{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0236087689713322, "eval_steps": 500, "global_step": 3600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005621135469364812, "grad_norm": 19.072066040018505, "learning_rate": 7.223113964686999e-07, "loss": 8.2549, "step": 10 }, { "epoch": 0.011242270938729624, "grad_norm": 19.552394701284502, "learning_rate": 1.5248796147672553e-06, "loss": 8.1791, "step": 20 }, { "epoch": 0.016863406408094434, "grad_norm": 9.93392906727828, "learning_rate": 2.3274478330658108e-06, "loss": 7.6759, "step": 30 }, { "epoch": 0.022484541877459248, "grad_norm": 7.426576059473498, "learning_rate": 3.1300160513643665e-06, "loss": 6.913, "step": 40 }, { "epoch": 0.028105677346824058, "grad_norm": 3.5646171014288366, "learning_rate": 3.932584269662922e-06, "loss": 6.3931, "step": 50 }, { "epoch": 0.03372681281618887, "grad_norm": 2.8779163477648666, "learning_rate": 4.735152487961477e-06, "loss": 6.0533, "step": 60 }, { "epoch": 0.03934794828555368, "grad_norm": 3.3997232487978883, "learning_rate": 5.537720706260032e-06, "loss": 5.7246, "step": 70 }, { "epoch": 0.044969083754918496, "grad_norm": 4.059106771548473, "learning_rate": 6.340288924558588e-06, "loss": 5.2465, "step": 80 }, { "epoch": 0.050590219224283306, "grad_norm": 4.7307302237777895, "learning_rate": 7.142857142857143e-06, "loss": 4.6393, "step": 90 }, { "epoch": 0.056211354693648116, "grad_norm": 5.242698651813807, "learning_rate": 7.9454253611557e-06, "loss": 4.0362, "step": 100 }, { "epoch": 0.061832490163012926, "grad_norm": 4.723996169899083, "learning_rate": 8.747993579454254e-06, "loss": 3.549, "step": 110 }, { "epoch": 0.06745362563237774, "grad_norm": 2.885143750378497, "learning_rate": 9.550561797752809e-06, "loss": 3.2171, "step": 120 }, { "epoch": 0.07307476110174255, "grad_norm": 6.825878781249646, "learning_rate": 1.0353130016051364e-05, "loss": 3.027, "step": 130 }, { "epoch": 0.07869589657110736, "grad_norm": 6.737230278162123, "learning_rate": 1.115569823434992e-05, "loss": 2.9055, "step": 140 }, { "epoch": 0.08431703204047218, "grad_norm": 6.716587811023919, "learning_rate": 1.1958266452648475e-05, "loss": 2.8089, "step": 150 }, { "epoch": 0.08993816750983699, "grad_norm": 7.201415197148535, "learning_rate": 1.276083467094703e-05, "loss": 2.7296, "step": 160 }, { "epoch": 0.0955593029792018, "grad_norm": 7.301380585480233, "learning_rate": 1.3563402889245585e-05, "loss": 2.6609, "step": 170 }, { "epoch": 0.10118043844856661, "grad_norm": 11.575326761105941, "learning_rate": 1.4365971107544143e-05, "loss": 2.5979, "step": 180 }, { "epoch": 0.10680157391793142, "grad_norm": 8.619354697957048, "learning_rate": 1.5168539325842698e-05, "loss": 2.5341, "step": 190 }, { "epoch": 0.11242270938729623, "grad_norm": 7.390257991673745, "learning_rate": 1.5971107544141253e-05, "loss": 2.4767, "step": 200 }, { "epoch": 0.11804384485666104, "grad_norm": 13.39500588081804, "learning_rate": 1.6773675762439807e-05, "loss": 2.4379, "step": 210 }, { "epoch": 0.12366498032602585, "grad_norm": 27.117334976761317, "learning_rate": 1.7576243980738362e-05, "loss": 2.3867, "step": 220 }, { "epoch": 0.12928611579539068, "grad_norm": 11.695868441564258, "learning_rate": 1.8378812199036917e-05, "loss": 2.3207, "step": 230 }, { "epoch": 0.13490725126475547, "grad_norm": 10.785553590242758, "learning_rate": 1.9181380417335472e-05, "loss": 2.2455, "step": 240 }, { "epoch": 0.1405283867341203, "grad_norm": 25.384076838053424, "learning_rate": 1.998394863563403e-05, "loss": 2.1723, "step": 250 }, { "epoch": 0.1461495222034851, "grad_norm": 16.42978149349179, "learning_rate": 2.0786516853932585e-05, "loss": 2.1322, "step": 260 }, { "epoch": 0.15177065767284992, "grad_norm": 15.299053481717623, "learning_rate": 2.158908507223114e-05, "loss": 2.0356, "step": 270 }, { "epoch": 0.15739179314221471, "grad_norm": 16.598966653865332, "learning_rate": 2.2391653290529695e-05, "loss": 1.9785, "step": 280 }, { "epoch": 0.16301292861157954, "grad_norm": 8.000521357822016, "learning_rate": 2.319422150882825e-05, "loss": 1.8885, "step": 290 }, { "epoch": 0.16863406408094436, "grad_norm": 12.337240959757104, "learning_rate": 2.3996789727126808e-05, "loss": 1.7929, "step": 300 }, { "epoch": 0.17425519955030916, "grad_norm": 9.313580975453032, "learning_rate": 2.4799357945425362e-05, "loss": 1.7252, "step": 310 }, { "epoch": 0.17987633501967398, "grad_norm": 9.713971076745432, "learning_rate": 2.5601926163723917e-05, "loss": 1.6366, "step": 320 }, { "epoch": 0.18549747048903878, "grad_norm": 6.604247664050388, "learning_rate": 2.6404494382022472e-05, "loss": 1.5532, "step": 330 }, { "epoch": 0.1911186059584036, "grad_norm": 8.06631111933664, "learning_rate": 2.7207062600321027e-05, "loss": 1.5014, "step": 340 }, { "epoch": 0.1967397414277684, "grad_norm": 5.369237324186266, "learning_rate": 2.8009630818619585e-05, "loss": 1.4407, "step": 350 }, { "epoch": 0.20236087689713322, "grad_norm": 6.309483928633083, "learning_rate": 2.881219903691814e-05, "loss": 1.398, "step": 360 }, { "epoch": 0.20798201236649802, "grad_norm": 6.173807170921828, "learning_rate": 2.9614767255216698e-05, "loss": 1.3462, "step": 370 }, { "epoch": 0.21360314783586284, "grad_norm": 7.913665828353373, "learning_rate": 3.0417335473515253e-05, "loss": 1.2942, "step": 380 }, { "epoch": 0.21922428330522767, "grad_norm": 6.320887435288008, "learning_rate": 3.1219903691813805e-05, "loss": 1.2581, "step": 390 }, { "epoch": 0.22484541877459246, "grad_norm": 4.001174978157139, "learning_rate": 3.202247191011236e-05, "loss": 1.2068, "step": 400 }, { "epoch": 0.2304665542439573, "grad_norm": 5.833384870789841, "learning_rate": 3.2825040128410914e-05, "loss": 1.1774, "step": 410 }, { "epoch": 0.23608768971332209, "grad_norm": 5.418298506902902, "learning_rate": 3.362760834670947e-05, "loss": 1.1285, "step": 420 }, { "epoch": 0.2417088251826869, "grad_norm": 6.822807280672466, "learning_rate": 3.4430176565008024e-05, "loss": 1.0971, "step": 430 }, { "epoch": 0.2473299606520517, "grad_norm": 5.1633853492959725, "learning_rate": 3.523274478330658e-05, "loss": 1.0631, "step": 440 }, { "epoch": 0.25295109612141653, "grad_norm": 4.794453623656116, "learning_rate": 3.6035313001605133e-05, "loss": 1.0233, "step": 450 }, { "epoch": 0.25857223159078135, "grad_norm": 6.493147309773226, "learning_rate": 3.683788121990369e-05, "loss": 1.0093, "step": 460 }, { "epoch": 0.2641933670601461, "grad_norm": 7.38273852542595, "learning_rate": 3.764044943820225e-05, "loss": 0.9745, "step": 470 }, { "epoch": 0.26981450252951095, "grad_norm": 5.953745454074908, "learning_rate": 3.8443017656500805e-05, "loss": 0.9609, "step": 480 }, { "epoch": 0.27543563799887577, "grad_norm": 5.92674703602574, "learning_rate": 3.924558587479936e-05, "loss": 0.9295, "step": 490 }, { "epoch": 0.2810567734682406, "grad_norm": 4.500282226524396, "learning_rate": 4.0048154093097914e-05, "loss": 0.8992, "step": 500 }, { "epoch": 0.2866779089376054, "grad_norm": 4.320018263048497, "learning_rate": 4.085072231139647e-05, "loss": 0.8855, "step": 510 }, { "epoch": 0.2922990444069702, "grad_norm": 6.008360095853525, "learning_rate": 4.1653290529695024e-05, "loss": 0.8589, "step": 520 }, { "epoch": 0.297920179876335, "grad_norm": 5.252075871228091, "learning_rate": 4.245585874799358e-05, "loss": 0.8272, "step": 530 }, { "epoch": 0.30354131534569984, "grad_norm": 6.427285353419691, "learning_rate": 4.3258426966292134e-05, "loss": 0.808, "step": 540 }, { "epoch": 0.30916245081506466, "grad_norm": 5.854800753365741, "learning_rate": 4.4060995184590695e-05, "loss": 0.7901, "step": 550 }, { "epoch": 0.31478358628442943, "grad_norm": 7.046341886366144, "learning_rate": 4.486356340288925e-05, "loss": 0.7701, "step": 560 }, { "epoch": 0.32040472175379425, "grad_norm": 5.594440118602691, "learning_rate": 4.5666131621187805e-05, "loss": 0.7462, "step": 570 }, { "epoch": 0.3260258572231591, "grad_norm": 5.653552049437021, "learning_rate": 4.646869983948636e-05, "loss": 0.7284, "step": 580 }, { "epoch": 0.3316469926925239, "grad_norm": 5.196665356454571, "learning_rate": 4.7271268057784915e-05, "loss": 0.712, "step": 590 }, { "epoch": 0.3372681281618887, "grad_norm": 6.1381022060931025, "learning_rate": 4.807383627608347e-05, "loss": 0.6868, "step": 600 }, { "epoch": 0.3428892636312535, "grad_norm": 5.052546164435208, "learning_rate": 4.8876404494382024e-05, "loss": 0.6672, "step": 610 }, { "epoch": 0.3485103991006183, "grad_norm": 4.916726449591455, "learning_rate": 4.9678972712680586e-05, "loss": 0.6501, "step": 620 }, { "epoch": 0.35413153456998314, "grad_norm": 4.832632041097204, "learning_rate": 5.0481540930979134e-05, "loss": 0.6313, "step": 630 }, { "epoch": 0.35975267003934797, "grad_norm": 4.751573877646501, "learning_rate": 5.1284109149277696e-05, "loss": 0.6165, "step": 640 }, { "epoch": 0.36537380550871273, "grad_norm": 5.912237963361695, "learning_rate": 5.2086677367576244e-05, "loss": 0.5907, "step": 650 }, { "epoch": 0.37099494097807756, "grad_norm": 4.086167788806448, "learning_rate": 5.2889245585874805e-05, "loss": 0.5768, "step": 660 }, { "epoch": 0.3766160764474424, "grad_norm": 4.582982284092926, "learning_rate": 5.369181380417335e-05, "loss": 0.5579, "step": 670 }, { "epoch": 0.3822372119168072, "grad_norm": 4.620402866105723, "learning_rate": 5.4494382022471915e-05, "loss": 0.5379, "step": 680 }, { "epoch": 0.38785834738617203, "grad_norm": 3.8404903506330834, "learning_rate": 5.5296950240770476e-05, "loss": 0.5112, "step": 690 }, { "epoch": 0.3934794828555368, "grad_norm": 3.2956728880451784, "learning_rate": 5.6099518459069025e-05, "loss": 0.502, "step": 700 }, { "epoch": 0.3991006183249016, "grad_norm": 4.455851011958456, "learning_rate": 5.6902086677367586e-05, "loss": 0.4889, "step": 710 }, { "epoch": 0.40472175379426645, "grad_norm": 3.3081515499225693, "learning_rate": 5.7704654895666134e-05, "loss": 0.4703, "step": 720 }, { "epoch": 0.41034288926363127, "grad_norm": 3.5766535302434037, "learning_rate": 5.8507223113964696e-05, "loss": 0.4591, "step": 730 }, { "epoch": 0.41596402473299604, "grad_norm": 3.1816986592066154, "learning_rate": 5.9309791332263244e-05, "loss": 0.437, "step": 740 }, { "epoch": 0.42158516020236086, "grad_norm": 2.746088460027587, "learning_rate": 6.0112359550561805e-05, "loss": 0.429, "step": 750 }, { "epoch": 0.4272062956717257, "grad_norm": 2.7638950111486777, "learning_rate": 6.0914927768860353e-05, "loss": 0.4056, "step": 760 }, { "epoch": 0.4328274311410905, "grad_norm": 2.621320210943319, "learning_rate": 6.171749598715892e-05, "loss": 0.3951, "step": 770 }, { "epoch": 0.43844856661045534, "grad_norm": 2.9039501807988635, "learning_rate": 6.252006420545746e-05, "loss": 0.3752, "step": 780 }, { "epoch": 0.4440697020798201, "grad_norm": 2.672708782303941, "learning_rate": 6.332263242375602e-05, "loss": 0.3732, "step": 790 }, { "epoch": 0.44969083754918493, "grad_norm": 2.534243622485374, "learning_rate": 6.412520064205457e-05, "loss": 0.3544, "step": 800 }, { "epoch": 0.45531197301854975, "grad_norm": 2.2060854376474297, "learning_rate": 6.492776886035313e-05, "loss": 0.337, "step": 810 }, { "epoch": 0.4609331084879146, "grad_norm": 2.8950080552663353, "learning_rate": 6.573033707865169e-05, "loss": 0.3278, "step": 820 }, { "epoch": 0.46655424395727935, "grad_norm": 2.8077239251031183, "learning_rate": 6.653290529695024e-05, "loss": 0.3188, "step": 830 }, { "epoch": 0.47217537942664417, "grad_norm": 2.4109713129957173, "learning_rate": 6.73354735152488e-05, "loss": 0.3023, "step": 840 }, { "epoch": 0.477796514896009, "grad_norm": 2.4108771548493864, "learning_rate": 6.813804173354735e-05, "loss": 0.2907, "step": 850 }, { "epoch": 0.4834176503653738, "grad_norm": 2.381688936764209, "learning_rate": 6.894060995184591e-05, "loss": 0.28, "step": 860 }, { "epoch": 0.48903878583473864, "grad_norm": 2.226240645538486, "learning_rate": 6.974317817014446e-05, "loss": 0.265, "step": 870 }, { "epoch": 0.4946599213041034, "grad_norm": 2.36477519460133, "learning_rate": 7.054574638844302e-05, "loss": 0.2563, "step": 880 }, { "epoch": 0.5002810567734682, "grad_norm": 2.1877534753089325, "learning_rate": 7.134831460674157e-05, "loss": 0.2458, "step": 890 }, { "epoch": 0.5059021922428331, "grad_norm": 1.9910110516875703, "learning_rate": 7.215088282504013e-05, "loss": 0.237, "step": 900 }, { "epoch": 0.5115233277121979, "grad_norm": 2.6541637478760203, "learning_rate": 7.295345104333868e-05, "loss": 0.2274, "step": 910 }, { "epoch": 0.5171444631815627, "grad_norm": 2.1481697620944273, "learning_rate": 7.375601926163724e-05, "loss": 0.2125, "step": 920 }, { "epoch": 0.5227655986509275, "grad_norm": 2.2194085230343283, "learning_rate": 7.455858747993579e-05, "loss": 0.2086, "step": 930 }, { "epoch": 0.5283867341202922, "grad_norm": 1.8687719324053211, "learning_rate": 7.536115569823435e-05, "loss": 0.2002, "step": 940 }, { "epoch": 0.5340078695896571, "grad_norm": 1.809218029026303, "learning_rate": 7.616372391653292e-05, "loss": 0.19, "step": 950 }, { "epoch": 0.5396290050590219, "grad_norm": 1.544075304452749, "learning_rate": 7.696629213483147e-05, "loss": 0.1824, "step": 960 }, { "epoch": 0.5452501405283867, "grad_norm": 1.7029729768183128, "learning_rate": 7.776886035313003e-05, "loss": 0.1766, "step": 970 }, { "epoch": 0.5508712759977515, "grad_norm": 1.9321640691371915, "learning_rate": 7.857142857142858e-05, "loss": 0.1674, "step": 980 }, { "epoch": 0.5564924114671164, "grad_norm": 1.6567308102186273, "learning_rate": 7.937399678972713e-05, "loss": 0.1616, "step": 990 }, { "epoch": 0.5621135469364812, "grad_norm": 1.75914588466869, "learning_rate": 8.017656500802569e-05, "loss": 0.1496, "step": 1000 }, { "epoch": 0.567734682405846, "grad_norm": 1.6033430089086067, "learning_rate": 8.097913322632424e-05, "loss": 0.1411, "step": 1010 }, { "epoch": 0.5733558178752108, "grad_norm": 1.5592637787510577, "learning_rate": 8.17817014446228e-05, "loss": 0.1349, "step": 1020 }, { "epoch": 0.5789769533445756, "grad_norm": 1.490862273444445, "learning_rate": 8.258426966292135e-05, "loss": 0.1321, "step": 1030 }, { "epoch": 0.5845980888139404, "grad_norm": 1.103403083662274, "learning_rate": 8.338683788121991e-05, "loss": 0.1237, "step": 1040 }, { "epoch": 0.5902192242833052, "grad_norm": 1.3322879027309737, "learning_rate": 8.418940609951846e-05, "loss": 0.1175, "step": 1050 }, { "epoch": 0.59584035975267, "grad_norm": 1.1302428773890956, "learning_rate": 8.499197431781702e-05, "loss": 0.1134, "step": 1060 }, { "epoch": 0.6014614952220348, "grad_norm": 1.043524404705153, "learning_rate": 8.579454253611557e-05, "loss": 0.1079, "step": 1070 }, { "epoch": 0.6070826306913997, "grad_norm": 1.0807715777082445, "learning_rate": 8.659711075441413e-05, "loss": 0.1027, "step": 1080 }, { "epoch": 0.6127037661607645, "grad_norm": 1.0613560487233085, "learning_rate": 8.739967897271268e-05, "loss": 0.1014, "step": 1090 }, { "epoch": 0.6183249016301293, "grad_norm": 1.7970050911102724, "learning_rate": 8.820224719101124e-05, "loss": 0.0956, "step": 1100 }, { "epoch": 0.6239460370994941, "grad_norm": 1.2518666492303272, "learning_rate": 8.900481540930979e-05, "loss": 0.0934, "step": 1110 }, { "epoch": 0.6295671725688589, "grad_norm": 1.1953063290224126, "learning_rate": 8.980738362760836e-05, "loss": 0.1004, "step": 1120 }, { "epoch": 0.6351883080382237, "grad_norm": 0.9616154833979669, "learning_rate": 9.06099518459069e-05, "loss": 0.0843, "step": 1130 }, { "epoch": 0.6408094435075885, "grad_norm": 0.8282021805405166, "learning_rate": 9.141252006420547e-05, "loss": 0.0788, "step": 1140 }, { "epoch": 0.6464305789769533, "grad_norm": 0.7645874993850531, "learning_rate": 9.221508828250401e-05, "loss": 0.0741, "step": 1150 }, { "epoch": 0.6520517144463182, "grad_norm": 1.0333771317137108, "learning_rate": 9.301765650080258e-05, "loss": 0.0708, "step": 1160 }, { "epoch": 0.657672849915683, "grad_norm": 0.6189773458607581, "learning_rate": 9.382022471910112e-05, "loss": 0.0722, "step": 1170 }, { "epoch": 0.6632939853850478, "grad_norm": 0.5553259399184006, "learning_rate": 9.462279293739969e-05, "loss": 0.0654, "step": 1180 }, { "epoch": 0.6689151208544126, "grad_norm": 0.6418699826913336, "learning_rate": 9.542536115569823e-05, "loss": 0.0625, "step": 1190 }, { "epoch": 0.6745362563237775, "grad_norm": 0.692560675949567, "learning_rate": 9.62279293739968e-05, "loss": 0.0591, "step": 1200 }, { "epoch": 0.6801573917931422, "grad_norm": 0.4228488541088058, "learning_rate": 9.703049759229535e-05, "loss": 0.0565, "step": 1210 }, { "epoch": 0.685778527262507, "grad_norm": 0.4504043674769784, "learning_rate": 9.783306581059391e-05, "loss": 0.0546, "step": 1220 }, { "epoch": 0.6913996627318718, "grad_norm": 0.44916766960088017, "learning_rate": 9.863563402889246e-05, "loss": 0.0518, "step": 1230 }, { "epoch": 0.6970207982012366, "grad_norm": 0.46844229890271083, "learning_rate": 9.943820224719102e-05, "loss": 0.0504, "step": 1240 }, { "epoch": 0.7026419336706015, "grad_norm": 0.4911174405862922, "learning_rate": 9.999998231913558e-05, "loss": 0.0482, "step": 1250 }, { "epoch": 0.7082630691399663, "grad_norm": 0.3927574276223742, "learning_rate": 9.999966799300477e-05, "loss": 0.0469, "step": 1260 }, { "epoch": 0.7138842046093311, "grad_norm": 0.3446568196906315, "learning_rate": 9.999896076161874e-05, "loss": 0.0447, "step": 1270 }, { "epoch": 0.7195053400786959, "grad_norm": 0.6708037379046565, "learning_rate": 9.999786063053502e-05, "loss": 0.0437, "step": 1280 }, { "epoch": 0.7251264755480608, "grad_norm": 0.5265622160752478, "learning_rate": 9.999636760839859e-05, "loss": 0.0428, "step": 1290 }, { "epoch": 0.7307476110174255, "grad_norm": 0.3741304206840176, "learning_rate": 9.999448170694188e-05, "loss": 0.0418, "step": 1300 }, { "epoch": 0.7363687464867903, "grad_norm": 0.3488892086457768, "learning_rate": 9.999220294098459e-05, "loss": 0.0401, "step": 1310 }, { "epoch": 0.7419898819561551, "grad_norm": 0.364156745530358, "learning_rate": 9.998953132843362e-05, "loss": 0.0392, "step": 1320 }, { "epoch": 0.7476110174255199, "grad_norm": 0.316984179052284, "learning_rate": 9.998646689028292e-05, "loss": 0.038, "step": 1330 }, { "epoch": 0.7532321528948848, "grad_norm": 0.4122286636140672, "learning_rate": 9.998300965061335e-05, "loss": 0.0369, "step": 1340 }, { "epoch": 0.7588532883642496, "grad_norm": 0.2828777162977292, "learning_rate": 9.997915963659241e-05, "loss": 0.0358, "step": 1350 }, { "epoch": 0.7644744238336144, "grad_norm": 0.35038412611293795, "learning_rate": 9.997491687847413e-05, "loss": 0.0344, "step": 1360 }, { "epoch": 0.7700955593029792, "grad_norm": 0.3359568867412438, "learning_rate": 9.997028140959878e-05, "loss": 0.0348, "step": 1370 }, { "epoch": 0.7757166947723441, "grad_norm": 0.3008434778248411, "learning_rate": 9.99652532663926e-05, "loss": 0.0331, "step": 1380 }, { "epoch": 0.7813378302417088, "grad_norm": 0.24375407955159972, "learning_rate": 9.995983248836749e-05, "loss": 0.0321, "step": 1390 }, { "epoch": 0.7869589657110736, "grad_norm": 0.2580356766574075, "learning_rate": 9.995401911812084e-05, "loss": 0.0305, "step": 1400 }, { "epoch": 0.7925801011804384, "grad_norm": 0.22377682987678044, "learning_rate": 9.994781320133499e-05, "loss": 0.0297, "step": 1410 }, { "epoch": 0.7982012366498032, "grad_norm": 0.3192038760895579, "learning_rate": 9.9941214786777e-05, "loss": 0.0295, "step": 1420 }, { "epoch": 0.8038223721191681, "grad_norm": 0.42209606301924135, "learning_rate": 9.99342239262983e-05, "loss": 0.0283, "step": 1430 }, { "epoch": 0.8094435075885329, "grad_norm": 0.2740277370912408, "learning_rate": 9.992684067483411e-05, "loss": 0.0276, "step": 1440 }, { "epoch": 0.8150646430578977, "grad_norm": 0.2403536361378785, "learning_rate": 9.991906509040323e-05, "loss": 0.027, "step": 1450 }, { "epoch": 0.8206857785272625, "grad_norm": 0.25177256736722925, "learning_rate": 9.99108972341074e-05, "loss": 0.026, "step": 1460 }, { "epoch": 0.8263069139966274, "grad_norm": 0.2611127538329995, "learning_rate": 9.990233717013092e-05, "loss": 0.0254, "step": 1470 }, { "epoch": 0.8319280494659921, "grad_norm": 0.26600699519251914, "learning_rate": 9.989338496574013e-05, "loss": 0.0246, "step": 1480 }, { "epoch": 0.8375491849353569, "grad_norm": 0.2511518661704276, "learning_rate": 9.988404069128286e-05, "loss": 0.0241, "step": 1490 }, { "epoch": 0.8431703204047217, "grad_norm": 0.24275092866635561, "learning_rate": 9.987430442018787e-05, "loss": 0.0231, "step": 1500 }, { "epoch": 0.8487914558740866, "grad_norm": 0.2117797837985066, "learning_rate": 9.986417622896433e-05, "loss": 0.0222, "step": 1510 }, { "epoch": 0.8544125913434514, "grad_norm": 0.23706464693081078, "learning_rate": 9.985365619720114e-05, "loss": 0.0224, "step": 1520 }, { "epoch": 0.8600337268128162, "grad_norm": 0.21681891631644465, "learning_rate": 9.984274440756639e-05, "loss": 0.0216, "step": 1530 }, { "epoch": 0.865654862282181, "grad_norm": 0.21895203687881423, "learning_rate": 9.983144094580662e-05, "loss": 0.0205, "step": 1540 }, { "epoch": 0.8712759977515458, "grad_norm": 0.20958525636292016, "learning_rate": 9.981974590074623e-05, "loss": 0.0197, "step": 1550 }, { "epoch": 0.8768971332209107, "grad_norm": 0.2092568671749629, "learning_rate": 9.980765936428668e-05, "loss": 0.0192, "step": 1560 }, { "epoch": 0.8825182686902754, "grad_norm": 0.20242771809585056, "learning_rate": 9.979518143140591e-05, "loss": 0.0186, "step": 1570 }, { "epoch": 0.8881394041596402, "grad_norm": 0.2067518737526698, "learning_rate": 9.97823122001575e-05, "loss": 0.0184, "step": 1580 }, { "epoch": 0.893760539629005, "grad_norm": 0.2131831404574167, "learning_rate": 9.976905177166984e-05, "loss": 0.0179, "step": 1590 }, { "epoch": 0.8993816750983699, "grad_norm": 0.19975090191123349, "learning_rate": 9.975540025014551e-05, "loss": 0.0171, "step": 1600 }, { "epoch": 0.9050028105677347, "grad_norm": 0.1840388312874417, "learning_rate": 9.974135774286027e-05, "loss": 0.0167, "step": 1610 }, { "epoch": 0.9106239460370995, "grad_norm": 0.16080844246323525, "learning_rate": 9.972692436016237e-05, "loss": 0.0162, "step": 1620 }, { "epoch": 0.9162450815064643, "grad_norm": 0.7406842420136835, "learning_rate": 9.971210021547163e-05, "loss": 0.0164, "step": 1630 }, { "epoch": 0.9218662169758292, "grad_norm": 0.6842280048869254, "learning_rate": 9.969688542527847e-05, "loss": 0.0185, "step": 1640 }, { "epoch": 0.927487352445194, "grad_norm": 1.580555984265757, "learning_rate": 9.968128010914313e-05, "loss": 0.0316, "step": 1650 }, { "epoch": 0.9331084879145587, "grad_norm": 0.37860426611015985, "learning_rate": 9.966528438969462e-05, "loss": 0.0249, "step": 1660 }, { "epoch": 0.9387296233839235, "grad_norm": 0.23262955055081527, "learning_rate": 9.964889839262983e-05, "loss": 0.0186, "step": 1670 }, { "epoch": 0.9443507588532883, "grad_norm": 0.20273477480045216, "learning_rate": 9.963212224671249e-05, "loss": 0.0161, "step": 1680 }, { "epoch": 0.9499718943226532, "grad_norm": 0.13881800111147724, "learning_rate": 9.961495608377221e-05, "loss": 0.0148, "step": 1690 }, { "epoch": 0.955593029792018, "grad_norm": 0.17108269648499383, "learning_rate": 9.959740003870339e-05, "loss": 0.0144, "step": 1700 }, { "epoch": 0.9612141652613828, "grad_norm": 0.16536831484992337, "learning_rate": 9.95794542494642e-05, "loss": 0.0137, "step": 1710 }, { "epoch": 0.9668353007307476, "grad_norm": 0.17400543803234356, "learning_rate": 9.956111885707546e-05, "loss": 0.0131, "step": 1720 }, { "epoch": 0.9724564362001125, "grad_norm": 0.14754960398432485, "learning_rate": 9.954239400561958e-05, "loss": 0.0126, "step": 1730 }, { "epoch": 0.9780775716694773, "grad_norm": 0.13872283525841225, "learning_rate": 9.952327984223938e-05, "loss": 0.012, "step": 1740 }, { "epoch": 0.983698707138842, "grad_norm": 0.15345071148869308, "learning_rate": 9.950377651713698e-05, "loss": 0.0119, "step": 1750 }, { "epoch": 0.9893198426082068, "grad_norm": 0.15868096773505136, "learning_rate": 9.948388418357255e-05, "loss": 0.0117, "step": 1760 }, { "epoch": 0.9949409780775716, "grad_norm": 0.13964728528048598, "learning_rate": 9.94636029978632e-05, "loss": 0.0111, "step": 1770 }, { "epoch": 1.0005621135469365, "grad_norm": 0.12990131986586648, "learning_rate": 9.944293311938164e-05, "loss": 0.0111, "step": 1780 }, { "epoch": 1.0061832490163012, "grad_norm": 0.15109117991919174, "learning_rate": 9.942187471055507e-05, "loss": 0.0106, "step": 1790 }, { "epoch": 1.0118043844856661, "grad_norm": 0.15023868490530576, "learning_rate": 9.940042793686378e-05, "loss": 0.0101, "step": 1800 }, { "epoch": 1.0174255199550308, "grad_norm": 0.13748040160742883, "learning_rate": 9.937859296683984e-05, "loss": 0.0098, "step": 1810 }, { "epoch": 1.0230466554243958, "grad_norm": 0.13694721938981147, "learning_rate": 9.935636997206592e-05, "loss": 0.0099, "step": 1820 }, { "epoch": 1.0286677908937605, "grad_norm": 0.13775398006820014, "learning_rate": 9.933375912717379e-05, "loss": 0.0096, "step": 1830 }, { "epoch": 1.0342889263631254, "grad_norm": 0.12873175645779594, "learning_rate": 9.931076060984306e-05, "loss": 0.0094, "step": 1840 }, { "epoch": 1.0399100618324901, "grad_norm": 0.13491704932600562, "learning_rate": 9.928737460079964e-05, "loss": 0.0093, "step": 1850 }, { "epoch": 1.045531197301855, "grad_norm": 0.13052217132802058, "learning_rate": 9.926360128381452e-05, "loss": 0.0089, "step": 1860 }, { "epoch": 1.0511523327712198, "grad_norm": 0.15139988915587, "learning_rate": 9.923944084570214e-05, "loss": 0.0089, "step": 1870 }, { "epoch": 1.0567734682405847, "grad_norm": 0.11412503222119044, "learning_rate": 9.9214893476319e-05, "loss": 0.0085, "step": 1880 }, { "epoch": 1.0623946037099494, "grad_norm": 0.13727989640704788, "learning_rate": 9.918995936856224e-05, "loss": 0.0085, "step": 1890 }, { "epoch": 1.0680157391793141, "grad_norm": 0.1249207256562971, "learning_rate": 9.916463871836796e-05, "loss": 0.0084, "step": 1900 }, { "epoch": 1.073636874648679, "grad_norm": 0.12406222038106689, "learning_rate": 9.913893172470982e-05, "loss": 0.0081, "step": 1910 }, { "epoch": 1.0792580101180438, "grad_norm": 0.13127597326529594, "learning_rate": 9.911283858959746e-05, "loss": 0.0083, "step": 1920 }, { "epoch": 1.0848791455874087, "grad_norm": 0.1368675589547782, "learning_rate": 9.908635951807477e-05, "loss": 0.0082, "step": 1930 }, { "epoch": 1.0905002810567734, "grad_norm": 0.1172965848549566, "learning_rate": 9.905949471821851e-05, "loss": 0.008, "step": 1940 }, { "epoch": 1.0961214165261384, "grad_norm": 0.11798553949395943, "learning_rate": 9.903224440113649e-05, "loss": 0.008, "step": 1950 }, { "epoch": 1.101742551995503, "grad_norm": 0.13016996611164902, "learning_rate": 9.900460878096598e-05, "loss": 0.0078, "step": 1960 }, { "epoch": 1.107363687464868, "grad_norm": 0.12122199750464839, "learning_rate": 9.897658807487202e-05, "loss": 0.0077, "step": 1970 }, { "epoch": 1.1129848229342327, "grad_norm": 0.11846619937347036, "learning_rate": 9.894818250304576e-05, "loss": 0.0075, "step": 1980 }, { "epoch": 1.1186059584035974, "grad_norm": 0.13622498242403422, "learning_rate": 9.891939228870261e-05, "loss": 0.0076, "step": 1990 }, { "epoch": 1.1242270938729624, "grad_norm": 0.1132057504919735, "learning_rate": 9.889021765808064e-05, "loss": 0.0076, "step": 2000 }, { "epoch": 1.129848229342327, "grad_norm": 0.12782091049281527, "learning_rate": 9.886065884043868e-05, "loss": 0.0076, "step": 2010 }, { "epoch": 1.135469364811692, "grad_norm": 0.1327283957213651, "learning_rate": 9.883071606805454e-05, "loss": 0.0072, "step": 2020 }, { "epoch": 1.1410905002810567, "grad_norm": 0.11466155852542638, "learning_rate": 9.880038957622327e-05, "loss": 0.0074, "step": 2030 }, { "epoch": 1.1467116357504217, "grad_norm": 0.1248526409625004, "learning_rate": 9.876967960325518e-05, "loss": 0.0071, "step": 2040 }, { "epoch": 1.1523327712197864, "grad_norm": 0.12458128006542332, "learning_rate": 9.873858639047409e-05, "loss": 0.0069, "step": 2050 }, { "epoch": 1.1579539066891513, "grad_norm": 0.11664744118592543, "learning_rate": 9.870711018221535e-05, "loss": 0.0066, "step": 2060 }, { "epoch": 1.163575042158516, "grad_norm": 0.12050522669971526, "learning_rate": 9.867525122582394e-05, "loss": 0.0068, "step": 2070 }, { "epoch": 1.1691961776278808, "grad_norm": 0.13065303841446785, "learning_rate": 9.864300977165259e-05, "loss": 0.0067, "step": 2080 }, { "epoch": 1.1748173130972457, "grad_norm": 0.10805422192260604, "learning_rate": 9.861038607305968e-05, "loss": 0.0066, "step": 2090 }, { "epoch": 1.1804384485666104, "grad_norm": 0.11507644557756966, "learning_rate": 9.857738038640737e-05, "loss": 0.0063, "step": 2100 }, { "epoch": 1.1860595840359753, "grad_norm": 0.10761515703888919, "learning_rate": 9.854399297105957e-05, "loss": 0.0061, "step": 2110 }, { "epoch": 1.19168071950534, "grad_norm": 0.12594601810241263, "learning_rate": 9.851022408937979e-05, "loss": 0.0067, "step": 2120 }, { "epoch": 1.197301854974705, "grad_norm": 0.12986420025775458, "learning_rate": 9.847607400672925e-05, "loss": 0.0065, "step": 2130 }, { "epoch": 1.2029229904440697, "grad_norm": 0.10577243861744662, "learning_rate": 9.844154299146466e-05, "loss": 0.0062, "step": 2140 }, { "epoch": 1.2085441259134346, "grad_norm": 0.11560521707742587, "learning_rate": 9.840663131493617e-05, "loss": 0.0063, "step": 2150 }, { "epoch": 1.2141652613827993, "grad_norm": 0.12172276197577853, "learning_rate": 9.837133925148523e-05, "loss": 0.006, "step": 2160 }, { "epoch": 1.219786396852164, "grad_norm": 0.11989705951251413, "learning_rate": 9.833566707844241e-05, "loss": 0.0061, "step": 2170 }, { "epoch": 1.225407532321529, "grad_norm": 0.12073736751173343, "learning_rate": 9.829961507612526e-05, "loss": 0.0062, "step": 2180 }, { "epoch": 1.2310286677908937, "grad_norm": 0.10581806093891255, "learning_rate": 9.82631835278361e-05, "loss": 0.006, "step": 2190 }, { "epoch": 1.2366498032602586, "grad_norm": 0.12350567107631101, "learning_rate": 9.822637271985977e-05, "loss": 0.0058, "step": 2200 }, { "epoch": 1.2422709387296234, "grad_norm": 0.10706106863986312, "learning_rate": 9.818918294146136e-05, "loss": 0.0055, "step": 2210 }, { "epoch": 1.2478920741989883, "grad_norm": 0.11497496683839335, "learning_rate": 9.815161448488403e-05, "loss": 0.0059, "step": 2220 }, { "epoch": 1.253513209668353, "grad_norm": 0.1230577251222716, "learning_rate": 9.81136676453466e-05, "loss": 0.0056, "step": 2230 }, { "epoch": 1.259134345137718, "grad_norm": 0.11408509041104613, "learning_rate": 9.80753427210413e-05, "loss": 0.0058, "step": 2240 }, { "epoch": 1.2647554806070826, "grad_norm": 0.13501233611835498, "learning_rate": 9.803664001313142e-05, "loss": 0.0057, "step": 2250 }, { "epoch": 1.2703766160764474, "grad_norm": 0.09995034213120912, "learning_rate": 9.799755982574894e-05, "loss": 0.0057, "step": 2260 }, { "epoch": 1.2759977515458123, "grad_norm": 0.10016312243592881, "learning_rate": 9.79581024659921e-05, "loss": 0.0055, "step": 2270 }, { "epoch": 1.281618887015177, "grad_norm": 0.12356597886645763, "learning_rate": 9.791826824392305e-05, "loss": 0.0056, "step": 2280 }, { "epoch": 1.287240022484542, "grad_norm": 0.10251488515673644, "learning_rate": 9.787805747256536e-05, "loss": 0.0055, "step": 2290 }, { "epoch": 1.2928611579539067, "grad_norm": 0.10694624192420116, "learning_rate": 9.783747046790162e-05, "loss": 0.0054, "step": 2300 }, { "epoch": 1.2984822934232714, "grad_norm": 0.0837306764941164, "learning_rate": 9.779650754887086e-05, "loss": 0.0052, "step": 2310 }, { "epoch": 1.3041034288926363, "grad_norm": 0.12536680825139915, "learning_rate": 9.775516903736616e-05, "loss": 0.0053, "step": 2320 }, { "epoch": 1.3097245643620012, "grad_norm": 0.09801113540564874, "learning_rate": 9.771345525823208e-05, "loss": 0.0053, "step": 2330 }, { "epoch": 1.315345699831366, "grad_norm": 0.3194597362808477, "learning_rate": 9.767136653926199e-05, "loss": 0.0055, "step": 2340 }, { "epoch": 1.3209668353007307, "grad_norm": 1.8141673380574084, "learning_rate": 9.762890321119572e-05, "loss": 0.0263, "step": 2350 }, { "epoch": 1.3265879707700956, "grad_norm": 2.0373228278291986, "learning_rate": 9.758606560771675e-05, "loss": 0.0595, "step": 2360 }, { "epoch": 1.3322091062394603, "grad_norm": 0.24089249295422568, "learning_rate": 9.754285406544969e-05, "loss": 0.0223, "step": 2370 }, { "epoch": 1.3378302417088253, "grad_norm": 0.14596942738787602, "learning_rate": 9.749926892395768e-05, "loss": 0.0095, "step": 2380 }, { "epoch": 1.34345137717819, "grad_norm": 0.11444722263474487, "learning_rate": 9.745531052573961e-05, "loss": 0.0072, "step": 2390 }, { "epoch": 1.3490725126475547, "grad_norm": 0.0997521525083771, "learning_rate": 9.741097921622746e-05, "loss": 0.0063, "step": 2400 }, { "epoch": 1.3546936481169196, "grad_norm": 0.10164810149706918, "learning_rate": 9.736627534378364e-05, "loss": 0.0058, "step": 2410 }, { "epoch": 1.3603147835862845, "grad_norm": 0.10637858866117042, "learning_rate": 9.732119925969823e-05, "loss": 0.0055, "step": 2420 }, { "epoch": 1.3659359190556493, "grad_norm": 0.1154184870469501, "learning_rate": 9.727575131818617e-05, "loss": 0.0052, "step": 2430 }, { "epoch": 1.371557054525014, "grad_norm": 0.09812174226964852, "learning_rate": 9.722993187638454e-05, "loss": 0.0051, "step": 2440 }, { "epoch": 1.377178189994379, "grad_norm": 0.08717591400124859, "learning_rate": 9.718374129434971e-05, "loss": 0.0051, "step": 2450 }, { "epoch": 1.3827993254637436, "grad_norm": 0.08608962077541132, "learning_rate": 9.713717993505456e-05, "loss": 0.0049, "step": 2460 }, { "epoch": 1.3884204609331086, "grad_norm": 0.10182986875302574, "learning_rate": 9.709024816438555e-05, "loss": 0.0047, "step": 2470 }, { "epoch": 1.3940415964024733, "grad_norm": 0.10115287527791918, "learning_rate": 9.704294635113993e-05, "loss": 0.0049, "step": 2480 }, { "epoch": 1.399662731871838, "grad_norm": 0.0784538159472712, "learning_rate": 9.69952748670228e-05, "loss": 0.0048, "step": 2490 }, { "epoch": 1.405283867341203, "grad_norm": 0.0776387928340622, "learning_rate": 9.694723408664414e-05, "loss": 0.0044, "step": 2500 }, { "epoch": 1.4109050028105679, "grad_norm": 0.0837732573729813, "learning_rate": 9.689882438751601e-05, "loss": 0.0046, "step": 2510 }, { "epoch": 1.4165261382799326, "grad_norm": 0.09489114181755515, "learning_rate": 9.68500461500494e-05, "loss": 0.0046, "step": 2520 }, { "epoch": 1.4221472737492973, "grad_norm": 0.101494695984547, "learning_rate": 9.680089975755139e-05, "loss": 0.0045, "step": 2530 }, { "epoch": 1.4277684092186622, "grad_norm": 0.08821477058203668, "learning_rate": 9.675138559622205e-05, "loss": 0.0043, "step": 2540 }, { "epoch": 1.433389544688027, "grad_norm": 0.07881075966273893, "learning_rate": 9.670150405515147e-05, "loss": 0.0044, "step": 2550 }, { "epoch": 1.4390106801573919, "grad_norm": 0.09899683557846178, "learning_rate": 9.665125552631662e-05, "loss": 0.0043, "step": 2560 }, { "epoch": 1.4446318156267566, "grad_norm": 0.08629556264118085, "learning_rate": 9.660064040457837e-05, "loss": 0.0044, "step": 2570 }, { "epoch": 1.4502529510961213, "grad_norm": 0.09415390850669993, "learning_rate": 9.654965908767827e-05, "loss": 0.0044, "step": 2580 }, { "epoch": 1.4558740865654862, "grad_norm": 0.09596874126004533, "learning_rate": 9.649831197623556e-05, "loss": 0.0043, "step": 2590 }, { "epoch": 1.4614952220348512, "grad_norm": 0.09072868361315219, "learning_rate": 9.64465994737439e-05, "loss": 0.0041, "step": 2600 }, { "epoch": 1.4671163575042159, "grad_norm": 0.08557262009476094, "learning_rate": 9.639452198656828e-05, "loss": 0.0041, "step": 2610 }, { "epoch": 1.4727374929735806, "grad_norm": 0.08310295695036411, "learning_rate": 9.634207992394178e-05, "loss": 0.0041, "step": 2620 }, { "epoch": 1.4783586284429455, "grad_norm": 0.09055939067871042, "learning_rate": 9.628927369796236e-05, "loss": 0.0041, "step": 2630 }, { "epoch": 1.4839797639123102, "grad_norm": 0.09604647791927998, "learning_rate": 9.623610372358969e-05, "loss": 0.0042, "step": 2640 }, { "epoch": 1.4896008993816752, "grad_norm": 0.08577660993704818, "learning_rate": 9.618257041864176e-05, "loss": 0.0043, "step": 2650 }, { "epoch": 1.4952220348510399, "grad_norm": 0.09123279036915018, "learning_rate": 9.61286742037917e-05, "loss": 0.0041, "step": 2660 }, { "epoch": 1.5008431703204046, "grad_norm": 0.08260166738909931, "learning_rate": 9.607441550256445e-05, "loss": 0.0039, "step": 2670 }, { "epoch": 1.5064643057897695, "grad_norm": 0.07923250866368316, "learning_rate": 9.601979474133343e-05, "loss": 0.004, "step": 2680 }, { "epoch": 1.5120854412591345, "grad_norm": 0.08239031912656816, "learning_rate": 9.596481234931713e-05, "loss": 0.0038, "step": 2690 }, { "epoch": 1.5177065767284992, "grad_norm": 0.07610828082112323, "learning_rate": 9.59094687585759e-05, "loss": 0.0039, "step": 2700 }, { "epoch": 1.523327712197864, "grad_norm": 0.11252793520644211, "learning_rate": 9.585376440400833e-05, "loss": 0.0041, "step": 2710 }, { "epoch": 1.5289488476672288, "grad_norm": 0.09330378622902911, "learning_rate": 9.579769972334802e-05, "loss": 0.004, "step": 2720 }, { "epoch": 1.5345699831365935, "grad_norm": 0.07857369281450616, "learning_rate": 9.574127515716004e-05, "loss": 0.0039, "step": 2730 }, { "epoch": 1.5401911186059585, "grad_norm": 0.07210626541279375, "learning_rate": 9.56844911488375e-05, "loss": 0.0038, "step": 2740 }, { "epoch": 1.5458122540753232, "grad_norm": 0.07707927197752867, "learning_rate": 9.562734814459811e-05, "loss": 0.0038, "step": 2750 }, { "epoch": 1.551433389544688, "grad_norm": 0.08248750325983276, "learning_rate": 9.556984659348052e-05, "loss": 0.0039, "step": 2760 }, { "epoch": 1.5570545250140528, "grad_norm": 0.08508167021142606, "learning_rate": 9.551198694734102e-05, "loss": 0.0039, "step": 2770 }, { "epoch": 1.5626756604834178, "grad_norm": 0.08080512980956885, "learning_rate": 9.545376966084977e-05, "loss": 0.0038, "step": 2780 }, { "epoch": 1.5682967959527825, "grad_norm": 0.09346422370365523, "learning_rate": 9.539519519148738e-05, "loss": 0.0037, "step": 2790 }, { "epoch": 1.5739179314221472, "grad_norm": 0.08917779155675297, "learning_rate": 9.533626399954126e-05, "loss": 0.0036, "step": 2800 }, { "epoch": 1.5795390668915121, "grad_norm": 0.06721304489449485, "learning_rate": 9.527697654810195e-05, "loss": 0.0035, "step": 2810 }, { "epoch": 1.5851602023608768, "grad_norm": 0.07427558428573001, "learning_rate": 9.52173333030596e-05, "loss": 0.0036, "step": 2820 }, { "epoch": 1.5907813378302418, "grad_norm": 0.08659228174058138, "learning_rate": 9.515733473310019e-05, "loss": 0.0036, "step": 2830 }, { "epoch": 1.5964024732996065, "grad_norm": 0.0719969223939997, "learning_rate": 9.509698130970193e-05, "loss": 0.0036, "step": 2840 }, { "epoch": 1.6020236087689712, "grad_norm": 0.08181084829875987, "learning_rate": 9.50362735071315e-05, "loss": 0.0034, "step": 2850 }, { "epoch": 1.6076447442383361, "grad_norm": 0.0894284800559242, "learning_rate": 9.497521180244038e-05, "loss": 0.0035, "step": 2860 }, { "epoch": 1.613265879707701, "grad_norm": 0.08282207277574022, "learning_rate": 9.491379667546104e-05, "loss": 0.0034, "step": 2870 }, { "epoch": 1.6188870151770658, "grad_norm": 0.145986818674443, "learning_rate": 9.485202860880321e-05, "loss": 0.0037, "step": 2880 }, { "epoch": 1.6245081506464305, "grad_norm": 0.08546744479627431, "learning_rate": 9.478990808785006e-05, "loss": 0.0036, "step": 2890 }, { "epoch": 1.6301292861157954, "grad_norm": 0.08759751416458819, "learning_rate": 9.472743560075446e-05, "loss": 0.0034, "step": 2900 }, { "epoch": 1.6357504215851602, "grad_norm": 0.07818496950657797, "learning_rate": 9.466461163843497e-05, "loss": 0.0033, "step": 2910 }, { "epoch": 1.641371557054525, "grad_norm": 0.07598460655098531, "learning_rate": 9.460143669457221e-05, "loss": 0.0034, "step": 2920 }, { "epoch": 1.6469926925238898, "grad_norm": 0.07204405112584633, "learning_rate": 9.453791126560482e-05, "loss": 0.0033, "step": 2930 }, { "epoch": 1.6526138279932545, "grad_norm": 0.07548100465060122, "learning_rate": 9.44740358507256e-05, "loss": 0.0033, "step": 2940 }, { "epoch": 1.6582349634626194, "grad_norm": 0.07627624404632878, "learning_rate": 9.440981095187764e-05, "loss": 0.0034, "step": 2950 }, { "epoch": 1.6638560989319844, "grad_norm": 0.07801223336358269, "learning_rate": 9.434523707375024e-05, "loss": 0.0033, "step": 2960 }, { "epoch": 1.669477234401349, "grad_norm": 0.07014240339623043, "learning_rate": 9.428031472377516e-05, "loss": 0.0031, "step": 2970 }, { "epoch": 1.6750983698707138, "grad_norm": 0.0725952595345933, "learning_rate": 9.421504441212238e-05, "loss": 0.0032, "step": 2980 }, { "epoch": 1.6807195053400787, "grad_norm": 0.08432049334212283, "learning_rate": 9.414942665169631e-05, "loss": 0.0032, "step": 2990 }, { "epoch": 1.6863406408094435, "grad_norm": 0.07105741598976323, "learning_rate": 9.408346195813159e-05, "loss": 0.0034, "step": 3000 }, { "epoch": 1.6919617762788084, "grad_norm": 0.13906184784395983, "learning_rate": 9.401715084978922e-05, "loss": 0.0052, "step": 3010 }, { "epoch": 1.697582911748173, "grad_norm": 0.11601157873012202, "learning_rate": 9.395049384775225e-05, "loss": 0.0042, "step": 3020 }, { "epoch": 1.7032040472175378, "grad_norm": 0.09015124532353191, "learning_rate": 9.388349147582194e-05, "loss": 0.0037, "step": 3030 }, { "epoch": 1.7088251826869028, "grad_norm": 0.07000264697695573, "learning_rate": 9.381614426051344e-05, "loss": 0.0034, "step": 3040 }, { "epoch": 1.7144463181562677, "grad_norm": 0.08113336516882994, "learning_rate": 9.374845273105177e-05, "loss": 0.0033, "step": 3050 }, { "epoch": 1.7200674536256324, "grad_norm": 0.08261811708445045, "learning_rate": 9.368041741936762e-05, "loss": 0.0033, "step": 3060 }, { "epoch": 1.7256885890949971, "grad_norm": 0.07838609207688987, "learning_rate": 9.361203886009316e-05, "loss": 0.0033, "step": 3070 }, { "epoch": 1.731309724564362, "grad_norm": 0.08665499355732291, "learning_rate": 9.354331759055787e-05, "loss": 0.0033, "step": 3080 }, { "epoch": 1.7369308600337268, "grad_norm": 0.07918424347748348, "learning_rate": 9.347425415078427e-05, "loss": 0.0034, "step": 3090 }, { "epoch": 1.7425519955030917, "grad_norm": 0.08191128168223484, "learning_rate": 9.34048490834838e-05, "loss": 0.0031, "step": 3100 }, { "epoch": 1.7481731309724564, "grad_norm": 0.0759010615813787, "learning_rate": 9.333510293405231e-05, "loss": 0.003, "step": 3110 }, { "epoch": 1.7537942664418211, "grad_norm": 0.08477221828549904, "learning_rate": 9.326501625056606e-05, "loss": 0.0031, "step": 3120 }, { "epoch": 1.759415401911186, "grad_norm": 0.08622296059752232, "learning_rate": 9.319458958377723e-05, "loss": 0.0032, "step": 3130 }, { "epoch": 1.765036537380551, "grad_norm": 0.07276169675225246, "learning_rate": 9.312382348710962e-05, "loss": 0.0031, "step": 3140 }, { "epoch": 1.7706576728499157, "grad_norm": 0.07298764401064435, "learning_rate": 9.305271851665438e-05, "loss": 0.0031, "step": 3150 }, { "epoch": 1.7762788083192804, "grad_norm": 0.0765870165752984, "learning_rate": 9.298127523116555e-05, "loss": 0.003, "step": 3160 }, { "epoch": 1.7818999437886454, "grad_norm": 0.0963853743897375, "learning_rate": 9.290949419205567e-05, "loss": 0.0032, "step": 3170 }, { "epoch": 1.78752107925801, "grad_norm": 0.08167306430005795, "learning_rate": 9.283737596339147e-05, "loss": 0.003, "step": 3180 }, { "epoch": 1.793142214727375, "grad_norm": 0.07386683946543225, "learning_rate": 9.276492111188933e-05, "loss": 0.0029, "step": 3190 }, { "epoch": 1.7987633501967397, "grad_norm": 0.079496491310148, "learning_rate": 9.269213020691083e-05, "loss": 0.003, "step": 3200 }, { "epoch": 1.8043844856661044, "grad_norm": 0.08006049495470177, "learning_rate": 9.261900382045841e-05, "loss": 0.003, "step": 3210 }, { "epoch": 1.8100056211354694, "grad_norm": 0.06946915908105838, "learning_rate": 9.254554252717067e-05, "loss": 0.003, "step": 3220 }, { "epoch": 1.8156267566048343, "grad_norm": 0.06692045669453084, "learning_rate": 9.247174690431803e-05, "loss": 0.0028, "step": 3230 }, { "epoch": 1.821247892074199, "grad_norm": 0.06938244252654852, "learning_rate": 9.23976175317981e-05, "loss": 0.0029, "step": 3240 }, { "epoch": 1.8268690275435637, "grad_norm": 0.0677124057287239, "learning_rate": 9.232315499213114e-05, "loss": 0.0028, "step": 3250 }, { "epoch": 1.8324901630129287, "grad_norm": 0.0659706764858958, "learning_rate": 9.224835987045549e-05, "loss": 0.0027, "step": 3260 }, { "epoch": 1.8381112984822934, "grad_norm": 0.07797163812538724, "learning_rate": 9.217323275452301e-05, "loss": 0.0029, "step": 3270 }, { "epoch": 1.8437324339516583, "grad_norm": 0.06371412754471345, "learning_rate": 9.209777423469436e-05, "loss": 0.0027, "step": 3280 }, { "epoch": 1.849353569421023, "grad_norm": 0.07195198600776227, "learning_rate": 9.202198490393448e-05, "loss": 0.0027, "step": 3290 }, { "epoch": 1.8549747048903877, "grad_norm": 0.09032730876019279, "learning_rate": 9.194586535780785e-05, "loss": 0.0027, "step": 3300 }, { "epoch": 1.8605958403597527, "grad_norm": 0.07184863572635682, "learning_rate": 9.186941619447382e-05, "loss": 0.0028, "step": 3310 }, { "epoch": 1.8662169758291176, "grad_norm": 0.07972046752123726, "learning_rate": 9.179263801468196e-05, "loss": 0.0028, "step": 3320 }, { "epoch": 1.8718381112984823, "grad_norm": 0.06462786356243252, "learning_rate": 9.171553142176725e-05, "loss": 0.0026, "step": 3330 }, { "epoch": 1.877459246767847, "grad_norm": 0.0748752457223882, "learning_rate": 9.163809702164547e-05, "loss": 0.0028, "step": 3340 }, { "epoch": 1.883080382237212, "grad_norm": 0.06644669684356859, "learning_rate": 9.156033542280829e-05, "loss": 0.0027, "step": 3350 }, { "epoch": 1.8887015177065767, "grad_norm": 0.06481410104589969, "learning_rate": 9.148224723631858e-05, "loss": 0.0028, "step": 3360 }, { "epoch": 1.8943226531759416, "grad_norm": 0.07493396927909493, "learning_rate": 9.14038330758056e-05, "loss": 0.0028, "step": 3370 }, { "epoch": 1.8999437886453063, "grad_norm": 0.07930938338708406, "learning_rate": 9.132509355746016e-05, "loss": 0.0028, "step": 3380 }, { "epoch": 1.905564924114671, "grad_norm": 0.0703227155299206, "learning_rate": 9.124602930002977e-05, "loss": 0.0027, "step": 3390 }, { "epoch": 1.911186059584036, "grad_norm": 0.06415414989508922, "learning_rate": 9.11666409248138e-05, "loss": 0.0027, "step": 3400 }, { "epoch": 1.916807195053401, "grad_norm": 0.05989446878848808, "learning_rate": 9.10869290556586e-05, "loss": 0.0026, "step": 3410 }, { "epoch": 1.9224283305227656, "grad_norm": 0.06596944372327754, "learning_rate": 9.100689431895257e-05, "loss": 0.0026, "step": 3420 }, { "epoch": 1.9280494659921303, "grad_norm": 0.06839374667585654, "learning_rate": 9.092653734362126e-05, "loss": 0.0025, "step": 3430 }, { "epoch": 1.9336706014614953, "grad_norm": 0.05902981335451462, "learning_rate": 9.084585876112241e-05, "loss": 0.0025, "step": 3440 }, { "epoch": 1.93929173693086, "grad_norm": 0.06610787957287352, "learning_rate": 9.076485920544105e-05, "loss": 0.0027, "step": 3450 }, { "epoch": 1.944912872400225, "grad_norm": 0.08257300358198327, "learning_rate": 9.068353931308437e-05, "loss": 0.0027, "step": 3460 }, { "epoch": 1.9505340078695896, "grad_norm": 0.0643606698153111, "learning_rate": 9.060189972307691e-05, "loss": 0.0025, "step": 3470 }, { "epoch": 1.9561551433389543, "grad_norm": 0.06558027003590208, "learning_rate": 9.051994107695541e-05, "loss": 0.0025, "step": 3480 }, { "epoch": 1.9617762788083193, "grad_norm": 0.0752177480017892, "learning_rate": 9.043766401876376e-05, "loss": 0.0024, "step": 3490 }, { "epoch": 1.9673974142776842, "grad_norm": 0.07854251356309212, "learning_rate": 9.03550691950481e-05, "loss": 0.0026, "step": 3500 }, { "epoch": 1.973018549747049, "grad_norm": 0.07298249855242128, "learning_rate": 9.027215725485148e-05, "loss": 0.0026, "step": 3510 }, { "epoch": 1.9786396852164136, "grad_norm": 0.08010026435433024, "learning_rate": 9.018892884970899e-05, "loss": 0.0026, "step": 3520 }, { "epoch": 1.9842608206857786, "grad_norm": 0.06202515462439953, "learning_rate": 9.010538463364256e-05, "loss": 0.0024, "step": 3530 }, { "epoch": 1.9898819561551433, "grad_norm": 0.0638298747620675, "learning_rate": 9.002152526315571e-05, "loss": 0.0025, "step": 3540 }, { "epoch": 1.9955030916245082, "grad_norm": 0.05989999228664472, "learning_rate": 8.993735139722862e-05, "loss": 0.0024, "step": 3550 }, { "epoch": 2.001124227093873, "grad_norm": 0.058109118290538206, "learning_rate": 8.985286369731275e-05, "loss": 0.0024, "step": 3560 }, { "epoch": 2.0067453625632377, "grad_norm": 0.057457616331219645, "learning_rate": 8.976806282732572e-05, "loss": 0.0019, "step": 3570 }, { "epoch": 2.0123664980326024, "grad_norm": 0.05651975998498543, "learning_rate": 8.968294945364613e-05, "loss": 0.002, "step": 3580 }, { "epoch": 2.0179876335019675, "grad_norm": 0.05599584314470216, "learning_rate": 8.959752424510824e-05, "loss": 0.0021, "step": 3590 }, { "epoch": 2.0236087689713322, "grad_norm": 0.06816841901562025, "learning_rate": 8.951178787299679e-05, "loss": 0.0018, "step": 3600 } ], "logging_steps": 10, "max_steps": 12453, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 1800, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 293610919034880.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }