{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 10797, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0046311304589450285, "grad_norm": 45311.37890625, "learning_rate": 4.537037037037038e-07, "loss": 5.1101, "step": 50 }, { "epoch": 0.009262260917890057, "grad_norm": 24385.150390625, "learning_rate": 9.166666666666666e-07, "loss": 5.4531, "step": 100 }, { "epoch": 0.013893391376835085, "grad_norm": 17766.69921875, "learning_rate": 1.3796296296296296e-06, "loss": 6.8544, "step": 150 }, { "epoch": 0.018524521835780114, "grad_norm": 24810.97265625, "learning_rate": 1.8425925925925927e-06, "loss": 8.9807, "step": 200 }, { "epoch": 0.023155652294725142, "grad_norm": 20551.3984375, "learning_rate": 2.305555555555556e-06, "loss": 14.0074, "step": 250 }, { "epoch": 0.02778678275367017, "grad_norm": 35652.94921875, "learning_rate": 2.7685185185185187e-06, "loss": 20.0341, "step": 300 }, { "epoch": 0.0324179132126152, "grad_norm": 43745.55859375, "learning_rate": 3.2314814814814814e-06, "loss": 22.4377, "step": 350 }, { "epoch": 0.03704904367156023, "grad_norm": 170773.203125, "learning_rate": 3.694444444444445e-06, "loss": 26.4996, "step": 400 }, { "epoch": 0.04168017413050526, "grad_norm": 158025.984375, "learning_rate": 4.157407407407408e-06, "loss": 36.6171, "step": 450 }, { "epoch": 0.046311304589450285, "grad_norm": 34478.3203125, "learning_rate": 4.620370370370371e-06, "loss": 30.4798, "step": 500 }, { "epoch": 0.05094243504839532, "grad_norm": 136783.609375, "learning_rate": 5.0833333333333335e-06, "loss": 34.9235, "step": 550 }, { "epoch": 0.05557356550734034, "grad_norm": 74166.8984375, "learning_rate": 5.546296296296296e-06, "loss": 36.3313, "step": 600 }, { "epoch": 0.060204695966285374, "grad_norm": 81349.1015625, "learning_rate": 6.009259259259261e-06, "loss": 35.7238, "step": 650 }, { "epoch": 0.0648358264252304, "grad_norm": 131790.796875, "learning_rate": 6.472222222222223e-06, "loss": 37.7356, "step": 700 }, { "epoch": 0.06946695688417542, "grad_norm": 104120.3359375, "learning_rate": 6.935185185185186e-06, "loss": 39.6583, "step": 750 }, { "epoch": 0.07409808734312046, "grad_norm": 20184.501953125, "learning_rate": 7.398148148148149e-06, "loss": 43.7877, "step": 800 }, { "epoch": 0.07872921780206549, "grad_norm": 28208.6328125, "learning_rate": 7.861111111111112e-06, "loss": 56.835, "step": 850 }, { "epoch": 0.08336034826101052, "grad_norm": 41647.78515625, "learning_rate": 8.324074074074074e-06, "loss": 52.439, "step": 900 }, { "epoch": 0.08799147871995554, "grad_norm": 44205.96875, "learning_rate": 8.787037037037038e-06, "loss": 51.0145, "step": 950 }, { "epoch": 0.09262260917890057, "grad_norm": 32592.4609375, "learning_rate": 9.250000000000001e-06, "loss": 48.7292, "step": 1000 }, { "epoch": 0.0972537396378456, "grad_norm": 18587.83984375, "learning_rate": 9.712962962962965e-06, "loss": 55.1206, "step": 1050 }, { "epoch": 0.10188487009679063, "grad_norm": 54501.23828125, "learning_rate": 9.980446639909439e-06, "loss": 55.8502, "step": 1100 }, { "epoch": 0.10651600055573565, "grad_norm": 31179.115234375, "learning_rate": 9.928990429144798e-06, "loss": 56.1253, "step": 1150 }, { "epoch": 0.11114713101468068, "grad_norm": 19028.408203125, "learning_rate": 9.877534218380159e-06, "loss": 51.6047, "step": 1200 }, { "epoch": 0.11577826147362572, "grad_norm": 23272.919921875, "learning_rate": 9.826078007615521e-06, "loss": 48.5006, "step": 1250 }, { "epoch": 0.12040939193257075, "grad_norm": 20129.248046875, "learning_rate": 9.77462179685088e-06, "loss": 47.4703, "step": 1300 }, { "epoch": 0.12504052239151578, "grad_norm": 20898.05859375, "learning_rate": 9.723165586086241e-06, "loss": 47.1912, "step": 1350 }, { "epoch": 0.1296716528504608, "grad_norm": 30558.55859375, "learning_rate": 9.671709375321602e-06, "loss": 41.2223, "step": 1400 }, { "epoch": 0.13430278330940582, "grad_norm": 25856.19140625, "learning_rate": 9.620253164556963e-06, "loss": 39.0084, "step": 1450 }, { "epoch": 0.13893391376835085, "grad_norm": 16568.400390625, "learning_rate": 9.568796953792322e-06, "loss": 41.6975, "step": 1500 }, { "epoch": 0.14356504422729588, "grad_norm": 14717.109375, "learning_rate": 9.517340743027685e-06, "loss": 34.7697, "step": 1550 }, { "epoch": 0.1481961746862409, "grad_norm": 16112.0263671875, "learning_rate": 9.465884532263044e-06, "loss": 32.84, "step": 1600 }, { "epoch": 0.15282730514518594, "grad_norm": 28320.36328125, "learning_rate": 9.414428321498405e-06, "loss": 30.6541, "step": 1650 }, { "epoch": 0.15745843560413098, "grad_norm": 14664.193359375, "learning_rate": 9.362972110733768e-06, "loss": 24.7009, "step": 1700 }, { "epoch": 0.162089566063076, "grad_norm": 5361.5087890625, "learning_rate": 9.311515899969127e-06, "loss": 18.9679, "step": 1750 }, { "epoch": 0.16672069652202104, "grad_norm": 3825.643798828125, "learning_rate": 9.260059689204488e-06, "loss": 14.1527, "step": 1800 }, { "epoch": 0.17135182698096604, "grad_norm": 687.0768432617188, "learning_rate": 9.208603478439848e-06, "loss": 8.0994, "step": 1850 }, { "epoch": 0.17598295743991108, "grad_norm": 161.3083038330078, "learning_rate": 9.15714726767521e-06, "loss": 5.4372, "step": 1900 }, { "epoch": 0.1806140878988561, "grad_norm": 111.15824890136719, "learning_rate": 9.10569105691057e-06, "loss": 5.0239, "step": 1950 }, { "epoch": 0.18524521835780114, "grad_norm": 62.675636291503906, "learning_rate": 9.054234846145931e-06, "loss": 4.9312, "step": 2000 }, { "epoch": 0.18987634881674617, "grad_norm": 40.70977020263672, "learning_rate": 9.00277863538129e-06, "loss": 4.8934, "step": 2050 }, { "epoch": 0.1945074792756912, "grad_norm": 31.48650550842285, "learning_rate": 8.951322424616651e-06, "loss": 4.8852, "step": 2100 }, { "epoch": 0.19913860973463623, "grad_norm": 28.155406951904297, "learning_rate": 8.899866213852014e-06, "loss": 4.8705, "step": 2150 }, { "epoch": 0.20376974019358127, "grad_norm": 30.841955184936523, "learning_rate": 8.848410003087373e-06, "loss": 4.8821, "step": 2200 }, { "epoch": 0.20840087065252627, "grad_norm": 17.3418025970459, "learning_rate": 8.796953792322734e-06, "loss": 4.8662, "step": 2250 }, { "epoch": 0.2130320011114713, "grad_norm": 15.722943305969238, "learning_rate": 8.745497581558095e-06, "loss": 4.8593, "step": 2300 }, { "epoch": 0.21766313157041633, "grad_norm": 12.287271499633789, "learning_rate": 8.694041370793456e-06, "loss": 4.8663, "step": 2350 }, { "epoch": 0.22229426202936137, "grad_norm": 8.732343673706055, "learning_rate": 8.642585160028816e-06, "loss": 4.861, "step": 2400 }, { "epoch": 0.2269253924883064, "grad_norm": 18.63037872314453, "learning_rate": 8.591128949264177e-06, "loss": 4.8586, "step": 2450 }, { "epoch": 0.23155652294725143, "grad_norm": 10.168179512023926, "learning_rate": 8.539672738499537e-06, "loss": 4.8613, "step": 2500 }, { "epoch": 0.23618765340619646, "grad_norm": 8.444642066955566, "learning_rate": 8.488216527734897e-06, "loss": 4.8552, "step": 2550 }, { "epoch": 0.2408187838651415, "grad_norm": 6.634263038635254, "learning_rate": 8.43676031697026e-06, "loss": 4.8612, "step": 2600 }, { "epoch": 0.2454499143240865, "grad_norm": 9.856132507324219, "learning_rate": 8.38530410620562e-06, "loss": 4.8555, "step": 2650 }, { "epoch": 0.25008104478303156, "grad_norm": 6.173237323760986, "learning_rate": 8.33384789544098e-06, "loss": 4.854, "step": 2700 }, { "epoch": 0.2547121752419766, "grad_norm": 8.70698356628418, "learning_rate": 8.282391684676341e-06, "loss": 4.8522, "step": 2750 }, { "epoch": 0.2593433057009216, "grad_norm": 4.96877908706665, "learning_rate": 8.230935473911702e-06, "loss": 4.8563, "step": 2800 }, { "epoch": 0.2639744361598666, "grad_norm": 6.604714393615723, "learning_rate": 8.179479263147063e-06, "loss": 4.8491, "step": 2850 }, { "epoch": 0.26860556661881163, "grad_norm": 7.707324981689453, "learning_rate": 8.128023052382424e-06, "loss": 4.8559, "step": 2900 }, { "epoch": 0.27323669707775666, "grad_norm": 6.189296245574951, "learning_rate": 8.076566841617785e-06, "loss": 4.8549, "step": 2950 }, { "epoch": 0.2778678275367017, "grad_norm": 4.309783935546875, "learning_rate": 8.025110630853145e-06, "loss": 4.8547, "step": 3000 }, { "epoch": 0.2824989579956467, "grad_norm": 5.0381999015808105, "learning_rate": 7.973654420088506e-06, "loss": 4.8552, "step": 3050 }, { "epoch": 0.28713008845459176, "grad_norm": 10.880996704101562, "learning_rate": 7.922198209323865e-06, "loss": 4.8581, "step": 3100 }, { "epoch": 0.2917612189135368, "grad_norm": 4.348069190979004, "learning_rate": 7.870741998559226e-06, "loss": 4.8557, "step": 3150 }, { "epoch": 0.2963923493724818, "grad_norm": 11.774301528930664, "learning_rate": 7.819285787794587e-06, "loss": 4.8533, "step": 3200 }, { "epoch": 0.30102347983142685, "grad_norm": 12.425819396972656, "learning_rate": 7.767829577029948e-06, "loss": 4.8567, "step": 3250 }, { "epoch": 0.3056546102903719, "grad_norm": 4.84695291519165, "learning_rate": 7.716373366265309e-06, "loss": 4.8513, "step": 3300 }, { "epoch": 0.3102857407493169, "grad_norm": 5.18828010559082, "learning_rate": 7.66491715550067e-06, "loss": 4.8538, "step": 3350 }, { "epoch": 0.31491687120826195, "grad_norm": 10.579144477844238, "learning_rate": 7.613460944736031e-06, "loss": 4.8549, "step": 3400 }, { "epoch": 0.319548001667207, "grad_norm": 3.7520084381103516, "learning_rate": 7.562004733971391e-06, "loss": 4.8546, "step": 3450 }, { "epoch": 0.324179132126152, "grad_norm": 5.303626537322998, "learning_rate": 7.510548523206752e-06, "loss": 4.8527, "step": 3500 }, { "epoch": 0.32881026258509705, "grad_norm": 3.4561500549316406, "learning_rate": 7.459092312442113e-06, "loss": 4.8547, "step": 3550 }, { "epoch": 0.3334413930440421, "grad_norm": 4.276394367218018, "learning_rate": 7.4076361016774735e-06, "loss": 4.854, "step": 3600 }, { "epoch": 0.33807252350298705, "grad_norm": 6.949066162109375, "learning_rate": 7.3561798909128335e-06, "loss": 4.8526, "step": 3650 }, { "epoch": 0.3427036539619321, "grad_norm": 3.7716352939605713, "learning_rate": 7.304723680148194e-06, "loss": 4.8529, "step": 3700 }, { "epoch": 0.3473347844208771, "grad_norm": 3.8829033374786377, "learning_rate": 7.2532674693835544e-06, "loss": 4.8516, "step": 3750 }, { "epoch": 0.35196591487982215, "grad_norm": 7.156257629394531, "learning_rate": 7.201811258618916e-06, "loss": 4.8566, "step": 3800 }, { "epoch": 0.3565970453387672, "grad_norm": 3.4680042266845703, "learning_rate": 7.150355047854277e-06, "loss": 4.8521, "step": 3850 }, { "epoch": 0.3612281757977122, "grad_norm": 6.309057712554932, "learning_rate": 7.098898837089637e-06, "loss": 4.852, "step": 3900 }, { "epoch": 0.36585930625665725, "grad_norm": 3.311298131942749, "learning_rate": 7.047442626324999e-06, "loss": 4.8532, "step": 3950 }, { "epoch": 0.3704904367156023, "grad_norm": 4.21369743347168, "learning_rate": 6.995986415560359e-06, "loss": 4.8541, "step": 4000 }, { "epoch": 0.3751215671745473, "grad_norm": 3.184129238128662, "learning_rate": 6.94453020479572e-06, "loss": 4.8545, "step": 4050 }, { "epoch": 0.37975269763349234, "grad_norm": 7.411576747894287, "learning_rate": 6.89307399403108e-06, "loss": 4.8561, "step": 4100 }, { "epoch": 0.3843838280924374, "grad_norm": 7.5306878089904785, "learning_rate": 6.841617783266441e-06, "loss": 4.8524, "step": 4150 }, { "epoch": 0.3890149585513824, "grad_norm": 6.128129005432129, "learning_rate": 6.790161572501801e-06, "loss": 4.8531, "step": 4200 }, { "epoch": 0.39364608901032744, "grad_norm": 5.687031269073486, "learning_rate": 6.7387053617371624e-06, "loss": 4.8514, "step": 4250 }, { "epoch": 0.39827721946927247, "grad_norm": 3.1113038063049316, "learning_rate": 6.687249150972523e-06, "loss": 4.8537, "step": 4300 }, { "epoch": 0.4029083499282175, "grad_norm": 8.376502990722656, "learning_rate": 6.635792940207883e-06, "loss": 4.8534, "step": 4350 }, { "epoch": 0.40753948038716253, "grad_norm": 7.945234775543213, "learning_rate": 6.584336729443245e-06, "loss": 4.8529, "step": 4400 }, { "epoch": 0.4121706108461075, "grad_norm": 3.565673351287842, "learning_rate": 6.532880518678605e-06, "loss": 4.8543, "step": 4450 }, { "epoch": 0.41680174130505254, "grad_norm": 3.2953274250030518, "learning_rate": 6.481424307913966e-06, "loss": 4.8503, "step": 4500 }, { "epoch": 0.4214328717639976, "grad_norm": 2.9050490856170654, "learning_rate": 6.429968097149326e-06, "loss": 4.8533, "step": 4550 }, { "epoch": 0.4260640022229426, "grad_norm": 7.26942777633667, "learning_rate": 6.378511886384687e-06, "loss": 4.854, "step": 4600 }, { "epoch": 0.43069513268188764, "grad_norm": 4.875161647796631, "learning_rate": 6.327055675620048e-06, "loss": 4.8547, "step": 4650 }, { "epoch": 0.43532626314083267, "grad_norm": 3.538259267807007, "learning_rate": 6.275599464855409e-06, "loss": 4.8524, "step": 4700 }, { "epoch": 0.4399573935997777, "grad_norm": 7.06084680557251, "learning_rate": 6.2241432540907696e-06, "loss": 4.8519, "step": 4750 }, { "epoch": 0.44458852405872273, "grad_norm": 3.635225534439087, "learning_rate": 6.17268704332613e-06, "loss": 4.8525, "step": 4800 }, { "epoch": 0.44921965451766777, "grad_norm": 4.0461835861206055, "learning_rate": 6.121230832561491e-06, "loss": 4.8534, "step": 4850 }, { "epoch": 0.4538507849766128, "grad_norm": 4.653171539306641, "learning_rate": 6.069774621796851e-06, "loss": 4.8505, "step": 4900 }, { "epoch": 0.45848191543555783, "grad_norm": 4.088388442993164, "learning_rate": 6.018318411032212e-06, "loss": 4.8543, "step": 4950 }, { "epoch": 0.46311304589450286, "grad_norm": 2.659907817840576, "learning_rate": 5.966862200267572e-06, "loss": 4.8551, "step": 5000 }, { "epoch": 0.4677441763534479, "grad_norm": 2.58552885055542, "learning_rate": 5.915405989502934e-06, "loss": 4.8521, "step": 5050 }, { "epoch": 0.4723753068123929, "grad_norm": 2.699875593185425, "learning_rate": 5.863949778738294e-06, "loss": 4.8543, "step": 5100 }, { "epoch": 0.47700643727133796, "grad_norm": 2.67714786529541, "learning_rate": 5.812493567973655e-06, "loss": 4.8525, "step": 5150 }, { "epoch": 0.481637567730283, "grad_norm": 4.694529056549072, "learning_rate": 5.761037357209016e-06, "loss": 4.8547, "step": 5200 }, { "epoch": 0.48626869818922797, "grad_norm": 2.6322555541992188, "learning_rate": 5.709581146444376e-06, "loss": 4.8512, "step": 5250 }, { "epoch": 0.490899828648173, "grad_norm": 3.097139835357666, "learning_rate": 5.658124935679738e-06, "loss": 4.853, "step": 5300 }, { "epoch": 0.49553095910711803, "grad_norm": 4.2281575202941895, "learning_rate": 5.606668724915098e-06, "loss": 4.8516, "step": 5350 }, { "epoch": 0.5001620895660631, "grad_norm": 4.780153274536133, "learning_rate": 5.5552125141504585e-06, "loss": 4.853, "step": 5400 }, { "epoch": 0.5047932200250081, "grad_norm": 4.7001051902771, "learning_rate": 5.5037563033858186e-06, "loss": 4.8519, "step": 5450 }, { "epoch": 0.5094243504839532, "grad_norm": 2.692204475402832, "learning_rate": 5.45230009262118e-06, "loss": 4.8527, "step": 5500 }, { "epoch": 0.5140554809428982, "grad_norm": 4.267179489135742, "learning_rate": 5.40084388185654e-06, "loss": 4.8527, "step": 5550 }, { "epoch": 0.5186866114018432, "grad_norm": 4.3875532150268555, "learning_rate": 5.349387671091901e-06, "loss": 4.8531, "step": 5600 }, { "epoch": 0.5233177418607882, "grad_norm": 4.2535223960876465, "learning_rate": 5.297931460327262e-06, "loss": 4.8529, "step": 5650 }, { "epoch": 0.5279488723197332, "grad_norm": 4.176506042480469, "learning_rate": 5.246475249562622e-06, "loss": 4.8527, "step": 5700 }, { "epoch": 0.5325800027786782, "grad_norm": 5.777888298034668, "learning_rate": 5.195019038797984e-06, "loss": 4.851, "step": 5750 }, { "epoch": 0.5372111332376233, "grad_norm": 2.5011487007141113, "learning_rate": 5.143562828033344e-06, "loss": 4.8525, "step": 5800 }, { "epoch": 0.5418422636965683, "grad_norm": 2.296004056930542, "learning_rate": 5.092106617268705e-06, "loss": 4.8537, "step": 5850 }, { "epoch": 0.5464733941555133, "grad_norm": 3.866945266723633, "learning_rate": 5.040650406504065e-06, "loss": 4.8507, "step": 5900 }, { "epoch": 0.5511045246144584, "grad_norm": 4.017833232879639, "learning_rate": 4.9891941957394266e-06, "loss": 4.8535, "step": 5950 }, { "epoch": 0.5557356550734034, "grad_norm": 2.5634918212890625, "learning_rate": 4.937737984974787e-06, "loss": 4.8522, "step": 6000 }, { "epoch": 0.5603667855323484, "grad_norm": 2.3562004566192627, "learning_rate": 4.8862817742101475e-06, "loss": 4.8537, "step": 6050 }, { "epoch": 0.5649979159912935, "grad_norm": 2.573345899581909, "learning_rate": 4.834825563445508e-06, "loss": 4.8525, "step": 6100 }, { "epoch": 0.5696290464502385, "grad_norm": 2.818164825439453, "learning_rate": 4.783369352680869e-06, "loss": 4.8537, "step": 6150 }, { "epoch": 0.5742601769091835, "grad_norm": 2.9981884956359863, "learning_rate": 4.731913141916229e-06, "loss": 4.8532, "step": 6200 }, { "epoch": 0.5788913073681285, "grad_norm": 3.1095032691955566, "learning_rate": 4.68045693115159e-06, "loss": 4.8512, "step": 6250 }, { "epoch": 0.5835224378270736, "grad_norm": 2.8659579753875732, "learning_rate": 4.629000720386951e-06, "loss": 4.8531, "step": 6300 }, { "epoch": 0.5881535682860186, "grad_norm": 4.299989700317383, "learning_rate": 4.577544509622312e-06, "loss": 4.8522, "step": 6350 }, { "epoch": 0.5927846987449636, "grad_norm": 1.9564199447631836, "learning_rate": 4.526088298857673e-06, "loss": 4.853, "step": 6400 }, { "epoch": 0.5974158292039087, "grad_norm": 2.792586326599121, "learning_rate": 4.474632088093034e-06, "loss": 4.8524, "step": 6450 }, { "epoch": 0.6020469596628537, "grad_norm": 2.5155632495880127, "learning_rate": 4.423175877328394e-06, "loss": 4.8535, "step": 6500 }, { "epoch": 0.6066780901217987, "grad_norm": 3.115560293197632, "learning_rate": 4.371719666563755e-06, "loss": 4.8523, "step": 6550 }, { "epoch": 0.6113092205807438, "grad_norm": 2.115840196609497, "learning_rate": 4.3202634557991155e-06, "loss": 4.8536, "step": 6600 }, { "epoch": 0.6159403510396888, "grad_norm": 1.9011411666870117, "learning_rate": 4.2688072450344755e-06, "loss": 4.8516, "step": 6650 }, { "epoch": 0.6205714814986338, "grad_norm": 4.708501815795898, "learning_rate": 4.217351034269836e-06, "loss": 4.8526, "step": 6700 }, { "epoch": 0.6252026119575789, "grad_norm": 1.7983591556549072, "learning_rate": 4.165894823505197e-06, "loss": 4.8545, "step": 6750 }, { "epoch": 0.6298337424165239, "grad_norm": 2.4441957473754883, "learning_rate": 4.114438612740558e-06, "loss": 4.8515, "step": 6800 }, { "epoch": 0.6344648728754689, "grad_norm": 4.444235324859619, "learning_rate": 4.062982401975919e-06, "loss": 4.8521, "step": 6850 }, { "epoch": 0.639096003334414, "grad_norm": 2.260263442993164, "learning_rate": 4.01152619121128e-06, "loss": 4.8527, "step": 6900 }, { "epoch": 0.643727133793359, "grad_norm": 3.5399653911590576, "learning_rate": 3.96006998044664e-06, "loss": 4.8527, "step": 6950 }, { "epoch": 0.648358264252304, "grad_norm": 3.3484957218170166, "learning_rate": 3.908613769682001e-06, "loss": 4.8526, "step": 7000 }, { "epoch": 0.6529893947112491, "grad_norm": 2.836869955062866, "learning_rate": 3.857157558917362e-06, "loss": 4.8517, "step": 7050 }, { "epoch": 0.6576205251701941, "grad_norm": 5.348451137542725, "learning_rate": 3.8057013481527222e-06, "loss": 4.8531, "step": 7100 }, { "epoch": 0.6622516556291391, "grad_norm": 1.7368900775909424, "learning_rate": 3.7542451373880827e-06, "loss": 4.851, "step": 7150 }, { "epoch": 0.6668827860880842, "grad_norm": 2.110898733139038, "learning_rate": 3.702788926623444e-06, "loss": 4.8519, "step": 7200 }, { "epoch": 0.6715139165470291, "grad_norm": 3.1552112102508545, "learning_rate": 3.651332715858805e-06, "loss": 4.852, "step": 7250 }, { "epoch": 0.6761450470059741, "grad_norm": 2.895655632019043, "learning_rate": 3.5998765050941653e-06, "loss": 4.8525, "step": 7300 }, { "epoch": 0.6807761774649191, "grad_norm": 2.147881269454956, "learning_rate": 3.548420294329526e-06, "loss": 4.8536, "step": 7350 }, { "epoch": 0.6854073079238642, "grad_norm": 3.5029313564300537, "learning_rate": 3.4969640835648867e-06, "loss": 4.8519, "step": 7400 }, { "epoch": 0.6900384383828092, "grad_norm": 7.018946170806885, "learning_rate": 3.445507872800247e-06, "loss": 4.8529, "step": 7450 }, { "epoch": 0.6946695688417542, "grad_norm": 2.3654017448425293, "learning_rate": 3.394051662035608e-06, "loss": 4.8515, "step": 7500 }, { "epoch": 0.6993006993006993, "grad_norm": 4.802801609039307, "learning_rate": 3.3425954512709685e-06, "loss": 4.852, "step": 7550 }, { "epoch": 0.7039318297596443, "grad_norm": 3.281493663787842, "learning_rate": 3.2911392405063294e-06, "loss": 4.8526, "step": 7600 }, { "epoch": 0.7085629602185893, "grad_norm": 5.945383548736572, "learning_rate": 3.2396830297416903e-06, "loss": 4.8526, "step": 7650 }, { "epoch": 0.7131940906775344, "grad_norm": 3.7236597537994385, "learning_rate": 3.188226818977051e-06, "loss": 4.8527, "step": 7700 }, { "epoch": 0.7178252211364794, "grad_norm": 3.1034650802612305, "learning_rate": 3.1367706082124116e-06, "loss": 4.8519, "step": 7750 }, { "epoch": 0.7224563515954244, "grad_norm": 1.2914083003997803, "learning_rate": 3.0853143974477725e-06, "loss": 4.8521, "step": 7800 }, { "epoch": 0.7270874820543695, "grad_norm": 3.742281436920166, "learning_rate": 3.033858186683133e-06, "loss": 4.8526, "step": 7850 }, { "epoch": 0.7317186125133145, "grad_norm": 1.8345437049865723, "learning_rate": 2.9824019759184934e-06, "loss": 4.8526, "step": 7900 }, { "epoch": 0.7363497429722595, "grad_norm": 2.8292195796966553, "learning_rate": 2.9309457651538543e-06, "loss": 4.8528, "step": 7950 }, { "epoch": 0.7409808734312046, "grad_norm": 8.58931827545166, "learning_rate": 2.8794895543892147e-06, "loss": 4.853, "step": 8000 }, { "epoch": 0.7456120038901496, "grad_norm": 3.2066941261291504, "learning_rate": 2.8280333436245756e-06, "loss": 4.8526, "step": 8050 }, { "epoch": 0.7502431343490946, "grad_norm": 5.162906646728516, "learning_rate": 2.7765771328599365e-06, "loss": 4.8529, "step": 8100 }, { "epoch": 0.7548742648080397, "grad_norm": 2.4766018390655518, "learning_rate": 2.7251209220952974e-06, "loss": 4.8519, "step": 8150 }, { "epoch": 0.7595053952669847, "grad_norm": 2.510815382003784, "learning_rate": 2.673664711330658e-06, "loss": 4.8519, "step": 8200 }, { "epoch": 0.7641365257259297, "grad_norm": 2.531654119491577, "learning_rate": 2.6222085005660187e-06, "loss": 4.8531, "step": 8250 }, { "epoch": 0.7687676561848747, "grad_norm": 2.691474437713623, "learning_rate": 2.570752289801379e-06, "loss": 4.8529, "step": 8300 }, { "epoch": 0.7733987866438198, "grad_norm": 2.490870475769043, "learning_rate": 2.51929607903674e-06, "loss": 4.8523, "step": 8350 }, { "epoch": 0.7780299171027648, "grad_norm": 3.6683449745178223, "learning_rate": 2.4678398682721005e-06, "loss": 4.8517, "step": 8400 }, { "epoch": 0.7826610475617098, "grad_norm": 1.9419876337051392, "learning_rate": 2.4163836575074614e-06, "loss": 4.8524, "step": 8450 }, { "epoch": 0.7872921780206549, "grad_norm": 3.776477575302124, "learning_rate": 2.364927446742822e-06, "loss": 4.8527, "step": 8500 }, { "epoch": 0.7919233084795999, "grad_norm": 5.972130298614502, "learning_rate": 2.3134712359781828e-06, "loss": 4.8522, "step": 8550 }, { "epoch": 0.7965544389385449, "grad_norm": 2.1102585792541504, "learning_rate": 2.2620150252135432e-06, "loss": 4.8527, "step": 8600 }, { "epoch": 0.80118556939749, "grad_norm": 3.494260549545288, "learning_rate": 2.210558814448904e-06, "loss": 4.8526, "step": 8650 }, { "epoch": 0.805816699856435, "grad_norm": 1.6491005420684814, "learning_rate": 2.159102603684265e-06, "loss": 4.853, "step": 8700 }, { "epoch": 0.81044783031538, "grad_norm": 3.104100227355957, "learning_rate": 2.1076463929196255e-06, "loss": 4.8522, "step": 8750 }, { "epoch": 0.8150789607743251, "grad_norm": 3.840959072113037, "learning_rate": 2.0561901821549863e-06, "loss": 4.8515, "step": 8800 }, { "epoch": 0.81971009123327, "grad_norm": 2.8900058269500732, "learning_rate": 2.004733971390347e-06, "loss": 4.8527, "step": 8850 }, { "epoch": 0.824341221692215, "grad_norm": 4.004197120666504, "learning_rate": 1.9532777606257077e-06, "loss": 4.8525, "step": 8900 }, { "epoch": 0.82897235215116, "grad_norm": 3.287238359451294, "learning_rate": 1.9018215498610684e-06, "loss": 4.8537, "step": 8950 }, { "epoch": 0.8336034826101051, "grad_norm": 1.3281551599502563, "learning_rate": 1.850365339096429e-06, "loss": 4.8526, "step": 9000 }, { "epoch": 0.8382346130690501, "grad_norm": 1.9539192914962769, "learning_rate": 1.7989091283317897e-06, "loss": 4.8516, "step": 9050 }, { "epoch": 0.8428657435279951, "grad_norm": 1.8044812679290771, "learning_rate": 1.7474529175671506e-06, "loss": 4.852, "step": 9100 }, { "epoch": 0.8474968739869402, "grad_norm": 2.2323732376098633, "learning_rate": 1.6959967068025113e-06, "loss": 4.8525, "step": 9150 }, { "epoch": 0.8521280044458852, "grad_norm": 6.444853782653809, "learning_rate": 1.644540496037872e-06, "loss": 4.8525, "step": 9200 }, { "epoch": 0.8567591349048302, "grad_norm": 2.432457447052002, "learning_rate": 1.5930842852732326e-06, "loss": 4.8532, "step": 9250 }, { "epoch": 0.8613902653637753, "grad_norm": 9.460570335388184, "learning_rate": 1.5416280745085933e-06, "loss": 4.8529, "step": 9300 }, { "epoch": 0.8660213958227203, "grad_norm": 1.7130793333053589, "learning_rate": 1.4901718637439542e-06, "loss": 4.8519, "step": 9350 }, { "epoch": 0.8706525262816653, "grad_norm": 1.7794573307037354, "learning_rate": 1.4387156529793148e-06, "loss": 4.8528, "step": 9400 }, { "epoch": 0.8752836567406104, "grad_norm": 2.324021816253662, "learning_rate": 1.3872594422146753e-06, "loss": 4.8515, "step": 9450 }, { "epoch": 0.8799147871995554, "grad_norm": 2.8876137733459473, "learning_rate": 1.335803231450036e-06, "loss": 4.8529, "step": 9500 }, { "epoch": 0.8845459176585004, "grad_norm": 1.5305650234222412, "learning_rate": 1.284347020685397e-06, "loss": 4.8528, "step": 9550 }, { "epoch": 0.8891770481174455, "grad_norm": 1.89708411693573, "learning_rate": 1.2328908099207575e-06, "loss": 4.8523, "step": 9600 }, { "epoch": 0.8938081785763905, "grad_norm": 1.8456463813781738, "learning_rate": 1.1814345991561182e-06, "loss": 4.8523, "step": 9650 }, { "epoch": 0.8984393090353355, "grad_norm": 3.4749717712402344, "learning_rate": 1.1299783883914789e-06, "loss": 4.8524, "step": 9700 }, { "epoch": 0.9030704394942806, "grad_norm": 2.6961116790771484, "learning_rate": 1.0785221776268398e-06, "loss": 4.8521, "step": 9750 }, { "epoch": 0.9077015699532256, "grad_norm": 4.795749187469482, "learning_rate": 1.0270659668622002e-06, "loss": 4.8518, "step": 9800 }, { "epoch": 0.9123327004121706, "grad_norm": 5.0294904708862305, "learning_rate": 9.75609756097561e-07, "loss": 4.8519, "step": 9850 }, { "epoch": 0.9169638308711157, "grad_norm": 2.320612668991089, "learning_rate": 9.241535453329218e-07, "loss": 4.8519, "step": 9900 }, { "epoch": 0.9215949613300607, "grad_norm": 1.5690840482711792, "learning_rate": 8.726973345682825e-07, "loss": 4.8525, "step": 9950 }, { "epoch": 0.9262260917890057, "grad_norm": 3.0287981033325195, "learning_rate": 8.212411238036431e-07, "loss": 4.8527, "step": 10000 }, { "epoch": 0.9308572222479508, "grad_norm": 4.888521194458008, "learning_rate": 7.697849130390039e-07, "loss": 4.8526, "step": 10050 }, { "epoch": 0.9354883527068958, "grad_norm": 8.247330665588379, "learning_rate": 7.183287022743646e-07, "loss": 4.8525, "step": 10100 }, { "epoch": 0.9401194831658408, "grad_norm": 4.7511982917785645, "learning_rate": 6.668724915097252e-07, "loss": 4.8515, "step": 10150 }, { "epoch": 0.9447506136247859, "grad_norm": 3.2248997688293457, "learning_rate": 6.15416280745086e-07, "loss": 4.8532, "step": 10200 }, { "epoch": 0.9493817440837309, "grad_norm": 3.083930730819702, "learning_rate": 5.639600699804467e-07, "loss": 4.8528, "step": 10250 }, { "epoch": 0.9540128745426759, "grad_norm": 6.262050151824951, "learning_rate": 5.125038592158075e-07, "loss": 4.8514, "step": 10300 }, { "epoch": 0.958644005001621, "grad_norm": 1.9046210050582886, "learning_rate": 4.610476484511681e-07, "loss": 4.8525, "step": 10350 }, { "epoch": 0.963275135460566, "grad_norm": 4.532755374908447, "learning_rate": 4.0959143768652876e-07, "loss": 4.8519, "step": 10400 }, { "epoch": 0.9679062659195109, "grad_norm": 1.4820815324783325, "learning_rate": 3.581352269218895e-07, "loss": 4.8527, "step": 10450 }, { "epoch": 0.9725373963784559, "grad_norm": 1.89457106590271, "learning_rate": 3.066790161572502e-07, "loss": 4.8516, "step": 10500 }, { "epoch": 0.977168526837401, "grad_norm": 1.8384500741958618, "learning_rate": 2.5522280539261093e-07, "loss": 4.8523, "step": 10550 }, { "epoch": 0.981799657296346, "grad_norm": 2.7351698875427246, "learning_rate": 2.0376659462797163e-07, "loss": 4.8524, "step": 10600 }, { "epoch": 0.986430787755291, "grad_norm": 3.5502257347106934, "learning_rate": 1.523103838633323e-07, "loss": 4.8523, "step": 10650 }, { "epoch": 0.9910619182142361, "grad_norm": 2.255584478378296, "learning_rate": 1.0085417309869303e-07, "loss": 4.8518, "step": 10700 }, { "epoch": 0.9956930486731811, "grad_norm": 1.546319842338562, "learning_rate": 4.9397962334053725e-08, "loss": 4.8524, "step": 10750 } ], "logging_steps": 50, "max_steps": 10797, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }