{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 39.0, "eval_steps": 500, "global_step": 1404, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.028169014084507043, "grad_norm": 6.119271278381348, "learning_rate": 9.999993146109795e-07, "loss": 0.7189172506332397, "step": 1 }, { "epoch": 0.056338028169014086, "grad_norm": 6.210888862609863, "learning_rate": 9.999972584460056e-07, "loss": 0.7133427262306213, "step": 2 }, { "epoch": 0.08450704225352113, "grad_norm": 6.092806816101074, "learning_rate": 9.99993831511342e-07, "loss": 0.7074416875839233, "step": 3 }, { "epoch": 0.11267605633802817, "grad_norm": 5.97125768661499, "learning_rate": 9.999890338174275e-07, "loss": 0.732918381690979, "step": 4 }, { "epoch": 0.14084507042253522, "grad_norm": 5.2337870597839355, "learning_rate": 9.99982865378877e-07, "loss": 0.6883118152618408, "step": 5 }, { "epoch": 0.16901408450704225, "grad_norm": 5.282492160797119, "learning_rate": 9.999753262144804e-07, "loss": 0.7119431495666504, "step": 6 }, { "epoch": 0.19718309859154928, "grad_norm": 5.101883888244629, "learning_rate": 9.999664163472034e-07, "loss": 0.676694929599762, "step": 7 }, { "epoch": 0.22535211267605634, "grad_norm": 5.041009426116943, "learning_rate": 9.999561358041868e-07, "loss": 0.6787284016609192, "step": 8 }, { "epoch": 0.2535211267605634, "grad_norm": 3.952293634414673, "learning_rate": 9.99944484616747e-07, "loss": 0.6841624975204468, "step": 9 }, { "epoch": 0.28169014084507044, "grad_norm": 3.8667240142822266, "learning_rate": 9.99931462820376e-07, "loss": 0.6778519749641418, "step": 10 }, { "epoch": 0.30985915492957744, "grad_norm": 3.7240049839019775, "learning_rate": 9.999170704547398e-07, "loss": 0.6599913835525513, "step": 11 }, { "epoch": 0.3380281690140845, "grad_norm": 3.7257325649261475, "learning_rate": 9.999013075636804e-07, "loss": 0.6581519246101379, "step": 12 }, { "epoch": 0.36619718309859156, "grad_norm": 3.390742301940918, "learning_rate": 9.998841741952141e-07, "loss": 0.6533472537994385, "step": 13 }, { "epoch": 0.39436619718309857, "grad_norm": 3.5247814655303955, "learning_rate": 9.998656704015323e-07, "loss": 0.6778960227966309, "step": 14 }, { "epoch": 0.4225352112676056, "grad_norm": 3.3745362758636475, "learning_rate": 9.998457962390008e-07, "loss": 0.647881031036377, "step": 15 }, { "epoch": 0.4507042253521127, "grad_norm": 3.357809066772461, "learning_rate": 9.998245517681593e-07, "loss": 0.6600426435470581, "step": 16 }, { "epoch": 0.4788732394366197, "grad_norm": 2.0050694942474365, "learning_rate": 9.998019370537227e-07, "loss": 0.6223803758621216, "step": 17 }, { "epoch": 0.5070422535211268, "grad_norm": 1.9662013053894043, "learning_rate": 9.997779521645791e-07, "loss": 0.6141380071640015, "step": 18 }, { "epoch": 0.5352112676056338, "grad_norm": 1.912354588508606, "learning_rate": 9.997525971737909e-07, "loss": 0.6148301959037781, "step": 19 }, { "epoch": 0.5633802816901409, "grad_norm": 1.8081035614013672, "learning_rate": 9.997258721585931e-07, "loss": 0.6116156578063965, "step": 20 }, { "epoch": 0.5915492957746479, "grad_norm": 1.7831499576568604, "learning_rate": 9.99697777200395e-07, "loss": 0.6001514196395874, "step": 21 }, { "epoch": 0.6197183098591549, "grad_norm": 1.733720064163208, "learning_rate": 9.996683123847795e-07, "loss": 0.5930601358413696, "step": 22 }, { "epoch": 0.647887323943662, "grad_norm": 1.7313363552093506, "learning_rate": 9.996374778015007e-07, "loss": 0.600416362285614, "step": 23 }, { "epoch": 0.676056338028169, "grad_norm": 1.5939713716506958, "learning_rate": 9.996052735444862e-07, "loss": 0.5838176608085632, "step": 24 }, { "epoch": 0.704225352112676, "grad_norm": 1.5792946815490723, "learning_rate": 9.99571699711836e-07, "loss": 0.6054390072822571, "step": 25 }, { "epoch": 0.7323943661971831, "grad_norm": 1.503157615661621, "learning_rate": 9.995367564058216e-07, "loss": 0.589947521686554, "step": 26 }, { "epoch": 0.7605633802816901, "grad_norm": 1.426310420036316, "learning_rate": 9.995004437328865e-07, "loss": 0.5833415985107422, "step": 27 }, { "epoch": 0.7887323943661971, "grad_norm": 1.4212743043899536, "learning_rate": 9.994627618036452e-07, "loss": 0.5824709534645081, "step": 28 }, { "epoch": 0.8169014084507042, "grad_norm": 1.4318434000015259, "learning_rate": 9.994237107328838e-07, "loss": 0.5912908315658569, "step": 29 }, { "epoch": 0.8450704225352113, "grad_norm": 1.3547085523605347, "learning_rate": 9.993832906395582e-07, "loss": 0.581213653087616, "step": 30 }, { "epoch": 0.8732394366197183, "grad_norm": 1.3216475248336792, "learning_rate": 9.993415016467952e-07, "loss": 0.5896694660186768, "step": 31 }, { "epoch": 0.9014084507042254, "grad_norm": 1.1472809314727783, "learning_rate": 9.992983438818915e-07, "loss": 0.5665017366409302, "step": 32 }, { "epoch": 0.9295774647887324, "grad_norm": 1.189638614654541, "learning_rate": 9.992538174763127e-07, "loss": 0.5583457946777344, "step": 33 }, { "epoch": 0.9577464788732394, "grad_norm": 1.3204843997955322, "learning_rate": 9.992079225656944e-07, "loss": 0.5481071472167969, "step": 34 }, { "epoch": 0.9859154929577465, "grad_norm": 1.355393409729004, "learning_rate": 9.9916065928984e-07, "loss": 0.540003776550293, "step": 35 }, { "epoch": 1.0, "grad_norm": 1.4106327295303345, "learning_rate": 9.991120277927223e-07, "loss": 0.5930083990097046, "step": 36 }, { "epoch": 1.028169014084507, "grad_norm": 1.2931945323944092, "learning_rate": 9.990620282224806e-07, "loss": 0.5400012731552124, "step": 37 }, { "epoch": 1.056338028169014, "grad_norm": 1.2562683820724487, "learning_rate": 9.990106607314225e-07, "loss": 0.5633293390274048, "step": 38 }, { "epoch": 1.084507042253521, "grad_norm": 1.1654468774795532, "learning_rate": 9.989579254760224e-07, "loss": 0.532966136932373, "step": 39 }, { "epoch": 1.1126760563380282, "grad_norm": 1.095537543296814, "learning_rate": 9.989038226169207e-07, "loss": 0.5428102016448975, "step": 40 }, { "epoch": 1.1408450704225352, "grad_norm": 0.9781971573829651, "learning_rate": 9.988483523189248e-07, "loss": 0.5413336157798767, "step": 41 }, { "epoch": 1.1690140845070423, "grad_norm": 0.9310394525527954, "learning_rate": 9.98791514751006e-07, "loss": 0.5297301411628723, "step": 42 }, { "epoch": 1.1971830985915493, "grad_norm": 0.8706420063972473, "learning_rate": 9.98733310086302e-07, "loss": 0.5210831165313721, "step": 43 }, { "epoch": 1.2253521126760563, "grad_norm": 0.8105738162994385, "learning_rate": 9.98673738502114e-07, "loss": 0.5330178737640381, "step": 44 }, { "epoch": 1.2535211267605635, "grad_norm": 0.7715710997581482, "learning_rate": 9.986128001799076e-07, "loss": 0.5241536498069763, "step": 45 }, { "epoch": 1.2816901408450705, "grad_norm": 0.7737131714820862, "learning_rate": 9.985504953053113e-07, "loss": 0.5341730713844299, "step": 46 }, { "epoch": 1.3098591549295775, "grad_norm": 0.7515022158622742, "learning_rate": 9.984868240681164e-07, "loss": 0.5346229076385498, "step": 47 }, { "epoch": 1.3380281690140845, "grad_norm": 0.7092189192771912, "learning_rate": 9.98421786662277e-07, "loss": 0.5273194909095764, "step": 48 }, { "epoch": 1.3661971830985915, "grad_norm": 0.7006992697715759, "learning_rate": 9.983553832859078e-07, "loss": 0.5130986571311951, "step": 49 }, { "epoch": 1.3943661971830985, "grad_norm": 0.7608235478401184, "learning_rate": 9.982876141412855e-07, "loss": 0.5286465883255005, "step": 50 }, { "epoch": 1.4225352112676055, "grad_norm": 0.7040536999702454, "learning_rate": 9.982184794348462e-07, "loss": 0.514992356300354, "step": 51 }, { "epoch": 1.4507042253521127, "grad_norm": 0.7056726813316345, "learning_rate": 9.981479793771866e-07, "loss": 0.5134010910987854, "step": 52 }, { "epoch": 1.4788732394366197, "grad_norm": 0.6980192065238953, "learning_rate": 9.98076114183062e-07, "loss": 0.5243700742721558, "step": 53 }, { "epoch": 1.5070422535211268, "grad_norm": 0.6883281469345093, "learning_rate": 9.98002884071386e-07, "loss": 0.533456563949585, "step": 54 }, { "epoch": 1.5352112676056338, "grad_norm": 0.6789364814758301, "learning_rate": 9.979282892652304e-07, "loss": 0.5107607841491699, "step": 55 }, { "epoch": 1.563380281690141, "grad_norm": 0.6524786353111267, "learning_rate": 9.97852329991824e-07, "loss": 0.5100893974304199, "step": 56 }, { "epoch": 1.591549295774648, "grad_norm": 0.6429108381271362, "learning_rate": 9.977750064825519e-07, "loss": 0.504834771156311, "step": 57 }, { "epoch": 1.619718309859155, "grad_norm": 0.640166699886322, "learning_rate": 9.976963189729547e-07, "loss": 0.5195026993751526, "step": 58 }, { "epoch": 1.647887323943662, "grad_norm": 0.6398917436599731, "learning_rate": 9.976162677027284e-07, "loss": 0.5107922554016113, "step": 59 }, { "epoch": 1.676056338028169, "grad_norm": 0.6268510818481445, "learning_rate": 9.975348529157229e-07, "loss": 0.5025534629821777, "step": 60 }, { "epoch": 1.704225352112676, "grad_norm": 0.6330083012580872, "learning_rate": 9.974520748599421e-07, "loss": 0.5268204212188721, "step": 61 }, { "epoch": 1.732394366197183, "grad_norm": 0.6181296110153198, "learning_rate": 9.973679337875418e-07, "loss": 0.5121350288391113, "step": 62 }, { "epoch": 1.76056338028169, "grad_norm": 0.6251637935638428, "learning_rate": 9.972824299548309e-07, "loss": 0.5083041191101074, "step": 63 }, { "epoch": 1.788732394366197, "grad_norm": 0.6216249465942383, "learning_rate": 9.971955636222684e-07, "loss": 0.4941920042037964, "step": 64 }, { "epoch": 1.8169014084507042, "grad_norm": 0.6167619228363037, "learning_rate": 9.971073350544644e-07, "loss": 0.5139775276184082, "step": 65 }, { "epoch": 1.8450704225352113, "grad_norm": 0.5856399536132812, "learning_rate": 9.970177445201783e-07, "loss": 0.49467232823371887, "step": 66 }, { "epoch": 1.8732394366197183, "grad_norm": 0.5677887201309204, "learning_rate": 9.969267922923188e-07, "loss": 0.48917800188064575, "step": 67 }, { "epoch": 1.9014084507042255, "grad_norm": 0.5781846642494202, "learning_rate": 9.968344786479415e-07, "loss": 0.49710148572921753, "step": 68 }, { "epoch": 1.9295774647887325, "grad_norm": 0.5702807903289795, "learning_rate": 9.967408038682505e-07, "loss": 0.5010455846786499, "step": 69 }, { "epoch": 1.9577464788732395, "grad_norm": 0.5541441440582275, "learning_rate": 9.96645768238595e-07, "loss": 0.48369255661964417, "step": 70 }, { "epoch": 1.9859154929577465, "grad_norm": 0.5757367014884949, "learning_rate": 9.965493720484698e-07, "loss": 0.4930347204208374, "step": 71 }, { "epoch": 2.0, "grad_norm": 0.6758991479873657, "learning_rate": 9.964516155915151e-07, "loss": 0.4696311354637146, "step": 72 }, { "epoch": 2.028169014084507, "grad_norm": 0.5600554943084717, "learning_rate": 9.963524991655133e-07, "loss": 0.4977237582206726, "step": 73 }, { "epoch": 2.056338028169014, "grad_norm": 0.5461347103118896, "learning_rate": 9.962520230723906e-07, "loss": 0.49581873416900635, "step": 74 }, { "epoch": 2.084507042253521, "grad_norm": 0.5371939539909363, "learning_rate": 9.961501876182148e-07, "loss": 0.4844444692134857, "step": 75 }, { "epoch": 2.112676056338028, "grad_norm": 0.5407112240791321, "learning_rate": 9.960469931131936e-07, "loss": 0.4627693295478821, "step": 76 }, { "epoch": 2.140845070422535, "grad_norm": 0.5260986089706421, "learning_rate": 9.959424398716763e-07, "loss": 0.47007229924201965, "step": 77 }, { "epoch": 2.169014084507042, "grad_norm": 0.5254941582679749, "learning_rate": 9.958365282121496e-07, "loss": 0.46428751945495605, "step": 78 }, { "epoch": 2.1971830985915495, "grad_norm": 0.4997383654117584, "learning_rate": 9.95729258457239e-07, "loss": 0.4665895700454712, "step": 79 }, { "epoch": 2.2253521126760565, "grad_norm": 0.47207513451576233, "learning_rate": 9.956206309337066e-07, "loss": 0.45952320098876953, "step": 80 }, { "epoch": 2.2535211267605635, "grad_norm": 0.5033359527587891, "learning_rate": 9.955106459724508e-07, "loss": 0.4830036759376526, "step": 81 }, { "epoch": 2.2816901408450705, "grad_norm": 0.49433037638664246, "learning_rate": 9.953993039085048e-07, "loss": 0.4792022109031677, "step": 82 }, { "epoch": 2.3098591549295775, "grad_norm": 0.47928422689437866, "learning_rate": 9.952866050810363e-07, "loss": 0.4605853259563446, "step": 83 }, { "epoch": 2.3380281690140845, "grad_norm": 0.4903593361377716, "learning_rate": 9.951725498333448e-07, "loss": 0.4785686433315277, "step": 84 }, { "epoch": 2.3661971830985915, "grad_norm": 0.4742894172668457, "learning_rate": 9.950571385128625e-07, "loss": 0.46115821599960327, "step": 85 }, { "epoch": 2.3943661971830985, "grad_norm": 0.4779631197452545, "learning_rate": 9.949403714711526e-07, "loss": 0.482327938079834, "step": 86 }, { "epoch": 2.4225352112676055, "grad_norm": 0.46615418791770935, "learning_rate": 9.948222490639075e-07, "loss": 0.4777219295501709, "step": 87 }, { "epoch": 2.4507042253521125, "grad_norm": 0.46539050340652466, "learning_rate": 9.947027716509488e-07, "loss": 0.4582518935203552, "step": 88 }, { "epoch": 2.4788732394366195, "grad_norm": 0.46740445494651794, "learning_rate": 9.94581939596225e-07, "loss": 0.4721161127090454, "step": 89 }, { "epoch": 2.507042253521127, "grad_norm": 0.47389939427375793, "learning_rate": 9.944597532678119e-07, "loss": 0.46307483315467834, "step": 90 }, { "epoch": 2.535211267605634, "grad_norm": 0.4830780327320099, "learning_rate": 9.943362130379101e-07, "loss": 0.45510873198509216, "step": 91 }, { "epoch": 2.563380281690141, "grad_norm": 0.459325909614563, "learning_rate": 9.942113192828444e-07, "loss": 0.4523160457611084, "step": 92 }, { "epoch": 2.591549295774648, "grad_norm": 0.45105743408203125, "learning_rate": 9.940850723830632e-07, "loss": 0.463370144367218, "step": 93 }, { "epoch": 2.619718309859155, "grad_norm": 0.45720189809799194, "learning_rate": 9.939574727231362e-07, "loss": 0.457330584526062, "step": 94 }, { "epoch": 2.647887323943662, "grad_norm": 0.46987929940223694, "learning_rate": 9.93828520691754e-07, "loss": 0.4691803455352783, "step": 95 }, { "epoch": 2.676056338028169, "grad_norm": 0.4466264545917511, "learning_rate": 9.93698216681727e-07, "loss": 0.4572003185749054, "step": 96 }, { "epoch": 2.704225352112676, "grad_norm": 0.4437786638736725, "learning_rate": 9.93566561089984e-07, "loss": 0.4381243884563446, "step": 97 }, { "epoch": 2.732394366197183, "grad_norm": 0.4545120298862457, "learning_rate": 9.934335543175705e-07, "loss": 0.4499259293079376, "step": 98 }, { "epoch": 2.76056338028169, "grad_norm": 0.44143691658973694, "learning_rate": 9.932991967696482e-07, "loss": 0.4642453193664551, "step": 99 }, { "epoch": 2.788732394366197, "grad_norm": 0.4832397997379303, "learning_rate": 9.931634888554935e-07, "loss": 0.4694593548774719, "step": 100 }, { "epoch": 2.816901408450704, "grad_norm": 0.43094682693481445, "learning_rate": 9.930264309884964e-07, "loss": 0.45000484585762024, "step": 101 }, { "epoch": 2.845070422535211, "grad_norm": 0.4435478448867798, "learning_rate": 9.928880235861588e-07, "loss": 0.4645836651325226, "step": 102 }, { "epoch": 2.873239436619718, "grad_norm": 0.444139301776886, "learning_rate": 9.927482670700936e-07, "loss": 0.4723513424396515, "step": 103 }, { "epoch": 2.9014084507042255, "grad_norm": 0.4250558316707611, "learning_rate": 9.926071618660237e-07, "loss": 0.4539216458797455, "step": 104 }, { "epoch": 2.9295774647887325, "grad_norm": 0.4474462568759918, "learning_rate": 9.924647084037797e-07, "loss": 0.46148908138275146, "step": 105 }, { "epoch": 2.9577464788732395, "grad_norm": 0.42733991146087646, "learning_rate": 9.923209071172994e-07, "loss": 0.45628565549850464, "step": 106 }, { "epoch": 2.9859154929577465, "grad_norm": 0.4464053511619568, "learning_rate": 9.921757584446268e-07, "loss": 0.43452945351600647, "step": 107 }, { "epoch": 3.0, "grad_norm": 0.5809227228164673, "learning_rate": 9.9202926282791e-07, "loss": 0.44677239656448364, "step": 108 }, { "epoch": 3.028169014084507, "grad_norm": 0.44219791889190674, "learning_rate": 9.918814207133997e-07, "loss": 0.4531911015510559, "step": 109 }, { "epoch": 3.056338028169014, "grad_norm": 0.42252233624458313, "learning_rate": 9.917322325514487e-07, "loss": 0.45887094736099243, "step": 110 }, { "epoch": 3.084507042253521, "grad_norm": 0.41009998321533203, "learning_rate": 9.915816987965102e-07, "loss": 0.4461494982242584, "step": 111 }, { "epoch": 3.112676056338028, "grad_norm": 0.42786458134651184, "learning_rate": 9.91429819907136e-07, "loss": 0.44171077013015747, "step": 112 }, { "epoch": 3.140845070422535, "grad_norm": 0.4436321258544922, "learning_rate": 9.912765963459756e-07, "loss": 0.45417094230651855, "step": 113 }, { "epoch": 3.169014084507042, "grad_norm": 0.42790186405181885, "learning_rate": 9.911220285797748e-07, "loss": 0.43987226486206055, "step": 114 }, { "epoch": 3.1971830985915495, "grad_norm": 0.43092527985572815, "learning_rate": 9.909661170793733e-07, "loss": 0.4397953748703003, "step": 115 }, { "epoch": 3.2253521126760565, "grad_norm": 0.43913376331329346, "learning_rate": 9.908088623197048e-07, "loss": 0.43508589267730713, "step": 116 }, { "epoch": 3.2535211267605635, "grad_norm": 0.4221682846546173, "learning_rate": 9.906502647797945e-07, "loss": 0.4442610740661621, "step": 117 }, { "epoch": 3.2816901408450705, "grad_norm": 0.4195612668991089, "learning_rate": 9.904903249427582e-07, "loss": 0.43617114424705505, "step": 118 }, { "epoch": 3.3098591549295775, "grad_norm": 0.43743807077407837, "learning_rate": 9.903290432958003e-07, "loss": 0.4431474804878235, "step": 119 }, { "epoch": 3.3380281690140845, "grad_norm": 0.4412403106689453, "learning_rate": 9.901664203302124e-07, "loss": 0.4504144787788391, "step": 120 }, { "epoch": 3.3661971830985915, "grad_norm": 0.4529508948326111, "learning_rate": 9.900024565413727e-07, "loss": 0.45065054297447205, "step": 121 }, { "epoch": 3.3943661971830985, "grad_norm": 0.421980082988739, "learning_rate": 9.89837152428743e-07, "loss": 0.4290427565574646, "step": 122 }, { "epoch": 3.4225352112676055, "grad_norm": 0.4221099019050598, "learning_rate": 9.896705084958687e-07, "loss": 0.42343345284461975, "step": 123 }, { "epoch": 3.4507042253521125, "grad_norm": 0.4531925618648529, "learning_rate": 9.895025252503755e-07, "loss": 0.4418011009693146, "step": 124 }, { "epoch": 3.4788732394366195, "grad_norm": 0.4296177923679352, "learning_rate": 9.8933320320397e-07, "loss": 0.4416682720184326, "step": 125 }, { "epoch": 3.507042253521127, "grad_norm": 0.43724027276039124, "learning_rate": 9.891625428724364e-07, "loss": 0.4223203659057617, "step": 126 }, { "epoch": 3.535211267605634, "grad_norm": 0.41997113823890686, "learning_rate": 9.889905447756355e-07, "loss": 0.45191723108291626, "step": 127 }, { "epoch": 3.563380281690141, "grad_norm": 0.41299012303352356, "learning_rate": 9.888172094375033e-07, "loss": 0.43722259998321533, "step": 128 }, { "epoch": 3.591549295774648, "grad_norm": 0.42296457290649414, "learning_rate": 9.886425373860496e-07, "loss": 0.43232589960098267, "step": 129 }, { "epoch": 3.619718309859155, "grad_norm": 0.42629241943359375, "learning_rate": 9.88466529153356e-07, "loss": 0.45389413833618164, "step": 130 }, { "epoch": 3.647887323943662, "grad_norm": 0.4336591958999634, "learning_rate": 9.882891852755732e-07, "loss": 0.4396490454673767, "step": 131 }, { "epoch": 3.676056338028169, "grad_norm": 0.4133699834346771, "learning_rate": 9.881105062929221e-07, "loss": 0.41916632652282715, "step": 132 }, { "epoch": 3.704225352112676, "grad_norm": 0.398794025182724, "learning_rate": 9.879304927496896e-07, "loss": 0.43504297733306885, "step": 133 }, { "epoch": 3.732394366197183, "grad_norm": 0.42575928568840027, "learning_rate": 9.877491451942284e-07, "loss": 0.4300439953804016, "step": 134 }, { "epoch": 3.76056338028169, "grad_norm": 0.41005146503448486, "learning_rate": 9.875664641789543e-07, "loss": 0.43460115790367126, "step": 135 }, { "epoch": 3.788732394366197, "grad_norm": 0.42240363359451294, "learning_rate": 9.873824502603459e-07, "loss": 0.4475589990615845, "step": 136 }, { "epoch": 3.816901408450704, "grad_norm": 0.4231485426425934, "learning_rate": 9.871971039989407e-07, "loss": 0.4443385601043701, "step": 137 }, { "epoch": 3.845070422535211, "grad_norm": 0.4161396026611328, "learning_rate": 9.870104259593362e-07, "loss": 0.4286690652370453, "step": 138 }, { "epoch": 3.873239436619718, "grad_norm": 0.4430389106273651, "learning_rate": 9.86822416710186e-07, "loss": 0.42875033617019653, "step": 139 }, { "epoch": 3.9014084507042255, "grad_norm": 0.45408958196640015, "learning_rate": 9.866330768241983e-07, "loss": 0.4233587682247162, "step": 140 }, { "epoch": 3.9295774647887325, "grad_norm": 0.42567622661590576, "learning_rate": 9.86442406878136e-07, "loss": 0.4428149163722992, "step": 141 }, { "epoch": 3.9577464788732395, "grad_norm": 0.4225475490093231, "learning_rate": 9.862504074528126e-07, "loss": 0.44222721457481384, "step": 142 }, { "epoch": 3.9859154929577465, "grad_norm": 0.42019423842430115, "learning_rate": 9.860570791330911e-07, "loss": 0.45220500230789185, "step": 143 }, { "epoch": 4.0, "grad_norm": 0.5528488159179688, "learning_rate": 9.85862422507884e-07, "loss": 0.40195268392562866, "step": 144 }, { "epoch": 4.028169014084507, "grad_norm": 0.3971721827983856, "learning_rate": 9.856664381701483e-07, "loss": 0.4286423325538635, "step": 145 }, { "epoch": 4.056338028169014, "grad_norm": 0.40409189462661743, "learning_rate": 9.854691267168871e-07, "loss": 0.43035459518432617, "step": 146 }, { "epoch": 4.084507042253521, "grad_norm": 0.41791510581970215, "learning_rate": 9.852704887491445e-07, "loss": 0.4135133922100067, "step": 147 }, { "epoch": 4.112676056338028, "grad_norm": 0.41965293884277344, "learning_rate": 9.850705248720068e-07, "loss": 0.4384373724460602, "step": 148 }, { "epoch": 4.140845070422535, "grad_norm": 0.4066624641418457, "learning_rate": 9.848692356945981e-07, "loss": 0.4170719385147095, "step": 149 }, { "epoch": 4.169014084507042, "grad_norm": 0.41751572489738464, "learning_rate": 9.846666218300807e-07, "loss": 0.4242548644542694, "step": 150 }, { "epoch": 4.197183098591549, "grad_norm": 0.4481653571128845, "learning_rate": 9.844626838956513e-07, "loss": 0.4261680543422699, "step": 151 }, { "epoch": 4.225352112676056, "grad_norm": 0.40597406029701233, "learning_rate": 9.8425742251254e-07, "loss": 0.42576903104782104, "step": 152 }, { "epoch": 4.253521126760563, "grad_norm": 0.4021463990211487, "learning_rate": 9.84050838306009e-07, "loss": 0.44204574823379517, "step": 153 }, { "epoch": 4.28169014084507, "grad_norm": 0.4047972559928894, "learning_rate": 9.838429319053495e-07, "loss": 0.4102432429790497, "step": 154 }, { "epoch": 4.309859154929577, "grad_norm": 0.40411484241485596, "learning_rate": 9.836337039438803e-07, "loss": 0.4174734950065613, "step": 155 }, { "epoch": 4.338028169014084, "grad_norm": 0.3924463987350464, "learning_rate": 9.83423155058946e-07, "loss": 0.4306033253669739, "step": 156 }, { "epoch": 4.366197183098592, "grad_norm": 0.4114137291908264, "learning_rate": 9.832112858919155e-07, "loss": 0.4216451942920685, "step": 157 }, { "epoch": 4.394366197183099, "grad_norm": 0.4420042932033539, "learning_rate": 9.829980970881784e-07, "loss": 0.4244844913482666, "step": 158 }, { "epoch": 4.422535211267606, "grad_norm": 0.40874671936035156, "learning_rate": 9.82783589297145e-07, "loss": 0.42342883348464966, "step": 159 }, { "epoch": 4.450704225352113, "grad_norm": 0.4102858304977417, "learning_rate": 9.825677631722435e-07, "loss": 0.41572105884552, "step": 160 }, { "epoch": 4.47887323943662, "grad_norm": 0.39961734414100647, "learning_rate": 9.823506193709174e-07, "loss": 0.41979867219924927, "step": 161 }, { "epoch": 4.507042253521127, "grad_norm": 0.3921862244606018, "learning_rate": 9.821321585546243e-07, "loss": 0.4211655557155609, "step": 162 }, { "epoch": 4.535211267605634, "grad_norm": 0.3990178108215332, "learning_rate": 9.81912381388834e-07, "loss": 0.40852388739585876, "step": 163 }, { "epoch": 4.563380281690141, "grad_norm": 0.42926791310310364, "learning_rate": 9.816912885430258e-07, "loss": 0.4178195297718048, "step": 164 }, { "epoch": 4.591549295774648, "grad_norm": 0.4242827892303467, "learning_rate": 9.814688806906868e-07, "loss": 0.4278091490268707, "step": 165 }, { "epoch": 4.619718309859155, "grad_norm": 0.40822485089302063, "learning_rate": 9.812451585093098e-07, "loss": 0.41916969418525696, "step": 166 }, { "epoch": 4.647887323943662, "grad_norm": 0.3851315975189209, "learning_rate": 9.810201226803917e-07, "loss": 0.4192688465118408, "step": 167 }, { "epoch": 4.676056338028169, "grad_norm": 0.4114606976509094, "learning_rate": 9.807937738894303e-07, "loss": 0.42044782638549805, "step": 168 }, { "epoch": 4.704225352112676, "grad_norm": 0.4305799603462219, "learning_rate": 9.805661128259235e-07, "loss": 0.4219653308391571, "step": 169 }, { "epoch": 4.732394366197183, "grad_norm": 0.3918915092945099, "learning_rate": 9.80337140183366e-07, "loss": 0.4259489178657532, "step": 170 }, { "epoch": 4.76056338028169, "grad_norm": 0.409164160490036, "learning_rate": 9.801068566592483e-07, "loss": 0.4121962785720825, "step": 171 }, { "epoch": 4.788732394366197, "grad_norm": 0.41790276765823364, "learning_rate": 9.798752629550546e-07, "loss": 0.41536441445350647, "step": 172 }, { "epoch": 4.816901408450704, "grad_norm": 0.40874162316322327, "learning_rate": 9.796423597762588e-07, "loss": 0.4193142056465149, "step": 173 }, { "epoch": 4.845070422535211, "grad_norm": 0.41308480501174927, "learning_rate": 9.794081478323245e-07, "loss": 0.42131903767585754, "step": 174 }, { "epoch": 4.873239436619718, "grad_norm": 0.4161160886287689, "learning_rate": 9.791726278367021e-07, "loss": 0.398072749376297, "step": 175 }, { "epoch": 4.901408450704225, "grad_norm": 0.4220758378505707, "learning_rate": 9.78935800506826e-07, "loss": 0.42168164253234863, "step": 176 }, { "epoch": 4.929577464788732, "grad_norm": 0.3985085189342499, "learning_rate": 9.786976665641138e-07, "loss": 0.4213156998157501, "step": 177 }, { "epoch": 4.957746478873239, "grad_norm": 0.40048250555992126, "learning_rate": 9.784582267339622e-07, "loss": 0.4084168076515198, "step": 178 }, { "epoch": 4.985915492957746, "grad_norm": 0.4005119800567627, "learning_rate": 9.78217481745747e-07, "loss": 0.4115833640098572, "step": 179 }, { "epoch": 5.0, "grad_norm": 0.5620749592781067, "learning_rate": 9.779754323328192e-07, "loss": 0.4229545593261719, "step": 180 }, { "epoch": 5.028169014084507, "grad_norm": 0.4124564826488495, "learning_rate": 9.777320792325025e-07, "loss": 0.40300124883651733, "step": 181 }, { "epoch": 5.056338028169014, "grad_norm": 0.39206236600875854, "learning_rate": 9.774874231860935e-07, "loss": 0.40934857726097107, "step": 182 }, { "epoch": 5.084507042253521, "grad_norm": 0.39972883462905884, "learning_rate": 9.772414649388568e-07, "loss": 0.4070882201194763, "step": 183 }, { "epoch": 5.112676056338028, "grad_norm": 0.41956591606140137, "learning_rate": 9.769942052400235e-07, "loss": 0.4054498076438904, "step": 184 }, { "epoch": 5.140845070422535, "grad_norm": 0.41228869557380676, "learning_rate": 9.767456448427896e-07, "loss": 0.41475123167037964, "step": 185 }, { "epoch": 5.169014084507042, "grad_norm": 0.37674757838249207, "learning_rate": 9.764957845043135e-07, "loss": 0.4103524088859558, "step": 186 }, { "epoch": 5.197183098591549, "grad_norm": 0.4229021966457367, "learning_rate": 9.76244624985713e-07, "loss": 0.3965042233467102, "step": 187 }, { "epoch": 5.225352112676056, "grad_norm": 0.3856871426105499, "learning_rate": 9.759921670520634e-07, "loss": 0.414482057094574, "step": 188 }, { "epoch": 5.253521126760563, "grad_norm": 0.41363710165023804, "learning_rate": 9.757384114723953e-07, "loss": 0.4230787456035614, "step": 189 }, { "epoch": 5.28169014084507, "grad_norm": 0.41514742374420166, "learning_rate": 9.754833590196926e-07, "loss": 0.4125136137008667, "step": 190 }, { "epoch": 5.309859154929577, "grad_norm": 0.3936339318752289, "learning_rate": 9.752270104708888e-07, "loss": 0.42837342619895935, "step": 191 }, { "epoch": 5.338028169014084, "grad_norm": 0.38952022790908813, "learning_rate": 9.749693666068663e-07, "loss": 0.4078400433063507, "step": 192 }, { "epoch": 5.366197183098592, "grad_norm": 0.41678085923194885, "learning_rate": 9.747104282124531e-07, "loss": 0.4196391701698303, "step": 193 }, { "epoch": 5.394366197183099, "grad_norm": 0.39327719807624817, "learning_rate": 9.744501960764203e-07, "loss": 0.3973960280418396, "step": 194 }, { "epoch": 5.422535211267606, "grad_norm": 0.38618800044059753, "learning_rate": 9.741886709914803e-07, "loss": 0.4038587212562561, "step": 195 }, { "epoch": 5.450704225352113, "grad_norm": 0.39070042967796326, "learning_rate": 9.739258537542835e-07, "loss": 0.39228275418281555, "step": 196 }, { "epoch": 5.47887323943662, "grad_norm": 0.3981262147426605, "learning_rate": 9.73661745165417e-07, "loss": 0.4140496253967285, "step": 197 }, { "epoch": 5.507042253521127, "grad_norm": 0.37878021597862244, "learning_rate": 9.733963460294015e-07, "loss": 0.39398297667503357, "step": 198 }, { "epoch": 5.535211267605634, "grad_norm": 0.38918426632881165, "learning_rate": 9.731296571546885e-07, "loss": 0.4071250557899475, "step": 199 }, { "epoch": 5.563380281690141, "grad_norm": 0.41153526306152344, "learning_rate": 9.728616793536587e-07, "loss": 0.39563220739364624, "step": 200 }, { "epoch": 5.591549295774648, "grad_norm": 0.40266478061676025, "learning_rate": 9.72592413442619e-07, "loss": 0.41241517663002014, "step": 201 }, { "epoch": 5.619718309859155, "grad_norm": 0.3959569036960602, "learning_rate": 9.723218602418e-07, "loss": 0.40159425139427185, "step": 202 }, { "epoch": 5.647887323943662, "grad_norm": 0.43270614743232727, "learning_rate": 9.720500205753538e-07, "loss": 0.40377816557884216, "step": 203 }, { "epoch": 5.676056338028169, "grad_norm": 0.4245915114879608, "learning_rate": 9.717768952713511e-07, "loss": 0.40518319606781006, "step": 204 }, { "epoch": 5.704225352112676, "grad_norm": 0.38795205950737, "learning_rate": 9.71502485161779e-07, "loss": 0.4032747745513916, "step": 205 }, { "epoch": 5.732394366197183, "grad_norm": 0.386687695980072, "learning_rate": 9.71226791082538e-07, "loss": 0.39289215207099915, "step": 206 }, { "epoch": 5.76056338028169, "grad_norm": 0.4055168628692627, "learning_rate": 9.709498138734403e-07, "loss": 0.4077930450439453, "step": 207 }, { "epoch": 5.788732394366197, "grad_norm": 0.4297349750995636, "learning_rate": 9.706715543782064e-07, "loss": 0.41212064027786255, "step": 208 }, { "epoch": 5.816901408450704, "grad_norm": 0.3813517689704895, "learning_rate": 9.703920134444632e-07, "loss": 0.4073314368724823, "step": 209 }, { "epoch": 5.845070422535211, "grad_norm": 0.3906748592853546, "learning_rate": 9.701111919237408e-07, "loss": 0.4028477668762207, "step": 210 }, { "epoch": 5.873239436619718, "grad_norm": 0.40895506739616394, "learning_rate": 9.698290906714702e-07, "loss": 0.40225616097450256, "step": 211 }, { "epoch": 5.901408450704225, "grad_norm": 0.3899952471256256, "learning_rate": 9.695457105469804e-07, "loss": 0.40987417101860046, "step": 212 }, { "epoch": 5.929577464788732, "grad_norm": 0.40246039628982544, "learning_rate": 9.69261052413497e-07, "loss": 0.4043743908405304, "step": 213 }, { "epoch": 5.957746478873239, "grad_norm": 0.3888782262802124, "learning_rate": 9.689751171381377e-07, "loss": 0.41095173358917236, "step": 214 }, { "epoch": 5.985915492957746, "grad_norm": 0.38841670751571655, "learning_rate": 9.68687905591911e-07, "loss": 0.4023211598396301, "step": 215 }, { "epoch": 6.0, "grad_norm": 0.5250245928764343, "learning_rate": 9.683994186497132e-07, "loss": 0.3995124101638794, "step": 216 }, { "epoch": 6.028169014084507, "grad_norm": 0.3878166973590851, "learning_rate": 9.681096571903252e-07, "loss": 0.38741564750671387, "step": 217 }, { "epoch": 6.056338028169014, "grad_norm": 0.3900756537914276, "learning_rate": 9.67818622096411e-07, "loss": 0.3982124328613281, "step": 218 }, { "epoch": 6.084507042253521, "grad_norm": 0.39002755284309387, "learning_rate": 9.67526314254514e-07, "loss": 0.39917469024658203, "step": 219 }, { "epoch": 6.112676056338028, "grad_norm": 0.388755738735199, "learning_rate": 9.672327345550543e-07, "loss": 0.40225809812545776, "step": 220 }, { "epoch": 6.140845070422535, "grad_norm": 0.3802153468132019, "learning_rate": 9.669378838923267e-07, "loss": 0.39574944972991943, "step": 221 }, { "epoch": 6.169014084507042, "grad_norm": 0.386984258890152, "learning_rate": 9.666417631644976e-07, "loss": 0.3936455249786377, "step": 222 }, { "epoch": 6.197183098591549, "grad_norm": 0.37910348176956177, "learning_rate": 9.66344373273602e-07, "loss": 0.4140435755252838, "step": 223 }, { "epoch": 6.225352112676056, "grad_norm": 0.39792004227638245, "learning_rate": 9.66045715125541e-07, "loss": 0.40117213129997253, "step": 224 }, { "epoch": 6.253521126760563, "grad_norm": 0.3902668356895447, "learning_rate": 9.657457896300791e-07, "loss": 0.4083721339702606, "step": 225 }, { "epoch": 6.28169014084507, "grad_norm": 0.42297157645225525, "learning_rate": 9.654445977008414e-07, "loss": 0.4038228392601013, "step": 226 }, { "epoch": 6.309859154929577, "grad_norm": 0.4099472165107727, "learning_rate": 9.651421402553108e-07, "loss": 0.3899737596511841, "step": 227 }, { "epoch": 6.338028169014084, "grad_norm": 0.373994916677475, "learning_rate": 9.648384182148252e-07, "loss": 0.39907342195510864, "step": 228 }, { "epoch": 6.366197183098592, "grad_norm": 0.3966023623943329, "learning_rate": 9.645334325045745e-07, "loss": 0.3945938050746918, "step": 229 }, { "epoch": 6.394366197183099, "grad_norm": 0.42777925729751587, "learning_rate": 9.64227184053598e-07, "loss": 0.4102497696876526, "step": 230 }, { "epoch": 6.422535211267606, "grad_norm": 0.39833584427833557, "learning_rate": 9.63919673794782e-07, "loss": 0.39916127920150757, "step": 231 }, { "epoch": 6.450704225352113, "grad_norm": 0.3920106291770935, "learning_rate": 9.636109026648554e-07, "loss": 0.4021705985069275, "step": 232 }, { "epoch": 6.47887323943662, "grad_norm": 0.4094751179218292, "learning_rate": 9.633008716043892e-07, "loss": 0.40074992179870605, "step": 233 }, { "epoch": 6.507042253521127, "grad_norm": 0.40727370977401733, "learning_rate": 9.629895815577915e-07, "loss": 0.38765621185302734, "step": 234 }, { "epoch": 6.535211267605634, "grad_norm": 0.39645060896873474, "learning_rate": 9.626770334733058e-07, "loss": 0.3924933969974518, "step": 235 }, { "epoch": 6.563380281690141, "grad_norm": 0.37045979499816895, "learning_rate": 9.623632283030077e-07, "loss": 0.38481301069259644, "step": 236 }, { "epoch": 6.591549295774648, "grad_norm": 0.40392062067985535, "learning_rate": 9.620481670028026e-07, "loss": 0.40656569600105286, "step": 237 }, { "epoch": 6.619718309859155, "grad_norm": 0.4091082811355591, "learning_rate": 9.617318505324212e-07, "loss": 0.3812691569328308, "step": 238 }, { "epoch": 6.647887323943662, "grad_norm": 0.3880692720413208, "learning_rate": 9.614142798554186e-07, "loss": 0.3706771731376648, "step": 239 }, { "epoch": 6.676056338028169, "grad_norm": 0.3998086154460907, "learning_rate": 9.610954559391704e-07, "loss": 0.40241339802742004, "step": 240 }, { "epoch": 6.704225352112676, "grad_norm": 0.41269201040267944, "learning_rate": 9.607753797548691e-07, "loss": 0.4123341143131256, "step": 241 }, { "epoch": 6.732394366197183, "grad_norm": 0.3929405212402344, "learning_rate": 9.604540522775227e-07, "loss": 0.3892459273338318, "step": 242 }, { "epoch": 6.76056338028169, "grad_norm": 0.3889841139316559, "learning_rate": 9.601314744859504e-07, "loss": 0.3876785933971405, "step": 243 }, { "epoch": 6.788732394366197, "grad_norm": 0.4093876779079437, "learning_rate": 9.598076473627796e-07, "loss": 0.40213003754615784, "step": 244 }, { "epoch": 6.816901408450704, "grad_norm": 0.38009846210479736, "learning_rate": 9.594825718944444e-07, "loss": 0.39333346486091614, "step": 245 }, { "epoch": 6.845070422535211, "grad_norm": 0.3948485851287842, "learning_rate": 9.59156249071181e-07, "loss": 0.39433354139328003, "step": 246 }, { "epoch": 6.873239436619718, "grad_norm": 0.3912011981010437, "learning_rate": 9.588286798870248e-07, "loss": 0.39452600479125977, "step": 247 }, { "epoch": 6.901408450704225, "grad_norm": 0.39858993887901306, "learning_rate": 9.58499865339809e-07, "loss": 0.398301899433136, "step": 248 }, { "epoch": 6.929577464788732, "grad_norm": 0.39438149333000183, "learning_rate": 9.581698064311592e-07, "loss": 0.3746541142463684, "step": 249 }, { "epoch": 6.957746478873239, "grad_norm": 0.38814306259155273, "learning_rate": 9.578385041664925e-07, "loss": 0.40119290351867676, "step": 250 }, { "epoch": 6.985915492957746, "grad_norm": 0.38463205099105835, "learning_rate": 9.575059595550127e-07, "loss": 0.38324254751205444, "step": 251 }, { "epoch": 7.0, "grad_norm": 0.512336790561676, "learning_rate": 9.571721736097088e-07, "loss": 0.3892096281051636, "step": 252 }, { "epoch": 7.028169014084507, "grad_norm": 0.3832947611808777, "learning_rate": 9.568371473473503e-07, "loss": 0.3952549993991852, "step": 253 }, { "epoch": 7.056338028169014, "grad_norm": 0.3827665448188782, "learning_rate": 9.565008817884854e-07, "loss": 0.3801252841949463, "step": 254 }, { "epoch": 7.084507042253521, "grad_norm": 0.39462706446647644, "learning_rate": 9.561633779574372e-07, "loss": 0.37541863322257996, "step": 255 }, { "epoch": 7.112676056338028, "grad_norm": 0.3986050486564636, "learning_rate": 9.55824636882301e-07, "loss": 0.38753676414489746, "step": 256 }, { "epoch": 7.140845070422535, "grad_norm": 0.38387978076934814, "learning_rate": 9.554846595949413e-07, "loss": 0.39041170477867126, "step": 257 }, { "epoch": 7.169014084507042, "grad_norm": 0.38619932532310486, "learning_rate": 9.55143447130987e-07, "loss": 0.3870781362056732, "step": 258 }, { "epoch": 7.197183098591549, "grad_norm": 0.3886691629886627, "learning_rate": 9.54801000529831e-07, "loss": 0.3816353678703308, "step": 259 }, { "epoch": 7.225352112676056, "grad_norm": 0.3752847909927368, "learning_rate": 9.54457320834625e-07, "loss": 0.3853958249092102, "step": 260 }, { "epoch": 7.253521126760563, "grad_norm": 0.39625924825668335, "learning_rate": 9.54112409092277e-07, "loss": 0.3863310217857361, "step": 261 }, { "epoch": 7.28169014084507, "grad_norm": 0.3740101754665375, "learning_rate": 9.537662663534477e-07, "loss": 0.3769490122795105, "step": 262 }, { "epoch": 7.309859154929577, "grad_norm": 0.36722782254219055, "learning_rate": 9.534188936725483e-07, "loss": 0.38238656520843506, "step": 263 }, { "epoch": 7.338028169014084, "grad_norm": 0.38367265462875366, "learning_rate": 9.530702921077358e-07, "loss": 0.3922719657421112, "step": 264 }, { "epoch": 7.366197183098592, "grad_norm": 0.37159886956214905, "learning_rate": 9.527204627209112e-07, "loss": 0.3855976462364197, "step": 265 }, { "epoch": 7.394366197183099, "grad_norm": 0.3731975257396698, "learning_rate": 9.523694065777156e-07, "loss": 0.39453253149986267, "step": 266 }, { "epoch": 7.422535211267606, "grad_norm": 0.3808491826057434, "learning_rate": 9.520171247475268e-07, "loss": 0.39547351002693176, "step": 267 }, { "epoch": 7.450704225352113, "grad_norm": 0.40034112334251404, "learning_rate": 9.516636183034564e-07, "loss": 0.40701085329055786, "step": 268 }, { "epoch": 7.47887323943662, "grad_norm": 0.3683933913707733, "learning_rate": 9.513088883223463e-07, "loss": 0.3724665939807892, "step": 269 }, { "epoch": 7.507042253521127, "grad_norm": 0.3895512819290161, "learning_rate": 9.509529358847654e-07, "loss": 0.3855685591697693, "step": 270 }, { "epoch": 7.535211267605634, "grad_norm": 0.39392992854118347, "learning_rate": 9.505957620750069e-07, "loss": 0.3997983932495117, "step": 271 }, { "epoch": 7.563380281690141, "grad_norm": 0.39526015520095825, "learning_rate": 9.502373679810839e-07, "loss": 0.39925113320350647, "step": 272 }, { "epoch": 7.591549295774648, "grad_norm": 0.3839961886405945, "learning_rate": 9.49877754694727e-07, "loss": 0.38556551933288574, "step": 273 }, { "epoch": 7.619718309859155, "grad_norm": 0.37695956230163574, "learning_rate": 9.495169233113806e-07, "loss": 0.3815164864063263, "step": 274 }, { "epoch": 7.647887323943662, "grad_norm": 0.38619664311408997, "learning_rate": 9.491548749301997e-07, "loss": 0.3830955922603607, "step": 275 }, { "epoch": 7.676056338028169, "grad_norm": 0.38984498381614685, "learning_rate": 9.487916106540465e-07, "loss": 0.3873262405395508, "step": 276 }, { "epoch": 7.704225352112676, "grad_norm": 0.379177063703537, "learning_rate": 9.484271315894871e-07, "loss": 0.3927234411239624, "step": 277 }, { "epoch": 7.732394366197183, "grad_norm": 0.3658169209957123, "learning_rate": 9.480614388467877e-07, "loss": 0.36901265382766724, "step": 278 }, { "epoch": 7.76056338028169, "grad_norm": 0.3819941580295563, "learning_rate": 9.47694533539912e-07, "loss": 0.38150596618652344, "step": 279 }, { "epoch": 7.788732394366197, "grad_norm": 0.3829544484615326, "learning_rate": 9.473264167865171e-07, "loss": 0.3858985900878906, "step": 280 }, { "epoch": 7.816901408450704, "grad_norm": 0.3701535165309906, "learning_rate": 9.469570897079504e-07, "loss": 0.39159393310546875, "step": 281 }, { "epoch": 7.845070422535211, "grad_norm": 0.3712180554866791, "learning_rate": 9.465865534292464e-07, "loss": 0.3787636458873749, "step": 282 }, { "epoch": 7.873239436619718, "grad_norm": 0.39336493611335754, "learning_rate": 9.462148090791228e-07, "loss": 0.395854651927948, "step": 283 }, { "epoch": 7.901408450704225, "grad_norm": 0.37657997012138367, "learning_rate": 9.458418577899774e-07, "loss": 0.39227941632270813, "step": 284 }, { "epoch": 7.929577464788732, "grad_norm": 0.38283368945121765, "learning_rate": 9.454677006978842e-07, "loss": 0.37147632241249084, "step": 285 }, { "epoch": 7.957746478873239, "grad_norm": 0.3838220536708832, "learning_rate": 9.450923389425911e-07, "loss": 0.4034760892391205, "step": 286 }, { "epoch": 7.985915492957746, "grad_norm": 0.37267106771469116, "learning_rate": 9.44715773667515e-07, "loss": 0.389766663312912, "step": 287 }, { "epoch": 8.0, "grad_norm": 0.5348430275917053, "learning_rate": 9.443380060197385e-07, "loss": 0.376720130443573, "step": 288 }, { "epoch": 8.028169014084508, "grad_norm": 0.37357982993125916, "learning_rate": 9.43959037150008e-07, "loss": 0.37634867429733276, "step": 289 }, { "epoch": 8.056338028169014, "grad_norm": 0.3882472813129425, "learning_rate": 9.43578868212728e-07, "loss": 0.3797028958797455, "step": 290 }, { "epoch": 8.084507042253522, "grad_norm": 0.3893776535987854, "learning_rate": 9.431975003659594e-07, "loss": 0.37434738874435425, "step": 291 }, { "epoch": 8.112676056338028, "grad_norm": 0.3701059818267822, "learning_rate": 9.428149347714143e-07, "loss": 0.3884342610836029, "step": 292 }, { "epoch": 8.140845070422536, "grad_norm": 0.3775370419025421, "learning_rate": 9.424311725944543e-07, "loss": 0.3782704770565033, "step": 293 }, { "epoch": 8.169014084507042, "grad_norm": 0.380548894405365, "learning_rate": 9.420462150040852e-07, "loss": 0.3933628797531128, "step": 294 }, { "epoch": 8.19718309859155, "grad_norm": 0.3580932319164276, "learning_rate": 9.416600631729548e-07, "loss": 0.3782176375389099, "step": 295 }, { "epoch": 8.225352112676056, "grad_norm": 0.36150234937667847, "learning_rate": 9.412727182773486e-07, "loss": 0.37162452936172485, "step": 296 }, { "epoch": 8.253521126760564, "grad_norm": 0.3930136263370514, "learning_rate": 9.408841814971861e-07, "loss": 0.38008132576942444, "step": 297 }, { "epoch": 8.28169014084507, "grad_norm": 0.3888865113258362, "learning_rate": 9.404944540160177e-07, "loss": 0.3665124475955963, "step": 298 }, { "epoch": 8.309859154929578, "grad_norm": 0.38649752736091614, "learning_rate": 9.401035370210212e-07, "loss": 0.3863350749015808, "step": 299 }, { "epoch": 8.338028169014084, "grad_norm": 0.38382744789123535, "learning_rate": 9.397114317029974e-07, "loss": 0.38738366961479187, "step": 300 }, { "epoch": 8.366197183098592, "grad_norm": 0.3768056333065033, "learning_rate": 9.393181392563669e-07, "loss": 0.3643200993537903, "step": 301 }, { "epoch": 8.394366197183098, "grad_norm": 0.382364958524704, "learning_rate": 9.38923660879167e-07, "loss": 0.3879460096359253, "step": 302 }, { "epoch": 8.422535211267606, "grad_norm": 0.3916151225566864, "learning_rate": 9.385279977730472e-07, "loss": 0.37250763177871704, "step": 303 }, { "epoch": 8.450704225352112, "grad_norm": 0.38189125061035156, "learning_rate": 9.381311511432658e-07, "loss": 0.39008766412734985, "step": 304 }, { "epoch": 8.47887323943662, "grad_norm": 0.3740954101085663, "learning_rate": 9.377331221986866e-07, "loss": 0.3884603679180145, "step": 305 }, { "epoch": 8.507042253521126, "grad_norm": 0.375465452671051, "learning_rate": 9.373339121517746e-07, "loss": 0.37713924050331116, "step": 306 }, { "epoch": 8.535211267605634, "grad_norm": 0.3769972324371338, "learning_rate": 9.36933522218593e-07, "loss": 0.3770156502723694, "step": 307 }, { "epoch": 8.56338028169014, "grad_norm": 0.37575188279151917, "learning_rate": 9.36531953618799e-07, "loss": 0.3902169466018677, "step": 308 }, { "epoch": 8.591549295774648, "grad_norm": 0.38152608275413513, "learning_rate": 9.361292075756401e-07, "loss": 0.3867529630661011, "step": 309 }, { "epoch": 8.619718309859154, "grad_norm": 0.3819044530391693, "learning_rate": 9.357252853159505e-07, "loss": 0.3807380497455597, "step": 310 }, { "epoch": 8.647887323943662, "grad_norm": 0.3812952935695648, "learning_rate": 9.353201880701477e-07, "loss": 0.3920441269874573, "step": 311 }, { "epoch": 8.676056338028168, "grad_norm": 0.3992844521999359, "learning_rate": 9.34913917072228e-07, "loss": 0.3915911316871643, "step": 312 }, { "epoch": 8.704225352112676, "grad_norm": 0.37549176812171936, "learning_rate": 9.345064735597633e-07, "loss": 0.3836255967617035, "step": 313 }, { "epoch": 8.732394366197184, "grad_norm": 0.38589218258857727, "learning_rate": 9.340978587738972e-07, "loss": 0.3890310823917389, "step": 314 }, { "epoch": 8.76056338028169, "grad_norm": 0.38828885555267334, "learning_rate": 9.336880739593415e-07, "loss": 0.38117384910583496, "step": 315 }, { "epoch": 8.788732394366198, "grad_norm": 0.39411139488220215, "learning_rate": 9.332771203643714e-07, "loss": 0.3856485188007355, "step": 316 }, { "epoch": 8.816901408450704, "grad_norm": 0.39936208724975586, "learning_rate": 9.328649992408231e-07, "loss": 0.3748643398284912, "step": 317 }, { "epoch": 8.845070422535212, "grad_norm": 0.3858584463596344, "learning_rate": 9.324517118440888e-07, "loss": 0.3715360462665558, "step": 318 }, { "epoch": 8.873239436619718, "grad_norm": 0.3810833692550659, "learning_rate": 9.320372594331137e-07, "loss": 0.3639200031757355, "step": 319 }, { "epoch": 8.901408450704226, "grad_norm": 0.3702692687511444, "learning_rate": 9.316216432703916e-07, "loss": 0.3586096167564392, "step": 320 }, { "epoch": 8.929577464788732, "grad_norm": 0.3870997726917267, "learning_rate": 9.312048646219617e-07, "loss": 0.37650924921035767, "step": 321 }, { "epoch": 8.95774647887324, "grad_norm": 0.3685506284236908, "learning_rate": 9.307869247574038e-07, "loss": 0.3866027295589447, "step": 322 }, { "epoch": 8.985915492957746, "grad_norm": 0.38240721821784973, "learning_rate": 9.303678249498352e-07, "loss": 0.3517172932624817, "step": 323 }, { "epoch": 9.0, "grad_norm": 0.5326734185218811, "learning_rate": 9.299475664759068e-07, "loss": 0.3801947832107544, "step": 324 }, { "epoch": 9.028169014084508, "grad_norm": 0.3827228546142578, "learning_rate": 9.295261506157985e-07, "loss": 0.3665362596511841, "step": 325 }, { "epoch": 9.056338028169014, "grad_norm": 0.3930126130580902, "learning_rate": 9.291035786532163e-07, "loss": 0.3840763568878174, "step": 326 }, { "epoch": 9.084507042253522, "grad_norm": 0.39712509512901306, "learning_rate": 9.286798518753878e-07, "loss": 0.3788590431213379, "step": 327 }, { "epoch": 9.112676056338028, "grad_norm": 0.39198365807533264, "learning_rate": 9.282549715730579e-07, "loss": 0.3776211440563202, "step": 328 }, { "epoch": 9.140845070422536, "grad_norm": 0.3789290487766266, "learning_rate": 9.278289390404859e-07, "loss": 0.3739659786224365, "step": 329 }, { "epoch": 9.169014084507042, "grad_norm": 0.4031192660331726, "learning_rate": 9.274017555754407e-07, "loss": 0.36898356676101685, "step": 330 }, { "epoch": 9.19718309859155, "grad_norm": 0.37126442790031433, "learning_rate": 9.269734224791974e-07, "loss": 0.375528484582901, "step": 331 }, { "epoch": 9.225352112676056, "grad_norm": 0.3997706472873688, "learning_rate": 9.265439410565328e-07, "loss": 0.3717716634273529, "step": 332 }, { "epoch": 9.253521126760564, "grad_norm": 0.379086434841156, "learning_rate": 9.261133126157217e-07, "loss": 0.37263017892837524, "step": 333 }, { "epoch": 9.28169014084507, "grad_norm": 0.3867016136646271, "learning_rate": 9.256815384685328e-07, "loss": 0.36468106508255005, "step": 334 }, { "epoch": 9.309859154929578, "grad_norm": 0.374311238527298, "learning_rate": 9.252486199302256e-07, "loss": 0.3739643394947052, "step": 335 }, { "epoch": 9.338028169014084, "grad_norm": 0.39617857336997986, "learning_rate": 9.248145583195447e-07, "loss": 0.365461528301239, "step": 336 }, { "epoch": 9.366197183098592, "grad_norm": 0.4135814905166626, "learning_rate": 9.243793549587171e-07, "loss": 0.3639392852783203, "step": 337 }, { "epoch": 9.394366197183098, "grad_norm": 0.3823402225971222, "learning_rate": 9.239430111734476e-07, "loss": 0.37368497252464294, "step": 338 }, { "epoch": 9.422535211267606, "grad_norm": 0.3841151297092438, "learning_rate": 9.235055282929153e-07, "loss": 0.36813288927078247, "step": 339 }, { "epoch": 9.450704225352112, "grad_norm": 0.38074299693107605, "learning_rate": 9.230669076497687e-07, "loss": 0.38240814208984375, "step": 340 }, { "epoch": 9.47887323943662, "grad_norm": 0.4174596667289734, "learning_rate": 9.226271505801224e-07, "loss": 0.37689781188964844, "step": 341 }, { "epoch": 9.507042253521126, "grad_norm": 0.37084081768989563, "learning_rate": 9.221862584235526e-07, "loss": 0.3710534870624542, "step": 342 }, { "epoch": 9.535211267605634, "grad_norm": 0.37257879972457886, "learning_rate": 9.217442325230936e-07, "loss": 0.3733557462692261, "step": 343 }, { "epoch": 9.56338028169014, "grad_norm": 0.380638986825943, "learning_rate": 9.213010742252327e-07, "loss": 0.382003515958786, "step": 344 }, { "epoch": 9.591549295774648, "grad_norm": 0.37657788395881653, "learning_rate": 9.208567848799069e-07, "loss": 0.3800239562988281, "step": 345 }, { "epoch": 9.619718309859154, "grad_norm": 0.374194860458374, "learning_rate": 9.204113658404989e-07, "loss": 0.3673850893974304, "step": 346 }, { "epoch": 9.647887323943662, "grad_norm": 0.37916600704193115, "learning_rate": 9.199648184638318e-07, "loss": 0.3701593279838562, "step": 347 }, { "epoch": 9.676056338028168, "grad_norm": 0.40940916538238525, "learning_rate": 9.195171441101668e-07, "loss": 0.36426401138305664, "step": 348 }, { "epoch": 9.704225352112676, "grad_norm": 0.36714640259742737, "learning_rate": 9.190683441431974e-07, "loss": 0.36105120182037354, "step": 349 }, { "epoch": 9.732394366197184, "grad_norm": 0.3987036347389221, "learning_rate": 9.186184199300463e-07, "loss": 0.377488374710083, "step": 350 }, { "epoch": 9.76056338028169, "grad_norm": 0.379881888628006, "learning_rate": 9.181673728412605e-07, "loss": 0.36418646574020386, "step": 351 }, { "epoch": 9.788732394366198, "grad_norm": 0.37683361768722534, "learning_rate": 9.177152042508077e-07, "loss": 0.3779636323451996, "step": 352 }, { "epoch": 9.816901408450704, "grad_norm": 0.39010605216026306, "learning_rate": 9.17261915536072e-07, "loss": 0.36634212732315063, "step": 353 }, { "epoch": 9.845070422535212, "grad_norm": 0.36802294850349426, "learning_rate": 9.168075080778494e-07, "loss": 0.38199418783187866, "step": 354 }, { "epoch": 9.873239436619718, "grad_norm": 0.3733425736427307, "learning_rate": 9.163519832603436e-07, "loss": 0.3606574833393097, "step": 355 }, { "epoch": 9.901408450704226, "grad_norm": 0.3822286128997803, "learning_rate": 9.158953424711624e-07, "loss": 0.37162789702415466, "step": 356 }, { "epoch": 9.929577464788732, "grad_norm": 0.3741500973701477, "learning_rate": 9.154375871013128e-07, "loss": 0.37218177318573, "step": 357 }, { "epoch": 9.95774647887324, "grad_norm": 0.3810633718967438, "learning_rate": 9.149787185451969e-07, "loss": 0.3858764171600342, "step": 358 }, { "epoch": 9.985915492957746, "grad_norm": 0.3737441599369049, "learning_rate": 9.145187382006081e-07, "loss": 0.3804674744606018, "step": 359 }, { "epoch": 10.0, "grad_norm": 0.5574419498443604, "learning_rate": 9.140576474687263e-07, "loss": 0.3975532650947571, "step": 360 }, { "epoch": 10.028169014084508, "grad_norm": 0.408914715051651, "learning_rate": 9.135954477541137e-07, "loss": 0.3823505640029907, "step": 361 }, { "epoch": 10.056338028169014, "grad_norm": 0.39666157960891724, "learning_rate": 9.131321404647109e-07, "loss": 0.37434619665145874, "step": 362 }, { "epoch": 10.084507042253522, "grad_norm": 0.35813018679618835, "learning_rate": 9.126677270118322e-07, "loss": 0.3701414465904236, "step": 363 }, { "epoch": 10.112676056338028, "grad_norm": 0.38024720549583435, "learning_rate": 9.122022088101613e-07, "loss": 0.3589220643043518, "step": 364 }, { "epoch": 10.140845070422536, "grad_norm": 0.3755195438861847, "learning_rate": 9.117355872777477e-07, "loss": 0.3666345477104187, "step": 365 }, { "epoch": 10.169014084507042, "grad_norm": 0.3826354742050171, "learning_rate": 9.112678638360015e-07, "loss": 0.3757998049259186, "step": 366 }, { "epoch": 10.19718309859155, "grad_norm": 0.3689386248588562, "learning_rate": 9.107990399096893e-07, "loss": 0.36412084102630615, "step": 367 }, { "epoch": 10.225352112676056, "grad_norm": 0.3600921034812927, "learning_rate": 9.103291169269299e-07, "loss": 0.37014394998550415, "step": 368 }, { "epoch": 10.253521126760564, "grad_norm": 0.36930346488952637, "learning_rate": 9.098580963191907e-07, "loss": 0.37366440892219543, "step": 369 }, { "epoch": 10.28169014084507, "grad_norm": 0.38112977147102356, "learning_rate": 9.093859795212817e-07, "loss": 0.35555559396743774, "step": 370 }, { "epoch": 10.309859154929578, "grad_norm": 0.3857463598251343, "learning_rate": 9.089127679713529e-07, "loss": 0.36690396070480347, "step": 371 }, { "epoch": 10.338028169014084, "grad_norm": 0.39062997698783875, "learning_rate": 9.084384631108882e-07, "loss": 0.3616250157356262, "step": 372 }, { "epoch": 10.366197183098592, "grad_norm": 0.3763197958469391, "learning_rate": 9.079630663847031e-07, "loss": 0.3588902950286865, "step": 373 }, { "epoch": 10.394366197183098, "grad_norm": 0.3925309479236603, "learning_rate": 9.074865792409381e-07, "loss": 0.3592212498188019, "step": 374 }, { "epoch": 10.422535211267606, "grad_norm": 0.38808441162109375, "learning_rate": 9.070090031310558e-07, "loss": 0.36339810490608215, "step": 375 }, { "epoch": 10.450704225352112, "grad_norm": 0.3804055154323578, "learning_rate": 9.065303395098358e-07, "loss": 0.35527950525283813, "step": 376 }, { "epoch": 10.47887323943662, "grad_norm": 0.40296220779418945, "learning_rate": 9.060505898353705e-07, "loss": 0.37981516122817993, "step": 377 }, { "epoch": 10.507042253521126, "grad_norm": 0.382583886384964, "learning_rate": 9.055697555690607e-07, "loss": 0.3662206530570984, "step": 378 }, { "epoch": 10.535211267605634, "grad_norm": 0.3722359836101532, "learning_rate": 9.050878381756107e-07, "loss": 0.38016411662101746, "step": 379 }, { "epoch": 10.56338028169014, "grad_norm": 0.37797069549560547, "learning_rate": 9.046048391230247e-07, "loss": 0.3583446741104126, "step": 380 }, { "epoch": 10.591549295774648, "grad_norm": 0.3818921148777008, "learning_rate": 9.041207598826017e-07, "loss": 0.3454791307449341, "step": 381 }, { "epoch": 10.619718309859154, "grad_norm": 0.3798826336860657, "learning_rate": 9.036356019289309e-07, "loss": 0.37033557891845703, "step": 382 }, { "epoch": 10.647887323943662, "grad_norm": 0.3845714032649994, "learning_rate": 9.031493667398872e-07, "loss": 0.38480767607688904, "step": 383 }, { "epoch": 10.676056338028168, "grad_norm": 0.38121894001960754, "learning_rate": 9.026620557966279e-07, "loss": 0.3667231500148773, "step": 384 }, { "epoch": 10.704225352112676, "grad_norm": 0.3911556005477905, "learning_rate": 9.021736705835862e-07, "loss": 0.38062405586242676, "step": 385 }, { "epoch": 10.732394366197184, "grad_norm": 0.3855709135532379, "learning_rate": 9.016842125884684e-07, "loss": 0.3813501298427582, "step": 386 }, { "epoch": 10.76056338028169, "grad_norm": 0.36581486463546753, "learning_rate": 9.011936833022484e-07, "loss": 0.37611764669418335, "step": 387 }, { "epoch": 10.788732394366198, "grad_norm": 0.36487480998039246, "learning_rate": 9.007020842191634e-07, "loss": 0.3561417758464813, "step": 388 }, { "epoch": 10.816901408450704, "grad_norm": 0.38142985105514526, "learning_rate": 9.002094168367095e-07, "loss": 0.36552196741104126, "step": 389 }, { "epoch": 10.845070422535212, "grad_norm": 0.43826037645339966, "learning_rate": 8.997156826556369e-07, "loss": 0.3591921329498291, "step": 390 }, { "epoch": 10.873239436619718, "grad_norm": 0.392564982175827, "learning_rate": 8.992208831799456e-07, "loss": 0.35333842039108276, "step": 391 }, { "epoch": 10.901408450704226, "grad_norm": 0.37918829917907715, "learning_rate": 8.987250199168808e-07, "loss": 0.3890402615070343, "step": 392 }, { "epoch": 10.929577464788732, "grad_norm": 0.3998699188232422, "learning_rate": 8.982280943769278e-07, "loss": 0.37613236904144287, "step": 393 }, { "epoch": 10.95774647887324, "grad_norm": 0.38326117396354675, "learning_rate": 8.977301080738079e-07, "loss": 0.3537328243255615, "step": 394 }, { "epoch": 10.985915492957746, "grad_norm": 0.4009212851524353, "learning_rate": 8.97231062524474e-07, "loss": 0.3686075806617737, "step": 395 }, { "epoch": 11.0, "grad_norm": 0.5113705992698669, "learning_rate": 8.967309592491052e-07, "loss": 0.3567275404930115, "step": 396 }, { "epoch": 11.028169014084508, "grad_norm": 0.39269763231277466, "learning_rate": 8.962297997711027e-07, "loss": 0.3689637780189514, "step": 397 }, { "epoch": 11.056338028169014, "grad_norm": 0.3715799152851105, "learning_rate": 8.957275856170855e-07, "loss": 0.3731398582458496, "step": 398 }, { "epoch": 11.084507042253522, "grad_norm": 0.3999379873275757, "learning_rate": 8.952243183168848e-07, "loss": 0.35057908296585083, "step": 399 }, { "epoch": 11.112676056338028, "grad_norm": 0.3621755540370941, "learning_rate": 8.9471999940354e-07, "loss": 0.36143216490745544, "step": 400 }, { "epoch": 11.140845070422536, "grad_norm": 0.3664521872997284, "learning_rate": 8.942146304132943e-07, "loss": 0.36459916830062866, "step": 401 }, { "epoch": 11.169014084507042, "grad_norm": 0.36989837884902954, "learning_rate": 8.937082128855891e-07, "loss": 0.35209208726882935, "step": 402 }, { "epoch": 11.19718309859155, "grad_norm": 0.3864418864250183, "learning_rate": 8.932007483630596e-07, "loss": 0.3611026406288147, "step": 403 }, { "epoch": 11.225352112676056, "grad_norm": 0.3848041892051697, "learning_rate": 8.926922383915315e-07, "loss": 0.3566674590110779, "step": 404 }, { "epoch": 11.253521126760564, "grad_norm": 0.3938388228416443, "learning_rate": 8.921826845200138e-07, "loss": 0.36684882640838623, "step": 405 }, { "epoch": 11.28169014084507, "grad_norm": 0.38600727915763855, "learning_rate": 8.916720883006963e-07, "loss": 0.3495212495326996, "step": 406 }, { "epoch": 11.309859154929578, "grad_norm": 0.3858475983142853, "learning_rate": 8.911604512889434e-07, "loss": 0.36758288741111755, "step": 407 }, { "epoch": 11.338028169014084, "grad_norm": 0.3926028609275818, "learning_rate": 8.906477750432903e-07, "loss": 0.3653443455696106, "step": 408 }, { "epoch": 11.366197183098592, "grad_norm": 0.3862815201282501, "learning_rate": 8.901340611254378e-07, "loss": 0.36144793033599854, "step": 409 }, { "epoch": 11.394366197183098, "grad_norm": 0.3828945755958557, "learning_rate": 8.896193111002475e-07, "loss": 0.36112335324287415, "step": 410 }, { "epoch": 11.422535211267606, "grad_norm": 0.36892107129096985, "learning_rate": 8.891035265357371e-07, "loss": 0.3514392375946045, "step": 411 }, { "epoch": 11.450704225352112, "grad_norm": 0.3868485391139984, "learning_rate": 8.88586709003076e-07, "loss": 0.3583905100822449, "step": 412 }, { "epoch": 11.47887323943662, "grad_norm": 0.3802708089351654, "learning_rate": 8.8806886007658e-07, "loss": 0.3574969470500946, "step": 413 }, { "epoch": 11.507042253521126, "grad_norm": 0.4039209187030792, "learning_rate": 8.875499813337067e-07, "loss": 0.3605828881263733, "step": 414 }, { "epoch": 11.535211267605634, "grad_norm": 0.36766496300697327, "learning_rate": 8.87030074355051e-07, "loss": 0.3580583333969116, "step": 415 }, { "epoch": 11.56338028169014, "grad_norm": 0.40306782722473145, "learning_rate": 8.865091407243394e-07, "loss": 0.3507153391838074, "step": 416 }, { "epoch": 11.591549295774648, "grad_norm": 0.3760242760181427, "learning_rate": 8.859871820284261e-07, "loss": 0.3610009551048279, "step": 417 }, { "epoch": 11.619718309859154, "grad_norm": 0.3728201687335968, "learning_rate": 8.85464199857288e-07, "loss": 0.36293601989746094, "step": 418 }, { "epoch": 11.647887323943662, "grad_norm": 0.3799256980419159, "learning_rate": 8.849401958040192e-07, "loss": 0.3622777760028839, "step": 419 }, { "epoch": 11.676056338028168, "grad_norm": 0.37681055068969727, "learning_rate": 8.844151714648274e-07, "loss": 0.37725430727005005, "step": 420 }, { "epoch": 11.704225352112676, "grad_norm": 0.36682507395744324, "learning_rate": 8.838891284390273e-07, "loss": 0.3608296513557434, "step": 421 }, { "epoch": 11.732394366197184, "grad_norm": 0.40212753415107727, "learning_rate": 8.833620683290375e-07, "loss": 0.36940503120422363, "step": 422 }, { "epoch": 11.76056338028169, "grad_norm": 0.39507851004600525, "learning_rate": 8.828339927403745e-07, "loss": 0.36940622329711914, "step": 423 }, { "epoch": 11.788732394366198, "grad_norm": 0.3753476142883301, "learning_rate": 8.823049032816478e-07, "loss": 0.3654807209968567, "step": 424 }, { "epoch": 11.816901408450704, "grad_norm": 0.40209904313087463, "learning_rate": 8.817748015645558e-07, "loss": 0.38087406754493713, "step": 425 }, { "epoch": 11.845070422535212, "grad_norm": 0.41672196984291077, "learning_rate": 8.812436892038805e-07, "loss": 0.376999169588089, "step": 426 }, { "epoch": 11.873239436619718, "grad_norm": 0.38997018337249756, "learning_rate": 8.807115678174819e-07, "loss": 0.36242201924324036, "step": 427 }, { "epoch": 11.901408450704226, "grad_norm": 0.3844313323497772, "learning_rate": 8.801784390262943e-07, "loss": 0.3589880168437958, "step": 428 }, { "epoch": 11.929577464788732, "grad_norm": 0.39721062779426575, "learning_rate": 8.796443044543203e-07, "loss": 0.3740372657775879, "step": 429 }, { "epoch": 11.95774647887324, "grad_norm": 0.3949345052242279, "learning_rate": 8.791091657286267e-07, "loss": 0.367824912071228, "step": 430 }, { "epoch": 11.985915492957746, "grad_norm": 0.3663078844547272, "learning_rate": 8.785730244793386e-07, "loss": 0.3459323048591614, "step": 431 }, { "epoch": 12.0, "grad_norm": 0.5153440237045288, "learning_rate": 8.780358823396352e-07, "loss": 0.3602818250656128, "step": 432 }, { "epoch": 12.028169014084508, "grad_norm": 0.4119972586631775, "learning_rate": 8.774977409457447e-07, "loss": 0.36752861738204956, "step": 433 }, { "epoch": 12.056338028169014, "grad_norm": 0.3773941993713379, "learning_rate": 8.769586019369391e-07, "loss": 0.36021482944488525, "step": 434 }, { "epoch": 12.084507042253522, "grad_norm": 0.3795655071735382, "learning_rate": 8.764184669555293e-07, "loss": 0.3426026999950409, "step": 435 }, { "epoch": 12.112676056338028, "grad_norm": 0.4020242691040039, "learning_rate": 8.758773376468604e-07, "loss": 0.3724130392074585, "step": 436 }, { "epoch": 12.140845070422536, "grad_norm": 0.3684321343898773, "learning_rate": 8.753352156593055e-07, "loss": 0.3493257761001587, "step": 437 }, { "epoch": 12.169014084507042, "grad_norm": 0.37732994556427, "learning_rate": 8.747921026442629e-07, "loss": 0.36222606897354126, "step": 438 }, { "epoch": 12.19718309859155, "grad_norm": 0.38256269693374634, "learning_rate": 8.742480002561487e-07, "loss": 0.3597019612789154, "step": 439 }, { "epoch": 12.225352112676056, "grad_norm": 0.37773433327674866, "learning_rate": 8.737029101523929e-07, "loss": 0.36569148302078247, "step": 440 }, { "epoch": 12.253521126760564, "grad_norm": 0.39633604884147644, "learning_rate": 8.731568339934348e-07, "loss": 0.34569287300109863, "step": 441 }, { "epoch": 12.28169014084507, "grad_norm": 0.3998453617095947, "learning_rate": 8.726097734427172e-07, "loss": 0.36068615317344666, "step": 442 }, { "epoch": 12.309859154929578, "grad_norm": 0.3984638750553131, "learning_rate": 8.72061730166681e-07, "loss": 0.355583518743515, "step": 443 }, { "epoch": 12.338028169014084, "grad_norm": 0.38659578561782837, "learning_rate": 8.715127058347614e-07, "loss": 0.3660207688808441, "step": 444 }, { "epoch": 12.366197183098592, "grad_norm": 0.3950231075286865, "learning_rate": 8.709627021193816e-07, "loss": 0.34942448139190674, "step": 445 }, { "epoch": 12.394366197183098, "grad_norm": 0.404268354177475, "learning_rate": 8.704117206959484e-07, "loss": 0.3557840585708618, "step": 446 }, { "epoch": 12.422535211267606, "grad_norm": 0.40802863240242004, "learning_rate": 8.698597632428466e-07, "loss": 0.3627977967262268, "step": 447 }, { "epoch": 12.450704225352112, "grad_norm": 0.3712429702281952, "learning_rate": 8.693068314414344e-07, "loss": 0.35522907972335815, "step": 448 }, { "epoch": 12.47887323943662, "grad_norm": 0.37290823459625244, "learning_rate": 8.687529269760379e-07, "loss": 0.3544667363166809, "step": 449 }, { "epoch": 12.507042253521126, "grad_norm": 0.37418875098228455, "learning_rate": 8.681980515339463e-07, "loss": 0.3554455041885376, "step": 450 }, { "epoch": 12.535211267605634, "grad_norm": 0.3866615891456604, "learning_rate": 8.676422068054064e-07, "loss": 0.366887629032135, "step": 451 }, { "epoch": 12.56338028169014, "grad_norm": 0.40141481161117554, "learning_rate": 8.670853944836176e-07, "loss": 0.3531399369239807, "step": 452 }, { "epoch": 12.591549295774648, "grad_norm": 0.38647815585136414, "learning_rate": 8.665276162647267e-07, "loss": 0.35906854271888733, "step": 453 }, { "epoch": 12.619718309859154, "grad_norm": 0.38703131675720215, "learning_rate": 8.659688738478231e-07, "loss": 0.3740598261356354, "step": 454 }, { "epoch": 12.647887323943662, "grad_norm": 0.3907453715801239, "learning_rate": 8.654091689349329e-07, "loss": 0.36058950424194336, "step": 455 }, { "epoch": 12.676056338028168, "grad_norm": 0.3824431598186493, "learning_rate": 8.648485032310144e-07, "loss": 0.346851646900177, "step": 456 }, { "epoch": 12.704225352112676, "grad_norm": 0.3692627251148224, "learning_rate": 8.642868784439527e-07, "loss": 0.36401131749153137, "step": 457 }, { "epoch": 12.732394366197184, "grad_norm": 0.38447362184524536, "learning_rate": 8.63724296284554e-07, "loss": 0.37208425998687744, "step": 458 }, { "epoch": 12.76056338028169, "grad_norm": 0.41238147020339966, "learning_rate": 8.631607584665413e-07, "loss": 0.3508748412132263, "step": 459 }, { "epoch": 12.788732394366198, "grad_norm": 0.4168914556503296, "learning_rate": 8.625962667065487e-07, "loss": 0.3689703941345215, "step": 460 }, { "epoch": 12.816901408450704, "grad_norm": 0.362250417470932, "learning_rate": 8.620308227241157e-07, "loss": 0.3565211892127991, "step": 461 }, { "epoch": 12.845070422535212, "grad_norm": 0.3882714807987213, "learning_rate": 8.614644282416831e-07, "loss": 0.354469358921051, "step": 462 }, { "epoch": 12.873239436619718, "grad_norm": 0.41290637850761414, "learning_rate": 8.608970849845862e-07, "loss": 0.3469231128692627, "step": 463 }, { "epoch": 12.901408450704226, "grad_norm": 0.3723019063472748, "learning_rate": 8.603287946810513e-07, "loss": 0.3601073920726776, "step": 464 }, { "epoch": 12.929577464788732, "grad_norm": 0.38471633195877075, "learning_rate": 8.597595590621892e-07, "loss": 0.35276687145233154, "step": 465 }, { "epoch": 12.95774647887324, "grad_norm": 0.3747471570968628, "learning_rate": 8.591893798619903e-07, "loss": 0.36324065923690796, "step": 466 }, { "epoch": 12.985915492957746, "grad_norm": 0.3682200014591217, "learning_rate": 8.586182588173194e-07, "loss": 0.3429381251335144, "step": 467 }, { "epoch": 13.0, "grad_norm": 0.5452975034713745, "learning_rate": 8.580461976679099e-07, "loss": 0.3639674186706543, "step": 468 }, { "epoch": 13.028169014084508, "grad_norm": 0.37994059920310974, "learning_rate": 8.574731981563597e-07, "loss": 0.35528022050857544, "step": 469 }, { "epoch": 13.056338028169014, "grad_norm": 0.36460980772972107, "learning_rate": 8.568992620281243e-07, "loss": 0.34681588411331177, "step": 470 }, { "epoch": 13.084507042253522, "grad_norm": 0.3725976347923279, "learning_rate": 8.56324391031513e-07, "loss": 0.3548527956008911, "step": 471 }, { "epoch": 13.112676056338028, "grad_norm": 0.3775046467781067, "learning_rate": 8.557485869176825e-07, "loss": 0.3620424270629883, "step": 472 }, { "epoch": 13.140845070422536, "grad_norm": 0.3839409053325653, "learning_rate": 8.551718514406318e-07, "loss": 0.3539167642593384, "step": 473 }, { "epoch": 13.169014084507042, "grad_norm": 0.374140202999115, "learning_rate": 8.545941863571973e-07, "loss": 0.3624025583267212, "step": 474 }, { "epoch": 13.19718309859155, "grad_norm": 0.3937068283557892, "learning_rate": 8.540155934270471e-07, "loss": 0.3401454985141754, "step": 475 }, { "epoch": 13.225352112676056, "grad_norm": 0.38825297355651855, "learning_rate": 8.534360744126753e-07, "loss": 0.3499498665332794, "step": 476 }, { "epoch": 13.253521126760564, "grad_norm": 0.39202409982681274, "learning_rate": 8.528556310793979e-07, "loss": 0.3489566743373871, "step": 477 }, { "epoch": 13.28169014084507, "grad_norm": 0.3716176748275757, "learning_rate": 8.522742651953456e-07, "loss": 0.35014504194259644, "step": 478 }, { "epoch": 13.309859154929578, "grad_norm": 0.3892640471458435, "learning_rate": 8.516919785314595e-07, "loss": 0.34187570214271545, "step": 479 }, { "epoch": 13.338028169014084, "grad_norm": 0.36670979857444763, "learning_rate": 8.511087728614862e-07, "loss": 0.36834079027175903, "step": 480 }, { "epoch": 13.366197183098592, "grad_norm": 0.37734806537628174, "learning_rate": 8.50524649961971e-07, "loss": 0.343334436416626, "step": 481 }, { "epoch": 13.394366197183098, "grad_norm": 0.3850347697734833, "learning_rate": 8.499396116122535e-07, "loss": 0.3575423061847687, "step": 482 }, { "epoch": 13.422535211267606, "grad_norm": 0.3864496350288391, "learning_rate": 8.493536595944622e-07, "loss": 0.36800649762153625, "step": 483 }, { "epoch": 13.450704225352112, "grad_norm": 0.3789742588996887, "learning_rate": 8.487667956935087e-07, "loss": 0.3633601665496826, "step": 484 }, { "epoch": 13.47887323943662, "grad_norm": 0.37209466099739075, "learning_rate": 8.481790216970819e-07, "loss": 0.36307400465011597, "step": 485 }, { "epoch": 13.507042253521126, "grad_norm": 0.37267136573791504, "learning_rate": 8.475903393956433e-07, "loss": 0.36202266812324524, "step": 486 }, { "epoch": 13.535211267605634, "grad_norm": 0.38834360241889954, "learning_rate": 8.470007505824215e-07, "loss": 0.3597005605697632, "step": 487 }, { "epoch": 13.56338028169014, "grad_norm": 0.37330684065818787, "learning_rate": 8.464102570534061e-07, "loss": 0.34499961137771606, "step": 488 }, { "epoch": 13.591549295774648, "grad_norm": 0.3997851014137268, "learning_rate": 8.458188606073431e-07, "loss": 0.3451351523399353, "step": 489 }, { "epoch": 13.619718309859154, "grad_norm": 0.38458433747291565, "learning_rate": 8.452265630457282e-07, "loss": 0.351215124130249, "step": 490 }, { "epoch": 13.647887323943662, "grad_norm": 0.3588864505290985, "learning_rate": 8.446333661728028e-07, "loss": 0.35790491104125977, "step": 491 }, { "epoch": 13.676056338028168, "grad_norm": 0.3922884166240692, "learning_rate": 8.440392717955475e-07, "loss": 0.3594629466533661, "step": 492 }, { "epoch": 13.704225352112676, "grad_norm": 0.3857049345970154, "learning_rate": 8.434442817236765e-07, "loss": 0.34881383180618286, "step": 493 }, { "epoch": 13.732394366197184, "grad_norm": 0.4017575681209564, "learning_rate": 8.428483977696328e-07, "loss": 0.3498556613922119, "step": 494 }, { "epoch": 13.76056338028169, "grad_norm": 0.3752291798591614, "learning_rate": 8.422516217485825e-07, "loss": 0.3405389189720154, "step": 495 }, { "epoch": 13.788732394366198, "grad_norm": 0.3852419853210449, "learning_rate": 8.416539554784089e-07, "loss": 0.3572129011154175, "step": 496 }, { "epoch": 13.816901408450704, "grad_norm": 0.4124152958393097, "learning_rate": 8.410554007797068e-07, "loss": 0.3448854684829712, "step": 497 }, { "epoch": 13.845070422535212, "grad_norm": 0.4105253219604492, "learning_rate": 8.404559594757777e-07, "loss": 0.35539665818214417, "step": 498 }, { "epoch": 13.873239436619718, "grad_norm": 0.39284518361091614, "learning_rate": 8.398556333926239e-07, "loss": 0.36244136095046997, "step": 499 }, { "epoch": 13.901408450704226, "grad_norm": 0.35972821712493896, "learning_rate": 8.392544243589427e-07, "loss": 0.3578004240989685, "step": 500 }, { "epoch": 13.929577464788732, "grad_norm": 0.3711358904838562, "learning_rate": 8.38652334206121e-07, "loss": 0.34361594915390015, "step": 501 }, { "epoch": 13.95774647887324, "grad_norm": 0.4135587513446808, "learning_rate": 8.3804936476823e-07, "loss": 0.36592596769332886, "step": 502 }, { "epoch": 13.985915492957746, "grad_norm": 0.37095075845718384, "learning_rate": 8.374455178820189e-07, "loss": 0.3628469705581665, "step": 503 }, { "epoch": 14.0, "grad_norm": 0.5396003127098083, "learning_rate": 8.368407953869103e-07, "loss": 0.34858113527297974, "step": 504 }, { "epoch": 14.028169014084508, "grad_norm": 0.3776472806930542, "learning_rate": 8.362351991249937e-07, "loss": 0.352533757686615, "step": 505 }, { "epoch": 14.056338028169014, "grad_norm": 0.3781091570854187, "learning_rate": 8.356287309410204e-07, "loss": 0.3604869246482849, "step": 506 }, { "epoch": 14.084507042253522, "grad_norm": 0.3902469277381897, "learning_rate": 8.350213926823974e-07, "loss": 0.3640694320201874, "step": 507 }, { "epoch": 14.112676056338028, "grad_norm": 0.3881576359272003, "learning_rate": 8.344131861991828e-07, "loss": 0.3508457541465759, "step": 508 }, { "epoch": 14.140845070422536, "grad_norm": 0.372915655374527, "learning_rate": 8.338041133440788e-07, "loss": 0.351182758808136, "step": 509 }, { "epoch": 14.169014084507042, "grad_norm": 0.3760332465171814, "learning_rate": 8.331941759724268e-07, "loss": 0.35791683197021484, "step": 510 }, { "epoch": 14.19718309859155, "grad_norm": 0.3700595796108246, "learning_rate": 8.325833759422021e-07, "loss": 0.35949069261550903, "step": 511 }, { "epoch": 14.225352112676056, "grad_norm": 0.3730723261833191, "learning_rate": 8.319717151140072e-07, "loss": 0.3404577374458313, "step": 512 }, { "epoch": 14.253521126760564, "grad_norm": 0.41635406017303467, "learning_rate": 8.313591953510673e-07, "loss": 0.37283679842948914, "step": 513 }, { "epoch": 14.28169014084507, "grad_norm": 0.4026881456375122, "learning_rate": 8.307458185192238e-07, "loss": 0.34543269872665405, "step": 514 }, { "epoch": 14.309859154929578, "grad_norm": 0.39402303099632263, "learning_rate": 8.301315864869289e-07, "loss": 0.34635818004608154, "step": 515 }, { "epoch": 14.338028169014084, "grad_norm": 0.3800695836544037, "learning_rate": 8.295165011252396e-07, "loss": 0.3433900475502014, "step": 516 }, { "epoch": 14.366197183098592, "grad_norm": 0.35776469111442566, "learning_rate": 8.289005643078131e-07, "loss": 0.3383639454841614, "step": 517 }, { "epoch": 14.394366197183098, "grad_norm": 0.3785316050052643, "learning_rate": 8.282837779108993e-07, "loss": 0.346576452255249, "step": 518 }, { "epoch": 14.422535211267606, "grad_norm": 0.3899250328540802, "learning_rate": 8.276661438133368e-07, "loss": 0.35042616724967957, "step": 519 }, { "epoch": 14.450704225352112, "grad_norm": 0.37631621956825256, "learning_rate": 8.270476638965461e-07, "loss": 0.3533529043197632, "step": 520 }, { "epoch": 14.47887323943662, "grad_norm": 0.3743092119693756, "learning_rate": 8.264283400445243e-07, "loss": 0.3409396708011627, "step": 521 }, { "epoch": 14.507042253521126, "grad_norm": 0.38056522607803345, "learning_rate": 8.258081741438394e-07, "loss": 0.35600903630256653, "step": 522 }, { "epoch": 14.535211267605634, "grad_norm": 0.37500396370887756, "learning_rate": 8.25187168083624e-07, "loss": 0.3521459400653839, "step": 523 }, { "epoch": 14.56338028169014, "grad_norm": 0.38654470443725586, "learning_rate": 8.245653237555705e-07, "loss": 0.3409499228000641, "step": 524 }, { "epoch": 14.591549295774648, "grad_norm": 0.40645715594291687, "learning_rate": 8.239426430539243e-07, "loss": 0.359097957611084, "step": 525 }, { "epoch": 14.619718309859154, "grad_norm": 0.37087902426719666, "learning_rate": 8.23319127875479e-07, "loss": 0.3505946099758148, "step": 526 }, { "epoch": 14.647887323943662, "grad_norm": 0.3707801401615143, "learning_rate": 8.226947801195699e-07, "loss": 0.3502677083015442, "step": 527 }, { "epoch": 14.676056338028168, "grad_norm": 0.38573163747787476, "learning_rate": 8.220696016880687e-07, "loss": 0.3493162989616394, "step": 528 }, { "epoch": 14.704225352112676, "grad_norm": 0.4001166820526123, "learning_rate": 8.21443594485377e-07, "loss": 0.3506782352924347, "step": 529 }, { "epoch": 14.732394366197184, "grad_norm": 0.38506975769996643, "learning_rate": 8.208167604184217e-07, "loss": 0.34733596444129944, "step": 530 }, { "epoch": 14.76056338028169, "grad_norm": 0.3804541826248169, "learning_rate": 8.201891013966478e-07, "loss": 0.33838513493537903, "step": 531 }, { "epoch": 14.788732394366198, "grad_norm": 0.3855923116207123, "learning_rate": 8.195606193320136e-07, "loss": 0.3545091450214386, "step": 532 }, { "epoch": 14.816901408450704, "grad_norm": 0.38002100586891174, "learning_rate": 8.189313161389844e-07, "loss": 0.3370533585548401, "step": 533 }, { "epoch": 14.845070422535212, "grad_norm": 0.3642506003379822, "learning_rate": 8.183011937345271e-07, "loss": 0.3401836156845093, "step": 534 }, { "epoch": 14.873239436619718, "grad_norm": 0.3708590865135193, "learning_rate": 8.176702540381036e-07, "loss": 0.34280404448509216, "step": 535 }, { "epoch": 14.901408450704226, "grad_norm": 0.39392298460006714, "learning_rate": 8.170384989716657e-07, "loss": 0.3544384837150574, "step": 536 }, { "epoch": 14.929577464788732, "grad_norm": 0.3707094192504883, "learning_rate": 8.164059304596488e-07, "loss": 0.3490797281265259, "step": 537 }, { "epoch": 14.95774647887324, "grad_norm": 0.38153553009033203, "learning_rate": 8.157725504289664e-07, "loss": 0.3643110990524292, "step": 538 }, { "epoch": 14.985915492957746, "grad_norm": 0.3858087360858917, "learning_rate": 8.151383608090039e-07, "loss": 0.350948303937912, "step": 539 }, { "epoch": 15.0, "grad_norm": 0.5356346368789673, "learning_rate": 8.145033635316128e-07, "loss": 0.3669792115688324, "step": 540 }, { "epoch": 15.028169014084508, "grad_norm": 0.3815496861934662, "learning_rate": 8.138675605311051e-07, "loss": 0.3322640657424927, "step": 541 }, { "epoch": 15.056338028169014, "grad_norm": 0.37720146775245667, "learning_rate": 8.13230953744247e-07, "loss": 0.3458060026168823, "step": 542 }, { "epoch": 15.084507042253522, "grad_norm": 0.3754969835281372, "learning_rate": 8.125935451102528e-07, "loss": 0.3553546965122223, "step": 543 }, { "epoch": 15.112676056338028, "grad_norm": 0.36978018283843994, "learning_rate": 8.119553365707802e-07, "loss": 0.3408074975013733, "step": 544 }, { "epoch": 15.140845070422536, "grad_norm": 0.3989609479904175, "learning_rate": 8.113163300699228e-07, "loss": 0.3464876413345337, "step": 545 }, { "epoch": 15.169014084507042, "grad_norm": 0.36658549308776855, "learning_rate": 8.106765275542053e-07, "loss": 0.3466334342956543, "step": 546 }, { "epoch": 15.19718309859155, "grad_norm": 0.39741599559783936, "learning_rate": 8.100359309725774e-07, "loss": 0.34825024008750916, "step": 547 }, { "epoch": 15.225352112676056, "grad_norm": 0.3813125789165497, "learning_rate": 8.093945422764069e-07, "loss": 0.3407784104347229, "step": 548 }, { "epoch": 15.253521126760564, "grad_norm": 0.3777227997779846, "learning_rate": 8.087523634194754e-07, "loss": 0.34016621112823486, "step": 549 }, { "epoch": 15.28169014084507, "grad_norm": 0.38441628217697144, "learning_rate": 8.081093963579707e-07, "loss": 0.34003114700317383, "step": 550 }, { "epoch": 15.309859154929578, "grad_norm": 0.3793286681175232, "learning_rate": 8.074656430504823e-07, "loss": 0.3448694348335266, "step": 551 }, { "epoch": 15.338028169014084, "grad_norm": 0.3836040198802948, "learning_rate": 8.068211054579943e-07, "loss": 0.3474279046058655, "step": 552 }, { "epoch": 15.366197183098592, "grad_norm": 0.37479010224342346, "learning_rate": 8.061757855438799e-07, "loss": 0.3372560739517212, "step": 553 }, { "epoch": 15.394366197183098, "grad_norm": 0.37694352865219116, "learning_rate": 8.055296852738956e-07, "loss": 0.34544262290000916, "step": 554 }, { "epoch": 15.422535211267606, "grad_norm": 0.3711282014846802, "learning_rate": 8.048828066161747e-07, "loss": 0.3580097556114197, "step": 555 }, { "epoch": 15.450704225352112, "grad_norm": 0.3893590569496155, "learning_rate": 8.04235151541222e-07, "loss": 0.34728002548217773, "step": 556 }, { "epoch": 15.47887323943662, "grad_norm": 0.36593759059906006, "learning_rate": 8.035867220219071e-07, "loss": 0.34468919038772583, "step": 557 }, { "epoch": 15.507042253521126, "grad_norm": 0.39856672286987305, "learning_rate": 8.029375200334587e-07, "loss": 0.3579489588737488, "step": 558 }, { "epoch": 15.535211267605634, "grad_norm": 0.3780282735824585, "learning_rate": 8.022875475534588e-07, "loss": 0.3498050272464752, "step": 559 }, { "epoch": 15.56338028169014, "grad_norm": 0.3642277121543884, "learning_rate": 8.01636806561836e-07, "loss": 0.33729854226112366, "step": 560 }, { "epoch": 15.591549295774648, "grad_norm": 0.37629276514053345, "learning_rate": 8.009852990408606e-07, "loss": 0.3551182746887207, "step": 561 }, { "epoch": 15.619718309859154, "grad_norm": 0.3910060226917267, "learning_rate": 8.003330269751372e-07, "loss": 0.34621596336364746, "step": 562 }, { "epoch": 15.647887323943662, "grad_norm": 0.39113184809684753, "learning_rate": 7.996799923515997e-07, "loss": 0.3548876643180847, "step": 563 }, { "epoch": 15.676056338028168, "grad_norm": 0.3808310329914093, "learning_rate": 7.990261971595048e-07, "loss": 0.36337122321128845, "step": 564 }, { "epoch": 15.704225352112676, "grad_norm": 0.39411720633506775, "learning_rate": 7.983716433904262e-07, "loss": 0.33870428800582886, "step": 565 }, { "epoch": 15.732394366197184, "grad_norm": 0.3887096047401428, "learning_rate": 7.977163330382479e-07, "loss": 0.35169994831085205, "step": 566 }, { "epoch": 15.76056338028169, "grad_norm": 0.3939286172389984, "learning_rate": 7.970602680991592e-07, "loss": 0.34998422861099243, "step": 567 }, { "epoch": 15.788732394366198, "grad_norm": 0.3565775454044342, "learning_rate": 7.964034505716476e-07, "loss": 0.3486759662628174, "step": 568 }, { "epoch": 15.816901408450704, "grad_norm": 0.3899053931236267, "learning_rate": 7.957458824564931e-07, "loss": 0.35851621627807617, "step": 569 }, { "epoch": 15.845070422535212, "grad_norm": 0.3830185830593109, "learning_rate": 7.950875657567621e-07, "loss": 0.33559471368789673, "step": 570 }, { "epoch": 15.873239436619718, "grad_norm": 0.40776732563972473, "learning_rate": 7.944285024778017e-07, "loss": 0.35246986150741577, "step": 571 }, { "epoch": 15.901408450704226, "grad_norm": 0.3857426047325134, "learning_rate": 7.93768694627233e-07, "loss": 0.36824092268943787, "step": 572 }, { "epoch": 15.929577464788732, "grad_norm": 0.3712272644042969, "learning_rate": 7.931081442149448e-07, "loss": 0.34515848755836487, "step": 573 }, { "epoch": 15.95774647887324, "grad_norm": 0.3721475303173065, "learning_rate": 7.924468532530883e-07, "loss": 0.3364425301551819, "step": 574 }, { "epoch": 15.985915492957746, "grad_norm": 0.37941086292266846, "learning_rate": 7.917848237560708e-07, "loss": 0.34333279728889465, "step": 575 }, { "epoch": 16.0, "grad_norm": 0.5400592684745789, "learning_rate": 7.911220577405484e-07, "loss": 0.34126609563827515, "step": 576 }, { "epoch": 16.028169014084508, "grad_norm": 0.3806915581226349, "learning_rate": 7.904585572254218e-07, "loss": 0.3439810276031494, "step": 577 }, { "epoch": 16.056338028169016, "grad_norm": 0.365713506937027, "learning_rate": 7.897943242318285e-07, "loss": 0.3540935218334198, "step": 578 }, { "epoch": 16.08450704225352, "grad_norm": 0.3724060654640198, "learning_rate": 7.891293607831373e-07, "loss": 0.3323290944099426, "step": 579 }, { "epoch": 16.112676056338028, "grad_norm": 0.38560864329338074, "learning_rate": 7.884636689049422e-07, "loss": 0.34806182980537415, "step": 580 }, { "epoch": 16.140845070422536, "grad_norm": 0.3800376057624817, "learning_rate": 7.877972506250562e-07, "loss": 0.33772388100624084, "step": 581 }, { "epoch": 16.169014084507044, "grad_norm": 0.38416358828544617, "learning_rate": 7.871301079735049e-07, "loss": 0.3476141095161438, "step": 582 }, { "epoch": 16.197183098591548, "grad_norm": 0.38566768169403076, "learning_rate": 7.864622429825204e-07, "loss": 0.357825368642807, "step": 583 }, { "epoch": 16.225352112676056, "grad_norm": 0.36804598569869995, "learning_rate": 7.857936576865356e-07, "loss": 0.34387123584747314, "step": 584 }, { "epoch": 16.253521126760564, "grad_norm": 0.37404003739356995, "learning_rate": 7.851243541221769e-07, "loss": 0.3607553243637085, "step": 585 }, { "epoch": 16.281690140845072, "grad_norm": 0.3866511881351471, "learning_rate": 7.844543343282595e-07, "loss": 0.34078526496887207, "step": 586 }, { "epoch": 16.309859154929576, "grad_norm": 0.37802958488464355, "learning_rate": 7.837836003457793e-07, "loss": 0.35176295042037964, "step": 587 }, { "epoch": 16.338028169014084, "grad_norm": 0.3895554542541504, "learning_rate": 7.831121542179086e-07, "loss": 0.35642701387405396, "step": 588 }, { "epoch": 16.366197183098592, "grad_norm": 0.38933444023132324, "learning_rate": 7.824399979899889e-07, "loss": 0.3432256579399109, "step": 589 }, { "epoch": 16.3943661971831, "grad_norm": 0.3860255181789398, "learning_rate": 7.817671337095244e-07, "loss": 0.33256232738494873, "step": 590 }, { "epoch": 16.422535211267604, "grad_norm": 0.37760087847709656, "learning_rate": 7.810935634261764e-07, "loss": 0.33182838559150696, "step": 591 }, { "epoch": 16.450704225352112, "grad_norm": 0.43271970748901367, "learning_rate": 7.804192891917571e-07, "loss": 0.3370242416858673, "step": 592 }, { "epoch": 16.47887323943662, "grad_norm": 0.3976680338382721, "learning_rate": 7.797443130602226e-07, "loss": 0.3409218490123749, "step": 593 }, { "epoch": 16.507042253521128, "grad_norm": 0.3847591280937195, "learning_rate": 7.79068637087667e-07, "loss": 0.34397250413894653, "step": 594 }, { "epoch": 16.535211267605632, "grad_norm": 0.4225793182849884, "learning_rate": 7.783922633323169e-07, "loss": 0.3583061099052429, "step": 595 }, { "epoch": 16.56338028169014, "grad_norm": 0.38739070296287537, "learning_rate": 7.777151938545235e-07, "loss": 0.3420133590698242, "step": 596 }, { "epoch": 16.591549295774648, "grad_norm": 0.38219913840293884, "learning_rate": 7.770374307167585e-07, "loss": 0.3353823721408844, "step": 597 }, { "epoch": 16.619718309859156, "grad_norm": 0.38513585925102234, "learning_rate": 7.763589759836058e-07, "loss": 0.3592385947704315, "step": 598 }, { "epoch": 16.647887323943664, "grad_norm": 0.37446147203445435, "learning_rate": 7.756798317217558e-07, "loss": 0.3497603237628937, "step": 599 }, { "epoch": 16.676056338028168, "grad_norm": 0.3799225091934204, "learning_rate": 7.75e-07, "loss": 0.33129948377609253, "step": 600 }, { "epoch": 16.704225352112676, "grad_norm": 0.3865351676940918, "learning_rate": 7.743194828892235e-07, "loss": 0.34597867727279663, "step": 601 }, { "epoch": 16.732394366197184, "grad_norm": 0.38422080874443054, "learning_rate": 7.736382824623999e-07, "loss": 0.34420183300971985, "step": 602 }, { "epoch": 16.760563380281692, "grad_norm": 0.3683478832244873, "learning_rate": 7.729564007945834e-07, "loss": 0.3431108593940735, "step": 603 }, { "epoch": 16.788732394366196, "grad_norm": 0.36752188205718994, "learning_rate": 7.72273839962904e-07, "loss": 0.3431229591369629, "step": 604 }, { "epoch": 16.816901408450704, "grad_norm": 0.38291314244270325, "learning_rate": 7.715906020465602e-07, "loss": 0.344490647315979, "step": 605 }, { "epoch": 16.845070422535212, "grad_norm": 0.3902081847190857, "learning_rate": 7.709066891268133e-07, "loss": 0.3327999711036682, "step": 606 }, { "epoch": 16.87323943661972, "grad_norm": 0.39360862970352173, "learning_rate": 7.702221032869808e-07, "loss": 0.3507109582424164, "step": 607 }, { "epoch": 16.901408450704224, "grad_norm": 0.38735586404800415, "learning_rate": 7.695368466124296e-07, "loss": 0.3384973704814911, "step": 608 }, { "epoch": 16.929577464788732, "grad_norm": 0.37811803817749023, "learning_rate": 7.688509211905707e-07, "loss": 0.34107083082199097, "step": 609 }, { "epoch": 16.95774647887324, "grad_norm": 0.3972027897834778, "learning_rate": 7.681643291108517e-07, "loss": 0.33823147416114807, "step": 610 }, { "epoch": 16.985915492957748, "grad_norm": 0.409056693315506, "learning_rate": 7.67477072464751e-07, "loss": 0.3435848653316498, "step": 611 }, { "epoch": 17.0, "grad_norm": 0.5482017397880554, "learning_rate": 7.667891533457718e-07, "loss": 0.34469878673553467, "step": 612 }, { "epoch": 17.028169014084508, "grad_norm": 0.37880438566207886, "learning_rate": 7.661005738494349e-07, "loss": 0.340010404586792, "step": 613 }, { "epoch": 17.056338028169016, "grad_norm": 0.37945932149887085, "learning_rate": 7.654113360732732e-07, "loss": 0.33479446172714233, "step": 614 }, { "epoch": 17.08450704225352, "grad_norm": 0.3803980350494385, "learning_rate": 7.647214421168238e-07, "loss": 0.33284443616867065, "step": 615 }, { "epoch": 17.112676056338028, "grad_norm": 0.3687640428543091, "learning_rate": 7.640308940816239e-07, "loss": 0.3429029881954193, "step": 616 }, { "epoch": 17.140845070422536, "grad_norm": 0.3732313811779022, "learning_rate": 7.633396940712023e-07, "loss": 0.346540242433548, "step": 617 }, { "epoch": 17.169014084507044, "grad_norm": 0.36889249086380005, "learning_rate": 7.626478441910744e-07, "loss": 0.34171944856643677, "step": 618 }, { "epoch": 17.197183098591548, "grad_norm": 0.3906193673610687, "learning_rate": 7.619553465487344e-07, "loss": 0.3259759545326233, "step": 619 }, { "epoch": 17.225352112676056, "grad_norm": 0.3841656744480133, "learning_rate": 7.612622032536507e-07, "loss": 0.331236869096756, "step": 620 }, { "epoch": 17.253521126760564, "grad_norm": 0.4112148880958557, "learning_rate": 7.60568416417258e-07, "loss": 0.34965720772743225, "step": 621 }, { "epoch": 17.281690140845072, "grad_norm": 0.3935334384441376, "learning_rate": 7.59873988152951e-07, "loss": 0.34438279271125793, "step": 622 }, { "epoch": 17.309859154929576, "grad_norm": 0.36690011620521545, "learning_rate": 7.591789205760789e-07, "loss": 0.346940815448761, "step": 623 }, { "epoch": 17.338028169014084, "grad_norm": 0.39343443512916565, "learning_rate": 7.584832158039378e-07, "loss": 0.3512117862701416, "step": 624 }, { "epoch": 17.366197183098592, "grad_norm": 0.39378273487091064, "learning_rate": 7.577868759557653e-07, "loss": 0.3479688763618469, "step": 625 }, { "epoch": 17.3943661971831, "grad_norm": 0.38349923491477966, "learning_rate": 7.570899031527332e-07, "loss": 0.3258413076400757, "step": 626 }, { "epoch": 17.422535211267604, "grad_norm": 0.3738706111907959, "learning_rate": 7.563922995179418e-07, "loss": 0.34239041805267334, "step": 627 }, { "epoch": 17.450704225352112, "grad_norm": 0.39493557810783386, "learning_rate": 7.556940671764124e-07, "loss": 0.35372307896614075, "step": 628 }, { "epoch": 17.47887323943662, "grad_norm": 0.3801724910736084, "learning_rate": 7.54995208255082e-07, "loss": 0.34363144636154175, "step": 629 }, { "epoch": 17.507042253521128, "grad_norm": 0.39354074001312256, "learning_rate": 7.54295724882796e-07, "loss": 0.35302555561065674, "step": 630 }, { "epoch": 17.535211267605632, "grad_norm": 0.3849182724952698, "learning_rate": 7.535956191903021e-07, "loss": 0.3301173448562622, "step": 631 }, { "epoch": 17.56338028169014, "grad_norm": 0.42660990357398987, "learning_rate": 7.528948933102438e-07, "loss": 0.34373244643211365, "step": 632 }, { "epoch": 17.591549295774648, "grad_norm": 0.4158874750137329, "learning_rate": 7.521935493771534e-07, "loss": 0.3334096670150757, "step": 633 }, { "epoch": 17.619718309859156, "grad_norm": 0.3729299008846283, "learning_rate": 7.514915895274463e-07, "loss": 0.34392040967941284, "step": 634 }, { "epoch": 17.647887323943664, "grad_norm": 0.37672823667526245, "learning_rate": 7.507890158994139e-07, "loss": 0.34529420733451843, "step": 635 }, { "epoch": 17.676056338028168, "grad_norm": 0.38537341356277466, "learning_rate": 7.500858306332172e-07, "loss": 0.3379954695701599, "step": 636 }, { "epoch": 17.704225352112676, "grad_norm": 0.3827511966228485, "learning_rate": 7.493820358708809e-07, "loss": 0.34008336067199707, "step": 637 }, { "epoch": 17.732394366197184, "grad_norm": 0.3780139684677124, "learning_rate": 7.486776337562853e-07, "loss": 0.34520262479782104, "step": 638 }, { "epoch": 17.760563380281692, "grad_norm": 0.40986132621765137, "learning_rate": 7.479726264351618e-07, "loss": 0.3471469283103943, "step": 639 }, { "epoch": 17.788732394366196, "grad_norm": 0.38342809677124023, "learning_rate": 7.472670160550848e-07, "loss": 0.3339645266532898, "step": 640 }, { "epoch": 17.816901408450704, "grad_norm": 0.3707945644855499, "learning_rate": 7.46560804765466e-07, "loss": 0.3366163969039917, "step": 641 }, { "epoch": 17.845070422535212, "grad_norm": 0.3779657483100891, "learning_rate": 7.458539947175473e-07, "loss": 0.3418515920639038, "step": 642 }, { "epoch": 17.87323943661972, "grad_norm": 0.3670470118522644, "learning_rate": 7.45146588064395e-07, "loss": 0.36023664474487305, "step": 643 }, { "epoch": 17.901408450704224, "grad_norm": 0.3905658721923828, "learning_rate": 7.444385869608921e-07, "loss": 0.3438882827758789, "step": 644 }, { "epoch": 17.929577464788732, "grad_norm": 0.3817150294780731, "learning_rate": 7.437299935637328e-07, "loss": 0.3405934274196625, "step": 645 }, { "epoch": 17.95774647887324, "grad_norm": 0.39704108238220215, "learning_rate": 7.430208100314156e-07, "loss": 0.34964901208877563, "step": 646 }, { "epoch": 17.985915492957748, "grad_norm": 0.3975781798362732, "learning_rate": 7.423110385242366e-07, "loss": 0.3247070908546448, "step": 647 }, { "epoch": 18.0, "grad_norm": 0.5164637565612793, "learning_rate": 7.416006812042827e-07, "loss": 0.32823723554611206, "step": 648 }, { "epoch": 18.028169014084508, "grad_norm": 0.3880039155483246, "learning_rate": 7.408897402354255e-07, "loss": 0.33646905422210693, "step": 649 }, { "epoch": 18.056338028169016, "grad_norm": 0.3736721873283386, "learning_rate": 7.401782177833147e-07, "loss": 0.34878233075141907, "step": 650 }, { "epoch": 18.08450704225352, "grad_norm": 0.3867191672325134, "learning_rate": 7.394661160153709e-07, "loss": 0.3172820508480072, "step": 651 }, { "epoch": 18.112676056338028, "grad_norm": 0.3890867531299591, "learning_rate": 7.387534371007797e-07, "loss": 0.3448027968406677, "step": 652 }, { "epoch": 18.140845070422536, "grad_norm": 0.3825511634349823, "learning_rate": 7.380401832104845e-07, "loss": 0.3210564851760864, "step": 653 }, { "epoch": 18.169014084507044, "grad_norm": 0.39171501994132996, "learning_rate": 7.373263565171805e-07, "loss": 0.3514065742492676, "step": 654 }, { "epoch": 18.197183098591548, "grad_norm": 0.39238640666007996, "learning_rate": 7.366119591953075e-07, "loss": 0.32657837867736816, "step": 655 }, { "epoch": 18.225352112676056, "grad_norm": 0.3783596456050873, "learning_rate": 7.358969934210438e-07, "loss": 0.34692835807800293, "step": 656 }, { "epoch": 18.253521126760564, "grad_norm": 0.3858647644519806, "learning_rate": 7.35181461372299e-07, "loss": 0.3333381414413452, "step": 657 }, { "epoch": 18.281690140845072, "grad_norm": 0.3780527114868164, "learning_rate": 7.344653652287077e-07, "loss": 0.3395627737045288, "step": 658 }, { "epoch": 18.309859154929576, "grad_norm": 0.39698007702827454, "learning_rate": 7.337487071716232e-07, "loss": 0.3523014485836029, "step": 659 }, { "epoch": 18.338028169014084, "grad_norm": 0.3739187717437744, "learning_rate": 7.330314893841101e-07, "loss": 0.3379012942314148, "step": 660 }, { "epoch": 18.366197183098592, "grad_norm": 0.3841306269168854, "learning_rate": 7.323137140509381e-07, "loss": 0.34076976776123047, "step": 661 }, { "epoch": 18.3943661971831, "grad_norm": 0.3925968110561371, "learning_rate": 7.315953833585755e-07, "loss": 0.3256088197231293, "step": 662 }, { "epoch": 18.422535211267604, "grad_norm": 0.3602692484855652, "learning_rate": 7.308764994951821e-07, "loss": 0.3451104164123535, "step": 663 }, { "epoch": 18.450704225352112, "grad_norm": 0.3772573173046112, "learning_rate": 7.301570646506027e-07, "loss": 0.3467863202095032, "step": 664 }, { "epoch": 18.47887323943662, "grad_norm": 0.39093321561813354, "learning_rate": 7.294370810163607e-07, "loss": 0.33636775612831116, "step": 665 }, { "epoch": 18.507042253521128, "grad_norm": 0.3880842328071594, "learning_rate": 7.287165507856512e-07, "loss": 0.3315805196762085, "step": 666 }, { "epoch": 18.535211267605632, "grad_norm": 0.38826221227645874, "learning_rate": 7.279954761533342e-07, "loss": 0.3530000150203705, "step": 667 }, { "epoch": 18.56338028169014, "grad_norm": 0.37676602602005005, "learning_rate": 7.27273859315928e-07, "loss": 0.3325963616371155, "step": 668 }, { "epoch": 18.591549295774648, "grad_norm": 0.3871600925922394, "learning_rate": 7.265517024716026e-07, "loss": 0.3362300395965576, "step": 669 }, { "epoch": 18.619718309859156, "grad_norm": 0.39551645517349243, "learning_rate": 7.258290078201731e-07, "loss": 0.3296426236629486, "step": 670 }, { "epoch": 18.647887323943664, "grad_norm": 0.3936498165130615, "learning_rate": 7.251057775630927e-07, "loss": 0.3340068757534027, "step": 671 }, { "epoch": 18.676056338028168, "grad_norm": 0.38042065501213074, "learning_rate": 7.243820139034464e-07, "loss": 0.33358412981033325, "step": 672 }, { "epoch": 18.704225352112676, "grad_norm": 0.39178362488746643, "learning_rate": 7.236577190459433e-07, "loss": 0.33916863799095154, "step": 673 }, { "epoch": 18.732394366197184, "grad_norm": 0.41885051131248474, "learning_rate": 7.229328951969115e-07, "loss": 0.3470945954322815, "step": 674 }, { "epoch": 18.760563380281692, "grad_norm": 0.40124213695526123, "learning_rate": 7.222075445642904e-07, "loss": 0.3349032402038574, "step": 675 }, { "epoch": 18.788732394366196, "grad_norm": 0.37713173031806946, "learning_rate": 7.214816693576234e-07, "loss": 0.342884361743927, "step": 676 }, { "epoch": 18.816901408450704, "grad_norm": 0.37491437792778015, "learning_rate": 7.207552717880522e-07, "loss": 0.33229076862335205, "step": 677 }, { "epoch": 18.845070422535212, "grad_norm": 0.38801443576812744, "learning_rate": 7.200283540683102e-07, "loss": 0.34812432527542114, "step": 678 }, { "epoch": 18.87323943661972, "grad_norm": 0.39582112431526184, "learning_rate": 7.193009184127145e-07, "loss": 0.3479095995426178, "step": 679 }, { "epoch": 18.901408450704224, "grad_norm": 0.38679373264312744, "learning_rate": 7.185729670371604e-07, "loss": 0.34037941694259644, "step": 680 }, { "epoch": 18.929577464788732, "grad_norm": 0.38188573718070984, "learning_rate": 7.17844502159114e-07, "loss": 0.33759552240371704, "step": 681 }, { "epoch": 18.95774647887324, "grad_norm": 0.37706470489501953, "learning_rate": 7.171155259976057e-07, "loss": 0.3348686695098877, "step": 682 }, { "epoch": 18.985915492957748, "grad_norm": 0.3883419334888458, "learning_rate": 7.163860407732231e-07, "loss": 0.34951701760292053, "step": 683 }, { "epoch": 19.0, "grad_norm": 0.5583506226539612, "learning_rate": 7.156560487081051e-07, "loss": 0.33454418182373047, "step": 684 }, { "epoch": 19.028169014084508, "grad_norm": 0.37495335936546326, "learning_rate": 7.149255520259338e-07, "loss": 0.3353433609008789, "step": 685 }, { "epoch": 19.056338028169016, "grad_norm": 0.4003477096557617, "learning_rate": 7.141945529519288e-07, "loss": 0.3362414836883545, "step": 686 }, { "epoch": 19.08450704225352, "grad_norm": 0.3699679374694824, "learning_rate": 7.134630537128403e-07, "loss": 0.33315083384513855, "step": 687 }, { "epoch": 19.112676056338028, "grad_norm": 0.39900684356689453, "learning_rate": 7.127310565369415e-07, "loss": 0.3300708532333374, "step": 688 }, { "epoch": 19.140845070422536, "grad_norm": 0.40120062232017517, "learning_rate": 7.11998563654023e-07, "loss": 0.3343963027000427, "step": 689 }, { "epoch": 19.169014084507044, "grad_norm": 0.36110588908195496, "learning_rate": 7.11265577295385e-07, "loss": 0.3359455466270447, "step": 690 }, { "epoch": 19.197183098591548, "grad_norm": 0.3858158588409424, "learning_rate": 7.105320996938314e-07, "loss": 0.3431977331638336, "step": 691 }, { "epoch": 19.225352112676056, "grad_norm": 0.38371938467025757, "learning_rate": 7.097981330836616e-07, "loss": 0.3372940421104431, "step": 692 }, { "epoch": 19.253521126760564, "grad_norm": 0.3879927396774292, "learning_rate": 7.090636797006657e-07, "loss": 0.3215637803077698, "step": 693 }, { "epoch": 19.281690140845072, "grad_norm": 0.3851448595523834, "learning_rate": 7.083287417821157e-07, "loss": 0.34024134278297424, "step": 694 }, { "epoch": 19.309859154929576, "grad_norm": 0.37001243233680725, "learning_rate": 7.075933215667604e-07, "loss": 0.3312854468822479, "step": 695 }, { "epoch": 19.338028169014084, "grad_norm": 0.3776569664478302, "learning_rate": 7.068574212948169e-07, "loss": 0.34480786323547363, "step": 696 }, { "epoch": 19.366197183098592, "grad_norm": 0.38904985785484314, "learning_rate": 7.06121043207965e-07, "loss": 0.3429100513458252, "step": 697 }, { "epoch": 19.3943661971831, "grad_norm": 0.38423457741737366, "learning_rate": 7.053841895493406e-07, "loss": 0.33715760707855225, "step": 698 }, { "epoch": 19.422535211267604, "grad_norm": 0.3800332248210907, "learning_rate": 7.046468625635274e-07, "loss": 0.3274102807044983, "step": 699 }, { "epoch": 19.450704225352112, "grad_norm": 0.3835005462169647, "learning_rate": 7.039090644965509e-07, "loss": 0.317699670791626, "step": 700 }, { "epoch": 19.47887323943662, "grad_norm": 0.3867398202419281, "learning_rate": 7.031707975958726e-07, "loss": 0.3352523446083069, "step": 701 }, { "epoch": 19.507042253521128, "grad_norm": 0.3985607624053955, "learning_rate": 7.024320641103811e-07, "loss": 0.33920618891716003, "step": 702 }, { "epoch": 19.535211267605632, "grad_norm": 0.3919280767440796, "learning_rate": 7.01692866290387e-07, "loss": 0.3378901183605194, "step": 703 }, { "epoch": 19.56338028169014, "grad_norm": 0.3975071609020233, "learning_rate": 7.009532063876148e-07, "loss": 0.3380805253982544, "step": 704 }, { "epoch": 19.591549295774648, "grad_norm": 0.3826391398906708, "learning_rate": 7.002130866551968e-07, "loss": 0.3308345675468445, "step": 705 }, { "epoch": 19.619718309859156, "grad_norm": 0.3827539086341858, "learning_rate": 6.994725093476664e-07, "loss": 0.3263572156429291, "step": 706 }, { "epoch": 19.647887323943664, "grad_norm": 0.3815464675426483, "learning_rate": 6.987314767209503e-07, "loss": 0.3306196928024292, "step": 707 }, { "epoch": 19.676056338028168, "grad_norm": 0.36781415343284607, "learning_rate": 6.979899910323624e-07, "loss": 0.33335480093955994, "step": 708 }, { "epoch": 19.704225352112676, "grad_norm": 0.3866605758666992, "learning_rate": 6.972480545405968e-07, "loss": 0.32704389095306396, "step": 709 }, { "epoch": 19.732394366197184, "grad_norm": 0.3858698308467865, "learning_rate": 6.965056695057204e-07, "loss": 0.34168708324432373, "step": 710 }, { "epoch": 19.760563380281692, "grad_norm": 0.39047256112098694, "learning_rate": 6.957628381891673e-07, "loss": 0.33112984895706177, "step": 711 }, { "epoch": 19.788732394366196, "grad_norm": 0.3946002721786499, "learning_rate": 6.950195628537299e-07, "loss": 0.34804296493530273, "step": 712 }, { "epoch": 19.816901408450704, "grad_norm": 0.3844221532344818, "learning_rate": 6.942758457635543e-07, "loss": 0.3490752577781677, "step": 713 }, { "epoch": 19.845070422535212, "grad_norm": 0.39914000034332275, "learning_rate": 6.935316891841315e-07, "loss": 0.35786545276641846, "step": 714 }, { "epoch": 19.87323943661972, "grad_norm": 0.39063403010368347, "learning_rate": 6.927870953822915e-07, "loss": 0.3300919830799103, "step": 715 }, { "epoch": 19.901408450704224, "grad_norm": 0.38942843675613403, "learning_rate": 6.920420666261961e-07, "loss": 0.3422998785972595, "step": 716 }, { "epoch": 19.929577464788732, "grad_norm": 0.3851071000099182, "learning_rate": 6.912966051853322e-07, "loss": 0.34118276834487915, "step": 717 }, { "epoch": 19.95774647887324, "grad_norm": 0.40658292174339294, "learning_rate": 6.905507133305047e-07, "loss": 0.3373083770275116, "step": 718 }, { "epoch": 19.985915492957748, "grad_norm": 0.3849228322505951, "learning_rate": 6.898043933338293e-07, "loss": 0.33878031373023987, "step": 719 }, { "epoch": 20.0, "grad_norm": 0.5402109026908875, "learning_rate": 6.890576474687263e-07, "loss": 0.3421837091445923, "step": 720 }, { "epoch": 20.028169014084508, "grad_norm": 0.38437139987945557, "learning_rate": 6.883104780099133e-07, "loss": 0.32037562131881714, "step": 721 }, { "epoch": 20.056338028169016, "grad_norm": 0.3756919205188751, "learning_rate": 6.875628872333975e-07, "loss": 0.3327672779560089, "step": 722 }, { "epoch": 20.08450704225352, "grad_norm": 0.37429380416870117, "learning_rate": 6.868148774164706e-07, "loss": 0.32762014865875244, "step": 723 }, { "epoch": 20.112676056338028, "grad_norm": 0.3806716799736023, "learning_rate": 6.860664508377001e-07, "loss": 0.3428674340248108, "step": 724 }, { "epoch": 20.140845070422536, "grad_norm": 0.3911280930042267, "learning_rate": 6.853176097769228e-07, "loss": 0.32650214433670044, "step": 725 }, { "epoch": 20.169014084507044, "grad_norm": 0.3932664394378662, "learning_rate": 6.84568356515239e-07, "loss": 0.3356166481971741, "step": 726 }, { "epoch": 20.197183098591548, "grad_norm": 0.38213464617729187, "learning_rate": 6.838186933350036e-07, "loss": 0.33551955223083496, "step": 727 }, { "epoch": 20.225352112676056, "grad_norm": 0.4010024666786194, "learning_rate": 6.83068622519821e-07, "loss": 0.35123541951179504, "step": 728 }, { "epoch": 20.253521126760564, "grad_norm": 0.3925156891345978, "learning_rate": 6.823181463545366e-07, "loss": 0.3408314287662506, "step": 729 }, { "epoch": 20.281690140845072, "grad_norm": 0.3899266719818115, "learning_rate": 6.815672671252315e-07, "loss": 0.340726763010025, "step": 730 }, { "epoch": 20.309859154929576, "grad_norm": 0.39596399664878845, "learning_rate": 6.808159871192136e-07, "loss": 0.32626962661743164, "step": 731 }, { "epoch": 20.338028169014084, "grad_norm": 0.3924717903137207, "learning_rate": 6.800643086250121e-07, "loss": 0.3350263833999634, "step": 732 }, { "epoch": 20.366197183098592, "grad_norm": 0.38622787594795227, "learning_rate": 6.793122339323705e-07, "loss": 0.3287360668182373, "step": 733 }, { "epoch": 20.3943661971831, "grad_norm": 0.38410770893096924, "learning_rate": 6.78559765332238e-07, "loss": 0.338472843170166, "step": 734 }, { "epoch": 20.422535211267604, "grad_norm": 0.40592262148857117, "learning_rate": 6.778069051167653e-07, "loss": 0.3270539939403534, "step": 735 }, { "epoch": 20.450704225352112, "grad_norm": 0.412509560585022, "learning_rate": 6.770536555792944e-07, "loss": 0.3392220437526703, "step": 736 }, { "epoch": 20.47887323943662, "grad_norm": 0.38412800431251526, "learning_rate": 6.763000190143545e-07, "loss": 0.3374585807323456, "step": 737 }, { "epoch": 20.507042253521128, "grad_norm": 0.3821827471256256, "learning_rate": 6.755459977176532e-07, "loss": 0.3369463086128235, "step": 738 }, { "epoch": 20.535211267605632, "grad_norm": 0.39306604862213135, "learning_rate": 6.747915939860701e-07, "loss": 0.33568012714385986, "step": 739 }, { "epoch": 20.56338028169014, "grad_norm": 0.3962586522102356, "learning_rate": 6.740368101176495e-07, "loss": 0.33102214336395264, "step": 740 }, { "epoch": 20.591549295774648, "grad_norm": 0.37576913833618164, "learning_rate": 6.732816484115946e-07, "loss": 0.3385513722896576, "step": 741 }, { "epoch": 20.619718309859156, "grad_norm": 0.39784473180770874, "learning_rate": 6.725261111682584e-07, "loss": 0.3244640529155731, "step": 742 }, { "epoch": 20.647887323943664, "grad_norm": 0.4142843186855316, "learning_rate": 6.717702006891386e-07, "loss": 0.331607460975647, "step": 743 }, { "epoch": 20.676056338028168, "grad_norm": 0.38871362805366516, "learning_rate": 6.710139192768694e-07, "loss": 0.3436110019683838, "step": 744 }, { "epoch": 20.704225352112676, "grad_norm": 0.4021725058555603, "learning_rate": 6.702572692352155e-07, "loss": 0.35173317790031433, "step": 745 }, { "epoch": 20.732394366197184, "grad_norm": 0.3940410017967224, "learning_rate": 6.695002528690639e-07, "loss": 0.33550578355789185, "step": 746 }, { "epoch": 20.760563380281692, "grad_norm": 0.3919907212257385, "learning_rate": 6.687428724844179e-07, "loss": 0.32640475034713745, "step": 747 }, { "epoch": 20.788732394366196, "grad_norm": 0.40651872754096985, "learning_rate": 6.679851303883891e-07, "loss": 0.33076268434524536, "step": 748 }, { "epoch": 20.816901408450704, "grad_norm": 0.3751327395439148, "learning_rate": 6.672270288891918e-07, "loss": 0.3242456912994385, "step": 749 }, { "epoch": 20.845070422535212, "grad_norm": 0.38218119740486145, "learning_rate": 6.664685702961344e-07, "loss": 0.3351116478443146, "step": 750 }, { "epoch": 20.87323943661972, "grad_norm": 0.3756243586540222, "learning_rate": 6.657097569196133e-07, "loss": 0.32466185092926025, "step": 751 }, { "epoch": 20.901408450704224, "grad_norm": 0.37298673391342163, "learning_rate": 6.649505910711058e-07, "loss": 0.3275296688079834, "step": 752 }, { "epoch": 20.929577464788732, "grad_norm": 0.37849190831184387, "learning_rate": 6.641910750631626e-07, "loss": 0.3319433331489563, "step": 753 }, { "epoch": 20.95774647887324, "grad_norm": 0.38188183307647705, "learning_rate": 6.634312112094013e-07, "loss": 0.3375653028488159, "step": 754 }, { "epoch": 20.985915492957748, "grad_norm": 0.3794807493686676, "learning_rate": 6.626710018244987e-07, "loss": 0.3360190987586975, "step": 755 }, { "epoch": 21.0, "grad_norm": 0.5494371056556702, "learning_rate": 6.619104492241847e-07, "loss": 0.33255964517593384, "step": 756 }, { "epoch": 21.028169014084508, "grad_norm": 0.38960424065589905, "learning_rate": 6.611495557252344e-07, "loss": 0.331976979970932, "step": 757 }, { "epoch": 21.056338028169016, "grad_norm": 0.38694149255752563, "learning_rate": 6.603883236454612e-07, "loss": 0.3247852623462677, "step": 758 }, { "epoch": 21.08450704225352, "grad_norm": 0.3758947253227234, "learning_rate": 6.596267553037102e-07, "loss": 0.3229767978191376, "step": 759 }, { "epoch": 21.112676056338028, "grad_norm": 0.37344521284103394, "learning_rate": 6.588648530198504e-07, "loss": 0.3300056457519531, "step": 760 }, { "epoch": 21.140845070422536, "grad_norm": 0.3657769560813904, "learning_rate": 6.581026191147687e-07, "loss": 0.3265196681022644, "step": 761 }, { "epoch": 21.169014084507044, "grad_norm": 0.365477055311203, "learning_rate": 6.573400559103613e-07, "loss": 0.33273735642433167, "step": 762 }, { "epoch": 21.197183098591548, "grad_norm": 0.37808549404144287, "learning_rate": 6.565771657295285e-07, "loss": 0.31984877586364746, "step": 763 }, { "epoch": 21.225352112676056, "grad_norm": 0.3769138753414154, "learning_rate": 6.558139508961654e-07, "loss": 0.34565865993499756, "step": 764 }, { "epoch": 21.253521126760564, "grad_norm": 0.39806798100471497, "learning_rate": 6.550504137351575e-07, "loss": 0.3433728516101837, "step": 765 }, { "epoch": 21.281690140845072, "grad_norm": 0.39546650648117065, "learning_rate": 6.542865565723707e-07, "loss": 0.34893685579299927, "step": 766 }, { "epoch": 21.309859154929576, "grad_norm": 0.3881830871105194, "learning_rate": 6.53522381734647e-07, "loss": 0.3205150067806244, "step": 767 }, { "epoch": 21.338028169014084, "grad_norm": 0.3741756081581116, "learning_rate": 6.527578915497951e-07, "loss": 0.33024320006370544, "step": 768 }, { "epoch": 21.366197183098592, "grad_norm": 0.3872038424015045, "learning_rate": 6.519930883465847e-07, "loss": 0.3330642879009247, "step": 769 }, { "epoch": 21.3943661971831, "grad_norm": 0.3687564730644226, "learning_rate": 6.512279744547392e-07, "loss": 0.3331137001514435, "step": 770 }, { "epoch": 21.422535211267604, "grad_norm": 0.3797539472579956, "learning_rate": 6.50462552204928e-07, "loss": 0.3351975381374359, "step": 771 }, { "epoch": 21.450704225352112, "grad_norm": 0.39143964648246765, "learning_rate": 6.496968239287603e-07, "loss": 0.3294268250465393, "step": 772 }, { "epoch": 21.47887323943662, "grad_norm": 0.3784260153770447, "learning_rate": 6.489307919587769e-07, "loss": 0.3408345580101013, "step": 773 }, { "epoch": 21.507042253521128, "grad_norm": 0.3762056231498718, "learning_rate": 6.481644586284442e-07, "loss": 0.33139801025390625, "step": 774 }, { "epoch": 21.535211267605632, "grad_norm": 0.3862803876399994, "learning_rate": 6.473978262721463e-07, "loss": 0.34327369928359985, "step": 775 }, { "epoch": 21.56338028169014, "grad_norm": 0.3758659362792969, "learning_rate": 6.466308972251785e-07, "loss": 0.32968389987945557, "step": 776 }, { "epoch": 21.591549295774648, "grad_norm": 0.3706018626689911, "learning_rate": 6.458636738237395e-07, "loss": 0.3400956392288208, "step": 777 }, { "epoch": 21.619718309859156, "grad_norm": 0.39726686477661133, "learning_rate": 6.45096158404925e-07, "loss": 0.33465176820755005, "step": 778 }, { "epoch": 21.647887323943664, "grad_norm": 0.4105653464794159, "learning_rate": 6.443283533067198e-07, "loss": 0.3266163766384125, "step": 779 }, { "epoch": 21.676056338028168, "grad_norm": 0.3946582078933716, "learning_rate": 6.435602608679916e-07, "loss": 0.3366073668003082, "step": 780 }, { "epoch": 21.704225352112676, "grad_norm": 0.3740902543067932, "learning_rate": 6.427918834284834e-07, "loss": 0.32955464720726013, "step": 781 }, { "epoch": 21.732394366197184, "grad_norm": 0.39744383096694946, "learning_rate": 6.420232233288055e-07, "loss": 0.34052732586860657, "step": 782 }, { "epoch": 21.760563380281692, "grad_norm": 0.38499632477760315, "learning_rate": 6.412542829104306e-07, "loss": 0.3195417821407318, "step": 783 }, { "epoch": 21.788732394366196, "grad_norm": 0.3770560324192047, "learning_rate": 6.404850645156841e-07, "loss": 0.32037222385406494, "step": 784 }, { "epoch": 21.816901408450704, "grad_norm": 0.38655078411102295, "learning_rate": 6.397155704877388e-07, "loss": 0.32680878043174744, "step": 785 }, { "epoch": 21.845070422535212, "grad_norm": 0.3888449966907501, "learning_rate": 6.389458031706068e-07, "loss": 0.3289785385131836, "step": 786 }, { "epoch": 21.87323943661972, "grad_norm": 0.38600072264671326, "learning_rate": 6.381757649091329e-07, "loss": 0.3329932689666748, "step": 787 }, { "epoch": 21.901408450704224, "grad_norm": 0.37920624017715454, "learning_rate": 6.374054580489873e-07, "loss": 0.3323825001716614, "step": 788 }, { "epoch": 21.929577464788732, "grad_norm": 0.3734983503818512, "learning_rate": 6.366348849366583e-07, "loss": 0.3282731771469116, "step": 789 }, { "epoch": 21.95774647887324, "grad_norm": 0.3893531560897827, "learning_rate": 6.358640479194451e-07, "loss": 0.32674992084503174, "step": 790 }, { "epoch": 21.985915492957748, "grad_norm": 0.3803586959838867, "learning_rate": 6.35092949345451e-07, "loss": 0.3355019986629486, "step": 791 }, { "epoch": 22.0, "grad_norm": 0.549261748790741, "learning_rate": 6.343215915635761e-07, "loss": 0.3333393335342407, "step": 792 }, { "epoch": 22.028169014084508, "grad_norm": 0.37239620089530945, "learning_rate": 6.335499769235098e-07, "loss": 0.33453333377838135, "step": 793 }, { "epoch": 22.056338028169016, "grad_norm": 0.37562069296836853, "learning_rate": 6.327781077757241e-07, "loss": 0.33604878187179565, "step": 794 }, { "epoch": 22.08450704225352, "grad_norm": 0.40688008069992065, "learning_rate": 6.320059864714664e-07, "loss": 0.33970382809638977, "step": 795 }, { "epoch": 22.112676056338028, "grad_norm": 0.38835394382476807, "learning_rate": 6.31233615362752e-07, "loss": 0.32596004009246826, "step": 796 }, { "epoch": 22.140845070422536, "grad_norm": 0.3961065709590912, "learning_rate": 6.304609968023572e-07, "loss": 0.3272387385368347, "step": 797 }, { "epoch": 22.169014084507044, "grad_norm": 0.3784503638744354, "learning_rate": 6.296881331438126e-07, "loss": 0.32076296210289, "step": 798 }, { "epoch": 22.197183098591548, "grad_norm": 0.4154704511165619, "learning_rate": 6.289150267413942e-07, "loss": 0.3484557271003723, "step": 799 }, { "epoch": 22.225352112676056, "grad_norm": 0.3906427323818207, "learning_rate": 6.281416799501187e-07, "loss": 0.33935999870300293, "step": 800 }, { "epoch": 22.253521126760564, "grad_norm": 0.3844432830810547, "learning_rate": 6.273680951257342e-07, "loss": 0.34040963649749756, "step": 801 }, { "epoch": 22.281690140845072, "grad_norm": 0.37825000286102295, "learning_rate": 6.265942746247146e-07, "loss": 0.33542725443840027, "step": 802 }, { "epoch": 22.309859154929576, "grad_norm": 0.37992310523986816, "learning_rate": 6.258202208042511e-07, "loss": 0.3131875693798065, "step": 803 }, { "epoch": 22.338028169014084, "grad_norm": 0.3949339687824249, "learning_rate": 6.25045936022246e-07, "loss": 0.3296380341053009, "step": 804 }, { "epoch": 22.366197183098592, "grad_norm": 0.3944908082485199, "learning_rate": 6.242714226373049e-07, "loss": 0.3167039453983307, "step": 805 }, { "epoch": 22.3943661971831, "grad_norm": 0.40283143520355225, "learning_rate": 6.2349668300873e-07, "loss": 0.3257637619972229, "step": 806 }, { "epoch": 22.422535211267604, "grad_norm": 0.3988412320613861, "learning_rate": 6.227217194965125e-07, "loss": 0.3284885883331299, "step": 807 }, { "epoch": 22.450704225352112, "grad_norm": 0.3859960734844208, "learning_rate": 6.219465344613258e-07, "loss": 0.3253086805343628, "step": 808 }, { "epoch": 22.47887323943662, "grad_norm": 0.3935350477695465, "learning_rate": 6.211711302645177e-07, "loss": 0.3332774043083191, "step": 809 }, { "epoch": 22.507042253521128, "grad_norm": 0.36818307638168335, "learning_rate": 6.203955092681039e-07, "loss": 0.3144124150276184, "step": 810 }, { "epoch": 22.535211267605632, "grad_norm": 0.4024381935596466, "learning_rate": 6.196196738347607e-07, "loss": 0.34560132026672363, "step": 811 }, { "epoch": 22.56338028169014, "grad_norm": 0.4075704514980316, "learning_rate": 6.188436263278172e-07, "loss": 0.34374749660491943, "step": 812 }, { "epoch": 22.591549295774648, "grad_norm": 0.4071885049343109, "learning_rate": 6.180673691112486e-07, "loss": 0.3240257203578949, "step": 813 }, { "epoch": 22.619718309859156, "grad_norm": 0.3949541747570038, "learning_rate": 6.172909045496694e-07, "loss": 0.3232196867465973, "step": 814 }, { "epoch": 22.647887323943664, "grad_norm": 0.3841669261455536, "learning_rate": 6.165142350083249e-07, "loss": 0.31785714626312256, "step": 815 }, { "epoch": 22.676056338028168, "grad_norm": 0.367186576128006, "learning_rate": 6.157373628530852e-07, "loss": 0.32530641555786133, "step": 816 }, { "epoch": 22.704225352112676, "grad_norm": 0.40135952830314636, "learning_rate": 6.149602904504378e-07, "loss": 0.3395450711250305, "step": 817 }, { "epoch": 22.732394366197184, "grad_norm": 0.38854143023490906, "learning_rate": 6.141830201674802e-07, "loss": 0.33484598994255066, "step": 818 }, { "epoch": 22.760563380281692, "grad_norm": 0.3972291648387909, "learning_rate": 6.134055543719121e-07, "loss": 0.3368615210056305, "step": 819 }, { "epoch": 22.788732394366196, "grad_norm": 0.3795410692691803, "learning_rate": 6.126278954320294e-07, "loss": 0.33861345052719116, "step": 820 }, { "epoch": 22.816901408450704, "grad_norm": 0.3890909254550934, "learning_rate": 6.118500457167159e-07, "loss": 0.3254876136779785, "step": 821 }, { "epoch": 22.845070422535212, "grad_norm": 0.40533915162086487, "learning_rate": 6.11072007595437e-07, "loss": 0.33061251044273376, "step": 822 }, { "epoch": 22.87323943661972, "grad_norm": 0.3912028670310974, "learning_rate": 6.102937834382315e-07, "loss": 0.3307432234287262, "step": 823 }, { "epoch": 22.901408450704224, "grad_norm": 0.4002802073955536, "learning_rate": 6.095153756157051e-07, "loss": 0.3190012276172638, "step": 824 }, { "epoch": 22.929577464788732, "grad_norm": 0.3895573616027832, "learning_rate": 6.087367864990232e-07, "loss": 0.3221516013145447, "step": 825 }, { "epoch": 22.95774647887324, "grad_norm": 0.38364264369010925, "learning_rate": 6.079580184599032e-07, "loss": 0.32783806324005127, "step": 826 }, { "epoch": 22.985915492957748, "grad_norm": 0.4016467332839966, "learning_rate": 6.071790738706078e-07, "loss": 0.3346102833747864, "step": 827 }, { "epoch": 23.0, "grad_norm": 0.5366764068603516, "learning_rate": 6.06399955103937e-07, "loss": 0.311079740524292, "step": 828 }, { "epoch": 23.028169014084508, "grad_norm": 0.39752188324928284, "learning_rate": 6.056206645332217e-07, "loss": 0.3157707452774048, "step": 829 }, { "epoch": 23.056338028169016, "grad_norm": 0.38852933049201965, "learning_rate": 6.048412045323164e-07, "loss": 0.31095701456069946, "step": 830 }, { "epoch": 23.08450704225352, "grad_norm": 0.3805243968963623, "learning_rate": 6.040615774755911e-07, "loss": 0.32847878336906433, "step": 831 }, { "epoch": 23.112676056338028, "grad_norm": 0.3875986635684967, "learning_rate": 6.032817857379256e-07, "loss": 0.33862489461898804, "step": 832 }, { "epoch": 23.140845070422536, "grad_norm": 0.39711037278175354, "learning_rate": 6.025018316946999e-07, "loss": 0.3232111632823944, "step": 833 }, { "epoch": 23.169014084507044, "grad_norm": 0.4081644117832184, "learning_rate": 6.017217177217899e-07, "loss": 0.33068814873695374, "step": 834 }, { "epoch": 23.197183098591548, "grad_norm": 0.3873186707496643, "learning_rate": 6.009414461955581e-07, "loss": 0.31904804706573486, "step": 835 }, { "epoch": 23.225352112676056, "grad_norm": 0.3813845217227936, "learning_rate": 6.001610194928464e-07, "loss": 0.3458956182003021, "step": 836 }, { "epoch": 23.253521126760564, "grad_norm": 0.41381752490997314, "learning_rate": 5.993804399909703e-07, "loss": 0.3196842074394226, "step": 837 }, { "epoch": 23.281690140845072, "grad_norm": 0.38108712434768677, "learning_rate": 5.985997100677103e-07, "loss": 0.3292678892612457, "step": 838 }, { "epoch": 23.309859154929576, "grad_norm": 0.3857171833515167, "learning_rate": 5.97818832101305e-07, "loss": 0.3455089032649994, "step": 839 }, { "epoch": 23.338028169014084, "grad_norm": 0.37924760580062866, "learning_rate": 5.97037808470444e-07, "loss": 0.3251941204071045, "step": 840 }, { "epoch": 23.366197183098592, "grad_norm": 0.389441579580307, "learning_rate": 5.96256641554261e-07, "loss": 0.31982478499412537, "step": 841 }, { "epoch": 23.3943661971831, "grad_norm": 0.39625149965286255, "learning_rate": 5.954753337323259e-07, "loss": 0.34537336230278015, "step": 842 }, { "epoch": 23.422535211267604, "grad_norm": 0.3788090646266937, "learning_rate": 5.946938873846375e-07, "loss": 0.3204682469367981, "step": 843 }, { "epoch": 23.450704225352112, "grad_norm": 0.3852907419204712, "learning_rate": 5.939123048916173e-07, "loss": 0.34239375591278076, "step": 844 }, { "epoch": 23.47887323943662, "grad_norm": 0.39305049180984497, "learning_rate": 5.931305886341008e-07, "loss": 0.31065675616264343, "step": 845 }, { "epoch": 23.507042253521128, "grad_norm": 0.37949338555336, "learning_rate": 5.923487409933315e-07, "loss": 0.32166263461112976, "step": 846 }, { "epoch": 23.535211267605632, "grad_norm": 0.36787232756614685, "learning_rate": 5.915667643509528e-07, "loss": 0.33992820978164673, "step": 847 }, { "epoch": 23.56338028169014, "grad_norm": 0.3767579197883606, "learning_rate": 5.907846610890011e-07, "loss": 0.32268887758255005, "step": 848 }, { "epoch": 23.591549295774648, "grad_norm": 0.3919663429260254, "learning_rate": 5.900024335898987e-07, "loss": 0.34025847911834717, "step": 849 }, { "epoch": 23.619718309859156, "grad_norm": 0.39601776003837585, "learning_rate": 5.892200842364462e-07, "loss": 0.32528138160705566, "step": 850 }, { "epoch": 23.647887323943664, "grad_norm": 0.38417696952819824, "learning_rate": 5.884376154118154e-07, "loss": 0.33787277340888977, "step": 851 }, { "epoch": 23.676056338028168, "grad_norm": 0.4001351594924927, "learning_rate": 5.87655029499542e-07, "loss": 0.32067933678627014, "step": 852 }, { "epoch": 23.704225352112676, "grad_norm": 0.3779655992984772, "learning_rate": 5.868723288835184e-07, "loss": 0.32543522119522095, "step": 853 }, { "epoch": 23.732394366197184, "grad_norm": 0.3973066210746765, "learning_rate": 5.860895159479864e-07, "loss": 0.32018131017684937, "step": 854 }, { "epoch": 23.760563380281692, "grad_norm": 0.37466490268707275, "learning_rate": 5.853065930775303e-07, "loss": 0.3267287611961365, "step": 855 }, { "epoch": 23.788732394366196, "grad_norm": 0.3884205222129822, "learning_rate": 5.845235626570683e-07, "loss": 0.33319422602653503, "step": 856 }, { "epoch": 23.816901408450704, "grad_norm": 0.38531872630119324, "learning_rate": 5.837404270718475e-07, "loss": 0.32968732714653015, "step": 857 }, { "epoch": 23.845070422535212, "grad_norm": 0.39171651005744934, "learning_rate": 5.829571887074343e-07, "loss": 0.32898926734924316, "step": 858 }, { "epoch": 23.87323943661972, "grad_norm": 0.39152058959007263, "learning_rate": 5.821738499497086e-07, "loss": 0.31961727142333984, "step": 859 }, { "epoch": 23.901408450704224, "grad_norm": 0.38459572196006775, "learning_rate": 5.813904131848564e-07, "loss": 0.3272324204444885, "step": 860 }, { "epoch": 23.929577464788732, "grad_norm": 0.3808923661708832, "learning_rate": 5.806068807993617e-07, "loss": 0.3303658068180084, "step": 861 }, { "epoch": 23.95774647887324, "grad_norm": 0.37708351016044617, "learning_rate": 5.798232551800002e-07, "loss": 0.32344508171081543, "step": 862 }, { "epoch": 23.985915492957748, "grad_norm": 0.39680951833724976, "learning_rate": 5.790395387138311e-07, "loss": 0.322632372379303, "step": 863 }, { "epoch": 24.0, "grad_norm": 0.5610886812210083, "learning_rate": 5.78255733788191e-07, "loss": 0.35141521692276, "step": 864 }, { "epoch": 24.028169014084508, "grad_norm": 0.35833173990249634, "learning_rate": 5.774718427906856e-07, "loss": 0.3206993341445923, "step": 865 }, { "epoch": 24.056338028169016, "grad_norm": 0.39589741826057434, "learning_rate": 5.766878681091828e-07, "loss": 0.32118743658065796, "step": 866 }, { "epoch": 24.08450704225352, "grad_norm": 0.38291966915130615, "learning_rate": 5.759038121318052e-07, "loss": 0.3344864249229431, "step": 867 }, { "epoch": 24.112676056338028, "grad_norm": 0.3832544684410095, "learning_rate": 5.751196772469237e-07, "loss": 0.32217106223106384, "step": 868 }, { "epoch": 24.140845070422536, "grad_norm": 0.3777797818183899, "learning_rate": 5.743354658431489e-07, "loss": 0.3226107954978943, "step": 869 }, { "epoch": 24.169014084507044, "grad_norm": 0.38655632734298706, "learning_rate": 5.735511803093248e-07, "loss": 0.3162218928337097, "step": 870 }, { "epoch": 24.197183098591548, "grad_norm": 0.3842180669307709, "learning_rate": 5.727668230345209e-07, "loss": 0.3252412974834442, "step": 871 }, { "epoch": 24.225352112676056, "grad_norm": 0.37772274017333984, "learning_rate": 5.71982396408026e-07, "loss": 0.3119194805622101, "step": 872 }, { "epoch": 24.253521126760564, "grad_norm": 0.41677844524383545, "learning_rate": 5.711979028193391e-07, "loss": 0.33274686336517334, "step": 873 }, { "epoch": 24.281690140845072, "grad_norm": 0.37274062633514404, "learning_rate": 5.704133446581642e-07, "loss": 0.3364775776863098, "step": 874 }, { "epoch": 24.309859154929576, "grad_norm": 0.3630687892436981, "learning_rate": 5.696287243144012e-07, "loss": 0.3175593912601471, "step": 875 }, { "epoch": 24.338028169014084, "grad_norm": 0.37973663210868835, "learning_rate": 5.688440441781398e-07, "loss": 0.3331897556781769, "step": 876 }, { "epoch": 24.366197183098592, "grad_norm": 0.38727322220802307, "learning_rate": 5.680593066396518e-07, "loss": 0.3193923234939575, "step": 877 }, { "epoch": 24.3943661971831, "grad_norm": 0.3952330946922302, "learning_rate": 5.672745140893839e-07, "loss": 0.32324185967445374, "step": 878 }, { "epoch": 24.422535211267604, "grad_norm": 0.3810881972312927, "learning_rate": 5.664896689179504e-07, "loss": 0.32108092308044434, "step": 879 }, { "epoch": 24.450704225352112, "grad_norm": 0.3821290135383606, "learning_rate": 5.657047735161255e-07, "loss": 0.3288062810897827, "step": 880 }, { "epoch": 24.47887323943662, "grad_norm": 0.38779404759407043, "learning_rate": 5.649198302748368e-07, "loss": 0.32277727127075195, "step": 881 }, { "epoch": 24.507042253521128, "grad_norm": 0.38833415508270264, "learning_rate": 5.641348415851577e-07, "loss": 0.32539644837379456, "step": 882 }, { "epoch": 24.535211267605632, "grad_norm": 0.38681596517562866, "learning_rate": 5.633498098382998e-07, "loss": 0.3325621485710144, "step": 883 }, { "epoch": 24.56338028169014, "grad_norm": 0.38750550150871277, "learning_rate": 5.625647374256061e-07, "loss": 0.33401745557785034, "step": 884 }, { "epoch": 24.591549295774648, "grad_norm": 0.39044085144996643, "learning_rate": 5.617796267385429e-07, "loss": 0.3323938846588135, "step": 885 }, { "epoch": 24.619718309859156, "grad_norm": 0.40796950459480286, "learning_rate": 5.60994480168694e-07, "loss": 0.32161277532577515, "step": 886 }, { "epoch": 24.647887323943664, "grad_norm": 0.3978534936904907, "learning_rate": 5.602093001077517e-07, "loss": 0.3238278925418854, "step": 887 }, { "epoch": 24.676056338028168, "grad_norm": 0.3848389983177185, "learning_rate": 5.594240889475106e-07, "loss": 0.33983445167541504, "step": 888 }, { "epoch": 24.704225352112676, "grad_norm": 0.38630858063697815, "learning_rate": 5.586388490798604e-07, "loss": 0.3141022026538849, "step": 889 }, { "epoch": 24.732394366197184, "grad_norm": 0.3843793272972107, "learning_rate": 5.578535828967777e-07, "loss": 0.3235158324241638, "step": 890 }, { "epoch": 24.760563380281692, "grad_norm": 0.44759678840637207, "learning_rate": 5.570682927903193e-07, "loss": 0.3171459436416626, "step": 891 }, { "epoch": 24.788732394366196, "grad_norm": 0.3951988220214844, "learning_rate": 5.562829811526154e-07, "loss": 0.34439194202423096, "step": 892 }, { "epoch": 24.816901408450704, "grad_norm": 0.38317352533340454, "learning_rate": 5.554976503758612e-07, "loss": 0.3283988833427429, "step": 893 }, { "epoch": 24.845070422535212, "grad_norm": 0.3897356688976288, "learning_rate": 5.547123028523106e-07, "loss": 0.3268943727016449, "step": 894 }, { "epoch": 24.87323943661972, "grad_norm": 0.38267654180526733, "learning_rate": 5.539269409742683e-07, "loss": 0.33294621109962463, "step": 895 }, { "epoch": 24.901408450704224, "grad_norm": 0.3854587972164154, "learning_rate": 5.531415671340826e-07, "loss": 0.3341590464115143, "step": 896 }, { "epoch": 24.929577464788732, "grad_norm": 0.3782542943954468, "learning_rate": 5.523561837241387e-07, "loss": 0.3125770688056946, "step": 897 }, { "epoch": 24.95774647887324, "grad_norm": 0.3936726450920105, "learning_rate": 5.515707931368507e-07, "loss": 0.3472646474838257, "step": 898 }, { "epoch": 24.985915492957748, "grad_norm": 0.3760293424129486, "learning_rate": 5.507853977646543e-07, "loss": 0.3173547387123108, "step": 899 }, { "epoch": 25.0, "grad_norm": 0.519473135471344, "learning_rate": 5.5e-07, "loss": 0.32919731736183167, "step": 900 }, { "epoch": 25.028169014084508, "grad_norm": 0.3907301425933838, "learning_rate": 5.492146022353459e-07, "loss": 0.32534489035606384, "step": 901 }, { "epoch": 25.056338028169016, "grad_norm": 0.38654443621635437, "learning_rate": 5.484292068631494e-07, "loss": 0.32049402594566345, "step": 902 }, { "epoch": 25.08450704225352, "grad_norm": 0.38321253657341003, "learning_rate": 5.476438162758611e-07, "loss": 0.3115282356739044, "step": 903 }, { "epoch": 25.112676056338028, "grad_norm": 0.3922843337059021, "learning_rate": 5.468584328659172e-07, "loss": 0.3124304711818695, "step": 904 }, { "epoch": 25.140845070422536, "grad_norm": 0.3907575309276581, "learning_rate": 5.460730590257317e-07, "loss": 0.3261442184448242, "step": 905 }, { "epoch": 25.169014084507044, "grad_norm": 0.4006910026073456, "learning_rate": 5.452876971476896e-07, "loss": 0.32373058795928955, "step": 906 }, { "epoch": 25.197183098591548, "grad_norm": 0.37622418999671936, "learning_rate": 5.445023496241388e-07, "loss": 0.3193475306034088, "step": 907 }, { "epoch": 25.225352112676056, "grad_norm": 0.37440574169158936, "learning_rate": 5.437170188473847e-07, "loss": 0.3142261803150177, "step": 908 }, { "epoch": 25.253521126760564, "grad_norm": 0.38481953740119934, "learning_rate": 5.429317072096807e-07, "loss": 0.337313711643219, "step": 909 }, { "epoch": 25.281690140845072, "grad_norm": 0.39551037549972534, "learning_rate": 5.421464171032224e-07, "loss": 0.321609228849411, "step": 910 }, { "epoch": 25.309859154929576, "grad_norm": 0.3888447880744934, "learning_rate": 5.413611509201396e-07, "loss": 0.32264670729637146, "step": 911 }, { "epoch": 25.338028169014084, "grad_norm": 0.39491352438926697, "learning_rate": 5.405759110524894e-07, "loss": 0.3198102116584778, "step": 912 }, { "epoch": 25.366197183098592, "grad_norm": 0.39912641048431396, "learning_rate": 5.397906998922483e-07, "loss": 0.3395056426525116, "step": 913 }, { "epoch": 25.3943661971831, "grad_norm": 0.4020642638206482, "learning_rate": 5.390055198313061e-07, "loss": 0.3330724239349365, "step": 914 }, { "epoch": 25.422535211267604, "grad_norm": 0.39527246356010437, "learning_rate": 5.382203732614571e-07, "loss": 0.3267742395401001, "step": 915 }, { "epoch": 25.450704225352112, "grad_norm": 0.38676416873931885, "learning_rate": 5.37435262574394e-07, "loss": 0.3360646963119507, "step": 916 }, { "epoch": 25.47887323943662, "grad_norm": 0.4009418785572052, "learning_rate": 5.366501901617001e-07, "loss": 0.33060988783836365, "step": 917 }, { "epoch": 25.507042253521128, "grad_norm": 0.3914986848831177, "learning_rate": 5.358651584148423e-07, "loss": 0.3179813027381897, "step": 918 }, { "epoch": 25.535211267605632, "grad_norm": 0.3900521993637085, "learning_rate": 5.350801697251633e-07, "loss": 0.3134571313858032, "step": 919 }, { "epoch": 25.56338028169014, "grad_norm": 0.4012114405632019, "learning_rate": 5.342952264838747e-07, "loss": 0.3299099802970886, "step": 920 }, { "epoch": 25.591549295774648, "grad_norm": 0.375319242477417, "learning_rate": 5.335103310820496e-07, "loss": 0.31661590933799744, "step": 921 }, { "epoch": 25.619718309859156, "grad_norm": 0.39108213782310486, "learning_rate": 5.32725485910616e-07, "loss": 0.31691405177116394, "step": 922 }, { "epoch": 25.647887323943664, "grad_norm": 0.3978103697299957, "learning_rate": 5.319406933603482e-07, "loss": 0.3219263255596161, "step": 923 }, { "epoch": 25.676056338028168, "grad_norm": 0.39544498920440674, "learning_rate": 5.311559558218603e-07, "loss": 0.331471711397171, "step": 924 }, { "epoch": 25.704225352112676, "grad_norm": 0.3808025121688843, "learning_rate": 5.303712756855988e-07, "loss": 0.3252677321434021, "step": 925 }, { "epoch": 25.732394366197184, "grad_norm": 0.3788142204284668, "learning_rate": 5.295866553418358e-07, "loss": 0.328635036945343, "step": 926 }, { "epoch": 25.760563380281692, "grad_norm": 0.3923240900039673, "learning_rate": 5.288020971806608e-07, "loss": 0.3163786232471466, "step": 927 }, { "epoch": 25.788732394366196, "grad_norm": 0.4067988991737366, "learning_rate": 5.28017603591974e-07, "loss": 0.3369380235671997, "step": 928 }, { "epoch": 25.816901408450704, "grad_norm": 0.39493855834007263, "learning_rate": 5.27233176965479e-07, "loss": 0.32654568552970886, "step": 929 }, { "epoch": 25.845070422535212, "grad_norm": 0.3966091275215149, "learning_rate": 5.264488196906752e-07, "loss": 0.33306634426116943, "step": 930 }, { "epoch": 25.87323943661972, "grad_norm": 0.3901676833629608, "learning_rate": 5.256645341568511e-07, "loss": 0.3169354796409607, "step": 931 }, { "epoch": 25.901408450704224, "grad_norm": 0.3857198655605316, "learning_rate": 5.248803227530763e-07, "loss": 0.3285425901412964, "step": 932 }, { "epoch": 25.929577464788732, "grad_norm": 0.4023548364639282, "learning_rate": 5.240961878681947e-07, "loss": 0.31917253136634827, "step": 933 }, { "epoch": 25.95774647887324, "grad_norm": 0.3841480016708374, "learning_rate": 5.233121318908173e-07, "loss": 0.3240397572517395, "step": 934 }, { "epoch": 25.985915492957748, "grad_norm": 0.3895663917064667, "learning_rate": 5.225281572093143e-07, "loss": 0.33682069182395935, "step": 935 }, { "epoch": 26.0, "grad_norm": 0.566136360168457, "learning_rate": 5.21744266211809e-07, "loss": 0.32911181449890137, "step": 936 }, { "epoch": 26.028169014084508, "grad_norm": 0.39425909519195557, "learning_rate": 5.20960461286169e-07, "loss": 0.3303253650665283, "step": 937 }, { "epoch": 26.056338028169016, "grad_norm": 0.3862634599208832, "learning_rate": 5.2017674482e-07, "loss": 0.3101719617843628, "step": 938 }, { "epoch": 26.08450704225352, "grad_norm": 0.39860761165618896, "learning_rate": 5.193931192006385e-07, "loss": 0.31626003980636597, "step": 939 }, { "epoch": 26.112676056338028, "grad_norm": 0.38230645656585693, "learning_rate": 5.186095868151436e-07, "loss": 0.33143383264541626, "step": 940 }, { "epoch": 26.140845070422536, "grad_norm": 0.3823683261871338, "learning_rate": 5.178261500502912e-07, "loss": 0.312152236700058, "step": 941 }, { "epoch": 26.169014084507044, "grad_norm": 0.3821384310722351, "learning_rate": 5.170428112925659e-07, "loss": 0.3198228180408478, "step": 942 }, { "epoch": 26.197183098591548, "grad_norm": 0.41778433322906494, "learning_rate": 5.162595729281526e-07, "loss": 0.32497596740722656, "step": 943 }, { "epoch": 26.225352112676056, "grad_norm": 0.38266506791114807, "learning_rate": 5.154764373429315e-07, "loss": 0.3314628303050995, "step": 944 }, { "epoch": 26.253521126760564, "grad_norm": 0.39124244451522827, "learning_rate": 5.146934069224698e-07, "loss": 0.3309955298900604, "step": 945 }, { "epoch": 26.281690140845072, "grad_norm": 0.39248421788215637, "learning_rate": 5.139104840520135e-07, "loss": 0.3193722665309906, "step": 946 }, { "epoch": 26.309859154929576, "grad_norm": 0.40721243619918823, "learning_rate": 5.131276711164815e-07, "loss": 0.3228180408477783, "step": 947 }, { "epoch": 26.338028169014084, "grad_norm": 0.3944093585014343, "learning_rate": 5.123449705004581e-07, "loss": 0.33869385719299316, "step": 948 }, { "epoch": 26.366197183098592, "grad_norm": 0.3867540955543518, "learning_rate": 5.115623845881847e-07, "loss": 0.31862741708755493, "step": 949 }, { "epoch": 26.3943661971831, "grad_norm": 0.3939334452152252, "learning_rate": 5.107799157635538e-07, "loss": 0.3260752856731415, "step": 950 }, { "epoch": 26.422535211267604, "grad_norm": 0.40836402773857117, "learning_rate": 5.099975664101014e-07, "loss": 0.3147823214530945, "step": 951 }, { "epoch": 26.450704225352112, "grad_norm": 0.385328471660614, "learning_rate": 5.09215338910999e-07, "loss": 0.315174400806427, "step": 952 }, { "epoch": 26.47887323943662, "grad_norm": 0.38579061627388, "learning_rate": 5.084332356490472e-07, "loss": 0.3160386383533478, "step": 953 }, { "epoch": 26.507042253521128, "grad_norm": 0.39817193150520325, "learning_rate": 5.076512590066685e-07, "loss": 0.3219284415245056, "step": 954 }, { "epoch": 26.535211267605632, "grad_norm": 0.3795187175273895, "learning_rate": 5.068694113658992e-07, "loss": 0.31202954053878784, "step": 955 }, { "epoch": 26.56338028169014, "grad_norm": 0.38538357615470886, "learning_rate": 5.060876951083828e-07, "loss": 0.32958048582077026, "step": 956 }, { "epoch": 26.591549295774648, "grad_norm": 0.38360247015953064, "learning_rate": 5.053061126153624e-07, "loss": 0.30957651138305664, "step": 957 }, { "epoch": 26.619718309859156, "grad_norm": 0.3785325288772583, "learning_rate": 5.045246662676741e-07, "loss": 0.3202337622642517, "step": 958 }, { "epoch": 26.647887323943664, "grad_norm": 0.3824126124382019, "learning_rate": 5.037433584457389e-07, "loss": 0.3125755786895752, "step": 959 }, { "epoch": 26.676056338028168, "grad_norm": 0.39519426226615906, "learning_rate": 5.02962191529556e-07, "loss": 0.3107134699821472, "step": 960 }, { "epoch": 26.704225352112676, "grad_norm": 0.3949263095855713, "learning_rate": 5.021811678986951e-07, "loss": 0.3313808739185333, "step": 961 }, { "epoch": 26.732394366197184, "grad_norm": 0.38503384590148926, "learning_rate": 5.014002899322896e-07, "loss": 0.32243454456329346, "step": 962 }, { "epoch": 26.760563380281692, "grad_norm": 0.391943097114563, "learning_rate": 5.006195600090296e-07, "loss": 0.32883143424987793, "step": 963 }, { "epoch": 26.788732394366196, "grad_norm": 0.4018123745918274, "learning_rate": 4.998389805071536e-07, "loss": 0.31251728534698486, "step": 964 }, { "epoch": 26.816901408450704, "grad_norm": 0.41714271903038025, "learning_rate": 4.990585538044419e-07, "loss": 0.3352566957473755, "step": 965 }, { "epoch": 26.845070422535212, "grad_norm": 0.3913467824459076, "learning_rate": 4.982782822782101e-07, "loss": 0.3217517137527466, "step": 966 }, { "epoch": 26.87323943661972, "grad_norm": 0.40836217999458313, "learning_rate": 4.974981683053001e-07, "loss": 0.3292587995529175, "step": 967 }, { "epoch": 26.901408450704224, "grad_norm": 0.39076730608940125, "learning_rate": 4.967182142620745e-07, "loss": 0.3406558334827423, "step": 968 }, { "epoch": 26.929577464788732, "grad_norm": 0.37997063994407654, "learning_rate": 4.959384225244087e-07, "loss": 0.3325538635253906, "step": 969 }, { "epoch": 26.95774647887324, "grad_norm": 0.4018656611442566, "learning_rate": 4.951587954676837e-07, "loss": 0.3161391615867615, "step": 970 }, { "epoch": 26.985915492957748, "grad_norm": 0.3974568843841553, "learning_rate": 4.943793354667783e-07, "loss": 0.3390060365200043, "step": 971 }, { "epoch": 27.0, "grad_norm": 0.5330749750137329, "learning_rate": 4.93600044896063e-07, "loss": 0.3339563012123108, "step": 972 }, { "epoch": 27.028169014084508, "grad_norm": 0.3700898587703705, "learning_rate": 4.928209261293923e-07, "loss": 0.32524925470352173, "step": 973 }, { "epoch": 27.056338028169016, "grad_norm": 0.36422741413116455, "learning_rate": 4.920419815400968e-07, "loss": 0.32383549213409424, "step": 974 }, { "epoch": 27.08450704225352, "grad_norm": 0.3969523012638092, "learning_rate": 4.912632135009769e-07, "loss": 0.3273283541202545, "step": 975 }, { "epoch": 27.112676056338028, "grad_norm": 0.3937308192253113, "learning_rate": 4.904846243842949e-07, "loss": 0.31272923946380615, "step": 976 }, { "epoch": 27.140845070422536, "grad_norm": 0.38353821635246277, "learning_rate": 4.897062165617686e-07, "loss": 0.31967559456825256, "step": 977 }, { "epoch": 27.169014084507044, "grad_norm": 0.3810458779335022, "learning_rate": 4.88927992404563e-07, "loss": 0.3191872537136078, "step": 978 }, { "epoch": 27.197183098591548, "grad_norm": 0.3873644769191742, "learning_rate": 4.881499542832841e-07, "loss": 0.327060729265213, "step": 979 }, { "epoch": 27.225352112676056, "grad_norm": 0.38196802139282227, "learning_rate": 4.873721045679706e-07, "loss": 0.3129046559333801, "step": 980 }, { "epoch": 27.253521126760564, "grad_norm": 0.3674769997596741, "learning_rate": 4.865944456280878e-07, "loss": 0.3162941038608551, "step": 981 }, { "epoch": 27.281690140845072, "grad_norm": 0.39371582865715027, "learning_rate": 4.858169798325198e-07, "loss": 0.3260490596294403, "step": 982 }, { "epoch": 27.309859154929576, "grad_norm": 0.3972032368183136, "learning_rate": 4.850397095495621e-07, "loss": 0.32622987031936646, "step": 983 }, { "epoch": 27.338028169014084, "grad_norm": 0.4014224410057068, "learning_rate": 4.842626371469149e-07, "loss": 0.3255884647369385, "step": 984 }, { "epoch": 27.366197183098592, "grad_norm": 0.38516417145729065, "learning_rate": 4.834857649916752e-07, "loss": 0.31208905577659607, "step": 985 }, { "epoch": 27.3943661971831, "grad_norm": 0.3933313190937042, "learning_rate": 4.827090954503308e-07, "loss": 0.3179953098297119, "step": 986 }, { "epoch": 27.422535211267604, "grad_norm": 0.3956094980239868, "learning_rate": 4.819326308887513e-07, "loss": 0.31834524869918823, "step": 987 }, { "epoch": 27.450704225352112, "grad_norm": 0.40339627861976624, "learning_rate": 4.811563736721829e-07, "loss": 0.3197236955165863, "step": 988 }, { "epoch": 27.47887323943662, "grad_norm": 0.3828282356262207, "learning_rate": 4.803803261652395e-07, "loss": 0.3316667675971985, "step": 989 }, { "epoch": 27.507042253521128, "grad_norm": 0.4123758375644684, "learning_rate": 4.79604490731896e-07, "loss": 0.3373149633407593, "step": 990 }, { "epoch": 27.535211267605632, "grad_norm": 0.4058115780353546, "learning_rate": 4.788288697354824e-07, "loss": 0.3256288170814514, "step": 991 }, { "epoch": 27.56338028169014, "grad_norm": 0.395881712436676, "learning_rate": 4.780534655386743e-07, "loss": 0.3255182206630707, "step": 992 }, { "epoch": 27.591549295774648, "grad_norm": 0.3949476480484009, "learning_rate": 4.772782805034876e-07, "loss": 0.31342440843582153, "step": 993 }, { "epoch": 27.619718309859156, "grad_norm": 0.41506338119506836, "learning_rate": 4.7650331699127013e-07, "loss": 0.30606886744499207, "step": 994 }, { "epoch": 27.647887323943664, "grad_norm": 0.3876069486141205, "learning_rate": 4.75728577362695e-07, "loss": 0.3338634967803955, "step": 995 }, { "epoch": 27.676056338028168, "grad_norm": 0.3984672725200653, "learning_rate": 4.749540639777539e-07, "loss": 0.3124704360961914, "step": 996 }, { "epoch": 27.704225352112676, "grad_norm": 0.38598647713661194, "learning_rate": 4.741797791957489e-07, "loss": 0.3206423819065094, "step": 997 }, { "epoch": 27.732394366197184, "grad_norm": 0.3830356001853943, "learning_rate": 4.7340572537528547e-07, "loss": 0.3193873465061188, "step": 998 }, { "epoch": 27.760563380281692, "grad_norm": 0.3961408734321594, "learning_rate": 4.7263190487426563e-07, "loss": 0.3182516098022461, "step": 999 }, { "epoch": 27.788732394366196, "grad_norm": 0.39305320382118225, "learning_rate": 4.7185832004988133e-07, "loss": 0.33710581064224243, "step": 1000 }, { "epoch": 27.816901408450704, "grad_norm": 0.38334742188453674, "learning_rate": 4.710849732586059e-07, "loss": 0.3107894957065582, "step": 1001 }, { "epoch": 27.845070422535212, "grad_norm": 0.3962097764015198, "learning_rate": 4.703118668561875e-07, "loss": 0.32310307025909424, "step": 1002 }, { "epoch": 27.87323943661972, "grad_norm": 0.4129899740219116, "learning_rate": 4.6953900319764274e-07, "loss": 0.3173657953739166, "step": 1003 }, { "epoch": 27.901408450704224, "grad_norm": 0.3933452069759369, "learning_rate": 4.68766384637248e-07, "loss": 0.3349849581718445, "step": 1004 }, { "epoch": 27.929577464788732, "grad_norm": 0.39463669061660767, "learning_rate": 4.679940135285336e-07, "loss": 0.31813567876815796, "step": 1005 }, { "epoch": 27.95774647887324, "grad_norm": 0.3807503283023834, "learning_rate": 4.672218922242759e-07, "loss": 0.3168887794017792, "step": 1006 }, { "epoch": 27.985915492957748, "grad_norm": 0.3904450535774231, "learning_rate": 4.664500230764903e-07, "loss": 0.3194056451320648, "step": 1007 }, { "epoch": 28.0, "grad_norm": 0.5729740858078003, "learning_rate": 4.656784084364238e-07, "loss": 0.3411839008331299, "step": 1008 }, { "epoch": 28.028169014084508, "grad_norm": 0.39187631011009216, "learning_rate": 4.6490705065454883e-07, "loss": 0.32139888405799866, "step": 1009 }, { "epoch": 28.056338028169016, "grad_norm": 0.38157594203948975, "learning_rate": 4.641359520805548e-07, "loss": 0.32903847098350525, "step": 1010 }, { "epoch": 28.08450704225352, "grad_norm": 0.3803679347038269, "learning_rate": 4.6336511506334177e-07, "loss": 0.30710792541503906, "step": 1011 }, { "epoch": 28.112676056338028, "grad_norm": 0.3928949534893036, "learning_rate": 4.6259454195101267e-07, "loss": 0.3159278333187103, "step": 1012 }, { "epoch": 28.140845070422536, "grad_norm": 0.3867454528808594, "learning_rate": 4.61824235090867e-07, "loss": 0.32183969020843506, "step": 1013 }, { "epoch": 28.169014084507044, "grad_norm": 0.3878993093967438, "learning_rate": 4.6105419682939316e-07, "loss": 0.327831506729126, "step": 1014 }, { "epoch": 28.197183098591548, "grad_norm": 0.39358532428741455, "learning_rate": 4.602844295122613e-07, "loss": 0.3066422641277313, "step": 1015 }, { "epoch": 28.225352112676056, "grad_norm": 0.3881267011165619, "learning_rate": 4.59514935484316e-07, "loss": 0.32231512665748596, "step": 1016 }, { "epoch": 28.253521126760564, "grad_norm": 0.3974669277667999, "learning_rate": 4.5874571708956953e-07, "loss": 0.34675514698028564, "step": 1017 }, { "epoch": 28.281690140845072, "grad_norm": 0.3743266463279724, "learning_rate": 4.579767766711944e-07, "loss": 0.32414931058883667, "step": 1018 }, { "epoch": 28.309859154929576, "grad_norm": 0.38628455996513367, "learning_rate": 4.572081165715167e-07, "loss": 0.30881208181381226, "step": 1019 }, { "epoch": 28.338028169014084, "grad_norm": 0.39688679575920105, "learning_rate": 4.5643973913200837e-07, "loss": 0.32995566725730896, "step": 1020 }, { "epoch": 28.366197183098592, "grad_norm": 0.39416512846946716, "learning_rate": 4.556716466932803e-07, "loss": 0.327730268239975, "step": 1021 }, { "epoch": 28.3943661971831, "grad_norm": 0.39930543303489685, "learning_rate": 4.549038415950751e-07, "loss": 0.32226401567459106, "step": 1022 }, { "epoch": 28.422535211267604, "grad_norm": 0.39673280715942383, "learning_rate": 4.5413632617626054e-07, "loss": 0.3158804774284363, "step": 1023 }, { "epoch": 28.450704225352112, "grad_norm": 0.38143086433410645, "learning_rate": 4.5336910277482155e-07, "loss": 0.3302033543586731, "step": 1024 }, { "epoch": 28.47887323943662, "grad_norm": 0.3939116299152374, "learning_rate": 4.526021737278537e-07, "loss": 0.3158111572265625, "step": 1025 }, { "epoch": 28.507042253521128, "grad_norm": 0.40622755885124207, "learning_rate": 4.51835541371556e-07, "loss": 0.32396200299263, "step": 1026 }, { "epoch": 28.535211267605632, "grad_norm": 0.3897394835948944, "learning_rate": 4.5106920804122304e-07, "loss": 0.31977495551109314, "step": 1027 }, { "epoch": 28.56338028169014, "grad_norm": 0.37125250697135925, "learning_rate": 4.503031760712397e-07, "loss": 0.325844943523407, "step": 1028 }, { "epoch": 28.591549295774648, "grad_norm": 0.3901251256465912, "learning_rate": 4.4953744779507197e-07, "loss": 0.3198482096195221, "step": 1029 }, { "epoch": 28.619718309859156, "grad_norm": 0.39370420575141907, "learning_rate": 4.4877202554526084e-07, "loss": 0.3141654133796692, "step": 1030 }, { "epoch": 28.647887323943664, "grad_norm": 0.4079742729663849, "learning_rate": 4.480069116534151e-07, "loss": 0.3289361298084259, "step": 1031 }, { "epoch": 28.676056338028168, "grad_norm": 0.39373448491096497, "learning_rate": 4.4724210845020494e-07, "loss": 0.303550124168396, "step": 1032 }, { "epoch": 28.704225352112676, "grad_norm": 0.3851517140865326, "learning_rate": 4.4647761826535303e-07, "loss": 0.3275371193885803, "step": 1033 }, { "epoch": 28.732394366197184, "grad_norm": 0.39749592542648315, "learning_rate": 4.457134434276293e-07, "loss": 0.3159153461456299, "step": 1034 }, { "epoch": 28.760563380281692, "grad_norm": 0.3872748017311096, "learning_rate": 4.449495862648427e-07, "loss": 0.32355499267578125, "step": 1035 }, { "epoch": 28.788732394366196, "grad_norm": 0.3984876573085785, "learning_rate": 4.441860491038345e-07, "loss": 0.3134092092514038, "step": 1036 }, { "epoch": 28.816901408450704, "grad_norm": 0.3975779414176941, "learning_rate": 4.4342283427047164e-07, "loss": 0.3197779655456543, "step": 1037 }, { "epoch": 28.845070422535212, "grad_norm": 0.3911439776420593, "learning_rate": 4.4265994408963867e-07, "loss": 0.2987986207008362, "step": 1038 }, { "epoch": 28.87323943661972, "grad_norm": 0.4075714349746704, "learning_rate": 4.418973808852313e-07, "loss": 0.3265843093395233, "step": 1039 }, { "epoch": 28.901408450704224, "grad_norm": 0.38900086283683777, "learning_rate": 4.4113514698014953e-07, "loss": 0.3064301013946533, "step": 1040 }, { "epoch": 28.929577464788732, "grad_norm": 0.40392547845840454, "learning_rate": 4.403732446962899e-07, "loss": 0.32852086424827576, "step": 1041 }, { "epoch": 28.95774647887324, "grad_norm": 0.3813670873641968, "learning_rate": 4.3961167635453876e-07, "loss": 0.31472861766815186, "step": 1042 }, { "epoch": 28.985915492957748, "grad_norm": 0.3869912922382355, "learning_rate": 4.388504442747657e-07, "loss": 0.32740145921707153, "step": 1043 }, { "epoch": 29.0, "grad_norm": 0.5705031752586365, "learning_rate": 4.3808955077581546e-07, "loss": 0.3294166922569275, "step": 1044 }, { "epoch": 29.028169014084508, "grad_norm": 0.39494118094444275, "learning_rate": 4.373289981755013e-07, "loss": 0.3015002906322479, "step": 1045 }, { "epoch": 29.056338028169016, "grad_norm": 0.3874528706073761, "learning_rate": 4.365687887905988e-07, "loss": 0.3175269365310669, "step": 1046 }, { "epoch": 29.08450704225352, "grad_norm": 0.39874911308288574, "learning_rate": 4.358089249368375e-07, "loss": 0.31463566422462463, "step": 1047 }, { "epoch": 29.112676056338028, "grad_norm": 0.37529608607292175, "learning_rate": 4.350494089288943e-07, "loss": 0.30158668756484985, "step": 1048 }, { "epoch": 29.140845070422536, "grad_norm": 0.39873558282852173, "learning_rate": 4.3429024308038686e-07, "loss": 0.333732545375824, "step": 1049 }, { "epoch": 29.169014084507044, "grad_norm": 0.38672471046447754, "learning_rate": 4.3353142970386557e-07, "loss": 0.3232831358909607, "step": 1050 }, { "epoch": 29.197183098591548, "grad_norm": 0.3907194435596466, "learning_rate": 4.327729711108082e-07, "loss": 0.3299405872821808, "step": 1051 }, { "epoch": 29.225352112676056, "grad_norm": 0.39557650685310364, "learning_rate": 4.3201486961161093e-07, "loss": 0.3152773976325989, "step": 1052 }, { "epoch": 29.253521126760564, "grad_norm": 0.39757251739501953, "learning_rate": 4.312571275155823e-07, "loss": 0.3137446641921997, "step": 1053 }, { "epoch": 29.281690140845072, "grad_norm": 0.3849915862083435, "learning_rate": 4.304997471309361e-07, "loss": 0.3286364674568176, "step": 1054 }, { "epoch": 29.309859154929576, "grad_norm": 0.3918253183364868, "learning_rate": 4.297427307647844e-07, "loss": 0.315084308385849, "step": 1055 }, { "epoch": 29.338028169014084, "grad_norm": 0.3852742910385132, "learning_rate": 4.2898608072313045e-07, "loss": 0.31480738520622253, "step": 1056 }, { "epoch": 29.366197183098592, "grad_norm": 0.3834691047668457, "learning_rate": 4.2822979931086144e-07, "loss": 0.3095092177391052, "step": 1057 }, { "epoch": 29.3943661971831, "grad_norm": 0.37344595789909363, "learning_rate": 4.2747388883174154e-07, "loss": 0.3210027813911438, "step": 1058 }, { "epoch": 29.422535211267604, "grad_norm": 0.3842324912548065, "learning_rate": 4.267183515884054e-07, "loss": 0.3216034770011902, "step": 1059 }, { "epoch": 29.450704225352112, "grad_norm": 0.4003050625324249, "learning_rate": 4.2596318988235037e-07, "loss": 0.3202718198299408, "step": 1060 }, { "epoch": 29.47887323943662, "grad_norm": 0.39783963561058044, "learning_rate": 4.2520840601392996e-07, "loss": 0.32778969407081604, "step": 1061 }, { "epoch": 29.507042253521128, "grad_norm": 0.4110214114189148, "learning_rate": 4.2445400228234687e-07, "loss": 0.32846492528915405, "step": 1062 }, { "epoch": 29.535211267605632, "grad_norm": 0.38798847794532776, "learning_rate": 4.2369998098564554e-07, "loss": 0.3126874566078186, "step": 1063 }, { "epoch": 29.56338028169014, "grad_norm": 0.3920050859451294, "learning_rate": 4.2294634442070553e-07, "loss": 0.31347280740737915, "step": 1064 }, { "epoch": 29.591549295774648, "grad_norm": 0.395717054605484, "learning_rate": 4.2219309488323487e-07, "loss": 0.3149852454662323, "step": 1065 }, { "epoch": 29.619718309859156, "grad_norm": 0.3909353017807007, "learning_rate": 4.214402346677619e-07, "loss": 0.31942200660705566, "step": 1066 }, { "epoch": 29.647887323943664, "grad_norm": 0.40153780579566956, "learning_rate": 4.206877660676297e-07, "loss": 0.31769323348999023, "step": 1067 }, { "epoch": 29.676056338028168, "grad_norm": 0.39828068017959595, "learning_rate": 4.1993569137498776e-07, "loss": 0.32722607254981995, "step": 1068 }, { "epoch": 29.704225352112676, "grad_norm": 0.40273886919021606, "learning_rate": 4.1918401288078633e-07, "loss": 0.318960040807724, "step": 1069 }, { "epoch": 29.732394366197184, "grad_norm": 0.39284440875053406, "learning_rate": 4.1843273287476854e-07, "loss": 0.3250141739845276, "step": 1070 }, { "epoch": 29.760563380281692, "grad_norm": 0.39350998401641846, "learning_rate": 4.1768185364546326e-07, "loss": 0.31926706433296204, "step": 1071 }, { "epoch": 29.788732394366196, "grad_norm": 0.38825103640556335, "learning_rate": 4.1693137748017915e-07, "loss": 0.31079530715942383, "step": 1072 }, { "epoch": 29.816901408450704, "grad_norm": 0.3988570272922516, "learning_rate": 4.161813066649963e-07, "loss": 0.3225058615207672, "step": 1073 }, { "epoch": 29.845070422535212, "grad_norm": 0.38783174753189087, "learning_rate": 4.15431643484761e-07, "loss": 0.3231118321418762, "step": 1074 }, { "epoch": 29.87323943661972, "grad_norm": 0.38935571908950806, "learning_rate": 4.146823902230772e-07, "loss": 0.31755387783050537, "step": 1075 }, { "epoch": 29.901408450704224, "grad_norm": 0.3997592628002167, "learning_rate": 4.1393354916230005e-07, "loss": 0.31156352162361145, "step": 1076 }, { "epoch": 29.929577464788732, "grad_norm": 0.3941832184791565, "learning_rate": 4.1318512258352936e-07, "loss": 0.32877519726753235, "step": 1077 }, { "epoch": 29.95774647887324, "grad_norm": 0.3960806131362915, "learning_rate": 4.124371127666024e-07, "loss": 0.3279528319835663, "step": 1078 }, { "epoch": 29.985915492957748, "grad_norm": 0.3978699743747711, "learning_rate": 4.1168952199008677e-07, "loss": 0.32546380162239075, "step": 1079 }, { "epoch": 30.0, "grad_norm": 0.5448852777481079, "learning_rate": 4.1094235253127374e-07, "loss": 0.3194052577018738, "step": 1080 }, { "epoch": 30.028169014084508, "grad_norm": 0.38849538564682007, "learning_rate": 4.101956066661708e-07, "loss": 0.3115946650505066, "step": 1081 }, { "epoch": 30.056338028169016, "grad_norm": 0.40076303482055664, "learning_rate": 4.0944928666949527e-07, "loss": 0.31541264057159424, "step": 1082 }, { "epoch": 30.08450704225352, "grad_norm": 0.40326187014579773, "learning_rate": 4.0870339481466774e-07, "loss": 0.31242895126342773, "step": 1083 }, { "epoch": 30.112676056338028, "grad_norm": 0.39550158381462097, "learning_rate": 4.079579333738039e-07, "loss": 0.32159218192100525, "step": 1084 }, { "epoch": 30.140845070422536, "grad_norm": 0.403601735830307, "learning_rate": 4.0721290461770863e-07, "loss": 0.30890560150146484, "step": 1085 }, { "epoch": 30.169014084507044, "grad_norm": 0.37984904646873474, "learning_rate": 4.064683108158685e-07, "loss": 0.3170987367630005, "step": 1086 }, { "epoch": 30.197183098591548, "grad_norm": 0.39652949571609497, "learning_rate": 4.057241542364457e-07, "loss": 0.30855971574783325, "step": 1087 }, { "epoch": 30.225352112676056, "grad_norm": 0.392037570476532, "learning_rate": 4.0498043714627006e-07, "loss": 0.314483642578125, "step": 1088 }, { "epoch": 30.253521126760564, "grad_norm": 0.38578787446022034, "learning_rate": 4.042371618108329e-07, "loss": 0.3012908399105072, "step": 1089 }, { "epoch": 30.281690140845072, "grad_norm": 0.4056507349014282, "learning_rate": 4.034943304942796e-07, "loss": 0.3289816975593567, "step": 1090 }, { "epoch": 30.309859154929576, "grad_norm": 0.3914753198623657, "learning_rate": 4.027519454594033e-07, "loss": 0.3191179633140564, "step": 1091 }, { "epoch": 30.338028169014084, "grad_norm": 0.39688926935195923, "learning_rate": 4.020100089676376e-07, "loss": 0.31635797023773193, "step": 1092 }, { "epoch": 30.366197183098592, "grad_norm": 0.40888601541519165, "learning_rate": 4.012685232790497e-07, "loss": 0.337239146232605, "step": 1093 }, { "epoch": 30.3943661971831, "grad_norm": 0.38824498653411865, "learning_rate": 4.005274906523336e-07, "loss": 0.3291058838367462, "step": 1094 }, { "epoch": 30.422535211267604, "grad_norm": 0.39377355575561523, "learning_rate": 3.9978691334480306e-07, "loss": 0.3118734359741211, "step": 1095 }, { "epoch": 30.450704225352112, "grad_norm": 0.38702377676963806, "learning_rate": 3.9904679361238526e-07, "loss": 0.3165128827095032, "step": 1096 }, { "epoch": 30.47887323943662, "grad_norm": 0.40049466490745544, "learning_rate": 3.9830713370961313e-07, "loss": 0.33711162209510803, "step": 1097 }, { "epoch": 30.507042253521128, "grad_norm": 0.39197808504104614, "learning_rate": 3.975679358896189e-07, "loss": 0.31467658281326294, "step": 1098 }, { "epoch": 30.535211267605632, "grad_norm": 0.39893972873687744, "learning_rate": 3.968292024041275e-07, "loss": 0.33131134510040283, "step": 1099 }, { "epoch": 30.56338028169014, "grad_norm": 0.3839150071144104, "learning_rate": 3.9609093550344907e-07, "loss": 0.3290913701057434, "step": 1100 }, { "epoch": 30.591549295774648, "grad_norm": 0.404299259185791, "learning_rate": 3.953531374364728e-07, "loss": 0.30184292793273926, "step": 1101 }, { "epoch": 30.619718309859156, "grad_norm": 0.3782462179660797, "learning_rate": 3.946158104506594e-07, "loss": 0.3098834156990051, "step": 1102 }, { "epoch": 30.647887323943664, "grad_norm": 0.4039967358112335, "learning_rate": 3.938789567920349e-07, "loss": 0.32133281230926514, "step": 1103 }, { "epoch": 30.676056338028168, "grad_norm": 0.4059436023235321, "learning_rate": 3.931425787051832e-07, "loss": 0.3101251721382141, "step": 1104 }, { "epoch": 30.704225352112676, "grad_norm": 0.3929320275783539, "learning_rate": 3.924066784332396e-07, "loss": 0.31787344813346863, "step": 1105 }, { "epoch": 30.732394366197184, "grad_norm": 0.38287827372550964, "learning_rate": 3.9167125821788416e-07, "loss": 0.3178418278694153, "step": 1106 }, { "epoch": 30.760563380281692, "grad_norm": 0.3842368423938751, "learning_rate": 3.909363202993343e-07, "loss": 0.32755303382873535, "step": 1107 }, { "epoch": 30.788732394366196, "grad_norm": 0.4044226109981537, "learning_rate": 3.902018669163384e-07, "loss": 0.3267000615596771, "step": 1108 }, { "epoch": 30.816901408450704, "grad_norm": 0.38188570737838745, "learning_rate": 3.894679003061686e-07, "loss": 0.3084525465965271, "step": 1109 }, { "epoch": 30.845070422535212, "grad_norm": 0.4103005528450012, "learning_rate": 3.8873442270461485e-07, "loss": 0.3223256468772888, "step": 1110 }, { "epoch": 30.87323943661972, "grad_norm": 0.3776779770851135, "learning_rate": 3.88001436345977e-07, "loss": 0.3046845495700836, "step": 1111 }, { "epoch": 30.901408450704224, "grad_norm": 0.38886573910713196, "learning_rate": 3.872689434630585e-07, "loss": 0.31088194251060486, "step": 1112 }, { "epoch": 30.929577464788732, "grad_norm": 0.3859104514122009, "learning_rate": 3.8653694628715984e-07, "loss": 0.3280540704727173, "step": 1113 }, { "epoch": 30.95774647887324, "grad_norm": 0.3934411108493805, "learning_rate": 3.8580544704807117e-07, "loss": 0.3201024532318115, "step": 1114 }, { "epoch": 30.985915492957748, "grad_norm": 0.40359586477279663, "learning_rate": 3.850744479740663e-07, "loss": 0.32668638229370117, "step": 1115 }, { "epoch": 31.0, "grad_norm": 0.5667273998260498, "learning_rate": 3.843439512918949e-07, "loss": 0.31717124581336975, "step": 1116 }, { "epoch": 31.028169014084508, "grad_norm": 0.3974464237689972, "learning_rate": 3.8361395922677687e-07, "loss": 0.32645559310913086, "step": 1117 }, { "epoch": 31.056338028169016, "grad_norm": 0.37796565890312195, "learning_rate": 3.8288447400239443e-07, "loss": 0.32420992851257324, "step": 1118 }, { "epoch": 31.08450704225352, "grad_norm": 0.37163782119750977, "learning_rate": 3.82155497840886e-07, "loss": 0.30221351981163025, "step": 1119 }, { "epoch": 31.112676056338028, "grad_norm": 0.3861401379108429, "learning_rate": 3.8142703296283953e-07, "loss": 0.30777591466903687, "step": 1120 }, { "epoch": 31.140845070422536, "grad_norm": 0.39134180545806885, "learning_rate": 3.806990815872855e-07, "loss": 0.31938445568084717, "step": 1121 }, { "epoch": 31.169014084507044, "grad_norm": 0.38608089089393616, "learning_rate": 3.7997164593168983e-07, "loss": 0.33145594596862793, "step": 1122 }, { "epoch": 31.197183098591548, "grad_norm": 0.38318222761154175, "learning_rate": 3.7924472821194765e-07, "loss": 0.3112245500087738, "step": 1123 }, { "epoch": 31.225352112676056, "grad_norm": 0.3927881419658661, "learning_rate": 3.785183306423767e-07, "loss": 0.3209717571735382, "step": 1124 }, { "epoch": 31.253521126760564, "grad_norm": 0.4041878879070282, "learning_rate": 3.777924554357096e-07, "loss": 0.32123109698295593, "step": 1125 }, { "epoch": 31.281690140845072, "grad_norm": 0.3883450925350189, "learning_rate": 3.7706710480308835e-07, "loss": 0.3294408917427063, "step": 1126 }, { "epoch": 31.309859154929576, "grad_norm": 0.39175716042518616, "learning_rate": 3.7634228095405673e-07, "loss": 0.3174056112766266, "step": 1127 }, { "epoch": 31.338028169014084, "grad_norm": 0.3895219564437866, "learning_rate": 3.7561798609655373e-07, "loss": 0.32326945662498474, "step": 1128 }, { "epoch": 31.366197183098592, "grad_norm": 0.3971575200557709, "learning_rate": 3.748942224369073e-07, "loss": 0.3159647583961487, "step": 1129 }, { "epoch": 31.3943661971831, "grad_norm": 0.38449063897132874, "learning_rate": 3.7417099217982686e-07, "loss": 0.3210757374763489, "step": 1130 }, { "epoch": 31.422535211267604, "grad_norm": 0.39810091257095337, "learning_rate": 3.734482975283975e-07, "loss": 0.3155862092971802, "step": 1131 }, { "epoch": 31.450704225352112, "grad_norm": 0.38643842935562134, "learning_rate": 3.72726140684072e-07, "loss": 0.3213554918766022, "step": 1132 }, { "epoch": 31.47887323943662, "grad_norm": 0.40853485465049744, "learning_rate": 3.720045238466658e-07, "loss": 0.3138027489185333, "step": 1133 }, { "epoch": 31.507042253521128, "grad_norm": 0.4142437279224396, "learning_rate": 3.712834492143487e-07, "loss": 0.3179730176925659, "step": 1134 }, { "epoch": 31.535211267605632, "grad_norm": 0.3936646282672882, "learning_rate": 3.7056291898363925e-07, "loss": 0.3315540850162506, "step": 1135 }, { "epoch": 31.56338028169014, "grad_norm": 0.3821287155151367, "learning_rate": 3.6984293534939737e-07, "loss": 0.3179962635040283, "step": 1136 }, { "epoch": 31.591549295774648, "grad_norm": 0.4053444266319275, "learning_rate": 3.69123500504818e-07, "loss": 0.31676068902015686, "step": 1137 }, { "epoch": 31.619718309859156, "grad_norm": 0.4046670198440552, "learning_rate": 3.6840461664142444e-07, "loss": 0.31589609384536743, "step": 1138 }, { "epoch": 31.647887323943664, "grad_norm": 0.3901018798351288, "learning_rate": 3.6768628594906193e-07, "loss": 0.31740763783454895, "step": 1139 }, { "epoch": 31.676056338028168, "grad_norm": 0.39474499225616455, "learning_rate": 3.6696851061588994e-07, "loss": 0.30351805686950684, "step": 1140 }, { "epoch": 31.704225352112676, "grad_norm": 0.4008373022079468, "learning_rate": 3.6625129282837685e-07, "loss": 0.32629507780075073, "step": 1141 }, { "epoch": 31.732394366197184, "grad_norm": 0.3907651901245117, "learning_rate": 3.655346347712922e-07, "loss": 0.3205425441265106, "step": 1142 }, { "epoch": 31.760563380281692, "grad_norm": 0.3975644111633301, "learning_rate": 3.6481853862770107e-07, "loss": 0.32961034774780273, "step": 1143 }, { "epoch": 31.788732394366196, "grad_norm": 0.4113752245903015, "learning_rate": 3.641030065789562e-07, "loss": 0.3072119355201721, "step": 1144 }, { "epoch": 31.816901408450704, "grad_norm": 0.3931373059749603, "learning_rate": 3.6338804080469253e-07, "loss": 0.31567418575286865, "step": 1145 }, { "epoch": 31.845070422535212, "grad_norm": 0.38958361744880676, "learning_rate": 3.6267364348281946e-07, "loss": 0.3123632073402405, "step": 1146 }, { "epoch": 31.87323943661972, "grad_norm": 0.39404842257499695, "learning_rate": 3.6195981678951535e-07, "loss": 0.31616076827049255, "step": 1147 }, { "epoch": 31.901408450704224, "grad_norm": 0.38980191946029663, "learning_rate": 3.612465628992203e-07, "loss": 0.3000359833240509, "step": 1148 }, { "epoch": 31.929577464788732, "grad_norm": 0.3883528709411621, "learning_rate": 3.60533883984629e-07, "loss": 0.309824138879776, "step": 1149 }, { "epoch": 31.95774647887324, "grad_norm": 0.4094480574131012, "learning_rate": 3.5982178221668533e-07, "loss": 0.30633270740509033, "step": 1150 }, { "epoch": 31.985915492957748, "grad_norm": 0.38380739092826843, "learning_rate": 3.591102597645743e-07, "loss": 0.31234949827194214, "step": 1151 }, { "epoch": 32.0, "grad_norm": 0.5602955222129822, "learning_rate": 3.5839931879571725e-07, "loss": 0.31611528992652893, "step": 1152 }, { "epoch": 32.028169014084504, "grad_norm": 0.4018133580684662, "learning_rate": 3.5768896147576344e-07, "loss": 0.32215580344200134, "step": 1153 }, { "epoch": 32.056338028169016, "grad_norm": 0.4073368012905121, "learning_rate": 3.5697918996858443e-07, "loss": 0.3258715867996216, "step": 1154 }, { "epoch": 32.08450704225352, "grad_norm": 0.408777117729187, "learning_rate": 3.5627000643626704e-07, "loss": 0.3060804307460785, "step": 1155 }, { "epoch": 32.11267605633803, "grad_norm": 0.3930269479751587, "learning_rate": 3.555614130391079e-07, "loss": 0.32482728362083435, "step": 1156 }, { "epoch": 32.140845070422536, "grad_norm": 0.39947202801704407, "learning_rate": 3.5485341193560503e-07, "loss": 0.3201334774494171, "step": 1157 }, { "epoch": 32.16901408450704, "grad_norm": 0.3942817747592926, "learning_rate": 3.5414600528245266e-07, "loss": 0.32069841027259827, "step": 1158 }, { "epoch": 32.19718309859155, "grad_norm": 0.39514264464378357, "learning_rate": 3.534391952345341e-07, "loss": 0.32367902994155884, "step": 1159 }, { "epoch": 32.225352112676056, "grad_norm": 0.39698925614356995, "learning_rate": 3.5273298394491515e-07, "loss": 0.31515800952911377, "step": 1160 }, { "epoch": 32.25352112676056, "grad_norm": 0.3976225256919861, "learning_rate": 3.5202737356483816e-07, "loss": 0.3132592737674713, "step": 1161 }, { "epoch": 32.28169014084507, "grad_norm": 0.40394356846809387, "learning_rate": 3.513223662437147e-07, "loss": 0.3175573945045471, "step": 1162 }, { "epoch": 32.309859154929576, "grad_norm": 0.38683125376701355, "learning_rate": 3.5061796412911913e-07, "loss": 0.30610936880111694, "step": 1163 }, { "epoch": 32.33802816901409, "grad_norm": 0.4044669568538666, "learning_rate": 3.4991416936678276e-07, "loss": 0.30757373571395874, "step": 1164 }, { "epoch": 32.36619718309859, "grad_norm": 0.38869938254356384, "learning_rate": 3.49210984100586e-07, "loss": 0.31542325019836426, "step": 1165 }, { "epoch": 32.394366197183096, "grad_norm": 0.413189560174942, "learning_rate": 3.4850841047255364e-07, "loss": 0.32431674003601074, "step": 1166 }, { "epoch": 32.42253521126761, "grad_norm": 0.38767367601394653, "learning_rate": 3.4780645062284665e-07, "loss": 0.2996947467327118, "step": 1167 }, { "epoch": 32.45070422535211, "grad_norm": 0.397091805934906, "learning_rate": 3.471051066897562e-07, "loss": 0.3342075049877167, "step": 1168 }, { "epoch": 32.478873239436616, "grad_norm": 0.3768722712993622, "learning_rate": 3.4640438080969773e-07, "loss": 0.2967293858528137, "step": 1169 }, { "epoch": 32.50704225352113, "grad_norm": 0.40602102875709534, "learning_rate": 3.45704275117204e-07, "loss": 0.31818103790283203, "step": 1170 }, { "epoch": 32.53521126760563, "grad_norm": 0.39303112030029297, "learning_rate": 3.450047917449181e-07, "loss": 0.3152144253253937, "step": 1171 }, { "epoch": 32.563380281690144, "grad_norm": 0.37823936343193054, "learning_rate": 3.4430593282358777e-07, "loss": 0.3238877058029175, "step": 1172 }, { "epoch": 32.59154929577465, "grad_norm": 0.3913912773132324, "learning_rate": 3.4360770048205843e-07, "loss": 0.3078921139240265, "step": 1173 }, { "epoch": 32.61971830985915, "grad_norm": 0.391293466091156, "learning_rate": 3.429100968472668e-07, "loss": 0.3184700608253479, "step": 1174 }, { "epoch": 32.647887323943664, "grad_norm": 0.39898040890693665, "learning_rate": 3.4221312404423486e-07, "loss": 0.3164503574371338, "step": 1175 }, { "epoch": 32.67605633802817, "grad_norm": 0.3929812014102936, "learning_rate": 3.4151678419606233e-07, "loss": 0.31639528274536133, "step": 1176 }, { "epoch": 32.70422535211267, "grad_norm": 0.3852669894695282, "learning_rate": 3.4082107942392136e-07, "loss": 0.32435524463653564, "step": 1177 }, { "epoch": 32.732394366197184, "grad_norm": 0.3911198079586029, "learning_rate": 3.4012601184704904e-07, "loss": 0.3171495199203491, "step": 1178 }, { "epoch": 32.76056338028169, "grad_norm": 0.408730685710907, "learning_rate": 3.3943158358274203e-07, "loss": 0.31861793994903564, "step": 1179 }, { "epoch": 32.7887323943662, "grad_norm": 0.40169358253479004, "learning_rate": 3.387377967463493e-07, "loss": 0.3263620436191559, "step": 1180 }, { "epoch": 32.816901408450704, "grad_norm": 0.38852429389953613, "learning_rate": 3.3804465345126545e-07, "loss": 0.3232026696205139, "step": 1181 }, { "epoch": 32.84507042253521, "grad_norm": 0.4023970365524292, "learning_rate": 3.3735215580892575e-07, "loss": 0.31828972697257996, "step": 1182 }, { "epoch": 32.87323943661972, "grad_norm": 0.4030397832393646, "learning_rate": 3.366603059287977e-07, "loss": 0.3154945969581604, "step": 1183 }, { "epoch": 32.901408450704224, "grad_norm": 0.4056568443775177, "learning_rate": 3.359691059183761e-07, "loss": 0.3123217523097992, "step": 1184 }, { "epoch": 32.929577464788736, "grad_norm": 0.3921235501766205, "learning_rate": 3.3527855788317614e-07, "loss": 0.2989099621772766, "step": 1185 }, { "epoch": 32.95774647887324, "grad_norm": 0.3885120451450348, "learning_rate": 3.3458866392672694e-07, "loss": 0.32516202330589294, "step": 1186 }, { "epoch": 32.985915492957744, "grad_norm": 0.37622588872909546, "learning_rate": 3.338994261505649e-07, "loss": 0.30330801010131836, "step": 1187 }, { "epoch": 33.0, "grad_norm": 0.5583658218383789, "learning_rate": 3.3321084665422803e-07, "loss": 0.3030303716659546, "step": 1188 }, { "epoch": 33.028169014084504, "grad_norm": 0.38058674335479736, "learning_rate": 3.325229275352489e-07, "loss": 0.3107704520225525, "step": 1189 }, { "epoch": 33.056338028169016, "grad_norm": 0.39352214336395264, "learning_rate": 3.3183567088914833e-07, "loss": 0.3055182099342346, "step": 1190 }, { "epoch": 33.08450704225352, "grad_norm": 0.4043877124786377, "learning_rate": 3.3114907880942933e-07, "loss": 0.3058846592903137, "step": 1191 }, { "epoch": 33.11267605633803, "grad_norm": 0.41904547810554504, "learning_rate": 3.3046315338757026e-07, "loss": 0.31596750020980835, "step": 1192 }, { "epoch": 33.140845070422536, "grad_norm": 0.3822769820690155, "learning_rate": 3.297778967130191e-07, "loss": 0.30997440218925476, "step": 1193 }, { "epoch": 33.16901408450704, "grad_norm": 0.376291424036026, "learning_rate": 3.290933108731866e-07, "loss": 0.30649077892303467, "step": 1194 }, { "epoch": 33.19718309859155, "grad_norm": 0.38749435544013977, "learning_rate": 3.2840939795343987e-07, "loss": 0.30899763107299805, "step": 1195 }, { "epoch": 33.225352112676056, "grad_norm": 0.40261176228523254, "learning_rate": 3.2772616003709616e-07, "loss": 0.3093717098236084, "step": 1196 }, { "epoch": 33.25352112676056, "grad_norm": 0.41514572501182556, "learning_rate": 3.270435992054166e-07, "loss": 0.3287634253501892, "step": 1197 }, { "epoch": 33.28169014084507, "grad_norm": 0.4071846306324005, "learning_rate": 3.263617175376001e-07, "loss": 0.31616729497909546, "step": 1198 }, { "epoch": 33.309859154929576, "grad_norm": 0.38315486907958984, "learning_rate": 3.2568051711077636e-07, "loss": 0.3143104016780853, "step": 1199 }, { "epoch": 33.33802816901409, "grad_norm": 0.38926801085472107, "learning_rate": 3.250000000000001e-07, "loss": 0.308053582906723, "step": 1200 }, { "epoch": 33.36619718309859, "grad_norm": 0.3905801773071289, "learning_rate": 3.2432016827824414e-07, "loss": 0.3189118802547455, "step": 1201 }, { "epoch": 33.394366197183096, "grad_norm": 0.3899874687194824, "learning_rate": 3.2364102401639423e-07, "loss": 0.31252649426460266, "step": 1202 }, { "epoch": 33.42253521126761, "grad_norm": 0.3951603174209595, "learning_rate": 3.229625692832414e-07, "loss": 0.31354963779449463, "step": 1203 }, { "epoch": 33.45070422535211, "grad_norm": 0.39145639538764954, "learning_rate": 3.222848061454764e-07, "loss": 0.3105824887752533, "step": 1204 }, { "epoch": 33.478873239436616, "grad_norm": 0.38273704051971436, "learning_rate": 3.216077366676833e-07, "loss": 0.31551212072372437, "step": 1205 }, { "epoch": 33.50704225352113, "grad_norm": 0.3839866518974304, "learning_rate": 3.209313629123329e-07, "loss": 0.3138643503189087, "step": 1206 }, { "epoch": 33.53521126760563, "grad_norm": 0.4124429523944855, "learning_rate": 3.2025568693977745e-07, "loss": 0.33224010467529297, "step": 1207 }, { "epoch": 33.563380281690144, "grad_norm": 0.4016134440898895, "learning_rate": 3.195807108082429e-07, "loss": 0.33052581548690796, "step": 1208 }, { "epoch": 33.59154929577465, "grad_norm": 0.39436864852905273, "learning_rate": 3.1890643657382356e-07, "loss": 0.314266562461853, "step": 1209 }, { "epoch": 33.61971830985915, "grad_norm": 0.394286572933197, "learning_rate": 3.182328662904756e-07, "loss": 0.3287787437438965, "step": 1210 }, { "epoch": 33.647887323943664, "grad_norm": 0.4159458577632904, "learning_rate": 3.175600020100112e-07, "loss": 0.3190838694572449, "step": 1211 }, { "epoch": 33.67605633802817, "grad_norm": 0.4120515286922455, "learning_rate": 3.168878457820915e-07, "loss": 0.31985390186309814, "step": 1212 }, { "epoch": 33.70422535211267, "grad_norm": 0.39022156596183777, "learning_rate": 3.162163996542209e-07, "loss": 0.31895437836647034, "step": 1213 }, { "epoch": 33.732394366197184, "grad_norm": 0.39561644196510315, "learning_rate": 3.155456656717408e-07, "loss": 0.32399284839630127, "step": 1214 }, { "epoch": 33.76056338028169, "grad_norm": 0.3976987898349762, "learning_rate": 3.14875645877823e-07, "loss": 0.3074451684951782, "step": 1215 }, { "epoch": 33.7887323943662, "grad_norm": 0.38399186730384827, "learning_rate": 3.142063423134644e-07, "loss": 0.3077697157859802, "step": 1216 }, { "epoch": 33.816901408450704, "grad_norm": 0.3910338580608368, "learning_rate": 3.135377570174796e-07, "loss": 0.3117101192474365, "step": 1217 }, { "epoch": 33.84507042253521, "grad_norm": 0.4071415960788727, "learning_rate": 3.1286989202649503e-07, "loss": 0.3167460858821869, "step": 1218 }, { "epoch": 33.87323943661972, "grad_norm": 0.3974032998085022, "learning_rate": 3.122027493749438e-07, "loss": 0.3139895796775818, "step": 1219 }, { "epoch": 33.901408450704224, "grad_norm": 0.4001885950565338, "learning_rate": 3.115363310950578e-07, "loss": 0.322579950094223, "step": 1220 }, { "epoch": 33.929577464788736, "grad_norm": 0.3947753608226776, "learning_rate": 3.1087063921686263e-07, "loss": 0.31145140528678894, "step": 1221 }, { "epoch": 33.95774647887324, "grad_norm": 0.3906185030937195, "learning_rate": 3.102056757681715e-07, "loss": 0.3211020827293396, "step": 1222 }, { "epoch": 33.985915492957744, "grad_norm": 0.385282963514328, "learning_rate": 3.0954144277457817e-07, "loss": 0.31468886137008667, "step": 1223 }, { "epoch": 34.0, "grad_norm": 0.5563029050827026, "learning_rate": 3.0887794225945143e-07, "loss": 0.3038271963596344, "step": 1224 }, { "epoch": 34.028169014084504, "grad_norm": 0.40991902351379395, "learning_rate": 3.0821517624392925e-07, "loss": 0.3129931092262268, "step": 1225 }, { "epoch": 34.056338028169016, "grad_norm": 0.38615328073501587, "learning_rate": 3.075531467469116e-07, "loss": 0.3070477545261383, "step": 1226 }, { "epoch": 34.08450704225352, "grad_norm": 0.39384523034095764, "learning_rate": 3.0689185578505525e-07, "loss": 0.3211158812046051, "step": 1227 }, { "epoch": 34.11267605633803, "grad_norm": 0.40033310651779175, "learning_rate": 3.062313053727671e-07, "loss": 0.3184252381324768, "step": 1228 }, { "epoch": 34.140845070422536, "grad_norm": 0.38089123368263245, "learning_rate": 3.055714975221981e-07, "loss": 0.31787848472595215, "step": 1229 }, { "epoch": 34.16901408450704, "grad_norm": 0.3946061432361603, "learning_rate": 3.0491243424323783e-07, "loss": 0.31338196992874146, "step": 1230 }, { "epoch": 34.19718309859155, "grad_norm": 0.3816863000392914, "learning_rate": 3.0425411754350694e-07, "loss": 0.3040848970413208, "step": 1231 }, { "epoch": 34.225352112676056, "grad_norm": 0.3998294770717621, "learning_rate": 3.0359654942835247e-07, "loss": 0.3072795271873474, "step": 1232 }, { "epoch": 34.25352112676056, "grad_norm": 0.3975134491920471, "learning_rate": 3.029397319008407e-07, "loss": 0.3205997943878174, "step": 1233 }, { "epoch": 34.28169014084507, "grad_norm": 0.4001832902431488, "learning_rate": 3.02283666961752e-07, "loss": 0.31004253029823303, "step": 1234 }, { "epoch": 34.309859154929576, "grad_norm": 0.37233975529670715, "learning_rate": 3.016283566095739e-07, "loss": 0.30895566940307617, "step": 1235 }, { "epoch": 34.33802816901409, "grad_norm": 0.401897132396698, "learning_rate": 3.0097380284049523e-07, "loss": 0.329042911529541, "step": 1236 }, { "epoch": 34.36619718309859, "grad_norm": 0.38255614042282104, "learning_rate": 3.003200076484004e-07, "loss": 0.31416550278663635, "step": 1237 }, { "epoch": 34.394366197183096, "grad_norm": 0.39941757917404175, "learning_rate": 2.996669730248628e-07, "loss": 0.3108985722064972, "step": 1238 }, { "epoch": 34.42253521126761, "grad_norm": 0.41284579038619995, "learning_rate": 2.9901470095913943e-07, "loss": 0.30534273386001587, "step": 1239 }, { "epoch": 34.45070422535211, "grad_norm": 0.4019896686077118, "learning_rate": 2.9836319343816397e-07, "loss": 0.31917524337768555, "step": 1240 }, { "epoch": 34.478873239436616, "grad_norm": 0.39007240533828735, "learning_rate": 2.977124524465413e-07, "loss": 0.3222888708114624, "step": 1241 }, { "epoch": 34.50704225352113, "grad_norm": 0.3870130181312561, "learning_rate": 2.9706247996654134e-07, "loss": 0.3138411343097687, "step": 1242 }, { "epoch": 34.53521126760563, "grad_norm": 0.3899694085121155, "learning_rate": 2.964132779780929e-07, "loss": 0.3281794786453247, "step": 1243 }, { "epoch": 34.563380281690144, "grad_norm": 0.3935675024986267, "learning_rate": 2.9576484845877793e-07, "loss": 0.3154052495956421, "step": 1244 }, { "epoch": 34.59154929577465, "grad_norm": 0.3940928876399994, "learning_rate": 2.9511719338382535e-07, "loss": 0.31348273158073425, "step": 1245 }, { "epoch": 34.61971830985915, "grad_norm": 0.3740212917327881, "learning_rate": 2.944703147261046e-07, "loss": 0.2983316481113434, "step": 1246 }, { "epoch": 34.647887323943664, "grad_norm": 0.41448095440864563, "learning_rate": 2.938242144561201e-07, "loss": 0.33039140701293945, "step": 1247 }, { "epoch": 34.67605633802817, "grad_norm": 0.39471182227134705, "learning_rate": 2.931788945420058e-07, "loss": 0.31286999583244324, "step": 1248 }, { "epoch": 34.70422535211267, "grad_norm": 0.39080023765563965, "learning_rate": 2.925343569495178e-07, "loss": 0.327096164226532, "step": 1249 }, { "epoch": 34.732394366197184, "grad_norm": 0.3840719163417816, "learning_rate": 2.918906036420294e-07, "loss": 0.30265432596206665, "step": 1250 }, { "epoch": 34.76056338028169, "grad_norm": 0.402336061000824, "learning_rate": 2.9124763658052474e-07, "loss": 0.3189278841018677, "step": 1251 }, { "epoch": 34.7887323943662, "grad_norm": 0.3936392664909363, "learning_rate": 2.9060545772359305e-07, "loss": 0.3178388178348541, "step": 1252 }, { "epoch": 34.816901408450704, "grad_norm": 0.38106682896614075, "learning_rate": 2.8996406902742267e-07, "loss": 0.31674206256866455, "step": 1253 }, { "epoch": 34.84507042253521, "grad_norm": 0.38882869482040405, "learning_rate": 2.893234724457946e-07, "loss": 0.3212617039680481, "step": 1254 }, { "epoch": 34.87323943661972, "grad_norm": 0.3885315954685211, "learning_rate": 2.886836699300771e-07, "loss": 0.3174636662006378, "step": 1255 }, { "epoch": 34.901408450704224, "grad_norm": 0.38163238763809204, "learning_rate": 2.8804466342921987e-07, "loss": 0.3052329421043396, "step": 1256 }, { "epoch": 34.929577464788736, "grad_norm": 0.37909209728240967, "learning_rate": 2.874064548897472e-07, "loss": 0.307166188955307, "step": 1257 }, { "epoch": 34.95774647887324, "grad_norm": 0.39070117473602295, "learning_rate": 2.86769046255753e-07, "loss": 0.30015793442726135, "step": 1258 }, { "epoch": 34.985915492957744, "grad_norm": 0.40061289072036743, "learning_rate": 2.8613243946889477e-07, "loss": 0.31698867678642273, "step": 1259 }, { "epoch": 35.0, "grad_norm": 0.5469854474067688, "learning_rate": 2.854966364683872e-07, "loss": 0.3162824511528015, "step": 1260 }, { "epoch": 35.028169014084504, "grad_norm": 0.38375627994537354, "learning_rate": 2.848616391909959e-07, "loss": 0.3240987956523895, "step": 1261 }, { "epoch": 35.056338028169016, "grad_norm": 0.3947782516479492, "learning_rate": 2.842274495710335e-07, "loss": 0.3070748448371887, "step": 1262 }, { "epoch": 35.08450704225352, "grad_norm": 0.3840290606021881, "learning_rate": 2.835940695403512e-07, "loss": 0.32247135043144226, "step": 1263 }, { "epoch": 35.11267605633803, "grad_norm": 0.39580774307250977, "learning_rate": 2.829615010283344e-07, "loss": 0.31654322147369385, "step": 1264 }, { "epoch": 35.140845070422536, "grad_norm": 0.40300124883651733, "learning_rate": 2.8232974596189653e-07, "loss": 0.31658655405044556, "step": 1265 }, { "epoch": 35.16901408450704, "grad_norm": 0.4221000373363495, "learning_rate": 2.8169880626547283e-07, "loss": 0.3018149137496948, "step": 1266 }, { "epoch": 35.19718309859155, "grad_norm": 0.41154927015304565, "learning_rate": 2.8106868386101545e-07, "loss": 0.31123965978622437, "step": 1267 }, { "epoch": 35.225352112676056, "grad_norm": 0.38422104716300964, "learning_rate": 2.8043938066798645e-07, "loss": 0.32581934332847595, "step": 1268 }, { "epoch": 35.25352112676056, "grad_norm": 0.40688958764076233, "learning_rate": 2.7981089860335225e-07, "loss": 0.30145514011383057, "step": 1269 }, { "epoch": 35.28169014084507, "grad_norm": 0.40068018436431885, "learning_rate": 2.791832395815782e-07, "loss": 0.31062182784080505, "step": 1270 }, { "epoch": 35.309859154929576, "grad_norm": 0.3960703909397125, "learning_rate": 2.7855640551462287e-07, "loss": 0.31022337079048157, "step": 1271 }, { "epoch": 35.33802816901409, "grad_norm": 0.4003959894180298, "learning_rate": 2.7793039831193133e-07, "loss": 0.31739750504493713, "step": 1272 }, { "epoch": 35.36619718309859, "grad_norm": 0.3881884515285492, "learning_rate": 2.773052198804301e-07, "loss": 0.3058944642543793, "step": 1273 }, { "epoch": 35.394366197183096, "grad_norm": 0.40606221556663513, "learning_rate": 2.766808721245211e-07, "loss": 0.33253830671310425, "step": 1274 }, { "epoch": 35.42253521126761, "grad_norm": 0.39820361137390137, "learning_rate": 2.760573569460757e-07, "loss": 0.31713157892227173, "step": 1275 }, { "epoch": 35.45070422535211, "grad_norm": 0.39283862709999084, "learning_rate": 2.7543467624442956e-07, "loss": 0.3196845054626465, "step": 1276 }, { "epoch": 35.478873239436616, "grad_norm": 0.41269436478614807, "learning_rate": 2.7481283191637605e-07, "loss": 0.32910704612731934, "step": 1277 }, { "epoch": 35.50704225352113, "grad_norm": 0.4029068052768707, "learning_rate": 2.741918258561607e-07, "loss": 0.3117852807044983, "step": 1278 }, { "epoch": 35.53521126760563, "grad_norm": 0.3975945711135864, "learning_rate": 2.7357165995547547e-07, "loss": 0.32075372338294983, "step": 1279 }, { "epoch": 35.563380281690144, "grad_norm": 0.3971504271030426, "learning_rate": 2.729523361034538e-07, "loss": 0.30926868319511414, "step": 1280 }, { "epoch": 35.59154929577465, "grad_norm": 0.4112488031387329, "learning_rate": 2.7233385618666315e-07, "loss": 0.3008139729499817, "step": 1281 }, { "epoch": 35.61971830985915, "grad_norm": 0.4135608673095703, "learning_rate": 2.717162220891007e-07, "loss": 0.3115188777446747, "step": 1282 }, { "epoch": 35.647887323943664, "grad_norm": 0.39683884382247925, "learning_rate": 2.7109943569218707e-07, "loss": 0.3205946981906891, "step": 1283 }, { "epoch": 35.67605633802817, "grad_norm": 0.4131380021572113, "learning_rate": 2.7048349887476037e-07, "loss": 0.31822240352630615, "step": 1284 }, { "epoch": 35.70422535211267, "grad_norm": 0.4036876857280731, "learning_rate": 2.698684135130713e-07, "loss": 0.3282153606414795, "step": 1285 }, { "epoch": 35.732394366197184, "grad_norm": 0.39315593242645264, "learning_rate": 2.692541814807763e-07, "loss": 0.31710994243621826, "step": 1286 }, { "epoch": 35.76056338028169, "grad_norm": 0.3925855755805969, "learning_rate": 2.686408046489328e-07, "loss": 0.30646851658821106, "step": 1287 }, { "epoch": 35.7887323943662, "grad_norm": 0.3933147192001343, "learning_rate": 2.6802828488599294e-07, "loss": 0.3093954920768738, "step": 1288 }, { "epoch": 35.816901408450704, "grad_norm": 0.38910675048828125, "learning_rate": 2.6741662405779796e-07, "loss": 0.31154313683509827, "step": 1289 }, { "epoch": 35.84507042253521, "grad_norm": 0.39552295207977295, "learning_rate": 2.6680582402757324e-07, "loss": 0.3187127709388733, "step": 1290 }, { "epoch": 35.87323943661972, "grad_norm": 0.4005042016506195, "learning_rate": 2.661958866559213e-07, "loss": 0.31399422883987427, "step": 1291 }, { "epoch": 35.901408450704224, "grad_norm": 0.3843257427215576, "learning_rate": 2.655868138008171e-07, "loss": 0.3131070137023926, "step": 1292 }, { "epoch": 35.929577464788736, "grad_norm": 0.38986068964004517, "learning_rate": 2.649786073176025e-07, "loss": 0.29762789607048035, "step": 1293 }, { "epoch": 35.95774647887324, "grad_norm": 0.41166046261787415, "learning_rate": 2.6437126905897967e-07, "loss": 0.3069561719894409, "step": 1294 }, { "epoch": 35.985915492957744, "grad_norm": 0.37798550724983215, "learning_rate": 2.637648008750062e-07, "loss": 0.2998811900615692, "step": 1295 }, { "epoch": 36.0, "grad_norm": 0.5611916780471802, "learning_rate": 2.631592046130896e-07, "loss": 0.3010321855545044, "step": 1296 }, { "epoch": 36.028169014084504, "grad_norm": 0.38474971055984497, "learning_rate": 2.6255448211798103e-07, "loss": 0.2947436273097992, "step": 1297 }, { "epoch": 36.056338028169016, "grad_norm": 0.3869876563549042, "learning_rate": 2.6195063523177e-07, "loss": 0.3073881268501282, "step": 1298 }, { "epoch": 36.08450704225352, "grad_norm": 0.38903966546058655, "learning_rate": 2.613476657938789e-07, "loss": 0.30671149492263794, "step": 1299 }, { "epoch": 36.11267605633803, "grad_norm": 0.39427390694618225, "learning_rate": 2.6074557564105724e-07, "loss": 0.30495786666870117, "step": 1300 }, { "epoch": 36.140845070422536, "grad_norm": 0.3966522514820099, "learning_rate": 2.6014436660737605e-07, "loss": 0.32202261686325073, "step": 1301 }, { "epoch": 36.16901408450704, "grad_norm": 0.3896190822124481, "learning_rate": 2.595440405242222e-07, "loss": 0.32409781217575073, "step": 1302 }, { "epoch": 36.19718309859155, "grad_norm": 0.38690999150276184, "learning_rate": 2.589445992202931e-07, "loss": 0.3142644464969635, "step": 1303 }, { "epoch": 36.225352112676056, "grad_norm": 0.3986409306526184, "learning_rate": 2.583460445215911e-07, "loss": 0.3045003414154053, "step": 1304 }, { "epoch": 36.25352112676056, "grad_norm": 0.39241185784339905, "learning_rate": 2.5774837825141736e-07, "loss": 0.3323992192745209, "step": 1305 }, { "epoch": 36.28169014084507, "grad_norm": 0.380597859621048, "learning_rate": 2.571516022303671e-07, "loss": 0.303973913192749, "step": 1306 }, { "epoch": 36.309859154929576, "grad_norm": 0.4070303738117218, "learning_rate": 2.565557182763235e-07, "loss": 0.320231556892395, "step": 1307 }, { "epoch": 36.33802816901409, "grad_norm": 0.4098987579345703, "learning_rate": 2.5596072820445254e-07, "loss": 0.30470702052116394, "step": 1308 }, { "epoch": 36.36619718309859, "grad_norm": 0.3843023478984833, "learning_rate": 2.5536663382719713e-07, "loss": 0.31042495369911194, "step": 1309 }, { "epoch": 36.394366197183096, "grad_norm": 0.39277711510658264, "learning_rate": 2.547734369542718e-07, "loss": 0.31068137288093567, "step": 1310 }, { "epoch": 36.42253521126761, "grad_norm": 0.4235474169254303, "learning_rate": 2.5418113939265686e-07, "loss": 0.3261791467666626, "step": 1311 }, { "epoch": 36.45070422535211, "grad_norm": 0.3789258301258087, "learning_rate": 2.5358974294659373e-07, "loss": 0.3244026303291321, "step": 1312 }, { "epoch": 36.478873239436616, "grad_norm": 0.38320809602737427, "learning_rate": 2.5299924941757843e-07, "loss": 0.30314409732818604, "step": 1313 }, { "epoch": 36.50704225352113, "grad_norm": 0.38217753171920776, "learning_rate": 2.5240966060435674e-07, "loss": 0.3076429069042206, "step": 1314 }, { "epoch": 36.53521126760563, "grad_norm": 0.39943623542785645, "learning_rate": 2.5182097830291824e-07, "loss": 0.3149079978466034, "step": 1315 }, { "epoch": 36.563380281690144, "grad_norm": 0.4079552888870239, "learning_rate": 2.512332043064913e-07, "loss": 0.31648725271224976, "step": 1316 }, { "epoch": 36.59154929577465, "grad_norm": 0.4055273234844208, "learning_rate": 2.5064634040553767e-07, "loss": 0.3102360665798187, "step": 1317 }, { "epoch": 36.61971830985915, "grad_norm": 0.3877866864204407, "learning_rate": 2.5006038838774647e-07, "loss": 0.32769399881362915, "step": 1318 }, { "epoch": 36.647887323943664, "grad_norm": 0.3878704607486725, "learning_rate": 2.494753500380291e-07, "loss": 0.2987005114555359, "step": 1319 }, { "epoch": 36.67605633802817, "grad_norm": 0.38627228140830994, "learning_rate": 2.488912271385139e-07, "loss": 0.3112736940383911, "step": 1320 }, { "epoch": 36.70422535211267, "grad_norm": 0.3981247842311859, "learning_rate": 2.483080214685404e-07, "loss": 0.3074178993701935, "step": 1321 }, { "epoch": 36.732394366197184, "grad_norm": 0.3987123668193817, "learning_rate": 2.4772573480465445e-07, "loss": 0.31392043828964233, "step": 1322 }, { "epoch": 36.76056338028169, "grad_norm": 0.3950229585170746, "learning_rate": 2.471443689206021e-07, "loss": 0.31246301531791687, "step": 1323 }, { "epoch": 36.7887323943662, "grad_norm": 0.3868275582790375, "learning_rate": 2.465639255873246e-07, "loss": 0.3093280792236328, "step": 1324 }, { "epoch": 36.816901408450704, "grad_norm": 0.4026741087436676, "learning_rate": 2.4598440657295286e-07, "loss": 0.32681965827941895, "step": 1325 }, { "epoch": 36.84507042253521, "grad_norm": 0.4036796987056732, "learning_rate": 2.454058136428027e-07, "loss": 0.3122265636920929, "step": 1326 }, { "epoch": 36.87323943661972, "grad_norm": 0.392522394657135, "learning_rate": 2.4482814855936834e-07, "loss": 0.30846884846687317, "step": 1327 }, { "epoch": 36.901408450704224, "grad_norm": 0.426935076713562, "learning_rate": 2.4425141308231765e-07, "loss": 0.325960636138916, "step": 1328 }, { "epoch": 36.929577464788736, "grad_norm": 0.418603777885437, "learning_rate": 2.43675608968487e-07, "loss": 0.32600370049476624, "step": 1329 }, { "epoch": 36.95774647887324, "grad_norm": 0.39998194575309753, "learning_rate": 2.4310073797187573e-07, "loss": 0.3105314075946808, "step": 1330 }, { "epoch": 36.985915492957744, "grad_norm": 0.3858794867992401, "learning_rate": 2.4252680184364045e-07, "loss": 0.3095932602882385, "step": 1331 }, { "epoch": 37.0, "grad_norm": 0.5600153803825378, "learning_rate": 2.4195380233209006e-07, "loss": 0.29655295610427856, "step": 1332 }, { "epoch": 37.028169014084504, "grad_norm": 0.3757314383983612, "learning_rate": 2.413817411826807e-07, "loss": 0.3107462227344513, "step": 1333 }, { "epoch": 37.056338028169016, "grad_norm": 0.37666600942611694, "learning_rate": 2.408106201380097e-07, "loss": 0.31727492809295654, "step": 1334 }, { "epoch": 37.08450704225352, "grad_norm": 0.4031192660331726, "learning_rate": 2.4024044093781063e-07, "loss": 0.31785914301872253, "step": 1335 }, { "epoch": 37.11267605633803, "grad_norm": 0.4000700116157532, "learning_rate": 2.3967120531894857e-07, "loss": 0.30468472838401794, "step": 1336 }, { "epoch": 37.140845070422536, "grad_norm": 0.38557133078575134, "learning_rate": 2.391029150154137e-07, "loss": 0.29351887106895447, "step": 1337 }, { "epoch": 37.16901408450704, "grad_norm": 0.39428290724754333, "learning_rate": 2.38535571758317e-07, "loss": 0.3094083070755005, "step": 1338 }, { "epoch": 37.19718309859155, "grad_norm": 0.40703415870666504, "learning_rate": 2.3796917727588412e-07, "loss": 0.3140762150287628, "step": 1339 }, { "epoch": 37.225352112676056, "grad_norm": 0.4024847745895386, "learning_rate": 2.374037332934512e-07, "loss": 0.31750038266181946, "step": 1340 }, { "epoch": 37.25352112676056, "grad_norm": 0.4012693464756012, "learning_rate": 2.3683924153345854e-07, "loss": 0.31085819005966187, "step": 1341 }, { "epoch": 37.28169014084507, "grad_norm": 0.4095834493637085, "learning_rate": 2.36275703715446e-07, "loss": 0.3142126202583313, "step": 1342 }, { "epoch": 37.309859154929576, "grad_norm": 0.39079487323760986, "learning_rate": 2.357131215560474e-07, "loss": 0.3125237822532654, "step": 1343 }, { "epoch": 37.33802816901409, "grad_norm": 0.38285982608795166, "learning_rate": 2.3515149676898552e-07, "loss": 0.30938810110092163, "step": 1344 }, { "epoch": 37.36619718309859, "grad_norm": 0.4154026210308075, "learning_rate": 2.3459083106506712e-07, "loss": 0.31037092208862305, "step": 1345 }, { "epoch": 37.394366197183096, "grad_norm": 0.3945370018482208, "learning_rate": 2.3403112615217693e-07, "loss": 0.30695176124572754, "step": 1346 }, { "epoch": 37.42253521126761, "grad_norm": 0.39862382411956787, "learning_rate": 2.334723837352733e-07, "loss": 0.3081490993499756, "step": 1347 }, { "epoch": 37.45070422535211, "grad_norm": 0.3906742334365845, "learning_rate": 2.3291460551638237e-07, "loss": 0.31045928597450256, "step": 1348 }, { "epoch": 37.478873239436616, "grad_norm": 0.3924495577812195, "learning_rate": 2.3235779319459355e-07, "loss": 0.31619560718536377, "step": 1349 }, { "epoch": 37.50704225352113, "grad_norm": 0.38988739252090454, "learning_rate": 2.3180194846605364e-07, "loss": 0.32699936628341675, "step": 1350 }, { "epoch": 37.53521126760563, "grad_norm": 0.405262291431427, "learning_rate": 2.312470730239621e-07, "loss": 0.3238704800605774, "step": 1351 }, { "epoch": 37.563380281690144, "grad_norm": 0.41496768593788147, "learning_rate": 2.306931685585657e-07, "loss": 0.31248730421066284, "step": 1352 }, { "epoch": 37.59154929577465, "grad_norm": 0.38783204555511475, "learning_rate": 2.3014023675715339e-07, "loss": 0.3076411485671997, "step": 1353 }, { "epoch": 37.61971830985915, "grad_norm": 0.39510872960090637, "learning_rate": 2.2958827930405162e-07, "loss": 0.3164839446544647, "step": 1354 }, { "epoch": 37.647887323943664, "grad_norm": 0.3897303342819214, "learning_rate": 2.2903729788061834e-07, "loss": 0.31742557883262634, "step": 1355 }, { "epoch": 37.67605633802817, "grad_norm": 0.4140264093875885, "learning_rate": 2.2848729416523859e-07, "loss": 0.3227437138557434, "step": 1356 }, { "epoch": 37.70422535211267, "grad_norm": 0.3824675679206848, "learning_rate": 2.2793826983331886e-07, "loss": 0.3105960488319397, "step": 1357 }, { "epoch": 37.732394366197184, "grad_norm": 0.39121127128601074, "learning_rate": 2.2739022655728277e-07, "loss": 0.3190494179725647, "step": 1358 }, { "epoch": 37.76056338028169, "grad_norm": 0.39836981892585754, "learning_rate": 2.268431660065651e-07, "loss": 0.31450414657592773, "step": 1359 }, { "epoch": 37.7887323943662, "grad_norm": 0.4026944935321808, "learning_rate": 2.2629708984760706e-07, "loss": 0.3044552206993103, "step": 1360 }, { "epoch": 37.816901408450704, "grad_norm": 0.4023437201976776, "learning_rate": 2.2575199974385144e-07, "loss": 0.30423471331596375, "step": 1361 }, { "epoch": 37.84507042253521, "grad_norm": 0.386771023273468, "learning_rate": 2.2520789735573704e-07, "loss": 0.3087488114833832, "step": 1362 }, { "epoch": 37.87323943661972, "grad_norm": 0.388527512550354, "learning_rate": 2.2466478434069435e-07, "loss": 0.30881020426750183, "step": 1363 }, { "epoch": 37.901408450704224, "grad_norm": 0.3937196731567383, "learning_rate": 2.2412266235313973e-07, "loss": 0.31379616260528564, "step": 1364 }, { "epoch": 37.929577464788736, "grad_norm": 0.4006229639053345, "learning_rate": 2.2358153304447066e-07, "loss": 0.3123682737350464, "step": 1365 }, { "epoch": 37.95774647887324, "grad_norm": 0.41852372884750366, "learning_rate": 2.230413980630609e-07, "loss": 0.3102847933769226, "step": 1366 }, { "epoch": 37.985915492957744, "grad_norm": 0.40430253744125366, "learning_rate": 2.2250225905425532e-07, "loss": 0.31682825088500977, "step": 1367 }, { "epoch": 38.0, "grad_norm": 0.5757198333740234, "learning_rate": 2.2196411766036487e-07, "loss": 0.31206148862838745, "step": 1368 }, { "epoch": 38.028169014084504, "grad_norm": 0.3904403746128082, "learning_rate": 2.2142697552066142e-07, "loss": 0.31840282678604126, "step": 1369 }, { "epoch": 38.056338028169016, "grad_norm": 0.40474748611450195, "learning_rate": 2.2089083427137329e-07, "loss": 0.314113587141037, "step": 1370 }, { "epoch": 38.08450704225352, "grad_norm": 0.39501574635505676, "learning_rate": 2.203556955456796e-07, "loss": 0.3120426833629608, "step": 1371 }, { "epoch": 38.11267605633803, "grad_norm": 0.3965202867984772, "learning_rate": 2.1982156097370557e-07, "loss": 0.3060588240623474, "step": 1372 }, { "epoch": 38.140845070422536, "grad_norm": 0.39132386445999146, "learning_rate": 2.1928843218251803e-07, "loss": 0.3127366006374359, "step": 1373 }, { "epoch": 38.16901408450704, "grad_norm": 0.39058858156204224, "learning_rate": 2.1875631079611956e-07, "loss": 0.3184279501438141, "step": 1374 }, { "epoch": 38.19718309859155, "grad_norm": 0.401569128036499, "learning_rate": 2.1822519843544422e-07, "loss": 0.32573437690734863, "step": 1375 }, { "epoch": 38.225352112676056, "grad_norm": 0.40431272983551025, "learning_rate": 2.1769509671835223e-07, "loss": 0.31891560554504395, "step": 1376 }, { "epoch": 38.25352112676056, "grad_norm": 0.3908335566520691, "learning_rate": 2.1716600725962558e-07, "loss": 0.31629955768585205, "step": 1377 }, { "epoch": 38.28169014084507, "grad_norm": 0.3957464396953583, "learning_rate": 2.166379316709625e-07, "loss": 0.31716036796569824, "step": 1378 }, { "epoch": 38.309859154929576, "grad_norm": 0.3994870185852051, "learning_rate": 2.1611087156097267e-07, "loss": 0.3021211624145508, "step": 1379 }, { "epoch": 38.33802816901409, "grad_norm": 0.3890848755836487, "learning_rate": 2.1558482853517253e-07, "loss": 0.32993414998054504, "step": 1380 }, { "epoch": 38.36619718309859, "grad_norm": 0.3980858027935028, "learning_rate": 2.1505980419598063e-07, "loss": 0.32392680644989014, "step": 1381 }, { "epoch": 38.394366197183096, "grad_norm": 0.39642319083213806, "learning_rate": 2.1453580014271203e-07, "loss": 0.3059401512145996, "step": 1382 }, { "epoch": 38.42253521126761, "grad_norm": 0.3873026371002197, "learning_rate": 2.1401281797157395e-07, "loss": 0.3207471966743469, "step": 1383 }, { "epoch": 38.45070422535211, "grad_norm": 0.3935808837413788, "learning_rate": 2.134908592756607e-07, "loss": 0.3021237552165985, "step": 1384 }, { "epoch": 38.478873239436616, "grad_norm": 0.392278790473938, "learning_rate": 2.1296992564494904e-07, "loss": 0.29950061440467834, "step": 1385 }, { "epoch": 38.50704225352113, "grad_norm": 0.38675200939178467, "learning_rate": 2.124500186662932e-07, "loss": 0.30802223086357117, "step": 1386 }, { "epoch": 38.53521126760563, "grad_norm": 0.40296921133995056, "learning_rate": 2.1193113992342001e-07, "loss": 0.30401256680488586, "step": 1387 }, { "epoch": 38.563380281690144, "grad_norm": 0.40829116106033325, "learning_rate": 2.1141329099692406e-07, "loss": 0.3227273225784302, "step": 1388 }, { "epoch": 38.59154929577465, "grad_norm": 0.39048704504966736, "learning_rate": 2.1089647346426303e-07, "loss": 0.30031925439834595, "step": 1389 }, { "epoch": 38.61971830985915, "grad_norm": 0.4031343460083008, "learning_rate": 2.1038068889975259e-07, "loss": 0.3076460361480713, "step": 1390 }, { "epoch": 38.647887323943664, "grad_norm": 0.3995644152164459, "learning_rate": 2.0986593887456223e-07, "loss": 0.3031764328479767, "step": 1391 }, { "epoch": 38.67605633802817, "grad_norm": 0.39107468724250793, "learning_rate": 2.0935222495670968e-07, "loss": 0.32095766067504883, "step": 1392 }, { "epoch": 38.70422535211267, "grad_norm": 0.3904801905155182, "learning_rate": 2.088395487110566e-07, "loss": 0.31498321890830994, "step": 1393 }, { "epoch": 38.732394366197184, "grad_norm": 0.42515355348587036, "learning_rate": 2.0832791169930363e-07, "loss": 0.2987384796142578, "step": 1394 }, { "epoch": 38.76056338028169, "grad_norm": 0.3929113447666168, "learning_rate": 2.078173154799861e-07, "loss": 0.3008019030094147, "step": 1395 }, { "epoch": 38.7887323943662, "grad_norm": 0.38760364055633545, "learning_rate": 2.0730776160846853e-07, "loss": 0.3130109906196594, "step": 1396 }, { "epoch": 38.816901408450704, "grad_norm": 0.40122318267822266, "learning_rate": 2.0679925163694033e-07, "loss": 0.32113420963287354, "step": 1397 }, { "epoch": 38.84507042253521, "grad_norm": 0.4061526954174042, "learning_rate": 2.0629178711441115e-07, "loss": 0.30463290214538574, "step": 1398 }, { "epoch": 38.87323943661972, "grad_norm": 0.39891040325164795, "learning_rate": 2.0578536958670574e-07, "loss": 0.30295246839523315, "step": 1399 }, { "epoch": 38.901408450704224, "grad_norm": 0.39336952567100525, "learning_rate": 2.0528000059645995e-07, "loss": 0.3047736883163452, "step": 1400 }, { "epoch": 38.929577464788736, "grad_norm": 0.38915321230888367, "learning_rate": 2.0477568168311525e-07, "loss": 0.33302927017211914, "step": 1401 }, { "epoch": 38.95774647887324, "grad_norm": 0.3906260132789612, "learning_rate": 2.042724143829146e-07, "loss": 0.30394965410232544, "step": 1402 }, { "epoch": 38.985915492957744, "grad_norm": 0.4056362807750702, "learning_rate": 2.037702002288973e-07, "loss": 0.3015964925289154, "step": 1403 }, { "epoch": 39.0, "grad_norm": 0.5561332106590271, "learning_rate": 2.032690407508949e-07, "loss": 0.3190940022468567, "step": 1404 } ], "logging_steps": 1, "max_steps": 1800, "num_input_tokens_seen": 0, "num_train_epochs": 50, "save_steps": 1.0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.9069259564638536e+18, "train_batch_size": 32, "trial_name": null, "trial_params": null }