoch": 1.2793168237105683, "grad_norm": 4.584432125091553, "learning_rate": 6.601224016512259e-05, "loss": 0.9275701522827149, "step": 45280 }, { "epoch": 1.279881899218783, "grad_norm": 2.400472640991211, "learning_rate": 6.598273293553349e-05, "loss": 1.0121750831604004, "step": 45300 }, { "epoch": 1.280446974726998, "grad_norm": 3.076275110244751, "learning_rate": 6.595321950483344e-05, "loss": 0.9673166275024414, "step": 45320 }, { "epoch": 1.2810120502352127, "grad_norm": 2.7416529655456543, "learning_rate": 6.59236998844733e-05, "loss": 0.9319985389709473, "step": 45340 }, { "epoch": 1.2815771257434274, "grad_norm": 2.6807467937469482, "learning_rate": 6.589417408590632e-05, "loss": 0.9948856353759765, "step": 45360 }, { "epoch": 1.2821422012516424, "grad_norm": 3.856269598007202, "learning_rate": 6.58646421205882e-05, "loss": 0.9309335708618164, "step": 45380 }, { "epoch": 1.282707276759857, "grad_norm": 2.9113211631774902, "learning_rate": 6.583510399997695e-05, "loss": 0.9321352958679199, "step": 45400 }, { "epoch": 1.2832723522680718, "grad_norm": 3.379185438156128, "learning_rate": 6.580555973553301e-05, "loss": 0.9941164970397949, "step": 45420 }, { "epoch": 1.2838374277762865, "grad_norm": 4.229931831359863, "learning_rate": 6.577600933871924e-05, "loss": 0.9654326438903809, "step": 45440 }, { "epoch": 1.2844025032845015, "grad_norm": 4.099865913391113, "learning_rate": 6.574645282100082e-05, "loss": 0.9841420173645019, "step": 45460 }, { "epoch": 1.2849675787927162, "grad_norm": 3.1151986122131348, "learning_rate": 6.571689019384533e-05, "loss": 0.9405189514160156, "step": 45480 }, { "epoch": 1.2855326543009309, "grad_norm": 3.035266637802124, "learning_rate": 6.568732146872275e-05, "loss": 0.9142757415771484, "step": 45500 }, { "epoch": 1.2860977298091458, "grad_norm": 5.008676052093506, "learning_rate": 6.565774665710532e-05, "loss": 0.9450777053833008, "step": 45520 }, { "epoch": 1.2866628053173605, "grad_norm": 2.724142551422119, "learning_rate": 6.56281657704678e-05, "loss": 0.9420586585998535, "step": 45540 }, { "epoch": 1.2872278808255753, "grad_norm": 4.345508575439453, "learning_rate": 6.559857882028716e-05, "loss": 0.9491643905639648, "step": 45560 }, { "epoch": 1.28779295633379, "grad_norm": 2.921722650527954, "learning_rate": 6.556898581804283e-05, "loss": 0.9137375831604004, "step": 45580 }, { "epoch": 1.288358031842005, "grad_norm": 2.351835250854492, "learning_rate": 6.553938677521652e-05, "loss": 0.9852944374084472, "step": 45600 }, { "epoch": 1.2889231073502196, "grad_norm": 3.1360843181610107, "learning_rate": 6.55097817032923e-05, "loss": 0.9970295906066895, "step": 45620 }, { "epoch": 1.2894881828584346, "grad_norm": 3.127843141555786, "learning_rate": 6.548017061375663e-05, "loss": 0.9721446990966797, "step": 45640 }, { "epoch": 1.2900532583666493, "grad_norm": 2.756023406982422, "learning_rate": 6.545055351809821e-05, "loss": 1.000441074371338, "step": 45660 }, { "epoch": 1.290618333874864, "grad_norm": 2.8868017196655273, "learning_rate": 6.542093042780817e-05, "loss": 1.0270976066589355, "step": 45680 }, { "epoch": 1.2911834093830787, "grad_norm": 3.7308273315429688, "learning_rate": 6.539130135437987e-05, "loss": 0.9195213317871094, "step": 45700 }, { "epoch": 1.2917484848912937, "grad_norm": 4.413290023803711, "learning_rate": 6.536166630930906e-05, "loss": 1.0143868446350097, "step": 45720 }, { "epoch": 1.2923135603995084, "grad_norm": 3.5413691997528076, "learning_rate": 6.533202530409379e-05, "loss": 0.8853384971618652, "step": 45740 }, { "epoch": 1.2928786359077231, "grad_norm": 3.6625614166259766, "learning_rate": 6.530237835023444e-05, "loss": 0.8924322128295898, "step": 45760 }, { "epoch": 1.293443711415938, "grad_norm": 4.040107250213623, "learning_rate": 6.527272545923364e-05, "loss": 0.9849625587463379, "step": 45780 }, { "epoch": 1.2940087869241528, "grad_norm": 3.1458992958068848, "learning_rate": 6.524306664259637e-05, "loss": 0.9736135482788086, "step": 45800 }, { "epoch": 1.2945738624323675, "grad_norm": 2.685410976409912, "learning_rate": 6.521340191182991e-05, "loss": 0.9832624435424805, "step": 45820 }, { "epoch": 1.2951389379405822, "grad_norm": 4.4171833992004395, "learning_rate": 6.518373127844382e-05, "loss": 1.0175798416137696, "step": 45840 }, { "epoch": 1.2957040134487972, "grad_norm": 2.6466054916381836, "learning_rate": 6.515405475394994e-05, "loss": 0.9340079307556153, "step": 45860 }, { "epoch": 1.2962690889570119, "grad_norm": 3.21510648727417, "learning_rate": 6.512437234986245e-05, "loss": 0.9255995750427246, "step": 45880 }, { "epoch": 1.2968341644652266, "grad_norm": 4.397275924682617, "learning_rate": 6.50946840776977e-05, "loss": 0.9611221313476562, "step": 45900 }, { "epoch": 1.2973992399734415, "grad_norm": 3.701996088027954, "learning_rate": 6.506498994897445e-05, "loss": 0.9730669021606445, "step": 45920 }, { "epoch": 1.2979643154816563, "grad_norm": 4.038397789001465, "learning_rate": 6.503528997521366e-05, "loss": 1.047017765045166, "step": 45940 }, { "epoch": 1.298529390989871, "grad_norm": 2.5745885372161865, "learning_rate": 6.500558416793856e-05, "loss": 0.9306368827819824, "step": 45960 }, { "epoch": 1.2990944664980857, "grad_norm": 2.8605620861053467, "learning_rate": 6.497587253867463e-05, "loss": 0.9713648796081543, "step": 45980 }, { "epoch": 1.2996595420063006, "grad_norm": 2.8919737339019775, "learning_rate": 6.494615509894967e-05, "loss": 0.9392419815063476, "step": 46000 }, { "epoch": 1.3002246175145153, "grad_norm": 3.7100400924682617, "learning_rate": 6.491643186029366e-05, "loss": 0.9812819480895996, "step": 46020 }, { "epoch": 1.3007896930227303, "grad_norm": 3.960808515548706, "learning_rate": 6.488670283423888e-05, "loss": 0.9473081588745117, "step": 46040 }, { "epoch": 1.301354768530945, "grad_norm": 3.0560760498046875, "learning_rate": 6.485696803231985e-05, "loss": 1.0226207733154298, "step": 46060 }, { "epoch": 1.3019198440391597, "grad_norm": 4.222957134246826, "learning_rate": 6.482722746607329e-05, "loss": 0.9585460662841797, "step": 46080 }, { "epoch": 1.3024849195473744, "grad_norm": 3.6269445419311523, "learning_rate": 6.479748114703821e-05, "loss": 0.9327133178710938, "step": 46100 }, { "epoch": 1.3030499950555894, "grad_norm": 3.295058250427246, "learning_rate": 6.476772908675582e-05, "loss": 0.8956917762756348, "step": 46120 }, { "epoch": 1.303615070563804, "grad_norm": 2.866785764694214, "learning_rate": 6.473797129676959e-05, "loss": 0.8988327980041504, "step": 46140 }, { "epoch": 1.3041801460720188, "grad_norm": 3.2118489742279053, "learning_rate": 6.470820778862516e-05, "loss": 0.9748429298400879, "step": 46160 }, { "epoch": 1.3047452215802338, "grad_norm": 3.3231475353240967, "learning_rate": 6.467843857387042e-05, "loss": 0.9637683868408203, "step": 46180 }, { "epoch": 1.3053102970884485, "grad_norm": 6.111841678619385, "learning_rate": 6.464866366405551e-05, "loss": 0.8517545700073242, "step": 46200 }, { "epoch": 1.3058753725966632, "grad_norm": 4.2406535148620605, "learning_rate": 6.461888307073269e-05, "loss": 1.0099580764770508, "step": 46220 }, { "epoch": 1.306440448104878, "grad_norm": 2.557666778564453, "learning_rate": 6.45890968054565e-05, "loss": 0.9899884223937988, "step": 46240 }, { "epoch": 1.3070055236130929, "grad_norm": 4.6552510261535645, "learning_rate": 6.455930487978368e-05, "loss": 0.8641530990600585, "step": 46260 }, { "epoch": 1.3075705991213076, "grad_norm": 3.0837090015411377, "learning_rate": 6.452950730527311e-05, "loss": 0.8983444213867188, "step": 46280 }, { "epoch": 1.3081356746295223, "grad_norm": 3.1345620155334473, "learning_rate": 6.449970409348593e-05, "loss": 0.9690345764160156, "step": 46300 }, { "epoch": 1.3087007501377372, "grad_norm": 3.8144679069519043, "learning_rate": 6.446989525598539e-05, "loss": 0.9547358512878418, "step": 46320 }, { "epoch": 1.309265825645952, "grad_norm": 4.283031940460205, "learning_rate": 6.4440080804337e-05, "loss": 0.9502501487731934, "step": 46340 }, { "epoch": 1.3098309011541667, "grad_norm": 2.1569015979766846, "learning_rate": 6.441026075010838e-05, "loss": 0.9164402961730957, "step": 46360 }, { "epoch": 1.3103959766623814, "grad_norm": 3.6368515491485596, "learning_rate": 6.438043510486941e-05, "loss": 0.9291369438171386, "step": 46380 }, { "epoch": 1.3109610521705963, "grad_norm": 3.86639142036438, "learning_rate": 6.435060388019203e-05, "loss": 1.0260749816894532, "step": 46400 }, { "epoch": 1.311526127678811, "grad_norm": 2.9512667655944824, "learning_rate": 6.432076708765045e-05, "loss": 0.9551112174987793, "step": 46420 }, { "epoch": 1.312091203187026, "grad_norm": 3.8868157863616943, "learning_rate": 6.429092473882095e-05, "loss": 0.8736427307128907, "step": 46440 }, { "epoch": 1.3126562786952407, "grad_norm": 2.8226661682128906, "learning_rate": 6.426107684528204e-05, "loss": 0.9575112342834473, "step": 46460 }, { "epoch": 1.3132213542034554, "grad_norm": 3.7711923122406006, "learning_rate": 6.423122341861434e-05, "loss": 0.8680739402770996, "step": 46480 }, { "epoch": 1.3137864297116701, "grad_norm": 4.2100348472595215, "learning_rate": 6.420136447040063e-05, "loss": 0.9408327102661133, "step": 46500 }, { "epoch": 1.314351505219885, "grad_norm": 3.1711223125457764, "learning_rate": 6.417150001222579e-05, "loss": 0.9523994445800781, "step": 46520 }, { "epoch": 1.3149165807280998, "grad_norm": 3.8103644847869873, "learning_rate": 6.414163005567694e-05, "loss": 0.8637454032897949, "step": 46540 }, { "epoch": 1.3154816562363145, "grad_norm": 3.407539129257202, "learning_rate": 6.41117546123432e-05, "loss": 0.9921404838562011, "step": 46560 }, { "epoch": 1.3160467317445295, "grad_norm": 4.323055267333984, "learning_rate": 6.408187369381596e-05, "loss": 0.9237247467041015, "step": 46580 }, { "epoch": 1.3166118072527442, "grad_norm": 3.7699167728424072, "learning_rate": 6.40519873116886e-05, "loss": 0.9853879928588867, "step": 46600 }, { "epoch": 1.317176882760959, "grad_norm": 4.9495134353637695, "learning_rate": 6.40220954775567e-05, "loss": 0.9289241790771484, "step": 46620 }, { "epoch": 1.3177419582691736, "grad_norm": 4.772343158721924, "learning_rate": 6.399219820301797e-05, "loss": 0.939759349822998, "step": 46640 }, { "epoch": 1.3183070337773886, "grad_norm": 4.383542060852051, "learning_rate": 6.396229549967217e-05, "loss": 0.9369330406188965, "step": 46660 }, { "epoch": 1.3188721092856033, "grad_norm": 3.5722718238830566, "learning_rate": 6.393238737912118e-05, "loss": 0.9225364685058594, "step": 46680 }, { "epoch": 1.319437184793818, "grad_norm": 3.3785922527313232, "learning_rate": 6.390247385296904e-05, "loss": 0.97080078125, "step": 46700 }, { "epoch": 1.320002260302033, "grad_norm": 2.9884798526763916, "learning_rate": 6.38725549328218e-05, "loss": 0.9609244346618653, "step": 46720 }, { "epoch": 1.3205673358102477, "grad_norm": 3.4604525566101074, "learning_rate": 6.384263063028766e-05, "loss": 1.0390816688537599, "step": 46740 }, { "epoch": 1.3211324113184624, "grad_norm": 3.439955949783325, "learning_rate": 6.381270095697692e-05, "loss": 0.8619365692138672, "step": 46760 }, { "epoch": 1.321697486826677, "grad_norm": 2.6829700469970703, "learning_rate": 6.378276592450189e-05, "loss": 0.9410004615783691, "step": 46780 }, { "epoch": 1.322262562334892, "grad_norm": 3.4770359992980957, "learning_rate": 6.375282554447704e-05, "loss": 0.9492053985595703, "step": 46800 }, { "epoch": 1.3228276378431068, "grad_norm": 3.0679972171783447, "learning_rate": 6.372287982851889e-05, "loss": 0.9518307685852051, "step": 46820 }, { "epoch": 1.3233927133513217, "grad_norm": 3.641691207885742, "learning_rate": 6.369292878824599e-05, "loss": 1.0330291748046876, "step": 46840 }, { "epoch": 1.3239577888595364, "grad_norm": 3.1018450260162354, "learning_rate": 6.366297243527903e-05, "loss": 0.907615852355957, "step": 46860 }, { "epoch": 1.3245228643677511, "grad_norm": 3.0622596740722656, "learning_rate": 6.363301078124069e-05, "loss": 0.9437707901000977, "step": 46880 }, { "epoch": 1.3250879398759658, "grad_norm": 3.268129348754883, "learning_rate": 6.360304383775575e-05, "loss": 0.975858497619629, "step": 46900 }, { "epoch": 1.3256530153841808, "grad_norm": 3.9423775672912598, "learning_rate": 6.357307161645103e-05, "loss": 0.9368727684020997, "step": 46920 }, { "epoch": 1.3262180908923955, "grad_norm": 2.9850265979766846, "learning_rate": 6.354309412895537e-05, "loss": 0.9264744758605957, "step": 46940 }, { "epoch": 1.3267831664006102, "grad_norm": 3.2953197956085205, "learning_rate": 6.351311138689973e-05, "loss": 0.9854205131530762, "step": 46960 }, { "epoch": 1.3273482419088252, "grad_norm": 4.7315192222595215, "learning_rate": 6.3483123401917e-05, "loss": 0.9286211013793946, "step": 46980 }, { "epoch": 1.3279133174170399, "grad_norm": 2.8707876205444336, "learning_rate": 6.345313018564222e-05, "loss": 0.9800966262817383, "step": 47000 }, { "epoch": 1.3284783929252546, "grad_norm": 4.635117053985596, "learning_rate": 6.342313174971236e-05, "loss": 0.9769717216491699, "step": 47020 }, { "epoch": 1.3290434684334693, "grad_norm": 3.4512436389923096, "learning_rate": 6.339312810576648e-05, "loss": 0.9103851318359375, "step": 47040 }, { "epoch": 1.3296085439416843, "grad_norm": 2.8720178604125977, "learning_rate": 6.33631192654456e-05, "loss": 0.9590926170349121, "step": 47060 }, { "epoch": 1.330173619449899, "grad_norm": 3.165698766708374, "learning_rate": 6.333310524039287e-05, "loss": 0.9438593864440918, "step": 47080 }, { "epoch": 1.3307386949581137, "grad_norm": 3.9290850162506104, "learning_rate": 6.330308604225329e-05, "loss": 0.8666901588439941, "step": 47100 }, { "epoch": 1.3313037704663286, "grad_norm": 3.4677040576934814, "learning_rate": 6.327306168267401e-05, "loss": 0.8783993721008301, "step": 47120 }, { "epoch": 1.3318688459745434, "grad_norm": 4.588788032531738, "learning_rate": 6.324303217330412e-05, "loss": 0.9201295852661133, "step": 47140 }, { "epoch": 1.332433921482758, "grad_norm": 3.048757791519165, "learning_rate": 6.32129975257947e-05, "loss": 0.9221014022827149, "step": 47160 }, { "epoch": 1.3329989969909728, "grad_norm": 4.087612152099609, "learning_rate": 6.318295775179884e-05, "loss": 0.8877177238464355, "step": 47180 }, { "epoch": 1.3335640724991877, "grad_norm": 3.5425431728363037, "learning_rate": 6.315291286297162e-05, "loss": 0.8678113937377929, "step": 47200 }, { "epoch": 1.3341291480074025, "grad_norm": 3.1624114513397217, "learning_rate": 6.312286287097008e-05, "loss": 0.8720553398132325, "step": 47220 }, { "epoch": 1.3346942235156174, "grad_norm": 3.6083319187164307, "learning_rate": 6.30928077874533e-05, "loss": 0.8948144912719727, "step": 47240 }, { "epoch": 1.3352592990238321, "grad_norm": 3.144942045211792, "learning_rate": 6.306274762408226e-05, "loss": 0.9549586296081543, "step": 47260 }, { "epoch": 1.3358243745320468, "grad_norm": 4.125078201293945, "learning_rate": 6.303268239251997e-05, "loss": 0.9421229362487793, "step": 47280 }, { "epoch": 1.3363894500402616, "grad_norm": 4.030561447143555, "learning_rate": 6.300261210443137e-05, "loss": 0.891802978515625, "step": 47300 }, { "epoch": 1.3369545255484765, "grad_norm": 3.8186159133911133, "learning_rate": 6.297253677148339e-05, "loss": 0.966123104095459, "step": 47320 }, { "epoch": 1.3375196010566912, "grad_norm": 3.786846876144409, "learning_rate": 6.294245640534488e-05, "loss": 0.9685314178466797, "step": 47340 }, { "epoch": 1.338084676564906, "grad_norm": 2.849379062652588, "learning_rate": 6.29123710176867e-05, "loss": 0.8524322509765625, "step": 47360 }, { "epoch": 1.3386497520731209, "grad_norm": 3.8850035667419434, "learning_rate": 6.288228062018158e-05, "loss": 0.9348845481872559, "step": 47380 }, { "epoch": 1.3392148275813356, "grad_norm": 4.395656585693359, "learning_rate": 6.285218522450427e-05, "loss": 0.9575538635253906, "step": 47400 }, { "epoch": 1.3397799030895503, "grad_norm": 4.856104373931885, "learning_rate": 6.28220848423314e-05, "loss": 0.9063329696655273, "step": 47420 }, { "epoch": 1.340344978597765, "grad_norm": 3.4948313236236572, "learning_rate": 6.27919794853416e-05, "loss": 0.9856765747070313, "step": 47440 }, { "epoch": 1.34091005410598, "grad_norm": 3.355055809020996, "learning_rate": 6.276186916521538e-05, "loss": 1.0350936889648437, "step": 47460 }, { "epoch": 1.3414751296141947, "grad_norm": 4.260690212249756, "learning_rate": 6.273175389363516e-05, "loss": 0.9464741706848144, "step": 47480 }, { "epoch": 1.3420402051224094, "grad_norm": 4.4288010597229, "learning_rate": 6.270163368228532e-05, "loss": 0.9462794303894043, "step": 47500 }, { "epoch": 1.3426052806306243, "grad_norm": 4.204542636871338, "learning_rate": 6.267150854285218e-05, "loss": 0.9347908973693848, "step": 47520 }, { "epoch": 1.343170356138839, "grad_norm": 4.29454231262207, "learning_rate": 6.264137848702387e-05, "loss": 0.8820394515991211, "step": 47540 }, { "epoch": 1.3437354316470538, "grad_norm": 4.884068489074707, "learning_rate": 6.261124352649055e-05, "loss": 0.9591106414794922, "step": 47560 }, { "epoch": 1.3443005071552685, "grad_norm": 3.712785482406616, "learning_rate": 6.258110367294421e-05, "loss": 0.8911801338195801, "step": 47580 }, { "epoch": 1.3448655826634834, "grad_norm": 4.2074384689331055, "learning_rate": 6.255095893807877e-05, "loss": 0.9375940322875976, "step": 47600 }, { "epoch": 1.3454306581716982, "grad_norm": 4.200201034545898, "learning_rate": 6.252080933359e-05, "loss": 0.9085944175720215, "step": 47620 }, { "epoch": 1.345995733679913, "grad_norm": 3.1714470386505127, "learning_rate": 6.249065487117562e-05, "loss": 0.9032210350036621, "step": 47640 }, { "epoch": 1.3465608091881278, "grad_norm": 3.6194612979888916, "learning_rate": 6.246049556253518e-05, "loss": 0.9221845626831054, "step": 47660 }, { "epoch": 1.3471258846963425, "grad_norm": 2.8839526176452637, "learning_rate": 6.243033141937013e-05, "loss": 0.9034195899963379, "step": 47680 }, { "epoch": 1.3476909602045573, "grad_norm": 3.012448787689209, "learning_rate": 6.240016245338385e-05, "loss": 0.9108141899108887, "step": 47700 }, { "epoch": 1.3482560357127722, "grad_norm": 3.5726239681243896, "learning_rate": 6.236998867628145e-05, "loss": 0.9759434700012207, "step": 47720 }, { "epoch": 1.348821111220987, "grad_norm": 3.724601984024048, "learning_rate": 6.23398100997701e-05, "loss": 0.9695759773254394, "step": 47740 }, { "epoch": 1.3493861867292016, "grad_norm": 3.253518581390381, "learning_rate": 6.230962673555866e-05, "loss": 0.9719939231872559, "step": 47760 }, { "epoch": 1.3499512622374166, "grad_norm": 3.1989331245422363, "learning_rate": 6.227943859535797e-05, "loss": 0.914603328704834, "step": 47780 }, { "epoch": 1.3505163377456313, "grad_norm": 2.947956085205078, "learning_rate": 6.224924569088061e-05, "loss": 0.9913640975952148, "step": 47800 }, { "epoch": 1.351081413253846, "grad_norm": 4.582201957702637, "learning_rate": 6.221904803384111e-05, "loss": 0.9422310829162598, "step": 47820 }, { "epoch": 1.3516464887620607, "grad_norm": 3.9757094383239746, "learning_rate": 6.21888456359558e-05, "loss": 0.9103528976440429, "step": 47840 }, { "epoch": 1.3522115642702757, "grad_norm": 4.230015277862549, "learning_rate": 6.215863850894283e-05, "loss": 0.9761717796325684, "step": 47860 }, { "epoch": 1.3527766397784904, "grad_norm": 2.5544729232788086, "learning_rate": 6.212842666452223e-05, "loss": 0.9896608352661133, "step": 47880 }, { "epoch": 1.353341715286705, "grad_norm": 2.5389509201049805, "learning_rate": 6.209821011441583e-05, "loss": 0.8981942176818848, "step": 47900 }, { "epoch": 1.35390679079492, "grad_norm": 3.2107415199279785, "learning_rate": 6.20679888703473e-05, "loss": 0.9490309715270996, "step": 47920 }, { "epoch": 1.3544718663031348, "grad_norm": 7.480419635772705, "learning_rate": 6.203776294404212e-05, "loss": 0.9424440383911132, "step": 47940 }, { "epoch": 1.3550369418113495, "grad_norm": 4.0094990730285645, "learning_rate": 6.200753234722758e-05, "loss": 1.0191701889038085, "step": 47960 }, { "epoch": 1.3556020173195642, "grad_norm": 3.127980947494507, "learning_rate": 6.197729709163281e-05, "loss": 0.969927978515625, "step": 47980 }, { "epoch": 1.3561670928277791, "grad_norm": 3.2553741931915283, "learning_rate": 6.194705718898873e-05, "loss": 0.9351100921630859, "step": 48000 }, { "epoch": 1.3567321683359939, "grad_norm": 2.9466660022735596, "learning_rate": 6.191681265102805e-05, "loss": 0.9495811462402344, "step": 48020 }, { "epoch": 1.3572972438442088, "grad_norm": 2.9721553325653076, "learning_rate": 6.18865634894853e-05, "loss": 0.9157462120056152, "step": 48040 }, { "epoch": 1.3578623193524235, "grad_norm": 3.423997640609741, "learning_rate": 6.185630971609679e-05, "loss": 0.9574726104736329, "step": 48060 }, { "epoch": 1.3584273948606382, "grad_norm": 4.444841384887695, "learning_rate": 6.182605134260064e-05, "loss": 0.8984537124633789, "step": 48080 }, { "epoch": 1.358992470368853, "grad_norm": 3.5039758682250977, "learning_rate": 6.179578838073672e-05, "loss": 0.9128849029541015, "step": 48100 }, { "epoch": 1.359557545877068, "grad_norm": 2.5563483238220215, "learning_rate": 6.176552084224672e-05, "loss": 0.9747494697570801, "step": 48120 }, { "epoch": 1.3601226213852826, "grad_norm": 5.416935920715332, "learning_rate": 6.173524873887408e-05, "loss": 0.9764509201049805, "step": 48140 }, { "epoch": 1.3606876968934973, "grad_norm": 3.8412716388702393, "learning_rate": 6.170497208236402e-05, "loss": 1.0021459579467773, "step": 48160 }, { "epoch": 1.3612527724017123, "grad_norm": 2.8638405799865723, "learning_rate": 6.167469088446351e-05, "loss": 0.9523405075073242, "step": 48180 }, { "epoch": 1.361817847909927, "grad_norm": 3.3774540424346924, "learning_rate": 6.164440515692129e-05, "loss": 0.9173818588256836, "step": 48200 }, { "epoch": 1.3623829234181417, "grad_norm": 2.7285194396972656, "learning_rate": 6.16141149114879e-05, "loss": 0.9065669059753418, "step": 48220 }, { "epoch": 1.3629479989263564, "grad_norm": 3.231947660446167, "learning_rate": 6.158382015991558e-05, "loss": 0.8614832878112793, "step": 48240 }, { "epoch": 1.3635130744345714, "grad_norm": 1.9915636777877808, "learning_rate": 6.155352091395832e-05, "loss": 0.9513410568237305, "step": 48260 }, { "epoch": 1.364078149942786, "grad_norm": 3.363889455795288, "learning_rate": 6.152321718537189e-05, "loss": 0.9175332069396973, "step": 48280 }, { "epoch": 1.3646432254510008, "grad_norm": 3.7010855674743652, "learning_rate": 6.149290898591375e-05, "loss": 0.9107134819030762, "step": 48300 }, { "epoch": 1.3652083009592157, "grad_norm": 2.775301933288574, "learning_rate": 6.146259632734314e-05, "loss": 1.0420126914978027, "step": 48320 }, { "epoch": 1.3657733764674305, "grad_norm": 3.67648983001709, "learning_rate": 6.143227922142101e-05, "loss": 1.005521297454834, "step": 48340 }, { "epoch": 1.3663384519756452, "grad_norm": 3.532844066619873, "learning_rate": 6.140195767991006e-05, "loss": 0.8836480140686035, "step": 48360 }, { "epoch": 1.36690352748386, "grad_norm": 3.5129923820495605, "learning_rate": 6.137163171457462e-05, "loss": 0.9568829536437988, "step": 48380 }, { "epoch": 1.3674686029920748, "grad_norm": 4.149759292602539, "learning_rate": 6.134130133718088e-05, "loss": 0.9788959503173829, "step": 48400 }, { "epoch": 1.3680336785002896, "grad_norm": 3.351973533630371, "learning_rate": 6.131096655949665e-05, "loss": 0.8776240348815918, "step": 48420 }, { "epoch": 1.3685987540085045, "grad_norm": 3.224412202835083, "learning_rate": 6.128062739329144e-05, "loss": 0.8940937042236328, "step": 48440 }, { "epoch": 1.3691638295167192, "grad_norm": 3.2914130687713623, "learning_rate": 6.125028385033649e-05, "loss": 0.9110599517822265, "step": 48460 }, { "epoch": 1.369728905024934, "grad_norm": 3.350944995880127, "learning_rate": 6.121993594240477e-05, "loss": 0.9087234497070312, "step": 48480 }, { "epoch": 1.3702939805331487, "grad_norm": 2.530379056930542, "learning_rate": 6.118958368127085e-05, "loss": 0.9837119102478027, "step": 48500 }, { "epoch": 1.3708590560413636, "grad_norm": 3.3590030670166016, "learning_rate": 6.11592270787111e-05, "loss": 0.8925747871398926, "step": 48520 }, { "epoch": 1.3714241315495783, "grad_norm": 4.148730754852295, "learning_rate": 6.11288661465035e-05, "loss": 0.9922610282897949, "step": 48540 }, { "epoch": 1.371989207057793, "grad_norm": 3.0926783084869385, "learning_rate": 6.109850089642773e-05, "loss": 0.9134330749511719, "step": 48560 }, { "epoch": 1.372554282566008, "grad_norm": 6.4546918869018555, "learning_rate": 6.106813134026515e-05, "loss": 0.9044357299804687, "step": 48580 }, { "epoch": 1.3731193580742227, "grad_norm": 3.5440800189971924, "learning_rate": 6.103775748979881e-05, "loss": 0.9282024383544922, "step": 48600 }, { "epoch": 1.3736844335824374, "grad_norm": 3.4456863403320312, "learning_rate": 6.1007379356813365e-05, "loss": 0.9959418296813964, "step": 48620 }, { "epoch": 1.3742495090906521, "grad_norm": 2.546262502670288, "learning_rate": 6.09769969530952e-05, "loss": 0.9395283699035645, "step": 48640 }, { "epoch": 1.374814584598867, "grad_norm": 3.5028152465820312, "learning_rate": 6.09466102904323e-05, "loss": 1.0568292617797852, "step": 48660 }, { "epoch": 1.3753796601070818, "grad_norm": 4.469364643096924, "learning_rate": 6.0916219380614367e-05, "loss": 0.9351106643676758, "step": 48680 }, { "epoch": 1.3759447356152967, "grad_norm": 3.774930953979492, "learning_rate": 6.0885824235432684e-05, "loss": 0.9239631652832031, "step": 48700 }, { "epoch": 1.3765098111235115, "grad_norm": 2.867377281188965, "learning_rate": 6.085542486668021e-05, "loss": 0.9054156303405761, "step": 48720 }, { "epoch": 1.3770748866317262, "grad_norm": 5.001415729522705, "learning_rate": 6.0825021286151574e-05, "loss": 0.9595309257507324, "step": 48740 }, { "epoch": 1.3776399621399409, "grad_norm": 3.6120731830596924, "learning_rate": 6.079461350564295e-05, "loss": 0.9405426025390625, "step": 48760 }, { "epoch": 1.3782050376481556, "grad_norm": 3.6903774738311768, "learning_rate": 6.076420153695224e-05, "loss": 0.9521150588989258, "step": 48780 }, { "epoch": 1.3787701131563705, "grad_norm": 3.626145601272583, "learning_rate": 6.0733785391878895e-05, "loss": 0.9067839622497559, "step": 48800 }, { "epoch": 1.3793351886645853, "grad_norm": 2.7889304161071777, "learning_rate": 6.070336508222405e-05, "loss": 0.9463833808898926, "step": 48820 }, { "epoch": 1.3799002641728002, "grad_norm": 2.2135982513427734, "learning_rate": 6.0672940619790395e-05, "loss": 0.9353168487548829, "step": 48840 }, { "epoch": 1.380465339681015, "grad_norm": 3.921675205230713, "learning_rate": 6.064251201638229e-05, "loss": 0.9401848793029786, "step": 48860 }, { "epoch": 1.3810304151892296, "grad_norm": 4.004924774169922, "learning_rate": 6.061207928380563e-05, "loss": 0.9969993591308594, "step": 48880 }, { "epoch": 1.3815954906974444, "grad_norm": 3.1154708862304688, "learning_rate": 6.0581642433868014e-05, "loss": 0.9417969703674316, "step": 48900 }, { "epoch": 1.3821605662056593, "grad_norm": 4.1620683670043945, "learning_rate": 6.0551201478378527e-05, "loss": 0.9755868911743164, "step": 48920 }, { "epoch": 1.382725641713874, "grad_norm": 2.381552219390869, "learning_rate": 6.052075642914794e-05, "loss": 0.9428409576416016, "step": 48940 }, { "epoch": 1.3832907172220887, "grad_norm": 4.6032185554504395, "learning_rate": 6.0490307297988534e-05, "loss": 0.9305233955383301, "step": 48960 }, { "epoch": 1.3838557927303037, "grad_norm": 4.610944747924805, "learning_rate": 6.045985409671424e-05, "loss": 0.8931713104248047, "step": 48980 }, { "epoch": 1.3844208682385184, "grad_norm": 3.6716115474700928, "learning_rate": 6.0429396837140514e-05, "loss": 0.9687304496765137, "step": 49000 }, { "epoch": 1.3849859437467331, "grad_norm": 5.548153877258301, "learning_rate": 6.0398935531084445e-05, "loss": 0.8985963821411133, "step": 49020 }, { "epoch": 1.3855510192549478, "grad_norm": 2.9277451038360596, "learning_rate": 6.03684701903646e-05, "loss": 0.9723916053771973, "step": 49040 }, { "epoch": 1.3861160947631628, "grad_norm": 4.2049431800842285, "learning_rate": 6.0338000826801244e-05, "loss": 0.911009407043457, "step": 49060 }, { "epoch": 1.3866811702713775, "grad_norm": 5.165469169616699, "learning_rate": 6.030752745221607e-05, "loss": 0.8945578575134278, "step": 49080 }, { "epoch": 1.3872462457795924, "grad_norm": 3.7371926307678223, "learning_rate": 6.027705007843243e-05, "loss": 0.8536270141601563, "step": 49100 }, { "epoch": 1.3878113212878072, "grad_norm": 3.5261735916137695, "learning_rate": 6.0246568717275156e-05, "loss": 1.0133986473083496, "step": 49120 }, { "epoch": 1.3883763967960219, "grad_norm": 3.2883923053741455, "learning_rate": 6.0216083380570664e-05, "loss": 0.9857243537902832, "step": 49140 }, { "epoch": 1.3889414723042366, "grad_norm": 3.95586895942688, "learning_rate": 6.0185594080146886e-05, "loss": 0.9136130332946777, "step": 49160 }, { "epoch": 1.3895065478124513, "grad_norm": 4.893153190612793, "learning_rate": 6.0155100827833356e-05, "loss": 0.9433610916137696, "step": 49180 }, { "epoch": 1.3900716233206662, "grad_norm": 3.57661509513855, "learning_rate": 6.012460363546103e-05, "loss": 0.9028300285339356, "step": 49200 }, { "epoch": 1.390636698828881, "grad_norm": 3.7826061248779297, "learning_rate": 6.00941025148625e-05, "loss": 0.9416829109191894, "step": 49220 }, { "epoch": 1.391201774337096, "grad_norm": 4.145908355712891, "learning_rate": 6.0063597477871835e-05, "loss": 0.8812217712402344, "step": 49240 }, { "epoch": 1.3917668498453106, "grad_norm": 4.650701522827148, "learning_rate": 6.003308853632463e-05, "loss": 0.9965420722961426, "step": 49260 }, { "epoch": 1.3923319253535253, "grad_norm": 2.40395188331604, "learning_rate": 6.000257570205797e-05, "loss": 0.9468132972717285, "step": 49280 }, { "epoch": 1.39289700086174, "grad_norm": 3.3456692695617676, "learning_rate": 5.9972058986910504e-05, "loss": 0.87637300491333, "step": 49300 }, { "epoch": 1.393462076369955, "grad_norm": 2.5702900886535645, "learning_rate": 5.994153840272233e-05, "loss": 0.8485482215881348, "step": 49320 }, { "epoch": 1.3940271518781697, "grad_norm": 2.3752281665802, "learning_rate": 5.9911013961335095e-05, "loss": 0.861599063873291, "step": 49340 }, { "epoch": 1.3945922273863844, "grad_norm": 2.9159634113311768, "learning_rate": 5.988048567459189e-05, "loss": 0.9057941436767578, "step": 49360 }, { "epoch": 1.3951573028945994, "grad_norm": 2.9381134510040283, "learning_rate": 5.9849953554337354e-05, "loss": 0.9087466239929199, "step": 49380 }, { "epoch": 1.395722378402814, "grad_norm": 3.022857904434204, "learning_rate": 5.9819417612417586e-05, "loss": 0.8923549652099609, "step": 49400 }, { "epoch": 1.3962874539110288, "grad_norm": 3.956317186355591, "learning_rate": 5.978887786068016e-05, "loss": 0.9673938751220703, "step": 49420 }, { "epoch": 1.3968525294192435, "grad_norm": 4.225233554840088, "learning_rate": 5.975833431097415e-05, "loss": 0.9206110954284668, "step": 49440 }, { "epoch": 1.3974176049274585, "grad_norm": 3.8192691802978516, "learning_rate": 5.972778697515007e-05, "loss": 0.9237181663513183, "step": 49460 }, { "epoch": 1.3979826804356732, "grad_norm": 2.672882556915283, "learning_rate": 5.9697235865059954e-05, "loss": 0.9896819114685058, "step": 49480 }, { "epoch": 1.3985477559438881, "grad_norm": 3.0043840408325195, "learning_rate": 5.9666680992557234e-05, "loss": 0.9642085075378418, "step": 49500 }, { "epoch": 1.3991128314521029, "grad_norm": 3.862466812133789, "learning_rate": 5.963612236949687e-05, "loss": 1.0197198867797852, "step": 49520 }, { "epoch": 1.3996779069603176, "grad_norm": 4.098424434661865, "learning_rate": 5.9605560007735215e-05, "loss": 0.9562471389770508, "step": 49540 }, { "epoch": 1.4002429824685323, "grad_norm": 3.9875855445861816, "learning_rate": 5.957499391913015e-05, "loss": 0.9166929244995117, "step": 49560 }, { "epoch": 1.400808057976747, "grad_norm": 3.302942991256714, "learning_rate": 5.954442411554091e-05, "loss": 0.8463929176330567, "step": 49580 }, { "epoch": 1.401373133484962, "grad_norm": 2.3587470054626465, "learning_rate": 5.951385060882825e-05, "loss": 0.9294145584106446, "step": 49600 }, { "epoch": 1.4019382089931767, "grad_norm": 5.34126615524292, "learning_rate": 5.94832734108543e-05, "loss": 0.9644201278686524, "step": 49620 }, { "epoch": 1.4025032845013916, "grad_norm": 4.601768970489502, "learning_rate": 5.945269253348267e-05, "loss": 0.9648308753967285, "step": 49640 }, { "epoch": 1.4030683600096063, "grad_norm": 2.3906543254852295, "learning_rate": 5.942210798857837e-05, "loss": 1.0131804466247558, "step": 49660 }, { "epoch": 1.403633435517821, "grad_norm": 2.966362953186035, "learning_rate": 5.939151978800784e-05, "loss": 0.8782308578491211, "step": 49680 }, { "epoch": 1.4041985110260358, "grad_norm": 3.534261703491211, "learning_rate": 5.936092794363892e-05, "loss": 0.8311078071594238, "step": 49700 }, { "epoch": 1.4047635865342507, "grad_norm": 4.040562152862549, "learning_rate": 5.933033246734093e-05, "loss": 0.936643123626709, "step": 49720 }, { "epoch": 1.4053286620424654, "grad_norm": 2.5554821491241455, "learning_rate": 5.9299733370984515e-05, "loss": 0.8759635925292969, "step": 49740 }, { "epoch": 1.4058937375506801, "grad_norm": 3.3331656455993652, "learning_rate": 5.926913066644178e-05, "loss": 0.9501501083374023, "step": 49760 }, { "epoch": 1.406458813058895, "grad_norm": 3.9393134117126465, "learning_rate": 5.92385243655862e-05, "loss": 0.9846272468566895, "step": 49780 }, { "epoch": 1.4070238885671098, "grad_norm": 2.43408465385437, "learning_rate": 5.9207914480292656e-05, "loss": 0.9289620399475098, "step": 49800 }, { "epoch": 1.4075889640753245, "grad_norm": 3.007260799407959, "learning_rate": 5.917730102243744e-05, "loss": 0.8943984031677246, "step": 49820 }, { "epoch": 1.4081540395835392, "grad_norm": 3.580491542816162, "learning_rate": 5.914668400389819e-05, "loss": 0.9309117317199707, "step": 49840 }, { "epoch": 1.4087191150917542, "grad_norm": 3.6086230278015137, "learning_rate": 5.911606343655394e-05, "loss": 0.9568391799926758, "step": 49860 }, { "epoch": 1.409284190599969, "grad_norm": 3.9287869930267334, "learning_rate": 5.908543933228513e-05, "loss": 0.8971682548522949, "step": 49880 }, { "epoch": 1.4098492661081838, "grad_norm": 3.8790299892425537, "learning_rate": 5.905481170297355e-05, "loss": 0.8647743225097656, "step": 49900 }, { "epoch": 1.4104143416163986, "grad_norm": 2.6955976486206055, "learning_rate": 5.9024180560502343e-05, "loss": 0.935234260559082, "step": 49920 }, { "epoch": 1.4109794171246133, "grad_norm": 3.4243710041046143, "learning_rate": 5.8993545916756024e-05, "loss": 0.9409634590148925, "step": 49940 }, { "epoch": 1.411544492632828, "grad_norm": 3.5256590843200684, "learning_rate": 5.896290778362049e-05, "loss": 0.8464009284973144, "step": 49960 }, { "epoch": 1.4121095681410427, "grad_norm": 3.0701892375946045, "learning_rate": 5.893226617298295e-05, "loss": 0.9439130783081054, "step": 49980 }, { "epoch": 1.4126746436492577, "grad_norm": 3.435940980911255, "learning_rate": 5.890162109673202e-05, "loss": 1.0077414512634277, "step": 50000 }, { "epoch": 1.4132397191574724, "grad_norm": 4.247842788696289, "learning_rate": 5.88709725667576e-05, "loss": 0.9687397003173828, "step": 50020 }, { "epoch": 1.4138047946656873, "grad_norm": 3.47139048576355, "learning_rate": 5.884032059495095e-05, "loss": 0.8907496452331543, "step": 50040 }, { "epoch": 1.414369870173902, "grad_norm": 4.017271041870117, "learning_rate": 5.8809665193204696e-05, "loss": 1.0127316474914552, "step": 50060 }, { "epoch": 1.4149349456821168, "grad_norm": 4.502533435821533, "learning_rate": 5.877900637341276e-05, "loss": 0.9169434547424317, "step": 50080 }, { "epoch": 1.4155000211903315, "grad_norm": 3.3935368061065674, "learning_rate": 5.87483441474704e-05, "loss": 0.9853878974914551, "step": 50100 }, { "epoch": 1.4160650966985464, "grad_norm": 3.5219943523406982, "learning_rate": 5.871767852727419e-05, "loss": 0.9573801040649415, "step": 50120 }, { "epoch": 1.4166301722067611, "grad_norm": 3.5544564723968506, "learning_rate": 5.868700952472205e-05, "loss": 0.9143581390380859, "step": 50140 }, { "epoch": 1.4171952477149758, "grad_norm": 3.5267927646636963, "learning_rate": 5.865633715171316e-05, "loss": 0.8835258483886719, "step": 50160 }, { "epoch": 1.4177603232231908, "grad_norm": 3.7383735179901123, "learning_rate": 5.862566142014806e-05, "loss": 0.9124834060668945, "step": 50180 }, { "epoch": 1.4183253987314055, "grad_norm": 5.322814464569092, "learning_rate": 5.859498234192853e-05, "loss": 0.893757438659668, "step": 50200 }, { "epoch": 1.4188904742396202, "grad_norm": 3.5906012058258057, "learning_rate": 5.856429992895776e-05, "loss": 0.8443498611450195, "step": 50220 }, { "epoch": 1.419455549747835, "grad_norm": 3.9049301147460938, "learning_rate": 5.853361419314008e-05, "loss": 0.9251952171325684, "step": 50240 }, { "epoch": 1.4200206252560499, "grad_norm": 4.837190628051758, "learning_rate": 5.850292514638127e-05, "loss": 0.9633933067321777, "step": 50260 }, { "epoch": 1.4205857007642646, "grad_norm": 3.570340394973755, "learning_rate": 5.847223280058827e-05, "loss": 0.8390614509582519, "step": 50280 }, { "epoch": 1.4211507762724795, "grad_norm": 2.7867050170898438, "learning_rate": 5.844153716766936e-05, "loss": 0.9570610046386718, "step": 50300 }, { "epoch": 1.4217158517806943, "grad_norm": 2.391572952270508, "learning_rate": 5.8410838259534063e-05, "loss": 0.9601571083068847, "step": 50320 }, { "epoch": 1.422280927288909, "grad_norm": 3.2726597785949707, "learning_rate": 5.838013608809322e-05, "loss": 0.9979551315307618, "step": 50340 }, { "epoch": 1.4228460027971237, "grad_norm": 4.692625522613525, "learning_rate": 5.834943066525887e-05, "loss": 0.9721231460571289, "step": 50360 }, { "epoch": 1.4234110783053384, "grad_norm": 5.544497489929199, "learning_rate": 5.831872200294442e-05, "loss": 0.8859992027282715, "step": 50380 }, { "epoch": 1.4239761538135534, "grad_norm": 3.6426706314086914, "learning_rate": 5.828801011306439e-05, "loss": 0.8745692253112793, "step": 50400 }, { "epoch": 1.424541229321768, "grad_norm": 3.362511157989502, "learning_rate": 5.82572950075347e-05, "loss": 0.94462890625, "step": 50420 }, { "epoch": 1.425106304829983, "grad_norm": 4.674734592437744, "learning_rate": 5.8226576698272396e-05, "loss": 0.9132084846496582, "step": 50440 }, { "epoch": 1.4256713803381977, "grad_norm": 3.2661001682281494, "learning_rate": 5.8195855197195836e-05, "loss": 1.01358060836792, "step": 50460 }, { "epoch": 1.4262364558464125, "grad_norm": 5.1162590980529785, "learning_rate": 5.816513051622459e-05, "loss": 0.9722542762756348, "step": 50480 }, { "epoch": 1.4268015313546272, "grad_norm": 3.813755750656128, "learning_rate": 5.813440266727949e-05, "loss": 0.9542178153991699, "step": 50500 }, { "epoch": 1.4273666068628421, "grad_norm": 3.538869619369507, "learning_rate": 5.810367166228256e-05, "loss": 0.9024548530578613, "step": 50520 }, { "epoch": 1.4279316823710568, "grad_norm": 3.7557613849639893, "learning_rate": 5.8072937513157054e-05, "loss": 0.8821892738342285, "step": 50540 }, { "epoch": 1.4284967578792716, "grad_norm": 3.6851439476013184, "learning_rate": 5.804220023182748e-05, "loss": 0.8942438125610351, "step": 50560 }, { "epoch": 1.4290618333874865, "grad_norm": 3.6196982860565186, "learning_rate": 5.801145983021955e-05, "loss": 0.9251511573791504, "step": 50580 }, { "epoch": 1.4296269088957012, "grad_norm": 2.6433331966400146, "learning_rate": 5.7980716320260144e-05, "loss": 0.9254919052124023, "step": 50600 }, { "epoch": 1.430191984403916, "grad_norm": 2.662045955657959, "learning_rate": 5.79499697138774e-05, "loss": 0.8576841354370117, "step": 50620 }, { "epoch": 1.4307570599121306, "grad_norm": 2.403322696685791, "learning_rate": 5.791922002300062e-05, "loss": 0.8719380378723145, "step": 50640 }, { "epoch": 1.4313221354203456, "grad_norm": 4.191130638122559, "learning_rate": 5.788846725956034e-05, "loss": 1.037200355529785, "step": 50660 }, { "epoch": 1.4318872109285603, "grad_norm": 3.592949390411377, "learning_rate": 5.785771143548825e-05, "loss": 0.9034720420837402, "step": 50680 }, { "epoch": 1.4324522864367752, "grad_norm": 5.638157844543457, "learning_rate": 5.7826952562717254e-05, "loss": 0.8941904067993164, "step": 50700 }, { "epoch": 1.43301736194499, "grad_norm": 3.562628984451294, "learning_rate": 5.7796190653181434e-05, "loss": 0.8838746070861816, "step": 50720 }, { "epoch": 1.4335824374532047, "grad_norm": 3.9340527057647705, "learning_rate": 5.7765425718816034e-05, "loss": 0.9516456604003907, "step": 50740 }, { "epoch": 1.4341475129614194, "grad_norm": 2.5328261852264404, "learning_rate": 5.773465777155751e-05, "loss": 0.9128545761108399, "step": 50760 }, { "epoch": 1.4347125884696341, "grad_norm": 3.3108274936676025, "learning_rate": 5.7703886823343424e-05, "loss": 0.8948954582214356, "step": 50780 }, { "epoch": 1.435277663977849, "grad_norm": 2.3527843952178955, "learning_rate": 5.7673112886112555e-05, "loss": 0.8477217674255371, "step": 50800 }, { "epoch": 1.4358427394860638, "grad_norm": 4.741580963134766, "learning_rate": 5.764233597180484e-05, "loss": 1.0296357154846192, "step": 50820 }, { "epoch": 1.4364078149942787, "grad_norm": 2.684325695037842, "learning_rate": 5.761155609236134e-05, "loss": 0.8604175567626953, "step": 50840 }, { "epoch": 1.4369728905024934, "grad_norm": 3.2631754875183105, "learning_rate": 5.758077325972427e-05, "loss": 0.8845515251159668, "step": 50860 }, { "epoch": 1.4375379660107082, "grad_norm": 3.5362257957458496, "learning_rate": 5.7549987485837045e-05, "loss": 0.9571455001831055, "step": 50880 }, { "epoch": 1.4381030415189229, "grad_norm": 2.626270055770874, "learning_rate": 5.7519198782644157e-05, "loss": 0.8803694725036622, "step": 50900 }, { "epoch": 1.4386681170271378, "grad_norm": 4.019353866577148, "learning_rate": 5.748840716209125e-05, "loss": 0.9071608543395996, "step": 50920 }, { "epoch": 1.4392331925353525, "grad_norm": 2.6830897331237793, "learning_rate": 5.745761263612512e-05, "loss": 0.8671665191650391, "step": 50940 }, { "epoch": 1.4397982680435673, "grad_norm": 4.193444728851318, "learning_rate": 5.7426815216693686e-05, "loss": 0.902991771697998, "step": 50960 }, { "epoch": 1.4403633435517822, "grad_norm": 6.204407215118408, "learning_rate": 5.7396014915745956e-05, "loss": 0.9016170501708984, "step": 50980 }, { "epoch": 1.440928419059997, "grad_norm": 3.291872024536133, "learning_rate": 5.7365211745232104e-05, "loss": 0.9775186538696289, "step": 51000 }, { "epoch": 1.4414934945682116, "grad_norm": 3.5179948806762695, "learning_rate": 5.733440571710338e-05, "loss": 0.9511962890625, "step": 51020 }, { "epoch": 1.4420585700764263, "grad_norm": 2.372680425643921, "learning_rate": 5.730359684331217e-05, "loss": 0.9116209983825684, "step": 51040 }, { "epoch": 1.4426236455846413, "grad_norm": 4.828286647796631, "learning_rate": 5.7272785135811945e-05, "loss": 0.9397391319274903, "step": 51060 }, { "epoch": 1.443188721092856, "grad_norm": 2.3674817085266113, "learning_rate": 5.7241970606557295e-05, "loss": 0.8553954124450683, "step": 51080 }, { "epoch": 1.443753796601071, "grad_norm": 4.353885173797607, "learning_rate": 5.721115326750387e-05, "loss": 0.8584841728210449, "step": 51100 }, { "epoch": 1.4443188721092857, "grad_norm": 4.519773006439209, "learning_rate": 5.718033313060846e-05, "loss": 0.9591422080993652, "step": 51120 }, { "epoch": 1.4448839476175004, "grad_norm": 2.8678572177886963, "learning_rate": 5.714951020782887e-05, "loss": 0.8386494636535644, "step": 51140 }, { "epoch": 1.445449023125715, "grad_norm": 3.2549798488616943, "learning_rate": 5.711868451112408e-05, "loss": 1.0259490966796876, "step": 51160 }, { "epoch": 1.4460140986339298, "grad_norm": 3.4573049545288086, "learning_rate": 5.708785605245406e-05, "loss": 0.8684022903442383, "step": 51180 }, { "epoch": 1.4465791741421448, "grad_norm": 3.54622220993042, "learning_rate": 5.705702484377989e-05, "loss": 0.8767189979553223, "step": 51200 }, { "epoch": 1.4471442496503595, "grad_norm": 3.5581343173980713, "learning_rate": 5.7026190897063726e-05, "loss": 0.9370171546936035, "step": 51220 }, { "epoch": 1.4477093251585744, "grad_norm": 4.423939228057861, "learning_rate": 5.699535422426877e-05, "loss": 0.8974188804626465, "step": 51240 }, { "epoch": 1.4482744006667891, "grad_norm": 3.117008924484253, "learning_rate": 5.696451483735929e-05, "loss": 0.9218616485595703, "step": 51260 }, { "epoch": 1.4488394761750039, "grad_norm": 2.3726983070373535, "learning_rate": 5.6933672748300595e-05, "loss": 0.9637120246887207, "step": 51280 }, { "epoch": 1.4494045516832186, "grad_norm": 3.9488635063171387, "learning_rate": 5.6902827969059035e-05, "loss": 0.9103434562683106, "step": 51300 }, { "epoch": 1.4499696271914335, "grad_norm": 3.583197832107544, "learning_rate": 5.6871980511602065e-05, "loss": 0.9975375175476074, "step": 51320 }, { "epoch": 1.4505347026996482, "grad_norm": 2.4675300121307373, "learning_rate": 5.6841130387898077e-05, "loss": 0.847695255279541, "step": 51340 }, { "epoch": 1.451099778207863, "grad_norm": 3.3450868129730225, "learning_rate": 5.681027760991658e-05, "loss": 0.9476242065429688, "step": 51360 }, { "epoch": 1.451664853716078, "grad_norm": 2.457536458969116, "learning_rate": 5.6779422189628106e-05, "loss": 0.8452150344848632, "step": 51380 }, { "epoch": 1.4522299292242926, "grad_norm": 2.617220878601074, "learning_rate": 5.674856413900415e-05, "loss": 0.9257718086242676, "step": 51400 }, { "epoch": 1.4527950047325073, "grad_norm": 2.9074742794036865, "learning_rate": 5.6717703470017324e-05, "loss": 0.8834877967834472, "step": 51420 }, { "epoch": 1.453360080240722, "grad_norm": 3.5306262969970703, "learning_rate": 5.668684019464114e-05, "loss": 0.981564712524414, "step": 51440 }, { "epoch": 1.453925155748937, "grad_norm": 3.384274482727051, "learning_rate": 5.665597432485024e-05, "loss": 0.8013628005981446, "step": 51460 }, { "epoch": 1.4544902312571517, "grad_norm": 3.706359386444092, "learning_rate": 5.6625105872620154e-05, "loss": 0.8752898216247559, "step": 51480 }, { "epoch": 1.4550553067653667, "grad_norm": 3.892650842666626, "learning_rate": 5.6594234849927544e-05, "loss": 0.900203800201416, "step": 51500 }, { "epoch": 1.4556203822735814, "grad_norm": 3.783039093017578, "learning_rate": 5.656336126874993e-05, "loss": 0.9377089500427246, "step": 51520 }, { "epoch": 1.456185457781796, "grad_norm": 2.2903711795806885, "learning_rate": 5.653248514106596e-05, "loss": 0.9761795997619629, "step": 51540 }, { "epoch": 1.4567505332900108, "grad_norm": 3.8119609355926514, "learning_rate": 5.650160647885517e-05, "loss": 0.838044261932373, "step": 51560 }, { "epoch": 1.4573156087982255, "grad_norm": 4.643988609313965, "learning_rate": 5.6470725294098136e-05, "loss": 0.9583789825439453, "step": 51580 }, { "epoch": 1.4578806843064405, "grad_norm": 3.4316720962524414, "learning_rate": 5.643984159877635e-05, "loss": 0.9101396560668945, "step": 51600 }, { "epoch": 1.4584457598146552, "grad_norm": 2.24009108543396, "learning_rate": 5.640895540487239e-05, "loss": 0.8823822975158692, "step": 51620 }, { "epoch": 1.4590108353228701, "grad_norm": 3.333057403564453, "learning_rate": 5.637806672436966e-05, "loss": 0.8780022621154785, "step": 51640 }, { "epoch": 1.4595759108310848, "grad_norm": 4.767101764678955, "learning_rate": 5.634717556925265e-05, "loss": 1.0057762145996094, "step": 51660 }, { "epoch": 1.4601409863392996, "grad_norm": 2.3432273864746094, "learning_rate": 5.631628195150672e-05, "loss": 0.9131845474243164, "step": 51680 }, { "epoch": 1.4607060618475143, "grad_norm": 2.6665122509002686, "learning_rate": 5.628538588311828e-05, "loss": 1.0062984466552733, "step": 51700 }, { "epoch": 1.4612711373557292, "grad_norm": 3.747694730758667, "learning_rate": 5.6254487376074605e-05, "loss": 0.9468475341796875, "step": 51720 }, { "epoch": 1.461836212863944, "grad_norm": 4.1866841316223145, "learning_rate": 5.622358644236396e-05, "loss": 0.9615422248840332, "step": 51740 }, { "epoch": 1.4624012883721587, "grad_norm": 5.072275161743164, "learning_rate": 5.619268309397553e-05, "loss": 0.839198112487793, "step": 51760 }, { "epoch": 1.4629663638803736, "grad_norm": 2.9653241634368896, "learning_rate": 5.616177734289947e-05, "loss": 0.8605691909790039, "step": 51780 }, { "epoch": 1.4635314393885883, "grad_norm": 2.9500961303710938, "learning_rate": 5.613086920112681e-05, "loss": 0.8862132072448731, "step": 51800 }, { "epoch": 1.464096514896803, "grad_norm": 5.275461673736572, "learning_rate": 5.609995868064958e-05, "loss": 0.8937873840332031, "step": 51820 }, { "epoch": 1.4646615904050178, "grad_norm": 3.6707208156585693, "learning_rate": 5.606904579346067e-05, "loss": 0.9298608779907227, "step": 51840 }, { "epoch": 1.4652266659132327, "grad_norm": 3.00494122505188, "learning_rate": 5.6038130551553916e-05, "loss": 0.9118955612182618, "step": 51860 }, { "epoch": 1.4657917414214474, "grad_norm": 2.459331750869751, "learning_rate": 5.6007212966924085e-05, "loss": 0.9344949722290039, "step": 51880 }, { "epoch": 1.4663568169296624, "grad_norm": 4.050687313079834, "learning_rate": 5.597629305156682e-05, "loss": 0.8890948295593262, "step": 51900 }, { "epoch": 1.466921892437877, "grad_norm": 4.373785018920898, "learning_rate": 5.594537081747867e-05, "loss": 0.9376641273498535, "step": 51920 }, { "epoch": 1.4674869679460918, "grad_norm": 4.219056606292725, "learning_rate": 5.5914446276657116e-05, "loss": 0.9381699562072754, "step": 51940 }, { "epoch": 1.4680520434543065, "grad_norm": 3.4411370754241943, "learning_rate": 5.5883519441100505e-05, "loss": 0.9053119659423828, "step": 51960 }, { "epoch": 1.4686171189625212, "grad_norm": 3.676460027694702, "learning_rate": 5.5852590322808085e-05, "loss": 0.8822751045227051, "step": 51980 }, { "epoch": 1.4691821944707362, "grad_norm": 4.848373889923096, "learning_rate": 5.5821658933779976e-05, "loss": 0.9062868118286133, "step": 52000 }, { "epoch": 1.4697472699789509, "grad_norm": 5.378192901611328, "learning_rate": 5.57907252860172e-05, "loss": 0.9680696487426758, "step": 52020 }, { "epoch": 1.4703123454871658, "grad_norm": 4.857975959777832, "learning_rate": 5.575978939152166e-05, "loss": 0.9171136856079102, "step": 52040 }, { "epoch": 1.4708774209953805, "grad_norm": 3.8938181400299072, "learning_rate": 5.572885126229608e-05, "loss": 1.0055106163024903, "step": 52060 }, { "epoch": 1.4714424965035953, "grad_norm": 4.007990837097168, "learning_rate": 5.569791091034413e-05, "loss": 0.9666448593139648, "step": 52080 }, { "epoch": 1.47200757201181, "grad_norm": 3.6436989307403564, "learning_rate": 5.566696834767026e-05, "loss": 0.9497662544250488, "step": 52100 }, { "epoch": 1.472572647520025, "grad_norm": 4.130839824676514, "learning_rate": 5.563602358627985e-05, "loss": 0.899873924255371, "step": 52120 }, { "epoch": 1.4731377230282396, "grad_norm": 2.657175302505493, "learning_rate": 5.560507663817908e-05, "loss": 0.7980451583862305, "step": 52140 }, { "epoch": 1.4737027985364544, "grad_norm": 3.9757022857666016, "learning_rate": 5.557412751537501e-05, "loss": 0.9167370796203613, "step": 52160 }, { "epoch": 1.4742678740446693, "grad_norm": 4.13066291809082, "learning_rate": 5.554317622987551e-05, "loss": 0.9594315528869629, "step": 52180 }, { "epoch": 1.474832949552884, "grad_norm": 2.7673115730285645, "learning_rate": 5.551222279368935e-05, "loss": 1.0243163108825684, "step": 52200 }, { "epoch": 1.4753980250610987, "grad_norm": 3.9867119789123535, "learning_rate": 5.548126721882607e-05, "loss": 0.9233041763305664, "step": 52220 }, { "epoch": 1.4759631005693135, "grad_norm": 3.1259233951568604, "learning_rate": 5.5450309517296083e-05, "loss": 0.8394780158996582, "step": 52240 }, { "epoch": 1.4765281760775284, "grad_norm": 3.025838613510132, "learning_rate": 5.541934970111059e-05, "loss": 0.8894022941589356, "step": 52260 }, { "epoch": 1.4770932515857431, "grad_norm": 3.232779026031494, "learning_rate": 5.538838778228165e-05, "loss": 0.919187355041504, "step": 52280 }, { "epoch": 1.477658327093958, "grad_norm": 4.593253135681152, "learning_rate": 5.53574237728221e-05, "loss": 0.9052934646606445, "step": 52300 }, { "epoch": 1.4782234026021728, "grad_norm": 3.1223936080932617, "learning_rate": 5.5326457684745645e-05, "loss": 0.8224306106567383, "step": 52320 }, { "epoch": 1.4787884781103875, "grad_norm": 3.2055182456970215, "learning_rate": 5.5295489530066716e-05, "loss": 0.9315972328186035, "step": 52340 }, { "epoch": 1.4793535536186022, "grad_norm": 4.755056858062744, "learning_rate": 5.526451932080062e-05, "loss": 0.9093555450439453, "step": 52360 }, { "epoch": 1.4799186291268172, "grad_norm": 3.293055534362793, "learning_rate": 5.523354706896342e-05, "loss": 0.9049525260925293, "step": 52380 }, { "epoch": 1.4804837046350319, "grad_norm": 4.83376407623291, "learning_rate": 5.5202572786571995e-05, "loss": 0.9552889823913574, "step": 52400 }, { "epoch": 1.4810487801432466, "grad_norm": 3.1918232440948486, "learning_rate": 5.517159648564398e-05, "loss": 0.8108542442321778, "step": 52420 }, { "epoch": 1.4816138556514615, "grad_norm": 2.7512056827545166, "learning_rate": 5.514061817819783e-05, "loss": 0.8933802604675293, "step": 52440 }, { "epoch": 1.4821789311596762, "grad_norm": 2.982028007507324, "learning_rate": 5.510963787625275e-05, "loss": 0.838526439666748, "step": 52460 }, { "epoch": 1.482744006667891, "grad_norm": 3.4176318645477295, "learning_rate": 5.507865559182873e-05, "loss": 0.8980241775512695, "step": 52480 }, { "epoch": 1.4833090821761057, "grad_norm": 3.3439085483551025, "learning_rate": 5.504767133694654e-05, "loss": 0.8073888778686523, "step": 52500 }, { "epoch": 1.4838741576843206, "grad_norm": 4.467909812927246, "learning_rate": 5.501668512362769e-05, "loss": 0.8772629737854004, "step": 52520 }, { "epoch": 1.4844392331925353, "grad_norm": 3.3838016986846924, "learning_rate": 5.498569696389447e-05, "loss": 0.8964526176452636, "step": 52540 }, { "epoch": 1.48500430870075, "grad_norm": 5.05269718170166, "learning_rate": 5.495470686976992e-05, "loss": 0.8958784103393554, "step": 52560 }, { "epoch": 1.485569384208965, "grad_norm": 3.170295000076294, "learning_rate": 5.492371485327783e-05, "loss": 0.9081698417663574, "step": 52580 }, { "epoch": 1.4861344597171797, "grad_norm": 3.2583396434783936, "learning_rate": 5.489272092644273e-05, "loss": 0.9453869819641113, "step": 52600 }, { "epoch": 1.4866995352253944, "grad_norm": 3.2933738231658936, "learning_rate": 5.486172510128989e-05, "loss": 0.8762960433959961, "step": 52620 }, { "epoch": 1.4872646107336092, "grad_norm": 4.213091850280762, "learning_rate": 5.483072738984536e-05, "loss": 0.9039674758911133, "step": 52640 }, { "epoch": 1.487829686241824, "grad_norm": 3.1786813735961914, "learning_rate": 5.4799727804135835e-05, "loss": 0.9383618354797363, "step": 52660 }, { "epoch": 1.4883947617500388, "grad_norm": 5.360016822814941, "learning_rate": 5.476872635618881e-05, "loss": 0.8859334945678711, "step": 52680 }, { "epoch": 1.4889598372582538, "grad_norm": 3.146395683288574, "learning_rate": 5.473772305803249e-05, "loss": 0.892091941833496, "step": 52700 }, { "epoch": 1.4895249127664685, "grad_norm": 3.1166930198669434, "learning_rate": 5.4706717921695746e-05, "loss": 0.9200531005859375, "step": 52720 }, { "epoch": 1.4900899882746832, "grad_norm": 3.9426801204681396, "learning_rate": 5.467571095920827e-05, "loss": 0.8939995765686035, "step": 52740 }, { "epoch": 1.490655063782898, "grad_norm": 2.919384002685547, "learning_rate": 5.464470218260033e-05, "loss": 0.9638799667358399, "step": 52760 }, { "epoch": 1.4912201392911129, "grad_norm": 2.5553340911865234, "learning_rate": 5.461369160390302e-05, "loss": 0.9381484985351562, "step": 52780 }, { "epoch": 1.4917852147993276, "grad_norm": 2.741821765899658, "learning_rate": 5.458267923514801e-05, "loss": 0.9454755783081055, "step": 52800 }, { "epoch": 1.4923502903075423, "grad_norm": 4.125094890594482, "learning_rate": 5.455166508836781e-05, "loss": 0.9226302146911621, "step": 52820 }, { "epoch": 1.4929153658157572, "grad_norm": 3.970338821411133, "learning_rate": 5.4520649175595475e-05, "loss": 0.9649397850036621, "step": 52840 }, { "epoch": 1.493480441323972, "grad_norm": 3.0090548992156982, "learning_rate": 5.448963150886485e-05, "loss": 0.9239380836486817, "step": 52860 }, { "epoch": 1.4940455168321867, "grad_norm": 2.890157699584961, "learning_rate": 5.44586121002104e-05, "loss": 0.883747673034668, "step": 52880 }, { "epoch": 1.4946105923404014, "grad_norm": 3.023723840713501, "learning_rate": 5.4427590961667316e-05, "loss": 0.9713255882263183, "step": 52900 }, { "epoch": 1.4951756678486163, "grad_norm": 3.098353147506714, "learning_rate": 5.439656810527141e-05, "loss": 0.8491273880004883, "step": 52920 }, { "epoch": 1.495740743356831, "grad_norm": 3.0344009399414062, "learning_rate": 5.4365543543059186e-05, "loss": 0.8343369483947753, "step": 52940 }, { "epoch": 1.4963058188650458, "grad_norm": 3.215139389038086, "learning_rate": 5.43345172870678e-05, "loss": 0.9006246566772461, "step": 52960 }, { "epoch": 1.4968708943732607, "grad_norm": 4.164676189422607, "learning_rate": 5.430348934933509e-05, "loss": 0.9859677314758301, "step": 52980 }, { "epoch": 1.4974359698814754, "grad_norm": 3.452099323272705, "learning_rate": 5.4272459741899496e-05, "loss": 0.8605245590209961, "step": 53000 }, { "epoch": 1.4980010453896901, "grad_norm": 2.838686466217041, "learning_rate": 5.424142847680018e-05, "loss": 0.9063582420349121, "step": 53020 }, { "epoch": 1.4985661208979049, "grad_norm": 3.2614829540252686, "learning_rate": 5.4210395566076874e-05, "loss": 0.87008056640625, "step": 53040 }, { "epoch": 1.4991311964061198, "grad_norm": 2.4808175563812256, "learning_rate": 5.417936102177001e-05, "loss": 0.8809882164001465, "step": 53060 }, { "epoch": 1.4996962719143345, "grad_norm": 3.0146331787109375, "learning_rate": 5.414832485592058e-05, "loss": 0.9069104194641113, "step": 53080 }, { "epoch": 1.5002613474225495, "grad_norm": 3.51292085647583, "learning_rate": 5.41172870805703e-05, "loss": 0.885813045501709, "step": 53100 }, { "epoch": 1.5008264229307642, "grad_norm": 3.9153103828430176, "learning_rate": 5.4086247707761404e-05, "loss": 0.8673760414123535, "step": 53120 }, { "epoch": 1.501391498438979, "grad_norm": 4.953059196472168, "learning_rate": 5.4055206749536846e-05, "loss": 0.917994499206543, "step": 53140 }, { "epoch": 1.5019565739471936, "grad_norm": 6.336383819580078, "learning_rate": 5.402416421794012e-05, "loss": 0.8512223243713379, "step": 53160 }, { "epoch": 1.5025216494554083, "grad_norm": 3.2325215339660645, "learning_rate": 5.399312012501536e-05, "loss": 0.9322655677795411, "step": 53180 }, { "epoch": 1.5030867249636233, "grad_norm": 2.9683454036712646, "learning_rate": 5.396207448280735e-05, "loss": 0.9373786926269532, "step": 53200 }, { "epoch": 1.503651800471838, "grad_norm": 3.1832773685455322, "learning_rate": 5.393102730336137e-05, "loss": 0.9545392036437989, "step": 53220 }, { "epoch": 1.504216875980053, "grad_norm": 4.680415630340576, "learning_rate": 5.389997859872341e-05, "loss": 0.9170063018798829, "step": 53240 }, { "epoch": 1.5047819514882677, "grad_norm": 3.714940309524536, "learning_rate": 5.3868928380939954e-05, "loss": 0.8806534767150879, "step": 53260 }, { "epoch": 1.5053470269964824, "grad_norm": 4.259309768676758, "learning_rate": 5.383787666205815e-05, "loss": 0.9610699653625489, "step": 53280 }, { "epoch": 1.505912102504697, "grad_norm": 3.3979737758636475, "learning_rate": 5.38068234541257e-05, "loss": 0.9455610275268554, "step": 53300 }, { "epoch": 1.5064771780129118, "grad_norm": 3.0146875381469727, "learning_rate": 5.377576876919085e-05, "loss": 0.8368276596069336, "step": 53320 }, { "epoch": 1.5070422535211268, "grad_norm": 3.082120895385742, "learning_rate": 5.3744712619302475e-05, "loss": 0.8357612609863281, "step": 53340 }, { "epoch": 1.5076073290293417, "grad_norm": 3.1729934215545654, "learning_rate": 5.371365501650999e-05, "loss": 0.9126691818237305, "step": 53360 }, { "epoch": 1.5081724045375564, "grad_norm": 3.850175142288208, "learning_rate": 5.368259597286336e-05, "loss": 0.9813826560974122, "step": 53380 }, { "epoch": 1.5087374800457711, "grad_norm": 3.0811703205108643, "learning_rate": 5.3651535500413156e-05, "loss": 0.7999313831329345, "step": 53400 }, { "epoch": 1.5093025555539858, "grad_norm": 4.509006977081299, "learning_rate": 5.362047361121044e-05, "loss": 0.897557544708252, "step": 53420 }, { "epoch": 1.5098676310622006, "grad_norm": 3.363166093826294, "learning_rate": 5.35894103173069e-05, "loss": 0.9797197341918945, "step": 53440 }, { "epoch": 1.5104327065704155, "grad_norm": 4.207457065582275, "learning_rate": 5.3558345630754666e-05, "loss": 0.9675288200378418, "step": 53460 }, { "epoch": 1.5109977820786302, "grad_norm": 1.918445348739624, "learning_rate": 5.352727956360652e-05, "loss": 0.9385510444641113, "step": 53480 }, { "epoch": 1.5115628575868452, "grad_norm": 4.725681781768799, "learning_rate": 5.349621212791569e-05, "loss": 0.9848820686340332, "step": 53500 }, { "epoch": 1.5121279330950599, "grad_norm": 4.334114074707031, "learning_rate": 5.346514333573601e-05, "loss": 0.9218484878540039, "step": 53520 }, { "epoch": 1.5126930086032746, "grad_norm": 3.945441722869873, "learning_rate": 5.343407319912178e-05, "loss": 0.9075450897216797, "step": 53540 }, { "epoch": 1.5132580841114893, "grad_norm": 3.6890511512756348, "learning_rate": 5.340300173012786e-05, "loss": 0.8635601043701172, "step": 53560 }, { "epoch": 1.513823159619704, "grad_norm": 4.462948322296143, "learning_rate": 5.337192894080958e-05, "loss": 0.8604166984558106, "step": 53580 }, { "epoch": 1.514388235127919, "grad_norm": 4.243091583251953, "learning_rate": 5.3340854843222854e-05, "loss": 0.8522522926330567, "step": 53600 }, { "epoch": 1.5149533106361337, "grad_norm": 3.7620999813079834, "learning_rate": 5.3309779449424025e-05, "loss": 0.88577299118042, "step": 53620 }, { "epoch": 1.5155183861443486, "grad_norm": 2.196272134780884, "learning_rate": 5.327870277147001e-05, "loss": 0.9115303993225098, "step": 53640 }, { "epoch": 1.5160834616525634, "grad_norm": 3.275296449661255, "learning_rate": 5.324762482141818e-05, "loss": 0.9126345634460449, "step": 53660 }, { "epoch": 1.516648537160778, "grad_norm": 3.217991590499878, "learning_rate": 5.321654561132641e-05, "loss": 0.8959705352783203, "step": 53680 }, { "epoch": 1.5172136126689928, "grad_norm": 4.561390399932861, "learning_rate": 5.318546515325305e-05, "loss": 0.9096014976501465, "step": 53700 }, { "epoch": 1.5177786881772075, "grad_norm": 3.1265201568603516, "learning_rate": 5.315438345925698e-05, "loss": 0.9585951805114746, "step": 53720 }, { "epoch": 1.5183437636854225, "grad_norm": 4.3414177894592285, "learning_rate": 5.3123300541397514e-05, "loss": 0.9448690414428711, "step": 53740 }, { "epoch": 1.5189088391936374, "grad_norm": 3.254082202911377, "learning_rate": 5.309221641173445e-05, "loss": 0.9028068542480469, "step": 53760 }, { "epoch": 1.5194739147018521, "grad_norm": 3.1482675075531006, "learning_rate": 5.3061131082328076e-05, "loss": 0.9276082992553711, "step": 53780 }, { "epoch": 1.5200389902100668, "grad_norm": 2.6709201335906982, "learning_rate": 5.3030044565239125e-05, "loss": 0.8793095588684082, "step": 53800 }, { "epoch": 1.5206040657182816, "grad_norm": 2.357696294784546, "learning_rate": 5.299895687252877e-05, "loss": 0.8346278190612793, "step": 53820 }, { "epoch": 1.5211691412264963, "grad_norm": 3.6539242267608643, "learning_rate": 5.2967868016258707e-05, "loss": 0.8767153739929199, "step": 53840 }, { "epoch": 1.5217342167347112, "grad_norm": 3.008049726486206, "learning_rate": 5.293677800849104e-05, "loss": 0.899569034576416, "step": 53860 }, { "epoch": 1.522299292242926, "grad_norm": 3.8779237270355225, "learning_rate": 5.2905686861288294e-05, "loss": 0.9255624771118164, "step": 53880 }, { "epoch": 1.5228643677511409, "grad_norm": 4.116599082946777, "learning_rate": 5.28745945867135e-05, "loss": 0.8959766387939453, "step": 53900 }, { "epoch": 1.5234294432593556, "grad_norm": 3.3405601978302, "learning_rate": 5.2843501196830066e-05, "loss": 0.8851805686950683, "step": 53920 }, { "epoch": 1.5239945187675703, "grad_norm": 2.8415188789367676, "learning_rate": 5.281240670370188e-05, "loss": 0.9176828384399414, "step": 53940 }, { "epoch": 1.524559594275785, "grad_norm": 4.092062473297119, "learning_rate": 5.278131111939321e-05, "loss": 0.9280879974365235, "step": 53960 }, { "epoch": 1.5251246697839997, "grad_norm": 2.5665957927703857, "learning_rate": 5.275021445596879e-05, "loss": 0.9241779327392579, "step": 53980 }, { "epoch": 1.5256897452922147, "grad_norm": 3.1951494216918945, "learning_rate": 5.271911672549377e-05, "loss": 0.8742160797119141, "step": 54000 }, { "epoch": 1.5262548208004296, "grad_norm": 3.9138689041137695, "learning_rate": 5.268801794003368e-05, "loss": 0.8814249038696289, "step": 54020 }, { "epoch": 1.5268198963086443, "grad_norm": 3.987401247024536, "learning_rate": 5.2656918111654484e-05, "loss": 0.9346366882324219, "step": 54040 }, { "epoch": 1.527384971816859, "grad_norm": 3.358973503112793, "learning_rate": 5.262581725242256e-05, "loss": 0.9705645561218261, "step": 54060 }, { "epoch": 1.5279500473250738, "grad_norm": 3.573836326599121, "learning_rate": 5.259471537440466e-05, "loss": 0.8559316635131836, "step": 54080 }, { "epoch": 1.5285151228332885, "grad_norm": 4.775996208190918, "learning_rate": 5.256361248966794e-05, "loss": 0.8109571456909179, "step": 54100 }, { "epoch": 1.5290801983415034, "grad_norm": 4.255273342132568, "learning_rate": 5.2532508610279975e-05, "loss": 0.8381452560424805, "step": 54120 }, { "epoch": 1.5296452738497182, "grad_norm": 4.004293441772461, "learning_rate": 5.2501403748308676e-05, "loss": 0.9828007698059082, "step": 54140 }, { "epoch": 1.530210349357933, "grad_norm": 3.4059925079345703, "learning_rate": 5.247029791582235e-05, "loss": 0.8790141105651855, "step": 54160 }, { "epoch": 1.5307754248661478, "grad_norm": 3.398514747619629, "learning_rate": 5.243919112488973e-05, "loss": 0.8534884452819824, "step": 54180 }, { "epoch": 1.5313405003743625, "grad_norm": 6.113980293273926, "learning_rate": 5.2408083387579865e-05, "loss": 0.8730703353881836, "step": 54200 }, { "epoch": 1.5319055758825773, "grad_norm": 3.220534324645996, "learning_rate": 5.237697471596219e-05, "loss": 0.8783894538879394, "step": 54220 }, { "epoch": 1.532470651390792, "grad_norm": 4.509275436401367, "learning_rate": 5.234586512210649e-05, "loss": 1.0847161293029786, "step": 54240 }, { "epoch": 1.533035726899007, "grad_norm": 4.217897415161133, "learning_rate": 5.231475461808292e-05, "loss": 0.9007205963134766, "step": 54260 }, { "epoch": 1.5336008024072216, "grad_norm": 2.8110530376434326, "learning_rate": 5.2283643215962e-05, "loss": 0.8632587432861328, "step": 54280 }, { "epoch": 1.5341658779154366, "grad_norm": 5.133057594299316, "learning_rate": 5.225253092781458e-05, "loss": 0.9167007446289063, "step": 54300 }, { "epoch": 1.5347309534236513, "grad_norm": 3.0434820652008057, "learning_rate": 5.2221417765711836e-05, "loss": 0.8653610229492188, "step": 54320 }, { "epoch": 1.535296028931866, "grad_norm": 3.840878963470459, "learning_rate": 5.219030374172534e-05, "loss": 0.9160244941711426, "step": 54340 }, { "epoch": 1.5358611044400807, "grad_norm": 3.521240472793579, "learning_rate": 5.2159188867926954e-05, "loss": 0.9967338562011718, "step": 54360 }, { "epoch": 1.5364261799482954, "grad_norm": 4.943854808807373, "learning_rate": 5.212807315638889e-05, "loss": 0.9683509826660156, "step": 54380 }, { "epoch": 1.5369912554565104, "grad_norm": 4.865475177764893, "learning_rate": 5.2096956619183645e-05, "loss": 0.9562701225280762, "step": 54400 }, { "epoch": 1.5375563309647253, "grad_norm": 3.249458074569702, "learning_rate": 5.206583926838411e-05, "loss": 0.8435431480407715, "step": 54420 }, { "epoch": 1.53812140647294, "grad_norm": 4.1324028968811035, "learning_rate": 5.20347211160634e-05, "loss": 0.8703981399536133, "step": 54440 }, { "epoch": 1.5386864819811548, "grad_norm": 3.5175564289093018, "learning_rate": 5.2003602174295017e-05, "loss": 0.8540376663208008, "step": 54460 }, { "epoch": 1.5392515574893695, "grad_norm": 2.939347267150879, "learning_rate": 5.1972482455152736e-05, "loss": 0.9113673210144043, "step": 54480 }, { "epoch": 1.5398166329975842, "grad_norm": 3.297858476638794, "learning_rate": 5.1941361970710644e-05, "loss": 0.8297234535217285, "step": 54500 }, { "epoch": 1.5403817085057991, "grad_norm": 3.2984538078308105, "learning_rate": 5.1910240733043115e-05, "loss": 0.8403326034545898, "step": 54520 }, { "epoch": 1.5409467840140139, "grad_norm": 2.816904306411743, "learning_rate": 5.187911875422482e-05, "loss": 0.8817662239074707, "step": 54540 }, { "epoch": 1.5415118595222288, "grad_norm": 3.0966997146606445, "learning_rate": 5.184799604633073e-05, "loss": 0.7940642356872558, "step": 54560 }, { "epoch": 1.5420769350304435, "grad_norm": 3.100912570953369, "learning_rate": 5.181687262143606e-05, "loss": 0.948647403717041, "step": 54580 }, { "epoch": 1.5426420105386582, "grad_norm": 4.092533588409424, "learning_rate": 5.178574849161637e-05, "loss": 0.9018247604370118, "step": 54600 }, { "epoch": 1.543207086046873, "grad_norm": 4.675783157348633, "learning_rate": 5.175462366894741e-05, "loss": 0.9167039871215821, "step": 54620 }, { "epoch": 1.5437721615550877, "grad_norm": 3.6432321071624756, "learning_rate": 5.1723498165505266e-05, "loss": 0.8839737892150878, "step": 54640 }, { "epoch": 1.5443372370633026, "grad_norm": 4.250858783721924, "learning_rate": 5.169237199336625e-05, "loss": 0.9456918716430665, "step": 54660 }, { "epoch": 1.5449023125715173, "grad_norm": 4.237773418426514, "learning_rate": 5.166124516460698e-05, "loss": 0.8198328018188477, "step": 54680 }, { "epoch": 1.5454673880797323, "grad_norm": 3.0633745193481445, "learning_rate": 5.163011769130426e-05, "loss": 0.8547380447387696, "step": 54700 }, { "epoch": 1.546032463587947, "grad_norm": 4.240952491760254, "learning_rate": 5.159898958553521e-05, "loss": 0.9019953727722168, "step": 54720 }, { "epoch": 1.5465975390961617, "grad_norm": 3.9372265338897705, "learning_rate": 5.156786085937714e-05, "loss": 0.9626302719116211, "step": 54740 }, { "epoch": 1.5471626146043764, "grad_norm": 4.004354476928711, "learning_rate": 5.153673152490764e-05, "loss": 0.9062777519226074, "step": 54760 }, { "epoch": 1.5477276901125911, "grad_norm": 4.229455947875977, "learning_rate": 5.150560159420452e-05, "loss": 0.8563760757446289, "step": 54780 }, { "epoch": 1.548292765620806, "grad_norm": 3.872300386428833, "learning_rate": 5.147447107934584e-05, "loss": 0.9165794372558593, "step": 54800 }, { "epoch": 1.548857841129021, "grad_norm": 2.5999696254730225, "learning_rate": 5.144333999240983e-05, "loss": 0.928151798248291, "step": 54820 }, { "epoch": 1.5494229166372357, "grad_norm": 6.626068115234375, "learning_rate": 5.141220834547503e-05, "loss": 0.8730684280395508, "step": 54840 }, { "epoch": 1.5499879921454505, "grad_norm": 5.332297325134277, "learning_rate": 5.138107615062013e-05, "loss": 0.8136445045471191, "step": 54860 }, { "epoch": 1.5505530676536652, "grad_norm": 2.568805456161499, "learning_rate": 5.134994341992405e-05, "loss": 0.8998163223266602, "step": 54880 }, { "epoch": 1.55111814316188, "grad_norm": 3.579637289047241, "learning_rate": 5.1318810165465916e-05, "loss": 0.9051121711730957, "step": 54900 }, { "epoch": 1.5516832186700948, "grad_norm": 4.15462064743042, "learning_rate": 5.128767639932508e-05, "loss": 0.8892250061035156, "step": 54920 }, { "epoch": 1.5522482941783096, "grad_norm": 3.4483320713043213, "learning_rate": 5.1256542133581054e-05, "loss": 0.9113802909851074, "step": 54940 }, { "epoch": 1.5528133696865245, "grad_norm": 2.8158068656921387, "learning_rate": 5.1225407380313584e-05, "loss": 0.9937457084655762, "step": 54960 }, { "epoch": 1.5533784451947392, "grad_norm": 4.29894495010376, "learning_rate": 5.119427215160254e-05, "loss": 0.7963562965393066, "step": 54980 }, { "epoch": 1.553943520702954, "grad_norm": 3.968653440475464, "learning_rate": 5.1163136459528096e-05, "loss": 0.9409724235534668, "step": 55000 }, { "epoch": 1.5545085962111687, "grad_norm": 3.1770708560943604, "learning_rate": 5.113200031617047e-05, "loss": 0.8332792282104492, "step": 55020 }, { "epoch": 1.5550736717193834, "grad_norm": 3.132981538772583, "learning_rate": 5.110086373361015e-05, "loss": 0.8869638442993164, "step": 55040 }, { "epoch": 1.5556387472275983, "grad_norm": 3.8394827842712402, "learning_rate": 5.1069726723927734e-05, "loss": 0.8495321273803711, "step": 55060 }, { "epoch": 1.556203822735813, "grad_norm": 2.081528663635254, "learning_rate": 5.103858929920404e-05, "loss": 0.8579594612121582, "step": 55080 }, { "epoch": 1.556768898244028, "grad_norm": 4.70947265625, "learning_rate": 5.1007451471519994e-05, "loss": 0.9256291389465332, "step": 55100 }, { "epoch": 1.5573339737522427, "grad_norm": 4.992101192474365, "learning_rate": 5.0976313252956744e-05, "loss": 0.8259572982788086, "step": 55120 }, { "epoch": 1.5578990492604574, "grad_norm": 3.822692632675171, "learning_rate": 5.0945174655595495e-05, "loss": 0.8707575798034668, "step": 55140 }, { "epoch": 1.5584641247686721, "grad_norm": 3.527334690093994, "learning_rate": 5.0914035691517695e-05, "loss": 0.9960488319396973, "step": 55160 }, { "epoch": 1.5590292002768869, "grad_norm": 3.679609775543213, "learning_rate": 5.088289637280488e-05, "loss": 0.9271079063415527, "step": 55180 }, { "epoch": 1.5595942757851018, "grad_norm": 3.673038959503174, "learning_rate": 5.0851756711538724e-05, "loss": 0.840921688079834, "step": 55200 }, { "epoch": 1.5601593512933167, "grad_norm": 2.4813292026519775, "learning_rate": 5.082061671980107e-05, "loss": 0.8881128311157227, "step": 55220 }, { "epoch": 1.5607244268015315, "grad_norm": 2.442316770553589, "learning_rate": 5.0789476409673854e-05, "loss": 0.8470095634460449, "step": 55240 }, { "epoch": 1.5612895023097462, "grad_norm": 3.6812045574188232, "learning_rate": 5.075833579323915e-05, "loss": 0.9626057624816895, "step": 55260 }, { "epoch": 1.5618545778179609, "grad_norm": 3.2347209453582764, "learning_rate": 5.072719488257914e-05, "loss": 0.8442933082580566, "step": 55280 }, { "epoch": 1.5624196533261756, "grad_norm": 2.7342357635498047, "learning_rate": 5.0696053689776146e-05, "loss": 0.8051191329956054, "step": 55300 }, { "epoch": 1.5629847288343905, "grad_norm": 3.06727933883667, "learning_rate": 5.066491222691254e-05, "loss": 0.9071332931518554, "step": 55320 }, { "epoch": 1.5635498043426053, "grad_norm": 2.578486204147339, "learning_rate": 5.06337705060709e-05, "loss": 0.8240762710571289, "step": 55340 }, { "epoch": 1.5641148798508202, "grad_norm": 3.403655529022217, "learning_rate": 5.060262853933381e-05, "loss": 0.836728286743164, "step": 55360 }, { "epoch": 1.564679955359035, "grad_norm": 2.364907741546631, "learning_rate": 5.057148633878399e-05, "loss": 1.0139591217041015, "step": 55380 }, { "epoch": 1.5652450308672496, "grad_norm": 3.707672119140625, "learning_rate": 5.054034391650423e-05, "loss": 0.8955490112304687, "step": 55400 }, { "epoch": 1.5658101063754644, "grad_norm": 3.4493510723114014, "learning_rate": 5.050920128457746e-05, "loss": 0.8821540832519531, "step": 55420 }, { "epoch": 1.566375181883679, "grad_norm": 2.908820152282715, "learning_rate": 5.0478058455086597e-05, "loss": 0.8740100860595703, "step": 55440 }, { "epoch": 1.566940257391894, "grad_norm": 2.527263641357422, "learning_rate": 5.044691544011474e-05, "loss": 0.8205899238586426, "step": 55460 }, { "epoch": 1.5675053329001087, "grad_norm": 3.4839279651641846, "learning_rate": 5.041577225174498e-05, "loss": 0.878383731842041, "step": 55480 }, { "epoch": 1.5680704084083237, "grad_norm": 3.8207244873046875, "learning_rate": 5.038462890206051e-05, "loss": 0.8367876052856446, "step": 55500 }, { "epoch": 1.5686354839165384, "grad_norm": 3.5050771236419678, "learning_rate": 5.0353485403144597e-05, "loss": 0.9210103034973145, "step": 55520 }, { "epoch": 1.5692005594247531, "grad_norm": 3.7257416248321533, "learning_rate": 5.032234176708053e-05, "loss": 0.9480504989624023, "step": 55540 }, { "epoch": 1.5697656349329678, "grad_norm": 3.169445514678955, "learning_rate": 5.029119800595168e-05, "loss": 0.9497528076171875, "step": 55560 }, { "epoch": 1.5703307104411826, "grad_norm": 3.373150587081909, "learning_rate": 5.026005413184146e-05, "loss": 0.8687201499938965, "step": 55580 }, { "epoch": 1.5708957859493975, "grad_norm": 2.113795757293701, "learning_rate": 5.022891015683331e-05, "loss": 0.8429777145385742, "step": 55600 }, { "epoch": 1.5714608614576124, "grad_norm": 3.6247806549072266, "learning_rate": 5.019776609301073e-05, "loss": 0.8531893730163574, "step": 55620 }, { "epoch": 1.5720259369658272, "grad_norm": 2.928877592086792, "learning_rate": 5.016662195245725e-05, "loss": 0.8494444847106933, "step": 55640 }, { "epoch": 1.5725910124740419, "grad_norm": 3.5078256130218506, "learning_rate": 5.013547774725643e-05, "loss": 0.8733296394348145, "step": 55660 }, { "epoch": 1.5731560879822566, "grad_norm": 6.335343837738037, "learning_rate": 5.010433348949185e-05, "loss": 0.9355060577392578, "step": 55680 }, { "epoch": 1.5737211634904713, "grad_norm": 5.070695877075195, "learning_rate": 5.007318919124713e-05, "loss": 0.8862996101379395, "step": 55700 }, { "epoch": 1.5742862389986862, "grad_norm": 3.330991506576538, "learning_rate": 5.004204486460584e-05, "loss": 0.9177059173583985, "step": 55720 }, { "epoch": 1.574851314506901, "grad_norm": 3.9975485801696777, "learning_rate": 5.001090052165167e-05, "loss": 0.9335500717163085, "step": 55740 }, { "epoch": 1.575416390015116, "grad_norm": 2.7027602195739746, "learning_rate": 4.9979756174468206e-05, "loss": 0.8741750717163086, "step": 55760 }, { "epoch": 1.5759814655233306, "grad_norm": 4.088897228240967, "learning_rate": 4.994861183513911e-05, "loss": 0.8915550231933593, "step": 55780 }, { "epoch": 1.5765465410315453, "grad_norm": 3.863429546356201, "learning_rate": 4.991746751574802e-05, "loss": 0.9309154510498047, "step": 55800 }, { "epoch": 1.57711161653976, "grad_norm": 3.221043109893799, "learning_rate": 4.988632322837855e-05, "loss": 0.8790902137756348, "step": 55820 }, { "epoch": 1.5776766920479748, "grad_norm": 4.761786937713623, "learning_rate": 4.985517898511433e-05, "loss": 0.8956962585449219, "step": 55840 }, { "epoch": 1.5782417675561897, "grad_norm": 3.8992903232574463, "learning_rate": 4.982403479803894e-05, "loss": 0.9562283515930176, "step": 55860 }, { "epoch": 1.5788068430644044, "grad_norm": 2.9761316776275635, "learning_rate": 4.9792890679235966e-05, "loss": 0.8818577766418457, "step": 55880 }, { "epoch": 1.5793719185726194, "grad_norm": 4.225212097167969, "learning_rate": 4.976174664078895e-05, "loss": 0.8464499473571777, "step": 55900 }, { "epoch": 1.579936994080834, "grad_norm": 4.6389946937561035, "learning_rate": 4.973060269478142e-05, "loss": 0.8672327041625977, "step": 55920 }, { "epoch": 1.5805020695890488, "grad_norm": 4.616949081420898, "learning_rate": 4.9699458853296836e-05, "loss": 0.8548979759216309, "step": 55940 }, { "epoch": 1.5810671450972635, "grad_norm": 3.09627103805542, "learning_rate": 4.966831512841867e-05, "loss": 0.8321397781372071, "step": 55960 }, { "epoch": 1.5816322206054783, "grad_norm": 3.294186592102051, "learning_rate": 4.96371715322303e-05, "loss": 0.9521600723266601, "step": 55980 }, { "epoch": 1.5821972961136932, "grad_norm": 3.5107085704803467, "learning_rate": 4.9606028076815076e-05, "loss": 0.928222942352295, "step": 56000 }, { "epoch": 1.5827623716219081, "grad_norm": 3.6813554763793945, "learning_rate": 4.957488477425628e-05, "loss": 0.9581534385681152, "step": 56020 }, { "epoch": 1.5833274471301229, "grad_norm": 3.098205089569092, "learning_rate": 4.9543741636637156e-05, "loss": 0.9294265747070313, "step": 56040 }, { "epoch": 1.5838925226383376, "grad_norm": 3.5096099376678467, "learning_rate": 4.951259867604085e-05, "loss": 0.8726882934570312, "step": 56060 }, { "epoch": 1.5844575981465523, "grad_norm": 3.892995834350586, "learning_rate": 4.948145590455052e-05, "loss": 0.9142684936523438, "step": 56080 }, { "epoch": 1.585022673654767, "grad_norm": 3.503633975982666, "learning_rate": 4.9450313334249134e-05, "loss": 0.8718483924865723, "step": 56100 }, { "epoch": 1.585587749162982, "grad_norm": 4.729655742645264, "learning_rate": 4.941917097721966e-05, "loss": 0.791053295135498, "step": 56120 }, { "epoch": 1.5861528246711967, "grad_norm": 5.287764549255371, "learning_rate": 4.9388028845544967e-05, "loss": 0.8909388542175293, "step": 56140 }, { "epoch": 1.5867179001794116, "grad_norm": 3.909130334854126, "learning_rate": 4.935688695130783e-05, "loss": 0.9815987586975098, "step": 56160 }, { "epoch": 1.5872829756876263, "grad_norm": 4.18034553527832, "learning_rate": 4.9325745306590925e-05, "loss": 0.8274064064025879, "step": 56180 }, { "epoch": 1.587848051195841, "grad_norm": 3.3395352363586426, "learning_rate": 4.929460392347686e-05, "loss": 0.9352959632873535, "step": 56200 }, { "epoch": 1.5884131267040558, "grad_norm": 4.604161262512207, "learning_rate": 4.9263462814048105e-05, "loss": 0.8578187942504882, "step": 56220 }, { "epoch": 1.5889782022122705, "grad_norm": 3.282402276992798, "learning_rate": 4.923232199038706e-05, "loss": 0.8406547546386719, "step": 56240 }, { "epoch": 1.5895432777204854, "grad_norm": 3.461440324783325, "learning_rate": 4.920118146457597e-05, "loss": 0.8378796577453613, "step": 56260 }, { "epoch": 1.5901083532287001, "grad_norm": 3.0235841274261475, "learning_rate": 4.9170041248697016e-05, "loss": 0.8714834213256836, "step": 56280 }, { "epoch": 1.590673428736915, "grad_norm": 2.4394474029541016, "learning_rate": 4.913890135483221e-05, "loss": 0.8660140037536621, "step": 56300 }, { "epoch": 1.5912385042451298, "grad_norm": 4.138663291931152, "learning_rate": 4.910776179506348e-05, "loss": 0.8916262626647949, "step": 56320 }, { "epoch": 1.5918035797533445, "grad_norm": 3.60432505607605, "learning_rate": 4.907662258147259e-05, "loss": 0.8776549339294434, "step": 56340 }, { "epoch": 1.5923686552615592, "grad_norm": 3.996286153793335, "learning_rate": 4.904548372614121e-05, "loss": 0.9405634880065918, "step": 56360 }, { "epoch": 1.592933730769774, "grad_norm": 3.20538592338562, "learning_rate": 4.901434524115081e-05, "loss": 0.8300411224365234, "step": 56380 }, { "epoch": 1.593498806277989, "grad_norm": 2.3526129722595215, "learning_rate": 4.898320713858278e-05, "loss": 0.9241615295410156, "step": 56400 }, { "epoch": 1.5940638817862038, "grad_norm": 2.713628053665161, "learning_rate": 4.8952069430518336e-05, "loss": 0.9483512878417969, "step": 56420 }, { "epoch": 1.5946289572944186, "grad_norm": 3.1233417987823486, "learning_rate": 4.892093212903853e-05, "loss": 0.9144718170166015, "step": 56440 }, { "epoch": 1.5951940328026333, "grad_norm": 5.096493244171143, "learning_rate": 4.888979524622428e-05, "loss": 0.8993992805480957, "step": 56460 }, { "epoch": 1.595759108310848, "grad_norm": 4.365126132965088, "learning_rate": 4.88586587941563e-05, "loss": 0.8670491218566895, "step": 56480 }, { "epoch": 1.5963241838190627, "grad_norm": 3.285626173019409, "learning_rate": 4.882752278491519e-05, "loss": 0.8709531784057617, "step": 56500 }, { "epoch": 1.5968892593272777, "grad_norm": 2.581730842590332, "learning_rate": 4.879638723058134e-05, "loss": 0.9635705947875977, "step": 56520 }, { "epoch": 1.5974543348354924, "grad_norm": 3.4972710609436035, "learning_rate": 4.876525214323499e-05, "loss": 0.9209428787231445, "step": 56540 }, { "epoch": 1.5980194103437073, "grad_norm": 3.381357431411743, "learning_rate": 4.873411753495616e-05, "loss": 0.8851014137268066, "step": 56560 }, { "epoch": 1.598584485851922, "grad_norm": 1.618451476097107, "learning_rate": 4.8702983417824735e-05, "loss": 0.870818042755127, "step": 56580 }, { "epoch": 1.5991495613601368, "grad_norm": 3.2553253173828125, "learning_rate": 4.867184980392036e-05, "loss": 0.8958244323730469, "step": 56600 }, { "epoch": 1.5997146368683515, "grad_norm": 3.327897548675537, "learning_rate": 4.8640716705322526e-05, "loss": 0.8127701759338379, "step": 56620 }, { "epoch": 1.6002797123765662, "grad_norm": 4.527971267700195, "learning_rate": 4.860958413411049e-05, "loss": 0.8449416160583496, "step": 56640 }, { "epoch": 1.6008447878847811, "grad_norm": 3.5691463947296143, "learning_rate": 4.857845210236335e-05, "loss": 0.8566247940063476, "step": 56660 }, { "epoch": 1.6014098633929958, "grad_norm": 2.903834342956543, "learning_rate": 4.854732062215993e-05, "loss": 0.9113935470581055, "step": 56680 }, { "epoch": 1.6019749389012108, "grad_norm": 3.765470027923584, "learning_rate": 4.8516189705578904e-05, "loss": 0.8337347984313965, "step": 56700 }, { "epoch": 1.6025400144094255, "grad_norm": 2.637862205505371, "learning_rate": 4.848505936469865e-05, "loss": 0.8335865020751954, "step": 56720 }, { "epoch": 1.6031050899176402, "grad_norm": 4.352963447570801, "learning_rate": 4.845392961159744e-05, "loss": 0.8793338775634766, "step": 56740 }, { "epoch": 1.603670165425855, "grad_norm": 4.25645112991333, "learning_rate": 4.8422800458353204e-05, "loss": 1.003303337097168, "step": 56760 }, { "epoch": 1.6042352409340697, "grad_norm": 3.723389148712158, "learning_rate": 4.839167191704372e-05, "loss": 0.9433449745178223, "step": 56780 }, { "epoch": 1.6048003164422846, "grad_norm": 4.030581474304199, "learning_rate": 4.836054399974645e-05, "loss": 0.8805924415588379, "step": 56800 }, { "epoch": 1.6053653919504995, "grad_norm": 5.2743096351623535, "learning_rate": 4.832941671853869e-05, "loss": 0.9500123023986816, "step": 56820 }, { "epoch": 1.6059304674587143, "grad_norm": 5.866901874542236, "learning_rate": 4.829829008549743e-05, "loss": 0.8701454162597656, "step": 56840 }, { "epoch": 1.606495542966929, "grad_norm": 3.6479477882385254, "learning_rate": 4.826716411269946e-05, "loss": 0.9088825225830078, "step": 56860 }, { "epoch": 1.6070606184751437, "grad_norm": 3.629148483276367, "learning_rate": 4.823603881222127e-05, "loss": 0.860962963104248, "step": 56880 }, { "epoch": 1.6076256939833584, "grad_norm": 4.996467113494873, "learning_rate": 4.820491419613912e-05, "loss": 0.8962726593017578, "step": 56900 }, { "epoch": 1.6081907694915734, "grad_norm": 2.5047757625579834, "learning_rate": 4.817379027652897e-05, "loss": 0.8647299766540527, "step": 56920 }, { "epoch": 1.608755844999788, "grad_norm": 3.687925100326538, "learning_rate": 4.814266706546657e-05, "loss": 0.8475747108459473, "step": 56940 }, { "epoch": 1.609320920508003, "grad_norm": 3.5586447715759277, "learning_rate": 4.8111544575027326e-05, "loss": 0.9002204895019531, "step": 56960 }, { "epoch": 1.6098859960162177, "grad_norm": 2.905505895614624, "learning_rate": 4.8080422817286405e-05, "loss": 0.845196533203125, "step": 56980 }, { "epoch": 1.6104510715244325, "grad_norm": 2.743567705154419, "learning_rate": 4.804930180431868e-05, "loss": 0.8837075233459473, "step": 57000 }, { "epoch": 1.6110161470326472, "grad_norm": 3.5416839122772217, "learning_rate": 4.801818154819874e-05, "loss": 0.876768970489502, "step": 57020 }, { "epoch": 1.611581222540862, "grad_norm": 6.300116539001465, "learning_rate": 4.7987062061000856e-05, "loss": 0.903406810760498, "step": 57040 }, { "epoch": 1.6121462980490768, "grad_norm": 4.233022212982178, "learning_rate": 4.795594335479904e-05, "loss": 0.908663272857666, "step": 57060 }, { "epoch": 1.6127113735572915, "grad_norm": 3.006810426712036, "learning_rate": 4.792482544166698e-05, "loss": 0.883425521850586, "step": 57080 }, { "epoch": 1.6132764490655065, "grad_norm": 4.252974510192871, "learning_rate": 4.789370833367806e-05, "loss": 0.8457976341247558, "step": 57100 }, { "epoch": 1.6138415245737212, "grad_norm": 3.426663637161255, "learning_rate": 4.786259204290533e-05, "loss": 0.9355461120605468, "step": 57120 }, { "epoch": 1.614406600081936, "grad_norm": 3.263307809829712, "learning_rate": 4.783147658142156e-05, "loss": 0.9218930244445801, "step": 57140 }, { "epoch": 1.6149716755901506, "grad_norm": 3.0489583015441895, "learning_rate": 4.7800361961299187e-05, "loss": 0.8605301856994629, "step": 57160 }, { "epoch": 1.6155367510983654, "grad_norm": 3.6243441104888916, "learning_rate": 4.7769248194610286e-05, "loss": 0.9229948997497559, "step": 57180 }, { "epoch": 1.6161018266065803, "grad_norm": 2.963547706604004, "learning_rate": 4.7738135293426665e-05, "loss": 0.8814208984375, "step": 57200 }, { "epoch": 1.6166669021147952, "grad_norm": 4.485185146331787, "learning_rate": 4.770702326981973e-05, "loss": 0.8753458976745605, "step": 57220 }, { "epoch": 1.61723197762301, "grad_norm": 2.8581786155700684, "learning_rate": 4.7675912135860597e-05, "loss": 0.8303105354309082, "step": 57240 }, { "epoch": 1.6177970531312247, "grad_norm": 4.825594902038574, "learning_rate": 4.764480190362e-05, "loss": 0.9191519737243652, "step": 57260 }, { "epoch": 1.6183621286394394, "grad_norm": 4.617002487182617, "learning_rate": 4.7613692585168354e-05, "loss": 0.9042185783386231, "step": 57280 }, { "epoch": 1.6189272041476541, "grad_norm": 4.816636085510254, "learning_rate": 4.75825841925757e-05, "loss": 0.8626128196716308, "step": 57300 }, { "epoch": 1.619492279655869, "grad_norm": 2.841257095336914, "learning_rate": 4.755147673791174e-05, "loss": 0.8579653739929199, "step": 57320 }, { "epoch": 1.6200573551640838, "grad_norm": 3.6887717247009277, "learning_rate": 4.752037023324577e-05, "loss": 0.9310956954956054, "step": 57340 }, { "epoch": 1.6206224306722987, "grad_norm": 4.204286575317383, "learning_rate": 4.748926469064677e-05, "loss": 0.9612234115600586, "step": 57360 }, { "epoch": 1.6211875061805134, "grad_norm": 5.135738372802734, "learning_rate": 4.7458160122183286e-05, "loss": 0.836529541015625, "step": 57380 }, { "epoch": 1.6217525816887282, "grad_norm": 2.789022207260132, "learning_rate": 4.742705653992358e-05, "loss": 0.958930492401123, "step": 57400 }, { "epoch": 1.6223176571969429, "grad_norm": 3.071284294128418, "learning_rate": 4.7395953955935434e-05, "loss": 0.8147919654846192, "step": 57420 }, { "epoch": 1.6228827327051576, "grad_norm": 3.223642110824585, "learning_rate": 4.73648523822863e-05, "loss": 0.8585064888000489, "step": 57440 }, { "epoch": 1.6234478082133725, "grad_norm": 3.217301607131958, "learning_rate": 4.733375183104319e-05, "loss": 0.9531063079833985, "step": 57460 }, { "epoch": 1.6240128837215873, "grad_norm": 3.9535329341888428, "learning_rate": 4.730265231427279e-05, "loss": 0.8456916809082031, "step": 57480 }, { "epoch": 1.6245779592298022, "grad_norm": 4.252240180969238, "learning_rate": 4.72715538440413e-05, "loss": 0.9327755928039551, "step": 57500 }, { "epoch": 1.625143034738017, "grad_norm": 3.7804245948791504, "learning_rate": 4.724045643241461e-05, "loss": 0.8922506332397461, "step": 57520 }, { "epoch": 1.6257081102462316, "grad_norm": 3.1219370365142822, "learning_rate": 4.720936009145809e-05, "loss": 0.843724536895752, "step": 57540 }, { "epoch": 1.6262731857544463, "grad_norm": 4.308350563049316, "learning_rate": 4.71782648332368e-05, "loss": 0.9112510681152344, "step": 57560 }, { "epoch": 1.626838261262661, "grad_norm": 3.1455674171447754, "learning_rate": 4.71471706698153e-05, "loss": 0.9707188606262207, "step": 57580 }, { "epoch": 1.627403336770876, "grad_norm": 4.119235992431641, "learning_rate": 4.711607761325778e-05, "loss": 0.9044174194335938, "step": 57600 }, { "epoch": 1.627968412279091, "grad_norm": 4.582209587097168, "learning_rate": 4.708498567562795e-05, "loss": 0.911253833770752, "step": 57620 }, { "epoch": 1.6285334877873057, "grad_norm": 3.343346357345581, "learning_rate": 4.705389486898914e-05, "loss": 0.8379268646240234, "step": 57640 }, { "epoch": 1.6290985632955204, "grad_norm": 3.6766629219055176, "learning_rate": 4.7022805205404196e-05, "loss": 0.8318651199340821, "step": 57660 }, { "epoch": 1.629663638803735, "grad_norm": 6.22855806350708, "learning_rate": 4.699171669693556e-05, "loss": 0.8662379264831543, "step": 57680 }, { "epoch": 1.6302287143119498, "grad_norm": 3.229985237121582, "learning_rate": 4.6960629355645165e-05, "loss": 0.9051274299621582, "step": 57700 }, { "epoch": 1.6307937898201648, "grad_norm": 2.9538674354553223, "learning_rate": 4.6929543193594574e-05, "loss": 0.8992338180541992, "step": 57720 }, { "epoch": 1.6313588653283795, "grad_norm": 4.649527549743652, "learning_rate": 4.689845822284484e-05, "loss": 0.8957122802734375, "step": 57740 }, { "epoch": 1.6319239408365944, "grad_norm": 4.015986919403076, "learning_rate": 4.686737445545654e-05, "loss": 0.8993066787719727, "step": 57760 }, { "epoch": 1.6324890163448091, "grad_norm": 4.476535320281982, "learning_rate": 4.6836291903489834e-05, "loss": 0.9016331672668457, "step": 57780 }, { "epoch": 1.6330540918530239, "grad_norm": 3.3825392723083496, "learning_rate": 4.680521057900437e-05, "loss": 0.8702305793762207, "step": 57800 }, { "epoch": 1.6336191673612386, "grad_norm": 4.287894248962402, "learning_rate": 4.677413049405934e-05, "loss": 0.7580429077148437, "step": 57820 }, { "epoch": 1.6341842428694533, "grad_norm": 3.7134368419647217, "learning_rate": 4.674305166071344e-05, "loss": 0.8809316635131836, "step": 57840 }, { "epoch": 1.6347493183776682, "grad_norm": 3.33252215385437, "learning_rate": 4.671197409102491e-05, "loss": 0.8486395835876465, "step": 57860 }, { "epoch": 1.635314393885883, "grad_norm": 3.3516781330108643, "learning_rate": 4.6680897797051445e-05, "loss": 0.8643050193786621, "step": 57880 }, { "epoch": 1.635879469394098, "grad_norm": 4.967357158660889, "learning_rate": 4.6649822790850304e-05, "loss": 0.8801865577697754, "step": 57900 }, { "epoch": 1.6364445449023126, "grad_norm": 2.6482577323913574, "learning_rate": 4.661874908447821e-05, "loss": 0.9023847579956055, "step": 57920 }, { "epoch": 1.6370096204105273, "grad_norm": 4.120211124420166, "learning_rate": 4.658767668999141e-05, "loss": 0.8680561065673829, "step": 57940 }, { "epoch": 1.637574695918742, "grad_norm": 2.195451498031616, "learning_rate": 4.655660561944559e-05, "loss": 0.9524897575378418, "step": 57960 }, { "epoch": 1.6381397714269568, "grad_norm": 2.7745771408081055, "learning_rate": 4.6525535884895994e-05, "loss": 0.9087635993957519, "step": 57980 }, { "epoch": 1.6387048469351717, "grad_norm": 3.0779073238372803, "learning_rate": 4.6494467498397286e-05, "loss": 0.9148242950439454, "step": 58000 }, { "epoch": 1.6392699224433867, "grad_norm": 3.4167890548706055, "learning_rate": 4.646340047200365e-05, "loss": 0.8887776374816895, "step": 58020 }, { "epoch": 1.6398349979516014, "grad_norm": 2.6754915714263916, "learning_rate": 4.643233481776868e-05, "loss": 0.911707592010498, "step": 58040 }, { "epoch": 1.640400073459816, "grad_norm": 4.422379493713379, "learning_rate": 4.6401270547745555e-05, "loss": 0.8975221633911132, "step": 58060 }, { "epoch": 1.6409651489680308, "grad_norm": 3.0717382431030273, "learning_rate": 4.637020767398679e-05, "loss": 0.9044670104980469, "step": 58080 }, { "epoch": 1.6415302244762455, "grad_norm": 3.4278502464294434, "learning_rate": 4.633914620854444e-05, "loss": 0.852958869934082, "step": 58100 }, { "epoch": 1.6420952999844605, "grad_norm": 4.395163059234619, "learning_rate": 4.6308086163469966e-05, "loss": 0.8537375450134277, "step": 58120 }, { "epoch": 1.6426603754926752, "grad_norm": 3.6023406982421875, "learning_rate": 4.627702755081431e-05, "loss": 0.8823452949523926, "step": 58140 }, { "epoch": 1.6432254510008901, "grad_norm": 3.865816831588745, "learning_rate": 4.6245970382627824e-05, "loss": 0.8446880340576172, "step": 58160 }, { "epoch": 1.6437905265091048, "grad_norm": 4.203664302825928, "learning_rate": 4.621491467096036e-05, "loss": 0.9138632774353027, "step": 58180 }, { "epoch": 1.6443556020173196, "grad_norm": 3.7917821407318115, "learning_rate": 4.618386042786112e-05, "loss": 0.8538110733032227, "step": 58200 }, { "epoch": 1.6449206775255343, "grad_norm": 3.326253652572632, "learning_rate": 4.615280766537882e-05, "loss": 0.8267094612121582, "step": 58220 }, { "epoch": 1.645485753033749, "grad_norm": 2.699676036834717, "learning_rate": 4.6121756395561536e-05, "loss": 0.9432575225830078, "step": 58240 }, { "epoch": 1.646050828541964, "grad_norm": 3.4451346397399902, "learning_rate": 4.609070663045682e-05, "loss": 0.9348804473876953, "step": 58260 }, { "epoch": 1.6466159040501787, "grad_norm": 2.7042441368103027, "learning_rate": 4.6059658382111586e-05, "loss": 0.8555363655090332, "step": 58280 }, { "epoch": 1.6471809795583936, "grad_norm": 3.7895166873931885, "learning_rate": 4.6028611662572216e-05, "loss": 0.919192123413086, "step": 58300 }, { "epoch": 1.6477460550666083, "grad_norm": 3.448178768157959, "learning_rate": 4.599756648388443e-05, "loss": 0.9541172027587891, "step": 58320 }, { "epoch": 1.648311130574823, "grad_norm": 4.60414457321167, "learning_rate": 4.5966522858093423e-05, "loss": 0.932528305053711, "step": 58340 }, { "epoch": 1.6488762060830378, "grad_norm": 3.5347206592559814, "learning_rate": 4.593548079724373e-05, "loss": 0.8312646865844726, "step": 58360 }, { "epoch": 1.6494412815912525, "grad_norm": 3.2708756923675537, "learning_rate": 4.590444031337932e-05, "loss": 0.8555805206298828, "step": 58380 }, { "epoch": 1.6500063570994674, "grad_norm": 4.5653395652771, "learning_rate": 4.587340141854354e-05, "loss": 0.8698336601257324, "step": 58400 }, { "epoch": 1.6505714326076824, "grad_norm": 2.8486452102661133, "learning_rate": 4.584236412477909e-05, "loss": 0.9311953544616699, "step": 58420 }, { "epoch": 1.651136508115897, "grad_norm": 3.9044134616851807, "learning_rate": 4.581132844412809e-05, "loss": 0.9403890609741211, "step": 58440 }, { "epoch": 1.6517015836241118, "grad_norm": 3.1302335262298584, "learning_rate": 4.5780294388632e-05, "loss": 0.8775270462036133, "step": 58460 }, { "epoch": 1.6522666591323265, "grad_norm": 4.253042221069336, "learning_rate": 4.574926197033169e-05, "loss": 0.8827965736389161, "step": 58480 }, { "epoch": 1.6528317346405412, "grad_norm": 4.380221366882324, "learning_rate": 4.5718231201267344e-05, "loss": 0.8513295173645019, "step": 58500 }, { "epoch": 1.6533968101487562, "grad_norm": 4.983356475830078, "learning_rate": 4.5687202093478553e-05, "loss": 0.8498151779174805, "step": 58520 }, { "epoch": 1.6539618856569709, "grad_norm": 5.118454456329346, "learning_rate": 4.5656174659004224e-05, "loss": 0.8782998085021972, "step": 58540 }, { "epoch": 1.6545269611651858, "grad_norm": 3.112246513366699, "learning_rate": 4.562514890988265e-05, "loss": 0.8734102249145508, "step": 58560 }, { "epoch": 1.6550920366734005, "grad_norm": 4.50927734375, "learning_rate": 4.559412485815145e-05, "loss": 0.8432339668273926, "step": 58580 }, { "epoch": 1.6556571121816153, "grad_norm": 3.678056478500366, "learning_rate": 4.556310251584759e-05, "loss": 0.8733566284179688, "step": 58600 }, { "epoch": 1.65622218768983, "grad_norm": 3.2549285888671875, "learning_rate": 4.5532081895007354e-05, "loss": 0.925629997253418, "step": 58620 }, { "epoch": 1.6567872631980447, "grad_norm": 5.196617126464844, "learning_rate": 4.55010630076664e-05, "loss": 0.8608118057250976, "step": 58640 }, { "epoch": 1.6573523387062596, "grad_norm": 4.592658996582031, "learning_rate": 4.547004586585967e-05, "loss": 0.7773328304290772, "step": 58660 }, { "epoch": 1.6579174142144744, "grad_norm": 2.507361888885498, "learning_rate": 4.543903048162147e-05, "loss": 0.9323184013366699, "step": 58680 }, { "epoch": 1.6584824897226893, "grad_norm": 3.2401089668273926, "learning_rate": 4.540801686698535e-05, "loss": 0.8899561882019043, "step": 58700 }, { "epoch": 1.659047565230904, "grad_norm": 4.091181755065918, "learning_rate": 4.5377005033984286e-05, "loss": 0.8526890754699707, "step": 58720 }, { "epoch": 1.6596126407391187, "grad_norm": 2.522500514984131, "learning_rate": 4.5345994994650474e-05, "loss": 0.9099120140075684, "step": 58740 }, { "epoch": 1.6601777162473335, "grad_norm": 5.3331685066223145, "learning_rate": 4.5314986761015455e-05, "loss": 0.9464930534362793, "step": 58760 }, { "epoch": 1.6607427917555482, "grad_norm": 2.617485761642456, "learning_rate": 4.5283980345110036e-05, "loss": 0.7980404853820801, "step": 58780 }, { "epoch": 1.6613078672637631, "grad_norm": 3.8274002075195312, "learning_rate": 4.525297575896436e-05, "loss": 0.8844066619873047, "step": 58800 }, { "epoch": 1.661872942771978, "grad_norm": 3.458699941635132, "learning_rate": 4.5221973014607816e-05, "loss": 0.8288088798522949, "step": 58820 }, { "epoch": 1.6624380182801928, "grad_norm": 2.8632583618164062, "learning_rate": 4.519097212406912e-05, "loss": 0.8474609375, "step": 58840 }, { "epoch": 1.6630030937884075, "grad_norm": 3.4331319332122803, "learning_rate": 4.515997309937624e-05, "loss": 0.8249417304992676, "step": 58860 }, { "epoch": 1.6635681692966222, "grad_norm": 2.5781424045562744, "learning_rate": 4.512897595255643e-05, "loss": 0.8363814353942871, "step": 58880 }, { "epoch": 1.664133244804837, "grad_norm": 3.870633840560913, "learning_rate": 4.509798069563622e-05, "loss": 0.846243953704834, "step": 58900 }, { "epoch": 1.6646983203130519, "grad_norm": 5.156625747680664, "learning_rate": 4.506698734064141e-05, "loss": 0.8630765914916992, "step": 58920 }, { "epoch": 1.6652633958212666, "grad_norm": 4.006246089935303, "learning_rate": 4.503599589959704e-05, "loss": 0.8300262451171875, "step": 58940 }, { "epoch": 1.6658284713294815, "grad_norm": 3.4522833824157715, "learning_rate": 4.500500638452743e-05, "loss": 0.9098063468933105, "step": 58960 }, { "epoch": 1.6663935468376962, "grad_norm": 3.916006565093994, "learning_rate": 4.497401880745613e-05, "loss": 0.8169742584228515, "step": 58980 }, { "epoch": 1.666958622345911, "grad_norm": 4.352824687957764, "learning_rate": 4.494303318040598e-05, "loss": 0.9022117614746094, "step": 59000 }, { "epoch": 1.6675236978541257, "grad_norm": 2.5737481117248535, "learning_rate": 4.4912049515399e-05, "loss": 0.9934693336486816, "step": 59020 }, { "epoch": 1.6680887733623404, "grad_norm": 4.300994873046875, "learning_rate": 4.488106782445652e-05, "loss": 0.8252830505371094, "step": 59040 }, { "epoch": 1.6686538488705553, "grad_norm": 3.5752429962158203, "learning_rate": 4.485008811959905e-05, "loss": 0.8251298904418946, "step": 59060 }, { "epoch": 1.66921892437877, "grad_norm": 2.7030415534973145, "learning_rate": 4.481911041284636e-05, "loss": 0.8443567276000976, "step": 59080 }, { "epoch": 1.669783999886985, "grad_norm": 4.145143508911133, "learning_rate": 4.478813471621743e-05, "loss": 0.8624477386474609, "step": 59100 }, { "epoch": 1.6703490753951997, "grad_norm": 3.614983558654785, "learning_rate": 4.4757161041730446e-05, "loss": 0.9802151679992676, "step": 59120 }, { "epoch": 1.6709141509034144, "grad_norm": 4.010517597198486, "learning_rate": 4.472618940140285e-05, "loss": 0.8503291130065918, "step": 59140 }, { "epoch": 1.6714792264116292, "grad_norm": 3.475818395614624, "learning_rate": 4.4695219807251256e-05, "loss": 0.9005612373352051, "step": 59160 }, { "epoch": 1.6720443019198439, "grad_norm": 2.4550082683563232, "learning_rate": 4.466425227129151e-05, "loss": 0.8569863319396973, "step": 59180 }, { "epoch": 1.6726093774280588, "grad_norm": 5.3380584716796875, "learning_rate": 4.4633286805538626e-05, "loss": 0.8744158744812012, "step": 59200 }, { "epoch": 1.6731744529362738, "grad_norm": 3.5040688514709473, "learning_rate": 4.460232342200687e-05, "loss": 0.8296205520629882, "step": 59220 }, { "epoch": 1.6737395284444885, "grad_norm": 4.346904277801514, "learning_rate": 4.457136213270965e-05, "loss": 0.8460803031921387, "step": 59240 }, { "epoch": 1.6743046039527032, "grad_norm": 4.66533899307251, "learning_rate": 4.4540402949659585e-05, "loss": 0.8982393264770507, "step": 59260 }, { "epoch": 1.674869679460918, "grad_norm": 3.7458600997924805, "learning_rate": 4.4509445884868467e-05, "loss": 0.9570161819458007, "step": 59280 }, { "epoch": 1.6754347549691326, "grad_norm": 3.613274574279785, "learning_rate": 4.4478490950347274e-05, "loss": 0.8169754028320313, "step": 59300 }, { "epoch": 1.6759998304773476, "grad_norm": 2.8098835945129395, "learning_rate": 4.444753815810614e-05, "loss": 0.9168247222900391, "step": 59320 }, { "epoch": 1.6765649059855623, "grad_norm": 5.2214789390563965, "learning_rate": 4.4416587520154404e-05, "loss": 0.8512397766113281, "step": 59340 }, { "epoch": 1.6771299814937772, "grad_norm": 3.7522451877593994, "learning_rate": 4.438563904850051e-05, "loss": 0.9423583030700684, "step": 59360 }, { "epoch": 1.677695057001992, "grad_norm": 4.5849103927612305, "learning_rate": 4.435469275515215e-05, "loss": 0.8540142059326172, "step": 59380 }, { "epoch": 1.6782601325102067, "grad_norm": 3.1913111209869385, "learning_rate": 4.432374865211608e-05, "loss": 0.9330638885498047, "step": 59400 }, { "epoch": 1.6788252080184214, "grad_norm": 4.074123382568359, "learning_rate": 4.429280675139827e-05, "loss": 0.9184786796569824, "step": 59420 }, { "epoch": 1.679390283526636, "grad_norm": 4.354849338531494, "learning_rate": 4.4261867065003796e-05, "loss": 0.9201838493347168, "step": 59440 }, { "epoch": 1.679955359034851, "grad_norm": 3.900238275527954, "learning_rate": 4.4230929604936894e-05, "loss": 0.8810221672058105, "step": 59460 }, { "epoch": 1.6805204345430658, "grad_norm": 3.0572597980499268, "learning_rate": 4.419999438320092e-05, "loss": 0.8818166732788086, "step": 59480 }, { "epoch": 1.6810855100512807, "grad_norm": 2.7698559761047363, "learning_rate": 4.41690614117984e-05, "loss": 0.8948578834533691, "step": 59500 }, { "epoch": 1.6816505855594954, "grad_norm": 3.288374185562134, "learning_rate": 4.413813070273093e-05, "loss": 0.8694158554077148, "step": 59520 }, { "epoch": 1.6822156610677101, "grad_norm": 4.732200622558594, "learning_rate": 4.410720226799928e-05, "loss": 0.8737277984619141, "step": 59540 }, { "epoch": 1.6827807365759249, "grad_norm": 3.071580171585083, "learning_rate": 4.4076276119603306e-05, "loss": 0.8804327011108398, "step": 59560 }, { "epoch": 1.6833458120841396, "grad_norm": 4.885799884796143, "learning_rate": 4.404535226954199e-05, "loss": 0.88522367477417, "step": 59580 }, { "epoch": 1.6839108875923545, "grad_norm": 4.040060043334961, "learning_rate": 4.401443072981342e-05, "loss": 0.8761440277099609, "step": 59600 }, { "epoch": 1.6844759631005695, "grad_norm": 3.425379753112793, "learning_rate": 4.3983511512414784e-05, "loss": 0.9153575897216797, "step": 59620 }, { "epoch": 1.6850410386087842, "grad_norm": 4.289301872253418, "learning_rate": 4.395259462934237e-05, "loss": 0.912388801574707, "step": 59640 }, { "epoch": 1.685606114116999, "grad_norm": 3.371210813522339, "learning_rate": 4.392168009259157e-05, "loss": 0.8824550628662109, "step": 59660 }, { "epoch": 1.6861711896252136, "grad_norm": 3.8740577697753906, "learning_rate": 4.389076791415684e-05, "loss": 0.8855094909667969, "step": 59680 }, { "epoch": 1.6867362651334283, "grad_norm": 4.112959861755371, "learning_rate": 4.385985810603176e-05, "loss": 0.8522166252136231, "step": 59700 }, { "epoch": 1.6873013406416433, "grad_norm": 3.5770626068115234, "learning_rate": 4.382895068020897e-05, "loss": 0.8705323219299317, "step": 59720 }, { "epoch": 1.687866416149858, "grad_norm": 4.1968255043029785, "learning_rate": 4.379804564868017e-05, "loss": 0.8890581130981445, "step": 59740 }, { "epoch": 1.688431491658073, "grad_norm": 3.3341383934020996, "learning_rate": 4.376714302343616e-05, "loss": 0.793816328048706, "step": 59760 }, { "epoch": 1.6889965671662877, "grad_norm": 3.580042600631714, "learning_rate": 4.373624281646678e-05, "loss": 0.9709608078002929, "step": 59780 }, { "epoch": 1.6895616426745024, "grad_norm": 3.669736385345459, "learning_rate": 4.370534503976095e-05, "loss": 0.8465720176696777, "step": 59800 }, { "epoch": 1.690126718182717, "grad_norm": 4.81746768951416, "learning_rate": 4.367444970530664e-05, "loss": 0.8145421981811524, "step": 59820 }, { "epoch": 1.6906917936909318, "grad_norm": 3.6261579990386963, "learning_rate": 4.364355682509088e-05, "loss": 0.9308454513549804, "step": 59840 }, { "epoch": 1.6912568691991468, "grad_norm": 4.273457050323486, "learning_rate": 4.361266641109972e-05, "loss": 0.8218532562255859, "step": 59860 }, { "epoch": 1.6918219447073615, "grad_norm": 3.428680181503296, "learning_rate": 4.358177847531831e-05, "loss": 0.8707486152648926, "step": 59880 }, { "epoch": 1.6923870202155764, "grad_norm": 3.128323793411255, "learning_rate": 4.3550893029730766e-05, "loss": 0.8509444236755371, "step": 59900 }, { "epoch": 1.6929520957237911, "grad_norm": 4.285588264465332, "learning_rate": 4.35200100863203e-05, "loss": 0.9574039459228516, "step": 59920 }, { "epoch": 1.6935171712320058, "grad_norm": 2.8754372596740723, "learning_rate": 4.3489129657069115e-05, "loss": 0.8036169052124024, "step": 59940 }, { "epoch": 1.6940822467402206, "grad_norm": 4.035620212554932, "learning_rate": 4.345825175395846e-05, "loss": 0.8519404411315918, "step": 59960 }, { "epoch": 1.6946473222484353, "grad_norm": 4.800774097442627, "learning_rate": 4.3427376388968586e-05, "loss": 0.9041661262512207, "step": 59980 }, { "epoch": 1.6952123977566502, "grad_norm": 4.201012134552002, "learning_rate": 4.339650357407878e-05, "loss": 0.7943154811859131, "step": 60000 }, { "epoch": 1.6957774732648652, "grad_norm": 3.5859055519104004, "learning_rate": 4.33656333212673e-05, "loss": 0.9017263412475586, "step": 60020 }, { "epoch": 1.6963425487730799, "grad_norm": 4.894337177276611, "learning_rate": 4.333476564251149e-05, "loss": 0.9950539588928222, "step": 60040 }, { "epoch": 1.6969076242812946, "grad_norm": 4.013128280639648, "learning_rate": 4.3303900549787596e-05, "loss": 0.8830694198608399, "step": 60060 }, { "epoch": 1.6974726997895093, "grad_norm": 3.889805316925049, "learning_rate": 4.327303805507094e-05, "loss": 0.922640323638916, "step": 60080 }, { "epoch": 1.698037775297724, "grad_norm": 5.758687496185303, "learning_rate": 4.324217817033578e-05, "loss": 0.9109372138977051, "step": 60100 }, { "epoch": 1.698602850805939, "grad_norm": 3.329439401626587, "learning_rate": 4.321132090755541e-05, "loss": 0.8298784255981445, "step": 60120 }, { "epoch": 1.6991679263141537, "grad_norm": 4.770193099975586, "learning_rate": 4.3180466278702054e-05, "loss": 0.8077301979064941, "step": 60140 }, { "epoch": 1.6997330018223686, "grad_norm": 3.1958303451538086, "learning_rate": 4.314961429574697e-05, "loss": 0.8849638938903809, "step": 60160 }, { "epoch": 1.7002980773305834, "grad_norm": 3.2262606620788574, "learning_rate": 4.311876497066033e-05, "loss": 0.8583522796630859, "step": 60180 }, { "epoch": 1.700863152838798, "grad_norm": 3.425276756286621, "learning_rate": 4.3087918315411346e-05, "loss": 0.7963547706604004, "step": 60200 }, { "epoch": 1.7014282283470128, "grad_norm": 3.293478488922119, "learning_rate": 4.305707434196812e-05, "loss": 0.8613668441772461, "step": 60220 }, { "epoch": 1.7019933038552275, "grad_norm": 3.112339735031128, "learning_rate": 4.302623306229777e-05, "loss": 0.858604907989502, "step": 60240 }, { "epoch": 1.7025583793634425, "grad_norm": 2.541006565093994, "learning_rate": 4.299539448836633e-05, "loss": 0.8586556434631347, "step": 60260 }, { "epoch": 1.7031234548716572, "grad_norm": 3.3399510383605957, "learning_rate": 4.2964558632138815e-05, "loss": 0.9293466567993164, "step": 60280 }, { "epoch": 1.7036885303798721, "grad_norm": 3.356156587600708, "learning_rate": 4.293372550557917e-05, "loss": 0.8256745338439941, "step": 60300 }, { "epoch": 1.7042536058880868, "grad_norm": 3.9602301120758057, "learning_rate": 4.290289512065028e-05, "loss": 0.8885763168334961, "step": 60320 }, { "epoch": 1.7048186813963015, "grad_norm": 3.5015554428100586, "learning_rate": 4.287206748931394e-05, "loss": 0.9292790412902832, "step": 60340 }, { "epoch": 1.7053837569045163, "grad_norm": 3.329089641571045, "learning_rate": 4.284124262353095e-05, "loss": 0.8943634033203125, "step": 60360 }, { "epoch": 1.705948832412731, "grad_norm": 3.692802667617798, "learning_rate": 4.281042053526099e-05, "loss": 0.9267314910888672, "step": 60380 }, { "epoch": 1.706513907920946, "grad_norm": 2.457543134689331, "learning_rate": 4.277960123646264e-05, "loss": 0.8450347900390625, "step": 60400 }, { "epoch": 1.7070789834291609, "grad_norm": 4.344062805175781, "learning_rate": 4.274878473909345e-05, "loss": 0.9117886543273925, "step": 60420 }, { "epoch": 1.7076440589373756, "grad_norm": 4.001559734344482, "learning_rate": 4.271797105510982e-05, "loss": 0.8100485801696777, "step": 60440 }, { "epoch": 1.7082091344455903, "grad_norm": 3.779277801513672, "learning_rate": 4.268716019646712e-05, "loss": 0.8234956741333008, "step": 60460 }, { "epoch": 1.708774209953805, "grad_norm": 5.223466396331787, "learning_rate": 4.26563521751196e-05, "loss": 0.869759464263916, "step": 60480 }, { "epoch": 1.7093392854620197, "grad_norm": 4.258129596710205, "learning_rate": 4.262554700302039e-05, "loss": 0.8356969833374024, "step": 60500 }, { "epoch": 1.7099043609702347, "grad_norm": 3.5177149772644043, "learning_rate": 4.259474469212154e-05, "loss": 0.844805908203125, "step": 60520 }, { "epoch": 1.7104694364784494, "grad_norm": 3.071213960647583, "learning_rate": 4.256394525437399e-05, "loss": 0.9353161811828613, "step": 60540 }, { "epoch": 1.7110345119866643, "grad_norm": 2.6734352111816406, "learning_rate": 4.253314870172754e-05, "loss": 0.8808902740478516, "step": 60560 }, { "epoch": 1.711599587494879, "grad_norm": 3.917189359664917, "learning_rate": 4.2502355046130903e-05, "loss": 0.8394220352172852, "step": 60580 }, { "epoch": 1.7121646630030938, "grad_norm": 3.359095811843872, "learning_rate": 4.247156429953164e-05, "loss": 0.9069055557250977, "step": 60600 }, { "epoch": 1.7127297385113085, "grad_norm": 4.133177757263184, "learning_rate": 4.244077647387622e-05, "loss": 0.8125590324401856, "step": 60620 }, { "epoch": 1.7132948140195232, "grad_norm": 3.3276922702789307, "learning_rate": 4.240999158110991e-05, "loss": 0.7905981063842773, "step": 60640 }, { "epoch": 1.7138598895277382, "grad_norm": 4.31410026550293, "learning_rate": 4.237920963317692e-05, "loss": 0.856661605834961, "step": 60660 }, { "epoch": 1.7144249650359529, "grad_norm": 3.408280611038208, "learning_rate": 4.234843064202026e-05, "loss": 0.9107250213623047, "step": 60680 }, { "epoch": 1.7149900405441678, "grad_norm": 5.47359037399292, "learning_rate": 4.231765461958183e-05, "loss": 0.8573918342590332, "step": 60700 }, { "epoch": 1.7155551160523825, "grad_norm": 5.633647918701172, "learning_rate": 4.2286881577802364e-05, "loss": 0.9384159088134766, "step": 60720 }, { "epoch": 1.7161201915605973, "grad_norm": 4.0665283203125, "learning_rate": 4.225611152862143e-05, "loss": 0.8905097007751465, "step": 60740 }, { "epoch": 1.716685267068812, "grad_norm": 2.1828715801239014, "learning_rate": 4.222534448397744e-05, "loss": 0.799714469909668, "step": 60760 }, { "epoch": 1.7172503425770267, "grad_norm": 4.562839984893799, "learning_rate": 4.219458045580764e-05, "loss": 0.8380011558532715, "step": 60780 }, { "epoch": 1.7178154180852416, "grad_norm": 3.1428632736206055, "learning_rate": 4.216381945604811e-05, "loss": 0.9194881439208984, "step": 60800 }, { "epoch": 1.7183804935934566, "grad_norm": 3.483675241470337, "learning_rate": 4.213306149663378e-05, "loss": 0.808502197265625, "step": 60820 }, { "epoch": 1.7189455691016713, "grad_norm": 4.781578540802002, "learning_rate": 4.210230658949833e-05, "loss": 0.894537353515625, "step": 60840 }, { "epoch": 1.719510644609886, "grad_norm": 4.458567142486572, "learning_rate": 4.2071554746574324e-05, "loss": 0.9611734390258789, "step": 60860 }, { "epoch": 1.7200757201181007, "grad_norm": 3.4005801677703857, "learning_rate": 4.204080597979311e-05, "loss": 0.8434486389160156, "step": 60880 }, { "epoch": 1.7206407956263154, "grad_norm": 2.5992636680603027, "learning_rate": 4.2010060301084844e-05, "loss": 0.7929048538208008, "step": 60900 }, { "epoch": 1.7212058711345304, "grad_norm": 2.8136446475982666, "learning_rate": 4.197931772237848e-05, "loss": 0.9054289817810058, "step": 60920 }, { "epoch": 1.721770946642745, "grad_norm": 5.7963433265686035, "learning_rate": 4.194857825560179e-05, "loss": 0.8519881248474122, "step": 60940 }, { "epoch": 1.72233602215096, "grad_norm": 3.5614285469055176, "learning_rate": 4.191784191268129e-05, "loss": 0.9030376434326172, "step": 60960 }, { "epoch": 1.7229010976591748, "grad_norm": 3.2500393390655518, "learning_rate": 4.188710870554236e-05, "loss": 0.9024062156677246, "step": 60980 }, { "epoch": 1.7234661731673895, "grad_norm": 3.024898052215576, "learning_rate": 4.1856378646109076e-05, "loss": 0.9316547393798829, "step": 61000 }, { "epoch": 1.7240312486756042, "grad_norm": 4.988564491271973, "learning_rate": 4.182565174630436e-05, "loss": 0.914303207397461, "step": 61020 }, { "epoch": 1.724596324183819, "grad_norm": 4.389753818511963, "learning_rate": 4.17949280180499e-05, "loss": 0.890129566192627, "step": 61040 }, { "epoch": 1.7251613996920339, "grad_norm": 2.848031759262085, "learning_rate": 4.1764207473266115e-05, "loss": 0.8632819175720214, "step": 61060 }, { "epoch": 1.7257264752002488, "grad_norm": 3.468341588973999, "learning_rate": 4.173349012387223e-05, "loss": 0.8301169395446777, "step": 61080 }, { "epoch": 1.7262915507084635, "grad_norm": 2.8439855575561523, "learning_rate": 4.170277598178619e-05, "loss": 0.8111382484436035, "step": 61100 }, { "epoch": 1.7268566262166782, "grad_norm": 3.856980562210083, "learning_rate": 4.1672065058924736e-05, "loss": 0.8235017776489257, "step": 61120 }, { "epoch": 1.727421701724893, "grad_norm": 2.547211170196533, "learning_rate": 4.1641357367203324e-05, "loss": 0.8456556320190429, "step": 61140 }, { "epoch": 1.7279867772331077, "grad_norm": 3.7628493309020996, "learning_rate": 4.161065291853621e-05, "loss": 0.9361031532287598, "step": 61160 }, { "epoch": 1.7285518527413226, "grad_norm": 3.6270248889923096, "learning_rate": 4.157995172483631e-05, "loss": 0.8794817924499512, "step": 61180 }, { "epoch": 1.7291169282495373, "grad_norm": 2.95579195022583, "learning_rate": 4.1549253798015364e-05, "loss": 0.8987853050231933, "step": 61200 }, { "epoch": 1.7296820037577523, "grad_norm": 3.3280231952667236, "learning_rate": 4.151855914998377e-05, "loss": 0.8918146133422852, "step": 61220 }, { "epoch": 1.730247079265967, "grad_norm": 3.091063976287842, "learning_rate": 4.148786779265072e-05, "loss": 0.7964492797851562, "step": 61240 }, { "epoch": 1.7308121547741817, "grad_norm": 4.406815528869629, "learning_rate": 4.145717973792407e-05, "loss": 0.893761157989502, "step": 61260 }, { "epoch": 1.7313772302823964, "grad_norm": 2.754066228866577, "learning_rate": 4.142649499771044e-05, "loss": 0.8892873764038086, "step": 61280 }, { "epoch": 1.7319423057906111, "grad_norm": 4.904123783111572, "learning_rate": 4.139581358391512e-05, "loss": 0.8339224815368652, "step": 61300 }, { "epoch": 1.732507381298826, "grad_norm": 3.2937052249908447, "learning_rate": 4.1365135508442176e-05, "loss": 0.8104979515075683, "step": 61320 }, { "epoch": 1.7330724568070408, "grad_norm": 3.1528565883636475, "learning_rate": 4.133446078319428e-05, "loss": 0.8618332862854003, "step": 61340 }, { "epoch": 1.7336375323152557, "grad_norm": 3.846034526824951, "learning_rate": 4.130378942007292e-05, "loss": 0.8578805923461914, "step": 61360 }, { "epoch": 1.7342026078234705, "grad_norm": 3.6017491817474365, "learning_rate": 4.1273121430978204e-05, "loss": 0.8866156578063965, "step": 61380 }, { "epoch": 1.7347676833316852, "grad_norm": 3.755816698074341, "learning_rate": 4.124245682780892e-05, "loss": 0.8122767448425293, "step": 61400 }, { "epoch": 1.7353327588399, "grad_norm": 3.545302152633667, "learning_rate": 4.121179562246261e-05, "loss": 0.84990234375, "step": 61420 }, { "epoch": 1.7358978343481146, "grad_norm": 3.0065298080444336, "learning_rate": 4.118113782683544e-05, "loss": 0.8623332023620606, "step": 61440 }, { "epoch": 1.7364629098563296, "grad_norm": 2.6160712242126465, "learning_rate": 4.115048345282226e-05, "loss": 0.8305213928222657, "step": 61460 }, { "epoch": 1.7370279853645445, "grad_norm": 3.8203859329223633, "learning_rate": 4.111983251231663e-05, "loss": 0.85814208984375, "step": 61480 }, { "epoch": 1.7375930608727592, "grad_norm": 3.1414105892181396, "learning_rate": 4.1089185017210725e-05, "loss": 0.8417094230651856, "step": 61500 }, { "epoch": 1.738158136380974, "grad_norm": 4.238119602203369, "learning_rate": 4.1058540979395434e-05, "loss": 0.8112228393554688, "step": 61520 }, { "epoch": 1.7387232118891887, "grad_norm": 3.8915412425994873, "learning_rate": 4.102790041076025e-05, "loss": 0.8360028266906738, "step": 61540 }, { "epoch": 1.7392882873974034, "grad_norm": 3.620774030685425, "learning_rate": 4.09972633231934e-05, "loss": 0.859956932067871, "step": 61560 }, { "epoch": 1.7398533629056183, "grad_norm": 4.418526649475098, "learning_rate": 4.096662972858165e-05, "loss": 0.827543830871582, "step": 61580 }, { "epoch": 1.740418438413833, "grad_norm": 4.137866020202637, "learning_rate": 4.0935999638810524e-05, "loss": 0.8961859703063965, "step": 61600 }, { "epoch": 1.740983513922048, "grad_norm": 4.543445587158203, "learning_rate": 4.0905373065764095e-05, "loss": 0.8281467437744141, "step": 61620 }, { "epoch": 1.7415485894302627, "grad_norm": 3.5318145751953125, "learning_rate": 4.087475002132514e-05, "loss": 0.8629885673522949, "step": 61640 }, { "epoch": 1.7421136649384774, "grad_norm": 4.194007873535156, "learning_rate": 4.0844130517375e-05, "loss": 0.8698214530944824, "step": 61660 }, { "epoch": 1.7426787404466921, "grad_norm": 5.532631874084473, "learning_rate": 4.081351456579371e-05, "loss": 0.8404345512390137, "step": 61680 }, { "epoch": 1.7432438159549069, "grad_norm": 3.474909543991089, "learning_rate": 4.0782902178459906e-05, "loss": 0.8365635871887207, "step": 61700 }, { "epoch": 1.7438088914631218, "grad_norm": 4.393076419830322, "learning_rate": 4.075229336725081e-05, "loss": 0.7792525291442871, "step": 61720 }, { "epoch": 1.7443739669713365, "grad_norm": 3.755260705947876, "learning_rate": 4.072168814404229e-05, "loss": 0.8378668785095215, "step": 61740 }, { "epoch": 1.7449390424795514, "grad_norm": 3.6545281410217285, "learning_rate": 4.069108652070879e-05, "loss": 0.9120203018188476, "step": 61760 }, { "epoch": 1.7455041179877662, "grad_norm": 4.275881290435791, "learning_rate": 4.0660488509123405e-05, "loss": 0.8810766220092774, "step": 61780 }, { "epoch": 1.7460691934959809, "grad_norm": 3.4361069202423096, "learning_rate": 4.0629894121157776e-05, "loss": 0.9120259284973145, "step": 61800 }, { "epoch": 1.7466342690041956, "grad_norm": 3.370460271835327, "learning_rate": 4.059930336868218e-05, "loss": 0.8589970588684082, "step": 61820 }, { "epoch": 1.7471993445124103, "grad_norm": 4.14451265335083, "learning_rate": 4.056871626356545e-05, "loss": 0.8574928283691406, "step": 61840 }, { "epoch": 1.7477644200206253, "grad_norm": 3.147231340408325, "learning_rate": 4.053813281767505e-05, "loss": 0.8766193389892578, "step": 61860 }, { "epoch": 1.7483294955288402, "grad_norm": 3.5880463123321533, "learning_rate": 4.0507553042876946e-05, "loss": 0.8312360763549804, "step": 61880 }, { "epoch": 1.748894571037055, "grad_norm": 2.8771426677703857, "learning_rate": 4.047697695103578e-05, "loss": 0.8461551666259766, "step": 61900 }, { "epoch": 1.7494596465452696, "grad_norm": 2.3171494007110596, "learning_rate": 4.044640455401467e-05, "loss": 0.8752084732055664, "step": 61920 }, { "epoch": 1.7500247220534844, "grad_norm": 3.533705472946167, "learning_rate": 4.0415835863675385e-05, "loss": 0.850072193145752, "step": 61940 }, { "epoch": 1.750589797561699, "grad_norm": 3.7397968769073486, "learning_rate": 4.038527089187818e-05, "loss": 0.8672079086303711, "step": 61960 }, { "epoch": 1.751154873069914, "grad_norm": 3.55625057220459, "learning_rate": 4.035470965048192e-05, "loss": 0.7907018184661865, "step": 61980 }, { "epoch": 1.7517199485781287, "grad_norm": 3.042956590652466, "learning_rate": 4.032415215134398e-05, "loss": 0.8608420372009278, "step": 62000 }, { "epoch": 1.7522850240863437, "grad_norm": 3.512146234512329, "learning_rate": 4.029359840632034e-05, "loss": 0.8082833290100098, "step": 62020 }, { "epoch": 1.7528500995945584, "grad_norm": 3.7182276248931885, "learning_rate": 4.026304842726549e-05, "loss": 0.8516898155212402, "step": 62040 }, { "epoch": 1.7534151751027731, "grad_norm": 3.563690662384033, "learning_rate": 4.023250222603244e-05, "loss": 0.833063793182373, "step": 62060 }, { "epoch": 1.7539802506109878, "grad_norm": 3.473925828933716, "learning_rate": 4.0201959814472764e-05, "loss": 0.8913681030273437, "step": 62080 }, { "epoch": 1.7545453261192026, "grad_norm": 3.428706407546997, "learning_rate": 4.017142120443654e-05, "loss": 0.8482893943786621, "step": 62100 }, { "epoch": 1.7551104016274175, "grad_norm": 4.0085930824279785, "learning_rate": 4.014088640777241e-05, "loss": 0.9004173278808594, "step": 62120 }, { "epoch": 1.7556754771356322, "grad_norm": 3.9059712886810303, "learning_rate": 4.011035543632751e-05, "loss": 0.9612983703613281, "step": 62140 }, { "epoch": 1.7562405526438472, "grad_norm": 3.7425436973571777, "learning_rate": 4.007982830194748e-05, "loss": 0.8092442512512207, "step": 62160 }, { "epoch": 1.7568056281520619, "grad_norm": 4.677156925201416, "learning_rate": 4.00493050164765e-05, "loss": 0.9199151039123535, "step": 62180 }, { "epoch": 1.7573707036602766, "grad_norm": 2.6000003814697266, "learning_rate": 4.001878559175724e-05, "loss": 0.8322249412536621, "step": 62200 }, { "epoch": 1.7579357791684913, "grad_norm": 4.205567359924316, "learning_rate": 3.998827003963087e-05, "loss": 0.8138960838317871, "step": 62220 }, { "epoch": 1.758500854676706, "grad_norm": 3.1997551918029785, "learning_rate": 3.995775837193706e-05, "loss": 0.8929213523864746, "step": 62240 }, { "epoch": 1.759065930184921, "grad_norm": 2.781141757965088, "learning_rate": 3.9927250600513986e-05, "loss": 0.8591977119445801, "step": 62260 }, { "epoch": 1.759631005693136, "grad_norm": 4.016928672790527, "learning_rate": 3.989674673719829e-05, "loss": 0.9346186637878418, "step": 62280 }, { "epoch": 1.7601960812013506, "grad_norm": 3.3278958797454834, "learning_rate": 3.986624679382513e-05, "loss": 0.8858322143554688, "step": 62300 }, { "epoch": 1.7607611567095653, "grad_norm": 2.8939759731292725, "learning_rate": 3.983575078222808e-05, "loss": 0.8109978675842285, "step": 62320 }, { "epoch": 1.76132623221778, "grad_norm": 4.053965091705322, "learning_rate": 3.980525871423928e-05, "loss": 0.8324026107788086, "step": 62340 }, { "epoch": 1.7618913077259948, "grad_norm": 3.5247321128845215, "learning_rate": 3.977477060168927e-05, "loss": 0.8756969451904297, "step": 62360 }, { "epoch": 1.7624563832342097, "grad_norm": 3.920654535293579, "learning_rate": 3.9744286456407075e-05, "loss": 0.7902242183685303, "step": 62380 }, { "epoch": 1.7630214587424244, "grad_norm": 3.2264809608459473, "learning_rate": 3.971380629022019e-05, "loss": 0.7689641952514649, "step": 62400 }, { "epoch": 1.7635865342506394, "grad_norm": 3.026817560195923, "learning_rate": 3.968333011495454e-05, "loss": 0.8056666374206543, "step": 62420 }, { "epoch": 1.764151609758854, "grad_norm": 3.5764694213867188, "learning_rate": 3.965285794243455e-05, "loss": 0.8401043891906739, "step": 62440 }, { "epoch": 1.7647166852670688, "grad_norm": 3.4195375442504883, "learning_rate": 3.9622389784483025e-05, "loss": 0.9488170623779297, "step": 62460 }, { "epoch": 1.7652817607752835, "grad_norm": 2.8516342639923096, "learning_rate": 3.959192565292129e-05, "loss": 0.8476188659667969, "step": 62480 }, { "epoch": 1.7658468362834983, "grad_norm": 3.8257675170898438, "learning_rate": 3.956146555956902e-05, "loss": 0.8223983764648437, "step": 62500 }, { "epoch": 1.7664119117917132, "grad_norm": 3.012516498565674, "learning_rate": 3.953100951624442e-05, "loss": 0.7901577472686767, "step": 62520 }, { "epoch": 1.766976987299928, "grad_norm": 2.5951693058013916, "learning_rate": 3.950055753476403e-05, "loss": 0.9357751846313477, "step": 62540 }, { "epoch": 1.7675420628081429, "grad_norm": 3.637331008911133, "learning_rate": 3.9470109626942886e-05, "loss": 0.8313035011291504, "step": 62560 }, { "epoch": 1.7681071383163576, "grad_norm": 3.346571922302246, "learning_rate": 3.94396658045944e-05, "loss": 0.8607031822204589, "step": 62580 }, { "epoch": 1.7686722138245723, "grad_norm": 3.8244261741638184, "learning_rate": 3.940922607953043e-05, "loss": 0.8609114646911621, "step": 62600 }, { "epoch": 1.769237289332787, "grad_norm": 4.35237455368042, "learning_rate": 3.937879046356121e-05, "loss": 0.8213590621948242, "step": 62620 }, { "epoch": 1.7698023648410017, "grad_norm": 2.8848705291748047, "learning_rate": 3.9348358968495415e-05, "loss": 0.819212532043457, "step": 62640 }, { "epoch": 1.7703674403492167, "grad_norm": 3.987056016921997, "learning_rate": 3.9317931606140074e-05, "loss": 0.8634170532226563, "step": 62660 }, { "epoch": 1.7709325158574316, "grad_norm": 3.505951404571533, "learning_rate": 3.928750838830068e-05, "loss": 0.9257691383361817, "step": 62680 }, { "epoch": 1.7714975913656463, "grad_norm": 3.920518159866333, "learning_rate": 3.925708932678108e-05, "loss": 0.8059439659118652, "step": 62700 }, { "epoch": 1.772062666873861, "grad_norm": 4.216236591339111, "learning_rate": 3.922667443338348e-05, "loss": 0.9071889877319336, "step": 62720 }, { "epoch": 1.7726277423820758, "grad_norm": 2.753225803375244, "learning_rate": 3.919626371990852e-05, "loss": 0.8873573303222656, "step": 62740 }, { "epoch": 1.7731928178902905, "grad_norm": 3.090075731277466, "learning_rate": 3.916585719815519e-05, "loss": 0.8799432754516602, "step": 62760 }, { "epoch": 1.7737578933985054, "grad_norm": 3.1857240200042725, "learning_rate": 3.913545487992086e-05, "loss": 0.8896809577941894, "step": 62780 }, { "epoch": 1.7743229689067201, "grad_norm": 4.418063640594482, "learning_rate": 3.910505677700128e-05, "loss": 0.8469503402709961, "step": 62800 }, { "epoch": 1.774888044414935, "grad_norm": 4.542629718780518, "learning_rate": 3.907466290119053e-05, "loss": 0.86477632522583, "step": 62820 }, { "epoch": 1.7754531199231498, "grad_norm": 2.095151424407959, "learning_rate": 3.90442732642811e-05, "loss": 0.8887469291687011, "step": 62840 }, { "epoch": 1.7760181954313645, "grad_norm": 2.351442337036133, "learning_rate": 3.9013887878063776e-05, "loss": 0.8984481811523437, "step": 62860 }, { "epoch": 1.7765832709395792, "grad_norm": 3.9740588665008545, "learning_rate": 3.8983506754327766e-05, "loss": 0.862792682647705, "step": 62880 }, { "epoch": 1.777148346447794, "grad_norm": 5.271975517272949, "learning_rate": 3.8953129904860555e-05, "loss": 0.8172812461853027, "step": 62900 }, { "epoch": 1.777713421956009, "grad_norm": 3.3546602725982666, "learning_rate": 3.892275734144802e-05, "loss": 0.8327548027038574, "step": 62920 }, { "epoch": 1.7782784974642236, "grad_norm": 3.362168788909912, "learning_rate": 3.8892389075874356e-05, "loss": 0.838775634765625, "step": 62940 }, { "epoch": 1.7788435729724386, "grad_norm": 2.67267107963562, "learning_rate": 3.8862025119922074e-05, "loss": 0.8338582992553711, "step": 62960 }, { "epoch": 1.7794086484806533, "grad_norm": 3.187164068222046, "learning_rate": 3.8831665485372024e-05, "loss": 0.8820333480834961, "step": 62980 }, { "epoch": 1.779973723988868, "grad_norm": 4.032535076141357, "learning_rate": 3.880131018400341e-05, "loss": 0.8754663467407227, "step": 63000 }, { "epoch": 1.7805387994970827, "grad_norm": 3.659752130508423, "learning_rate": 3.877095922759373e-05, "loss": 0.8237470626831055, "step": 63020 }, { "epoch": 1.7811038750052974, "grad_norm": 3.5349926948547363, "learning_rate": 3.8740612627918764e-05, "loss": 0.8864712715148926, "step": 63040 }, { "epoch": 1.7816689505135124, "grad_norm": 3.2818050384521484, "learning_rate": 3.871027039675267e-05, "loss": 0.9125813484191895, "step": 63060 }, { "epoch": 1.7822340260217273, "grad_norm": 2.460209369659424, "learning_rate": 3.8679932545867845e-05, "loss": 0.8987258911132813, "step": 63080 }, { "epoch": 1.782799101529942, "grad_norm": 3.2410178184509277, "learning_rate": 3.8649599087035035e-05, "loss": 0.7984802722930908, "step": 63100 }, { "epoch": 1.7833641770381568, "grad_norm": 2.2599236965179443, "learning_rate": 3.861927003202324e-05, "loss": 0.9147424697875977, "step": 63120 }, { "epoch": 1.7839292525463715, "grad_norm": 4.307438850402832, "learning_rate": 3.858894539259981e-05, "loss": 0.8916177749633789, "step": 63140 }, { "epoch": 1.7844943280545862, "grad_norm": 2.523035764694214, "learning_rate": 3.85586251805303e-05, "loss": 0.7981860637664795, "step": 63160 }, { "epoch": 1.7850594035628011, "grad_norm": 5.118955612182617, "learning_rate": 3.8528309407578634e-05, "loss": 0.9300802230834961, "step": 63180 }, { "epoch": 1.7856244790710158, "grad_norm": 3.267314910888672, "learning_rate": 3.8497998085506944e-05, "loss": 0.9003190040588379, "step": 63200 }, { "epoch": 1.7861895545792308, "grad_norm": 2.3224010467529297, "learning_rate": 3.846769122607568e-05, "loss": 0.8537353515625, "step": 63220 }, { "epoch": 1.7867546300874455, "grad_norm": 3.42999005317688, "learning_rate": 3.8437388841043536e-05, "loss": 0.8127226829528809, "step": 63240 }, { "epoch": 1.7873197055956602, "grad_norm": 3.080019474029541, "learning_rate": 3.840709094216749e-05, "loss": 0.8569021224975586, "step": 63260 }, { "epoch": 1.787884781103875, "grad_norm": 3.6901662349700928, "learning_rate": 3.837679754120275e-05, "loss": 0.8389816284179688, "step": 63280 }, { "epoch": 1.7884498566120897, "grad_norm": 3.027003765106201, "learning_rate": 3.834650864990281e-05, "loss": 0.8385743141174317, "step": 63300 }, { "epoch": 1.7890149321203046, "grad_norm": 3.168074607849121, "learning_rate": 3.831622428001937e-05, "loss": 0.8414340019226074, "step": 63320 }, { "epoch": 1.7895800076285193, "grad_norm": 3.1372416019439697, "learning_rate": 3.828594444330246e-05, "loss": 0.8333102226257324, "step": 63340 }, { "epoch": 1.7901450831367343, "grad_norm": 3.752612829208374, "learning_rate": 3.8255669151500275e-05, "loss": 0.8886789321899414, "step": 63360 }, { "epoch": 1.790710158644949, "grad_norm": 2.2965760231018066, "learning_rate": 3.822539841635925e-05, "loss": 0.8580530166625977, "step": 63380 }, { "epoch": 1.7912752341531637, "grad_norm": 4.5674357414245605, "learning_rate": 3.81951322496241e-05, "loss": 0.8325008392333985, "step": 63400 }, { "epoch": 1.7918403096613784, "grad_norm": 3.4286205768585205, "learning_rate": 3.816487066303772e-05, "loss": 0.8946798324584961, "step": 63420 }, { "epoch": 1.7924053851695931, "grad_norm": 3.4616758823394775, "learning_rate": 3.813461366834126e-05, "loss": 0.7935647964477539, "step": 63440 }, { "epoch": 1.792970460677808, "grad_norm": 2.7286298274993896, "learning_rate": 3.8104361277274054e-05, "loss": 0.7986112594604492, "step": 63460 }, { "epoch": 1.793535536186023, "grad_norm": 3.442655086517334, "learning_rate": 3.807411350157369e-05, "loss": 0.847136116027832, "step": 63480 }, { "epoch": 1.7941006116942377, "grad_norm": 3.1427536010742188, "learning_rate": 3.8043870352975944e-05, "loss": 0.9506465911865234, "step": 63500 }, { "epoch": 1.7946656872024525, "grad_norm": 2.9382548332214355, "learning_rate": 3.801363184321479e-05, "loss": 0.7764491081237793, "step": 63520 }, { "epoch": 1.7952307627106672, "grad_norm": 3.648387908935547, "learning_rate": 3.798339798402243e-05, "loss": 0.8387417793273926, "step": 63540 }, { "epoch": 1.795795838218882, "grad_norm": 4.0410027503967285, "learning_rate": 3.7953168787129226e-05, "loss": 0.874632740020752, "step": 63560 }, { "epoch": 1.7963609137270968, "grad_norm": 3.5099644660949707, "learning_rate": 3.792294426426376e-05, "loss": 0.8057015419006348, "step": 63580 }, { "epoch": 1.7969259892353115, "grad_norm": 4.556948661804199, "learning_rate": 3.789272442715277e-05, "loss": 0.8049711227416992, "step": 63600 }, { "epoch": 1.7974910647435265, "grad_norm": 2.892045259475708, "learning_rate": 3.786250928752122e-05, "loss": 0.7980139255523682, "step": 63620 }, { "epoch": 1.7980561402517412, "grad_norm": 4.020461082458496, "learning_rate": 3.783229885709218e-05, "loss": 0.8370772361755371, "step": 63640 }, { "epoch": 1.798621215759956, "grad_norm": 3.73470139503479, "learning_rate": 3.7802093147586996e-05, "loss": 0.8460614204406738, "step": 63660 }, { "epoch": 1.7991862912681706, "grad_norm": 3.804534435272217, "learning_rate": 3.777189217072511e-05, "loss": 0.8809258460998535, "step": 63680 }, { "epoch": 1.7997513667763854, "grad_norm": 3.50201416015625, "learning_rate": 3.774169593822412e-05, "loss": 0.8965141296386718, "step": 63700 }, { "epoch": 1.8003164422846003, "grad_norm": 3.8827028274536133, "learning_rate": 3.771150446179983e-05, "loss": 0.839355182647705, "step": 63720 }, { "epoch": 1.800881517792815, "grad_norm": 3.6402904987335205, "learning_rate": 3.768131775316616e-05, "loss": 0.8656179428100585, "step": 63740 }, { "epoch": 1.80144659330103, "grad_norm": 5.376563549041748, "learning_rate": 3.76511358240352e-05, "loss": 0.8931944847106934, "step": 63760 }, { "epoch": 1.8020116688092447, "grad_norm": 2.6094460487365723, "learning_rate": 3.762095868611718e-05, "loss": 0.8216567039489746, "step": 63780 }, { "epoch": 1.8025767443174594, "grad_norm": 3.263645648956299, "learning_rate": 3.759078635112048e-05, "loss": 0.7966292381286622, "step": 63800 }, { "epoch": 1.8031418198256741, "grad_norm": 3.0702333450317383, "learning_rate": 3.7560618830751595e-05, "loss": 0.8163496017456054, "step": 63820 }, { "epoch": 1.8037068953338888, "grad_norm": 3.2609386444091797, "learning_rate": 3.753045613671517e-05, "loss": 0.8381487846374511, "step": 63840 }, { "epoch": 1.8042719708421038, "grad_norm": 3.9777708053588867, "learning_rate": 3.750029828071398e-05, "loss": 0.8555446624755859, "step": 63860 }, { "epoch": 1.8048370463503187, "grad_norm": 2.7176990509033203, "learning_rate": 3.7470145274448916e-05, "loss": 0.8859663963317871, "step": 63880 }, { "epoch": 1.8054021218585334, "grad_norm": 2.714451313018799, "learning_rate": 3.7439997129618964e-05, "loss": 0.8372721672058105, "step": 63900 }, { "epoch": 1.8059671973667482, "grad_norm": 3.196122169494629, "learning_rate": 3.7409853857921285e-05, "loss": 0.7823999881744385, "step": 63920 }, { "epoch": 1.8065322728749629, "grad_norm": 4.597112655639648, "learning_rate": 3.737971547105107e-05, "loss": 0.8706559181213379, "step": 63940 }, { "epoch": 1.8070973483831776, "grad_norm": 4.043209552764893, "learning_rate": 3.73495819807017e-05, "loss": 0.8647319793701171, "step": 63960 }, { "epoch": 1.8076624238913925, "grad_norm": 2.6992950439453125, "learning_rate": 3.7319453398564556e-05, "loss": 0.7992334842681885, "step": 63980 }, { "epoch": 1.8082274993996073, "grad_norm": 3.6558542251586914, "learning_rate": 3.728932973632921e-05, "loss": 0.7634235382080078, "step": 64000 }, { "epoch": 1.8087925749078222, "grad_norm": 4.708037376403809, "learning_rate": 3.72592110056833e-05, "loss": 0.8933769226074219, "step": 64020 }, { "epoch": 1.809357650416037, "grad_norm": 3.3587162494659424, "learning_rate": 3.72290972183125e-05, "loss": 0.8132997512817383, "step": 64040 }, { "epoch": 1.8099227259242516, "grad_norm": 2.9483566284179688, "learning_rate": 3.7198988385900636e-05, "loss": 0.8384006500244141, "step": 64060 }, { "epoch": 1.8104878014324663, "grad_norm": 2.8439297676086426, "learning_rate": 3.7168884520129545e-05, "loss": 0.888037109375, "step": 64080 }, { "epoch": 1.811052876940681, "grad_norm": 4.265848636627197, "learning_rate": 3.7138785632679195e-05, "loss": 0.9070199012756348, "step": 64100 }, { "epoch": 1.811617952448896, "grad_norm": 3.8492624759674072, "learning_rate": 3.710869173522759e-05, "loss": 0.7868821144104003, "step": 64120 }, { "epoch": 1.8121830279571107, "grad_norm": 3.8357009887695312, "learning_rate": 3.7078602839450796e-05, "loss": 0.8123347282409668, "step": 64140 }, { "epoch": 1.8127481034653257, "grad_norm": 4.442394256591797, "learning_rate": 3.7048518957022946e-05, "loss": 0.8696711540222168, "step": 64160 }, { "epoch": 1.8133131789735404, "grad_norm": 2.997330665588379, "learning_rate": 3.7018440099616245e-05, "loss": 0.933087158203125, "step": 64180 }, { "epoch": 1.813878254481755, "grad_norm": 3.4803991317749023, "learning_rate": 3.6988366278900946e-05, "loss": 0.8732217788696289, "step": 64200 }, { "epoch": 1.8144433299899698, "grad_norm": 3.6095669269561768, "learning_rate": 3.69582975065453e-05, "loss": 0.7941482067108154, "step": 64220 }, { "epoch": 1.8150084054981845, "grad_norm": 5.187275409698486, "learning_rate": 3.692823379421566e-05, "loss": 0.8490430831909179, "step": 64240 }, { "epoch": 1.8155734810063995, "grad_norm": 4.259722709655762, "learning_rate": 3.689817515357637e-05, "loss": 0.9078254699707031, "step": 64260 }, { "epoch": 1.8161385565146144, "grad_norm": 3.1678500175476074, "learning_rate": 3.6868121596289854e-05, "loss": 0.8494122505187989, "step": 64280 }, { "epoch": 1.8167036320228291, "grad_norm": 3.63828706741333, "learning_rate": 3.6838073134016484e-05, "loss": 0.8193518638610839, "step": 64300 }, { "epoch": 1.8172687075310439, "grad_norm": 4.139860153198242, "learning_rate": 3.6808029778414764e-05, "loss": 0.831143569946289, "step": 64320 }, { "epoch": 1.8178337830392586, "grad_norm": 3.7812118530273438, "learning_rate": 3.677799154114114e-05, "loss": 0.8781316757202149, "step": 64340 }, { "epoch": 1.8183988585474733, "grad_norm": 4.257019996643066, "learning_rate": 3.674795843385009e-05, "loss": 0.7236040115356446, "step": 64360 }, { "epoch": 1.8189639340556882, "grad_norm": 3.028083562850952, "learning_rate": 3.671793046819412e-05, "loss": 0.8280239105224609, "step": 64380 }, { "epoch": 1.819529009563903, "grad_norm": 2.113673686981201, "learning_rate": 3.6687907655823686e-05, "loss": 0.936985969543457, "step": 64400 }, { "epoch": 1.820094085072118, "grad_norm": 3.386936902999878, "learning_rate": 3.665789000838732e-05, "loss": 0.89846830368042, "step": 64420 }, { "epoch": 1.8206591605803326, "grad_norm": 4.656060695648193, "learning_rate": 3.662787753753149e-05, "loss": 0.8399011611938476, "step": 64440 }, { "epoch": 1.8212242360885473, "grad_norm": 4.364652156829834, "learning_rate": 3.65978702549007e-05, "loss": 0.8549094200134277, "step": 64460 }, { "epoch": 1.821789311596762, "grad_norm": 3.1111350059509277, "learning_rate": 3.6567868172137395e-05, "loss": 0.8554928779602051, "step": 64480 }, { "epoch": 1.8223543871049768, "grad_norm": 3.251863479614258, "learning_rate": 3.6537871300882056e-05, "loss": 0.8263132095336914, "step": 64500 }, { "epoch": 1.8229194626131917, "grad_norm": 4.434566020965576, "learning_rate": 3.650787965277309e-05, "loss": 0.8529376029968262, "step": 64520 }, { "epoch": 1.8234845381214064, "grad_norm": 4.334110260009766, "learning_rate": 3.6477893239446917e-05, "loss": 0.9512231826782227, "step": 64540 }, { "epoch": 1.8240496136296214, "grad_norm": 4.2220001220703125, "learning_rate": 3.6447912072537896e-05, "loss": 0.8681698799133301, "step": 64560 }, { "epoch": 1.824614689137836, "grad_norm": 3.0006942749023438, "learning_rate": 3.641793616367838e-05, "loss": 0.7966197490692138, "step": 64580 }, { "epoch": 1.8251797646460508, "grad_norm": 2.9744579792022705, "learning_rate": 3.6387965524498646e-05, "loss": 0.853785514831543, "step": 64600 }, { "epoch": 1.8257448401542655, "grad_norm": 5.14345645904541, "learning_rate": 3.6358000166626966e-05, "loss": 0.8280275344848633, "step": 64620 }, { "epoch": 1.8263099156624802, "grad_norm": 2.5494213104248047, "learning_rate": 3.632804010168952e-05, "loss": 0.7939864158630371, "step": 64640 }, { "epoch": 1.8268749911706952, "grad_norm": 3.675201416015625, "learning_rate": 3.6298085341310486e-05, "loss": 0.8886420249938964, "step": 64660 }, { "epoch": 1.8274400666789101, "grad_norm": 3.218771457672119, "learning_rate": 3.626813589711194e-05, "loss": 0.8125035285949707, "step": 64680 }, { "epoch": 1.8280051421871248, "grad_norm": 4.392259120941162, "learning_rate": 3.6238191780713923e-05, "loss": 0.9039138793945313, "step": 64700 }, { "epoch": 1.8285702176953396, "grad_norm": 3.008200168609619, "learning_rate": 3.6208253003734394e-05, "loss": 0.8496155738830566, "step": 64720 }, { "epoch": 1.8291352932035543, "grad_norm": 3.549961805343628, "learning_rate": 3.6178319577789225e-05, "loss": 0.9414108276367188, "step": 64740 }, { "epoch": 1.829700368711769, "grad_norm": 4.337545871734619, "learning_rate": 3.614839151449226e-05, "loss": 0.8778736114501953, "step": 64760 }, { "epoch": 1.830265444219984, "grad_norm": 2.630842685699463, "learning_rate": 3.611846882545521e-05, "loss": 0.8060840606689453, "step": 64780 }, { "epoch": 1.8308305197281987, "grad_norm": 2.627586841583252, "learning_rate": 3.608855152228774e-05, "loss": 0.8649720191955567, "step": 64800 }, { "epoch": 1.8313955952364136, "grad_norm": 4.143579006195068, "learning_rate": 3.6058639616597384e-05, "loss": 0.8128489494323731, "step": 64820 }, { "epoch": 1.8319606707446283, "grad_norm": 4.249096870422363, "learning_rate": 3.602873311998963e-05, "loss": 0.8297677993774414, "step": 64840 }, { "epoch": 1.832525746252843, "grad_norm": 4.6282148361206055, "learning_rate": 3.5998832044067844e-05, "loss": 0.8863738059997559, "step": 64860 }, { "epoch": 1.8330908217610578, "grad_norm": 4.310213565826416, "learning_rate": 3.596893640043327e-05, "loss": 0.8465056419372559, "step": 64880 }, { "epoch": 1.8336558972692725, "grad_norm": 3.4760141372680664, "learning_rate": 3.59390462006851e-05, "loss": 0.8945977210998535, "step": 64900 }, { "epoch": 1.8342209727774874, "grad_norm": 2.9789743423461914, "learning_rate": 3.5909161456420334e-05, "loss": 0.8794346809387207, "step": 64920 }, { "epoch": 1.8347860482857021, "grad_norm": 3.6751983165740967, "learning_rate": 3.5879282179233925e-05, "loss": 0.9042997360229492, "step": 64940 }, { "epoch": 1.835351123793917, "grad_norm": 3.979483127593994, "learning_rate": 3.5849408380718655e-05, "loss": 0.8360645294189453, "step": 64960 }, { "epoch": 1.8359161993021318, "grad_norm": 2.62827205657959, "learning_rate": 3.581954007246523e-05, "loss": 0.8178543090820313, "step": 64980 }, { "epoch": 1.8364812748103465, "grad_norm": 5.05656099319458, "learning_rate": 3.57896772660622e-05, "loss": 0.8346542358398438, "step": 65000 }, { "epoch": 1.8370463503185612, "grad_norm": 2.743671178817749, "learning_rate": 3.575981997309596e-05, "loss": 0.7939407348632812, "step": 65020 }, { "epoch": 1.837611425826776, "grad_norm": 3.1336629390716553, "learning_rate": 3.57299682051508e-05, "loss": 0.9071642875671386, "step": 65040 }, { "epoch": 1.8381765013349909, "grad_norm": 3.337808132171631, "learning_rate": 3.570012197380885e-05, "loss": 0.8752437591552734, "step": 65060 }, { "epoch": 1.8387415768432058, "grad_norm": 2.9367411136627197, "learning_rate": 3.567028129065009e-05, "loss": 0.7550147533416748, "step": 65080 }, { "epoch": 1.8393066523514205, "grad_norm": 3.0214004516601562, "learning_rate": 3.564044616725235e-05, "loss": 0.8187725067138671, "step": 65100 }, { "epoch": 1.8398717278596353, "grad_norm": 3.033843755722046, "learning_rate": 3.561061661519132e-05, "loss": 0.8734933853149414, "step": 65120 }, { "epoch": 1.84043680336785, "grad_norm": 4.085078716278076, "learning_rate": 3.558079264604049e-05, "loss": 0.892152976989746, "step": 65140 }, { "epoch": 1.8410018788760647, "grad_norm": 3.649890899658203, "learning_rate": 3.555097427137121e-05, "loss": 0.787691593170166, "step": 65160 }, { "epoch": 1.8415669543842796, "grad_norm": 3.083587884902954, "learning_rate": 3.552116150275267e-05, "loss": 0.8816815376281738, "step": 65180 }, { "epoch": 1.8421320298924944, "grad_norm": 3.365280866622925, "learning_rate": 3.549135435175186e-05, "loss": 0.9111181259155273, "step": 65200 }, { "epoch": 1.8426971054007093, "grad_norm": 4.021494388580322, "learning_rate": 3.546155282993361e-05, "loss": 0.9065479278564453, "step": 65220 }, { "epoch": 1.843262180908924, "grad_norm": 3.4179165363311768, "learning_rate": 3.543175694886055e-05, "loss": 0.9117271423339843, "step": 65240 }, { "epoch": 1.8438272564171387, "grad_norm": 4.264194488525391, "learning_rate": 3.5401966720093125e-05, "loss": 0.8880901336669922, "step": 65260 }, { "epoch": 1.8443923319253535, "grad_norm": 4.570460796356201, "learning_rate": 3.5372182155189606e-05, "loss": 0.9325912475585938, "step": 65280 }, { "epoch": 1.8449574074335682, "grad_norm": 2.524549722671509, "learning_rate": 3.534240326570603e-05, "loss": 0.7999899864196778, "step": 65300 }, { "epoch": 1.8455224829417831, "grad_norm": 4.707256317138672, "learning_rate": 3.531263006319626e-05, "loss": 0.8563831329345704, "step": 65320 }, { "epoch": 1.8460875584499978, "grad_norm": 2.076871156692505, "learning_rate": 3.528286255921197e-05, "loss": 0.8970622062683106, "step": 65340 }, { "epoch": 1.8466526339582128, "grad_norm": 3.161740779876709, "learning_rate": 3.5253100765302565e-05, "loss": 0.8388425827026367, "step": 65360 }, { "epoch": 1.8472177094664275, "grad_norm": 5.003326416015625, "learning_rate": 3.52233446930153e-05, "loss": 0.8254639625549316, "step": 65380 }, { "epoch": 1.8477827849746422, "grad_norm": 3.2583651542663574, "learning_rate": 3.519359435389514e-05, "loss": 0.8515897750854492, "step": 65400 }, { "epoch": 1.848347860482857, "grad_norm": 3.9238879680633545, "learning_rate": 3.51638497594849e-05, "loss": 0.850075626373291, "step": 65420 }, { "epoch": 1.8489129359910716, "grad_norm": 2.8713324069976807, "learning_rate": 3.513411092132511e-05, "loss": 0.8388484954833985, "step": 65440 }, { "epoch": 1.8494780114992866, "grad_norm": 4.515575885772705, "learning_rate": 3.510437785095409e-05, "loss": 0.823956298828125, "step": 65460 }, { "epoch": 1.8500430870075015, "grad_norm": 3.87416934967041, "learning_rate": 3.5074650559907916e-05, "loss": 0.8440437316894531, "step": 65480 }, { "epoch": 1.8506081625157162, "grad_norm": 3.8969664573669434, "learning_rate": 3.5044929059720444e-05, "loss": 0.7511775970458985, "step": 65500 }, { "epoch": 1.851173238023931, "grad_norm": 4.8727827072143555, "learning_rate": 3.501521336192324e-05, "loss": 0.7872442245483399, "step": 65520 }, { "epoch": 1.8517383135321457, "grad_norm": 5.918417930603027, "learning_rate": 3.498550347804564e-05, "loss": 0.8127568244934082, "step": 65540 }, { "epoch": 1.8523033890403604, "grad_norm": 4.366297721862793, "learning_rate": 3.495579941961477e-05, "loss": 0.7941176414489746, "step": 65560 }, { "epoch": 1.8528684645485753, "grad_norm": 2.5150868892669678, "learning_rate": 3.492610119815539e-05, "loss": 0.7726879119873047, "step": 65580 }, { "epoch": 1.85343354005679, "grad_norm": 3.713834524154663, "learning_rate": 3.489640882519011e-05, "loss": 0.923063087463379, "step": 65600 }, { "epoch": 1.853998615565005, "grad_norm": 4.272360801696777, "learning_rate": 3.486672231223916e-05, "loss": 0.8140745162963867, "step": 65620 }, { "epoch": 1.8545636910732197, "grad_norm": 3.0752053260803223, "learning_rate": 3.483704167082062e-05, "loss": 0.8199312210083007, "step": 65640 }, { "epoch": 1.8551287665814344, "grad_norm": 4.213811874389648, "learning_rate": 3.480736691245021e-05, "loss": 0.8589079856872559, "step": 65660 }, { "epoch": 1.8556938420896492, "grad_norm": 3.005977153778076, "learning_rate": 3.477769804864136e-05, "loss": 0.8592041015625, "step": 65680 }, { "epoch": 1.8562589175978639, "grad_norm": 3.366907835006714, "learning_rate": 3.474803509090526e-05, "loss": 0.8342079162597656, "step": 65700 }, { "epoch": 1.8568239931060788, "grad_norm": 3.8724052906036377, "learning_rate": 3.4718378050750775e-05, "loss": 0.8479954719543457, "step": 65720 }, { "epoch": 1.8573890686142935, "grad_norm": 3.9155125617980957, "learning_rate": 3.46887269396845e-05, "loss": 0.8441323280334473, "step": 65740 }, { "epoch": 1.8579541441225085, "grad_norm": 3.781672954559326, "learning_rate": 3.465908176921068e-05, "loss": 0.8260994911193847, "step": 65760 }, { "epoch": 1.8585192196307232, "grad_norm": 3.5493433475494385, "learning_rate": 3.462944255083134e-05, "loss": 0.8267704963684082, "step": 65780 }, { "epoch": 1.859084295138938, "grad_norm": 3.177584648132324, "learning_rate": 3.459980929604609e-05, "loss": 0.8647939682006835, "step": 65800 }, { "epoch": 1.8596493706471526, "grad_norm": 4.793774604797363, "learning_rate": 3.457018201635233e-05, "loss": 0.8272153854370117, "step": 65820 }, { "epoch": 1.8602144461553674, "grad_norm": 3.3804855346679688, "learning_rate": 3.454056072324506e-05, "loss": 0.9328771591186523, "step": 65840 }, { "epoch": 1.8607795216635823, "grad_norm": 4.685257911682129, "learning_rate": 3.451094542821702e-05, "loss": 0.8526578903198242, "step": 65860 }, { "epoch": 1.8613445971717972, "grad_norm": 3.3263282775878906, "learning_rate": 3.448133614275856e-05, "loss": 0.854792594909668, "step": 65880 }, { "epoch": 1.861909672680012, "grad_norm": 2.7706143856048584, "learning_rate": 3.445173287835776e-05, "loss": 0.7796186447143555, "step": 65900 }, { "epoch": 1.8624747481882267, "grad_norm": 4.742332458496094, "learning_rate": 3.442213564650032e-05, "loss": 0.8466161727905274, "step": 65920 }, { "epoch": 1.8630398236964414, "grad_norm": 4.7573771476745605, "learning_rate": 3.439254445866962e-05, "loss": 0.8402034759521484, "step": 65940 }, { "epoch": 1.863604899204656, "grad_norm": 3.7105395793914795, "learning_rate": 3.436295932634668e-05, "loss": 0.9229872703552247, "step": 65960 }, { "epoch": 1.864169974712871, "grad_norm": 2.5994930267333984, "learning_rate": 3.43333802610102e-05, "loss": 0.8418272972106934, "step": 65980 }, { "epoch": 1.8647350502210858, "grad_norm": 2.0882034301757812, "learning_rate": 3.43038072741365e-05, "loss": 0.8264106750488281, "step": 66000 }, { "epoch": 1.8653001257293007, "grad_norm": 3.87268328666687, "learning_rate": 3.427424037719954e-05, "loss": 0.8014383316040039, "step": 66020 }, { "epoch": 1.8658652012375154, "grad_norm": 5.181473255157471, "learning_rate": 3.4244679581670945e-05, "loss": 0.8886034965515137, "step": 66040 }, { "epoch": 1.8664302767457301, "grad_norm": 2.5433008670806885, "learning_rate": 3.421512489901992e-05, "loss": 0.8807577133178711, "step": 66060 }, { "epoch": 1.8669953522539449, "grad_norm": 3.209137201309204, "learning_rate": 3.418557634071338e-05, "loss": 0.8327577590942383, "step": 66080 }, { "epoch": 1.8675604277621596, "grad_norm": 3.628549814224243, "learning_rate": 3.415603391821576e-05, "loss": 0.8071842193603516, "step": 66100 }, { "epoch": 1.8681255032703745, "grad_norm": 3.6081151962280273, "learning_rate": 3.412649764298922e-05, "loss": 0.8307461738586426, "step": 66120 }, { "epoch": 1.8686905787785892, "grad_norm": 2.9199438095092773, "learning_rate": 3.409696752649344e-05, "loss": 0.7702274322509766, "step": 66140 }, { "epoch": 1.8692556542868042, "grad_norm": 5.944656848907471, "learning_rate": 3.4067443580185784e-05, "loss": 0.8513961791992187, "step": 66160 }, { "epoch": 1.869820729795019, "grad_norm": 4.3981099128723145, "learning_rate": 3.403792581552119e-05, "loss": 0.873900032043457, "step": 66180 }, { "epoch": 1.8703858053032336, "grad_norm": 3.8487303256988525, "learning_rate": 3.40084142439522e-05, "loss": 0.8377788543701172, "step": 66200 }, { "epoch": 1.8709508808114483, "grad_norm": 3.176892042160034, "learning_rate": 3.397890887692894e-05, "loss": 0.8305639266967774, "step": 66220 }, { "epoch": 1.871515956319663, "grad_norm": 4.3395185470581055, "learning_rate": 3.3949409725899154e-05, "loss": 0.8813796043395996, "step": 66240 }, { "epoch": 1.872081031827878, "grad_norm": 5.3892645835876465, "learning_rate": 3.391991680230817e-05, "loss": 0.8757122039794922, "step": 66260 }, { "epoch": 1.872646107336093, "grad_norm": 3.679117441177368, "learning_rate": 3.389043011759887e-05, "loss": 0.8016243934631347, "step": 66280 }, { "epoch": 1.8732111828443077, "grad_norm": 3.1207115650177, "learning_rate": 3.386094968321176e-05, "loss": 0.8021149635314941, "step": 66300 }, { "epoch": 1.8737762583525224, "grad_norm": 3.6141085624694824, "learning_rate": 3.38314755105849e-05, "loss": 0.855204963684082, "step": 66320 }, { "epoch": 1.874341333860737, "grad_norm": 4.118927955627441, "learning_rate": 3.380200761115391e-05, "loss": 0.8691047668457031, "step": 66340 }, { "epoch": 1.8749064093689518, "grad_norm": 3.0444839000701904, "learning_rate": 3.3772545996351986e-05, "loss": 0.8700364112854004, "step": 66360 }, { "epoch": 1.8754714848771668, "grad_norm": 3.514017105102539, "learning_rate": 3.374309067760989e-05, "loss": 0.8255784034729003, "step": 66380 }, { "epoch": 1.8760365603853815, "grad_norm": 3.565159559249878, "learning_rate": 3.371364166635594e-05, "loss": 0.7963305950164795, "step": 66400 }, { "epoch": 1.8766016358935964, "grad_norm": 4.717800140380859, "learning_rate": 3.368419897401599e-05, "loss": 0.7459409236907959, "step": 66420 }, { "epoch": 1.8771667114018111, "grad_norm": 4.134191513061523, "learning_rate": 3.365476261201347e-05, "loss": 0.9069786071777344, "step": 66440 }, { "epoch": 1.8777317869100258, "grad_norm": 4.201652526855469, "learning_rate": 3.362533259176932e-05, "loss": 0.8349147796630859, "step": 66460 }, { "epoch": 1.8782968624182406, "grad_norm": 4.923301696777344, "learning_rate": 3.359590892470206e-05, "loss": 0.8653502464294434, "step": 66480 }, { "epoch": 1.8788619379264553, "grad_norm": 3.434178590774536, "learning_rate": 3.3566491622227706e-05, "loss": 0.8309326171875, "step": 66500 }, { "epoch": 1.8794270134346702, "grad_norm": 2.669034481048584, "learning_rate": 3.353708069575985e-05, "loss": 0.8038381576538086, "step": 66520 }, { "epoch": 1.879992088942885, "grad_norm": 4.140077590942383, "learning_rate": 3.350767615670955e-05, "loss": 0.893902587890625, "step": 66540 }, { "epoch": 1.8805571644510999, "grad_norm": 3.6033682823181152, "learning_rate": 3.3478278016485444e-05, "loss": 0.8588689804077149, "step": 66560 }, { "epoch": 1.8811222399593146, "grad_norm": 5.061689853668213, "learning_rate": 3.344888628649364e-05, "loss": 0.8639122009277344, "step": 66580 }, { "epoch": 1.8816873154675293, "grad_norm": 4.042256832122803, "learning_rate": 3.3419500978137805e-05, "loss": 0.8890527725219727, "step": 66600 }, { "epoch": 1.882252390975744, "grad_norm": 4.345634937286377, "learning_rate": 3.339012210281906e-05, "loss": 0.7571448802947998, "step": 66620 }, { "epoch": 1.8828174664839588, "grad_norm": 4.516566276550293, "learning_rate": 3.336074967193609e-05, "loss": 0.8402204513549805, "step": 66640 }, { "epoch": 1.8833825419921737, "grad_norm": 2.4283759593963623, "learning_rate": 3.333138369688504e-05, "loss": 0.8126829147338868, "step": 66660 }, { "epoch": 1.8839476175003886, "grad_norm": 2.5961883068084717, "learning_rate": 3.3302024189059556e-05, "loss": 0.790913724899292, "step": 66680 }, { "epoch": 1.8845126930086034, "grad_norm": 2.2338743209838867, "learning_rate": 3.327267115985079e-05, "loss": 0.7885649681091309, "step": 66700 }, { "epoch": 1.885077768516818, "grad_norm": 3.852552890777588, "learning_rate": 3.3243324620647346e-05, "loss": 0.8362565040588379, "step": 66720 }, { "epoch": 1.8856428440250328, "grad_norm": 3.3156425952911377, "learning_rate": 3.321398458283537e-05, "loss": 0.8844633102416992, "step": 66740 }, { "epoch": 1.8862079195332475, "grad_norm": 5.012298107147217, "learning_rate": 3.3184651057798405e-05, "loss": 0.7553212165832519, "step": 66760 }, { "epoch": 1.8867729950414625, "grad_norm": 4.044927597045898, "learning_rate": 3.315532405691755e-05, "loss": 0.8211840629577637, "step": 66780 }, { "epoch": 1.8873380705496772, "grad_norm": 5.853135585784912, "learning_rate": 3.312600359157131e-05, "loss": 0.8593810081481934, "step": 66800 }, { "epoch": 1.8879031460578921, "grad_norm": 3.549893379211426, "learning_rate": 3.309668967313569e-05, "loss": 0.7885219097137451, "step": 66820 }, { "epoch": 1.8884682215661068, "grad_norm": 4.238415718078613, "learning_rate": 3.306738231298413e-05, "loss": 0.8385205268859863, "step": 66840 }, { "epoch": 1.8890332970743215, "grad_norm": 4.566399574279785, "learning_rate": 3.303808152248756e-05, "loss": 0.8255406379699707, "step": 66860 }, { "epoch": 1.8895983725825363, "grad_norm": 3.319716215133667, "learning_rate": 3.300878731301431e-05, "loss": 0.7472109317779541, "step": 66880 }, { "epoch": 1.890163448090751, "grad_norm": 3.926213502883911, "learning_rate": 3.2979499695930213e-05, "loss": 0.8707271575927734, "step": 66900 }, { "epoch": 1.890728523598966, "grad_norm": 2.437098741531372, "learning_rate": 3.295021868259851e-05, "loss": 0.9065363883972168, "step": 66920 }, { "epoch": 1.8912935991071806, "grad_norm": 5.053323745727539, "learning_rate": 3.292094428437986e-05, "loss": 0.7849741458892823, "step": 66940 }, { "epoch": 1.8918586746153956, "grad_norm": 4.745518207550049, "learning_rate": 3.289167651263243e-05, "loss": 0.8209545135498046, "step": 66960 }, { "epoch": 1.8924237501236103, "grad_norm": 3.559748411178589, "learning_rate": 3.2862415378711744e-05, "loss": 0.8470315933227539, "step": 66980 }, { "epoch": 1.892988825631825, "grad_norm": 4.855998516082764, "learning_rate": 3.283316089397076e-05, "loss": 0.8374007225036622, "step": 67000 }, { "epoch": 1.8935539011400397, "grad_norm": 3.985837459564209, "learning_rate": 3.280391306975991e-05, "loss": 0.7819403648376465, "step": 67020 }, { "epoch": 1.8941189766482545, "grad_norm": 3.1705081462860107, "learning_rate": 3.2774671917426966e-05, "loss": 0.7818261623382569, "step": 67040 }, { "epoch": 1.8946840521564694, "grad_norm": 3.6496989727020264, "learning_rate": 3.274543744831717e-05, "loss": 0.8492171287536621, "step": 67060 }, { "epoch": 1.8952491276646843, "grad_norm": 3.415436029434204, "learning_rate": 3.271620967377313e-05, "loss": 0.7910166263580323, "step": 67080 }, { "epoch": 1.895814203172899, "grad_norm": 3.5960285663604736, "learning_rate": 3.268698860513491e-05, "loss": 0.7961134910583496, "step": 67100 }, { "epoch": 1.8963792786811138, "grad_norm": 4.218757152557373, "learning_rate": 3.265777425373991e-05, "loss": 0.8163267135620117, "step": 67120 }, { "epoch": 1.8969443541893285, "grad_norm": 2.8409759998321533, "learning_rate": 3.2628566630922955e-05, "loss": 0.8185060501098633, "step": 67140 }, { "epoch": 1.8975094296975432, "grad_norm": 2.95440673828125, "learning_rate": 3.2599365748016255e-05, "loss": 0.8113141059875488, "step": 67160 }, { "epoch": 1.8980745052057582, "grad_norm": 3.9665334224700928, "learning_rate": 3.257017161634942e-05, "loss": 0.7539136409759521, "step": 67180 }, { "epoch": 1.8986395807139729, "grad_norm": 4.08485746383667, "learning_rate": 3.254098424724942e-05, "loss": 0.8530635833740234, "step": 67200 }, { "epoch": 1.8992046562221878, "grad_norm": 5.568637371063232, "learning_rate": 3.251180365204061e-05, "loss": 0.8660952568054199, "step": 67220 }, { "epoch": 1.8997697317304025, "grad_norm": 3.475816488265991, "learning_rate": 3.24826298420447e-05, "loss": 0.8641000747680664, "step": 67240 }, { "epoch": 1.9003348072386173, "grad_norm": 3.218744993209839, "learning_rate": 3.245346282858081e-05, "loss": 0.7974773406982422, "step": 67260 }, { "epoch": 1.900899882746832, "grad_norm": 2.843008041381836, "learning_rate": 3.242430262296535e-05, "loss": 0.8337616920471191, "step": 67280 }, { "epoch": 1.9014649582550467, "grad_norm": 4.5461201667785645, "learning_rate": 3.2395149236512183e-05, "loss": 0.8468854904174805, "step": 67300 }, { "epoch": 1.9020300337632616, "grad_norm": 3.5538129806518555, "learning_rate": 3.236600268053247e-05, "loss": 0.8276375770568848, "step": 67320 }, { "epoch": 1.9025951092714763, "grad_norm": 3.6696884632110596, "learning_rate": 3.2336862966334714e-05, "loss": 0.7691239833831787, "step": 67340 }, { "epoch": 1.9031601847796913, "grad_norm": 3.4392802715301514, "learning_rate": 3.230773010522478e-05, "loss": 0.862037181854248, "step": 67360 }, { "epoch": 1.903725260287906, "grad_norm": 4.104720592498779, "learning_rate": 3.227860410850587e-05, "loss": 0.8501570701599122, "step": 67380 }, { "epoch": 1.9042903357961207, "grad_norm": 3.5765750408172607, "learning_rate": 3.224948498747855e-05, "loss": 0.8527947425842285, "step": 67400 }, { "epoch": 1.9048554113043354, "grad_norm": 3.817479133605957, "learning_rate": 3.2220372753440656e-05, "loss": 0.8639466285705566, "step": 67420 }, { "epoch": 1.9054204868125502, "grad_norm": 3.8668081760406494, "learning_rate": 3.2191267417687424e-05, "loss": 0.8263797760009766, "step": 67440 }, { "epoch": 1.905985562320765, "grad_norm": 3.9746201038360596, "learning_rate": 3.216216899151135e-05, "loss": 0.8474527359008789, "step": 67460 }, { "epoch": 1.90655063782898, "grad_norm": 3.196802854537964, "learning_rate": 3.2133077486202315e-05, "loss": 0.7964752674102783, "step": 67480 }, { "epoch": 1.9071157133371948, "grad_norm": 2.7198705673217773, "learning_rate": 3.210399291304743e-05, "loss": 0.8838924407958985, "step": 67500 }, { "epoch": 1.9076807888454095, "grad_norm": 4.361026763916016, "learning_rate": 3.2074915283331214e-05, "loss": 0.8307966232299805, "step": 67520 }, { "epoch": 1.9082458643536242, "grad_norm": 3.4047000408172607, "learning_rate": 3.204584460833541e-05, "loss": 0.8149153709411621, "step": 67540 }, { "epoch": 1.908810939861839, "grad_norm": 4.012640476226807, "learning_rate": 3.20167808993391e-05, "loss": 0.7670155525207519, "step": 67560 }, { "epoch": 1.9093760153700539, "grad_norm": 3.396652936935425, "learning_rate": 3.198772416761866e-05, "loss": 0.8785974502563476, "step": 67580 }, { "epoch": 1.9099410908782686, "grad_norm": 3.5775883197784424, "learning_rate": 3.195867442444776e-05, "loss": 0.7927193641662598, "step": 67600 }, { "epoch": 1.9105061663864835, "grad_norm": 4.360819339752197, "learning_rate": 3.192963168109736e-05, "loss": 0.8194280624389648, "step": 67620 }, { "epoch": 1.9110712418946982, "grad_norm": 4.412997245788574, "learning_rate": 3.1900595948835707e-05, "loss": 0.7810070037841796, "step": 67640 }, { "epoch": 1.911636317402913, "grad_norm": 4.8490400314331055, "learning_rate": 3.18715672389283e-05, "loss": 0.8060158729553223, "step": 67660 }, { "epoch": 1.9122013929111277, "grad_norm": 4.36797571182251, "learning_rate": 3.1842545562637964e-05, "loss": 0.8633017539978027, "step": 67680 }, { "epoch": 1.9127664684193424, "grad_norm": 3.3376150131225586, "learning_rate": 3.1813530931224734e-05, "loss": 0.8331551551818848, "step": 67700 }, { "epoch": 1.9133315439275573, "grad_norm": 3.7519495487213135, "learning_rate": 3.178452335594596e-05, "loss": 0.872934627532959, "step": 67720 }, { "epoch": 1.913896619435772, "grad_norm": 2.7998626232147217, "learning_rate": 3.175552284805623e-05, "loss": 0.845616340637207, "step": 67740 }, { "epoch": 1.914461694943987, "grad_norm": 3.949859619140625, "learning_rate": 3.172652941880741e-05, "loss": 0.788057804107666, "step": 67760 }, { "epoch": 1.9150267704522017, "grad_norm": 5.102591514587402, "learning_rate": 3.169754307944859e-05, "loss": 0.8536770820617676, "step": 67780 }, { "epoch": 1.9155918459604164, "grad_norm": 3.739924192428589, "learning_rate": 3.166856384122614e-05, "loss": 0.7882839202880859, "step": 67800 }, { "epoch": 1.9161569214686311, "grad_norm": 5.034226417541504, "learning_rate": 3.163959171538364e-05, "loss": 0.7598131179809571, "step": 67820 }, { "epoch": 1.9167219969768459, "grad_norm": 3.05067777633667, "learning_rate": 3.161062671316196e-05, "loss": 0.8353962898254395, "step": 67840 }, { "epoch": 1.9172870724850608, "grad_norm": 5.4679789543151855, "learning_rate": 3.158166884579916e-05, "loss": 0.829857063293457, "step": 67860 }, { "epoch": 1.9178521479932757, "grad_norm": 4.84648323059082, "learning_rate": 3.155271812453056e-05, "loss": 0.8397284507751465, "step": 67880 }, { "epoch": 1.9184172235014905, "grad_norm": 2.4045026302337646, "learning_rate": 3.152377456058868e-05, "loss": 0.9013854026794433, "step": 67900 }, { "epoch": 1.9189822990097052, "grad_norm": 3.9285690784454346, "learning_rate": 3.14948381652033e-05, "loss": 0.8076070785522461, "step": 67920 }, { "epoch": 1.91954737451792, "grad_norm": 3.2356226444244385, "learning_rate": 3.146590894960137e-05, "loss": 0.8932768821716308, "step": 67940 }, { "epoch": 1.9201124500261346, "grad_norm": 2.3981411457061768, "learning_rate": 3.1436986925007106e-05, "loss": 0.7863497734069824, "step": 67960 }, { "epoch": 1.9206775255343496, "grad_norm": 2.8624980449676514, "learning_rate": 3.140807210264192e-05, "loss": 0.8460922241210938, "step": 67980 }, { "epoch": 1.9212426010425643, "grad_norm": 4.137787818908691, "learning_rate": 3.13791644937244e-05, "loss": 0.794547176361084, "step": 68000 }, { "epoch": 1.9218076765507792, "grad_norm": 3.5376698970794678, "learning_rate": 3.135026410947037e-05, "loss": 0.853154182434082, "step": 68020 }, { "epoch": 1.922372752058994, "grad_norm": 3.444946765899658, "learning_rate": 3.132137096109281e-05, "loss": 0.8342280387878418, "step": 68040 }, { "epoch": 1.9229378275672087, "grad_norm": 3.345395803451538, "learning_rate": 3.1292485059801954e-05, "loss": 0.8021570205688476, "step": 68060 }, { "epoch": 1.9235029030754234, "grad_norm": 3.1621272563934326, "learning_rate": 3.126360641680517e-05, "loss": 0.8128481864929199, "step": 68080 }, { "epoch": 1.924067978583638, "grad_norm": 5.273843288421631, "learning_rate": 3.123473504330703e-05, "loss": 0.8501601219177246, "step": 68100 }, { "epoch": 1.924633054091853, "grad_norm": 5.450573921203613, "learning_rate": 3.120587095050929e-05, "loss": 0.9410232543945313, "step": 68120 }, { "epoch": 1.925198129600068, "grad_norm": 3.154268980026245, "learning_rate": 3.117701414961087e-05, "loss": 0.7860538005828858, "step": 68140 }, { "epoch": 1.9257632051082827, "grad_norm": 3.0343258380889893, "learning_rate": 3.114816465180787e-05, "loss": 0.8779147148132325, "step": 68160 }, { "epoch": 1.9263282806164974, "grad_norm": 3.526890516281128, "learning_rate": 3.111932246829355e-05, "loss": 0.8701862335205078, "step": 68180 }, { "epoch": 1.9268933561247121, "grad_norm": 3.4515914916992188, "learning_rate": 3.109048761025833e-05, "loss": 0.7953407764434814, "step": 68200 }, { "epoch": 1.9274584316329268, "grad_norm": 3.0377187728881836, "learning_rate": 3.1061660088889825e-05, "loss": 0.8792536735534668, "step": 68220 }, { "epoch": 1.9280235071411418, "grad_norm": 3.7501988410949707, "learning_rate": 3.103283991537272e-05, "loss": 0.7995936870574951, "step": 68240 }, { "epoch": 1.9285885826493565, "grad_norm": 2.999403476715088, "learning_rate": 3.100402710088893e-05, "loss": 0.8135796546936035, "step": 68260 }, { "epoch": 1.9291536581575714, "grad_norm": 3.3850862979888916, "learning_rate": 3.097522165661749e-05, "loss": 0.842048454284668, "step": 68280 }, { "epoch": 1.9297187336657862, "grad_norm": 3.1827077865600586, "learning_rate": 3.0946423593734584e-05, "loss": 0.9039175033569335, "step": 68300 }, { "epoch": 1.9302838091740009, "grad_norm": 5.019059181213379, "learning_rate": 3.0917632923413484e-05, "loss": 0.7507012844085693, "step": 68320 }, { "epoch": 1.9308488846822156, "grad_norm": 3.8080337047576904, "learning_rate": 3.0888849656824654e-05, "loss": 0.8424393653869628, "step": 68340 }, { "epoch": 1.9314139601904303, "grad_norm": 2.7363624572753906, "learning_rate": 3.086007380513564e-05, "loss": 0.8207647323608398, "step": 68360 }, { "epoch": 1.9319790356986453, "grad_norm": 3.8668344020843506, "learning_rate": 3.083130537951116e-05, "loss": 0.7990220546722412, "step": 68380 }, { "epoch": 1.93254411120686, "grad_norm": 4.279224872589111, "learning_rate": 3.080254439111299e-05, "loss": 0.941158390045166, "step": 68400 }, { "epoch": 1.933109186715075, "grad_norm": 2.870635747909546, "learning_rate": 3.0773790851100074e-05, "loss": 0.8307697296142578, "step": 68420 }, { "epoch": 1.9336742622232896, "grad_norm": 2.9017879962921143, "learning_rate": 3.0745044770628426e-05, "loss": 0.7673811912536621, "step": 68440 }, { "epoch": 1.9342393377315044, "grad_norm": 3.4829418659210205, "learning_rate": 3.071630616085122e-05, "loss": 0.9075515747070313, "step": 68460 }, { "epoch": 1.934804413239719, "grad_norm": 3.100363254547119, "learning_rate": 3.068757503291866e-05, "loss": 0.8566058158874512, "step": 68480 }, { "epoch": 1.9353694887479338, "grad_norm": 4.258108615875244, "learning_rate": 3.0658851397978096e-05, "loss": 0.8462926864624023, "step": 68500 }, { "epoch": 1.9359345642561487, "grad_norm": 3.2373602390289307, "learning_rate": 3.063013526717396e-05, "loss": 0.7961102962493897, "step": 68520 }, { "epoch": 1.9364996397643637, "grad_norm": 3.3843095302581787, "learning_rate": 3.060142665164777e-05, "loss": 0.836610984802246, "step": 68540 }, { "epoch": 1.9370647152725784, "grad_norm": 4.4384541511535645, "learning_rate": 3.0572725562538116e-05, "loss": 0.7585995197296143, "step": 68560 }, { "epoch": 1.9376297907807931, "grad_norm": 3.76194167137146, "learning_rate": 3.05440320109807e-05, "loss": 0.792236328125, "step": 68580 }, { "epoch": 1.9381948662890078, "grad_norm": 4.610005855560303, "learning_rate": 3.051534600810826e-05, "loss": 0.9547796249389648, "step": 68600 }, { "epoch": 1.9387599417972226, "grad_norm": 4.034448146820068, "learning_rate": 3.048666756505064e-05, "loss": 0.8775774955749511, "step": 68620 }, { "epoch": 1.9393250173054375, "grad_norm": 2.771202564239502, "learning_rate": 3.045799669293474e-05, "loss": 0.9511969566345215, "step": 68640 }, { "epoch": 1.9398900928136522, "grad_norm": 4.158891677856445, "learning_rate": 3.0429333402884507e-05, "loss": 0.9008964538574219, "step": 68660 }, { "epoch": 1.9404551683218672, "grad_norm": 3.2205638885498047, "learning_rate": 3.0400677706020975e-05, "loss": 0.8576825141906739, "step": 68680 }, { "epoch": 1.9410202438300819, "grad_norm": 3.5697953701019287, "learning_rate": 3.037202961346218e-05, "loss": 0.7574080467224121, "step": 68700 }, { "epoch": 1.9415853193382966, "grad_norm": 3.9990735054016113, "learning_rate": 3.0343389136323286e-05, "loss": 0.8743219375610352, "step": 68720 }, { "epoch": 1.9421503948465113, "grad_norm": 2.2023606300354004, "learning_rate": 3.0314756285716417e-05, "loss": 0.7961803436279297, "step": 68740 }, { "epoch": 1.942715470354726, "grad_norm": 3.551506519317627, "learning_rate": 3.028613107275082e-05, "loss": 0.7846038818359375, "step": 68760 }, { "epoch": 1.943280545862941, "grad_norm": 2.8576509952545166, "learning_rate": 3.0257513508532698e-05, "loss": 0.8738293647766113, "step": 68780 }, { "epoch": 1.9438456213711557, "grad_norm": 4.411487102508545, "learning_rate": 3.0228903604165358e-05, "loss": 0.9057913780212402, "step": 68800 }, { "epoch": 1.9444106968793706, "grad_norm": 5.227587699890137, "learning_rate": 3.0200301370749085e-05, "loss": 0.8334802627563477, "step": 68820 }, { "epoch": 1.9449757723875853, "grad_norm": 3.5911121368408203, "learning_rate": 3.017170681938122e-05, "loss": 0.7865786075592041, "step": 68840 }, { "epoch": 1.9455408478958, "grad_norm": 3.4687421321868896, "learning_rate": 3.0143119961156096e-05, "loss": 0.8153704643249512, "step": 68860 }, { "epoch": 1.9461059234040148, "grad_norm": 3.9938700199127197, "learning_rate": 3.0114540807165092e-05, "loss": 0.8598862648010254, "step": 68880 }, { "epoch": 1.9466709989122295, "grad_norm": 4.331612586975098, "learning_rate": 3.0085969368496562e-05, "loss": 0.8019458770751953, "step": 68900 }, { "epoch": 1.9472360744204444, "grad_norm": 3.113187074661255, "learning_rate": 3.0057405656235887e-05, "loss": 0.86935453414917, "step": 68920 }, { "epoch": 1.9478011499286594, "grad_norm": 3.401242971420288, "learning_rate": 3.0028849681465464e-05, "loss": 0.8455039978027343, "step": 68940 }, { "epoch": 1.948366225436874, "grad_norm": 3.4540655612945557, "learning_rate": 3.000030145526468e-05, "loss": 0.8142413139343262, "step": 68960 }, { "epoch": 1.9489313009450888, "grad_norm": 3.7977521419525146, "learning_rate": 2.9971760988709884e-05, "loss": 0.7706093788146973, "step": 68980 }, { "epoch": 1.9494963764533035, "grad_norm": 3.2842354774475098, "learning_rate": 2.994322829287446e-05, "loss": 0.8454442024230957, "step": 69000 }, { "epoch": 1.9500614519615183, "grad_norm": 2.8540704250335693, "learning_rate": 2.9914703378828735e-05, "loss": 0.9176202774047851, "step": 69020 }, { "epoch": 1.9506265274697332, "grad_norm": 3.6986281871795654, "learning_rate": 2.988618625764006e-05, "loss": 0.783326244354248, "step": 69040 }, { "epoch": 1.951191602977948, "grad_norm": 3.234910249710083, "learning_rate": 2.9857676940372713e-05, "loss": 0.9575455665588379, "step": 69060 }, { "epoch": 1.9517566784861629, "grad_norm": 4.172423839569092, "learning_rate": 2.9829175438088e-05, "loss": 0.8456483840942383, "step": 69080 }, { "epoch": 1.9523217539943776, "grad_norm": 5.523186206817627, "learning_rate": 2.980068176184413e-05, "loss": 0.9101304054260254, "step": 69100 }, { "epoch": 1.9528868295025923, "grad_norm": 2.962883472442627, "learning_rate": 2.9772195922696356e-05, "loss": 0.7485940456390381, "step": 69120 }, { "epoch": 1.953451905010807, "grad_norm": 4.335747241973877, "learning_rate": 2.9743717931696812e-05, "loss": 0.8711782455444336, "step": 69140 }, { "epoch": 1.9540169805190217, "grad_norm": 3.9456653594970703, "learning_rate": 2.971524779989464e-05, "loss": 0.8169912338256836, "step": 69160 }, { "epoch": 1.9545820560272367, "grad_norm": 3.0179715156555176, "learning_rate": 2.9686785538335897e-05, "loss": 0.7821602821350098, "step": 69180 }, { "epoch": 1.9551471315354514, "grad_norm": 4.592218399047852, "learning_rate": 2.9658331158063624e-05, "loss": 0.8083127021789551, "step": 69200 }, { "epoch": 1.9557122070436663, "grad_norm": 4.1321001052856445, "learning_rate": 2.9629884670117758e-05, "loss": 0.8207260131835937, "step": 69220 }, { "epoch": 1.956277282551881, "grad_norm": 4.032535552978516, "learning_rate": 2.9601446085535227e-05, "loss": 0.791352653503418, "step": 69240 }, { "epoch": 1.9568423580600958, "grad_norm": 4.121984004974365, "learning_rate": 2.957301541534983e-05, "loss": 0.8368189811706543, "step": 69260 }, { "epoch": 1.9574074335683105, "grad_norm": 3.326188325881958, "learning_rate": 2.9544592670592362e-05, "loss": 0.8484750747680664, "step": 69280 }, { "epoch": 1.9579725090765252, "grad_norm": 4.632954120635986, "learning_rate": 2.9516177862290505e-05, "loss": 0.8073825836181641, "step": 69300 }, { "epoch": 1.9585375845847401, "grad_norm": 3.735172986984253, "learning_rate": 2.9487771001468857e-05, "loss": 0.9418980598449707, "step": 69320 }, { "epoch": 1.959102660092955, "grad_norm": 3.671024799346924, "learning_rate": 2.945937209914896e-05, "loss": 0.9400545120239258, "step": 69340 }, { "epoch": 1.9596677356011698, "grad_norm": 3.655942678451538, "learning_rate": 2.9430981166349225e-05, "loss": 0.8318549156188965, "step": 69360 }, { "epoch": 1.9602328111093845, "grad_norm": 3.3184449672698975, "learning_rate": 2.940259821408503e-05, "loss": 0.8223931312561035, "step": 69380 }, { "epoch": 1.9607978866175992, "grad_norm": 4.059197902679443, "learning_rate": 2.9374223253368595e-05, "loss": 0.8853306770324707, "step": 69400 }, { "epoch": 1.961362962125814, "grad_norm": 4.3880696296691895, "learning_rate": 2.9345856295209084e-05, "loss": 0.8450174331665039, "step": 69420 }, { "epoch": 1.961928037634029, "grad_norm": 3.7448995113372803, "learning_rate": 2.9317497350612534e-05, "loss": 0.870364761352539, "step": 69440 }, { "epoch": 1.9624931131422436, "grad_norm": 3.023921012878418, "learning_rate": 2.9289146430581894e-05, "loss": 0.7983298778533936, "step": 69460 }, { "epoch": 1.9630581886504586, "grad_norm": 3.838308334350586, "learning_rate": 2.9260803546116962e-05, "loss": 0.8492424011230468, "step": 69480 }, { "epoch": 1.9636232641586733, "grad_norm": 3.3463661670684814, "learning_rate": 2.923246870821446e-05, "loss": 0.8360137939453125, "step": 69500 }, { "epoch": 1.964188339666888, "grad_norm": 2.6510608196258545, "learning_rate": 2.9204141927867957e-05, "loss": 0.7386987686157227, "step": 69520 }, { "epoch": 1.9647534151751027, "grad_norm": 3.22035551071167, "learning_rate": 2.9175823216067916e-05, "loss": 0.8315434455871582, "step": 69540 }, { "epoch": 1.9653184906833174, "grad_norm": 4.202005863189697, "learning_rate": 2.914751258380166e-05, "loss": 0.7953696250915527, "step": 69560 }, { "epoch": 1.9658835661915324, "grad_norm": 3.6210944652557373, "learning_rate": 2.911921004205334e-05, "loss": 0.799855089187622, "step": 69580 }, { "epoch": 1.966448641699747, "grad_norm": 4.309656143188477, "learning_rate": 2.9090915601804082e-05, "loss": 0.8711670875549317, "step": 69600 }, { "epoch": 1.967013717207962, "grad_norm": 3.957712173461914, "learning_rate": 2.906262927403176e-05, "loss": 0.7916879653930664, "step": 69620 }, { "epoch": 1.9675787927161767, "grad_norm": 3.522331953048706, "learning_rate": 2.903435106971113e-05, "loss": 0.7316568851470947, "step": 69640 }, { "epoch": 1.9681438682243915, "grad_norm": 3.2455832958221436, "learning_rate": 2.9006080999813773e-05, "loss": 0.9053407669067383, "step": 69660 }, { "epoch": 1.9687089437326062, "grad_norm": 3.5705573558807373, "learning_rate": 2.897781907530819e-05, "loss": 0.8240213394165039, "step": 69680 }, { "epoch": 1.969274019240821, "grad_norm": 4.186919212341309, "learning_rate": 2.8949565307159655e-05, "loss": 0.8429988861083985, "step": 69700 }, { "epoch": 1.9698390947490358, "grad_norm": 4.148439407348633, "learning_rate": 2.8921319706330284e-05, "loss": 0.8086137771606445, "step": 69720 }, { "epoch": 1.9704041702572508, "grad_norm": 4.1635870933532715, "learning_rate": 2.8893082283779026e-05, "loss": 0.790609884262085, "step": 69740 }, { "epoch": 1.9709692457654655, "grad_norm": 4.827350616455078, "learning_rate": 2.8864853050461703e-05, "loss": 0.8679553985595703, "step": 69760 }, { "epoch": 1.9715343212736802, "grad_norm": 6.686722278594971, "learning_rate": 2.88366320173309e-05, "loss": 0.8399951934814454, "step": 69780 }, { "epoch": 1.972099396781895, "grad_norm": 2.9461190700531006, "learning_rate": 2.8808419195336046e-05, "loss": 0.8243483543395996, "step": 69800 }, { "epoch": 1.9726644722901097, "grad_norm": 2.9608185291290283, "learning_rate": 2.878021459542336e-05, "loss": 0.7986231327056885, "step": 69820 }, { "epoch": 1.9732295477983246, "grad_norm": 5.374630451202393, "learning_rate": 2.8752018228535938e-05, "loss": 0.8203442573547364, "step": 69840 }, { "epoch": 1.9737946233065393, "grad_norm": 4.308218955993652, "learning_rate": 2.8723830105613614e-05, "loss": 0.7755993843078614, "step": 69860 }, { "epoch": 1.9743596988147543, "grad_norm": 3.1941304206848145, "learning_rate": 2.8695650237593037e-05, "loss": 0.7095926761627197, "step": 69880 }, { "epoch": 1.974924774322969, "grad_norm": 4.783695220947266, "learning_rate": 2.8667478635407647e-05, "loss": 0.752003288269043, "step": 69900 }, { "epoch": 1.9754898498311837, "grad_norm": 3.431000232696533, "learning_rate": 2.8639315309987712e-05, "loss": 0.7857307910919189, "step": 69920 }, { "epoch": 1.9760549253393984, "grad_norm": 5.880250453948975, "learning_rate": 2.8611160272260295e-05, "loss": 0.8258731842041016, "step": 69940 }, { "epoch": 1.9766200008476131, "grad_norm": 3.2262561321258545, "learning_rate": 2.8583013533149194e-05, "loss": 0.7663909435272217, "step": 69960 }, { "epoch": 1.977185076355828, "grad_norm": 4.2963457107543945, "learning_rate": 2.8554875103575e-05, "loss": 0.7590419769287109, "step": 69980 }, { "epoch": 1.9777501518640428, "grad_norm": 4.061379909515381, "learning_rate": 2.8526744994455084e-05, "loss": 0.8346955299377441, "step": 70000 }, { "epoch": 1.9783152273722577, "grad_norm": 4.007025718688965, "learning_rate": 2.8498623216703623e-05, "loss": 0.8230352401733398, "step": 70020 }, { "epoch": 1.9788803028804725, "grad_norm": 4.82417106628418, "learning_rate": 2.8470509781231524e-05, "loss": 0.8314441680908203, "step": 70040 }, { "epoch": 1.9794453783886872, "grad_norm": 3.2273221015930176, "learning_rate": 2.8442404698946456e-05, "loss": 0.8390264511108398, "step": 70060 }, { "epoch": 1.980010453896902, "grad_norm": 3.6698856353759766, "learning_rate": 2.8414307980752852e-05, "loss": 0.761473560333252, "step": 70080 }, { "epoch": 1.9805755294051166, "grad_norm": 2.676786422729492, "learning_rate": 2.8386219637551936e-05, "loss": 0.8100576400756836, "step": 70100 }, { "epoch": 1.9811406049133315, "grad_norm": 3.176363945007324, "learning_rate": 2.835813968024163e-05, "loss": 0.828548526763916, "step": 70120 }, { "epoch": 1.9817056804215465, "grad_norm": 3.733114719390869, "learning_rate": 2.8330068119716626e-05, "loss": 0.8551468849182129, "step": 70140 }, { "epoch": 1.9822707559297612, "grad_norm": 3.0394153594970703, "learning_rate": 2.8302004966868345e-05, "loss": 0.8548236846923828, "step": 70160 }, { "epoch": 1.982835831437976, "grad_norm": 3.570523977279663, "learning_rate": 2.827395023258499e-05, "loss": 0.782105827331543, "step": 70180 }, { "epoch": 1.9834009069461906, "grad_norm": 3.615781784057617, "learning_rate": 2.8245903927751445e-05, "loss": 0.8490313529968262, "step": 70200 }, { "epoch": 1.9839659824544054, "grad_norm": 3.302180051803589, "learning_rate": 2.8217866063249343e-05, "loss": 0.7997402667999267, "step": 70220 }, { "epoch": 1.9845310579626203, "grad_norm": 2.9701013565063477, "learning_rate": 2.8189836649957014e-05, "loss": 0.7984236240386963, "step": 70240 }, { "epoch": 1.985096133470835, "grad_norm": 2.4816389083862305, "learning_rate": 2.8161815698749604e-05, "loss": 0.783840274810791, "step": 70260 }, { "epoch": 1.98566120897905, "grad_norm": 3.4617679119110107, "learning_rate": 2.8133803220498885e-05, "loss": 0.7837006568908691, "step": 70280 }, { "epoch": 1.9862262844872647, "grad_norm": 3.07897686958313, "learning_rate": 2.810579922607335e-05, "loss": 0.7985406398773194, "step": 70300 }, { "epoch": 1.9867913599954794, "grad_norm": 4.265600204467773, "learning_rate": 2.8077803726338202e-05, "loss": 0.8667867660522461, "step": 70320 }, { "epoch": 1.9873564355036941, "grad_norm": 3.5245237350463867, "learning_rate": 2.8049816732155416e-05, "loss": 0.8128533363342285, "step": 70340 }, { "epoch": 1.9879215110119088, "grad_norm": 3.268373966217041, "learning_rate": 2.802183825438358e-05, "loss": 0.8708540916442871, "step": 70360 }, { "epoch": 1.9884865865201238, "grad_norm": 3.336756706237793, "learning_rate": 2.7993868303878012e-05, "loss": 0.7166572093963623, "step": 70380 }, { "epoch": 1.9890516620283385, "grad_norm": 3.6822471618652344, "learning_rate": 2.796590689149071e-05, "loss": 0.8258820533752441, "step": 70400 }, { "epoch": 1.9896167375365534, "grad_norm": 3.64286732673645, "learning_rate": 2.79379540280704e-05, "loss": 0.8704060554504395, "step": 70420 }, { "epoch": 1.9901818130447682, "grad_norm": 3.0087432861328125, "learning_rate": 2.791000972446245e-05, "loss": 0.8480619430541992, "step": 70440 }, { "epoch": 1.9907468885529829, "grad_norm": 4.105153560638428, "learning_rate": 2.7882073991508916e-05, "loss": 0.7407011032104492, "step": 70460 }, { "epoch": 1.9913119640611976, "grad_norm": 3.1159753799438477, "learning_rate": 2.785414684004851e-05, "loss": 0.8964628219604492, "step": 70480 }, { "epoch": 1.9918770395694123, "grad_norm": 3.6559603214263916, "learning_rate": 2.782622828091668e-05, "loss": 0.7919179439544678, "step": 70500 }, { "epoch": 1.9924421150776273, "grad_norm": 4.422297954559326, "learning_rate": 2.779831832494547e-05, "loss": 0.877132511138916, "step": 70520 }, { "epoch": 1.9930071905858422, "grad_norm": 5.429287433624268, "learning_rate": 2.777041698296362e-05, "loss": 0.868562889099121, "step": 70540 }, { "epoch": 1.993572266094057, "grad_norm": 3.7928521633148193, "learning_rate": 2.774252426579649e-05, "loss": 0.7959251403808594, "step": 70560 }, { "epoch": 1.9941373416022716, "grad_norm": 3.0282013416290283, "learning_rate": 2.771464018426615e-05, "loss": 0.8628267288208008, "step": 70580 }, { "epoch": 1.9947024171104863, "grad_norm": 3.453432321548462, "learning_rate": 2.7686764749191313e-05, "loss": 0.7677070140838623, "step": 70600 }, { "epoch": 1.995267492618701, "grad_norm": 3.4580535888671875, "learning_rate": 2.76588979713873e-05, "loss": 0.8203208923339844, "step": 70620 }, { "epoch": 1.995832568126916, "grad_norm": 7.595881462097168, "learning_rate": 2.7631039861666082e-05, "loss": 0.8177145004272461, "step": 70640 }, { "epoch": 1.9963976436351307, "grad_norm": 2.0054547786712646, "learning_rate": 2.7603190430836257e-05, "loss": 0.800590705871582, "step": 70660 }, { "epoch": 1.9969627191433457, "grad_norm": 3.232069969177246, "learning_rate": 2.7575349689703124e-05, "loss": 0.8690615653991699, "step": 70680 }, { "epoch": 1.9975277946515604, "grad_norm": 3.4077248573303223, "learning_rate": 2.7547517649068534e-05, "loss": 0.8747376441955567, "step": 70700 }, { "epoch": 1.998092870159775, "grad_norm": 4.6290602684021, "learning_rate": 2.751969431973098e-05, "loss": 0.8610843658447266, "step": 70720 }, { "epoch": 1.9986579456679898, "grad_norm": 4.498955726623535, "learning_rate": 2.749187971248558e-05, "loss": 0.8646313667297363, "step": 70740 }, { "epoch": 1.9992230211762045, "grad_norm": 3.680103302001953, "learning_rate": 2.7464073838124105e-05, "loss": 0.8384143829345703, "step": 70760 }, { "epoch": 1.9997880966844195, "grad_norm": 2.9979000091552734, "learning_rate": 2.743627670743488e-05, "loss": 0.7924168109893799, "step": 70780 }, { "epoch": 2.000339045304929, "grad_norm": 3.3205196857452393, "learning_rate": 2.7408488331202877e-05, "loss": 0.7878951072692871, "step": 70800 }, { "epoch": 2.0009041208131437, "grad_norm": 4.046046733856201, "learning_rate": 2.738070872020962e-05, "loss": 0.7735122680664063, "step": 70820 }, { "epoch": 2.0014691963213584, "grad_norm": 4.396385192871094, "learning_rate": 2.7352937885233315e-05, "loss": 0.8575838088989258, "step": 70840 }, { "epoch": 2.002034271829573, "grad_norm": 4.224153995513916, "learning_rate": 2.73251758370487e-05, "loss": 0.8549278259277344, "step": 70860 }, { "epoch": 2.002599347337788, "grad_norm": 3.984555244445801, "learning_rate": 2.7297422586427114e-05, "loss": 0.8392295837402344, "step": 70880 }, { "epoch": 2.0031644228460026, "grad_norm": 2.4817724227905273, "learning_rate": 2.7269678144136456e-05, "loss": 0.7704484939575196, "step": 70900 }, { "epoch": 2.0037294983542178, "grad_norm": 3.3903820514678955, "learning_rate": 2.724194252094131e-05, "loss": 0.7723571300506592, "step": 70920 }, { "epoch": 2.0042945738624325, "grad_norm": 3.284292697906494, "learning_rate": 2.7214215727602744e-05, "loss": 0.7979929924011231, "step": 70940 }, { "epoch": 2.004859649370647, "grad_norm": 2.7665677070617676, "learning_rate": 2.718649777487842e-05, "loss": 0.7637144565582276, "step": 70960 }, { "epoch": 2.005424724878862, "grad_norm": 3.764000415802002, "learning_rate": 2.715878867352255e-05, "loss": 0.8668987274169921, "step": 70980 }, { "epoch": 2.0059898003870766, "grad_norm": 3.5673625469207764, "learning_rate": 2.7131088434285978e-05, "loss": 0.8536218643188477, "step": 71000 }, { "epoch": 2.0065548758952914, "grad_norm": 2.6214969158172607, "learning_rate": 2.7103397067916058e-05, "loss": 0.8078701972961426, "step": 71020 }, { "epoch": 2.007119951403506, "grad_norm": 2.7767066955566406, "learning_rate": 2.7075714585156697e-05, "loss": 0.7487697601318359, "step": 71040 }, { "epoch": 2.0076850269117212, "grad_norm": 2.683960437774658, "learning_rate": 2.7048040996748364e-05, "loss": 0.833707618713379, "step": 71060 }, { "epoch": 2.008250102419936, "grad_norm": 3.193814277648926, "learning_rate": 2.7020376313428114e-05, "loss": 0.8490534782409668, "step": 71080 }, { "epoch": 2.0088151779281507, "grad_norm": 3.3310563564300537, "learning_rate": 2.6992720545929494e-05, "loss": 0.8190691947937012, "step": 71100 }, { "epoch": 2.0093802534363654, "grad_norm": 3.9876902103424072, "learning_rate": 2.696507370498263e-05, "loss": 0.8046100616455079, "step": 71120 }, { "epoch": 2.00994532894458, "grad_norm": 4.3494744300842285, "learning_rate": 2.6937435801314137e-05, "loss": 0.8185254096984863, "step": 71140 }, { "epoch": 2.010510404452795, "grad_norm": 4.096269130706787, "learning_rate": 2.690980684564723e-05, "loss": 0.8600902557373047, "step": 71160 }, { "epoch": 2.01107547996101, "grad_norm": 2.292384147644043, "learning_rate": 2.6882186848701602e-05, "loss": 0.8385150909423829, "step": 71180 }, { "epoch": 2.0116405554692247, "grad_norm": 2.992699146270752, "learning_rate": 2.6854575821193482e-05, "loss": 0.7730217456817627, "step": 71200 }, { "epoch": 2.0122056309774394, "grad_norm": 4.739639759063721, "learning_rate": 2.6826973773835608e-05, "loss": 0.790595006942749, "step": 71220 }, { "epoch": 2.012770706485654, "grad_norm": 5.157436847686768, "learning_rate": 2.6799380717337263e-05, "loss": 0.7783360958099366, "step": 71240 }, { "epoch": 2.013335781993869, "grad_norm": 3.992812395095825, "learning_rate": 2.6771796662404243e-05, "loss": 0.850045108795166, "step": 71260 }, { "epoch": 2.0139008575020836, "grad_norm": 4.526637554168701, "learning_rate": 2.6744221619738813e-05, "loss": 0.8837390899658203, "step": 71280 }, { "epoch": 2.0144659330102983, "grad_norm": 2.845777988433838, "learning_rate": 2.6716655600039774e-05, "loss": 0.8386824607849122, "step": 71300 }, { "epoch": 2.0150310085185135, "grad_norm": 3.216442823410034, "learning_rate": 2.6689098614002382e-05, "loss": 0.806765365600586, "step": 71320 }, { "epoch": 2.015596084026728, "grad_norm": 2.7732958793640137, "learning_rate": 2.666155067231847e-05, "loss": 0.8408016204833985, "step": 71340 }, { "epoch": 2.016161159534943, "grad_norm": 3.8444488048553467, "learning_rate": 2.6634011785676282e-05, "loss": 0.8009928703308106, "step": 71360 }, { "epoch": 2.0167262350431576, "grad_norm": 2.962474822998047, "learning_rate": 2.6606481964760598e-05, "loss": 0.7986786842346192, "step": 71380 }, { "epoch": 2.0172913105513723, "grad_norm": 4.612185478210449, "learning_rate": 2.657896122025263e-05, "loss": 0.794724416732788, "step": 71400 }, { "epoch": 2.017856386059587, "grad_norm": 3.5512142181396484, "learning_rate": 2.6551449562830133e-05, "loss": 0.8208184242248535, "step": 71420 }, { "epoch": 2.0184214615678018, "grad_norm": 3.7502806186676025, "learning_rate": 2.6523947003167297e-05, "loss": 0.8387323379516601, "step": 71440 }, { "epoch": 2.018986537076017, "grad_norm": 3.1156423091888428, "learning_rate": 2.6496453551934784e-05, "loss": 0.8146828651428223, "step": 71460 }, { "epoch": 2.0195516125842317, "grad_norm": 2.7358696460723877, "learning_rate": 2.6468969219799716e-05, "loss": 0.8531863212585449, "step": 71480 }, { "epoch": 2.0201166880924464, "grad_norm": 6.008853912353516, "learning_rate": 2.6441494017425715e-05, "loss": 0.8948517799377441, "step": 71500 }, { "epoch": 2.020681763600661, "grad_norm": 2.98608136177063, "learning_rate": 2.641402795547282e-05, "loss": 0.814241886138916, "step": 71520 }, { "epoch": 2.021246839108876, "grad_norm": 3.239555597305298, "learning_rate": 2.6386571044597535e-05, "loss": 0.8257452011108398, "step": 71540 }, { "epoch": 2.0218119146170905, "grad_norm": 3.858656167984009, "learning_rate": 2.6359123295452803e-05, "loss": 0.8839638710021973, "step": 71560 }, { "epoch": 2.0223769901253057, "grad_norm": 4.152698516845703, "learning_rate": 2.6331684718688032e-05, "loss": 0.8371783256530761, "step": 71580 }, { "epoch": 2.0229420656335204, "grad_norm": 3.6100833415985107, "learning_rate": 2.63042553249491e-05, "loss": 0.812370777130127, "step": 71600 }, { "epoch": 2.023507141141735, "grad_norm": 4.486398220062256, "learning_rate": 2.627683512487825e-05, "loss": 0.7997956275939941, "step": 71620 }, { "epoch": 2.02407221664995, "grad_norm": 3.821671962738037, "learning_rate": 2.6249424129114197e-05, "loss": 0.8448203086853028, "step": 71640 }, { "epoch": 2.0246372921581646, "grad_norm": 4.414091110229492, "learning_rate": 2.6222022348292102e-05, "loss": 0.8802535057067871, "step": 71660 }, { "epoch": 2.0252023676663793, "grad_norm": 2.8497278690338135, "learning_rate": 2.6194629793043522e-05, "loss": 0.7407563686370849, "step": 71680 }, { "epoch": 2.025767443174594, "grad_norm": 3.157334327697754, "learning_rate": 2.6167246473996437e-05, "loss": 0.901551342010498, "step": 71700 }, { "epoch": 2.026332518682809, "grad_norm": 3.460693120956421, "learning_rate": 2.6139872401775235e-05, "loss": 0.8783346176147461, "step": 71720 }, { "epoch": 2.026897594191024, "grad_norm": 2.0319983959198, "learning_rate": 2.611250758700077e-05, "loss": 0.7201312065124512, "step": 71740 }, { "epoch": 2.0274626696992386, "grad_norm": 3.005199909210205, "learning_rate": 2.608515204029025e-05, "loss": 0.8105596542358399, "step": 71760 }, { "epoch": 2.0280277452074533, "grad_norm": 4.721499443054199, "learning_rate": 2.6057805772257292e-05, "loss": 0.7772791385650635, "step": 71780 }, { "epoch": 2.028592820715668, "grad_norm": 3.2788822650909424, "learning_rate": 2.603046879351192e-05, "loss": 0.8092229843139649, "step": 71800 }, { "epoch": 2.0291578962238828, "grad_norm": 2.5344717502593994, "learning_rate": 2.6003141114660584e-05, "loss": 0.7973676681518554, "step": 71820 }, { "epoch": 2.029722971732098, "grad_norm": 3.7249159812927246, "learning_rate": 2.597582274630609e-05, "loss": 0.7413341522216796, "step": 71840 }, { "epoch": 2.0302880472403126, "grad_norm": 3.089042901992798, "learning_rate": 2.5948513699047627e-05, "loss": 0.8339714050292969, "step": 71860 }, { "epoch": 2.0308531227485274, "grad_norm": 3.518171787261963, "learning_rate": 2.5921213983480774e-05, "loss": 0.7645380973815918, "step": 71880 }, { "epoch": 2.031418198256742, "grad_norm": 1.956613302230835, "learning_rate": 2.5893923610197513e-05, "loss": 0.7852834701538086, "step": 71900 }, { "epoch": 2.031983273764957, "grad_norm": 4.171185493469238, "learning_rate": 2.5866642589786204e-05, "loss": 0.8100605964660644, "step": 71920 }, { "epoch": 2.0325483492731715, "grad_norm": 3.5039548873901367, "learning_rate": 2.583937093283154e-05, "loss": 0.8792890548706055, "step": 71940 }, { "epoch": 2.0331134247813862, "grad_norm": 6.393611431121826, "learning_rate": 2.5812108649914603e-05, "loss": 0.8995626449584961, "step": 71960 }, { "epoch": 2.0336785002896014, "grad_norm": 4.4137678146362305, "learning_rate": 2.5784855751612813e-05, "loss": 0.7985224723815918, "step": 71980 }, { "epoch": 2.034243575797816, "grad_norm": 3.493298053741455, "learning_rate": 2.5757612248500017e-05, "loss": 0.8728242874145508, "step": 72000 }, { "epoch": 2.034808651306031, "grad_norm": 4.145141124725342, "learning_rate": 2.573037815114635e-05, "loss": 0.8495089530944824, "step": 72020 }, { "epoch": 2.0353737268142456, "grad_norm": 3.6942384243011475, "learning_rate": 2.5703153470118308e-05, "loss": 0.7895363330841064, "step": 72040 }, { "epoch": 2.0359388023224603, "grad_norm": 3.1950531005859375, "learning_rate": 2.5675938215978734e-05, "loss": 0.9092183113098145, "step": 72060 }, { "epoch": 2.036503877830675, "grad_norm": 3.525190591812134, "learning_rate": 2.5648732399286867e-05, "loss": 0.7372456550598144, "step": 72080 }, { "epoch": 2.0370689533388897, "grad_norm": 3.9033164978027344, "learning_rate": 2.5621536030598215e-05, "loss": 0.7490850925445557, "step": 72100 }, { "epoch": 2.037634028847105, "grad_norm": 3.9693572521209717, "learning_rate": 2.5594349120464657e-05, "loss": 0.7532715320587158, "step": 72120 }, { "epoch": 2.0381991043553196, "grad_norm": 2.253523349761963, "learning_rate": 2.5567171679434355e-05, "loss": 0.8644585609436035, "step": 72140 }, { "epoch": 2.0387641798635343, "grad_norm": 3.723098039627075, "learning_rate": 2.5540003718051887e-05, "loss": 0.8581296920776367, "step": 72160 }, { "epoch": 2.039329255371749, "grad_norm": 3.235536813735962, "learning_rate": 2.5512845246858073e-05, "loss": 0.7586436748504639, "step": 72180 }, { "epoch": 2.0398943308799637, "grad_norm": 2.1501338481903076, "learning_rate": 2.548569627639008e-05, "loss": 0.8622268676757813, "step": 72200 }, { "epoch": 2.0404594063881785, "grad_norm": 5.154755592346191, "learning_rate": 2.545855681718137e-05, "loss": 0.8820239067077636, "step": 72220 }, { "epoch": 2.041024481896393, "grad_norm": 5.0977091789245605, "learning_rate": 2.543142687976175e-05, "loss": 0.7576107501983642, "step": 72240 }, { "epoch": 2.0415895574046083, "grad_norm": 4.324434757232666, "learning_rate": 2.5404306474657334e-05, "loss": 0.8812179565429688, "step": 72260 }, { "epoch": 2.042154632912823, "grad_norm": 4.837496280670166, "learning_rate": 2.537719561239049e-05, "loss": 0.8669064521789551, "step": 72280 }, { "epoch": 2.042719708421038, "grad_norm": 4.475560188293457, "learning_rate": 2.535009430347991e-05, "loss": 0.8012311935424805, "step": 72300 }, { "epoch": 2.0432847839292525, "grad_norm": 3.6126341819763184, "learning_rate": 2.53230025584406e-05, "loss": 0.7884466648101807, "step": 72320 }, { "epoch": 2.043849859437467, "grad_norm": 5.756821155548096, "learning_rate": 2.5295920387783834e-05, "loss": 0.8631237983703614, "step": 72340 }, { "epoch": 2.044414934945682, "grad_norm": 2.602141857147217, "learning_rate": 2.526884780201716e-05, "loss": 0.7739677429199219, "step": 72360 }, { "epoch": 2.044980010453897, "grad_norm": 3.8331987857818604, "learning_rate": 2.5241784811644398e-05, "loss": 0.8455545425415039, "step": 72380 }, { "epoch": 2.045545085962112, "grad_norm": 4.538423538208008, "learning_rate": 2.521473142716572e-05, "loss": 0.7842369556427002, "step": 72400 }, { "epoch": 2.0461101614703265, "grad_norm": 4.185757637023926, "learning_rate": 2.5187687659077496e-05, "loss": 0.8226768493652343, "step": 72420 }, { "epoch": 2.0466752369785413, "grad_norm": 4.217533111572266, "learning_rate": 2.516065351787238e-05, "loss": 0.8060593605041504, "step": 72440 }, { "epoch": 2.047240312486756, "grad_norm": 3.9197916984558105, "learning_rate": 2.5133629014039285e-05, "loss": 0.908632469177246, "step": 72460 }, { "epoch": 2.0478053879949707, "grad_norm": 6.540335655212402, "learning_rate": 2.5106614158063435e-05, "loss": 0.7472723007202149, "step": 72480 }, { "epoch": 2.0483704635031854, "grad_norm": 3.3220317363739014, "learning_rate": 2.507960896042625e-05, "loss": 0.8102608680725097, "step": 72500 }, { "epoch": 2.0489355390114006, "grad_norm": 3.9183833599090576, "learning_rate": 2.5052613431605432e-05, "loss": 0.7592677593231201, "step": 72520 }, { "epoch": 2.0495006145196153, "grad_norm": 2.83996319770813, "learning_rate": 2.5025627582074916e-05, "loss": 0.8396099090576172, "step": 72540 }, { "epoch": 2.05006569002783, "grad_norm": 3.253230571746826, "learning_rate": 2.4998651422304892e-05, "loss": 0.8379338264465332, "step": 72560 }, { "epoch": 2.0506307655360447, "grad_norm": 4.34168004989624, "learning_rate": 2.4971684962761822e-05, "loss": 0.7978246212005615, "step": 72580 }, { "epoch": 2.0511958410442594, "grad_norm": 3.67645001411438, "learning_rate": 2.4944728213908354e-05, "loss": 0.912332820892334, "step": 72600 }, { "epoch": 2.051760916552474, "grad_norm": 3.832145929336548, "learning_rate": 2.4917781186203377e-05, "loss": 0.8032338142395019, "step": 72620 }, { "epoch": 2.0523259920606893, "grad_norm": 3.943145751953125, "learning_rate": 2.4890843890102004e-05, "loss": 0.7282727241516114, "step": 72640 }, { "epoch": 2.052891067568904, "grad_norm": 5.825082302093506, "learning_rate": 2.4863916336055637e-05, "loss": 0.8312736511230469, "step": 72660 }, { "epoch": 2.0534561430771188, "grad_norm": 3.743618965148926, "learning_rate": 2.4836998534511814e-05, "loss": 0.7726634025573731, "step": 72680 }, { "epoch": 2.0540212185853335, "grad_norm": 2.8612282276153564, "learning_rate": 2.4810090495914322e-05, "loss": 0.7910595893859863, "step": 72700 }, { "epoch": 2.054586294093548, "grad_norm": 3.108635663986206, "learning_rate": 2.478319223070315e-05, "loss": 0.8123208045959472, "step": 72720 }, { "epoch": 2.055151369601763, "grad_norm": 3.200596809387207, "learning_rate": 2.475630374931454e-05, "loss": 0.8442198753356933, "step": 72740 }, { "epoch": 2.0557164451099776, "grad_norm": 3.182119846343994, "learning_rate": 2.4729425062180888e-05, "loss": 0.7685138702392578, "step": 72760 }, { "epoch": 2.056281520618193, "grad_norm": 3.6463849544525146, "learning_rate": 2.4702556179730806e-05, "loss": 0.8075490951538086, "step": 72780 }, { "epoch": 2.0568465961264075, "grad_norm": 2.605071544647217, "learning_rate": 2.4675697112389085e-05, "loss": 0.7133950233459473, "step": 72800 }, { "epoch": 2.0574116716346222, "grad_norm": 4.450802326202393, "learning_rate": 2.4648847870576752e-05, "loss": 0.8063350677490234, "step": 72820 }, { "epoch": 2.057976747142837, "grad_norm": 2.7261478900909424, "learning_rate": 2.4622008464710987e-05, "loss": 0.7897323131561279, "step": 72840 }, { "epoch": 2.0585418226510517, "grad_norm": 3.0467467308044434, "learning_rate": 2.459517890520516e-05, "loss": 0.7960954189300538, "step": 72860 }, { "epoch": 2.0591068981592664, "grad_norm": 3.203221082687378, "learning_rate": 2.4568359202468794e-05, "loss": 0.8086041450500489, "step": 72880 }, { "epoch": 2.059671973667481, "grad_norm": 4.884363651275635, "learning_rate": 2.454154936690764e-05, "loss": 0.7751566410064697, "step": 72900 }, { "epoch": 2.0602370491756963, "grad_norm": 3.1903016567230225, "learning_rate": 2.4514749408923622e-05, "loss": 0.8579310417175293, "step": 72920 }, { "epoch": 2.060802124683911, "grad_norm": 4.172165393829346, "learning_rate": 2.448795933891478e-05, "loss": 0.8357752799987793, "step": 72940 }, { "epoch": 2.0613672001921257, "grad_norm": 3.302729845046997, "learning_rate": 2.446117916727532e-05, "loss": 0.8376407623291016, "step": 72960 }, { "epoch": 2.0619322757003404, "grad_norm": 3.584409475326538, "learning_rate": 2.4434408904395685e-05, "loss": 0.8227651596069336, "step": 72980 }, { "epoch": 2.062497351208555, "grad_norm": 3.7329678535461426, "learning_rate": 2.4407648560662388e-05, "loss": 0.8501964569091797, "step": 73000 }, { "epoch": 2.06306242671677, "grad_norm": 3.3883302211761475, "learning_rate": 2.4380898146458133e-05, "loss": 0.8570172309875488, "step": 73020 }, { "epoch": 2.0636275022249846, "grad_norm": 3.2509305477142334, "learning_rate": 2.4354157672161732e-05, "loss": 0.8787705421447753, "step": 73040 }, { "epoch": 2.0641925777331998, "grad_norm": 3.012411594390869, "learning_rate": 2.4327427148148218e-05, "loss": 0.6884623050689698, "step": 73060 }, { "epoch": 2.0647576532414145, "grad_norm": 2.4112913608551025, "learning_rate": 2.4300706584788707e-05, "loss": 0.755750322341919, "step": 73080 }, { "epoch": 2.065322728749629, "grad_norm": 4.157016277313232, "learning_rate": 2.4273995992450444e-05, "loss": 0.8309800148010253, "step": 73100 }, { "epoch": 2.065887804257844, "grad_norm": 3.2864930629730225, "learning_rate": 2.4247295381496816e-05, "loss": 0.8421950340270996, "step": 73120 }, { "epoch": 2.0664528797660586, "grad_norm": 4.354990005493164, "learning_rate": 2.422060476228738e-05, "loss": 0.8071442604064941, "step": 73140 }, { "epoch": 2.0670179552742733, "grad_norm": 4.510962963104248, "learning_rate": 2.4193924145177755e-05, "loss": 0.7803591251373291, "step": 73160 }, { "epoch": 2.0675830307824885, "grad_norm": 2.6988565921783447, "learning_rate": 2.416725354051971e-05, "loss": 0.7612102508544922, "step": 73180 }, { "epoch": 2.0681481062907032, "grad_norm": 4.624034404754639, "learning_rate": 2.4140592958661097e-05, "loss": 0.8239178657531738, "step": 73200 }, { "epoch": 2.068713181798918, "grad_norm": 5.212399959564209, "learning_rate": 2.4113942409945933e-05, "loss": 0.8285467147827148, "step": 73220 }, { "epoch": 2.0692782573071327, "grad_norm": 3.752821922302246, "learning_rate": 2.4087301904714327e-05, "loss": 0.7472661018371582, "step": 73240 }, { "epoch": 2.0698433328153474, "grad_norm": 3.527466058731079, "learning_rate": 2.4060671453302467e-05, "loss": 0.8218225479125977, "step": 73260 }, { "epoch": 2.070408408323562, "grad_norm": 4.887964725494385, "learning_rate": 2.403405106604265e-05, "loss": 0.7609794616699219, "step": 73280 }, { "epoch": 2.070973483831777, "grad_norm": 2.5749242305755615, "learning_rate": 2.4007440753263255e-05, "loss": 0.775443696975708, "step": 73300 }, { "epoch": 2.071538559339992, "grad_norm": 3.5506350994110107, "learning_rate": 2.39808405252888e-05, "loss": 0.8449922561645508, "step": 73320 }, { "epoch": 2.0721036348482067, "grad_norm": 2.9802451133728027, "learning_rate": 2.3954250392439843e-05, "loss": 0.778253698348999, "step": 73340 }, { "epoch": 2.0726687103564214, "grad_norm": 4.198441505432129, "learning_rate": 2.3927670365033032e-05, "loss": 0.8634803771972657, "step": 73360 }, { "epoch": 2.073233785864636, "grad_norm": 3.7611658573150635, "learning_rate": 2.3901100453381097e-05, "loss": 0.8303658485412597, "step": 73380 }, { "epoch": 2.073798861372851, "grad_norm": 4.294368743896484, "learning_rate": 2.3874540667792877e-05, "loss": 0.8612006187438965, "step": 73400 }, { "epoch": 2.0743639368810656, "grad_norm": 2.8879318237304688, "learning_rate": 2.3847991018573242e-05, "loss": 0.7820961952209473, "step": 73420 }, { "epoch": 2.0749290123892807, "grad_norm": 3.0128917694091797, "learning_rate": 2.3821451516023135e-05, "loss": 0.835510540008545, "step": 73440 }, { "epoch": 2.0754940878974955, "grad_norm": 3.72113037109375, "learning_rate": 2.3794922170439555e-05, "loss": 0.8086554527282714, "step": 73460 }, { "epoch": 2.07605916340571, "grad_norm": 2.348571300506592, "learning_rate": 2.3768402992115606e-05, "loss": 0.9164802551269531, "step": 73480 }, { "epoch": 2.076624238913925, "grad_norm": 3.9318296909332275, "learning_rate": 2.3741893991340403e-05, "loss": 0.75846266746521, "step": 73500 }, { "epoch": 2.0771893144221396, "grad_norm": 3.3657467365264893, "learning_rate": 2.3715395178399114e-05, "loss": 0.7219085216522216, "step": 73520 }, { "epoch": 2.0777543899303543, "grad_norm": 3.2938055992126465, "learning_rate": 2.3688906563572954e-05, "loss": 0.8739019393920898, "step": 73540 }, { "epoch": 2.078319465438569, "grad_norm": 4.353974342346191, "learning_rate": 2.3662428157139203e-05, "loss": 0.8056146621704101, "step": 73560 }, { "epoch": 2.078884540946784, "grad_norm": 2.334529161453247, "learning_rate": 2.3635959969371203e-05, "loss": 0.8255596160888672, "step": 73580 }, { "epoch": 2.079449616454999, "grad_norm": 5.553468704223633, "learning_rate": 2.360950201053826e-05, "loss": 0.8234426498413085, "step": 73600 }, { "epoch": 2.0800146919632136, "grad_norm": 3.947049617767334, "learning_rate": 2.3583054290905753e-05, "loss": 0.7829229354858398, "step": 73620 }, { "epoch": 2.0805797674714284, "grad_norm": 3.3127424716949463, "learning_rate": 2.355661682073508e-05, "loss": 0.7952718257904052, "step": 73640 }, { "epoch": 2.081144842979643, "grad_norm": 4.069746494293213, "learning_rate": 2.353018961028368e-05, "loss": 0.7350387096405029, "step": 73660 }, { "epoch": 2.081709918487858, "grad_norm": 4.151239395141602, "learning_rate": 2.3503772669804998e-05, "loss": 0.8097084999084473, "step": 73680 }, { "epoch": 2.0822749939960725, "grad_norm": 3.334291458129883, "learning_rate": 2.3477366009548464e-05, "loss": 0.797877836227417, "step": 73700 }, { "epoch": 2.0828400695042877, "grad_norm": 2.6008992195129395, "learning_rate": 2.345096963975959e-05, "loss": 0.7664985179901123, "step": 73720 }, { "epoch": 2.0834051450125024, "grad_norm": 3.3045592308044434, "learning_rate": 2.3424583570679835e-05, "loss": 0.8873014450073242, "step": 73740 }, { "epoch": 2.083970220520717, "grad_norm": 3.668668270111084, "learning_rate": 2.3398207812546687e-05, "loss": 0.7924921989440918, "step": 73760 }, { "epoch": 2.084535296028932, "grad_norm": 3.6165060997009277, "learning_rate": 2.33718423755936e-05, "loss": 0.8051892280578613, "step": 73780 }, { "epoch": 2.0851003715371466, "grad_norm": 3.5150516033172607, "learning_rate": 2.33454872700501e-05, "loss": 0.8295926094055176, "step": 73800 }, { "epoch": 2.0856654470453613, "grad_norm": 3.263288736343384, "learning_rate": 2.3319142506141617e-05, "loss": 0.8044112205505372, "step": 73820 }, { "epoch": 2.086230522553576, "grad_norm": 4.593034267425537, "learning_rate": 2.329280809408963e-05, "loss": 0.8314883232116699, "step": 73840 }, { "epoch": 2.086795598061791, "grad_norm": 2.3773975372314453, "learning_rate": 2.3266484044111542e-05, "loss": 0.8355743408203125, "step": 73860 }, { "epoch": 2.087360673570006, "grad_norm": 3.0787508487701416, "learning_rate": 2.3240170366420804e-05, "loss": 0.8644227981567383, "step": 73880 }, { "epoch": 2.0879257490782206, "grad_norm": 3.480257987976074, "learning_rate": 2.3213867071226826e-05, "loss": 0.7980453491210937, "step": 73900 }, { "epoch": 2.0884908245864353, "grad_norm": 4.239839553833008, "learning_rate": 2.318757416873495e-05, "loss": 0.7733752250671386, "step": 73920 }, { "epoch": 2.08905590009465, "grad_norm": 4.913479328155518, "learning_rate": 2.3161291669146518e-05, "loss": 0.7853944778442383, "step": 73940 }, { "epoch": 2.0896209756028647, "grad_norm": 3.393181800842285, "learning_rate": 2.3135019582658802e-05, "loss": 0.7806739330291748, "step": 73960 }, { "epoch": 2.09018605111108, "grad_norm": 5.384422302246094, "learning_rate": 2.3108757919465107e-05, "loss": 0.7784559249877929, "step": 73980 }, { "epoch": 2.0907511266192946, "grad_norm": 3.8818657398223877, "learning_rate": 2.3082506689754624e-05, "loss": 0.7654753208160401, "step": 74000 }, { "epoch": 2.0913162021275093, "grad_norm": 2.531581163406372, "learning_rate": 2.3056265903712515e-05, "loss": 0.8424041748046875, "step": 74020 }, { "epoch": 2.091881277635724, "grad_norm": 3.1646361351013184, "learning_rate": 2.3030035571519883e-05, "loss": 0.7737356662750244, "step": 74040 }, { "epoch": 2.092446353143939, "grad_norm": 4.133730411529541, "learning_rate": 2.3003815703353814e-05, "loss": 0.7793585777282714, "step": 74060 }, { "epoch": 2.0930114286521535, "grad_norm": 5.985233783721924, "learning_rate": 2.29776063093873e-05, "loss": 0.8327739715576172, "step": 74080 }, { "epoch": 2.0935765041603682, "grad_norm": 3.5395054817199707, "learning_rate": 2.2951407399789266e-05, "loss": 0.8233748435974121, "step": 74100 }, { "epoch": 2.0941415796685834, "grad_norm": 3.645050525665283, "learning_rate": 2.2925218984724554e-05, "loss": 0.7462948799133301, "step": 74120 }, { "epoch": 2.094706655176798, "grad_norm": 3.3604021072387695, "learning_rate": 2.289904107435401e-05, "loss": 0.824433422088623, "step": 74140 }, { "epoch": 2.095271730685013, "grad_norm": 4.094882965087891, "learning_rate": 2.2872873678834334e-05, "loss": 0.7891686916351318, "step": 74160 }, { "epoch": 2.0958368061932275, "grad_norm": 4.565607070922852, "learning_rate": 2.2846716808318154e-05, "loss": 0.8008849143981933, "step": 74180 }, { "epoch": 2.0964018817014423, "grad_norm": 5.301302433013916, "learning_rate": 2.2820570472954007e-05, "loss": 0.7918015480041504, "step": 74200 }, { "epoch": 2.096966957209657, "grad_norm": 4.186741352081299, "learning_rate": 2.279443468288639e-05, "loss": 0.7772294998168945, "step": 74220 }, { "epoch": 2.097532032717872, "grad_norm": 3.538285493850708, "learning_rate": 2.27683094482557e-05, "loss": 0.8333602905273437, "step": 74240 }, { "epoch": 2.098097108226087, "grad_norm": 3.1098556518554688, "learning_rate": 2.2742194779198182e-05, "loss": 0.7013570308685303, "step": 74260 }, { "epoch": 2.0986621837343016, "grad_norm": 4.018774032592773, "learning_rate": 2.2716090685846037e-05, "loss": 0.7289543628692627, "step": 74280 }, { "epoch": 2.0992272592425163, "grad_norm": 3.5064494609832764, "learning_rate": 2.2689997178327317e-05, "loss": 0.8456475257873535, "step": 74300 }, { "epoch": 2.099792334750731, "grad_norm": 3.9402101039886475, "learning_rate": 2.266391426676603e-05, "loss": 0.7117990016937256, "step": 74320 }, { "epoch": 2.1003574102589457, "grad_norm": 3.8007237911224365, "learning_rate": 2.263784196128202e-05, "loss": 0.8025959968566895, "step": 74340 }, { "epoch": 2.1009224857671605, "grad_norm": 3.660593271255493, "learning_rate": 2.2611780271991012e-05, "loss": 0.8621037483215332, "step": 74360 }, { "epoch": 2.1014875612753756, "grad_norm": 4.064393043518066, "learning_rate": 2.2585729209004674e-05, "loss": 0.7503808021545411, "step": 74380 }, { "epoch": 2.1020526367835903, "grad_norm": 3.1919050216674805, "learning_rate": 2.2559688782430487e-05, "loss": 0.7356378555297851, "step": 74400 }, { "epoch": 2.102617712291805, "grad_norm": 3.877657413482666, "learning_rate": 2.2533659002371833e-05, "loss": 0.7916053771972656, "step": 74420 }, { "epoch": 2.1031827878000198, "grad_norm": 2.4133853912353516, "learning_rate": 2.2507639878927933e-05, "loss": 0.8003324508666992, "step": 74440 }, { "epoch": 2.1037478633082345, "grad_norm": 3.5922763347625732, "learning_rate": 2.248163142219394e-05, "loss": 0.8075864791870118, "step": 74460 }, { "epoch": 2.104312938816449, "grad_norm": 3.5037267208099365, "learning_rate": 2.2455633642260804e-05, "loss": 0.8158896446228028, "step": 74480 }, { "epoch": 2.104878014324664, "grad_norm": 3.0213239192962646, "learning_rate": 2.2429646549215362e-05, "loss": 0.770880126953125, "step": 74500 }, { "epoch": 2.105443089832879, "grad_norm": 3.306939125061035, "learning_rate": 2.2403670153140272e-05, "loss": 0.750935173034668, "step": 74520 }, { "epoch": 2.106008165341094, "grad_norm": 3.5922815799713135, "learning_rate": 2.237770446411409e-05, "loss": 0.7784481048583984, "step": 74540 }, { "epoch": 2.1065732408493085, "grad_norm": 2.8094561100006104, "learning_rate": 2.235174949221122e-05, "loss": 0.7377644538879394, "step": 74560 }, { "epoch": 2.1071383163575232, "grad_norm": 4.142202377319336, "learning_rate": 2.2325805247501858e-05, "loss": 0.7969454765319824, "step": 74580 }, { "epoch": 2.107703391865738, "grad_norm": 3.4965665340423584, "learning_rate": 2.229987174005206e-05, "loss": 0.7738646030426025, "step": 74600 }, { "epoch": 2.1082684673739527, "grad_norm": 4.115969657897949, "learning_rate": 2.2273948979923707e-05, "loss": 0.874461555480957, "step": 74620 }, { "epoch": 2.108833542882168, "grad_norm": 4.536371231079102, "learning_rate": 2.224803697717456e-05, "loss": 0.7493422031402588, "step": 74640 }, { "epoch": 2.1093986183903826, "grad_norm": 3.062164068222046, "learning_rate": 2.222213574185815e-05, "loss": 0.8251254081726074, "step": 74660 }, { "epoch": 2.1099636938985973, "grad_norm": 3.522793769836426, "learning_rate": 2.2196245284023848e-05, "loss": 0.7773987293243408, "step": 74680 }, { "epoch": 2.110528769406812, "grad_norm": 3.0648012161254883, "learning_rate": 2.2170365613716832e-05, "loss": 0.725884199142456, "step": 74700 }, { "epoch": 2.1110938449150267, "grad_norm": 3.7966973781585693, "learning_rate": 2.214449674097813e-05, "loss": 0.7941681861877441, "step": 74720 }, { "epoch": 2.1116589204232414, "grad_norm": 3.082986831665039, "learning_rate": 2.2118638675844555e-05, "loss": 0.8172029495239258, "step": 74740 }, { "epoch": 2.112223995931456, "grad_norm": 4.305399417877197, "learning_rate": 2.209279142834872e-05, "loss": 0.817319679260254, "step": 74760 }, { "epoch": 2.1127890714396713, "grad_norm": 3.0024173259735107, "learning_rate": 2.2066955008519035e-05, "loss": 0.829066276550293, "step": 74780 }, { "epoch": 2.113354146947886, "grad_norm": 2.8030574321746826, "learning_rate": 2.2041129426379764e-05, "loss": 0.8235011100769043, "step": 74800 }, { "epoch": 2.1139192224561008, "grad_norm": 3.2236108779907227, "learning_rate": 2.2015314691950905e-05, "loss": 0.7627852439880372, "step": 74820 }, { "epoch": 2.1144842979643155, "grad_norm": 3.167757511138916, "learning_rate": 2.198951081524827e-05, "loss": 0.7594892501831054, "step": 74840 }, { "epoch": 2.11504937347253, "grad_norm": 3.0601868629455566, "learning_rate": 2.196371780628344e-05, "loss": 0.8603424072265625, "step": 74860 }, { "epoch": 2.115614448980745, "grad_norm": 3.6692628860473633, "learning_rate": 2.1937935675063813e-05, "loss": 0.7958740711212158, "step": 74880 }, { "epoch": 2.1161795244889596, "grad_norm": 4.337457180023193, "learning_rate": 2.1912164431592575e-05, "loss": 0.8324475288391113, "step": 74900 }, { "epoch": 2.116744599997175, "grad_norm": 5.0509867668151855, "learning_rate": 2.1886404085868638e-05, "loss": 0.7834982872009277, "step": 74920 }, { "epoch": 2.1173096755053895, "grad_norm": 2.544687509536743, "learning_rate": 2.1860654647886712e-05, "loss": 0.860446548461914, "step": 74940 }, { "epoch": 2.1178747510136042, "grad_norm": 3.7145633697509766, "learning_rate": 2.1834916127637257e-05, "loss": 0.8409214973449707, "step": 74960 }, { "epoch": 2.118439826521819, "grad_norm": 3.505237102508545, "learning_rate": 2.180918853510655e-05, "loss": 0.838005542755127, "step": 74980 }, { "epoch": 2.1190049020300337, "grad_norm": 3.868335723876953, "learning_rate": 2.1783471880276574e-05, "loss": 0.8168130874633789, "step": 75000 }, { "epoch": 2.1195699775382484, "grad_norm": 3.187774419784546, "learning_rate": 2.1757766173125065e-05, "loss": 0.7486459732055664, "step": 75020 }, { "epoch": 2.1201350530464635, "grad_norm": 3.684650421142578, "learning_rate": 2.173207142362557e-05, "loss": 0.7844229698181152, "step": 75040 }, { "epoch": 2.1207001285546783, "grad_norm": 4.360696792602539, "learning_rate": 2.1706387641747334e-05, "loss": 0.8271763801574707, "step": 75060 }, { "epoch": 2.121265204062893, "grad_norm": 3.0155394077301025, "learning_rate": 2.1680714837455358e-05, "loss": 0.8437940597534179, "step": 75080 }, { "epoch": 2.1218302795711077, "grad_norm": 3.7745728492736816, "learning_rate": 2.1655053020710366e-05, "loss": 0.8557309150695801, "step": 75100 }, { "epoch": 2.1223953550793224, "grad_norm": 2.8913767337799072, "learning_rate": 2.162940220146887e-05, "loss": 0.7417750835418702, "step": 75120 }, { "epoch": 2.122960430587537, "grad_norm": 5.175230979919434, "learning_rate": 2.1603762389683075e-05, "loss": 0.711916446685791, "step": 75140 }, { "epoch": 2.123525506095752, "grad_norm": 2.3392629623413086, "learning_rate": 2.1578133595300915e-05, "loss": 0.7407203674316406, "step": 75160 }, { "epoch": 2.124090581603967, "grad_norm": 3.504863739013672, "learning_rate": 2.155251582826605e-05, "loss": 0.7917758464813233, "step": 75180 }, { "epoch": 2.1246556571121817, "grad_norm": 3.5160419940948486, "learning_rate": 2.1526909098517884e-05, "loss": 0.8160796165466309, "step": 75200 }, { "epoch": 2.1252207326203965, "grad_norm": 3.0507211685180664, "learning_rate": 2.150131341599154e-05, "loss": 0.8021737098693847, "step": 75220 }, { "epoch": 2.125785808128611, "grad_norm": 4.84306001663208, "learning_rate": 2.1475728790617827e-05, "loss": 0.8416831016540527, "step": 75240 }, { "epoch": 2.126350883636826, "grad_norm": 3.880660057067871, "learning_rate": 2.1450155232323272e-05, "loss": 0.7835936069488525, "step": 75260 }, { "epoch": 2.1269159591450406, "grad_norm": 4.786235809326172, "learning_rate": 2.1424592751030094e-05, "loss": 0.7720831394195556, "step": 75280 }, { "epoch": 2.1274810346532558, "grad_norm": 2.918349504470825, "learning_rate": 2.139904135665627e-05, "loss": 0.7845899581909179, "step": 75300 }, { "epoch": 2.1280461101614705, "grad_norm": 3.490940570831299, "learning_rate": 2.137350105911542e-05, "loss": 0.7936330795288086, "step": 75320 }, { "epoch": 2.128611185669685, "grad_norm": 3.449254035949707, "learning_rate": 2.134797186831688e-05, "loss": 0.790064811706543, "step": 75340 }, { "epoch": 2.1291762611779, "grad_norm": 3.9977827072143555, "learning_rate": 2.1322453794165646e-05, "loss": 0.7785178184509277, "step": 75360 }, { "epoch": 2.1297413366861146, "grad_norm": 2.8746232986450195, "learning_rate": 2.1296946846562477e-05, "loss": 0.7529407501220703, "step": 75380 }, { "epoch": 2.1303064121943294, "grad_norm": 4.512541770935059, "learning_rate": 2.1271451035403745e-05, "loss": 0.797045373916626, "step": 75400 }, { "epoch": 2.130871487702544, "grad_norm": 5.260992050170898, "learning_rate": 2.1245966370581515e-05, "loss": 0.8269517898559571, "step": 75420 }, { "epoch": 2.131436563210759, "grad_norm": 3.1400513648986816, "learning_rate": 2.1220492861983522e-05, "loss": 0.8808860778808594, "step": 75440 }, { "epoch": 2.132001638718974, "grad_norm": 3.4851789474487305, "learning_rate": 2.1195030519493226e-05, "loss": 0.7677007675170898, "step": 75460 }, { "epoch": 2.1325667142271887, "grad_norm": 3.09559965133667, "learning_rate": 2.116957935298969e-05, "loss": 0.8128585815429688, "step": 75480 }, { "epoch": 2.1331317897354034, "grad_norm": 3.1274988651275635, "learning_rate": 2.114413937234766e-05, "loss": 0.8098649978637695, "step": 75500 }, { "epoch": 2.133696865243618, "grad_norm": 2.885084390640259, "learning_rate": 2.111871058743754e-05, "loss": 0.8175445556640625, "step": 75520 }, { "epoch": 2.134261940751833, "grad_norm": 5.857853412628174, "learning_rate": 2.109329300812541e-05, "loss": 0.7918192863464355, "step": 75540 }, { "epoch": 2.1348270162600476, "grad_norm": 2.9817731380462646, "learning_rate": 2.1067886644273006e-05, "loss": 0.7656750679016113, "step": 75560 }, { "epoch": 2.1353920917682627, "grad_norm": 5.432491302490234, "learning_rate": 2.1042491505737683e-05, "loss": 0.7362504005432129, "step": 75580 }, { "epoch": 2.1359571672764774, "grad_norm": 4.321016788482666, "learning_rate": 2.101710760237245e-05, "loss": 0.8430970191955567, "step": 75600 }, { "epoch": 2.136522242784692, "grad_norm": 3.6235196590423584, "learning_rate": 2.0991734944025942e-05, "loss": 0.7996111392974854, "step": 75620 }, { "epoch": 2.137087318292907, "grad_norm": 3.3484621047973633, "learning_rate": 2.0966373540542487e-05, "loss": 0.7803807735443116, "step": 75640 }, { "epoch": 2.1376523938011216, "grad_norm": 3.6081018447875977, "learning_rate": 2.0941023401761995e-05, "loss": 0.7460759162902832, "step": 75660 }, { "epoch": 2.1382174693093363, "grad_norm": 3.546751022338867, "learning_rate": 2.0915684537520013e-05, "loss": 0.7363063335418701, "step": 75680 }, { "epoch": 2.138782544817551, "grad_norm": 4.9073309898376465, "learning_rate": 2.0890356957647707e-05, "loss": 0.7850529670715332, "step": 75700 }, { "epoch": 2.139347620325766, "grad_norm": 2.44003963470459, "learning_rate": 2.086504067197191e-05, "loss": 0.7781918048858643, "step": 75720 }, { "epoch": 2.139912695833981, "grad_norm": 3.935265302658081, "learning_rate": 2.0839735690315022e-05, "loss": 0.8023113250732422, "step": 75740 }, { "epoch": 2.1404777713421956, "grad_norm": 3.9109389781951904, "learning_rate": 2.081444202249506e-05, "loss": 0.8506698608398438, "step": 75760 }, { "epoch": 2.1410428468504104, "grad_norm": 5.026703834533691, "learning_rate": 2.0789159678325704e-05, "loss": 0.7725084304809571, "step": 75780 }, { "epoch": 2.141607922358625, "grad_norm": 2.4652388095855713, "learning_rate": 2.0763888667616187e-05, "loss": 0.7759890556335449, "step": 75800 }, { "epoch": 2.14217299786684, "grad_norm": 3.1143622398376465, "learning_rate": 2.0738629000171363e-05, "loss": 0.843952751159668, "step": 75820 }, { "epoch": 2.142738073375055, "grad_norm": 5.369499683380127, "learning_rate": 2.0713380685791656e-05, "loss": 0.7776941299438477, "step": 75840 }, { "epoch": 2.1433031488832697, "grad_norm": 3.6950912475585938, "learning_rate": 2.068814373427314e-05, "loss": 0.7806602954864502, "step": 75860 }, { "epoch": 2.1438682243914844, "grad_norm": 3.6441235542297363, "learning_rate": 2.0662918155407467e-05, "loss": 0.7456657409667968, "step": 75880 }, { "epoch": 2.144433299899699, "grad_norm": 3.373544692993164, "learning_rate": 2.0637703958981852e-05, "loss": 0.7917006969451904, "step": 75900 }, { "epoch": 2.144998375407914, "grad_norm": 2.8391551971435547, "learning_rate": 2.0612501154779092e-05, "loss": 0.7187428951263428, "step": 75920 }, { "epoch": 2.1455634509161285, "grad_norm": 3.427910089492798, "learning_rate": 2.0587309752577566e-05, "loss": 0.8591278076171875, "step": 75940 }, { "epoch": 2.1461285264243433, "grad_norm": 2.6572115421295166, "learning_rate": 2.0562129762151278e-05, "loss": 0.7903264999389649, "step": 75960 }, { "epoch": 2.1466936019325584, "grad_norm": 5.466305732727051, "learning_rate": 2.0536961193269737e-05, "loss": 0.8139169692993165, "step": 75980 }, { "epoch": 2.147258677440773, "grad_norm": 3.0017004013061523, "learning_rate": 2.0511804055698064e-05, "loss": 0.795274305343628, "step": 76000 }, { "epoch": 2.147823752948988, "grad_norm": 2.9392080307006836, "learning_rate": 2.04866583591969e-05, "loss": 0.7924840450286865, "step": 76020 }, { "epoch": 2.1483888284572026, "grad_norm": 3.9281318187713623, "learning_rate": 2.0461524113522516e-05, "loss": 0.80422945022583, "step": 76040 }, { "epoch": 2.1489539039654173, "grad_norm": 3.235048294067383, "learning_rate": 2.043640132842669e-05, "loss": 0.7238891124725342, "step": 76060 }, { "epoch": 2.149518979473632, "grad_norm": 3.7192022800445557, "learning_rate": 2.0411290013656758e-05, "loss": 0.769675874710083, "step": 76080 }, { "epoch": 2.150084054981847, "grad_norm": 4.243265151977539, "learning_rate": 2.03861901789556e-05, "loss": 0.8103129386901855, "step": 76100 }, { "epoch": 2.150649130490062, "grad_norm": 4.442367076873779, "learning_rate": 2.0361101834061685e-05, "loss": 0.9161614418029785, "step": 76120 }, { "epoch": 2.1512142059982766, "grad_norm": 4.553062438964844, "learning_rate": 2.0336024988708978e-05, "loss": 0.8014037132263183, "step": 76140 }, { "epoch": 2.1517792815064913, "grad_norm": 3.0925776958465576, "learning_rate": 2.0310959652626997e-05, "loss": 0.7506383419036865, "step": 76160 }, { "epoch": 2.152344357014706, "grad_norm": 3.0014448165893555, "learning_rate": 2.0285905835540776e-05, "loss": 0.7505208492279053, "step": 76180 }, { "epoch": 2.1529094325229208, "grad_norm": 3.644779920578003, "learning_rate": 2.026086354717092e-05, "loss": 0.8480803489685058, "step": 76200 }, { "epoch": 2.1534745080311355, "grad_norm": 3.099238872528076, "learning_rate": 2.0235832797233557e-05, "loss": 0.9010891914367676, "step": 76220 }, { "epoch": 2.15403958353935, "grad_norm": 4.551876544952393, "learning_rate": 2.0210813595440305e-05, "loss": 0.8395946502685547, "step": 76240 }, { "epoch": 2.1546046590475654, "grad_norm": 3.3507213592529297, "learning_rate": 2.0185805951498316e-05, "loss": 0.8039501190185547, "step": 76260 }, { "epoch": 2.15516973455578, "grad_norm": 2.5655055046081543, "learning_rate": 2.0160809875110236e-05, "loss": 0.7311485767364502, "step": 76280 }, { "epoch": 2.155734810063995, "grad_norm": 4.2868547439575195, "learning_rate": 2.0135825375974293e-05, "loss": 0.7400227069854737, "step": 76300 }, { "epoch": 2.1562998855722095, "grad_norm": 3.5836048126220703, "learning_rate": 2.0110852463784152e-05, "loss": 0.7883285522460938, "step": 76320 }, { "epoch": 2.1568649610804242, "grad_norm": 5.052436351776123, "learning_rate": 2.008589114822901e-05, "loss": 0.8444489479064942, "step": 76340 }, { "epoch": 2.157430036588639, "grad_norm": 3.9922897815704346, "learning_rate": 2.0060941438993536e-05, "loss": 0.7774549961090088, "step": 76360 }, { "epoch": 2.157995112096854, "grad_norm": 4.082696914672852, "learning_rate": 2.003600334575797e-05, "loss": 0.7804163932800293, "step": 76380 }, { "epoch": 2.158560187605069, "grad_norm": 3.807222843170166, "learning_rate": 2.0011076878197966e-05, "loss": 0.8135083198547364, "step": 76400 }, { "epoch": 2.1591252631132836, "grad_norm": 3.6168100833892822, "learning_rate": 1.998616204598469e-05, "loss": 0.827819538116455, "step": 76420 }, { "epoch": 2.1596903386214983, "grad_norm": 3.5200283527374268, "learning_rate": 1.996125885878483e-05, "loss": 0.8210506439208984, "step": 76440 }, { "epoch": 2.160255414129713, "grad_norm": 5.99599027633667, "learning_rate": 1.9936367326260517e-05, "loss": 0.8084279060363769, "step": 76460 }, { "epoch": 2.1608204896379277, "grad_norm": 4.380662441253662, "learning_rate": 1.9911487458069365e-05, "loss": 0.7691091060638428, "step": 76480 }, { "epoch": 2.1613855651461424, "grad_norm": 4.203381538391113, "learning_rate": 1.9886619263864453e-05, "loss": 0.7444543838500977, "step": 76500 }, { "epoch": 2.1619506406543576, "grad_norm": 2.727409839630127, "learning_rate": 1.9861762753294362e-05, "loss": 0.7974413394927978, "step": 76520 }, { "epoch": 2.1625157161625723, "grad_norm": 3.9234871864318848, "learning_rate": 1.983691793600314e-05, "loss": 0.8303940773010254, "step": 76540 }, { "epoch": 2.163080791670787, "grad_norm": 3.7462620735168457, "learning_rate": 1.9812084821630266e-05, "loss": 0.770125150680542, "step": 76560 }, { "epoch": 2.1636458671790018, "grad_norm": 3.108240842819214, "learning_rate": 1.97872634198107e-05, "loss": 0.7810993194580078, "step": 76580 }, { "epoch": 2.1642109426872165, "grad_norm": 3.345864772796631, "learning_rate": 1.976245374017482e-05, "loss": 0.7149604320526123, "step": 76600 }, { "epoch": 2.164776018195431, "grad_norm": 4.19679594039917, "learning_rate": 1.973765579234853e-05, "loss": 0.8024328231811524, "step": 76620 }, { "epoch": 2.1653410937036464, "grad_norm": 4.1082353591918945, "learning_rate": 1.9712869585953125e-05, "loss": 0.7507089614868164, "step": 76640 }, { "epoch": 2.165906169211861, "grad_norm": 3.263946771621704, "learning_rate": 1.9688095130605354e-05, "loss": 0.8007369995117187, "step": 76660 }, { "epoch": 2.166471244720076, "grad_norm": 2.5192739963531494, "learning_rate": 1.9663332435917405e-05, "loss": 0.8803353309631348, "step": 76680 }, { "epoch": 2.1670363202282905, "grad_norm": 4.239125728607178, "learning_rate": 1.963858151149693e-05, "loss": 0.7777909755706787, "step": 76700 }, { "epoch": 2.1676013957365052, "grad_norm": 5.288764953613281, "learning_rate": 1.961384236694699e-05, "loss": 0.6941838741302491, "step": 76720 }, { "epoch": 2.16816647124472, "grad_norm": 2.83563494682312, "learning_rate": 1.9589115011866067e-05, "loss": 0.743166732788086, "step": 76740 }, { "epoch": 2.1687315467529347, "grad_norm": 5.215737819671631, "learning_rate": 1.9564399455848076e-05, "loss": 0.734696626663208, "step": 76760 }, { "epoch": 2.16929662226115, "grad_norm": 3.600383996963501, "learning_rate": 1.953969570848239e-05, "loss": 0.7781504631042481, "step": 76780 }, { "epoch": 2.1698616977693646, "grad_norm": 4.179132461547852, "learning_rate": 1.951500377935375e-05, "loss": 0.7728603839874267, "step": 76800 }, { "epoch": 2.1704267732775793, "grad_norm": 4.395376682281494, "learning_rate": 1.9490323678042344e-05, "loss": 0.808378791809082, "step": 76820 }, { "epoch": 2.170991848785794, "grad_norm": 3.2761664390563965, "learning_rate": 1.9465655414123724e-05, "loss": 0.7161890029907226, "step": 76840 }, { "epoch": 2.1715569242940087, "grad_norm": 3.372955322265625, "learning_rate": 1.9440998997168914e-05, "loss": 0.8002363204956054, "step": 76860 }, { "epoch": 2.1721219998022234, "grad_norm": 3.0300967693328857, "learning_rate": 1.9416354436744323e-05, "loss": 0.8057714462280273, "step": 76880 }, { "epoch": 2.1726870753104386, "grad_norm": 2.7836506366729736, "learning_rate": 1.9391721742411727e-05, "loss": 0.7945122241973877, "step": 76900 }, { "epoch": 2.1732521508186533, "grad_norm": 3.6983983516693115, "learning_rate": 1.936710092372833e-05, "loss": 0.8437843322753906, "step": 76920 }, { "epoch": 2.173817226326868, "grad_norm": 3.7792458534240723, "learning_rate": 1.9342491990246698e-05, "loss": 0.7395200729370117, "step": 76940 }, { "epoch": 2.1743823018350827, "grad_norm": 3.426589012145996, "learning_rate": 1.9317894951514838e-05, "loss": 0.8209906578063965, "step": 76960 }, { "epoch": 2.1749473773432975, "grad_norm": 3.805083751678467, "learning_rate": 1.9293309817076084e-05, "loss": 0.8974625587463378, "step": 76980 }, { "epoch": 2.175512452851512, "grad_norm": 4.057372093200684, "learning_rate": 1.926873659646919e-05, "loss": 0.759000301361084, "step": 77000 }, { "epoch": 2.176077528359727, "grad_norm": 4.091095447540283, "learning_rate": 1.9244175299228252e-05, "loss": 0.8591044425964356, "step": 77020 }, { "epoch": 2.176642603867942, "grad_norm": 5.007255554199219, "learning_rate": 1.9219625934882796e-05, "loss": 0.7947961807250976, "step": 77040 }, { "epoch": 2.177207679376157, "grad_norm": 4.775986194610596, "learning_rate": 1.919508851295767e-05, "loss": 0.7950547695159912, "step": 77060 }, { "epoch": 2.1777727548843715, "grad_norm": 4.70046329498291, "learning_rate": 1.9170563042973076e-05, "loss": 0.8031634330749512, "step": 77080 }, { "epoch": 2.178337830392586, "grad_norm": 4.584305286407471, "learning_rate": 1.9146049534444654e-05, "loss": 0.7859219551086426, "step": 77100 }, { "epoch": 2.178902905900801, "grad_norm": 2.5320796966552734, "learning_rate": 1.9121547996883333e-05, "loss": 0.757667064666748, "step": 77120 }, { "epoch": 2.1794679814090157, "grad_norm": 4.31068229675293, "learning_rate": 1.9097058439795412e-05, "loss": 0.807280158996582, "step": 77140 }, { "epoch": 2.1800330569172304, "grad_norm": 3.1520493030548096, "learning_rate": 1.9072580872682538e-05, "loss": 0.8126411437988281, "step": 77160 }, { "epoch": 2.1805981324254455, "grad_norm": 4.23549747467041, "learning_rate": 1.9048115305041737e-05, "loss": 0.7650228023529053, "step": 77180 }, { "epoch": 2.1811632079336603, "grad_norm": 3.014875650405884, "learning_rate": 1.9023661746365367e-05, "loss": 0.7727316379547119, "step": 77200 }, { "epoch": 2.181728283441875, "grad_norm": 3.9763894081115723, "learning_rate": 1.899922020614111e-05, "loss": 0.8541267395019532, "step": 77220 }, { "epoch": 2.1822933589500897, "grad_norm": 5.02509880065918, "learning_rate": 1.897479069385199e-05, "loss": 0.8108928680419922, "step": 77240 }, { "epoch": 2.1828584344583044, "grad_norm": 4.106426239013672, "learning_rate": 1.8950373218976354e-05, "loss": 0.8123779296875, "step": 77260 }, { "epoch": 2.183423509966519, "grad_norm": 2.8271093368530273, "learning_rate": 1.8925967790987926e-05, "loss": 0.7594285488128663, "step": 77280 }, { "epoch": 2.183988585474734, "grad_norm": 3.496866226196289, "learning_rate": 1.89015744193557e-05, "loss": 0.8337183952331543, "step": 77300 }, { "epoch": 2.184553660982949, "grad_norm": 3.936950206756592, "learning_rate": 1.887719311354402e-05, "loss": 0.7028422832489014, "step": 77320 }, { "epoch": 2.1851187364911637, "grad_norm": 2.2341902256011963, "learning_rate": 1.885282388301253e-05, "loss": 0.807096290588379, "step": 77340 }, { "epoch": 2.1856838119993784, "grad_norm": 3.6472227573394775, "learning_rate": 1.882846673721624e-05, "loss": 0.7441328048706055, "step": 77360 }, { "epoch": 2.186248887507593, "grad_norm": 2.6889564990997314, "learning_rate": 1.8804121685605404e-05, "loss": 0.7669519901275634, "step": 77380 }, { "epoch": 2.186813963015808, "grad_norm": 3.6085357666015625, "learning_rate": 1.877978873762562e-05, "loss": 0.7743950366973877, "step": 77400 }, { "epoch": 2.1873790385240226, "grad_norm": 2.9114973545074463, "learning_rate": 1.8755467902717767e-05, "loss": 0.7959272384643554, "step": 77420 }, { "epoch": 2.1879441140322378, "grad_norm": 4.620005130767822, "learning_rate": 1.873115919031807e-05, "loss": 0.8541646003723145, "step": 77440 }, { "epoch": 2.1885091895404525, "grad_norm": 5.510796070098877, "learning_rate": 1.870686260985801e-05, "loss": 0.6853730201721191, "step": 77460 }, { "epoch": 2.189074265048667, "grad_norm": 5.163947105407715, "learning_rate": 1.8682578170764376e-05, "loss": 0.8328428268432617, "step": 77480 }, { "epoch": 2.189639340556882, "grad_norm": 3.647596597671509, "learning_rate": 1.8658305882459214e-05, "loss": 0.7097148895263672, "step": 77500 }, { "epoch": 2.1902044160650966, "grad_norm": 3.8905656337738037, "learning_rate": 1.8634045754359907e-05, "loss": 0.7708431243896484, "step": 77520 }, { "epoch": 2.1907694915733114, "grad_norm": 3.076120138168335, "learning_rate": 1.8609797795879118e-05, "loss": 0.776554536819458, "step": 77540 }, { "epoch": 2.191334567081526, "grad_norm": 3.5491089820861816, "learning_rate": 1.8585562016424745e-05, "loss": 0.7817909717559814, "step": 77560 }, { "epoch": 2.1918996425897412, "grad_norm": 2.773568630218506, "learning_rate": 1.856133842539999e-05, "loss": 0.7288865566253662, "step": 77580 }, { "epoch": 2.192464718097956, "grad_norm": 3.394320487976074, "learning_rate": 1.8537127032203288e-05, "loss": 0.7509514808654785, "step": 77600 }, { "epoch": 2.1930297936061707, "grad_norm": 3.4502804279327393, "learning_rate": 1.8512927846228423e-05, "loss": 0.7765026092529297, "step": 77620 }, { "epoch": 2.1935948691143854, "grad_norm": 3.6280839443206787, "learning_rate": 1.8488740876864364e-05, "loss": 0.8229310035705566, "step": 77640 }, { "epoch": 2.1941599446226, "grad_norm": 4.015406131744385, "learning_rate": 1.8464566133495377e-05, "loss": 0.8247737884521484, "step": 77660 }, { "epoch": 2.194725020130815, "grad_norm": 2.55521297454834, "learning_rate": 1.8440403625500952e-05, "loss": 0.8050369262695313, "step": 77680 }, { "epoch": 2.19529009563903, "grad_norm": 3.4565935134887695, "learning_rate": 1.8416253362255893e-05, "loss": 0.776087760925293, "step": 77700 }, { "epoch": 2.1958551711472447, "grad_norm": 3.5512478351593018, "learning_rate": 1.8392115353130195e-05, "loss": 0.6877179145812988, "step": 77720 }, { "epoch": 2.1964202466554594, "grad_norm": 3.353191375732422, "learning_rate": 1.8367989607489127e-05, "loss": 0.7980044841766357, "step": 77740 }, { "epoch": 2.196985322163674, "grad_norm": 3.918832778930664, "learning_rate": 1.8343876134693174e-05, "loss": 0.8197669982910156, "step": 77760 }, { "epoch": 2.197550397671889, "grad_norm": 3.1030712127685547, "learning_rate": 1.83197749440981e-05, "loss": 0.844631576538086, "step": 77780 }, { "epoch": 2.1981154731801036, "grad_norm": 5.188279151916504, "learning_rate": 1.829568604505488e-05, "loss": 0.785766315460205, "step": 77800 }, { "epoch": 2.1986805486883183, "grad_norm": 4.553363800048828, "learning_rate": 1.827160944690969e-05, "loss": 0.714394474029541, "step": 77820 }, { "epoch": 2.1992456241965335, "grad_norm": 3.960881233215332, "learning_rate": 1.8247545159004e-05, "loss": 0.8075678825378418, "step": 77840 }, { "epoch": 2.199810699704748, "grad_norm": 3.281989336013794, "learning_rate": 1.822349319067447e-05, "loss": 0.9088086128234864, "step": 77860 }, { "epoch": 2.200375775212963, "grad_norm": 2.9580695629119873, "learning_rate": 1.819945355125296e-05, "loss": 0.8419708251953125, "step": 77880 }, { "epoch": 2.2009408507211776, "grad_norm": 4.900851249694824, "learning_rate": 1.8175426250066572e-05, "loss": 0.803317928314209, "step": 77900 }, { "epoch": 2.2015059262293923, "grad_norm": 2.7791194915771484, "learning_rate": 1.8151411296437605e-05, "loss": 0.799897575378418, "step": 77920 }, { "epoch": 2.202071001737607, "grad_norm": 5.3182268142700195, "learning_rate": 1.8127408699683594e-05, "loss": 0.8025655746459961, "step": 77940 }, { "epoch": 2.2026360772458218, "grad_norm": 3.308957099914551, "learning_rate": 1.810341846911726e-05, "loss": 0.7365511417388916, "step": 77960 }, { "epoch": 2.203201152754037, "grad_norm": 3.2643420696258545, "learning_rate": 1.8079440614046518e-05, "loss": 0.7533967971801758, "step": 77980 }, { "epoch": 2.2037662282622517, "grad_norm": 3.0688915252685547, "learning_rate": 1.8055475143774476e-05, "loss": 0.7685523986816406, "step": 78000 }, { "epoch": 2.2043313037704664, "grad_norm": 3.40741229057312, "learning_rate": 1.8031522067599492e-05, "loss": 0.7908616542816163, "step": 78020 }, { "epoch": 2.204896379278681, "grad_norm": 3.737393379211426, "learning_rate": 1.8007581394815055e-05, "loss": 0.7634860038757324, "step": 78040 }, { "epoch": 2.205461454786896, "grad_norm": 3.9757423400878906, "learning_rate": 1.7983653134709853e-05, "loss": 0.7661709308624267, "step": 78060 }, { "epoch": 2.2060265302951105, "grad_norm": 3.7689828872680664, "learning_rate": 1.7959737296567768e-05, "loss": 0.7713944911956787, "step": 78080 }, { "epoch": 2.2065916058033253, "grad_norm": 4.780637264251709, "learning_rate": 1.7935833889667885e-05, "loss": 0.7594983100891113, "step": 78100 }, { "epoch": 2.2071566813115404, "grad_norm": 2.3527252674102783, "learning_rate": 1.7911942923284424e-05, "loss": 0.7553064823150635, "step": 78120 }, { "epoch": 2.207721756819755, "grad_norm": 3.2509138584136963, "learning_rate": 1.7888064406686804e-05, "loss": 0.7649794578552246, "step": 78140 }, { "epoch": 2.20828683232797, "grad_norm": 3.6401174068450928, "learning_rate": 1.7864198349139587e-05, "loss": 0.819124412536621, "step": 78160 }, { "epoch": 2.2088519078361846, "grad_norm": 6.263796806335449, "learning_rate": 1.784034475990254e-05, "loss": 0.7639554023742676, "step": 78180 }, { "epoch": 2.2094169833443993, "grad_norm": 3.670271158218384, "learning_rate": 1.781650364823058e-05, "loss": 0.8551193237304687, "step": 78200 }, { "epoch": 2.209982058852614, "grad_norm": 3.0973193645477295, "learning_rate": 1.7792675023373767e-05, "loss": 0.7780595302581788, "step": 78220 }, { "epoch": 2.210547134360829, "grad_norm": 3.0000054836273193, "learning_rate": 1.7768858894577324e-05, "loss": 0.7789278507232666, "step": 78240 }, { "epoch": 2.211112209869044, "grad_norm": 3.720524549484253, "learning_rate": 1.7745055271081606e-05, "loss": 0.7143091678619384, "step": 78260 }, { "epoch": 2.2116772853772586, "grad_norm": 3.1453232765197754, "learning_rate": 1.7721264162122175e-05, "loss": 0.7916767597198486, "step": 78280 }, { "epoch": 2.2122423608854733, "grad_norm": 3.9945337772369385, "learning_rate": 1.769748557692968e-05, "loss": 0.7588681697845459, "step": 78300 }, { "epoch": 2.212807436393688, "grad_norm": 3.4841487407684326, "learning_rate": 1.767371952472993e-05, "loss": 0.8078164100646973, "step": 78320 }, { "epoch": 2.2133725119019028, "grad_norm": 4.457259178161621, "learning_rate": 1.7649966014743858e-05, "loss": 0.8580706596374512, "step": 78340 }, { "epoch": 2.2139375874101175, "grad_norm": 3.093728542327881, "learning_rate": 1.7626225056187577e-05, "loss": 0.7316929817199707, "step": 78360 }, { "epoch": 2.2145026629183326, "grad_norm": 3.6018736362457275, "learning_rate": 1.7602496658272277e-05, "loss": 0.7587901592254639, "step": 78380 }, { "epoch": 2.2150677384265474, "grad_norm": 4.577037811279297, "learning_rate": 1.75787808302043e-05, "loss": 0.8186858177185059, "step": 78400 }, { "epoch": 2.215632813934762, "grad_norm": 4.100895881652832, "learning_rate": 1.7555077581185085e-05, "loss": 0.7847703456878662, "step": 78420 }, { "epoch": 2.216197889442977, "grad_norm": 4.575995922088623, "learning_rate": 1.7531386920411254e-05, "loss": 0.7972790241241455, "step": 78440 }, { "epoch": 2.2167629649511915, "grad_norm": 2.6869359016418457, "learning_rate": 1.7507708857074472e-05, "loss": 0.7405963897705078, "step": 78460 }, { "epoch": 2.2173280404594062, "grad_norm": 4.963977813720703, "learning_rate": 1.748404340036154e-05, "loss": 0.7914881229400634, "step": 78480 }, { "epoch": 2.2178931159676214, "grad_norm": 2.9141173362731934, "learning_rate": 1.7460390559454388e-05, "loss": 0.8149759292602539, "step": 78500 }, { "epoch": 2.218458191475836, "grad_norm": 3.239424705505371, "learning_rate": 1.7436750343530057e-05, "loss": 0.7471578598022461, "step": 78520 }, { "epoch": 2.219023266984051, "grad_norm": 3.788207769393921, "learning_rate": 1.7413122761760648e-05, "loss": 0.8009841918945313, "step": 78540 }, { "epoch": 2.2195883424922656, "grad_norm": 2.6536269187927246, "learning_rate": 1.7389507823313388e-05, "loss": 0.751081132888794, "step": 78560 }, { "epoch": 2.2201534180004803, "grad_norm": 3.4650957584381104, "learning_rate": 1.736590553735058e-05, "loss": 0.7757143020629883, "step": 78580 }, { "epoch": 2.220718493508695, "grad_norm": 3.4281911849975586, "learning_rate": 1.734231591302966e-05, "loss": 0.7623554706573487, "step": 78600 }, { "epoch": 2.2212835690169097, "grad_norm": 4.378473281860352, "learning_rate": 1.7318738959503105e-05, "loss": 0.7872261047363281, "step": 78620 }, { "epoch": 2.221848644525125, "grad_norm": 4.229304313659668, "learning_rate": 1.729517468591849e-05, "loss": 0.780977201461792, "step": 78640 }, { "epoch": 2.2224137200333396, "grad_norm": 3.7917046546936035, "learning_rate": 1.7271623101418472e-05, "loss": 0.7667651176452637, "step": 78660 }, { "epoch": 2.2229787955415543, "grad_norm": 3.440932512283325, "learning_rate": 1.7248084215140803e-05, "loss": 0.7897769451141358, "step": 78680 }, { "epoch": 2.223543871049769, "grad_norm": 3.7123048305511475, "learning_rate": 1.722455803621828e-05, "loss": 0.7840344429016113, "step": 78700 }, { "epoch": 2.2241089465579837, "grad_norm": 3.0700812339782715, "learning_rate": 1.720104457377879e-05, "loss": 0.7729057312011719, "step": 78720 }, { "epoch": 2.2246740220661985, "grad_norm": 2.8307414054870605, "learning_rate": 1.7177543836945253e-05, "loss": 0.7571916580200195, "step": 78740 }, { "epoch": 2.225239097574413, "grad_norm": 3.0744166374206543, "learning_rate": 1.715405583483571e-05, "loss": 0.7920873165130615, "step": 78760 }, { "epoch": 2.2258041730826283, "grad_norm": 5.017424583435059, "learning_rate": 1.713058057656321e-05, "loss": 0.7428155422210694, "step": 78780 }, { "epoch": 2.226369248590843, "grad_norm": 4.51143741607666, "learning_rate": 1.7107118071235884e-05, "loss": 0.8389787673950195, "step": 78800 }, { "epoch": 2.226934324099058, "grad_norm": 3.2088401317596436, "learning_rate": 1.7083668327956876e-05, "loss": 0.7996484756469726, "step": 78820 }, { "epoch": 2.2274993996072725, "grad_norm": 4.421040058135986, "learning_rate": 1.7060231355824434e-05, "loss": 0.8053784370422363, "step": 78840 }, { "epoch": 2.228064475115487, "grad_norm": 5.469296455383301, "learning_rate": 1.7036807163931838e-05, "loss": 0.8075112342834473, "step": 78860 }, { "epoch": 2.228629550623702, "grad_norm": 3.878774404525757, "learning_rate": 1.701339576136739e-05, "loss": 0.7306974411010743, "step": 78880 }, { "epoch": 2.2291946261319167, "grad_norm": 3.1660964488983154, "learning_rate": 1.698999715721442e-05, "loss": 0.7928032875061035, "step": 78900 }, { "epoch": 2.229759701640132, "grad_norm": 3.8719754219055176, "learning_rate": 1.6966611360551305e-05, "loss": 0.8426943778991699, "step": 78920 }, { "epoch": 2.2303247771483465, "grad_norm": 4.691878318786621, "learning_rate": 1.6943238380451487e-05, "loss": 0.8002659797668457, "step": 78940 }, { "epoch": 2.2308898526565613, "grad_norm": 2.686286211013794, "learning_rate": 1.6919878225983386e-05, "loss": 0.7648988723754883, "step": 78960 }, { "epoch": 2.231454928164776, "grad_norm": 2.3974668979644775, "learning_rate": 1.6896530906210466e-05, "loss": 0.7515769004821777, "step": 78980 }, { "epoch": 2.2320200036729907, "grad_norm": 3.497860908508301, "learning_rate": 1.6873196430191197e-05, "loss": 0.8319724082946778, "step": 79000 }, { "epoch": 2.2325850791812054, "grad_norm": 3.1486454010009766, "learning_rate": 1.684987480697911e-05, "loss": 0.7652676582336426, "step": 79020 }, { "epoch": 2.2331501546894206, "grad_norm": 2.8405003547668457, "learning_rate": 1.6826566045622705e-05, "loss": 0.8383161544799804, "step": 79040 }, { "epoch": 2.2337152301976353, "grad_norm": 7.7535600662231445, "learning_rate": 1.6803270155165496e-05, "loss": 0.84708251953125, "step": 79060 }, { "epoch": 2.23428030570585, "grad_norm": 4.666282653808594, "learning_rate": 1.6779987144646003e-05, "loss": 0.8169013977050781, "step": 79080 }, { "epoch": 2.2348453812140647, "grad_norm": 2.897084951400757, "learning_rate": 1.6756717023097794e-05, "loss": 0.7726743698120118, "step": 79100 }, { "epoch": 2.2354104567222794, "grad_norm": 4.384051322937012, "learning_rate": 1.6733459799549377e-05, "loss": 0.8065007209777832, "step": 79120 }, { "epoch": 2.235975532230494, "grad_norm": 4.191479682922363, "learning_rate": 1.6710215483024284e-05, "loss": 0.828702735900879, "step": 79140 }, { "epoch": 2.236540607738709, "grad_norm": 3.546367883682251, "learning_rate": 1.6686984082540997e-05, "loss": 0.8336964607238769, "step": 79160 }, { "epoch": 2.237105683246924, "grad_norm": 4.897117614746094, "learning_rate": 1.6663765607113097e-05, "loss": 0.8213943481445313, "step": 79180 }, { "epoch": 2.2376707587551388, "grad_norm": 3.812173843383789, "learning_rate": 1.6640560065749034e-05, "loss": 0.7602269172668457, "step": 79200 }, { "epoch": 2.2382358342633535, "grad_norm": 3.3543317317962646, "learning_rate": 1.6617367467452294e-05, "loss": 0.7163599491119385, "step": 79220 }, { "epoch": 2.238800909771568, "grad_norm": 3.167945623397827, "learning_rate": 1.65941878212213e-05, "loss": 0.7766584873199462, "step": 79240 }, { "epoch": 2.239365985279783, "grad_norm": 2.762533187866211, "learning_rate": 1.657102113604953e-05, "loss": 0.7501668930053711, "step": 79260 }, { "epoch": 2.2399310607879976, "grad_norm": 4.232727527618408, "learning_rate": 1.6547867420925357e-05, "loss": 0.863107967376709, "step": 79280 }, { "epoch": 2.240496136296213, "grad_norm": 3.511046886444092, "learning_rate": 1.6524726684832147e-05, "loss": 0.7666867256164551, "step": 79300 }, { "epoch": 2.2410612118044275, "grad_norm": 5.568286895751953, "learning_rate": 1.650159893674822e-05, "loss": 0.7997052192687988, "step": 79320 }, { "epoch": 2.2416262873126422, "grad_norm": 3.387037754058838, "learning_rate": 1.64784841856469e-05, "loss": 0.8648911476135254, "step": 79340 }, { "epoch": 2.242191362820857, "grad_norm": 4.080453395843506, "learning_rate": 1.6455382440496407e-05, "loss": 0.8435572624206543, "step": 79360 }, { "epoch": 2.2427564383290717, "grad_norm": 3.412781000137329, "learning_rate": 1.6432293710259965e-05, "loss": 0.8126791000366211, "step": 79380 }, { "epoch": 2.2433215138372864, "grad_norm": 3.78778076171875, "learning_rate": 1.6409218003895706e-05, "loss": 0.8469174385070801, "step": 79400 }, { "epoch": 2.243886589345501, "grad_norm": 4.634326934814453, "learning_rate": 1.638615533035675e-05, "loss": 0.8262483596801757, "step": 79420 }, { "epoch": 2.2444516648537163, "grad_norm": 3.725855827331543, "learning_rate": 1.6363105698591134e-05, "loss": 0.758292818069458, "step": 79440 }, { "epoch": 2.245016740361931, "grad_norm": 4.196238040924072, "learning_rate": 1.6340069117541852e-05, "loss": 0.8028375625610351, "step": 79460 }, { "epoch": 2.2455818158701457, "grad_norm": 4.802389621734619, "learning_rate": 1.6317045596146792e-05, "loss": 0.7593327045440674, "step": 79480 }, { "epoch": 2.2461468913783604, "grad_norm": 5.5508856773376465, "learning_rate": 1.6294035143338824e-05, "loss": 0.7347856521606445, "step": 79500 }, { "epoch": 2.246711966886575, "grad_norm": 7.366341590881348, "learning_rate": 1.627103776804576e-05, "loss": 0.7341649532318115, "step": 79520 }, { "epoch": 2.24727704239479, "grad_norm": 2.7733702659606934, "learning_rate": 1.6248053479190285e-05, "loss": 0.8165178298950195, "step": 79540 }, { "epoch": 2.2478421179030046, "grad_norm": 3.997248649597168, "learning_rate": 1.622508228569003e-05, "loss": 0.7360166549682617, "step": 79560 }, { "epoch": 2.2484071934112198, "grad_norm": 4.231871604919434, "learning_rate": 1.620212419645753e-05, "loss": 0.9280065536499024, "step": 79580 }, { "epoch": 2.2489722689194345, "grad_norm": 2.732187032699585, "learning_rate": 1.6179179220400282e-05, "loss": 0.8245916366577148, "step": 79600 }, { "epoch": 2.249537344427649, "grad_norm": 3.6978659629821777, "learning_rate": 1.6156247366420657e-05, "loss": 0.7365025997161865, "step": 79620 }, { "epoch": 2.250102419935864, "grad_norm": 2.604541540145874, "learning_rate": 1.6133328643415934e-05, "loss": 0.7459746360778808, "step": 79640 }, { "epoch": 2.2506674954440786, "grad_norm": 3.575774669647217, "learning_rate": 1.6110423060278297e-05, "loss": 0.7122453212738037, "step": 79660 }, { "epoch": 2.2512325709522933, "grad_norm": 4.282100200653076, "learning_rate": 1.6087530625894864e-05, "loss": 0.7744583129882813, "step": 79680 }, { "epoch": 2.251797646460508, "grad_norm": 2.0926406383514404, "learning_rate": 1.606465134914762e-05, "loss": 0.6905725955963135, "step": 79700 }, { "epoch": 2.2523627219687232, "grad_norm": 2.9579930305480957, "learning_rate": 1.6041785238913447e-05, "loss": 0.8656414985656739, "step": 79720 }, { "epoch": 2.252927797476938, "grad_norm": 4.043223857879639, "learning_rate": 1.6018932304064117e-05, "loss": 0.8316109657287598, "step": 79740 }, { "epoch": 2.2534928729851527, "grad_norm": 2.0500221252441406, "learning_rate": 1.599609255346632e-05, "loss": 0.7261079311370849, "step": 79760 }, { "epoch": 2.2540579484933674, "grad_norm": 4.0574822425842285, "learning_rate": 1.5973265995981596e-05, "loss": 0.8044941902160645, "step": 79780 }, { "epoch": 2.254623024001582, "grad_norm": 3.2660024166107178, "learning_rate": 1.5950452640466383e-05, "loss": 0.7304559230804444, "step": 79800 }, { "epoch": 2.255188099509797, "grad_norm": 4.037505626678467, "learning_rate": 1.5927652495771954e-05, "loss": 0.763026237487793, "step": 79820 }, { "epoch": 2.255753175018012, "grad_norm": 3.988788604736328, "learning_rate": 1.590486557074457e-05, "loss": 0.6963035583496093, "step": 79840 }, { "epoch": 2.2563182505262267, "grad_norm": 4.548211574554443, "learning_rate": 1.588209187422524e-05, "loss": 0.7878765106201172, "step": 79860 }, { "epoch": 2.2568833260344414, "grad_norm": 2.722726821899414, "learning_rate": 1.5859331415049906e-05, "loss": 0.7367054939270019, "step": 79880 }, { "epoch": 2.257448401542656, "grad_norm": 3.794912576675415, "learning_rate": 1.5836584202049325e-05, "loss": 0.8395631790161133, "step": 79900 }, { "epoch": 2.258013477050871, "grad_norm": 3.623060464859009, "learning_rate": 1.5813850244049184e-05, "loss": 0.7490495681762696, "step": 79920 }, { "epoch": 2.2585785525590856, "grad_norm": 2.223285436630249, "learning_rate": 1.5791129549869976e-05, "loss": 0.7121714115142822, "step": 79940 }, { "epoch": 2.2591436280673003, "grad_norm": 3.1216492652893066, "learning_rate": 1.5768422128327053e-05, "loss": 0.770006799697876, "step": 79960 }, { "epoch": 2.2597087035755155, "grad_norm": 4.280343055725098, "learning_rate": 1.5745727988230624e-05, "loss": 0.7522024631500244, "step": 79980 }, { "epoch": 2.26027377908373, "grad_norm": 3.7781689167022705, "learning_rate": 1.572304713838576e-05, "loss": 0.7848323345184326, "step": 80000 }, { "epoch": 2.260838854591945, "grad_norm": 3.708451986312866, "learning_rate": 1.5700379587592362e-05, "loss": 0.8255378723144531, "step": 80020 }, { "epoch": 2.2614039301001596, "grad_norm": 3.7109644412994385, "learning_rate": 1.5677725344645162e-05, "loss": 0.7953368663787842, "step": 80040 }, { "epoch": 2.2619690056083743, "grad_norm": 3.2573254108428955, "learning_rate": 1.565508441833372e-05, "loss": 0.8175703048706054, "step": 80060 }, { "epoch": 2.262534081116589, "grad_norm": 4.261499404907227, "learning_rate": 1.5632456817442488e-05, "loss": 0.8325658798217773, "step": 80080 }, { "epoch": 2.263099156624804, "grad_norm": 3.9692330360412598, "learning_rate": 1.5609842550750688e-05, "loss": 0.8347932815551757, "step": 80100 }, { "epoch": 2.263664232133019, "grad_norm": 2.7271878719329834, "learning_rate": 1.558724162703238e-05, "loss": 0.8315546035766601, "step": 80120 }, { "epoch": 2.2642293076412336, "grad_norm": 4.073660373687744, "learning_rate": 1.5564654055056445e-05, "loss": 0.7912359714508057, "step": 80140 }, { "epoch": 2.2647943831494484, "grad_norm": 3.4978582859039307, "learning_rate": 1.554207984358661e-05, "loss": 0.8904163360595703, "step": 80160 }, { "epoch": 2.265359458657663, "grad_norm": 4.086015224456787, "learning_rate": 1.5519519001381417e-05, "loss": 0.8283321380615234, "step": 80180 }, { "epoch": 2.265924534165878, "grad_norm": 5.979555130004883, "learning_rate": 1.5496971537194182e-05, "loss": 0.7822320461273193, "step": 80200 }, { "epoch": 2.2664896096740925, "grad_norm": 3.882172107696533, "learning_rate": 1.547443745977307e-05, "loss": 0.7941802024841309, "step": 80220 }, { "epoch": 2.2670546851823072, "grad_norm": 4.479428291320801, "learning_rate": 1.5451916777861002e-05, "loss": 0.8487833976745606, "step": 80240 }, { "epoch": 2.2676197606905224, "grad_norm": 3.208887815475464, "learning_rate": 1.542940950019578e-05, "loss": 0.7530840396881103, "step": 80260 }, { "epoch": 2.268184836198737, "grad_norm": 3.808974027633667, "learning_rate": 1.5406915635509932e-05, "loss": 0.7650301933288575, "step": 80280 }, { "epoch": 2.268749911706952, "grad_norm": 4.045953750610352, "learning_rate": 1.5384435192530826e-05, "loss": 0.855587387084961, "step": 80300 }, { "epoch": 2.2693149872151666, "grad_norm": 5.138125896453857, "learning_rate": 1.5361968179980592e-05, "loss": 0.7241320610046387, "step": 80320 }, { "epoch": 2.2698800627233813, "grad_norm": 3.6970198154449463, "learning_rate": 1.5339514606576176e-05, "loss": 0.7693186283111573, "step": 80340 }, { "epoch": 2.2704451382315964, "grad_norm": 3.5738184452056885, "learning_rate": 1.5317074481029304e-05, "loss": 0.83582763671875, "step": 80360 }, { "epoch": 2.271010213739811, "grad_norm": 3.292973041534424, "learning_rate": 1.529464781204647e-05, "loss": 0.7776636600494384, "step": 80380 }, { "epoch": 2.271575289248026, "grad_norm": 3.7759037017822266, "learning_rate": 1.5272234608328938e-05, "loss": 0.7580859184265136, "step": 80400 }, { "epoch": 2.2721403647562406, "grad_norm": 4.279855251312256, "learning_rate": 1.5249834878572806e-05, "loss": 0.8222249984741211, "step": 80420 }, { "epoch": 2.2727054402644553, "grad_norm": 3.3471932411193848, "learning_rate": 1.5227448631468877e-05, "loss": 0.8108893394470215, "step": 80440 }, { "epoch": 2.27327051577267, "grad_norm": 3.6906511783599854, "learning_rate": 1.520507587570275e-05, "loss": 0.8450224876403809, "step": 80460 }, { "epoch": 2.2738355912808847, "grad_norm": 2.784250497817993, "learning_rate": 1.5182716619954768e-05, "loss": 0.726308012008667, "step": 80480 }, { "epoch": 2.2744006667890995, "grad_norm": 5.069814682006836, "learning_rate": 1.516037087290011e-05, "loss": 0.7884685039520264, "step": 80500 }, { "epoch": 2.2749657422973146, "grad_norm": 4.205713748931885, "learning_rate": 1.5138038643208635e-05, "loss": 0.7813305854797363, "step": 80520 }, { "epoch": 2.2755308178055293, "grad_norm": 4.36079740524292, "learning_rate": 1.5115719939544981e-05, "loss": 0.7136820793151856, "step": 80540 }, { "epoch": 2.276095893313744, "grad_norm": 2.5034942626953125, "learning_rate": 1.5093414770568525e-05, "loss": 0.6796653747558594, "step": 80560 }, { "epoch": 2.276660968821959, "grad_norm": 4.06275749206543, "learning_rate": 1.5071123144933441e-05, "loss": 0.818907642364502, "step": 80580 }, { "epoch": 2.2772260443301735, "grad_norm": 3.7020087242126465, "learning_rate": 1.5048845071288597e-05, "loss": 0.7686077117919922, "step": 80600 }, { "epoch": 2.2777911198383882, "grad_norm": 3.8640809059143066, "learning_rate": 1.5026580558277625e-05, "loss": 0.7591675281524658, "step": 80620 }, { "epoch": 2.2783561953466034, "grad_norm": 4.029528617858887, "learning_rate": 1.500432961453888e-05, "loss": 0.7110762596130371, "step": 80640 }, { "epoch": 2.278921270854818, "grad_norm": 3.7926220893859863, "learning_rate": 1.4982092248705487e-05, "loss": 0.807093620300293, "step": 80660 }, { "epoch": 2.279486346363033, "grad_norm": 2.7458248138427734, "learning_rate": 1.495986846940527e-05, "loss": 0.8081642150878906, "step": 80680 }, { "epoch": 2.2800514218712475, "grad_norm": 5.184706687927246, "learning_rate": 1.4937658285260786e-05, "loss": 0.8035412788391113, "step": 80700 }, { "epoch": 2.2806164973794623, "grad_norm": 3.62939190864563, "learning_rate": 1.4915461704889316e-05, "loss": 0.7969812393188477, "step": 80720 }, { "epoch": 2.281181572887677, "grad_norm": 3.66528582572937, "learning_rate": 1.4893278736902894e-05, "loss": 0.9171151161193848, "step": 80740 }, { "epoch": 2.2817466483958917, "grad_norm": 2.9189789295196533, "learning_rate": 1.487110938990824e-05, "loss": 0.7724376678466797, "step": 80760 }, { "epoch": 2.282311723904107, "grad_norm": 4.403928279876709, "learning_rate": 1.4848953672506793e-05, "loss": 0.7540390014648437, "step": 80780 }, { "epoch": 2.2828767994123216, "grad_norm": 4.722652912139893, "learning_rate": 1.4826811593294692e-05, "loss": 0.8538131713867188, "step": 80800 }, { "epoch": 2.2834418749205363, "grad_norm": 5.033580303192139, "learning_rate": 1.4804683160862825e-05, "loss": 0.7974216938018799, "step": 80820 }, { "epoch": 2.284006950428751, "grad_norm": 4.15449857711792, "learning_rate": 1.4782568383796768e-05, "loss": 0.8010878562927246, "step": 80840 }, { "epoch": 2.2845720259369657, "grad_norm": 3.635573148727417, "learning_rate": 1.4760467270676781e-05, "loss": 0.7526412963867187, "step": 80860 }, { "epoch": 2.2851371014451805, "grad_norm": 4.08115291595459, "learning_rate": 1.4738379830077836e-05, "loss": 0.826118278503418, "step": 80880 }, { "epoch": 2.2857021769533956, "grad_norm": 3.4142353534698486, "learning_rate": 1.4716306070569574e-05, "loss": 0.817654800415039, "step": 80900 }, { "epoch": 2.2862672524616103, "grad_norm": 4.138049125671387, "learning_rate": 1.4694246000716393e-05, "loss": 0.8091878890991211, "step": 80920 }, { "epoch": 2.286832327969825, "grad_norm": 3.20154070854187, "learning_rate": 1.4672199629077322e-05, "loss": 0.8152887344360351, "step": 80940 }, { "epoch": 2.2873974034780398, "grad_norm": 3.1460394859313965, "learning_rate": 1.4650166964206086e-05, "loss": 0.7785624504089356, "step": 80960 }, { "epoch": 2.2879624789862545, "grad_norm": 3.1590864658355713, "learning_rate": 1.4628148014651083e-05, "loss": 0.7330465316772461, "step": 80980 }, { "epoch": 2.288527554494469, "grad_norm": 2.6811254024505615, "learning_rate": 1.4606142788955441e-05, "loss": 0.8578168869018554, "step": 81000 }, { "epoch": 2.289092630002684, "grad_norm": 3.1791329383850098, "learning_rate": 1.4584151295656912e-05, "loss": 0.8873350143432617, "step": 81020 }, { "epoch": 2.2896577055108986, "grad_norm": 4.111835479736328, "learning_rate": 1.4562173543287927e-05, "loss": 0.7886018753051758, "step": 81040 }, { "epoch": 2.290222781019114, "grad_norm": 4.492977142333984, "learning_rate": 1.4540209540375577e-05, "loss": 0.7406282424926758, "step": 81060 }, { "epoch": 2.2907878565273285, "grad_norm": 3.74033522605896, "learning_rate": 1.4518259295441678e-05, "loss": 0.7566552639007569, "step": 81080 }, { "epoch": 2.2913529320355432, "grad_norm": 3.1736559867858887, "learning_rate": 1.4496322817002638e-05, "loss": 0.732465124130249, "step": 81100 }, { "epoch": 2.291918007543758, "grad_norm": 3.752671718597412, "learning_rate": 1.4474400113569559e-05, "loss": 0.7307399272918701, "step": 81120 }, { "epoch": 2.2924830830519727, "grad_norm": 3.9970967769622803, "learning_rate": 1.4452491193648149e-05, "loss": 0.7858337879180908, "step": 81140 }, { "epoch": 2.293048158560188, "grad_norm": 3.5133605003356934, "learning_rate": 1.4430596065738882e-05, "loss": 0.7923203468322754, "step": 81160 }, { "epoch": 2.2936132340684026, "grad_norm": 4.4975996017456055, "learning_rate": 1.440871473833677e-05, "loss": 0.8134217262268066, "step": 81180 }, { "epoch": 2.2941783095766173, "grad_norm": 2.9751837253570557, "learning_rate": 1.438684721993151e-05, "loss": 0.866635799407959, "step": 81200 }, { "epoch": 2.294743385084832, "grad_norm": 5.290301322937012, "learning_rate": 1.4364993519007426e-05, "loss": 0.7934330463409424, "step": 81220 }, { "epoch": 2.2953084605930467, "grad_norm": 3.644225835800171, "learning_rate": 1.4343153644043527e-05, "loss": 0.7721847534179688, "step": 81240 }, { "epoch": 2.2958735361012614, "grad_norm": 3.3702657222747803, "learning_rate": 1.4321327603513408e-05, "loss": 0.7322246074676514, "step": 81260 }, { "epoch": 2.296438611609476, "grad_norm": 2.762162446975708, "learning_rate": 1.429951540588531e-05, "loss": 0.805355167388916, "step": 81280 }, { "epoch": 2.297003687117691, "grad_norm": 3.3985722064971924, "learning_rate": 1.4277717059622104e-05, "loss": 0.8399263381958008, "step": 81300 }, { "epoch": 2.297568762625906, "grad_norm": 3.2825920581817627, "learning_rate": 1.4255932573181308e-05, "loss": 0.8009817123413085, "step": 81320 }, { "epoch": 2.2981338381341208, "grad_norm": 3.4125871658325195, "learning_rate": 1.4234161955015035e-05, "loss": 0.774392032623291, "step": 81340 }, { "epoch": 2.2986989136423355, "grad_norm": 2.8571324348449707, "learning_rate": 1.4212405213570028e-05, "loss": 0.7842702388763427, "step": 81360 }, { "epoch": 2.29926398915055, "grad_norm": 4.901949405670166, "learning_rate": 1.4190662357287627e-05, "loss": 0.7509865283966064, "step": 81380 }, { "epoch": 2.299829064658765, "grad_norm": 4.714860916137695, "learning_rate": 1.4168933394603833e-05, "loss": 0.7828945636749267, "step": 81400 }, { "epoch": 2.3003941401669796, "grad_norm": 4.296299457550049, "learning_rate": 1.4147218333949207e-05, "loss": 0.7465278148651123, "step": 81420 }, { "epoch": 2.300959215675195, "grad_norm": 4.002254009246826, "learning_rate": 1.4125517183748948e-05, "loss": 0.7875649452209472, "step": 81440 }, { "epoch": 2.3015242911834095, "grad_norm": 5.143505096435547, "learning_rate": 1.4103829952422814e-05, "loss": 0.8440805435180664, "step": 81460 }, { "epoch": 2.3020893666916242, "grad_norm": 3.780613422393799, "learning_rate": 1.408215664838522e-05, "loss": 0.8271028518676757, "step": 81480 }, { "epoch": 2.302654442199839, "grad_norm": 3.2447052001953125, "learning_rate": 1.4060497280045164e-05, "loss": 0.8065423965454102, "step": 81500 }, { "epoch": 2.3032195177080537, "grad_norm": 2.9157891273498535, "learning_rate": 1.4038851855806206e-05, "loss": 0.7603499412536621, "step": 81520 }, { "epoch": 2.3037845932162684, "grad_norm": 4.684916973114014, "learning_rate": 1.4017220384066515e-05, "loss": 0.8203575134277343, "step": 81540 }, { "epoch": 2.304349668724483, "grad_norm": 2.1121842861175537, "learning_rate": 1.3995602873218833e-05, "loss": 0.7920024394989014, "step": 81560 }, { "epoch": 2.3049147442326983, "grad_norm": 4.452271938323975, "learning_rate": 1.3973999331650522e-05, "loss": 0.792746639251709, "step": 81580 }, { "epoch": 2.305479819740913, "grad_norm": 3.12353515625, "learning_rate": 1.3952409767743496e-05, "loss": 0.6926276206970214, "step": 81600 }, { "epoch": 2.3060448952491277, "grad_norm": 3.706200361251831, "learning_rate": 1.3930834189874236e-05, "loss": 0.7648197650909424, "step": 81620 }, { "epoch": 2.3066099707573424, "grad_norm": 4.218122482299805, "learning_rate": 1.3909272606413809e-05, "loss": 0.7627655982971191, "step": 81640 }, { "epoch": 2.307175046265557, "grad_norm": 3.461519479751587, "learning_rate": 1.3887725025727876e-05, "loss": 0.7501046657562256, "step": 81660 }, { "epoch": 2.307740121773772, "grad_norm": 3.3693926334381104, "learning_rate": 1.386619145617663e-05, "loss": 0.7820556163787842, "step": 81680 }, { "epoch": 2.308305197281987, "grad_norm": 5.965185642242432, "learning_rate": 1.3844671906114837e-05, "loss": 0.7382539749145508, "step": 81700 }, { "epoch": 2.3088702727902017, "grad_norm": 2.7881479263305664, "learning_rate": 1.3823166383891822e-05, "loss": 0.8532247543334961, "step": 81720 }, { "epoch": 2.3094353482984165, "grad_norm": 3.309769630432129, "learning_rate": 1.3801674897851491e-05, "loss": 0.7818784713745117, "step": 81740 }, { "epoch": 2.310000423806631, "grad_norm": 5.207481384277344, "learning_rate": 1.3780197456332277e-05, "loss": 0.8044872283935547, "step": 81760 }, { "epoch": 2.310565499314846, "grad_norm": 4.495160102844238, "learning_rate": 1.3758734067667172e-05, "loss": 0.8321401596069335, "step": 81780 }, { "epoch": 2.3111305748230606, "grad_norm": 4.778069972991943, "learning_rate": 1.3737284740183693e-05, "loss": 0.9233972549438476, "step": 81800 }, { "epoch": 2.3116956503312753, "grad_norm": 2.38356351852417, "learning_rate": 1.3715849482203969e-05, "loss": 0.843499755859375, "step": 81820 }, { "epoch": 2.3122607258394905, "grad_norm": 3.4806809425354004, "learning_rate": 1.3694428302044609e-05, "loss": 0.8084514617919922, "step": 81840 }, { "epoch": 2.312825801347705, "grad_norm": 4.540796756744385, "learning_rate": 1.3673021208016779e-05, "loss": 0.7504607677459717, "step": 81860 }, { "epoch": 2.31339087685592, "grad_norm": 2.542572259902954, "learning_rate": 1.3651628208426148e-05, "loss": 0.8236981391906738, "step": 81880 }, { "epoch": 2.3139559523641346, "grad_norm": 3.7355992794036865, "learning_rate": 1.363024931157299e-05, "loss": 0.7568394184112549, "step": 81900 }, { "epoch": 2.3145210278723494, "grad_norm": 3.7950165271759033, "learning_rate": 1.3608884525752047e-05, "loss": 0.7853872776031494, "step": 81920 }, { "epoch": 2.315086103380564, "grad_norm": 2.9277284145355225, "learning_rate": 1.3587533859252599e-05, "loss": 0.7758684635162354, "step": 81940 }, { "epoch": 2.3156511788887792, "grad_norm": 4.019928932189941, "learning_rate": 1.356619732035843e-05, "loss": 0.8088485717773437, "step": 81960 }, { "epoch": 2.316216254396994, "grad_norm": 3.2696330547332764, "learning_rate": 1.354487491734791e-05, "loss": 0.7665602207183838, "step": 81980 }, { "epoch": 2.3167813299052087, "grad_norm": 4.743733882904053, "learning_rate": 1.3523566658493853e-05, "loss": 0.7937307834625245, "step": 82000 }, { "epoch": 2.3173464054134234, "grad_norm": 6.254756927490234, "learning_rate": 1.3502272552063611e-05, "loss": 0.785880184173584, "step": 82020 }, { "epoch": 2.317911480921638, "grad_norm": 3.7794063091278076, "learning_rate": 1.3480992606319031e-05, "loss": 0.7838637351989746, "step": 82040 }, { "epoch": 2.318476556429853, "grad_norm": 2.636167049407959, "learning_rate": 1.3459726829516516e-05, "loss": 0.710435152053833, "step": 82060 }, { "epoch": 2.3190416319380676, "grad_norm": 3.764566659927368, "learning_rate": 1.343847522990691e-05, "loss": 0.7676219463348388, "step": 82080 }, { "epoch": 2.3196067074462823, "grad_norm": 3.31276273727417, "learning_rate": 1.3417237815735589e-05, "loss": 0.8416424751281738, "step": 82100 }, { "epoch": 2.3201717829544974, "grad_norm": 4.087599277496338, "learning_rate": 1.33960145952424e-05, "loss": 0.7453144550323486, "step": 82120 }, { "epoch": 2.320736858462712, "grad_norm": 5.242518901824951, "learning_rate": 1.337480557666172e-05, "loss": 0.8434710502624512, "step": 82140 }, { "epoch": 2.321301933970927, "grad_norm": 3.1520121097564697, "learning_rate": 1.3353610768222408e-05, "loss": 0.7567298412322998, "step": 82160 }, { "epoch": 2.3218670094791416, "grad_norm": 4.0882062911987305, "learning_rate": 1.3332430178147781e-05, "loss": 0.880281925201416, "step": 82180 }, { "epoch": 2.3224320849873563, "grad_norm": 4.073628902435303, "learning_rate": 1.3311263814655661e-05, "loss": 0.8264787673950196, "step": 82200 }, { "epoch": 2.322997160495571, "grad_norm": 3.290713310241699, "learning_rate": 1.3290111685958335e-05, "loss": 0.7501272201538086, "step": 82220 }, { "epoch": 2.323562236003786, "grad_norm": 4.209397315979004, "learning_rate": 1.3268973800262596e-05, "loss": 0.8168806076049805, "step": 82240 }, { "epoch": 2.324127311512001, "grad_norm": 3.0544826984405518, "learning_rate": 1.3247850165769693e-05, "loss": 0.7443465709686279, "step": 82260 }, { "epoch": 2.3246923870202156, "grad_norm": 2.6576356887817383, "learning_rate": 1.3226740790675335e-05, "loss": 0.7226147651672363, "step": 82280 }, { "epoch": 2.3252574625284304, "grad_norm": 4.020327568054199, "learning_rate": 1.3205645683169693e-05, "loss": 0.7769548892974854, "step": 82300 }, { "epoch": 2.325822538036645, "grad_norm": 3.4038808345794678, "learning_rate": 1.3184564851437458e-05, "loss": 0.7834347248077392, "step": 82320 }, { "epoch": 2.32638761354486, "grad_norm": 3.1743760108947754, "learning_rate": 1.3163498303657723e-05, "loss": 0.7240900993347168, "step": 82340 }, { "epoch": 2.3269526890530745, "grad_norm": 4.339410781860352, "learning_rate": 1.3142446048004065e-05, "loss": 0.7445759773254395, "step": 82360 }, { "epoch": 2.3275177645612897, "grad_norm": 4.210756301879883, "learning_rate": 1.3121408092644482e-05, "loss": 0.7898149490356445, "step": 82380 }, { "epoch": 2.3280828400695044, "grad_norm": 5.174499034881592, "learning_rate": 1.3100384445741487e-05, "loss": 0.8463150024414062, "step": 82400 }, { "epoch": 2.328647915577719, "grad_norm": 5.02923583984375, "learning_rate": 1.3079375115451997e-05, "loss": 0.7222788333892822, "step": 82420 }, { "epoch": 2.329212991085934, "grad_norm": 3.6966371536254883, "learning_rate": 1.3058380109927376e-05, "loss": 0.8028740882873535, "step": 82440 }, { "epoch": 2.3297780665941485, "grad_norm": 2.941741704940796, "learning_rate": 1.3037399437313408e-05, "loss": 0.7975917816162109, "step": 82460 }, { "epoch": 2.3303431421023633, "grad_norm": 3.8282110691070557, "learning_rate": 1.3016433105750408e-05, "loss": 0.7376543045043945, "step": 82480 }, { "epoch": 2.3309082176105784, "grad_norm": 3.971191167831421, "learning_rate": 1.2995481123373038e-05, "loss": 0.7926918983459472, "step": 82500 }, { "epoch": 2.331473293118793, "grad_norm": 4.074705123901367, "learning_rate": 1.297454349831041e-05, "loss": 0.7405814170837403, "step": 82520 }, { "epoch": 2.332038368627008, "grad_norm": 3.4247710704803467, "learning_rate": 1.295362023868606e-05, "loss": 0.729137372970581, "step": 82540 }, { "epoch": 2.3326034441352226, "grad_norm": 2.154315948486328, "learning_rate": 1.2932711352618004e-05, "loss": 0.8503626823425293, "step": 82560 }, { "epoch": 2.3331685196434373, "grad_norm": 3.0894360542297363, "learning_rate": 1.2911816848218617e-05, "loss": 0.7831286907196044, "step": 82580 }, { "epoch": 2.333733595151652, "grad_norm": 2.538086414337158, "learning_rate": 1.2890936733594721e-05, "loss": 0.8261680603027344, "step": 82600 }, { "epoch": 2.3342986706598667, "grad_norm": 2.0446207523345947, "learning_rate": 1.2870071016847546e-05, "loss": 0.7955878257751465, "step": 82620 }, { "epoch": 2.334863746168082, "grad_norm": 4.4102888107299805, "learning_rate": 1.2849219706072763e-05, "loss": 0.8082730293273925, "step": 82640 }, { "epoch": 2.3354288216762966, "grad_norm": 3.9884684085845947, "learning_rate": 1.2828382809360423e-05, "loss": 0.7749831676483154, "step": 82660 }, { "epoch": 2.3359938971845113, "grad_norm": 3.637664556503296, "learning_rate": 1.2807560334794993e-05, "loss": 0.7975213050842285, "step": 82680 }, { "epoch": 2.336558972692726, "grad_norm": 3.057943820953369, "learning_rate": 1.2786752290455334e-05, "loss": 0.7870500087738037, "step": 82700 }, { "epoch": 2.3371240482009408, "grad_norm": 3.5595173835754395, "learning_rate": 1.2765958684414747e-05, "loss": 0.8107622146606446, "step": 82720 }, { "epoch": 2.3376891237091555, "grad_norm": 5.820321559906006, "learning_rate": 1.2745179524740897e-05, "loss": 0.8159497261047364, "step": 82740 }, { "epoch": 2.3382541992173707, "grad_norm": 4.851790428161621, "learning_rate": 1.272441481949584e-05, "loss": 0.7151447296142578, "step": 82760 }, { "epoch": 2.3388192747255854, "grad_norm": 3.687507152557373, "learning_rate": 1.270366457673603e-05, "loss": 0.7189755439758301, "step": 82780 }, { "epoch": 2.3393843502338, "grad_norm": 2.969515323638916, "learning_rate": 1.2682928804512329e-05, "loss": 0.7653630256652832, "step": 82800 }, { "epoch": 2.339949425742015, "grad_norm": 5.257813453674316, "learning_rate": 1.2662207510869983e-05, "loss": 0.7629103183746337, "step": 82820 }, { "epoch": 2.3405145012502295, "grad_norm": 4.004858493804932, "learning_rate": 1.2641500703848596e-05, "loss": 0.7450492858886719, "step": 82840 }, { "epoch": 2.3410795767584442, "grad_norm": 5.0034565925598145, "learning_rate": 1.2620808391482158e-05, "loss": 0.7665285587310791, "step": 82860 }, { "epoch": 2.341644652266659, "grad_norm": 3.6980679035186768, "learning_rate": 1.2600130581799036e-05, "loss": 0.8333803176879883, "step": 82880 }, { "epoch": 2.3422097277748737, "grad_norm": 3.253016710281372, "learning_rate": 1.2579467282821994e-05, "loss": 0.7634428024291993, "step": 82900 }, { "epoch": 2.342774803283089, "grad_norm": 4.200607776641846, "learning_rate": 1.2558818502568143e-05, "loss": 0.8215437889099121, "step": 82920 }, { "epoch": 2.3433398787913036, "grad_norm": 4.697434902191162, "learning_rate": 1.2538184249048951e-05, "loss": 0.7798111915588379, "step": 82940 }, { "epoch": 2.3439049542995183, "grad_norm": 4.10985803604126, "learning_rate": 1.2517564530270265e-05, "loss": 0.7683693885803222, "step": 82960 }, { "epoch": 2.344470029807733, "grad_norm": 3.9709997177124023, "learning_rate": 1.2496959354232313e-05, "loss": 0.7818724155426026, "step": 82980 }, { "epoch": 2.3450351053159477, "grad_norm": 4.199160099029541, "learning_rate": 1.2476368728929638e-05, "loss": 0.7719195365905762, "step": 83000 }, { "epoch": 2.3456001808241624, "grad_norm": 3.2973756790161133, "learning_rate": 1.2455792662351174e-05, "loss": 0.8273377418518066, "step": 83020 }, { "epoch": 2.3461652563323776, "grad_norm": 3.622976064682007, "learning_rate": 1.243523116248016e-05, "loss": 0.7549376964569092, "step": 83040 }, { "epoch": 2.3467303318405923, "grad_norm": 4.0658087730407715, "learning_rate": 1.2414684237294255e-05, "loss": 0.72293119430542, "step": 83060 }, { "epoch": 2.347295407348807, "grad_norm": 5.088714599609375, "learning_rate": 1.2394151894765405e-05, "loss": 0.7859160423278808, "step": 83080 }, { "epoch": 2.3478604828570218, "grad_norm": 2.819171667098999, "learning_rate": 1.2373634142859914e-05, "loss": 0.7045097351074219, "step": 83100 }, { "epoch": 2.3484255583652365, "grad_norm": 3.7941627502441406, "learning_rate": 1.2353130989538408e-05, "loss": 0.8186097145080566, "step": 83120 }, { "epoch": 2.348990633873451, "grad_norm": 3.5820887088775635, "learning_rate": 1.2332642442755893e-05, "loss": 0.7793148040771485, "step": 83140 }, { "epoch": 2.349555709381666, "grad_norm": 3.360745906829834, "learning_rate": 1.2312168510461686e-05, "loss": 0.7904468536376953, "step": 83160 }, { "epoch": 2.350120784889881, "grad_norm": 4.449474811553955, "learning_rate": 1.2291709200599427e-05, "loss": 0.8119724273681641, "step": 83180 }, { "epoch": 2.350685860398096, "grad_norm": 4.980803966522217, "learning_rate": 1.2271264521107057e-05, "loss": 0.7732424736022949, "step": 83200 }, { "epoch": 2.3512509359063105, "grad_norm": 3.544820785522461, "learning_rate": 1.2250834479916905e-05, "loss": 0.8347243309020996, "step": 83220 }, { "epoch": 2.3518160114145252, "grad_norm": 3.759171962738037, "learning_rate": 1.2230419084955574e-05, "loss": 0.7634744644165039, "step": 83240 }, { "epoch": 2.35238108692274, "grad_norm": 4.335824489593506, "learning_rate": 1.2210018344143997e-05, "loss": 0.7317697525024414, "step": 83260 }, { "epoch": 2.3529461624309547, "grad_norm": 3.2003560066223145, "learning_rate": 1.2189632265397395e-05, "loss": 0.708723783493042, "step": 83280 }, { "epoch": 2.35351123793917, "grad_norm": 3.9061765670776367, "learning_rate": 1.216926085662536e-05, "loss": 0.7696092605590821, "step": 83300 }, { "epoch": 2.3540763134473845, "grad_norm": 3.3495635986328125, "learning_rate": 1.2148904125731742e-05, "loss": 0.7403831481933594, "step": 83320 }, { "epoch": 2.3546413889555993, "grad_norm": 3.308730125427246, "learning_rate": 1.2128562080614708e-05, "loss": 0.6766162395477295, "step": 83340 }, { "epoch": 2.355206464463814, "grad_norm": 2.6399943828582764, "learning_rate": 1.2108234729166724e-05, "loss": 0.7793753147125244, "step": 83360 }, { "epoch": 2.3557715399720287, "grad_norm": 3.9712560176849365, "learning_rate": 1.2087922079274583e-05, "loss": 0.7407863140106201, "step": 83380 }, { "epoch": 2.3563366154802434, "grad_norm": 2.667463779449463, "learning_rate": 1.2067624138819344e-05, "loss": 0.7078051567077637, "step": 83400 }, { "epoch": 2.356901690988458, "grad_norm": 4.340091228485107, "learning_rate": 1.2047340915676358e-05, "loss": 0.7842981815338135, "step": 83420 }, { "epoch": 2.3574667664966733, "grad_norm": 3.6220810413360596, "learning_rate": 1.2027072417715274e-05, "loss": 0.770440149307251, "step": 83440 }, { "epoch": 2.358031842004888, "grad_norm": 2.4401025772094727, "learning_rate": 1.2006818652800028e-05, "loss": 0.8070019721984864, "step": 83460 }, { "epoch": 2.3585969175131027, "grad_norm": 3.0397157669067383, "learning_rate": 1.1986579628788868e-05, "loss": 0.7861456394195556, "step": 83480 }, { "epoch": 2.3591619930213175, "grad_norm": 4.323162078857422, "learning_rate": 1.1966355353534276e-05, "loss": 0.7738558292388916, "step": 83500 }, { "epoch": 2.359727068529532, "grad_norm": 3.8684842586517334, "learning_rate": 1.1946145834883033e-05, "loss": 0.7783700942993164, "step": 83520 }, { "epoch": 2.360292144037747, "grad_norm": 3.277006149291992, "learning_rate": 1.1925951080676173e-05, "loss": 0.759977912902832, "step": 83540 }, { "epoch": 2.360857219545962, "grad_norm": 4.700310230255127, "learning_rate": 1.1905771098749052e-05, "loss": 0.7681956768035889, "step": 83560 }, { "epoch": 2.361422295054177, "grad_norm": 4.123680591583252, "learning_rate": 1.1885605896931257e-05, "loss": 0.7177043437957764, "step": 83580 }, { "epoch": 2.3619873705623915, "grad_norm": 3.2494277954101562, "learning_rate": 1.1865455483046639e-05, "loss": 0.7386969089508056, "step": 83600 }, { "epoch": 2.362552446070606, "grad_norm": 3.0520942211151123, "learning_rate": 1.1845319864913306e-05, "loss": 0.8021201133728028, "step": 83620 }, { "epoch": 2.363117521578821, "grad_norm": 3.184147834777832, "learning_rate": 1.1825199050343671e-05, "loss": 0.7381375789642334, "step": 83640 }, { "epoch": 2.3636825970870357, "grad_norm": 4.636650085449219, "learning_rate": 1.1805093047144355e-05, "loss": 0.7047631740570068, "step": 83660 }, { "epoch": 2.3642476725952504, "grad_norm": 3.2415664196014404, "learning_rate": 1.1785001863116252e-05, "loss": 0.7917477130889893, "step": 83680 }, { "epoch": 2.364812748103465, "grad_norm": 6.082545280456543, "learning_rate": 1.1764925506054486e-05, "loss": 0.7733253002166748, "step": 83700 }, { "epoch": 2.3653778236116803, "grad_norm": 2.830172300338745, "learning_rate": 1.1744863983748477e-05, "loss": 0.7329069137573242, "step": 83720 }, { "epoch": 2.365942899119895, "grad_norm": 4.401980876922607, "learning_rate": 1.1724817303981839e-05, "loss": 0.7528052806854248, "step": 83740 }, { "epoch": 2.3665079746281097, "grad_norm": 2.8230717182159424, "learning_rate": 1.1704785474532454e-05, "loss": 0.8093035697937012, "step": 83760 }, { "epoch": 2.3670730501363244, "grad_norm": 3.641228199005127, "learning_rate": 1.168476850317241e-05, "loss": 0.8188260078430176, "step": 83780 }, { "epoch": 2.367638125644539, "grad_norm": 3.5060501098632812, "learning_rate": 1.1664766397668075e-05, "loss": 0.8045381546020508, "step": 83800 }, { "epoch": 2.368203201152754, "grad_norm": 3.1559157371520996, "learning_rate": 1.164477916578004e-05, "loss": 0.8188864707946777, "step": 83820 }, { "epoch": 2.368768276660969, "grad_norm": 3.6556928157806396, "learning_rate": 1.16248068152631e-05, "loss": 0.8058143615722656, "step": 83840 }, { "epoch": 2.3693333521691837, "grad_norm": 3.2093284130096436, "learning_rate": 1.1604849353866288e-05, "loss": 0.783805513381958, "step": 83860 }, { "epoch": 2.3698984276773984, "grad_norm": 2.9235048294067383, "learning_rate": 1.1584906789332873e-05, "loss": 0.7930412769317627, "step": 83880 }, { "epoch": 2.370463503185613, "grad_norm": 4.376664638519287, "learning_rate": 1.1564979129400327e-05, "loss": 0.7847588539123536, "step": 83900 }, { "epoch": 2.371028578693828, "grad_norm": 5.285249710083008, "learning_rate": 1.1545066381800346e-05, "loss": 0.7979694366455078, "step": 83920 }, { "epoch": 2.3715936542020426, "grad_norm": 3.3885996341705322, "learning_rate": 1.152516855425883e-05, "loss": 0.788667106628418, "step": 83940 }, { "epoch": 2.3721587297102573, "grad_norm": 4.375945568084717, "learning_rate": 1.1505285654495923e-05, "loss": 0.834808349609375, "step": 83960 }, { "epoch": 2.3727238052184725, "grad_norm": 4.653935432434082, "learning_rate": 1.148541769022594e-05, "loss": 0.6925000667572021, "step": 83980 }, { "epoch": 2.373288880726687, "grad_norm": 5.054378032684326, "learning_rate": 1.146556466915742e-05, "loss": 0.7941573143005372, "step": 84000 }, { "epoch": 2.373853956234902, "grad_norm": 3.4178590774536133, "learning_rate": 1.1445726598993085e-05, "loss": 0.7755790233612061, "step": 84020 }, { "epoch": 2.3744190317431166, "grad_norm": 3.862189769744873, "learning_rate": 1.142590348742989e-05, "loss": 0.7613359928131104, "step": 84040 }, { "epoch": 2.3749841072513314, "grad_norm": 4.444727420806885, "learning_rate": 1.1406095342158968e-05, "loss": 0.7511565685272217, "step": 84060 }, { "epoch": 2.375549182759546, "grad_norm": 4.7633256912231445, "learning_rate": 1.1386302170865638e-05, "loss": 0.7709274291992188, "step": 84080 }, { "epoch": 2.3761142582677612, "grad_norm": 2.5754776000976562, "learning_rate": 1.1366523981229399e-05, "loss": 0.7522830486297607, "step": 84100 }, { "epoch": 2.376679333775976, "grad_norm": 4.586276054382324, "learning_rate": 1.134676078092397e-05, "loss": 0.7793413639068604, "step": 84120 }, { "epoch": 2.3772444092841907, "grad_norm": 3.0785374641418457, "learning_rate": 1.1327012577617252e-05, "loss": 0.8259894371032714, "step": 84140 }, { "epoch": 2.3778094847924054, "grad_norm": 4.941317081451416, "learning_rate": 1.1307279378971303e-05, "loss": 0.7400146961212158, "step": 84160 }, { "epoch": 2.37837456030062, "grad_norm": 3.929921865463257, "learning_rate": 1.1287561192642365e-05, "loss": 0.7471573829650879, "step": 84180 }, { "epoch": 2.378939635808835, "grad_norm": 3.9332501888275146, "learning_rate": 1.1267858026280853e-05, "loss": 0.777916145324707, "step": 84200 }, { "epoch": 2.3795047113170495, "grad_norm": 3.3303756713867188, "learning_rate": 1.1248169887531385e-05, "loss": 0.8339418411254883, "step": 84220 }, { "epoch": 2.3800697868252647, "grad_norm": 4.358711242675781, "learning_rate": 1.1228496784032715e-05, "loss": 0.8216455459594727, "step": 84240 }, { "epoch": 2.3806348623334794, "grad_norm": 1.5923035144805908, "learning_rate": 1.1208838723417775e-05, "loss": 0.7951209068298339, "step": 84260 }, { "epoch": 2.381199937841694, "grad_norm": 3.3951621055603027, "learning_rate": 1.1189195713313639e-05, "loss": 0.747951078414917, "step": 84280 }, { "epoch": 2.381765013349909, "grad_norm": 4.1382975578308105, "learning_rate": 1.1169567761341592e-05, "loss": 0.7744330883026123, "step": 84300 }, { "epoch": 2.3823300888581236, "grad_norm": 3.3067054748535156, "learning_rate": 1.1149954875117035e-05, "loss": 0.7613057613372802, "step": 84320 }, { "epoch": 2.3828951643663383, "grad_norm": 4.141878128051758, "learning_rate": 1.1130357062249536e-05, "loss": 0.826261329650879, "step": 84340 }, { "epoch": 2.3834602398745535, "grad_norm": 4.040863513946533, "learning_rate": 1.11107743303428e-05, "loss": 0.7240976333618164, "step": 84360 }, { "epoch": 2.384025315382768, "grad_norm": 3.6922965049743652, "learning_rate": 1.1091206686994721e-05, "loss": 0.7762754917144775, "step": 84380 }, { "epoch": 2.384590390890983, "grad_norm": 3.6640658378601074, "learning_rate": 1.10716541397973e-05, "loss": 0.815501594543457, "step": 84400 }, { "epoch": 2.3851554663991976, "grad_norm": 3.7644436359405518, "learning_rate": 1.1052116696336695e-05, "loss": 0.7756116390228271, "step": 84420 }, { "epoch": 2.3857205419074123, "grad_norm": 4.178004264831543, "learning_rate": 1.1032594364193183e-05, "loss": 0.7926980972290039, "step": 84440 }, { "epoch": 2.386285617415627, "grad_norm": 6.506679058074951, "learning_rate": 1.1013087150941221e-05, "loss": 0.7395549774169922, "step": 84460 }, { "epoch": 2.3868506929238418, "grad_norm": 4.159578800201416, "learning_rate": 1.0993595064149382e-05, "loss": 0.799601936340332, "step": 84480 }, { "epoch": 2.3874157684320565, "grad_norm": 3.1551878452301025, "learning_rate": 1.097411811138035e-05, "loss": 0.7381839752197266, "step": 84500 }, { "epoch": 2.3879808439402717, "grad_norm": 4.208391189575195, "learning_rate": 1.0954656300190941e-05, "loss": 0.7512909889221191, "step": 84520 }, { "epoch": 2.3885459194484864, "grad_norm": 3.340456485748291, "learning_rate": 1.0935209638132143e-05, "loss": 0.777680778503418, "step": 84540 }, { "epoch": 2.389110994956701, "grad_norm": 5.1425323486328125, "learning_rate": 1.0915778132748999e-05, "loss": 0.8412992477416992, "step": 84560 }, { "epoch": 2.389676070464916, "grad_norm": 3.3675920963287354, "learning_rate": 1.0896361791580722e-05, "loss": 0.8018610954284668, "step": 84580 }, { "epoch": 2.3902411459731305, "grad_norm": 3.400738000869751, "learning_rate": 1.0876960622160592e-05, "loss": 0.7164946556091308, "step": 84600 }, { "epoch": 2.3908062214813453, "grad_norm": 3.9173061847686768, "learning_rate": 1.0857574632016071e-05, "loss": 0.8152475357055664, "step": 84620 }, { "epoch": 2.3913712969895604, "grad_norm": 3.8223178386688232, "learning_rate": 1.0838203828668676e-05, "loss": 0.7358336925506592, "step": 84640 }, { "epoch": 2.391936372497775, "grad_norm": 3.0121982097625732, "learning_rate": 1.0818848219634048e-05, "loss": 0.8343954086303711, "step": 84660 }, { "epoch": 2.39250144800599, "grad_norm": 2.4401166439056396, "learning_rate": 1.0799507812421917e-05, "loss": 0.677042293548584, "step": 84680 }, { "epoch": 2.3930665235142046, "grad_norm": 3.5367560386657715, "learning_rate": 1.0780182614536172e-05, "loss": 0.758472204208374, "step": 84700 }, { "epoch": 2.3936315990224193, "grad_norm": 4.3043904304504395, "learning_rate": 1.0760872633474734e-05, "loss": 0.7658045768737793, "step": 84720 }, { "epoch": 2.394196674530634, "grad_norm": 3.4725236892700195, "learning_rate": 1.0741577876729647e-05, "loss": 0.7745372772216796, "step": 84740 }, { "epoch": 2.3947617500388487, "grad_norm": 4.508697986602783, "learning_rate": 1.0722298351787047e-05, "loss": 0.7892178058624267, "step": 84760 }, { "epoch": 2.395326825547064, "grad_norm": 2.665072202682495, "learning_rate": 1.070303406612716e-05, "loss": 0.8577996253967285, "step": 84780 }, { "epoch": 2.3958919010552786, "grad_norm": 4.358849048614502, "learning_rate": 1.0683785027224325e-05, "loss": 0.859218692779541, "step": 84800 }, { "epoch": 2.3964569765634933, "grad_norm": 3.523416757583618, "learning_rate": 1.0664551242546921e-05, "loss": 0.7057406425476074, "step": 84820 }, { "epoch": 2.397022052071708, "grad_norm": 4.420276165008545, "learning_rate": 1.0645332719557427e-05, "loss": 0.8074054718017578, "step": 84840 }, { "epoch": 2.3975871275799228, "grad_norm": 4.518294334411621, "learning_rate": 1.0626129465712398e-05, "loss": 0.7871347427368164, "step": 84860 }, { "epoch": 2.3981522030881375, "grad_norm": 4.866281509399414, "learning_rate": 1.0606941488462485e-05, "loss": 0.8552992820739747, "step": 84880 }, { "epoch": 2.3987172785963526, "grad_norm": 3.7527010440826416, "learning_rate": 1.058776879525239e-05, "loss": 0.8181772232055664, "step": 84900 }, { "epoch": 2.3992823541045674, "grad_norm": 3.0076444149017334, "learning_rate": 1.0568611393520888e-05, "loss": 0.7659108638763428, "step": 84920 }, { "epoch": 2.399847429612782, "grad_norm": 4.282532691955566, "learning_rate": 1.054946929070081e-05, "loss": 0.8065922737121582, "step": 84940 }, { "epoch": 2.400412505120997, "grad_norm": 3.3374476432800293, "learning_rate": 1.0530342494219093e-05, "loss": 0.7803067684173584, "step": 84960 }, { "epoch": 2.4009775806292115, "grad_norm": 3.8729958534240723, "learning_rate": 1.0511231011496692e-05, "loss": 0.8231592178344727, "step": 84980 }, { "epoch": 2.4015426561374262, "grad_norm": 4.15248966217041, "learning_rate": 1.0492134849948637e-05, "loss": 0.7914824485778809, "step": 85000 }, { "epoch": 2.402107731645641, "grad_norm": 4.159509181976318, "learning_rate": 1.0473054016983997e-05, "loss": 0.7630951881408692, "step": 85020 }, { "epoch": 2.402672807153856, "grad_norm": 6.004925727844238, "learning_rate": 1.0453988520005936e-05, "loss": 0.7443535804748536, "step": 85040 }, { "epoch": 2.403237882662071, "grad_norm": 2.8808584213256836, "learning_rate": 1.0434938366411635e-05, "loss": 0.7880670070648194, "step": 85060 }, { "epoch": 2.4038029581702856, "grad_norm": 2.5390353202819824, "learning_rate": 1.0415903563592323e-05, "loss": 0.8160289764404297, "step": 85080 }, { "epoch": 2.4043680336785003, "grad_norm": 4.042405605316162, "learning_rate": 1.0396884118933253e-05, "loss": 0.7407596588134766, "step": 85100 }, { "epoch": 2.404933109186715, "grad_norm": 4.839715003967285, "learning_rate": 1.0377880039813775e-05, "loss": 0.7363058567047119, "step": 85120 }, { "epoch": 2.4054981846949297, "grad_norm": 3.4164817333221436, "learning_rate": 1.0358891333607257e-05, "loss": 0.7507744789123535, "step": 85140 }, { "epoch": 2.406063260203145, "grad_norm": 3.8430516719818115, "learning_rate": 1.0339918007681066e-05, "loss": 0.8200907707214355, "step": 85160 }, { "epoch": 2.4066283357113596, "grad_norm": 2.8672642707824707, "learning_rate": 1.032096006939664e-05, "loss": 0.7598097324371338, "step": 85180 }, { "epoch": 2.4071934112195743, "grad_norm": 3.5710201263427734, "learning_rate": 1.030201752610942e-05, "loss": 0.7179461002349854, "step": 85200 }, { "epoch": 2.407758486727789, "grad_norm": 2.6487033367156982, "learning_rate": 1.028309038516891e-05, "loss": 0.7962603092193603, "step": 85220 }, { "epoch": 2.4083235622360037, "grad_norm": 5.798426628112793, "learning_rate": 1.0264178653918599e-05, "loss": 0.8157235145568847, "step": 85240 }, { "epoch": 2.4088886377442185, "grad_norm": 3.524358034133911, "learning_rate": 1.0245282339696017e-05, "loss": 0.7984787464141846, "step": 85260 }, { "epoch": 2.409453713252433, "grad_norm": 2.673046827316284, "learning_rate": 1.0226401449832717e-05, "loss": 0.779768991470337, "step": 85280 }, { "epoch": 2.410018788760648, "grad_norm": 5.88630485534668, "learning_rate": 1.0207535991654266e-05, "loss": 0.8292757034301758, "step": 85300 }, { "epoch": 2.410583864268863, "grad_norm": 3.249605894088745, "learning_rate": 1.0188685972480223e-05, "loss": 0.7419206619262695, "step": 85320 }, { "epoch": 2.411148939777078, "grad_norm": 3.257596492767334, "learning_rate": 1.0169851399624164e-05, "loss": 0.7245604515075683, "step": 85340 }, { "epoch": 2.4117140152852925, "grad_norm": 4.979645252227783, "learning_rate": 1.0151032280393714e-05, "loss": 0.7855522632598877, "step": 85360 }, { "epoch": 2.412279090793507, "grad_norm": 4.295136451721191, "learning_rate": 1.0132228622090445e-05, "loss": 0.8294408798217774, "step": 85380 }, { "epoch": 2.412844166301722, "grad_norm": 3.535231590270996, "learning_rate": 1.0113440432009957e-05, "loss": 0.7401269912719727, "step": 85400 }, { "epoch": 2.413409241809937, "grad_norm": 4.007174015045166, "learning_rate": 1.009466771744183e-05, "loss": 0.750699234008789, "step": 85420 }, { "epoch": 2.413974317318152, "grad_norm": 2.949389934539795, "learning_rate": 1.0075910485669671e-05, "loss": 0.7318950176239014, "step": 85440 }, { "epoch": 2.4145393928263665, "grad_norm": 5.8050408363342285, "learning_rate": 1.0057168743971079e-05, "loss": 0.7490020275115967, "step": 85460 }, { "epoch": 2.4151044683345813, "grad_norm": 4.6892523765563965, "learning_rate": 1.0038442499617607e-05, "loss": 0.7729369640350342, "step": 85480 }, { "epoch": 2.415669543842796, "grad_norm": 4.962608814239502, "learning_rate": 1.0019731759874824e-05, "loss": 0.8201943397521972, "step": 85500 }, { "epoch": 2.4162346193510107, "grad_norm": 4.852030277252197, "learning_rate": 1.0001036532002251e-05, "loss": 0.835635757446289, "step": 85520 }, { "epoch": 2.4167996948592254, "grad_norm": 4.4257941246032715, "learning_rate": 9.982356823253452e-06, "loss": 0.7732503414154053, "step": 85540 }, { "epoch": 2.41736477036744, "grad_norm": 2.7557082176208496, "learning_rate": 9.963692640875921e-06, "loss": 0.8014350891113281, "step": 85560 }, { "epoch": 2.4179298458756553, "grad_norm": 5.273290634155273, "learning_rate": 9.945043992111126e-06, "loss": 0.8145781517028808, "step": 85580 }, { "epoch": 2.41849492138387, "grad_norm": 3.755037784576416, "learning_rate": 9.92641088419452e-06, "loss": 0.7816825866699219, "step": 85600 }, { "epoch": 2.4190599968920847, "grad_norm": 3.3451225757598877, "learning_rate": 9.907793324355552e-06, "loss": 0.7916551113128663, "step": 85620 }, { "epoch": 2.4196250724002994, "grad_norm": 3.5436673164367676, "learning_rate": 9.889191319817603e-06, "loss": 0.7381454944610596, "step": 85640 }, { "epoch": 2.420190147908514, "grad_norm": 3.602152109146118, "learning_rate": 9.870604877798023e-06, "loss": 0.7674891948699951, "step": 85660 }, { "epoch": 2.420755223416729, "grad_norm": 3.02756404876709, "learning_rate": 9.852034005508126e-06, "loss": 0.7821181297302247, "step": 85680 }, { "epoch": 2.421320298924944, "grad_norm": 5.190047264099121, "learning_rate": 9.83347871015321e-06, "loss": 0.8103974342346192, "step": 85700 }, { "epoch": 2.4218853744331588, "grad_norm": 4.2097578048706055, "learning_rate": 9.814938998932505e-06, "loss": 0.6790063858032227, "step": 85720 }, { "epoch": 2.4224504499413735, "grad_norm": 5.432483673095703, "learning_rate": 9.79641487903919e-06, "loss": 0.8215378761291504, "step": 85740 }, { "epoch": 2.423015525449588, "grad_norm": 3.2540664672851562, "learning_rate": 9.777906357660399e-06, "loss": 0.7017354011535645, "step": 85760 }, { "epoch": 2.423580600957803, "grad_norm": 2.9312026500701904, "learning_rate": 9.759413441977222e-06, "loss": 0.7380111694335938, "step": 85780 }, { "epoch": 2.4241456764660176, "grad_norm": 5.831116199493408, "learning_rate": 9.740936139164718e-06, "loss": 0.7178843975067138, "step": 85800 }, { "epoch": 2.4247107519742324, "grad_norm": 3.349933385848999, "learning_rate": 9.72247445639184e-06, "loss": 0.7027928829193115, "step": 85820 }, { "epoch": 2.4252758274824475, "grad_norm": 2.9121813774108887, "learning_rate": 9.704028400821497e-06, "loss": 0.8576474189758301, "step": 85840 }, { "epoch": 2.4258409029906622, "grad_norm": 3.34173583984375, "learning_rate": 9.685597979610533e-06, "loss": 0.7535797595977783, "step": 85860 }, { "epoch": 2.426405978498877, "grad_norm": 4.337006092071533, "learning_rate": 9.667183199909763e-06, "loss": 0.7663783073425293, "step": 85880 }, { "epoch": 2.4269710540070917, "grad_norm": 4.4047369956970215, "learning_rate": 9.648784068863886e-06, "loss": 0.7747152805328369, "step": 85900 }, { "epoch": 2.4275361295153064, "grad_norm": 3.382321357727051, "learning_rate": 9.630400593611533e-06, "loss": 0.7826601505279541, "step": 85920 }, { "epoch": 2.428101205023521, "grad_norm": 3.826883316040039, "learning_rate": 9.612032781285301e-06, "loss": 0.7141889572143555, "step": 85940 }, { "epoch": 2.4286662805317363, "grad_norm": 3.24593186378479, "learning_rate": 9.59368063901167e-06, "loss": 0.7575994014739991, "step": 85960 }, { "epoch": 2.429231356039951, "grad_norm": 3.9390177726745605, "learning_rate": 9.575344173911055e-06, "loss": 0.7229100704193115, "step": 85980 }, { "epoch": 2.4297964315481657, "grad_norm": 3.8023059368133545, "learning_rate": 9.557023393097775e-06, "loss": 0.8751662254333497, "step": 86000 }, { "epoch": 2.4303615070563804, "grad_norm": 5.4128546714782715, "learning_rate": 9.5387183036801e-06, "loss": 0.7681063175201416, "step": 86020 }, { "epoch": 2.430926582564595, "grad_norm": 3.016798257827759, "learning_rate": 9.520428912760176e-06, "loss": 0.7114534854888916, "step": 86040 }, { "epoch": 2.43149165807281, "grad_norm": 3.5259623527526855, "learning_rate": 9.502155227434068e-06, "loss": 0.73389892578125, "step": 86060 }, { "epoch": 2.4320567335810246, "grad_norm": 4.600218296051025, "learning_rate": 9.48389725479174e-06, "loss": 0.753520154953003, "step": 86080 }, { "epoch": 2.4326218090892393, "grad_norm": 3.3720645904541016, "learning_rate": 9.465655001917073e-06, "loss": 0.8722713470458985, "step": 86100 }, { "epoch": 2.4331868845974545, "grad_norm": 5.095703601837158, "learning_rate": 9.44742847588787e-06, "loss": 0.7919457912445068, "step": 86120 }, { "epoch": 2.433751960105669, "grad_norm": 5.271791458129883, "learning_rate": 9.429217683775787e-06, "loss": 0.793790054321289, "step": 86140 }, { "epoch": 2.434317035613884, "grad_norm": 4.468227863311768, "learning_rate": 9.4110226326464e-06, "loss": 0.788459062576294, "step": 86160 }, { "epoch": 2.4348821111220986, "grad_norm": 4.60917854309082, "learning_rate": 9.392843329559153e-06, "loss": 0.7916751861572265, "step": 86180 }, { "epoch": 2.4354471866303133, "grad_norm": 3.436596393585205, "learning_rate": 9.37467978156743e-06, "loss": 0.7441141605377197, "step": 86200 }, { "epoch": 2.4360122621385285, "grad_norm": 3.630356788635254, "learning_rate": 9.356531995718465e-06, "loss": 0.7283052444458008, "step": 86220 }, { "epoch": 2.4365773376467432, "grad_norm": 3.17832350730896, "learning_rate": 9.338399979053375e-06, "loss": 0.7963704586029052, "step": 86240 }, { "epoch": 2.437142413154958, "grad_norm": 3.1133577823638916, "learning_rate": 9.320283738607155e-06, "loss": 0.7667943477630615, "step": 86260 }, { "epoch": 2.4377074886631727, "grad_norm": 2.578235626220703, "learning_rate": 9.302183281408727e-06, "loss": 0.7582167625427246, "step": 86280 }, { "epoch": 2.4382725641713874, "grad_norm": 3.6078412532806396, "learning_rate": 9.28409861448083e-06, "loss": 0.6952986240386962, "step": 86300 }, { "epoch": 2.438837639679602, "grad_norm": 2.787311553955078, "learning_rate": 9.266029744840104e-06, "loss": 0.8177623748779297, "step": 86320 }, { "epoch": 2.439402715187817, "grad_norm": 3.062108278274536, "learning_rate": 9.247976679497045e-06, "loss": 0.7755098819732666, "step": 86340 }, { "epoch": 2.4399677906960315, "grad_norm": 4.397172927856445, "learning_rate": 9.229939425456058e-06, "loss": 0.7582170963287354, "step": 86360 }, { "epoch": 2.4405328662042467, "grad_norm": 4.2137861251831055, "learning_rate": 9.211917989715363e-06, "loss": 0.8039824485778808, "step": 86380 }, { "epoch": 2.4410979417124614, "grad_norm": 3.6765801906585693, "learning_rate": 9.193912379267067e-06, "loss": 0.7806293487548828, "step": 86400 }, { "epoch": 2.441663017220676, "grad_norm": 3.476916551589966, "learning_rate": 9.17592260109712e-06, "loss": 0.6685647964477539, "step": 86420 }, { "epoch": 2.442228092728891, "grad_norm": 2.4931039810180664, "learning_rate": 9.157948662185356e-06, "loss": 0.7167598724365234, "step": 86440 }, { "epoch": 2.4427931682371056, "grad_norm": 4.356160640716553, "learning_rate": 9.139990569505463e-06, "loss": 0.8374106407165527, "step": 86460 }, { "epoch": 2.4433582437453203, "grad_norm": 2.967524290084839, "learning_rate": 9.122048330024958e-06, "loss": 0.7488699913024902, "step": 86480 }, { "epoch": 2.4439233192535355, "grad_norm": 3.9328858852386475, "learning_rate": 9.104121950705213e-06, "loss": 0.753175687789917, "step": 86500 }, { "epoch": 2.44448839476175, "grad_norm": 3.5082478523254395, "learning_rate": 9.086211438501435e-06, "loss": 0.7726191520690918, "step": 86520 }, { "epoch": 2.445053470269965, "grad_norm": 2.7773425579071045, "learning_rate": 9.068316800362726e-06, "loss": 0.7991880893707275, "step": 86540 }, { "epoch": 2.4456185457781796, "grad_norm": 2.837481737136841, "learning_rate": 9.050438043231973e-06, "loss": 0.7551753044128418, "step": 86560 }, { "epoch": 2.4461836212863943, "grad_norm": 2.7876949310302734, "learning_rate": 9.032575174045915e-06, "loss": 0.7684639453887939, "step": 86580 }, { "epoch": 2.446748696794609, "grad_norm": 2.3237500190734863, "learning_rate": 9.014728199735152e-06, "loss": 0.728824234008789, "step": 86600 }, { "epoch": 2.4473137723028238, "grad_norm": 4.468892574310303, "learning_rate": 8.996897127224092e-06, "loss": 0.759291696548462, "step": 86620 }, { "epoch": 2.447878847811039, "grad_norm": 4.063180923461914, "learning_rate": 8.979081963430975e-06, "loss": 0.8353736877441407, "step": 86640 }, { "epoch": 2.4484439233192536, "grad_norm": 2.2949347496032715, "learning_rate": 8.96128271526786e-06, "loss": 0.7056080818176269, "step": 86660 }, { "epoch": 2.4490089988274684, "grad_norm": 3.9096548557281494, "learning_rate": 8.94349938964068e-06, "loss": 0.8385739326477051, "step": 86680 }, { "epoch": 2.449574074335683, "grad_norm": 3.7801389694213867, "learning_rate": 8.925731993449128e-06, "loss": 0.777956485748291, "step": 86700 }, { "epoch": 2.450139149843898, "grad_norm": 5.174614429473877, "learning_rate": 8.907980533586752e-06, "loss": 0.7994635581970215, "step": 86720 }, { "epoch": 2.4507042253521125, "grad_norm": 3.925729513168335, "learning_rate": 8.89024501694089e-06, "loss": 0.8789805412292481, "step": 86740 }, { "epoch": 2.4512693008603277, "grad_norm": 3.6220784187316895, "learning_rate": 8.872525450392733e-06, "loss": 0.7259369373321534, "step": 86760 }, { "epoch": 2.4518343763685424, "grad_norm": 2.7072246074676514, "learning_rate": 8.854821840817268e-06, "loss": 0.8288836479187012, "step": 86780 }, { "epoch": 2.452399451876757, "grad_norm": 2.319674491882324, "learning_rate": 8.837134195083274e-06, "loss": 0.7698293685913086, "step": 86800 }, { "epoch": 2.452964527384972, "grad_norm": 4.789357662200928, "learning_rate": 8.81946252005335e-06, "loss": 0.7620539665222168, "step": 86820 }, { "epoch": 2.4535296028931866, "grad_norm": 3.9885599613189697, "learning_rate": 8.801806822583886e-06, "loss": 0.774237585067749, "step": 86840 }, { "epoch": 2.4540946784014013, "grad_norm": 4.289137840270996, "learning_rate": 8.784167109525098e-06, "loss": 0.7397143363952636, "step": 86860 }, { "epoch": 2.454659753909616, "grad_norm": 3.9796416759490967, "learning_rate": 8.766543387720987e-06, "loss": 0.7848375320434571, "step": 86880 }, { "epoch": 2.4552248294178307, "grad_norm": 3.5809109210968018, "learning_rate": 8.748935664009339e-06, "loss": 0.7262988567352295, "step": 86900 }, { "epoch": 2.455789904926046, "grad_norm": 3.8569390773773193, "learning_rate": 8.731343945221737e-06, "loss": 0.622722864151001, "step": 86920 }, { "epoch": 2.4563549804342606, "grad_norm": 4.742008686065674, "learning_rate": 8.713768238183573e-06, "loss": 0.7837406635284424, "step": 86940 }, { "epoch": 2.4569200559424753, "grad_norm": 3.6203813552856445, "learning_rate": 8.696208549714013e-06, "loss": 0.8340774536132812, "step": 86960 }, { "epoch": 2.45748513145069, "grad_norm": 3.4105286598205566, "learning_rate": 8.678664886625998e-06, "loss": 0.8012278556823731, "step": 86980 }, { "epoch": 2.4580502069589047, "grad_norm": 3.8855907917022705, "learning_rate": 8.661137255726259e-06, "loss": 0.759066104888916, "step": 87000 }, { "epoch": 2.45861528246712, "grad_norm": 4.750863552093506, "learning_rate": 8.643625663815324e-06, "loss": 0.7978575706481934, "step": 87020 }, { "epoch": 2.4591803579753346, "grad_norm": 4.39989709854126, "learning_rate": 8.626130117687475e-06, "loss": 0.7556412220001221, "step": 87040 }, { "epoch": 2.4597454334835493, "grad_norm": 2.322150707244873, "learning_rate": 8.608650624130777e-06, "loss": 0.7566864967346192, "step": 87060 }, { "epoch": 2.460310508991764, "grad_norm": 4.16815185546875, "learning_rate": 8.591187189927053e-06, "loss": 0.7603628635406494, "step": 87080 }, { "epoch": 2.460875584499979, "grad_norm": 4.271665573120117, "learning_rate": 8.573739821851922e-06, "loss": 0.7520546913146973, "step": 87100 }, { "epoch": 2.4614406600081935, "grad_norm": 1.9240987300872803, "learning_rate": 8.556308526674766e-06, "loss": 0.7627281188964844, "step": 87120 }, { "epoch": 2.4620057355164082, "grad_norm": 4.281585693359375, "learning_rate": 8.538893311158713e-06, "loss": 0.7451375007629395, "step": 87140 }, { "epoch": 2.462570811024623, "grad_norm": 5.077117919921875, "learning_rate": 8.521494182060657e-06, "loss": 0.7534412384033203, "step": 87160 }, { "epoch": 2.463135886532838, "grad_norm": 5.919799327850342, "learning_rate": 8.504111146131238e-06, "loss": 0.8158864974975586, "step": 87180 }, { "epoch": 2.463700962041053, "grad_norm": 3.453195333480835, "learning_rate": 8.4867442101149e-06, "loss": 0.7391574382781982, "step": 87200 }, { "epoch": 2.4642660375492675, "grad_norm": 4.694527626037598, "learning_rate": 8.469393380749797e-06, "loss": 0.7882349491119385, "step": 87220 }, { "epoch": 2.4648311130574823, "grad_norm": 4.19426965713501, "learning_rate": 8.452058664767832e-06, "loss": 0.7874440670013427, "step": 87240 }, { "epoch": 2.465396188565697, "grad_norm": 4.509309768676758, "learning_rate": 8.43474006889467e-06, "loss": 0.7586234092712403, "step": 87260 }, { "epoch": 2.4659612640739117, "grad_norm": 4.370847225189209, "learning_rate": 8.417437599849742e-06, "loss": 0.7606383800506592, "step": 87280 }, { "epoch": 2.466526339582127, "grad_norm": 2.788273811340332, "learning_rate": 8.400151264346185e-06, "loss": 0.7801759243011475, "step": 87300 }, { "epoch": 2.4670914150903416, "grad_norm": 3.773197650909424, "learning_rate": 8.382881069090887e-06, "loss": 0.7373196601867675, "step": 87320 }, { "epoch": 2.4676564905985563, "grad_norm": 3.0460450649261475, "learning_rate": 8.365627020784495e-06, "loss": 0.6932239532470703, "step": 87340 }, { "epoch": 2.468221566106771, "grad_norm": 3.872987747192383, "learning_rate": 8.34838912612137e-06, "loss": 0.779692554473877, "step": 87360 }, { "epoch": 2.4687866416149857, "grad_norm": 3.5608885288238525, "learning_rate": 8.331167391789607e-06, "loss": 0.8281385421752929, "step": 87380 }, { "epoch": 2.4693517171232005, "grad_norm": 3.121687412261963, "learning_rate": 8.313961824471029e-06, "loss": 0.7343574523925781, "step": 87400 }, { "epoch": 2.469916792631415, "grad_norm": 3.5173959732055664, "learning_rate": 8.296772430841193e-06, "loss": 0.6913098812103271, "step": 87420 }, { "epoch": 2.4704818681396303, "grad_norm": 4.885379314422607, "learning_rate": 8.2795992175694e-06, "loss": 0.7888975143432617, "step": 87440 }, { "epoch": 2.471046943647845, "grad_norm": 4.441590309143066, "learning_rate": 8.262442191318643e-06, "loss": 0.701589298248291, "step": 87460 }, { "epoch": 2.4716120191560598, "grad_norm": 3.8940327167510986, "learning_rate": 8.245301358745638e-06, "loss": 0.8040285110473633, "step": 87480 }, { "epoch": 2.4721770946642745, "grad_norm": 3.0015597343444824, "learning_rate": 8.228176726500814e-06, "loss": 0.822449016571045, "step": 87500 }, { "epoch": 2.472742170172489, "grad_norm": 4.533535480499268, "learning_rate": 8.211068301228358e-06, "loss": 0.7151208877563476, "step": 87520 }, { "epoch": 2.473307245680704, "grad_norm": 3.4501280784606934, "learning_rate": 8.193976089566113e-06, "loss": 0.7200364589691162, "step": 87540 }, { "epoch": 2.473872321188919, "grad_norm": 3.732931613922119, "learning_rate": 8.176900098145661e-06, "loss": 0.7350716114044189, "step": 87560 }, { "epoch": 2.474437396697134, "grad_norm": 3.492079019546509, "learning_rate": 8.159840333592272e-06, "loss": 0.6847165584564209, "step": 87580 }, { "epoch": 2.4750024722053485, "grad_norm": 4.482754707336426, "learning_rate": 8.142796802524954e-06, "loss": 0.7986353397369385, "step": 87600 }, { "epoch": 2.4755675477135632, "grad_norm": 2.936160087585449, "learning_rate": 8.125769511556387e-06, "loss": 0.678397274017334, "step": 87620 }, { "epoch": 2.476132623221778, "grad_norm": 2.9420859813690186, "learning_rate": 8.108758467292948e-06, "loss": 0.7368019104003907, "step": 87640 }, { "epoch": 2.4766976987299927, "grad_norm": 3.614805221557617, "learning_rate": 8.091763676334724e-06, "loss": 0.6561582565307618, "step": 87660 }, { "epoch": 2.4772627742382074, "grad_norm": 4.749064922332764, "learning_rate": 8.074785145275503e-06, "loss": 0.7455184459686279, "step": 87680 }, { "epoch": 2.477827849746422, "grad_norm": 3.6163032054901123, "learning_rate": 8.057822880702749e-06, "loss": 0.7808268547058106, "step": 87700 }, { "epoch": 2.4783929252546373, "grad_norm": 4.503411293029785, "learning_rate": 8.040876889197618e-06, "loss": 0.7812530040740967, "step": 87720 }, { "epoch": 2.478958000762852, "grad_norm": 3.782233238220215, "learning_rate": 8.02394717733494e-06, "loss": 0.7188766479492188, "step": 87740 }, { "epoch": 2.4795230762710667, "grad_norm": 3.4867660999298096, "learning_rate": 8.007033751683256e-06, "loss": 0.7503834724426269, "step": 87760 }, { "epoch": 2.4800881517792814, "grad_norm": 3.0239288806915283, "learning_rate": 7.990136618804794e-06, "loss": 0.7584984779357911, "step": 87780 }, { "epoch": 2.480653227287496, "grad_norm": 3.0406908988952637, "learning_rate": 7.973255785255413e-06, "loss": 0.7905250072479248, "step": 87800 }, { "epoch": 2.4812183027957113, "grad_norm": 3.1807658672332764, "learning_rate": 7.956391257584689e-06, "loss": 0.7665982723236084, "step": 87820 }, { "epoch": 2.481783378303926, "grad_norm": 4.090981960296631, "learning_rate": 7.939543042335845e-06, "loss": 0.7531799793243408, "step": 87840 }, { "epoch": 2.4823484538121408, "grad_norm": 3.2505252361297607, "learning_rate": 7.922711146045808e-06, "loss": 0.7490447998046875, "step": 87860 }, { "epoch": 2.4829135293203555, "grad_norm": 3.8484981060028076, "learning_rate": 7.905895575245148e-06, "loss": 0.7453812599182129, "step": 87880 }, { "epoch": 2.48347860482857, "grad_norm": 4.439576148986816, "learning_rate": 7.889096336458107e-06, "loss": 0.7085547924041748, "step": 87900 }, { "epoch": 2.484043680336785, "grad_norm": 4.3837199211120605, "learning_rate": 7.872313436202572e-06, "loss": 0.7894624710083008, "step": 87920 }, { "epoch": 2.4846087558449996, "grad_norm": 3.455808639526367, "learning_rate": 7.85554688099014e-06, "loss": 0.7048059463500976, "step": 87940 }, { "epoch": 2.4851738313532143, "grad_norm": 3.5246543884277344, "learning_rate": 7.838796677326021e-06, "loss": 0.7568171501159668, "step": 87960 }, { "epoch": 2.4857389068614295, "grad_norm": 3.68330717086792, "learning_rate": 7.822062831709081e-06, "loss": 0.8052160263061523, "step": 87980 }, { "epoch": 2.4863039823696442, "grad_norm": 3.600069046020508, "learning_rate": 7.805345350631882e-06, "loss": 0.7919841289520264, "step": 88000 }, { "epoch": 2.486869057877859, "grad_norm": 4.128960609436035, "learning_rate": 7.788644240580595e-06, "loss": 0.6908183574676514, "step": 88020 }, { "epoch": 2.4874341333860737, "grad_norm": 3.1534693241119385, "learning_rate": 7.771959508035053e-06, "loss": 0.7970425605773925, "step": 88040 }, { "epoch": 2.4879992088942884, "grad_norm": 2.6047661304473877, "learning_rate": 7.755291159468725e-06, "loss": 0.7455958366394043, "step": 88060 }, { "epoch": 2.488564284402503, "grad_norm": 3.6120073795318604, "learning_rate": 7.738639201348741e-06, "loss": 0.8498714447021485, "step": 88080 }, { "epoch": 2.4891293599107183, "grad_norm": 3.5787911415100098, "learning_rate": 7.722003640135871e-06, "loss": 0.720628023147583, "step": 88100 }, { "epoch": 2.489694435418933, "grad_norm": 4.272941589355469, "learning_rate": 7.705384482284516e-06, "loss": 0.6731250286102295, "step": 88120 }, { "epoch": 2.4902595109271477, "grad_norm": 2.059004306793213, "learning_rate": 7.6887817342427e-06, "loss": 0.7193769454956055, "step": 88140 }, { "epoch": 2.4908245864353624, "grad_norm": 2.9225659370422363, "learning_rate": 7.672195402452093e-06, "loss": 0.8475885391235352, "step": 88160 }, { "epoch": 2.491389661943577, "grad_norm": 4.911548137664795, "learning_rate": 7.655625493348006e-06, "loss": 0.7313380241394043, "step": 88180 }, { "epoch": 2.491954737451792, "grad_norm": 3.3781015872955322, "learning_rate": 7.63907201335936e-06, "loss": 0.7637479782104493, "step": 88200 }, { "epoch": 2.4925198129600066, "grad_norm": 3.9304893016815186, "learning_rate": 7.622534968908712e-06, "loss": 0.7471214294433594, "step": 88220 }, { "epoch": 2.4930848884682217, "grad_norm": 4.403439998626709, "learning_rate": 7.606014366412228e-06, "loss": 0.8193406105041504, "step": 88240 }, { "epoch": 2.4936499639764365, "grad_norm": 3.505089282989502, "learning_rate": 7.589510212279727e-06, "loss": 0.7030675411224365, "step": 88260 }, { "epoch": 2.494215039484651, "grad_norm": 3.9012577533721924, "learning_rate": 7.573022512914607e-06, "loss": 0.728065299987793, "step": 88280 }, { "epoch": 2.494780114992866, "grad_norm": 3.8455007076263428, "learning_rate": 7.556551274713913e-06, "loss": 0.7589799404144287, "step": 88300 }, { "epoch": 2.4953451905010806, "grad_norm": 2.182314395904541, "learning_rate": 7.540096504068273e-06, "loss": 0.794608211517334, "step": 88320 }, { "epoch": 2.4959102660092953, "grad_norm": 2.9535629749298096, "learning_rate": 7.523658207361961e-06, "loss": 0.7880488872528076, "step": 88340 }, { "epoch": 2.4964753415175105, "grad_norm": 3.6581552028656006, "learning_rate": 7.5072363909728385e-06, "loss": 0.7494381904602051, "step": 88360 }, { "epoch": 2.497040417025725, "grad_norm": 4.2589616775512695, "learning_rate": 7.490831061272369e-06, "loss": 0.7636521339416504, "step": 88380 }, { "epoch": 2.49760549253394, "grad_norm": 3.093259572982788, "learning_rate": 7.474442224625617e-06, "loss": 0.7537079334259034, "step": 88400 }, { "epoch": 2.4981705680421546, "grad_norm": 4.338472843170166, "learning_rate": 7.458069887391267e-06, "loss": 0.8086137771606445, "step": 88420 }, { "epoch": 2.4987356435503694, "grad_norm": 4.012104034423828, "learning_rate": 7.441714055921606e-06, "loss": 0.7186063289642334, "step": 88440 }, { "epoch": 2.499300719058584, "grad_norm": 3.2183876037597656, "learning_rate": 7.425374736562491e-06, "loss": 0.6713987350463867, "step": 88460 }, { "epoch": 2.499865794566799, "grad_norm": 3.2449376583099365, "learning_rate": 7.409051935653377e-06, "loss": 0.7095026016235352, "step": 88480 }, { "epoch": 2.5004308700750135, "grad_norm": 4.3925676345825195, "learning_rate": 7.392745659527317e-06, "loss": 0.7801973342895507, "step": 88500 }, { "epoch": 2.5009959455832287, "grad_norm": 3.041543483734131, "learning_rate": 7.376455914510971e-06, "loss": 0.7303394317626953, "step": 88520 }, { "epoch": 2.5015610210914434, "grad_norm": 5.5606279373168945, "learning_rate": 7.360182706924551e-06, "loss": 0.7625636100769043, "step": 88540 }, { "epoch": 2.502126096599658, "grad_norm": 4.352936744689941, "learning_rate": 7.343926043081878e-06, "loss": 0.739004373550415, "step": 88560 }, { "epoch": 2.502691172107873, "grad_norm": 3.2792248725891113, "learning_rate": 7.327685929290323e-06, "loss": 0.8326931953430176, "step": 88580 }, { "epoch": 2.5032562476160876, "grad_norm": 4.6583991050720215, "learning_rate": 7.311462371850891e-06, "loss": 0.8370357513427734, "step": 88600 }, { "epoch": 2.5038213231243027, "grad_norm": 4.956724166870117, "learning_rate": 7.295255377058108e-06, "loss": 0.8201211929321289, "step": 88620 }, { "epoch": 2.5043863986325174, "grad_norm": 3.9101712703704834, "learning_rate": 7.279064951200093e-06, "loss": 0.6993293285369873, "step": 88640 }, { "epoch": 2.504951474140732, "grad_norm": 4.283665180206299, "learning_rate": 7.262891100558561e-06, "loss": 0.6599490642547607, "step": 88660 }, { "epoch": 2.505516549648947, "grad_norm": 6.203860759735107, "learning_rate": 7.246733831408753e-06, "loss": 0.7676724910736084, "step": 88680 }, { "epoch": 2.5060816251571616, "grad_norm": 3.8561720848083496, "learning_rate": 7.230593150019515e-06, "loss": 0.8035811424255371, "step": 88700 }, { "epoch": 2.5066467006653763, "grad_norm": 4.042520523071289, "learning_rate": 7.214469062653212e-06, "loss": 0.7143960952758789, "step": 88720 }, { "epoch": 2.507211776173591, "grad_norm": 3.006505012512207, "learning_rate": 7.198361575565826e-06, "loss": 0.756709098815918, "step": 88740 }, { "epoch": 2.5077768516818058, "grad_norm": 4.123170375823975, "learning_rate": 7.182270695006865e-06, "loss": 0.6965462684631347, "step": 88760 }, { "epoch": 2.508341927190021, "grad_norm": 3.4016079902648926, "learning_rate": 7.166196427219407e-06, "loss": 0.7796252727508545, "step": 88780 }, { "epoch": 2.5089070026982356, "grad_norm": 3.5336554050445557, "learning_rate": 7.1501387784400635e-06, "loss": 0.7333576202392578, "step": 88800 }, { "epoch": 2.5094720782064504, "grad_norm": 3.9327924251556396, "learning_rate": 7.134097754899005e-06, "loss": 0.7553854942321777, "step": 88820 }, { "epoch": 2.510037153714665, "grad_norm": 3.5385384559631348, "learning_rate": 7.118073362819982e-06, "loss": 0.7500325679779053, "step": 88840 }, { "epoch": 2.51060222922288, "grad_norm": 4.068134307861328, "learning_rate": 7.102065608420255e-06, "loss": 0.7780195236206054, "step": 88860 }, { "epoch": 2.511167304731095, "grad_norm": 2.832646131515503, "learning_rate": 7.086074497910644e-06, "loss": 0.7791770458221435, "step": 88880 }, { "epoch": 2.5117323802393097, "grad_norm": 2.8144285678863525, "learning_rate": 7.070100037495503e-06, "loss": 0.8090979576110839, "step": 88900 }, { "epoch": 2.5122974557475244, "grad_norm": 4.748924732208252, "learning_rate": 7.054142233372751e-06, "loss": 0.8042171478271485, "step": 88920 }, { "epoch": 2.512862531255739, "grad_norm": 2.5819005966186523, "learning_rate": 7.038201091733821e-06, "loss": 0.7999480724334717, "step": 88940 }, { "epoch": 2.513427606763954, "grad_norm": 4.924988746643066, "learning_rate": 7.022276618763679e-06, "loss": 0.740594482421875, "step": 88960 }, { "epoch": 2.5139926822721685, "grad_norm": 3.376319169998169, "learning_rate": 7.006368820640824e-06, "loss": 0.680556058883667, "step": 88980 }, { "epoch": 2.5145577577803833, "grad_norm": 3.267634630203247, "learning_rate": 6.990477703537323e-06, "loss": 0.7436215877532959, "step": 89000 }, { "epoch": 2.515122833288598, "grad_norm": 4.023623943328857, "learning_rate": 6.974603273618718e-06, "loss": 0.733825397491455, "step": 89020 }, { "epoch": 2.5156879087968127, "grad_norm": 3.6312012672424316, "learning_rate": 6.958745537044104e-06, "loss": 0.7865072727203369, "step": 89040 }, { "epoch": 2.516252984305028, "grad_norm": 3.035630464553833, "learning_rate": 6.942904499966091e-06, "loss": 0.7086317539215088, "step": 89060 }, { "epoch": 2.5168180598132426, "grad_norm": 2.853874444961548, "learning_rate": 6.927080168530814e-06, "loss": 0.7358696460723877, "step": 89080 }, { "epoch": 2.5173831353214573, "grad_norm": 4.115476131439209, "learning_rate": 6.91127254887794e-06, "loss": 0.7846050262451172, "step": 89100 }, { "epoch": 2.517948210829672, "grad_norm": 2.6949901580810547, "learning_rate": 6.895481647140628e-06, "loss": 0.7612287998199463, "step": 89120 }, { "epoch": 2.5185132863378867, "grad_norm": 4.952055931091309, "learning_rate": 6.8797074694455676e-06, "loss": 0.7638996601104736, "step": 89140 }, { "epoch": 2.519078361846102, "grad_norm": 3.411890745162964, "learning_rate": 6.863950021912929e-06, "loss": 0.8681394577026367, "step": 89160 }, { "epoch": 2.5196434373543166, "grad_norm": 2.3443617820739746, "learning_rate": 6.848209310656445e-06, "loss": 0.7824079990386963, "step": 89180 }, { "epoch": 2.5202085128625313, "grad_norm": 4.494699954986572, "learning_rate": 6.832485341783318e-06, "loss": 0.8185864448547363, "step": 89200 }, { "epoch": 2.520773588370746, "grad_norm": 4.882739067077637, "learning_rate": 6.816778121394252e-06, "loss": 0.8556125640869141, "step": 89220 }, { "epoch": 2.5213386638789608, "grad_norm": 2.8772740364074707, "learning_rate": 6.801087655583455e-06, "loss": 0.7882428646087647, "step": 89240 }, { "epoch": 2.5219037393871755, "grad_norm": 2.743161201477051, "learning_rate": 6.7854139504386626e-06, "loss": 0.7730641841888428, "step": 89260 }, { "epoch": 2.52246881489539, "grad_norm": 3.7398180961608887, "learning_rate": 6.769757012041084e-06, "loss": 0.7396051406860351, "step": 89280 }, { "epoch": 2.523033890403605, "grad_norm": 3.1797614097595215, "learning_rate": 6.754116846465414e-06, "loss": 0.7303593158721924, "step": 89300 }, { "epoch": 2.52359896591182, "grad_norm": 2.2615299224853516, "learning_rate": 6.738493459779843e-06, "loss": 0.7991369247436524, "step": 89320 }, { "epoch": 2.524164041420035, "grad_norm": 2.504185438156128, "learning_rate": 6.7228868580460905e-06, "loss": 0.7500786781311035, "step": 89340 }, { "epoch": 2.5247291169282495, "grad_norm": 4.251724720001221, "learning_rate": 6.707297047319311e-06, "loss": 0.7153632164001464, "step": 89360 }, { "epoch": 2.5252941924364642, "grad_norm": 5.150746822357178, "learning_rate": 6.6917240336481615e-06, "loss": 0.8330142974853516, "step": 89380 }, { "epoch": 2.525859267944679, "grad_norm": 4.238997459411621, "learning_rate": 6.676167823074797e-06, "loss": 0.8705698013305664, "step": 89400 }, { "epoch": 2.526424343452894, "grad_norm": 3.002934217453003, "learning_rate": 6.660628421634851e-06, "loss": 0.7233604907989502, "step": 89420 }, { "epoch": 2.526989418961109, "grad_norm": 4.113124370574951, "learning_rate": 6.6451058353574236e-06, "loss": 0.7759288311004638, "step": 89440 }, { "epoch": 2.5275544944693236, "grad_norm": 3.410466432571411, "learning_rate": 6.629600070265085e-06, "loss": 0.7353177547454834, "step": 89460 }, { "epoch": 2.5281195699775383, "grad_norm": 3.121436834335327, "learning_rate": 6.614111132373885e-06, "loss": 0.7992044925689697, "step": 89480 }, { "epoch": 2.528684645485753, "grad_norm": 3.600285768508911, "learning_rate": 6.59863902769336e-06, "loss": 0.7380915641784668, "step": 89500 }, { "epoch": 2.5292497209939677, "grad_norm": 3.4652369022369385, "learning_rate": 6.583183762226503e-06, "loss": 0.6447897911071777, "step": 89520 }, { "epoch": 2.5298147965021824, "grad_norm": 4.016637802124023, "learning_rate": 6.567745341969766e-06, "loss": 0.7408390522003174, "step": 89540 }, { "epoch": 2.530379872010397, "grad_norm": 4.168907165527344, "learning_rate": 6.552323772913071e-06, "loss": 0.7941583633422852, "step": 89560 }, { "epoch": 2.5309449475186123, "grad_norm": 2.3711025714874268, "learning_rate": 6.536919061039814e-06, "loss": 0.8299317359924316, "step": 89580 }, { "epoch": 2.531510023026827, "grad_norm": 4.0922746658325195, "learning_rate": 6.521531212326842e-06, "loss": 0.7849037647247314, "step": 89600 }, { "epoch": 2.5320750985350418, "grad_norm": 3.9117486476898193, "learning_rate": 6.5061602327444516e-06, "loss": 0.7646312713623047, "step": 89620 }, { "epoch": 2.5326401740432565, "grad_norm": 2.869751214981079, "learning_rate": 6.490806128256388e-06, "loss": 0.7091171264648437, "step": 89640 }, { "epoch": 2.533205249551471, "grad_norm": 4.430116653442383, "learning_rate": 6.475468904819881e-06, "loss": 0.8503606796264649, "step": 89660 }, { "epoch": 2.5337703250596864, "grad_norm": 3.761836528778076, "learning_rate": 6.460148568385593e-06, "loss": 0.7581312656402588, "step": 89680 }, { "epoch": 2.534335400567901, "grad_norm": 2.406115770339966, "learning_rate": 6.44484512489762e-06, "loss": 0.7171465873718261, "step": 89700 }, { "epoch": 2.534900476076116, "grad_norm": 3.634082794189453, "learning_rate": 6.429558580293515e-06, "loss": 0.7288050651550293, "step": 89720 }, { "epoch": 2.5354655515843305, "grad_norm": 3.113368511199951, "learning_rate": 6.414288940504282e-06, "loss": 0.7758362293243408, "step": 89740 }, { "epoch": 2.5360306270925452, "grad_norm": 2.3023841381073, "learning_rate": 6.399036211454368e-06, "loss": 0.7128942012786865, "step": 89760 }, { "epoch": 2.53659570260076, "grad_norm": 3.5008251667022705, "learning_rate": 6.383800399061651e-06, "loss": 0.7740753173828125, "step": 89780 }, { "epoch": 2.5371607781089747, "grad_norm": 4.485708713531494, "learning_rate": 6.368581509237437e-06, "loss": 0.6809597492218018, "step": 89800 }, { "epoch": 2.5377258536171894, "grad_norm": 3.2426390647888184, "learning_rate": 6.353379547886462e-06, "loss": 0.7765144348144531, "step": 89820 }, { "epoch": 2.538290929125404, "grad_norm": 4.02284574508667, "learning_rate": 6.338194520906937e-06, "loss": 0.7675814151763916, "step": 89840 }, { "epoch": 2.5388560046336193, "grad_norm": 3.7724204063415527, "learning_rate": 6.323026434190455e-06, "loss": 0.7943633556365967, "step": 89860 }, { "epoch": 2.539421080141834, "grad_norm": 3.542212963104248, "learning_rate": 6.307875293622056e-06, "loss": 0.7715907573699952, "step": 89880 }, { "epoch": 2.5399861556500487, "grad_norm": 4.588747978210449, "learning_rate": 6.2927411050801965e-06, "loss": 0.6999811649322509, "step": 89900 }, { "epoch": 2.5405512311582634, "grad_norm": 4.384550094604492, "learning_rate": 6.2776238744367774e-06, "loss": 0.7653748512268066, "step": 89920 }, { "epoch": 2.541116306666478, "grad_norm": 3.3829379081726074, "learning_rate": 6.262523607557097e-06, "loss": 0.7903259754180908, "step": 89940 }, { "epoch": 2.5416813821746933, "grad_norm": 3.5777182579040527, "learning_rate": 6.247440310299879e-06, "loss": 0.6696672439575195, "step": 89960 }, { "epoch": 2.542246457682908, "grad_norm": 2.6589066982269287, "learning_rate": 6.232373988517254e-06, "loss": 0.7308051109313964, "step": 89980 }, { "epoch": 2.5428115331911227, "grad_norm": 3.1903069019317627, "learning_rate": 6.217324648054796e-06, "loss": 0.7210105895996094, "step": 90000 }, { "epoch": 2.5433766086993375, "grad_norm": 3.2226626873016357, "learning_rate": 6.202292294751461e-06, "loss": 0.7170364856719971, "step": 90020 }, { "epoch": 2.543941684207552, "grad_norm": 3.9488816261291504, "learning_rate": 6.187276934439612e-06, "loss": 0.7848269462585449, "step": 90040 }, { "epoch": 2.544506759715767, "grad_norm": 2.5282111167907715, "learning_rate": 6.172278572945051e-06, "loss": 0.7860430240631103, "step": 90060 }, { "epoch": 2.5450718352239816, "grad_norm": 4.306345462799072, "learning_rate": 6.15729721608696e-06, "loss": 0.7171304225921631, "step": 90080 }, { "epoch": 2.5456369107321963, "grad_norm": 4.218946933746338, "learning_rate": 6.142332869677925e-06, "loss": 0.8018427848815918, "step": 90100 }, { "epoch": 2.5462019862404115, "grad_norm": 3.1472830772399902, "learning_rate": 6.127385539523939e-06, "loss": 0.782880163192749, "step": 90120 }, { "epoch": 2.546767061748626, "grad_norm": 3.4753036499023438, "learning_rate": 6.112455231424369e-06, "loss": 0.7622081756591796, "step": 90140 }, { "epoch": 2.547332137256841, "grad_norm": 6.1556525230407715, "learning_rate": 6.0975419511720314e-06, "loss": 0.7413138389587403, "step": 90160 }, { "epoch": 2.5478972127650557, "grad_norm": 3.5327811241149902, "learning_rate": 6.082645704553075e-06, "loss": 0.696201753616333, "step": 90180 }, { "epoch": 2.5484622882732704, "grad_norm": 3.3028244972229004, "learning_rate": 6.067766497347082e-06, "loss": 0.699787950515747, "step": 90200 }, { "epoch": 2.5490273637814855, "grad_norm": 3.642774820327759, "learning_rate": 6.052904335326986e-06, "loss": 0.8722975730895997, "step": 90220 }, { "epoch": 2.5495924392897003, "grad_norm": 3.423335313796997, "learning_rate": 6.038059224259163e-06, "loss": 0.7209027767181396, "step": 90240 }, { "epoch": 2.550157514797915, "grad_norm": 4.004622936248779, "learning_rate": 6.023231169903321e-06, "loss": 0.7759610176086426, "step": 90260 }, { "epoch": 2.5507225903061297, "grad_norm": 4.536641597747803, "learning_rate": 6.008420178012569e-06, "loss": 0.8231071472167969, "step": 90280 }, { "epoch": 2.5512876658143444, "grad_norm": 3.5933749675750732, "learning_rate": 5.99362625433339e-06, "loss": 0.798817777633667, "step": 90300 }, { "epoch": 2.551852741322559, "grad_norm": 3.8064513206481934, "learning_rate": 5.978849404605675e-06, "loss": 0.7764759063720703, "step": 90320 }, { "epoch": 2.552417816830774, "grad_norm": 6.228252410888672, "learning_rate": 5.964089634562642e-06, "loss": 0.733837366104126, "step": 90340 }, { "epoch": 2.5529828923389886, "grad_norm": 4.5979814529418945, "learning_rate": 5.949346949930923e-06, "loss": 0.8097436904907227, "step": 90360 }, { "epoch": 2.5535479678472037, "grad_norm": 3.9490132331848145, "learning_rate": 5.9346213564304866e-06, "loss": 0.7040843009948731, "step": 90380 }, { "epoch": 2.5541130433554184, "grad_norm": 4.3952765464782715, "learning_rate": 5.9199128597747014e-06, "loss": 0.7533852577209472, "step": 90400 }, { "epoch": 2.554678118863633, "grad_norm": 2.5215651988983154, "learning_rate": 5.905221465670296e-06, "loss": 0.7213047504425049, "step": 90420 }, { "epoch": 2.555243194371848, "grad_norm": 3.2700116634368896, "learning_rate": 5.890547179817352e-06, "loss": 0.7969419002532959, "step": 90440 }, { "epoch": 2.5558082698800626, "grad_norm": 3.781207323074341, "learning_rate": 5.8758900079093125e-06, "loss": 0.798229169845581, "step": 90460 }, { "epoch": 2.5563733453882778, "grad_norm": 4.1250176429748535, "learning_rate": 5.861249955632986e-06, "loss": 0.725218391418457, "step": 90480 }, { "epoch": 2.5569384208964925, "grad_norm": 2.4764533042907715, "learning_rate": 5.84662702866855e-06, "loss": 0.7465393543243408, "step": 90500 }, { "epoch": 2.557503496404707, "grad_norm": 3.8529675006866455, "learning_rate": 5.832021232689521e-06, "loss": 0.7971485137939454, "step": 90520 }, { "epoch": 2.558068571912922, "grad_norm": 4.812093257904053, "learning_rate": 5.817432573362775e-06, "loss": 0.7618765830993652, "step": 90540 }, { "epoch": 2.5586336474211366, "grad_norm": 2.7692415714263916, "learning_rate": 5.8028610563485246e-06, "loss": 0.7867856025695801, "step": 90560 }, { "epoch": 2.5591987229293514, "grad_norm": 3.1249194145202637, "learning_rate": 5.788306687300371e-06, "loss": 0.7236032962799073, "step": 90580 }, { "epoch": 2.559763798437566, "grad_norm": 2.988368034362793, "learning_rate": 5.773769471865226e-06, "loss": 0.7885629653930664, "step": 90600 }, { "epoch": 2.560328873945781, "grad_norm": 3.463561534881592, "learning_rate": 5.759249415683354e-06, "loss": 0.7446463584899903, "step": 90620 }, { "epoch": 2.560893949453996, "grad_norm": 3.703153610229492, "learning_rate": 5.744746524388356e-06, "loss": 0.7998320102691651, "step": 90640 }, { "epoch": 2.5614590249622107, "grad_norm": 3.412759780883789, "learning_rate": 5.730260803607202e-06, "loss": 0.8038314819335938, "step": 90660 }, { "epoch": 2.5620241004704254, "grad_norm": 4.240920543670654, "learning_rate": 5.715792258960173e-06, "loss": 0.6927952289581298, "step": 90680 }, { "epoch": 2.56258917597864, "grad_norm": 3.1825220584869385, "learning_rate": 5.701340896060875e-06, "loss": 0.7749605178833008, "step": 90700 }, { "epoch": 2.563154251486855, "grad_norm": 3.5554733276367188, "learning_rate": 5.686906720516288e-06, "loss": 0.7430215835571289, "step": 90720 }, { "epoch": 2.56371932699507, "grad_norm": 3.072695732116699, "learning_rate": 5.6724897379267005e-06, "loss": 0.6970977783203125, "step": 90740 }, { "epoch": 2.5642844025032847, "grad_norm": 3.755681276321411, "learning_rate": 5.65808995388572e-06, "loss": 0.740147590637207, "step": 90760 }, { "epoch": 2.5648494780114994, "grad_norm": 5.590826034545898, "learning_rate": 5.643707373980306e-06, "loss": 0.7696740627288818, "step": 90780 }, { "epoch": 2.565414553519714, "grad_norm": 3.8644144535064697, "learning_rate": 5.6293420037907e-06, "loss": 0.8196160316467285, "step": 90800 }, { "epoch": 2.565979629027929, "grad_norm": 4.358401775360107, "learning_rate": 5.6149938488905266e-06, "loss": 0.7188660621643066, "step": 90820 }, { "epoch": 2.5665447045361436, "grad_norm": 2.889371633529663, "learning_rate": 5.600662914846694e-06, "loss": 0.7073334693908692, "step": 90840 }, { "epoch": 2.5671097800443583, "grad_norm": 3.024477243423462, "learning_rate": 5.586349207219421e-06, "loss": 0.8203614234924317, "step": 90860 }, { "epoch": 2.567674855552573, "grad_norm": 2.8027994632720947, "learning_rate": 5.572052731562261e-06, "loss": 0.7514754295349121, "step": 90880 }, { "epoch": 2.5682399310607877, "grad_norm": 4.113388538360596, "learning_rate": 5.557773493422086e-06, "loss": 0.8007716178894043, "step": 90900 }, { "epoch": 2.568805006569003, "grad_norm": 4.115687847137451, "learning_rate": 5.543511498339066e-06, "loss": 0.7316133499145507, "step": 90920 }, { "epoch": 2.5693700820772176, "grad_norm": 4.072326183319092, "learning_rate": 5.529266751846685e-06, "loss": 0.7413663387298584, "step": 90940 }, { "epoch": 2.5699351575854323, "grad_norm": 4.202876567840576, "learning_rate": 5.515039259471727e-06, "loss": 0.7273301601409912, "step": 90960 }, { "epoch": 2.570500233093647, "grad_norm": 3.0105419158935547, "learning_rate": 5.5008290267343055e-06, "loss": 0.7059346675872803, "step": 90980 }, { "epoch": 2.5710653086018618, "grad_norm": 3.0350186824798584, "learning_rate": 5.4866360591478205e-06, "loss": 0.8185003280639649, "step": 91000 }, { "epoch": 2.571630384110077, "grad_norm": 3.550139904022217, "learning_rate": 5.472460362218973e-06, "loss": 0.7271588325500489, "step": 91020 }, { "epoch": 2.5721954596182917, "grad_norm": 2.7400269508361816, "learning_rate": 5.458301941447752e-06, "loss": 0.7511868953704834, "step": 91040 }, { "epoch": 2.5727605351265064, "grad_norm": 4.579282760620117, "learning_rate": 5.444160802327469e-06, "loss": 0.7084877967834473, "step": 91060 }, { "epoch": 2.573325610634721, "grad_norm": 4.387929439544678, "learning_rate": 5.430036950344725e-06, "loss": 0.7670147895812989, "step": 91080 }, { "epoch": 2.573890686142936, "grad_norm": 3.05674147605896, "learning_rate": 5.415930390979407e-06, "loss": 0.7773653507232666, "step": 91100 }, { "epoch": 2.5744557616511505, "grad_norm": 4.556069374084473, "learning_rate": 5.4018411297046765e-06, "loss": 0.7409967899322509, "step": 91120 }, { "epoch": 2.5750208371593653, "grad_norm": 4.772727966308594, "learning_rate": 5.387769171987006e-06, "loss": 0.7529835224151611, "step": 91140 }, { "epoch": 2.57558591266758, "grad_norm": 3.122504234313965, "learning_rate": 5.373714523286161e-06, "loss": 0.693272590637207, "step": 91160 }, { "epoch": 2.576150988175795, "grad_norm": 3.3154752254486084, "learning_rate": 5.359677189055168e-06, "loss": 0.7374614238739013, "step": 91180 }, { "epoch": 2.57671606368401, "grad_norm": 2.8714895248413086, "learning_rate": 5.3456571747403485e-06, "loss": 0.7433236122131348, "step": 91200 }, { "epoch": 2.5772811391922246, "grad_norm": 3.732090473175049, "learning_rate": 5.33165448578129e-06, "loss": 0.703919506072998, "step": 91220 }, { "epoch": 2.5778462147004393, "grad_norm": 3.012389898300171, "learning_rate": 5.317669127610897e-06, "loss": 0.7577526569366455, "step": 91240 }, { "epoch": 2.578411290208654, "grad_norm": 4.521931171417236, "learning_rate": 5.303701105655301e-06, "loss": 0.7431331157684327, "step": 91260 }, { "epoch": 2.578976365716869, "grad_norm": 3.8835151195526123, "learning_rate": 5.289750425333933e-06, "loss": 0.7373466968536377, "step": 91280 }, { "epoch": 2.579541441225084, "grad_norm": 5.637130260467529, "learning_rate": 5.275817092059487e-06, "loss": 0.7867118835449218, "step": 91300 }, { "epoch": 2.5801065167332986, "grad_norm": 4.483243465423584, "learning_rate": 5.261901111237943e-06, "loss": 0.7608829498291015, "step": 91320 }, { "epoch": 2.5806715922415133, "grad_norm": 3.2567484378814697, "learning_rate": 5.248002488268533e-06, "loss": 0.730799388885498, "step": 91340 }, { "epoch": 2.581236667749728, "grad_norm": 2.333845376968384, "learning_rate": 5.2341212285437595e-06, "loss": 0.7558868885040283, "step": 91360 }, { "epoch": 2.5818017432579428, "grad_norm": 3.7593302726745605, "learning_rate": 5.220257337449358e-06, "loss": 0.7610093116760254, "step": 91380 }, { "epoch": 2.5823668187661575, "grad_norm": 3.3963842391967773, "learning_rate": 5.206410820364404e-06, "loss": 0.825713062286377, "step": 91400 }, { "epoch": 2.582931894274372, "grad_norm": 3.533172607421875, "learning_rate": 5.192581682661157e-06, "loss": 0.7586144924163818, "step": 91420 }, { "epoch": 2.5834969697825874, "grad_norm": 4.297733306884766, "learning_rate": 5.178769929705157e-06, "loss": 0.8231800079345704, "step": 91440 }, { "epoch": 2.584062045290802, "grad_norm": 3.545001268386841, "learning_rate": 5.16497556685519e-06, "loss": 0.6850061893463135, "step": 91460 }, { "epoch": 2.584627120799017, "grad_norm": 3.6401658058166504, "learning_rate": 5.151198599463331e-06, "loss": 0.7836624622344971, "step": 91480 }, { "epoch": 2.5851921963072315, "grad_norm": 4.472024917602539, "learning_rate": 5.137439032874863e-06, "loss": 0.7268909454345703, "step": 91500 }, { "epoch": 2.5857572718154462, "grad_norm": 9.26905632019043, "learning_rate": 5.123696872428341e-06, "loss": 0.7752074718475341, "step": 91520 }, { "epoch": 2.5863223473236614, "grad_norm": 3.5900259017944336, "learning_rate": 5.109972123455548e-06, "loss": 0.6903856754302978, "step": 91540 }, { "epoch": 2.586887422831876, "grad_norm": 4.528866767883301, "learning_rate": 5.096264791281541e-06, "loss": 0.7859383583068847, "step": 91560 }, { "epoch": 2.587452498340091, "grad_norm": 4.1607232093811035, "learning_rate": 5.082574881224594e-06, "loss": 0.780470895767212, "step": 91580 }, { "epoch": 2.5880175738483056, "grad_norm": 4.050161361694336, "learning_rate": 5.068902398596237e-06, "loss": 0.7698423385620117, "step": 91600 }, { "epoch": 2.5885826493565203, "grad_norm": 3.9522836208343506, "learning_rate": 5.055247348701208e-06, "loss": 0.8013111114501953, "step": 91620 }, { "epoch": 2.589147724864735, "grad_norm": 2.714982271194458, "learning_rate": 5.0416097368375384e-06, "loss": 0.8064332008361816, "step": 91640 }, { "epoch": 2.5897128003729497, "grad_norm": 4.185009956359863, "learning_rate": 5.027989568296437e-06, "loss": 0.7686254024505615, "step": 91660 }, { "epoch": 2.5902778758811644, "grad_norm": 2.942978858947754, "learning_rate": 5.014386848362379e-06, "loss": 0.7595343589782715, "step": 91680 }, { "epoch": 2.590842951389379, "grad_norm": 3.6429390907287598, "learning_rate": 5.000801582313042e-06, "loss": 0.7401575565338134, "step": 91700 }, { "epoch": 2.5914080268975943, "grad_norm": 2.4565491676330566, "learning_rate": 4.987233775419359e-06, "loss": 0.7244480609893799, "step": 91720 }, { "epoch": 2.591973102405809, "grad_norm": 4.069096565246582, "learning_rate": 4.9736834329454865e-06, "loss": 0.6502140998840332, "step": 91740 }, { "epoch": 2.5925381779140237, "grad_norm": 3.292924404144287, "learning_rate": 4.960150560148796e-06, "loss": 0.7615046501159668, "step": 91760 }, { "epoch": 2.5931032534222385, "grad_norm": 3.6495914459228516, "learning_rate": 4.946635162279867e-06, "loss": 0.6604416847229004, "step": 91780 }, { "epoch": 2.593668328930453, "grad_norm": 3.8349103927612305, "learning_rate": 4.93313724458252e-06, "loss": 0.733400535583496, "step": 91800 }, { "epoch": 2.5942334044386683, "grad_norm": 5.180512428283691, "learning_rate": 4.9196568122937935e-06, "loss": 0.7498401641845703, "step": 91820 }, { "epoch": 2.594798479946883, "grad_norm": 4.884401321411133, "learning_rate": 4.906193870643927e-06, "loss": 0.8169868469238282, "step": 91840 }, { "epoch": 2.595363555455098, "grad_norm": 4.042937278747559, "learning_rate": 4.892748424856392e-06, "loss": 0.7408829689025879, "step": 91860 }, { "epoch": 2.5959286309633125, "grad_norm": 3.4131312370300293, "learning_rate": 4.879320480147848e-06, "loss": 0.7509589672088623, "step": 91880 }, { "epoch": 2.596493706471527, "grad_norm": 4.3996734619140625, "learning_rate": 4.865910041728189e-06, "loss": 0.706973934173584, "step": 91900 }, { "epoch": 2.597058781979742, "grad_norm": 3.0091843605041504, "learning_rate": 4.8525171148005086e-06, "loss": 0.7729925632476806, "step": 91920 }, { "epoch": 2.5976238574879567, "grad_norm": 5.675329208374023, "learning_rate": 4.839141704561101e-06, "loss": 0.6927186965942382, "step": 91940 }, { "epoch": 2.5981889329961714, "grad_norm": 2.135828971862793, "learning_rate": 4.825783816199448e-06, "loss": 0.7768511295318603, "step": 91960 }, { "epoch": 2.5987540085043865, "grad_norm": 4.468100547790527, "learning_rate": 4.812443454898285e-06, "loss": 0.6607948780059815, "step": 91980 }, { "epoch": 2.5993190840126013, "grad_norm": 3.5092954635620117, "learning_rate": 4.799120625833492e-06, "loss": 0.8054460525512696, "step": 92000 }, { "epoch": 2.599884159520816, "grad_norm": 3.067741632461548, "learning_rate": 4.785815334174176e-06, "loss": 0.7501646041870117, "step": 92020 }, { "epoch": 2.6004492350290307, "grad_norm": 2.982259511947632, "learning_rate": 4.7725275850826146e-06, "loss": 0.835079288482666, "step": 92040 }, { "epoch": 2.6010143105372454, "grad_norm": 3.8827075958251953, "learning_rate": 4.759257383714333e-06, "loss": 0.8105080604553223, "step": 92060 }, { "epoch": 2.6015793860454606, "grad_norm": 3.806659460067749, "learning_rate": 4.746004735217991e-06, "loss": 0.8050829887390136, "step": 92080 }, { "epoch": 2.6021444615536753, "grad_norm": 3.5856480598449707, "learning_rate": 4.732769644735458e-06, "loss": 0.7724627494812012, "step": 92100 }, { "epoch": 2.60270953706189, "grad_norm": 2.8892433643341064, "learning_rate": 4.719552117401788e-06, "loss": 0.8256768226623535, "step": 92120 }, { "epoch": 2.6032746125701047, "grad_norm": 4.199977874755859, "learning_rate": 4.7063521583452395e-06, "loss": 0.7071042060852051, "step": 92140 }, { "epoch": 2.6038396880783194, "grad_norm": 3.261777877807617, "learning_rate": 4.693169772687234e-06, "loss": 0.7242946624755859, "step": 92160 }, { "epoch": 2.604404763586534, "grad_norm": 3.869621753692627, "learning_rate": 4.680004965542378e-06, "loss": 0.7396883010864258, "step": 92180 }, { "epoch": 2.604969839094749, "grad_norm": 2.970305919647217, "learning_rate": 4.666857742018455e-06, "loss": 0.7668228149414062, "step": 92200 }, { "epoch": 2.6055349146029636, "grad_norm": 3.5574872493743896, "learning_rate": 4.653728107216443e-06, "loss": 0.7547708511352539, "step": 92220 }, { "epoch": 2.6060999901111788, "grad_norm": 3.872762441635132, "learning_rate": 4.640616066230485e-06, "loss": 0.7096238613128663, "step": 92240 }, { "epoch": 2.6066650656193935, "grad_norm": 3.464520215988159, "learning_rate": 4.62752162414789e-06, "loss": 0.7245837688446045, "step": 92260 }, { "epoch": 2.607230141127608, "grad_norm": 3.207615613937378, "learning_rate": 4.614444786049144e-06, "loss": 0.7545083522796631, "step": 92280 }, { "epoch": 2.607795216635823, "grad_norm": 2.911435842514038, "learning_rate": 4.601385557007914e-06, "loss": 0.8065189361572266, "step": 92300 }, { "epoch": 2.6083602921440376, "grad_norm": 3.687232732772827, "learning_rate": 4.588343942091028e-06, "loss": 0.7398360252380372, "step": 92320 }, { "epoch": 2.608925367652253, "grad_norm": 3.5300867557525635, "learning_rate": 4.57531994635847e-06, "loss": 0.7878963470458984, "step": 92340 }, { "epoch": 2.6094904431604675, "grad_norm": 4.036169052124023, "learning_rate": 4.5623135748633915e-06, "loss": 0.7499199390411377, "step": 92360 }, { "epoch": 2.6100555186686822, "grad_norm": 3.162414073944092, "learning_rate": 4.549324832652113e-06, "loss": 0.7801686763763428, "step": 92380 }, { "epoch": 2.610620594176897, "grad_norm": 3.1610634326934814, "learning_rate": 4.536353724764131e-06, "loss": 0.706063985824585, "step": 92400 }, { "epoch": 2.6111856696851117, "grad_norm": 5.00316858291626, "learning_rate": 4.523400256232069e-06, "loss": 0.8317882537841796, "step": 92420 }, { "epoch": 2.6117507451933264, "grad_norm": 2.9992258548736572, "learning_rate": 4.510464432081712e-06, "loss": 0.777284574508667, "step": 92440 }, { "epoch": 2.612315820701541, "grad_norm": 4.472997188568115, "learning_rate": 4.497546257332008e-06, "loss": 0.7310008049011231, "step": 92460 }, { "epoch": 2.612880896209756, "grad_norm": 4.11522102355957, "learning_rate": 4.484645736995069e-06, "loss": 0.816403865814209, "step": 92480 }, { "epoch": 2.6134459717179706, "grad_norm": 5.927530288696289, "learning_rate": 4.47176287607613e-06, "loss": 0.7755026817321777, "step": 92500 }, { "epoch": 2.6140110472261857, "grad_norm": 2.995107650756836, "learning_rate": 4.458897679573598e-06, "loss": 0.815158748626709, "step": 92520 }, { "epoch": 2.6145761227344004, "grad_norm": 3.2539045810699463, "learning_rate": 4.446050152479003e-06, "loss": 0.7282363891601562, "step": 92540 }, { "epoch": 2.615141198242615, "grad_norm": 3.7759501934051514, "learning_rate": 4.433220299777052e-06, "loss": 0.7737781524658203, "step": 92560 }, { "epoch": 2.61570627375083, "grad_norm": 3.5984861850738525, "learning_rate": 4.420408126445569e-06, "loss": 0.7156067848205566, "step": 92580 }, { "epoch": 2.6162713492590446, "grad_norm": 4.241478443145752, "learning_rate": 4.407613637455516e-06, "loss": 0.7266971111297608, "step": 92600 }, { "epoch": 2.6168364247672598, "grad_norm": 4.134816646575928, "learning_rate": 4.3948368377710045e-06, "loss": 0.7871066093444824, "step": 92620 }, { "epoch": 2.6174015002754745, "grad_norm": 3.990485429763794, "learning_rate": 4.382077732349299e-06, "loss": 0.7581036567687989, "step": 92640 }, { "epoch": 2.617966575783689, "grad_norm": 3.292323112487793, "learning_rate": 4.369336326140766e-06, "loss": 0.7149014949798584, "step": 92660 }, { "epoch": 2.618531651291904, "grad_norm": 3.8986713886260986, "learning_rate": 4.356612624088918e-06, "loss": 0.7620784282684326, "step": 92680 }, { "epoch": 2.6190967268001186, "grad_norm": 4.361053466796875, "learning_rate": 4.343906631130396e-06, "loss": 0.7687686443328857, "step": 92700 }, { "epoch": 2.6196618023083333, "grad_norm": 3.9531362056732178, "learning_rate": 4.3312183521949936e-06, "loss": 0.7445015430450439, "step": 92720 }, { "epoch": 2.620226877816548, "grad_norm": 3.763967514038086, "learning_rate": 4.318547792205607e-06, "loss": 0.7558951377868652, "step": 92740 }, { "epoch": 2.620791953324763, "grad_norm": 3.6779332160949707, "learning_rate": 4.30589495607826e-06, "loss": 0.7408101558685303, "step": 92760 }, { "epoch": 2.621357028832978, "grad_norm": 3.7152841091156006, "learning_rate": 4.293259848722097e-06, "loss": 0.7638146877288818, "step": 92780 }, { "epoch": 2.6219221043411927, "grad_norm": 5.850330829620361, "learning_rate": 4.280642475039403e-06, "loss": 0.8760307312011719, "step": 92800 }, { "epoch": 2.6224871798494074, "grad_norm": 3.3500514030456543, "learning_rate": 4.268042839925557e-06, "loss": 0.7188445568084717, "step": 92820 }, { "epoch": 2.623052255357622, "grad_norm": 3.1396021842956543, "learning_rate": 4.25546094826908e-06, "loss": 0.8590169906616211, "step": 92840 }, { "epoch": 2.623617330865837, "grad_norm": 3.9406847953796387, "learning_rate": 4.242896804951574e-06, "loss": 0.7363849639892578, "step": 92860 }, { "epoch": 2.624182406374052, "grad_norm": 3.1262617111206055, "learning_rate": 4.2303504148478055e-06, "loss": 0.7598383903503418, "step": 92880 }, { "epoch": 2.6247474818822667, "grad_norm": 3.876229763031006, "learning_rate": 4.217821782825615e-06, "loss": 0.7593338012695312, "step": 92900 }, { "epoch": 2.6253125573904814, "grad_norm": 3.061940908432007, "learning_rate": 4.205310913745958e-06, "loss": 0.783343505859375, "step": 92920 }, { "epoch": 2.625877632898696, "grad_norm": 3.3014214038848877, "learning_rate": 4.1928178124629015e-06, "loss": 0.7483107089996338, "step": 92940 }, { "epoch": 2.626442708406911, "grad_norm": 2.8944733142852783, "learning_rate": 4.180342483823635e-06, "loss": 0.6797560214996338, "step": 92960 }, { "epoch": 2.6270077839151256, "grad_norm": 4.318055152893066, "learning_rate": 4.167884932668425e-06, "loss": 0.7359752655029297, "step": 92980 }, { "epoch": 2.6275728594233403, "grad_norm": 1.6480950117111206, "learning_rate": 4.155445163830662e-06, "loss": 0.6989009857177735, "step": 93000 }, { "epoch": 2.628137934931555, "grad_norm": 4.382110595703125, "learning_rate": 4.143023182136818e-06, "loss": 0.7667386054992675, "step": 93020 }, { "epoch": 2.62870301043977, "grad_norm": 2.753911256790161, "learning_rate": 4.130618992406476e-06, "loss": 0.753386116027832, "step": 93040 }, { "epoch": 2.629268085947985, "grad_norm": 3.99027681350708, "learning_rate": 4.118232599452332e-06, "loss": 0.8629287719726563, "step": 93060 }, { "epoch": 2.6298331614561996, "grad_norm": 3.0419585704803467, "learning_rate": 4.105864008080146e-06, "loss": 0.6915903091430664, "step": 93080 }, { "epoch": 2.6303982369644143, "grad_norm": 4.921574592590332, "learning_rate": 4.09351322308879e-06, "loss": 0.7702122688293457, "step": 93100 }, { "epoch": 2.630963312472629, "grad_norm": 4.50968074798584, "learning_rate": 4.081180249270206e-06, "loss": 0.7891176223754883, "step": 93120 }, { "epoch": 2.631528387980844, "grad_norm": 4.088270664215088, "learning_rate": 4.068865091409468e-06, "loss": 0.7026349544525147, "step": 93140 }, { "epoch": 2.632093463489059, "grad_norm": 2.9963386058807373, "learning_rate": 4.056567754284696e-06, "loss": 0.7579624652862549, "step": 93160 }, { "epoch": 2.6326585389972736, "grad_norm": 3.80806827545166, "learning_rate": 4.04428824266711e-06, "loss": 0.7179211616516114, "step": 93180 }, { "epoch": 2.6332236145054884, "grad_norm": 3.9361965656280518, "learning_rate": 4.032026561321012e-06, "loss": 0.7374162197113037, "step": 93200 }, { "epoch": 2.633788690013703, "grad_norm": 2.9015798568725586, "learning_rate": 4.0197827150038e-06, "loss": 0.7334261894226074, "step": 93220 }, { "epoch": 2.634353765521918, "grad_norm": 3.2135393619537354, "learning_rate": 4.007556708465942e-06, "loss": 0.7774141788482666, "step": 93240 }, { "epoch": 2.6349188410301325, "grad_norm": 3.4721806049346924, "learning_rate": 3.9953485464509724e-06, "loss": 0.7349721431732178, "step": 93260 }, { "epoch": 2.6354839165383472, "grad_norm": 3.863175630569458, "learning_rate": 3.983158233695516e-06, "loss": 0.7738768100738526, "step": 93280 }, { "epoch": 2.636048992046562, "grad_norm": 4.088034152984619, "learning_rate": 3.970985774929276e-06, "loss": 0.7150162696838379, "step": 93300 }, { "epoch": 2.636614067554777, "grad_norm": 3.9102320671081543, "learning_rate": 3.958831174875021e-06, "loss": 0.8036300659179687, "step": 93320 }, { "epoch": 2.637179143062992, "grad_norm": 4.115681171417236, "learning_rate": 3.946694438248588e-06, "loss": 0.7573657989501953, "step": 93340 }, { "epoch": 2.6377442185712066, "grad_norm": 3.3529465198516846, "learning_rate": 3.93457556975887e-06, "loss": 0.6724170684814453, "step": 93360 }, { "epoch": 2.6383092940794213, "grad_norm": 2.519479274749756, "learning_rate": 3.922474574107882e-06, "loss": 0.8320174217224121, "step": 93380 }, { "epoch": 2.638874369587636, "grad_norm": 3.085305690765381, "learning_rate": 3.910391455990647e-06, "loss": 0.776435375213623, "step": 93400 }, { "epoch": 2.639439445095851, "grad_norm": 5.1564106941223145, "learning_rate": 3.898326220095272e-06, "loss": 0.7567571640014649, "step": 93420 }, { "epoch": 2.640004520604066, "grad_norm": 3.685389995574951, "learning_rate": 3.886278871102917e-06, "loss": 0.721942949295044, "step": 93440 }, { "epoch": 2.6405695961122806, "grad_norm": 4.532622337341309, "learning_rate": 3.87424941368783e-06, "loss": 0.7945776462554932, "step": 93460 }, { "epoch": 2.6411346716204953, "grad_norm": 4.076175689697266, "learning_rate": 3.862237852517281e-06, "loss": 0.7463136672973633, "step": 93480 }, { "epoch": 2.64169974712871, "grad_norm": 3.1539556980133057, "learning_rate": 3.850244192251623e-06, "loss": 0.7402029037475586, "step": 93500 }, { "epoch": 2.6422648226369247, "grad_norm": 4.5992751121521, "learning_rate": 3.838268437544246e-06, "loss": 0.7929640293121338, "step": 93520 }, { "epoch": 2.6428298981451395, "grad_norm": 3.419518232345581, "learning_rate": 3.8263105930416095e-06, "loss": 0.7202672004699707, "step": 93540 }, { "epoch": 2.643394973653354, "grad_norm": 3.552731513977051, "learning_rate": 3.8143706633832153e-06, "loss": 0.7442058563232422, "step": 93560 }, { "epoch": 2.6439600491615693, "grad_norm": 2.9070730209350586, "learning_rate": 3.802448653201607e-06, "loss": 0.7136704921722412, "step": 93580 }, { "epoch": 2.644525124669784, "grad_norm": 4.181140422821045, "learning_rate": 3.7905445671223784e-06, "loss": 0.713711166381836, "step": 93600 }, { "epoch": 2.645090200177999, "grad_norm": 2.5027618408203125, "learning_rate": 3.7786584097641907e-06, "loss": 0.8053555488586426, "step": 93620 }, { "epoch": 2.6456552756862135, "grad_norm": 3.3623437881469727, "learning_rate": 3.766790185738728e-06, "loss": 0.7625900745391846, "step": 93640 }, { "epoch": 2.646220351194428, "grad_norm": 3.4424004554748535, "learning_rate": 3.7549398996507113e-06, "loss": 0.7505341053009034, "step": 93660 }, { "epoch": 2.6467854267026434, "grad_norm": 3.7574126720428467, "learning_rate": 3.7431075560979133e-06, "loss": 0.7641051769256592, "step": 93680 }, { "epoch": 2.647350502210858, "grad_norm": 4.515941143035889, "learning_rate": 3.73129315967114e-06, "loss": 0.7151418685913086, "step": 93700 }, { "epoch": 2.647915577719073, "grad_norm": 3.268401861190796, "learning_rate": 3.7194967149542515e-06, "loss": 0.7650156497955323, "step": 93720 }, { "epoch": 2.6484806532272875, "grad_norm": 3.3854644298553467, "learning_rate": 3.707718226524126e-06, "loss": 0.7363290786743164, "step": 93740 }, { "epoch": 2.6490457287355023, "grad_norm": 3.359328269958496, "learning_rate": 3.6959576989506695e-06, "loss": 0.7624368667602539, "step": 93760 }, { "epoch": 2.649610804243717, "grad_norm": 2.8515517711639404, "learning_rate": 3.6842151367968205e-06, "loss": 0.7291697978973388, "step": 93780 }, { "epoch": 2.6501758797519317, "grad_norm": 2.8890578746795654, "learning_rate": 3.6724905446185674e-06, "loss": 0.7659220695495605, "step": 93800 }, { "epoch": 2.6507409552601464, "grad_norm": 4.170234203338623, "learning_rate": 3.6607839269649112e-06, "loss": 0.7715217590332031, "step": 93820 }, { "epoch": 2.6513060307683616, "grad_norm": 4.139700412750244, "learning_rate": 3.6490952883778794e-06, "loss": 0.7543524742126465, "step": 93840 }, { "epoch": 2.6518711062765763, "grad_norm": 2.8981759548187256, "learning_rate": 3.6374246333925168e-06, "loss": 0.7426187992095947, "step": 93860 }, { "epoch": 2.652436181784791, "grad_norm": 3.287287712097168, "learning_rate": 3.6257719665369116e-06, "loss": 0.7184501647949219, "step": 93880 }, { "epoch": 2.6530012572930057, "grad_norm": 3.1436851024627686, "learning_rate": 3.614137292332154e-06, "loss": 0.776173448562622, "step": 93900 }, { "epoch": 2.6535663328012205, "grad_norm": 4.129060745239258, "learning_rate": 3.602520615292365e-06, "loss": 0.7596028327941895, "step": 93920 }, { "epoch": 2.6541314083094356, "grad_norm": 2.9788661003112793, "learning_rate": 3.590921939924663e-06, "loss": 0.7503623485565185, "step": 93940 }, { "epoch": 2.6546964838176503, "grad_norm": 3.369065999984741, "learning_rate": 3.579341270729214e-06, "loss": 0.7646988868713379, "step": 93960 }, { "epoch": 2.655261559325865, "grad_norm": 3.995877981185913, "learning_rate": 3.567778612199174e-06, "loss": 0.7733615398406982, "step": 93980 }, { "epoch": 2.6558266348340798, "grad_norm": 4.324748992919922, "learning_rate": 3.556233968820716e-06, "loss": 0.7976439476013184, "step": 94000 }, { "epoch": 2.6563917103422945, "grad_norm": 3.8819947242736816, "learning_rate": 3.5447073450730117e-06, "loss": 0.6780472755432129, "step": 94020 }, { "epoch": 2.656956785850509, "grad_norm": 3.8728177547454834, "learning_rate": 3.5331987454282843e-06, "loss": 0.7847508907318115, "step": 94040 }, { "epoch": 2.657521861358724, "grad_norm": 4.032902717590332, "learning_rate": 3.5217081743517176e-06, "loss": 0.7525805950164794, "step": 94060 }, { "epoch": 2.6580869368669386, "grad_norm": 3.3128533363342285, "learning_rate": 3.5102356363015174e-06, "loss": 0.8499149322509766, "step": 94080 }, { "epoch": 2.6586520123751534, "grad_norm": 4.8931565284729, "learning_rate": 3.4987811357288847e-06, "loss": 0.7853232383728027, "step": 94100 }, { "epoch": 2.6592170878833685, "grad_norm": 2.489884376525879, "learning_rate": 3.487344677078047e-06, "loss": 0.7706162452697753, "step": 94120 }, { "epoch": 2.6597821633915832, "grad_norm": 3.8507349491119385, "learning_rate": 3.475926264786206e-06, "loss": 0.7503835201263428, "step": 94140 }, { "epoch": 2.660347238899798, "grad_norm": 4.8780951499938965, "learning_rate": 3.4645259032835664e-06, "loss": 0.7235280990600585, "step": 94160 }, { "epoch": 2.6609123144080127, "grad_norm": 2.9052042961120605, "learning_rate": 3.4531435969933356e-06, "loss": 0.7286582469940186, "step": 94180 }, { "epoch": 2.6614773899162274, "grad_norm": 3.8488967418670654, "learning_rate": 3.4417793503317198e-06, "loss": 0.7546254158020019, "step": 94200 }, { "epoch": 2.6620424654244426, "grad_norm": 3.6779139041900635, "learning_rate": 3.4304331677079026e-06, "loss": 0.8020838737487793, "step": 94220 }, { "epoch": 2.6626075409326573, "grad_norm": 4.480523109436035, "learning_rate": 3.4191050535240796e-06, "loss": 0.7002540588378906, "step": 94240 }, { "epoch": 2.663172616440872, "grad_norm": 2.2442479133605957, "learning_rate": 3.4077950121754077e-06, "loss": 0.8057920455932617, "step": 94260 }, { "epoch": 2.6637376919490867, "grad_norm": 4.3945817947387695, "learning_rate": 3.3965030480500648e-06, "loss": 0.8251914978027344, "step": 94280 }, { "epoch": 2.6643027674573014, "grad_norm": 3.547581434249878, "learning_rate": 3.3852291655291966e-06, "loss": 0.7699577808380127, "step": 94300 }, { "epoch": 2.664867842965516, "grad_norm": 2.947464942932129, "learning_rate": 3.3739733689869325e-06, "loss": 0.7808582305908203, "step": 94320 }, { "epoch": 2.665432918473731, "grad_norm": 4.210326194763184, "learning_rate": 3.3627356627903783e-06, "loss": 0.6947793960571289, "step": 94340 }, { "epoch": 2.6659979939819456, "grad_norm": 3.0809476375579834, "learning_rate": 3.3515160512996467e-06, "loss": 0.7977633476257324, "step": 94360 }, { "epoch": 2.6665630694901608, "grad_norm": 3.247027635574341, "learning_rate": 3.3403145388678115e-06, "loss": 0.7806368827819824, "step": 94380 }, { "epoch": 2.6671281449983755, "grad_norm": 4.489386558532715, "learning_rate": 3.3291311298409235e-06, "loss": 0.7598426818847657, "step": 94400 }, { "epoch": 2.66769322050659, "grad_norm": 4.6649980545043945, "learning_rate": 3.3179658285580172e-06, "loss": 0.7583106517791748, "step": 94420 }, { "epoch": 2.668258296014805, "grad_norm": 3.0227980613708496, "learning_rate": 3.3068186393510835e-06, "loss": 0.7331140041351318, "step": 94440 }, { "epoch": 2.6688233715230196, "grad_norm": 4.013112545013428, "learning_rate": 3.295689566545113e-06, "loss": 0.7126386642456055, "step": 94460 }, { "epoch": 2.669388447031235, "grad_norm": 3.675168991088867, "learning_rate": 3.284578614458056e-06, "loss": 0.7901036739349365, "step": 94480 }, { "epoch": 2.6699535225394495, "grad_norm": 3.8016788959503174, "learning_rate": 3.2734857874008205e-06, "loss": 0.7273840427398681, "step": 94500 }, { "epoch": 2.6705185980476642, "grad_norm": 5.1350908279418945, "learning_rate": 3.262411089677292e-06, "loss": 0.7013351440429687, "step": 94520 }, { "epoch": 2.671083673555879, "grad_norm": 3.698460817337036, "learning_rate": 3.251354525584327e-06, "loss": 0.6966608047485352, "step": 94540 }, { "epoch": 2.6716487490640937, "grad_norm": 3.473829984664917, "learning_rate": 3.2403160994117497e-06, "loss": 0.7259060859680175, "step": 94560 }, { "epoch": 2.6722138245723084, "grad_norm": 3.596679925918579, "learning_rate": 3.2292958154423235e-06, "loss": 0.7641230583190918, "step": 94580 }, { "epoch": 2.672778900080523, "grad_norm": 4.831677436828613, "learning_rate": 3.2182936779517834e-06, "loss": 0.7368326187133789, "step": 94600 }, { "epoch": 2.673343975588738, "grad_norm": 3.4382450580596924, "learning_rate": 3.2073096912088486e-06, "loss": 0.7024074077606202, "step": 94620 }, { "epoch": 2.673909051096953, "grad_norm": 3.1323065757751465, "learning_rate": 3.1963438594751704e-06, "loss": 0.7208561897277832, "step": 94640 }, { "epoch": 2.6744741266051677, "grad_norm": 4.067119598388672, "learning_rate": 3.185396187005352e-06, "loss": 0.7695045948028565, "step": 94660 }, { "epoch": 2.6750392021133824, "grad_norm": 3.7669131755828857, "learning_rate": 3.1744666780469556e-06, "loss": 0.7641220569610596, "step": 94680 }, { "epoch": 2.675604277621597, "grad_norm": 2.6069512367248535, "learning_rate": 3.163555336840518e-06, "loss": 0.6819882392883301, "step": 94700 }, { "epoch": 2.676169353129812, "grad_norm": 3.9158787727355957, "learning_rate": 3.152662167619502e-06, "loss": 0.724684190750122, "step": 94720 }, { "epoch": 2.676734428638027, "grad_norm": 5.475016117095947, "learning_rate": 3.141787174610339e-06, "loss": 0.6819281101226806, "step": 94740 }, { "epoch": 2.6772995041462417, "grad_norm": 2.1956393718719482, "learning_rate": 3.130930362032375e-06, "loss": 0.7406699657440186, "step": 94760 }, { "epoch": 2.6778645796544565, "grad_norm": 3.7790629863739014, "learning_rate": 3.120091734097946e-06, "loss": 0.6277597904205322, "step": 94780 }, { "epoch": 2.678429655162671, "grad_norm": 3.70084547996521, "learning_rate": 3.1092712950123004e-06, "loss": 0.7820093631744385, "step": 94800 }, { "epoch": 2.678994730670886, "grad_norm": 4.433177947998047, "learning_rate": 3.0984690489736458e-06, "loss": 0.8558335304260254, "step": 94820 }, { "epoch": 2.6795598061791006, "grad_norm": 3.8787221908569336, "learning_rate": 3.0876850001731127e-06, "loss": 0.7194746971130371, "step": 94840 }, { "epoch": 2.6801248816873153, "grad_norm": 2.7982349395751953, "learning_rate": 3.0769191527947995e-06, "loss": 0.7436867713928222, "step": 94860 }, { "epoch": 2.68068995719553, "grad_norm": 5.3370561599731445, "learning_rate": 3.0661715110157252e-06, "loss": 0.7181621551513672, "step": 94880 }, { "epoch": 2.6812550327037448, "grad_norm": 3.2424278259277344, "learning_rate": 3.0554420790058435e-06, "loss": 0.7776577472686768, "step": 94900 }, { "epoch": 2.68182010821196, "grad_norm": 4.416662216186523, "learning_rate": 3.044730860928041e-06, "loss": 0.8009421348571777, "step": 94920 }, { "epoch": 2.6823851837201746, "grad_norm": 4.489235877990723, "learning_rate": 3.034037860938155e-06, "loss": 0.7547584056854248, "step": 94940 }, { "epoch": 2.6829502592283894, "grad_norm": 4.675174236297607, "learning_rate": 3.023363083184938e-06, "loss": 0.63852858543396, "step": 94960 }, { "epoch": 2.683515334736604, "grad_norm": 5.044027805328369, "learning_rate": 3.012706531810078e-06, "loss": 0.731445026397705, "step": 94980 }, { "epoch": 2.684080410244819, "grad_norm": 4.17926549911499, "learning_rate": 3.002068210948178e-06, "loss": 0.7592526435852051, "step": 95000 }, { "epoch": 2.684645485753034, "grad_norm": 2.8781497478485107, "learning_rate": 2.9914481247267923e-06, "loss": 0.7858617305755615, "step": 95020 }, { "epoch": 2.6852105612612487, "grad_norm": 2.7238364219665527, "learning_rate": 2.980846277266397e-06, "loss": 0.7103788375854492, "step": 95040 }, { "epoch": 2.6857756367694634, "grad_norm": 2.4236721992492676, "learning_rate": 2.9702626726803795e-06, "loss": 0.7350324630737305, "step": 95060 }, { "epoch": 2.686340712277678, "grad_norm": 4.660572528839111, "learning_rate": 2.9596973150750386e-06, "loss": 0.7530683040618896, "step": 95080 }, { "epoch": 2.686905787785893, "grad_norm": 3.314678192138672, "learning_rate": 2.949150208549617e-06, "loss": 0.7232630252838135, "step": 95100 }, { "epoch": 2.6874708632941076, "grad_norm": 3.184703826904297, "learning_rate": 2.9386213571962694e-06, "loss": 0.8199353218078613, "step": 95120 }, { "epoch": 2.6880359388023223, "grad_norm": 3.510195016860962, "learning_rate": 2.9281107651000616e-06, "loss": 0.8337512969970703, "step": 95140 }, { "epoch": 2.688601014310537, "grad_norm": 4.042627334594727, "learning_rate": 2.917618436338987e-06, "loss": 0.7649662971496582, "step": 95160 }, { "epoch": 2.689166089818752, "grad_norm": 2.1079537868499756, "learning_rate": 2.9071443749839223e-06, "loss": 0.7089301586151123, "step": 95180 }, { "epoch": 2.689731165326967, "grad_norm": 3.0142884254455566, "learning_rate": 2.8966885850987057e-06, "loss": 0.727196455001831, "step": 95200 }, { "epoch": 2.6902962408351816, "grad_norm": 4.138429164886475, "learning_rate": 2.886251070740048e-06, "loss": 0.675248670578003, "step": 95220 }, { "epoch": 2.6908613163433963, "grad_norm": 3.685656785964966, "learning_rate": 2.8758318359575877e-06, "loss": 0.7054895877838134, "step": 95240 }, { "epoch": 2.691426391851611, "grad_norm": 4.40869140625, "learning_rate": 2.865430884793846e-06, "loss": 0.7044014930725098, "step": 95260 }, { "epoch": 2.691991467359826, "grad_norm": 5.537776470184326, "learning_rate": 2.8550482212842843e-06, "loss": 0.7567248821258545, "step": 95280 }, { "epoch": 2.692556542868041, "grad_norm": 2.8416011333465576, "learning_rate": 2.8446838494572583e-06, "loss": 0.7285076141357422, "step": 95300 }, { "epoch": 2.6931216183762556, "grad_norm": 1.7370070219039917, "learning_rate": 2.834337773334006e-06, "loss": 0.7463578224182129, "step": 95320 }, { "epoch": 2.6936866938844704, "grad_norm": 3.33323073387146, "learning_rate": 2.8240099969286838e-06, "loss": 0.7063543319702148, "step": 95340 }, { "epoch": 2.694251769392685, "grad_norm": 3.2807164192199707, "learning_rate": 2.8137005242483527e-06, "loss": 0.7713628292083741, "step": 95360 }, { "epoch": 2.6948168449009, "grad_norm": 2.7757532596588135, "learning_rate": 2.8034093592929746e-06, "loss": 0.7379007339477539, "step": 95380 }, { "epoch": 2.6953819204091145, "grad_norm": 3.4032368659973145, "learning_rate": 2.7931365060553884e-06, "loss": 0.7324366569519043, "step": 95400 }, { "epoch": 2.6959469959173292, "grad_norm": 4.561141014099121, "learning_rate": 2.782881968521334e-06, "loss": 0.7259119987487793, "step": 95420 }, { "epoch": 2.6965120714255444, "grad_norm": 4.7602996826171875, "learning_rate": 2.772645750669467e-06, "loss": 0.6843719959259034, "step": 95440 }, { "epoch": 2.697077146933759, "grad_norm": 4.883210182189941, "learning_rate": 2.762427856471306e-06, "loss": 0.7639389514923096, "step": 95460 }, { "epoch": 2.697642222441974, "grad_norm": 5.394327163696289, "learning_rate": 2.752228289891273e-06, "loss": 0.7500880241394043, "step": 95480 }, { "epoch": 2.6982072979501885, "grad_norm": 3.4717001914978027, "learning_rate": 2.7420470548866817e-06, "loss": 0.7841912746429444, "step": 95500 }, { "epoch": 2.6987723734584033, "grad_norm": 4.814495086669922, "learning_rate": 2.731884155407738e-06, "loss": 0.7782947063446045, "step": 95520 }, { "epoch": 2.6993374489666184, "grad_norm": 3.0554263591766357, "learning_rate": 2.7217395953975154e-06, "loss": 0.8332831382751464, "step": 95540 }, { "epoch": 2.699902524474833, "grad_norm": 3.663672924041748, "learning_rate": 2.7116133787919886e-06, "loss": 0.7485408782958984, "step": 95560 }, { "epoch": 2.700467599983048, "grad_norm": 4.256589889526367, "learning_rate": 2.701505509519997e-06, "loss": 0.7444677352905273, "step": 95580 }, { "epoch": 2.7010326754912626, "grad_norm": 3.400570869445801, "learning_rate": 2.6914159915032988e-06, "loss": 0.7961688041687012, "step": 95600 }, { "epoch": 2.7015977509994773, "grad_norm": 3.584242820739746, "learning_rate": 2.68134482865649e-06, "loss": 0.727991247177124, "step": 95620 }, { "epoch": 2.702162826507692, "grad_norm": 3.896637201309204, "learning_rate": 2.6712920248870676e-06, "loss": 0.7400825977325439, "step": 95640 }, { "epoch": 2.7027279020159067, "grad_norm": 3.0828890800476074, "learning_rate": 2.661257584095389e-06, "loss": 0.8095718383789062, "step": 95660 }, { "epoch": 2.7032929775241215, "grad_norm": 4.287500381469727, "learning_rate": 2.6512415101747066e-06, "loss": 0.7164906978607177, "step": 95680 }, { "epoch": 2.703858053032336, "grad_norm": 2.8093390464782715, "learning_rate": 2.641243807011151e-06, "loss": 0.6893928050994873, "step": 95700 }, { "epoch": 2.7044231285405513, "grad_norm": 3.9659194946289062, "learning_rate": 2.6312644784837026e-06, "loss": 0.7364337921142579, "step": 95720 }, { "epoch": 2.704988204048766, "grad_norm": 3.156841516494751, "learning_rate": 2.6213035284642197e-06, "loss": 0.8024464607238769, "step": 95740 }, { "epoch": 2.7055532795569808, "grad_norm": 3.119305372238159, "learning_rate": 2.6113609608174274e-06, "loss": 0.6821823120117188, "step": 95760 }, { "epoch": 2.7061183550651955, "grad_norm": 4.432268142700195, "learning_rate": 2.601436779400934e-06, "loss": 0.7006831169128418, "step": 95780 }, { "epoch": 2.70668343057341, "grad_norm": 3.6540632247924805, "learning_rate": 2.591530988065205e-06, "loss": 0.7999743938446044, "step": 95800 }, { "epoch": 2.7072485060816254, "grad_norm": 5.8787522315979, "learning_rate": 2.5816435906535705e-06, "loss": 0.865394401550293, "step": 95820 }, { "epoch": 2.70781358158984, "grad_norm": 4.70010232925415, "learning_rate": 2.5717745910022073e-06, "loss": 0.789880895614624, "step": 95840 }, { "epoch": 2.708378657098055, "grad_norm": 3.711191415786743, "learning_rate": 2.5619239929401907e-06, "loss": 0.7541636466979981, "step": 95860 }, { "epoch": 2.7089437326062695, "grad_norm": 4.7240214347839355, "learning_rate": 2.55209180028943e-06, "loss": 0.7357531547546386, "step": 95880 }, { "epoch": 2.7095088081144842, "grad_norm": 4.1271891593933105, "learning_rate": 2.542278016864691e-06, "loss": 0.7197568416595459, "step": 95900 }, { "epoch": 2.710073883622699, "grad_norm": 4.228117942810059, "learning_rate": 2.5324826464736107e-06, "loss": 0.8050104141235351, "step": 95920 }, { "epoch": 2.7106389591309137, "grad_norm": 3.616180896759033, "learning_rate": 2.5227056929166827e-06, "loss": 0.77646484375, "step": 95940 }, { "epoch": 2.7112040346391284, "grad_norm": 3.8418362140655518, "learning_rate": 2.5129471599872446e-06, "loss": 0.7083987236022949, "step": 95960 }, { "epoch": 2.7117691101473436, "grad_norm": 3.1254358291625977, "learning_rate": 2.50320705147149e-06, "loss": 0.7678520679473877, "step": 95980 }, { "epoch": 2.7123341856555583, "grad_norm": 3.915313959121704, "learning_rate": 2.4934853711484628e-06, "loss": 0.7774358272552491, "step": 96000 }, { "epoch": 2.712899261163773, "grad_norm": 2.833996534347534, "learning_rate": 2.4837821227900573e-06, "loss": 0.7321971893310547, "step": 96020 }, { "epoch": 2.7134643366719877, "grad_norm": 3.1631698608398438, "learning_rate": 2.4740973101610387e-06, "loss": 0.7168502807617188, "step": 96040 }, { "epoch": 2.7140294121802024, "grad_norm": 3.8150174617767334, "learning_rate": 2.46443093701898e-06, "loss": 0.7259203910827636, "step": 96060 }, { "epoch": 2.7145944876884176, "grad_norm": 4.356371879577637, "learning_rate": 2.4547830071143194e-06, "loss": 0.7321439266204834, "step": 96080 }, { "epoch": 2.7151595631966323, "grad_norm": 3.8332650661468506, "learning_rate": 2.445153524190358e-06, "loss": 0.7796533584594727, "step": 96100 }, { "epoch": 2.715724638704847, "grad_norm": 3.858433723449707, "learning_rate": 2.4355424919832006e-06, "loss": 0.7937849044799805, "step": 96120 }, { "epoch": 2.7162897142130618, "grad_norm": 2.5047054290771484, "learning_rate": 2.4259499142218256e-06, "loss": 0.7395134449005127, "step": 96140 }, { "epoch": 2.7168547897212765, "grad_norm": 6.133002281188965, "learning_rate": 2.4163757946280287e-06, "loss": 0.8083181381225586, "step": 96160 }, { "epoch": 2.717419865229491, "grad_norm": 3.542499303817749, "learning_rate": 2.4068201369164657e-06, "loss": 0.7862574100494385, "step": 96180 }, { "epoch": 2.717984940737706, "grad_norm": 4.756120204925537, "learning_rate": 2.3972829447946154e-06, "loss": 0.7004033088684082, "step": 96200 }, { "epoch": 2.7185500162459206, "grad_norm": 3.708970308303833, "learning_rate": 2.387764221962796e-06, "loss": 0.6968698501586914, "step": 96220 }, { "epoch": 2.719115091754136, "grad_norm": 3.2455925941467285, "learning_rate": 2.3782639721141473e-06, "loss": 0.7141858577728272, "step": 96240 }, { "epoch": 2.7196801672623505, "grad_norm": 3.025648355484009, "learning_rate": 2.368782198934677e-06, "loss": 0.796836519241333, "step": 96260 }, { "epoch": 2.7202452427705652, "grad_norm": 5.683477878570557, "learning_rate": 2.3593189061031807e-06, "loss": 0.7383206367492676, "step": 96280 }, { "epoch": 2.72081031827878, "grad_norm": 4.470215320587158, "learning_rate": 2.3498740972913104e-06, "loss": 0.7411966323852539, "step": 96300 }, { "epoch": 2.7213753937869947, "grad_norm": 2.9321470260620117, "learning_rate": 2.3404477761635347e-06, "loss": 0.7161251068115234, "step": 96320 }, { "epoch": 2.72194046929521, "grad_norm": 4.044042110443115, "learning_rate": 2.3310399463771614e-06, "loss": 0.7450586795806885, "step": 96340 }, { "epoch": 2.7225055448034245, "grad_norm": 3.5690698623657227, "learning_rate": 2.321650611582321e-06, "loss": 0.7731002330780029, "step": 96360 }, { "epoch": 2.7230706203116393, "grad_norm": 3.1720733642578125, "learning_rate": 2.3122797754219603e-06, "loss": 0.6324253559112549, "step": 96380 }, { "epoch": 2.723635695819854, "grad_norm": 4.147177219390869, "learning_rate": 2.302927441531849e-06, "loss": 0.7928482055664062, "step": 96400 }, { "epoch": 2.7242007713280687, "grad_norm": 3.1270229816436768, "learning_rate": 2.293593613540579e-06, "loss": 0.7512900829315186, "step": 96420 }, { "epoch": 2.7247658468362834, "grad_norm": 3.101681709289551, "learning_rate": 2.2842782950695753e-06, "loss": 0.783455753326416, "step": 96440 }, { "epoch": 2.725330922344498, "grad_norm": 2.679741382598877, "learning_rate": 2.2749814897330633e-06, "loss": 0.743285846710205, "step": 96460 }, { "epoch": 2.725895997852713, "grad_norm": 3.3086893558502197, "learning_rate": 2.2657032011380975e-06, "loss": 0.6482701778411866, "step": 96480 }, { "epoch": 2.7264610733609276, "grad_norm": 3.7210628986358643, "learning_rate": 2.2564434328845363e-06, "loss": 0.7213587284088134, "step": 96500 }, { "epoch": 2.7270261488691427, "grad_norm": 4.672501087188721, "learning_rate": 2.2472021885650728e-06, "loss": 0.7668561458587646, "step": 96520 }, { "epoch": 2.7275912243773575, "grad_norm": 3.6887319087982178, "learning_rate": 2.237979471765189e-06, "loss": 0.7243677616119385, "step": 96540 }, { "epoch": 2.728156299885572, "grad_norm": 5.376861572265625, "learning_rate": 2.228775286063195e-06, "loss": 0.7959907531738282, "step": 96560 }, { "epoch": 2.728721375393787, "grad_norm": 3.7342231273651123, "learning_rate": 2.2195896350302e-06, "loss": 0.7350684642791748, "step": 96580 }, { "epoch": 2.7292864509020016, "grad_norm": 2.881425380706787, "learning_rate": 2.210422522230138e-06, "loss": 0.7857671737670898, "step": 96600 }, { "epoch": 2.7298515264102168, "grad_norm": 3.8825860023498535, "learning_rate": 2.2012739512197344e-06, "loss": 0.7826356410980224, "step": 96620 }, { "epoch": 2.7304166019184315, "grad_norm": 3.164217233657837, "learning_rate": 2.192143925548529e-06, "loss": 0.7880990028381347, "step": 96640 }, { "epoch": 2.730981677426646, "grad_norm": 3.9641294479370117, "learning_rate": 2.1830324487588484e-06, "loss": 0.7638239860534668, "step": 96660 }, { "epoch": 2.731546752934861, "grad_norm": 4.3354668617248535, "learning_rate": 2.173939524385854e-06, "loss": 0.7150889873504639, "step": 96680 }, { "epoch": 2.7321118284430757, "grad_norm": 2.8808155059814453, "learning_rate": 2.1648651559574963e-06, "loss": 0.8004815101623535, "step": 96700 }, { "epoch": 2.7326769039512904, "grad_norm": 2.6173150539398193, "learning_rate": 2.1558093469945086e-06, "loss": 0.8017740249633789, "step": 96720 }, { "epoch": 2.733241979459505, "grad_norm": 4.608136177062988, "learning_rate": 2.1467721010104526e-06, "loss": 0.7418782711029053, "step": 96740 }, { "epoch": 2.73380705496772, "grad_norm": 3.1243629455566406, "learning_rate": 2.137753421511651e-06, "loss": 0.7477731227874755, "step": 96760 }, { "epoch": 2.734372130475935, "grad_norm": 3.87404203414917, "learning_rate": 2.128753311997267e-06, "loss": 0.808309268951416, "step": 96780 }, { "epoch": 2.7349372059841497, "grad_norm": 6.023615837097168, "learning_rate": 2.119771775959228e-06, "loss": 0.7126302242279052, "step": 96800 }, { "epoch": 2.7355022814923644, "grad_norm": 2.523763418197632, "learning_rate": 2.110808816882254e-06, "loss": 0.6420260906219483, "step": 96820 }, { "epoch": 2.736067357000579, "grad_norm": 3.2324366569519043, "learning_rate": 2.1018644382438833e-06, "loss": 0.672900390625, "step": 96840 }, { "epoch": 2.736632432508794, "grad_norm": 3.4099440574645996, "learning_rate": 2.092938643514419e-06, "loss": 0.7210893154144287, "step": 96860 }, { "epoch": 2.737197508017009, "grad_norm": 3.2608065605163574, "learning_rate": 2.0840314361569637e-06, "loss": 0.782463264465332, "step": 96880 }, { "epoch": 2.7377625835252237, "grad_norm": 3.867932081222534, "learning_rate": 2.075142819627407e-06, "loss": 0.7319160461425781, "step": 96900 }, { "epoch": 2.7383276590334384, "grad_norm": 3.7560973167419434, "learning_rate": 2.0662727973744355e-06, "loss": 0.7477685451507569, "step": 96920 }, { "epoch": 2.738892734541653, "grad_norm": 3.084144353866577, "learning_rate": 2.0574213728395075e-06, "loss": 0.7626550674438477, "step": 96940 }, { "epoch": 2.739457810049868, "grad_norm": 3.020631790161133, "learning_rate": 2.04858854945687e-06, "loss": 0.7104151725769043, "step": 96960 }, { "epoch": 2.7400228855580826, "grad_norm": 2.6382875442504883, "learning_rate": 2.039774330653549e-06, "loss": 0.706021499633789, "step": 96980 }, { "epoch": 2.7405879610662973, "grad_norm": 3.295456886291504, "learning_rate": 2.0309787198493637e-06, "loss": 0.7175056457519531, "step": 97000 }, { "epoch": 2.741153036574512, "grad_norm": 4.056973934173584, "learning_rate": 2.022201720456912e-06, "loss": 0.7790933609008789, "step": 97020 }, { "epoch": 2.741718112082727, "grad_norm": 5.303586959838867, "learning_rate": 2.013443335881554e-06, "loss": 0.7378820896148681, "step": 97040 }, { "epoch": 2.742283187590942, "grad_norm": 3.81834077835083, "learning_rate": 2.004703569521449e-06, "loss": 0.7982577800750732, "step": 97060 }, { "epoch": 2.7428482630991566, "grad_norm": 2.9366371631622314, "learning_rate": 1.995982424767506e-06, "loss": 0.7716881275177002, "step": 97080 }, { "epoch": 2.7434133386073714, "grad_norm": 5.0356011390686035, "learning_rate": 1.9872799050034473e-06, "loss": 0.7559042930603027, "step": 97100 }, { "epoch": 2.743978414115586, "grad_norm": 2.486424684524536, "learning_rate": 1.978596013605738e-06, "loss": 0.7430251598358154, "step": 97120 }, { "epoch": 2.7445434896238012, "grad_norm": 3.2646358013153076, "learning_rate": 1.9699307539436274e-06, "loss": 0.758413553237915, "step": 97140 }, { "epoch": 2.745108565132016, "grad_norm": 2.9765076637268066, "learning_rate": 1.9612841293791206e-06, "loss": 0.7289614677429199, "step": 97160 }, { "epoch": 2.7456736406402307, "grad_norm": 3.5391507148742676, "learning_rate": 1.952656143267023e-06, "loss": 0.6349109172821045, "step": 97180 }, { "epoch": 2.7462387161484454, "grad_norm": 4.983766078948975, "learning_rate": 1.944046798954885e-06, "loss": 0.7810863494873047, "step": 97200 }, { "epoch": 2.74680379165666, "grad_norm": 3.521135091781616, "learning_rate": 1.9354560997830227e-06, "loss": 0.701008939743042, "step": 97220 }, { "epoch": 2.747368867164875, "grad_norm": 3.984678030014038, "learning_rate": 1.926884049084532e-06, "loss": 0.6748887062072754, "step": 97240 }, { "epoch": 2.7479339426730895, "grad_norm": 4.568266868591309, "learning_rate": 1.918330650185274e-06, "loss": 0.6674945831298829, "step": 97260 }, { "epoch": 2.7484990181813043, "grad_norm": 3.371781587600708, "learning_rate": 1.9097959064038552e-06, "loss": 0.7577249050140381, "step": 97280 }, { "epoch": 2.7490640936895194, "grad_norm": 3.383094549179077, "learning_rate": 1.9012798210516602e-06, "loss": 0.7685121536254883, "step": 97300 }, { "epoch": 2.749629169197734, "grad_norm": 4.015735149383545, "learning_rate": 1.8927823974328185e-06, "loss": 0.7021923542022706, "step": 97320 }, { "epoch": 2.750194244705949, "grad_norm": 2.978860378265381, "learning_rate": 1.8843036388442426e-06, "loss": 0.758549690246582, "step": 97340 }, { "epoch": 2.7507593202141636, "grad_norm": 2.8083901405334473, "learning_rate": 1.8758435485755954e-06, "loss": 0.65214524269104, "step": 97360 }, { "epoch": 2.7513243957223783, "grad_norm": 4.347059726715088, "learning_rate": 1.8674021299092792e-06, "loss": 0.7195967674255371, "step": 97380 }, { "epoch": 2.7518894712305935, "grad_norm": 3.2386085987091064, "learning_rate": 1.8589793861204685e-06, "loss": 0.7138598918914795, "step": 97400 }, { "epoch": 2.752454546738808, "grad_norm": 3.693268299102783, "learning_rate": 1.850575320477077e-06, "loss": 0.6796635150909424, "step": 97420 }, { "epoch": 2.753019622247023, "grad_norm": 3.6834230422973633, "learning_rate": 1.8421899362398076e-06, "loss": 0.7471239566802979, "step": 97440 }, { "epoch": 2.7535846977552376, "grad_norm": 3.321647882461548, "learning_rate": 1.8338232366620688e-06, "loss": 0.7831416130065918, "step": 97460 }, { "epoch": 2.7541497732634523, "grad_norm": 3.773444890975952, "learning_rate": 1.8254752249900475e-06, "loss": 0.8077766418457031, "step": 97480 }, { "epoch": 2.754714848771667, "grad_norm": 3.461554527282715, "learning_rate": 1.8171459044626748e-06, "loss": 0.7487839698791504, "step": 97500 }, { "epoch": 2.7552799242798818, "grad_norm": 3.770507335662842, "learning_rate": 1.8088352783116268e-06, "loss": 0.7334539890289307, "step": 97520 }, { "epoch": 2.7558449997880965, "grad_norm": 3.815864324569702, "learning_rate": 1.80054334976133e-06, "loss": 0.7231059074401855, "step": 97540 }, { "epoch": 2.756410075296311, "grad_norm": 3.6258091926574707, "learning_rate": 1.7922701220289495e-06, "loss": 0.7376895427703858, "step": 97560 }, { "epoch": 2.7569751508045264, "grad_norm": 4.48807954788208, "learning_rate": 1.7840155983244067e-06, "loss": 0.8122498512268066, "step": 97580 }, { "epoch": 2.757540226312741, "grad_norm": 3.3291032314300537, "learning_rate": 1.7757797818503563e-06, "loss": 0.781374454498291, "step": 97600 }, { "epoch": 2.758105301820956, "grad_norm": 2.040940284729004, "learning_rate": 1.7675626758021923e-06, "loss": 0.6699029922485351, "step": 97620 }, { "epoch": 2.7586703773291705, "grad_norm": 5.572581768035889, "learning_rate": 1.7593642833680536e-06, "loss": 0.8343088150024414, "step": 97640 }, { "epoch": 2.7592354528373852, "grad_norm": 3.331326484680176, "learning_rate": 1.751184607728823e-06, "loss": 0.7000308513641358, "step": 97660 }, { "epoch": 2.7598005283456004, "grad_norm": 2.570216655731201, "learning_rate": 1.7430236520581288e-06, "loss": 0.8073712348937988, "step": 97680 }, { "epoch": 2.760365603853815, "grad_norm": 5.606550216674805, "learning_rate": 1.7348814195223107e-06, "loss": 0.7166836738586426, "step": 97700 }, { "epoch": 2.76093067936203, "grad_norm": 3.13502836227417, "learning_rate": 1.7267579132804634e-06, "loss": 0.8289766311645508, "step": 97720 }, { "epoch": 2.7614957548702446, "grad_norm": 4.597285747528076, "learning_rate": 1.718653136484405e-06, "loss": 0.7611979007720947, "step": 97740 }, { "epoch": 2.7620608303784593, "grad_norm": 2.9661784172058105, "learning_rate": 1.7105670922787086e-06, "loss": 0.769493293762207, "step": 97760 }, { "epoch": 2.762625905886674, "grad_norm": 3.585029363632202, "learning_rate": 1.7024997838006485e-06, "loss": 0.8269964218139648, "step": 97780 }, { "epoch": 2.7631909813948887, "grad_norm": 4.4674296379089355, "learning_rate": 1.6944512141802483e-06, "loss": 0.8368711471557617, "step": 97800 }, { "epoch": 2.7637560569031034, "grad_norm": 3.5436837673187256, "learning_rate": 1.6864213865402545e-06, "loss": 0.6953563213348388, "step": 97820 }, { "epoch": 2.7643211324113186, "grad_norm": 3.6451315879821777, "learning_rate": 1.678410303996153e-06, "loss": 0.7784425735473632, "step": 97840 }, { "epoch": 2.7648862079195333, "grad_norm": 3.6038386821746826, "learning_rate": 1.6704179696561462e-06, "loss": 0.7773226261138916, "step": 97860 }, { "epoch": 2.765451283427748, "grad_norm": 4.830781936645508, "learning_rate": 1.6624443866211647e-06, "loss": 0.7927275180816651, "step": 97880 }, { "epoch": 2.7660163589359628, "grad_norm": 2.6711082458496094, "learning_rate": 1.6544895579848619e-06, "loss": 0.8189481735229492, "step": 97900 }, { "epoch": 2.7665814344441775, "grad_norm": 2.8610332012176514, "learning_rate": 1.6465534868336186e-06, "loss": 0.8218358039855957, "step": 97920 }, { "epoch": 2.7671465099523926, "grad_norm": 2.3924477100372314, "learning_rate": 1.6386361762465385e-06, "loss": 0.8270375251770019, "step": 97940 }, { "epoch": 2.7677115854606074, "grad_norm": 4.328883171081543, "learning_rate": 1.6307376292954425e-06, "loss": 0.733357286453247, "step": 97960 }, { "epoch": 2.768276660968822, "grad_norm": 3.658759355545044, "learning_rate": 1.6228578490448676e-06, "loss": 0.6722662448883057, "step": 97980 }, { "epoch": 2.768841736477037, "grad_norm": 3.909989595413208, "learning_rate": 1.6149968385520797e-06, "loss": 0.7331840991973877, "step": 98000 }, { "epoch": 2.7694068119852515, "grad_norm": 4.316508769989014, "learning_rate": 1.6071546008670614e-06, "loss": 0.7668466567993164, "step": 98020 }, { "epoch": 2.7699718874934662, "grad_norm": 5.080063819885254, "learning_rate": 1.5993311390325117e-06, "loss": 0.7270821094512939, "step": 98040 }, { "epoch": 2.770536963001681, "grad_norm": 3.0122406482696533, "learning_rate": 1.591526456083825e-06, "loss": 0.7008641242980957, "step": 98060 }, { "epoch": 2.7711020385098957, "grad_norm": 3.7999517917633057, "learning_rate": 1.5837405550491402e-06, "loss": 0.7478127956390381, "step": 98080 }, { "epoch": 2.771667114018111, "grad_norm": 3.7459897994995117, "learning_rate": 1.5759734389492853e-06, "loss": 0.7363200187683105, "step": 98100 }, { "epoch": 2.7722321895263256, "grad_norm": 5.306386470794678, "learning_rate": 1.568225110797822e-06, "loss": 0.6657612800598145, "step": 98120 }, { "epoch": 2.7727972650345403, "grad_norm": 4.600188255310059, "learning_rate": 1.5604955736009896e-06, "loss": 0.8214378356933594, "step": 98140 }, { "epoch": 2.773362340542755, "grad_norm": 3.662838935852051, "learning_rate": 1.5527848303577785e-06, "loss": 0.6887694835662842, "step": 98160 }, { "epoch": 2.7739274160509697, "grad_norm": 4.0455451011657715, "learning_rate": 1.545092884059851e-06, "loss": 0.6830094337463379, "step": 98180 }, { "epoch": 2.774492491559185, "grad_norm": 3.8780624866485596, "learning_rate": 1.5374197376915978e-06, "loss": 0.807585334777832, "step": 98200 }, { "epoch": 2.7750575670673996, "grad_norm": 3.974574565887451, "learning_rate": 1.5297653942301037e-06, "loss": 0.7836899757385254, "step": 98220 }, { "epoch": 2.7756226425756143, "grad_norm": 3.2406816482543945, "learning_rate": 1.5221298566451713e-06, "loss": 0.7976213932037354, "step": 98240 }, { "epoch": 2.776187718083829, "grad_norm": 4.284224987030029, "learning_rate": 1.5145131278992919e-06, "loss": 0.793891716003418, "step": 98260 }, { "epoch": 2.7767527935920437, "grad_norm": 4.7231621742248535, "learning_rate": 1.5069152109476736e-06, "loss": 0.7535593509674072, "step": 98280 }, { "epoch": 2.7773178691002585, "grad_norm": 5.9495062828063965, "learning_rate": 1.4993361087382029e-06, "loss": 0.7265000343322754, "step": 98300 }, { "epoch": 2.777882944608473, "grad_norm": 3.0820472240448, "learning_rate": 1.4917758242114887e-06, "loss": 0.7827130794525147, "step": 98320 }, { "epoch": 2.778448020116688, "grad_norm": 3.792088747024536, "learning_rate": 1.48423436030084e-06, "loss": 0.6986668586730957, "step": 98340 }, { "epoch": 2.7790130956249026, "grad_norm": 4.414890289306641, "learning_rate": 1.4767117199322555e-06, "loss": 0.7906436920166016, "step": 98360 }, { "epoch": 2.779578171133118, "grad_norm": 3.9313900470733643, "learning_rate": 1.469207906024417e-06, "loss": 0.7171494960784912, "step": 98380 }, { "epoch": 2.7801432466413325, "grad_norm": 4.580255508422852, "learning_rate": 1.461722921488723e-06, "loss": 0.761480712890625, "step": 98400 }, { "epoch": 2.780708322149547, "grad_norm": 4.885865688323975, "learning_rate": 1.454256769229262e-06, "loss": 0.7857946872711181, "step": 98420 }, { "epoch": 2.781273397657762, "grad_norm": 4.879461288452148, "learning_rate": 1.446809452142811e-06, "loss": 0.6960564136505127, "step": 98440 }, { "epoch": 2.7818384731659767, "grad_norm": 5.403075218200684, "learning_rate": 1.4393809731188424e-06, "loss": 0.7553040504455566, "step": 98460 }, { "epoch": 2.782403548674192, "grad_norm": 2.7006447315216064, "learning_rate": 1.431971335039506e-06, "loss": 0.7325033664703369, "step": 98480 }, { "epoch": 2.7829686241824065, "grad_norm": 3.8653743267059326, "learning_rate": 1.4245805407796631e-06, "loss": 0.6970623970031739, "step": 98500 }, { "epoch": 2.7835336996906213, "grad_norm": 5.663297176361084, "learning_rate": 1.417208593206859e-06, "loss": 0.7874276161193847, "step": 98520 }, { "epoch": 2.784098775198836, "grad_norm": 4.088474273681641, "learning_rate": 1.409855495181317e-06, "loss": 0.7054286479949952, "step": 98540 }, { "epoch": 2.7846638507070507, "grad_norm": 3.7981619834899902, "learning_rate": 1.4025212495559437e-06, "loss": 0.755116319656372, "step": 98560 }, { "epoch": 2.7852289262152654, "grad_norm": 3.788660764694214, "learning_rate": 1.3952058591763518e-06, "loss": 0.7374494075775146, "step": 98580 }, { "epoch": 2.78579400172348, "grad_norm": 3.405954360961914, "learning_rate": 1.3879093268808262e-06, "loss": 0.7046016693115235, "step": 98600 }, { "epoch": 2.786359077231695, "grad_norm": 3.3626484870910645, "learning_rate": 1.3806316555003251e-06, "loss": 0.6967050075531006, "step": 98620 }, { "epoch": 2.78692415273991, "grad_norm": 4.068420886993408, "learning_rate": 1.3733728478585006e-06, "loss": 0.7480377674102783, "step": 98640 }, { "epoch": 2.7874892282481247, "grad_norm": 3.999460220336914, "learning_rate": 1.3661329067716888e-06, "loss": 0.718564224243164, "step": 98660 }, { "epoch": 2.7880543037563394, "grad_norm": 3.6973297595977783, "learning_rate": 1.358911835048904e-06, "loss": 0.7490324020385742, "step": 98680 }, { "epoch": 2.788619379264554, "grad_norm": 3.490919828414917, "learning_rate": 1.3517096354918325e-06, "loss": 0.8258583068847656, "step": 98700 }, { "epoch": 2.789184454772769, "grad_norm": 3.451266050338745, "learning_rate": 1.3445263108948392e-06, "loss": 0.7880918979644775, "step": 98720 }, { "epoch": 2.789749530280984, "grad_norm": 4.461663246154785, "learning_rate": 1.3373618640449726e-06, "loss": 0.7959236621856689, "step": 98740 }, { "epoch": 2.7903146057891988, "grad_norm": 3.044480323791504, "learning_rate": 1.3302162977219534e-06, "loss": 0.7420346736907959, "step": 98760 }, { "epoch": 2.7908796812974135, "grad_norm": 3.503983974456787, "learning_rate": 1.3230896146981753e-06, "loss": 0.7422689437866211, "step": 98780 }, { "epoch": 2.791444756805628, "grad_norm": 5.429333686828613, "learning_rate": 1.315981817738704e-06, "loss": 0.7532001495361328, "step": 98800 }, { "epoch": 2.792009832313843, "grad_norm": 3.1430840492248535, "learning_rate": 1.3088929096012836e-06, "loss": 0.712765884399414, "step": 98820 }, { "epoch": 2.7925749078220576, "grad_norm": 3.5192253589630127, "learning_rate": 1.3018228930363308e-06, "loss": 0.7333662033081054, "step": 98840 }, { "epoch": 2.7931399833302724, "grad_norm": 4.610355377197266, "learning_rate": 1.2947717707869177e-06, "loss": 0.6672893047332764, "step": 98860 }, { "epoch": 2.793705058838487, "grad_norm": 2.609875202178955, "learning_rate": 1.2877395455888064e-06, "loss": 0.699915599822998, "step": 98880 }, { "epoch": 2.7942701343467022, "grad_norm": 3.7321560382843018, "learning_rate": 1.2807262201704085e-06, "loss": 0.7470156192779541, "step": 98900 }, { "epoch": 2.794835209854917, "grad_norm": 3.0475893020629883, "learning_rate": 1.2737317972528252e-06, "loss": 0.7597740650177002, "step": 98920 }, { "epoch": 2.7954002853631317, "grad_norm": 3.162080764770508, "learning_rate": 1.266756279549791e-06, "loss": 0.737626600265503, "step": 98940 }, { "epoch": 2.7959653608713464, "grad_norm": 3.642310380935669, "learning_rate": 1.2597996697677305e-06, "loss": 0.7922741889953613, "step": 98960 }, { "epoch": 2.796530436379561, "grad_norm": 2.929814577102661, "learning_rate": 1.2528619706057342e-06, "loss": 0.705705213546753, "step": 98980 }, { "epoch": 2.7970955118877763, "grad_norm": 3.197681188583374, "learning_rate": 1.245943184755538e-06, "loss": 0.7200329303741455, "step": 99000 }, { "epoch": 2.797660587395991, "grad_norm": 2.705842971801758, "learning_rate": 1.2390433149015557e-06, "loss": 0.7872982978820801, "step": 99020 }, { "epoch": 2.7982256629042057, "grad_norm": 4.642360687255859, "learning_rate": 1.2321623637208513e-06, "loss": 0.7696716785430908, "step": 99040 }, { "epoch": 2.7987907384124204, "grad_norm": 3.5174715518951416, "learning_rate": 1.2253003338831504e-06, "loss": 0.748165225982666, "step": 99060 }, { "epoch": 2.799355813920635, "grad_norm": 2.401857614517212, "learning_rate": 1.2184572280508399e-06, "loss": 0.751579475402832, "step": 99080 }, { "epoch": 2.79992088942885, "grad_norm": 4.12299919128418, "learning_rate": 1.2116330488789684e-06, "loss": 0.6980317592620849, "step": 99100 }, { "epoch": 2.8004859649370646, "grad_norm": 3.491720199584961, "learning_rate": 1.2048277990152346e-06, "loss": 0.8187700271606445, "step": 99120 }, { "epoch": 2.8010510404452793, "grad_norm": 2.469975471496582, "learning_rate": 1.1980414810999874e-06, "loss": 0.7357584476470947, "step": 99140 }, { "epoch": 2.801616115953494, "grad_norm": 4.333127975463867, "learning_rate": 1.1912740977662483e-06, "loss": 0.7578778743743897, "step": 99160 }, { "epoch": 2.802181191461709, "grad_norm": 4.449081897735596, "learning_rate": 1.1845256516396785e-06, "loss": 0.7650796890258789, "step": 99180 }, { "epoch": 2.802746266969924, "grad_norm": 4.733542442321777, "learning_rate": 1.1777961453385943e-06, "loss": 0.7823302268981933, "step": 99200 }, { "epoch": 2.8033113424781386, "grad_norm": 4.428135871887207, "learning_rate": 1.1710855814739575e-06, "loss": 0.7948253154754639, "step": 99220 }, { "epoch": 2.8038764179863533, "grad_norm": 3.7224910259246826, "learning_rate": 1.1643939626494017e-06, "loss": 0.739929485321045, "step": 99240 }, { "epoch": 2.804441493494568, "grad_norm": 3.531261920928955, "learning_rate": 1.1577212914611834e-06, "loss": 0.7696402549743653, "step": 99260 }, { "epoch": 2.8050065690027832, "grad_norm": 2.4533519744873047, "learning_rate": 1.1510675704982267e-06, "loss": 0.7351463794708252, "step": 99280 }, { "epoch": 2.805571644510998, "grad_norm": 2.6710453033447266, "learning_rate": 1.144432802342088e-06, "loss": 0.7802803039550781, "step": 99300 }, { "epoch": 2.8061367200192127, "grad_norm": 3.608546257019043, "learning_rate": 1.1378169895669865e-06, "loss": 0.6995814323425293, "step": 99320 }, { "epoch": 2.8067017955274274, "grad_norm": 2.7031240463256836, "learning_rate": 1.13122013473978e-06, "loss": 0.7887616634368897, "step": 99340 }, { "epoch": 2.807266871035642, "grad_norm": 3.053493022918701, "learning_rate": 1.1246422404199707e-06, "loss": 0.7453176021575928, "step": 99360 }, { "epoch": 2.807831946543857, "grad_norm": 3.660271644592285, "learning_rate": 1.1180833091596954e-06, "loss": 0.7772398948669433, "step": 99380 }, { "epoch": 2.8083970220520715, "grad_norm": 4.802231788635254, "learning_rate": 1.1115433435037458e-06, "loss": 0.7407779693603516, "step": 99400 }, { "epoch": 2.8089620975602863, "grad_norm": 3.2945613861083984, "learning_rate": 1.1050223459895592e-06, "loss": 0.745064640045166, "step": 99420 }, { "epoch": 2.8095271730685014, "grad_norm": 2.5300774574279785, "learning_rate": 1.098520319147195e-06, "loss": 0.7601948261260987, "step": 99440 }, { "epoch": 2.810092248576716, "grad_norm": 5.207333564758301, "learning_rate": 1.0920372654993626e-06, "loss": 0.6926486015319824, "step": 99460 }, { "epoch": 2.810657324084931, "grad_norm": 3.295799493789673, "learning_rate": 1.0855731875614116e-06, "loss": 0.7811919212341308, "step": 99480 }, { "epoch": 2.8112223995931456, "grad_norm": 3.872915267944336, "learning_rate": 1.0791280878413357e-06, "loss": 0.790940237045288, "step": 99500 }, { "epoch": 2.8117874751013603, "grad_norm": 4.848781108856201, "learning_rate": 1.072701968839751e-06, "loss": 0.7967469215393066, "step": 99520 }, { "epoch": 2.8123525506095755, "grad_norm": 4.357503414154053, "learning_rate": 1.0662948330499079e-06, "loss": 0.7524806022644043, "step": 99540 }, { "epoch": 2.81291762611779, "grad_norm": 3.5884549617767334, "learning_rate": 1.0599066829577064e-06, "loss": 0.7748937129974365, "step": 99560 }, { "epoch": 2.813482701626005, "grad_norm": 4.109784126281738, "learning_rate": 1.053537521041681e-06, "loss": 0.6839848041534424, "step": 99580 }, { "epoch": 2.8140477771342196, "grad_norm": 4.950179100036621, "learning_rate": 1.0471873497729767e-06, "loss": 0.7306643962860108, "step": 99600 }, { "epoch": 2.8146128526424343, "grad_norm": 3.160403251647949, "learning_rate": 1.0408561716153898e-06, "loss": 0.7365239143371582, "step": 99620 }, { "epoch": 2.815177928150649, "grad_norm": 3.8190605640411377, "learning_rate": 1.0345439890253439e-06, "loss": 0.7344482421875, "step": 99640 }, { "epoch": 2.8157430036588638, "grad_norm": 3.611771821975708, "learning_rate": 1.0282508044518968e-06, "loss": 0.7862628936767578, "step": 99660 }, { "epoch": 2.8163080791670785, "grad_norm": 3.0356903076171875, "learning_rate": 1.0219766203367176e-06, "loss": 0.7151691436767578, "step": 99680 }, { "epoch": 2.8168731546752936, "grad_norm": 3.9838459491729736, "learning_rate": 1.0157214391141256e-06, "loss": 0.7620373725891113, "step": 99700 }, { "epoch": 2.8174382301835084, "grad_norm": 3.146070957183838, "learning_rate": 1.0094852632110519e-06, "loss": 0.7394536972045899, "step": 99720 }, { "epoch": 2.818003305691723, "grad_norm": 3.5273969173431396, "learning_rate": 1.0032680950470552e-06, "loss": 0.7420840740203858, "step": 99740 }, { "epoch": 2.818568381199938, "grad_norm": 5.159999370574951, "learning_rate": 9.97069937034334e-07, "loss": 0.7756667137145996, "step": 99760 }, { "epoch": 2.8191334567081525, "grad_norm": 3.6034224033355713, "learning_rate": 9.908907915776922e-07, "loss": 0.7331911087036133, "step": 99780 }, { "epoch": 2.8196985322163677, "grad_norm": 3.4036731719970703, "learning_rate": 9.847306610745622e-07, "loss": 0.7267039299011231, "step": 99800 }, { "epoch": 2.8202636077245824, "grad_norm": 2.9208600521087646, "learning_rate": 9.785895479150043e-07, "loss": 0.7599226474761963, "step": 99820 }, { "epoch": 2.820828683232797, "grad_norm": 3.30224347114563, "learning_rate": 9.72467454481707e-07, "loss": 0.6257846355438232, "step": 99840 }, { "epoch": 2.821393758741012, "grad_norm": 3.5153582096099854, "learning_rate": 9.663643831499592e-07, "loss": 0.7551005840301513, "step": 99860 }, { "epoch": 2.8219588342492266, "grad_norm": 3.0964272022247314, "learning_rate": 9.602803362876778e-07, "loss": 0.7222594261169434, "step": 99880 }, { "epoch": 2.8225239097574413, "grad_norm": 3.1057307720184326, "learning_rate": 9.54215316255408e-07, "loss": 0.7214175224304199, "step": 99900 }, { "epoch": 2.823088985265656, "grad_norm": 3.7412590980529785, "learning_rate": 9.481693254063117e-07, "loss": 0.720116662979126, "step": 99920 }, { "epoch": 2.8236540607738707, "grad_norm": 4.524574279785156, "learning_rate": 9.421423660861461e-07, "loss": 0.6746103763580322, "step": 99940 }, { "epoch": 2.8242191362820854, "grad_norm": 3.5923869609832764, "learning_rate": 9.361344406333073e-07, "loss": 0.7780489444732666, "step": 99960 }, { "epoch": 2.8247842117903006, "grad_norm": 2.6429226398468018, "learning_rate": 9.301455513787971e-07, "loss": 0.7171051025390625, "step": 99980 }, { "epoch": 2.8253492872985153, "grad_norm": 2.670799970626831, "learning_rate": 9.241757006462459e-07, "loss": 0.7869481563568115, "step": 100000 }, { "epoch": 2.82591436280673, "grad_norm": 3.262821912765503, "learning_rate": 9.182248907518676e-07, "loss": 0.7721604347229004, "step": 100020 }, { "epoch": 2.8264794383149447, "grad_norm": 3.671290636062622, "learning_rate": 9.122931240045207e-07, "loss": 0.678067970275879, "step": 100040 }, { "epoch": 2.8270445138231595, "grad_norm": 3.1285665035247803, "learning_rate": 9.063804027056422e-07, "loss": 0.7673723220825195, "step": 100060 }, { "epoch": 2.8276095893313746, "grad_norm": 4.450141429901123, "learning_rate": 9.004867291493191e-07, "loss": 0.72957763671875, "step": 100080 }, { "epoch": 2.8281746648395893, "grad_norm": 3.316572904586792, "learning_rate": 8.946121056222168e-07, "loss": 0.812220287322998, "step": 100100 }, { "epoch": 2.828739740347804, "grad_norm": 3.0829880237579346, "learning_rate": 8.88756534403612e-07, "loss": 0.7071527957916259, "step": 100120 }, { "epoch": 2.829304815856019, "grad_norm": 3.3772170543670654, "learning_rate": 8.829200177654096e-07, "loss": 0.7874905586242675, "step": 100140 }, { "epoch": 2.8298698913642335, "grad_norm": 2.960954189300537, "learning_rate": 8.771025579721037e-07, "loss": 0.695820951461792, "step": 100160 }, { "epoch": 2.830434966872448, "grad_norm": 3.857304096221924, "learning_rate": 8.713041572808001e-07, "loss": 0.7558726310729981, "step": 100180 }, { "epoch": 2.831000042380663, "grad_norm": 4.06553840637207, "learning_rate": 8.655248179412045e-07, "loss": 0.7357994079589844, "step": 100200 }, { "epoch": 2.8315651178888777, "grad_norm": 3.163125514984131, "learning_rate": 8.597645421956402e-07, "loss": 0.8057103157043457, "step": 100220 }, { "epoch": 2.832130193397093, "grad_norm": 2.868053674697876, "learning_rate": 8.540233322790193e-07, "loss": 0.7318521976470947, "step": 100240 }, { "epoch": 2.8326952689053075, "grad_norm": 3.9247822761535645, "learning_rate": 8.483011904188709e-07, "loss": 0.7476538181304931, "step": 100260 }, { "epoch": 2.8332603444135223, "grad_norm": 4.276839256286621, "learning_rate": 8.425981188353138e-07, "loss": 0.7375657081604003, "step": 100280 }, { "epoch": 2.833825419921737, "grad_norm": 2.6172709465026855, "learning_rate": 8.369141197410669e-07, "loss": 0.7504080295562744, "step": 100300 }, { "epoch": 2.8343904954299517, "grad_norm": 4.508641719818115, "learning_rate": 8.312491953414603e-07, "loss": 0.7316061496734619, "step": 100320 }, { "epoch": 2.834955570938167, "grad_norm": 4.803271293640137, "learning_rate": 8.256033478344249e-07, "loss": 0.6846398830413818, "step": 100340 }, { "epoch": 2.8355206464463816, "grad_norm": 3.291306734085083, "learning_rate": 8.199765794104697e-07, "loss": 0.7210005283355713, "step": 100360 }, { "epoch": 2.8360857219545963, "grad_norm": 4.656992435455322, "learning_rate": 8.143688922527148e-07, "loss": 0.7343875885009765, "step": 100380 }, { "epoch": 2.836650797462811, "grad_norm": 4.566182613372803, "learning_rate": 8.087802885368867e-07, "loss": 0.7440684318542481, "step": 100400 }, { "epoch": 2.8372158729710257, "grad_norm": 4.315635681152344, "learning_rate": 8.032107704312897e-07, "loss": 0.784705114364624, "step": 100420 }, { "epoch": 2.8377809484792405, "grad_norm": 4.301319122314453, "learning_rate": 7.976603400968341e-07, "loss": 0.7619469165802002, "step": 100440 }, { "epoch": 2.838346023987455, "grad_norm": 3.882087469100952, "learning_rate": 7.921289996870141e-07, "loss": 0.6895913124084473, "step": 100460 }, { "epoch": 2.83891109949567, "grad_norm": 4.251160144805908, "learning_rate": 7.86616751347935e-07, "loss": 0.79532790184021, "step": 100480 }, { "epoch": 2.839476175003885, "grad_norm": 3.5381150245666504, "learning_rate": 7.811235972182751e-07, "loss": 0.7140614032745362, "step": 100500 }, { "epoch": 2.8400412505120998, "grad_norm": 4.8183488845825195, "learning_rate": 7.756495394293184e-07, "loss": 0.768342924118042, "step": 100520 }, { "epoch": 2.8406063260203145, "grad_norm": 3.310994863510132, "learning_rate": 7.701945801049326e-07, "loss": 0.8208147048950195, "step": 100540 }, { "epoch": 2.841171401528529, "grad_norm": 2.8821849822998047, "learning_rate": 7.647587213615748e-07, "loss": 0.8311963081359863, "step": 100560 }, { "epoch": 2.841736477036744, "grad_norm": 3.086921215057373, "learning_rate": 7.593419653082968e-07, "loss": 0.7647129535675049, "step": 100580 }, { "epoch": 2.842301552544959, "grad_norm": 3.124072790145874, "learning_rate": 7.539443140467395e-07, "loss": 0.7897443294525146, "step": 100600 }, { "epoch": 2.842866628053174, "grad_norm": 4.175358295440674, "learning_rate": 7.485657696711168e-07, "loss": 0.7349327564239502, "step": 100620 }, { "epoch": 2.8434317035613885, "grad_norm": 3.25777006149292, "learning_rate": 7.432063342682483e-07, "loss": 0.802736759185791, "step": 100640 }, { "epoch": 2.8439967790696032, "grad_norm": 3.9967660903930664, "learning_rate": 7.378660099175316e-07, "loss": 0.7713562488555908, "step": 100660 }, { "epoch": 2.844561854577818, "grad_norm": 3.4569919109344482, "learning_rate": 7.325447986909428e-07, "loss": 0.687210988998413, "step": 100680 }, { "epoch": 2.8451269300860327, "grad_norm": 5.176520347595215, "learning_rate": 7.272427026530582e-07, "loss": 0.7073773860931396, "step": 100700 }, { "epoch": 2.8456920055942474, "grad_norm": 4.663492202758789, "learning_rate": 7.21959723861021e-07, "loss": 0.7068897724151612, "step": 100720 }, { "epoch": 2.846257081102462, "grad_norm": 6.0441460609436035, "learning_rate": 7.166958643645693e-07, "loss": 0.706155252456665, "step": 100740 }, { "epoch": 2.846822156610677, "grad_norm": 4.860780715942383, "learning_rate": 7.114511262060141e-07, "loss": 0.7427144527435303, "step": 100760 }, { "epoch": 2.847387232118892, "grad_norm": 3.967763662338257, "learning_rate": 7.062255114202498e-07, "loss": 0.7797159194946289, "step": 100780 }, { "epoch": 2.8479523076271067, "grad_norm": 3.434558868408203, "learning_rate": 7.010190220347601e-07, "loss": 0.8487390518188477, "step": 100800 }, { "epoch": 2.8485173831353214, "grad_norm": 4.966612815856934, "learning_rate": 6.958316600695958e-07, "loss": 0.7830751895904541, "step": 100820 }, { "epoch": 2.849082458643536, "grad_norm": 3.8520684242248535, "learning_rate": 6.906634275373969e-07, "loss": 0.8189821243286133, "step": 100840 }, { "epoch": 2.849647534151751, "grad_norm": 3.0231242179870605, "learning_rate": 6.855143264433705e-07, "loss": 0.713496208190918, "step": 100860 }, { "epoch": 2.850212609659966, "grad_norm": 3.8239030838012695, "learning_rate": 6.803843587853076e-07, "loss": 0.7627095699310302, "step": 100880 }, { "epoch": 2.8507776851681808, "grad_norm": 4.132513523101807, "learning_rate": 6.75273526553577e-07, "loss": 0.6769662857055664, "step": 100900 }, { "epoch": 2.8513427606763955, "grad_norm": 2.809107542037964, "learning_rate": 6.701818317311204e-07, "loss": 0.7222545623779297, "step": 100920 }, { "epoch": 2.85190783618461, "grad_norm": 2.2615725994110107, "learning_rate": 6.651092762934519e-07, "loss": 0.7662099838256836, "step": 100940 }, { "epoch": 2.852472911692825, "grad_norm": 3.2621572017669678, "learning_rate": 6.600558622086694e-07, "loss": 0.7402661323547364, "step": 100960 }, { "epoch": 2.8530379872010396, "grad_norm": 3.941507339477539, "learning_rate": 6.55021591437438e-07, "loss": 0.7644114017486572, "step": 100980 }, { "epoch": 2.8536030627092543, "grad_norm": 3.681976079940796, "learning_rate": 6.500064659329841e-07, "loss": 0.7183994293212891, "step": 101000 }, { "epoch": 2.854168138217469, "grad_norm": 7.234644412994385, "learning_rate": 6.450104876411345e-07, "loss": 0.7274422168731689, "step": 101020 }, { "epoch": 2.8547332137256842, "grad_norm": 3.4646244049072266, "learning_rate": 6.400336585002497e-07, "loss": 0.6868879318237304, "step": 101040 }, { "epoch": 2.855298289233899, "grad_norm": 4.078085422515869, "learning_rate": 6.350759804412965e-07, "loss": 0.7628633499145507, "step": 101060 }, { "epoch": 2.8558633647421137, "grad_norm": 4.359576225280762, "learning_rate": 6.301374553877859e-07, "loss": 0.7075144290924072, "step": 101080 }, { "epoch": 2.8564284402503284, "grad_norm": 3.6082844734191895, "learning_rate": 6.252180852558076e-07, "loss": 0.735913610458374, "step": 101100 }, { "epoch": 2.856993515758543, "grad_norm": 3.8323514461517334, "learning_rate": 6.203178719540237e-07, "loss": 0.7936047077178955, "step": 101120 }, { "epoch": 2.8575585912667583, "grad_norm": 2.683225393295288, "learning_rate": 6.154368173836578e-07, "loss": 0.7346923351287842, "step": 101140 }, { "epoch": 2.858123666774973, "grad_norm": 5.919692039489746, "learning_rate": 6.105749234385005e-07, "loss": 0.7182632923126221, "step": 101160 }, { "epoch": 2.8586887422831877, "grad_norm": 4.321704864501953, "learning_rate": 6.057321920049097e-07, "loss": 0.7298765182495117, "step": 101180 }, { "epoch": 2.8592538177914024, "grad_norm": 4.169435501098633, "learning_rate": 6.00908624961799e-07, "loss": 0.723655366897583, "step": 101200 }, { "epoch": 2.859818893299617, "grad_norm": 3.623765707015991, "learning_rate": 5.961042241806714e-07, "loss": 0.7711855888366699, "step": 101220 }, { "epoch": 2.860383968807832, "grad_norm": 4.77227258682251, "learning_rate": 5.913189915255634e-07, "loss": 0.7165985584259034, "step": 101240 }, { "epoch": 2.8609490443160466, "grad_norm": 3.431225299835205, "learning_rate": 5.865529288530957e-07, "loss": 0.8580479621887207, "step": 101260 }, { "epoch": 2.8615141198242613, "grad_norm": 3.8277807235717773, "learning_rate": 5.818060380124446e-07, "loss": 0.7093324184417724, "step": 101280 }, { "epoch": 2.8620791953324765, "grad_norm": 3.149636745452881, "learning_rate": 5.770783208453367e-07, "loss": 0.7687753200531006, "step": 101300 }, { "epoch": 2.862644270840691, "grad_norm": 3.6041224002838135, "learning_rate": 5.723697791860882e-07, "loss": 0.8803590774536133, "step": 101320 }, { "epoch": 2.863209346348906, "grad_norm": 3.133467435836792, "learning_rate": 5.676804148615488e-07, "loss": 0.8256299018859863, "step": 101340 }, { "epoch": 2.8637744218571206, "grad_norm": 3.4737324714660645, "learning_rate": 5.6301022969113e-07, "loss": 0.7184693813323975, "step": 101360 }, { "epoch": 2.8643394973653353, "grad_norm": 3.860900640487671, "learning_rate": 5.583592254868153e-07, "loss": 0.7170694828033447, "step": 101380 }, { "epoch": 2.8649045728735505, "grad_norm": 4.355077743530273, "learning_rate": 5.537274040531393e-07, "loss": 0.6846706390380859, "step": 101400 }, { "epoch": 2.865469648381765, "grad_norm": 2.847109317779541, "learning_rate": 5.491147671871921e-07, "loss": 0.783647871017456, "step": 101420 }, { "epoch": 2.86603472388998, "grad_norm": 4.103838920593262, "learning_rate": 5.445213166786256e-07, "loss": 0.7889167785644531, "step": 101440 }, { "epoch": 2.8665997993981946, "grad_norm": 4.900249004364014, "learning_rate": 5.399470543096308e-07, "loss": 0.7522364616394043, "step": 101460 }, { "epoch": 2.8671648749064094, "grad_norm": 4.471371173858643, "learning_rate": 5.35391981854988e-07, "loss": 0.7393785953521729, "step": 101480 }, { "epoch": 2.867729950414624, "grad_norm": 3.255082607269287, "learning_rate": 5.308561010819946e-07, "loss": 0.7695613861083984, "step": 101500 }, { "epoch": 2.868295025922839, "grad_norm": 4.349358558654785, "learning_rate": 5.263394137505317e-07, "loss": 0.7309256076812745, "step": 101520 }, { "epoch": 2.8688601014310535, "grad_norm": 3.864137887954712, "learning_rate": 5.218419216130033e-07, "loss": 0.7723464488983154, "step": 101540 }, { "epoch": 2.8694251769392682, "grad_norm": 3.7728707790374756, "learning_rate": 5.173636264144022e-07, "loss": 0.7624324798583985, "step": 101560 }, { "epoch": 2.8699902524474834, "grad_norm": 4.420743942260742, "learning_rate": 5.129045298922386e-07, "loss": 0.784086275100708, "step": 101580 }, { "epoch": 2.870555327955698, "grad_norm": 2.9645256996154785, "learning_rate": 5.084646337765953e-07, "loss": 0.7647421360015869, "step": 101600 }, { "epoch": 2.871120403463913, "grad_norm": 2.7086052894592285, "learning_rate": 5.040439397900997e-07, "loss": 0.699286413192749, "step": 101620 }, { "epoch": 2.8716854789721276, "grad_norm": 4.431682586669922, "learning_rate": 4.996424496479357e-07, "loss": 0.7257440090179443, "step": 101640 }, { "epoch": 2.8722505544803423, "grad_norm": 3.9335522651672363, "learning_rate": 4.952601650578148e-07, "loss": 0.7477519989013672, "step": 101660 }, { "epoch": 2.8728156299885574, "grad_norm": 5.329588413238525, "learning_rate": 4.908970877200214e-07, "loss": 0.743050479888916, "step": 101680 }, { "epoch": 2.873380705496772, "grad_norm": 3.9414846897125244, "learning_rate": 4.865532193273736e-07, "loss": 0.7468695163726806, "step": 101700 }, { "epoch": 2.873945781004987, "grad_norm": 3.3608243465423584, "learning_rate": 4.822285615652456e-07, "loss": 0.7868297100067139, "step": 101720 }, { "epoch": 2.8745108565132016, "grad_norm": 3.290574073791504, "learning_rate": 4.779231161115505e-07, "loss": 0.8291897773742676, "step": 101740 }, { "epoch": 2.8750759320214163, "grad_norm": 2.559358835220337, "learning_rate": 4.736368846367467e-07, "loss": 0.7367759227752686, "step": 101760 }, { "epoch": 2.875641007529631, "grad_norm": 3.15582013130188, "learning_rate": 4.693698688038428e-07, "loss": 0.7790046215057373, "step": 101780 }, { "epoch": 2.8762060830378458, "grad_norm": 3.498284101486206, "learning_rate": 4.651220702683978e-07, "loss": 0.703178071975708, "step": 101800 }, { "epoch": 2.8767711585460605, "grad_norm": 4.18316650390625, "learning_rate": 4.608934906784934e-07, "loss": 0.7916061878204346, "step": 101820 }, { "epoch": 2.8773362340542756, "grad_norm": 4.106255531311035, "learning_rate": 4.5668413167478386e-07, "loss": 0.7231284141540527, "step": 101840 }, { "epoch": 2.8779013095624904, "grad_norm": 4.07065486907959, "learning_rate": 4.52493994890435e-07, "loss": 0.7235467910766602, "step": 101860 }, { "epoch": 2.878466385070705, "grad_norm": 3.9207253456115723, "learning_rate": 4.483230819511852e-07, "loss": 0.7938002109527588, "step": 101880 }, { "epoch": 2.87903146057892, "grad_norm": 5.955325603485107, "learning_rate": 4.441713944752901e-07, "loss": 0.7861047744750976, "step": 101900 }, { "epoch": 2.8795965360871345, "grad_norm": 2.263801097869873, "learning_rate": 4.4003893407355556e-07, "loss": 0.7228745460510254, "step": 101920 }, { "epoch": 2.8801616115953497, "grad_norm": 2.6097841262817383, "learning_rate": 4.3592570234932686e-07, "loss": 0.7581802368164062, "step": 101940 }, { "epoch": 2.8807266871035644, "grad_norm": 3.056119680404663, "learning_rate": 4.31831700898494e-07, "loss": 0.7433155536651611, "step": 101960 }, { "epoch": 2.881291762611779, "grad_norm": 3.350517511367798, "learning_rate": 4.277569313094809e-07, "loss": 0.7273513317108155, "step": 101980 }, { "epoch": 2.881856838119994, "grad_norm": 3.7823541164398193, "learning_rate": 4.2370139516324516e-07, "loss": 0.7480232238769531, "step": 102000 }, { "epoch": 2.8824219136282085, "grad_norm": 3.2922914028167725, "learning_rate": 4.196650940332891e-07, "loss": 0.8075333595275879, "step": 102020 }, { "epoch": 2.8829869891364233, "grad_norm": 3.4841084480285645, "learning_rate": 4.156480294856435e-07, "loss": 0.7925189971923828, "step": 102040 }, { "epoch": 2.883552064644638, "grad_norm": 4.263974666595459, "learning_rate": 4.116502030788949e-07, "loss": 0.7857651233673095, "step": 102060 }, { "epoch": 2.8841171401528527, "grad_norm": 3.229341983795166, "learning_rate": 4.0767161636414696e-07, "loss": 0.7698472499847412, "step": 102080 }, { "epoch": 2.884682215661068, "grad_norm": 4.472731590270996, "learning_rate": 4.037122708850372e-07, "loss": 0.7688792228698731, "step": 102100 }, { "epoch": 2.8852472911692826, "grad_norm": 2.7309110164642334, "learning_rate": 3.997721681777533e-07, "loss": 0.7411386966705322, "step": 102120 }, { "epoch": 2.8858123666774973, "grad_norm": 4.238055229187012, "learning_rate": 3.9585130977100594e-07, "loss": 0.7052815437316895, "step": 102140 }, { "epoch": 2.886377442185712, "grad_norm": 3.7685935497283936, "learning_rate": 3.919496971860392e-07, "loss": 0.7306113243103027, "step": 102160 }, { "epoch": 2.8869425176939267, "grad_norm": 3.9458987712860107, "learning_rate": 3.880673319366368e-07, "loss": 0.7388712406158447, "step": 102180 }, { "epoch": 2.887507593202142, "grad_norm": 4.106438636779785, "learning_rate": 3.8420421552909924e-07, "loss": 0.6962684154510498, "step": 102200 }, { "epoch": 2.8880726687103566, "grad_norm": 3.9001517295837402, "learning_rate": 3.803603494622887e-07, "loss": 0.718560266494751, "step": 102220 }, { "epoch": 2.8886377442185713, "grad_norm": 3.526780605316162, "learning_rate": 3.765357352275678e-07, "loss": 0.6841948509216309, "step": 102240 }, { "epoch": 2.889202819726786, "grad_norm": 2.347264528274536, "learning_rate": 3.727303743088384e-07, "loss": 0.7066475868225097, "step": 102260 }, { "epoch": 2.8897678952350008, "grad_norm": 4.716393947601318, "learning_rate": 3.689442681825417e-07, "loss": 0.6812514305114746, "step": 102280 }, { "epoch": 2.8903329707432155, "grad_norm": 4.226380348205566, "learning_rate": 3.6517741831764153e-07, "loss": 0.7239709854125976, "step": 102300 }, { "epoch": 2.89089804625143, "grad_norm": 3.5159082412719727, "learning_rate": 3.614298261756355e-07, "loss": 0.7370168685913085, "step": 102320 }, { "epoch": 2.891463121759645, "grad_norm": 4.394326686859131, "learning_rate": 3.577014932105327e-07, "loss": 0.7057728290557861, "step": 102340 }, { "epoch": 2.8920281972678596, "grad_norm": 3.84487247467041, "learning_rate": 3.5399242086889275e-07, "loss": 0.7081706047058105, "step": 102360 }, { "epoch": 2.892593272776075, "grad_norm": 3.8888440132141113, "learning_rate": 3.5030261058978666e-07, "loss": 0.7659111022949219, "step": 102380 }, { "epoch": 2.8931583482842895, "grad_norm": 3.718935966491699, "learning_rate": 3.4663206380481925e-07, "loss": 0.730536413192749, "step": 102400 }, { "epoch": 2.8937234237925042, "grad_norm": 5.847701072692871, "learning_rate": 3.429807819381181e-07, "loss": 0.6851122856140137, "step": 102420 }, { "epoch": 2.894288499300719, "grad_norm": 4.200329303741455, "learning_rate": 3.3934876640633886e-07, "loss": 0.7898626804351807, "step": 102440 }, { "epoch": 2.8948535748089337, "grad_norm": 3.146658420562744, "learning_rate": 3.3573601861865976e-07, "loss": 0.7515853404998779, "step": 102460 }, { "epoch": 2.895418650317149, "grad_norm": 4.145699501037598, "learning_rate": 3.321425399767819e-07, "loss": 0.7174042224884033, "step": 102480 }, { "epoch": 2.8959837258253636, "grad_norm": 3.199852705001831, "learning_rate": 3.285683318749344e-07, "loss": 0.7429968357086182, "step": 102500 }, { "epoch": 2.8965488013335783, "grad_norm": 4.839597225189209, "learning_rate": 3.2501339569986357e-07, "loss": 0.7121914386749267, "step": 102520 }, { "epoch": 2.897113876841793, "grad_norm": 3.6335384845733643, "learning_rate": 3.2147773283084935e-07, "loss": 0.7862421989440918, "step": 102540 }, { "epoch": 2.8976789523500077, "grad_norm": 3.517030954360962, "learning_rate": 3.1796134463968894e-07, "loss": 0.7197807312011719, "step": 102560 }, { "epoch": 2.8982440278582224, "grad_norm": 3.6633660793304443, "learning_rate": 3.1446423249068547e-07, "loss": 0.7168002128601074, "step": 102580 }, { "epoch": 2.898809103366437, "grad_norm": 3.2551794052124023, "learning_rate": 3.1098639774069237e-07, "loss": 0.7852145195007324, "step": 102600 }, { "epoch": 2.899374178874652, "grad_norm": 5.385288715362549, "learning_rate": 3.075278417390581e-07, "loss": 0.7465030193328858, "step": 102620 }, { "epoch": 2.899939254382867, "grad_norm": 5.141129016876221, "learning_rate": 3.0408856582766485e-07, "loss": 0.7358888626098633, "step": 102640 }, { "epoch": 2.9005043298910818, "grad_norm": 3.4078431129455566, "learning_rate": 3.0066857134091187e-07, "loss": 0.6744303226470947, "step": 102660 }, { "epoch": 2.9010694053992965, "grad_norm": 2.6452112197875977, "learning_rate": 2.97267859605721e-07, "loss": 0.801241111755371, "step": 102680 }, { "epoch": 2.901634480907511, "grad_norm": 2.8442540168762207, "learning_rate": 2.9388643194151467e-07, "loss": 0.8010720252990723, "step": 102700 }, { "epoch": 2.902199556415726, "grad_norm": 2.8676810264587402, "learning_rate": 2.9052428966026004e-07, "loss": 0.7295275688171386, "step": 102720 }, { "epoch": 2.902764631923941, "grad_norm": 2.5930280685424805, "learning_rate": 2.871814340664247e-07, "loss": 0.8156121253967286, "step": 102740 }, { "epoch": 2.903329707432156, "grad_norm": 4.187572479248047, "learning_rate": 2.8385786645699354e-07, "loss": 0.7888881683349609, "step": 102760 }, { "epoch": 2.9038947829403705, "grad_norm": 3.4142842292785645, "learning_rate": 2.805535881214683e-07, "loss": 0.7697405815124512, "step": 102780 }, { "epoch": 2.9044598584485852, "grad_norm": 3.6015400886535645, "learning_rate": 2.772686003418845e-07, "loss": 0.7626083850860595, "step": 102800 }, { "epoch": 2.9050249339568, "grad_norm": 4.53941011428833, "learning_rate": 2.7400290439276165e-07, "loss": 0.7293891429901123, "step": 102820 }, { "epoch": 2.9055900094650147, "grad_norm": 4.2989349365234375, "learning_rate": 2.7075650154116393e-07, "loss": 0.748551893234253, "step": 102840 }, { "epoch": 2.9061550849732294, "grad_norm": 4.650300979614258, "learning_rate": 2.675293930466449e-07, "loss": 0.7553473472595215, "step": 102860 }, { "epoch": 2.906720160481444, "grad_norm": 4.1850199699401855, "learning_rate": 2.643215801612975e-07, "loss": 0.7925632953643799, "step": 102880 }, { "epoch": 2.9072852359896593, "grad_norm": 4.846817493438721, "learning_rate": 2.6113306412970383e-07, "loss": 0.7245571613311768, "step": 102900 }, { "epoch": 2.907850311497874, "grad_norm": 3.3648154735565186, "learning_rate": 2.5796384618898e-07, "loss": 0.8322622299194335, "step": 102920 }, { "epoch": 2.9084153870060887, "grad_norm": 2.8017866611480713, "learning_rate": 2.5481392756873667e-07, "loss": 0.7682181835174561, "step": 102940 }, { "epoch": 2.9089804625143034, "grad_norm": 4.028689384460449, "learning_rate": 2.516833094911075e-07, "loss": 0.7102112293243408, "step": 102960 }, { "epoch": 2.909545538022518, "grad_norm": 3.903052806854248, "learning_rate": 2.4857199317073753e-07, "loss": 0.8035874366760254, "step": 102980 }, { "epoch": 2.9101106135307333, "grad_norm": 4.290704727172852, "learning_rate": 2.454799798147833e-07, "loss": 0.7085844039916992, "step": 103000 }, { "epoch": 2.910675689038948, "grad_norm": 5.710406303405762, "learning_rate": 2.424072706229019e-07, "loss": 0.7689108848571777, "step": 103020 }, { "epoch": 2.9112407645471627, "grad_norm": 4.041535377502441, "learning_rate": 2.39353866787273e-07, "loss": 0.6951083660125732, "step": 103040 }, { "epoch": 2.9118058400553775, "grad_norm": 3.4254250526428223, "learning_rate": 2.3631976949257673e-07, "loss": 0.7977161407470703, "step": 103060 }, { "epoch": 2.912370915563592, "grad_norm": 4.584230899810791, "learning_rate": 2.333049799160103e-07, "loss": 0.7121208190917969, "step": 103080 }, { "epoch": 2.912935991071807, "grad_norm": 4.1561126708984375, "learning_rate": 2.3030949922727695e-07, "loss": 0.7133224487304688, "step": 103100 }, { "epoch": 2.9135010665800216, "grad_norm": 5.171423435211182, "learning_rate": 2.2733332858859146e-07, "loss": 0.7410810470581055, "step": 103120 }, { "epoch": 2.9140661420882363, "grad_norm": 3.6818833351135254, "learning_rate": 2.2437646915466348e-07, "loss": 0.7835178375244141, "step": 103140 }, { "epoch": 2.914631217596451, "grad_norm": 4.201707363128662, "learning_rate": 2.2143892207271977e-07, "loss": 0.7580132007598877, "step": 103160 }, { "epoch": 2.915196293104666, "grad_norm": 3.656492233276367, "learning_rate": 2.1852068848250417e-07, "loss": 0.7847595691680909, "step": 103180 }, { "epoch": 2.915761368612881, "grad_norm": 3.2487597465515137, "learning_rate": 2.1562176951624435e-07, "loss": 0.8322074890136719, "step": 103200 }, { "epoch": 2.9163264441210957, "grad_norm": 2.5781748294830322, "learning_rate": 2.1274216629869614e-07, "loss": 0.7593335151672364, "step": 103220 }, { "epoch": 2.9168915196293104, "grad_norm": 5.113391399383545, "learning_rate": 2.0988187994711027e-07, "loss": 0.7170499324798584, "step": 103240 }, { "epoch": 2.917456595137525, "grad_norm": 3.4651994705200195, "learning_rate": 2.0704091157123796e-07, "loss": 0.8533154487609863, "step": 103260 }, { "epoch": 2.9180216706457403, "grad_norm": 3.9025542736053467, "learning_rate": 2.0421926227334188e-07, "loss": 0.7842249393463134, "step": 103280 }, { "epoch": 2.918586746153955, "grad_norm": 8.272074699401855, "learning_rate": 2.014169331481963e-07, "loss": 0.6730296611785889, "step": 103300 }, { "epoch": 2.9191518216621697, "grad_norm": 3.301175355911255, "learning_rate": 1.9863392528307047e-07, "loss": 0.7432570934295655, "step": 103320 }, { "epoch": 2.9197168971703844, "grad_norm": 3.381725311279297, "learning_rate": 1.9587023975772834e-07, "loss": 0.6562498092651368, "step": 103340 }, { "epoch": 2.920281972678599, "grad_norm": 3.553452968597412, "learning_rate": 1.9312587764445666e-07, "loss": 0.7455522537231445, "step": 103360 }, { "epoch": 2.920847048186814, "grad_norm": 2.980252265930176, "learning_rate": 1.904008400080315e-07, "loss": 0.687023401260376, "step": 103380 }, { "epoch": 2.9214121236950286, "grad_norm": 2.652050256729126, "learning_rate": 1.8769512790573484e-07, "loss": 0.7146897792816163, "step": 103400 }, { "epoch": 2.9219771992032433, "grad_norm": 3.899747371673584, "learning_rate": 1.8500874238735476e-07, "loss": 0.7721996784210206, "step": 103420 }, { "epoch": 2.9225422747114584, "grad_norm": 4.255768775939941, "learning_rate": 1.823416844951742e-07, "loss": 0.7809062957763672, "step": 103440 }, { "epoch": 2.923107350219673, "grad_norm": 2.7436091899871826, "learning_rate": 1.7969395526397648e-07, "loss": 0.6982208728790283, "step": 103460 }, { "epoch": 2.923672425727888, "grad_norm": 3.5258891582489014, "learning_rate": 1.7706555572105655e-07, "loss": 0.7352511405944824, "step": 103480 }, { "epoch": 2.9242375012361026, "grad_norm": 3.383455514907837, "learning_rate": 1.7445648688619864e-07, "loss": 0.7575727462768554, "step": 103500 }, { "epoch": 2.9248025767443173, "grad_norm": 1.93491530418396, "learning_rate": 1.718667497716875e-07, "loss": 0.7381282806396484, "step": 103520 }, { "epoch": 2.9253676522525325, "grad_norm": 3.261298656463623, "learning_rate": 1.6929634538231376e-07, "loss": 0.7438905239105225, "step": 103540 }, { "epoch": 2.925932727760747, "grad_norm": 2.662167549133301, "learning_rate": 1.667452747153686e-07, "loss": 0.7096760749816895, "step": 103560 }, { "epoch": 2.926497803268962, "grad_norm": 4.666449069976807, "learning_rate": 1.6421353876062694e-07, "loss": 0.6885947704315185, "step": 103580 }, { "epoch": 2.9270628787771766, "grad_norm": 3.6246423721313477, "learning_rate": 1.6170113850037526e-07, "loss": 0.7225694179534912, "step": 103600 }, { "epoch": 2.9276279542853914, "grad_norm": 3.4890472888946533, "learning_rate": 1.5920807490940603e-07, "loss": 0.7425868511199951, "step": 103620 }, { "epoch": 2.928193029793606, "grad_norm": 2.6777358055114746, "learning_rate": 1.567343489549844e-07, "loss": 0.7885773181915283, "step": 103640 }, { "epoch": 2.928758105301821, "grad_norm": 5.571156978607178, "learning_rate": 1.5427996159689262e-07, "loss": 0.7390400409698487, "step": 103660 }, { "epoch": 2.9293231808100355, "grad_norm": 3.1475636959075928, "learning_rate": 1.518449137874023e-07, "loss": 0.653846263885498, "step": 103680 }, { "epoch": 2.9298882563182507, "grad_norm": 4.346538543701172, "learning_rate": 1.4942920647128544e-07, "loss": 0.8221024513244629, "step": 103700 }, { "epoch": 2.9304533318264654, "grad_norm": 4.652528762817383, "learning_rate": 1.4703284058580348e-07, "loss": 0.8153985977172852, "step": 103720 }, { "epoch": 2.93101840733468, "grad_norm": 3.266695499420166, "learning_rate": 1.4465581706072373e-07, "loss": 0.7082282543182373, "step": 103740 }, { "epoch": 2.931583482842895, "grad_norm": 3.0935182571411133, "learning_rate": 1.4229813681830295e-07, "loss": 0.7526671409606933, "step": 103760 }, { "epoch": 2.9321485583511095, "grad_norm": 3.6189544200897217, "learning_rate": 1.399598007732872e-07, "loss": 0.7764111995697022, "step": 103780 }, { "epoch": 2.9327136338593247, "grad_norm": 2.5480761528015137, "learning_rate": 1.3764080983292848e-07, "loss": 0.6868762016296387, "step": 103800 }, { "epoch": 2.9332787093675394, "grad_norm": 3.6226329803466797, "learning_rate": 1.353411648969627e-07, "loss": 0.7339027881622314, "step": 103820 }, { "epoch": 2.933843784875754, "grad_norm": 2.9475932121276855, "learning_rate": 1.3306086685763163e-07, "loss": 0.7719410419464111, "step": 103840 }, { "epoch": 2.934408860383969, "grad_norm": 5.307343006134033, "learning_rate": 1.3079991659966096e-07, "loss": 0.7445406913757324, "step": 103860 }, { "epoch": 2.9349739358921836, "grad_norm": 3.6775295734405518, "learning_rate": 1.2855831500027117e-07, "loss": 0.7234294414520264, "step": 103880 }, { "epoch": 2.9355390114003983, "grad_norm": 2.678783416748047, "learning_rate": 1.263360629291721e-07, "loss": 0.7840944290161133, "step": 103900 }, { "epoch": 2.936104086908613, "grad_norm": 4.161248207092285, "learning_rate": 1.2413316124857965e-07, "loss": 0.7251946926116943, "step": 103920 }, { "epoch": 2.9366691624168277, "grad_norm": 3.2039496898651123, "learning_rate": 1.2194961081319344e-07, "loss": 0.7817496299743653, "step": 103940 }, { "epoch": 2.9372342379250425, "grad_norm": 2.4271790981292725, "learning_rate": 1.1978541247020246e-07, "loss": 0.7531351089477539, "step": 103960 }, { "epoch": 2.9377993134332576, "grad_norm": 4.259115219116211, "learning_rate": 1.176405670592906e-07, "loss": 0.7631626129150391, "step": 103980 }, { "epoch": 2.9383643889414723, "grad_norm": 3.0198793411254883, "learning_rate": 1.1551507541263107e-07, "loss": 0.7101433753967286, "step": 104000 }, { "epoch": 2.938929464449687, "grad_norm": 2.6961700916290283, "learning_rate": 1.1340893835489198e-07, "loss": 0.6811171054840088, "step": 104020 }, { "epoch": 2.9394945399579018, "grad_norm": 3.0098989009857178, "learning_rate": 1.1132215670322521e-07, "loss": 0.7507858276367188, "step": 104040 }, { "epoch": 2.9400596154661165, "grad_norm": 4.266958236694336, "learning_rate": 1.0925473126728314e-07, "loss": 0.7479236602783204, "step": 104060 }, { "epoch": 2.9406246909743317, "grad_norm": 5.362696170806885, "learning_rate": 1.0720666284919634e-07, "loss": 0.7861573696136475, "step": 104080 }, { "epoch": 2.9411897664825464, "grad_norm": 3.4340922832489014, "learning_rate": 1.0517795224359028e-07, "loss": 0.7405506610870362, "step": 104100 }, { "epoch": 2.941754841990761, "grad_norm": 3.8392751216888428, "learning_rate": 1.031686002375909e-07, "loss": 0.7242162704467774, "step": 104120 }, { "epoch": 2.942319917498976, "grad_norm": 6.3120341300964355, "learning_rate": 1.0117860761079678e-07, "loss": 0.7317235469818115, "step": 104140 }, { "epoch": 2.9428849930071905, "grad_norm": 3.336538076400757, "learning_rate": 9.92079751352959e-08, "loss": 0.8276382446289062, "step": 104160 }, { "epoch": 2.9434500685154052, "grad_norm": 3.5151612758636475, "learning_rate": 9.725670357567663e-08, "loss": 0.7456445693969727, "step": 104180 }, { "epoch": 2.94401514402362, "grad_norm": 4.099350452423096, "learning_rate": 9.532479368901115e-08, "loss": 0.7178452968597412, "step": 104200 }, { "epoch": 2.9445802195318347, "grad_norm": 3.7780566215515137, "learning_rate": 9.341224622485545e-08, "loss": 0.6384541034698487, "step": 104220 }, { "epoch": 2.94514529504005, "grad_norm": 4.447210788726807, "learning_rate": 9.151906192524928e-08, "loss": 0.7599322319030761, "step": 104240 }, { "epoch": 2.9457103705482646, "grad_norm": 3.3222999572753906, "learning_rate": 8.964524152473285e-08, "loss": 0.7359830379486084, "step": 104260 }, { "epoch": 2.9462754460564793, "grad_norm": 5.159239768981934, "learning_rate": 8.779078575032462e-08, "loss": 0.701627779006958, "step": 104280 }, { "epoch": 2.946840521564694, "grad_norm": 6.083093643188477, "learning_rate": 8.595569532153235e-08, "loss": 0.8198593139648438, "step": 104300 }, { "epoch": 2.9474055970729087, "grad_norm": 2.87579083442688, "learning_rate": 8.413997095034764e-08, "loss": 0.7674360275268555, "step": 104320 }, { "epoch": 2.947970672581124, "grad_norm": 3.170172929763794, "learning_rate": 8.23436133412514e-08, "loss": 0.7402498722076416, "step": 104340 }, { "epoch": 2.9485357480893386, "grad_norm": 3.59977650642395, "learning_rate": 8.056662319120834e-08, "loss": 0.7376179218292236, "step": 104360 }, { "epoch": 2.9491008235975533, "grad_norm": 3.8904476165771484, "learning_rate": 7.880900118966695e-08, "loss": 0.699659776687622, "step": 104380 }, { "epoch": 2.949665899105768, "grad_norm": 3.735724449157715, "learning_rate": 7.707074801856506e-08, "loss": 0.721026086807251, "step": 104400 }, { "epoch": 2.9502309746139828, "grad_norm": 4.293506622314453, "learning_rate": 7.535186435232989e-08, "loss": 0.7732013702392578, "step": 104420 }, { "epoch": 2.9507960501221975, "grad_norm": 3.271266460418701, "learning_rate": 7.365235085786126e-08, "loss": 0.7623799324035645, "step": 104440 }, { "epoch": 2.951361125630412, "grad_norm": 5.933332443237305, "learning_rate": 7.197220819454842e-08, "loss": 0.7265616893768311, "step": 104460 }, { "epoch": 2.951926201138627, "grad_norm": 3.209658145904541, "learning_rate": 7.031143701427545e-08, "loss": 0.7710423469543457, "step": 104480 }, { "epoch": 2.952491276646842, "grad_norm": 3.04109525680542, "learning_rate": 6.867003796139914e-08, "loss": 0.7455042839050293, "step": 104500 }, { "epoch": 2.953056352155057, "grad_norm": 3.9623677730560303, "learning_rate": 6.704801167275453e-08, "loss": 0.7209254264831543, "step": 104520 }, { "epoch": 2.9536214276632715, "grad_norm": 2.631855010986328, "learning_rate": 6.544535877768266e-08, "loss": 0.7704589366912842, "step": 104540 }, { "epoch": 2.9541865031714862, "grad_norm": 4.382111549377441, "learning_rate": 6.386207989798054e-08, "loss": 0.7307291030883789, "step": 104560 }, { "epoch": 2.954751578679701, "grad_norm": 3.6443135738372803, "learning_rate": 6.229817564794571e-08, "loss": 0.6318872928619385, "step": 104580 }, { "epoch": 2.955316654187916, "grad_norm": 4.267136096954346, "learning_rate": 6.075364663435945e-08, "loss": 0.7808576583862304, "step": 104600 }, { "epoch": 2.955881729696131, "grad_norm": 3.130013942718506, "learning_rate": 5.9228493456481296e-08, "loss": 0.7034039497375488, "step": 104620 }, { "epoch": 2.9564468052043456, "grad_norm": 2.929933547973633, "learning_rate": 5.7722716706043455e-08, "loss": 0.7439420223236084, "step": 104640 }, { "epoch": 2.9570118807125603, "grad_norm": 4.1645331382751465, "learning_rate": 5.62363169672786e-08, "loss": 0.7877416133880615, "step": 104660 }, { "epoch": 2.957576956220775, "grad_norm": 2.6916918754577637, "learning_rate": 5.4769294816880976e-08, "loss": 0.6900686740875244, "step": 104680 }, { "epoch": 2.9581420317289897, "grad_norm": 2.486707925796509, "learning_rate": 5.3321650824050826e-08, "loss": 0.7612568378448487, "step": 104700 }, { "epoch": 2.9587071072372044, "grad_norm": 3.5412702560424805, "learning_rate": 5.189338555044998e-08, "loss": 0.69962158203125, "step": 104720 }, { "epoch": 2.959272182745419, "grad_norm": 3.2482657432556152, "learning_rate": 5.0484499550229606e-08, "loss": 0.6773478507995605, "step": 104740 }, { "epoch": 2.9598372582536343, "grad_norm": 4.5106282234191895, "learning_rate": 4.9094993370024654e-08, "loss": 0.8127034187316895, "step": 104760 }, { "epoch": 2.960402333761849, "grad_norm": 3.251251220703125, "learning_rate": 4.772486754893724e-08, "loss": 0.7839215755462646, "step": 104780 }, { "epoch": 2.9609674092700637, "grad_norm": 3.1020898818969727, "learning_rate": 4.637412261856988e-08, "loss": 0.738300895690918, "step": 104800 }, { "epoch": 2.9615324847782785, "grad_norm": 3.353025436401367, "learning_rate": 4.504275910298672e-08, "loss": 0.7368519306182861, "step": 104820 }, { "epoch": 2.962097560286493, "grad_norm": 3.327768564224243, "learning_rate": 4.373077751875232e-08, "loss": 0.7608389377593994, "step": 104840 }, { "epoch": 2.9626626357947083, "grad_norm": 4.881365776062012, "learning_rate": 4.243817837488728e-08, "loss": 0.8652527809143067, "step": 104860 }, { "epoch": 2.963227711302923, "grad_norm": 3.204847574234009, "learning_rate": 4.116496217291821e-08, "loss": 0.7348035335540771, "step": 104880 }, { "epoch": 2.963792786811138, "grad_norm": 4.04777193069458, "learning_rate": 3.991112940682218e-08, "loss": 0.7272647857666016, "step": 104900 }, { "epoch": 2.9643578623193525, "grad_norm": 4.567259311676025, "learning_rate": 3.8676680563087817e-08, "loss": 0.7085630893707275, "step": 104920 }, { "epoch": 2.964922937827567, "grad_norm": 3.435236692428589, "learning_rate": 3.746161612065424e-08, "loss": 0.7013966083526612, "step": 104940 }, { "epoch": 2.965488013335782, "grad_norm": 4.9909844398498535, "learning_rate": 3.626593655095545e-08, "loss": 0.7324191570281983, "step": 104960 }, { "epoch": 2.9660530888439967, "grad_norm": 2.933518886566162, "learning_rate": 3.5089642317903684e-08, "loss": 0.7939290046691895, "step": 104980 }, { "epoch": 2.9666181643522114, "grad_norm": 4.266222953796387, "learning_rate": 3.393273387788942e-08, "loss": 0.7496802330017089, "step": 105000 }, { "epoch": 2.967183239860426, "grad_norm": 4.020092010498047, "learning_rate": 3.2795211679770285e-08, "loss": 0.767484474182129, "step": 105020 }, { "epoch": 2.9677483153686413, "grad_norm": 4.781620502471924, "learning_rate": 3.167707616489879e-08, "loss": 0.7182043552398681, "step": 105040 }, { "epoch": 2.968313390876856, "grad_norm": 2.94049334526062, "learning_rate": 3.057832776710012e-08, "loss": 0.7200721740722656, "step": 105060 }, { "epoch": 2.9688784663850707, "grad_norm": 2.9238948822021484, "learning_rate": 2.9498966912666626e-08, "loss": 0.7392875194549561, "step": 105080 }, { "epoch": 2.9694435418932854, "grad_norm": 3.655456781387329, "learning_rate": 2.8438994020385524e-08, "loss": 0.6994399070739746, "step": 105100 }, { "epoch": 2.9700086174015, "grad_norm": 3.9902920722961426, "learning_rate": 2.739840950150563e-08, "loss": 0.7050798892974853, "step": 105120 }, { "epoch": 2.9705736929097153, "grad_norm": 2.7123336791992188, "learning_rate": 2.6377213759770647e-08, "loss": 0.7703039646148682, "step": 105140 }, { "epoch": 2.97113876841793, "grad_norm": 5.677708625793457, "learning_rate": 2.537540719139142e-08, "loss": 0.780115270614624, "step": 105160 }, { "epoch": 2.9717038439261447, "grad_norm": 5.396571159362793, "learning_rate": 2.4392990185045927e-08, "loss": 0.7605045318603516, "step": 105180 }, { "epoch": 2.9722689194343594, "grad_norm": 2.9243881702423096, "learning_rate": 2.342996312191814e-08, "loss": 0.7050458908081054, "step": 105200 }, { "epoch": 2.972833994942574, "grad_norm": 3.4803192615509033, "learning_rate": 2.248632637563697e-08, "loss": 0.7583983898162842, "step": 105220 }, { "epoch": 2.973399070450789, "grad_norm": 4.822579383850098, "learning_rate": 2.1562080312320652e-08, "loss": 0.7633265495300293, "step": 105240 }, { "epoch": 2.9739641459590036, "grad_norm": 2.8616650104522705, "learning_rate": 2.0657225290576787e-08, "loss": 0.7876972198486328, "step": 105260 }, { "epoch": 2.9745292214672183, "grad_norm": 3.153918504714966, "learning_rate": 1.977176166147454e-08, "loss": 0.7369769096374512, "step": 105280 }, { "epoch": 2.9750942969754335, "grad_norm": 3.859205961227417, "learning_rate": 1.890568976856133e-08, "loss": 0.7231922149658203, "step": 105300 }, { "epoch": 2.975659372483648, "grad_norm": 4.986781597137451, "learning_rate": 1.8059009947862802e-08, "loss": 0.6607360363006591, "step": 105320 }, { "epoch": 2.976224447991863, "grad_norm": 3.2118327617645264, "learning_rate": 1.7231722527882853e-08, "loss": 0.7503192901611329, "step": 105340 }, { "epoch": 2.9767895235000776, "grad_norm": 4.297379493713379, "learning_rate": 1.642382782959806e-08, "loss": 0.7823060989379883, "step": 105360 }, { "epoch": 2.9773545990082924, "grad_norm": 4.547895908355713, "learning_rate": 1.5635326166463238e-08, "loss": 0.791249132156372, "step": 105380 }, { "epoch": 2.9779196745165075, "grad_norm": 3.6519675254821777, "learning_rate": 1.4866217844400343e-08, "loss": 0.7749728679656982, "step": 105400 }, { "epoch": 2.9784847500247222, "grad_norm": 2.465097188949585, "learning_rate": 1.4116503161826222e-08, "loss": 0.7140283584594727, "step": 105420 }, { "epoch": 2.979049825532937, "grad_norm": 3.657827377319336, "learning_rate": 1.3386182409613756e-08, "loss": 0.7278260231018067, "step": 105440 }, { "epoch": 2.9796149010411517, "grad_norm": 3.617384672164917, "learning_rate": 1.2675255871119617e-08, "loss": 0.7729177474975586, "step": 105460 }, { "epoch": 2.9801799765493664, "grad_norm": 3.2274065017700195, "learning_rate": 1.1983723822173165e-08, "loss": 0.7110044479370117, "step": 105480 }, { "epoch": 2.980745052057581, "grad_norm": 2.8142600059509277, "learning_rate": 1.1311586531081998e-08, "loss": 0.759593152999878, "step": 105500 }, { "epoch": 2.981310127565796, "grad_norm": 2.8436758518218994, "learning_rate": 1.0658844258631951e-08, "loss": 0.7496458053588867, "step": 105520 }, { "epoch": 2.9818752030740105, "grad_norm": 4.189398765563965, "learning_rate": 1.0025497258076e-08, "loss": 0.7691264152526855, "step": 105540 }, { "epoch": 2.9824402785822257, "grad_norm": 3.8557820320129395, "learning_rate": 9.411545775145358e-09, "loss": 0.682146406173706, "step": 105560 }, { "epoch": 2.9830053540904404, "grad_norm": 3.80090594291687, "learning_rate": 8.816990048043928e-09, "loss": 0.7083302497863769, "step": 105580 }, { "epoch": 2.983570429598655, "grad_norm": 3.600450038909912, "learning_rate": 8.241830307453846e-09, "loss": 0.6735452651977539, "step": 105600 }, { "epoch": 2.98413550510687, "grad_norm": 4.679409980773926, "learning_rate": 7.686066776529943e-09, "loss": 0.7307502269744873, "step": 105620 }, { "epoch": 2.9847005806150846, "grad_norm": 4.136692047119141, "learning_rate": 7.1496996708997345e-09, "loss": 0.8120885848999023, "step": 105640 }, { "epoch": 2.9852656561232997, "grad_norm": 3.244462251663208, "learning_rate": 6.632729198674525e-09, "loss": 0.7207778930664063, "step": 105660 }, { "epoch": 2.9858307316315145, "grad_norm": 2.9332449436187744, "learning_rate": 6.135155560427208e-09, "loss": 0.8040857315063477, "step": 105680 }, { "epoch": 2.986395807139729, "grad_norm": 4.761850357055664, "learning_rate": 5.656978949208913e-09, "loss": 0.8257059097290039, "step": 105700 }, { "epoch": 2.986960882647944, "grad_norm": 4.325450420379639, "learning_rate": 5.19819955054901e-09, "loss": 0.780093002319336, "step": 105720 }, { "epoch": 2.9875259581561586, "grad_norm": 2.6540143489837646, "learning_rate": 4.758817542449556e-09, "loss": 0.7841536045074463, "step": 105740 }, { "epoch": 2.9880910336643733, "grad_norm": 2.5766024589538574, "learning_rate": 4.338833095385297e-09, "loss": 0.6853007316589356, "step": 105760 }, { "epoch": 2.988656109172588, "grad_norm": 3.1695165634155273, "learning_rate": 3.9382463723036665e-09, "loss": 0.7245151042938233, "step": 105780 }, { "epoch": 2.989221184680803, "grad_norm": 3.7060022354125977, "learning_rate": 3.5570575286247854e-09, "loss": 0.7650035381317138, "step": 105800 }, { "epoch": 2.9897862601890175, "grad_norm": 5.964327812194824, "learning_rate": 3.195266712252565e-09, "loss": 0.6780899047851563, "step": 105820 }, { "epoch": 2.9903513356972327, "grad_norm": 2.7125296592712402, "learning_rate": 2.852874063552502e-09, "loss": 0.6953757762908935, "step": 105840 }, { "epoch": 2.9909164112054474, "grad_norm": 3.174798011779785, "learning_rate": 2.529879715373884e-09, "loss": 0.6934971809387207, "step": 105860 }, { "epoch": 2.991481486713662, "grad_norm": 3.881653070449829, "learning_rate": 2.2262837930275836e-09, "loss": 0.7792358875274659, "step": 105880 }, { "epoch": 2.992046562221877, "grad_norm": 3.9865691661834717, "learning_rate": 1.942086414308264e-09, "loss": 0.7794184207916259, "step": 105900 }, { "epoch": 2.9926116377300915, "grad_norm": 5.097354412078857, "learning_rate": 1.6772876894777245e-09, "loss": 0.624259090423584, "step": 105920 }, { "epoch": 2.9931767132383067, "grad_norm": 3.1484298706054688, "learning_rate": 1.4318877212815551e-09, "loss": 0.6797066688537597, "step": 105940 }, { "epoch": 2.9937417887465214, "grad_norm": 4.459686279296875, "learning_rate": 1.2058866049324823e-09, "loss": 0.7926575183868408, "step": 105960 }, { "epoch": 2.994306864254736, "grad_norm": 2.511639356613159, "learning_rate": 9.992844281103698e-10, "loss": 0.7472986221313477, "step": 105980 }, { "epoch": 2.994871939762951, "grad_norm": 3.5226924419403076, "learning_rate": 8.120812709788706e-10, "loss": 0.7801615715026855, "step": 106000 }, { "epoch": 2.9954370152711656, "grad_norm": 2.045840263366699, "learning_rate": 6.442772061632241e-10, "loss": 0.7658201217651367, "step": 106020 }, { "epoch": 2.9960020907793803, "grad_norm": 3.7994372844696045, "learning_rate": 4.958722987780107e-10, "loss": 0.7130777835845947, "step": 106040 }, { "epoch": 2.996567166287595, "grad_norm": 4.285068035125732, "learning_rate": 3.668666063993964e-10, "loss": 0.8268923759460449, "step": 106060 }, { "epoch": 2.9971322417958097, "grad_norm": 2.7168378829956055, "learning_rate": 2.572601790762352e-10, "loss": 0.7658215045928956, "step": 106080 }, { "epoch": 2.997697317304025, "grad_norm": 3.006124973297119, "learning_rate": 1.670530593411712e-10, "loss": 0.7454598426818848, "step": 106100 }, { "epoch": 2.9982623928122396, "grad_norm": 4.194490432739258, "learning_rate": 9.624528219398521e-11, "loss": 0.7970759391784668, "step": 106120 }, { "epoch": 2.9988274683204543, "grad_norm": 3.304054021835327, "learning_rate": 4.483687510159484e-11, "loss": 0.7499718189239502, "step": 106140 }, { "epoch": 2.999392543828669, "grad_norm": 2.7533209323883057, "learning_rate": 1.2827858009156757e-11, "loss": 0.7339781761169434, "step": 106160 }, { "epoch": 2.9999576193368838, "grad_norm": 3.763478994369507, "learning_rate": 2.1824334006659285e-13, "loss": 0.7150230407714844, "step": 106180 }, { "epoch": 3.0, "step": 106182, "total_flos": 0.0, "train_loss": 1.0381244404265966, "train_runtime": 46838.5662, "train_samples_per_second": 18.136, "train_steps_per_second": 2.267 } ], "logging_steps": 20, "max_steps": 106182, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 4000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }