{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 29704, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00033665499596014, "grad_norm": 1.8023041068681644, "learning_rate": 9.999999552565099e-06, "loss": 0.8554452896118164, "num_input_tokens_seen": 202080, "step": 5, "train_runtime": 21.3769, "train_tokens_per_second": 9453.194 }, { "epoch": 0.00067330999192028, "grad_norm": 1.4359019335235004, "learning_rate": 9.999997734860948e-06, "loss": 0.6747116565704345, "num_input_tokens_seen": 394008, "step": 10, "train_runtime": 39.2743, "train_tokens_per_second": 10032.219 }, { "epoch": 0.0010099649878804202, "grad_norm": 1.4195974341023023, "learning_rate": 9.999994518923374e-06, "loss": 0.6515717029571533, "num_input_tokens_seen": 594336, "step": 15, "train_runtime": 57.8089, "train_tokens_per_second": 10281.052 }, { "epoch": 0.00134661998384056, "grad_norm": 1.1626161311189784, "learning_rate": 9.999989904753278e-06, "loss": 0.6154236793518066, "num_input_tokens_seen": 798392, "step": 20, "train_runtime": 78.9937, "train_tokens_per_second": 10107.036 }, { "epoch": 0.0016832749798007002, "grad_norm": 1.2054081380400452, "learning_rate": 9.999983892351947e-06, "loss": 0.5996163368225098, "num_input_tokens_seen": 1004952, "step": 25, "train_runtime": 97.5889, "train_tokens_per_second": 10297.815 }, { "epoch": 0.0020199299757608404, "grad_norm": 1.1434073300784593, "learning_rate": 9.999976481721066e-06, "loss": 0.5232698440551757, "num_input_tokens_seen": 1210688, "step": 30, "train_runtime": 115.4617, "train_tokens_per_second": 10485.621 }, { "epoch": 0.0023565849717209803, "grad_norm": 1.1032791537249889, "learning_rate": 9.999967672862704e-06, "loss": 0.5547462940216065, "num_input_tokens_seen": 1411336, "step": 35, "train_runtime": 134.7359, "train_tokens_per_second": 10474.83 }, { "epoch": 0.00269323996768112, "grad_norm": 1.174762817493225, "learning_rate": 9.999957465779326e-06, "loss": 0.5217256546020508, "num_input_tokens_seen": 1617752, "step": 40, "train_runtime": 155.5415, "train_tokens_per_second": 10400.774 }, { "epoch": 0.0030298949636412605, "grad_norm": 1.2789484451347286, "learning_rate": 9.999945860473788e-06, "loss": 0.540006446838379, "num_input_tokens_seen": 1814224, "step": 45, "train_runtime": 177.027, "train_tokens_per_second": 10248.288 }, { "epoch": 0.0033665499596014004, "grad_norm": 0.9139480725228064, "learning_rate": 9.999932856949333e-06, "loss": 0.5196146011352539, "num_input_tokens_seen": 2020496, "step": 50, "train_runtime": 197.6036, "train_tokens_per_second": 10224.993 }, { "epoch": 0.0037032049555615404, "grad_norm": 1.003793599659393, "learning_rate": 9.999918455209599e-06, "loss": 0.504750919342041, "num_input_tokens_seen": 2232792, "step": 55, "train_runtime": 216.1346, "train_tokens_per_second": 10330.563 }, { "epoch": 0.004039859951521681, "grad_norm": 1.0720250564764418, "learning_rate": 9.99990265525861e-06, "loss": 0.525866174697876, "num_input_tokens_seen": 2439808, "step": 60, "train_runtime": 233.6348, "train_tokens_per_second": 10442.829 }, { "epoch": 0.004376514947481821, "grad_norm": 1.2743151107551811, "learning_rate": 9.999885457100789e-06, "loss": 0.5508274078369141, "num_input_tokens_seen": 2643312, "step": 65, "train_runtime": 250.9155, "train_tokens_per_second": 10534.669 }, { "epoch": 0.0047131699434419605, "grad_norm": 1.0515227504074804, "learning_rate": 9.999866860740943e-06, "loss": 0.5177194595336914, "num_input_tokens_seen": 2842304, "step": 70, "train_runtime": 270.3572, "train_tokens_per_second": 10513.143 }, { "epoch": 0.005049824939402101, "grad_norm": 0.9292754077434702, "learning_rate": 9.999846866184274e-06, "loss": 0.517300033569336, "num_input_tokens_seen": 3058344, "step": 75, "train_runtime": 291.8151, "train_tokens_per_second": 10480.419 }, { "epoch": 0.00538647993536224, "grad_norm": 0.9465566306463575, "learning_rate": 9.99982547343637e-06, "loss": 0.506367301940918, "num_input_tokens_seen": 3241376, "step": 80, "train_runtime": 309.9312, "train_tokens_per_second": 10458.374 }, { "epoch": 0.005723134931322381, "grad_norm": 1.0707574270850464, "learning_rate": 9.999802682503217e-06, "loss": 0.47463693618774416, "num_input_tokens_seen": 3447160, "step": 85, "train_runtime": 329.4975, "train_tokens_per_second": 10461.871 }, { "epoch": 0.006059789927282521, "grad_norm": 0.9767428779493836, "learning_rate": 9.999778493391186e-06, "loss": 0.5212706565856934, "num_input_tokens_seen": 3660656, "step": 90, "train_runtime": 349.4146, "train_tokens_per_second": 10476.54 }, { "epoch": 0.0063964449232426605, "grad_norm": 1.0369510607421957, "learning_rate": 9.999752906107043e-06, "loss": 0.5373851299285889, "num_input_tokens_seen": 3871264, "step": 95, "train_runtime": 368.2761, "train_tokens_per_second": 10511.853 }, { "epoch": 0.006733099919202801, "grad_norm": 1.0511914270717198, "learning_rate": 9.999725920657944e-06, "loss": 0.5242082595825195, "num_input_tokens_seen": 4073680, "step": 100, "train_runtime": 387.9704, "train_tokens_per_second": 10499.976 }, { "epoch": 0.007069754915162941, "grad_norm": 1.0504585010721366, "learning_rate": 9.999697537051432e-06, "loss": 0.49468517303466797, "num_input_tokens_seen": 4267152, "step": 105, "train_runtime": 406.4912, "train_tokens_per_second": 10497.527 }, { "epoch": 0.007406409911123081, "grad_norm": 1.0142939546163043, "learning_rate": 9.999667755295449e-06, "loss": 0.48414459228515627, "num_input_tokens_seen": 4470072, "step": 110, "train_runtime": 426.2655, "train_tokens_per_second": 10486.591 }, { "epoch": 0.007743064907083221, "grad_norm": 1.266355579860123, "learning_rate": 9.999636575398319e-06, "loss": 0.49400887489318845, "num_input_tokens_seen": 4670216, "step": 115, "train_runtime": 446.1848, "train_tokens_per_second": 10466.998 }, { "epoch": 0.008079719903043361, "grad_norm": 1.0026877251132427, "learning_rate": 9.999603997368766e-06, "loss": 0.4367683410644531, "num_input_tokens_seen": 4866064, "step": 120, "train_runtime": 464.9091, "train_tokens_per_second": 10466.7 }, { "epoch": 0.008416374899003501, "grad_norm": 1.055686797604033, "learning_rate": 9.999570021215895e-06, "loss": 0.4773660659790039, "num_input_tokens_seen": 5069768, "step": 125, "train_runtime": 482.9733, "train_tokens_per_second": 10496.994 }, { "epoch": 0.008753029894963642, "grad_norm": 0.9973922584534358, "learning_rate": 9.99953464694921e-06, "loss": 0.4965666770935059, "num_input_tokens_seen": 5264144, "step": 130, "train_runtime": 501.459, "train_tokens_per_second": 10497.655 }, { "epoch": 0.009089684890923782, "grad_norm": 1.095712357667202, "learning_rate": 9.999497874578606e-06, "loss": 0.5002108573913574, "num_input_tokens_seen": 5478800, "step": 135, "train_runtime": 521.4372, "train_tokens_per_second": 10507.114 }, { "epoch": 0.009426339886883921, "grad_norm": 1.0638737957219175, "learning_rate": 9.999459704114361e-06, "loss": 0.5046937942504883, "num_input_tokens_seen": 5684752, "step": 140, "train_runtime": 541.0901, "train_tokens_per_second": 10506.11 }, { "epoch": 0.00976299488284406, "grad_norm": 1.0253820752115312, "learning_rate": 9.999420135567153e-06, "loss": 0.5274062633514405, "num_input_tokens_seen": 5888432, "step": 145, "train_runtime": 562.2677, "train_tokens_per_second": 10472.648 }, { "epoch": 0.010099649878804202, "grad_norm": 1.0892945607288262, "learning_rate": 9.999379168948047e-06, "loss": 0.5096631050109863, "num_input_tokens_seen": 6098936, "step": 150, "train_runtime": 582.4879, "train_tokens_per_second": 10470.494 }, { "epoch": 0.010436304874764341, "grad_norm": 1.0649082442925186, "learning_rate": 9.999336804268496e-06, "loss": 0.47516622543334963, "num_input_tokens_seen": 6309240, "step": 155, "train_runtime": 602.9696, "train_tokens_per_second": 10463.611 }, { "epoch": 0.01077295987072448, "grad_norm": 1.160449453801732, "learning_rate": 9.999293041540351e-06, "loss": 0.5019990921020507, "num_input_tokens_seen": 6512664, "step": 160, "train_runtime": 622.7005, "train_tokens_per_second": 10458.743 }, { "epoch": 0.011109614866684622, "grad_norm": 1.6107719805714698, "learning_rate": 9.999247880775849e-06, "loss": 0.50371413230896, "num_input_tokens_seen": 6708232, "step": 165, "train_runtime": 642.4316, "train_tokens_per_second": 10441.939 }, { "epoch": 0.011446269862644761, "grad_norm": 1.0935245361967756, "learning_rate": 9.999201321987617e-06, "loss": 0.4693948745727539, "num_input_tokens_seen": 6912072, "step": 170, "train_runtime": 663.853, "train_tokens_per_second": 10412.053 }, { "epoch": 0.011782924858604901, "grad_norm": 0.9826839951197696, "learning_rate": 9.999153365188676e-06, "loss": 0.5085118770599365, "num_input_tokens_seen": 7119440, "step": 175, "train_runtime": 683.743, "train_tokens_per_second": 10412.451 }, { "epoch": 0.012119579854565042, "grad_norm": 1.1253193930985343, "learning_rate": 9.99910401039244e-06, "loss": 0.4652301788330078, "num_input_tokens_seen": 7316712, "step": 180, "train_runtime": 702.9735, "train_tokens_per_second": 10408.232 }, { "epoch": 0.012456234850525182, "grad_norm": 1.055097265903326, "learning_rate": 9.999053257612708e-06, "loss": 0.47227630615234373, "num_input_tokens_seen": 7529688, "step": 185, "train_runtime": 723.7943, "train_tokens_per_second": 10403.077 }, { "epoch": 0.012792889846485321, "grad_norm": 1.0675825328066881, "learning_rate": 9.999001106863672e-06, "loss": 0.5300945281982422, "num_input_tokens_seen": 7736240, "step": 190, "train_runtime": 742.8714, "train_tokens_per_second": 10413.969 }, { "epoch": 0.013129544842445462, "grad_norm": 0.9777433378316299, "learning_rate": 9.998947558159916e-06, "loss": 0.5001294136047363, "num_input_tokens_seen": 7947264, "step": 195, "train_runtime": 762.5097, "train_tokens_per_second": 10422.509 }, { "epoch": 0.013466199838405602, "grad_norm": 1.0461838406773292, "learning_rate": 9.99889261151642e-06, "loss": 0.44949703216552733, "num_input_tokens_seen": 8147392, "step": 200, "train_runtime": 780.9677, "train_tokens_per_second": 10432.432 }, { "epoch": 0.013802854834365741, "grad_norm": 1.0275597653488167, "learning_rate": 9.998836266948542e-06, "loss": 0.4723933219909668, "num_input_tokens_seen": 8345752, "step": 205, "train_runtime": 799.3643, "train_tokens_per_second": 10440.487 }, { "epoch": 0.014139509830325882, "grad_norm": 1.1823946349020005, "learning_rate": 9.998778524472043e-06, "loss": 0.446744441986084, "num_input_tokens_seen": 8541016, "step": 210, "train_runtime": 820.1014, "train_tokens_per_second": 10414.585 }, { "epoch": 0.014476164826286022, "grad_norm": 1.0869329500794649, "learning_rate": 9.99871938410307e-06, "loss": 0.4704752445220947, "num_input_tokens_seen": 8742272, "step": 215, "train_runtime": 838.0421, "train_tokens_per_second": 10431.781 }, { "epoch": 0.014812819822246161, "grad_norm": 0.9428032109790857, "learning_rate": 9.99865884585816e-06, "loss": 0.5175796985626221, "num_input_tokens_seen": 8943024, "step": 220, "train_runtime": 855.4802, "train_tokens_per_second": 10453.807 }, { "epoch": 0.015149474818206303, "grad_norm": 1.0622316324608152, "learning_rate": 9.998596909754245e-06, "loss": 0.4868607521057129, "num_input_tokens_seen": 9151664, "step": 225, "train_runtime": 874.4095, "train_tokens_per_second": 10466.108 }, { "epoch": 0.015486129814166442, "grad_norm": 1.0349827012403403, "learning_rate": 9.998533575808642e-06, "loss": 0.4580791473388672, "num_input_tokens_seen": 9351368, "step": 230, "train_runtime": 893.6414, "train_tokens_per_second": 10464.341 }, { "epoch": 0.015822784810126583, "grad_norm": 0.9205662554792616, "learning_rate": 9.998468844039064e-06, "loss": 0.4634833812713623, "num_input_tokens_seen": 9549632, "step": 235, "train_runtime": 912.1054, "train_tokens_per_second": 10469.877 }, { "epoch": 0.016159439806086723, "grad_norm": 1.011387422993793, "learning_rate": 9.998402714463613e-06, "loss": 0.5033318519592285, "num_input_tokens_seen": 9760016, "step": 240, "train_runtime": 931.6408, "train_tokens_per_second": 10476.158 }, { "epoch": 0.016496094802046862, "grad_norm": 0.8653016788275054, "learning_rate": 9.998335187100782e-06, "loss": 0.49373621940612794, "num_input_tokens_seen": 9965224, "step": 245, "train_runtime": 952.0081, "train_tokens_per_second": 10467.583 }, { "epoch": 0.016832749798007002, "grad_norm": 0.969873443531456, "learning_rate": 9.998266261969453e-06, "loss": 0.4993463039398193, "num_input_tokens_seen": 10169416, "step": 250, "train_runtime": 972.0428, "train_tokens_per_second": 10461.901 }, { "epoch": 0.01716940479396714, "grad_norm": 1.1014727604945351, "learning_rate": 9.998195939088905e-06, "loss": 0.4711878776550293, "num_input_tokens_seen": 10378512, "step": 255, "train_runtime": 989.5821, "train_tokens_per_second": 10487.773 }, { "epoch": 0.017506059789927284, "grad_norm": 0.928657289262277, "learning_rate": 9.998124218478797e-06, "loss": 0.48172731399536134, "num_input_tokens_seen": 10581400, "step": 260, "train_runtime": 1010.9029, "train_tokens_per_second": 10467.277 }, { "epoch": 0.017842714785887424, "grad_norm": 1.051757204359682, "learning_rate": 9.998051100159192e-06, "loss": 0.4902351379394531, "num_input_tokens_seen": 10795448, "step": 265, "train_runtime": 1029.5177, "train_tokens_per_second": 10485.927 }, { "epoch": 0.018179369781847563, "grad_norm": 1.0293251258187404, "learning_rate": 9.997976584150533e-06, "loss": 0.4981817722320557, "num_input_tokens_seen": 10994208, "step": 270, "train_runtime": 1047.6474, "train_tokens_per_second": 10494.187 }, { "epoch": 0.018516024777807703, "grad_norm": 0.8043284126132298, "learning_rate": 9.997900670473662e-06, "loss": 0.44077539443969727, "num_input_tokens_seen": 11209856, "step": 275, "train_runtime": 1067.1461, "train_tokens_per_second": 10504.518 }, { "epoch": 0.018852679773767842, "grad_norm": 0.9285214181981034, "learning_rate": 9.997823359149804e-06, "loss": 0.4723237991333008, "num_input_tokens_seen": 11412304, "step": 280, "train_runtime": 1085.7634, "train_tokens_per_second": 10510.857 }, { "epoch": 0.01918933476972798, "grad_norm": 0.9927920625010482, "learning_rate": 9.997744650200579e-06, "loss": 0.5116092681884765, "num_input_tokens_seen": 11620320, "step": 285, "train_runtime": 1106.2349, "train_tokens_per_second": 10504.388 }, { "epoch": 0.01952598976568812, "grad_norm": 1.0034649363240031, "learning_rate": 9.997664543648e-06, "loss": 0.4755118370056152, "num_input_tokens_seen": 11825712, "step": 290, "train_runtime": 1128.4284, "train_tokens_per_second": 10479.807 }, { "epoch": 0.019862644761648264, "grad_norm": 0.8966409279295605, "learning_rate": 9.997583039514469e-06, "loss": 0.478699779510498, "num_input_tokens_seen": 12033824, "step": 295, "train_runtime": 1149.2389, "train_tokens_per_second": 10471.125 }, { "epoch": 0.020199299757608404, "grad_norm": 1.0766041278347525, "learning_rate": 9.997500137822776e-06, "loss": 0.4873472213745117, "num_input_tokens_seen": 12243696, "step": 300, "train_runtime": 1169.1821, "train_tokens_per_second": 10472.018 }, { "epoch": 0.020535954753568543, "grad_norm": 1.135269746312447, "learning_rate": 9.997415838596106e-06, "loss": 0.47737894058227537, "num_input_tokens_seen": 12444896, "step": 305, "train_runtime": 1188.468, "train_tokens_per_second": 10471.376 }, { "epoch": 0.020872609749528682, "grad_norm": 0.9232597221890366, "learning_rate": 9.997330141858032e-06, "loss": 0.5105112075805665, "num_input_tokens_seen": 12649624, "step": 310, "train_runtime": 1207.4223, "train_tokens_per_second": 10476.554 }, { "epoch": 0.021209264745488822, "grad_norm": 1.080225592843678, "learning_rate": 9.997243047632519e-06, "loss": 0.4735543251037598, "num_input_tokens_seen": 12853352, "step": 315, "train_runtime": 1226.0596, "train_tokens_per_second": 10483.465 }, { "epoch": 0.02154591974144896, "grad_norm": 0.848973741612504, "learning_rate": 9.997154555943923e-06, "loss": 0.4395160675048828, "num_input_tokens_seen": 13060256, "step": 320, "train_runtime": 1247.0937, "train_tokens_per_second": 10472.554 }, { "epoch": 0.021882574737409104, "grad_norm": 1.1554690759229993, "learning_rate": 9.997064666816992e-06, "loss": 0.4580986022949219, "num_input_tokens_seen": 13265920, "step": 325, "train_runtime": 1267.209, "train_tokens_per_second": 10468.613 }, { "epoch": 0.022219229733369244, "grad_norm": 1.0778962349232601, "learning_rate": 9.996973380276858e-06, "loss": 0.5536511421203614, "num_input_tokens_seen": 13473776, "step": 330, "train_runtime": 1285.3052, "train_tokens_per_second": 10482.939 }, { "epoch": 0.022555884729329383, "grad_norm": 1.1003633558774037, "learning_rate": 9.996880696349053e-06, "loss": 0.4546688079833984, "num_input_tokens_seen": 13682944, "step": 335, "train_runtime": 1303.8293, "train_tokens_per_second": 10494.429 }, { "epoch": 0.022892539725289523, "grad_norm": 1.0554261152730464, "learning_rate": 9.996786615059497e-06, "loss": 0.541576337814331, "num_input_tokens_seen": 13895496, "step": 340, "train_runtime": 1323.576, "train_tokens_per_second": 10498.449 }, { "epoch": 0.023229194721249662, "grad_norm": 0.9791686105443802, "learning_rate": 9.996691136434498e-06, "loss": 0.43371267318725587, "num_input_tokens_seen": 14104224, "step": 345, "train_runtime": 1341.7749, "train_tokens_per_second": 10511.617 }, { "epoch": 0.023565849717209802, "grad_norm": 0.8635647316880177, "learning_rate": 9.996594260500753e-06, "loss": 0.5142106056213379, "num_input_tokens_seen": 14314904, "step": 350, "train_runtime": 1359.4661, "train_tokens_per_second": 10529.798 }, { "epoch": 0.023902504713169945, "grad_norm": 1.1863589693189929, "learning_rate": 9.996495987285358e-06, "loss": 0.4660197257995605, "num_input_tokens_seen": 14520832, "step": 355, "train_runtime": 1379.1711, "train_tokens_per_second": 10528.666 }, { "epoch": 0.024239159709130084, "grad_norm": 0.9976570668781082, "learning_rate": 9.996396316815793e-06, "loss": 0.4663111209869385, "num_input_tokens_seen": 14728800, "step": 360, "train_runtime": 1400.1629, "train_tokens_per_second": 10519.347 }, { "epoch": 0.024575814705090224, "grad_norm": 1.1410387661268238, "learning_rate": 9.99629524911993e-06, "loss": 0.46405839920043945, "num_input_tokens_seen": 14933584, "step": 365, "train_runtime": 1420.3128, "train_tokens_per_second": 10514.293 }, { "epoch": 0.024912469701050363, "grad_norm": 1.0325050157117646, "learning_rate": 9.996192784226033e-06, "loss": 0.4423470973968506, "num_input_tokens_seen": 15124256, "step": 370, "train_runtime": 1439.2817, "train_tokens_per_second": 10508.197 }, { "epoch": 0.025249124697010503, "grad_norm": 0.8749635304681062, "learning_rate": 9.996088922162755e-06, "loss": 0.46005868911743164, "num_input_tokens_seen": 15339936, "step": 375, "train_runtime": 1456.8714, "train_tokens_per_second": 10529.368 }, { "epoch": 0.025585779692970642, "grad_norm": 0.9180516945232349, "learning_rate": 9.995983662959141e-06, "loss": 0.46544342041015624, "num_input_tokens_seen": 15550448, "step": 380, "train_runtime": 1477.0867, "train_tokens_per_second": 10527.783 }, { "epoch": 0.025922434688930785, "grad_norm": 0.9068461598731318, "learning_rate": 9.995877006644627e-06, "loss": 0.48908586502075196, "num_input_tokens_seen": 15766728, "step": 385, "train_runtime": 1497.9284, "train_tokens_per_second": 10525.689 }, { "epoch": 0.026259089684890925, "grad_norm": 0.9380627134523101, "learning_rate": 9.995768953249038e-06, "loss": 0.48847532272338867, "num_input_tokens_seen": 15979896, "step": 390, "train_runtime": 1516.9818, "train_tokens_per_second": 10534.007 }, { "epoch": 0.026595744680851064, "grad_norm": 0.983580451312203, "learning_rate": 9.995659502802594e-06, "loss": 0.4660794258117676, "num_input_tokens_seen": 16185680, "step": 395, "train_runtime": 1536.6491, "train_tokens_per_second": 10533.101 }, { "epoch": 0.026932399676811204, "grad_norm": 0.9876299285732283, "learning_rate": 9.995548655335899e-06, "loss": 0.4908111572265625, "num_input_tokens_seen": 16385392, "step": 400, "train_runtime": 1556.3218, "train_tokens_per_second": 10528.28 }, { "epoch": 0.027269054672771343, "grad_norm": 0.9726806869903435, "learning_rate": 9.995436410879951e-06, "loss": 0.5063217639923095, "num_input_tokens_seen": 16595400, "step": 405, "train_runtime": 1575.4059, "train_tokens_per_second": 10534.047 }, { "epoch": 0.027605709668731482, "grad_norm": 1.0104302586464564, "learning_rate": 9.99532276946614e-06, "loss": 0.4342332363128662, "num_input_tokens_seen": 16798456, "step": 410, "train_runtime": 1595.4391, "train_tokens_per_second": 10529.049 }, { "epoch": 0.027942364664691625, "grad_norm": 0.9554901226987682, "learning_rate": 9.995207731126246e-06, "loss": 0.4849515914916992, "num_input_tokens_seen": 17010656, "step": 415, "train_runtime": 1615.2087, "train_tokens_per_second": 10531.553 }, { "epoch": 0.028279019660651765, "grad_norm": 0.9354606426860639, "learning_rate": 9.99509129589244e-06, "loss": 0.4621271133422852, "num_input_tokens_seen": 17213768, "step": 420, "train_runtime": 1634.7443, "train_tokens_per_second": 10529.946 }, { "epoch": 0.028615674656611904, "grad_norm": 0.9331632466037965, "learning_rate": 9.994973463797279e-06, "loss": 0.4625368118286133, "num_input_tokens_seen": 17426568, "step": 425, "train_runtime": 1653.2567, "train_tokens_per_second": 10540.751 }, { "epoch": 0.028952329652572044, "grad_norm": 0.850776462767769, "learning_rate": 9.99485423487372e-06, "loss": 0.4355166912078857, "num_input_tokens_seen": 17630592, "step": 430, "train_runtime": 1674.469, "train_tokens_per_second": 10529.065 }, { "epoch": 0.029288984648532183, "grad_norm": 0.9802399454138695, "learning_rate": 9.994733609155097e-06, "loss": 0.4691582202911377, "num_input_tokens_seen": 17832328, "step": 435, "train_runtime": 1694.2127, "train_tokens_per_second": 10525.436 }, { "epoch": 0.029625639644492323, "grad_norm": 1.0002320073541695, "learning_rate": 9.994611586675149e-06, "loss": 0.4469753265380859, "num_input_tokens_seen": 18043720, "step": 440, "train_runtime": 1712.053, "train_tokens_per_second": 10539.23 }, { "epoch": 0.029962294640452466, "grad_norm": 0.9695297491270629, "learning_rate": 9.994488167468e-06, "loss": 0.4620168685913086, "num_input_tokens_seen": 18246360, "step": 445, "train_runtime": 1731.6059, "train_tokens_per_second": 10537.247 }, { "epoch": 0.030298949636412605, "grad_norm": 0.8750552094360504, "learning_rate": 9.994363351568158e-06, "loss": 0.49673948287963865, "num_input_tokens_seen": 18448024, "step": 450, "train_runtime": 1751.0482, "train_tokens_per_second": 10535.418 }, { "epoch": 0.030635604632372745, "grad_norm": 0.8516233763938397, "learning_rate": 9.994237139010532e-06, "loss": 0.4327442169189453, "num_input_tokens_seen": 18644944, "step": 455, "train_runtime": 1770.5886, "train_tokens_per_second": 10530.365 }, { "epoch": 0.030972259628332884, "grad_norm": 0.9208625404639668, "learning_rate": 9.994109529830414e-06, "loss": 0.4723031044006348, "num_input_tokens_seen": 18865752, "step": 460, "train_runtime": 1789.2843, "train_tokens_per_second": 10543.742 }, { "epoch": 0.03130891462429303, "grad_norm": 0.8545596179906617, "learning_rate": 9.993980524063494e-06, "loss": 0.44826245307922363, "num_input_tokens_seen": 19074112, "step": 465, "train_runtime": 1808.2496, "train_tokens_per_second": 10548.385 }, { "epoch": 0.03164556962025317, "grad_norm": 0.8843265387452625, "learning_rate": 9.993850121745842e-06, "loss": 0.45360565185546875, "num_input_tokens_seen": 19280592, "step": 470, "train_runtime": 1826.8371, "train_tokens_per_second": 10554.084 }, { "epoch": 0.031982224616213306, "grad_norm": 0.9124844133316536, "learning_rate": 9.99371832291393e-06, "loss": 0.4445066452026367, "num_input_tokens_seen": 19485712, "step": 475, "train_runtime": 1847.0554, "train_tokens_per_second": 10549.609 }, { "epoch": 0.032318879612173446, "grad_norm": 0.9773608296328672, "learning_rate": 9.993585127604612e-06, "loss": 0.4446268558502197, "num_input_tokens_seen": 19678904, "step": 480, "train_runtime": 1866.1167, "train_tokens_per_second": 10545.377 }, { "epoch": 0.032655534608133585, "grad_norm": 0.8968516831630639, "learning_rate": 9.993450535855136e-06, "loss": 0.46390414237976074, "num_input_tokens_seen": 19871568, "step": 485, "train_runtime": 1884.7149, "train_tokens_per_second": 10543.54 }, { "epoch": 0.032992189604093725, "grad_norm": 1.0322095045042465, "learning_rate": 9.993314547703142e-06, "loss": 0.438554573059082, "num_input_tokens_seen": 20079968, "step": 490, "train_runtime": 1905.2707, "train_tokens_per_second": 10539.168 }, { "epoch": 0.033328844600053864, "grad_norm": 0.8910181379539883, "learning_rate": 9.993177163186655e-06, "loss": 0.4378040790557861, "num_input_tokens_seen": 20282200, "step": 495, "train_runtime": 1923.1871, "train_tokens_per_second": 10546.14 }, { "epoch": 0.033665499596014004, "grad_norm": 0.9882353891670147, "learning_rate": 9.993038382344097e-06, "loss": 0.44132280349731445, "num_input_tokens_seen": 20485712, "step": 500, "train_runtime": 1942.896, "train_tokens_per_second": 10543.906 }, { "epoch": 0.03400215459197414, "grad_norm": 0.8996381671222595, "learning_rate": 9.992898205214279e-06, "loss": 0.44514875411987304, "num_input_tokens_seen": 20691560, "step": 505, "train_runtime": 1961.1988, "train_tokens_per_second": 10550.466 }, { "epoch": 0.03433880958793428, "grad_norm": 1.057503460105163, "learning_rate": 9.992756631836397e-06, "loss": 0.44048752784729006, "num_input_tokens_seen": 20897432, "step": 510, "train_runtime": 1981.7067, "train_tokens_per_second": 10545.169 }, { "epoch": 0.03467546458389442, "grad_norm": 0.8503266699015379, "learning_rate": 9.992613662250044e-06, "loss": 0.4641111373901367, "num_input_tokens_seen": 21105408, "step": 515, "train_runtime": 2001.396, "train_tokens_per_second": 10545.344 }, { "epoch": 0.03501211957985457, "grad_norm": 0.9253026000775727, "learning_rate": 9.992469296495201e-06, "loss": 0.4584599494934082, "num_input_tokens_seen": 21318248, "step": 520, "train_runtime": 2020.9593, "train_tokens_per_second": 10548.579 }, { "epoch": 0.03534877457581471, "grad_norm": 0.838824919481942, "learning_rate": 9.992323534612238e-06, "loss": 0.41715059280395506, "num_input_tokens_seen": 21527856, "step": 525, "train_runtime": 2040.6733, "train_tokens_per_second": 10549.389 }, { "epoch": 0.03568542957177485, "grad_norm": 0.9293631443991255, "learning_rate": 9.99217637664192e-06, "loss": 0.45984373092651365, "num_input_tokens_seen": 21737832, "step": 530, "train_runtime": 2060.4271, "train_tokens_per_second": 10550.158 }, { "epoch": 0.03602208456773499, "grad_norm": 0.8739400158489766, "learning_rate": 9.992027822625397e-06, "loss": 0.45856523513793945, "num_input_tokens_seen": 21936952, "step": 535, "train_runtime": 2080.2976, "train_tokens_per_second": 10545.103 }, { "epoch": 0.036358739563695126, "grad_norm": 0.9659397561527802, "learning_rate": 9.99187787260421e-06, "loss": 0.4660188674926758, "num_input_tokens_seen": 22136808, "step": 540, "train_runtime": 2098.4349, "train_tokens_per_second": 10549.199 }, { "epoch": 0.036695394559655266, "grad_norm": 0.8361100737676761, "learning_rate": 9.991726526620294e-06, "loss": 0.4365182876586914, "num_input_tokens_seen": 22353536, "step": 545, "train_runtime": 2116.8239, "train_tokens_per_second": 10559.941 }, { "epoch": 0.037032049555615405, "grad_norm": 0.9164643032167938, "learning_rate": 9.991573784715973e-06, "loss": 0.47978858947753905, "num_input_tokens_seen": 22559024, "step": 550, "train_runtime": 2137.0623, "train_tokens_per_second": 10556.091 }, { "epoch": 0.037368704551575545, "grad_norm": 1.0079686263797893, "learning_rate": 9.99141964693396e-06, "loss": 0.4823866844177246, "num_input_tokens_seen": 22767904, "step": 555, "train_runtime": 2156.1014, "train_tokens_per_second": 10559.755 }, { "epoch": 0.037705359547535684, "grad_norm": 0.8619825269986808, "learning_rate": 9.99126411331736e-06, "loss": 0.4420760154724121, "num_input_tokens_seen": 22980288, "step": 560, "train_runtime": 2175.7554, "train_tokens_per_second": 10561.981 }, { "epoch": 0.038042014543495824, "grad_norm": 0.9349450526682583, "learning_rate": 9.991107183909665e-06, "loss": 0.4685372352600098, "num_input_tokens_seen": 23190024, "step": 565, "train_runtime": 2194.3404, "train_tokens_per_second": 10568.107 }, { "epoch": 0.03837866953945596, "grad_norm": 0.9265865452202805, "learning_rate": 9.990948858754763e-06, "loss": 0.46530303955078123, "num_input_tokens_seen": 23388312, "step": 570, "train_runtime": 2214.9114, "train_tokens_per_second": 10559.48 }, { "epoch": 0.0387153245354161, "grad_norm": 0.8191470446321233, "learning_rate": 9.990789137896927e-06, "loss": 0.46095619201660154, "num_input_tokens_seen": 23598320, "step": 575, "train_runtime": 2235.2619, "train_tokens_per_second": 10557.295 }, { "epoch": 0.03905197953137624, "grad_norm": 0.968397425753136, "learning_rate": 9.990628021380823e-06, "loss": 0.48248538970947263, "num_input_tokens_seen": 23803048, "step": 580, "train_runtime": 2254.2349, "train_tokens_per_second": 10559.258 }, { "epoch": 0.03938863452733639, "grad_norm": 1.1134437829578399, "learning_rate": 9.990465509251508e-06, "loss": 0.4651199817657471, "num_input_tokens_seen": 24000672, "step": 585, "train_runtime": 2272.8288, "train_tokens_per_second": 10559.824 }, { "epoch": 0.03972528952329653, "grad_norm": 0.9917016248066278, "learning_rate": 9.990301601554425e-06, "loss": 0.48305377960205076, "num_input_tokens_seen": 24189776, "step": 590, "train_runtime": 2292.2923, "train_tokens_per_second": 10552.658 }, { "epoch": 0.04006194451925667, "grad_norm": 0.8712929843764018, "learning_rate": 9.990136298335414e-06, "loss": 0.41217827796936035, "num_input_tokens_seen": 24393464, "step": 595, "train_runtime": 2311.0522, "train_tokens_per_second": 10555.133 }, { "epoch": 0.04039859951521681, "grad_norm": 0.8777934383467562, "learning_rate": 9.989969599640698e-06, "loss": 0.43137211799621583, "num_input_tokens_seen": 24607424, "step": 600, "train_runtime": 2329.1884, "train_tokens_per_second": 10564.806 }, { "epoch": 0.040735254511176947, "grad_norm": 0.9300053437477424, "learning_rate": 9.989801505516895e-06, "loss": 0.5046572685241699, "num_input_tokens_seen": 24822912, "step": 605, "train_runtime": 2347.31, "train_tokens_per_second": 10575.046 }, { "epoch": 0.041071909507137086, "grad_norm": 0.982200917764079, "learning_rate": 9.989632016011012e-06, "loss": 0.47648916244506834, "num_input_tokens_seen": 25031536, "step": 610, "train_runtime": 2365.4912, "train_tokens_per_second": 10581.961 }, { "epoch": 0.041408564503097225, "grad_norm": 1.00359192428285, "learning_rate": 9.989461131170448e-06, "loss": 0.4821319580078125, "num_input_tokens_seen": 25220624, "step": 615, "train_runtime": 2385.4629, "train_tokens_per_second": 10572.633 }, { "epoch": 0.041745219499057365, "grad_norm": 0.8342666232305305, "learning_rate": 9.98928885104299e-06, "loss": 0.4485942840576172, "num_input_tokens_seen": 25426248, "step": 620, "train_runtime": 2404.4989, "train_tokens_per_second": 10574.448 }, { "epoch": 0.042081874495017504, "grad_norm": 0.7955779765083809, "learning_rate": 9.989115175676812e-06, "loss": 0.43010311126708983, "num_input_tokens_seen": 25636032, "step": 625, "train_runtime": 2422.7055, "train_tokens_per_second": 10581.572 }, { "epoch": 0.042418529490977644, "grad_norm": 0.9264471062856978, "learning_rate": 9.988940105120483e-06, "loss": 0.47361955642700193, "num_input_tokens_seen": 25836016, "step": 630, "train_runtime": 2441.9321, "train_tokens_per_second": 10580.153 }, { "epoch": 0.04275518448693778, "grad_norm": 0.8601233182627043, "learning_rate": 9.988763639422965e-06, "loss": 0.48220529556274416, "num_input_tokens_seen": 26049032, "step": 635, "train_runtime": 2461.0384, "train_tokens_per_second": 10584.569 }, { "epoch": 0.04309183948289792, "grad_norm": 0.8978216144473047, "learning_rate": 9.988585778633604e-06, "loss": 0.44269633293151855, "num_input_tokens_seen": 26237784, "step": 640, "train_runtime": 2479.4494, "train_tokens_per_second": 10582.101 }, { "epoch": 0.04342849447885807, "grad_norm": 0.9755954378961985, "learning_rate": 9.988406522802134e-06, "loss": 0.4528481960296631, "num_input_tokens_seen": 26435192, "step": 645, "train_runtime": 2498.11, "train_tokens_per_second": 10582.077 }, { "epoch": 0.04376514947481821, "grad_norm": 0.8585086785068149, "learning_rate": 9.98822587197869e-06, "loss": 0.4157420635223389, "num_input_tokens_seen": 26637728, "step": 650, "train_runtime": 2517.036, "train_tokens_per_second": 10582.975 }, { "epoch": 0.04410180447077835, "grad_norm": 0.9450527071495605, "learning_rate": 9.988043826213785e-06, "loss": 0.43828706741333007, "num_input_tokens_seen": 26834240, "step": 655, "train_runtime": 2535.0204, "train_tokens_per_second": 10585.414 }, { "epoch": 0.04443845946673849, "grad_norm": 0.862605389970749, "learning_rate": 9.98786038555833e-06, "loss": 0.4042038917541504, "num_input_tokens_seen": 27041424, "step": 660, "train_runtime": 2553.8782, "train_tokens_per_second": 10588.377 }, { "epoch": 0.04477511446269863, "grad_norm": 0.814466378236778, "learning_rate": 9.987675550063625e-06, "loss": 0.45628890991210935, "num_input_tokens_seen": 27255448, "step": 665, "train_runtime": 2572.6105, "train_tokens_per_second": 10594.471 }, { "epoch": 0.04511176945865877, "grad_norm": 0.953664396617726, "learning_rate": 9.987489319781355e-06, "loss": 0.4485955238342285, "num_input_tokens_seen": 27461216, "step": 670, "train_runtime": 2590.4288, "train_tokens_per_second": 10601.031 }, { "epoch": 0.045448424454618906, "grad_norm": 0.7598877639999213, "learning_rate": 9.987301694763602e-06, "loss": 0.48266754150390623, "num_input_tokens_seen": 27664280, "step": 675, "train_runtime": 2609.969, "train_tokens_per_second": 10599.467 }, { "epoch": 0.045785079450579046, "grad_norm": 0.8882568347275471, "learning_rate": 9.987112675062834e-06, "loss": 0.4167341232299805, "num_input_tokens_seen": 27866896, "step": 680, "train_runtime": 2629.7068, "train_tokens_per_second": 10596.959 }, { "epoch": 0.046121734446539185, "grad_norm": 0.9406161265273447, "learning_rate": 9.986922260731908e-06, "loss": 0.4289733409881592, "num_input_tokens_seen": 28064344, "step": 685, "train_runtime": 2648.9641, "train_tokens_per_second": 10594.46 }, { "epoch": 0.046458389442499325, "grad_norm": 0.8659455025772859, "learning_rate": 9.986730451824073e-06, "loss": 0.46906251907348634, "num_input_tokens_seen": 28266584, "step": 690, "train_runtime": 2669.8514, "train_tokens_per_second": 10587.325 }, { "epoch": 0.046795044438459464, "grad_norm": 0.8435296284822515, "learning_rate": 9.986537248392969e-06, "loss": 0.48019771575927733, "num_input_tokens_seen": 28476208, "step": 695, "train_runtime": 2689.2063, "train_tokens_per_second": 10589.075 }, { "epoch": 0.047131699434419604, "grad_norm": 0.9682830256795324, "learning_rate": 9.986342650492626e-06, "loss": 0.4483360290527344, "num_input_tokens_seen": 28684352, "step": 700, "train_runtime": 2707.9178, "train_tokens_per_second": 10592.77 }, { "epoch": 0.04746835443037975, "grad_norm": 0.8749077522442358, "learning_rate": 9.98614665817746e-06, "loss": 0.423960018157959, "num_input_tokens_seen": 28872896, "step": 705, "train_runtime": 2727.4832, "train_tokens_per_second": 10585.911 }, { "epoch": 0.04780500942633989, "grad_norm": 0.8877652117571686, "learning_rate": 9.98594927150228e-06, "loss": 0.4373324394226074, "num_input_tokens_seen": 29089272, "step": 710, "train_runtime": 2747.0424, "train_tokens_per_second": 10589.306 }, { "epoch": 0.04814166442230003, "grad_norm": 0.7650381560236775, "learning_rate": 9.985750490522286e-06, "loss": 0.39348363876342773, "num_input_tokens_seen": 29291760, "step": 715, "train_runtime": 2765.9708, "train_tokens_per_second": 10590.047 }, { "epoch": 0.04847831941826017, "grad_norm": 0.9257738169684695, "learning_rate": 9.985550315293066e-06, "loss": 0.46934804916381834, "num_input_tokens_seen": 29507800, "step": 720, "train_runtime": 2785.806, "train_tokens_per_second": 10592.195 }, { "epoch": 0.04881497441422031, "grad_norm": 0.9616526088499284, "learning_rate": 9.985348745870598e-06, "loss": 0.46381025314331054, "num_input_tokens_seen": 29719040, "step": 725, "train_runtime": 2803.9614, "train_tokens_per_second": 10598.948 }, { "epoch": 0.04915162941018045, "grad_norm": 0.8438120420572233, "learning_rate": 9.98514578231125e-06, "loss": 0.4180117130279541, "num_input_tokens_seen": 29933400, "step": 730, "train_runtime": 2821.9744, "train_tokens_per_second": 10607.254 }, { "epoch": 0.04948828440614059, "grad_norm": 0.9003967295108559, "learning_rate": 9.984941424671781e-06, "loss": 0.4702353000640869, "num_input_tokens_seen": 30138952, "step": 735, "train_runtime": 2840.9762, "train_tokens_per_second": 10608.66 }, { "epoch": 0.049824939402100726, "grad_norm": 0.8574139757989973, "learning_rate": 9.984735673009337e-06, "loss": 0.43060693740844724, "num_input_tokens_seen": 30347968, "step": 740, "train_runtime": 2861.7341, "train_tokens_per_second": 10604.748 }, { "epoch": 0.050161594398060866, "grad_norm": 0.7957932152450856, "learning_rate": 9.984528527381458e-06, "loss": 0.45335874557495115, "num_input_tokens_seen": 30554992, "step": 745, "train_runtime": 2881.6464, "train_tokens_per_second": 10603.311 }, { "epoch": 0.050498249394021005, "grad_norm": 0.88283447768756, "learning_rate": 9.984319987846072e-06, "loss": 0.44902429580688474, "num_input_tokens_seen": 30756432, "step": 750, "train_runtime": 2901.9708, "train_tokens_per_second": 10598.464 }, { "epoch": 0.050834904389981145, "grad_norm": 0.8531447200564191, "learning_rate": 9.984110054461495e-06, "loss": 0.4439187526702881, "num_input_tokens_seen": 30977920, "step": 755, "train_runtime": 2921.4102, "train_tokens_per_second": 10603.756 }, { "epoch": 0.051171559385941284, "grad_norm": 0.8418690950417069, "learning_rate": 9.983898727286435e-06, "loss": 0.44115710258483887, "num_input_tokens_seen": 31184216, "step": 760, "train_runtime": 2940.0158, "train_tokens_per_second": 10606.819 }, { "epoch": 0.05150821438190143, "grad_norm": 0.9025145700098686, "learning_rate": 9.983686006379985e-06, "loss": 0.4564334869384766, "num_input_tokens_seen": 31387904, "step": 765, "train_runtime": 2957.8092, "train_tokens_per_second": 10611.876 }, { "epoch": 0.05184486937786157, "grad_norm": 0.9016512209550924, "learning_rate": 9.983471891801638e-06, "loss": 0.4442739486694336, "num_input_tokens_seen": 31600208, "step": 770, "train_runtime": 2976.9945, "train_tokens_per_second": 10614.802 }, { "epoch": 0.05218152437382171, "grad_norm": 0.882696125503099, "learning_rate": 9.983256383611267e-06, "loss": 0.4449764251708984, "num_input_tokens_seen": 31808136, "step": 775, "train_runtime": 2996.9081, "train_tokens_per_second": 10613.651 }, { "epoch": 0.05251817936978185, "grad_norm": 0.8227484491915815, "learning_rate": 9.983039481869138e-06, "loss": 0.42351551055908204, "num_input_tokens_seen": 32013400, "step": 780, "train_runtime": 3016.1283, "train_tokens_per_second": 10614.071 }, { "epoch": 0.05285483436574199, "grad_norm": 0.8705299534952147, "learning_rate": 9.98282118663591e-06, "loss": 0.43862152099609375, "num_input_tokens_seen": 32224024, "step": 785, "train_runtime": 3036.1101, "train_tokens_per_second": 10613.589 }, { "epoch": 0.05319148936170213, "grad_norm": 0.879202433461479, "learning_rate": 9.982601497972624e-06, "loss": 0.45266385078430177, "num_input_tokens_seen": 32428104, "step": 790, "train_runtime": 3055.4112, "train_tokens_per_second": 10613.336 }, { "epoch": 0.05352814435766227, "grad_norm": 0.8675698224740415, "learning_rate": 9.982380415940717e-06, "loss": 0.42397642135620117, "num_input_tokens_seen": 32625936, "step": 795, "train_runtime": 3074.2381, "train_tokens_per_second": 10612.69 }, { "epoch": 0.05386479935362241, "grad_norm": 0.8362235341026091, "learning_rate": 9.982157940602015e-06, "loss": 0.47054805755615237, "num_input_tokens_seen": 32841240, "step": 800, "train_runtime": 3093.8022, "train_tokens_per_second": 10615.171 }, { "epoch": 0.05420145434958255, "grad_norm": 0.8700470745399767, "learning_rate": 9.981934072018732e-06, "loss": 0.4464433670043945, "num_input_tokens_seen": 33057824, "step": 805, "train_runtime": 3112.9477, "train_tokens_per_second": 10619.46 }, { "epoch": 0.054538109345542686, "grad_norm": 0.9594868829841791, "learning_rate": 9.981708810253472e-06, "loss": 0.46278038024902346, "num_input_tokens_seen": 33264784, "step": 810, "train_runtime": 3132.1005, "train_tokens_per_second": 10620.599 }, { "epoch": 0.054874764341502826, "grad_norm": 0.9906973853521399, "learning_rate": 9.981482155369229e-06, "loss": 0.45875964164733884, "num_input_tokens_seen": 33476696, "step": 815, "train_runtime": 3153.1058, "train_tokens_per_second": 10617.054 }, { "epoch": 0.055211419337462965, "grad_norm": 0.9896968718359188, "learning_rate": 9.981254107429385e-06, "loss": 0.4071864128112793, "num_input_tokens_seen": 33675648, "step": 820, "train_runtime": 3173.3864, "train_tokens_per_second": 10611.897 }, { "epoch": 0.05554807433342311, "grad_norm": 0.8358796531877521, "learning_rate": 9.981024666497716e-06, "loss": 0.41853628158569334, "num_input_tokens_seen": 33880336, "step": 825, "train_runtime": 3192.4859, "train_tokens_per_second": 10612.525 }, { "epoch": 0.05588472932938325, "grad_norm": 0.9792634348670534, "learning_rate": 9.98079383263838e-06, "loss": 0.4510931968688965, "num_input_tokens_seen": 34073528, "step": 830, "train_runtime": 3211.6726, "train_tokens_per_second": 10609.278 }, { "epoch": 0.05622138432534339, "grad_norm": 0.9649757470380363, "learning_rate": 9.980561605915932e-06, "loss": 0.4359869956970215, "num_input_tokens_seen": 34283752, "step": 835, "train_runtime": 3230.0878, "train_tokens_per_second": 10613.876 }, { "epoch": 0.05655803932130353, "grad_norm": 0.8103551506807546, "learning_rate": 9.980327986395316e-06, "loss": 0.4525885581970215, "num_input_tokens_seen": 34487896, "step": 840, "train_runtime": 3251.681, "train_tokens_per_second": 10606.174 }, { "epoch": 0.05689469431726367, "grad_norm": 0.872095650653209, "learning_rate": 9.980092974141855e-06, "loss": 0.4294156074523926, "num_input_tokens_seen": 34701328, "step": 845, "train_runtime": 3270.9078, "train_tokens_per_second": 10609.082 }, { "epoch": 0.05723134931322381, "grad_norm": 1.521941304968622, "learning_rate": 9.979856569221276e-06, "loss": 0.4327985763549805, "num_input_tokens_seen": 34910168, "step": 850, "train_runtime": 3290.9513, "train_tokens_per_second": 10607.926 }, { "epoch": 0.05756800430918395, "grad_norm": 0.959838649243433, "learning_rate": 9.979618771699688e-06, "loss": 0.4831608772277832, "num_input_tokens_seen": 35118808, "step": 855, "train_runtime": 3309.2473, "train_tokens_per_second": 10612.325 }, { "epoch": 0.05790465930514409, "grad_norm": 1.0100168894066364, "learning_rate": 9.979379581643588e-06, "loss": 0.4275313377380371, "num_input_tokens_seen": 35324616, "step": 860, "train_runtime": 3329.0495, "train_tokens_per_second": 10611.022 }, { "epoch": 0.05824131430110423, "grad_norm": 0.8971588385803994, "learning_rate": 9.979138999119866e-06, "loss": 0.4643044948577881, "num_input_tokens_seen": 35529360, "step": 865, "train_runtime": 3349.9667, "train_tokens_per_second": 10605.884 }, { "epoch": 0.05857796929706437, "grad_norm": 0.8294770789854748, "learning_rate": 9.978897024195801e-06, "loss": 0.444273853302002, "num_input_tokens_seen": 35751520, "step": 870, "train_runtime": 3369.6009, "train_tokens_per_second": 10610.016 }, { "epoch": 0.058914624293024506, "grad_norm": 0.8606387723972748, "learning_rate": 9.978653656939058e-06, "loss": 0.4298581600189209, "num_input_tokens_seen": 35959280, "step": 875, "train_runtime": 3390.2095, "train_tokens_per_second": 10606.802 }, { "epoch": 0.059251279288984646, "grad_norm": 1.1924278867529137, "learning_rate": 9.978408897417699e-06, "loss": 0.4600965976715088, "num_input_tokens_seen": 36171424, "step": 880, "train_runtime": 3410.4378, "train_tokens_per_second": 10606.094 }, { "epoch": 0.059587934284944785, "grad_norm": 0.7821125101333485, "learning_rate": 9.978162745700165e-06, "loss": 0.4377596378326416, "num_input_tokens_seen": 36382832, "step": 885, "train_runtime": 3429.6901, "train_tokens_per_second": 10608.198 }, { "epoch": 0.05992458928090493, "grad_norm": 0.8484492064368293, "learning_rate": 9.977915201855293e-06, "loss": 0.42601475715637205, "num_input_tokens_seen": 36588552, "step": 890, "train_runtime": 3447.8685, "train_tokens_per_second": 10611.934 }, { "epoch": 0.06026124427686507, "grad_norm": 1.000729139224448, "learning_rate": 9.977666265952309e-06, "loss": 0.44201860427856443, "num_input_tokens_seen": 36793472, "step": 895, "train_runtime": 3467.3819, "train_tokens_per_second": 10611.312 }, { "epoch": 0.06059789927282521, "grad_norm": 0.9074205352397163, "learning_rate": 9.977415938060823e-06, "loss": 0.44513835906982424, "num_input_tokens_seen": 37000024, "step": 900, "train_runtime": 3485.8387, "train_tokens_per_second": 10614.382 }, { "epoch": 0.06093455426878535, "grad_norm": 0.9028478468312564, "learning_rate": 9.977164218250846e-06, "loss": 0.44185695648193357, "num_input_tokens_seen": 37204648, "step": 905, "train_runtime": 3506.4516, "train_tokens_per_second": 10610.341 }, { "epoch": 0.06127120926474549, "grad_norm": 0.8187437352468376, "learning_rate": 9.976911106592765e-06, "loss": 0.4089504718780518, "num_input_tokens_seen": 37404736, "step": 910, "train_runtime": 3524.8048, "train_tokens_per_second": 10611.86 }, { "epoch": 0.06160786426070563, "grad_norm": 0.7975997575442423, "learning_rate": 9.976656603157363e-06, "loss": 0.4435403823852539, "num_input_tokens_seen": 37608736, "step": 915, "train_runtime": 3543.1773, "train_tokens_per_second": 10614.41 }, { "epoch": 0.06194451925666577, "grad_norm": 0.8711688076660334, "learning_rate": 9.976400708015811e-06, "loss": 0.42921199798583987, "num_input_tokens_seen": 37808616, "step": 920, "train_runtime": 3561.4586, "train_tokens_per_second": 10616.048 }, { "epoch": 0.06228117425262591, "grad_norm": 0.8042252004207933, "learning_rate": 9.97614342123967e-06, "loss": 0.4245273590087891, "num_input_tokens_seen": 38025904, "step": 925, "train_runtime": 3580.0396, "train_tokens_per_second": 10621.643 }, { "epoch": 0.06261782924858605, "grad_norm": 0.9446053617135461, "learning_rate": 9.97588474290089e-06, "loss": 0.4290931701660156, "num_input_tokens_seen": 38230320, "step": 930, "train_runtime": 3601.8973, "train_tokens_per_second": 10613.94 }, { "epoch": 0.0629544842445462, "grad_norm": 1.0572717263829843, "learning_rate": 9.975624673071806e-06, "loss": 0.4401254653930664, "num_input_tokens_seen": 38433480, "step": 935, "train_runtime": 3622.6974, "train_tokens_per_second": 10609.078 }, { "epoch": 0.06329113924050633, "grad_norm": 1.0184743339864808, "learning_rate": 9.97536321182515e-06, "loss": 0.4074659824371338, "num_input_tokens_seen": 38629536, "step": 940, "train_runtime": 3640.3716, "train_tokens_per_second": 10611.427 }, { "epoch": 0.06362779423646647, "grad_norm": 0.9475922972961215, "learning_rate": 9.975100359234037e-06, "loss": 0.45264205932617185, "num_input_tokens_seen": 38838072, "step": 945, "train_runtime": 3660.0786, "train_tokens_per_second": 10611.267 }, { "epoch": 0.06396444923242661, "grad_norm": 0.9461925267320072, "learning_rate": 9.974836115371972e-06, "loss": 0.46712894439697267, "num_input_tokens_seen": 39042736, "step": 950, "train_runtime": 3680.3028, "train_tokens_per_second": 10608.566 }, { "epoch": 0.06430110422838675, "grad_norm": 0.8649920365093956, "learning_rate": 9.974570480312852e-06, "loss": 0.4090930938720703, "num_input_tokens_seen": 39256016, "step": 955, "train_runtime": 3700.079, "train_tokens_per_second": 10609.507 }, { "epoch": 0.06463775922434689, "grad_norm": 0.9314959503617491, "learning_rate": 9.974303454130962e-06, "loss": 0.44704723358154297, "num_input_tokens_seen": 39446536, "step": 960, "train_runtime": 3718.5458, "train_tokens_per_second": 10608.054 }, { "epoch": 0.06497441422030703, "grad_norm": 0.7977716605962399, "learning_rate": 9.97403503690097e-06, "loss": 0.4297036170959473, "num_input_tokens_seen": 39653992, "step": 965, "train_runtime": 3737.8245, "train_tokens_per_second": 10608.843 }, { "epoch": 0.06531106921626717, "grad_norm": 0.8651790620235685, "learning_rate": 9.973765228697942e-06, "loss": 0.40104165077209475, "num_input_tokens_seen": 39863728, "step": 970, "train_runtime": 3756.032, "train_tokens_per_second": 10613.256 }, { "epoch": 0.06564772421222731, "grad_norm": 0.8908144557121672, "learning_rate": 9.973494029597327e-06, "loss": 0.43081979751586913, "num_input_tokens_seen": 40055936, "step": 975, "train_runtime": 3774.7357, "train_tokens_per_second": 10611.587 }, { "epoch": 0.06598437920818745, "grad_norm": 0.9404283158822119, "learning_rate": 9.973221439674968e-06, "loss": 0.42476229667663573, "num_input_tokens_seen": 40254656, "step": 980, "train_runtime": 3794.2469, "train_tokens_per_second": 10609.393 }, { "epoch": 0.06632103420414759, "grad_norm": 0.8462433741232247, "learning_rate": 9.972947459007089e-06, "loss": 0.4532536506652832, "num_input_tokens_seen": 40456776, "step": 985, "train_runtime": 3813.6765, "train_tokens_per_second": 10608.34 }, { "epoch": 0.06665768920010773, "grad_norm": 0.8893551101953908, "learning_rate": 9.972672087670313e-06, "loss": 0.43755502700805665, "num_input_tokens_seen": 40665232, "step": 990, "train_runtime": 3833.1737, "train_tokens_per_second": 10608.763 }, { "epoch": 0.06699434419606787, "grad_norm": 0.7674743809204909, "learning_rate": 9.972395325741644e-06, "loss": 0.41808671951293946, "num_input_tokens_seen": 40873600, "step": 995, "train_runtime": 3851.746, "train_tokens_per_second": 10611.707 }, { "epoch": 0.06733099919202801, "grad_norm": 0.8406377099015265, "learning_rate": 9.972117173298476e-06, "loss": 0.4004251003265381, "num_input_tokens_seen": 41075104, "step": 1000, "train_runtime": 3870.5275, "train_tokens_per_second": 10612.275 }, { "epoch": 0.06766765418798815, "grad_norm": 0.8849113867111419, "learning_rate": 9.971837630418597e-06, "loss": 0.4282681465148926, "num_input_tokens_seen": 41281824, "step": 1005, "train_runtime": 3889.6234, "train_tokens_per_second": 10613.322 }, { "epoch": 0.06800430918394829, "grad_norm": 0.8373926578645123, "learning_rate": 9.971556697180179e-06, "loss": 0.4435893535614014, "num_input_tokens_seen": 41483016, "step": 1010, "train_runtime": 3909.4333, "train_tokens_per_second": 10611.005 }, { "epoch": 0.06834096417990843, "grad_norm": 0.9041059940417192, "learning_rate": 9.971274373661784e-06, "loss": 0.42342462539672854, "num_input_tokens_seen": 41690144, "step": 1015, "train_runtime": 3927.4714, "train_tokens_per_second": 10615.009 }, { "epoch": 0.06867761917586857, "grad_norm": 0.7929863456554104, "learning_rate": 9.97099065994236e-06, "loss": 0.39858222007751465, "num_input_tokens_seen": 41903848, "step": 1020, "train_runtime": 3946.1224, "train_tokens_per_second": 10618.994 }, { "epoch": 0.0690142741718287, "grad_norm": 0.9162110180437267, "learning_rate": 9.970705556101253e-06, "loss": 0.4370746612548828, "num_input_tokens_seen": 42096032, "step": 1025, "train_runtime": 3965.6003, "train_tokens_per_second": 10615.299 }, { "epoch": 0.06935092916778884, "grad_norm": 0.8618096548120175, "learning_rate": 9.970419062218186e-06, "loss": 0.4544537544250488, "num_input_tokens_seen": 42314776, "step": 1030, "train_runtime": 3984.6682, "train_tokens_per_second": 10619.398 }, { "epoch": 0.06968758416374898, "grad_norm": 0.8741365582164753, "learning_rate": 9.970131178373276e-06, "loss": 0.4625950813293457, "num_input_tokens_seen": 42529408, "step": 1035, "train_runtime": 4004.8039, "train_tokens_per_second": 10619.598 }, { "epoch": 0.07002423915970914, "grad_norm": 0.9329941588402872, "learning_rate": 9.969841904647033e-06, "loss": 0.48327484130859377, "num_input_tokens_seen": 42736048, "step": 1040, "train_runtime": 4025.0815, "train_tokens_per_second": 10617.437 }, { "epoch": 0.07036089415566928, "grad_norm": 0.8678105421094197, "learning_rate": 9.969551241120349e-06, "loss": 0.4349653244018555, "num_input_tokens_seen": 42949520, "step": 1045, "train_runtime": 4043.8258, "train_tokens_per_second": 10621.011 }, { "epoch": 0.07069754915162942, "grad_norm": 0.8039386041519369, "learning_rate": 9.969259187874507e-06, "loss": 0.4103522300720215, "num_input_tokens_seen": 43164360, "step": 1050, "train_runtime": 4063.2214, "train_tokens_per_second": 10623.187 }, { "epoch": 0.07103420414758956, "grad_norm": 0.8603921561565813, "learning_rate": 9.968965744991178e-06, "loss": 0.43480596542358396, "num_input_tokens_seen": 43371680, "step": 1055, "train_runtime": 4081.0948, "train_tokens_per_second": 10627.462 }, { "epoch": 0.0713708591435497, "grad_norm": 0.9109657412232987, "learning_rate": 9.968670912552422e-06, "loss": 0.41443257331848143, "num_input_tokens_seen": 43578296, "step": 1060, "train_runtime": 4100.2442, "train_tokens_per_second": 10628.22 }, { "epoch": 0.07170751413950983, "grad_norm": 0.8422935535927741, "learning_rate": 9.968374690640692e-06, "loss": 0.4304975509643555, "num_input_tokens_seen": 43788728, "step": 1065, "train_runtime": 4119.2042, "train_tokens_per_second": 10630.385 }, { "epoch": 0.07204416913546997, "grad_norm": 1.0187695112799389, "learning_rate": 9.968077079338822e-06, "loss": 0.4512287139892578, "num_input_tokens_seen": 43993616, "step": 1070, "train_runtime": 4137.3156, "train_tokens_per_second": 10633.372 }, { "epoch": 0.07238082413143011, "grad_norm": 0.9157807792980056, "learning_rate": 9.967778078730038e-06, "loss": 0.4494725227355957, "num_input_tokens_seen": 44198288, "step": 1075, "train_runtime": 4156.9758, "train_tokens_per_second": 10632.318 }, { "epoch": 0.07271747912739025, "grad_norm": 0.8978128041781737, "learning_rate": 9.967477688897957e-06, "loss": 0.4488961219787598, "num_input_tokens_seen": 44405960, "step": 1080, "train_runtime": 4175.2249, "train_tokens_per_second": 10635.585 }, { "epoch": 0.07305413412335039, "grad_norm": 0.77883537914323, "learning_rate": 9.967175909926578e-06, "loss": 0.45905027389526365, "num_input_tokens_seen": 44620904, "step": 1085, "train_runtime": 4193.2294, "train_tokens_per_second": 10641.179 }, { "epoch": 0.07339078911931053, "grad_norm": 0.9101356486349935, "learning_rate": 9.966872741900296e-06, "loss": 0.4715388298034668, "num_input_tokens_seen": 44838456, "step": 1090, "train_runtime": 4212.9094, "train_tokens_per_second": 10643.109 }, { "epoch": 0.07372744411527067, "grad_norm": 0.9727564328775116, "learning_rate": 9.96656818490389e-06, "loss": 0.45829343795776367, "num_input_tokens_seen": 45041552, "step": 1095, "train_runtime": 4232.1101, "train_tokens_per_second": 10642.812 }, { "epoch": 0.07406409911123081, "grad_norm": 0.8499740409887068, "learning_rate": 9.966262239022529e-06, "loss": 0.48304762840271, "num_input_tokens_seen": 45252032, "step": 1100, "train_runtime": 4250.8167, "train_tokens_per_second": 10645.491 }, { "epoch": 0.07440075410719095, "grad_norm": 0.8348448998418739, "learning_rate": 9.965954904341768e-06, "loss": 0.46138820648193357, "num_input_tokens_seen": 45458552, "step": 1105, "train_runtime": 4269.7991, "train_tokens_per_second": 10646.532 }, { "epoch": 0.07473740910315109, "grad_norm": 0.9762873597708416, "learning_rate": 9.965646180947555e-06, "loss": 0.4373610019683838, "num_input_tokens_seen": 45661008, "step": 1110, "train_runtime": 4290.4703, "train_tokens_per_second": 10642.425 }, { "epoch": 0.07507406409911123, "grad_norm": 0.8410417353685606, "learning_rate": 9.96533606892622e-06, "loss": 0.43042144775390623, "num_input_tokens_seen": 45856960, "step": 1115, "train_runtime": 4309.9138, "train_tokens_per_second": 10639.879 }, { "epoch": 0.07541071909507137, "grad_norm": 0.8442274137967591, "learning_rate": 9.965024568364487e-06, "loss": 0.44811406135559084, "num_input_tokens_seen": 46071160, "step": 1120, "train_runtime": 4329.0513, "train_tokens_per_second": 10642.322 }, { "epoch": 0.07574737409103151, "grad_norm": 0.9298657370848641, "learning_rate": 9.964711679349467e-06, "loss": 0.41810336112976076, "num_input_tokens_seen": 46270272, "step": 1125, "train_runtime": 4347.3438, "train_tokens_per_second": 10643.343 }, { "epoch": 0.07608402908699165, "grad_norm": 0.7843715275008346, "learning_rate": 9.964397401968656e-06, "loss": 0.4689475536346436, "num_input_tokens_seen": 46481072, "step": 1130, "train_runtime": 4366.4965, "train_tokens_per_second": 10644.935 }, { "epoch": 0.07642068408295179, "grad_norm": 0.8643285455977622, "learning_rate": 9.964081736309942e-06, "loss": 0.4153473377227783, "num_input_tokens_seen": 46701680, "step": 1135, "train_runtime": 4385.296, "train_tokens_per_second": 10649.607 }, { "epoch": 0.07675733907891193, "grad_norm": 0.813540691787574, "learning_rate": 9.963764682461599e-06, "loss": 0.4351953029632568, "num_input_tokens_seen": 46916424, "step": 1140, "train_runtime": 4403.9946, "train_tokens_per_second": 10653.152 }, { "epoch": 0.07709399407487207, "grad_norm": 0.833735777795436, "learning_rate": 9.96344624051229e-06, "loss": 0.43962249755859373, "num_input_tokens_seen": 47120392, "step": 1145, "train_runtime": 4421.8427, "train_tokens_per_second": 10656.28 }, { "epoch": 0.0774306490708322, "grad_norm": 0.9807421778247656, "learning_rate": 9.96312641055107e-06, "loss": 0.41779422760009766, "num_input_tokens_seen": 47327528, "step": 1150, "train_runtime": 4441.1402, "train_tokens_per_second": 10656.617 }, { "epoch": 0.07776730406679234, "grad_norm": 0.7430488863396796, "learning_rate": 9.962805192667375e-06, "loss": 0.4148519039154053, "num_input_tokens_seen": 47532800, "step": 1155, "train_runtime": 4460.8113, "train_tokens_per_second": 10655.64 }, { "epoch": 0.07810395906275248, "grad_norm": 0.9820111937784586, "learning_rate": 9.962482586951033e-06, "loss": 0.4203987121582031, "num_input_tokens_seen": 47748576, "step": 1160, "train_runtime": 4478.8502, "train_tokens_per_second": 10660.9 }, { "epoch": 0.07844061405871264, "grad_norm": 0.8600932553296446, "learning_rate": 9.962158593492258e-06, "loss": 0.440095043182373, "num_input_tokens_seen": 47946392, "step": 1165, "train_runtime": 4500.2229, "train_tokens_per_second": 10654.226 }, { "epoch": 0.07877726905467278, "grad_norm": 0.8153311445714948, "learning_rate": 9.961833212381657e-06, "loss": 0.4439291477203369, "num_input_tokens_seen": 48155448, "step": 1170, "train_runtime": 4518.9928, "train_tokens_per_second": 10656.235 }, { "epoch": 0.07911392405063292, "grad_norm": 0.7505048656227314, "learning_rate": 9.961506443710221e-06, "loss": 0.4240240573883057, "num_input_tokens_seen": 48366424, "step": 1175, "train_runtime": 4539.8978, "train_tokens_per_second": 10653.637 }, { "epoch": 0.07945057904659306, "grad_norm": 0.9016697900606733, "learning_rate": 9.961178287569326e-06, "loss": 0.41486635208129885, "num_input_tokens_seen": 48579272, "step": 1180, "train_runtime": 4558.9505, "train_tokens_per_second": 10655.802 }, { "epoch": 0.0797872340425532, "grad_norm": 0.8611247992164531, "learning_rate": 9.960848744050747e-06, "loss": 0.44910717010498047, "num_input_tokens_seen": 48783752, "step": 1185, "train_runtime": 4576.8345, "train_tokens_per_second": 10658.841 }, { "epoch": 0.08012388903851334, "grad_norm": 0.7989841302958044, "learning_rate": 9.960517813246633e-06, "loss": 0.4473024845123291, "num_input_tokens_seen": 48982872, "step": 1190, "train_runtime": 4596.9046, "train_tokens_per_second": 10655.621 }, { "epoch": 0.08046054403447347, "grad_norm": 0.9095031633760052, "learning_rate": 9.96018549524953e-06, "loss": 0.4258852005004883, "num_input_tokens_seen": 49189360, "step": 1195, "train_runtime": 4615.9978, "train_tokens_per_second": 10656.279 }, { "epoch": 0.08079719903043361, "grad_norm": 0.9369312241209223, "learning_rate": 9.959851790152371e-06, "loss": 0.43015027046203613, "num_input_tokens_seen": 49397832, "step": 1200, "train_runtime": 4636.6806, "train_tokens_per_second": 10653.706 }, { "epoch": 0.08113385402639375, "grad_norm": 0.8123491668992873, "learning_rate": 9.959516698048475e-06, "loss": 0.38898704051971433, "num_input_tokens_seen": 49594056, "step": 1205, "train_runtime": 4656.778, "train_tokens_per_second": 10649.865 }, { "epoch": 0.08147050902235389, "grad_norm": 0.935478993329335, "learning_rate": 9.959180219031551e-06, "loss": 0.40725011825561525, "num_input_tokens_seen": 49794272, "step": 1210, "train_runtime": 4677.4275, "train_tokens_per_second": 10645.654 }, { "epoch": 0.08180716401831403, "grad_norm": 0.8200041146738679, "learning_rate": 9.958842353195688e-06, "loss": 0.4236556053161621, "num_input_tokens_seen": 50006776, "step": 1215, "train_runtime": 4696.7261, "train_tokens_per_second": 10647.156 }, { "epoch": 0.08214381901427417, "grad_norm": 0.9047966373730165, "learning_rate": 9.958503100635377e-06, "loss": 0.43204054832458494, "num_input_tokens_seen": 50204624, "step": 1220, "train_runtime": 4715.943, "train_tokens_per_second": 10645.723 }, { "epoch": 0.08248047401023431, "grad_norm": 0.8555046109732064, "learning_rate": 9.958162461445484e-06, "loss": 0.4643999099731445, "num_input_tokens_seen": 50418424, "step": 1225, "train_runtime": 4735.0042, "train_tokens_per_second": 10648.021 }, { "epoch": 0.08281712900619445, "grad_norm": 0.8580155315447947, "learning_rate": 9.957820435721271e-06, "loss": 0.4389303207397461, "num_input_tokens_seen": 50622000, "step": 1230, "train_runtime": 4754.3023, "train_tokens_per_second": 10647.619 }, { "epoch": 0.08315378400215459, "grad_norm": 0.9042516328716815, "learning_rate": 9.95747702355838e-06, "loss": 0.46552338600158694, "num_input_tokens_seen": 50832912, "step": 1235, "train_runtime": 4773.3708, "train_tokens_per_second": 10649.269 }, { "epoch": 0.08349043899811473, "grad_norm": 0.7922750702229753, "learning_rate": 9.957132225052848e-06, "loss": 0.4654229164123535, "num_input_tokens_seen": 51039248, "step": 1240, "train_runtime": 4792.794, "train_tokens_per_second": 10649.164 }, { "epoch": 0.08382709399407487, "grad_norm": 0.7909977483968254, "learning_rate": 9.956786040301098e-06, "loss": 0.41388444900512694, "num_input_tokens_seen": 51243872, "step": 1245, "train_runtime": 4812.0884, "train_tokens_per_second": 10648.988 }, { "epoch": 0.08416374899003501, "grad_norm": 0.9017357127817439, "learning_rate": 9.956438469399936e-06, "loss": 0.43239946365356446, "num_input_tokens_seen": 51443480, "step": 1250, "train_runtime": 4831.5208, "train_tokens_per_second": 10647.472 }, { "epoch": 0.08450040398599515, "grad_norm": 0.8587304895029456, "learning_rate": 9.956089512446562e-06, "loss": 0.4310599327087402, "num_input_tokens_seen": 51637424, "step": 1255, "train_runtime": 4849.6415, "train_tokens_per_second": 10647.679 }, { "epoch": 0.08483705898195529, "grad_norm": 0.8690689970457035, "learning_rate": 9.955739169538559e-06, "loss": 0.4402626991271973, "num_input_tokens_seen": 51838944, "step": 1260, "train_runtime": 4868.5471, "train_tokens_per_second": 10647.724 }, { "epoch": 0.08517371397791543, "grad_norm": 0.9859174821158134, "learning_rate": 9.955387440773902e-06, "loss": 0.4315632820129395, "num_input_tokens_seen": 52033832, "step": 1265, "train_runtime": 4887.8926, "train_tokens_per_second": 10645.453 }, { "epoch": 0.08551036897387557, "grad_norm": 1.0503394464427531, "learning_rate": 9.955034326250947e-06, "loss": 0.4231212615966797, "num_input_tokens_seen": 52240368, "step": 1270, "train_runtime": 4906.4509, "train_tokens_per_second": 10647.282 }, { "epoch": 0.0858470239698357, "grad_norm": 0.9051520349725554, "learning_rate": 9.954679826068444e-06, "loss": 0.422595739364624, "num_input_tokens_seen": 52440376, "step": 1275, "train_runtime": 4926.5773, "train_tokens_per_second": 10644.383 }, { "epoch": 0.08618367896579585, "grad_norm": 0.9722330395687256, "learning_rate": 9.954323940325526e-06, "loss": 0.43520054817199705, "num_input_tokens_seen": 52640704, "step": 1280, "train_runtime": 4946.1632, "train_tokens_per_second": 10642.735 }, { "epoch": 0.086520333961756, "grad_norm": 0.8096457056776741, "learning_rate": 9.953966669121715e-06, "loss": 0.45537467002868653, "num_input_tokens_seen": 52860472, "step": 1285, "train_runtime": 4967.1358, "train_tokens_per_second": 10642.043 }, { "epoch": 0.08685698895771614, "grad_norm": 0.8519916225835449, "learning_rate": 9.953608012556924e-06, "loss": 0.44853506088256834, "num_input_tokens_seen": 53073416, "step": 1290, "train_runtime": 4987.0369, "train_tokens_per_second": 10642.275 }, { "epoch": 0.08719364395367628, "grad_norm": 0.7929655644583888, "learning_rate": 9.953247970731449e-06, "loss": 0.45364961624145506, "num_input_tokens_seen": 53274768, "step": 1295, "train_runtime": 5007.1878, "train_tokens_per_second": 10639.658 }, { "epoch": 0.08753029894963642, "grad_norm": 0.951441771005959, "learning_rate": 9.952886543745973e-06, "loss": 0.4578502655029297, "num_input_tokens_seen": 53479704, "step": 1300, "train_runtime": 5027.5624, "train_tokens_per_second": 10637.303 }, { "epoch": 0.08786695394559656, "grad_norm": 0.9415386773638766, "learning_rate": 9.952523731701566e-06, "loss": 0.44289360046386717, "num_input_tokens_seen": 53696352, "step": 1305, "train_runtime": 5047.0325, "train_tokens_per_second": 10639.193 }, { "epoch": 0.0882036089415567, "grad_norm": 0.7668763357121131, "learning_rate": 9.952159534699693e-06, "loss": 0.3991614818572998, "num_input_tokens_seen": 53894616, "step": 1310, "train_runtime": 5065.7601, "train_tokens_per_second": 10638.999 }, { "epoch": 0.08854026393751684, "grad_norm": 0.8606578405404248, "learning_rate": 9.951793952842197e-06, "loss": 0.46473045349121095, "num_input_tokens_seen": 54094032, "step": 1315, "train_runtime": 5083.7359, "train_tokens_per_second": 10640.606 }, { "epoch": 0.08887691893347698, "grad_norm": 0.8966100901682026, "learning_rate": 9.95142698623131e-06, "loss": 0.4093886375427246, "num_input_tokens_seen": 54283976, "step": 1320, "train_runtime": 5103.0804, "train_tokens_per_second": 10637.492 }, { "epoch": 0.08921357392943711, "grad_norm": 1.3650861456022014, "learning_rate": 9.951058634969657e-06, "loss": 0.45738587379455564, "num_input_tokens_seen": 54484520, "step": 1325, "train_runtime": 5122.9942, "train_tokens_per_second": 10635.288 }, { "epoch": 0.08955022892539725, "grad_norm": 0.8089575971749701, "learning_rate": 9.950688899160244e-06, "loss": 0.4314689636230469, "num_input_tokens_seen": 54700984, "step": 1330, "train_runtime": 5141.729, "train_tokens_per_second": 10638.636 }, { "epoch": 0.0898868839213574, "grad_norm": 0.9012005955164745, "learning_rate": 9.950317778906469e-06, "loss": 0.4348163604736328, "num_input_tokens_seen": 54915160, "step": 1335, "train_runtime": 5160.3572, "train_tokens_per_second": 10641.736 }, { "epoch": 0.09022353891731753, "grad_norm": 1.3551027359242835, "learning_rate": 9.949945274312109e-06, "loss": 0.41330909729003906, "num_input_tokens_seen": 55124040, "step": 1340, "train_runtime": 5180.4213, "train_tokens_per_second": 10640.841 }, { "epoch": 0.09056019391327767, "grad_norm": 1.0275103275954476, "learning_rate": 9.94957138548134e-06, "loss": 0.44407477378845217, "num_input_tokens_seen": 55310776, "step": 1345, "train_runtime": 5198.1248, "train_tokens_per_second": 10640.525 }, { "epoch": 0.09089684890923781, "grad_norm": 0.9514672154201436, "learning_rate": 9.949196112518715e-06, "loss": 0.4163506507873535, "num_input_tokens_seen": 55523336, "step": 1350, "train_runtime": 5217.8937, "train_tokens_per_second": 10640.948 }, { "epoch": 0.09123350390519795, "grad_norm": 0.8342256963231724, "learning_rate": 9.94881945552918e-06, "loss": 0.44128990173339844, "num_input_tokens_seen": 55734576, "step": 1355, "train_runtime": 5238.0804, "train_tokens_per_second": 10640.267 }, { "epoch": 0.09157015890115809, "grad_norm": 0.8902511368397538, "learning_rate": 9.948441414618064e-06, "loss": 0.45806331634521485, "num_input_tokens_seen": 55934840, "step": 1360, "train_runtime": 5257.9811, "train_tokens_per_second": 10638.083 }, { "epoch": 0.09190681389711823, "grad_norm": 0.8657710257479798, "learning_rate": 9.948061989891085e-06, "loss": 0.4105788230895996, "num_input_tokens_seen": 56146368, "step": 1365, "train_runtime": 5277.3945, "train_tokens_per_second": 10639.032 }, { "epoch": 0.09224346889307837, "grad_norm": 0.920394355620971, "learning_rate": 9.94768118145435e-06, "loss": 0.42171306610107423, "num_input_tokens_seen": 56347120, "step": 1370, "train_runtime": 5297.2523, "train_tokens_per_second": 10637.047 }, { "epoch": 0.09258012388903851, "grad_norm": 0.8104541898457928, "learning_rate": 9.947298989414349e-06, "loss": 0.4155605316162109, "num_input_tokens_seen": 56560448, "step": 1375, "train_runtime": 5317.4658, "train_tokens_per_second": 10636.73 }, { "epoch": 0.09291677888499865, "grad_norm": 0.9522938174490322, "learning_rate": 9.946915413877963e-06, "loss": 0.4245589733123779, "num_input_tokens_seen": 56775672, "step": 1380, "train_runtime": 5339.2571, "train_tokens_per_second": 10633.628 }, { "epoch": 0.09325343388095879, "grad_norm": 0.8717769631574397, "learning_rate": 9.946530454952454e-06, "loss": 0.44962310791015625, "num_input_tokens_seen": 56989568, "step": 1385, "train_runtime": 5359.261, "train_tokens_per_second": 10633.848 }, { "epoch": 0.09359008887691893, "grad_norm": 0.907226000724348, "learning_rate": 9.946144112745477e-06, "loss": 0.45713376998901367, "num_input_tokens_seen": 57203400, "step": 1390, "train_runtime": 5379.3928, "train_tokens_per_second": 10633.802 }, { "epoch": 0.09392674387287907, "grad_norm": 0.9723649474859724, "learning_rate": 9.94575638736507e-06, "loss": 0.43345842361450193, "num_input_tokens_seen": 57414432, "step": 1395, "train_runtime": 5397.4175, "train_tokens_per_second": 10637.389 }, { "epoch": 0.09426339886883921, "grad_norm": 0.8929673617076966, "learning_rate": 9.945367278919662e-06, "loss": 0.46543316841125487, "num_input_tokens_seen": 57624536, "step": 1400, "train_runtime": 5416.1445, "train_tokens_per_second": 10639.402 }, { "epoch": 0.09460005386479936, "grad_norm": 0.9289908211468887, "learning_rate": 9.944976787518064e-06, "loss": 0.44035658836364744, "num_input_tokens_seen": 57830328, "step": 1405, "train_runtime": 5434.9844, "train_tokens_per_second": 10640.385 }, { "epoch": 0.0949367088607595, "grad_norm": 0.8155455895294678, "learning_rate": 9.944584913269474e-06, "loss": 0.4479948043823242, "num_input_tokens_seen": 58047056, "step": 1410, "train_runtime": 5456.4529, "train_tokens_per_second": 10638.24 }, { "epoch": 0.09527336385671964, "grad_norm": 0.843322861272841, "learning_rate": 9.944191656283481e-06, "loss": 0.416276741027832, "num_input_tokens_seen": 58257480, "step": 1415, "train_runtime": 5475.5019, "train_tokens_per_second": 10639.66 }, { "epoch": 0.09561001885267978, "grad_norm": 0.8458870427088127, "learning_rate": 9.943797016670059e-06, "loss": 0.42166891098022463, "num_input_tokens_seen": 58457208, "step": 1420, "train_runtime": 5493.1584, "train_tokens_per_second": 10641.821 }, { "epoch": 0.09594667384863992, "grad_norm": 1.0255305143621163, "learning_rate": 9.943400994539565e-06, "loss": 0.4156886100769043, "num_input_tokens_seen": 58663608, "step": 1425, "train_runtime": 5513.6866, "train_tokens_per_second": 10639.634 }, { "epoch": 0.09628332884460006, "grad_norm": 0.8022134478984804, "learning_rate": 9.943003590002744e-06, "loss": 0.44020724296569824, "num_input_tokens_seen": 58875040, "step": 1430, "train_runtime": 5532.7801, "train_tokens_per_second": 10641.131 }, { "epoch": 0.0966199838405602, "grad_norm": 0.9226821135341375, "learning_rate": 9.942604803170733e-06, "loss": 0.42770771980285643, "num_input_tokens_seen": 59075064, "step": 1435, "train_runtime": 5552.9317, "train_tokens_per_second": 10638.536 }, { "epoch": 0.09695663883652034, "grad_norm": 0.8799454563794225, "learning_rate": 9.94220463415505e-06, "loss": 0.4583366870880127, "num_input_tokens_seen": 59276424, "step": 1440, "train_runtime": 5571.9931, "train_tokens_per_second": 10638.28 }, { "epoch": 0.09729329383248048, "grad_norm": 0.8175377734966676, "learning_rate": 9.9418030830676e-06, "loss": 0.4437218189239502, "num_input_tokens_seen": 59486888, "step": 1445, "train_runtime": 5591.684, "train_tokens_per_second": 10638.457 }, { "epoch": 0.09762994882844062, "grad_norm": 0.957769926222571, "learning_rate": 9.941400150020676e-06, "loss": 0.4496159553527832, "num_input_tokens_seen": 59679976, "step": 1450, "train_runtime": 5610.3708, "train_tokens_per_second": 10637.439 }, { "epoch": 0.09796660382440076, "grad_norm": 0.870750066442978, "learning_rate": 9.940995835126957e-06, "loss": 0.46126842498779297, "num_input_tokens_seen": 59888256, "step": 1455, "train_runtime": 5629.7227, "train_tokens_per_second": 10637.87 }, { "epoch": 0.0983032588203609, "grad_norm": 0.9665021088491607, "learning_rate": 9.940590138499508e-06, "loss": 0.40877747535705566, "num_input_tokens_seen": 60100200, "step": 1460, "train_runtime": 5649.8173, "train_tokens_per_second": 10637.547 }, { "epoch": 0.09863991381632103, "grad_norm": 0.9282824513847673, "learning_rate": 9.940183060251783e-06, "loss": 0.42709665298461913, "num_input_tokens_seen": 60287808, "step": 1465, "train_runtime": 5669.4697, "train_tokens_per_second": 10633.765 }, { "epoch": 0.09897656881228117, "grad_norm": 0.7801599417794142, "learning_rate": 9.939774600497616e-06, "loss": 0.3785432815551758, "num_input_tokens_seen": 60492992, "step": 1470, "train_runtime": 5689.2465, "train_tokens_per_second": 10632.865 }, { "epoch": 0.09931322380824131, "grad_norm": 0.8343723074865044, "learning_rate": 9.939364759351236e-06, "loss": 0.43668398857116697, "num_input_tokens_seen": 60696624, "step": 1475, "train_runtime": 5709.2466, "train_tokens_per_second": 10631.284 }, { "epoch": 0.09964987880420145, "grad_norm": 1.020614550127764, "learning_rate": 9.938953536927249e-06, "loss": 0.39807753562927245, "num_input_tokens_seen": 60910040, "step": 1480, "train_runtime": 5729.867, "train_tokens_per_second": 10630.271 }, { "epoch": 0.09998653380016159, "grad_norm": 0.7931406786249561, "learning_rate": 9.938540933340657e-06, "loss": 0.4472785949707031, "num_input_tokens_seen": 61121672, "step": 1485, "train_runtime": 5747.5116, "train_tokens_per_second": 10634.458 }, { "epoch": 0.10032318879612173, "grad_norm": 0.7042167392504642, "learning_rate": 9.938126948706839e-06, "loss": 0.4258891582489014, "num_input_tokens_seen": 61334320, "step": 1490, "train_runtime": 5767.3875, "train_tokens_per_second": 10634.68 }, { "epoch": 0.10065984379208187, "grad_norm": 0.7612809286158415, "learning_rate": 9.937711583141567e-06, "loss": 0.4126432418823242, "num_input_tokens_seen": 61540720, "step": 1495, "train_runtime": 5787.4914, "train_tokens_per_second": 10633.402 }, { "epoch": 0.10099649878804201, "grad_norm": 1.0200606821276896, "learning_rate": 9.937294836760995e-06, "loss": 0.43465380668640136, "num_input_tokens_seen": 61745784, "step": 1500, "train_runtime": 5805.7406, "train_tokens_per_second": 10635.298 }, { "epoch": 0.10133315378400215, "grad_norm": 0.8621303221505212, "learning_rate": 9.936876709681668e-06, "loss": 0.4810704231262207, "num_input_tokens_seen": 61948720, "step": 1505, "train_runtime": 5824.3414, "train_tokens_per_second": 10636.176 }, { "epoch": 0.10166980877996229, "grad_norm": 0.762087834141803, "learning_rate": 9.93645720202051e-06, "loss": 0.3830185651779175, "num_input_tokens_seen": 62153384, "step": 1510, "train_runtime": 5842.4891, "train_tokens_per_second": 10638.169 }, { "epoch": 0.10200646377592243, "grad_norm": 0.7954562662407637, "learning_rate": 9.936036313894836e-06, "loss": 0.46245489120483396, "num_input_tokens_seen": 62354992, "step": 1515, "train_runtime": 5861.6387, "train_tokens_per_second": 10637.809 }, { "epoch": 0.10234311877188257, "grad_norm": 0.9092668239758874, "learning_rate": 9.935614045422349e-06, "loss": 0.45439624786376953, "num_input_tokens_seen": 62562176, "step": 1520, "train_runtime": 5881.1861, "train_tokens_per_second": 10637.68 }, { "epoch": 0.10267977376784271, "grad_norm": 0.78463368436816, "learning_rate": 9.935190396721132e-06, "loss": 0.40851435661315916, "num_input_tokens_seen": 62771512, "step": 1525, "train_runtime": 5901.5445, "train_tokens_per_second": 10636.455 }, { "epoch": 0.10301642876380286, "grad_norm": 0.9575395377754524, "learning_rate": 9.934765367909658e-06, "loss": 0.4425245761871338, "num_input_tokens_seen": 62973792, "step": 1530, "train_runtime": 5921.0632, "train_tokens_per_second": 10635.555 }, { "epoch": 0.103353083759763, "grad_norm": 0.9109395723248139, "learning_rate": 9.934338959106783e-06, "loss": 0.420426082611084, "num_input_tokens_seen": 63181232, "step": 1535, "train_runtime": 5938.6495, "train_tokens_per_second": 10638.99 }, { "epoch": 0.10368973875572314, "grad_norm": 1.000114202636845, "learning_rate": 9.933911170431753e-06, "loss": 0.4609443187713623, "num_input_tokens_seen": 63374568, "step": 1540, "train_runtime": 5957.0931, "train_tokens_per_second": 10638.506 }, { "epoch": 0.10402639375168328, "grad_norm": 0.8904974509153278, "learning_rate": 9.933482002004198e-06, "loss": 0.44725022315979, "num_input_tokens_seen": 63589040, "step": 1545, "train_runtime": 5976.4215, "train_tokens_per_second": 10639.986 }, { "epoch": 0.10436304874764342, "grad_norm": 1.0538869234041277, "learning_rate": 9.933051453944134e-06, "loss": 0.47659921646118164, "num_input_tokens_seen": 63797840, "step": 1550, "train_runtime": 5994.5992, "train_tokens_per_second": 10642.553 }, { "epoch": 0.10469970374360356, "grad_norm": 0.8822263861501276, "learning_rate": 9.932619526371958e-06, "loss": 0.41258888244628905, "num_input_tokens_seen": 64004432, "step": 1555, "train_runtime": 6013.3877, "train_tokens_per_second": 10643.656 }, { "epoch": 0.1050363587395637, "grad_norm": 0.8654885858151171, "learning_rate": 9.932186219408463e-06, "loss": 0.4064056396484375, "num_input_tokens_seen": 64202712, "step": 1560, "train_runtime": 6033.2227, "train_tokens_per_second": 10641.529 }, { "epoch": 0.10537301373552384, "grad_norm": 0.9080032417339834, "learning_rate": 9.931751533174819e-06, "loss": 0.4500283241271973, "num_input_tokens_seen": 64399640, "step": 1565, "train_runtime": 6054.1555, "train_tokens_per_second": 10637.262 }, { "epoch": 0.10570966873148398, "grad_norm": 0.9095671465782665, "learning_rate": 9.931315467792584e-06, "loss": 0.458544397354126, "num_input_tokens_seen": 64618224, "step": 1570, "train_runtime": 6072.6472, "train_tokens_per_second": 10640.866 }, { "epoch": 0.10604632372744412, "grad_norm": 0.9768767364881712, "learning_rate": 9.930878023383705e-06, "loss": 0.4438627243041992, "num_input_tokens_seen": 64822720, "step": 1575, "train_runtime": 6092.1674, "train_tokens_per_second": 10640.338 }, { "epoch": 0.10638297872340426, "grad_norm": 0.7492650531213797, "learning_rate": 9.93043920007051e-06, "loss": 0.4022563934326172, "num_input_tokens_seen": 65030544, "step": 1580, "train_runtime": 6111.1646, "train_tokens_per_second": 10641.269 }, { "epoch": 0.1067196337193644, "grad_norm": 0.8068026232705048, "learning_rate": 9.929998997975712e-06, "loss": 0.4226208209991455, "num_input_tokens_seen": 65249816, "step": 1585, "train_runtime": 6131.0231, "train_tokens_per_second": 10642.566 }, { "epoch": 0.10705628871532454, "grad_norm": 0.8576482393026004, "learning_rate": 9.929557417222417e-06, "loss": 0.41456146240234376, "num_input_tokens_seen": 65444216, "step": 1590, "train_runtime": 6149.627, "train_tokens_per_second": 10641.981 }, { "epoch": 0.10739294371128467, "grad_norm": 0.9141398413106383, "learning_rate": 9.929114457934109e-06, "loss": 0.4391796588897705, "num_input_tokens_seen": 65647128, "step": 1595, "train_runtime": 6169.2873, "train_tokens_per_second": 10640.958 }, { "epoch": 0.10772959870724481, "grad_norm": 0.8182919435787043, "learning_rate": 9.92867012023466e-06, "loss": 0.43295903205871583, "num_input_tokens_seen": 65857736, "step": 1600, "train_runtime": 6188.5608, "train_tokens_per_second": 10641.85 }, { "epoch": 0.10806625370320495, "grad_norm": 0.7805740405047967, "learning_rate": 9.92822440424833e-06, "loss": 0.470686149597168, "num_input_tokens_seen": 66067888, "step": 1605, "train_runtime": 6208.4333, "train_tokens_per_second": 10641.636 }, { "epoch": 0.1084029086991651, "grad_norm": 0.8989601981377027, "learning_rate": 9.927777310099759e-06, "loss": 0.48636975288391116, "num_input_tokens_seen": 66283456, "step": 1610, "train_runtime": 6227.3992, "train_tokens_per_second": 10643.842 }, { "epoch": 0.10873956369512523, "grad_norm": 0.8135516857292326, "learning_rate": 9.927328837913976e-06, "loss": 0.42408103942871095, "num_input_tokens_seen": 66492416, "step": 1615, "train_runtime": 6246.9498, "train_tokens_per_second": 10643.981 }, { "epoch": 0.10907621869108537, "grad_norm": 10.345939691951264, "learning_rate": 9.926878987816397e-06, "loss": 0.4189730644226074, "num_input_tokens_seen": 66706976, "step": 1620, "train_runtime": 6266.0393, "train_tokens_per_second": 10645.796 }, { "epoch": 0.10941287368704551, "grad_norm": 0.7705048077347006, "learning_rate": 9.92642775993282e-06, "loss": 0.41550912857055666, "num_input_tokens_seen": 66920928, "step": 1625, "train_runtime": 6285.9933, "train_tokens_per_second": 10646.039 }, { "epoch": 0.10974952868300565, "grad_norm": 0.7961357726206388, "learning_rate": 9.925975154389428e-06, "loss": 0.3990105390548706, "num_input_tokens_seen": 67122696, "step": 1630, "train_runtime": 6307.3014, "train_tokens_per_second": 10642.063 }, { "epoch": 0.11008618367896579, "grad_norm": 0.8102606461947545, "learning_rate": 9.925521171312792e-06, "loss": 0.41927032470703124, "num_input_tokens_seen": 67329200, "step": 1635, "train_runtime": 6325.6991, "train_tokens_per_second": 10643.756 }, { "epoch": 0.11042283867492593, "grad_norm": 0.8356623350337755, "learning_rate": 9.925065810829868e-06, "loss": 0.4464064598083496, "num_input_tokens_seen": 67520336, "step": 1640, "train_runtime": 6345.9908, "train_tokens_per_second": 10639.841 }, { "epoch": 0.11075949367088607, "grad_norm": 0.8406879227652089, "learning_rate": 9.924609073067994e-06, "loss": 0.4507251262664795, "num_input_tokens_seen": 67718128, "step": 1645, "train_runtime": 6366.3046, "train_tokens_per_second": 10636.96 }, { "epoch": 0.11109614866684622, "grad_norm": 0.8175797487283717, "learning_rate": 9.924150958154897e-06, "loss": 0.43839244842529296, "num_input_tokens_seen": 67930912, "step": 1650, "train_runtime": 6386.1523, "train_tokens_per_second": 10637.221 }, { "epoch": 0.11143280366280636, "grad_norm": 0.8257226431376068, "learning_rate": 9.923691466218686e-06, "loss": 0.4085533618927002, "num_input_tokens_seen": 68142408, "step": 1655, "train_runtime": 6407.3414, "train_tokens_per_second": 10635.052 }, { "epoch": 0.1117694586587665, "grad_norm": 0.8942635483461298, "learning_rate": 9.923230597387856e-06, "loss": 0.43062400817871094, "num_input_tokens_seen": 68362040, "step": 1660, "train_runtime": 6427.4862, "train_tokens_per_second": 10635.891 }, { "epoch": 0.11210611365472664, "grad_norm": 0.9197230560995711, "learning_rate": 9.922768351791289e-06, "loss": 0.46361351013183594, "num_input_tokens_seen": 68567888, "step": 1665, "train_runtime": 6446.6194, "train_tokens_per_second": 10636.255 }, { "epoch": 0.11244276865068678, "grad_norm": 0.8627063629947233, "learning_rate": 9.92230472955825e-06, "loss": 0.42408552169799807, "num_input_tokens_seen": 68774936, "step": 1670, "train_runtime": 6465.4807, "train_tokens_per_second": 10637.25 }, { "epoch": 0.11277942364664692, "grad_norm": 0.7759281534522168, "learning_rate": 9.92183973081839e-06, "loss": 0.3926481485366821, "num_input_tokens_seen": 68988072, "step": 1675, "train_runtime": 6484.9157, "train_tokens_per_second": 10638.237 }, { "epoch": 0.11311607864260706, "grad_norm": 0.7764277283593326, "learning_rate": 9.921373355701743e-06, "loss": 0.46454949378967286, "num_input_tokens_seen": 69205088, "step": 1680, "train_runtime": 6503.4797, "train_tokens_per_second": 10641.24 }, { "epoch": 0.1134527336385672, "grad_norm": 0.7960390216443716, "learning_rate": 9.920905604338732e-06, "loss": 0.45255699157714846, "num_input_tokens_seen": 69414256, "step": 1685, "train_runtime": 6524.1069, "train_tokens_per_second": 10639.656 }, { "epoch": 0.11378938863452734, "grad_norm": 0.7465354894852876, "learning_rate": 9.920436476860158e-06, "loss": 0.3933742046356201, "num_input_tokens_seen": 69614200, "step": 1690, "train_runtime": 6543.1589, "train_tokens_per_second": 10639.234 }, { "epoch": 0.11412604363048748, "grad_norm": 0.7946131464391801, "learning_rate": 9.919965973397214e-06, "loss": 0.4044051170349121, "num_input_tokens_seen": 69818776, "step": 1695, "train_runtime": 6561.7072, "train_tokens_per_second": 10640.337 }, { "epoch": 0.11446269862644762, "grad_norm": 0.8591358454857704, "learning_rate": 9.919494094081475e-06, "loss": 0.46263628005981444, "num_input_tokens_seen": 70010960, "step": 1700, "train_runtime": 6582.1324, "train_tokens_per_second": 10636.517 }, { "epoch": 0.11479935362240776, "grad_norm": 0.8766943268542038, "learning_rate": 9.919020839044899e-06, "loss": 0.4286296844482422, "num_input_tokens_seen": 70229832, "step": 1705, "train_runtime": 6600.259, "train_tokens_per_second": 10640.466 }, { "epoch": 0.1151360086183679, "grad_norm": 0.7848211580598677, "learning_rate": 9.918546208419832e-06, "loss": 0.4067856311798096, "num_input_tokens_seen": 70440992, "step": 1710, "train_runtime": 6622.657, "train_tokens_per_second": 10636.364 }, { "epoch": 0.11547266361432804, "grad_norm": 1.3404369154592195, "learning_rate": 9.918070202339e-06, "loss": 0.41479339599609377, "num_input_tokens_seen": 70653488, "step": 1715, "train_runtime": 6640.6933, "train_tokens_per_second": 10639.475 }, { "epoch": 0.11580931861028818, "grad_norm": 0.7985111508752418, "learning_rate": 9.91759282093552e-06, "loss": 0.40851335525512694, "num_input_tokens_seen": 70860240, "step": 1720, "train_runtime": 6658.3639, "train_tokens_per_second": 10642.29 }, { "epoch": 0.11614597360624832, "grad_norm": 0.8617618428088164, "learning_rate": 9.917114064342888e-06, "loss": 0.38633480072021487, "num_input_tokens_seen": 71061008, "step": 1725, "train_runtime": 6679.0032, "train_tokens_per_second": 10639.463 }, { "epoch": 0.11648262860220845, "grad_norm": 0.8436279967854733, "learning_rate": 9.916633932694988e-06, "loss": 0.400101375579834, "num_input_tokens_seen": 71269648, "step": 1730, "train_runtime": 6697.2698, "train_tokens_per_second": 10641.597 }, { "epoch": 0.1168192835981686, "grad_norm": 0.7834968521516567, "learning_rate": 9.916152426126086e-06, "loss": 0.3967332601547241, "num_input_tokens_seen": 71475200, "step": 1735, "train_runtime": 6716.8412, "train_tokens_per_second": 10641.193 }, { "epoch": 0.11715593859412873, "grad_norm": 6.846583842733043, "learning_rate": 9.915669544770837e-06, "loss": 0.41666336059570314, "num_input_tokens_seen": 71693944, "step": 1740, "train_runtime": 6735.9482, "train_tokens_per_second": 10643.482 }, { "epoch": 0.11749259359008887, "grad_norm": 1.1059493516958627, "learning_rate": 9.915185288764272e-06, "loss": 0.40627503395080566, "num_input_tokens_seen": 71914840, "step": 1745, "train_runtime": 6753.5536, "train_tokens_per_second": 10648.444 }, { "epoch": 0.11782924858604901, "grad_norm": 0.7720262847198119, "learning_rate": 9.914699658241815e-06, "loss": 0.40276260375976564, "num_input_tokens_seen": 72128464, "step": 1750, "train_runtime": 6774.3772, "train_tokens_per_second": 10647.247 }, { "epoch": 0.11816590358200915, "grad_norm": 0.9176923120586366, "learning_rate": 9.91421265333927e-06, "loss": 0.4450021266937256, "num_input_tokens_seen": 72342488, "step": 1755, "train_runtime": 6793.6312, "train_tokens_per_second": 10648.574 }, { "epoch": 0.11850255857796929, "grad_norm": 0.7478350492013741, "learning_rate": 9.913724274192829e-06, "loss": 0.4158039569854736, "num_input_tokens_seen": 72560576, "step": 1760, "train_runtime": 6813.5663, "train_tokens_per_second": 10649.427 }, { "epoch": 0.11883921357392943, "grad_norm": 0.8778317455167134, "learning_rate": 9.91323452093906e-06, "loss": 0.415944766998291, "num_input_tokens_seen": 72767128, "step": 1765, "train_runtime": 6833.7937, "train_tokens_per_second": 10648.131 }, { "epoch": 0.11917586856988957, "grad_norm": 0.8243033267562667, "learning_rate": 9.912743393714927e-06, "loss": 0.3919795274734497, "num_input_tokens_seen": 72980480, "step": 1770, "train_runtime": 6851.8307, "train_tokens_per_second": 10651.238 }, { "epoch": 0.11951252356584972, "grad_norm": 0.8266136372457167, "learning_rate": 9.912250892657769e-06, "loss": 0.4129928112030029, "num_input_tokens_seen": 73185608, "step": 1775, "train_runtime": 6870.6755, "train_tokens_per_second": 10651.88 }, { "epoch": 0.11984917856180986, "grad_norm": 0.9176766679895713, "learning_rate": 9.911757017905312e-06, "loss": 0.424575662612915, "num_input_tokens_seen": 73380904, "step": 1780, "train_runtime": 6888.8383, "train_tokens_per_second": 10652.145 }, { "epoch": 0.12018583355777, "grad_norm": 0.8031943882552417, "learning_rate": 9.911261769595668e-06, "loss": 0.41825156211853026, "num_input_tokens_seen": 73599424, "step": 1785, "train_runtime": 6908.8591, "train_tokens_per_second": 10652.906 }, { "epoch": 0.12052248855373014, "grad_norm": 0.8493265669449348, "learning_rate": 9.910765147867332e-06, "loss": 0.4233997344970703, "num_input_tokens_seen": 73807320, "step": 1790, "train_runtime": 6927.9535, "train_tokens_per_second": 10653.553 }, { "epoch": 0.12085914354969028, "grad_norm": 0.8419398252622229, "learning_rate": 9.91026715285918e-06, "loss": 0.42969331741333006, "num_input_tokens_seen": 74013296, "step": 1795, "train_runtime": 6947.6509, "train_tokens_per_second": 10652.996 }, { "epoch": 0.12119579854565042, "grad_norm": 0.9454421155743721, "learning_rate": 9.909767784710476e-06, "loss": 0.4584502220153809, "num_input_tokens_seen": 74237280, "step": 1800, "train_runtime": 6965.7477, "train_tokens_per_second": 10657.475 }, { "epoch": 0.12153245354161056, "grad_norm": 0.807534044916603, "learning_rate": 9.909267043560868e-06, "loss": 0.43119058609008787, "num_input_tokens_seen": 74444912, "step": 1805, "train_runtime": 6984.5017, "train_tokens_per_second": 10658.586 }, { "epoch": 0.1218691085375707, "grad_norm": 0.8009223378356172, "learning_rate": 9.908764929550388e-06, "loss": 0.42565412521362306, "num_input_tokens_seen": 74652264, "step": 1810, "train_runtime": 7002.4021, "train_tokens_per_second": 10660.951 }, { "epoch": 0.12220576353353084, "grad_norm": 0.8163111976269702, "learning_rate": 9.908261442819444e-06, "loss": 0.4196030616760254, "num_input_tokens_seen": 74845024, "step": 1815, "train_runtime": 7021.8776, "train_tokens_per_second": 10658.833 }, { "epoch": 0.12254241852949098, "grad_norm": 0.8529778232172465, "learning_rate": 9.907756583508842e-06, "loss": 0.4008845329284668, "num_input_tokens_seen": 75065128, "step": 1820, "train_runtime": 7040.9921, "train_tokens_per_second": 10661.158 }, { "epoch": 0.12287907352545112, "grad_norm": 0.7233827790734578, "learning_rate": 9.907250351759761e-06, "loss": 0.4091904640197754, "num_input_tokens_seen": 75274392, "step": 1825, "train_runtime": 7059.8948, "train_tokens_per_second": 10662.254 }, { "epoch": 0.12321572852141126, "grad_norm": 0.9068839226165174, "learning_rate": 9.906742747713766e-06, "loss": 0.4258375644683838, "num_input_tokens_seen": 75479680, "step": 1830, "train_runtime": 7079.2433, "train_tokens_per_second": 10662.111 }, { "epoch": 0.1235523835173714, "grad_norm": 0.9521604497939551, "learning_rate": 9.906233771512808e-06, "loss": 0.43643913269042967, "num_input_tokens_seen": 75678360, "step": 1835, "train_runtime": 7098.3971, "train_tokens_per_second": 10661.331 }, { "epoch": 0.12388903851333154, "grad_norm": 0.8981716477295378, "learning_rate": 9.905723423299222e-06, "loss": 0.4600534439086914, "num_input_tokens_seen": 75892168, "step": 1840, "train_runtime": 7117.9655, "train_tokens_per_second": 10662.059 }, { "epoch": 0.12422569350929168, "grad_norm": 0.8637180139659293, "learning_rate": 9.905211703215723e-06, "loss": 0.40131549835205077, "num_input_tokens_seen": 76092744, "step": 1845, "train_runtime": 7137.3223, "train_tokens_per_second": 10661.245 }, { "epoch": 0.12456234850525182, "grad_norm": 0.8382027434863565, "learning_rate": 9.904698611405412e-06, "loss": 0.4266026973724365, "num_input_tokens_seen": 76302800, "step": 1850, "train_runtime": 7154.9838, "train_tokens_per_second": 10664.287 }, { "epoch": 0.12489900350121196, "grad_norm": 0.7610144979672272, "learning_rate": 9.904184148011774e-06, "loss": 0.43503098487854003, "num_input_tokens_seen": 76506424, "step": 1855, "train_runtime": 7173.7473, "train_tokens_per_second": 10664.778 }, { "epoch": 0.1252356584971721, "grad_norm": 0.8635614518601293, "learning_rate": 9.903668313178681e-06, "loss": 0.4470223426818848, "num_input_tokens_seen": 76719608, "step": 1860, "train_runtime": 7193.198, "train_tokens_per_second": 10665.577 }, { "epoch": 0.12557231349313225, "grad_norm": 0.8577695573217499, "learning_rate": 9.903151107050377e-06, "loss": 0.3968682765960693, "num_input_tokens_seen": 76914656, "step": 1865, "train_runtime": 7211.9627, "train_tokens_per_second": 10664.872 }, { "epoch": 0.1259089684890924, "grad_norm": 0.732221797841643, "learning_rate": 9.902632529771502e-06, "loss": 0.43075971603393554, "num_input_tokens_seen": 77120776, "step": 1870, "train_runtime": 7231.3493, "train_tokens_per_second": 10664.784 }, { "epoch": 0.12624562348505253, "grad_norm": 0.9754806894014677, "learning_rate": 9.902112581487074e-06, "loss": 0.4284185886383057, "num_input_tokens_seen": 77330096, "step": 1875, "train_runtime": 7252.3736, "train_tokens_per_second": 10662.729 }, { "epoch": 0.12658227848101267, "grad_norm": 1.0658554998481438, "learning_rate": 9.901591262342494e-06, "loss": 0.4422458171844482, "num_input_tokens_seen": 77530648, "step": 1880, "train_runtime": 7273.52, "train_tokens_per_second": 10659.302 }, { "epoch": 0.1269189334769728, "grad_norm": 0.8962565125930877, "learning_rate": 9.901068572483548e-06, "loss": 0.4095472812652588, "num_input_tokens_seen": 77735080, "step": 1885, "train_runtime": 7292.2609, "train_tokens_per_second": 10659.942 }, { "epoch": 0.12725558847293295, "grad_norm": 0.8685570594720023, "learning_rate": 9.900544512056402e-06, "loss": 0.46703462600708007, "num_input_tokens_seen": 77950536, "step": 1890, "train_runtime": 7310.2447, "train_tokens_per_second": 10663.191 }, { "epoch": 0.12759224346889309, "grad_norm": 0.7457656303453225, "learning_rate": 9.900019081207612e-06, "loss": 0.4253969192504883, "num_input_tokens_seen": 78165728, "step": 1895, "train_runtime": 7329.5958, "train_tokens_per_second": 10664.398 }, { "epoch": 0.12792889846485322, "grad_norm": 1.316027819791204, "learning_rate": 9.89949228008411e-06, "loss": 0.4220001220703125, "num_input_tokens_seen": 78380944, "step": 1900, "train_runtime": 7349.6318, "train_tokens_per_second": 10664.608 }, { "epoch": 0.12826555346081336, "grad_norm": 0.8160693850022832, "learning_rate": 9.898964108833216e-06, "loss": 0.43538722991943357, "num_input_tokens_seen": 78592160, "step": 1905, "train_runtime": 7369.4363, "train_tokens_per_second": 10664.609 }, { "epoch": 0.1286022084567735, "grad_norm": 0.7819160913158283, "learning_rate": 9.898434567602629e-06, "loss": 0.39718780517578123, "num_input_tokens_seen": 78801920, "step": 1910, "train_runtime": 7388.6996, "train_tokens_per_second": 10665.195 }, { "epoch": 0.12893886345273364, "grad_norm": 0.9346508397920357, "learning_rate": 9.897903656540437e-06, "loss": 0.43187775611877444, "num_input_tokens_seen": 79008272, "step": 1915, "train_runtime": 7408.1753, "train_tokens_per_second": 10665.011 }, { "epoch": 0.12927551844869378, "grad_norm": 0.9258994185148072, "learning_rate": 9.897371375795103e-06, "loss": 0.442092227935791, "num_input_tokens_seen": 79210824, "step": 1920, "train_runtime": 7426.0473, "train_tokens_per_second": 10666.62 }, { "epoch": 0.12961217344465392, "grad_norm": 0.7813849242693964, "learning_rate": 9.896837725515484e-06, "loss": 0.44512271881103516, "num_input_tokens_seen": 79410136, "step": 1925, "train_runtime": 7444.7952, "train_tokens_per_second": 10666.531 }, { "epoch": 0.12994882844061406, "grad_norm": 0.6101297453432667, "learning_rate": 9.89630270585081e-06, "loss": 0.38402810096740725, "num_input_tokens_seen": 79613416, "step": 1930, "train_runtime": 7464.314, "train_tokens_per_second": 10665.872 }, { "epoch": 0.1302854834365742, "grad_norm": 0.8698105399800286, "learning_rate": 9.895766316950694e-06, "loss": 0.44153432846069335, "num_input_tokens_seen": 79819256, "step": 1935, "train_runtime": 7483.7555, "train_tokens_per_second": 10665.669 }, { "epoch": 0.13062213843253434, "grad_norm": 0.814400092620223, "learning_rate": 9.89522855896514e-06, "loss": 0.41197872161865234, "num_input_tokens_seen": 80035456, "step": 1940, "train_runtime": 7504.1305, "train_tokens_per_second": 10665.52 }, { "epoch": 0.13095879342849448, "grad_norm": 0.8691110713694135, "learning_rate": 9.89468943204453e-06, "loss": 0.4179690361022949, "num_input_tokens_seen": 80241008, "step": 1945, "train_runtime": 7524.4461, "train_tokens_per_second": 10664.042 }, { "epoch": 0.13129544842445462, "grad_norm": 0.916935344845284, "learning_rate": 9.89414893633963e-06, "loss": 0.41397871971130373, "num_input_tokens_seen": 80440480, "step": 1950, "train_runtime": 7543.1923, "train_tokens_per_second": 10663.984 }, { "epoch": 0.13163210342041476, "grad_norm": 0.788377652635603, "learning_rate": 9.893607072001584e-06, "loss": 0.43161377906799314, "num_input_tokens_seen": 80657728, "step": 1955, "train_runtime": 7562.508, "train_tokens_per_second": 10665.473 }, { "epoch": 0.1319687584163749, "grad_norm": 0.7207952626871745, "learning_rate": 9.893063839181925e-06, "loss": 0.420587158203125, "num_input_tokens_seen": 80863408, "step": 1960, "train_runtime": 7582.2778, "train_tokens_per_second": 10664.791 }, { "epoch": 0.13230541341233504, "grad_norm": 0.7565243815321462, "learning_rate": 9.892519238032566e-06, "loss": 0.4308616638183594, "num_input_tokens_seen": 81076432, "step": 1965, "train_runtime": 7600.9839, "train_tokens_per_second": 10666.571 }, { "epoch": 0.13264206840829518, "grad_norm": 0.7966796167333805, "learning_rate": 9.891973268705804e-06, "loss": 0.4394186496734619, "num_input_tokens_seen": 81278296, "step": 1970, "train_runtime": 7620.1454, "train_tokens_per_second": 10666.239 }, { "epoch": 0.13297872340425532, "grad_norm": 0.7686018760641162, "learning_rate": 9.891425931354316e-06, "loss": 0.4249259471893311, "num_input_tokens_seen": 81488704, "step": 1975, "train_runtime": 7638.6457, "train_tokens_per_second": 10667.952 }, { "epoch": 0.13331537840021546, "grad_norm": 0.829824305929578, "learning_rate": 9.890877226131165e-06, "loss": 0.4203059196472168, "num_input_tokens_seen": 81706432, "step": 1980, "train_runtime": 7657.5074, "train_tokens_per_second": 10670.108 }, { "epoch": 0.1336520333961756, "grad_norm": 0.8685464672036384, "learning_rate": 9.890327153189793e-06, "loss": 0.4323458671569824, "num_input_tokens_seen": 81915512, "step": 1985, "train_runtime": 7677.97, "train_tokens_per_second": 10668.902 }, { "epoch": 0.13398868839213574, "grad_norm": 0.8733476133732644, "learning_rate": 9.889775712684026e-06, "loss": 0.43114557266235354, "num_input_tokens_seen": 82127432, "step": 1990, "train_runtime": 7696.7256, "train_tokens_per_second": 10670.438 }, { "epoch": 0.13432534338809587, "grad_norm": 0.9096781079109404, "learning_rate": 9.889222904768074e-06, "loss": 0.42453479766845703, "num_input_tokens_seen": 82333072, "step": 1995, "train_runtime": 7715.1676, "train_tokens_per_second": 10671.586 }, { "epoch": 0.13466199838405601, "grad_norm": 0.862600101791322, "learning_rate": 9.888668729596528e-06, "loss": 0.4214371681213379, "num_input_tokens_seen": 82527408, "step": 2000, "train_runtime": 7735.3403, "train_tokens_per_second": 10668.879 }, { "epoch": 0.13499865338001615, "grad_norm": 0.9133787452026367, "learning_rate": 9.88811318732436e-06, "loss": 0.4205611228942871, "num_input_tokens_seen": 82725280, "step": 2005, "train_runtime": 7755.5665, "train_tokens_per_second": 10666.568 }, { "epoch": 0.1353353083759763, "grad_norm": 0.7968824850767627, "learning_rate": 9.887556278106927e-06, "loss": 0.4333763122558594, "num_input_tokens_seen": 82939560, "step": 2010, "train_runtime": 7774.3913, "train_tokens_per_second": 10668.303 }, { "epoch": 0.13567196337193643, "grad_norm": 0.7778736366868274, "learning_rate": 9.886998002099964e-06, "loss": 0.43096218109130857, "num_input_tokens_seen": 83154424, "step": 2015, "train_runtime": 7793.7421, "train_tokens_per_second": 10669.384 }, { "epoch": 0.13600861836789657, "grad_norm": 0.8809027995083507, "learning_rate": 9.886438359459595e-06, "loss": 0.45303845405578613, "num_input_tokens_seen": 83357800, "step": 2020, "train_runtime": 7812.8243, "train_tokens_per_second": 10669.356 }, { "epoch": 0.1363452733638567, "grad_norm": 0.7343340169774945, "learning_rate": 9.885877350342319e-06, "loss": 0.388365364074707, "num_input_tokens_seen": 83570680, "step": 2025, "train_runtime": 7831.8763, "train_tokens_per_second": 10670.582 }, { "epoch": 0.13668192835981685, "grad_norm": 0.7397022067424177, "learning_rate": 9.885314974905024e-06, "loss": 0.3842461347579956, "num_input_tokens_seen": 83791088, "step": 2030, "train_runtime": 7850.9375, "train_tokens_per_second": 10672.749 }, { "epoch": 0.137018583355777, "grad_norm": 0.8603258478247148, "learning_rate": 9.884751233304973e-06, "loss": 0.39946794509887695, "num_input_tokens_seen": 83984856, "step": 2035, "train_runtime": 7869.3831, "train_tokens_per_second": 10672.356 }, { "epoch": 0.13735523835173713, "grad_norm": 0.8309614540746859, "learning_rate": 9.884186125699816e-06, "loss": 0.4300520896911621, "num_input_tokens_seen": 84187424, "step": 2040, "train_runtime": 7888.6869, "train_tokens_per_second": 10671.919 }, { "epoch": 0.13769189334769727, "grad_norm": 0.8655651133387938, "learning_rate": 9.883619652247584e-06, "loss": 0.41631760597229006, "num_input_tokens_seen": 84395480, "step": 2045, "train_runtime": 7907.4643, "train_tokens_per_second": 10672.888 }, { "epoch": 0.1380285483436574, "grad_norm": 0.7129021677743062, "learning_rate": 9.883051813106687e-06, "loss": 0.383374285697937, "num_input_tokens_seen": 84605856, "step": 2050, "train_runtime": 7927.8433, "train_tokens_per_second": 10671.989 }, { "epoch": 0.13836520333961755, "grad_norm": 0.8757420807425996, "learning_rate": 9.882482608435924e-06, "loss": 0.44014887809753417, "num_input_tokens_seen": 84814832, "step": 2055, "train_runtime": 7947.0786, "train_tokens_per_second": 10672.454 }, { "epoch": 0.1387018583355777, "grad_norm": 0.8283405078311469, "learning_rate": 9.881912038394468e-06, "loss": 0.4327888488769531, "num_input_tokens_seen": 85024464, "step": 2060, "train_runtime": 7967.5705, "train_tokens_per_second": 10671.316 }, { "epoch": 0.13903851333153783, "grad_norm": 0.7428584745601357, "learning_rate": 9.881340103141878e-06, "loss": 0.4286364555358887, "num_input_tokens_seen": 85239184, "step": 2065, "train_runtime": 7987.6438, "train_tokens_per_second": 10671.38 }, { "epoch": 0.13937516832749797, "grad_norm": 0.8237651206696271, "learning_rate": 9.880766802838092e-06, "loss": 0.40738258361816404, "num_input_tokens_seen": 85444168, "step": 2070, "train_runtime": 8008.7729, "train_tokens_per_second": 10668.821 }, { "epoch": 0.1397118233234581, "grad_norm": 0.7295826500286611, "learning_rate": 9.880192137643434e-06, "loss": 0.40607576370239257, "num_input_tokens_seen": 85648032, "step": 2075, "train_runtime": 8027.4932, "train_tokens_per_second": 10669.337 }, { "epoch": 0.14004847831941827, "grad_norm": 0.8913153341378998, "learning_rate": 9.879616107718608e-06, "loss": 0.4286367416381836, "num_input_tokens_seen": 85851832, "step": 2080, "train_runtime": 8045.6365, "train_tokens_per_second": 10670.608 }, { "epoch": 0.1403851333153784, "grad_norm": 2.969263697977821, "learning_rate": 9.879038713224695e-06, "loss": 0.422914981842041, "num_input_tokens_seen": 86064376, "step": 2085, "train_runtime": 8066.0966, "train_tokens_per_second": 10669.892 }, { "epoch": 0.14072178831133855, "grad_norm": 0.8385047784498532, "learning_rate": 9.878459954323165e-06, "loss": 0.4079585075378418, "num_input_tokens_seen": 86274256, "step": 2090, "train_runtime": 8084.7748, "train_tokens_per_second": 10671.201 }, { "epoch": 0.1410584433072987, "grad_norm": 0.8226748293866323, "learning_rate": 9.877879831175865e-06, "loss": 0.4018754005432129, "num_input_tokens_seen": 86484576, "step": 2095, "train_runtime": 8102.8645, "train_tokens_per_second": 10673.334 }, { "epoch": 0.14139509830325883, "grad_norm": 0.738877132470077, "learning_rate": 9.877298343945025e-06, "loss": 0.416547966003418, "num_input_tokens_seen": 86694632, "step": 2100, "train_runtime": 8122.9124, "train_tokens_per_second": 10672.851 }, { "epoch": 0.14173175329921897, "grad_norm": 0.7679485283340541, "learning_rate": 9.876715492793256e-06, "loss": 0.41460371017456055, "num_input_tokens_seen": 86902408, "step": 2105, "train_runtime": 8142.8586, "train_tokens_per_second": 10672.224 }, { "epoch": 0.1420684082951791, "grad_norm": 0.7416359893413528, "learning_rate": 9.87613127788355e-06, "loss": 0.39178555011749266, "num_input_tokens_seen": 87102096, "step": 2110, "train_runtime": 8162.4625, "train_tokens_per_second": 10671.056 }, { "epoch": 0.14240506329113925, "grad_norm": 0.8221264043111595, "learning_rate": 9.87554569937928e-06, "loss": 0.46303644180297854, "num_input_tokens_seen": 87319112, "step": 2115, "train_runtime": 8181.3722, "train_tokens_per_second": 10672.918 }, { "epoch": 0.1427417182870994, "grad_norm": 0.8249386124530439, "learning_rate": 9.874958757444203e-06, "loss": 0.45568113327026366, "num_input_tokens_seen": 87538368, "step": 2120, "train_runtime": 8201.1663, "train_tokens_per_second": 10673.893 }, { "epoch": 0.14307837328305953, "grad_norm": 0.8198551983331464, "learning_rate": 9.874370452242454e-06, "loss": 0.43779993057250977, "num_input_tokens_seen": 87756640, "step": 2125, "train_runtime": 8220.1252, "train_tokens_per_second": 10675.828 }, { "epoch": 0.14341502827901967, "grad_norm": 0.8866932105304529, "learning_rate": 9.873780783938553e-06, "loss": 0.4540559768676758, "num_input_tokens_seen": 87962840, "step": 2130, "train_runtime": 8238.3615, "train_tokens_per_second": 10677.225 }, { "epoch": 0.1437516832749798, "grad_norm": 0.7960540986460095, "learning_rate": 9.873189752697396e-06, "loss": 0.39634294509887696, "num_input_tokens_seen": 88169712, "step": 2135, "train_runtime": 8256.9665, "train_tokens_per_second": 10678.221 }, { "epoch": 0.14408833827093995, "grad_norm": 0.8636168603494317, "learning_rate": 9.872597358684265e-06, "loss": 0.4605863571166992, "num_input_tokens_seen": 88368448, "step": 2140, "train_runtime": 8274.5583, "train_tokens_per_second": 10679.537 }, { "epoch": 0.1444249932669001, "grad_norm": 0.8147400498753216, "learning_rate": 9.872003602064816e-06, "loss": 0.43373727798461914, "num_input_tokens_seen": 88584536, "step": 2145, "train_runtime": 8292.236, "train_tokens_per_second": 10682.829 }, { "epoch": 0.14476164826286023, "grad_norm": 0.7362934874105656, "learning_rate": 9.8714084830051e-06, "loss": 0.4016655445098877, "num_input_tokens_seen": 88801544, "step": 2150, "train_runtime": 8310.6297, "train_tokens_per_second": 10685.297 }, { "epoch": 0.14509830325882037, "grad_norm": 0.7894277637894951, "learning_rate": 9.870812001671533e-06, "loss": 0.40799875259399415, "num_input_tokens_seen": 89014272, "step": 2155, "train_runtime": 8329.2917, "train_tokens_per_second": 10686.896 }, { "epoch": 0.1454349582547805, "grad_norm": 0.9010237247114223, "learning_rate": 9.870214158230922e-06, "loss": 0.4231081008911133, "num_input_tokens_seen": 89225416, "step": 2160, "train_runtime": 8348.3201, "train_tokens_per_second": 10687.829 }, { "epoch": 0.14577161325074064, "grad_norm": 0.7616432321713121, "learning_rate": 9.869614952850454e-06, "loss": 0.41712331771850586, "num_input_tokens_seen": 89433576, "step": 2165, "train_runtime": 8366.3434, "train_tokens_per_second": 10689.685 }, { "epoch": 0.14610826824670078, "grad_norm": 0.7451307530347692, "learning_rate": 9.86901438569769e-06, "loss": 0.42617435455322267, "num_input_tokens_seen": 89645960, "step": 2170, "train_runtime": 8385.0531, "train_tokens_per_second": 10691.162 }, { "epoch": 0.14644492324266092, "grad_norm": 0.8371270748360767, "learning_rate": 9.86841245694058e-06, "loss": 0.41733856201171876, "num_input_tokens_seen": 89833856, "step": 2175, "train_runtime": 8404.5977, "train_tokens_per_second": 10688.656 }, { "epoch": 0.14678157823862106, "grad_norm": 0.8245589306729242, "learning_rate": 9.86780916674745e-06, "loss": 0.45882349014282225, "num_input_tokens_seen": 90024640, "step": 2180, "train_runtime": 8424.6054, "train_tokens_per_second": 10685.918 }, { "epoch": 0.1471182332345812, "grad_norm": 0.85436932322421, "learning_rate": 9.86720451528701e-06, "loss": 0.41278553009033203, "num_input_tokens_seen": 90222336, "step": 2185, "train_runtime": 8444.4456, "train_tokens_per_second": 10684.223 }, { "epoch": 0.14745488823054134, "grad_norm": 0.8365345930825809, "learning_rate": 9.866598502728348e-06, "loss": 0.4382607460021973, "num_input_tokens_seen": 90420288, "step": 2190, "train_runtime": 8465.3321, "train_tokens_per_second": 10681.245 }, { "epoch": 0.14779154322650148, "grad_norm": 0.8349187913400021, "learning_rate": 9.865991129240931e-06, "loss": 0.4169161319732666, "num_input_tokens_seen": 90622968, "step": 2195, "train_runtime": 8483.9821, "train_tokens_per_second": 10681.655 }, { "epoch": 0.14812819822246162, "grad_norm": 0.824736739786115, "learning_rate": 9.865382394994614e-06, "loss": 0.4098381996154785, "num_input_tokens_seen": 90828080, "step": 2200, "train_runtime": 8502.6713, "train_tokens_per_second": 10682.299 }, { "epoch": 0.14846485321842176, "grad_norm": 0.6765426067584654, "learning_rate": 9.864772300159622e-06, "loss": 0.4035033226013184, "num_input_tokens_seen": 91032304, "step": 2205, "train_runtime": 8521.5176, "train_tokens_per_second": 10682.64 }, { "epoch": 0.1488015082143819, "grad_norm": 0.8372166174090198, "learning_rate": 9.864160844906571e-06, "loss": 0.43967313766479493, "num_input_tokens_seen": 91238504, "step": 2210, "train_runtime": 8539.5843, "train_tokens_per_second": 10684.186 }, { "epoch": 0.14913816321034204, "grad_norm": 0.7998775573106428, "learning_rate": 9.863548029406449e-06, "loss": 0.4187567710876465, "num_input_tokens_seen": 91445864, "step": 2215, "train_runtime": 8559.4356, "train_tokens_per_second": 10683.633 }, { "epoch": 0.14947481820630218, "grad_norm": 0.7914805197974979, "learning_rate": 9.86293385383063e-06, "loss": 0.3981011390686035, "num_input_tokens_seen": 91646608, "step": 2220, "train_runtime": 8578.9411, "train_tokens_per_second": 10682.741 }, { "epoch": 0.14981147320226232, "grad_norm": 1.2184651493702476, "learning_rate": 9.862318318350865e-06, "loss": 0.4453770160675049, "num_input_tokens_seen": 91855680, "step": 2225, "train_runtime": 8598.8699, "train_tokens_per_second": 10682.297 }, { "epoch": 0.15014812819822246, "grad_norm": 0.8094679881797694, "learning_rate": 9.861701423139287e-06, "loss": 0.3898141384124756, "num_input_tokens_seen": 92067360, "step": 2230, "train_runtime": 8616.7684, "train_tokens_per_second": 10684.674 }, { "epoch": 0.1504847831941826, "grad_norm": 0.8129195138563763, "learning_rate": 9.861083168368411e-06, "loss": 0.42241511344909666, "num_input_tokens_seen": 92279952, "step": 2235, "train_runtime": 8636.8986, "train_tokens_per_second": 10684.385 }, { "epoch": 0.15082143819014274, "grad_norm": 0.8715826873786572, "learning_rate": 9.860463554211125e-06, "loss": 0.38762698173522947, "num_input_tokens_seen": 92489504, "step": 2240, "train_runtime": 8655.676, "train_tokens_per_second": 10685.417 }, { "epoch": 0.15115809318610288, "grad_norm": 0.9498182433569043, "learning_rate": 9.859842580840706e-06, "loss": 0.46895246505737304, "num_input_tokens_seen": 92699728, "step": 2245, "train_runtime": 8674.2752, "train_tokens_per_second": 10686.74 }, { "epoch": 0.15149474818206302, "grad_norm": 0.6801678365495255, "learning_rate": 9.859220248430806e-06, "loss": 0.42631168365478517, "num_input_tokens_seen": 92921128, "step": 2250, "train_runtime": 8693.8381, "train_tokens_per_second": 10688.159 }, { "epoch": 0.15183140317802316, "grad_norm": 0.8036036625934626, "learning_rate": 9.85859655715546e-06, "loss": 0.4003633499145508, "num_input_tokens_seen": 93131672, "step": 2255, "train_runtime": 8714.5393, "train_tokens_per_second": 10686.93 }, { "epoch": 0.1521680581739833, "grad_norm": 0.8567415769071905, "learning_rate": 9.857971507189077e-06, "loss": 0.4152532577514648, "num_input_tokens_seen": 93339120, "step": 2260, "train_runtime": 8733.4762, "train_tokens_per_second": 10687.511 }, { "epoch": 0.15250471316994343, "grad_norm": 0.8818387463243377, "learning_rate": 9.857345098706455e-06, "loss": 0.4281785011291504, "num_input_tokens_seen": 93554328, "step": 2265, "train_runtime": 8753.3669, "train_tokens_per_second": 10687.811 }, { "epoch": 0.15284136816590357, "grad_norm": 0.8741953983559625, "learning_rate": 9.856717331882765e-06, "loss": 0.42978129386901853, "num_input_tokens_seen": 93748928, "step": 2270, "train_runtime": 8772.8309, "train_tokens_per_second": 10686.28 }, { "epoch": 0.1531780231618637, "grad_norm": 0.8029912839383654, "learning_rate": 9.85608820689356e-06, "loss": 0.39054055213928224, "num_input_tokens_seen": 93957920, "step": 2275, "train_runtime": 8792.666, "train_tokens_per_second": 10685.942 }, { "epoch": 0.15351467815782385, "grad_norm": 0.8036443737646346, "learning_rate": 9.855457723914772e-06, "loss": 0.40737552642822267, "num_input_tokens_seen": 94163800, "step": 2280, "train_runtime": 8810.1116, "train_tokens_per_second": 10688.151 }, { "epoch": 0.153851333153784, "grad_norm": 0.8793229377594315, "learning_rate": 9.854825883122713e-06, "loss": 0.4033447265625, "num_input_tokens_seen": 94363816, "step": 2285, "train_runtime": 8830.0565, "train_tokens_per_second": 10686.661 }, { "epoch": 0.15418798814974413, "grad_norm": 0.8205162373378678, "learning_rate": 9.85419268469408e-06, "loss": 0.4010470867156982, "num_input_tokens_seen": 94559144, "step": 2290, "train_runtime": 8848.6568, "train_tokens_per_second": 10686.271 }, { "epoch": 0.15452464314570427, "grad_norm": 0.7749478200476106, "learning_rate": 9.85355812880594e-06, "loss": 0.392416787147522, "num_input_tokens_seen": 94766288, "step": 2295, "train_runtime": 8868.1085, "train_tokens_per_second": 10686.189 }, { "epoch": 0.1548612981416644, "grad_norm": 0.7159927586241372, "learning_rate": 9.852922215635747e-06, "loss": 0.37967448234558104, "num_input_tokens_seen": 94974216, "step": 2300, "train_runtime": 8887.8406, "train_tokens_per_second": 10685.86 }, { "epoch": 0.15519795313762455, "grad_norm": 0.8192027377830481, "learning_rate": 9.85228494536133e-06, "loss": 0.43508014678955076, "num_input_tokens_seen": 95182536, "step": 2305, "train_runtime": 8906.4431, "train_tokens_per_second": 10686.93 }, { "epoch": 0.1555346081335847, "grad_norm": 0.7899706057058807, "learning_rate": 9.851646318160901e-06, "loss": 0.4236175537109375, "num_input_tokens_seen": 95387080, "step": 2310, "train_runtime": 8926.6794, "train_tokens_per_second": 10685.617 }, { "epoch": 0.15587126312954483, "grad_norm": 0.7033083634642274, "learning_rate": 9.85100633421305e-06, "loss": 0.38906378746032716, "num_input_tokens_seen": 95586888, "step": 2315, "train_runtime": 8947.1274, "train_tokens_per_second": 10683.528 }, { "epoch": 0.15620791812550497, "grad_norm": 0.8361568488560175, "learning_rate": 9.850364993696749e-06, "loss": 0.43230133056640624, "num_input_tokens_seen": 95789296, "step": 2320, "train_runtime": 8966.6837, "train_tokens_per_second": 10682.801 }, { "epoch": 0.15654457312146514, "grad_norm": 0.9184462362488928, "learning_rate": 9.849722296791339e-06, "loss": 0.4147991180419922, "num_input_tokens_seen": 95987344, "step": 2325, "train_runtime": 8985.1118, "train_tokens_per_second": 10682.933 }, { "epoch": 0.15688122811742528, "grad_norm": 0.8950663925777521, "learning_rate": 9.849078243676558e-06, "loss": 0.4368453502655029, "num_input_tokens_seen": 96189800, "step": 2330, "train_runtime": 9006.7879, "train_tokens_per_second": 10679.701 }, { "epoch": 0.15721788311338541, "grad_norm": 0.7128275688995169, "learning_rate": 9.848432834532506e-06, "loss": 0.39038972854614257, "num_input_tokens_seen": 96394768, "step": 2335, "train_runtime": 9026.8082, "train_tokens_per_second": 10678.721 }, { "epoch": 0.15755453810934555, "grad_norm": 0.7670233641627413, "learning_rate": 9.847786069539673e-06, "loss": 0.4296896457672119, "num_input_tokens_seen": 96604432, "step": 2340, "train_runtime": 9047.3879, "train_tokens_per_second": 10677.605 }, { "epoch": 0.1578911931053057, "grad_norm": 0.7867197901877502, "learning_rate": 9.847137948878926e-06, "loss": 0.4375267028808594, "num_input_tokens_seen": 96814656, "step": 2345, "train_runtime": 9064.7694, "train_tokens_per_second": 10680.322 }, { "epoch": 0.15822784810126583, "grad_norm": 0.907178047995538, "learning_rate": 9.846488472731505e-06, "loss": 0.4551233291625977, "num_input_tokens_seen": 97029352, "step": 2350, "train_runtime": 9083.2071, "train_tokens_per_second": 10682.279 }, { "epoch": 0.15856450309722597, "grad_norm": 0.7890494360939428, "learning_rate": 9.845837641279038e-06, "loss": 0.42661633491516116, "num_input_tokens_seen": 97244072, "step": 2355, "train_runtime": 9101.1154, "train_tokens_per_second": 10684.852 }, { "epoch": 0.1589011580931861, "grad_norm": 0.8358895281661181, "learning_rate": 9.845185454703528e-06, "loss": 0.4295192718505859, "num_input_tokens_seen": 97450704, "step": 2360, "train_runtime": 9121.3506, "train_tokens_per_second": 10683.802 }, { "epoch": 0.15923781308914625, "grad_norm": 0.7804619182920811, "learning_rate": 9.844531913187356e-06, "loss": 0.40438618659973147, "num_input_tokens_seen": 97655024, "step": 2365, "train_runtime": 9139.9171, "train_tokens_per_second": 10684.454 }, { "epoch": 0.1595744680851064, "grad_norm": 0.9550971223769664, "learning_rate": 9.84387701691328e-06, "loss": 0.4213782787322998, "num_input_tokens_seen": 97845904, "step": 2370, "train_runtime": 9160.6383, "train_tokens_per_second": 10681.123 }, { "epoch": 0.15991112308106653, "grad_norm": 0.9034117242408678, "learning_rate": 9.843220766064443e-06, "loss": 0.4268840789794922, "num_input_tokens_seen": 98039368, "step": 2375, "train_runtime": 9179.2895, "train_tokens_per_second": 10680.496 }, { "epoch": 0.16024777807702667, "grad_norm": 0.9484208565291508, "learning_rate": 9.842563160824364e-06, "loss": 0.43108630180358887, "num_input_tokens_seen": 98238280, "step": 2380, "train_runtime": 9198.3911, "train_tokens_per_second": 10679.942 }, { "epoch": 0.1605844330729868, "grad_norm": 0.8025916957961562, "learning_rate": 9.841904201376939e-06, "loss": 0.45601863861083985, "num_input_tokens_seen": 98454456, "step": 2385, "train_runtime": 9218.052, "train_tokens_per_second": 10680.614 }, { "epoch": 0.16092108806894695, "grad_norm": 0.8639590619785557, "learning_rate": 9.841243887906443e-06, "loss": 0.39296412467956543, "num_input_tokens_seen": 98660944, "step": 2390, "train_runtime": 9237.7405, "train_tokens_per_second": 10680.203 }, { "epoch": 0.1612577430649071, "grad_norm": 0.8427834162489, "learning_rate": 9.840582220597532e-06, "loss": 0.38774240016937256, "num_input_tokens_seen": 98868528, "step": 2395, "train_runtime": 9255.8807, "train_tokens_per_second": 10681.699 }, { "epoch": 0.16159439806086723, "grad_norm": 1.4212783951348429, "learning_rate": 9.839919199635238e-06, "loss": 0.4487201690673828, "num_input_tokens_seen": 99077904, "step": 2400, "train_runtime": 9275.1707, "train_tokens_per_second": 10682.057 }, { "epoch": 0.16193105305682737, "grad_norm": 0.7528901508517034, "learning_rate": 9.839254825204973e-06, "loss": 0.4350761413574219, "num_input_tokens_seen": 99291928, "step": 2405, "train_runtime": 9295.4691, "train_tokens_per_second": 10681.755 }, { "epoch": 0.1622677080527875, "grad_norm": 0.8496980701994122, "learning_rate": 9.838589097492527e-06, "loss": 0.42038254737854003, "num_input_tokens_seen": 99497032, "step": 2410, "train_runtime": 9315.8601, "train_tokens_per_second": 10680.391 }, { "epoch": 0.16260436304874765, "grad_norm": 0.8897975671789583, "learning_rate": 9.83792201668407e-06, "loss": 0.4159724235534668, "num_input_tokens_seen": 99710544, "step": 2415, "train_runtime": 9334.6366, "train_tokens_per_second": 10681.781 }, { "epoch": 0.16294101804470779, "grad_norm": 0.9295825705263189, "learning_rate": 9.837253582966146e-06, "loss": 0.4370729446411133, "num_input_tokens_seen": 99920584, "step": 2420, "train_runtime": 9353.9696, "train_tokens_per_second": 10682.158 }, { "epoch": 0.16327767304066793, "grad_norm": 5.006279055036305, "learning_rate": 9.836583796525686e-06, "loss": 0.39238533973693845, "num_input_tokens_seen": 100112392, "step": 2425, "train_runtime": 9374.1892, "train_tokens_per_second": 10679.579 }, { "epoch": 0.16361432803662807, "grad_norm": 0.8180004044188124, "learning_rate": 9.835912657549986e-06, "loss": 0.4532860279083252, "num_input_tokens_seen": 100322120, "step": 2430, "train_runtime": 9394.2094, "train_tokens_per_second": 10679.145 }, { "epoch": 0.1639509830325882, "grad_norm": 0.9312788918681126, "learning_rate": 9.835240166226734e-06, "loss": 0.39463860988616944, "num_input_tokens_seen": 100521400, "step": 2435, "train_runtime": 9413.0432, "train_tokens_per_second": 10678.948 }, { "epoch": 0.16428763802854834, "grad_norm": 0.768464146885512, "learning_rate": 9.834566322743987e-06, "loss": 0.4353370666503906, "num_input_tokens_seen": 100722064, "step": 2440, "train_runtime": 9431.776, "train_tokens_per_second": 10679.014 }, { "epoch": 0.16462429302450848, "grad_norm": 0.7804935741892106, "learning_rate": 9.833891127290186e-06, "loss": 0.4258899688720703, "num_input_tokens_seen": 100941736, "step": 2445, "train_runtime": 9449.7964, "train_tokens_per_second": 10681.895 }, { "epoch": 0.16496094802046862, "grad_norm": 0.763507961452628, "learning_rate": 9.833214580054145e-06, "loss": 0.40638346672058107, "num_input_tokens_seen": 101148088, "step": 2450, "train_runtime": 9469.16, "train_tokens_per_second": 10681.844 }, { "epoch": 0.16529760301642876, "grad_norm": 0.81903229143611, "learning_rate": 9.832536681225058e-06, "loss": 0.4587855815887451, "num_input_tokens_seen": 101356320, "step": 2455, "train_runtime": 9487.2564, "train_tokens_per_second": 10683.417 }, { "epoch": 0.1656342580123889, "grad_norm": 0.9974647664337114, "learning_rate": 9.831857430992497e-06, "loss": 0.3987353563308716, "num_input_tokens_seen": 101559104, "step": 2460, "train_runtime": 9506.1804, "train_tokens_per_second": 10683.482 }, { "epoch": 0.16597091300834904, "grad_norm": 0.8043391494270331, "learning_rate": 9.831176829546416e-06, "loss": 0.41919445991516113, "num_input_tokens_seen": 101766040, "step": 2465, "train_runtime": 9525.4928, "train_tokens_per_second": 10683.546 }, { "epoch": 0.16630756800430918, "grad_norm": 0.9514658916918233, "learning_rate": 9.830494877077137e-06, "loss": 0.4713226318359375, "num_input_tokens_seen": 101981832, "step": 2470, "train_runtime": 9543.677, "train_tokens_per_second": 10685.801 }, { "epoch": 0.16664422300026932, "grad_norm": 0.8472937662674767, "learning_rate": 9.82981157377537e-06, "loss": 0.41448001861572265, "num_input_tokens_seen": 102185152, "step": 2475, "train_runtime": 9565.3113, "train_tokens_per_second": 10682.888 }, { "epoch": 0.16698087799622946, "grad_norm": 0.7840631089182251, "learning_rate": 9.829126919832198e-06, "loss": 0.38814828395843504, "num_input_tokens_seen": 102389952, "step": 2480, "train_runtime": 9585.1626, "train_tokens_per_second": 10682.13 }, { "epoch": 0.1673175329921896, "grad_norm": 0.7220909070722416, "learning_rate": 9.82844091543908e-06, "loss": 0.4396186828613281, "num_input_tokens_seen": 102609088, "step": 2485, "train_runtime": 9606.0366, "train_tokens_per_second": 10681.73 }, { "epoch": 0.16765418798814974, "grad_norm": 0.7724614526847672, "learning_rate": 9.82775356078786e-06, "loss": 0.40910587310791013, "num_input_tokens_seen": 102812208, "step": 2490, "train_runtime": 9625.5958, "train_tokens_per_second": 10681.127 }, { "epoch": 0.16799084298410988, "grad_norm": 0.7383796481552539, "learning_rate": 9.82706485607075e-06, "loss": 0.3530332088470459, "num_input_tokens_seen": 103009448, "step": 2495, "train_runtime": 9645.0637, "train_tokens_per_second": 10680.017 }, { "epoch": 0.16832749798007002, "grad_norm": 0.7615933587157595, "learning_rate": 9.826374801480346e-06, "loss": 0.4113924026489258, "num_input_tokens_seen": 103206768, "step": 2500, "train_runtime": 9664.7593, "train_tokens_per_second": 10678.669 }, { "epoch": 0.16866415297603016, "grad_norm": 0.7753247547098113, "learning_rate": 9.825683397209617e-06, "loss": 0.4148609161376953, "num_input_tokens_seen": 103389840, "step": 2505, "train_runtime": 9683.7325, "train_tokens_per_second": 10676.652 }, { "epoch": 0.1690008079719903, "grad_norm": 0.7747072978135988, "learning_rate": 9.824990643451915e-06, "loss": 0.413633918762207, "num_input_tokens_seen": 103603832, "step": 2510, "train_runtime": 9703.9519, "train_tokens_per_second": 10676.458 }, { "epoch": 0.16933746296795044, "grad_norm": 0.7387627070736908, "learning_rate": 9.824296540400965e-06, "loss": 0.40469703674316404, "num_input_tokens_seen": 103822472, "step": 2515, "train_runtime": 9722.733, "train_tokens_per_second": 10678.322 }, { "epoch": 0.16967411796391058, "grad_norm": 0.9352000674878359, "learning_rate": 9.823601088250872e-06, "loss": 0.4368617534637451, "num_input_tokens_seen": 104021984, "step": 2520, "train_runtime": 9742.4037, "train_tokens_per_second": 10677.24 }, { "epoch": 0.17001077295987072, "grad_norm": 0.8304725413263454, "learning_rate": 9.822904287196114e-06, "loss": 0.4295315742492676, "num_input_tokens_seen": 104222272, "step": 2525, "train_runtime": 9761.3218, "train_tokens_per_second": 10677.065 }, { "epoch": 0.17034742795583085, "grad_norm": 0.7600229602905635, "learning_rate": 9.822206137431553e-06, "loss": 0.39794790744781494, "num_input_tokens_seen": 104431536, "step": 2530, "train_runtime": 9781.1117, "train_tokens_per_second": 10676.858 }, { "epoch": 0.170684082951791, "grad_norm": 0.7387132285065549, "learning_rate": 9.821506639152421e-06, "loss": 0.42319750785827637, "num_input_tokens_seen": 104634960, "step": 2535, "train_runtime": 9799.9965, "train_tokens_per_second": 10677.041 }, { "epoch": 0.17102073794775113, "grad_norm": 0.781807922332195, "learning_rate": 9.820805792554334e-06, "loss": 0.39918150901794436, "num_input_tokens_seen": 104846384, "step": 2540, "train_runtime": 9819.9498, "train_tokens_per_second": 10676.876 }, { "epoch": 0.17135739294371127, "grad_norm": 0.9316393702032948, "learning_rate": 9.820103597833278e-06, "loss": 0.4073935508728027, "num_input_tokens_seen": 105055520, "step": 2545, "train_runtime": 9839.2843, "train_tokens_per_second": 10677.151 }, { "epoch": 0.1716940479396714, "grad_norm": 0.7626197736099503, "learning_rate": 9.819400055185622e-06, "loss": 0.3999081373214722, "num_input_tokens_seen": 105259200, "step": 2550, "train_runtime": 9858.2983, "train_tokens_per_second": 10677.218 }, { "epoch": 0.17203070293563155, "grad_norm": 0.9353106582506023, "learning_rate": 9.818695164808108e-06, "loss": 0.4074892997741699, "num_input_tokens_seen": 105466832, "step": 2555, "train_runtime": 9879.0857, "train_tokens_per_second": 10675.768 }, { "epoch": 0.1723673579315917, "grad_norm": 0.8048106413255709, "learning_rate": 9.817988926897856e-06, "loss": 0.3937970161437988, "num_input_tokens_seen": 105675024, "step": 2560, "train_runtime": 9899.0931, "train_tokens_per_second": 10675.223 }, { "epoch": 0.17270401292755186, "grad_norm": 0.8679703985857153, "learning_rate": 9.817281341652367e-06, "loss": 0.4128702640533447, "num_input_tokens_seen": 105886768, "step": 2565, "train_runtime": 9918.4935, "train_tokens_per_second": 10675.691 }, { "epoch": 0.173040667923512, "grad_norm": 0.8064761172889058, "learning_rate": 9.816572409269508e-06, "loss": 0.39209208488464353, "num_input_tokens_seen": 106100112, "step": 2570, "train_runtime": 9937.9059, "train_tokens_per_second": 10676.305 }, { "epoch": 0.17337732291947214, "grad_norm": 0.7302996925729051, "learning_rate": 9.815862129947537e-06, "loss": 0.4044454097747803, "num_input_tokens_seen": 106307224, "step": 2575, "train_runtime": 9956.7039, "train_tokens_per_second": 10676.949 }, { "epoch": 0.17371397791543228, "grad_norm": 0.7049323118584873, "learning_rate": 9.815150503885078e-06, "loss": 0.3796691417694092, "num_input_tokens_seen": 106517480, "step": 2580, "train_runtime": 9975.0077, "train_tokens_per_second": 10678.436 }, { "epoch": 0.17405063291139242, "grad_norm": 0.8156336490455081, "learning_rate": 9.814437531281133e-06, "loss": 0.4041304588317871, "num_input_tokens_seen": 106727664, "step": 2585, "train_runtime": 9996.9851, "train_tokens_per_second": 10675.985 }, { "epoch": 0.17438728790735256, "grad_norm": 0.9779189324842646, "learning_rate": 9.813723212335085e-06, "loss": 0.43491640090942385, "num_input_tokens_seen": 106923344, "step": 2590, "train_runtime": 10016.7668, "train_tokens_per_second": 10674.437 }, { "epoch": 0.1747239429033127, "grad_norm": 0.7859074187313112, "learning_rate": 9.813007547246691e-06, "loss": 0.391992974281311, "num_input_tokens_seen": 107129952, "step": 2595, "train_runtime": 10036.3614, "train_tokens_per_second": 10674.182 }, { "epoch": 0.17506059789927284, "grad_norm": 0.7710349611390589, "learning_rate": 9.812290536216083e-06, "loss": 0.456257963180542, "num_input_tokens_seen": 107321760, "step": 2600, "train_runtime": 10056.5493, "train_tokens_per_second": 10671.828 }, { "epoch": 0.17539725289523297, "grad_norm": 0.7764866332136362, "learning_rate": 9.811572179443773e-06, "loss": 0.39283225536346433, "num_input_tokens_seen": 107534808, "step": 2605, "train_runtime": 10075.4305, "train_tokens_per_second": 10672.974 }, { "epoch": 0.17573390789119311, "grad_norm": 0.791977371371534, "learning_rate": 9.810852477130645e-06, "loss": 0.4047110080718994, "num_input_tokens_seen": 107733200, "step": 2610, "train_runtime": 10095.7886, "train_tokens_per_second": 10671.103 }, { "epoch": 0.17607056288715325, "grad_norm": 0.8303585128328085, "learning_rate": 9.810131429477964e-06, "loss": 0.39269165992736815, "num_input_tokens_seen": 107944896, "step": 2615, "train_runtime": 10113.7705, "train_tokens_per_second": 10673.062 }, { "epoch": 0.1764072178831134, "grad_norm": 0.800595799396048, "learning_rate": 9.809409036687364e-06, "loss": 0.3958165407180786, "num_input_tokens_seen": 108151920, "step": 2620, "train_runtime": 10133.3235, "train_tokens_per_second": 10672.897 }, { "epoch": 0.17674387287907353, "grad_norm": 0.7045729670867898, "learning_rate": 9.808685298960867e-06, "loss": 0.4164566993713379, "num_input_tokens_seen": 108365952, "step": 2625, "train_runtime": 10151.0397, "train_tokens_per_second": 10675.355 }, { "epoch": 0.17708052787503367, "grad_norm": 0.7563658432715352, "learning_rate": 9.807960216500858e-06, "loss": 0.42152814865112304, "num_input_tokens_seen": 108570680, "step": 2630, "train_runtime": 10170.6343, "train_tokens_per_second": 10674.917 }, { "epoch": 0.1774171828709938, "grad_norm": 0.7320042353416759, "learning_rate": 9.807233789510106e-06, "loss": 0.38150384426116946, "num_input_tokens_seen": 108773208, "step": 2635, "train_runtime": 10191.1906, "train_tokens_per_second": 10673.258 }, { "epoch": 0.17775383786695395, "grad_norm": 0.7321640752277211, "learning_rate": 9.806506018191754e-06, "loss": 0.3987225770950317, "num_input_tokens_seen": 108982472, "step": 2640, "train_runtime": 10211.1571, "train_tokens_per_second": 10672.882 }, { "epoch": 0.1780904928629141, "grad_norm": 0.8293668016708937, "learning_rate": 9.80577690274932e-06, "loss": 0.4022545337677002, "num_input_tokens_seen": 109192168, "step": 2645, "train_runtime": 10229.6129, "train_tokens_per_second": 10674.125 }, { "epoch": 0.17842714785887423, "grad_norm": 0.6202745070780746, "learning_rate": 9.8050464433867e-06, "loss": 0.3769534111022949, "num_input_tokens_seen": 109404608, "step": 2650, "train_runtime": 10248.2614, "train_tokens_per_second": 10675.431 }, { "epoch": 0.17876380285483437, "grad_norm": 1.0091393060663567, "learning_rate": 9.804314640308165e-06, "loss": 0.439023494720459, "num_input_tokens_seen": 109622672, "step": 2655, "train_runtime": 10267.9447, "train_tokens_per_second": 10676.204 }, { "epoch": 0.1791004578507945, "grad_norm": 0.8213851093008653, "learning_rate": 9.803581493718361e-06, "loss": 0.41071929931640627, "num_input_tokens_seen": 109828312, "step": 2660, "train_runtime": 10287.4491, "train_tokens_per_second": 10675.952 }, { "epoch": 0.17943711284675465, "grad_norm": 0.747652624318304, "learning_rate": 9.80284700382231e-06, "loss": 0.4192197799682617, "num_input_tokens_seen": 110047696, "step": 2665, "train_runtime": 10307.1355, "train_tokens_per_second": 10676.846 }, { "epoch": 0.1797737678427148, "grad_norm": 0.7600662161395381, "learning_rate": 9.802111170825408e-06, "loss": 0.4078816413879395, "num_input_tokens_seen": 110260832, "step": 2670, "train_runtime": 10326.1632, "train_tokens_per_second": 10677.812 }, { "epoch": 0.18011042283867493, "grad_norm": 0.6779421739429478, "learning_rate": 9.80137399493343e-06, "loss": 0.4123178005218506, "num_input_tokens_seen": 110463096, "step": 2675, "train_runtime": 10344.0747, "train_tokens_per_second": 10678.876 }, { "epoch": 0.18044707783463507, "grad_norm": 1.0297183295415027, "learning_rate": 9.800635476352525e-06, "loss": 0.3960280418395996, "num_input_tokens_seen": 110653200, "step": 2680, "train_runtime": 10363.4582, "train_tokens_per_second": 10677.247 }, { "epoch": 0.1807837328305952, "grad_norm": 0.7948260395372255, "learning_rate": 9.799895615289218e-06, "loss": 0.39124040603637694, "num_input_tokens_seen": 110851856, "step": 2685, "train_runtime": 10383.5858, "train_tokens_per_second": 10675.682 }, { "epoch": 0.18112038782655535, "grad_norm": 0.765973600166989, "learning_rate": 9.799154411950407e-06, "loss": 0.4416506767272949, "num_input_tokens_seen": 111071328, "step": 2690, "train_runtime": 10402.704, "train_tokens_per_second": 10677.159 }, { "epoch": 0.18145704282251549, "grad_norm": 0.7723063862026821, "learning_rate": 9.79841186654337e-06, "loss": 0.4037912368774414, "num_input_tokens_seen": 111271952, "step": 2695, "train_runtime": 10421.191, "train_tokens_per_second": 10677.47 }, { "epoch": 0.18179369781847562, "grad_norm": 0.8616693819585222, "learning_rate": 9.797667979275752e-06, "loss": 0.43509693145751954, "num_input_tokens_seen": 111470272, "step": 2700, "train_runtime": 10439.8891, "train_tokens_per_second": 10677.343 }, { "epoch": 0.18213035281443576, "grad_norm": 0.7361031903661451, "learning_rate": 9.796922750355584e-06, "loss": 0.38787758350372314, "num_input_tokens_seen": 111670520, "step": 2705, "train_runtime": 10457.5153, "train_tokens_per_second": 10678.495 }, { "epoch": 0.1824670078103959, "grad_norm": 0.8802752148662836, "learning_rate": 9.796176179991266e-06, "loss": 0.43028106689453127, "num_input_tokens_seen": 111876552, "step": 2710, "train_runtime": 10477.2316, "train_tokens_per_second": 10678.064 }, { "epoch": 0.18280366280635604, "grad_norm": 0.7686059808252189, "learning_rate": 9.795428268391572e-06, "loss": 0.40622763633728026, "num_input_tokens_seen": 112071280, "step": 2715, "train_runtime": 10497.2376, "train_tokens_per_second": 10676.264 }, { "epoch": 0.18314031780231618, "grad_norm": 0.8847624779179257, "learning_rate": 9.794679015765655e-06, "loss": 0.4124784469604492, "num_input_tokens_seen": 112272888, "step": 2720, "train_runtime": 10516.7732, "train_tokens_per_second": 10675.602 }, { "epoch": 0.18347697279827632, "grad_norm": 0.9097674015218516, "learning_rate": 9.793928422323041e-06, "loss": 0.4103695869445801, "num_input_tokens_seen": 112484968, "step": 2725, "train_runtime": 10536.5437, "train_tokens_per_second": 10675.699 }, { "epoch": 0.18381362779423646, "grad_norm": 0.9052698941119895, "learning_rate": 9.793176488273629e-06, "loss": 0.41200456619262693, "num_input_tokens_seen": 112678840, "step": 2730, "train_runtime": 10555.7003, "train_tokens_per_second": 10674.691 }, { "epoch": 0.1841502827901966, "grad_norm": 0.8571514362226168, "learning_rate": 9.792423213827697e-06, "loss": 0.387072229385376, "num_input_tokens_seen": 112884176, "step": 2735, "train_runtime": 10575.6629, "train_tokens_per_second": 10673.957 }, { "epoch": 0.18448693778615674, "grad_norm": 0.7565307674307971, "learning_rate": 9.791668599195897e-06, "loss": 0.39119548797607423, "num_input_tokens_seen": 113094456, "step": 2740, "train_runtime": 10593.7875, "train_tokens_per_second": 10675.545 }, { "epoch": 0.18482359278211688, "grad_norm": 0.7506854981633858, "learning_rate": 9.790912644589248e-06, "loss": 0.42231478691101076, "num_input_tokens_seen": 113291848, "step": 2745, "train_runtime": 10615.4745, "train_tokens_per_second": 10672.33 }, { "epoch": 0.18516024777807702, "grad_norm": 0.8083120947917324, "learning_rate": 9.790155350219159e-06, "loss": 0.3947108507156372, "num_input_tokens_seen": 113500056, "step": 2750, "train_runtime": 10635.4613, "train_tokens_per_second": 10671.851 }, { "epoch": 0.18549690277403716, "grad_norm": 0.7288808882124775, "learning_rate": 9.789396716297399e-06, "loss": 0.4087664127349854, "num_input_tokens_seen": 113715224, "step": 2755, "train_runtime": 10654.2994, "train_tokens_per_second": 10673.177 }, { "epoch": 0.1858335577699973, "grad_norm": 0.8152238628132533, "learning_rate": 9.788636743036122e-06, "loss": 0.3852862358093262, "num_input_tokens_seen": 113915024, "step": 2760, "train_runtime": 10673.977, "train_tokens_per_second": 10672.219 }, { "epoch": 0.18617021276595744, "grad_norm": 1.0813338558580123, "learning_rate": 9.787875430647847e-06, "loss": 0.3970200061798096, "num_input_tokens_seen": 114122440, "step": 2765, "train_runtime": 10693.8126, "train_tokens_per_second": 10671.82 }, { "epoch": 0.18650686776191758, "grad_norm": 0.7744685755969747, "learning_rate": 9.787112779345477e-06, "loss": 0.40085949897766116, "num_input_tokens_seen": 114317368, "step": 2770, "train_runtime": 10713.6837, "train_tokens_per_second": 10670.221 }, { "epoch": 0.18684352275787772, "grad_norm": 0.824802286502042, "learning_rate": 9.786348789342283e-06, "loss": 0.4393282413482666, "num_input_tokens_seen": 114524400, "step": 2775, "train_runtime": 10734.6431, "train_tokens_per_second": 10668.673 }, { "epoch": 0.18718017775383786, "grad_norm": 0.7350503564401507, "learning_rate": 9.785583460851912e-06, "loss": 0.4030846118927002, "num_input_tokens_seen": 114736808, "step": 2780, "train_runtime": 10755.2815, "train_tokens_per_second": 10667.95 }, { "epoch": 0.187516832749798, "grad_norm": 0.7436949946783754, "learning_rate": 9.784816794088386e-06, "loss": 0.4147237777709961, "num_input_tokens_seen": 114955272, "step": 2785, "train_runtime": 10774.4665, "train_tokens_per_second": 10669.231 }, { "epoch": 0.18785348774575814, "grad_norm": 0.798770819010382, "learning_rate": 9.784048789266101e-06, "loss": 0.39918994903564453, "num_input_tokens_seen": 115152736, "step": 2790, "train_runtime": 10793.0282, "train_tokens_per_second": 10669.178 }, { "epoch": 0.18819014274171827, "grad_norm": 0.7182409401201103, "learning_rate": 9.78327944659983e-06, "loss": 0.4135266304016113, "num_input_tokens_seen": 115358136, "step": 2795, "train_runtime": 10813.8892, "train_tokens_per_second": 10667.59 }, { "epoch": 0.18852679773767841, "grad_norm": 0.7719159189581015, "learning_rate": 9.78250876630471e-06, "loss": 0.40374116897583007, "num_input_tokens_seen": 115555408, "step": 2800, "train_runtime": 10834.0938, "train_tokens_per_second": 10665.904 }, { "epoch": 0.18886345273363855, "grad_norm": 0.9464942127268501, "learning_rate": 9.781736748596267e-06, "loss": 0.4015201568603516, "num_input_tokens_seen": 115753216, "step": 2805, "train_runtime": 10852.5164, "train_tokens_per_second": 10666.025 }, { "epoch": 0.18920010772959872, "grad_norm": 0.6651250299796013, "learning_rate": 9.78096339369039e-06, "loss": 0.38889615535736083, "num_input_tokens_seen": 115950376, "step": 2810, "train_runtime": 10870.3787, "train_tokens_per_second": 10666.636 }, { "epoch": 0.18953676272555886, "grad_norm": 0.7273428798520221, "learning_rate": 9.780188701803345e-06, "loss": 0.42763471603393555, "num_input_tokens_seen": 116158624, "step": 2815, "train_runtime": 10891.3286, "train_tokens_per_second": 10665.239 }, { "epoch": 0.189873417721519, "grad_norm": 0.7658741534801341, "learning_rate": 9.779412673151772e-06, "loss": 0.41707601547241213, "num_input_tokens_seen": 116371968, "step": 2820, "train_runtime": 10911.002, "train_tokens_per_second": 10665.562 }, { "epoch": 0.19021007271747914, "grad_norm": 0.7204172601452988, "learning_rate": 9.778635307952686e-06, "loss": 0.41555171012878417, "num_input_tokens_seen": 116583896, "step": 2825, "train_runtime": 10931.3144, "train_tokens_per_second": 10665.131 }, { "epoch": 0.19054672771343928, "grad_norm": 0.8337307534877905, "learning_rate": 9.777856606423472e-06, "loss": 0.4061650276184082, "num_input_tokens_seen": 116795496, "step": 2830, "train_runtime": 10950.8246, "train_tokens_per_second": 10665.452 }, { "epoch": 0.19088338270939942, "grad_norm": 0.7665597930815005, "learning_rate": 9.777076568781897e-06, "loss": 0.43362088203430177, "num_input_tokens_seen": 116985352, "step": 2835, "train_runtime": 10970.4244, "train_tokens_per_second": 10663.703 }, { "epoch": 0.19122003770535956, "grad_norm": 0.6691526468644446, "learning_rate": 9.77629519524609e-06, "loss": 0.3745547294616699, "num_input_tokens_seen": 117188128, "step": 2840, "train_runtime": 10989.8009, "train_tokens_per_second": 10663.353 }, { "epoch": 0.1915566927013197, "grad_norm": 0.7047795893556512, "learning_rate": 9.775512486034564e-06, "loss": 0.41118564605712893, "num_input_tokens_seen": 117391720, "step": 2845, "train_runtime": 11010.2184, "train_tokens_per_second": 10662.07 }, { "epoch": 0.19189334769727984, "grad_norm": 0.7925232322012965, "learning_rate": 9.774728441366197e-06, "loss": 0.42744855880737304, "num_input_tokens_seen": 117587968, "step": 2850, "train_runtime": 11029.5848, "train_tokens_per_second": 10661.142 }, { "epoch": 0.19223000269323998, "grad_norm": 0.723607121974921, "learning_rate": 9.773943061460249e-06, "loss": 0.39412357807159426, "num_input_tokens_seen": 117787800, "step": 2855, "train_runtime": 11049.3537, "train_tokens_per_second": 10660.153 }, { "epoch": 0.19256665768920012, "grad_norm": 0.8144389302789469, "learning_rate": 9.773156346536345e-06, "loss": 0.43053302764892576, "num_input_tokens_seen": 117992808, "step": 2860, "train_runtime": 11068.6469, "train_tokens_per_second": 10660.093 }, { "epoch": 0.19290331268516026, "grad_norm": 0.7664908292546913, "learning_rate": 9.772368296814489e-06, "loss": 0.3973098278045654, "num_input_tokens_seen": 118198264, "step": 2865, "train_runtime": 11087.346, "train_tokens_per_second": 10660.645 }, { "epoch": 0.1932399676811204, "grad_norm": 0.747961498338228, "learning_rate": 9.771578912515058e-06, "loss": 0.4420153141021729, "num_input_tokens_seen": 118403136, "step": 2870, "train_runtime": 11106.5236, "train_tokens_per_second": 10660.684 }, { "epoch": 0.19357662267708053, "grad_norm": 0.8076173031670907, "learning_rate": 9.7707881938588e-06, "loss": 0.3960169076919556, "num_input_tokens_seen": 118610728, "step": 2875, "train_runtime": 11125.2189, "train_tokens_per_second": 10661.429 }, { "epoch": 0.19391327767304067, "grad_norm": 0.7494888797117295, "learning_rate": 9.769996141066836e-06, "loss": 0.43148102760314944, "num_input_tokens_seen": 118830192, "step": 2880, "train_runtime": 11143.3, "train_tokens_per_second": 10663.824 }, { "epoch": 0.1942499326690008, "grad_norm": 0.7103489268587918, "learning_rate": 9.76920275436066e-06, "loss": 0.42076621055603025, "num_input_tokens_seen": 119050880, "step": 2885, "train_runtime": 11161.6587, "train_tokens_per_second": 10666.056 }, { "epoch": 0.19458658766496095, "grad_norm": 0.7485001228941556, "learning_rate": 9.768408033962145e-06, "loss": 0.4385850429534912, "num_input_tokens_seen": 119261040, "step": 2890, "train_runtime": 11181.3214, "train_tokens_per_second": 10666.095 }, { "epoch": 0.1949232426609211, "grad_norm": 0.7788982051847765, "learning_rate": 9.767611980093525e-06, "loss": 0.41283378601074217, "num_input_tokens_seen": 119471272, "step": 2895, "train_runtime": 11200.9282, "train_tokens_per_second": 10666.194 }, { "epoch": 0.19525989765688123, "grad_norm": 0.7354431397518827, "learning_rate": 9.76681459297742e-06, "loss": 0.4186208724975586, "num_input_tokens_seen": 119679472, "step": 2900, "train_runtime": 11220.8079, "train_tokens_per_second": 10665.852 }, { "epoch": 0.19559655265284137, "grad_norm": 0.8564584206893389, "learning_rate": 9.766015872836814e-06, "loss": 0.46146721839904786, "num_input_tokens_seen": 119892272, "step": 2905, "train_runtime": 11240.1553, "train_tokens_per_second": 10666.425 }, { "epoch": 0.1959332076488015, "grad_norm": 0.9596780789888537, "learning_rate": 9.765215819895066e-06, "loss": 0.42627744674682616, "num_input_tokens_seen": 120109448, "step": 2910, "train_runtime": 11258.8489, "train_tokens_per_second": 10668.004 }, { "epoch": 0.19626986264476165, "grad_norm": 0.7920900288407947, "learning_rate": 9.76441443437591e-06, "loss": 0.383670973777771, "num_input_tokens_seen": 120323608, "step": 2915, "train_runtime": 11277.4026, "train_tokens_per_second": 10669.443 }, { "epoch": 0.1966065176407218, "grad_norm": 1.1099717413322796, "learning_rate": 9.76361171650345e-06, "loss": 0.42893314361572266, "num_input_tokens_seen": 120524072, "step": 2920, "train_runtime": 11298.2719, "train_tokens_per_second": 10667.478 }, { "epoch": 0.19694317263668193, "grad_norm": 0.8061194545512923, "learning_rate": 9.762807666502164e-06, "loss": 0.4137547016143799, "num_input_tokens_seen": 120724264, "step": 2925, "train_runtime": 11317.6624, "train_tokens_per_second": 10666.89 }, { "epoch": 0.19727982763264207, "grad_norm": 1.48082401220653, "learning_rate": 9.762002284596898e-06, "loss": 0.4218252182006836, "num_input_tokens_seen": 120927784, "step": 2930, "train_runtime": 11339.8517, "train_tokens_per_second": 10663.965 }, { "epoch": 0.1976164826286022, "grad_norm": 0.8623662066248609, "learning_rate": 9.761195571012882e-06, "loss": 0.432908821105957, "num_input_tokens_seen": 121124984, "step": 2935, "train_runtime": 11358.1303, "train_tokens_per_second": 10664.166 }, { "epoch": 0.19795313762456235, "grad_norm": 0.7688921040100593, "learning_rate": 9.760387525975705e-06, "loss": 0.4021341323852539, "num_input_tokens_seen": 121336112, "step": 2940, "train_runtime": 11376.8174, "train_tokens_per_second": 10665.207 }, { "epoch": 0.1982897926205225, "grad_norm": 0.7445332479375185, "learning_rate": 9.759578149711337e-06, "loss": 0.3632680892944336, "num_input_tokens_seen": 121552464, "step": 2945, "train_runtime": 11397.2349, "train_tokens_per_second": 10665.084 }, { "epoch": 0.19862644761648263, "grad_norm": 0.7168027487476629, "learning_rate": 9.758767442446117e-06, "loss": 0.39040987491607665, "num_input_tokens_seen": 121769040, "step": 2950, "train_runtime": 11416.4278, "train_tokens_per_second": 10666.124 }, { "epoch": 0.19896310261244277, "grad_norm": 0.7613367505084957, "learning_rate": 9.757955404406755e-06, "loss": 0.38323972225189207, "num_input_tokens_seen": 121977936, "step": 2955, "train_runtime": 11435.7641, "train_tokens_per_second": 10666.356 }, { "epoch": 0.1992997576084029, "grad_norm": 0.8175014500622216, "learning_rate": 9.757142035820337e-06, "loss": 0.3876933574676514, "num_input_tokens_seen": 122168416, "step": 2960, "train_runtime": 11454.8463, "train_tokens_per_second": 10665.217 }, { "epoch": 0.19963641260436304, "grad_norm": 0.8907506215434677, "learning_rate": 9.756327336914318e-06, "loss": 0.41463346481323243, "num_input_tokens_seen": 122369272, "step": 2965, "train_runtime": 11475.5662, "train_tokens_per_second": 10663.463 }, { "epoch": 0.19997306760032318, "grad_norm": 1.0987757743698798, "learning_rate": 9.755511307916526e-06, "loss": 0.41399354934692384, "num_input_tokens_seen": 122573136, "step": 2970, "train_runtime": 11494.3208, "train_tokens_per_second": 10663.8 }, { "epoch": 0.20030972259628332, "grad_norm": 0.8015572532581626, "learning_rate": 9.754693949055161e-06, "loss": 0.4187516212463379, "num_input_tokens_seen": 122787744, "step": 2975, "train_runtime": 11512.3732, "train_tokens_per_second": 10665.72 }, { "epoch": 0.20064637759224346, "grad_norm": 0.7794450214531995, "learning_rate": 9.753875260558795e-06, "loss": 0.4371305465698242, "num_input_tokens_seen": 122977312, "step": 2980, "train_runtime": 11530.4554, "train_tokens_per_second": 10665.434 }, { "epoch": 0.2009830325882036, "grad_norm": 0.8123888129992862, "learning_rate": 9.75305524265637e-06, "loss": 0.39745876789093015, "num_input_tokens_seen": 123192680, "step": 2985, "train_runtime": 11549.0463, "train_tokens_per_second": 10666.914 }, { "epoch": 0.20131968758416374, "grad_norm": 0.9138241367701013, "learning_rate": 9.752233895577205e-06, "loss": 0.4039150238037109, "num_input_tokens_seen": 123387168, "step": 2990, "train_runtime": 11566.982, "train_tokens_per_second": 10667.188 }, { "epoch": 0.20165634258012388, "grad_norm": 0.7079585414509154, "learning_rate": 9.751411219550984e-06, "loss": 0.4085063934326172, "num_input_tokens_seen": 123592160, "step": 2995, "train_runtime": 11586.2584, "train_tokens_per_second": 10667.133 }, { "epoch": 0.20199299757608402, "grad_norm": 0.9188667790789445, "learning_rate": 9.750587214807766e-06, "loss": 0.3970187664031982, "num_input_tokens_seen": 123791328, "step": 3000, "train_runtime": 11606.8526, "train_tokens_per_second": 10665.366 }, { "epoch": 0.20232965257204416, "grad_norm": 0.8339636313396449, "learning_rate": 9.749761881577981e-06, "loss": 0.41858229637145994, "num_input_tokens_seen": 124008048, "step": 3005, "train_runtime": 11628.2329, "train_tokens_per_second": 10664.393 }, { "epoch": 0.2026663075680043, "grad_norm": 0.7356891641454895, "learning_rate": 9.748935220092434e-06, "loss": 0.3991279125213623, "num_input_tokens_seen": 124216656, "step": 3010, "train_runtime": 11647.7503, "train_tokens_per_second": 10664.433 }, { "epoch": 0.20300296256396444, "grad_norm": 0.8824832620714803, "learning_rate": 9.748107230582295e-06, "loss": 0.4004825592041016, "num_input_tokens_seen": 124409808, "step": 3015, "train_runtime": 11666.1411, "train_tokens_per_second": 10664.178 }, { "epoch": 0.20333961755992458, "grad_norm": 0.714936501807228, "learning_rate": 9.747277913279109e-06, "loss": 0.4592285633087158, "num_input_tokens_seen": 124616496, "step": 3020, "train_runtime": 11687.6565, "train_tokens_per_second": 10662.231 }, { "epoch": 0.20367627255588472, "grad_norm": 0.701229445446051, "learning_rate": 9.746447268414794e-06, "loss": 0.44213094711303713, "num_input_tokens_seen": 124832208, "step": 3025, "train_runtime": 11706.028, "train_tokens_per_second": 10663.925 }, { "epoch": 0.20401292755184486, "grad_norm": 0.9358418827786709, "learning_rate": 9.745615296221635e-06, "loss": 0.4098640441894531, "num_input_tokens_seen": 125046768, "step": 3030, "train_runtime": 11724.9843, "train_tokens_per_second": 10664.984 }, { "epoch": 0.204349582547805, "grad_norm": 0.7475465541500227, "learning_rate": 9.74478199693229e-06, "loss": 0.43330631256103513, "num_input_tokens_seen": 125260480, "step": 3035, "train_runtime": 11744.8366, "train_tokens_per_second": 10665.153 }, { "epoch": 0.20468623754376514, "grad_norm": 0.8409160052456424, "learning_rate": 9.743947370779791e-06, "loss": 0.4305333137512207, "num_input_tokens_seen": 125474840, "step": 3040, "train_runtime": 11763.9473, "train_tokens_per_second": 10666.049 }, { "epoch": 0.20502289253972528, "grad_norm": 0.821942922340096, "learning_rate": 9.743111417997536e-06, "loss": 0.42463269233703616, "num_input_tokens_seen": 125686856, "step": 3045, "train_runtime": 11783.3545, "train_tokens_per_second": 10666.475 }, { "epoch": 0.20535954753568542, "grad_norm": 0.8143682140293748, "learning_rate": 9.742274138819298e-06, "loss": 0.4255844593048096, "num_input_tokens_seen": 125891536, "step": 3050, "train_runtime": 11801.7527, "train_tokens_per_second": 10667.19 }, { "epoch": 0.20569620253164558, "grad_norm": 0.8361142730652172, "learning_rate": 9.74143553347922e-06, "loss": 0.4511284828186035, "num_input_tokens_seen": 126100624, "step": 3055, "train_runtime": 11820.1745, "train_tokens_per_second": 10668.254 }, { "epoch": 0.20603285752760572, "grad_norm": 0.7482019039158514, "learning_rate": 9.740595602211814e-06, "loss": 0.4029798984527588, "num_input_tokens_seen": 126308456, "step": 3060, "train_runtime": 11837.966, "train_tokens_per_second": 10669.777 }, { "epoch": 0.20636951252356586, "grad_norm": 0.7385516615927556, "learning_rate": 9.739754345251963e-06, "loss": 0.385905385017395, "num_input_tokens_seen": 126504016, "step": 3065, "train_runtime": 11857.258, "train_tokens_per_second": 10668.91 }, { "epoch": 0.206706167519526, "grad_norm": 0.7362279639272101, "learning_rate": 9.738911762834924e-06, "loss": 0.3616596221923828, "num_input_tokens_seen": 126712096, "step": 3070, "train_runtime": 11875.7545, "train_tokens_per_second": 10669.814 }, { "epoch": 0.20704282251548614, "grad_norm": 0.8662006421618345, "learning_rate": 9.738067855196323e-06, "loss": 0.40332698822021484, "num_input_tokens_seen": 126917064, "step": 3075, "train_runtime": 11893.9348, "train_tokens_per_second": 10670.738 }, { "epoch": 0.20737947751144628, "grad_norm": 0.8519921641328394, "learning_rate": 9.737222622572153e-06, "loss": 0.44964938163757323, "num_input_tokens_seen": 127117984, "step": 3080, "train_runtime": 11912.8303, "train_tokens_per_second": 10670.679 }, { "epoch": 0.20771613250740642, "grad_norm": 1.0275158129830106, "learning_rate": 9.736376065198784e-06, "loss": 0.4180001258850098, "num_input_tokens_seen": 127330944, "step": 3085, "train_runtime": 11931.4886, "train_tokens_per_second": 10671.841 }, { "epoch": 0.20805278750336656, "grad_norm": 0.8543856049715004, "learning_rate": 9.735528183312951e-06, "loss": 0.3993419408798218, "num_input_tokens_seen": 127549752, "step": 3090, "train_runtime": 11950.8194, "train_tokens_per_second": 10672.888 }, { "epoch": 0.2083894424993267, "grad_norm": 0.7658184277021092, "learning_rate": 9.734678977151762e-06, "loss": 0.38107881546020506, "num_input_tokens_seen": 127754312, "step": 3095, "train_runtime": 11970.66, "train_tokens_per_second": 10672.286 }, { "epoch": 0.20872609749528684, "grad_norm": 0.8493059748760365, "learning_rate": 9.733828446952696e-06, "loss": 0.40283756256103515, "num_input_tokens_seen": 127964344, "step": 3100, "train_runtime": 11989.8732, "train_tokens_per_second": 10672.702 }, { "epoch": 0.20906275249124698, "grad_norm": 0.7506162940161502, "learning_rate": 9.732976592953598e-06, "loss": 0.40561561584472655, "num_input_tokens_seen": 128179888, "step": 3105, "train_runtime": 12010.4305, "train_tokens_per_second": 10672.381 }, { "epoch": 0.20939940748720712, "grad_norm": 0.7625807882814194, "learning_rate": 9.73212341539269e-06, "loss": 0.4047882556915283, "num_input_tokens_seen": 128392968, "step": 3110, "train_runtime": 12031.3789, "train_tokens_per_second": 10671.509 }, { "epoch": 0.20973606248316726, "grad_norm": 0.7394846267111655, "learning_rate": 9.731268914508556e-06, "loss": 0.3971658945083618, "num_input_tokens_seen": 128599112, "step": 3115, "train_runtime": 12051.6337, "train_tokens_per_second": 10670.679 }, { "epoch": 0.2100727174791274, "grad_norm": 0.7368668506717214, "learning_rate": 9.730413090540158e-06, "loss": 0.3833997488021851, "num_input_tokens_seen": 128808352, "step": 3120, "train_runtime": 12070.7913, "train_tokens_per_second": 10671.078 }, { "epoch": 0.21040937247508754, "grad_norm": 0.7365583513297386, "learning_rate": 9.729555943726825e-06, "loss": 0.39826254844665526, "num_input_tokens_seen": 129011480, "step": 3125, "train_runtime": 12091.5527, "train_tokens_per_second": 10669.554 }, { "epoch": 0.21074602747104768, "grad_norm": 0.7478873685350521, "learning_rate": 9.728697474308253e-06, "loss": 0.40678815841674804, "num_input_tokens_seen": 129212664, "step": 3130, "train_runtime": 12110.9931, "train_tokens_per_second": 10669.04 }, { "epoch": 0.21108268246700782, "grad_norm": 0.7755654858208861, "learning_rate": 9.72783768252451e-06, "loss": 0.38765246868133546, "num_input_tokens_seen": 129410272, "step": 3135, "train_runtime": 12129.8024, "train_tokens_per_second": 10668.786 }, { "epoch": 0.21141933746296795, "grad_norm": 0.7743170259648143, "learning_rate": 9.726976568616036e-06, "loss": 0.4079334259033203, "num_input_tokens_seen": 129608008, "step": 3140, "train_runtime": 12148.6987, "train_tokens_per_second": 10668.468 }, { "epoch": 0.2117559924589281, "grad_norm": 0.8990052674891492, "learning_rate": 9.726114132823638e-06, "loss": 0.39177870750427246, "num_input_tokens_seen": 129813432, "step": 3145, "train_runtime": 12167.1669, "train_tokens_per_second": 10669.159 }, { "epoch": 0.21209264745488823, "grad_norm": 0.7507893003846524, "learning_rate": 9.725250375388493e-06, "loss": 0.42183618545532225, "num_input_tokens_seen": 130013744, "step": 3150, "train_runtime": 12187.6148, "train_tokens_per_second": 10667.694 }, { "epoch": 0.21242930245084837, "grad_norm": 0.809717986142705, "learning_rate": 9.724385296552147e-06, "loss": 0.4328293323516846, "num_input_tokens_seen": 130221680, "step": 3155, "train_runtime": 12205.8624, "train_tokens_per_second": 10668.782 }, { "epoch": 0.2127659574468085, "grad_norm": 0.8738478878630684, "learning_rate": 9.72351889655652e-06, "loss": 0.41585025787353513, "num_input_tokens_seen": 130431656, "step": 3160, "train_runtime": 12224.2366, "train_tokens_per_second": 10669.922 }, { "epoch": 0.21310261244276865, "grad_norm": 0.7938453566548515, "learning_rate": 9.722651175643895e-06, "loss": 0.40381717681884766, "num_input_tokens_seen": 130637056, "step": 3165, "train_runtime": 12242.5071, "train_tokens_per_second": 10670.776 }, { "epoch": 0.2134392674387288, "grad_norm": 0.7377188457586745, "learning_rate": 9.721782134056928e-06, "loss": 0.36607069969177247, "num_input_tokens_seen": 130846816, "step": 3170, "train_runtime": 12262.2726, "train_tokens_per_second": 10670.682 }, { "epoch": 0.21377592243468893, "grad_norm": 0.7058628930202414, "learning_rate": 9.720911772038645e-06, "loss": 0.4207786560058594, "num_input_tokens_seen": 131059360, "step": 3175, "train_runtime": 12281.2536, "train_tokens_per_second": 10671.497 }, { "epoch": 0.21411257743064907, "grad_norm": 0.8850294304525206, "learning_rate": 9.720040089832436e-06, "loss": 0.4127528667449951, "num_input_tokens_seen": 131247088, "step": 3180, "train_runtime": 12302.2609, "train_tokens_per_second": 10668.534 }, { "epoch": 0.2144492324266092, "grad_norm": 0.7088545696576372, "learning_rate": 9.719167087682069e-06, "loss": 0.3799713134765625, "num_input_tokens_seen": 131457032, "step": 3185, "train_runtime": 12323.7135, "train_tokens_per_second": 10666.998 }, { "epoch": 0.21478588742256935, "grad_norm": 0.7997569900015749, "learning_rate": 9.718292765831673e-06, "loss": 0.40279474258422854, "num_input_tokens_seen": 131669000, "step": 3190, "train_runtime": 12342.7985, "train_tokens_per_second": 10667.678 }, { "epoch": 0.2151225424185295, "grad_norm": 0.7984551065407496, "learning_rate": 9.71741712452575e-06, "loss": 0.4149317741394043, "num_input_tokens_seen": 131876968, "step": 3195, "train_runtime": 12361.1575, "train_tokens_per_second": 10668.659 }, { "epoch": 0.21545919741448963, "grad_norm": 0.7826797021638917, "learning_rate": 9.716540164009174e-06, "loss": 0.3906437635421753, "num_input_tokens_seen": 132069880, "step": 3200, "train_runtime": 12380.8168, "train_tokens_per_second": 10667.299 }, { "epoch": 0.21579585241044977, "grad_norm": 0.8041515342833753, "learning_rate": 9.715661884527178e-06, "loss": 0.41373729705810547, "num_input_tokens_seen": 132282472, "step": 3205, "train_runtime": 12400.1855, "train_tokens_per_second": 10667.782 }, { "epoch": 0.2161325074064099, "grad_norm": 0.8559945883924337, "learning_rate": 9.714782286325374e-06, "loss": 0.4097625732421875, "num_input_tokens_seen": 132490816, "step": 3210, "train_runtime": 12420.6176, "train_tokens_per_second": 10667.007 }, { "epoch": 0.21646916240237005, "grad_norm": 0.8122321640536513, "learning_rate": 9.713901369649738e-06, "loss": 0.3985300064086914, "num_input_tokens_seen": 132698864, "step": 3215, "train_runtime": 12440.4461, "train_tokens_per_second": 10666.729 }, { "epoch": 0.2168058173983302, "grad_norm": 0.7634865789071675, "learning_rate": 9.713019134746618e-06, "loss": 0.3912019729614258, "num_input_tokens_seen": 132917416, "step": 3220, "train_runtime": 12458.7836, "train_tokens_per_second": 10668.571 }, { "epoch": 0.21714247239429033, "grad_norm": 0.7362975796526748, "learning_rate": 9.712135581862722e-06, "loss": 0.4021367073059082, "num_input_tokens_seen": 133133624, "step": 3225, "train_runtime": 12479.2605, "train_tokens_per_second": 10668.39 }, { "epoch": 0.21747912739025047, "grad_norm": 0.757070528138669, "learning_rate": 9.711250711245139e-06, "loss": 0.4103682518005371, "num_input_tokens_seen": 133336552, "step": 3230, "train_runtime": 12499.2095, "train_tokens_per_second": 10667.599 }, { "epoch": 0.2178157823862106, "grad_norm": 0.7465761013439177, "learning_rate": 9.710364523141317e-06, "loss": 0.41610050201416016, "num_input_tokens_seen": 133547720, "step": 3235, "train_runtime": 12520.3736, "train_tokens_per_second": 10666.432 }, { "epoch": 0.21815243738217074, "grad_norm": 0.7484077255809186, "learning_rate": 9.709477017799076e-06, "loss": 0.427622127532959, "num_input_tokens_seen": 133755024, "step": 3240, "train_runtime": 12538.6738, "train_tokens_per_second": 10667.398 }, { "epoch": 0.21848909237813088, "grad_norm": 0.8266392274137228, "learning_rate": 9.708588195466604e-06, "loss": 0.41709127426147463, "num_input_tokens_seen": 133961368, "step": 3245, "train_runtime": 12557.2609, "train_tokens_per_second": 10668.04 }, { "epoch": 0.21882574737409102, "grad_norm": 0.7033343523037864, "learning_rate": 9.707698056392458e-06, "loss": 0.4131514549255371, "num_input_tokens_seen": 134165376, "step": 3250, "train_runtime": 12576.2232, "train_tokens_per_second": 10668.177 }, { "epoch": 0.21916240237005116, "grad_norm": 0.8373570126769121, "learning_rate": 9.706806600825562e-06, "loss": 0.41636366844177247, "num_input_tokens_seen": 134368120, "step": 3255, "train_runtime": 12596.5206, "train_tokens_per_second": 10667.082 }, { "epoch": 0.2194990573660113, "grad_norm": 0.9983743725437877, "learning_rate": 9.70591382901521e-06, "loss": 0.4256845474243164, "num_input_tokens_seen": 134572016, "step": 3260, "train_runtime": 12615.9096, "train_tokens_per_second": 10666.85 }, { "epoch": 0.21983571236197144, "grad_norm": 0.7214771149054097, "learning_rate": 9.705019741211061e-06, "loss": 0.3921862840652466, "num_input_tokens_seen": 134780584, "step": 3265, "train_runtime": 12636.7416, "train_tokens_per_second": 10665.77 }, { "epoch": 0.22017236735793158, "grad_norm": 0.8130085005847847, "learning_rate": 9.704124337663145e-06, "loss": 0.39963316917419434, "num_input_tokens_seen": 134992368, "step": 3270, "train_runtime": 12656.1616, "train_tokens_per_second": 10666.138 }, { "epoch": 0.22050902235389172, "grad_norm": 0.8435048329418073, "learning_rate": 9.703227618621859e-06, "loss": 0.4107822895050049, "num_input_tokens_seen": 135202448, "step": 3275, "train_runtime": 12674.7374, "train_tokens_per_second": 10667.081 }, { "epoch": 0.22084567734985186, "grad_norm": 0.8025145200115495, "learning_rate": 9.702329584337965e-06, "loss": 0.4170698165893555, "num_input_tokens_seen": 135395496, "step": 3280, "train_runtime": 12696.2197, "train_tokens_per_second": 10664.237 }, { "epoch": 0.221182332345812, "grad_norm": 0.8795202020689726, "learning_rate": 9.701430235062599e-06, "loss": 0.42885870933532716, "num_input_tokens_seen": 135597904, "step": 3285, "train_runtime": 12716.7778, "train_tokens_per_second": 10662.914 }, { "epoch": 0.22151898734177214, "grad_norm": 0.9371773616112886, "learning_rate": 9.700529571047259e-06, "loss": 0.4384544849395752, "num_input_tokens_seen": 135799056, "step": 3290, "train_runtime": 12736.7357, "train_tokens_per_second": 10661.998 }, { "epoch": 0.22185564233773228, "grad_norm": 0.8255467593195367, "learning_rate": 9.699627592543814e-06, "loss": 0.39978694915771484, "num_input_tokens_seen": 136003392, "step": 3295, "train_runtime": 12757.2553, "train_tokens_per_second": 10660.866 }, { "epoch": 0.22219229733369245, "grad_norm": 0.7400622966342034, "learning_rate": 9.698724299804498e-06, "loss": 0.4204193115234375, "num_input_tokens_seen": 136213504, "step": 3300, "train_runtime": 12776.9421, "train_tokens_per_second": 10660.885 }, { "epoch": 0.22252895232965259, "grad_norm": 0.7617711354361751, "learning_rate": 9.697819693081915e-06, "loss": 0.41207451820373536, "num_input_tokens_seen": 136421256, "step": 3305, "train_runtime": 12795.4662, "train_tokens_per_second": 10661.687 }, { "epoch": 0.22286560732561272, "grad_norm": 0.8705157871732759, "learning_rate": 9.696913772629034e-06, "loss": 0.3896224021911621, "num_input_tokens_seen": 136631080, "step": 3310, "train_runtime": 12815.2006, "train_tokens_per_second": 10661.642 }, { "epoch": 0.22320226232157286, "grad_norm": 0.7504516316067272, "learning_rate": 9.696006538699195e-06, "loss": 0.43175435066223145, "num_input_tokens_seen": 136837144, "step": 3315, "train_runtime": 12833.3735, "train_tokens_per_second": 10662.601 }, { "epoch": 0.223538917317533, "grad_norm": 0.8533410731585238, "learning_rate": 9.695097991546102e-06, "loss": 0.4202885627746582, "num_input_tokens_seen": 137024256, "step": 3320, "train_runtime": 12852.7399, "train_tokens_per_second": 10661.093 }, { "epoch": 0.22387557231349314, "grad_norm": 0.8068582596867908, "learning_rate": 9.694188131423828e-06, "loss": 0.3909752607345581, "num_input_tokens_seen": 137228104, "step": 3325, "train_runtime": 12872.3673, "train_tokens_per_second": 10660.673 }, { "epoch": 0.22421222730945328, "grad_norm": 0.7818782406858779, "learning_rate": 9.693276958586809e-06, "loss": 0.4512490749359131, "num_input_tokens_seen": 137438264, "step": 3330, "train_runtime": 12892.3098, "train_tokens_per_second": 10660.484 }, { "epoch": 0.22454888230541342, "grad_norm": 0.7229467046340613, "learning_rate": 9.692364473289856e-06, "loss": 0.38381471633911135, "num_input_tokens_seen": 137640384, "step": 3335, "train_runtime": 12911.1639, "train_tokens_per_second": 10660.571 }, { "epoch": 0.22488553730137356, "grad_norm": 0.7766624829408972, "learning_rate": 9.69145067578814e-06, "loss": 0.3817091941833496, "num_input_tokens_seen": 137851352, "step": 3340, "train_runtime": 12929.8334, "train_tokens_per_second": 10661.495 }, { "epoch": 0.2252221922973337, "grad_norm": 0.8194672968183372, "learning_rate": 9.690535566337205e-06, "loss": 0.4504354000091553, "num_input_tokens_seen": 138059248, "step": 3345, "train_runtime": 12950.2129, "train_tokens_per_second": 10660.77 }, { "epoch": 0.22555884729329384, "grad_norm": 0.7957502083668059, "learning_rate": 9.689619145192955e-06, "loss": 0.4221219062805176, "num_input_tokens_seen": 138268304, "step": 3350, "train_runtime": 12971.3323, "train_tokens_per_second": 10659.53 }, { "epoch": 0.22589550228925398, "grad_norm": 0.7077921084689657, "learning_rate": 9.688701412611663e-06, "loss": 0.4029393672943115, "num_input_tokens_seen": 138483760, "step": 3355, "train_runtime": 12990.6215, "train_tokens_per_second": 10660.287 }, { "epoch": 0.22623215728521412, "grad_norm": 0.7597409302991369, "learning_rate": 9.687782368849973e-06, "loss": 0.4076250076293945, "num_input_tokens_seen": 138691320, "step": 3360, "train_runtime": 13010.9872, "train_tokens_per_second": 10659.554 }, { "epoch": 0.22656881228117426, "grad_norm": 0.748758734892406, "learning_rate": 9.686862014164893e-06, "loss": 0.38603734970092773, "num_input_tokens_seen": 138904208, "step": 3365, "train_runtime": 13031.4173, "train_tokens_per_second": 10659.179 }, { "epoch": 0.2269054672771344, "grad_norm": 0.8054787239907997, "learning_rate": 9.685940348813795e-06, "loss": 0.38964552879333497, "num_input_tokens_seen": 139110344, "step": 3370, "train_runtime": 13051.7557, "train_tokens_per_second": 10658.363 }, { "epoch": 0.22724212227309454, "grad_norm": 0.7901404233889147, "learning_rate": 9.685017373054421e-06, "loss": 0.39953246116638186, "num_input_tokens_seen": 139317720, "step": 3375, "train_runtime": 13071.8241, "train_tokens_per_second": 10657.864 }, { "epoch": 0.22757877726905468, "grad_norm": 0.7466849244761063, "learning_rate": 9.68409308714488e-06, "loss": 0.40087251663208007, "num_input_tokens_seen": 139521896, "step": 3380, "train_runtime": 13092.2756, "train_tokens_per_second": 10656.81 }, { "epoch": 0.22791543226501482, "grad_norm": 0.7363071079856944, "learning_rate": 9.68316749134364e-06, "loss": 0.40204634666442873, "num_input_tokens_seen": 139739376, "step": 3385, "train_runtime": 13112.308, "train_tokens_per_second": 10657.115 }, { "epoch": 0.22825208726097496, "grad_norm": 0.7676653462702518, "learning_rate": 9.682240585909545e-06, "loss": 0.379516077041626, "num_input_tokens_seen": 139939104, "step": 3390, "train_runtime": 13132.4317, "train_tokens_per_second": 10655.993 }, { "epoch": 0.2285887422569351, "grad_norm": 0.9559269694063456, "learning_rate": 9.681312371101803e-06, "loss": 0.3650658130645752, "num_input_tokens_seen": 140154320, "step": 3395, "train_runtime": 13151.1451, "train_tokens_per_second": 10657.195 }, { "epoch": 0.22892539725289524, "grad_norm": 0.818531752921934, "learning_rate": 9.680382847179984e-06, "loss": 0.4145817279815674, "num_input_tokens_seen": 140360536, "step": 3400, "train_runtime": 13172.7673, "train_tokens_per_second": 10655.357 }, { "epoch": 0.22926205224885537, "grad_norm": 1.0591513445492282, "learning_rate": 9.679452014404025e-06, "loss": 0.4058515548706055, "num_input_tokens_seen": 140558592, "step": 3405, "train_runtime": 13192.239, "train_tokens_per_second": 10654.643 }, { "epoch": 0.22959870724481551, "grad_norm": 0.817736985274923, "learning_rate": 9.678519873034234e-06, "loss": 0.4392539024353027, "num_input_tokens_seen": 140772336, "step": 3410, "train_runtime": 13212.1769, "train_tokens_per_second": 10654.742 }, { "epoch": 0.22993536224077565, "grad_norm": 0.9125186079823369, "learning_rate": 9.677586423331277e-06, "loss": 0.42935638427734374, "num_input_tokens_seen": 140981392, "step": 3415, "train_runtime": 13230.228, "train_tokens_per_second": 10656.006 }, { "epoch": 0.2302720172367358, "grad_norm": 0.6878241980166803, "learning_rate": 9.676651665556194e-06, "loss": 0.3907495021820068, "num_input_tokens_seen": 141199176, "step": 3420, "train_runtime": 13249.7122, "train_tokens_per_second": 10656.773 }, { "epoch": 0.23060867223269593, "grad_norm": 0.8190163327971124, "learning_rate": 9.675715599970383e-06, "loss": 0.395477819442749, "num_input_tokens_seen": 141396120, "step": 3425, "train_runtime": 13269.6497, "train_tokens_per_second": 10655.603 }, { "epoch": 0.23094532722865607, "grad_norm": 0.8211498592688941, "learning_rate": 9.674778226835617e-06, "loss": 0.4356833457946777, "num_input_tokens_seen": 141590464, "step": 3430, "train_runtime": 13287.2567, "train_tokens_per_second": 10656.11 }, { "epoch": 0.2312819822246162, "grad_norm": 0.7354121313196078, "learning_rate": 9.673839546414026e-06, "loss": 0.42177329063415525, "num_input_tokens_seen": 141789576, "step": 3435, "train_runtime": 13305.1578, "train_tokens_per_second": 10656.738 }, { "epoch": 0.23161863722057635, "grad_norm": 0.6861236618460081, "learning_rate": 9.672899558968107e-06, "loss": 0.3918553590774536, "num_input_tokens_seen": 141991664, "step": 3440, "train_runtime": 13325.3003, "train_tokens_per_second": 10655.795 }, { "epoch": 0.2319552922165365, "grad_norm": 0.7730152455658976, "learning_rate": 9.67195826476073e-06, "loss": 0.43802585601806643, "num_input_tokens_seen": 142202544, "step": 3445, "train_runtime": 13345.0488, "train_tokens_per_second": 10655.828 }, { "epoch": 0.23229194721249663, "grad_norm": 0.8447088124651432, "learning_rate": 9.671015664055122e-06, "loss": 0.40470499992370607, "num_input_tokens_seen": 142403536, "step": 3450, "train_runtime": 13363.6751, "train_tokens_per_second": 10656.016 }, { "epoch": 0.23262860220845677, "grad_norm": 0.8483462485631308, "learning_rate": 9.670071757114877e-06, "loss": 0.40624332427978516, "num_input_tokens_seen": 142610600, "step": 3455, "train_runtime": 13382.7706, "train_tokens_per_second": 10656.284 }, { "epoch": 0.2329652572044169, "grad_norm": 0.7535479696022566, "learning_rate": 9.669126544203957e-06, "loss": 0.3919724941253662, "num_input_tokens_seen": 142806232, "step": 3460, "train_runtime": 13401.9552, "train_tokens_per_second": 10655.627 }, { "epoch": 0.23330191220037705, "grad_norm": 1.1216303632044136, "learning_rate": 9.668180025586689e-06, "loss": 0.41576247215270995, "num_input_tokens_seen": 143024320, "step": 3465, "train_runtime": 13422.453, "train_tokens_per_second": 10655.602 }, { "epoch": 0.2336385671963372, "grad_norm": 0.7117630423740704, "learning_rate": 9.667232201527761e-06, "loss": 0.39499788284301757, "num_input_tokens_seen": 143214872, "step": 3470, "train_runtime": 13441.8247, "train_tokens_per_second": 10654.422 }, { "epoch": 0.23397522219229733, "grad_norm": 0.8687469249505125, "learning_rate": 9.666283072292234e-06, "loss": 0.41616239547729494, "num_input_tokens_seen": 143407592, "step": 3475, "train_runtime": 13461.8002, "train_tokens_per_second": 10652.928 }, { "epoch": 0.23431187718825747, "grad_norm": 0.7117121190873618, "learning_rate": 9.665332638145522e-06, "loss": 0.4190967082977295, "num_input_tokens_seen": 143616608, "step": 3480, "train_runtime": 13481.5989, "train_tokens_per_second": 10652.787 }, { "epoch": 0.2346485321842176, "grad_norm": 0.7488350284294726, "learning_rate": 9.664380899353414e-06, "loss": 0.4404623508453369, "num_input_tokens_seen": 143823752, "step": 3485, "train_runtime": 13500.5899, "train_tokens_per_second": 10653.146 }, { "epoch": 0.23498518718017775, "grad_norm": 0.8853444461716483, "learning_rate": 9.663427856182062e-06, "loss": 0.42197113037109374, "num_input_tokens_seen": 144041544, "step": 3490, "train_runtime": 13521.3287, "train_tokens_per_second": 10652.913 }, { "epoch": 0.23532184217613789, "grad_norm": 0.7300344735525324, "learning_rate": 9.662473508897981e-06, "loss": 0.4144586563110352, "num_input_tokens_seen": 144253024, "step": 3495, "train_runtime": 13543.0595, "train_tokens_per_second": 10651.435 }, { "epoch": 0.23565849717209802, "grad_norm": 0.8578610574044353, "learning_rate": 9.661517857768052e-06, "loss": 0.4364321231842041, "num_input_tokens_seen": 144452808, "step": 3500, "train_runtime": 13560.9077, "train_tokens_per_second": 10652.149 }, { "epoch": 0.23599515216805816, "grad_norm": 0.8846916256443927, "learning_rate": 9.660560903059517e-06, "loss": 0.40876522064208987, "num_input_tokens_seen": 144649840, "step": 3505, "train_runtime": 13580.3392, "train_tokens_per_second": 10651.416 }, { "epoch": 0.2363318071640183, "grad_norm": 0.6812697008566235, "learning_rate": 9.659602645039988e-06, "loss": 0.4190493583679199, "num_input_tokens_seen": 144860416, "step": 3510, "train_runtime": 13598.1317, "train_tokens_per_second": 10652.965 }, { "epoch": 0.23666846215997844, "grad_norm": 0.7226805413758438, "learning_rate": 9.658643083977435e-06, "loss": 0.3650641918182373, "num_input_tokens_seen": 145060328, "step": 3515, "train_runtime": 13617.1729, "train_tokens_per_second": 10652.749 }, { "epoch": 0.23700511715593858, "grad_norm": 0.7589549412607597, "learning_rate": 9.657682220140202e-06, "loss": 0.3869511365890503, "num_input_tokens_seen": 145252848, "step": 3520, "train_runtime": 13636.5052, "train_tokens_per_second": 10651.765 }, { "epoch": 0.23734177215189872, "grad_norm": 0.9858274117932594, "learning_rate": 9.656720053796987e-06, "loss": 0.43033246994018554, "num_input_tokens_seen": 145452416, "step": 3525, "train_runtime": 13655.206, "train_tokens_per_second": 10651.792 }, { "epoch": 0.23767842714785886, "grad_norm": 0.8947156651714848, "learning_rate": 9.655756585216859e-06, "loss": 0.39640583992004397, "num_input_tokens_seen": 145653192, "step": 3530, "train_runtime": 13675.6478, "train_tokens_per_second": 10650.552 }, { "epoch": 0.238015082143819, "grad_norm": 0.7986839064126623, "learning_rate": 9.654791814669246e-06, "loss": 0.4199096202850342, "num_input_tokens_seen": 145855904, "step": 3535, "train_runtime": 13694.9039, "train_tokens_per_second": 10650.378 }, { "epoch": 0.23835173713977914, "grad_norm": 0.740275926354348, "learning_rate": 9.653825742423949e-06, "loss": 0.3678280353546143, "num_input_tokens_seen": 146065600, "step": 3540, "train_runtime": 13714.3834, "train_tokens_per_second": 10650.541 }, { "epoch": 0.2386883921357393, "grad_norm": 0.7121061707137216, "learning_rate": 9.652858368751118e-06, "loss": 0.38494086265563965, "num_input_tokens_seen": 146260928, "step": 3545, "train_runtime": 13731.7627, "train_tokens_per_second": 10651.286 }, { "epoch": 0.23902504713169945, "grad_norm": 0.8047535342276049, "learning_rate": 9.651889693921284e-06, "loss": 0.3987760305404663, "num_input_tokens_seen": 146473560, "step": 3550, "train_runtime": 13750.5434, "train_tokens_per_second": 10652.202 }, { "epoch": 0.2393617021276596, "grad_norm": 0.8337138796571224, "learning_rate": 9.650919718205331e-06, "loss": 0.46805315017700194, "num_input_tokens_seen": 146675104, "step": 3555, "train_runtime": 13768.8896, "train_tokens_per_second": 10652.646 }, { "epoch": 0.23969835712361973, "grad_norm": 0.6729666434710313, "learning_rate": 9.649948441874509e-06, "loss": 0.4147489547729492, "num_input_tokens_seen": 146887200, "step": 3560, "train_runtime": 13790.6569, "train_tokens_per_second": 10651.211 }, { "epoch": 0.24003501211957987, "grad_norm": 1.0236371637191837, "learning_rate": 9.648975865200434e-06, "loss": 0.3766873836517334, "num_input_tokens_seen": 147085560, "step": 3565, "train_runtime": 13809.2906, "train_tokens_per_second": 10651.203 }, { "epoch": 0.24037166711554, "grad_norm": 0.7504307035943751, "learning_rate": 9.648001988455082e-06, "loss": 0.43297758102416994, "num_input_tokens_seen": 147295360, "step": 3570, "train_runtime": 13828.8451, "train_tokens_per_second": 10651.313 }, { "epoch": 0.24070832211150014, "grad_norm": 0.7840870883492179, "learning_rate": 9.647026811910794e-06, "loss": 0.4180153846740723, "num_input_tokens_seen": 147498080, "step": 3575, "train_runtime": 13850.3015, "train_tokens_per_second": 10649.449 }, { "epoch": 0.24104497710746028, "grad_norm": 0.6755525776478565, "learning_rate": 9.646050335840279e-06, "loss": 0.43952603340148927, "num_input_tokens_seen": 147712864, "step": 3580, "train_runtime": 13868.9237, "train_tokens_per_second": 10650.636 }, { "epoch": 0.24138163210342042, "grad_norm": 0.8753376083536548, "learning_rate": 9.6450725605166e-06, "loss": 0.4005459785461426, "num_input_tokens_seen": 147911840, "step": 3585, "train_runtime": 13887.4636, "train_tokens_per_second": 10650.745 }, { "epoch": 0.24171828709938056, "grad_norm": 0.7997682499231382, "learning_rate": 9.644093486213192e-06, "loss": 0.43932905197143557, "num_input_tokens_seen": 148129736, "step": 3590, "train_runtime": 13907.5377, "train_tokens_per_second": 10651.04 }, { "epoch": 0.2420549420953407, "grad_norm": 0.8320681490163317, "learning_rate": 9.64311311320385e-06, "loss": 0.4141496181488037, "num_input_tokens_seen": 148337824, "step": 3595, "train_runtime": 13925.0215, "train_tokens_per_second": 10652.61 }, { "epoch": 0.24239159709130084, "grad_norm": 0.7794690880845359, "learning_rate": 9.642131441762732e-06, "loss": 0.40236454010009765, "num_input_tokens_seen": 148534008, "step": 3600, "train_runtime": 13943.7117, "train_tokens_per_second": 10652.401 }, { "epoch": 0.24272825208726098, "grad_norm": 0.7766441861514009, "learning_rate": 9.641148472164359e-06, "loss": 0.37749812602996824, "num_input_tokens_seen": 148734624, "step": 3605, "train_runtime": 13962.5605, "train_tokens_per_second": 10652.389 }, { "epoch": 0.24306490708322112, "grad_norm": 0.7709506093466421, "learning_rate": 9.640164204683616e-06, "loss": 0.3983339309692383, "num_input_tokens_seen": 148948312, "step": 3610, "train_runtime": 13981.3422, "train_tokens_per_second": 10653.363 }, { "epoch": 0.24340156207918126, "grad_norm": 0.8123056241700308, "learning_rate": 9.639178639595748e-06, "loss": 0.4325235366821289, "num_input_tokens_seen": 149156752, "step": 3615, "train_runtime": 13998.7026, "train_tokens_per_second": 10655.041 }, { "epoch": 0.2437382170751414, "grad_norm": 0.7558320669734351, "learning_rate": 9.638191777176367e-06, "loss": 0.39970927238464354, "num_input_tokens_seen": 149364200, "step": 3620, "train_runtime": 14017.1451, "train_tokens_per_second": 10655.822 }, { "epoch": 0.24407487207110154, "grad_norm": 0.7437141199500412, "learning_rate": 9.637203617701446e-06, "loss": 0.41918535232543946, "num_input_tokens_seen": 149578064, "step": 3625, "train_runtime": 14034.8594, "train_tokens_per_second": 10657.61 }, { "epoch": 0.24441152706706168, "grad_norm": 0.7796663199885331, "learning_rate": 9.63621416144732e-06, "loss": 0.3938539981842041, "num_input_tokens_seen": 149780048, "step": 3630, "train_runtime": 14054.4535, "train_tokens_per_second": 10657.124 }, { "epoch": 0.24474818206302182, "grad_norm": 0.8194476494247425, "learning_rate": 9.635223408690688e-06, "loss": 0.3880708456039429, "num_input_tokens_seen": 149970432, "step": 3635, "train_runtime": 14072.3693, "train_tokens_per_second": 10657.085 }, { "epoch": 0.24508483705898196, "grad_norm": 0.7693547655144453, "learning_rate": 9.63423135970861e-06, "loss": 0.41475496292114256, "num_input_tokens_seen": 150186440, "step": 3640, "train_runtime": 14093.4869, "train_tokens_per_second": 10656.443 }, { "epoch": 0.2454214920549421, "grad_norm": 0.8482301697498092, "learning_rate": 9.633238014778511e-06, "loss": 0.42216835021972654, "num_input_tokens_seen": 150399536, "step": 3645, "train_runtime": 14111.9721, "train_tokens_per_second": 10657.585 }, { "epoch": 0.24575814705090224, "grad_norm": 0.8454728064602536, "learning_rate": 9.632243374178173e-06, "loss": 0.40486783981323243, "num_input_tokens_seen": 150608496, "step": 3650, "train_runtime": 14130.183, "train_tokens_per_second": 10658.637 }, { "epoch": 0.24609480204686238, "grad_norm": 0.8158592615272219, "learning_rate": 9.63124743818575e-06, "loss": 0.4278604507446289, "num_input_tokens_seen": 150819488, "step": 3655, "train_runtime": 14149.7246, "train_tokens_per_second": 10658.829 }, { "epoch": 0.24643145704282252, "grad_norm": 0.7079861386085329, "learning_rate": 9.630250207079745e-06, "loss": 0.3891493558883667, "num_input_tokens_seen": 151020104, "step": 3660, "train_runtime": 14169.2367, "train_tokens_per_second": 10658.309 }, { "epoch": 0.24676811203878266, "grad_norm": 0.7403162751644806, "learning_rate": 9.629251681139038e-06, "loss": 0.42408075332641604, "num_input_tokens_seen": 151230232, "step": 3665, "train_runtime": 14189.0031, "train_tokens_per_second": 10658.27 }, { "epoch": 0.2471047670347428, "grad_norm": 0.7089627890893575, "learning_rate": 9.628251860642857e-06, "loss": 0.41371688842773435, "num_input_tokens_seen": 151434160, "step": 3670, "train_runtime": 14209.3093, "train_tokens_per_second": 10657.391 }, { "epoch": 0.24744142203070293, "grad_norm": 0.792816343124125, "learning_rate": 9.627250745870805e-06, "loss": 0.41003050804138186, "num_input_tokens_seen": 151634496, "step": 3675, "train_runtime": 14229.0042, "train_tokens_per_second": 10656.719 }, { "epoch": 0.24777807702666307, "grad_norm": 0.798468654469609, "learning_rate": 9.626248337102834e-06, "loss": 0.4514158248901367, "num_input_tokens_seen": 151842376, "step": 3680, "train_runtime": 14248.3802, "train_tokens_per_second": 10656.817 }, { "epoch": 0.2481147320226232, "grad_norm": 0.8204479413026423, "learning_rate": 9.625244634619269e-06, "loss": 0.42368078231811523, "num_input_tokens_seen": 152046872, "step": 3685, "train_runtime": 14266.7573, "train_tokens_per_second": 10657.423 }, { "epoch": 0.24845138701858335, "grad_norm": 2.276267643166748, "learning_rate": 9.62423963870079e-06, "loss": 0.40313568115234377, "num_input_tokens_seen": 152247096, "step": 3690, "train_runtime": 14285.1821, "train_tokens_per_second": 10657.694 }, { "epoch": 0.2487880420145435, "grad_norm": 0.7289606738349931, "learning_rate": 9.623233349628441e-06, "loss": 0.3650083541870117, "num_input_tokens_seen": 152447240, "step": 3695, "train_runtime": 14305.1999, "train_tokens_per_second": 10656.771 }, { "epoch": 0.24912469701050363, "grad_norm": 1.09369104600187, "learning_rate": 9.62222576768363e-06, "loss": 0.38216357231140136, "num_input_tokens_seen": 152650120, "step": 3700, "train_runtime": 14324.1556, "train_tokens_per_second": 10656.832 }, { "epoch": 0.24946135200646377, "grad_norm": 0.7753972156849305, "learning_rate": 9.62121689314812e-06, "loss": 0.45311403274536133, "num_input_tokens_seen": 152855416, "step": 3705, "train_runtime": 14344.3107, "train_tokens_per_second": 10656.17 }, { "epoch": 0.2497980070024239, "grad_norm": 0.8452698683971366, "learning_rate": 9.620206726304045e-06, "loss": 0.4183089256286621, "num_input_tokens_seen": 153057072, "step": 3710, "train_runtime": 14364.893, "train_tokens_per_second": 10654.94 }, { "epoch": 0.2501346619983841, "grad_norm": 0.7399589398154185, "learning_rate": 9.61919526743389e-06, "loss": 0.4065828323364258, "num_input_tokens_seen": 153266064, "step": 3715, "train_runtime": 14383.2121, "train_tokens_per_second": 10655.9 }, { "epoch": 0.2504713169943442, "grad_norm": 0.8674191213422187, "learning_rate": 9.618182516820507e-06, "loss": 0.4285894870758057, "num_input_tokens_seen": 153478992, "step": 3720, "train_runtime": 14401.7361, "train_tokens_per_second": 10656.979 }, { "epoch": 0.25080797199030436, "grad_norm": 0.7403211434238587, "learning_rate": 9.61716847474711e-06, "loss": 0.38581075668334963, "num_input_tokens_seen": 153679104, "step": 3725, "train_runtime": 14421.2084, "train_tokens_per_second": 10656.465 }, { "epoch": 0.2511446269862645, "grad_norm": 0.761424364527256, "learning_rate": 9.616153141497273e-06, "loss": 0.41538352966308595, "num_input_tokens_seen": 153882544, "step": 3730, "train_runtime": 14441.9276, "train_tokens_per_second": 10655.263 }, { "epoch": 0.25148128198222464, "grad_norm": 0.8259702521142352, "learning_rate": 9.61513651735493e-06, "loss": 0.3796579837799072, "num_input_tokens_seen": 154082696, "step": 3735, "train_runtime": 14461.1522, "train_tokens_per_second": 10654.939 }, { "epoch": 0.2518179369781848, "grad_norm": 0.8707255002999627, "learning_rate": 9.614118602604376e-06, "loss": 0.3972978353500366, "num_input_tokens_seen": 154271304, "step": 3740, "train_runtime": 14480.9842, "train_tokens_per_second": 10653.372 }, { "epoch": 0.2521545919741449, "grad_norm": 0.8016384705810986, "learning_rate": 9.613099397530267e-06, "loss": 0.3778103828430176, "num_input_tokens_seen": 154483872, "step": 3745, "train_runtime": 14500.207, "train_tokens_per_second": 10653.908 }, { "epoch": 0.25249124697010505, "grad_norm": 1.014639251019504, "learning_rate": 9.612078902417623e-06, "loss": 0.4170527935028076, "num_input_tokens_seen": 154698144, "step": 3750, "train_runtime": 14520.0072, "train_tokens_per_second": 10654.137 }, { "epoch": 0.2528279019660652, "grad_norm": 0.8228082181760525, "learning_rate": 9.611057117551821e-06, "loss": 0.40984067916870115, "num_input_tokens_seen": 154889136, "step": 3755, "train_runtime": 14538.8981, "train_tokens_per_second": 10653.43 }, { "epoch": 0.25316455696202533, "grad_norm": 0.741568916123291, "learning_rate": 9.610034043218598e-06, "loss": 0.41805224418640136, "num_input_tokens_seen": 155104896, "step": 3760, "train_runtime": 14560.2843, "train_tokens_per_second": 10652.601 }, { "epoch": 0.2535012119579855, "grad_norm": 0.8669492974161598, "learning_rate": 9.609009679704057e-06, "loss": 0.41010284423828125, "num_input_tokens_seen": 155311168, "step": 3765, "train_runtime": 14578.8546, "train_tokens_per_second": 10653.18 }, { "epoch": 0.2538378669539456, "grad_norm": 0.8898229002749998, "learning_rate": 9.607984027294654e-06, "loss": 0.4077720642089844, "num_input_tokens_seen": 155509328, "step": 3770, "train_runtime": 14599.2384, "train_tokens_per_second": 10651.88 }, { "epoch": 0.25417452194990575, "grad_norm": 0.6982204990425053, "learning_rate": 9.606957086277213e-06, "loss": 0.4076286792755127, "num_input_tokens_seen": 155719104, "step": 3775, "train_runtime": 14618.7646, "train_tokens_per_second": 10652.002 }, { "epoch": 0.2545111769458659, "grad_norm": 0.8959499946299616, "learning_rate": 9.605928856938913e-06, "loss": 0.4090163230895996, "num_input_tokens_seen": 155924120, "step": 3780, "train_runtime": 14637.4903, "train_tokens_per_second": 10652.381 }, { "epoch": 0.25484783194182603, "grad_norm": 0.746748318373039, "learning_rate": 9.604899339567298e-06, "loss": 0.3713984489440918, "num_input_tokens_seen": 156129448, "step": 3785, "train_runtime": 14657.2925, "train_tokens_per_second": 10651.998 }, { "epoch": 0.25518448693778617, "grad_norm": 0.7926470919770126, "learning_rate": 9.603868534450263e-06, "loss": 0.3770298957824707, "num_input_tokens_seen": 156345712, "step": 3790, "train_runtime": 14675.2586, "train_tokens_per_second": 10653.694 }, { "epoch": 0.2555211419337463, "grad_norm": 0.7784341995889421, "learning_rate": 9.602836441876074e-06, "loss": 0.36330108642578124, "num_input_tokens_seen": 156557744, "step": 3795, "train_runtime": 14694.9029, "train_tokens_per_second": 10653.881 }, { "epoch": 0.25585779692970645, "grad_norm": 0.9646890608049332, "learning_rate": 9.601803062133353e-06, "loss": 0.4037928581237793, "num_input_tokens_seen": 156767080, "step": 3800, "train_runtime": 14713.7783, "train_tokens_per_second": 10654.441 }, { "epoch": 0.2561944519256666, "grad_norm": 0.7479872779513245, "learning_rate": 9.600768395511078e-06, "loss": 0.3747291088104248, "num_input_tokens_seen": 156973328, "step": 3805, "train_runtime": 14732.0179, "train_tokens_per_second": 10655.25 }, { "epoch": 0.25653110692162673, "grad_norm": 0.747821569780277, "learning_rate": 9.599732442298592e-06, "loss": 0.40314207077026365, "num_input_tokens_seen": 157181232, "step": 3810, "train_runtime": 14750.0916, "train_tokens_per_second": 10656.288 }, { "epoch": 0.25686776191758687, "grad_norm": 0.7909143454914189, "learning_rate": 9.598695202785596e-06, "loss": 0.40096297264099123, "num_input_tokens_seen": 157378216, "step": 3815, "train_runtime": 14768.6539, "train_tokens_per_second": 10656.233 }, { "epoch": 0.257204416913547, "grad_norm": 0.8462944197812983, "learning_rate": 9.59765667726215e-06, "loss": 0.3925511360168457, "num_input_tokens_seen": 157586232, "step": 3820, "train_runtime": 14788.4963, "train_tokens_per_second": 10656.001 }, { "epoch": 0.25754107190950715, "grad_norm": 0.8085418673098026, "learning_rate": 9.596616866018677e-06, "loss": 0.4649686813354492, "num_input_tokens_seen": 157786040, "step": 3825, "train_runtime": 14807.5489, "train_tokens_per_second": 10655.784 }, { "epoch": 0.2578777269054673, "grad_norm": 0.8547262976729952, "learning_rate": 9.595575769345955e-06, "loss": 0.3910703182220459, "num_input_tokens_seen": 157974384, "step": 3830, "train_runtime": 14825.9284, "train_tokens_per_second": 10655.278 }, { "epoch": 0.2582143819014274, "grad_norm": 0.7572236915210724, "learning_rate": 9.594533387535122e-06, "loss": 0.41174612045288084, "num_input_tokens_seen": 158188192, "step": 3835, "train_runtime": 14845.2912, "train_tokens_per_second": 10655.782 }, { "epoch": 0.25855103689738757, "grad_norm": 0.7044767520068921, "learning_rate": 9.593489720877678e-06, "loss": 0.40086946487426756, "num_input_tokens_seen": 158393856, "step": 3840, "train_runtime": 14863.481, "train_tokens_per_second": 10656.579 }, { "epoch": 0.2588876918933477, "grad_norm": 0.6988851968298188, "learning_rate": 9.592444769665482e-06, "loss": 0.3805535316467285, "num_input_tokens_seen": 158611488, "step": 3845, "train_runtime": 14883.9897, "train_tokens_per_second": 10656.517 }, { "epoch": 0.25922434688930784, "grad_norm": 0.8920790012962613, "learning_rate": 9.59139853419075e-06, "loss": 0.3779738903045654, "num_input_tokens_seen": 158802848, "step": 3850, "train_runtime": 14902.7138, "train_tokens_per_second": 10655.968 }, { "epoch": 0.259561001885268, "grad_norm": 0.7054252855532942, "learning_rate": 9.590351014746059e-06, "loss": 0.40111708641052246, "num_input_tokens_seen": 159013368, "step": 3855, "train_runtime": 14921.674, "train_tokens_per_second": 10656.537 }, { "epoch": 0.2598976568812281, "grad_norm": 0.7573423254741412, "learning_rate": 9.589302211624343e-06, "loss": 0.400237512588501, "num_input_tokens_seen": 159217800, "step": 3860, "train_runtime": 14940.268, "train_tokens_per_second": 10656.957 }, { "epoch": 0.26023431187718826, "grad_norm": 0.7973286115033932, "learning_rate": 9.5882521251189e-06, "loss": 0.40644474029541017, "num_input_tokens_seen": 159424648, "step": 3865, "train_runtime": 14960.206, "train_tokens_per_second": 10656.581 }, { "epoch": 0.2605709668731484, "grad_norm": 0.8445943741374011, "learning_rate": 9.58720075552338e-06, "loss": 0.4279238224029541, "num_input_tokens_seen": 159625720, "step": 3870, "train_runtime": 14978.0326, "train_tokens_per_second": 10657.322 }, { "epoch": 0.26090762186910854, "grad_norm": 0.8452753690005668, "learning_rate": 9.586148103131797e-06, "loss": 0.39851672649383546, "num_input_tokens_seen": 159822232, "step": 3875, "train_runtime": 14996.1872, "train_tokens_per_second": 10657.524 }, { "epoch": 0.2612442768650687, "grad_norm": 0.8182676063177198, "learning_rate": 9.585094168238518e-06, "loss": 0.4345248699188232, "num_input_tokens_seen": 160021200, "step": 3880, "train_runtime": 15016.4247, "train_tokens_per_second": 10656.411 }, { "epoch": 0.2615809318610288, "grad_norm": 0.7862833060773766, "learning_rate": 9.58403895113828e-06, "loss": 0.3958085060119629, "num_input_tokens_seen": 160228544, "step": 3885, "train_runtime": 15035.3419, "train_tokens_per_second": 10656.794 }, { "epoch": 0.26191758685698896, "grad_norm": 0.7561980937648636, "learning_rate": 9.582982452126164e-06, "loss": 0.38547863960266116, "num_input_tokens_seen": 160432296, "step": 3890, "train_runtime": 15055.2634, "train_tokens_per_second": 10656.226 }, { "epoch": 0.2622542418529491, "grad_norm": 0.8061704565120391, "learning_rate": 9.58192467149762e-06, "loss": 0.3745398998260498, "num_input_tokens_seen": 160632392, "step": 3895, "train_runtime": 15075.0916, "train_tokens_per_second": 10655.484 }, { "epoch": 0.26259089684890924, "grad_norm": 0.824021001486456, "learning_rate": 9.580865609548452e-06, "loss": 0.4144713878631592, "num_input_tokens_seen": 160823920, "step": 3900, "train_runtime": 15093.8676, "train_tokens_per_second": 10654.918 }, { "epoch": 0.2629275518448694, "grad_norm": 0.6684266495811501, "learning_rate": 9.579805266574824e-06, "loss": 0.3842451810836792, "num_input_tokens_seen": 161026376, "step": 3905, "train_runtime": 15113.0781, "train_tokens_per_second": 10654.77 }, { "epoch": 0.2632642068408295, "grad_norm": 0.6326645178513441, "learning_rate": 9.578743642873258e-06, "loss": 0.40051631927490233, "num_input_tokens_seen": 161220712, "step": 3910, "train_runtime": 15133.8234, "train_tokens_per_second": 10653.006 }, { "epoch": 0.26360086183678966, "grad_norm": 0.7658193951872068, "learning_rate": 9.57768073874063e-06, "loss": 0.41124444007873534, "num_input_tokens_seen": 161430056, "step": 3915, "train_runtime": 15152.1947, "train_tokens_per_second": 10653.906 }, { "epoch": 0.2639375168327498, "grad_norm": 0.7770166652227082, "learning_rate": 9.576616554474182e-06, "loss": 0.4125207901000977, "num_input_tokens_seen": 161622288, "step": 3920, "train_runtime": 15170.4695, "train_tokens_per_second": 10653.743 }, { "epoch": 0.26427417182870994, "grad_norm": 0.7064236404129938, "learning_rate": 9.575551090371512e-06, "loss": 0.39879164695739744, "num_input_tokens_seen": 161818288, "step": 3925, "train_runtime": 15189.287, "train_tokens_per_second": 10653.449 }, { "epoch": 0.2646108268246701, "grad_norm": 0.7753277054609227, "learning_rate": 9.574484346730564e-06, "loss": 0.40401334762573243, "num_input_tokens_seen": 162024824, "step": 3930, "train_runtime": 15207.3834, "train_tokens_per_second": 10654.353 }, { "epoch": 0.2649474818206302, "grad_norm": 0.7420529554149761, "learning_rate": 9.573416323849658e-06, "loss": 0.41291241645812987, "num_input_tokens_seen": 162233344, "step": 3935, "train_runtime": 15226.4184, "train_tokens_per_second": 10654.728 }, { "epoch": 0.26528413681659035, "grad_norm": 0.7713121610170856, "learning_rate": 9.572347022027461e-06, "loss": 0.3960822105407715, "num_input_tokens_seen": 162446160, "step": 3940, "train_runtime": 15246.144, "train_tokens_per_second": 10654.901 }, { "epoch": 0.2656207918125505, "grad_norm": 0.7299798943586203, "learning_rate": 9.571276441563e-06, "loss": 0.4064935684204102, "num_input_tokens_seen": 162635088, "step": 3945, "train_runtime": 15264.5063, "train_tokens_per_second": 10654.461 }, { "epoch": 0.26595744680851063, "grad_norm": 0.831784126683486, "learning_rate": 9.570204582755659e-06, "loss": 0.38399596214294435, "num_input_tokens_seen": 162842864, "step": 3950, "train_runtime": 15282.6894, "train_tokens_per_second": 10655.38 }, { "epoch": 0.2662941018044708, "grad_norm": 0.9346782406505662, "learning_rate": 9.569131445905178e-06, "loss": 0.4172950744628906, "num_input_tokens_seen": 163043576, "step": 3955, "train_runtime": 15301.5607, "train_tokens_per_second": 10655.356 }, { "epoch": 0.2666307568004309, "grad_norm": 0.7986246412849244, "learning_rate": 9.568057031311659e-06, "loss": 0.4161484718322754, "num_input_tokens_seen": 163241200, "step": 3960, "train_runtime": 15320.4578, "train_tokens_per_second": 10655.112 }, { "epoch": 0.26696741179639105, "grad_norm": 0.8553242086801934, "learning_rate": 9.566981339275557e-06, "loss": 0.4379969596862793, "num_input_tokens_seen": 163438512, "step": 3965, "train_runtime": 15338.6588, "train_tokens_per_second": 10655.333 }, { "epoch": 0.2673040667923512, "grad_norm": 0.7694552149387541, "learning_rate": 9.565904370097687e-06, "loss": 0.4073976993560791, "num_input_tokens_seen": 163628632, "step": 3970, "train_runtime": 15357.3474, "train_tokens_per_second": 10654.746 }, { "epoch": 0.26764072178831133, "grad_norm": 0.7134089448562349, "learning_rate": 9.564826124079219e-06, "loss": 0.3873851776123047, "num_input_tokens_seen": 163835680, "step": 3975, "train_runtime": 15377.9886, "train_tokens_per_second": 10653.908 }, { "epoch": 0.26797737678427147, "grad_norm": 0.7991647154324066, "learning_rate": 9.563746601521681e-06, "loss": 0.3726832151412964, "num_input_tokens_seen": 164047720, "step": 3980, "train_runtime": 15399.1181, "train_tokens_per_second": 10653.059 }, { "epoch": 0.2683140317802316, "grad_norm": 0.8203487892738176, "learning_rate": 9.562665802726961e-06, "loss": 0.39577174186706543, "num_input_tokens_seen": 164263272, "step": 3985, "train_runtime": 15418.6533, "train_tokens_per_second": 10653.542 }, { "epoch": 0.26865068677619175, "grad_norm": 0.802971565095264, "learning_rate": 9.561583727997297e-06, "loss": 0.4010136604309082, "num_input_tokens_seen": 164464544, "step": 3990, "train_runtime": 15438.5888, "train_tokens_per_second": 10652.822 }, { "epoch": 0.2689873417721519, "grad_norm": 0.9040738471368827, "learning_rate": 9.560500377635288e-06, "loss": 0.42191033363342284, "num_input_tokens_seen": 164672736, "step": 3995, "train_runtime": 15458.9065, "train_tokens_per_second": 10652.289 }, { "epoch": 0.26932399676811203, "grad_norm": 0.8560688662458239, "learning_rate": 9.559415751943893e-06, "loss": 0.4115410804748535, "num_input_tokens_seen": 164876544, "step": 4000, "train_runtime": 15477.7342, "train_tokens_per_second": 10652.499 }, { "epoch": 0.26966065176407217, "grad_norm": 0.717824295451807, "learning_rate": 9.558329851226422e-06, "loss": 0.39913234710693357, "num_input_tokens_seen": 165087584, "step": 4005, "train_runtime": 15495.6204, "train_tokens_per_second": 10653.822 }, { "epoch": 0.2699973067600323, "grad_norm": 0.8364353589212891, "learning_rate": 9.557242675786542e-06, "loss": 0.42235193252563474, "num_input_tokens_seen": 165301672, "step": 4010, "train_runtime": 15516.3212, "train_tokens_per_second": 10653.406 }, { "epoch": 0.27033396175599245, "grad_norm": 0.7136400853576, "learning_rate": 9.55615422592828e-06, "loss": 0.4438282012939453, "num_input_tokens_seen": 165515960, "step": 4015, "train_runtime": 15536.1482, "train_tokens_per_second": 10653.603 }, { "epoch": 0.2706706167519526, "grad_norm": 0.8513172353062485, "learning_rate": 9.555064501956018e-06, "loss": 0.4276585102081299, "num_input_tokens_seen": 165719776, "step": 4020, "train_runtime": 15553.9844, "train_tokens_per_second": 10654.49 }, { "epoch": 0.2710072717479127, "grad_norm": 0.7371687407504927, "learning_rate": 9.553973504174493e-06, "loss": 0.37175986766815183, "num_input_tokens_seen": 165932104, "step": 4025, "train_runtime": 15573.8605, "train_tokens_per_second": 10654.526 }, { "epoch": 0.27134392674387287, "grad_norm": 0.7954554147375134, "learning_rate": 9.5528812328888e-06, "loss": 0.4121258735656738, "num_input_tokens_seen": 166129192, "step": 4030, "train_runtime": 15593.0641, "train_tokens_per_second": 10654.044 }, { "epoch": 0.271680581739833, "grad_norm": 0.7955111254740174, "learning_rate": 9.551787688404386e-06, "loss": 0.39014301300048826, "num_input_tokens_seen": 166330624, "step": 4035, "train_runtime": 15611.0821, "train_tokens_per_second": 10654.651 }, { "epoch": 0.27201723673579314, "grad_norm": 0.724101270277665, "learning_rate": 9.550692871027061e-06, "loss": 0.3959085464477539, "num_input_tokens_seen": 166540384, "step": 4040, "train_runtime": 15630.6104, "train_tokens_per_second": 10654.759 }, { "epoch": 0.2723538917317533, "grad_norm": 0.7456900750049912, "learning_rate": 9.549596781062984e-06, "loss": 0.3781397342681885, "num_input_tokens_seen": 166755432, "step": 4045, "train_runtime": 15649.5101, "train_tokens_per_second": 10655.633 }, { "epoch": 0.2726905467277134, "grad_norm": 1.0145160000534188, "learning_rate": 9.548499418818677e-06, "loss": 0.39144554138183596, "num_input_tokens_seen": 166953744, "step": 4050, "train_runtime": 15669.1976, "train_tokens_per_second": 10654.901 }, { "epoch": 0.27302720172367356, "grad_norm": 0.8197470604223265, "learning_rate": 9.547400784601011e-06, "loss": 0.4507724761962891, "num_input_tokens_seen": 167158072, "step": 4055, "train_runtime": 15688.6149, "train_tokens_per_second": 10654.737 }, { "epoch": 0.2733638567196337, "grad_norm": 0.7694509269606125, "learning_rate": 9.546300878717216e-06, "loss": 0.42034339904785156, "num_input_tokens_seen": 167369760, "step": 4060, "train_runtime": 15706.827, "train_tokens_per_second": 10655.861 }, { "epoch": 0.27370051171559384, "grad_norm": 0.7634661884189083, "learning_rate": 9.545199701474877e-06, "loss": 0.3954088926315308, "num_input_tokens_seen": 167578880, "step": 4065, "train_runtime": 15728.0014, "train_tokens_per_second": 10654.811 }, { "epoch": 0.274037166711554, "grad_norm": 0.8015760554588486, "learning_rate": 9.544097253181935e-06, "loss": 0.38714663982391356, "num_input_tokens_seen": 167781760, "step": 4070, "train_runtime": 15748.0831, "train_tokens_per_second": 10654.107 }, { "epoch": 0.2743738217075141, "grad_norm": 0.8019881542152207, "learning_rate": 9.542993534146687e-06, "loss": 0.4113685131072998, "num_input_tokens_seen": 167984472, "step": 4075, "train_runtime": 15768.2868, "train_tokens_per_second": 10653.312 }, { "epoch": 0.27471047670347426, "grad_norm": 0.7496277376834889, "learning_rate": 9.541888544677784e-06, "loss": 0.40914068222045896, "num_input_tokens_seen": 168190160, "step": 4080, "train_runtime": 15787.5165, "train_tokens_per_second": 10653.364 }, { "epoch": 0.2750471316994344, "grad_norm": 0.8032402773972411, "learning_rate": 9.540782285084232e-06, "loss": 0.35713748931884765, "num_input_tokens_seen": 168392664, "step": 4085, "train_runtime": 15807.2111, "train_tokens_per_second": 10652.902 }, { "epoch": 0.27538378669539454, "grad_norm": 0.7629648636062857, "learning_rate": 9.539674755675392e-06, "loss": 0.40299167633056643, "num_input_tokens_seen": 168599080, "step": 4090, "train_runtime": 15827.0469, "train_tokens_per_second": 10652.592 }, { "epoch": 0.2757204416913547, "grad_norm": 0.6540965372087627, "learning_rate": 9.538565956760983e-06, "loss": 0.35927953720092776, "num_input_tokens_seen": 168816424, "step": 4095, "train_runtime": 15844.6857, "train_tokens_per_second": 10654.451 }, { "epoch": 0.2760570966873148, "grad_norm": 0.8185610046159575, "learning_rate": 9.537455888651078e-06, "loss": 0.40056800842285156, "num_input_tokens_seen": 169031992, "step": 4100, "train_runtime": 15863.2753, "train_tokens_per_second": 10655.554 }, { "epoch": 0.27639375168327496, "grad_norm": 0.7701277581950315, "learning_rate": 9.536344551656103e-06, "loss": 0.4132696628570557, "num_input_tokens_seen": 169244504, "step": 4105, "train_runtime": 15881.5236, "train_tokens_per_second": 10656.692 }, { "epoch": 0.2767304066792351, "grad_norm": 0.7534384843526151, "learning_rate": 9.535231946086838e-06, "loss": 0.40245351791381834, "num_input_tokens_seen": 169449496, "step": 4110, "train_runtime": 15899.9928, "train_tokens_per_second": 10657.206 }, { "epoch": 0.27706706167519524, "grad_norm": 0.7712489702918973, "learning_rate": 9.534118072254421e-06, "loss": 0.4138979911804199, "num_input_tokens_seen": 169661200, "step": 4115, "train_runtime": 15918.9659, "train_tokens_per_second": 10657.803 }, { "epoch": 0.2774037166711554, "grad_norm": 0.7100495327138849, "learning_rate": 9.533002930470345e-06, "loss": 0.37774291038513186, "num_input_tokens_seen": 169870576, "step": 4120, "train_runtime": 15939.7903, "train_tokens_per_second": 10657.014 }, { "epoch": 0.2777403716671155, "grad_norm": 0.6640271281782752, "learning_rate": 9.531886521046452e-06, "loss": 0.3855604648590088, "num_input_tokens_seen": 170064560, "step": 4125, "train_runtime": 15959.2882, "train_tokens_per_second": 10656.149 }, { "epoch": 0.27807702666307565, "grad_norm": 0.788546128578615, "learning_rate": 9.530768844294947e-06, "loss": 0.4207219123840332, "num_input_tokens_seen": 170272104, "step": 4130, "train_runtime": 15978.6371, "train_tokens_per_second": 10656.234 }, { "epoch": 0.2784136816590358, "grad_norm": 0.8399693349001469, "learning_rate": 9.52964990052838e-06, "loss": 0.4268766403198242, "num_input_tokens_seen": 170476144, "step": 4135, "train_runtime": 15996.2373, "train_tokens_per_second": 10657.265 }, { "epoch": 0.27875033665499593, "grad_norm": 0.7513884878088332, "learning_rate": 9.528529690059663e-06, "loss": 0.37296690940856936, "num_input_tokens_seen": 170687152, "step": 4140, "train_runtime": 16016.4571, "train_tokens_per_second": 10656.986 }, { "epoch": 0.2790869916509561, "grad_norm": 0.8936908001782918, "learning_rate": 9.52740821320206e-06, "loss": 0.4071652412414551, "num_input_tokens_seen": 170890000, "step": 4145, "train_runtime": 16034.4604, "train_tokens_per_second": 10657.671 }, { "epoch": 0.2794236466469162, "grad_norm": 0.7001904721847106, "learning_rate": 9.526285470269185e-06, "loss": 0.44103131294250486, "num_input_tokens_seen": 171101088, "step": 4150, "train_runtime": 16053.5319, "train_tokens_per_second": 10658.159 }, { "epoch": 0.2797603016428764, "grad_norm": 0.7724265102321839, "learning_rate": 9.525161461575012e-06, "loss": 0.4137882232666016, "num_input_tokens_seen": 171295696, "step": 4155, "train_runtime": 16072.879, "train_tokens_per_second": 10657.437 }, { "epoch": 0.28009695663883655, "grad_norm": 0.728442323682135, "learning_rate": 9.524036187433867e-06, "loss": 0.3822883129119873, "num_input_tokens_seen": 171490816, "step": 4160, "train_runtime": 16092.8374, "train_tokens_per_second": 10656.344 }, { "epoch": 0.2804336116347967, "grad_norm": 0.7620035547916927, "learning_rate": 9.522909648160427e-06, "loss": 0.38776559829711915, "num_input_tokens_seen": 171696176, "step": 4165, "train_runtime": 16111.5847, "train_tokens_per_second": 10656.691 }, { "epoch": 0.2807702666307568, "grad_norm": 0.8289739255134403, "learning_rate": 9.521781844069727e-06, "loss": 0.4065378665924072, "num_input_tokens_seen": 171907128, "step": 4170, "train_runtime": 16131.8141, "train_tokens_per_second": 10656.404 }, { "epoch": 0.28110692162671697, "grad_norm": 0.7999094548472084, "learning_rate": 9.520652775477154e-06, "loss": 0.3889214038848877, "num_input_tokens_seen": 172113880, "step": 4175, "train_runtime": 16150.5203, "train_tokens_per_second": 10656.863 }, { "epoch": 0.2814435766226771, "grad_norm": 0.6659359302187786, "learning_rate": 9.519522442698447e-06, "loss": 0.369017505645752, "num_input_tokens_seen": 172310080, "step": 4180, "train_runtime": 16168.1946, "train_tokens_per_second": 10657.348 }, { "epoch": 0.28178023161863724, "grad_norm": 0.7725803035894954, "learning_rate": 9.518390846049699e-06, "loss": 0.4044185638427734, "num_input_tokens_seen": 172514104, "step": 4185, "train_runtime": 16188.2339, "train_tokens_per_second": 10656.759 }, { "epoch": 0.2821168866145974, "grad_norm": 0.7019354963397106, "learning_rate": 9.517257985847361e-06, "loss": 0.42027974128723145, "num_input_tokens_seen": 172715864, "step": 4190, "train_runtime": 16208.8531, "train_tokens_per_second": 10655.65 }, { "epoch": 0.2824535416105575, "grad_norm": 0.7085491345737279, "learning_rate": 9.516123862408232e-06, "loss": 0.43021745681762696, "num_input_tokens_seen": 172927784, "step": 4195, "train_runtime": 16227.3973, "train_tokens_per_second": 10656.532 }, { "epoch": 0.28279019660651766, "grad_norm": 0.7761285596650593, "learning_rate": 9.514988476049466e-06, "loss": 0.37699198722839355, "num_input_tokens_seen": 173129688, "step": 4200, "train_runtime": 16246.7421, "train_tokens_per_second": 10656.271 }, { "epoch": 0.2831268516024778, "grad_norm": 0.7075633377880107, "learning_rate": 9.513851827088567e-06, "loss": 0.4040982246398926, "num_input_tokens_seen": 173324736, "step": 4205, "train_runtime": 16266.5604, "train_tokens_per_second": 10655.279 }, { "epoch": 0.28346350659843794, "grad_norm": 0.8545141645655058, "learning_rate": 9.512713915843402e-06, "loss": 0.39457249641418457, "num_input_tokens_seen": 173534904, "step": 4210, "train_runtime": 16285.1708, "train_tokens_per_second": 10656.008 }, { "epoch": 0.2838001615943981, "grad_norm": 0.7217206352222058, "learning_rate": 9.511574742632177e-06, "loss": 0.3805173397064209, "num_input_tokens_seen": 173744576, "step": 4215, "train_runtime": 16306.8239, "train_tokens_per_second": 10654.716 }, { "epoch": 0.2841368165903582, "grad_norm": 0.75203241113619, "learning_rate": 9.510434307773464e-06, "loss": 0.4594120979309082, "num_input_tokens_seen": 173955864, "step": 4220, "train_runtime": 16325.4498, "train_tokens_per_second": 10655.502 }, { "epoch": 0.28447347158631836, "grad_norm": 0.6192446080552504, "learning_rate": 9.509292611586179e-06, "loss": 0.35884366035461424, "num_input_tokens_seen": 174136368, "step": 4225, "train_runtime": 16344.6238, "train_tokens_per_second": 10654.046 }, { "epoch": 0.2848101265822785, "grad_norm": 0.7730328087141588, "learning_rate": 9.508149654389592e-06, "loss": 0.41068382263183595, "num_input_tokens_seen": 174348992, "step": 4230, "train_runtime": 16365.3289, "train_tokens_per_second": 10653.559 }, { "epoch": 0.28514678157823864, "grad_norm": 0.6828393679923109, "learning_rate": 9.507005436503331e-06, "loss": 0.38035311698913576, "num_input_tokens_seen": 174564160, "step": 4235, "train_runtime": 16384.3163, "train_tokens_per_second": 10654.345 }, { "epoch": 0.2854834365741988, "grad_norm": 0.8400901274038406, "learning_rate": 9.505859958247373e-06, "loss": 0.4047652244567871, "num_input_tokens_seen": 174767136, "step": 4240, "train_runtime": 16403.48, "train_tokens_per_second": 10654.272 }, { "epoch": 0.2858200915701589, "grad_norm": 0.6866591592009111, "learning_rate": 9.504713219942045e-06, "loss": 0.37401344776153567, "num_input_tokens_seen": 174974472, "step": 4245, "train_runtime": 16423.0496, "train_tokens_per_second": 10654.201 }, { "epoch": 0.28615674656611906, "grad_norm": 0.7336136479576492, "learning_rate": 9.503565221908029e-06, "loss": 0.3977606773376465, "num_input_tokens_seen": 175182704, "step": 4250, "train_runtime": 16441.1081, "train_tokens_per_second": 10655.164 }, { "epoch": 0.2864934015620792, "grad_norm": 0.7662579285585377, "learning_rate": 9.50241596446636e-06, "loss": 0.4263883113861084, "num_input_tokens_seen": 175395664, "step": 4255, "train_runtime": 16460.1762, "train_tokens_per_second": 10655.759 }, { "epoch": 0.28683005655803934, "grad_norm": 0.8603697674431303, "learning_rate": 9.501265447938423e-06, "loss": 0.4059725761413574, "num_input_tokens_seen": 175592448, "step": 4260, "train_runtime": 16480.0238, "train_tokens_per_second": 10654.866 }, { "epoch": 0.2871667115539995, "grad_norm": 0.8985817093674345, "learning_rate": 9.500113672645958e-06, "loss": 0.4125247001647949, "num_input_tokens_seen": 175793560, "step": 4265, "train_runtime": 16497.4821, "train_tokens_per_second": 10655.781 }, { "epoch": 0.2875033665499596, "grad_norm": 0.8057215563348386, "learning_rate": 9.498960638911054e-06, "loss": 0.37838857173919677, "num_input_tokens_seen": 175993136, "step": 4270, "train_runtime": 16518.8552, "train_tokens_per_second": 10654.076 }, { "epoch": 0.28784002154591976, "grad_norm": 0.7888016748763194, "learning_rate": 9.497806347056153e-06, "loss": 0.40094146728515623, "num_input_tokens_seen": 176200776, "step": 4275, "train_runtime": 16540.1209, "train_tokens_per_second": 10652.932 }, { "epoch": 0.2881766765418799, "grad_norm": 0.9316739569355581, "learning_rate": 9.49665079740405e-06, "loss": 0.41986689567565916, "num_input_tokens_seen": 176408936, "step": 4280, "train_runtime": 16558.2782, "train_tokens_per_second": 10653.821 }, { "epoch": 0.28851333153784003, "grad_norm": 0.8732258328386652, "learning_rate": 9.495493990277889e-06, "loss": 0.41122827529907224, "num_input_tokens_seen": 176609848, "step": 4285, "train_runtime": 16576.9218, "train_tokens_per_second": 10653.959 }, { "epoch": 0.2888499865338002, "grad_norm": 0.7294390303231233, "learning_rate": 9.49433592600117e-06, "loss": 0.39946422576904295, "num_input_tokens_seen": 176823000, "step": 4290, "train_runtime": 16597.7293, "train_tokens_per_second": 10653.445 }, { "epoch": 0.2891866415297603, "grad_norm": 0.7362688498972407, "learning_rate": 9.49317660489774e-06, "loss": 0.39108073711395264, "num_input_tokens_seen": 177035760, "step": 4295, "train_runtime": 16616.3976, "train_tokens_per_second": 10654.28 }, { "epoch": 0.28952329652572045, "grad_norm": 1.0666838448996232, "learning_rate": 9.4920160272918e-06, "loss": 0.39768936634063723, "num_input_tokens_seen": 177250688, "step": 4300, "train_runtime": 16634.6052, "train_tokens_per_second": 10655.539 }, { "epoch": 0.2898599515216806, "grad_norm": 0.919954375536276, "learning_rate": 9.490854193507904e-06, "loss": 0.4089491367340088, "num_input_tokens_seen": 177453832, "step": 4305, "train_runtime": 16652.1332, "train_tokens_per_second": 10656.523 }, { "epoch": 0.29019660651764073, "grad_norm": 0.9094331123919969, "learning_rate": 9.489691103870951e-06, "loss": 0.4212177276611328, "num_input_tokens_seen": 177666936, "step": 4310, "train_runtime": 16670.4662, "train_tokens_per_second": 10657.587 }, { "epoch": 0.29053326151360087, "grad_norm": 0.6819727109738735, "learning_rate": 9.488526758706198e-06, "loss": 0.3947953701019287, "num_input_tokens_seen": 177876520, "step": 4315, "train_runtime": 16689.3054, "train_tokens_per_second": 10658.114 }, { "epoch": 0.290869916509561, "grad_norm": 0.9227701000888976, "learning_rate": 9.48736115833925e-06, "loss": 0.42429094314575194, "num_input_tokens_seen": 178070528, "step": 4320, "train_runtime": 16707.8087, "train_tokens_per_second": 10657.922 }, { "epoch": 0.29120657150552115, "grad_norm": 0.7677776170420632, "learning_rate": 9.486194303096062e-06, "loss": 0.39724206924438477, "num_input_tokens_seen": 178279096, "step": 4325, "train_runtime": 16727.3672, "train_tokens_per_second": 10657.929 }, { "epoch": 0.2915432265014813, "grad_norm": 0.6788754024979888, "learning_rate": 9.485026193302945e-06, "loss": 0.37708590030670164, "num_input_tokens_seen": 178486808, "step": 4330, "train_runtime": 16746.3667, "train_tokens_per_second": 10658.241 }, { "epoch": 0.29187988149744143, "grad_norm": 0.7260369539009889, "learning_rate": 9.483856829286552e-06, "loss": 0.4390455722808838, "num_input_tokens_seen": 178698376, "step": 4335, "train_runtime": 16766.3633, "train_tokens_per_second": 10658.148 }, { "epoch": 0.29221653649340157, "grad_norm": 0.7923597046056181, "learning_rate": 9.482686211373896e-06, "loss": 0.41038899421691893, "num_input_tokens_seen": 178910504, "step": 4340, "train_runtime": 16785.7521, "train_tokens_per_second": 10658.474 }, { "epoch": 0.2925531914893617, "grad_norm": 0.8115743708420803, "learning_rate": 9.481514339892335e-06, "loss": 0.4199807643890381, "num_input_tokens_seen": 179128576, "step": 4345, "train_runtime": 16805.1854, "train_tokens_per_second": 10659.125 }, { "epoch": 0.29288984648532185, "grad_norm": 0.7553971310886115, "learning_rate": 9.48034121516958e-06, "loss": 0.42109041213989257, "num_input_tokens_seen": 179328992, "step": 4350, "train_runtime": 16823.7479, "train_tokens_per_second": 10659.277 }, { "epoch": 0.293226501481282, "grad_norm": 0.658123618567573, "learning_rate": 9.47916683753369e-06, "loss": 0.3943612575531006, "num_input_tokens_seen": 179535248, "step": 4355, "train_runtime": 16843.4702, "train_tokens_per_second": 10659.042 }, { "epoch": 0.2935631564772421, "grad_norm": 0.7255291741709058, "learning_rate": 9.477991207313077e-06, "loss": 0.40187749862670896, "num_input_tokens_seen": 179747368, "step": 4360, "train_runtime": 16860.7941, "train_tokens_per_second": 10660.67 }, { "epoch": 0.29389981147320227, "grad_norm": 0.6921179124600305, "learning_rate": 9.476814324836504e-06, "loss": 0.390589165687561, "num_input_tokens_seen": 179961216, "step": 4365, "train_runtime": 16879.7569, "train_tokens_per_second": 10661.363 }, { "epoch": 0.2942364664691624, "grad_norm": 0.7628674598633559, "learning_rate": 9.475636190433078e-06, "loss": 0.4457608699798584, "num_input_tokens_seen": 180176656, "step": 4370, "train_runtime": 16898.7855, "train_tokens_per_second": 10662.107 }, { "epoch": 0.29457312146512254, "grad_norm": 0.7517275858835449, "learning_rate": 9.474456804432264e-06, "loss": 0.40600128173828126, "num_input_tokens_seen": 180390944, "step": 4375, "train_runtime": 16918.5088, "train_tokens_per_second": 10662.343 }, { "epoch": 0.2949097764610827, "grad_norm": 0.7438884180183516, "learning_rate": 9.473276167163872e-06, "loss": 0.41520085334777834, "num_input_tokens_seen": 180605552, "step": 4380, "train_runtime": 16938.0885, "train_tokens_per_second": 10662.688 }, { "epoch": 0.2952464314570428, "grad_norm": 0.8008346545806762, "learning_rate": 9.472094278958066e-06, "loss": 0.42991185188293457, "num_input_tokens_seen": 180822408, "step": 4385, "train_runtime": 16957.3922, "train_tokens_per_second": 10663.338 }, { "epoch": 0.29558308645300296, "grad_norm": 0.7271545247863683, "learning_rate": 9.470911140145353e-06, "loss": 0.40178070068359373, "num_input_tokens_seen": 181022032, "step": 4390, "train_runtime": 16976.6794, "train_tokens_per_second": 10662.982 }, { "epoch": 0.2959197414489631, "grad_norm": 0.8088352380817185, "learning_rate": 9.469726751056599e-06, "loss": 0.40119404792785646, "num_input_tokens_seen": 181231856, "step": 4395, "train_runtime": 16995.8772, "train_tokens_per_second": 10663.283 }, { "epoch": 0.29625639644492324, "grad_norm": 0.852972061388971, "learning_rate": 9.468541112023009e-06, "loss": 0.42597761154174807, "num_input_tokens_seen": 181430496, "step": 4400, "train_runtime": 17014.349, "train_tokens_per_second": 10663.382 }, { "epoch": 0.2965930514408834, "grad_norm": 0.822848362397139, "learning_rate": 9.467354223376149e-06, "loss": 0.41387434005737306, "num_input_tokens_seen": 181612976, "step": 4405, "train_runtime": 17032.187, "train_tokens_per_second": 10662.928 }, { "epoch": 0.2969297064368435, "grad_norm": 0.7472855882763499, "learning_rate": 9.466166085447923e-06, "loss": 0.4016547203063965, "num_input_tokens_seen": 181812984, "step": 4410, "train_runtime": 17050.7087, "train_tokens_per_second": 10663.075 }, { "epoch": 0.29726636143280366, "grad_norm": 0.8099864786901436, "learning_rate": 9.464976698570595e-06, "loss": 0.38450260162353517, "num_input_tokens_seen": 181997896, "step": 4415, "train_runtime": 17069.3182, "train_tokens_per_second": 10662.283 }, { "epoch": 0.2976030164287638, "grad_norm": 0.8127766417985148, "learning_rate": 9.463786063076769e-06, "loss": 0.42432069778442383, "num_input_tokens_seen": 182203640, "step": 4420, "train_runtime": 17088.2685, "train_tokens_per_second": 10662.499 }, { "epoch": 0.29793967142472394, "grad_norm": 0.7984692869137867, "learning_rate": 9.462594179299408e-06, "loss": 0.348390007019043, "num_input_tokens_seen": 182407280, "step": 4425, "train_runtime": 17107.6361, "train_tokens_per_second": 10662.331 }, { "epoch": 0.2982763264206841, "grad_norm": 0.6989344337088239, "learning_rate": 9.461401047571811e-06, "loss": 0.3924091339111328, "num_input_tokens_seen": 182622736, "step": 4430, "train_runtime": 17125.4989, "train_tokens_per_second": 10663.791 }, { "epoch": 0.2986129814166442, "grad_norm": 0.713946212111527, "learning_rate": 9.460206668227639e-06, "loss": 0.4179711818695068, "num_input_tokens_seen": 182836936, "step": 4435, "train_runtime": 17145.557, "train_tokens_per_second": 10663.808 }, { "epoch": 0.29894963641260436, "grad_norm": 0.6736974293050753, "learning_rate": 9.459011041600895e-06, "loss": 0.39478535652160646, "num_input_tokens_seen": 183052192, "step": 4440, "train_runtime": 17165.497, "train_tokens_per_second": 10663.961 }, { "epoch": 0.2992862914085645, "grad_norm": 0.7974263344858615, "learning_rate": 9.457814168025932e-06, "loss": 0.38154296875, "num_input_tokens_seen": 183259864, "step": 4445, "train_runtime": 17185.8212, "train_tokens_per_second": 10663.434 }, { "epoch": 0.29962294640452464, "grad_norm": 0.8508830995442309, "learning_rate": 9.456616047837452e-06, "loss": 0.42380919456481936, "num_input_tokens_seen": 183448512, "step": 4450, "train_runtime": 17205.5437, "train_tokens_per_second": 10662.175 }, { "epoch": 0.2999596014004848, "grad_norm": 0.698905431037744, "learning_rate": 9.455416681370506e-06, "loss": 0.43410701751708985, "num_input_tokens_seen": 183660848, "step": 4455, "train_runtime": 17224.8656, "train_tokens_per_second": 10662.542 }, { "epoch": 0.3002962563964449, "grad_norm": 0.7846942117942425, "learning_rate": 9.45421606896049e-06, "loss": 0.41393022537231444, "num_input_tokens_seen": 183876240, "step": 4460, "train_runtime": 17244.3153, "train_tokens_per_second": 10663.006 }, { "epoch": 0.30063291139240506, "grad_norm": 0.7140274702407582, "learning_rate": 9.453014210943155e-06, "loss": 0.39944186210632326, "num_input_tokens_seen": 184084496, "step": 4465, "train_runtime": 17264.9441, "train_tokens_per_second": 10662.328 }, { "epoch": 0.3009695663883652, "grad_norm": 1.2254509153709685, "learning_rate": 9.451811107654596e-06, "loss": 0.4034105777740479, "num_input_tokens_seen": 184295408, "step": 4470, "train_runtime": 17284.4937, "train_tokens_per_second": 10662.471 }, { "epoch": 0.30130622138432533, "grad_norm": 0.7832657475511323, "learning_rate": 9.450606759431255e-06, "loss": 0.4047177791595459, "num_input_tokens_seen": 184508216, "step": 4475, "train_runtime": 17303.4314, "train_tokens_per_second": 10663.1 }, { "epoch": 0.3016428763802855, "grad_norm": 0.8056331988380249, "learning_rate": 9.449401166609928e-06, "loss": 0.4226834774017334, "num_input_tokens_seen": 184707184, "step": 4480, "train_runtime": 17322.4135, "train_tokens_per_second": 10662.901 }, { "epoch": 0.3019795313762456, "grad_norm": 0.824787194650633, "learning_rate": 9.448194329527752e-06, "loss": 0.4146411418914795, "num_input_tokens_seen": 184907592, "step": 4485, "train_runtime": 17341.1359, "train_tokens_per_second": 10662.946 }, { "epoch": 0.30231618637220575, "grad_norm": 0.6917529178324715, "learning_rate": 9.446986248522216e-06, "loss": 0.3824875593185425, "num_input_tokens_seen": 185112168, "step": 4490, "train_runtime": 17360.227, "train_tokens_per_second": 10663.004 }, { "epoch": 0.3026528413681659, "grad_norm": 0.7512776214905045, "learning_rate": 9.445776923931157e-06, "loss": 0.37563910484313967, "num_input_tokens_seen": 185312336, "step": 4495, "train_runtime": 17378.8777, "train_tokens_per_second": 10663.078 }, { "epoch": 0.30298949636412603, "grad_norm": 0.7818308129286154, "learning_rate": 9.444566356092754e-06, "loss": 0.40988311767578123, "num_input_tokens_seen": 185525144, "step": 4500, "train_runtime": 17397.7244, "train_tokens_per_second": 10663.759 }, { "epoch": 0.30332615136008617, "grad_norm": 0.7749201656994748, "learning_rate": 9.443354545345545e-06, "loss": 0.3668079853057861, "num_input_tokens_seen": 185730856, "step": 4505, "train_runtime": 17417.5743, "train_tokens_per_second": 10663.417 }, { "epoch": 0.3036628063560463, "grad_norm": 0.6719603617508118, "learning_rate": 9.442141492028406e-06, "loss": 0.3985143184661865, "num_input_tokens_seen": 185938488, "step": 4510, "train_runtime": 17437.5727, "train_tokens_per_second": 10663.095 }, { "epoch": 0.30399946135200645, "grad_norm": 0.6947409187069117, "learning_rate": 9.440927196480563e-06, "loss": 0.38428421020507814, "num_input_tokens_seen": 186151704, "step": 4515, "train_runtime": 17456.0037, "train_tokens_per_second": 10664.05 }, { "epoch": 0.3043361163479666, "grad_norm": 0.6471319307510259, "learning_rate": 9.439711659041593e-06, "loss": 0.3942800760269165, "num_input_tokens_seen": 186356480, "step": 4520, "train_runtime": 17476.8094, "train_tokens_per_second": 10663.072 }, { "epoch": 0.30467277134392673, "grad_norm": 0.7559666871585324, "learning_rate": 9.438494880051413e-06, "loss": 0.41124253273010253, "num_input_tokens_seen": 186564384, "step": 4525, "train_runtime": 17495.3778, "train_tokens_per_second": 10663.638 }, { "epoch": 0.30500942633988687, "grad_norm": 0.7788829565096268, "learning_rate": 9.437276859850293e-06, "loss": 0.3996626138687134, "num_input_tokens_seen": 186774536, "step": 4530, "train_runtime": 17514.5408, "train_tokens_per_second": 10663.97 }, { "epoch": 0.305346081335847, "grad_norm": 0.7914626579536873, "learning_rate": 9.436057598778848e-06, "loss": 0.42639880180358886, "num_input_tokens_seen": 186976192, "step": 4535, "train_runtime": 17532.5047, "train_tokens_per_second": 10664.545 }, { "epoch": 0.30568273633180715, "grad_norm": 0.765130291256437, "learning_rate": 9.434837097178043e-06, "loss": 0.4563887596130371, "num_input_tokens_seen": 187183112, "step": 4540, "train_runtime": 17550.9537, "train_tokens_per_second": 10665.125 }, { "epoch": 0.3060193913277673, "grad_norm": 0.8634604751839694, "learning_rate": 9.433615355389183e-06, "loss": 0.41733784675598146, "num_input_tokens_seen": 187376864, "step": 4545, "train_runtime": 17570.4286, "train_tokens_per_second": 10664.331 }, { "epoch": 0.3063560463237274, "grad_norm": 0.7531226908747997, "learning_rate": 9.432392373753926e-06, "loss": 0.39666337966918946, "num_input_tokens_seen": 187591912, "step": 4550, "train_runtime": 17588.0586, "train_tokens_per_second": 10665.868 }, { "epoch": 0.30669270131968757, "grad_norm": 0.719864068946141, "learning_rate": 9.431168152614278e-06, "loss": 0.39423069953918455, "num_input_tokens_seen": 187796496, "step": 4555, "train_runtime": 17606.8095, "train_tokens_per_second": 10666.129 }, { "epoch": 0.3070293563156477, "grad_norm": 0.8147499405762886, "learning_rate": 9.429942692312585e-06, "loss": 0.36205253601074217, "num_input_tokens_seen": 188002464, "step": 4560, "train_runtime": 17625.0021, "train_tokens_per_second": 10666.805 }, { "epoch": 0.30736601131160785, "grad_norm": 0.6148459528595093, "learning_rate": 9.428715993191546e-06, "loss": 0.3866480827331543, "num_input_tokens_seen": 188212832, "step": 4565, "train_runtime": 17644.7213, "train_tokens_per_second": 10666.807 }, { "epoch": 0.307702666307568, "grad_norm": 0.7605692707800263, "learning_rate": 9.427488055594199e-06, "loss": 0.4088300704956055, "num_input_tokens_seen": 188408088, "step": 4570, "train_runtime": 17664.5619, "train_tokens_per_second": 10665.879 }, { "epoch": 0.3080393213035281, "grad_norm": 0.8115586431713201, "learning_rate": 9.426258879863937e-06, "loss": 0.4160768508911133, "num_input_tokens_seen": 188627248, "step": 4575, "train_runtime": 17683.02, "train_tokens_per_second": 10667.14 }, { "epoch": 0.30837597629948826, "grad_norm": 0.6417727129601064, "learning_rate": 9.425028466344494e-06, "loss": 0.3524350166320801, "num_input_tokens_seen": 188832096, "step": 4580, "train_runtime": 17700.9355, "train_tokens_per_second": 10667.916 }, { "epoch": 0.3087126312954484, "grad_norm": 0.7438833630076667, "learning_rate": 9.42379681537995e-06, "loss": 0.40123610496520995, "num_input_tokens_seen": 189038440, "step": 4585, "train_runtime": 17721.5464, "train_tokens_per_second": 10667.153 }, { "epoch": 0.30904928629140854, "grad_norm": 0.8300095132637539, "learning_rate": 9.422563927314732e-06, "loss": 0.4043739318847656, "num_input_tokens_seen": 189246856, "step": 4590, "train_runtime": 17739.8855, "train_tokens_per_second": 10667.874 }, { "epoch": 0.3093859412873687, "grad_norm": 0.7446759244025011, "learning_rate": 9.421329802493615e-06, "loss": 0.3770340919494629, "num_input_tokens_seen": 189457232, "step": 4595, "train_runtime": 17759.9797, "train_tokens_per_second": 10667.649 }, { "epoch": 0.3097225962833288, "grad_norm": 0.7293033350051127, "learning_rate": 9.420094441261717e-06, "loss": 0.4153287887573242, "num_input_tokens_seen": 189668024, "step": 4600, "train_runtime": 17780.7003, "train_tokens_per_second": 10667.073 }, { "epoch": 0.31005925127928896, "grad_norm": 0.8520353908602487, "learning_rate": 9.418857843964506e-06, "loss": 0.3893829107284546, "num_input_tokens_seen": 189871440, "step": 4605, "train_runtime": 17800.7806, "train_tokens_per_second": 10666.467 }, { "epoch": 0.3103959062752491, "grad_norm": 0.7084050657284465, "learning_rate": 9.417620010947786e-06, "loss": 0.4126879692077637, "num_input_tokens_seen": 190071720, "step": 4610, "train_runtime": 17821.7797, "train_tokens_per_second": 10665.137 }, { "epoch": 0.31073256127120924, "grad_norm": 0.7504916397711137, "learning_rate": 9.416380942557719e-06, "loss": 0.37334132194519043, "num_input_tokens_seen": 190278824, "step": 4615, "train_runtime": 17840.8955, "train_tokens_per_second": 10665.318 }, { "epoch": 0.3110692162671694, "grad_norm": 0.7433218614451514, "learning_rate": 9.415140639140803e-06, "loss": 0.4107921600341797, "num_input_tokens_seen": 190474128, "step": 4620, "train_runtime": 17860.5454, "train_tokens_per_second": 10664.519 }, { "epoch": 0.3114058712631295, "grad_norm": 0.6655015794192554, "learning_rate": 9.413899101043887e-06, "loss": 0.42977705001831057, "num_input_tokens_seen": 190678152, "step": 4625, "train_runtime": 17878.1049, "train_tokens_per_second": 10665.457 }, { "epoch": 0.31174252625908966, "grad_norm": 0.8622170474969603, "learning_rate": 9.412656328614162e-06, "loss": 0.4095268726348877, "num_input_tokens_seen": 190872088, "step": 4630, "train_runtime": 17898.6429, "train_tokens_per_second": 10664.054 }, { "epoch": 0.3120791812550498, "grad_norm": 0.7570284252902711, "learning_rate": 9.411412322199165e-06, "loss": 0.40881733894348143, "num_input_tokens_seen": 191086496, "step": 4635, "train_runtime": 17917.52, "train_tokens_per_second": 10664.785 }, { "epoch": 0.31241583625100994, "grad_norm": 0.7159456543135865, "learning_rate": 9.41016708214678e-06, "loss": 0.40338897705078125, "num_input_tokens_seen": 191281312, "step": 4640, "train_runtime": 17938.1067, "train_tokens_per_second": 10663.406 }, { "epoch": 0.31275249124697013, "grad_norm": 0.7953190538344803, "learning_rate": 9.408920608805233e-06, "loss": 0.37680587768554685, "num_input_tokens_seen": 191483504, "step": 4645, "train_runtime": 17959.1923, "train_tokens_per_second": 10662.145 }, { "epoch": 0.31308914624293027, "grad_norm": 0.6791264450221566, "learning_rate": 9.407672902523097e-06, "loss": 0.41029911041259765, "num_input_tokens_seen": 191696712, "step": 4650, "train_runtime": 17981.2668, "train_tokens_per_second": 10660.912 }, { "epoch": 0.3134258012388904, "grad_norm": 0.8036402610953702, "learning_rate": 9.406423963649287e-06, "loss": 0.40120930671691896, "num_input_tokens_seen": 191892504, "step": 4655, "train_runtime": 18002.4424, "train_tokens_per_second": 10659.248 }, { "epoch": 0.31376245623485055, "grad_norm": 0.6611930038638052, "learning_rate": 9.405173792533069e-06, "loss": 0.3911645174026489, "num_input_tokens_seen": 192101696, "step": 4660, "train_runtime": 18021.1481, "train_tokens_per_second": 10659.792 }, { "epoch": 0.3140991112308107, "grad_norm": 0.7206208832147695, "learning_rate": 9.403922389524045e-06, "loss": 0.38199281692504883, "num_input_tokens_seen": 192304928, "step": 4665, "train_runtime": 18039.2837, "train_tokens_per_second": 10660.342 }, { "epoch": 0.31443576622677083, "grad_norm": 0.7575395939603778, "learning_rate": 9.40266975497217e-06, "loss": 0.4140642166137695, "num_input_tokens_seen": 192508504, "step": 4670, "train_runtime": 18059.7844, "train_tokens_per_second": 10659.513 }, { "epoch": 0.31477242122273097, "grad_norm": 0.7581312081981678, "learning_rate": 9.401415889227736e-06, "loss": 0.41334986686706543, "num_input_tokens_seen": 192725240, "step": 4675, "train_runtime": 18079.3228, "train_tokens_per_second": 10659.981 }, { "epoch": 0.3151090762186911, "grad_norm": 0.6545515514932069, "learning_rate": 9.400160792641385e-06, "loss": 0.4136824607849121, "num_input_tokens_seen": 192945184, "step": 4680, "train_runtime": 18099.1448, "train_tokens_per_second": 10660.459 }, { "epoch": 0.31544573121465125, "grad_norm": 0.6868621838587858, "learning_rate": 9.398904465564097e-06, "loss": 0.38922340869903566, "num_input_tokens_seen": 193152472, "step": 4685, "train_runtime": 18117.045, "train_tokens_per_second": 10661.367 }, { "epoch": 0.3157823862106114, "grad_norm": 0.6834030594056776, "learning_rate": 9.397646908347203e-06, "loss": 0.37664291858673093, "num_input_tokens_seen": 193355712, "step": 4690, "train_runtime": 18137.3543, "train_tokens_per_second": 10660.635 }, { "epoch": 0.3161190412065715, "grad_norm": 0.7445898079405069, "learning_rate": 9.396388121342375e-06, "loss": 0.36492199897766114, "num_input_tokens_seen": 193571192, "step": 4695, "train_runtime": 18156.0117, "train_tokens_per_second": 10661.548 }, { "epoch": 0.31645569620253167, "grad_norm": 0.8524555558008152, "learning_rate": 9.395128104901628e-06, "loss": 0.3834716320037842, "num_input_tokens_seen": 193772360, "step": 4700, "train_runtime": 18175.1776, "train_tokens_per_second": 10661.374 }, { "epoch": 0.3167923511984918, "grad_norm": 0.7077173917087377, "learning_rate": 9.393866859377321e-06, "loss": 0.42777767181396487, "num_input_tokens_seen": 193982216, "step": 4705, "train_runtime": 18193.5782, "train_tokens_per_second": 10662.126 }, { "epoch": 0.31712900619445195, "grad_norm": 0.6671452166626269, "learning_rate": 9.392604385122157e-06, "loss": 0.40276660919189455, "num_input_tokens_seen": 194198184, "step": 4710, "train_runtime": 18211.743, "train_tokens_per_second": 10663.35 }, { "epoch": 0.3174656611904121, "grad_norm": 0.7352396813310038, "learning_rate": 9.391340682489185e-06, "loss": 0.37886595726013184, "num_input_tokens_seen": 194398320, "step": 4715, "train_runtime": 18230.8445, "train_tokens_per_second": 10663.155 }, { "epoch": 0.3178023161863722, "grad_norm": 0.9446565640262536, "learning_rate": 9.390075751831794e-06, "loss": 0.3937553405761719, "num_input_tokens_seen": 194610224, "step": 4720, "train_runtime": 18249.3431, "train_tokens_per_second": 10663.958 }, { "epoch": 0.31813897118233236, "grad_norm": 3.0468827529834996, "learning_rate": 9.388809593503718e-06, "loss": 0.4166855335235596, "num_input_tokens_seen": 194820128, "step": 4725, "train_runtime": 18268.075, "train_tokens_per_second": 10664.513 }, { "epoch": 0.3184756261782925, "grad_norm": 0.8110025649751729, "learning_rate": 9.387542207859034e-06, "loss": 0.43344850540161134, "num_input_tokens_seen": 195026208, "step": 4730, "train_runtime": 18285.7452, "train_tokens_per_second": 10665.478 }, { "epoch": 0.31881228117425264, "grad_norm": 0.7166354581660168, "learning_rate": 9.386273595252161e-06, "loss": 0.4237386226654053, "num_input_tokens_seen": 195240376, "step": 4735, "train_runtime": 18304.1158, "train_tokens_per_second": 10666.474 }, { "epoch": 0.3191489361702128, "grad_norm": 0.8000565709854803, "learning_rate": 9.385003756037865e-06, "loss": 0.4237193584442139, "num_input_tokens_seen": 195451240, "step": 4740, "train_runtime": 18323.2346, "train_tokens_per_second": 10666.852 }, { "epoch": 0.3194855911661729, "grad_norm": 0.9158661296685211, "learning_rate": 9.383732690571253e-06, "loss": 0.40421171188354493, "num_input_tokens_seen": 195674936, "step": 4745, "train_runtime": 18341.3235, "train_tokens_per_second": 10668.529 }, { "epoch": 0.31982224616213306, "grad_norm": 0.7504797400803941, "learning_rate": 9.382460399207769e-06, "loss": 0.4041430950164795, "num_input_tokens_seen": 195889664, "step": 4750, "train_runtime": 18362.4393, "train_tokens_per_second": 10667.954 }, { "epoch": 0.3201589011580932, "grad_norm": 0.729254947233091, "learning_rate": 9.381186882303212e-06, "loss": 0.38881189823150636, "num_input_tokens_seen": 196078448, "step": 4755, "train_runtime": 18381.5368, "train_tokens_per_second": 10667.141 }, { "epoch": 0.32049555615405334, "grad_norm": 0.9070951752625229, "learning_rate": 9.379912140213713e-06, "loss": 0.39372644424438474, "num_input_tokens_seen": 196278000, "step": 4760, "train_runtime": 18400.7905, "train_tokens_per_second": 10666.824 }, { "epoch": 0.3208322111500135, "grad_norm": 0.7212638599392454, "learning_rate": 9.37863617329575e-06, "loss": 0.37946715354919436, "num_input_tokens_seen": 196472576, "step": 4765, "train_runtime": 18419.4528, "train_tokens_per_second": 10666.581 }, { "epoch": 0.3211688661459736, "grad_norm": 0.7732031194383863, "learning_rate": 9.377358981906145e-06, "loss": 0.3883737802505493, "num_input_tokens_seen": 196679872, "step": 4770, "train_runtime": 18438.1976, "train_tokens_per_second": 10666.979 }, { "epoch": 0.32150552114193376, "grad_norm": 0.6731450625499177, "learning_rate": 9.376080566402059e-06, "loss": 0.41810030937194825, "num_input_tokens_seen": 196896696, "step": 4775, "train_runtime": 18457.6877, "train_tokens_per_second": 10667.463 }, { "epoch": 0.3218421761378939, "grad_norm": 0.7016023001050596, "learning_rate": 9.374800927140994e-06, "loss": 0.33476498126983645, "num_input_tokens_seen": 197109672, "step": 4780, "train_runtime": 18476.7713, "train_tokens_per_second": 10667.972 }, { "epoch": 0.32217883113385404, "grad_norm": 0.8135969636675557, "learning_rate": 9.373520064480804e-06, "loss": 0.3946814060211182, "num_input_tokens_seen": 197320608, "step": 4785, "train_runtime": 18497.6918, "train_tokens_per_second": 10667.31 }, { "epoch": 0.3225154861298142, "grad_norm": 0.7303344028813346, "learning_rate": 9.372237978779672e-06, "loss": 0.39739089012145995, "num_input_tokens_seen": 197535664, "step": 4790, "train_runtime": 18515.923, "train_tokens_per_second": 10668.421 }, { "epoch": 0.3228521411257743, "grad_norm": 0.7088511898866595, "learning_rate": 9.37095467039613e-06, "loss": 0.38985095024108884, "num_input_tokens_seen": 197726536, "step": 4795, "train_runtime": 18534.6234, "train_tokens_per_second": 10667.955 }, { "epoch": 0.32318879612173446, "grad_norm": 0.7278715791917675, "learning_rate": 9.369670139689056e-06, "loss": 0.39288902282714844, "num_input_tokens_seen": 197929592, "step": 4800, "train_runtime": 18553.7467, "train_tokens_per_second": 10667.904 }, { "epoch": 0.3235254511176946, "grad_norm": 0.7138750957663776, "learning_rate": 9.368384387017659e-06, "loss": 0.3807713747024536, "num_input_tokens_seen": 198120128, "step": 4805, "train_runtime": 18573.0545, "train_tokens_per_second": 10667.073 }, { "epoch": 0.32386210611365474, "grad_norm": 0.7487115044056798, "learning_rate": 9.367097412741497e-06, "loss": 0.3859452486038208, "num_input_tokens_seen": 198319696, "step": 4810, "train_runtime": 18590.7489, "train_tokens_per_second": 10667.655 }, { "epoch": 0.3241987611096149, "grad_norm": 0.8551648483406182, "learning_rate": 9.36580921722047e-06, "loss": 0.4139377593994141, "num_input_tokens_seen": 198528432, "step": 4815, "train_runtime": 18610.8103, "train_tokens_per_second": 10667.372 }, { "epoch": 0.324535416105575, "grad_norm": 0.668150216129034, "learning_rate": 9.364519800814818e-06, "loss": 0.3656489849090576, "num_input_tokens_seen": 198740360, "step": 4820, "train_runtime": 18631.2991, "train_tokens_per_second": 10667.016 }, { "epoch": 0.32487207110153515, "grad_norm": 0.612200314359583, "learning_rate": 9.36322916388512e-06, "loss": 0.3911462306976318, "num_input_tokens_seen": 198952264, "step": 4825, "train_runtime": 18651.27, "train_tokens_per_second": 10666.955 }, { "epoch": 0.3252087260974953, "grad_norm": 0.6969016804479198, "learning_rate": 9.3619373067923e-06, "loss": 0.35567054748535154, "num_input_tokens_seen": 199168504, "step": 4830, "train_runtime": 18669.4162, "train_tokens_per_second": 10668.17 }, { "epoch": 0.32554538109345543, "grad_norm": 0.702416559483334, "learning_rate": 9.360644229897622e-06, "loss": 0.39689500331878663, "num_input_tokens_seen": 199371560, "step": 4835, "train_runtime": 18687.8136, "train_tokens_per_second": 10668.533 }, { "epoch": 0.32588203608941557, "grad_norm": 0.8205588611956653, "learning_rate": 9.35934993356269e-06, "loss": 0.4082200050354004, "num_input_tokens_seen": 199575680, "step": 4840, "train_runtime": 18706.5041, "train_tokens_per_second": 10668.786 }, { "epoch": 0.3262186910853757, "grad_norm": 0.849946177079669, "learning_rate": 9.35805441814945e-06, "loss": 0.37399275302886964, "num_input_tokens_seen": 199786880, "step": 4845, "train_runtime": 18725.7696, "train_tokens_per_second": 10669.088 }, { "epoch": 0.32655534608133585, "grad_norm": 0.8704720781120159, "learning_rate": 9.356757684020188e-06, "loss": 0.4161193370819092, "num_input_tokens_seen": 199979552, "step": 4850, "train_runtime": 18744.6238, "train_tokens_per_second": 10668.635 }, { "epoch": 0.326892001077296, "grad_norm": 0.7816476182381571, "learning_rate": 9.355459731537533e-06, "loss": 0.3830487012863159, "num_input_tokens_seen": 200183576, "step": 4855, "train_runtime": 18764.5548, "train_tokens_per_second": 10668.176 }, { "epoch": 0.32722865607325613, "grad_norm": 0.7652022981619312, "learning_rate": 9.354160561064451e-06, "loss": 0.4129038333892822, "num_input_tokens_seen": 200396360, "step": 4860, "train_runtime": 18784.8858, "train_tokens_per_second": 10667.957 }, { "epoch": 0.32756531106921627, "grad_norm": 0.6404049587212105, "learning_rate": 9.352860172964254e-06, "loss": 0.4166914939880371, "num_input_tokens_seen": 200610352, "step": 4865, "train_runtime": 18802.5522, "train_tokens_per_second": 10669.315 }, { "epoch": 0.3279019660651764, "grad_norm": 0.6879469218892831, "learning_rate": 9.35155856760059e-06, "loss": 0.361515736579895, "num_input_tokens_seen": 200827776, "step": 4870, "train_runtime": 18823.2299, "train_tokens_per_second": 10669.145 }, { "epoch": 0.32823862106113655, "grad_norm": 0.9110452296051822, "learning_rate": 9.35025574533745e-06, "loss": 0.41402263641357423, "num_input_tokens_seen": 201040832, "step": 4875, "train_runtime": 18841.6733, "train_tokens_per_second": 10670.009 }, { "epoch": 0.3285752760570967, "grad_norm": 0.6856801523819358, "learning_rate": 9.34895170653916e-06, "loss": 0.38352136611938475, "num_input_tokens_seen": 201250088, "step": 4880, "train_runtime": 18859.905, "train_tokens_per_second": 10670.79 }, { "epoch": 0.3289119310530568, "grad_norm": 0.6569713933167411, "learning_rate": 9.347646451570394e-06, "loss": 0.37700326442718507, "num_input_tokens_seen": 201459640, "step": 4885, "train_runtime": 18877.8152, "train_tokens_per_second": 10671.767 }, { "epoch": 0.32924858604901697, "grad_norm": 0.7541078158394626, "learning_rate": 9.346339980796162e-06, "loss": 0.4478188991546631, "num_input_tokens_seen": 201679224, "step": 4890, "train_runtime": 18895.6873, "train_tokens_per_second": 10673.294 }, { "epoch": 0.3295852410449771, "grad_norm": 0.745681574416046, "learning_rate": 9.345032294581813e-06, "loss": 0.39865086078643797, "num_input_tokens_seen": 201887064, "step": 4895, "train_runtime": 18913.7506, "train_tokens_per_second": 10674.089 }, { "epoch": 0.32992189604093725, "grad_norm": 0.6834522006425398, "learning_rate": 9.343723393293038e-06, "loss": 0.3824453592300415, "num_input_tokens_seen": 202090864, "step": 4900, "train_runtime": 18933.6174, "train_tokens_per_second": 10673.653 }, { "epoch": 0.3302585510368974, "grad_norm": 0.7747357823761182, "learning_rate": 9.342413277295869e-06, "loss": 0.4061680793762207, "num_input_tokens_seen": 202301432, "step": 4905, "train_runtime": 18953.0895, "train_tokens_per_second": 10673.797 }, { "epoch": 0.3305952060328575, "grad_norm": 0.6215264556702729, "learning_rate": 9.341101946956672e-06, "loss": 0.3976979494094849, "num_input_tokens_seen": 202500792, "step": 4910, "train_runtime": 18971.5965, "train_tokens_per_second": 10673.893 }, { "epoch": 0.33093186102881766, "grad_norm": 0.6996420940649833, "learning_rate": 9.33978940264216e-06, "loss": 0.4043109893798828, "num_input_tokens_seen": 202697448, "step": 4915, "train_runtime": 18993.3667, "train_tokens_per_second": 10672.013 }, { "epoch": 0.3312685160247778, "grad_norm": 0.81130187727203, "learning_rate": 9.338475644719377e-06, "loss": 0.4019026279449463, "num_input_tokens_seen": 202911176, "step": 4920, "train_runtime": 19013.1109, "train_tokens_per_second": 10672.171 }, { "epoch": 0.33160517102073794, "grad_norm": 0.7677178280366074, "learning_rate": 9.337160673555719e-06, "loss": 0.3984062194824219, "num_input_tokens_seen": 203118664, "step": 4925, "train_runtime": 19031.6403, "train_tokens_per_second": 10672.683 }, { "epoch": 0.3319418260166981, "grad_norm": 0.6991968582240169, "learning_rate": 9.335844489518905e-06, "loss": 0.39093761444091796, "num_input_tokens_seen": 203318768, "step": 4930, "train_runtime": 19051.9847, "train_tokens_per_second": 10671.789 }, { "epoch": 0.3322784810126582, "grad_norm": 0.789018458870126, "learning_rate": 9.334527092977008e-06, "loss": 0.3877824306488037, "num_input_tokens_seen": 203507584, "step": 4935, "train_runtime": 19070.6823, "train_tokens_per_second": 10671.227 }, { "epoch": 0.33261513600861836, "grad_norm": 0.6846835321296995, "learning_rate": 9.33320848429843e-06, "loss": 0.40002946853637694, "num_input_tokens_seen": 203729208, "step": 4940, "train_runtime": 19091.3511, "train_tokens_per_second": 10671.283 }, { "epoch": 0.3329517910045785, "grad_norm": 0.9622350101813781, "learning_rate": 9.331888663851917e-06, "loss": 0.4101069450378418, "num_input_tokens_seen": 203940208, "step": 4945, "train_runtime": 19109.048, "train_tokens_per_second": 10672.442 }, { "epoch": 0.33328844600053864, "grad_norm": 0.7399354248041046, "learning_rate": 9.330567632006552e-06, "loss": 0.4107541561126709, "num_input_tokens_seen": 204145528, "step": 4950, "train_runtime": 19127.9592, "train_tokens_per_second": 10672.625 }, { "epoch": 0.3336251009964988, "grad_norm": 0.801530907886732, "learning_rate": 9.329245389131759e-06, "loss": 0.405044412612915, "num_input_tokens_seen": 204353496, "step": 4955, "train_runtime": 19146.7111, "train_tokens_per_second": 10673.034 }, { "epoch": 0.3339617559924589, "grad_norm": 0.7509899866562139, "learning_rate": 9.327921935597298e-06, "loss": 0.38187122344970703, "num_input_tokens_seen": 204555304, "step": 4960, "train_runtime": 19167.3196, "train_tokens_per_second": 10672.087 }, { "epoch": 0.33429841098841906, "grad_norm": 0.9039109988432068, "learning_rate": 9.326597271773267e-06, "loss": 0.3971426963806152, "num_input_tokens_seen": 204747320, "step": 4965, "train_runtime": 19187.6785, "train_tokens_per_second": 10670.771 }, { "epoch": 0.3346350659843792, "grad_norm": 0.8318580118498375, "learning_rate": 9.325271398030107e-06, "loss": 0.3955172777175903, "num_input_tokens_seen": 204949328, "step": 4970, "train_runtime": 19206.8225, "train_tokens_per_second": 10670.652 }, { "epoch": 0.33497172098033934, "grad_norm": 0.8267598275462499, "learning_rate": 9.323944314738591e-06, "loss": 0.410984468460083, "num_input_tokens_seen": 205156832, "step": 4975, "train_runtime": 19225.0003, "train_tokens_per_second": 10671.356 }, { "epoch": 0.3353083759762995, "grad_norm": 0.9395773633551397, "learning_rate": 9.322616022269838e-06, "loss": 0.3630945682525635, "num_input_tokens_seen": 205353032, "step": 4980, "train_runtime": 19244.655, "train_tokens_per_second": 10670.653 }, { "epoch": 0.3356450309722596, "grad_norm": 0.7854360790249886, "learning_rate": 9.321286520995297e-06, "loss": 0.404550838470459, "num_input_tokens_seen": 205551272, "step": 4985, "train_runtime": 19263.6372, "train_tokens_per_second": 10670.429 }, { "epoch": 0.33598168596821976, "grad_norm": 0.7855875061072597, "learning_rate": 9.319955811286758e-06, "loss": 0.39385850429534913, "num_input_tokens_seen": 205758920, "step": 4990, "train_runtime": 19284.3385, "train_tokens_per_second": 10669.742 }, { "epoch": 0.3363183409641799, "grad_norm": 0.6982662173098674, "learning_rate": 9.318623893516354e-06, "loss": 0.3804080247879028, "num_input_tokens_seen": 205958184, "step": 4995, "train_runtime": 19302.3172, "train_tokens_per_second": 10670.127 }, { "epoch": 0.33665499596014004, "grad_norm": 0.7941517597159, "learning_rate": 9.317290768056548e-06, "loss": 0.3966778516769409, "num_input_tokens_seen": 206155920, "step": 5000, "train_runtime": 19320.8689, "train_tokens_per_second": 10670.116 }, { "epoch": 0.3369916509561002, "grad_norm": 0.7517235517660152, "learning_rate": 9.315956435280147e-06, "loss": 0.40701818466186523, "num_input_tokens_seen": 206352344, "step": 5005, "train_runtime": 19341.8754, "train_tokens_per_second": 10668.683 }, { "epoch": 0.3373283059520603, "grad_norm": 0.7477095189313746, "learning_rate": 9.314620895560292e-06, "loss": 0.3901797294616699, "num_input_tokens_seen": 206556064, "step": 5010, "train_runtime": 19360.9115, "train_tokens_per_second": 10668.716 }, { "epoch": 0.33766496094802045, "grad_norm": 0.8214752219088182, "learning_rate": 9.313284149270459e-06, "loss": 0.42746729850769044, "num_input_tokens_seen": 206759248, "step": 5015, "train_runtime": 19380.4231, "train_tokens_per_second": 10668.459 }, { "epoch": 0.3380016159439806, "grad_norm": 0.834673254934263, "learning_rate": 9.311946196784469e-06, "loss": 0.39533677101135256, "num_input_tokens_seen": 206962048, "step": 5020, "train_runtime": 19399.3786, "train_tokens_per_second": 10668.489 }, { "epoch": 0.33833827093994073, "grad_norm": 0.7027567342262283, "learning_rate": 9.310607038476476e-06, "loss": 0.40471506118774414, "num_input_tokens_seen": 207163752, "step": 5025, "train_runtime": 19419.9672, "train_tokens_per_second": 10667.564 }, { "epoch": 0.3386749259359009, "grad_norm": 0.7296325193241275, "learning_rate": 9.30926667472097e-06, "loss": 0.38095812797546386, "num_input_tokens_seen": 207375536, "step": 5030, "train_runtime": 19440.315, "train_tokens_per_second": 10667.293 }, { "epoch": 0.339011580931861, "grad_norm": 0.7236779360508491, "learning_rate": 9.307925105892779e-06, "loss": 0.40716238021850587, "num_input_tokens_seen": 207592416, "step": 5035, "train_runtime": 19459.5657, "train_tokens_per_second": 10667.885 }, { "epoch": 0.33934823592782115, "grad_norm": 0.7637485802226424, "learning_rate": 9.30658233236707e-06, "loss": 0.3975398540496826, "num_input_tokens_seen": 207809872, "step": 5040, "train_runtime": 19479.583, "train_tokens_per_second": 10668.086 }, { "epoch": 0.3396848909237813, "grad_norm": 0.7273205214299845, "learning_rate": 9.30523835451934e-06, "loss": 0.3935713529586792, "num_input_tokens_seen": 208020096, "step": 5045, "train_runtime": 19500.2521, "train_tokens_per_second": 10667.559 }, { "epoch": 0.34002154591974143, "grad_norm": 0.7997095456011288, "learning_rate": 9.303893172725437e-06, "loss": 0.43334355354309084, "num_input_tokens_seen": 208235304, "step": 5050, "train_runtime": 19519.3078, "train_tokens_per_second": 10668.171 }, { "epoch": 0.34035820091570157, "grad_norm": 0.7168553549265178, "learning_rate": 9.302546787361533e-06, "loss": 0.38083481788635254, "num_input_tokens_seen": 208446024, "step": 5055, "train_runtime": 19537.0299, "train_tokens_per_second": 10669.279 }, { "epoch": 0.3406948559116617, "grad_norm": 1.0225638645710413, "learning_rate": 9.301199198804139e-06, "loss": 0.37522842884063723, "num_input_tokens_seen": 208645760, "step": 5060, "train_runtime": 19555.9034, "train_tokens_per_second": 10669.196 }, { "epoch": 0.34103151090762185, "grad_norm": 0.814432929985624, "learning_rate": 9.299850407430102e-06, "loss": 0.4118349552154541, "num_input_tokens_seen": 208858376, "step": 5065, "train_runtime": 19575.5515, "train_tokens_per_second": 10669.348 }, { "epoch": 0.341368165903582, "grad_norm": 0.8322285812000553, "learning_rate": 9.298500413616613e-06, "loss": 0.3965138912200928, "num_input_tokens_seen": 209066624, "step": 5070, "train_runtime": 19594.8969, "train_tokens_per_second": 10669.442 }, { "epoch": 0.3417048208995421, "grad_norm": 0.7374699023035822, "learning_rate": 9.297149217741188e-06, "loss": 0.3788412570953369, "num_input_tokens_seen": 209272696, "step": 5075, "train_runtime": 19614.1746, "train_tokens_per_second": 10669.462 }, { "epoch": 0.34204147589550227, "grad_norm": 0.7760394477531464, "learning_rate": 9.295796820181688e-06, "loss": 0.42304625511169436, "num_input_tokens_seen": 209482504, "step": 5080, "train_runtime": 19634.0031, "train_tokens_per_second": 10669.373 }, { "epoch": 0.3423781308914624, "grad_norm": 0.7906701695024021, "learning_rate": 9.294443221316305e-06, "loss": 0.3981821060180664, "num_input_tokens_seen": 209686624, "step": 5085, "train_runtime": 19653.5798, "train_tokens_per_second": 10669.131 }, { "epoch": 0.34271478588742255, "grad_norm": 0.6631994062572864, "learning_rate": 9.293088421523569e-06, "loss": 0.4052303314208984, "num_input_tokens_seen": 209886888, "step": 5090, "train_runtime": 19672.0577, "train_tokens_per_second": 10669.29 }, { "epoch": 0.3430514408833827, "grad_norm": 0.8047884347200848, "learning_rate": 9.291732421182346e-06, "loss": 0.383170485496521, "num_input_tokens_seen": 210090752, "step": 5095, "train_runtime": 19693.3618, "train_tokens_per_second": 10668.1 }, { "epoch": 0.3433880958793428, "grad_norm": 0.8062402882217041, "learning_rate": 9.290375220671837e-06, "loss": 0.39216783046722414, "num_input_tokens_seen": 210292760, "step": 5100, "train_runtime": 19711.108, "train_tokens_per_second": 10668.744 }, { "epoch": 0.34372475087530296, "grad_norm": 0.7616416891860718, "learning_rate": 9.28901682037158e-06, "loss": 0.3644718170166016, "num_input_tokens_seen": 210493424, "step": 5105, "train_runtime": 19729.6495, "train_tokens_per_second": 10668.888 }, { "epoch": 0.3440614058712631, "grad_norm": 0.6637267902390557, "learning_rate": 9.287657220661442e-06, "loss": 0.42269482612609866, "num_input_tokens_seen": 210705584, "step": 5110, "train_runtime": 19748.8201, "train_tokens_per_second": 10669.275 }, { "epoch": 0.34439806086722324, "grad_norm": 0.8190255970313092, "learning_rate": 9.286296421921636e-06, "loss": 0.37175378799438474, "num_input_tokens_seen": 210908712, "step": 5115, "train_runtime": 19769.03, "train_tokens_per_second": 10668.642 }, { "epoch": 0.3447347158631834, "grad_norm": 0.8420035643510807, "learning_rate": 9.284934424532706e-06, "loss": 0.4548757553100586, "num_input_tokens_seen": 211109672, "step": 5120, "train_runtime": 19790.1377, "train_tokens_per_second": 10667.418 }, { "epoch": 0.3450713708591435, "grad_norm": 0.6536794531267892, "learning_rate": 9.283571228875525e-06, "loss": 0.3491057395935059, "num_input_tokens_seen": 211301432, "step": 5125, "train_runtime": 19810.4908, "train_tokens_per_second": 10666.138 }, { "epoch": 0.3454080258551037, "grad_norm": 0.7114274386449131, "learning_rate": 9.282206835331311e-06, "loss": 0.422836971282959, "num_input_tokens_seen": 211512056, "step": 5130, "train_runtime": 19829.0662, "train_tokens_per_second": 10666.768 }, { "epoch": 0.34574468085106386, "grad_norm": 0.7300808425297518, "learning_rate": 9.28084124428161e-06, "loss": 0.3552213430404663, "num_input_tokens_seen": 211717656, "step": 5135, "train_runtime": 19850.6636, "train_tokens_per_second": 10665.52 }, { "epoch": 0.346081335847024, "grad_norm": 0.6855807199246082, "learning_rate": 9.279474456108305e-06, "loss": 0.3680870056152344, "num_input_tokens_seen": 211936952, "step": 5140, "train_runtime": 19870.1791, "train_tokens_per_second": 10666.082 }, { "epoch": 0.34641799084298414, "grad_norm": 0.7241296548908893, "learning_rate": 9.278106471193615e-06, "loss": 0.3730999231338501, "num_input_tokens_seen": 212142896, "step": 5145, "train_runtime": 19890.1005, "train_tokens_per_second": 10665.753 }, { "epoch": 0.3467546458389443, "grad_norm": 0.7870781407103422, "learning_rate": 9.276737289920093e-06, "loss": 0.41350545883178713, "num_input_tokens_seen": 212349752, "step": 5150, "train_runtime": 19911.7954, "train_tokens_per_second": 10664.521 }, { "epoch": 0.3470913008349044, "grad_norm": 0.7048183107999672, "learning_rate": 9.275366912670624e-06, "loss": 0.4050206184387207, "num_input_tokens_seen": 212548696, "step": 5155, "train_runtime": 19930.3272, "train_tokens_per_second": 10664.586 }, { "epoch": 0.34742795583086455, "grad_norm": 0.7534647208177269, "learning_rate": 9.273995339828432e-06, "loss": 0.3902651309967041, "num_input_tokens_seen": 212750680, "step": 5160, "train_runtime": 19948.4336, "train_tokens_per_second": 10665.032 }, { "epoch": 0.3477646108268247, "grad_norm": 0.8020591724136878, "learning_rate": 9.272622571777072e-06, "loss": 0.43332905769348146, "num_input_tokens_seen": 212958904, "step": 5165, "train_runtime": 19968.2384, "train_tokens_per_second": 10664.882 }, { "epoch": 0.34810126582278483, "grad_norm": 0.7522680019953794, "learning_rate": 9.271248608900434e-06, "loss": 0.3654604196548462, "num_input_tokens_seen": 213171576, "step": 5170, "train_runtime": 19987.2266, "train_tokens_per_second": 10665.39 }, { "epoch": 0.348437920818745, "grad_norm": 0.790754708362606, "learning_rate": 9.269873451582741e-06, "loss": 0.4067992210388184, "num_input_tokens_seen": 213375144, "step": 5175, "train_runtime": 20006.2253, "train_tokens_per_second": 10665.437 }, { "epoch": 0.3487745758147051, "grad_norm": 0.7685214339352522, "learning_rate": 9.268497100208556e-06, "loss": 0.4070613861083984, "num_input_tokens_seen": 213575672, "step": 5180, "train_runtime": 20028.192, "train_tokens_per_second": 10663.752 }, { "epoch": 0.34911123081066525, "grad_norm": 0.8013646053810212, "learning_rate": 9.267119555162765e-06, "loss": 0.40584750175476075, "num_input_tokens_seen": 213791968, "step": 5185, "train_runtime": 20049.347, "train_tokens_per_second": 10663.288 }, { "epoch": 0.3494478858066254, "grad_norm": 0.7328371318114514, "learning_rate": 9.2657408168306e-06, "loss": 0.3966103792190552, "num_input_tokens_seen": 213997576, "step": 5190, "train_runtime": 20067.8119, "train_tokens_per_second": 10663.722 }, { "epoch": 0.34978454080258553, "grad_norm": 0.7721572355365685, "learning_rate": 9.264360885597617e-06, "loss": 0.39230995178222655, "num_input_tokens_seen": 214205600, "step": 5195, "train_runtime": 20088.073, "train_tokens_per_second": 10663.322 }, { "epoch": 0.35012119579854567, "grad_norm": 0.7868160348188079, "learning_rate": 9.262979761849709e-06, "loss": 0.3999286651611328, "num_input_tokens_seen": 214413160, "step": 5200, "train_runtime": 20108.3431, "train_tokens_per_second": 10662.895 }, { "epoch": 0.3504578507945058, "grad_norm": 0.7727777469547285, "learning_rate": 9.261597445973106e-06, "loss": 0.4082481384277344, "num_input_tokens_seen": 214627792, "step": 5205, "train_runtime": 20127.8823, "train_tokens_per_second": 10663.208 }, { "epoch": 0.35079450579046595, "grad_norm": 0.737453511830601, "learning_rate": 9.260213938354365e-06, "loss": 0.3937270164489746, "num_input_tokens_seen": 214828176, "step": 5210, "train_runtime": 20146.5675, "train_tokens_per_second": 10663.264 }, { "epoch": 0.3511311607864261, "grad_norm": 0.6795803531380781, "learning_rate": 9.25882923938038e-06, "loss": 0.4115775108337402, "num_input_tokens_seen": 215030120, "step": 5215, "train_runtime": 20166.7361, "train_tokens_per_second": 10662.614 }, { "epoch": 0.35146781578238623, "grad_norm": 0.9455103841368886, "learning_rate": 9.257443349438382e-06, "loss": 0.4252187252044678, "num_input_tokens_seen": 215239592, "step": 5220, "train_runtime": 20185.4743, "train_tokens_per_second": 10663.093 }, { "epoch": 0.35180447077834637, "grad_norm": 0.840339462226661, "learning_rate": 9.256056268915924e-06, "loss": 0.410122013092041, "num_input_tokens_seen": 215450080, "step": 5225, "train_runtime": 20205.7925, "train_tokens_per_second": 10662.788 }, { "epoch": 0.3521411257743065, "grad_norm": 0.6571641867598489, "learning_rate": 9.254667998200906e-06, "loss": 0.41117143630981445, "num_input_tokens_seen": 215659680, "step": 5230, "train_runtime": 20224.5409, "train_tokens_per_second": 10663.267 }, { "epoch": 0.35247778077026665, "grad_norm": 0.7562645469837294, "learning_rate": 9.253278537681548e-06, "loss": 0.43152551651000975, "num_input_tokens_seen": 215878352, "step": 5235, "train_runtime": 20242.8765, "train_tokens_per_second": 10664.411 }, { "epoch": 0.3528144357662268, "grad_norm": 0.7622030057511789, "learning_rate": 9.251887887746407e-06, "loss": 0.3945940017700195, "num_input_tokens_seen": 216090504, "step": 5240, "train_runtime": 20262.1742, "train_tokens_per_second": 10664.724 }, { "epoch": 0.3531510907621869, "grad_norm": 0.8372402847255518, "learning_rate": 9.25049604878438e-06, "loss": 0.39055280685424804, "num_input_tokens_seen": 216297120, "step": 5245, "train_runtime": 20281.5671, "train_tokens_per_second": 10664.714 }, { "epoch": 0.35348774575814707, "grad_norm": 0.8097699229226427, "learning_rate": 9.249103021184684e-06, "loss": 0.39725561141967775, "num_input_tokens_seen": 216500696, "step": 5250, "train_runtime": 20300.6665, "train_tokens_per_second": 10664.709 }, { "epoch": 0.3538244007541072, "grad_norm": 0.7288105805224065, "learning_rate": 9.24770880533688e-06, "loss": 0.4271368503570557, "num_input_tokens_seen": 216715968, "step": 5255, "train_runtime": 20318.9993, "train_tokens_per_second": 10665.681 }, { "epoch": 0.35416105575006734, "grad_norm": 0.9025283470995507, "learning_rate": 9.24631340163085e-06, "loss": 0.41793146133422854, "num_input_tokens_seen": 216895200, "step": 5260, "train_runtime": 20338.2583, "train_tokens_per_second": 10664.394 }, { "epoch": 0.3544977107460275, "grad_norm": 0.7205731870720162, "learning_rate": 9.244916810456822e-06, "loss": 0.36079583168029783, "num_input_tokens_seen": 217110120, "step": 5265, "train_runtime": 20356.3466, "train_tokens_per_second": 10665.476 }, { "epoch": 0.3548343657419876, "grad_norm": 0.6851997278681621, "learning_rate": 9.24351903220534e-06, "loss": 0.40517635345458985, "num_input_tokens_seen": 217321696, "step": 5270, "train_runtime": 20376.359, "train_tokens_per_second": 10665.384 }, { "epoch": 0.35517102073794776, "grad_norm": 0.801531907428412, "learning_rate": 9.242120067267295e-06, "loss": 0.36540684700012205, "num_input_tokens_seen": 217526168, "step": 5275, "train_runtime": 20395.2924, "train_tokens_per_second": 10665.509 }, { "epoch": 0.3555076757339079, "grad_norm": 0.7811713607153448, "learning_rate": 9.2407199160339e-06, "loss": 0.39802260398864747, "num_input_tokens_seen": 217727152, "step": 5280, "train_runtime": 20414.2957, "train_tokens_per_second": 10665.426 }, { "epoch": 0.35584433072986804, "grad_norm": 0.8204022848068101, "learning_rate": 9.239318578896701e-06, "loss": 0.39220170974731444, "num_input_tokens_seen": 217930480, "step": 5285, "train_runtime": 20434.1482, "train_tokens_per_second": 10665.014 }, { "epoch": 0.3561809857258282, "grad_norm": 0.8721851373192286, "learning_rate": 9.237916056247583e-06, "loss": 0.41135320663452146, "num_input_tokens_seen": 218131760, "step": 5290, "train_runtime": 20452.8669, "train_tokens_per_second": 10665.095 }, { "epoch": 0.3565176407217883, "grad_norm": 0.7834106323810962, "learning_rate": 9.23651234847875e-06, "loss": 0.4196471214294434, "num_input_tokens_seen": 218334512, "step": 5295, "train_runtime": 20473.2194, "train_tokens_per_second": 10664.396 }, { "epoch": 0.35685429571774846, "grad_norm": 0.7988533309729209, "learning_rate": 9.23510745598275e-06, "loss": 0.39126780033111574, "num_input_tokens_seen": 218529416, "step": 5300, "train_runtime": 20492.3119, "train_tokens_per_second": 10663.971 }, { "epoch": 0.3571909507137086, "grad_norm": 0.587701333960172, "learning_rate": 9.233701379152456e-06, "loss": 0.38498358726501464, "num_input_tokens_seen": 218738424, "step": 5305, "train_runtime": 20512.701, "train_tokens_per_second": 10663.56 }, { "epoch": 0.35752760570966874, "grad_norm": 0.7585707552259083, "learning_rate": 9.232294118381069e-06, "loss": 0.42433595657348633, "num_input_tokens_seen": 218948104, "step": 5310, "train_runtime": 20530.0727, "train_tokens_per_second": 10664.751 }, { "epoch": 0.3578642607056289, "grad_norm": 0.6841098254614572, "learning_rate": 9.230885674062129e-06, "loss": 0.38097643852233887, "num_input_tokens_seen": 219154800, "step": 5315, "train_runtime": 20548.954, "train_tokens_per_second": 10665.01 }, { "epoch": 0.358200915701589, "grad_norm": 0.8140267021490619, "learning_rate": 9.2294760465895e-06, "loss": 0.4089194297790527, "num_input_tokens_seen": 219368120, "step": 5320, "train_runtime": 20568.0772, "train_tokens_per_second": 10665.466 }, { "epoch": 0.35853757069754916, "grad_norm": 0.7899421544623492, "learning_rate": 9.228065236357383e-06, "loss": 0.39807949066162107, "num_input_tokens_seen": 219579984, "step": 5325, "train_runtime": 20585.5825, "train_tokens_per_second": 10666.688 }, { "epoch": 0.3588742256935093, "grad_norm": 0.6302560382191112, "learning_rate": 9.226653243760304e-06, "loss": 0.37761311531066893, "num_input_tokens_seen": 219783232, "step": 5330, "train_runtime": 20604.1454, "train_tokens_per_second": 10666.942 }, { "epoch": 0.35921088068946944, "grad_norm": 0.6788357280047466, "learning_rate": 9.225240069193124e-06, "loss": 0.4119251728057861, "num_input_tokens_seen": 219990328, "step": 5335, "train_runtime": 20624.6908, "train_tokens_per_second": 10666.358 }, { "epoch": 0.3595475356854296, "grad_norm": 0.7959026573817127, "learning_rate": 9.223825713051034e-06, "loss": 0.4027989387512207, "num_input_tokens_seen": 220191968, "step": 5340, "train_runtime": 20642.6014, "train_tokens_per_second": 10666.871 }, { "epoch": 0.3598841906813897, "grad_norm": 0.7907673258774192, "learning_rate": 9.222410175729549e-06, "loss": 0.38942251205444334, "num_input_tokens_seen": 220399264, "step": 5345, "train_runtime": 20663.6317, "train_tokens_per_second": 10666.047 }, { "epoch": 0.36022084567734985, "grad_norm": 0.6875280223898185, "learning_rate": 9.220993457624523e-06, "loss": 0.3712606430053711, "num_input_tokens_seen": 220605496, "step": 5350, "train_runtime": 20683.7297, "train_tokens_per_second": 10665.654 }, { "epoch": 0.36055750067331, "grad_norm": 0.9030668419059319, "learning_rate": 9.219575559132136e-06, "loss": 0.41153392791748045, "num_input_tokens_seen": 220810024, "step": 5355, "train_runtime": 20703.1794, "train_tokens_per_second": 10665.513 }, { "epoch": 0.36089415566927013, "grad_norm": 0.8954733930811473, "learning_rate": 9.2181564806489e-06, "loss": 0.3722836017608643, "num_input_tokens_seen": 221008688, "step": 5360, "train_runtime": 20721.4669, "train_tokens_per_second": 10665.687 }, { "epoch": 0.3612308106652303, "grad_norm": 0.6551431603046217, "learning_rate": 9.216736222571655e-06, "loss": 0.36536331176757814, "num_input_tokens_seen": 221217664, "step": 5365, "train_runtime": 20740.8389, "train_tokens_per_second": 10665.801 }, { "epoch": 0.3615674656611904, "grad_norm": 0.7779504709199748, "learning_rate": 9.215314785297572e-06, "loss": 0.4434269905090332, "num_input_tokens_seen": 221407272, "step": 5370, "train_runtime": 20760.2417, "train_tokens_per_second": 10664.966 }, { "epoch": 0.36190412065715055, "grad_norm": 0.7552782382222336, "learning_rate": 9.21389216922415e-06, "loss": 0.3921216011047363, "num_input_tokens_seen": 221616760, "step": 5375, "train_runtime": 20779.1342, "train_tokens_per_second": 10665.351 }, { "epoch": 0.3622407756531107, "grad_norm": 0.7577726324708023, "learning_rate": 9.212468374749222e-06, "loss": 0.4346291542053223, "num_input_tokens_seen": 221823920, "step": 5380, "train_runtime": 20799.5043, "train_tokens_per_second": 10664.866 }, { "epoch": 0.36257743064907083, "grad_norm": 0.7227645640031692, "learning_rate": 9.211043402270942e-06, "loss": 0.39769134521484373, "num_input_tokens_seen": 222026736, "step": 5385, "train_runtime": 20817.7284, "train_tokens_per_second": 10665.272 }, { "epoch": 0.36291408564503097, "grad_norm": 0.7501316605260205, "learning_rate": 9.209617252187806e-06, "loss": 0.3728576898574829, "num_input_tokens_seen": 222228864, "step": 5390, "train_runtime": 20837.7756, "train_tokens_per_second": 10664.711 }, { "epoch": 0.3632507406409911, "grad_norm": 0.6923720561658041, "learning_rate": 9.208189924898627e-06, "loss": 0.3508558750152588, "num_input_tokens_seen": 222429408, "step": 5395, "train_runtime": 20859.7427, "train_tokens_per_second": 10663.095 }, { "epoch": 0.36358739563695125, "grad_norm": 0.7772900293239862, "learning_rate": 9.206761420802554e-06, "loss": 0.43315868377685546, "num_input_tokens_seen": 222637568, "step": 5400, "train_runtime": 20878.784, "train_tokens_per_second": 10663.34 }, { "epoch": 0.3639240506329114, "grad_norm": 0.7492047869184861, "learning_rate": 9.205331740299065e-06, "loss": 0.3810384273529053, "num_input_tokens_seen": 222837520, "step": 5405, "train_runtime": 20898.6486, "train_tokens_per_second": 10662.772 }, { "epoch": 0.36426070562887153, "grad_norm": 0.689205772876786, "learning_rate": 9.203900883787967e-06, "loss": 0.4177751064300537, "num_input_tokens_seen": 223046712, "step": 5410, "train_runtime": 20918.065, "train_tokens_per_second": 10662.875 }, { "epoch": 0.36459736062483167, "grad_norm": 0.7464816895451662, "learning_rate": 9.202468851669388e-06, "loss": 0.42368154525756835, "num_input_tokens_seen": 223255912, "step": 5415, "train_runtime": 20939.7074, "train_tokens_per_second": 10661.845 }, { "epoch": 0.3649340156207918, "grad_norm": 0.6884389625467369, "learning_rate": 9.201035644343797e-06, "loss": 0.41063222885131834, "num_input_tokens_seen": 223458264, "step": 5420, "train_runtime": 20959.1487, "train_tokens_per_second": 10661.61 }, { "epoch": 0.36527067061675195, "grad_norm": 0.8157821193525892, "learning_rate": 9.199601262211985e-06, "loss": 0.39802711009979247, "num_input_tokens_seen": 223653680, "step": 5425, "train_runtime": 20978.2612, "train_tokens_per_second": 10661.212 }, { "epoch": 0.3656073256127121, "grad_norm": 0.7283574408200473, "learning_rate": 9.19816570567507e-06, "loss": 0.40195207595825194, "num_input_tokens_seen": 223863232, "step": 5430, "train_runtime": 20996.1768, "train_tokens_per_second": 10662.095 }, { "epoch": 0.3659439806086722, "grad_norm": 0.8241465106566984, "learning_rate": 9.196728975134503e-06, "loss": 0.4122671127319336, "num_input_tokens_seen": 224062264, "step": 5435, "train_runtime": 21016.8646, "train_tokens_per_second": 10661.07 }, { "epoch": 0.36628063560463237, "grad_norm": 0.8829227654219252, "learning_rate": 9.195291070992061e-06, "loss": 0.40197067260742186, "num_input_tokens_seen": 224259720, "step": 5440, "train_runtime": 21035.71, "train_tokens_per_second": 10660.906 }, { "epoch": 0.3666172906005925, "grad_norm": 0.7915851722862793, "learning_rate": 9.193851993649849e-06, "loss": 0.3651571750640869, "num_input_tokens_seen": 224472808, "step": 5445, "train_runtime": 21055.6829, "train_tokens_per_second": 10660.913 }, { "epoch": 0.36695394559655264, "grad_norm": 0.747008381258428, "learning_rate": 9.1924117435103e-06, "loss": 0.3943001747131348, "num_input_tokens_seen": 224676752, "step": 5450, "train_runtime": 21074.5873, "train_tokens_per_second": 10661.027 }, { "epoch": 0.3672906005925128, "grad_norm": 0.8212868857848525, "learning_rate": 9.190970320976176e-06, "loss": 0.3735776424407959, "num_input_tokens_seen": 224887632, "step": 5455, "train_runtime": 21093.7117, "train_tokens_per_second": 10661.359 }, { "epoch": 0.3676272555884729, "grad_norm": 1.0527296730878517, "learning_rate": 9.189527726450565e-06, "loss": 0.4363835334777832, "num_input_tokens_seen": 225070280, "step": 5460, "train_runtime": 21112.149, "train_tokens_per_second": 10660.7 }, { "epoch": 0.36796391058443306, "grad_norm": 0.6571866698545193, "learning_rate": 9.188083960336885e-06, "loss": 0.3786278247833252, "num_input_tokens_seen": 225280824, "step": 5465, "train_runtime": 21131.7074, "train_tokens_per_second": 10660.796 }, { "epoch": 0.3683005655803932, "grad_norm": 0.69709572885758, "learning_rate": 9.186639023038879e-06, "loss": 0.4120427131652832, "num_input_tokens_seen": 225487424, "step": 5470, "train_runtime": 21151.1271, "train_tokens_per_second": 10660.776 }, { "epoch": 0.36863722057635334, "grad_norm": 0.8225813530212571, "learning_rate": 9.185192914960622e-06, "loss": 0.4302685737609863, "num_input_tokens_seen": 225690304, "step": 5475, "train_runtime": 21171.1967, "train_tokens_per_second": 10660.253 }, { "epoch": 0.3689738755723135, "grad_norm": 0.7332611737907476, "learning_rate": 9.183745636506511e-06, "loss": 0.3958707094192505, "num_input_tokens_seen": 225881344, "step": 5480, "train_runtime": 21188.965, "train_tokens_per_second": 10660.329 }, { "epoch": 0.3693105305682736, "grad_norm": 0.6643871421567312, "learning_rate": 9.182297188081274e-06, "loss": 0.3993483066558838, "num_input_tokens_seen": 226090304, "step": 5485, "train_runtime": 21206.5209, "train_tokens_per_second": 10661.358 }, { "epoch": 0.36964718556423376, "grad_norm": 0.7234566690423953, "learning_rate": 9.180847570089964e-06, "loss": 0.3818791151046753, "num_input_tokens_seen": 226279712, "step": 5490, "train_runtime": 21228.0015, "train_tokens_per_second": 10659.492 }, { "epoch": 0.3699838405601939, "grad_norm": 0.7061411413328829, "learning_rate": 9.179396782937965e-06, "loss": 0.4325400829315186, "num_input_tokens_seen": 226497704, "step": 5495, "train_runtime": 21247.0959, "train_tokens_per_second": 10660.172 }, { "epoch": 0.37032049555615404, "grad_norm": 0.7817587544050054, "learning_rate": 9.17794482703098e-06, "loss": 0.4243051528930664, "num_input_tokens_seen": 226703856, "step": 5500, "train_runtime": 21266.5455, "train_tokens_per_second": 10660.117 }, { "epoch": 0.3706571505521142, "grad_norm": 0.7331951980216324, "learning_rate": 9.176491702775049e-06, "loss": 0.41129751205444337, "num_input_tokens_seen": 226899456, "step": 5505, "train_runtime": 21287.9648, "train_tokens_per_second": 10658.579 }, { "epoch": 0.3709938055480743, "grad_norm": 0.7246834359126296, "learning_rate": 9.17503741057653e-06, "loss": 0.42662367820739744, "num_input_tokens_seen": 227108736, "step": 5510, "train_runtime": 21307.0934, "train_tokens_per_second": 10658.832 }, { "epoch": 0.37133046054403446, "grad_norm": 0.7453363420607928, "learning_rate": 9.173581950842111e-06, "loss": 0.3931560039520264, "num_input_tokens_seen": 227312128, "step": 5515, "train_runtime": 21325.9404, "train_tokens_per_second": 10658.95 }, { "epoch": 0.3716671155399946, "grad_norm": 0.8134312159510764, "learning_rate": 9.172125323978811e-06, "loss": 0.40500750541687014, "num_input_tokens_seen": 227519704, "step": 5520, "train_runtime": 21344.2288, "train_tokens_per_second": 10659.542 }, { "epoch": 0.37200377053595474, "grad_norm": 0.737246069764175, "learning_rate": 9.170667530393966e-06, "loss": 0.4075812816619873, "num_input_tokens_seen": 227731664, "step": 5525, "train_runtime": 21363.4146, "train_tokens_per_second": 10659.891 }, { "epoch": 0.3723404255319149, "grad_norm": 0.7060367057688742, "learning_rate": 9.169208570495247e-06, "loss": 0.3741891860961914, "num_input_tokens_seen": 227939808, "step": 5530, "train_runtime": 21381.4366, "train_tokens_per_second": 10660.64 }, { "epoch": 0.372677080527875, "grad_norm": 0.680093430857472, "learning_rate": 9.167748444690646e-06, "loss": 0.38414435386657714, "num_input_tokens_seen": 228130288, "step": 5535, "train_runtime": 21401.2939, "train_tokens_per_second": 10659.649 }, { "epoch": 0.37301373552383515, "grad_norm": 0.7820719027079994, "learning_rate": 9.16628715338848e-06, "loss": 0.38912005424499513, "num_input_tokens_seen": 228328376, "step": 5540, "train_runtime": 21419.4164, "train_tokens_per_second": 10659.878 }, { "epoch": 0.3733503905197953, "grad_norm": 0.7350283528507529, "learning_rate": 9.164824696997398e-06, "loss": 0.37906494140625, "num_input_tokens_seen": 228523832, "step": 5545, "train_runtime": 21439.0185, "train_tokens_per_second": 10659.249 }, { "epoch": 0.37368704551575543, "grad_norm": 0.7138467298013633, "learning_rate": 9.163361075926371e-06, "loss": 0.4168558120727539, "num_input_tokens_seen": 228731552, "step": 5550, "train_runtime": 21458.4969, "train_tokens_per_second": 10659.253 }, { "epoch": 0.3740237005117156, "grad_norm": 0.6814185784702307, "learning_rate": 9.161896290584695e-06, "loss": 0.37846717834472654, "num_input_tokens_seen": 228943520, "step": 5555, "train_runtime": 21478.2925, "train_tokens_per_second": 10659.298 }, { "epoch": 0.3743603555076757, "grad_norm": 0.7268854354339761, "learning_rate": 9.160430341381991e-06, "loss": 0.3968531608581543, "num_input_tokens_seen": 229146120, "step": 5560, "train_runtime": 21499.6381, "train_tokens_per_second": 10658.138 }, { "epoch": 0.37469701050363585, "grad_norm": 0.7451574355209115, "learning_rate": 9.15896322872821e-06, "loss": 0.4018373489379883, "num_input_tokens_seen": 229353504, "step": 5565, "train_runtime": 21519.0644, "train_tokens_per_second": 10658.154 }, { "epoch": 0.375033665499596, "grad_norm": 0.8530581119436037, "learning_rate": 9.157494953033625e-06, "loss": 0.42658090591430664, "num_input_tokens_seen": 229563280, "step": 5570, "train_runtime": 21538.1097, "train_tokens_per_second": 10658.469 }, { "epoch": 0.37537032049555613, "grad_norm": 0.7224180801698608, "learning_rate": 9.156025514708832e-06, "loss": 0.40842418670654296, "num_input_tokens_seen": 229784880, "step": 5575, "train_runtime": 21556.9104, "train_tokens_per_second": 10659.453 }, { "epoch": 0.37570697549151627, "grad_norm": 0.7649861238481007, "learning_rate": 9.154554914164757e-06, "loss": 0.3819375514984131, "num_input_tokens_seen": 230004048, "step": 5580, "train_runtime": 21575.5945, "train_tokens_per_second": 10660.381 }, { "epoch": 0.3760436304874764, "grad_norm": 0.6725279803460136, "learning_rate": 9.153083151812649e-06, "loss": 0.3819655656814575, "num_input_tokens_seen": 230216528, "step": 5585, "train_runtime": 21594.6034, "train_tokens_per_second": 10660.836 }, { "epoch": 0.37638028548343655, "grad_norm": 0.7975897426219458, "learning_rate": 9.151610228064078e-06, "loss": 0.4074870109558105, "num_input_tokens_seen": 230425688, "step": 5590, "train_runtime": 21613.5312, "train_tokens_per_second": 10661.177 }, { "epoch": 0.3767169404793967, "grad_norm": 0.7687950951083993, "learning_rate": 9.150136143330949e-06, "loss": 0.41956892013549807, "num_input_tokens_seen": 230629952, "step": 5595, "train_runtime": 21633.4761, "train_tokens_per_second": 10660.79 }, { "epoch": 0.37705359547535683, "grad_norm": 0.6843364429444004, "learning_rate": 9.14866089802548e-06, "loss": 0.3784327507019043, "num_input_tokens_seen": 230843232, "step": 5600, "train_runtime": 21655.0385, "train_tokens_per_second": 10660.024 }, { "epoch": 0.37739025047131697, "grad_norm": 0.8382530227827135, "learning_rate": 9.147184492560219e-06, "loss": 0.37260732650756834, "num_input_tokens_seen": 231045384, "step": 5605, "train_runtime": 21676.1204, "train_tokens_per_second": 10658.982 }, { "epoch": 0.3777269054672771, "grad_norm": 0.7550172455540014, "learning_rate": 9.14570692734804e-06, "loss": 0.3833783626556396, "num_input_tokens_seen": 231256688, "step": 5610, "train_runtime": 21695.6843, "train_tokens_per_second": 10659.11 }, { "epoch": 0.37806356046323725, "grad_norm": 0.7898967087776719, "learning_rate": 9.144228202802137e-06, "loss": 0.41146321296691896, "num_input_tokens_seen": 231469072, "step": 5615, "train_runtime": 21714.5102, "train_tokens_per_second": 10659.65 }, { "epoch": 0.37840021545919744, "grad_norm": 0.7639729610145478, "learning_rate": 9.142748319336033e-06, "loss": 0.3904709339141846, "num_input_tokens_seen": 231678880, "step": 5620, "train_runtime": 21734.7452, "train_tokens_per_second": 10659.379 }, { "epoch": 0.3787368704551576, "grad_norm": 0.7965546081293088, "learning_rate": 9.141267277363573e-06, "loss": 0.39295339584350586, "num_input_tokens_seen": 231864104, "step": 5625, "train_runtime": 21753.5911, "train_tokens_per_second": 10658.659 }, { "epoch": 0.3790735254511177, "grad_norm": 0.7317113711242033, "learning_rate": 9.139785077298921e-06, "loss": 0.3633030652999878, "num_input_tokens_seen": 232075584, "step": 5630, "train_runtime": 21772.2216, "train_tokens_per_second": 10659.251 }, { "epoch": 0.37941018044707786, "grad_norm": 0.7464045079501975, "learning_rate": 9.138301719556577e-06, "loss": 0.39244534969329836, "num_input_tokens_seen": 232280704, "step": 5635, "train_runtime": 21792.7186, "train_tokens_per_second": 10658.638 }, { "epoch": 0.379746835443038, "grad_norm": 0.6685657221655367, "learning_rate": 9.136817204551352e-06, "loss": 0.382822322845459, "num_input_tokens_seen": 232494944, "step": 5640, "train_runtime": 21810.9712, "train_tokens_per_second": 10659.541 }, { "epoch": 0.38008349043899814, "grad_norm": 0.7114255581203617, "learning_rate": 9.135331532698385e-06, "loss": 0.39030656814575193, "num_input_tokens_seen": 232696488, "step": 5645, "train_runtime": 21830.0932, "train_tokens_per_second": 10659.436 }, { "epoch": 0.3804201454349583, "grad_norm": 0.7292818529264308, "learning_rate": 9.133844704413144e-06, "loss": 0.3800482273101807, "num_input_tokens_seen": 232896184, "step": 5650, "train_runtime": 21850.0646, "train_tokens_per_second": 10658.833 }, { "epoch": 0.3807568004309184, "grad_norm": 0.7818274977978985, "learning_rate": 9.132356720111413e-06, "loss": 0.4058388710021973, "num_input_tokens_seen": 233100464, "step": 5655, "train_runtime": 21869.4002, "train_tokens_per_second": 10658.75 }, { "epoch": 0.38109345542687856, "grad_norm": 0.7750985218356016, "learning_rate": 9.1308675802093e-06, "loss": 0.38852906227111816, "num_input_tokens_seen": 233301440, "step": 5660, "train_runtime": 21888.6203, "train_tokens_per_second": 10658.572 }, { "epoch": 0.3814301104228387, "grad_norm": 0.7026077110565174, "learning_rate": 9.129377285123241e-06, "loss": 0.40459418296813965, "num_input_tokens_seen": 233503696, "step": 5665, "train_runtime": 21907.4681, "train_tokens_per_second": 10658.635 }, { "epoch": 0.38176676541879884, "grad_norm": 0.8142379821229568, "learning_rate": 9.127885835269996e-06, "loss": 0.41389966011047363, "num_input_tokens_seen": 233712464, "step": 5670, "train_runtime": 21925.1139, "train_tokens_per_second": 10659.578 }, { "epoch": 0.382103420414759, "grad_norm": 0.6783268717636304, "learning_rate": 9.126393231066636e-06, "loss": 0.3875293254852295, "num_input_tokens_seen": 233912432, "step": 5675, "train_runtime": 21944.2001, "train_tokens_per_second": 10659.419 }, { "epoch": 0.3824400754107191, "grad_norm": 0.7274307907680426, "learning_rate": 9.124899472930568e-06, "loss": 0.4090718269348145, "num_input_tokens_seen": 234123760, "step": 5680, "train_runtime": 21963.8071, "train_tokens_per_second": 10659.525 }, { "epoch": 0.38277673040667926, "grad_norm": 0.7511559430034369, "learning_rate": 9.123404561279517e-06, "loss": 0.41834349632263185, "num_input_tokens_seen": 234318920, "step": 5685, "train_runtime": 21982.7329, "train_tokens_per_second": 10659.226 }, { "epoch": 0.3831133854026394, "grad_norm": 0.8234070789840504, "learning_rate": 9.121908496531527e-06, "loss": 0.38933496475219725, "num_input_tokens_seen": 234527056, "step": 5690, "train_runtime": 22001.3528, "train_tokens_per_second": 10659.665 }, { "epoch": 0.38345004039859953, "grad_norm": 0.6731891703410409, "learning_rate": 9.120411279104971e-06, "loss": 0.39592680931091306, "num_input_tokens_seen": 234734984, "step": 5695, "train_runtime": 22022.9834, "train_tokens_per_second": 10658.637 }, { "epoch": 0.3837866953945597, "grad_norm": 0.751593364398191, "learning_rate": 9.118912909418538e-06, "loss": 0.39847066402435305, "num_input_tokens_seen": 234945232, "step": 5700, "train_runtime": 22043.2993, "train_tokens_per_second": 10658.351 }, { "epoch": 0.3841233503905198, "grad_norm": 0.761494882017179, "learning_rate": 9.117413387891246e-06, "loss": 0.41308159828186036, "num_input_tokens_seen": 235149912, "step": 5705, "train_runtime": 22064.4496, "train_tokens_per_second": 10657.411 }, { "epoch": 0.38446000538647995, "grad_norm": 1.010015786769423, "learning_rate": 9.11591271494243e-06, "loss": 0.3939544200897217, "num_input_tokens_seen": 235354816, "step": 5710, "train_runtime": 22083.8721, "train_tokens_per_second": 10657.317 }, { "epoch": 0.3847966603824401, "grad_norm": 0.8615040633322211, "learning_rate": 9.114410890991748e-06, "loss": 0.40891056060791015, "num_input_tokens_seen": 235558776, "step": 5715, "train_runtime": 22103.8169, "train_tokens_per_second": 10656.928 }, { "epoch": 0.38513331537840023, "grad_norm": 0.7366093741834869, "learning_rate": 9.112907916459177e-06, "loss": 0.3729217052459717, "num_input_tokens_seen": 235744344, "step": 5720, "train_runtime": 22123.0023, "train_tokens_per_second": 10656.074 }, { "epoch": 0.38546997037436037, "grad_norm": 0.7431717977529716, "learning_rate": 9.111403791765025e-06, "loss": 0.39297964572906496, "num_input_tokens_seen": 235955360, "step": 5725, "train_runtime": 22141.1018, "train_tokens_per_second": 10656.893 }, { "epoch": 0.3858066253703205, "grad_norm": 0.7026939521156358, "learning_rate": 9.109898517329914e-06, "loss": 0.37209329605102537, "num_input_tokens_seen": 236168968, "step": 5730, "train_runtime": 22159.3504, "train_tokens_per_second": 10657.757 }, { "epoch": 0.38614328036628065, "grad_norm": 0.7073264752471625, "learning_rate": 9.108392093574785e-06, "loss": 0.3978463649749756, "num_input_tokens_seen": 236374200, "step": 5735, "train_runtime": 22178.1858, "train_tokens_per_second": 10657.959 }, { "epoch": 0.3864799353622408, "grad_norm": 0.802787764528894, "learning_rate": 9.10688452092091e-06, "loss": 0.3575890302658081, "num_input_tokens_seen": 236578456, "step": 5740, "train_runtime": 22195.9034, "train_tokens_per_second": 10658.654 }, { "epoch": 0.38681659035820093, "grad_norm": 0.8448079214727254, "learning_rate": 9.105375799789874e-06, "loss": 0.4023919582366943, "num_input_tokens_seen": 236781568, "step": 5745, "train_runtime": 22215.8803, "train_tokens_per_second": 10658.212 }, { "epoch": 0.38715324535416107, "grad_norm": 0.7919926815339101, "learning_rate": 9.103865930603586e-06, "loss": 0.38658294677734373, "num_input_tokens_seen": 236980240, "step": 5750, "train_runtime": 22237.2054, "train_tokens_per_second": 10656.925 }, { "epoch": 0.3874899003501212, "grad_norm": 0.7572903095837098, "learning_rate": 9.102354913784279e-06, "loss": 0.3800193309783936, "num_input_tokens_seen": 237188208, "step": 5755, "train_runtime": 22255.1724, "train_tokens_per_second": 10657.667 }, { "epoch": 0.38782655534608135, "grad_norm": 0.7228629672434557, "learning_rate": 9.100842749754499e-06, "loss": 0.3615226745605469, "num_input_tokens_seen": 237400088, "step": 5760, "train_runtime": 22274.3377, "train_tokens_per_second": 10658.009 }, { "epoch": 0.3881632103420415, "grad_norm": 0.7120361651920923, "learning_rate": 9.099329438937122e-06, "loss": 0.41047468185424807, "num_input_tokens_seen": 237603424, "step": 5765, "train_runtime": 22292.7461, "train_tokens_per_second": 10658.329 }, { "epoch": 0.3884998653380016, "grad_norm": 0.8703212045125727, "learning_rate": 9.09781498175534e-06, "loss": 0.36102919578552245, "num_input_tokens_seen": 237803456, "step": 5770, "train_runtime": 22312.1544, "train_tokens_per_second": 10658.023 }, { "epoch": 0.38883652033396177, "grad_norm": 0.7143714134265303, "learning_rate": 9.096299378632666e-06, "loss": 0.3838529586791992, "num_input_tokens_seen": 238019224, "step": 5775, "train_runtime": 22331.3128, "train_tokens_per_second": 10658.541 }, { "epoch": 0.3891731753299219, "grad_norm": 0.7343635573355448, "learning_rate": 9.09478262999293e-06, "loss": 0.428206205368042, "num_input_tokens_seen": 238236448, "step": 5780, "train_runtime": 22349.4261, "train_tokens_per_second": 10659.623 }, { "epoch": 0.38950983032588204, "grad_norm": 0.7615510827331069, "learning_rate": 9.09326473626029e-06, "loss": 0.3778141975402832, "num_input_tokens_seen": 238436792, "step": 5785, "train_runtime": 22368.8352, "train_tokens_per_second": 10659.33 }, { "epoch": 0.3898464853218422, "grad_norm": 0.7995416532067136, "learning_rate": 9.091745697859218e-06, "loss": 0.41457204818725585, "num_input_tokens_seen": 238649912, "step": 5790, "train_runtime": 22388.5111, "train_tokens_per_second": 10659.481 }, { "epoch": 0.3901831403178023, "grad_norm": 0.7464654319017472, "learning_rate": 9.090225515214512e-06, "loss": 0.40692882537841796, "num_input_tokens_seen": 238855936, "step": 5795, "train_runtime": 22407.9185, "train_tokens_per_second": 10659.443 }, { "epoch": 0.39051979531376246, "grad_norm": 0.8510649497197147, "learning_rate": 9.088704188751281e-06, "loss": 0.41722536087036133, "num_input_tokens_seen": 239056696, "step": 5800, "train_runtime": 22427.743, "train_tokens_per_second": 10658.973 }, { "epoch": 0.3908564503097226, "grad_norm": 0.7998447920788373, "learning_rate": 9.087181718894963e-06, "loss": 0.39131870269775393, "num_input_tokens_seen": 239269256, "step": 5805, "train_runtime": 22447.6782, "train_tokens_per_second": 10658.976 }, { "epoch": 0.39119310530568274, "grad_norm": 0.7197872625501633, "learning_rate": 9.085658106071309e-06, "loss": 0.3935730218887329, "num_input_tokens_seen": 239474352, "step": 5810, "train_runtime": 22466.8265, "train_tokens_per_second": 10659.02 }, { "epoch": 0.3915297603016429, "grad_norm": 0.7266772043229679, "learning_rate": 9.084133350706394e-06, "loss": 0.37368154525756836, "num_input_tokens_seen": 239675400, "step": 5815, "train_runtime": 22486.5424, "train_tokens_per_second": 10658.615 }, { "epoch": 0.391866415297603, "grad_norm": 0.684171184443501, "learning_rate": 9.082607453226613e-06, "loss": 0.38204050064086914, "num_input_tokens_seen": 239882416, "step": 5820, "train_runtime": 22504.3072, "train_tokens_per_second": 10659.4 }, { "epoch": 0.39220307029356316, "grad_norm": 0.7099551616871694, "learning_rate": 9.081080414058674e-06, "loss": 0.4030238151550293, "num_input_tokens_seen": 240081488, "step": 5825, "train_runtime": 22523.0087, "train_tokens_per_second": 10659.388 }, { "epoch": 0.3925397252895233, "grad_norm": 0.7455510417064315, "learning_rate": 9.079552233629612e-06, "loss": 0.37485804557800295, "num_input_tokens_seen": 240282064, "step": 5830, "train_runtime": 22542.3429, "train_tokens_per_second": 10659.143 }, { "epoch": 0.39287638028548344, "grad_norm": 0.7587076972607659, "learning_rate": 9.078022912366776e-06, "loss": 0.39361934661865233, "num_input_tokens_seen": 240495768, "step": 5835, "train_runtime": 22561.0113, "train_tokens_per_second": 10659.796 }, { "epoch": 0.3932130352814436, "grad_norm": 0.776960872058204, "learning_rate": 9.076492450697835e-06, "loss": 0.4018550872802734, "num_input_tokens_seen": 240712048, "step": 5840, "train_runtime": 22579.5379, "train_tokens_per_second": 10660.628 }, { "epoch": 0.3935496902774037, "grad_norm": 0.8336825695877618, "learning_rate": 9.074960849050782e-06, "loss": 0.3854856252670288, "num_input_tokens_seen": 240920856, "step": 5845, "train_runtime": 22599.0349, "train_tokens_per_second": 10660.67 }, { "epoch": 0.39388634527336386, "grad_norm": 0.7009348264305525, "learning_rate": 9.07342810785392e-06, "loss": 0.38190104961395266, "num_input_tokens_seen": 241110480, "step": 5850, "train_runtime": 22618.1697, "train_tokens_per_second": 10660.035 }, { "epoch": 0.394223000269324, "grad_norm": 0.7262272255137634, "learning_rate": 9.071894227535878e-06, "loss": 0.38515219688415525, "num_input_tokens_seen": 241314832, "step": 5855, "train_runtime": 22638.3552, "train_tokens_per_second": 10659.557 }, { "epoch": 0.39455965526528414, "grad_norm": 0.8234241344972416, "learning_rate": 9.070359208525598e-06, "loss": 0.4025091648101807, "num_input_tokens_seen": 241526304, "step": 5860, "train_runtime": 22656.6629, "train_tokens_per_second": 10660.277 }, { "epoch": 0.3948963102612443, "grad_norm": 0.7330465322716825, "learning_rate": 9.068823051252346e-06, "loss": 0.3968078374862671, "num_input_tokens_seen": 241737848, "step": 5865, "train_runtime": 22676.3491, "train_tokens_per_second": 10660.351 }, { "epoch": 0.3952329652572044, "grad_norm": 0.7639384637537434, "learning_rate": 9.067285756145702e-06, "loss": 0.3821371078491211, "num_input_tokens_seen": 241952296, "step": 5870, "train_runtime": 22695.3495, "train_tokens_per_second": 10660.876 }, { "epoch": 0.39556962025316456, "grad_norm": 0.7719154318385656, "learning_rate": 9.065747323635565e-06, "loss": 0.3324697256088257, "num_input_tokens_seen": 242129024, "step": 5875, "train_runtime": 22715.6604, "train_tokens_per_second": 10659.123 }, { "epoch": 0.3959062752491247, "grad_norm": 0.7294462100909115, "learning_rate": 9.064207754152154e-06, "loss": 0.40439529418945314, "num_input_tokens_seen": 242332864, "step": 5880, "train_runtime": 22735.0887, "train_tokens_per_second": 10658.98 }, { "epoch": 0.39624293024508483, "grad_norm": 0.6912511652616805, "learning_rate": 9.062667048126005e-06, "loss": 0.39128139019012453, "num_input_tokens_seen": 242548408, "step": 5885, "train_runtime": 22755.9928, "train_tokens_per_second": 10658.661 }, { "epoch": 0.396579585241045, "grad_norm": 0.9193167775473432, "learning_rate": 9.061125205987971e-06, "loss": 0.4198793411254883, "num_input_tokens_seen": 242749448, "step": 5890, "train_runtime": 22774.3311, "train_tokens_per_second": 10658.906 }, { "epoch": 0.3969162402370051, "grad_norm": 0.7301178537215846, "learning_rate": 9.059582228169222e-06, "loss": 0.3750178575515747, "num_input_tokens_seen": 242940256, "step": 5895, "train_runtime": 22791.6455, "train_tokens_per_second": 10659.18 }, { "epoch": 0.39725289523296525, "grad_norm": 0.6981412454126158, "learning_rate": 9.058038115101248e-06, "loss": 0.40938568115234375, "num_input_tokens_seen": 243156280, "step": 5900, "train_runtime": 22810.591, "train_tokens_per_second": 10659.797 }, { "epoch": 0.3975895502289254, "grad_norm": 0.6724255386963401, "learning_rate": 9.056492867215857e-06, "loss": 0.35339808464050293, "num_input_tokens_seen": 243351768, "step": 5905, "train_runtime": 22830.977, "train_tokens_per_second": 10658.842 }, { "epoch": 0.39792620522488553, "grad_norm": 0.6471920347665647, "learning_rate": 9.05494648494517e-06, "loss": 0.3954996824264526, "num_input_tokens_seen": 243547080, "step": 5910, "train_runtime": 22849.751, "train_tokens_per_second": 10658.632 }, { "epoch": 0.39826286022084567, "grad_norm": 0.6651078203639816, "learning_rate": 9.053398968721629e-06, "loss": 0.3703948497772217, "num_input_tokens_seen": 243760064, "step": 5915, "train_runtime": 22870.2304, "train_tokens_per_second": 10658.4 }, { "epoch": 0.3985995152168058, "grad_norm": 0.7217284134785978, "learning_rate": 9.05185031897799e-06, "loss": 0.43773617744445803, "num_input_tokens_seen": 243963832, "step": 5920, "train_runtime": 22888.4406, "train_tokens_per_second": 10658.823 }, { "epoch": 0.39893617021276595, "grad_norm": 0.7548150374983776, "learning_rate": 9.050300536147331e-06, "loss": 0.4249082088470459, "num_input_tokens_seen": 244182928, "step": 5925, "train_runtime": 22907.0927, "train_tokens_per_second": 10659.708 }, { "epoch": 0.3992728252087261, "grad_norm": 0.7903809925582774, "learning_rate": 9.048749620663044e-06, "loss": 0.36412773132324217, "num_input_tokens_seen": 244400328, "step": 5930, "train_runtime": 22925.3352, "train_tokens_per_second": 10660.709 }, { "epoch": 0.39960948020468623, "grad_norm": 0.6863680338376983, "learning_rate": 9.047197572958834e-06, "loss": 0.374293851852417, "num_input_tokens_seen": 244609752, "step": 5935, "train_runtime": 22945.5915, "train_tokens_per_second": 10660.425 }, { "epoch": 0.39994613520064637, "grad_norm": 0.6946694128381384, "learning_rate": 9.04564439346873e-06, "loss": 0.3929856777191162, "num_input_tokens_seen": 244808120, "step": 5940, "train_runtime": 22964.0364, "train_tokens_per_second": 10660.5 }, { "epoch": 0.4002827901966065, "grad_norm": 0.9712643549121261, "learning_rate": 9.044090082627071e-06, "loss": 0.40324153900146487, "num_input_tokens_seen": 245003720, "step": 5945, "train_runtime": 22982.101, "train_tokens_per_second": 10660.632 }, { "epoch": 0.40061944519256665, "grad_norm": 0.7023748551061254, "learning_rate": 9.042534640868514e-06, "loss": 0.39799985885620115, "num_input_tokens_seen": 245198424, "step": 5950, "train_runtime": 22999.9489, "train_tokens_per_second": 10660.825 }, { "epoch": 0.4009561001885268, "grad_norm": 0.6422708173650269, "learning_rate": 9.04097806862804e-06, "loss": 0.4072426795959473, "num_input_tokens_seen": 245407208, "step": 5955, "train_runtime": 23017.7601, "train_tokens_per_second": 10661.646 }, { "epoch": 0.4012927551844869, "grad_norm": 0.7353758220024751, "learning_rate": 9.03942036634093e-06, "loss": 0.4104832649230957, "num_input_tokens_seen": 245611952, "step": 5960, "train_runtime": 23036.9909, "train_tokens_per_second": 10661.633 }, { "epoch": 0.40162941018044707, "grad_norm": 0.7370241730245665, "learning_rate": 9.037861534442797e-06, "loss": 0.37140183448791503, "num_input_tokens_seen": 245826512, "step": 5965, "train_runtime": 23057.3045, "train_tokens_per_second": 10661.546 }, { "epoch": 0.4019660651764072, "grad_norm": 1.2843428619395472, "learning_rate": 9.036301573369563e-06, "loss": 0.3963762760162354, "num_input_tokens_seen": 246041416, "step": 5970, "train_runtime": 23075.8753, "train_tokens_per_second": 10662.279 }, { "epoch": 0.40230272017236735, "grad_norm": 0.7831332824659111, "learning_rate": 9.034740483557465e-06, "loss": 0.38660635948181155, "num_input_tokens_seen": 246246128, "step": 5975, "train_runtime": 23094.7387, "train_tokens_per_second": 10662.434 }, { "epoch": 0.4026393751683275, "grad_norm": 0.715900880678426, "learning_rate": 9.033178265443055e-06, "loss": 0.3872606515884399, "num_input_tokens_seen": 246452056, "step": 5980, "train_runtime": 23112.7261, "train_tokens_per_second": 10663.046 }, { "epoch": 0.4029760301642876, "grad_norm": 0.7493894154654384, "learning_rate": 9.031614919463206e-06, "loss": 0.37859311103820803, "num_input_tokens_seen": 246661200, "step": 5985, "train_runtime": 23132.4569, "train_tokens_per_second": 10662.992 }, { "epoch": 0.40331268516024776, "grad_norm": 0.731163617277982, "learning_rate": 9.030050446055099e-06, "loss": 0.36972684860229493, "num_input_tokens_seen": 246863152, "step": 5990, "train_runtime": 23150.8904, "train_tokens_per_second": 10663.225 }, { "epoch": 0.4036493401562079, "grad_norm": 0.6751345370211234, "learning_rate": 9.028484845656235e-06, "loss": 0.39739580154418946, "num_input_tokens_seen": 247082392, "step": 5995, "train_runtime": 23169.8637, "train_tokens_per_second": 10663.955 }, { "epoch": 0.40398599515216804, "grad_norm": 0.6965238009440774, "learning_rate": 9.026918118704431e-06, "loss": 0.4261068344116211, "num_input_tokens_seen": 247290848, "step": 6000, "train_runtime": 23191.1626, "train_tokens_per_second": 10663.15 }, { "epoch": 0.4043226501481282, "grad_norm": 0.5936889217367407, "learning_rate": 9.025350265637816e-06, "loss": 0.36901102066040037, "num_input_tokens_seen": 247507576, "step": 6005, "train_runtime": 23211.1838, "train_tokens_per_second": 10663.29 }, { "epoch": 0.4046593051440883, "grad_norm": 0.7348657878849456, "learning_rate": 9.023781286894834e-06, "loss": 0.38260204792022706, "num_input_tokens_seen": 247707560, "step": 6010, "train_runtime": 23230.3612, "train_tokens_per_second": 10663.096 }, { "epoch": 0.40499596014004846, "grad_norm": 0.7080587346647202, "learning_rate": 9.022211182914247e-06, "loss": 0.38999600410461427, "num_input_tokens_seen": 247915768, "step": 6015, "train_runtime": 23250.7563, "train_tokens_per_second": 10662.697 }, { "epoch": 0.4053326151360086, "grad_norm": 0.7444069338328437, "learning_rate": 9.020639954135128e-06, "loss": 0.3823970556259155, "num_input_tokens_seen": 248116192, "step": 6020, "train_runtime": 23269.7945, "train_tokens_per_second": 10662.586 }, { "epoch": 0.40566927013196874, "grad_norm": 0.7539171006889798, "learning_rate": 9.019067600996867e-06, "loss": 0.3304227352142334, "num_input_tokens_seen": 248307232, "step": 6025, "train_runtime": 23289.7834, "train_tokens_per_second": 10661.638 }, { "epoch": 0.4060059251279289, "grad_norm": 0.7138381652579401, "learning_rate": 9.017494123939169e-06, "loss": 0.39053561687469485, "num_input_tokens_seen": 248511440, "step": 6030, "train_runtime": 23310.2109, "train_tokens_per_second": 10661.055 }, { "epoch": 0.406342580123889, "grad_norm": 0.7674204694425829, "learning_rate": 9.015919523402048e-06, "loss": 0.39113645553588866, "num_input_tokens_seen": 248716368, "step": 6035, "train_runtime": 23330.201, "train_tokens_per_second": 10660.704 }, { "epoch": 0.40667923511984916, "grad_norm": 0.8624123930616381, "learning_rate": 9.014343799825838e-06, "loss": 0.40047006607055663, "num_input_tokens_seen": 248908640, "step": 6040, "train_runtime": 23349.1825, "train_tokens_per_second": 10660.272 }, { "epoch": 0.4070158901158093, "grad_norm": 0.6714511612634518, "learning_rate": 9.012766953651186e-06, "loss": 0.4324782371520996, "num_input_tokens_seen": 249120616, "step": 6045, "train_runtime": 23367.6991, "train_tokens_per_second": 10660.896 }, { "epoch": 0.40735254511176944, "grad_norm": 0.7244418807924995, "learning_rate": 9.01118898531905e-06, "loss": 0.408212947845459, "num_input_tokens_seen": 249318560, "step": 6050, "train_runtime": 23388.2046, "train_tokens_per_second": 10660.013 }, { "epoch": 0.4076892001077296, "grad_norm": 0.6806332767866665, "learning_rate": 9.009609895270708e-06, "loss": 0.3674753665924072, "num_input_tokens_seen": 249534720, "step": 6055, "train_runtime": 23407.7746, "train_tokens_per_second": 10660.335 }, { "epoch": 0.4080258551036897, "grad_norm": 0.8290311320364725, "learning_rate": 9.008029683947743e-06, "loss": 0.43631491661071775, "num_input_tokens_seen": 249745096, "step": 6060, "train_runtime": 23427.3411, "train_tokens_per_second": 10660.411 }, { "epoch": 0.40836251009964986, "grad_norm": 0.7249871881191923, "learning_rate": 9.006448351792057e-06, "loss": 0.40093345642089845, "num_input_tokens_seen": 249953560, "step": 6065, "train_runtime": 23446.2352, "train_tokens_per_second": 10660.712 }, { "epoch": 0.40869916509561, "grad_norm": 0.7018178658859769, "learning_rate": 9.004865899245864e-06, "loss": 0.3869432210922241, "num_input_tokens_seen": 250159104, "step": 6070, "train_runtime": 23466.1807, "train_tokens_per_second": 10660.41 }, { "epoch": 0.40903582009157013, "grad_norm": 0.6994919990282353, "learning_rate": 9.003282326751694e-06, "loss": 0.40515985488891604, "num_input_tokens_seen": 250367840, "step": 6075, "train_runtime": 23487.1575, "train_tokens_per_second": 10659.776 }, { "epoch": 0.4093724750875303, "grad_norm": 1.4901439672992982, "learning_rate": 9.001697634752387e-06, "loss": 0.4090542793273926, "num_input_tokens_seen": 250566456, "step": 6080, "train_runtime": 23504.7674, "train_tokens_per_second": 10660.24 }, { "epoch": 0.4097091300834904, "grad_norm": 0.7378913606640798, "learning_rate": 9.000111823691097e-06, "loss": 0.3806684255599976, "num_input_tokens_seen": 250774512, "step": 6085, "train_runtime": 23524.3094, "train_tokens_per_second": 10660.228 }, { "epoch": 0.41004578507945055, "grad_norm": 0.7857924984143314, "learning_rate": 8.99852489401129e-06, "loss": 0.4086737632751465, "num_input_tokens_seen": 250986264, "step": 6090, "train_runtime": 23543.8599, "train_tokens_per_second": 10660.37 }, { "epoch": 0.4103824400754107, "grad_norm": 0.7270207310332262, "learning_rate": 8.996936846156748e-06, "loss": 0.35579671859741213, "num_input_tokens_seen": 251191720, "step": 6095, "train_runtime": 23561.8997, "train_tokens_per_second": 10660.928 }, { "epoch": 0.41071909507137083, "grad_norm": 0.7584741412343321, "learning_rate": 8.995347680571563e-06, "loss": 0.4100190162658691, "num_input_tokens_seen": 251399112, "step": 6100, "train_runtime": 23579.3888, "train_tokens_per_second": 10661.816 }, { "epoch": 0.41105575006733097, "grad_norm": 0.5964454639274721, "learning_rate": 8.993757397700137e-06, "loss": 0.3835061311721802, "num_input_tokens_seen": 251606848, "step": 6105, "train_runtime": 23597.7607, "train_tokens_per_second": 10662.319 }, { "epoch": 0.41139240506329117, "grad_norm": 0.7975964072265533, "learning_rate": 8.99216599798719e-06, "loss": 0.4293512344360352, "num_input_tokens_seen": 251826920, "step": 6110, "train_runtime": 23617.6892, "train_tokens_per_second": 10662.64 }, { "epoch": 0.4117290600592513, "grad_norm": 0.8155218516473413, "learning_rate": 8.990573481877753e-06, "loss": 0.3667956829071045, "num_input_tokens_seen": 252019224, "step": 6115, "train_runtime": 23636.2413, "train_tokens_per_second": 10662.407 }, { "epoch": 0.41206571505521145, "grad_norm": 0.7059019738180535, "learning_rate": 8.988979849817167e-06, "loss": 0.3710786819458008, "num_input_tokens_seen": 252205896, "step": 6120, "train_runtime": 23656.4678, "train_tokens_per_second": 10661.181 }, { "epoch": 0.4124023700511716, "grad_norm": 0.8268824373965136, "learning_rate": 8.987385102251085e-06, "loss": 0.3804017543792725, "num_input_tokens_seen": 252396544, "step": 6125, "train_runtime": 23674.9579, "train_tokens_per_second": 10660.908 }, { "epoch": 0.4127390250471317, "grad_norm": 0.7437559538114012, "learning_rate": 8.985789239625475e-06, "loss": 0.3997964859008789, "num_input_tokens_seen": 252605248, "step": 6130, "train_runtime": 23694.9449, "train_tokens_per_second": 10660.723 }, { "epoch": 0.41307568004309186, "grad_norm": 0.7463753870894264, "learning_rate": 8.984192262386613e-06, "loss": 0.36299571990966795, "num_input_tokens_seen": 252811424, "step": 6135, "train_runtime": 23713.3822, "train_tokens_per_second": 10661.129 }, { "epoch": 0.413412335039052, "grad_norm": 0.7269839876188401, "learning_rate": 8.98259417098109e-06, "loss": 0.4044351577758789, "num_input_tokens_seen": 253028296, "step": 6140, "train_runtime": 23732.7629, "train_tokens_per_second": 10661.561 }, { "epoch": 0.41374899003501214, "grad_norm": 0.7146860323122972, "learning_rate": 8.980994965855808e-06, "loss": 0.39677767753601073, "num_input_tokens_seen": 253235720, "step": 6145, "train_runtime": 23751.4801, "train_tokens_per_second": 10661.892 }, { "epoch": 0.4140856450309723, "grad_norm": 0.6950285558927286, "learning_rate": 8.979394647457976e-06, "loss": 0.38901286125183104, "num_input_tokens_seen": 253445000, "step": 6150, "train_runtime": 23770.6959, "train_tokens_per_second": 10662.077 }, { "epoch": 0.4144223000269324, "grad_norm": 0.7203243393661256, "learning_rate": 8.97779321623512e-06, "loss": 0.35787482261657716, "num_input_tokens_seen": 253639424, "step": 6155, "train_runtime": 23789.4152, "train_tokens_per_second": 10661.86 }, { "epoch": 0.41475895502289256, "grad_norm": 0.737528897528166, "learning_rate": 8.976190672635077e-06, "loss": 0.40205721855163573, "num_input_tokens_seen": 253850160, "step": 6160, "train_runtime": 23809.2103, "train_tokens_per_second": 10661.847 }, { "epoch": 0.4150956100188527, "grad_norm": 0.7446198190806754, "learning_rate": 8.974587017105991e-06, "loss": 0.4142397403717041, "num_input_tokens_seen": 254047480, "step": 6165, "train_runtime": 23826.8236, "train_tokens_per_second": 10662.247 }, { "epoch": 0.41543226501481284, "grad_norm": 0.6812184643710041, "learning_rate": 8.97298225009632e-06, "loss": 0.39635610580444336, "num_input_tokens_seen": 254257608, "step": 6170, "train_runtime": 23846.5335, "train_tokens_per_second": 10662.246 }, { "epoch": 0.415768920010773, "grad_norm": 0.7556536456947281, "learning_rate": 8.971376372054829e-06, "loss": 0.40092954635620115, "num_input_tokens_seen": 254464456, "step": 6175, "train_runtime": 23866.4893, "train_tokens_per_second": 10661.998 }, { "epoch": 0.4161055750067331, "grad_norm": 0.6656432660909013, "learning_rate": 8.969769383430602e-06, "loss": 0.39543848037719725, "num_input_tokens_seen": 254674144, "step": 6180, "train_runtime": 23884.5415, "train_tokens_per_second": 10662.719 }, { "epoch": 0.41644223000269326, "grad_norm": 0.6719497353862932, "learning_rate": 8.968161284673027e-06, "loss": 0.375246524810791, "num_input_tokens_seen": 254888768, "step": 6185, "train_runtime": 23903.6766, "train_tokens_per_second": 10663.162 }, { "epoch": 0.4167788849986534, "grad_norm": 0.7575646695653689, "learning_rate": 8.9665520762318e-06, "loss": 0.3770207405090332, "num_input_tokens_seen": 255091544, "step": 6190, "train_runtime": 23923.2756, "train_tokens_per_second": 10662.902 }, { "epoch": 0.41711553999461354, "grad_norm": 0.6722436147183287, "learning_rate": 8.964941758556934e-06, "loss": 0.3958683967590332, "num_input_tokens_seen": 255293120, "step": 6195, "train_runtime": 23943.2425, "train_tokens_per_second": 10662.429 }, { "epoch": 0.4174521949905737, "grad_norm": 0.7071617197125688, "learning_rate": 8.963330332098747e-06, "loss": 0.3878986597061157, "num_input_tokens_seen": 255489072, "step": 6200, "train_runtime": 23963.0619, "train_tokens_per_second": 10661.787 }, { "epoch": 0.4177888499865338, "grad_norm": 0.7279598268263975, "learning_rate": 8.961717797307872e-06, "loss": 0.3720714569091797, "num_input_tokens_seen": 255695824, "step": 6205, "train_runtime": 23981.6305, "train_tokens_per_second": 10662.153 }, { "epoch": 0.41812550498249396, "grad_norm": 0.7527901891192446, "learning_rate": 8.960104154635248e-06, "loss": 0.40451393127441404, "num_input_tokens_seen": 255900256, "step": 6210, "train_runtime": 24000.8558, "train_tokens_per_second": 10662.13 }, { "epoch": 0.4184621599784541, "grad_norm": 0.7589304519730875, "learning_rate": 8.958489404532125e-06, "loss": 0.40040087699890137, "num_input_tokens_seen": 256097208, "step": 6215, "train_runtime": 24019.7275, "train_tokens_per_second": 10661.953 }, { "epoch": 0.41879881497441424, "grad_norm": 0.7024314238275072, "learning_rate": 8.956873547450062e-06, "loss": 0.4073676109313965, "num_input_tokens_seen": 256299968, "step": 6220, "train_runtime": 24039.3102, "train_tokens_per_second": 10661.702 }, { "epoch": 0.4191354699703744, "grad_norm": 0.8633451736256872, "learning_rate": 8.95525658384093e-06, "loss": 0.43225650787353515, "num_input_tokens_seen": 256500792, "step": 6225, "train_runtime": 24058.1072, "train_tokens_per_second": 10661.72 }, { "epoch": 0.4194721249663345, "grad_norm": 0.7606670785114833, "learning_rate": 8.953638514156908e-06, "loss": 0.384546685218811, "num_input_tokens_seen": 256709648, "step": 6230, "train_runtime": 24076.8084, "train_tokens_per_second": 10662.113 }, { "epoch": 0.41980877996229465, "grad_norm": 0.7420614725448339, "learning_rate": 8.952019338850481e-06, "loss": 0.3932356834411621, "num_input_tokens_seen": 256918424, "step": 6235, "train_runtime": 24096.2845, "train_tokens_per_second": 10662.159 }, { "epoch": 0.4201454349582548, "grad_norm": 0.7460387743413969, "learning_rate": 8.950399058374447e-06, "loss": 0.37935771942138674, "num_input_tokens_seen": 257129880, "step": 6240, "train_runtime": 24113.9594, "train_tokens_per_second": 10663.113 }, { "epoch": 0.42048208995421493, "grad_norm": 0.8639442082325435, "learning_rate": 8.948777673181913e-06, "loss": 0.38997950553894045, "num_input_tokens_seen": 257340040, "step": 6245, "train_runtime": 24132.6058, "train_tokens_per_second": 10663.583 }, { "epoch": 0.42081874495017507, "grad_norm": 0.7320004645080332, "learning_rate": 8.947155183726296e-06, "loss": 0.3613597869873047, "num_input_tokens_seen": 257552256, "step": 6250, "train_runtime": 24151.6535, "train_tokens_per_second": 10663.96 }, { "epoch": 0.4211553999461352, "grad_norm": 0.7086020716956808, "learning_rate": 8.94553159046132e-06, "loss": 0.3767553806304932, "num_input_tokens_seen": 257757176, "step": 6255, "train_runtime": 24171.3461, "train_tokens_per_second": 10663.749 }, { "epoch": 0.42149205494209535, "grad_norm": 0.6568368054182543, "learning_rate": 8.943906893841015e-06, "loss": 0.36991305351257325, "num_input_tokens_seen": 257963912, "step": 6260, "train_runtime": 24189.5307, "train_tokens_per_second": 10664.279 }, { "epoch": 0.4218287099380555, "grad_norm": 0.7452501416903502, "learning_rate": 8.942281094319721e-06, "loss": 0.4177358627319336, "num_input_tokens_seen": 258163304, "step": 6265, "train_runtime": 24207.4766, "train_tokens_per_second": 10664.61 }, { "epoch": 0.42216536493401563, "grad_norm": 0.8095973895591508, "learning_rate": 8.940654192352092e-06, "loss": 0.4024096965789795, "num_input_tokens_seen": 258360568, "step": 6270, "train_runtime": 24227.1065, "train_tokens_per_second": 10664.112 }, { "epoch": 0.42250201992997577, "grad_norm": 0.7986779569985849, "learning_rate": 8.939026188393083e-06, "loss": 0.3871390104293823, "num_input_tokens_seen": 258570488, "step": 6275, "train_runtime": 24249.1315, "train_tokens_per_second": 10663.082 }, { "epoch": 0.4228386749259359, "grad_norm": 0.8030872055955958, "learning_rate": 8.937397082897963e-06, "loss": 0.40488290786743164, "num_input_tokens_seen": 258784320, "step": 6280, "train_runtime": 24268.8983, "train_tokens_per_second": 10663.208 }, { "epoch": 0.42317532992189605, "grad_norm": 0.7550637587868557, "learning_rate": 8.935766876322303e-06, "loss": 0.4112743377685547, "num_input_tokens_seen": 258989360, "step": 6285, "train_runtime": 24287.7868, "train_tokens_per_second": 10663.358 }, { "epoch": 0.4235119849178562, "grad_norm": 0.6818701198034173, "learning_rate": 8.934135569121985e-06, "loss": 0.40695390701293943, "num_input_tokens_seen": 259201624, "step": 6290, "train_runtime": 24306.4274, "train_tokens_per_second": 10663.913 }, { "epoch": 0.4238486399138163, "grad_norm": 0.6806725331129084, "learning_rate": 8.932503161753202e-06, "loss": 0.38223919868469236, "num_input_tokens_seen": 259407936, "step": 6295, "train_runtime": 24324.7653, "train_tokens_per_second": 10664.355 }, { "epoch": 0.42418529490977647, "grad_norm": 0.7851324864739101, "learning_rate": 8.930869654672449e-06, "loss": 0.39082908630371094, "num_input_tokens_seen": 259614144, "step": 6300, "train_runtime": 24344.3504, "train_tokens_per_second": 10664.246 }, { "epoch": 0.4245219499057366, "grad_norm": 1.1390214718491039, "learning_rate": 8.929235048336531e-06, "loss": 0.3767747640609741, "num_input_tokens_seen": 259823472, "step": 6305, "train_runtime": 24363.3972, "train_tokens_per_second": 10664.501 }, { "epoch": 0.42485860490169675, "grad_norm": 0.8587854823524381, "learning_rate": 8.927599343202563e-06, "loss": 0.4195088386535645, "num_input_tokens_seen": 260037328, "step": 6310, "train_runtime": 24382.2356, "train_tokens_per_second": 10665.032 }, { "epoch": 0.4251952598976569, "grad_norm": 0.7200465055166885, "learning_rate": 8.92596253972796e-06, "loss": 0.3918612003326416, "num_input_tokens_seen": 260259992, "step": 6315, "train_runtime": 24400.154, "train_tokens_per_second": 10666.326 }, { "epoch": 0.425531914893617, "grad_norm": 0.7478806849315156, "learning_rate": 8.924324638370454e-06, "loss": 0.4184259414672852, "num_input_tokens_seen": 260473424, "step": 6320, "train_runtime": 24419.7067, "train_tokens_per_second": 10666.525 }, { "epoch": 0.42586856988957716, "grad_norm": 0.6123554641338883, "learning_rate": 8.922685639588076e-06, "loss": 0.3469987154006958, "num_input_tokens_seen": 260662888, "step": 6325, "train_runtime": 24438.0837, "train_tokens_per_second": 10666.257 }, { "epoch": 0.4262052248855373, "grad_norm": 0.8006563533550671, "learning_rate": 8.921045543839167e-06, "loss": 0.41678338050842284, "num_input_tokens_seen": 260873320, "step": 6330, "train_runtime": 24457.2776, "train_tokens_per_second": 10666.491 }, { "epoch": 0.42654187988149744, "grad_norm": 0.7563546872659579, "learning_rate": 8.919404351582376e-06, "loss": 0.378070068359375, "num_input_tokens_seen": 261071352, "step": 6335, "train_runtime": 24476.6923, "train_tokens_per_second": 10666.121 }, { "epoch": 0.4268785348774576, "grad_norm": 0.6975624735488568, "learning_rate": 8.917762063276657e-06, "loss": 0.39292106628417967, "num_input_tokens_seen": 261272856, "step": 6340, "train_runtime": 24496.6825, "train_tokens_per_second": 10665.642 }, { "epoch": 0.4272151898734177, "grad_norm": 0.6855911616015616, "learning_rate": 8.916118679381268e-06, "loss": 0.38216233253479004, "num_input_tokens_seen": 261479552, "step": 6345, "train_runtime": 24516.2115, "train_tokens_per_second": 10665.577 }, { "epoch": 0.42755184486937786, "grad_norm": 0.8091344700094257, "learning_rate": 8.914474200355777e-06, "loss": 0.39418554306030273, "num_input_tokens_seen": 261685344, "step": 6350, "train_runtime": 24535.0478, "train_tokens_per_second": 10665.777 }, { "epoch": 0.427888499865338, "grad_norm": 0.7952310023430943, "learning_rate": 8.912828626660059e-06, "loss": 0.4033997058868408, "num_input_tokens_seen": 261896912, "step": 6355, "train_runtime": 24553.5131, "train_tokens_per_second": 10666.372 }, { "epoch": 0.42822515486129814, "grad_norm": 0.7767409524657519, "learning_rate": 8.911181958754294e-06, "loss": 0.42862257957458494, "num_input_tokens_seen": 262104520, "step": 6360, "train_runtime": 24573.396, "train_tokens_per_second": 10666.19 }, { "epoch": 0.4285618098572583, "grad_norm": 0.6493236162168367, "learning_rate": 8.909534197098966e-06, "loss": 0.4073795795440674, "num_input_tokens_seen": 262318760, "step": 6365, "train_runtime": 24593.5862, "train_tokens_per_second": 10666.145 }, { "epoch": 0.4288984648532184, "grad_norm": 0.8384632023800329, "learning_rate": 8.907885342154865e-06, "loss": 0.3913240432739258, "num_input_tokens_seen": 262524512, "step": 6370, "train_runtime": 24612.3116, "train_tokens_per_second": 10666.39 }, { "epoch": 0.42923511984917856, "grad_norm": 0.7540437625604177, "learning_rate": 8.906235394383089e-06, "loss": 0.37575201988220214, "num_input_tokens_seen": 262713488, "step": 6375, "train_runtime": 24633.2296, "train_tokens_per_second": 10665.004 }, { "epoch": 0.4295717748451387, "grad_norm": 0.751125960392899, "learning_rate": 8.904584354245042e-06, "loss": 0.3811084747314453, "num_input_tokens_seen": 262920656, "step": 6380, "train_runtime": 24652.1198, "train_tokens_per_second": 10665.235 }, { "epoch": 0.42990842984109884, "grad_norm": 0.7329361020208497, "learning_rate": 8.902932222202433e-06, "loss": 0.40091724395751954, "num_input_tokens_seen": 263138920, "step": 6385, "train_runtime": 24671.0802, "train_tokens_per_second": 10665.886 }, { "epoch": 0.430245084837059, "grad_norm": 0.6573480725902906, "learning_rate": 8.901278998717272e-06, "loss": 0.38337054252624514, "num_input_tokens_seen": 263347472, "step": 6390, "train_runtime": 24688.9403, "train_tokens_per_second": 10666.617 }, { "epoch": 0.4305817398330191, "grad_norm": 0.7561736557763562, "learning_rate": 8.899624684251878e-06, "loss": 0.38008995056152345, "num_input_tokens_seen": 263552600, "step": 6395, "train_runtime": 24707.7144, "train_tokens_per_second": 10666.814 }, { "epoch": 0.43091839482897926, "grad_norm": 0.7532334553676087, "learning_rate": 8.897969279268877e-06, "loss": 0.3771694183349609, "num_input_tokens_seen": 263759032, "step": 6400, "train_runtime": 24726.8255, "train_tokens_per_second": 10666.918 }, { "epoch": 0.4312550498249394, "grad_norm": 0.676827193114439, "learning_rate": 8.896312784231196e-06, "loss": 0.37210540771484374, "num_input_tokens_seen": 263958160, "step": 6405, "train_runtime": 24746.0626, "train_tokens_per_second": 10666.673 }, { "epoch": 0.43159170482089954, "grad_norm": 0.7456053846730761, "learning_rate": 8.89465519960207e-06, "loss": 0.4289558887481689, "num_input_tokens_seen": 264171568, "step": 6410, "train_runtime": 24764.6698, "train_tokens_per_second": 10667.276 }, { "epoch": 0.4319283598168597, "grad_norm": 0.7055823976152331, "learning_rate": 8.892996525845037e-06, "loss": 0.39712331295013426, "num_input_tokens_seen": 264385872, "step": 6415, "train_runtime": 24785.7331, "train_tokens_per_second": 10666.857 }, { "epoch": 0.4322650148128198, "grad_norm": 0.8741137235816292, "learning_rate": 8.89133676342394e-06, "loss": 0.4029685974121094, "num_input_tokens_seen": 264575712, "step": 6420, "train_runtime": 24804.4316, "train_tokens_per_second": 10666.469 }, { "epoch": 0.43260166980877995, "grad_norm": 0.7682606248449878, "learning_rate": 8.889675912802923e-06, "loss": 0.3873955249786377, "num_input_tokens_seen": 264779096, "step": 6425, "train_runtime": 24824.2846, "train_tokens_per_second": 10666.132 }, { "epoch": 0.4329383248047401, "grad_norm": 0.7979536846387033, "learning_rate": 8.888013974446443e-06, "loss": 0.4157212734222412, "num_input_tokens_seen": 264988152, "step": 6430, "train_runtime": 24844.8806, "train_tokens_per_second": 10665.704 }, { "epoch": 0.43327497980070023, "grad_norm": 0.8246734002033083, "learning_rate": 8.886350948819253e-06, "loss": 0.37306511402130127, "num_input_tokens_seen": 265185104, "step": 6435, "train_runtime": 24863.5162, "train_tokens_per_second": 10665.632 }, { "epoch": 0.4336116347966604, "grad_norm": 0.729997954288094, "learning_rate": 8.884686836386412e-06, "loss": 0.3806516885757446, "num_input_tokens_seen": 265390016, "step": 6440, "train_runtime": 24883.5397, "train_tokens_per_second": 10665.284 }, { "epoch": 0.4339482897926205, "grad_norm": 0.7236830316196301, "learning_rate": 8.883021637613286e-06, "loss": 0.40662541389465334, "num_input_tokens_seen": 265601880, "step": 6445, "train_runtime": 24902.7656, "train_tokens_per_second": 10665.558 }, { "epoch": 0.43428494478858065, "grad_norm": 0.6625106873512177, "learning_rate": 8.881355352965537e-06, "loss": 0.3905913829803467, "num_input_tokens_seen": 265803432, "step": 6450, "train_runtime": 24920.8583, "train_tokens_per_second": 10665.902 }, { "epoch": 0.4346215997845408, "grad_norm": 0.6892549822642658, "learning_rate": 8.879687982909145e-06, "loss": 0.3543532371520996, "num_input_tokens_seen": 265995472, "step": 6455, "train_runtime": 24940.5069, "train_tokens_per_second": 10665.199 }, { "epoch": 0.43495825478050093, "grad_norm": 0.8638254243874408, "learning_rate": 8.878019527910378e-06, "loss": 0.41061110496520997, "num_input_tokens_seen": 266188192, "step": 6460, "train_runtime": 24959.8456, "train_tokens_per_second": 10664.657 }, { "epoch": 0.43529490977646107, "grad_norm": 0.7989770958023761, "learning_rate": 8.876349988435815e-06, "loss": 0.45392599105834963, "num_input_tokens_seen": 266394392, "step": 6465, "train_runtime": 24978.5639, "train_tokens_per_second": 10664.92 }, { "epoch": 0.4356315647724212, "grad_norm": 0.6259838195179974, "learning_rate": 8.874679364952339e-06, "loss": 0.39786198139190676, "num_input_tokens_seen": 266617720, "step": 6470, "train_runtime": 24998.8192, "train_tokens_per_second": 10665.213 }, { "epoch": 0.43596821976838135, "grad_norm": 0.6789155902615903, "learning_rate": 8.873007657927135e-06, "loss": 0.3894918918609619, "num_input_tokens_seen": 266832704, "step": 6475, "train_runtime": 25018.7217, "train_tokens_per_second": 10665.321 }, { "epoch": 0.4363048747643415, "grad_norm": 0.6656484146740906, "learning_rate": 8.87133486782769e-06, "loss": 0.36257209777832033, "num_input_tokens_seen": 267022440, "step": 6480, "train_runtime": 25037.0653, "train_tokens_per_second": 10665.085 }, { "epoch": 0.4366415297603016, "grad_norm": 0.663968776493667, "learning_rate": 8.869660995121792e-06, "loss": 0.4060776710510254, "num_input_tokens_seen": 267228672, "step": 6485, "train_runtime": 25055.0433, "train_tokens_per_second": 10665.664 }, { "epoch": 0.43697818475626177, "grad_norm": 0.7141604703179091, "learning_rate": 8.867986040277537e-06, "loss": 0.4061444282531738, "num_input_tokens_seen": 267426024, "step": 6490, "train_runtime": 25073.3639, "train_tokens_per_second": 10665.742 }, { "epoch": 0.4373148397522219, "grad_norm": 0.730779869120202, "learning_rate": 8.86631000376332e-06, "loss": 0.4117245674133301, "num_input_tokens_seen": 267622384, "step": 6495, "train_runtime": 25091.9015, "train_tokens_per_second": 10665.688 }, { "epoch": 0.43765149474818205, "grad_norm": 0.7106983090134252, "learning_rate": 8.864632886047841e-06, "loss": 0.37832963466644287, "num_input_tokens_seen": 267823272, "step": 6500, "train_runtime": 25111.4355, "train_tokens_per_second": 10665.391 }, { "epoch": 0.4379881497441422, "grad_norm": 0.9265226166892354, "learning_rate": 8.862954687600097e-06, "loss": 0.4244832992553711, "num_input_tokens_seen": 268024376, "step": 6505, "train_runtime": 25131.7193, "train_tokens_per_second": 10664.785 }, { "epoch": 0.4383248047401023, "grad_norm": 0.7921892694585815, "learning_rate": 8.861275408889393e-06, "loss": 0.4067218780517578, "num_input_tokens_seen": 268221752, "step": 6510, "train_runtime": 25151.1527, "train_tokens_per_second": 10664.392 }, { "epoch": 0.43866145973606246, "grad_norm": 0.7845721807093844, "learning_rate": 8.859595050385332e-06, "loss": 0.40453424453735354, "num_input_tokens_seen": 268431776, "step": 6515, "train_runtime": 25170.3996, "train_tokens_per_second": 10664.581 }, { "epoch": 0.4389981147320226, "grad_norm": 0.7474489376630539, "learning_rate": 8.857913612557825e-06, "loss": 0.3959219455718994, "num_input_tokens_seen": 268642736, "step": 6520, "train_runtime": 25189.5652, "train_tokens_per_second": 10664.842 }, { "epoch": 0.43933476972798274, "grad_norm": 0.8308628143268244, "learning_rate": 8.856231095877077e-06, "loss": 0.3726328134536743, "num_input_tokens_seen": 268839536, "step": 6525, "train_runtime": 25209.7509, "train_tokens_per_second": 10664.109 }, { "epoch": 0.4396714247239429, "grad_norm": 0.6725620193911716, "learning_rate": 8.8545475008136e-06, "loss": 0.37138869762420657, "num_input_tokens_seen": 269050968, "step": 6530, "train_runtime": 25228.954, "train_tokens_per_second": 10664.373 }, { "epoch": 0.440008079719903, "grad_norm": 0.7821046377092643, "learning_rate": 8.852862827838207e-06, "loss": 0.3786689519882202, "num_input_tokens_seen": 269247064, "step": 6535, "train_runtime": 25248.2141, "train_tokens_per_second": 10664.004 }, { "epoch": 0.44034473471586316, "grad_norm": 0.6690622475897057, "learning_rate": 8.851177077422008e-06, "loss": 0.40105204582214354, "num_input_tokens_seen": 269463400, "step": 6540, "train_runtime": 25266.9241, "train_tokens_per_second": 10664.67 }, { "epoch": 0.4406813897118233, "grad_norm": 0.7456784776361132, "learning_rate": 8.849490250036421e-06, "loss": 0.42618522644042967, "num_input_tokens_seen": 269665736, "step": 6545, "train_runtime": 25285.6743, "train_tokens_per_second": 10664.763 }, { "epoch": 0.44101804470778344, "grad_norm": 0.8791550535029015, "learning_rate": 8.847802346153159e-06, "loss": 0.3829249143600464, "num_input_tokens_seen": 269866840, "step": 6550, "train_runtime": 25304.2711, "train_tokens_per_second": 10664.873 }, { "epoch": 0.4413546997037436, "grad_norm": 0.7250515088048787, "learning_rate": 8.846113366244241e-06, "loss": 0.4059779167175293, "num_input_tokens_seen": 270076464, "step": 6555, "train_runtime": 25322.3353, "train_tokens_per_second": 10665.543 }, { "epoch": 0.4416913546997037, "grad_norm": 0.7362862125018538, "learning_rate": 8.844423310781986e-06, "loss": 0.36601767539978025, "num_input_tokens_seen": 270283136, "step": 6560, "train_runtime": 25342.2179, "train_tokens_per_second": 10665.331 }, { "epoch": 0.44202800969566386, "grad_norm": 0.7900734625525029, "learning_rate": 8.842732180239011e-06, "loss": 0.4233404636383057, "num_input_tokens_seen": 270487832, "step": 6565, "train_runtime": 25363.0814, "train_tokens_per_second": 10664.628 }, { "epoch": 0.442364664691624, "grad_norm": 0.7381045051016839, "learning_rate": 8.841039975088234e-06, "loss": 0.3837776184082031, "num_input_tokens_seen": 270692584, "step": 6570, "train_runtime": 25383.4984, "train_tokens_per_second": 10664.116 }, { "epoch": 0.44270131968758414, "grad_norm": 0.748454400697105, "learning_rate": 8.839346695802878e-06, "loss": 0.4537996768951416, "num_input_tokens_seen": 270907232, "step": 6575, "train_runtime": 25403.3615, "train_tokens_per_second": 10664.228 }, { "epoch": 0.4430379746835443, "grad_norm": 0.6369661418382075, "learning_rate": 8.837652342856459e-06, "loss": 0.40617942810058594, "num_input_tokens_seen": 271116304, "step": 6580, "train_runtime": 25422.232, "train_tokens_per_second": 10664.536 }, { "epoch": 0.4433746296795044, "grad_norm": 0.685039508356547, "learning_rate": 8.835956916722803e-06, "loss": 0.3647735357284546, "num_input_tokens_seen": 271323408, "step": 6585, "train_runtime": 25442.7629, "train_tokens_per_second": 10664.07 }, { "epoch": 0.44371128467546456, "grad_norm": 0.7208975955125394, "learning_rate": 8.834260417876024e-06, "loss": 0.39628100395202637, "num_input_tokens_seen": 271525000, "step": 6590, "train_runtime": 25461.6123, "train_tokens_per_second": 10664.093 }, { "epoch": 0.4440479396714247, "grad_norm": 0.718600374512291, "learning_rate": 8.832562846790549e-06, "loss": 0.4130753517150879, "num_input_tokens_seen": 271735376, "step": 6595, "train_runtime": 25480.616, "train_tokens_per_second": 10664.396 }, { "epoch": 0.4443845946673849, "grad_norm": 0.7215180507536648, "learning_rate": 8.830864203941092e-06, "loss": 0.41234140396118163, "num_input_tokens_seen": 271942864, "step": 6600, "train_runtime": 25500.7371, "train_tokens_per_second": 10664.118 }, { "epoch": 0.44472124966334503, "grad_norm": 0.7531246333961068, "learning_rate": 8.829164489802677e-06, "loss": 0.38051295280456543, "num_input_tokens_seen": 272141896, "step": 6605, "train_runtime": 25518.6285, "train_tokens_per_second": 10664.441 }, { "epoch": 0.44505790465930517, "grad_norm": 0.7790295304864562, "learning_rate": 8.827463704850622e-06, "loss": 0.3856348991394043, "num_input_tokens_seen": 272346360, "step": 6610, "train_runtime": 25537.3261, "train_tokens_per_second": 10664.639 }, { "epoch": 0.4453945596552653, "grad_norm": 0.8881154591582695, "learning_rate": 8.825761849560547e-06, "loss": 0.37786388397216797, "num_input_tokens_seen": 272549456, "step": 6615, "train_runtime": 25556.7484, "train_tokens_per_second": 10664.481 }, { "epoch": 0.44573121465122545, "grad_norm": 0.8670156886591105, "learning_rate": 8.824058924408371e-06, "loss": 0.39339773654937743, "num_input_tokens_seen": 272754048, "step": 6620, "train_runtime": 25577.5488, "train_tokens_per_second": 10663.807 }, { "epoch": 0.4460678696471856, "grad_norm": 0.631127458466543, "learning_rate": 8.822354929870311e-06, "loss": 0.3674155712127686, "num_input_tokens_seen": 272956608, "step": 6625, "train_runtime": 25597.1164, "train_tokens_per_second": 10663.569 }, { "epoch": 0.44640452464314573, "grad_norm": 0.6285487369889892, "learning_rate": 8.820649866422884e-06, "loss": 0.39181976318359374, "num_input_tokens_seen": 273167464, "step": 6630, "train_runtime": 25615.7984, "train_tokens_per_second": 10664.023 }, { "epoch": 0.44674117963910587, "grad_norm": 0.6864142553411525, "learning_rate": 8.818943734542905e-06, "loss": 0.38042147159576417, "num_input_tokens_seen": 273380688, "step": 6635, "train_runtime": 25633.7092, "train_tokens_per_second": 10664.89 }, { "epoch": 0.447077834635066, "grad_norm": 0.7253469228081055, "learning_rate": 8.817236534707486e-06, "loss": 0.39186227321624756, "num_input_tokens_seen": 273588352, "step": 6640, "train_runtime": 25654.1064, "train_tokens_per_second": 10664.505 }, { "epoch": 0.44741448963102615, "grad_norm": 0.7940768074216425, "learning_rate": 8.815528267394045e-06, "loss": 0.385449743270874, "num_input_tokens_seen": 273797752, "step": 6645, "train_runtime": 25675.5002, "train_tokens_per_second": 10663.775 }, { "epoch": 0.4477511446269863, "grad_norm": 0.7808362991653258, "learning_rate": 8.81381893308029e-06, "loss": 0.42250308990478513, "num_input_tokens_seen": 274009200, "step": 6650, "train_runtime": 25694.8051, "train_tokens_per_second": 10663.992 }, { "epoch": 0.4480877996229464, "grad_norm": 0.6854745197611725, "learning_rate": 8.81210853224423e-06, "loss": 0.40427255630493164, "num_input_tokens_seen": 274213792, "step": 6655, "train_runtime": 25714.0961, "train_tokens_per_second": 10663.948 }, { "epoch": 0.44842445461890656, "grad_norm": 0.7627149846935665, "learning_rate": 8.810397065364177e-06, "loss": 0.3677982807159424, "num_input_tokens_seen": 274408744, "step": 6660, "train_runtime": 25735.5771, "train_tokens_per_second": 10662.623 }, { "epoch": 0.4487611096148667, "grad_norm": 0.6820700329953205, "learning_rate": 8.808684532918735e-06, "loss": 0.4055652618408203, "num_input_tokens_seen": 274613056, "step": 6665, "train_runtime": 25755.0924, "train_tokens_per_second": 10662.476 }, { "epoch": 0.44909776461082684, "grad_norm": 0.8137042674467689, "learning_rate": 8.806970935386807e-06, "loss": 0.37290205955505373, "num_input_tokens_seen": 274811800, "step": 6670, "train_runtime": 25774.5331, "train_tokens_per_second": 10662.145 }, { "epoch": 0.449434419606787, "grad_norm": 0.7621877826743075, "learning_rate": 8.805256273247597e-06, "loss": 0.38497703075408934, "num_input_tokens_seen": 275013984, "step": 6675, "train_runtime": 25794.546, "train_tokens_per_second": 10661.711 }, { "epoch": 0.4497710746027471, "grad_norm": 0.8333071073803905, "learning_rate": 8.803540546980605e-06, "loss": 0.39663009643554686, "num_input_tokens_seen": 275212872, "step": 6680, "train_runtime": 25813.1362, "train_tokens_per_second": 10661.737 }, { "epoch": 0.45010772959870726, "grad_norm": 0.689149436818342, "learning_rate": 8.801823757065628e-06, "loss": 0.393865180015564, "num_input_tokens_seen": 275417376, "step": 6685, "train_runtime": 25832.3706, "train_tokens_per_second": 10661.715 }, { "epoch": 0.4504443845946674, "grad_norm": 0.6807948157373249, "learning_rate": 8.800105903982758e-06, "loss": 0.37335519790649413, "num_input_tokens_seen": 275616248, "step": 6690, "train_runtime": 25849.735, "train_tokens_per_second": 10662.247 }, { "epoch": 0.45078103959062754, "grad_norm": 0.9009329132079877, "learning_rate": 8.798386988212393e-06, "loss": 0.3663817882537842, "num_input_tokens_seen": 275804368, "step": 6695, "train_runtime": 25869.6016, "train_tokens_per_second": 10661.33 }, { "epoch": 0.4511176945865877, "grad_norm": 0.7087526413680615, "learning_rate": 8.796667010235216e-06, "loss": 0.4093910217285156, "num_input_tokens_seen": 276012888, "step": 6700, "train_runtime": 25888.928, "train_tokens_per_second": 10661.426 }, { "epoch": 0.4514543495825478, "grad_norm": 0.7040257923929322, "learning_rate": 8.794945970532219e-06, "loss": 0.38848114013671875, "num_input_tokens_seen": 276225056, "step": 6705, "train_runtime": 25910.4404, "train_tokens_per_second": 10660.763 }, { "epoch": 0.45179100457850796, "grad_norm": 0.7799156406592511, "learning_rate": 8.79322386958468e-06, "loss": 0.4247751235961914, "num_input_tokens_seen": 276435992, "step": 6710, "train_runtime": 25928.6134, "train_tokens_per_second": 10661.426 }, { "epoch": 0.4521276595744681, "grad_norm": 0.7741512849005517, "learning_rate": 8.791500707874183e-06, "loss": 0.361043906211853, "num_input_tokens_seen": 276638192, "step": 6715, "train_runtime": 25948.3183, "train_tokens_per_second": 10661.122 }, { "epoch": 0.45246431457042824, "grad_norm": 0.6729090706148669, "learning_rate": 8.789776485882601e-06, "loss": 0.4056418418884277, "num_input_tokens_seen": 276851184, "step": 6720, "train_runtime": 25967.0615, "train_tokens_per_second": 10661.629 }, { "epoch": 0.4528009695663884, "grad_norm": 0.7811664998965051, "learning_rate": 8.788051204092112e-06, "loss": 0.38480343818664553, "num_input_tokens_seen": 277059320, "step": 6725, "train_runtime": 25985.9834, "train_tokens_per_second": 10661.876 }, { "epoch": 0.4531376245623485, "grad_norm": 0.8050911069290759, "learning_rate": 8.786324862985183e-06, "loss": 0.39441580772399903, "num_input_tokens_seen": 277260496, "step": 6730, "train_runtime": 26005.4597, "train_tokens_per_second": 10661.626 }, { "epoch": 0.45347427955830866, "grad_norm": 0.7368645422866216, "learning_rate": 8.78459746304458e-06, "loss": 0.3687868356704712, "num_input_tokens_seen": 277435216, "step": 6735, "train_runtime": 26024.74, "train_tokens_per_second": 10660.441 }, { "epoch": 0.4538109345542688, "grad_norm": 0.7875681350684139, "learning_rate": 8.782869004753363e-06, "loss": 0.4024641990661621, "num_input_tokens_seen": 277638184, "step": 6740, "train_runtime": 26043.9514, "train_tokens_per_second": 10660.371 }, { "epoch": 0.45414758955022894, "grad_norm": 0.7167286530615599, "learning_rate": 8.781139488594892e-06, "loss": 0.39694573879241946, "num_input_tokens_seen": 277847144, "step": 6745, "train_runtime": 26062.6902, "train_tokens_per_second": 10660.724 }, { "epoch": 0.4544842445461891, "grad_norm": 0.6942935052140726, "learning_rate": 8.779408915052821e-06, "loss": 0.3582333564758301, "num_input_tokens_seen": 278053432, "step": 6750, "train_runtime": 26082.7331, "train_tokens_per_second": 10660.441 }, { "epoch": 0.4548208995421492, "grad_norm": 0.8243801076962107, "learning_rate": 8.777677284611096e-06, "loss": 0.36185708045959475, "num_input_tokens_seen": 278238176, "step": 6755, "train_runtime": 26101.8847, "train_tokens_per_second": 10659.697 }, { "epoch": 0.45515755453810935, "grad_norm": 0.7520780103619741, "learning_rate": 8.775944597753969e-06, "loss": 0.38496904373168944, "num_input_tokens_seen": 278433904, "step": 6760, "train_runtime": 26119.8232, "train_tokens_per_second": 10659.869 }, { "epoch": 0.4554942095340695, "grad_norm": 0.6912704026819496, "learning_rate": 8.774210854965972e-06, "loss": 0.4058850765228271, "num_input_tokens_seen": 278642160, "step": 6765, "train_runtime": 26137.9992, "train_tokens_per_second": 10660.424 }, { "epoch": 0.45583086453002963, "grad_norm": 0.7486245163854477, "learning_rate": 8.772476056731946e-06, "loss": 0.36036376953125, "num_input_tokens_seen": 278856544, "step": 6770, "train_runtime": 26156.6759, "train_tokens_per_second": 10661.008 }, { "epoch": 0.4561675195259898, "grad_norm": 0.6697080675450451, "learning_rate": 8.77074020353702e-06, "loss": 0.3679489612579346, "num_input_tokens_seen": 279056496, "step": 6775, "train_runtime": 26175.8975, "train_tokens_per_second": 10660.819 }, { "epoch": 0.4565041745219499, "grad_norm": 0.8340587771558728, "learning_rate": 8.76900329586662e-06, "loss": 0.415862512588501, "num_input_tokens_seen": 279264264, "step": 6780, "train_runtime": 26196.1508, "train_tokens_per_second": 10660.508 }, { "epoch": 0.45684082951791005, "grad_norm": 0.7289351999895255, "learning_rate": 8.767265334206467e-06, "loss": 0.3840612888336182, "num_input_tokens_seen": 279473264, "step": 6785, "train_runtime": 26214.8236, "train_tokens_per_second": 10660.887 }, { "epoch": 0.4571774845138702, "grad_norm": 0.6992774885146441, "learning_rate": 8.765526319042577e-06, "loss": 0.38797175884246826, "num_input_tokens_seen": 279680584, "step": 6790, "train_runtime": 26232.8088, "train_tokens_per_second": 10661.481 }, { "epoch": 0.45751413950983033, "grad_norm": 0.7688040138007165, "learning_rate": 8.763786250861258e-06, "loss": 0.35965375900268554, "num_input_tokens_seen": 279893528, "step": 6795, "train_runtime": 26252.406, "train_tokens_per_second": 10661.633 }, { "epoch": 0.45785079450579047, "grad_norm": 0.7255619341832039, "learning_rate": 8.762045130149114e-06, "loss": 0.3762292146682739, "num_input_tokens_seen": 280106624, "step": 6800, "train_runtime": 26272.2954, "train_tokens_per_second": 10661.673 }, { "epoch": 0.4581874495017506, "grad_norm": 0.6897922703454104, "learning_rate": 8.76030295739305e-06, "loss": 0.3962437629699707, "num_input_tokens_seen": 280320440, "step": 6805, "train_runtime": 26290.8554, "train_tokens_per_second": 10662.279 }, { "epoch": 0.45852410449771075, "grad_norm": 0.7126629144845197, "learning_rate": 8.758559733080252e-06, "loss": 0.40538625717163085, "num_input_tokens_seen": 280528376, "step": 6810, "train_runtime": 26309.3043, "train_tokens_per_second": 10662.706 }, { "epoch": 0.4588607594936709, "grad_norm": 0.6927334489882626, "learning_rate": 8.75681545769821e-06, "loss": 0.38998165130615237, "num_input_tokens_seen": 280745320, "step": 6815, "train_runtime": 26327.7987, "train_tokens_per_second": 10663.456 }, { "epoch": 0.45919741448963103, "grad_norm": 0.7822861173974317, "learning_rate": 8.755070131734706e-06, "loss": 0.3879373788833618, "num_input_tokens_seen": 280947704, "step": 6820, "train_runtime": 26347.7136, "train_tokens_per_second": 10663.077 }, { "epoch": 0.45953406948559117, "grad_norm": 0.9533587303077605, "learning_rate": 8.753323755677812e-06, "loss": 0.40569276809692384, "num_input_tokens_seen": 281150808, "step": 6825, "train_runtime": 26369.0841, "train_tokens_per_second": 10662.138 }, { "epoch": 0.4598707244815513, "grad_norm": 0.7378883761778124, "learning_rate": 8.7515763300159e-06, "loss": 0.3493526458740234, "num_input_tokens_seen": 281353712, "step": 6830, "train_runtime": 26389.5251, "train_tokens_per_second": 10661.568 }, { "epoch": 0.46020737947751145, "grad_norm": 0.6790782641158689, "learning_rate": 8.74982785523763e-06, "loss": 0.4037109375, "num_input_tokens_seen": 281564096, "step": 6835, "train_runtime": 26408.2381, "train_tokens_per_second": 10661.98 }, { "epoch": 0.4605440344734716, "grad_norm": 0.6687102924751948, "learning_rate": 8.748078331831957e-06, "loss": 0.39697625637054446, "num_input_tokens_seen": 281777488, "step": 6840, "train_runtime": 26427.9038, "train_tokens_per_second": 10662.12 }, { "epoch": 0.4608806894694317, "grad_norm": 0.6989760094342694, "learning_rate": 8.746327760288129e-06, "loss": 0.3870044231414795, "num_input_tokens_seen": 281997064, "step": 6845, "train_runtime": 26446.3507, "train_tokens_per_second": 10662.986 }, { "epoch": 0.46121734446539187, "grad_norm": 0.8071169937526268, "learning_rate": 8.744576141095691e-06, "loss": 0.40034985542297363, "num_input_tokens_seen": 282192448, "step": 6850, "train_runtime": 26465.8796, "train_tokens_per_second": 10662.5 }, { "epoch": 0.461553999461352, "grad_norm": 0.7613321128467657, "learning_rate": 8.742823474744476e-06, "loss": 0.3994886875152588, "num_input_tokens_seen": 282391936, "step": 6855, "train_runtime": 26485.544, "train_tokens_per_second": 10662.116 }, { "epoch": 0.46189065445731214, "grad_norm": 0.6923480346927173, "learning_rate": 8.74106976172461e-06, "loss": 0.4052131175994873, "num_input_tokens_seen": 282602896, "step": 6860, "train_runtime": 26506.0828, "train_tokens_per_second": 10661.813 }, { "epoch": 0.4622273094532723, "grad_norm": 0.8282448400659573, "learning_rate": 8.739315002526513e-06, "loss": 0.4011868476867676, "num_input_tokens_seen": 282806040, "step": 6865, "train_runtime": 26525.0729, "train_tokens_per_second": 10661.838 }, { "epoch": 0.4625639644492324, "grad_norm": 0.6861717744493431, "learning_rate": 8.737559197640902e-06, "loss": 0.37395281791687013, "num_input_tokens_seen": 283005312, "step": 6870, "train_runtime": 26544.3512, "train_tokens_per_second": 10661.602 }, { "epoch": 0.46290061944519256, "grad_norm": 1.0194511771913424, "learning_rate": 8.735802347558778e-06, "loss": 0.4085562229156494, "num_input_tokens_seen": 283206344, "step": 6875, "train_runtime": 26563.5221, "train_tokens_per_second": 10661.476 }, { "epoch": 0.4632372744411527, "grad_norm": 0.713270627653609, "learning_rate": 8.734044452771442e-06, "loss": 0.3875460147857666, "num_input_tokens_seen": 283404584, "step": 6880, "train_runtime": 26583.6796, "train_tokens_per_second": 10660.849 }, { "epoch": 0.46357392943711284, "grad_norm": 0.8056880164750039, "learning_rate": 8.73228551377048e-06, "loss": 0.412307071685791, "num_input_tokens_seen": 283612240, "step": 6885, "train_runtime": 26601.0393, "train_tokens_per_second": 10661.698 }, { "epoch": 0.463910584433073, "grad_norm": 0.687746539825467, "learning_rate": 8.730525531047776e-06, "loss": 0.4153013229370117, "num_input_tokens_seen": 283821840, "step": 6890, "train_runtime": 26620.8466, "train_tokens_per_second": 10661.638 }, { "epoch": 0.4642472394290331, "grad_norm": 0.6984973714974457, "learning_rate": 8.728764505095503e-06, "loss": 0.4113753318786621, "num_input_tokens_seen": 284033152, "step": 6895, "train_runtime": 26639.5466, "train_tokens_per_second": 10662.087 }, { "epoch": 0.46458389442499326, "grad_norm": 0.6048990085737126, "learning_rate": 8.727002436406126e-06, "loss": 0.37281510829925535, "num_input_tokens_seen": 284252192, "step": 6900, "train_runtime": 26657.7297, "train_tokens_per_second": 10663.031 }, { "epoch": 0.4649205494209534, "grad_norm": 0.725176219561051, "learning_rate": 8.725239325472404e-06, "loss": 0.41089940071105957, "num_input_tokens_seen": 284462808, "step": 6905, "train_runtime": 26678.1706, "train_tokens_per_second": 10662.755 }, { "epoch": 0.46525720441691354, "grad_norm": 0.7497410076507837, "learning_rate": 8.723475172787381e-06, "loss": 0.39655003547668455, "num_input_tokens_seen": 284673872, "step": 6910, "train_runtime": 26698.1394, "train_tokens_per_second": 10662.686 }, { "epoch": 0.4655938594128737, "grad_norm": 0.8795492080526576, "learning_rate": 8.7217099788444e-06, "loss": 0.3912800788879395, "num_input_tokens_seen": 284876288, "step": 6915, "train_runtime": 26717.3066, "train_tokens_per_second": 10662.613 }, { "epoch": 0.4659305144088338, "grad_norm": 0.7177003510147831, "learning_rate": 8.719943744137091e-06, "loss": 0.3905658721923828, "num_input_tokens_seen": 285087208, "step": 6920, "train_runtime": 26739.4469, "train_tokens_per_second": 10661.672 }, { "epoch": 0.46626716940479396, "grad_norm": 0.7071299262958782, "learning_rate": 8.718176469159378e-06, "loss": 0.3980704784393311, "num_input_tokens_seen": 285308552, "step": 6925, "train_runtime": 26757.0272, "train_tokens_per_second": 10662.939 }, { "epoch": 0.4666038244007541, "grad_norm": 0.6960223382549365, "learning_rate": 8.716408154405469e-06, "loss": 0.3806361198425293, "num_input_tokens_seen": 285518560, "step": 6930, "train_runtime": 26775.2687, "train_tokens_per_second": 10663.518 }, { "epoch": 0.46694047939671424, "grad_norm": 0.8550355594128742, "learning_rate": 8.714638800369872e-06, "loss": 0.4211139678955078, "num_input_tokens_seen": 285710360, "step": 6935, "train_runtime": 26793.0459, "train_tokens_per_second": 10663.601 }, { "epoch": 0.4672771343926744, "grad_norm": 0.6463675238366596, "learning_rate": 8.712868407547378e-06, "loss": 0.41929235458374026, "num_input_tokens_seen": 285924192, "step": 6940, "train_runtime": 26810.5778, "train_tokens_per_second": 10664.604 }, { "epoch": 0.4676137893886345, "grad_norm": 0.8398503780353201, "learning_rate": 8.711096976433076e-06, "loss": 0.40418300628662107, "num_input_tokens_seen": 286137704, "step": 6945, "train_runtime": 26829.8752, "train_tokens_per_second": 10664.891 }, { "epoch": 0.46795044438459465, "grad_norm": 0.7187611278040464, "learning_rate": 8.709324507522337e-06, "loss": 0.35797929763793945, "num_input_tokens_seen": 286344616, "step": 6950, "train_runtime": 26848.3786, "train_tokens_per_second": 10665.248 }, { "epoch": 0.4682870993805548, "grad_norm": 0.7244947186380477, "learning_rate": 8.707551001310828e-06, "loss": 0.37493133544921875, "num_input_tokens_seen": 286558824, "step": 6955, "train_runtime": 26869.2812, "train_tokens_per_second": 10664.923 }, { "epoch": 0.46862375437651493, "grad_norm": 0.6946025464278553, "learning_rate": 8.705776458294503e-06, "loss": 0.3903285026550293, "num_input_tokens_seen": 286755880, "step": 6960, "train_runtime": 26887.0627, "train_tokens_per_second": 10665.199 }, { "epoch": 0.4689604093724751, "grad_norm": 0.6691042935409561, "learning_rate": 8.704000878969608e-06, "loss": 0.37240564823150635, "num_input_tokens_seen": 286952536, "step": 6965, "train_runtime": 26905.4405, "train_tokens_per_second": 10665.224 }, { "epoch": 0.4692970643684352, "grad_norm": 0.6843065278156061, "learning_rate": 8.702224263832679e-06, "loss": 0.37013492584228513, "num_input_tokens_seen": 287166648, "step": 6970, "train_runtime": 26924.3151, "train_tokens_per_second": 10665.699 }, { "epoch": 0.46963371936439535, "grad_norm": 0.7015496721701158, "learning_rate": 8.700446613380542e-06, "loss": 0.42146711349487304, "num_input_tokens_seen": 287380056, "step": 6975, "train_runtime": 26944.0638, "train_tokens_per_second": 10665.802 }, { "epoch": 0.4699703743603555, "grad_norm": 0.7081519726802035, "learning_rate": 8.698667928110307e-06, "loss": 0.3745051145553589, "num_input_tokens_seen": 287588992, "step": 6980, "train_runtime": 26964.2256, "train_tokens_per_second": 10665.576 }, { "epoch": 0.47030702935631563, "grad_norm": 0.8659637969874657, "learning_rate": 8.696888208519381e-06, "loss": 0.3943177700042725, "num_input_tokens_seen": 287788872, "step": 6985, "train_runtime": 26983.4151, "train_tokens_per_second": 10665.398 }, { "epoch": 0.47064368435227577, "grad_norm": 0.7067692980051228, "learning_rate": 8.695107455105454e-06, "loss": 0.35477266311645506, "num_input_tokens_seen": 287985176, "step": 6990, "train_runtime": 27000.1758, "train_tokens_per_second": 10666.048 }, { "epoch": 0.4709803393482359, "grad_norm": 0.6480340021251182, "learning_rate": 8.693325668366513e-06, "loss": 0.38688862323760986, "num_input_tokens_seen": 288186488, "step": 6995, "train_runtime": 27019.9636, "train_tokens_per_second": 10665.688 }, { "epoch": 0.47131699434419605, "grad_norm": 0.7949683084959556, "learning_rate": 8.691542848800825e-06, "loss": 0.3983886241912842, "num_input_tokens_seen": 288385528, "step": 7000, "train_runtime": 27040.1019, "train_tokens_per_second": 10665.105 }, { "epoch": 0.4716536493401562, "grad_norm": 0.8423938390627581, "learning_rate": 8.68975899690695e-06, "loss": 0.38346519470214846, "num_input_tokens_seen": 288597320, "step": 7005, "train_runtime": 27060.076, "train_tokens_per_second": 10665.059 }, { "epoch": 0.47199030433611633, "grad_norm": 0.6978624905045666, "learning_rate": 8.687974113183738e-06, "loss": 0.3840068817138672, "num_input_tokens_seen": 288811616, "step": 7010, "train_runtime": 27079.6155, "train_tokens_per_second": 10665.278 }, { "epoch": 0.47232695933207647, "grad_norm": 0.7792665948007668, "learning_rate": 8.686188198130326e-06, "loss": 0.3912602424621582, "num_input_tokens_seen": 289020760, "step": 7015, "train_runtime": 27098.3349, "train_tokens_per_second": 10665.628 }, { "epoch": 0.4726636143280366, "grad_norm": 0.6617956272333051, "learning_rate": 8.684401252246138e-06, "loss": 0.39978790283203125, "num_input_tokens_seen": 289232552, "step": 7020, "train_runtime": 27118.9037, "train_tokens_per_second": 10665.348 }, { "epoch": 0.47300026932399675, "grad_norm": 0.739189850902136, "learning_rate": 8.68261327603089e-06, "loss": 0.4253434181213379, "num_input_tokens_seen": 289433240, "step": 7025, "train_runtime": 27139.4025, "train_tokens_per_second": 10664.687 }, { "epoch": 0.4733369243199569, "grad_norm": 0.7471524842480041, "learning_rate": 8.68082426998458e-06, "loss": 0.4229531764984131, "num_input_tokens_seen": 289650200, "step": 7030, "train_runtime": 27160.6383, "train_tokens_per_second": 10664.337 }, { "epoch": 0.473673579315917, "grad_norm": 0.757710051570957, "learning_rate": 8.6790342346075e-06, "loss": 0.3575979471206665, "num_input_tokens_seen": 289841240, "step": 7035, "train_runtime": 27180.5802, "train_tokens_per_second": 10663.541 }, { "epoch": 0.47401023431187717, "grad_norm": 0.6888377969878955, "learning_rate": 8.677243170400228e-06, "loss": 0.38321700096130373, "num_input_tokens_seen": 290036992, "step": 7040, "train_runtime": 27200.063, "train_tokens_per_second": 10663.1 }, { "epoch": 0.4743468893078373, "grad_norm": 0.775567848088653, "learning_rate": 8.675451077863632e-06, "loss": 0.40198659896850586, "num_input_tokens_seen": 290239184, "step": 7045, "train_runtime": 27218.4386, "train_tokens_per_second": 10663.33 }, { "epoch": 0.47468354430379744, "grad_norm": 1.0667819317767222, "learning_rate": 8.67365795749886e-06, "loss": 0.3805910348892212, "num_input_tokens_seen": 290440920, "step": 7050, "train_runtime": 27238.0951, "train_tokens_per_second": 10663.041 }, { "epoch": 0.4750201992997576, "grad_norm": 0.646456006720448, "learning_rate": 8.671863809807355e-06, "loss": 0.36270871162414553, "num_input_tokens_seen": 290635200, "step": 7055, "train_runtime": 27256.319, "train_tokens_per_second": 10663.039 }, { "epoch": 0.4753568542957177, "grad_norm": 0.7267349595863981, "learning_rate": 8.670068635290844e-06, "loss": 0.3800172805786133, "num_input_tokens_seen": 290839544, "step": 7060, "train_runtime": 27276.2224, "train_tokens_per_second": 10662.75 }, { "epoch": 0.47569350929167786, "grad_norm": 0.779681625772798, "learning_rate": 8.668272434451343e-06, "loss": 0.35762510299682615, "num_input_tokens_seen": 291046616, "step": 7065, "train_runtime": 27294.3676, "train_tokens_per_second": 10663.248 }, { "epoch": 0.476030164287638, "grad_norm": 0.7283866031841609, "learning_rate": 8.666475207791154e-06, "loss": 0.40032663345336916, "num_input_tokens_seen": 291236608, "step": 7070, "train_runtime": 27312.5172, "train_tokens_per_second": 10663.119 }, { "epoch": 0.47636681928359814, "grad_norm": 0.6497668773074367, "learning_rate": 8.664676955812863e-06, "loss": 0.38009521961212156, "num_input_tokens_seen": 291446424, "step": 7075, "train_runtime": 27331.5306, "train_tokens_per_second": 10663.377 }, { "epoch": 0.4767034742795583, "grad_norm": 0.724141640289115, "learning_rate": 8.662877679019348e-06, "loss": 0.3905357360839844, "num_input_tokens_seen": 291650352, "step": 7080, "train_runtime": 27351.2455, "train_tokens_per_second": 10663.147 }, { "epoch": 0.4770401292755185, "grad_norm": 0.7269563472246506, "learning_rate": 8.66107737791377e-06, "loss": 0.40166678428649905, "num_input_tokens_seen": 291866888, "step": 7085, "train_runtime": 27370.4085, "train_tokens_per_second": 10663.593 }, { "epoch": 0.4773767842714786, "grad_norm": 0.7552869072768884, "learning_rate": 8.659276052999574e-06, "loss": 0.37063477039337156, "num_input_tokens_seen": 292058784, "step": 7090, "train_runtime": 27389.851, "train_tokens_per_second": 10663.029 }, { "epoch": 0.47771343926743876, "grad_norm": 0.8191107863715392, "learning_rate": 8.657473704780504e-06, "loss": 0.400272798538208, "num_input_tokens_seen": 292254520, "step": 7095, "train_runtime": 27407.7201, "train_tokens_per_second": 10663.219 }, { "epoch": 0.4780500942633989, "grad_norm": 0.7536588560854202, "learning_rate": 8.65567033376057e-06, "loss": 0.3849473476409912, "num_input_tokens_seen": 292467880, "step": 7100, "train_runtime": 27427.1592, "train_tokens_per_second": 10663.441 }, { "epoch": 0.47838674925935903, "grad_norm": 0.6790740385864303, "learning_rate": 8.65386594044409e-06, "loss": 0.3942903995513916, "num_input_tokens_seen": 292677976, "step": 7105, "train_runtime": 27446.9205, "train_tokens_per_second": 10663.418 }, { "epoch": 0.4787234042553192, "grad_norm": 0.8402151179315631, "learning_rate": 8.652060525335647e-06, "loss": 0.3602935552597046, "num_input_tokens_seen": 292877120, "step": 7110, "train_runtime": 27465.7779, "train_tokens_per_second": 10663.347 }, { "epoch": 0.4790600592512793, "grad_norm": 0.6221678395725733, "learning_rate": 8.650254088940125e-06, "loss": 0.3794663667678833, "num_input_tokens_seen": 293072520, "step": 7115, "train_runtime": 27483.8318, "train_tokens_per_second": 10663.452 }, { "epoch": 0.47939671424723945, "grad_norm": 0.7936891614159796, "learning_rate": 8.648446631762686e-06, "loss": 0.3886625528335571, "num_input_tokens_seen": 293264264, "step": 7120, "train_runtime": 27502.2203, "train_tokens_per_second": 10663.294 }, { "epoch": 0.4797333692431996, "grad_norm": 0.7430335471364096, "learning_rate": 8.646638154308781e-06, "loss": 0.3737387418746948, "num_input_tokens_seen": 293464928, "step": 7125, "train_runtime": 27521.2322, "train_tokens_per_second": 10663.219 }, { "epoch": 0.48007002423915973, "grad_norm": 0.6826601389599005, "learning_rate": 8.644828657084144e-06, "loss": 0.35544533729553224, "num_input_tokens_seen": 293676560, "step": 7130, "train_runtime": 27541.593, "train_tokens_per_second": 10663.02 }, { "epoch": 0.48040667923511987, "grad_norm": 0.6833440790604008, "learning_rate": 8.643018140594797e-06, "loss": 0.3566237211227417, "num_input_tokens_seen": 293876664, "step": 7135, "train_runtime": 27559.6833, "train_tokens_per_second": 10663.282 }, { "epoch": 0.48074333423108, "grad_norm": 0.6966162196527711, "learning_rate": 8.641206605347042e-06, "loss": 0.36773993968963625, "num_input_tokens_seen": 294076584, "step": 7140, "train_runtime": 27578.8872, "train_tokens_per_second": 10663.106 }, { "epoch": 0.48107998922704015, "grad_norm": 0.7416615297438482, "learning_rate": 8.639394051847472e-06, "loss": 0.38283183574676516, "num_input_tokens_seen": 294281512, "step": 7145, "train_runtime": 27598.2837, "train_tokens_per_second": 10663.037 }, { "epoch": 0.4814166442230003, "grad_norm": 0.7738280350593989, "learning_rate": 8.63758048060296e-06, "loss": 0.37618677616119384, "num_input_tokens_seen": 294485360, "step": 7150, "train_runtime": 27616.444, "train_tokens_per_second": 10663.406 }, { "epoch": 0.48175329921896043, "grad_norm": 0.7599002883606547, "learning_rate": 8.635765892120666e-06, "loss": 0.3674804449081421, "num_input_tokens_seen": 294708736, "step": 7155, "train_runtime": 27635.2578, "train_tokens_per_second": 10664.23 }, { "epoch": 0.48208995421492057, "grad_norm": 0.6300187469186969, "learning_rate": 8.633950286908032e-06, "loss": 0.3923660755157471, "num_input_tokens_seen": 294915184, "step": 7160, "train_runtime": 27654.4518, "train_tokens_per_second": 10664.293 }, { "epoch": 0.4824266092108807, "grad_norm": 0.7968243011231634, "learning_rate": 8.63213366547279e-06, "loss": 0.41269845962524415, "num_input_tokens_seen": 295110600, "step": 7165, "train_runtime": 27673.5048, "train_tokens_per_second": 10664.012 }, { "epoch": 0.48276326420684085, "grad_norm": 0.8112277269067086, "learning_rate": 8.630316028322952e-06, "loss": 0.3681860685348511, "num_input_tokens_seen": 295305968, "step": 7170, "train_runtime": 27693.7721, "train_tokens_per_second": 10663.263 }, { "epoch": 0.483099919202801, "grad_norm": 0.73196829276755, "learning_rate": 8.628497375966811e-06, "loss": 0.36719317436218263, "num_input_tokens_seen": 295526128, "step": 7175, "train_runtime": 27713.086, "train_tokens_per_second": 10663.776 }, { "epoch": 0.4834365741987611, "grad_norm": 0.707864718025213, "learning_rate": 8.62667770891295e-06, "loss": 0.4214580535888672, "num_input_tokens_seen": 295745792, "step": 7180, "train_runtime": 27733.1812, "train_tokens_per_second": 10663.969 }, { "epoch": 0.48377322919472127, "grad_norm": 0.5821808358029952, "learning_rate": 8.624857027670232e-06, "loss": 0.37439258098602296, "num_input_tokens_seen": 295959272, "step": 7185, "train_runtime": 27752.7838, "train_tokens_per_second": 10664.129 }, { "epoch": 0.4841098841906814, "grad_norm": 0.6317481761161161, "learning_rate": 8.623035332747804e-06, "loss": 0.4230562686920166, "num_input_tokens_seen": 296152736, "step": 7190, "train_runtime": 27771.4768, "train_tokens_per_second": 10663.917 }, { "epoch": 0.48444653918664154, "grad_norm": 0.7686385958174912, "learning_rate": 8.6212126246551e-06, "loss": 0.35896174907684325, "num_input_tokens_seen": 296344432, "step": 7195, "train_runtime": 27790.7235, "train_tokens_per_second": 10663.43 }, { "epoch": 0.4847831941826017, "grad_norm": 0.6768043936650747, "learning_rate": 8.619388903901833e-06, "loss": 0.39588055610656736, "num_input_tokens_seen": 296555824, "step": 7200, "train_runtime": 27809.5603, "train_tokens_per_second": 10663.808 }, { "epoch": 0.4851198491785618, "grad_norm": 0.7348171355729842, "learning_rate": 8.617564170997998e-06, "loss": 0.39182224273681643, "num_input_tokens_seen": 296767624, "step": 7205, "train_runtime": 27828.2248, "train_tokens_per_second": 10664.267 }, { "epoch": 0.48545650417452196, "grad_norm": 0.685969567558962, "learning_rate": 8.61573842645388e-06, "loss": 0.3990617752075195, "num_input_tokens_seen": 296979240, "step": 7210, "train_runtime": 27847.1159, "train_tokens_per_second": 10664.632 }, { "epoch": 0.4857931591704821, "grad_norm": 0.6784138962518141, "learning_rate": 8.61391167078004e-06, "loss": 0.3809805870056152, "num_input_tokens_seen": 297191752, "step": 7215, "train_runtime": 27867.5019, "train_tokens_per_second": 10664.456 }, { "epoch": 0.48612981416644224, "grad_norm": 0.7632226580210213, "learning_rate": 8.612083904487324e-06, "loss": 0.42757368087768555, "num_input_tokens_seen": 297396152, "step": 7220, "train_runtime": 27886.71, "train_tokens_per_second": 10664.44 }, { "epoch": 0.4864664691624024, "grad_norm": 0.7925426935221764, "learning_rate": 8.610255128086867e-06, "loss": 0.402387809753418, "num_input_tokens_seen": 297590472, "step": 7225, "train_runtime": 27905.9072, "train_tokens_per_second": 10664.067 }, { "epoch": 0.4868031241583625, "grad_norm": 0.7338900944486236, "learning_rate": 8.60842534209007e-06, "loss": 0.3608182668685913, "num_input_tokens_seen": 297798712, "step": 7230, "train_runtime": 27925.581, "train_tokens_per_second": 10664.011 }, { "epoch": 0.48713977915432266, "grad_norm": 0.6932216617703478, "learning_rate": 8.606594547008636e-06, "loss": 0.3288411617279053, "num_input_tokens_seen": 298005992, "step": 7235, "train_runtime": 27943.0682, "train_tokens_per_second": 10664.756 }, { "epoch": 0.4874764341502828, "grad_norm": 0.8356691984911649, "learning_rate": 8.604762743354536e-06, "loss": 0.3983235597610474, "num_input_tokens_seen": 298227464, "step": 7240, "train_runtime": 27961.664, "train_tokens_per_second": 10665.584 }, { "epoch": 0.48781308914624294, "grad_norm": 0.7406459146374798, "learning_rate": 8.602929931640029e-06, "loss": 0.4048879623413086, "num_input_tokens_seen": 298419328, "step": 7245, "train_runtime": 27979.6424, "train_tokens_per_second": 10665.588 }, { "epoch": 0.4881497441422031, "grad_norm": 0.7677514846211575, "learning_rate": 8.601096112377659e-06, "loss": 0.41484818458557127, "num_input_tokens_seen": 298621288, "step": 7250, "train_runtime": 28000.0682, "train_tokens_per_second": 10665.02 }, { "epoch": 0.4884863991381632, "grad_norm": 0.6844930851003017, "learning_rate": 8.59926128608024e-06, "loss": 0.3829127550125122, "num_input_tokens_seen": 298829776, "step": 7255, "train_runtime": 28019.4801, "train_tokens_per_second": 10665.072 }, { "epoch": 0.48882305413412336, "grad_norm": 1.115985726708094, "learning_rate": 8.597425453260881e-06, "loss": 0.38410153388977053, "num_input_tokens_seen": 299030472, "step": 7260, "train_runtime": 28038.5334, "train_tokens_per_second": 10664.983 }, { "epoch": 0.4891597091300835, "grad_norm": 0.8302519436858289, "learning_rate": 8.595588614432967e-06, "loss": 0.370586633682251, "num_input_tokens_seen": 299225000, "step": 7265, "train_runtime": 28058.4628, "train_tokens_per_second": 10664.34 }, { "epoch": 0.48949636412604364, "grad_norm": 0.7329488395698431, "learning_rate": 8.59375077011016e-06, "loss": 0.36975650787353515, "num_input_tokens_seen": 299438624, "step": 7270, "train_runtime": 28076.9048, "train_tokens_per_second": 10664.944 }, { "epoch": 0.4898330191220038, "grad_norm": 0.7535346762598369, "learning_rate": 8.591911920806412e-06, "loss": 0.4119251251220703, "num_input_tokens_seen": 299654328, "step": 7275, "train_runtime": 28096.7923, "train_tokens_per_second": 10665.073 }, { "epoch": 0.4901696741179639, "grad_norm": 0.6834109171015744, "learning_rate": 8.590072067035947e-06, "loss": 0.3947604656219482, "num_input_tokens_seen": 299870864, "step": 7280, "train_runtime": 28116.5313, "train_tokens_per_second": 10665.287 }, { "epoch": 0.49050632911392406, "grad_norm": 0.8261234141892778, "learning_rate": 8.588231209313278e-06, "loss": 0.3728387117385864, "num_input_tokens_seen": 300096144, "step": 7285, "train_runtime": 28134.0705, "train_tokens_per_second": 10666.645 }, { "epoch": 0.4908429841098842, "grad_norm": 0.7356173516596133, "learning_rate": 8.586389348153192e-06, "loss": 0.39172117710113524, "num_input_tokens_seen": 300301616, "step": 7290, "train_runtime": 28151.7504, "train_tokens_per_second": 10667.245 }, { "epoch": 0.49117963910584433, "grad_norm": 0.7386072378373093, "learning_rate": 8.584546484070762e-06, "loss": 0.4027562141418457, "num_input_tokens_seen": 300501672, "step": 7295, "train_runtime": 28171.0879, "train_tokens_per_second": 10667.024 }, { "epoch": 0.4915162941018045, "grad_norm": 0.7629596996110681, "learning_rate": 8.582702617581338e-06, "loss": 0.3845263719558716, "num_input_tokens_seen": 300711272, "step": 7300, "train_runtime": 28190.2849, "train_tokens_per_second": 10667.195 }, { "epoch": 0.4918529490977646, "grad_norm": 0.7537667991840314, "learning_rate": 8.58085774920055e-06, "loss": 0.3944259166717529, "num_input_tokens_seen": 300905528, "step": 7305, "train_runtime": 28209.4812, "train_tokens_per_second": 10666.822 }, { "epoch": 0.49218960409372475, "grad_norm": 0.7418767106137435, "learning_rate": 8.579011879444313e-06, "loss": 0.41945247650146483, "num_input_tokens_seen": 301122056, "step": 7310, "train_runtime": 28229.8666, "train_tokens_per_second": 10666.79 }, { "epoch": 0.4925262590896849, "grad_norm": 0.6271940046162412, "learning_rate": 8.577165008828817e-06, "loss": 0.35617015361785886, "num_input_tokens_seen": 301315672, "step": 7315, "train_runtime": 28249.9151, "train_tokens_per_second": 10666.074 }, { "epoch": 0.49286291408564503, "grad_norm": 0.7218438739976211, "learning_rate": 8.57531713787053e-06, "loss": 0.39009642601013184, "num_input_tokens_seen": 301512192, "step": 7320, "train_runtime": 28269.6171, "train_tokens_per_second": 10665.592 }, { "epoch": 0.49319956908160517, "grad_norm": 0.8143498240019154, "learning_rate": 8.573468267086208e-06, "loss": 0.3976858854293823, "num_input_tokens_seen": 301715488, "step": 7325, "train_runtime": 28287.0718, "train_tokens_per_second": 10666.197 }, { "epoch": 0.4935362240775653, "grad_norm": 0.7533742469735069, "learning_rate": 8.57161839699288e-06, "loss": 0.361602783203125, "num_input_tokens_seen": 301922632, "step": 7330, "train_runtime": 28306.6267, "train_tokens_per_second": 10666.147 }, { "epoch": 0.49387287907352545, "grad_norm": 0.8503497736099982, "learning_rate": 8.569767528107857e-06, "loss": 0.3946902513504028, "num_input_tokens_seen": 302126392, "step": 7335, "train_runtime": 28326.0446, "train_tokens_per_second": 10666.028 }, { "epoch": 0.4942095340694856, "grad_norm": 0.6701522379699635, "learning_rate": 8.567915660948727e-06, "loss": 0.3778455018997192, "num_input_tokens_seen": 302336480, "step": 7340, "train_runtime": 28345.3534, "train_tokens_per_second": 10666.174 }, { "epoch": 0.49454618906544573, "grad_norm": 0.7793934548830403, "learning_rate": 8.566062796033358e-06, "loss": 0.4111305236816406, "num_input_tokens_seen": 302538992, "step": 7345, "train_runtime": 28364.3507, "train_tokens_per_second": 10666.17 }, { "epoch": 0.49488284406140587, "grad_norm": 0.6624315680680849, "learning_rate": 8.564208933879903e-06, "loss": 0.374592924118042, "num_input_tokens_seen": 302739520, "step": 7350, "train_runtime": 28384.1389, "train_tokens_per_second": 10665.799 }, { "epoch": 0.495219499057366, "grad_norm": 0.6870770499540597, "learning_rate": 8.562354075006782e-06, "loss": 0.3480309724807739, "num_input_tokens_seen": 302944960, "step": 7355, "train_runtime": 28402.5533, "train_tokens_per_second": 10666.117 }, { "epoch": 0.49555615405332615, "grad_norm": 0.6988336789743255, "learning_rate": 8.560498219932706e-06, "loss": 0.4289520263671875, "num_input_tokens_seen": 303153560, "step": 7360, "train_runtime": 28421.4683, "train_tokens_per_second": 10666.358 }, { "epoch": 0.4958928090492863, "grad_norm": 0.7110222043014791, "learning_rate": 8.558641369176654e-06, "loss": 0.3432353973388672, "num_input_tokens_seen": 303344776, "step": 7365, "train_runtime": 28439.8546, "train_tokens_per_second": 10666.186 }, { "epoch": 0.4962294640452464, "grad_norm": 0.742910376273375, "learning_rate": 8.556783523257892e-06, "loss": 0.39832186698913574, "num_input_tokens_seen": 303545184, "step": 7370, "train_runtime": 28460.1927, "train_tokens_per_second": 10665.605 }, { "epoch": 0.49656611904120657, "grad_norm": 0.7090721487198324, "learning_rate": 8.554924682695959e-06, "loss": 0.35245909690856936, "num_input_tokens_seen": 303741768, "step": 7375, "train_runtime": 28478.6907, "train_tokens_per_second": 10665.58 }, { "epoch": 0.4969027740371667, "grad_norm": 0.6993175292664321, "learning_rate": 8.553064848010677e-06, "loss": 0.4006857395172119, "num_input_tokens_seen": 303938304, "step": 7380, "train_runtime": 28498.0096, "train_tokens_per_second": 10665.247 }, { "epoch": 0.49723942903312685, "grad_norm": 0.7299820355547245, "learning_rate": 8.551204019722137e-06, "loss": 0.36638522148132324, "num_input_tokens_seen": 304139440, "step": 7385, "train_runtime": 28517.0954, "train_tokens_per_second": 10665.162 }, { "epoch": 0.497576084029087, "grad_norm": 0.7610240469874799, "learning_rate": 8.549342198350718e-06, "loss": 0.410584545135498, "num_input_tokens_seen": 304349680, "step": 7390, "train_runtime": 28535.5453, "train_tokens_per_second": 10665.634 }, { "epoch": 0.4979127390250471, "grad_norm": 0.6582475322914317, "learning_rate": 8.54747938441707e-06, "loss": 0.37069149017333985, "num_input_tokens_seen": 304559024, "step": 7395, "train_runtime": 28556.5418, "train_tokens_per_second": 10665.123 }, { "epoch": 0.49824939402100726, "grad_norm": 0.7122091820651187, "learning_rate": 8.545615578442126e-06, "loss": 0.3598170757293701, "num_input_tokens_seen": 304765008, "step": 7400, "train_runtime": 28574.3283, "train_tokens_per_second": 10665.693 }, { "epoch": 0.4985860490169674, "grad_norm": 0.8197375001316616, "learning_rate": 8.54375078094709e-06, "loss": 0.37699027061462403, "num_input_tokens_seen": 304974000, "step": 7405, "train_runtime": 28593.5639, "train_tokens_per_second": 10665.827 }, { "epoch": 0.49892270401292754, "grad_norm": 0.6729713539904562, "learning_rate": 8.541884992453449e-06, "loss": 0.37670111656188965, "num_input_tokens_seen": 305183024, "step": 7410, "train_runtime": 28612.3888, "train_tokens_per_second": 10666.115 }, { "epoch": 0.4992593590088877, "grad_norm": 0.7153841605260535, "learning_rate": 8.540018213482966e-06, "loss": 0.3809486389160156, "num_input_tokens_seen": 305401120, "step": 7415, "train_runtime": 28631.9838, "train_tokens_per_second": 10666.432 }, { "epoch": 0.4995960140048478, "grad_norm": 0.7458746179498573, "learning_rate": 8.538150444557676e-06, "loss": 0.391895055770874, "num_input_tokens_seen": 305598296, "step": 7420, "train_runtime": 28652.5943, "train_tokens_per_second": 10665.641 }, { "epoch": 0.49993266900080796, "grad_norm": 0.9638287610306009, "learning_rate": 8.536281686199896e-06, "loss": 0.39306344985961916, "num_input_tokens_seen": 305808504, "step": 7425, "train_runtime": 28671.4487, "train_tokens_per_second": 10665.959 }, { "epoch": 0.5002693239967682, "grad_norm": 0.6930855683947799, "learning_rate": 8.534411938932218e-06, "loss": 0.38206119537353517, "num_input_tokens_seen": 306021024, "step": 7430, "train_runtime": 28690.4373, "train_tokens_per_second": 10666.307 }, { "epoch": 0.5006059789927283, "grad_norm": 0.7193344185990245, "learning_rate": 8.532541203277515e-06, "loss": 0.37118656635284425, "num_input_tokens_seen": 306232496, "step": 7435, "train_runtime": 28708.9206, "train_tokens_per_second": 10666.806 }, { "epoch": 0.5009426339886884, "grad_norm": 0.7961653195426706, "learning_rate": 8.530669479758926e-06, "loss": 0.3811478853225708, "num_input_tokens_seen": 306438800, "step": 7440, "train_runtime": 28728.5886, "train_tokens_per_second": 10666.685 }, { "epoch": 0.5012792889846486, "grad_norm": 0.8878010448323473, "learning_rate": 8.528796768899878e-06, "loss": 0.39930813312530516, "num_input_tokens_seen": 306630368, "step": 7445, "train_runtime": 28746.9683, "train_tokens_per_second": 10666.529 }, { "epoch": 0.5016159439806087, "grad_norm": 0.7548146465306067, "learning_rate": 8.526923071224064e-06, "loss": 0.390773344039917, "num_input_tokens_seen": 306840264, "step": 7450, "train_runtime": 28765.5701, "train_tokens_per_second": 10666.928 }, { "epoch": 0.5019525989765689, "grad_norm": 0.7121971164631625, "learning_rate": 8.525048387255461e-06, "loss": 0.3946845531463623, "num_input_tokens_seen": 307052400, "step": 7455, "train_runtime": 28785.2838, "train_tokens_per_second": 10666.992 }, { "epoch": 0.502289253972529, "grad_norm": 0.736700079731411, "learning_rate": 8.523172717518315e-06, "loss": 0.3747260093688965, "num_input_tokens_seen": 307252328, "step": 7460, "train_runtime": 28805.2174, "train_tokens_per_second": 10666.551 }, { "epoch": 0.5026259089684891, "grad_norm": 0.7173485130564538, "learning_rate": 8.521296062537156e-06, "loss": 0.3770965576171875, "num_input_tokens_seen": 307455136, "step": 7465, "train_runtime": 28824.6024, "train_tokens_per_second": 10666.414 }, { "epoch": 0.5029625639644493, "grad_norm": 0.7562953187887723, "learning_rate": 8.51941842283678e-06, "loss": 0.37341301441192626, "num_input_tokens_seen": 307657208, "step": 7470, "train_runtime": 28844.8445, "train_tokens_per_second": 10665.934 }, { "epoch": 0.5032992189604094, "grad_norm": 0.7724908558434957, "learning_rate": 8.517539798942265e-06, "loss": 0.3762083053588867, "num_input_tokens_seen": 307873448, "step": 7475, "train_runtime": 28862.3208, "train_tokens_per_second": 10666.968 }, { "epoch": 0.5036358739563696, "grad_norm": 0.652970516465623, "learning_rate": 8.515660191378962e-06, "loss": 0.3950355052947998, "num_input_tokens_seen": 308082856, "step": 7480, "train_runtime": 28882.0705, "train_tokens_per_second": 10666.924 }, { "epoch": 0.5039725289523297, "grad_norm": 0.6626091080884778, "learning_rate": 8.513779600672495e-06, "loss": 0.36356801986694337, "num_input_tokens_seen": 308301048, "step": 7485, "train_runtime": 28899.7251, "train_tokens_per_second": 10667.958 }, { "epoch": 0.5043091839482898, "grad_norm": 0.6736085510451354, "learning_rate": 8.511898027348771e-06, "loss": 0.37669644355773924, "num_input_tokens_seen": 308494504, "step": 7490, "train_runtime": 28919.9082, "train_tokens_per_second": 10667.202 }, { "epoch": 0.50464583894425, "grad_norm": 0.6798619673349326, "learning_rate": 8.51001547193396e-06, "loss": 0.372920560836792, "num_input_tokens_seen": 308704520, "step": 7495, "train_runtime": 28938.965, "train_tokens_per_second": 10667.435 }, { "epoch": 0.5049824939402101, "grad_norm": 0.8013473214547115, "learning_rate": 8.508131934954515e-06, "loss": 0.368045711517334, "num_input_tokens_seen": 308897744, "step": 7500, "train_runtime": 28959.517, "train_tokens_per_second": 10666.536 }, { "epoch": 0.5053191489361702, "grad_norm": 0.6924024300093707, "learning_rate": 8.50624741693716e-06, "loss": 0.39351255893707277, "num_input_tokens_seen": 309093552, "step": 7505, "train_runtime": 28979.9706, "train_tokens_per_second": 10665.765 }, { "epoch": 0.5056558039321304, "grad_norm": 0.7998803034695547, "learning_rate": 8.5043619184089e-06, "loss": 0.41560931205749513, "num_input_tokens_seen": 309299552, "step": 7510, "train_runtime": 28997.6026, "train_tokens_per_second": 10666.384 }, { "epoch": 0.5059924589280905, "grad_norm": 0.7153006523647664, "learning_rate": 8.502475439897e-06, "loss": 0.4104278564453125, "num_input_tokens_seen": 309509368, "step": 7515, "train_runtime": 29015.9682, "train_tokens_per_second": 10666.863 }, { "epoch": 0.5063291139240507, "grad_norm": 0.6613181249168189, "learning_rate": 8.500587981929013e-06, "loss": 0.38866586685180665, "num_input_tokens_seen": 309717648, "step": 7520, "train_runtime": 29035.8225, "train_tokens_per_second": 10666.743 }, { "epoch": 0.5066657689200108, "grad_norm": 0.7248107460389412, "learning_rate": 8.498699545032758e-06, "loss": 0.3846409320831299, "num_input_tokens_seen": 309936584, "step": 7525, "train_runtime": 29054.0765, "train_tokens_per_second": 10667.577 }, { "epoch": 0.507002423915971, "grad_norm": 0.6754707261542254, "learning_rate": 8.496810129736334e-06, "loss": 0.38599045276641847, "num_input_tokens_seen": 310145456, "step": 7530, "train_runtime": 29074.5038, "train_tokens_per_second": 10667.266 }, { "epoch": 0.5073390789119311, "grad_norm": 0.7450773704237649, "learning_rate": 8.494919736568105e-06, "loss": 0.3825652837753296, "num_input_tokens_seen": 310345584, "step": 7535, "train_runtime": 29094.693, "train_tokens_per_second": 10666.742 }, { "epoch": 0.5076757339078912, "grad_norm": 0.7314987616524891, "learning_rate": 8.49302836605672e-06, "loss": 0.37611281871795654, "num_input_tokens_seen": 310557976, "step": 7540, "train_runtime": 29114.2384, "train_tokens_per_second": 10666.876 }, { "epoch": 0.5080123889038514, "grad_norm": 0.6961217908795218, "learning_rate": 8.491136018731088e-06, "loss": 0.37459983825683596, "num_input_tokens_seen": 310768992, "step": 7545, "train_runtime": 29134.0171, "train_tokens_per_second": 10666.878 }, { "epoch": 0.5083490438998115, "grad_norm": 0.793188045695128, "learning_rate": 8.4892426951204e-06, "loss": 0.3926174879074097, "num_input_tokens_seen": 310974912, "step": 7550, "train_runtime": 29151.2998, "train_tokens_per_second": 10667.617 }, { "epoch": 0.5086856988957716, "grad_norm": 0.6688734125633659, "learning_rate": 8.48734839575412e-06, "loss": 0.3770395517349243, "num_input_tokens_seen": 311189752, "step": 7555, "train_runtime": 29169.7708, "train_tokens_per_second": 10668.228 }, { "epoch": 0.5090223538917318, "grad_norm": 0.6673395331869354, "learning_rate": 8.485453121161983e-06, "loss": 0.37133049964904785, "num_input_tokens_seen": 311395872, "step": 7560, "train_runtime": 29190.2399, "train_tokens_per_second": 10667.808 }, { "epoch": 0.5093590088876919, "grad_norm": 0.8201361879724167, "learning_rate": 8.483556871873993e-06, "loss": 0.42520980834960936, "num_input_tokens_seen": 311604352, "step": 7565, "train_runtime": 29209.5667, "train_tokens_per_second": 10667.887 }, { "epoch": 0.5096956638836521, "grad_norm": 0.7080860619950804, "learning_rate": 8.481659648420433e-06, "loss": 0.37879669666290283, "num_input_tokens_seen": 311812400, "step": 7570, "train_runtime": 29228.6305, "train_tokens_per_second": 10668.047 }, { "epoch": 0.5100323188796122, "grad_norm": 0.8342148873690725, "learning_rate": 8.479761451331855e-06, "loss": 0.37928855419158936, "num_input_tokens_seen": 311992088, "step": 7575, "train_runtime": 29246.7328, "train_tokens_per_second": 10667.588 }, { "epoch": 0.5103689738755723, "grad_norm": 0.7986087631790508, "learning_rate": 8.477862281139082e-06, "loss": 0.35706820487976076, "num_input_tokens_seen": 312199472, "step": 7580, "train_runtime": 29268.4303, "train_tokens_per_second": 10666.765 }, { "epoch": 0.5107056288715325, "grad_norm": 0.8262032807612194, "learning_rate": 8.475962138373212e-06, "loss": 0.413095760345459, "num_input_tokens_seen": 312388600, "step": 7585, "train_runtime": 29286.5344, "train_tokens_per_second": 10666.629 }, { "epoch": 0.5110422838674926, "grad_norm": 0.7027256599672264, "learning_rate": 8.474061023565614e-06, "loss": 0.4044356346130371, "num_input_tokens_seen": 312601104, "step": 7590, "train_runtime": 29305.507, "train_tokens_per_second": 10666.975 }, { "epoch": 0.5113789388634528, "grad_norm": 0.7531341837862852, "learning_rate": 8.472158937247931e-06, "loss": 0.41010456085205077, "num_input_tokens_seen": 312806272, "step": 7595, "train_runtime": 29324.5843, "train_tokens_per_second": 10667.032 }, { "epoch": 0.5117155938594129, "grad_norm": 0.7074368704450417, "learning_rate": 8.47025587995207e-06, "loss": 0.3914539098739624, "num_input_tokens_seen": 313007048, "step": 7600, "train_runtime": 29342.0787, "train_tokens_per_second": 10667.514 }, { "epoch": 0.512052248855373, "grad_norm": 0.7429037851672801, "learning_rate": 8.46835185221022e-06, "loss": 0.39538285732269285, "num_input_tokens_seen": 313203256, "step": 7605, "train_runtime": 29361.8865, "train_tokens_per_second": 10667.0 }, { "epoch": 0.5123889038513332, "grad_norm": 0.8092077404923637, "learning_rate": 8.466446854554835e-06, "loss": 0.35824241638183596, "num_input_tokens_seen": 313400408, "step": 7610, "train_runtime": 29379.9037, "train_tokens_per_second": 10667.169 }, { "epoch": 0.5127255588472933, "grad_norm": 0.6874211074343812, "learning_rate": 8.464540887518638e-06, "loss": 0.3832658529281616, "num_input_tokens_seen": 313596728, "step": 7615, "train_runtime": 29399.0579, "train_tokens_per_second": 10666.897 }, { "epoch": 0.5130622138432535, "grad_norm": 0.8897554372612041, "learning_rate": 8.462633951634631e-06, "loss": 0.3706249952316284, "num_input_tokens_seen": 313804808, "step": 7620, "train_runtime": 29419.0754, "train_tokens_per_second": 10666.712 }, { "epoch": 0.5133988688392136, "grad_norm": 0.6382588432618158, "learning_rate": 8.46072604743608e-06, "loss": 0.35714409351348875, "num_input_tokens_seen": 314004808, "step": 7625, "train_runtime": 29438.656, "train_tokens_per_second": 10666.411 }, { "epoch": 0.5137355238351737, "grad_norm": 0.8567566044713121, "learning_rate": 8.458817175456528e-06, "loss": 0.40443572998046873, "num_input_tokens_seen": 314209104, "step": 7630, "train_runtime": 29457.745, "train_tokens_per_second": 10666.434 }, { "epoch": 0.5140721788311339, "grad_norm": 0.7096545272860193, "learning_rate": 8.45690733622978e-06, "loss": 0.36046905517578126, "num_input_tokens_seen": 314419480, "step": 7635, "train_runtime": 29477.1765, "train_tokens_per_second": 10666.54 }, { "epoch": 0.514408833827094, "grad_norm": 0.8361806862960937, "learning_rate": 8.45499653028992e-06, "loss": 0.37140765190124514, "num_input_tokens_seen": 314622760, "step": 7640, "train_runtime": 29496.0126, "train_tokens_per_second": 10666.62 }, { "epoch": 0.5147454888230542, "grad_norm": 0.6913896147787908, "learning_rate": 8.453084758171297e-06, "loss": 0.38297119140625, "num_input_tokens_seen": 314831608, "step": 7645, "train_runtime": 29516.5359, "train_tokens_per_second": 10666.279 }, { "epoch": 0.5150821438190143, "grad_norm": 0.6983310615703315, "learning_rate": 8.451172020408532e-06, "loss": 0.39296393394470214, "num_input_tokens_seen": 315041512, "step": 7650, "train_runtime": 29535.5745, "train_tokens_per_second": 10666.51 }, { "epoch": 0.5154187988149744, "grad_norm": 0.7338853779009823, "learning_rate": 8.449258317536517e-06, "loss": 0.3590440511703491, "num_input_tokens_seen": 315246296, "step": 7655, "train_runtime": 29553.9106, "train_tokens_per_second": 10666.822 }, { "epoch": 0.5157554538109346, "grad_norm": 0.7067855489183164, "learning_rate": 8.447343650090412e-06, "loss": 0.3576109170913696, "num_input_tokens_seen": 315453728, "step": 7660, "train_runtime": 29572.5416, "train_tokens_per_second": 10667.116 }, { "epoch": 0.5160921088068947, "grad_norm": 0.6785588127858565, "learning_rate": 8.445428018605647e-06, "loss": 0.40924921035766604, "num_input_tokens_seen": 315664760, "step": 7665, "train_runtime": 29592.1823, "train_tokens_per_second": 10667.167 }, { "epoch": 0.5164287638028549, "grad_norm": 0.7882723363480633, "learning_rate": 8.443511423617924e-06, "loss": 0.35135536193847655, "num_input_tokens_seen": 315873192, "step": 7670, "train_runtime": 29611.9401, "train_tokens_per_second": 10667.089 }, { "epoch": 0.516765418798815, "grad_norm": 0.6795540986487375, "learning_rate": 8.441593865663213e-06, "loss": 0.39581639766693116, "num_input_tokens_seen": 316083968, "step": 7675, "train_runtime": 29630.7751, "train_tokens_per_second": 10667.422 }, { "epoch": 0.5171020737947751, "grad_norm": 0.6550636219174655, "learning_rate": 8.439675345277751e-06, "loss": 0.4022339344024658, "num_input_tokens_seen": 316290864, "step": 7680, "train_runtime": 29649.5826, "train_tokens_per_second": 10667.633 }, { "epoch": 0.5174387287907353, "grad_norm": 0.6391144243203615, "learning_rate": 8.437755862998047e-06, "loss": 0.3699688673019409, "num_input_tokens_seen": 316498880, "step": 7685, "train_runtime": 29667.4391, "train_tokens_per_second": 10668.224 }, { "epoch": 0.5177753837866954, "grad_norm": 0.6051489150517257, "learning_rate": 8.435835419360878e-06, "loss": 0.39701828956604, "num_input_tokens_seen": 316718624, "step": 7690, "train_runtime": 29684.9656, "train_tokens_per_second": 10669.328 }, { "epoch": 0.5181120387826555, "grad_norm": 0.730235647844181, "learning_rate": 8.433914014903291e-06, "loss": 0.43290185928344727, "num_input_tokens_seen": 316921352, "step": 7695, "train_runtime": 29703.289, "train_tokens_per_second": 10669.571 }, { "epoch": 0.5184486937786157, "grad_norm": 0.7162173546595707, "learning_rate": 8.431991650162599e-06, "loss": 0.37759838104248045, "num_input_tokens_seen": 317127032, "step": 7700, "train_runtime": 29723.7792, "train_tokens_per_second": 10669.136 }, { "epoch": 0.5187853487745758, "grad_norm": 0.6451156074822586, "learning_rate": 8.430068325676386e-06, "loss": 0.3887176513671875, "num_input_tokens_seen": 317331152, "step": 7705, "train_runtime": 29742.8948, "train_tokens_per_second": 10669.141 }, { "epoch": 0.519122003770536, "grad_norm": 0.7236616714126546, "learning_rate": 8.428144041982502e-06, "loss": 0.3971863746643066, "num_input_tokens_seen": 317533352, "step": 7710, "train_runtime": 29761.2901, "train_tokens_per_second": 10669.341 }, { "epoch": 0.5194586587664961, "grad_norm": 0.6366722945519879, "learning_rate": 8.42621879961907e-06, "loss": 0.3842915058135986, "num_input_tokens_seen": 317741136, "step": 7715, "train_runtime": 29779.8623, "train_tokens_per_second": 10669.664 }, { "epoch": 0.5197953137624562, "grad_norm": 0.6852079470853624, "learning_rate": 8.424292599124476e-06, "loss": 0.3631861686706543, "num_input_tokens_seen": 317953272, "step": 7720, "train_runtime": 29799.0697, "train_tokens_per_second": 10669.906 }, { "epoch": 0.5201319687584164, "grad_norm": 0.7722268347848646, "learning_rate": 8.422365441037374e-06, "loss": 0.4027854919433594, "num_input_tokens_seen": 318166312, "step": 7725, "train_runtime": 29817.6567, "train_tokens_per_second": 10670.4 }, { "epoch": 0.5204686237543765, "grad_norm": 0.6501020149998817, "learning_rate": 8.420437325896692e-06, "loss": 0.3893125534057617, "num_input_tokens_seen": 318379704, "step": 7730, "train_runtime": 29836.1826, "train_tokens_per_second": 10670.926 }, { "epoch": 0.5208052787503367, "grad_norm": 0.7384029264970075, "learning_rate": 8.418508254241617e-06, "loss": 0.39316864013671876, "num_input_tokens_seen": 318584208, "step": 7735, "train_runtime": 29855.0938, "train_tokens_per_second": 10671.017 }, { "epoch": 0.5211419337462968, "grad_norm": 0.7855712138479317, "learning_rate": 8.416578226611612e-06, "loss": 0.35736708641052245, "num_input_tokens_seen": 318783880, "step": 7740, "train_runtime": 29873.8684, "train_tokens_per_second": 10670.994 }, { "epoch": 0.5214785887422569, "grad_norm": 0.775788172405177, "learning_rate": 8.414647243546398e-06, "loss": 0.3789716958999634, "num_input_tokens_seen": 318992656, "step": 7745, "train_runtime": 29893.8214, "train_tokens_per_second": 10670.856 }, { "epoch": 0.5218152437382171, "grad_norm": 0.6598680173435514, "learning_rate": 8.412715305585973e-06, "loss": 0.3798691272735596, "num_input_tokens_seen": 319207304, "step": 7750, "train_runtime": 29913.4965, "train_tokens_per_second": 10671.013 }, { "epoch": 0.5221518987341772, "grad_norm": 0.657474369283945, "learning_rate": 8.410782413270594e-06, "loss": 0.3764036178588867, "num_input_tokens_seen": 319419776, "step": 7755, "train_runtime": 29932.6631, "train_tokens_per_second": 10671.278 }, { "epoch": 0.5224885537301374, "grad_norm": 0.8876558542649545, "learning_rate": 8.408848567140787e-06, "loss": 0.372241735458374, "num_input_tokens_seen": 319605008, "step": 7760, "train_runtime": 29952.4545, "train_tokens_per_second": 10670.411 }, { "epoch": 0.5228252087260975, "grad_norm": 0.7364596715495697, "learning_rate": 8.406913767737353e-06, "loss": 0.386940598487854, "num_input_tokens_seen": 319807120, "step": 7765, "train_runtime": 29971.8446, "train_tokens_per_second": 10670.252 }, { "epoch": 0.5231618637220576, "grad_norm": 0.6841311869028011, "learning_rate": 8.404978015601344e-06, "loss": 0.3947484254837036, "num_input_tokens_seen": 320016832, "step": 7770, "train_runtime": 29991.3054, "train_tokens_per_second": 10670.32 }, { "epoch": 0.5234985187180178, "grad_norm": 0.6936287593928062, "learning_rate": 8.403041311274091e-06, "loss": 0.4000382900238037, "num_input_tokens_seen": 320227576, "step": 7775, "train_runtime": 30010.2105, "train_tokens_per_second": 10670.621 }, { "epoch": 0.5238351737139779, "grad_norm": 0.7969477953528664, "learning_rate": 8.401103655297188e-06, "loss": 0.39126877784729003, "num_input_tokens_seen": 320429904, "step": 7780, "train_runtime": 30029.0138, "train_tokens_per_second": 10670.677 }, { "epoch": 0.5241718287099381, "grad_norm": 0.7099599207250751, "learning_rate": 8.399165048212494e-06, "loss": 0.3562298059463501, "num_input_tokens_seen": 320632672, "step": 7785, "train_runtime": 30048.8539, "train_tokens_per_second": 10670.379 }, { "epoch": 0.5245084837058982, "grad_norm": 0.6955318548447438, "learning_rate": 8.397225490562131e-06, "loss": 0.4020421028137207, "num_input_tokens_seen": 320845912, "step": 7790, "train_runtime": 30067.9557, "train_tokens_per_second": 10670.693 }, { "epoch": 0.5248451387018583, "grad_norm": 0.7594329474305855, "learning_rate": 8.395284982888494e-06, "loss": 0.3701248407363892, "num_input_tokens_seen": 321053352, "step": 7795, "train_runtime": 30086.2979, "train_tokens_per_second": 10671.082 }, { "epoch": 0.5251817936978185, "grad_norm": 0.6456861937910884, "learning_rate": 8.393343525734239e-06, "loss": 0.39694149494171144, "num_input_tokens_seen": 321263736, "step": 7800, "train_runtime": 30105.2185, "train_tokens_per_second": 10671.364 }, { "epoch": 0.5255184486937786, "grad_norm": 0.802978198872244, "learning_rate": 8.391401119642286e-06, "loss": 0.3984774827957153, "num_input_tokens_seen": 321452712, "step": 7805, "train_runtime": 30124.4453, "train_tokens_per_second": 10670.826 }, { "epoch": 0.5258551036897388, "grad_norm": 0.712530936473305, "learning_rate": 8.389457765155824e-06, "loss": 0.40579586029052733, "num_input_tokens_seen": 321646912, "step": 7810, "train_runtime": 30145.4813, "train_tokens_per_second": 10669.822 }, { "epoch": 0.5261917586856989, "grad_norm": 0.7389321520079071, "learning_rate": 8.387513462818309e-06, "loss": 0.3698542594909668, "num_input_tokens_seen": 321855160, "step": 7815, "train_runtime": 30166.0225, "train_tokens_per_second": 10669.46 }, { "epoch": 0.526528413681659, "grad_norm": 0.7154830448933215, "learning_rate": 8.385568213173453e-06, "loss": 0.3680989742279053, "num_input_tokens_seen": 322057904, "step": 7820, "train_runtime": 30185.4682, "train_tokens_per_second": 10669.303 }, { "epoch": 0.5268650686776192, "grad_norm": 0.645787324102921, "learning_rate": 8.383622016765242e-06, "loss": 0.36203417778015134, "num_input_tokens_seen": 322266304, "step": 7825, "train_runtime": 30205.4867, "train_tokens_per_second": 10669.131 }, { "epoch": 0.5272017236735793, "grad_norm": 0.7057813857107303, "learning_rate": 8.381674874137926e-06, "loss": 0.40050768852233887, "num_input_tokens_seen": 322464856, "step": 7830, "train_runtime": 30224.0821, "train_tokens_per_second": 10669.136 }, { "epoch": 0.5275383786695395, "grad_norm": 0.6904728642724235, "learning_rate": 8.379726785836013e-06, "loss": 0.3649367094039917, "num_input_tokens_seen": 322668144, "step": 7835, "train_runtime": 30243.8928, "train_tokens_per_second": 10668.869 }, { "epoch": 0.5278750336654996, "grad_norm": 0.662358569835286, "learning_rate": 8.377777752404283e-06, "loss": 0.3723143100738525, "num_input_tokens_seen": 322884976, "step": 7840, "train_runtime": 30264.6819, "train_tokens_per_second": 10668.705 }, { "epoch": 0.5282116886614597, "grad_norm": 0.7756623904350415, "learning_rate": 8.375827774387774e-06, "loss": 0.35005066394805906, "num_input_tokens_seen": 323074288, "step": 7845, "train_runtime": 30284.6254, "train_tokens_per_second": 10667.931 }, { "epoch": 0.5285483436574199, "grad_norm": 0.616999648406278, "learning_rate": 8.373876852331793e-06, "loss": 0.3457553625106812, "num_input_tokens_seen": 323287384, "step": 7850, "train_runtime": 30304.5931, "train_tokens_per_second": 10667.933 }, { "epoch": 0.52888499865338, "grad_norm": 0.7057795202006445, "learning_rate": 8.371924986781909e-06, "loss": 0.3943150997161865, "num_input_tokens_seen": 323490384, "step": 7855, "train_runtime": 30323.3844, "train_tokens_per_second": 10668.017 }, { "epoch": 0.5292216536493402, "grad_norm": 0.7485181001099696, "learning_rate": 8.369972178283955e-06, "loss": 0.3712784290313721, "num_input_tokens_seen": 323705136, "step": 7860, "train_runtime": 30343.7323, "train_tokens_per_second": 10667.941 }, { "epoch": 0.5295583086453003, "grad_norm": 0.701341893450852, "learning_rate": 8.368018427384027e-06, "loss": 0.3821697473526001, "num_input_tokens_seen": 323916544, "step": 7865, "train_runtime": 30365.6513, "train_tokens_per_second": 10667.202 }, { "epoch": 0.5298949636412604, "grad_norm": 0.7859914882981589, "learning_rate": 8.366063734628485e-06, "loss": 0.3825965881347656, "num_input_tokens_seen": 324111960, "step": 7870, "train_runtime": 30384.8557, "train_tokens_per_second": 10666.892 }, { "epoch": 0.5302316186372206, "grad_norm": 0.7732189484100693, "learning_rate": 8.364108100563955e-06, "loss": 0.39859030246734617, "num_input_tokens_seen": 324316984, "step": 7875, "train_runtime": 30403.6683, "train_tokens_per_second": 10667.035 }, { "epoch": 0.5305682736331807, "grad_norm": 0.8165353416985199, "learning_rate": 8.362151525737321e-06, "loss": 0.42402920722961424, "num_input_tokens_seen": 324525464, "step": 7880, "train_runtime": 30423.3816, "train_tokens_per_second": 10666.975 }, { "epoch": 0.5309049286291408, "grad_norm": 0.7071327973560986, "learning_rate": 8.360194010695733e-06, "loss": 0.35443754196166993, "num_input_tokens_seen": 324732112, "step": 7885, "train_runtime": 30442.0057, "train_tokens_per_second": 10667.238 }, { "epoch": 0.531241583625101, "grad_norm": 0.6440498737285782, "learning_rate": 8.358235555986607e-06, "loss": 0.3947384595870972, "num_input_tokens_seen": 324942968, "step": 7890, "train_runtime": 30459.6875, "train_tokens_per_second": 10667.968 }, { "epoch": 0.5315782386210611, "grad_norm": 0.7543404178734677, "learning_rate": 8.356276162157613e-06, "loss": 0.3648514270782471, "num_input_tokens_seen": 325143096, "step": 7895, "train_runtime": 30480.5548, "train_tokens_per_second": 10667.23 }, { "epoch": 0.5319148936170213, "grad_norm": 0.7250785831760326, "learning_rate": 8.354315829756696e-06, "loss": 0.38411455154418944, "num_input_tokens_seen": 325354504, "step": 7900, "train_runtime": 30498.4854, "train_tokens_per_second": 10667.891 }, { "epoch": 0.5322515486129814, "grad_norm": 0.6725101547317001, "learning_rate": 8.352354559332053e-06, "loss": 0.3662379264831543, "num_input_tokens_seen": 325559880, "step": 7905, "train_runtime": 30516.6162, "train_tokens_per_second": 10668.282 }, { "epoch": 0.5325882036089415, "grad_norm": 0.7298781499425311, "learning_rate": 8.350392351432146e-06, "loss": 0.3936772346496582, "num_input_tokens_seen": 325759936, "step": 7910, "train_runtime": 30534.7065, "train_tokens_per_second": 10668.514 }, { "epoch": 0.5329248586049017, "grad_norm": 0.6367757528936794, "learning_rate": 8.348429206605702e-06, "loss": 0.36289033889770506, "num_input_tokens_seen": 325980736, "step": 7915, "train_runtime": 30555.9034, "train_tokens_per_second": 10668.339 }, { "epoch": 0.5332615136008618, "grad_norm": 0.7921855264117278, "learning_rate": 8.346465125401706e-06, "loss": 0.42093501091003416, "num_input_tokens_seen": 326187592, "step": 7920, "train_runtime": 30577.214, "train_tokens_per_second": 10667.669 }, { "epoch": 0.533598168596822, "grad_norm": 0.7107012331534462, "learning_rate": 8.344500108369412e-06, "loss": 0.37152681350708006, "num_input_tokens_seen": 326388896, "step": 7925, "train_runtime": 30598.4041, "train_tokens_per_second": 10666.86 }, { "epoch": 0.5339348235927821, "grad_norm": 0.6554696428542859, "learning_rate": 8.342534156058326e-06, "loss": 0.38762741088867186, "num_input_tokens_seen": 326596576, "step": 7930, "train_runtime": 30618.3729, "train_tokens_per_second": 10666.686 }, { "epoch": 0.5342714785887422, "grad_norm": 0.7176769812207632, "learning_rate": 8.34056726901822e-06, "loss": 0.39376134872436525, "num_input_tokens_seen": 326799336, "step": 7935, "train_runtime": 30638.3381, "train_tokens_per_second": 10666.353 }, { "epoch": 0.5346081335847024, "grad_norm": 0.7272692203472002, "learning_rate": 8.338599447799132e-06, "loss": 0.3838132381439209, "num_input_tokens_seen": 326991840, "step": 7940, "train_runtime": 30656.6993, "train_tokens_per_second": 10666.244 }, { "epoch": 0.5349447885806625, "grad_norm": 0.810924349519634, "learning_rate": 8.336630692951353e-06, "loss": 0.373362398147583, "num_input_tokens_seen": 327198592, "step": 7945, "train_runtime": 30675.8691, "train_tokens_per_second": 10666.319 }, { "epoch": 0.5352814435766227, "grad_norm": 0.7303370271947086, "learning_rate": 8.334661005025441e-06, "loss": 0.3972501516342163, "num_input_tokens_seen": 327402480, "step": 7950, "train_runtime": 30695.2088, "train_tokens_per_second": 10666.241 }, { "epoch": 0.5356180985725828, "grad_norm": 0.7609851062579762, "learning_rate": 8.332690384572213e-06, "loss": 0.4134214878082275, "num_input_tokens_seen": 327604736, "step": 7955, "train_runtime": 30714.0492, "train_tokens_per_second": 10666.283 }, { "epoch": 0.5359547535685429, "grad_norm": 0.6988752462416652, "learning_rate": 8.330718832142746e-06, "loss": 0.4001334190368652, "num_input_tokens_seen": 327823320, "step": 7960, "train_runtime": 30732.8484, "train_tokens_per_second": 10666.871 }, { "epoch": 0.5362914085645031, "grad_norm": 0.6669602517264855, "learning_rate": 8.328746348288379e-06, "loss": 0.3843061447143555, "num_input_tokens_seen": 328019952, "step": 7965, "train_runtime": 30752.6023, "train_tokens_per_second": 10666.413 }, { "epoch": 0.5366280635604632, "grad_norm": 0.7043334895969853, "learning_rate": 8.32677293356071e-06, "loss": 0.42766742706298827, "num_input_tokens_seen": 328236248, "step": 7970, "train_runtime": 30772.0222, "train_tokens_per_second": 10666.71 }, { "epoch": 0.5369647185564234, "grad_norm": 0.7853971580209198, "learning_rate": 8.324798588511598e-06, "loss": 0.36816205978393557, "num_input_tokens_seen": 328425872, "step": 7975, "train_runtime": 30790.3359, "train_tokens_per_second": 10666.524 }, { "epoch": 0.5373013735523835, "grad_norm": 0.7938230617102565, "learning_rate": 8.322823313693162e-06, "loss": 0.3927563190460205, "num_input_tokens_seen": 328626912, "step": 7980, "train_runtime": 30808.1489, "train_tokens_per_second": 10666.883 }, { "epoch": 0.5376380285483436, "grad_norm": 0.7100174052255326, "learning_rate": 8.320847109657782e-06, "loss": 0.3812283515930176, "num_input_tokens_seen": 328828120, "step": 7985, "train_runtime": 30829.3106, "train_tokens_per_second": 10666.087 }, { "epoch": 0.5379746835443038, "grad_norm": 0.7079016800694559, "learning_rate": 8.318869976958099e-06, "loss": 0.3462749719619751, "num_input_tokens_seen": 329036776, "step": 7990, "train_runtime": 30850.6108, "train_tokens_per_second": 10665.487 }, { "epoch": 0.5383113385402639, "grad_norm": 0.6925776741928005, "learning_rate": 8.316891916147007e-06, "loss": 0.40938358306884765, "num_input_tokens_seen": 329240696, "step": 7995, "train_runtime": 30870.0033, "train_tokens_per_second": 10665.392 }, { "epoch": 0.5386479935362241, "grad_norm": 0.7890272742876181, "learning_rate": 8.314912927777671e-06, "loss": 0.39191374778747556, "num_input_tokens_seen": 329445888, "step": 8000, "train_runtime": 30888.8954, "train_tokens_per_second": 10665.512 }, { "epoch": 0.5389846485321842, "grad_norm": 0.7464330616735401, "learning_rate": 8.312933012403503e-06, "loss": 0.3809122800827026, "num_input_tokens_seen": 329640160, "step": 8005, "train_runtime": 30908.2875, "train_tokens_per_second": 10665.106 }, { "epoch": 0.5393213035281443, "grad_norm": 0.652959009772801, "learning_rate": 8.310952170578184e-06, "loss": 0.3961684226989746, "num_input_tokens_seen": 329841872, "step": 8010, "train_runtime": 30926.6512, "train_tokens_per_second": 10665.295 }, { "epoch": 0.5396579585241045, "grad_norm": 0.7656498313281103, "learning_rate": 8.308970402855647e-06, "loss": 0.3496106624603271, "num_input_tokens_seen": 330039320, "step": 8015, "train_runtime": 30944.6405, "train_tokens_per_second": 10665.476 }, { "epoch": 0.5399946135200646, "grad_norm": 0.7129061681582616, "learning_rate": 8.306987709790087e-06, "loss": 0.35733447074890134, "num_input_tokens_seen": 330240608, "step": 8020, "train_runtime": 30962.8929, "train_tokens_per_second": 10665.69 }, { "epoch": 0.5403312685160248, "grad_norm": 0.779649072222544, "learning_rate": 8.305004091935962e-06, "loss": 0.38627138137817385, "num_input_tokens_seen": 330447336, "step": 8025, "train_runtime": 30982.2553, "train_tokens_per_second": 10665.697 }, { "epoch": 0.5406679235119849, "grad_norm": 0.7147435031153012, "learning_rate": 8.303019549847979e-06, "loss": 0.4060565948486328, "num_input_tokens_seen": 330652440, "step": 8030, "train_runtime": 31002.3266, "train_tokens_per_second": 10665.407 }, { "epoch": 0.541004578507945, "grad_norm": 0.7716780525107738, "learning_rate": 8.301034084081114e-06, "loss": 0.38458211421966554, "num_input_tokens_seen": 330865232, "step": 8035, "train_runtime": 31020.9582, "train_tokens_per_second": 10665.861 }, { "epoch": 0.5413412335039052, "grad_norm": 0.8233116736366657, "learning_rate": 8.299047695190592e-06, "loss": 0.40970439910888673, "num_input_tokens_seen": 331061872, "step": 8040, "train_runtime": 31040.6299, "train_tokens_per_second": 10665.437 }, { "epoch": 0.5416778884998653, "grad_norm": 0.7408213865967362, "learning_rate": 8.297060383731903e-06, "loss": 0.3899158239364624, "num_input_tokens_seen": 331264408, "step": 8045, "train_runtime": 31059.9694, "train_tokens_per_second": 10665.317 }, { "epoch": 0.5420145434958255, "grad_norm": 0.7960352593161734, "learning_rate": 8.29507215026079e-06, "loss": 0.40250186920166015, "num_input_tokens_seen": 331469904, "step": 8050, "train_runtime": 31078.1947, "train_tokens_per_second": 10665.674 }, { "epoch": 0.5423511984917856, "grad_norm": 0.7898650349725767, "learning_rate": 8.293082995333257e-06, "loss": 0.38386242389678954, "num_input_tokens_seen": 331682152, "step": 8055, "train_runtime": 31095.5224, "train_tokens_per_second": 10666.557 }, { "epoch": 0.5426878534877457, "grad_norm": 0.7445388942450694, "learning_rate": 8.291092919505568e-06, "loss": 0.3538321256637573, "num_input_tokens_seen": 331885256, "step": 8060, "train_runtime": 31115.3048, "train_tokens_per_second": 10666.303 }, { "epoch": 0.5430245084837059, "grad_norm": 0.7172228477677535, "learning_rate": 8.289101923334237e-06, "loss": 0.39918568134307864, "num_input_tokens_seen": 332095376, "step": 8065, "train_runtime": 31134.9953, "train_tokens_per_second": 10666.306 }, { "epoch": 0.543361163479666, "grad_norm": 0.8493519695752447, "learning_rate": 8.28711000737604e-06, "loss": 0.37673521041870117, "num_input_tokens_seen": 332293512, "step": 8070, "train_runtime": 31153.2622, "train_tokens_per_second": 10666.411 }, { "epoch": 0.5436978184756261, "grad_norm": 0.7721426496306656, "learning_rate": 8.285117172188013e-06, "loss": 0.3959439754486084, "num_input_tokens_seen": 332503792, "step": 8075, "train_runtime": 31171.9253, "train_tokens_per_second": 10666.771 }, { "epoch": 0.5440344734715863, "grad_norm": 0.8068568786703985, "learning_rate": 8.283123418327443e-06, "loss": 0.4009416580200195, "num_input_tokens_seen": 332708048, "step": 8080, "train_runtime": 31190.4271, "train_tokens_per_second": 10666.992 }, { "epoch": 0.5443711284675464, "grad_norm": 0.6865299297720728, "learning_rate": 8.281128746351878e-06, "loss": 0.3640693187713623, "num_input_tokens_seen": 332922480, "step": 8085, "train_runtime": 31209.0678, "train_tokens_per_second": 10667.492 }, { "epoch": 0.5447077834635066, "grad_norm": 0.6529888992669175, "learning_rate": 8.279133156819123e-06, "loss": 0.40049047470092775, "num_input_tokens_seen": 333126672, "step": 8090, "train_runtime": 31227.8901, "train_tokens_per_second": 10667.601 }, { "epoch": 0.5450444384594667, "grad_norm": 0.7151383378813566, "learning_rate": 8.277136650287237e-06, "loss": 0.3654077768325806, "num_input_tokens_seen": 333340808, "step": 8095, "train_runtime": 31247.2573, "train_tokens_per_second": 10667.842 }, { "epoch": 0.5453810934554268, "grad_norm": 0.8248734943984779, "learning_rate": 8.275139227314537e-06, "loss": 0.3754036664962769, "num_input_tokens_seen": 333540000, "step": 8100, "train_runtime": 31267.9712, "train_tokens_per_second": 10667.146 }, { "epoch": 0.545717748451387, "grad_norm": 0.8341518069939228, "learning_rate": 8.273140888459594e-06, "loss": 0.42709989547729493, "num_input_tokens_seen": 333754920, "step": 8105, "train_runtime": 31286.1687, "train_tokens_per_second": 10667.811 }, { "epoch": 0.5460544034473471, "grad_norm": 0.7632798293173809, "learning_rate": 8.27114163428124e-06, "loss": 0.397280216217041, "num_input_tokens_seen": 333958464, "step": 8110, "train_runtime": 31304.9652, "train_tokens_per_second": 10667.907 }, { "epoch": 0.5463910584433073, "grad_norm": 0.7239534040309855, "learning_rate": 8.26914146533856e-06, "loss": 0.37759881019592284, "num_input_tokens_seen": 334175400, "step": 8115, "train_runtime": 31323.1642, "train_tokens_per_second": 10668.635 }, { "epoch": 0.5467277134392674, "grad_norm": 0.7076525084265881, "learning_rate": 8.267140382190892e-06, "loss": 0.3865623712539673, "num_input_tokens_seen": 334384776, "step": 8120, "train_runtime": 31343.9471, "train_tokens_per_second": 10668.241 }, { "epoch": 0.5470643684352275, "grad_norm": 0.6497735359972903, "learning_rate": 8.265138385397835e-06, "loss": 0.379496169090271, "num_input_tokens_seen": 334590064, "step": 8125, "train_runtime": 31363.3283, "train_tokens_per_second": 10668.194 }, { "epoch": 0.5474010234311877, "grad_norm": 0.5959170772744204, "learning_rate": 8.263135475519241e-06, "loss": 0.3556403636932373, "num_input_tokens_seen": 334811616, "step": 8130, "train_runtime": 31381.8806, "train_tokens_per_second": 10668.947 }, { "epoch": 0.5477376784271478, "grad_norm": 0.690946069203896, "learning_rate": 8.261131653115216e-06, "loss": 0.4212022304534912, "num_input_tokens_seen": 335025248, "step": 8135, "train_runtime": 31403.0995, "train_tokens_per_second": 10668.541 }, { "epoch": 0.548074333423108, "grad_norm": 0.7283316697978879, "learning_rate": 8.259126918746122e-06, "loss": 0.36560540199279784, "num_input_tokens_seen": 335231272, "step": 8140, "train_runtime": 31421.8819, "train_tokens_per_second": 10668.72 }, { "epoch": 0.5484109884190681, "grad_norm": 0.6235815230970988, "learning_rate": 8.25712127297258e-06, "loss": 0.3795539379119873, "num_input_tokens_seen": 335439224, "step": 8145, "train_runtime": 31441.0523, "train_tokens_per_second": 10668.829 }, { "epoch": 0.5487476434150282, "grad_norm": 0.7310400119407545, "learning_rate": 8.255114716355459e-06, "loss": 0.4146160125732422, "num_input_tokens_seen": 335654328, "step": 8150, "train_runtime": 31459.5867, "train_tokens_per_second": 10669.381 }, { "epoch": 0.5490842984109884, "grad_norm": 0.6015373761789026, "learning_rate": 8.253107249455887e-06, "loss": 0.3943221092224121, "num_input_tokens_seen": 335860256, "step": 8155, "train_runtime": 31478.0277, "train_tokens_per_second": 10669.673 }, { "epoch": 0.5494209534069485, "grad_norm": 0.6794298331289395, "learning_rate": 8.251098872835247e-06, "loss": 0.3909998655319214, "num_input_tokens_seen": 336071392, "step": 8160, "train_runtime": 31498.4608, "train_tokens_per_second": 10669.454 }, { "epoch": 0.5497576084029087, "grad_norm": 0.7050786396348898, "learning_rate": 8.249089587055175e-06, "loss": 0.35357213020324707, "num_input_tokens_seen": 336273392, "step": 8165, "train_runtime": 31518.4932, "train_tokens_per_second": 10669.082 }, { "epoch": 0.5500942633988688, "grad_norm": 0.6666159015671934, "learning_rate": 8.247079392677558e-06, "loss": 0.37820494174957275, "num_input_tokens_seen": 336480544, "step": 8170, "train_runtime": 31538.8278, "train_tokens_per_second": 10668.771 }, { "epoch": 0.5504309183948289, "grad_norm": 0.6897334839711616, "learning_rate": 8.245068290264544e-06, "loss": 0.3729065418243408, "num_input_tokens_seen": 336690920, "step": 8175, "train_runtime": 31559.133, "train_tokens_per_second": 10668.573 }, { "epoch": 0.5507675733907891, "grad_norm": 0.6892348546683557, "learning_rate": 8.243056280378531e-06, "loss": 0.37908368110656737, "num_input_tokens_seen": 336899232, "step": 8180, "train_runtime": 31579.8193, "train_tokens_per_second": 10668.181 }, { "epoch": 0.5511042283867492, "grad_norm": 0.6890672402669591, "learning_rate": 8.241043363582171e-06, "loss": 0.366745138168335, "num_input_tokens_seen": 337113216, "step": 8185, "train_runtime": 31599.3895, "train_tokens_per_second": 10668.346 }, { "epoch": 0.5514408833827094, "grad_norm": 0.637664118023288, "learning_rate": 8.239029540438369e-06, "loss": 0.3494518041610718, "num_input_tokens_seen": 337320208, "step": 8190, "train_runtime": 31619.6771, "train_tokens_per_second": 10668.047 }, { "epoch": 0.5517775383786695, "grad_norm": 0.7299747617129184, "learning_rate": 8.237014811510284e-06, "loss": 0.3689711570739746, "num_input_tokens_seen": 337532344, "step": 8195, "train_runtime": 31640.0454, "train_tokens_per_second": 10667.884 }, { "epoch": 0.5521141933746296, "grad_norm": 0.9130114126385479, "learning_rate": 8.234999177361329e-06, "loss": 0.3780252456665039, "num_input_tokens_seen": 337744968, "step": 8200, "train_runtime": 31659.5471, "train_tokens_per_second": 10668.029 }, { "epoch": 0.5524508483705898, "grad_norm": 0.6984037348111891, "learning_rate": 8.232982638555169e-06, "loss": 0.406351375579834, "num_input_tokens_seen": 337953136, "step": 8205, "train_runtime": 31677.5336, "train_tokens_per_second": 10668.543 }, { "epoch": 0.5527875033665499, "grad_norm": 0.8469464152131501, "learning_rate": 8.230965195655724e-06, "loss": 0.38977532386779784, "num_input_tokens_seen": 338172728, "step": 8210, "train_runtime": 31696.5227, "train_tokens_per_second": 10669.08 }, { "epoch": 0.55312415836251, "grad_norm": 0.7438073578073614, "learning_rate": 8.228946849227167e-06, "loss": 0.4047860145568848, "num_input_tokens_seen": 338389248, "step": 8215, "train_runtime": 31716.5351, "train_tokens_per_second": 10669.175 }, { "epoch": 0.5534608133584702, "grad_norm": 0.6923287641989705, "learning_rate": 8.226927599833916e-06, "loss": 0.39557466506958006, "num_input_tokens_seen": 338601088, "step": 8220, "train_runtime": 31734.6141, "train_tokens_per_second": 10669.772 }, { "epoch": 0.5537974683544303, "grad_norm": 0.6635944393883575, "learning_rate": 8.224907448040655e-06, "loss": 0.3859529972076416, "num_input_tokens_seen": 338815288, "step": 8225, "train_runtime": 31752.4971, "train_tokens_per_second": 10670.508 }, { "epoch": 0.5541341233503905, "grad_norm": 0.7662021928915863, "learning_rate": 8.222886394412309e-06, "loss": 0.40723419189453125, "num_input_tokens_seen": 339022016, "step": 8230, "train_runtime": 31772.5796, "train_tokens_per_second": 10670.27 }, { "epoch": 0.5544707783463506, "grad_norm": 0.7073894376840325, "learning_rate": 8.220864439514057e-06, "loss": 0.38754708766937257, "num_input_tokens_seen": 339236176, "step": 8235, "train_runtime": 31791.9158, "train_tokens_per_second": 10670.517 }, { "epoch": 0.5548074333423108, "grad_norm": 0.6427121159706624, "learning_rate": 8.218841583911338e-06, "loss": 0.3693054676055908, "num_input_tokens_seen": 339442344, "step": 8240, "train_runtime": 31812.7094, "train_tokens_per_second": 10670.023 }, { "epoch": 0.5551440883382709, "grad_norm": 0.7274505666120374, "learning_rate": 8.216817828169834e-06, "loss": 0.41214380264282224, "num_input_tokens_seen": 339645856, "step": 8245, "train_runtime": 31832.0945, "train_tokens_per_second": 10669.919 }, { "epoch": 0.555480743334231, "grad_norm": 0.8439265029423503, "learning_rate": 8.214793172855481e-06, "loss": 0.3721212863922119, "num_input_tokens_seen": 339849640, "step": 8250, "train_runtime": 31853.1356, "train_tokens_per_second": 10669.268 }, { "epoch": 0.5558173983301912, "grad_norm": 0.68396916972238, "learning_rate": 8.21276761853447e-06, "loss": 0.36893086433410643, "num_input_tokens_seen": 340059856, "step": 8255, "train_runtime": 31872.7696, "train_tokens_per_second": 10669.291 }, { "epoch": 0.5561540533261513, "grad_norm": 1.1684921795415113, "learning_rate": 8.210741165773238e-06, "loss": 0.39026308059692383, "num_input_tokens_seen": 340276848, "step": 8260, "train_runtime": 31890.6936, "train_tokens_per_second": 10670.099 }, { "epoch": 0.5564907083221114, "grad_norm": 0.6985913169123413, "learning_rate": 8.208713815138476e-06, "loss": 0.36422252655029297, "num_input_tokens_seen": 340492520, "step": 8265, "train_runtime": 31910.0029, "train_tokens_per_second": 10670.401 }, { "epoch": 0.5568273633180716, "grad_norm": 0.6460867915814267, "learning_rate": 8.20668556719713e-06, "loss": 0.3613330841064453, "num_input_tokens_seen": 340688384, "step": 8270, "train_runtime": 31928.6665, "train_tokens_per_second": 10670.298 }, { "epoch": 0.5571640183140317, "grad_norm": 0.795422003225037, "learning_rate": 8.204656422516388e-06, "loss": 0.3512824773788452, "num_input_tokens_seen": 340888544, "step": 8275, "train_runtime": 31946.653, "train_tokens_per_second": 10670.556 }, { "epoch": 0.5575006733099919, "grad_norm": 0.7774147091717661, "learning_rate": 8.2026263816637e-06, "loss": 0.38039226531982423, "num_input_tokens_seen": 341083632, "step": 8280, "train_runtime": 31966.2849, "train_tokens_per_second": 10670.105 }, { "epoch": 0.557837328305952, "grad_norm": 0.7413667536614827, "learning_rate": 8.200595445206753e-06, "loss": 0.3830323457717896, "num_input_tokens_seen": 341289440, "step": 8285, "train_runtime": 31984.7176, "train_tokens_per_second": 10670.391 }, { "epoch": 0.5581739833019121, "grad_norm": 0.7660359123699313, "learning_rate": 8.198563613713497e-06, "loss": 0.3663779258728027, "num_input_tokens_seen": 341487504, "step": 8290, "train_runtime": 32003.9181, "train_tokens_per_second": 10670.178 }, { "epoch": 0.5585106382978723, "grad_norm": 0.7218554073951191, "learning_rate": 8.196530887752127e-06, "loss": 0.3662185907363892, "num_input_tokens_seen": 341697312, "step": 8295, "train_runtime": 32022.5794, "train_tokens_per_second": 10670.512 }, { "epoch": 0.5588472932938324, "grad_norm": 0.7811199857662576, "learning_rate": 8.194497267891086e-06, "loss": 0.37457871437072754, "num_input_tokens_seen": 341906992, "step": 8300, "train_runtime": 32041.5067, "train_tokens_per_second": 10670.753 }, { "epoch": 0.5591839482897926, "grad_norm": 0.718216922209834, "learning_rate": 8.19246275469907e-06, "loss": 0.38263323307037356, "num_input_tokens_seen": 342120672, "step": 8305, "train_runtime": 32061.4293, "train_tokens_per_second": 10670.787 }, { "epoch": 0.5595206032857528, "grad_norm": 0.6529981329372592, "learning_rate": 8.190427348745027e-06, "loss": 0.3776914119720459, "num_input_tokens_seen": 342330856, "step": 8310, "train_runtime": 32080.9532, "train_tokens_per_second": 10670.844 }, { "epoch": 0.559857258281713, "grad_norm": 0.6841896460195095, "learning_rate": 8.188391050598146e-06, "loss": 0.36792716979980467, "num_input_tokens_seen": 342548304, "step": 8315, "train_runtime": 32099.7032, "train_tokens_per_second": 10671.385 }, { "epoch": 0.5601939132776731, "grad_norm": 0.7491040830739898, "learning_rate": 8.186353860827878e-06, "loss": 0.37871298789978025, "num_input_tokens_seen": 342745344, "step": 8320, "train_runtime": 32120.7063, "train_tokens_per_second": 10670.542 }, { "epoch": 0.5605305682736332, "grad_norm": 0.6424344562396861, "learning_rate": 8.184315780003911e-06, "loss": 0.3730928897857666, "num_input_tokens_seen": 342955656, "step": 8325, "train_runtime": 32140.0807, "train_tokens_per_second": 10670.653 }, { "epoch": 0.5608672232695934, "grad_norm": 0.6535552101457438, "learning_rate": 8.182276808696193e-06, "loss": 0.41115198135375974, "num_input_tokens_seen": 343151256, "step": 8330, "train_runtime": 32158.5819, "train_tokens_per_second": 10670.597 }, { "epoch": 0.5612038782655535, "grad_norm": 0.5917227620541127, "learning_rate": 8.18023694747491e-06, "loss": 0.3865976810455322, "num_input_tokens_seen": 343364504, "step": 8335, "train_runtime": 32176.8454, "train_tokens_per_second": 10671.167 }, { "epoch": 0.5615405332615137, "grad_norm": 0.7573640096285263, "learning_rate": 8.178196196910508e-06, "loss": 0.36875262260437014, "num_input_tokens_seen": 343577944, "step": 8340, "train_runtime": 32195.7279, "train_tokens_per_second": 10671.538 }, { "epoch": 0.5618771882574738, "grad_norm": 0.7375652028023791, "learning_rate": 8.176154557573672e-06, "loss": 0.3993030071258545, "num_input_tokens_seen": 343794816, "step": 8345, "train_runtime": 32213.4234, "train_tokens_per_second": 10672.409 }, { "epoch": 0.5622138432534339, "grad_norm": 0.6699090583240205, "learning_rate": 8.174112030035344e-06, "loss": 0.371988582611084, "num_input_tokens_seen": 344009392, "step": 8350, "train_runtime": 32232.2706, "train_tokens_per_second": 10672.825 }, { "epoch": 0.5625504982493941, "grad_norm": 0.7910975188677816, "learning_rate": 8.172068614866707e-06, "loss": 0.36304872035980223, "num_input_tokens_seen": 344205568, "step": 8355, "train_runtime": 32249.9254, "train_tokens_per_second": 10673.066 }, { "epoch": 0.5628871532453542, "grad_norm": 0.7183734010780234, "learning_rate": 8.170024312639197e-06, "loss": 0.40297975540161135, "num_input_tokens_seen": 344420928, "step": 8360, "train_runtime": 32270.2654, "train_tokens_per_second": 10673.012 }, { "epoch": 0.5632238082413143, "grad_norm": 0.6892974277215674, "learning_rate": 8.167979123924496e-06, "loss": 0.3868196964263916, "num_input_tokens_seen": 344628960, "step": 8365, "train_runtime": 32289.4641, "train_tokens_per_second": 10673.109 }, { "epoch": 0.5635604632372745, "grad_norm": 0.724554148987452, "learning_rate": 8.165933049294537e-06, "loss": 0.4111189842224121, "num_input_tokens_seen": 344834336, "step": 8370, "train_runtime": 32309.2421, "train_tokens_per_second": 10672.932 }, { "epoch": 0.5638971182332346, "grad_norm": 0.7098869878561741, "learning_rate": 8.163886089321493e-06, "loss": 0.36889166831970216, "num_input_tokens_seen": 345050232, "step": 8375, "train_runtime": 32329.7815, "train_tokens_per_second": 10672.829 }, { "epoch": 0.5642337732291948, "grad_norm": 0.6268475341434256, "learning_rate": 8.161838244577795e-06, "loss": 0.3602753639221191, "num_input_tokens_seen": 345257856, "step": 8380, "train_runtime": 32349.544, "train_tokens_per_second": 10672.727 }, { "epoch": 0.5645704282251549, "grad_norm": 0.6970865043024698, "learning_rate": 8.159789515636114e-06, "loss": 0.35967538356781004, "num_input_tokens_seen": 345463208, "step": 8385, "train_runtime": 32369.4033, "train_tokens_per_second": 10672.523 }, { "epoch": 0.564907083221115, "grad_norm": 0.7672349602076804, "learning_rate": 8.15773990306937e-06, "loss": 0.40271682739257814, "num_input_tokens_seen": 345650160, "step": 8390, "train_runtime": 32388.2749, "train_tokens_per_second": 10672.077 }, { "epoch": 0.5652437382170752, "grad_norm": 0.7769389093670405, "learning_rate": 8.155689407450732e-06, "loss": 0.38317346572875977, "num_input_tokens_seen": 345860992, "step": 8395, "train_runtime": 32407.1313, "train_tokens_per_second": 10672.373 }, { "epoch": 0.5655803932130353, "grad_norm": 0.7124897790186836, "learning_rate": 8.153638029353615e-06, "loss": 0.3718392848968506, "num_input_tokens_seen": 346056608, "step": 8400, "train_runtime": 32427.9903, "train_tokens_per_second": 10671.54 }, { "epoch": 0.5659170482089955, "grad_norm": 0.7051847796300645, "learning_rate": 8.151585769351678e-06, "loss": 0.4200584888458252, "num_input_tokens_seen": 346267696, "step": 8405, "train_runtime": 32446.295, "train_tokens_per_second": 10672.026 }, { "epoch": 0.5662537032049556, "grad_norm": 0.803196482832258, "learning_rate": 8.149532628018833e-06, "loss": 0.393517804145813, "num_input_tokens_seen": 346464304, "step": 8410, "train_runtime": 32465.0133, "train_tokens_per_second": 10671.929 }, { "epoch": 0.5665903582009157, "grad_norm": 0.7492605879218494, "learning_rate": 8.147478605929228e-06, "loss": 0.37380454540252683, "num_input_tokens_seen": 346680512, "step": 8415, "train_runtime": 32482.5431, "train_tokens_per_second": 10672.825 }, { "epoch": 0.5669270131968759, "grad_norm": 0.6691708416347748, "learning_rate": 8.145423703657269e-06, "loss": 0.3682526111602783, "num_input_tokens_seen": 346890656, "step": 8420, "train_runtime": 32502.6369, "train_tokens_per_second": 10672.693 }, { "epoch": 0.567263668192836, "grad_norm": 0.7302308483054962, "learning_rate": 8.143367921777601e-06, "loss": 0.388266921043396, "num_input_tokens_seen": 347102680, "step": 8425, "train_runtime": 32521.1326, "train_tokens_per_second": 10673.142 }, { "epoch": 0.5676003231887962, "grad_norm": 0.7121439542291418, "learning_rate": 8.141311260865117e-06, "loss": 0.4261192321777344, "num_input_tokens_seen": 347316056, "step": 8430, "train_runtime": 32538.7603, "train_tokens_per_second": 10673.918 }, { "epoch": 0.5679369781847563, "grad_norm": 0.7340324931996638, "learning_rate": 8.139253721494956e-06, "loss": 0.4132406234741211, "num_input_tokens_seen": 347516896, "step": 8435, "train_runtime": 32558.2167, "train_tokens_per_second": 10673.708 }, { "epoch": 0.5682736331807164, "grad_norm": 0.6528834160391311, "learning_rate": 8.137195304242502e-06, "loss": 0.36935813426971437, "num_input_tokens_seen": 347726816, "step": 8440, "train_runtime": 32577.8379, "train_tokens_per_second": 10673.723 }, { "epoch": 0.5686102881766766, "grad_norm": 0.6526476596349174, "learning_rate": 8.135136009683387e-06, "loss": 0.3699324131011963, "num_input_tokens_seen": 347930512, "step": 8445, "train_runtime": 32595.4547, "train_tokens_per_second": 10674.203 }, { "epoch": 0.5689469431726367, "grad_norm": 0.7345907426825361, "learning_rate": 8.13307583839348e-06, "loss": 0.38436386585235593, "num_input_tokens_seen": 348142056, "step": 8450, "train_runtime": 32614.3178, "train_tokens_per_second": 10674.516 }, { "epoch": 0.5692835981685969, "grad_norm": 0.7006585436821328, "learning_rate": 8.131014790948908e-06, "loss": 0.3924187183380127, "num_input_tokens_seen": 348350544, "step": 8455, "train_runtime": 32633.9503, "train_tokens_per_second": 10674.483 }, { "epoch": 0.569620253164557, "grad_norm": 0.7831190561119581, "learning_rate": 8.128952867926035e-06, "loss": 0.4248223781585693, "num_input_tokens_seen": 348552376, "step": 8460, "train_runtime": 32651.4903, "train_tokens_per_second": 10674.93 }, { "epoch": 0.5699569081605171, "grad_norm": 0.7014143683888969, "learning_rate": 8.126890069901468e-06, "loss": 0.39351739883422854, "num_input_tokens_seen": 348757784, "step": 8465, "train_runtime": 32669.3259, "train_tokens_per_second": 10675.39 }, { "epoch": 0.5702935631564773, "grad_norm": 0.685633215764111, "learning_rate": 8.124826397452064e-06, "loss": 0.37531936168670654, "num_input_tokens_seen": 348972224, "step": 8470, "train_runtime": 32688.5148, "train_tokens_per_second": 10675.683 }, { "epoch": 0.5706302181524374, "grad_norm": 0.6423246980023493, "learning_rate": 8.122761851154923e-06, "loss": 0.37507336139678954, "num_input_tokens_seen": 349175680, "step": 8475, "train_runtime": 32707.0493, "train_tokens_per_second": 10675.854 }, { "epoch": 0.5709668731483976, "grad_norm": 0.7491395649104411, "learning_rate": 8.120696431587387e-06, "loss": 0.3754862070083618, "num_input_tokens_seen": 349381024, "step": 8480, "train_runtime": 32726.0717, "train_tokens_per_second": 10675.923 }, { "epoch": 0.5713035281443577, "grad_norm": 0.6311765996429334, "learning_rate": 8.118630139327046e-06, "loss": 0.3653577327728271, "num_input_tokens_seen": 349585136, "step": 8485, "train_runtime": 32745.4578, "train_tokens_per_second": 10675.836 }, { "epoch": 0.5716401831403178, "grad_norm": 0.6440208010609502, "learning_rate": 8.116562974951731e-06, "loss": 0.39571199417114256, "num_input_tokens_seen": 349799568, "step": 8490, "train_runtime": 32765.2999, "train_tokens_per_second": 10675.915 }, { "epoch": 0.571976838136278, "grad_norm": 0.654513138448306, "learning_rate": 8.11449493903952e-06, "loss": 0.381154203414917, "num_input_tokens_seen": 350014464, "step": 8495, "train_runtime": 32784.469, "train_tokens_per_second": 10676.228 }, { "epoch": 0.5723134931322381, "grad_norm": 0.6822657422810218, "learning_rate": 8.112426032168727e-06, "loss": 0.3957352161407471, "num_input_tokens_seen": 350217552, "step": 8500, "train_runtime": 32803.3362, "train_tokens_per_second": 10676.278 }, { "epoch": 0.5726501481281983, "grad_norm": 0.6789806117641055, "learning_rate": 8.11035625491792e-06, "loss": 0.3575897693634033, "num_input_tokens_seen": 350411728, "step": 8505, "train_runtime": 32821.5171, "train_tokens_per_second": 10676.281 }, { "epoch": 0.5729868031241584, "grad_norm": 0.7475534654241546, "learning_rate": 8.108285607865907e-06, "loss": 0.3788754463195801, "num_input_tokens_seen": 350612104, "step": 8510, "train_runtime": 32841.1516, "train_tokens_per_second": 10675.999 }, { "epoch": 0.5733234581201185, "grad_norm": 0.6981918096351849, "learning_rate": 8.106214091591731e-06, "loss": 0.3683158874511719, "num_input_tokens_seen": 350821936, "step": 8515, "train_runtime": 32859.5293, "train_tokens_per_second": 10676.414 }, { "epoch": 0.5736601131160787, "grad_norm": 0.7038493257330197, "learning_rate": 8.104141706674693e-06, "loss": 0.34744577407836913, "num_input_tokens_seen": 351034112, "step": 8520, "train_runtime": 32878.9892, "train_tokens_per_second": 10676.548 }, { "epoch": 0.5739967681120388, "grad_norm": 0.7356529792497426, "learning_rate": 8.102068453694324e-06, "loss": 0.40432987213134763, "num_input_tokens_seen": 351242032, "step": 8525, "train_runtime": 32897.9668, "train_tokens_per_second": 10676.709 }, { "epoch": 0.574333423107999, "grad_norm": 0.6886424371559229, "learning_rate": 8.099994333230404e-06, "loss": 0.3948256254196167, "num_input_tokens_seen": 351441024, "step": 8530, "train_runtime": 32917.123, "train_tokens_per_second": 10676.541 }, { "epoch": 0.5746700781039591, "grad_norm": 0.7944126994168671, "learning_rate": 8.097919345862952e-06, "loss": 0.3911997556686401, "num_input_tokens_seen": 351629680, "step": 8535, "train_runtime": 32934.6181, "train_tokens_per_second": 10676.598 }, { "epoch": 0.5750067330999192, "grad_norm": 0.7094283994584297, "learning_rate": 8.095843492172235e-06, "loss": 0.39789113998413084, "num_input_tokens_seen": 351832520, "step": 8540, "train_runtime": 32953.0906, "train_tokens_per_second": 10676.769 }, { "epoch": 0.5753433880958794, "grad_norm": 0.7573392035035489, "learning_rate": 8.093766772738758e-06, "loss": 0.3275596618652344, "num_input_tokens_seen": 352035208, "step": 8545, "train_runtime": 32971.1025, "train_tokens_per_second": 10677.083 }, { "epoch": 0.5756800430918395, "grad_norm": 0.7399874469844634, "learning_rate": 8.091689188143267e-06, "loss": 0.39560346603393554, "num_input_tokens_seen": 352237024, "step": 8550, "train_runtime": 32989.8048, "train_tokens_per_second": 10677.148 }, { "epoch": 0.5760166980877997, "grad_norm": 0.7420810723160776, "learning_rate": 8.089610738966754e-06, "loss": 0.3856737375259399, "num_input_tokens_seen": 352432096, "step": 8555, "train_runtime": 33009.7981, "train_tokens_per_second": 10676.59 }, { "epoch": 0.5763533530837598, "grad_norm": 0.8040227521812626, "learning_rate": 8.08753142579045e-06, "loss": 0.40883579254150393, "num_input_tokens_seen": 352636480, "step": 8560, "train_runtime": 33028.8836, "train_tokens_per_second": 10676.609 }, { "epoch": 0.5766900080797199, "grad_norm": 0.6622026988921713, "learning_rate": 8.085451249195828e-06, "loss": 0.36812329292297363, "num_input_tokens_seen": 352857008, "step": 8565, "train_runtime": 33047.5149, "train_tokens_per_second": 10677.263 }, { "epoch": 0.5770266630756801, "grad_norm": 0.6899647104683108, "learning_rate": 8.083370209764603e-06, "loss": 0.38667616844177244, "num_input_tokens_seen": 353064240, "step": 8570, "train_runtime": 33065.6224, "train_tokens_per_second": 10677.683 }, { "epoch": 0.5773633180716402, "grad_norm": 0.727350932666227, "learning_rate": 8.081288308078731e-06, "loss": 0.3959543228149414, "num_input_tokens_seen": 353282216, "step": 8575, "train_runtime": 33084.0807, "train_tokens_per_second": 10678.314 }, { "epoch": 0.5776999730676003, "grad_norm": 0.6614225595664717, "learning_rate": 8.07920554472041e-06, "loss": 0.35960073471069337, "num_input_tokens_seen": 353494864, "step": 8580, "train_runtime": 33102.8092, "train_tokens_per_second": 10678.697 }, { "epoch": 0.5780366280635605, "grad_norm": 0.7384633115840639, "learning_rate": 8.077121920272075e-06, "loss": 0.3779592752456665, "num_input_tokens_seen": 353708272, "step": 8585, "train_runtime": 33121.118, "train_tokens_per_second": 10679.237 }, { "epoch": 0.5783732830595206, "grad_norm": 0.6555312427675432, "learning_rate": 8.07503743531641e-06, "loss": 0.3475764751434326, "num_input_tokens_seen": 353909624, "step": 8590, "train_runtime": 33141.6213, "train_tokens_per_second": 10678.706 }, { "epoch": 0.5787099380554808, "grad_norm": 0.6476576129015406, "learning_rate": 8.072952090436328e-06, "loss": 0.3478261470794678, "num_input_tokens_seen": 354122280, "step": 8595, "train_runtime": 33159.5903, "train_tokens_per_second": 10679.332 }, { "epoch": 0.5790465930514409, "grad_norm": 0.7670562706009492, "learning_rate": 8.070865886214996e-06, "loss": 0.382037615776062, "num_input_tokens_seen": 354329480, "step": 8600, "train_runtime": 33178.4383, "train_tokens_per_second": 10679.51 }, { "epoch": 0.579383248047401, "grad_norm": 0.7609655423329864, "learning_rate": 8.06877882323581e-06, "loss": 0.37614448070526124, "num_input_tokens_seen": 354534656, "step": 8605, "train_runtime": 33196.9638, "train_tokens_per_second": 10679.731 }, { "epoch": 0.5797199030433612, "grad_norm": 0.6370279235705835, "learning_rate": 8.066690902082413e-06, "loss": 0.36131627559661866, "num_input_tokens_seen": 354744136, "step": 8610, "train_runtime": 33216.6942, "train_tokens_per_second": 10679.694 }, { "epoch": 0.5800565580393213, "grad_norm": 0.6927198588774607, "learning_rate": 8.064602123338683e-06, "loss": 0.4198298931121826, "num_input_tokens_seen": 354963792, "step": 8615, "train_runtime": 33235.042, "train_tokens_per_second": 10680.407 }, { "epoch": 0.5803932130352815, "grad_norm": 0.7020957035529992, "learning_rate": 8.06251248758874e-06, "loss": 0.37006592750549316, "num_input_tokens_seen": 355164904, "step": 8620, "train_runtime": 33254.5986, "train_tokens_per_second": 10680.174 }, { "epoch": 0.5807298680312416, "grad_norm": 0.73749419700285, "learning_rate": 8.060421995416949e-06, "loss": 0.4120265007019043, "num_input_tokens_seen": 355361568, "step": 8625, "train_runtime": 33274.5445, "train_tokens_per_second": 10679.682 }, { "epoch": 0.5810665230272017, "grad_norm": 0.7784131389085519, "learning_rate": 8.058330647407904e-06, "loss": 0.3903190135955811, "num_input_tokens_seen": 355561400, "step": 8630, "train_runtime": 33293.878, "train_tokens_per_second": 10679.483 }, { "epoch": 0.5814031780231619, "grad_norm": 0.8751256767607729, "learning_rate": 8.056238444146445e-06, "loss": 0.4059361457824707, "num_input_tokens_seen": 355764208, "step": 8635, "train_runtime": 33313.0929, "train_tokens_per_second": 10679.411 }, { "epoch": 0.581739833019122, "grad_norm": 0.7262716738105813, "learning_rate": 8.054145386217652e-06, "loss": 0.35751967430114745, "num_input_tokens_seen": 355973232, "step": 8640, "train_runtime": 33331.4635, "train_tokens_per_second": 10679.796 }, { "epoch": 0.5820764880150822, "grad_norm": 0.7333009157438761, "learning_rate": 8.05205147420684e-06, "loss": 0.36164517402648927, "num_input_tokens_seen": 356174840, "step": 8645, "train_runtime": 33349.9176, "train_tokens_per_second": 10679.932 }, { "epoch": 0.5824131430110423, "grad_norm": 1.1418917738578478, "learning_rate": 8.049956708699567e-06, "loss": 0.41550607681274415, "num_input_tokens_seen": 356377592, "step": 8650, "train_runtime": 33367.9299, "train_tokens_per_second": 10680.243 }, { "epoch": 0.5827497980070024, "grad_norm": 0.7586322925651914, "learning_rate": 8.047861090281623e-06, "loss": 0.4049872398376465, "num_input_tokens_seen": 356578984, "step": 8655, "train_runtime": 33387.9044, "train_tokens_per_second": 10679.885 }, { "epoch": 0.5830864530029626, "grad_norm": 0.6596248253282729, "learning_rate": 8.045764619539047e-06, "loss": 0.3652834415435791, "num_input_tokens_seen": 356792088, "step": 8660, "train_runtime": 33407.7569, "train_tokens_per_second": 10679.918 }, { "epoch": 0.5834231079989227, "grad_norm": 0.6386054517829952, "learning_rate": 8.043667297058106e-06, "loss": 0.3582956790924072, "num_input_tokens_seen": 356990968, "step": 8665, "train_runtime": 33427.1527, "train_tokens_per_second": 10679.67 }, { "epoch": 0.5837597629948829, "grad_norm": 0.7443253566302419, "learning_rate": 8.04156912342531e-06, "loss": 0.39299492835998534, "num_input_tokens_seen": 357198920, "step": 8670, "train_runtime": 33445.5823, "train_tokens_per_second": 10680.003 }, { "epoch": 0.584096417990843, "grad_norm": 0.9580715189684279, "learning_rate": 8.03947009922741e-06, "loss": 0.37804853916168213, "num_input_tokens_seen": 357404944, "step": 8675, "train_runtime": 33464.9245, "train_tokens_per_second": 10679.987 }, { "epoch": 0.5844330729868031, "grad_norm": 0.7750566007342238, "learning_rate": 8.037370225051387e-06, "loss": 0.4227855682373047, "num_input_tokens_seen": 357607344, "step": 8680, "train_runtime": 33485.2566, "train_tokens_per_second": 10679.546 }, { "epoch": 0.5847697279827633, "grad_norm": 0.716076657328966, "learning_rate": 8.035269501484467e-06, "loss": 0.37400212287902834, "num_input_tokens_seen": 357818152, "step": 8685, "train_runtime": 33504.1212, "train_tokens_per_second": 10679.825 }, { "epoch": 0.5851063829787234, "grad_norm": 0.7095486290442463, "learning_rate": 8.03316792911411e-06, "loss": 0.40728139877319336, "num_input_tokens_seen": 358021024, "step": 8690, "train_runtime": 33522.9841, "train_tokens_per_second": 10679.867 }, { "epoch": 0.5854430379746836, "grad_norm": 0.6401833668589523, "learning_rate": 8.031065508528011e-06, "loss": 0.3666227340698242, "num_input_tokens_seen": 358233760, "step": 8695, "train_runtime": 33541.4207, "train_tokens_per_second": 10680.339 }, { "epoch": 0.5857796929706437, "grad_norm": 0.7049179907411145, "learning_rate": 8.028962240314111e-06, "loss": 0.3695788621902466, "num_input_tokens_seen": 358444104, "step": 8700, "train_runtime": 33560.9726, "train_tokens_per_second": 10680.385 }, { "epoch": 0.5861163479666038, "grad_norm": 0.6972623555500609, "learning_rate": 8.026858125060577e-06, "loss": 0.3930441617965698, "num_input_tokens_seen": 358650984, "step": 8705, "train_runtime": 33581.4323, "train_tokens_per_second": 10680.038 }, { "epoch": 0.586453002962564, "grad_norm": 0.6775995447609278, "learning_rate": 8.024753163355821e-06, "loss": 0.4240133762359619, "num_input_tokens_seen": 358861360, "step": 8710, "train_runtime": 33602.0065, "train_tokens_per_second": 10679.76 }, { "epoch": 0.5867896579585241, "grad_norm": 0.6739919587142325, "learning_rate": 8.022647355788489e-06, "loss": 0.3720284938812256, "num_input_tokens_seen": 359067936, "step": 8715, "train_runtime": 33620.8221, "train_tokens_per_second": 10679.927 }, { "epoch": 0.5871263129544843, "grad_norm": 0.7090846822804808, "learning_rate": 8.02054070294746e-06, "loss": 0.4087704658508301, "num_input_tokens_seen": 359273376, "step": 8720, "train_runtime": 33640.8891, "train_tokens_per_second": 10679.664 }, { "epoch": 0.5874629679504444, "grad_norm": 0.6570060958989412, "learning_rate": 8.018433205421859e-06, "loss": 0.3643190860748291, "num_input_tokens_seen": 359488480, "step": 8725, "train_runtime": 33660.7002, "train_tokens_per_second": 10679.768 }, { "epoch": 0.5877996229464045, "grad_norm": 0.7875328445226999, "learning_rate": 8.016324863801036e-06, "loss": 0.39802565574646, "num_input_tokens_seen": 359697744, "step": 8730, "train_runtime": 33679.9274, "train_tokens_per_second": 10679.885 }, { "epoch": 0.5881362779423647, "grad_norm": 0.678540299805327, "learning_rate": 8.014215678674581e-06, "loss": 0.40113105773925783, "num_input_tokens_seen": 359908632, "step": 8735, "train_runtime": 33699.4557, "train_tokens_per_second": 10679.954 }, { "epoch": 0.5884729329383248, "grad_norm": 0.6178356140230221, "learning_rate": 8.012105650632325e-06, "loss": 0.37025182247161864, "num_input_tokens_seen": 360112184, "step": 8740, "train_runtime": 33719.3582, "train_tokens_per_second": 10679.687 }, { "epoch": 0.588809587934285, "grad_norm": 0.6995816058906507, "learning_rate": 8.009994780264328e-06, "loss": 0.39139251708984374, "num_input_tokens_seen": 360298832, "step": 8745, "train_runtime": 33738.3788, "train_tokens_per_second": 10679.198 }, { "epoch": 0.5891462429302451, "grad_norm": 0.754993853668207, "learning_rate": 8.00788306816089e-06, "loss": 0.38045287132263184, "num_input_tokens_seen": 360503168, "step": 8750, "train_runtime": 33756.8014, "train_tokens_per_second": 10679.423 }, { "epoch": 0.5894828979262052, "grad_norm": 0.7365022790087211, "learning_rate": 8.005770514912543e-06, "loss": 0.3976957082748413, "num_input_tokens_seen": 360715216, "step": 8755, "train_runtime": 33777.2301, "train_tokens_per_second": 10679.242 }, { "epoch": 0.5898195529221654, "grad_norm": 0.6960597102694192, "learning_rate": 8.003657121110055e-06, "loss": 0.3813591241836548, "num_input_tokens_seen": 360933920, "step": 8760, "train_runtime": 33795.0422, "train_tokens_per_second": 10680.085 }, { "epoch": 0.5901562079181255, "grad_norm": 0.7238544057198485, "learning_rate": 8.001542887344432e-06, "loss": 0.37199769020080564, "num_input_tokens_seen": 361139720, "step": 8765, "train_runtime": 33813.0151, "train_tokens_per_second": 10680.494 }, { "epoch": 0.5904928629140856, "grad_norm": 0.7136803087302842, "learning_rate": 7.999427814206911e-06, "loss": 0.3959347248077393, "num_input_tokens_seen": 361344568, "step": 8770, "train_runtime": 33831.3586, "train_tokens_per_second": 10680.758 }, { "epoch": 0.5908295179100458, "grad_norm": 0.7702338423334137, "learning_rate": 7.997311902288968e-06, "loss": 0.3575681209564209, "num_input_tokens_seen": 361553688, "step": 8775, "train_runtime": 33850.2413, "train_tokens_per_second": 10680.978 }, { "epoch": 0.5911661729060059, "grad_norm": 0.8164247800494178, "learning_rate": 7.995195152182307e-06, "loss": 0.3560000419616699, "num_input_tokens_seen": 361746560, "step": 8780, "train_runtime": 33869.7096, "train_tokens_per_second": 10680.533 }, { "epoch": 0.5915028279019661, "grad_norm": 0.6459520573786426, "learning_rate": 7.993077564478875e-06, "loss": 0.35982823371887207, "num_input_tokens_seen": 361959552, "step": 8785, "train_runtime": 33888.8127, "train_tokens_per_second": 10680.798 }, { "epoch": 0.5918394828979262, "grad_norm": 0.7321305450675133, "learning_rate": 7.990959139770844e-06, "loss": 0.39851906299591067, "num_input_tokens_seen": 362177640, "step": 8790, "train_runtime": 33907.469, "train_tokens_per_second": 10681.353 }, { "epoch": 0.5921761378938863, "grad_norm": 0.7098682451487245, "learning_rate": 7.988839878650628e-06, "loss": 0.3800812244415283, "num_input_tokens_seen": 362392128, "step": 8795, "train_runtime": 33928.4291, "train_tokens_per_second": 10681.076 }, { "epoch": 0.5925127928898465, "grad_norm": 0.7714224867172694, "learning_rate": 7.986719781710872e-06, "loss": 0.3955139875411987, "num_input_tokens_seen": 362606352, "step": 8800, "train_runtime": 33949.9243, "train_tokens_per_second": 10680.623 }, { "epoch": 0.5928494478858066, "grad_norm": 0.721571202791747, "learning_rate": 7.984598849544452e-06, "loss": 0.37847580909729006, "num_input_tokens_seen": 362810336, "step": 8805, "train_runtime": 33968.9908, "train_tokens_per_second": 10680.633 }, { "epoch": 0.5931861028817668, "grad_norm": 0.7530562562631442, "learning_rate": 7.98247708274448e-06, "loss": 0.3917290687561035, "num_input_tokens_seen": 363013936, "step": 8810, "train_runtime": 33988.1432, "train_tokens_per_second": 10680.605 }, { "epoch": 0.5935227578777269, "grad_norm": 0.9001811210379538, "learning_rate": 7.980354481904303e-06, "loss": 0.4165827751159668, "num_input_tokens_seen": 363224616, "step": 8815, "train_runtime": 34005.9321, "train_tokens_per_second": 10681.213 }, { "epoch": 0.593859412873687, "grad_norm": 0.7687353338561713, "learning_rate": 7.978231047617498e-06, "loss": 0.4087789535522461, "num_input_tokens_seen": 363427960, "step": 8820, "train_runtime": 34026.0113, "train_tokens_per_second": 10680.886 }, { "epoch": 0.5941960678696472, "grad_norm": 0.7368485659685818, "learning_rate": 7.976106780477878e-06, "loss": 0.40363273620605467, "num_input_tokens_seen": 363639672, "step": 8825, "train_runtime": 34044.9817, "train_tokens_per_second": 10681.153 }, { "epoch": 0.5945327228656073, "grad_norm": 0.7008447333172573, "learning_rate": 7.973981681079487e-06, "loss": 0.3708693504333496, "num_input_tokens_seen": 363840120, "step": 8830, "train_runtime": 34063.9295, "train_tokens_per_second": 10681.097 }, { "epoch": 0.5948693778615675, "grad_norm": 0.7453452818576828, "learning_rate": 7.971855750016603e-06, "loss": 0.38704941272735593, "num_input_tokens_seen": 364043944, "step": 8835, "train_runtime": 34082.5078, "train_tokens_per_second": 10681.255 }, { "epoch": 0.5952060328575276, "grad_norm": 0.7164720503175007, "learning_rate": 7.969728987883734e-06, "loss": 0.39131555557250974, "num_input_tokens_seen": 364251952, "step": 8840, "train_runtime": 34103.1091, "train_tokens_per_second": 10680.902 }, { "epoch": 0.5955426878534877, "grad_norm": 0.809147957677313, "learning_rate": 7.967601395275624e-06, "loss": 0.3839267253875732, "num_input_tokens_seen": 364458952, "step": 8845, "train_runtime": 34123.4325, "train_tokens_per_second": 10680.606 }, { "epoch": 0.5958793428494479, "grad_norm": 0.6048080989418931, "learning_rate": 7.965472972787247e-06, "loss": 0.3630438089370728, "num_input_tokens_seen": 364666328, "step": 8850, "train_runtime": 34142.1347, "train_tokens_per_second": 10680.83 }, { "epoch": 0.596215997845408, "grad_norm": 0.7071496419269568, "learning_rate": 7.963343721013808e-06, "loss": 0.37535576820373534, "num_input_tokens_seen": 364884704, "step": 8855, "train_runtime": 34159.9399, "train_tokens_per_second": 10681.655 }, { "epoch": 0.5965526528413682, "grad_norm": 0.6804011333666865, "learning_rate": 7.961213640550748e-06, "loss": 0.38644859790802, "num_input_tokens_seen": 365095488, "step": 8860, "train_runtime": 34178.8535, "train_tokens_per_second": 10681.911 }, { "epoch": 0.5968893078373283, "grad_norm": 0.6855191507103687, "learning_rate": 7.959082731993736e-06, "loss": 0.36980252265930175, "num_input_tokens_seen": 365300888, "step": 8865, "train_runtime": 34197.3796, "train_tokens_per_second": 10682.131 }, { "epoch": 0.5972259628332884, "grad_norm": 0.7793289234058812, "learning_rate": 7.956950995938673e-06, "loss": 0.37082223892211913, "num_input_tokens_seen": 365500720, "step": 8870, "train_runtime": 34216.3153, "train_tokens_per_second": 10682.06 }, { "epoch": 0.5975626178292486, "grad_norm": 0.7299218714734469, "learning_rate": 7.954818432981694e-06, "loss": 0.39113972187042234, "num_input_tokens_seen": 365695408, "step": 8875, "train_runtime": 34236.5726, "train_tokens_per_second": 10681.426 }, { "epoch": 0.5978992728252087, "grad_norm": 0.7145280637829431, "learning_rate": 7.952685043719162e-06, "loss": 0.36751832962036135, "num_input_tokens_seen": 365905912, "step": 8880, "train_runtime": 34256.9629, "train_tokens_per_second": 10681.213 }, { "epoch": 0.5982359278211689, "grad_norm": 0.7394018207616251, "learning_rate": 7.950550828747672e-06, "loss": 0.3762918472290039, "num_input_tokens_seen": 366115544, "step": 8885, "train_runtime": 34277.4666, "train_tokens_per_second": 10680.939 }, { "epoch": 0.598572582817129, "grad_norm": 0.6658760250992855, "learning_rate": 7.948415788664052e-06, "loss": 0.4145673274993896, "num_input_tokens_seen": 366322512, "step": 8890, "train_runtime": 34295.5906, "train_tokens_per_second": 10681.33 }, { "epoch": 0.5989092378130891, "grad_norm": 0.7652904864281451, "learning_rate": 7.946279924065359e-06, "loss": 0.3763004779815674, "num_input_tokens_seen": 366526456, "step": 8895, "train_runtime": 34313.1222, "train_tokens_per_second": 10681.816 }, { "epoch": 0.5992458928090493, "grad_norm": 0.7223507470714867, "learning_rate": 7.94414323554888e-06, "loss": 0.37641894817352295, "num_input_tokens_seen": 366739984, "step": 8900, "train_runtime": 34331.5753, "train_tokens_per_second": 10682.294 }, { "epoch": 0.5995825478050094, "grad_norm": 0.6863921453967978, "learning_rate": 7.942005723712135e-06, "loss": 0.3781764030456543, "num_input_tokens_seen": 366959168, "step": 8905, "train_runtime": 34349.3434, "train_tokens_per_second": 10683.149 }, { "epoch": 0.5999192028009696, "grad_norm": 0.6805556267540867, "learning_rate": 7.939867389152868e-06, "loss": 0.3582695722579956, "num_input_tokens_seen": 367163928, "step": 8910, "train_runtime": 34366.9013, "train_tokens_per_second": 10683.65 }, { "epoch": 0.6002558577969297, "grad_norm": 0.7326825806341288, "learning_rate": 7.937728232469062e-06, "loss": 0.3937227725982666, "num_input_tokens_seen": 367366200, "step": 8915, "train_runtime": 34386.4917, "train_tokens_per_second": 10683.445 }, { "epoch": 0.6005925127928898, "grad_norm": 0.7464027571217842, "learning_rate": 7.935588254258921e-06, "loss": 0.40627317428588866, "num_input_tokens_seen": 367562456, "step": 8920, "train_runtime": 34405.7804, "train_tokens_per_second": 10683.16 }, { "epoch": 0.60092916778885, "grad_norm": 0.6905662580090001, "learning_rate": 7.933447455120889e-06, "loss": 0.37513582706451415, "num_input_tokens_seen": 367767424, "step": 8925, "train_runtime": 34426.6853, "train_tokens_per_second": 10682.627 }, { "epoch": 0.6012658227848101, "grad_norm": 0.7500964901872476, "learning_rate": 7.931305835653629e-06, "loss": 0.35579466819763184, "num_input_tokens_seen": 367980960, "step": 8930, "train_runtime": 34446.2144, "train_tokens_per_second": 10682.769 }, { "epoch": 0.6016024777807703, "grad_norm": 0.6963597509435614, "learning_rate": 7.929163396456038e-06, "loss": 0.4045404434204102, "num_input_tokens_seen": 368180008, "step": 8935, "train_runtime": 34465.4169, "train_tokens_per_second": 10682.593 }, { "epoch": 0.6019391327767304, "grad_norm": 0.7458502738673317, "learning_rate": 7.927020138127245e-06, "loss": 0.37575862407684324, "num_input_tokens_seen": 368388360, "step": 8940, "train_runtime": 34483.4164, "train_tokens_per_second": 10683.059 }, { "epoch": 0.6022757877726905, "grad_norm": 0.6512414076751148, "learning_rate": 7.924876061266603e-06, "loss": 0.35671272277832033, "num_input_tokens_seen": 368603560, "step": 8945, "train_runtime": 34503.7909, "train_tokens_per_second": 10682.987 }, { "epoch": 0.6026124427686507, "grad_norm": 0.8012775603616388, "learning_rate": 7.922731166473698e-06, "loss": 0.3941660404205322, "num_input_tokens_seen": 368807416, "step": 8950, "train_runtime": 34522.5041, "train_tokens_per_second": 10683.102 }, { "epoch": 0.6029490977646108, "grad_norm": 0.7341222786778199, "learning_rate": 7.920585454348341e-06, "loss": 0.36333608627319336, "num_input_tokens_seen": 369009040, "step": 8955, "train_runtime": 34541.4927, "train_tokens_per_second": 10683.066 }, { "epoch": 0.603285752760571, "grad_norm": 0.6543688160345068, "learning_rate": 7.918438925490578e-06, "loss": 0.3553627490997314, "num_input_tokens_seen": 369220280, "step": 8960, "train_runtime": 34560.0489, "train_tokens_per_second": 10683.442 }, { "epoch": 0.6036224077565311, "grad_norm": 0.7959644037060081, "learning_rate": 7.916291580500672e-06, "loss": 0.37610225677490233, "num_input_tokens_seen": 369425128, "step": 8965, "train_runtime": 34579.8757, "train_tokens_per_second": 10683.24 }, { "epoch": 0.6039590627524912, "grad_norm": 0.7423475391345495, "learning_rate": 7.914143419979127e-06, "loss": 0.3638737201690674, "num_input_tokens_seen": 369637480, "step": 8970, "train_runtime": 34598.5529, "train_tokens_per_second": 10683.611 }, { "epoch": 0.6042957177484514, "grad_norm": 0.6352813948149603, "learning_rate": 7.911994444526667e-06, "loss": 0.34762618541717527, "num_input_tokens_seen": 369845064, "step": 8975, "train_runtime": 34617.26, "train_tokens_per_second": 10683.834 }, { "epoch": 0.6046323727444115, "grad_norm": 0.6193588031534197, "learning_rate": 7.909844654744246e-06, "loss": 0.35239672660827637, "num_input_tokens_seen": 370056424, "step": 8980, "train_runtime": 34635.9415, "train_tokens_per_second": 10684.174 }, { "epoch": 0.6049690277403716, "grad_norm": 0.7076238646298244, "learning_rate": 7.907694051233044e-06, "loss": 0.39432368278503416, "num_input_tokens_seen": 370262848, "step": 8985, "train_runtime": 34654.9084, "train_tokens_per_second": 10684.283 }, { "epoch": 0.6053056827363318, "grad_norm": 0.594454698550676, "learning_rate": 7.905542634594476e-06, "loss": 0.3767405986785889, "num_input_tokens_seen": 370475632, "step": 8990, "train_runtime": 34674.5175, "train_tokens_per_second": 10684.377 }, { "epoch": 0.6056423377322919, "grad_norm": 0.7342828197531732, "learning_rate": 7.903390405430174e-06, "loss": 0.3671229839324951, "num_input_tokens_seen": 370682664, "step": 8995, "train_runtime": 34693.6578, "train_tokens_per_second": 10684.45 }, { "epoch": 0.6059789927282521, "grad_norm": 0.7431813570820578, "learning_rate": 7.901237364342003e-06, "loss": 0.35371582508087157, "num_input_tokens_seen": 370872408, "step": 9000, "train_runtime": 34711.3832, "train_tokens_per_second": 10684.461 }, { "epoch": 0.6063156477242122, "grad_norm": 0.783909559316092, "learning_rate": 7.899083511932053e-06, "loss": 0.357270336151123, "num_input_tokens_seen": 371074848, "step": 9005, "train_runtime": 34730.719, "train_tokens_per_second": 10684.341 }, { "epoch": 0.6066523027201723, "grad_norm": 0.6659348408313628, "learning_rate": 7.896928848802645e-06, "loss": 0.3774899482727051, "num_input_tokens_seen": 371287760, "step": 9010, "train_runtime": 34749.9417, "train_tokens_per_second": 10684.558 }, { "epoch": 0.6069889577161325, "grad_norm": 0.7419972856167415, "learning_rate": 7.894773375556322e-06, "loss": 0.3981044769287109, "num_input_tokens_seen": 371475640, "step": 9015, "train_runtime": 34769.1623, "train_tokens_per_second": 10684.055 }, { "epoch": 0.6073256127120926, "grad_norm": 0.7095653408983298, "learning_rate": 7.892617092795855e-06, "loss": 0.39386069774627686, "num_input_tokens_seen": 371684024, "step": 9020, "train_runtime": 34788.3879, "train_tokens_per_second": 10684.14 }, { "epoch": 0.6076622677080528, "grad_norm": 0.6715533980426941, "learning_rate": 7.890460001124242e-06, "loss": 0.38324432373046874, "num_input_tokens_seen": 371882568, "step": 9025, "train_runtime": 34806.6377, "train_tokens_per_second": 10684.243 }, { "epoch": 0.6079989227040129, "grad_norm": 0.7248170026324937, "learning_rate": 7.888302101144707e-06, "loss": 0.3784316062927246, "num_input_tokens_seen": 372086696, "step": 9030, "train_runtime": 34828.0347, "train_tokens_per_second": 10683.54 }, { "epoch": 0.608335577699973, "grad_norm": 0.6955681217253674, "learning_rate": 7.886143393460699e-06, "loss": 0.3842020988464355, "num_input_tokens_seen": 372302104, "step": 9035, "train_runtime": 34848.0565, "train_tokens_per_second": 10683.583 }, { "epoch": 0.6086722326959332, "grad_norm": 0.6683545654266684, "learning_rate": 7.883983878675895e-06, "loss": 0.36795787811279296, "num_input_tokens_seen": 372521488, "step": 9040, "train_runtime": 34867.9448, "train_tokens_per_second": 10683.781 }, { "epoch": 0.6090088876918933, "grad_norm": 0.671265254080653, "learning_rate": 7.881823557394194e-06, "loss": 0.37367734909057615, "num_input_tokens_seen": 372736720, "step": 9045, "train_runtime": 34887.3385, "train_tokens_per_second": 10684.011 }, { "epoch": 0.6093455426878535, "grad_norm": 0.7368079448626703, "learning_rate": 7.879662430219728e-06, "loss": 0.35792064666748047, "num_input_tokens_seen": 372926688, "step": 9050, "train_runtime": 34908.3923, "train_tokens_per_second": 10683.01 }, { "epoch": 0.6096821976838136, "grad_norm": 0.8082246696702188, "learning_rate": 7.877500497756843e-06, "loss": 0.3974011421203613, "num_input_tokens_seen": 373134760, "step": 9055, "train_runtime": 34928.9478, "train_tokens_per_second": 10682.68 }, { "epoch": 0.6100188526797737, "grad_norm": 0.8608666738053122, "learning_rate": 7.87533776061012e-06, "loss": 0.39512052536010744, "num_input_tokens_seen": 373344424, "step": 9060, "train_runtime": 34949.0781, "train_tokens_per_second": 10682.526 }, { "epoch": 0.6103555076757339, "grad_norm": 0.7087035654579131, "learning_rate": 7.873174219384362e-06, "loss": 0.4006196975708008, "num_input_tokens_seen": 373549896, "step": 9065, "train_runtime": 34967.5333, "train_tokens_per_second": 10682.764 }, { "epoch": 0.610692162671694, "grad_norm": 0.7120049517083847, "learning_rate": 7.871009874684595e-06, "loss": 0.40212059020996094, "num_input_tokens_seen": 373766896, "step": 9070, "train_runtime": 34985.2862, "train_tokens_per_second": 10683.545 }, { "epoch": 0.6110288176676542, "grad_norm": 0.8270273688331299, "learning_rate": 7.868844727116072e-06, "loss": 0.3928108215332031, "num_input_tokens_seen": 373976456, "step": 9075, "train_runtime": 35004.6448, "train_tokens_per_second": 10683.624 }, { "epoch": 0.6113654726636143, "grad_norm": 0.6447654918635664, "learning_rate": 7.866678777284267e-06, "loss": 0.37916572093963624, "num_input_tokens_seen": 374188280, "step": 9080, "train_runtime": 35024.0199, "train_tokens_per_second": 10683.762 }, { "epoch": 0.6117021276595744, "grad_norm": 0.6596069306348011, "learning_rate": 7.864512025794886e-06, "loss": 0.37543227672576907, "num_input_tokens_seen": 374398872, "step": 9085, "train_runtime": 35043.2341, "train_tokens_per_second": 10683.913 }, { "epoch": 0.6120387826555346, "grad_norm": 0.6946024578738255, "learning_rate": 7.86234447325385e-06, "loss": 0.3601562976837158, "num_input_tokens_seen": 374602064, "step": 9090, "train_runtime": 35063.4959, "train_tokens_per_second": 10683.534 }, { "epoch": 0.6123754376514947, "grad_norm": 0.6463167612092304, "learning_rate": 7.860176120267309e-06, "loss": 0.40998544692993166, "num_input_tokens_seen": 374821584, "step": 9095, "train_runtime": 35082.3611, "train_tokens_per_second": 10684.047 }, { "epoch": 0.6127120926474549, "grad_norm": 0.7745915004607594, "learning_rate": 7.858006967441637e-06, "loss": 0.36174712181091306, "num_input_tokens_seen": 375020776, "step": 9100, "train_runtime": 35101.0011, "train_tokens_per_second": 10684.048 }, { "epoch": 0.613048747643415, "grad_norm": 0.868910238454563, "learning_rate": 7.85583701538343e-06, "loss": 0.41002688407897947, "num_input_tokens_seen": 375237208, "step": 9105, "train_runtime": 35121.4461, "train_tokens_per_second": 10683.991 }, { "epoch": 0.6133854026393751, "grad_norm": 0.7754862288035872, "learning_rate": 7.853666264699506e-06, "loss": 0.3649952173233032, "num_input_tokens_seen": 375437680, "step": 9110, "train_runtime": 35143.3036, "train_tokens_per_second": 10683.05 }, { "epoch": 0.6137220576353353, "grad_norm": 0.7045981792584164, "learning_rate": 7.851494715996914e-06, "loss": 0.4119990348815918, "num_input_tokens_seen": 375640880, "step": 9115, "train_runtime": 35164.4428, "train_tokens_per_second": 10682.407 }, { "epoch": 0.6140587126312954, "grad_norm": 0.7023316755545659, "learning_rate": 7.849322369882915e-06, "loss": 0.3678452014923096, "num_input_tokens_seen": 375848488, "step": 9120, "train_runtime": 35183.9048, "train_tokens_per_second": 10682.398 }, { "epoch": 0.6143953676272556, "grad_norm": 0.7076537168122535, "learning_rate": 7.847149226965003e-06, "loss": 0.3497342586517334, "num_input_tokens_seen": 376050224, "step": 9125, "train_runtime": 35204.1996, "train_tokens_per_second": 10681.971 }, { "epoch": 0.6147320226232157, "grad_norm": 0.8045241086527013, "learning_rate": 7.844975287850886e-06, "loss": 0.34809126853942873, "num_input_tokens_seen": 376259040, "step": 9130, "train_runtime": 35222.6494, "train_tokens_per_second": 10682.304 }, { "epoch": 0.6150686776191758, "grad_norm": 0.7086425363409933, "learning_rate": 7.842800553148506e-06, "loss": 0.4028881549835205, "num_input_tokens_seen": 376458504, "step": 9135, "train_runtime": 35241.9626, "train_tokens_per_second": 10682.11 }, { "epoch": 0.615405332615136, "grad_norm": 0.6863338225911964, "learning_rate": 7.840625023466014e-06, "loss": 0.37575531005859375, "num_input_tokens_seen": 376669488, "step": 9140, "train_runtime": 35261.2832, "train_tokens_per_second": 10682.24 }, { "epoch": 0.6157419876110961, "grad_norm": 0.6851873149331802, "learning_rate": 7.838448699411792e-06, "loss": 0.3424068450927734, "num_input_tokens_seen": 376878824, "step": 9145, "train_runtime": 35280.8867, "train_tokens_per_second": 10682.238 }, { "epoch": 0.6160786426070562, "grad_norm": 0.6832782100633992, "learning_rate": 7.836271581594442e-06, "loss": 0.42234344482421876, "num_input_tokens_seen": 377088712, "step": 9150, "train_runtime": 35300.4942, "train_tokens_per_second": 10682.25 }, { "epoch": 0.6164152976030164, "grad_norm": 0.8497581568763334, "learning_rate": 7.834093670622789e-06, "loss": 0.3994917631149292, "num_input_tokens_seen": 377292504, "step": 9155, "train_runtime": 35319.4932, "train_tokens_per_second": 10682.274 }, { "epoch": 0.6167519525989765, "grad_norm": 0.7116783929334697, "learning_rate": 7.831914967105878e-06, "loss": 0.41499671936035154, "num_input_tokens_seen": 377507136, "step": 9160, "train_runtime": 35337.5338, "train_tokens_per_second": 10682.894 }, { "epoch": 0.6170886075949367, "grad_norm": 0.6510190926523447, "learning_rate": 7.829735471652978e-06, "loss": 0.35659902095794677, "num_input_tokens_seen": 377713416, "step": 9165, "train_runtime": 35356.901, "train_tokens_per_second": 10682.877 }, { "epoch": 0.6174252625908968, "grad_norm": 0.8316058283878176, "learning_rate": 7.827555184873575e-06, "loss": 0.38825719356536864, "num_input_tokens_seen": 377922960, "step": 9170, "train_runtime": 35375.1011, "train_tokens_per_second": 10683.304 }, { "epoch": 0.617761917586857, "grad_norm": 0.6403579247422532, "learning_rate": 7.825374107377381e-06, "loss": 0.3606876373291016, "num_input_tokens_seen": 378126648, "step": 9175, "train_runtime": 35395.2667, "train_tokens_per_second": 10682.972 }, { "epoch": 0.6180985725828171, "grad_norm": 0.7671816109372483, "learning_rate": 7.823192239774327e-06, "loss": 0.383701229095459, "num_input_tokens_seen": 378326760, "step": 9180, "train_runtime": 35413.2717, "train_tokens_per_second": 10683.191 }, { "epoch": 0.6184352275787772, "grad_norm": 0.6724820479003994, "learning_rate": 7.821009582674567e-06, "loss": 0.39283089637756347, "num_input_tokens_seen": 378530584, "step": 9185, "train_runtime": 35431.5386, "train_tokens_per_second": 10683.436 }, { "epoch": 0.6187718825747374, "grad_norm": 0.7123076583018698, "learning_rate": 7.818826136688473e-06, "loss": 0.4203207969665527, "num_input_tokens_seen": 378742128, "step": 9190, "train_runtime": 35450.2322, "train_tokens_per_second": 10683.77 }, { "epoch": 0.6191085375706975, "grad_norm": 0.7878476197403009, "learning_rate": 7.816641902426638e-06, "loss": 0.3967305660247803, "num_input_tokens_seen": 378955384, "step": 9195, "train_runtime": 35470.6218, "train_tokens_per_second": 10683.641 }, { "epoch": 0.6194451925666576, "grad_norm": 0.7497769975164732, "learning_rate": 7.814456880499877e-06, "loss": 0.4017162322998047, "num_input_tokens_seen": 379158880, "step": 9200, "train_runtime": 35489.1136, "train_tokens_per_second": 10683.808 }, { "epoch": 0.6197818475626178, "grad_norm": 0.7893605524055224, "learning_rate": 7.812271071519222e-06, "loss": 0.4065096378326416, "num_input_tokens_seen": 379365080, "step": 9205, "train_runtime": 35506.5383, "train_tokens_per_second": 10684.372 }, { "epoch": 0.6201185025585779, "grad_norm": 0.6202575762021965, "learning_rate": 7.810084476095932e-06, "loss": 0.3507330894470215, "num_input_tokens_seen": 379574288, "step": 9210, "train_runtime": 35526.7115, "train_tokens_per_second": 10684.194 }, { "epoch": 0.6204551575545381, "grad_norm": 0.7056500642328266, "learning_rate": 7.807897094841476e-06, "loss": 0.374141263961792, "num_input_tokens_seen": 379772352, "step": 9215, "train_runtime": 35546.0615, "train_tokens_per_second": 10683.95 }, { "epoch": 0.6207918125504982, "grad_norm": 0.7590117610798224, "learning_rate": 7.805708928367555e-06, "loss": 0.36546595096588136, "num_input_tokens_seen": 379968488, "step": 9220, "train_runtime": 35563.9484, "train_tokens_per_second": 10684.092 }, { "epoch": 0.6211284675464583, "grad_norm": 0.72609417651189, "learning_rate": 7.803519977286075e-06, "loss": 0.4028463840484619, "num_input_tokens_seen": 380165168, "step": 9225, "train_runtime": 35583.1292, "train_tokens_per_second": 10683.86 }, { "epoch": 0.6214651225424185, "grad_norm": 0.7334335928648061, "learning_rate": 7.801330242209176e-06, "loss": 0.38183820247650146, "num_input_tokens_seen": 380360360, "step": 9230, "train_runtime": 35602.8326, "train_tokens_per_second": 10683.43 }, { "epoch": 0.6218017775383786, "grad_norm": 0.75047723188034, "learning_rate": 7.799139723749207e-06, "loss": 0.38935930728912355, "num_input_tokens_seen": 380559216, "step": 9235, "train_runtime": 35621.5872, "train_tokens_per_second": 10683.387 }, { "epoch": 0.6221384325343388, "grad_norm": 0.6843970592816373, "learning_rate": 7.79694842251874e-06, "loss": 0.38491795063018797, "num_input_tokens_seen": 380771512, "step": 9240, "train_runtime": 35641.4086, "train_tokens_per_second": 10683.402 }, { "epoch": 0.6224750875302989, "grad_norm": 0.6439261652831769, "learning_rate": 7.794756339130565e-06, "loss": 0.3760078907012939, "num_input_tokens_seen": 380982736, "step": 9245, "train_runtime": 35663.0954, "train_tokens_per_second": 10682.829 }, { "epoch": 0.622811742526259, "grad_norm": 0.65479835662806, "learning_rate": 7.792563474197692e-06, "loss": 0.37955031394958494, "num_input_tokens_seen": 381183808, "step": 9250, "train_runtime": 35681.9009, "train_tokens_per_second": 10682.834 }, { "epoch": 0.6231483975222192, "grad_norm": 0.8100596893971642, "learning_rate": 7.79036982833335e-06, "loss": 0.40332746505737305, "num_input_tokens_seen": 381398816, "step": 9255, "train_runtime": 35699.7192, "train_tokens_per_second": 10683.524 }, { "epoch": 0.6234850525181793, "grad_norm": 0.7404355292427607, "learning_rate": 7.78817540215098e-06, "loss": 0.37077040672302247, "num_input_tokens_seen": 381609888, "step": 9260, "train_runtime": 35719.577, "train_tokens_per_second": 10683.494 }, { "epoch": 0.6238217075141395, "grad_norm": 0.7669054637173818, "learning_rate": 7.78598019626425e-06, "loss": 0.3730456829071045, "num_input_tokens_seen": 381829704, "step": 9265, "train_runtime": 35736.8354, "train_tokens_per_second": 10684.486 }, { "epoch": 0.6241583625100996, "grad_norm": 0.7165656306682088, "learning_rate": 7.783784211287044e-06, "loss": 0.40035719871520997, "num_input_tokens_seen": 382023416, "step": 9270, "train_runtime": 35757.4305, "train_tokens_per_second": 10683.749 }, { "epoch": 0.6244950175060597, "grad_norm": 0.7668038476177658, "learning_rate": 7.78158744783346e-06, "loss": 0.4120952606201172, "num_input_tokens_seen": 382231880, "step": 9275, "train_runtime": 35776.7847, "train_tokens_per_second": 10683.796 }, { "epoch": 0.6248316725020199, "grad_norm": 0.6956540887211856, "learning_rate": 7.779389906517813e-06, "loss": 0.3525416612625122, "num_input_tokens_seen": 382433072, "step": 9280, "train_runtime": 35795.0002, "train_tokens_per_second": 10683.98 }, { "epoch": 0.6251683274979801, "grad_norm": 0.7271768485149241, "learning_rate": 7.777191587954645e-06, "loss": 0.3700286865234375, "num_input_tokens_seen": 382633880, "step": 9285, "train_runtime": 35816.5715, "train_tokens_per_second": 10683.152 }, { "epoch": 0.6255049824939403, "grad_norm": 0.7479536683402078, "learning_rate": 7.774992492758704e-06, "loss": 0.3641063690185547, "num_input_tokens_seen": 382827296, "step": 9290, "train_runtime": 35836.1068, "train_tokens_per_second": 10682.726 }, { "epoch": 0.6258416374899004, "grad_norm": 0.6902830368576215, "learning_rate": 7.77279262154496e-06, "loss": 0.390631103515625, "num_input_tokens_seen": 383038432, "step": 9295, "train_runtime": 35854.4372, "train_tokens_per_second": 10683.153 }, { "epoch": 0.6261782924858605, "grad_norm": 0.7058388409502669, "learning_rate": 7.770591974928604e-06, "loss": 0.40048694610595703, "num_input_tokens_seen": 383253304, "step": 9300, "train_runtime": 35873.9385, "train_tokens_per_second": 10683.335 }, { "epoch": 0.6265149474818207, "grad_norm": 0.7021192800519463, "learning_rate": 7.768390553525034e-06, "loss": 0.3737443208694458, "num_input_tokens_seen": 383468680, "step": 9305, "train_runtime": 35894.6474, "train_tokens_per_second": 10683.172 }, { "epoch": 0.6268516024777808, "grad_norm": 0.7153421702293359, "learning_rate": 7.766188357949875e-06, "loss": 0.37944326400756834, "num_input_tokens_seen": 383676904, "step": 9310, "train_runtime": 35914.0173, "train_tokens_per_second": 10683.208 }, { "epoch": 0.627188257473741, "grad_norm": 0.7903212076550136, "learning_rate": 7.763985388818963e-06, "loss": 0.3708808183670044, "num_input_tokens_seen": 383884504, "step": 9315, "train_runtime": 35933.5706, "train_tokens_per_second": 10683.172 }, { "epoch": 0.6275249124697011, "grad_norm": 0.8021715160607915, "learning_rate": 7.76178164674835e-06, "loss": 0.35650362968444826, "num_input_tokens_seen": 384081672, "step": 9320, "train_runtime": 35950.7058, "train_tokens_per_second": 10683.564 }, { "epoch": 0.6278615674656612, "grad_norm": 0.6996566668596008, "learning_rate": 7.759577132354305e-06, "loss": 0.3760733127593994, "num_input_tokens_seen": 384294584, "step": 9325, "train_runtime": 35969.269, "train_tokens_per_second": 10683.97 }, { "epoch": 0.6281982224616214, "grad_norm": 0.7376735773504481, "learning_rate": 7.757371846253315e-06, "loss": 0.3508958101272583, "num_input_tokens_seen": 384494528, "step": 9330, "train_runtime": 35990.0955, "train_tokens_per_second": 10683.343 }, { "epoch": 0.6285348774575815, "grad_norm": 0.6792771045562103, "learning_rate": 7.755165789062083e-06, "loss": 0.40282316207885743, "num_input_tokens_seen": 384703808, "step": 9335, "train_runtime": 36010.3947, "train_tokens_per_second": 10683.132 }, { "epoch": 0.6288715324535417, "grad_norm": 0.6751918614140081, "learning_rate": 7.752958961397522e-06, "loss": 0.38770740032196044, "num_input_tokens_seen": 384920320, "step": 9340, "train_runtime": 36028.2209, "train_tokens_per_second": 10683.856 }, { "epoch": 0.6292081874495018, "grad_norm": 0.772838705118148, "learning_rate": 7.750751363876765e-06, "loss": 0.39199860095977784, "num_input_tokens_seen": 385120184, "step": 9345, "train_runtime": 36050.2456, "train_tokens_per_second": 10682.873 }, { "epoch": 0.6295448424454619, "grad_norm": 0.7155274135330679, "learning_rate": 7.748542997117162e-06, "loss": 0.37010798454284666, "num_input_tokens_seen": 385326696, "step": 9350, "train_runtime": 36067.9976, "train_tokens_per_second": 10683.34 }, { "epoch": 0.6298814974414221, "grad_norm": 0.7256126066085457, "learning_rate": 7.746333861736275e-06, "loss": 0.36905536651611326, "num_input_tokens_seen": 385523960, "step": 9355, "train_runtime": 36085.7119, "train_tokens_per_second": 10683.563 }, { "epoch": 0.6302181524373822, "grad_norm": 0.6779851136047969, "learning_rate": 7.74412395835188e-06, "loss": 0.3691998481750488, "num_input_tokens_seen": 385724368, "step": 9360, "train_runtime": 36104.4237, "train_tokens_per_second": 10683.576 }, { "epoch": 0.6305548074333424, "grad_norm": 0.6426798980846958, "learning_rate": 7.74191328758197e-06, "loss": 0.375079870223999, "num_input_tokens_seen": 385925120, "step": 9365, "train_runtime": 36123.9206, "train_tokens_per_second": 10683.368 }, { "epoch": 0.6308914624293025, "grad_norm": 0.7238934848233151, "learning_rate": 7.739701850044752e-06, "loss": 0.4073034286499023, "num_input_tokens_seen": 386136576, "step": 9370, "train_runtime": 36142.4823, "train_tokens_per_second": 10683.731 }, { "epoch": 0.6312281174252626, "grad_norm": 0.7046954170561016, "learning_rate": 7.73748964635865e-06, "loss": 0.374718451499939, "num_input_tokens_seen": 386343800, "step": 9375, "train_runtime": 36162.1905, "train_tokens_per_second": 10683.639 }, { "epoch": 0.6315647724212228, "grad_norm": 0.6987157684210498, "learning_rate": 7.735276677142297e-06, "loss": 0.3625496387481689, "num_input_tokens_seen": 386534256, "step": 9380, "train_runtime": 36179.9571, "train_tokens_per_second": 10683.657 }, { "epoch": 0.6319014274171829, "grad_norm": 0.7116862967496492, "learning_rate": 7.733062943014542e-06, "loss": 0.40407958030700686, "num_input_tokens_seen": 386747616, "step": 9385, "train_runtime": 36198.8235, "train_tokens_per_second": 10683.983 }, { "epoch": 0.632238082413143, "grad_norm": 0.6917847836330281, "learning_rate": 7.730848444594452e-06, "loss": 0.36053032875061036, "num_input_tokens_seen": 386963896, "step": 9390, "train_runtime": 36216.9642, "train_tokens_per_second": 10684.603 }, { "epoch": 0.6325747374091032, "grad_norm": 0.6883924889324002, "learning_rate": 7.7286331825013e-06, "loss": 0.36778619289398196, "num_input_tokens_seen": 387170680, "step": 9395, "train_runtime": 36234.4819, "train_tokens_per_second": 10685.145 }, { "epoch": 0.6329113924050633, "grad_norm": 0.7577947987371073, "learning_rate": 7.72641715735458e-06, "loss": 0.3668079376220703, "num_input_tokens_seen": 387372824, "step": 9400, "train_runtime": 36255.0195, "train_tokens_per_second": 10684.667 }, { "epoch": 0.6332480474010235, "grad_norm": 0.7201575582507821, "learning_rate": 7.724200369773998e-06, "loss": 0.3912539005279541, "num_input_tokens_seen": 387585816, "step": 9405, "train_runtime": 36274.0174, "train_tokens_per_second": 10684.943 }, { "epoch": 0.6335847023969836, "grad_norm": 0.6675075970214825, "learning_rate": 7.721982820379467e-06, "loss": 0.3705634117126465, "num_input_tokens_seen": 387794176, "step": 9410, "train_runtime": 36291.5202, "train_tokens_per_second": 10685.531 }, { "epoch": 0.6339213573929438, "grad_norm": 0.9237770839766031, "learning_rate": 7.719764509791123e-06, "loss": 0.37182226181030276, "num_input_tokens_seen": 387973960, "step": 9415, "train_runtime": 36309.8056, "train_tokens_per_second": 10685.102 }, { "epoch": 0.6342580123889039, "grad_norm": 0.7155699666239088, "learning_rate": 7.717545438629303e-06, "loss": 0.4356858730316162, "num_input_tokens_seen": 388195160, "step": 9420, "train_runtime": 36327.3965, "train_tokens_per_second": 10686.017 }, { "epoch": 0.634594667384864, "grad_norm": 0.662560818969222, "learning_rate": 7.71532560751457e-06, "loss": 0.37032737731933596, "num_input_tokens_seen": 388402192, "step": 9425, "train_runtime": 36346.8675, "train_tokens_per_second": 10685.988 }, { "epoch": 0.6349313223808242, "grad_norm": 0.7002718060362956, "learning_rate": 7.713105017067686e-06, "loss": 0.3859281301498413, "num_input_tokens_seen": 388619848, "step": 9430, "train_runtime": 36365.7138, "train_tokens_per_second": 10686.435 }, { "epoch": 0.6352679773767843, "grad_norm": 0.7636503950129163, "learning_rate": 7.710883667909639e-06, "loss": 0.37295379638671877, "num_input_tokens_seen": 388824672, "step": 9435, "train_runtime": 36385.2805, "train_tokens_per_second": 10686.318 }, { "epoch": 0.6356046323727444, "grad_norm": 0.7013147674314846, "learning_rate": 7.708661560661617e-06, "loss": 0.40069942474365233, "num_input_tokens_seen": 389035976, "step": 9440, "train_runtime": 36404.259, "train_tokens_per_second": 10686.551 }, { "epoch": 0.6359412873687046, "grad_norm": 0.7259759637103255, "learning_rate": 7.706438695945026e-06, "loss": 0.39327192306518555, "num_input_tokens_seen": 389242000, "step": 9445, "train_runtime": 36423.9955, "train_tokens_per_second": 10686.417 }, { "epoch": 0.6362779423646647, "grad_norm": 0.9744114714275186, "learning_rate": 7.704215074381484e-06, "loss": 0.39724953174591066, "num_input_tokens_seen": 389435888, "step": 9450, "train_runtime": 36442.2057, "train_tokens_per_second": 10686.397 }, { "epoch": 0.6366145973606249, "grad_norm": 0.7142548391629253, "learning_rate": 7.70199069659282e-06, "loss": 0.3907075166702271, "num_input_tokens_seen": 389637568, "step": 9455, "train_runtime": 36461.3196, "train_tokens_per_second": 10686.327 }, { "epoch": 0.636951252356585, "grad_norm": 0.6845134138904888, "learning_rate": 7.699765563201075e-06, "loss": 0.38851242065429686, "num_input_tokens_seen": 389847440, "step": 9460, "train_runtime": 36479.0665, "train_tokens_per_second": 10686.881 }, { "epoch": 0.6372879073525451, "grad_norm": 0.6178677793490827, "learning_rate": 7.697539674828498e-06, "loss": 0.3659019470214844, "num_input_tokens_seen": 390063712, "step": 9465, "train_runtime": 36497.0185, "train_tokens_per_second": 10687.55 }, { "epoch": 0.6376245623485053, "grad_norm": 0.6638251161831344, "learning_rate": 7.695313032097554e-06, "loss": 0.35878872871398926, "num_input_tokens_seen": 390270008, "step": 9470, "train_runtime": 36516.2068, "train_tokens_per_second": 10687.583 }, { "epoch": 0.6379612173444654, "grad_norm": 0.6699495241603529, "learning_rate": 7.693085635630913e-06, "loss": 0.3789350509643555, "num_input_tokens_seen": 390462832, "step": 9475, "train_runtime": 36536.3719, "train_tokens_per_second": 10686.962 }, { "epoch": 0.6382978723404256, "grad_norm": 0.7142423389386878, "learning_rate": 7.690857486051463e-06, "loss": 0.3719592571258545, "num_input_tokens_seen": 390677200, "step": 9480, "train_runtime": 36555.8317, "train_tokens_per_second": 10687.138 }, { "epoch": 0.6386345273363857, "grad_norm": 0.6407840693352355, "learning_rate": 7.688628583982298e-06, "loss": 0.37234690189361574, "num_input_tokens_seen": 390877528, "step": 9485, "train_runtime": 36575.7527, "train_tokens_per_second": 10686.794 }, { "epoch": 0.6389711823323458, "grad_norm": 0.6565158797725944, "learning_rate": 7.68639893004672e-06, "loss": 0.3633148193359375, "num_input_tokens_seen": 391088000, "step": 9490, "train_runtime": 36595.742, "train_tokens_per_second": 10686.708 }, { "epoch": 0.639307837328306, "grad_norm": 0.6740079267591738, "learning_rate": 7.684168524868253e-06, "loss": 0.3607438802719116, "num_input_tokens_seen": 391304432, "step": 9495, "train_runtime": 36615.055, "train_tokens_per_second": 10686.982 }, { "epoch": 0.6396444923242661, "grad_norm": 0.6375623870270577, "learning_rate": 7.681937369070612e-06, "loss": 0.3764339447021484, "num_input_tokens_seen": 391506624, "step": 9500, "train_runtime": 36633.4584, "train_tokens_per_second": 10687.133 }, { "epoch": 0.6399811473202263, "grad_norm": 0.7143211674261691, "learning_rate": 7.67970546327774e-06, "loss": 0.38482840061187745, "num_input_tokens_seen": 391715312, "step": 9505, "train_runtime": 36653.3697, "train_tokens_per_second": 10687.02 }, { "epoch": 0.6403178023161864, "grad_norm": 0.6576973894070457, "learning_rate": 7.67747280811378e-06, "loss": 0.36203923225402834, "num_input_tokens_seen": 391919360, "step": 9510, "train_runtime": 36672.7922, "train_tokens_per_second": 10686.924 }, { "epoch": 0.6406544573121465, "grad_norm": 0.6338725085352875, "learning_rate": 7.675239404203088e-06, "loss": 0.35704631805419923, "num_input_tokens_seen": 392123320, "step": 9515, "train_runtime": 36692.6115, "train_tokens_per_second": 10686.711 }, { "epoch": 0.6409911123081067, "grad_norm": 0.6843737254467163, "learning_rate": 7.673005252170226e-06, "loss": 0.37882883548736573, "num_input_tokens_seen": 392336648, "step": 9520, "train_runtime": 36711.9681, "train_tokens_per_second": 10686.887 }, { "epoch": 0.6413277673040668, "grad_norm": 0.6823205866544065, "learning_rate": 7.670770352639968e-06, "loss": 0.3674900054931641, "num_input_tokens_seen": 392534096, "step": 9525, "train_runtime": 36731.0435, "train_tokens_per_second": 10686.712 }, { "epoch": 0.641664422300027, "grad_norm": 0.7502539394144336, "learning_rate": 7.668534706237299e-06, "loss": 0.37969222068786623, "num_input_tokens_seen": 392740048, "step": 9530, "train_runtime": 36749.3053, "train_tokens_per_second": 10687.006 }, { "epoch": 0.6420010772959871, "grad_norm": 0.7519214746873926, "learning_rate": 7.666298313587409e-06, "loss": 0.42354459762573243, "num_input_tokens_seen": 392948256, "step": 9535, "train_runtime": 36769.6658, "train_tokens_per_second": 10686.751 }, { "epoch": 0.6423377322919472, "grad_norm": 0.7523714148081581, "learning_rate": 7.664061175315696e-06, "loss": 0.36963791847229005, "num_input_tokens_seen": 393135216, "step": 9540, "train_runtime": 36788.4618, "train_tokens_per_second": 10686.373 }, { "epoch": 0.6426743872879074, "grad_norm": 0.7163323944809101, "learning_rate": 7.661823292047771e-06, "loss": 0.37872750759124757, "num_input_tokens_seen": 393341352, "step": 9545, "train_runtime": 36807.1008, "train_tokens_per_second": 10686.562 }, { "epoch": 0.6430110422838675, "grad_norm": 0.7848823633957892, "learning_rate": 7.659584664409452e-06, "loss": 0.3811967134475708, "num_input_tokens_seen": 393554152, "step": 9550, "train_runtime": 36826.0259, "train_tokens_per_second": 10686.848 }, { "epoch": 0.6433476972798277, "grad_norm": 0.7279560024986693, "learning_rate": 7.65734529302676e-06, "loss": 0.3391754627227783, "num_input_tokens_seen": 393748440, "step": 9555, "train_runtime": 36845.0793, "train_tokens_per_second": 10686.595 }, { "epoch": 0.6436843522757878, "grad_norm": 0.713838479921085, "learning_rate": 7.655105178525932e-06, "loss": 0.36218552589416503, "num_input_tokens_seen": 393953920, "step": 9560, "train_runtime": 36865.3583, "train_tokens_per_second": 10686.29 }, { "epoch": 0.6440210072717479, "grad_norm": 0.9691831178896948, "learning_rate": 7.652864321533406e-06, "loss": 0.37881791591644287, "num_input_tokens_seen": 394154344, "step": 9565, "train_runtime": 36884.6701, "train_tokens_per_second": 10686.129 }, { "epoch": 0.6443576622677081, "grad_norm": 0.6419670223502364, "learning_rate": 7.650622722675833e-06, "loss": 0.3887354373931885, "num_input_tokens_seen": 394367248, "step": 9570, "train_runtime": 36904.5044, "train_tokens_per_second": 10686.155 }, { "epoch": 0.6446943172636682, "grad_norm": 0.7471602807156725, "learning_rate": 7.648380382580067e-06, "loss": 0.39195570945739744, "num_input_tokens_seen": 394571752, "step": 9575, "train_runtime": 36924.599, "train_tokens_per_second": 10685.878 }, { "epoch": 0.6450309722596284, "grad_norm": 0.7864099848200121, "learning_rate": 7.646137301873173e-06, "loss": 0.38346679210662843, "num_input_tokens_seen": 394771392, "step": 9580, "train_runtime": 36945.4686, "train_tokens_per_second": 10685.245 }, { "epoch": 0.6453676272555885, "grad_norm": 0.7961741116141738, "learning_rate": 7.643893481182421e-06, "loss": 0.359751296043396, "num_input_tokens_seen": 394980400, "step": 9585, "train_runtime": 36965.2366, "train_tokens_per_second": 10685.185 }, { "epoch": 0.6457042822515486, "grad_norm": 0.7524855072840261, "learning_rate": 7.641648921135287e-06, "loss": 0.4146468162536621, "num_input_tokens_seen": 395194848, "step": 9590, "train_runtime": 36983.9154, "train_tokens_per_second": 10685.587 }, { "epoch": 0.6460409372475088, "grad_norm": 0.7980018118333444, "learning_rate": 7.639403622359455e-06, "loss": 0.3858792781829834, "num_input_tokens_seen": 395392704, "step": 9595, "train_runtime": 37003.6249, "train_tokens_per_second": 10685.242 }, { "epoch": 0.6463775922434689, "grad_norm": 0.6940781848762863, "learning_rate": 7.637157585482817e-06, "loss": 0.3722890138626099, "num_input_tokens_seen": 395597728, "step": 9600, "train_runtime": 37023.3145, "train_tokens_per_second": 10685.098 }, { "epoch": 0.646714247239429, "grad_norm": 0.6564572435265508, "learning_rate": 7.63491081113347e-06, "loss": 0.4029213905334473, "num_input_tokens_seen": 395814328, "step": 9605, "train_runtime": 37041.465, "train_tokens_per_second": 10685.709 }, { "epoch": 0.6470509022353892, "grad_norm": 0.761175311407608, "learning_rate": 7.632663299939718e-06, "loss": 0.39779608249664306, "num_input_tokens_seen": 396027336, "step": 9610, "train_runtime": 37061.511, "train_tokens_per_second": 10685.677 }, { "epoch": 0.6473875572313493, "grad_norm": 0.7594180258260084, "learning_rate": 7.630415052530066e-06, "loss": 0.38155150413513184, "num_input_tokens_seen": 396230936, "step": 9615, "train_runtime": 37080.0159, "train_tokens_per_second": 10685.835 }, { "epoch": 0.6477242122273095, "grad_norm": 0.7960191187516589, "learning_rate": 7.628166069533235e-06, "loss": 0.3851162433624268, "num_input_tokens_seen": 396428920, "step": 9620, "train_runtime": 37099.5952, "train_tokens_per_second": 10685.532 }, { "epoch": 0.6480608672232696, "grad_norm": 1.6253323400324449, "learning_rate": 7.625916351578141e-06, "loss": 0.4091392993927002, "num_input_tokens_seen": 396633984, "step": 9625, "train_runtime": 37119.4164, "train_tokens_per_second": 10685.351 }, { "epoch": 0.6483975222192297, "grad_norm": 0.6124046151410726, "learning_rate": 7.623665899293914e-06, "loss": 0.3565532207489014, "num_input_tokens_seen": 396839952, "step": 9630, "train_runtime": 37140.4531, "train_tokens_per_second": 10684.844 }, { "epoch": 0.6487341772151899, "grad_norm": 0.6843923652288886, "learning_rate": 7.621414713309885e-06, "loss": 0.3408329486846924, "num_input_tokens_seen": 397045576, "step": 9635, "train_runtime": 37160.1315, "train_tokens_per_second": 10684.719 }, { "epoch": 0.64907083221115, "grad_norm": 0.6968845913024023, "learning_rate": 7.61916279425559e-06, "loss": 0.3939297437667847, "num_input_tokens_seen": 397260264, "step": 9640, "train_runtime": 37180.6468, "train_tokens_per_second": 10684.598 }, { "epoch": 0.6494074872071102, "grad_norm": 0.6937320233369714, "learning_rate": 7.6169101427607716e-06, "loss": 0.3807823181152344, "num_input_tokens_seen": 397477432, "step": 9645, "train_runtime": 37199.0539, "train_tokens_per_second": 10685.149 }, { "epoch": 0.6497441422030703, "grad_norm": 0.713866210057699, "learning_rate": 7.614656759455375e-06, "loss": 0.3820813179016113, "num_input_tokens_seen": 397685864, "step": 9650, "train_runtime": 37218.9302, "train_tokens_per_second": 10685.043 }, { "epoch": 0.6500807971990304, "grad_norm": 0.7678226537485624, "learning_rate": 7.612402644969555e-06, "loss": 0.38394315242767335, "num_input_tokens_seen": 397887328, "step": 9655, "train_runtime": 37239.9694, "train_tokens_per_second": 10684.416 }, { "epoch": 0.6504174521949906, "grad_norm": 0.7082942223307394, "learning_rate": 7.6101477999336646e-06, "loss": 0.38046846389770506, "num_input_tokens_seen": 398094232, "step": 9660, "train_runtime": 37261.3104, "train_tokens_per_second": 10683.849 }, { "epoch": 0.6507541071909507, "grad_norm": 0.8564580372125329, "learning_rate": 7.607892224978266e-06, "loss": 0.37298016548156737, "num_input_tokens_seen": 398292248, "step": 9665, "train_runtime": 37279.069, "train_tokens_per_second": 10684.072 }, { "epoch": 0.6510907621869109, "grad_norm": 0.6785426768272456, "learning_rate": 7.605635920734122e-06, "loss": 0.3474737167358398, "num_input_tokens_seen": 398492608, "step": 9670, "train_runtime": 37298.6858, "train_tokens_per_second": 10683.824 }, { "epoch": 0.651427417182871, "grad_norm": 0.6780720228000084, "learning_rate": 7.603378887832202e-06, "loss": 0.38177454471588135, "num_input_tokens_seen": 398690080, "step": 9675, "train_runtime": 37319.5869, "train_tokens_per_second": 10683.132 }, { "epoch": 0.6517640721788311, "grad_norm": 0.6646228173252627, "learning_rate": 7.601121126903676e-06, "loss": 0.38001255989074706, "num_input_tokens_seen": 398900416, "step": 9680, "train_runtime": 37339.0424, "train_tokens_per_second": 10683.199 }, { "epoch": 0.6521007271747913, "grad_norm": 0.7482988165296466, "learning_rate": 7.598862638579922e-06, "loss": 0.3821424961090088, "num_input_tokens_seen": 399119000, "step": 9685, "train_runtime": 37356.8898, "train_tokens_per_second": 10683.946 }, { "epoch": 0.6524373821707514, "grad_norm": 0.6941598407008747, "learning_rate": 7.5966034234925205e-06, "loss": 0.38524808883666994, "num_input_tokens_seen": 399336016, "step": 9690, "train_runtime": 37376.5485, "train_tokens_per_second": 10684.133 }, { "epoch": 0.6527740371667116, "grad_norm": 0.7190958238819064, "learning_rate": 7.59434348227325e-06, "loss": 0.4326727867126465, "num_input_tokens_seen": 399547272, "step": 9695, "train_runtime": 37395.4856, "train_tokens_per_second": 10684.372 }, { "epoch": 0.6531106921626717, "grad_norm": 0.7683965458139159, "learning_rate": 7.592082815554098e-06, "loss": 0.41515226364135743, "num_input_tokens_seen": 399756600, "step": 9700, "train_runtime": 37413.2355, "train_tokens_per_second": 10684.898 }, { "epoch": 0.6534473471586318, "grad_norm": 0.9025586097079927, "learning_rate": 7.58982142396725e-06, "loss": 0.42514333724975584, "num_input_tokens_seen": 399944416, "step": 9705, "train_runtime": 37434.5558, "train_tokens_per_second": 10683.83 }, { "epoch": 0.653784002154592, "grad_norm": 0.7640184840782422, "learning_rate": 7.5875593081451e-06, "loss": 0.3758402824401855, "num_input_tokens_seen": 400157064, "step": 9710, "train_runtime": 37452.8508, "train_tokens_per_second": 10684.289 }, { "epoch": 0.6541206571505521, "grad_norm": 0.6934614239411571, "learning_rate": 7.585296468720243e-06, "loss": 0.36301288604736326, "num_input_tokens_seen": 400369792, "step": 9715, "train_runtime": 37473.4464, "train_tokens_per_second": 10684.093 }, { "epoch": 0.6544573121465123, "grad_norm": 0.6959566607982702, "learning_rate": 7.5830329063254705e-06, "loss": 0.38737969398498534, "num_input_tokens_seen": 400571088, "step": 9720, "train_runtime": 37492.5351, "train_tokens_per_second": 10684.022 }, { "epoch": 0.6547939671424724, "grad_norm": 0.7011274266300719, "learning_rate": 7.5807686215937835e-06, "loss": 0.38814876079559324, "num_input_tokens_seen": 400773088, "step": 9725, "train_runtime": 37513.2722, "train_tokens_per_second": 10683.501 }, { "epoch": 0.6551306221384325, "grad_norm": 0.6870393229727046, "learning_rate": 7.578503615158379e-06, "loss": 0.3384148597717285, "num_input_tokens_seen": 400974976, "step": 9730, "train_runtime": 37532.6599, "train_tokens_per_second": 10683.362 }, { "epoch": 0.6554672771343927, "grad_norm": 0.6680289352802284, "learning_rate": 7.576237887652662e-06, "loss": 0.39319720268249514, "num_input_tokens_seen": 401190160, "step": 9735, "train_runtime": 37550.6197, "train_tokens_per_second": 10683.982 }, { "epoch": 0.6558039321303528, "grad_norm": 0.8009338801160456, "learning_rate": 7.573971439710235e-06, "loss": 0.34558672904968263, "num_input_tokens_seen": 401394416, "step": 9740, "train_runtime": 37569.9507, "train_tokens_per_second": 10683.922 }, { "epoch": 0.656140587126313, "grad_norm": 0.7714568061477152, "learning_rate": 7.571704271964902e-06, "loss": 0.3653956413269043, "num_input_tokens_seen": 401592168, "step": 9745, "train_runtime": 37589.1364, "train_tokens_per_second": 10683.73 }, { "epoch": 0.6564772421222731, "grad_norm": 0.7700367646475144, "learning_rate": 7.56943638505067e-06, "loss": 0.3704387664794922, "num_input_tokens_seen": 401803072, "step": 9750, "train_runtime": 37608.2942, "train_tokens_per_second": 10683.895 }, { "epoch": 0.6568138971182332, "grad_norm": 0.6773989522124707, "learning_rate": 7.567167779601746e-06, "loss": 0.3866323471069336, "num_input_tokens_seen": 402016648, "step": 9755, "train_runtime": 37626.9703, "train_tokens_per_second": 10684.268 }, { "epoch": 0.6571505521141934, "grad_norm": 0.7629483634897811, "learning_rate": 7.56489845625254e-06, "loss": 0.41835451126098633, "num_input_tokens_seen": 402222672, "step": 9760, "train_runtime": 37646.6756, "train_tokens_per_second": 10684.148 }, { "epoch": 0.6574872071101535, "grad_norm": 0.6993971738800265, "learning_rate": 7.562628415637659e-06, "loss": 0.3727128982543945, "num_input_tokens_seen": 402420744, "step": 9765, "train_runtime": 37667.7096, "train_tokens_per_second": 10683.441 }, { "epoch": 0.6578238621061137, "grad_norm": 0.6970170032293618, "learning_rate": 7.560357658391913e-06, "loss": 0.4112259864807129, "num_input_tokens_seen": 402628336, "step": 9770, "train_runtime": 37686.9011, "train_tokens_per_second": 10683.509 }, { "epoch": 0.6581605171020738, "grad_norm": 0.6843533653605328, "learning_rate": 7.558086185150311e-06, "loss": 0.387186336517334, "num_input_tokens_seen": 402830040, "step": 9775, "train_runtime": 37706.9261, "train_tokens_per_second": 10683.184 }, { "epoch": 0.6584971720980339, "grad_norm": 0.7509751809059497, "learning_rate": 7.555813996548065e-06, "loss": 0.40376987457275393, "num_input_tokens_seen": 403041272, "step": 9780, "train_runtime": 37726.4843, "train_tokens_per_second": 10683.245 }, { "epoch": 0.6588338270939941, "grad_norm": 0.8200499650780443, "learning_rate": 7.553541093220586e-06, "loss": 0.3825526237487793, "num_input_tokens_seen": 403243448, "step": 9785, "train_runtime": 37744.2786, "train_tokens_per_second": 10683.565 }, { "epoch": 0.6591704820899542, "grad_norm": 0.6807401580274353, "learning_rate": 7.551267475803481e-06, "loss": 0.37834911346435546, "num_input_tokens_seen": 403457816, "step": 9790, "train_runtime": 37762.3506, "train_tokens_per_second": 10684.129 }, { "epoch": 0.6595071370859144, "grad_norm": 0.7222237028414097, "learning_rate": 7.5489931449325635e-06, "loss": 0.378787899017334, "num_input_tokens_seen": 403663368, "step": 9795, "train_runtime": 37781.3431, "train_tokens_per_second": 10684.198 }, { "epoch": 0.6598437920818745, "grad_norm": 0.7728838137448946, "learning_rate": 7.546718101243842e-06, "loss": 0.3901359558105469, "num_input_tokens_seen": 403864136, "step": 9800, "train_runtime": 37800.8655, "train_tokens_per_second": 10683.992 }, { "epoch": 0.6601804470778346, "grad_norm": 0.7981382340275028, "learning_rate": 7.544442345373522e-06, "loss": 0.3765082359313965, "num_input_tokens_seen": 404061936, "step": 9805, "train_runtime": 37819.494, "train_tokens_per_second": 10683.959 }, { "epoch": 0.6605171020737948, "grad_norm": 0.6383957491430862, "learning_rate": 7.542165877958014e-06, "loss": 0.3741722583770752, "num_input_tokens_seen": 404264808, "step": 9810, "train_runtime": 37839.3687, "train_tokens_per_second": 10683.709 }, { "epoch": 0.6608537570697549, "grad_norm": 0.7229585711593463, "learning_rate": 7.539888699633926e-06, "loss": 0.38417925834655764, "num_input_tokens_seen": 404478448, "step": 9815, "train_runtime": 37857.6848, "train_tokens_per_second": 10684.183 }, { "epoch": 0.661190412065715, "grad_norm": 0.6689905930569565, "learning_rate": 7.5376108110380606e-06, "loss": 0.35189385414123536, "num_input_tokens_seen": 404693504, "step": 9820, "train_runtime": 37876.7338, "train_tokens_per_second": 10684.488 }, { "epoch": 0.6615270670616752, "grad_norm": 0.648167084977009, "learning_rate": 7.535332212807426e-06, "loss": 0.34443082809448244, "num_input_tokens_seen": 404884608, "step": 9825, "train_runtime": 37894.5532, "train_tokens_per_second": 10684.507 }, { "epoch": 0.6618637220576353, "grad_norm": 0.7041046130292984, "learning_rate": 7.53305290557922e-06, "loss": 0.3952155828475952, "num_input_tokens_seen": 405101216, "step": 9830, "train_runtime": 37914.5338, "train_tokens_per_second": 10684.589 }, { "epoch": 0.6622003770535955, "grad_norm": 0.7143437888766068, "learning_rate": 7.530772889990848e-06, "loss": 0.377201509475708, "num_input_tokens_seen": 405317728, "step": 9835, "train_runtime": 37933.315, "train_tokens_per_second": 10685.007 }, { "epoch": 0.6625370320495556, "grad_norm": 0.6221036377986929, "learning_rate": 7.528492166679907e-06, "loss": 0.3539456844329834, "num_input_tokens_seen": 405533584, "step": 9840, "train_runtime": 37953.8099, "train_tokens_per_second": 10684.924 }, { "epoch": 0.6628736870455157, "grad_norm": 0.676832032687683, "learning_rate": 7.526210736284194e-06, "loss": 0.3891479730606079, "num_input_tokens_seen": 405726096, "step": 9845, "train_runtime": 37972.3951, "train_tokens_per_second": 10684.764 }, { "epoch": 0.6632103420414759, "grad_norm": 0.6885106256518927, "learning_rate": 7.523928599441706e-06, "loss": 0.3869965076446533, "num_input_tokens_seen": 405937680, "step": 9850, "train_runtime": 37991.6052, "train_tokens_per_second": 10684.931 }, { "epoch": 0.663546997037436, "grad_norm": 0.7787101182823161, "learning_rate": 7.5216457567906295e-06, "loss": 0.3932418584823608, "num_input_tokens_seen": 406151400, "step": 9855, "train_runtime": 38010.0003, "train_tokens_per_second": 10685.383 }, { "epoch": 0.6638836520333962, "grad_norm": 0.833230632726778, "learning_rate": 7.519362208969362e-06, "loss": 0.3596032619476318, "num_input_tokens_seen": 406362056, "step": 9860, "train_runtime": 38028.3333, "train_tokens_per_second": 10685.771 }, { "epoch": 0.6642203070293563, "grad_norm": 0.6383389885105186, "learning_rate": 7.5170779566164855e-06, "loss": 0.40471687316894533, "num_input_tokens_seen": 406570104, "step": 9865, "train_runtime": 38047.8248, "train_tokens_per_second": 10685.765 }, { "epoch": 0.6645569620253164, "grad_norm": 0.7341363602800139, "learning_rate": 7.514793000370783e-06, "loss": 0.3952347278594971, "num_input_tokens_seen": 406769856, "step": 9870, "train_runtime": 38067.3217, "train_tokens_per_second": 10685.539 }, { "epoch": 0.6648936170212766, "grad_norm": 0.6982471323248536, "learning_rate": 7.512507340871239e-06, "loss": 0.37077791690826417, "num_input_tokens_seen": 406975824, "step": 9875, "train_runtime": 38086.7067, "train_tokens_per_second": 10685.508 }, { "epoch": 0.6652302720172367, "grad_norm": 0.7516112253867481, "learning_rate": 7.510220978757028e-06, "loss": 0.39798340797424314, "num_input_tokens_seen": 407180808, "step": 9880, "train_runtime": 38106.4569, "train_tokens_per_second": 10685.349 }, { "epoch": 0.6655669270131969, "grad_norm": 0.758101375996963, "learning_rate": 7.507933914667524e-06, "loss": 0.41948566436767576, "num_input_tokens_seen": 407393904, "step": 9885, "train_runtime": 38126.6896, "train_tokens_per_second": 10685.268 }, { "epoch": 0.665903582009157, "grad_norm": 0.703156505814568, "learning_rate": 7.505646149242299e-06, "loss": 0.3748434066772461, "num_input_tokens_seen": 407602704, "step": 9890, "train_runtime": 38147.866, "train_tokens_per_second": 10684.81 }, { "epoch": 0.6662402370051171, "grad_norm": 0.6633329240298158, "learning_rate": 7.503357683121119e-06, "loss": 0.36188645362854005, "num_input_tokens_seen": 407816448, "step": 9895, "train_runtime": 38167.0954, "train_tokens_per_second": 10685.027 }, { "epoch": 0.6665768920010773, "grad_norm": 0.6873864039542459, "learning_rate": 7.501068516943944e-06, "loss": 0.32127013206481936, "num_input_tokens_seen": 408017960, "step": 9900, "train_runtime": 38185.4357, "train_tokens_per_second": 10685.172 }, { "epoch": 0.6669135469970374, "grad_norm": 0.6624367384055055, "learning_rate": 7.498778651350934e-06, "loss": 0.3918678522109985, "num_input_tokens_seen": 408229784, "step": 9905, "train_runtime": 38205.0931, "train_tokens_per_second": 10685.219 }, { "epoch": 0.6672502019929976, "grad_norm": 0.7522968398026472, "learning_rate": 7.496488086982443e-06, "loss": 0.3717939853668213, "num_input_tokens_seen": 408437816, "step": 9910, "train_runtime": 38224.2846, "train_tokens_per_second": 10685.297 }, { "epoch": 0.6675868569889577, "grad_norm": 0.8256119573181936, "learning_rate": 7.494196824479019e-06, "loss": 0.37599108219146726, "num_input_tokens_seen": 408640152, "step": 9915, "train_runtime": 38244.3529, "train_tokens_per_second": 10684.98 }, { "epoch": 0.6679235119849178, "grad_norm": 0.6637219587603042, "learning_rate": 7.491904864481406e-06, "loss": 0.3797877550125122, "num_input_tokens_seen": 408841400, "step": 9920, "train_runtime": 38263.5925, "train_tokens_per_second": 10684.867 }, { "epoch": 0.668260166980878, "grad_norm": 0.6489010150523005, "learning_rate": 7.489612207630543e-06, "loss": 0.33827762603759765, "num_input_tokens_seen": 409056776, "step": 9925, "train_runtime": 38282.18, "train_tokens_per_second": 10685.305 }, { "epoch": 0.6685968219768381, "grad_norm": 0.6864766734221677, "learning_rate": 7.487318854567566e-06, "loss": 0.37743330001831055, "num_input_tokens_seen": 409255080, "step": 9930, "train_runtime": 38300.6585, "train_tokens_per_second": 10685.328 }, { "epoch": 0.6689334769727983, "grad_norm": 0.7223937928796067, "learning_rate": 7.485024805933803e-06, "loss": 0.36581902503967284, "num_input_tokens_seen": 409447808, "step": 9935, "train_runtime": 38318.2741, "train_tokens_per_second": 10685.445 }, { "epoch": 0.6692701319687584, "grad_norm": 0.6001526959212448, "learning_rate": 7.482730062370776e-06, "loss": 0.3653615713119507, "num_input_tokens_seen": 409649096, "step": 9940, "train_runtime": 38337.712, "train_tokens_per_second": 10685.278 }, { "epoch": 0.6696067869647185, "grad_norm": 0.683713427291979, "learning_rate": 7.480434624520205e-06, "loss": 0.3568159580230713, "num_input_tokens_seen": 409869152, "step": 9945, "train_runtime": 38356.1936, "train_tokens_per_second": 10685.866 }, { "epoch": 0.6699434419606787, "grad_norm": 0.6699473216485108, "learning_rate": 7.478138493024001e-06, "loss": 0.3948239326477051, "num_input_tokens_seen": 410081464, "step": 9950, "train_runtime": 38375.7635, "train_tokens_per_second": 10685.949 }, { "epoch": 0.6702800969566388, "grad_norm": 0.6681512879385534, "learning_rate": 7.475841668524268e-06, "loss": 0.3541509389877319, "num_input_tokens_seen": 410282472, "step": 9955, "train_runtime": 38394.4102, "train_tokens_per_second": 10685.995 }, { "epoch": 0.670616751952599, "grad_norm": 0.7698771490664527, "learning_rate": 7.473544151663309e-06, "loss": 0.4120823383331299, "num_input_tokens_seen": 410487456, "step": 9960, "train_runtime": 38412.743, "train_tokens_per_second": 10686.231 }, { "epoch": 0.6709534069485591, "grad_norm": 0.7076895959424484, "learning_rate": 7.471245943083615e-06, "loss": 0.3760012149810791, "num_input_tokens_seen": 410696824, "step": 9965, "train_runtime": 38431.1057, "train_tokens_per_second": 10686.573 }, { "epoch": 0.6712900619445192, "grad_norm": 0.7015626343308221, "learning_rate": 7.468947043427873e-06, "loss": 0.3446054935455322, "num_input_tokens_seen": 410901840, "step": 9970, "train_runtime": 38449.5107, "train_tokens_per_second": 10686.79 }, { "epoch": 0.6716267169404794, "grad_norm": 0.7658454779158502, "learning_rate": 7.466647453338965e-06, "loss": 0.380652117729187, "num_input_tokens_seen": 411101232, "step": 9975, "train_runtime": 38468.3727, "train_tokens_per_second": 10686.733 }, { "epoch": 0.6719633719364395, "grad_norm": 0.6414791554286339, "learning_rate": 7.464347173459958e-06, "loss": 0.39258222579956054, "num_input_tokens_seen": 411324024, "step": 9980, "train_runtime": 38487.7346, "train_tokens_per_second": 10687.146 }, { "epoch": 0.6723000269323997, "grad_norm": 0.586340756625192, "learning_rate": 7.462046204434126e-06, "loss": 0.34933593273162844, "num_input_tokens_seen": 411544360, "step": 9985, "train_runtime": 38505.825, "train_tokens_per_second": 10687.847 }, { "epoch": 0.6726366819283598, "grad_norm": 0.765583185648394, "learning_rate": 7.459744546904922e-06, "loss": 0.37443416118621825, "num_input_tokens_seen": 411747952, "step": 9990, "train_runtime": 38524.8405, "train_tokens_per_second": 10687.856 }, { "epoch": 0.6729733369243199, "grad_norm": 0.6323646332432883, "learning_rate": 7.457442201516001e-06, "loss": 0.34482784271240235, "num_input_tokens_seen": 411953216, "step": 9995, "train_runtime": 38544.9231, "train_tokens_per_second": 10687.613 }, { "epoch": 0.6733099919202801, "grad_norm": 0.7039360341737809, "learning_rate": 7.455139168911203e-06, "loss": 0.37264432907104494, "num_input_tokens_seen": 412142904, "step": 10000, "train_runtime": 38564.6727, "train_tokens_per_second": 10687.058 }, { "epoch": 0.6736466469162402, "grad_norm": 0.7713285061032082, "learning_rate": 7.452835449734564e-06, "loss": 0.3733638525009155, "num_input_tokens_seen": 412348296, "step": 10005, "train_runtime": 38583.3675, "train_tokens_per_second": 10687.203 }, { "epoch": 0.6739833019122003, "grad_norm": 0.7269965733126029, "learning_rate": 7.450531044630315e-06, "loss": 0.3554370880126953, "num_input_tokens_seen": 412554232, "step": 10010, "train_runtime": 38602.084, "train_tokens_per_second": 10687.356 }, { "epoch": 0.6743199569081605, "grad_norm": 0.8916179192225939, "learning_rate": 7.448225954242874e-06, "loss": 0.3955848693847656, "num_input_tokens_seen": 412768488, "step": 10015, "train_runtime": 38622.0213, "train_tokens_per_second": 10687.387 }, { "epoch": 0.6746566119041206, "grad_norm": 0.6860062530219295, "learning_rate": 7.44592017921685e-06, "loss": 0.38590426445007325, "num_input_tokens_seen": 412976376, "step": 10020, "train_runtime": 38641.042, "train_tokens_per_second": 10687.506 }, { "epoch": 0.6749932669000808, "grad_norm": 0.692827562230775, "learning_rate": 7.443613720197048e-06, "loss": 0.392451810836792, "num_input_tokens_seen": 413184368, "step": 10025, "train_runtime": 38663.1641, "train_tokens_per_second": 10686.771 }, { "epoch": 0.6753299218960409, "grad_norm": 0.7369000826772353, "learning_rate": 7.44130657782846e-06, "loss": 0.3622234344482422, "num_input_tokens_seen": 413379944, "step": 10030, "train_runtime": 38682.1437, "train_tokens_per_second": 10686.583 }, { "epoch": 0.675666576892001, "grad_norm": 0.6937151035647251, "learning_rate": 7.438998752756274e-06, "loss": 0.37694129943847654, "num_input_tokens_seen": 413587160, "step": 10035, "train_runtime": 38702.4654, "train_tokens_per_second": 10686.326 }, { "epoch": 0.6760032318879612, "grad_norm": 0.7129899279395124, "learning_rate": 7.436690245625864e-06, "loss": 0.37236597537994387, "num_input_tokens_seen": 413791432, "step": 10040, "train_runtime": 38720.7136, "train_tokens_per_second": 10686.565 }, { "epoch": 0.6763398868839213, "grad_norm": 0.8309853533261624, "learning_rate": 7.434381057082797e-06, "loss": 0.37053751945495605, "num_input_tokens_seen": 413987944, "step": 10045, "train_runtime": 38738.6771, "train_tokens_per_second": 10686.683 }, { "epoch": 0.6766765418798815, "grad_norm": 0.7201575445695781, "learning_rate": 7.4320711877728305e-06, "loss": 0.3999882936477661, "num_input_tokens_seen": 414199008, "step": 10050, "train_runtime": 38759.7161, "train_tokens_per_second": 10686.327 }, { "epoch": 0.6770131968758416, "grad_norm": 0.7321998813159287, "learning_rate": 7.429760638341909e-06, "loss": 0.3501319646835327, "num_input_tokens_seen": 414389056, "step": 10055, "train_runtime": 38778.8228, "train_tokens_per_second": 10685.963 }, { "epoch": 0.6773498518718017, "grad_norm": 0.7142845103387634, "learning_rate": 7.427449409436176e-06, "loss": 0.4236575126647949, "num_input_tokens_seen": 414594200, "step": 10060, "train_runtime": 38797.1751, "train_tokens_per_second": 10686.196 }, { "epoch": 0.6776865068677619, "grad_norm": 0.6116336665271289, "learning_rate": 7.425137501701955e-06, "loss": 0.35617499351501464, "num_input_tokens_seen": 414812600, "step": 10065, "train_runtime": 38815.6333, "train_tokens_per_second": 10686.74 }, { "epoch": 0.678023161863722, "grad_norm": 0.8200669931207036, "learning_rate": 7.422824915785765e-06, "loss": 0.3820950508117676, "num_input_tokens_seen": 415018688, "step": 10070, "train_runtime": 38834.7688, "train_tokens_per_second": 10686.781 }, { "epoch": 0.6783598168596822, "grad_norm": 0.7636306781773281, "learning_rate": 7.420511652334313e-06, "loss": 0.39130640029907227, "num_input_tokens_seen": 415212400, "step": 10075, "train_runtime": 38853.0677, "train_tokens_per_second": 10686.734 }, { "epoch": 0.6786964718556423, "grad_norm": 0.740275239838449, "learning_rate": 7.418197711994495e-06, "loss": 0.35831561088562014, "num_input_tokens_seen": 415412656, "step": 10080, "train_runtime": 38871.7935, "train_tokens_per_second": 10686.738 }, { "epoch": 0.6790331268516024, "grad_norm": 0.7606791695202693, "learning_rate": 7.4158830954133984e-06, "loss": 0.3677213668823242, "num_input_tokens_seen": 415627816, "step": 10085, "train_runtime": 38890.8396, "train_tokens_per_second": 10687.036 }, { "epoch": 0.6793697818475626, "grad_norm": 0.6552255293890689, "learning_rate": 7.413567803238298e-06, "loss": 0.36359615325927735, "num_input_tokens_seen": 415829736, "step": 10090, "train_runtime": 38909.4482, "train_tokens_per_second": 10687.115 }, { "epoch": 0.6797064368435227, "grad_norm": 0.6202946295201816, "learning_rate": 7.411251836116658e-06, "loss": 0.37451355457305907, "num_input_tokens_seen": 416043504, "step": 10095, "train_runtime": 38930.6935, "train_tokens_per_second": 10686.774 }, { "epoch": 0.6800430918394829, "grad_norm": 0.6635227905700292, "learning_rate": 7.408935194696132e-06, "loss": 0.38468940258026124, "num_input_tokens_seen": 416250416, "step": 10100, "train_runtime": 38951.0485, "train_tokens_per_second": 10686.501 }, { "epoch": 0.680379746835443, "grad_norm": 0.6920934381953584, "learning_rate": 7.406617879624558e-06, "loss": 0.39902026653289796, "num_input_tokens_seen": 416465832, "step": 10105, "train_runtime": 38970.7032, "train_tokens_per_second": 10686.639 }, { "epoch": 0.6807164018314031, "grad_norm": 0.6475982591120489, "learning_rate": 7.40429989154997e-06, "loss": 0.35114169120788574, "num_input_tokens_seen": 416669488, "step": 10110, "train_runtime": 38991.4745, "train_tokens_per_second": 10686.169 }, { "epoch": 0.6810530568273633, "grad_norm": 0.6784029254533922, "learning_rate": 7.4019812311205826e-06, "loss": 0.39939944744110106, "num_input_tokens_seen": 416884912, "step": 10115, "train_runtime": 39012.3521, "train_tokens_per_second": 10685.972 }, { "epoch": 0.6813897118233234, "grad_norm": 0.6956115768551924, "learning_rate": 7.399661898984805e-06, "loss": 0.39931697845458985, "num_input_tokens_seen": 417108472, "step": 10120, "train_runtime": 39032.7097, "train_tokens_per_second": 10686.126 }, { "epoch": 0.6817263668192836, "grad_norm": 0.677867918356341, "learning_rate": 7.397341895791228e-06, "loss": 0.38387293815612794, "num_input_tokens_seen": 417312712, "step": 10125, "train_runtime": 39051.6345, "train_tokens_per_second": 10686.178 }, { "epoch": 0.6820630218152437, "grad_norm": 0.7265992863239497, "learning_rate": 7.395021222188634e-06, "loss": 0.37428033351898193, "num_input_tokens_seen": 417521896, "step": 10130, "train_runtime": 39069.703, "train_tokens_per_second": 10686.59 }, { "epoch": 0.6823996768112038, "grad_norm": 0.7704857918940913, "learning_rate": 7.392699878825993e-06, "loss": 0.40662360191345215, "num_input_tokens_seen": 417718048, "step": 10135, "train_runtime": 39090.6256, "train_tokens_per_second": 10685.888 }, { "epoch": 0.682736331807164, "grad_norm": 0.6843857270050161, "learning_rate": 7.390377866352462e-06, "loss": 0.377101993560791, "num_input_tokens_seen": 417916192, "step": 10140, "train_runtime": 39109.3664, "train_tokens_per_second": 10685.834 }, { "epoch": 0.6830729868031241, "grad_norm": 0.7346869928851066, "learning_rate": 7.388055185417382e-06, "loss": 0.36733987331390383, "num_input_tokens_seen": 418129216, "step": 10145, "train_runtime": 39129.6452, "train_tokens_per_second": 10685.74 }, { "epoch": 0.6834096417990843, "grad_norm": 0.6662191276533772, "learning_rate": 7.3857318366702844e-06, "loss": 0.3580689668655396, "num_input_tokens_seen": 418337232, "step": 10150, "train_runtime": 39149.2641, "train_tokens_per_second": 10685.698 }, { "epoch": 0.6837462967950444, "grad_norm": 0.6844203713358812, "learning_rate": 7.383407820760885e-06, "loss": 0.3868083953857422, "num_input_tokens_seen": 418548472, "step": 10155, "train_runtime": 39168.0648, "train_tokens_per_second": 10685.963 }, { "epoch": 0.6840829517910045, "grad_norm": 0.7423862981581313, "learning_rate": 7.381083138339089e-06, "loss": 0.3858452796936035, "num_input_tokens_seen": 418748080, "step": 10160, "train_runtime": 39186.1886, "train_tokens_per_second": 10686.114 }, { "epoch": 0.6844196067869647, "grad_norm": 0.7393469067182956, "learning_rate": 7.378757790054988e-06, "loss": 0.41028356552124023, "num_input_tokens_seen": 418964592, "step": 10165, "train_runtime": 39204.8785, "train_tokens_per_second": 10686.542 }, { "epoch": 0.6847562617829248, "grad_norm": 0.7643367865675362, "learning_rate": 7.376431776558855e-06, "loss": 0.3995654106140137, "num_input_tokens_seen": 419172928, "step": 10170, "train_runtime": 39223.9881, "train_tokens_per_second": 10686.647 }, { "epoch": 0.685092916778885, "grad_norm": 0.6875036514026288, "learning_rate": 7.3741050985011546e-06, "loss": 0.36375017166137696, "num_input_tokens_seen": 419382480, "step": 10175, "train_runtime": 39244.8503, "train_tokens_per_second": 10686.306 }, { "epoch": 0.6854295717748451, "grad_norm": 0.6681316452088053, "learning_rate": 7.371777756532531e-06, "loss": 0.3597510576248169, "num_input_tokens_seen": 419592520, "step": 10180, "train_runtime": 39262.8779, "train_tokens_per_second": 10686.749 }, { "epoch": 0.6857662267708052, "grad_norm": 0.7938760955358328, "learning_rate": 7.369449751303823e-06, "loss": 0.4044830799102783, "num_input_tokens_seen": 419797944, "step": 10185, "train_runtime": 39281.5503, "train_tokens_per_second": 10686.899 }, { "epoch": 0.6861028817667654, "grad_norm": 0.557955105700375, "learning_rate": 7.367121083466048e-06, "loss": 0.3575391054153442, "num_input_tokens_seen": 420006672, "step": 10190, "train_runtime": 39299.9986, "train_tokens_per_second": 10687.193 }, { "epoch": 0.6864395367627255, "grad_norm": 0.8110655240572614, "learning_rate": 7.364791753670409e-06, "loss": 0.3898300647735596, "num_input_tokens_seen": 420217400, "step": 10195, "train_runtime": 39318.8843, "train_tokens_per_second": 10687.419 }, { "epoch": 0.6867761917586857, "grad_norm": 0.7378220919985732, "learning_rate": 7.362461762568298e-06, "loss": 0.3757860898971558, "num_input_tokens_seen": 420424224, "step": 10200, "train_runtime": 39337.7492, "train_tokens_per_second": 10687.552 }, { "epoch": 0.6871128467546458, "grad_norm": 0.6065295557649343, "learning_rate": 7.360131110811287e-06, "loss": 0.3570034742355347, "num_input_tokens_seen": 420634128, "step": 10205, "train_runtime": 39357.7219, "train_tokens_per_second": 10687.461 }, { "epoch": 0.6874495017506059, "grad_norm": 0.64791011883433, "learning_rate": 7.357799799051138e-06, "loss": 0.36814992427825927, "num_input_tokens_seen": 420838160, "step": 10210, "train_runtime": 39378.3192, "train_tokens_per_second": 10687.052 }, { "epoch": 0.6877861567465661, "grad_norm": 0.7999735835838163, "learning_rate": 7.355467827939794e-06, "loss": 0.38641581535339353, "num_input_tokens_seen": 421037376, "step": 10215, "train_runtime": 39399.4888, "train_tokens_per_second": 10686.366 }, { "epoch": 0.6881228117425262, "grad_norm": 0.7594131663383059, "learning_rate": 7.353135198129382e-06, "loss": 0.3961194038391113, "num_input_tokens_seen": 421234064, "step": 10220, "train_runtime": 39418.8372, "train_tokens_per_second": 10686.111 }, { "epoch": 0.6884594667384863, "grad_norm": 0.7522407207322911, "learning_rate": 7.350801910272216e-06, "loss": 0.38294548988342286, "num_input_tokens_seen": 421443328, "step": 10225, "train_runtime": 39439.7139, "train_tokens_per_second": 10685.76 }, { "epoch": 0.6887961217344465, "grad_norm": 0.727887360554576, "learning_rate": 7.348467965020791e-06, "loss": 0.34349799156188965, "num_input_tokens_seen": 421649952, "step": 10230, "train_runtime": 39458.1517, "train_tokens_per_second": 10686.004 }, { "epoch": 0.6891327767304066, "grad_norm": 0.7496311702211642, "learning_rate": 7.3461333630277885e-06, "loss": 0.36138913631439207, "num_input_tokens_seen": 421833520, "step": 10235, "train_runtime": 39477.0634, "train_tokens_per_second": 10685.534 }, { "epoch": 0.6894694317263668, "grad_norm": 0.6983154721671285, "learning_rate": 7.343798104946074e-06, "loss": 0.35587730407714846, "num_input_tokens_seen": 422044528, "step": 10240, "train_runtime": 39495.9631, "train_tokens_per_second": 10685.764 }, { "epoch": 0.6898060867223269, "grad_norm": 0.7202480336928142, "learning_rate": 7.341462191428692e-06, "loss": 0.38531670570373533, "num_input_tokens_seen": 422247696, "step": 10245, "train_runtime": 39515.5066, "train_tokens_per_second": 10685.62 }, { "epoch": 0.690142741718287, "grad_norm": 0.7132538694354471, "learning_rate": 7.339125623128874e-06, "loss": 0.3921194314956665, "num_input_tokens_seen": 422459304, "step": 10250, "train_runtime": 39536.6338, "train_tokens_per_second": 10685.262 }, { "epoch": 0.6904793967142472, "grad_norm": 0.6735364294513208, "learning_rate": 7.336788400700035e-06, "loss": 0.3726626396179199, "num_input_tokens_seen": 422660088, "step": 10255, "train_runtime": 39557.5535, "train_tokens_per_second": 10684.687 }, { "epoch": 0.6908160517102074, "grad_norm": 0.8048849516838724, "learning_rate": 7.334450524795771e-06, "loss": 0.4063465118408203, "num_input_tokens_seen": 422872800, "step": 10260, "train_runtime": 39578.9597, "train_tokens_per_second": 10684.283 }, { "epoch": 0.6911527067061676, "grad_norm": 0.6305545165844989, "learning_rate": 7.332111996069863e-06, "loss": 0.3725297212600708, "num_input_tokens_seen": 423082072, "step": 10265, "train_runtime": 39597.4119, "train_tokens_per_second": 10684.589 }, { "epoch": 0.6914893617021277, "grad_norm": 0.8278008658721903, "learning_rate": 7.32977281517627e-06, "loss": 0.40920419692993165, "num_input_tokens_seen": 423272216, "step": 10270, "train_runtime": 39615.8633, "train_tokens_per_second": 10684.412 }, { "epoch": 0.6918260166980879, "grad_norm": 0.7471530744554874, "learning_rate": 7.3274329827691406e-06, "loss": 0.38669724464416505, "num_input_tokens_seen": 423472208, "step": 10275, "train_runtime": 39633.4529, "train_tokens_per_second": 10684.716 }, { "epoch": 0.692162671694048, "grad_norm": 0.6111235515156666, "learning_rate": 7.325092499502796e-06, "loss": 0.35570402145385743, "num_input_tokens_seen": 423687856, "step": 10280, "train_runtime": 39651.1771, "train_tokens_per_second": 10685.379 }, { "epoch": 0.6924993266900081, "grad_norm": 0.6499640977037558, "learning_rate": 7.322751366031751e-06, "loss": 0.378520131111145, "num_input_tokens_seen": 423898072, "step": 10285, "train_runtime": 39671.7791, "train_tokens_per_second": 10685.129 }, { "epoch": 0.6928359816859683, "grad_norm": 0.8093149889146477, "learning_rate": 7.320409583010691e-06, "loss": 0.3600494384765625, "num_input_tokens_seen": 424109048, "step": 10290, "train_runtime": 39689.9445, "train_tokens_per_second": 10685.554 }, { "epoch": 0.6931726366819284, "grad_norm": 0.7076667443949146, "learning_rate": 7.318067151094493e-06, "loss": 0.42547016143798827, "num_input_tokens_seen": 424318192, "step": 10295, "train_runtime": 39708.2025, "train_tokens_per_second": 10685.908 }, { "epoch": 0.6935092916778886, "grad_norm": 0.641693317164351, "learning_rate": 7.3157240709382046e-06, "loss": 0.3932755947113037, "num_input_tokens_seen": 424533264, "step": 10300, "train_runtime": 39726.0811, "train_tokens_per_second": 10686.513 }, { "epoch": 0.6938459466738487, "grad_norm": 0.6998500438772407, "learning_rate": 7.313380343197066e-06, "loss": 0.36475656032562254, "num_input_tokens_seen": 424751728, "step": 10305, "train_runtime": 39743.9291, "train_tokens_per_second": 10687.21 }, { "epoch": 0.6941826016698088, "grad_norm": 0.6838574617604299, "learning_rate": 7.311035968526492e-06, "loss": 0.38222379684448243, "num_input_tokens_seen": 424959800, "step": 10310, "train_runtime": 39762.4167, "train_tokens_per_second": 10687.474 }, { "epoch": 0.694519256665769, "grad_norm": 0.7080521914288782, "learning_rate": 7.308690947582078e-06, "loss": 0.3883992910385132, "num_input_tokens_seen": 425157784, "step": 10315, "train_runtime": 39780.1867, "train_tokens_per_second": 10687.677 }, { "epoch": 0.6948559116617291, "grad_norm": 0.6660112356326988, "learning_rate": 7.306345281019602e-06, "loss": 0.37590556144714354, "num_input_tokens_seen": 425365648, "step": 10320, "train_runtime": 39800.3785, "train_tokens_per_second": 10687.477 }, { "epoch": 0.6951925666576892, "grad_norm": 0.7342946396982785, "learning_rate": 7.303998969495023e-06, "loss": 0.41351680755615233, "num_input_tokens_seen": 425568416, "step": 10325, "train_runtime": 39819.5778, "train_tokens_per_second": 10687.417 }, { "epoch": 0.6955292216536494, "grad_norm": 0.6926152097013336, "learning_rate": 7.301652013664479e-06, "loss": 0.39969031810760497, "num_input_tokens_seen": 425779512, "step": 10330, "train_runtime": 39837.7782, "train_tokens_per_second": 10687.833 }, { "epoch": 0.6958658766496095, "grad_norm": 0.7491967212568903, "learning_rate": 7.299304414184288e-06, "loss": 0.40522260665893556, "num_input_tokens_seen": 425988000, "step": 10335, "train_runtime": 39857.2099, "train_tokens_per_second": 10687.853 }, { "epoch": 0.6962025316455697, "grad_norm": 0.6465038604013034, "learning_rate": 7.296956171710951e-06, "loss": 0.39175798892974856, "num_input_tokens_seen": 426206320, "step": 10340, "train_runtime": 39875.4511, "train_tokens_per_second": 10688.439 }, { "epoch": 0.6965391866415298, "grad_norm": 0.7910144405459824, "learning_rate": 7.294607286901146e-06, "loss": 0.3964226245880127, "num_input_tokens_seen": 426414296, "step": 10345, "train_runtime": 39894.5752, "train_tokens_per_second": 10688.528 }, { "epoch": 0.69687584163749, "grad_norm": 0.7284138846299232, "learning_rate": 7.292257760411726e-06, "loss": 0.38352141380310056, "num_input_tokens_seen": 426614400, "step": 10350, "train_runtime": 39912.7291, "train_tokens_per_second": 10688.68 }, { "epoch": 0.6972124966334501, "grad_norm": 0.7255163692327485, "learning_rate": 7.289907592899737e-06, "loss": 0.3874220848083496, "num_input_tokens_seen": 426812104, "step": 10355, "train_runtime": 39931.8849, "train_tokens_per_second": 10688.504 }, { "epoch": 0.6975491516294102, "grad_norm": 0.6585592399663938, "learning_rate": 7.287556785022389e-06, "loss": 0.3855206251144409, "num_input_tokens_seen": 427021496, "step": 10360, "train_runtime": 39950.4214, "train_tokens_per_second": 10688.786 }, { "epoch": 0.6978858066253704, "grad_norm": 0.6954041536246143, "learning_rate": 7.285205337437082e-06, "loss": 0.3921914339065552, "num_input_tokens_seen": 427219408, "step": 10365, "train_runtime": 39970.2019, "train_tokens_per_second": 10688.448 }, { "epoch": 0.6982224616213305, "grad_norm": 0.7786724680121389, "learning_rate": 7.2828532508013895e-06, "loss": 0.394624662399292, "num_input_tokens_seen": 427425736, "step": 10370, "train_runtime": 39988.447, "train_tokens_per_second": 10688.731 }, { "epoch": 0.6985591166172906, "grad_norm": 0.7912043132737193, "learning_rate": 7.2805005257730625e-06, "loss": 0.3829874753952026, "num_input_tokens_seen": 427631560, "step": 10375, "train_runtime": 40007.1475, "train_tokens_per_second": 10688.879 }, { "epoch": 0.6988957716132508, "grad_norm": 0.6574774788946369, "learning_rate": 7.278147163010037e-06, "loss": 0.35963757038116456, "num_input_tokens_seen": 427844416, "step": 10380, "train_runtime": 40027.1287, "train_tokens_per_second": 10688.861 }, { "epoch": 0.6992324266092109, "grad_norm": 0.8002971968027444, "learning_rate": 7.275793163170423e-06, "loss": 0.3726168394088745, "num_input_tokens_seen": 428057872, "step": 10385, "train_runtime": 40046.84, "train_tokens_per_second": 10688.93 }, { "epoch": 0.6995690816051711, "grad_norm": 0.6900893060400439, "learning_rate": 7.273438526912506e-06, "loss": 0.3999228000640869, "num_input_tokens_seen": 428255304, "step": 10390, "train_runtime": 40065.2069, "train_tokens_per_second": 10688.958 }, { "epoch": 0.6999057366011312, "grad_norm": 0.6596232797554693, "learning_rate": 7.271083254894757e-06, "loss": 0.35472955703735354, "num_input_tokens_seen": 428458696, "step": 10395, "train_runtime": 40085.7509, "train_tokens_per_second": 10688.554 }, { "epoch": 0.7002423915970913, "grad_norm": 0.7254105223799083, "learning_rate": 7.268727347775815e-06, "loss": 0.3764458179473877, "num_input_tokens_seen": 428670448, "step": 10400, "train_runtime": 40103.2882, "train_tokens_per_second": 10689.16 }, { "epoch": 0.7005790465930515, "grad_norm": 0.6778107237928852, "learning_rate": 7.266370806214506e-06, "loss": 0.3269533395767212, "num_input_tokens_seen": 428878512, "step": 10405, "train_runtime": 40121.9441, "train_tokens_per_second": 10689.375 }, { "epoch": 0.7009157015890116, "grad_norm": 0.6589282832111446, "learning_rate": 7.264013630869827e-06, "loss": 0.3768906593322754, "num_input_tokens_seen": 429084504, "step": 10410, "train_runtime": 40142.0951, "train_tokens_per_second": 10689.141 }, { "epoch": 0.7012523565849718, "grad_norm": 0.6541515472646675, "learning_rate": 7.261655822400957e-06, "loss": 0.40319128036499025, "num_input_tokens_seen": 429299968, "step": 10415, "train_runtime": 40160.4404, "train_tokens_per_second": 10689.623 }, { "epoch": 0.7015890115809319, "grad_norm": 0.6932281853926004, "learning_rate": 7.259297381467248e-06, "loss": 0.38369026184082033, "num_input_tokens_seen": 429508232, "step": 10420, "train_runtime": 40180.312, "train_tokens_per_second": 10689.52 }, { "epoch": 0.701925666576892, "grad_norm": 0.6521274387335705, "learning_rate": 7.2569383087282285e-06, "loss": 0.34854898452758787, "num_input_tokens_seen": 429695824, "step": 10425, "train_runtime": 40200.0885, "train_tokens_per_second": 10688.927 }, { "epoch": 0.7022623215728522, "grad_norm": 0.6944799814761246, "learning_rate": 7.25457860484361e-06, "loss": 0.40300769805908204, "num_input_tokens_seen": 429901752, "step": 10430, "train_runtime": 40218.5148, "train_tokens_per_second": 10689.15 }, { "epoch": 0.7025989765688123, "grad_norm": 0.7049192698256109, "learning_rate": 7.252218270473274e-06, "loss": 0.3799306869506836, "num_input_tokens_seen": 430101800, "step": 10435, "train_runtime": 40239.4049, "train_tokens_per_second": 10688.573 }, { "epoch": 0.7029356315647725, "grad_norm": 0.6954056006834699, "learning_rate": 7.249857306277279e-06, "loss": 0.3723963737487793, "num_input_tokens_seen": 430305440, "step": 10440, "train_runtime": 40258.1565, "train_tokens_per_second": 10688.652 }, { "epoch": 0.7032722865607326, "grad_norm": 0.8845011355772152, "learning_rate": 7.247495712915864e-06, "loss": 0.35449867248535155, "num_input_tokens_seen": 430511944, "step": 10445, "train_runtime": 40275.8894, "train_tokens_per_second": 10689.074 }, { "epoch": 0.7036089415566927, "grad_norm": 0.6560237290929706, "learning_rate": 7.245133491049439e-06, "loss": 0.3680055856704712, "num_input_tokens_seen": 430718064, "step": 10450, "train_runtime": 40294.589, "train_tokens_per_second": 10689.228 }, { "epoch": 0.7039455965526529, "grad_norm": 0.6871060449083065, "learning_rate": 7.242770641338592e-06, "loss": 0.41347622871398926, "num_input_tokens_seen": 430925032, "step": 10455, "train_runtime": 40314.5999, "train_tokens_per_second": 10689.056 }, { "epoch": 0.704282251548613, "grad_norm": 0.6718278155010281, "learning_rate": 7.240407164444088e-06, "loss": 0.36804995536804197, "num_input_tokens_seen": 431126576, "step": 10460, "train_runtime": 40333.1829, "train_tokens_per_second": 10689.129 }, { "epoch": 0.7046189065445732, "grad_norm": 0.7388537433551248, "learning_rate": 7.238043061026862e-06, "loss": 0.3466887712478638, "num_input_tokens_seen": 431326248, "step": 10465, "train_runtime": 40354.1084, "train_tokens_per_second": 10688.534 }, { "epoch": 0.7049555615405333, "grad_norm": 0.6564475904424955, "learning_rate": 7.235678331748034e-06, "loss": 0.3545418977737427, "num_input_tokens_seen": 431514160, "step": 10470, "train_runtime": 40373.143, "train_tokens_per_second": 10688.149 }, { "epoch": 0.7052922165364934, "grad_norm": 0.7388176508445038, "learning_rate": 7.233312977268887e-06, "loss": 0.41165738105773925, "num_input_tokens_seen": 431724360, "step": 10475, "train_runtime": 40391.8781, "train_tokens_per_second": 10688.395 }, { "epoch": 0.7056288715324536, "grad_norm": 0.830380027525509, "learning_rate": 7.230946998250889e-06, "loss": 0.3737924098968506, "num_input_tokens_seen": 431917672, "step": 10480, "train_runtime": 40411.0058, "train_tokens_per_second": 10688.12 }, { "epoch": 0.7059655265284137, "grad_norm": 0.6767067336434849, "learning_rate": 7.228580395355676e-06, "loss": 0.3506386995315552, "num_input_tokens_seen": 432120216, "step": 10485, "train_runtime": 40430.6314, "train_tokens_per_second": 10687.941 }, { "epoch": 0.7063021815243739, "grad_norm": 0.7247377957595906, "learning_rate": 7.226213169245062e-06, "loss": 0.386786675453186, "num_input_tokens_seen": 432328008, "step": 10490, "train_runtime": 40449.6766, "train_tokens_per_second": 10688.046 }, { "epoch": 0.706638836520334, "grad_norm": 0.7100285567952964, "learning_rate": 7.223845320581035e-06, "loss": 0.35976200103759765, "num_input_tokens_seen": 432531024, "step": 10495, "train_runtime": 40470.2378, "train_tokens_per_second": 10687.632 }, { "epoch": 0.7069754915162941, "grad_norm": 0.656155967860376, "learning_rate": 7.221476850025754e-06, "loss": 0.3774406909942627, "num_input_tokens_seen": 432745264, "step": 10500, "train_runtime": 40491.1351, "train_tokens_per_second": 10687.408 }, { "epoch": 0.7073121465122543, "grad_norm": 0.6865468077855489, "learning_rate": 7.219107758241557e-06, "loss": 0.38320484161376955, "num_input_tokens_seen": 432954176, "step": 10505, "train_runtime": 40512.5379, "train_tokens_per_second": 10686.918 }, { "epoch": 0.7076488015082144, "grad_norm": 0.7179902693578971, "learning_rate": 7.2167380458909505e-06, "loss": 0.37953317165374756, "num_input_tokens_seen": 433163976, "step": 10510, "train_runtime": 40531.555, "train_tokens_per_second": 10687.08 }, { "epoch": 0.7079854565041745, "grad_norm": 0.6441499362064235, "learning_rate": 7.214367713636619e-06, "loss": 0.38411047458648684, "num_input_tokens_seen": 433373176, "step": 10515, "train_runtime": 40551.1244, "train_tokens_per_second": 10687.082 }, { "epoch": 0.7083221115001347, "grad_norm": 0.6966231724317324, "learning_rate": 7.211996762141418e-06, "loss": 0.38234715461730956, "num_input_tokens_seen": 433577560, "step": 10520, "train_runtime": 40569.8218, "train_tokens_per_second": 10687.194 }, { "epoch": 0.7086587664960948, "grad_norm": 0.6601517604557696, "learning_rate": 7.209625192068374e-06, "loss": 0.40475215911865237, "num_input_tokens_seen": 433783688, "step": 10525, "train_runtime": 40587.983, "train_tokens_per_second": 10687.491 }, { "epoch": 0.708995421492055, "grad_norm": 0.6602145729498561, "learning_rate": 7.207253004080692e-06, "loss": 0.3728623390197754, "num_input_tokens_seen": 433999856, "step": 10530, "train_runtime": 40606.6638, "train_tokens_per_second": 10687.897 }, { "epoch": 0.7093320764880151, "grad_norm": 0.7299372609939597, "learning_rate": 7.204880198841746e-06, "loss": 0.34524950981140134, "num_input_tokens_seen": 434200576, "step": 10535, "train_runtime": 40624.9509, "train_tokens_per_second": 10688.027 }, { "epoch": 0.7096687314839752, "grad_norm": 0.7614707310635431, "learning_rate": 7.2025067770150835e-06, "loss": 0.39874801635742185, "num_input_tokens_seen": 434413928, "step": 10540, "train_runtime": 40645.1284, "train_tokens_per_second": 10687.97 }, { "epoch": 0.7100053864799354, "grad_norm": 0.9763672782491839, "learning_rate": 7.2001327392644235e-06, "loss": 0.3490768909454346, "num_input_tokens_seen": 434627592, "step": 10545, "train_runtime": 40663.9406, "train_tokens_per_second": 10688.28 }, { "epoch": 0.7103420414758955, "grad_norm": 0.7383159572023967, "learning_rate": 7.197758086253659e-06, "loss": 0.39962170124053953, "num_input_tokens_seen": 434837336, "step": 10550, "train_runtime": 40682.9775, "train_tokens_per_second": 10688.434 }, { "epoch": 0.7106786964718557, "grad_norm": 0.6832629001493619, "learning_rate": 7.195382818646854e-06, "loss": 0.3936068773269653, "num_input_tokens_seen": 435036152, "step": 10555, "train_runtime": 40702.1982, "train_tokens_per_second": 10688.272 }, { "epoch": 0.7110153514678158, "grad_norm": 0.715937789388788, "learning_rate": 7.1930069371082445e-06, "loss": 0.3686094284057617, "num_input_tokens_seen": 435235880, "step": 10560, "train_runtime": 40723.5402, "train_tokens_per_second": 10687.575 }, { "epoch": 0.7113520064637759, "grad_norm": 0.6727518034964773, "learning_rate": 7.190630442302238e-06, "loss": 0.383117151260376, "num_input_tokens_seen": 435448912, "step": 10565, "train_runtime": 40745.2908, "train_tokens_per_second": 10687.098 }, { "epoch": 0.7116886614597361, "grad_norm": 0.6598342879806273, "learning_rate": 7.188253334893414e-06, "loss": 0.40042915344238283, "num_input_tokens_seen": 435656144, "step": 10570, "train_runtime": 40764.9709, "train_tokens_per_second": 10687.022 }, { "epoch": 0.7120253164556962, "grad_norm": 0.8779827303007216, "learning_rate": 7.18587561554652e-06, "loss": 0.40506958961486816, "num_input_tokens_seen": 435853744, "step": 10575, "train_runtime": 40782.9975, "train_tokens_per_second": 10687.143 }, { "epoch": 0.7123619714516564, "grad_norm": 0.6443602482351047, "learning_rate": 7.183497284926483e-06, "loss": 0.3676735877990723, "num_input_tokens_seen": 436073520, "step": 10580, "train_runtime": 40801.4169, "train_tokens_per_second": 10687.705 }, { "epoch": 0.7126986264476165, "grad_norm": 0.7065383460183897, "learning_rate": 7.181118343698392e-06, "loss": 0.3592132806777954, "num_input_tokens_seen": 436271848, "step": 10585, "train_runtime": 40820.4753, "train_tokens_per_second": 10687.574 }, { "epoch": 0.7130352814435766, "grad_norm": 0.6797940395746718, "learning_rate": 7.178738792527512e-06, "loss": 0.39815583229064944, "num_input_tokens_seen": 436477120, "step": 10590, "train_runtime": 40841.2474, "train_tokens_per_second": 10687.164 }, { "epoch": 0.7133719364395368, "grad_norm": 0.7142485722323177, "learning_rate": 7.176358632079277e-06, "loss": 0.369372296333313, "num_input_tokens_seen": 436678080, "step": 10595, "train_runtime": 40861.3438, "train_tokens_per_second": 10686.826 }, { "epoch": 0.7137085914354969, "grad_norm": 0.6589481319311858, "learning_rate": 7.173977863019288e-06, "loss": 0.37570168972015383, "num_input_tokens_seen": 436892432, "step": 10600, "train_runtime": 40880.7701, "train_tokens_per_second": 10686.991 }, { "epoch": 0.7140452464314571, "grad_norm": 0.6522310737311042, "learning_rate": 7.171596486013323e-06, "loss": 0.3546773910522461, "num_input_tokens_seen": 437107424, "step": 10605, "train_runtime": 40900.5813, "train_tokens_per_second": 10687.071 }, { "epoch": 0.7143819014274172, "grad_norm": 0.7722755642514302, "learning_rate": 7.169214501727326e-06, "loss": 0.3804292917251587, "num_input_tokens_seen": 437297864, "step": 10610, "train_runtime": 40920.0291, "train_tokens_per_second": 10686.646 }, { "epoch": 0.7147185564233773, "grad_norm": 0.7056286718315669, "learning_rate": 7.16683191082741e-06, "loss": 0.36931428909301756, "num_input_tokens_seen": 437504304, "step": 10615, "train_runtime": 40938.0622, "train_tokens_per_second": 10686.981 }, { "epoch": 0.7150552114193375, "grad_norm": 0.831227174342315, "learning_rate": 7.16444871397986e-06, "loss": 0.3698180913925171, "num_input_tokens_seen": 437699728, "step": 10620, "train_runtime": 40957.2554, "train_tokens_per_second": 10686.745 }, { "epoch": 0.7153918664152976, "grad_norm": 0.7247737024364522, "learning_rate": 7.162064911851129e-06, "loss": 0.3631428241729736, "num_input_tokens_seen": 437903640, "step": 10625, "train_runtime": 40976.7935, "train_tokens_per_second": 10686.625 }, { "epoch": 0.7157285214112578, "grad_norm": 0.6628179487907825, "learning_rate": 7.15968050510784e-06, "loss": 0.3948248863220215, "num_input_tokens_seen": 438105016, "step": 10630, "train_runtime": 40994.888, "train_tokens_per_second": 10686.821 }, { "epoch": 0.7160651764072179, "grad_norm": 0.8168714515151165, "learning_rate": 7.1572954944167834e-06, "loss": 0.3754547357559204, "num_input_tokens_seen": 438310248, "step": 10635, "train_runtime": 41015.8888, "train_tokens_per_second": 10686.353 }, { "epoch": 0.716401831403178, "grad_norm": 0.6602518404325336, "learning_rate": 7.154909880444922e-06, "loss": 0.39936065673828125, "num_input_tokens_seen": 438521312, "step": 10640, "train_runtime": 41036.3943, "train_tokens_per_second": 10686.156 }, { "epoch": 0.7167384863991382, "grad_norm": 0.7521264951645753, "learning_rate": 7.152523663859384e-06, "loss": 0.3807456731796265, "num_input_tokens_seen": 438722816, "step": 10645, "train_runtime": 41055.0068, "train_tokens_per_second": 10686.22 }, { "epoch": 0.7170751413950983, "grad_norm": 0.7306142514768856, "learning_rate": 7.150136845327466e-06, "loss": 0.36783733367919924, "num_input_tokens_seen": 438925456, "step": 10650, "train_runtime": 41076.4243, "train_tokens_per_second": 10685.581 }, { "epoch": 0.7174117963910585, "grad_norm": 0.8709823215373376, "learning_rate": 7.147749425516637e-06, "loss": 0.3747855663299561, "num_input_tokens_seen": 439141536, "step": 10655, "train_runtime": 41095.4671, "train_tokens_per_second": 10685.887 }, { "epoch": 0.7177484513870186, "grad_norm": 0.812556501241643, "learning_rate": 7.145361405094529e-06, "loss": 0.3628098487854004, "num_input_tokens_seen": 439359312, "step": 10660, "train_runtime": 41113.7215, "train_tokens_per_second": 10686.44 }, { "epoch": 0.7180851063829787, "grad_norm": 0.6599384711517235, "learning_rate": 7.142972784728945e-06, "loss": 0.34280431270599365, "num_input_tokens_seen": 439560568, "step": 10665, "train_runtime": 41134.1807, "train_tokens_per_second": 10686.017 }, { "epoch": 0.7184217613789389, "grad_norm": 0.7789777952685607, "learning_rate": 7.140583565087856e-06, "loss": 0.3574836254119873, "num_input_tokens_seen": 439766552, "step": 10670, "train_runtime": 41154.0019, "train_tokens_per_second": 10685.876 }, { "epoch": 0.718758416374899, "grad_norm": 0.7435132513398323, "learning_rate": 7.138193746839399e-06, "loss": 0.39718060493469237, "num_input_tokens_seen": 439983136, "step": 10675, "train_runtime": 41172.2559, "train_tokens_per_second": 10686.399 }, { "epoch": 0.7190950713708592, "grad_norm": 0.6803660616077178, "learning_rate": 7.135803330651878e-06, "loss": 0.3782310724258423, "num_input_tokens_seen": 440202440, "step": 10680, "train_runtime": 41191.6124, "train_tokens_per_second": 10686.701 }, { "epoch": 0.7194317263668193, "grad_norm": 0.7125652081141042, "learning_rate": 7.133412317193766e-06, "loss": 0.3681192874908447, "num_input_tokens_seen": 440416504, "step": 10685, "train_runtime": 41211.4493, "train_tokens_per_second": 10686.751 }, { "epoch": 0.7197683813627794, "grad_norm": 0.7419560899979003, "learning_rate": 7.131020707133703e-06, "loss": 0.38283090591430663, "num_input_tokens_seen": 440609608, "step": 10690, "train_runtime": 41229.7787, "train_tokens_per_second": 10686.684 }, { "epoch": 0.7201050363587396, "grad_norm": 0.7968778352885109, "learning_rate": 7.128628501140495e-06, "loss": 0.3989142417907715, "num_input_tokens_seen": 440806896, "step": 10695, "train_runtime": 41248.1298, "train_tokens_per_second": 10686.712 }, { "epoch": 0.7204416913546997, "grad_norm": 0.673629520281263, "learning_rate": 7.126235699883115e-06, "loss": 0.35800268650054934, "num_input_tokens_seen": 440998768, "step": 10700, "train_runtime": 41269.5082, "train_tokens_per_second": 10685.826 }, { "epoch": 0.7207783463506598, "grad_norm": 0.6896100907905122, "learning_rate": 7.1238423040306995e-06, "loss": 0.37061266899108886, "num_input_tokens_seen": 441207136, "step": 10705, "train_runtime": 41288.9561, "train_tokens_per_second": 10685.839 }, { "epoch": 0.72111500134662, "grad_norm": 0.6708028160590185, "learning_rate": 7.121448314252557e-06, "loss": 0.3351728439331055, "num_input_tokens_seen": 441426320, "step": 10710, "train_runtime": 41309.9046, "train_tokens_per_second": 10685.726 }, { "epoch": 0.7214516563425801, "grad_norm": 0.7137852141473167, "learning_rate": 7.1190537312181586e-06, "loss": 0.3610539436340332, "num_input_tokens_seen": 441620616, "step": 10715, "train_runtime": 41328.5788, "train_tokens_per_second": 10685.599 }, { "epoch": 0.7217883113385403, "grad_norm": 0.7408303523165507, "learning_rate": 7.116658555597141e-06, "loss": 0.3613840103149414, "num_input_tokens_seen": 441798336, "step": 10720, "train_runtime": 41348.0933, "train_tokens_per_second": 10684.854 }, { "epoch": 0.7221249663345004, "grad_norm": 0.7191342561663814, "learning_rate": 7.114262788059308e-06, "loss": 0.36504974365234377, "num_input_tokens_seen": 441997104, "step": 10725, "train_runtime": 41367.324, "train_tokens_per_second": 10684.692 }, { "epoch": 0.7224616213304605, "grad_norm": 0.7013855969366385, "learning_rate": 7.111866429274627e-06, "loss": 0.37516586780548095, "num_input_tokens_seen": 442201352, "step": 10730, "train_runtime": 41385.2018, "train_tokens_per_second": 10685.011 }, { "epoch": 0.7227982763264207, "grad_norm": 0.7647875974113382, "learning_rate": 7.1094694799132356e-06, "loss": 0.3924453020095825, "num_input_tokens_seen": 442414104, "step": 10735, "train_runtime": 41406.1554, "train_tokens_per_second": 10684.742 }, { "epoch": 0.7231349313223808, "grad_norm": 0.697927229698881, "learning_rate": 7.10707194064543e-06, "loss": 0.3591035842895508, "num_input_tokens_seen": 442618640, "step": 10740, "train_runtime": 41426.1799, "train_tokens_per_second": 10684.515 }, { "epoch": 0.723471586318341, "grad_norm": 0.7297513439104568, "learning_rate": 7.104673812141676e-06, "loss": 0.40500354766845703, "num_input_tokens_seen": 442830608, "step": 10745, "train_runtime": 41445.6639, "train_tokens_per_second": 10684.606 }, { "epoch": 0.7238082413143011, "grad_norm": 0.7660361819345648, "learning_rate": 7.102275095072601e-06, "loss": 0.394919753074646, "num_input_tokens_seen": 443050248, "step": 10750, "train_runtime": 41467.3326, "train_tokens_per_second": 10684.32 }, { "epoch": 0.7241448963102612, "grad_norm": 0.6990965885873636, "learning_rate": 7.099875790108998e-06, "loss": 0.3703528642654419, "num_input_tokens_seen": 443264728, "step": 10755, "train_runtime": 41486.2287, "train_tokens_per_second": 10684.623 }, { "epoch": 0.7244815513062214, "grad_norm": 0.6403428133014898, "learning_rate": 7.097475897921827e-06, "loss": 0.3756544589996338, "num_input_tokens_seen": 443469040, "step": 10760, "train_runtime": 41506.0207, "train_tokens_per_second": 10684.451 }, { "epoch": 0.7248182063021815, "grad_norm": 0.6961286128783066, "learning_rate": 7.09507541918221e-06, "loss": 0.3966048717498779, "num_input_tokens_seen": 443672288, "step": 10765, "train_runtime": 41525.8758, "train_tokens_per_second": 10684.237 }, { "epoch": 0.7251548612981417, "grad_norm": 0.6211737577705854, "learning_rate": 7.092674354561433e-06, "loss": 0.39023168087005616, "num_input_tokens_seen": 443881368, "step": 10770, "train_runtime": 41544.6123, "train_tokens_per_second": 10684.451 }, { "epoch": 0.7254915162941018, "grad_norm": 0.7497089499244363, "learning_rate": 7.090272704730945e-06, "loss": 0.35589871406555174, "num_input_tokens_seen": 444074168, "step": 10775, "train_runtime": 41562.3662, "train_tokens_per_second": 10684.526 }, { "epoch": 0.7258281712900619, "grad_norm": 0.6723570445503442, "learning_rate": 7.08787047036236e-06, "loss": 0.35904736518859864, "num_input_tokens_seen": 444294216, "step": 10780, "train_runtime": 41580.8104, "train_tokens_per_second": 10685.078 }, { "epoch": 0.7261648262860221, "grad_norm": 0.9370549641257886, "learning_rate": 7.085467652127457e-06, "loss": 0.38192019462585447, "num_input_tokens_seen": 444506704, "step": 10785, "train_runtime": 41599.1113, "train_tokens_per_second": 10685.486 }, { "epoch": 0.7265014812819822, "grad_norm": 0.6798952678161866, "learning_rate": 7.083064250698175e-06, "loss": 0.35553314685821535, "num_input_tokens_seen": 444723184, "step": 10790, "train_runtime": 41619.489, "train_tokens_per_second": 10685.455 }, { "epoch": 0.7268381362779424, "grad_norm": 0.69171967454897, "learning_rate": 7.0806602667466175e-06, "loss": 0.3841921329498291, "num_input_tokens_seen": 444939368, "step": 10795, "train_runtime": 41638.0864, "train_tokens_per_second": 10685.875 }, { "epoch": 0.7271747912739025, "grad_norm": 0.7104437227975985, "learning_rate": 7.078255700945051e-06, "loss": 0.3922066926956177, "num_input_tokens_seen": 445139024, "step": 10800, "train_runtime": 41656.3606, "train_tokens_per_second": 10685.98 }, { "epoch": 0.7275114462698626, "grad_norm": 0.7155269231404097, "learning_rate": 7.075850553965904e-06, "loss": 0.37084646224975587, "num_input_tokens_seen": 445335864, "step": 10805, "train_runtime": 41673.8526, "train_tokens_per_second": 10686.218 }, { "epoch": 0.7278481012658228, "grad_norm": 0.6893007569181969, "learning_rate": 7.07344482648177e-06, "loss": 0.38821897506713865, "num_input_tokens_seen": 445544240, "step": 10810, "train_runtime": 41692.1969, "train_tokens_per_second": 10686.514 }, { "epoch": 0.7281847562617829, "grad_norm": 0.7494254445212907, "learning_rate": 7.071038519165402e-06, "loss": 0.384244966506958, "num_input_tokens_seen": 445748416, "step": 10815, "train_runtime": 41712.1064, "train_tokens_per_second": 10686.308 }, { "epoch": 0.7285214112577431, "grad_norm": 0.7288423517331241, "learning_rate": 7.068631632689716e-06, "loss": 0.3832577705383301, "num_input_tokens_seen": 445960504, "step": 10820, "train_runtime": 41731.2617, "train_tokens_per_second": 10686.485 }, { "epoch": 0.7288580662537032, "grad_norm": 0.77796714542003, "learning_rate": 7.066224167727791e-06, "loss": 0.39018371105194094, "num_input_tokens_seen": 446168216, "step": 10825, "train_runtime": 41750.3285, "train_tokens_per_second": 10686.58 }, { "epoch": 0.7291947212496633, "grad_norm": 0.7276846831076024, "learning_rate": 7.063816124952865e-06, "loss": 0.3697798252105713, "num_input_tokens_seen": 446373224, "step": 10830, "train_runtime": 41769.247, "train_tokens_per_second": 10686.648 }, { "epoch": 0.7295313762456235, "grad_norm": 0.6520985398324872, "learning_rate": 7.061407505038341e-06, "loss": 0.3587232828140259, "num_input_tokens_seen": 446577512, "step": 10835, "train_runtime": 41788.0431, "train_tokens_per_second": 10686.729 }, { "epoch": 0.7298680312415836, "grad_norm": 0.7374973365824962, "learning_rate": 7.058998308657782e-06, "loss": 0.391416597366333, "num_input_tokens_seen": 446791944, "step": 10840, "train_runtime": 41806.4396, "train_tokens_per_second": 10687.156 }, { "epoch": 0.7302046862375438, "grad_norm": 0.6400546675458246, "learning_rate": 7.056588536484912e-06, "loss": 0.3513751983642578, "num_input_tokens_seen": 446985776, "step": 10845, "train_runtime": 41824.065, "train_tokens_per_second": 10687.287 }, { "epoch": 0.7305413412335039, "grad_norm": 0.6533833701460734, "learning_rate": 7.0541781891936145e-06, "loss": 0.35227982997894286, "num_input_tokens_seen": 447193200, "step": 10850, "train_runtime": 41843.7226, "train_tokens_per_second": 10687.223 }, { "epoch": 0.730877996229464, "grad_norm": 0.7404760148816729, "learning_rate": 7.0517672674579364e-06, "loss": 0.3693334341049194, "num_input_tokens_seen": 447396936, "step": 10855, "train_runtime": 41862.2862, "train_tokens_per_second": 10687.351 }, { "epoch": 0.7312146512254242, "grad_norm": 0.7015953906194706, "learning_rate": 7.049355771952087e-06, "loss": 0.3687720775604248, "num_input_tokens_seen": 447596120, "step": 10860, "train_runtime": 41882.1204, "train_tokens_per_second": 10687.045 }, { "epoch": 0.7315513062213843, "grad_norm": 0.6770179221955845, "learning_rate": 7.046943703350429e-06, "loss": 0.3729452133178711, "num_input_tokens_seen": 447809608, "step": 10865, "train_runtime": 41903.8312, "train_tokens_per_second": 10686.603 }, { "epoch": 0.7318879612173445, "grad_norm": 0.6175997386918415, "learning_rate": 7.044531062327492e-06, "loss": 0.35283937454223635, "num_input_tokens_seen": 448010920, "step": 10870, "train_runtime": 41922.6828, "train_tokens_per_second": 10686.599 }, { "epoch": 0.7322246162133046, "grad_norm": 0.6963823847392399, "learning_rate": 7.042117849557963e-06, "loss": 0.37329764366149903, "num_input_tokens_seen": 448220872, "step": 10875, "train_runtime": 41942.5503, "train_tokens_per_second": 10686.543 }, { "epoch": 0.7325612712092647, "grad_norm": 0.7557521944510026, "learning_rate": 7.0397040657166885e-06, "loss": 0.37408156394958497, "num_input_tokens_seen": 448434456, "step": 10880, "train_runtime": 41960.5156, "train_tokens_per_second": 10687.058 }, { "epoch": 0.7328979262052249, "grad_norm": 0.6382986420693771, "learning_rate": 7.037289711478676e-06, "loss": 0.358691930770874, "num_input_tokens_seen": 448634960, "step": 10885, "train_runtime": 41979.7843, "train_tokens_per_second": 10686.929 }, { "epoch": 0.733234581201185, "grad_norm": 0.6949925302213746, "learning_rate": 7.034874787519095e-06, "loss": 0.3698907375335693, "num_input_tokens_seen": 448845480, "step": 10890, "train_runtime": 41999.4542, "train_tokens_per_second": 10686.936 }, { "epoch": 0.7335712361971451, "grad_norm": 0.6399261815413453, "learning_rate": 7.0324592945132655e-06, "loss": 0.41274294853210447, "num_input_tokens_seen": 449054024, "step": 10895, "train_runtime": 42017.5602, "train_tokens_per_second": 10687.294 }, { "epoch": 0.7339078911931053, "grad_norm": 0.7148165235350069, "learning_rate": 7.0300432331366764e-06, "loss": 0.3834859371185303, "num_input_tokens_seen": 449255832, "step": 10900, "train_runtime": 42036.2746, "train_tokens_per_second": 10687.337 }, { "epoch": 0.7342445461890654, "grad_norm": 0.6848742930588225, "learning_rate": 7.02762660406497e-06, "loss": 0.38342580795288084, "num_input_tokens_seen": 449462832, "step": 10905, "train_runtime": 42054.8584, "train_tokens_per_second": 10687.536 }, { "epoch": 0.7345812011850256, "grad_norm": 0.5959707693293701, "learning_rate": 7.02520940797395e-06, "loss": 0.367600417137146, "num_input_tokens_seen": 449659216, "step": 10910, "train_runtime": 42074.5994, "train_tokens_per_second": 10687.189 }, { "epoch": 0.7349178561809857, "grad_norm": 0.618267371966921, "learning_rate": 7.022791645539576e-06, "loss": 0.37008962631225584, "num_input_tokens_seen": 449852952, "step": 10915, "train_runtime": 42092.0614, "train_tokens_per_second": 10687.359 }, { "epoch": 0.7352545111769458, "grad_norm": 0.7078940390854687, "learning_rate": 7.02037331743797e-06, "loss": 0.4102656364440918, "num_input_tokens_seen": 450059032, "step": 10920, "train_runtime": 42110.0697, "train_tokens_per_second": 10687.682 }, { "epoch": 0.735591166172906, "grad_norm": 0.6684820417301593, "learning_rate": 7.0179544243454076e-06, "loss": 0.3626387357711792, "num_input_tokens_seen": 450273520, "step": 10925, "train_runtime": 42128.6541, "train_tokens_per_second": 10688.059 }, { "epoch": 0.7359278211688661, "grad_norm": 0.7701723746956224, "learning_rate": 7.0155349669383245e-06, "loss": 0.37200322151184084, "num_input_tokens_seen": 450481912, "step": 10930, "train_runtime": 42146.9945, "train_tokens_per_second": 10688.352 }, { "epoch": 0.7362644761648263, "grad_norm": 0.6768098746750784, "learning_rate": 7.013114945893316e-06, "loss": 0.3670751333236694, "num_input_tokens_seen": 450693176, "step": 10935, "train_runtime": 42166.0458, "train_tokens_per_second": 10688.533 }, { "epoch": 0.7366011311607864, "grad_norm": 0.6912217590476428, "learning_rate": 7.010694361887131e-06, "loss": 0.3674756050109863, "num_input_tokens_seen": 450909400, "step": 10940, "train_runtime": 42186.9441, "train_tokens_per_second": 10688.364 }, { "epoch": 0.7369377861567465, "grad_norm": 0.6746521300446887, "learning_rate": 7.008273215596681e-06, "loss": 0.3838853597640991, "num_input_tokens_seen": 451114728, "step": 10945, "train_runtime": 42205.5613, "train_tokens_per_second": 10688.514 }, { "epoch": 0.7372744411527067, "grad_norm": 0.7445899425189234, "learning_rate": 7.005851507699029e-06, "loss": 0.38232309818267823, "num_input_tokens_seen": 451328072, "step": 10950, "train_runtime": 42222.9065, "train_tokens_per_second": 10689.176 }, { "epoch": 0.7376110961486668, "grad_norm": 0.6793130439634159, "learning_rate": 7.003429238871399e-06, "loss": 0.3726634502410889, "num_input_tokens_seen": 451545368, "step": 10955, "train_runtime": 42243.3223, "train_tokens_per_second": 10689.154 }, { "epoch": 0.737947751144627, "grad_norm": 0.7194776070127107, "learning_rate": 7.001006409791171e-06, "loss": 0.4108330726623535, "num_input_tokens_seen": 451748832, "step": 10960, "train_runtime": 42263.4231, "train_tokens_per_second": 10688.884 }, { "epoch": 0.7382844061405871, "grad_norm": 0.9133862403016623, "learning_rate": 6.998583021135882e-06, "loss": 0.382647705078125, "num_input_tokens_seen": 451953384, "step": 10965, "train_runtime": 42281.4667, "train_tokens_per_second": 10689.161 }, { "epoch": 0.7386210611365472, "grad_norm": 0.758335718493767, "learning_rate": 6.996159073583224e-06, "loss": 0.37371368408203126, "num_input_tokens_seen": 452158936, "step": 10970, "train_runtime": 42300.208, "train_tokens_per_second": 10689.284 }, { "epoch": 0.7389577161325074, "grad_norm": 0.6929870748566718, "learning_rate": 6.993734567811046e-06, "loss": 0.3562830924987793, "num_input_tokens_seen": 452365792, "step": 10975, "train_runtime": 42321.8835, "train_tokens_per_second": 10688.697 }, { "epoch": 0.7392943711284675, "grad_norm": 0.654717225974549, "learning_rate": 6.991309504497352e-06, "loss": 0.3764050483703613, "num_input_tokens_seen": 452575728, "step": 10980, "train_runtime": 42342.0523, "train_tokens_per_second": 10688.564 }, { "epoch": 0.7396310261244277, "grad_norm": 0.7713883569284257, "learning_rate": 6.988883884320307e-06, "loss": 0.3547018051147461, "num_input_tokens_seen": 452773176, "step": 10985, "train_runtime": 42361.4723, "train_tokens_per_second": 10688.325 }, { "epoch": 0.7399676811203878, "grad_norm": 0.7318984755785534, "learning_rate": 6.9864577079582254e-06, "loss": 0.39829282760620116, "num_input_tokens_seen": 452984808, "step": 10990, "train_runtime": 42381.7239, "train_tokens_per_second": 10688.211 }, { "epoch": 0.7403043361163479, "grad_norm": 0.7757983492657621, "learning_rate": 6.984030976089581e-06, "loss": 0.36774492263793945, "num_input_tokens_seen": 453190224, "step": 10995, "train_runtime": 42399.9417, "train_tokens_per_second": 10688.463 }, { "epoch": 0.7406409911123081, "grad_norm": 0.7244074592990889, "learning_rate": 6.981603689392999e-06, "loss": 0.37537398338317873, "num_input_tokens_seen": 453395992, "step": 11000, "train_runtime": 42421.2916, "train_tokens_per_second": 10687.935 }, { "epoch": 0.7409776461082682, "grad_norm": 0.734709199474308, "learning_rate": 6.979175848547263e-06, "loss": 0.36416330337524416, "num_input_tokens_seen": 453597840, "step": 11005, "train_runtime": 42440.308, "train_tokens_per_second": 10687.902 }, { "epoch": 0.7413143011042284, "grad_norm": 0.7573738322193102, "learning_rate": 6.976747454231316e-06, "loss": 0.36149938106536866, "num_input_tokens_seen": 453795976, "step": 11010, "train_runtime": 42461.3279, "train_tokens_per_second": 10687.277 }, { "epoch": 0.7416509561001885, "grad_norm": 5.773536421523387, "learning_rate": 6.974318507124245e-06, "loss": 0.3815335273742676, "num_input_tokens_seen": 453997936, "step": 11015, "train_runtime": 42480.6438, "train_tokens_per_second": 10687.172 }, { "epoch": 0.7419876110961486, "grad_norm": 0.857744676593128, "learning_rate": 6.971889007905299e-06, "loss": 0.3934885740280151, "num_input_tokens_seen": 454190408, "step": 11020, "train_runtime": 42498.1401, "train_tokens_per_second": 10687.301 }, { "epoch": 0.7423242660921088, "grad_norm": 0.6996813855658324, "learning_rate": 6.9694589572538795e-06, "loss": 0.4128869533538818, "num_input_tokens_seen": 454404856, "step": 11025, "train_runtime": 42516.6712, "train_tokens_per_second": 10687.687 }, { "epoch": 0.7426609210880689, "grad_norm": 0.6357127291940755, "learning_rate": 6.9670283558495436e-06, "loss": 0.37315974235534666, "num_input_tokens_seen": 454617696, "step": 11030, "train_runtime": 42536.5228, "train_tokens_per_second": 10687.702 }, { "epoch": 0.742997576084029, "grad_norm": 0.6675269849509146, "learning_rate": 6.964597204371999e-06, "loss": 0.3799604892730713, "num_input_tokens_seen": 454819440, "step": 11035, "train_runtime": 42555.7164, "train_tokens_per_second": 10687.623 }, { "epoch": 0.7433342310799892, "grad_norm": 0.7755699970819353, "learning_rate": 6.962165503501111e-06, "loss": 0.3468319892883301, "num_input_tokens_seen": 455027080, "step": 11040, "train_runtime": 42575.9652, "train_tokens_per_second": 10687.417 }, { "epoch": 0.7436708860759493, "grad_norm": 0.7000283601389728, "learning_rate": 6.959733253916899e-06, "loss": 0.39494569301605226, "num_input_tokens_seen": 455238680, "step": 11045, "train_runtime": 42595.641, "train_tokens_per_second": 10687.448 }, { "epoch": 0.7440075410719095, "grad_norm": 0.6608808151894058, "learning_rate": 6.95730045629953e-06, "loss": 0.3699952602386475, "num_input_tokens_seen": 455428296, "step": 11050, "train_runtime": 42614.2507, "train_tokens_per_second": 10687.23 }, { "epoch": 0.7443441960678696, "grad_norm": 0.7882836979294217, "learning_rate": 6.954867111329329e-06, "loss": 0.4005612373352051, "num_input_tokens_seen": 455639656, "step": 11055, "train_runtime": 42632.3313, "train_tokens_per_second": 10687.655 }, { "epoch": 0.7446808510638298, "grad_norm": 0.9430193180707183, "learning_rate": 6.952433219686775e-06, "loss": 0.36520938873291015, "num_input_tokens_seen": 455849208, "step": 11060, "train_runtime": 42653.0204, "train_tokens_per_second": 10687.384 }, { "epoch": 0.7450175060597899, "grad_norm": 0.664751009467184, "learning_rate": 6.949998782052497e-06, "loss": 0.3829323768615723, "num_input_tokens_seen": 456055552, "step": 11065, "train_runtime": 42673.9369, "train_tokens_per_second": 10686.981 }, { "epoch": 0.74535416105575, "grad_norm": 0.7500457910418988, "learning_rate": 6.947563799107277e-06, "loss": 0.3720050811767578, "num_input_tokens_seen": 456252624, "step": 11070, "train_runtime": 42691.3927, "train_tokens_per_second": 10687.227 }, { "epoch": 0.7456908160517102, "grad_norm": 0.7726005096977673, "learning_rate": 6.945128271532052e-06, "loss": 0.36924066543579104, "num_input_tokens_seen": 456471112, "step": 11075, "train_runtime": 42709.2883, "train_tokens_per_second": 10687.865 }, { "epoch": 0.7460274710476703, "grad_norm": 0.7185175581418294, "learning_rate": 6.942692200007908e-06, "loss": 0.3788987398147583, "num_input_tokens_seen": 456675408, "step": 11080, "train_runtime": 42727.2531, "train_tokens_per_second": 10688.153 }, { "epoch": 0.7463641260436304, "grad_norm": 0.7320985651291468, "learning_rate": 6.9402555852160845e-06, "loss": 0.3854942798614502, "num_input_tokens_seen": 456887760, "step": 11085, "train_runtime": 42745.3734, "train_tokens_per_second": 10688.59 }, { "epoch": 0.7467007810395906, "grad_norm": 0.6493805316968653, "learning_rate": 6.937818427837975e-06, "loss": 0.3619593620300293, "num_input_tokens_seen": 457098216, "step": 11090, "train_runtime": 42764.5379, "train_tokens_per_second": 10688.721 }, { "epoch": 0.7470374360355507, "grad_norm": 0.74038525595693, "learning_rate": 6.93538072855512e-06, "loss": 0.4026585578918457, "num_input_tokens_seen": 457306272, "step": 11095, "train_runtime": 42783.7764, "train_tokens_per_second": 10688.778 }, { "epoch": 0.7473740910315109, "grad_norm": 0.6680913278185318, "learning_rate": 6.932942488049217e-06, "loss": 0.3456205606460571, "num_input_tokens_seen": 457508288, "step": 11100, "train_runtime": 42803.6617, "train_tokens_per_second": 10688.532 }, { "epoch": 0.747710746027471, "grad_norm": 0.7092976870805464, "learning_rate": 6.930503707002108e-06, "loss": 0.3960667610168457, "num_input_tokens_seen": 457714512, "step": 11105, "train_runtime": 42823.1452, "train_tokens_per_second": 10688.484 }, { "epoch": 0.7480474010234311, "grad_norm": 0.6809028339991674, "learning_rate": 6.928064386095796e-06, "loss": 0.37265825271606445, "num_input_tokens_seen": 457927968, "step": 11110, "train_runtime": 42843.673, "train_tokens_per_second": 10688.345 }, { "epoch": 0.7483840560193913, "grad_norm": 0.7676350818925667, "learning_rate": 6.9256245260124264e-06, "loss": 0.38018150329589845, "num_input_tokens_seen": 458138920, "step": 11115, "train_runtime": 42861.9303, "train_tokens_per_second": 10688.714 }, { "epoch": 0.7487207110153514, "grad_norm": 0.9195843510989091, "learning_rate": 6.923184127434298e-06, "loss": 0.37871131896972654, "num_input_tokens_seen": 458329904, "step": 11120, "train_runtime": 42880.5659, "train_tokens_per_second": 10688.523 }, { "epoch": 0.7490573660113116, "grad_norm": 0.8414781945181613, "learning_rate": 6.920743191043861e-06, "loss": 0.3598013401031494, "num_input_tokens_seen": 458528728, "step": 11125, "train_runtime": 42900.0383, "train_tokens_per_second": 10688.306 }, { "epoch": 0.7493940210072717, "grad_norm": 0.612498271201067, "learning_rate": 6.918301717523714e-06, "loss": 0.3534430265426636, "num_input_tokens_seen": 458729824, "step": 11130, "train_runtime": 42919.092, "train_tokens_per_second": 10688.246 }, { "epoch": 0.7497306760032318, "grad_norm": 0.7096977128277271, "learning_rate": 6.915859707556611e-06, "loss": 0.37984142303466795, "num_input_tokens_seen": 458934080, "step": 11135, "train_runtime": 42938.2045, "train_tokens_per_second": 10688.246 }, { "epoch": 0.750067330999192, "grad_norm": 0.7609418470438924, "learning_rate": 6.913417161825449e-06, "loss": 0.40504016876220705, "num_input_tokens_seen": 459133952, "step": 11140, "train_runtime": 42956.4942, "train_tokens_per_second": 10688.348 }, { "epoch": 0.7504039859951521, "grad_norm": 0.6950964169560347, "learning_rate": 6.91097408101328e-06, "loss": 0.37393999099731445, "num_input_tokens_seen": 459338648, "step": 11145, "train_runtime": 42976.5039, "train_tokens_per_second": 10688.134 }, { "epoch": 0.7507406409911123, "grad_norm": 0.865312286973234, "learning_rate": 6.908530465803302e-06, "loss": 0.37439110279083254, "num_input_tokens_seen": 459533448, "step": 11150, "train_runtime": 42994.2094, "train_tokens_per_second": 10688.264 }, { "epoch": 0.7510772959870724, "grad_norm": 0.7910422186599019, "learning_rate": 6.906086316878865e-06, "loss": 0.3722621202468872, "num_input_tokens_seen": 459726672, "step": 11155, "train_runtime": 43013.4179, "train_tokens_per_second": 10687.983 }, { "epoch": 0.7514139509830325, "grad_norm": 0.61834043178417, "learning_rate": 6.903641634923468e-06, "loss": 0.3554039478302002, "num_input_tokens_seen": 459928656, "step": 11160, "train_runtime": 43031.0305, "train_tokens_per_second": 10688.302 }, { "epoch": 0.7517506059789927, "grad_norm": 0.8658591191652444, "learning_rate": 6.9011964206207585e-06, "loss": 0.39388155937194824, "num_input_tokens_seen": 460117904, "step": 11165, "train_runtime": 43049.1067, "train_tokens_per_second": 10688.21 }, { "epoch": 0.7520872609749528, "grad_norm": 0.7395025043722432, "learning_rate": 6.898750674654531e-06, "loss": 0.36003224849700927, "num_input_tokens_seen": 460325944, "step": 11170, "train_runtime": 43069.28, "train_tokens_per_second": 10688.034 }, { "epoch": 0.752423915970913, "grad_norm": 0.6245203327585436, "learning_rate": 6.896304397708733e-06, "loss": 0.35375826358795165, "num_input_tokens_seen": 460523720, "step": 11175, "train_runtime": 43088.0084, "train_tokens_per_second": 10687.979 }, { "epoch": 0.7527605709668731, "grad_norm": 0.767939824995386, "learning_rate": 6.893857590467456e-06, "loss": 0.3617475748062134, "num_input_tokens_seen": 460728056, "step": 11180, "train_runtime": 43106.2236, "train_tokens_per_second": 10688.203 }, { "epoch": 0.7530972259628332, "grad_norm": 0.7995056880630966, "learning_rate": 6.891410253614944e-06, "loss": 0.35715718269348146, "num_input_tokens_seen": 460924080, "step": 11185, "train_runtime": 43125.9362, "train_tokens_per_second": 10687.863 }, { "epoch": 0.7534338809587934, "grad_norm": 0.6728166212432599, "learning_rate": 6.888962387835586e-06, "loss": 0.378295373916626, "num_input_tokens_seen": 461140800, "step": 11190, "train_runtime": 43143.3619, "train_tokens_per_second": 10688.569 }, { "epoch": 0.7537705359547535, "grad_norm": 0.7171435035617769, "learning_rate": 6.886513993813919e-06, "loss": 0.3828647375106812, "num_input_tokens_seen": 461341384, "step": 11195, "train_runtime": 43161.7301, "train_tokens_per_second": 10688.668 }, { "epoch": 0.7541071909507137, "grad_norm": 0.6876529392883787, "learning_rate": 6.88406507223463e-06, "loss": 0.36248581409454345, "num_input_tokens_seen": 461555832, "step": 11200, "train_runtime": 43181.5336, "train_tokens_per_second": 10688.732 }, { "epoch": 0.7544438459466738, "grad_norm": 0.6965161017000954, "learning_rate": 6.881615623782551e-06, "loss": 0.3545789003372192, "num_input_tokens_seen": 461753096, "step": 11205, "train_runtime": 43199.6036, "train_tokens_per_second": 10688.827 }, { "epoch": 0.7547805009426339, "grad_norm": 0.6601196373939553, "learning_rate": 6.879165649142663e-06, "loss": 0.36424975395202636, "num_input_tokens_seen": 461945280, "step": 11210, "train_runtime": 43219.1674, "train_tokens_per_second": 10688.435 }, { "epoch": 0.7551171559385941, "grad_norm": 0.636758367730606, "learning_rate": 6.876715149000093e-06, "loss": 0.3665897369384766, "num_input_tokens_seen": 462138784, "step": 11215, "train_runtime": 43237.1557, "train_tokens_per_second": 10688.464 }, { "epoch": 0.7554538109345542, "grad_norm": 0.6819413614023578, "learning_rate": 6.874264124040117e-06, "loss": 0.3849313735961914, "num_input_tokens_seen": 462350160, "step": 11220, "train_runtime": 43255.6679, "train_tokens_per_second": 10688.776 }, { "epoch": 0.7557904659305144, "grad_norm": 0.7032685575780575, "learning_rate": 6.871812574948154e-06, "loss": 0.39900765419006345, "num_input_tokens_seen": 462561872, "step": 11225, "train_runtime": 43274.1518, "train_tokens_per_second": 10689.103 }, { "epoch": 0.7561271209264745, "grad_norm": 0.6873591233884412, "learning_rate": 6.869360502409773e-06, "loss": 0.385396671295166, "num_input_tokens_seen": 462774064, "step": 11230, "train_runtime": 43292.7748, "train_tokens_per_second": 10689.406 }, { "epoch": 0.7564637759224346, "grad_norm": 0.6618253181251817, "learning_rate": 6.866907907110689e-06, "loss": 0.3564007759094238, "num_input_tokens_seen": 462972568, "step": 11235, "train_runtime": 43313.0566, "train_tokens_per_second": 10688.984 }, { "epoch": 0.7568004309183949, "grad_norm": 0.6729189877249175, "learning_rate": 6.864454789736763e-06, "loss": 0.349070405960083, "num_input_tokens_seen": 463189552, "step": 11240, "train_runtime": 43330.9397, "train_tokens_per_second": 10689.58 }, { "epoch": 0.757137085914355, "grad_norm": 0.6430577768891015, "learning_rate": 6.8620011509740005e-06, "loss": 0.3707849979400635, "num_input_tokens_seen": 463392216, "step": 11245, "train_runtime": 43349.5826, "train_tokens_per_second": 10689.658 }, { "epoch": 0.7574737409103152, "grad_norm": 0.7684565264193934, "learning_rate": 6.859546991508552e-06, "loss": 0.35278520584106443, "num_input_tokens_seen": 463597528, "step": 11250, "train_runtime": 43368.1481, "train_tokens_per_second": 10689.816 }, { "epoch": 0.7578103959062753, "grad_norm": 0.6862347648674024, "learning_rate": 6.857092312026716e-06, "loss": 0.3756120681762695, "num_input_tokens_seen": 463814816, "step": 11255, "train_runtime": 43387.9028, "train_tokens_per_second": 10689.957 }, { "epoch": 0.7581470509022354, "grad_norm": 0.7103837393925876, "learning_rate": 6.8546371132149395e-06, "loss": 0.3931757926940918, "num_input_tokens_seen": 464019224, "step": 11260, "train_runtime": 43406.5011, "train_tokens_per_second": 10690.086 }, { "epoch": 0.7584837058981956, "grad_norm": 0.679770046080278, "learning_rate": 6.852181395759807e-06, "loss": 0.39992284774780273, "num_input_tokens_seen": 464234080, "step": 11265, "train_runtime": 43424.3994, "train_tokens_per_second": 10690.628 }, { "epoch": 0.7588203608941557, "grad_norm": 0.5422793086115096, "learning_rate": 6.849725160348054e-06, "loss": 0.3494361400604248, "num_input_tokens_seen": 464434984, "step": 11270, "train_runtime": 43443.5638, "train_tokens_per_second": 10690.536 }, { "epoch": 0.7591570158901159, "grad_norm": 0.6724446552215978, "learning_rate": 6.847268407666557e-06, "loss": 0.35218586921691897, "num_input_tokens_seen": 464646144, "step": 11275, "train_runtime": 43462.9554, "train_tokens_per_second": 10690.625 }, { "epoch": 0.759493670886076, "grad_norm": 0.8686980330927395, "learning_rate": 6.844811138402341e-06, "loss": 0.37933785915374757, "num_input_tokens_seen": 464853256, "step": 11280, "train_runtime": 43483.0116, "train_tokens_per_second": 10690.457 }, { "epoch": 0.7598303258820361, "grad_norm": 0.7198741356526486, "learning_rate": 6.842353353242574e-06, "loss": 0.36729333400726316, "num_input_tokens_seen": 465052488, "step": 11285, "train_runtime": 43502.2684, "train_tokens_per_second": 10690.304 }, { "epoch": 0.7601669808779963, "grad_norm": 0.7191908404777894, "learning_rate": 6.839895052874565e-06, "loss": 0.38039991855621336, "num_input_tokens_seen": 465263768, "step": 11290, "train_runtime": 43521.7761, "train_tokens_per_second": 10690.367 }, { "epoch": 0.7605036358739564, "grad_norm": 0.6821631420164826, "learning_rate": 6.837436237985772e-06, "loss": 0.36537647247314453, "num_input_tokens_seen": 465466816, "step": 11295, "train_runtime": 43543.7233, "train_tokens_per_second": 10689.642 }, { "epoch": 0.7608402908699166, "grad_norm": 0.7732539690765008, "learning_rate": 6.834976909263794e-06, "loss": 0.3766451358795166, "num_input_tokens_seen": 465667744, "step": 11300, "train_runtime": 43563.0386, "train_tokens_per_second": 10689.515 }, { "epoch": 0.7611769458658767, "grad_norm": 0.7783813483532106, "learning_rate": 6.832517067396374e-06, "loss": 0.35306384563446047, "num_input_tokens_seen": 465885544, "step": 11305, "train_runtime": 43581.302, "train_tokens_per_second": 10690.033 }, { "epoch": 0.7615136008618368, "grad_norm": 0.7066146375625236, "learning_rate": 6.8300567130714e-06, "loss": 0.39626374244689944, "num_input_tokens_seen": 466099696, "step": 11310, "train_runtime": 43600.923, "train_tokens_per_second": 10690.134 }, { "epoch": 0.761850255857797, "grad_norm": 0.6700680445409289, "learning_rate": 6.8275958469769035e-06, "loss": 0.3901375293731689, "num_input_tokens_seen": 466315480, "step": 11315, "train_runtime": 43620.5718, "train_tokens_per_second": 10690.265 }, { "epoch": 0.7621869108537571, "grad_norm": 0.9340157756473119, "learning_rate": 6.825134469801055e-06, "loss": 0.3580639123916626, "num_input_tokens_seen": 466531152, "step": 11320, "train_runtime": 43641.7379, "train_tokens_per_second": 10690.022 }, { "epoch": 0.7625235658497173, "grad_norm": 0.7290039346976042, "learning_rate": 6.8226725822321715e-06, "loss": 0.4022355556488037, "num_input_tokens_seen": 466727448, "step": 11325, "train_runtime": 43659.6652, "train_tokens_per_second": 10690.129 }, { "epoch": 0.7628602208456774, "grad_norm": 0.7035330245727934, "learning_rate": 6.820210184958712e-06, "loss": 0.3781903266906738, "num_input_tokens_seen": 466939280, "step": 11330, "train_runtime": 43678.2125, "train_tokens_per_second": 10690.439 }, { "epoch": 0.7631968758416375, "grad_norm": 0.761861043201224, "learning_rate": 6.81774727866928e-06, "loss": 0.3853703737258911, "num_input_tokens_seen": 467138240, "step": 11335, "train_runtime": 43697.8312, "train_tokens_per_second": 10690.193 }, { "epoch": 0.7635335308375977, "grad_norm": 0.7495165077950475, "learning_rate": 6.815283864052617e-06, "loss": 0.3865309238433838, "num_input_tokens_seen": 467345944, "step": 11340, "train_runtime": 43716.5144, "train_tokens_per_second": 10690.375 }, { "epoch": 0.7638701858335578, "grad_norm": 0.7379260446426945, "learning_rate": 6.812819941797611e-06, "loss": 0.3862548828125, "num_input_tokens_seen": 467541296, "step": 11345, "train_runtime": 43737.1659, "train_tokens_per_second": 10689.794 }, { "epoch": 0.764206840829518, "grad_norm": 0.7211079613337645, "learning_rate": 6.810355512593288e-06, "loss": 0.3860186576843262, "num_input_tokens_seen": 467753280, "step": 11350, "train_runtime": 43756.9247, "train_tokens_per_second": 10689.812 }, { "epoch": 0.7645434958254781, "grad_norm": 0.6423519783118107, "learning_rate": 6.807890577128817e-06, "loss": 0.3425148010253906, "num_input_tokens_seen": 467964832, "step": 11355, "train_runtime": 43776.5225, "train_tokens_per_second": 10689.859 }, { "epoch": 0.7648801508214382, "grad_norm": 0.7690340605348394, "learning_rate": 6.805425136093513e-06, "loss": 0.3679905891418457, "num_input_tokens_seen": 468170408, "step": 11360, "train_runtime": 43794.119, "train_tokens_per_second": 10690.257 }, { "epoch": 0.7652168058173984, "grad_norm": 0.7291073562783726, "learning_rate": 6.802959190176827e-06, "loss": 0.38682045936584475, "num_input_tokens_seen": 468368936, "step": 11365, "train_runtime": 43813.5939, "train_tokens_per_second": 10690.037 }, { "epoch": 0.7655534608133585, "grad_norm": 0.7738982595523095, "learning_rate": 6.800492740068352e-06, "loss": 0.3735480546951294, "num_input_tokens_seen": 468561648, "step": 11370, "train_runtime": 43831.9702, "train_tokens_per_second": 10689.952 }, { "epoch": 0.7658901158093187, "grad_norm": 0.8093142067128822, "learning_rate": 6.798025786457825e-06, "loss": 0.36521272659301757, "num_input_tokens_seen": 468774720, "step": 11375, "train_runtime": 43851.7096, "train_tokens_per_second": 10689.999 }, { "epoch": 0.7662267708052788, "grad_norm": 0.6501238142068381, "learning_rate": 6.795558330035118e-06, "loss": 0.3649320602416992, "num_input_tokens_seen": 468991856, "step": 11380, "train_runtime": 43873.0228, "train_tokens_per_second": 10689.755 }, { "epoch": 0.7665634258012389, "grad_norm": 0.6028073281287939, "learning_rate": 6.793090371490251e-06, "loss": 0.3762960910797119, "num_input_tokens_seen": 469207048, "step": 11385, "train_runtime": 43890.5214, "train_tokens_per_second": 10690.396 }, { "epoch": 0.7669000807971991, "grad_norm": 0.6419695884023348, "learning_rate": 6.790621911513378e-06, "loss": 0.361385440826416, "num_input_tokens_seen": 469411672, "step": 11390, "train_runtime": 43908.92, "train_tokens_per_second": 10690.577 }, { "epoch": 0.7672367357931592, "grad_norm": 0.6770456706936738, "learning_rate": 6.788152950794799e-06, "loss": 0.3899927377700806, "num_input_tokens_seen": 469615192, "step": 11395, "train_runtime": 43926.917, "train_tokens_per_second": 10690.83 }, { "epoch": 0.7675733907891193, "grad_norm": 0.8807611860605178, "learning_rate": 6.7856834900249495e-06, "loss": 0.3959368705749512, "num_input_tokens_seen": 469822096, "step": 11400, "train_runtime": 43947.1439, "train_tokens_per_second": 10690.617 }, { "epoch": 0.7679100457850795, "grad_norm": 0.7424630084833023, "learning_rate": 6.783213529894405e-06, "loss": 0.3433100938796997, "num_input_tokens_seen": 470029384, "step": 11405, "train_runtime": 43967.1056, "train_tokens_per_second": 10690.478 }, { "epoch": 0.7682467007810396, "grad_norm": 0.7231574436268706, "learning_rate": 6.780743071093883e-06, "loss": 0.3599123477935791, "num_input_tokens_seen": 470240200, "step": 11410, "train_runtime": 43986.0379, "train_tokens_per_second": 10690.67 }, { "epoch": 0.7685833557769998, "grad_norm": 0.9588708365682542, "learning_rate": 6.77827211431424e-06, "loss": 0.37321531772613525, "num_input_tokens_seen": 470450792, "step": 11415, "train_runtime": 44004.8465, "train_tokens_per_second": 10690.886 }, { "epoch": 0.7689200107729599, "grad_norm": 0.6891747041883636, "learning_rate": 6.775800660246471e-06, "loss": 0.3650075912475586, "num_input_tokens_seen": 470640656, "step": 11420, "train_runtime": 44023.2554, "train_tokens_per_second": 10690.728 }, { "epoch": 0.76925666576892, "grad_norm": 0.7323975778819141, "learning_rate": 6.77332870958171e-06, "loss": 0.3758340120315552, "num_input_tokens_seen": 470856864, "step": 11425, "train_runtime": 44042.7221, "train_tokens_per_second": 10690.912 }, { "epoch": 0.7695933207648802, "grad_norm": 0.7013775173513405, "learning_rate": 6.770856263011229e-06, "loss": 0.36583890914916994, "num_input_tokens_seen": 471055944, "step": 11430, "train_runtime": 44061.0128, "train_tokens_per_second": 10690.992 }, { "epoch": 0.7699299757608403, "grad_norm": 0.7684485053834774, "learning_rate": 6.768383321226442e-06, "loss": 0.3895734786987305, "num_input_tokens_seen": 471248976, "step": 11435, "train_runtime": 44079.9697, "train_tokens_per_second": 10690.774 }, { "epoch": 0.7702666307568005, "grad_norm": 0.7654635566570887, "learning_rate": 6.765909884918898e-06, "loss": 0.37192158699035643, "num_input_tokens_seen": 471446640, "step": 11440, "train_runtime": 44099.7393, "train_tokens_per_second": 10690.463 }, { "epoch": 0.7706032857527606, "grad_norm": 0.6722430088375256, "learning_rate": 6.763435954780286e-06, "loss": 0.3979313373565674, "num_input_tokens_seen": 471653824, "step": 11445, "train_runtime": 44118.2836, "train_tokens_per_second": 10690.666 }, { "epoch": 0.7709399407487207, "grad_norm": 0.7262551202831029, "learning_rate": 6.7609615315024325e-06, "loss": 0.37273130416870115, "num_input_tokens_seen": 471857120, "step": 11450, "train_runtime": 44136.8277, "train_tokens_per_second": 10690.78 }, { "epoch": 0.7712765957446809, "grad_norm": 0.7379120779038965, "learning_rate": 6.758486615777301e-06, "loss": 0.3675090789794922, "num_input_tokens_seen": 472061016, "step": 11455, "train_runtime": 44158.0994, "train_tokens_per_second": 10690.248 }, { "epoch": 0.771613250740641, "grad_norm": 0.7820166064157416, "learning_rate": 6.756011208296995e-06, "loss": 0.36801557540893554, "num_input_tokens_seen": 472261848, "step": 11460, "train_runtime": 44178.2797, "train_tokens_per_second": 10689.91 }, { "epoch": 0.7719499057366012, "grad_norm": 0.7545859366689639, "learning_rate": 6.753535309753755e-06, "loss": 0.3593705654144287, "num_input_tokens_seen": 472455704, "step": 11465, "train_runtime": 44196.6767, "train_tokens_per_second": 10689.847 }, { "epoch": 0.7722865607325613, "grad_norm": 0.7032756559765024, "learning_rate": 6.7510589208399565e-06, "loss": 0.37022981643676756, "num_input_tokens_seen": 472661640, "step": 11470, "train_runtime": 44215.08, "train_tokens_per_second": 10690.055 }, { "epoch": 0.7726232157285214, "grad_norm": 0.7187638792851636, "learning_rate": 6.748582042248115e-06, "loss": 0.36203181743621826, "num_input_tokens_seen": 472861680, "step": 11475, "train_runtime": 44234.7337, "train_tokens_per_second": 10689.828 }, { "epoch": 0.7729598707244816, "grad_norm": 0.6917707609523737, "learning_rate": 6.746104674670882e-06, "loss": 0.38666658401489257, "num_input_tokens_seen": 473071224, "step": 11480, "train_runtime": 44252.9707, "train_tokens_per_second": 10690.157 }, { "epoch": 0.7732965257204417, "grad_norm": 0.6538680510358075, "learning_rate": 6.743626818801042e-06, "loss": 0.39917089939117434, "num_input_tokens_seen": 473279888, "step": 11485, "train_runtime": 44274.1065, "train_tokens_per_second": 10689.767 }, { "epoch": 0.7736331807164019, "grad_norm": 0.6494866529559443, "learning_rate": 6.741148475331525e-06, "loss": 0.37424778938293457, "num_input_tokens_seen": 473487776, "step": 11490, "train_runtime": 44292.3798, "train_tokens_per_second": 10690.05 }, { "epoch": 0.773969835712362, "grad_norm": 0.6465660359922708, "learning_rate": 6.738669644955388e-06, "loss": 0.346470308303833, "num_input_tokens_seen": 473691456, "step": 11495, "train_runtime": 44312.0797, "train_tokens_per_second": 10689.894 }, { "epoch": 0.7743064907083221, "grad_norm": 0.7067188933281707, "learning_rate": 6.736190328365828e-06, "loss": 0.37489023208618166, "num_input_tokens_seen": 473902680, "step": 11500, "train_runtime": 44331.6634, "train_tokens_per_second": 10689.937 }, { "epoch": 0.7746431457042823, "grad_norm": 0.7227642034552072, "learning_rate": 6.73371052625618e-06, "loss": 0.37453250885009765, "num_input_tokens_seen": 474111768, "step": 11505, "train_runtime": 44349.9664, "train_tokens_per_second": 10690.24 }, { "epoch": 0.7749798007002424, "grad_norm": 0.6760911695745225, "learning_rate": 6.731230239319912e-06, "loss": 0.37352514266967773, "num_input_tokens_seen": 474324136, "step": 11510, "train_runtime": 44371.4153, "train_tokens_per_second": 10689.858 }, { "epoch": 0.7753164556962026, "grad_norm": 0.5902730248913429, "learning_rate": 6.728749468250627e-06, "loss": 0.38402714729309084, "num_input_tokens_seen": 474537176, "step": 11515, "train_runtime": 44390.7837, "train_tokens_per_second": 10689.993 }, { "epoch": 0.7756531106921627, "grad_norm": 0.8611162666483705, "learning_rate": 6.726268213742066e-06, "loss": 0.3778719186782837, "num_input_tokens_seen": 474733184, "step": 11520, "train_runtime": 44410.5183, "train_tokens_per_second": 10689.656 }, { "epoch": 0.7759897656881228, "grad_norm": 0.7114634253396976, "learning_rate": 6.723786476488105e-06, "loss": 0.39086410999298093, "num_input_tokens_seen": 474945168, "step": 11525, "train_runtime": 44429.6496, "train_tokens_per_second": 10689.825 }, { "epoch": 0.776326420684083, "grad_norm": 0.6640073078593475, "learning_rate": 6.72130425718275e-06, "loss": 0.352234935760498, "num_input_tokens_seen": 475141400, "step": 11530, "train_runtime": 44448.9007, "train_tokens_per_second": 10689.61 }, { "epoch": 0.7766630756800431, "grad_norm": 0.741462403568669, "learning_rate": 6.718821556520151e-06, "loss": 0.3934935092926025, "num_input_tokens_seen": 475338736, "step": 11535, "train_runtime": 44467.5326, "train_tokens_per_second": 10689.569 }, { "epoch": 0.7769997306760033, "grad_norm": 0.6412014178907269, "learning_rate": 6.716338375194583e-06, "loss": 0.36296591758728025, "num_input_tokens_seen": 475548400, "step": 11540, "train_runtime": 44486.0896, "train_tokens_per_second": 10689.822 }, { "epoch": 0.7773363856719634, "grad_norm": 0.7035277711236706, "learning_rate": 6.713854713900463e-06, "loss": 0.40902318954467776, "num_input_tokens_seen": 475757752, "step": 11545, "train_runtime": 44507.4433, "train_tokens_per_second": 10689.397 }, { "epoch": 0.7776730406679235, "grad_norm": 0.8491827194837313, "learning_rate": 6.7113705733323365e-06, "loss": 0.39376718997955323, "num_input_tokens_seen": 475953472, "step": 11550, "train_runtime": 44526.4973, "train_tokens_per_second": 10689.219 }, { "epoch": 0.7780096956638837, "grad_norm": 0.7968966706550504, "learning_rate": 6.708885954184885e-06, "loss": 0.3777567625045776, "num_input_tokens_seen": 476160432, "step": 11555, "train_runtime": 44545.8553, "train_tokens_per_second": 10689.22 }, { "epoch": 0.7783463506598438, "grad_norm": 0.8339863663887372, "learning_rate": 6.7064008571529275e-06, "loss": 0.3615944147109985, "num_input_tokens_seen": 476370280, "step": 11560, "train_runtime": 44566.0093, "train_tokens_per_second": 10689.094 }, { "epoch": 0.778683005655804, "grad_norm": 0.6201600423085298, "learning_rate": 6.703915282931411e-06, "loss": 0.3771646499633789, "num_input_tokens_seen": 476584304, "step": 11565, "train_runtime": 44586.2768, "train_tokens_per_second": 10689.036 }, { "epoch": 0.7790196606517641, "grad_norm": 0.7159177857070865, "learning_rate": 6.701429232215418e-06, "loss": 0.38285117149353026, "num_input_tokens_seen": 476777536, "step": 11570, "train_runtime": 44605.5856, "train_tokens_per_second": 10688.741 }, { "epoch": 0.7793563156477242, "grad_norm": 0.7994444793653163, "learning_rate": 6.6989427057001665e-06, "loss": 0.37943599224090574, "num_input_tokens_seen": 476989552, "step": 11575, "train_runtime": 44624.3179, "train_tokens_per_second": 10689.005 }, { "epoch": 0.7796929706436844, "grad_norm": 0.6693677879956476, "learning_rate": 6.696455704081006e-06, "loss": 0.37842278480529784, "num_input_tokens_seen": 477195632, "step": 11580, "train_runtime": 44644.9177, "train_tokens_per_second": 10688.689 }, { "epoch": 0.7800296256396445, "grad_norm": 0.666083642017978, "learning_rate": 6.693968228053416e-06, "loss": 0.38592393398284913, "num_input_tokens_seen": 477402224, "step": 11585, "train_runtime": 44662.7069, "train_tokens_per_second": 10689.057 }, { "epoch": 0.7803662806356046, "grad_norm": 0.6630090444825741, "learning_rate": 6.691480278313013e-06, "loss": 0.37808690071105955, "num_input_tokens_seen": 477606696, "step": 11590, "train_runtime": 44682.63, "train_tokens_per_second": 10688.867 }, { "epoch": 0.7807029356315648, "grad_norm": 0.6852669029154399, "learning_rate": 6.688991855555545e-06, "loss": 0.3476670265197754, "num_input_tokens_seen": 477811704, "step": 11595, "train_runtime": 44703.4889, "train_tokens_per_second": 10688.466 }, { "epoch": 0.7810395906275249, "grad_norm": 0.6165498375405627, "learning_rate": 6.686502960476888e-06, "loss": 0.3608450412750244, "num_input_tokens_seen": 478031928, "step": 11600, "train_runtime": 44721.4249, "train_tokens_per_second": 10689.103 }, { "epoch": 0.7813762456234851, "grad_norm": 0.6849837686729355, "learning_rate": 6.684013593773058e-06, "loss": 0.3309787750244141, "num_input_tokens_seen": 478249280, "step": 11605, "train_runtime": 44739.4518, "train_tokens_per_second": 10689.654 }, { "epoch": 0.7817129006194452, "grad_norm": 0.7598202123840018, "learning_rate": 6.6815237561401955e-06, "loss": 0.3401951313018799, "num_input_tokens_seen": 478434600, "step": 11610, "train_runtime": 44758.4169, "train_tokens_per_second": 10689.265 }, { "epoch": 0.7820495556154053, "grad_norm": 0.7451019328690278, "learning_rate": 6.679033448274577e-06, "loss": 0.3531888246536255, "num_input_tokens_seen": 478643000, "step": 11615, "train_runtime": 44778.4362, "train_tokens_per_second": 10689.141 }, { "epoch": 0.7823862106113655, "grad_norm": 0.6262270471681102, "learning_rate": 6.676542670872609e-06, "loss": 0.37163195610046384, "num_input_tokens_seen": 478846592, "step": 11620, "train_runtime": 44796.4951, "train_tokens_per_second": 10689.376 }, { "epoch": 0.7827228656073256, "grad_norm": 0.6347654809399916, "learning_rate": 6.674051424630829e-06, "loss": 0.36177573204040525, "num_input_tokens_seen": 479058672, "step": 11625, "train_runtime": 44815.0226, "train_tokens_per_second": 10689.689 }, { "epoch": 0.7830595206032858, "grad_norm": 0.6835315857527268, "learning_rate": 6.671559710245905e-06, "loss": 0.369555139541626, "num_input_tokens_seen": 479270920, "step": 11630, "train_runtime": 44835.0719, "train_tokens_per_second": 10689.643 }, { "epoch": 0.7833961755992459, "grad_norm": 0.7819190653576205, "learning_rate": 6.669067528414639e-06, "loss": 0.3627415657043457, "num_input_tokens_seen": 479484616, "step": 11635, "train_runtime": 44854.8874, "train_tokens_per_second": 10689.685 }, { "epoch": 0.783732830595206, "grad_norm": 0.7047168696444969, "learning_rate": 6.6665748798339606e-06, "loss": 0.3905082941055298, "num_input_tokens_seen": 479697440, "step": 11640, "train_runtime": 44873.8089, "train_tokens_per_second": 10689.92 }, { "epoch": 0.7840694855911662, "grad_norm": 0.7434910591559247, "learning_rate": 6.664081765200932e-06, "loss": 0.3881762742996216, "num_input_tokens_seen": 479887312, "step": 11645, "train_runtime": 44891.4677, "train_tokens_per_second": 10689.945 }, { "epoch": 0.7844061405871263, "grad_norm": 0.6621976332841489, "learning_rate": 6.661588185212745e-06, "loss": 0.3901242256164551, "num_input_tokens_seen": 480096520, "step": 11650, "train_runtime": 44910.6323, "train_tokens_per_second": 10690.041 }, { "epoch": 0.7847427955830865, "grad_norm": 0.7091658630325746, "learning_rate": 6.65909414056672e-06, "loss": 0.379769492149353, "num_input_tokens_seen": 480296008, "step": 11655, "train_runtime": 44929.2651, "train_tokens_per_second": 10690.048 }, { "epoch": 0.7850794505790466, "grad_norm": 0.7477726457449498, "learning_rate": 6.6565996319603075e-06, "loss": 0.36979944705963136, "num_input_tokens_seen": 480498680, "step": 11660, "train_runtime": 44948.3993, "train_tokens_per_second": 10690.006 }, { "epoch": 0.7854161055750067, "grad_norm": 0.6817080695804035, "learning_rate": 6.6541046600910915e-06, "loss": 0.3617604970932007, "num_input_tokens_seen": 480699592, "step": 11665, "train_runtime": 44967.0449, "train_tokens_per_second": 10690.042 }, { "epoch": 0.7857527605709669, "grad_norm": 0.7057058229364183, "learning_rate": 6.6516092256567824e-06, "loss": 0.3679654598236084, "num_input_tokens_seen": 480911856, "step": 11670, "train_runtime": 44984.6913, "train_tokens_per_second": 10690.567 }, { "epoch": 0.786089415566927, "grad_norm": 0.853322289423235, "learning_rate": 6.64911332935522e-06, "loss": 0.40032501220703126, "num_input_tokens_seen": 481123480, "step": 11675, "train_runtime": 45004.1158, "train_tokens_per_second": 10690.655 }, { "epoch": 0.7864260705628872, "grad_norm": 0.6800868674305621, "learning_rate": 6.646616971884373e-06, "loss": 0.36400928497314455, "num_input_tokens_seen": 481335704, "step": 11680, "train_runtime": 45024.5455, "train_tokens_per_second": 10690.518 }, { "epoch": 0.7867627255588473, "grad_norm": 0.6091825779287955, "learning_rate": 6.64412015394234e-06, "loss": 0.35527758598327636, "num_input_tokens_seen": 481524944, "step": 11685, "train_runtime": 45043.7357, "train_tokens_per_second": 10690.164 }, { "epoch": 0.7870993805548074, "grad_norm": 0.7867175380394927, "learning_rate": 6.641622876227349e-06, "loss": 0.38516247272491455, "num_input_tokens_seen": 481720424, "step": 11690, "train_runtime": 45063.6404, "train_tokens_per_second": 10689.78 }, { "epoch": 0.7874360355507676, "grad_norm": 0.7035153409707735, "learning_rate": 6.639125139437756e-06, "loss": 0.3621467113494873, "num_input_tokens_seen": 481926584, "step": 11695, "train_runtime": 45083.5839, "train_tokens_per_second": 10689.625 }, { "epoch": 0.7877726905467277, "grad_norm": 0.8073174678924343, "learning_rate": 6.6366269442720446e-06, "loss": 0.3685892105102539, "num_input_tokens_seen": 482128568, "step": 11700, "train_runtime": 45103.5567, "train_tokens_per_second": 10689.369 }, { "epoch": 0.7881093455426879, "grad_norm": 0.7229278575401754, "learning_rate": 6.634128291428827e-06, "loss": 0.4223929405212402, "num_input_tokens_seen": 482328360, "step": 11705, "train_runtime": 45121.9569, "train_tokens_per_second": 10689.438 }, { "epoch": 0.788446000538648, "grad_norm": 1.9120476534282607, "learning_rate": 6.631629181606842e-06, "loss": 0.38430118560791016, "num_input_tokens_seen": 482539024, "step": 11710, "train_runtime": 45142.11, "train_tokens_per_second": 10689.332 }, { "epoch": 0.7887826555346081, "grad_norm": 0.6955085196437788, "learning_rate": 6.629129615504961e-06, "loss": 0.3781575679779053, "num_input_tokens_seen": 482749864, "step": 11715, "train_runtime": 45161.8241, "train_tokens_per_second": 10689.335 }, { "epoch": 0.7891193105305683, "grad_norm": 0.8568230729730621, "learning_rate": 6.626629593822178e-06, "loss": 0.3499631404876709, "num_input_tokens_seen": 482955712, "step": 11720, "train_runtime": 45181.6705, "train_tokens_per_second": 10689.196 }, { "epoch": 0.7894559655265284, "grad_norm": 0.730302247094122, "learning_rate": 6.624129117257616e-06, "loss": 0.39296712875366213, "num_input_tokens_seen": 483167272, "step": 11725, "train_runtime": 45200.4882, "train_tokens_per_second": 10689.426 }, { "epoch": 0.7897926205224886, "grad_norm": 0.7769232074488635, "learning_rate": 6.621628186510524e-06, "loss": 0.38841686248779295, "num_input_tokens_seen": 483372048, "step": 11730, "train_runtime": 45219.0261, "train_tokens_per_second": 10689.572 }, { "epoch": 0.7901292755184487, "grad_norm": 0.6812913059118011, "learning_rate": 6.619126802280281e-06, "loss": 0.36264982223510744, "num_input_tokens_seen": 483576912, "step": 11735, "train_runtime": 45240.0805, "train_tokens_per_second": 10689.126 }, { "epoch": 0.7904659305144088, "grad_norm": 0.645307546442983, "learning_rate": 6.616624965266392e-06, "loss": 0.3748537302017212, "num_input_tokens_seen": 483783512, "step": 11740, "train_runtime": 45258.3438, "train_tokens_per_second": 10689.377 }, { "epoch": 0.790802585510369, "grad_norm": 0.7031631003240699, "learning_rate": 6.614122676168486e-06, "loss": 0.3997942924499512, "num_input_tokens_seen": 483988096, "step": 11745, "train_runtime": 45279.5153, "train_tokens_per_second": 10688.897 }, { "epoch": 0.7911392405063291, "grad_norm": 0.9626813729425435, "learning_rate": 6.611619935686321e-06, "loss": 0.35587406158447266, "num_input_tokens_seen": 484182904, "step": 11750, "train_runtime": 45298.106, "train_tokens_per_second": 10688.811 }, { "epoch": 0.7914758955022893, "grad_norm": 0.7474382497008409, "learning_rate": 6.609116744519779e-06, "loss": 0.3938132286071777, "num_input_tokens_seen": 484394792, "step": 11755, "train_runtime": 45315.6772, "train_tokens_per_second": 10689.342 }, { "epoch": 0.7918125504982494, "grad_norm": 0.7460189272039914, "learning_rate": 6.60661310336887e-06, "loss": 0.33640346527099607, "num_input_tokens_seen": 484592008, "step": 11760, "train_runtime": 45334.9045, "train_tokens_per_second": 10689.159 }, { "epoch": 0.7921492054942095, "grad_norm": 0.7400277812611078, "learning_rate": 6.604109012933732e-06, "loss": 0.37258234024047854, "num_input_tokens_seen": 484781600, "step": 11765, "train_runtime": 45353.2539, "train_tokens_per_second": 10689.015 }, { "epoch": 0.7924858604901697, "grad_norm": 0.6877979050622524, "learning_rate": 6.601604473914622e-06, "loss": 0.3939949035644531, "num_input_tokens_seen": 484987840, "step": 11770, "train_runtime": 45373.5747, "train_tokens_per_second": 10688.773 }, { "epoch": 0.7928225154861298, "grad_norm": 0.6696281350793122, "learning_rate": 6.599099487011928e-06, "loss": 0.37260196208953855, "num_input_tokens_seen": 485201016, "step": 11775, "train_runtime": 45393.8843, "train_tokens_per_second": 10688.687 }, { "epoch": 0.79315917048209, "grad_norm": 0.7178345988324355, "learning_rate": 6.596594052926163e-06, "loss": 0.3835891246795654, "num_input_tokens_seen": 485412168, "step": 11780, "train_runtime": 45413.9047, "train_tokens_per_second": 10688.624 }, { "epoch": 0.7934958254780501, "grad_norm": 0.6115825927393015, "learning_rate": 6.5940881723579595e-06, "loss": 0.36771512031555176, "num_input_tokens_seen": 485620496, "step": 11785, "train_runtime": 45433.7613, "train_tokens_per_second": 10688.538 }, { "epoch": 0.7938324804740102, "grad_norm": 0.7041277394562374, "learning_rate": 6.591581846008085e-06, "loss": 0.34604592323303224, "num_input_tokens_seen": 485828280, "step": 11790, "train_runtime": 45452.8241, "train_tokens_per_second": 10688.627 }, { "epoch": 0.7941691354699704, "grad_norm": 0.7555366330619787, "learning_rate": 6.589075074577421e-06, "loss": 0.3708884477615356, "num_input_tokens_seen": 486036512, "step": 11795, "train_runtime": 45472.4733, "train_tokens_per_second": 10688.588 }, { "epoch": 0.7945057904659305, "grad_norm": 0.6896374561861234, "learning_rate": 6.5865678587669805e-06, "loss": 0.3585993528366089, "num_input_tokens_seen": 486250072, "step": 11800, "train_runtime": 45490.7017, "train_tokens_per_second": 10688.999 }, { "epoch": 0.7948424454618906, "grad_norm": 0.8589670434898939, "learning_rate": 6.584060199277897e-06, "loss": 0.39775934219360354, "num_input_tokens_seen": 486449760, "step": 11805, "train_runtime": 45508.9971, "train_tokens_per_second": 10689.09 }, { "epoch": 0.7951791004578508, "grad_norm": 0.6895074006929985, "learning_rate": 6.581552096811428e-06, "loss": 0.3795022010803223, "num_input_tokens_seen": 486653792, "step": 11810, "train_runtime": 45527.4916, "train_tokens_per_second": 10689.229 }, { "epoch": 0.7955157554538109, "grad_norm": 0.720327826800005, "learning_rate": 6.57904355206896e-06, "loss": 0.38076708316802976, "num_input_tokens_seen": 486861688, "step": 11815, "train_runtime": 45546.3386, "train_tokens_per_second": 10689.371 }, { "epoch": 0.7958524104497711, "grad_norm": 0.7229595087054135, "learning_rate": 6.576534565751997e-06, "loss": 0.34561882019042967, "num_input_tokens_seen": 487067440, "step": 11820, "train_runtime": 45565.6786, "train_tokens_per_second": 10689.349 }, { "epoch": 0.7961890654457312, "grad_norm": 0.7373851455324426, "learning_rate": 6.574025138562172e-06, "loss": 0.3846292018890381, "num_input_tokens_seen": 487263192, "step": 11825, "train_runtime": 45583.718, "train_tokens_per_second": 10689.413 }, { "epoch": 0.7965257204416913, "grad_norm": 0.6080124789643225, "learning_rate": 6.571515271201234e-06, "loss": 0.35044078826904296, "num_input_tokens_seen": 487474136, "step": 11830, "train_runtime": 45603.2746, "train_tokens_per_second": 10689.455 }, { "epoch": 0.7968623754376515, "grad_norm": 0.6409172773923807, "learning_rate": 6.569004964371062e-06, "loss": 0.3849016666412354, "num_input_tokens_seen": 487684664, "step": 11835, "train_runtime": 45620.5903, "train_tokens_per_second": 10690.012 }, { "epoch": 0.7971990304336116, "grad_norm": 0.6663741763084807, "learning_rate": 6.566494218773656e-06, "loss": 0.3611558675765991, "num_input_tokens_seen": 487897176, "step": 11840, "train_runtime": 45639.7154, "train_tokens_per_second": 10690.189 }, { "epoch": 0.7975356854295718, "grad_norm": 0.7716933894086101, "learning_rate": 6.563983035111136e-06, "loss": 0.3803549289703369, "num_input_tokens_seen": 488112048, "step": 11845, "train_runtime": 45659.701, "train_tokens_per_second": 10690.216 }, { "epoch": 0.7978723404255319, "grad_norm": 0.7104866272322365, "learning_rate": 6.561471414085748e-06, "loss": 0.3730647087097168, "num_input_tokens_seen": 488311904, "step": 11850, "train_runtime": 45678.9473, "train_tokens_per_second": 10690.087 }, { "epoch": 0.798208995421492, "grad_norm": 0.7044203186802042, "learning_rate": 6.558959356399859e-06, "loss": 0.37790117263793943, "num_input_tokens_seen": 488513736, "step": 11855, "train_runtime": 45697.3915, "train_tokens_per_second": 10690.189 }, { "epoch": 0.7985456504174522, "grad_norm": 0.6147361339582188, "learning_rate": 6.5564468627559544e-06, "loss": 0.3597301483154297, "num_input_tokens_seen": 488711336, "step": 11860, "train_runtime": 45717.5024, "train_tokens_per_second": 10689.808 }, { "epoch": 0.7988823054134123, "grad_norm": 0.6815803716028839, "learning_rate": 6.5539339338566495e-06, "loss": 0.39038786888122556, "num_input_tokens_seen": 488916496, "step": 11865, "train_runtime": 45737.8182, "train_tokens_per_second": 10689.546 }, { "epoch": 0.7992189604093725, "grad_norm": 0.8163356964415008, "learning_rate": 6.5514205704046754e-06, "loss": 0.3468745231628418, "num_input_tokens_seen": 489116360, "step": 11870, "train_runtime": 45756.2817, "train_tokens_per_second": 10689.6 }, { "epoch": 0.7995556154053326, "grad_norm": 0.6966387710854366, "learning_rate": 6.548906773102886e-06, "loss": 0.34504098892211915, "num_input_tokens_seen": 489316704, "step": 11875, "train_runtime": 45774.9034, "train_tokens_per_second": 10689.628 }, { "epoch": 0.7998922704012927, "grad_norm": 0.648194450657596, "learning_rate": 6.546392542654257e-06, "loss": 0.36384761333465576, "num_input_tokens_seen": 489519840, "step": 11880, "train_runtime": 45793.5993, "train_tokens_per_second": 10689.7 }, { "epoch": 0.8002289253972529, "grad_norm": 0.7225043630972854, "learning_rate": 6.543877879761882e-06, "loss": 0.39927875995635986, "num_input_tokens_seen": 489723648, "step": 11885, "train_runtime": 45812.1395, "train_tokens_per_second": 10689.823 }, { "epoch": 0.800565580393213, "grad_norm": 0.6508147126013756, "learning_rate": 6.5413627851289825e-06, "loss": 0.3555765628814697, "num_input_tokens_seen": 489936528, "step": 11890, "train_runtime": 45831.6524, "train_tokens_per_second": 10689.916 }, { "epoch": 0.8009022353891732, "grad_norm": 0.7157507532094193, "learning_rate": 6.538847259458896e-06, "loss": 0.3581544399261475, "num_input_tokens_seen": 490146320, "step": 11895, "train_runtime": 45850.2104, "train_tokens_per_second": 10690.165 }, { "epoch": 0.8012388903851333, "grad_norm": 0.698267796823246, "learning_rate": 6.5363313034550805e-06, "loss": 0.3446503639221191, "num_input_tokens_seen": 490346688, "step": 11900, "train_runtime": 45868.252, "train_tokens_per_second": 10690.329 }, { "epoch": 0.8015755453810934, "grad_norm": 0.7369567037057002, "learning_rate": 6.533814917821114e-06, "loss": 0.376096510887146, "num_input_tokens_seen": 490556688, "step": 11905, "train_runtime": 45888.8696, "train_tokens_per_second": 10690.102 }, { "epoch": 0.8019122003770536, "grad_norm": 0.633311000936507, "learning_rate": 6.531298103260696e-06, "loss": 0.36550226211547854, "num_input_tokens_seen": 490756376, "step": 11910, "train_runtime": 45907.9961, "train_tokens_per_second": 10689.998 }, { "epoch": 0.8022488553730137, "grad_norm": 0.7033511047946183, "learning_rate": 6.528780860477648e-06, "loss": 0.38238067626953126, "num_input_tokens_seen": 490972704, "step": 11915, "train_runtime": 45925.5241, "train_tokens_per_second": 10690.628 }, { "epoch": 0.8025855103689739, "grad_norm": 0.8068288141193891, "learning_rate": 6.526263190175907e-06, "loss": 0.34558258056640623, "num_input_tokens_seen": 491188184, "step": 11920, "train_runtime": 45944.7402, "train_tokens_per_second": 10690.847 }, { "epoch": 0.802922165364934, "grad_norm": 0.6661450183441116, "learning_rate": 6.523745093059531e-06, "loss": 0.3644066572189331, "num_input_tokens_seen": 491394920, "step": 11925, "train_runtime": 45964.9318, "train_tokens_per_second": 10690.648 }, { "epoch": 0.8032588203608941, "grad_norm": 0.7767744522515988, "learning_rate": 6.521226569832699e-06, "loss": 0.3668138265609741, "num_input_tokens_seen": 491602656, "step": 11930, "train_runtime": 45983.7167, "train_tokens_per_second": 10690.799 }, { "epoch": 0.8035954753568543, "grad_norm": 0.7021700115834462, "learning_rate": 6.518707621199707e-06, "loss": 0.3586526393890381, "num_input_tokens_seen": 491808840, "step": 11935, "train_runtime": 46003.9701, "train_tokens_per_second": 10690.574 }, { "epoch": 0.8039321303528144, "grad_norm": 1.1499931029835901, "learning_rate": 6.516188247864972e-06, "loss": 0.38192014694213866, "num_input_tokens_seen": 492021328, "step": 11940, "train_runtime": 46022.817, "train_tokens_per_second": 10690.813 }, { "epoch": 0.8042687853487746, "grad_norm": 0.7471989353775104, "learning_rate": 6.513668450533028e-06, "loss": 0.3716482162475586, "num_input_tokens_seen": 492233320, "step": 11945, "train_runtime": 46041.6445, "train_tokens_per_second": 10691.046 }, { "epoch": 0.8046054403447347, "grad_norm": 0.7202875307764711, "learning_rate": 6.511148229908531e-06, "loss": 0.3962061643600464, "num_input_tokens_seen": 492442440, "step": 11950, "train_runtime": 46060.1254, "train_tokens_per_second": 10691.296 }, { "epoch": 0.8049420953406948, "grad_norm": 0.8280603181863079, "learning_rate": 6.508627586696248e-06, "loss": 0.3628817558288574, "num_input_tokens_seen": 492644376, "step": 11955, "train_runtime": 46079.0206, "train_tokens_per_second": 10691.294 }, { "epoch": 0.805278750336655, "grad_norm": 0.6802468762091337, "learning_rate": 6.5061065216010695e-06, "loss": 0.3675155401229858, "num_input_tokens_seen": 492850248, "step": 11960, "train_runtime": 46097.9788, "train_tokens_per_second": 10691.363 }, { "epoch": 0.8056154053326151, "grad_norm": 0.7182485027164487, "learning_rate": 6.5035850353280075e-06, "loss": 0.34661502838134767, "num_input_tokens_seen": 493054592, "step": 11965, "train_runtime": 46116.1696, "train_tokens_per_second": 10691.577 }, { "epoch": 0.8059520603285752, "grad_norm": 0.7533037690090698, "learning_rate": 6.501063128582183e-06, "loss": 0.3624297618865967, "num_input_tokens_seen": 493251376, "step": 11970, "train_runtime": 46134.0155, "train_tokens_per_second": 10691.707 }, { "epoch": 0.8062887153245354, "grad_norm": 0.8321421113767142, "learning_rate": 6.498540802068843e-06, "loss": 0.3725386619567871, "num_input_tokens_seen": 493455024, "step": 11975, "train_runtime": 46152.2953, "train_tokens_per_second": 10691.885 }, { "epoch": 0.8066253703204955, "grad_norm": 0.772525398639042, "learning_rate": 6.4960180564933454e-06, "loss": 0.35671749114990237, "num_input_tokens_seen": 493664544, "step": 11980, "train_runtime": 46172.2967, "train_tokens_per_second": 10691.791 }, { "epoch": 0.8069620253164557, "grad_norm": 0.7372876745687961, "learning_rate": 6.493494892561167e-06, "loss": 0.35898542404174805, "num_input_tokens_seen": 493864416, "step": 11985, "train_runtime": 46190.9056, "train_tokens_per_second": 10691.811 }, { "epoch": 0.8072986803124158, "grad_norm": 0.7630172193544843, "learning_rate": 6.490971310977907e-06, "loss": 0.3847797870635986, "num_input_tokens_seen": 494073904, "step": 11990, "train_runtime": 46210.9092, "train_tokens_per_second": 10691.716 }, { "epoch": 0.807635335308376, "grad_norm": 0.6734003082497204, "learning_rate": 6.488447312449273e-06, "loss": 0.390543532371521, "num_input_tokens_seen": 494283112, "step": 11995, "train_runtime": 46228.7524, "train_tokens_per_second": 10692.114 }, { "epoch": 0.8079719903043361, "grad_norm": 0.7286501813410619, "learning_rate": 6.485922897681095e-06, "loss": 0.37635579109191897, "num_input_tokens_seen": 494493376, "step": 12000, "train_runtime": 46246.7155, "train_tokens_per_second": 10692.508 }, { "epoch": 0.8083086453002962, "grad_norm": 0.6115644667454996, "learning_rate": 6.483398067379316e-06, "loss": 0.40738582611083984, "num_input_tokens_seen": 494710224, "step": 12005, "train_runtime": 46264.5496, "train_tokens_per_second": 10693.073 }, { "epoch": 0.8086453002962564, "grad_norm": 0.6910359413071975, "learning_rate": 6.480872822249998e-06, "loss": 0.36455085277557375, "num_input_tokens_seen": 494922528, "step": 12010, "train_runtime": 46282.5493, "train_tokens_per_second": 10693.502 }, { "epoch": 0.8089819552922165, "grad_norm": 0.736934472550339, "learning_rate": 6.478347162999318e-06, "loss": 0.38556268215179446, "num_input_tokens_seen": 495124640, "step": 12015, "train_runtime": 46301.6995, "train_tokens_per_second": 10693.444 }, { "epoch": 0.8093186102881766, "grad_norm": 0.6301177117213933, "learning_rate": 6.475821090333568e-06, "loss": 0.3656028985977173, "num_input_tokens_seen": 495333784, "step": 12020, "train_runtime": 46321.717, "train_tokens_per_second": 10693.338 }, { "epoch": 0.8096552652841368, "grad_norm": 0.6951083556394116, "learning_rate": 6.473294604959156e-06, "loss": 0.3930091381072998, "num_input_tokens_seen": 495532912, "step": 12025, "train_runtime": 46340.9206, "train_tokens_per_second": 10693.204 }, { "epoch": 0.8099919202800969, "grad_norm": 0.8667622708314193, "learning_rate": 6.470767707582605e-06, "loss": 0.34512040615081785, "num_input_tokens_seen": 495743024, "step": 12030, "train_runtime": 46359.7586, "train_tokens_per_second": 10693.391 }, { "epoch": 0.8103285752760571, "grad_norm": 0.7800284277581376, "learning_rate": 6.468240398910555e-06, "loss": 0.361209774017334, "num_input_tokens_seen": 495930864, "step": 12035, "train_runtime": 46380.182, "train_tokens_per_second": 10692.732 }, { "epoch": 0.8106652302720172, "grad_norm": 0.6737522658993382, "learning_rate": 6.4657126796497595e-06, "loss": 0.36118927001953127, "num_input_tokens_seen": 496148104, "step": 12040, "train_runtime": 46399.8202, "train_tokens_per_second": 10692.889 }, { "epoch": 0.8110018852679773, "grad_norm": 0.8537201655724918, "learning_rate": 6.463184550507087e-06, "loss": 0.3837599754333496, "num_input_tokens_seen": 496351944, "step": 12045, "train_runtime": 46419.6425, "train_tokens_per_second": 10692.714 }, { "epoch": 0.8113385402639375, "grad_norm": 0.6838376857649898, "learning_rate": 6.46065601218952e-06, "loss": 0.33774096965789796, "num_input_tokens_seen": 496558032, "step": 12050, "train_runtime": 46439.7516, "train_tokens_per_second": 10692.521 }, { "epoch": 0.8116751952598976, "grad_norm": 0.6697280237294989, "learning_rate": 6.458127065404156e-06, "loss": 0.3824258089065552, "num_input_tokens_seen": 496769368, "step": 12055, "train_runtime": 46460.2864, "train_tokens_per_second": 10692.344 }, { "epoch": 0.8120118502558578, "grad_norm": 0.6338534622300693, "learning_rate": 6.45559771085821e-06, "loss": 0.361936354637146, "num_input_tokens_seen": 496981512, "step": 12060, "train_runtime": 46480.7843, "train_tokens_per_second": 10692.193 }, { "epoch": 0.8123485052518179, "grad_norm": 0.6992014290237165, "learning_rate": 6.453067949259005e-06, "loss": 0.36039912700653076, "num_input_tokens_seen": 497192704, "step": 12065, "train_runtime": 46500.1543, "train_tokens_per_second": 10692.281 }, { "epoch": 0.812685160247778, "grad_norm": 0.6522685273193713, "learning_rate": 6.450537781313982e-06, "loss": 0.34694490432739256, "num_input_tokens_seen": 497395672, "step": 12070, "train_runtime": 46518.728, "train_tokens_per_second": 10692.375 }, { "epoch": 0.8130218152437382, "grad_norm": 0.811491034197238, "learning_rate": 6.448007207730693e-06, "loss": 0.375395393371582, "num_input_tokens_seen": 497604056, "step": 12075, "train_runtime": 46538.7068, "train_tokens_per_second": 10692.262 }, { "epoch": 0.8133584702396983, "grad_norm": 0.7272222068624569, "learning_rate": 6.445476229216805e-06, "loss": 0.35945079326629636, "num_input_tokens_seen": 497822496, "step": 12080, "train_runtime": 46557.4935, "train_tokens_per_second": 10692.64 }, { "epoch": 0.8136951252356585, "grad_norm": 0.6903067995353661, "learning_rate": 6.442944846480099e-06, "loss": 0.3930485725402832, "num_input_tokens_seen": 498022144, "step": 12085, "train_runtime": 46576.0036, "train_tokens_per_second": 10692.677 }, { "epoch": 0.8140317802316186, "grad_norm": 0.8901135152449632, "learning_rate": 6.44041306022847e-06, "loss": 0.3994277000427246, "num_input_tokens_seen": 498235008, "step": 12090, "train_runtime": 46595.2981, "train_tokens_per_second": 10692.817 }, { "epoch": 0.8143684352275787, "grad_norm": 0.916382600534659, "learning_rate": 6.43788087116992e-06, "loss": 0.39616050720214846, "num_input_tokens_seen": 498450408, "step": 12095, "train_runtime": 46615.2057, "train_tokens_per_second": 10692.872 }, { "epoch": 0.8147050902235389, "grad_norm": 0.7912031569306731, "learning_rate": 6.43534828001257e-06, "loss": 0.3709789991378784, "num_input_tokens_seen": 498663024, "step": 12100, "train_runtime": 46633.5371, "train_tokens_per_second": 10693.228 }, { "epoch": 0.815041745219499, "grad_norm": 0.8129132049322564, "learning_rate": 6.43281528746465e-06, "loss": 0.37270004749298097, "num_input_tokens_seen": 498857648, "step": 12105, "train_runtime": 46651.0093, "train_tokens_per_second": 10693.395 }, { "epoch": 0.8153784002154592, "grad_norm": 0.6202694318694683, "learning_rate": 6.430281894234504e-06, "loss": 0.37369346618652344, "num_input_tokens_seen": 499068168, "step": 12110, "train_runtime": 46670.463, "train_tokens_per_second": 10693.448 }, { "epoch": 0.8157150552114193, "grad_norm": 0.7021327957870344, "learning_rate": 6.427748101030587e-06, "loss": 0.3813769817352295, "num_input_tokens_seen": 499270832, "step": 12115, "train_runtime": 46690.6282, "train_tokens_per_second": 10693.17 }, { "epoch": 0.8160517102073794, "grad_norm": 0.6908162467008817, "learning_rate": 6.425213908561468e-06, "loss": 0.3676988363265991, "num_input_tokens_seen": 499479672, "step": 12120, "train_runtime": 46710.2832, "train_tokens_per_second": 10693.142 }, { "epoch": 0.8163883652033396, "grad_norm": 0.67816822522844, "learning_rate": 6.422679317535823e-06, "loss": 0.38452901840209963, "num_input_tokens_seen": 499677968, "step": 12125, "train_runtime": 46729.2791, "train_tokens_per_second": 10693.038 }, { "epoch": 0.8167250201992997, "grad_norm": 0.7417236102701672, "learning_rate": 6.420144328662441e-06, "loss": 0.41634154319763184, "num_input_tokens_seen": 499892776, "step": 12130, "train_runtime": 46747.7955, "train_tokens_per_second": 10693.398 }, { "epoch": 0.8170616751952599, "grad_norm": 0.6510309400097822, "learning_rate": 6.417608942650229e-06, "loss": 0.373291540145874, "num_input_tokens_seen": 500085024, "step": 12135, "train_runtime": 46768.7268, "train_tokens_per_second": 10692.723 }, { "epoch": 0.81739833019122, "grad_norm": 0.8728284162484083, "learning_rate": 6.415073160208196e-06, "loss": 0.3705869197845459, "num_input_tokens_seen": 500302000, "step": 12140, "train_runtime": 46786.3366, "train_tokens_per_second": 10693.336 }, { "epoch": 0.8177349851871801, "grad_norm": 0.7930690830075414, "learning_rate": 6.412536982045465e-06, "loss": 0.3863478660583496, "num_input_tokens_seen": 500489648, "step": 12145, "train_runtime": 46805.7042, "train_tokens_per_second": 10692.92 }, { "epoch": 0.8180716401831403, "grad_norm": 0.7554612625428492, "learning_rate": 6.410000408871273e-06, "loss": 0.38945033550262453, "num_input_tokens_seen": 500691864, "step": 12150, "train_runtime": 46823.8594, "train_tokens_per_second": 10693.093 }, { "epoch": 0.8184082951791004, "grad_norm": 0.7565683723362396, "learning_rate": 6.407463441394961e-06, "loss": 0.3782930850982666, "num_input_tokens_seen": 500904856, "step": 12155, "train_runtime": 46843.5288, "train_tokens_per_second": 10693.149 }, { "epoch": 0.8187449501750605, "grad_norm": 0.7419960477378624, "learning_rate": 6.4049260803259874e-06, "loss": 0.390920352935791, "num_input_tokens_seen": 501115176, "step": 12160, "train_runtime": 46863.8077, "train_tokens_per_second": 10693.01 }, { "epoch": 0.8190816051710207, "grad_norm": 0.8056469945466367, "learning_rate": 6.402388326373914e-06, "loss": 0.3650729894638062, "num_input_tokens_seen": 501324464, "step": 12165, "train_runtime": 46884.3094, "train_tokens_per_second": 10692.798 }, { "epoch": 0.8194182601669808, "grad_norm": 0.6665979108791943, "learning_rate": 6.399850180248418e-06, "loss": 0.40616841316223146, "num_input_tokens_seen": 501542144, "step": 12170, "train_runtime": 46903.094, "train_tokens_per_second": 10693.157 }, { "epoch": 0.819754915162941, "grad_norm": 0.7393192173360101, "learning_rate": 6.397311642659283e-06, "loss": 0.3779463291168213, "num_input_tokens_seen": 501741208, "step": 12175, "train_runtime": 46921.0933, "train_tokens_per_second": 10693.297 }, { "epoch": 0.8200915701589011, "grad_norm": 0.6985362998997616, "learning_rate": 6.394772714316402e-06, "loss": 0.3798034429550171, "num_input_tokens_seen": 501956664, "step": 12180, "train_runtime": 46938.8164, "train_tokens_per_second": 10693.85 }, { "epoch": 0.8204282251548612, "grad_norm": 0.6583323971138192, "learning_rate": 6.392233395929779e-06, "loss": 0.3501091480255127, "num_input_tokens_seen": 502155840, "step": 12185, "train_runtime": 46956.1217, "train_tokens_per_second": 10694.151 }, { "epoch": 0.8207648801508214, "grad_norm": 0.627893151663388, "learning_rate": 6.389693688209526e-06, "loss": 0.3626955270767212, "num_input_tokens_seen": 502364280, "step": 12190, "train_runtime": 46976.7495, "train_tokens_per_second": 10693.892 }, { "epoch": 0.8211015351467815, "grad_norm": 0.6501110286778734, "learning_rate": 6.387153591865867e-06, "loss": 0.37912602424621583, "num_input_tokens_seen": 502578568, "step": 12195, "train_runtime": 46996.1916, "train_tokens_per_second": 10694.028 }, { "epoch": 0.8214381901427417, "grad_norm": 0.7133825303267093, "learning_rate": 6.384613107609127e-06, "loss": 0.38680181503295896, "num_input_tokens_seen": 502778744, "step": 12200, "train_runtime": 47014.1932, "train_tokens_per_second": 10694.191 }, { "epoch": 0.8217748451387018, "grad_norm": 0.59469513620908, "learning_rate": 6.382072236149747e-06, "loss": 0.3622967481613159, "num_input_tokens_seen": 502992352, "step": 12205, "train_runtime": 47031.9214, "train_tokens_per_second": 10694.701 }, { "epoch": 0.8221115001346619, "grad_norm": 0.7084570529241369, "learning_rate": 6.379530978198273e-06, "loss": 0.34511799812316896, "num_input_tokens_seen": 503190488, "step": 12210, "train_runtime": 47050.8991, "train_tokens_per_second": 10694.599 }, { "epoch": 0.8224481551306222, "grad_norm": 0.6109894140852417, "learning_rate": 6.376989334465361e-06, "loss": 0.34758384227752687, "num_input_tokens_seen": 503400488, "step": 12215, "train_runtime": 47069.7491, "train_tokens_per_second": 10694.777 }, { "epoch": 0.8227848101265823, "grad_norm": 0.6692682778360864, "learning_rate": 6.374447305661772e-06, "loss": 0.3582954168319702, "num_input_tokens_seen": 503619520, "step": 12220, "train_runtime": 47089.0168, "train_tokens_per_second": 10695.053 }, { "epoch": 0.8231214651225425, "grad_norm": 0.6340623615177271, "learning_rate": 6.3719048924983776e-06, "loss": 0.35860204696655273, "num_input_tokens_seen": 503815816, "step": 12225, "train_runtime": 47109.0802, "train_tokens_per_second": 10694.665 }, { "epoch": 0.8234581201185026, "grad_norm": 0.7170073568813808, "learning_rate": 6.369362095686152e-06, "loss": 0.38410038948059083, "num_input_tokens_seen": 504018280, "step": 12230, "train_runtime": 47127.1852, "train_tokens_per_second": 10694.852 }, { "epoch": 0.8237947751144628, "grad_norm": 0.6788199856176789, "learning_rate": 6.366818915936185e-06, "loss": 0.3466202259063721, "num_input_tokens_seen": 504223664, "step": 12235, "train_runtime": 47144.5628, "train_tokens_per_second": 10695.267 }, { "epoch": 0.8241314301104229, "grad_norm": 0.7061724989470012, "learning_rate": 6.364275353959667e-06, "loss": 0.37665839195251466, "num_input_tokens_seen": 504423664, "step": 12240, "train_runtime": 47164.3072, "train_tokens_per_second": 10695.03 }, { "epoch": 0.824468085106383, "grad_norm": 0.7409096939313102, "learning_rate": 6.3617314104678966e-06, "loss": 0.36662611961364744, "num_input_tokens_seen": 504642280, "step": 12245, "train_runtime": 47182.6297, "train_tokens_per_second": 10695.51 }, { "epoch": 0.8248047401023432, "grad_norm": 0.734148930759195, "learning_rate": 6.359187086172278e-06, "loss": 0.3932323694229126, "num_input_tokens_seen": 504835128, "step": 12250, "train_runtime": 47200.4001, "train_tokens_per_second": 10695.569 }, { "epoch": 0.8251413950983033, "grad_norm": 0.6609309196427652, "learning_rate": 6.356642381784326e-06, "loss": 0.3819995880126953, "num_input_tokens_seen": 505036808, "step": 12255, "train_runtime": 47219.0022, "train_tokens_per_second": 10695.626 }, { "epoch": 0.8254780500942634, "grad_norm": 0.8199815760614162, "learning_rate": 6.354097298015658e-06, "loss": 0.3581740140914917, "num_input_tokens_seen": 505221440, "step": 12260, "train_runtime": 47236.4664, "train_tokens_per_second": 10695.581 }, { "epoch": 0.8258147050902236, "grad_norm": 0.7115880342979133, "learning_rate": 6.3515518355779985e-06, "loss": 0.38808088302612304, "num_input_tokens_seen": 505415504, "step": 12265, "train_runtime": 47255.134, "train_tokens_per_second": 10695.462 }, { "epoch": 0.8261513600861837, "grad_norm": 0.6851345507064921, "learning_rate": 6.349005995183177e-06, "loss": 0.35250661373138426, "num_input_tokens_seen": 505628688, "step": 12270, "train_runtime": 47273.8533, "train_tokens_per_second": 10695.737 }, { "epoch": 0.8264880150821439, "grad_norm": 0.6027111428886356, "learning_rate": 6.346459777543131e-06, "loss": 0.36123099327087405, "num_input_tokens_seen": 505834064, "step": 12275, "train_runtime": 47292.177, "train_tokens_per_second": 10695.935 }, { "epoch": 0.826824670078104, "grad_norm": 0.6806231213293354, "learning_rate": 6.343913183369902e-06, "loss": 0.3593674898147583, "num_input_tokens_seen": 506029096, "step": 12280, "train_runtime": 47311.797, "train_tokens_per_second": 10695.622 }, { "epoch": 0.8271613250740641, "grad_norm": 0.6567993629434257, "learning_rate": 6.341366213375637e-06, "loss": 0.36157591342926027, "num_input_tokens_seen": 506243384, "step": 12285, "train_runtime": 47329.5328, "train_tokens_per_second": 10696.142 }, { "epoch": 0.8274979800700243, "grad_norm": 0.6614117869378269, "learning_rate": 6.338818868272587e-06, "loss": 0.3756159067153931, "num_input_tokens_seen": 506445760, "step": 12290, "train_runtime": 47349.9231, "train_tokens_per_second": 10695.81 }, { "epoch": 0.8278346350659844, "grad_norm": 0.6418394600726333, "learning_rate": 6.336271148773111e-06, "loss": 0.3726262092590332, "num_input_tokens_seen": 506664032, "step": 12295, "train_runtime": 47369.7449, "train_tokens_per_second": 10695.942 }, { "epoch": 0.8281712900619446, "grad_norm": 0.6458339393678464, "learning_rate": 6.333723055589669e-06, "loss": 0.4152766227722168, "num_input_tokens_seen": 506871736, "step": 12300, "train_runtime": 47389.9193, "train_tokens_per_second": 10695.771 }, { "epoch": 0.8285079450579047, "grad_norm": 0.7381979851132201, "learning_rate": 6.331174589434826e-06, "loss": 0.37571213245391843, "num_input_tokens_seen": 507077584, "step": 12305, "train_runtime": 47409.6789, "train_tokens_per_second": 10695.655 }, { "epoch": 0.8288446000538648, "grad_norm": 0.7162835721423431, "learning_rate": 6.328625751021254e-06, "loss": 0.35003113746643066, "num_input_tokens_seen": 507274864, "step": 12310, "train_runtime": 47428.3863, "train_tokens_per_second": 10695.596 }, { "epoch": 0.829181255049825, "grad_norm": 0.6671563134139294, "learning_rate": 6.326076541061729e-06, "loss": 0.3396151542663574, "num_input_tokens_seen": 507479576, "step": 12315, "train_runtime": 47447.3987, "train_tokens_per_second": 10695.625 }, { "epoch": 0.8295179100457851, "grad_norm": 0.9309022114521849, "learning_rate": 6.323526960269127e-06, "loss": 0.4028827667236328, "num_input_tokens_seen": 507677952, "step": 12320, "train_runtime": 47466.7927, "train_tokens_per_second": 10695.434 }, { "epoch": 0.8298545650417453, "grad_norm": 0.8765073358346324, "learning_rate": 6.3209770093564315e-06, "loss": 0.3594415903091431, "num_input_tokens_seen": 507889400, "step": 12325, "train_runtime": 47485.7784, "train_tokens_per_second": 10695.611 }, { "epoch": 0.8301912200377054, "grad_norm": 0.969785270620946, "learning_rate": 6.318426689036727e-06, "loss": 0.35783944129943845, "num_input_tokens_seen": 508094208, "step": 12330, "train_runtime": 47507.4226, "train_tokens_per_second": 10695.049 }, { "epoch": 0.8305278750336655, "grad_norm": 0.7224782503475782, "learning_rate": 6.315876000023202e-06, "loss": 0.3748546838760376, "num_input_tokens_seen": 508294584, "step": 12335, "train_runtime": 47526.3995, "train_tokens_per_second": 10694.995 }, { "epoch": 0.8308645300296257, "grad_norm": 0.6760921409544947, "learning_rate": 6.313324943029151e-06, "loss": 0.38138570785522463, "num_input_tokens_seen": 508497048, "step": 12340, "train_runtime": 47547.2545, "train_tokens_per_second": 10694.562 }, { "epoch": 0.8312011850255858, "grad_norm": 0.6051398529446763, "learning_rate": 6.310773518767967e-06, "loss": 0.3586656332015991, "num_input_tokens_seen": 508696600, "step": 12345, "train_runtime": 47565.5155, "train_tokens_per_second": 10694.651 }, { "epoch": 0.831537840021546, "grad_norm": 0.703656074447125, "learning_rate": 6.30822172795315e-06, "loss": 0.3735224723815918, "num_input_tokens_seen": 508891400, "step": 12350, "train_runtime": 47584.4007, "train_tokens_per_second": 10694.501 }, { "epoch": 0.8318744950175061, "grad_norm": 0.7647859987620237, "learning_rate": 6.3056695712982965e-06, "loss": 0.4237032890319824, "num_input_tokens_seen": 509100016, "step": 12355, "train_runtime": 47602.4805, "train_tokens_per_second": 10694.821 }, { "epoch": 0.8322111500134662, "grad_norm": 0.6730364974902364, "learning_rate": 6.303117049517111e-06, "loss": 0.34355523586273196, "num_input_tokens_seen": 509304296, "step": 12360, "train_runtime": 47622.697, "train_tokens_per_second": 10694.571 }, { "epoch": 0.8325478050094264, "grad_norm": 0.6897444976086832, "learning_rate": 6.300564163323398e-06, "loss": 0.3662103176116943, "num_input_tokens_seen": 509505952, "step": 12365, "train_runtime": 47642.0708, "train_tokens_per_second": 10694.454 }, { "epoch": 0.8328844600053865, "grad_norm": 0.7548581333990814, "learning_rate": 6.298010913431065e-06, "loss": 0.3760966777801514, "num_input_tokens_seen": 509709200, "step": 12370, "train_runtime": 47660.2225, "train_tokens_per_second": 10694.646 }, { "epoch": 0.8332211150013467, "grad_norm": 0.7436195161590975, "learning_rate": 6.295457300554119e-06, "loss": 0.359889554977417, "num_input_tokens_seen": 509922152, "step": 12375, "train_runtime": 47679.19, "train_tokens_per_second": 10694.858 }, { "epoch": 0.8335577699973068, "grad_norm": 0.789592617494116, "learning_rate": 6.292903325406668e-06, "loss": 0.39346396923065186, "num_input_tokens_seen": 510113600, "step": 12380, "train_runtime": 47698.108, "train_tokens_per_second": 10694.63 }, { "epoch": 0.8338944249932669, "grad_norm": 0.7313719816219346, "learning_rate": 6.2903489887029255e-06, "loss": 0.35265517234802246, "num_input_tokens_seen": 510323296, "step": 12385, "train_runtime": 47716.7286, "train_tokens_per_second": 10694.851 }, { "epoch": 0.8342310799892271, "grad_norm": 0.6366861164661117, "learning_rate": 6.287794291157204e-06, "loss": 0.36598658561706543, "num_input_tokens_seen": 510526896, "step": 12390, "train_runtime": 47735.4507, "train_tokens_per_second": 10694.921 }, { "epoch": 0.8345677349851872, "grad_norm": 0.7218513509614443, "learning_rate": 6.285239233483915e-06, "loss": 0.3708180904388428, "num_input_tokens_seen": 510744040, "step": 12395, "train_runtime": 47753.6158, "train_tokens_per_second": 10695.4 }, { "epoch": 0.8349043899811474, "grad_norm": 0.6388585127825546, "learning_rate": 6.2826838163975724e-06, "loss": 0.3763378620147705, "num_input_tokens_seen": 510946616, "step": 12400, "train_runtime": 47771.1475, "train_tokens_per_second": 10695.716 }, { "epoch": 0.8352410449771075, "grad_norm": 0.6935578828935915, "learning_rate": 6.2801280406127905e-06, "loss": 0.34698007106781004, "num_input_tokens_seen": 511157944, "step": 12405, "train_runtime": 47790.6663, "train_tokens_per_second": 10695.769 }, { "epoch": 0.8355776999730676, "grad_norm": 0.7117583622694726, "learning_rate": 6.2775719068442845e-06, "loss": 0.359056282043457, "num_input_tokens_seen": 511361800, "step": 12410, "train_runtime": 47808.7987, "train_tokens_per_second": 10695.977 }, { "epoch": 0.8359143549690278, "grad_norm": 0.6533189468303153, "learning_rate": 6.275015415806869e-06, "loss": 0.35450446605682373, "num_input_tokens_seen": 511558848, "step": 12415, "train_runtime": 47828.639, "train_tokens_per_second": 10695.66 }, { "epoch": 0.8362510099649879, "grad_norm": 0.6425275182502073, "learning_rate": 6.272458568215458e-06, "loss": 0.38054571151733396, "num_input_tokens_seen": 511763904, "step": 12420, "train_runtime": 47847.5707, "train_tokens_per_second": 10695.713 }, { "epoch": 0.836587664960948, "grad_norm": 0.7234318668335151, "learning_rate": 6.269901364785066e-06, "loss": 0.37750020027160647, "num_input_tokens_seen": 511975088, "step": 12425, "train_runtime": 47865.2284, "train_tokens_per_second": 10696.18 }, { "epoch": 0.8369243199569082, "grad_norm": 0.671716438349271, "learning_rate": 6.2673438062308055e-06, "loss": 0.37099518775939944, "num_input_tokens_seen": 512199712, "step": 12430, "train_runtime": 47883.6869, "train_tokens_per_second": 10696.748 }, { "epoch": 0.8372609749528683, "grad_norm": 0.7593281659555264, "learning_rate": 6.264785893267892e-06, "loss": 0.3515657901763916, "num_input_tokens_seen": 512391416, "step": 12435, "train_runtime": 47901.5792, "train_tokens_per_second": 10696.754 }, { "epoch": 0.8375976299488285, "grad_norm": 0.7112700666934871, "learning_rate": 6.2622276266116366e-06, "loss": 0.36327762603759767, "num_input_tokens_seen": 512600792, "step": 12440, "train_runtime": 47919.6608, "train_tokens_per_second": 10697.087 }, { "epoch": 0.8379342849447886, "grad_norm": 0.6378888671709556, "learning_rate": 6.25966900697745e-06, "loss": 0.38032984733581543, "num_input_tokens_seen": 512812232, "step": 12445, "train_runtime": 47938.3775, "train_tokens_per_second": 10697.321 }, { "epoch": 0.8382709399407487, "grad_norm": 0.6375818141194641, "learning_rate": 6.257110035080843e-06, "loss": 0.3507856369018555, "num_input_tokens_seen": 513023848, "step": 12450, "train_runtime": 47957.3163, "train_tokens_per_second": 10697.51 }, { "epoch": 0.8386075949367089, "grad_norm": 0.6741694289863218, "learning_rate": 6.254550711637422e-06, "loss": 0.4172701835632324, "num_input_tokens_seen": 513220816, "step": 12455, "train_runtime": 47976.7064, "train_tokens_per_second": 10697.292 }, { "epoch": 0.838944249932669, "grad_norm": 0.8418801497819061, "learning_rate": 6.251991037362897e-06, "loss": 0.38213448524475097, "num_input_tokens_seen": 513417720, "step": 12460, "train_runtime": 47995.489, "train_tokens_per_second": 10697.208 }, { "epoch": 0.8392809049286292, "grad_norm": 0.7161811709473286, "learning_rate": 6.249431012973068e-06, "loss": 0.3765326976776123, "num_input_tokens_seen": 513616880, "step": 12465, "train_runtime": 48014.6823, "train_tokens_per_second": 10697.08 }, { "epoch": 0.8396175599245893, "grad_norm": 0.6934040397487011, "learning_rate": 6.246870639183843e-06, "loss": 0.3746959924697876, "num_input_tokens_seen": 513817160, "step": 12470, "train_runtime": 48034.4673, "train_tokens_per_second": 10696.843 }, { "epoch": 0.8399542149205494, "grad_norm": 0.7565946916425765, "learning_rate": 6.2443099167112185e-06, "loss": 0.3992312908172607, "num_input_tokens_seen": 514029096, "step": 12475, "train_runtime": 48054.2261, "train_tokens_per_second": 10696.855 }, { "epoch": 0.8402908699165096, "grad_norm": 0.657855795899407, "learning_rate": 6.241748846271293e-06, "loss": 0.37391462326049807, "num_input_tokens_seen": 514242120, "step": 12480, "train_runtime": 48073.0876, "train_tokens_per_second": 10697.089 }, { "epoch": 0.8406275249124697, "grad_norm": 0.7303705017647775, "learning_rate": 6.239187428580263e-06, "loss": 0.37525601387023927, "num_input_tokens_seen": 514436568, "step": 12485, "train_runtime": 48091.747, "train_tokens_per_second": 10696.982 }, { "epoch": 0.8409641799084299, "grad_norm": 0.7161914346605113, "learning_rate": 6.236625664354421e-06, "loss": 0.38015174865722656, "num_input_tokens_seen": 514647448, "step": 12490, "train_runtime": 48110.2214, "train_tokens_per_second": 10697.258 }, { "epoch": 0.84130083490439, "grad_norm": 0.7819160015614802, "learning_rate": 6.2340635543101545e-06, "loss": 0.36240205764770506, "num_input_tokens_seen": 514835352, "step": 12495, "train_runtime": 48130.6782, "train_tokens_per_second": 10696.615 }, { "epoch": 0.8416374899003501, "grad_norm": 0.6373066722309301, "learning_rate": 6.23150109916395e-06, "loss": 0.3442065238952637, "num_input_tokens_seen": 515045136, "step": 12500, "train_runtime": 48150.3364, "train_tokens_per_second": 10696.605 }, { "epoch": 0.8419741448963103, "grad_norm": 0.6608575763352064, "learning_rate": 6.22893829963239e-06, "loss": 0.3896924018859863, "num_input_tokens_seen": 515245392, "step": 12505, "train_runtime": 48169.532, "train_tokens_per_second": 10696.5 }, { "epoch": 0.8423107998922704, "grad_norm": 0.7420503999801638, "learning_rate": 6.226375156432153e-06, "loss": 0.36340258121490476, "num_input_tokens_seen": 515459896, "step": 12510, "train_runtime": 48187.9943, "train_tokens_per_second": 10696.853 }, { "epoch": 0.8426474548882306, "grad_norm": 0.6999765729652203, "learning_rate": 6.2238116702800145e-06, "loss": 0.373760986328125, "num_input_tokens_seen": 515661872, "step": 12515, "train_runtime": 48205.9552, "train_tokens_per_second": 10697.057 }, { "epoch": 0.8429841098841907, "grad_norm": 0.7403677524005302, "learning_rate": 6.221247841892846e-06, "loss": 0.3934285640716553, "num_input_tokens_seen": 515860856, "step": 12520, "train_runtime": 48225.8123, "train_tokens_per_second": 10696.779 }, { "epoch": 0.8433207648801508, "grad_norm": 0.8147609152171995, "learning_rate": 6.218683671987611e-06, "loss": 0.37361693382263184, "num_input_tokens_seen": 516080072, "step": 12525, "train_runtime": 48243.7825, "train_tokens_per_second": 10697.339 }, { "epoch": 0.843657419876111, "grad_norm": 0.8270114924575949, "learning_rate": 6.216119161281373e-06, "loss": 0.37630457878112794, "num_input_tokens_seen": 516291408, "step": 12530, "train_runtime": 48263.9353, "train_tokens_per_second": 10697.251 }, { "epoch": 0.8439940748720711, "grad_norm": 0.6725781619012211, "learning_rate": 6.213554310491291e-06, "loss": 0.36432576179504395, "num_input_tokens_seen": 516493320, "step": 12535, "train_runtime": 48284.2129, "train_tokens_per_second": 10696.94 }, { "epoch": 0.8443307298680313, "grad_norm": 0.6284460866855709, "learning_rate": 6.210989120334616e-06, "loss": 0.3693974256515503, "num_input_tokens_seen": 516701376, "step": 12540, "train_runtime": 48304.5201, "train_tokens_per_second": 10696.75 }, { "epoch": 0.8446673848639914, "grad_norm": 0.741734327748075, "learning_rate": 6.208423591528694e-06, "loss": 0.3844477891921997, "num_input_tokens_seen": 516900016, "step": 12545, "train_runtime": 48322.6041, "train_tokens_per_second": 10696.858 }, { "epoch": 0.8450040398599515, "grad_norm": 0.7209904738881459, "learning_rate": 6.205857724790969e-06, "loss": 0.3651737213134766, "num_input_tokens_seen": 517103048, "step": 12550, "train_runtime": 48340.5081, "train_tokens_per_second": 10697.096 }, { "epoch": 0.8453406948559117, "grad_norm": 0.7720545911306782, "learning_rate": 6.203291520838974e-06, "loss": 0.4080327033996582, "num_input_tokens_seen": 517318368, "step": 12555, "train_runtime": 48359.4171, "train_tokens_per_second": 10697.366 }, { "epoch": 0.8456773498518718, "grad_norm": 0.65896209335533, "learning_rate": 6.200724980390344e-06, "loss": 0.34375145435333254, "num_input_tokens_seen": 517503888, "step": 12560, "train_runtime": 48379.7367, "train_tokens_per_second": 10696.707 }, { "epoch": 0.846014004847832, "grad_norm": 0.6580167532067056, "learning_rate": 6.198158104162804e-06, "loss": 0.32467103004455566, "num_input_tokens_seen": 517706880, "step": 12565, "train_runtime": 48398.2285, "train_tokens_per_second": 10696.815 }, { "epoch": 0.8463506598437921, "grad_norm": 0.6976990632479525, "learning_rate": 6.1955908928741685e-06, "loss": 0.3791512489318848, "num_input_tokens_seen": 517929528, "step": 12570, "train_runtime": 48416.7636, "train_tokens_per_second": 10697.318 }, { "epoch": 0.8466873148397522, "grad_norm": 0.6578401435694221, "learning_rate": 6.193023347242353e-06, "loss": 0.3855516672134399, "num_input_tokens_seen": 518145328, "step": 12575, "train_runtime": 48435.4499, "train_tokens_per_second": 10697.647 }, { "epoch": 0.8470239698357124, "grad_norm": 0.7253685459557482, "learning_rate": 6.190455467985361e-06, "loss": 0.373577356338501, "num_input_tokens_seen": 518354104, "step": 12580, "train_runtime": 48453.6121, "train_tokens_per_second": 10697.946 }, { "epoch": 0.8473606248316725, "grad_norm": 0.7212863192556168, "learning_rate": 6.187887255821295e-06, "loss": 0.3996755599975586, "num_input_tokens_seen": 518561208, "step": 12585, "train_runtime": 48472.1028, "train_tokens_per_second": 10698.137 }, { "epoch": 0.8476972798276327, "grad_norm": 0.7830093443354731, "learning_rate": 6.185318711468345e-06, "loss": 0.3553699254989624, "num_input_tokens_seen": 518753184, "step": 12590, "train_runtime": 48492.8412, "train_tokens_per_second": 10697.521 }, { "epoch": 0.8480339348235928, "grad_norm": 0.7184713518139837, "learning_rate": 6.182749835644799e-06, "loss": 0.35891387462615965, "num_input_tokens_seen": 518950520, "step": 12595, "train_runtime": 48511.2185, "train_tokens_per_second": 10697.536 }, { "epoch": 0.8483705898195529, "grad_norm": 0.6404082279073382, "learning_rate": 6.180180629069031e-06, "loss": 0.35750784873962405, "num_input_tokens_seen": 519167496, "step": 12600, "train_runtime": 48531.4205, "train_tokens_per_second": 10697.554 }, { "epoch": 0.8487072448155131, "grad_norm": 0.7283210187986441, "learning_rate": 6.177611092459514e-06, "loss": 0.34214680194854735, "num_input_tokens_seen": 519372320, "step": 12605, "train_runtime": 48551.3594, "train_tokens_per_second": 10697.38 }, { "epoch": 0.8490438998114732, "grad_norm": 0.703400805214901, "learning_rate": 6.175041226534809e-06, "loss": 0.3668935775756836, "num_input_tokens_seen": 519580376, "step": 12610, "train_runtime": 48570.0213, "train_tokens_per_second": 10697.553 }, { "epoch": 0.8493805548074334, "grad_norm": 0.6494278429494813, "learning_rate": 6.172471032013574e-06, "loss": 0.32718400955200194, "num_input_tokens_seen": 519793720, "step": 12615, "train_runtime": 48590.8673, "train_tokens_per_second": 10697.354 }, { "epoch": 0.8497172098033935, "grad_norm": 0.6149362930986026, "learning_rate": 6.169900509614553e-06, "loss": 0.3608169794082642, "num_input_tokens_seen": 520011344, "step": 12620, "train_runtime": 48609.4099, "train_tokens_per_second": 10697.751 }, { "epoch": 0.8500538647993536, "grad_norm": 0.7348269191751972, "learning_rate": 6.167329660056585e-06, "loss": 0.368850040435791, "num_input_tokens_seen": 520211440, "step": 12625, "train_runtime": 48627.3354, "train_tokens_per_second": 10697.922 }, { "epoch": 0.8503905197953138, "grad_norm": 0.6006677947690707, "learning_rate": 6.1647584840586e-06, "loss": 0.37121214866638186, "num_input_tokens_seen": 520423568, "step": 12630, "train_runtime": 48647.5722, "train_tokens_per_second": 10697.832 }, { "epoch": 0.8507271747912739, "grad_norm": 0.6726998292156215, "learning_rate": 6.1621869823396175e-06, "loss": 0.36881630420684813, "num_input_tokens_seen": 520640544, "step": 12635, "train_runtime": 48665.2294, "train_tokens_per_second": 10698.409 }, { "epoch": 0.851063829787234, "grad_norm": 0.7604191316330903, "learning_rate": 6.159615155618752e-06, "loss": 0.37218687534332273, "num_input_tokens_seen": 520852448, "step": 12640, "train_runtime": 48683.906, "train_tokens_per_second": 10698.658 }, { "epoch": 0.8514004847831942, "grad_norm": 0.7528879326891564, "learning_rate": 6.157043004615207e-06, "loss": 0.3862943172454834, "num_input_tokens_seen": 521076936, "step": 12645, "train_runtime": 48703.6797, "train_tokens_per_second": 10698.923 }, { "epoch": 0.8517371397791543, "grad_norm": 0.7747214904032371, "learning_rate": 6.1544705300482755e-06, "loss": 0.36604273319244385, "num_input_tokens_seen": 521292368, "step": 12650, "train_runtime": 48723.621, "train_tokens_per_second": 10698.966 }, { "epoch": 0.8520737947751145, "grad_norm": 0.6359862366240009, "learning_rate": 6.151897732637341e-06, "loss": 0.3438862323760986, "num_input_tokens_seen": 521488280, "step": 12655, "train_runtime": 48741.8643, "train_tokens_per_second": 10698.981 }, { "epoch": 0.8524104497710746, "grad_norm": 0.794006619839161, "learning_rate": 6.149324613101877e-06, "loss": 0.37916340827941897, "num_input_tokens_seen": 521696552, "step": 12660, "train_runtime": 48762.7388, "train_tokens_per_second": 10698.672 }, { "epoch": 0.8527471047670347, "grad_norm": 0.5938751766560403, "learning_rate": 6.146751172161453e-06, "loss": 0.3463816404342651, "num_input_tokens_seen": 521911360, "step": 12665, "train_runtime": 48781.37, "train_tokens_per_second": 10698.989 }, { "epoch": 0.8530837597629949, "grad_norm": 0.7969625557513234, "learning_rate": 6.144177410535719e-06, "loss": 0.36754014492034914, "num_input_tokens_seen": 522121120, "step": 12670, "train_runtime": 48799.4197, "train_tokens_per_second": 10699.331 }, { "epoch": 0.853420414758955, "grad_norm": 0.6800172676101385, "learning_rate": 6.14160332894442e-06, "loss": 0.357354736328125, "num_input_tokens_seen": 522319768, "step": 12675, "train_runtime": 48818.7808, "train_tokens_per_second": 10699.156 }, { "epoch": 0.8537570697549152, "grad_norm": 0.7402785425156081, "learning_rate": 6.139028928107391e-06, "loss": 0.37166829109191896, "num_input_tokens_seen": 522524320, "step": 12680, "train_runtime": 48837.2173, "train_tokens_per_second": 10699.306 }, { "epoch": 0.8540937247508753, "grad_norm": 0.6661439792388875, "learning_rate": 6.136454208744553e-06, "loss": 0.34337787628173827, "num_input_tokens_seen": 522729672, "step": 12685, "train_runtime": 48855.605, "train_tokens_per_second": 10699.482 }, { "epoch": 0.8544303797468354, "grad_norm": 0.715153622451024, "learning_rate": 6.133879171575921e-06, "loss": 0.3743175506591797, "num_input_tokens_seen": 522933888, "step": 12690, "train_runtime": 48875.4985, "train_tokens_per_second": 10699.305 }, { "epoch": 0.8547670347427956, "grad_norm": 0.6973441037915752, "learning_rate": 6.131303817321595e-06, "loss": 0.39978153705596925, "num_input_tokens_seen": 523150184, "step": 12695, "train_runtime": 48895.7441, "train_tokens_per_second": 10699.299 }, { "epoch": 0.8551036897387557, "grad_norm": 0.6526683298074512, "learning_rate": 6.128728146701763e-06, "loss": 0.3920637845993042, "num_input_tokens_seen": 523363544, "step": 12700, "train_runtime": 48913.8925, "train_tokens_per_second": 10699.691 }, { "epoch": 0.8554403447347159, "grad_norm": 0.6602838158450008, "learning_rate": 6.126152160436705e-06, "loss": 0.33115692138671876, "num_input_tokens_seen": 523571544, "step": 12705, "train_runtime": 48932.8747, "train_tokens_per_second": 10699.791 }, { "epoch": 0.855776999730676, "grad_norm": 0.9206357378385513, "learning_rate": 6.123575859246784e-06, "loss": 0.38689823150634767, "num_input_tokens_seen": 523769960, "step": 12710, "train_runtime": 48952.9147, "train_tokens_per_second": 10699.464 }, { "epoch": 0.8561136547266361, "grad_norm": 0.7010837054905428, "learning_rate": 6.120999243852459e-06, "loss": 0.35260155200958254, "num_input_tokens_seen": 523971024, "step": 12715, "train_runtime": 48972.642, "train_tokens_per_second": 10699.26 }, { "epoch": 0.8564503097225963, "grad_norm": 0.7668583831730781, "learning_rate": 6.118422314974269e-06, "loss": 0.3807115077972412, "num_input_tokens_seen": 524179792, "step": 12720, "train_runtime": 48992.5646, "train_tokens_per_second": 10699.17 }, { "epoch": 0.8567869647185564, "grad_norm": 0.711774020162355, "learning_rate": 6.115845073332845e-06, "loss": 0.3746687412261963, "num_input_tokens_seen": 524396120, "step": 12725, "train_runtime": 49010.6827, "train_tokens_per_second": 10699.629 }, { "epoch": 0.8571236197145166, "grad_norm": 0.817952149205225, "learning_rate": 6.113267519648905e-06, "loss": 0.39794216156005857, "num_input_tokens_seen": 524618264, "step": 12730, "train_runtime": 49029.1912, "train_tokens_per_second": 10700.121 }, { "epoch": 0.8574602747104767, "grad_norm": 0.6156070178521492, "learning_rate": 6.110689654643253e-06, "loss": 0.36534733772277833, "num_input_tokens_seen": 524816440, "step": 12735, "train_runtime": 49049.5245, "train_tokens_per_second": 10699.725 }, { "epoch": 0.8577969297064368, "grad_norm": 0.6512888373439462, "learning_rate": 6.1081114790367805e-06, "loss": 0.3757661819458008, "num_input_tokens_seen": 525013952, "step": 12740, "train_runtime": 49068.0959, "train_tokens_per_second": 10699.701 }, { "epoch": 0.858133584702397, "grad_norm": 0.7158888360768694, "learning_rate": 6.105532993550467e-06, "loss": 0.37044467926025393, "num_input_tokens_seen": 525223840, "step": 12745, "train_runtime": 49086.3555, "train_tokens_per_second": 10699.997 }, { "epoch": 0.8584702396983571, "grad_norm": 0.7373106381993569, "learning_rate": 6.1029541989053765e-06, "loss": 0.36229567527770995, "num_input_tokens_seen": 525430080, "step": 12750, "train_runtime": 49107.3582, "train_tokens_per_second": 10699.62 }, { "epoch": 0.8588068946943173, "grad_norm": 0.5956585536559881, "learning_rate": 6.100375095822661e-06, "loss": 0.3691676139831543, "num_input_tokens_seen": 525635480, "step": 12755, "train_runtime": 49127.2269, "train_tokens_per_second": 10699.474 }, { "epoch": 0.8591435496902774, "grad_norm": 0.6827698200350242, "learning_rate": 6.097795685023558e-06, "loss": 0.3640700578689575, "num_input_tokens_seen": 525842480, "step": 12760, "train_runtime": 49145.4393, "train_tokens_per_second": 10699.721 }, { "epoch": 0.8594802046862375, "grad_norm": 0.6797108804809036, "learning_rate": 6.095215967229396e-06, "loss": 0.34571108818054197, "num_input_tokens_seen": 526036824, "step": 12765, "train_runtime": 49164.6917, "train_tokens_per_second": 10699.484 }, { "epoch": 0.8598168596821977, "grad_norm": 0.653361349353786, "learning_rate": 6.092635943161578e-06, "loss": 0.3743870973587036, "num_input_tokens_seen": 526250088, "step": 12770, "train_runtime": 49182.806, "train_tokens_per_second": 10699.879 }, { "epoch": 0.8601535146781578, "grad_norm": 0.6965597151128863, "learning_rate": 6.090055613541603e-06, "loss": 0.35263235569000245, "num_input_tokens_seen": 526464128, "step": 12775, "train_runtime": 49201.6863, "train_tokens_per_second": 10700.124 }, { "epoch": 0.860490169674118, "grad_norm": 0.7411597877277329, "learning_rate": 6.087474979091052e-06, "loss": 0.36073205471038816, "num_input_tokens_seen": 526662928, "step": 12780, "train_runtime": 49223.4746, "train_tokens_per_second": 10699.426 }, { "epoch": 0.8608268246700781, "grad_norm": 0.6817237924801, "learning_rate": 6.084894040531591e-06, "loss": 0.3649157524108887, "num_input_tokens_seen": 526872224, "step": 12785, "train_runtime": 49242.3133, "train_tokens_per_second": 10699.583 }, { "epoch": 0.8611634796660382, "grad_norm": 0.7184042453635167, "learning_rate": 6.0823127985849705e-06, "loss": 0.3551290512084961, "num_input_tokens_seen": 527068440, "step": 12790, "train_runtime": 49263.0642, "train_tokens_per_second": 10699.059 }, { "epoch": 0.8615001346619984, "grad_norm": 0.6820025169776506, "learning_rate": 6.079731253973028e-06, "loss": 0.3526898384094238, "num_input_tokens_seen": 527278968, "step": 12795, "train_runtime": 49283.1938, "train_tokens_per_second": 10698.961 }, { "epoch": 0.8618367896579585, "grad_norm": 0.7156471704706077, "learning_rate": 6.077149407417683e-06, "loss": 0.35791740417480467, "num_input_tokens_seen": 527481488, "step": 12800, "train_runtime": 49302.4795, "train_tokens_per_second": 10698.884 }, { "epoch": 0.8621734446539187, "grad_norm": 0.6809804349153191, "learning_rate": 6.07456725964094e-06, "loss": 0.3742764949798584, "num_input_tokens_seen": 527679288, "step": 12805, "train_runtime": 49321.4347, "train_tokens_per_second": 10698.782 }, { "epoch": 0.8625100996498788, "grad_norm": 0.6653166942437883, "learning_rate": 6.07198481136489e-06, "loss": 0.34651942253112794, "num_input_tokens_seen": 527878960, "step": 12810, "train_runtime": 49339.4552, "train_tokens_per_second": 10698.922 }, { "epoch": 0.8628467546458389, "grad_norm": 0.7284351202587671, "learning_rate": 6.069402063311706e-06, "loss": 0.3549565315246582, "num_input_tokens_seen": 528079752, "step": 12815, "train_runtime": 49358.547, "train_tokens_per_second": 10698.851 }, { "epoch": 0.8631834096417991, "grad_norm": 0.7889611647319732, "learning_rate": 6.066819016203646e-06, "loss": 0.3694820165634155, "num_input_tokens_seen": 528281608, "step": 12820, "train_runtime": 49377.508, "train_tokens_per_second": 10698.831 }, { "epoch": 0.8635200646377592, "grad_norm": 0.7027686619224588, "learning_rate": 6.064235670763048e-06, "loss": 0.37345871925354, "num_input_tokens_seen": 528489672, "step": 12825, "train_runtime": 49396.9447, "train_tokens_per_second": 10698.833 }, { "epoch": 0.8638567196337193, "grad_norm": 0.6653725085093666, "learning_rate": 6.06165202771234e-06, "loss": 0.3802985191345215, "num_input_tokens_seen": 528703472, "step": 12830, "train_runtime": 49415.7017, "train_tokens_per_second": 10699.099 }, { "epoch": 0.8641933746296795, "grad_norm": 0.6341565812954956, "learning_rate": 6.059068087774026e-06, "loss": 0.3477687120437622, "num_input_tokens_seen": 528895840, "step": 12835, "train_runtime": 49435.5836, "train_tokens_per_second": 10698.687 }, { "epoch": 0.8645300296256396, "grad_norm": 0.6616035646687891, "learning_rate": 6.0564838516707005e-06, "loss": 0.40116262435913086, "num_input_tokens_seen": 529109864, "step": 12840, "train_runtime": 49455.824, "train_tokens_per_second": 10698.636 }, { "epoch": 0.8648666846215998, "grad_norm": 0.6114690491411636, "learning_rate": 6.053899320125033e-06, "loss": 0.3491672992706299, "num_input_tokens_seen": 529317144, "step": 12845, "train_runtime": 49475.2248, "train_tokens_per_second": 10698.63 }, { "epoch": 0.8652033396175599, "grad_norm": 0.7080793113429159, "learning_rate": 6.051314493859782e-06, "loss": 0.3800661087036133, "num_input_tokens_seen": 529528344, "step": 12850, "train_runtime": 49493.2171, "train_tokens_per_second": 10699.008 }, { "epoch": 0.86553999461352, "grad_norm": 0.6620665828439922, "learning_rate": 6.048729373597786e-06, "loss": 0.36305985450744627, "num_input_tokens_seen": 529734392, "step": 12855, "train_runtime": 49511.3826, "train_tokens_per_second": 10699.245 }, { "epoch": 0.8658766496094802, "grad_norm": 0.6654498612692272, "learning_rate": 6.046143960061963e-06, "loss": 0.3825050354003906, "num_input_tokens_seen": 529946552, "step": 12860, "train_runtime": 49530.4711, "train_tokens_per_second": 10699.405 }, { "epoch": 0.8662133046054403, "grad_norm": 0.8153848785556935, "learning_rate": 6.043558253975319e-06, "loss": 0.39293608665466306, "num_input_tokens_seen": 530163960, "step": 12865, "train_runtime": 49547.9964, "train_tokens_per_second": 10700.008 }, { "epoch": 0.8665499596014005, "grad_norm": 0.7284153583981318, "learning_rate": 6.040972256060936e-06, "loss": 0.3584618330001831, "num_input_tokens_seen": 530365096, "step": 12870, "train_runtime": 49567.9996, "train_tokens_per_second": 10699.748 }, { "epoch": 0.8668866145973606, "grad_norm": 0.7101842920864795, "learning_rate": 6.038385967041982e-06, "loss": 0.3556619167327881, "num_input_tokens_seen": 530563360, "step": 12875, "train_runtime": 49587.2064, "train_tokens_per_second": 10699.602 }, { "epoch": 0.8672232695933207, "grad_norm": 0.7185477573327342, "learning_rate": 6.035799387641703e-06, "loss": 0.3725925922393799, "num_input_tokens_seen": 530774696, "step": 12880, "train_runtime": 49606.417, "train_tokens_per_second": 10699.718 }, { "epoch": 0.8675599245892809, "grad_norm": 0.7207595806721574, "learning_rate": 6.033212518583427e-06, "loss": 0.37887229919433596, "num_input_tokens_seen": 530973416, "step": 12885, "train_runtime": 49627.107, "train_tokens_per_second": 10699.262 }, { "epoch": 0.867896579585241, "grad_norm": 0.7269098331243308, "learning_rate": 6.030625360590567e-06, "loss": 0.361545467376709, "num_input_tokens_seen": 531185832, "step": 12890, "train_runtime": 49647.4015, "train_tokens_per_second": 10699.167 }, { "epoch": 0.8682332345812012, "grad_norm": 0.6162935840705447, "learning_rate": 6.028037914386609e-06, "loss": 0.3577485799789429, "num_input_tokens_seen": 531394248, "step": 12895, "train_runtime": 49666.8617, "train_tokens_per_second": 10699.171 }, { "epoch": 0.8685698895771613, "grad_norm": 0.6915897361582527, "learning_rate": 6.025450180695128e-06, "loss": 0.3880067110061646, "num_input_tokens_seen": 531600744, "step": 12900, "train_runtime": 49685.8637, "train_tokens_per_second": 10699.235 }, { "epoch": 0.8689065445731214, "grad_norm": 0.8117638543810042, "learning_rate": 6.022862160239774e-06, "loss": 0.363564133644104, "num_input_tokens_seen": 531803264, "step": 12905, "train_runtime": 49707.5877, "train_tokens_per_second": 10698.634 }, { "epoch": 0.8692431995690816, "grad_norm": 0.6099265546171233, "learning_rate": 6.020273853744277e-06, "loss": 0.35659017562866213, "num_input_tokens_seen": 532009680, "step": 12910, "train_runtime": 49725.769, "train_tokens_per_second": 10698.873 }, { "epoch": 0.8695798545650417, "grad_norm": 0.7710684758849251, "learning_rate": 6.017685261932452e-06, "loss": 0.3561567306518555, "num_input_tokens_seen": 532199104, "step": 12915, "train_runtime": 49743.4116, "train_tokens_per_second": 10698.886 }, { "epoch": 0.8699165095610019, "grad_norm": 0.6969006479556715, "learning_rate": 6.015096385528189e-06, "loss": 0.37289748191833494, "num_input_tokens_seen": 532400344, "step": 12920, "train_runtime": 49763.1068, "train_tokens_per_second": 10698.696 }, { "epoch": 0.870253164556962, "grad_norm": 0.693636649094152, "learning_rate": 6.012507225255457e-06, "loss": 0.3906707763671875, "num_input_tokens_seen": 532586896, "step": 12925, "train_runtime": 49781.8545, "train_tokens_per_second": 10698.414 }, { "epoch": 0.8705898195529221, "grad_norm": 0.6474981994268777, "learning_rate": 6.009917781838309e-06, "loss": 0.3758047342300415, "num_input_tokens_seen": 532793648, "step": 12930, "train_runtime": 49800.0566, "train_tokens_per_second": 10698.655 }, { "epoch": 0.8709264745488823, "grad_norm": 0.6542224171787283, "learning_rate": 6.007328056000873e-06, "loss": 0.376707649230957, "num_input_tokens_seen": 533002496, "step": 12935, "train_runtime": 49818.6197, "train_tokens_per_second": 10698.861 }, { "epoch": 0.8712631295448424, "grad_norm": 0.7352649914354925, "learning_rate": 6.004738048467359e-06, "loss": 0.3837728500366211, "num_input_tokens_seen": 533210080, "step": 12940, "train_runtime": 49838.9046, "train_tokens_per_second": 10698.672 }, { "epoch": 0.8715997845408026, "grad_norm": 0.7007695081903464, "learning_rate": 6.002147759962054e-06, "loss": 0.3717973232269287, "num_input_tokens_seen": 533417744, "step": 12945, "train_runtime": 49857.199, "train_tokens_per_second": 10698.911 }, { "epoch": 0.8719364395367627, "grad_norm": 0.7171605598329797, "learning_rate": 5.999557191209323e-06, "loss": 0.3862166166305542, "num_input_tokens_seen": 533632128, "step": 12950, "train_runtime": 49876.9188, "train_tokens_per_second": 10698.979 }, { "epoch": 0.8722730945327228, "grad_norm": 0.7541662598309695, "learning_rate": 5.996966342933611e-06, "loss": 0.3341783046722412, "num_input_tokens_seen": 533838392, "step": 12955, "train_runtime": 49895.8999, "train_tokens_per_second": 10699.043 }, { "epoch": 0.872609749528683, "grad_norm": 0.7066305814550065, "learning_rate": 5.99437521585944e-06, "loss": 0.37609362602233887, "num_input_tokens_seen": 534034696, "step": 12960, "train_runtime": 49914.0054, "train_tokens_per_second": 10699.095 }, { "epoch": 0.8729464045246431, "grad_norm": 0.7033752910710124, "learning_rate": 5.99178381071141e-06, "loss": 0.37670650482177737, "num_input_tokens_seen": 534241168, "step": 12965, "train_runtime": 49934.0525, "train_tokens_per_second": 10698.935 }, { "epoch": 0.8732830595206033, "grad_norm": 0.7005224779076822, "learning_rate": 5.989192128214201e-06, "loss": 0.36357181072235106, "num_input_tokens_seen": 534446432, "step": 12970, "train_runtime": 49953.9166, "train_tokens_per_second": 10698.789 }, { "epoch": 0.8736197145165634, "grad_norm": 0.726202912034422, "learning_rate": 5.986600169092568e-06, "loss": 0.3557180166244507, "num_input_tokens_seen": 534649760, "step": 12975, "train_runtime": 49972.6591, "train_tokens_per_second": 10698.846 }, { "epoch": 0.8739563695125235, "grad_norm": 0.6836294053875916, "learning_rate": 5.984007934071343e-06, "loss": 0.3790142059326172, "num_input_tokens_seen": 534867960, "step": 12980, "train_runtime": 49992.8582, "train_tokens_per_second": 10698.887 }, { "epoch": 0.8742930245084837, "grad_norm": 0.6992607614020233, "learning_rate": 5.981415423875436e-06, "loss": 0.37014334201812743, "num_input_tokens_seen": 535079528, "step": 12985, "train_runtime": 50012.331, "train_tokens_per_second": 10698.952 }, { "epoch": 0.8746296795044438, "grad_norm": 0.6905642230249951, "learning_rate": 5.978822639229836e-06, "loss": 0.3523120641708374, "num_input_tokens_seen": 535270712, "step": 12990, "train_runtime": 50030.2082, "train_tokens_per_second": 10698.95 }, { "epoch": 0.874966334500404, "grad_norm": 0.6636560012582197, "learning_rate": 5.976229580859607e-06, "loss": 0.35713777542114256, "num_input_tokens_seen": 535483088, "step": 12995, "train_runtime": 50048.5469, "train_tokens_per_second": 10699.273 }, { "epoch": 0.8753029894963641, "grad_norm": 0.6563793629765322, "learning_rate": 5.9736362494898895e-06, "loss": 0.35345323085784913, "num_input_tokens_seen": 535688336, "step": 13000, "train_runtime": 50067.537, "train_tokens_per_second": 10699.315 }, { "epoch": 0.8756396444923242, "grad_norm": 0.6225307015393045, "learning_rate": 5.971042645845897e-06, "loss": 0.3743724822998047, "num_input_tokens_seen": 535892456, "step": 13005, "train_runtime": 50088.3217, "train_tokens_per_second": 10698.95 }, { "epoch": 0.8759762994882844, "grad_norm": 0.6659653852967942, "learning_rate": 5.968448770652926e-06, "loss": 0.3599968910217285, "num_input_tokens_seen": 536109864, "step": 13010, "train_runtime": 50105.9011, "train_tokens_per_second": 10699.535 }, { "epoch": 0.8763129544842445, "grad_norm": 0.6871675137658788, "learning_rate": 5.965854624636345e-06, "loss": 0.390108060836792, "num_input_tokens_seen": 536311104, "step": 13015, "train_runtime": 50124.3615, "train_tokens_per_second": 10699.61 }, { "epoch": 0.8766496094802047, "grad_norm": 0.6488041728159807, "learning_rate": 5.963260208521598e-06, "loss": 0.3690535545349121, "num_input_tokens_seen": 536511584, "step": 13020, "train_runtime": 50143.7722, "train_tokens_per_second": 10699.466 }, { "epoch": 0.8769862644761648, "grad_norm": 0.6351652177691797, "learning_rate": 5.960665523034205e-06, "loss": 0.3840355396270752, "num_input_tokens_seen": 536709192, "step": 13025, "train_runtime": 50163.1266, "train_tokens_per_second": 10699.277 }, { "epoch": 0.8773229194721249, "grad_norm": 0.7341663845750046, "learning_rate": 5.958070568899762e-06, "loss": 0.343523645401001, "num_input_tokens_seen": 536920080, "step": 13030, "train_runtime": 50182.9563, "train_tokens_per_second": 10699.252 }, { "epoch": 0.8776595744680851, "grad_norm": 0.6731231881063092, "learning_rate": 5.955475346843939e-06, "loss": 0.3594912052154541, "num_input_tokens_seen": 537119568, "step": 13035, "train_runtime": 50201.3323, "train_tokens_per_second": 10699.309 }, { "epoch": 0.8779962294640452, "grad_norm": 0.7155944271161926, "learning_rate": 5.952879857592482e-06, "loss": 0.3449664354324341, "num_input_tokens_seen": 537321144, "step": 13040, "train_runtime": 50220.9523, "train_tokens_per_second": 10699.143 }, { "epoch": 0.8783328844600053, "grad_norm": 0.6824032435638313, "learning_rate": 5.950284101871212e-06, "loss": 0.3917157888412476, "num_input_tokens_seen": 537517944, "step": 13045, "train_runtime": 50240.3227, "train_tokens_per_second": 10698.935 }, { "epoch": 0.8786695394559655, "grad_norm": 0.717505568847202, "learning_rate": 5.947688080406023e-06, "loss": 0.3470283031463623, "num_input_tokens_seen": 537710456, "step": 13050, "train_runtime": 50258.9041, "train_tokens_per_second": 10698.81 }, { "epoch": 0.8790061944519256, "grad_norm": 0.7446737412052197, "learning_rate": 5.945091793922885e-06, "loss": 0.36561629772186277, "num_input_tokens_seen": 537914552, "step": 13055, "train_runtime": 50277.2501, "train_tokens_per_second": 10698.965 }, { "epoch": 0.8793428494478858, "grad_norm": 0.6833327422722928, "learning_rate": 5.942495243147839e-06, "loss": 0.3965196371078491, "num_input_tokens_seen": 538121024, "step": 13060, "train_runtime": 50295.1983, "train_tokens_per_second": 10699.252 }, { "epoch": 0.8796795044438459, "grad_norm": 0.6575328096229237, "learning_rate": 5.939898428807004e-06, "loss": 0.37971744537353513, "num_input_tokens_seen": 538323144, "step": 13065, "train_runtime": 50313.5326, "train_tokens_per_second": 10699.371 }, { "epoch": 0.880016159439806, "grad_norm": 0.7754154894747539, "learning_rate": 5.937301351626571e-06, "loss": 0.376740550994873, "num_input_tokens_seen": 538523272, "step": 13070, "train_runtime": 50333.4425, "train_tokens_per_second": 10699.115 }, { "epoch": 0.8803528144357662, "grad_norm": 0.7135068114495426, "learning_rate": 5.934704012332803e-06, "loss": 0.3585189342498779, "num_input_tokens_seen": 538737216, "step": 13075, "train_runtime": 50352.1416, "train_tokens_per_second": 10699.39 }, { "epoch": 0.8806894694317263, "grad_norm": 0.725590928976916, "learning_rate": 5.93210641165204e-06, "loss": 0.407816219329834, "num_input_tokens_seen": 538948056, "step": 13080, "train_runtime": 50372.9225, "train_tokens_per_second": 10699.162 }, { "epoch": 0.8810261244276865, "grad_norm": 0.7480030389480915, "learning_rate": 5.92950855031069e-06, "loss": 0.37763028144836425, "num_input_tokens_seen": 539154272, "step": 13085, "train_runtime": 50392.2424, "train_tokens_per_second": 10699.152 }, { "epoch": 0.8813627794236466, "grad_norm": 0.7575916322149756, "learning_rate": 5.926910429035239e-06, "loss": 0.36137900352478025, "num_input_tokens_seen": 539354880, "step": 13090, "train_runtime": 50411.0204, "train_tokens_per_second": 10699.146 }, { "epoch": 0.8816994344196067, "grad_norm": 0.6617834799851123, "learning_rate": 5.924312048552241e-06, "loss": 0.35442471504211426, "num_input_tokens_seen": 539565544, "step": 13095, "train_runtime": 50429.9203, "train_tokens_per_second": 10699.314 }, { "epoch": 0.8820360894155669, "grad_norm": 0.6874098646475308, "learning_rate": 5.9217134095883265e-06, "loss": 0.36498236656188965, "num_input_tokens_seen": 539773080, "step": 13100, "train_runtime": 50448.8257, "train_tokens_per_second": 10699.418 }, { "epoch": 0.882372744411527, "grad_norm": 0.6976064938216835, "learning_rate": 5.919114512870197e-06, "loss": 0.3593911170959473, "num_input_tokens_seen": 539988272, "step": 13105, "train_runtime": 50467.2762, "train_tokens_per_second": 10699.77 }, { "epoch": 0.8827093994074872, "grad_norm": 0.701321088169654, "learning_rate": 5.916515359124623e-06, "loss": 0.3424126863479614, "num_input_tokens_seen": 540180240, "step": 13110, "train_runtime": 50487.5065, "train_tokens_per_second": 10699.285 }, { "epoch": 0.8830460544034473, "grad_norm": 0.6962172518886601, "learning_rate": 5.913915949078453e-06, "loss": 0.37134251594543455, "num_input_tokens_seen": 540387632, "step": 13115, "train_runtime": 50508.1984, "train_tokens_per_second": 10699.008 }, { "epoch": 0.8833827093994074, "grad_norm": 0.714124010645318, "learning_rate": 5.911316283458601e-06, "loss": 0.36361403465270997, "num_input_tokens_seen": 540584392, "step": 13120, "train_runtime": 50527.0247, "train_tokens_per_second": 10698.916 }, { "epoch": 0.8837193643953676, "grad_norm": 0.7052226334994002, "learning_rate": 5.908716362992057e-06, "loss": 0.37182960510253904, "num_input_tokens_seen": 540781336, "step": 13125, "train_runtime": 50546.675, "train_tokens_per_second": 10698.653 }, { "epoch": 0.8840560193913277, "grad_norm": 0.6622741284326019, "learning_rate": 5.90611618840588e-06, "loss": 0.38386218547821044, "num_input_tokens_seen": 540987592, "step": 13130, "train_runtime": 50565.8427, "train_tokens_per_second": 10698.676 }, { "epoch": 0.8843926743872879, "grad_norm": 0.7015712127943756, "learning_rate": 5.903515760427198e-06, "loss": 0.40595340728759766, "num_input_tokens_seen": 541192848, "step": 13135, "train_runtime": 50584.384, "train_tokens_per_second": 10698.813 }, { "epoch": 0.884729329383248, "grad_norm": 0.7197941532409395, "learning_rate": 5.900915079783218e-06, "loss": 0.3610012292861938, "num_input_tokens_seen": 541409664, "step": 13140, "train_runtime": 50602.4402, "train_tokens_per_second": 10699.28 }, { "epoch": 0.8850659843792081, "grad_norm": 0.6812096423463414, "learning_rate": 5.898314147201207e-06, "loss": 0.34230771064758303, "num_input_tokens_seen": 541611048, "step": 13145, "train_runtime": 50619.8073, "train_tokens_per_second": 10699.587 }, { "epoch": 0.8854026393751683, "grad_norm": 0.6985723398358197, "learning_rate": 5.895712963408511e-06, "loss": 0.3933114051818848, "num_input_tokens_seen": 541809016, "step": 13150, "train_runtime": 50640.1853, "train_tokens_per_second": 10699.191 }, { "epoch": 0.8857392943711284, "grad_norm": 0.6833023760460037, "learning_rate": 5.893111529132539e-06, "loss": 0.382668662071228, "num_input_tokens_seen": 542007344, "step": 13155, "train_runtime": 50659.7403, "train_tokens_per_second": 10698.976 }, { "epoch": 0.8860759493670886, "grad_norm": 0.7096457204520304, "learning_rate": 5.8905098451007755e-06, "loss": 0.3802436113357544, "num_input_tokens_seen": 542201552, "step": 13160, "train_runtime": 50679.1498, "train_tokens_per_second": 10698.71 }, { "epoch": 0.8864126043630487, "grad_norm": 0.6676698798104661, "learning_rate": 5.887907912040774e-06, "loss": 0.3773787021636963, "num_input_tokens_seen": 542409744, "step": 13165, "train_runtime": 50696.6913, "train_tokens_per_second": 10699.115 }, { "epoch": 0.8867492593590088, "grad_norm": 0.8732068309313328, "learning_rate": 5.885305730680158e-06, "loss": 0.3780364513397217, "num_input_tokens_seen": 542622064, "step": 13170, "train_runtime": 50715.2305, "train_tokens_per_second": 10699.391 }, { "epoch": 0.887085914354969, "grad_norm": 0.7298651138543955, "learning_rate": 5.882703301746616e-06, "loss": 0.36997165679931643, "num_input_tokens_seen": 542825592, "step": 13175, "train_runtime": 50734.9048, "train_tokens_per_second": 10699.253 }, { "epoch": 0.8874225693509291, "grad_norm": 0.6766176763229231, "learning_rate": 5.88010062596791e-06, "loss": 0.3624583721160889, "num_input_tokens_seen": 543024248, "step": 13180, "train_runtime": 50754.8367, "train_tokens_per_second": 10698.966 }, { "epoch": 0.8877592243468893, "grad_norm": 0.5982212553197453, "learning_rate": 5.877497704071871e-06, "loss": 0.35221333503723146, "num_input_tokens_seen": 543241168, "step": 13185, "train_runtime": 50772.2703, "train_tokens_per_second": 10699.564 }, { "epoch": 0.8880958793428494, "grad_norm": 0.7192270635851605, "learning_rate": 5.874894536786396e-06, "loss": 0.32763283252716063, "num_input_tokens_seen": 543442136, "step": 13190, "train_runtime": 50790.0797, "train_tokens_per_second": 10699.769 }, { "epoch": 0.8884325343388096, "grad_norm": 0.6632970325589949, "learning_rate": 5.8722911248394555e-06, "loss": 0.345784592628479, "num_input_tokens_seen": 543629688, "step": 13195, "train_runtime": 50808.5135, "train_tokens_per_second": 10699.579 }, { "epoch": 0.8887691893347698, "grad_norm": 0.7217024002732054, "learning_rate": 5.8696874689590824e-06, "loss": 0.342358922958374, "num_input_tokens_seen": 543827352, "step": 13200, "train_runtime": 50826.6933, "train_tokens_per_second": 10699.641 }, { "epoch": 0.8891058443307299, "grad_norm": 0.7531985309629617, "learning_rate": 5.867083569873383e-06, "loss": 0.36597380638122556, "num_input_tokens_seen": 544037792, "step": 13205, "train_runtime": 50845.564, "train_tokens_per_second": 10699.808 }, { "epoch": 0.8894424993266901, "grad_norm": 0.7270542357770424, "learning_rate": 5.8644794283105255e-06, "loss": 0.37141172885894774, "num_input_tokens_seen": 544244816, "step": 13210, "train_runtime": 50864.8558, "train_tokens_per_second": 10699.82 }, { "epoch": 0.8897791543226502, "grad_norm": 0.7209665522820762, "learning_rate": 5.861875044998755e-06, "loss": 0.3984645128250122, "num_input_tokens_seen": 544453808, "step": 13215, "train_runtime": 50882.5795, "train_tokens_per_second": 10700.201 }, { "epoch": 0.8901158093186103, "grad_norm": 0.8512421636614868, "learning_rate": 5.859270420666377e-06, "loss": 0.3690722703933716, "num_input_tokens_seen": 544659136, "step": 13220, "train_runtime": 50900.7793, "train_tokens_per_second": 10700.409 }, { "epoch": 0.8904524643145705, "grad_norm": 0.7074241231979705, "learning_rate": 5.856665556041764e-06, "loss": 0.3461319923400879, "num_input_tokens_seen": 544853192, "step": 13225, "train_runtime": 50919.498, "train_tokens_per_second": 10700.286 }, { "epoch": 0.8907891193105306, "grad_norm": 0.6808004048766503, "learning_rate": 5.8540604518533605e-06, "loss": 0.3866400718688965, "num_input_tokens_seen": 545063512, "step": 13230, "train_runtime": 50938.141, "train_tokens_per_second": 10700.499 }, { "epoch": 0.8911257743064908, "grad_norm": 0.7271644562715439, "learning_rate": 5.851455108829675e-06, "loss": 0.3593264102935791, "num_input_tokens_seen": 545261560, "step": 13235, "train_runtime": 50956.6615, "train_tokens_per_second": 10700.496 }, { "epoch": 0.8914624293024509, "grad_norm": 0.6388145031427295, "learning_rate": 5.848849527699283e-06, "loss": 0.37213473320007323, "num_input_tokens_seen": 545467920, "step": 13240, "train_runtime": 50974.2111, "train_tokens_per_second": 10700.86 }, { "epoch": 0.891799084298411, "grad_norm": 0.7280819646658453, "learning_rate": 5.846243709190827e-06, "loss": 0.351688551902771, "num_input_tokens_seen": 545673232, "step": 13245, "train_runtime": 50993.3216, "train_tokens_per_second": 10700.876 }, { "epoch": 0.8921357392943712, "grad_norm": 0.8330519254468578, "learning_rate": 5.843637654033019e-06, "loss": 0.3782889604568481, "num_input_tokens_seen": 545866008, "step": 13250, "train_runtime": 51012.0981, "train_tokens_per_second": 10700.717 }, { "epoch": 0.8924723942903313, "grad_norm": 0.6311606844242629, "learning_rate": 5.841031362954629e-06, "loss": 0.3948682308197021, "num_input_tokens_seen": 546078936, "step": 13255, "train_runtime": 51031.55, "train_tokens_per_second": 10700.81 }, { "epoch": 0.8928090492862915, "grad_norm": 0.6476816336495734, "learning_rate": 5.8384248366845e-06, "loss": 0.37016143798828127, "num_input_tokens_seen": 546292672, "step": 13260, "train_runtime": 51050.9342, "train_tokens_per_second": 10700.934 }, { "epoch": 0.8931457042822516, "grad_norm": 0.659754832545341, "learning_rate": 5.8358180759515396e-06, "loss": 0.37449007034301757, "num_input_tokens_seen": 546492256, "step": 13265, "train_runtime": 51070.4732, "train_tokens_per_second": 10700.748 }, { "epoch": 0.8934823592782117, "grad_norm": 0.7144859179599773, "learning_rate": 5.833211081484719e-06, "loss": 0.374530029296875, "num_input_tokens_seen": 546697704, "step": 13270, "train_runtime": 51090.1785, "train_tokens_per_second": 10700.642 }, { "epoch": 0.8938190142741719, "grad_norm": 0.6159144487564961, "learning_rate": 5.830603854013077e-06, "loss": 0.3742021083831787, "num_input_tokens_seen": 546902296, "step": 13275, "train_runtime": 51108.5824, "train_tokens_per_second": 10700.792 }, { "epoch": 0.894155669270132, "grad_norm": 0.7875442389923938, "learning_rate": 5.827996394265716e-06, "loss": 0.35219035148620603, "num_input_tokens_seen": 547101576, "step": 13280, "train_runtime": 51127.0983, "train_tokens_per_second": 10700.814 }, { "epoch": 0.8944923242660922, "grad_norm": 0.7113564149469422, "learning_rate": 5.825388702971802e-06, "loss": 0.3502956867218018, "num_input_tokens_seen": 547304456, "step": 13285, "train_runtime": 51144.9678, "train_tokens_per_second": 10701.042 }, { "epoch": 0.8948289792620523, "grad_norm": 0.7463143015373354, "learning_rate": 5.822780780860571e-06, "loss": 0.36437559127807617, "num_input_tokens_seen": 547508616, "step": 13290, "train_runtime": 51163.3761, "train_tokens_per_second": 10701.182 }, { "epoch": 0.8951656342580124, "grad_norm": 0.6773887354990855, "learning_rate": 5.820172628661317e-06, "loss": 0.37190680503845214, "num_input_tokens_seen": 547726856, "step": 13295, "train_runtime": 51181.1489, "train_tokens_per_second": 10701.73 }, { "epoch": 0.8955022892539726, "grad_norm": 0.692328505919783, "learning_rate": 5.8175642471034045e-06, "loss": 0.35528714656829835, "num_input_tokens_seen": 547932896, "step": 13300, "train_runtime": 51199.7761, "train_tokens_per_second": 10701.861 }, { "epoch": 0.8958389442499327, "grad_norm": 0.7214904105913675, "learning_rate": 5.8149556369162565e-06, "loss": 0.3813814878463745, "num_input_tokens_seen": 548129976, "step": 13305, "train_runtime": 51218.5105, "train_tokens_per_second": 10701.795 }, { "epoch": 0.8961755992458929, "grad_norm": 0.7325467891189638, "learning_rate": 5.812346798829361e-06, "loss": 0.37437877655029295, "num_input_tokens_seen": 548340768, "step": 13310, "train_runtime": 51235.9043, "train_tokens_per_second": 10702.276 }, { "epoch": 0.896512254241853, "grad_norm": 0.7272538350527779, "learning_rate": 5.809737733572276e-06, "loss": 0.35332503318786623, "num_input_tokens_seen": 548542712, "step": 13315, "train_runtime": 51256.4053, "train_tokens_per_second": 10701.935 }, { "epoch": 0.8968489092378131, "grad_norm": 0.7428121173904934, "learning_rate": 5.8071284418746166e-06, "loss": 0.3599346160888672, "num_input_tokens_seen": 548749184, "step": 13320, "train_runtime": 51275.777, "train_tokens_per_second": 10701.918 }, { "epoch": 0.8971855642337733, "grad_norm": 0.6716127391311408, "learning_rate": 5.80451892446606e-06, "loss": 0.3891899824142456, "num_input_tokens_seen": 548963848, "step": 13325, "train_runtime": 51296.1529, "train_tokens_per_second": 10701.852 }, { "epoch": 0.8975222192297334, "grad_norm": 0.6709493011152701, "learning_rate": 5.801909182076354e-06, "loss": 0.36298828125, "num_input_tokens_seen": 549173424, "step": 13330, "train_runtime": 51313.9152, "train_tokens_per_second": 10702.232 }, { "epoch": 0.8978588742256935, "grad_norm": 0.7260759538495241, "learning_rate": 5.7992992154353e-06, "loss": 0.3973310232162476, "num_input_tokens_seen": 549377728, "step": 13335, "train_runtime": 51333.2444, "train_tokens_per_second": 10702.182 }, { "epoch": 0.8981955292216537, "grad_norm": 0.6932874691386127, "learning_rate": 5.79668902527277e-06, "loss": 0.37354192733764646, "num_input_tokens_seen": 549579864, "step": 13340, "train_runtime": 51351.6664, "train_tokens_per_second": 10702.279 }, { "epoch": 0.8985321842176138, "grad_norm": 0.6590113885519947, "learning_rate": 5.794078612318695e-06, "loss": 0.3626625776290894, "num_input_tokens_seen": 549785736, "step": 13345, "train_runtime": 51371.2497, "train_tokens_per_second": 10702.207 }, { "epoch": 0.898868839213574, "grad_norm": 0.6587170032934831, "learning_rate": 5.791467977303068e-06, "loss": 0.3654374837875366, "num_input_tokens_seen": 549985392, "step": 13350, "train_runtime": 51390.4908, "train_tokens_per_second": 10702.085 }, { "epoch": 0.8992054942095341, "grad_norm": 0.8836406332114383, "learning_rate": 5.788857120955945e-06, "loss": 0.3838632345199585, "num_input_tokens_seen": 550187720, "step": 13355, "train_runtime": 51409.2872, "train_tokens_per_second": 10702.108 }, { "epoch": 0.8995421492054942, "grad_norm": 0.7191131300617981, "learning_rate": 5.786246044007443e-06, "loss": 0.34202792644500735, "num_input_tokens_seen": 550385576, "step": 13360, "train_runtime": 51428.6957, "train_tokens_per_second": 10701.916 }, { "epoch": 0.8998788042014544, "grad_norm": 0.6711174333433715, "learning_rate": 5.783634747187743e-06, "loss": 0.37988643646240233, "num_input_tokens_seen": 550597600, "step": 13365, "train_runtime": 51447.317, "train_tokens_per_second": 10702.164 }, { "epoch": 0.9002154591974145, "grad_norm": 0.7045061630846264, "learning_rate": 5.781023231227084e-06, "loss": 0.36345126628875735, "num_input_tokens_seen": 550802672, "step": 13370, "train_runtime": 51467.826, "train_tokens_per_second": 10701.883 }, { "epoch": 0.9005521141933747, "grad_norm": 0.6676181832062615, "learning_rate": 5.778411496855769e-06, "loss": 0.38044047355651855, "num_input_tokens_seen": 551011168, "step": 13375, "train_runtime": 51486.735, "train_tokens_per_second": 10702.003 }, { "epoch": 0.9008887691893348, "grad_norm": 0.7715560162360963, "learning_rate": 5.775799544804161e-06, "loss": 0.3893284797668457, "num_input_tokens_seen": 551222712, "step": 13380, "train_runtime": 51504.9236, "train_tokens_per_second": 10702.33 }, { "epoch": 0.9012254241852949, "grad_norm": 0.7196396722681263, "learning_rate": 5.7731873758026845e-06, "loss": 0.3603400468826294, "num_input_tokens_seen": 551426344, "step": 13385, "train_runtime": 51523.0514, "train_tokens_per_second": 10702.517 }, { "epoch": 0.9015620791812551, "grad_norm": 0.7669923147594067, "learning_rate": 5.770574990581823e-06, "loss": 0.36920695304870604, "num_input_tokens_seen": 551631104, "step": 13390, "train_runtime": 51543.3516, "train_tokens_per_second": 10702.275 }, { "epoch": 0.9018987341772152, "grad_norm": 0.7068754656526897, "learning_rate": 5.767962389872124e-06, "loss": 0.3456581592559814, "num_input_tokens_seen": 551834544, "step": 13395, "train_runtime": 51561.6285, "train_tokens_per_second": 10702.427 }, { "epoch": 0.9022353891731754, "grad_norm": 0.7615061572759875, "learning_rate": 5.765349574404191e-06, "loss": 0.35583181381225587, "num_input_tokens_seen": 552026592, "step": 13400, "train_runtime": 51580.3162, "train_tokens_per_second": 10702.272 }, { "epoch": 0.9025720441691355, "grad_norm": 0.6615853197838276, "learning_rate": 5.7627365449086905e-06, "loss": 0.36869709491729735, "num_input_tokens_seen": 552210800, "step": 13405, "train_runtime": 51598.8298, "train_tokens_per_second": 10702.002 }, { "epoch": 0.9029086991650956, "grad_norm": 0.8331024019987008, "learning_rate": 5.760123302116345e-06, "loss": 0.3905704736709595, "num_input_tokens_seen": 552419152, "step": 13410, "train_runtime": 51616.9941, "train_tokens_per_second": 10702.273 }, { "epoch": 0.9032453541610558, "grad_norm": 0.8556994889265418, "learning_rate": 5.757509846757945e-06, "loss": 0.37052044868469236, "num_input_tokens_seen": 552630664, "step": 13415, "train_runtime": 51637.4026, "train_tokens_per_second": 10702.139 }, { "epoch": 0.9035820091570159, "grad_norm": 0.7851392865998919, "learning_rate": 5.75489617956433e-06, "loss": 0.39432764053344727, "num_input_tokens_seen": 552842400, "step": 13420, "train_runtime": 51657.9876, "train_tokens_per_second": 10701.973 }, { "epoch": 0.9039186641529761, "grad_norm": 0.7145288454303671, "learning_rate": 5.752282301266406e-06, "loss": 0.3746475696563721, "num_input_tokens_seen": 553048136, "step": 13425, "train_runtime": 51676.6315, "train_tokens_per_second": 10702.093 }, { "epoch": 0.9042553191489362, "grad_norm": 0.6402347495625352, "learning_rate": 5.749668212595136e-06, "loss": 0.3752699375152588, "num_input_tokens_seen": 553250664, "step": 13430, "train_runtime": 51695.7111, "train_tokens_per_second": 10702.061 }, { "epoch": 0.9045919741448963, "grad_norm": 0.6928634569931182, "learning_rate": 5.747053914281539e-06, "loss": 0.3646227836608887, "num_input_tokens_seen": 553446016, "step": 13435, "train_runtime": 51717.614, "train_tokens_per_second": 10701.306 }, { "epoch": 0.9049286291408565, "grad_norm": 0.6501130142762525, "learning_rate": 5.744439407056699e-06, "loss": 0.35020761489868163, "num_input_tokens_seen": 553644768, "step": 13440, "train_runtime": 51737.217, "train_tokens_per_second": 10701.093 }, { "epoch": 0.9052652841368166, "grad_norm": 0.6013964162283547, "learning_rate": 5.741824691651752e-06, "loss": 0.3415040969848633, "num_input_tokens_seen": 553855176, "step": 13445, "train_runtime": 51756.4029, "train_tokens_per_second": 10701.191 }, { "epoch": 0.9056019391327768, "grad_norm": 0.7818820807779303, "learning_rate": 5.739209768797896e-06, "loss": 0.3651643037796021, "num_input_tokens_seen": 554049592, "step": 13450, "train_runtime": 51774.9329, "train_tokens_per_second": 10701.117 }, { "epoch": 0.9059385941287369, "grad_norm": 0.6919750221166108, "learning_rate": 5.736594639226385e-06, "loss": 0.3261881828308105, "num_input_tokens_seen": 554255720, "step": 13455, "train_runtime": 51793.7593, "train_tokens_per_second": 10701.207 }, { "epoch": 0.906275249124697, "grad_norm": 0.6735942346744003, "learning_rate": 5.7339793036685306e-06, "loss": 0.3801831483840942, "num_input_tokens_seen": 554466464, "step": 13460, "train_runtime": 51812.647, "train_tokens_per_second": 10701.373 }, { "epoch": 0.9066119041206572, "grad_norm": 0.6867240826084754, "learning_rate": 5.731363762855706e-06, "loss": 0.35399580001831055, "num_input_tokens_seen": 554670328, "step": 13465, "train_runtime": 51833.521, "train_tokens_per_second": 10700.997 }, { "epoch": 0.9069485591166173, "grad_norm": 0.7171053077380871, "learning_rate": 5.728748017519337e-06, "loss": 0.40008015632629396, "num_input_tokens_seen": 554874136, "step": 13470, "train_runtime": 51853.4205, "train_tokens_per_second": 10700.82 }, { "epoch": 0.9072852141125775, "grad_norm": 0.6854150966295857, "learning_rate": 5.726132068390908e-06, "loss": 0.3705361604690552, "num_input_tokens_seen": 555066688, "step": 13475, "train_runtime": 51870.7861, "train_tokens_per_second": 10700.95 }, { "epoch": 0.9076218691085376, "grad_norm": 0.7648729509030979, "learning_rate": 5.723515916201962e-06, "loss": 0.4150794506072998, "num_input_tokens_seen": 555278528, "step": 13480, "train_runtime": 51889.3485, "train_tokens_per_second": 10701.204 }, { "epoch": 0.9079585241044977, "grad_norm": 0.9239702001617126, "learning_rate": 5.720899561684098e-06, "loss": 0.3481105327606201, "num_input_tokens_seen": 555484992, "step": 13485, "train_runtime": 51909.9209, "train_tokens_per_second": 10700.941 }, { "epoch": 0.9082951791004579, "grad_norm": 0.688013409192298, "learning_rate": 5.71828300556897e-06, "loss": 0.36736891269683836, "num_input_tokens_seen": 555697536, "step": 13490, "train_runtime": 51929.4014, "train_tokens_per_second": 10701.019 }, { "epoch": 0.908631834096418, "grad_norm": 0.5862341921357821, "learning_rate": 5.715666248588289e-06, "loss": 0.3684476375579834, "num_input_tokens_seen": 555908920, "step": 13495, "train_runtime": 51949.4402, "train_tokens_per_second": 10700.961 }, { "epoch": 0.9089684890923782, "grad_norm": 0.8236619111231086, "learning_rate": 5.713049291473825e-06, "loss": 0.39096343517303467, "num_input_tokens_seen": 556123680, "step": 13500, "train_runtime": 51970.1666, "train_tokens_per_second": 10700.825 }, { "epoch": 0.9093051440883383, "grad_norm": 0.7389432816052867, "learning_rate": 5.710432134957399e-06, "loss": 0.34229001998901365, "num_input_tokens_seen": 556316568, "step": 13505, "train_runtime": 51989.8794, "train_tokens_per_second": 10700.478 }, { "epoch": 0.9096417990842984, "grad_norm": 0.8353053800325811, "learning_rate": 5.707814779770892e-06, "loss": 0.3408064365386963, "num_input_tokens_seen": 556517760, "step": 13510, "train_runtime": 52010.8243, "train_tokens_per_second": 10700.037 }, { "epoch": 0.9099784540802586, "grad_norm": 0.6988147084206549, "learning_rate": 5.7051972266462395e-06, "loss": 0.35260586738586425, "num_input_tokens_seen": 556721768, "step": 13515, "train_runtime": 52029.5944, "train_tokens_per_second": 10700.098 }, { "epoch": 0.9103151090762187, "grad_norm": 0.7516909072955109, "learning_rate": 5.702579476315431e-06, "loss": 0.32787466049194336, "num_input_tokens_seen": 556927840, "step": 13520, "train_runtime": 52047.8961, "train_tokens_per_second": 10700.295 }, { "epoch": 0.9106517640721788, "grad_norm": 0.7249273188374985, "learning_rate": 5.699961529510513e-06, "loss": 0.3575684309005737, "num_input_tokens_seen": 557122096, "step": 13525, "train_runtime": 52065.9537, "train_tokens_per_second": 10700.315 }, { "epoch": 0.910988419068139, "grad_norm": 0.7140321015585325, "learning_rate": 5.697343386963586e-06, "loss": 0.3762962341308594, "num_input_tokens_seen": 557327104, "step": 13530, "train_runtime": 52086.8914, "train_tokens_per_second": 10699.949 }, { "epoch": 0.9113250740640991, "grad_norm": 0.630059170515717, "learning_rate": 5.694725049406801e-06, "loss": 0.3742865562438965, "num_input_tokens_seen": 557532976, "step": 13535, "train_runtime": 52106.8906, "train_tokens_per_second": 10699.794 }, { "epoch": 0.9116617290600593, "grad_norm": 0.6232523548130551, "learning_rate": 5.692106517572373e-06, "loss": 0.38649301528930663, "num_input_tokens_seen": 557733632, "step": 13540, "train_runtime": 52124.8833, "train_tokens_per_second": 10699.95 }, { "epoch": 0.9119983840560194, "grad_norm": 0.7249976871890809, "learning_rate": 5.689487792192566e-06, "loss": 0.39646477699279786, "num_input_tokens_seen": 557943400, "step": 13545, "train_runtime": 52144.7717, "train_tokens_per_second": 10699.892 }, { "epoch": 0.9123350390519795, "grad_norm": 0.7443972712457353, "learning_rate": 5.686868873999696e-06, "loss": 0.38536021709442136, "num_input_tokens_seen": 558150088, "step": 13550, "train_runtime": 52164.3445, "train_tokens_per_second": 10699.839 }, { "epoch": 0.9126716940479397, "grad_norm": 0.6585042634944274, "learning_rate": 5.684249763726135e-06, "loss": 0.3764821529388428, "num_input_tokens_seen": 558356936, "step": 13555, "train_runtime": 52184.2686, "train_tokens_per_second": 10699.718 }, { "epoch": 0.9130083490438998, "grad_norm": 0.724981326825258, "learning_rate": 5.681630462104308e-06, "loss": 0.35632915496826173, "num_input_tokens_seen": 558549104, "step": 13560, "train_runtime": 52202.5689, "train_tokens_per_second": 10699.648 }, { "epoch": 0.91334500403986, "grad_norm": 0.9428923099340413, "learning_rate": 5.679010969866697e-06, "loss": 0.36115260124206544, "num_input_tokens_seen": 558748624, "step": 13565, "train_runtime": 52221.1326, "train_tokens_per_second": 10699.665 }, { "epoch": 0.9136816590358201, "grad_norm": 0.7023284174607888, "learning_rate": 5.676391287745835e-06, "loss": 0.35560431480407717, "num_input_tokens_seen": 558964632, "step": 13570, "train_runtime": 52238.9637, "train_tokens_per_second": 10700.148 }, { "epoch": 0.9140183140317802, "grad_norm": 0.6466742567634802, "learning_rate": 5.673771416474305e-06, "loss": 0.347554087638855, "num_input_tokens_seen": 559174688, "step": 13575, "train_runtime": 52258.754, "train_tokens_per_second": 10700.115 }, { "epoch": 0.9143549690277404, "grad_norm": 0.7414460554469915, "learning_rate": 5.671151356784747e-06, "loss": 0.34471354484558103, "num_input_tokens_seen": 559372672, "step": 13580, "train_runtime": 52278.5989, "train_tokens_per_second": 10699.841 }, { "epoch": 0.9146916240237005, "grad_norm": 0.655090256768152, "learning_rate": 5.668531109409851e-06, "loss": 0.375110387802124, "num_input_tokens_seen": 559580016, "step": 13585, "train_runtime": 52296.9992, "train_tokens_per_second": 10700.041 }, { "epoch": 0.9150282790196607, "grad_norm": 0.7212215029920681, "learning_rate": 5.665910675082362e-06, "loss": 0.3599992752075195, "num_input_tokens_seen": 559784160, "step": 13590, "train_runtime": 52316.545, "train_tokens_per_second": 10699.945 }, { "epoch": 0.9153649340156208, "grad_norm": 0.7022792957086813, "learning_rate": 5.663290054535078e-06, "loss": 0.3505870342254639, "num_input_tokens_seen": 559983040, "step": 13595, "train_runtime": 52334.8763, "train_tokens_per_second": 10699.997 }, { "epoch": 0.9157015890115809, "grad_norm": 0.8186155717619822, "learning_rate": 5.660669248500846e-06, "loss": 0.40430397987365724, "num_input_tokens_seen": 560187704, "step": 13600, "train_runtime": 52354.7079, "train_tokens_per_second": 10699.853 }, { "epoch": 0.9160382440075411, "grad_norm": 0.7217749629319539, "learning_rate": 5.658048257712563e-06, "loss": 0.35095720291137694, "num_input_tokens_seen": 560398128, "step": 13605, "train_runtime": 52374.0105, "train_tokens_per_second": 10699.928 }, { "epoch": 0.9163748990035012, "grad_norm": 0.668170319015275, "learning_rate": 5.655427082903184e-06, "loss": 0.3637503147125244, "num_input_tokens_seen": 560604672, "step": 13610, "train_runtime": 52393.4914, "train_tokens_per_second": 10699.891 }, { "epoch": 0.9167115539994614, "grad_norm": 0.6846670413751942, "learning_rate": 5.652805724805711e-06, "loss": 0.3560380458831787, "num_input_tokens_seen": 560811992, "step": 13615, "train_runtime": 52413.4725, "train_tokens_per_second": 10699.768 }, { "epoch": 0.9170482089954215, "grad_norm": 0.7510431572067289, "learning_rate": 5.650184184153199e-06, "loss": 0.37002508640289306, "num_input_tokens_seen": 561023776, "step": 13620, "train_runtime": 52433.6841, "train_tokens_per_second": 10699.683 }, { "epoch": 0.9173848639913816, "grad_norm": 0.6823853931068349, "learning_rate": 5.647562461678754e-06, "loss": 0.39197607040405275, "num_input_tokens_seen": 561234536, "step": 13625, "train_runtime": 52452.4617, "train_tokens_per_second": 10699.87 }, { "epoch": 0.9177215189873418, "grad_norm": 0.7327071448491544, "learning_rate": 5.64494055811553e-06, "loss": 0.35401763916015627, "num_input_tokens_seen": 561442472, "step": 13630, "train_runtime": 52472.7837, "train_tokens_per_second": 10699.689 }, { "epoch": 0.9180581739833019, "grad_norm": 0.677116522556283, "learning_rate": 5.642318474196737e-06, "loss": 0.35039684772491453, "num_input_tokens_seen": 561651344, "step": 13635, "train_runtime": 52492.3838, "train_tokens_per_second": 10699.673 }, { "epoch": 0.9183948289792621, "grad_norm": 0.7094623475198506, "learning_rate": 5.63969621065563e-06, "loss": 0.3618741989135742, "num_input_tokens_seen": 561853912, "step": 13640, "train_runtime": 52511.8484, "train_tokens_per_second": 10699.565 }, { "epoch": 0.9187314839752222, "grad_norm": 0.6465062419098878, "learning_rate": 5.637073768225517e-06, "loss": 0.3411413192749023, "num_input_tokens_seen": 562054016, "step": 13645, "train_runtime": 52532.2004, "train_tokens_per_second": 10699.229 }, { "epoch": 0.9190681389711823, "grad_norm": 0.6868359339639278, "learning_rate": 5.634451147639758e-06, "loss": 0.33493690490722655, "num_input_tokens_seen": 562247344, "step": 13650, "train_runtime": 52552.731, "train_tokens_per_second": 10698.727 }, { "epoch": 0.9194047939671425, "grad_norm": 0.660295252411339, "learning_rate": 5.631828349631757e-06, "loss": 0.34705801010131837, "num_input_tokens_seen": 562457208, "step": 13655, "train_runtime": 52571.199, "train_tokens_per_second": 10698.961 }, { "epoch": 0.9197414489631026, "grad_norm": 0.6576709064017487, "learning_rate": 5.629205374934974e-06, "loss": 0.3453697681427002, "num_input_tokens_seen": 562655360, "step": 13660, "train_runtime": 52590.2958, "train_tokens_per_second": 10698.844 }, { "epoch": 0.9200781039590628, "grad_norm": 0.659423616488429, "learning_rate": 5.626582224282913e-06, "loss": 0.36219851970672606, "num_input_tokens_seen": 562867176, "step": 13665, "train_runtime": 52609.9193, "train_tokens_per_second": 10698.879 }, { "epoch": 0.9204147589550229, "grad_norm": 0.778496746452163, "learning_rate": 5.623958898409132e-06, "loss": 0.396626353263855, "num_input_tokens_seen": 563076280, "step": 13670, "train_runtime": 52627.5985, "train_tokens_per_second": 10699.258 }, { "epoch": 0.920751413950983, "grad_norm": 0.6427021428913057, "learning_rate": 5.621335398047234e-06, "loss": 0.3864113807678223, "num_input_tokens_seen": 563280056, "step": 13675, "train_runtime": 52647.0753, "train_tokens_per_second": 10699.171 }, { "epoch": 0.9210880689469432, "grad_norm": 0.7018320425482006, "learning_rate": 5.618711723930874e-06, "loss": 0.36655426025390625, "num_input_tokens_seen": 563483480, "step": 13680, "train_runtime": 52664.8545, "train_tokens_per_second": 10699.422 }, { "epoch": 0.9214247239429033, "grad_norm": 0.7350281507275335, "learning_rate": 5.616087876793753e-06, "loss": 0.37822494506835935, "num_input_tokens_seen": 563695176, "step": 13685, "train_runtime": 52682.9347, "train_tokens_per_second": 10699.768 }, { "epoch": 0.9217613789388635, "grad_norm": 0.6484573830561157, "learning_rate": 5.613463857369621e-06, "loss": 0.36631202697753906, "num_input_tokens_seen": 563906544, "step": 13690, "train_runtime": 52703.5237, "train_tokens_per_second": 10699.599 }, { "epoch": 0.9220980339348236, "grad_norm": 0.6733159789429582, "learning_rate": 5.610839666392278e-06, "loss": 0.35529389381408694, "num_input_tokens_seen": 564116416, "step": 13695, "train_runtime": 52722.7421, "train_tokens_per_second": 10699.679 }, { "epoch": 0.9224346889307837, "grad_norm": 0.7237085739959155, "learning_rate": 5.608215304595571e-06, "loss": 0.38459932804107666, "num_input_tokens_seen": 564323600, "step": 13700, "train_runtime": 52740.9451, "train_tokens_per_second": 10699.914 }, { "epoch": 0.9227713439267439, "grad_norm": 0.6582341557854035, "learning_rate": 5.605590772713393e-06, "loss": 0.3480700492858887, "num_input_tokens_seen": 564515360, "step": 13705, "train_runtime": 52760.5969, "train_tokens_per_second": 10699.564 }, { "epoch": 0.923107998922704, "grad_norm": 0.7443064909019582, "learning_rate": 5.602966071479687e-06, "loss": 0.37510731220245364, "num_input_tokens_seen": 564709224, "step": 13710, "train_runtime": 52778.9313, "train_tokens_per_second": 10699.52 }, { "epoch": 0.9234446539186641, "grad_norm": 0.6708027095247421, "learning_rate": 5.600341201628439e-06, "loss": 0.3678430557250977, "num_input_tokens_seen": 564921144, "step": 13715, "train_runtime": 52797.8254, "train_tokens_per_second": 10699.705 }, { "epoch": 0.9237813089146243, "grad_norm": 0.5762057399580591, "learning_rate": 5.597716163893692e-06, "loss": 0.312945818901062, "num_input_tokens_seen": 565136776, "step": 13720, "train_runtime": 52816.7787, "train_tokens_per_second": 10699.948 }, { "epoch": 0.9241179639105844, "grad_norm": 0.6845145473231914, "learning_rate": 5.595090959009525e-06, "loss": 0.34069204330444336, "num_input_tokens_seen": 565348728, "step": 13725, "train_runtime": 52837.276, "train_tokens_per_second": 10699.808 }, { "epoch": 0.9244546189065446, "grad_norm": 0.6247762633278928, "learning_rate": 5.592465587710068e-06, "loss": 0.3431239604949951, "num_input_tokens_seen": 565566536, "step": 13730, "train_runtime": 52856.3503, "train_tokens_per_second": 10700.068 }, { "epoch": 0.9247912739025047, "grad_norm": 0.6056126301362769, "learning_rate": 5.589840050729498e-06, "loss": 0.3271608829498291, "num_input_tokens_seen": 565775256, "step": 13735, "train_runtime": 52874.3222, "train_tokens_per_second": 10700.378 }, { "epoch": 0.9251279288984648, "grad_norm": 0.7409939029876164, "learning_rate": 5.587214348802039e-06, "loss": 0.39456911087036134, "num_input_tokens_seen": 565976624, "step": 13740, "train_runtime": 52893.6937, "train_tokens_per_second": 10700.267 }, { "epoch": 0.925464583894425, "grad_norm": 0.6908885060151972, "learning_rate": 5.5845884826619615e-06, "loss": 0.36872143745422364, "num_input_tokens_seen": 566187776, "step": 13745, "train_runtime": 52912.2301, "train_tokens_per_second": 10700.509 }, { "epoch": 0.9258012388903851, "grad_norm": 0.6168234331022525, "learning_rate": 5.5819624530435775e-06, "loss": 0.3572822093963623, "num_input_tokens_seen": 566390816, "step": 13750, "train_runtime": 52933.0832, "train_tokens_per_second": 10700.129 }, { "epoch": 0.9261378938863453, "grad_norm": 0.734893919915853, "learning_rate": 5.57933626068125e-06, "loss": 0.3934147596359253, "num_input_tokens_seen": 566599672, "step": 13755, "train_runtime": 52954.3747, "train_tokens_per_second": 10699.771 }, { "epoch": 0.9264745488823054, "grad_norm": 0.7376910898314807, "learning_rate": 5.5767099063093835e-06, "loss": 0.37956843376159666, "num_input_tokens_seen": 566812456, "step": 13760, "train_runtime": 52972.8705, "train_tokens_per_second": 10700.052 }, { "epoch": 0.9268112038782655, "grad_norm": 0.7579266837500983, "learning_rate": 5.574083390662431e-06, "loss": 0.37464103698730467, "num_input_tokens_seen": 567027176, "step": 13765, "train_runtime": 52990.7151, "train_tokens_per_second": 10700.501 }, { "epoch": 0.9271478588742257, "grad_norm": 0.7755426213852864, "learning_rate": 5.57145671447489e-06, "loss": 0.3697237014770508, "num_input_tokens_seen": 567219696, "step": 13770, "train_runtime": 53009.9632, "train_tokens_per_second": 10700.247 }, { "epoch": 0.9274845138701858, "grad_norm": 0.8030244765277235, "learning_rate": 5.5688298784813e-06, "loss": 0.394665002822876, "num_input_tokens_seen": 567425344, "step": 13775, "train_runtime": 53027.546, "train_tokens_per_second": 10700.577 }, { "epoch": 0.927821168866146, "grad_norm": 0.6622053421980311, "learning_rate": 5.566202883416249e-06, "loss": 0.3974961757659912, "num_input_tokens_seen": 567639120, "step": 13780, "train_runtime": 53046.9392, "train_tokens_per_second": 10700.695 }, { "epoch": 0.9281578238621061, "grad_norm": 0.7297849311904776, "learning_rate": 5.563575730014366e-06, "loss": 0.39152600765228274, "num_input_tokens_seen": 567841040, "step": 13785, "train_runtime": 53064.4419, "train_tokens_per_second": 10700.971 }, { "epoch": 0.9284944788580662, "grad_norm": 0.7659032735936295, "learning_rate": 5.560948419010328e-06, "loss": 0.382231330871582, "num_input_tokens_seen": 568049568, "step": 13790, "train_runtime": 53084.1064, "train_tokens_per_second": 10700.935 }, { "epoch": 0.9288311338540264, "grad_norm": 0.6600252286402505, "learning_rate": 5.558320951138853e-06, "loss": 0.34195609092712403, "num_input_tokens_seen": 568252808, "step": 13795, "train_runtime": 53103.6606, "train_tokens_per_second": 10700.822 }, { "epoch": 0.9291677888499865, "grad_norm": 0.7278596537790569, "learning_rate": 5.5556933271347046e-06, "loss": 0.3766955852508545, "num_input_tokens_seen": 568451648, "step": 13800, "train_runtime": 53122.0298, "train_tokens_per_second": 10700.865 }, { "epoch": 0.9295044438459467, "grad_norm": 0.6821073242279905, "learning_rate": 5.55306554773269e-06, "loss": 0.39478554725646975, "num_input_tokens_seen": 568650496, "step": 13805, "train_runtime": 53141.9594, "train_tokens_per_second": 10700.593 }, { "epoch": 0.9298410988419068, "grad_norm": 0.8486603293942425, "learning_rate": 5.550437613667658e-06, "loss": 0.35734670162200927, "num_input_tokens_seen": 568830712, "step": 13810, "train_runtime": 53159.211, "train_tokens_per_second": 10700.511 }, { "epoch": 0.9301777538378669, "grad_norm": 0.6819120285618606, "learning_rate": 5.547809525674501e-06, "loss": 0.35715456008911134, "num_input_tokens_seen": 569028280, "step": 13815, "train_runtime": 53178.4372, "train_tokens_per_second": 10700.357 }, { "epoch": 0.9305144088338271, "grad_norm": 0.7497795822922095, "learning_rate": 5.545181284488159e-06, "loss": 0.39307780265808107, "num_input_tokens_seen": 569241920, "step": 13820, "train_runtime": 53197.8527, "train_tokens_per_second": 10700.468 }, { "epoch": 0.9308510638297872, "grad_norm": 0.7688626908156637, "learning_rate": 5.5425528908436085e-06, "loss": 0.35745964050292967, "num_input_tokens_seen": 569435488, "step": 13825, "train_runtime": 53217.3082, "train_tokens_per_second": 10700.193 }, { "epoch": 0.9311877188257474, "grad_norm": 0.7165777897914654, "learning_rate": 5.539924345475873e-06, "loss": 0.38864641189575194, "num_input_tokens_seen": 569622408, "step": 13830, "train_runtime": 53236.4238, "train_tokens_per_second": 10699.862 }, { "epoch": 0.9315243738217075, "grad_norm": 0.7041210602179061, "learning_rate": 5.5372956491200145e-06, "loss": 0.3828885555267334, "num_input_tokens_seen": 569821984, "step": 13835, "train_runtime": 53254.8481, "train_tokens_per_second": 10699.908 }, { "epoch": 0.9318610288176676, "grad_norm": 0.7010677668943143, "learning_rate": 5.534666802511143e-06, "loss": 0.36651268005371096, "num_input_tokens_seen": 570013424, "step": 13840, "train_runtime": 53273.941, "train_tokens_per_second": 10699.667 }, { "epoch": 0.9321976838136278, "grad_norm": 0.6771898033949098, "learning_rate": 5.532037806384404e-06, "loss": 0.3715245008468628, "num_input_tokens_seen": 570226768, "step": 13845, "train_runtime": 53294.5247, "train_tokens_per_second": 10699.538 }, { "epoch": 0.9325343388095879, "grad_norm": 0.7136478797826542, "learning_rate": 5.529408661474989e-06, "loss": 0.33954567909240724, "num_input_tokens_seen": 570416984, "step": 13850, "train_runtime": 53313.7862, "train_tokens_per_second": 10699.24 }, { "epoch": 0.932870993805548, "grad_norm": 0.6640791290080621, "learning_rate": 5.526779368518129e-06, "loss": 0.3869551420211792, "num_input_tokens_seen": 570627472, "step": 13855, "train_runtime": 53332.877, "train_tokens_per_second": 10699.357 }, { "epoch": 0.9332076488015082, "grad_norm": 0.735407459913838, "learning_rate": 5.5241499282491e-06, "loss": 0.362178373336792, "num_input_tokens_seen": 570818840, "step": 13860, "train_runtime": 53353.1464, "train_tokens_per_second": 10698.879 }, { "epoch": 0.9335443037974683, "grad_norm": 0.6445909293610261, "learning_rate": 5.5215203414032135e-06, "loss": 0.3450345516204834, "num_input_tokens_seen": 571035072, "step": 13865, "train_runtime": 53373.5125, "train_tokens_per_second": 10698.848 }, { "epoch": 0.9338809587934285, "grad_norm": 0.7745259399039832, "learning_rate": 5.518890608715828e-06, "loss": 0.3627780914306641, "num_input_tokens_seen": 571240544, "step": 13870, "train_runtime": 53393.6986, "train_tokens_per_second": 10698.651 }, { "epoch": 0.9342176137893886, "grad_norm": 0.8218566808243116, "learning_rate": 5.516260730922337e-06, "loss": 0.37743725776672366, "num_input_tokens_seen": 571434864, "step": 13875, "train_runtime": 53413.2206, "train_tokens_per_second": 10698.379 }, { "epoch": 0.9345542687853488, "grad_norm": 0.6536583960806103, "learning_rate": 5.51363070875818e-06, "loss": 0.37146170139312745, "num_input_tokens_seen": 571640272, "step": 13880, "train_runtime": 53432.9964, "train_tokens_per_second": 10698.263 }, { "epoch": 0.9348909237813089, "grad_norm": 0.7248710228115886, "learning_rate": 5.511000542958832e-06, "loss": 0.383185601234436, "num_input_tokens_seen": 571840344, "step": 13885, "train_runtime": 53452.4287, "train_tokens_per_second": 10698.117 }, { "epoch": 0.935227578777269, "grad_norm": 0.7557788365000611, "learning_rate": 5.508370234259812e-06, "loss": 0.3616978645324707, "num_input_tokens_seen": 572043464, "step": 13890, "train_runtime": 53472.0669, "train_tokens_per_second": 10697.987 }, { "epoch": 0.9355642337732292, "grad_norm": 0.7223444299080957, "learning_rate": 5.505739783396678e-06, "loss": 0.4150699138641357, "num_input_tokens_seen": 572243352, "step": 13895, "train_runtime": 53490.9809, "train_tokens_per_second": 10697.941 }, { "epoch": 0.9359008887691893, "grad_norm": 0.7233032327930405, "learning_rate": 5.503109191105026e-06, "loss": 0.3707020044326782, "num_input_tokens_seen": 572443832, "step": 13900, "train_runtime": 53510.8887, "train_tokens_per_second": 10697.707 }, { "epoch": 0.9362375437651494, "grad_norm": 0.658961067325258, "learning_rate": 5.500478458120493e-06, "loss": 0.38662009239196776, "num_input_tokens_seen": 572657456, "step": 13905, "train_runtime": 53529.3536, "train_tokens_per_second": 10698.008 }, { "epoch": 0.9365741987611096, "grad_norm": 0.6226035064770035, "learning_rate": 5.497847585178754e-06, "loss": 0.38346621990203855, "num_input_tokens_seen": 572870176, "step": 13910, "train_runtime": 53548.3274, "train_tokens_per_second": 10698.19 }, { "epoch": 0.9369108537570697, "grad_norm": 0.6271035230104008, "learning_rate": 5.495216573015526e-06, "loss": 0.34463913440704347, "num_input_tokens_seen": 573072096, "step": 13915, "train_runtime": 53567.2841, "train_tokens_per_second": 10698.173 }, { "epoch": 0.9372475087530299, "grad_norm": 0.714121988646974, "learning_rate": 5.492585422366562e-06, "loss": 0.34395999908447267, "num_input_tokens_seen": 573276336, "step": 13920, "train_runtime": 53586.8297, "train_tokens_per_second": 10698.083 }, { "epoch": 0.93758416374899, "grad_norm": 0.6650231638394019, "learning_rate": 5.489954133967657e-06, "loss": 0.3354897975921631, "num_input_tokens_seen": 573472632, "step": 13925, "train_runtime": 53607.5367, "train_tokens_per_second": 10697.612 }, { "epoch": 0.9379208187449501, "grad_norm": 0.6677858612230342, "learning_rate": 5.48732270855464e-06, "loss": 0.3459118127822876, "num_input_tokens_seen": 573688200, "step": 13930, "train_runtime": 53626.2637, "train_tokens_per_second": 10697.896 }, { "epoch": 0.9382574737409103, "grad_norm": 0.7399377687323303, "learning_rate": 5.48469114686338e-06, "loss": 0.36015963554382324, "num_input_tokens_seen": 573882992, "step": 13935, "train_runtime": 53645.937, "train_tokens_per_second": 10697.604 }, { "epoch": 0.9385941287368704, "grad_norm": 0.6559934974743785, "learning_rate": 5.482059449629788e-06, "loss": 0.3535609722137451, "num_input_tokens_seen": 574097384, "step": 13940, "train_runtime": 53665.0745, "train_tokens_per_second": 10697.784 }, { "epoch": 0.9389307837328306, "grad_norm": 0.7001552998527489, "learning_rate": 5.479427617589808e-06, "loss": 0.34983057975769044, "num_input_tokens_seen": 574300168, "step": 13945, "train_runtime": 53683.8734, "train_tokens_per_second": 10697.815 }, { "epoch": 0.9392674387287907, "grad_norm": 0.6253961638231518, "learning_rate": 5.4767956514794226e-06, "loss": 0.368470287322998, "num_input_tokens_seen": 574512560, "step": 13950, "train_runtime": 53702.2152, "train_tokens_per_second": 10698.117 }, { "epoch": 0.9396040937247508, "grad_norm": 0.8036084365564095, "learning_rate": 5.474163552034655e-06, "loss": 0.35469255447387693, "num_input_tokens_seen": 574709864, "step": 13955, "train_runtime": 53720.4875, "train_tokens_per_second": 10698.151 }, { "epoch": 0.939940748720711, "grad_norm": 0.7376634897841962, "learning_rate": 5.4715313199915595e-06, "loss": 0.3383415937423706, "num_input_tokens_seen": 574907248, "step": 13960, "train_runtime": 53739.3793, "train_tokens_per_second": 10698.063 }, { "epoch": 0.9402774037166711, "grad_norm": 0.8273230638292483, "learning_rate": 5.468898956086236e-06, "loss": 0.3758941888809204, "num_input_tokens_seen": 575117296, "step": 13965, "train_runtime": 53758.401, "train_tokens_per_second": 10698.185 }, { "epoch": 0.9406140587126313, "grad_norm": 0.6621044900104179, "learning_rate": 5.466266461054815e-06, "loss": 0.3702735900878906, "num_input_tokens_seen": 575326752, "step": 13970, "train_runtime": 53778.0402, "train_tokens_per_second": 10698.173 }, { "epoch": 0.9409507137085914, "grad_norm": 0.7050865095886919, "learning_rate": 5.463633835633464e-06, "loss": 0.3825553894042969, "num_input_tokens_seen": 575544832, "step": 13975, "train_runtime": 53798.4153, "train_tokens_per_second": 10698.174 }, { "epoch": 0.9412873687045515, "grad_norm": 0.6528832357812475, "learning_rate": 5.46100108055839e-06, "loss": 0.3788674592971802, "num_input_tokens_seen": 575757320, "step": 13980, "train_runtime": 53816.9818, "train_tokens_per_second": 10698.432 }, { "epoch": 0.9416240237005117, "grad_norm": 0.730296538506172, "learning_rate": 5.458368196565833e-06, "loss": 0.3507805109024048, "num_input_tokens_seen": 575963432, "step": 13985, "train_runtime": 53835.4458, "train_tokens_per_second": 10698.591 }, { "epoch": 0.9419606786964718, "grad_norm": 0.6688893133294272, "learning_rate": 5.455735184392073e-06, "loss": 0.3865692377090454, "num_input_tokens_seen": 576176672, "step": 13990, "train_runtime": 53853.5397, "train_tokens_per_second": 10698.956 }, { "epoch": 0.942297333692432, "grad_norm": 0.850780335107097, "learning_rate": 5.4531020447734204e-06, "loss": 0.3826320648193359, "num_input_tokens_seen": 576377168, "step": 13995, "train_runtime": 53871.724, "train_tokens_per_second": 10699.067 }, { "epoch": 0.9426339886883921, "grad_norm": 0.6812905181461694, "learning_rate": 5.450468778446226e-06, "loss": 0.38164515495300294, "num_input_tokens_seen": 576594248, "step": 14000, "train_runtime": 53891.7099, "train_tokens_per_second": 10699.127 }, { "epoch": 0.9429706436843522, "grad_norm": 0.8856599851783457, "learning_rate": 5.447835386146875e-06, "loss": 0.37124099731445315, "num_input_tokens_seen": 576807584, "step": 14005, "train_runtime": 53911.6021, "train_tokens_per_second": 10699.136 }, { "epoch": 0.9433072986803124, "grad_norm": 0.6568192640706285, "learning_rate": 5.445201868611784e-06, "loss": 0.3994922399520874, "num_input_tokens_seen": 577008408, "step": 14010, "train_runtime": 53931.2175, "train_tokens_per_second": 10698.969 }, { "epoch": 0.9436439536762725, "grad_norm": 0.6816214095482555, "learning_rate": 5.442568226577413e-06, "loss": 0.3737906217575073, "num_input_tokens_seen": 577213272, "step": 14015, "train_runtime": 53949.6298, "train_tokens_per_second": 10699.115 }, { "epoch": 0.9439806086722327, "grad_norm": 0.6294541121243186, "learning_rate": 5.439934460780247e-06, "loss": 0.3611295700073242, "num_input_tokens_seen": 577422408, "step": 14020, "train_runtime": 53967.9006, "train_tokens_per_second": 10699.368 }, { "epoch": 0.9443172636681928, "grad_norm": 0.6330279198757912, "learning_rate": 5.437300571956813e-06, "loss": 0.3787305116653442, "num_input_tokens_seen": 577613144, "step": 14025, "train_runtime": 53986.1332, "train_tokens_per_second": 10699.287 }, { "epoch": 0.9446539186641529, "grad_norm": 0.627803175377604, "learning_rate": 5.434666560843667e-06, "loss": 0.3599610567092896, "num_input_tokens_seen": 577809536, "step": 14030, "train_runtime": 54005.4917, "train_tokens_per_second": 10699.089 }, { "epoch": 0.9449905736601131, "grad_norm": 0.6645494041514669, "learning_rate": 5.432032428177405e-06, "loss": 0.3766767978668213, "num_input_tokens_seen": 578023360, "step": 14035, "train_runtime": 54024.9251, "train_tokens_per_second": 10699.198 }, { "epoch": 0.9453272286560732, "grad_norm": 0.6834744375676648, "learning_rate": 5.429398174694651e-06, "loss": 0.3588553905487061, "num_input_tokens_seen": 578239040, "step": 14040, "train_runtime": 54044.458, "train_tokens_per_second": 10699.322 }, { "epoch": 0.9456638836520334, "grad_norm": 0.6803901639977777, "learning_rate": 5.426763801132067e-06, "loss": 0.36076674461364744, "num_input_tokens_seen": 578418384, "step": 14045, "train_runtime": 54063.7493, "train_tokens_per_second": 10698.821 }, { "epoch": 0.9460005386479935, "grad_norm": 0.7003178969842663, "learning_rate": 5.424129308226347e-06, "loss": 0.38560757637023924, "num_input_tokens_seen": 578615576, "step": 14050, "train_runtime": 54082.7987, "train_tokens_per_second": 10698.699 }, { "epoch": 0.9463371936439536, "grad_norm": 0.760598183613404, "learning_rate": 5.421494696714219e-06, "loss": 0.40221443176269533, "num_input_tokens_seen": 578836384, "step": 14055, "train_runtime": 54100.6908, "train_tokens_per_second": 10699.242 }, { "epoch": 0.9466738486399138, "grad_norm": 2.0883161763388296, "learning_rate": 5.418859967332442e-06, "loss": 0.3708867311477661, "num_input_tokens_seen": 579050016, "step": 14060, "train_runtime": 54119.0573, "train_tokens_per_second": 10699.558 }, { "epoch": 0.9470105036358739, "grad_norm": 0.8735564892597462, "learning_rate": 5.416225120817811e-06, "loss": 0.368639612197876, "num_input_tokens_seen": 579232280, "step": 14065, "train_runtime": 54138.392, "train_tokens_per_second": 10699.104 }, { "epoch": 0.947347158631834, "grad_norm": 0.6271483267268343, "learning_rate": 5.413590157907153e-06, "loss": 0.343410849571228, "num_input_tokens_seen": 579456888, "step": 14070, "train_runtime": 54156.9355, "train_tokens_per_second": 10699.588 }, { "epoch": 0.9476838136277942, "grad_norm": 0.6608805152284373, "learning_rate": 5.4109550793373255e-06, "loss": 0.35612988471984863, "num_input_tokens_seen": 579667960, "step": 14075, "train_runtime": 54177.0824, "train_tokens_per_second": 10699.505 }, { "epoch": 0.9480204686237543, "grad_norm": 0.7185013624823214, "learning_rate": 5.40831988584522e-06, "loss": 0.3876546859741211, "num_input_tokens_seen": 579877352, "step": 14080, "train_runtime": 54194.9388, "train_tokens_per_second": 10699.843 }, { "epoch": 0.9483571236197145, "grad_norm": 0.6673699914082225, "learning_rate": 5.40568457816776e-06, "loss": 0.3762470006942749, "num_input_tokens_seen": 580094608, "step": 14085, "train_runtime": 54214.0729, "train_tokens_per_second": 10700.074 }, { "epoch": 0.9486937786156746, "grad_norm": 0.5904946600535981, "learning_rate": 5.403049157041903e-06, "loss": 0.3568359136581421, "num_input_tokens_seen": 580301624, "step": 14090, "train_runtime": 54232.5631, "train_tokens_per_second": 10700.243 }, { "epoch": 0.9490304336116347, "grad_norm": 0.7350588795377018, "learning_rate": 5.400413623204635e-06, "loss": 0.3573333263397217, "num_input_tokens_seen": 580507520, "step": 14095, "train_runtime": 54252.6116, "train_tokens_per_second": 10700.084 }, { "epoch": 0.9493670886075949, "grad_norm": 0.7280614202455883, "learning_rate": 5.397777977392973e-06, "loss": 0.39266581535339357, "num_input_tokens_seen": 580718192, "step": 14100, "train_runtime": 54272.7649, "train_tokens_per_second": 10699.993 }, { "epoch": 0.949703743603555, "grad_norm": 0.6742597030546785, "learning_rate": 5.395142220343967e-06, "loss": 0.37393956184387206, "num_input_tokens_seen": 580928192, "step": 14105, "train_runtime": 54291.8678, "train_tokens_per_second": 10700.096 }, { "epoch": 0.9500403985995152, "grad_norm": 0.6630613473777218, "learning_rate": 5.3925063527947e-06, "loss": 0.3482337713241577, "num_input_tokens_seen": 581134536, "step": 14110, "train_runtime": 54313.1098, "train_tokens_per_second": 10699.71 }, { "epoch": 0.9503770535954753, "grad_norm": 0.7785916588301481, "learning_rate": 5.389870375482283e-06, "loss": 0.37725205421447755, "num_input_tokens_seen": 581323096, "step": 14115, "train_runtime": 54331.2446, "train_tokens_per_second": 10699.609 }, { "epoch": 0.9507137085914354, "grad_norm": 0.6611404554206808, "learning_rate": 5.387234289143859e-06, "loss": 0.3396444797515869, "num_input_tokens_seen": 581527864, "step": 14120, "train_runtime": 54349.3887, "train_tokens_per_second": 10699.805 }, { "epoch": 0.9510503635873956, "grad_norm": 0.6923551101822615, "learning_rate": 5.384598094516601e-06, "loss": 0.3772579669952393, "num_input_tokens_seen": 581738784, "step": 14125, "train_runtime": 54369.1504, "train_tokens_per_second": 10699.795 }, { "epoch": 0.9513870185833557, "grad_norm": 0.631539206243817, "learning_rate": 5.381961792337712e-06, "loss": 0.36998953819274905, "num_input_tokens_seen": 581952680, "step": 14130, "train_runtime": 54387.4272, "train_tokens_per_second": 10700.133 }, { "epoch": 0.9517236735793159, "grad_norm": 0.6597509137936944, "learning_rate": 5.3793253833444245e-06, "loss": 0.34386847019195554, "num_input_tokens_seen": 582162080, "step": 14135, "train_runtime": 54405.2345, "train_tokens_per_second": 10700.479 }, { "epoch": 0.952060328575276, "grad_norm": 0.749538965096943, "learning_rate": 5.3766888682740045e-06, "loss": 0.3588763475418091, "num_input_tokens_seen": 582373432, "step": 14140, "train_runtime": 54423.2471, "train_tokens_per_second": 10700.821 }, { "epoch": 0.9523969835712361, "grad_norm": 0.788602921990121, "learning_rate": 5.374052247863745e-06, "loss": 0.37481606006622314, "num_input_tokens_seen": 582574136, "step": 14145, "train_runtime": 54440.9314, "train_tokens_per_second": 10701.032 }, { "epoch": 0.9527336385671963, "grad_norm": 0.710276641631738, "learning_rate": 5.371415522850966e-06, "loss": 0.34732034206390383, "num_input_tokens_seen": 582779768, "step": 14150, "train_runtime": 54459.737, "train_tokens_per_second": 10701.112 }, { "epoch": 0.9530702935631564, "grad_norm": 0.7726358040662767, "learning_rate": 5.368778693973019e-06, "loss": 0.35257587432861326, "num_input_tokens_seen": 582982584, "step": 14155, "train_runtime": 54481.2991, "train_tokens_per_second": 10700.6 }, { "epoch": 0.9534069485591166, "grad_norm": 0.6081036985251941, "learning_rate": 5.366141761967287e-06, "loss": 0.37608673572540285, "num_input_tokens_seen": 583184488, "step": 14160, "train_runtime": 54499.3885, "train_tokens_per_second": 10700.753 }, { "epoch": 0.9537436035550767, "grad_norm": 0.8143296686174379, "learning_rate": 5.363504727571179e-06, "loss": 0.3870896577835083, "num_input_tokens_seen": 583391744, "step": 14165, "train_runtime": 54518.31, "train_tokens_per_second": 10700.841 }, { "epoch": 0.954080258551037, "grad_norm": 0.6849280163094067, "learning_rate": 5.360867591522133e-06, "loss": 0.4348581314086914, "num_input_tokens_seen": 583608696, "step": 14170, "train_runtime": 54537.841, "train_tokens_per_second": 10700.986 }, { "epoch": 0.9544169135469971, "grad_norm": 0.7083105337863833, "learning_rate": 5.358230354557617e-06, "loss": 0.353751540184021, "num_input_tokens_seen": 583819936, "step": 14175, "train_runtime": 54555.5377, "train_tokens_per_second": 10701.387 }, { "epoch": 0.9547535685429572, "grad_norm": 0.7650278765078105, "learning_rate": 5.355593017415123e-06, "loss": 0.3996608734130859, "num_input_tokens_seen": 584030792, "step": 14180, "train_runtime": 54574.2138, "train_tokens_per_second": 10701.589 }, { "epoch": 0.9550902235389174, "grad_norm": 0.7210235094482492, "learning_rate": 5.352955580832176e-06, "loss": 0.37434024810791017, "num_input_tokens_seen": 584242512, "step": 14185, "train_runtime": 54592.4855, "train_tokens_per_second": 10701.885 }, { "epoch": 0.9554268785348775, "grad_norm": 0.6513577023447256, "learning_rate": 5.350318045546326e-06, "loss": 0.38152451515197755, "num_input_tokens_seen": 584453120, "step": 14190, "train_runtime": 54613.0671, "train_tokens_per_second": 10701.708 }, { "epoch": 0.9557635335308377, "grad_norm": 0.6790977677161639, "learning_rate": 5.347680412295152e-06, "loss": 0.3806413412094116, "num_input_tokens_seen": 584657960, "step": 14195, "train_runtime": 54633.5881, "train_tokens_per_second": 10701.438 }, { "epoch": 0.9561001885267978, "grad_norm": 0.7650619334199915, "learning_rate": 5.34504268181626e-06, "loss": 0.37325057983398435, "num_input_tokens_seen": 584855656, "step": 14200, "train_runtime": 54652.6612, "train_tokens_per_second": 10701.321 }, { "epoch": 0.9564368435227579, "grad_norm": 0.775616680382046, "learning_rate": 5.342404854847282e-06, "loss": 0.3689694881439209, "num_input_tokens_seen": 585046640, "step": 14205, "train_runtime": 54672.0912, "train_tokens_per_second": 10701.011 }, { "epoch": 0.9567734985187181, "grad_norm": 0.7115746614544939, "learning_rate": 5.3397669321258776e-06, "loss": 0.3562792778015137, "num_input_tokens_seen": 585261392, "step": 14210, "train_runtime": 54690.5542, "train_tokens_per_second": 10701.325 }, { "epoch": 0.9571101535146782, "grad_norm": 0.6899799388875771, "learning_rate": 5.337128914389734e-06, "loss": 0.4005392074584961, "num_input_tokens_seen": 585477000, "step": 14215, "train_runtime": 54710.0277, "train_tokens_per_second": 10701.457 }, { "epoch": 0.9574468085106383, "grad_norm": 0.7267166971117395, "learning_rate": 5.334490802376565e-06, "loss": 0.3648582696914673, "num_input_tokens_seen": 585691656, "step": 14220, "train_runtime": 54730.6987, "train_tokens_per_second": 10701.337 }, { "epoch": 0.9577834635065985, "grad_norm": 1.0178266575162391, "learning_rate": 5.33185259682411e-06, "loss": 0.38952558040618895, "num_input_tokens_seen": 585891936, "step": 14225, "train_runtime": 54748.7337, "train_tokens_per_second": 10701.47 }, { "epoch": 0.9581201185025586, "grad_norm": 0.6529266197993443, "learning_rate": 5.329214298470134e-06, "loss": 0.39412631988525393, "num_input_tokens_seen": 586102112, "step": 14230, "train_runtime": 54766.6015, "train_tokens_per_second": 10701.816 }, { "epoch": 0.9584567734985188, "grad_norm": 0.6260876230552388, "learning_rate": 5.326575908052428e-06, "loss": 0.3537588119506836, "num_input_tokens_seen": 586315536, "step": 14235, "train_runtime": 54785.9106, "train_tokens_per_second": 10701.94 }, { "epoch": 0.9587934284944789, "grad_norm": 1.8800599115106547, "learning_rate": 5.323937426308813e-06, "loss": 0.4046344757080078, "num_input_tokens_seen": 586528080, "step": 14240, "train_runtime": 54805.7492, "train_tokens_per_second": 10701.944 }, { "epoch": 0.959130083490439, "grad_norm": 0.6798975948467675, "learning_rate": 5.321298853977128e-06, "loss": 0.3502375841140747, "num_input_tokens_seen": 586750256, "step": 14245, "train_runtime": 54824.33, "train_tokens_per_second": 10702.37 }, { "epoch": 0.9594667384863992, "grad_norm": 0.6768782594307496, "learning_rate": 5.318660191795244e-06, "loss": 0.35112829208374025, "num_input_tokens_seen": 586955096, "step": 14250, "train_runtime": 54841.6398, "train_tokens_per_second": 10702.727 }, { "epoch": 0.9598033934823593, "grad_norm": 0.672896924667533, "learning_rate": 5.316021440501053e-06, "loss": 0.32686378955841067, "num_input_tokens_seen": 587160712, "step": 14255, "train_runtime": 54860.7858, "train_tokens_per_second": 10702.74 }, { "epoch": 0.9601400484783195, "grad_norm": 0.6360327780141244, "learning_rate": 5.313382600832474e-06, "loss": 0.32350940704345704, "num_input_tokens_seen": 587368616, "step": 14260, "train_runtime": 54881.3042, "train_tokens_per_second": 10702.527 }, { "epoch": 0.9604767034742796, "grad_norm": 0.6578036448880263, "learning_rate": 5.310743673527451e-06, "loss": 0.38058793544769287, "num_input_tokens_seen": 587582712, "step": 14265, "train_runtime": 54900.1982, "train_tokens_per_second": 10702.743 }, { "epoch": 0.9608133584702397, "grad_norm": 0.68388721071557, "learning_rate": 5.3081046593239496e-06, "loss": 0.3803699970245361, "num_input_tokens_seen": 587789056, "step": 14270, "train_runtime": 54920.2204, "train_tokens_per_second": 10702.598 }, { "epoch": 0.9611500134661999, "grad_norm": 0.6890589854612229, "learning_rate": 5.305465558959964e-06, "loss": 0.3721219539642334, "num_input_tokens_seen": 587990744, "step": 14275, "train_runtime": 54939.6685, "train_tokens_per_second": 10702.481 }, { "epoch": 0.96148666846216, "grad_norm": 0.6729888201384554, "learning_rate": 5.302826373173506e-06, "loss": 0.36037919521331785, "num_input_tokens_seen": 588202744, "step": 14280, "train_runtime": 54957.3149, "train_tokens_per_second": 10702.902 }, { "epoch": 0.9618233234581202, "grad_norm": 0.6536679686358383, "learning_rate": 5.3001871027026194e-06, "loss": 0.3522597074508667, "num_input_tokens_seen": 588403968, "step": 14285, "train_runtime": 54977.1895, "train_tokens_per_second": 10702.693 }, { "epoch": 0.9621599784540803, "grad_norm": 0.6629008980990901, "learning_rate": 5.2975477482853685e-06, "loss": 0.3496358394622803, "num_input_tokens_seen": 588615296, "step": 14290, "train_runtime": 54997.5384, "train_tokens_per_second": 10702.575 }, { "epoch": 0.9624966334500404, "grad_norm": 0.7238177605407726, "learning_rate": 5.294908310659838e-06, "loss": 0.37053985595703126, "num_input_tokens_seen": 588829232, "step": 14295, "train_runtime": 55016.1386, "train_tokens_per_second": 10702.846 }, { "epoch": 0.9628332884460006, "grad_norm": 0.7492656418509208, "learning_rate": 5.292268790564138e-06, "loss": 0.34981675148010255, "num_input_tokens_seen": 589031480, "step": 14300, "train_runtime": 55035.4304, "train_tokens_per_second": 10702.769 }, { "epoch": 0.9631699434419607, "grad_norm": 0.6882389101260076, "learning_rate": 5.289629188736403e-06, "loss": 0.38977096080780027, "num_input_tokens_seen": 589240632, "step": 14305, "train_runtime": 55055.6448, "train_tokens_per_second": 10702.638 }, { "epoch": 0.9635065984379209, "grad_norm": 0.7640624787596377, "learning_rate": 5.286989505914788e-06, "loss": 0.3857623815536499, "num_input_tokens_seen": 589454552, "step": 14310, "train_runtime": 55075.1391, "train_tokens_per_second": 10702.734 }, { "epoch": 0.963843253433881, "grad_norm": 0.7463996215502015, "learning_rate": 5.284349742837475e-06, "loss": 0.3760960340499878, "num_input_tokens_seen": 589670248, "step": 14315, "train_runtime": 55093.6744, "train_tokens_per_second": 10703.048 }, { "epoch": 0.9641799084298411, "grad_norm": 0.8724452858831728, "learning_rate": 5.281709900242662e-06, "loss": 0.363153338432312, "num_input_tokens_seen": 589879248, "step": 14320, "train_runtime": 55112.2458, "train_tokens_per_second": 10703.234 }, { "epoch": 0.9645165634258013, "grad_norm": 0.7481314697576814, "learning_rate": 5.279069978868574e-06, "loss": 0.350467586517334, "num_input_tokens_seen": 590086344, "step": 14325, "train_runtime": 55131.6181, "train_tokens_per_second": 10703.229 }, { "epoch": 0.9648532184217614, "grad_norm": 0.6994578844328243, "learning_rate": 5.276429979453455e-06, "loss": 0.37242445945739744, "num_input_tokens_seen": 590291128, "step": 14330, "train_runtime": 55149.8756, "train_tokens_per_second": 10703.399 }, { "epoch": 0.9651898734177216, "grad_norm": 0.6039814658878587, "learning_rate": 5.273789902735575e-06, "loss": 0.369755220413208, "num_input_tokens_seen": 590494640, "step": 14335, "train_runtime": 55168.5052, "train_tokens_per_second": 10703.474 }, { "epoch": 0.9655265284136817, "grad_norm": 0.7008296730996196, "learning_rate": 5.27114974945322e-06, "loss": 0.3381878614425659, "num_input_tokens_seen": 590697328, "step": 14340, "train_runtime": 55188.1467, "train_tokens_per_second": 10703.337 }, { "epoch": 0.9658631834096418, "grad_norm": 0.706488482320109, "learning_rate": 5.2685095203447046e-06, "loss": 0.3661853551864624, "num_input_tokens_seen": 590908304, "step": 14345, "train_runtime": 55205.6884, "train_tokens_per_second": 10703.758 }, { "epoch": 0.966199838405602, "grad_norm": 0.7014667588680824, "learning_rate": 5.265869216148357e-06, "loss": 0.35205397605895994, "num_input_tokens_seen": 591114440, "step": 14350, "train_runtime": 55225.9947, "train_tokens_per_second": 10703.554 }, { "epoch": 0.9665364934015621, "grad_norm": 0.8574235399785544, "learning_rate": 5.263228837602532e-06, "loss": 0.41980805397033694, "num_input_tokens_seen": 591315184, "step": 14355, "train_runtime": 55244.0932, "train_tokens_per_second": 10703.682 }, { "epoch": 0.9668731483975223, "grad_norm": 0.7787345661314962, "learning_rate": 5.2605883854456e-06, "loss": 0.37664618492126467, "num_input_tokens_seen": 591523232, "step": 14360, "train_runtime": 55263.0506, "train_tokens_per_second": 10703.775 }, { "epoch": 0.9672098033934824, "grad_norm": 0.5980747443204433, "learning_rate": 5.257947860415957e-06, "loss": 0.3372334480285645, "num_input_tokens_seen": 591734680, "step": 14365, "train_runtime": 55280.6122, "train_tokens_per_second": 10704.199 }, { "epoch": 0.9675464583894425, "grad_norm": 0.8130800848650102, "learning_rate": 5.255307263252019e-06, "loss": 0.355433988571167, "num_input_tokens_seen": 591949280, "step": 14370, "train_runtime": 55299.8863, "train_tokens_per_second": 10704.349 }, { "epoch": 0.9678831133854027, "grad_norm": 0.6577047617695784, "learning_rate": 5.2526665946922185e-06, "loss": 0.38936452865600585, "num_input_tokens_seen": 592155560, "step": 14375, "train_runtime": 55320.3426, "train_tokens_per_second": 10704.12 }, { "epoch": 0.9682197683813628, "grad_norm": 0.6129578837328077, "learning_rate": 5.25002585547501e-06, "loss": 0.354550838470459, "num_input_tokens_seen": 592366112, "step": 14380, "train_runtime": 55339.5646, "train_tokens_per_second": 10704.206 }, { "epoch": 0.968556423377323, "grad_norm": 0.6870237570792325, "learning_rate": 5.2473850463388675e-06, "loss": 0.3996854782104492, "num_input_tokens_seen": 592576256, "step": 14385, "train_runtime": 55358.9792, "train_tokens_per_second": 10704.248 }, { "epoch": 0.9688930783732831, "grad_norm": 0.6382825342207149, "learning_rate": 5.244744168022288e-06, "loss": 0.3627357006072998, "num_input_tokens_seen": 592787984, "step": 14390, "train_runtime": 55378.3217, "train_tokens_per_second": 10704.333 }, { "epoch": 0.9692297333692432, "grad_norm": 0.7455310378705171, "learning_rate": 5.24210322126378e-06, "loss": 0.37008180618286135, "num_input_tokens_seen": 593006624, "step": 14395, "train_runtime": 55395.8916, "train_tokens_per_second": 10704.885 }, { "epoch": 0.9695663883652034, "grad_norm": 0.6692351274481771, "learning_rate": 5.23946220680188e-06, "loss": 0.3708339214324951, "num_input_tokens_seen": 593226760, "step": 14400, "train_runtime": 55416.1027, "train_tokens_per_second": 10704.953 }, { "epoch": 0.9699030433611635, "grad_norm": 0.7966293264702334, "learning_rate": 5.236821125375136e-06, "loss": 0.35860023498535154, "num_input_tokens_seen": 593435416, "step": 14405, "train_runtime": 55435.1654, "train_tokens_per_second": 10705.036 }, { "epoch": 0.9702396983571236, "grad_norm": 0.6292186604667684, "learning_rate": 5.234179977722119e-06, "loss": 0.31839990615844727, "num_input_tokens_seen": 593657344, "step": 14410, "train_runtime": 55454.8965, "train_tokens_per_second": 10705.229 }, { "epoch": 0.9705763533530838, "grad_norm": 0.6655986898835857, "learning_rate": 5.23153876458142e-06, "loss": 0.3694854021072388, "num_input_tokens_seen": 593857424, "step": 14415, "train_runtime": 55474.8232, "train_tokens_per_second": 10704.99 }, { "epoch": 0.9709130083490439, "grad_norm": 0.7444128217057349, "learning_rate": 5.2288974866916435e-06, "loss": 0.3641714096069336, "num_input_tokens_seen": 594043144, "step": 14420, "train_runtime": 55494.0021, "train_tokens_per_second": 10704.637 }, { "epoch": 0.9712496633450041, "grad_norm": 0.7030123804747099, "learning_rate": 5.226256144791414e-06, "loss": 0.3639823436737061, "num_input_tokens_seen": 594237960, "step": 14425, "train_runtime": 55513.1806, "train_tokens_per_second": 10704.448 }, { "epoch": 0.9715863183409642, "grad_norm": 0.7119649875336552, "learning_rate": 5.223614739619375e-06, "loss": 0.3751939296722412, "num_input_tokens_seen": 594429944, "step": 14430, "train_runtime": 55533.0742, "train_tokens_per_second": 10704.071 }, { "epoch": 0.9719229733369243, "grad_norm": 0.5898274358939127, "learning_rate": 5.2209732719141855e-06, "loss": 0.33538455963134767, "num_input_tokens_seen": 594628848, "step": 14435, "train_runtime": 55552.5953, "train_tokens_per_second": 10703.89 }, { "epoch": 0.9722596283328845, "grad_norm": 0.6825473523331292, "learning_rate": 5.218331742414528e-06, "loss": 0.3486657619476318, "num_input_tokens_seen": 594843048, "step": 14440, "train_runtime": 55570.0335, "train_tokens_per_second": 10704.385 }, { "epoch": 0.9725962833288446, "grad_norm": 0.6338202459854271, "learning_rate": 5.215690151859094e-06, "loss": 0.3400124073028564, "num_input_tokens_seen": 595038128, "step": 14445, "train_runtime": 55588.7114, "train_tokens_per_second": 10704.298 }, { "epoch": 0.9729329383248048, "grad_norm": 0.688110033530119, "learning_rate": 5.213048500986597e-06, "loss": 0.371809196472168, "num_input_tokens_seen": 595246592, "step": 14450, "train_runtime": 55608.8213, "train_tokens_per_second": 10704.176 }, { "epoch": 0.9732695933207649, "grad_norm": 0.7745564549715059, "learning_rate": 5.210406790535766e-06, "loss": 0.37198572158813475, "num_input_tokens_seen": 595445184, "step": 14455, "train_runtime": 55627.7005, "train_tokens_per_second": 10704.113 }, { "epoch": 0.973606248316725, "grad_norm": 0.7029466898434872, "learning_rate": 5.207765021245346e-06, "loss": 0.36609683036804197, "num_input_tokens_seen": 595648368, "step": 14460, "train_runtime": 55646.9107, "train_tokens_per_second": 10704.069 }, { "epoch": 0.9739429033126852, "grad_norm": 0.6924757419145895, "learning_rate": 5.2051231938541015e-06, "loss": 0.36783111095428467, "num_input_tokens_seen": 595839712, "step": 14465, "train_runtime": 55665.5685, "train_tokens_per_second": 10703.919 }, { "epoch": 0.9742795583086453, "grad_norm": 0.9239652132745969, "learning_rate": 5.202481309100808e-06, "loss": 0.3736591339111328, "num_input_tokens_seen": 596039256, "step": 14470, "train_runtime": 55684.916, "train_tokens_per_second": 10703.783 }, { "epoch": 0.9746162133046055, "grad_norm": 0.6508897165336788, "learning_rate": 5.199839367724266e-06, "loss": 0.3666075706481934, "num_input_tokens_seen": 596252960, "step": 14475, "train_runtime": 55703.6092, "train_tokens_per_second": 10704.027 }, { "epoch": 0.9749528683005656, "grad_norm": 0.6567548047960582, "learning_rate": 5.197197370463278e-06, "loss": 0.3443185567855835, "num_input_tokens_seen": 596473648, "step": 14480, "train_runtime": 55721.2459, "train_tokens_per_second": 10704.6 }, { "epoch": 0.9752895232965257, "grad_norm": 0.6736403310137796, "learning_rate": 5.194555318056675e-06, "loss": 0.39211091995239256, "num_input_tokens_seen": 596691992, "step": 14485, "train_runtime": 55739.6856, "train_tokens_per_second": 10704.976 }, { "epoch": 0.9756261782924859, "grad_norm": 0.8884464095380058, "learning_rate": 5.191913211243299e-06, "loss": 0.3858195781707764, "num_input_tokens_seen": 596906120, "step": 14490, "train_runtime": 55760.8906, "train_tokens_per_second": 10704.745 }, { "epoch": 0.975962833288446, "grad_norm": 0.6848555172327254, "learning_rate": 5.1892710507620055e-06, "loss": 0.37550153732299807, "num_input_tokens_seen": 597112144, "step": 14495, "train_runtime": 55779.1509, "train_tokens_per_second": 10704.934 }, { "epoch": 0.9762994882844062, "grad_norm": 0.6829817836514289, "learning_rate": 5.186628837351666e-06, "loss": 0.35300517082214355, "num_input_tokens_seen": 597326296, "step": 14500, "train_runtime": 55798.3405, "train_tokens_per_second": 10705.091 }, { "epoch": 0.9766361432803663, "grad_norm": 0.6665652255424576, "learning_rate": 5.183986571751167e-06, "loss": 0.3668668270111084, "num_input_tokens_seen": 597535832, "step": 14505, "train_runtime": 55818.1737, "train_tokens_per_second": 10705.041 }, { "epoch": 0.9769727982763264, "grad_norm": 0.6639771288836251, "learning_rate": 5.181344254699408e-06, "loss": 0.38603317737579346, "num_input_tokens_seen": 597739144, "step": 14510, "train_runtime": 55836.8856, "train_tokens_per_second": 10705.095 }, { "epoch": 0.9773094532722866, "grad_norm": 0.6742400510945652, "learning_rate": 5.178701886935309e-06, "loss": 0.350083327293396, "num_input_tokens_seen": 597935608, "step": 14515, "train_runtime": 55856.4154, "train_tokens_per_second": 10704.869 }, { "epoch": 0.9776461082682467, "grad_norm": 0.6588228897613833, "learning_rate": 5.176059469197796e-06, "loss": 0.3593077421188354, "num_input_tokens_seen": 598143072, "step": 14520, "train_runtime": 55874.9677, "train_tokens_per_second": 10705.028 }, { "epoch": 0.9779827632642069, "grad_norm": 0.7561686897630294, "learning_rate": 5.173417002225815e-06, "loss": 0.35675368309020994, "num_input_tokens_seen": 598350232, "step": 14525, "train_runtime": 55893.9707, "train_tokens_per_second": 10705.094 }, { "epoch": 0.978319418260167, "grad_norm": 0.7148466120631893, "learning_rate": 5.170774486758322e-06, "loss": 0.3664527893066406, "num_input_tokens_seen": 598534648, "step": 14530, "train_runtime": 55912.0235, "train_tokens_per_second": 10704.936 }, { "epoch": 0.9786560732561271, "grad_norm": 0.6648586289944572, "learning_rate": 5.168131923534287e-06, "loss": 0.3835784912109375, "num_input_tokens_seen": 598745864, "step": 14535, "train_runtime": 55931.3313, "train_tokens_per_second": 10705.017 }, { "epoch": 0.9789927282520873, "grad_norm": 0.6390458624782521, "learning_rate": 5.165489313292696e-06, "loss": 0.3549033164978027, "num_input_tokens_seen": 598948728, "step": 14540, "train_runtime": 55952.3605, "train_tokens_per_second": 10704.619 }, { "epoch": 0.9793293832480474, "grad_norm": 0.7191531266052977, "learning_rate": 5.162846656772548e-06, "loss": 0.354375433921814, "num_input_tokens_seen": 599151728, "step": 14545, "train_runtime": 55973.3337, "train_tokens_per_second": 10704.235 }, { "epoch": 0.9796660382440076, "grad_norm": 0.7314582115430271, "learning_rate": 5.16020395471285e-06, "loss": 0.3474612236022949, "num_input_tokens_seen": 599360168, "step": 14550, "train_runtime": 55991.8607, "train_tokens_per_second": 10704.416 }, { "epoch": 0.9800026932399677, "grad_norm": 0.7502387820266647, "learning_rate": 5.157561207852628e-06, "loss": 0.38005943298339845, "num_input_tokens_seen": 599552488, "step": 14555, "train_runtime": 56009.8315, "train_tokens_per_second": 10704.415 }, { "epoch": 0.9803393482359278, "grad_norm": 0.6722341257183487, "learning_rate": 5.154918416930915e-06, "loss": 0.34089324474334715, "num_input_tokens_seen": 599756768, "step": 14560, "train_runtime": 56028.4033, "train_tokens_per_second": 10704.513 }, { "epoch": 0.980676003231888, "grad_norm": 0.7103960903301264, "learning_rate": 5.152275582686761e-06, "loss": 0.3869309902191162, "num_input_tokens_seen": 599958688, "step": 14565, "train_runtime": 56046.6416, "train_tokens_per_second": 10704.632 }, { "epoch": 0.9810126582278481, "grad_norm": 0.6578340888231854, "learning_rate": 5.149632705859227e-06, "loss": 0.3716651678085327, "num_input_tokens_seen": 600170688, "step": 14570, "train_runtime": 56065.571, "train_tokens_per_second": 10704.799 }, { "epoch": 0.9813493132238083, "grad_norm": 0.6979290028146917, "learning_rate": 5.146989787187383e-06, "loss": 0.3678715229034424, "num_input_tokens_seen": 600384208, "step": 14575, "train_runtime": 56083.7874, "train_tokens_per_second": 10705.13 }, { "epoch": 0.9816859682197684, "grad_norm": 0.6810008561593167, "learning_rate": 5.144346827410314e-06, "loss": 0.3724397659301758, "num_input_tokens_seen": 600593624, "step": 14580, "train_runtime": 56101.389, "train_tokens_per_second": 10705.504 }, { "epoch": 0.9820226232157285, "grad_norm": 0.8627186899363761, "learning_rate": 5.141703827267117e-06, "loss": 0.37199862003326417, "num_input_tokens_seen": 600805168, "step": 14585, "train_runtime": 56119.8992, "train_tokens_per_second": 10705.742 }, { "epoch": 0.9823592782116887, "grad_norm": 0.6588362071938278, "learning_rate": 5.139060787496893e-06, "loss": 0.37877755165100097, "num_input_tokens_seen": 601012720, "step": 14590, "train_runtime": 56138.2123, "train_tokens_per_second": 10705.947 }, { "epoch": 0.9826959332076488, "grad_norm": 0.6525606608452568, "learning_rate": 5.136417708838766e-06, "loss": 0.37831921577453614, "num_input_tokens_seen": 601206520, "step": 14595, "train_runtime": 56157.017, "train_tokens_per_second": 10705.813 }, { "epoch": 0.983032588203609, "grad_norm": 0.7280331248412636, "learning_rate": 5.13377459203186e-06, "loss": 0.3664341688156128, "num_input_tokens_seen": 601403768, "step": 14600, "train_runtime": 56175.7885, "train_tokens_per_second": 10705.747 }, { "epoch": 0.9833692431995691, "grad_norm": 0.6948687022490309, "learning_rate": 5.131131437815318e-06, "loss": 0.34191036224365234, "num_input_tokens_seen": 601611856, "step": 14605, "train_runtime": 56194.3669, "train_tokens_per_second": 10705.91 }, { "epoch": 0.9837058981955292, "grad_norm": 0.6824638170344125, "learning_rate": 5.128488246928287e-06, "loss": 0.37106571197509763, "num_input_tokens_seen": 601824056, "step": 14610, "train_runtime": 56212.5414, "train_tokens_per_second": 10706.224 }, { "epoch": 0.9840425531914894, "grad_norm": 0.7138393261874614, "learning_rate": 5.125845020109925e-06, "loss": 0.37199447154998777, "num_input_tokens_seen": 602033584, "step": 14615, "train_runtime": 56233.5694, "train_tokens_per_second": 10705.946 }, { "epoch": 0.9843792081874495, "grad_norm": 0.7771310499124783, "learning_rate": 5.123201758099406e-06, "loss": 0.36733255386352537, "num_input_tokens_seen": 602236424, "step": 14620, "train_runtime": 56253.7357, "train_tokens_per_second": 10705.714 }, { "epoch": 0.9847158631834096, "grad_norm": 0.6891064688242827, "learning_rate": 5.12055846163591e-06, "loss": 0.37278099060058595, "num_input_tokens_seen": 602437432, "step": 14625, "train_runtime": 56272.1058, "train_tokens_per_second": 10705.792 }, { "epoch": 0.9850525181793698, "grad_norm": 0.6130949650393065, "learning_rate": 5.117915131458623e-06, "loss": 0.32522995471954347, "num_input_tokens_seen": 602647296, "step": 14630, "train_runtime": 56289.8015, "train_tokens_per_second": 10706.154 }, { "epoch": 0.9853891731753299, "grad_norm": 0.8040110864470087, "learning_rate": 5.115271768306745e-06, "loss": 0.3638998746871948, "num_input_tokens_seen": 602848320, "step": 14635, "train_runtime": 56308.5942, "train_tokens_per_second": 10706.151 }, { "epoch": 0.9857258281712901, "grad_norm": 0.8739385041628531, "learning_rate": 5.112628372919485e-06, "loss": 0.3805741310119629, "num_input_tokens_seen": 603053584, "step": 14640, "train_runtime": 56327.7754, "train_tokens_per_second": 10706.149 }, { "epoch": 0.9860624831672502, "grad_norm": 0.6873790483743231, "learning_rate": 5.1099849460360595e-06, "loss": 0.3526569128036499, "num_input_tokens_seen": 603240376, "step": 14645, "train_runtime": 56346.6424, "train_tokens_per_second": 10705.88 }, { "epoch": 0.9863991381632103, "grad_norm": 0.630945038855212, "learning_rate": 5.107341488395695e-06, "loss": 0.3388943910598755, "num_input_tokens_seen": 603450256, "step": 14650, "train_runtime": 56366.951, "train_tokens_per_second": 10705.746 }, { "epoch": 0.9867357931591705, "grad_norm": 0.7236725003116389, "learning_rate": 5.104698000737626e-06, "loss": 0.37667367458343504, "num_input_tokens_seen": 603661120, "step": 14655, "train_runtime": 56387.8323, "train_tokens_per_second": 10705.521 }, { "epoch": 0.9870724481551306, "grad_norm": 0.698395141139058, "learning_rate": 5.102054483801094e-06, "loss": 0.38927767276763914, "num_input_tokens_seen": 603876728, "step": 14660, "train_runtime": 56407.516, "train_tokens_per_second": 10705.608 }, { "epoch": 0.9874091031510908, "grad_norm": 0.6244400377622477, "learning_rate": 5.099410938325351e-06, "loss": 0.37406167984008787, "num_input_tokens_seen": 604089360, "step": 14665, "train_runtime": 56425.5919, "train_tokens_per_second": 10705.946 }, { "epoch": 0.9877457581470509, "grad_norm": 0.73537554971377, "learning_rate": 5.096767365049657e-06, "loss": 0.3575319766998291, "num_input_tokens_seen": 604284328, "step": 14670, "train_runtime": 56445.4663, "train_tokens_per_second": 10705.631 }, { "epoch": 0.988082413143011, "grad_norm": 0.6320372513262975, "learning_rate": 5.094123764713277e-06, "loss": 0.33565773963928225, "num_input_tokens_seen": 604500464, "step": 14675, "train_runtime": 56464.2164, "train_tokens_per_second": 10705.904 }, { "epoch": 0.9884190681389712, "grad_norm": 0.7107710723034006, "learning_rate": 5.091480138055487e-06, "loss": 0.3637369155883789, "num_input_tokens_seen": 604714912, "step": 14680, "train_runtime": 56481.9756, "train_tokens_per_second": 10706.334 }, { "epoch": 0.9887557231349313, "grad_norm": 0.7182957576105171, "learning_rate": 5.088836485815568e-06, "loss": 0.3564146518707275, "num_input_tokens_seen": 604903144, "step": 14685, "train_runtime": 56499.9864, "train_tokens_per_second": 10706.253 }, { "epoch": 0.9890923781308915, "grad_norm": 0.6982582657137926, "learning_rate": 5.086192808732809e-06, "loss": 0.36078174114227296, "num_input_tokens_seen": 605098376, "step": 14690, "train_runtime": 56520.3639, "train_tokens_per_second": 10705.847 }, { "epoch": 0.9894290331268516, "grad_norm": 0.8081448477692238, "learning_rate": 5.083549107546505e-06, "loss": 0.36605033874511717, "num_input_tokens_seen": 605292720, "step": 14695, "train_runtime": 56539.2628, "train_tokens_per_second": 10705.706 }, { "epoch": 0.9897656881228117, "grad_norm": 0.6882334785305778, "learning_rate": 5.080905382995961e-06, "loss": 0.38703303337097167, "num_input_tokens_seen": 605507176, "step": 14700, "train_runtime": 56559.0014, "train_tokens_per_second": 10705.761 }, { "epoch": 0.9901023431187719, "grad_norm": 0.7039704837982761, "learning_rate": 5.0782616358204835e-06, "loss": 0.37345051765441895, "num_input_tokens_seen": 605713096, "step": 14705, "train_runtime": 56579.2597, "train_tokens_per_second": 10705.568 }, { "epoch": 0.990438998114732, "grad_norm": 0.8327942910134545, "learning_rate": 5.075617866759389e-06, "loss": 0.33956844806671144, "num_input_tokens_seen": 605911952, "step": 14710, "train_runtime": 56597.841, "train_tokens_per_second": 10705.567 }, { "epoch": 0.9907756531106922, "grad_norm": 0.6950474338486041, "learning_rate": 5.0729740765519995e-06, "loss": 0.4124958038330078, "num_input_tokens_seen": 606114048, "step": 14715, "train_runtime": 56617.5922, "train_tokens_per_second": 10705.401 }, { "epoch": 0.9911123081066523, "grad_norm": 0.7428811795463044, "learning_rate": 5.070330265937643e-06, "loss": 0.36759328842163086, "num_input_tokens_seen": 606311120, "step": 14720, "train_runtime": 56635.4751, "train_tokens_per_second": 10705.501 }, { "epoch": 0.9914489631026124, "grad_norm": 0.6640290681767811, "learning_rate": 5.067686435655651e-06, "loss": 0.3904300928115845, "num_input_tokens_seen": 606523448, "step": 14725, "train_runtime": 56655.3228, "train_tokens_per_second": 10705.498 }, { "epoch": 0.9917856180985726, "grad_norm": 0.7144452462843699, "learning_rate": 5.065042586445363e-06, "loss": 0.3901395797729492, "num_input_tokens_seen": 606715704, "step": 14730, "train_runtime": 56673.5902, "train_tokens_per_second": 10705.44 }, { "epoch": 0.9921222730945327, "grad_norm": 0.7437082164872872, "learning_rate": 5.0623987190461245e-06, "loss": 0.3133833646774292, "num_input_tokens_seen": 606910776, "step": 14735, "train_runtime": 56693.9563, "train_tokens_per_second": 10705.035 }, { "epoch": 0.9924589280904929, "grad_norm": 0.7284444341918279, "learning_rate": 5.059754834197281e-06, "loss": 0.38290820121765134, "num_input_tokens_seen": 607114104, "step": 14740, "train_runtime": 56713.9798, "train_tokens_per_second": 10704.84 }, { "epoch": 0.992795583086453, "grad_norm": 0.7799798558131211, "learning_rate": 5.05711093263819e-06, "loss": 0.3291158199310303, "num_input_tokens_seen": 607317736, "step": 14745, "train_runtime": 56732.3736, "train_tokens_per_second": 10704.959 }, { "epoch": 0.9931322380824131, "grad_norm": 0.7534711403558795, "learning_rate": 5.054467015108208e-06, "loss": 0.37997732162475584, "num_input_tokens_seen": 607534824, "step": 14750, "train_runtime": 56751.7476, "train_tokens_per_second": 10705.13 }, { "epoch": 0.9934688930783733, "grad_norm": 0.8743426571205551, "learning_rate": 5.051823082346701e-06, "loss": 0.3781935453414917, "num_input_tokens_seen": 607739056, "step": 14755, "train_runtime": 56770.606, "train_tokens_per_second": 10705.171 }, { "epoch": 0.9938055480743334, "grad_norm": 0.7120255403387951, "learning_rate": 5.049179135093033e-06, "loss": 0.3659658670425415, "num_input_tokens_seen": 607951768, "step": 14760, "train_runtime": 56788.3194, "train_tokens_per_second": 10705.578 }, { "epoch": 0.9941422030702936, "grad_norm": 0.6516925472685802, "learning_rate": 5.046535174086575e-06, "loss": 0.3803450584411621, "num_input_tokens_seen": 608154112, "step": 14765, "train_runtime": 56808.5233, "train_tokens_per_second": 10705.332 }, { "epoch": 0.9944788580662537, "grad_norm": 0.8528302832963136, "learning_rate": 5.043891200066706e-06, "loss": 0.3650444507598877, "num_input_tokens_seen": 608359216, "step": 14770, "train_runtime": 56829.0975, "train_tokens_per_second": 10705.066 }, { "epoch": 0.9948155130622138, "grad_norm": 0.630694973157622, "learning_rate": 5.041247213772802e-06, "loss": 0.3622326374053955, "num_input_tokens_seen": 608572576, "step": 14775, "train_runtime": 56847.8567, "train_tokens_per_second": 10705.286 }, { "epoch": 0.995152168058174, "grad_norm": 0.8531757388180848, "learning_rate": 5.038603215944247e-06, "loss": 0.3724282026290894, "num_input_tokens_seen": 608759480, "step": 14780, "train_runtime": 56866.795, "train_tokens_per_second": 10705.008 }, { "epoch": 0.9954888230541341, "grad_norm": 0.6779572396937793, "learning_rate": 5.0359592073204254e-06, "loss": 0.3464805126190186, "num_input_tokens_seen": 608962320, "step": 14785, "train_runtime": 56885.9976, "train_tokens_per_second": 10704.96 }, { "epoch": 0.9958254780500942, "grad_norm": 0.7606085692011485, "learning_rate": 5.033315188640725e-06, "loss": 0.35943586826324464, "num_input_tokens_seen": 609177584, "step": 14790, "train_runtime": 56905.778, "train_tokens_per_second": 10705.022 }, { "epoch": 0.9961621330460544, "grad_norm": 0.6422926943629005, "learning_rate": 5.03067116064454e-06, "loss": 0.3481135368347168, "num_input_tokens_seen": 609387392, "step": 14795, "train_runtime": 56924.2521, "train_tokens_per_second": 10705.233 }, { "epoch": 0.9964987880420145, "grad_norm": 0.7136822972818775, "learning_rate": 5.028027124071262e-06, "loss": 0.36469211578369143, "num_input_tokens_seen": 609583008, "step": 14800, "train_runtime": 56942.8495, "train_tokens_per_second": 10705.172 }, { "epoch": 0.9968354430379747, "grad_norm": 0.6308772658361012, "learning_rate": 5.025383079660289e-06, "loss": 0.35090069770812987, "num_input_tokens_seen": 609799104, "step": 14805, "train_runtime": 56961.6538, "train_tokens_per_second": 10705.432 }, { "epoch": 0.9971720980339348, "grad_norm": 0.6538983392063097, "learning_rate": 5.0227390281510166e-06, "loss": 0.3678788661956787, "num_input_tokens_seen": 610008352, "step": 14810, "train_runtime": 56980.4252, "train_tokens_per_second": 10705.577 }, { "epoch": 0.997508753029895, "grad_norm": 0.6616083504141536, "learning_rate": 5.020094970282849e-06, "loss": 0.3645080804824829, "num_input_tokens_seen": 610200928, "step": 14815, "train_runtime": 57001.4206, "train_tokens_per_second": 10705.013 }, { "epoch": 0.9978454080258551, "grad_norm": 0.6943978104692302, "learning_rate": 5.017450906795187e-06, "loss": 0.3674218416213989, "num_input_tokens_seen": 610412192, "step": 14820, "train_runtime": 57019.2807, "train_tokens_per_second": 10705.365 }, { "epoch": 0.9981820630218152, "grad_norm": 0.7113496576456626, "learning_rate": 5.014806838427434e-06, "loss": 0.36234872341156005, "num_input_tokens_seen": 610605152, "step": 14825, "train_runtime": 57039.2611, "train_tokens_per_second": 10704.998 }, { "epoch": 0.9985187180177754, "grad_norm": 0.6683020145479035, "learning_rate": 5.0121627659189964e-06, "loss": 0.36649155616760254, "num_input_tokens_seen": 610819640, "step": 14830, "train_runtime": 57057.3846, "train_tokens_per_second": 10705.356 }, { "epoch": 0.9988553730137355, "grad_norm": 0.6327222388298479, "learning_rate": 5.009518690009281e-06, "loss": 0.35632028579711916, "num_input_tokens_seen": 611017248, "step": 14835, "train_runtime": 57077.6805, "train_tokens_per_second": 10705.012 }, { "epoch": 0.9991920280096956, "grad_norm": 0.7356753639428016, "learning_rate": 5.006874611437692e-06, "loss": 0.384340500831604, "num_input_tokens_seen": 611228440, "step": 14840, "train_runtime": 57097.1994, "train_tokens_per_second": 10705.051 }, { "epoch": 0.9995286830056558, "grad_norm": 0.6361579402782661, "learning_rate": 5.004230530943641e-06, "loss": 0.3565553903579712, "num_input_tokens_seen": 611434312, "step": 14845, "train_runtime": 57117.647, "train_tokens_per_second": 10704.823 }, { "epoch": 0.9998653380016159, "grad_norm": 0.6718218099261463, "learning_rate": 5.001586449266536e-06, "loss": 0.33271007537841796, "num_input_tokens_seen": 611645408, "step": 14850, "train_runtime": 57136.495, "train_tokens_per_second": 10704.987 }, { "epoch": 1.000201992997576, "grad_norm": 0.610271703634763, "learning_rate": 4.998942367145787e-06, "loss": 0.35215559005737307, "num_input_tokens_seen": 611853608, "step": 14855, "train_runtime": 57313.7072, "train_tokens_per_second": 10675.52 }, { "epoch": 1.0005386479935363, "grad_norm": 0.6840711290568278, "learning_rate": 4.996298285320798e-06, "loss": 0.30749900341033937, "num_input_tokens_seen": 612045808, "step": 14860, "train_runtime": 57332.2033, "train_tokens_per_second": 10675.428 }, { "epoch": 1.0008753029894963, "grad_norm": 0.7626206307089208, "learning_rate": 4.993654204530983e-06, "loss": 0.28953232765197756, "num_input_tokens_seen": 612256648, "step": 14865, "train_runtime": 57352.7546, "train_tokens_per_second": 10675.279 }, { "epoch": 1.0012119579854566, "grad_norm": 0.7302039753330539, "learning_rate": 4.99101012551575e-06, "loss": 0.31067790985107424, "num_input_tokens_seen": 612438088, "step": 14870, "train_runtime": 57372.7324, "train_tokens_per_second": 10674.724 }, { "epoch": 1.0015486129814166, "grad_norm": 0.6834349625847937, "learning_rate": 4.9883660490145075e-06, "loss": 0.31824164390563964, "num_input_tokens_seen": 612653976, "step": 14875, "train_runtime": 57391.806, "train_tokens_per_second": 10674.938 }, { "epoch": 1.0018852679773769, "grad_norm": 0.6571334950992896, "learning_rate": 4.985721975766661e-06, "loss": 0.3250891923904419, "num_input_tokens_seen": 612859408, "step": 14880, "train_runtime": 57411.2045, "train_tokens_per_second": 10674.909 }, { "epoch": 1.002221922973337, "grad_norm": 0.7207880621293253, "learning_rate": 4.983077906511619e-06, "loss": 0.32339613437652587, "num_input_tokens_seen": 613057240, "step": 14885, "train_runtime": 57430.3136, "train_tokens_per_second": 10674.802 }, { "epoch": 1.0025585779692971, "grad_norm": 0.7194992272890125, "learning_rate": 4.980433841988786e-06, "loss": 0.3061397075653076, "num_input_tokens_seen": 613265480, "step": 14890, "train_runtime": 57449.899, "train_tokens_per_second": 10674.788 }, { "epoch": 1.0028952329652572, "grad_norm": 0.705543317483432, "learning_rate": 4.977789782937568e-06, "loss": 0.3100464344024658, "num_input_tokens_seen": 613478256, "step": 14895, "train_runtime": 57467.9724, "train_tokens_per_second": 10675.133 }, { "epoch": 1.0032318879612174, "grad_norm": 0.7099348292765533, "learning_rate": 4.975145730097364e-06, "loss": 0.3269608497619629, "num_input_tokens_seen": 613672912, "step": 14900, "train_runtime": 57487.5707, "train_tokens_per_second": 10674.88 }, { "epoch": 1.0035685429571775, "grad_norm": 0.6536442877111645, "learning_rate": 4.97250168420758e-06, "loss": 0.3128445863723755, "num_input_tokens_seen": 613873552, "step": 14905, "train_runtime": 57506.919, "train_tokens_per_second": 10674.777 }, { "epoch": 1.0039051979531377, "grad_norm": 0.7042508205408685, "learning_rate": 4.96985764600761e-06, "loss": 0.3117003679275513, "num_input_tokens_seen": 614089992, "step": 14910, "train_runtime": 57527.7473, "train_tokens_per_second": 10674.675 }, { "epoch": 1.0042418529490977, "grad_norm": 0.6625875386764687, "learning_rate": 4.967213616236855e-06, "loss": 0.3231248617172241, "num_input_tokens_seen": 614287976, "step": 14915, "train_runtime": 57547.0369, "train_tokens_per_second": 10674.537 }, { "epoch": 1.004578507945058, "grad_norm": 1.0355931582354927, "learning_rate": 4.964569595634706e-06, "loss": 0.3227235317230225, "num_input_tokens_seen": 614496552, "step": 14920, "train_runtime": 57565.5166, "train_tokens_per_second": 10674.734 }, { "epoch": 1.004915162941018, "grad_norm": 0.7073776417441348, "learning_rate": 4.961925584940559e-06, "loss": 0.3356854200363159, "num_input_tokens_seen": 614710320, "step": 14925, "train_runtime": 57583.878, "train_tokens_per_second": 10675.042 }, { "epoch": 1.0052518179369783, "grad_norm": 0.7131358864336803, "learning_rate": 4.959281584893799e-06, "loss": 0.284328556060791, "num_input_tokens_seen": 614911096, "step": 14930, "train_runtime": 57603.0191, "train_tokens_per_second": 10674.98 }, { "epoch": 1.0055884729329383, "grad_norm": 0.704862839358786, "learning_rate": 4.956637596233814e-06, "loss": 0.3170325756072998, "num_input_tokens_seen": 615101024, "step": 14935, "train_runtime": 57621.2735, "train_tokens_per_second": 10674.895 }, { "epoch": 1.0059251279288985, "grad_norm": 0.7339050638817762, "learning_rate": 4.953993619699986e-06, "loss": 0.29060404300689696, "num_input_tokens_seen": 615309248, "step": 14940, "train_runtime": 57639.8998, "train_tokens_per_second": 10675.058 }, { "epoch": 1.0062617829248586, "grad_norm": 0.6963602300430833, "learning_rate": 4.951349656031698e-06, "loss": 0.30392885208129883, "num_input_tokens_seen": 615509912, "step": 14945, "train_runtime": 57658.4561, "train_tokens_per_second": 10675.102 }, { "epoch": 1.0065984379208188, "grad_norm": 0.7165956773437578, "learning_rate": 4.948705705968322e-06, "loss": 0.3149674654006958, "num_input_tokens_seen": 615722160, "step": 14950, "train_runtime": 57676.2424, "train_tokens_per_second": 10675.49 }, { "epoch": 1.0069350929167789, "grad_norm": 0.6599266096290317, "learning_rate": 4.946061770249233e-06, "loss": 0.31733250617980957, "num_input_tokens_seen": 615929472, "step": 14955, "train_runtime": 57695.8539, "train_tokens_per_second": 10675.455 }, { "epoch": 1.007271747912739, "grad_norm": 0.7356435312032172, "learning_rate": 4.9434178496137955e-06, "loss": 0.33478143215179446, "num_input_tokens_seen": 616134576, "step": 14960, "train_runtime": 57713.8588, "train_tokens_per_second": 10675.678 }, { "epoch": 1.0076084029086991, "grad_norm": 0.6013444728443054, "learning_rate": 4.940773944801378e-06, "loss": 0.31310837268829345, "num_input_tokens_seen": 616340200, "step": 14965, "train_runtime": 57732.418, "train_tokens_per_second": 10675.808 }, { "epoch": 1.0079450579046594, "grad_norm": 0.8131116194533932, "learning_rate": 4.938130056551337e-06, "loss": 0.329771089553833, "num_input_tokens_seen": 616541552, "step": 14970, "train_runtime": 57752.9936, "train_tokens_per_second": 10675.491 }, { "epoch": 1.0082817129006194, "grad_norm": 0.6757604550849876, "learning_rate": 4.9354861856030305e-06, "loss": 0.3262836456298828, "num_input_tokens_seen": 616749360, "step": 14975, "train_runtime": 57771.7574, "train_tokens_per_second": 10675.621 }, { "epoch": 1.0086183678965797, "grad_norm": 0.7279061308576351, "learning_rate": 4.932842332695803e-06, "loss": 0.2872582674026489, "num_input_tokens_seen": 616941392, "step": 14980, "train_runtime": 57790.1831, "train_tokens_per_second": 10675.54 }, { "epoch": 1.0089550228925397, "grad_norm": 0.6620529933220821, "learning_rate": 4.9301984985690055e-06, "loss": 0.3174774169921875, "num_input_tokens_seen": 617160792, "step": 14985, "train_runtime": 57808.8699, "train_tokens_per_second": 10675.884 }, { "epoch": 1.0092916778885, "grad_norm": 0.7665789692328799, "learning_rate": 4.927554683961974e-06, "loss": 0.3313608169555664, "num_input_tokens_seen": 617358096, "step": 14990, "train_runtime": 57827.1825, "train_tokens_per_second": 10675.915 }, { "epoch": 1.00962833288446, "grad_norm": 0.690212056792821, "learning_rate": 4.924910889614046e-06, "loss": 0.30544109344482423, "num_input_tokens_seen": 617564760, "step": 14995, "train_runtime": 57845.6285, "train_tokens_per_second": 10676.083 }, { "epoch": 1.0099649878804202, "grad_norm": 0.7057148228032155, "learning_rate": 4.922267116264546e-06, "loss": 0.3249383449554443, "num_input_tokens_seen": 617761496, "step": 15000, "train_runtime": 57863.2917, "train_tokens_per_second": 10676.225 }, { "epoch": 1.0103016428763802, "grad_norm": 0.7837560343022473, "learning_rate": 4.919623364652801e-06, "loss": 0.3085649490356445, "num_input_tokens_seen": 617965016, "step": 15005, "train_runtime": 57883.3148, "train_tokens_per_second": 10676.047 }, { "epoch": 1.0106382978723405, "grad_norm": 0.7259711542263615, "learning_rate": 4.916979635518124e-06, "loss": 0.3163361787796021, "num_input_tokens_seen": 618157432, "step": 15010, "train_runtime": 57901.5341, "train_tokens_per_second": 10676.011 }, { "epoch": 1.0109749528683005, "grad_norm": 0.7007433726221068, "learning_rate": 4.914335929599828e-06, "loss": 0.31771092414855956, "num_input_tokens_seen": 618369480, "step": 15015, "train_runtime": 57921.203, "train_tokens_per_second": 10676.047 }, { "epoch": 1.0113116078642608, "grad_norm": 0.7251186406472598, "learning_rate": 4.9116922476372155e-06, "loss": 0.3217296600341797, "num_input_tokens_seen": 618578520, "step": 15020, "train_runtime": 57941.4695, "train_tokens_per_second": 10675.92 }, { "epoch": 1.0116482628602208, "grad_norm": 0.7935461101162886, "learning_rate": 4.909048590369586e-06, "loss": 0.32212061882019044, "num_input_tokens_seen": 618783360, "step": 15025, "train_runtime": 57959.8323, "train_tokens_per_second": 10676.072 }, { "epoch": 1.011984917856181, "grad_norm": 0.6748024101717329, "learning_rate": 4.906404958536227e-06, "loss": 0.314815092086792, "num_input_tokens_seen": 618996592, "step": 15030, "train_runtime": 57979.9673, "train_tokens_per_second": 10676.042 }, { "epoch": 1.012321572852141, "grad_norm": 0.6914411620573991, "learning_rate": 4.903761352876422e-06, "loss": 0.31631147861480713, "num_input_tokens_seen": 619185024, "step": 15035, "train_runtime": 57999.57, "train_tokens_per_second": 10675.683 }, { "epoch": 1.0126582278481013, "grad_norm": 0.831177232005523, "learning_rate": 4.9011177741294485e-06, "loss": 0.32747721672058105, "num_input_tokens_seen": 619382952, "step": 15040, "train_runtime": 58018.4751, "train_tokens_per_second": 10675.616 }, { "epoch": 1.0129948828440614, "grad_norm": 0.6549194178653891, "learning_rate": 4.898474223034576e-06, "loss": 0.3180050849914551, "num_input_tokens_seen": 619599416, "step": 15045, "train_runtime": 58037.4136, "train_tokens_per_second": 10675.862 }, { "epoch": 1.0133315378400216, "grad_norm": 0.676679640643212, "learning_rate": 4.895830700331061e-06, "loss": 0.31315581798553466, "num_input_tokens_seen": 619796600, "step": 15050, "train_runtime": 58057.0492, "train_tokens_per_second": 10675.648 }, { "epoch": 1.0136681928359816, "grad_norm": 0.7249578782714352, "learning_rate": 4.893187206758158e-06, "loss": 0.3082882881164551, "num_input_tokens_seen": 620007808, "step": 15055, "train_runtime": 58075.8907, "train_tokens_per_second": 10675.821 }, { "epoch": 1.014004847831942, "grad_norm": 0.759499219240117, "learning_rate": 4.890543743055115e-06, "loss": 0.3018385410308838, "num_input_tokens_seen": 620213576, "step": 15060, "train_runtime": 58095.7061, "train_tokens_per_second": 10675.721 }, { "epoch": 1.014341502827902, "grad_norm": 1.0340943131096245, "learning_rate": 4.887900309961163e-06, "loss": 0.31733226776123047, "num_input_tokens_seen": 620419976, "step": 15065, "train_runtime": 58113.2284, "train_tokens_per_second": 10676.054 }, { "epoch": 1.0146781578238622, "grad_norm": 0.6885143232805416, "learning_rate": 4.885256908215532e-06, "loss": 0.32682433128356936, "num_input_tokens_seen": 620626248, "step": 15070, "train_runtime": 58130.6565, "train_tokens_per_second": 10676.402 }, { "epoch": 1.0150148128198222, "grad_norm": 0.7933902126693406, "learning_rate": 4.88261353855744e-06, "loss": 0.3060291767120361, "num_input_tokens_seen": 620838872, "step": 15075, "train_runtime": 58150.8289, "train_tokens_per_second": 10676.355 }, { "epoch": 1.0153514678157824, "grad_norm": 0.6487898526806717, "learning_rate": 4.8799702017261e-06, "loss": 0.2838993310928345, "num_input_tokens_seen": 621042312, "step": 15080, "train_runtime": 58170.5003, "train_tokens_per_second": 10676.242 }, { "epoch": 1.0156881228117425, "grad_norm": 0.8595013242591935, "learning_rate": 4.877326898460709e-06, "loss": 0.3182201385498047, "num_input_tokens_seen": 621243576, "step": 15085, "train_runtime": 58190.4697, "train_tokens_per_second": 10676.036 }, { "epoch": 1.0160247778077027, "grad_norm": 0.6870037235712246, "learning_rate": 4.87468362950046e-06, "loss": 0.28493537902832033, "num_input_tokens_seen": 621453760, "step": 15090, "train_runtime": 58207.9333, "train_tokens_per_second": 10676.444 }, { "epoch": 1.0163614328036628, "grad_norm": 0.7142884148261331, "learning_rate": 4.872040395584533e-06, "loss": 0.3081677436828613, "num_input_tokens_seen": 621651336, "step": 15095, "train_runtime": 58227.2326, "train_tokens_per_second": 10676.299 }, { "epoch": 1.016698087799623, "grad_norm": 0.8390649784218943, "learning_rate": 4.869397197452104e-06, "loss": 0.2806903123855591, "num_input_tokens_seen": 621859192, "step": 15100, "train_runtime": 58246.6449, "train_tokens_per_second": 10676.309 }, { "epoch": 1.017034742795583, "grad_norm": 0.8782652648851181, "learning_rate": 4.866754035842329e-06, "loss": 0.30269129276275636, "num_input_tokens_seen": 622066296, "step": 15105, "train_runtime": 58265.6549, "train_tokens_per_second": 10676.38 }, { "epoch": 1.0173713977915433, "grad_norm": 0.7342721161452543, "learning_rate": 4.8641109114943666e-06, "loss": 0.2999631404876709, "num_input_tokens_seen": 622268128, "step": 15110, "train_runtime": 58285.162, "train_tokens_per_second": 10676.27 }, { "epoch": 1.0177080527875033, "grad_norm": 0.6672759635487873, "learning_rate": 4.861467825147352e-06, "loss": 0.31626410484313966, "num_input_tokens_seen": 622474944, "step": 15115, "train_runtime": 58303.4449, "train_tokens_per_second": 10676.469 }, { "epoch": 1.0180447077834636, "grad_norm": 0.6955661880772541, "learning_rate": 4.858824777540419e-06, "loss": 0.29726996421813967, "num_input_tokens_seen": 622681944, "step": 15120, "train_runtime": 58324.9459, "train_tokens_per_second": 10676.083 }, { "epoch": 1.0183813627794236, "grad_norm": 0.6842617966460907, "learning_rate": 4.856181769412686e-06, "loss": 0.30617828369140626, "num_input_tokens_seen": 622883568, "step": 15125, "train_runtime": 58344.4955, "train_tokens_per_second": 10675.961 }, { "epoch": 1.0187180177753838, "grad_norm": 0.7855523403738961, "learning_rate": 4.8535388015032644e-06, "loss": 0.3040048599243164, "num_input_tokens_seen": 623082200, "step": 15130, "train_runtime": 58362.9043, "train_tokens_per_second": 10675.997 }, { "epoch": 1.0190546727713439, "grad_norm": 0.6561933588696209, "learning_rate": 4.850895874551248e-06, "loss": 0.32374637126922606, "num_input_tokens_seen": 623296200, "step": 15135, "train_runtime": 58381.6853, "train_tokens_per_second": 10676.228 }, { "epoch": 1.0193913277673041, "grad_norm": 0.6514572008455879, "learning_rate": 4.848252989295726e-06, "loss": 0.32893905639648435, "num_input_tokens_seen": 623486712, "step": 15140, "train_runtime": 58400.9746, "train_tokens_per_second": 10675.964 }, { "epoch": 1.0197279827632642, "grad_norm": 0.6971853867558757, "learning_rate": 4.845610146475771e-06, "loss": 0.2984177112579346, "num_input_tokens_seen": 623694080, "step": 15145, "train_runtime": 58419.7709, "train_tokens_per_second": 10676.079 }, { "epoch": 1.0200646377592244, "grad_norm": 0.7448558726437773, "learning_rate": 4.842967346830447e-06, "loss": 0.29785990715026855, "num_input_tokens_seen": 623903104, "step": 15150, "train_runtime": 58439.3398, "train_tokens_per_second": 10676.081 }, { "epoch": 1.0204012927551844, "grad_norm": 0.777376130629867, "learning_rate": 4.840324591098803e-06, "loss": 0.3105461597442627, "num_input_tokens_seen": 624102224, "step": 15155, "train_runtime": 58458.6376, "train_tokens_per_second": 10675.963 }, { "epoch": 1.0207379477511447, "grad_norm": 0.728817079933933, "learning_rate": 4.83768188001988e-06, "loss": 0.3103981018066406, "num_input_tokens_seen": 624296912, "step": 15160, "train_runtime": 58477.5878, "train_tokens_per_second": 10675.832 }, { "epoch": 1.0210746027471047, "grad_norm": 0.7579273772642011, "learning_rate": 4.835039214332699e-06, "loss": 0.30444438457489015, "num_input_tokens_seen": 624491736, "step": 15165, "train_runtime": 58497.8839, "train_tokens_per_second": 10675.459 }, { "epoch": 1.021411257743065, "grad_norm": 0.6768885294357037, "learning_rate": 4.832396594776277e-06, "loss": 0.3052684783935547, "num_input_tokens_seen": 624702920, "step": 15170, "train_runtime": 58518.6911, "train_tokens_per_second": 10675.272 }, { "epoch": 1.021747912739025, "grad_norm": 0.720002198375251, "learning_rate": 4.82975402208961e-06, "loss": 0.2951354026794434, "num_input_tokens_seen": 624909328, "step": 15175, "train_runtime": 58538.8665, "train_tokens_per_second": 10675.118 }, { "epoch": 1.0220845677349852, "grad_norm": 0.7183980643887784, "learning_rate": 4.827111497011692e-06, "loss": 0.2903998613357544, "num_input_tokens_seen": 625132008, "step": 15180, "train_runtime": 58558.1623, "train_tokens_per_second": 10675.403 }, { "epoch": 1.0224212227309453, "grad_norm": 0.768444512270142, "learning_rate": 4.82446902028149e-06, "loss": 0.3113518953323364, "num_input_tokens_seen": 625339880, "step": 15185, "train_runtime": 58576.9799, "train_tokens_per_second": 10675.523 }, { "epoch": 1.0227578777269055, "grad_norm": 0.719712526095045, "learning_rate": 4.821826592637968e-06, "loss": 0.3204931735992432, "num_input_tokens_seen": 625544592, "step": 15190, "train_runtime": 58596.0436, "train_tokens_per_second": 10675.543 }, { "epoch": 1.0230945327228655, "grad_norm": 0.682964153490895, "learning_rate": 4.8191842148200694e-06, "loss": 0.30363361835479735, "num_input_tokens_seen": 625760448, "step": 15195, "train_runtime": 58614.25, "train_tokens_per_second": 10675.91 }, { "epoch": 1.0234311877188258, "grad_norm": 0.6938220934145677, "learning_rate": 4.8165418875667315e-06, "loss": 0.29697480201721194, "num_input_tokens_seen": 625976736, "step": 15200, "train_runtime": 58632.8896, "train_tokens_per_second": 10676.205 }, { "epoch": 1.0237678427147858, "grad_norm": 0.6747572174927273, "learning_rate": 4.813899611616867e-06, "loss": 0.32530572414398196, "num_input_tokens_seen": 626182328, "step": 15205, "train_runtime": 58650.7882, "train_tokens_per_second": 10676.452 }, { "epoch": 1.024104497710746, "grad_norm": 0.8327391234821511, "learning_rate": 4.8112573877093855e-06, "loss": 0.30452680587768555, "num_input_tokens_seen": 626400488, "step": 15210, "train_runtime": 58670.6831, "train_tokens_per_second": 10676.55 }, { "epoch": 1.024441152706706, "grad_norm": 0.7029148580216197, "learning_rate": 4.808615216583171e-06, "loss": 0.3133798599243164, "num_input_tokens_seen": 626600760, "step": 15215, "train_runtime": 58689.403, "train_tokens_per_second": 10676.557 }, { "epoch": 1.0247778077026664, "grad_norm": 0.8295894703516061, "learning_rate": 4.805973098977102e-06, "loss": 0.3194364786148071, "num_input_tokens_seen": 626801192, "step": 15220, "train_runtime": 58708.2597, "train_tokens_per_second": 10676.542 }, { "epoch": 1.0251144626986264, "grad_norm": 0.8038137736963997, "learning_rate": 4.803331035630037e-06, "loss": 0.32619600296020507, "num_input_tokens_seen": 627015696, "step": 15225, "train_runtime": 58726.8271, "train_tokens_per_second": 10676.819 }, { "epoch": 1.0254511176945866, "grad_norm": 0.8537458939420858, "learning_rate": 4.800689027280822e-06, "loss": 0.2961438179016113, "num_input_tokens_seen": 627217232, "step": 15230, "train_runtime": 58745.0667, "train_tokens_per_second": 10676.935 }, { "epoch": 1.0257877726905467, "grad_norm": 0.7290895741264032, "learning_rate": 4.798047074668283e-06, "loss": 0.29620654582977296, "num_input_tokens_seen": 627422488, "step": 15235, "train_runtime": 58764.2852, "train_tokens_per_second": 10676.936 }, { "epoch": 1.026124427686507, "grad_norm": 0.6485334978666633, "learning_rate": 4.795405178531236e-06, "loss": 0.2925023794174194, "num_input_tokens_seen": 627620368, "step": 15240, "train_runtime": 58781.8891, "train_tokens_per_second": 10677.104 }, { "epoch": 1.026461082682467, "grad_norm": 0.71481770446126, "learning_rate": 4.792763339608478e-06, "loss": 0.3122455596923828, "num_input_tokens_seen": 627816416, "step": 15245, "train_runtime": 58801.6854, "train_tokens_per_second": 10676.844 }, { "epoch": 1.0267977376784272, "grad_norm": 0.7239386509946639, "learning_rate": 4.790121558638793e-06, "loss": 0.27198450565338134, "num_input_tokens_seen": 628025016, "step": 15250, "train_runtime": 58822.2066, "train_tokens_per_second": 10676.665 }, { "epoch": 1.0271343926743872, "grad_norm": 0.6752357379412757, "learning_rate": 4.787479836360944e-06, "loss": 0.332152271270752, "num_input_tokens_seen": 628226848, "step": 15255, "train_runtime": 58840.5783, "train_tokens_per_second": 10676.762 }, { "epoch": 1.0274710476703475, "grad_norm": 0.6948244474153292, "learning_rate": 4.784838173513682e-06, "loss": 0.30771851539611816, "num_input_tokens_seen": 628432368, "step": 15260, "train_runtime": 58860.7724, "train_tokens_per_second": 10676.591 }, { "epoch": 1.0278077026663075, "grad_norm": 0.7864255733604992, "learning_rate": 4.782196570835737e-06, "loss": 0.30431513786315917, "num_input_tokens_seen": 628644984, "step": 15265, "train_runtime": 58879.0128, "train_tokens_per_second": 10676.894 }, { "epoch": 1.0281443576622677, "grad_norm": 0.7575211247649475, "learning_rate": 4.779555029065827e-06, "loss": 0.2964078426361084, "num_input_tokens_seen": 628835256, "step": 15270, "train_runtime": 58899.7574, "train_tokens_per_second": 10676.364 }, { "epoch": 1.0284810126582278, "grad_norm": 0.7628258037058103, "learning_rate": 4.776913548942649e-06, "loss": 0.31412086486816404, "num_input_tokens_seen": 629047464, "step": 15275, "train_runtime": 58918.2742, "train_tokens_per_second": 10676.61 }, { "epoch": 1.028817667654188, "grad_norm": 0.6850909245413652, "learning_rate": 4.774272131204889e-06, "loss": 0.31585743427276614, "num_input_tokens_seen": 629261232, "step": 15280, "train_runtime": 58937.1481, "train_tokens_per_second": 10676.818 }, { "epoch": 1.029154322650148, "grad_norm": 0.816806164161717, "learning_rate": 4.7716307765912045e-06, "loss": 0.3158428430557251, "num_input_tokens_seen": 629468352, "step": 15285, "train_runtime": 58958.6201, "train_tokens_per_second": 10676.443 }, { "epoch": 1.0294909776461083, "grad_norm": 0.6608405245565523, "learning_rate": 4.768989485840246e-06, "loss": 0.32962229251861574, "num_input_tokens_seen": 629683296, "step": 15290, "train_runtime": 58978.3014, "train_tokens_per_second": 10676.525 }, { "epoch": 1.0298276326420683, "grad_norm": 0.7441258673663814, "learning_rate": 4.766348259690641e-06, "loss": 0.2963393211364746, "num_input_tokens_seen": 629892776, "step": 15295, "train_runtime": 58996.9051, "train_tokens_per_second": 10676.709 }, { "epoch": 1.0301642876380286, "grad_norm": 0.8123880335719477, "learning_rate": 4.763707098881002e-06, "loss": 0.3018446922302246, "num_input_tokens_seen": 630095152, "step": 15300, "train_runtime": 59015.7306, "train_tokens_per_second": 10676.732 }, { "epoch": 1.0305009426339886, "grad_norm": 0.7719399904018734, "learning_rate": 4.761066004149917e-06, "loss": 0.34139950275421144, "num_input_tokens_seen": 630290320, "step": 15305, "train_runtime": 59035.9679, "train_tokens_per_second": 10676.378 }, { "epoch": 1.0308375976299489, "grad_norm": 0.7568093791852845, "learning_rate": 4.758424976235964e-06, "loss": 0.32442028522491456, "num_input_tokens_seen": 630498496, "step": 15310, "train_runtime": 59055.8906, "train_tokens_per_second": 10676.302 }, { "epoch": 1.031174252625909, "grad_norm": 0.7784625601018975, "learning_rate": 4.755784015877694e-06, "loss": 0.3309309482574463, "num_input_tokens_seen": 630714120, "step": 15315, "train_runtime": 59073.7703, "train_tokens_per_second": 10676.72 }, { "epoch": 1.0315109076218691, "grad_norm": 0.7275367433426125, "learning_rate": 4.753143123813646e-06, "loss": 0.3188300132751465, "num_input_tokens_seen": 630916480, "step": 15320, "train_runtime": 59092.4115, "train_tokens_per_second": 10676.777 }, { "epoch": 1.0318475626178292, "grad_norm": 0.8011146753029957, "learning_rate": 4.7505023007823365e-06, "loss": 0.3195781230926514, "num_input_tokens_seen": 631125952, "step": 15325, "train_runtime": 59111.4767, "train_tokens_per_second": 10676.877 }, { "epoch": 1.0321842176137894, "grad_norm": 0.6428296889297274, "learning_rate": 4.747861547522264e-06, "loss": 0.29236531257629395, "num_input_tokens_seen": 631334072, "step": 15330, "train_runtime": 59129.6973, "train_tokens_per_second": 10677.106 }, { "epoch": 1.0325208726097495, "grad_norm": 0.7140296071489223, "learning_rate": 4.745220864771904e-06, "loss": 0.2912886142730713, "num_input_tokens_seen": 631528824, "step": 15335, "train_runtime": 59150.1293, "train_tokens_per_second": 10676.711 }, { "epoch": 1.0328575276057097, "grad_norm": 0.6711349379098315, "learning_rate": 4.742580253269718e-06, "loss": 0.3142076969146729, "num_input_tokens_seen": 631724528, "step": 15340, "train_runtime": 59169.3983, "train_tokens_per_second": 10676.541 }, { "epoch": 1.0331941826016697, "grad_norm": 0.7773517245072777, "learning_rate": 4.739939713754141e-06, "loss": 0.2838461399078369, "num_input_tokens_seen": 631924680, "step": 15345, "train_runtime": 59188.4471, "train_tokens_per_second": 10676.487 }, { "epoch": 1.03353083759763, "grad_norm": 0.7599904737424229, "learning_rate": 4.737299246963597e-06, "loss": 0.3014411449432373, "num_input_tokens_seen": 632124168, "step": 15350, "train_runtime": 59207.0714, "train_tokens_per_second": 10676.498 }, { "epoch": 1.03386749259359, "grad_norm": 0.6454774034791136, "learning_rate": 4.734658853636479e-06, "loss": 0.3036791801452637, "num_input_tokens_seen": 632331680, "step": 15355, "train_runtime": 59225.7302, "train_tokens_per_second": 10676.638 }, { "epoch": 1.0342041475895503, "grad_norm": 0.7454753226926998, "learning_rate": 4.732018534511167e-06, "loss": 0.3316079378128052, "num_input_tokens_seen": 632536768, "step": 15360, "train_runtime": 59245.106, "train_tokens_per_second": 10676.608 }, { "epoch": 1.0345408025855103, "grad_norm": 0.6978159492408357, "learning_rate": 4.729378290326017e-06, "loss": 0.293642258644104, "num_input_tokens_seen": 632730832, "step": 15365, "train_runtime": 59263.3819, "train_tokens_per_second": 10676.59 }, { "epoch": 1.0348774575814705, "grad_norm": 0.632407617487515, "learning_rate": 4.726738121819365e-06, "loss": 0.3180454015731812, "num_input_tokens_seen": 632935168, "step": 15370, "train_runtime": 59282.1408, "train_tokens_per_second": 10676.658 }, { "epoch": 1.0352141125774306, "grad_norm": 0.7659331625908977, "learning_rate": 4.7240980297295255e-06, "loss": 0.2777672290802002, "num_input_tokens_seen": 633133688, "step": 15375, "train_runtime": 59300.6999, "train_tokens_per_second": 10676.665 }, { "epoch": 1.0355507675733908, "grad_norm": 0.5965233271693751, "learning_rate": 4.721458014794795e-06, "loss": 0.3027809143066406, "num_input_tokens_seen": 633343032, "step": 15380, "train_runtime": 59319.2344, "train_tokens_per_second": 10676.858 }, { "epoch": 1.0358874225693508, "grad_norm": 0.7577452343439224, "learning_rate": 4.718818077753439e-06, "loss": 0.32341227531433103, "num_input_tokens_seen": 633556928, "step": 15385, "train_runtime": 59339.1218, "train_tokens_per_second": 10676.884 }, { "epoch": 1.036224077565311, "grad_norm": 0.7293627097891427, "learning_rate": 4.716178219343712e-06, "loss": 0.3141986846923828, "num_input_tokens_seen": 633758080, "step": 15390, "train_runtime": 59357.8712, "train_tokens_per_second": 10676.9 }, { "epoch": 1.0365607325612711, "grad_norm": 0.8941287524931368, "learning_rate": 4.713538440303841e-06, "loss": 0.3087383508682251, "num_input_tokens_seen": 633940632, "step": 15395, "train_runtime": 59374.7404, "train_tokens_per_second": 10676.942 }, { "epoch": 1.0368973875572314, "grad_norm": 1.5647830612134268, "learning_rate": 4.7108987413720335e-06, "loss": 0.3319809675216675, "num_input_tokens_seen": 634141144, "step": 15400, "train_runtime": 59393.9407, "train_tokens_per_second": 10676.866 }, { "epoch": 1.0372340425531914, "grad_norm": 0.8433897596577806, "learning_rate": 4.708259123286469e-06, "loss": 0.3197494029998779, "num_input_tokens_seen": 634340280, "step": 15405, "train_runtime": 59411.9503, "train_tokens_per_second": 10676.981 }, { "epoch": 1.0375706975491517, "grad_norm": 0.7083396055123552, "learning_rate": 4.7056195867853105e-06, "loss": 0.30918135643005373, "num_input_tokens_seen": 634554072, "step": 15410, "train_runtime": 59432.3691, "train_tokens_per_second": 10676.91 }, { "epoch": 1.0379073525451117, "grad_norm": 0.7131783047075806, "learning_rate": 4.702980132606696e-06, "loss": 0.28607425689697263, "num_input_tokens_seen": 634765360, "step": 15415, "train_runtime": 59451.0788, "train_tokens_per_second": 10677.104 }, { "epoch": 1.038244007541072, "grad_norm": 0.7536804989717341, "learning_rate": 4.700340761488741e-06, "loss": 0.29149224758148196, "num_input_tokens_seen": 634971552, "step": 15420, "train_runtime": 59468.5495, "train_tokens_per_second": 10677.435 }, { "epoch": 1.038580662537032, "grad_norm": 0.7086662884728577, "learning_rate": 4.6977014741695345e-06, "loss": 0.30226430892944334, "num_input_tokens_seen": 635181712, "step": 15425, "train_runtime": 59488.9297, "train_tokens_per_second": 10677.309 }, { "epoch": 1.0389173175329922, "grad_norm": 0.6930030891176153, "learning_rate": 4.69506227138715e-06, "loss": 0.3164176940917969, "num_input_tokens_seen": 635399952, "step": 15430, "train_runtime": 59510.468, "train_tokens_per_second": 10677.112 }, { "epoch": 1.0392539725289522, "grad_norm": 0.7603710303152587, "learning_rate": 4.6924231538796265e-06, "loss": 0.33755605220794677, "num_input_tokens_seen": 635610272, "step": 15435, "train_runtime": 59529.5869, "train_tokens_per_second": 10677.216 }, { "epoch": 1.0395906275249125, "grad_norm": 0.74579320106381, "learning_rate": 4.6897841223849885e-06, "loss": 0.31362740993499755, "num_input_tokens_seen": 635813592, "step": 15440, "train_runtime": 59549.1142, "train_tokens_per_second": 10677.129 }, { "epoch": 1.0399272825208725, "grad_norm": 0.7169038281080073, "learning_rate": 4.68714517764123e-06, "loss": 0.28928849697113035, "num_input_tokens_seen": 636019624, "step": 15445, "train_runtime": 59568.7343, "train_tokens_per_second": 10677.071 }, { "epoch": 1.0402639375168328, "grad_norm": 0.5901741339686147, "learning_rate": 4.684506320386327e-06, "loss": 0.286083459854126, "num_input_tokens_seen": 636216152, "step": 15450, "train_runtime": 59589.2991, "train_tokens_per_second": 10676.685 }, { "epoch": 1.0406005925127928, "grad_norm": 0.6880082154279007, "learning_rate": 4.6818675513582235e-06, "loss": 0.29574012756347656, "num_input_tokens_seen": 636427432, "step": 15455, "train_runtime": 59609.4352, "train_tokens_per_second": 10676.622 }, { "epoch": 1.040937247508753, "grad_norm": 0.7502058646097581, "learning_rate": 4.679228871294846e-06, "loss": 0.2883344888687134, "num_input_tokens_seen": 636636016, "step": 15460, "train_runtime": 59629.01, "train_tokens_per_second": 10676.616 }, { "epoch": 1.041273902504713, "grad_norm": 0.6766395377429899, "learning_rate": 4.67659028093409e-06, "loss": 0.31049370765686035, "num_input_tokens_seen": 636845256, "step": 15465, "train_runtime": 59647.9072, "train_tokens_per_second": 10676.741 }, { "epoch": 1.0416105575006733, "grad_norm": 0.9214451454621345, "learning_rate": 4.673951781013834e-06, "loss": 0.32568926811218263, "num_input_tokens_seen": 637045656, "step": 15470, "train_runtime": 59667.3094, "train_tokens_per_second": 10676.628 }, { "epoch": 1.0419472124966334, "grad_norm": 0.7007011701116822, "learning_rate": 4.67131337227192e-06, "loss": 0.3296172618865967, "num_input_tokens_seen": 637255024, "step": 15475, "train_runtime": 59685.7178, "train_tokens_per_second": 10676.843 }, { "epoch": 1.0422838674925936, "grad_norm": 0.6889160541915387, "learning_rate": 4.668675055446175e-06, "loss": 0.3181513547897339, "num_input_tokens_seen": 637458200, "step": 15480, "train_runtime": 59703.5667, "train_tokens_per_second": 10677.054 }, { "epoch": 1.0426205224885536, "grad_norm": 0.8317337932710075, "learning_rate": 4.666036831274392e-06, "loss": 0.2783323049545288, "num_input_tokens_seen": 637659072, "step": 15485, "train_runtime": 59721.8531, "train_tokens_per_second": 10677.148 }, { "epoch": 1.0429571774845139, "grad_norm": 0.708029681911493, "learning_rate": 4.663398700494346e-06, "loss": 0.3074409008026123, "num_input_tokens_seen": 637858056, "step": 15490, "train_runtime": 59742.1768, "train_tokens_per_second": 10676.847 }, { "epoch": 1.043293832480474, "grad_norm": 0.7145962069482934, "learning_rate": 4.66076066384378e-06, "loss": 0.3228140354156494, "num_input_tokens_seen": 638067392, "step": 15495, "train_runtime": 59760.9017, "train_tokens_per_second": 10677.004 }, { "epoch": 1.0436304874764342, "grad_norm": 0.7049395149772592, "learning_rate": 4.658122722060413e-06, "loss": 0.3158139228820801, "num_input_tokens_seen": 638273104, "step": 15500, "train_runtime": 59779.0316, "train_tokens_per_second": 10677.207 }, { "epoch": 1.0439671424723942, "grad_norm": 0.6918363183318254, "learning_rate": 4.655484875881935e-06, "loss": 0.32020010948181155, "num_input_tokens_seen": 638475648, "step": 15505, "train_runtime": 59799.2044, "train_tokens_per_second": 10676.992 }, { "epoch": 1.0443037974683544, "grad_norm": 0.7523538870069452, "learning_rate": 4.652847126046014e-06, "loss": 0.3372265577316284, "num_input_tokens_seen": 638660208, "step": 15510, "train_runtime": 59818.4307, "train_tokens_per_second": 10676.646 }, { "epoch": 1.0446404524643145, "grad_norm": 0.7169730289395774, "learning_rate": 4.650209473290286e-06, "loss": 0.3261427640914917, "num_input_tokens_seen": 638871216, "step": 15515, "train_runtime": 59838.0487, "train_tokens_per_second": 10676.672 }, { "epoch": 1.0449771074602747, "grad_norm": 0.7533482166381479, "learning_rate": 4.647571918352366e-06, "loss": 0.319809627532959, "num_input_tokens_seen": 639076400, "step": 15520, "train_runtime": 59858.0243, "train_tokens_per_second": 10676.537 }, { "epoch": 1.0453137624562348, "grad_norm": 0.7021952793124497, "learning_rate": 4.644934461969833e-06, "loss": 0.30494279861450196, "num_input_tokens_seen": 639287816, "step": 15525, "train_runtime": 59877.9274, "train_tokens_per_second": 10676.519 }, { "epoch": 1.045650417452195, "grad_norm": 0.6683321787801048, "learning_rate": 4.642297104880247e-06, "loss": 0.2921912670135498, "num_input_tokens_seen": 639499392, "step": 15530, "train_runtime": 59898.6001, "train_tokens_per_second": 10676.366 }, { "epoch": 1.045987072448155, "grad_norm": 0.7424556566263993, "learning_rate": 4.639659847821133e-06, "loss": 0.2972586631774902, "num_input_tokens_seen": 639702408, "step": 15535, "train_runtime": 59917.358, "train_tokens_per_second": 10676.412 }, { "epoch": 1.0463237274441153, "grad_norm": 0.701956711503253, "learning_rate": 4.6370226915299945e-06, "loss": 0.2989682912826538, "num_input_tokens_seen": 639906800, "step": 15540, "train_runtime": 59936.017, "train_tokens_per_second": 10676.499 }, { "epoch": 1.0466603824400753, "grad_norm": 0.6710050608529069, "learning_rate": 4.634385636744302e-06, "loss": 0.3108957052230835, "num_input_tokens_seen": 640122128, "step": 15545, "train_runtime": 59956.1107, "train_tokens_per_second": 10676.512 }, { "epoch": 1.0469970374360356, "grad_norm": 0.7384473586196484, "learning_rate": 4.631748684201503e-06, "loss": 0.3222243070602417, "num_input_tokens_seen": 640335888, "step": 15550, "train_runtime": 59974.2449, "train_tokens_per_second": 10676.848 }, { "epoch": 1.0473336924319956, "grad_norm": 0.741174023879348, "learning_rate": 4.629111834639008e-06, "loss": 0.3094134569168091, "num_input_tokens_seen": 640547664, "step": 15555, "train_runtime": 59991.8583, "train_tokens_per_second": 10677.243 }, { "epoch": 1.0476703474279558, "grad_norm": 0.7048348913709439, "learning_rate": 4.626475088794206e-06, "loss": 0.30411720275878906, "num_input_tokens_seen": 640756704, "step": 15560, "train_runtime": 60009.7607, "train_tokens_per_second": 10677.541 }, { "epoch": 1.0480070024239159, "grad_norm": 0.7596748843896566, "learning_rate": 4.623838447404454e-06, "loss": 0.310543417930603, "num_input_tokens_seen": 640972320, "step": 15565, "train_runtime": 60030.3434, "train_tokens_per_second": 10677.472 }, { "epoch": 1.0483436574198761, "grad_norm": 0.6694766351866445, "learning_rate": 4.621201911207082e-06, "loss": 0.2973322868347168, "num_input_tokens_seen": 641172256, "step": 15570, "train_runtime": 60048.9047, "train_tokens_per_second": 10677.501 }, { "epoch": 1.0486803124158361, "grad_norm": 0.6713082222062264, "learning_rate": 4.618565480939387e-06, "loss": 0.316133451461792, "num_input_tokens_seen": 641385048, "step": 15575, "train_runtime": 60067.0706, "train_tokens_per_second": 10677.815 }, { "epoch": 1.0490169674117964, "grad_norm": 0.7922112636047375, "learning_rate": 4.6159291573386395e-06, "loss": 0.3171581745147705, "num_input_tokens_seen": 641590800, "step": 15580, "train_runtime": 60085.2119, "train_tokens_per_second": 10678.015 }, { "epoch": 1.0493536224077564, "grad_norm": 0.67518842219529, "learning_rate": 4.613292941142077e-06, "loss": 0.3055455207824707, "num_input_tokens_seen": 641799248, "step": 15585, "train_runtime": 60106.1369, "train_tokens_per_second": 10677.766 }, { "epoch": 1.0496902774037167, "grad_norm": 0.7295407908732446, "learning_rate": 4.610656833086912e-06, "loss": 0.3217565298080444, "num_input_tokens_seen": 641996584, "step": 15590, "train_runtime": 60125.0536, "train_tokens_per_second": 10677.688 }, { "epoch": 1.0500269323996767, "grad_norm": 0.9110489398445166, "learning_rate": 4.60802083391032e-06, "loss": 0.35767498016357424, "num_input_tokens_seen": 642203152, "step": 15595, "train_runtime": 60143.2848, "train_tokens_per_second": 10677.886 }, { "epoch": 1.050363587395637, "grad_norm": 0.7679348529420543, "learning_rate": 4.605384944349454e-06, "loss": 0.2936492919921875, "num_input_tokens_seen": 642401304, "step": 15600, "train_runtime": 60161.9614, "train_tokens_per_second": 10677.865 }, { "epoch": 1.050700242391597, "grad_norm": 0.6827591063014589, "learning_rate": 4.602749165141429e-06, "loss": 0.29890153408050535, "num_input_tokens_seen": 642593720, "step": 15605, "train_runtime": 60181.3328, "train_tokens_per_second": 10677.625 }, { "epoch": 1.0510368973875572, "grad_norm": 0.720723293704013, "learning_rate": 4.600113497023333e-06, "loss": 0.32755773067474364, "num_input_tokens_seen": 642798672, "step": 15610, "train_runtime": 60201.382, "train_tokens_per_second": 10677.474 }, { "epoch": 1.0513735523835175, "grad_norm": 0.7377412909154076, "learning_rate": 4.597477940732222e-06, "loss": 0.2917536020278931, "num_input_tokens_seen": 642992888, "step": 15615, "train_runtime": 60220.9725, "train_tokens_per_second": 10677.225 }, { "epoch": 1.0517102073794775, "grad_norm": 0.7326189386475476, "learning_rate": 4.594842497005124e-06, "loss": 0.3028987407684326, "num_input_tokens_seen": 643207864, "step": 15620, "train_runtime": 60238.3579, "train_tokens_per_second": 10677.712 }, { "epoch": 1.0520468623754375, "grad_norm": 0.6653513762233874, "learning_rate": 4.5922071665790264e-06, "loss": 0.3172469139099121, "num_input_tokens_seen": 643409224, "step": 15625, "train_runtime": 60256.414, "train_tokens_per_second": 10677.855 }, { "epoch": 1.0523835173713978, "grad_norm": 0.6281998116618416, "learning_rate": 4.589571950190897e-06, "loss": 0.3156686782836914, "num_input_tokens_seen": 643625456, "step": 15630, "train_runtime": 60276.6645, "train_tokens_per_second": 10677.855 }, { "epoch": 1.052720172367358, "grad_norm": 0.6939696771683976, "learning_rate": 4.586936848577661e-06, "loss": 0.31195650100708006, "num_input_tokens_seen": 643831872, "step": 15635, "train_runtime": 60294.1653, "train_tokens_per_second": 10678.179 }, { "epoch": 1.053056827363318, "grad_norm": 0.6692045632974882, "learning_rate": 4.584301862476219e-06, "loss": 0.31540446281433104, "num_input_tokens_seen": 644036160, "step": 15640, "train_runtime": 60312.7746, "train_tokens_per_second": 10678.271 }, { "epoch": 1.053393482359278, "grad_norm": 0.7029151401796095, "learning_rate": 4.581666992623435e-06, "loss": 0.2963371753692627, "num_input_tokens_seen": 644251664, "step": 15645, "train_runtime": 60333.8244, "train_tokens_per_second": 10678.117 }, { "epoch": 1.0537301373552383, "grad_norm": 0.7556273727510064, "learning_rate": 4.579032239756144e-06, "loss": 0.3205817937850952, "num_input_tokens_seen": 644458144, "step": 15650, "train_runtime": 60351.9974, "train_tokens_per_second": 10678.323 }, { "epoch": 1.0540667923511986, "grad_norm": 0.7031620240706925, "learning_rate": 4.576397604611143e-06, "loss": 0.29947786331176757, "num_input_tokens_seen": 644666016, "step": 15655, "train_runtime": 60370.7695, "train_tokens_per_second": 10678.446 }, { "epoch": 1.0544034473471586, "grad_norm": 0.7064627822833303, "learning_rate": 4.573763087925202e-06, "loss": 0.30903234481811526, "num_input_tokens_seen": 644877640, "step": 15660, "train_runtime": 60391.7162, "train_tokens_per_second": 10678.247 }, { "epoch": 1.0547401023431189, "grad_norm": 0.7061212905973999, "learning_rate": 4.571128690435053e-06, "loss": 0.32277851104736327, "num_input_tokens_seen": 645088600, "step": 15665, "train_runtime": 60410.9547, "train_tokens_per_second": 10678.338 }, { "epoch": 1.055076757339079, "grad_norm": 0.7996608213663704, "learning_rate": 4.568494412877401e-06, "loss": 0.30909976959228513, "num_input_tokens_seen": 645280064, "step": 15670, "train_runtime": 60428.4299, "train_tokens_per_second": 10678.419 }, { "epoch": 1.0554134123350392, "grad_norm": 0.768039906928747, "learning_rate": 4.565860255988908e-06, "loss": 0.31464014053344724, "num_input_tokens_seen": 645486920, "step": 15675, "train_runtime": 60447.0243, "train_tokens_per_second": 10678.556 }, { "epoch": 1.0557500673309992, "grad_norm": 0.6709725809177641, "learning_rate": 4.563226220506212e-06, "loss": 0.31235907077789304, "num_input_tokens_seen": 645709896, "step": 15680, "train_runtime": 60467.4661, "train_tokens_per_second": 10678.633 }, { "epoch": 1.0560867223269594, "grad_norm": 0.6566428573471373, "learning_rate": 4.5605923071659085e-06, "loss": 0.3162671089172363, "num_input_tokens_seen": 645910416, "step": 15685, "train_runtime": 60486.6955, "train_tokens_per_second": 10678.554 }, { "epoch": 1.0564233773229195, "grad_norm": 0.6888703046584826, "learning_rate": 4.557958516704566e-06, "loss": 0.29800236225128174, "num_input_tokens_seen": 646119208, "step": 15690, "train_runtime": 60507.0089, "train_tokens_per_second": 10678.419 }, { "epoch": 1.0567600323188797, "grad_norm": 0.7400975059251165, "learning_rate": 4.5553248498587144e-06, "loss": 0.30796308517456056, "num_input_tokens_seen": 646321656, "step": 15695, "train_runtime": 60524.7513, "train_tokens_per_second": 10678.634 }, { "epoch": 1.0570966873148397, "grad_norm": 0.7914657811553722, "learning_rate": 4.552691307364853e-06, "loss": 0.3118155002593994, "num_input_tokens_seen": 646522416, "step": 15700, "train_runtime": 60546.0437, "train_tokens_per_second": 10678.194 }, { "epoch": 1.0574333423108, "grad_norm": 0.7994993688127168, "learning_rate": 4.5500578899594375e-06, "loss": 0.33344178199768065, "num_input_tokens_seen": 646731640, "step": 15705, "train_runtime": 60565.0487, "train_tokens_per_second": 10678.298 }, { "epoch": 1.05776999730676, "grad_norm": 0.6867146426070503, "learning_rate": 4.5474245983789e-06, "loss": 0.311765718460083, "num_input_tokens_seen": 646939176, "step": 15710, "train_runtime": 60584.1146, "train_tokens_per_second": 10678.363 }, { "epoch": 1.0581066523027203, "grad_norm": 0.6604436464960569, "learning_rate": 4.54479143335963e-06, "loss": 0.29688053131103515, "num_input_tokens_seen": 647147568, "step": 15715, "train_runtime": 60603.402, "train_tokens_per_second": 10678.403 }, { "epoch": 1.0584433072986803, "grad_norm": 0.7749809715934809, "learning_rate": 4.5421583956379855e-06, "loss": 0.3241950273513794, "num_input_tokens_seen": 647347200, "step": 15720, "train_runtime": 60622.2518, "train_tokens_per_second": 10678.376 }, { "epoch": 1.0587799622946406, "grad_norm": 0.6766579723081672, "learning_rate": 4.539525485950284e-06, "loss": 0.29626595973968506, "num_input_tokens_seen": 647560504, "step": 15725, "train_runtime": 60641.2733, "train_tokens_per_second": 10678.544 }, { "epoch": 1.0591166172906006, "grad_norm": 0.9677188505789174, "learning_rate": 4.536892705032815e-06, "loss": 0.3230659008026123, "num_input_tokens_seen": 647770160, "step": 15730, "train_runtime": 60660.2889, "train_tokens_per_second": 10678.653 }, { "epoch": 1.0594532722865608, "grad_norm": 0.7633438126265327, "learning_rate": 4.534260053621821e-06, "loss": 0.2975139617919922, "num_input_tokens_seen": 647974424, "step": 15735, "train_runtime": 60679.356, "train_tokens_per_second": 10678.663 }, { "epoch": 1.0597899272825209, "grad_norm": 0.7182571042538499, "learning_rate": 4.531627532453519e-06, "loss": 0.2771912097930908, "num_input_tokens_seen": 648181472, "step": 15740, "train_runtime": 60699.6748, "train_tokens_per_second": 10678.5 }, { "epoch": 1.0601265822784811, "grad_norm": 0.6715254274656943, "learning_rate": 4.5289951422640826e-06, "loss": 0.3070959568023682, "num_input_tokens_seen": 648372784, "step": 15745, "train_runtime": 60719.2201, "train_tokens_per_second": 10678.213 }, { "epoch": 1.0604632372744411, "grad_norm": 0.7161183841717117, "learning_rate": 4.526362883789655e-06, "loss": 0.29703779220581056, "num_input_tokens_seen": 648584792, "step": 15750, "train_runtime": 60738.1894, "train_tokens_per_second": 10678.369 }, { "epoch": 1.0607998922704014, "grad_norm": 0.8195300896974722, "learning_rate": 4.5237307577663345e-06, "loss": 0.33053085803985593, "num_input_tokens_seen": 648798312, "step": 15755, "train_runtime": 60758.2966, "train_tokens_per_second": 10678.349 }, { "epoch": 1.0611365472663614, "grad_norm": 0.6313492305613048, "learning_rate": 4.52109876493019e-06, "loss": 0.30983402729034426, "num_input_tokens_seen": 649005784, "step": 15760, "train_runtime": 60778.5166, "train_tokens_per_second": 10678.21 }, { "epoch": 1.0614732022623217, "grad_norm": 0.7077721900379946, "learning_rate": 4.518466906017249e-06, "loss": 0.32857823371887207, "num_input_tokens_seen": 649206904, "step": 15765, "train_runtime": 60798.6372, "train_tokens_per_second": 10677.984 }, { "epoch": 1.0618098572582817, "grad_norm": 0.747670563951919, "learning_rate": 4.515835181763503e-06, "loss": 0.30318050384521483, "num_input_tokens_seen": 649412808, "step": 15770, "train_runtime": 60818.0877, "train_tokens_per_second": 10677.955 }, { "epoch": 1.062146512254242, "grad_norm": 0.7237679654996938, "learning_rate": 4.513203592904903e-06, "loss": 0.3131886005401611, "num_input_tokens_seen": 649618216, "step": 15775, "train_runtime": 60836.4099, "train_tokens_per_second": 10678.116 }, { "epoch": 1.062483167250202, "grad_norm": 0.6762115441117089, "learning_rate": 4.510572140177368e-06, "loss": 0.31056985855102537, "num_input_tokens_seen": 649831392, "step": 15780, "train_runtime": 60857.3587, "train_tokens_per_second": 10677.943 }, { "epoch": 1.0628198222461622, "grad_norm": 0.783388377652337, "learning_rate": 4.507940824316771e-06, "loss": 0.31093974113464357, "num_input_tokens_seen": 650038032, "step": 15785, "train_runtime": 60878.1715, "train_tokens_per_second": 10677.687 }, { "epoch": 1.0631564772421223, "grad_norm": 0.7408986154968108, "learning_rate": 4.505309646058954e-06, "loss": 0.3054028034210205, "num_input_tokens_seen": 650241136, "step": 15790, "train_runtime": 60897.353, "train_tokens_per_second": 10677.658 }, { "epoch": 1.0634931322380825, "grad_norm": 0.8213471122329621, "learning_rate": 4.502678606139716e-06, "loss": 0.2931317090988159, "num_input_tokens_seen": 650441328, "step": 15795, "train_runtime": 60916.0859, "train_tokens_per_second": 10677.661 }, { "epoch": 1.0638297872340425, "grad_norm": 0.6486298563294922, "learning_rate": 4.500047705294823e-06, "loss": 0.29173119068145753, "num_input_tokens_seen": 650650840, "step": 15800, "train_runtime": 60934.5175, "train_tokens_per_second": 10677.87 }, { "epoch": 1.0641664422300028, "grad_norm": 0.7034924956209726, "learning_rate": 4.497416944259993e-06, "loss": 0.3081763744354248, "num_input_tokens_seen": 650856424, "step": 15805, "train_runtime": 60952.7195, "train_tokens_per_second": 10678.054 }, { "epoch": 1.0645030972259628, "grad_norm": 0.7291636344218337, "learning_rate": 4.494786323770912e-06, "loss": 0.3267565488815308, "num_input_tokens_seen": 651059112, "step": 15810, "train_runtime": 60973.3896, "train_tokens_per_second": 10677.758 }, { "epoch": 1.064839752221923, "grad_norm": 0.6435984676289417, "learning_rate": 4.492155844563224e-06, "loss": 0.2984444618225098, "num_input_tokens_seen": 651269712, "step": 15815, "train_runtime": 60991.4524, "train_tokens_per_second": 10678.049 }, { "epoch": 1.065176407217883, "grad_norm": 0.740027988340077, "learning_rate": 4.489525507372537e-06, "loss": 0.3267201900482178, "num_input_tokens_seen": 651474496, "step": 15820, "train_runtime": 61010.7296, "train_tokens_per_second": 10678.032 }, { "epoch": 1.0655130622138433, "grad_norm": 0.697132192211165, "learning_rate": 4.486895312934411e-06, "loss": 0.30820024013519287, "num_input_tokens_seen": 651678016, "step": 15825, "train_runtime": 61029.7945, "train_tokens_per_second": 10678.031 }, { "epoch": 1.0658497172098034, "grad_norm": 0.7650442751678799, "learning_rate": 4.484265261984378e-06, "loss": 0.34914748668670653, "num_input_tokens_seen": 651886112, "step": 15830, "train_runtime": 61050.9266, "train_tokens_per_second": 10677.743 }, { "epoch": 1.0661863722057636, "grad_norm": 0.6709637655152838, "learning_rate": 4.4816353552579165e-06, "loss": 0.29379260540008545, "num_input_tokens_seen": 652087216, "step": 15835, "train_runtime": 61070.7535, "train_tokens_per_second": 10677.57 }, { "epoch": 1.0665230272017237, "grad_norm": 0.738724941087931, "learning_rate": 4.479005593490477e-06, "loss": 0.3147528648376465, "num_input_tokens_seen": 652293496, "step": 15840, "train_runtime": 61090.005, "train_tokens_per_second": 10677.581 }, { "epoch": 1.066859682197684, "grad_norm": 0.7050788240712254, "learning_rate": 4.476375977417461e-06, "loss": 0.28179192543029785, "num_input_tokens_seen": 652503304, "step": 15845, "train_runtime": 61110.033, "train_tokens_per_second": 10677.515 }, { "epoch": 1.067196337193644, "grad_norm": 0.7495996878135827, "learning_rate": 4.473746507774235e-06, "loss": 0.3069297790527344, "num_input_tokens_seen": 652715656, "step": 15850, "train_runtime": 61128.3012, "train_tokens_per_second": 10677.798 }, { "epoch": 1.0675329921896042, "grad_norm": 0.6601378955891697, "learning_rate": 4.471117185296117e-06, "loss": 0.28841276168823243, "num_input_tokens_seen": 652921008, "step": 15855, "train_runtime": 61147.6412, "train_tokens_per_second": 10677.779 }, { "epoch": 1.0678696471855642, "grad_norm": 0.6609362153737793, "learning_rate": 4.468488010718394e-06, "loss": 0.2853057384490967, "num_input_tokens_seen": 653115312, "step": 15860, "train_runtime": 61166.8919, "train_tokens_per_second": 10677.595 }, { "epoch": 1.0682063021815245, "grad_norm": 0.7380859437340711, "learning_rate": 4.465858984776302e-06, "loss": 0.3128810882568359, "num_input_tokens_seen": 653318792, "step": 15865, "train_runtime": 61186.1341, "train_tokens_per_second": 10677.563 }, { "epoch": 1.0685429571774845, "grad_norm": 0.7777533080591154, "learning_rate": 4.463230108205044e-06, "loss": 0.3070794105529785, "num_input_tokens_seen": 653501224, "step": 15870, "train_runtime": 61205.3681, "train_tokens_per_second": 10677.188 }, { "epoch": 1.0688796121734447, "grad_norm": 0.693604757592491, "learning_rate": 4.460601381739772e-06, "loss": 0.31386194229125974, "num_input_tokens_seen": 653709016, "step": 15875, "train_runtime": 61225.3452, "train_tokens_per_second": 10677.098 }, { "epoch": 1.0692162671694048, "grad_norm": 0.7716170844424886, "learning_rate": 4.457972806115607e-06, "loss": 0.33697099685668946, "num_input_tokens_seen": 653913528, "step": 15880, "train_runtime": 61246.7889, "train_tokens_per_second": 10676.699 }, { "epoch": 1.069552922165365, "grad_norm": 0.6205785515628511, "learning_rate": 4.455344382067616e-06, "loss": 0.3156982421875, "num_input_tokens_seen": 654117832, "step": 15885, "train_runtime": 61266.5134, "train_tokens_per_second": 10676.596 }, { "epoch": 1.069889577161325, "grad_norm": 0.72694444607797, "learning_rate": 4.452716110330832e-06, "loss": 0.31151769161224363, "num_input_tokens_seen": 654325992, "step": 15890, "train_runtime": 61284.3663, "train_tokens_per_second": 10676.883 }, { "epoch": 1.0702262321572853, "grad_norm": 0.7403821036597753, "learning_rate": 4.450087991640242e-06, "loss": 0.3120032787322998, "num_input_tokens_seen": 654519752, "step": 15895, "train_runtime": 61303.7738, "train_tokens_per_second": 10676.663 }, { "epoch": 1.0705628871532453, "grad_norm": 0.7711523230111481, "learning_rate": 4.447460026730794e-06, "loss": 0.31582136154174806, "num_input_tokens_seen": 654721480, "step": 15900, "train_runtime": 61323.2075, "train_tokens_per_second": 10676.569 }, { "epoch": 1.0708995421492056, "grad_norm": 0.7708690753341696, "learning_rate": 4.444832216337384e-06, "loss": 0.30790255069732664, "num_input_tokens_seen": 654929552, "step": 15905, "train_runtime": 61341.7662, "train_tokens_per_second": 10676.731 }, { "epoch": 1.0712361971451656, "grad_norm": 0.897402228716333, "learning_rate": 4.442204561194877e-06, "loss": 0.3093201398849487, "num_input_tokens_seen": 655135336, "step": 15910, "train_runtime": 61360.2454, "train_tokens_per_second": 10676.87 }, { "epoch": 1.0715728521411259, "grad_norm": 0.6555184149827656, "learning_rate": 4.439577062038085e-06, "loss": 0.29600112438201903, "num_input_tokens_seen": 655355016, "step": 15915, "train_runtime": 61379.0692, "train_tokens_per_second": 10677.174 }, { "epoch": 1.0719095071370859, "grad_norm": 0.705517313547825, "learning_rate": 4.436949719601782e-06, "loss": 0.3312522411346436, "num_input_tokens_seen": 655558744, "step": 15920, "train_runtime": 61397.5665, "train_tokens_per_second": 10677.276 }, { "epoch": 1.0722461621330461, "grad_norm": 0.8634662652472574, "learning_rate": 4.434322534620692e-06, "loss": 0.3218878507614136, "num_input_tokens_seen": 655751072, "step": 15925, "train_runtime": 61417.2374, "train_tokens_per_second": 10676.987 }, { "epoch": 1.0725828171290062, "grad_norm": 0.6622509101616438, "learning_rate": 4.431695507829504e-06, "loss": 0.2758625984191895, "num_input_tokens_seen": 655959080, "step": 15930, "train_runtime": 61436.5812, "train_tokens_per_second": 10677.011 }, { "epoch": 1.0729194721249664, "grad_norm": 0.747550815830059, "learning_rate": 4.429068639962853e-06, "loss": 0.3137178897857666, "num_input_tokens_seen": 656161072, "step": 15935, "train_runtime": 61455.2755, "train_tokens_per_second": 10677.05 }, { "epoch": 1.0732561271209264, "grad_norm": 0.724666296257816, "learning_rate": 4.426441931755337e-06, "loss": 0.30340917110443116, "num_input_tokens_seen": 656373840, "step": 15940, "train_runtime": 61475.6214, "train_tokens_per_second": 10676.978 }, { "epoch": 1.0735927821168867, "grad_norm": 0.7333246409475705, "learning_rate": 4.4238153839415045e-06, "loss": 0.3183551788330078, "num_input_tokens_seen": 656589376, "step": 15945, "train_runtime": 61494.0073, "train_tokens_per_second": 10677.29 }, { "epoch": 1.0739294371128467, "grad_norm": 0.7651588372775883, "learning_rate": 4.421188997255865e-06, "loss": 0.33234496116638185, "num_input_tokens_seen": 656786040, "step": 15950, "train_runtime": 61512.8844, "train_tokens_per_second": 10677.211 }, { "epoch": 1.074266092108807, "grad_norm": 0.7225514205329309, "learning_rate": 4.418562772432874e-06, "loss": 0.3109236478805542, "num_input_tokens_seen": 656991032, "step": 15955, "train_runtime": 61531.4628, "train_tokens_per_second": 10677.319 }, { "epoch": 1.074602747104767, "grad_norm": 0.7568341657022862, "learning_rate": 4.415936710206952e-06, "loss": 0.31374387741088866, "num_input_tokens_seen": 657209984, "step": 15960, "train_runtime": 61550.8245, "train_tokens_per_second": 10677.517 }, { "epoch": 1.0749394021007272, "grad_norm": 0.7966619885522482, "learning_rate": 4.413310811312465e-06, "loss": 0.3084887504577637, "num_input_tokens_seen": 657411888, "step": 15965, "train_runtime": 61568.4983, "train_tokens_per_second": 10677.731 }, { "epoch": 1.0752760570966873, "grad_norm": 0.7143266469265104, "learning_rate": 4.41068507648374e-06, "loss": 0.28737452030181887, "num_input_tokens_seen": 657622664, "step": 15970, "train_runtime": 61586.6735, "train_tokens_per_second": 10678.003 }, { "epoch": 1.0756127120926475, "grad_norm": 0.6666564155191982, "learning_rate": 4.408059506455053e-06, "loss": 0.29503602981567384, "num_input_tokens_seen": 657844424, "step": 15975, "train_runtime": 61605.4029, "train_tokens_per_second": 10678.356 }, { "epoch": 1.0759493670886076, "grad_norm": 0.668412706183429, "learning_rate": 4.40543410196064e-06, "loss": 0.3155190467834473, "num_input_tokens_seen": 658052576, "step": 15980, "train_runtime": 61623.3957, "train_tokens_per_second": 10678.616 }, { "epoch": 1.0762860220845678, "grad_norm": 1.0398066408742845, "learning_rate": 4.402808863734681e-06, "loss": 0.32759168148040774, "num_input_tokens_seen": 658259024, "step": 15985, "train_runtime": 61642.8629, "train_tokens_per_second": 10678.593 }, { "epoch": 1.0766226770805278, "grad_norm": 0.6609491114733155, "learning_rate": 4.40018379251132e-06, "loss": 0.31818442344665526, "num_input_tokens_seen": 658469216, "step": 15990, "train_runtime": 61663.5923, "train_tokens_per_second": 10678.412 }, { "epoch": 1.076959332076488, "grad_norm": 0.803850753821485, "learning_rate": 4.397558889024649e-06, "loss": 0.3522644996643066, "num_input_tokens_seen": 658661088, "step": 15995, "train_runtime": 61682.4192, "train_tokens_per_second": 10678.263 }, { "epoch": 1.0772959870724481, "grad_norm": 0.6279454818194868, "learning_rate": 4.394934154008715e-06, "loss": 0.3216850280761719, "num_input_tokens_seen": 658871040, "step": 16000, "train_runtime": 61702.2675, "train_tokens_per_second": 10678.231 }, { "epoch": 1.0776326420684084, "grad_norm": 0.6999649116750375, "learning_rate": 4.392309588197514e-06, "loss": 0.3026751518249512, "num_input_tokens_seen": 659080424, "step": 16005, "train_runtime": 61722.4835, "train_tokens_per_second": 10678.125 }, { "epoch": 1.0779692970643684, "grad_norm": 0.653298820262712, "learning_rate": 4.389685192324999e-06, "loss": 0.30374832153320314, "num_input_tokens_seen": 659286320, "step": 16010, "train_runtime": 61741.5765, "train_tokens_per_second": 10678.158 }, { "epoch": 1.0783059520603286, "grad_norm": 0.6681773563194413, "learning_rate": 4.387060967125073e-06, "loss": 0.3223487138748169, "num_input_tokens_seen": 659481728, "step": 16015, "train_runtime": 61760.4167, "train_tokens_per_second": 10678.065 }, { "epoch": 1.0786426070562887, "grad_norm": 0.7480955231087342, "learning_rate": 4.384436913331596e-06, "loss": 0.3354581594467163, "num_input_tokens_seen": 659689672, "step": 16020, "train_runtime": 61780.1849, "train_tokens_per_second": 10678.014 }, { "epoch": 1.078979262052249, "grad_norm": 0.7390942583789581, "learning_rate": 4.38181303167837e-06, "loss": 0.3064218521118164, "num_input_tokens_seen": 659897192, "step": 16025, "train_runtime": 61798.7943, "train_tokens_per_second": 10678.156 }, { "epoch": 1.079315917048209, "grad_norm": 0.7124376984043332, "learning_rate": 4.379189322899159e-06, "loss": 0.29042179584503175, "num_input_tokens_seen": 660093840, "step": 16030, "train_runtime": 61817.0872, "train_tokens_per_second": 10678.178 }, { "epoch": 1.0796525720441692, "grad_norm": 0.7039638242654053, "learning_rate": 4.376565787727676e-06, "loss": 0.30756776332855223, "num_input_tokens_seen": 660303040, "step": 16035, "train_runtime": 61835.2672, "train_tokens_per_second": 10678.421 }, { "epoch": 1.0799892270401292, "grad_norm": 0.7221891584878594, "learning_rate": 4.373942426897581e-06, "loss": 0.3059417486190796, "num_input_tokens_seen": 660497208, "step": 16040, "train_runtime": 61854.393, "train_tokens_per_second": 10678.259 }, { "epoch": 1.0803258820360895, "grad_norm": 0.7994828043285837, "learning_rate": 4.37131924114249e-06, "loss": 0.32651596069335936, "num_input_tokens_seen": 660692936, "step": 16045, "train_runtime": 61872.3688, "train_tokens_per_second": 10678.32 }, { "epoch": 1.0806625370320495, "grad_norm": 0.6967525699555785, "learning_rate": 4.368696231195968e-06, "loss": 0.3124654293060303, "num_input_tokens_seen": 660902344, "step": 16050, "train_runtime": 61891.467, "train_tokens_per_second": 10678.408 }, { "epoch": 1.0809991920280098, "grad_norm": 0.779107073272801, "learning_rate": 4.366073397791534e-06, "loss": 0.29955031871795657, "num_input_tokens_seen": 661105352, "step": 16055, "train_runtime": 61910.3666, "train_tokens_per_second": 10678.427 }, { "epoch": 1.0813358470239698, "grad_norm": 0.6431339947435308, "learning_rate": 4.363450741662651e-06, "loss": 0.2858445644378662, "num_input_tokens_seen": 661311320, "step": 16060, "train_runtime": 61930.1072, "train_tokens_per_second": 10678.349 }, { "epoch": 1.08167250201993, "grad_norm": 0.7245495613037974, "learning_rate": 4.360828263542739e-06, "loss": 0.28951277732849123, "num_input_tokens_seen": 661519256, "step": 16065, "train_runtime": 61949.2139, "train_tokens_per_second": 10678.412 }, { "epoch": 1.08200915701589, "grad_norm": 0.7663403162819752, "learning_rate": 4.358205964165164e-06, "loss": 0.3217752456665039, "num_input_tokens_seen": 661727136, "step": 16070, "train_runtime": 61968.649, "train_tokens_per_second": 10678.418 }, { "epoch": 1.0823458120118503, "grad_norm": 0.7042713751027949, "learning_rate": 4.355583844263247e-06, "loss": 0.32646448612213136, "num_input_tokens_seen": 661938800, "step": 16075, "train_runtime": 61988.3359, "train_tokens_per_second": 10678.441 }, { "epoch": 1.0826824670078103, "grad_norm": 0.8079301710526715, "learning_rate": 4.352961904570251e-06, "loss": 0.3137331485748291, "num_input_tokens_seen": 662142664, "step": 16080, "train_runtime": 62008.0464, "train_tokens_per_second": 10678.335 }, { "epoch": 1.0830191220037706, "grad_norm": 0.695380214987531, "learning_rate": 4.350340145819397e-06, "loss": 0.3165487766265869, "num_input_tokens_seen": 662343656, "step": 16085, "train_runtime": 62026.3725, "train_tokens_per_second": 10678.42 }, { "epoch": 1.0833557769997306, "grad_norm": 0.6897939685611074, "learning_rate": 4.347718568743847e-06, "loss": 0.31386561393737794, "num_input_tokens_seen": 662551920, "step": 16090, "train_runtime": 62045.2937, "train_tokens_per_second": 10678.52 }, { "epoch": 1.0836924319956909, "grad_norm": 0.6687536793216406, "learning_rate": 4.34509717407672e-06, "loss": 0.32332792282104494, "num_input_tokens_seen": 662770544, "step": 16095, "train_runtime": 62065.1754, "train_tokens_per_second": 10678.622 }, { "epoch": 1.084029086991651, "grad_norm": 0.7430470959559488, "learning_rate": 4.342475962551081e-06, "loss": 0.3133992671966553, "num_input_tokens_seen": 662975648, "step": 16100, "train_runtime": 62084.666, "train_tokens_per_second": 10678.573 }, { "epoch": 1.0843657419876112, "grad_norm": 0.6877450085830693, "learning_rate": 4.339854934899943e-06, "loss": 0.28485846519470215, "num_input_tokens_seen": 663178144, "step": 16105, "train_runtime": 62104.4167, "train_tokens_per_second": 10678.438 }, { "epoch": 1.0847023969835712, "grad_norm": 0.6656773624476301, "learning_rate": 4.337234091856265e-06, "loss": 0.2775494337081909, "num_input_tokens_seen": 663394296, "step": 16110, "train_runtime": 62125.1336, "train_tokens_per_second": 10678.356 }, { "epoch": 1.0850390519795314, "grad_norm": 0.7384277619568191, "learning_rate": 4.334613434152961e-06, "loss": 0.3021878480911255, "num_input_tokens_seen": 663590288, "step": 16115, "train_runtime": 62144.5083, "train_tokens_per_second": 10678.181 }, { "epoch": 1.0853757069754915, "grad_norm": 0.8069657401125313, "learning_rate": 4.331992962522888e-06, "loss": 0.3377904176712036, "num_input_tokens_seen": 663797408, "step": 16120, "train_runtime": 62163.1204, "train_tokens_per_second": 10678.315 }, { "epoch": 1.0857123619714517, "grad_norm": 0.7339459210926367, "learning_rate": 4.329372677698854e-06, "loss": 0.3123623371124268, "num_input_tokens_seen": 664010928, "step": 16125, "train_runtime": 62182.4874, "train_tokens_per_second": 10678.423 }, { "epoch": 1.0860490169674117, "grad_norm": 0.7392959066855969, "learning_rate": 4.3267525804136114e-06, "loss": 0.3187535047531128, "num_input_tokens_seen": 664216144, "step": 16130, "train_runtime": 62199.9149, "train_tokens_per_second": 10678.731 }, { "epoch": 1.086385671963372, "grad_norm": 0.7448512473068165, "learning_rate": 4.324132671399864e-06, "loss": 0.3165557861328125, "num_input_tokens_seen": 664410896, "step": 16135, "train_runtime": 62219.9861, "train_tokens_per_second": 10678.416 }, { "epoch": 1.086722326959332, "grad_norm": 0.7166673476633308, "learning_rate": 4.321512951390258e-06, "loss": 0.32718777656555176, "num_input_tokens_seen": 664617824, "step": 16140, "train_runtime": 62238.1148, "train_tokens_per_second": 10678.63 }, { "epoch": 1.0870589819552923, "grad_norm": 0.7056949405993366, "learning_rate": 4.318893421117393e-06, "loss": 0.3069819211959839, "num_input_tokens_seen": 664825712, "step": 16145, "train_runtime": 62257.4678, "train_tokens_per_second": 10678.65 }, { "epoch": 1.0873956369512523, "grad_norm": 0.6971270157430736, "learning_rate": 4.31627408131381e-06, "loss": 0.29558663368225097, "num_input_tokens_seen": 665026912, "step": 16150, "train_runtime": 62279.8225, "train_tokens_per_second": 10678.048 }, { "epoch": 1.0877322919472125, "grad_norm": 0.679798006714874, "learning_rate": 4.313654932712001e-06, "loss": 0.2785980463027954, "num_input_tokens_seen": 665231544, "step": 16155, "train_runtime": 62299.5656, "train_tokens_per_second": 10677.948 }, { "epoch": 1.0880689469431726, "grad_norm": 0.7302538461129721, "learning_rate": 4.3110359760444e-06, "loss": 0.30950140953063965, "num_input_tokens_seen": 665446496, "step": 16160, "train_runtime": 62317.6877, "train_tokens_per_second": 10678.292 }, { "epoch": 1.0884056019391328, "grad_norm": 0.6916552791509226, "learning_rate": 4.308417212043392e-06, "loss": 0.2891394138336182, "num_input_tokens_seen": 665646392, "step": 16165, "train_runtime": 62336.4084, "train_tokens_per_second": 10678.292 }, { "epoch": 1.0887422569350929, "grad_norm": 0.7085919324598224, "learning_rate": 4.305798641441304e-06, "loss": 0.29604713916778563, "num_input_tokens_seen": 665859584, "step": 16170, "train_runtime": 62355.1306, "train_tokens_per_second": 10678.505 }, { "epoch": 1.089078911931053, "grad_norm": 0.729608002718267, "learning_rate": 4.303180264970416e-06, "loss": 0.3075398921966553, "num_input_tokens_seen": 666062728, "step": 16175, "train_runtime": 62374.1875, "train_tokens_per_second": 10678.499 }, { "epoch": 1.0894155669270131, "grad_norm": 0.6484312391503118, "learning_rate": 4.3005620833629415e-06, "loss": 0.28503875732421874, "num_input_tokens_seen": 666268048, "step": 16180, "train_runtime": 62394.6646, "train_tokens_per_second": 10678.286 }, { "epoch": 1.0897522219229734, "grad_norm": 0.7798002163614262, "learning_rate": 4.297944097351053e-06, "loss": 0.31362004280090333, "num_input_tokens_seen": 666461472, "step": 16185, "train_runtime": 62413.4333, "train_tokens_per_second": 10678.174 }, { "epoch": 1.0900888769189334, "grad_norm": 0.7040835117035907, "learning_rate": 4.295326307666856e-06, "loss": 0.3285574197769165, "num_input_tokens_seen": 666679680, "step": 16190, "train_runtime": 62433.1776, "train_tokens_per_second": 10678.292 }, { "epoch": 1.0904255319148937, "grad_norm": 0.6954584674652297, "learning_rate": 4.292708715042411e-06, "loss": 0.30684752464294435, "num_input_tokens_seen": 666885536, "step": 16195, "train_runtime": 62451.9138, "train_tokens_per_second": 10678.384 }, { "epoch": 1.0907621869108537, "grad_norm": 0.776530291000612, "learning_rate": 4.290091320209718e-06, "loss": 0.3222876310348511, "num_input_tokens_seen": 667101656, "step": 16200, "train_runtime": 62471.4789, "train_tokens_per_second": 10678.499 }, { "epoch": 1.091098841906814, "grad_norm": 0.7529733361472578, "learning_rate": 4.287474123900726e-06, "loss": 0.31529555320739744, "num_input_tokens_seen": 667297616, "step": 16205, "train_runtime": 62490.6095, "train_tokens_per_second": 10678.366 }, { "epoch": 1.091435496902774, "grad_norm": 0.7005271012343227, "learning_rate": 4.284857126847321e-06, "loss": 0.3110833168029785, "num_input_tokens_seen": 667499008, "step": 16210, "train_runtime": 62508.9448, "train_tokens_per_second": 10678.456 }, { "epoch": 1.0917721518987342, "grad_norm": 0.6681889542655972, "learning_rate": 4.28224032978134e-06, "loss": 0.3237039566040039, "num_input_tokens_seen": 667713200, "step": 16215, "train_runtime": 62528.7638, "train_tokens_per_second": 10678.497 }, { "epoch": 1.0921088068946943, "grad_norm": 0.6373505648327643, "learning_rate": 4.279623733434561e-06, "loss": 0.2969686508178711, "num_input_tokens_seen": 667920528, "step": 16220, "train_runtime": 62548.8217, "train_tokens_per_second": 10678.387 }, { "epoch": 1.0924454618906545, "grad_norm": 0.6778853974116044, "learning_rate": 4.277007338538711e-06, "loss": 0.28007609844207765, "num_input_tokens_seen": 668141576, "step": 16225, "train_runtime": 62567.779, "train_tokens_per_second": 10678.685 }, { "epoch": 1.0927821168866145, "grad_norm": 0.6064809544769572, "learning_rate": 4.27439114582545e-06, "loss": 0.2760073184967041, "num_input_tokens_seen": 668350320, "step": 16230, "train_runtime": 62588.3404, "train_tokens_per_second": 10678.512 }, { "epoch": 1.0931187718825748, "grad_norm": 0.7348523797710567, "learning_rate": 4.271775156026395e-06, "loss": 0.32493612766265867, "num_input_tokens_seen": 668543840, "step": 16235, "train_runtime": 62608.5461, "train_tokens_per_second": 10678.156 }, { "epoch": 1.0934554268785348, "grad_norm": 0.6830434684272672, "learning_rate": 4.269159369873093e-06, "loss": 0.30362012386322024, "num_input_tokens_seen": 668739040, "step": 16240, "train_runtime": 62628.8566, "train_tokens_per_second": 10677.81 }, { "epoch": 1.093792081874495, "grad_norm": 0.6437500995669632, "learning_rate": 4.266543788097043e-06, "loss": 0.30153698921203614, "num_input_tokens_seen": 668957968, "step": 16245, "train_runtime": 62646.5658, "train_tokens_per_second": 10678.286 }, { "epoch": 1.094128736870455, "grad_norm": 0.7383489041615036, "learning_rate": 4.263928411429683e-06, "loss": 0.345462703704834, "num_input_tokens_seen": 669158448, "step": 16250, "train_runtime": 62667.2466, "train_tokens_per_second": 10677.962 }, { "epoch": 1.0944653918664153, "grad_norm": 0.703234630362938, "learning_rate": 4.261313240602398e-06, "loss": 0.318255352973938, "num_input_tokens_seen": 669359312, "step": 16255, "train_runtime": 62686.3792, "train_tokens_per_second": 10677.907 }, { "epoch": 1.0948020468623754, "grad_norm": 0.7123507218720508, "learning_rate": 4.2586982763465064e-06, "loss": 0.31457645893096925, "num_input_tokens_seen": 669572600, "step": 16260, "train_runtime": 62705.0997, "train_tokens_per_second": 10678.12 }, { "epoch": 1.0951387018583356, "grad_norm": 0.6995778537313074, "learning_rate": 4.256083519393281e-06, "loss": 0.3000232696533203, "num_input_tokens_seen": 669778056, "step": 16265, "train_runtime": 62724.1954, "train_tokens_per_second": 10678.145 }, { "epoch": 1.0954753568542956, "grad_norm": 0.7220638128804147, "learning_rate": 4.253468970473925e-06, "loss": 0.3250237464904785, "num_input_tokens_seen": 669985688, "step": 16270, "train_runtime": 62742.2327, "train_tokens_per_second": 10678.385 }, { "epoch": 1.095812011850256, "grad_norm": 0.7170037126162689, "learning_rate": 4.250854630319593e-06, "loss": 0.3425016403198242, "num_input_tokens_seen": 670193312, "step": 16275, "train_runtime": 62761.9354, "train_tokens_per_second": 10678.34 }, { "epoch": 1.096148666846216, "grad_norm": 0.6622578784174726, "learning_rate": 4.248240499661373e-06, "loss": 0.305840802192688, "num_input_tokens_seen": 670389416, "step": 16280, "train_runtime": 62780.9776, "train_tokens_per_second": 10678.225 }, { "epoch": 1.0964853218421762, "grad_norm": 0.741904311793784, "learning_rate": 4.245626579230302e-06, "loss": 0.2857199192047119, "num_input_tokens_seen": 670596552, "step": 16285, "train_runtime": 62799.1622, "train_tokens_per_second": 10678.431 }, { "epoch": 1.0968219768381362, "grad_norm": 0.8600931039257467, "learning_rate": 4.243012869757351e-06, "loss": 0.3015458345413208, "num_input_tokens_seen": 670816912, "step": 16290, "train_runtime": 62819.5132, "train_tokens_per_second": 10678.48 }, { "epoch": 1.0971586318340965, "grad_norm": 0.6564008824025449, "learning_rate": 4.240399371973438e-06, "loss": 0.31393980979919434, "num_input_tokens_seen": 671032824, "step": 16295, "train_runtime": 62837.9795, "train_tokens_per_second": 10678.778 }, { "epoch": 1.0974952868300565, "grad_norm": 0.7508126127378282, "learning_rate": 4.2377860866094165e-06, "loss": 0.3216238498687744, "num_input_tokens_seen": 671240376, "step": 16300, "train_runtime": 62856.9626, "train_tokens_per_second": 10678.855 }, { "epoch": 1.0978319418260167, "grad_norm": 0.7663210557735368, "learning_rate": 4.235173014396088e-06, "loss": 0.3131229877471924, "num_input_tokens_seen": 671446168, "step": 16305, "train_runtime": 62876.3266, "train_tokens_per_second": 10678.839 }, { "epoch": 1.0981685968219768, "grad_norm": 0.7037920176765885, "learning_rate": 4.2325601560641854e-06, "loss": 0.33066549301147463, "num_input_tokens_seen": 671659816, "step": 16310, "train_runtime": 62897.1963, "train_tokens_per_second": 10678.692 }, { "epoch": 1.098505251817937, "grad_norm": 0.7539167251759945, "learning_rate": 4.229947512344389e-06, "loss": 0.3005320310592651, "num_input_tokens_seen": 671865152, "step": 16315, "train_runtime": 62917.2304, "train_tokens_per_second": 10678.556 }, { "epoch": 1.098841906813897, "grad_norm": 0.7109274361077746, "learning_rate": 4.227335083967314e-06, "loss": 0.3105002403259277, "num_input_tokens_seen": 672070096, "step": 16320, "train_runtime": 62936.5665, "train_tokens_per_second": 10678.531 }, { "epoch": 1.0991785618098573, "grad_norm": 0.6515864926178858, "learning_rate": 4.224722871663522e-06, "loss": 0.30127639770507814, "num_input_tokens_seen": 672276512, "step": 16325, "train_runtime": 62954.8841, "train_tokens_per_second": 10678.703 }, { "epoch": 1.0995152168058173, "grad_norm": 0.6557626315008113, "learning_rate": 4.222110876163503e-06, "loss": 0.3367269515991211, "num_input_tokens_seen": 672492408, "step": 16330, "train_runtime": 62975.2939, "train_tokens_per_second": 10678.67 }, { "epoch": 1.0998518718017776, "grad_norm": 0.7990839610333673, "learning_rate": 4.2194990981977e-06, "loss": 0.30327205657958983, "num_input_tokens_seen": 672703576, "step": 16335, "train_runtime": 62993.6114, "train_tokens_per_second": 10678.917 }, { "epoch": 1.1001885267977376, "grad_norm": 0.6815580074381477, "learning_rate": 4.216887538496482e-06, "loss": 0.2966787099838257, "num_input_tokens_seen": 672906096, "step": 16340, "train_runtime": 63011.7703, "train_tokens_per_second": 10679.054 }, { "epoch": 1.1005251817936978, "grad_norm": 0.7229159716699544, "learning_rate": 4.2142761977901695e-06, "loss": 0.3562399625778198, "num_input_tokens_seen": 673110672, "step": 16345, "train_runtime": 63031.4144, "train_tokens_per_second": 10678.971 }, { "epoch": 1.1008618367896579, "grad_norm": 0.7300213811026584, "learning_rate": 4.21166507680901e-06, "loss": 0.317742133140564, "num_input_tokens_seen": 673308200, "step": 16350, "train_runtime": 63048.9588, "train_tokens_per_second": 10679.133 }, { "epoch": 1.1011984917856181, "grad_norm": 0.7421865883420301, "learning_rate": 4.209054176283202e-06, "loss": 0.3107206583023071, "num_input_tokens_seen": 673508384, "step": 16355, "train_runtime": 63067.5514, "train_tokens_per_second": 10679.159 }, { "epoch": 1.1015351467815782, "grad_norm": 0.7203836919065623, "learning_rate": 4.206443496942868e-06, "loss": 0.31241626739501954, "num_input_tokens_seen": 673712592, "step": 16360, "train_runtime": 63086.1866, "train_tokens_per_second": 10679.241 }, { "epoch": 1.1018718017775384, "grad_norm": 0.7290235222817392, "learning_rate": 4.203833039518081e-06, "loss": 0.2881391763687134, "num_input_tokens_seen": 673911520, "step": 16365, "train_runtime": 63105.3921, "train_tokens_per_second": 10679.143 }, { "epoch": 1.1022084567734984, "grad_norm": 0.7005888293336567, "learning_rate": 4.201222804738845e-06, "loss": 0.2960522651672363, "num_input_tokens_seen": 674126928, "step": 16370, "train_runtime": 63124.559, "train_tokens_per_second": 10679.313 }, { "epoch": 1.1025451117694587, "grad_norm": 0.7245713636020454, "learning_rate": 4.198612793335107e-06, "loss": 0.2862293481826782, "num_input_tokens_seen": 674337640, "step": 16375, "train_runtime": 63145.0999, "train_tokens_per_second": 10679.176 }, { "epoch": 1.1028817667654187, "grad_norm": 0.647778218181261, "learning_rate": 4.196003006036743e-06, "loss": 0.304993724822998, "num_input_tokens_seen": 674538424, "step": 16380, "train_runtime": 63164.4677, "train_tokens_per_second": 10679.08 }, { "epoch": 1.103218421761379, "grad_norm": 0.8759931267787672, "learning_rate": 4.193393443573576e-06, "loss": 0.31102101802825927, "num_input_tokens_seen": 674747448, "step": 16385, "train_runtime": 63182.9089, "train_tokens_per_second": 10679.272 }, { "epoch": 1.103555076757339, "grad_norm": 0.7558192984760538, "learning_rate": 4.19078410667536e-06, "loss": 0.3385432243347168, "num_input_tokens_seen": 674949016, "step": 16390, "train_runtime": 63202.0284, "train_tokens_per_second": 10679.23 }, { "epoch": 1.1038917317532992, "grad_norm": 0.7412712514649187, "learning_rate": 4.188174996071788e-06, "loss": 0.32584452629089355, "num_input_tokens_seen": 675129864, "step": 16395, "train_runtime": 63220.0825, "train_tokens_per_second": 10679.041 }, { "epoch": 1.1042283867492593, "grad_norm": 0.6986974843049599, "learning_rate": 4.18556611249249e-06, "loss": 0.30715360641479494, "num_input_tokens_seen": 675335448, "step": 16400, "train_runtime": 63239.0699, "train_tokens_per_second": 10679.086 }, { "epoch": 1.1045650417452195, "grad_norm": 0.787673007680441, "learning_rate": 4.182957456667032e-06, "loss": 0.3111401081085205, "num_input_tokens_seen": 675547088, "step": 16405, "train_runtime": 63259.6911, "train_tokens_per_second": 10678.95 }, { "epoch": 1.1049016967411796, "grad_norm": 0.7078903972464929, "learning_rate": 4.1803490293249145e-06, "loss": 0.3382100582122803, "num_input_tokens_seen": 675755368, "step": 16410, "train_runtime": 63279.1762, "train_tokens_per_second": 10678.953 }, { "epoch": 1.1052383517371398, "grad_norm": 0.8186363061757662, "learning_rate": 4.1777408311955785e-06, "loss": 0.3097421169281006, "num_input_tokens_seen": 675948432, "step": 16415, "train_runtime": 63298.0163, "train_tokens_per_second": 10678.825 }, { "epoch": 1.1055750067330998, "grad_norm": 0.7068531289229799, "learning_rate": 4.175132863008395e-06, "loss": 0.337348198890686, "num_input_tokens_seen": 676159680, "step": 16420, "train_runtime": 63318.571, "train_tokens_per_second": 10678.695 }, { "epoch": 1.10591166172906, "grad_norm": 0.8483701657821058, "learning_rate": 4.17252512549268e-06, "loss": 0.313153600692749, "num_input_tokens_seen": 676342552, "step": 16425, "train_runtime": 63336.5116, "train_tokens_per_second": 10678.557 }, { "epoch": 1.10624831672502, "grad_norm": 0.7272640985819894, "learning_rate": 4.169917619377671e-06, "loss": 0.30330886840820315, "num_input_tokens_seen": 676545576, "step": 16430, "train_runtime": 63356.9476, "train_tokens_per_second": 10678.317 }, { "epoch": 1.1065849717209804, "grad_norm": 0.7870939668253545, "learning_rate": 4.167310345392557e-06, "loss": 0.3387830972671509, "num_input_tokens_seen": 676745912, "step": 16435, "train_runtime": 63375.0738, "train_tokens_per_second": 10678.424 }, { "epoch": 1.1069216267169404, "grad_norm": 0.7376235902046012, "learning_rate": 4.1647033042664455e-06, "loss": 0.3401787281036377, "num_input_tokens_seen": 676946896, "step": 16440, "train_runtime": 63394.2197, "train_tokens_per_second": 10678.369 }, { "epoch": 1.1072582817129006, "grad_norm": 0.6874177445360644, "learning_rate": 4.162096496728394e-06, "loss": 0.30113108158111573, "num_input_tokens_seen": 677155016, "step": 16445, "train_runtime": 63414.5826, "train_tokens_per_second": 10678.222 }, { "epoch": 1.1075949367088607, "grad_norm": 0.6606049847070429, "learning_rate": 4.1594899235073835e-06, "loss": 0.303371787071228, "num_input_tokens_seen": 677371272, "step": 16450, "train_runtime": 63433.2116, "train_tokens_per_second": 10678.496 }, { "epoch": 1.107931591704821, "grad_norm": 0.7042681258353246, "learning_rate": 4.156883585332338e-06, "loss": 0.3348741054534912, "num_input_tokens_seen": 677585384, "step": 16455, "train_runtime": 63452.5478, "train_tokens_per_second": 10678.616 }, { "epoch": 1.108268246700781, "grad_norm": 0.6562517100365601, "learning_rate": 4.154277482932107e-06, "loss": 0.32059497833251954, "num_input_tokens_seen": 677779824, "step": 16460, "train_runtime": 63470.6465, "train_tokens_per_second": 10678.634 }, { "epoch": 1.1086049016967412, "grad_norm": 0.703108125008387, "learning_rate": 4.151671617035482e-06, "loss": 0.30482826232910154, "num_input_tokens_seen": 677978480, "step": 16465, "train_runtime": 63488.5113, "train_tokens_per_second": 10678.759 }, { "epoch": 1.1089415566927012, "grad_norm": 0.7154519693429707, "learning_rate": 4.149065988371184e-06, "loss": 0.2903615951538086, "num_input_tokens_seen": 678182832, "step": 16470, "train_runtime": 63507.2395, "train_tokens_per_second": 10678.827 }, { "epoch": 1.1092782116886615, "grad_norm": 0.7271026061005085, "learning_rate": 4.14646059766787e-06, "loss": 0.3021388053894043, "num_input_tokens_seen": 678375352, "step": 16475, "train_runtime": 63525.5248, "train_tokens_per_second": 10678.784 }, { "epoch": 1.1096148666846215, "grad_norm": 0.6725242806564722, "learning_rate": 4.143855445654127e-06, "loss": 0.29107663631439207, "num_input_tokens_seen": 678591128, "step": 16480, "train_runtime": 63546.0056, "train_tokens_per_second": 10678.738 }, { "epoch": 1.1099515216805818, "grad_norm": 0.7730068044345006, "learning_rate": 4.14125053305848e-06, "loss": 0.29190566539764407, "num_input_tokens_seen": 678783424, "step": 16485, "train_runtime": 63565.9795, "train_tokens_per_second": 10678.407 }, { "epoch": 1.1102881766765418, "grad_norm": 0.6533067473920809, "learning_rate": 4.1386458606093805e-06, "loss": 0.30664892196655275, "num_input_tokens_seen": 678990216, "step": 16490, "train_runtime": 63585.7852, "train_tokens_per_second": 10678.333 }, { "epoch": 1.110624831672502, "grad_norm": 0.7337852504863973, "learning_rate": 4.1360414290352214e-06, "loss": 0.33688578605651853, "num_input_tokens_seen": 679207040, "step": 16495, "train_runtime": 63604.4494, "train_tokens_per_second": 10678.609 }, { "epoch": 1.110961486668462, "grad_norm": 0.7509838870560351, "learning_rate": 4.1334372390643205e-06, "loss": 0.30723395347595217, "num_input_tokens_seen": 679422656, "step": 16500, "train_runtime": 63623.6117, "train_tokens_per_second": 10678.782 }, { "epoch": 1.1112981416644223, "grad_norm": 0.6378172924048054, "learning_rate": 4.130833291424934e-06, "loss": 0.3249903678894043, "num_input_tokens_seen": 679630144, "step": 16505, "train_runtime": 63642.3216, "train_tokens_per_second": 10678.902 }, { "epoch": 1.1116347966603823, "grad_norm": 0.7651160064680046, "learning_rate": 4.128229586845244e-06, "loss": 0.299479341506958, "num_input_tokens_seen": 679838352, "step": 16510, "train_runtime": 63662.2099, "train_tokens_per_second": 10678.837 }, { "epoch": 1.1119714516563426, "grad_norm": 0.585911527344234, "learning_rate": 4.125626126053372e-06, "loss": 0.2836728096008301, "num_input_tokens_seen": 680048312, "step": 16515, "train_runtime": 63681.9004, "train_tokens_per_second": 10678.832 }, { "epoch": 1.1123081066523026, "grad_norm": 0.7384639037861839, "learning_rate": 4.123022909777364e-06, "loss": 0.31476056575775146, "num_input_tokens_seen": 680254152, "step": 16520, "train_runtime": 63699.4607, "train_tokens_per_second": 10679.119 }, { "epoch": 1.1126447616482629, "grad_norm": 0.8594445244429552, "learning_rate": 4.120419938745205e-06, "loss": 0.3129788875579834, "num_input_tokens_seen": 680474176, "step": 16525, "train_runtime": 63720.4897, "train_tokens_per_second": 10679.048 }, { "epoch": 1.112981416644223, "grad_norm": 0.8054491165713907, "learning_rate": 4.1178172136848035e-06, "loss": 0.302414608001709, "num_input_tokens_seen": 680669312, "step": 16530, "train_runtime": 63739.1729, "train_tokens_per_second": 10678.979 }, { "epoch": 1.1133180716401831, "grad_norm": 0.7255148774767629, "learning_rate": 4.115214735324007e-06, "loss": 0.29073736667633054, "num_input_tokens_seen": 680886624, "step": 16535, "train_runtime": 63757.2625, "train_tokens_per_second": 10679.358 }, { "epoch": 1.1136547266361432, "grad_norm": 0.6271548125762018, "learning_rate": 4.112612504390586e-06, "loss": 0.2732783555984497, "num_input_tokens_seen": 681096056, "step": 16540, "train_runtime": 63776.7902, "train_tokens_per_second": 10679.372 }, { "epoch": 1.1139913816321034, "grad_norm": 0.6897400564395372, "learning_rate": 4.11001052161225e-06, "loss": 0.32874383926391604, "num_input_tokens_seen": 681300856, "step": 16545, "train_runtime": 63796.4283, "train_tokens_per_second": 10679.295 }, { "epoch": 1.1143280366280637, "grad_norm": 0.7340695307715882, "learning_rate": 4.107408787716632e-06, "loss": 0.3113517761230469, "num_input_tokens_seen": 681512632, "step": 16550, "train_runtime": 63815.9736, "train_tokens_per_second": 10679.342 }, { "epoch": 1.1146646916240237, "grad_norm": 0.6597869556845535, "learning_rate": 4.104807303431303e-06, "loss": 0.30329692363739014, "num_input_tokens_seen": 681722576, "step": 16555, "train_runtime": 63834.9134, "train_tokens_per_second": 10679.463 }, { "epoch": 1.1150013466199837, "grad_norm": 0.7836730168564724, "learning_rate": 4.102206069483754e-06, "loss": 0.3261480093002319, "num_input_tokens_seen": 681923696, "step": 16560, "train_runtime": 63853.748, "train_tokens_per_second": 10679.462 }, { "epoch": 1.115338001615944, "grad_norm": 0.7043258009790511, "learning_rate": 4.099605086601417e-06, "loss": 0.2802162170410156, "num_input_tokens_seen": 682117152, "step": 16565, "train_runtime": 63873.9704, "train_tokens_per_second": 10679.11 }, { "epoch": 1.1156746566119042, "grad_norm": 0.7017816493781384, "learning_rate": 4.097004355511645e-06, "loss": 0.2901111125946045, "num_input_tokens_seen": 682323376, "step": 16570, "train_runtime": 63892.1387, "train_tokens_per_second": 10679.301 }, { "epoch": 1.1160113116078643, "grad_norm": 0.7709867787428186, "learning_rate": 4.094403876941728e-06, "loss": 0.27942662239074706, "num_input_tokens_seen": 682527296, "step": 16575, "train_runtime": 63910.7, "train_tokens_per_second": 10679.39 }, { "epoch": 1.1163479666038243, "grad_norm": 0.6625172419755774, "learning_rate": 4.0918036516188755e-06, "loss": 0.3137340545654297, "num_input_tokens_seen": 682722288, "step": 16580, "train_runtime": 63930.4954, "train_tokens_per_second": 10679.133 }, { "epoch": 1.1166846215997845, "grad_norm": 0.6933711042032213, "learning_rate": 4.0892036802702395e-06, "loss": 0.30905790328979493, "num_input_tokens_seen": 682934248, "step": 16585, "train_runtime": 63950.9353, "train_tokens_per_second": 10679.035 }, { "epoch": 1.1170212765957448, "grad_norm": 0.6492145148782954, "learning_rate": 4.086603963622887e-06, "loss": 0.2830516338348389, "num_input_tokens_seen": 683145536, "step": 16590, "train_runtime": 63972.2186, "train_tokens_per_second": 10678.784 }, { "epoch": 1.1173579315917048, "grad_norm": 0.7059431484745115, "learning_rate": 4.084004502403825e-06, "loss": 0.3186694622039795, "num_input_tokens_seen": 683351432, "step": 16595, "train_runtime": 63990.6588, "train_tokens_per_second": 10678.925 }, { "epoch": 1.1176945865876649, "grad_norm": 0.6728634321803553, "learning_rate": 4.081405297339982e-06, "loss": 0.301891565322876, "num_input_tokens_seen": 683568960, "step": 16600, "train_runtime": 64009.5017, "train_tokens_per_second": 10679.18 }, { "epoch": 1.118031241583625, "grad_norm": 0.7336286486612362, "learning_rate": 4.0788063491582205e-06, "loss": 0.30415072441101076, "num_input_tokens_seen": 683767144, "step": 16605, "train_runtime": 64029.5537, "train_tokens_per_second": 10678.93 }, { "epoch": 1.1183678965795854, "grad_norm": 0.8026149208666722, "learning_rate": 4.076207658585323e-06, "loss": 0.3105595827102661, "num_input_tokens_seen": 683982336, "step": 16610, "train_runtime": 64048.8877, "train_tokens_per_second": 10679.067 }, { "epoch": 1.1187045515755454, "grad_norm": 0.6591014847654315, "learning_rate": 4.07360922634801e-06, "loss": 0.310200834274292, "num_input_tokens_seen": 684196072, "step": 16615, "train_runtime": 64067.7948, "train_tokens_per_second": 10679.251 }, { "epoch": 1.1190412065715054, "grad_norm": 0.7650891625489645, "learning_rate": 4.071011053172922e-06, "loss": 0.30477759838104246, "num_input_tokens_seen": 684388592, "step": 16620, "train_runtime": 64087.6785, "train_tokens_per_second": 10678.942 }, { "epoch": 1.1193778615674657, "grad_norm": 0.7614451266470476, "learning_rate": 4.068413139786631e-06, "loss": 0.30214872360229494, "num_input_tokens_seen": 684593328, "step": 16625, "train_runtime": 64106.2673, "train_tokens_per_second": 10679.039 }, { "epoch": 1.119714516563426, "grad_norm": 0.7415918352004688, "learning_rate": 4.065815486915635e-06, "loss": 0.3046860218048096, "num_input_tokens_seen": 684808792, "step": 16630, "train_runtime": 64125.5406, "train_tokens_per_second": 10679.189 }, { "epoch": 1.120051171559386, "grad_norm": 0.6629341298745745, "learning_rate": 4.063218095286359e-06, "loss": 0.31753854751586913, "num_input_tokens_seen": 685023720, "step": 16635, "train_runtime": 64144.1743, "train_tokens_per_second": 10679.438 }, { "epoch": 1.120387826555346, "grad_norm": 0.7418881465723017, "learning_rate": 4.0606209656251555e-06, "loss": 0.3021045923233032, "num_input_tokens_seen": 685232632, "step": 16640, "train_runtime": 64162.0602, "train_tokens_per_second": 10679.717 }, { "epoch": 1.1207244815513062, "grad_norm": 0.7403603739457629, "learning_rate": 4.058024098658304e-06, "loss": 0.3285261869430542, "num_input_tokens_seen": 685444216, "step": 16645, "train_runtime": 64180.7296, "train_tokens_per_second": 10679.907 }, { "epoch": 1.1210611365472665, "grad_norm": 0.6783107010816871, "learning_rate": 4.055427495112008e-06, "loss": 0.338456916809082, "num_input_tokens_seen": 685654920, "step": 16650, "train_runtime": 64199.9954, "train_tokens_per_second": 10679.984 }, { "epoch": 1.1213977915432265, "grad_norm": 0.7289750181736322, "learning_rate": 4.052831155712403e-06, "loss": 0.287942099571228, "num_input_tokens_seen": 685865632, "step": 16655, "train_runtime": 64218.2533, "train_tokens_per_second": 10680.229 }, { "epoch": 1.1217344465391865, "grad_norm": 0.706516303463476, "learning_rate": 4.050235081185544e-06, "loss": 0.2794365167617798, "num_input_tokens_seen": 686072928, "step": 16660, "train_runtime": 64238.2148, "train_tokens_per_second": 10680.137 }, { "epoch": 1.1220711015351468, "grad_norm": 0.746845284355316, "learning_rate": 4.047639272257415e-06, "loss": 0.31590976715087893, "num_input_tokens_seen": 686287208, "step": 16665, "train_runtime": 64257.8891, "train_tokens_per_second": 10680.202 }, { "epoch": 1.122407756531107, "grad_norm": 0.6587468640333408, "learning_rate": 4.045043729653927e-06, "loss": 0.2821390628814697, "num_input_tokens_seen": 686500792, "step": 16670, "train_runtime": 64277.3619, "train_tokens_per_second": 10680.289 }, { "epoch": 1.122744411527067, "grad_norm": 0.7075070574290137, "learning_rate": 4.0424484541009175e-06, "loss": 0.32582640647888184, "num_input_tokens_seen": 686717592, "step": 16675, "train_runtime": 64297.7612, "train_tokens_per_second": 10680.272 }, { "epoch": 1.1230810665230273, "grad_norm": 0.7639475367941287, "learning_rate": 4.039853446324141e-06, "loss": 0.295678973197937, "num_input_tokens_seen": 686915880, "step": 16680, "train_runtime": 64317.4924, "train_tokens_per_second": 10680.079 }, { "epoch": 1.1234177215189873, "grad_norm": 0.740986165411585, "learning_rate": 4.037258707049289e-06, "loss": 0.29887166023254397, "num_input_tokens_seen": 687120760, "step": 16685, "train_runtime": 64336.0716, "train_tokens_per_second": 10680.179 }, { "epoch": 1.1237543765149476, "grad_norm": 0.6452216881039465, "learning_rate": 4.034664237001969e-06, "loss": 0.29931297302246096, "num_input_tokens_seen": 687330728, "step": 16690, "train_runtime": 64356.2281, "train_tokens_per_second": 10680.097 }, { "epoch": 1.1240910315109076, "grad_norm": 0.8010798104133282, "learning_rate": 4.032070036907716e-06, "loss": 0.31953303813934325, "num_input_tokens_seen": 687526752, "step": 16695, "train_runtime": 64375.0441, "train_tokens_per_second": 10680.02 }, { "epoch": 1.1244276865068679, "grad_norm": 0.9340095199605555, "learning_rate": 4.029476107491991e-06, "loss": 0.32198753356933596, "num_input_tokens_seen": 687734648, "step": 16700, "train_runtime": 64396.0946, "train_tokens_per_second": 10679.757 }, { "epoch": 1.124764341502828, "grad_norm": 0.6877040545934349, "learning_rate": 4.0268824494801784e-06, "loss": 0.305548095703125, "num_input_tokens_seen": 687941464, "step": 16705, "train_runtime": 64414.91, "train_tokens_per_second": 10679.848 }, { "epoch": 1.1251009964987881, "grad_norm": 0.6767474961986801, "learning_rate": 4.024289063597585e-06, "loss": 0.3102246284484863, "num_input_tokens_seen": 688135288, "step": 16710, "train_runtime": 64433.8245, "train_tokens_per_second": 10679.721 }, { "epoch": 1.1254376514947482, "grad_norm": 0.7029021310591193, "learning_rate": 4.021695950569443e-06, "loss": 0.2954124450683594, "num_input_tokens_seen": 688343000, "step": 16715, "train_runtime": 64451.4401, "train_tokens_per_second": 10680.025 }, { "epoch": 1.1257743064907082, "grad_norm": 0.77323966707042, "learning_rate": 4.01910311112091e-06, "loss": 0.3179192066192627, "num_input_tokens_seen": 688548320, "step": 16720, "train_runtime": 64471.6135, "train_tokens_per_second": 10679.868 }, { "epoch": 1.1261109614866684, "grad_norm": 0.7335565201537512, "learning_rate": 4.016510545977064e-06, "loss": 0.2999091386795044, "num_input_tokens_seen": 688763104, "step": 16725, "train_runtime": 64491.4607, "train_tokens_per_second": 10679.912 }, { "epoch": 1.1264476164826287, "grad_norm": 0.7756911257801689, "learning_rate": 4.013918255862908e-06, "loss": 0.31701064109802246, "num_input_tokens_seen": 688959448, "step": 16730, "train_runtime": 64509.6746, "train_tokens_per_second": 10679.94 }, { "epoch": 1.1267842714785887, "grad_norm": 0.7760992717809185, "learning_rate": 4.011326241503369e-06, "loss": 0.2949777126312256, "num_input_tokens_seen": 689158640, "step": 16735, "train_runtime": 64529.6881, "train_tokens_per_second": 10679.714 }, { "epoch": 1.127120926474549, "grad_norm": 0.6919987294496467, "learning_rate": 4.00873450362329e-06, "loss": 0.3220959663391113, "num_input_tokens_seen": 689368088, "step": 16740, "train_runtime": 64549.1738, "train_tokens_per_second": 10679.735 }, { "epoch": 1.127457581470509, "grad_norm": 0.6713213424336913, "learning_rate": 4.0061430429474476e-06, "loss": 0.3142240047454834, "num_input_tokens_seen": 689561024, "step": 16745, "train_runtime": 64568.0935, "train_tokens_per_second": 10679.594 }, { "epoch": 1.1277942364664693, "grad_norm": 0.6745534238906732, "learning_rate": 4.003551860200534e-06, "loss": 0.3078951835632324, "num_input_tokens_seen": 689756704, "step": 16750, "train_runtime": 64587.8354, "train_tokens_per_second": 10679.359 }, { "epoch": 1.1281308914624293, "grad_norm": 0.7459354864337318, "learning_rate": 4.000960956107167e-06, "loss": 0.3319541454315186, "num_input_tokens_seen": 689952536, "step": 16755, "train_runtime": 64607.8054, "train_tokens_per_second": 10679.09 }, { "epoch": 1.1284675464583895, "grad_norm": 0.749287878110653, "learning_rate": 3.998370331391881e-06, "loss": 0.30253138542175295, "num_input_tokens_seen": 690143704, "step": 16760, "train_runtime": 64626.9623, "train_tokens_per_second": 10678.882 }, { "epoch": 1.1288042014543496, "grad_norm": 0.7796951340576017, "learning_rate": 3.995779986779139e-06, "loss": 0.30478897094726565, "num_input_tokens_seen": 690334408, "step": 16765, "train_runtime": 64645.1958, "train_tokens_per_second": 10678.82 }, { "epoch": 1.1291408564503098, "grad_norm": 0.7090673350072798, "learning_rate": 3.9931899229933204e-06, "loss": 0.3251091241836548, "num_input_tokens_seen": 690540152, "step": 16770, "train_runtime": 64663.5536, "train_tokens_per_second": 10678.97 }, { "epoch": 1.1294775114462698, "grad_norm": 0.7367550586249852, "learning_rate": 3.990600140758731e-06, "loss": 0.3005242347717285, "num_input_tokens_seen": 690751240, "step": 16775, "train_runtime": 64682.14, "train_tokens_per_second": 10679.165 }, { "epoch": 1.12981416644223, "grad_norm": 0.6094647894320685, "learning_rate": 3.988010640799591e-06, "loss": 0.29215660095214846, "num_input_tokens_seen": 690959664, "step": 16780, "train_runtime": 64704.0245, "train_tokens_per_second": 10678.774 }, { "epoch": 1.1301508214381901, "grad_norm": 0.8247135719232714, "learning_rate": 3.985421423840051e-06, "loss": 0.3349085807800293, "num_input_tokens_seen": 691160200, "step": 16785, "train_runtime": 64723.8662, "train_tokens_per_second": 10678.599 }, { "epoch": 1.1304874764341504, "grad_norm": 0.7308940122437748, "learning_rate": 3.982832490604173e-06, "loss": 0.2906652450561523, "num_input_tokens_seen": 691373656, "step": 16790, "train_runtime": 64742.9376, "train_tokens_per_second": 10678.75 }, { "epoch": 1.1308241314301104, "grad_norm": 0.810158625254545, "learning_rate": 3.9802438418159465e-06, "loss": 0.3143734931945801, "num_input_tokens_seen": 691596288, "step": 16795, "train_runtime": 64763.0177, "train_tokens_per_second": 10678.877 }, { "epoch": 1.1311607864260707, "grad_norm": 0.7071539144129794, "learning_rate": 3.977655478199275e-06, "loss": 0.32188777923583983, "num_input_tokens_seen": 691809680, "step": 16800, "train_runtime": 64782.3095, "train_tokens_per_second": 10678.991 }, { "epoch": 1.1314974414220307, "grad_norm": 0.7425933929686356, "learning_rate": 3.975067400477993e-06, "loss": 0.34084606170654297, "num_input_tokens_seen": 691996048, "step": 16805, "train_runtime": 64801.2194, "train_tokens_per_second": 10678.75 }, { "epoch": 1.131834096417991, "grad_norm": 0.7515380497876682, "learning_rate": 3.972479609375842e-06, "loss": 0.31883702278137205, "num_input_tokens_seen": 692206112, "step": 16810, "train_runtime": 64819.8253, "train_tokens_per_second": 10678.926 }, { "epoch": 1.132170751413951, "grad_norm": 0.719405854339749, "learning_rate": 3.969892105616492e-06, "loss": 0.31632161140441895, "num_input_tokens_seen": 692417664, "step": 16815, "train_runtime": 64838.3516, "train_tokens_per_second": 10679.137 }, { "epoch": 1.1325074064099112, "grad_norm": 0.7499120373315116, "learning_rate": 3.967304889923529e-06, "loss": 0.3018058776855469, "num_input_tokens_seen": 692624376, "step": 16820, "train_runtime": 64858.5274, "train_tokens_per_second": 10679.002 }, { "epoch": 1.1328440614058712, "grad_norm": 0.7909011753137598, "learning_rate": 3.964717963020463e-06, "loss": 0.3029530763626099, "num_input_tokens_seen": 692827296, "step": 16825, "train_runtime": 64876.942, "train_tokens_per_second": 10679.099 }, { "epoch": 1.1331807164018315, "grad_norm": 0.7655123809855628, "learning_rate": 3.962131325630715e-06, "loss": 0.28811111450195315, "num_input_tokens_seen": 693045272, "step": 16830, "train_runtime": 64895.4188, "train_tokens_per_second": 10679.418 }, { "epoch": 1.1335173713977915, "grad_norm": 0.8617082560165042, "learning_rate": 3.959544978477634e-06, "loss": 0.32992305755615237, "num_input_tokens_seen": 693241008, "step": 16835, "train_runtime": 64914.0624, "train_tokens_per_second": 10679.366 }, { "epoch": 1.1338540263937518, "grad_norm": 0.6272253078404457, "learning_rate": 3.9569589222844805e-06, "loss": 0.3165726184844971, "num_input_tokens_seen": 693446448, "step": 16840, "train_runtime": 64934.8318, "train_tokens_per_second": 10679.114 }, { "epoch": 1.1341906813897118, "grad_norm": 0.7435481151582751, "learning_rate": 3.954373157774439e-06, "loss": 0.31243646144866943, "num_input_tokens_seen": 693657320, "step": 16845, "train_runtime": 64954.6922, "train_tokens_per_second": 10679.095 }, { "epoch": 1.134527336385672, "grad_norm": 0.733136825181969, "learning_rate": 3.951787685670609e-06, "loss": 0.307487416267395, "num_input_tokens_seen": 693868112, "step": 16850, "train_runtime": 64973.8296, "train_tokens_per_second": 10679.194 }, { "epoch": 1.134863991381632, "grad_norm": 0.7916512516642259, "learning_rate": 3.949202506696012e-06, "loss": 0.31396186351776123, "num_input_tokens_seen": 694066728, "step": 16855, "train_runtime": 64991.7959, "train_tokens_per_second": 10679.298 }, { "epoch": 1.1352006463775923, "grad_norm": 0.7077991509155224, "learning_rate": 3.946617621573581e-06, "loss": 0.30414116382598877, "num_input_tokens_seen": 694285432, "step": 16860, "train_runtime": 65011.9943, "train_tokens_per_second": 10679.344 }, { "epoch": 1.1355373013735524, "grad_norm": 0.7662813408152802, "learning_rate": 3.944033031026175e-06, "loss": 0.2840475559234619, "num_input_tokens_seen": 694475296, "step": 16865, "train_runtime": 65030.8597, "train_tokens_per_second": 10679.165 }, { "epoch": 1.1358739563695126, "grad_norm": 0.7308111784872939, "learning_rate": 3.941448735776563e-06, "loss": 0.312376070022583, "num_input_tokens_seen": 694680624, "step": 16870, "train_runtime": 65048.1537, "train_tokens_per_second": 10679.483 }, { "epoch": 1.1362106113654726, "grad_norm": 0.6338449923209596, "learning_rate": 3.938864736547439e-06, "loss": 0.3130274057388306, "num_input_tokens_seen": 694893960, "step": 16875, "train_runtime": 65067.017, "train_tokens_per_second": 10679.665 }, { "epoch": 1.1365472663614329, "grad_norm": 0.7428969508066409, "learning_rate": 3.936281034061405e-06, "loss": 0.3008079767227173, "num_input_tokens_seen": 695106072, "step": 16880, "train_runtime": 65086.388, "train_tokens_per_second": 10679.746 }, { "epoch": 1.136883921357393, "grad_norm": 0.6896196682278386, "learning_rate": 3.93369762904099e-06, "loss": 0.3140367269515991, "num_input_tokens_seen": 695302576, "step": 16885, "train_runtime": 65105.8031, "train_tokens_per_second": 10679.579 }, { "epoch": 1.1372205763533532, "grad_norm": 0.6940223687108729, "learning_rate": 3.931114522208631e-06, "loss": 0.31325154304504393, "num_input_tokens_seen": 695497248, "step": 16890, "train_runtime": 65125.5473, "train_tokens_per_second": 10679.331 }, { "epoch": 1.1375572313493132, "grad_norm": 0.7082011511754388, "learning_rate": 3.928531714286689e-06, "loss": 0.31166298389434816, "num_input_tokens_seen": 695708976, "step": 16895, "train_runtime": 65144.7091, "train_tokens_per_second": 10679.439 }, { "epoch": 1.1378938863452734, "grad_norm": 0.7860997415275541, "learning_rate": 3.925949205997434e-06, "loss": 0.33036441802978517, "num_input_tokens_seen": 695908176, "step": 16900, "train_runtime": 65163.3664, "train_tokens_per_second": 10679.439 }, { "epoch": 1.1382305413412335, "grad_norm": 0.7129943330402964, "learning_rate": 3.923366998063062e-06, "loss": 0.28895905017852785, "num_input_tokens_seen": 696107888, "step": 16905, "train_runtime": 65182.5867, "train_tokens_per_second": 10679.354 }, { "epoch": 1.1385671963371937, "grad_norm": 0.6263615525972317, "learning_rate": 3.920785091205674e-06, "loss": 0.27706522941589357, "num_input_tokens_seen": 696321120, "step": 16910, "train_runtime": 65200.17, "train_tokens_per_second": 10679.744 }, { "epoch": 1.1389038513331537, "grad_norm": 0.7546046790252818, "learning_rate": 3.918203486147294e-06, "loss": 0.3464799404144287, "num_input_tokens_seen": 696520400, "step": 16915, "train_runtime": 65219.8119, "train_tokens_per_second": 10679.583 }, { "epoch": 1.139240506329114, "grad_norm": 0.7731651388331632, "learning_rate": 3.9156221836098594e-06, "loss": 0.3209843158721924, "num_input_tokens_seen": 696728848, "step": 16920, "train_runtime": 65238.2132, "train_tokens_per_second": 10679.766 }, { "epoch": 1.139577161325074, "grad_norm": 0.6481119362746077, "learning_rate": 3.913041184315224e-06, "loss": 0.30780229568481443, "num_input_tokens_seen": 696931960, "step": 16925, "train_runtime": 65257.182, "train_tokens_per_second": 10679.774 }, { "epoch": 1.1399138163210343, "grad_norm": 0.8140118281561067, "learning_rate": 3.910460488985154e-06, "loss": 0.309424901008606, "num_input_tokens_seen": 697138784, "step": 16930, "train_runtime": 65276.9713, "train_tokens_per_second": 10679.705 }, { "epoch": 1.1402504713169943, "grad_norm": 0.8043155739951032, "learning_rate": 3.9078800983413355e-06, "loss": 0.3141251802444458, "num_input_tokens_seen": 697348400, "step": 16935, "train_runtime": 65296.0788, "train_tokens_per_second": 10679.79 }, { "epoch": 1.1405871263129546, "grad_norm": 0.704308445842581, "learning_rate": 3.905300013105365e-06, "loss": 0.29364852905273436, "num_input_tokens_seen": 697557144, "step": 16940, "train_runtime": 65315.3739, "train_tokens_per_second": 10679.831 }, { "epoch": 1.1409237813089146, "grad_norm": 0.8896125718121001, "learning_rate": 3.902720233998754e-06, "loss": 0.3016610622406006, "num_input_tokens_seen": 697758528, "step": 16945, "train_runtime": 65333.2533, "train_tokens_per_second": 10679.991 }, { "epoch": 1.1412604363048748, "grad_norm": 0.6914766050114731, "learning_rate": 3.90014076174293e-06, "loss": 0.3146719455718994, "num_input_tokens_seen": 697966768, "step": 16950, "train_runtime": 65351.3841, "train_tokens_per_second": 10680.214 }, { "epoch": 1.1415970913008349, "grad_norm": 0.6362954232834857, "learning_rate": 3.897561597059237e-06, "loss": 0.29063551425933837, "num_input_tokens_seen": 698176688, "step": 16955, "train_runtime": 65369.644, "train_tokens_per_second": 10680.442 }, { "epoch": 1.1419337462967951, "grad_norm": 0.6941776771130374, "learning_rate": 3.894982740668927e-06, "loss": 0.2894591331481934, "num_input_tokens_seen": 698369456, "step": 16960, "train_runtime": 65387.8523, "train_tokens_per_second": 10680.416 }, { "epoch": 1.1422704012927551, "grad_norm": 0.8389758138720067, "learning_rate": 3.89240419329317e-06, "loss": 0.32032999992370603, "num_input_tokens_seen": 698594088, "step": 16965, "train_runtime": 65405.457, "train_tokens_per_second": 10680.976 }, { "epoch": 1.1426070562887154, "grad_norm": 0.694992851967504, "learning_rate": 3.889825955653046e-06, "loss": 0.313480019569397, "num_input_tokens_seen": 698799016, "step": 16970, "train_runtime": 65424.9817, "train_tokens_per_second": 10680.92 }, { "epoch": 1.1429437112846754, "grad_norm": 0.7461233720775148, "learning_rate": 3.887248028469558e-06, "loss": 0.28116354942321775, "num_input_tokens_seen": 699016632, "step": 16975, "train_runtime": 65442.503, "train_tokens_per_second": 10681.386 }, { "epoch": 1.1432803662806357, "grad_norm": 0.6458890301616385, "learning_rate": 3.884670412463607e-06, "loss": 0.29759433269500735, "num_input_tokens_seen": 699221160, "step": 16980, "train_runtime": 65461.6291, "train_tokens_per_second": 10681.39 }, { "epoch": 1.1436170212765957, "grad_norm": 0.7357862781059714, "learning_rate": 3.8820931083560194e-06, "loss": 0.31571886539459226, "num_input_tokens_seen": 699417664, "step": 16985, "train_runtime": 65480.2255, "train_tokens_per_second": 10681.357 }, { "epoch": 1.143953676272556, "grad_norm": 0.6665462467253952, "learning_rate": 3.879516116867531e-06, "loss": 0.2870979309082031, "num_input_tokens_seen": 699618744, "step": 16990, "train_runtime": 65499.4208, "train_tokens_per_second": 10681.297 }, { "epoch": 1.144290331268516, "grad_norm": 0.7585221226731462, "learning_rate": 3.876939438718786e-06, "loss": 0.30668256282806394, "num_input_tokens_seen": 699825728, "step": 16995, "train_runtime": 65521.0303, "train_tokens_per_second": 10680.933 }, { "epoch": 1.1446269862644762, "grad_norm": 0.6470353455598448, "learning_rate": 3.874363074630345e-06, "loss": 0.2873255968093872, "num_input_tokens_seen": 700021416, "step": 17000, "train_runtime": 65540.8485, "train_tokens_per_second": 10680.689 }, { "epoch": 1.1449636412604363, "grad_norm": 0.7461597733824981, "learning_rate": 3.871787025322681e-06, "loss": 0.3159276008605957, "num_input_tokens_seen": 700233808, "step": 17005, "train_runtime": 65558.7663, "train_tokens_per_second": 10681.01 }, { "epoch": 1.1453002962563965, "grad_norm": 0.8399271467009899, "learning_rate": 3.86921129151618e-06, "loss": 0.3027914762496948, "num_input_tokens_seen": 700430968, "step": 17010, "train_runtime": 65576.4346, "train_tokens_per_second": 10681.138 }, { "epoch": 1.1456369512523565, "grad_norm": 0.7438776273489356, "learning_rate": 3.866635873931133e-06, "loss": 0.32955183982849123, "num_input_tokens_seen": 700632752, "step": 17015, "train_runtime": 65596.3931, "train_tokens_per_second": 10680.965 }, { "epoch": 1.1459736062483168, "grad_norm": 0.7140066744504908, "learning_rate": 3.864060773287751e-06, "loss": 0.3135065078735352, "num_input_tokens_seen": 700841384, "step": 17020, "train_runtime": 65615.8163, "train_tokens_per_second": 10680.982 }, { "epoch": 1.1463102612442768, "grad_norm": 0.7042519360141843, "learning_rate": 3.861485990306151e-06, "loss": 0.31575472354888917, "num_input_tokens_seen": 701054936, "step": 17025, "train_runtime": 65636.4107, "train_tokens_per_second": 10680.885 }, { "epoch": 1.146646916240237, "grad_norm": 0.7656394088446244, "learning_rate": 3.858911525706365e-06, "loss": 0.30383303165435793, "num_input_tokens_seen": 701268088, "step": 17030, "train_runtime": 65654.851, "train_tokens_per_second": 10681.131 }, { "epoch": 1.146983571236197, "grad_norm": 0.7754034013853908, "learning_rate": 3.85633738020833e-06, "loss": 0.3480847358703613, "num_input_tokens_seen": 701484656, "step": 17035, "train_runtime": 65672.7076, "train_tokens_per_second": 10681.525 }, { "epoch": 1.1473202262321573, "grad_norm": 0.7100279139077578, "learning_rate": 3.853763554531902e-06, "loss": 0.3161055088043213, "num_input_tokens_seen": 701680312, "step": 17040, "train_runtime": 65691.7536, "train_tokens_per_second": 10681.406 }, { "epoch": 1.1476568812281174, "grad_norm": 0.683780590371794, "learning_rate": 3.851190049396839e-06, "loss": 0.2857990264892578, "num_input_tokens_seen": 701887160, "step": 17045, "train_runtime": 65709.7545, "train_tokens_per_second": 10681.628 }, { "epoch": 1.1479935362240776, "grad_norm": 0.675600567559006, "learning_rate": 3.848616865522815e-06, "loss": 0.3080662965774536, "num_input_tokens_seen": 702094336, "step": 17050, "train_runtime": 65728.3136, "train_tokens_per_second": 10681.764 }, { "epoch": 1.1483301912200377, "grad_norm": 0.6915846412619429, "learning_rate": 3.846044003629414e-06, "loss": 0.31047520637512205, "num_input_tokens_seen": 702301736, "step": 17055, "train_runtime": 65747.1785, "train_tokens_per_second": 10681.854 }, { "epoch": 1.148666846215998, "grad_norm": 0.6783798102035308, "learning_rate": 3.843471464436128e-06, "loss": 0.27981154918670653, "num_input_tokens_seen": 702492696, "step": 17060, "train_runtime": 65768.0213, "train_tokens_per_second": 10681.372 }, { "epoch": 1.149003501211958, "grad_norm": 0.7846094895071097, "learning_rate": 3.840899248662358e-06, "loss": 0.33664417266845703, "num_input_tokens_seen": 702691424, "step": 17065, "train_runtime": 65785.7392, "train_tokens_per_second": 10681.516 }, { "epoch": 1.1493401562079182, "grad_norm": 0.7615863014994336, "learning_rate": 3.838327357027419e-06, "loss": 0.3238218307495117, "num_input_tokens_seen": 702891872, "step": 17070, "train_runtime": 65804.8834, "train_tokens_per_second": 10681.455 }, { "epoch": 1.1496768112038782, "grad_norm": 0.6935258813819855, "learning_rate": 3.835755790250528e-06, "loss": 0.31297078132629397, "num_input_tokens_seen": 703103968, "step": 17075, "train_runtime": 65824.5976, "train_tokens_per_second": 10681.478 }, { "epoch": 1.1500134661998385, "grad_norm": 0.6531625047333877, "learning_rate": 3.83318454905082e-06, "loss": 0.29387483596801756, "num_input_tokens_seen": 703317600, "step": 17080, "train_runtime": 65843.8284, "train_tokens_per_second": 10681.602 }, { "epoch": 1.1503501211957985, "grad_norm": 0.74231952615626, "learning_rate": 3.830613634147331e-06, "loss": 0.31726441383361814, "num_input_tokens_seen": 703524584, "step": 17085, "train_runtime": 65862.1379, "train_tokens_per_second": 10681.776 }, { "epoch": 1.1506867761917587, "grad_norm": 0.7430103951296398, "learning_rate": 3.82804304625901e-06, "loss": 0.3126509666442871, "num_input_tokens_seen": 703741496, "step": 17090, "train_runtime": 65881.4875, "train_tokens_per_second": 10681.931 }, { "epoch": 1.1510234311877188, "grad_norm": 0.7236838491560003, "learning_rate": 3.825472786104715e-06, "loss": 0.2944999933242798, "num_input_tokens_seen": 703959776, "step": 17095, "train_runtime": 65899.8938, "train_tokens_per_second": 10682.26 }, { "epoch": 1.151360086183679, "grad_norm": 0.8415156409250064, "learning_rate": 3.8229028544032095e-06, "loss": 0.31919155120849607, "num_input_tokens_seen": 704152352, "step": 17100, "train_runtime": 65920.6615, "train_tokens_per_second": 10681.816 }, { "epoch": 1.151696741179639, "grad_norm": 0.8986371565051235, "learning_rate": 3.8203332518731666e-06, "loss": 0.31533093452453614, "num_input_tokens_seen": 704359328, "step": 17105, "train_runtime": 65939.0293, "train_tokens_per_second": 10681.979 }, { "epoch": 1.1520333961755993, "grad_norm": 0.6245613870148877, "learning_rate": 3.8177639792331695e-06, "loss": 0.30937602519989016, "num_input_tokens_seen": 704572960, "step": 17110, "train_runtime": 65957.1263, "train_tokens_per_second": 10682.287 }, { "epoch": 1.1523700511715593, "grad_norm": 0.8899510061959292, "learning_rate": 3.815195037201704e-06, "loss": 0.3430128335952759, "num_input_tokens_seen": 704769088, "step": 17115, "train_runtime": 65976.6782, "train_tokens_per_second": 10682.094 }, { "epoch": 1.1527067061675196, "grad_norm": 0.7755025642580554, "learning_rate": 3.8126264264971694e-06, "loss": 0.3233584642410278, "num_input_tokens_seen": 704979656, "step": 17120, "train_runtime": 65997.0249, "train_tokens_per_second": 10681.991 }, { "epoch": 1.1530433611634796, "grad_norm": 0.7806917911962938, "learning_rate": 3.8100581478378673e-06, "loss": 0.3130837917327881, "num_input_tokens_seen": 705185624, "step": 17125, "train_runtime": 66016.1295, "train_tokens_per_second": 10682.02 }, { "epoch": 1.1533800161594399, "grad_norm": 0.7562962041279871, "learning_rate": 3.807490201942012e-06, "loss": 0.3186499118804932, "num_input_tokens_seen": 705393424, "step": 17130, "train_runtime": 66034.7003, "train_tokens_per_second": 10682.163 }, { "epoch": 1.1537166711553999, "grad_norm": 0.7772286120695365, "learning_rate": 3.804922589527717e-06, "loss": 0.2990067720413208, "num_input_tokens_seen": 705597752, "step": 17135, "train_runtime": 66055.2804, "train_tokens_per_second": 10681.928 }, { "epoch": 1.1540533261513601, "grad_norm": 0.71248674466022, "learning_rate": 3.8023553113130096e-06, "loss": 0.32623093128204345, "num_input_tokens_seen": 705817104, "step": 17140, "train_runtime": 66075.2369, "train_tokens_per_second": 10682.022 }, { "epoch": 1.1543899811473202, "grad_norm": 0.7517736888635698, "learning_rate": 3.799788368015821e-06, "loss": 0.28052196502685545, "num_input_tokens_seen": 706024488, "step": 17145, "train_runtime": 66095.5878, "train_tokens_per_second": 10681.87 }, { "epoch": 1.1547266361432804, "grad_norm": 0.8010371747930743, "learning_rate": 3.7972217603539873e-06, "loss": 0.3098182201385498, "num_input_tokens_seen": 706219480, "step": 17150, "train_runtime": 66114.6938, "train_tokens_per_second": 10681.733 }, { "epoch": 1.1550632911392404, "grad_norm": 0.7819771609024275, "learning_rate": 3.7946554890452524e-06, "loss": 0.31763291358947754, "num_input_tokens_seen": 706433440, "step": 17155, "train_runtime": 66133.7306, "train_tokens_per_second": 10681.893 }, { "epoch": 1.1553999461352007, "grad_norm": 0.7193030176671621, "learning_rate": 3.792089554807269e-06, "loss": 0.31219418048858644, "num_input_tokens_seen": 706646384, "step": 17160, "train_runtime": 66153.9208, "train_tokens_per_second": 10681.852 }, { "epoch": 1.1557366011311607, "grad_norm": 0.7835862398225252, "learning_rate": 3.789523958357587e-06, "loss": 0.318782901763916, "num_input_tokens_seen": 706845416, "step": 17165, "train_runtime": 66172.9384, "train_tokens_per_second": 10681.79 }, { "epoch": 1.156073256127121, "grad_norm": 0.6812493942543434, "learning_rate": 3.7869587004136714e-06, "loss": 0.2786086559295654, "num_input_tokens_seen": 707060024, "step": 17170, "train_runtime": 66191.8125, "train_tokens_per_second": 10681.986 }, { "epoch": 1.156409911123081, "grad_norm": 0.7221691854325631, "learning_rate": 3.7843937816928864e-06, "loss": 0.32367825508117676, "num_input_tokens_seen": 707275680, "step": 17175, "train_runtime": 66211.6792, "train_tokens_per_second": 10682.038 }, { "epoch": 1.1567465661190413, "grad_norm": 0.7620723749999074, "learning_rate": 3.781829202912506e-06, "loss": 0.32339630126953123, "num_input_tokens_seen": 707475520, "step": 17180, "train_runtime": 66231.6397, "train_tokens_per_second": 10681.836 }, { "epoch": 1.1570832211150013, "grad_norm": 0.6990045779966774, "learning_rate": 3.7792649647897023e-06, "loss": 0.30769906044006345, "num_input_tokens_seen": 707687144, "step": 17185, "train_runtime": 66251.9529, "train_tokens_per_second": 10681.755 }, { "epoch": 1.1574198761109615, "grad_norm": 0.7037116425267592, "learning_rate": 3.7767010680415595e-06, "loss": 0.3114015102386475, "num_input_tokens_seen": 707888760, "step": 17190, "train_runtime": 66271.3385, "train_tokens_per_second": 10681.673 }, { "epoch": 1.1577565311069216, "grad_norm": 0.754384028094851, "learning_rate": 3.774137513385061e-06, "loss": 0.30060391426086425, "num_input_tokens_seen": 708096128, "step": 17195, "train_runtime": 66294.092, "train_tokens_per_second": 10681.135 }, { "epoch": 1.1580931861028818, "grad_norm": 0.6745069014684665, "learning_rate": 3.7715743015371005e-06, "loss": 0.31865744590759276, "num_input_tokens_seen": 708311384, "step": 17200, "train_runtime": 66313.335, "train_tokens_per_second": 10681.281 }, { "epoch": 1.1584298410988418, "grad_norm": 0.6405316522687083, "learning_rate": 3.769011433214467e-06, "loss": 0.29127614498138427, "num_input_tokens_seen": 708523056, "step": 17205, "train_runtime": 66334.7807, "train_tokens_per_second": 10681.019 }, { "epoch": 1.158766496094802, "grad_norm": 0.6798827307569494, "learning_rate": 3.766448909133863e-06, "loss": 0.32932534217834475, "num_input_tokens_seen": 708738808, "step": 17210, "train_runtime": 66352.8477, "train_tokens_per_second": 10681.362 }, { "epoch": 1.1591031510907621, "grad_norm": 0.7138437588049951, "learning_rate": 3.7638867300118864e-06, "loss": 0.2925687789916992, "num_input_tokens_seen": 708938672, "step": 17215, "train_runtime": 66370.8719, "train_tokens_per_second": 10681.473 }, { "epoch": 1.1594398060867224, "grad_norm": 0.7467499470752335, "learning_rate": 3.7613248965650447e-06, "loss": 0.2917101621627808, "num_input_tokens_seen": 709148720, "step": 17220, "train_runtime": 66391.1215, "train_tokens_per_second": 10681.379 }, { "epoch": 1.1597764610826824, "grad_norm": 0.6917897806916139, "learning_rate": 3.758763409509745e-06, "loss": 0.30158076286315916, "num_input_tokens_seen": 709362160, "step": 17225, "train_runtime": 66409.334, "train_tokens_per_second": 10681.664 }, { "epoch": 1.1601131160786426, "grad_norm": 0.7618552333496276, "learning_rate": 3.7562022695623013e-06, "loss": 0.3154015064239502, "num_input_tokens_seen": 709568392, "step": 17230, "train_runtime": 66429.6583, "train_tokens_per_second": 10681.5 }, { "epoch": 1.1604497710746027, "grad_norm": 0.6545074710457109, "learning_rate": 3.7536414774389252e-06, "loss": 0.3119531154632568, "num_input_tokens_seen": 709778080, "step": 17235, "train_runtime": 66448.6903, "train_tokens_per_second": 10681.596 }, { "epoch": 1.160786426070563, "grad_norm": 0.7597818135223358, "learning_rate": 3.7510810338557363e-06, "loss": 0.2969247817993164, "num_input_tokens_seen": 709975584, "step": 17240, "train_runtime": 66470.0717, "train_tokens_per_second": 10681.132 }, { "epoch": 1.161123081066523, "grad_norm": 0.7047795158592499, "learning_rate": 3.748520939528753e-06, "loss": 0.30959329605102537, "num_input_tokens_seen": 710182488, "step": 17245, "train_runtime": 66489.8136, "train_tokens_per_second": 10681.072 }, { "epoch": 1.1614597360624832, "grad_norm": 0.7166065378176584, "learning_rate": 3.7459611951739007e-06, "loss": 0.29494998455047605, "num_input_tokens_seen": 710395272, "step": 17250, "train_runtime": 66510.4873, "train_tokens_per_second": 10680.951 }, { "epoch": 1.1617963910584432, "grad_norm": 0.7770009856534741, "learning_rate": 3.7434018015069984e-06, "loss": 0.3229037284851074, "num_input_tokens_seen": 710602624, "step": 17255, "train_runtime": 66530.5393, "train_tokens_per_second": 10680.849 }, { "epoch": 1.1621330460544035, "grad_norm": 0.77230505957683, "learning_rate": 3.740842759243778e-06, "loss": 0.3170770168304443, "num_input_tokens_seen": 710809992, "step": 17260, "train_runtime": 66549.3837, "train_tokens_per_second": 10680.94 }, { "epoch": 1.1624697010503635, "grad_norm": 0.644493459357182, "learning_rate": 3.738284069099862e-06, "loss": 0.2941843032836914, "num_input_tokens_seen": 711027944, "step": 17265, "train_runtime": 66568.959, "train_tokens_per_second": 10681.073 }, { "epoch": 1.1628063560463238, "grad_norm": 0.6888987907488925, "learning_rate": 3.735725731790785e-06, "loss": 0.31150577068328855, "num_input_tokens_seen": 711238656, "step": 17270, "train_runtime": 66587.7183, "train_tokens_per_second": 10681.229 }, { "epoch": 1.1631430110422838, "grad_norm": 0.6764173623755747, "learning_rate": 3.733167748031974e-06, "loss": 0.31149849891662595, "num_input_tokens_seen": 711452664, "step": 17275, "train_runtime": 66607.9013, "train_tokens_per_second": 10681.205 }, { "epoch": 1.163479666038244, "grad_norm": 0.6897458913884149, "learning_rate": 3.7306101185387646e-06, "loss": 0.30630292892456057, "num_input_tokens_seen": 711663376, "step": 17280, "train_runtime": 66626.9795, "train_tokens_per_second": 10681.309 }, { "epoch": 1.163816321034204, "grad_norm": 0.7043772846982618, "learning_rate": 3.728052844026386e-06, "loss": 0.30864758491516114, "num_input_tokens_seen": 711872176, "step": 17285, "train_runtime": 66646.9694, "train_tokens_per_second": 10681.239 }, { "epoch": 1.1641529760301643, "grad_norm": 0.7676672645923556, "learning_rate": 3.7254959252099745e-06, "loss": 0.3003665924072266, "num_input_tokens_seen": 712068592, "step": 17290, "train_runtime": 66666.8041, "train_tokens_per_second": 10681.007 }, { "epoch": 1.1644896310261243, "grad_norm": 0.7432711259866936, "learning_rate": 3.7229393628045617e-06, "loss": 0.2969087600708008, "num_input_tokens_seen": 712279136, "step": 17295, "train_runtime": 66685.9508, "train_tokens_per_second": 10681.097 }, { "epoch": 1.1648262860220846, "grad_norm": 0.6900403722232571, "learning_rate": 3.720383157525087e-06, "loss": 0.2969041347503662, "num_input_tokens_seen": 712486040, "step": 17300, "train_runtime": 66706.2254, "train_tokens_per_second": 10680.953 }, { "epoch": 1.1651629410180446, "grad_norm": 0.7898900846828036, "learning_rate": 3.717827310086379e-06, "loss": 0.3022970199584961, "num_input_tokens_seen": 712686816, "step": 17305, "train_runtime": 66724.6327, "train_tokens_per_second": 10681.015 }, { "epoch": 1.1654995960140049, "grad_norm": 0.723481707626026, "learning_rate": 3.7152718212031778e-06, "loss": 0.309521222114563, "num_input_tokens_seen": 712892376, "step": 17310, "train_runtime": 66743.4685, "train_tokens_per_second": 10681.081 }, { "epoch": 1.165836251009965, "grad_norm": 0.8799865649245666, "learning_rate": 3.7127166915901123e-06, "loss": 0.3438547611236572, "num_input_tokens_seen": 713085536, "step": 17315, "train_runtime": 66762.9367, "train_tokens_per_second": 10680.859 }, { "epoch": 1.1661729060059252, "grad_norm": 0.7195857992587964, "learning_rate": 3.710161921961721e-06, "loss": 0.31651279926300047, "num_input_tokens_seen": 713289576, "step": 17320, "train_runtime": 66781.4253, "train_tokens_per_second": 10680.958 }, { "epoch": 1.1665095610018852, "grad_norm": 0.7156034685506925, "learning_rate": 3.707607513032434e-06, "loss": 0.30170245170593263, "num_input_tokens_seen": 713490992, "step": 17325, "train_runtime": 66799.6031, "train_tokens_per_second": 10681.066 }, { "epoch": 1.1668462159978454, "grad_norm": 0.7599370267881934, "learning_rate": 3.705053465516587e-06, "loss": 0.30138704776763914, "num_input_tokens_seen": 713699392, "step": 17330, "train_runtime": 66818.4947, "train_tokens_per_second": 10681.165 }, { "epoch": 1.1671828709938055, "grad_norm": 0.6918327922853387, "learning_rate": 3.702499780128407e-06, "loss": 0.29648385047912595, "num_input_tokens_seen": 713896048, "step": 17335, "train_runtime": 66838.3929, "train_tokens_per_second": 10680.928 }, { "epoch": 1.1675195259897657, "grad_norm": 0.6921772551896473, "learning_rate": 3.6999464575820266e-06, "loss": 0.30272502899169923, "num_input_tokens_seen": 714101680, "step": 17340, "train_runtime": 66857.8106, "train_tokens_per_second": 10680.901 }, { "epoch": 1.1678561809857257, "grad_norm": 0.6532267838604671, "learning_rate": 3.697393498591473e-06, "loss": 0.29816489219665526, "num_input_tokens_seen": 714310336, "step": 17345, "train_runtime": 66876.7602, "train_tokens_per_second": 10680.995 }, { "epoch": 1.168192835981686, "grad_norm": 0.7480656651352492, "learning_rate": 3.694840903870676e-06, "loss": 0.3265828609466553, "num_input_tokens_seen": 714514344, "step": 17350, "train_runtime": 66894.4707, "train_tokens_per_second": 10681.217 }, { "epoch": 1.168529490977646, "grad_norm": 0.7531196750689878, "learning_rate": 3.6922886741334564e-06, "loss": 0.323640251159668, "num_input_tokens_seen": 714720944, "step": 17355, "train_runtime": 66913.9881, "train_tokens_per_second": 10681.189 }, { "epoch": 1.1688661459736063, "grad_norm": 0.6742419766451474, "learning_rate": 3.689736810093541e-06, "loss": 0.3004702806472778, "num_input_tokens_seen": 714933896, "step": 17360, "train_runtime": 66932.7614, "train_tokens_per_second": 10681.375 }, { "epoch": 1.1692028009695663, "grad_norm": 0.756057448971392, "learning_rate": 3.6871853124645464e-06, "loss": 0.31316466331481935, "num_input_tokens_seen": 715147784, "step": 17365, "train_runtime": 66951.4774, "train_tokens_per_second": 10681.583 }, { "epoch": 1.1695394559655266, "grad_norm": 0.681755953905609, "learning_rate": 3.684634181959994e-06, "loss": 0.3086702346801758, "num_input_tokens_seen": 715366784, "step": 17370, "train_runtime": 66971.2091, "train_tokens_per_second": 10681.706 }, { "epoch": 1.1698761109614866, "grad_norm": 0.8522205229421728, "learning_rate": 3.6820834192932974e-06, "loss": 0.3224832773208618, "num_input_tokens_seen": 715569840, "step": 17375, "train_runtime": 66990.245, "train_tokens_per_second": 10681.702 }, { "epoch": 1.1702127659574468, "grad_norm": 0.7185303395045912, "learning_rate": 3.679533025177772e-06, "loss": 0.33493814468383787, "num_input_tokens_seen": 715794896, "step": 17380, "train_runtime": 67008.9247, "train_tokens_per_second": 10682.083 }, { "epoch": 1.1705494209534069, "grad_norm": 0.9359499515427427, "learning_rate": 3.6769830003266234e-06, "loss": 0.3155909299850464, "num_input_tokens_seen": 716001712, "step": 17385, "train_runtime": 67027.0497, "train_tokens_per_second": 10682.28 }, { "epoch": 1.1708860759493671, "grad_norm": 0.6911887006569156, "learning_rate": 3.6744333454529607e-06, "loss": 0.3123589277267456, "num_input_tokens_seen": 716215672, "step": 17390, "train_runtime": 67046.9392, "train_tokens_per_second": 10682.302 }, { "epoch": 1.1712227309453271, "grad_norm": 0.6742635924859925, "learning_rate": 3.6718840612697847e-06, "loss": 0.30669119358062746, "num_input_tokens_seen": 716435672, "step": 17395, "train_runtime": 67065.9065, "train_tokens_per_second": 10682.562 }, { "epoch": 1.1715593859412874, "grad_norm": 0.7342316459101582, "learning_rate": 3.6693351484899986e-06, "loss": 0.29968438148498533, "num_input_tokens_seen": 716634608, "step": 17400, "train_runtime": 67084.292, "train_tokens_per_second": 10682.599 }, { "epoch": 1.1718960409372474, "grad_norm": 0.9538194299180113, "learning_rate": 3.6667866078263937e-06, "loss": 0.29923510551452637, "num_input_tokens_seen": 716831592, "step": 17405, "train_runtime": 67103.3679, "train_tokens_per_second": 10682.498 }, { "epoch": 1.1722326959332077, "grad_norm": 0.7005369083012444, "learning_rate": 3.664238439991663e-06, "loss": 0.33851332664489747, "num_input_tokens_seen": 717036072, "step": 17410, "train_runtime": 67122.1077, "train_tokens_per_second": 10682.562 }, { "epoch": 1.1725693509291677, "grad_norm": 0.6949867630831911, "learning_rate": 3.6616906456983925e-06, "loss": 0.31352953910827636, "num_input_tokens_seen": 717244616, "step": 17415, "train_runtime": 67140.8499, "train_tokens_per_second": 10682.686 }, { "epoch": 1.172906005925128, "grad_norm": 0.7271577666571051, "learning_rate": 3.659143225659065e-06, "loss": 0.3257251262664795, "num_input_tokens_seen": 717449752, "step": 17420, "train_runtime": 67159.7142, "train_tokens_per_second": 10682.74 }, { "epoch": 1.173242660921088, "grad_norm": 0.672146089312343, "learning_rate": 3.6565961805860595e-06, "loss": 0.30337541103363036, "num_input_tokens_seen": 717667104, "step": 17425, "train_runtime": 67179.0298, "train_tokens_per_second": 10682.904 }, { "epoch": 1.1735793159170482, "grad_norm": 0.6382202746672538, "learning_rate": 3.654049511191649e-06, "loss": 0.304219913482666, "num_input_tokens_seen": 717865872, "step": 17430, "train_runtime": 67198.9581, "train_tokens_per_second": 10682.693 }, { "epoch": 1.1739159709130083, "grad_norm": 0.7135598950635239, "learning_rate": 3.6515032181879995e-06, "loss": 0.30534539222717283, "num_input_tokens_seen": 718071920, "step": 17435, "train_runtime": 67217.848, "train_tokens_per_second": 10682.757 }, { "epoch": 1.1742526259089685, "grad_norm": 0.6460370583793692, "learning_rate": 3.6489573022871755e-06, "loss": 0.28421993255615235, "num_input_tokens_seen": 718278928, "step": 17440, "train_runtime": 67236.7015, "train_tokens_per_second": 10682.84 }, { "epoch": 1.1745892809049285, "grad_norm": 0.6378259591721336, "learning_rate": 3.6464117642011333e-06, "loss": 0.31879563331604005, "num_input_tokens_seen": 718474384, "step": 17445, "train_runtime": 67254.7052, "train_tokens_per_second": 10682.887 }, { "epoch": 1.1749259359008888, "grad_norm": 0.7491397838180105, "learning_rate": 3.643866604641726e-06, "loss": 0.309140682220459, "num_input_tokens_seen": 718690768, "step": 17450, "train_runtime": 67273.7432, "train_tokens_per_second": 10683.08 }, { "epoch": 1.1752625908968488, "grad_norm": 0.7010720293926495, "learning_rate": 3.641321824320697e-06, "loss": 0.2979999780654907, "num_input_tokens_seen": 718898472, "step": 17455, "train_runtime": 67292.709, "train_tokens_per_second": 10683.155 }, { "epoch": 1.175599245892809, "grad_norm": 0.6623134626871885, "learning_rate": 3.6387774239496893e-06, "loss": 0.2913991451263428, "num_input_tokens_seen": 719117408, "step": 17460, "train_runtime": 67311.4491, "train_tokens_per_second": 10683.434 }, { "epoch": 1.175935900888769, "grad_norm": 0.6979967860305579, "learning_rate": 3.6362334042402326e-06, "loss": 0.30728940963745116, "num_input_tokens_seen": 719324352, "step": 17465, "train_runtime": 67330.8693, "train_tokens_per_second": 10683.426 }, { "epoch": 1.1762725558847293, "grad_norm": 0.6828902083649786, "learning_rate": 3.6336897659037563e-06, "loss": 0.28564019203186036, "num_input_tokens_seen": 719519888, "step": 17470, "train_runtime": 67349.727, "train_tokens_per_second": 10683.338 }, { "epoch": 1.1766092108806894, "grad_norm": 0.7405616425515584, "learning_rate": 3.6311465096515787e-06, "loss": 0.29876017570495605, "num_input_tokens_seen": 719729832, "step": 17475, "train_runtime": 67367.7152, "train_tokens_per_second": 10683.602 }, { "epoch": 1.1769458658766496, "grad_norm": 0.6926725361492173, "learning_rate": 3.6286036361949175e-06, "loss": 0.27777059078216554, "num_input_tokens_seen": 719942016, "step": 17480, "train_runtime": 67387.2714, "train_tokens_per_second": 10683.65 }, { "epoch": 1.1772825208726099, "grad_norm": 0.6590197455624078, "learning_rate": 3.6260611462448736e-06, "loss": 0.25676898956298827, "num_input_tokens_seen": 720152800, "step": 17485, "train_runtime": 67406.2464, "train_tokens_per_second": 10683.77 }, { "epoch": 1.17761917586857, "grad_norm": 0.9266617524304033, "learning_rate": 3.623519040512451e-06, "loss": 0.34525039196014407, "num_input_tokens_seen": 720346088, "step": 17490, "train_runtime": 67424.2542, "train_tokens_per_second": 10683.783 }, { "epoch": 1.17795583086453, "grad_norm": 0.5909492780505631, "learning_rate": 3.6209773197085373e-06, "loss": 0.2708892345428467, "num_input_tokens_seen": 720556128, "step": 17495, "train_runtime": 67443.0874, "train_tokens_per_second": 10683.914 }, { "epoch": 1.1782924858604902, "grad_norm": 0.7247251143385863, "learning_rate": 3.6184359845439214e-06, "loss": 0.3106063365936279, "num_input_tokens_seen": 720773696, "step": 17500, "train_runtime": 67461.5432, "train_tokens_per_second": 10684.216 }, { "epoch": 1.1786291408564504, "grad_norm": 0.7406379075682019, "learning_rate": 3.615895035729275e-06, "loss": 0.3288693904876709, "num_input_tokens_seen": 720986600, "step": 17505, "train_runtime": 67480.1259, "train_tokens_per_second": 10684.429 }, { "epoch": 1.1789657958524105, "grad_norm": 0.6958415436243985, "learning_rate": 3.6133544739751703e-06, "loss": 0.2980682611465454, "num_input_tokens_seen": 721187040, "step": 17510, "train_runtime": 67500.1921, "train_tokens_per_second": 10684.222 }, { "epoch": 1.1793024508483705, "grad_norm": 0.7134026477171662, "learning_rate": 3.6108142999920633e-06, "loss": 0.31394646167755125, "num_input_tokens_seen": 721391312, "step": 17515, "train_runtime": 67519.0723, "train_tokens_per_second": 10684.26 }, { "epoch": 1.1796391058443307, "grad_norm": 0.6913112773500256, "learning_rate": 3.608274514490308e-06, "loss": 0.308346152305603, "num_input_tokens_seen": 721603112, "step": 17520, "train_runtime": 67538.6091, "train_tokens_per_second": 10684.305 }, { "epoch": 1.179975760840291, "grad_norm": 0.720792895065273, "learning_rate": 3.605735118180146e-06, "loss": 0.29197039604187014, "num_input_tokens_seen": 721812784, "step": 17525, "train_runtime": 67559.1323, "train_tokens_per_second": 10684.163 }, { "epoch": 1.180312415836251, "grad_norm": 0.6911099983957475, "learning_rate": 3.6031961117717144e-06, "loss": 0.2815223217010498, "num_input_tokens_seen": 722014032, "step": 17530, "train_runtime": 67579.0404, "train_tokens_per_second": 10683.994 }, { "epoch": 1.180649070832211, "grad_norm": 0.6596671416758735, "learning_rate": 3.600657495975034e-06, "loss": 0.29863605499267576, "num_input_tokens_seen": 722226744, "step": 17535, "train_runtime": 67598.6302, "train_tokens_per_second": 10684.044 }, { "epoch": 1.1809857258281713, "grad_norm": 0.6653102618428227, "learning_rate": 3.598119271500024e-06, "loss": 0.30046353340148924, "num_input_tokens_seen": 722430888, "step": 17540, "train_runtime": 67616.6945, "train_tokens_per_second": 10684.209 }, { "epoch": 1.1813223808241315, "grad_norm": 0.730201966314085, "learning_rate": 3.5955814390564882e-06, "loss": 0.2972467660903931, "num_input_tokens_seen": 722639968, "step": 17545, "train_runtime": 67635.0488, "train_tokens_per_second": 10684.401 }, { "epoch": 1.1816590358200916, "grad_norm": 0.7183576377069558, "learning_rate": 3.5930439993541265e-06, "loss": 0.30849251747131345, "num_input_tokens_seen": 722839240, "step": 17550, "train_runtime": 67653.6917, "train_tokens_per_second": 10684.402 }, { "epoch": 1.1819956908160516, "grad_norm": 0.7293274664485399, "learning_rate": 3.590506953102522e-06, "loss": 0.32335858345031737, "num_input_tokens_seen": 723043152, "step": 17555, "train_runtime": 67672.5177, "train_tokens_per_second": 10684.443 }, { "epoch": 1.1823323458120119, "grad_norm": 0.6708609571699888, "learning_rate": 3.5879703010111554e-06, "loss": 0.3123878717422485, "num_input_tokens_seen": 723246616, "step": 17560, "train_runtime": 67691.6949, "train_tokens_per_second": 10684.422 }, { "epoch": 1.182669000807972, "grad_norm": 0.662994491365883, "learning_rate": 3.5854340437893898e-06, "loss": 0.3020447015762329, "num_input_tokens_seen": 723455920, "step": 17565, "train_runtime": 67709.6236, "train_tokens_per_second": 10684.684 }, { "epoch": 1.1830056558039321, "grad_norm": 0.7651186797615303, "learning_rate": 3.5828981821464838e-06, "loss": 0.3153041124343872, "num_input_tokens_seen": 723653192, "step": 17570, "train_runtime": 67730.4176, "train_tokens_per_second": 10684.316 }, { "epoch": 1.1833423107998922, "grad_norm": 0.7151287594011021, "learning_rate": 3.580362716791582e-06, "loss": 0.3226076364517212, "num_input_tokens_seen": 723870384, "step": 17575, "train_runtime": 67748.7539, "train_tokens_per_second": 10684.63 }, { "epoch": 1.1836789657958524, "grad_norm": 0.7106622554471821, "learning_rate": 3.5778276484337205e-06, "loss": 0.33576083183288574, "num_input_tokens_seen": 724068888, "step": 17580, "train_runtime": 67767.5925, "train_tokens_per_second": 10684.589 }, { "epoch": 1.1840156207918127, "grad_norm": 0.6555059307314863, "learning_rate": 3.575292977781821e-06, "loss": 0.29345502853393557, "num_input_tokens_seen": 724268088, "step": 17585, "train_runtime": 67786.4485, "train_tokens_per_second": 10684.556 }, { "epoch": 1.1843522757877727, "grad_norm": 0.7772537150763288, "learning_rate": 3.5727587055446976e-06, "loss": 0.3035531997680664, "num_input_tokens_seen": 724482944, "step": 17590, "train_runtime": 67806.443, "train_tokens_per_second": 10684.574 }, { "epoch": 1.1846889307837327, "grad_norm": 0.6545366645375393, "learning_rate": 3.570224832431051e-06, "loss": 0.3242922782897949, "num_input_tokens_seen": 724692248, "step": 17595, "train_runtime": 67825.6733, "train_tokens_per_second": 10684.63 }, { "epoch": 1.185025585779693, "grad_norm": 0.7466476133447492, "learning_rate": 3.5676913591494715e-06, "loss": 0.30276031494140626, "num_input_tokens_seen": 724902616, "step": 17600, "train_runtime": 67845.509, "train_tokens_per_second": 10684.607 }, { "epoch": 1.1853622407756532, "grad_norm": 0.6732687841283859, "learning_rate": 3.5651582864084345e-06, "loss": 0.32857885360717776, "num_input_tokens_seen": 725108832, "step": 17605, "train_runtime": 67865.6038, "train_tokens_per_second": 10684.482 }, { "epoch": 1.1856988957716132, "grad_norm": 0.7189015696424338, "learning_rate": 3.5626256149163096e-06, "loss": 0.30852909088134767, "num_input_tokens_seen": 725314448, "step": 17610, "train_runtime": 67884.8032, "train_tokens_per_second": 10684.489 }, { "epoch": 1.1860355507675733, "grad_norm": 0.7370494944097495, "learning_rate": 3.5600933453813464e-06, "loss": 0.30918169021606445, "num_input_tokens_seen": 725518544, "step": 17615, "train_runtime": 67903.7295, "train_tokens_per_second": 10684.517 }, { "epoch": 1.1863722057635335, "grad_norm": 0.6836530360809941, "learning_rate": 3.5575614785116886e-06, "loss": 0.28793432712554934, "num_input_tokens_seen": 725719848, "step": 17620, "train_runtime": 67923.1046, "train_tokens_per_second": 10684.433 }, { "epoch": 1.1867088607594938, "grad_norm": 0.8066613191638661, "learning_rate": 3.5550300150153618e-06, "loss": 0.3081228256225586, "num_input_tokens_seen": 725927064, "step": 17625, "train_runtime": 67941.9869, "train_tokens_per_second": 10684.513 }, { "epoch": 1.1870455157554538, "grad_norm": 0.7581013405482098, "learning_rate": 3.5524989556002863e-06, "loss": 0.30070838928222654, "num_input_tokens_seen": 726132544, "step": 17630, "train_runtime": 67962.3558, "train_tokens_per_second": 10684.335 }, { "epoch": 1.1873821707514138, "grad_norm": 0.6606242760416289, "learning_rate": 3.5499683009742604e-06, "loss": 0.2986333131790161, "num_input_tokens_seen": 726325040, "step": 17635, "train_runtime": 67981.1187, "train_tokens_per_second": 10684.217 }, { "epoch": 1.187718825747374, "grad_norm": 0.7575522942715688, "learning_rate": 3.5474380518449757e-06, "loss": 0.29784843921661375, "num_input_tokens_seen": 726533168, "step": 17640, "train_runtime": 67999.9973, "train_tokens_per_second": 10684.312 }, { "epoch": 1.1880554807433343, "grad_norm": 0.7955218823494715, "learning_rate": 3.5449082089200072e-06, "loss": 0.30785579681396485, "num_input_tokens_seen": 726741800, "step": 17645, "train_runtime": 68020.4577, "train_tokens_per_second": 10684.165 }, { "epoch": 1.1883921357392944, "grad_norm": 0.681750288169353, "learning_rate": 3.5423787729068206e-06, "loss": 0.32306158542633057, "num_input_tokens_seen": 726949728, "step": 17650, "train_runtime": 68038.8207, "train_tokens_per_second": 10684.338 }, { "epoch": 1.1887287907352544, "grad_norm": 0.6769437388698892, "learning_rate": 3.539849744512759e-06, "loss": 0.2949356555938721, "num_input_tokens_seen": 727149856, "step": 17655, "train_runtime": 68058.6449, "train_tokens_per_second": 10684.166 }, { "epoch": 1.1890654457312146, "grad_norm": 0.699196640158942, "learning_rate": 3.5373211244450633e-06, "loss": 0.29924783706665037, "num_input_tokens_seen": 727362976, "step": 17660, "train_runtime": 68079.5986, "train_tokens_per_second": 10684.008 }, { "epoch": 1.189402100727175, "grad_norm": 0.703163011379877, "learning_rate": 3.5347929134108483e-06, "loss": 0.3229963302612305, "num_input_tokens_seen": 727564760, "step": 17665, "train_runtime": 68099.3052, "train_tokens_per_second": 10683.879 }, { "epoch": 1.189738755723135, "grad_norm": 0.852911734106207, "learning_rate": 3.532265112117125e-06, "loss": 0.3388907194137573, "num_input_tokens_seen": 727779632, "step": 17670, "train_runtime": 68120.7866, "train_tokens_per_second": 10683.665 }, { "epoch": 1.190075410719095, "grad_norm": 0.6765203150221863, "learning_rate": 3.5297377212707805e-06, "loss": 0.26041998863220217, "num_input_tokens_seen": 727979464, "step": 17675, "train_runtime": 68138.5331, "train_tokens_per_second": 10683.815 }, { "epoch": 1.1904120657150552, "grad_norm": 0.7465361740017314, "learning_rate": 3.527210741578596e-06, "loss": 0.3029452323913574, "num_input_tokens_seen": 728188448, "step": 17680, "train_runtime": 68156.9238, "train_tokens_per_second": 10683.998 }, { "epoch": 1.1907487207110155, "grad_norm": 0.7183512201571829, "learning_rate": 3.5246841737472304e-06, "loss": 0.3176783561706543, "num_input_tokens_seen": 728385328, "step": 17685, "train_runtime": 68176.3418, "train_tokens_per_second": 10683.843 }, { "epoch": 1.1910853757069755, "grad_norm": 0.704595828893867, "learning_rate": 3.522158018483231e-06, "loss": 0.29078810214996337, "num_input_tokens_seen": 728599048, "step": 17690, "train_runtime": 68195.8105, "train_tokens_per_second": 10683.927 }, { "epoch": 1.1914220307029355, "grad_norm": 0.725820801499685, "learning_rate": 3.519632276493029e-06, "loss": 0.30874061584472656, "num_input_tokens_seen": 728806216, "step": 17695, "train_runtime": 68216.3609, "train_tokens_per_second": 10683.745 }, { "epoch": 1.1917586856988958, "grad_norm": 0.7496187046857212, "learning_rate": 3.5171069484829417e-06, "loss": 0.3303786039352417, "num_input_tokens_seen": 729010632, "step": 17700, "train_runtime": 68236.0775, "train_tokens_per_second": 10683.654 }, { "epoch": 1.192095340694856, "grad_norm": 0.7477530138834542, "learning_rate": 3.5145820351591663e-06, "loss": 0.28746519088745115, "num_input_tokens_seen": 729210528, "step": 17705, "train_runtime": 68256.9541, "train_tokens_per_second": 10683.315 }, { "epoch": 1.192431995690816, "grad_norm": 0.7499922741748304, "learning_rate": 3.51205753722779e-06, "loss": 0.31944828033447265, "num_input_tokens_seen": 729425296, "step": 17710, "train_runtime": 68276.0448, "train_tokens_per_second": 10683.473 }, { "epoch": 1.1927686506867763, "grad_norm": 0.8997832488285092, "learning_rate": 3.5095334553947757e-06, "loss": 0.3356014251708984, "num_input_tokens_seen": 729640632, "step": 17715, "train_runtime": 68295.111, "train_tokens_per_second": 10683.644 }, { "epoch": 1.1931053056827363, "grad_norm": 0.6847793751909945, "learning_rate": 3.50700979036598e-06, "loss": 0.3046675443649292, "num_input_tokens_seen": 729844376, "step": 17720, "train_runtime": 68313.0038, "train_tokens_per_second": 10683.828 }, { "epoch": 1.1934419606786966, "grad_norm": 0.7394304255515136, "learning_rate": 3.5044865428471343e-06, "loss": 0.29175395965576173, "num_input_tokens_seen": 730038936, "step": 17725, "train_runtime": 68330.9904, "train_tokens_per_second": 10683.863 }, { "epoch": 1.1937786156746566, "grad_norm": 0.6883417513439538, "learning_rate": 3.50196371354386e-06, "loss": 0.3087155818939209, "num_input_tokens_seen": 730242304, "step": 17730, "train_runtime": 68350.0221, "train_tokens_per_second": 10683.863 }, { "epoch": 1.1941152706706168, "grad_norm": 0.8120225569839213, "learning_rate": 3.499441303161655e-06, "loss": 0.33836443424224855, "num_input_tokens_seen": 730453440, "step": 17735, "train_runtime": 68369.5867, "train_tokens_per_second": 10683.894 }, { "epoch": 1.1944519256665769, "grad_norm": 0.6203745023475443, "learning_rate": 3.4969193124059042e-06, "loss": 0.2864560604095459, "num_input_tokens_seen": 730665824, "step": 17740, "train_runtime": 68388.0875, "train_tokens_per_second": 10684.11 }, { "epoch": 1.1947885806625371, "grad_norm": 0.6627970284615048, "learning_rate": 3.4943977419818748e-06, "loss": 0.29851541519165037, "num_input_tokens_seen": 730884056, "step": 17745, "train_runtime": 68407.0073, "train_tokens_per_second": 10684.345 }, { "epoch": 1.1951252356584972, "grad_norm": 0.6785425233954268, "learning_rate": 3.4918765925947173e-06, "loss": 0.29342851638793943, "num_input_tokens_seen": 731096480, "step": 17750, "train_runtime": 68426.4564, "train_tokens_per_second": 10684.412 }, { "epoch": 1.1954618906544574, "grad_norm": 0.7692957066381655, "learning_rate": 3.4893558649494595e-06, "loss": 0.3239474058151245, "num_input_tokens_seen": 731315904, "step": 17755, "train_runtime": 68448.4677, "train_tokens_per_second": 10684.182 }, { "epoch": 1.1957985456504174, "grad_norm": 0.7248316635192859, "learning_rate": 3.4868355597510194e-06, "loss": 0.2885741233825684, "num_input_tokens_seen": 731520704, "step": 17760, "train_runtime": 68467.9888, "train_tokens_per_second": 10684.127 }, { "epoch": 1.1961352006463777, "grad_norm": 0.7510210169551087, "learning_rate": 3.4843156777041887e-06, "loss": 0.28222002983093264, "num_input_tokens_seen": 731730840, "step": 17765, "train_runtime": 68486.2028, "train_tokens_per_second": 10684.354 }, { "epoch": 1.1964718556423377, "grad_norm": 0.7382043849733675, "learning_rate": 3.4817962195136457e-06, "loss": 0.30564179420471194, "num_input_tokens_seen": 731934496, "step": 17770, "train_runtime": 68505.5738, "train_tokens_per_second": 10684.306 }, { "epoch": 1.196808510638298, "grad_norm": 0.8141965168621838, "learning_rate": 3.479277185883947e-06, "loss": 0.309740686416626, "num_input_tokens_seen": 732136744, "step": 17775, "train_runtime": 68525.7461, "train_tokens_per_second": 10684.112 }, { "epoch": 1.197145165634258, "grad_norm": 0.6815150922702382, "learning_rate": 3.476758577519537e-06, "loss": 0.29441032409667967, "num_input_tokens_seen": 732341560, "step": 17780, "train_runtime": 68544.1213, "train_tokens_per_second": 10684.236 }, { "epoch": 1.1974818206302182, "grad_norm": 0.7545035936748367, "learning_rate": 3.4742403951247318e-06, "loss": 0.3076906681060791, "num_input_tokens_seen": 732549344, "step": 17785, "train_runtime": 68564.2473, "train_tokens_per_second": 10684.13 }, { "epoch": 1.1978184756261783, "grad_norm": 0.767870625387586, "learning_rate": 3.471722639403735e-06, "loss": 0.2888141632080078, "num_input_tokens_seen": 732751536, "step": 17790, "train_runtime": 68584.1793, "train_tokens_per_second": 10683.973 }, { "epoch": 1.1981551306221385, "grad_norm": 0.7365573329575077, "learning_rate": 3.4692053110606277e-06, "loss": 0.30224382877349854, "num_input_tokens_seen": 732942344, "step": 17795, "train_runtime": 68604.6052, "train_tokens_per_second": 10683.574 }, { "epoch": 1.1984917856180985, "grad_norm": 0.6294171311683796, "learning_rate": 3.4666884107993766e-06, "loss": 0.2915024995803833, "num_input_tokens_seen": 733142832, "step": 17800, "train_runtime": 68623.1492, "train_tokens_per_second": 10683.608 }, { "epoch": 1.1988284406140588, "grad_norm": 0.6984724105138278, "learning_rate": 3.464171939323819e-06, "loss": 0.29935450553894044, "num_input_tokens_seen": 733348240, "step": 17805, "train_runtime": 68643.9012, "train_tokens_per_second": 10683.371 }, { "epoch": 1.1991650956100188, "grad_norm": 0.7459995874633606, "learning_rate": 3.4616558973376848e-06, "loss": 0.30455989837646485, "num_input_tokens_seen": 733546192, "step": 17810, "train_runtime": 68662.5429, "train_tokens_per_second": 10683.353 }, { "epoch": 1.199501750605979, "grad_norm": 0.791649230032538, "learning_rate": 3.4591402855445697e-06, "loss": 0.3059530735015869, "num_input_tokens_seen": 733753432, "step": 17815, "train_runtime": 68680.8813, "train_tokens_per_second": 10683.518 }, { "epoch": 1.199838405601939, "grad_norm": 0.6881766700410581, "learning_rate": 3.4566251046479625e-06, "loss": 0.3043722152709961, "num_input_tokens_seen": 733962336, "step": 17820, "train_runtime": 68700.9815, "train_tokens_per_second": 10683.433 }, { "epoch": 1.2001750605978994, "grad_norm": 0.7338341370678246, "learning_rate": 3.454110355351221e-06, "loss": 0.31304953098297117, "num_input_tokens_seen": 734169736, "step": 17825, "train_runtime": 68721.8906, "train_tokens_per_second": 10683.201 }, { "epoch": 1.2005117155938594, "grad_norm": 0.7217290423800663, "learning_rate": 3.451596038357593e-06, "loss": 0.3037586212158203, "num_input_tokens_seen": 734385456, "step": 17830, "train_runtime": 68740.8306, "train_tokens_per_second": 10683.395 }, { "epoch": 1.2008483705898196, "grad_norm": 0.7487096109674051, "learning_rate": 3.4490821543701924e-06, "loss": 0.3273715257644653, "num_input_tokens_seen": 734595840, "step": 17835, "train_runtime": 68760.6167, "train_tokens_per_second": 10683.381 }, { "epoch": 1.2011850255857797, "grad_norm": 0.6741410742044736, "learning_rate": 3.4465687040920227e-06, "loss": 0.3143296718597412, "num_input_tokens_seen": 734805976, "step": 17840, "train_runtime": 68780.0087, "train_tokens_per_second": 10683.424 }, { "epoch": 1.20152168058174, "grad_norm": 0.6232391620178972, "learning_rate": 3.44405568822596e-06, "loss": 0.2791558504104614, "num_input_tokens_seen": 735011656, "step": 17845, "train_runtime": 68799.8347, "train_tokens_per_second": 10683.335 }, { "epoch": 1.2018583355777, "grad_norm": 0.812392825275549, "learning_rate": 3.441543107474765e-06, "loss": 0.3003761053085327, "num_input_tokens_seen": 735207280, "step": 17850, "train_runtime": 68817.6295, "train_tokens_per_second": 10683.415 }, { "epoch": 1.2021949905736602, "grad_norm": 0.7716161452178484, "learning_rate": 3.439030962541069e-06, "loss": 0.3002284288406372, "num_input_tokens_seen": 735410928, "step": 17855, "train_runtime": 68836.0378, "train_tokens_per_second": 10683.516 }, { "epoch": 1.2025316455696202, "grad_norm": 0.725365617106607, "learning_rate": 3.4365192541273885e-06, "loss": 0.3054239511489868, "num_input_tokens_seen": 735602512, "step": 17860, "train_runtime": 68855.253, "train_tokens_per_second": 10683.317 }, { "epoch": 1.2028683005655805, "grad_norm": 0.756827024377306, "learning_rate": 3.4340079829361108e-06, "loss": 0.3199190616607666, "num_input_tokens_seen": 735796448, "step": 17865, "train_runtime": 68873.6525, "train_tokens_per_second": 10683.279 }, { "epoch": 1.2032049555615405, "grad_norm": 0.712003721743229, "learning_rate": 3.4314971496695078e-06, "loss": 0.3198267459869385, "num_input_tokens_seen": 736008368, "step": 17870, "train_runtime": 68891.6407, "train_tokens_per_second": 10683.566 }, { "epoch": 1.2035416105575008, "grad_norm": 0.6885957457632107, "learning_rate": 3.428986755029724e-06, "loss": 0.28827862739562987, "num_input_tokens_seen": 736225864, "step": 17875, "train_runtime": 68911.7321, "train_tokens_per_second": 10683.607 }, { "epoch": 1.2038782655534608, "grad_norm": 0.6928485352377637, "learning_rate": 3.4264767997187874e-06, "loss": 0.3020036697387695, "num_input_tokens_seen": 736440984, "step": 17880, "train_runtime": 68930.0155, "train_tokens_per_second": 10683.894 }, { "epoch": 1.204214920549421, "grad_norm": 0.7075656371200756, "learning_rate": 3.423967284438594e-06, "loss": 0.3122206211090088, "num_input_tokens_seen": 736639560, "step": 17885, "train_runtime": 68948.0457, "train_tokens_per_second": 10683.98 }, { "epoch": 1.204551575545381, "grad_norm": 0.6500830755143668, "learning_rate": 3.421458209890925e-06, "loss": 0.29749250411987305, "num_input_tokens_seen": 736855408, "step": 17890, "train_runtime": 68965.6897, "train_tokens_per_second": 10684.377 }, { "epoch": 1.2048882305413413, "grad_norm": 0.6522883463705001, "learning_rate": 3.418949576777433e-06, "loss": 0.29423112869262696, "num_input_tokens_seen": 737071616, "step": 17895, "train_runtime": 68984.4775, "train_tokens_per_second": 10684.601 }, { "epoch": 1.2052248855373013, "grad_norm": 0.7395380063824009, "learning_rate": 3.4164413857996513e-06, "loss": 0.29544355869293215, "num_input_tokens_seen": 737270128, "step": 17900, "train_runtime": 69003.2455, "train_tokens_per_second": 10684.572 }, { "epoch": 1.2055615405332616, "grad_norm": 0.7682170976152174, "learning_rate": 3.4139336376589853e-06, "loss": 0.2901193857192993, "num_input_tokens_seen": 737482688, "step": 17905, "train_runtime": 69021.3936, "train_tokens_per_second": 10684.842 }, { "epoch": 1.2058981955292216, "grad_norm": 0.8440628411936453, "learning_rate": 3.411426333056722e-06, "loss": 0.30626816749572755, "num_input_tokens_seen": 737675336, "step": 17910, "train_runtime": 69041.8133, "train_tokens_per_second": 10684.472 }, { "epoch": 1.2062348505251819, "grad_norm": 0.7490095963289807, "learning_rate": 3.408919472694017e-06, "loss": 0.3193103075027466, "num_input_tokens_seen": 737887360, "step": 17915, "train_runtime": 69060.976, "train_tokens_per_second": 10684.578 }, { "epoch": 1.206571505521142, "grad_norm": 0.6906432316711424, "learning_rate": 3.406413057271909e-06, "loss": 0.3023536682128906, "num_input_tokens_seen": 738089016, "step": 17920, "train_runtime": 69078.8797, "train_tokens_per_second": 10684.728 }, { "epoch": 1.2069081605171021, "grad_norm": 0.7224579385243994, "learning_rate": 3.403907087491306e-06, "loss": 0.30785071849823, "num_input_tokens_seen": 738293208, "step": 17925, "train_runtime": 69096.8139, "train_tokens_per_second": 10684.91 }, { "epoch": 1.2072448155130622, "grad_norm": 0.6994648655076282, "learning_rate": 3.4014015640529996e-06, "loss": 0.3035434722900391, "num_input_tokens_seen": 738495536, "step": 17930, "train_runtime": 69114.6192, "train_tokens_per_second": 10685.084 }, { "epoch": 1.2075814705090224, "grad_norm": 0.7278309577047221, "learning_rate": 3.398896487657646e-06, "loss": 0.31152901649475095, "num_input_tokens_seen": 738702840, "step": 17935, "train_runtime": 69134.057, "train_tokens_per_second": 10685.079 }, { "epoch": 1.2079181255049825, "grad_norm": 0.7740869036208515, "learning_rate": 3.396391859005785e-06, "loss": 0.30003743171691893, "num_input_tokens_seen": 738911192, "step": 17940, "train_runtime": 69151.3373, "train_tokens_per_second": 10685.422 }, { "epoch": 1.2082547805009427, "grad_norm": 0.657743850686156, "learning_rate": 3.393887678797826e-06, "loss": 0.29850115776062014, "num_input_tokens_seen": 739109072, "step": 17945, "train_runtime": 69170.014, "train_tokens_per_second": 10685.397 }, { "epoch": 1.2085914354969027, "grad_norm": 0.7201034030909015, "learning_rate": 3.3913839477340575e-06, "loss": 0.3103626012802124, "num_input_tokens_seen": 739311376, "step": 17950, "train_runtime": 69187.3911, "train_tokens_per_second": 10685.637 }, { "epoch": 1.208928090492863, "grad_norm": 0.7491090931319567, "learning_rate": 3.388880666514637e-06, "loss": 0.28342177867889407, "num_input_tokens_seen": 739523912, "step": 17955, "train_runtime": 69206.5255, "train_tokens_per_second": 10685.754 }, { "epoch": 1.209264745488823, "grad_norm": 0.6882062017161817, "learning_rate": 3.3863778358396033e-06, "loss": 0.315179443359375, "num_input_tokens_seen": 739728592, "step": 17960, "train_runtime": 69226.1541, "train_tokens_per_second": 10685.681 }, { "epoch": 1.2096014004847833, "grad_norm": 0.6867147523814923, "learning_rate": 3.3838754564088592e-06, "loss": 0.2980120420455933, "num_input_tokens_seen": 739940528, "step": 17965, "train_runtime": 69246.5159, "train_tokens_per_second": 10685.599 }, { "epoch": 1.2099380554807433, "grad_norm": 0.8047896741216257, "learning_rate": 3.3813735289221923e-06, "loss": 0.29705655574798584, "num_input_tokens_seen": 740146672, "step": 17970, "train_runtime": 69266.988, "train_tokens_per_second": 10685.417 }, { "epoch": 1.2102747104767035, "grad_norm": 0.6272716756459787, "learning_rate": 3.378872054079255e-06, "loss": 0.29434235095977784, "num_input_tokens_seen": 740352352, "step": 17975, "train_runtime": 69286.2967, "train_tokens_per_second": 10685.408 }, { "epoch": 1.2106113654726636, "grad_norm": 0.7735904584852069, "learning_rate": 3.3763710325795784e-06, "loss": 0.33016190528869627, "num_input_tokens_seen": 740545272, "step": 17980, "train_runtime": 69304.6981, "train_tokens_per_second": 10685.355 }, { "epoch": 1.2109480204686238, "grad_norm": 0.6867244532891108, "learning_rate": 3.3738704651225673e-06, "loss": 0.29891936779022216, "num_input_tokens_seen": 740759736, "step": 17985, "train_runtime": 69324.5353, "train_tokens_per_second": 10685.391 }, { "epoch": 1.2112846754645838, "grad_norm": 0.7340123422888678, "learning_rate": 3.3713703524074936e-06, "loss": 0.27559826374053953, "num_input_tokens_seen": 740953624, "step": 17990, "train_runtime": 69344.4006, "train_tokens_per_second": 10685.126 }, { "epoch": 1.211621330460544, "grad_norm": 0.79149141626913, "learning_rate": 3.3688706951335082e-06, "loss": 0.31748509407043457, "num_input_tokens_seen": 741146248, "step": 17995, "train_runtime": 69363.372, "train_tokens_per_second": 10684.98 }, { "epoch": 1.2119579854565041, "grad_norm": 0.6793737882921903, "learning_rate": 3.3663714939996305e-06, "loss": 0.30954315662384035, "num_input_tokens_seen": 741366120, "step": 18000, "train_runtime": 69381.861, "train_tokens_per_second": 10685.302 }, { "epoch": 1.2122946404524644, "grad_norm": 0.7133521458769285, "learning_rate": 3.3638727497047575e-06, "loss": 0.29133317470550535, "num_input_tokens_seen": 741559296, "step": 18005, "train_runtime": 69400.8384, "train_tokens_per_second": 10685.163 }, { "epoch": 1.2126312954484244, "grad_norm": 0.6874242852462028, "learning_rate": 3.3613744629476507e-06, "loss": 0.2952426910400391, "num_input_tokens_seen": 741761224, "step": 18010, "train_runtime": 69420.8177, "train_tokens_per_second": 10684.997 }, { "epoch": 1.2129679504443847, "grad_norm": 0.7204070539430654, "learning_rate": 3.358876634426952e-06, "loss": 0.2810047149658203, "num_input_tokens_seen": 741972600, "step": 18015, "train_runtime": 69441.0189, "train_tokens_per_second": 10684.932 }, { "epoch": 1.2133046054403447, "grad_norm": 0.6612189987209744, "learning_rate": 3.3563792648411676e-06, "loss": 0.3166376829147339, "num_input_tokens_seen": 742165232, "step": 18020, "train_runtime": 69458.7313, "train_tokens_per_second": 10684.981 }, { "epoch": 1.213641260436305, "grad_norm": 0.705023975711425, "learning_rate": 3.353882354888681e-06, "loss": 0.28996222019195556, "num_input_tokens_seen": 742372808, "step": 18025, "train_runtime": 69478.4079, "train_tokens_per_second": 10684.943 }, { "epoch": 1.213977915432265, "grad_norm": 0.7202075965957143, "learning_rate": 3.3513859052677444e-06, "loss": 0.27007815837860105, "num_input_tokens_seen": 742562856, "step": 18030, "train_runtime": 69496.9116, "train_tokens_per_second": 10684.832 }, { "epoch": 1.2143145704282252, "grad_norm": 0.7698634954475935, "learning_rate": 3.3488899166764842e-06, "loss": 0.3234349250793457, "num_input_tokens_seen": 742773536, "step": 18035, "train_runtime": 69515.3123, "train_tokens_per_second": 10685.035 }, { "epoch": 1.2146512254241852, "grad_norm": 0.7793218386520226, "learning_rate": 3.346394389812892e-06, "loss": 0.304577112197876, "num_input_tokens_seen": 742979112, "step": 18040, "train_runtime": 69532.9408, "train_tokens_per_second": 10685.282 }, { "epoch": 1.2149878804201455, "grad_norm": 0.6733900962854995, "learning_rate": 3.3438993253748365e-06, "loss": 0.2960213184356689, "num_input_tokens_seen": 743179472, "step": 18045, "train_runtime": 69552.6831, "train_tokens_per_second": 10685.13 }, { "epoch": 1.2153245354161055, "grad_norm": 0.6739381822652963, "learning_rate": 3.3414047240600526e-06, "loss": 0.3035456657409668, "num_input_tokens_seen": 743388888, "step": 18050, "train_runtime": 69572.2721, "train_tokens_per_second": 10685.132 }, { "epoch": 1.2156611904120658, "grad_norm": 0.8585723385699645, "learning_rate": 3.338910586566151e-06, "loss": 0.304868221282959, "num_input_tokens_seen": 743584456, "step": 18055, "train_runtime": 69589.9122, "train_tokens_per_second": 10685.233 }, { "epoch": 1.2159978454080258, "grad_norm": 0.7059341536287214, "learning_rate": 3.336416913590605e-06, "loss": 0.2997075080871582, "num_input_tokens_seen": 743780904, "step": 18060, "train_runtime": 69608.6438, "train_tokens_per_second": 10685.18 }, { "epoch": 1.216334500403986, "grad_norm": 0.7516795535409296, "learning_rate": 3.333923705830766e-06, "loss": 0.3195933818817139, "num_input_tokens_seen": 743992064, "step": 18065, "train_runtime": 69629.1964, "train_tokens_per_second": 10685.059 }, { "epoch": 1.216671155399946, "grad_norm": 0.7632272434336794, "learning_rate": 3.3314309639838484e-06, "loss": 0.32642245292663574, "num_input_tokens_seen": 744198368, "step": 18070, "train_runtime": 69646.9698, "train_tokens_per_second": 10685.294 }, { "epoch": 1.2170078103959063, "grad_norm": 0.7101140873531708, "learning_rate": 3.328938688746942e-06, "loss": 0.307998514175415, "num_input_tokens_seen": 744413256, "step": 18075, "train_runtime": 69666.3051, "train_tokens_per_second": 10685.413 }, { "epoch": 1.2173444653918664, "grad_norm": 0.7167804317507361, "learning_rate": 3.3264468808170012e-06, "loss": 0.34618449211120605, "num_input_tokens_seen": 744625152, "step": 18080, "train_runtime": 69685.9433, "train_tokens_per_second": 10685.443 }, { "epoch": 1.2176811203878266, "grad_norm": 0.7672091365442771, "learning_rate": 3.3239555408908562e-06, "loss": 0.31294617652893064, "num_input_tokens_seen": 744812192, "step": 18085, "train_runtime": 69703.2186, "train_tokens_per_second": 10685.478 }, { "epoch": 1.2180177753837866, "grad_norm": 0.7440180518075435, "learning_rate": 3.3214646696651974e-06, "loss": 0.2951935291290283, "num_input_tokens_seen": 745016568, "step": 18090, "train_runtime": 69723.4228, "train_tokens_per_second": 10685.313 }, { "epoch": 1.2183544303797469, "grad_norm": 0.7437723431035115, "learning_rate": 3.3189742678365923e-06, "loss": 0.31595535278320314, "num_input_tokens_seen": 745222888, "step": 18095, "train_runtime": 69742.2824, "train_tokens_per_second": 10685.381 }, { "epoch": 1.218691085375707, "grad_norm": 0.6665380898767682, "learning_rate": 3.316484336101472e-06, "loss": 0.27806456089019777, "num_input_tokens_seen": 745417952, "step": 18100, "train_runtime": 69761.6014, "train_tokens_per_second": 10685.218 }, { "epoch": 1.2190277403716672, "grad_norm": 0.7071309285741362, "learning_rate": 3.313994875156141e-06, "loss": 0.30867776870727537, "num_input_tokens_seen": 745623536, "step": 18105, "train_runtime": 69781.0392, "train_tokens_per_second": 10685.188 }, { "epoch": 1.2193643953676272, "grad_norm": 0.7271265017043999, "learning_rate": 3.3115058856967643e-06, "loss": 0.31921634674072263, "num_input_tokens_seen": 745837600, "step": 18110, "train_runtime": 69799.6174, "train_tokens_per_second": 10685.411 }, { "epoch": 1.2197010503635874, "grad_norm": 0.7873285932062324, "learning_rate": 3.3090173684193845e-06, "loss": 0.27419304847717285, "num_input_tokens_seen": 746041600, "step": 18115, "train_runtime": 69819.6581, "train_tokens_per_second": 10685.266 }, { "epoch": 1.2200377053595475, "grad_norm": 0.6685582102408079, "learning_rate": 3.3065293240199037e-06, "loss": 0.31856536865234375, "num_input_tokens_seen": 746251880, "step": 18120, "train_runtime": 69839.0074, "train_tokens_per_second": 10685.316 }, { "epoch": 1.2203743603555077, "grad_norm": 0.7673911632299195, "learning_rate": 3.3040417531940982e-06, "loss": 0.3207931756973267, "num_input_tokens_seen": 746463096, "step": 18125, "train_runtime": 69857.7155, "train_tokens_per_second": 10685.478 }, { "epoch": 1.2207110153514678, "grad_norm": 0.6694190175722269, "learning_rate": 3.301554656637607e-06, "loss": 0.2978257179260254, "num_input_tokens_seen": 746663264, "step": 18130, "train_runtime": 69875.8683, "train_tokens_per_second": 10685.567 }, { "epoch": 1.221047670347428, "grad_norm": 0.7112800144546855, "learning_rate": 3.2990680350459427e-06, "loss": 0.30327863693237306, "num_input_tokens_seen": 746863136, "step": 18135, "train_runtime": 69895.6395, "train_tokens_per_second": 10685.404 }, { "epoch": 1.221384325343388, "grad_norm": 0.7706771941648403, "learning_rate": 3.2965818891144763e-06, "loss": 0.31159038543701173, "num_input_tokens_seen": 747071384, "step": 18140, "train_runtime": 69913.1232, "train_tokens_per_second": 10685.71 }, { "epoch": 1.2217209803393483, "grad_norm": 0.744469324710781, "learning_rate": 3.294096219538454e-06, "loss": 0.3233118772506714, "num_input_tokens_seen": 747289816, "step": 18145, "train_runtime": 69932.0757, "train_tokens_per_second": 10685.938 }, { "epoch": 1.2220576353353083, "grad_norm": 0.6909723702417585, "learning_rate": 3.291611027012983e-06, "loss": 0.3186054229736328, "num_input_tokens_seen": 747502720, "step": 18150, "train_runtime": 69953.9058, "train_tokens_per_second": 10685.647 }, { "epoch": 1.2223942903312686, "grad_norm": 0.7850598721178248, "learning_rate": 3.289126312233043e-06, "loss": 0.29604220390319824, "num_input_tokens_seen": 747721328, "step": 18155, "train_runtime": 69974.6105, "train_tokens_per_second": 10685.609 }, { "epoch": 1.2227309453272286, "grad_norm": 0.6734621595752907, "learning_rate": 3.2866420758934714e-06, "loss": 0.31109938621520994, "num_input_tokens_seen": 747928880, "step": 18160, "train_runtime": 69993.2247, "train_tokens_per_second": 10685.733 }, { "epoch": 1.2230676003231888, "grad_norm": 0.6755217225629778, "learning_rate": 3.2841583186889826e-06, "loss": 0.30683207511901855, "num_input_tokens_seen": 748140552, "step": 18165, "train_runtime": 70012.1417, "train_tokens_per_second": 10685.869 }, { "epoch": 1.2234042553191489, "grad_norm": 1.13890162709856, "learning_rate": 3.281675041314146e-06, "loss": 0.29276700019836427, "num_input_tokens_seen": 748342912, "step": 18170, "train_runtime": 70031.2996, "train_tokens_per_second": 10685.835 }, { "epoch": 1.2237409103151091, "grad_norm": 0.7192875000795402, "learning_rate": 3.279192244463406e-06, "loss": 0.2978383779525757, "num_input_tokens_seen": 748546344, "step": 18175, "train_runtime": 70051.1459, "train_tokens_per_second": 10685.712 }, { "epoch": 1.2240775653110691, "grad_norm": 0.6988399548626895, "learning_rate": 3.2767099288310667e-06, "loss": 0.2983490705490112, "num_input_tokens_seen": 748757848, "step": 18180, "train_runtime": 70071.3959, "train_tokens_per_second": 10685.642 }, { "epoch": 1.2244142203070294, "grad_norm": 0.6399014955616996, "learning_rate": 3.2742280951113025e-06, "loss": 0.30640807151794436, "num_input_tokens_seen": 748972232, "step": 18185, "train_runtime": 70091.1909, "train_tokens_per_second": 10685.683 }, { "epoch": 1.2247508753029894, "grad_norm": 0.6990664500073804, "learning_rate": 3.2717467439981464e-06, "loss": 0.3069631099700928, "num_input_tokens_seen": 749171752, "step": 18190, "train_runtime": 70113.0409, "train_tokens_per_second": 10685.198 }, { "epoch": 1.2250875302989497, "grad_norm": 0.7060413843834781, "learning_rate": 3.2692658761855033e-06, "loss": 0.2753478765487671, "num_input_tokens_seen": 749362752, "step": 18195, "train_runtime": 70130.7764, "train_tokens_per_second": 10685.22 }, { "epoch": 1.2254241852949097, "grad_norm": 0.6471775767939019, "learning_rate": 3.266785492367138e-06, "loss": 0.2851977825164795, "num_input_tokens_seen": 749569600, "step": 18200, "train_runtime": 70148.4697, "train_tokens_per_second": 10685.473 }, { "epoch": 1.22576084029087, "grad_norm": 0.6742266629747447, "learning_rate": 3.2643055932366852e-06, "loss": 0.2878549098968506, "num_input_tokens_seen": 749768912, "step": 18205, "train_runtime": 70167.4852, "train_tokens_per_second": 10685.418 }, { "epoch": 1.22609749528683, "grad_norm": 0.7782200525916276, "learning_rate": 3.2618261794876365e-06, "loss": 0.30014514923095703, "num_input_tokens_seen": 749983320, "step": 18210, "train_runtime": 70186.8651, "train_tokens_per_second": 10685.522 }, { "epoch": 1.2264341502827902, "grad_norm": 0.704101299320144, "learning_rate": 3.259347251813356e-06, "loss": 0.29569215774536134, "num_input_tokens_seen": 750193320, "step": 18215, "train_runtime": 70206.9383, "train_tokens_per_second": 10685.458 }, { "epoch": 1.2267708052787503, "grad_norm": 0.7285513638299272, "learning_rate": 3.256868810907064e-06, "loss": 0.3241967916488647, "num_input_tokens_seen": 750412520, "step": 18220, "train_runtime": 70225.1115, "train_tokens_per_second": 10685.815 }, { "epoch": 1.2271074602747105, "grad_norm": 0.6966323788216068, "learning_rate": 3.2543908574618514e-06, "loss": 0.31064577102661134, "num_input_tokens_seen": 750618512, "step": 18225, "train_runtime": 70244.42, "train_tokens_per_second": 10685.81 }, { "epoch": 1.2274441152706705, "grad_norm": 0.639346416224288, "learning_rate": 3.251913392170668e-06, "loss": 0.29746289253234864, "num_input_tokens_seen": 750828560, "step": 18230, "train_runtime": 70264.7204, "train_tokens_per_second": 10685.712 }, { "epoch": 1.2277807702666308, "grad_norm": 0.7472383189572299, "learning_rate": 3.249436415726333e-06, "loss": 0.29661898612976073, "num_input_tokens_seen": 751039792, "step": 18235, "train_runtime": 70285.1421, "train_tokens_per_second": 10685.612 }, { "epoch": 1.2281174252625908, "grad_norm": 0.7564362378191346, "learning_rate": 3.24695992882152e-06, "loss": 0.313493013381958, "num_input_tokens_seen": 751239552, "step": 18240, "train_runtime": 70305.7997, "train_tokens_per_second": 10685.314 }, { "epoch": 1.228454080258551, "grad_norm": 0.6763910607777159, "learning_rate": 3.244483932148773e-06, "loss": 0.3089442253112793, "num_input_tokens_seen": 751443952, "step": 18245, "train_runtime": 70323.97, "train_tokens_per_second": 10685.46 }, { "epoch": 1.228790735254511, "grad_norm": 0.6964062577160958, "learning_rate": 3.2420084264004966e-06, "loss": 0.3025315761566162, "num_input_tokens_seen": 751648472, "step": 18250, "train_runtime": 70343.1588, "train_tokens_per_second": 10685.452 }, { "epoch": 1.2291273902504714, "grad_norm": 0.7196555490322786, "learning_rate": 3.2395334122689594e-06, "loss": 0.3049164295196533, "num_input_tokens_seen": 751856672, "step": 18255, "train_runtime": 70363.6996, "train_tokens_per_second": 10685.292 }, { "epoch": 1.2294640452464314, "grad_norm": 0.7076688877274717, "learning_rate": 3.2370588904462873e-06, "loss": 0.3095088958740234, "num_input_tokens_seen": 752071680, "step": 18260, "train_runtime": 70383.0612, "train_tokens_per_second": 10685.407 }, { "epoch": 1.2298007002423916, "grad_norm": 0.7349139532457661, "learning_rate": 3.2345848616244775e-06, "loss": 0.30430572032928466, "num_input_tokens_seen": 752258184, "step": 18265, "train_runtime": 70402.0771, "train_tokens_per_second": 10685.17 }, { "epoch": 1.2301373552383517, "grad_norm": 0.9415078390385083, "learning_rate": 3.2321113264953797e-06, "loss": 0.3068270444869995, "num_input_tokens_seen": 752466648, "step": 18270, "train_runtime": 70420.1487, "train_tokens_per_second": 10685.389 }, { "epoch": 1.230474010234312, "grad_norm": 0.794156854358431, "learning_rate": 3.2296382857507124e-06, "loss": 0.29191467761993406, "num_input_tokens_seen": 752667912, "step": 18275, "train_runtime": 70440.8282, "train_tokens_per_second": 10685.109 }, { "epoch": 1.230810665230272, "grad_norm": 0.6580797893762848, "learning_rate": 3.227165740082053e-06, "loss": 0.3086179256439209, "num_input_tokens_seen": 752874344, "step": 18280, "train_runtime": 70461.3435, "train_tokens_per_second": 10684.927 }, { "epoch": 1.2311473202262322, "grad_norm": 0.7242574377333048, "learning_rate": 3.2246936901808424e-06, "loss": 0.2933472156524658, "num_input_tokens_seen": 753084512, "step": 18285, "train_runtime": 70479.2424, "train_tokens_per_second": 10685.196 }, { "epoch": 1.2314839752221922, "grad_norm": 0.7293406178387227, "learning_rate": 3.2222221367383786e-06, "loss": 0.3240374565124512, "num_input_tokens_seen": 753295568, "step": 18290, "train_runtime": 70499.973, "train_tokens_per_second": 10685.048 }, { "epoch": 1.2318206302181525, "grad_norm": 0.7052982124474203, "learning_rate": 3.2197510804458265e-06, "loss": 0.2982195854187012, "num_input_tokens_seen": 753493232, "step": 18295, "train_runtime": 70520.0356, "train_tokens_per_second": 10684.811 }, { "epoch": 1.2321572852141125, "grad_norm": 0.619894113634097, "learning_rate": 3.217280521994207e-06, "loss": 0.3064931869506836, "num_input_tokens_seen": 753704456, "step": 18300, "train_runtime": 70538.2813, "train_tokens_per_second": 10685.041 }, { "epoch": 1.2324939402100727, "grad_norm": 0.7598356609027785, "learning_rate": 3.214810462074407e-06, "loss": 0.30252134799957275, "num_input_tokens_seen": 753911520, "step": 18305, "train_runtime": 70556.6349, "train_tokens_per_second": 10685.197 }, { "epoch": 1.2328305952060328, "grad_norm": 0.7397814167265707, "learning_rate": 3.2123409013771666e-06, "loss": 0.29979715347290037, "num_input_tokens_seen": 754122408, "step": 18310, "train_runtime": 70574.9428, "train_tokens_per_second": 10685.413 }, { "epoch": 1.233167250201993, "grad_norm": 0.6373233356066428, "learning_rate": 3.209871840593095e-06, "loss": 0.30856778621673586, "num_input_tokens_seen": 754340384, "step": 18315, "train_runtime": 70596.2744, "train_tokens_per_second": 10685.272 }, { "epoch": 1.233503905197953, "grad_norm": 0.6852803186407723, "learning_rate": 3.207403280412652e-06, "loss": 0.307573938369751, "num_input_tokens_seen": 754546072, "step": 18320, "train_runtime": 70615.5985, "train_tokens_per_second": 10685.261 }, { "epoch": 1.2338405601939133, "grad_norm": 0.6814139502202912, "learning_rate": 3.2049352215261677e-06, "loss": 0.28683905601501464, "num_input_tokens_seen": 754761256, "step": 18325, "train_runtime": 70635.3982, "train_tokens_per_second": 10685.312 }, { "epoch": 1.2341772151898733, "grad_norm": 0.6576639655799219, "learning_rate": 3.2024676646238222e-06, "loss": 0.29456377029418945, "num_input_tokens_seen": 754969160, "step": 18330, "train_runtime": 70653.6638, "train_tokens_per_second": 10685.492 }, { "epoch": 1.2345138701858336, "grad_norm": 0.7520347725029374, "learning_rate": 3.2000006103956653e-06, "loss": 0.30841426849365233, "num_input_tokens_seen": 755177648, "step": 18335, "train_runtime": 70673.6109, "train_tokens_per_second": 10685.426 }, { "epoch": 1.2348505251817936, "grad_norm": 0.8372844487033587, "learning_rate": 3.1975340595315956e-06, "loss": 0.2906350612640381, "num_input_tokens_seen": 755375512, "step": 18340, "train_runtime": 70692.5319, "train_tokens_per_second": 10685.365 }, { "epoch": 1.2351871801777539, "grad_norm": 0.717831729225175, "learning_rate": 3.1950680127213796e-06, "loss": 0.29487369060516355, "num_input_tokens_seen": 755581928, "step": 18345, "train_runtime": 70711.1646, "train_tokens_per_second": 10685.469 }, { "epoch": 1.235523835173714, "grad_norm": 0.7097212259073605, "learning_rate": 3.192602470654638e-06, "loss": 0.32154319286346433, "num_input_tokens_seen": 755785192, "step": 18350, "train_runtime": 70731.5824, "train_tokens_per_second": 10685.258 }, { "epoch": 1.2358604901696741, "grad_norm": 0.7475257381111633, "learning_rate": 3.190137434020853e-06, "loss": 0.2918834209442139, "num_input_tokens_seen": 755995512, "step": 18355, "train_runtime": 70752.4289, "train_tokens_per_second": 10685.082 }, { "epoch": 1.2361971451656342, "grad_norm": 0.7893604894178321, "learning_rate": 3.1876729035093616e-06, "loss": 0.3011518955230713, "num_input_tokens_seen": 756201712, "step": 18360, "train_runtime": 70770.7009, "train_tokens_per_second": 10685.237 }, { "epoch": 1.2365338001615944, "grad_norm": 0.7095811234283492, "learning_rate": 3.185208879809366e-06, "loss": 0.29860672950744627, "num_input_tokens_seen": 756414456, "step": 18365, "train_runtime": 70789.1509, "train_tokens_per_second": 10685.457 }, { "epoch": 1.2368704551575544, "grad_norm": 0.7158021231861256, "learning_rate": 3.1827453636099183e-06, "loss": 0.30619111061096194, "num_input_tokens_seen": 756633544, "step": 18370, "train_runtime": 70807.421, "train_tokens_per_second": 10685.794 }, { "epoch": 1.2372071101535147, "grad_norm": 0.8499718366690523, "learning_rate": 3.1802823555999356e-06, "loss": 0.28728518486022947, "num_input_tokens_seen": 756843896, "step": 18375, "train_runtime": 70825.8364, "train_tokens_per_second": 10685.986 }, { "epoch": 1.2375437651494747, "grad_norm": 0.8417150979426754, "learning_rate": 3.1778198564681885e-06, "loss": 0.32341709136962893, "num_input_tokens_seen": 757056584, "step": 18380, "train_runtime": 70844.2227, "train_tokens_per_second": 10686.215 }, { "epoch": 1.237880420145435, "grad_norm": 0.7353932011574018, "learning_rate": 3.17535786690331e-06, "loss": 0.3157517433166504, "num_input_tokens_seen": 757262624, "step": 18385, "train_runtime": 70864.4574, "train_tokens_per_second": 10686.071 }, { "epoch": 1.238217075141395, "grad_norm": 0.7687646166032216, "learning_rate": 3.172896387593784e-06, "loss": 0.30957798957824706, "num_input_tokens_seen": 757474104, "step": 18390, "train_runtime": 70883.4661, "train_tokens_per_second": 10686.189 }, { "epoch": 1.2385537301373553, "grad_norm": 0.7928808884193307, "learning_rate": 3.1704354192279573e-06, "loss": 0.3165458917617798, "num_input_tokens_seen": 757678304, "step": 18395, "train_runtime": 70902.8985, "train_tokens_per_second": 10686.14 }, { "epoch": 1.2388903851333153, "grad_norm": 0.7451034513856479, "learning_rate": 3.1679749624940316e-06, "loss": 0.31646728515625, "num_input_tokens_seen": 757886736, "step": 18400, "train_runtime": 70922.5285, "train_tokens_per_second": 10686.121 }, { "epoch": 1.2392270401292755, "grad_norm": 0.7564333442113723, "learning_rate": 3.165515018080067e-06, "loss": 0.30226917266845704, "num_input_tokens_seen": 758091768, "step": 18405, "train_runtime": 70941.3085, "train_tokens_per_second": 10686.182 }, { "epoch": 1.2395636951252356, "grad_norm": 0.7586958163975407, "learning_rate": 3.163055586673976e-06, "loss": 0.291187047958374, "num_input_tokens_seen": 758298112, "step": 18410, "train_runtime": 70958.8951, "train_tokens_per_second": 10686.442 }, { "epoch": 1.2399003501211958, "grad_norm": 0.7340813827096887, "learning_rate": 3.1605966689635348e-06, "loss": 0.3209094047546387, "num_input_tokens_seen": 758509480, "step": 18415, "train_runtime": 70977.2029, "train_tokens_per_second": 10686.663 }, { "epoch": 1.2402370051171558, "grad_norm": 0.8499456064474421, "learning_rate": 3.1581382656363666e-06, "loss": 0.302050518989563, "num_input_tokens_seen": 758701272, "step": 18420, "train_runtime": 70994.6776, "train_tokens_per_second": 10686.735 }, { "epoch": 1.240573660113116, "grad_norm": 0.6774226558457197, "learning_rate": 3.1556803773799616e-06, "loss": 0.3155226707458496, "num_input_tokens_seen": 758909968, "step": 18425, "train_runtime": 71014.7508, "train_tokens_per_second": 10686.653 }, { "epoch": 1.2409103151090761, "grad_norm": 0.7189385786976626, "learning_rate": 3.1532230048816564e-06, "loss": 0.3047914505004883, "num_input_tokens_seen": 759114600, "step": 18430, "train_runtime": 71034.9278, "train_tokens_per_second": 10686.498 }, { "epoch": 1.2412469701050364, "grad_norm": 0.6417330603870427, "learning_rate": 3.150766148828651e-06, "loss": 0.3077030420303345, "num_input_tokens_seen": 759319392, "step": 18435, "train_runtime": 71052.5092, "train_tokens_per_second": 10686.736 }, { "epoch": 1.2415836251009964, "grad_norm": 0.7146323097846058, "learning_rate": 3.1483098099079934e-06, "loss": 0.28674001693725587, "num_input_tokens_seen": 759530408, "step": 18440, "train_runtime": 71071.0498, "train_tokens_per_second": 10686.917 }, { "epoch": 1.2419202800969567, "grad_norm": 0.7035097262974941, "learning_rate": 3.1458539888065937e-06, "loss": 0.3025383949279785, "num_input_tokens_seen": 759731736, "step": 18445, "train_runtime": 71089.7982, "train_tokens_per_second": 10686.931 }, { "epoch": 1.2422569350929167, "grad_norm": 0.7796842220952002, "learning_rate": 3.143398686211212e-06, "loss": 0.2955173015594482, "num_input_tokens_seen": 759929624, "step": 18450, "train_runtime": 71109.3036, "train_tokens_per_second": 10686.782 }, { "epoch": 1.242593590088877, "grad_norm": 0.6927383630463512, "learning_rate": 3.1409439028084706e-06, "loss": 0.31551413536071776, "num_input_tokens_seen": 760137072, "step": 18455, "train_runtime": 71129.7884, "train_tokens_per_second": 10686.621 }, { "epoch": 1.2429302450848372, "grad_norm": 0.6718551220138265, "learning_rate": 3.1384896392848363e-06, "loss": 0.2882070779800415, "num_input_tokens_seen": 760344392, "step": 18460, "train_runtime": 71149.9189, "train_tokens_per_second": 10686.511 }, { "epoch": 1.2432669000807972, "grad_norm": 0.7395674612059358, "learning_rate": 3.1360358963266404e-06, "loss": 0.3318660736083984, "num_input_tokens_seen": 760555368, "step": 18465, "train_runtime": 71167.7099, "train_tokens_per_second": 10686.804 }, { "epoch": 1.2436035550767572, "grad_norm": 0.7251417163440275, "learning_rate": 3.1335826746200594e-06, "loss": 0.30448055267333984, "num_input_tokens_seen": 760742536, "step": 18470, "train_runtime": 71186.745, "train_tokens_per_second": 10686.576 }, { "epoch": 1.2439402100727175, "grad_norm": 0.7282393044808444, "learning_rate": 3.1311299748511335e-06, "loss": 0.3216533184051514, "num_input_tokens_seen": 760951544, "step": 18475, "train_runtime": 71205.5935, "train_tokens_per_second": 10686.682 }, { "epoch": 1.2442768650686777, "grad_norm": 0.7029619087498836, "learning_rate": 3.1286777977057504e-06, "loss": 0.2927834510803223, "num_input_tokens_seen": 761151064, "step": 18480, "train_runtime": 71225.8711, "train_tokens_per_second": 10686.441 }, { "epoch": 1.2446135200646378, "grad_norm": 0.7771952427340859, "learning_rate": 3.126226143869655e-06, "loss": 0.3225777387619019, "num_input_tokens_seen": 761350360, "step": 18485, "train_runtime": 71243.4561, "train_tokens_per_second": 10686.601 }, { "epoch": 1.2449501750605978, "grad_norm": 0.6672079667061005, "learning_rate": 3.1237750140284424e-06, "loss": 0.2738663673400879, "num_input_tokens_seen": 761552056, "step": 18490, "train_runtime": 71262.4139, "train_tokens_per_second": 10686.588 }, { "epoch": 1.245286830056558, "grad_norm": 0.719888968542124, "learning_rate": 3.1213244088675647e-06, "loss": 0.30700387954711916, "num_input_tokens_seen": 761755736, "step": 18495, "train_runtime": 71282.316, "train_tokens_per_second": 10686.462 }, { "epoch": 1.2456234850525183, "grad_norm": 0.7759444686448864, "learning_rate": 3.1188743290723246e-06, "loss": 0.31720433235168455, "num_input_tokens_seen": 761963280, "step": 18500, "train_runtime": 71304.5345, "train_tokens_per_second": 10686.042 }, { "epoch": 1.2459601400484783, "grad_norm": 0.7986697813264317, "learning_rate": 3.116424775327882e-06, "loss": 0.30136091709136964, "num_input_tokens_seen": 762169120, "step": 18505, "train_runtime": 71322.7628, "train_tokens_per_second": 10686.197 }, { "epoch": 1.2462967950444384, "grad_norm": 0.6689989624653766, "learning_rate": 3.1139757483192423e-06, "loss": 0.30402522087097167, "num_input_tokens_seen": 762382376, "step": 18510, "train_runtime": 71341.1778, "train_tokens_per_second": 10686.428 }, { "epoch": 1.2466334500403986, "grad_norm": 0.8084474144063898, "learning_rate": 3.1115272487312727e-06, "loss": 0.300734281539917, "num_input_tokens_seen": 762577456, "step": 18515, "train_runtime": 71359.0361, "train_tokens_per_second": 10686.488 }, { "epoch": 1.2469701050363589, "grad_norm": 0.8031952709084947, "learning_rate": 3.109079277248684e-06, "loss": 0.29400434494018557, "num_input_tokens_seen": 762772352, "step": 18520, "train_runtime": 71378.7038, "train_tokens_per_second": 10686.274 }, { "epoch": 1.2473067600323189, "grad_norm": 0.7181630446082632, "learning_rate": 3.1066318345560463e-06, "loss": 0.3193758487701416, "num_input_tokens_seen": 762972816, "step": 18525, "train_runtime": 71396.5689, "train_tokens_per_second": 10686.407 }, { "epoch": 1.247643415028279, "grad_norm": 0.7231094516136753, "learning_rate": 3.1041849213377782e-06, "loss": 0.32068643569946287, "num_input_tokens_seen": 763189552, "step": 18530, "train_runtime": 71414.6577, "train_tokens_per_second": 10686.735 }, { "epoch": 1.2479800700242392, "grad_norm": 0.7255986990870752, "learning_rate": 3.101738538278154e-06, "loss": 0.29286918640136717, "num_input_tokens_seen": 763397408, "step": 18535, "train_runtime": 71432.724, "train_tokens_per_second": 10686.942 }, { "epoch": 1.2483167250201994, "grad_norm": 0.7265751343059857, "learning_rate": 3.0992926860612914e-06, "loss": 0.304166841506958, "num_input_tokens_seen": 763599416, "step": 18540, "train_runtime": 71452.4704, "train_tokens_per_second": 10686.816 }, { "epoch": 1.2486533800161594, "grad_norm": 0.733543291245351, "learning_rate": 3.0968473653711693e-06, "loss": 0.29898734092712403, "num_input_tokens_seen": 763821208, "step": 18545, "train_runtime": 71470.9925, "train_tokens_per_second": 10687.15 }, { "epoch": 1.2489900350121195, "grad_norm": 0.7950114761404151, "learning_rate": 3.094402576891613e-06, "loss": 0.3174330949783325, "num_input_tokens_seen": 764028064, "step": 18550, "train_runtime": 71488.9081, "train_tokens_per_second": 10687.365 }, { "epoch": 1.2493266900080797, "grad_norm": 0.6617521414895642, "learning_rate": 3.0919583213063004e-06, "loss": 0.3219028949737549, "num_input_tokens_seen": 764243376, "step": 18555, "train_runtime": 71506.9997, "train_tokens_per_second": 10687.672 }, { "epoch": 1.24966334500404, "grad_norm": 0.7107904847874726, "learning_rate": 3.0895145992987574e-06, "loss": 0.2989363431930542, "num_input_tokens_seen": 764458776, "step": 18560, "train_runtime": 71526.9273, "train_tokens_per_second": 10687.706 }, { "epoch": 1.25, "grad_norm": 0.7290573398433167, "learning_rate": 3.087071411552366e-06, "loss": 0.2967213153839111, "num_input_tokens_seen": 764662448, "step": 18565, "train_runtime": 71546.3568, "train_tokens_per_second": 10687.65 }, { "epoch": 1.25033665499596, "grad_norm": 0.6815387795655508, "learning_rate": 3.084628758750353e-06, "loss": 0.3120149612426758, "num_input_tokens_seen": 764869760, "step": 18570, "train_runtime": 71566.4164, "train_tokens_per_second": 10687.551 }, { "epoch": 1.2506733099919203, "grad_norm": 0.8427947296891737, "learning_rate": 3.082186641575801e-06, "loss": 0.32192943096160886, "num_input_tokens_seen": 765075912, "step": 18575, "train_runtime": 71586.6009, "train_tokens_per_second": 10687.418 }, { "epoch": 1.2510099649878805, "grad_norm": 0.6960430562926149, "learning_rate": 3.0797450607116384e-06, "loss": 0.3013256311416626, "num_input_tokens_seen": 765282960, "step": 18580, "train_runtime": 71606.5962, "train_tokens_per_second": 10687.325 }, { "epoch": 1.2513466199838406, "grad_norm": 0.6762842806856125, "learning_rate": 3.0773040168406475e-06, "loss": 0.3130093336105347, "num_input_tokens_seen": 765498904, "step": 18585, "train_runtime": 71625.1711, "train_tokens_per_second": 10687.568 }, { "epoch": 1.2516832749798006, "grad_norm": 0.8399193563535782, "learning_rate": 3.074863510645456e-06, "loss": 0.31697418689727785, "num_input_tokens_seen": 765706064, "step": 18590, "train_runtime": 71644.3832, "train_tokens_per_second": 10687.594 }, { "epoch": 1.2520199299757608, "grad_norm": 0.6771388789789129, "learning_rate": 3.072423542808546e-06, "loss": 0.30218050479888914, "num_input_tokens_seen": 765909936, "step": 18595, "train_runtime": 71662.0224, "train_tokens_per_second": 10687.808 }, { "epoch": 1.252356584971721, "grad_norm": 0.7567860420291049, "learning_rate": 3.0699841140122443e-06, "loss": 0.3113452196121216, "num_input_tokens_seen": 766118816, "step": 18600, "train_runtime": 71683.0497, "train_tokens_per_second": 10687.587 }, { "epoch": 1.2526932399676811, "grad_norm": 0.7022549479969497, "learning_rate": 3.0675452249387327e-06, "loss": 0.29018473625183105, "num_input_tokens_seen": 766333768, "step": 18605, "train_runtime": 71704.3149, "train_tokens_per_second": 10687.415 }, { "epoch": 1.2530298949636411, "grad_norm": 0.733311407025865, "learning_rate": 3.0651068762700354e-06, "loss": 0.33750166893005373, "num_input_tokens_seen": 766531480, "step": 18610, "train_runtime": 71723.7646, "train_tokens_per_second": 10687.273 }, { "epoch": 1.2533665499596014, "grad_norm": 0.7445996703191397, "learning_rate": 3.0626690686880313e-06, "loss": 0.3214420318603516, "num_input_tokens_seen": 766751576, "step": 18615, "train_runtime": 71742.7633, "train_tokens_per_second": 10687.511 }, { "epoch": 1.2537032049555616, "grad_norm": 0.7402952467105838, "learning_rate": 3.060231802874443e-06, "loss": 0.30179433822631835, "num_input_tokens_seen": 766964088, "step": 18620, "train_runtime": 71761.1142, "train_tokens_per_second": 10687.739 }, { "epoch": 1.2540398599515217, "grad_norm": 0.7226388136893123, "learning_rate": 3.0577950795108462e-06, "loss": 0.3058619976043701, "num_input_tokens_seen": 767174992, "step": 18625, "train_runtime": 71780.1428, "train_tokens_per_second": 10687.844 }, { "epoch": 1.2543765149474817, "grad_norm": 0.7613330202855662, "learning_rate": 3.055358899278662e-06, "loss": 0.29321794509887694, "num_input_tokens_seen": 767374576, "step": 18630, "train_runtime": 71799.2881, "train_tokens_per_second": 10687.774 }, { "epoch": 1.254713169943442, "grad_norm": 0.7272093849654336, "learning_rate": 3.052923262859162e-06, "loss": 0.30442447662353517, "num_input_tokens_seen": 767586840, "step": 18635, "train_runtime": 71818.8406, "train_tokens_per_second": 10687.82 }, { "epoch": 1.2550498249394022, "grad_norm": 0.6686798393342016, "learning_rate": 3.0504881709334603e-06, "loss": 0.29777143001556394, "num_input_tokens_seen": 767797112, "step": 18640, "train_runtime": 71838.8524, "train_tokens_per_second": 10687.77 }, { "epoch": 1.2553864799353622, "grad_norm": 0.6575651321734682, "learning_rate": 3.0480536241825263e-06, "loss": 0.2871812582015991, "num_input_tokens_seen": 768005560, "step": 18645, "train_runtime": 71859.318, "train_tokens_per_second": 10687.627 }, { "epoch": 1.2557231349313223, "grad_norm": 0.7145351211467422, "learning_rate": 3.0456196232871715e-06, "loss": 0.3079071521759033, "num_input_tokens_seen": 768207096, "step": 18650, "train_runtime": 71879.4821, "train_tokens_per_second": 10687.432 }, { "epoch": 1.2560597899272825, "grad_norm": 0.7596459458361102, "learning_rate": 3.043186168928059e-06, "loss": 0.3055105686187744, "num_input_tokens_seen": 768404128, "step": 18655, "train_runtime": 71899.816, "train_tokens_per_second": 10687.15 }, { "epoch": 1.2563964449232428, "grad_norm": 0.8519903225931499, "learning_rate": 3.040753261785692e-06, "loss": 0.2774746179580688, "num_input_tokens_seen": 768602368, "step": 18660, "train_runtime": 71918.9188, "train_tokens_per_second": 10687.068 }, { "epoch": 1.2567330999192028, "grad_norm": 0.7269317096064035, "learning_rate": 3.038320902540429e-06, "loss": 0.2869354248046875, "num_input_tokens_seen": 768809624, "step": 18665, "train_runtime": 71939.8758, "train_tokens_per_second": 10686.836 }, { "epoch": 1.2570697549151628, "grad_norm": 0.7166152387519272, "learning_rate": 3.0358890918724706e-06, "loss": 0.3037984371185303, "num_input_tokens_seen": 769026304, "step": 18670, "train_runtime": 71959.2117, "train_tokens_per_second": 10686.975 }, { "epoch": 1.257406409911123, "grad_norm": 0.7497038188443689, "learning_rate": 3.0334578304618646e-06, "loss": 0.2995076417922974, "num_input_tokens_seen": 769218896, "step": 18675, "train_runtime": 71980.2715, "train_tokens_per_second": 10686.524 }, { "epoch": 1.2577430649070833, "grad_norm": 0.6906724099304585, "learning_rate": 3.0310271189885037e-06, "loss": 0.3059638261795044, "num_input_tokens_seen": 769415760, "step": 18680, "train_runtime": 71998.9949, "train_tokens_per_second": 10686.479 }, { "epoch": 1.2580797199030433, "grad_norm": 0.7030726894208557, "learning_rate": 3.0285969581321328e-06, "loss": 0.29846811294555664, "num_input_tokens_seen": 769623536, "step": 18685, "train_runtime": 72018.8905, "train_tokens_per_second": 10686.412 }, { "epoch": 1.2584163748990034, "grad_norm": 0.7225068878133025, "learning_rate": 3.0261673485723343e-06, "loss": 0.3487494468688965, "num_input_tokens_seen": 769823480, "step": 18690, "train_runtime": 72038.467, "train_tokens_per_second": 10686.283 }, { "epoch": 1.2587530298949636, "grad_norm": 0.6921363731134225, "learning_rate": 3.023738290988544e-06, "loss": 0.29176394939422606, "num_input_tokens_seen": 770034056, "step": 18695, "train_runtime": 72058.7828, "train_tokens_per_second": 10686.193 }, { "epoch": 1.2590896848909239, "grad_norm": 0.741828315957373, "learning_rate": 3.021309786060037e-06, "loss": 0.3081328868865967, "num_input_tokens_seen": 770230240, "step": 18700, "train_runtime": 72079.7096, "train_tokens_per_second": 10685.812 }, { "epoch": 1.259426339886884, "grad_norm": 0.6696370974168009, "learning_rate": 3.018881834465941e-06, "loss": 0.28402693271636964, "num_input_tokens_seen": 770431272, "step": 18705, "train_runtime": 72100.1471, "train_tokens_per_second": 10685.571 }, { "epoch": 1.259762994882844, "grad_norm": 0.7082877964170075, "learning_rate": 3.016454436885221e-06, "loss": 0.312184476852417, "num_input_tokens_seen": 770636632, "step": 18710, "train_runtime": 72119.9313, "train_tokens_per_second": 10685.488 }, { "epoch": 1.2600996498788042, "grad_norm": 0.7247489936407656, "learning_rate": 3.0140275939966934e-06, "loss": 0.30790698528289795, "num_input_tokens_seen": 770846448, "step": 18715, "train_runtime": 72139.5992, "train_tokens_per_second": 10685.483 }, { "epoch": 1.2604363048747644, "grad_norm": 0.773515456577208, "learning_rate": 3.0116013064790166e-06, "loss": 0.35373289585113527, "num_input_tokens_seen": 771061072, "step": 18720, "train_runtime": 72157.9141, "train_tokens_per_second": 10685.745 }, { "epoch": 1.2607729598707245, "grad_norm": 0.919399748026669, "learning_rate": 3.0091755750106937e-06, "loss": 0.31322283744812013, "num_input_tokens_seen": 771263920, "step": 18725, "train_runtime": 72175.766, "train_tokens_per_second": 10685.913 }, { "epoch": 1.2611096148666845, "grad_norm": 0.7074065618158146, "learning_rate": 3.006750400270072e-06, "loss": 0.28590433597564696, "num_input_tokens_seen": 771466008, "step": 18730, "train_runtime": 72195.1611, "train_tokens_per_second": 10685.841 }, { "epoch": 1.2614462698626447, "grad_norm": 0.6634347056385153, "learning_rate": 3.0043257829353466e-06, "loss": 0.29170467853546145, "num_input_tokens_seen": 771672888, "step": 18735, "train_runtime": 72214.4853, "train_tokens_per_second": 10685.846 }, { "epoch": 1.261782924858605, "grad_norm": 0.7202781996617211, "learning_rate": 3.0019017236845504e-06, "loss": 0.3175733804702759, "num_input_tokens_seen": 771877744, "step": 18740, "train_runtime": 72234.2188, "train_tokens_per_second": 10685.763 }, { "epoch": 1.262119579854565, "grad_norm": 0.8177718573782228, "learning_rate": 2.9994782231955673e-06, "loss": 0.3086109161376953, "num_input_tokens_seen": 772081448, "step": 18745, "train_runtime": 72252.9847, "train_tokens_per_second": 10685.807 }, { "epoch": 1.262456234850525, "grad_norm": 0.6580456876913165, "learning_rate": 2.9970552821461185e-06, "loss": 0.2895681381225586, "num_input_tokens_seen": 772281528, "step": 18750, "train_runtime": 72272.2537, "train_tokens_per_second": 10685.726 }, { "epoch": 1.2627928898464853, "grad_norm": 0.817626226596891, "learning_rate": 2.994632901213775e-06, "loss": 0.30153393745422363, "num_input_tokens_seen": 772480680, "step": 18755, "train_runtime": 72292.3673, "train_tokens_per_second": 10685.508 }, { "epoch": 1.2631295448424456, "grad_norm": 0.8235284890522667, "learning_rate": 2.9922110810759443e-06, "loss": 0.3189918041229248, "num_input_tokens_seen": 772682080, "step": 18760, "train_runtime": 72311.4799, "train_tokens_per_second": 10685.469 }, { "epoch": 1.2634661998384056, "grad_norm": 0.7309897691603319, "learning_rate": 2.989789822409883e-06, "loss": 0.3258535146713257, "num_input_tokens_seen": 772891416, "step": 18765, "train_runtime": 72329.6659, "train_tokens_per_second": 10685.677 }, { "epoch": 1.2638028548343656, "grad_norm": 0.6919512299655708, "learning_rate": 2.9873691258926864e-06, "loss": 0.32625417709350585, "num_input_tokens_seen": 773113568, "step": 18770, "train_runtime": 72349.3225, "train_tokens_per_second": 10685.844 }, { "epoch": 1.2641395098303259, "grad_norm": 0.7116961582847195, "learning_rate": 2.9849489922012985e-06, "loss": 0.3056730031967163, "num_input_tokens_seen": 773312000, "step": 18775, "train_runtime": 72369.7678, "train_tokens_per_second": 10685.567 }, { "epoch": 1.264476164826286, "grad_norm": 0.7078680789383808, "learning_rate": 2.982529422012498e-06, "loss": 0.33696327209472654, "num_input_tokens_seen": 773531128, "step": 18780, "train_runtime": 72390.0455, "train_tokens_per_second": 10685.601 }, { "epoch": 1.2648128198222461, "grad_norm": 0.7443089258834993, "learning_rate": 2.9801104160029127e-06, "loss": 0.2702555894851685, "num_input_tokens_seen": 773727832, "step": 18785, "train_runtime": 72409.8485, "train_tokens_per_second": 10685.395 }, { "epoch": 1.2651494748182062, "grad_norm": 0.7380668183887764, "learning_rate": 2.9776919748490063e-06, "loss": 0.3161613941192627, "num_input_tokens_seen": 773931416, "step": 18790, "train_runtime": 72429.3493, "train_tokens_per_second": 10685.329 }, { "epoch": 1.2654861298141664, "grad_norm": 0.8188425010159007, "learning_rate": 2.975274099227092e-06, "loss": 0.3260714054107666, "num_input_tokens_seen": 774127800, "step": 18795, "train_runtime": 72449.7119, "train_tokens_per_second": 10685.036 }, { "epoch": 1.2658227848101267, "grad_norm": 0.8485725032815462, "learning_rate": 2.9728567898133183e-06, "loss": 0.31565308570861816, "num_input_tokens_seen": 774336120, "step": 18800, "train_runtime": 72469.9975, "train_tokens_per_second": 10684.92 }, { "epoch": 1.2661594398060867, "grad_norm": 0.6711946150931188, "learning_rate": 2.9704400472836816e-06, "loss": 0.3020011901855469, "num_input_tokens_seen": 774542880, "step": 18805, "train_runtime": 72489.0963, "train_tokens_per_second": 10684.957 }, { "epoch": 1.266496094802047, "grad_norm": 0.7638786802957765, "learning_rate": 2.9680238723140108e-06, "loss": 0.33070011138916017, "num_input_tokens_seen": 774744160, "step": 18810, "train_runtime": 72508.13, "train_tokens_per_second": 10684.928 }, { "epoch": 1.266832749798007, "grad_norm": 0.6966105340921925, "learning_rate": 2.9656082655799866e-06, "loss": 0.3185291290283203, "num_input_tokens_seen": 774943472, "step": 18815, "train_runtime": 72528.2002, "train_tokens_per_second": 10684.719 }, { "epoch": 1.2671694047939672, "grad_norm": 0.8446222026915324, "learning_rate": 2.9631932277571225e-06, "loss": 0.3132080793380737, "num_input_tokens_seen": 775151488, "step": 18820, "train_runtime": 72546.2805, "train_tokens_per_second": 10684.924 }, { "epoch": 1.2675060597899273, "grad_norm": 0.6922056860175154, "learning_rate": 2.9607787595207794e-06, "loss": 0.2939446926116943, "num_input_tokens_seen": 775357576, "step": 18825, "train_runtime": 72566.8142, "train_tokens_per_second": 10684.74 }, { "epoch": 1.2678427147858875, "grad_norm": 0.6089036266249871, "learning_rate": 2.9583648615461514e-06, "loss": 0.2953668117523193, "num_input_tokens_seen": 775559792, "step": 18830, "train_runtime": 72586.9694, "train_tokens_per_second": 10684.559 }, { "epoch": 1.2681793697818475, "grad_norm": 0.6762863893452233, "learning_rate": 2.955951534508281e-06, "loss": 0.32690041065216063, "num_input_tokens_seen": 775759704, "step": 18835, "train_runtime": 72605.924, "train_tokens_per_second": 10684.524 }, { "epoch": 1.2685160247778078, "grad_norm": 0.6518531772249438, "learning_rate": 2.9535387790820452e-06, "loss": 0.31324291229248047, "num_input_tokens_seen": 775975392, "step": 18840, "train_runtime": 72626.1479, "train_tokens_per_second": 10684.518 }, { "epoch": 1.2688526797737678, "grad_norm": 0.7758283812166717, "learning_rate": 2.951126595942165e-06, "loss": 0.2903739929199219, "num_input_tokens_seen": 776188144, "step": 18845, "train_runtime": 72644.6358, "train_tokens_per_second": 10684.728 }, { "epoch": 1.269189334769728, "grad_norm": 0.6942600318484227, "learning_rate": 2.948714985763197e-06, "loss": 0.2772603750228882, "num_input_tokens_seen": 776382848, "step": 18850, "train_runtime": 72664.136, "train_tokens_per_second": 10684.54 }, { "epoch": 1.269525989765688, "grad_norm": 0.7686046863793413, "learning_rate": 2.9463039492195445e-06, "loss": 0.31255857944488524, "num_input_tokens_seen": 776601680, "step": 18855, "train_runtime": 72684.3511, "train_tokens_per_second": 10684.579 }, { "epoch": 1.2698626447616483, "grad_norm": 0.7490385798864683, "learning_rate": 2.9438934869854417e-06, "loss": 0.2935356855392456, "num_input_tokens_seen": 776813424, "step": 18860, "train_runtime": 72704.264, "train_tokens_per_second": 10684.565 }, { "epoch": 1.2701992997576084, "grad_norm": 0.7618328740622589, "learning_rate": 2.9414835997349705e-06, "loss": 0.2904599666595459, "num_input_tokens_seen": 777017392, "step": 18865, "train_runtime": 72723.3515, "train_tokens_per_second": 10684.565 }, { "epoch": 1.2705359547535686, "grad_norm": 0.6745888898141588, "learning_rate": 2.939074288142045e-06, "loss": 0.3214207649230957, "num_input_tokens_seen": 777232408, "step": 18870, "train_runtime": 72742.1481, "train_tokens_per_second": 10684.76 }, { "epoch": 1.2708726097495286, "grad_norm": 0.9259746434564864, "learning_rate": 2.9366655528804257e-06, "loss": 0.29028823375701907, "num_input_tokens_seen": 777439592, "step": 18875, "train_runtime": 72762.5271, "train_tokens_per_second": 10684.615 }, { "epoch": 1.271209264745489, "grad_norm": 0.6767134689194919, "learning_rate": 2.934257394623702e-06, "loss": 0.29122228622436525, "num_input_tokens_seen": 777648376, "step": 18880, "train_runtime": 72780.8658, "train_tokens_per_second": 10684.791 }, { "epoch": 1.271545919741449, "grad_norm": 0.6814086856565504, "learning_rate": 2.9318498140453134e-06, "loss": 0.3174391508102417, "num_input_tokens_seen": 777854800, "step": 18885, "train_runtime": 72799.6352, "train_tokens_per_second": 10684.872 }, { "epoch": 1.2718825747374092, "grad_norm": 0.8053233189533924, "learning_rate": 2.929442811818527e-06, "loss": 0.31589958667755125, "num_input_tokens_seen": 778053920, "step": 18890, "train_runtime": 72820.4456, "train_tokens_per_second": 10684.553 }, { "epoch": 1.2722192297333692, "grad_norm": 0.7860745283578277, "learning_rate": 2.927036388616457e-06, "loss": 0.30019388198852537, "num_input_tokens_seen": 778246776, "step": 18895, "train_runtime": 72838.6433, "train_tokens_per_second": 10684.531 }, { "epoch": 1.2725558847293295, "grad_norm": 0.8332560885924838, "learning_rate": 2.9246305451120494e-06, "loss": 0.3212893962860107, "num_input_tokens_seen": 778440280, "step": 18900, "train_runtime": 72857.7335, "train_tokens_per_second": 10684.388 }, { "epoch": 1.2728925397252895, "grad_norm": 0.6876913557619078, "learning_rate": 2.922225281978095e-06, "loss": 0.3048374176025391, "num_input_tokens_seen": 778648144, "step": 18905, "train_runtime": 72878.6493, "train_tokens_per_second": 10684.174 }, { "epoch": 1.2732291947212497, "grad_norm": 0.7273806847707641, "learning_rate": 2.919820599887212e-06, "loss": 0.2993419647216797, "num_input_tokens_seen": 778854784, "step": 18910, "train_runtime": 72899.7433, "train_tokens_per_second": 10683.917 }, { "epoch": 1.2735658497172098, "grad_norm": 0.7907447634538094, "learning_rate": 2.917416499511866e-06, "loss": 0.30165491104125974, "num_input_tokens_seen": 779047800, "step": 18915, "train_runtime": 72917.8382, "train_tokens_per_second": 10683.912 }, { "epoch": 1.27390250471317, "grad_norm": 0.7238329359289503, "learning_rate": 2.9150129815243553e-06, "loss": 0.2849942684173584, "num_input_tokens_seen": 779252504, "step": 18920, "train_runtime": 72938.5448, "train_tokens_per_second": 10683.686 }, { "epoch": 1.27423915970913, "grad_norm": 0.7816788544887173, "learning_rate": 2.912610046596816e-06, "loss": 0.30049374103546145, "num_input_tokens_seen": 779450824, "step": 18925, "train_runtime": 72958.5453, "train_tokens_per_second": 10683.475 }, { "epoch": 1.2745758147050903, "grad_norm": 0.6627650104822751, "learning_rate": 2.91020769540122e-06, "loss": 0.31568284034729005, "num_input_tokens_seen": 779640416, "step": 18930, "train_runtime": 72978.0891, "train_tokens_per_second": 10683.212 }, { "epoch": 1.2749124697010503, "grad_norm": 0.6930482880328889, "learning_rate": 2.9078059286093795e-06, "loss": 0.2978449821472168, "num_input_tokens_seen": 779837688, "step": 18935, "train_runtime": 72997.931, "train_tokens_per_second": 10683.011 }, { "epoch": 1.2752491246970106, "grad_norm": 0.6780102353869192, "learning_rate": 2.905404746892937e-06, "loss": 0.2902296304702759, "num_input_tokens_seen": 780039184, "step": 18940, "train_runtime": 73017.7636, "train_tokens_per_second": 10682.869 }, { "epoch": 1.2755857796929706, "grad_norm": 1.2262550575701807, "learning_rate": 2.903004150923382e-06, "loss": 0.30759372711181643, "num_input_tokens_seen": 780249696, "step": 18945, "train_runtime": 73037.1491, "train_tokens_per_second": 10682.916 }, { "epoch": 1.2759224346889309, "grad_norm": 0.7040876770076394, "learning_rate": 2.9006041413720252e-06, "loss": 0.3302470207214355, "num_input_tokens_seen": 780461248, "step": 18950, "train_runtime": 73057.5691, "train_tokens_per_second": 10682.825 }, { "epoch": 1.2762590896848909, "grad_norm": 0.6910523172282028, "learning_rate": 2.8982047189100276e-06, "loss": 0.3034370899200439, "num_input_tokens_seen": 780677520, "step": 18955, "train_runtime": 73075.5126, "train_tokens_per_second": 10683.162 }, { "epoch": 1.2765957446808511, "grad_norm": 0.7427963345094164, "learning_rate": 2.895805884208378e-06, "loss": 0.3098992586135864, "num_input_tokens_seen": 780866640, "step": 18960, "train_runtime": 73095.3199, "train_tokens_per_second": 10682.854 }, { "epoch": 1.2769323996768112, "grad_norm": 0.7883952933356054, "learning_rate": 2.8934076379379016e-06, "loss": 0.3157687187194824, "num_input_tokens_seen": 781081832, "step": 18965, "train_runtime": 73113.1133, "train_tokens_per_second": 10683.198 }, { "epoch": 1.2772690546727714, "grad_norm": 0.8672179656618203, "learning_rate": 2.891009980769266e-06, "loss": 0.30914719104766847, "num_input_tokens_seen": 781292672, "step": 18970, "train_runtime": 73133.5389, "train_tokens_per_second": 10683.097 }, { "epoch": 1.2776057096687314, "grad_norm": 0.7962484065681265, "learning_rate": 2.88861291337296e-06, "loss": 0.30281682014465333, "num_input_tokens_seen": 781498280, "step": 18975, "train_runtime": 73152.5994, "train_tokens_per_second": 10683.124 }, { "epoch": 1.2779423646646917, "grad_norm": 0.7081615442517594, "learning_rate": 2.8862164364193236e-06, "loss": 0.2948120355606079, "num_input_tokens_seen": 781706416, "step": 18980, "train_runtime": 73172.2004, "train_tokens_per_second": 10683.107 }, { "epoch": 1.2782790196606517, "grad_norm": 0.7179998512811891, "learning_rate": 2.8838205505785168e-06, "loss": 0.30994954109191897, "num_input_tokens_seen": 781917176, "step": 18985, "train_runtime": 73190.9077, "train_tokens_per_second": 10683.256 }, { "epoch": 1.278615674656612, "grad_norm": 0.6333237279208724, "learning_rate": 2.881425256520547e-06, "loss": 0.2899285316467285, "num_input_tokens_seen": 782120072, "step": 18990, "train_runtime": 73209.3632, "train_tokens_per_second": 10683.334 }, { "epoch": 1.278952329652572, "grad_norm": 0.6730940548048859, "learning_rate": 2.8790305549152487e-06, "loss": 0.25345916748046876, "num_input_tokens_seen": 782331904, "step": 18995, "train_runtime": 73227.7823, "train_tokens_per_second": 10683.539 }, { "epoch": 1.2792889846485322, "grad_norm": 0.7203164229481714, "learning_rate": 2.876636446432292e-06, "loss": 0.3233451843261719, "num_input_tokens_seen": 782541704, "step": 19000, "train_runtime": 73246.571, "train_tokens_per_second": 10683.663 }, { "epoch": 1.2796256396444923, "grad_norm": 0.68798817165948, "learning_rate": 2.8742429317411826e-06, "loss": 0.3109186410903931, "num_input_tokens_seen": 782752280, "step": 19005, "train_runtime": 73265.0168, "train_tokens_per_second": 10683.848 }, { "epoch": 1.2799622946404525, "grad_norm": 0.7573102698020893, "learning_rate": 2.8718500115112585e-06, "loss": 0.3134957551956177, "num_input_tokens_seen": 782947168, "step": 19010, "train_runtime": 73283.8776, "train_tokens_per_second": 10683.757 }, { "epoch": 1.2802989496364126, "grad_norm": 0.7247050658199153, "learning_rate": 2.869457686411691e-06, "loss": 0.32781970500946045, "num_input_tokens_seen": 783144504, "step": 19015, "train_runtime": 73303.4155, "train_tokens_per_second": 10683.602 }, { "epoch": 1.2806356046323728, "grad_norm": 0.7190126784988192, "learning_rate": 2.8670659571114912e-06, "loss": 0.3069463729858398, "num_input_tokens_seen": 783357248, "step": 19020, "train_runtime": 73322.7791, "train_tokens_per_second": 10683.682 }, { "epoch": 1.2809722596283328, "grad_norm": 0.6411982661083866, "learning_rate": 2.864674824279491e-06, "loss": 0.29516329765319826, "num_input_tokens_seen": 783563880, "step": 19025, "train_runtime": 73341.2133, "train_tokens_per_second": 10683.814 }, { "epoch": 1.281308914624293, "grad_norm": 0.6873028827518474, "learning_rate": 2.862284288584371e-06, "loss": 0.28817195892333985, "num_input_tokens_seen": 783777016, "step": 19030, "train_runtime": 73361.5396, "train_tokens_per_second": 10683.759 }, { "epoch": 1.2816455696202531, "grad_norm": 0.7887689993799301, "learning_rate": 2.8598943506946297e-06, "loss": 0.2959585189819336, "num_input_tokens_seen": 783983392, "step": 19035, "train_runtime": 73381.4486, "train_tokens_per_second": 10683.673 }, { "epoch": 1.2819822246162134, "grad_norm": 0.68005531162117, "learning_rate": 2.85750501127861e-06, "loss": 0.28128159046173096, "num_input_tokens_seen": 784185520, "step": 19040, "train_runtime": 73399.6443, "train_tokens_per_second": 10683.778 }, { "epoch": 1.2823188796121734, "grad_norm": 0.6533291111693313, "learning_rate": 2.8551162710044827e-06, "loss": 0.304369854927063, "num_input_tokens_seen": 784389376, "step": 19045, "train_runtime": 73419.0182, "train_tokens_per_second": 10683.736 }, { "epoch": 1.2826555346081336, "grad_norm": 0.7358411746204836, "learning_rate": 2.8527281305402503e-06, "loss": 0.3263739585876465, "num_input_tokens_seen": 784596912, "step": 19050, "train_runtime": 73437.4994, "train_tokens_per_second": 10683.873 }, { "epoch": 1.2829921896040937, "grad_norm": 0.7746612389683889, "learning_rate": 2.8503405905537496e-06, "loss": 0.29060509204864504, "num_input_tokens_seen": 784798424, "step": 19055, "train_runtime": 73456.5681, "train_tokens_per_second": 10683.843 }, { "epoch": 1.283328844600054, "grad_norm": 0.7117494141666973, "learning_rate": 2.847953651712647e-06, "loss": 0.30803446769714354, "num_input_tokens_seen": 785016512, "step": 19060, "train_runtime": 73474.387, "train_tokens_per_second": 10684.22 }, { "epoch": 1.283665499596014, "grad_norm": 0.7101839557359216, "learning_rate": 2.8455673146844426e-06, "loss": 0.2987882852554321, "num_input_tokens_seen": 785209560, "step": 19065, "train_runtime": 73493.5532, "train_tokens_per_second": 10684.06 }, { "epoch": 1.2840021545919742, "grad_norm": 0.7300898666321001, "learning_rate": 2.8431815801364717e-06, "loss": 0.3211266279220581, "num_input_tokens_seen": 785415136, "step": 19070, "train_runtime": 73513.7991, "train_tokens_per_second": 10683.914 }, { "epoch": 1.2843388095879342, "grad_norm": 0.7694236068433513, "learning_rate": 2.8407964487358906e-06, "loss": 0.30827927589416504, "num_input_tokens_seen": 785626448, "step": 19075, "train_runtime": 73533.1539, "train_tokens_per_second": 10683.976 }, { "epoch": 1.2846754645838945, "grad_norm": 0.7699134776681286, "learning_rate": 2.838411921149702e-06, "loss": 0.30194873809814454, "num_input_tokens_seen": 785816880, "step": 19080, "train_runtime": 73551.6273, "train_tokens_per_second": 10683.882 }, { "epoch": 1.2850121195798545, "grad_norm": 0.7111747617751648, "learning_rate": 2.836027998044722e-06, "loss": 0.3029590129852295, "num_input_tokens_seen": 786017072, "step": 19085, "train_runtime": 73571.1378, "train_tokens_per_second": 10683.769 }, { "epoch": 1.2853487745758148, "grad_norm": 0.7717929423670136, "learning_rate": 2.8336446800876143e-06, "loss": 0.30313334465026853, "num_input_tokens_seen": 786201776, "step": 19090, "train_runtime": 73590.2037, "train_tokens_per_second": 10683.511 }, { "epoch": 1.2856854295717748, "grad_norm": 0.8023860175043782, "learning_rate": 2.8312619679448637e-06, "loss": 0.28399455547332764, "num_input_tokens_seen": 786410624, "step": 19095, "train_runtime": 73609.6989, "train_tokens_per_second": 10683.519 }, { "epoch": 1.286022084567735, "grad_norm": 0.7190530917369979, "learning_rate": 2.8288798622827884e-06, "loss": 0.31529221534729, "num_input_tokens_seen": 786600400, "step": 19100, "train_runtime": 73629.7864, "train_tokens_per_second": 10683.182 }, { "epoch": 1.286358739563695, "grad_norm": 0.867037969528795, "learning_rate": 2.826498363767536e-06, "loss": 0.3155048131942749, "num_input_tokens_seen": 786790616, "step": 19105, "train_runtime": 73649.8195, "train_tokens_per_second": 10682.859 }, { "epoch": 1.2866953945596553, "grad_norm": 0.7813456580861825, "learning_rate": 2.8241174730650855e-06, "loss": 0.30308282375335693, "num_input_tokens_seen": 786999952, "step": 19110, "train_runtime": 73669.3821, "train_tokens_per_second": 10682.863 }, { "epoch": 1.2870320495556153, "grad_norm": 0.726964973077904, "learning_rate": 2.821737190841244e-06, "loss": 0.2959714651107788, "num_input_tokens_seen": 787203624, "step": 19115, "train_runtime": 73688.501, "train_tokens_per_second": 10682.856 }, { "epoch": 1.2873687045515756, "grad_norm": 0.7117198041652357, "learning_rate": 2.8193575177616537e-06, "loss": 0.2939032793045044, "num_input_tokens_seen": 787410040, "step": 19120, "train_runtime": 73707.6396, "train_tokens_per_second": 10682.882 }, { "epoch": 1.2877053595475356, "grad_norm": 0.6842777986066882, "learning_rate": 2.816978454491777e-06, "loss": 0.28047804832458495, "num_input_tokens_seen": 787626352, "step": 19125, "train_runtime": 73726.4746, "train_tokens_per_second": 10683.087 }, { "epoch": 1.2880420145434959, "grad_norm": 0.8074514610729424, "learning_rate": 2.814600001696919e-06, "loss": 0.3199965715408325, "num_input_tokens_seen": 787826720, "step": 19130, "train_runtime": 73744.898, "train_tokens_per_second": 10683.135 }, { "epoch": 1.288378669539456, "grad_norm": 0.7253672305457787, "learning_rate": 2.812222160042196e-06, "loss": 0.3126213788986206, "num_input_tokens_seen": 788038608, "step": 19135, "train_runtime": 73764.6419, "train_tokens_per_second": 10683.148 }, { "epoch": 1.2887153245354162, "grad_norm": 0.7045009822327317, "learning_rate": 2.809844930192573e-06, "loss": 0.31743669509887695, "num_input_tokens_seen": 788242008, "step": 19140, "train_runtime": 73783.112, "train_tokens_per_second": 10683.231 }, { "epoch": 1.2890519795313762, "grad_norm": 0.7360603744584413, "learning_rate": 2.807468312812831e-06, "loss": 0.32561745643615725, "num_input_tokens_seen": 788444048, "step": 19145, "train_runtime": 73802.5039, "train_tokens_per_second": 10683.161 }, { "epoch": 1.2893886345273364, "grad_norm": 0.7084808450133323, "learning_rate": 2.805092308567584e-06, "loss": 0.2865345001220703, "num_input_tokens_seen": 788656008, "step": 19150, "train_runtime": 73821.2212, "train_tokens_per_second": 10683.324 }, { "epoch": 1.2897252895232965, "grad_norm": 0.737770573234967, "learning_rate": 2.802716918121273e-06, "loss": 0.3013970136642456, "num_input_tokens_seen": 788869880, "step": 19155, "train_runtime": 73840.9212, "train_tokens_per_second": 10683.37 }, { "epoch": 1.2900619445192567, "grad_norm": 0.7136669518845556, "learning_rate": 2.8003421421381704e-06, "loss": 0.2929009675979614, "num_input_tokens_seen": 789081672, "step": 19160, "train_runtime": 73859.3189, "train_tokens_per_second": 10683.576 }, { "epoch": 1.2903985995152167, "grad_norm": 0.7248521354583463, "learning_rate": 2.797967981282371e-06, "loss": 0.32056293487548826, "num_input_tokens_seen": 789292584, "step": 19165, "train_runtime": 73879.7502, "train_tokens_per_second": 10683.477 }, { "epoch": 1.290735254511177, "grad_norm": 0.6867857370559063, "learning_rate": 2.795594436217808e-06, "loss": 0.2950688362121582, "num_input_tokens_seen": 789497616, "step": 19170, "train_runtime": 73898.0678, "train_tokens_per_second": 10683.603 }, { "epoch": 1.291071909507137, "grad_norm": 0.6324038960496169, "learning_rate": 2.7932215076082277e-06, "loss": 0.29258313179016116, "num_input_tokens_seen": 789694080, "step": 19175, "train_runtime": 73917.6703, "train_tokens_per_second": 10683.428 }, { "epoch": 1.2914085645030973, "grad_norm": 0.6999624614232092, "learning_rate": 2.790849196117219e-06, "loss": 0.3139002323150635, "num_input_tokens_seen": 789916344, "step": 19180, "train_runtime": 73937.1412, "train_tokens_per_second": 10683.62 }, { "epoch": 1.2917452194990573, "grad_norm": 0.7063488626960513, "learning_rate": 2.7884775024081856e-06, "loss": 0.30747246742248535, "num_input_tokens_seen": 790120904, "step": 19185, "train_runtime": 73955.5853, "train_tokens_per_second": 10683.722 }, { "epoch": 1.2920818744950175, "grad_norm": 0.7270616055863215, "learning_rate": 2.786106427144367e-06, "loss": 0.29291305541992185, "num_input_tokens_seen": 790324880, "step": 19190, "train_runtime": 73974.7629, "train_tokens_per_second": 10683.71 }, { "epoch": 1.2924185294909776, "grad_norm": 0.7287861893528547, "learning_rate": 2.783735970988828e-06, "loss": 0.27472629547119143, "num_input_tokens_seen": 790527792, "step": 19195, "train_runtime": 73995.3817, "train_tokens_per_second": 10683.475 }, { "epoch": 1.2927551844869378, "grad_norm": 0.7681711275714914, "learning_rate": 2.7813661346044566e-06, "loss": 0.31622202396392823, "num_input_tokens_seen": 790729248, "step": 19200, "train_runtime": 74013.7884, "train_tokens_per_second": 10683.54 }, { "epoch": 1.2930918394828979, "grad_norm": 0.7604124134225705, "learning_rate": 2.7789969186539713e-06, "loss": 0.3070987224578857, "num_input_tokens_seen": 790925704, "step": 19205, "train_runtime": 74034.0636, "train_tokens_per_second": 10683.267 }, { "epoch": 1.293428494478858, "grad_norm": 0.7541175941293012, "learning_rate": 2.776628323799915e-06, "loss": 0.32070255279541016, "num_input_tokens_seen": 791129288, "step": 19210, "train_runtime": 74052.352, "train_tokens_per_second": 10683.378 }, { "epoch": 1.2937651494748181, "grad_norm": 0.7674615730125115, "learning_rate": 2.774260350704657e-06, "loss": 0.31845979690551757, "num_input_tokens_seen": 791331816, "step": 19215, "train_runtime": 74071.4048, "train_tokens_per_second": 10683.364 }, { "epoch": 1.2941018044707784, "grad_norm": 0.7324909981672387, "learning_rate": 2.771893000030398e-06, "loss": 0.3176593542098999, "num_input_tokens_seen": 791533584, "step": 19220, "train_runtime": 74091.0468, "train_tokens_per_second": 10683.256 }, { "epoch": 1.2944384594667384, "grad_norm": 0.7062030671581886, "learning_rate": 2.7695262724391526e-06, "loss": 0.2945362091064453, "num_input_tokens_seen": 791734224, "step": 19225, "train_runtime": 74110.85, "train_tokens_per_second": 10683.108 }, { "epoch": 1.2947751144626987, "grad_norm": 0.730532204053038, "learning_rate": 2.767160168592777e-06, "loss": 0.34368157386779785, "num_input_tokens_seen": 791950040, "step": 19230, "train_runtime": 74130.3083, "train_tokens_per_second": 10683.215 }, { "epoch": 1.2951117694586587, "grad_norm": 0.7375828207283733, "learning_rate": 2.7647946891529355e-06, "loss": 0.3188678503036499, "num_input_tokens_seen": 792138592, "step": 19235, "train_runtime": 74148.285, "train_tokens_per_second": 10683.168 }, { "epoch": 1.295448424454619, "grad_norm": 0.6826559275117073, "learning_rate": 2.7624298347811342e-06, "loss": 0.30719170570373533, "num_input_tokens_seen": 792332760, "step": 19240, "train_runtime": 74166.7264, "train_tokens_per_second": 10683.13 }, { "epoch": 1.295785079450579, "grad_norm": 0.7701775268350984, "learning_rate": 2.7600656061386945e-06, "loss": 0.3170806884765625, "num_input_tokens_seen": 792546536, "step": 19245, "train_runtime": 74186.4864, "train_tokens_per_second": 10683.166 }, { "epoch": 1.2961217344465392, "grad_norm": 0.7374921734593359, "learning_rate": 2.757702003886765e-06, "loss": 0.29309887886047364, "num_input_tokens_seen": 792751488, "step": 19250, "train_runtime": 74205.1939, "train_tokens_per_second": 10683.235 }, { "epoch": 1.2964583894424992, "grad_norm": 0.7914876467744435, "learning_rate": 2.7553390286863205e-06, "loss": 0.29722323417663576, "num_input_tokens_seen": 792943392, "step": 19255, "train_runtime": 74223.1612, "train_tokens_per_second": 10683.234 }, { "epoch": 1.2967950444384595, "grad_norm": 0.725574261425603, "learning_rate": 2.752976681198159e-06, "loss": 0.32051544189453124, "num_input_tokens_seen": 793156632, "step": 19260, "train_runtime": 74241.9502, "train_tokens_per_second": 10683.402 }, { "epoch": 1.2971316994344195, "grad_norm": 0.7690909795855506, "learning_rate": 2.750614962082901e-06, "loss": 0.2826441526412964, "num_input_tokens_seen": 793367784, "step": 19265, "train_runtime": 74261.2524, "train_tokens_per_second": 10683.469 }, { "epoch": 1.2974683544303798, "grad_norm": 0.6698851154395757, "learning_rate": 2.748253872001e-06, "loss": 0.30166480541229246, "num_input_tokens_seen": 793572464, "step": 19270, "train_runtime": 74279.4812, "train_tokens_per_second": 10683.603 }, { "epoch": 1.2978050094263398, "grad_norm": 0.7718866401884016, "learning_rate": 2.74589341161272e-06, "loss": 0.3056966304779053, "num_input_tokens_seen": 793762256, "step": 19275, "train_runtime": 74299.9203, "train_tokens_per_second": 10683.218 }, { "epoch": 1.2981416644223, "grad_norm": 0.8155233458547274, "learning_rate": 2.743533581578163e-06, "loss": 0.3123161315917969, "num_input_tokens_seen": 793961368, "step": 19280, "train_runtime": 74319.455, "train_tokens_per_second": 10683.089 }, { "epoch": 1.29847831941826, "grad_norm": 0.7767130064493634, "learning_rate": 2.7411743825572407e-06, "loss": 0.3459150314331055, "num_input_tokens_seen": 794178352, "step": 19285, "train_runtime": 74337.2851, "train_tokens_per_second": 10683.446 }, { "epoch": 1.2988149744142203, "grad_norm": 0.701033360385787, "learning_rate": 2.7388158152097015e-06, "loss": 0.30738518238067625, "num_input_tokens_seen": 794391240, "step": 19290, "train_runtime": 74355.2181, "train_tokens_per_second": 10683.732 }, { "epoch": 1.2991516294101804, "grad_norm": 0.6864935080911797, "learning_rate": 2.736457880195109e-06, "loss": 0.3198849678039551, "num_input_tokens_seen": 794592504, "step": 19295, "train_runtime": 74373.9525, "train_tokens_per_second": 10683.747 }, { "epoch": 1.2994882844061406, "grad_norm": 0.7301500592493397, "learning_rate": 2.7341005781728523e-06, "loss": 0.32888362407684324, "num_input_tokens_seen": 794808952, "step": 19300, "train_runtime": 74392.6969, "train_tokens_per_second": 10683.965 }, { "epoch": 1.2998249394021006, "grad_norm": 0.7241459441417822, "learning_rate": 2.7317439098021444e-06, "loss": 0.3063692092895508, "num_input_tokens_seen": 795014672, "step": 19305, "train_runtime": 74413.7784, "train_tokens_per_second": 10683.703 }, { "epoch": 1.300161594398061, "grad_norm": 0.7764400958073746, "learning_rate": 2.7293878757420185e-06, "loss": 0.32222733497619627, "num_input_tokens_seen": 795220288, "step": 19310, "train_runtime": 74432.766, "train_tokens_per_second": 10683.74 }, { "epoch": 1.3004982493940211, "grad_norm": 0.6665458529759936, "learning_rate": 2.7270324766513306e-06, "loss": 0.31339735984802247, "num_input_tokens_seen": 795436456, "step": 19315, "train_runtime": 74453.1741, "train_tokens_per_second": 10683.715 }, { "epoch": 1.3008349043899812, "grad_norm": 0.7186463611360173, "learning_rate": 2.724677713188767e-06, "loss": 0.30579338073730467, "num_input_tokens_seen": 795632672, "step": 19320, "train_runtime": 74473.434, "train_tokens_per_second": 10683.443 }, { "epoch": 1.3011715593859412, "grad_norm": 0.7702120838648372, "learning_rate": 2.722323586012821e-06, "loss": 0.3153712511062622, "num_input_tokens_seen": 795838000, "step": 19325, "train_runtime": 74492.0909, "train_tokens_per_second": 10683.523 }, { "epoch": 1.3015082143819015, "grad_norm": 0.7272076827312373, "learning_rate": 2.7199700957818252e-06, "loss": 0.3007438898086548, "num_input_tokens_seen": 796049600, "step": 19330, "train_runtime": 74512.2836, "train_tokens_per_second": 10683.468 }, { "epoch": 1.3018448693778617, "grad_norm": 0.8449958264710974, "learning_rate": 2.717617243153918e-06, "loss": 0.3032217502593994, "num_input_tokens_seen": 796249664, "step": 19335, "train_runtime": 74531.8295, "train_tokens_per_second": 10683.351 }, { "epoch": 1.3021815243738217, "grad_norm": 0.7206501031101102, "learning_rate": 2.715265028787073e-06, "loss": 0.31675138473510744, "num_input_tokens_seen": 796445432, "step": 19340, "train_runtime": 74551.775, "train_tokens_per_second": 10683.118 }, { "epoch": 1.3025181793697818, "grad_norm": 0.8331839800548895, "learning_rate": 2.7129134533390765e-06, "loss": 0.33556787967681884, "num_input_tokens_seen": 796661264, "step": 19345, "train_runtime": 74570.5383, "train_tokens_per_second": 10683.325 }, { "epoch": 1.302854834365742, "grad_norm": 0.7485175093584052, "learning_rate": 2.7105625174675404e-06, "loss": 0.2945798397064209, "num_input_tokens_seen": 796876144, "step": 19350, "train_runtime": 74590.2258, "train_tokens_per_second": 10683.386 }, { "epoch": 1.3031914893617023, "grad_norm": 0.7081934765879077, "learning_rate": 2.7082122218298957e-06, "loss": 0.2945189237594604, "num_input_tokens_seen": 797075296, "step": 19355, "train_runtime": 74607.9514, "train_tokens_per_second": 10683.517 }, { "epoch": 1.3035281443576623, "grad_norm": 0.7554501479511403, "learning_rate": 2.7058625670833947e-06, "loss": 0.30231807231903074, "num_input_tokens_seen": 797277616, "step": 19360, "train_runtime": 74626.6276, "train_tokens_per_second": 10683.554 }, { "epoch": 1.3038647993536223, "grad_norm": 0.9027522933392418, "learning_rate": 2.70351355388511e-06, "loss": 0.3071136951446533, "num_input_tokens_seen": 797480648, "step": 19365, "train_runtime": 74645.7325, "train_tokens_per_second": 10683.54 }, { "epoch": 1.3042014543495826, "grad_norm": 0.7268905872303294, "learning_rate": 2.7011651828919407e-06, "loss": 0.3069450855255127, "num_input_tokens_seen": 797690640, "step": 19370, "train_runtime": 74663.4017, "train_tokens_per_second": 10683.824 }, { "epoch": 1.3045381093455428, "grad_norm": 0.7392141943130213, "learning_rate": 2.698817454760593e-06, "loss": 0.3054459571838379, "num_input_tokens_seen": 797894120, "step": 19375, "train_runtime": 74680.774, "train_tokens_per_second": 10684.063 }, { "epoch": 1.3048747643415028, "grad_norm": 0.8083537359208073, "learning_rate": 2.696470370147611e-06, "loss": 0.3153265953063965, "num_input_tokens_seen": 798098744, "step": 19380, "train_runtime": 74699.9073, "train_tokens_per_second": 10684.066 }, { "epoch": 1.3052114193374629, "grad_norm": 0.7439686277193146, "learning_rate": 2.69412392970934e-06, "loss": 0.3333925247192383, "num_input_tokens_seen": 798304984, "step": 19385, "train_runtime": 74720.1623, "train_tokens_per_second": 10683.93 }, { "epoch": 1.3055480743334231, "grad_norm": 0.6301030095412882, "learning_rate": 2.6917781341019615e-06, "loss": 0.29944791793823244, "num_input_tokens_seen": 798512008, "step": 19390, "train_runtime": 74738.8921, "train_tokens_per_second": 10684.023 }, { "epoch": 1.3058847293293834, "grad_norm": 0.7517340949983847, "learning_rate": 2.689432983981467e-06, "loss": 0.30283751487731936, "num_input_tokens_seen": 798728624, "step": 19395, "train_runtime": 74759.191, "train_tokens_per_second": 10684.019 }, { "epoch": 1.3062213843253434, "grad_norm": 0.6831652709307888, "learning_rate": 2.6870884800036713e-06, "loss": 0.3131109714508057, "num_input_tokens_seen": 798928664, "step": 19400, "train_runtime": 74777.7929, "train_tokens_per_second": 10684.036 }, { "epoch": 1.3065580393213034, "grad_norm": 0.8053622902613746, "learning_rate": 2.684744622824207e-06, "loss": 0.3288958787918091, "num_input_tokens_seen": 799125216, "step": 19405, "train_runtime": 74796.5891, "train_tokens_per_second": 10683.979 }, { "epoch": 1.3068946943172637, "grad_norm": 0.7439362428953269, "learning_rate": 2.6824014130985255e-06, "loss": 0.31491641998291015, "num_input_tokens_seen": 799329680, "step": 19410, "train_runtime": 74815.5865, "train_tokens_per_second": 10683.999 }, { "epoch": 1.307231349313224, "grad_norm": 0.6968288608313954, "learning_rate": 2.680058851481896e-06, "loss": 0.30065834522247314, "num_input_tokens_seen": 799534072, "step": 19415, "train_runtime": 74834.8022, "train_tokens_per_second": 10683.987 }, { "epoch": 1.307568004309184, "grad_norm": 0.759399554873167, "learning_rate": 2.6777169386294154e-06, "loss": 0.3144219398498535, "num_input_tokens_seen": 799739304, "step": 19420, "train_runtime": 74853.2111, "train_tokens_per_second": 10684.101 }, { "epoch": 1.307904659305144, "grad_norm": 0.7265945223828852, "learning_rate": 2.6753756751959846e-06, "loss": 0.30338330268859864, "num_input_tokens_seen": 799954616, "step": 19425, "train_runtime": 74872.0494, "train_tokens_per_second": 10684.289 }, { "epoch": 1.3082413143011042, "grad_norm": 0.6986241512555004, "learning_rate": 2.6730350618363367e-06, "loss": 0.29942145347595217, "num_input_tokens_seen": 800160800, "step": 19430, "train_runtime": 74889.8904, "train_tokens_per_second": 10684.497 }, { "epoch": 1.3085779692970645, "grad_norm": 0.6682374414593746, "learning_rate": 2.6706950992050097e-06, "loss": 0.30070154666900634, "num_input_tokens_seen": 800367264, "step": 19435, "train_runtime": 74908.5893, "train_tokens_per_second": 10684.586 }, { "epoch": 1.3089146242930245, "grad_norm": 0.7303177603633808, "learning_rate": 2.6683557879563726e-06, "loss": 0.32249913215637205, "num_input_tokens_seen": 800573824, "step": 19440, "train_runtime": 74926.2298, "train_tokens_per_second": 10684.827 }, { "epoch": 1.3092512792889845, "grad_norm": 0.7252298989352877, "learning_rate": 2.6660171287446045e-06, "loss": 0.3311166763305664, "num_input_tokens_seen": 800783064, "step": 19445, "train_runtime": 74945.1197, "train_tokens_per_second": 10684.926 }, { "epoch": 1.3095879342849448, "grad_norm": 0.703491211080701, "learning_rate": 2.6636791222237034e-06, "loss": 0.3253315925598145, "num_input_tokens_seen": 800989448, "step": 19450, "train_runtime": 74964.3378, "train_tokens_per_second": 10684.94 }, { "epoch": 1.309924589280905, "grad_norm": 0.716674008943527, "learning_rate": 2.6613417690474864e-06, "loss": 0.3074014663696289, "num_input_tokens_seen": 801198072, "step": 19455, "train_runtime": 74982.2327, "train_tokens_per_second": 10685.172 }, { "epoch": 1.310261244276865, "grad_norm": 0.6559801295310712, "learning_rate": 2.6590050698695856e-06, "loss": 0.30452651977539064, "num_input_tokens_seen": 801402616, "step": 19460, "train_runtime": 75001.0061, "train_tokens_per_second": 10685.225 }, { "epoch": 1.310597899272825, "grad_norm": 0.6631034907667814, "learning_rate": 2.6566690253434508e-06, "loss": 0.3174558162689209, "num_input_tokens_seen": 801618776, "step": 19465, "train_runtime": 75019.8006, "train_tokens_per_second": 10685.429 }, { "epoch": 1.3109345542687854, "grad_norm": 0.7819408573264197, "learning_rate": 2.654333636122354e-06, "loss": 0.29915223121643064, "num_input_tokens_seen": 801831000, "step": 19470, "train_runtime": 75039.1919, "train_tokens_per_second": 10685.496 }, { "epoch": 1.3112712092647456, "grad_norm": 0.7149747557830627, "learning_rate": 2.6519989028593728e-06, "loss": 0.314014196395874, "num_input_tokens_seen": 802044224, "step": 19475, "train_runtime": 75058.9332, "train_tokens_per_second": 10685.527 }, { "epoch": 1.3116078642607056, "grad_norm": 0.8012354829665723, "learning_rate": 2.649664826207414e-06, "loss": 0.3180240631103516, "num_input_tokens_seen": 802247128, "step": 19480, "train_runtime": 75078.0139, "train_tokens_per_second": 10685.513 }, { "epoch": 1.3119445192566657, "grad_norm": 0.7924979217038349, "learning_rate": 2.647331406819189e-06, "loss": 0.3375687837600708, "num_input_tokens_seen": 802446424, "step": 19485, "train_runtime": 75097.613, "train_tokens_per_second": 10685.379 }, { "epoch": 1.312281174252626, "grad_norm": 0.6413171780767968, "learning_rate": 2.644998645347236e-06, "loss": 0.29669549465179446, "num_input_tokens_seen": 802649064, "step": 19490, "train_runtime": 75116.7947, "train_tokens_per_second": 10685.348 }, { "epoch": 1.3126178292485862, "grad_norm": 0.6987127478887959, "learning_rate": 2.6426665424439025e-06, "loss": 0.3225651025772095, "num_input_tokens_seen": 802862600, "step": 19495, "train_runtime": 75135.8049, "train_tokens_per_second": 10685.486 }, { "epoch": 1.3129544842445462, "grad_norm": 0.8341104472491438, "learning_rate": 2.6403350987613526e-06, "loss": 0.31740403175354004, "num_input_tokens_seen": 803071560, "step": 19500, "train_runtime": 75154.4826, "train_tokens_per_second": 10685.611 }, { "epoch": 1.3132911392405062, "grad_norm": 0.784599168316527, "learning_rate": 2.6380043149515676e-06, "loss": 0.3096177577972412, "num_input_tokens_seen": 803273896, "step": 19505, "train_runtime": 75172.5164, "train_tokens_per_second": 10685.739 }, { "epoch": 1.3136277942364665, "grad_norm": 0.6992919457529959, "learning_rate": 2.6356741916663453e-06, "loss": 0.30334489345550536, "num_input_tokens_seen": 803484800, "step": 19510, "train_runtime": 75191.327, "train_tokens_per_second": 10685.871 }, { "epoch": 1.3139644492324267, "grad_norm": 0.759856448422474, "learning_rate": 2.6333447295572933e-06, "loss": 0.3182713747024536, "num_input_tokens_seen": 803691784, "step": 19515, "train_runtime": 75210.0521, "train_tokens_per_second": 10685.962 }, { "epoch": 1.3143011042283868, "grad_norm": 0.7212906494994218, "learning_rate": 2.631015929275845e-06, "loss": 0.30528252124786376, "num_input_tokens_seen": 803890112, "step": 19520, "train_runtime": 75229.5829, "train_tokens_per_second": 10685.824 }, { "epoch": 1.3146377592243468, "grad_norm": 0.7494278696962112, "learning_rate": 2.628687791473234e-06, "loss": 0.2892716407775879, "num_input_tokens_seen": 804103288, "step": 19525, "train_runtime": 75247.2431, "train_tokens_per_second": 10686.149 }, { "epoch": 1.314974414220307, "grad_norm": 0.7580783168259642, "learning_rate": 2.6263603168005224e-06, "loss": 0.2844714164733887, "num_input_tokens_seen": 804311832, "step": 19530, "train_runtime": 75268.3812, "train_tokens_per_second": 10685.919 }, { "epoch": 1.3153110692162673, "grad_norm": 0.6451241141287444, "learning_rate": 2.6240335059085797e-06, "loss": 0.30487871170043945, "num_input_tokens_seen": 804524600, "step": 19535, "train_runtime": 75287.0949, "train_tokens_per_second": 10686.089 }, { "epoch": 1.3156477242122273, "grad_norm": 0.7317317578588018, "learning_rate": 2.62170735944809e-06, "loss": 0.3144144773483276, "num_input_tokens_seen": 804730432, "step": 19540, "train_runtime": 75307.07, "train_tokens_per_second": 10685.988 }, { "epoch": 1.3159843792081873, "grad_norm": 0.7193099953751575, "learning_rate": 2.6193818780695537e-06, "loss": 0.30026247501373293, "num_input_tokens_seen": 804941768, "step": 19545, "train_runtime": 75324.6096, "train_tokens_per_second": 10686.305 }, { "epoch": 1.3163210342041476, "grad_norm": 0.7161944430607917, "learning_rate": 2.6170570624232837e-06, "loss": 0.31201796531677245, "num_input_tokens_seen": 805130680, "step": 19550, "train_runtime": 75345.4397, "train_tokens_per_second": 10685.858 }, { "epoch": 1.3166576892001078, "grad_norm": 0.6916994161699461, "learning_rate": 2.6147329131594078e-06, "loss": 0.2842207908630371, "num_input_tokens_seen": 805346136, "step": 19555, "train_runtime": 75365.8018, "train_tokens_per_second": 10685.83 }, { "epoch": 1.3169943441960679, "grad_norm": 0.6287057201013159, "learning_rate": 2.612409430927867e-06, "loss": 0.2749126434326172, "num_input_tokens_seen": 805553232, "step": 19560, "train_runtime": 75385.2843, "train_tokens_per_second": 10685.815 }, { "epoch": 1.317330999192028, "grad_norm": 0.7868982434620968, "learning_rate": 2.610086616378413e-06, "loss": 0.29115393161773684, "num_input_tokens_seen": 805750296, "step": 19565, "train_runtime": 75403.7114, "train_tokens_per_second": 10685.817 }, { "epoch": 1.3176676541879881, "grad_norm": 0.6327818342261946, "learning_rate": 2.60776447016062e-06, "loss": 0.31588685512542725, "num_input_tokens_seen": 805959544, "step": 19570, "train_runtime": 75423.658, "train_tokens_per_second": 10685.766 }, { "epoch": 1.3180043091839484, "grad_norm": 0.7690898666881593, "learning_rate": 2.6054429929238607e-06, "loss": 0.31549797058105467, "num_input_tokens_seen": 806160792, "step": 19575, "train_runtime": 75441.1263, "train_tokens_per_second": 10685.959 }, { "epoch": 1.3183409641799084, "grad_norm": 0.6188178676861292, "learning_rate": 2.603122185317335e-06, "loss": 0.29292712211608884, "num_input_tokens_seen": 806354344, "step": 19580, "train_runtime": 75460.1556, "train_tokens_per_second": 10685.829 }, { "epoch": 1.3186776191758685, "grad_norm": 0.7407888666500537, "learning_rate": 2.6008020479900465e-06, "loss": 0.272747278213501, "num_input_tokens_seen": 806556496, "step": 19585, "train_runtime": 75480.0879, "train_tokens_per_second": 10685.686 }, { "epoch": 1.3190142741718287, "grad_norm": 0.7158096411513272, "learning_rate": 2.598482581590815e-06, "loss": 0.3093989849090576, "num_input_tokens_seen": 806773016, "step": 19590, "train_runtime": 75499.736, "train_tokens_per_second": 10685.773 }, { "epoch": 1.319350929167789, "grad_norm": 0.683824821619866, "learning_rate": 2.5961637867682715e-06, "loss": 0.2776422739028931, "num_input_tokens_seen": 806989960, "step": 19595, "train_runtime": 75520.904, "train_tokens_per_second": 10685.65 }, { "epoch": 1.319687584163749, "grad_norm": 0.6762193959599404, "learning_rate": 2.5938456641708598e-06, "loss": 0.2874451160430908, "num_input_tokens_seen": 807193856, "step": 19600, "train_runtime": 75538.5383, "train_tokens_per_second": 10685.855 }, { "epoch": 1.320024239159709, "grad_norm": 0.7105366132709362, "learning_rate": 2.591528214446836e-06, "loss": 0.310866641998291, "num_input_tokens_seen": 807410152, "step": 19605, "train_runtime": 75557.4038, "train_tokens_per_second": 10686.049 }, { "epoch": 1.3203608941556693, "grad_norm": 0.709925512763229, "learning_rate": 2.5892114382442664e-06, "loss": 0.32600882053375246, "num_input_tokens_seen": 807614872, "step": 19610, "train_runtime": 75576.1123, "train_tokens_per_second": 10686.113 }, { "epoch": 1.3206975491516295, "grad_norm": 0.6150953068854036, "learning_rate": 2.5868953362110287e-06, "loss": 0.30087985992431643, "num_input_tokens_seen": 807822992, "step": 19615, "train_runtime": 75595.6958, "train_tokens_per_second": 10686.098 }, { "epoch": 1.3210342041475895, "grad_norm": 0.6901383307937667, "learning_rate": 2.5845799089948196e-06, "loss": 0.3004458904266357, "num_input_tokens_seen": 808021680, "step": 19620, "train_runtime": 75615.569, "train_tokens_per_second": 10685.917 }, { "epoch": 1.3213708591435496, "grad_norm": 0.7193813248229155, "learning_rate": 2.5822651572431323e-06, "loss": 0.2993509769439697, "num_input_tokens_seen": 808232592, "step": 19625, "train_runtime": 75634.0247, "train_tokens_per_second": 10686.098 }, { "epoch": 1.3217075141395098, "grad_norm": 0.7410795038301732, "learning_rate": 2.5799510816032867e-06, "loss": 0.3006757736206055, "num_input_tokens_seen": 808416056, "step": 19630, "train_runtime": 75653.8133, "train_tokens_per_second": 10685.728 }, { "epoch": 1.32204416913547, "grad_norm": 0.7032623154098545, "learning_rate": 2.577637682722404e-06, "loss": 0.3110344886779785, "num_input_tokens_seen": 808621688, "step": 19635, "train_runtime": 75672.7961, "train_tokens_per_second": 10685.765 }, { "epoch": 1.32238082413143, "grad_norm": 0.8527199449387112, "learning_rate": 2.5753249612474195e-06, "loss": 0.3178708076477051, "num_input_tokens_seen": 808826736, "step": 19640, "train_runtime": 75691.654, "train_tokens_per_second": 10685.811 }, { "epoch": 1.3227174791273901, "grad_norm": 0.6931261153379024, "learning_rate": 2.5730129178250774e-06, "loss": 0.31498606204986573, "num_input_tokens_seen": 809040480, "step": 19645, "train_runtime": 75711.2128, "train_tokens_per_second": 10685.874 }, { "epoch": 1.3230541341233504, "grad_norm": 0.6963382500039054, "learning_rate": 2.570701553101933e-06, "loss": 0.3023268699645996, "num_input_tokens_seen": 809241344, "step": 19650, "train_runtime": 75730.0481, "train_tokens_per_second": 10685.869 }, { "epoch": 1.3233907891193106, "grad_norm": 0.686516900994134, "learning_rate": 2.568390867724354e-06, "loss": 0.3287865161895752, "num_input_tokens_seen": 809451048, "step": 19655, "train_runtime": 75750.0972, "train_tokens_per_second": 10685.809 }, { "epoch": 1.3237274441152707, "grad_norm": 0.8010755779591973, "learning_rate": 2.5660808623385143e-06, "loss": 0.30606255531311033, "num_input_tokens_seen": 809650768, "step": 19660, "train_runtime": 75770.0938, "train_tokens_per_second": 10685.624 }, { "epoch": 1.3240640991112307, "grad_norm": 0.6735081944884117, "learning_rate": 2.5637715375903984e-06, "loss": 0.282197380065918, "num_input_tokens_seen": 809858520, "step": 19665, "train_runtime": 75791.0801, "train_tokens_per_second": 10685.407 }, { "epoch": 1.324400754107191, "grad_norm": 0.8019866101475264, "learning_rate": 2.5614628941258075e-06, "loss": 0.2975594520568848, "num_input_tokens_seen": 810053832, "step": 19670, "train_runtime": 75808.9817, "train_tokens_per_second": 10685.46 }, { "epoch": 1.3247374091031512, "grad_norm": 0.755435877185499, "learning_rate": 2.5591549325903388e-06, "loss": 0.3129906177520752, "num_input_tokens_seen": 810275544, "step": 19675, "train_runtime": 75827.7057, "train_tokens_per_second": 10685.745 }, { "epoch": 1.3250740640991112, "grad_norm": 0.6945526833545896, "learning_rate": 2.5568476536294105e-06, "loss": 0.32065644264221194, "num_input_tokens_seen": 810484904, "step": 19680, "train_runtime": 75845.8264, "train_tokens_per_second": 10685.953 }, { "epoch": 1.3254107190950712, "grad_norm": 0.7190298337703631, "learning_rate": 2.5545410578882466e-06, "loss": 0.2928189516067505, "num_input_tokens_seen": 810699712, "step": 19685, "train_runtime": 75864.1033, "train_tokens_per_second": 10686.21 }, { "epoch": 1.3257473740910315, "grad_norm": 0.825798472360401, "learning_rate": 2.5522351460118776e-06, "loss": 0.2863339424133301, "num_input_tokens_seen": 810892264, "step": 19690, "train_runtime": 75881.7194, "train_tokens_per_second": 10686.266 }, { "epoch": 1.3260840290869917, "grad_norm": 0.6959978037123965, "learning_rate": 2.549929918645144e-06, "loss": 0.31107971668243406, "num_input_tokens_seen": 811109336, "step": 19695, "train_runtime": 75900.2497, "train_tokens_per_second": 10686.517 }, { "epoch": 1.3264206840829518, "grad_norm": 0.7007577636049328, "learning_rate": 2.5476253764326963e-06, "loss": 0.29242007732391356, "num_input_tokens_seen": 811304184, "step": 19700, "train_runtime": 75918.4551, "train_tokens_per_second": 10686.521 }, { "epoch": 1.3267573390789118, "grad_norm": 0.6772780407998348, "learning_rate": 2.5453215200189927e-06, "loss": 0.2962291479110718, "num_input_tokens_seen": 811505544, "step": 19705, "train_runtime": 75937.9178, "train_tokens_per_second": 10686.434 }, { "epoch": 1.327093994074872, "grad_norm": 0.7328929349549115, "learning_rate": 2.543018350048298e-06, "loss": 0.288499116897583, "num_input_tokens_seen": 811712144, "step": 19710, "train_runtime": 75956.5173, "train_tokens_per_second": 10686.537 }, { "epoch": 1.3274306490708323, "grad_norm": 0.7047662869677868, "learning_rate": 2.540715867164685e-06, "loss": 0.3119885683059692, "num_input_tokens_seen": 811919096, "step": 19715, "train_runtime": 75976.3233, "train_tokens_per_second": 10686.475 }, { "epoch": 1.3277673040667923, "grad_norm": 0.7112081309975978, "learning_rate": 2.538414072012042e-06, "loss": 0.31286258697509767, "num_input_tokens_seen": 812116712, "step": 19720, "train_runtime": 75996.4524, "train_tokens_per_second": 10686.245 }, { "epoch": 1.3281039590627524, "grad_norm": 0.7922058551723002, "learning_rate": 2.53611296523405e-06, "loss": 0.31715586185455324, "num_input_tokens_seen": 812314632, "step": 19725, "train_runtime": 76014.4994, "train_tokens_per_second": 10686.312 }, { "epoch": 1.3284406140587126, "grad_norm": 0.7379088388799118, "learning_rate": 2.5338125474742127e-06, "loss": 0.29776821136474607, "num_input_tokens_seen": 812516528, "step": 19730, "train_runtime": 76034.4543, "train_tokens_per_second": 10686.162 }, { "epoch": 1.3287772690546729, "grad_norm": 0.6554619168071859, "learning_rate": 2.531512819375832e-06, "loss": 0.2943256139755249, "num_input_tokens_seen": 812726192, "step": 19735, "train_runtime": 76055.9211, "train_tokens_per_second": 10685.903 }, { "epoch": 1.3291139240506329, "grad_norm": 0.7360459622679542, "learning_rate": 2.52921378158202e-06, "loss": 0.29257931709289553, "num_input_tokens_seen": 812924344, "step": 19740, "train_runtime": 76073.6157, "train_tokens_per_second": 10686.022 }, { "epoch": 1.329450579046593, "grad_norm": 0.7817804939062938, "learning_rate": 2.5269154347356957e-06, "loss": 0.2871829032897949, "num_input_tokens_seen": 813134080, "step": 19745, "train_runtime": 76092.6608, "train_tokens_per_second": 10686.104 }, { "epoch": 1.3297872340425532, "grad_norm": 0.868059765063452, "learning_rate": 2.5246177794795834e-06, "loss": 0.3110774517059326, "num_input_tokens_seen": 813325192, "step": 19750, "train_runtime": 76113.0996, "train_tokens_per_second": 10685.745 }, { "epoch": 1.3301238890385134, "grad_norm": 0.6215656167099225, "learning_rate": 2.5223208164562163e-06, "loss": 0.3131412029266357, "num_input_tokens_seen": 813528552, "step": 19755, "train_runtime": 76132.6694, "train_tokens_per_second": 10685.67 }, { "epoch": 1.3304605440344734, "grad_norm": 0.6695917305848926, "learning_rate": 2.5200245463079315e-06, "loss": 0.3192810297012329, "num_input_tokens_seen": 813730936, "step": 19760, "train_runtime": 76152.344, "train_tokens_per_second": 10685.567 }, { "epoch": 1.3307971990304335, "grad_norm": 0.7094100086941084, "learning_rate": 2.5177289696768725e-06, "loss": 0.32139575481414795, "num_input_tokens_seen": 813937728, "step": 19765, "train_runtime": 76171.1714, "train_tokens_per_second": 10685.64 }, { "epoch": 1.3311338540263937, "grad_norm": 0.7162374087129196, "learning_rate": 2.515434087204996e-06, "loss": 0.2912620544433594, "num_input_tokens_seen": 814156400, "step": 19770, "train_runtime": 76190.417, "train_tokens_per_second": 10685.811 }, { "epoch": 1.331470509022354, "grad_norm": 0.6545524225908329, "learning_rate": 2.51313989953405e-06, "loss": 0.30854291915893556, "num_input_tokens_seen": 814369760, "step": 19775, "train_runtime": 76208.0163, "train_tokens_per_second": 10686.143 }, { "epoch": 1.331807164018314, "grad_norm": 0.69319799353421, "learning_rate": 2.510846407305603e-06, "loss": 0.2988208532333374, "num_input_tokens_seen": 814576976, "step": 19780, "train_runtime": 76227.2967, "train_tokens_per_second": 10686.159 }, { "epoch": 1.332143819014274, "grad_norm": 0.6608328893394291, "learning_rate": 2.508553611161021e-06, "loss": 0.3079995632171631, "num_input_tokens_seen": 814786496, "step": 19785, "train_runtime": 76247.0533, "train_tokens_per_second": 10686.138 }, { "epoch": 1.3324804740102343, "grad_norm": 0.6724269567692617, "learning_rate": 2.5062615117414773e-06, "loss": 0.302402925491333, "num_input_tokens_seen": 815005728, "step": 19790, "train_runtime": 76266.6965, "train_tokens_per_second": 10686.26 }, { "epoch": 1.3328171290061945, "grad_norm": 0.7194386508074797, "learning_rate": 2.50397010968795e-06, "loss": 0.28492441177368166, "num_input_tokens_seen": 815208440, "step": 19795, "train_runtime": 76288.515, "train_tokens_per_second": 10685.861 }, { "epoch": 1.3331537840021546, "grad_norm": 0.723567846831908, "learning_rate": 2.501679405641222e-06, "loss": 0.32473695278167725, "num_input_tokens_seen": 815416480, "step": 19800, "train_runtime": 76306.826, "train_tokens_per_second": 10686.023 }, { "epoch": 1.3334904389981148, "grad_norm": 0.7455935472638895, "learning_rate": 2.499389400241881e-06, "loss": 0.3100839853286743, "num_input_tokens_seen": 815608280, "step": 19805, "train_runtime": 76325.1339, "train_tokens_per_second": 10685.972 }, { "epoch": 1.3338270939940748, "grad_norm": 0.709212659653101, "learning_rate": 2.497100094130321e-06, "loss": 0.26926250457763673, "num_input_tokens_seen": 815813592, "step": 19810, "train_runtime": 76344.7159, "train_tokens_per_second": 10685.921 }, { "epoch": 1.334163748990035, "grad_norm": 0.6609642518611751, "learning_rate": 2.494811487946737e-06, "loss": 0.2922847270965576, "num_input_tokens_seen": 816023480, "step": 19815, "train_runtime": 76363.2111, "train_tokens_per_second": 10686.081 }, { "epoch": 1.3345004039859951, "grad_norm": 0.70021393632862, "learning_rate": 2.492523582331135e-06, "loss": 0.30788087844848633, "num_input_tokens_seen": 816232144, "step": 19820, "train_runtime": 76382.9487, "train_tokens_per_second": 10686.052 }, { "epoch": 1.3348370589819554, "grad_norm": 0.8223532947928568, "learning_rate": 2.4902363779233134e-06, "loss": 0.298014235496521, "num_input_tokens_seen": 816439896, "step": 19825, "train_runtime": 76402.4565, "train_tokens_per_second": 10686.042 }, { "epoch": 1.3351737139779154, "grad_norm": 0.706645397650051, "learning_rate": 2.4879498753628885e-06, "loss": 0.3055229902267456, "num_input_tokens_seen": 816628704, "step": 19830, "train_runtime": 76421.5115, "train_tokens_per_second": 10685.849 }, { "epoch": 1.3355103689738757, "grad_norm": 0.6251508440830215, "learning_rate": 2.4856640752892702e-06, "loss": 0.27330722808837893, "num_input_tokens_seen": 816840920, "step": 19835, "train_runtime": 76439.4488, "train_tokens_per_second": 10686.117 }, { "epoch": 1.3358470239698357, "grad_norm": 0.711183068363569, "learning_rate": 2.4833789783416757e-06, "loss": 0.2836280345916748, "num_input_tokens_seen": 817049136, "step": 19840, "train_runtime": 76458.9606, "train_tokens_per_second": 10686.114 }, { "epoch": 1.336183678965796, "grad_norm": 0.7638858433365643, "learning_rate": 2.4810945851591245e-06, "loss": 0.31646504402160647, "num_input_tokens_seen": 817245272, "step": 19845, "train_runtime": 76478.4794, "train_tokens_per_second": 10685.951 }, { "epoch": 1.336520333961756, "grad_norm": 0.7232455014814079, "learning_rate": 2.4788108963804406e-06, "loss": 0.29510633945465087, "num_input_tokens_seen": 817452560, "step": 19850, "train_runtime": 76497.6401, "train_tokens_per_second": 10685.984 }, { "epoch": 1.3368569889577162, "grad_norm": 0.69593195218333, "learning_rate": 2.4765279126442502e-06, "loss": 0.30003962516784666, "num_input_tokens_seen": 817662256, "step": 19855, "train_runtime": 76516.9178, "train_tokens_per_second": 10686.032 }, { "epoch": 1.3371936439536762, "grad_norm": 0.7275640611433607, "learning_rate": 2.4742456345889828e-06, "loss": 0.3052230358123779, "num_input_tokens_seen": 817862272, "step": 19860, "train_runtime": 76535.5485, "train_tokens_per_second": 10686.044 }, { "epoch": 1.3375302989496365, "grad_norm": 0.8041736214043609, "learning_rate": 2.471964062852867e-06, "loss": 0.3094948291778564, "num_input_tokens_seen": 818069696, "step": 19865, "train_runtime": 76553.8658, "train_tokens_per_second": 10686.197 }, { "epoch": 1.3378669539455965, "grad_norm": 0.7053358300270819, "learning_rate": 2.469683198073943e-06, "loss": 0.29259023666381834, "num_input_tokens_seen": 818281304, "step": 19870, "train_runtime": 76571.6008, "train_tokens_per_second": 10686.486 }, { "epoch": 1.3382036089415568, "grad_norm": 0.8995308421846056, "learning_rate": 2.4674030408900414e-06, "loss": 0.2892108678817749, "num_input_tokens_seen": 818461888, "step": 19875, "train_runtime": 76590.6972, "train_tokens_per_second": 10686.179 }, { "epoch": 1.3385402639375168, "grad_norm": 0.760644296623004, "learning_rate": 2.465123591938805e-06, "loss": 0.3108653545379639, "num_input_tokens_seen": 818664832, "step": 19880, "train_runtime": 76610.0547, "train_tokens_per_second": 10686.128 }, { "epoch": 1.338876918933477, "grad_norm": 0.684917096997088, "learning_rate": 2.462844851857673e-06, "loss": 0.31890091896057127, "num_input_tokens_seen": 818863840, "step": 19885, "train_runtime": 76630.149, "train_tokens_per_second": 10685.923 }, { "epoch": 1.339213573929437, "grad_norm": 0.7315279292114989, "learning_rate": 2.4605668212838878e-06, "loss": 0.31229190826416015, "num_input_tokens_seen": 819066512, "step": 19890, "train_runtime": 76648.7784, "train_tokens_per_second": 10685.97 }, { "epoch": 1.3395502289253973, "grad_norm": 0.7697760166739156, "learning_rate": 2.458289500854493e-06, "loss": 0.35078270435333253, "num_input_tokens_seen": 819272640, "step": 19895, "train_runtime": 76668.0081, "train_tokens_per_second": 10685.978 }, { "epoch": 1.3398868839213574, "grad_norm": 0.6816496795179391, "learning_rate": 2.4560128912063353e-06, "loss": 0.3130338191986084, "num_input_tokens_seen": 819470040, "step": 19900, "train_runtime": 76689.1656, "train_tokens_per_second": 10685.604 }, { "epoch": 1.3402235389173176, "grad_norm": 0.7343262493783116, "learning_rate": 2.4537369929760596e-06, "loss": 0.3394294500350952, "num_input_tokens_seen": 819686912, "step": 19905, "train_runtime": 76709.2263, "train_tokens_per_second": 10685.637 }, { "epoch": 1.3405601939132776, "grad_norm": 0.7149215850260147, "learning_rate": 2.4514618068001144e-06, "loss": 0.3044985294342041, "num_input_tokens_seen": 819889208, "step": 19910, "train_runtime": 76729.4879, "train_tokens_per_second": 10685.451 }, { "epoch": 1.3408968489092379, "grad_norm": 0.7258818251412789, "learning_rate": 2.4491873333147463e-06, "loss": 0.29542908668518064, "num_input_tokens_seen": 820093176, "step": 19915, "train_runtime": 76748.1678, "train_tokens_per_second": 10685.508 }, { "epoch": 1.341233503905198, "grad_norm": 0.7747363977694584, "learning_rate": 2.4469135731560106e-06, "loss": 0.27081568241119386, "num_input_tokens_seen": 820292024, "step": 19920, "train_runtime": 76767.4383, "train_tokens_per_second": 10685.416 }, { "epoch": 1.3415701589011582, "grad_norm": 0.7386282924266162, "learning_rate": 2.4446405269597494e-06, "loss": 0.3103013515472412, "num_input_tokens_seen": 820508216, "step": 19925, "train_runtime": 76788.3285, "train_tokens_per_second": 10685.325 }, { "epoch": 1.3419068138971182, "grad_norm": 0.7153916530960042, "learning_rate": 2.442368195361618e-06, "loss": 0.27449908256530764, "num_input_tokens_seen": 820717376, "step": 19930, "train_runtime": 76807.784, "train_tokens_per_second": 10685.341 }, { "epoch": 1.3422434688930784, "grad_norm": 0.7340299027674297, "learning_rate": 2.4400965789970647e-06, "loss": 0.28477504253387453, "num_input_tokens_seen": 820915144, "step": 19935, "train_runtime": 76825.9989, "train_tokens_per_second": 10685.382 }, { "epoch": 1.3425801238890385, "grad_norm": 0.7328818524540023, "learning_rate": 2.437825678501339e-06, "loss": 0.31703546047210696, "num_input_tokens_seen": 821125736, "step": 19940, "train_runtime": 76845.2023, "train_tokens_per_second": 10685.452 }, { "epoch": 1.3429167788849987, "grad_norm": 0.6471892826662303, "learning_rate": 2.4355554945094956e-06, "loss": 0.3017308712005615, "num_input_tokens_seen": 821332200, "step": 19945, "train_runtime": 76864.4996, "train_tokens_per_second": 10685.456 }, { "epoch": 1.3432534338809587, "grad_norm": 0.7198704606306119, "learning_rate": 2.4332860276563763e-06, "loss": 0.2966472148895264, "num_input_tokens_seen": 821541704, "step": 19950, "train_runtime": 76884.1556, "train_tokens_per_second": 10685.449 }, { "epoch": 1.343590088876919, "grad_norm": 0.6469072344244422, "learning_rate": 2.4310172785766396e-06, "loss": 0.3131601810455322, "num_input_tokens_seen": 821747624, "step": 19955, "train_runtime": 76903.0021, "train_tokens_per_second": 10685.508 }, { "epoch": 1.343926743872879, "grad_norm": 0.8528315295839737, "learning_rate": 2.428749247904724e-06, "loss": 0.32141642570495604, "num_input_tokens_seen": 821951536, "step": 19960, "train_runtime": 76922.764, "train_tokens_per_second": 10685.413 }, { "epoch": 1.3442633988688393, "grad_norm": 0.7724318778317252, "learning_rate": 2.4264819362748856e-06, "loss": 0.31084494590759276, "num_input_tokens_seen": 822157456, "step": 19965, "train_runtime": 76941.3462, "train_tokens_per_second": 10685.509 }, { "epoch": 1.3446000538647993, "grad_norm": 0.8056976090630581, "learning_rate": 2.4242153443211663e-06, "loss": 0.32831783294677735, "num_input_tokens_seen": 822364544, "step": 19970, "train_runtime": 76959.7415, "train_tokens_per_second": 10685.646 }, { "epoch": 1.3449367088607596, "grad_norm": 0.6688559963967015, "learning_rate": 2.4219494726774124e-06, "loss": 0.29214751720428467, "num_input_tokens_seen": 822573256, "step": 19975, "train_runtime": 76978.9953, "train_tokens_per_second": 10685.684 }, { "epoch": 1.3452733638567196, "grad_norm": 0.7024072347422412, "learning_rate": 2.419684321977268e-06, "loss": 0.2920111656188965, "num_input_tokens_seen": 822769664, "step": 19980, "train_runtime": 76998.0232, "train_tokens_per_second": 10685.595 }, { "epoch": 1.3456100188526798, "grad_norm": 0.6548290719225459, "learning_rate": 2.417419892854175e-06, "loss": 0.29374303817749026, "num_input_tokens_seen": 822986624, "step": 19985, "train_runtime": 77018.5934, "train_tokens_per_second": 10685.558 }, { "epoch": 1.3459466738486399, "grad_norm": 0.8299431859697863, "learning_rate": 2.415156185941371e-06, "loss": 0.29914419651031493, "num_input_tokens_seen": 823184608, "step": 19990, "train_runtime": 77037.7168, "train_tokens_per_second": 10685.475 }, { "epoch": 1.3462833288446001, "grad_norm": 0.7696993350478196, "learning_rate": 2.412893201871902e-06, "loss": 0.3059276580810547, "num_input_tokens_seen": 823388064, "step": 19995, "train_runtime": 77056.8104, "train_tokens_per_second": 10685.468 }, { "epoch": 1.3466199838405601, "grad_norm": 0.7745605595530632, "learning_rate": 2.410630941278595e-06, "loss": 0.3202518463134766, "num_input_tokens_seen": 823597400, "step": 20000, "train_runtime": 77078.737, "train_tokens_per_second": 10685.144 }, { "epoch": 1.3469566388365204, "grad_norm": 0.815930752451879, "learning_rate": 2.408369404794092e-06, "loss": 0.31179656982421877, "num_input_tokens_seen": 823799120, "step": 20005, "train_runtime": 77096.6888, "train_tokens_per_second": 10685.272 }, { "epoch": 1.3472932938324804, "grad_norm": 0.6872347049715269, "learning_rate": 2.4061085930508176e-06, "loss": 0.3054495811462402, "num_input_tokens_seen": 824001296, "step": 20010, "train_runtime": 77115.0322, "train_tokens_per_second": 10685.352 }, { "epoch": 1.3476299488284407, "grad_norm": 0.7505962037589791, "learning_rate": 2.4038485066810058e-06, "loss": 0.3064106941223145, "num_input_tokens_seen": 824202616, "step": 20015, "train_runtime": 77135.3268, "train_tokens_per_second": 10685.151 }, { "epoch": 1.3479666038244007, "grad_norm": 0.7288213630932091, "learning_rate": 2.40158914631668e-06, "loss": 0.27460541725158694, "num_input_tokens_seen": 824400272, "step": 20020, "train_runtime": 77153.722, "train_tokens_per_second": 10685.165 }, { "epoch": 1.348303258820361, "grad_norm": 0.7036454977850037, "learning_rate": 2.399330512589664e-06, "loss": 0.29352855682373047, "num_input_tokens_seen": 824611120, "step": 20025, "train_runtime": 77173.1545, "train_tokens_per_second": 10685.207 }, { "epoch": 1.348639913816321, "grad_norm": 0.68255187976437, "learning_rate": 2.3970726061315775e-06, "loss": 0.3035129070281982, "num_input_tokens_seen": 824819296, "step": 20030, "train_runtime": 77192.4776, "train_tokens_per_second": 10685.229 }, { "epoch": 1.3489765688122812, "grad_norm": 0.6854337180733676, "learning_rate": 2.394815427573836e-06, "loss": 0.2968101978302002, "num_input_tokens_seen": 825035968, "step": 20035, "train_runtime": 77213.3922, "train_tokens_per_second": 10685.141 }, { "epoch": 1.3493132238082413, "grad_norm": 0.6840873082604749, "learning_rate": 2.3925589775476516e-06, "loss": 0.29289219379425047, "num_input_tokens_seen": 825235040, "step": 20040, "train_runtime": 77231.9594, "train_tokens_per_second": 10685.15 }, { "epoch": 1.3496498788042015, "grad_norm": 0.6702703060634786, "learning_rate": 2.3903032566840377e-06, "loss": 0.309478235244751, "num_input_tokens_seen": 825445592, "step": 20045, "train_runtime": 77252.9562, "train_tokens_per_second": 10684.971 }, { "epoch": 1.3499865338001615, "grad_norm": 0.676980597693415, "learning_rate": 2.3880482656137926e-06, "loss": 0.3124652862548828, "num_input_tokens_seen": 825663160, "step": 20050, "train_runtime": 77271.5461, "train_tokens_per_second": 10685.216 }, { "epoch": 1.3503231887961218, "grad_norm": 0.7244607931525839, "learning_rate": 2.3857940049675254e-06, "loss": 0.3048631906509399, "num_input_tokens_seen": 825874472, "step": 20055, "train_runtime": 77291.4593, "train_tokens_per_second": 10685.197 }, { "epoch": 1.3506598437920818, "grad_norm": 0.7076576063089821, "learning_rate": 2.383540475375625e-06, "loss": 0.29305238723754884, "num_input_tokens_seen": 826082728, "step": 20060, "train_runtime": 77310.5095, "train_tokens_per_second": 10685.258 }, { "epoch": 1.350996498788042, "grad_norm": 0.746219927313328, "learning_rate": 2.3812876774682886e-06, "loss": 0.30280604362487795, "num_input_tokens_seen": 826298680, "step": 20065, "train_runtime": 77329.1255, "train_tokens_per_second": 10685.478 }, { "epoch": 1.351333153784002, "grad_norm": 0.712595429006528, "learning_rate": 2.379035611875503e-06, "loss": 0.33251161575317384, "num_input_tokens_seen": 826513392, "step": 20070, "train_runtime": 77347.5277, "train_tokens_per_second": 10685.712 }, { "epoch": 1.3516698087799623, "grad_norm": 0.6806367861665186, "learning_rate": 2.376784279227051e-06, "loss": 0.2987000226974487, "num_input_tokens_seen": 826731672, "step": 20075, "train_runtime": 77366.4409, "train_tokens_per_second": 10685.921 }, { "epoch": 1.3520064637759224, "grad_norm": 0.6709921030872564, "learning_rate": 2.3745336801525105e-06, "loss": 0.2940009117126465, "num_input_tokens_seen": 826950472, "step": 20080, "train_runtime": 77386.3086, "train_tokens_per_second": 10686.005 }, { "epoch": 1.3523431187718826, "grad_norm": 0.7230575022171285, "learning_rate": 2.3722838152812543e-06, "loss": 0.31799750328063964, "num_input_tokens_seen": 827160848, "step": 20085, "train_runtime": 77407.5771, "train_tokens_per_second": 10685.787 }, { "epoch": 1.3526797737678427, "grad_norm": 0.5885137842658297, "learning_rate": 2.3700346852424485e-06, "loss": 0.2971769332885742, "num_input_tokens_seen": 827363752, "step": 20090, "train_runtime": 77425.8992, "train_tokens_per_second": 10685.879 }, { "epoch": 1.353016428763803, "grad_norm": 0.7832347026466298, "learning_rate": 2.3677862906650594e-06, "loss": 0.3253528118133545, "num_input_tokens_seen": 827565192, "step": 20095, "train_runtime": 77444.8272, "train_tokens_per_second": 10685.868 }, { "epoch": 1.353353083759763, "grad_norm": 0.844179010968188, "learning_rate": 2.365538632177837e-06, "loss": 0.33354458808898924, "num_input_tokens_seen": 827760056, "step": 20100, "train_runtime": 77463.4527, "train_tokens_per_second": 10685.814 }, { "epoch": 1.3536897387557232, "grad_norm": 0.7298300649968212, "learning_rate": 2.36329171040934e-06, "loss": 0.30390305519104005, "num_input_tokens_seen": 827971920, "step": 20105, "train_runtime": 77481.571, "train_tokens_per_second": 10686.05 }, { "epoch": 1.3540263937516832, "grad_norm": 0.7087560456085591, "learning_rate": 2.3610455259879045e-06, "loss": 0.2872833490371704, "num_input_tokens_seen": 828170560, "step": 20110, "train_runtime": 77500.9609, "train_tokens_per_second": 10685.939 }, { "epoch": 1.3543630487476435, "grad_norm": 0.778709642697149, "learning_rate": 2.358800079541674e-06, "loss": 0.3201912879943848, "num_input_tokens_seen": 828371864, "step": 20115, "train_runtime": 77519.302, "train_tokens_per_second": 10686.008 }, { "epoch": 1.3546997037436035, "grad_norm": 0.7680606413493818, "learning_rate": 2.3565553716985794e-06, "loss": 0.3251060962677002, "num_input_tokens_seen": 828580528, "step": 20120, "train_runtime": 77538.21, "train_tokens_per_second": 10686.093 }, { "epoch": 1.3550363587395637, "grad_norm": 0.7868223204972916, "learning_rate": 2.3543114030863457e-06, "loss": 0.2893475770950317, "num_input_tokens_seen": 828772088, "step": 20125, "train_runtime": 77557.4207, "train_tokens_per_second": 10685.916 }, { "epoch": 1.3553730137355238, "grad_norm": 0.7358019391065641, "learning_rate": 2.352068174332491e-06, "loss": 0.2885709285736084, "num_input_tokens_seen": 828966984, "step": 20130, "train_runtime": 77576.5113, "train_tokens_per_second": 10685.799 }, { "epoch": 1.355709668731484, "grad_norm": 0.6484911699309394, "learning_rate": 2.349825686064329e-06, "loss": 0.26274847984313965, "num_input_tokens_seen": 829172096, "step": 20135, "train_runtime": 77595.6501, "train_tokens_per_second": 10685.806 }, { "epoch": 1.356046323727444, "grad_norm": 0.6973834528987821, "learning_rate": 2.3475839389089605e-06, "loss": 0.32182488441467283, "num_input_tokens_seen": 829387184, "step": 20140, "train_runtime": 77614.217, "train_tokens_per_second": 10686.021 }, { "epoch": 1.3563829787234043, "grad_norm": 0.7285139555322118, "learning_rate": 2.345342933493289e-06, "loss": 0.3054229736328125, "num_input_tokens_seen": 829588632, "step": 20145, "train_runtime": 77634.1645, "train_tokens_per_second": 10685.871 }, { "epoch": 1.3567196337193643, "grad_norm": 0.6531593643616053, "learning_rate": 2.343102670443998e-06, "loss": 0.29865872859954834, "num_input_tokens_seen": 829793744, "step": 20150, "train_runtime": 77654.1004, "train_tokens_per_second": 10685.769 }, { "epoch": 1.3570562887153246, "grad_norm": 0.7390304083504412, "learning_rate": 2.3408631503875763e-06, "loss": 0.32306418418884275, "num_input_tokens_seen": 830011928, "step": 20155, "train_runtime": 77674.735, "train_tokens_per_second": 10685.739 }, { "epoch": 1.3573929437112846, "grad_norm": 0.8453257559097663, "learning_rate": 2.338624373950291e-06, "loss": 0.2635021448135376, "num_input_tokens_seen": 830215280, "step": 20160, "train_runtime": 77693.1139, "train_tokens_per_second": 10685.828 }, { "epoch": 1.3577295987072449, "grad_norm": 0.7563804523627116, "learning_rate": 2.336386341758216e-06, "loss": 0.3052072286605835, "num_input_tokens_seen": 830434448, "step": 20165, "train_runtime": 77713.3988, "train_tokens_per_second": 10685.859 }, { "epoch": 1.3580662537032049, "grad_norm": 0.7893703465108801, "learning_rate": 2.3341490544372063e-06, "loss": 0.3095747709274292, "num_input_tokens_seen": 830640424, "step": 20170, "train_runtime": 77733.506, "train_tokens_per_second": 10685.745 }, { "epoch": 1.3584029086991651, "grad_norm": 0.6786208215235874, "learning_rate": 2.3319125126129128e-06, "loss": 0.31030979156494143, "num_input_tokens_seen": 830848176, "step": 20175, "train_runtime": 77753.6089, "train_tokens_per_second": 10685.654 }, { "epoch": 1.3587395636951252, "grad_norm": 0.731111790753842, "learning_rate": 2.329676716910777e-06, "loss": 0.32668285369873046, "num_input_tokens_seen": 831052552, "step": 20180, "train_runtime": 77773.6007, "train_tokens_per_second": 10685.535 }, { "epoch": 1.3590762186910854, "grad_norm": 0.7695395935606896, "learning_rate": 2.3274416679560325e-06, "loss": 0.31777215003967285, "num_input_tokens_seen": 831258584, "step": 20185, "train_runtime": 77792.3599, "train_tokens_per_second": 10685.607 }, { "epoch": 1.3594128736870454, "grad_norm": 0.7733122265908291, "learning_rate": 2.3252073663737016e-06, "loss": 0.3188926696777344, "num_input_tokens_seen": 831473112, "step": 20190, "train_runtime": 77811.0141, "train_tokens_per_second": 10685.802 }, { "epoch": 1.3597495286830057, "grad_norm": 0.8378790757268205, "learning_rate": 2.3229738127886054e-06, "loss": 0.31621718406677246, "num_input_tokens_seen": 831669856, "step": 20195, "train_runtime": 77831.7129, "train_tokens_per_second": 10685.488 }, { "epoch": 1.3600861836789657, "grad_norm": 0.6275906547273326, "learning_rate": 2.3207410078253416e-06, "loss": 0.3060434103012085, "num_input_tokens_seen": 831882736, "step": 20200, "train_runtime": 77853.2213, "train_tokens_per_second": 10685.271 }, { "epoch": 1.360422838674926, "grad_norm": 0.7009157500756139, "learning_rate": 2.3185089521083154e-06, "loss": 0.30642774105072024, "num_input_tokens_seen": 832084200, "step": 20205, "train_runtime": 77872.9864, "train_tokens_per_second": 10685.146 }, { "epoch": 1.360759493670886, "grad_norm": 0.7417533458397264, "learning_rate": 2.3162776462617067e-06, "loss": 0.3019516944885254, "num_input_tokens_seen": 832289040, "step": 20210, "train_runtime": 77891.7202, "train_tokens_per_second": 10685.206 }, { "epoch": 1.3610961486668463, "grad_norm": 0.7865691296725138, "learning_rate": 2.314047090909498e-06, "loss": 0.29076309204101564, "num_input_tokens_seen": 832493744, "step": 20215, "train_runtime": 77910.7631, "train_tokens_per_second": 10685.221 }, { "epoch": 1.3614328036628063, "grad_norm": 0.6956204355664014, "learning_rate": 2.3118172866754557e-06, "loss": 0.2857412338256836, "num_input_tokens_seen": 832700888, "step": 20220, "train_runtime": 77931.6045, "train_tokens_per_second": 10685.022 }, { "epoch": 1.3617694586587665, "grad_norm": 0.791207572183273, "learning_rate": 2.309588234183137e-06, "loss": 0.30385432243347166, "num_input_tokens_seen": 832914432, "step": 20225, "train_runtime": 77952.0307, "train_tokens_per_second": 10684.961 }, { "epoch": 1.3621061136547266, "grad_norm": 0.7352546928220974, "learning_rate": 2.3073599340558896e-06, "loss": 0.3206615924835205, "num_input_tokens_seen": 833110176, "step": 20230, "train_runtime": 77970.8382, "train_tokens_per_second": 10684.894 }, { "epoch": 1.3624427686506868, "grad_norm": 0.7304292749641844, "learning_rate": 2.3051323869168506e-06, "loss": 0.31322741508483887, "num_input_tokens_seen": 833324296, "step": 20235, "train_runtime": 77989.0129, "train_tokens_per_second": 10685.15 }, { "epoch": 1.3627794236466468, "grad_norm": 0.6589418081019561, "learning_rate": 2.3029055933889443e-06, "loss": 0.2978940486907959, "num_input_tokens_seen": 833525392, "step": 20240, "train_runtime": 78009.0751, "train_tokens_per_second": 10684.98 }, { "epoch": 1.363116078642607, "grad_norm": 0.6698513305373865, "learning_rate": 2.300679554094892e-06, "loss": 0.2712245941162109, "num_input_tokens_seen": 833722256, "step": 20245, "train_runtime": 78027.7315, "train_tokens_per_second": 10684.948 }, { "epoch": 1.3634527336385671, "grad_norm": 0.6972870995857722, "learning_rate": 2.298454269657191e-06, "loss": 0.2997845888137817, "num_input_tokens_seen": 833932008, "step": 20250, "train_runtime": 78047.1357, "train_tokens_per_second": 10684.979 }, { "epoch": 1.3637893886345274, "grad_norm": 0.6927451073576892, "learning_rate": 2.2962297406981432e-06, "loss": 0.3018352031707764, "num_input_tokens_seen": 834139920, "step": 20255, "train_runtime": 78067.8562, "train_tokens_per_second": 10684.806 }, { "epoch": 1.3641260436304874, "grad_norm": 0.7013367674077936, "learning_rate": 2.2940059678398223e-06, "loss": 0.3021678447723389, "num_input_tokens_seen": 834344968, "step": 20260, "train_runtime": 78086.4196, "train_tokens_per_second": 10684.892 }, { "epoch": 1.3644626986264476, "grad_norm": 0.7392128817949877, "learning_rate": 2.291782951704106e-06, "loss": 0.2980006217956543, "num_input_tokens_seen": 834545784, "step": 20265, "train_runtime": 78104.9254, "train_tokens_per_second": 10684.932 }, { "epoch": 1.3647993536224077, "grad_norm": 0.764611009663866, "learning_rate": 2.289560692912651e-06, "loss": 0.3084030866622925, "num_input_tokens_seen": 834753760, "step": 20270, "train_runtime": 78124.7196, "train_tokens_per_second": 10684.886 }, { "epoch": 1.365136008618368, "grad_norm": 0.6767571211473812, "learning_rate": 2.287339192086906e-06, "loss": 0.3061953544616699, "num_input_tokens_seen": 834961872, "step": 20275, "train_runtime": 78144.2244, "train_tokens_per_second": 10684.883 }, { "epoch": 1.365472663614328, "grad_norm": 0.7389142456649078, "learning_rate": 2.2851184498481056e-06, "loss": 0.3053052186965942, "num_input_tokens_seen": 835163440, "step": 20280, "train_runtime": 78162.7168, "train_tokens_per_second": 10684.934 }, { "epoch": 1.3658093186102882, "grad_norm": 0.7657186631491212, "learning_rate": 2.2828984668172732e-06, "loss": 0.29406561851501467, "num_input_tokens_seen": 835361512, "step": 20285, "train_runtime": 78181.8383, "train_tokens_per_second": 10684.854 }, { "epoch": 1.3661459736062485, "grad_norm": 0.8281612309840714, "learning_rate": 2.2806792436152185e-06, "loss": 0.3113540172576904, "num_input_tokens_seen": 835565560, "step": 20290, "train_runtime": 78201.4899, "train_tokens_per_second": 10684.778 }, { "epoch": 1.3664826286022085, "grad_norm": 0.7374091414391607, "learning_rate": 2.2784607808625463e-06, "loss": 0.30615668296813964, "num_input_tokens_seen": 835767920, "step": 20295, "train_runtime": 78220.5202, "train_tokens_per_second": 10684.766 }, { "epoch": 1.3668192835981685, "grad_norm": 0.7546876813670225, "learning_rate": 2.276243079179634e-06, "loss": 0.3037422180175781, "num_input_tokens_seen": 835970488, "step": 20300, "train_runtime": 78238.4693, "train_tokens_per_second": 10684.903 }, { "epoch": 1.3671559385941288, "grad_norm": 0.7702360611219538, "learning_rate": 2.2740261391866634e-06, "loss": 0.3198751211166382, "num_input_tokens_seen": 836176200, "step": 20305, "train_runtime": 78256.5908, "train_tokens_per_second": 10685.058 }, { "epoch": 1.367492593590089, "grad_norm": 0.706897022012345, "learning_rate": 2.2718099615035865e-06, "loss": 0.2623456001281738, "num_input_tokens_seen": 836382744, "step": 20310, "train_runtime": 78275.5768, "train_tokens_per_second": 10685.105 }, { "epoch": 1.367829248586049, "grad_norm": 0.6800433875840796, "learning_rate": 2.2695945467501567e-06, "loss": 0.31324989795684816, "num_input_tokens_seen": 836592608, "step": 20315, "train_runtime": 78294.5468, "train_tokens_per_second": 10685.196 }, { "epoch": 1.368165903582009, "grad_norm": 0.710722763694732, "learning_rate": 2.267379895545905e-06, "loss": 0.29290165901184084, "num_input_tokens_seen": 836799440, "step": 20320, "train_runtime": 78313.8159, "train_tokens_per_second": 10685.208 }, { "epoch": 1.3685025585779693, "grad_norm": 0.6623027313507553, "learning_rate": 2.2651660085101513e-06, "loss": 0.31116571426391604, "num_input_tokens_seen": 837010448, "step": 20325, "train_runtime": 78333.7431, "train_tokens_per_second": 10685.184 }, { "epoch": 1.3688392135739296, "grad_norm": 0.6924258034603445, "learning_rate": 2.262952886262003e-06, "loss": 0.30666542053222656, "num_input_tokens_seen": 837225640, "step": 20330, "train_runtime": 78353.6245, "train_tokens_per_second": 10685.219 }, { "epoch": 1.3691758685698896, "grad_norm": 0.6615882277916664, "learning_rate": 2.260740529420352e-06, "loss": 0.29550533294677733, "num_input_tokens_seen": 837433848, "step": 20335, "train_runtime": 78373.2473, "train_tokens_per_second": 10685.2 }, { "epoch": 1.3695125235658496, "grad_norm": 0.7652231925838775, "learning_rate": 2.2585289386038754e-06, "loss": 0.29401111602783203, "num_input_tokens_seen": 837651240, "step": 20340, "train_runtime": 78393.0287, "train_tokens_per_second": 10685.277 }, { "epoch": 1.3698491785618099, "grad_norm": 0.6778553451513544, "learning_rate": 2.256318114431043e-06, "loss": 0.33610494136810304, "num_input_tokens_seen": 837870352, "step": 20345, "train_runtime": 78411.7497, "train_tokens_per_second": 10685.52 }, { "epoch": 1.3701858335577701, "grad_norm": 0.7719853730588829, "learning_rate": 2.2541080575200973e-06, "loss": 0.2984076738357544, "num_input_tokens_seen": 838068464, "step": 20350, "train_runtime": 78431.884, "train_tokens_per_second": 10685.303 }, { "epoch": 1.3705224885537302, "grad_norm": 0.7507190975939341, "learning_rate": 2.251898768489081e-06, "loss": 0.3181284189224243, "num_input_tokens_seen": 838283520, "step": 20355, "train_runtime": 78450.8582, "train_tokens_per_second": 10685.46 }, { "epoch": 1.3708591435496902, "grad_norm": 0.73334672511216, "learning_rate": 2.249690247955807e-06, "loss": 0.3074968338012695, "num_input_tokens_seen": 838489424, "step": 20360, "train_runtime": 78472.3349, "train_tokens_per_second": 10685.16 }, { "epoch": 1.3711957985456504, "grad_norm": 0.702503969542685, "learning_rate": 2.247482496537887e-06, "loss": 0.3337711334228516, "num_input_tokens_seen": 838696400, "step": 20365, "train_runtime": 78490.4832, "train_tokens_per_second": 10685.326 }, { "epoch": 1.3715324535416107, "grad_norm": 1.6590966578311062, "learning_rate": 2.24527551485271e-06, "loss": 0.30984997749328613, "num_input_tokens_seen": 838901392, "step": 20370, "train_runtime": 78509.0197, "train_tokens_per_second": 10685.414 }, { "epoch": 1.3718691085375707, "grad_norm": 0.761267672464528, "learning_rate": 2.243069303517451e-06, "loss": 0.33157782554626464, "num_input_tokens_seen": 839102640, "step": 20375, "train_runtime": 78527.189, "train_tokens_per_second": 10685.505 }, { "epoch": 1.3722057635335307, "grad_norm": 0.6734458143616241, "learning_rate": 2.2408638631490696e-06, "loss": 0.28542351722717285, "num_input_tokens_seen": 839308048, "step": 20380, "train_runtime": 78545.2756, "train_tokens_per_second": 10685.659 }, { "epoch": 1.372542418529491, "grad_norm": 0.7164021467729109, "learning_rate": 2.2386591943643117e-06, "loss": 0.29254348278045655, "num_input_tokens_seen": 839520208, "step": 20385, "train_runtime": 78564.4034, "train_tokens_per_second": 10685.758 }, { "epoch": 1.3728790735254512, "grad_norm": 0.7225313747824709, "learning_rate": 2.2364552977797023e-06, "loss": 0.31540052890777587, "num_input_tokens_seen": 839728784, "step": 20390, "train_runtime": 78584.5473, "train_tokens_per_second": 10685.673 }, { "epoch": 1.3732157285214113, "grad_norm": 1.012861346375329, "learning_rate": 2.23425217401156e-06, "loss": 0.3178895950317383, "num_input_tokens_seen": 839934752, "step": 20395, "train_runtime": 78603.1324, "train_tokens_per_second": 10685.767 }, { "epoch": 1.3735523835173713, "grad_norm": 0.7209092033370676, "learning_rate": 2.2320498236759746e-06, "loss": 0.2969876527786255, "num_input_tokens_seen": 840141344, "step": 20400, "train_runtime": 78621.333, "train_tokens_per_second": 10685.921 }, { "epoch": 1.3738890385133316, "grad_norm": 0.7065403474225909, "learning_rate": 2.2298482473888335e-06, "loss": 0.3000949382781982, "num_input_tokens_seen": 840345464, "step": 20405, "train_runtime": 78639.7655, "train_tokens_per_second": 10686.012 }, { "epoch": 1.3742256935092918, "grad_norm": 0.7080164992053471, "learning_rate": 2.227647445765792e-06, "loss": 0.3068520545959473, "num_input_tokens_seen": 840557912, "step": 20410, "train_runtime": 78657.7487, "train_tokens_per_second": 10686.27 }, { "epoch": 1.3745623485052518, "grad_norm": 0.8148910021022556, "learning_rate": 2.225447419422305e-06, "loss": 0.2753275394439697, "num_input_tokens_seen": 840758744, "step": 20415, "train_runtime": 78676.9746, "train_tokens_per_second": 10686.211 }, { "epoch": 1.3748990035012119, "grad_norm": 0.7192579388539965, "learning_rate": 2.223248168973599e-06, "loss": 0.2927100658416748, "num_input_tokens_seen": 840965120, "step": 20420, "train_runtime": 78696.0493, "train_tokens_per_second": 10686.243 }, { "epoch": 1.375235658497172, "grad_norm": 0.7461105280149583, "learning_rate": 2.221049695034688e-06, "loss": 0.2898909091949463, "num_input_tokens_seen": 841175896, "step": 20425, "train_runtime": 78714.616, "train_tokens_per_second": 10686.4 }, { "epoch": 1.3755723134931324, "grad_norm": 0.7321797789171421, "learning_rate": 2.218851998220369e-06, "loss": 0.3086683750152588, "num_input_tokens_seen": 841383568, "step": 20430, "train_runtime": 78733.4231, "train_tokens_per_second": 10686.485 }, { "epoch": 1.3759089684890924, "grad_norm": 0.7074765337452339, "learning_rate": 2.21665507914522e-06, "loss": 0.286102294921875, "num_input_tokens_seen": 841573928, "step": 20435, "train_runtime": 78752.7427, "train_tokens_per_second": 10686.281 }, { "epoch": 1.3762456234850524, "grad_norm": 0.760683367599518, "learning_rate": 2.214458938423601e-06, "loss": 0.30880725383758545, "num_input_tokens_seen": 841785216, "step": 20440, "train_runtime": 78770.7008, "train_tokens_per_second": 10686.527 }, { "epoch": 1.3765822784810127, "grad_norm": 0.6487619258174294, "learning_rate": 2.212263576669661e-06, "loss": 0.2998666286468506, "num_input_tokens_seen": 841999976, "step": 20445, "train_runtime": 78789.2332, "train_tokens_per_second": 10686.739 }, { "epoch": 1.376918933476973, "grad_norm": 0.7494621686617973, "learning_rate": 2.2100689944973182e-06, "loss": 0.3160398483276367, "num_input_tokens_seen": 842214592, "step": 20450, "train_runtime": 78810.2057, "train_tokens_per_second": 10686.618 }, { "epoch": 1.377255588472933, "grad_norm": 0.7044610482989317, "learning_rate": 2.2078751925202886e-06, "loss": 0.3393260955810547, "num_input_tokens_seen": 842432400, "step": 20455, "train_runtime": 78830.792, "train_tokens_per_second": 10686.591 }, { "epoch": 1.377592243468893, "grad_norm": 0.7148369960425135, "learning_rate": 2.205682171352054e-06, "loss": 0.30718059539794923, "num_input_tokens_seen": 842641880, "step": 20460, "train_runtime": 78849.8417, "train_tokens_per_second": 10686.665 }, { "epoch": 1.3779288984648532, "grad_norm": 0.7788767019624421, "learning_rate": 2.2034899316058926e-06, "loss": 0.28958740234375, "num_input_tokens_seen": 842844240, "step": 20465, "train_runtime": 78870.0312, "train_tokens_per_second": 10686.496 }, { "epoch": 1.3782655534608135, "grad_norm": 0.7452375074578775, "learning_rate": 2.201298473894854e-06, "loss": 0.29304649829864504, "num_input_tokens_seen": 843037032, "step": 20470, "train_runtime": 78889.2795, "train_tokens_per_second": 10686.332 }, { "epoch": 1.3786022084567735, "grad_norm": 0.7048153730764788, "learning_rate": 2.1991077988317723e-06, "loss": 0.3015951633453369, "num_input_tokens_seen": 843253584, "step": 20475, "train_runtime": 78907.9081, "train_tokens_per_second": 10686.554 }, { "epoch": 1.3789388634527335, "grad_norm": 0.676291197791641, "learning_rate": 2.1969179070292637e-06, "loss": 0.2804278373718262, "num_input_tokens_seen": 843453616, "step": 20480, "train_runtime": 78927.3269, "train_tokens_per_second": 10686.459 }, { "epoch": 1.3792755184486938, "grad_norm": 0.7297147290367615, "learning_rate": 2.1947287990997236e-06, "loss": 0.30213940143585205, "num_input_tokens_seen": 843655800, "step": 20485, "train_runtime": 78945.0565, "train_tokens_per_second": 10686.62 }, { "epoch": 1.379612173444654, "grad_norm": 0.739418510668805, "learning_rate": 2.192540475655328e-06, "loss": 0.295147967338562, "num_input_tokens_seen": 843854872, "step": 20490, "train_runtime": 78964.2638, "train_tokens_per_second": 10686.541 }, { "epoch": 1.379948828440614, "grad_norm": 0.7240098975057945, "learning_rate": 2.1903529373080397e-06, "loss": 0.31889917850494387, "num_input_tokens_seen": 844062816, "step": 20495, "train_runtime": 78984.8707, "train_tokens_per_second": 10686.386 }, { "epoch": 1.380285483436574, "grad_norm": 0.7513676542350808, "learning_rate": 2.1881661846695895e-06, "loss": 0.27654845714569093, "num_input_tokens_seen": 844246784, "step": 20500, "train_runtime": 79002.362, "train_tokens_per_second": 10686.349 }, { "epoch": 1.3806221384325343, "grad_norm": 0.7970257947204336, "learning_rate": 2.185980218351503e-06, "loss": 0.3190426826477051, "num_input_tokens_seen": 844448080, "step": 20505, "train_runtime": 79021.4548, "train_tokens_per_second": 10686.314 }, { "epoch": 1.3809587934284946, "grad_norm": 0.7055359521478558, "learning_rate": 2.1837950389650714e-06, "loss": 0.30787272453308107, "num_input_tokens_seen": 844665392, "step": 20510, "train_runtime": 79041.2872, "train_tokens_per_second": 10686.382 }, { "epoch": 1.3812954484244546, "grad_norm": 0.6245638232766247, "learning_rate": 2.1816106471213787e-06, "loss": 0.30388765335083007, "num_input_tokens_seen": 844882440, "step": 20515, "train_runtime": 79061.8851, "train_tokens_per_second": 10686.343 }, { "epoch": 1.3816321034204146, "grad_norm": 0.7332892089989117, "learning_rate": 2.179427043431282e-06, "loss": 0.325454568862915, "num_input_tokens_seen": 845093016, "step": 20520, "train_runtime": 79080.3427, "train_tokens_per_second": 10686.512 }, { "epoch": 1.381968758416375, "grad_norm": 0.6972936559123032, "learning_rate": 2.177244228505418e-06, "loss": 0.3230432510375977, "num_input_tokens_seen": 845286168, "step": 20525, "train_runtime": 79098.8446, "train_tokens_per_second": 10686.454 }, { "epoch": 1.3823054134123351, "grad_norm": 0.9899059793112543, "learning_rate": 2.1750622029542047e-06, "loss": 0.29483129978179934, "num_input_tokens_seen": 845501776, "step": 20530, "train_runtime": 79116.6532, "train_tokens_per_second": 10686.774 }, { "epoch": 1.3826420684082952, "grad_norm": 0.7688707484478564, "learning_rate": 2.1728809673878374e-06, "loss": 0.3072760581970215, "num_input_tokens_seen": 845702936, "step": 20535, "train_runtime": 79136.3995, "train_tokens_per_second": 10686.649 }, { "epoch": 1.3829787234042552, "grad_norm": 0.7328836632299089, "learning_rate": 2.1707005224162915e-06, "loss": 0.2908041000366211, "num_input_tokens_seen": 845911720, "step": 20540, "train_runtime": 79155.0815, "train_tokens_per_second": 10686.765 }, { "epoch": 1.3833153784002155, "grad_norm": 0.7287857376070603, "learning_rate": 2.1685208686493257e-06, "loss": 0.3042143821716309, "num_input_tokens_seen": 846104504, "step": 20545, "train_runtime": 79174.6954, "train_tokens_per_second": 10686.552 }, { "epoch": 1.3836520333961757, "grad_norm": 0.7334119579612641, "learning_rate": 2.166342006696467e-06, "loss": 0.3157516956329346, "num_input_tokens_seen": 846304368, "step": 20550, "train_runtime": 79193.4401, "train_tokens_per_second": 10686.546 }, { "epoch": 1.3839886883921357, "grad_norm": 0.7785470069348824, "learning_rate": 2.1641639371670335e-06, "loss": 0.3060342788696289, "num_input_tokens_seen": 846506008, "step": 20555, "train_runtime": 79211.4853, "train_tokens_per_second": 10686.657 }, { "epoch": 1.3843253433880958, "grad_norm": 0.8050462708632421, "learning_rate": 2.161986660670109e-06, "loss": 0.3248995304107666, "num_input_tokens_seen": 846715760, "step": 20560, "train_runtime": 79229.3599, "train_tokens_per_second": 10686.894 }, { "epoch": 1.384661998384056, "grad_norm": 0.6256287041129834, "learning_rate": 2.159810177814566e-06, "loss": 0.29456558227539065, "num_input_tokens_seen": 846912880, "step": 20565, "train_runtime": 79247.9376, "train_tokens_per_second": 10686.876 }, { "epoch": 1.3849986533800163, "grad_norm": 0.6932268731484925, "learning_rate": 2.1576344892090507e-06, "loss": 0.31670451164245605, "num_input_tokens_seen": 847115760, "step": 20570, "train_runtime": 79268.4761, "train_tokens_per_second": 10686.666 }, { "epoch": 1.3853353083759763, "grad_norm": 0.6818819950437565, "learning_rate": 2.1554595954619866e-06, "loss": 0.3057210922241211, "num_input_tokens_seen": 847319504, "step": 20575, "train_runtime": 79288.0611, "train_tokens_per_second": 10686.596 }, { "epoch": 1.3856719633719363, "grad_norm": 0.7299223037724305, "learning_rate": 2.1532854971815763e-06, "loss": 0.30439534187316897, "num_input_tokens_seen": 847519760, "step": 20580, "train_runtime": 79306.8411, "train_tokens_per_second": 10686.591 }, { "epoch": 1.3860086183678966, "grad_norm": 0.6291754992994046, "learning_rate": 2.151112194975799e-06, "loss": 0.27935969829559326, "num_input_tokens_seen": 847731680, "step": 20585, "train_runtime": 79327.8346, "train_tokens_per_second": 10686.434 }, { "epoch": 1.3863452733638568, "grad_norm": 0.6482383838334026, "learning_rate": 2.1489396894524106e-06, "loss": 0.2869689464569092, "num_input_tokens_seen": 847947952, "step": 20590, "train_runtime": 79348.7543, "train_tokens_per_second": 10686.342 }, { "epoch": 1.3866819283598169, "grad_norm": 0.6270598516195882, "learning_rate": 2.1467679812189497e-06, "loss": 0.299603271484375, "num_input_tokens_seen": 848152512, "step": 20595, "train_runtime": 79368.9326, "train_tokens_per_second": 10686.203 }, { "epoch": 1.3870185833557769, "grad_norm": 0.8275917527800953, "learning_rate": 2.1445970708827213e-06, "loss": 0.3098380327224731, "num_input_tokens_seen": 848347424, "step": 20600, "train_runtime": 79388.4503, "train_tokens_per_second": 10686.031 }, { "epoch": 1.3873552383517371, "grad_norm": 0.6531440981692307, "learning_rate": 2.14242695905082e-06, "loss": 0.2890744209289551, "num_input_tokens_seen": 848554712, "step": 20605, "train_runtime": 79406.8484, "train_tokens_per_second": 10686.165 }, { "epoch": 1.3876918933476974, "grad_norm": 0.710839573786497, "learning_rate": 2.1402576463301044e-06, "loss": 0.3179774284362793, "num_input_tokens_seen": 848774200, "step": 20610, "train_runtime": 79427.5221, "train_tokens_per_second": 10686.147 }, { "epoch": 1.3880285483436574, "grad_norm": 0.8068758077339434, "learning_rate": 2.13808913332722e-06, "loss": 0.28652329444885255, "num_input_tokens_seen": 848977560, "step": 20615, "train_runtime": 79445.9101, "train_tokens_per_second": 10686.234 }, { "epoch": 1.3883652033396174, "grad_norm": 0.7781277248113416, "learning_rate": 2.1359214206485845e-06, "loss": 0.3224474430084229, "num_input_tokens_seen": 849180800, "step": 20620, "train_runtime": 79464.5215, "train_tokens_per_second": 10686.288 }, { "epoch": 1.3887018583355777, "grad_norm": 0.6713012159261257, "learning_rate": 2.1337545089003905e-06, "loss": 0.2632595062255859, "num_input_tokens_seen": 849370704, "step": 20625, "train_runtime": 79482.9005, "train_tokens_per_second": 10686.207 }, { "epoch": 1.389038513331538, "grad_norm": 0.745892337535167, "learning_rate": 2.131588398688608e-06, "loss": 0.3135321617126465, "num_input_tokens_seen": 849580016, "step": 20630, "train_runtime": 79502.9213, "train_tokens_per_second": 10686.148 }, { "epoch": 1.389375168327498, "grad_norm": 0.7242690641477679, "learning_rate": 2.1294230906189833e-06, "loss": 0.2851271152496338, "num_input_tokens_seen": 849778016, "step": 20635, "train_runtime": 79523.0258, "train_tokens_per_second": 10685.937 }, { "epoch": 1.389711823323458, "grad_norm": 0.7108192481578989, "learning_rate": 2.1272585852970358e-06, "loss": 0.2963099956512451, "num_input_tokens_seen": 849974104, "step": 20640, "train_runtime": 79542.257, "train_tokens_per_second": 10685.818 }, { "epoch": 1.3900484783194182, "grad_norm": 0.6877867676698313, "learning_rate": 2.125094883328068e-06, "loss": 0.29377820491790774, "num_input_tokens_seen": 850168976, "step": 20645, "train_runtime": 79561.0575, "train_tokens_per_second": 10685.743 }, { "epoch": 1.3903851333153785, "grad_norm": 0.7467984557447785, "learning_rate": 2.1229319853171447e-06, "loss": 0.27530360221862793, "num_input_tokens_seen": 850367552, "step": 20650, "train_runtime": 79578.6191, "train_tokens_per_second": 10685.88 }, { "epoch": 1.3907217883113385, "grad_norm": 0.7620710492063532, "learning_rate": 2.1207698918691217e-06, "loss": 0.3218740940093994, "num_input_tokens_seen": 850574848, "step": 20655, "train_runtime": 79598.3382, "train_tokens_per_second": 10685.837 }, { "epoch": 1.3910584433072986, "grad_norm": 0.744034818067787, "learning_rate": 2.1186086035886133e-06, "loss": 0.2905986785888672, "num_input_tokens_seen": 850787512, "step": 20660, "train_runtime": 79617.7205, "train_tokens_per_second": 10685.906 }, { "epoch": 1.3913950983032588, "grad_norm": 0.758061303986339, "learning_rate": 2.116448121080023e-06, "loss": 0.30747194290161134, "num_input_tokens_seen": 851011176, "step": 20665, "train_runtime": 79638.0199, "train_tokens_per_second": 10685.991 }, { "epoch": 1.391731753299219, "grad_norm": 0.7362926545948786, "learning_rate": 2.1142884449475205e-06, "loss": 0.31135079860687254, "num_input_tokens_seen": 851218176, "step": 20670, "train_runtime": 79657.7165, "train_tokens_per_second": 10685.947 }, { "epoch": 1.392068408295179, "grad_norm": 0.7451104482550001, "learning_rate": 2.112129575795052e-06, "loss": 0.2995465278625488, "num_input_tokens_seen": 851427520, "step": 20675, "train_runtime": 79677.2867, "train_tokens_per_second": 10685.95 }, { "epoch": 1.3924050632911391, "grad_norm": 0.6477017356838737, "learning_rate": 2.1099715142263394e-06, "loss": 0.27633204460144045, "num_input_tokens_seen": 851628112, "step": 20680, "train_runtime": 79695.8402, "train_tokens_per_second": 10685.979 }, { "epoch": 1.3927417182870994, "grad_norm": 0.6528688410584691, "learning_rate": 2.1078142608448773e-06, "loss": 0.2918430805206299, "num_input_tokens_seen": 851835032, "step": 20685, "train_runtime": 79714.5156, "train_tokens_per_second": 10686.072 }, { "epoch": 1.3930783732830596, "grad_norm": 0.7741407924247723, "learning_rate": 2.1056578162539327e-06, "loss": 0.32411346435546873, "num_input_tokens_seen": 852043080, "step": 20690, "train_runtime": 79733.2998, "train_tokens_per_second": 10686.164 }, { "epoch": 1.3934150282790196, "grad_norm": 0.7959221082078574, "learning_rate": 2.103502181056554e-06, "loss": 0.3075122833251953, "num_input_tokens_seen": 852248880, "step": 20695, "train_runtime": 79752.7569, "train_tokens_per_second": 10686.137 }, { "epoch": 1.3937516832749797, "grad_norm": 0.7100858048107336, "learning_rate": 2.1013473558555503e-06, "loss": 0.29110112190246584, "num_input_tokens_seen": 852470352, "step": 20700, "train_runtime": 79772.5709, "train_tokens_per_second": 10686.259 }, { "epoch": 1.39408833827094, "grad_norm": 0.7189269212428372, "learning_rate": 2.099193341253519e-06, "loss": 0.2940558195114136, "num_input_tokens_seen": 852666960, "step": 20705, "train_runtime": 79791.5821, "train_tokens_per_second": 10686.177 }, { "epoch": 1.3944249932669002, "grad_norm": 0.8689132273748869, "learning_rate": 2.0970401378528167e-06, "loss": 0.28880164623260496, "num_input_tokens_seen": 852861944, "step": 20710, "train_runtime": 79810.7017, "train_tokens_per_second": 10686.06 }, { "epoch": 1.3947616482628602, "grad_norm": 0.6504717249778569, "learning_rate": 2.0948877462555844e-06, "loss": 0.27566606998443605, "num_input_tokens_seen": 853072768, "step": 20715, "train_runtime": 79829.1668, "train_tokens_per_second": 10686.229 }, { "epoch": 1.3950983032588202, "grad_norm": 0.7108755270530404, "learning_rate": 2.09273616706373e-06, "loss": 0.3232423305511475, "num_input_tokens_seen": 853286688, "step": 20720, "train_runtime": 79848.0305, "train_tokens_per_second": 10686.384 }, { "epoch": 1.3954349582547805, "grad_norm": 0.72182216026974, "learning_rate": 2.090585400878936e-06, "loss": 0.318605899810791, "num_input_tokens_seen": 853495072, "step": 20725, "train_runtime": 79868.6663, "train_tokens_per_second": 10686.232 }, { "epoch": 1.3957716132507407, "grad_norm": 0.7508453600524202, "learning_rate": 2.0884354483026576e-06, "loss": 0.30780692100524903, "num_input_tokens_seen": 853702272, "step": 20730, "train_runtime": 79886.1745, "train_tokens_per_second": 10686.483 }, { "epoch": 1.3961082682467008, "grad_norm": 0.6796351896728681, "learning_rate": 2.0862863099361214e-06, "loss": 0.3085170745849609, "num_input_tokens_seen": 853919736, "step": 20735, "train_runtime": 79904.4731, "train_tokens_per_second": 10686.758 }, { "epoch": 1.3964449232426608, "grad_norm": 0.6869597918838389, "learning_rate": 2.084137986380326e-06, "loss": 0.31849007606506347, "num_input_tokens_seen": 854120240, "step": 20740, "train_runtime": 79925.8506, "train_tokens_per_second": 10686.408 }, { "epoch": 1.396781578238621, "grad_norm": 0.70151706201184, "learning_rate": 2.081990478236048e-06, "loss": 0.28432607650756836, "num_input_tokens_seen": 854310616, "step": 20745, "train_runtime": 79944.8667, "train_tokens_per_second": 10686.247 }, { "epoch": 1.3971182332345813, "grad_norm": 0.7447322885017874, "learning_rate": 2.079843786103824e-06, "loss": 0.29441099166870116, "num_input_tokens_seen": 854511824, "step": 20750, "train_runtime": 79966.0685, "train_tokens_per_second": 10685.93 }, { "epoch": 1.3974548882305413, "grad_norm": 0.806147258608507, "learning_rate": 2.0776979105839774e-06, "loss": 0.3101045608520508, "num_input_tokens_seen": 854725568, "step": 20755, "train_runtime": 79984.7827, "train_tokens_per_second": 10686.102 }, { "epoch": 1.3977915432265013, "grad_norm": 0.7936092435048668, "learning_rate": 2.075552852276588e-06, "loss": 0.3415255069732666, "num_input_tokens_seen": 854938432, "step": 20760, "train_runtime": 80004.3543, "train_tokens_per_second": 10686.149 }, { "epoch": 1.3981281982224616, "grad_norm": 0.7957949891478917, "learning_rate": 2.07340861178152e-06, "loss": 0.30536985397338867, "num_input_tokens_seen": 855143456, "step": 20765, "train_runtime": 80023.2991, "train_tokens_per_second": 10686.181 }, { "epoch": 1.3984648532184218, "grad_norm": 0.6951577724822595, "learning_rate": 2.0712651896984013e-06, "loss": 0.30127859115600586, "num_input_tokens_seen": 855355704, "step": 20770, "train_runtime": 80042.9161, "train_tokens_per_second": 10686.214 }, { "epoch": 1.3988015082143819, "grad_norm": 0.739514029630989, "learning_rate": 2.0691225866266335e-06, "loss": 0.301642918586731, "num_input_tokens_seen": 855554832, "step": 20775, "train_runtime": 80061.9896, "train_tokens_per_second": 10686.155 }, { "epoch": 1.3991381632103421, "grad_norm": 0.7959711288323958, "learning_rate": 2.066980803165388e-06, "loss": 0.31196250915527346, "num_input_tokens_seen": 855763280, "step": 20780, "train_runtime": 80079.982, "train_tokens_per_second": 10686.357 }, { "epoch": 1.3994748182063022, "grad_norm": 0.7562139796280422, "learning_rate": 2.0648398399136088e-06, "loss": 0.31349596977233884, "num_input_tokens_seen": 855976040, "step": 20785, "train_runtime": 80099.874, "train_tokens_per_second": 10686.359 }, { "epoch": 1.3998114732022624, "grad_norm": 0.6817996507856504, "learning_rate": 2.062699697470007e-06, "loss": 0.29534525871276857, "num_input_tokens_seen": 856177064, "step": 20790, "train_runtime": 80120.0111, "train_tokens_per_second": 10686.183 }, { "epoch": 1.4001481281982224, "grad_norm": 0.6845749732560631, "learning_rate": 2.060560376433072e-06, "loss": 0.3292046070098877, "num_input_tokens_seen": 856391512, "step": 20795, "train_runtime": 80138.9028, "train_tokens_per_second": 10686.339 }, { "epoch": 1.4004847831941827, "grad_norm": 0.703519799894669, "learning_rate": 2.05842187740105e-06, "loss": 0.30940086841583253, "num_input_tokens_seen": 856594568, "step": 20800, "train_runtime": 80158.5764, "train_tokens_per_second": 10686.25 }, { "epoch": 1.4008214381901427, "grad_norm": 0.7692162837678844, "learning_rate": 2.0562842009719745e-06, "loss": 0.2820030450820923, "num_input_tokens_seen": 856772784, "step": 20805, "train_runtime": 80178.0842, "train_tokens_per_second": 10685.872 }, { "epoch": 1.401158093186103, "grad_norm": 0.7135717709146094, "learning_rate": 2.0541473477436317e-06, "loss": 0.2863647699356079, "num_input_tokens_seen": 856978160, "step": 20810, "train_runtime": 80196.8228, "train_tokens_per_second": 10685.937 }, { "epoch": 1.401494748182063, "grad_norm": 0.765208537902179, "learning_rate": 2.052011318313591e-06, "loss": 0.2893018007278442, "num_input_tokens_seen": 857187952, "step": 20815, "train_runtime": 80215.5289, "train_tokens_per_second": 10686.06 }, { "epoch": 1.4018314031780232, "grad_norm": 0.6781264485754516, "learning_rate": 2.049876113279185e-06, "loss": 0.32324063777923584, "num_input_tokens_seen": 857396352, "step": 20820, "train_runtime": 80234.1045, "train_tokens_per_second": 10686.183 }, { "epoch": 1.4021680581739833, "grad_norm": 0.6542741085300953, "learning_rate": 2.0477417332375165e-06, "loss": 0.29372491836547854, "num_input_tokens_seen": 857609240, "step": 20825, "train_runtime": 80252.5246, "train_tokens_per_second": 10686.383 }, { "epoch": 1.4025047131699435, "grad_norm": 0.725091711531566, "learning_rate": 2.045608178785458e-06, "loss": 0.2963188886642456, "num_input_tokens_seen": 857819704, "step": 20830, "train_runtime": 80271.7808, "train_tokens_per_second": 10686.442 }, { "epoch": 1.4028413681659035, "grad_norm": 0.6788194938440237, "learning_rate": 2.043475450519652e-06, "loss": 0.2963943719863892, "num_input_tokens_seen": 858022120, "step": 20835, "train_runtime": 80289.9399, "train_tokens_per_second": 10686.546 }, { "epoch": 1.4031780231618638, "grad_norm": 0.7679679039294379, "learning_rate": 2.0413435490365064e-06, "loss": 0.31096491813659666, "num_input_tokens_seen": 858218504, "step": 20840, "train_runtime": 80308.3793, "train_tokens_per_second": 10686.537 }, { "epoch": 1.4035146781578238, "grad_norm": 0.7297450702202818, "learning_rate": 2.0392124749322064e-06, "loss": 0.32165989875793455, "num_input_tokens_seen": 858432344, "step": 20845, "train_runtime": 80328.156, "train_tokens_per_second": 10686.569 }, { "epoch": 1.403851333153784, "grad_norm": 0.7923324382607783, "learning_rate": 2.037082228802693e-06, "loss": 0.2877426385879517, "num_input_tokens_seen": 858638384, "step": 20850, "train_runtime": 80347.0217, "train_tokens_per_second": 10686.624 }, { "epoch": 1.404187988149744, "grad_norm": 0.6753084985972011, "learning_rate": 2.03495281124369e-06, "loss": 0.2810673713684082, "num_input_tokens_seen": 858842536, "step": 20855, "train_runtime": 80367.3634, "train_tokens_per_second": 10686.459 }, { "epoch": 1.4045246431457044, "grad_norm": 0.6767255068384999, "learning_rate": 2.0328242228506746e-06, "loss": 0.29042279720306396, "num_input_tokens_seen": 859045120, "step": 20860, "train_runtime": 80386.4102, "train_tokens_per_second": 10686.447 }, { "epoch": 1.4048612981416644, "grad_norm": 0.7973930606153136, "learning_rate": 2.0306964642189053e-06, "loss": 0.3045050621032715, "num_input_tokens_seen": 859249528, "step": 20865, "train_runtime": 80405.9151, "train_tokens_per_second": 10686.397 }, { "epoch": 1.4051979531376246, "grad_norm": 0.736027485648019, "learning_rate": 2.028569535943402e-06, "loss": 0.2937159061431885, "num_input_tokens_seen": 859447624, "step": 20870, "train_runtime": 80424.8572, "train_tokens_per_second": 10686.343 }, { "epoch": 1.4055346081335847, "grad_norm": 0.7432926635200493, "learning_rate": 2.0264434386189524e-06, "loss": 0.3045713186264038, "num_input_tokens_seen": 859650248, "step": 20875, "train_runtime": 80443.0364, "train_tokens_per_second": 10686.447 }, { "epoch": 1.405871263129545, "grad_norm": 0.6406890238216549, "learning_rate": 2.0243181728401136e-06, "loss": 0.29553585052490233, "num_input_tokens_seen": 859859496, "step": 20880, "train_runtime": 80462.6044, "train_tokens_per_second": 10686.449 }, { "epoch": 1.406207918125505, "grad_norm": 0.7766199886817882, "learning_rate": 2.022193739201208e-06, "loss": 0.3138155460357666, "num_input_tokens_seen": 860049440, "step": 20885, "train_runtime": 80481.3515, "train_tokens_per_second": 10686.32 }, { "epoch": 1.4065445731214652, "grad_norm": 0.681956314784868, "learning_rate": 2.0200701382963267e-06, "loss": 0.2813447952270508, "num_input_tokens_seen": 860254808, "step": 20890, "train_runtime": 80501.7635, "train_tokens_per_second": 10686.161 }, { "epoch": 1.4068812281174252, "grad_norm": 0.7467007077045494, "learning_rate": 2.0179473707193324e-06, "loss": 0.2992174863815308, "num_input_tokens_seen": 860467600, "step": 20895, "train_runtime": 80521.7559, "train_tokens_per_second": 10686.15 }, { "epoch": 1.4072178831133855, "grad_norm": 0.6605517476868309, "learning_rate": 2.0158254370638435e-06, "loss": 0.306179404258728, "num_input_tokens_seen": 860675552, "step": 20900, "train_runtime": 80541.0697, "train_tokens_per_second": 10686.17 }, { "epoch": 1.4075545381093455, "grad_norm": 0.634811927366343, "learning_rate": 2.0137043379232585e-06, "loss": 0.3021426200866699, "num_input_tokens_seen": 860887152, "step": 20905, "train_runtime": 80560.9438, "train_tokens_per_second": 10686.16 }, { "epoch": 1.4078911931053057, "grad_norm": 0.6776664198740187, "learning_rate": 2.0115840738907293e-06, "loss": 0.2960165739059448, "num_input_tokens_seen": 861082352, "step": 20910, "train_runtime": 80581.2764, "train_tokens_per_second": 10685.886 }, { "epoch": 1.4082278481012658, "grad_norm": 0.7584765965467849, "learning_rate": 2.0094646455591865e-06, "loss": 0.30627257823944093, "num_input_tokens_seen": 861293544, "step": 20915, "train_runtime": 80602.2529, "train_tokens_per_second": 10685.725 }, { "epoch": 1.408564503097226, "grad_norm": 0.6819450531196236, "learning_rate": 2.007346053521319e-06, "loss": 0.3175514698028564, "num_input_tokens_seen": 861501672, "step": 20920, "train_runtime": 80622.7011, "train_tokens_per_second": 10685.597 }, { "epoch": 1.408901158093186, "grad_norm": 0.7382508789331648, "learning_rate": 2.005228298369583e-06, "loss": 0.31633830070495605, "num_input_tokens_seen": 861694208, "step": 20925, "train_runtime": 80643.3286, "train_tokens_per_second": 10685.251 }, { "epoch": 1.4092378130891463, "grad_norm": 0.7026073207056484, "learning_rate": 2.003111380696208e-06, "loss": 0.28212366104125974, "num_input_tokens_seen": 861907448, "step": 20930, "train_runtime": 80662.2994, "train_tokens_per_second": 10685.382 }, { "epoch": 1.4095744680851063, "grad_norm": 0.7983865843119368, "learning_rate": 2.0009953010931747e-06, "loss": 0.2899780750274658, "num_input_tokens_seen": 862118272, "step": 20935, "train_runtime": 80684.0579, "train_tokens_per_second": 10685.113 }, { "epoch": 1.4099111230810666, "grad_norm": 0.7721205660032587, "learning_rate": 1.998880060152244e-06, "loss": 0.32182295322418214, "num_input_tokens_seen": 862329232, "step": 20940, "train_runtime": 80702.6808, "train_tokens_per_second": 10685.261 }, { "epoch": 1.4102477780770266, "grad_norm": 0.7381184656332012, "learning_rate": 1.9967656584649354e-06, "loss": 0.31608736515045166, "num_input_tokens_seen": 862534432, "step": 20945, "train_runtime": 80721.111, "train_tokens_per_second": 10685.364 }, { "epoch": 1.4105844330729869, "grad_norm": 0.674361124487375, "learning_rate": 1.994652096622533e-06, "loss": 0.32326231002807615, "num_input_tokens_seen": 862742088, "step": 20950, "train_runtime": 80740.806, "train_tokens_per_second": 10685.329 }, { "epoch": 1.410921088068947, "grad_norm": 0.6892820281677943, "learning_rate": 1.992539375216089e-06, "loss": 0.3158289909362793, "num_input_tokens_seen": 862954744, "step": 20955, "train_runtime": 80760.5744, "train_tokens_per_second": 10685.347 }, { "epoch": 1.4112577430649071, "grad_norm": 0.6812002655050665, "learning_rate": 1.9904274948364184e-06, "loss": 0.30939671993255613, "num_input_tokens_seen": 863165608, "step": 20960, "train_runtime": 80781.0255, "train_tokens_per_second": 10685.252 }, { "epoch": 1.4115943980608672, "grad_norm": 0.7679907334859916, "learning_rate": 1.988316456074102e-06, "loss": 0.31055517196655275, "num_input_tokens_seen": 863379344, "step": 20965, "train_runtime": 80800.3185, "train_tokens_per_second": 10685.346 }, { "epoch": 1.4119310530568274, "grad_norm": 0.6680174635072769, "learning_rate": 1.9862062595194854e-06, "loss": 0.3141848087310791, "num_input_tokens_seen": 863580080, "step": 20970, "train_runtime": 80819.7746, "train_tokens_per_second": 10685.257 }, { "epoch": 1.4122677080527875, "grad_norm": 0.8168618518860967, "learning_rate": 1.984096905762676e-06, "loss": 0.2987366676330566, "num_input_tokens_seen": 863782104, "step": 20975, "train_runtime": 80840.3338, "train_tokens_per_second": 10685.039 }, { "epoch": 1.4126043630487477, "grad_norm": 0.726442406967637, "learning_rate": 1.9819883953935533e-06, "loss": 0.30407209396362306, "num_input_tokens_seen": 863997392, "step": 20980, "train_runtime": 80858.9103, "train_tokens_per_second": 10685.247 }, { "epoch": 1.4129410180447077, "grad_norm": 0.7737205725701113, "learning_rate": 1.9798807290017485e-06, "loss": 0.2928401708602905, "num_input_tokens_seen": 864194488, "step": 20985, "train_runtime": 80877.9189, "train_tokens_per_second": 10685.172 }, { "epoch": 1.413277673040668, "grad_norm": 0.6827203913147443, "learning_rate": 1.9777739071766693e-06, "loss": 0.3045379638671875, "num_input_tokens_seen": 864396296, "step": 20990, "train_runtime": 80897.9247, "train_tokens_per_second": 10685.024 }, { "epoch": 1.413614328036628, "grad_norm": 0.7129923906077866, "learning_rate": 1.97566793050748e-06, "loss": 0.3026515007019043, "num_input_tokens_seen": 864588072, "step": 20995, "train_runtime": 80917.391, "train_tokens_per_second": 10684.824 }, { "epoch": 1.4139509830325883, "grad_norm": 0.7532340129035087, "learning_rate": 1.9735627995831096e-06, "loss": 0.2829909801483154, "num_input_tokens_seen": 864798568, "step": 21000, "train_runtime": 80935.3606, "train_tokens_per_second": 10685.052 }, { "epoch": 1.4142876380285483, "grad_norm": 0.8050405488392535, "learning_rate": 1.9714585149922523e-06, "loss": 0.32485640048980713, "num_input_tokens_seen": 865012024, "step": 21005, "train_runtime": 80955.7032, "train_tokens_per_second": 10685.004 }, { "epoch": 1.4146242930245085, "grad_norm": 0.734776134299804, "learning_rate": 1.9693550773233634e-06, "loss": 0.2847509622573853, "num_input_tokens_seen": 865221824, "step": 21010, "train_runtime": 80973.7326, "train_tokens_per_second": 10685.216 }, { "epoch": 1.4149609480204686, "grad_norm": 0.7417119315295636, "learning_rate": 1.967252487164663e-06, "loss": 0.2835427522659302, "num_input_tokens_seen": 865434400, "step": 21015, "train_runtime": 80992.2637, "train_tokens_per_second": 10685.396 }, { "epoch": 1.4152976030164288, "grad_norm": 0.8024302317439597, "learning_rate": 1.9651507451041344e-06, "loss": 0.3098809003829956, "num_input_tokens_seen": 865636904, "step": 21020, "train_runtime": 81011.665, "train_tokens_per_second": 10685.337 }, { "epoch": 1.4156342580123888, "grad_norm": 0.7216075575386819, "learning_rate": 1.9630498517295204e-06, "loss": 0.3072973251342773, "num_input_tokens_seen": 865850680, "step": 21025, "train_runtime": 81030.2453, "train_tokens_per_second": 10685.525 }, { "epoch": 1.415970913008349, "grad_norm": 0.7247274594161697, "learning_rate": 1.960949807628335e-06, "loss": 0.30808885097503663, "num_input_tokens_seen": 866056240, "step": 21030, "train_runtime": 81048.4614, "train_tokens_per_second": 10685.659 }, { "epoch": 1.4163075680043091, "grad_norm": 0.7455074482864688, "learning_rate": 1.9588506133878415e-06, "loss": 0.33289785385131837, "num_input_tokens_seen": 866262944, "step": 21035, "train_runtime": 81068.4276, "train_tokens_per_second": 10685.577 }, { "epoch": 1.4166442230002694, "grad_norm": 0.6964615555126471, "learning_rate": 1.956752269595078e-06, "loss": 0.31774470806121824, "num_input_tokens_seen": 866475584, "step": 21040, "train_runtime": 81090.175, "train_tokens_per_second": 10685.334 }, { "epoch": 1.4169808779962294, "grad_norm": 0.7322370477132637, "learning_rate": 1.9546547768368384e-06, "loss": 0.29918456077575684, "num_input_tokens_seen": 866690632, "step": 21045, "train_runtime": 81108.3527, "train_tokens_per_second": 10685.59 }, { "epoch": 1.4173175329921897, "grad_norm": 0.8624217459937634, "learning_rate": 1.9525581356996793e-06, "loss": 0.28696322441101074, "num_input_tokens_seen": 866894008, "step": 21050, "train_runtime": 81127.2007, "train_tokens_per_second": 10685.615 }, { "epoch": 1.4176541879881497, "grad_norm": 0.7589719823950725, "learning_rate": 1.95046234676992e-06, "loss": 0.2994281768798828, "num_input_tokens_seen": 867116536, "step": 21055, "train_runtime": 81147.1365, "train_tokens_per_second": 10685.732 }, { "epoch": 1.41799084298411, "grad_norm": 0.8129729517120565, "learning_rate": 1.9483674106336416e-06, "loss": 0.2812483310699463, "num_input_tokens_seen": 867315800, "step": 21060, "train_runtime": 81166.1156, "train_tokens_per_second": 10685.688 }, { "epoch": 1.41832749798007, "grad_norm": 0.6826624452653162, "learning_rate": 1.9462733278766853e-06, "loss": 0.2969754934310913, "num_input_tokens_seen": 867515288, "step": 21065, "train_runtime": 81186.1058, "train_tokens_per_second": 10685.514 }, { "epoch": 1.4186641529760302, "grad_norm": 0.7073001568921861, "learning_rate": 1.9441800990846553e-06, "loss": 0.2932869911193848, "num_input_tokens_seen": 867728800, "step": 21070, "train_runtime": 81204.5665, "train_tokens_per_second": 10685.714 }, { "epoch": 1.4190008079719902, "grad_norm": 0.8155512109839362, "learning_rate": 1.942087724842915e-06, "loss": 0.32593021392822263, "num_input_tokens_seen": 867925368, "step": 21075, "train_runtime": 81223.63, "train_tokens_per_second": 10685.626 }, { "epoch": 1.4193374629679505, "grad_norm": 0.7434285238068328, "learning_rate": 1.9399962057365944e-06, "loss": 0.29973626136779785, "num_input_tokens_seen": 868118624, "step": 21080, "train_runtime": 81241.7605, "train_tokens_per_second": 10685.621 }, { "epoch": 1.4196741179639105, "grad_norm": 0.6947411461356198, "learning_rate": 1.937905542350574e-06, "loss": 0.3219170093536377, "num_input_tokens_seen": 868330664, "step": 21085, "train_runtime": 81262.6568, "train_tokens_per_second": 10685.482 }, { "epoch": 1.4200107729598708, "grad_norm": 0.7589476202350369, "learning_rate": 1.935815735269506e-06, "loss": 0.30747768878936765, "num_input_tokens_seen": 868536184, "step": 21090, "train_runtime": 81281.209, "train_tokens_per_second": 10685.572 }, { "epoch": 1.4203474279558308, "grad_norm": 0.7916267198930005, "learning_rate": 1.933726785077797e-06, "loss": 0.32496817111968995, "num_input_tokens_seen": 868738600, "step": 21095, "train_runtime": 81301.2734, "train_tokens_per_second": 10685.424 }, { "epoch": 1.420684082951791, "grad_norm": 0.8520666606362649, "learning_rate": 1.9316386923596146e-06, "loss": 0.3226409912109375, "num_input_tokens_seen": 868944448, "step": 21100, "train_runtime": 81319.0862, "train_tokens_per_second": 10685.615 }, { "epoch": 1.421020737947751, "grad_norm": 0.9167705699812932, "learning_rate": 1.929551457698888e-06, "loss": 0.31392979621887207, "num_input_tokens_seen": 869152848, "step": 21105, "train_runtime": 81336.5676, "train_tokens_per_second": 10685.881 }, { "epoch": 1.4213573929437113, "grad_norm": 0.6704656136453735, "learning_rate": 1.9274650816793044e-06, "loss": 0.30378165245056155, "num_input_tokens_seen": 869369328, "step": 21110, "train_runtime": 81355.5772, "train_tokens_per_second": 10686.045 }, { "epoch": 1.4216940479396714, "grad_norm": 0.7286159097179157, "learning_rate": 1.9253795648843136e-06, "loss": 0.31484394073486327, "num_input_tokens_seen": 869580816, "step": 21115, "train_runtime": 81373.3607, "train_tokens_per_second": 10686.308 }, { "epoch": 1.4220307029356316, "grad_norm": 0.7383323525947922, "learning_rate": 1.9232949078971236e-06, "loss": 0.3096004009246826, "num_input_tokens_seen": 869785200, "step": 21120, "train_runtime": 81392.3547, "train_tokens_per_second": 10686.326 }, { "epoch": 1.4223673579315916, "grad_norm": 0.6659457165078425, "learning_rate": 1.9212111113006998e-06, "loss": 0.29003610610961916, "num_input_tokens_seen": 870006304, "step": 21125, "train_runtime": 81411.973, "train_tokens_per_second": 10686.466 }, { "epoch": 1.4227040129275519, "grad_norm": 0.7861267361637524, "learning_rate": 1.919128175677775e-06, "loss": 0.2976623773574829, "num_input_tokens_seen": 870200792, "step": 21130, "train_runtime": 81430.3051, "train_tokens_per_second": 10686.449 }, { "epoch": 1.423040667923512, "grad_norm": 0.7147715710744592, "learning_rate": 1.917046101610827e-06, "loss": 0.3003503084182739, "num_input_tokens_seen": 870413128, "step": 21135, "train_runtime": 81449.0405, "train_tokens_per_second": 10686.598 }, { "epoch": 1.4233773229194722, "grad_norm": 0.6817058979614165, "learning_rate": 1.9149648896821087e-06, "loss": 0.31226286888122556, "num_input_tokens_seen": 870617856, "step": 21140, "train_runtime": 81468.158, "train_tokens_per_second": 10686.603 }, { "epoch": 1.4237139779154322, "grad_norm": 0.7792836355586777, "learning_rate": 1.912884540473621e-06, "loss": 0.2943993091583252, "num_input_tokens_seen": 870809336, "step": 21145, "train_runtime": 81487.2758, "train_tokens_per_second": 10686.446 }, { "epoch": 1.4240506329113924, "grad_norm": 0.7601805850526686, "learning_rate": 1.9108050545671283e-06, "loss": 0.2779939889907837, "num_input_tokens_seen": 871004216, "step": 21150, "train_runtime": 81506.2237, "train_tokens_per_second": 10686.352 }, { "epoch": 1.4243872879073525, "grad_norm": 0.7362452793951282, "learning_rate": 1.9087264325441507e-06, "loss": 0.26901199817657473, "num_input_tokens_seen": 871202384, "step": 21155, "train_runtime": 81525.9891, "train_tokens_per_second": 10686.192 }, { "epoch": 1.4247239429033127, "grad_norm": 0.7268013592168361, "learning_rate": 1.9066486749859686e-06, "loss": 0.30831782817840575, "num_input_tokens_seen": 871403136, "step": 21160, "train_runtime": 81544.754, "train_tokens_per_second": 10686.195 }, { "epoch": 1.4250605978992728, "grad_norm": 0.6767389016779363, "learning_rate": 1.9045717824736209e-06, "loss": 0.3155606985092163, "num_input_tokens_seen": 871615400, "step": 21165, "train_runtime": 81563.8348, "train_tokens_per_second": 10686.297 }, { "epoch": 1.425397252895233, "grad_norm": 0.7887345370140294, "learning_rate": 1.9024957555879037e-06, "loss": 0.3095280647277832, "num_input_tokens_seen": 871812016, "step": 21170, "train_runtime": 81581.6883, "train_tokens_per_second": 10686.369 }, { "epoch": 1.425733907891193, "grad_norm": 0.7412725126606983, "learning_rate": 1.9004205949093695e-06, "loss": 0.30314619541168214, "num_input_tokens_seen": 872016480, "step": 21175, "train_runtime": 81599.4716, "train_tokens_per_second": 10686.546 }, { "epoch": 1.4260705628871533, "grad_norm": 0.6990277299959414, "learning_rate": 1.8983463010183355e-06, "loss": 0.32007427215576173, "num_input_tokens_seen": 872217344, "step": 21180, "train_runtime": 81617.9931, "train_tokens_per_second": 10686.582 }, { "epoch": 1.4264072178831133, "grad_norm": 0.6605498992284738, "learning_rate": 1.8962728744948644e-06, "loss": 0.31262271404266356, "num_input_tokens_seen": 872431144, "step": 21185, "train_runtime": 81637.1865, "train_tokens_per_second": 10686.688 }, { "epoch": 1.4267438728790736, "grad_norm": 0.8046926736188658, "learning_rate": 1.894200315918789e-06, "loss": 0.3043628454208374, "num_input_tokens_seen": 872649504, "step": 21190, "train_runtime": 81654.9402, "train_tokens_per_second": 10687.039 }, { "epoch": 1.4270805278750336, "grad_norm": 0.7740637324995692, "learning_rate": 1.8921286258696913e-06, "loss": 0.29843478202819823, "num_input_tokens_seen": 872841128, "step": 21195, "train_runtime": 81673.7392, "train_tokens_per_second": 10686.925 }, { "epoch": 1.4274171828709938, "grad_norm": 0.6750931141504471, "learning_rate": 1.890057804926913e-06, "loss": 0.2900581359863281, "num_input_tokens_seen": 873053496, "step": 21200, "train_runtime": 81692.7633, "train_tokens_per_second": 10687.036 }, { "epoch": 1.4277538378669539, "grad_norm": 0.6630933255164687, "learning_rate": 1.887987853669553e-06, "loss": 0.2612194299697876, "num_input_tokens_seen": 873265336, "step": 21205, "train_runtime": 81714.7404, "train_tokens_per_second": 10686.754 }, { "epoch": 1.4280904928629141, "grad_norm": 0.8061783524536383, "learning_rate": 1.8859187726764654e-06, "loss": 0.3125759124755859, "num_input_tokens_seen": 873477176, "step": 21210, "train_runtime": 81733.9359, "train_tokens_per_second": 10686.836 }, { "epoch": 1.4284271478588741, "grad_norm": 0.7862599613505328, "learning_rate": 1.8838505625262638e-06, "loss": 0.29993577003479005, "num_input_tokens_seen": 873692640, "step": 21215, "train_runtime": 81752.8223, "train_tokens_per_second": 10687.003 }, { "epoch": 1.4287638028548344, "grad_norm": 0.7079862164885184, "learning_rate": 1.8817832237973154e-06, "loss": 0.29716613292694094, "num_input_tokens_seen": 873898608, "step": 21220, "train_runtime": 81772.8324, "train_tokens_per_second": 10686.906 }, { "epoch": 1.4291004578507944, "grad_norm": 0.692527777577776, "learning_rate": 1.8797167570677439e-06, "loss": 0.2838526725769043, "num_input_tokens_seen": 874108752, "step": 21225, "train_runtime": 81794.521, "train_tokens_per_second": 10686.642 }, { "epoch": 1.4294371128467547, "grad_norm": 0.726632996852127, "learning_rate": 1.8776511629154342e-06, "loss": 0.3104121208190918, "num_input_tokens_seen": 874324744, "step": 21230, "train_runtime": 81813.7581, "train_tokens_per_second": 10686.769 }, { "epoch": 1.4297737678427147, "grad_norm": 0.6840425367472502, "learning_rate": 1.8755864419180176e-06, "loss": 0.30433313846588134, "num_input_tokens_seen": 874535912, "step": 21235, "train_runtime": 81832.9923, "train_tokens_per_second": 10686.838 }, { "epoch": 1.430110422838675, "grad_norm": 0.7175728457594953, "learning_rate": 1.8735225946528906e-06, "loss": 0.3068469285964966, "num_input_tokens_seen": 874749344, "step": 21240, "train_runtime": 81852.4613, "train_tokens_per_second": 10686.903 }, { "epoch": 1.430447077834635, "grad_norm": 0.7961796370666687, "learning_rate": 1.8714596216972008e-06, "loss": 0.31528615951538086, "num_input_tokens_seen": 874952792, "step": 21245, "train_runtime": 81870.3717, "train_tokens_per_second": 10687.05 }, { "epoch": 1.4307837328305952, "grad_norm": 0.7156435396032129, "learning_rate": 1.8693975236278512e-06, "loss": 0.30375056266784667, "num_input_tokens_seen": 875155376, "step": 21250, "train_runtime": 81892.0494, "train_tokens_per_second": 10686.695 }, { "epoch": 1.4311203878265553, "grad_norm": 0.7886977618852598, "learning_rate": 1.8673363010215017e-06, "loss": 0.3250682830810547, "num_input_tokens_seen": 875357912, "step": 21255, "train_runtime": 81911.6978, "train_tokens_per_second": 10686.604 }, { "epoch": 1.4314570428225155, "grad_norm": 0.7825272352645918, "learning_rate": 1.8652759544545661e-06, "loss": 0.3097062587738037, "num_input_tokens_seen": 875566192, "step": 21260, "train_runtime": 81931.12, "train_tokens_per_second": 10686.613 }, { "epoch": 1.4317936978184758, "grad_norm": 0.708464261354613, "learning_rate": 1.863216484503214e-06, "loss": 0.30914936065673826, "num_input_tokens_seen": 875770840, "step": 21265, "train_runtime": 81952.4149, "train_tokens_per_second": 10686.334 }, { "epoch": 1.4321303528144358, "grad_norm": 0.7524020161569918, "learning_rate": 1.8611578917433698e-06, "loss": 0.3298330783843994, "num_input_tokens_seen": 875981360, "step": 21270, "train_runtime": 81970.8499, "train_tokens_per_second": 10686.498 }, { "epoch": 1.4324670078103958, "grad_norm": 0.7889761868324071, "learning_rate": 1.85910017675071e-06, "loss": 0.32344207763671873, "num_input_tokens_seen": 876185056, "step": 21275, "train_runtime": 81989.0838, "train_tokens_per_second": 10686.606 }, { "epoch": 1.432803662806356, "grad_norm": 0.6753499391035276, "learning_rate": 1.8570433401006737e-06, "loss": 0.26982252597808837, "num_input_tokens_seen": 876396320, "step": 21280, "train_runtime": 82006.9354, "train_tokens_per_second": 10686.856 }, { "epoch": 1.4331403178023163, "grad_norm": 0.7081536748827642, "learning_rate": 1.8549873823684418e-06, "loss": 0.28198373317718506, "num_input_tokens_seen": 876598808, "step": 21285, "train_runtime": 82025.2658, "train_tokens_per_second": 10686.937 }, { "epoch": 1.4334769727982763, "grad_norm": 0.6801186926813142, "learning_rate": 1.8529323041289616e-06, "loss": 0.32545783519744875, "num_input_tokens_seen": 876808808, "step": 21290, "train_runtime": 82043.5458, "train_tokens_per_second": 10687.115 }, { "epoch": 1.4338136277942364, "grad_norm": 0.697095851796711, "learning_rate": 1.850878105956927e-06, "loss": 0.295987606048584, "num_input_tokens_seen": 877019856, "step": 21295, "train_runtime": 82060.785, "train_tokens_per_second": 10687.442 }, { "epoch": 1.4341502827901966, "grad_norm": 0.7026898927622345, "learning_rate": 1.8488247884267885e-06, "loss": 0.29092657566070557, "num_input_tokens_seen": 877234608, "step": 21300, "train_runtime": 82080.3853, "train_tokens_per_second": 10687.506 }, { "epoch": 1.4344869377861569, "grad_norm": 0.7199200247496472, "learning_rate": 1.8467723521127495e-06, "loss": 0.31032211780548097, "num_input_tokens_seen": 877432656, "step": 21305, "train_runtime": 82099.8957, "train_tokens_per_second": 10687.378 }, { "epoch": 1.434823592782117, "grad_norm": 0.7238563039573613, "learning_rate": 1.8447207975887671e-06, "loss": 0.29379839897155763, "num_input_tokens_seen": 877636416, "step": 21310, "train_runtime": 82118.2424, "train_tokens_per_second": 10687.472 }, { "epoch": 1.435160247778077, "grad_norm": 0.7243460316518358, "learning_rate": 1.8426701254285522e-06, "loss": 0.3133138656616211, "num_input_tokens_seen": 877849648, "step": 21315, "train_runtime": 82138.1615, "train_tokens_per_second": 10687.476 }, { "epoch": 1.4354969027740372, "grad_norm": 0.7856173668892446, "learning_rate": 1.840620336205569e-06, "loss": 0.31566381454467773, "num_input_tokens_seen": 878058920, "step": 21320, "train_runtime": 82155.7437, "train_tokens_per_second": 10687.736 }, { "epoch": 1.4358335577699974, "grad_norm": 0.6745537822149029, "learning_rate": 1.8385714304930324e-06, "loss": 0.27221453189849854, "num_input_tokens_seen": 878271312, "step": 21325, "train_runtime": 82175.4281, "train_tokens_per_second": 10687.761 }, { "epoch": 1.4361702127659575, "grad_norm": 0.7285855768685231, "learning_rate": 1.8365234088639178e-06, "loss": 0.2939030170440674, "num_input_tokens_seen": 878480936, "step": 21330, "train_runtime": 82194.049, "train_tokens_per_second": 10687.89 }, { "epoch": 1.4365068677619175, "grad_norm": 0.7518929808608145, "learning_rate": 1.834476271890941e-06, "loss": 0.2806416034698486, "num_input_tokens_seen": 878671568, "step": 21335, "train_runtime": 82213.4112, "train_tokens_per_second": 10687.691 }, { "epoch": 1.4368435227578777, "grad_norm": 0.836298536114204, "learning_rate": 1.8324300201465823e-06, "loss": 0.29042508602142336, "num_input_tokens_seen": 878880776, "step": 21340, "train_runtime": 82232.7412, "train_tokens_per_second": 10687.723 }, { "epoch": 1.437180177753838, "grad_norm": 0.8714333006833975, "learning_rate": 1.8303846542030674e-06, "loss": 0.31939005851745605, "num_input_tokens_seen": 879078952, "step": 21345, "train_runtime": 82251.6839, "train_tokens_per_second": 10687.671 }, { "epoch": 1.437516832749798, "grad_norm": 0.62903780541137, "learning_rate": 1.828340174632377e-06, "loss": 0.2818665742874146, "num_input_tokens_seen": 879286224, "step": 21350, "train_runtime": 82270.025, "train_tokens_per_second": 10687.808 }, { "epoch": 1.437853487745758, "grad_norm": 0.7658166123814877, "learning_rate": 1.8262965820062434e-06, "loss": 0.2941282272338867, "num_input_tokens_seen": 879492112, "step": 21355, "train_runtime": 82289.1715, "train_tokens_per_second": 10687.823 }, { "epoch": 1.4381901427417183, "grad_norm": 0.6913338020271628, "learning_rate": 1.8242538768961499e-06, "loss": 0.28028531074523927, "num_input_tokens_seen": 879696984, "step": 21360, "train_runtime": 82307.7079, "train_tokens_per_second": 10687.905 }, { "epoch": 1.4385267977376786, "grad_norm": 0.7577502295901238, "learning_rate": 1.8222120598733317e-06, "loss": 0.28630244731903076, "num_input_tokens_seen": 879911504, "step": 21365, "train_runtime": 82326.4869, "train_tokens_per_second": 10688.073 }, { "epoch": 1.4388634527336386, "grad_norm": 0.647794028577741, "learning_rate": 1.820171131508781e-06, "loss": 0.32766146659851075, "num_input_tokens_seen": 880110664, "step": 21370, "train_runtime": 82345.9141, "train_tokens_per_second": 10687.97 }, { "epoch": 1.4392001077295986, "grad_norm": 0.6479984170510752, "learning_rate": 1.8181310923732304e-06, "loss": 0.2789600849151611, "num_input_tokens_seen": 880314184, "step": 21375, "train_runtime": 82366.3456, "train_tokens_per_second": 10687.79 }, { "epoch": 1.4395367627255589, "grad_norm": 0.7271706678249596, "learning_rate": 1.8160919430371764e-06, "loss": 0.3204392194747925, "num_input_tokens_seen": 880511928, "step": 21380, "train_runtime": 82385.3699, "train_tokens_per_second": 10687.722 }, { "epoch": 1.439873417721519, "grad_norm": 0.6766307818834342, "learning_rate": 1.814053684070855e-06, "loss": 0.2937586545944214, "num_input_tokens_seen": 880724560, "step": 21385, "train_runtime": 82405.4002, "train_tokens_per_second": 10687.704 }, { "epoch": 1.4402100727174791, "grad_norm": 0.6955334436864804, "learning_rate": 1.8120163160442633e-06, "loss": 0.27727108001708983, "num_input_tokens_seen": 880936656, "step": 21390, "train_runtime": 82424.5269, "train_tokens_per_second": 10687.798 }, { "epoch": 1.4405467277134392, "grad_norm": 0.7059812219156382, "learning_rate": 1.8099798395271428e-06, "loss": 0.3124536514282227, "num_input_tokens_seen": 881154656, "step": 21395, "train_runtime": 82442.2063, "train_tokens_per_second": 10688.15 }, { "epoch": 1.4408833827093994, "grad_norm": 0.7996259299958192, "learning_rate": 1.807944255088988e-06, "loss": 0.28826777935028075, "num_input_tokens_seen": 881354432, "step": 21400, "train_runtime": 82460.2904, "train_tokens_per_second": 10688.229 }, { "epoch": 1.4412200377053597, "grad_norm": 0.7208077314849662, "learning_rate": 1.8059095632990437e-06, "loss": 0.2924607515335083, "num_input_tokens_seen": 881559120, "step": 21405, "train_runtime": 82478.428, "train_tokens_per_second": 10688.36 }, { "epoch": 1.4415566927013197, "grad_norm": 0.7499803935058472, "learning_rate": 1.8038757647263045e-06, "loss": 0.31218230724334717, "num_input_tokens_seen": 881762480, "step": 21410, "train_runtime": 82496.593, "train_tokens_per_second": 10688.471 }, { "epoch": 1.4418933476972797, "grad_norm": 0.720650476601659, "learning_rate": 1.8018428599395143e-06, "loss": 0.2900655508041382, "num_input_tokens_seen": 881977160, "step": 21415, "train_runtime": 82515.4807, "train_tokens_per_second": 10688.627 }, { "epoch": 1.44223000269324, "grad_norm": 0.7252715008623262, "learning_rate": 1.7998108495071743e-06, "loss": 0.29198412895202636, "num_input_tokens_seen": 882188184, "step": 21420, "train_runtime": 82535.1545, "train_tokens_per_second": 10688.636 }, { "epoch": 1.4425666576892002, "grad_norm": 0.6469297953090382, "learning_rate": 1.797779733997521e-06, "loss": 0.2971491813659668, "num_input_tokens_seen": 882395496, "step": 21425, "train_runtime": 82554.8327, "train_tokens_per_second": 10688.599 }, { "epoch": 1.4429033126851603, "grad_norm": 0.7620604676091348, "learning_rate": 1.7957495139785585e-06, "loss": 0.318796443939209, "num_input_tokens_seen": 882605328, "step": 21430, "train_runtime": 82575.1344, "train_tokens_per_second": 10688.512 }, { "epoch": 1.4432399676811203, "grad_norm": 0.755535904864072, "learning_rate": 1.7937201900180228e-06, "loss": 0.30057640075683595, "num_input_tokens_seen": 882799312, "step": 21435, "train_runtime": 82594.7758, "train_tokens_per_second": 10688.319 }, { "epoch": 1.4435766226770805, "grad_norm": 0.7611140650357097, "learning_rate": 1.7916917626834134e-06, "loss": 0.34035253524780273, "num_input_tokens_seen": 883007944, "step": 21440, "train_runtime": 82614.3753, "train_tokens_per_second": 10688.309 }, { "epoch": 1.4439132776730408, "grad_norm": 0.7252268347296634, "learning_rate": 1.7896642325419722e-06, "loss": 0.31437268257141116, "num_input_tokens_seen": 883214304, "step": 21445, "train_runtime": 82634.5946, "train_tokens_per_second": 10688.191 }, { "epoch": 1.4442499326690008, "grad_norm": 0.7923612840780381, "learning_rate": 1.7876376001606915e-06, "loss": 0.3039292335510254, "num_input_tokens_seen": 883408664, "step": 21450, "train_runtime": 82653.8145, "train_tokens_per_second": 10688.057 }, { "epoch": 1.4445865876649608, "grad_norm": 0.6911923786542082, "learning_rate": 1.7856118661063128e-06, "loss": 0.28440265655517577, "num_input_tokens_seen": 883624320, "step": 21455, "train_runtime": 82673.535, "train_tokens_per_second": 10688.116 }, { "epoch": 1.444923242660921, "grad_norm": 0.7478972381368492, "learning_rate": 1.7835870309453251e-06, "loss": 0.3042238712310791, "num_input_tokens_seen": 883826136, "step": 21460, "train_runtime": 82692.3782, "train_tokens_per_second": 10688.121 }, { "epoch": 1.4452598976568813, "grad_norm": 0.7911909611626022, "learning_rate": 1.7815630952439667e-06, "loss": 0.2975651741027832, "num_input_tokens_seen": 884027440, "step": 21465, "train_runtime": 82711.7878, "train_tokens_per_second": 10688.047 }, { "epoch": 1.4455965526528414, "grad_norm": 0.6506696196109136, "learning_rate": 1.7795400595682289e-06, "loss": 0.2991589307785034, "num_input_tokens_seen": 884225576, "step": 21470, "train_runtime": 82731.6921, "train_tokens_per_second": 10687.87 }, { "epoch": 1.4459332076488014, "grad_norm": 0.7532721309114288, "learning_rate": 1.7775179244838408e-06, "loss": 0.3418420314788818, "num_input_tokens_seen": 884422376, "step": 21475, "train_runtime": 82749.9194, "train_tokens_per_second": 10687.894 }, { "epoch": 1.4462698626447617, "grad_norm": 0.711219656367298, "learning_rate": 1.7754966905562925e-06, "loss": 0.29956879615783694, "num_input_tokens_seen": 884615664, "step": 21480, "train_runtime": 82767.2408, "train_tokens_per_second": 10687.993 }, { "epoch": 1.446606517640722, "grad_norm": 0.8444499857881121, "learning_rate": 1.7734763583508098e-06, "loss": 0.29669461250305174, "num_input_tokens_seen": 884821304, "step": 21485, "train_runtime": 82786.5675, "train_tokens_per_second": 10687.982 }, { "epoch": 1.446943172636682, "grad_norm": 0.7096382209056185, "learning_rate": 1.7714569284323757e-06, "loss": 0.31615390777587893, "num_input_tokens_seen": 885036712, "step": 21490, "train_runtime": 82805.572, "train_tokens_per_second": 10688.13 }, { "epoch": 1.447279827632642, "grad_norm": 0.7581768983972678, "learning_rate": 1.7694384013657173e-06, "loss": 0.29598815441131593, "num_input_tokens_seen": 885239856, "step": 21495, "train_runtime": 82824.1818, "train_tokens_per_second": 10688.181 }, { "epoch": 1.4476164826286022, "grad_norm": 0.7133692996809243, "learning_rate": 1.767420777715308e-06, "loss": 0.3122076988220215, "num_input_tokens_seen": 885456384, "step": 21500, "train_runtime": 82843.0055, "train_tokens_per_second": 10688.366 }, { "epoch": 1.4479531376245625, "grad_norm": 0.7229454949495228, "learning_rate": 1.7654040580453702e-06, "loss": 0.28534770011901855, "num_input_tokens_seen": 885668432, "step": 21505, "train_runtime": 82860.6761, "train_tokens_per_second": 10688.646 }, { "epoch": 1.4482897926205225, "grad_norm": 0.6035803680989825, "learning_rate": 1.7633882429198734e-06, "loss": 0.317385196685791, "num_input_tokens_seen": 885881560, "step": 21510, "train_runtime": 82881.6995, "train_tokens_per_second": 10688.506 }, { "epoch": 1.4486264476164825, "grad_norm": 0.6939510254780552, "learning_rate": 1.7613733329025318e-06, "loss": 0.2993293762207031, "num_input_tokens_seen": 886100760, "step": 21515, "train_runtime": 82901.3772, "train_tokens_per_second": 10688.613 }, { "epoch": 1.4489631026124428, "grad_norm": 0.6541747492631317, "learning_rate": 1.759359328556814e-06, "loss": 0.3107997179031372, "num_input_tokens_seen": 886312800, "step": 21520, "train_runtime": 82920.6658, "train_tokens_per_second": 10688.684 }, { "epoch": 1.449299757608403, "grad_norm": 0.6818789648093141, "learning_rate": 1.7573462304459227e-06, "loss": 0.3041474103927612, "num_input_tokens_seen": 886519080, "step": 21525, "train_runtime": 82939.1272, "train_tokens_per_second": 10688.792 }, { "epoch": 1.449636412604363, "grad_norm": 0.7375862905284589, "learning_rate": 1.7553340391328216e-06, "loss": 0.2886679172515869, "num_input_tokens_seen": 886725448, "step": 21530, "train_runtime": 82958.0356, "train_tokens_per_second": 10688.843 }, { "epoch": 1.449973067600323, "grad_norm": 0.7109992546740005, "learning_rate": 1.7533227551802068e-06, "loss": 0.30740573406219485, "num_input_tokens_seen": 886938048, "step": 21535, "train_runtime": 82977.0325, "train_tokens_per_second": 10688.958 }, { "epoch": 1.4503097225962833, "grad_norm": 0.6989816885607639, "learning_rate": 1.7513123791505321e-06, "loss": 0.32097320556640624, "num_input_tokens_seen": 887137040, "step": 21540, "train_runtime": 82998.3715, "train_tokens_per_second": 10688.608 }, { "epoch": 1.4506463775922436, "grad_norm": 0.6852711924801245, "learning_rate": 1.7493029116059913e-06, "loss": 0.30911262035369874, "num_input_tokens_seen": 887340800, "step": 21545, "train_runtime": 83017.1732, "train_tokens_per_second": 10688.641 }, { "epoch": 1.4509830325882036, "grad_norm": 0.655548242615012, "learning_rate": 1.7472943531085252e-06, "loss": 0.3001275062561035, "num_input_tokens_seen": 887553536, "step": 21550, "train_runtime": 83035.7396, "train_tokens_per_second": 10688.814 }, { "epoch": 1.4513196875841636, "grad_norm": 0.7641927728080976, "learning_rate": 1.7452867042198212e-06, "loss": 0.28624489307403567, "num_input_tokens_seen": 887753752, "step": 21555, "train_runtime": 83055.7722, "train_tokens_per_second": 10688.646 }, { "epoch": 1.4516563425801239, "grad_norm": 0.618715230560964, "learning_rate": 1.7432799655013122e-06, "loss": 0.28097174167633054, "num_input_tokens_seen": 887964728, "step": 21560, "train_runtime": 83076.1767, "train_tokens_per_second": 10688.56 }, { "epoch": 1.4519929975760841, "grad_norm": 0.7156595740520096, "learning_rate": 1.741274137514174e-06, "loss": 0.31643128395080566, "num_input_tokens_seen": 888164144, "step": 21565, "train_runtime": 83095.3188, "train_tokens_per_second": 10688.498 }, { "epoch": 1.4523296525720442, "grad_norm": 0.7349267499640255, "learning_rate": 1.7392692208193351e-06, "loss": 0.290786075592041, "num_input_tokens_seen": 888368664, "step": 21570, "train_runtime": 83114.018, "train_tokens_per_second": 10688.554 }, { "epoch": 1.4526663075680042, "grad_norm": 0.7077888662540706, "learning_rate": 1.7372652159774578e-06, "loss": 0.27406575679779055, "num_input_tokens_seen": 888581504, "step": 21575, "train_runtime": 83133.758, "train_tokens_per_second": 10688.576 }, { "epoch": 1.4530029625639644, "grad_norm": 0.78682207489462, "learning_rate": 1.7352621235489625e-06, "loss": 0.291827917098999, "num_input_tokens_seen": 888786184, "step": 21580, "train_runtime": 83152.0329, "train_tokens_per_second": 10688.689 }, { "epoch": 1.4533396175599247, "grad_norm": 0.8743140527525329, "learning_rate": 1.733259944094e-06, "loss": 0.31530845165252686, "num_input_tokens_seen": 888991232, "step": 21585, "train_runtime": 83170.0858, "train_tokens_per_second": 10688.834 }, { "epoch": 1.4536762725558847, "grad_norm": 0.7815992542798825, "learning_rate": 1.7312586781724789e-06, "loss": 0.30535311698913575, "num_input_tokens_seen": 889196312, "step": 21590, "train_runtime": 83187.9971, "train_tokens_per_second": 10688.998 }, { "epoch": 1.4540129275518447, "grad_norm": 0.709167230467626, "learning_rate": 1.7292583263440454e-06, "loss": 0.31220808029174807, "num_input_tokens_seen": 889396712, "step": 21595, "train_runtime": 83207.2219, "train_tokens_per_second": 10688.937 }, { "epoch": 1.454349582547805, "grad_norm": 0.6933604243156747, "learning_rate": 1.7272588891680914e-06, "loss": 0.29007768630981445, "num_input_tokens_seen": 889592128, "step": 21600, "train_runtime": 83227.907, "train_tokens_per_second": 10688.628 }, { "epoch": 1.4546862375437652, "grad_norm": 0.9841007292871476, "learning_rate": 1.7252603672037527e-06, "loss": 0.28956897258758546, "num_input_tokens_seen": 889793176, "step": 21605, "train_runtime": 83247.9979, "train_tokens_per_second": 10688.463 }, { "epoch": 1.4550228925397253, "grad_norm": 0.6697805541791672, "learning_rate": 1.72326276100991e-06, "loss": 0.2813713550567627, "num_input_tokens_seen": 890007944, "step": 21610, "train_runtime": 83267.653, "train_tokens_per_second": 10688.52 }, { "epoch": 1.4553595475356853, "grad_norm": 0.7818471996823949, "learning_rate": 1.721266071145186e-06, "loss": 0.3046153783798218, "num_input_tokens_seen": 890218488, "step": 21615, "train_runtime": 83285.5565, "train_tokens_per_second": 10688.75 }, { "epoch": 1.4556962025316456, "grad_norm": 0.6566168979562378, "learning_rate": 1.7192702981679531e-06, "loss": 0.3072495937347412, "num_input_tokens_seen": 890430480, "step": 21620, "train_runtime": 83303.3478, "train_tokens_per_second": 10689.012 }, { "epoch": 1.4560328575276058, "grad_norm": 0.7481527503752726, "learning_rate": 1.717275442636317e-06, "loss": 0.2767538547515869, "num_input_tokens_seen": 890639240, "step": 21625, "train_runtime": 83321.4362, "train_tokens_per_second": 10689.197 }, { "epoch": 1.4563695125235658, "grad_norm": 0.7720872824019585, "learning_rate": 1.7152815051081384e-06, "loss": 0.3119265079498291, "num_input_tokens_seen": 890843832, "step": 21630, "train_runtime": 83340.1963, "train_tokens_per_second": 10689.246 }, { "epoch": 1.4567061675195259, "grad_norm": 0.6334873062024279, "learning_rate": 1.7132884861410093e-06, "loss": 0.30737130641937255, "num_input_tokens_seen": 891042320, "step": 21635, "train_runtime": 83358.8853, "train_tokens_per_second": 10689.23 }, { "epoch": 1.4570428225154861, "grad_norm": 0.6972786830116419, "learning_rate": 1.7112963862922766e-06, "loss": 0.2846538782119751, "num_input_tokens_seen": 891241984, "step": 21640, "train_runtime": 83378.2811, "train_tokens_per_second": 10689.138 }, { "epoch": 1.4573794775114464, "grad_norm": 0.7920147915868108, "learning_rate": 1.7093052061190224e-06, "loss": 0.3057241439819336, "num_input_tokens_seen": 891458304, "step": 21645, "train_runtime": 83397.9768, "train_tokens_per_second": 10689.208 }, { "epoch": 1.4577161325074064, "grad_norm": 0.8317940489557729, "learning_rate": 1.7073149461780742e-06, "loss": 0.3015773296356201, "num_input_tokens_seen": 891676496, "step": 21650, "train_runtime": 83417.1454, "train_tokens_per_second": 10689.367 }, { "epoch": 1.4580527875033664, "grad_norm": 0.787415861206265, "learning_rate": 1.705325607026001e-06, "loss": 0.3095995426177979, "num_input_tokens_seen": 891870368, "step": 21655, "train_runtime": 83436.1525, "train_tokens_per_second": 10689.256 }, { "epoch": 1.4583894424993267, "grad_norm": 0.7814689207509096, "learning_rate": 1.7033371892191164e-06, "loss": 0.310380220413208, "num_input_tokens_seen": 892078872, "step": 21660, "train_runtime": 83455.8285, "train_tokens_per_second": 10689.234 }, { "epoch": 1.458726097495287, "grad_norm": 0.8240776960881261, "learning_rate": 1.7013496933134726e-06, "loss": 0.3129431247711182, "num_input_tokens_seen": 892278560, "step": 21665, "train_runtime": 83475.697, "train_tokens_per_second": 10689.082 }, { "epoch": 1.459062752491247, "grad_norm": 0.69780067729999, "learning_rate": 1.6993631198648724e-06, "loss": 0.34530112743377683, "num_input_tokens_seen": 892485936, "step": 21670, "train_runtime": 83494.4456, "train_tokens_per_second": 10689.165 }, { "epoch": 1.459399407487207, "grad_norm": 0.7450361849108459, "learning_rate": 1.697377469428847e-06, "loss": 0.2963066577911377, "num_input_tokens_seen": 892695936, "step": 21675, "train_runtime": 83512.5016, "train_tokens_per_second": 10689.369 }, { "epoch": 1.4597360624831672, "grad_norm": 0.7184135393303995, "learning_rate": 1.6953927425606842e-06, "loss": 0.32324531078338625, "num_input_tokens_seen": 892901920, "step": 21680, "train_runtime": 83532.9659, "train_tokens_per_second": 10689.216 }, { "epoch": 1.4600727174791275, "grad_norm": 0.6656479199424107, "learning_rate": 1.6934089398154002e-06, "loss": 0.28367180824279786, "num_input_tokens_seen": 893105768, "step": 21685, "train_runtime": 83553.3915, "train_tokens_per_second": 10689.043 }, { "epoch": 1.4604093724750875, "grad_norm": 0.6299547142864631, "learning_rate": 1.6914260617477634e-06, "loss": 0.2827741622924805, "num_input_tokens_seen": 893315856, "step": 21690, "train_runtime": 83571.9859, "train_tokens_per_second": 10689.178 }, { "epoch": 1.4607460274710475, "grad_norm": 0.638828704466538, "learning_rate": 1.6894441089122788e-06, "loss": 0.2705039978027344, "num_input_tokens_seen": 893519968, "step": 21695, "train_runtime": 83591.919, "train_tokens_per_second": 10689.071 }, { "epoch": 1.4610826824670078, "grad_norm": 0.9368831816160034, "learning_rate": 1.6874630818631926e-06, "loss": 0.31410486698150636, "num_input_tokens_seen": 893729200, "step": 21700, "train_runtime": 83613.1494, "train_tokens_per_second": 10688.859 }, { "epoch": 1.461419337462968, "grad_norm": 0.7291724627893443, "learning_rate": 1.685482981154492e-06, "loss": 0.3096056699752808, "num_input_tokens_seen": 893936296, "step": 21705, "train_runtime": 83630.7503, "train_tokens_per_second": 10689.086 }, { "epoch": 1.461755992458928, "grad_norm": 0.6492413455118082, "learning_rate": 1.683503807339907e-06, "loss": 0.29175686836242676, "num_input_tokens_seen": 894150880, "step": 21710, "train_runtime": 83650.0511, "train_tokens_per_second": 10689.185 }, { "epoch": 1.462092647454888, "grad_norm": 0.6521404122977443, "learning_rate": 1.6815255609729047e-06, "loss": 0.3052048921585083, "num_input_tokens_seen": 894361944, "step": 21715, "train_runtime": 83668.3319, "train_tokens_per_second": 10689.372 }, { "epoch": 1.4624293024508483, "grad_norm": 0.8408280453008564, "learning_rate": 1.6795482426067012e-06, "loss": 0.29610252380371094, "num_input_tokens_seen": 894557056, "step": 21720, "train_runtime": 83687.6823, "train_tokens_per_second": 10689.232 }, { "epoch": 1.4627659574468086, "grad_norm": 0.7781200093013587, "learning_rate": 1.6775718527942403e-06, "loss": 0.290622878074646, "num_input_tokens_seen": 894742280, "step": 21725, "train_runtime": 83706.8006, "train_tokens_per_second": 10689.003 }, { "epoch": 1.4631026124427686, "grad_norm": 0.7536379668024593, "learning_rate": 1.675596392088219e-06, "loss": 0.30874977111816404, "num_input_tokens_seen": 894953752, "step": 21730, "train_runtime": 83725.4805, "train_tokens_per_second": 10689.144 }, { "epoch": 1.4634392674387287, "grad_norm": 0.6626078747152907, "learning_rate": 1.6736218610410633e-06, "loss": 0.2804556131362915, "num_input_tokens_seen": 895171840, "step": 21735, "train_runtime": 83744.6597, "train_tokens_per_second": 10689.301 }, { "epoch": 1.463775922434689, "grad_norm": 0.7132513403549788, "learning_rate": 1.6716482602049483e-06, "loss": 0.2976118564605713, "num_input_tokens_seen": 895379024, "step": 21740, "train_runtime": 83764.7983, "train_tokens_per_second": 10689.204 }, { "epoch": 1.4641125774306492, "grad_norm": 0.8177064073870677, "learning_rate": 1.669675590131784e-06, "loss": 0.3092564582824707, "num_input_tokens_seen": 895571320, "step": 21745, "train_runtime": 83782.8145, "train_tokens_per_second": 10689.201 }, { "epoch": 1.4644492324266092, "grad_norm": 0.7239654218881905, "learning_rate": 1.6677038513732214e-06, "loss": 0.30738368034362795, "num_input_tokens_seen": 895782680, "step": 21750, "train_runtime": 83802.7762, "train_tokens_per_second": 10689.177 }, { "epoch": 1.4647858874225694, "grad_norm": 0.7571381012044235, "learning_rate": 1.6657330444806508e-06, "loss": 0.3109379529953003, "num_input_tokens_seen": 895984160, "step": 21755, "train_runtime": 83821.9189, "train_tokens_per_second": 10689.139 }, { "epoch": 1.4651225424185295, "grad_norm": 0.6963164873109918, "learning_rate": 1.6637631700052021e-06, "loss": 0.2943947076797485, "num_input_tokens_seen": 896200552, "step": 21760, "train_runtime": 83840.5115, "train_tokens_per_second": 10689.35 }, { "epoch": 1.4654591974144897, "grad_norm": 0.7364044351383514, "learning_rate": 1.6617942284977428e-06, "loss": 0.28778700828552245, "num_input_tokens_seen": 896417592, "step": 21765, "train_runtime": 83858.7406, "train_tokens_per_second": 10689.614 }, { "epoch": 1.4657958524104497, "grad_norm": 0.8379785849687852, "learning_rate": 1.6598262205088862e-06, "loss": 0.32074408531188964, "num_input_tokens_seen": 896628152, "step": 21770, "train_runtime": 83877.5221, "train_tokens_per_second": 10689.731 }, { "epoch": 1.46613250740641, "grad_norm": 0.8091974100373359, "learning_rate": 1.6578591465889722e-06, "loss": 0.3091949701309204, "num_input_tokens_seen": 896841616, "step": 21775, "train_runtime": 83897.3654, "train_tokens_per_second": 10689.747 }, { "epoch": 1.46646916240237, "grad_norm": 0.7688266973417985, "learning_rate": 1.6558930072880942e-06, "loss": 0.3210612773895264, "num_input_tokens_seen": 897051864, "step": 21780, "train_runtime": 83917.3287, "train_tokens_per_second": 10689.709 }, { "epoch": 1.4668058173983303, "grad_norm": 0.7418421655516992, "learning_rate": 1.6539278031560695e-06, "loss": 0.32389657497406005, "num_input_tokens_seen": 897255224, "step": 21785, "train_runtime": 83937.1496, "train_tokens_per_second": 10689.608 }, { "epoch": 1.4671424723942903, "grad_norm": 0.8255274187495729, "learning_rate": 1.6519635347424672e-06, "loss": 0.30038766860961913, "num_input_tokens_seen": 897457512, "step": 21790, "train_runtime": 83955.4639, "train_tokens_per_second": 10689.686 }, { "epoch": 1.4674791273902505, "grad_norm": 0.7415924679713646, "learning_rate": 1.650000202596586e-06, "loss": 0.3257285594940186, "num_input_tokens_seen": 897675600, "step": 21795, "train_runtime": 83975.5861, "train_tokens_per_second": 10689.721 }, { "epoch": 1.4678157823862106, "grad_norm": 0.7927787349051493, "learning_rate": 1.6480378072674659e-06, "loss": 0.3131972312927246, "num_input_tokens_seen": 897884856, "step": 21800, "train_runtime": 83994.7704, "train_tokens_per_second": 10689.771 }, { "epoch": 1.4681524373821708, "grad_norm": 0.7040294460530104, "learning_rate": 1.646076349303884e-06, "loss": 0.29314537048339845, "num_input_tokens_seen": 898093528, "step": 21805, "train_runtime": 84015.3713, "train_tokens_per_second": 10689.634 }, { "epoch": 1.4684890923781309, "grad_norm": 0.7822992276687736, "learning_rate": 1.6441158292543557e-06, "loss": 0.30367443561553953, "num_input_tokens_seen": 898294216, "step": 21810, "train_runtime": 84034.6242, "train_tokens_per_second": 10689.573 }, { "epoch": 1.468825747374091, "grad_norm": 0.6560948965815518, "learning_rate": 1.6421562476671339e-06, "loss": 0.3267970085144043, "num_input_tokens_seen": 898499448, "step": 21815, "train_runtime": 84054.9448, "train_tokens_per_second": 10689.43 }, { "epoch": 1.4691624023700511, "grad_norm": 0.7817428855499029, "learning_rate": 1.640197605090213e-06, "loss": 0.2726292133331299, "num_input_tokens_seen": 898707408, "step": 21820, "train_runtime": 84074.7683, "train_tokens_per_second": 10689.383 }, { "epoch": 1.4694990573660114, "grad_norm": 1.0920942877470035, "learning_rate": 1.6382399020713146e-06, "loss": 0.28942131996154785, "num_input_tokens_seen": 898897160, "step": 21825, "train_runtime": 84092.6483, "train_tokens_per_second": 10689.367 }, { "epoch": 1.4698357123619714, "grad_norm": 0.7919395140855053, "learning_rate": 1.6362831391579115e-06, "loss": 0.2940690994262695, "num_input_tokens_seen": 899100392, "step": 21830, "train_runtime": 84112.2645, "train_tokens_per_second": 10689.29 }, { "epoch": 1.4701723673579317, "grad_norm": 0.7826147416799122, "learning_rate": 1.634327316897199e-06, "loss": 0.3090731382369995, "num_input_tokens_seen": 899298776, "step": 21835, "train_runtime": 84131.5833, "train_tokens_per_second": 10689.194 }, { "epoch": 1.4705090223538917, "grad_norm": 0.740621173408121, "learning_rate": 1.6323724358361216e-06, "loss": 0.2929354667663574, "num_input_tokens_seen": 899495720, "step": 21840, "train_runtime": 84150.7259, "train_tokens_per_second": 10689.102 }, { "epoch": 1.470845677349852, "grad_norm": 0.7223112953558165, "learning_rate": 1.6304184965213537e-06, "loss": 0.29372053146362304, "num_input_tokens_seen": 899695832, "step": 21845, "train_runtime": 84169.8271, "train_tokens_per_second": 10689.054 }, { "epoch": 1.471182332345812, "grad_norm": 0.7481083399395909, "learning_rate": 1.6284654994993088e-06, "loss": 0.309336519241333, "num_input_tokens_seen": 899912000, "step": 21850, "train_runtime": 84189.3476, "train_tokens_per_second": 10689.143 }, { "epoch": 1.4715189873417722, "grad_norm": 0.6283696165778855, "learning_rate": 1.6265134453161358e-06, "loss": 0.2910313606262207, "num_input_tokens_seen": 900112496, "step": 21855, "train_runtime": 84208.3515, "train_tokens_per_second": 10689.112 }, { "epoch": 1.4718556423377323, "grad_norm": 0.7396879637868772, "learning_rate": 1.6245623345177203e-06, "loss": 0.304166841506958, "num_input_tokens_seen": 900309080, "step": 21860, "train_runtime": 84227.3938, "train_tokens_per_second": 10689.029 }, { "epoch": 1.4721922973336925, "grad_norm": 0.6607040139524186, "learning_rate": 1.622612167649683e-06, "loss": 0.2879739284515381, "num_input_tokens_seen": 900505088, "step": 21865, "train_runtime": 84246.241, "train_tokens_per_second": 10688.965 }, { "epoch": 1.4725289523296525, "grad_norm": 0.6421215357046619, "learning_rate": 1.6206629452573868e-06, "loss": 0.2697411775588989, "num_input_tokens_seen": 900713200, "step": 21870, "train_runtime": 84265.1623, "train_tokens_per_second": 10689.034 }, { "epoch": 1.4728656073256128, "grad_norm": 0.9569198965711987, "learning_rate": 1.618714667885919e-06, "loss": 0.2953769683837891, "num_input_tokens_seen": 900918712, "step": 21875, "train_runtime": 84283.3181, "train_tokens_per_second": 10689.17 }, { "epoch": 1.4732022623215728, "grad_norm": 0.7069647338695803, "learning_rate": 1.6167673360801151e-06, "loss": 0.29752726554870607, "num_input_tokens_seen": 901132736, "step": 21880, "train_runtime": 84301.6933, "train_tokens_per_second": 10689.379 }, { "epoch": 1.473538917317533, "grad_norm": 0.7660926540203074, "learning_rate": 1.6148209503845336e-06, "loss": 0.3345245361328125, "num_input_tokens_seen": 901338224, "step": 21885, "train_runtime": 84320.1069, "train_tokens_per_second": 10689.482 }, { "epoch": 1.473875572313493, "grad_norm": 0.787134937868578, "learning_rate": 1.6128755113434808e-06, "loss": 0.2973806381225586, "num_input_tokens_seen": 901541632, "step": 21890, "train_runtime": 84340.4045, "train_tokens_per_second": 10689.321 }, { "epoch": 1.4742122273094533, "grad_norm": 0.6561735669708421, "learning_rate": 1.6109310195009908e-06, "loss": 0.2974536895751953, "num_input_tokens_seen": 901758416, "step": 21895, "train_runtime": 84359.551, "train_tokens_per_second": 10689.464 }, { "epoch": 1.4745488823054134, "grad_norm": 0.7849875312381625, "learning_rate": 1.6089874754008323e-06, "loss": 0.29174957275390623, "num_input_tokens_seen": 901952720, "step": 21900, "train_runtime": 84378.4931, "train_tokens_per_second": 10689.367 }, { "epoch": 1.4748855373013736, "grad_norm": 0.760256286598397, "learning_rate": 1.6070448795865162e-06, "loss": 0.3047230005264282, "num_input_tokens_seen": 902156720, "step": 21905, "train_runtime": 84397.6434, "train_tokens_per_second": 10689.359 }, { "epoch": 1.4752221922973336, "grad_norm": 0.6704510912774093, "learning_rate": 1.605103232601277e-06, "loss": 0.2987827301025391, "num_input_tokens_seen": 902360496, "step": 21910, "train_runtime": 84415.556, "train_tokens_per_second": 10689.505 }, { "epoch": 1.475558847293294, "grad_norm": 0.5972943718995626, "learning_rate": 1.603162534988096e-06, "loss": 0.2625176668167114, "num_input_tokens_seen": 902566504, "step": 21915, "train_runtime": 84434.6637, "train_tokens_per_second": 10689.526 }, { "epoch": 1.475895502289254, "grad_norm": 0.6917832396923523, "learning_rate": 1.6012227872896791e-06, "loss": 0.2862212657928467, "num_input_tokens_seen": 902765264, "step": 21920, "train_runtime": 84453.3922, "train_tokens_per_second": 10689.509 }, { "epoch": 1.4762321572852142, "grad_norm": 0.7429032287718347, "learning_rate": 1.599283990048472e-06, "loss": 0.29678409099578856, "num_input_tokens_seen": 902961240, "step": 21925, "train_runtime": 84472.6562, "train_tokens_per_second": 10689.391 }, { "epoch": 1.4765688122811742, "grad_norm": 0.6906904462815798, "learning_rate": 1.5973461438066533e-06, "loss": 0.29929018020629883, "num_input_tokens_seen": 903171792, "step": 21930, "train_runtime": 84492.6765, "train_tokens_per_second": 10689.35 }, { "epoch": 1.4769054672771345, "grad_norm": 0.724946249582719, "learning_rate": 1.5954092491061351e-06, "loss": 0.29095561504364015, "num_input_tokens_seen": 903377144, "step": 21935, "train_runtime": 84513.8831, "train_tokens_per_second": 10689.098 }, { "epoch": 1.4772421222730945, "grad_norm": 0.6231846262308879, "learning_rate": 1.5934733064885637e-06, "loss": 0.3019443988800049, "num_input_tokens_seen": 903590424, "step": 21940, "train_runtime": 84533.3795, "train_tokens_per_second": 10689.155 }, { "epoch": 1.4775787772690547, "grad_norm": 0.730729530162599, "learning_rate": 1.5915383164953203e-06, "loss": 0.3028738975524902, "num_input_tokens_seen": 903785128, "step": 21945, "train_runtime": 84551.7781, "train_tokens_per_second": 10689.132 }, { "epoch": 1.4779154322650148, "grad_norm": 0.810697620305203, "learning_rate": 1.5896042796675155e-06, "loss": 0.2904727697372437, "num_input_tokens_seen": 903979104, "step": 21950, "train_runtime": 84571.3812, "train_tokens_per_second": 10688.948 }, { "epoch": 1.478252087260975, "grad_norm": 0.7382736304288687, "learning_rate": 1.5876711965460023e-06, "loss": 0.2974765062332153, "num_input_tokens_seen": 904187128, "step": 21955, "train_runtime": 84590.0623, "train_tokens_per_second": 10689.047 }, { "epoch": 1.478588742256935, "grad_norm": 0.6869792713925944, "learning_rate": 1.5857390676713546e-06, "loss": 0.3013021945953369, "num_input_tokens_seen": 904382064, "step": 21960, "train_runtime": 84608.5621, "train_tokens_per_second": 10689.014 }, { "epoch": 1.4789253972528953, "grad_norm": 0.6537942006432291, "learning_rate": 1.5838078935838913e-06, "loss": 0.25974068641662595, "num_input_tokens_seen": 904576808, "step": 21965, "train_runtime": 84628.1413, "train_tokens_per_second": 10688.842 }, { "epoch": 1.4792620522488553, "grad_norm": 0.7129661041158203, "learning_rate": 1.581877674823657e-06, "loss": 0.283967113494873, "num_input_tokens_seen": 904770184, "step": 21970, "train_runtime": 84646.2627, "train_tokens_per_second": 10688.838 }, { "epoch": 1.4795987072448156, "grad_norm": 0.6973616198177274, "learning_rate": 1.5799484119304308e-06, "loss": 0.31192774772644044, "num_input_tokens_seen": 904975760, "step": 21975, "train_runtime": 84664.3338, "train_tokens_per_second": 10688.985 }, { "epoch": 1.4799353622407756, "grad_norm": 0.7058793206726279, "learning_rate": 1.578020105443726e-06, "loss": 0.2871628046035767, "num_input_tokens_seen": 905183352, "step": 21980, "train_runtime": 84683.2262, "train_tokens_per_second": 10689.051 }, { "epoch": 1.4802720172367358, "grad_norm": 0.8382014284469401, "learning_rate": 1.576092755902787e-06, "loss": 0.3171116590499878, "num_input_tokens_seen": 905385392, "step": 21985, "train_runtime": 84701.545, "train_tokens_per_second": 10689.125 }, { "epoch": 1.4806086722326959, "grad_norm": 0.7066416780397206, "learning_rate": 1.5741663638465903e-06, "loss": 0.3177147388458252, "num_input_tokens_seen": 905578552, "step": 21990, "train_runtime": 84720.1675, "train_tokens_per_second": 10689.055 }, { "epoch": 1.4809453272286561, "grad_norm": 0.7402489536581909, "learning_rate": 1.5722409298138463e-06, "loss": 0.2819089412689209, "num_input_tokens_seen": 905772896, "step": 21995, "train_runtime": 84740.7267, "train_tokens_per_second": 10688.755 }, { "epoch": 1.4812819822246162, "grad_norm": 0.8844707154042615, "learning_rate": 1.570316454342994e-06, "loss": 0.32681856155395506, "num_input_tokens_seen": 905975936, "step": 22000, "train_runtime": 84760.0949, "train_tokens_per_second": 10688.708 }, { "epoch": 1.4816186372205764, "grad_norm": 0.6788042054855941, "learning_rate": 1.568392937972212e-06, "loss": 0.3026883602142334, "num_input_tokens_seen": 906195264, "step": 22005, "train_runtime": 84779.0437, "train_tokens_per_second": 10688.906 }, { "epoch": 1.4819552922165364, "grad_norm": 0.7267642789000002, "learning_rate": 1.5664703812393988e-06, "loss": 0.30174527168273924, "num_input_tokens_seen": 906412632, "step": 22010, "train_runtime": 84799.1198, "train_tokens_per_second": 10688.939 }, { "epoch": 1.4822919472124967, "grad_norm": 0.7109982071759811, "learning_rate": 1.5645487846821967e-06, "loss": 0.30186028480529786, "num_input_tokens_seen": 906624296, "step": 22015, "train_runtime": 84817.9836, "train_tokens_per_second": 10689.057 }, { "epoch": 1.4826286022084567, "grad_norm": 0.7290771704617851, "learning_rate": 1.5626281488379724e-06, "loss": 0.30007359981536863, "num_input_tokens_seen": 906830600, "step": 22020, "train_runtime": 84837.1483, "train_tokens_per_second": 10689.075 }, { "epoch": 1.482965257204417, "grad_norm": 1.0037496872726221, "learning_rate": 1.560708474243825e-06, "loss": 0.283681845664978, "num_input_tokens_seen": 907037296, "step": 22025, "train_runtime": 84856.9775, "train_tokens_per_second": 10689.013 }, { "epoch": 1.483301912200377, "grad_norm": 0.7979444016008648, "learning_rate": 1.5587897614365854e-06, "loss": 0.30898146629333495, "num_input_tokens_seen": 907251800, "step": 22030, "train_runtime": 84875.9027, "train_tokens_per_second": 10689.156 }, { "epoch": 1.4836385671963372, "grad_norm": 0.7492148439008304, "learning_rate": 1.5568720109528163e-06, "loss": 0.2978041172027588, "num_input_tokens_seen": 907461272, "step": 22035, "train_runtime": 84897.3574, "train_tokens_per_second": 10688.922 }, { "epoch": 1.4839752221922973, "grad_norm": 0.8220825578287956, "learning_rate": 1.5549552233288095e-06, "loss": 0.3243819236755371, "num_input_tokens_seen": 907663624, "step": 22040, "train_runtime": 84916.1426, "train_tokens_per_second": 10688.941 }, { "epoch": 1.4843118771882575, "grad_norm": 0.6757741055184466, "learning_rate": 1.5530393991005893e-06, "loss": 0.29829704761505127, "num_input_tokens_seen": 907869584, "step": 22045, "train_runtime": 84936.1859, "train_tokens_per_second": 10688.843 }, { "epoch": 1.4846485321842176, "grad_norm": 0.7189528383553747, "learning_rate": 1.551124538803908e-06, "loss": 0.29630584716796876, "num_input_tokens_seen": 908081208, "step": 22050, "train_runtime": 84955.846, "train_tokens_per_second": 10688.861 }, { "epoch": 1.4849851871801778, "grad_norm": 0.7211817236867182, "learning_rate": 1.5492106429742547e-06, "loss": 0.30805459022521975, "num_input_tokens_seen": 908290760, "step": 22055, "train_runtime": 84975.3321, "train_tokens_per_second": 10688.876 }, { "epoch": 1.4853218421761378, "grad_norm": 0.7664854332066228, "learning_rate": 1.5472977121468386e-06, "loss": 0.3106490135192871, "num_input_tokens_seen": 908503104, "step": 22060, "train_runtime": 84993.2706, "train_tokens_per_second": 10689.118 }, { "epoch": 1.485658497172098, "grad_norm": 0.7796802534717433, "learning_rate": 1.545385746856609e-06, "loss": 0.2903266429901123, "num_input_tokens_seen": 908702256, "step": 22065, "train_runtime": 85011.226, "train_tokens_per_second": 10689.203 }, { "epoch": 1.485995152168058, "grad_norm": 0.710369850835588, "learning_rate": 1.5434747476382388e-06, "loss": 0.2687708854675293, "num_input_tokens_seen": 908919104, "step": 22070, "train_runtime": 85030.2366, "train_tokens_per_second": 10689.363 }, { "epoch": 1.4863318071640184, "grad_norm": 0.8204796942786035, "learning_rate": 1.5415647150261337e-06, "loss": 0.28986330032348634, "num_input_tokens_seen": 909111256, "step": 22075, "train_runtime": 85049.004, "train_tokens_per_second": 10689.264 }, { "epoch": 1.4866684621599784, "grad_norm": 0.762271575056004, "learning_rate": 1.539655649554428e-06, "loss": 0.2943394660949707, "num_input_tokens_seen": 909315888, "step": 22080, "train_runtime": 85070.1398, "train_tokens_per_second": 10689.014 }, { "epoch": 1.4870051171559386, "grad_norm": 0.7193695418873416, "learning_rate": 1.5377475517569856e-06, "loss": 0.28883073329925535, "num_input_tokens_seen": 909511696, "step": 22085, "train_runtime": 85089.6728, "train_tokens_per_second": 10688.861 }, { "epoch": 1.4873417721518987, "grad_norm": 0.7615057075652641, "learning_rate": 1.5358404221674e-06, "loss": 0.3012441635131836, "num_input_tokens_seen": 909709024, "step": 22090, "train_runtime": 85110.4094, "train_tokens_per_second": 10688.575 }, { "epoch": 1.487678427147859, "grad_norm": 0.7196293718728627, "learning_rate": 1.533934261318994e-06, "loss": 0.3016850471496582, "num_input_tokens_seen": 909916776, "step": 22095, "train_runtime": 85128.192, "train_tokens_per_second": 10688.783 }, { "epoch": 1.488015082143819, "grad_norm": 0.6831032784427328, "learning_rate": 1.5320290697448177e-06, "loss": 0.2787220239639282, "num_input_tokens_seen": 910118512, "step": 22100, "train_runtime": 85147.7461, "train_tokens_per_second": 10688.698 }, { "epoch": 1.4883517371397792, "grad_norm": 0.7910826415418729, "learning_rate": 1.530124847977657e-06, "loss": 0.3158533573150635, "num_input_tokens_seen": 910320728, "step": 22105, "train_runtime": 85166.585, "train_tokens_per_second": 10688.708 }, { "epoch": 1.4886883921357392, "grad_norm": 0.7370234561984639, "learning_rate": 1.528221596550014e-06, "loss": 0.28954010009765624, "num_input_tokens_seen": 910525384, "step": 22110, "train_runtime": 85186.4211, "train_tokens_per_second": 10688.621 }, { "epoch": 1.4890250471316995, "grad_norm": 0.7291656679053375, "learning_rate": 1.5263193159941331e-06, "loss": 0.29694533348083496, "num_input_tokens_seen": 910732704, "step": 22115, "train_runtime": 85207.0214, "train_tokens_per_second": 10688.47 }, { "epoch": 1.4893617021276595, "grad_norm": 0.7134335403640398, "learning_rate": 1.5244180068419783e-06, "loss": 0.28150248527526855, "num_input_tokens_seen": 910940448, "step": 22120, "train_runtime": 85226.9321, "train_tokens_per_second": 10688.411 }, { "epoch": 1.4896983571236198, "grad_norm": 0.7859003194478204, "learning_rate": 1.5225176696252453e-06, "loss": 0.32440981864929197, "num_input_tokens_seen": 911141064, "step": 22125, "train_runtime": 85248.5316, "train_tokens_per_second": 10688.056 }, { "epoch": 1.4900350121195798, "grad_norm": 0.7563186012210898, "learning_rate": 1.5206183048753575e-06, "loss": 0.3043471097946167, "num_input_tokens_seen": 911342472, "step": 22130, "train_runtime": 85267.5777, "train_tokens_per_second": 10688.031 }, { "epoch": 1.49037166711554, "grad_norm": 0.8575867005026148, "learning_rate": 1.5187199131234653e-06, "loss": 0.34398784637451174, "num_input_tokens_seen": 911549936, "step": 22135, "train_runtime": 85286.5714, "train_tokens_per_second": 10688.083 }, { "epoch": 1.4907083221115, "grad_norm": 0.7762420951704125, "learning_rate": 1.5168224949004484e-06, "loss": 0.3003726005554199, "num_input_tokens_seen": 911747904, "step": 22140, "train_runtime": 85306.2916, "train_tokens_per_second": 10687.933 }, { "epoch": 1.4910449771074603, "grad_norm": 0.6807238116336713, "learning_rate": 1.514926050736914e-06, "loss": 0.27695982456207274, "num_input_tokens_seen": 911959640, "step": 22145, "train_runtime": 85326.7803, "train_tokens_per_second": 10687.848 }, { "epoch": 1.4913816321034203, "grad_norm": 0.6917282684662841, "learning_rate": 1.5130305811631945e-06, "loss": 0.30359063148498533, "num_input_tokens_seen": 912170872, "step": 22150, "train_runtime": 85345.6325, "train_tokens_per_second": 10687.962 }, { "epoch": 1.4917182870993806, "grad_norm": 0.7680852602736368, "learning_rate": 1.5111360867093571e-06, "loss": 0.30828309059143066, "num_input_tokens_seen": 912382224, "step": 22155, "train_runtime": 85364.1295, "train_tokens_per_second": 10688.122 }, { "epoch": 1.4920549420953406, "grad_norm": 0.6982164645963391, "learning_rate": 1.5092425679051848e-06, "loss": 0.2788836479187012, "num_input_tokens_seen": 912590704, "step": 22160, "train_runtime": 85381.7, "train_tokens_per_second": 10688.364 }, { "epoch": 1.4923915970913009, "grad_norm": 0.7459951760798222, "learning_rate": 1.5073500252801988e-06, "loss": 0.31992130279541015, "num_input_tokens_seen": 912801032, "step": 22165, "train_runtime": 85399.1311, "train_tokens_per_second": 10688.645 }, { "epoch": 1.492728252087261, "grad_norm": 0.7406992888069666, "learning_rate": 1.5054584593636412e-06, "loss": 0.2983019590377808, "num_input_tokens_seen": 913015888, "step": 22170, "train_runtime": 85417.5308, "train_tokens_per_second": 10688.858 }, { "epoch": 1.4930649070832211, "grad_norm": 0.7605521187987607, "learning_rate": 1.5035678706844814e-06, "loss": 0.31116199493408203, "num_input_tokens_seen": 913220248, "step": 22175, "train_runtime": 85436.7753, "train_tokens_per_second": 10688.843 }, { "epoch": 1.4934015620791812, "grad_norm": 0.6947535535791634, "learning_rate": 1.501678259771418e-06, "loss": 0.3082144737243652, "num_input_tokens_seen": 913430168, "step": 22180, "train_runtime": 85456.8022, "train_tokens_per_second": 10688.794 }, { "epoch": 1.4937382170751414, "grad_norm": 0.7540105062620694, "learning_rate": 1.499789627152874e-06, "loss": 0.3095115661621094, "num_input_tokens_seen": 913639680, "step": 22185, "train_runtime": 85475.1604, "train_tokens_per_second": 10688.95 }, { "epoch": 1.4940748720711015, "grad_norm": 0.7317024045630593, "learning_rate": 1.497901973356999e-06, "loss": 0.26853582859039304, "num_input_tokens_seen": 913849080, "step": 22190, "train_runtime": 85493.565, "train_tokens_per_second": 10689.098 }, { "epoch": 1.4944115270670617, "grad_norm": 0.6328691609046814, "learning_rate": 1.4960152989116694e-06, "loss": 0.2929676055908203, "num_input_tokens_seen": 914057720, "step": 22195, "train_runtime": 85511.5202, "train_tokens_per_second": 10689.293 }, { "epoch": 1.4947481820630217, "grad_norm": 0.7383497439761262, "learning_rate": 1.4941296043444869e-06, "loss": 0.31284284591674805, "num_input_tokens_seen": 914253232, "step": 22200, "train_runtime": 85532.307, "train_tokens_per_second": 10688.981 }, { "epoch": 1.495084837058982, "grad_norm": 0.6407530078251692, "learning_rate": 1.4922448901827847e-06, "loss": 0.2849703311920166, "num_input_tokens_seen": 914466560, "step": 22205, "train_runtime": 85552.9408, "train_tokens_per_second": 10688.897 }, { "epoch": 1.495421492054942, "grad_norm": 0.8078395296164274, "learning_rate": 1.4903611569536103e-06, "loss": 0.2705158948898315, "num_input_tokens_seen": 914651792, "step": 22210, "train_runtime": 85572.5564, "train_tokens_per_second": 10688.611 }, { "epoch": 1.4957581470509023, "grad_norm": 0.7246810996841224, "learning_rate": 1.488478405183748e-06, "loss": 0.30737733840942383, "num_input_tokens_seen": 914848640, "step": 22215, "train_runtime": 85592.1725, "train_tokens_per_second": 10688.461 }, { "epoch": 1.4960948020468623, "grad_norm": 0.7089458216578642, "learning_rate": 1.4865966353997024e-06, "loss": 0.2997529745101929, "num_input_tokens_seen": 915063256, "step": 22220, "train_runtime": 85611.1385, "train_tokens_per_second": 10688.6 }, { "epoch": 1.4964314570428225, "grad_norm": 0.6393158521719448, "learning_rate": 1.4847158481277047e-06, "loss": 0.2819270133972168, "num_input_tokens_seen": 915270568, "step": 22225, "train_runtime": 85629.7535, "train_tokens_per_second": 10688.698 }, { "epoch": 1.4967681120387826, "grad_norm": 0.8284079625333318, "learning_rate": 1.48283604389371e-06, "loss": 0.27483839988708497, "num_input_tokens_seen": 915465744, "step": 22230, "train_runtime": 85649.3737, "train_tokens_per_second": 10688.528 }, { "epoch": 1.4971047670347428, "grad_norm": 0.6493922611959544, "learning_rate": 1.480957223223401e-06, "loss": 0.2871537685394287, "num_input_tokens_seen": 915673128, "step": 22235, "train_runtime": 85667.9752, "train_tokens_per_second": 10688.628 }, { "epoch": 1.497441422030703, "grad_norm": 0.7381623399581103, "learning_rate": 1.4790793866421826e-06, "loss": 0.32456955909729, "num_input_tokens_seen": 915872992, "step": 22240, "train_runtime": 85686.1323, "train_tokens_per_second": 10688.696 }, { "epoch": 1.497778077026663, "grad_norm": 0.8609759923968078, "learning_rate": 1.4772025346751862e-06, "loss": 0.3029127597808838, "num_input_tokens_seen": 916077456, "step": 22245, "train_runtime": 85704.6657, "train_tokens_per_second": 10688.77 }, { "epoch": 1.4981147320226231, "grad_norm": 0.6284411158427649, "learning_rate": 1.475326667847266e-06, "loss": 0.30434632301330566, "num_input_tokens_seen": 916284800, "step": 22250, "train_runtime": 85723.5194, "train_tokens_per_second": 10688.838 }, { "epoch": 1.4984513870185834, "grad_norm": 0.7401265317105604, "learning_rate": 1.4734517866830073e-06, "loss": 0.30623493194580076, "num_input_tokens_seen": 916497536, "step": 22255, "train_runtime": 85742.097, "train_tokens_per_second": 10689.003 }, { "epoch": 1.4987880420145436, "grad_norm": 0.7227189944274108, "learning_rate": 1.4715778917067081e-06, "loss": 0.30799117088317873, "num_input_tokens_seen": 916699688, "step": 22260, "train_runtime": 85761.735, "train_tokens_per_second": 10688.913 }, { "epoch": 1.4991246970105037, "grad_norm": 0.6419483470921444, "learning_rate": 1.4697049834424016e-06, "loss": 0.2864984512329102, "num_input_tokens_seen": 916903456, "step": 22265, "train_runtime": 85780.5928, "train_tokens_per_second": 10688.938 }, { "epoch": 1.4994613520064637, "grad_norm": 0.7847012961366526, "learning_rate": 1.4678330624138387e-06, "loss": 0.2880880355834961, "num_input_tokens_seen": 917101408, "step": 22270, "train_runtime": 85799.0763, "train_tokens_per_second": 10688.943 }, { "epoch": 1.499798007002424, "grad_norm": 0.6899539232366066, "learning_rate": 1.465962129144497e-06, "loss": 0.29935903549194337, "num_input_tokens_seen": 917306056, "step": 22275, "train_runtime": 85818.0959, "train_tokens_per_second": 10688.958 }, { "epoch": 1.5001346619983842, "grad_norm": 0.7948352020776431, "learning_rate": 1.4640921841575766e-06, "loss": 0.32486002445220946, "num_input_tokens_seen": 917523368, "step": 22280, "train_runtime": 85836.2929, "train_tokens_per_second": 10689.224 }, { "epoch": 1.5004713169943442, "grad_norm": 0.6774691530248791, "learning_rate": 1.4622232279760018e-06, "loss": 0.28789291381835935, "num_input_tokens_seen": 917728104, "step": 22285, "train_runtime": 85854.2397, "train_tokens_per_second": 10689.374 }, { "epoch": 1.5008079719903042, "grad_norm": 0.7413217102178233, "learning_rate": 1.4603552611224202e-06, "loss": 0.3215296745300293, "num_input_tokens_seen": 917924816, "step": 22290, "train_runtime": 85873.0599, "train_tokens_per_second": 10689.322 }, { "epoch": 1.5011446269862645, "grad_norm": 0.714358761083531, "learning_rate": 1.4584882841192027e-06, "loss": 0.32076306343078614, "num_input_tokens_seen": 918130520, "step": 22295, "train_runtime": 85892.8607, "train_tokens_per_second": 10689.253 }, { "epoch": 1.5014812819822247, "grad_norm": 0.7174470118489766, "learning_rate": 1.456622297488442e-06, "loss": 0.2820044755935669, "num_input_tokens_seen": 918328328, "step": 22300, "train_runtime": 85911.8937, "train_tokens_per_second": 10689.187 }, { "epoch": 1.5018179369781848, "grad_norm": 0.8157266270103604, "learning_rate": 1.4547573017519595e-06, "loss": 0.29525682926177976, "num_input_tokens_seen": 918525928, "step": 22305, "train_runtime": 85931.0996, "train_tokens_per_second": 10689.098 }, { "epoch": 1.5021545919741448, "grad_norm": 0.7628913616593894, "learning_rate": 1.4528932974312897e-06, "loss": 0.28474652767181396, "num_input_tokens_seen": 918744088, "step": 22310, "train_runtime": 85951.2188, "train_tokens_per_second": 10689.134 }, { "epoch": 1.502491246970105, "grad_norm": 0.7968660425096333, "learning_rate": 1.4510302850477005e-06, "loss": 0.29343585968017577, "num_input_tokens_seen": 918949288, "step": 22315, "train_runtime": 85970.1506, "train_tokens_per_second": 10689.167 }, { "epoch": 1.5028279019660653, "grad_norm": 0.7220836033024622, "learning_rate": 1.4491682651221746e-06, "loss": 0.2864638328552246, "num_input_tokens_seen": 919145152, "step": 22320, "train_runtime": 85989.5, "train_tokens_per_second": 10689.039 }, { "epoch": 1.5031645569620253, "grad_norm": 0.7847412201497547, "learning_rate": 1.447307238175421e-06, "loss": 0.30025382041931153, "num_input_tokens_seen": 919340744, "step": 22325, "train_runtime": 86008.3451, "train_tokens_per_second": 10688.971 }, { "epoch": 1.5035012119579854, "grad_norm": 0.6935174088521906, "learning_rate": 1.4454472047278688e-06, "loss": 0.29350056648254397, "num_input_tokens_seen": 919540456, "step": 22330, "train_runtime": 86029.8547, "train_tokens_per_second": 10688.62 }, { "epoch": 1.5038378669539456, "grad_norm": 0.6850721028752332, "learning_rate": 1.443588165299672e-06, "loss": 0.27257351875305175, "num_input_tokens_seen": 919754264, "step": 22335, "train_runtime": 86050.5725, "train_tokens_per_second": 10688.532 }, { "epoch": 1.5041745219499059, "grad_norm": 0.7379524376104567, "learning_rate": 1.4417301204107037e-06, "loss": 0.310164737701416, "num_input_tokens_seen": 919962344, "step": 22340, "train_runtime": 86068.9659, "train_tokens_per_second": 10688.665 }, { "epoch": 1.504511176945866, "grad_norm": 0.7734467244871377, "learning_rate": 1.4398730705805607e-06, "loss": 0.2991847276687622, "num_input_tokens_seen": 920171928, "step": 22345, "train_runtime": 86087.4467, "train_tokens_per_second": 10688.805 }, { "epoch": 1.504847831941826, "grad_norm": 0.7119546644421672, "learning_rate": 1.43801701632856e-06, "loss": 0.2983027458190918, "num_input_tokens_seen": 920384512, "step": 22350, "train_runtime": 86106.6024, "train_tokens_per_second": 10688.896 }, { "epoch": 1.5051844869377862, "grad_norm": 0.744291934748754, "learning_rate": 1.436161958173745e-06, "loss": 0.33117592334747314, "num_input_tokens_seen": 920594504, "step": 22355, "train_runtime": 86125.6166, "train_tokens_per_second": 10688.974 }, { "epoch": 1.5055211419337464, "grad_norm": 0.6835692189106478, "learning_rate": 1.4343078966348718e-06, "loss": 0.3050952911376953, "num_input_tokens_seen": 920794584, "step": 22360, "train_runtime": 86145.429, "train_tokens_per_second": 10688.839 }, { "epoch": 1.5058577969297064, "grad_norm": 0.7287500551085504, "learning_rate": 1.432454832230426e-06, "loss": 0.2859179973602295, "num_input_tokens_seen": 921011520, "step": 22365, "train_runtime": 86165.6688, "train_tokens_per_second": 10688.845 }, { "epoch": 1.5061944519256665, "grad_norm": 0.6647599974911699, "learning_rate": 1.4306027654786103e-06, "loss": 0.280266261100769, "num_input_tokens_seen": 921224112, "step": 22370, "train_runtime": 86184.8269, "train_tokens_per_second": 10688.936 }, { "epoch": 1.5065311069216267, "grad_norm": 0.6959995479299819, "learning_rate": 1.4287516968973491e-06, "loss": 0.3144621610641479, "num_input_tokens_seen": 921427904, "step": 22375, "train_runtime": 86203.5639, "train_tokens_per_second": 10688.977 }, { "epoch": 1.506867761917587, "grad_norm": 0.7685566972467351, "learning_rate": 1.4269016270042884e-06, "loss": 0.32176733016967773, "num_input_tokens_seen": 921637344, "step": 22380, "train_runtime": 86225.2245, "train_tokens_per_second": 10688.721 }, { "epoch": 1.507204416913547, "grad_norm": 0.7984678835842501, "learning_rate": 1.425052556316794e-06, "loss": 0.2911965847015381, "num_input_tokens_seen": 921842376, "step": 22385, "train_runtime": 86245.0828, "train_tokens_per_second": 10688.637 }, { "epoch": 1.507541071909507, "grad_norm": 0.8525040224849971, "learning_rate": 1.4232044853519522e-06, "loss": 0.31941063404083253, "num_input_tokens_seen": 922037392, "step": 22390, "train_runtime": 86265.3464, "train_tokens_per_second": 10688.387 }, { "epoch": 1.5078777269054673, "grad_norm": 0.6435357571267204, "learning_rate": 1.4213574146265708e-06, "loss": 0.29373559951782224, "num_input_tokens_seen": 922232216, "step": 22395, "train_runtime": 86283.142, "train_tokens_per_second": 10688.44 }, { "epoch": 1.5082143819014275, "grad_norm": 0.7364828909460666, "learning_rate": 1.4195113446571752e-06, "loss": 0.33255825042724607, "num_input_tokens_seen": 922440296, "step": 22400, "train_runtime": 86302.4337, "train_tokens_per_second": 10688.462 }, { "epoch": 1.5085510368973876, "grad_norm": 0.7407210767897998, "learning_rate": 1.417666275960018e-06, "loss": 0.2821336269378662, "num_input_tokens_seen": 922656912, "step": 22405, "train_runtime": 86320.5406, "train_tokens_per_second": 10688.73 }, { "epoch": 1.5088876918933476, "grad_norm": 0.6533940308625878, "learning_rate": 1.4158222090510605e-06, "loss": 0.2710870265960693, "num_input_tokens_seen": 922870672, "step": 22410, "train_runtime": 86338.7412, "train_tokens_per_second": 10688.952 }, { "epoch": 1.5092243468893078, "grad_norm": 0.6851381164450328, "learning_rate": 1.4139791444459945e-06, "loss": 0.3149515151977539, "num_input_tokens_seen": 923076584, "step": 22415, "train_runtime": 86356.9683, "train_tokens_per_second": 10689.08 }, { "epoch": 1.509561001885268, "grad_norm": 0.8480211216639547, "learning_rate": 1.4121370826602254e-06, "loss": 0.30541081428527833, "num_input_tokens_seen": 923273480, "step": 22420, "train_runtime": 86376.6792, "train_tokens_per_second": 10688.921 }, { "epoch": 1.5098976568812281, "grad_norm": 0.6610347891575269, "learning_rate": 1.4102960242088803e-06, "loss": 0.30448737144470217, "num_input_tokens_seen": 923481344, "step": 22425, "train_runtime": 86397.422, "train_tokens_per_second": 10688.76 }, { "epoch": 1.5102343118771882, "grad_norm": 0.7262921396841989, "learning_rate": 1.4084559696068057e-06, "loss": 0.29460821151733396, "num_input_tokens_seen": 923686568, "step": 22430, "train_runtime": 86416.4565, "train_tokens_per_second": 10688.781 }, { "epoch": 1.5105709668731484, "grad_norm": 0.697468815943985, "learning_rate": 1.406616919368567e-06, "loss": 0.3026840925216675, "num_input_tokens_seen": 923893440, "step": 22435, "train_runtime": 86436.7833, "train_tokens_per_second": 10688.661 }, { "epoch": 1.5109076218691087, "grad_norm": 0.7866588247998423, "learning_rate": 1.4047788740084474e-06, "loss": 0.2911728858947754, "num_input_tokens_seen": 924103848, "step": 22440, "train_runtime": 86455.756, "train_tokens_per_second": 10688.749 }, { "epoch": 1.5112442768650687, "grad_norm": 0.6266261100163433, "learning_rate": 1.402941834040452e-06, "loss": 0.28525476455688475, "num_input_tokens_seen": 924320544, "step": 22445, "train_runtime": 86474.2049, "train_tokens_per_second": 10688.974 }, { "epoch": 1.5115809318610287, "grad_norm": 0.7065831275636264, "learning_rate": 1.4011057999783006e-06, "loss": 0.280762767791748, "num_input_tokens_seen": 924518416, "step": 22450, "train_runtime": 86493.0332, "train_tokens_per_second": 10688.935 }, { "epoch": 1.511917586856989, "grad_norm": 0.7084075550377027, "learning_rate": 1.3992707723354398e-06, "loss": 0.29846844673156736, "num_input_tokens_seen": 924726816, "step": 22455, "train_runtime": 86512.4047, "train_tokens_per_second": 10688.951 }, { "epoch": 1.5122542418529492, "grad_norm": 0.6715250038819348, "learning_rate": 1.397436751625022e-06, "loss": 0.28617563247680666, "num_input_tokens_seen": 924929592, "step": 22460, "train_runtime": 86533.6288, "train_tokens_per_second": 10688.672 }, { "epoch": 1.5125908968489092, "grad_norm": 0.8098136564041258, "learning_rate": 1.3956037383599308e-06, "loss": 0.29217915534973143, "num_input_tokens_seen": 925138496, "step": 22465, "train_runtime": 86552.9668, "train_tokens_per_second": 10688.698 }, { "epoch": 1.5129275518448693, "grad_norm": 0.6966457732779722, "learning_rate": 1.39377173305276e-06, "loss": 0.28122270107269287, "num_input_tokens_seen": 925334912, "step": 22470, "train_runtime": 86571.8088, "train_tokens_per_second": 10688.64 }, { "epoch": 1.5132642068408295, "grad_norm": 0.7259357258929426, "learning_rate": 1.3919407362158254e-06, "loss": 0.3235860586166382, "num_input_tokens_seen": 925552040, "step": 22475, "train_runtime": 86591.9645, "train_tokens_per_second": 10688.66 }, { "epoch": 1.5136008618367898, "grad_norm": 0.7833274078353885, "learning_rate": 1.3901107483611582e-06, "loss": 0.28696379661560056, "num_input_tokens_seen": 925746912, "step": 22480, "train_runtime": 86611.1405, "train_tokens_per_second": 10688.543 }, { "epoch": 1.5139375168327498, "grad_norm": 0.67768845269076, "learning_rate": 1.3882817700005091e-06, "loss": 0.29239003658294677, "num_input_tokens_seen": 925952144, "step": 22485, "train_runtime": 86632.8874, "train_tokens_per_second": 10688.229 }, { "epoch": 1.5142741718287098, "grad_norm": 0.731665733867748, "learning_rate": 1.3864538016453466e-06, "loss": 0.2994621515274048, "num_input_tokens_seen": 926142088, "step": 22490, "train_runtime": 86652.8907, "train_tokens_per_second": 10687.954 }, { "epoch": 1.51461082682467, "grad_norm": 0.8507040318210349, "learning_rate": 1.384626843806855e-06, "loss": 0.3088738203048706, "num_input_tokens_seen": 926332728, "step": 22495, "train_runtime": 86671.0915, "train_tokens_per_second": 10687.909 }, { "epoch": 1.5149474818206303, "grad_norm": 0.806324007094122, "learning_rate": 1.3828008969959367e-06, "loss": 0.3060689687728882, "num_input_tokens_seen": 926547936, "step": 22500, "train_runtime": 86689.4433, "train_tokens_per_second": 10688.129 }, { "epoch": 1.5152841368165904, "grad_norm": 0.8305502332382335, "learning_rate": 1.3809759617232166e-06, "loss": 0.28897905349731445, "num_input_tokens_seen": 926750224, "step": 22505, "train_runtime": 86709.516, "train_tokens_per_second": 10687.988 }, { "epoch": 1.5156207918125504, "grad_norm": 0.6548970211845272, "learning_rate": 1.3791520384990247e-06, "loss": 0.2867670297622681, "num_input_tokens_seen": 926951968, "step": 22510, "train_runtime": 86729.0764, "train_tokens_per_second": 10687.903 }, { "epoch": 1.5159574468085106, "grad_norm": 0.6717604774171746, "learning_rate": 1.3773291278334216e-06, "loss": 0.2973329067230225, "num_input_tokens_seen": 927156024, "step": 22515, "train_runtime": 86748.762, "train_tokens_per_second": 10687.83 }, { "epoch": 1.5162941018044709, "grad_norm": 0.7233598920275833, "learning_rate": 1.3755072302361754e-06, "loss": 0.30509514808654786, "num_input_tokens_seen": 927372904, "step": 22520, "train_runtime": 86767.0394, "train_tokens_per_second": 10688.078 }, { "epoch": 1.516630756800431, "grad_norm": 0.7239032620344121, "learning_rate": 1.3736863462167749e-06, "loss": 0.28715968132019043, "num_input_tokens_seen": 927566368, "step": 22525, "train_runtime": 86787.7989, "train_tokens_per_second": 10687.751 }, { "epoch": 1.516967411796391, "grad_norm": 0.711740904506671, "learning_rate": 1.3718664762844242e-06, "loss": 0.28755037784576415, "num_input_tokens_seen": 927764032, "step": 22530, "train_runtime": 86806.3714, "train_tokens_per_second": 10687.741 }, { "epoch": 1.5173040667923512, "grad_norm": 0.7229285348871611, "learning_rate": 1.370047620948044e-06, "loss": 0.2904862880706787, "num_input_tokens_seen": 927973712, "step": 22535, "train_runtime": 86826.0333, "train_tokens_per_second": 10687.736 }, { "epoch": 1.5176407217883114, "grad_norm": 0.752511242302152, "learning_rate": 1.368229780716272e-06, "loss": 0.31262907981872556, "num_input_tokens_seen": 928178560, "step": 22540, "train_runtime": 86844.0083, "train_tokens_per_second": 10687.883 }, { "epoch": 1.5179773767842715, "grad_norm": 0.7760914746920443, "learning_rate": 1.3664129560974604e-06, "loss": 0.28988137245178225, "num_input_tokens_seen": 928381752, "step": 22545, "train_runtime": 86862.4754, "train_tokens_per_second": 10687.95 }, { "epoch": 1.5183140317802315, "grad_norm": 0.7349664559692933, "learning_rate": 1.3645971475996777e-06, "loss": 0.2929499626159668, "num_input_tokens_seen": 928576008, "step": 22550, "train_runtime": 86881.847, "train_tokens_per_second": 10687.802 }, { "epoch": 1.5186506867761917, "grad_norm": 0.7701174545295976, "learning_rate": 1.3627823557307135e-06, "loss": 0.2972066879272461, "num_input_tokens_seen": 928792888, "step": 22555, "train_runtime": 86901.9546, "train_tokens_per_second": 10687.825 }, { "epoch": 1.518987341772152, "grad_norm": 0.6369428037751362, "learning_rate": 1.3609685809980616e-06, "loss": 0.30274205207824706, "num_input_tokens_seen": 929008672, "step": 22560, "train_runtime": 86921.9958, "train_tokens_per_second": 10687.843 }, { "epoch": 1.519323996768112, "grad_norm": 0.7034541344252039, "learning_rate": 1.3591558239089443e-06, "loss": 0.2809900760650635, "num_input_tokens_seen": 929218792, "step": 22565, "train_runtime": 86943.9818, "train_tokens_per_second": 10687.557 }, { "epoch": 1.519660651764072, "grad_norm": 0.8123995758179117, "learning_rate": 1.3573440849702902e-06, "loss": 0.31931304931640625, "num_input_tokens_seen": 929434696, "step": 22570, "train_runtime": 86962.9095, "train_tokens_per_second": 10687.714 }, { "epoch": 1.5199973067600323, "grad_norm": 0.7027079820494597, "learning_rate": 1.3555333646887476e-06, "loss": 0.3073214769363403, "num_input_tokens_seen": 929644560, "step": 22575, "train_runtime": 86980.9874, "train_tokens_per_second": 10687.905 }, { "epoch": 1.5203339617559926, "grad_norm": 0.6859904356825381, "learning_rate": 1.3537236635706779e-06, "loss": 0.29469637870788573, "num_input_tokens_seen": 929860968, "step": 22580, "train_runtime": 86999.9526, "train_tokens_per_second": 10688.063 }, { "epoch": 1.5206706167519526, "grad_norm": 0.8232463493119203, "learning_rate": 1.351914982122159e-06, "loss": 0.2791555404663086, "num_input_tokens_seen": 930073064, "step": 22585, "train_runtime": 87019.9718, "train_tokens_per_second": 10688.041 }, { "epoch": 1.5210072717479126, "grad_norm": 0.7473711291999041, "learning_rate": 1.3501073208489823e-06, "loss": 0.2994969129562378, "num_input_tokens_seen": 930277912, "step": 22590, "train_runtime": 87037.6229, "train_tokens_per_second": 10688.227 }, { "epoch": 1.5213439267438729, "grad_norm": 0.6863446486871595, "learning_rate": 1.3483006802566546e-06, "loss": 0.29572582244873047, "num_input_tokens_seen": 930487704, "step": 22595, "train_runtime": 87056.2928, "train_tokens_per_second": 10688.345 }, { "epoch": 1.5216805817398331, "grad_norm": 0.7563992907934255, "learning_rate": 1.3464950608503957e-06, "loss": 0.31183347702026365, "num_input_tokens_seen": 930690000, "step": 22600, "train_runtime": 87075.8092, "train_tokens_per_second": 10688.273 }, { "epoch": 1.5220172367357931, "grad_norm": 0.813269286985361, "learning_rate": 1.344690463135146e-06, "loss": 0.30864078998565675, "num_input_tokens_seen": 930894720, "step": 22605, "train_runtime": 87095.7095, "train_tokens_per_second": 10688.181 }, { "epoch": 1.5223538917317532, "grad_norm": 0.7571139289989814, "learning_rate": 1.3428868876155493e-06, "loss": 0.3277894496917725, "num_input_tokens_seen": 931085864, "step": 22610, "train_runtime": 87115.2701, "train_tokens_per_second": 10687.975 }, { "epoch": 1.5226905467277134, "grad_norm": 0.6007474770197828, "learning_rate": 1.3410843347959745e-06, "loss": 0.2805646419525146, "num_input_tokens_seen": 931289328, "step": 22615, "train_runtime": 87134.0347, "train_tokens_per_second": 10688.009 }, { "epoch": 1.5230272017236737, "grad_norm": 0.6684107643587738, "learning_rate": 1.3392828051804979e-06, "loss": 0.3072920560836792, "num_input_tokens_seen": 931503488, "step": 22620, "train_runtime": 87153.5937, "train_tokens_per_second": 10688.067 }, { "epoch": 1.5233638567196337, "grad_norm": 0.6681946869552154, "learning_rate": 1.3374822992729114e-06, "loss": 0.319638729095459, "num_input_tokens_seen": 931710960, "step": 22625, "train_runtime": 87175.2913, "train_tokens_per_second": 10687.787 }, { "epoch": 1.5237005117155937, "grad_norm": 0.7641583354115418, "learning_rate": 1.3356828175767212e-06, "loss": 0.30330643653869627, "num_input_tokens_seen": 931908960, "step": 22630, "train_runtime": 87194.4165, "train_tokens_per_second": 10687.714 }, { "epoch": 1.524037166711554, "grad_norm": 0.6861555528597391, "learning_rate": 1.3338843605951462e-06, "loss": 0.27744555473327637, "num_input_tokens_seen": 932121840, "step": 22635, "train_runtime": 87214.9872, "train_tokens_per_second": 10687.634 }, { "epoch": 1.5243738217075142, "grad_norm": 0.6875952449492923, "learning_rate": 1.33208692883112e-06, "loss": 0.28685009479522705, "num_input_tokens_seen": 932342864, "step": 22640, "train_runtime": 87234.6159, "train_tokens_per_second": 10687.763 }, { "epoch": 1.5247104767034743, "grad_norm": 0.6122380812286791, "learning_rate": 1.3302905227872876e-06, "loss": 0.2792071342468262, "num_input_tokens_seen": 932562384, "step": 22645, "train_runtime": 87253.815, "train_tokens_per_second": 10687.927 }, { "epoch": 1.5250471316994343, "grad_norm": 0.7229692397299002, "learning_rate": 1.328495142966007e-06, "loss": 0.30457363128662107, "num_input_tokens_seen": 932762584, "step": 22650, "train_runtime": 87272.0025, "train_tokens_per_second": 10687.993 }, { "epoch": 1.5253837866953945, "grad_norm": 0.6798372170969448, "learning_rate": 1.3267007898693552e-06, "loss": 0.2921234130859375, "num_input_tokens_seen": 932981232, "step": 22655, "train_runtime": 87291.9931, "train_tokens_per_second": 10688.051 }, { "epoch": 1.5257204416913548, "grad_norm": 0.7221709050219239, "learning_rate": 1.324907463999111e-06, "loss": 0.31026620864868165, "num_input_tokens_seen": 933193424, "step": 22660, "train_runtime": 87310.8942, "train_tokens_per_second": 10688.167 }, { "epoch": 1.5260570966873148, "grad_norm": 0.7338154834116465, "learning_rate": 1.3231151658567776e-06, "loss": 0.3099897146224976, "num_input_tokens_seen": 933392848, "step": 22665, "train_runtime": 87328.1584, "train_tokens_per_second": 10688.338 }, { "epoch": 1.5263937516832748, "grad_norm": 0.7029704643426763, "learning_rate": 1.321323895943563e-06, "loss": 0.3014364242553711, "num_input_tokens_seen": 933599544, "step": 22670, "train_runtime": 87347.5893, "train_tokens_per_second": 10688.326 }, { "epoch": 1.526730406679235, "grad_norm": 0.6447244334697039, "learning_rate": 1.3195336547603905e-06, "loss": 0.3147465705871582, "num_input_tokens_seen": 933806000, "step": 22675, "train_runtime": 87367.6007, "train_tokens_per_second": 10688.241 }, { "epoch": 1.5270670616751953, "grad_norm": 0.7004536540956539, "learning_rate": 1.3177444428078951e-06, "loss": 0.289259934425354, "num_input_tokens_seen": 934003768, "step": 22680, "train_runtime": 87385.8815, "train_tokens_per_second": 10688.269 }, { "epoch": 1.5274037166711554, "grad_norm": 0.7866485727825837, "learning_rate": 1.3159562605864245e-06, "loss": 0.30142908096313475, "num_input_tokens_seen": 934218744, "step": 22685, "train_runtime": 87406.1074, "train_tokens_per_second": 10688.255 }, { "epoch": 1.5277403716671154, "grad_norm": 0.7743490933985209, "learning_rate": 1.3141691085960385e-06, "loss": 0.290567684173584, "num_input_tokens_seen": 934441472, "step": 22690, "train_runtime": 87425.8028, "train_tokens_per_second": 10688.395 }, { "epoch": 1.5280770266630757, "grad_norm": 0.7082711922978413, "learning_rate": 1.3123829873365073e-06, "loss": 0.28253722190856934, "num_input_tokens_seen": 934642408, "step": 22695, "train_runtime": 87443.7267, "train_tokens_per_second": 10688.502 }, { "epoch": 1.528413681659036, "grad_norm": 0.7200554935746679, "learning_rate": 1.3105978973073136e-06, "loss": 0.2846479892730713, "num_input_tokens_seen": 934847192, "step": 22700, "train_runtime": 87464.4964, "train_tokens_per_second": 10688.305 }, { "epoch": 1.528750336654996, "grad_norm": 0.7423934623083271, "learning_rate": 1.3088138390076565e-06, "loss": 0.310698413848877, "num_input_tokens_seen": 935054816, "step": 22705, "train_runtime": 87483.5647, "train_tokens_per_second": 10688.348 }, { "epoch": 1.529086991650956, "grad_norm": 0.770891449889052, "learning_rate": 1.3070308129364357e-06, "loss": 0.290645694732666, "num_input_tokens_seen": 935260360, "step": 22710, "train_runtime": 87504.1876, "train_tokens_per_second": 10688.178 }, { "epoch": 1.5294236466469162, "grad_norm": 0.8928141205975607, "learning_rate": 1.3052488195922736e-06, "loss": 0.28851842880249023, "num_input_tokens_seen": 935455952, "step": 22715, "train_runtime": 87522.4176, "train_tokens_per_second": 10688.187 }, { "epoch": 1.5297603016428765, "grad_norm": 0.7534430015897414, "learning_rate": 1.3034678594734972e-06, "loss": 0.2852447032928467, "num_input_tokens_seen": 935666128, "step": 22720, "train_runtime": 87541.6742, "train_tokens_per_second": 10688.237 }, { "epoch": 1.5300969566388365, "grad_norm": 0.8415054984441626, "learning_rate": 1.3016879330781468e-06, "loss": 0.3070669651031494, "num_input_tokens_seen": 935862136, "step": 22725, "train_runtime": 87560.3091, "train_tokens_per_second": 10688.2 }, { "epoch": 1.5304336116347965, "grad_norm": 0.7146982721636285, "learning_rate": 1.2999090409039728e-06, "loss": 0.2986551284790039, "num_input_tokens_seen": 936072312, "step": 22730, "train_runtime": 87580.0852, "train_tokens_per_second": 10688.187 }, { "epoch": 1.5307702666307568, "grad_norm": 0.7292121209689959, "learning_rate": 1.2981311834484367e-06, "loss": 0.31122989654541017, "num_input_tokens_seen": 936280104, "step": 22735, "train_runtime": 87601.4133, "train_tokens_per_second": 10687.957 }, { "epoch": 1.531106921626717, "grad_norm": 0.7245594017899968, "learning_rate": 1.296354361208711e-06, "loss": 0.2801478624343872, "num_input_tokens_seen": 936484656, "step": 22740, "train_runtime": 87621.7007, "train_tokens_per_second": 10687.816 }, { "epoch": 1.531443576622677, "grad_norm": 0.7663779964429049, "learning_rate": 1.294578574681678e-06, "loss": 0.3241244316101074, "num_input_tokens_seen": 936681776, "step": 22745, "train_runtime": 87641.5959, "train_tokens_per_second": 10687.639 }, { "epoch": 1.531780231618637, "grad_norm": 0.7478393413801533, "learning_rate": 1.292803824363929e-06, "loss": 0.2860511302947998, "num_input_tokens_seen": 936889576, "step": 22750, "train_runtime": 87660.7046, "train_tokens_per_second": 10687.68 }, { "epoch": 1.5321168866145973, "grad_norm": 0.7581029240549776, "learning_rate": 1.2910301107517726e-06, "loss": 0.3250305414199829, "num_input_tokens_seen": 937098200, "step": 22755, "train_runtime": 87679.2593, "train_tokens_per_second": 10687.798 }, { "epoch": 1.5324535416105576, "grad_norm": 0.7705566984897931, "learning_rate": 1.2892574343412156e-06, "loss": 0.31759932041168215, "num_input_tokens_seen": 937303368, "step": 22760, "train_runtime": 87696.9424, "train_tokens_per_second": 10687.982 }, { "epoch": 1.5327901966065176, "grad_norm": 0.7101439903456144, "learning_rate": 1.2874857956279858e-06, "loss": 0.30532059669494627, "num_input_tokens_seen": 937502656, "step": 22765, "train_runtime": 87715.195, "train_tokens_per_second": 10688.03 }, { "epoch": 1.5331268516024776, "grad_norm": 0.7656557395023641, "learning_rate": 1.2857151951075147e-06, "loss": 0.30213027000427245, "num_input_tokens_seen": 937712968, "step": 22770, "train_runtime": 87734.5094, "train_tokens_per_second": 10688.074 }, { "epoch": 1.5334635065984379, "grad_norm": 0.6875199807517876, "learning_rate": 1.2839456332749456e-06, "loss": 0.29900507926940917, "num_input_tokens_seen": 937915960, "step": 22775, "train_runtime": 87753.3725, "train_tokens_per_second": 10688.09 }, { "epoch": 1.5338001615943981, "grad_norm": 0.7523938967471095, "learning_rate": 1.2821771106251308e-06, "loss": 0.2957391023635864, "num_input_tokens_seen": 938120144, "step": 22780, "train_runtime": 87772.7121, "train_tokens_per_second": 10688.061 }, { "epoch": 1.5341368165903582, "grad_norm": 0.7465935929863031, "learning_rate": 1.2804096276526312e-06, "loss": 0.2824448347091675, "num_input_tokens_seen": 938323344, "step": 22785, "train_runtime": 87791.2123, "train_tokens_per_second": 10688.124 }, { "epoch": 1.5344734715863182, "grad_norm": 0.7373718838249363, "learning_rate": 1.2786431848517184e-06, "loss": 0.2867497444152832, "num_input_tokens_seen": 938517584, "step": 22790, "train_runtime": 87809.712, "train_tokens_per_second": 10688.084 }, { "epoch": 1.5348101265822784, "grad_norm": 0.7741096145914977, "learning_rate": 1.2768777827163725e-06, "loss": 0.2995618343353271, "num_input_tokens_seen": 938721928, "step": 22795, "train_runtime": 87829.5716, "train_tokens_per_second": 10687.994 }, { "epoch": 1.5351467815782387, "grad_norm": 0.7812809573818749, "learning_rate": 1.2751134217402811e-06, "loss": 0.29545619487762453, "num_input_tokens_seen": 938917000, "step": 22800, "train_runtime": 87848.0501, "train_tokens_per_second": 10687.966 }, { "epoch": 1.5354834365741987, "grad_norm": 0.6781037751859249, "learning_rate": 1.2733501024168465e-06, "loss": 0.2821607828140259, "num_input_tokens_seen": 939124136, "step": 22805, "train_runtime": 87866.672, "train_tokens_per_second": 10688.059 }, { "epoch": 1.5358200915701588, "grad_norm": 0.7919478846300655, "learning_rate": 1.2715878252391695e-06, "loss": 0.30570025444030763, "num_input_tokens_seen": 939319784, "step": 22810, "train_runtime": 87887.0914, "train_tokens_per_second": 10687.801 }, { "epoch": 1.536156746566119, "grad_norm": 0.7410422663336973, "learning_rate": 1.269826590700069e-06, "loss": 0.3011265516281128, "num_input_tokens_seen": 939526088, "step": 22815, "train_runtime": 87905.4156, "train_tokens_per_second": 10687.92 }, { "epoch": 1.5364934015620793, "grad_norm": 0.6926764472929218, "learning_rate": 1.2680663992920684e-06, "loss": 0.28264803886413575, "num_input_tokens_seen": 939735216, "step": 22820, "train_runtime": 87925.5275, "train_tokens_per_second": 10687.854 }, { "epoch": 1.5368300565580393, "grad_norm": 0.9813526276207172, "learning_rate": 1.2663072515073988e-06, "loss": 0.30090985298156736, "num_input_tokens_seen": 939935496, "step": 22825, "train_runtime": 87944.484, "train_tokens_per_second": 10687.828 }, { "epoch": 1.5371667115539993, "grad_norm": 0.7820735476681019, "learning_rate": 1.2645491478380002e-06, "loss": 0.2989997863769531, "num_input_tokens_seen": 940137032, "step": 22830, "train_runtime": 87964.9572, "train_tokens_per_second": 10687.631 }, { "epoch": 1.5375033665499596, "grad_norm": 0.8067856429876834, "learning_rate": 1.2627920887755212e-06, "loss": 0.30141510963439944, "num_input_tokens_seen": 940335432, "step": 22835, "train_runtime": 87984.047, "train_tokens_per_second": 10687.567 }, { "epoch": 1.5378400215459198, "grad_norm": 0.6625337648776294, "learning_rate": 1.261036074811317e-06, "loss": 0.3101222276687622, "num_input_tokens_seen": 940545144, "step": 22840, "train_runtime": 88002.3465, "train_tokens_per_second": 10687.728 }, { "epoch": 1.5381766765418798, "grad_norm": 0.7347898966378387, "learning_rate": 1.2592811064364524e-06, "loss": 0.2954885244369507, "num_input_tokens_seen": 940753104, "step": 22845, "train_runtime": 88023.4081, "train_tokens_per_second": 10687.533 }, { "epoch": 1.5385133315378399, "grad_norm": 0.9146548838819307, "learning_rate": 1.2575271841416963e-06, "loss": 0.32297701835632325, "num_input_tokens_seen": 940934680, "step": 22850, "train_runtime": 88041.8204, "train_tokens_per_second": 10687.361 }, { "epoch": 1.5388499865338001, "grad_norm": 0.7293988181573465, "learning_rate": 1.2557743084175327e-06, "loss": 0.27531468868255615, "num_input_tokens_seen": 941136512, "step": 22855, "train_runtime": 88059.7033, "train_tokens_per_second": 10687.482 }, { "epoch": 1.5391866415297604, "grad_norm": 0.6783492593094387, "learning_rate": 1.254022479754141e-06, "loss": 0.28401646614074705, "num_input_tokens_seen": 941348928, "step": 22860, "train_runtime": 88078.3694, "train_tokens_per_second": 10687.629 }, { "epoch": 1.5395232965257204, "grad_norm": 0.7325901985064041, "learning_rate": 1.252271698641419e-06, "loss": 0.29267206192016604, "num_input_tokens_seen": 941552136, "step": 22865, "train_runtime": 88097.0537, "train_tokens_per_second": 10687.669 }, { "epoch": 1.5398599515216804, "grad_norm": 0.6942996921900834, "learning_rate": 1.2505219655689659e-06, "loss": 0.3121662139892578, "num_input_tokens_seen": 941765216, "step": 22870, "train_runtime": 88115.29, "train_tokens_per_second": 10687.875 }, { "epoch": 1.5401966065176407, "grad_norm": 0.7657068567811363, "learning_rate": 1.2487732810260877e-06, "loss": 0.30160276889801024, "num_input_tokens_seen": 941973256, "step": 22875, "train_runtime": 88135.1208, "train_tokens_per_second": 10687.831 }, { "epoch": 1.540533261513601, "grad_norm": 0.6616794348668936, "learning_rate": 1.2470256455018027e-06, "loss": 0.2843189716339111, "num_input_tokens_seen": 942178840, "step": 22880, "train_runtime": 88154.8188, "train_tokens_per_second": 10687.775 }, { "epoch": 1.540869916509561, "grad_norm": 0.710336739804261, "learning_rate": 1.2452790594848257e-06, "loss": 0.2790225028991699, "num_input_tokens_seen": 942382296, "step": 22885, "train_runtime": 88176.3751, "train_tokens_per_second": 10687.469 }, { "epoch": 1.541206571505521, "grad_norm": 0.8337859575584363, "learning_rate": 1.2435335234635892e-06, "loss": 0.325435209274292, "num_input_tokens_seen": 942586584, "step": 22890, "train_runtime": 88194.5339, "train_tokens_per_second": 10687.585 }, { "epoch": 1.5415432265014812, "grad_norm": 0.7558584784026242, "learning_rate": 1.2417890379262221e-06, "loss": 0.2940948963165283, "num_input_tokens_seen": 942794792, "step": 22895, "train_runtime": 88213.9892, "train_tokens_per_second": 10687.588 }, { "epoch": 1.5418798814974415, "grad_norm": 0.7474871094058765, "learning_rate": 1.2400456033605672e-06, "loss": 0.2647612810134888, "num_input_tokens_seen": 942995880, "step": 22900, "train_runtime": 88232.2166, "train_tokens_per_second": 10687.659 }, { "epoch": 1.5422165364934015, "grad_norm": 0.6733477725697973, "learning_rate": 1.2383032202541706e-06, "loss": 0.3081067562103271, "num_input_tokens_seen": 943196952, "step": 22905, "train_runtime": 88250.6876, "train_tokens_per_second": 10687.701 }, { "epoch": 1.5425531914893615, "grad_norm": 0.7513176268724898, "learning_rate": 1.2365618890942827e-06, "loss": 0.3210129737854004, "num_input_tokens_seen": 943403448, "step": 22910, "train_runtime": 88268.854, "train_tokens_per_second": 10687.841 }, { "epoch": 1.5428898464853218, "grad_norm": 0.7104343300253234, "learning_rate": 1.2348216103678618e-06, "loss": 0.32284820079803467, "num_input_tokens_seen": 943608664, "step": 22915, "train_runtime": 88286.7872, "train_tokens_per_second": 10687.994 }, { "epoch": 1.543226501481282, "grad_norm": 0.8440493969771202, "learning_rate": 1.2330823845615713e-06, "loss": 0.2933905601501465, "num_input_tokens_seen": 943798232, "step": 22920, "train_runtime": 88305.5684, "train_tokens_per_second": 10687.868 }, { "epoch": 1.543563156477242, "grad_norm": 0.7683366152583495, "learning_rate": 1.2313442121617785e-06, "loss": 0.2922946929931641, "num_input_tokens_seen": 944014624, "step": 22925, "train_runtime": 88325.1383, "train_tokens_per_second": 10687.95 }, { "epoch": 1.543899811473202, "grad_norm": 0.739713975269839, "learning_rate": 1.229607093654563e-06, "loss": 0.28192055225372314, "num_input_tokens_seen": 944226424, "step": 22930, "train_runtime": 88344.0039, "train_tokens_per_second": 10688.065 }, { "epoch": 1.5442364664691623, "grad_norm": 0.6703917143648717, "learning_rate": 1.2278710295256974e-06, "loss": 0.30680367946624754, "num_input_tokens_seen": 944441352, "step": 22935, "train_runtime": 88362.4877, "train_tokens_per_second": 10688.261 }, { "epoch": 1.5445731214651226, "grad_norm": 0.671709384901741, "learning_rate": 1.2261360202606725e-06, "loss": 0.2922227382659912, "num_input_tokens_seen": 944658152, "step": 22940, "train_runtime": 88381.0089, "train_tokens_per_second": 10688.474 }, { "epoch": 1.5449097764610826, "grad_norm": 0.7142599892645084, "learning_rate": 1.2244020663446731e-06, "loss": 0.3131686210632324, "num_input_tokens_seen": 944859432, "step": 22945, "train_runtime": 88401.4551, "train_tokens_per_second": 10688.279 }, { "epoch": 1.5452464314570427, "grad_norm": 0.8519933718388665, "learning_rate": 1.222669168262598e-06, "loss": 0.3013161182403564, "num_input_tokens_seen": 945067776, "step": 22950, "train_runtime": 88421.0921, "train_tokens_per_second": 10688.262 }, { "epoch": 1.545583086453003, "grad_norm": 0.6970574138690482, "learning_rate": 1.2209373264990448e-06, "loss": 0.2930248737335205, "num_input_tokens_seen": 945271608, "step": 22955, "train_runtime": 88438.4497, "train_tokens_per_second": 10688.469 }, { "epoch": 1.5459197414489632, "grad_norm": 1.1017280764797441, "learning_rate": 1.2192065415383176e-06, "loss": 0.2914071559906006, "num_input_tokens_seen": 945474576, "step": 22960, "train_runtime": 88458.3369, "train_tokens_per_second": 10688.36 }, { "epoch": 1.5462563964449232, "grad_norm": 0.7365794082566978, "learning_rate": 1.217476813864425e-06, "loss": 0.31507484912872313, "num_input_tokens_seen": 945692696, "step": 22965, "train_runtime": 88478.9276, "train_tokens_per_second": 10688.338 }, { "epoch": 1.5465930514408834, "grad_norm": 0.7041912175614564, "learning_rate": 1.2157481439610801e-06, "loss": 0.270328426361084, "num_input_tokens_seen": 945898560, "step": 22970, "train_runtime": 88498.0365, "train_tokens_per_second": 10688.356 }, { "epoch": 1.5469297064368437, "grad_norm": 0.832507897924473, "learning_rate": 1.2140205323116976e-06, "loss": 0.3029277563095093, "num_input_tokens_seen": 946086144, "step": 22975, "train_runtime": 88516.5863, "train_tokens_per_second": 10688.236 }, { "epoch": 1.5472663614328037, "grad_norm": 0.9988412026801424, "learning_rate": 1.2122939793994043e-06, "loss": 0.2847175121307373, "num_input_tokens_seen": 946289576, "step": 22980, "train_runtime": 88535.6377, "train_tokens_per_second": 10688.234 }, { "epoch": 1.5476030164287637, "grad_norm": 0.7108197849056944, "learning_rate": 1.2105684857070182e-06, "loss": 0.2886810779571533, "num_input_tokens_seen": 946497832, "step": 22985, "train_runtime": 88555.2407, "train_tokens_per_second": 10688.219 }, { "epoch": 1.547939671424724, "grad_norm": 0.7144589066096508, "learning_rate": 1.2088440517170729e-06, "loss": 0.3030792951583862, "num_input_tokens_seen": 946707976, "step": 22990, "train_runtime": 88575.0322, "train_tokens_per_second": 10688.204 }, { "epoch": 1.5482763264206842, "grad_norm": 0.8462596957179587, "learning_rate": 1.2071206779117994e-06, "loss": 0.30989344120025636, "num_input_tokens_seen": 946915952, "step": 22995, "train_runtime": 88594.5165, "train_tokens_per_second": 10688.2 }, { "epoch": 1.5486129814166443, "grad_norm": 0.709792156657596, "learning_rate": 1.2053983647731337e-06, "loss": 0.30201470851898193, "num_input_tokens_seen": 947132408, "step": 23000, "train_runtime": 88612.4223, "train_tokens_per_second": 10688.483 }, { "epoch": 1.5489496364126043, "grad_norm": 0.779939723634734, "learning_rate": 1.2036771127827152e-06, "loss": 0.2990402698516846, "num_input_tokens_seen": 947326800, "step": 23005, "train_runtime": 88630.309, "train_tokens_per_second": 10688.52 }, { "epoch": 1.5492862914085646, "grad_norm": 0.83918231692217, "learning_rate": 1.2019569224218869e-06, "loss": 0.3056324481964111, "num_input_tokens_seen": 947547240, "step": 23010, "train_runtime": 88648.4007, "train_tokens_per_second": 10688.825 }, { "epoch": 1.5496229464045248, "grad_norm": 0.6779229378649972, "learning_rate": 1.2002377941716936e-06, "loss": 0.2765904188156128, "num_input_tokens_seen": 947747304, "step": 23015, "train_runtime": 88667.2891, "train_tokens_per_second": 10688.804 }, { "epoch": 1.5499596014004848, "grad_norm": 0.8268464542605181, "learning_rate": 1.1985197285128853e-06, "loss": 0.3014521598815918, "num_input_tokens_seen": 947947848, "step": 23020, "train_runtime": 88688.1539, "train_tokens_per_second": 10688.551 }, { "epoch": 1.5502962563964449, "grad_norm": 0.7309373837712065, "learning_rate": 1.1968027259259107e-06, "loss": 0.29485440254211426, "num_input_tokens_seen": 948141696, "step": 23025, "train_runtime": 88708.524, "train_tokens_per_second": 10688.282 }, { "epoch": 1.5506329113924051, "grad_norm": 0.7418061177094563, "learning_rate": 1.1950867868909293e-06, "loss": 0.27242093086242675, "num_input_tokens_seen": 948341152, "step": 23030, "train_runtime": 88728.6989, "train_tokens_per_second": 10688.099 }, { "epoch": 1.5509695663883654, "grad_norm": 0.7723783681840259, "learning_rate": 1.1933719118877923e-06, "loss": 0.301695728302002, "num_input_tokens_seen": 948565320, "step": 23035, "train_runtime": 88747.134, "train_tokens_per_second": 10688.405 }, { "epoch": 1.5513062213843254, "grad_norm": 0.6210896589853844, "learning_rate": 1.1916581013960632e-06, "loss": 0.27483491897583007, "num_input_tokens_seen": 948786960, "step": 23040, "train_runtime": 88767.2674, "train_tokens_per_second": 10688.478 }, { "epoch": 1.5516428763802854, "grad_norm": 0.7585845495011703, "learning_rate": 1.189945355895002e-06, "loss": 0.3103985548019409, "num_input_tokens_seen": 948992784, "step": 23045, "train_runtime": 88788.5486, "train_tokens_per_second": 10688.234 }, { "epoch": 1.5519795313762457, "grad_norm": 0.7361608680283167, "learning_rate": 1.1882336758635727e-06, "loss": 0.27683134078979493, "num_input_tokens_seen": 949210184, "step": 23050, "train_runtime": 88808.2534, "train_tokens_per_second": 10688.31 }, { "epoch": 1.552316186372206, "grad_norm": 0.7785232440695272, "learning_rate": 1.1865230617804412e-06, "loss": 0.3222759008407593, "num_input_tokens_seen": 949427232, "step": 23055, "train_runtime": 88826.504, "train_tokens_per_second": 10688.558 }, { "epoch": 1.552652841368166, "grad_norm": 0.6863385720819051, "learning_rate": 1.1848135141239753e-06, "loss": 0.29602296352386476, "num_input_tokens_seen": 949632328, "step": 23060, "train_runtime": 88847.6183, "train_tokens_per_second": 10688.326 }, { "epoch": 1.552989496364126, "grad_norm": 0.8445365087327015, "learning_rate": 1.1831050333722438e-06, "loss": 0.3098031997680664, "num_input_tokens_seen": 949834744, "step": 23065, "train_runtime": 88866.8328, "train_tokens_per_second": 10688.293 }, { "epoch": 1.5533261513600862, "grad_norm": 0.6699872577454438, "learning_rate": 1.1813976200030191e-06, "loss": 0.2936935663223267, "num_input_tokens_seen": 950038912, "step": 23070, "train_runtime": 88885.5431, "train_tokens_per_second": 10688.34 }, { "epoch": 1.5536628063560465, "grad_norm": 0.6587273159029594, "learning_rate": 1.1796912744937717e-06, "loss": 0.3113705158233643, "num_input_tokens_seen": 950249272, "step": 23075, "train_runtime": 88904.1114, "train_tokens_per_second": 10688.474 }, { "epoch": 1.5539994613520065, "grad_norm": 0.7850157592239709, "learning_rate": 1.1779859973216802e-06, "loss": 0.2912999153137207, "num_input_tokens_seen": 950450864, "step": 23080, "train_runtime": 88924.8282, "train_tokens_per_second": 10688.251 }, { "epoch": 1.5543361163479665, "grad_norm": 0.8359110855571198, "learning_rate": 1.1762817889636142e-06, "loss": 0.30094685554504397, "num_input_tokens_seen": 950641160, "step": 23085, "train_runtime": 88943.9265, "train_tokens_per_second": 10688.095 }, { "epoch": 1.5546727713439268, "grad_norm": 0.7446039851683214, "learning_rate": 1.1745786498961542e-06, "loss": 0.3155487537384033, "num_input_tokens_seen": 950863976, "step": 23090, "train_runtime": 88963.6096, "train_tokens_per_second": 10688.235 }, { "epoch": 1.555009426339887, "grad_norm": 0.7035489096608432, "learning_rate": 1.1728765805955766e-06, "loss": 0.2764021873474121, "num_input_tokens_seen": 951064616, "step": 23095, "train_runtime": 88981.2841, "train_tokens_per_second": 10688.367 }, { "epoch": 1.555346081335847, "grad_norm": 0.8379116568581257, "learning_rate": 1.1711755815378595e-06, "loss": 0.3266140937805176, "num_input_tokens_seen": 951261128, "step": 23100, "train_runtime": 88999.886, "train_tokens_per_second": 10688.341 }, { "epoch": 1.555682736331807, "grad_norm": 0.6555289932157782, "learning_rate": 1.1694756531986818e-06, "loss": 0.2950438499450684, "num_input_tokens_seen": 951474680, "step": 23105, "train_runtime": 89019.6221, "train_tokens_per_second": 10688.37 }, { "epoch": 1.5560193913277673, "grad_norm": 0.7316413755785222, "learning_rate": 1.1677767960534232e-06, "loss": 0.30477352142333985, "num_input_tokens_seen": 951682136, "step": 23110, "train_runtime": 89039.185, "train_tokens_per_second": 10688.352 }, { "epoch": 1.5563560463237276, "grad_norm": 0.7010863465620603, "learning_rate": 1.166079010577163e-06, "loss": 0.31782994270324705, "num_input_tokens_seen": 951880480, "step": 23115, "train_runtime": 89059.0512, "train_tokens_per_second": 10688.195 }, { "epoch": 1.5566927013196876, "grad_norm": 0.8014115688827024, "learning_rate": 1.1643822972446823e-06, "loss": 0.3178088903427124, "num_input_tokens_seen": 952092032, "step": 23120, "train_runtime": 89078.139, "train_tokens_per_second": 10688.279 }, { "epoch": 1.5570293563156477, "grad_norm": 0.6993614103824592, "learning_rate": 1.1626866565304594e-06, "loss": 0.29741106033325193, "num_input_tokens_seen": 952310720, "step": 23125, "train_runtime": 89098.016, "train_tokens_per_second": 10688.349 }, { "epoch": 1.557366011311608, "grad_norm": 0.6917060037517492, "learning_rate": 1.16099208890868e-06, "loss": 0.2947490930557251, "num_input_tokens_seen": 952513632, "step": 23130, "train_runtime": 89117.1612, "train_tokens_per_second": 10688.33 }, { "epoch": 1.5577026663075682, "grad_norm": 0.7039815181297016, "learning_rate": 1.1592985948532187e-06, "loss": 0.2952183723449707, "num_input_tokens_seen": 952711312, "step": 23135, "train_runtime": 89136.141, "train_tokens_per_second": 10688.272 }, { "epoch": 1.5580393213035282, "grad_norm": 0.7108370384795947, "learning_rate": 1.1576061748376594e-06, "loss": 0.28752312660217283, "num_input_tokens_seen": 952914848, "step": 23140, "train_runtime": 89155.5522, "train_tokens_per_second": 10688.228 }, { "epoch": 1.5583759762994882, "grad_norm": 0.7326130299185505, "learning_rate": 1.1559148293352805e-06, "loss": 0.2932422637939453, "num_input_tokens_seen": 953124960, "step": 23145, "train_runtime": 89175.2895, "train_tokens_per_second": 10688.218 }, { "epoch": 1.5587126312954485, "grad_norm": 0.6802392342740848, "learning_rate": 1.154224558819062e-06, "loss": 0.2951206684112549, "num_input_tokens_seen": 953334944, "step": 23150, "train_runtime": 89196.02, "train_tokens_per_second": 10688.088 }, { "epoch": 1.5590492862914087, "grad_norm": 0.7420437685252699, "learning_rate": 1.1525353637616821e-06, "loss": 0.30240559577941895, "num_input_tokens_seen": 953541792, "step": 23155, "train_runtime": 89215.4572, "train_tokens_per_second": 10688.078 }, { "epoch": 1.5593859412873687, "grad_norm": 0.7552933437251149, "learning_rate": 1.1508472446355196e-06, "loss": 0.30454444885253906, "num_input_tokens_seen": 953758936, "step": 23160, "train_runtime": 89233.8916, "train_tokens_per_second": 10688.304 }, { "epoch": 1.5597225962833288, "grad_norm": 0.6776318068298958, "learning_rate": 1.1491602019126501e-06, "loss": 0.30215561389923096, "num_input_tokens_seen": 953975496, "step": 23165, "train_runtime": 89251.603, "train_tokens_per_second": 10688.609 }, { "epoch": 1.560059251279289, "grad_norm": 0.7238547413591946, "learning_rate": 1.1474742360648515e-06, "loss": 0.3156610012054443, "num_input_tokens_seen": 954187696, "step": 23170, "train_runtime": 89270.118, "train_tokens_per_second": 10688.769 }, { "epoch": 1.5603959062752493, "grad_norm": 0.8014024206686928, "learning_rate": 1.1457893475635968e-06, "loss": 0.31828200817108154, "num_input_tokens_seen": 954388976, "step": 23175, "train_runtime": 89289.4321, "train_tokens_per_second": 10688.711 }, { "epoch": 1.5607325612712093, "grad_norm": 0.6602889833193909, "learning_rate": 1.144105536880063e-06, "loss": 0.27493886947631835, "num_input_tokens_seen": 954590528, "step": 23180, "train_runtime": 89307.8858, "train_tokens_per_second": 10688.76 }, { "epoch": 1.5610692162671693, "grad_norm": 0.7403916884766446, "learning_rate": 1.1424228044851176e-06, "loss": 0.2945625066757202, "num_input_tokens_seen": 954772088, "step": 23185, "train_runtime": 89326.8239, "train_tokens_per_second": 10688.526 }, { "epoch": 1.5614058712631296, "grad_norm": 0.6507715543663246, "learning_rate": 1.1407411508493355e-06, "loss": 0.2946333408355713, "num_input_tokens_seen": 954969840, "step": 23190, "train_runtime": 89346.9223, "train_tokens_per_second": 10688.335 }, { "epoch": 1.5617425262590898, "grad_norm": 0.7013751060514102, "learning_rate": 1.1390605764429846e-06, "loss": 0.26598825454711916, "num_input_tokens_seen": 955170200, "step": 23195, "train_runtime": 89367.3062, "train_tokens_per_second": 10688.139 }, { "epoch": 1.5620791812550499, "grad_norm": 0.7539953496699511, "learning_rate": 1.1373810817360314e-06, "loss": 0.2938087463378906, "num_input_tokens_seen": 955386784, "step": 23200, "train_runtime": 89385.4634, "train_tokens_per_second": 10688.391 }, { "epoch": 1.5624158362510099, "grad_norm": 0.7988545253775655, "learning_rate": 1.135702667198142e-06, "loss": 0.32207341194152833, "num_input_tokens_seen": 955597064, "step": 23205, "train_runtime": 89404.2495, "train_tokens_per_second": 10688.497 }, { "epoch": 1.5627524912469701, "grad_norm": 0.7450527934901675, "learning_rate": 1.134025333298679e-06, "loss": 0.2695708513259888, "num_input_tokens_seen": 955787256, "step": 23210, "train_runtime": 89423.657, "train_tokens_per_second": 10688.304 }, { "epoch": 1.5630891462429304, "grad_norm": 0.6782560315345358, "learning_rate": 1.1323490805067045e-06, "loss": 0.275922155380249, "num_input_tokens_seen": 955992504, "step": 23215, "train_runtime": 89442.1032, "train_tokens_per_second": 10688.395 }, { "epoch": 1.5634258012388904, "grad_norm": 0.7544049021562372, "learning_rate": 1.1306739092909757e-06, "loss": 0.27423772811889646, "num_input_tokens_seen": 956189040, "step": 23220, "train_runtime": 89462.8263, "train_tokens_per_second": 10688.116 }, { "epoch": 1.5637624562348504, "grad_norm": 0.6925206589612355, "learning_rate": 1.1289998201199493e-06, "loss": 0.28267221450805663, "num_input_tokens_seen": 956396224, "step": 23225, "train_runtime": 89482.0404, "train_tokens_per_second": 10688.136 }, { "epoch": 1.5640991112308107, "grad_norm": 0.7380808736935781, "learning_rate": 1.1273268134617816e-06, "loss": 0.30006752014160154, "num_input_tokens_seen": 956608560, "step": 23230, "train_runtime": 89502.6616, "train_tokens_per_second": 10688.046 }, { "epoch": 1.564435766226771, "grad_norm": 0.5957545814954023, "learning_rate": 1.1256548897843189e-06, "loss": 0.29850091934204104, "num_input_tokens_seen": 956824672, "step": 23235, "train_runtime": 89521.4812, "train_tokens_per_second": 10688.213 }, { "epoch": 1.564772421222731, "grad_norm": 0.6653463097310987, "learning_rate": 1.1239840495551136e-06, "loss": 0.293147611618042, "num_input_tokens_seen": 957034488, "step": 23240, "train_runtime": 89540.3692, "train_tokens_per_second": 10688.302 }, { "epoch": 1.565109076218691, "grad_norm": 0.736147609555366, "learning_rate": 1.1223142932414087e-06, "loss": 0.3253899335861206, "num_input_tokens_seen": 957248616, "step": 23245, "train_runtime": 89560.4531, "train_tokens_per_second": 10688.296 }, { "epoch": 1.5654457312146512, "grad_norm": 0.648654329901954, "learning_rate": 1.120645621310147e-06, "loss": 0.29245424270629883, "num_input_tokens_seen": 957455832, "step": 23250, "train_runtime": 89580.097, "train_tokens_per_second": 10688.265 }, { "epoch": 1.5657823862106115, "grad_norm": 0.8071364157894452, "learning_rate": 1.1189780342279666e-06, "loss": 0.29366202354431153, "num_input_tokens_seen": 957651272, "step": 23255, "train_runtime": 89599.229, "train_tokens_per_second": 10688.164 }, { "epoch": 1.5661190412065715, "grad_norm": 0.6719255948919214, "learning_rate": 1.1173115324612033e-06, "loss": 0.31249587535858153, "num_input_tokens_seen": 957844760, "step": 23260, "train_runtime": 89619.0501, "train_tokens_per_second": 10687.959 }, { "epoch": 1.5664556962025316, "grad_norm": 0.75902175414191, "learning_rate": 1.1156461164758891e-06, "loss": 0.32770886421203616, "num_input_tokens_seen": 958061192, "step": 23265, "train_runtime": 89638.7763, "train_tokens_per_second": 10688.022 }, { "epoch": 1.5667923511984918, "grad_norm": 0.6575973469678387, "learning_rate": 1.1139817867377522e-06, "loss": 0.2553058624267578, "num_input_tokens_seen": 958276280, "step": 23270, "train_runtime": 89657.7675, "train_tokens_per_second": 10688.157 }, { "epoch": 1.567129006194452, "grad_norm": 0.7003847234884664, "learning_rate": 1.1123185437122153e-06, "loss": 0.2894434928894043, "num_input_tokens_seen": 958492400, "step": 23275, "train_runtime": 89677.4709, "train_tokens_per_second": 10688.218 }, { "epoch": 1.567465661190412, "grad_norm": 0.731229111640578, "learning_rate": 1.1106563878644038e-06, "loss": 0.3002240419387817, "num_input_tokens_seen": 958705552, "step": 23280, "train_runtime": 89696.1267, "train_tokens_per_second": 10688.372 }, { "epoch": 1.5678023161863721, "grad_norm": 0.7239757072730756, "learning_rate": 1.1089953196591286e-06, "loss": 0.30293090343475343, "num_input_tokens_seen": 958910864, "step": 23285, "train_runtime": 89716.5511, "train_tokens_per_second": 10688.227 }, { "epoch": 1.5681389711823324, "grad_norm": 0.7780323864909853, "learning_rate": 1.107335339560906e-06, "loss": 0.31608102321624754, "num_input_tokens_seen": 959105920, "step": 23290, "train_runtime": 89736.261, "train_tokens_per_second": 10688.053 }, { "epoch": 1.5684756261782926, "grad_norm": 0.8754339392773606, "learning_rate": 1.1056764480339427e-06, "loss": 0.3068833589553833, "num_input_tokens_seen": 959319960, "step": 23295, "train_runtime": 89755.3147, "train_tokens_per_second": 10688.169 }, { "epoch": 1.5688122811742526, "grad_norm": 0.7629883312253121, "learning_rate": 1.1040186455421425e-06, "loss": 0.3311607837677002, "num_input_tokens_seen": 959538024, "step": 23300, "train_runtime": 89774.0782, "train_tokens_per_second": 10688.364 }, { "epoch": 1.5691489361702127, "grad_norm": 0.789731734143017, "learning_rate": 1.1023619325491052e-06, "loss": 0.30561165809631347, "num_input_tokens_seen": 959740032, "step": 23305, "train_runtime": 89791.8881, "train_tokens_per_second": 10688.494 }, { "epoch": 1.569485591166173, "grad_norm": 0.5844601880777135, "learning_rate": 1.1007063095181248e-06, "loss": 0.2748584747314453, "num_input_tokens_seen": 959948088, "step": 23310, "train_runtime": 89811.6982, "train_tokens_per_second": 10688.453 }, { "epoch": 1.5698222461621332, "grad_norm": 0.8215685678969992, "learning_rate": 1.0990517769121905e-06, "loss": 0.2950908184051514, "num_input_tokens_seen": 960140696, "step": 23315, "train_runtime": 89830.9355, "train_tokens_per_second": 10688.308 }, { "epoch": 1.5701589011580932, "grad_norm": 0.7975747634598304, "learning_rate": 1.0973983351939876e-06, "loss": 0.31035542488098145, "num_input_tokens_seen": 960348696, "step": 23320, "train_runtime": 89849.4363, "train_tokens_per_second": 10688.422 }, { "epoch": 1.5704955561540532, "grad_norm": 0.6996259459839538, "learning_rate": 1.095745984825895e-06, "loss": 0.29632689952850344, "num_input_tokens_seen": 960561192, "step": 23325, "train_runtime": 89867.229, "train_tokens_per_second": 10688.67 }, { "epoch": 1.5708322111500135, "grad_norm": 0.9368770179014051, "learning_rate": 1.0940947262699902e-06, "loss": 0.3004031181335449, "num_input_tokens_seen": 960755696, "step": 23330, "train_runtime": 89886.9196, "train_tokens_per_second": 10688.493 }, { "epoch": 1.5711688661459737, "grad_norm": 0.6630884982636516, "learning_rate": 1.092444559988038e-06, "loss": 0.28925046920776365, "num_input_tokens_seen": 960960856, "step": 23335, "train_runtime": 89906.3995, "train_tokens_per_second": 10688.459 }, { "epoch": 1.5715055211419338, "grad_norm": 0.8252894939047051, "learning_rate": 1.0907954864415048e-06, "loss": 0.2954926252365112, "num_input_tokens_seen": 961174000, "step": 23340, "train_runtime": 89926.6169, "train_tokens_per_second": 10688.426 }, { "epoch": 1.5718421761378938, "grad_norm": 0.7980270412161113, "learning_rate": 1.089147506091549e-06, "loss": 0.28292920589447024, "num_input_tokens_seen": 961379760, "step": 23345, "train_runtime": 89944.3073, "train_tokens_per_second": 10688.612 }, { "epoch": 1.572178831133854, "grad_norm": 0.8216791026249687, "learning_rate": 1.0875006193990217e-06, "loss": 0.3119589567184448, "num_input_tokens_seen": 961579672, "step": 23350, "train_runtime": 89963.04, "train_tokens_per_second": 10688.608 }, { "epoch": 1.5725154861298143, "grad_norm": 0.740135710128464, "learning_rate": 1.0858548268244706e-06, "loss": 0.29170129299163816, "num_input_tokens_seen": 961786128, "step": 23355, "train_runtime": 89981.7629, "train_tokens_per_second": 10688.678 }, { "epoch": 1.5728521411257743, "grad_norm": 0.7554478845652846, "learning_rate": 1.0842101288281359e-06, "loss": 0.2889859676361084, "num_input_tokens_seen": 961994616, "step": 23360, "train_runtime": 90001.0327, "train_tokens_per_second": 10688.706 }, { "epoch": 1.5731887961217343, "grad_norm": 0.7424399679388761, "learning_rate": 1.082566525869952e-06, "loss": 0.2844655990600586, "num_input_tokens_seen": 962210512, "step": 23365, "train_runtime": 90021.0599, "train_tokens_per_second": 10688.727 }, { "epoch": 1.5735254511176946, "grad_norm": 0.8220535126329408, "learning_rate": 1.0809240184095476e-06, "loss": 0.3094356536865234, "num_input_tokens_seen": 962413496, "step": 23370, "train_runtime": 90039.6583, "train_tokens_per_second": 10688.773 }, { "epoch": 1.5738621061136548, "grad_norm": 0.6787277516870173, "learning_rate": 1.0792826069062429e-06, "loss": 0.27352180480957033, "num_input_tokens_seen": 962621712, "step": 23375, "train_runtime": 90058.6477, "train_tokens_per_second": 10688.832 }, { "epoch": 1.5741987611096149, "grad_norm": 0.6687769183300022, "learning_rate": 1.0776422918190576e-06, "loss": 0.31435580253601075, "num_input_tokens_seen": 962829760, "step": 23380, "train_runtime": 90076.9654, "train_tokens_per_second": 10688.968 }, { "epoch": 1.574535416105575, "grad_norm": 0.7642509491679307, "learning_rate": 1.0760030736066952e-06, "loss": 0.27960896492004395, "num_input_tokens_seen": 963025424, "step": 23385, "train_runtime": 90098.1481, "train_tokens_per_second": 10688.626 }, { "epoch": 1.5748720711015352, "grad_norm": 0.704957062381949, "learning_rate": 1.0743649527275619e-06, "loss": 0.31715998649597166, "num_input_tokens_seen": 963238936, "step": 23390, "train_runtime": 90117.4311, "train_tokens_per_second": 10688.708 }, { "epoch": 1.5752087260974954, "grad_norm": 0.7978229083681466, "learning_rate": 1.0727279296397514e-06, "loss": 0.3038949966430664, "num_input_tokens_seen": 963454496, "step": 23395, "train_runtime": 90137.2163, "train_tokens_per_second": 10688.754 }, { "epoch": 1.5755453810934554, "grad_norm": 0.846760011449159, "learning_rate": 1.0710920048010526e-06, "loss": 0.31269245147705077, "num_input_tokens_seen": 963661720, "step": 23400, "train_runtime": 90155.4634, "train_tokens_per_second": 10688.889 }, { "epoch": 1.5758820360894155, "grad_norm": 0.7123052048762643, "learning_rate": 1.0694571786689462e-06, "loss": 0.3008697271347046, "num_input_tokens_seen": 963886528, "step": 23405, "train_runtime": 90176.45, "train_tokens_per_second": 10688.894 }, { "epoch": 1.5762186910853757, "grad_norm": 0.7491136196068935, "learning_rate": 1.067823451700606e-06, "loss": 0.3005941867828369, "num_input_tokens_seen": 964090984, "step": 23410, "train_runtime": 90194.3405, "train_tokens_per_second": 10689.041 }, { "epoch": 1.576555346081336, "grad_norm": 0.7508556983236367, "learning_rate": 1.066190824352899e-06, "loss": 0.3020128011703491, "num_input_tokens_seen": 964303840, "step": 23415, "train_runtime": 90215.4415, "train_tokens_per_second": 10688.9 }, { "epoch": 1.576892001077296, "grad_norm": 0.6537034604127167, "learning_rate": 1.0645592970823837e-06, "loss": 0.27405176162719724, "num_input_tokens_seen": 964497976, "step": 23420, "train_runtime": 90234.8187, "train_tokens_per_second": 10688.756 }, { "epoch": 1.577228656073256, "grad_norm": 0.9329465972284752, "learning_rate": 1.0629288703453105e-06, "loss": 0.30569844245910643, "num_input_tokens_seen": 964709432, "step": 23425, "train_runtime": 90254.2533, "train_tokens_per_second": 10688.797 }, { "epoch": 1.5775653110692163, "grad_norm": 0.8229748227938367, "learning_rate": 1.061299544597627e-06, "loss": 0.301184344291687, "num_input_tokens_seen": 964902984, "step": 23430, "train_runtime": 90271.9842, "train_tokens_per_second": 10688.842 }, { "epoch": 1.5779019660651765, "grad_norm": 0.7151957507896091, "learning_rate": 1.0596713202949637e-06, "loss": 0.3159533262252808, "num_input_tokens_seen": 965117336, "step": 23435, "train_runtime": 90292.8739, "train_tokens_per_second": 10688.743 }, { "epoch": 1.5782386210611365, "grad_norm": 0.6921806459884181, "learning_rate": 1.0580441978926527e-06, "loss": 0.29924540519714354, "num_input_tokens_seen": 965318872, "step": 23440, "train_runtime": 90312.4974, "train_tokens_per_second": 10688.652 }, { "epoch": 1.5785752760570966, "grad_norm": 0.8297944394341958, "learning_rate": 1.056418177845711e-06, "loss": 0.2895346164703369, "num_input_tokens_seen": 965513728, "step": 23445, "train_runtime": 90332.1564, "train_tokens_per_second": 10688.483 }, { "epoch": 1.5789119310530568, "grad_norm": 0.6890694669586614, "learning_rate": 1.0547932606088506e-06, "loss": 0.3009631156921387, "num_input_tokens_seen": 965712784, "step": 23450, "train_runtime": 90351.4204, "train_tokens_per_second": 10688.407 }, { "epoch": 1.579248586049017, "grad_norm": 0.7200553135845509, "learning_rate": 1.053169446636475e-06, "loss": 0.2954357147216797, "num_input_tokens_seen": 965915872, "step": 23455, "train_runtime": 90370.8599, "train_tokens_per_second": 10688.355 }, { "epoch": 1.579585241044977, "grad_norm": 0.8715362002067542, "learning_rate": 1.0515467363826782e-06, "loss": 0.30681111812591555, "num_input_tokens_seen": 966128112, "step": 23460, "train_runtime": 90388.5159, "train_tokens_per_second": 10688.616 }, { "epoch": 1.5799218960409371, "grad_norm": 0.700126394219807, "learning_rate": 1.0499251303012454e-06, "loss": 0.2867446422576904, "num_input_tokens_seen": 966339672, "step": 23465, "train_runtime": 90407.9543, "train_tokens_per_second": 10688.658 }, { "epoch": 1.5802585510368974, "grad_norm": 0.7513086264990754, "learning_rate": 1.0483046288456544e-06, "loss": 0.3048264980316162, "num_input_tokens_seen": 966534048, "step": 23470, "train_runtime": 90425.7838, "train_tokens_per_second": 10688.7 }, { "epoch": 1.5805952060328576, "grad_norm": 0.7483407766216252, "learning_rate": 1.0466852324690719e-06, "loss": 0.2994597673416138, "num_input_tokens_seen": 966735408, "step": 23475, "train_runtime": 90445.639, "train_tokens_per_second": 10688.58 }, { "epoch": 1.5809318610288177, "grad_norm": 0.775520524485069, "learning_rate": 1.0450669416243596e-06, "loss": 0.29664130210876466, "num_input_tokens_seen": 966947536, "step": 23480, "train_runtime": 90464.3452, "train_tokens_per_second": 10688.714 }, { "epoch": 1.5812685160247777, "grad_norm": 0.7024119732260599, "learning_rate": 1.0434497567640639e-06, "loss": 0.3101475715637207, "num_input_tokens_seen": 967157224, "step": 23485, "train_runtime": 90484.0058, "train_tokens_per_second": 10688.709 }, { "epoch": 1.581605171020738, "grad_norm": 0.7710038669736891, "learning_rate": 1.0418336783404282e-06, "loss": 0.3023500919342041, "num_input_tokens_seen": 967363080, "step": 23490, "train_runtime": 90502.6713, "train_tokens_per_second": 10688.779 }, { "epoch": 1.5819418260166982, "grad_norm": 0.6860023245167318, "learning_rate": 1.0402187068053825e-06, "loss": 0.3017685890197754, "num_input_tokens_seen": 967565416, "step": 23495, "train_runtime": 90520.4422, "train_tokens_per_second": 10688.916 }, { "epoch": 1.5822784810126582, "grad_norm": 0.6628600434323993, "learning_rate": 1.0386048426105495e-06, "loss": 0.2870330333709717, "num_input_tokens_seen": 967768248, "step": 23500, "train_runtime": 90538.4476, "train_tokens_per_second": 10689.031 }, { "epoch": 1.5826151360086183, "grad_norm": 0.6746284525091016, "learning_rate": 1.0369920862072396e-06, "loss": 0.2825700521469116, "num_input_tokens_seen": 967966552, "step": 23505, "train_runtime": 90559.8256, "train_tokens_per_second": 10688.697 }, { "epoch": 1.5829517910045785, "grad_norm": 0.715042914935067, "learning_rate": 1.0353804380464556e-06, "loss": 0.27926025390625, "num_input_tokens_seen": 968177680, "step": 23510, "train_runtime": 90580.495, "train_tokens_per_second": 10688.589 }, { "epoch": 1.5832884460005388, "grad_norm": 0.688283941075012, "learning_rate": 1.0337698985788903e-06, "loss": 0.2928598403930664, "num_input_tokens_seen": 968392520, "step": 23515, "train_runtime": 90600.7972, "train_tokens_per_second": 10688.565 }, { "epoch": 1.5836251009964988, "grad_norm": 0.7183732309083121, "learning_rate": 1.0321604682549247e-06, "loss": 0.2772254228591919, "num_input_tokens_seen": 968611192, "step": 23520, "train_runtime": 90620.585, "train_tokens_per_second": 10688.644 }, { "epoch": 1.5839617559924588, "grad_norm": 0.7769538072494138, "learning_rate": 1.0305521475246311e-06, "loss": 0.313828706741333, "num_input_tokens_seen": 968808016, "step": 23525, "train_runtime": 90639.424, "train_tokens_per_second": 10688.594 }, { "epoch": 1.584298410988419, "grad_norm": 0.7872872095741973, "learning_rate": 1.028944936837774e-06, "loss": 0.3215691804885864, "num_input_tokens_seen": 968999184, "step": 23530, "train_runtime": 90658.2165, "train_tokens_per_second": 10688.487 }, { "epoch": 1.5846350659843793, "grad_norm": 0.6917533961274617, "learning_rate": 1.0273388366438003e-06, "loss": 0.30582218170166015, "num_input_tokens_seen": 969211152, "step": 23535, "train_runtime": 90679.0654, "train_tokens_per_second": 10688.367 }, { "epoch": 1.5849717209803393, "grad_norm": 0.7267971672908725, "learning_rate": 1.0257338473918538e-06, "loss": 0.30242369174957273, "num_input_tokens_seen": 969419936, "step": 23540, "train_runtime": 90697.6615, "train_tokens_per_second": 10688.478 }, { "epoch": 1.5853083759762994, "grad_norm": 0.6664653130462178, "learning_rate": 1.0241299695307644e-06, "loss": 0.3006892204284668, "num_input_tokens_seen": 969623232, "step": 23545, "train_runtime": 90715.8379, "train_tokens_per_second": 10688.577 }, { "epoch": 1.5856450309722596, "grad_norm": 0.6601514972910398, "learning_rate": 1.0225272035090506e-06, "loss": 0.28227720260620115, "num_input_tokens_seen": 969840024, "step": 23550, "train_runtime": 90735.2455, "train_tokens_per_second": 10688.68 }, { "epoch": 1.5859816859682199, "grad_norm": 0.7809285625598661, "learning_rate": 1.0209255497749209e-06, "loss": 0.3071380615234375, "num_input_tokens_seen": 970051904, "step": 23555, "train_runtime": 90755.9545, "train_tokens_per_second": 10688.576 }, { "epoch": 1.58631834096418, "grad_norm": 0.705470851388267, "learning_rate": 1.0193250087762735e-06, "loss": 0.2849541902542114, "num_input_tokens_seen": 970259984, "step": 23560, "train_runtime": 90775.6622, "train_tokens_per_second": 10688.548 }, { "epoch": 1.58665499596014, "grad_norm": 0.607578310020175, "learning_rate": 1.0177255809606934e-06, "loss": 0.2915698528289795, "num_input_tokens_seen": 970469016, "step": 23565, "train_runtime": 90794.2841, "train_tokens_per_second": 10688.658 }, { "epoch": 1.5869916509561002, "grad_norm": 0.7824141308054459, "learning_rate": 1.0161272667754562e-06, "loss": 0.2944023132324219, "num_input_tokens_seen": 970688280, "step": 23570, "train_runtime": 90814.6201, "train_tokens_per_second": 10688.679 }, { "epoch": 1.5873283059520604, "grad_norm": 0.6163911588638492, "learning_rate": 1.014530066667524e-06, "loss": 0.2905706882476807, "num_input_tokens_seen": 970901880, "step": 23575, "train_runtime": 90834.95, "train_tokens_per_second": 10688.638 }, { "epoch": 1.5876649609480205, "grad_norm": 0.7017370554462523, "learning_rate": 1.0129339810835526e-06, "loss": 0.2699403762817383, "num_input_tokens_seen": 971097616, "step": 23580, "train_runtime": 90854.8451, "train_tokens_per_second": 10688.452 }, { "epoch": 1.5880016159439805, "grad_norm": 0.7514822770719456, "learning_rate": 1.0113390104698767e-06, "loss": 0.2819315671920776, "num_input_tokens_seen": 971314288, "step": 23585, "train_runtime": 90873.4943, "train_tokens_per_second": 10688.642 }, { "epoch": 1.5883382709399407, "grad_norm": 0.6371654802583415, "learning_rate": 1.009745155272529e-06, "loss": 0.32755088806152344, "num_input_tokens_seen": 971526016, "step": 23590, "train_runtime": 90891.6872, "train_tokens_per_second": 10688.832 }, { "epoch": 1.588674925935901, "grad_norm": 0.679890093369431, "learning_rate": 1.0081524159372246e-06, "loss": 0.3044525146484375, "num_input_tokens_seen": 971723328, "step": 23595, "train_runtime": 90909.3686, "train_tokens_per_second": 10688.924 }, { "epoch": 1.589011580931861, "grad_norm": 0.6964434384872165, "learning_rate": 1.0065607929093685e-06, "loss": 0.29643476009368896, "num_input_tokens_seen": 971925344, "step": 23600, "train_runtime": 90928.3626, "train_tokens_per_second": 10688.913 }, { "epoch": 1.589348235927821, "grad_norm": 0.6973459953961096, "learning_rate": 1.0049702866340521e-06, "loss": 0.2658666133880615, "num_input_tokens_seen": 972137648, "step": 23605, "train_runtime": 90947.5855, "train_tokens_per_second": 10688.988 }, { "epoch": 1.5896848909237813, "grad_norm": 0.7294025712664699, "learning_rate": 1.0033808975560556e-06, "loss": 0.2826035737991333, "num_input_tokens_seen": 972340888, "step": 23610, "train_runtime": 90967.5035, "train_tokens_per_second": 10688.882 }, { "epoch": 1.5900215459197415, "grad_norm": 0.7345310973288419, "learning_rate": 1.0017926261198473e-06, "loss": 0.29577486515045165, "num_input_tokens_seen": 972546008, "step": 23615, "train_runtime": 90987.721, "train_tokens_per_second": 10688.761 }, { "epoch": 1.5903582009157016, "grad_norm": 0.8463012799984994, "learning_rate": 1.0002054727695814e-06, "loss": 0.299570894241333, "num_input_tokens_seen": 972743216, "step": 23620, "train_runtime": 91007.4353, "train_tokens_per_second": 10688.613 }, { "epoch": 1.5906948559116616, "grad_norm": 0.6491224804886937, "learning_rate": 9.986194379490993e-07, "loss": 0.2980299949645996, "num_input_tokens_seen": 972942960, "step": 23625, "train_runtime": 91026.1642, "train_tokens_per_second": 10688.608 }, { "epoch": 1.5910315109076218, "grad_norm": 0.7127457102107609, "learning_rate": 9.970345221019345e-07, "loss": 0.3038078546524048, "num_input_tokens_seen": 973143632, "step": 23630, "train_runtime": 91046.1162, "train_tokens_per_second": 10688.469 }, { "epoch": 1.591368165903582, "grad_norm": 0.91665985569685, "learning_rate": 9.954507256712987e-07, "loss": 0.30216965675354, "num_input_tokens_seen": 973344256, "step": 23635, "train_runtime": 91065.1873, "train_tokens_per_second": 10688.434 }, { "epoch": 1.5917048208995421, "grad_norm": 0.9066628975259514, "learning_rate": 9.938680491000991e-07, "loss": 0.3032233715057373, "num_input_tokens_seen": 973545280, "step": 23640, "train_runtime": 91085.2002, "train_tokens_per_second": 10688.293 }, { "epoch": 1.5920414758955022, "grad_norm": 0.6837066690890032, "learning_rate": 9.92286492830925e-07, "loss": 0.2914875030517578, "num_input_tokens_seen": 973757968, "step": 23645, "train_runtime": 91104.5452, "train_tokens_per_second": 10688.358 }, { "epoch": 1.5923781308914624, "grad_norm": 0.6803146307509725, "learning_rate": 9.907060573060535e-07, "loss": 0.3134547233581543, "num_input_tokens_seen": 973970160, "step": 23650, "train_runtime": 91123.9836, "train_tokens_per_second": 10688.406 }, { "epoch": 1.5927147858874227, "grad_norm": 0.7256288495995502, "learning_rate": 9.891267429674484e-07, "loss": 0.31360583305358886, "num_input_tokens_seen": 974168520, "step": 23655, "train_runtime": 91143.8521, "train_tokens_per_second": 10688.253 }, { "epoch": 1.5930514408833827, "grad_norm": 0.6875464210869967, "learning_rate": 9.8754855025676e-07, "loss": 0.2884730339050293, "num_input_tokens_seen": 974373704, "step": 23660, "train_runtime": 91162.8833, "train_tokens_per_second": 10688.272 }, { "epoch": 1.5933880958793427, "grad_norm": 0.7753608191618642, "learning_rate": 9.85971479615324e-07, "loss": 0.29705281257629396, "num_input_tokens_seen": 974587736, "step": 23665, "train_runtime": 91182.7098, "train_tokens_per_second": 10688.295 }, { "epoch": 1.593724750875303, "grad_norm": 0.7703295808836153, "learning_rate": 9.843955314841647e-07, "loss": 0.2846726655960083, "num_input_tokens_seen": 974797272, "step": 23670, "train_runtime": 91201.1272, "train_tokens_per_second": 10688.434 }, { "epoch": 1.5940614058712632, "grad_norm": 0.7298554615248132, "learning_rate": 9.82820706303989e-07, "loss": 0.29722042083740235, "num_input_tokens_seen": 975008544, "step": 23675, "train_runtime": 91219.8191, "train_tokens_per_second": 10688.56 }, { "epoch": 1.5943980608672232, "grad_norm": 0.7616052270803086, "learning_rate": 9.812470045151952e-07, "loss": 0.3028102397918701, "num_input_tokens_seen": 975202800, "step": 23680, "train_runtime": 91238.2195, "train_tokens_per_second": 10688.534 }, { "epoch": 1.5947347158631833, "grad_norm": 0.7194651954937018, "learning_rate": 9.79674426557859e-07, "loss": 0.293375563621521, "num_input_tokens_seen": 975402776, "step": 23685, "train_runtime": 91257.0917, "train_tokens_per_second": 10688.515 }, { "epoch": 1.5950713708591435, "grad_norm": 0.6688179923449699, "learning_rate": 9.781029728717513e-07, "loss": 0.28283841609954835, "num_input_tokens_seen": 975605624, "step": 23690, "train_runtime": 91276.2347, "train_tokens_per_second": 10688.496 }, { "epoch": 1.5954080258551038, "grad_norm": 0.682306708006741, "learning_rate": 9.765326438963218e-07, "loss": 0.31719632148742677, "num_input_tokens_seen": 975810304, "step": 23695, "train_runtime": 91295.5372, "train_tokens_per_second": 10688.478 }, { "epoch": 1.5957446808510638, "grad_norm": 0.7153495933709182, "learning_rate": 9.749634400707087e-07, "loss": 0.2901041030883789, "num_input_tokens_seen": 976003232, "step": 23700, "train_runtime": 91314.5339, "train_tokens_per_second": 10688.367 }, { "epoch": 1.5960813358470238, "grad_norm": 0.7045295108480607, "learning_rate": 9.733953618337344e-07, "loss": 0.30620386600494387, "num_input_tokens_seen": 976198768, "step": 23705, "train_runtime": 91334.6059, "train_tokens_per_second": 10688.159 }, { "epoch": 1.596417990842984, "grad_norm": 0.767633257857897, "learning_rate": 9.718284096239077e-07, "loss": 0.3172248363494873, "num_input_tokens_seen": 976422736, "step": 23710, "train_runtime": 91353.9882, "train_tokens_per_second": 10688.343 }, { "epoch": 1.5967546458389443, "grad_norm": 0.7615198978846145, "learning_rate": 9.702625838794215e-07, "loss": 0.2888712644577026, "num_input_tokens_seen": 976628320, "step": 23715, "train_runtime": 91372.9311, "train_tokens_per_second": 10688.377 }, { "epoch": 1.5970913008349044, "grad_norm": 0.6926880258296241, "learning_rate": 9.686978850381535e-07, "loss": 0.2828983306884766, "num_input_tokens_seen": 976838936, "step": 23720, "train_runtime": 91393.1561, "train_tokens_per_second": 10688.316 }, { "epoch": 1.5974279558308644, "grad_norm": 0.6822727889885079, "learning_rate": 9.67134313537666e-07, "loss": 0.2844418525695801, "num_input_tokens_seen": 977039664, "step": 23725, "train_runtime": 91412.2359, "train_tokens_per_second": 10688.281 }, { "epoch": 1.5977646108268246, "grad_norm": 0.750673407678243, "learning_rate": 9.6557186981521e-07, "loss": 0.29744601249694824, "num_input_tokens_seen": 977249064, "step": 23730, "train_runtime": 91431.0934, "train_tokens_per_second": 10688.367 }, { "epoch": 1.5981012658227849, "grad_norm": 0.7209835749762181, "learning_rate": 9.640105543077133e-07, "loss": 0.29286952018737794, "num_input_tokens_seen": 977456688, "step": 23735, "train_runtime": 91450.6639, "train_tokens_per_second": 10688.35 }, { "epoch": 1.598437920818745, "grad_norm": 0.677654224499752, "learning_rate": 9.624503674517972e-07, "loss": 0.3075717926025391, "num_input_tokens_seen": 977665216, "step": 23740, "train_runtime": 91469.8891, "train_tokens_per_second": 10688.383 }, { "epoch": 1.598774575814705, "grad_norm": 0.6779153348776469, "learning_rate": 9.608913096837603e-07, "loss": 0.2758145809173584, "num_input_tokens_seen": 977876640, "step": 23745, "train_runtime": 91488.8882, "train_tokens_per_second": 10688.474 }, { "epoch": 1.5991112308106652, "grad_norm": 0.8120132620508258, "learning_rate": 9.593333814395889e-07, "loss": 0.30866098403930664, "num_input_tokens_seen": 978069656, "step": 23750, "train_runtime": 91507.2878, "train_tokens_per_second": 10688.435 }, { "epoch": 1.5994478858066254, "grad_norm": 0.6612951043745507, "learning_rate": 9.577765831549529e-07, "loss": 0.2907003879547119, "num_input_tokens_seen": 978279560, "step": 23755, "train_runtime": 91525.979, "train_tokens_per_second": 10688.545 }, { "epoch": 1.5997845408025855, "grad_norm": 0.6883044781169165, "learning_rate": 9.562209152652058e-07, "loss": 0.3038051605224609, "num_input_tokens_seen": 978478120, "step": 23760, "train_runtime": 91544.5432, "train_tokens_per_second": 10688.547 }, { "epoch": 1.6001211957985455, "grad_norm": 0.7664876064899335, "learning_rate": 9.54666378205385e-07, "loss": 0.3178126811981201, "num_input_tokens_seen": 978694360, "step": 23765, "train_runtime": 91566.0961, "train_tokens_per_second": 10688.392 }, { "epoch": 1.6004578507945058, "grad_norm": 0.746672526639069, "learning_rate": 9.531129724102117e-07, "loss": 0.2873732089996338, "num_input_tokens_seen": 978896480, "step": 23770, "train_runtime": 91586.366, "train_tokens_per_second": 10688.234 }, { "epoch": 1.600794505790466, "grad_norm": 0.762399581861527, "learning_rate": 9.515606983140896e-07, "loss": 0.2977363109588623, "num_input_tokens_seen": 979104288, "step": 23775, "train_runtime": 91604.2088, "train_tokens_per_second": 10688.42 }, { "epoch": 1.601131160786426, "grad_norm": 0.7252753548047892, "learning_rate": 9.500095563511119e-07, "loss": 0.30105769634246826, "num_input_tokens_seen": 979318192, "step": 23780, "train_runtime": 91622.4109, "train_tokens_per_second": 10688.632 }, { "epoch": 1.601467815782386, "grad_norm": 0.6582575245132235, "learning_rate": 9.484595469550445e-07, "loss": 0.29169430732727053, "num_input_tokens_seen": 979529616, "step": 23785, "train_runtime": 91641.8831, "train_tokens_per_second": 10688.667 }, { "epoch": 1.6018044707783463, "grad_norm": 0.660001821950523, "learning_rate": 9.469106705593462e-07, "loss": 0.2792278528213501, "num_input_tokens_seen": 979721784, "step": 23790, "train_runtime": 91660.6343, "train_tokens_per_second": 10688.577 }, { "epoch": 1.6021411257743066, "grad_norm": 0.8803153935193354, "learning_rate": 9.453629275971549e-07, "loss": 0.2972386121749878, "num_input_tokens_seen": 979928264, "step": 23795, "train_runtime": 91678.3124, "train_tokens_per_second": 10688.769 }, { "epoch": 1.6024777807702666, "grad_norm": 0.7260963723107401, "learning_rate": 9.438163185012916e-07, "loss": 0.28862924575805665, "num_input_tokens_seen": 980127184, "step": 23800, "train_runtime": 91697.1323, "train_tokens_per_second": 10688.744 }, { "epoch": 1.6028144357662266, "grad_norm": 0.6928995277930162, "learning_rate": 9.422708437042604e-07, "loss": 0.28379068374633787, "num_input_tokens_seen": 980340704, "step": 23805, "train_runtime": 91715.7923, "train_tokens_per_second": 10688.898 }, { "epoch": 1.6031510907621869, "grad_norm": 0.6974130802812221, "learning_rate": 9.40726503638249e-07, "loss": 0.3141864538192749, "num_input_tokens_seen": 980543168, "step": 23810, "train_runtime": 91734.2089, "train_tokens_per_second": 10688.959 }, { "epoch": 1.6034877457581471, "grad_norm": 0.7222391952438697, "learning_rate": 9.391832987351268e-07, "loss": 0.3016597986221313, "num_input_tokens_seen": 980745056, "step": 23815, "train_runtime": 91753.2514, "train_tokens_per_second": 10688.941 }, { "epoch": 1.6038244007541071, "grad_norm": 0.767815169004756, "learning_rate": 9.376412294264458e-07, "loss": 0.3000552415847778, "num_input_tokens_seen": 980953984, "step": 23820, "train_runtime": 91773.6291, "train_tokens_per_second": 10688.844 }, { "epoch": 1.6041610557500672, "grad_norm": 0.6693716320236536, "learning_rate": 9.361002961434401e-07, "loss": 0.29968829154968263, "num_input_tokens_seen": 981159456, "step": 23825, "train_runtime": 91794.1236, "train_tokens_per_second": 10688.696 }, { "epoch": 1.6044977107460274, "grad_norm": 0.7512588447252189, "learning_rate": 9.345604993170299e-07, "loss": 0.3123624324798584, "num_input_tokens_seen": 981372664, "step": 23830, "train_runtime": 91813.2137, "train_tokens_per_second": 10688.795 }, { "epoch": 1.6048343657419877, "grad_norm": 0.7544733872605534, "learning_rate": 9.330218393778101e-07, "loss": 0.29471185207366946, "num_input_tokens_seen": 981568120, "step": 23835, "train_runtime": 91832.3793, "train_tokens_per_second": 10688.693 }, { "epoch": 1.6051710207379477, "grad_norm": 0.7875517221030692, "learning_rate": 9.314843167560656e-07, "loss": 0.2943143129348755, "num_input_tokens_seen": 981768456, "step": 23840, "train_runtime": 91850.0374, "train_tokens_per_second": 10688.819 }, { "epoch": 1.6055076757339077, "grad_norm": 0.6658524791045161, "learning_rate": 9.299479318817578e-07, "loss": 0.28782119750976565, "num_input_tokens_seen": 981970136, "step": 23845, "train_runtime": 91868.2228, "train_tokens_per_second": 10688.899 }, { "epoch": 1.605844330729868, "grad_norm": 0.7333740638222662, "learning_rate": 9.284126851845316e-07, "loss": 0.2822941780090332, "num_input_tokens_seen": 982189384, "step": 23850, "train_runtime": 91886.7947, "train_tokens_per_second": 10689.124 }, { "epoch": 1.6061809857258282, "grad_norm": 0.7252562480698304, "learning_rate": 9.268785770937172e-07, "loss": 0.3021427392959595, "num_input_tokens_seen": 982392440, "step": 23855, "train_runtime": 91905.444, "train_tokens_per_second": 10689.165 }, { "epoch": 1.6065176407217883, "grad_norm": 0.7641557498192943, "learning_rate": 9.253456080383178e-07, "loss": 0.3090315818786621, "num_input_tokens_seen": 982599912, "step": 23860, "train_runtime": 91925.3833, "train_tokens_per_second": 10689.103 }, { "epoch": 1.6068542957177483, "grad_norm": 0.7724238281095002, "learning_rate": 9.238137784470286e-07, "loss": 0.32960782051086424, "num_input_tokens_seen": 982794144, "step": 23865, "train_runtime": 91943.2528, "train_tokens_per_second": 10689.138 }, { "epoch": 1.6071909507137085, "grad_norm": 0.7531107397558114, "learning_rate": 9.222830887482153e-07, "loss": 0.2682220935821533, "num_input_tokens_seen": 983003408, "step": 23870, "train_runtime": 91961.5573, "train_tokens_per_second": 10689.286 }, { "epoch": 1.6075276057096688, "grad_norm": 0.8386276537933954, "learning_rate": 9.207535393699351e-07, "loss": 0.31032543182373046, "num_input_tokens_seen": 983199528, "step": 23875, "train_runtime": 91979.6741, "train_tokens_per_second": 10689.313 }, { "epoch": 1.6078642607056288, "grad_norm": 0.7469447163130063, "learning_rate": 9.192251307399197e-07, "loss": 0.29808993339538575, "num_input_tokens_seen": 983405712, "step": 23880, "train_runtime": 91999.2269, "train_tokens_per_second": 10689.282 }, { "epoch": 1.6082009157015889, "grad_norm": 0.7280535848606651, "learning_rate": 9.176978632855842e-07, "loss": 0.2919490814208984, "num_input_tokens_seen": 983611584, "step": 23885, "train_runtime": 92017.8026, "train_tokens_per_second": 10689.362 }, { "epoch": 1.608537570697549, "grad_norm": 0.6515892812794053, "learning_rate": 9.161717374340235e-07, "loss": 0.2864096641540527, "num_input_tokens_seen": 983831208, "step": 23890, "train_runtime": 92035.8229, "train_tokens_per_second": 10689.655 }, { "epoch": 1.6088742256935094, "grad_norm": 0.841292309801706, "learning_rate": 9.14646753612014e-07, "loss": 0.30292587280273436, "num_input_tokens_seen": 984040104, "step": 23895, "train_runtime": 92054.2344, "train_tokens_per_second": 10689.786 }, { "epoch": 1.6092108806894694, "grad_norm": 0.6773793491408695, "learning_rate": 9.131229122460112e-07, "loss": 0.29511046409606934, "num_input_tokens_seen": 984260632, "step": 23900, "train_runtime": 92073.2384, "train_tokens_per_second": 10689.975 }, { "epoch": 1.6095475356854294, "grad_norm": 0.6841194628901079, "learning_rate": 9.116002137621566e-07, "loss": 0.29911465644836427, "num_input_tokens_seen": 984466656, "step": 23905, "train_runtime": 92091.384, "train_tokens_per_second": 10690.106 }, { "epoch": 1.6098841906813897, "grad_norm": 0.7791157874753905, "learning_rate": 9.100786585862626e-07, "loss": 0.329285717010498, "num_input_tokens_seen": 984659752, "step": 23910, "train_runtime": 92110.7951, "train_tokens_per_second": 10689.95 }, { "epoch": 1.61022084567735, "grad_norm": 0.795264831483333, "learning_rate": 9.085582471438326e-07, "loss": 0.30430405139923095, "num_input_tokens_seen": 984864440, "step": 23915, "train_runtime": 92130.1225, "train_tokens_per_second": 10689.929 }, { "epoch": 1.61055750067331, "grad_norm": 0.8953103246135228, "learning_rate": 9.070389798600394e-07, "loss": 0.30960884094238283, "num_input_tokens_seen": 985065312, "step": 23920, "train_runtime": 92148.0869, "train_tokens_per_second": 10690.025 }, { "epoch": 1.61089415566927, "grad_norm": 0.7701940478477252, "learning_rate": 9.055208571597451e-07, "loss": 0.30399260520935056, "num_input_tokens_seen": 985270352, "step": 23925, "train_runtime": 92165.6, "train_tokens_per_second": 10690.218 }, { "epoch": 1.6112308106652302, "grad_norm": 0.7895076965606541, "learning_rate": 9.040038794674872e-07, "loss": 0.30699183940887453, "num_input_tokens_seen": 985478752, "step": 23930, "train_runtime": 92184.6991, "train_tokens_per_second": 10690.264 }, { "epoch": 1.6115674656611905, "grad_norm": 0.7890846196870782, "learning_rate": 9.024880472074831e-07, "loss": 0.2865405559539795, "num_input_tokens_seen": 985673632, "step": 23935, "train_runtime": 92205.0178, "train_tokens_per_second": 10690.022 }, { "epoch": 1.6119041206571505, "grad_norm": 0.6799090513382124, "learning_rate": 9.009733608036308e-07, "loss": 0.3066180467605591, "num_input_tokens_seen": 985885920, "step": 23940, "train_runtime": 92224.183, "train_tokens_per_second": 10690.102 }, { "epoch": 1.6122407756531107, "grad_norm": 0.7431840072353152, "learning_rate": 8.994598206795068e-07, "loss": 0.2973369359970093, "num_input_tokens_seen": 986087504, "step": 23945, "train_runtime": 92242.0195, "train_tokens_per_second": 10690.22 }, { "epoch": 1.612577430649071, "grad_norm": 0.7070284194377436, "learning_rate": 8.979474272583672e-07, "loss": 0.2915219783782959, "num_input_tokens_seen": 986284064, "step": 23950, "train_runtime": 92260.8292, "train_tokens_per_second": 10690.171 }, { "epoch": 1.612914085645031, "grad_norm": 0.7191044995539249, "learning_rate": 8.964361809631517e-07, "loss": 0.31426057815551756, "num_input_tokens_seen": 986496952, "step": 23955, "train_runtime": 92280.8907, "train_tokens_per_second": 10690.154 }, { "epoch": 1.613250740640991, "grad_norm": 0.7584236030280872, "learning_rate": 8.949260822164707e-07, "loss": 0.31198673248291015, "num_input_tokens_seen": 986703816, "step": 23960, "train_runtime": 92298.9893, "train_tokens_per_second": 10690.299 }, { "epoch": 1.6135873956369513, "grad_norm": 0.7065551395121805, "learning_rate": 8.934171314406226e-07, "loss": 0.30185296535491946, "num_input_tokens_seen": 986915440, "step": 23965, "train_runtime": 92318.3095, "train_tokens_per_second": 10690.354 }, { "epoch": 1.6139240506329116, "grad_norm": 0.7446288028370255, "learning_rate": 8.919093290575765e-07, "loss": 0.301640248298645, "num_input_tokens_seen": 987112304, "step": 23970, "train_runtime": 92338.1617, "train_tokens_per_second": 10690.188 }, { "epoch": 1.6142607056288716, "grad_norm": 0.7649717345986452, "learning_rate": 8.904026754889877e-07, "loss": 0.30121912956237795, "num_input_tokens_seen": 987311800, "step": 23975, "train_runtime": 92358.3758, "train_tokens_per_second": 10690.008 }, { "epoch": 1.6145973606248316, "grad_norm": 0.8224885459510777, "learning_rate": 8.888971711561867e-07, "loss": 0.3167358636856079, "num_input_tokens_seen": 987510656, "step": 23980, "train_runtime": 92377.6179, "train_tokens_per_second": 10689.934 }, { "epoch": 1.6149340156207919, "grad_norm": 0.8438656750297799, "learning_rate": 8.873928164801821e-07, "loss": 0.331290078163147, "num_input_tokens_seen": 987720096, "step": 23985, "train_runtime": 92395.7469, "train_tokens_per_second": 10690.103 }, { "epoch": 1.6152706706167521, "grad_norm": 0.699894390973498, "learning_rate": 8.858896118816624e-07, "loss": 0.29380648136138915, "num_input_tokens_seen": 987902128, "step": 23990, "train_runtime": 92415.51, "train_tokens_per_second": 10689.787 }, { "epoch": 1.6156073256127121, "grad_norm": 0.7094819008507347, "learning_rate": 8.84387557780994e-07, "loss": 0.2831032991409302, "num_input_tokens_seen": 988100968, "step": 23995, "train_runtime": 92435.3105, "train_tokens_per_second": 10689.648 }, { "epoch": 1.6159439806086722, "grad_norm": 0.7954055750850156, "learning_rate": 8.828866545982196e-07, "loss": 0.2828115224838257, "num_input_tokens_seen": 988309848, "step": 24000, "train_runtime": 92455.0568, "train_tokens_per_second": 10689.625 }, { "epoch": 1.6162806356046324, "grad_norm": 0.683726009935005, "learning_rate": 8.813869027530664e-07, "loss": 0.2889594078063965, "num_input_tokens_seen": 988523640, "step": 24005, "train_runtime": 92476.8675, "train_tokens_per_second": 10689.415 }, { "epoch": 1.6166172906005927, "grad_norm": 0.7569577451967665, "learning_rate": 8.798883026649302e-07, "loss": 0.31429908275604246, "num_input_tokens_seen": 988739968, "step": 24010, "train_runtime": 92495.3104, "train_tokens_per_second": 10689.623 }, { "epoch": 1.6169539455965527, "grad_norm": 0.6090028964912076, "learning_rate": 8.783908547528947e-07, "loss": 0.2657804012298584, "num_input_tokens_seen": 988941120, "step": 24015, "train_runtime": 92513.2072, "train_tokens_per_second": 10689.729 }, { "epoch": 1.6172906005925127, "grad_norm": 0.7616823028113863, "learning_rate": 8.768945594357109e-07, "loss": 0.2984952926635742, "num_input_tokens_seen": 989142040, "step": 24020, "train_runtime": 92532.9771, "train_tokens_per_second": 10689.617 }, { "epoch": 1.617627255588473, "grad_norm": 0.8183779820247797, "learning_rate": 8.753994171318175e-07, "loss": 0.30951991081237795, "num_input_tokens_seen": 989338240, "step": 24025, "train_runtime": 92551.3398, "train_tokens_per_second": 10689.616 }, { "epoch": 1.6179639105844332, "grad_norm": 0.6845932084322668, "learning_rate": 8.739054282593245e-07, "loss": 0.3179972171783447, "num_input_tokens_seen": 989549408, "step": 24030, "train_runtime": 92571.131, "train_tokens_per_second": 10689.611 }, { "epoch": 1.6183005655803933, "grad_norm": 0.7790970801611095, "learning_rate": 8.724125932360217e-07, "loss": 0.3089434146881104, "num_input_tokens_seen": 989749264, "step": 24035, "train_runtime": 92589.1067, "train_tokens_per_second": 10689.694 }, { "epoch": 1.6186372205763533, "grad_norm": 0.7140988125080636, "learning_rate": 8.70920912479375e-07, "loss": 0.3172154903411865, "num_input_tokens_seen": 989949152, "step": 24040, "train_runtime": 92608.0244, "train_tokens_per_second": 10689.669 }, { "epoch": 1.6189738755723135, "grad_norm": 0.7473022963786795, "learning_rate": 8.694303864065285e-07, "loss": 0.30105292797088623, "num_input_tokens_seen": 990164112, "step": 24045, "train_runtime": 92627.504, "train_tokens_per_second": 10689.742 }, { "epoch": 1.6193105305682738, "grad_norm": 0.6862136614406109, "learning_rate": 8.679410154343015e-07, "loss": 0.292303729057312, "num_input_tokens_seen": 990370928, "step": 24050, "train_runtime": 92645.7896, "train_tokens_per_second": 10689.864 }, { "epoch": 1.6196471855642338, "grad_norm": 0.7785021401074266, "learning_rate": 8.664527999791961e-07, "loss": 0.33053390979766845, "num_input_tokens_seen": 990576568, "step": 24055, "train_runtime": 92665.5241, "train_tokens_per_second": 10689.807 }, { "epoch": 1.6199838405601938, "grad_norm": 0.7383754165866477, "learning_rate": 8.649657404573819e-07, "loss": 0.29567632675170896, "num_input_tokens_seen": 990791576, "step": 24060, "train_runtime": 92686.4594, "train_tokens_per_second": 10689.712 }, { "epoch": 1.620320495556154, "grad_norm": 0.7979609779497716, "learning_rate": 8.634798372847148e-07, "loss": 0.3177814960479736, "num_input_tokens_seen": 991000544, "step": 24065, "train_runtime": 92704.6504, "train_tokens_per_second": 10689.869 }, { "epoch": 1.6206571505521143, "grad_norm": 0.7607544332098055, "learning_rate": 8.619950908767189e-07, "loss": 0.26908459663391116, "num_input_tokens_seen": 991192888, "step": 24070, "train_runtime": 92725.7244, "train_tokens_per_second": 10689.514 }, { "epoch": 1.6209938055480744, "grad_norm": 0.6682501143332923, "learning_rate": 8.605115016486016e-07, "loss": 0.2877199649810791, "num_input_tokens_seen": 991410032, "step": 24075, "train_runtime": 92744.4511, "train_tokens_per_second": 10689.696 }, { "epoch": 1.6213304605440344, "grad_norm": 0.8283918900476683, "learning_rate": 8.590290700152426e-07, "loss": 0.2786327123641968, "num_input_tokens_seen": 991616392, "step": 24080, "train_runtime": 92765.9329, "train_tokens_per_second": 10689.446 }, { "epoch": 1.6216671155399947, "grad_norm": 0.7409008441870834, "learning_rate": 8.575477963912005e-07, "loss": 0.29974267482757566, "num_input_tokens_seen": 991827408, "step": 24085, "train_runtime": 92785.051, "train_tokens_per_second": 10689.517 }, { "epoch": 1.622003770535955, "grad_norm": 0.8294652906195588, "learning_rate": 8.560676811907071e-07, "loss": 0.30840725898742677, "num_input_tokens_seen": 992036200, "step": 24090, "train_runtime": 92804.5616, "train_tokens_per_second": 10689.52 }, { "epoch": 1.622340425531915, "grad_norm": 0.9213738466072732, "learning_rate": 8.54588724827673e-07, "loss": 0.2896758556365967, "num_input_tokens_seen": 992223536, "step": 24095, "train_runtime": 92824.871, "train_tokens_per_second": 10689.199 }, { "epoch": 1.622677080527875, "grad_norm": 0.7344949649979977, "learning_rate": 8.531109277156818e-07, "loss": 0.2951209306716919, "num_input_tokens_seen": 992440120, "step": 24100, "train_runtime": 92843.192, "train_tokens_per_second": 10689.423 }, { "epoch": 1.6230137355238352, "grad_norm": 0.5937212363785379, "learning_rate": 8.516342902679986e-07, "loss": 0.2674710273742676, "num_input_tokens_seen": 992639128, "step": 24105, "train_runtime": 92863.3977, "train_tokens_per_second": 10689.24 }, { "epoch": 1.6233503905197955, "grad_norm": 0.6820827128750717, "learning_rate": 8.501588128975557e-07, "loss": 0.2740818738937378, "num_input_tokens_seen": 992849184, "step": 24110, "train_runtime": 92881.374, "train_tokens_per_second": 10689.433 }, { "epoch": 1.6236870455157555, "grad_norm": 0.7188401548440503, "learning_rate": 8.486844960169704e-07, "loss": 0.2813979148864746, "num_input_tokens_seen": 993055208, "step": 24115, "train_runtime": 92901.626, "train_tokens_per_second": 10689.32 }, { "epoch": 1.6240237005117155, "grad_norm": 0.736334451086244, "learning_rate": 8.472113400385257e-07, "loss": 0.27677011489868164, "num_input_tokens_seen": 993268712, "step": 24120, "train_runtime": 92922.8701, "train_tokens_per_second": 10689.174 }, { "epoch": 1.6243603555076758, "grad_norm": 0.6982484960648179, "learning_rate": 8.457393453741886e-07, "loss": 0.29508090019226074, "num_input_tokens_seen": 993470536, "step": 24125, "train_runtime": 92944.3121, "train_tokens_per_second": 10688.879 }, { "epoch": 1.624697010503636, "grad_norm": 0.8674725677811216, "learning_rate": 8.442685124355965e-07, "loss": 0.2836089372634888, "num_input_tokens_seen": 993672328, "step": 24130, "train_runtime": 92962.4315, "train_tokens_per_second": 10688.967 }, { "epoch": 1.625033665499596, "grad_norm": 0.7354891903200634, "learning_rate": 8.427988416340633e-07, "loss": 0.3229799747467041, "num_input_tokens_seen": 993864712, "step": 24135, "train_runtime": 92981.8979, "train_tokens_per_second": 10688.798 }, { "epoch": 1.625370320495556, "grad_norm": 0.8001461573713117, "learning_rate": 8.413303333805777e-07, "loss": 0.29042716026306153, "num_input_tokens_seen": 994068960, "step": 24140, "train_runtime": 93003.1257, "train_tokens_per_second": 10688.554 }, { "epoch": 1.6257069754915163, "grad_norm": 0.788179015095593, "learning_rate": 8.398629880858034e-07, "loss": 0.3109175682067871, "num_input_tokens_seen": 994286024, "step": 24145, "train_runtime": 93022.7374, "train_tokens_per_second": 10688.634 }, { "epoch": 1.6260436304874766, "grad_norm": 0.6621670605084431, "learning_rate": 8.383968061600778e-07, "loss": 0.30820398330688475, "num_input_tokens_seen": 994484888, "step": 24150, "train_runtime": 93042.3612, "train_tokens_per_second": 10688.517 }, { "epoch": 1.6263802854834366, "grad_norm": 0.6634752764385831, "learning_rate": 8.36931788013417e-07, "loss": 0.2862269163131714, "num_input_tokens_seen": 994695776, "step": 24155, "train_runtime": 93061.5846, "train_tokens_per_second": 10688.576 }, { "epoch": 1.6267169404793966, "grad_norm": 0.7551073910337345, "learning_rate": 8.354679340555044e-07, "loss": 0.30238473415374756, "num_input_tokens_seen": 994894632, "step": 24160, "train_runtime": 93080.0897, "train_tokens_per_second": 10688.587 }, { "epoch": 1.6270535954753569, "grad_norm": 0.7082244929615231, "learning_rate": 8.34005244695707e-07, "loss": 0.2881366968154907, "num_input_tokens_seen": 995094744, "step": 24165, "train_runtime": 93097.7106, "train_tokens_per_second": 10688.713 }, { "epoch": 1.6273902504713171, "grad_norm": 0.6438467144876752, "learning_rate": 8.325437203430558e-07, "loss": 0.2949963569641113, "num_input_tokens_seen": 995302600, "step": 24170, "train_runtime": 93118.045, "train_tokens_per_second": 10688.611 }, { "epoch": 1.6277269054672772, "grad_norm": 0.6936175871476294, "learning_rate": 8.310833614062652e-07, "loss": 0.29209322929382325, "num_input_tokens_seen": 995506136, "step": 24175, "train_runtime": 93137.4829, "train_tokens_per_second": 10688.566 }, { "epoch": 1.6280635604632372, "grad_norm": 0.8379400899986726, "learning_rate": 8.296241682937189e-07, "loss": 0.30294482707977294, "num_input_tokens_seen": 995719560, "step": 24180, "train_runtime": 93157.639, "train_tokens_per_second": 10688.544 }, { "epoch": 1.6284002154591974, "grad_norm": 0.7283072454606854, "learning_rate": 8.281661414134761e-07, "loss": 0.3027581453323364, "num_input_tokens_seen": 995920552, "step": 24185, "train_runtime": 93176.2864, "train_tokens_per_second": 10688.562 }, { "epoch": 1.6287368704551577, "grad_norm": 0.7193525251285876, "learning_rate": 8.267092811732686e-07, "loss": 0.3119077444076538, "num_input_tokens_seen": 996129664, "step": 24190, "train_runtime": 93195.7506, "train_tokens_per_second": 10688.574 }, { "epoch": 1.6290735254511177, "grad_norm": 0.6721405865661512, "learning_rate": 8.252535879805029e-07, "loss": 0.27401974201202395, "num_input_tokens_seen": 996342848, "step": 24195, "train_runtime": 93215.2107, "train_tokens_per_second": 10688.629 }, { "epoch": 1.6294101804470777, "grad_norm": 0.8225145428041437, "learning_rate": 8.237990622422576e-07, "loss": 0.2896445274353027, "num_input_tokens_seen": 996549104, "step": 24200, "train_runtime": 93234.1568, "train_tokens_per_second": 10688.67 }, { "epoch": 1.629746835443038, "grad_norm": 0.6984002756442916, "learning_rate": 8.223457043652905e-07, "loss": 0.31049294471740724, "num_input_tokens_seen": 996756448, "step": 24205, "train_runtime": 93252.6945, "train_tokens_per_second": 10688.768 }, { "epoch": 1.6300834904389983, "grad_norm": 0.903344969974164, "learning_rate": 8.208935147560227e-07, "loss": 0.2891451120376587, "num_input_tokens_seen": 996942120, "step": 24210, "train_runtime": 93271.1133, "train_tokens_per_second": 10688.648 }, { "epoch": 1.6304201454349583, "grad_norm": 0.7214532598050054, "learning_rate": 8.194424938205597e-07, "loss": 0.3242331981658936, "num_input_tokens_seen": 997161664, "step": 24215, "train_runtime": 93290.5284, "train_tokens_per_second": 10688.777 }, { "epoch": 1.6307568004309183, "grad_norm": 0.7058033526701504, "learning_rate": 8.179926419646705e-07, "loss": 0.2828759908676147, "num_input_tokens_seen": 997366192, "step": 24220, "train_runtime": 93308.2799, "train_tokens_per_second": 10688.936 }, { "epoch": 1.6310934554268786, "grad_norm": 0.7710239296164126, "learning_rate": 8.165439595938047e-07, "loss": 0.3232009172439575, "num_input_tokens_seen": 997558768, "step": 24225, "train_runtime": 93329.0877, "train_tokens_per_second": 10688.616 }, { "epoch": 1.6314301104228388, "grad_norm": 0.7167664541562199, "learning_rate": 8.150964471130801e-07, "loss": 0.27013506889343264, "num_input_tokens_seen": 997772016, "step": 24230, "train_runtime": 93348.0609, "train_tokens_per_second": 10688.728 }, { "epoch": 1.6317667654187988, "grad_norm": 0.7110150302404179, "learning_rate": 8.136501049272899e-07, "loss": 0.3069852113723755, "num_input_tokens_seen": 997975552, "step": 24235, "train_runtime": 93367.0282, "train_tokens_per_second": 10688.736 }, { "epoch": 1.6321034204147589, "grad_norm": 0.7008758946098895, "learning_rate": 8.122049334408983e-07, "loss": 0.29677021503448486, "num_input_tokens_seen": 998178288, "step": 24240, "train_runtime": 93384.1631, "train_tokens_per_second": 10688.946 }, { "epoch": 1.6324400754107191, "grad_norm": 0.6571251809064691, "learning_rate": 8.107609330580429e-07, "loss": 0.2929670810699463, "num_input_tokens_seen": 998382520, "step": 24245, "train_runtime": 93403.7595, "train_tokens_per_second": 10688.89 }, { "epoch": 1.6327767304066794, "grad_norm": 0.7171510123105993, "learning_rate": 8.093181041825332e-07, "loss": 0.3038928985595703, "num_input_tokens_seen": 998592264, "step": 24250, "train_runtime": 93424.8639, "train_tokens_per_second": 10688.721 }, { "epoch": 1.6331133854026394, "grad_norm": 0.7264841289938003, "learning_rate": 8.078764472178552e-07, "loss": 0.29544763565063475, "num_input_tokens_seen": 998794280, "step": 24255, "train_runtime": 93444.5136, "train_tokens_per_second": 10688.635 }, { "epoch": 1.6334500403985994, "grad_norm": 0.6332806759202246, "learning_rate": 8.06435962567158e-07, "loss": 0.32688441276550295, "num_input_tokens_seen": 998979504, "step": 24260, "train_runtime": 93464.4191, "train_tokens_per_second": 10688.34 }, { "epoch": 1.6337866953945597, "grad_norm": 0.6873875735769635, "learning_rate": 8.049966506332746e-07, "loss": 0.2640297651290894, "num_input_tokens_seen": 999185728, "step": 24265, "train_runtime": 93481.8024, "train_tokens_per_second": 10688.559 }, { "epoch": 1.63412335039052, "grad_norm": 0.6617735541701791, "learning_rate": 8.035585118186984e-07, "loss": 0.2836017370223999, "num_input_tokens_seen": 999383624, "step": 24270, "train_runtime": 93500.1019, "train_tokens_per_second": 10688.583 }, { "epoch": 1.63446000538648, "grad_norm": 0.7404130511725403, "learning_rate": 8.021215465256038e-07, "loss": 0.2796090364456177, "num_input_tokens_seen": 999597544, "step": 24275, "train_runtime": 93520.63, "train_tokens_per_second": 10688.524 }, { "epoch": 1.63479666038244, "grad_norm": 0.7000119333369919, "learning_rate": 8.006857551558328e-07, "loss": 0.2983422756195068, "num_input_tokens_seen": 999802824, "step": 24280, "train_runtime": 93539.855, "train_tokens_per_second": 10688.522 }, { "epoch": 1.6351333153784002, "grad_norm": 0.7411548552147317, "learning_rate": 7.992511381108997e-07, "loss": 0.30780029296875, "num_input_tokens_seen": 1000027752, "step": 24285, "train_runtime": 93558.5898, "train_tokens_per_second": 10688.786 }, { "epoch": 1.6354699703743605, "grad_norm": 0.7378474519138619, "learning_rate": 7.978176957919909e-07, "loss": 0.30387153625488283, "num_input_tokens_seen": 1000227496, "step": 24290, "train_runtime": 93577.2249, "train_tokens_per_second": 10688.792 }, { "epoch": 1.6358066253703205, "grad_norm": 0.6265836602418628, "learning_rate": 7.963854285999634e-07, "loss": 0.2744173049926758, "num_input_tokens_seen": 1000433736, "step": 24295, "train_runtime": 93596.2086, "train_tokens_per_second": 10688.828 }, { "epoch": 1.6361432803662805, "grad_norm": 0.8144986743884542, "learning_rate": 7.949543369353452e-07, "loss": 0.3033405542373657, "num_input_tokens_seen": 1000623856, "step": 24300, "train_runtime": 93614.921, "train_tokens_per_second": 10688.722 }, { "epoch": 1.6364799353622408, "grad_norm": 0.6905817732798167, "learning_rate": 7.9352442119834e-07, "loss": 0.3196810007095337, "num_input_tokens_seen": 1000825688, "step": 24305, "train_runtime": 93634.6048, "train_tokens_per_second": 10688.63 }, { "epoch": 1.636816590358201, "grad_norm": 0.742114652401845, "learning_rate": 7.920956817888148e-07, "loss": 0.3061820983886719, "num_input_tokens_seen": 1001030960, "step": 24310, "train_runtime": 93654.1252, "train_tokens_per_second": 10688.594 }, { "epoch": 1.637153245354161, "grad_norm": 0.834722549146527, "learning_rate": 7.906681191063165e-07, "loss": 0.28836426734924314, "num_input_tokens_seen": 1001239512, "step": 24315, "train_runtime": 93673.8952, "train_tokens_per_second": 10688.565 }, { "epoch": 1.637489900350121, "grad_norm": 0.7372943936532802, "learning_rate": 7.892417335500541e-07, "loss": 0.3043433666229248, "num_input_tokens_seen": 1001437632, "step": 24320, "train_runtime": 93692.1895, "train_tokens_per_second": 10688.592 }, { "epoch": 1.6378265553460813, "grad_norm": 0.7812420586512179, "learning_rate": 7.878165255189146e-07, "loss": 0.31844539642333985, "num_input_tokens_seen": 1001630328, "step": 24325, "train_runtime": 93712.1045, "train_tokens_per_second": 10688.377 }, { "epoch": 1.6381632103420416, "grad_norm": 0.8837122436406218, "learning_rate": 7.863924954114522e-07, "loss": 0.2878684997558594, "num_input_tokens_seen": 1001825248, "step": 24330, "train_runtime": 93729.8963, "train_tokens_per_second": 10688.428 }, { "epoch": 1.6384998653380016, "grad_norm": 0.6659351040650733, "learning_rate": 7.849696436258919e-07, "loss": 0.28220386505126954, "num_input_tokens_seen": 1002025928, "step": 24335, "train_runtime": 93748.1168, "train_tokens_per_second": 10688.491 }, { "epoch": 1.6388365203339617, "grad_norm": 0.7064767627173337, "learning_rate": 7.835479705601307e-07, "loss": 0.31432178020477297, "num_input_tokens_seen": 1002221984, "step": 24340, "train_runtime": 93766.6091, "train_tokens_per_second": 10688.474 }, { "epoch": 1.639173175329922, "grad_norm": 0.6716068908371607, "learning_rate": 7.821274766117337e-07, "loss": 0.30405824184417723, "num_input_tokens_seen": 1002427240, "step": 24345, "train_runtime": 93786.7211, "train_tokens_per_second": 10688.371 }, { "epoch": 1.6395098303258822, "grad_norm": 0.7586854822532219, "learning_rate": 7.807081621779367e-07, "loss": 0.3221384286880493, "num_input_tokens_seen": 1002636184, "step": 24350, "train_runtime": 93806.6869, "train_tokens_per_second": 10688.323 }, { "epoch": 1.6398464853218422, "grad_norm": 0.6636523591408788, "learning_rate": 7.792900276556509e-07, "loss": 0.30629515647888184, "num_input_tokens_seen": 1002847992, "step": 24355, "train_runtime": 93825.7935, "train_tokens_per_second": 10688.404 }, { "epoch": 1.6401831403178022, "grad_norm": 0.8246315585000502, "learning_rate": 7.778730734414469e-07, "loss": 0.30146036148071287, "num_input_tokens_seen": 1003050152, "step": 24360, "train_runtime": 93844.0469, "train_tokens_per_second": 10688.479 }, { "epoch": 1.6405197953137625, "grad_norm": 0.7291584157997563, "learning_rate": 7.764572999315772e-07, "loss": 0.29230542182922364, "num_input_tokens_seen": 1003261920, "step": 24365, "train_runtime": 93863.2676, "train_tokens_per_second": 10688.547 }, { "epoch": 1.6408564503097227, "grad_norm": 0.7339865965503954, "learning_rate": 7.750427075219536e-07, "loss": 0.3050410509109497, "num_input_tokens_seen": 1003464264, "step": 24370, "train_runtime": 93883.0766, "train_tokens_per_second": 10688.447 }, { "epoch": 1.6411931053056827, "grad_norm": 0.8541451733367504, "learning_rate": 7.736292966081655e-07, "loss": 0.28686938285827634, "num_input_tokens_seen": 1003649152, "step": 24375, "train_runtime": 93902.6609, "train_tokens_per_second": 10688.186 }, { "epoch": 1.6415297603016428, "grad_norm": 0.6228857594217957, "learning_rate": 7.722170675854673e-07, "loss": 0.2671206474304199, "num_input_tokens_seen": 1003862192, "step": 24380, "train_runtime": 93922.0289, "train_tokens_per_second": 10688.251 }, { "epoch": 1.641866415297603, "grad_norm": 0.7427251535665916, "learning_rate": 7.70806020848785e-07, "loss": 0.28453702926635743, "num_input_tokens_seen": 1004067720, "step": 24385, "train_runtime": 93939.995, "train_tokens_per_second": 10688.394 }, { "epoch": 1.6422030702935633, "grad_norm": 0.681527399974366, "learning_rate": 7.693961567927133e-07, "loss": 0.28522419929504395, "num_input_tokens_seen": 1004276024, "step": 24390, "train_runtime": 93958.5167, "train_tokens_per_second": 10688.504 }, { "epoch": 1.6425397252895233, "grad_norm": 0.6761886528643453, "learning_rate": 7.679874758115153e-07, "loss": 0.28595943450927735, "num_input_tokens_seen": 1004493088, "step": 24395, "train_runtime": 93978.8334, "train_tokens_per_second": 10688.503 }, { "epoch": 1.6428763802854833, "grad_norm": 0.674070138208808, "learning_rate": 7.66579978299124e-07, "loss": 0.29606380462646487, "num_input_tokens_seen": 1004706328, "step": 24400, "train_runtime": 93997.4414, "train_tokens_per_second": 10688.656 }, { "epoch": 1.6432130352814436, "grad_norm": 0.7963679451680683, "learning_rate": 7.651736646491447e-07, "loss": 0.3212648868560791, "num_input_tokens_seen": 1004898536, "step": 24405, "train_runtime": 94017.2858, "train_tokens_per_second": 10688.444 }, { "epoch": 1.6435496902774038, "grad_norm": 0.5978230920806332, "learning_rate": 7.63768535254844e-07, "loss": 0.2697460174560547, "num_input_tokens_seen": 1005104320, "step": 24410, "train_runtime": 94035.9693, "train_tokens_per_second": 10688.509 }, { "epoch": 1.6438863452733639, "grad_norm": 0.762127712209437, "learning_rate": 7.623645905091664e-07, "loss": 0.3027761697769165, "num_input_tokens_seen": 1005312680, "step": 24415, "train_runtime": 94056.3292, "train_tokens_per_second": 10688.411 }, { "epoch": 1.6442230002693239, "grad_norm": 0.7550323308632522, "learning_rate": 7.609618308047156e-07, "loss": 0.3108607530593872, "num_input_tokens_seen": 1005514600, "step": 24420, "train_runtime": 94074.7867, "train_tokens_per_second": 10688.46 }, { "epoch": 1.6445596552652841, "grad_norm": 0.6899490341237091, "learning_rate": 7.595602565337729e-07, "loss": 0.29651384353637694, "num_input_tokens_seen": 1005729016, "step": 24425, "train_runtime": 94094.6839, "train_tokens_per_second": 10688.479 }, { "epoch": 1.6448963102612444, "grad_norm": 0.8141540509416161, "learning_rate": 7.581598680882829e-07, "loss": 0.3208041191101074, "num_input_tokens_seen": 1005936992, "step": 24430, "train_runtime": 94114.0242, "train_tokens_per_second": 10688.492 }, { "epoch": 1.6452329652572044, "grad_norm": 0.7693669242051879, "learning_rate": 7.567606658598592e-07, "loss": 0.2990417957305908, "num_input_tokens_seen": 1006142704, "step": 24435, "train_runtime": 94134.1556, "train_tokens_per_second": 10688.391 }, { "epoch": 1.6455696202531644, "grad_norm": 0.7206117361195641, "learning_rate": 7.553626502397848e-07, "loss": 0.3222554445266724, "num_input_tokens_seen": 1006352328, "step": 24440, "train_runtime": 94155.2851, "train_tokens_per_second": 10688.219 }, { "epoch": 1.6459062752491247, "grad_norm": 0.7248004022984517, "learning_rate": 7.539658216190099e-07, "loss": 0.2802440166473389, "num_input_tokens_seen": 1006560456, "step": 24445, "train_runtime": 94175.2121, "train_tokens_per_second": 10688.168 }, { "epoch": 1.646242930245085, "grad_norm": 0.8040010795551314, "learning_rate": 7.525701803881525e-07, "loss": 0.3048041343688965, "num_input_tokens_seen": 1006758880, "step": 24450, "train_runtime": 94194.0009, "train_tokens_per_second": 10688.142 }, { "epoch": 1.646579585241045, "grad_norm": 0.7499154914658851, "learning_rate": 7.511757269375019e-07, "loss": 0.2837828636169434, "num_input_tokens_seen": 1006958008, "step": 24455, "train_runtime": 94215.4928, "train_tokens_per_second": 10687.818 }, { "epoch": 1.646916240237005, "grad_norm": 0.7251985074873745, "learning_rate": 7.497824616570087e-07, "loss": 0.31569705009460447, "num_input_tokens_seen": 1007147472, "step": 24460, "train_runtime": 94233.7491, "train_tokens_per_second": 10687.758 }, { "epoch": 1.6472528952329653, "grad_norm": 0.6839715035180529, "learning_rate": 7.483903849362995e-07, "loss": 0.30326151847839355, "num_input_tokens_seen": 1007356752, "step": 24465, "train_runtime": 94253.0848, "train_tokens_per_second": 10687.785 }, { "epoch": 1.6475895502289255, "grad_norm": 0.690515816504404, "learning_rate": 7.469994971646594e-07, "loss": 0.30289950370788576, "num_input_tokens_seen": 1007574944, "step": 24470, "train_runtime": 94272.6788, "train_tokens_per_second": 10687.879 }, { "epoch": 1.6479262052248855, "grad_norm": 0.6810917243461493, "learning_rate": 7.456097987310495e-07, "loss": 0.30988149642944335, "num_input_tokens_seen": 1007774552, "step": 24475, "train_runtime": 94292.5481, "train_tokens_per_second": 10687.743 }, { "epoch": 1.6482628602208456, "grad_norm": 0.8461516297643757, "learning_rate": 7.442212900240931e-07, "loss": 0.30913820266723635, "num_input_tokens_seen": 1007976224, "step": 24480, "train_runtime": 94313.1087, "train_tokens_per_second": 10687.552 }, { "epoch": 1.6485995152168058, "grad_norm": 0.7053146243798459, "learning_rate": 7.42833971432082e-07, "loss": 0.2705451488494873, "num_input_tokens_seen": 1008173328, "step": 24485, "train_runtime": 94331.2232, "train_tokens_per_second": 10687.589 }, { "epoch": 1.648936170212766, "grad_norm": 0.7249505717991835, "learning_rate": 7.414478433429756e-07, "loss": 0.30898637771606446, "num_input_tokens_seen": 1008381792, "step": 24490, "train_runtime": 94351.34, "train_tokens_per_second": 10687.52 }, { "epoch": 1.649272825208726, "grad_norm": 0.8014884575789866, "learning_rate": 7.400629061444003e-07, "loss": 0.2899330139160156, "num_input_tokens_seen": 1008590232, "step": 24495, "train_runtime": 94371.8504, "train_tokens_per_second": 10687.405 }, { "epoch": 1.6496094802046861, "grad_norm": 0.6659486116259983, "learning_rate": 7.386791602236482e-07, "loss": 0.3239527463912964, "num_input_tokens_seen": 1008804072, "step": 24500, "train_runtime": 94390.1034, "train_tokens_per_second": 10687.604 }, { "epoch": 1.6499461352006464, "grad_norm": 0.6738747353890898, "learning_rate": 7.372966059676834e-07, "loss": 0.3485828399658203, "num_input_tokens_seen": 1009015160, "step": 24505, "train_runtime": 94410.5084, "train_tokens_per_second": 10687.53 }, { "epoch": 1.6502827901966066, "grad_norm": 0.6820948498361755, "learning_rate": 7.359152437631273e-07, "loss": 0.31439766883850095, "num_input_tokens_seen": 1009224176, "step": 24510, "train_runtime": 94428.8252, "train_tokens_per_second": 10687.671 }, { "epoch": 1.6506194451925666, "grad_norm": 0.6729726699598425, "learning_rate": 7.345350739962781e-07, "loss": 0.2884806156158447, "num_input_tokens_seen": 1009431144, "step": 24515, "train_runtime": 94448.1775, "train_tokens_per_second": 10687.672 }, { "epoch": 1.6509561001885267, "grad_norm": 0.7313130826818395, "learning_rate": 7.331560970530921e-07, "loss": 0.29159677028656006, "num_input_tokens_seen": 1009640336, "step": 24520, "train_runtime": 94467.8648, "train_tokens_per_second": 10687.659 }, { "epoch": 1.651292755184487, "grad_norm": 0.6736166480564961, "learning_rate": 7.317783133191986e-07, "loss": 0.3098663091659546, "num_input_tokens_seen": 1009847936, "step": 24525, "train_runtime": 94485.4987, "train_tokens_per_second": 10687.862 }, { "epoch": 1.6516294101804472, "grad_norm": 0.7388300374389906, "learning_rate": 7.304017231798893e-07, "loss": 0.29330251216888426, "num_input_tokens_seen": 1010058864, "step": 24530, "train_runtime": 94504.4877, "train_tokens_per_second": 10687.946 }, { "epoch": 1.6519660651764072, "grad_norm": 0.8218140965686102, "learning_rate": 7.290263270201231e-07, "loss": 0.29824445247650144, "num_input_tokens_seen": 1010265392, "step": 24535, "train_runtime": 94524.6495, "train_tokens_per_second": 10687.851 }, { "epoch": 1.6523027201723672, "grad_norm": 0.7653948621762311, "learning_rate": 7.276521252245261e-07, "loss": 0.28413450717926025, "num_input_tokens_seen": 1010463456, "step": 24540, "train_runtime": 94543.9522, "train_tokens_per_second": 10687.764 }, { "epoch": 1.6526393751683275, "grad_norm": 0.7395420782142045, "learning_rate": 7.262791181773882e-07, "loss": 0.2901134729385376, "num_input_tokens_seen": 1010675448, "step": 24545, "train_runtime": 94563.1684, "train_tokens_per_second": 10687.834 }, { "epoch": 1.6529760301642877, "grad_norm": 0.7950832801479716, "learning_rate": 7.24907306262666e-07, "loss": 0.31015381813049314, "num_input_tokens_seen": 1010878072, "step": 24550, "train_runtime": 94584.023, "train_tokens_per_second": 10687.62 }, { "epoch": 1.6533126851602478, "grad_norm": 0.7295433895317187, "learning_rate": 7.235366898639856e-07, "loss": 0.3187826633453369, "num_input_tokens_seen": 1011089008, "step": 24555, "train_runtime": 94603.5565, "train_tokens_per_second": 10687.643 }, { "epoch": 1.6536493401562078, "grad_norm": 0.7620079243082428, "learning_rate": 7.221672693646309e-07, "loss": 0.3158267021179199, "num_input_tokens_seen": 1011299496, "step": 24560, "train_runtime": 94622.4854, "train_tokens_per_second": 10687.729 }, { "epoch": 1.653985995152168, "grad_norm": 0.7490594614400347, "learning_rate": 7.207990451475594e-07, "loss": 0.3089115619659424, "num_input_tokens_seen": 1011514176, "step": 24565, "train_runtime": 94640.0368, "train_tokens_per_second": 10688.015 }, { "epoch": 1.6543226501481283, "grad_norm": 0.776638838509645, "learning_rate": 7.194320175953901e-07, "loss": 0.3031835317611694, "num_input_tokens_seen": 1011715752, "step": 24570, "train_runtime": 94659.437, "train_tokens_per_second": 10687.954 }, { "epoch": 1.6546593051440883, "grad_norm": 0.75425464871219, "learning_rate": 7.180661870904066e-07, "loss": 0.28659749031066895, "num_input_tokens_seen": 1011924488, "step": 24575, "train_runtime": 94678.2376, "train_tokens_per_second": 10688.037 }, { "epoch": 1.6549959601400483, "grad_norm": 0.6645497910967454, "learning_rate": 7.167015540145599e-07, "loss": 0.28199708461761475, "num_input_tokens_seen": 1012124344, "step": 24580, "train_runtime": 94698.7843, "train_tokens_per_second": 10687.828 }, { "epoch": 1.6553326151360086, "grad_norm": 0.7161996725784175, "learning_rate": 7.153381187494657e-07, "loss": 0.3062631845474243, "num_input_tokens_seen": 1012329384, "step": 24585, "train_runtime": 94717.7125, "train_tokens_per_second": 10687.857 }, { "epoch": 1.6556692701319689, "grad_norm": 0.7183544024630195, "learning_rate": 7.139758816764036e-07, "loss": 0.28194141387939453, "num_input_tokens_seen": 1012523976, "step": 24590, "train_runtime": 94736.0389, "train_tokens_per_second": 10687.844 }, { "epoch": 1.6560059251279289, "grad_norm": 0.6813263855414263, "learning_rate": 7.126148431763191e-07, "loss": 0.2849756956100464, "num_input_tokens_seen": 1012739600, "step": 24595, "train_runtime": 94755.1496, "train_tokens_per_second": 10687.964 }, { "epoch": 1.656342580123889, "grad_norm": 0.7091300393011172, "learning_rate": 7.11255003629821e-07, "loss": 0.30746915340423586, "num_input_tokens_seen": 1012953456, "step": 24600, "train_runtime": 94773.8062, "train_tokens_per_second": 10688.116 }, { "epoch": 1.6566792351198492, "grad_norm": 0.6290584904532603, "learning_rate": 7.098963634171874e-07, "loss": 0.30080471038818357, "num_input_tokens_seen": 1013174096, "step": 24605, "train_runtime": 94793.0883, "train_tokens_per_second": 10688.27 }, { "epoch": 1.6570158901158094, "grad_norm": 0.833691087214237, "learning_rate": 7.085389229183537e-07, "loss": 0.30675106048583983, "num_input_tokens_seen": 1013362472, "step": 24610, "train_runtime": 94811.7662, "train_tokens_per_second": 10688.151 }, { "epoch": 1.6573525451117694, "grad_norm": 0.7228587534622447, "learning_rate": 7.071826825129264e-07, "loss": 0.29072368144989014, "num_input_tokens_seen": 1013563864, "step": 24615, "train_runtime": 94832.5862, "train_tokens_per_second": 10687.928 }, { "epoch": 1.6576892001077295, "grad_norm": 0.7488423268691274, "learning_rate": 7.058276425801735e-07, "loss": 0.29977965354919434, "num_input_tokens_seen": 1013771552, "step": 24620, "train_runtime": 94852.208, "train_tokens_per_second": 10687.907 }, { "epoch": 1.6580258551036897, "grad_norm": 0.765061158124774, "learning_rate": 7.044738034990273e-07, "loss": 0.2963339567184448, "num_input_tokens_seen": 1013964920, "step": 24625, "train_runtime": 94870.3826, "train_tokens_per_second": 10687.897 }, { "epoch": 1.65836251009965, "grad_norm": 0.7607166929015096, "learning_rate": 7.031211656480841e-07, "loss": 0.317240834236145, "num_input_tokens_seen": 1014166200, "step": 24630, "train_runtime": 94889.599, "train_tokens_per_second": 10687.854 }, { "epoch": 1.65869916509561, "grad_norm": 0.7459298145904613, "learning_rate": 7.017697294056058e-07, "loss": 0.2775655508041382, "num_input_tokens_seen": 1014368504, "step": 24635, "train_runtime": 94911.1827, "train_tokens_per_second": 10687.555 }, { "epoch": 1.65903582009157, "grad_norm": 0.790292642812247, "learning_rate": 7.004194951495163e-07, "loss": 0.3232302188873291, "num_input_tokens_seen": 1014581296, "step": 24640, "train_runtime": 94929.683, "train_tokens_per_second": 10687.714 }, { "epoch": 1.6593724750875303, "grad_norm": 0.7312360431279188, "learning_rate": 6.990704632574046e-07, "loss": 0.2975070238113403, "num_input_tokens_seen": 1014794712, "step": 24645, "train_runtime": 94947.5844, "train_tokens_per_second": 10687.947 }, { "epoch": 1.6597091300834905, "grad_norm": 0.7483990776313156, "learning_rate": 6.977226341065219e-07, "loss": 0.29776859283447266, "num_input_tokens_seen": 1014998816, "step": 24650, "train_runtime": 94965.8275, "train_tokens_per_second": 10688.043 }, { "epoch": 1.6600457850794506, "grad_norm": 0.6839877851667643, "learning_rate": 6.96376008073788e-07, "loss": 0.3063023567199707, "num_input_tokens_seen": 1015192896, "step": 24655, "train_runtime": 94984.2948, "train_tokens_per_second": 10688.008 }, { "epoch": 1.6603824400754106, "grad_norm": 0.6802940008719235, "learning_rate": 6.950305855357781e-07, "loss": 0.2781516551971436, "num_input_tokens_seen": 1015393928, "step": 24660, "train_runtime": 95003.2144, "train_tokens_per_second": 10687.996 }, { "epoch": 1.6607190950713708, "grad_norm": 0.7184615815098137, "learning_rate": 6.936863668687383e-07, "loss": 0.30747575759887696, "num_input_tokens_seen": 1015598072, "step": 24665, "train_runtime": 95023.0496, "train_tokens_per_second": 10687.913 }, { "epoch": 1.661055750067331, "grad_norm": 0.7870214842279438, "learning_rate": 6.923433524485745e-07, "loss": 0.3206217050552368, "num_input_tokens_seen": 1015809608, "step": 24670, "train_runtime": 95042.9556, "train_tokens_per_second": 10687.9 }, { "epoch": 1.6613924050632911, "grad_norm": 0.7382037446688076, "learning_rate": 6.910015426508554e-07, "loss": 0.2924154758453369, "num_input_tokens_seen": 1016020888, "step": 24675, "train_runtime": 95062.3359, "train_tokens_per_second": 10687.944 }, { "epoch": 1.6617290600592511, "grad_norm": 0.7680856379884364, "learning_rate": 6.896609378508152e-07, "loss": 0.3105254411697388, "num_input_tokens_seen": 1016213632, "step": 24680, "train_runtime": 95080.6576, "train_tokens_per_second": 10687.911 }, { "epoch": 1.6620657150552114, "grad_norm": 0.6917626918451768, "learning_rate": 6.883215384233488e-07, "loss": 0.30051960945129397, "num_input_tokens_seen": 1016430240, "step": 24685, "train_runtime": 95099.1285, "train_tokens_per_second": 10688.113 }, { "epoch": 1.6624023700511716, "grad_norm": 0.7646524942210509, "learning_rate": 6.869833447430152e-07, "loss": 0.288275146484375, "num_input_tokens_seen": 1016625552, "step": 24690, "train_runtime": 95118.4194, "train_tokens_per_second": 10687.999 }, { "epoch": 1.6627390250471317, "grad_norm": 0.8403094808533038, "learning_rate": 6.856463571840361e-07, "loss": 0.29941248893737793, "num_input_tokens_seen": 1016820832, "step": 24695, "train_runtime": 95138.4945, "train_tokens_per_second": 10687.796 }, { "epoch": 1.6630756800430917, "grad_norm": 0.7206974611432198, "learning_rate": 6.843105761202945e-07, "loss": 0.3169513702392578, "num_input_tokens_seen": 1017034360, "step": 24700, "train_runtime": 95158.2207, "train_tokens_per_second": 10687.824 }, { "epoch": 1.663412335039052, "grad_norm": 0.7186450199161253, "learning_rate": 6.829760019253412e-07, "loss": 0.313178563117981, "num_input_tokens_seen": 1017238608, "step": 24705, "train_runtime": 95178.0998, "train_tokens_per_second": 10687.738 }, { "epoch": 1.6637489900350122, "grad_norm": 0.6873862436141358, "learning_rate": 6.816426349723804e-07, "loss": 0.3035502672195435, "num_input_tokens_seen": 1017439072, "step": 24710, "train_runtime": 95197.9732, "train_tokens_per_second": 10687.613 }, { "epoch": 1.6640856450309722, "grad_norm": 0.6529183815640075, "learning_rate": 6.803104756342877e-07, "loss": 0.27712445259094237, "num_input_tokens_seen": 1017652064, "step": 24715, "train_runtime": 95218.0007, "train_tokens_per_second": 10687.602 }, { "epoch": 1.6644223000269323, "grad_norm": 0.667784673704325, "learning_rate": 6.789795242835962e-07, "loss": 0.2713497161865234, "num_input_tokens_seen": 1017859112, "step": 24720, "train_runtime": 95238.2856, "train_tokens_per_second": 10687.499 }, { "epoch": 1.6647589550228925, "grad_norm": 0.7246983776876931, "learning_rate": 6.776497812925015e-07, "loss": 0.29989066123962405, "num_input_tokens_seen": 1018056344, "step": 24725, "train_runtime": 95257.2429, "train_tokens_per_second": 10687.443 }, { "epoch": 1.6650956100188528, "grad_norm": 0.7654667983363577, "learning_rate": 6.763212470328628e-07, "loss": 0.3305804967880249, "num_input_tokens_seen": 1018264360, "step": 24730, "train_runtime": 95277.1943, "train_tokens_per_second": 10687.388 }, { "epoch": 1.6654322650148128, "grad_norm": 0.7525650645699657, "learning_rate": 6.749939218762003e-07, "loss": 0.2922225475311279, "num_input_tokens_seen": 1018469808, "step": 24735, "train_runtime": 95297.3078, "train_tokens_per_second": 10687.288 }, { "epoch": 1.6657689200107728, "grad_norm": 0.7299589640793106, "learning_rate": 6.736678061936958e-07, "loss": 0.31871724128723145, "num_input_tokens_seen": 1018687368, "step": 24740, "train_runtime": 95316.068, "train_tokens_per_second": 10687.467 }, { "epoch": 1.666105575006733, "grad_norm": 0.8162485314318763, "learning_rate": 6.723429003561937e-07, "loss": 0.3265735149383545, "num_input_tokens_seen": 1018907664, "step": 24745, "train_runtime": 95333.9739, "train_tokens_per_second": 10687.771 }, { "epoch": 1.6664422300026933, "grad_norm": 0.7272535878980199, "learning_rate": 6.710192047341984e-07, "loss": 0.29885857105255126, "num_input_tokens_seen": 1019117136, "step": 24750, "train_runtime": 95353.5353, "train_tokens_per_second": 10687.775 }, { "epoch": 1.6667788849986533, "grad_norm": 0.7638477880175276, "learning_rate": 6.69696719697881e-07, "loss": 0.29502224922180176, "num_input_tokens_seen": 1019325920, "step": 24755, "train_runtime": 95370.9621, "train_tokens_per_second": 10688.011 }, { "epoch": 1.6671155399946134, "grad_norm": 0.7567516528830579, "learning_rate": 6.683754456170655e-07, "loss": 0.2783820152282715, "num_input_tokens_seen": 1019527312, "step": 24760, "train_runtime": 95389.8143, "train_tokens_per_second": 10688.01 }, { "epoch": 1.6674521949905736, "grad_norm": 0.784706763976522, "learning_rate": 6.670553828612448e-07, "loss": 0.28679397106170657, "num_input_tokens_seen": 1019712720, "step": 24765, "train_runtime": 95408.6868, "train_tokens_per_second": 10687.839 }, { "epoch": 1.6677888499865339, "grad_norm": 0.6603183612311884, "learning_rate": 6.657365317995696e-07, "loss": 0.2885587215423584, "num_input_tokens_seen": 1019918368, "step": 24770, "train_runtime": 95429.1899, "train_tokens_per_second": 10687.698 }, { "epoch": 1.668125504982494, "grad_norm": 0.7021124273184924, "learning_rate": 6.644188928008521e-07, "loss": 0.31823689937591554, "num_input_tokens_seen": 1020118320, "step": 24775, "train_runtime": 95448.9523, "train_tokens_per_second": 10687.58 }, { "epoch": 1.668462159978454, "grad_norm": 0.7725380753132037, "learning_rate": 6.631024662335667e-07, "loss": 0.3103692293167114, "num_input_tokens_seen": 1020323904, "step": 24780, "train_runtime": 95469.488, "train_tokens_per_second": 10687.435 }, { "epoch": 1.6687988149744142, "grad_norm": 0.7116145377039574, "learning_rate": 6.617872524658469e-07, "loss": 0.29567291736602785, "num_input_tokens_seen": 1020537320, "step": 24785, "train_runtime": 95487.4475, "train_tokens_per_second": 10687.659 }, { "epoch": 1.6691354699703744, "grad_norm": 0.7772955562185438, "learning_rate": 6.604732518654882e-07, "loss": 0.3278659820556641, "num_input_tokens_seen": 1020741200, "step": 24790, "train_runtime": 95507.8001, "train_tokens_per_second": 10687.517 }, { "epoch": 1.6694721249663345, "grad_norm": 0.8656585274486377, "learning_rate": 6.591604647999473e-07, "loss": 0.33393757343292235, "num_input_tokens_seen": 1020956936, "step": 24795, "train_runtime": 95527.7615, "train_tokens_per_second": 10687.542 }, { "epoch": 1.6698087799622945, "grad_norm": 0.6693968103541742, "learning_rate": 6.57848891636339e-07, "loss": 0.2821103572845459, "num_input_tokens_seen": 1021169872, "step": 24800, "train_runtime": 95548.7927, "train_tokens_per_second": 10687.418 }, { "epoch": 1.6701454349582547, "grad_norm": 0.7422441210204169, "learning_rate": 6.565385327414441e-07, "loss": 0.31112074851989746, "num_input_tokens_seen": 1021382224, "step": 24805, "train_runtime": 95567.9696, "train_tokens_per_second": 10687.495 }, { "epoch": 1.670482089954215, "grad_norm": 0.7854201667784946, "learning_rate": 6.552293884816968e-07, "loss": 0.28879971504211427, "num_input_tokens_seen": 1021594872, "step": 24810, "train_runtime": 95587.32, "train_tokens_per_second": 10687.556 }, { "epoch": 1.670818744950175, "grad_norm": 0.6870082565195806, "learning_rate": 6.539214592231968e-07, "loss": 0.297025203704834, "num_input_tokens_seen": 1021806512, "step": 24815, "train_runtime": 95605.5887, "train_tokens_per_second": 10687.728 }, { "epoch": 1.671155399946135, "grad_norm": 0.662217864486581, "learning_rate": 6.526147453317028e-07, "loss": 0.26836276054382324, "num_input_tokens_seen": 1022009592, "step": 24820, "train_runtime": 95624.9747, "train_tokens_per_second": 10687.685 }, { "epoch": 1.6714920549420953, "grad_norm": 0.7382020754362613, "learning_rate": 6.513092471726307e-07, "loss": 0.2975008964538574, "num_input_tokens_seen": 1022226536, "step": 24825, "train_runtime": 95643.5517, "train_tokens_per_second": 10687.877 }, { "epoch": 1.6718287099380555, "grad_norm": 0.6935547809339317, "learning_rate": 6.500049651110635e-07, "loss": 0.29288320541381835, "num_input_tokens_seen": 1022436072, "step": 24830, "train_runtime": 95664.41, "train_tokens_per_second": 10687.737 }, { "epoch": 1.6721653649340156, "grad_norm": 0.7118923899211542, "learning_rate": 6.487018995117339e-07, "loss": 0.29261183738708496, "num_input_tokens_seen": 1022655328, "step": 24835, "train_runtime": 95682.0199, "train_tokens_per_second": 10688.062 }, { "epoch": 1.6725020199299756, "grad_norm": 0.7499566286826066, "learning_rate": 6.474000507390455e-07, "loss": 0.29463469982147217, "num_input_tokens_seen": 1022859784, "step": 24840, "train_runtime": 95700.5726, "train_tokens_per_second": 10688.126 }, { "epoch": 1.6728386749259359, "grad_norm": 0.6965250575021728, "learning_rate": 6.460994191570513e-07, "loss": 0.3057586669921875, "num_input_tokens_seen": 1023066896, "step": 24845, "train_runtime": 95719.2587, "train_tokens_per_second": 10688.203 }, { "epoch": 1.673175329921896, "grad_norm": 0.672379810109781, "learning_rate": 6.448000051294717e-07, "loss": 0.28905789852142333, "num_input_tokens_seen": 1023272672, "step": 24850, "train_runtime": 95738.5107, "train_tokens_per_second": 10688.203 }, { "epoch": 1.6735119849178561, "grad_norm": 0.6899297410575715, "learning_rate": 6.435018090196832e-07, "loss": 0.30484714508056643, "num_input_tokens_seen": 1023486560, "step": 24855, "train_runtime": 95756.8694, "train_tokens_per_second": 10688.388 }, { "epoch": 1.6738486399138162, "grad_norm": 0.7428943477119975, "learning_rate": 6.42204831190722e-07, "loss": 0.2911080360412598, "num_input_tokens_seen": 1023695320, "step": 24860, "train_runtime": 95775.6629, "train_tokens_per_second": 10688.47 }, { "epoch": 1.6741852949097764, "grad_norm": 0.7190866391014539, "learning_rate": 6.409090720052835e-07, "loss": 0.3024300575256348, "num_input_tokens_seen": 1023898944, "step": 24865, "train_runtime": 95796.0088, "train_tokens_per_second": 10688.326 }, { "epoch": 1.6745219499057367, "grad_norm": 0.7336947563453062, "learning_rate": 6.396145318257229e-07, "loss": 0.2703845500946045, "num_input_tokens_seen": 1024107192, "step": 24870, "train_runtime": 95813.9362, "train_tokens_per_second": 10688.499 }, { "epoch": 1.6748586049016967, "grad_norm": 0.7112620086241741, "learning_rate": 6.383212110140535e-07, "loss": 0.3164429903030396, "num_input_tokens_seen": 1024311088, "step": 24875, "train_runtime": 95832.3276, "train_tokens_per_second": 10688.576 }, { "epoch": 1.6751952598976567, "grad_norm": 0.9010288082452951, "learning_rate": 6.370291099319509e-07, "loss": 0.31120765209198, "num_input_tokens_seen": 1024495424, "step": 24880, "train_runtime": 95851.0989, "train_tokens_per_second": 10688.406 }, { "epoch": 1.675531914893617, "grad_norm": 0.717472977606872, "learning_rate": 6.357382289407433e-07, "loss": 0.2984041690826416, "num_input_tokens_seen": 1024710272, "step": 24885, "train_runtime": 95870.3401, "train_tokens_per_second": 10688.501 }, { "epoch": 1.6758685698895772, "grad_norm": 0.7008769600949449, "learning_rate": 6.344485684014251e-07, "loss": 0.306719970703125, "num_input_tokens_seen": 1024913304, "step": 24890, "train_runtime": 95890.1848, "train_tokens_per_second": 10688.407 }, { "epoch": 1.6762052248855372, "grad_norm": 0.7379649424419977, "learning_rate": 6.33160128674642e-07, "loss": 0.30941243171691896, "num_input_tokens_seen": 1025107608, "step": 24895, "train_runtime": 95909.5307, "train_tokens_per_second": 10688.277 }, { "epoch": 1.6765418798814973, "grad_norm": 0.7025302200859013, "learning_rate": 6.318729101207055e-07, "loss": 0.2904832363128662, "num_input_tokens_seen": 1025321432, "step": 24900, "train_runtime": 95929.9135, "train_tokens_per_second": 10688.235 }, { "epoch": 1.6768785348774575, "grad_norm": 0.6390771718636789, "learning_rate": 6.305869130995807e-07, "loss": 0.30631821155548095, "num_input_tokens_seen": 1025527656, "step": 24905, "train_runtime": 95949.2842, "train_tokens_per_second": 10688.226 }, { "epoch": 1.6772151898734178, "grad_norm": 0.7602873720192359, "learning_rate": 6.293021379708924e-07, "loss": 0.3002511262893677, "num_input_tokens_seen": 1025737936, "step": 24910, "train_runtime": 95969.4213, "train_tokens_per_second": 10688.175 }, { "epoch": 1.6775518448693778, "grad_norm": 0.7537707819267769, "learning_rate": 6.280185850939241e-07, "loss": 0.31717672348022463, "num_input_tokens_seen": 1025943936, "step": 24915, "train_runtime": 95989.5798, "train_tokens_per_second": 10688.076 }, { "epoch": 1.677888499865338, "grad_norm": 0.7929263257560962, "learning_rate": 6.267362548276173e-07, "loss": 0.3067145824432373, "num_input_tokens_seen": 1026142344, "step": 24920, "train_runtime": 96008.0444, "train_tokens_per_second": 10688.087 }, { "epoch": 1.6782251548612983, "grad_norm": 0.8724426449812618, "learning_rate": 6.254551475305703e-07, "loss": 0.30551881790161134, "num_input_tokens_seen": 1026327896, "step": 24925, "train_runtime": 96028.0442, "train_tokens_per_second": 10687.793 }, { "epoch": 1.6785618098572583, "grad_norm": 0.7971825128887806, "learning_rate": 6.241752635610443e-07, "loss": 0.3243920087814331, "num_input_tokens_seen": 1026531432, "step": 24930, "train_runtime": 96046.8161, "train_tokens_per_second": 10687.824 }, { "epoch": 1.6788984648532184, "grad_norm": 0.9293201286761705, "learning_rate": 6.228966032769496e-07, "loss": 0.31058125495910643, "num_input_tokens_seen": 1026733352, "step": 24935, "train_runtime": 96066.2888, "train_tokens_per_second": 10687.759 }, { "epoch": 1.6792351198491786, "grad_norm": 0.7254509874974516, "learning_rate": 6.216191670358651e-07, "loss": 0.2856894016265869, "num_input_tokens_seen": 1026939136, "step": 24940, "train_runtime": 96087.7986, "train_tokens_per_second": 10687.508 }, { "epoch": 1.6795717748451389, "grad_norm": 0.7285441614567525, "learning_rate": 6.203429551950163e-07, "loss": 0.32529897689819337, "num_input_tokens_seen": 1027150248, "step": 24945, "train_runtime": 96106.105, "train_tokens_per_second": 10687.669 }, { "epoch": 1.679908429841099, "grad_norm": 0.7706723878423296, "learning_rate": 6.19067968111296e-07, "loss": 0.2895487070083618, "num_input_tokens_seen": 1027346456, "step": 24950, "train_runtime": 96125.389, "train_tokens_per_second": 10687.566 }, { "epoch": 1.680245084837059, "grad_norm": 0.6907802693514197, "learning_rate": 6.177942061412478e-07, "loss": 0.2769299030303955, "num_input_tokens_seen": 1027548104, "step": 24955, "train_runtime": 96144.4536, "train_tokens_per_second": 10687.544 }, { "epoch": 1.6805817398330192, "grad_norm": 0.703732502548144, "learning_rate": 6.16521669641077e-07, "loss": 0.28638997077941897, "num_input_tokens_seen": 1027761664, "step": 24960, "train_runtime": 96162.8346, "train_tokens_per_second": 10687.722 }, { "epoch": 1.6809183948289794, "grad_norm": 0.7110375210760708, "learning_rate": 6.152503589666426e-07, "loss": 0.2999764680862427, "num_input_tokens_seen": 1027976872, "step": 24965, "train_runtime": 96181.3053, "train_tokens_per_second": 10687.907 }, { "epoch": 1.6812550498249395, "grad_norm": 0.6697822110344486, "learning_rate": 6.139802744734636e-07, "loss": 0.27085165977478026, "num_input_tokens_seen": 1028180936, "step": 24970, "train_runtime": 96200.788, "train_tokens_per_second": 10687.864 }, { "epoch": 1.6815917048208995, "grad_norm": 0.7090244329958619, "learning_rate": 6.127114165167142e-07, "loss": 0.2708765745162964, "num_input_tokens_seen": 1028378368, "step": 24975, "train_runtime": 96218.7965, "train_tokens_per_second": 10687.916 }, { "epoch": 1.6819283598168597, "grad_norm": 0.7943898374969302, "learning_rate": 6.11443785451229e-07, "loss": 0.29872736930847166, "num_input_tokens_seen": 1028585488, "step": 24980, "train_runtime": 96238.9182, "train_tokens_per_second": 10687.833 }, { "epoch": 1.68226501481282, "grad_norm": 0.7196267891238718, "learning_rate": 6.101773816314926e-07, "loss": 0.2998657703399658, "num_input_tokens_seen": 1028797304, "step": 24985, "train_runtime": 96258.6996, "train_tokens_per_second": 10687.837 }, { "epoch": 1.68260166980878, "grad_norm": 0.7264986056713443, "learning_rate": 6.089122054116558e-07, "loss": 0.30480740070343015, "num_input_tokens_seen": 1029010256, "step": 24990, "train_runtime": 96278.2884, "train_tokens_per_second": 10687.874 }, { "epoch": 1.68293832480474, "grad_norm": 0.7543161500275865, "learning_rate": 6.076482571455161e-07, "loss": 0.2918501853942871, "num_input_tokens_seen": 1029220936, "step": 24995, "train_runtime": 96297.9829, "train_tokens_per_second": 10687.876 }, { "epoch": 1.6832749798007003, "grad_norm": 0.8233855472755952, "learning_rate": 6.063855371865369e-07, "loss": 0.3086587905883789, "num_input_tokens_seen": 1029414880, "step": 25000, "train_runtime": 96317.6356, "train_tokens_per_second": 10687.709 }, { "epoch": 1.6836116347966605, "grad_norm": 0.7843630030591079, "learning_rate": 6.051240458878316e-07, "loss": 0.33011016845703123, "num_input_tokens_seen": 1029620488, "step": 25005, "train_runtime": 96337.1854, "train_tokens_per_second": 10687.675 }, { "epoch": 1.6839482897926206, "grad_norm": 0.7663805095288567, "learning_rate": 6.038637836021721e-07, "loss": 0.30872220993041993, "num_input_tokens_seen": 1029827896, "step": 25010, "train_runtime": 96357.0664, "train_tokens_per_second": 10687.622 }, { "epoch": 1.6842849447885806, "grad_norm": 0.7150939229914001, "learning_rate": 6.026047506819882e-07, "loss": 0.29668850898742677, "num_input_tokens_seen": 1030026688, "step": 25015, "train_runtime": 96375.198, "train_tokens_per_second": 10687.674 }, { "epoch": 1.6846215997845408, "grad_norm": 0.7295046999095303, "learning_rate": 6.013469474793632e-07, "loss": 0.29956727027893065, "num_input_tokens_seen": 1030234648, "step": 25020, "train_runtime": 96394.8186, "train_tokens_per_second": 10687.656 }, { "epoch": 1.684958254780501, "grad_norm": 0.8813600588259769, "learning_rate": 6.000903743460368e-07, "loss": 0.29161977767944336, "num_input_tokens_seen": 1030442856, "step": 25025, "train_runtime": 96414.0934, "train_tokens_per_second": 10687.679 }, { "epoch": 1.6852949097764611, "grad_norm": 0.6478278977367943, "learning_rate": 5.98835031633409e-07, "loss": 0.2964852571487427, "num_input_tokens_seen": 1030654016, "step": 25030, "train_runtime": 96434.4446, "train_tokens_per_second": 10687.613 }, { "epoch": 1.6856315647724212, "grad_norm": 0.7361917873125163, "learning_rate": 5.97580919692528e-07, "loss": 0.310629677772522, "num_input_tokens_seen": 1030870808, "step": 25035, "train_runtime": 96452.8785, "train_tokens_per_second": 10687.818 }, { "epoch": 1.6859682197683814, "grad_norm": 0.7710860791968711, "learning_rate": 5.963280388741072e-07, "loss": 0.280461049079895, "num_input_tokens_seen": 1031078568, "step": 25040, "train_runtime": 96472.2378, "train_tokens_per_second": 10687.827 }, { "epoch": 1.6863048747643417, "grad_norm": 0.8036877089238493, "learning_rate": 5.950763895285055e-07, "loss": 0.29325451850891116, "num_input_tokens_seen": 1031273512, "step": 25045, "train_runtime": 96492.7424, "train_tokens_per_second": 10687.576 }, { "epoch": 1.6866415297603017, "grad_norm": 0.6494405966375042, "learning_rate": 5.938259720057465e-07, "loss": 0.2918378829956055, "num_input_tokens_seen": 1031484336, "step": 25050, "train_runtime": 96511.5405, "train_tokens_per_second": 10687.679 }, { "epoch": 1.6869781847562617, "grad_norm": 0.7285315116515353, "learning_rate": 5.925767866555043e-07, "loss": 0.2901437520980835, "num_input_tokens_seen": 1031685768, "step": 25055, "train_runtime": 96530.7617, "train_tokens_per_second": 10687.637 }, { "epoch": 1.687314839752222, "grad_norm": 0.8066068058856042, "learning_rate": 5.913288338271095e-07, "loss": 0.3133868217468262, "num_input_tokens_seen": 1031895584, "step": 25060, "train_runtime": 96549.5382, "train_tokens_per_second": 10687.732 }, { "epoch": 1.6876514947481822, "grad_norm": 0.6728794319283422, "learning_rate": 5.900821138695478e-07, "loss": 0.2934118747711182, "num_input_tokens_seen": 1032103568, "step": 25065, "train_runtime": 96569.2907, "train_tokens_per_second": 10687.7 }, { "epoch": 1.6879881497441422, "grad_norm": 0.7787819675742236, "learning_rate": 5.888366271314605e-07, "loss": 0.3017313003540039, "num_input_tokens_seen": 1032317944, "step": 25070, "train_runtime": 96589.5778, "train_tokens_per_second": 10687.674 }, { "epoch": 1.6883248047401023, "grad_norm": 0.6627390680402665, "learning_rate": 5.875923739611439e-07, "loss": 0.3140779256820679, "num_input_tokens_seen": 1032529720, "step": 25075, "train_runtime": 96608.1299, "train_tokens_per_second": 10687.814 }, { "epoch": 1.6886614597360625, "grad_norm": 0.6535780948140175, "learning_rate": 5.863493547065513e-07, "loss": 0.28738179206848147, "num_input_tokens_seen": 1032731288, "step": 25080, "train_runtime": 96628.8509, "train_tokens_per_second": 10687.608 }, { "epoch": 1.6889981147320228, "grad_norm": 0.6598008876569474, "learning_rate": 5.851075697152858e-07, "loss": 0.28611025810241697, "num_input_tokens_seen": 1032949624, "step": 25085, "train_runtime": 96647.9075, "train_tokens_per_second": 10687.76 }, { "epoch": 1.6893347697279828, "grad_norm": 0.692302682249588, "learning_rate": 5.838670193346118e-07, "loss": 0.302885913848877, "num_input_tokens_seen": 1033150472, "step": 25090, "train_runtime": 96668.5106, "train_tokens_per_second": 10687.56 }, { "epoch": 1.6896714247239428, "grad_norm": 0.7178985531951222, "learning_rate": 5.826277039114426e-07, "loss": 0.2837608575820923, "num_input_tokens_seen": 1033355952, "step": 25095, "train_runtime": 96687.5769, "train_tokens_per_second": 10687.577 }, { "epoch": 1.690008079719903, "grad_norm": 0.6913333224459799, "learning_rate": 5.813896237923505e-07, "loss": 0.3304457187652588, "num_input_tokens_seen": 1033564976, "step": 25100, "train_runtime": 96706.9984, "train_tokens_per_second": 10687.592 }, { "epoch": 1.6903447347158633, "grad_norm": 0.712225444836872, "learning_rate": 5.801527793235606e-07, "loss": 0.3065957069396973, "num_input_tokens_seen": 1033779144, "step": 25105, "train_runtime": 96726.2941, "train_tokens_per_second": 10687.674 }, { "epoch": 1.6906813897118234, "grad_norm": 0.7002567680258981, "learning_rate": 5.789171708509516e-07, "loss": 0.2880049705505371, "num_input_tokens_seen": 1033969424, "step": 25110, "train_runtime": 96746.0809, "train_tokens_per_second": 10687.455 }, { "epoch": 1.6910180447077834, "grad_norm": 0.7048659385852736, "learning_rate": 5.776827987200584e-07, "loss": 0.30175797939300536, "num_input_tokens_seen": 1034176960, "step": 25115, "train_runtime": 96764.8116, "train_tokens_per_second": 10687.531 }, { "epoch": 1.6913546997037436, "grad_norm": 0.7679536029740625, "learning_rate": 5.764496632760691e-07, "loss": 0.2925248622894287, "num_input_tokens_seen": 1034371696, "step": 25120, "train_runtime": 96783.6544, "train_tokens_per_second": 10687.463 }, { "epoch": 1.6916913546997039, "grad_norm": 0.7578235367804087, "learning_rate": 5.752177648638241e-07, "loss": 0.2802034616470337, "num_input_tokens_seen": 1034581400, "step": 25125, "train_runtime": 96802.9002, "train_tokens_per_second": 10687.504 }, { "epoch": 1.692028009695664, "grad_norm": 0.80076171843857, "learning_rate": 5.739871038278239e-07, "loss": 0.31072473526000977, "num_input_tokens_seen": 1034789024, "step": 25130, "train_runtime": 96821.5463, "train_tokens_per_second": 10687.59 }, { "epoch": 1.692364664691624, "grad_norm": 0.7847650175537817, "learning_rate": 5.727576805122142e-07, "loss": 0.2792636871337891, "num_input_tokens_seen": 1034988600, "step": 25135, "train_runtime": 96841.9718, "train_tokens_per_second": 10687.397 }, { "epoch": 1.6927013196875842, "grad_norm": 0.6586014700600055, "learning_rate": 5.715294952608041e-07, "loss": 0.29943482875823973, "num_input_tokens_seen": 1035204872, "step": 25140, "train_runtime": 96860.4087, "train_tokens_per_second": 10687.596 }, { "epoch": 1.6930379746835444, "grad_norm": 0.8058786722465499, "learning_rate": 5.703025484170471e-07, "loss": 0.306259822845459, "num_input_tokens_seen": 1035420864, "step": 25145, "train_runtime": 96879.1996, "train_tokens_per_second": 10687.752 }, { "epoch": 1.6933746296795045, "grad_norm": 0.7726539531140358, "learning_rate": 5.690768403240587e-07, "loss": 0.31602964401245115, "num_input_tokens_seen": 1035628632, "step": 25150, "train_runtime": 96898.5367, "train_tokens_per_second": 10687.763 }, { "epoch": 1.6937112846754645, "grad_norm": 0.6869816940340338, "learning_rate": 5.67852371324602e-07, "loss": 0.3075075626373291, "num_input_tokens_seen": 1035845712, "step": 25155, "train_runtime": 96917.9177, "train_tokens_per_second": 10687.866 }, { "epoch": 1.6940479396714248, "grad_norm": 0.6833940875730019, "learning_rate": 5.66629141761097e-07, "loss": 0.2899328231811523, "num_input_tokens_seen": 1036063920, "step": 25160, "train_runtime": 96937.8764, "train_tokens_per_second": 10687.916 }, { "epoch": 1.694384594667385, "grad_norm": 0.7351896571887431, "learning_rate": 5.654071519756154e-07, "loss": 0.3093409538269043, "num_input_tokens_seen": 1036275320, "step": 25165, "train_runtime": 96956.921, "train_tokens_per_second": 10687.997 }, { "epoch": 1.694721249663345, "grad_norm": 0.7489028533311771, "learning_rate": 5.641864023098831e-07, "loss": 0.33106651306152346, "num_input_tokens_seen": 1036483240, "step": 25170, "train_runtime": 96977.1888, "train_tokens_per_second": 10687.908 }, { "epoch": 1.695057904659305, "grad_norm": 0.6901862076103507, "learning_rate": 5.629668931052773e-07, "loss": 0.29619317054748534, "num_input_tokens_seen": 1036701504, "step": 25175, "train_runtime": 96996.8721, "train_tokens_per_second": 10687.989 }, { "epoch": 1.6953945596552653, "grad_norm": 0.7320541340911347, "learning_rate": 5.61748624702833e-07, "loss": 0.3215886116027832, "num_input_tokens_seen": 1036912144, "step": 25180, "train_runtime": 97015.9564, "train_tokens_per_second": 10688.058 }, { "epoch": 1.6957312146512256, "grad_norm": 0.7421795693460952, "learning_rate": 5.605315974432313e-07, "loss": 0.3020993947982788, "num_input_tokens_seen": 1037118936, "step": 25185, "train_runtime": 97035.1012, "train_tokens_per_second": 10688.08 }, { "epoch": 1.6960678696471856, "grad_norm": 0.6579430161980508, "learning_rate": 5.593158116668146e-07, "loss": 0.29680747985839845, "num_input_tokens_seen": 1037342176, "step": 25190, "train_runtime": 97054.4956, "train_tokens_per_second": 10688.244 }, { "epoch": 1.6964045246431456, "grad_norm": 0.7433585155787572, "learning_rate": 5.581012677135683e-07, "loss": 0.29815077781677246, "num_input_tokens_seen": 1037533960, "step": 25195, "train_runtime": 97072.4383, "train_tokens_per_second": 10688.245 }, { "epoch": 1.6967411796391059, "grad_norm": 0.7076072451094421, "learning_rate": 5.56887965923139e-07, "loss": 0.3038212060928345, "num_input_tokens_seen": 1037748584, "step": 25200, "train_runtime": 97091.3308, "train_tokens_per_second": 10688.375 }, { "epoch": 1.6970778346350661, "grad_norm": 0.831580000117784, "learning_rate": 5.556759066348227e-07, "loss": 0.296083927154541, "num_input_tokens_seen": 1037955152, "step": 25205, "train_runtime": 97110.2636, "train_tokens_per_second": 10688.419 }, { "epoch": 1.6974144896310261, "grad_norm": 0.7212292908274415, "learning_rate": 5.54465090187567e-07, "loss": 0.3015348672866821, "num_input_tokens_seen": 1038155872, "step": 25210, "train_runtime": 97129.4736, "train_tokens_per_second": 10688.371 }, { "epoch": 1.6977511446269862, "grad_norm": 0.7598575026955054, "learning_rate": 5.532555169199727e-07, "loss": 0.2872861385345459, "num_input_tokens_seen": 1038357224, "step": 25215, "train_runtime": 97148.0442, "train_tokens_per_second": 10688.401 }, { "epoch": 1.6980877996229464, "grad_norm": 0.6827023917138855, "learning_rate": 5.520471871702937e-07, "loss": 0.28663339614868166, "num_input_tokens_seen": 1038570008, "step": 25220, "train_runtime": 97165.4633, "train_tokens_per_second": 10688.674 }, { "epoch": 1.6984244546189067, "grad_norm": 0.8005476847453646, "learning_rate": 5.508401012764341e-07, "loss": 0.2933193206787109, "num_input_tokens_seen": 1038773288, "step": 25225, "train_runtime": 97182.9826, "train_tokens_per_second": 10688.839 }, { "epoch": 1.6987611096148667, "grad_norm": 0.6862237669722838, "learning_rate": 5.496342595759552e-07, "loss": 0.28551902770996096, "num_input_tokens_seen": 1038988016, "step": 25230, "train_runtime": 97202.3317, "train_tokens_per_second": 10688.921 }, { "epoch": 1.6990977646108267, "grad_norm": 0.6685801929159362, "learning_rate": 5.484296624060626e-07, "loss": 0.2864408493041992, "num_input_tokens_seen": 1039201560, "step": 25235, "train_runtime": 97221.7159, "train_tokens_per_second": 10688.986 }, { "epoch": 1.699434419606787, "grad_norm": 0.7091537583062115, "learning_rate": 5.472263101036212e-07, "loss": 0.2949539661407471, "num_input_tokens_seen": 1039411560, "step": 25240, "train_runtime": 97241.4015, "train_tokens_per_second": 10688.982 }, { "epoch": 1.6997710746027472, "grad_norm": 0.8563623004258417, "learning_rate": 5.460242030051421e-07, "loss": 0.3118251085281372, "num_input_tokens_seen": 1039610784, "step": 25245, "train_runtime": 97260.2887, "train_tokens_per_second": 10688.954 }, { "epoch": 1.7001077295987073, "grad_norm": 0.683011222506792, "learning_rate": 5.448233414467924e-07, "loss": 0.305493426322937, "num_input_tokens_seen": 1039829296, "step": 25250, "train_runtime": 97280.0766, "train_tokens_per_second": 10689.026 }, { "epoch": 1.7004443845946673, "grad_norm": 0.7143857904307952, "learning_rate": 5.43623725764389e-07, "loss": 0.32039270401000974, "num_input_tokens_seen": 1040032168, "step": 25255, "train_runtime": 97299.5667, "train_tokens_per_second": 10688.97 }, { "epoch": 1.7007810395906275, "grad_norm": 0.7026900211435636, "learning_rate": 5.424253562934001e-07, "loss": 0.2958377361297607, "num_input_tokens_seen": 1040247984, "step": 25260, "train_runtime": 97319.7524, "train_tokens_per_second": 10688.971 }, { "epoch": 1.7011176945865878, "grad_norm": 0.7176191652856312, "learning_rate": 5.412282333689461e-07, "loss": 0.29465413093566895, "num_input_tokens_seen": 1040460400, "step": 25265, "train_runtime": 97339.4482, "train_tokens_per_second": 10688.99 }, { "epoch": 1.7014543495825478, "grad_norm": 0.6511963008022666, "learning_rate": 5.400323573257987e-07, "loss": 0.2942551374435425, "num_input_tokens_seen": 1040672624, "step": 25270, "train_runtime": 97357.9791, "train_tokens_per_second": 10689.135 }, { "epoch": 1.7017910045785078, "grad_norm": 0.6847004057068714, "learning_rate": 5.388377284983803e-07, "loss": 0.2866601228713989, "num_input_tokens_seen": 1040884016, "step": 25275, "train_runtime": 97376.2526, "train_tokens_per_second": 10689.3 }, { "epoch": 1.702127659574468, "grad_norm": 0.707604747045918, "learning_rate": 5.37644347220767e-07, "loss": 0.2913754940032959, "num_input_tokens_seen": 1041086056, "step": 25280, "train_runtime": 97394.0078, "train_tokens_per_second": 10689.426 }, { "epoch": 1.7024643145704283, "grad_norm": 0.7831518251628398, "learning_rate": 5.364522138266809e-07, "loss": 0.31163735389709474, "num_input_tokens_seen": 1041301776, "step": 25285, "train_runtime": 97411.9814, "train_tokens_per_second": 10689.668 }, { "epoch": 1.7028009695663884, "grad_norm": 0.7122723512717942, "learning_rate": 5.352613286495018e-07, "loss": 0.2934358835220337, "num_input_tokens_seen": 1041501464, "step": 25290, "train_runtime": 97431.2586, "train_tokens_per_second": 10689.603 }, { "epoch": 1.7031376245623484, "grad_norm": 0.6474167331792093, "learning_rate": 5.340716920222527e-07, "loss": 0.27745862007141114, "num_input_tokens_seen": 1041709664, "step": 25295, "train_runtime": 97451.6768, "train_tokens_per_second": 10689.5 }, { "epoch": 1.7034742795583087, "grad_norm": 0.8005943544340175, "learning_rate": 5.32883304277616e-07, "loss": 0.3233341693878174, "num_input_tokens_seen": 1041911112, "step": 25300, "train_runtime": 97472.5263, "train_tokens_per_second": 10689.28 }, { "epoch": 1.703810934554269, "grad_norm": 0.7556320243016807, "learning_rate": 5.31696165747918e-07, "loss": 0.27761449813842776, "num_input_tokens_seen": 1042120168, "step": 25305, "train_runtime": 97492.3857, "train_tokens_per_second": 10689.247 }, { "epoch": 1.704147589550229, "grad_norm": 0.7233999302034958, "learning_rate": 5.305102767651393e-07, "loss": 0.2880266189575195, "num_input_tokens_seen": 1042336392, "step": 25310, "train_runtime": 97511.8763, "train_tokens_per_second": 10689.328 }, { "epoch": 1.704484244546189, "grad_norm": 0.7224955169032918, "learning_rate": 5.293256376609091e-07, "loss": 0.30724501609802246, "num_input_tokens_seen": 1042546400, "step": 25315, "train_runtime": 97532.1173, "train_tokens_per_second": 10689.262 }, { "epoch": 1.7048208995421492, "grad_norm": 0.6952596040512371, "learning_rate": 5.281422487665089e-07, "loss": 0.2704369783401489, "num_input_tokens_seen": 1042762512, "step": 25320, "train_runtime": 97552.918, "train_tokens_per_second": 10689.199 }, { "epoch": 1.7051575545381095, "grad_norm": 0.7680667236456769, "learning_rate": 5.269601104128674e-07, "loss": 0.28826346397399905, "num_input_tokens_seen": 1042976280, "step": 25325, "train_runtime": 97573.0169, "train_tokens_per_second": 10689.188 }, { "epoch": 1.7054942095340695, "grad_norm": 0.7065085483066377, "learning_rate": 5.257792229305702e-07, "loss": 0.3103371858596802, "num_input_tokens_seen": 1043183280, "step": 25330, "train_runtime": 97591.0345, "train_tokens_per_second": 10689.335 }, { "epoch": 1.7058308645300295, "grad_norm": 0.8332709172335497, "learning_rate": 5.245995866498438e-07, "loss": 0.2783116102218628, "num_input_tokens_seen": 1043380712, "step": 25335, "train_runtime": 97610.2411, "train_tokens_per_second": 10689.255 }, { "epoch": 1.7061675195259898, "grad_norm": 0.7594571223422432, "learning_rate": 5.234212019005741e-07, "loss": 0.3059995174407959, "num_input_tokens_seen": 1043579184, "step": 25340, "train_runtime": 97630.3303, "train_tokens_per_second": 10689.088 }, { "epoch": 1.70650417452195, "grad_norm": 0.7447047695550354, "learning_rate": 5.222440690122882e-07, "loss": 0.2975228548049927, "num_input_tokens_seen": 1043782944, "step": 25345, "train_runtime": 97649.7837, "train_tokens_per_second": 10689.045 }, { "epoch": 1.70684082951791, "grad_norm": 0.6789396487691176, "learning_rate": 5.210681883141716e-07, "loss": 0.2802223443984985, "num_input_tokens_seen": 1043989376, "step": 25350, "train_runtime": 97669.3289, "train_tokens_per_second": 10689.02 }, { "epoch": 1.70717748451387, "grad_norm": 0.7773663861974824, "learning_rate": 5.19893560135053e-07, "loss": 0.309729790687561, "num_input_tokens_seen": 1044205808, "step": 25355, "train_runtime": 97687.4888, "train_tokens_per_second": 10689.248 }, { "epoch": 1.7075141395098303, "grad_norm": 0.7294013165181585, "learning_rate": 5.187201848034146e-07, "loss": 0.29875788688659666, "num_input_tokens_seen": 1044413136, "step": 25360, "train_runtime": 97706.6046, "train_tokens_per_second": 10689.279 }, { "epoch": 1.7078507945057906, "grad_norm": 0.724878244382244, "learning_rate": 5.175480626473873e-07, "loss": 0.28993754386901854, "num_input_tokens_seen": 1044612496, "step": 25365, "train_runtime": 97726.7553, "train_tokens_per_second": 10689.115 }, { "epoch": 1.7081874495017506, "grad_norm": 0.7641113619846441, "learning_rate": 5.163771939947504e-07, "loss": 0.31216821670532224, "num_input_tokens_seen": 1044819688, "step": 25370, "train_runtime": 97746.5066, "train_tokens_per_second": 10689.074 }, { "epoch": 1.7085241044977106, "grad_norm": 0.6574416402505695, "learning_rate": 5.152075791729327e-07, "loss": 0.32161917686462405, "num_input_tokens_seen": 1045038336, "step": 25375, "train_runtime": 97766.0852, "train_tokens_per_second": 10689.17 }, { "epoch": 1.7088607594936709, "grad_norm": 0.6673020851522296, "learning_rate": 5.140392185090165e-07, "loss": 0.30206224918365476, "num_input_tokens_seen": 1045234504, "step": 25380, "train_runtime": 97787.5508, "train_tokens_per_second": 10688.83 }, { "epoch": 1.7091974144896311, "grad_norm": 0.8130966582694847, "learning_rate": 5.128721123297265e-07, "loss": 0.29916844367980955, "num_input_tokens_seen": 1045454136, "step": 25385, "train_runtime": 97806.1997, "train_tokens_per_second": 10689.037 }, { "epoch": 1.7095340694855912, "grad_norm": 0.7821338415221697, "learning_rate": 5.117062609614438e-07, "loss": 0.28233349323272705, "num_input_tokens_seen": 1045660928, "step": 25390, "train_runtime": 97824.3052, "train_tokens_per_second": 10689.173 }, { "epoch": 1.7098707244815512, "grad_norm": 0.7339396427394611, "learning_rate": 5.105416647301909e-07, "loss": 0.2940813064575195, "num_input_tokens_seen": 1045871880, "step": 25395, "train_runtime": 97844.2689, "train_tokens_per_second": 10689.148 }, { "epoch": 1.7102073794775114, "grad_norm": 0.777731183688445, "learning_rate": 5.093783239616468e-07, "loss": 0.27096123695373536, "num_input_tokens_seen": 1046068136, "step": 25400, "train_runtime": 97863.2471, "train_tokens_per_second": 10689.081 }, { "epoch": 1.7105440344734717, "grad_norm": 0.8518919771022432, "learning_rate": 5.082162389811352e-07, "loss": 0.293508243560791, "num_input_tokens_seen": 1046270984, "step": 25405, "train_runtime": 97881.2807, "train_tokens_per_second": 10689.184 }, { "epoch": 1.7108806894694317, "grad_norm": 0.77815263217912, "learning_rate": 5.070554101136288e-07, "loss": 0.2779042720794678, "num_input_tokens_seen": 1046462424, "step": 25410, "train_runtime": 97899.2666, "train_tokens_per_second": 10689.175 }, { "epoch": 1.7112173444653918, "grad_norm": 0.6899619997796519, "learning_rate": 5.058958376837497e-07, "loss": 0.29887173175811765, "num_input_tokens_seen": 1046676120, "step": 25415, "train_runtime": 97920.3588, "train_tokens_per_second": 10689.055 }, { "epoch": 1.711553999461352, "grad_norm": 1.25279336222127, "learning_rate": 5.047375220157691e-07, "loss": 0.30473015308380125, "num_input_tokens_seen": 1046888952, "step": 25420, "train_runtime": 97941.2689, "train_tokens_per_second": 10688.946 }, { "epoch": 1.7118906544573123, "grad_norm": 0.7140734150548387, "learning_rate": 5.035804634336056e-07, "loss": 0.3204843044281006, "num_input_tokens_seen": 1047096728, "step": 25425, "train_runtime": 97960.6259, "train_tokens_per_second": 10688.955 }, { "epoch": 1.7122273094532723, "grad_norm": 0.6697564879538974, "learning_rate": 5.024246622608292e-07, "loss": 0.29503560066223145, "num_input_tokens_seen": 1047319232, "step": 25430, "train_runtime": 97981.2306, "train_tokens_per_second": 10688.978 }, { "epoch": 1.7125639644492323, "grad_norm": 0.8215597612082169, "learning_rate": 5.01270118820652e-07, "loss": 0.3212262153625488, "num_input_tokens_seen": 1047532848, "step": 25435, "train_runtime": 98000.2963, "train_tokens_per_second": 10689.078 }, { "epoch": 1.7129006194451926, "grad_norm": 0.7750787926879936, "learning_rate": 5.001168334359429e-07, "loss": 0.32527780532836914, "num_input_tokens_seen": 1047747856, "step": 25440, "train_runtime": 98017.8271, "train_tokens_per_second": 10689.36 }, { "epoch": 1.7132372744411528, "grad_norm": 0.7110460872918438, "learning_rate": 4.989648064292102e-07, "loss": 0.3077778100967407, "num_input_tokens_seen": 1047960992, "step": 25445, "train_runtime": 98035.4517, "train_tokens_per_second": 10689.613 }, { "epoch": 1.7135739294371128, "grad_norm": 0.7593946450887116, "learning_rate": 4.978140381226177e-07, "loss": 0.3097731590270996, "num_input_tokens_seen": 1048168984, "step": 25450, "train_runtime": 98054.885, "train_tokens_per_second": 10689.615 }, { "epoch": 1.7139105844330729, "grad_norm": 0.6724476204407512, "learning_rate": 4.966645288379729e-07, "loss": 0.284191370010376, "num_input_tokens_seen": 1048381040, "step": 25455, "train_runtime": 98074.5561, "train_tokens_per_second": 10689.633 }, { "epoch": 1.7142472394290331, "grad_norm": 0.7931833747487993, "learning_rate": 4.955162788967327e-07, "loss": 0.31455824375152586, "num_input_tokens_seen": 1048563312, "step": 25460, "train_runtime": 98094.5505, "train_tokens_per_second": 10689.313 }, { "epoch": 1.7145838944249934, "grad_norm": 0.673424701472676, "learning_rate": 4.943692886200013e-07, "loss": 0.307358455657959, "num_input_tokens_seen": 1048765120, "step": 25465, "train_runtime": 98113.9099, "train_tokens_per_second": 10689.26 }, { "epoch": 1.7149205494209534, "grad_norm": 0.7075426738393459, "learning_rate": 4.932235583285305e-07, "loss": 0.3081015110015869, "num_input_tokens_seen": 1048984024, "step": 25470, "train_runtime": 98133.1524, "train_tokens_per_second": 10689.395 }, { "epoch": 1.7152572044169134, "grad_norm": 0.7458405467261648, "learning_rate": 4.920790883427201e-07, "loss": 0.2979478359222412, "num_input_tokens_seen": 1049176000, "step": 25475, "train_runtime": 98152.5232, "train_tokens_per_second": 10689.241 }, { "epoch": 1.7155938594128737, "grad_norm": 0.7517792511024183, "learning_rate": 4.909358789826196e-07, "loss": 0.309256386756897, "num_input_tokens_seen": 1049358568, "step": 25480, "train_runtime": 98171.0776, "train_tokens_per_second": 10689.081 }, { "epoch": 1.715930514408834, "grad_norm": 0.8028567231792343, "learning_rate": 4.897939305679206e-07, "loss": 0.3085469722747803, "num_input_tokens_seen": 1049572216, "step": 25485, "train_runtime": 98189.1859, "train_tokens_per_second": 10689.285 }, { "epoch": 1.716267169404794, "grad_norm": 0.6572581766723319, "learning_rate": 4.886532434179686e-07, "loss": 0.2893794536590576, "num_input_tokens_seen": 1049778664, "step": 25490, "train_runtime": 98208.6948, "train_tokens_per_second": 10689.264 }, { "epoch": 1.716603824400754, "grad_norm": 0.6783993028154053, "learning_rate": 4.875138178517497e-07, "loss": 0.2646089792251587, "num_input_tokens_seen": 1049982352, "step": 25495, "train_runtime": 98227.532, "train_tokens_per_second": 10689.288 }, { "epoch": 1.7169404793967142, "grad_norm": 0.7444277946224527, "learning_rate": 4.863756541879028e-07, "loss": 0.31967720985412595, "num_input_tokens_seen": 1050194768, "step": 25500, "train_runtime": 98248.0089, "train_tokens_per_second": 10689.222 }, { "epoch": 1.7172771343926745, "grad_norm": 0.650355248164458, "learning_rate": 4.852387527447117e-07, "loss": 0.2771495819091797, "num_input_tokens_seen": 1050415152, "step": 25505, "train_runtime": 98267.3707, "train_tokens_per_second": 10689.358 }, { "epoch": 1.7176137893886345, "grad_norm": 0.6826080561042044, "learning_rate": 4.84103113840107e-07, "loss": 0.2959118366241455, "num_input_tokens_seen": 1050629000, "step": 25510, "train_runtime": 98285.452, "train_tokens_per_second": 10689.568 }, { "epoch": 1.7179504443845945, "grad_norm": 0.7191318275465607, "learning_rate": 4.829687377916664e-07, "loss": 0.29724745750427245, "num_input_tokens_seen": 1050826664, "step": 25515, "train_runtime": 98303.3604, "train_tokens_per_second": 10689.631 }, { "epoch": 1.7182870993805548, "grad_norm": 0.8154908881841009, "learning_rate": 4.81835624916614e-07, "loss": 0.28770673274993896, "num_input_tokens_seen": 1051029120, "step": 25520, "train_runtime": 98322.3625, "train_tokens_per_second": 10689.624 }, { "epoch": 1.718623754376515, "grad_norm": 0.7856710228173892, "learning_rate": 4.807037755318211e-07, "loss": 0.29225175380706786, "num_input_tokens_seen": 1051245360, "step": 25525, "train_runtime": 98340.2123, "train_tokens_per_second": 10689.883 }, { "epoch": 1.718960409372475, "grad_norm": 0.6201653769020243, "learning_rate": 4.795731899538086e-07, "loss": 0.3108567953109741, "num_input_tokens_seen": 1051447240, "step": 25530, "train_runtime": 98360.1115, "train_tokens_per_second": 10689.773 }, { "epoch": 1.719297064368435, "grad_norm": 0.6731219843454114, "learning_rate": 4.78443868498737e-07, "loss": 0.28201186656951904, "num_input_tokens_seen": 1051655608, "step": 25535, "train_runtime": 98379.6112, "train_tokens_per_second": 10689.772 }, { "epoch": 1.7196337193643954, "grad_norm": 0.6885838595689214, "learning_rate": 4.773158114824206e-07, "loss": 0.2828006029129028, "num_input_tokens_seen": 1051866120, "step": 25540, "train_runtime": 98397.8293, "train_tokens_per_second": 10689.932 }, { "epoch": 1.7199703743603556, "grad_norm": 0.7646442855674354, "learning_rate": 4.7618901922031445e-07, "loss": 0.27526843547821045, "num_input_tokens_seen": 1052075760, "step": 25545, "train_runtime": 98417.968, "train_tokens_per_second": 10689.875 }, { "epoch": 1.7203070293563156, "grad_norm": 1.4681853664592603, "learning_rate": 4.750634920275243e-07, "loss": 0.303803825378418, "num_input_tokens_seen": 1052277800, "step": 25550, "train_runtime": 98437.4239, "train_tokens_per_second": 10689.814 }, { "epoch": 1.7206436843522757, "grad_norm": 0.7423981206622023, "learning_rate": 4.739392302188001e-07, "loss": 0.3224016666412354, "num_input_tokens_seen": 1052491824, "step": 25555, "train_runtime": 98456.8367, "train_tokens_per_second": 10689.881 }, { "epoch": 1.720980339348236, "grad_norm": 0.7178924347622515, "learning_rate": 4.728162341085368e-07, "loss": 0.3036672353744507, "num_input_tokens_seen": 1052697688, "step": 25560, "train_runtime": 98477.0415, "train_tokens_per_second": 10689.778 }, { "epoch": 1.7213169943441962, "grad_norm": 0.6748448465540865, "learning_rate": 4.7169450401077843e-07, "loss": 0.31398935317993165, "num_input_tokens_seen": 1052911968, "step": 25565, "train_runtime": 98497.3065, "train_tokens_per_second": 10689.754 }, { "epoch": 1.7216536493401562, "grad_norm": 0.7920921945734793, "learning_rate": 4.7057404023921174e-07, "loss": 0.3092198371887207, "num_input_tokens_seen": 1053124032, "step": 25570, "train_runtime": 98515.3785, "train_tokens_per_second": 10689.946 }, { "epoch": 1.7219903043361162, "grad_norm": 0.7782372352290068, "learning_rate": 4.694548431071705e-07, "loss": 0.3142277717590332, "num_input_tokens_seen": 1053329408, "step": 25575, "train_runtime": 98535.2189, "train_tokens_per_second": 10689.877 }, { "epoch": 1.7223269593320765, "grad_norm": 0.7229280162510824, "learning_rate": 4.683369129276377e-07, "loss": 0.31145486831665037, "num_input_tokens_seen": 1053538776, "step": 25580, "train_runtime": 98554.2564, "train_tokens_per_second": 10689.937 }, { "epoch": 1.7226636143280367, "grad_norm": 0.6404311143109147, "learning_rate": 4.6722025001323444e-07, "loss": 0.2782719612121582, "num_input_tokens_seen": 1053731512, "step": 25585, "train_runtime": 98575.7545, "train_tokens_per_second": 10689.561 }, { "epoch": 1.7230002693239967, "grad_norm": 0.7301267767363954, "learning_rate": 4.6610485467623643e-07, "loss": 0.2986452579498291, "num_input_tokens_seen": 1053926408, "step": 25590, "train_runtime": 98595.3155, "train_tokens_per_second": 10689.417 }, { "epoch": 1.7233369243199568, "grad_norm": 0.6990841114550689, "learning_rate": 4.649907272285564e-07, "loss": 0.29245178699493407, "num_input_tokens_seen": 1054133136, "step": 25595, "train_runtime": 98614.3159, "train_tokens_per_second": 10689.453 }, { "epoch": 1.723673579315917, "grad_norm": 0.6912935000168858, "learning_rate": 4.638778679817596e-07, "loss": 0.28856568336486815, "num_input_tokens_seen": 1054348952, "step": 25600, "train_runtime": 98636.4269, "train_tokens_per_second": 10689.245 }, { "epoch": 1.7240102343118773, "grad_norm": 0.7421778916667545, "learning_rate": 4.6276627724705204e-07, "loss": 0.310761833190918, "num_input_tokens_seen": 1054554560, "step": 25605, "train_runtime": 98657.8229, "train_tokens_per_second": 10689.011 }, { "epoch": 1.7243468893078373, "grad_norm": 0.639554092688567, "learning_rate": 4.616559553352873e-07, "loss": 0.27671351432800295, "num_input_tokens_seen": 1054759920, "step": 25610, "train_runtime": 98677.7318, "train_tokens_per_second": 10688.936 }, { "epoch": 1.7246835443037973, "grad_norm": 0.738844569660465, "learning_rate": 4.6054690255696256e-07, "loss": 0.32097625732421875, "num_input_tokens_seen": 1054968944, "step": 25615, "train_runtime": 98696.8416, "train_tokens_per_second": 10688.984 }, { "epoch": 1.7250201992997576, "grad_norm": 0.7621834056139537, "learning_rate": 4.594391192222214e-07, "loss": 0.2967867851257324, "num_input_tokens_seen": 1055171712, "step": 25620, "train_runtime": 98716.6404, "train_tokens_per_second": 10688.894 }, { "epoch": 1.7253568542957178, "grad_norm": 0.679204480140684, "learning_rate": 4.583326056408505e-07, "loss": 0.2793277263641357, "num_input_tokens_seen": 1055379208, "step": 25625, "train_runtime": 98737.2602, "train_tokens_per_second": 10688.763 }, { "epoch": 1.7256935092916779, "grad_norm": 0.8161157270569862, "learning_rate": 4.5722736212228613e-07, "loss": 0.3047205448150635, "num_input_tokens_seen": 1055568664, "step": 25630, "train_runtime": 98758.5123, "train_tokens_per_second": 10688.382 }, { "epoch": 1.726030164287638, "grad_norm": 0.7343184337921606, "learning_rate": 4.5612338897560227e-07, "loss": 0.3128689765930176, "num_input_tokens_seen": 1055784608, "step": 25635, "train_runtime": 98776.2774, "train_tokens_per_second": 10688.645 }, { "epoch": 1.7263668192835981, "grad_norm": 0.7959225513828134, "learning_rate": 4.5502068650952527e-07, "loss": 0.3099062442779541, "num_input_tokens_seen": 1055986920, "step": 25640, "train_runtime": 98795.4746, "train_tokens_per_second": 10688.616 }, { "epoch": 1.7267034742795584, "grad_norm": 0.8124441014651872, "learning_rate": 4.5391925503241894e-07, "loss": 0.2990616798400879, "num_input_tokens_seen": 1056200576, "step": 25645, "train_runtime": 98815.9078, "train_tokens_per_second": 10688.568 }, { "epoch": 1.7270401292755184, "grad_norm": 0.752929314390055, "learning_rate": 4.5281909485229704e-07, "loss": 0.30027480125427247, "num_input_tokens_seen": 1056402528, "step": 25650, "train_runtime": 98834.2475, "train_tokens_per_second": 10688.628 }, { "epoch": 1.7273767842714784, "grad_norm": 0.8649541792557157, "learning_rate": 4.51720206276815e-07, "loss": 0.26756341457366944, "num_input_tokens_seen": 1056604976, "step": 25655, "train_runtime": 98853.6534, "train_tokens_per_second": 10688.578 }, { "epoch": 1.7277134392674387, "grad_norm": 0.7295951707221228, "learning_rate": 4.506225896132743e-07, "loss": 0.2821979522705078, "num_input_tokens_seen": 1056806976, "step": 25660, "train_runtime": 98872.5079, "train_tokens_per_second": 10688.583 }, { "epoch": 1.728050094263399, "grad_norm": 0.7407010601715148, "learning_rate": 4.4952624516861944e-07, "loss": 0.2954383850097656, "num_input_tokens_seen": 1056999768, "step": 25665, "train_runtime": 98891.7127, "train_tokens_per_second": 10688.456 }, { "epoch": 1.728386749259359, "grad_norm": 0.7097220371211799, "learning_rate": 4.4843117324944005e-07, "loss": 0.27136032581329345, "num_input_tokens_seen": 1057218824, "step": 25670, "train_runtime": 98911.0853, "train_tokens_per_second": 10688.578 }, { "epoch": 1.728723404255319, "grad_norm": 0.7727472366639319, "learning_rate": 4.4733737416196745e-07, "loss": 0.29611911773681643, "num_input_tokens_seen": 1057389824, "step": 25675, "train_runtime": 98929.4732, "train_tokens_per_second": 10688.32 }, { "epoch": 1.7290600592512793, "grad_norm": 0.6680949842507153, "learning_rate": 4.4624484821208346e-07, "loss": 0.2924178600311279, "num_input_tokens_seen": 1057591136, "step": 25680, "train_runtime": 98949.5394, "train_tokens_per_second": 10688.187 }, { "epoch": 1.7293967142472395, "grad_norm": 0.7697869614445987, "learning_rate": 4.451535957053044e-07, "loss": 0.26893112659454343, "num_input_tokens_seen": 1057798192, "step": 25685, "train_runtime": 98970.202, "train_tokens_per_second": 10688.047 }, { "epoch": 1.7297333692431995, "grad_norm": 0.7605209723928302, "learning_rate": 4.440636169467999e-07, "loss": 0.290544319152832, "num_input_tokens_seen": 1057998336, "step": 25690, "train_runtime": 98988.9086, "train_tokens_per_second": 10688.049 }, { "epoch": 1.7300700242391596, "grad_norm": 0.8411092868467474, "learning_rate": 4.429749122413757e-07, "loss": 0.2889115810394287, "num_input_tokens_seen": 1058199408, "step": 25695, "train_runtime": 99006.1383, "train_tokens_per_second": 10688.22 }, { "epoch": 1.7304066792351198, "grad_norm": 0.7436799518233864, "learning_rate": 4.418874818934865e-07, "loss": 0.29523520469665526, "num_input_tokens_seen": 1058409216, "step": 25700, "train_runtime": 99025.5078, "train_tokens_per_second": 10688.248 }, { "epoch": 1.73074333423108, "grad_norm": 0.7727424632410065, "learning_rate": 4.4080132620722806e-07, "loss": 0.3046144962310791, "num_input_tokens_seen": 1058597800, "step": 25705, "train_runtime": 99045.1864, "train_tokens_per_second": 10688.029 }, { "epoch": 1.73107998922704, "grad_norm": 0.7190147755514475, "learning_rate": 4.3971644548634116e-07, "loss": 0.30265016555786134, "num_input_tokens_seen": 1058798264, "step": 25710, "train_runtime": 99064.4619, "train_tokens_per_second": 10687.973 }, { "epoch": 1.7314166442230001, "grad_norm": 0.8980976694223958, "learning_rate": 4.3863284003420826e-07, "loss": 0.3188623905181885, "num_input_tokens_seen": 1059003928, "step": 25715, "train_runtime": 99083.4563, "train_tokens_per_second": 10687.999 }, { "epoch": 1.7317532992189604, "grad_norm": 0.7090451834048143, "learning_rate": 4.375505101538563e-07, "loss": 0.2814345359802246, "num_input_tokens_seen": 1059208232, "step": 25720, "train_runtime": 99102.3216, "train_tokens_per_second": 10688.026 }, { "epoch": 1.7320899542149206, "grad_norm": 0.7889267495912414, "learning_rate": 4.3646945614795487e-07, "loss": 0.31908516883850097, "num_input_tokens_seen": 1059416472, "step": 25725, "train_runtime": 99121.1447, "train_tokens_per_second": 10688.098 }, { "epoch": 1.7324266092108807, "grad_norm": 0.7235156434877928, "learning_rate": 4.3538967831881995e-07, "loss": 0.3141897201538086, "num_input_tokens_seen": 1059631536, "step": 25730, "train_runtime": 99139.5326, "train_tokens_per_second": 10688.285 }, { "epoch": 1.7327632642068407, "grad_norm": 0.7137355686525282, "learning_rate": 4.343111769684039e-07, "loss": 0.29079556465148926, "num_input_tokens_seen": 1059827608, "step": 25735, "train_runtime": 99160.4512, "train_tokens_per_second": 10688.007 }, { "epoch": 1.733099919202801, "grad_norm": 0.663902972233646, "learning_rate": 4.332339523983103e-07, "loss": 0.27959790229797366, "num_input_tokens_seen": 1060039344, "step": 25740, "train_runtime": 99179.3857, "train_tokens_per_second": 10688.102 }, { "epoch": 1.7334365741987612, "grad_norm": 0.7471359421160526, "learning_rate": 4.321580049097773e-07, "loss": 0.2837721347808838, "num_input_tokens_seen": 1060247208, "step": 25745, "train_runtime": 99197.1965, "train_tokens_per_second": 10688.278 }, { "epoch": 1.7337732291947212, "grad_norm": 0.7684560927741, "learning_rate": 4.310833348036941e-07, "loss": 0.2756755828857422, "num_input_tokens_seen": 1060451608, "step": 25750, "train_runtime": 99217.1103, "train_tokens_per_second": 10688.193 }, { "epoch": 1.7341098841906812, "grad_norm": 0.7017941117870865, "learning_rate": 4.300099423805865e-07, "loss": 0.3009187698364258, "num_input_tokens_seen": 1060645800, "step": 25755, "train_runtime": 99237.4298, "train_tokens_per_second": 10687.961 }, { "epoch": 1.7344465391866415, "grad_norm": 0.7358911162019921, "learning_rate": 4.289378279406264e-07, "loss": 0.30638108253479, "num_input_tokens_seen": 1060854008, "step": 25760, "train_runtime": 99255.0101, "train_tokens_per_second": 10688.166 }, { "epoch": 1.7347831941826017, "grad_norm": 0.7560760103822705, "learning_rate": 4.2786699178362647e-07, "loss": 0.3039027214050293, "num_input_tokens_seen": 1061061960, "step": 25765, "train_runtime": 99274.2112, "train_tokens_per_second": 10688.193 }, { "epoch": 1.7351198491785618, "grad_norm": 0.7566164107744068, "learning_rate": 4.2679743420904254e-07, "loss": 0.31157846450805665, "num_input_tokens_seen": 1061274832, "step": 25770, "train_runtime": 99292.0901, "train_tokens_per_second": 10688.413 }, { "epoch": 1.7354565041745218, "grad_norm": 0.7455208490835125, "learning_rate": 4.257291555159726e-07, "loss": 0.2627583980560303, "num_input_tokens_seen": 1061477344, "step": 25775, "train_runtime": 99310.5863, "train_tokens_per_second": 10688.461 }, { "epoch": 1.735793159170482, "grad_norm": 0.7286757504572519, "learning_rate": 4.246621560031594e-07, "loss": 0.2918559551239014, "num_input_tokens_seen": 1061674144, "step": 25780, "train_runtime": 99329.3224, "train_tokens_per_second": 10688.426 }, { "epoch": 1.7361298141664423, "grad_norm": 0.7446260561333075, "learning_rate": 4.235964359689837e-07, "loss": 0.27457900047302247, "num_input_tokens_seen": 1061887768, "step": 25785, "train_runtime": 99349.6959, "train_tokens_per_second": 10688.385 }, { "epoch": 1.7364664691624023, "grad_norm": 0.8360523401843538, "learning_rate": 4.225319957114726e-07, "loss": 0.304378867149353, "num_input_tokens_seen": 1062085000, "step": 25790, "train_runtime": 99370.5839, "train_tokens_per_second": 10688.123 }, { "epoch": 1.7368031241583624, "grad_norm": 0.6852561169429965, "learning_rate": 4.214688355282909e-07, "loss": 0.28112866878509524, "num_input_tokens_seen": 1062290600, "step": 25795, "train_runtime": 99391.194, "train_tokens_per_second": 10687.975 }, { "epoch": 1.7371397791543226, "grad_norm": 0.7523324020170388, "learning_rate": 4.204069557167506e-07, "loss": 0.28633670806884765, "num_input_tokens_seen": 1062492296, "step": 25800, "train_runtime": 99410.9874, "train_tokens_per_second": 10687.876 }, { "epoch": 1.7374764341502829, "grad_norm": 0.8021450742509034, "learning_rate": 4.1934635657380153e-07, "loss": 0.30090510845184326, "num_input_tokens_seen": 1062698872, "step": 25805, "train_runtime": 99428.7539, "train_tokens_per_second": 10688.044 }, { "epoch": 1.7378130891462429, "grad_norm": 0.6988128354130793, "learning_rate": 4.1828703839603637e-07, "loss": 0.2779444694519043, "num_input_tokens_seen": 1062911272, "step": 25810, "train_runtime": 99447.4903, "train_tokens_per_second": 10688.166 }, { "epoch": 1.738149744142203, "grad_norm": 0.7874052214776303, "learning_rate": 4.172290014796926e-07, "loss": 0.3177019119262695, "num_input_tokens_seen": 1063115208, "step": 25815, "train_runtime": 99466.0783, "train_tokens_per_second": 10688.219 }, { "epoch": 1.7384863991381632, "grad_norm": 0.7410065929953388, "learning_rate": 4.1617224612064353e-07, "loss": 0.3012667179107666, "num_input_tokens_seen": 1063317008, "step": 25820, "train_runtime": 99486.9462, "train_tokens_per_second": 10688.005 }, { "epoch": 1.7388230541341234, "grad_norm": 0.7341599332206112, "learning_rate": 4.151167726144101e-07, "loss": 0.2950291633605957, "num_input_tokens_seen": 1063535432, "step": 25825, "train_runtime": 99504.7654, "train_tokens_per_second": 10688.286 }, { "epoch": 1.7391597091300834, "grad_norm": 0.7621043811658387, "learning_rate": 4.1406258125615106e-07, "loss": 0.3103386878967285, "num_input_tokens_seen": 1063745576, "step": 25830, "train_runtime": 99522.5223, "train_tokens_per_second": 10688.491 }, { "epoch": 1.7394963641260435, "grad_norm": 0.6803689102116752, "learning_rate": 4.130096723406674e-07, "loss": 0.2929518461227417, "num_input_tokens_seen": 1063951568, "step": 25835, "train_runtime": 99541.6481, "train_tokens_per_second": 10688.507 }, { "epoch": 1.7398330191220037, "grad_norm": 0.7315920636276838, "learning_rate": 4.119580461624023e-07, "loss": 0.3038344383239746, "num_input_tokens_seen": 1064148304, "step": 25840, "train_runtime": 99559.7345, "train_tokens_per_second": 10688.541 }, { "epoch": 1.740169674117964, "grad_norm": 0.7150110581787739, "learning_rate": 4.109077030154396e-07, "loss": 0.3049629688262939, "num_input_tokens_seen": 1064353736, "step": 25845, "train_runtime": 99578.4938, "train_tokens_per_second": 10688.59 }, { "epoch": 1.740506329113924, "grad_norm": 0.661208763812143, "learning_rate": 4.0985864319350366e-07, "loss": 0.3064114570617676, "num_input_tokens_seen": 1064560568, "step": 25850, "train_runtime": 99597.4665, "train_tokens_per_second": 10688.631 }, { "epoch": 1.740842984109884, "grad_norm": 1.072484860082054, "learning_rate": 4.0881086698996154e-07, "loss": 0.2924654483795166, "num_input_tokens_seen": 1064770160, "step": 25855, "train_runtime": 99616.2254, "train_tokens_per_second": 10688.722 }, { "epoch": 1.7411796391058443, "grad_norm": 0.6301535334383662, "learning_rate": 4.077643746978194e-07, "loss": 0.29956352710723877, "num_input_tokens_seen": 1064979016, "step": 25860, "train_runtime": 99634.1494, "train_tokens_per_second": 10688.896 }, { "epoch": 1.7415162941018045, "grad_norm": 0.6544468233418016, "learning_rate": 4.067191666097281e-07, "loss": 0.28918592929840087, "num_input_tokens_seen": 1065183832, "step": 25865, "train_runtime": 99653.0837, "train_tokens_per_second": 10688.92 }, { "epoch": 1.7418529490977646, "grad_norm": 0.6701259503039463, "learning_rate": 4.056752430179728e-07, "loss": 0.2819520950317383, "num_input_tokens_seen": 1065392432, "step": 25870, "train_runtime": 99672.2179, "train_tokens_per_second": 10688.961 }, { "epoch": 1.7421896040937246, "grad_norm": 0.7175959044598005, "learning_rate": 4.046326042144866e-07, "loss": 0.28495059013366697, "num_input_tokens_seen": 1065602704, "step": 25875, "train_runtime": 99690.5674, "train_tokens_per_second": 10689.103 }, { "epoch": 1.7425262590896848, "grad_norm": 0.6399895250217328, "learning_rate": 4.0359125049083956e-07, "loss": 0.27583727836608884, "num_input_tokens_seen": 1065806328, "step": 25880, "train_runtime": 99708.913, "train_tokens_per_second": 10689.178 }, { "epoch": 1.742862914085645, "grad_norm": 0.7650512902896384, "learning_rate": 4.025511821382422e-07, "loss": 0.29570508003234863, "num_input_tokens_seen": 1066011328, "step": 25885, "train_runtime": 99731.321, "train_tokens_per_second": 10688.832 }, { "epoch": 1.7431995690816051, "grad_norm": 0.718391031678931, "learning_rate": 4.015123994475462e-07, "loss": 0.2828272819519043, "num_input_tokens_seen": 1066209304, "step": 25890, "train_runtime": 99751.6617, "train_tokens_per_second": 10688.637 }, { "epoch": 1.7435362240775654, "grad_norm": 0.7166112396446209, "learning_rate": 4.0047490270924417e-07, "loss": 0.30162320137023924, "num_input_tokens_seen": 1066429712, "step": 25895, "train_runtime": 99769.803, "train_tokens_per_second": 10688.903 }, { "epoch": 1.7438728790735256, "grad_norm": 0.6972264739750131, "learning_rate": 3.994386922134691e-07, "loss": 0.30052871704101564, "num_input_tokens_seen": 1066637136, "step": 25900, "train_runtime": 99788.2718, "train_tokens_per_second": 10689.003 }, { "epoch": 1.7442095340694856, "grad_norm": 0.6362394048467519, "learning_rate": 3.984037682499936e-07, "loss": 0.2865917205810547, "num_input_tokens_seen": 1066847744, "step": 25905, "train_runtime": 99808.1496, "train_tokens_per_second": 10688.984 }, { "epoch": 1.7445461890654457, "grad_norm": 0.7342313022455339, "learning_rate": 3.973701311082301e-07, "loss": 0.31545960903167725, "num_input_tokens_seen": 1067050720, "step": 25910, "train_runtime": 99827.6611, "train_tokens_per_second": 10688.928 }, { "epoch": 1.744882844061406, "grad_norm": 0.7998896950879862, "learning_rate": 3.9633778107723454e-07, "loss": 0.28844919204711916, "num_input_tokens_seen": 1067245016, "step": 25915, "train_runtime": 99847.4688, "train_tokens_per_second": 10688.754 }, { "epoch": 1.7452194990573662, "grad_norm": 0.6773106647620137, "learning_rate": 3.953067184456966e-07, "loss": 0.3086927175521851, "num_input_tokens_seen": 1067450752, "step": 25920, "train_runtime": 99867.3018, "train_tokens_per_second": 10688.691 }, { "epoch": 1.7455561540533262, "grad_norm": 0.7441217536508641, "learning_rate": 3.9427694350195224e-07, "loss": 0.3166250705718994, "num_input_tokens_seen": 1067665000, "step": 25925, "train_runtime": 99886.1727, "train_tokens_per_second": 10688.817 }, { "epoch": 1.7458928090492862, "grad_norm": 0.7098461083524342, "learning_rate": 3.9324845653397446e-07, "loss": 0.31019082069396975, "num_input_tokens_seen": 1067875176, "step": 25930, "train_runtime": 99905.7438, "train_tokens_per_second": 10688.827 }, { "epoch": 1.7462294640452465, "grad_norm": 0.7036679418132111, "learning_rate": 3.922212578293755e-07, "loss": 0.2731588363647461, "num_input_tokens_seen": 1068077432, "step": 25935, "train_runtime": 99926.7094, "train_tokens_per_second": 10688.608 }, { "epoch": 1.7465661190412067, "grad_norm": 0.7842075921850364, "learning_rate": 3.911953476754088e-07, "loss": 0.291110897064209, "num_input_tokens_seen": 1068286648, "step": 25940, "train_runtime": 99945.1635, "train_tokens_per_second": 10688.728 }, { "epoch": 1.7469027740371668, "grad_norm": 0.823008327227785, "learning_rate": 3.9017072635896716e-07, "loss": 0.31740784645080566, "num_input_tokens_seen": 1068500160, "step": 25945, "train_runtime": 99964.0436, "train_tokens_per_second": 10688.845 }, { "epoch": 1.7472394290331268, "grad_norm": 0.7125125338295228, "learning_rate": 3.891473941665819e-07, "loss": 0.30106024742126464, "num_input_tokens_seen": 1068716208, "step": 25950, "train_runtime": 99983.2838, "train_tokens_per_second": 10688.949 }, { "epoch": 1.747576084029087, "grad_norm": 0.8032366346265497, "learning_rate": 3.881253513844246e-07, "loss": 0.2998847007751465, "num_input_tokens_seen": 1068910320, "step": 25955, "train_runtime": 100003.6971, "train_tokens_per_second": 10688.708 }, { "epoch": 1.7479127390250473, "grad_norm": 0.9020011502404446, "learning_rate": 3.871045982983063e-07, "loss": 0.29460456371307375, "num_input_tokens_seen": 1069121120, "step": 25960, "train_runtime": 100021.518, "train_tokens_per_second": 10688.911 }, { "epoch": 1.7482493940210073, "grad_norm": 0.6933830246324652, "learning_rate": 3.8608513519367897e-07, "loss": 0.2678172826766968, "num_input_tokens_seen": 1069338384, "step": 25965, "train_runtime": 100041.3473, "train_tokens_per_second": 10688.964 }, { "epoch": 1.7485860490169673, "grad_norm": 0.7843222922142541, "learning_rate": 3.8506696235562915e-07, "loss": 0.2976375102996826, "num_input_tokens_seen": 1069539504, "step": 25970, "train_runtime": 100061.4959, "train_tokens_per_second": 10688.822 }, { "epoch": 1.7489227040129276, "grad_norm": 0.7169688381422893, "learning_rate": 3.840500800688884e-07, "loss": 0.2919629573822021, "num_input_tokens_seen": 1069757544, "step": 25975, "train_runtime": 100081.2065, "train_tokens_per_second": 10688.895 }, { "epoch": 1.7492593590088878, "grad_norm": 0.7510823561531209, "learning_rate": 3.8303448861782333e-07, "loss": 0.29884335994720457, "num_input_tokens_seen": 1069950960, "step": 25980, "train_runtime": 100099.8104, "train_tokens_per_second": 10688.841 }, { "epoch": 1.7495960140048479, "grad_norm": 0.7772297465330411, "learning_rate": 3.8202018828644105e-07, "loss": 0.28201496601104736, "num_input_tokens_seen": 1070155984, "step": 25985, "train_runtime": 100118.4159, "train_tokens_per_second": 10688.902 }, { "epoch": 1.749932669000808, "grad_norm": 0.8661718410553275, "learning_rate": 3.8100717935838804e-07, "loss": 0.3170497417449951, "num_input_tokens_seen": 1070360488, "step": 25990, "train_runtime": 100138.2864, "train_tokens_per_second": 10688.824 }, { "epoch": 1.7502693239967682, "grad_norm": 0.7630600613148146, "learning_rate": 3.799954621169477e-07, "loss": 0.27300424575805665, "num_input_tokens_seen": 1070565176, "step": 25995, "train_runtime": 100158.0999, "train_tokens_per_second": 10688.753 }, { "epoch": 1.7506059789927284, "grad_norm": 0.7318548093834616, "learning_rate": 3.7898503684504483e-07, "loss": 0.2935200214385986, "num_input_tokens_seen": 1070766288, "step": 26000, "train_runtime": 100178.1133, "train_tokens_per_second": 10688.625 }, { "epoch": 1.7509426339886884, "grad_norm": 0.6621191768273209, "learning_rate": 3.7797590382524066e-07, "loss": 0.28708367347717284, "num_input_tokens_seen": 1070958248, "step": 26005, "train_runtime": 100196.8073, "train_tokens_per_second": 10688.547 }, { "epoch": 1.7512792889846485, "grad_norm": 0.7163660046156639, "learning_rate": 3.76968063339736e-07, "loss": 0.2997905731201172, "num_input_tokens_seen": 1071174656, "step": 26010, "train_runtime": 100215.087, "train_tokens_per_second": 10688.756 }, { "epoch": 1.7516159439806087, "grad_norm": 0.7542345925032773, "learning_rate": 3.759615156703722e-07, "loss": 0.2822559833526611, "num_input_tokens_seen": 1071377024, "step": 26015, "train_runtime": 100234.9915, "train_tokens_per_second": 10688.653 }, { "epoch": 1.751952598976569, "grad_norm": 0.7168355150854111, "learning_rate": 3.749562610986235e-07, "loss": 0.31146528720855715, "num_input_tokens_seen": 1071581936, "step": 26020, "train_runtime": 100254.6299, "train_tokens_per_second": 10688.603 }, { "epoch": 1.752289253972529, "grad_norm": 0.7018936011146979, "learning_rate": 3.739522999056094e-07, "loss": 0.2807086229324341, "num_input_tokens_seen": 1071775440, "step": 26025, "train_runtime": 100272.7162, "train_tokens_per_second": 10688.605 }, { "epoch": 1.752625908968489, "grad_norm": 0.688159011963565, "learning_rate": 3.7294963237208326e-07, "loss": 0.2946134567260742, "num_input_tokens_seen": 1071986328, "step": 26030, "train_runtime": 100292.6463, "train_tokens_per_second": 10688.584 }, { "epoch": 1.7529625639644493, "grad_norm": 0.7678228618625258, "learning_rate": 3.7194825877843786e-07, "loss": 0.28845384120941164, "num_input_tokens_seen": 1072198768, "step": 26035, "train_runtime": 100312.1735, "train_tokens_per_second": 10688.621 }, { "epoch": 1.7532992189604095, "grad_norm": 0.6978820069136707, "learning_rate": 3.7094817940470375e-07, "loss": 0.30446629524230956, "num_input_tokens_seen": 1072396960, "step": 26040, "train_runtime": 100333.0822, "train_tokens_per_second": 10688.369 }, { "epoch": 1.7536358739563696, "grad_norm": 0.6884676454028912, "learning_rate": 3.6994939453055044e-07, "loss": 0.29955596923828126, "num_input_tokens_seen": 1072611040, "step": 26045, "train_runtime": 100351.1271, "train_tokens_per_second": 10688.58 }, { "epoch": 1.7539725289523296, "grad_norm": 0.7538183283157949, "learning_rate": 3.6895190443528515e-07, "loss": 0.2976208209991455, "num_input_tokens_seen": 1072823776, "step": 26050, "train_runtime": 100370.6001, "train_tokens_per_second": 10688.626 }, { "epoch": 1.7543091839482898, "grad_norm": 0.6675124792235319, "learning_rate": 3.679557093978525e-07, "loss": 0.30975916385650637, "num_input_tokens_seen": 1073031656, "step": 26055, "train_runtime": 100390.8773, "train_tokens_per_second": 10688.537 }, { "epoch": 1.75464583894425, "grad_norm": 0.7496533250122082, "learning_rate": 3.669608096968341e-07, "loss": 0.2889568567276001, "num_input_tokens_seen": 1073229272, "step": 26060, "train_runtime": 100409.4729, "train_tokens_per_second": 10688.526 }, { "epoch": 1.75498249394021, "grad_norm": 0.7687678702075906, "learning_rate": 3.6596720561045295e-07, "loss": 0.2900463819503784, "num_input_tokens_seen": 1073440544, "step": 26065, "train_runtime": 100429.0176, "train_tokens_per_second": 10688.55 }, { "epoch": 1.7553191489361701, "grad_norm": 0.7795792915141637, "learning_rate": 3.6497489741656455e-07, "loss": 0.30313451290130616, "num_input_tokens_seen": 1073650016, "step": 26070, "train_runtime": 100448.266, "train_tokens_per_second": 10688.587 }, { "epoch": 1.7556558039321304, "grad_norm": 0.6649855978043098, "learning_rate": 3.639838853926669e-07, "loss": 0.2930476188659668, "num_input_tokens_seen": 1073866176, "step": 26075, "train_runtime": 100466.8832, "train_tokens_per_second": 10688.758 }, { "epoch": 1.7559924589280906, "grad_norm": 0.7286132502514463, "learning_rate": 3.629941698158923e-07, "loss": 0.3148168087005615, "num_input_tokens_seen": 1074073432, "step": 26080, "train_runtime": 100487.2859, "train_tokens_per_second": 10688.65 }, { "epoch": 1.7563291139240507, "grad_norm": 0.6733794907072795, "learning_rate": 3.6200575096301207e-07, "loss": 0.27848761081695556, "num_input_tokens_seen": 1074278768, "step": 26085, "train_runtime": 100506.7972, "train_tokens_per_second": 10688.618 }, { "epoch": 1.7566657689200107, "grad_norm": 0.7751343874928684, "learning_rate": 3.61018629110434e-07, "loss": 0.3209546566009521, "num_input_tokens_seen": 1074488872, "step": 26090, "train_runtime": 100525.5332, "train_tokens_per_second": 10688.716 }, { "epoch": 1.757002423915971, "grad_norm": 0.6713224975732225, "learning_rate": 3.6003280453420386e-07, "loss": 0.28715536594390867, "num_input_tokens_seen": 1074696408, "step": 26095, "train_runtime": 100543.7057, "train_tokens_per_second": 10688.848 }, { "epoch": 1.7573390789119312, "grad_norm": 0.7321547354065117, "learning_rate": 3.59048277510004e-07, "loss": 0.28300747871398924, "num_input_tokens_seen": 1074904632, "step": 26100, "train_runtime": 100562.9067, "train_tokens_per_second": 10688.878 }, { "epoch": 1.7576757339078912, "grad_norm": 0.7803538847251124, "learning_rate": 3.5806504831315423e-07, "loss": 0.29092931747436523, "num_input_tokens_seen": 1075111520, "step": 26105, "train_runtime": 100583.4211, "train_tokens_per_second": 10688.755 }, { "epoch": 1.7580123889038513, "grad_norm": 0.7329116892611625, "learning_rate": 3.570831172186112e-07, "loss": 0.30411415100097655, "num_input_tokens_seen": 1075322264, "step": 26110, "train_runtime": 100601.8017, "train_tokens_per_second": 10688.897 }, { "epoch": 1.7583490438998115, "grad_norm": 0.7625713369158282, "learning_rate": 3.5610248450097084e-07, "loss": 0.30416293144226075, "num_input_tokens_seen": 1075529112, "step": 26115, "train_runtime": 100621.2677, "train_tokens_per_second": 10688.885 }, { "epoch": 1.7586856988957718, "grad_norm": 0.660624432568573, "learning_rate": 3.551231504344604e-07, "loss": 0.2887174367904663, "num_input_tokens_seen": 1075735344, "step": 26120, "train_runtime": 100640.3489, "train_tokens_per_second": 10688.907 }, { "epoch": 1.7590223538917318, "grad_norm": 0.6501418871249343, "learning_rate": 3.5414511529295036e-07, "loss": 0.3023014307022095, "num_input_tokens_seen": 1075935296, "step": 26125, "train_runtime": 100658.3941, "train_tokens_per_second": 10688.977 }, { "epoch": 1.7593590088876918, "grad_norm": 0.8007384173477892, "learning_rate": 3.5316837934994465e-07, "loss": 0.31098754405975343, "num_input_tokens_seen": 1076140872, "step": 26130, "train_runtime": 100679.2048, "train_tokens_per_second": 10688.81 }, { "epoch": 1.759695663883652, "grad_norm": 0.7069090804315538, "learning_rate": 3.521929428785836e-07, "loss": 0.30125672817230226, "num_input_tokens_seen": 1076355424, "step": 26135, "train_runtime": 100700.1083, "train_tokens_per_second": 10688.722 }, { "epoch": 1.7600323188796123, "grad_norm": 0.790836975287447, "learning_rate": 3.5121880615164584e-07, "loss": 0.317656946182251, "num_input_tokens_seen": 1076558248, "step": 26140, "train_runtime": 100718.0957, "train_tokens_per_second": 10688.826 }, { "epoch": 1.7603689738755723, "grad_norm": 0.7066047974297875, "learning_rate": 3.5024596944154445e-07, "loss": 0.30439023971557616, "num_input_tokens_seen": 1076762232, "step": 26145, "train_runtime": 100736.203, "train_tokens_per_second": 10688.93 }, { "epoch": 1.7607056288715324, "grad_norm": 0.7548379942704424, "learning_rate": 3.4927443302033127e-07, "loss": 0.2739942789077759, "num_input_tokens_seen": 1076974904, "step": 26150, "train_runtime": 100756.4919, "train_tokens_per_second": 10688.888 }, { "epoch": 1.7610422838674926, "grad_norm": 0.7538151700810496, "learning_rate": 3.4830419715969233e-07, "loss": 0.2748421192169189, "num_input_tokens_seen": 1077175232, "step": 26155, "train_runtime": 100775.3948, "train_tokens_per_second": 10688.871 }, { "epoch": 1.7613789388634529, "grad_norm": 0.7899644303669077, "learning_rate": 3.4733526213095114e-07, "loss": 0.30200355052947997, "num_input_tokens_seen": 1077383760, "step": 26160, "train_runtime": 100794.6863, "train_tokens_per_second": 10688.894 }, { "epoch": 1.761715593859413, "grad_norm": 0.7765730110822598, "learning_rate": 3.4636762820506876e-07, "loss": 0.3022803544998169, "num_input_tokens_seen": 1077592312, "step": 26165, "train_runtime": 100814.4666, "train_tokens_per_second": 10688.866 }, { "epoch": 1.762052248855373, "grad_norm": 0.8323065090766141, "learning_rate": 3.4540129565263867e-07, "loss": 0.3108691215515137, "num_input_tokens_seen": 1077793960, "step": 26170, "train_runtime": 100833.9184, "train_tokens_per_second": 10688.804 }, { "epoch": 1.7623889038513332, "grad_norm": 0.7300400897828653, "learning_rate": 3.444362647438942e-07, "loss": 0.3081367015838623, "num_input_tokens_seen": 1078007328, "step": 26175, "train_runtime": 100853.3345, "train_tokens_per_second": 10688.862 }, { "epoch": 1.7627255588472934, "grad_norm": 0.6980950881125989, "learning_rate": 3.434725357487029e-07, "loss": 0.29404072761535643, "num_input_tokens_seen": 1078221176, "step": 26180, "train_runtime": 100873.7789, "train_tokens_per_second": 10688.815 }, { "epoch": 1.7630622138432535, "grad_norm": 0.7663253899152604, "learning_rate": 3.4251010893656844e-07, "loss": 0.3216234683990479, "num_input_tokens_seen": 1078426896, "step": 26185, "train_runtime": 100892.3535, "train_tokens_per_second": 10688.886 }, { "epoch": 1.7633988688392135, "grad_norm": 0.780683393346668, "learning_rate": 3.4154898457663065e-07, "loss": 0.2979679346084595, "num_input_tokens_seen": 1078623024, "step": 26190, "train_runtime": 100911.2231, "train_tokens_per_second": 10688.831 }, { "epoch": 1.7637355238351737, "grad_norm": 0.670550549011571, "learning_rate": 3.40589162937664e-07, "loss": 0.29341557025909426, "num_input_tokens_seen": 1078812648, "step": 26195, "train_runtime": 100930.2122, "train_tokens_per_second": 10688.699 }, { "epoch": 1.764072178831134, "grad_norm": 0.7247622614183925, "learning_rate": 3.3963064428808034e-07, "loss": 0.27037293910980226, "num_input_tokens_seen": 1079010928, "step": 26200, "train_runtime": 100950.7627, "train_tokens_per_second": 10688.487 }, { "epoch": 1.764408833827094, "grad_norm": 0.637061157285013, "learning_rate": 3.386734288959265e-07, "loss": 0.297744607925415, "num_input_tokens_seen": 1079200832, "step": 26205, "train_runtime": 100971.0327, "train_tokens_per_second": 10688.222 }, { "epoch": 1.764745488823054, "grad_norm": 0.782044788696775, "learning_rate": 3.377175170288838e-07, "loss": 0.3037066698074341, "num_input_tokens_seen": 1079410072, "step": 26210, "train_runtime": 100989.9408, "train_tokens_per_second": 10688.293 }, { "epoch": 1.7650821438190143, "grad_norm": 0.7016725897471064, "learning_rate": 3.367629089542712e-07, "loss": 0.2932668924331665, "num_input_tokens_seen": 1079629280, "step": 26215, "train_runtime": 101008.1299, "train_tokens_per_second": 10688.538 }, { "epoch": 1.7654187988149745, "grad_norm": 0.7384456438985257, "learning_rate": 3.3580960493904024e-07, "loss": 0.30618901252746583, "num_input_tokens_seen": 1079836800, "step": 26220, "train_runtime": 101027.7252, "train_tokens_per_second": 10688.519 }, { "epoch": 1.7657554538109346, "grad_norm": 0.720837202882629, "learning_rate": 3.3485760524978093e-07, "loss": 0.3072517395019531, "num_input_tokens_seen": 1080030696, "step": 26225, "train_runtime": 101045.3883, "train_tokens_per_second": 10688.57 }, { "epoch": 1.7660921088068946, "grad_norm": 0.7673061380311637, "learning_rate": 3.3390691015271646e-07, "loss": 0.2970618724822998, "num_input_tokens_seen": 1080234976, "step": 26230, "train_runtime": 101063.5615, "train_tokens_per_second": 10688.669 }, { "epoch": 1.7664287638028549, "grad_norm": 0.7410788628042716, "learning_rate": 3.329575199137053e-07, "loss": 0.2833516836166382, "num_input_tokens_seen": 1080443704, "step": 26235, "train_runtime": 101082.1793, "train_tokens_per_second": 10688.765 }, { "epoch": 1.766765418798815, "grad_norm": 0.8108354816703944, "learning_rate": 3.3200943479824113e-07, "loss": 0.32409560680389404, "num_input_tokens_seen": 1080647880, "step": 26240, "train_runtime": 101102.12, "train_tokens_per_second": 10688.677 }, { "epoch": 1.7671020737947751, "grad_norm": 0.6207472698895399, "learning_rate": 3.3106265507145406e-07, "loss": 0.25365774631500243, "num_input_tokens_seen": 1080849192, "step": 26245, "train_runtime": 101121.2559, "train_tokens_per_second": 10688.645 }, { "epoch": 1.7674387287907352, "grad_norm": 0.6961225599256013, "learning_rate": 3.3011718099810687e-07, "loss": 0.28513240814208984, "num_input_tokens_seen": 1081047424, "step": 26250, "train_runtime": 101140.3317, "train_tokens_per_second": 10688.589 }, { "epoch": 1.7677753837866954, "grad_norm": 0.7567892001271288, "learning_rate": 3.2917301284259904e-07, "loss": 0.30402777194976804, "num_input_tokens_seen": 1081260712, "step": 26255, "train_runtime": 101160.0828, "train_tokens_per_second": 10688.61 }, { "epoch": 1.7681120387826557, "grad_norm": 0.7173022342356028, "learning_rate": 3.2823015086896335e-07, "loss": 0.3131782054901123, "num_input_tokens_seen": 1081465048, "step": 26260, "train_runtime": 101179.5214, "train_tokens_per_second": 10688.576 }, { "epoch": 1.7684486937786157, "grad_norm": 0.7129256100984208, "learning_rate": 3.2728859534087e-07, "loss": 0.29275922775268554, "num_input_tokens_seen": 1081678328, "step": 26265, "train_runtime": 101199.0947, "train_tokens_per_second": 10688.617 }, { "epoch": 1.7687853487745757, "grad_norm": 0.6964638085775661, "learning_rate": 3.263483465216194e-07, "loss": 0.3049002647399902, "num_input_tokens_seen": 1081893320, "step": 26270, "train_runtime": 101218.5215, "train_tokens_per_second": 10688.689 }, { "epoch": 1.769122003770536, "grad_norm": 0.6578655384837561, "learning_rate": 3.2540940467415126e-07, "loss": 0.2965759038925171, "num_input_tokens_seen": 1082098392, "step": 26275, "train_runtime": 101237.2959, "train_tokens_per_second": 10688.733 }, { "epoch": 1.7694586587664962, "grad_norm": 0.6578670896830704, "learning_rate": 3.2447177006103726e-07, "loss": 0.30354511737823486, "num_input_tokens_seen": 1082301288, "step": 26280, "train_runtime": 101258.2239, "train_tokens_per_second": 10688.527 }, { "epoch": 1.7697953137624562, "grad_norm": 0.6799070123736927, "learning_rate": 3.235354429444831e-07, "loss": 0.2987574577331543, "num_input_tokens_seen": 1082492504, "step": 26285, "train_runtime": 101276.8847, "train_tokens_per_second": 10688.446 }, { "epoch": 1.7701319687584163, "grad_norm": 0.7110116952508463, "learning_rate": 3.226004235863306e-07, "loss": 0.3008877754211426, "num_input_tokens_seen": 1082704712, "step": 26290, "train_runtime": 101298.0874, "train_tokens_per_second": 10688.304 }, { "epoch": 1.7704686237543765, "grad_norm": 0.7536605682349607, "learning_rate": 3.2166671224805437e-07, "loss": 0.29301745891571046, "num_input_tokens_seen": 1082918376, "step": 26295, "train_runtime": 101316.7461, "train_tokens_per_second": 10688.444 }, { "epoch": 1.7708052787503368, "grad_norm": 0.7559549918956743, "learning_rate": 3.207343091907633e-07, "loss": 0.28940529823303224, "num_input_tokens_seen": 1083115512, "step": 26300, "train_runtime": 101336.7983, "train_tokens_per_second": 10688.274 }, { "epoch": 1.7711419337462968, "grad_norm": 0.7427200174021666, "learning_rate": 3.1980321467520226e-07, "loss": 0.306252646446228, "num_input_tokens_seen": 1083304632, "step": 26305, "train_runtime": 101355.5509, "train_tokens_per_second": 10688.163 }, { "epoch": 1.7714785887422568, "grad_norm": 0.7961743405962808, "learning_rate": 3.1887342896174735e-07, "loss": 0.310301685333252, "num_input_tokens_seen": 1083499368, "step": 26310, "train_runtime": 101377.4903, "train_tokens_per_second": 10687.771 }, { "epoch": 1.771815243738217, "grad_norm": 0.6208451646619824, "learning_rate": 3.1794495231041276e-07, "loss": 0.28247437477111814, "num_input_tokens_seen": 1083712600, "step": 26315, "train_runtime": 101396.2348, "train_tokens_per_second": 10687.898 }, { "epoch": 1.7721518987341773, "grad_norm": 0.6811606450194969, "learning_rate": 3.1701778498084035e-07, "loss": 0.3041219711303711, "num_input_tokens_seen": 1083907184, "step": 26320, "train_runtime": 101415.9673, "train_tokens_per_second": 10687.737 }, { "epoch": 1.7724885537301374, "grad_norm": 0.7268172833134913, "learning_rate": 3.160919272323121e-07, "loss": 0.30868067741394045, "num_input_tokens_seen": 1084124272, "step": 26325, "train_runtime": 101435.9427, "train_tokens_per_second": 10687.772 }, { "epoch": 1.7728252087260974, "grad_norm": 0.6696233191278835, "learning_rate": 3.1516737932374087e-07, "loss": 0.3042840242385864, "num_input_tokens_seen": 1084320272, "step": 26330, "train_runtime": 101454.8811, "train_tokens_per_second": 10687.709 }, { "epoch": 1.7731618637220576, "grad_norm": 0.7105455303010483, "learning_rate": 3.142441415136727e-07, "loss": 0.294967794418335, "num_input_tokens_seen": 1084534024, "step": 26335, "train_runtime": 101473.6537, "train_tokens_per_second": 10687.839 }, { "epoch": 1.773498518718018, "grad_norm": 0.7373589227520401, "learning_rate": 3.133222140602893e-07, "loss": 0.2801822185516357, "num_input_tokens_seen": 1084728208, "step": 26340, "train_runtime": 101490.8646, "train_tokens_per_second": 10687.939 }, { "epoch": 1.773835173713978, "grad_norm": 0.7154316650226009, "learning_rate": 3.124015972214034e-07, "loss": 0.3072362899780273, "num_input_tokens_seen": 1084936568, "step": 26345, "train_runtime": 101508.3381, "train_tokens_per_second": 10688.152 }, { "epoch": 1.774171828709938, "grad_norm": 0.7798228824889422, "learning_rate": 3.114822912544635e-07, "loss": 0.3172905445098877, "num_input_tokens_seen": 1085136248, "step": 26350, "train_runtime": 101529.5322, "train_tokens_per_second": 10687.888 }, { "epoch": 1.7745084837058982, "grad_norm": 0.745805481037662, "learning_rate": 3.1056429641655007e-07, "loss": 0.2916240692138672, "num_input_tokens_seen": 1085333440, "step": 26355, "train_runtime": 101549.3806, "train_tokens_per_second": 10687.741 }, { "epoch": 1.7748451387018584, "grad_norm": 0.7659679329056573, "learning_rate": 3.0964761296437665e-07, "loss": 0.2932368040084839, "num_input_tokens_seen": 1085542488, "step": 26360, "train_runtime": 101567.6982, "train_tokens_per_second": 10687.871 }, { "epoch": 1.7751817936978185, "grad_norm": 0.7265883496770023, "learning_rate": 3.087322411542937e-07, "loss": 0.30570862293243406, "num_input_tokens_seen": 1085756032, "step": 26365, "train_runtime": 101585.5628, "train_tokens_per_second": 10688.094 }, { "epoch": 1.7755184486937785, "grad_norm": 0.7700810505559074, "learning_rate": 3.0781818124227867e-07, "loss": 0.2785022258758545, "num_input_tokens_seen": 1085955440, "step": 26370, "train_runtime": 101604.7057, "train_tokens_per_second": 10688.043 }, { "epoch": 1.7758551036897388, "grad_norm": 0.7148815246272952, "learning_rate": 3.0690543348394776e-07, "loss": 0.29209635257720945, "num_input_tokens_seen": 1086165496, "step": 26375, "train_runtime": 101624.175, "train_tokens_per_second": 10688.062 }, { "epoch": 1.776191758685699, "grad_norm": 0.718983909693136, "learning_rate": 3.059939981345467e-07, "loss": 0.28342084884643554, "num_input_tokens_seen": 1086365712, "step": 26380, "train_runtime": 101641.381, "train_tokens_per_second": 10688.223 }, { "epoch": 1.776528413681659, "grad_norm": 0.7823488932232364, "learning_rate": 3.050838754489566e-07, "loss": 0.29657270908355715, "num_input_tokens_seen": 1086571264, "step": 26385, "train_runtime": 101661.2858, "train_tokens_per_second": 10688.152 }, { "epoch": 1.776865068677619, "grad_norm": 0.6942719906122933, "learning_rate": 3.041750656816894e-07, "loss": 0.29666996002197266, "num_input_tokens_seen": 1086777280, "step": 26390, "train_runtime": 101679.9492, "train_tokens_per_second": 10688.216 }, { "epoch": 1.7772017236735793, "grad_norm": 0.8043068180597595, "learning_rate": 3.0326756908689135e-07, "loss": 0.31491353511810305, "num_input_tokens_seen": 1086985688, "step": 26395, "train_runtime": 101700.0899, "train_tokens_per_second": 10688.149 }, { "epoch": 1.7775383786695396, "grad_norm": 0.6544091670355889, "learning_rate": 3.0236138591833995e-07, "loss": 0.2784532308578491, "num_input_tokens_seen": 1087192960, "step": 26400, "train_runtime": 101718.8619, "train_tokens_per_second": 10688.214 }, { "epoch": 1.7778750336654996, "grad_norm": 0.7130809532359411, "learning_rate": 3.0145651642944863e-07, "loss": 0.31468002796173095, "num_input_tokens_seen": 1087409384, "step": 26405, "train_runtime": 101739.1901, "train_tokens_per_second": 10688.206 }, { "epoch": 1.7782116886614596, "grad_norm": 0.6992622578154271, "learning_rate": 3.005529608732588e-07, "loss": 0.2622381687164307, "num_input_tokens_seen": 1087610952, "step": 26410, "train_runtime": 101758.02, "train_tokens_per_second": 10688.209 }, { "epoch": 1.7785483436574199, "grad_norm": 0.708030621998934, "learning_rate": 2.996507195024495e-07, "loss": 0.3230019807815552, "num_input_tokens_seen": 1087828192, "step": 26415, "train_runtime": 101777.9054, "train_tokens_per_second": 10688.255 }, { "epoch": 1.7788849986533801, "grad_norm": 0.775853948951779, "learning_rate": 2.9874979256932614e-07, "loss": 0.2928619384765625, "num_input_tokens_seen": 1088034688, "step": 26420, "train_runtime": 101796.7986, "train_tokens_per_second": 10688.3 }, { "epoch": 1.7792216536493402, "grad_norm": 0.7687511487889331, "learning_rate": 2.9785018032583325e-07, "loss": 0.31228365898132326, "num_input_tokens_seen": 1088245664, "step": 26425, "train_runtime": 101817.2107, "train_tokens_per_second": 10688.229 }, { "epoch": 1.7795583086453002, "grad_norm": 0.8273142597124105, "learning_rate": 2.969518830235435e-07, "loss": 0.29835824966430663, "num_input_tokens_seen": 1088449456, "step": 26430, "train_runtime": 101834.6376, "train_tokens_per_second": 10688.401 }, { "epoch": 1.7798949636412604, "grad_norm": 0.7431233370692863, "learning_rate": 2.960549009136626e-07, "loss": 0.29845967292785647, "num_input_tokens_seen": 1088658336, "step": 26435, "train_runtime": 101854.472, "train_tokens_per_second": 10688.371 }, { "epoch": 1.7802316186372207, "grad_norm": 0.8173036540984758, "learning_rate": 2.951592342470289e-07, "loss": 0.32927818298339845, "num_input_tokens_seen": 1088868992, "step": 26440, "train_runtime": 101872.4319, "train_tokens_per_second": 10688.554 }, { "epoch": 1.7805682736331807, "grad_norm": 0.7171437403381155, "learning_rate": 2.942648832741124e-07, "loss": 0.2833122730255127, "num_input_tokens_seen": 1089064904, "step": 26445, "train_runtime": 101892.2655, "train_tokens_per_second": 10688.396 }, { "epoch": 1.7809049286291407, "grad_norm": 0.6473696073775396, "learning_rate": 2.933718482450154e-07, "loss": 0.29249820709228513, "num_input_tokens_seen": 1089271152, "step": 26450, "train_runtime": 101911.5218, "train_tokens_per_second": 10688.4 }, { "epoch": 1.781241583625101, "grad_norm": 1.5218534380013757, "learning_rate": 2.9248012940947423e-07, "loss": 0.3193804740905762, "num_input_tokens_seen": 1089485240, "step": 26455, "train_runtime": 101929.7838, "train_tokens_per_second": 10688.586 }, { "epoch": 1.7815782386210612, "grad_norm": 0.7288114509035954, "learning_rate": 2.915897270168522e-07, "loss": 0.3037823438644409, "num_input_tokens_seen": 1089681704, "step": 26460, "train_runtime": 101949.7226, "train_tokens_per_second": 10688.422 }, { "epoch": 1.7819148936170213, "grad_norm": 0.7956870669451988, "learning_rate": 2.9070064131615004e-07, "loss": 0.3005529403686523, "num_input_tokens_seen": 1089880728, "step": 26465, "train_runtime": 101969.8456, "train_tokens_per_second": 10688.265 }, { "epoch": 1.7822515486129813, "grad_norm": 0.7604213169241111, "learning_rate": 2.8981287255599567e-07, "loss": 0.287932300567627, "num_input_tokens_seen": 1090065672, "step": 26470, "train_runtime": 101988.5649, "train_tokens_per_second": 10688.117 }, { "epoch": 1.7825882036089415, "grad_norm": 0.7226628529430965, "learning_rate": 2.8892642098465205e-07, "loss": 0.2922965526580811, "num_input_tokens_seen": 1090272448, "step": 26475, "train_runtime": 102007.9254, "train_tokens_per_second": 10688.115 }, { "epoch": 1.7829248586049018, "grad_norm": 0.7229843474228593, "learning_rate": 2.8804128685001263e-07, "loss": 0.29262919425964357, "num_input_tokens_seen": 1090486696, "step": 26480, "train_runtime": 102027.2211, "train_tokens_per_second": 10688.194 }, { "epoch": 1.7832615136008618, "grad_norm": 0.7700138012482051, "learning_rate": 2.8715747039960216e-07, "loss": 0.2727129220962524, "num_input_tokens_seen": 1090686352, "step": 26485, "train_runtime": 102045.4972, "train_tokens_per_second": 10688.236 }, { "epoch": 1.7835981685968219, "grad_norm": 0.7887264175830143, "learning_rate": 2.8627497188057684e-07, "loss": 0.30376248359680175, "num_input_tokens_seen": 1090896488, "step": 26490, "train_runtime": 102065.2679, "train_tokens_per_second": 10688.224 }, { "epoch": 1.783934823592782, "grad_norm": 0.7220313904898069, "learning_rate": 2.853937915397248e-07, "loss": 0.3185889720916748, "num_input_tokens_seen": 1091102672, "step": 26495, "train_runtime": 102085.3803, "train_tokens_per_second": 10688.138 }, { "epoch": 1.7842714785887424, "grad_norm": 0.7248367739886199, "learning_rate": 2.845139296234639e-07, "loss": 0.28315463066101076, "num_input_tokens_seen": 1091317824, "step": 26500, "train_runtime": 102105.3412, "train_tokens_per_second": 10688.156 }, { "epoch": 1.7846081335847024, "grad_norm": 0.6470107204644675, "learning_rate": 2.836353863778479e-07, "loss": 0.2908551454544067, "num_input_tokens_seen": 1091524648, "step": 26505, "train_runtime": 102124.4466, "train_tokens_per_second": 10688.182 }, { "epoch": 1.7849447885806624, "grad_norm": 0.6396297982733048, "learning_rate": 2.8275816204855534e-07, "loss": 0.3023655414581299, "num_input_tokens_seen": 1091730744, "step": 26510, "train_runtime": 102145.8332, "train_tokens_per_second": 10687.962 }, { "epoch": 1.7852814435766227, "grad_norm": 0.7590342144888007, "learning_rate": 2.818822568809015e-07, "loss": 0.31840436458587645, "num_input_tokens_seen": 1091924848, "step": 26515, "train_runtime": 102164.3262, "train_tokens_per_second": 10687.927 }, { "epoch": 1.785618098572583, "grad_norm": 0.7153934400530002, "learning_rate": 2.810076711198284e-07, "loss": 0.28369171619415284, "num_input_tokens_seen": 1092126192, "step": 26520, "train_runtime": 102183.4515, "train_tokens_per_second": 10687.897 }, { "epoch": 1.785954753568543, "grad_norm": 0.723107878361945, "learning_rate": 2.801344050099131e-07, "loss": 0.31170358657836916, "num_input_tokens_seen": 1092347512, "step": 26525, "train_runtime": 102203.3855, "train_tokens_per_second": 10687.978 }, { "epoch": 1.786291408564503, "grad_norm": 0.6741464739784142, "learning_rate": 2.7926245879536076e-07, "loss": 0.29854934215545653, "num_input_tokens_seen": 1092554800, "step": 26530, "train_runtime": 102223.9846, "train_tokens_per_second": 10687.852 }, { "epoch": 1.7866280635604632, "grad_norm": 0.6744068020782554, "learning_rate": 2.7839183272000857e-07, "loss": 0.28508405685424804, "num_input_tokens_seen": 1092771320, "step": 26535, "train_runtime": 102241.8546, "train_tokens_per_second": 10688.102 }, { "epoch": 1.7869647185564235, "grad_norm": 0.7729349660299211, "learning_rate": 2.775225270273241e-07, "loss": 0.30348477363586424, "num_input_tokens_seen": 1092984192, "step": 26540, "train_runtime": 102261.2164, "train_tokens_per_second": 10688.16 }, { "epoch": 1.7873013735523835, "grad_norm": 0.6871615567417672, "learning_rate": 2.7665454196040665e-07, "loss": 0.2745073318481445, "num_input_tokens_seen": 1093195848, "step": 26545, "train_runtime": 102281.1411, "train_tokens_per_second": 10688.147 }, { "epoch": 1.7876380285483435, "grad_norm": 0.7620764608967082, "learning_rate": 2.7578787776198325e-07, "loss": 0.31154623031616213, "num_input_tokens_seen": 1093394448, "step": 26550, "train_runtime": 102299.5793, "train_tokens_per_second": 10688.162 }, { "epoch": 1.7879746835443038, "grad_norm": 0.7225141626992257, "learning_rate": 2.7492253467441775e-07, "loss": 0.27040905952453614, "num_input_tokens_seen": 1093602512, "step": 26555, "train_runtime": 102319.2393, "train_tokens_per_second": 10688.142 }, { "epoch": 1.788311338540264, "grad_norm": 0.6778567714105612, "learning_rate": 2.740585129396961e-07, "loss": 0.3026124477386475, "num_input_tokens_seen": 1093813592, "step": 26560, "train_runtime": 102338.9226, "train_tokens_per_second": 10688.148 }, { "epoch": 1.788647993536224, "grad_norm": 0.7280467097554217, "learning_rate": 2.731958127994433e-07, "loss": 0.27365386486053467, "num_input_tokens_seen": 1094019872, "step": 26565, "train_runtime": 102359.5195, "train_tokens_per_second": 10688.013 }, { "epoch": 1.788984648532184, "grad_norm": 0.7830904483740326, "learning_rate": 2.7233443449490695e-07, "loss": 0.3070545196533203, "num_input_tokens_seen": 1094222040, "step": 26570, "train_runtime": 102377.9593, "train_tokens_per_second": 10688.063 }, { "epoch": 1.7893213035281443, "grad_norm": 0.7364769852060075, "learning_rate": 2.7147437826697153e-07, "loss": 0.2973869800567627, "num_input_tokens_seen": 1094427056, "step": 26575, "train_runtime": 102396.7695, "train_tokens_per_second": 10688.101 }, { "epoch": 1.7896579585241046, "grad_norm": 0.8085468756454278, "learning_rate": 2.706156443561481e-07, "loss": 0.29561505317687986, "num_input_tokens_seen": 1094641992, "step": 26580, "train_runtime": 102415.8608, "train_tokens_per_second": 10688.208 }, { "epoch": 1.7899946135200646, "grad_norm": 0.6546425526405426, "learning_rate": 2.6975823300257884e-07, "loss": 0.2959133625030518, "num_input_tokens_seen": 1094842232, "step": 26585, "train_runtime": 102434.4462, "train_tokens_per_second": 10688.223 }, { "epoch": 1.7903312685160246, "grad_norm": 0.6569238463142484, "learning_rate": 2.6890214444603604e-07, "loss": 0.2955836534500122, "num_input_tokens_seen": 1095048792, "step": 26590, "train_runtime": 102452.6409, "train_tokens_per_second": 10688.341 }, { "epoch": 1.790667923511985, "grad_norm": 0.7568429304375658, "learning_rate": 2.6804737892592193e-07, "loss": 0.30517730712890623, "num_input_tokens_seen": 1095253232, "step": 26595, "train_runtime": 102472.1719, "train_tokens_per_second": 10688.299 }, { "epoch": 1.7910045785079451, "grad_norm": 0.7966048587528766, "learning_rate": 2.671939366812687e-07, "loss": 0.30507621765136717, "num_input_tokens_seen": 1095456000, "step": 26600, "train_runtime": 102491.2974, "train_tokens_per_second": 10688.283 }, { "epoch": 1.7913412335039052, "grad_norm": 0.7448687276437849, "learning_rate": 2.66341817950741e-07, "loss": 0.2939338445663452, "num_input_tokens_seen": 1095675376, "step": 26605, "train_runtime": 102509.5938, "train_tokens_per_second": 10688.515 }, { "epoch": 1.7916778884998652, "grad_norm": 0.6717127256176626, "learning_rate": 2.6549102297262764e-07, "loss": 0.2944059371948242, "num_input_tokens_seen": 1095883200, "step": 26610, "train_runtime": 102528.2446, "train_tokens_per_second": 10688.598 }, { "epoch": 1.7920145434958255, "grad_norm": 0.8139260668654039, "learning_rate": 2.6464155198485387e-07, "loss": 0.30252699851989745, "num_input_tokens_seen": 1096095744, "step": 26615, "train_runtime": 102547.8258, "train_tokens_per_second": 10688.63 }, { "epoch": 1.7923511984917857, "grad_norm": 0.7234223500662211, "learning_rate": 2.6379340522496853e-07, "loss": 0.2969655513763428, "num_input_tokens_seen": 1096303296, "step": 26620, "train_runtime": 102565.5709, "train_tokens_per_second": 10688.804 }, { "epoch": 1.7926878534877457, "grad_norm": 0.7269639851042966, "learning_rate": 2.6294658293015584e-07, "loss": 0.3189507484436035, "num_input_tokens_seen": 1096515504, "step": 26625, "train_runtime": 102583.7069, "train_tokens_per_second": 10688.983 }, { "epoch": 1.7930245084837058, "grad_norm": 0.8023055735396042, "learning_rate": 2.621010853372258e-07, "loss": 0.3155696868896484, "num_input_tokens_seen": 1096713096, "step": 26630, "train_runtime": 102603.2313, "train_tokens_per_second": 10688.875 }, { "epoch": 1.793361163479666, "grad_norm": 0.8419274336791471, "learning_rate": 2.612569126826187e-07, "loss": 0.33434228897094725, "num_input_tokens_seen": 1096918376, "step": 26635, "train_runtime": 102622.9025, "train_tokens_per_second": 10688.826 }, { "epoch": 1.7936978184756263, "grad_norm": 0.7031355299239025, "learning_rate": 2.6041406520240563e-07, "loss": 0.31784443855285643, "num_input_tokens_seen": 1097134608, "step": 26640, "train_runtime": 102640.4107, "train_tokens_per_second": 10689.11 }, { "epoch": 1.7940344734715863, "grad_norm": 0.8942707386493461, "learning_rate": 2.5957254313228595e-07, "loss": 0.30931117534637453, "num_input_tokens_seen": 1097335000, "step": 26645, "train_runtime": 102659.3717, "train_tokens_per_second": 10689.087 }, { "epoch": 1.7943711284675463, "grad_norm": 0.6521501025352031, "learning_rate": 2.5873234670758753e-07, "loss": 0.2736152172088623, "num_input_tokens_seen": 1097550304, "step": 26650, "train_runtime": 102679.4856, "train_tokens_per_second": 10689.09 }, { "epoch": 1.7947077834635066, "grad_norm": 0.7076968473105114, "learning_rate": 2.578934761632712e-07, "loss": 0.2891359329223633, "num_input_tokens_seen": 1097765104, "step": 26655, "train_runtime": 102697.6491, "train_tokens_per_second": 10689.291 }, { "epoch": 1.7950444384594668, "grad_norm": 0.7741383205975592, "learning_rate": 2.570559317339211e-07, "loss": 0.3071547508239746, "num_input_tokens_seen": 1097976272, "step": 26660, "train_runtime": 102716.1557, "train_tokens_per_second": 10689.421 }, { "epoch": 1.7953810934554268, "grad_norm": 0.6894321911182114, "learning_rate": 2.56219713653757e-07, "loss": 0.29558706283569336, "num_input_tokens_seen": 1098190640, "step": 26665, "train_runtime": 102735.1838, "train_tokens_per_second": 10689.528 }, { "epoch": 1.7957177484513869, "grad_norm": 0.7968559650280025, "learning_rate": 2.5538482215662187e-07, "loss": 0.32386507987976076, "num_input_tokens_seen": 1098393336, "step": 26670, "train_runtime": 102753.9652, "train_tokens_per_second": 10689.547 }, { "epoch": 1.7960544034473471, "grad_norm": 0.7182306354231426, "learning_rate": 2.545512574759923e-07, "loss": 0.2742929458618164, "num_input_tokens_seen": 1098600304, "step": 26675, "train_runtime": 102774.3543, "train_tokens_per_second": 10689.44 }, { "epoch": 1.7963910584433074, "grad_norm": 0.7078506159048868, "learning_rate": 2.537190198449713e-07, "loss": 0.30375142097473146, "num_input_tokens_seen": 1098802968, "step": 26680, "train_runtime": 102791.6991, "train_tokens_per_second": 10689.608 }, { "epoch": 1.7967277134392674, "grad_norm": 0.7194064734594785, "learning_rate": 2.5288810949629207e-07, "loss": 0.30069496631622317, "num_input_tokens_seen": 1099015216, "step": 26685, "train_runtime": 102811.8715, "train_tokens_per_second": 10689.575 }, { "epoch": 1.7970643684352274, "grad_norm": 0.8478879935926261, "learning_rate": 2.5205852666231544e-07, "loss": 0.2812362194061279, "num_input_tokens_seen": 1099216680, "step": 26690, "train_runtime": 102832.2264, "train_tokens_per_second": 10689.418 }, { "epoch": 1.7974010234311877, "grad_norm": 1.2394384455458458, "learning_rate": 2.5123027157503144e-07, "loss": 0.28280200958251955, "num_input_tokens_seen": 1099408120, "step": 26695, "train_runtime": 102852.063, "train_tokens_per_second": 10689.218 }, { "epoch": 1.797737678427148, "grad_norm": 0.7011461720274915, "learning_rate": 2.504033444660592e-07, "loss": 0.3060636043548584, "num_input_tokens_seen": 1099626672, "step": 26700, "train_runtime": 102870.4489, "train_tokens_per_second": 10689.432 }, { "epoch": 1.798074333423108, "grad_norm": 0.6658226042381729, "learning_rate": 2.4957774556664706e-07, "loss": 0.28348593711853026, "num_input_tokens_seen": 1099840232, "step": 26705, "train_runtime": 102891.5688, "train_tokens_per_second": 10689.313 }, { "epoch": 1.798410988419068, "grad_norm": 0.7946212248133687, "learning_rate": 2.487534751076692e-07, "loss": 0.292840576171875, "num_input_tokens_seen": 1100050304, "step": 26710, "train_runtime": 102911.3299, "train_tokens_per_second": 10689.302 }, { "epoch": 1.7987476434150282, "grad_norm": 0.7369075128274942, "learning_rate": 2.47930533319633e-07, "loss": 0.27648773193359377, "num_input_tokens_seen": 1100250784, "step": 26715, "train_runtime": 102931.7136, "train_tokens_per_second": 10689.133 }, { "epoch": 1.7990842984109885, "grad_norm": 0.8459867513897759, "learning_rate": 2.4710892043266823e-07, "loss": 0.3248885631561279, "num_input_tokens_seen": 1100460120, "step": 26720, "train_runtime": 102950.7671, "train_tokens_per_second": 10689.188 }, { "epoch": 1.7994209534069485, "grad_norm": 0.7622342526106198, "learning_rate": 2.462886366765388e-07, "loss": 0.2911403656005859, "num_input_tokens_seen": 1100671176, "step": 26725, "train_runtime": 102971.9427, "train_tokens_per_second": 10689.04 }, { "epoch": 1.7997576084029085, "grad_norm": 0.7865232687307789, "learning_rate": 2.454696822806341e-07, "loss": 0.30704007148742674, "num_input_tokens_seen": 1100871832, "step": 26730, "train_runtime": 102992.2651, "train_tokens_per_second": 10688.879 }, { "epoch": 1.8000942633988688, "grad_norm": 0.6779600499672743, "learning_rate": 2.446520574739708e-07, "loss": 0.28501071929931643, "num_input_tokens_seen": 1101082184, "step": 26735, "train_runtime": 103010.8811, "train_tokens_per_second": 10688.989 }, { "epoch": 1.800430918394829, "grad_norm": 0.7834236611555184, "learning_rate": 2.438357624851967e-07, "loss": 0.26830480098724363, "num_input_tokens_seen": 1101286736, "step": 26740, "train_runtime": 103029.4592, "train_tokens_per_second": 10689.047 }, { "epoch": 1.800767573390789, "grad_norm": 0.7043273806681419, "learning_rate": 2.430207975425847e-07, "loss": 0.30883421897888186, "num_input_tokens_seen": 1101499848, "step": 26745, "train_runtime": 103048.4567, "train_tokens_per_second": 10689.145 }, { "epoch": 1.801104228386749, "grad_norm": 0.7495691142865747, "learning_rate": 2.4220716287403744e-07, "loss": 0.304278302192688, "num_input_tokens_seen": 1101718264, "step": 26750, "train_runtime": 103068.4782, "train_tokens_per_second": 10689.187 }, { "epoch": 1.8014408833827094, "grad_norm": 0.6744800210929874, "learning_rate": 2.413948587070869e-07, "loss": 0.29744279384613037, "num_input_tokens_seen": 1101895896, "step": 26755, "train_runtime": 103089.0531, "train_tokens_per_second": 10688.777 }, { "epoch": 1.8017775383786696, "grad_norm": 0.7402851035258066, "learning_rate": 2.405838852688891e-07, "loss": 0.31288044452667235, "num_input_tokens_seen": 1102106608, "step": 26760, "train_runtime": 103107.4248, "train_tokens_per_second": 10688.916 }, { "epoch": 1.8021141933746296, "grad_norm": 0.7942742914823767, "learning_rate": 2.397742427862315e-07, "loss": 0.26749267578125, "num_input_tokens_seen": 1102319392, "step": 26765, "train_runtime": 103126.5639, "train_tokens_per_second": 10688.996 }, { "epoch": 1.8024508483705897, "grad_norm": 0.7834445709704059, "learning_rate": 2.3896593148552695e-07, "loss": 0.3059642791748047, "num_input_tokens_seen": 1102518792, "step": 26770, "train_runtime": 103144.8843, "train_tokens_per_second": 10689.03 }, { "epoch": 1.80278750336655, "grad_norm": 0.7830823583051424, "learning_rate": 2.3815895159281844e-07, "loss": 0.2822261333465576, "num_input_tokens_seen": 1102730288, "step": 26775, "train_runtime": 103164.5494, "train_tokens_per_second": 10689.043 }, { "epoch": 1.8031241583625102, "grad_norm": 0.7506341092126219, "learning_rate": 2.3735330333377493e-07, "loss": 0.28550703525543214, "num_input_tokens_seen": 1102945200, "step": 26780, "train_runtime": 103184.601, "train_tokens_per_second": 10689.048 }, { "epoch": 1.8034608133584702, "grad_norm": 0.7389518345928956, "learning_rate": 2.3654898693369232e-07, "loss": 0.3008666276931763, "num_input_tokens_seen": 1103149248, "step": 26785, "train_runtime": 103204.8156, "train_tokens_per_second": 10688.932 }, { "epoch": 1.8037974683544302, "grad_norm": 0.7498834198147881, "learning_rate": 2.3574600261749735e-07, "loss": 0.3007487773895264, "num_input_tokens_seen": 1103356704, "step": 26790, "train_runtime": 103223.2073, "train_tokens_per_second": 10689.037 }, { "epoch": 1.8041341233503905, "grad_norm": 0.7748083223676302, "learning_rate": 2.3494435060973875e-07, "loss": 0.32119121551513674, "num_input_tokens_seen": 1103566136, "step": 26795, "train_runtime": 103242.1572, "train_tokens_per_second": 10689.104 }, { "epoch": 1.8044707783463507, "grad_norm": 0.86639808338955, "learning_rate": 2.3414403113459937e-07, "loss": 0.30560100078582764, "num_input_tokens_seen": 1103770344, "step": 26800, "train_runtime": 103260.4675, "train_tokens_per_second": 10689.186 }, { "epoch": 1.8048074333423108, "grad_norm": 0.7138949759353281, "learning_rate": 2.3334504441588413e-07, "loss": 0.28151330947875974, "num_input_tokens_seen": 1103977880, "step": 26805, "train_runtime": 103280.0198, "train_tokens_per_second": 10689.172 }, { "epoch": 1.8051440883382708, "grad_norm": 0.7271285275478993, "learning_rate": 2.3254739067702704e-07, "loss": 0.28261642456054686, "num_input_tokens_seen": 1104188984, "step": 26810, "train_runtime": 103298.6338, "train_tokens_per_second": 10689.289 }, { "epoch": 1.805480743334231, "grad_norm": 0.8232535681223057, "learning_rate": 2.3175107014109077e-07, "loss": 0.2814193248748779, "num_input_tokens_seen": 1104396224, "step": 26815, "train_runtime": 103317.5042, "train_tokens_per_second": 10689.343 }, { "epoch": 1.8058173983301913, "grad_norm": 0.7651344642442184, "learning_rate": 2.3095608303076223e-07, "loss": 0.309893536567688, "num_input_tokens_seen": 1104604752, "step": 26820, "train_runtime": 103336.3049, "train_tokens_per_second": 10689.416 }, { "epoch": 1.8061540533261513, "grad_norm": 0.7242987960533357, "learning_rate": 2.3016242956835798e-07, "loss": 0.32116923332214353, "num_input_tokens_seen": 1104817640, "step": 26825, "train_runtime": 103356.7223, "train_tokens_per_second": 10689.364 }, { "epoch": 1.8064907083221113, "grad_norm": 0.7112880077167701, "learning_rate": 2.2937010997581999e-07, "loss": 0.2834202766418457, "num_input_tokens_seen": 1105032776, "step": 26830, "train_runtime": 103376.1445, "train_tokens_per_second": 10689.437 }, { "epoch": 1.8068273633180716, "grad_norm": 0.8399178473916803, "learning_rate": 2.2857912447471818e-07, "loss": 0.2816702604293823, "num_input_tokens_seen": 1105227488, "step": 26835, "train_runtime": 103394.3327, "train_tokens_per_second": 10689.44 }, { "epoch": 1.8071640183140318, "grad_norm": 0.6868253335729015, "learning_rate": 2.2778947328625012e-07, "loss": 0.28576297760009767, "num_input_tokens_seen": 1105420880, "step": 26840, "train_runtime": 103413.8887, "train_tokens_per_second": 10689.288 }, { "epoch": 1.8075006733099919, "grad_norm": 0.8817671374540982, "learning_rate": 2.2700115663123745e-07, "loss": 0.3223025560379028, "num_input_tokens_seen": 1105623496, "step": 26845, "train_runtime": 103432.1622, "train_tokens_per_second": 10689.359 }, { "epoch": 1.807837328305952, "grad_norm": 0.7825337481136595, "learning_rate": 2.2621417473013164e-07, "loss": 0.2832350254058838, "num_input_tokens_seen": 1105831880, "step": 26850, "train_runtime": 103451.7557, "train_tokens_per_second": 10689.349 }, { "epoch": 1.8081739833019121, "grad_norm": 0.8163772769785407, "learning_rate": 2.254285278030094e-07, "loss": 0.2997663736343384, "num_input_tokens_seen": 1106044200, "step": 26855, "train_runtime": 103469.175, "train_tokens_per_second": 10689.601 }, { "epoch": 1.8085106382978724, "grad_norm": 0.7687411732047462, "learning_rate": 2.24644216069575e-07, "loss": 0.2973028182983398, "num_input_tokens_seen": 1106241528, "step": 26860, "train_runtime": 103488.5826, "train_tokens_per_second": 10689.503 }, { "epoch": 1.8088472932938324, "grad_norm": 0.6451875765858542, "learning_rate": 2.238612397491574e-07, "loss": 0.27717430591583253, "num_input_tokens_seen": 1106453472, "step": 26865, "train_runtime": 103507.5091, "train_tokens_per_second": 10689.596 }, { "epoch": 1.8091839482897925, "grad_norm": 0.7534845455672963, "learning_rate": 2.230795990607143e-07, "loss": 0.2971823692321777, "num_input_tokens_seen": 1106666432, "step": 26870, "train_runtime": 103526.6195, "train_tokens_per_second": 10689.68 }, { "epoch": 1.809520603285753, "grad_norm": 0.7416703093659183, "learning_rate": 2.2229929422282915e-07, "loss": 0.27936525344848634, "num_input_tokens_seen": 1106867784, "step": 26875, "train_runtime": 103545.8768, "train_tokens_per_second": 10689.637 }, { "epoch": 1.809857258281713, "grad_norm": 0.7687069712877882, "learning_rate": 2.215203254537107e-07, "loss": 0.3160111665725708, "num_input_tokens_seen": 1107075648, "step": 26880, "train_runtime": 103564.6089, "train_tokens_per_second": 10689.71 }, { "epoch": 1.810193913277673, "grad_norm": 0.7017927477690655, "learning_rate": 2.2074269297119588e-07, "loss": 0.30351808071136477, "num_input_tokens_seen": 1107285936, "step": 26885, "train_runtime": 103582.9378, "train_tokens_per_second": 10689.849 }, { "epoch": 1.8105305682736332, "grad_norm": 0.7645916333783164, "learning_rate": 2.199663969927479e-07, "loss": 0.2888953685760498, "num_input_tokens_seen": 1107490808, "step": 26890, "train_runtime": 103604.1849, "train_tokens_per_second": 10689.634 }, { "epoch": 1.8108672232695935, "grad_norm": 0.7465704114703234, "learning_rate": 2.1919143773545316e-07, "loss": 0.2929201602935791, "num_input_tokens_seen": 1107700112, "step": 26895, "train_runtime": 103622.8905, "train_tokens_per_second": 10689.724 }, { "epoch": 1.8112038782655535, "grad_norm": 0.86007974092211, "learning_rate": 2.184178154160288e-07, "loss": 0.2973903179168701, "num_input_tokens_seen": 1107903208, "step": 26900, "train_runtime": 103642.2841, "train_tokens_per_second": 10689.683 }, { "epoch": 1.8115405332615135, "grad_norm": 0.7200962036785536, "learning_rate": 2.1764553025081514e-07, "loss": 0.2992074489593506, "num_input_tokens_seen": 1108110688, "step": 26905, "train_runtime": 103660.6478, "train_tokens_per_second": 10689.791 }, { "epoch": 1.8118771882574738, "grad_norm": 0.8092906770062114, "learning_rate": 2.168745824557794e-07, "loss": 0.28490047454833983, "num_input_tokens_seen": 1108313576, "step": 26910, "train_runtime": 103680.1644, "train_tokens_per_second": 10689.736 }, { "epoch": 1.812213843253434, "grad_norm": 0.7453937066052376, "learning_rate": 2.161049722465136e-07, "loss": 0.28475112915039064, "num_input_tokens_seen": 1108518992, "step": 26915, "train_runtime": 103700.1112, "train_tokens_per_second": 10689.661 }, { "epoch": 1.812550498249394, "grad_norm": 0.7352926488740564, "learning_rate": 2.1533669983823835e-07, "loss": 0.29768967628479004, "num_input_tokens_seen": 1108737400, "step": 26920, "train_runtime": 103719.5885, "train_tokens_per_second": 10689.759 }, { "epoch": 1.812887153245354, "grad_norm": 0.6023322539951692, "learning_rate": 2.1456976544579732e-07, "loss": 0.27208378314971926, "num_input_tokens_seen": 1108959848, "step": 26925, "train_runtime": 103737.2524, "train_tokens_per_second": 10690.083 }, { "epoch": 1.8132238082413143, "grad_norm": 0.7142817563471463, "learning_rate": 2.138041692836623e-07, "loss": 0.2937882423400879, "num_input_tokens_seen": 1109163256, "step": 26930, "train_runtime": 103755.4824, "train_tokens_per_second": 10690.165 }, { "epoch": 1.8135604632372746, "grad_norm": 0.9596881002311041, "learning_rate": 2.1303991156592818e-07, "loss": 0.29552602767944336, "num_input_tokens_seen": 1109363120, "step": 26935, "train_runtime": 103775.6388, "train_tokens_per_second": 10690.015 }, { "epoch": 1.8138971182332346, "grad_norm": 0.7272135763279263, "learning_rate": 2.122769925063195e-07, "loss": 0.28259997367858886, "num_input_tokens_seen": 1109565840, "step": 26940, "train_runtime": 103796.2496, "train_tokens_per_second": 10689.845 }, { "epoch": 1.8142337732291947, "grad_norm": 0.8376901435874169, "learning_rate": 2.1151541231818174e-07, "loss": 0.28657677173614504, "num_input_tokens_seen": 1109769600, "step": 26945, "train_runtime": 103814.2629, "train_tokens_per_second": 10689.953 }, { "epoch": 1.814570428225155, "grad_norm": 0.7659997656394725, "learning_rate": 2.1075517121449063e-07, "loss": 0.31893210411071776, "num_input_tokens_seen": 1109978288, "step": 26950, "train_runtime": 103834.7793, "train_tokens_per_second": 10689.851 }, { "epoch": 1.8149070832211152, "grad_norm": 0.7790877330762676, "learning_rate": 2.0999626940784334e-07, "loss": 0.26987228393554685, "num_input_tokens_seen": 1110174472, "step": 26955, "train_runtime": 103854.0947, "train_tokens_per_second": 10689.752 }, { "epoch": 1.8152437382170752, "grad_norm": 0.8357136077075454, "learning_rate": 2.0923870711046568e-07, "loss": 0.2998065710067749, "num_input_tokens_seen": 1110385008, "step": 26960, "train_runtime": 103873.2182, "train_tokens_per_second": 10689.81 }, { "epoch": 1.8155803932130352, "grad_norm": 0.6603571334137389, "learning_rate": 2.0848248453420704e-07, "loss": 0.2860421180725098, "num_input_tokens_seen": 1110596008, "step": 26965, "train_runtime": 103891.9302, "train_tokens_per_second": 10689.916 }, { "epoch": 1.8159170482089955, "grad_norm": 0.7975399818907373, "learning_rate": 2.077276018905422e-07, "loss": 0.29471259117126464, "num_input_tokens_seen": 1110802560, "step": 26970, "train_runtime": 103911.4311, "train_tokens_per_second": 10689.898 }, { "epoch": 1.8162537032049557, "grad_norm": 0.7272071431149582, "learning_rate": 2.0697405939057225e-07, "loss": 0.30031094551086424, "num_input_tokens_seen": 1110989136, "step": 26975, "train_runtime": 103929.956, "train_tokens_per_second": 10689.787 }, { "epoch": 1.8165903582009157, "grad_norm": 0.6329684886521951, "learning_rate": 2.0622185724502253e-07, "loss": 0.28473949432373047, "num_input_tokens_seen": 1111193488, "step": 26980, "train_runtime": 103947.7894, "train_tokens_per_second": 10689.919 }, { "epoch": 1.8169270131968758, "grad_norm": 0.7711683025099798, "learning_rate": 2.0547099566424367e-07, "loss": 0.2795230865478516, "num_input_tokens_seen": 1111399432, "step": 26985, "train_runtime": 103967.6324, "train_tokens_per_second": 10689.86 }, { "epoch": 1.817263668192836, "grad_norm": 0.7769623595747038, "learning_rate": 2.0472147485821325e-07, "loss": 0.2777698040008545, "num_input_tokens_seen": 1111594112, "step": 26990, "train_runtime": 103986.2405, "train_tokens_per_second": 10689.819 }, { "epoch": 1.8176003231887963, "grad_norm": 0.6749923960723903, "learning_rate": 2.0397329503653084e-07, "loss": 0.2829620838165283, "num_input_tokens_seen": 1111796872, "step": 26995, "train_runtime": 104005.1472, "train_tokens_per_second": 10689.825 }, { "epoch": 1.8179369781847563, "grad_norm": 0.7852517405989367, "learning_rate": 2.03226456408423e-07, "loss": 0.3106169939041138, "num_input_tokens_seen": 1111987032, "step": 27000, "train_runtime": 104024.0877, "train_tokens_per_second": 10689.707 }, { "epoch": 1.8182736331807163, "grad_norm": 0.6896377478557543, "learning_rate": 2.024809591827409e-07, "loss": 0.30623302459716795, "num_input_tokens_seen": 1112199872, "step": 27005, "train_runtime": 104044.4121, "train_tokens_per_second": 10689.665 }, { "epoch": 1.8186102881766766, "grad_norm": 0.7812353609411657, "learning_rate": 2.0173680356796066e-07, "loss": 0.27093052864074707, "num_input_tokens_seen": 1112391104, "step": 27010, "train_runtime": 104063.2066, "train_tokens_per_second": 10689.572 }, { "epoch": 1.8189469431726368, "grad_norm": 0.7496198660264293, "learning_rate": 2.00993989772183e-07, "loss": 0.295663046836853, "num_input_tokens_seen": 1112595328, "step": 27015, "train_runtime": 104081.476, "train_tokens_per_second": 10689.657 }, { "epoch": 1.8192835981685969, "grad_norm": 0.7555485450166863, "learning_rate": 2.0025251800313284e-07, "loss": 0.31569738388061525, "num_input_tokens_seen": 1112797720, "step": 27020, "train_runtime": 104101.2096, "train_tokens_per_second": 10689.575 }, { "epoch": 1.8196202531645569, "grad_norm": 0.7251772631198885, "learning_rate": 1.9951238846816045e-07, "loss": 0.3169147253036499, "num_input_tokens_seen": 1113013232, "step": 27025, "train_runtime": 104119.5786, "train_tokens_per_second": 10689.759 }, { "epoch": 1.8199569081605171, "grad_norm": 0.7543124992973189, "learning_rate": 1.987736013742414e-07, "loss": 0.31148841381073, "num_input_tokens_seen": 1113212704, "step": 27030, "train_runtime": 104138.5671, "train_tokens_per_second": 10689.726 }, { "epoch": 1.8202935631564774, "grad_norm": 0.7185313504758841, "learning_rate": 1.9803615692797375e-07, "loss": 0.2723869562149048, "num_input_tokens_seen": 1113420144, "step": 27035, "train_runtime": 104157.1823, "train_tokens_per_second": 10689.807 }, { "epoch": 1.8206302181524374, "grad_norm": 0.713689591541908, "learning_rate": 1.9730005533558417e-07, "loss": 0.2902393341064453, "num_input_tokens_seen": 1113636792, "step": 27040, "train_runtime": 104176.6133, "train_tokens_per_second": 10689.892 }, { "epoch": 1.8209668731483974, "grad_norm": 0.6866674722152495, "learning_rate": 1.9656529680291802e-07, "loss": 0.27458891868591306, "num_input_tokens_seen": 1113845680, "step": 27045, "train_runtime": 104194.8524, "train_tokens_per_second": 10690.026 }, { "epoch": 1.8213035281443577, "grad_norm": 0.7138689208410575, "learning_rate": 1.9583188153544986e-07, "loss": 0.2881120443344116, "num_input_tokens_seen": 1114038208, "step": 27050, "train_runtime": 104214.1595, "train_tokens_per_second": 10689.893 }, { "epoch": 1.821640183140318, "grad_norm": 0.7220430570984847, "learning_rate": 1.9509980973827724e-07, "loss": 0.2964170455932617, "num_input_tokens_seen": 1114244808, "step": 27055, "train_runtime": 104232.8152, "train_tokens_per_second": 10689.962 }, { "epoch": 1.821976838136278, "grad_norm": 0.7480913482193567, "learning_rate": 1.943690816161209e-07, "loss": 0.30737080574035647, "num_input_tokens_seen": 1114459256, "step": 27060, "train_runtime": 104251.29, "train_tokens_per_second": 10690.124 }, { "epoch": 1.822313493132238, "grad_norm": 0.7114840727510361, "learning_rate": 1.9363969737332677e-07, "loss": 0.2718838691711426, "num_input_tokens_seen": 1114666680, "step": 27065, "train_runtime": 104269.2492, "train_tokens_per_second": 10690.272 }, { "epoch": 1.8226501481281983, "grad_norm": 0.6098302402683169, "learning_rate": 1.9291165721386507e-07, "loss": 0.27412340641021726, "num_input_tokens_seen": 1114863552, "step": 27070, "train_runtime": 104288.384, "train_tokens_per_second": 10690.199 }, { "epoch": 1.8229868031241585, "grad_norm": 0.7993078399246906, "learning_rate": 1.9218496134132957e-07, "loss": 0.30428617000579833, "num_input_tokens_seen": 1115074752, "step": 27075, "train_runtime": 104306.8364, "train_tokens_per_second": 10690.332 }, { "epoch": 1.8233234581201185, "grad_norm": 0.6592112232659108, "learning_rate": 1.9145960995893831e-07, "loss": 0.28048479557037354, "num_input_tokens_seen": 1115279032, "step": 27080, "train_runtime": 104326.3541, "train_tokens_per_second": 10690.291 }, { "epoch": 1.8236601131160786, "grad_norm": 0.6889312999077082, "learning_rate": 1.9073560326953344e-07, "loss": 0.2970155715942383, "num_input_tokens_seen": 1115489152, "step": 27085, "train_runtime": 104345.4787, "train_tokens_per_second": 10690.345 }, { "epoch": 1.8239967681120388, "grad_norm": 0.7146696378019204, "learning_rate": 1.9001294147558303e-07, "loss": 0.30985660552978517, "num_input_tokens_seen": 1115691256, "step": 27090, "train_runtime": 104365.3076, "train_tokens_per_second": 10690.25 }, { "epoch": 1.824333423107999, "grad_norm": 0.8210136470542105, "learning_rate": 1.892916247791743e-07, "loss": 0.30728797912597655, "num_input_tokens_seen": 1115889984, "step": 27095, "train_runtime": 104384.6292, "train_tokens_per_second": 10690.175 }, { "epoch": 1.824670078103959, "grad_norm": 0.7235457454042981, "learning_rate": 1.885716533820231e-07, "loss": 0.2980057716369629, "num_input_tokens_seen": 1116098728, "step": 27100, "train_runtime": 104405.2466, "train_tokens_per_second": 10690.064 }, { "epoch": 1.8250067330999191, "grad_norm": 0.699897584985559, "learning_rate": 1.878530274854662e-07, "loss": 0.29379231929779054, "num_input_tokens_seen": 1116303080, "step": 27105, "train_runtime": 104423.1262, "train_tokens_per_second": 10690.19 }, { "epoch": 1.8253433880958794, "grad_norm": 0.7506516973400652, "learning_rate": 1.8713574729046557e-07, "loss": 0.30999438762664794, "num_input_tokens_seen": 1116516016, "step": 27110, "train_runtime": 104441.7015, "train_tokens_per_second": 10690.328 }, { "epoch": 1.8256800430918396, "grad_norm": 0.7241298962131592, "learning_rate": 1.8641981299760582e-07, "loss": 0.29220678806304934, "num_input_tokens_seen": 1116712288, "step": 27115, "train_runtime": 104460.288, "train_tokens_per_second": 10690.305 }, { "epoch": 1.8260166980877997, "grad_norm": 0.7122711943652575, "learning_rate": 1.857052248070962e-07, "loss": 0.3033742904663086, "num_input_tokens_seen": 1116912704, "step": 27120, "train_runtime": 104478.7527, "train_tokens_per_second": 10690.333 }, { "epoch": 1.8263533530837597, "grad_norm": 0.785348736364034, "learning_rate": 1.8499198291876907e-07, "loss": 0.28459935188293456, "num_input_tokens_seen": 1117107576, "step": 27125, "train_runtime": 104498.5918, "train_tokens_per_second": 10690.169 }, { "epoch": 1.82669000807972, "grad_norm": 0.6223957519082953, "learning_rate": 1.8428008753207937e-07, "loss": 0.30476179122924807, "num_input_tokens_seen": 1117319376, "step": 27130, "train_runtime": 104520.4868, "train_tokens_per_second": 10689.956 }, { "epoch": 1.8270266630756802, "grad_norm": 0.719102358245903, "learning_rate": 1.8356953884610673e-07, "loss": 0.30538430213928225, "num_input_tokens_seen": 1117530456, "step": 27135, "train_runtime": 104540.9403, "train_tokens_per_second": 10689.883 }, { "epoch": 1.8273633180716402, "grad_norm": 0.7766423464816451, "learning_rate": 1.8286033705955554e-07, "loss": 0.29223856925964353, "num_input_tokens_seen": 1117742160, "step": 27140, "train_runtime": 104558.9159, "train_tokens_per_second": 10690.07 }, { "epoch": 1.8276999730676002, "grad_norm": 0.7685368005147248, "learning_rate": 1.8215248237074879e-07, "loss": 0.2964195728302002, "num_input_tokens_seen": 1117951736, "step": 27145, "train_runtime": 104578.2971, "train_tokens_per_second": 10690.093 }, { "epoch": 1.8280366280635605, "grad_norm": 0.59228307003116, "learning_rate": 1.8144597497763816e-07, "loss": 0.29413015842437745, "num_input_tokens_seen": 1118151440, "step": 27150, "train_runtime": 104596.9839, "train_tokens_per_second": 10690.093 }, { "epoch": 1.8283732830595207, "grad_norm": 0.7181291159457811, "learning_rate": 1.8074081507779506e-07, "loss": 0.28676633834838866, "num_input_tokens_seen": 1118366616, "step": 27155, "train_runtime": 104617.1919, "train_tokens_per_second": 10690.084 }, { "epoch": 1.8287099380554808, "grad_norm": 0.7456678527785215, "learning_rate": 1.8003700286841563e-07, "loss": 0.3031982183456421, "num_input_tokens_seen": 1118575528, "step": 27160, "train_runtime": 104636.6143, "train_tokens_per_second": 10690.097 }, { "epoch": 1.8290465930514408, "grad_norm": 0.7684119794096177, "learning_rate": 1.793345385463191e-07, "loss": 0.29713101387023927, "num_input_tokens_seen": 1118783472, "step": 27165, "train_runtime": 104655.489, "train_tokens_per_second": 10690.156 }, { "epoch": 1.829383248047401, "grad_norm": 0.7719967151397662, "learning_rate": 1.7863342230794667e-07, "loss": 0.3093894958496094, "num_input_tokens_seen": 1118988168, "step": 27170, "train_runtime": 104673.3236, "train_tokens_per_second": 10690.29 }, { "epoch": 1.8297199030433613, "grad_norm": 0.6726109923070024, "learning_rate": 1.7793365434936316e-07, "loss": 0.2995491027832031, "num_input_tokens_seen": 1119204824, "step": 27175, "train_runtime": 104693.0509, "train_tokens_per_second": 10690.345 }, { "epoch": 1.8300565580393213, "grad_norm": 0.7970940246069605, "learning_rate": 1.7723523486625704e-07, "loss": 0.30028274059295657, "num_input_tokens_seen": 1119404688, "step": 27180, "train_runtime": 104711.6817, "train_tokens_per_second": 10690.352 }, { "epoch": 1.8303932130352814, "grad_norm": 0.8746989114146809, "learning_rate": 1.7653816405393766e-07, "loss": 0.307506799697876, "num_input_tokens_seen": 1119608720, "step": 27185, "train_runtime": 104730.3211, "train_tokens_per_second": 10690.397 }, { "epoch": 1.8307298680312416, "grad_norm": 0.827864590937718, "learning_rate": 1.758424421073418e-07, "loss": 0.3147634267807007, "num_input_tokens_seen": 1119822504, "step": 27190, "train_runtime": 104749.1665, "train_tokens_per_second": 10690.515 }, { "epoch": 1.8310665230272019, "grad_norm": 0.6892421417305917, "learning_rate": 1.7514806922102222e-07, "loss": 0.27822375297546387, "num_input_tokens_seen": 1120011928, "step": 27195, "train_runtime": 104768.8347, "train_tokens_per_second": 10690.316 }, { "epoch": 1.8314031780231619, "grad_norm": 0.7835701939504249, "learning_rate": 1.7445504558916027e-07, "loss": 0.29053435325622556, "num_input_tokens_seen": 1120212432, "step": 27200, "train_runtime": 104786.3615, "train_tokens_per_second": 10690.441 }, { "epoch": 1.831739833019122, "grad_norm": 0.7458441493675976, "learning_rate": 1.7376337140555754e-07, "loss": 0.28238592147827146, "num_input_tokens_seen": 1120410928, "step": 27205, "train_runtime": 104805.7976, "train_tokens_per_second": 10690.353 }, { "epoch": 1.8320764880150822, "grad_norm": 0.7068977931719661, "learning_rate": 1.7307304686363825e-07, "loss": 0.29882786273956297, "num_input_tokens_seen": 1120616992, "step": 27210, "train_runtime": 104824.368, "train_tokens_per_second": 10690.425 }, { "epoch": 1.8324131430110424, "grad_norm": 0.6608078223255337, "learning_rate": 1.723840721564496e-07, "loss": 0.28854424953460694, "num_input_tokens_seen": 1120833448, "step": 27215, "train_runtime": 104844.9745, "train_tokens_per_second": 10690.388 }, { "epoch": 1.8327497980070024, "grad_norm": 0.7584724052484239, "learning_rate": 1.7169644747666081e-07, "loss": 0.2889303207397461, "num_input_tokens_seen": 1121047920, "step": 27220, "train_runtime": 104863.4841, "train_tokens_per_second": 10690.546 }, { "epoch": 1.8330864530029625, "grad_norm": 0.6470006597908546, "learning_rate": 1.710101730165642e-07, "loss": 0.30394341945648196, "num_input_tokens_seen": 1121259360, "step": 27225, "train_runtime": 104881.5343, "train_tokens_per_second": 10690.722 }, { "epoch": 1.8334231079989227, "grad_norm": 0.7291358282389475, "learning_rate": 1.7032524896807402e-07, "loss": 0.28139314651489256, "num_input_tokens_seen": 1121456248, "step": 27230, "train_runtime": 104901.2272, "train_tokens_per_second": 10690.592 }, { "epoch": 1.833759762994883, "grad_norm": 0.7555647720911816, "learning_rate": 1.6964167552272702e-07, "loss": 0.30953078269958495, "num_input_tokens_seen": 1121652768, "step": 27235, "train_runtime": 104921.059, "train_tokens_per_second": 10690.445 }, { "epoch": 1.834096417990843, "grad_norm": 0.8919074536004523, "learning_rate": 1.6895945287168314e-07, "loss": 0.30438530445098877, "num_input_tokens_seen": 1121853360, "step": 27240, "train_runtime": 104940.5877, "train_tokens_per_second": 10690.367 }, { "epoch": 1.834433072986803, "grad_norm": 0.7997603423767842, "learning_rate": 1.682785812057225e-07, "loss": 0.31446018218994143, "num_input_tokens_seen": 1122042496, "step": 27245, "train_runtime": 104958.2068, "train_tokens_per_second": 10690.374 }, { "epoch": 1.8347697279827633, "grad_norm": 0.708508695893003, "learning_rate": 1.6759906071525e-07, "loss": 0.29027891159057617, "num_input_tokens_seen": 1122247952, "step": 27250, "train_runtime": 104976.7375, "train_tokens_per_second": 10690.444 }, { "epoch": 1.8351063829787235, "grad_norm": 0.7660050132048819, "learning_rate": 1.669208915902909e-07, "loss": 0.33294556140899656, "num_input_tokens_seen": 1122468568, "step": 27255, "train_runtime": 104994.9927, "train_tokens_per_second": 10690.687 }, { "epoch": 1.8354430379746836, "grad_norm": 0.8555340426114075, "learning_rate": 1.6624407402049237e-07, "loss": 0.2777735233306885, "num_input_tokens_seen": 1122669192, "step": 27260, "train_runtime": 105014.0192, "train_tokens_per_second": 10690.66 }, { "epoch": 1.8357796929706436, "grad_norm": 0.7588037907091271, "learning_rate": 1.655686081951252e-07, "loss": 0.2947369575500488, "num_input_tokens_seen": 1122871344, "step": 27265, "train_runtime": 105031.6345, "train_tokens_per_second": 10690.792 }, { "epoch": 1.8361163479666038, "grad_norm": 0.774921151697798, "learning_rate": 1.6489449430308058e-07, "loss": 0.3218813419342041, "num_input_tokens_seen": 1123084016, "step": 27270, "train_runtime": 105049.5972, "train_tokens_per_second": 10690.988 }, { "epoch": 1.836453002962564, "grad_norm": 0.6619080645520689, "learning_rate": 1.6422173253287323e-07, "loss": 0.3091400623321533, "num_input_tokens_seen": 1123298856, "step": 27275, "train_runtime": 105068.5681, "train_tokens_per_second": 10691.103 }, { "epoch": 1.8367896579585241, "grad_norm": 0.7840312507493151, "learning_rate": 1.6355032307263764e-07, "loss": 0.28950607776641846, "num_input_tokens_seen": 1123509520, "step": 27280, "train_runtime": 105087.425, "train_tokens_per_second": 10691.189 }, { "epoch": 1.8371263129544841, "grad_norm": 0.7121685926689448, "learning_rate": 1.628802661101314e-07, "loss": 0.276812219619751, "num_input_tokens_seen": 1123711432, "step": 27285, "train_runtime": 105105.0643, "train_tokens_per_second": 10691.316 }, { "epoch": 1.8374629679504444, "grad_norm": 0.6652615093511803, "learning_rate": 1.6221156183273524e-07, "loss": 0.288313102722168, "num_input_tokens_seen": 1123922280, "step": 27290, "train_runtime": 105124.0867, "train_tokens_per_second": 10691.387 }, { "epoch": 1.8377996229464046, "grad_norm": 0.803052674024658, "learning_rate": 1.615442104274484e-07, "loss": 0.2968291759490967, "num_input_tokens_seen": 1124137224, "step": 27295, "train_runtime": 105142.6511, "train_tokens_per_second": 10691.543 }, { "epoch": 1.8381362779423647, "grad_norm": 0.7549519830399387, "learning_rate": 1.6087821208089492e-07, "loss": 0.30027749538421633, "num_input_tokens_seen": 1124346184, "step": 27300, "train_runtime": 105161.2757, "train_tokens_per_second": 10691.637 }, { "epoch": 1.8384729329383247, "grad_norm": 0.6359608295612239, "learning_rate": 1.6021356697931866e-07, "loss": 0.27202601432800294, "num_input_tokens_seen": 1124557592, "step": 27305, "train_runtime": 105180.288, "train_tokens_per_second": 10691.714 }, { "epoch": 1.838809587934285, "grad_norm": 0.7417628915632365, "learning_rate": 1.5955027530858537e-07, "loss": 0.27588462829589844, "num_input_tokens_seen": 1124764480, "step": 27310, "train_runtime": 105198.8722, "train_tokens_per_second": 10691.792 }, { "epoch": 1.8391462429302452, "grad_norm": 0.6773251917160086, "learning_rate": 1.5888833725418275e-07, "loss": 0.27678892612457273, "num_input_tokens_seen": 1124970600, "step": 27315, "train_runtime": 105218.435, "train_tokens_per_second": 10691.763 }, { "epoch": 1.8394828979262052, "grad_norm": 0.6881246989009716, "learning_rate": 1.582277530012194e-07, "loss": 0.2645848751068115, "num_input_tokens_seen": 1125187936, "step": 27320, "train_runtime": 105237.5236, "train_tokens_per_second": 10691.889 }, { "epoch": 1.8398195529221653, "grad_norm": 0.786830432099348, "learning_rate": 1.5756852273442536e-07, "loss": 0.29075639247894286, "num_input_tokens_seen": 1125385080, "step": 27325, "train_runtime": 105257.4668, "train_tokens_per_second": 10691.736 }, { "epoch": 1.8401562079181255, "grad_norm": 0.6432001055205483, "learning_rate": 1.569106466381526e-07, "loss": 0.3117210865020752, "num_input_tokens_seen": 1125594440, "step": 27330, "train_runtime": 105276.5104, "train_tokens_per_second": 10691.791 }, { "epoch": 1.8404928629140858, "grad_norm": 0.7176950004524171, "learning_rate": 1.5625412489637337e-07, "loss": 0.2715280294418335, "num_input_tokens_seen": 1125808800, "step": 27335, "train_runtime": 105296.5028, "train_tokens_per_second": 10691.797 }, { "epoch": 1.8408295179100458, "grad_norm": 0.7089264064897278, "learning_rate": 1.555989576926842e-07, "loss": 0.28884453773498536, "num_input_tokens_seen": 1126023920, "step": 27340, "train_runtime": 105317.9922, "train_tokens_per_second": 10691.658 }, { "epoch": 1.8411661729060058, "grad_norm": 0.7719177331551723, "learning_rate": 1.5494514521029736e-07, "loss": 0.3004020690917969, "num_input_tokens_seen": 1126235064, "step": 27345, "train_runtime": 105338.9284, "train_tokens_per_second": 10691.537 }, { "epoch": 1.841502827901966, "grad_norm": 0.7295774149146382, "learning_rate": 1.5429268763205108e-07, "loss": 0.29961092472076417, "num_input_tokens_seen": 1126444544, "step": 27350, "train_runtime": 105358.6429, "train_tokens_per_second": 10691.525 }, { "epoch": 1.8418394828979263, "grad_norm": 0.8000584570523906, "learning_rate": 1.5364158514040328e-07, "loss": 0.3191661834716797, "num_input_tokens_seen": 1126649544, "step": 27355, "train_runtime": 105378.5815, "train_tokens_per_second": 10691.447 }, { "epoch": 1.8421761378938863, "grad_norm": 0.8883582500937617, "learning_rate": 1.5299183791743223e-07, "loss": 0.29807381629943847, "num_input_tokens_seen": 1126845208, "step": 27360, "train_runtime": 105396.3784, "train_tokens_per_second": 10691.498 }, { "epoch": 1.8425127928898464, "grad_norm": 0.7744733079216007, "learning_rate": 1.523434461448381e-07, "loss": 0.3196394681930542, "num_input_tokens_seen": 1127063432, "step": 27365, "train_runtime": 105416.0278, "train_tokens_per_second": 10691.576 }, { "epoch": 1.8428494478858066, "grad_norm": 0.6706246881001315, "learning_rate": 1.5169641000394086e-07, "loss": 0.2947872161865234, "num_input_tokens_seen": 1127281160, "step": 27370, "train_runtime": 105435.7196, "train_tokens_per_second": 10691.644 }, { "epoch": 1.8431861028817669, "grad_norm": 0.6930483163536874, "learning_rate": 1.5105072967568246e-07, "loss": 0.2891897678375244, "num_input_tokens_seen": 1127481904, "step": 27375, "train_runtime": 105455.8813, "train_tokens_per_second": 10691.503 }, { "epoch": 1.843522757877727, "grad_norm": 0.672173920887284, "learning_rate": 1.504064053406251e-07, "loss": 0.2986405372619629, "num_input_tokens_seen": 1127685560, "step": 27380, "train_runtime": 105475.2003, "train_tokens_per_second": 10691.476 }, { "epoch": 1.843859412873687, "grad_norm": 0.7242401954279157, "learning_rate": 1.4976343717895192e-07, "loss": 0.2974234104156494, "num_input_tokens_seen": 1127898824, "step": 27385, "train_runtime": 105493.3698, "train_tokens_per_second": 10691.656 }, { "epoch": 1.8441960678696472, "grad_norm": 0.7223128351507231, "learning_rate": 1.491218253704685e-07, "loss": 0.30426721572875975, "num_input_tokens_seen": 1128112720, "step": 27390, "train_runtime": 105513.3139, "train_tokens_per_second": 10691.662 }, { "epoch": 1.8445327228656074, "grad_norm": 0.6946558108235541, "learning_rate": 1.484815700945974e-07, "loss": 0.306914234161377, "num_input_tokens_seen": 1128317376, "step": 27395, "train_runtime": 105532.7903, "train_tokens_per_second": 10691.628 }, { "epoch": 1.8448693778615675, "grad_norm": 0.6918726084361917, "learning_rate": 1.478426715303849e-07, "loss": 0.2872256517410278, "num_input_tokens_seen": 1128512192, "step": 27400, "train_runtime": 105552.1165, "train_tokens_per_second": 10691.516 }, { "epoch": 1.8452060328575275, "grad_norm": 0.7164980269220157, "learning_rate": 1.4720512985649694e-07, "loss": 0.28620138168334963, "num_input_tokens_seen": 1128714304, "step": 27405, "train_runtime": 105572.8906, "train_tokens_per_second": 10691.327 }, { "epoch": 1.8455426878534877, "grad_norm": 0.9052879351214139, "learning_rate": 1.4656894525122034e-07, "loss": 0.29957807064056396, "num_input_tokens_seen": 1128908800, "step": 27410, "train_runtime": 105592.613, "train_tokens_per_second": 10691.172 }, { "epoch": 1.845879342849448, "grad_norm": 0.7886630655424627, "learning_rate": 1.459341178924617e-07, "loss": 0.31295368671417234, "num_input_tokens_seen": 1129117224, "step": 27415, "train_runtime": 105611.8881, "train_tokens_per_second": 10691.194 }, { "epoch": 1.846215997845408, "grad_norm": 0.7571717215750694, "learning_rate": 1.453006479577479e-07, "loss": 0.28766756057739257, "num_input_tokens_seen": 1129316344, "step": 27420, "train_runtime": 105631.4545, "train_tokens_per_second": 10691.099 }, { "epoch": 1.846552652841368, "grad_norm": 0.7202466458212097, "learning_rate": 1.4466853562422778e-07, "loss": 0.3094740390777588, "num_input_tokens_seen": 1129503320, "step": 27425, "train_runtime": 105650.1417, "train_tokens_per_second": 10690.978 }, { "epoch": 1.8468893078373283, "grad_norm": 0.8231309334714896, "learning_rate": 1.440377810686694e-07, "loss": 0.29578347206115724, "num_input_tokens_seen": 1129711648, "step": 27430, "train_runtime": 105668.6305, "train_tokens_per_second": 10691.079 }, { "epoch": 1.8472259628332885, "grad_norm": 0.7376029610192044, "learning_rate": 1.4340838446746052e-07, "loss": 0.29396135807037355, "num_input_tokens_seen": 1129922664, "step": 27435, "train_runtime": 105688.6359, "train_tokens_per_second": 10691.052 }, { "epoch": 1.8475626178292486, "grad_norm": 0.7075441706219315, "learning_rate": 1.4278034599661094e-07, "loss": 0.2747061252593994, "num_input_tokens_seen": 1130124480, "step": 27440, "train_runtime": 105705.9895, "train_tokens_per_second": 10691.206 }, { "epoch": 1.8478992728252086, "grad_norm": 0.7495474793431315, "learning_rate": 1.421536658317485e-07, "loss": 0.27053232192993165, "num_input_tokens_seen": 1130311032, "step": 27445, "train_runtime": 105725.063, "train_tokens_per_second": 10691.041 }, { "epoch": 1.8482359278211689, "grad_norm": 0.7516152896470855, "learning_rate": 1.41528344148123e-07, "loss": 0.2826594591140747, "num_input_tokens_seen": 1130530224, "step": 27450, "train_runtime": 105743.6851, "train_tokens_per_second": 10691.232 }, { "epoch": 1.848572582817129, "grad_norm": 0.8628199681107175, "learning_rate": 1.40904381120604e-07, "loss": 0.25522894859313966, "num_input_tokens_seen": 1130733592, "step": 27455, "train_runtime": 105761.8361, "train_tokens_per_second": 10691.32 }, { "epoch": 1.8489092378130891, "grad_norm": 0.7490532831943423, "learning_rate": 1.4028177692367973e-07, "loss": 0.29623005390167234, "num_input_tokens_seen": 1130931944, "step": 27460, "train_runtime": 105781.6613, "train_tokens_per_second": 10691.191 }, { "epoch": 1.8492458928090492, "grad_norm": 0.7788199861897461, "learning_rate": 1.3966053173146032e-07, "loss": 0.3009164333343506, "num_input_tokens_seen": 1131143232, "step": 27465, "train_runtime": 105800.4586, "train_tokens_per_second": 10691.289 }, { "epoch": 1.8495825478050094, "grad_norm": 0.6420426045870188, "learning_rate": 1.3904064571767462e-07, "loss": 0.29417667388916013, "num_input_tokens_seen": 1131360416, "step": 27470, "train_runtime": 105821.6183, "train_tokens_per_second": 10691.203 }, { "epoch": 1.8499192028009697, "grad_norm": 0.6772166323079316, "learning_rate": 1.3842211905567227e-07, "loss": 0.27883038520812986, "num_input_tokens_seen": 1131570024, "step": 27475, "train_runtime": 105840.2677, "train_tokens_per_second": 10691.3 }, { "epoch": 1.8502558577969297, "grad_norm": 0.7935174823505035, "learning_rate": 1.378049519184216e-07, "loss": 0.2891415596008301, "num_input_tokens_seen": 1131768896, "step": 27480, "train_runtime": 105859.5609, "train_tokens_per_second": 10691.23 }, { "epoch": 1.8505925127928897, "grad_norm": 0.6793388590527983, "learning_rate": 1.3718914447851116e-07, "loss": 0.2705254554748535, "num_input_tokens_seen": 1131983216, "step": 27485, "train_runtime": 105880.193, "train_tokens_per_second": 10691.171 }, { "epoch": 1.85092916778885, "grad_norm": 0.6960980793156423, "learning_rate": 1.3657469690815106e-07, "loss": 0.2855386734008789, "num_input_tokens_seen": 1132204496, "step": 27490, "train_runtime": 105898.6815, "train_tokens_per_second": 10691.394 }, { "epoch": 1.8512658227848102, "grad_norm": 0.6938688926012974, "learning_rate": 1.359616093791677e-07, "loss": 0.3192328929901123, "num_input_tokens_seen": 1132421240, "step": 27495, "train_runtime": 105918.179, "train_tokens_per_second": 10691.472 }, { "epoch": 1.8516024777807703, "grad_norm": 0.6620118441045182, "learning_rate": 1.353498820630106e-07, "loss": 0.2984445095062256, "num_input_tokens_seen": 1132629224, "step": 27500, "train_runtime": 105937.0627, "train_tokens_per_second": 10691.529 }, { "epoch": 1.8519391327767303, "grad_norm": 0.7091077263464853, "learning_rate": 1.3473951513074625e-07, "loss": 0.30792927742004395, "num_input_tokens_seen": 1132837432, "step": 27505, "train_runtime": 105957.1453, "train_tokens_per_second": 10691.468 }, { "epoch": 1.8522757877726905, "grad_norm": 0.7709258185829613, "learning_rate": 1.341305087530631e-07, "loss": 0.29096806049346924, "num_input_tokens_seen": 1133039976, "step": 27510, "train_runtime": 105975.0364, "train_tokens_per_second": 10691.574 }, { "epoch": 1.8526124427686508, "grad_norm": 0.8791344046475954, "learning_rate": 1.3352286310026663e-07, "loss": 0.31216537952423096, "num_input_tokens_seen": 1133240912, "step": 27515, "train_runtime": 105993.5334, "train_tokens_per_second": 10691.604 }, { "epoch": 1.8529490977646108, "grad_norm": 0.777709841964353, "learning_rate": 1.329165783422831e-07, "loss": 0.3159898519515991, "num_input_tokens_seen": 1133441976, "step": 27520, "train_runtime": 106012.4827, "train_tokens_per_second": 10691.59 }, { "epoch": 1.8532857527605708, "grad_norm": 0.7884381676781878, "learning_rate": 1.3231165464865914e-07, "loss": 0.30037484169006345, "num_input_tokens_seen": 1133644576, "step": 27525, "train_runtime": 106030.7054, "train_tokens_per_second": 10691.663 }, { "epoch": 1.853622407756531, "grad_norm": 0.6728520277649029, "learning_rate": 1.3170809218855884e-07, "loss": 0.2910719871520996, "num_input_tokens_seen": 1133860432, "step": 27530, "train_runtime": 106051.0196, "train_tokens_per_second": 10691.65 }, { "epoch": 1.8539590627524913, "grad_norm": 0.6896364898538716, "learning_rate": 1.3110589113076554e-07, "loss": 0.2883816480636597, "num_input_tokens_seen": 1134070008, "step": 27535, "train_runtime": 106071.5248, "train_tokens_per_second": 10691.559 }, { "epoch": 1.8542957177484514, "grad_norm": 0.7368732093427849, "learning_rate": 1.3050505164368566e-07, "loss": 0.29881045818328855, "num_input_tokens_seen": 1134275640, "step": 27540, "train_runtime": 106089.362, "train_tokens_per_second": 10691.7 }, { "epoch": 1.8546323727444114, "grad_norm": 0.8064286850764181, "learning_rate": 1.299055738953392e-07, "loss": 0.28144192695617676, "num_input_tokens_seen": 1134466064, "step": 27545, "train_runtime": 106110.3688, "train_tokens_per_second": 10691.378 }, { "epoch": 1.8549690277403716, "grad_norm": 0.7625129619486505, "learning_rate": 1.293074580533704e-07, "loss": 0.29143056869506834, "num_input_tokens_seen": 1134671184, "step": 27550, "train_runtime": 106131.6464, "train_tokens_per_second": 10691.167 }, { "epoch": 1.855305682736332, "grad_norm": 0.9706655736493155, "learning_rate": 1.2871070428503885e-07, "loss": 0.3058194637298584, "num_input_tokens_seen": 1134868312, "step": 27555, "train_runtime": 106152.1879, "train_tokens_per_second": 10690.955 }, { "epoch": 1.855642337732292, "grad_norm": 0.6440477202996912, "learning_rate": 1.2811531275722543e-07, "loss": 0.32110445499420165, "num_input_tokens_seen": 1135082328, "step": 27560, "train_runtime": 106170.4366, "train_tokens_per_second": 10691.134 }, { "epoch": 1.855978992728252, "grad_norm": 0.797663218782825, "learning_rate": 1.275212836364298e-07, "loss": 0.3076620101928711, "num_input_tokens_seen": 1135290200, "step": 27565, "train_runtime": 106191.0019, "train_tokens_per_second": 10691.021 }, { "epoch": 1.8563156477242122, "grad_norm": 0.7471952076241963, "learning_rate": 1.2692861708877014e-07, "loss": 0.28410563468933103, "num_input_tokens_seen": 1135490424, "step": 27570, "train_runtime": 106212.5753, "train_tokens_per_second": 10690.734 }, { "epoch": 1.8566523027201725, "grad_norm": 0.6870880827020256, "learning_rate": 1.2633731327998332e-07, "loss": 0.2784524202346802, "num_input_tokens_seen": 1135696624, "step": 27575, "train_runtime": 106231.7464, "train_tokens_per_second": 10690.746 }, { "epoch": 1.8569889577161325, "grad_norm": 0.8041490259759885, "learning_rate": 1.25747372375426e-07, "loss": 0.28519573211669924, "num_input_tokens_seen": 1135893456, "step": 27580, "train_runtime": 106250.0862, "train_tokens_per_second": 10690.753 }, { "epoch": 1.8573256127120925, "grad_norm": 0.8743690518736856, "learning_rate": 1.251587945400723e-07, "loss": 0.2998641014099121, "num_input_tokens_seen": 1136101808, "step": 27585, "train_runtime": 106271.0455, "train_tokens_per_second": 10690.605 }, { "epoch": 1.8576622677080528, "grad_norm": 0.6991721532451923, "learning_rate": 1.2457157993851832e-07, "loss": 0.2912652015686035, "num_input_tokens_seen": 1136311664, "step": 27590, "train_runtime": 106289.8225, "train_tokens_per_second": 10690.691 }, { "epoch": 1.857998922704013, "grad_norm": 0.7164151507310188, "learning_rate": 1.2398572873497438e-07, "loss": 0.29792373180389403, "num_input_tokens_seen": 1136518200, "step": 27595, "train_runtime": 106309.498, "train_tokens_per_second": 10690.655 }, { "epoch": 1.858335577699973, "grad_norm": 0.7340267254774739, "learning_rate": 1.2340124109327334e-07, "loss": 0.2935673952102661, "num_input_tokens_seen": 1136717768, "step": 27600, "train_runtime": 106329.0152, "train_tokens_per_second": 10690.57 }, { "epoch": 1.858672232695933, "grad_norm": 0.7501934342918848, "learning_rate": 1.22818117176865e-07, "loss": 0.3132030487060547, "num_input_tokens_seen": 1136927056, "step": 27605, "train_runtime": 106348.3408, "train_tokens_per_second": 10690.595 }, { "epoch": 1.8590088876918933, "grad_norm": 0.6695054188176688, "learning_rate": 1.2223635714881777e-07, "loss": 0.3020598888397217, "num_input_tokens_seen": 1137124528, "step": 27610, "train_runtime": 106366.519, "train_tokens_per_second": 10690.625 }, { "epoch": 1.8593455426878536, "grad_norm": 0.6719996261194395, "learning_rate": 1.2165596117181931e-07, "loss": 0.2905984163284302, "num_input_tokens_seen": 1137336448, "step": 27615, "train_runtime": 106384.5927, "train_tokens_per_second": 10690.8 }, { "epoch": 1.8596821976838136, "grad_norm": 0.7038191226361254, "learning_rate": 1.2107692940817594e-07, "loss": 0.3112048149108887, "num_input_tokens_seen": 1137541696, "step": 27620, "train_runtime": 106404.9202, "train_tokens_per_second": 10690.687 }, { "epoch": 1.8600188526797736, "grad_norm": 0.7952839296431728, "learning_rate": 1.2049926201981088e-07, "loss": 0.29305410385131836, "num_input_tokens_seen": 1137747136, "step": 27625, "train_runtime": 106423.3902, "train_tokens_per_second": 10690.762 }, { "epoch": 1.8603555076757339, "grad_norm": 0.6761709676009529, "learning_rate": 1.199229591682677e-07, "loss": 0.3049408197402954, "num_input_tokens_seen": 1137956064, "step": 27630, "train_runtime": 106442.4159, "train_tokens_per_second": 10690.814 }, { "epoch": 1.8606921626716941, "grad_norm": 0.8284878952546524, "learning_rate": 1.193480210147069e-07, "loss": 0.3077120065689087, "num_input_tokens_seen": 1138169656, "step": 27635, "train_runtime": 106462.0683, "train_tokens_per_second": 10690.847 }, { "epoch": 1.8610288176676542, "grad_norm": 0.7003301402448242, "learning_rate": 1.1877444771991042e-07, "loss": 0.2795266628265381, "num_input_tokens_seen": 1138383912, "step": 27640, "train_runtime": 106480.9493, "train_tokens_per_second": 10690.963 }, { "epoch": 1.8613654726636142, "grad_norm": 0.7183685749276939, "learning_rate": 1.1820223944427279e-07, "loss": 0.28186464309692383, "num_input_tokens_seen": 1138583312, "step": 27645, "train_runtime": 106502.3882, "train_tokens_per_second": 10690.683 }, { "epoch": 1.8617021276595744, "grad_norm": 0.7103811878980045, "learning_rate": 1.1763139634781262e-07, "loss": 0.29441118240356445, "num_input_tokens_seen": 1138794560, "step": 27650, "train_runtime": 106522.3866, "train_tokens_per_second": 10690.659 }, { "epoch": 1.8620387826555347, "grad_norm": 0.7096081483155529, "learning_rate": 1.1706191859016392e-07, "loss": 0.3281415462493896, "num_input_tokens_seen": 1139001688, "step": 27655, "train_runtime": 106543.0801, "train_tokens_per_second": 10690.527 }, { "epoch": 1.8623754376514947, "grad_norm": 0.7862987433248393, "learning_rate": 1.1649380633057927e-07, "loss": 0.30341424942016604, "num_input_tokens_seen": 1139205968, "step": 27660, "train_runtime": 106562.4701, "train_tokens_per_second": 10690.499 }, { "epoch": 1.8627120926474547, "grad_norm": 0.7137684210706505, "learning_rate": 1.1592705972792939e-07, "loss": 0.273210334777832, "num_input_tokens_seen": 1139409104, "step": 27665, "train_runtime": 106583.176, "train_tokens_per_second": 10690.328 }, { "epoch": 1.863048747643415, "grad_norm": 0.6871605730667567, "learning_rate": 1.1536167894070249e-07, "loss": 0.3073277473449707, "num_input_tokens_seen": 1139621872, "step": 27670, "train_runtime": 106602.9927, "train_tokens_per_second": 10690.337 }, { "epoch": 1.8633854026393752, "grad_norm": 0.7263559551525726, "learning_rate": 1.1479766412700655e-07, "loss": 0.33051722049713134, "num_input_tokens_seen": 1139836200, "step": 27675, "train_runtime": 106623.4242, "train_tokens_per_second": 10690.298 }, { "epoch": 1.8637220576353353, "grad_norm": 0.7776340251908007, "learning_rate": 1.1423501544456595e-07, "loss": 0.31616194248199464, "num_input_tokens_seen": 1140036440, "step": 27680, "train_runtime": 106641.8978, "train_tokens_per_second": 10690.324 }, { "epoch": 1.8640587126312953, "grad_norm": 0.7437392726361719, "learning_rate": 1.1367373305072315e-07, "loss": 0.28658466339111327, "num_input_tokens_seen": 1140244560, "step": 27685, "train_runtime": 106660.9594, "train_tokens_per_second": 10690.365 }, { "epoch": 1.8643953676272556, "grad_norm": 0.7345970450876683, "learning_rate": 1.1311381710244096e-07, "loss": 0.26259191036224366, "num_input_tokens_seen": 1140455840, "step": 27690, "train_runtime": 106681.5515, "train_tokens_per_second": 10690.282 }, { "epoch": 1.8647320226232158, "grad_norm": 0.7655128398572973, "learning_rate": 1.1255526775629521e-07, "loss": 0.2698326587677002, "num_input_tokens_seen": 1140658480, "step": 27695, "train_runtime": 106700.984, "train_tokens_per_second": 10690.234 }, { "epoch": 1.8650686776191758, "grad_norm": 0.7192379192800469, "learning_rate": 1.1199808516848487e-07, "loss": 0.29761581420898436, "num_input_tokens_seen": 1140859560, "step": 27700, "train_runtime": 106720.6944, "train_tokens_per_second": 10690.144 }, { "epoch": 1.8654053326151359, "grad_norm": 0.6983809884547483, "learning_rate": 1.1144226949482306e-07, "loss": 0.28289964199066164, "num_input_tokens_seen": 1141057096, "step": 27705, "train_runtime": 106739.7487, "train_tokens_per_second": 10690.086 }, { "epoch": 1.865741987611096, "grad_norm": 0.6713300458107616, "learning_rate": 1.1088782089074157e-07, "loss": 0.2773505687713623, "num_input_tokens_seen": 1141260128, "step": 27710, "train_runtime": 106759.49, "train_tokens_per_second": 10690.011 }, { "epoch": 1.8660786426070564, "grad_norm": 1.0608379551871618, "learning_rate": 1.1033473951129137e-07, "loss": 0.3056326389312744, "num_input_tokens_seen": 1141469088, "step": 27715, "train_runtime": 106777.3556, "train_tokens_per_second": 10690.179 }, { "epoch": 1.8664152976030164, "grad_norm": 0.7296152833108179, "learning_rate": 1.0978302551113929e-07, "loss": 0.3150584936141968, "num_input_tokens_seen": 1141683888, "step": 27720, "train_runtime": 106796.7784, "train_tokens_per_second": 10690.247 }, { "epoch": 1.8667519525989764, "grad_norm": 0.7461986919375506, "learning_rate": 1.0923267904457025e-07, "loss": 0.3001850605010986, "num_input_tokens_seen": 1141896840, "step": 27725, "train_runtime": 106816.4762, "train_tokens_per_second": 10690.269 }, { "epoch": 1.8670886075949367, "grad_norm": 0.7391968836675085, "learning_rate": 1.086837002654867e-07, "loss": 0.29894270896911623, "num_input_tokens_seen": 1142097120, "step": 27730, "train_runtime": 106836.1371, "train_tokens_per_second": 10690.176 }, { "epoch": 1.867425262590897, "grad_norm": 0.7130277063222676, "learning_rate": 1.0813608932740915e-07, "loss": 0.30509319305419924, "num_input_tokens_seen": 1142314696, "step": 27735, "train_runtime": 106854.2715, "train_tokens_per_second": 10690.398 }, { "epoch": 1.867761917586857, "grad_norm": 0.8269970614373829, "learning_rate": 1.0758984638347569e-07, "loss": 0.2944596290588379, "num_input_tokens_seen": 1142528952, "step": 27740, "train_runtime": 106872.2754, "train_tokens_per_second": 10690.602 }, { "epoch": 1.868098572582817, "grad_norm": 0.7838180359079387, "learning_rate": 1.0704497158644022e-07, "loss": 0.32862286567687987, "num_input_tokens_seen": 1142732968, "step": 27745, "train_runtime": 106890.7037, "train_tokens_per_second": 10690.667 }, { "epoch": 1.8684352275787772, "grad_norm": 0.6206044454268653, "learning_rate": 1.0650146508867642e-07, "loss": 0.28988778591156006, "num_input_tokens_seen": 1142940552, "step": 27750, "train_runtime": 106909.586, "train_tokens_per_second": 10690.721 }, { "epoch": 1.8687718825747375, "grad_norm": 0.7310850771910135, "learning_rate": 1.0595932704217327e-07, "loss": 0.2855924129486084, "num_input_tokens_seen": 1143149696, "step": 27755, "train_runtime": 106928.7711, "train_tokens_per_second": 10690.759 }, { "epoch": 1.8691085375706975, "grad_norm": 0.7752491208731921, "learning_rate": 1.0541855759853837e-07, "loss": 0.28408992290496826, "num_input_tokens_seen": 1143364200, "step": 27760, "train_runtime": 106946.2812, "train_tokens_per_second": 10691.014 }, { "epoch": 1.8694451925666575, "grad_norm": 0.6801034580288075, "learning_rate": 1.0487915690899685e-07, "loss": 0.3035732269287109, "num_input_tokens_seen": 1143571176, "step": 27765, "train_runtime": 106965.7992, "train_tokens_per_second": 10690.998 }, { "epoch": 1.8697818475626178, "grad_norm": 0.667882177217508, "learning_rate": 1.0434112512438921e-07, "loss": 0.29768075942993166, "num_input_tokens_seen": 1143774976, "step": 27770, "train_runtime": 106985.8892, "train_tokens_per_second": 10690.896 }, { "epoch": 1.870118502558578, "grad_norm": 0.8624095514887341, "learning_rate": 1.0380446239517506e-07, "loss": 0.27074470520019533, "num_input_tokens_seen": 1143962776, "step": 27775, "train_runtime": 107004.3513, "train_tokens_per_second": 10690.806 }, { "epoch": 1.870455157554538, "grad_norm": 0.8195906593182681, "learning_rate": 1.032691688714299e-07, "loss": 0.28744874000549314, "num_input_tokens_seen": 1144144248, "step": 27780, "train_runtime": 107025.5292, "train_tokens_per_second": 10690.386 }, { "epoch": 1.870791812550498, "grad_norm": 0.7406537480161298, "learning_rate": 1.0273524470284734e-07, "loss": 0.31628122329711916, "num_input_tokens_seen": 1144357368, "step": 27785, "train_runtime": 107044.9165, "train_tokens_per_second": 10690.441 }, { "epoch": 1.8711284675464583, "grad_norm": 0.8725636199646799, "learning_rate": 1.0220269003873739e-07, "loss": 0.2927736759185791, "num_input_tokens_seen": 1144561544, "step": 27790, "train_runtime": 107062.8482, "train_tokens_per_second": 10690.558 }, { "epoch": 1.8714651225424186, "grad_norm": 0.7720138694477736, "learning_rate": 1.0167150502802703e-07, "loss": 0.2887770652770996, "num_input_tokens_seen": 1144768736, "step": 27795, "train_runtime": 107081.492, "train_tokens_per_second": 10690.631 }, { "epoch": 1.8718017775383786, "grad_norm": 0.7083769125998913, "learning_rate": 1.0114168981926075e-07, "loss": 0.3140178918838501, "num_input_tokens_seen": 1144977736, "step": 27800, "train_runtime": 107099.3634, "train_tokens_per_second": 10690.799 }, { "epoch": 1.8721384325343386, "grad_norm": 0.7467290795828068, "learning_rate": 1.006132445605995e-07, "loss": 0.31010799407958983, "num_input_tokens_seen": 1145169704, "step": 27805, "train_runtime": 107117.7051, "train_tokens_per_second": 10690.76 }, { "epoch": 1.872475087530299, "grad_norm": 0.7027719406584784, "learning_rate": 1.0008616939982118e-07, "loss": 0.29045255184173585, "num_input_tokens_seen": 1145372704, "step": 27810, "train_runtime": 107136.4138, "train_tokens_per_second": 10690.788 }, { "epoch": 1.8728117425262591, "grad_norm": 0.769986607086884, "learning_rate": 9.956046448432177e-08, "loss": 0.28675806522369385, "num_input_tokens_seen": 1145578808, "step": 27815, "train_runtime": 107154.8679, "train_tokens_per_second": 10690.87 }, { "epoch": 1.8731483975222192, "grad_norm": 0.6828260538266349, "learning_rate": 9.90361299611109e-08, "loss": 0.31200995445251467, "num_input_tokens_seen": 1145792912, "step": 27820, "train_runtime": 107173.4251, "train_tokens_per_second": 10691.017 }, { "epoch": 1.8734850525181792, "grad_norm": 0.8036180392985318, "learning_rate": 9.851316597681959e-08, "loss": 0.3116159439086914, "num_input_tokens_seen": 1145993384, "step": 27825, "train_runtime": 107192.9548, "train_tokens_per_second": 10690.939 }, { "epoch": 1.8738217075141395, "grad_norm": 0.7662443067836635, "learning_rate": 9.799157267769088e-08, "loss": 0.30114216804504396, "num_input_tokens_seen": 1146201328, "step": 27830, "train_runtime": 107211.1937, "train_tokens_per_second": 10691.06 }, { "epoch": 1.8741583625100997, "grad_norm": 0.6528427088125871, "learning_rate": 9.747135020958753e-08, "loss": 0.2954397678375244, "num_input_tokens_seen": 1146409776, "step": 27835, "train_runtime": 107231.2666, "train_tokens_per_second": 10691.003 }, { "epoch": 1.8744950175060597, "grad_norm": 0.7017806993953386, "learning_rate": 9.695249871798818e-08, "loss": 0.2792781114578247, "num_input_tokens_seen": 1146614968, "step": 27840, "train_runtime": 107250.0505, "train_tokens_per_second": 10691.044 }, { "epoch": 1.8748316725020198, "grad_norm": 0.7894079628791877, "learning_rate": 9.643501834798786e-08, "loss": 0.30141026973724366, "num_input_tokens_seen": 1146817200, "step": 27845, "train_runtime": 107268.6232, "train_tokens_per_second": 10691.078 }, { "epoch": 1.8751683274979802, "grad_norm": 0.727990791844457, "learning_rate": 9.591890924429858e-08, "loss": 0.30137107372283933, "num_input_tokens_seen": 1147036584, "step": 27850, "train_runtime": 107288.5175, "train_tokens_per_second": 10691.14 }, { "epoch": 1.8755049824939403, "grad_norm": 0.7239853164596921, "learning_rate": 9.540417155124826e-08, "loss": 0.2763482332229614, "num_input_tokens_seen": 1147225720, "step": 27855, "train_runtime": 107308.1968, "train_tokens_per_second": 10690.942 }, { "epoch": 1.8758416374899003, "grad_norm": 0.7142458788614624, "learning_rate": 9.489080541278117e-08, "loss": 0.30286710262298583, "num_input_tokens_seen": 1147425816, "step": 27860, "train_runtime": 107330.0636, "train_tokens_per_second": 10690.628 }, { "epoch": 1.8761782924858605, "grad_norm": 0.6967592059833608, "learning_rate": 9.437881097246026e-08, "loss": 0.30404374599456785, "num_input_tokens_seen": 1147639408, "step": 27865, "train_runtime": 107350.0135, "train_tokens_per_second": 10690.631 }, { "epoch": 1.8765149474818208, "grad_norm": 0.6809583447776539, "learning_rate": 9.3868188373461e-08, "loss": 0.2968709945678711, "num_input_tokens_seen": 1147841648, "step": 27870, "train_runtime": 107368.0934, "train_tokens_per_second": 10690.715 }, { "epoch": 1.8768516024777808, "grad_norm": 0.7962638028963382, "learning_rate": 9.335893775857918e-08, "loss": 0.3096435546875, "num_input_tokens_seen": 1148039472, "step": 27875, "train_runtime": 107385.9975, "train_tokens_per_second": 10690.774 }, { "epoch": 1.8771882574737409, "grad_norm": 0.7027944524776372, "learning_rate": 9.285105927022309e-08, "loss": 0.28367934226989744, "num_input_tokens_seen": 1148248816, "step": 27880, "train_runtime": 107405.2005, "train_tokens_per_second": 10690.812 }, { "epoch": 1.877524912469701, "grad_norm": 0.788606630461678, "learning_rate": 9.234455305042133e-08, "loss": 0.2880712985992432, "num_input_tokens_seen": 1148445952, "step": 27885, "train_runtime": 107426.2291, "train_tokens_per_second": 10690.554 }, { "epoch": 1.8778615674656614, "grad_norm": 0.8487990857086243, "learning_rate": 9.183941924081563e-08, "loss": 0.2910784721374512, "num_input_tokens_seen": 1148649968, "step": 27890, "train_runtime": 107444.9498, "train_tokens_per_second": 10690.591 }, { "epoch": 1.8781982224616214, "grad_norm": 0.7508113378068005, "learning_rate": 9.133565798266574e-08, "loss": 0.2920281648635864, "num_input_tokens_seen": 1148855096, "step": 27895, "train_runtime": 107463.2543, "train_tokens_per_second": 10690.678 }, { "epoch": 1.8785348774575814, "grad_norm": 0.7396487855136223, "learning_rate": 9.083326941684622e-08, "loss": 0.31253325939178467, "num_input_tokens_seen": 1149065400, "step": 27900, "train_runtime": 107481.4345, "train_tokens_per_second": 10690.827 }, { "epoch": 1.8788715324535417, "grad_norm": 1.2216029475157695, "learning_rate": 9.033225368384912e-08, "loss": 0.31148347854614256, "num_input_tokens_seen": 1149266608, "step": 27905, "train_runtime": 107501.4601, "train_tokens_per_second": 10690.707 }, { "epoch": 1.879208187449502, "grad_norm": 0.6047856442392452, "learning_rate": 8.98326109237807e-08, "loss": 0.27253258228302, "num_input_tokens_seen": 1149473408, "step": 27910, "train_runtime": 107520.4061, "train_tokens_per_second": 10690.747 }, { "epoch": 1.879544842445462, "grad_norm": 0.6735529179250634, "learning_rate": 8.933434127636586e-08, "loss": 0.3182716369628906, "num_input_tokens_seen": 1149684768, "step": 27915, "train_runtime": 107540.5981, "train_tokens_per_second": 10690.705 }, { "epoch": 1.879881497441422, "grad_norm": 0.6921454247875076, "learning_rate": 8.883744488094314e-08, "loss": 0.3013193368911743, "num_input_tokens_seen": 1149884992, "step": 27920, "train_runtime": 107559.0961, "train_tokens_per_second": 10690.728 }, { "epoch": 1.8802181524373822, "grad_norm": 0.6593556667097784, "learning_rate": 8.834192187646917e-08, "loss": 0.2984726905822754, "num_input_tokens_seen": 1150100432, "step": 27925, "train_runtime": 107578.2644, "train_tokens_per_second": 10690.825 }, { "epoch": 1.8805548074333425, "grad_norm": 0.7773431404890425, "learning_rate": 8.784777240151365e-08, "loss": 0.3064869403839111, "num_input_tokens_seen": 1150309808, "step": 27930, "train_runtime": 107596.1655, "train_tokens_per_second": 10690.993 }, { "epoch": 1.8808914624293025, "grad_norm": 0.706998411654235, "learning_rate": 8.73549965942655e-08, "loss": 0.30242433547973635, "num_input_tokens_seen": 1150521288, "step": 27935, "train_runtime": 107615.3333, "train_tokens_per_second": 10691.054 }, { "epoch": 1.8812281174252625, "grad_norm": 0.6708050841202675, "learning_rate": 8.686359459252725e-08, "loss": 0.29296126365661623, "num_input_tokens_seen": 1150721440, "step": 27940, "train_runtime": 107635.5562, "train_tokens_per_second": 10690.904 }, { "epoch": 1.8815647724212228, "grad_norm": 0.6338945544200589, "learning_rate": 8.637356653371787e-08, "loss": 0.2834184169769287, "num_input_tokens_seen": 1150933368, "step": 27945, "train_runtime": 107653.6443, "train_tokens_per_second": 10691.077 }, { "epoch": 1.881901427417183, "grad_norm": 0.7995947816003556, "learning_rate": 8.588491255487163e-08, "loss": 0.2719877243041992, "num_input_tokens_seen": 1151134432, "step": 27950, "train_runtime": 107674.3993, "train_tokens_per_second": 10690.883 }, { "epoch": 1.882238082413143, "grad_norm": 0.7156990434096944, "learning_rate": 8.539763279264035e-08, "loss": 0.2802781343460083, "num_input_tokens_seen": 1151339336, "step": 27955, "train_runtime": 107693.9691, "train_tokens_per_second": 10690.843 }, { "epoch": 1.882574737409103, "grad_norm": 0.6734437853836369, "learning_rate": 8.49117273832889e-08, "loss": 0.31632657051086427, "num_input_tokens_seen": 1151551424, "step": 27960, "train_runtime": 107712.0851, "train_tokens_per_second": 10691.014 }, { "epoch": 1.8829113924050633, "grad_norm": 0.6475709763426168, "learning_rate": 8.442719646270082e-08, "loss": 0.27906298637390137, "num_input_tokens_seen": 1151754584, "step": 27965, "train_runtime": 107731.2095, "train_tokens_per_second": 10691.002 }, { "epoch": 1.8832480474010236, "grad_norm": 0.6942270264476994, "learning_rate": 8.394404016637159e-08, "loss": 0.2904759407043457, "num_input_tokens_seen": 1151962320, "step": 27970, "train_runtime": 107750.7425, "train_tokens_per_second": 10690.992 }, { "epoch": 1.8835847023969836, "grad_norm": 0.7533731863994199, "learning_rate": 8.346225862941592e-08, "loss": 0.2931795120239258, "num_input_tokens_seen": 1152157992, "step": 27975, "train_runtime": 107769.6468, "train_tokens_per_second": 10690.932 }, { "epoch": 1.8839213573929436, "grad_norm": 0.7137817860418099, "learning_rate": 8.298185198656161e-08, "loss": 0.307939338684082, "num_input_tokens_seen": 1152374680, "step": 27980, "train_runtime": 107788.4751, "train_tokens_per_second": 10691.075 }, { "epoch": 1.884258012388904, "grad_norm": 0.6981636686360544, "learning_rate": 8.25028203721534e-08, "loss": 0.2834949970245361, "num_input_tokens_seen": 1152576744, "step": 27985, "train_runtime": 107809.0424, "train_tokens_per_second": 10690.91 }, { "epoch": 1.8845946673848641, "grad_norm": 0.7722648193620512, "learning_rate": 8.202516392015081e-08, "loss": 0.30651981830596925, "num_input_tokens_seen": 1152785512, "step": 27990, "train_runtime": 107829.0814, "train_tokens_per_second": 10690.859 }, { "epoch": 1.8849313223808242, "grad_norm": 0.8575698350006369, "learning_rate": 8.154888276412865e-08, "loss": 0.3071486473083496, "num_input_tokens_seen": 1152980368, "step": 27995, "train_runtime": 107847.6527, "train_tokens_per_second": 10690.825 }, { "epoch": 1.8852679773767842, "grad_norm": 0.7010648792639766, "learning_rate": 8.10739770372776e-08, "loss": 0.27765769958496095, "num_input_tokens_seen": 1153189960, "step": 28000, "train_runtime": 107866.0116, "train_tokens_per_second": 10690.948 }, { "epoch": 1.8856046323727444, "grad_norm": 0.6155497416091247, "learning_rate": 8.060044687240365e-08, "loss": 0.270482611656189, "num_input_tokens_seen": 1153411176, "step": 28005, "train_runtime": 107884.1292, "train_tokens_per_second": 10691.203 }, { "epoch": 1.8859412873687047, "grad_norm": 0.6680591806787095, "learning_rate": 8.012829240192754e-08, "loss": 0.30779078006744387, "num_input_tokens_seen": 1153616304, "step": 28010, "train_runtime": 107904.253, "train_tokens_per_second": 10691.111 }, { "epoch": 1.8862779423646647, "grad_norm": 0.669623821355315, "learning_rate": 7.9657513757887e-08, "loss": 0.27957563400268554, "num_input_tokens_seen": 1153825656, "step": 28015, "train_runtime": 107924.116, "train_tokens_per_second": 10691.083 }, { "epoch": 1.8866145973606248, "grad_norm": 0.7251683412317306, "learning_rate": 7.918811107193225e-08, "loss": 0.28422954082489016, "num_input_tokens_seen": 1154039864, "step": 28020, "train_runtime": 107942.9651, "train_tokens_per_second": 10691.2 }, { "epoch": 1.886951252356585, "grad_norm": 0.7968618788562805, "learning_rate": 7.872008447533109e-08, "loss": 0.3173130989074707, "num_input_tokens_seen": 1154245032, "step": 28025, "train_runtime": 107961.0037, "train_tokens_per_second": 10691.314 }, { "epoch": 1.8872879073525453, "grad_norm": 0.7486296302948319, "learning_rate": 7.825343409896547e-08, "loss": 0.30968608856201174, "num_input_tokens_seen": 1154448224, "step": 28030, "train_runtime": 107980.9002, "train_tokens_per_second": 10691.226 }, { "epoch": 1.8876245623485053, "grad_norm": 0.7513114101861158, "learning_rate": 7.778816007333268e-08, "loss": 0.3128221035003662, "num_input_tokens_seen": 1154658296, "step": 28035, "train_runtime": 108001.2681, "train_tokens_per_second": 10691.155 }, { "epoch": 1.8879612173444653, "grad_norm": 0.8431502045667152, "learning_rate": 7.73242625285453e-08, "loss": 0.28689758777618407, "num_input_tokens_seen": 1154863608, "step": 28040, "train_runtime": 108020.4561, "train_tokens_per_second": 10691.157 }, { "epoch": 1.8882978723404256, "grad_norm": 0.6907242768681339, "learning_rate": 7.686174159433069e-08, "loss": 0.30277602672576903, "num_input_tokens_seen": 1155067280, "step": 28045, "train_runtime": 108039.9976, "train_tokens_per_second": 10691.108 }, { "epoch": 1.8886345273363858, "grad_norm": 0.6268092029764223, "learning_rate": 7.640059740003091e-08, "loss": 0.27518324851989745, "num_input_tokens_seen": 1155279976, "step": 28050, "train_runtime": 108059.2167, "train_tokens_per_second": 10691.175 }, { "epoch": 1.8889711823323458, "grad_norm": 0.7662984569081863, "learning_rate": 7.594083007460396e-08, "loss": 0.2957940578460693, "num_input_tokens_seen": 1155476336, "step": 28055, "train_runtime": 108078.0548, "train_tokens_per_second": 10691.128 }, { "epoch": 1.8893078373283059, "grad_norm": 0.6661658493362852, "learning_rate": 7.54824397466225e-08, "loss": 0.2909574031829834, "num_input_tokens_seen": 1155683656, "step": 28060, "train_runtime": 108095.1601, "train_tokens_per_second": 10691.354 }, { "epoch": 1.8896444923242661, "grad_norm": 0.7142397204659632, "learning_rate": 7.502542654427347e-08, "loss": 0.28316192626953124, "num_input_tokens_seen": 1155880736, "step": 28065, "train_runtime": 108112.9919, "train_tokens_per_second": 10691.414 }, { "epoch": 1.8899811473202264, "grad_norm": 0.710955073123546, "learning_rate": 7.456979059535907e-08, "loss": 0.3012054920196533, "num_input_tokens_seen": 1156091080, "step": 28070, "train_runtime": 108134.2753, "train_tokens_per_second": 10691.255 }, { "epoch": 1.8903178023161864, "grad_norm": 0.8422585123274399, "learning_rate": 7.411553202729682e-08, "loss": 0.297117018699646, "num_input_tokens_seen": 1156275272, "step": 28075, "train_runtime": 108153.482, "train_tokens_per_second": 10691.059 }, { "epoch": 1.8906544573121464, "grad_norm": 0.7061485895935197, "learning_rate": 7.3662650967119e-08, "loss": 0.27710011005401614, "num_input_tokens_seen": 1156476664, "step": 28080, "train_runtime": 108172.5167, "train_tokens_per_second": 10691.04 }, { "epoch": 1.8909911123081067, "grad_norm": 0.7228956915891207, "learning_rate": 7.321114754147151e-08, "loss": 0.2960049629211426, "num_input_tokens_seen": 1156685312, "step": 28085, "train_runtime": 108191.2521, "train_tokens_per_second": 10691.117 }, { "epoch": 1.891327767304067, "grad_norm": 1.0114292901161779, "learning_rate": 7.276102187661615e-08, "loss": 0.31980462074279786, "num_input_tokens_seen": 1156889936, "step": 28090, "train_runtime": 108211.947, "train_tokens_per_second": 10690.963 }, { "epoch": 1.891664422300027, "grad_norm": 0.693020490754202, "learning_rate": 7.231227409842944e-08, "loss": 0.3092316150665283, "num_input_tokens_seen": 1157103128, "step": 28095, "train_runtime": 108230.8394, "train_tokens_per_second": 10691.067 }, { "epoch": 1.892001077295987, "grad_norm": 0.7122713756638619, "learning_rate": 7.186490433240156e-08, "loss": 0.30755460262298584, "num_input_tokens_seen": 1157294992, "step": 28100, "train_runtime": 108249.6414, "train_tokens_per_second": 10690.982 }, { "epoch": 1.8923377322919472, "grad_norm": 0.7525180232414576, "learning_rate": 7.14189127036391e-08, "loss": 0.28200058937072753, "num_input_tokens_seen": 1157500176, "step": 28105, "train_runtime": 108268.819, "train_tokens_per_second": 10690.984 }, { "epoch": 1.8926743872879075, "grad_norm": 0.7080342626515855, "learning_rate": 7.097429933686118e-08, "loss": 0.30401694774627686, "num_input_tokens_seen": 1157703632, "step": 28110, "train_runtime": 108288.8675, "train_tokens_per_second": 10690.883 }, { "epoch": 1.8930110422838675, "grad_norm": 0.8423025073949743, "learning_rate": 7.053106435640333e-08, "loss": 0.31955866813659667, "num_input_tokens_seen": 1157921952, "step": 28115, "train_runtime": 108307.8681, "train_tokens_per_second": 10691.023 }, { "epoch": 1.8933476972798275, "grad_norm": 0.7210437928744221, "learning_rate": 7.008920788621366e-08, "loss": 0.29896059036254885, "num_input_tokens_seen": 1158126568, "step": 28120, "train_runtime": 108327.1617, "train_tokens_per_second": 10691.008 }, { "epoch": 1.8936843522757878, "grad_norm": 0.7292294353018944, "learning_rate": 6.964873004985717e-08, "loss": 0.3051054239273071, "num_input_tokens_seen": 1158329728, "step": 28125, "train_runtime": 108346.4185, "train_tokens_per_second": 10690.983 }, { "epoch": 1.894021007271748, "grad_norm": 0.7083176810988023, "learning_rate": 6.920963097051148e-08, "loss": 0.3131895065307617, "num_input_tokens_seen": 1158537040, "step": 28130, "train_runtime": 108365.5892, "train_tokens_per_second": 10691.005 }, { "epoch": 1.894357662267708, "grad_norm": 0.7672867707183699, "learning_rate": 6.877191077096945e-08, "loss": 0.28474404811859133, "num_input_tokens_seen": 1158734584, "step": 28135, "train_runtime": 108385.5913, "train_tokens_per_second": 10690.854 }, { "epoch": 1.894694317263668, "grad_norm": 0.7103305715229729, "learning_rate": 6.833556957363818e-08, "loss": 0.31003389358520506, "num_input_tokens_seen": 1158939000, "step": 28140, "train_runtime": 108404.582, "train_tokens_per_second": 10690.867 }, { "epoch": 1.8950309722596284, "grad_norm": 0.6914550626787778, "learning_rate": 6.790060750053895e-08, "loss": 0.28378806114196775, "num_input_tokens_seen": 1159139704, "step": 28145, "train_runtime": 108422.8245, "train_tokens_per_second": 10690.92 }, { "epoch": 1.8953676272555886, "grad_norm": 0.5954804584871034, "learning_rate": 6.746702467330723e-08, "loss": 0.26448488235473633, "num_input_tokens_seen": 1159356512, "step": 28150, "train_runtime": 108442.4098, "train_tokens_per_second": 10690.988 }, { "epoch": 1.8957042822515486, "grad_norm": 0.6688422100200431, "learning_rate": 6.703482121319383e-08, "loss": 0.2959005117416382, "num_input_tokens_seen": 1159563320, "step": 28155, "train_runtime": 108461.3096, "train_tokens_per_second": 10691.032 }, { "epoch": 1.8960409372475087, "grad_norm": 0.7556349294534336, "learning_rate": 6.660399724106204e-08, "loss": 0.31644203662872317, "num_input_tokens_seen": 1159778664, "step": 28160, "train_runtime": 108480.6591, "train_tokens_per_second": 10691.11 }, { "epoch": 1.896377592243469, "grad_norm": 0.7396080869153971, "learning_rate": 6.617455287739161e-08, "loss": 0.2918878078460693, "num_input_tokens_seen": 1159988016, "step": 28165, "train_runtime": 108499.2453, "train_tokens_per_second": 10691.208 }, { "epoch": 1.8967142472394292, "grad_norm": 0.704135682876384, "learning_rate": 6.574648824227369e-08, "loss": 0.29622840881347656, "num_input_tokens_seen": 1160198208, "step": 28170, "train_runtime": 108518.4816, "train_tokens_per_second": 10691.25 }, { "epoch": 1.8970509022353892, "grad_norm": 0.7227541938885795, "learning_rate": 6.5319803455417e-08, "loss": 0.3075922250747681, "num_input_tokens_seen": 1160408632, "step": 28175, "train_runtime": 108538.7605, "train_tokens_per_second": 10691.191 }, { "epoch": 1.8973875572313492, "grad_norm": 0.7548932621828027, "learning_rate": 6.489449863614106e-08, "loss": 0.3179227113723755, "num_input_tokens_seen": 1160615640, "step": 28180, "train_runtime": 108557.6671, "train_tokens_per_second": 10691.236 }, { "epoch": 1.8977242122273095, "grad_norm": 0.7124233839609977, "learning_rate": 6.44705739033824e-08, "loss": 0.29976763725280764, "num_input_tokens_seen": 1160818504, "step": 28185, "train_runtime": 108577.0452, "train_tokens_per_second": 10691.196 }, { "epoch": 1.8980608672232697, "grad_norm": 0.8398224121454114, "learning_rate": 6.404802937568899e-08, "loss": 0.2840009927749634, "num_input_tokens_seen": 1161009088, "step": 28190, "train_runtime": 108595.5394, "train_tokens_per_second": 10691.131 }, { "epoch": 1.8983975222192297, "grad_norm": 0.6038495229869111, "learning_rate": 6.362686517122463e-08, "loss": 0.28210835456848143, "num_input_tokens_seen": 1161213888, "step": 28195, "train_runtime": 108615.8554, "train_tokens_per_second": 10691.016 }, { "epoch": 1.8987341772151898, "grad_norm": 0.7178219923965509, "learning_rate": 6.320708140776676e-08, "loss": 0.2865053653717041, "num_input_tokens_seen": 1161421328, "step": 28200, "train_runtime": 108636.1348, "train_tokens_per_second": 10690.93 }, { "epoch": 1.89907083221115, "grad_norm": 0.7307243652163236, "learning_rate": 6.278867820270596e-08, "loss": 0.29622421264648435, "num_input_tokens_seen": 1161628424, "step": 28205, "train_runtime": 108654.8182, "train_tokens_per_second": 10690.998 }, { "epoch": 1.8994074872071103, "grad_norm": 0.7222628608148555, "learning_rate": 6.237165567304749e-08, "loss": 0.299841570854187, "num_input_tokens_seen": 1161828304, "step": 28210, "train_runtime": 108674.8065, "train_tokens_per_second": 10690.871 }, { "epoch": 1.8997441422030703, "grad_norm": 0.6874441379315503, "learning_rate": 6.19560139354114e-08, "loss": 0.3104872703552246, "num_input_tokens_seen": 1162048744, "step": 28215, "train_runtime": 108692.4532, "train_tokens_per_second": 10691.163 }, { "epoch": 1.9000807971990303, "grad_norm": 0.722508947245945, "learning_rate": 6.154175310602916e-08, "loss": 0.29940345287323, "num_input_tokens_seen": 1162257800, "step": 28220, "train_runtime": 108710.8853, "train_tokens_per_second": 10691.273 }, { "epoch": 1.9004174521949906, "grad_norm": 0.7106050698723081, "learning_rate": 6.112887330074812e-08, "loss": 0.2870344638824463, "num_input_tokens_seen": 1162456768, "step": 28225, "train_runtime": 108729.5662, "train_tokens_per_second": 10691.266 }, { "epoch": 1.9007541071909508, "grad_norm": 0.7336483118428901, "learning_rate": 6.07173746350287e-08, "loss": 0.2954366207122803, "num_input_tokens_seen": 1162666272, "step": 28230, "train_runtime": 108749.462, "train_tokens_per_second": 10691.237 }, { "epoch": 1.9010907621869109, "grad_norm": 0.7012104982246419, "learning_rate": 6.030725722394548e-08, "loss": 0.3116260528564453, "num_input_tokens_seen": 1162878000, "step": 28235, "train_runtime": 108768.9238, "train_tokens_per_second": 10691.271 }, { "epoch": 1.901427417182871, "grad_norm": 0.8823376626126407, "learning_rate": 5.98985211821862e-08, "loss": 0.31708788871765137, "num_input_tokens_seen": 1163081240, "step": 28240, "train_runtime": 108787.1903, "train_tokens_per_second": 10691.344 }, { "epoch": 1.9017640721788311, "grad_norm": 0.8305336894654903, "learning_rate": 5.9491166624052185e-08, "loss": 0.28808889389038084, "num_input_tokens_seen": 1163296024, "step": 28245, "train_runtime": 108804.8098, "train_tokens_per_second": 10691.586 }, { "epoch": 1.9021007271747914, "grad_norm": 0.7548495703513755, "learning_rate": 5.908519366345955e-08, "loss": 0.29161744117736815, "num_input_tokens_seen": 1163490232, "step": 28250, "train_runtime": 108822.0579, "train_tokens_per_second": 10691.676 }, { "epoch": 1.9024373821707514, "grad_norm": 0.7967289661651176, "learning_rate": 5.868060241393747e-08, "loss": 0.3214111804962158, "num_input_tokens_seen": 1163709952, "step": 28255, "train_runtime": 108841.4777, "train_tokens_per_second": 10691.788 }, { "epoch": 1.9027740371667115, "grad_norm": 0.7203883050686753, "learning_rate": 5.8277392988627665e-08, "loss": 0.2940948009490967, "num_input_tokens_seen": 1163913960, "step": 28260, "train_runtime": 108861.984, "train_tokens_per_second": 10691.648 }, { "epoch": 1.9031106921626717, "grad_norm": 0.8118807274507696, "learning_rate": 5.787556550028772e-08, "loss": 0.2851356744766235, "num_input_tokens_seen": 1164118688, "step": 28265, "train_runtime": 108881.917, "train_tokens_per_second": 10691.57 }, { "epoch": 1.903447347158632, "grad_norm": 0.7333064818276724, "learning_rate": 5.747512006128553e-08, "loss": 0.3123323440551758, "num_input_tokens_seen": 1164334112, "step": 28270, "train_runtime": 108901.3086, "train_tokens_per_second": 10691.645 }, { "epoch": 1.903784002154592, "grad_norm": 0.824320068925617, "learning_rate": 5.707605678360595e-08, "loss": 0.3063490629196167, "num_input_tokens_seen": 1164543336, "step": 28275, "train_runtime": 108921.8506, "train_tokens_per_second": 10691.549 }, { "epoch": 1.904120657150552, "grad_norm": 0.6510473470708609, "learning_rate": 5.6678375778845276e-08, "loss": 0.2918813467025757, "num_input_tokens_seen": 1164756496, "step": 28280, "train_runtime": 108940.1897, "train_tokens_per_second": 10691.706 }, { "epoch": 1.9044573121465123, "grad_norm": 0.689080808845556, "learning_rate": 5.6282077158213435e-08, "loss": 0.28545331954956055, "num_input_tokens_seen": 1164967848, "step": 28285, "train_runtime": 108959.458, "train_tokens_per_second": 10691.755 }, { "epoch": 1.9047939671424725, "grad_norm": 0.8177422854468717, "learning_rate": 5.588716103253511e-08, "loss": 0.3008997917175293, "num_input_tokens_seen": 1165183056, "step": 28290, "train_runtime": 108978.2553, "train_tokens_per_second": 10691.886 }, { "epoch": 1.9051306221384325, "grad_norm": 0.7645668300099756, "learning_rate": 5.549362751224585e-08, "loss": 0.3160692691802979, "num_input_tokens_seen": 1165379280, "step": 28295, "train_runtime": 108996.6739, "train_tokens_per_second": 10691.879 }, { "epoch": 1.9054672771343926, "grad_norm": 0.7203717082771861, "learning_rate": 5.5101476707397075e-08, "loss": 0.2854162216186523, "num_input_tokens_seen": 1165588936, "step": 28300, "train_runtime": 109015.3822, "train_tokens_per_second": 10691.968 }, { "epoch": 1.9058039321303528, "grad_norm": 0.6745069841822974, "learning_rate": 5.471070872765216e-08, "loss": 0.3133185863494873, "num_input_tokens_seen": 1165798360, "step": 28305, "train_runtime": 109034.7366, "train_tokens_per_second": 10691.99 }, { "epoch": 1.906140587126313, "grad_norm": 0.7697619175418845, "learning_rate": 5.432132368228815e-08, "loss": 0.3085129737854004, "num_input_tokens_seen": 1166005552, "step": 28310, "train_runtime": 109052.4844, "train_tokens_per_second": 10692.15 }, { "epoch": 1.906477242122273, "grad_norm": 0.7117479104783808, "learning_rate": 5.393332168019572e-08, "loss": 0.29524683952331543, "num_input_tokens_seen": 1166223352, "step": 28315, "train_runtime": 109072.687, "train_tokens_per_second": 10692.167 }, { "epoch": 1.9068138971182331, "grad_norm": 0.727951626921836, "learning_rate": 5.354670282987695e-08, "loss": 0.3203886032104492, "num_input_tokens_seen": 1166445272, "step": 28320, "train_runtime": 109091.7827, "train_tokens_per_second": 10692.329 }, { "epoch": 1.9071505521141934, "grad_norm": 0.7596997635114503, "learning_rate": 5.316146723945037e-08, "loss": 0.31751189231872556, "num_input_tokens_seen": 1166656016, "step": 28325, "train_runtime": 109111.0996, "train_tokens_per_second": 10692.368 }, { "epoch": 1.9074872071101536, "grad_norm": 0.7300443176511636, "learning_rate": 5.277761501664535e-08, "loss": 0.28869826793670655, "num_input_tokens_seen": 1166861192, "step": 28330, "train_runtime": 109132.1276, "train_tokens_per_second": 10692.188 }, { "epoch": 1.9078238621061137, "grad_norm": 0.8096833097691947, "learning_rate": 5.2395146268804934e-08, "loss": 0.304044771194458, "num_input_tokens_seen": 1167072344, "step": 28335, "train_runtime": 109150.5202, "train_tokens_per_second": 10692.32 }, { "epoch": 1.9081605171020737, "grad_norm": 0.6767600659533383, "learning_rate": 5.201406110288465e-08, "loss": 0.29661245346069337, "num_input_tokens_seen": 1167281760, "step": 28340, "train_runtime": 109170.1803, "train_tokens_per_second": 10692.313 }, { "epoch": 1.908497172098034, "grad_norm": 0.7203351411637444, "learning_rate": 5.1634359625454266e-08, "loss": 0.25519418716430664, "num_input_tokens_seen": 1167484720, "step": 28345, "train_runtime": 109189.182, "train_tokens_per_second": 10692.311 }, { "epoch": 1.9088338270939942, "grad_norm": 0.7756614840849501, "learning_rate": 5.125604194269606e-08, "loss": 0.32717485427856446, "num_input_tokens_seen": 1167688296, "step": 28350, "train_runtime": 109208.5366, "train_tokens_per_second": 10692.28 }, { "epoch": 1.9091704820899542, "grad_norm": 0.7988225241139744, "learning_rate": 5.087910816040542e-08, "loss": 0.31823458671569826, "num_input_tokens_seen": 1167897040, "step": 28355, "train_runtime": 109228.4001, "train_tokens_per_second": 10692.247 }, { "epoch": 1.9095071370859142, "grad_norm": 0.6745589363109097, "learning_rate": 5.0503558383990235e-08, "loss": 0.29276270866394044, "num_input_tokens_seen": 1168111312, "step": 28360, "train_runtime": 109247.5563, "train_tokens_per_second": 10692.334 }, { "epoch": 1.9098437920818745, "grad_norm": 0.811852820668063, "learning_rate": 5.0129392718472614e-08, "loss": 0.2907986640930176, "num_input_tokens_seen": 1168317240, "step": 28365, "train_runtime": 109266.4896, "train_tokens_per_second": 10692.365 }, { "epoch": 1.9101804470778347, "grad_norm": 0.7272930535627543, "learning_rate": 4.9756611268486077e-08, "loss": 0.32683002948760986, "num_input_tokens_seen": 1168532960, "step": 28370, "train_runtime": 109284.4697, "train_tokens_per_second": 10692.58 }, { "epoch": 1.9105171020737948, "grad_norm": 0.7957017170819224, "learning_rate": 4.9385214138277795e-08, "loss": 0.30582025051116946, "num_input_tokens_seen": 1168744216, "step": 28375, "train_runtime": 109306.753, "train_tokens_per_second": 10692.333 }, { "epoch": 1.9108537570697548, "grad_norm": 0.7130899751806262, "learning_rate": 4.901520143170857e-08, "loss": 0.3174252986907959, "num_input_tokens_seen": 1168955072, "step": 28380, "train_runtime": 109326.0697, "train_tokens_per_second": 10692.373 }, { "epoch": 1.911190412065715, "grad_norm": 0.7625683856125196, "learning_rate": 4.864657325225064e-08, "loss": 0.2925252437591553, "num_input_tokens_seen": 1169164320, "step": 28385, "train_runtime": 109345.2078, "train_tokens_per_second": 10692.415 }, { "epoch": 1.9115270670616753, "grad_norm": 0.7094032991584492, "learning_rate": 4.827932970298932e-08, "loss": 0.286814284324646, "num_input_tokens_seen": 1169360104, "step": 28390, "train_runtime": 109364.7387, "train_tokens_per_second": 10692.296 }, { "epoch": 1.9118637220576353, "grad_norm": 0.8766680838873971, "learning_rate": 4.7913470886624125e-08, "loss": 0.30745229721069334, "num_input_tokens_seen": 1169567784, "step": 28395, "train_runtime": 109384.514, "train_tokens_per_second": 10692.261 }, { "epoch": 1.9122003770535954, "grad_norm": 0.7368190749370361, "learning_rate": 4.754899690546544e-08, "loss": 0.28100855350494386, "num_input_tokens_seen": 1169773312, "step": 28400, "train_runtime": 109402.949, "train_tokens_per_second": 10692.338 }, { "epoch": 1.9125370320495556, "grad_norm": 0.7490828644945529, "learning_rate": 4.718590786143729e-08, "loss": 0.30324954986572267, "num_input_tokens_seen": 1169979704, "step": 28405, "train_runtime": 109420.5722, "train_tokens_per_second": 10692.502 }, { "epoch": 1.9128736870455159, "grad_norm": 0.7278764913232882, "learning_rate": 4.6824203856076776e-08, "loss": 0.30341787338256837, "num_input_tokens_seen": 1170200040, "step": 28410, "train_runtime": 109439.3342, "train_tokens_per_second": 10692.682 }, { "epoch": 1.9132103420414759, "grad_norm": 0.6897174149687298, "learning_rate": 4.646388499053356e-08, "loss": 0.2769184589385986, "num_input_tokens_seen": 1170399672, "step": 28415, "train_runtime": 109458.5614, "train_tokens_per_second": 10692.628 }, { "epoch": 1.913546997037436, "grad_norm": 0.7080130540054393, "learning_rate": 4.6104951365568696e-08, "loss": 0.2743279457092285, "num_input_tokens_seen": 1170607112, "step": 28420, "train_runtime": 109477.2433, "train_tokens_per_second": 10692.698 }, { "epoch": 1.9138836520333962, "grad_norm": 0.7881511881798398, "learning_rate": 4.574740308155801e-08, "loss": 0.2949679374694824, "num_input_tokens_seen": 1170808008, "step": 28425, "train_runtime": 109498.0823, "train_tokens_per_second": 10692.498 }, { "epoch": 1.9142203070293564, "grad_norm": 0.8449841651632208, "learning_rate": 4.539124023848762e-08, "loss": 0.2971165657043457, "num_input_tokens_seen": 1171026600, "step": 28430, "train_runtime": 109517.2997, "train_tokens_per_second": 10692.618 }, { "epoch": 1.9145569620253164, "grad_norm": 0.7207684097631579, "learning_rate": 4.503646293595787e-08, "loss": 0.3195672512054443, "num_input_tokens_seen": 1171229640, "step": 28435, "train_runtime": 109536.253, "train_tokens_per_second": 10692.621 }, { "epoch": 1.9148936170212765, "grad_norm": 0.7396527046729573, "learning_rate": 4.468307127318105e-08, "loss": 0.29060218334197996, "num_input_tokens_seen": 1171440128, "step": 28440, "train_runtime": 109554.2338, "train_tokens_per_second": 10692.787 }, { "epoch": 1.9152302720172367, "grad_norm": 0.8476284285877587, "learning_rate": 4.4331065348982014e-08, "loss": 0.2827327013015747, "num_input_tokens_seen": 1171643416, "step": 28445, "train_runtime": 109571.8518, "train_tokens_per_second": 10692.923 }, { "epoch": 1.915566927013197, "grad_norm": 0.7015415545960865, "learning_rate": 4.3980445261798125e-08, "loss": 0.303954553604126, "num_input_tokens_seen": 1171853064, "step": 28450, "train_runtime": 109591.3063, "train_tokens_per_second": 10692.938 }, { "epoch": 1.915903582009157, "grad_norm": 0.7853025991614921, "learning_rate": 4.363121110967927e-08, "loss": 0.2821982383728027, "num_input_tokens_seen": 1172047328, "step": 28455, "train_runtime": 109611.0693, "train_tokens_per_second": 10692.783 }, { "epoch": 1.916240237005117, "grad_norm": 0.7098482842700373, "learning_rate": 4.328336299028735e-08, "loss": 0.27444617748260497, "num_input_tokens_seen": 1172244824, "step": 28460, "train_runtime": 109630.3861, "train_tokens_per_second": 10692.7 }, { "epoch": 1.9165768920010773, "grad_norm": 0.7924815498282698, "learning_rate": 4.293690100089731e-08, "loss": 0.30277559757232664, "num_input_tokens_seen": 1172445360, "step": 28465, "train_runtime": 109648.5206, "train_tokens_per_second": 10692.76 }, { "epoch": 1.9169135469970375, "grad_norm": 0.7896859517152397, "learning_rate": 4.259182523839556e-08, "loss": 0.2887148857116699, "num_input_tokens_seen": 1172656096, "step": 28470, "train_runtime": 109667.3998, "train_tokens_per_second": 10692.841 }, { "epoch": 1.9172502019929976, "grad_norm": 0.7786233025494238, "learning_rate": 4.224813579928211e-08, "loss": 0.3174459218978882, "num_input_tokens_seen": 1172865024, "step": 28475, "train_runtime": 109687.0158, "train_tokens_per_second": 10692.834 }, { "epoch": 1.9175868569889576, "grad_norm": 0.6926903369126101, "learning_rate": 4.190583277966842e-08, "loss": 0.29579362869262693, "num_input_tokens_seen": 1173071736, "step": 28480, "train_runtime": 109706.5281, "train_tokens_per_second": 10692.816 }, { "epoch": 1.9179235119849178, "grad_norm": 0.8478072336811068, "learning_rate": 4.1564916275278477e-08, "loss": 0.2822216510772705, "num_input_tokens_seen": 1173268928, "step": 28485, "train_runtime": 109726.9885, "train_tokens_per_second": 10692.619 }, { "epoch": 1.918260166980878, "grad_norm": 0.7329329809370797, "learning_rate": 4.122538638144824e-08, "loss": 0.2950504541397095, "num_input_tokens_seen": 1173476144, "step": 28490, "train_runtime": 109746.5917, "train_tokens_per_second": 10692.598 }, { "epoch": 1.9185968219768381, "grad_norm": 0.6615845338444575, "learning_rate": 4.08872431931262e-08, "loss": 0.27306351661682127, "num_input_tokens_seen": 1173678824, "step": 28495, "train_runtime": 109766.716, "train_tokens_per_second": 10692.484 }, { "epoch": 1.9189334769727981, "grad_norm": 0.7326705151449496, "learning_rate": 4.055048680487339e-08, "loss": 0.2910433530807495, "num_input_tokens_seen": 1173891456, "step": 28500, "train_runtime": 109786.1855, "train_tokens_per_second": 10692.524 }, { "epoch": 1.9192701319687584, "grad_norm": 0.7127555238327461, "learning_rate": 4.0215117310862806e-08, "loss": 0.31376633644104, "num_input_tokens_seen": 1174080968, "step": 28505, "train_runtime": 109807.3737, "train_tokens_per_second": 10692.187 }, { "epoch": 1.9196067869647186, "grad_norm": 0.8041443502259895, "learning_rate": 3.9881134804878316e-08, "loss": 0.2990253448486328, "num_input_tokens_seen": 1174274304, "step": 28510, "train_runtime": 109828.5092, "train_tokens_per_second": 10691.89 }, { "epoch": 1.9199434419606787, "grad_norm": 0.7665931912675156, "learning_rate": 3.9548539380318e-08, "loss": 0.31842827796936035, "num_input_tokens_seen": 1174486664, "step": 28515, "train_runtime": 109847.1972, "train_tokens_per_second": 10692.004 }, { "epoch": 1.9202800969566387, "grad_norm": 0.7458307587540802, "learning_rate": 3.921733113019077e-08, "loss": 0.3036266565322876, "num_input_tokens_seen": 1174677600, "step": 28520, "train_runtime": 109865.4981, "train_tokens_per_second": 10691.961 }, { "epoch": 1.920616751952599, "grad_norm": 0.731040900509969, "learning_rate": 3.888751014711867e-08, "loss": 0.3156641960144043, "num_input_tokens_seen": 1174868752, "step": 28525, "train_runtime": 109882.6398, "train_tokens_per_second": 10692.032 }, { "epoch": 1.9209534069485592, "grad_norm": 0.6563034461296925, "learning_rate": 3.855907652333402e-08, "loss": 0.2872683048248291, "num_input_tokens_seen": 1175078120, "step": 28530, "train_runtime": 109903.4617, "train_tokens_per_second": 10691.912 }, { "epoch": 1.9212900619445192, "grad_norm": 0.6906978260461828, "learning_rate": 3.8232030350683344e-08, "loss": 0.29242582321166993, "num_input_tokens_seen": 1175294368, "step": 28535, "train_runtime": 109923.6668, "train_tokens_per_second": 10691.914 }, { "epoch": 1.9216267169404793, "grad_norm": 0.7441025315237018, "learning_rate": 3.7906371720622946e-08, "loss": 0.3014089584350586, "num_input_tokens_seen": 1175508112, "step": 28540, "train_runtime": 109942.4635, "train_tokens_per_second": 10692.03 }, { "epoch": 1.9219633719364395, "grad_norm": 0.6904797513680162, "learning_rate": 3.758210072422275e-08, "loss": 0.2825160503387451, "num_input_tokens_seen": 1175713424, "step": 28545, "train_runtime": 109961.3502, "train_tokens_per_second": 10692.061 }, { "epoch": 1.9223000269323998, "grad_norm": 0.816937147226853, "learning_rate": 3.72592174521641e-08, "loss": 0.3118185520172119, "num_input_tokens_seen": 1175923608, "step": 28550, "train_runtime": 109980.8522, "train_tokens_per_second": 10692.076 }, { "epoch": 1.9226366819283598, "grad_norm": 0.7256198664556961, "learning_rate": 3.693772199474033e-08, "loss": 0.3046120166778564, "num_input_tokens_seen": 1176132072, "step": 28555, "train_runtime": 110000.5673, "train_tokens_per_second": 10692.055 }, { "epoch": 1.9229733369243198, "grad_norm": 0.7781511477810871, "learning_rate": 3.661761444185674e-08, "loss": 0.29980013370513914, "num_input_tokens_seen": 1176335344, "step": 28560, "train_runtime": 110020.3477, "train_tokens_per_second": 10691.98 }, { "epoch": 1.92330999192028, "grad_norm": 1.0563584291417367, "learning_rate": 3.6298894883030066e-08, "loss": 0.30217270851135253, "num_input_tokens_seen": 1176546944, "step": 28565, "train_runtime": 110038.3938, "train_tokens_per_second": 10692.149 }, { "epoch": 1.9236466469162403, "grad_norm": 0.7912499113076461, "learning_rate": 3.5981563407389007e-08, "loss": 0.3202293157577515, "num_input_tokens_seen": 1176755200, "step": 28570, "train_runtime": 110058.1052, "train_tokens_per_second": 10692.127 }, { "epoch": 1.9239833019122003, "grad_norm": 0.7304217903502339, "learning_rate": 3.566562010367536e-08, "loss": 0.2787317752838135, "num_input_tokens_seen": 1176950048, "step": 28575, "train_runtime": 110076.2745, "train_tokens_per_second": 10692.132 }, { "epoch": 1.9243199569081604, "grad_norm": 0.6850325573291881, "learning_rate": 3.535106506024011e-08, "loss": 0.29954068660736083, "num_input_tokens_seen": 1177156168, "step": 28580, "train_runtime": 110096.2643, "train_tokens_per_second": 10692.063 }, { "epoch": 1.9246566119041206, "grad_norm": 0.7321343335664776, "learning_rate": 3.5037898365049005e-08, "loss": 0.26548118591308595, "num_input_tokens_seen": 1177364520, "step": 28585, "train_runtime": 110115.1392, "train_tokens_per_second": 10692.122 }, { "epoch": 1.9249932669000809, "grad_norm": 1.739123627198899, "learning_rate": 3.472612010567755e-08, "loss": 0.2962028980255127, "num_input_tokens_seen": 1177559664, "step": 28590, "train_runtime": 110133.2997, "train_tokens_per_second": 10692.131 }, { "epoch": 1.925329921896041, "grad_norm": 0.763822959438285, "learning_rate": 3.441573036931323e-08, "loss": 0.3118077516555786, "num_input_tokens_seen": 1177772960, "step": 28595, "train_runtime": 110152.1611, "train_tokens_per_second": 10692.237 }, { "epoch": 1.925666576892001, "grad_norm": 0.7226133296018143, "learning_rate": 3.410672924275604e-08, "loss": 0.27268161773681643, "num_input_tokens_seen": 1177989432, "step": 28600, "train_runtime": 110172.3052, "train_tokens_per_second": 10692.246 }, { "epoch": 1.9260032318879612, "grad_norm": 0.7697629483853936, "learning_rate": 3.3799116812416876e-08, "loss": 0.31268463134765623, "num_input_tokens_seen": 1178190448, "step": 28605, "train_runtime": 110191.7672, "train_tokens_per_second": 10692.182 }, { "epoch": 1.9263398868839214, "grad_norm": 0.8289371887771183, "learning_rate": 3.349289316431803e-08, "loss": 0.3120110511779785, "num_input_tokens_seen": 1178400896, "step": 28610, "train_runtime": 110210.0119, "train_tokens_per_second": 10692.322 }, { "epoch": 1.9266765418798815, "grad_norm": 0.7128363853086295, "learning_rate": 3.3188058384095446e-08, "loss": 0.2912312984466553, "num_input_tokens_seen": 1178604456, "step": 28615, "train_runtime": 110228.0747, "train_tokens_per_second": 10692.416 }, { "epoch": 1.9270131968758415, "grad_norm": 0.754159575021504, "learning_rate": 3.2884612556993714e-08, "loss": 0.3230398416519165, "num_input_tokens_seen": 1178812432, "step": 28620, "train_runtime": 110247.2506, "train_tokens_per_second": 10692.443 }, { "epoch": 1.9273498518718017, "grad_norm": 0.8305883004014386, "learning_rate": 3.258255576787161e-08, "loss": 0.313142991065979, "num_input_tokens_seen": 1179013816, "step": 28625, "train_runtime": 110266.707, "train_tokens_per_second": 10692.383 }, { "epoch": 1.927686506867762, "grad_norm": 0.8144064644235768, "learning_rate": 3.22818881011977e-08, "loss": 0.31524693965911865, "num_input_tokens_seen": 1179231792, "step": 28630, "train_runtime": 110285.045, "train_tokens_per_second": 10692.581 }, { "epoch": 1.928023161863722, "grad_norm": 0.746937091457366, "learning_rate": 3.198260964105249e-08, "loss": 0.28096766471862794, "num_input_tokens_seen": 1179433760, "step": 28635, "train_runtime": 110303.8343, "train_tokens_per_second": 10692.591 }, { "epoch": 1.928359816859682, "grad_norm": 0.7302351690984955, "learning_rate": 3.168472047112903e-08, "loss": 0.2981107711791992, "num_input_tokens_seen": 1179639568, "step": 28640, "train_runtime": 110324.8049, "train_tokens_per_second": 10692.424 }, { "epoch": 1.9286964718556423, "grad_norm": 0.8085147814227318, "learning_rate": 3.138822067473068e-08, "loss": 0.28764901161193845, "num_input_tokens_seen": 1179840152, "step": 28645, "train_runtime": 110343.6666, "train_tokens_per_second": 10692.414 }, { "epoch": 1.9290331268516026, "grad_norm": 0.693758430734716, "learning_rate": 3.10931103347728e-08, "loss": 0.3033994197845459, "num_input_tokens_seen": 1180051776, "step": 28650, "train_runtime": 110364.3629, "train_tokens_per_second": 10692.326 }, { "epoch": 1.9293697818475626, "grad_norm": 0.7336810111881945, "learning_rate": 3.0799389533781587e-08, "loss": 0.3249834060668945, "num_input_tokens_seen": 1180265120, "step": 28655, "train_runtime": 110381.8825, "train_tokens_per_second": 10692.562 }, { "epoch": 1.9297064368435226, "grad_norm": 0.7287558765131533, "learning_rate": 3.050705835389578e-08, "loss": 0.2819077491760254, "num_input_tokens_seen": 1180470120, "step": 28660, "train_runtime": 110401.0915, "train_tokens_per_second": 10692.558 }, { "epoch": 1.9300430918394829, "grad_norm": 0.8151477427331347, "learning_rate": 3.021611687686443e-08, "loss": 0.29762492179870603, "num_input_tokens_seen": 1180669608, "step": 28665, "train_runtime": 110420.9657, "train_tokens_per_second": 10692.441 }, { "epoch": 1.9303797468354431, "grad_norm": 0.7790712548643981, "learning_rate": 2.992656518404857e-08, "loss": 0.3132267951965332, "num_input_tokens_seen": 1180867448, "step": 28670, "train_runtime": 110441.0876, "train_tokens_per_second": 10692.284 }, { "epoch": 1.9307164018314031, "grad_norm": 0.6430338428428849, "learning_rate": 2.96384033564201e-08, "loss": 0.2857546806335449, "num_input_tokens_seen": 1181070088, "step": 28675, "train_runtime": 110459.4767, "train_tokens_per_second": 10692.338 }, { "epoch": 1.9310530568273632, "grad_norm": 0.7634319542807351, "learning_rate": 2.935163147456288e-08, "loss": 0.2816734552383423, "num_input_tokens_seen": 1181278736, "step": 28680, "train_runtime": 110477.6064, "train_tokens_per_second": 10692.472 }, { "epoch": 1.9313897118233234, "grad_norm": 0.7859706445739006, "learning_rate": 2.906624961867166e-08, "loss": 0.30389060974121096, "num_input_tokens_seen": 1181486488, "step": 28685, "train_runtime": 110497.4595, "train_tokens_per_second": 10692.431 }, { "epoch": 1.9317263668192837, "grad_norm": 0.7694128968432153, "learning_rate": 2.8782257868553154e-08, "loss": 0.2777946710586548, "num_input_tokens_seen": 1181690264, "step": 28690, "train_runtime": 110517.2787, "train_tokens_per_second": 10692.358 }, { "epoch": 1.9320630218152437, "grad_norm": 0.7261647892412492, "learning_rate": 2.849965630362328e-08, "loss": 0.2991067409515381, "num_input_tokens_seen": 1181888152, "step": 28695, "train_runtime": 110535.5763, "train_tokens_per_second": 10692.378 }, { "epoch": 1.9323996768112037, "grad_norm": 0.810729325291832, "learning_rate": 2.8218445002912153e-08, "loss": 0.2931236743927002, "num_input_tokens_seen": 1182101864, "step": 28700, "train_runtime": 110556.9769, "train_tokens_per_second": 10692.241 }, { "epoch": 1.932736331807164, "grad_norm": 0.7595017996040252, "learning_rate": 2.7938624045059094e-08, "loss": 0.29619584083557127, "num_input_tokens_seen": 1182310816, "step": 28705, "train_runtime": 110574.7075, "train_tokens_per_second": 10692.416 }, { "epoch": 1.9330729868031242, "grad_norm": 0.8106017249523474, "learning_rate": 2.766019350831428e-08, "loss": 0.30831055641174315, "num_input_tokens_seen": 1182534384, "step": 28710, "train_runtime": 110593.8743, "train_tokens_per_second": 10692.585 }, { "epoch": 1.9334096417990843, "grad_norm": 0.7304163759262664, "learning_rate": 2.7383153470541546e-08, "loss": 0.30352087020874025, "num_input_tokens_seen": 1182748432, "step": 28715, "train_runtime": 110612.8464, "train_tokens_per_second": 10692.686 }, { "epoch": 1.9337462967950443, "grad_norm": 0.7459203248392638, "learning_rate": 2.710750400921336e-08, "loss": 0.28237175941467285, "num_input_tokens_seen": 1182938696, "step": 28720, "train_runtime": 110632.5037, "train_tokens_per_second": 10692.506 }, { "epoch": 1.9340829517910045, "grad_norm": 0.7029038727507284, "learning_rate": 2.683324520141417e-08, "loss": 0.29702959060668943, "num_input_tokens_seen": 1183149592, "step": 28725, "train_runtime": 110651.2406, "train_tokens_per_second": 10692.601 }, { "epoch": 1.9344196067869648, "grad_norm": 0.7420004278317662, "learning_rate": 2.65603771238393e-08, "loss": 0.3058670997619629, "num_input_tokens_seen": 1183349848, "step": 28730, "train_runtime": 110672.2086, "train_tokens_per_second": 10692.385 }, { "epoch": 1.9347562617829248, "grad_norm": 0.705063719808837, "learning_rate": 2.6288899852796036e-08, "loss": 0.29687550067901614, "num_input_tokens_seen": 1183569512, "step": 28735, "train_runtime": 110691.8754, "train_tokens_per_second": 10692.47 }, { "epoch": 1.9350929167788848, "grad_norm": 0.7833976034045594, "learning_rate": 2.6018813464202543e-08, "loss": 0.303099250793457, "num_input_tokens_seen": 1183768592, "step": 28740, "train_runtime": 110710.893, "train_tokens_per_second": 10692.431 }, { "epoch": 1.935429571774845, "grad_norm": 0.6816645233896961, "learning_rate": 2.575011803358618e-08, "loss": 0.29332790374755857, "num_input_tokens_seen": 1183978752, "step": 28745, "train_runtime": 110729.6531, "train_tokens_per_second": 10692.517 }, { "epoch": 1.9357662267708053, "grad_norm": 0.6588610107520526, "learning_rate": 2.5482813636087955e-08, "loss": 0.2766729354858398, "num_input_tokens_seen": 1184177488, "step": 28750, "train_runtime": 110749.3716, "train_tokens_per_second": 10692.408 }, { "epoch": 1.9361028817667654, "grad_norm": 0.7717195892514409, "learning_rate": 2.5216900346458073e-08, "loss": 0.2877663612365723, "num_input_tokens_seen": 1184384520, "step": 28755, "train_runtime": 110771.103, "train_tokens_per_second": 10692.18 }, { "epoch": 1.9364395367627254, "grad_norm": 0.7269361957207366, "learning_rate": 2.4952378239058716e-08, "loss": 0.2899739980697632, "num_input_tokens_seen": 1184596816, "step": 28760, "train_runtime": 110788.4848, "train_tokens_per_second": 10692.418 }, { "epoch": 1.9367761917586857, "grad_norm": 0.7696419027074466, "learning_rate": 2.4689247387862934e-08, "loss": 0.29292595386505127, "num_input_tokens_seen": 1184797424, "step": 28765, "train_runtime": 110806.8549, "train_tokens_per_second": 10692.456 }, { "epoch": 1.937112846754646, "grad_norm": 0.7574533907459972, "learning_rate": 2.4427507866453537e-08, "loss": 0.28291022777557373, "num_input_tokens_seen": 1184982056, "step": 28770, "train_runtime": 110826.2015, "train_tokens_per_second": 10692.255 }, { "epoch": 1.937449501750606, "grad_norm": 0.8370796341952184, "learning_rate": 2.416715974802586e-08, "loss": 0.28802545070648194, "num_input_tokens_seen": 1185180296, "step": 28775, "train_runtime": 110844.8617, "train_tokens_per_second": 10692.244 }, { "epoch": 1.937786156746566, "grad_norm": 0.6966459020354414, "learning_rate": 2.3908203105384997e-08, "loss": 0.2977855920791626, "num_input_tokens_seen": 1185387144, "step": 28780, "train_runtime": 110862.6982, "train_tokens_per_second": 10692.389 }, { "epoch": 1.9381228117425262, "grad_norm": 0.7007555858693898, "learning_rate": 2.365063801094747e-08, "loss": 0.2837554454803467, "num_input_tokens_seen": 1185590248, "step": 28785, "train_runtime": 110881.22, "train_tokens_per_second": 10692.435 }, { "epoch": 1.9384594667384865, "grad_norm": 0.699223352895718, "learning_rate": 2.3394464536740658e-08, "loss": 0.3096569538116455, "num_input_tokens_seen": 1185810384, "step": 28790, "train_runtime": 110902.465, "train_tokens_per_second": 10692.372 }, { "epoch": 1.9387961217344465, "grad_norm": 0.7815752858753886, "learning_rate": 2.3139682754402816e-08, "loss": 0.31529409885406495, "num_input_tokens_seen": 1186024120, "step": 28795, "train_runtime": 110920.7322, "train_tokens_per_second": 10692.538 }, { "epoch": 1.9391327767304065, "grad_norm": 0.7117354429798358, "learning_rate": 2.2886292735182502e-08, "loss": 0.29137482643127444, "num_input_tokens_seen": 1186240520, "step": 28800, "train_runtime": 110938.9612, "train_tokens_per_second": 10692.731 }, { "epoch": 1.9394694317263668, "grad_norm": 0.7014394102728067, "learning_rate": 2.2634294549939705e-08, "loss": 0.2934577465057373, "num_input_tokens_seen": 1186455304, "step": 28805, "train_runtime": 110958.7261, "train_tokens_per_second": 10692.762 }, { "epoch": 1.939806086722327, "grad_norm": 0.7406676607056929, "learning_rate": 2.2383688269144723e-08, "loss": 0.3595703601837158, "num_input_tokens_seen": 1186663008, "step": 28810, "train_runtime": 110976.8205, "train_tokens_per_second": 10692.891 }, { "epoch": 1.940142741718287, "grad_norm": 0.7573173957148998, "learning_rate": 2.2134473962878712e-08, "loss": 0.29187698364257814, "num_input_tokens_seen": 1186864872, "step": 28815, "train_runtime": 110996.1648, "train_tokens_per_second": 10692.846 }, { "epoch": 1.940479396714247, "grad_norm": 0.9488251416853745, "learning_rate": 2.1886651700833705e-08, "loss": 0.2886594295501709, "num_input_tokens_seen": 1187044280, "step": 28820, "train_runtime": 111015.0375, "train_tokens_per_second": 10692.644 }, { "epoch": 1.9408160517102075, "grad_norm": 0.6718150963397272, "learning_rate": 2.1640221552312603e-08, "loss": 0.30231471061706544, "num_input_tokens_seen": 1187249752, "step": 28825, "train_runtime": 111033.8369, "train_tokens_per_second": 10692.684 }, { "epoch": 1.9411527067061676, "grad_norm": 0.7034301889559711, "learning_rate": 2.1395183586229163e-08, "loss": 0.30983049869537355, "num_input_tokens_seen": 1187469192, "step": 28830, "train_runtime": 111053.0148, "train_tokens_per_second": 10692.814 }, { "epoch": 1.9414893617021276, "grad_norm": 0.7343128095065966, "learning_rate": 2.1151537871106353e-08, "loss": 0.2917337417602539, "num_input_tokens_seen": 1187667264, "step": 28835, "train_runtime": 111072.3666, "train_tokens_per_second": 10692.734 }, { "epoch": 1.9418260166980879, "grad_norm": 0.7780591383883861, "learning_rate": 2.0909284475080226e-08, "loss": 0.28926055431365966, "num_input_tokens_seen": 1187875344, "step": 28840, "train_runtime": 111092.3691, "train_tokens_per_second": 10692.682 }, { "epoch": 1.942162671694048, "grad_norm": 0.7522242196176765, "learning_rate": 2.0668423465894928e-08, "loss": 0.27972097396850587, "num_input_tokens_seen": 1188082536, "step": 28845, "train_runtime": 111111.8623, "train_tokens_per_second": 10692.671 }, { "epoch": 1.9424993266900081, "grad_norm": 0.7242310941553288, "learning_rate": 2.0428954910907684e-08, "loss": 0.2878722667694092, "num_input_tokens_seen": 1188268208, "step": 28850, "train_runtime": 111130.6204, "train_tokens_per_second": 10692.536 }, { "epoch": 1.9428359816859682, "grad_norm": 0.7759701042666132, "learning_rate": 2.019087887708382e-08, "loss": 0.3009951591491699, "num_input_tokens_seen": 1188474800, "step": 28855, "train_runtime": 111150.1429, "train_tokens_per_second": 10692.517 }, { "epoch": 1.9431726366819284, "grad_norm": 0.7490114368577561, "learning_rate": 1.9954195431001744e-08, "loss": 0.29886317253112793, "num_input_tokens_seen": 1188687632, "step": 28860, "train_runtime": 111169.2003, "train_tokens_per_second": 10692.599 }, { "epoch": 1.9435092916778887, "grad_norm": 0.7546750330884631, "learning_rate": 1.9718904638848513e-08, "loss": 0.28019146919250487, "num_input_tokens_seen": 1188887808, "step": 28865, "train_runtime": 111187.3607, "train_tokens_per_second": 10692.652 }, { "epoch": 1.9438459466738487, "grad_norm": 0.705185768801072, "learning_rate": 1.9485006566422602e-08, "loss": 0.294357967376709, "num_input_tokens_seen": 1189106664, "step": 28870, "train_runtime": 111207.7778, "train_tokens_per_second": 10692.657 }, { "epoch": 1.9441826016698087, "grad_norm": 0.7012900044357507, "learning_rate": 1.9252501279132806e-08, "loss": 0.3038753271102905, "num_input_tokens_seen": 1189311880, "step": 28875, "train_runtime": 111228.9573, "train_tokens_per_second": 10692.466 }, { "epoch": 1.944519256665769, "grad_norm": 0.6622654900630239, "learning_rate": 1.902138884199878e-08, "loss": 0.3012328386306763, "num_input_tokens_seen": 1189523312, "step": 28880, "train_runtime": 111248.2424, "train_tokens_per_second": 10692.513 }, { "epoch": 1.9448559116617292, "grad_norm": 0.6868577256281964, "learning_rate": 1.879166931964993e-08, "loss": 0.30173263549804685, "num_input_tokens_seen": 1189726536, "step": 28885, "train_runtime": 111266.8144, "train_tokens_per_second": 10692.555 }, { "epoch": 1.9451925666576892, "grad_norm": 0.720371935300416, "learning_rate": 1.856334277632765e-08, "loss": 0.2924393653869629, "num_input_tokens_seen": 1189948024, "step": 28890, "train_runtime": 111285.9617, "train_tokens_per_second": 10692.706 }, { "epoch": 1.9455292216536493, "grad_norm": 0.6789180183108366, "learning_rate": 1.8336409275880872e-08, "loss": 0.2973504066467285, "num_input_tokens_seen": 1190165048, "step": 28895, "train_runtime": 111305.1277, "train_tokens_per_second": 10692.814 }, { "epoch": 1.9458658766496095, "grad_norm": 0.7375860528567995, "learning_rate": 1.8110868881772713e-08, "loss": 0.2918103694915771, "num_input_tokens_seen": 1190363168, "step": 28900, "train_runtime": 111323.642, "train_tokens_per_second": 10692.816 }, { "epoch": 1.9462025316455698, "grad_norm": 0.6839436513112511, "learning_rate": 1.788672165707328e-08, "loss": 0.27029736042022706, "num_input_tokens_seen": 1190569024, "step": 28905, "train_runtime": 111341.8223, "train_tokens_per_second": 10692.918 }, { "epoch": 1.9465391866415298, "grad_norm": 0.7145352716037602, "learning_rate": 1.7663967664465763e-08, "loss": 0.2739124298095703, "num_input_tokens_seen": 1190765248, "step": 28910, "train_runtime": 111361.6608, "train_tokens_per_second": 10692.776 }, { "epoch": 1.9468758416374898, "grad_norm": 0.7412867814369131, "learning_rate": 1.7442606966242005e-08, "loss": 0.312425422668457, "num_input_tokens_seen": 1190986264, "step": 28915, "train_runtime": 111380.6357, "train_tokens_per_second": 10692.938 }, { "epoch": 1.94721249663345, "grad_norm": 0.7085298810106957, "learning_rate": 1.722263962430526e-08, "loss": 0.3082741737365723, "num_input_tokens_seen": 1191195864, "step": 28920, "train_runtime": 111400.3813, "train_tokens_per_second": 10692.924 }, { "epoch": 1.9475491516294103, "grad_norm": 0.9656604817767291, "learning_rate": 1.7004065700168547e-08, "loss": 0.2853408336639404, "num_input_tokens_seen": 1191404264, "step": 28925, "train_runtime": 111418.6457, "train_tokens_per_second": 10693.042 }, { "epoch": 1.9478858066253704, "grad_norm": 0.6777124876136035, "learning_rate": 1.6786885254954644e-08, "loss": 0.297095513343811, "num_input_tokens_seen": 1191623832, "step": 28930, "train_runtime": 111438.5629, "train_tokens_per_second": 10693.101 }, { "epoch": 1.9482224616213304, "grad_norm": 0.8043574982105793, "learning_rate": 1.6571098349398296e-08, "loss": 0.2928506374359131, "num_input_tokens_seen": 1191816656, "step": 28935, "train_runtime": 111456.292, "train_tokens_per_second": 10693.13 }, { "epoch": 1.9485591166172906, "grad_norm": 0.8156960840333797, "learning_rate": 1.635670504384346e-08, "loss": 0.31500060558319093, "num_input_tokens_seen": 1192009712, "step": 28940, "train_runtime": 111476.7387, "train_tokens_per_second": 10692.901 }, { "epoch": 1.948895771613251, "grad_norm": 1.035229728967924, "learning_rate": 1.6143705398243837e-08, "loss": 0.28920209407806396, "num_input_tokens_seen": 1192205152, "step": 28945, "train_runtime": 111497.012, "train_tokens_per_second": 10692.709 }, { "epoch": 1.949232426609211, "grad_norm": 0.7787371434929179, "learning_rate": 1.5932099472165674e-08, "loss": 0.293032169342041, "num_input_tokens_seen": 1192403920, "step": 28950, "train_runtime": 111515.8343, "train_tokens_per_second": 10692.687 }, { "epoch": 1.949569081605171, "grad_norm": 0.7321574333214932, "learning_rate": 1.572188732478164e-08, "loss": 0.2918828010559082, "num_input_tokens_seen": 1192620856, "step": 28955, "train_runtime": 111535.5408, "train_tokens_per_second": 10692.743 }, { "epoch": 1.9499057366011312, "grad_norm": 0.7192760635387455, "learning_rate": 1.551306901487859e-08, "loss": 0.3043519973754883, "num_input_tokens_seen": 1192824152, "step": 28960, "train_runtime": 111555.8701, "train_tokens_per_second": 10692.617 }, { "epoch": 1.9502423915970915, "grad_norm": 0.654061933653328, "learning_rate": 1.5305644600852043e-08, "loss": 0.2758917331695557, "num_input_tokens_seen": 1193039752, "step": 28965, "train_runtime": 111574.983, "train_tokens_per_second": 10692.717 }, { "epoch": 1.9505790465930515, "grad_norm": 0.711019801772596, "learning_rate": 1.5099614140706154e-08, "loss": 0.2862734079360962, "num_input_tokens_seen": 1193245848, "step": 28970, "train_runtime": 111596.32, "train_tokens_per_second": 10692.52 }, { "epoch": 1.9509157015890115, "grad_norm": 0.7263393484200671, "learning_rate": 1.489497769205761e-08, "loss": 0.3112738609313965, "num_input_tokens_seen": 1193442840, "step": 28975, "train_runtime": 111616.8912, "train_tokens_per_second": 10692.314 }, { "epoch": 1.9512523565849718, "grad_norm": 0.6683480263042376, "learning_rate": 1.4691735312132304e-08, "loss": 0.2891531944274902, "num_input_tokens_seen": 1193658032, "step": 28980, "train_runtime": 111637.1342, "train_tokens_per_second": 10692.303 }, { "epoch": 1.951589011580932, "grad_norm": 0.7370489507384917, "learning_rate": 1.4489887057766439e-08, "loss": 0.30303192138671875, "num_input_tokens_seen": 1193863224, "step": 28985, "train_runtime": 111656.4507, "train_tokens_per_second": 10692.291 }, { "epoch": 1.951925666576892, "grad_norm": 0.6682123394204477, "learning_rate": 1.428943298540597e-08, "loss": 0.2913183689117432, "num_input_tokens_seen": 1194074456, "step": 28990, "train_runtime": 111674.9881, "train_tokens_per_second": 10692.407 }, { "epoch": 1.952262321572852, "grad_norm": 0.6659244141479588, "learning_rate": 1.4090373151107173e-08, "loss": 0.31016294956207274, "num_input_tokens_seen": 1194286376, "step": 28995, "train_runtime": 111693.5336, "train_tokens_per_second": 10692.529 }, { "epoch": 1.9525989765688123, "grad_norm": 0.6991082620821649, "learning_rate": 1.3892707610536627e-08, "loss": 0.2572926998138428, "num_input_tokens_seen": 1194483936, "step": 29000, "train_runtime": 111713.1873, "train_tokens_per_second": 10692.417 }, { "epoch": 1.9529356315647726, "grad_norm": 0.7448856908776794, "learning_rate": 1.3696436418970672e-08, "loss": 0.2825974225997925, "num_input_tokens_seen": 1194687880, "step": 29005, "train_runtime": 111733.2024, "train_tokens_per_second": 10692.326 }, { "epoch": 1.9532722865607326, "grad_norm": 0.7876217142701475, "learning_rate": 1.3501559631296512e-08, "loss": 0.31710474491119384, "num_input_tokens_seen": 1194884296, "step": 29010, "train_runtime": 111754.6314, "train_tokens_per_second": 10692.034 }, { "epoch": 1.9536089415566926, "grad_norm": 0.7247099956868163, "learning_rate": 1.3308077302010557e-08, "loss": 0.3144548416137695, "num_input_tokens_seen": 1195102424, "step": 29015, "train_runtime": 111773.3519, "train_tokens_per_second": 10692.195 }, { "epoch": 1.9539455965526529, "grad_norm": 0.7683319050739567, "learning_rate": 1.3115989485218972e-08, "loss": 0.3013054370880127, "num_input_tokens_seen": 1195297408, "step": 29020, "train_runtime": 111792.3095, "train_tokens_per_second": 10692.126 }, { "epoch": 1.9542822515486131, "grad_norm": 0.7690094600608736, "learning_rate": 1.2925296234638784e-08, "loss": 0.2805083990097046, "num_input_tokens_seen": 1195502216, "step": 29025, "train_runtime": 111812.2196, "train_tokens_per_second": 10692.053 }, { "epoch": 1.9546189065445732, "grad_norm": 0.6947377098473657, "learning_rate": 1.2735997603597339e-08, "loss": 0.2981600761413574, "num_input_tokens_seen": 1195721416, "step": 29030, "train_runtime": 111830.698, "train_tokens_per_second": 10692.247 }, { "epoch": 1.9549555615405332, "grad_norm": 0.7304999823168484, "learning_rate": 1.2548093645030623e-08, "loss": 0.29490420818328855, "num_input_tokens_seen": 1195936784, "step": 29035, "train_runtime": 111850.4964, "train_tokens_per_second": 10692.28 }, { "epoch": 1.9552922165364934, "grad_norm": 0.7248066571889219, "learning_rate": 1.236158441148605e-08, "loss": 0.28997485637664794, "num_input_tokens_seen": 1196149248, "step": 29040, "train_runtime": 111869.2041, "train_tokens_per_second": 10692.391 }, { "epoch": 1.9556288715324537, "grad_norm": 0.7460378438547092, "learning_rate": 1.2176469955119119e-08, "loss": 0.32675371170043943, "num_input_tokens_seen": 1196364392, "step": 29045, "train_runtime": 111888.5498, "train_tokens_per_second": 10692.465 }, { "epoch": 1.9559655265284137, "grad_norm": 0.8067505246391169, "learning_rate": 1.199275032769842e-08, "loss": 0.31903491020202634, "num_input_tokens_seen": 1196574384, "step": 29050, "train_runtime": 111907.5059, "train_tokens_per_second": 10692.53 }, { "epoch": 1.9563021815243737, "grad_norm": 0.7783375929427078, "learning_rate": 1.1810425580598971e-08, "loss": 0.3276975631713867, "num_input_tokens_seen": 1196791864, "step": 29055, "train_runtime": 111926.9614, "train_tokens_per_second": 10692.615 }, { "epoch": 1.956638836520334, "grad_norm": 0.8118588739566905, "learning_rate": 1.1629495764807763e-08, "loss": 0.30114796161651614, "num_input_tokens_seen": 1197011928, "step": 29060, "train_runtime": 111947.1608, "train_tokens_per_second": 10692.651 }, { "epoch": 1.9569754915162942, "grad_norm": 0.7307703260484604, "learning_rate": 1.1449960930921544e-08, "loss": 0.29733402729034425, "num_input_tokens_seen": 1197213000, "step": 29065, "train_runtime": 111966.6251, "train_tokens_per_second": 10692.588 }, { "epoch": 1.9573121465122543, "grad_norm": 0.7271802674432294, "learning_rate": 1.1271821129146266e-08, "loss": 0.28048751354217527, "num_input_tokens_seen": 1197421448, "step": 29070, "train_runtime": 111984.5517, "train_tokens_per_second": 10692.738 }, { "epoch": 1.9576488015082143, "grad_norm": 0.798994872880539, "learning_rate": 1.1095076409298189e-08, "loss": 0.2881986856460571, "num_input_tokens_seen": 1197621208, "step": 29075, "train_runtime": 112003.1234, "train_tokens_per_second": 10692.748 }, { "epoch": 1.9579854565041745, "grad_norm": 0.7698181992288091, "learning_rate": 1.0919726820803889e-08, "loss": 0.2888026714324951, "num_input_tokens_seen": 1197821760, "step": 29080, "train_runtime": 112022.564, "train_tokens_per_second": 10692.683 }, { "epoch": 1.9583221115001348, "grad_norm": 0.7036387105257155, "learning_rate": 1.0745772412698585e-08, "loss": 0.2912430763244629, "num_input_tokens_seen": 1198022880, "step": 29085, "train_runtime": 112043.7896, "train_tokens_per_second": 10692.452 }, { "epoch": 1.9586587664960948, "grad_norm": 0.7193851534995729, "learning_rate": 1.057321323362892e-08, "loss": 0.28659610748291015, "num_input_tokens_seen": 1198241584, "step": 29090, "train_runtime": 112063.3484, "train_tokens_per_second": 10692.538 }, { "epoch": 1.9589954214920549, "grad_norm": 0.70199732239555, "learning_rate": 1.0402049331849629e-08, "loss": 0.2934147357940674, "num_input_tokens_seen": 1198449744, "step": 29095, "train_runtime": 112081.4259, "train_tokens_per_second": 10692.67 }, { "epoch": 1.959332076488015, "grad_norm": 0.7465813743942098, "learning_rate": 1.0232280755226865e-08, "loss": 0.30575778484344485, "num_input_tokens_seen": 1198654280, "step": 29100, "train_runtime": 112100.7144, "train_tokens_per_second": 10692.655 }, { "epoch": 1.9596687314839754, "grad_norm": 0.6606913054639348, "learning_rate": 1.006390755123543e-08, "loss": 0.2884057521820068, "num_input_tokens_seen": 1198857744, "step": 29105, "train_runtime": 112120.5527, "train_tokens_per_second": 10692.578 }, { "epoch": 1.9600053864799354, "grad_norm": 0.8061078800148627, "learning_rate": 9.89692976696044e-09, "loss": 0.3127633333206177, "num_input_tokens_seen": 1199061936, "step": 29110, "train_runtime": 112142.3754, "train_tokens_per_second": 10692.318 }, { "epoch": 1.9603420414758954, "grad_norm": 0.6621507992336286, "learning_rate": 9.731347449097316e-09, "loss": 0.3154993772506714, "num_input_tokens_seen": 1199270728, "step": 29115, "train_runtime": 112161.5223, "train_tokens_per_second": 10692.354 }, { "epoch": 1.9606786964718557, "grad_norm": 0.7426155525173861, "learning_rate": 9.56716064394958e-09, "loss": 0.3076958656311035, "num_input_tokens_seen": 1199482920, "step": 29120, "train_runtime": 112179.9545, "train_tokens_per_second": 10692.489 }, { "epoch": 1.961015351467816, "grad_norm": 0.8377247449431305, "learning_rate": 9.404369397432166e-09, "loss": 0.2857853889465332, "num_input_tokens_seen": 1199686816, "step": 29125, "train_runtime": 112198.0549, "train_tokens_per_second": 10692.581 }, { "epoch": 1.961352006463776, "grad_norm": 0.7122410522129357, "learning_rate": 9.242973755068663e-09, "loss": 0.2953819751739502, "num_input_tokens_seen": 1199896648, "step": 29130, "train_runtime": 112217.3431, "train_tokens_per_second": 10692.613 }, { "epoch": 1.961688661459736, "grad_norm": 0.779489662574123, "learning_rate": 9.082973761993518e-09, "loss": 0.29818196296691896, "num_input_tokens_seen": 1200098808, "step": 29135, "train_runtime": 112238.481, "train_tokens_per_second": 10692.401 }, { "epoch": 1.9620253164556962, "grad_norm": 0.7818318325009618, "learning_rate": 8.924369462949834e-09, "loss": 0.32633023262023925, "num_input_tokens_seen": 1200292496, "step": 29140, "train_runtime": 112259.4212, "train_tokens_per_second": 10692.132 }, { "epoch": 1.9623619714516565, "grad_norm": 0.7484142018155835, "learning_rate": 8.767160902291016e-09, "loss": 0.30082223415374754, "num_input_tokens_seen": 1200497720, "step": 29145, "train_runtime": 112279.3431, "train_tokens_per_second": 10692.062 }, { "epoch": 1.9626986264476165, "grad_norm": 0.6996681379737479, "learning_rate": 8.61134812397968e-09, "loss": 0.29842190742492675, "num_input_tokens_seen": 1200704528, "step": 29150, "train_runtime": 112297.6757, "train_tokens_per_second": 10692.158 }, { "epoch": 1.9630352814435765, "grad_norm": 0.7414672700727041, "learning_rate": 8.45693117158819e-09, "loss": 0.27811739444732664, "num_input_tokens_seen": 1200899824, "step": 29155, "train_runtime": 112316.4703, "train_tokens_per_second": 10692.108 }, { "epoch": 1.9633719364395368, "grad_norm": 0.8053278454388606, "learning_rate": 8.303910088299228e-09, "loss": 0.289806604385376, "num_input_tokens_seen": 1201104752, "step": 29160, "train_runtime": 112335.3752, "train_tokens_per_second": 10692.133 }, { "epoch": 1.963708591435497, "grad_norm": 0.731668034227181, "learning_rate": 8.152284916904674e-09, "loss": 0.30056562423706057, "num_input_tokens_seen": 1201318904, "step": 29165, "train_runtime": 112354.3358, "train_tokens_per_second": 10692.234 }, { "epoch": 1.964045246431457, "grad_norm": 0.7287276263417908, "learning_rate": 8.002055699805612e-09, "loss": 0.28467986583709715, "num_input_tokens_seen": 1201520544, "step": 29170, "train_runtime": 112374.5724, "train_tokens_per_second": 10692.103 }, { "epoch": 1.964381901427417, "grad_norm": 0.7971910725852412, "learning_rate": 7.853222479013434e-09, "loss": 0.290664005279541, "num_input_tokens_seen": 1201742448, "step": 29175, "train_runtime": 112394.3178, "train_tokens_per_second": 10692.199 }, { "epoch": 1.9647185564233773, "grad_norm": 0.6577763630282105, "learning_rate": 7.705785296148737e-09, "loss": 0.2917932033538818, "num_input_tokens_seen": 1201945264, "step": 29180, "train_runtime": 112413.011, "train_tokens_per_second": 10692.226 }, { "epoch": 1.9650552114193376, "grad_norm": 0.7795555300690371, "learning_rate": 7.55974419244132e-09, "loss": 0.3106503486633301, "num_input_tokens_seen": 1202151960, "step": 29185, "train_runtime": 112431.0523, "train_tokens_per_second": 10692.348 }, { "epoch": 1.9653918664152976, "grad_norm": 0.6922227912831368, "learning_rate": 7.415099208732402e-09, "loss": 0.28123960494995115, "num_input_tokens_seen": 1202358392, "step": 29190, "train_runtime": 112449.3776, "train_tokens_per_second": 10692.442 }, { "epoch": 1.9657285214112576, "grad_norm": 0.6999724949854472, "learning_rate": 7.2718503854707355e-09, "loss": 0.3046185731887817, "num_input_tokens_seen": 1202570920, "step": 29195, "train_runtime": 112469.1569, "train_tokens_per_second": 10692.451 }, { "epoch": 1.966065176407218, "grad_norm": 0.7018347497089396, "learning_rate": 7.129997762715391e-09, "loss": 0.27210354804992676, "num_input_tokens_seen": 1202778648, "step": 29200, "train_runtime": 112486.8887, "train_tokens_per_second": 10692.612 }, { "epoch": 1.9664018314031781, "grad_norm": 0.7522142512400082, "learning_rate": 6.98954138013519e-09, "loss": 0.2897094964981079, "num_input_tokens_seen": 1202978088, "step": 29205, "train_runtime": 112505.7157, "train_tokens_per_second": 10692.595 }, { "epoch": 1.9667384863991382, "grad_norm": 0.7031107101337248, "learning_rate": 6.850481277008159e-09, "loss": 0.3032383918762207, "num_input_tokens_seen": 1203192792, "step": 29210, "train_runtime": 112525.7124, "train_tokens_per_second": 10692.603 }, { "epoch": 1.9670751413950982, "grad_norm": 0.7513499498697889, "learning_rate": 6.712817492222079e-09, "loss": 0.3199549436569214, "num_input_tokens_seen": 1203398528, "step": 29215, "train_runtime": 112544.1799, "train_tokens_per_second": 10692.677 }, { "epoch": 1.9674117963910585, "grad_norm": 0.849111169566201, "learning_rate": 6.576550064273934e-09, "loss": 0.299768328666687, "num_input_tokens_seen": 1203604848, "step": 29220, "train_runtime": 112563.3975, "train_tokens_per_second": 10692.684 }, { "epoch": 1.9677484513870187, "grad_norm": 0.6403062948256859, "learning_rate": 6.44167903127102e-09, "loss": 0.3060131072998047, "num_input_tokens_seen": 1203816336, "step": 29225, "train_runtime": 112584.9498, "train_tokens_per_second": 10692.516 }, { "epoch": 1.9680851063829787, "grad_norm": 0.7288790126447522, "learning_rate": 6.3082044309287215e-09, "loss": 0.28420989513397216, "num_input_tokens_seen": 1204026872, "step": 29230, "train_runtime": 112603.7146, "train_tokens_per_second": 10692.603 }, { "epoch": 1.9684217613789388, "grad_norm": 0.680322096090221, "learning_rate": 6.176126300573848e-09, "loss": 0.29647068977355956, "num_input_tokens_seen": 1204232688, "step": 29235, "train_runtime": 112624.5425, "train_tokens_per_second": 10692.454 }, { "epoch": 1.968758416374899, "grad_norm": 0.7284282170681994, "learning_rate": 6.045444677140744e-09, "loss": 0.27941231727600097, "num_input_tokens_seen": 1204445064, "step": 29240, "train_runtime": 112644.371, "train_tokens_per_second": 10692.457 }, { "epoch": 1.9690950713708593, "grad_norm": 0.7444805892625795, "learning_rate": 5.91615959717462e-09, "loss": 0.2924336910247803, "num_input_tokens_seen": 1204653216, "step": 29245, "train_runtime": 112662.0415, "train_tokens_per_second": 10692.627 }, { "epoch": 1.9694317263668193, "grad_norm": 0.6947072171147364, "learning_rate": 5.78827109682989e-09, "loss": 0.2694587707519531, "num_input_tokens_seen": 1204860080, "step": 29250, "train_runtime": 112680.2425, "train_tokens_per_second": 10692.736 }, { "epoch": 1.9697683813627793, "grad_norm": 0.701065728727167, "learning_rate": 5.661779211869056e-09, "loss": 0.28092341423034667, "num_input_tokens_seen": 1205064120, "step": 29255, "train_runtime": 112699.3432, "train_tokens_per_second": 10692.734 }, { "epoch": 1.9701050363587396, "grad_norm": 0.7457260379705605, "learning_rate": 5.536683977666601e-09, "loss": 0.30829682350158694, "num_input_tokens_seen": 1205281840, "step": 29260, "train_runtime": 112717.8425, "train_tokens_per_second": 10692.911 }, { "epoch": 1.9704416913546998, "grad_norm": 0.6508972029724228, "learning_rate": 5.412985429203988e-09, "loss": 0.28867497444152834, "num_input_tokens_seen": 1205482808, "step": 29265, "train_runtime": 112737.8248, "train_tokens_per_second": 10692.798 }, { "epoch": 1.9707783463506598, "grad_norm": 0.740426265480285, "learning_rate": 5.290683601073543e-09, "loss": 0.2887573719024658, "num_input_tokens_seen": 1205694248, "step": 29270, "train_runtime": 112756.2953, "train_tokens_per_second": 10692.922 }, { "epoch": 1.9711150013466199, "grad_norm": 0.7231237414607322, "learning_rate": 5.169778527476243e-09, "loss": 0.294691276550293, "num_input_tokens_seen": 1205906984, "step": 29275, "train_runtime": 112774.1313, "train_tokens_per_second": 10693.117 }, { "epoch": 1.9714516563425801, "grad_norm": 0.7888034980493843, "learning_rate": 5.050270242222821e-09, "loss": 0.31383647918701174, "num_input_tokens_seen": 1206096664, "step": 29280, "train_runtime": 112793.233, "train_tokens_per_second": 10692.988 }, { "epoch": 1.9717883113385404, "grad_norm": 0.7790131977150209, "learning_rate": 4.932158778733765e-09, "loss": 0.2877519130706787, "num_input_tokens_seen": 1206306736, "step": 29285, "train_runtime": 112812.4568, "train_tokens_per_second": 10693.028 }, { "epoch": 1.9721249663345004, "grad_norm": 0.8386674028252494, "learning_rate": 4.8154441700387636e-09, "loss": 0.31526756286621094, "num_input_tokens_seen": 1206495640, "step": 29290, "train_runtime": 112830.8702, "train_tokens_per_second": 10692.957 }, { "epoch": 1.9724616213304604, "grad_norm": 0.7264565192043484, "learning_rate": 4.7001264487761545e-09, "loss": 0.31388771533966064, "num_input_tokens_seen": 1206706064, "step": 29295, "train_runtime": 112850.4155, "train_tokens_per_second": 10692.97 }, { "epoch": 1.9727982763264207, "grad_norm": 0.6742887739505609, "learning_rate": 4.586205647194031e-09, "loss": 0.3138408660888672, "num_input_tokens_seen": 1206913952, "step": 29300, "train_runtime": 112868.9264, "train_tokens_per_second": 10693.058 }, { "epoch": 1.973134931322381, "grad_norm": 0.8855552921420387, "learning_rate": 4.4736817971507974e-09, "loss": 0.3049854040145874, "num_input_tokens_seen": 1207118240, "step": 29305, "train_runtime": 112888.2845, "train_tokens_per_second": 10693.034 }, { "epoch": 1.973471586318341, "grad_norm": 0.7964256791832194, "learning_rate": 4.362554930112395e-09, "loss": 0.30274786949157717, "num_input_tokens_seen": 1207319808, "step": 29310, "train_runtime": 112905.9163, "train_tokens_per_second": 10693.149 }, { "epoch": 1.973808241314301, "grad_norm": 0.6883990435207794, "learning_rate": 4.252825077155631e-09, "loss": 0.2895658493041992, "num_input_tokens_seen": 1207527352, "step": 29315, "train_runtime": 112925.1426, "train_tokens_per_second": 10693.167 }, { "epoch": 1.9741448963102612, "grad_norm": 0.7311126461690867, "learning_rate": 4.1444922689665156e-09, "loss": 0.29823861122131345, "num_input_tokens_seen": 1207728856, "step": 29320, "train_runtime": 112944.4404, "train_tokens_per_second": 10693.124 }, { "epoch": 1.9744815513062215, "grad_norm": 0.7961874464443148, "learning_rate": 4.037556535839149e-09, "loss": 0.26604452133178713, "num_input_tokens_seen": 1207936160, "step": 29325, "train_runtime": 112962.7776, "train_tokens_per_second": 10693.223 }, { "epoch": 1.9748182063021815, "grad_norm": 0.6724439916257773, "learning_rate": 3.932017907677943e-09, "loss": 0.28085641860961913, "num_input_tokens_seen": 1208151024, "step": 29330, "train_runtime": 112980.9021, "train_tokens_per_second": 10693.409 }, { "epoch": 1.9751548612981416, "grad_norm": 0.6969347076693486, "learning_rate": 3.827876413997067e-09, "loss": 0.31205670833587645, "num_input_tokens_seen": 1208337536, "step": 29335, "train_runtime": 112998.3364, "train_tokens_per_second": 10693.41 }, { "epoch": 1.9754915162941018, "grad_norm": 0.7809780024287827, "learning_rate": 3.725132083918781e-09, "loss": 0.2927842617034912, "num_input_tokens_seen": 1208535088, "step": 29340, "train_runtime": 113019.6175, "train_tokens_per_second": 10693.144 }, { "epoch": 1.975828171290062, "grad_norm": 0.7023081332636698, "learning_rate": 3.623784946175102e-09, "loss": 0.3094215154647827, "num_input_tokens_seen": 1208727208, "step": 29345, "train_runtime": 113038.7729, "train_tokens_per_second": 10693.032 }, { "epoch": 1.976164826286022, "grad_norm": 0.692065880721466, "learning_rate": 3.5238350291083577e-09, "loss": 0.280277681350708, "num_input_tokens_seen": 1208923408, "step": 29350, "train_runtime": 113058.2678, "train_tokens_per_second": 10692.923 }, { "epoch": 1.976501481281982, "grad_norm": 0.6932907999752114, "learning_rate": 3.4252823606678588e-09, "loss": 0.316843843460083, "num_input_tokens_seen": 1209134680, "step": 29355, "train_runtime": 113076.0043, "train_tokens_per_second": 10693.115 }, { "epoch": 1.9768381362779424, "grad_norm": 0.7396157040308902, "learning_rate": 3.328126968414336e-09, "loss": 0.3061677932739258, "num_input_tokens_seen": 1209321064, "step": 29360, "train_runtime": 113094.6818, "train_tokens_per_second": 10692.997 }, { "epoch": 1.9771747912739026, "grad_norm": 0.7121669739125052, "learning_rate": 3.232368879517167e-09, "loss": 0.31612043380737304, "num_input_tokens_seen": 1209530016, "step": 29365, "train_runtime": 113115.1403, "train_tokens_per_second": 10692.91 }, { "epoch": 1.9775114462698626, "grad_norm": 0.7946479961943397, "learning_rate": 3.1380081207543766e-09, "loss": 0.27659149169921876, "num_input_tokens_seen": 1209731376, "step": 29370, "train_runtime": 113133.2359, "train_tokens_per_second": 10692.98 }, { "epoch": 1.9778481012658227, "grad_norm": 0.7905572914804984, "learning_rate": 3.0450447185137454e-09, "loss": 0.3060769081115723, "num_input_tokens_seen": 1209932048, "step": 29375, "train_runtime": 113154.0594, "train_tokens_per_second": 10692.785 }, { "epoch": 1.978184756261783, "grad_norm": 0.7614882087840632, "learning_rate": 2.953478698792256e-09, "loss": 0.29476151466369627, "num_input_tokens_seen": 1210146136, "step": 29380, "train_runtime": 113173.6213, "train_tokens_per_second": 10692.829 }, { "epoch": 1.9785214112577432, "grad_norm": 0.7781771271399703, "learning_rate": 2.8633100871960917e-09, "loss": 0.28174529075622556, "num_input_tokens_seen": 1210341464, "step": 29385, "train_runtime": 113191.8391, "train_tokens_per_second": 10692.833 }, { "epoch": 1.9788580662537032, "grad_norm": 0.7822442070423811, "learning_rate": 2.774538908940638e-09, "loss": 0.30196146965026854, "num_input_tokens_seen": 1210539072, "step": 29390, "train_runtime": 113210.6094, "train_tokens_per_second": 10692.806 }, { "epoch": 1.9791947212496632, "grad_norm": 0.6941980213770228, "learning_rate": 2.687165188849927e-09, "loss": 0.2949812889099121, "num_input_tokens_seen": 1210752456, "step": 29395, "train_runtime": 113228.9128, "train_tokens_per_second": 10692.962 }, { "epoch": 1.9795313762456235, "grad_norm": 0.7408714316310859, "learning_rate": 2.6011889513588574e-09, "loss": 0.2875296831130981, "num_input_tokens_seen": 1210956480, "step": 29400, "train_runtime": 113248.7971, "train_tokens_per_second": 10692.886 }, { "epoch": 1.9798680312415837, "grad_norm": 0.740774207971415, "learning_rate": 2.5166102205093077e-09, "loss": 0.3066087245941162, "num_input_tokens_seen": 1211166080, "step": 29405, "train_runtime": 113266.6445, "train_tokens_per_second": 10693.052 }, { "epoch": 1.9802046862375438, "grad_norm": 0.7864063482055834, "learning_rate": 2.4334290199540254e-09, "loss": 0.298319149017334, "num_input_tokens_seen": 1211375064, "step": 29410, "train_runtime": 113287.5942, "train_tokens_per_second": 10692.919 }, { "epoch": 1.9805413412335038, "grad_norm": 0.7080952702416141, "learning_rate": 2.351645372953848e-09, "loss": 0.2775014877319336, "num_input_tokens_seen": 1211578480, "step": 29415, "train_runtime": 113307.4388, "train_tokens_per_second": 10692.841 }, { "epoch": 1.980877996229464, "grad_norm": 0.79144526775015, "learning_rate": 2.2712593023804795e-09, "loss": 0.2949090480804443, "num_input_tokens_seen": 1211774920, "step": 29420, "train_runtime": 113324.912, "train_tokens_per_second": 10692.926 }, { "epoch": 1.9812146512254243, "grad_norm": 0.6940805055418279, "learning_rate": 2.1922708307120512e-09, "loss": 0.2992425441741943, "num_input_tokens_seen": 1211981424, "step": 29425, "train_runtime": 113347.125, "train_tokens_per_second": 10692.653 }, { "epoch": 1.9815513062213843, "grad_norm": 0.7159077034039266, "learning_rate": 2.1146799800386698e-09, "loss": 0.32199959754943847, "num_input_tokens_seen": 1212187720, "step": 29430, "train_runtime": 113365.9664, "train_tokens_per_second": 10692.695 }, { "epoch": 1.9818879612173443, "grad_norm": 0.7777282893864637, "learning_rate": 2.0384867720579794e-09, "loss": 0.2806693553924561, "num_input_tokens_seen": 1212382304, "step": 29435, "train_runtime": 113385.2947, "train_tokens_per_second": 10692.589 }, { "epoch": 1.9822246162133046, "grad_norm": 0.7438184925990878, "learning_rate": 1.96369122807738e-09, "loss": 0.3016960620880127, "num_input_tokens_seen": 1212595696, "step": 29440, "train_runtime": 113403.312, "train_tokens_per_second": 10692.771 }, { "epoch": 1.9825612712092648, "grad_norm": 0.7758379394473573, "learning_rate": 1.8902933690123637e-09, "loss": 0.2780677318572998, "num_input_tokens_seen": 1212800232, "step": 29445, "train_runtime": 113420.9908, "train_tokens_per_second": 10692.908 }, { "epoch": 1.9828979262052249, "grad_norm": 0.7638948170223442, "learning_rate": 1.8182932153892884e-09, "loss": 0.29865574836730957, "num_input_tokens_seen": 1213006576, "step": 29450, "train_runtime": 113441.1027, "train_tokens_per_second": 10692.831 }, { "epoch": 1.983234581201185, "grad_norm": 0.7956107913760966, "learning_rate": 1.7476907873426041e-09, "loss": 0.2912738800048828, "num_input_tokens_seen": 1213218176, "step": 29455, "train_runtime": 113460.8489, "train_tokens_per_second": 10692.835 }, { "epoch": 1.9835712361971451, "grad_norm": 0.68560138030883, "learning_rate": 1.6784861046159617e-09, "loss": 0.2967612028121948, "num_input_tokens_seen": 1213427688, "step": 29460, "train_runtime": 113480.834, "train_tokens_per_second": 10692.798 }, { "epoch": 1.9839078911931054, "grad_norm": 0.6747413167074118, "learning_rate": 1.610679186561659e-09, "loss": 0.3040454864501953, "num_input_tokens_seen": 1213635960, "step": 29465, "train_runtime": 113500.9444, "train_tokens_per_second": 10692.739 }, { "epoch": 1.9842445461890654, "grad_norm": 0.649579398533009, "learning_rate": 1.5442700521428599e-09, "loss": 0.2688948154449463, "num_input_tokens_seen": 1213835824, "step": 29470, "train_runtime": 113521.3616, "train_tokens_per_second": 10692.576 }, { "epoch": 1.9845812011850255, "grad_norm": 0.7411698265249144, "learning_rate": 1.4792587199297103e-09, "loss": 0.2879544734954834, "num_input_tokens_seen": 1214046528, "step": 29475, "train_runtime": 113542.3916, "train_tokens_per_second": 10692.452 }, { "epoch": 1.9849178561809857, "grad_norm": 0.8241488498333289, "learning_rate": 1.4156452081026672e-09, "loss": 0.31122124195098877, "num_input_tokens_seen": 1214259064, "step": 29480, "train_runtime": 113563.2294, "train_tokens_per_second": 10692.361 }, { "epoch": 1.985254511176946, "grad_norm": 0.8012173311915141, "learning_rate": 1.3534295344513893e-09, "loss": 0.2977353572845459, "num_input_tokens_seen": 1214471984, "step": 29485, "train_runtime": 113582.5078, "train_tokens_per_second": 10692.421 }, { "epoch": 1.985591166172906, "grad_norm": 0.7786614951638078, "learning_rate": 1.2926117163741813e-09, "loss": 0.2866343021392822, "num_input_tokens_seen": 1214680872, "step": 29490, "train_runtime": 113602.7597, "train_tokens_per_second": 10692.354 }, { "epoch": 1.985927821168866, "grad_norm": 0.7181887375790907, "learning_rate": 1.233191770877995e-09, "loss": 0.30398690700531006, "num_input_tokens_seen": 1214888752, "step": 29495, "train_runtime": 113622.8592, "train_tokens_per_second": 10692.292 }, { "epoch": 1.9862644761648263, "grad_norm": 0.742053584828907, "learning_rate": 1.1751697145800934e-09, "loss": 0.2861011266708374, "num_input_tokens_seen": 1215100776, "step": 29500, "train_runtime": 113641.7298, "train_tokens_per_second": 10692.382 }, { "epoch": 1.9866011311607865, "grad_norm": 0.7795568139145512, "learning_rate": 1.1185455637052756e-09, "loss": 0.33814253807067873, "num_input_tokens_seen": 1215313520, "step": 29505, "train_runtime": 113660.2396, "train_tokens_per_second": 10692.512 }, { "epoch": 1.9869377861567465, "grad_norm": 0.7911047046152049, "learning_rate": 1.063319334089763e-09, "loss": 0.3035390853881836, "num_input_tokens_seen": 1215515592, "step": 29510, "train_runtime": 113680.3575, "train_tokens_per_second": 10692.398 }, { "epoch": 1.9872744411527066, "grad_norm": 0.7664476787468792, "learning_rate": 1.0094910411762027e-09, "loss": 0.278767991065979, "num_input_tokens_seen": 1215724776, "step": 29515, "train_runtime": 113700.8281, "train_tokens_per_second": 10692.312 }, { "epoch": 1.9876110961486668, "grad_norm": 0.8412585852454774, "learning_rate": 9.570607000175536e-10, "loss": 0.31874980926513674, "num_input_tokens_seen": 1215931192, "step": 29520, "train_runtime": 113721.6127, "train_tokens_per_second": 10692.173 }, { "epoch": 1.987947751144627, "grad_norm": 0.857606578797875, "learning_rate": 9.060283252765311e-10, "loss": 0.29208760261535643, "num_input_tokens_seen": 1216132040, "step": 29525, "train_runtime": 113742.5074, "train_tokens_per_second": 10691.975 }, { "epoch": 1.988284406140587, "grad_norm": 0.701333659612413, "learning_rate": 8.563939312233871e-10, "loss": 0.279740047454834, "num_input_tokens_seen": 1216333240, "step": 29530, "train_runtime": 113761.1823, "train_tokens_per_second": 10691.988 }, { "epoch": 1.9886210611365471, "grad_norm": 0.7317790818816396, "learning_rate": 8.081575317386847e-10, "loss": 0.30320034027099607, "num_input_tokens_seen": 1216542120, "step": 29535, "train_runtime": 113780.1898, "train_tokens_per_second": 10692.038 }, { "epoch": 1.9889577161325074, "grad_norm": 0.7075052971753272, "learning_rate": 7.613191403116338e-10, "loss": 0.30790760517120364, "num_input_tokens_seen": 1216754200, "step": 29540, "train_runtime": 113798.6694, "train_tokens_per_second": 10692.165 }, { "epoch": 1.9892943711284676, "grad_norm": 0.7305844509593611, "learning_rate": 7.158787700400905e-10, "loss": 0.30919270515441893, "num_input_tokens_seen": 1216969432, "step": 29545, "train_runtime": 113817.9492, "train_tokens_per_second": 10692.245 }, { "epoch": 1.9896310261244277, "grad_norm": 0.7126085958863091, "learning_rate": 6.718364336316674e-10, "loss": 0.2900279998779297, "num_input_tokens_seen": 1217178984, "step": 29550, "train_runtime": 113837.8734, "train_tokens_per_second": 10692.215 }, { "epoch": 1.9899676811203877, "grad_norm": 0.7361908673292479, "learning_rate": 6.291921434026238e-10, "loss": 0.2916138172149658, "num_input_tokens_seen": 1217388248, "step": 29555, "train_runtime": 113857.4718, "train_tokens_per_second": 10692.212 }, { "epoch": 1.990304336116348, "grad_norm": 0.6182871030054192, "learning_rate": 5.879459112778651e-10, "loss": 0.27405080795288084, "num_input_tokens_seen": 1217585016, "step": 29560, "train_runtime": 113877.7165, "train_tokens_per_second": 10692.039 }, { "epoch": 1.9906409911123082, "grad_norm": 0.6818943123785648, "learning_rate": 5.480977487920536e-10, "loss": 0.3108879566192627, "num_input_tokens_seen": 1217804408, "step": 29565, "train_runtime": 113896.5626, "train_tokens_per_second": 10692.196 }, { "epoch": 1.9909776461082682, "grad_norm": 0.6986718380646855, "learning_rate": 5.096476670890526e-10, "loss": 0.2923633098602295, "num_input_tokens_seen": 1218012416, "step": 29570, "train_runtime": 113917.6887, "train_tokens_per_second": 10692.039 }, { "epoch": 1.9913143011042282, "grad_norm": 0.7663474774273445, "learning_rate": 4.725956769202622e-10, "loss": 0.30362844467163086, "num_input_tokens_seen": 1218211576, "step": 29575, "train_runtime": 113936.846, "train_tokens_per_second": 10691.99 }, { "epoch": 1.9916509561001885, "grad_norm": 0.708286090057978, "learning_rate": 4.369417886485039e-10, "loss": 0.30016241073608396, "num_input_tokens_seen": 1218408928, "step": 29580, "train_runtime": 113956.8993, "train_tokens_per_second": 10691.84 }, { "epoch": 1.9919876110961487, "grad_norm": 0.7126295535260984, "learning_rate": 4.026860122430254e-10, "loss": 0.29035468101501466, "num_input_tokens_seen": 1218617944, "step": 29585, "train_runtime": 113975.3727, "train_tokens_per_second": 10691.941 }, { "epoch": 1.9923242660921088, "grad_norm": 0.7637050806447334, "learning_rate": 3.698283572839412e-10, "loss": 0.3025479316711426, "num_input_tokens_seen": 1218826392, "step": 29590, "train_runtime": 113994.2663, "train_tokens_per_second": 10691.997 }, { "epoch": 1.9926609210880688, "grad_norm": 0.8335952217411139, "learning_rate": 3.38368832959457e-10, "loss": 0.29154167175292967, "num_input_tokens_seen": 1219020896, "step": 29595, "train_runtime": 114013.7995, "train_tokens_per_second": 10691.872 }, { "epoch": 1.992997576084029, "grad_norm": 0.7947599968788132, "learning_rate": 3.0830744806753523e-10, "loss": 0.29865546226501466, "num_input_tokens_seen": 1219225136, "step": 29600, "train_runtime": 114032.9096, "train_tokens_per_second": 10691.871 }, { "epoch": 1.9933342310799893, "grad_norm": 0.7615415177060743, "learning_rate": 2.7964421101478457e-10, "loss": 0.2872196912765503, "num_input_tokens_seen": 1219421328, "step": 29605, "train_runtime": 114050.5879, "train_tokens_per_second": 10691.934 }, { "epoch": 1.9936708860759493, "grad_norm": 0.6953519473768419, "learning_rate": 2.5237912981646016e-10, "loss": 0.3028742790222168, "num_input_tokens_seen": 1219625680, "step": 29610, "train_runtime": 114069.5107, "train_tokens_per_second": 10691.952 }, { "epoch": 1.9940075410719094, "grad_norm": 0.8205778613839902, "learning_rate": 2.265122120975738e-10, "loss": 0.2854419231414795, "num_input_tokens_seen": 1219826128, "step": 29615, "train_runtime": 114090.1433, "train_tokens_per_second": 10691.775 }, { "epoch": 1.9943441960678696, "grad_norm": 0.6759216121371189, "learning_rate": 2.020434650906733e-10, "loss": 0.29778637886047366, "num_input_tokens_seen": 1220035792, "step": 29620, "train_runtime": 114109.4332, "train_tokens_per_second": 10691.805 }, { "epoch": 1.9946808510638299, "grad_norm": 0.709422245943155, "learning_rate": 1.7897289563972854e-10, "loss": 0.2894426822662354, "num_input_tokens_seen": 1220253744, "step": 29625, "train_runtime": 114128.2004, "train_tokens_per_second": 10691.956 }, { "epoch": 1.99501750605979, "grad_norm": 0.723766671134275, "learning_rate": 1.5730051019569037e-10, "loss": 0.285392165184021, "num_input_tokens_seen": 1220455928, "step": 29630, "train_runtime": 114147.5782, "train_tokens_per_second": 10691.913 }, { "epoch": 1.99535416105575, "grad_norm": 0.6905988259275109, "learning_rate": 1.3702631481926633e-10, "loss": 0.2872457027435303, "num_input_tokens_seen": 1220661896, "step": 29635, "train_runtime": 114165.6376, "train_tokens_per_second": 10692.025 }, { "epoch": 1.9956908160517102, "grad_norm": 0.7400452189988714, "learning_rate": 1.1815031517981023e-10, "loss": 0.2905673265457153, "num_input_tokens_seen": 1220851400, "step": 29640, "train_runtime": 114183.3557, "train_tokens_per_second": 10692.026 }, { "epoch": 1.9960274710476704, "grad_norm": 0.7021115624406421, "learning_rate": 1.0067251655643262e-10, "loss": 0.2781172037124634, "num_input_tokens_seen": 1221064928, "step": 29645, "train_runtime": 114202.7828, "train_tokens_per_second": 10692.077 }, { "epoch": 1.9963641260436304, "grad_norm": 0.7996956606819676, "learning_rate": 8.459292383633522e-11, "loss": 0.2937340021133423, "num_input_tokens_seen": 1221258360, "step": 29650, "train_runtime": 114222.4587, "train_tokens_per_second": 10691.928 }, { "epoch": 1.9967007810395905, "grad_norm": 0.7715365505840709, "learning_rate": 6.991154151592128e-11, "loss": 0.28460543155670165, "num_input_tokens_seen": 1221456488, "step": 29655, "train_runtime": 114242.5395, "train_tokens_per_second": 10691.783 }, { "epoch": 1.9970374360355507, "grad_norm": 0.7262013564207801, "learning_rate": 5.662837370135066e-11, "loss": 0.3065640926361084, "num_input_tokens_seen": 1221669184, "step": 29660, "train_runtime": 114261.7541, "train_tokens_per_second": 10691.847 }, { "epoch": 1.997374091031511, "grad_norm": 0.7841599674666847, "learning_rate": 4.47434241074296e-11, "loss": 0.30481157302856443, "num_input_tokens_seen": 1221868256, "step": 29665, "train_runtime": 114279.6031, "train_tokens_per_second": 10691.919 }, { "epoch": 1.997710746027471, "grad_norm": 0.8760509686372914, "learning_rate": 3.4256696057055615e-11, "loss": 0.3033610820770264, "num_input_tokens_seen": 1222070672, "step": 29670, "train_runtime": 114300.5592, "train_tokens_per_second": 10691.73 }, { "epoch": 1.998047401023431, "grad_norm": 0.7781467686755718, "learning_rate": 2.5168192482882824e-11, "loss": 0.30757961273193357, "num_input_tokens_seen": 1222279752, "step": 29675, "train_runtime": 114319.5292, "train_tokens_per_second": 10691.784 }, { "epoch": 1.9983840560193913, "grad_norm": 0.7469737012716313, "learning_rate": 1.747791592676684e-11, "loss": 0.2707680702209473, "num_input_tokens_seen": 1222501960, "step": 29680, "train_runtime": 114338.4047, "train_tokens_per_second": 10691.963 }, { "epoch": 1.9987207110153515, "grad_norm": 0.7196398409605063, "learning_rate": 1.1185868539209665e-11, "loss": 0.30005204677581787, "num_input_tokens_seen": 1222700104, "step": 29685, "train_runtime": 114356.4583, "train_tokens_per_second": 10692.007 }, { "epoch": 1.9990573660113116, "grad_norm": 0.7595112154795203, "learning_rate": 6.29205207991479e-12, "loss": 0.2989821434020996, "num_input_tokens_seen": 1222892496, "step": 29690, "train_runtime": 114374.4445, "train_tokens_per_second": 10692.008 }, { "epoch": 1.9993940210072716, "grad_norm": 0.7509635642848308, "learning_rate": 2.7964679166769815e-12, "loss": 0.2897747278213501, "num_input_tokens_seen": 1223100256, "step": 29695, "train_runtime": 114393.8334, "train_tokens_per_second": 10692.012 }, { "epoch": 1.9997306760032318, "grad_norm": 0.7983268645171185, "learning_rate": 6.991170281578364e-13, "loss": 0.2559999942779541, "num_input_tokens_seen": 1223296488, "step": 29700, "train_runtime": 114412.5318, "train_tokens_per_second": 10691.98 }, { "epoch": 2.0, "num_input_tokens_seen": 1223460320, "step": 29704, "total_flos": 2262599001948160.0, "train_loss": 0.3480319225768853, "train_runtime": 114584.0471, "train_samples_per_second": 1.037, "train_steps_per_second": 0.259 } ], "logging_steps": 5, "max_steps": 29704, "num_input_tokens_seen": 1223460320, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2262599001948160.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }