{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.9976558837318334, "eval_steps": 500, "global_step": 2665, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009376465072667605, "grad_norm": 0.23995593190193176, "learning_rate": 4.999956573574533e-05, "loss": 0.8631, "step": 5 }, { "epoch": 0.01875293014533521, "grad_norm": 0.2710498571395874, "learning_rate": 4.999826295806815e-05, "loss": 0.8372, "step": 10 }, { "epoch": 0.02812939521800281, "grad_norm": 0.20431986451148987, "learning_rate": 4.999609171222846e-05, "loss": 0.769, "step": 15 }, { "epoch": 0.03750586029067042, "grad_norm": 0.2436569333076477, "learning_rate": 4.99930520736578e-05, "loss": 0.7971, "step": 20 }, { "epoch": 0.04688232536333802, "grad_norm": 0.25712528824806213, "learning_rate": 4.998914414795668e-05, "loss": 0.7329, "step": 25 }, { "epoch": 0.05625879043600562, "grad_norm": 0.24791960418224335, "learning_rate": 4.99843680708909e-05, "loss": 0.7026, "step": 30 }, { "epoch": 0.06563525550867323, "grad_norm": 0.27433285117149353, "learning_rate": 4.997872400838682e-05, "loss": 0.7233, "step": 35 }, { "epoch": 0.07501172058134084, "grad_norm": 0.2803635597229004, "learning_rate": 4.997221215652562e-05, "loss": 0.7185, "step": 40 }, { "epoch": 0.08438818565400844, "grad_norm": 0.24648822844028473, "learning_rate": 4.9964832741536444e-05, "loss": 0.738, "step": 45 }, { "epoch": 0.09376465072667604, "grad_norm": 0.3567708730697632, "learning_rate": 4.9956586019788584e-05, "loss": 0.6857, "step": 50 }, { "epoch": 0.10314111579934365, "grad_norm": 0.22938202321529388, "learning_rate": 4.9947472277782584e-05, "loss": 0.6763, "step": 55 }, { "epoch": 0.11251758087201125, "grad_norm": 0.314599871635437, "learning_rate": 4.993749183214021e-05, "loss": 0.6673, "step": 60 }, { "epoch": 0.12189404594467886, "grad_norm": 0.22777864336967468, "learning_rate": 4.992664502959351e-05, "loss": 0.6489, "step": 65 }, { "epoch": 0.13127051101734646, "grad_norm": 0.2409321665763855, "learning_rate": 4.991493224697281e-05, "loss": 0.6335, "step": 70 }, { "epoch": 0.14064697609001406, "grad_norm": 0.25169098377227783, "learning_rate": 4.990235389119352e-05, "loss": 0.6739, "step": 75 }, { "epoch": 0.15002344116268168, "grad_norm": 0.25553980469703674, "learning_rate": 4.9888910399242065e-05, "loss": 0.6087, "step": 80 }, { "epoch": 0.15939990623534928, "grad_norm": 0.2406449317932129, "learning_rate": 4.987460223816067e-05, "loss": 0.6207, "step": 85 }, { "epoch": 0.16877637130801687, "grad_norm": 0.300151526927948, "learning_rate": 4.985942990503119e-05, "loss": 0.6429, "step": 90 }, { "epoch": 0.1781528363806845, "grad_norm": 0.2550767660140991, "learning_rate": 4.984339392695777e-05, "loss": 0.6033, "step": 95 }, { "epoch": 0.1875293014533521, "grad_norm": 0.27587273716926575, "learning_rate": 4.9826494861048576e-05, "loss": 0.5861, "step": 100 }, { "epoch": 0.19690576652601968, "grad_norm": 0.23900988698005676, "learning_rate": 4.980873329439644e-05, "loss": 0.6604, "step": 105 }, { "epoch": 0.2062822315986873, "grad_norm": 0.25917357206344604, "learning_rate": 4.979010984405842e-05, "loss": 0.614, "step": 110 }, { "epoch": 0.2156586966713549, "grad_norm": 0.27334660291671753, "learning_rate": 4.9770625157034436e-05, "loss": 0.6376, "step": 115 }, { "epoch": 0.2250351617440225, "grad_norm": 0.28814154863357544, "learning_rate": 4.975027991024473e-05, "loss": 0.6502, "step": 120 }, { "epoch": 0.23441162681669012, "grad_norm": 0.28324735164642334, "learning_rate": 4.972907481050637e-05, "loss": 0.6162, "step": 125 }, { "epoch": 0.2437880918893577, "grad_norm": 0.326524555683136, "learning_rate": 4.970701059450872e-05, "loss": 0.6333, "step": 130 }, { "epoch": 0.25316455696202533, "grad_norm": 0.2594030797481537, "learning_rate": 4.968408802878778e-05, "loss": 0.6405, "step": 135 }, { "epoch": 0.26254102203469293, "grad_norm": 0.2970665395259857, "learning_rate": 4.9660307909699645e-05, "loss": 0.5961, "step": 140 }, { "epoch": 0.2719174871073605, "grad_norm": 0.274636447429657, "learning_rate": 4.963567106339276e-05, "loss": 0.5913, "step": 145 }, { "epoch": 0.2812939521800281, "grad_norm": 0.30863094329833984, "learning_rate": 4.961017834577927e-05, "loss": 0.6354, "step": 150 }, { "epoch": 0.2906704172526957, "grad_norm": 0.30860957503318787, "learning_rate": 4.958383064250525e-05, "loss": 0.5861, "step": 155 }, { "epoch": 0.30004688232536336, "grad_norm": 0.31627291440963745, "learning_rate": 4.955662886891995e-05, "loss": 0.6287, "step": 160 }, { "epoch": 0.30942334739803096, "grad_norm": 0.2863800525665283, "learning_rate": 4.952857397004401e-05, "loss": 0.648, "step": 165 }, { "epoch": 0.31879981247069855, "grad_norm": 0.30252712965011597, "learning_rate": 4.949966692053663e-05, "loss": 0.6162, "step": 170 }, { "epoch": 0.32817627754336615, "grad_norm": 0.24963121116161346, "learning_rate": 4.946990872466164e-05, "loss": 0.6344, "step": 175 }, { "epoch": 0.33755274261603374, "grad_norm": 0.3113265335559845, "learning_rate": 4.943930041625272e-05, "loss": 0.6029, "step": 180 }, { "epoch": 0.34692920768870134, "grad_norm": 0.28185218572616577, "learning_rate": 4.940784305867741e-05, "loss": 0.5946, "step": 185 }, { "epoch": 0.356305672761369, "grad_norm": 0.3129664659500122, "learning_rate": 4.937553774480018e-05, "loss": 0.5829, "step": 190 }, { "epoch": 0.3656821378340366, "grad_norm": 0.3760225474834442, "learning_rate": 4.934238559694448e-05, "loss": 0.659, "step": 195 }, { "epoch": 0.3750586029067042, "grad_norm": 0.34029099345207214, "learning_rate": 4.9308387766853725e-05, "loss": 0.6483, "step": 200 }, { "epoch": 0.38443506797937177, "grad_norm": 0.3152872920036316, "learning_rate": 4.92735454356513e-05, "loss": 0.611, "step": 205 }, { "epoch": 0.39381153305203936, "grad_norm": 0.32286536693573, "learning_rate": 4.9237859813799535e-05, "loss": 0.6201, "step": 210 }, { "epoch": 0.40318799812470696, "grad_norm": 0.3486417531967163, "learning_rate": 4.9201332141057623e-05, "loss": 0.5775, "step": 215 }, { "epoch": 0.4125644631973746, "grad_norm": 0.33769914507865906, "learning_rate": 4.9163963686438575e-05, "loss": 0.6115, "step": 220 }, { "epoch": 0.4219409282700422, "grad_norm": 0.31967395544052124, "learning_rate": 4.912575574816511e-05, "loss": 0.5879, "step": 225 }, { "epoch": 0.4313173933427098, "grad_norm": 0.40602371096611023, "learning_rate": 4.908670965362457e-05, "loss": 0.5617, "step": 230 }, { "epoch": 0.4406938584153774, "grad_norm": 0.31485116481781006, "learning_rate": 4.9046826759322825e-05, "loss": 0.6132, "step": 235 }, { "epoch": 0.450070323488045, "grad_norm": 0.3902187645435333, "learning_rate": 4.9006108450837095e-05, "loss": 0.5923, "step": 240 }, { "epoch": 0.45944678856071264, "grad_norm": 0.3169301152229309, "learning_rate": 4.8964556142767845e-05, "loss": 0.6131, "step": 245 }, { "epoch": 0.46882325363338023, "grad_norm": 0.31579890847206116, "learning_rate": 4.892217127868965e-05, "loss": 0.6137, "step": 250 }, { "epoch": 0.4781997187060478, "grad_norm": 0.3303227126598358, "learning_rate": 4.8878955331101026e-05, "loss": 0.6239, "step": 255 }, { "epoch": 0.4875761837787154, "grad_norm": 0.33773812651634216, "learning_rate": 4.8834909801373264e-05, "loss": 0.5665, "step": 260 }, { "epoch": 0.496952648851383, "grad_norm": 0.3913642466068268, "learning_rate": 4.879003621969831e-05, "loss": 0.5801, "step": 265 }, { "epoch": 0.5063291139240507, "grad_norm": 0.33499622344970703, "learning_rate": 4.874433614503554e-05, "loss": 0.5682, "step": 270 }, { "epoch": 0.5157055789967182, "grad_norm": 0.3137553930282593, "learning_rate": 4.869781116505768e-05, "loss": 0.5698, "step": 275 }, { "epoch": 0.5250820440693859, "grad_norm": 0.3507164716720581, "learning_rate": 4.8650462896095597e-05, "loss": 0.5948, "step": 280 }, { "epoch": 0.5344585091420534, "grad_norm": 0.33271023631095886, "learning_rate": 4.860229298308213e-05, "loss": 0.566, "step": 285 }, { "epoch": 0.543834974214721, "grad_norm": 0.4269760251045227, "learning_rate": 4.8553303099495e-05, "loss": 0.5867, "step": 290 }, { "epoch": 0.5532114392873887, "grad_norm": 0.37852942943573, "learning_rate": 4.8503494947298634e-05, "loss": 0.6045, "step": 295 }, { "epoch": 0.5625879043600562, "grad_norm": 0.354078084230423, "learning_rate": 4.845287025688503e-05, "loss": 0.5963, "step": 300 }, { "epoch": 0.5719643694327239, "grad_norm": 0.36660170555114746, "learning_rate": 4.8401430787013666e-05, "loss": 0.6019, "step": 305 }, { "epoch": 0.5813408345053914, "grad_norm": 0.3099578320980072, "learning_rate": 4.8349178324750387e-05, "loss": 0.5811, "step": 310 }, { "epoch": 0.5907172995780591, "grad_norm": 0.3528560996055603, "learning_rate": 4.8296114685405324e-05, "loss": 0.5702, "step": 315 }, { "epoch": 0.6000937646507267, "grad_norm": 0.3307196795940399, "learning_rate": 4.824224171246981e-05, "loss": 0.6386, "step": 320 }, { "epoch": 0.6094702297233943, "grad_norm": 0.3812682628631592, "learning_rate": 4.8187561277552374e-05, "loss": 0.5937, "step": 325 }, { "epoch": 0.6188466947960619, "grad_norm": 0.35563403367996216, "learning_rate": 4.813207528031366e-05, "loss": 0.5537, "step": 330 }, { "epoch": 0.6282231598687295, "grad_norm": 0.3535631597042084, "learning_rate": 4.807578564840051e-05, "loss": 0.6272, "step": 335 }, { "epoch": 0.6375996249413971, "grad_norm": 0.3569740951061249, "learning_rate": 4.801869433737891e-05, "loss": 0.5732, "step": 340 }, { "epoch": 0.6469760900140648, "grad_norm": 0.37414535880088806, "learning_rate": 4.796080333066613e-05, "loss": 0.6062, "step": 345 }, { "epoch": 0.6563525550867323, "grad_norm": 0.38426753878593445, "learning_rate": 4.790211463946174e-05, "loss": 0.6212, "step": 350 }, { "epoch": 0.6657290201593999, "grad_norm": 0.46834492683410645, "learning_rate": 4.784263030267781e-05, "loss": 0.5662, "step": 355 }, { "epoch": 0.6751054852320675, "grad_norm": 0.3643794655799866, "learning_rate": 4.7782352386868035e-05, "loss": 0.6173, "step": 360 }, { "epoch": 0.6844819503047351, "grad_norm": 0.36537444591522217, "learning_rate": 4.7721282986155945e-05, "loss": 0.5543, "step": 365 }, { "epoch": 0.6938584153774027, "grad_norm": 0.40244394540786743, "learning_rate": 4.7659424222162165e-05, "loss": 0.5608, "step": 370 }, { "epoch": 0.7032348804500703, "grad_norm": 0.376693457365036, "learning_rate": 4.7596778243930694e-05, "loss": 0.6113, "step": 375 }, { "epoch": 0.712611345522738, "grad_norm": 0.3722762167453766, "learning_rate": 4.7533347227854265e-05, "loss": 0.604, "step": 380 }, { "epoch": 0.7219878105954055, "grad_norm": 0.40300458669662476, "learning_rate": 4.7469133377598695e-05, "loss": 0.5725, "step": 385 }, { "epoch": 0.7313642756680732, "grad_norm": 0.37405309081077576, "learning_rate": 4.740413892402639e-05, "loss": 0.5792, "step": 390 }, { "epoch": 0.7407407407407407, "grad_norm": 0.39936429262161255, "learning_rate": 4.7338366125118775e-05, "loss": 0.601, "step": 395 }, { "epoch": 0.7501172058134083, "grad_norm": 0.398360013961792, "learning_rate": 4.727181726589789e-05, "loss": 0.6168, "step": 400 }, { "epoch": 0.759493670886076, "grad_norm": 0.3800843060016632, "learning_rate": 4.7204494658346996e-05, "loss": 0.5719, "step": 405 }, { "epoch": 0.7688701359587435, "grad_norm": 0.3811691105365753, "learning_rate": 4.713640064133025e-05, "loss": 0.5798, "step": 410 }, { "epoch": 0.7782466010314112, "grad_norm": 0.3757120966911316, "learning_rate": 4.706753758051145e-05, "loss": 0.5852, "step": 415 }, { "epoch": 0.7876230661040787, "grad_norm": 0.4053094983100891, "learning_rate": 4.699790786827188e-05, "loss": 0.6183, "step": 420 }, { "epoch": 0.7969995311767464, "grad_norm": 0.4359457492828369, "learning_rate": 4.6927513923627124e-05, "loss": 0.59, "step": 425 }, { "epoch": 0.8063759962494139, "grad_norm": 0.42008543014526367, "learning_rate": 4.68563581921431e-05, "loss": 0.5661, "step": 430 }, { "epoch": 0.8157524613220816, "grad_norm": 0.43090564012527466, "learning_rate": 4.6784443145851074e-05, "loss": 0.5222, "step": 435 }, { "epoch": 0.8251289263947492, "grad_norm": 0.41035380959510803, "learning_rate": 4.671177128316176e-05, "loss": 0.5407, "step": 440 }, { "epoch": 0.8345053914674168, "grad_norm": 0.38988974690437317, "learning_rate": 4.663834512877853e-05, "loss": 0.5922, "step": 445 }, { "epoch": 0.8438818565400844, "grad_norm": 0.3898136019706726, "learning_rate": 4.6564167233609736e-05, "loss": 0.5714, "step": 450 }, { "epoch": 0.853258321612752, "grad_norm": 0.3754185736179352, "learning_rate": 4.648924017468003e-05, "loss": 0.5588, "step": 455 }, { "epoch": 0.8626347866854196, "grad_norm": 0.42259371280670166, "learning_rate": 4.6413566555040896e-05, "loss": 0.5935, "step": 460 }, { "epoch": 0.8720112517580872, "grad_norm": 0.3977474272251129, "learning_rate": 4.633714900368018e-05, "loss": 0.5626, "step": 465 }, { "epoch": 0.8813877168307548, "grad_norm": 0.3957667052745819, "learning_rate": 4.625999017543075e-05, "loss": 0.5625, "step": 470 }, { "epoch": 0.8907641819034224, "grad_norm": 0.4148056209087372, "learning_rate": 4.618209275087829e-05, "loss": 0.586, "step": 475 }, { "epoch": 0.90014064697609, "grad_norm": 0.4572969079017639, "learning_rate": 4.610345943626817e-05, "loss": 0.5806, "step": 480 }, { "epoch": 0.9095171120487576, "grad_norm": 0.37934327125549316, "learning_rate": 4.602409296341141e-05, "loss": 0.5682, "step": 485 }, { "epoch": 0.9188935771214253, "grad_norm": 0.4195612370967865, "learning_rate": 4.5943996089589775e-05, "loss": 0.5594, "step": 490 }, { "epoch": 0.9282700421940928, "grad_norm": 0.42826300859451294, "learning_rate": 4.586317159746001e-05, "loss": 0.6643, "step": 495 }, { "epoch": 0.9376465072667605, "grad_norm": 0.4025145471096039, "learning_rate": 4.5781622294957136e-05, "loss": 0.5672, "step": 500 }, { "epoch": 0.947022972339428, "grad_norm": 0.37648695707321167, "learning_rate": 4.569935101519692e-05, "loss": 0.5906, "step": 505 }, { "epoch": 0.9563994374120957, "grad_norm": 0.39290428161621094, "learning_rate": 4.561636061637745e-05, "loss": 0.6222, "step": 510 }, { "epoch": 0.9657759024847632, "grad_norm": 0.36130473017692566, "learning_rate": 4.553265398167981e-05, "loss": 0.5787, "step": 515 }, { "epoch": 0.9751523675574308, "grad_norm": 0.409842312335968, "learning_rate": 4.5448234019167945e-05, "loss": 0.5627, "step": 520 }, { "epoch": 0.9845288326300985, "grad_norm": 0.40280935168266296, "learning_rate": 4.536310366168763e-05, "loss": 0.5704, "step": 525 }, { "epoch": 0.993905297702766, "grad_norm": 0.3929194509983063, "learning_rate": 4.5277265866764565e-05, "loss": 0.5879, "step": 530 }, { "epoch": 1.0032817627754336, "grad_norm": 0.5179246664047241, "learning_rate": 4.519072361650163e-05, "loss": 0.5509, "step": 535 }, { "epoch": 1.0126582278481013, "grad_norm": 0.433220773935318, "learning_rate": 4.5103479917475286e-05, "loss": 0.5293, "step": 540 }, { "epoch": 1.0220346929207689, "grad_norm": 0.47541534900665283, "learning_rate": 4.501553780063113e-05, "loss": 0.5393, "step": 545 }, { "epoch": 1.0314111579934364, "grad_norm": 0.3974189758300781, "learning_rate": 4.4926900321178595e-05, "loss": 0.5949, "step": 550 }, { "epoch": 1.0407876230661042, "grad_norm": 0.41597846150398254, "learning_rate": 4.483757055848479e-05, "loss": 0.5715, "step": 555 }, { "epoch": 1.0501640881387717, "grad_norm": 0.42423322796821594, "learning_rate": 4.4747551615967534e-05, "loss": 0.5321, "step": 560 }, { "epoch": 1.0595405532114393, "grad_norm": 0.4616020917892456, "learning_rate": 4.4656846620987557e-05, "loss": 0.591, "step": 565 }, { "epoch": 1.0689170182841068, "grad_norm": 0.39147764444351196, "learning_rate": 4.4565458724739825e-05, "loss": 0.5834, "step": 570 }, { "epoch": 1.0782934833567746, "grad_norm": 0.4559531509876251, "learning_rate": 4.447339110214405e-05, "loss": 0.5609, "step": 575 }, { "epoch": 1.087669948429442, "grad_norm": 0.4997139871120453, "learning_rate": 4.438064695173446e-05, "loss": 0.5792, "step": 580 }, { "epoch": 1.0970464135021096, "grad_norm": 0.45987358689308167, "learning_rate": 4.428722949554857e-05, "loss": 0.568, "step": 585 }, { "epoch": 1.1064228785747774, "grad_norm": 0.3987531065940857, "learning_rate": 4.419314197901537e-05, "loss": 0.5428, "step": 590 }, { "epoch": 1.115799343647445, "grad_norm": 0.40742579102516174, "learning_rate": 4.4098387670842466e-05, "loss": 0.564, "step": 595 }, { "epoch": 1.1251758087201125, "grad_norm": 0.41294044256210327, "learning_rate": 4.400296986290258e-05, "loss": 0.5625, "step": 600 }, { "epoch": 1.1345522737927802, "grad_norm": 0.46300792694091797, "learning_rate": 4.390689187011917e-05, "loss": 0.5716, "step": 605 }, { "epoch": 1.1439287388654478, "grad_norm": 0.45359134674072266, "learning_rate": 4.3810157030351276e-05, "loss": 0.5394, "step": 610 }, { "epoch": 1.1533052039381153, "grad_norm": 0.46484261751174927, "learning_rate": 4.371276870427753e-05, "loss": 0.5344, "step": 615 }, { "epoch": 1.1626816690107828, "grad_norm": 0.42876294255256653, "learning_rate": 4.3614730275279457e-05, "loss": 0.544, "step": 620 }, { "epoch": 1.1720581340834506, "grad_norm": 0.5274311900138855, "learning_rate": 4.351604514932387e-05, "loss": 0.5481, "step": 625 }, { "epoch": 1.1814345991561181, "grad_norm": 0.5408082604408264, "learning_rate": 4.341671675484459e-05, "loss": 0.5715, "step": 630 }, { "epoch": 1.1908110642287857, "grad_norm": 0.41055697202682495, "learning_rate": 4.331674854262331e-05, "loss": 0.5602, "step": 635 }, { "epoch": 1.2001875293014534, "grad_norm": 0.42665359377861023, "learning_rate": 4.321614398566972e-05, "loss": 0.5441, "step": 640 }, { "epoch": 1.209563994374121, "grad_norm": 0.4585810601711273, "learning_rate": 4.3114906579100853e-05, "loss": 0.5369, "step": 645 }, { "epoch": 1.2189404594467885, "grad_norm": 0.4821290969848633, "learning_rate": 4.301303984001967e-05, "loss": 0.577, "step": 650 }, { "epoch": 1.228316924519456, "grad_norm": 0.44844305515289307, "learning_rate": 4.291054730739286e-05, "loss": 0.5762, "step": 655 }, { "epoch": 1.2376933895921238, "grad_norm": 0.47802606225013733, "learning_rate": 4.2807432541927865e-05, "loss": 0.5726, "step": 660 }, { "epoch": 1.2470698546647914, "grad_norm": 0.5414724946022034, "learning_rate": 4.2703699125949245e-05, "loss": 0.5686, "step": 665 }, { "epoch": 1.256446319737459, "grad_norm": 0.4859514832496643, "learning_rate": 4.259935066327415e-05, "loss": 0.6473, "step": 670 }, { "epoch": 1.2658227848101267, "grad_norm": 0.4125962555408478, "learning_rate": 4.2494390779087187e-05, "loss": 0.6009, "step": 675 }, { "epoch": 1.2751992498827942, "grad_norm": 0.45781227946281433, "learning_rate": 4.238882311981441e-05, "loss": 0.5301, "step": 680 }, { "epoch": 1.2845757149554617, "grad_norm": 0.5371187925338745, "learning_rate": 4.228265135299669e-05, "loss": 0.5715, "step": 685 }, { "epoch": 1.2939521800281293, "grad_norm": 0.42323383688926697, "learning_rate": 4.2175879167162304e-05, "loss": 0.6022, "step": 690 }, { "epoch": 1.303328645100797, "grad_norm": 0.5018748641014099, "learning_rate": 4.206851027169871e-05, "loss": 0.5765, "step": 695 }, { "epoch": 1.3127051101734646, "grad_norm": 0.4469924569129944, "learning_rate": 4.196054839672382e-05, "loss": 0.5521, "step": 700 }, { "epoch": 1.3220815752461323, "grad_norm": 0.3689207136631012, "learning_rate": 4.1851997292956255e-05, "loss": 0.5709, "step": 705 }, { "epoch": 1.3314580403187999, "grad_norm": 0.46595776081085205, "learning_rate": 4.174286073158516e-05, "loss": 0.5751, "step": 710 }, { "epoch": 1.3408345053914674, "grad_norm": 0.430705189704895, "learning_rate": 4.163314250413913e-05, "loss": 0.5276, "step": 715 }, { "epoch": 1.350210970464135, "grad_norm": 0.45362386107444763, "learning_rate": 4.152284642235452e-05, "loss": 0.5654, "step": 720 }, { "epoch": 1.3595874355368025, "grad_norm": 0.4694269895553589, "learning_rate": 4.141197631804298e-05, "loss": 0.5771, "step": 725 }, { "epoch": 1.3689639006094703, "grad_norm": 0.4499427080154419, "learning_rate": 4.1300536042958354e-05, "loss": 0.5849, "step": 730 }, { "epoch": 1.3783403656821378, "grad_norm": 0.4603768587112427, "learning_rate": 4.118852946866291e-05, "loss": 0.5539, "step": 735 }, { "epoch": 1.3877168307548056, "grad_norm": 0.5671654343605042, "learning_rate": 4.107596048639274e-05, "loss": 0.5408, "step": 740 }, { "epoch": 1.397093295827473, "grad_norm": 0.4729969799518585, "learning_rate": 4.0962833006922675e-05, "loss": 0.5717, "step": 745 }, { "epoch": 1.4064697609001406, "grad_norm": 0.4194209575653076, "learning_rate": 4.0849150960430356e-05, "loss": 0.5612, "step": 750 }, { "epoch": 1.4158462259728082, "grad_norm": 0.43975749611854553, "learning_rate": 4.0734918296359716e-05, "loss": 0.5587, "step": 755 }, { "epoch": 1.4252226910454757, "grad_norm": 0.3893047273159027, "learning_rate": 4.0620138983283785e-05, "loss": 0.5965, "step": 760 }, { "epoch": 1.4345991561181435, "grad_norm": 0.4223731458187103, "learning_rate": 4.050481700876677e-05, "loss": 0.5576, "step": 765 }, { "epoch": 1.443975621190811, "grad_norm": 0.504723310470581, "learning_rate": 4.038895637922559e-05, "loss": 0.5481, "step": 770 }, { "epoch": 1.4533520862634788, "grad_norm": 0.4618123173713684, "learning_rate": 4.027256111979063e-05, "loss": 0.5343, "step": 775 }, { "epoch": 1.4627285513361463, "grad_norm": 0.4357120990753174, "learning_rate": 4.015563527416595e-05, "loss": 0.5677, "step": 780 }, { "epoch": 1.4721050164088139, "grad_norm": 0.4497866928577423, "learning_rate": 4.003818290448876e-05, "loss": 0.565, "step": 785 }, { "epoch": 1.4814814814814814, "grad_norm": 0.4233000874519348, "learning_rate": 3.992020809118832e-05, "loss": 0.6299, "step": 790 }, { "epoch": 1.4908579465541492, "grad_norm": 0.522912859916687, "learning_rate": 3.980171493284418e-05, "loss": 0.5588, "step": 795 }, { "epoch": 1.5002344116268167, "grad_norm": 0.5034630298614502, "learning_rate": 3.9682707546043785e-05, "loss": 0.6042, "step": 800 }, { "epoch": 1.5096108766994845, "grad_norm": 0.47972697019577026, "learning_rate": 3.9563190065239474e-05, "loss": 0.5613, "step": 805 }, { "epoch": 1.518987341772152, "grad_norm": 0.4823983311653137, "learning_rate": 3.9443166642604814e-05, "loss": 0.5466, "step": 810 }, { "epoch": 1.5283638068448195, "grad_norm": 0.4230092465877533, "learning_rate": 3.932264144789038e-05, "loss": 0.5305, "step": 815 }, { "epoch": 1.537740271917487, "grad_norm": 0.42191463708877563, "learning_rate": 3.920161866827889e-05, "loss": 0.5822, "step": 820 }, { "epoch": 1.5471167369901546, "grad_norm": 0.4600556194782257, "learning_rate": 3.908010250823972e-05, "loss": 0.5585, "step": 825 }, { "epoch": 1.5564932020628222, "grad_norm": 0.5136891603469849, "learning_rate": 3.895809718938283e-05, "loss": 0.5693, "step": 830 }, { "epoch": 1.56586966713549, "grad_norm": 0.4428097903728485, "learning_rate": 3.883560695031213e-05, "loss": 0.5137, "step": 835 }, { "epoch": 1.5752461322081577, "grad_norm": 0.4338129758834839, "learning_rate": 3.871263604647822e-05, "loss": 0.5622, "step": 840 }, { "epoch": 1.5846225972808252, "grad_norm": 0.4927155077457428, "learning_rate": 3.858918875003053e-05, "loss": 0.5321, "step": 845 }, { "epoch": 1.5939990623534928, "grad_norm": 0.44332149624824524, "learning_rate": 3.846526934966891e-05, "loss": 0.5623, "step": 850 }, { "epoch": 1.6033755274261603, "grad_norm": 0.5348272919654846, "learning_rate": 3.834088215049464e-05, "loss": 0.5781, "step": 855 }, { "epoch": 1.6127519924988278, "grad_norm": 0.4220760464668274, "learning_rate": 3.821603147386088e-05, "loss": 0.5724, "step": 860 }, { "epoch": 1.6221284575714956, "grad_norm": 0.47724246978759766, "learning_rate": 3.80907216572225e-05, "loss": 0.5351, "step": 865 }, { "epoch": 1.6315049226441631, "grad_norm": 0.5851244926452637, "learning_rate": 3.796495705398544e-05, "loss": 0.5726, "step": 870 }, { "epoch": 1.640881387716831, "grad_norm": 0.45955443382263184, "learning_rate": 3.783874203335542e-05, "loss": 0.5326, "step": 875 }, { "epoch": 1.6502578527894984, "grad_norm": 0.528683066368103, "learning_rate": 3.77120809801862e-05, "loss": 0.5384, "step": 880 }, { "epoch": 1.659634317862166, "grad_norm": 0.42244866490364075, "learning_rate": 3.758497829482721e-05, "loss": 0.5808, "step": 885 }, { "epoch": 1.6690107829348335, "grad_norm": 0.4697413742542267, "learning_rate": 3.7457438392970686e-05, "loss": 0.5123, "step": 890 }, { "epoch": 1.678387248007501, "grad_norm": 0.47603949904441833, "learning_rate": 3.732946570549825e-05, "loss": 0.5437, "step": 895 }, { "epoch": 1.6877637130801688, "grad_norm": 0.5042173862457275, "learning_rate": 3.720106467832701e-05, "loss": 0.6003, "step": 900 }, { "epoch": 1.6971401781528364, "grad_norm": 0.4678844213485718, "learning_rate": 3.707223977225507e-05, "loss": 0.5941, "step": 905 }, { "epoch": 1.7065166432255041, "grad_norm": 0.4053237736225128, "learning_rate": 3.694299546280657e-05, "loss": 0.6019, "step": 910 }, { "epoch": 1.7158931082981717, "grad_norm": 0.49923238158226013, "learning_rate": 3.681333624007623e-05, "loss": 0.5774, "step": 915 }, { "epoch": 1.7252695733708392, "grad_norm": 0.5050910711288452, "learning_rate": 3.6683266608573286e-05, "loss": 0.6598, "step": 920 }, { "epoch": 1.7346460384435067, "grad_norm": 0.4897356331348419, "learning_rate": 3.6552791087065075e-05, "loss": 0.5536, "step": 925 }, { "epoch": 1.7440225035161743, "grad_norm": 0.4682961702346802, "learning_rate": 3.642191420842e-05, "loss": 0.5606, "step": 930 }, { "epoch": 1.753398968588842, "grad_norm": 0.46142104268074036, "learning_rate": 3.6290640519450074e-05, "loss": 0.5553, "step": 935 }, { "epoch": 1.7627754336615096, "grad_norm": 0.4685068726539612, "learning_rate": 3.6158974580752954e-05, "loss": 0.5974, "step": 940 }, { "epoch": 1.7721518987341773, "grad_norm": 0.4957576394081116, "learning_rate": 3.60269209665535e-05, "loss": 0.5381, "step": 945 }, { "epoch": 1.7815283638068449, "grad_norm": 0.5038308501243591, "learning_rate": 3.589448426454486e-05, "loss": 0.5858, "step": 950 }, { "epoch": 1.7909048288795124, "grad_norm": 0.5150238871574402, "learning_rate": 3.5761669075729084e-05, "loss": 0.552, "step": 955 }, { "epoch": 1.80028129395218, "grad_norm": 0.4681142568588257, "learning_rate": 3.562848001425729e-05, "loss": 0.6042, "step": 960 }, { "epoch": 1.8096577590248475, "grad_norm": 0.4891737401485443, "learning_rate": 3.549492170726937e-05, "loss": 0.5418, "step": 965 }, { "epoch": 1.8190342240975153, "grad_norm": 0.523688554763794, "learning_rate": 3.53609987947332e-05, "loss": 0.5743, "step": 970 }, { "epoch": 1.8284106891701828, "grad_norm": 0.46937504410743713, "learning_rate": 3.5226715929283506e-05, "loss": 0.5245, "step": 975 }, { "epoch": 1.8377871542428506, "grad_norm": 0.4652925729751587, "learning_rate": 3.509207777606013e-05, "loss": 0.5232, "step": 980 }, { "epoch": 1.847163619315518, "grad_norm": 0.5381861925125122, "learning_rate": 3.49570890125461e-05, "loss": 0.5354, "step": 985 }, { "epoch": 1.8565400843881856, "grad_norm": 0.47162288427352905, "learning_rate": 3.482175432840495e-05, "loss": 0.5296, "step": 990 }, { "epoch": 1.8659165494608532, "grad_norm": 0.5244145393371582, "learning_rate": 3.468607842531797e-05, "loss": 0.5486, "step": 995 }, { "epoch": 1.8752930145335207, "grad_norm": 0.5489354729652405, "learning_rate": 3.455006601682075e-05, "loss": 0.5339, "step": 1000 }, { "epoch": 1.8846694796061885, "grad_norm": 0.48319703340530396, "learning_rate": 3.441372182813946e-05, "loss": 0.5105, "step": 1005 }, { "epoch": 1.8940459446788562, "grad_norm": 0.4515131413936615, "learning_rate": 3.427705059602671e-05, "loss": 0.5353, "step": 1010 }, { "epoch": 1.9034224097515238, "grad_norm": 0.49319255352020264, "learning_rate": 3.414005706859693e-05, "loss": 0.574, "step": 1015 }, { "epoch": 1.9127988748241913, "grad_norm": 0.47591525316238403, "learning_rate": 3.400274600516152e-05, "loss": 0.558, "step": 1020 }, { "epoch": 1.9221753398968588, "grad_norm": 0.4464595913887024, "learning_rate": 3.386512217606339e-05, "loss": 0.5312, "step": 1025 }, { "epoch": 1.9315518049695264, "grad_norm": 0.5216926336288452, "learning_rate": 3.372719036251132e-05, "loss": 0.5401, "step": 1030 }, { "epoch": 1.9409282700421941, "grad_norm": 0.44332537055015564, "learning_rate": 3.3588955356413795e-05, "loss": 0.5468, "step": 1035 }, { "epoch": 1.9503047351148617, "grad_norm": 0.5241976976394653, "learning_rate": 3.3450421960212566e-05, "loss": 0.5533, "step": 1040 }, { "epoch": 1.9596812001875294, "grad_norm": 0.5050984621047974, "learning_rate": 3.3311594986715814e-05, "loss": 0.5615, "step": 1045 }, { "epoch": 1.969057665260197, "grad_norm": 0.5221999883651733, "learning_rate": 3.317247925893089e-05, "loss": 0.5201, "step": 1050 }, { "epoch": 1.9784341303328645, "grad_norm": 0.4861835241317749, "learning_rate": 3.3033079609896834e-05, "loss": 0.5404, "step": 1055 }, { "epoch": 1.987810595405532, "grad_norm": 0.5304378867149353, "learning_rate": 3.289340088251642e-05, "loss": 0.5162, "step": 1060 }, { "epoch": 1.9971870604781996, "grad_norm": 0.4507236182689667, "learning_rate": 3.275344792938791e-05, "loss": 0.543, "step": 1065 }, { "epoch": 2.006563525550867, "grad_norm": 0.42468950152397156, "learning_rate": 3.2613225612636525e-05, "loss": 0.4996, "step": 1070 }, { "epoch": 2.015939990623535, "grad_norm": 0.4971221089363098, "learning_rate": 3.247273880374542e-05, "loss": 0.5008, "step": 1075 }, { "epoch": 2.0253164556962027, "grad_norm": 0.5252302885055542, "learning_rate": 3.2331992383386566e-05, "loss": 0.5758, "step": 1080 }, { "epoch": 2.03469292076887, "grad_norm": 0.450898140668869, "learning_rate": 3.21909912412511e-05, "loss": 0.5323, "step": 1085 }, { "epoch": 2.0440693858415377, "grad_norm": 0.480165034532547, "learning_rate": 3.2049740275879493e-05, "loss": 0.5572, "step": 1090 }, { "epoch": 2.0534458509142053, "grad_norm": 0.5092324018478394, "learning_rate": 3.190824439449137e-05, "loss": 0.5761, "step": 1095 }, { "epoch": 2.062822315986873, "grad_norm": 0.5136324167251587, "learning_rate": 3.176650851281499e-05, "loss": 0.5328, "step": 1100 }, { "epoch": 2.0721987810595404, "grad_norm": 0.47322919964790344, "learning_rate": 3.162453755491655e-05, "loss": 0.4987, "step": 1105 }, { "epoch": 2.0815752461322083, "grad_norm": 0.4827199876308441, "learning_rate": 3.1482336453028986e-05, "loss": 0.5158, "step": 1110 }, { "epoch": 2.090951711204876, "grad_norm": 0.4925857484340668, "learning_rate": 3.133991014738076e-05, "loss": 0.5462, "step": 1115 }, { "epoch": 2.1003281762775434, "grad_norm": 0.4654436409473419, "learning_rate": 3.1197263586024155e-05, "loss": 0.5337, "step": 1120 }, { "epoch": 2.109704641350211, "grad_norm": 0.5248768925666809, "learning_rate": 3.105440172466337e-05, "loss": 0.5591, "step": 1125 }, { "epoch": 2.1190811064228785, "grad_norm": 0.5586119294166565, "learning_rate": 3.09113295264824e-05, "loss": 0.5473, "step": 1130 }, { "epoch": 2.128457571495546, "grad_norm": 0.500682532787323, "learning_rate": 3.076805196197255e-05, "loss": 0.5381, "step": 1135 }, { "epoch": 2.1378340365682136, "grad_norm": 0.5898781418800354, "learning_rate": 3.0624574008759805e-05, "loss": 0.6433, "step": 1140 }, { "epoch": 2.1472105016408816, "grad_norm": 0.5896307826042175, "learning_rate": 3.0480900651431876e-05, "loss": 0.5256, "step": 1145 }, { "epoch": 2.156586966713549, "grad_norm": 0.5270710587501526, "learning_rate": 3.0337036881365045e-05, "loss": 0.512, "step": 1150 }, { "epoch": 2.1659634317862166, "grad_norm": 0.5556356906890869, "learning_rate": 3.0192987696550746e-05, "loss": 0.5319, "step": 1155 }, { "epoch": 2.175339896858884, "grad_norm": 0.5308244228363037, "learning_rate": 3.0048758101421914e-05, "loss": 0.536, "step": 1160 }, { "epoch": 2.1847163619315517, "grad_norm": 0.5032731294631958, "learning_rate": 2.9904353106679178e-05, "loss": 0.544, "step": 1165 }, { "epoch": 2.1940928270042193, "grad_norm": 0.4815014898777008, "learning_rate": 2.975977772911671e-05, "loss": 0.5989, "step": 1170 }, { "epoch": 2.2034692920768872, "grad_norm": 0.5544810891151428, "learning_rate": 2.9615036991448015e-05, "loss": 0.5598, "step": 1175 }, { "epoch": 2.212845757149555, "grad_norm": 0.5214317440986633, "learning_rate": 2.947013592213137e-05, "loss": 0.5667, "step": 1180 }, { "epoch": 2.2222222222222223, "grad_norm": 0.47054922580718994, "learning_rate": 2.9325079555195163e-05, "loss": 0.5661, "step": 1185 }, { "epoch": 2.23159868729489, "grad_norm": 0.5608205795288086, "learning_rate": 2.9179872930063e-05, "loss": 0.5312, "step": 1190 }, { "epoch": 2.2409751523675574, "grad_norm": 0.5608832240104675, "learning_rate": 2.9034521091378635e-05, "loss": 0.5118, "step": 1195 }, { "epoch": 2.250351617440225, "grad_norm": 0.5235047936439514, "learning_rate": 2.8889029088830686e-05, "loss": 0.5503, "step": 1200 }, { "epoch": 2.2597280825128925, "grad_norm": 0.5191235542297363, "learning_rate": 2.8743401976977257e-05, "loss": 0.5345, "step": 1205 }, { "epoch": 2.2691045475855605, "grad_norm": 0.5068000555038452, "learning_rate": 2.8597644815070263e-05, "loss": 0.594, "step": 1210 }, { "epoch": 2.278481012658228, "grad_norm": 0.525265097618103, "learning_rate": 2.845176266687974e-05, "loss": 0.5237, "step": 1215 }, { "epoch": 2.2878574777308955, "grad_norm": 0.5695721507072449, "learning_rate": 2.8305760600517862e-05, "loss": 0.5142, "step": 1220 }, { "epoch": 2.297233942803563, "grad_norm": 0.5257561802864075, "learning_rate": 2.815964368826292e-05, "loss": 0.5414, "step": 1225 }, { "epoch": 2.3066104078762306, "grad_norm": 0.5726068019866943, "learning_rate": 2.8013417006383076e-05, "loss": 0.525, "step": 1230 }, { "epoch": 2.315986872948898, "grad_norm": 0.555002748966217, "learning_rate": 2.7867085634960016e-05, "loss": 0.5435, "step": 1235 }, { "epoch": 2.3253633380215657, "grad_norm": 0.6023123860359192, "learning_rate": 2.772065465771244e-05, "loss": 0.5355, "step": 1240 }, { "epoch": 2.3347398030942337, "grad_norm": 0.6386926174163818, "learning_rate": 2.7574129161819495e-05, "loss": 0.5647, "step": 1245 }, { "epoch": 2.344116268166901, "grad_norm": 0.4695705771446228, "learning_rate": 2.7427514237744e-05, "loss": 0.558, "step": 1250 }, { "epoch": 2.3534927332395688, "grad_norm": 0.5911107063293457, "learning_rate": 2.7280814979055612e-05, "loss": 0.5683, "step": 1255 }, { "epoch": 2.3628691983122363, "grad_norm": 0.4722149074077606, "learning_rate": 2.713403648225388e-05, "loss": 0.5172, "step": 1260 }, { "epoch": 2.372245663384904, "grad_norm": 0.5362224578857422, "learning_rate": 2.698718384659114e-05, "loss": 0.5339, "step": 1265 }, { "epoch": 2.3816221284575714, "grad_norm": 0.5780048370361328, "learning_rate": 2.684026217389544e-05, "loss": 0.6172, "step": 1270 }, { "epoch": 2.390998593530239, "grad_norm": 0.4645563066005707, "learning_rate": 2.6693276568393245e-05, "loss": 0.5337, "step": 1275 }, { "epoch": 2.400375058602907, "grad_norm": 0.48818090558052063, "learning_rate": 2.6546232136532083e-05, "loss": 0.5903, "step": 1280 }, { "epoch": 2.4097515236755744, "grad_norm": 0.5511724948883057, "learning_rate": 2.639913398680322e-05, "loss": 0.5693, "step": 1285 }, { "epoch": 2.419127988748242, "grad_norm": 0.506675124168396, "learning_rate": 2.6251987229564123e-05, "loss": 0.5415, "step": 1290 }, { "epoch": 2.4285044538209095, "grad_norm": 0.5370191335678101, "learning_rate": 2.610479697686093e-05, "loss": 0.5063, "step": 1295 }, { "epoch": 2.437880918893577, "grad_norm": 0.5342317223548889, "learning_rate": 2.595756834225089e-05, "loss": 0.5556, "step": 1300 }, { "epoch": 2.4472573839662446, "grad_norm": 0.5420209765434265, "learning_rate": 2.5810306440624644e-05, "loss": 0.6267, "step": 1305 }, { "epoch": 2.456633849038912, "grad_norm": 0.5854496359825134, "learning_rate": 2.566301638802861e-05, "loss": 0.5637, "step": 1310 }, { "epoch": 2.46601031411158, "grad_norm": 0.5205966234207153, "learning_rate": 2.551570330148716e-05, "loss": 0.5426, "step": 1315 }, { "epoch": 2.4753867791842477, "grad_norm": 0.5490741729736328, "learning_rate": 2.5368372298824922e-05, "loss": 0.5028, "step": 1320 }, { "epoch": 2.484763244256915, "grad_norm": 0.5535454750061035, "learning_rate": 2.5221028498488947e-05, "loss": 0.5536, "step": 1325 }, { "epoch": 2.4941397093295827, "grad_norm": 0.624588668346405, "learning_rate": 2.507367701937087e-05, "loss": 0.5199, "step": 1330 }, { "epoch": 2.5035161744022503, "grad_norm": 0.5129014253616333, "learning_rate": 2.492632298062913e-05, "loss": 0.5328, "step": 1335 }, { "epoch": 2.512892639474918, "grad_norm": 0.5573890805244446, "learning_rate": 2.4778971501511063e-05, "loss": 0.5625, "step": 1340 }, { "epoch": 2.5222691045475853, "grad_norm": 0.5620486736297607, "learning_rate": 2.4631627701175084e-05, "loss": 0.5238, "step": 1345 }, { "epoch": 2.5316455696202533, "grad_norm": 0.5784332752227783, "learning_rate": 2.448429669851285e-05, "loss": 0.5108, "step": 1350 }, { "epoch": 2.541022034692921, "grad_norm": 0.6034047603607178, "learning_rate": 2.43369836119714e-05, "loss": 0.5603, "step": 1355 }, { "epoch": 2.5503984997655884, "grad_norm": 0.5075374841690063, "learning_rate": 2.4189693559375365e-05, "loss": 0.574, "step": 1360 }, { "epoch": 2.559774964838256, "grad_norm": 0.5321151614189148, "learning_rate": 2.4042431657749117e-05, "loss": 0.5086, "step": 1365 }, { "epoch": 2.5691514299109235, "grad_norm": 0.5753352642059326, "learning_rate": 2.3895203023139073e-05, "loss": 0.5052, "step": 1370 }, { "epoch": 2.578527894983591, "grad_norm": 0.552044153213501, "learning_rate": 2.3748012770435883e-05, "loss": 0.5636, "step": 1375 }, { "epoch": 2.5879043600562586, "grad_norm": 0.5452053546905518, "learning_rate": 2.3600866013196787e-05, "loss": 0.5367, "step": 1380 }, { "epoch": 2.5972808251289266, "grad_norm": 0.5029872059822083, "learning_rate": 2.3453767863467923e-05, "loss": 0.5316, "step": 1385 }, { "epoch": 2.606657290201594, "grad_norm": 0.5490592122077942, "learning_rate": 2.3306723431606758e-05, "loss": 0.5161, "step": 1390 }, { "epoch": 2.6160337552742616, "grad_norm": 0.5136232376098633, "learning_rate": 2.3159737826104565e-05, "loss": 0.5728, "step": 1395 }, { "epoch": 2.625410220346929, "grad_norm": 0.5669593811035156, "learning_rate": 2.3012816153408863e-05, "loss": 0.5436, "step": 1400 }, { "epoch": 2.6347866854195967, "grad_norm": 0.5253113508224487, "learning_rate": 2.286596351774613e-05, "loss": 0.5236, "step": 1405 }, { "epoch": 2.6441631504922647, "grad_norm": 0.6063436269760132, "learning_rate": 2.271918502094439e-05, "loss": 0.5078, "step": 1410 }, { "epoch": 2.653539615564932, "grad_norm": 0.5364498496055603, "learning_rate": 2.2572485762256005e-05, "loss": 0.503, "step": 1415 }, { "epoch": 2.6629160806375998, "grad_norm": 0.5893564820289612, "learning_rate": 2.2425870838180507e-05, "loss": 0.5348, "step": 1420 }, { "epoch": 2.6722925457102673, "grad_norm": 0.523727536201477, "learning_rate": 2.2279345342287567e-05, "loss": 0.5343, "step": 1425 }, { "epoch": 2.681669010782935, "grad_norm": 0.5448949337005615, "learning_rate": 2.2132914365039993e-05, "loss": 0.5586, "step": 1430 }, { "epoch": 2.6910454758556024, "grad_norm": 0.5735951662063599, "learning_rate": 2.1986582993616926e-05, "loss": 0.5474, "step": 1435 }, { "epoch": 2.70042194092827, "grad_norm": 0.5605931878089905, "learning_rate": 2.1840356311737084e-05, "loss": 0.5474, "step": 1440 }, { "epoch": 2.709798406000938, "grad_norm": 0.48015716671943665, "learning_rate": 2.169423939948215e-05, "loss": 0.572, "step": 1445 }, { "epoch": 2.719174871073605, "grad_norm": 0.5914106965065002, "learning_rate": 2.154823733312027e-05, "loss": 0.5636, "step": 1450 }, { "epoch": 2.728551336146273, "grad_norm": 0.5666556358337402, "learning_rate": 2.140235518492975e-05, "loss": 0.5305, "step": 1455 }, { "epoch": 2.7379278012189405, "grad_norm": 0.6020416617393494, "learning_rate": 2.125659802302275e-05, "loss": 0.5273, "step": 1460 }, { "epoch": 2.747304266291608, "grad_norm": 0.46794259548187256, "learning_rate": 2.1110970911169316e-05, "loss": 0.5383, "step": 1465 }, { "epoch": 2.7566807313642756, "grad_norm": 0.525830864906311, "learning_rate": 2.096547890862137e-05, "loss": 0.5482, "step": 1470 }, { "epoch": 2.766057196436943, "grad_norm": 0.5674699544906616, "learning_rate": 2.0820127069937008e-05, "loss": 0.5226, "step": 1475 }, { "epoch": 2.775433661509611, "grad_norm": 0.5397214293479919, "learning_rate": 2.0674920444804847e-05, "loss": 0.5276, "step": 1480 }, { "epoch": 2.7848101265822782, "grad_norm": 0.5620929002761841, "learning_rate": 2.0529864077868643e-05, "loss": 0.5636, "step": 1485 }, { "epoch": 2.794186591654946, "grad_norm": 0.5328047275543213, "learning_rate": 2.0384963008551995e-05, "loss": 0.5531, "step": 1490 }, { "epoch": 2.8035630567276137, "grad_norm": 0.5161858797073364, "learning_rate": 2.0240222270883288e-05, "loss": 0.5709, "step": 1495 }, { "epoch": 2.8129395218002813, "grad_norm": 0.547215461730957, "learning_rate": 2.0095646893320828e-05, "loss": 0.53, "step": 1500 }, { "epoch": 2.822315986872949, "grad_norm": 0.5471156239509583, "learning_rate": 1.9951241898578085e-05, "loss": 0.5258, "step": 1505 }, { "epoch": 2.8316924519456164, "grad_norm": 0.576733410358429, "learning_rate": 1.980701230344926e-05, "loss": 0.536, "step": 1510 }, { "epoch": 2.8410689170182843, "grad_norm": 0.5285231471061707, "learning_rate": 1.9662963118634954e-05, "loss": 0.5724, "step": 1515 }, { "epoch": 2.8504453820909514, "grad_norm": 0.571106493473053, "learning_rate": 1.9519099348568127e-05, "loss": 0.5325, "step": 1520 }, { "epoch": 2.8598218471636194, "grad_norm": 0.5687730312347412, "learning_rate": 1.93754259912402e-05, "loss": 0.5505, "step": 1525 }, { "epoch": 2.869198312236287, "grad_norm": 0.5169468522071838, "learning_rate": 1.9231948038027462e-05, "loss": 0.5153, "step": 1530 }, { "epoch": 2.8785747773089545, "grad_norm": 0.5131816267967224, "learning_rate": 1.9088670473517605e-05, "loss": 0.5411, "step": 1535 }, { "epoch": 2.887951242381622, "grad_norm": 0.509089469909668, "learning_rate": 1.8945598275336633e-05, "loss": 0.5085, "step": 1540 }, { "epoch": 2.8973277074542896, "grad_norm": 0.5635603070259094, "learning_rate": 1.8802736413975844e-05, "loss": 0.5683, "step": 1545 }, { "epoch": 2.9067041725269576, "grad_norm": 0.6164025068283081, "learning_rate": 1.866008985261924e-05, "loss": 0.5393, "step": 1550 }, { "epoch": 2.916080637599625, "grad_norm": 0.5791330337524414, "learning_rate": 1.8517663546971013e-05, "loss": 0.5303, "step": 1555 }, { "epoch": 2.9254571026722926, "grad_norm": 0.5574399828910828, "learning_rate": 1.8375462445083464e-05, "loss": 0.5599, "step": 1560 }, { "epoch": 2.93483356774496, "grad_norm": 0.5197755098342896, "learning_rate": 1.8233491487185006e-05, "loss": 0.5712, "step": 1565 }, { "epoch": 2.9442100328176277, "grad_norm": 0.5005416870117188, "learning_rate": 1.8091755605508643e-05, "loss": 0.5459, "step": 1570 }, { "epoch": 2.9535864978902953, "grad_norm": 0.6060538291931152, "learning_rate": 1.7950259724120512e-05, "loss": 0.5754, "step": 1575 }, { "epoch": 2.962962962962963, "grad_norm": 0.570067286491394, "learning_rate": 1.7809008758748913e-05, "loss": 0.5615, "step": 1580 }, { "epoch": 2.972339428035631, "grad_norm": 0.6312186121940613, "learning_rate": 1.766800761661344e-05, "loss": 0.5135, "step": 1585 }, { "epoch": 2.9817158931082983, "grad_norm": 0.6070550084114075, "learning_rate": 1.752726119625459e-05, "loss": 0.566, "step": 1590 }, { "epoch": 2.991092358180966, "grad_norm": 0.5160552859306335, "learning_rate": 1.7386774387363484e-05, "loss": 0.579, "step": 1595 }, { "epoch": 3.0004688232536334, "grad_norm": 0.5943719148635864, "learning_rate": 1.724655207061209e-05, "loss": 0.5286, "step": 1600 }, { "epoch": 3.009845288326301, "grad_norm": 0.5501561760902405, "learning_rate": 1.710659911748359e-05, "loss": 0.5806, "step": 1605 }, { "epoch": 3.0192217533989685, "grad_norm": 0.5667310953140259, "learning_rate": 1.696692039010317e-05, "loss": 0.534, "step": 1610 }, { "epoch": 3.028598218471636, "grad_norm": 0.5230310559272766, "learning_rate": 1.6827520741069118e-05, "loss": 0.5507, "step": 1615 }, { "epoch": 3.037974683544304, "grad_norm": 0.6031038165092468, "learning_rate": 1.6688405013284192e-05, "loss": 0.5537, "step": 1620 }, { "epoch": 3.0473511486169715, "grad_norm": 0.4670465290546417, "learning_rate": 1.6549578039787436e-05, "loss": 0.5575, "step": 1625 }, { "epoch": 3.056727613689639, "grad_norm": 0.5443038940429688, "learning_rate": 1.6411044643586204e-05, "loss": 0.5043, "step": 1630 }, { "epoch": 3.0661040787623066, "grad_norm": 0.6336117386817932, "learning_rate": 1.627280963748869e-05, "loss": 0.4903, "step": 1635 }, { "epoch": 3.075480543834974, "grad_norm": 0.49661606550216675, "learning_rate": 1.613487782393661e-05, "loss": 0.5934, "step": 1640 }, { "epoch": 3.0848570089076417, "grad_norm": 0.5555146932601929, "learning_rate": 1.5997253994838484e-05, "loss": 0.4922, "step": 1645 }, { "epoch": 3.0942334739803092, "grad_norm": 0.6635964512825012, "learning_rate": 1.5859942931403072e-05, "loss": 0.5327, "step": 1650 }, { "epoch": 3.103609939052977, "grad_norm": 0.5776465535163879, "learning_rate": 1.5722949403973308e-05, "loss": 0.5836, "step": 1655 }, { "epoch": 3.1129864041256448, "grad_norm": 0.6424173712730408, "learning_rate": 1.5586278171860546e-05, "loss": 0.527, "step": 1660 }, { "epoch": 3.1223628691983123, "grad_norm": 0.5594909191131592, "learning_rate": 1.5449933983179256e-05, "loss": 0.5466, "step": 1665 }, { "epoch": 3.13173933427098, "grad_norm": 0.5368645787239075, "learning_rate": 1.5313921574682032e-05, "loss": 0.5162, "step": 1670 }, { "epoch": 3.1411157993436474, "grad_norm": 0.5256815552711487, "learning_rate": 1.517824567159506e-05, "loss": 0.4985, "step": 1675 }, { "epoch": 3.150492264416315, "grad_norm": 0.5784279108047485, "learning_rate": 1.5042910987453909e-05, "loss": 0.5674, "step": 1680 }, { "epoch": 3.1598687294889825, "grad_norm": 0.5585960149765015, "learning_rate": 1.4907922223939874e-05, "loss": 0.5051, "step": 1685 }, { "epoch": 3.1692451945616504, "grad_norm": 0.5591123104095459, "learning_rate": 1.4773284070716503e-05, "loss": 0.5327, "step": 1690 }, { "epoch": 3.178621659634318, "grad_norm": 0.5815097689628601, "learning_rate": 1.4639001205266803e-05, "loss": 0.5064, "step": 1695 }, { "epoch": 3.1879981247069855, "grad_norm": 0.5162126421928406, "learning_rate": 1.4505078292730632e-05, "loss": 0.5338, "step": 1700 }, { "epoch": 3.197374589779653, "grad_norm": 0.6133378744125366, "learning_rate": 1.4371519985742715e-05, "loss": 0.4959, "step": 1705 }, { "epoch": 3.2067510548523206, "grad_norm": 0.6034416556358337, "learning_rate": 1.4238330924270927e-05, "loss": 0.5289, "step": 1710 }, { "epoch": 3.216127519924988, "grad_norm": 0.5579488277435303, "learning_rate": 1.4105515735455149e-05, "loss": 0.5657, "step": 1715 }, { "epoch": 3.2255039849976557, "grad_norm": 0.5845019221305847, "learning_rate": 1.3973079033446501e-05, "loss": 0.578, "step": 1720 }, { "epoch": 3.2348804500703237, "grad_norm": 0.6357687711715698, "learning_rate": 1.3841025419247045e-05, "loss": 0.5262, "step": 1725 }, { "epoch": 3.244256915142991, "grad_norm": 0.6028162240982056, "learning_rate": 1.3709359480549932e-05, "loss": 0.5048, "step": 1730 }, { "epoch": 3.2536333802156587, "grad_norm": 0.6072187423706055, "learning_rate": 1.3578085791580008e-05, "loss": 0.4904, "step": 1735 }, { "epoch": 3.2630098452883263, "grad_norm": 0.5650848150253296, "learning_rate": 1.3447208912934927e-05, "loss": 0.5938, "step": 1740 }, { "epoch": 3.272386310360994, "grad_norm": 0.6589064002037048, "learning_rate": 1.3316733391426716e-05, "loss": 0.5274, "step": 1745 }, { "epoch": 3.2817627754336613, "grad_norm": 0.5519670844078064, "learning_rate": 1.3186663759923782e-05, "loss": 0.5083, "step": 1750 }, { "epoch": 3.291139240506329, "grad_norm": 0.5798940658569336, "learning_rate": 1.3057004537193423e-05, "loss": 0.5323, "step": 1755 }, { "epoch": 3.300515705578997, "grad_norm": 0.5830232501029968, "learning_rate": 1.2927760227744943e-05, "loss": 0.4991, "step": 1760 }, { "epoch": 3.3098921706516644, "grad_norm": 0.583799421787262, "learning_rate": 1.2798935321673e-05, "loss": 0.4954, "step": 1765 }, { "epoch": 3.319268635724332, "grad_norm": 0.5336604714393616, "learning_rate": 1.2670534294501756e-05, "loss": 0.5194, "step": 1770 }, { "epoch": 3.3286451007969995, "grad_norm": 0.6230494976043701, "learning_rate": 1.2542561607029322e-05, "loss": 0.5209, "step": 1775 }, { "epoch": 3.338021565869667, "grad_norm": 0.5860636234283447, "learning_rate": 1.2415021705172799e-05, "loss": 0.5699, "step": 1780 }, { "epoch": 3.3473980309423346, "grad_norm": 0.5983242392539978, "learning_rate": 1.2287919019813807e-05, "loss": 0.51, "step": 1785 }, { "epoch": 3.356774496015002, "grad_norm": 0.6714468002319336, "learning_rate": 1.2161257966644588e-05, "loss": 0.5497, "step": 1790 }, { "epoch": 3.36615096108767, "grad_norm": 0.5774706602096558, "learning_rate": 1.2035042946014572e-05, "loss": 0.566, "step": 1795 }, { "epoch": 3.3755274261603376, "grad_norm": 0.5805652737617493, "learning_rate": 1.1909278342777513e-05, "loss": 0.5246, "step": 1800 }, { "epoch": 3.384903891233005, "grad_norm": 0.5634963512420654, "learning_rate": 1.1783968526139121e-05, "loss": 0.5261, "step": 1805 }, { "epoch": 3.3942803563056727, "grad_norm": 0.6619728207588196, "learning_rate": 1.1659117849505367e-05, "loss": 0.5497, "step": 1810 }, { "epoch": 3.4036568213783402, "grad_norm": 0.5979011058807373, "learning_rate": 1.1534730650331096e-05, "loss": 0.5185, "step": 1815 }, { "epoch": 3.413033286451008, "grad_norm": 0.6057260632514954, "learning_rate": 1.1410811249969475e-05, "loss": 0.5836, "step": 1820 }, { "epoch": 3.4224097515236753, "grad_norm": 0.5888515114784241, "learning_rate": 1.1287363953521779e-05, "loss": 0.5318, "step": 1825 }, { "epoch": 3.4317862165963433, "grad_norm": 0.5773415565490723, "learning_rate": 1.1164393049687868e-05, "loss": 0.5141, "step": 1830 }, { "epoch": 3.441162681669011, "grad_norm": 0.542140007019043, "learning_rate": 1.104190281061718e-05, "loss": 0.5626, "step": 1835 }, { "epoch": 3.4505391467416784, "grad_norm": 0.5948598980903625, "learning_rate": 1.0919897491760279e-05, "loss": 0.4792, "step": 1840 }, { "epoch": 3.459915611814346, "grad_norm": 0.5241517424583435, "learning_rate": 1.0798381331721109e-05, "loss": 0.515, "step": 1845 }, { "epoch": 3.4692920768870135, "grad_norm": 0.5624334812164307, "learning_rate": 1.0677358552109618e-05, "loss": 0.5393, "step": 1850 }, { "epoch": 3.4786685419596814, "grad_norm": 0.5150102376937866, "learning_rate": 1.0556833357395188e-05, "loss": 0.5096, "step": 1855 }, { "epoch": 3.488045007032349, "grad_norm": 0.5694672465324402, "learning_rate": 1.0436809934760527e-05, "loss": 0.5266, "step": 1860 }, { "epoch": 3.4974214721050165, "grad_norm": 0.6179835200309753, "learning_rate": 1.031729245395622e-05, "loss": 0.5003, "step": 1865 }, { "epoch": 3.506797937177684, "grad_norm": 0.6380405426025391, "learning_rate": 1.0198285067155827e-05, "loss": 0.5228, "step": 1870 }, { "epoch": 3.5161744022503516, "grad_norm": 0.6013153791427612, "learning_rate": 1.0079791908811683e-05, "loss": 0.5204, "step": 1875 }, { "epoch": 3.525550867323019, "grad_norm": 0.5853320956230164, "learning_rate": 9.961817095511242e-06, "loss": 0.5138, "step": 1880 }, { "epoch": 3.5349273323956867, "grad_norm": 0.5283975601196289, "learning_rate": 9.844364725834057e-06, "loss": 0.5748, "step": 1885 }, { "epoch": 3.5443037974683547, "grad_norm": 0.7122249603271484, "learning_rate": 9.727438880209366e-06, "loss": 0.5042, "step": 1890 }, { "epoch": 3.5536802625410218, "grad_norm": 0.6497731804847717, "learning_rate": 9.611043620774419e-06, "loss": 0.5591, "step": 1895 }, { "epoch": 3.5630567276136897, "grad_norm": 0.5497525930404663, "learning_rate": 9.495182991233236e-06, "loss": 0.5268, "step": 1900 }, { "epoch": 3.5724331926863573, "grad_norm": 0.6197280287742615, "learning_rate": 9.379861016716224e-06, "loss": 0.5592, "step": 1905 }, { "epoch": 3.581809657759025, "grad_norm": 0.564769446849823, "learning_rate": 9.265081703640285e-06, "loss": 0.5537, "step": 1910 }, { "epoch": 3.5911861228316924, "grad_norm": 0.5738486051559448, "learning_rate": 9.150849039569655e-06, "loss": 0.5243, "step": 1915 }, { "epoch": 3.60056258790436, "grad_norm": 0.5415158867835999, "learning_rate": 9.037166993077337e-06, "loss": 0.5264, "step": 1920 }, { "epoch": 3.609939052977028, "grad_norm": 0.5810761451721191, "learning_rate": 8.92403951360726e-06, "loss": 0.5062, "step": 1925 }, { "epoch": 3.6193155180496954, "grad_norm": 0.5113641619682312, "learning_rate": 8.811470531337102e-06, "loss": 0.5729, "step": 1930 }, { "epoch": 3.628691983122363, "grad_norm": 0.5926602482795715, "learning_rate": 8.699463957041649e-06, "loss": 0.5901, "step": 1935 }, { "epoch": 3.6380684481950305, "grad_norm": 0.5843651294708252, "learning_rate": 8.588023681957028e-06, "loss": 0.5517, "step": 1940 }, { "epoch": 3.647444913267698, "grad_norm": 0.6659519672393799, "learning_rate": 8.477153577645481e-06, "loss": 0.5617, "step": 1945 }, { "epoch": 3.6568213783403656, "grad_norm": 0.5458998084068298, "learning_rate": 8.36685749586087e-06, "loss": 0.551, "step": 1950 }, { "epoch": 3.666197843413033, "grad_norm": 0.6160162687301636, "learning_rate": 8.257139268414844e-06, "loss": 0.5394, "step": 1955 }, { "epoch": 3.675574308485701, "grad_norm": 0.5762403011322021, "learning_rate": 8.14800270704375e-06, "loss": 0.5532, "step": 1960 }, { "epoch": 3.6849507735583686, "grad_norm": 0.6198619604110718, "learning_rate": 8.039451603276185e-06, "loss": 0.5242, "step": 1965 }, { "epoch": 3.694327238631036, "grad_norm": 0.5094100832939148, "learning_rate": 7.931489728301292e-06, "loss": 0.6371, "step": 1970 }, { "epoch": 3.7037037037037037, "grad_norm": 0.6113427877426147, "learning_rate": 7.8241208328377e-06, "loss": 0.5144, "step": 1975 }, { "epoch": 3.7130801687763713, "grad_norm": 0.48081642389297485, "learning_rate": 7.71734864700331e-06, "loss": 0.5271, "step": 1980 }, { "epoch": 3.722456633849039, "grad_norm": 0.6206328868865967, "learning_rate": 7.611176880185597e-06, "loss": 0.5273, "step": 1985 }, { "epoch": 3.7318330989217063, "grad_norm": 0.5632244944572449, "learning_rate": 7.505609220912821e-06, "loss": 0.5249, "step": 1990 }, { "epoch": 3.7412095639943743, "grad_norm": 0.5980995893478394, "learning_rate": 7.4006493367258515e-06, "loss": 0.5625, "step": 1995 }, { "epoch": 3.750586029067042, "grad_norm": 0.6244497895240784, "learning_rate": 7.2963008740507656e-06, "loss": 0.5701, "step": 2000 }, { "epoch": 3.7599624941397094, "grad_norm": 0.589423656463623, "learning_rate": 7.192567458072138e-06, "loss": 0.583, "step": 2005 }, { "epoch": 3.769338959212377, "grad_norm": 0.5806391835212708, "learning_rate": 7.089452692607146e-06, "loss": 0.4779, "step": 2010 }, { "epoch": 3.7787154242850445, "grad_norm": 0.6201165914535522, "learning_rate": 6.986960159980327e-06, "loss": 0.4985, "step": 2015 }, { "epoch": 3.788091889357712, "grad_norm": 0.5155811905860901, "learning_rate": 6.885093420899152e-06, "loss": 0.5305, "step": 2020 }, { "epoch": 3.7974683544303796, "grad_norm": 0.6702911257743835, "learning_rate": 6.783856014330281e-06, "loss": 0.5356, "step": 2025 }, { "epoch": 3.8068448195030475, "grad_norm": 0.6424790024757385, "learning_rate": 6.68325145737669e-06, "loss": 0.5269, "step": 2030 }, { "epoch": 3.816221284575715, "grad_norm": 0.6156381368637085, "learning_rate": 6.583283245155414e-06, "loss": 0.5563, "step": 2035 }, { "epoch": 3.8255977496483826, "grad_norm": 0.7311144471168518, "learning_rate": 6.483954850676133e-06, "loss": 0.5146, "step": 2040 }, { "epoch": 3.83497421472105, "grad_norm": 0.5719829797744751, "learning_rate": 6.385269724720547e-06, "loss": 0.5614, "step": 2045 }, { "epoch": 3.8443506797937177, "grad_norm": 0.6313838958740234, "learning_rate": 6.28723129572247e-06, "loss": 0.4988, "step": 2050 }, { "epoch": 3.8537271448663852, "grad_norm": 0.649053156375885, "learning_rate": 6.189842969648737e-06, "loss": 0.5621, "step": 2055 }, { "epoch": 3.8631036099390528, "grad_norm": 0.5733803510665894, "learning_rate": 6.0931081298808316e-06, "loss": 0.5282, "step": 2060 }, { "epoch": 3.8724800750117208, "grad_norm": 0.6120590567588806, "learning_rate": 5.997030137097426e-06, "loss": 0.5119, "step": 2065 }, { "epoch": 3.8818565400843883, "grad_norm": 0.5763484239578247, "learning_rate": 5.901612329157535e-06, "loss": 0.5431, "step": 2070 }, { "epoch": 3.891233005157056, "grad_norm": 0.5271406173706055, "learning_rate": 5.806858020984629e-06, "loss": 0.5971, "step": 2075 }, { "epoch": 3.9006094702297234, "grad_norm": 0.6094108819961548, "learning_rate": 5.712770504451426e-06, "loss": 0.54, "step": 2080 }, { "epoch": 3.909985935302391, "grad_norm": 0.6518940329551697, "learning_rate": 5.619353048265552e-06, "loss": 0.5045, "step": 2085 }, { "epoch": 3.9193624003750585, "grad_norm": 0.5773950815200806, "learning_rate": 5.526608897855953e-06, "loss": 0.5086, "step": 2090 }, { "epoch": 3.928738865447726, "grad_norm": 0.5974025726318359, "learning_rate": 5.434541275260182e-06, "loss": 0.5774, "step": 2095 }, { "epoch": 3.938115330520394, "grad_norm": 0.5835773348808289, "learning_rate": 5.343153379012444e-06, "loss": 0.5541, "step": 2100 }, { "epoch": 3.9474917955930615, "grad_norm": 0.5908766388893127, "learning_rate": 5.252448384032471e-06, "loss": 0.517, "step": 2105 }, { "epoch": 3.956868260665729, "grad_norm": 0.6290919780731201, "learning_rate": 5.162429441515221e-06, "loss": 0.5474, "step": 2110 }, { "epoch": 3.9662447257383966, "grad_norm": 0.5998512506484985, "learning_rate": 5.073099678821413e-06, "loss": 0.5178, "step": 2115 }, { "epoch": 3.975621190811064, "grad_norm": 0.5630286335945129, "learning_rate": 4.984462199368872e-06, "loss": 0.5671, "step": 2120 }, { "epoch": 3.9849976558837317, "grad_norm": 0.6709501147270203, "learning_rate": 4.8965200825247245e-06, "loss": 0.5148, "step": 2125 }, { "epoch": 3.994374120956399, "grad_norm": 0.5447418689727783, "learning_rate": 4.809276383498376e-06, "loss": 0.5418, "step": 2130 }, { "epoch": 4.003750586029067, "grad_norm": 0.5624414086341858, "learning_rate": 4.722734133235438e-06, "loss": 0.5433, "step": 2135 }, { "epoch": 4.013127051101734, "grad_norm": 0.6009880304336548, "learning_rate": 4.636896338312374e-06, "loss": 0.581, "step": 2140 }, { "epoch": 4.022503516174402, "grad_norm": 0.6356287002563477, "learning_rate": 4.551765980832059e-06, "loss": 0.5108, "step": 2145 }, { "epoch": 4.03187998124707, "grad_norm": 0.6711658835411072, "learning_rate": 4.467346018320198e-06, "loss": 0.5533, "step": 2150 }, { "epoch": 4.041256446319737, "grad_norm": 0.6147199869155884, "learning_rate": 4.383639383622557e-06, "loss": 0.5372, "step": 2155 }, { "epoch": 4.050632911392405, "grad_norm": 0.6129254102706909, "learning_rate": 4.300648984803085e-06, "loss": 0.5183, "step": 2160 }, { "epoch": 4.060009376465072, "grad_norm": 0.5274255275726318, "learning_rate": 4.218377705042867e-06, "loss": 0.5426, "step": 2165 }, { "epoch": 4.06938584153774, "grad_norm": 0.5687923431396484, "learning_rate": 4.1368284025399965e-06, "loss": 0.5491, "step": 2170 }, { "epoch": 4.0787623066104075, "grad_norm": 0.5000860095024109, "learning_rate": 4.0560039104102305e-06, "loss": 0.5401, "step": 2175 }, { "epoch": 4.0881387716830755, "grad_norm": 0.5673547387123108, "learning_rate": 3.975907036588594e-06, "loss": 0.4976, "step": 2180 }, { "epoch": 4.0975152367557435, "grad_norm": 0.6658757925033569, "learning_rate": 3.8965405637318294e-06, "loss": 0.5103, "step": 2185 }, { "epoch": 4.106891701828411, "grad_norm": 0.6456134915351868, "learning_rate": 3.817907249121713e-06, "loss": 0.5443, "step": 2190 }, { "epoch": 4.1162681669010786, "grad_norm": 0.5926840901374817, "learning_rate": 3.7400098245692572e-06, "loss": 0.5377, "step": 2195 }, { "epoch": 4.125644631973746, "grad_norm": 0.5508164763450623, "learning_rate": 3.662850996319825e-06, "loss": 0.5117, "step": 2200 }, { "epoch": 4.135021097046414, "grad_norm": 0.6228732466697693, "learning_rate": 3.586433444959103e-06, "loss": 0.5157, "step": 2205 }, { "epoch": 4.144397562119081, "grad_norm": 0.6101076006889343, "learning_rate": 3.5107598253199758e-06, "loss": 0.5058, "step": 2210 }, { "epoch": 4.153774027191749, "grad_norm": 0.6002482175827026, "learning_rate": 3.4358327663902677e-06, "loss": 0.5233, "step": 2215 }, { "epoch": 4.163150492264417, "grad_norm": 0.6422848701477051, "learning_rate": 3.3616548712214756e-06, "loss": 0.5347, "step": 2220 }, { "epoch": 4.172526957337084, "grad_norm": 0.5175875425338745, "learning_rate": 3.288228716838246e-06, "loss": 0.5124, "step": 2225 }, { "epoch": 4.181903422409752, "grad_norm": 0.6100782155990601, "learning_rate": 3.2155568541489268e-06, "loss": 0.5641, "step": 2230 }, { "epoch": 4.191279887482419, "grad_norm": 0.5398646593093872, "learning_rate": 3.143641807856898e-06, "loss": 0.5416, "step": 2235 }, { "epoch": 4.200656352555087, "grad_norm": 0.5987186431884766, "learning_rate": 3.0724860763728767e-06, "loss": 0.5602, "step": 2240 }, { "epoch": 4.210032817627754, "grad_norm": 0.5340943336486816, "learning_rate": 3.0020921317281264e-06, "loss": 0.4998, "step": 2245 }, { "epoch": 4.219409282700422, "grad_norm": 0.6151329874992371, "learning_rate": 2.9324624194885436e-06, "loss": 0.5699, "step": 2250 }, { "epoch": 4.22878574777309, "grad_norm": 0.6071544885635376, "learning_rate": 2.8635993586697553e-06, "loss": 0.5114, "step": 2255 }, { "epoch": 4.238162212845757, "grad_norm": 0.5918383002281189, "learning_rate": 2.795505341653007e-06, "loss": 0.5061, "step": 2260 }, { "epoch": 4.247538677918425, "grad_norm": 0.5735620260238647, "learning_rate": 2.728182734102111e-06, "loss": 0.5334, "step": 2265 }, { "epoch": 4.256915142991092, "grad_norm": 0.579006016254425, "learning_rate": 2.6616338748812255e-06, "loss": 0.5867, "step": 2270 }, { "epoch": 4.26629160806376, "grad_norm": 0.5297543406486511, "learning_rate": 2.595861075973613e-06, "loss": 0.5287, "step": 2275 }, { "epoch": 4.275668073136427, "grad_norm": 0.5488983392715454, "learning_rate": 2.530866622401304e-06, "loss": 0.5324, "step": 2280 }, { "epoch": 4.285044538209095, "grad_norm": 0.5938432812690735, "learning_rate": 2.4666527721457416e-06, "loss": 0.5267, "step": 2285 }, { "epoch": 4.294421003281763, "grad_norm": 0.5408592224121094, "learning_rate": 2.40322175606931e-06, "loss": 0.548, "step": 2290 }, { "epoch": 4.30379746835443, "grad_norm": 0.6493216753005981, "learning_rate": 2.3405757778378445e-06, "loss": 0.4996, "step": 2295 }, { "epoch": 4.313173933427098, "grad_norm": 0.5764236450195312, "learning_rate": 2.278717013844059e-06, "loss": 0.5294, "step": 2300 }, { "epoch": 4.322550398499765, "grad_norm": 0.5868895053863525, "learning_rate": 2.2176476131319707e-06, "loss": 0.4882, "step": 2305 }, { "epoch": 4.331926863572433, "grad_norm": 0.7049744725227356, "learning_rate": 2.1573696973221922e-06, "loss": 0.5169, "step": 2310 }, { "epoch": 4.3413033286451, "grad_norm": 0.5863852500915527, "learning_rate": 2.0978853605382624e-06, "loss": 0.5325, "step": 2315 }, { "epoch": 4.350679793717768, "grad_norm": 0.5573306679725647, "learning_rate": 2.0391966693338733e-06, "loss": 0.4942, "step": 2320 }, { "epoch": 4.360056258790436, "grad_norm": 0.6028510928153992, "learning_rate": 1.9813056626210886e-06, "loss": 0.5117, "step": 2325 }, { "epoch": 4.369432723863103, "grad_norm": 0.5050864815711975, "learning_rate": 1.9242143515994933e-06, "loss": 0.5069, "step": 2330 }, { "epoch": 4.378809188935771, "grad_norm": 0.5868462920188904, "learning_rate": 1.8679247196863425e-06, "loss": 0.5183, "step": 2335 }, { "epoch": 4.3881856540084385, "grad_norm": 0.5458810925483704, "learning_rate": 1.8124387224476347e-06, "loss": 0.4979, "step": 2340 }, { "epoch": 4.3975621190811065, "grad_norm": 0.5342989563941956, "learning_rate": 1.757758287530195e-06, "loss": 0.5365, "step": 2345 }, { "epoch": 4.4069385841537745, "grad_norm": 0.5850876569747925, "learning_rate": 1.7038853145946804e-06, "loss": 0.5165, "step": 2350 }, { "epoch": 4.416315049226442, "grad_norm": 0.6274101734161377, "learning_rate": 1.6508216752496141e-06, "loss": 0.5718, "step": 2355 }, { "epoch": 4.42569151429911, "grad_norm": 0.6325822472572327, "learning_rate": 1.5985692129863395e-06, "loss": 0.5244, "step": 2360 }, { "epoch": 4.435067979371777, "grad_norm": 0.5776230692863464, "learning_rate": 1.547129743114978e-06, "loss": 0.5609, "step": 2365 }, { "epoch": 4.444444444444445, "grad_norm": 0.5962603092193604, "learning_rate": 1.496505052701372e-06, "loss": 0.494, "step": 2370 }, { "epoch": 4.453820909517112, "grad_norm": 0.5872151851654053, "learning_rate": 1.4466969005050013e-06, "loss": 0.5198, "step": 2375 }, { "epoch": 4.46319737458978, "grad_norm": 0.5666322112083435, "learning_rate": 1.3977070169178763e-06, "loss": 0.5284, "step": 2380 }, { "epoch": 4.472573839662447, "grad_norm": 0.5479874610900879, "learning_rate": 1.349537103904408e-06, "loss": 0.5223, "step": 2385 }, { "epoch": 4.481950304735115, "grad_norm": 0.598061740398407, "learning_rate": 1.3021888349423222e-06, "loss": 0.5128, "step": 2390 }, { "epoch": 4.491326769807783, "grad_norm": 0.5555986762046814, "learning_rate": 1.2556638549644644e-06, "loss": 0.5634, "step": 2395 }, { "epoch": 4.50070323488045, "grad_norm": 0.5764344930648804, "learning_rate": 1.2099637803016983e-06, "loss": 0.5168, "step": 2400 }, { "epoch": 4.510079699953118, "grad_norm": 0.5597651600837708, "learning_rate": 1.1650901986267365e-06, "loss": 0.4968, "step": 2405 }, { "epoch": 4.519456165025785, "grad_norm": 0.6328330039978027, "learning_rate": 1.1210446688989768e-06, "loss": 0.6302, "step": 2410 }, { "epoch": 4.528832630098453, "grad_norm": 0.6118944883346558, "learning_rate": 1.0778287213103478e-06, "loss": 0.5114, "step": 2415 }, { "epoch": 4.538209095171121, "grad_norm": 0.6393660306930542, "learning_rate": 1.0354438572321546e-06, "loss": 0.5136, "step": 2420 }, { "epoch": 4.547585560243788, "grad_norm": 0.5955559611320496, "learning_rate": 9.938915491629063e-07, "loss": 0.5265, "step": 2425 }, { "epoch": 4.556962025316456, "grad_norm": 0.635802686214447, "learning_rate": 9.531732406771771e-07, "loss": 0.5299, "step": 2430 }, { "epoch": 4.566338490389123, "grad_norm": 0.6105532050132751, "learning_rate": 9.132903463754256e-07, "loss": 0.594, "step": 2435 }, { "epoch": 4.575714955461791, "grad_norm": 0.5851595997810364, "learning_rate": 8.742442518348965e-07, "loss": 0.5352, "step": 2440 }, { "epoch": 4.585091420534458, "grad_norm": 0.573544442653656, "learning_rate": 8.360363135614307e-07, "loss": 0.5262, "step": 2445 }, { "epoch": 4.594467885607126, "grad_norm": 0.6063082814216614, "learning_rate": 7.986678589423758e-07, "loss": 0.5779, "step": 2450 }, { "epoch": 4.603844350679793, "grad_norm": 0.5579631328582764, "learning_rate": 7.621401862004634e-07, "loss": 0.5588, "step": 2455 }, { "epoch": 4.613220815752461, "grad_norm": 0.6332941651344299, "learning_rate": 7.264545643486997e-07, "loss": 0.5025, "step": 2460 }, { "epoch": 4.622597280825129, "grad_norm": 0.564562201499939, "learning_rate": 6.916122331462799e-07, "loss": 0.5156, "step": 2465 }, { "epoch": 4.631973745897796, "grad_norm": 0.5456069111824036, "learning_rate": 6.576144030555259e-07, "loss": 0.575, "step": 2470 }, { "epoch": 4.641350210970464, "grad_norm": 0.5309081077575684, "learning_rate": 6.244622551998203e-07, "loss": 0.5262, "step": 2475 }, { "epoch": 4.650726676043131, "grad_norm": 0.5958854556083679, "learning_rate": 5.921569413225913e-07, "loss": 0.5399, "step": 2480 }, { "epoch": 4.660103141115799, "grad_norm": 0.6013832092285156, "learning_rate": 5.606995837472817e-07, "loss": 0.5328, "step": 2485 }, { "epoch": 4.669479606188467, "grad_norm": 0.5663477182388306, "learning_rate": 5.300912753383625e-07, "loss": 0.5403, "step": 2490 }, { "epoch": 4.6788560712611345, "grad_norm": 0.539078950881958, "learning_rate": 5.003330794633776e-07, "loss": 0.5219, "step": 2495 }, { "epoch": 4.688232536333802, "grad_norm": 0.5885345339775085, "learning_rate": 4.714260299559875e-07, "loss": 0.5515, "step": 2500 }, { "epoch": 4.6976090014064695, "grad_norm": 0.6007012724876404, "learning_rate": 4.4337113108005314e-07, "loss": 0.527, "step": 2505 }, { "epoch": 4.7069854664791375, "grad_norm": 0.5390775799751282, "learning_rate": 4.161693574947556e-07, "loss": 0.5766, "step": 2510 }, { "epoch": 4.716361931551805, "grad_norm": 0.5515893697738647, "learning_rate": 3.8982165422073445e-07, "loss": 0.5084, "step": 2515 }, { "epoch": 4.725738396624473, "grad_norm": 0.5834362506866455, "learning_rate": 3.6432893660723886e-07, "loss": 0.5616, "step": 2520 }, { "epoch": 4.73511486169714, "grad_norm": 0.5748853087425232, "learning_rate": 3.396920903003559e-07, "loss": 0.5003, "step": 2525 }, { "epoch": 4.744491326769808, "grad_norm": 0.6511205434799194, "learning_rate": 3.1591197121222107e-07, "loss": 0.5369, "step": 2530 }, { "epoch": 4.753867791842476, "grad_norm": 0.6432448625564575, "learning_rate": 2.9298940549128964e-07, "loss": 0.5319, "step": 2535 }, { "epoch": 4.763244256915143, "grad_norm": 0.5946859121322632, "learning_rate": 2.7092518949362875e-07, "loss": 0.4929, "step": 2540 }, { "epoch": 4.772620721987811, "grad_norm": 0.5316891670227051, "learning_rate": 2.4972008975527593e-07, "loss": 0.5774, "step": 2545 }, { "epoch": 4.781997187060478, "grad_norm": 0.6336256265640259, "learning_rate": 2.2937484296556566e-07, "loss": 0.5231, "step": 2550 }, { "epoch": 4.791373652133146, "grad_norm": 0.5824437141418457, "learning_rate": 2.0989015594158058e-07, "loss": 0.5563, "step": 2555 }, { "epoch": 4.800750117205814, "grad_norm": 0.6376898288726807, "learning_rate": 1.9126670560356553e-07, "loss": 0.5601, "step": 2560 }, { "epoch": 4.810126582278481, "grad_norm": 0.610390305519104, "learning_rate": 1.735051389514214e-07, "loss": 0.5116, "step": 2565 }, { "epoch": 4.819503047351149, "grad_norm": 0.6232736706733704, "learning_rate": 1.5660607304223141e-07, "loss": 0.5159, "step": 2570 }, { "epoch": 4.828879512423816, "grad_norm": 0.6081536412239075, "learning_rate": 1.4057009496881158e-07, "loss": 0.5555, "step": 2575 }, { "epoch": 4.838255977496484, "grad_norm": 0.5945781469345093, "learning_rate": 1.2539776183932982e-07, "loss": 0.5433, "step": 2580 }, { "epoch": 4.847632442569151, "grad_norm": 0.574899435043335, "learning_rate": 1.1108960075794372e-07, "loss": 0.4752, "step": 2585 }, { "epoch": 4.857008907641819, "grad_norm": 0.5889243483543396, "learning_rate": 9.764610880648451e-08, "loss": 0.4921, "step": 2590 }, { "epoch": 4.866385372714487, "grad_norm": 0.5796253681182861, "learning_rate": 8.506775302719039e-08, "loss": 0.5313, "step": 2595 }, { "epoch": 4.875761837787154, "grad_norm": 0.5696360468864441, "learning_rate": 7.335497040648898e-08, "loss": 0.518, "step": 2600 }, { "epoch": 4.885138302859822, "grad_norm": 0.5847044587135315, "learning_rate": 6.250816785980385e-08, "loss": 0.5785, "step": 2605 }, { "epoch": 4.894514767932489, "grad_norm": 0.6327594518661499, "learning_rate": 5.2527722217421416e-08, "loss": 0.5209, "step": 2610 }, { "epoch": 4.903891233005157, "grad_norm": 0.6338078379631042, "learning_rate": 4.3413980211412516e-08, "loss": 0.5438, "step": 2615 }, { "epoch": 4.913267698077824, "grad_norm": 0.6505990624427795, "learning_rate": 3.516725846355873e-08, "loss": 0.4971, "step": 2620 }, { "epoch": 4.922644163150492, "grad_norm": 0.6756799817085266, "learning_rate": 2.7787843474386123e-08, "loss": 0.495, "step": 2625 }, { "epoch": 4.93202062822316, "grad_norm": 0.5888404250144958, "learning_rate": 2.127599161318161e-08, "loss": 0.5463, "step": 2630 }, { "epoch": 4.941397093295827, "grad_norm": 0.5684934258460999, "learning_rate": 1.5631929109102828e-08, "loss": 0.5461, "step": 2635 }, { "epoch": 4.950773558368495, "grad_norm": 0.5537897348403931, "learning_rate": 1.0855852043323289e-08, "loss": 0.5319, "step": 2640 }, { "epoch": 4.960150023441162, "grad_norm": 0.5860295295715332, "learning_rate": 6.947926342204536e-09, "loss": 0.5068, "step": 2645 }, { "epoch": 4.96952648851383, "grad_norm": 0.566766619682312, "learning_rate": 3.908287771542396e-09, "loss": 0.5091, "step": 2650 }, { "epoch": 4.978902953586498, "grad_norm": 0.5283293724060059, "learning_rate": 1.737041931845762e-09, "loss": 0.5747, "step": 2655 }, { "epoch": 4.9882794186591655, "grad_norm": 0.5808627009391785, "learning_rate": 4.3426425467008035e-10, "loss": 0.5346, "step": 2660 }, { "epoch": 4.9976558837318334, "grad_norm": 0.5620869398117065, "learning_rate": 0.0, "loss": 0.5285, "step": 2665 }, { "epoch": 4.9976558837318334, "step": 2665, "total_flos": 1.9473516408636703e+18, "train_loss": 0.5572177461119575, "train_runtime": 35175.961, "train_samples_per_second": 1.213, "train_steps_per_second": 0.076 } ], "logging_steps": 5, "max_steps": 2665, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 100, "total_flos": 1.9473516408636703e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }