{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.2481317141522653, "eval_steps": 500, "global_step": 8500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.919196637085474e-05, "grad_norm": 3.253763198852539, "learning_rate": 0.0, "loss": 0.4384, "step": 1 }, { "epoch": 5.838393274170948e-05, "grad_norm": 3.232410430908203, "learning_rate": 2.9188558085230592e-09, "loss": 0.4035, "step": 2 }, { "epoch": 8.757589911256423e-05, "grad_norm": 2.9930222034454346, "learning_rate": 5.8377116170461185e-09, "loss": 0.3996, "step": 3 }, { "epoch": 0.00011676786548341896, "grad_norm": 2.9095542430877686, "learning_rate": 8.756567425569178e-09, "loss": 0.3702, "step": 4 }, { "epoch": 0.0001459598318542737, "grad_norm": 3.707209348678589, "learning_rate": 1.1675423234092237e-08, "loss": 0.4293, "step": 5 }, { "epoch": 0.00017515179822512846, "grad_norm": 2.9176390171051025, "learning_rate": 1.4594279042615296e-08, "loss": 0.4204, "step": 6 }, { "epoch": 0.00020434376459598318, "grad_norm": 3.471895933151245, "learning_rate": 1.7513134851138356e-08, "loss": 0.3575, "step": 7 }, { "epoch": 0.00023353573096683791, "grad_norm": 3.1231250762939453, "learning_rate": 2.0431990659661415e-08, "loss": 0.4177, "step": 8 }, { "epoch": 0.00026272769733769267, "grad_norm": 3.517387866973877, "learning_rate": 2.3350846468184474e-08, "loss": 0.4664, "step": 9 }, { "epoch": 0.0002919196637085474, "grad_norm": 3.1319544315338135, "learning_rate": 2.6269702276707533e-08, "loss": 0.436, "step": 10 }, { "epoch": 0.00032111163007940213, "grad_norm": 5.176347255706787, "learning_rate": 2.918855808523059e-08, "loss": 0.4525, "step": 11 }, { "epoch": 0.0003503035964502569, "grad_norm": 3.7868685722351074, "learning_rate": 3.210741389375365e-08, "loss": 0.4545, "step": 12 }, { "epoch": 0.00037949556282111164, "grad_norm": 2.9558708667755127, "learning_rate": 3.502626970227671e-08, "loss": 0.3695, "step": 13 }, { "epoch": 0.00040868752919196637, "grad_norm": 3.1111505031585693, "learning_rate": 3.794512551079977e-08, "loss": 0.4177, "step": 14 }, { "epoch": 0.0004378794955628211, "grad_norm": 3.571023464202881, "learning_rate": 4.086398131932283e-08, "loss": 0.4169, "step": 15 }, { "epoch": 0.00046707146193367583, "grad_norm": 3.121920108795166, "learning_rate": 4.3782837127845886e-08, "loss": 0.3604, "step": 16 }, { "epoch": 0.0004962634283045306, "grad_norm": 3.197615146636963, "learning_rate": 4.670169293636895e-08, "loss": 0.4315, "step": 17 }, { "epoch": 0.0005254553946753853, "grad_norm": 4.092521667480469, "learning_rate": 4.962054874489201e-08, "loss": 0.3667, "step": 18 }, { "epoch": 0.0005546473610462401, "grad_norm": 3.2151150703430176, "learning_rate": 5.2539404553415065e-08, "loss": 0.4591, "step": 19 }, { "epoch": 0.0005838393274170948, "grad_norm": 6.288403511047363, "learning_rate": 5.545826036193813e-08, "loss": 0.4135, "step": 20 }, { "epoch": 0.0006130312937879496, "grad_norm": 3.7934393882751465, "learning_rate": 5.837711617046118e-08, "loss": 0.4912, "step": 21 }, { "epoch": 0.0006422232601588043, "grad_norm": 2.974414825439453, "learning_rate": 6.129597197898424e-08, "loss": 0.3954, "step": 22 }, { "epoch": 0.000671415226529659, "grad_norm": 3.5364139080047607, "learning_rate": 6.42148277875073e-08, "loss": 0.4199, "step": 23 }, { "epoch": 0.0007006071929005138, "grad_norm": 4.272359848022461, "learning_rate": 6.713368359603036e-08, "loss": 0.3762, "step": 24 }, { "epoch": 0.0007297991592713685, "grad_norm": 3.359107494354248, "learning_rate": 7.005253940455342e-08, "loss": 0.4006, "step": 25 }, { "epoch": 0.0007589911256422233, "grad_norm": 3.5076427459716797, "learning_rate": 7.297139521307649e-08, "loss": 0.4106, "step": 26 }, { "epoch": 0.000788183092013078, "grad_norm": 3.199404716491699, "learning_rate": 7.589025102159954e-08, "loss": 0.3897, "step": 27 }, { "epoch": 0.0008173750583839327, "grad_norm": 3.4374802112579346, "learning_rate": 7.88091068301226e-08, "loss": 0.4747, "step": 28 }, { "epoch": 0.0008465670247547875, "grad_norm": 3.075533628463745, "learning_rate": 8.172796263864566e-08, "loss": 0.3599, "step": 29 }, { "epoch": 0.0008757589911256422, "grad_norm": 2.9556777477264404, "learning_rate": 8.464681844716872e-08, "loss": 0.3729, "step": 30 }, { "epoch": 0.000904950957496497, "grad_norm": 3.1111984252929688, "learning_rate": 8.756567425569177e-08, "loss": 0.4133, "step": 31 }, { "epoch": 0.0009341429238673517, "grad_norm": 3.6810057163238525, "learning_rate": 9.048453006421483e-08, "loss": 0.4289, "step": 32 }, { "epoch": 0.0009633348902382064, "grad_norm": 3.5205137729644775, "learning_rate": 9.34033858727379e-08, "loss": 0.4488, "step": 33 }, { "epoch": 0.0009925268566090611, "grad_norm": 3.5423312187194824, "learning_rate": 9.632224168126096e-08, "loss": 0.5033, "step": 34 }, { "epoch": 0.001021718822979916, "grad_norm": 3.109638214111328, "learning_rate": 9.924109748978402e-08, "loss": 0.4194, "step": 35 }, { "epoch": 0.0010509107893507707, "grad_norm": 3.37129807472229, "learning_rate": 1.0215995329830707e-07, "loss": 0.4519, "step": 36 }, { "epoch": 0.0010801027557216254, "grad_norm": 3.302353858947754, "learning_rate": 1.0507880910683013e-07, "loss": 0.4992, "step": 37 }, { "epoch": 0.0011092947220924802, "grad_norm": 2.845963716506958, "learning_rate": 1.0799766491535319e-07, "loss": 0.3771, "step": 38 }, { "epoch": 0.001138486688463335, "grad_norm": 3.1332225799560547, "learning_rate": 1.1091652072387625e-07, "loss": 0.4842, "step": 39 }, { "epoch": 0.0011676786548341896, "grad_norm": 3.3259119987487793, "learning_rate": 1.138353765323993e-07, "loss": 0.4367, "step": 40 }, { "epoch": 0.0011968706212050443, "grad_norm": 3.0589256286621094, "learning_rate": 1.1675423234092237e-07, "loss": 0.3879, "step": 41 }, { "epoch": 0.0012260625875758992, "grad_norm": 3.4503564834594727, "learning_rate": 1.1967308814944543e-07, "loss": 0.4361, "step": 42 }, { "epoch": 0.0012552545539467538, "grad_norm": 3.137117624282837, "learning_rate": 1.2259194395796848e-07, "loss": 0.3882, "step": 43 }, { "epoch": 0.0012844465203176085, "grad_norm": 3.2438597679138184, "learning_rate": 1.2551079976649155e-07, "loss": 0.3671, "step": 44 }, { "epoch": 0.0013136384866884634, "grad_norm": 2.4356689453125, "learning_rate": 1.284296555750146e-07, "loss": 0.4028, "step": 45 }, { "epoch": 0.001342830453059318, "grad_norm": 3.504063129425049, "learning_rate": 1.3134851138353768e-07, "loss": 0.5156, "step": 46 }, { "epoch": 0.0013720224194301728, "grad_norm": 3.06072735786438, "learning_rate": 1.3426736719206073e-07, "loss": 0.3918, "step": 47 }, { "epoch": 0.0014012143858010276, "grad_norm": 3.247130870819092, "learning_rate": 1.3718622300058377e-07, "loss": 0.4564, "step": 48 }, { "epoch": 0.0014304063521718823, "grad_norm": 2.8268518447875977, "learning_rate": 1.4010507880910685e-07, "loss": 0.4041, "step": 49 }, { "epoch": 0.001459598318542737, "grad_norm": 3.1831116676330566, "learning_rate": 1.430239346176299e-07, "loss": 0.4335, "step": 50 }, { "epoch": 0.0014887902849135919, "grad_norm": 3.2223169803619385, "learning_rate": 1.4594279042615297e-07, "loss": 0.4327, "step": 51 }, { "epoch": 0.0015179822512844466, "grad_norm": 3.362168312072754, "learning_rate": 1.4886164623467602e-07, "loss": 0.4465, "step": 52 }, { "epoch": 0.0015471742176553012, "grad_norm": 2.639658212661743, "learning_rate": 1.5178050204319907e-07, "loss": 0.406, "step": 53 }, { "epoch": 0.001576366184026156, "grad_norm": 2.9397900104522705, "learning_rate": 1.5469935785172215e-07, "loss": 0.4424, "step": 54 }, { "epoch": 0.0016055581503970108, "grad_norm": 4.377064228057861, "learning_rate": 1.576182136602452e-07, "loss": 0.4516, "step": 55 }, { "epoch": 0.0016347501167678655, "grad_norm": 2.810347318649292, "learning_rate": 1.6053706946876824e-07, "loss": 0.372, "step": 56 }, { "epoch": 0.0016639420831387202, "grad_norm": 2.7254161834716797, "learning_rate": 1.6345592527729132e-07, "loss": 0.4327, "step": 57 }, { "epoch": 0.001693134049509575, "grad_norm": 2.2067768573760986, "learning_rate": 1.6637478108581437e-07, "loss": 0.3819, "step": 58 }, { "epoch": 0.0017223260158804297, "grad_norm": 2.798175096511841, "learning_rate": 1.6929363689433744e-07, "loss": 0.4254, "step": 59 }, { "epoch": 0.0017515179822512844, "grad_norm": 2.896899461746216, "learning_rate": 1.722124927028605e-07, "loss": 0.4059, "step": 60 }, { "epoch": 0.0017807099486221393, "grad_norm": 2.648064613342285, "learning_rate": 1.7513134851138354e-07, "loss": 0.4179, "step": 61 }, { "epoch": 0.001809901914992994, "grad_norm": 2.8295252323150635, "learning_rate": 1.7805020431990662e-07, "loss": 0.4372, "step": 62 }, { "epoch": 0.0018390938813638486, "grad_norm": 2.6113836765289307, "learning_rate": 1.8096906012842967e-07, "loss": 0.3463, "step": 63 }, { "epoch": 0.0018682858477347033, "grad_norm": 2.533231496810913, "learning_rate": 1.8388791593695274e-07, "loss": 0.3649, "step": 64 }, { "epoch": 0.0018974778141055582, "grad_norm": 2.4169373512268066, "learning_rate": 1.868067717454758e-07, "loss": 0.377, "step": 65 }, { "epoch": 0.0019266697804764129, "grad_norm": 2.575723648071289, "learning_rate": 1.8972562755399884e-07, "loss": 0.3512, "step": 66 }, { "epoch": 0.0019558617468472678, "grad_norm": 2.8795199394226074, "learning_rate": 1.9264448336252192e-07, "loss": 0.4123, "step": 67 }, { "epoch": 0.0019850537132181222, "grad_norm": 2.55507755279541, "learning_rate": 1.9556333917104496e-07, "loss": 0.41, "step": 68 }, { "epoch": 0.002014245679588977, "grad_norm": 2.8309667110443115, "learning_rate": 1.9848219497956804e-07, "loss": 0.4217, "step": 69 }, { "epoch": 0.002043437645959832, "grad_norm": 2.5286812782287598, "learning_rate": 2.014010507880911e-07, "loss": 0.3932, "step": 70 }, { "epoch": 0.0020726296123306865, "grad_norm": 2.3271470069885254, "learning_rate": 2.0431990659661414e-07, "loss": 0.3771, "step": 71 }, { "epoch": 0.0021018215787015414, "grad_norm": 2.4817028045654297, "learning_rate": 2.072387624051372e-07, "loss": 0.3899, "step": 72 }, { "epoch": 0.0021310135450723963, "grad_norm": 2.6110270023345947, "learning_rate": 2.1015761821366026e-07, "loss": 0.4415, "step": 73 }, { "epoch": 0.0021602055114432507, "grad_norm": 2.4183671474456787, "learning_rate": 2.130764740221833e-07, "loss": 0.3945, "step": 74 }, { "epoch": 0.0021893974778141056, "grad_norm": 1.9257429838180542, "learning_rate": 2.1599532983070639e-07, "loss": 0.3578, "step": 75 }, { "epoch": 0.0022185894441849605, "grad_norm": 4.110969066619873, "learning_rate": 2.1891418563922943e-07, "loss": 0.4217, "step": 76 }, { "epoch": 0.002247781410555815, "grad_norm": 2.234574794769287, "learning_rate": 2.218330414477525e-07, "loss": 0.4164, "step": 77 }, { "epoch": 0.00227697337692667, "grad_norm": 1.5591657161712646, "learning_rate": 2.2475189725627556e-07, "loss": 0.3792, "step": 78 }, { "epoch": 0.0023061653432975247, "grad_norm": 2.972350835800171, "learning_rate": 2.276707530647986e-07, "loss": 0.3655, "step": 79 }, { "epoch": 0.002335357309668379, "grad_norm": 2.0097315311431885, "learning_rate": 2.3058960887332168e-07, "loss": 0.3751, "step": 80 }, { "epoch": 0.002364549276039234, "grad_norm": 9.850420951843262, "learning_rate": 2.3350846468184473e-07, "loss": 0.4278, "step": 81 }, { "epoch": 0.0023937412424100885, "grad_norm": 1.9521209001541138, "learning_rate": 2.364273204903678e-07, "loss": 0.4169, "step": 82 }, { "epoch": 0.0024229332087809434, "grad_norm": 1.5361061096191406, "learning_rate": 2.3934617629889086e-07, "loss": 0.3836, "step": 83 }, { "epoch": 0.0024521251751517983, "grad_norm": 1.876330852508545, "learning_rate": 2.4226503210741393e-07, "loss": 0.3885, "step": 84 }, { "epoch": 0.0024813171415226528, "grad_norm": 1.770538330078125, "learning_rate": 2.4518388791593695e-07, "loss": 0.4038, "step": 85 }, { "epoch": 0.0025105091078935077, "grad_norm": 2.085822582244873, "learning_rate": 2.4810274372446003e-07, "loss": 0.3835, "step": 86 }, { "epoch": 0.0025397010742643626, "grad_norm": 1.771301031112671, "learning_rate": 2.510215995329831e-07, "loss": 0.3491, "step": 87 }, { "epoch": 0.002568893040635217, "grad_norm": 1.8698935508728027, "learning_rate": 2.5394045534150613e-07, "loss": 0.3858, "step": 88 }, { "epoch": 0.002598085007006072, "grad_norm": 1.7197195291519165, "learning_rate": 2.568593111500292e-07, "loss": 0.4055, "step": 89 }, { "epoch": 0.002627276973376927, "grad_norm": 3.150951623916626, "learning_rate": 2.597781669585523e-07, "loss": 0.3963, "step": 90 }, { "epoch": 0.0026564689397477813, "grad_norm": 2.143348455429077, "learning_rate": 2.6269702276707535e-07, "loss": 0.3864, "step": 91 }, { "epoch": 0.002685660906118636, "grad_norm": 1.574230670928955, "learning_rate": 2.656158785755984e-07, "loss": 0.3567, "step": 92 }, { "epoch": 0.002714852872489491, "grad_norm": 2.0652353763580322, "learning_rate": 2.6853473438412145e-07, "loss": 0.3092, "step": 93 }, { "epoch": 0.0027440448388603455, "grad_norm": 1.7388883829116821, "learning_rate": 2.714535901926445e-07, "loss": 0.4214, "step": 94 }, { "epoch": 0.0027732368052312004, "grad_norm": 1.6928139925003052, "learning_rate": 2.7437244600116755e-07, "loss": 0.4021, "step": 95 }, { "epoch": 0.0028024287716020553, "grad_norm": 2.0101866722106934, "learning_rate": 2.772913018096906e-07, "loss": 0.3465, "step": 96 }, { "epoch": 0.0028316207379729097, "grad_norm": 1.7354997396469116, "learning_rate": 2.802101576182137e-07, "loss": 0.321, "step": 97 }, { "epoch": 0.0028608127043437646, "grad_norm": 1.2833030223846436, "learning_rate": 2.831290134267367e-07, "loss": 0.3508, "step": 98 }, { "epoch": 0.0028900046707146195, "grad_norm": 1.9458171129226685, "learning_rate": 2.860478692352598e-07, "loss": 0.3284, "step": 99 }, { "epoch": 0.002919196637085474, "grad_norm": 1.2258881330490112, "learning_rate": 2.8896672504378287e-07, "loss": 0.3048, "step": 100 }, { "epoch": 0.002948388603456329, "grad_norm": 1.4292488098144531, "learning_rate": 2.9188558085230595e-07, "loss": 0.3882, "step": 101 }, { "epoch": 0.0029775805698271838, "grad_norm": 2.198915481567383, "learning_rate": 2.9480443666082897e-07, "loss": 0.3969, "step": 102 }, { "epoch": 0.0030067725361980382, "grad_norm": 1.6783552169799805, "learning_rate": 2.9772329246935205e-07, "loss": 0.3379, "step": 103 }, { "epoch": 0.003035964502568893, "grad_norm": 1.0969667434692383, "learning_rate": 3.006421482778751e-07, "loss": 0.3498, "step": 104 }, { "epoch": 0.0030651564689397476, "grad_norm": 1.3606605529785156, "learning_rate": 3.0356100408639814e-07, "loss": 0.4153, "step": 105 }, { "epoch": 0.0030943484353106025, "grad_norm": 1.2530851364135742, "learning_rate": 3.064798598949212e-07, "loss": 0.3527, "step": 106 }, { "epoch": 0.0031235404016814574, "grad_norm": 1.1721932888031006, "learning_rate": 3.093987157034443e-07, "loss": 0.3571, "step": 107 }, { "epoch": 0.003152732368052312, "grad_norm": 1.0741304159164429, "learning_rate": 3.123175715119673e-07, "loss": 0.3232, "step": 108 }, { "epoch": 0.0031819243344231667, "grad_norm": 1.9813166856765747, "learning_rate": 3.152364273204904e-07, "loss": 0.3844, "step": 109 }, { "epoch": 0.0032111163007940216, "grad_norm": 1.5058143138885498, "learning_rate": 3.181552831290134e-07, "loss": 0.3426, "step": 110 }, { "epoch": 0.003240308267164876, "grad_norm": 1.0648778676986694, "learning_rate": 3.210741389375365e-07, "loss": 0.3752, "step": 111 }, { "epoch": 0.003269500233535731, "grad_norm": 0.9725266098976135, "learning_rate": 3.239929947460595e-07, "loss": 0.3507, "step": 112 }, { "epoch": 0.003298692199906586, "grad_norm": 0.9889642596244812, "learning_rate": 3.2691185055458264e-07, "loss": 0.3508, "step": 113 }, { "epoch": 0.0033278841662774403, "grad_norm": 0.9859651923179626, "learning_rate": 3.2983070636310566e-07, "loss": 0.3031, "step": 114 }, { "epoch": 0.003357076132648295, "grad_norm": 1.1448770761489868, "learning_rate": 3.3274956217162874e-07, "loss": 0.3331, "step": 115 }, { "epoch": 0.00338626809901915, "grad_norm": 1.3046393394470215, "learning_rate": 3.3566841798015176e-07, "loss": 0.3248, "step": 116 }, { "epoch": 0.0034154600653900045, "grad_norm": 1.4932116270065308, "learning_rate": 3.385872737886749e-07, "loss": 0.3452, "step": 117 }, { "epoch": 0.0034446520317608594, "grad_norm": 1.036775827407837, "learning_rate": 3.415061295971979e-07, "loss": 0.3853, "step": 118 }, { "epoch": 0.0034738439981317143, "grad_norm": 1.392801284790039, "learning_rate": 3.44424985405721e-07, "loss": 0.3356, "step": 119 }, { "epoch": 0.003503035964502569, "grad_norm": 1.358550786972046, "learning_rate": 3.47343841214244e-07, "loss": 0.3328, "step": 120 }, { "epoch": 0.0035322279308734237, "grad_norm": 0.8763356804847717, "learning_rate": 3.502626970227671e-07, "loss": 0.3516, "step": 121 }, { "epoch": 0.0035614198972442786, "grad_norm": 1.1368739604949951, "learning_rate": 3.531815528312901e-07, "loss": 0.3311, "step": 122 }, { "epoch": 0.003590611863615133, "grad_norm": 1.5491137504577637, "learning_rate": 3.5610040863981324e-07, "loss": 0.3322, "step": 123 }, { "epoch": 0.003619803829985988, "grad_norm": 1.4954379796981812, "learning_rate": 3.5901926444833626e-07, "loss": 0.3283, "step": 124 }, { "epoch": 0.003648995796356843, "grad_norm": 1.795778512954712, "learning_rate": 3.6193812025685933e-07, "loss": 0.3399, "step": 125 }, { "epoch": 0.0036781877627276973, "grad_norm": 1.3705323934555054, "learning_rate": 3.6485697606538236e-07, "loss": 0.4382, "step": 126 }, { "epoch": 0.003707379729098552, "grad_norm": 1.4359776973724365, "learning_rate": 3.677758318739055e-07, "loss": 0.3458, "step": 127 }, { "epoch": 0.0037365716954694066, "grad_norm": 1.7919903993606567, "learning_rate": 3.706946876824285e-07, "loss": 0.3573, "step": 128 }, { "epoch": 0.0037657636618402615, "grad_norm": 1.0313708782196045, "learning_rate": 3.736135434909516e-07, "loss": 0.3528, "step": 129 }, { "epoch": 0.0037949556282111164, "grad_norm": 1.92235267162323, "learning_rate": 3.765323992994746e-07, "loss": 0.3853, "step": 130 }, { "epoch": 0.003824147594581971, "grad_norm": 1.5343955755233765, "learning_rate": 3.794512551079977e-07, "loss": 0.3243, "step": 131 }, { "epoch": 0.0038533395609528258, "grad_norm": 0.8613026142120361, "learning_rate": 3.823701109165207e-07, "loss": 0.3624, "step": 132 }, { "epoch": 0.0038825315273236806, "grad_norm": 0.9648137092590332, "learning_rate": 3.8528896672504383e-07, "loss": 0.3151, "step": 133 }, { "epoch": 0.0039117234936945355, "grad_norm": 0.7552794814109802, "learning_rate": 3.8820782253356685e-07, "loss": 0.3135, "step": 134 }, { "epoch": 0.00394091546006539, "grad_norm": 0.8979153633117676, "learning_rate": 3.9112667834208993e-07, "loss": 0.3413, "step": 135 }, { "epoch": 0.0039701074264362445, "grad_norm": 0.7630147337913513, "learning_rate": 3.9404553415061295e-07, "loss": 0.3302, "step": 136 }, { "epoch": 0.0039992993928071, "grad_norm": 1.0652612447738647, "learning_rate": 3.969643899591361e-07, "loss": 0.3088, "step": 137 }, { "epoch": 0.004028491359177954, "grad_norm": 0.8046591877937317, "learning_rate": 3.998832457676591e-07, "loss": 0.3275, "step": 138 }, { "epoch": 0.004057683325548809, "grad_norm": 1.3640562295913696, "learning_rate": 4.028021015761822e-07, "loss": 0.3302, "step": 139 }, { "epoch": 0.004086875291919664, "grad_norm": 1.2027623653411865, "learning_rate": 4.057209573847052e-07, "loss": 0.3272, "step": 140 }, { "epoch": 0.0041160672582905185, "grad_norm": 1.1852232217788696, "learning_rate": 4.086398131932283e-07, "loss": 0.3808, "step": 141 }, { "epoch": 0.004145259224661373, "grad_norm": 1.4646902084350586, "learning_rate": 4.115586690017513e-07, "loss": 0.2703, "step": 142 }, { "epoch": 0.004174451191032228, "grad_norm": 0.8278629183769226, "learning_rate": 4.144775248102744e-07, "loss": 0.3442, "step": 143 }, { "epoch": 0.004203643157403083, "grad_norm": 1.4551981687545776, "learning_rate": 4.1739638061879745e-07, "loss": 0.3849, "step": 144 }, { "epoch": 0.004232835123773937, "grad_norm": 1.2958778142929077, "learning_rate": 4.203152364273205e-07, "loss": 0.3588, "step": 145 }, { "epoch": 0.0042620270901447925, "grad_norm": 1.3782662153244019, "learning_rate": 4.2323409223584355e-07, "loss": 0.391, "step": 146 }, { "epoch": 0.004291219056515647, "grad_norm": 1.8233325481414795, "learning_rate": 4.261529480443666e-07, "loss": 0.3255, "step": 147 }, { "epoch": 0.004320411022886501, "grad_norm": 0.9293618202209473, "learning_rate": 4.290718038528897e-07, "loss": 0.3319, "step": 148 }, { "epoch": 0.004349602989257357, "grad_norm": 1.01087486743927, "learning_rate": 4.3199065966141277e-07, "loss": 0.3116, "step": 149 }, { "epoch": 0.004378794955628211, "grad_norm": 0.7973979711532593, "learning_rate": 4.349095154699358e-07, "loss": 0.2993, "step": 150 }, { "epoch": 0.004407986921999066, "grad_norm": 1.1870194673538208, "learning_rate": 4.3782837127845887e-07, "loss": 0.404, "step": 151 }, { "epoch": 0.004437178888369921, "grad_norm": 1.091627597808838, "learning_rate": 4.407472270869819e-07, "loss": 0.3599, "step": 152 }, { "epoch": 0.0044663708547407754, "grad_norm": 1.2990412712097168, "learning_rate": 4.43666082895505e-07, "loss": 0.3093, "step": 153 }, { "epoch": 0.00449556282111163, "grad_norm": 0.8098524212837219, "learning_rate": 4.4658493870402804e-07, "loss": 0.2441, "step": 154 }, { "epoch": 0.004524754787482485, "grad_norm": 0.8084087371826172, "learning_rate": 4.495037945125511e-07, "loss": 0.3073, "step": 155 }, { "epoch": 0.00455394675385334, "grad_norm": 0.8314881920814514, "learning_rate": 4.5242265032107414e-07, "loss": 0.3044, "step": 156 }, { "epoch": 0.004583138720224194, "grad_norm": 0.9202438592910767, "learning_rate": 4.553415061295972e-07, "loss": 0.3087, "step": 157 }, { "epoch": 0.0046123306865950495, "grad_norm": 0.6748988628387451, "learning_rate": 4.5826036193812024e-07, "loss": 0.3304, "step": 158 }, { "epoch": 0.004641522652965904, "grad_norm": 0.889873206615448, "learning_rate": 4.6117921774664337e-07, "loss": 0.3217, "step": 159 }, { "epoch": 0.004670714619336758, "grad_norm": 0.9595389366149902, "learning_rate": 4.640980735551664e-07, "loss": 0.3252, "step": 160 }, { "epoch": 0.004699906585707613, "grad_norm": 0.9378253221511841, "learning_rate": 4.6701692936368946e-07, "loss": 0.3005, "step": 161 }, { "epoch": 0.004729098552078468, "grad_norm": 0.8817343711853027, "learning_rate": 4.699357851722125e-07, "loss": 0.3137, "step": 162 }, { "epoch": 0.004758290518449323, "grad_norm": 0.814365804195404, "learning_rate": 4.728546409807356e-07, "loss": 0.2718, "step": 163 }, { "epoch": 0.004787482484820177, "grad_norm": 0.8074374794960022, "learning_rate": 4.7577349678925864e-07, "loss": 0.3461, "step": 164 }, { "epoch": 0.004816674451191032, "grad_norm": 1.2190598249435425, "learning_rate": 4.786923525977817e-07, "loss": 0.3231, "step": 165 }, { "epoch": 0.004845866417561887, "grad_norm": 0.7654194831848145, "learning_rate": 4.816112084063047e-07, "loss": 0.2856, "step": 166 }, { "epoch": 0.004875058383932741, "grad_norm": 0.7704591751098633, "learning_rate": 4.845300642148279e-07, "loss": 0.3104, "step": 167 }, { "epoch": 0.004904250350303597, "grad_norm": 3.5539698600769043, "learning_rate": 4.874489200233509e-07, "loss": 0.3734, "step": 168 }, { "epoch": 0.004933442316674451, "grad_norm": 0.8007470369338989, "learning_rate": 4.903677758318739e-07, "loss": 0.3064, "step": 169 }, { "epoch": 0.0049626342830453056, "grad_norm": 0.861976146697998, "learning_rate": 4.932866316403969e-07, "loss": 0.3079, "step": 170 }, { "epoch": 0.004991826249416161, "grad_norm": 1.0884239673614502, "learning_rate": 4.962054874489201e-07, "loss": 0.3573, "step": 171 }, { "epoch": 0.005021018215787015, "grad_norm": 1.108737826347351, "learning_rate": 4.991243432574431e-07, "loss": 0.2842, "step": 172 }, { "epoch": 0.00505021018215787, "grad_norm": 1.0760679244995117, "learning_rate": 5.020431990659662e-07, "loss": 0.3068, "step": 173 }, { "epoch": 0.005079402148528725, "grad_norm": 0.9858543276786804, "learning_rate": 5.049620548744892e-07, "loss": 0.3132, "step": 174 }, { "epoch": 0.00510859411489958, "grad_norm": 1.3938764333724976, "learning_rate": 5.078809106830123e-07, "loss": 0.3197, "step": 175 }, { "epoch": 0.005137786081270434, "grad_norm": 1.0590518712997437, "learning_rate": 5.107997664915353e-07, "loss": 0.2398, "step": 176 }, { "epoch": 0.005166978047641289, "grad_norm": 1.0197386741638184, "learning_rate": 5.137186223000584e-07, "loss": 0.3198, "step": 177 }, { "epoch": 0.005196170014012144, "grad_norm": 0.9090692400932312, "learning_rate": 5.166374781085814e-07, "loss": 0.3368, "step": 178 }, { "epoch": 0.005225361980382998, "grad_norm": 0.9444124698638916, "learning_rate": 5.195563339171046e-07, "loss": 0.3342, "step": 179 }, { "epoch": 0.005254553946753854, "grad_norm": 0.8249809145927429, "learning_rate": 5.224751897256276e-07, "loss": 0.2769, "step": 180 }, { "epoch": 0.005283745913124708, "grad_norm": 0.8326698541641235, "learning_rate": 5.253940455341507e-07, "loss": 0.3079, "step": 181 }, { "epoch": 0.0053129378794955625, "grad_norm": 1.1595877408981323, "learning_rate": 5.283129013426737e-07, "loss": 0.3014, "step": 182 }, { "epoch": 0.005342129845866418, "grad_norm": 0.9315177202224731, "learning_rate": 5.312317571511968e-07, "loss": 0.2755, "step": 183 }, { "epoch": 0.005371321812237272, "grad_norm": 1.0849418640136719, "learning_rate": 5.341506129597198e-07, "loss": 0.3132, "step": 184 }, { "epoch": 0.005400513778608127, "grad_norm": 1.38004732131958, "learning_rate": 5.370694687682429e-07, "loss": 0.2864, "step": 185 }, { "epoch": 0.005429705744978982, "grad_norm": 0.7805374264717102, "learning_rate": 5.399883245767659e-07, "loss": 0.3451, "step": 186 }, { "epoch": 0.0054588977113498366, "grad_norm": 0.6063517332077026, "learning_rate": 5.42907180385289e-07, "loss": 0.3158, "step": 187 }, { "epoch": 0.005488089677720691, "grad_norm": 0.8187215924263, "learning_rate": 5.458260361938121e-07, "loss": 0.2966, "step": 188 }, { "epoch": 0.005517281644091546, "grad_norm": 0.7313492894172668, "learning_rate": 5.487448920023351e-07, "loss": 0.3192, "step": 189 }, { "epoch": 0.005546473610462401, "grad_norm": 1.0754899978637695, "learning_rate": 5.516637478108581e-07, "loss": 0.2899, "step": 190 }, { "epoch": 0.005575665576833255, "grad_norm": 1.1896650791168213, "learning_rate": 5.545826036193812e-07, "loss": 0.3024, "step": 191 }, { "epoch": 0.005604857543204111, "grad_norm": 0.7870485186576843, "learning_rate": 5.575014594279043e-07, "loss": 0.3385, "step": 192 }, { "epoch": 0.005634049509574965, "grad_norm": 1.2263846397399902, "learning_rate": 5.604203152364274e-07, "loss": 0.3519, "step": 193 }, { "epoch": 0.0056632414759458195, "grad_norm": 0.9082961082458496, "learning_rate": 5.633391710449504e-07, "loss": 0.3123, "step": 194 }, { "epoch": 0.005692433442316675, "grad_norm": 1.18455970287323, "learning_rate": 5.662580268534734e-07, "loss": 0.3279, "step": 195 }, { "epoch": 0.005721625408687529, "grad_norm": 1.3420954942703247, "learning_rate": 5.691768826619965e-07, "loss": 0.2815, "step": 196 }, { "epoch": 0.005750817375058384, "grad_norm": 0.6394249200820923, "learning_rate": 5.720957384705196e-07, "loss": 0.2788, "step": 197 }, { "epoch": 0.005780009341429239, "grad_norm": 1.2573682069778442, "learning_rate": 5.750145942790426e-07, "loss": 0.2736, "step": 198 }, { "epoch": 0.0058092013078000935, "grad_norm": 1.3950047492980957, "learning_rate": 5.779334500875657e-07, "loss": 0.3025, "step": 199 }, { "epoch": 0.005838393274170948, "grad_norm": 0.8407323360443115, "learning_rate": 5.808523058960888e-07, "loss": 0.34, "step": 200 }, { "epoch": 0.005867585240541803, "grad_norm": 0.7678521275520325, "learning_rate": 5.837711617046119e-07, "loss": 0.3259, "step": 201 }, { "epoch": 0.005896777206912658, "grad_norm": 0.7844319939613342, "learning_rate": 5.866900175131349e-07, "loss": 0.2246, "step": 202 }, { "epoch": 0.005925969173283512, "grad_norm": 0.7778900265693665, "learning_rate": 5.896088733216579e-07, "loss": 0.2796, "step": 203 }, { "epoch": 0.0059551611396543675, "grad_norm": 0.7624730467796326, "learning_rate": 5.92527729130181e-07, "loss": 0.3117, "step": 204 }, { "epoch": 0.005984353106025222, "grad_norm": 1.2478680610656738, "learning_rate": 5.954465849387041e-07, "loss": 0.3208, "step": 205 }, { "epoch": 0.0060135450723960765, "grad_norm": 0.7766502499580383, "learning_rate": 5.983654407472271e-07, "loss": 0.3497, "step": 206 }, { "epoch": 0.006042737038766931, "grad_norm": 0.7533957362174988, "learning_rate": 6.012842965557502e-07, "loss": 0.3219, "step": 207 }, { "epoch": 0.006071929005137786, "grad_norm": 0.7943652272224426, "learning_rate": 6.042031523642733e-07, "loss": 0.2637, "step": 208 }, { "epoch": 0.006101120971508641, "grad_norm": 2.199875831604004, "learning_rate": 6.071220081727963e-07, "loss": 0.3023, "step": 209 }, { "epoch": 0.006130312937879495, "grad_norm": 1.762034296989441, "learning_rate": 6.100408639813193e-07, "loss": 0.3028, "step": 210 }, { "epoch": 0.0061595049042503505, "grad_norm": 0.8351932764053345, "learning_rate": 6.129597197898424e-07, "loss": 0.3026, "step": 211 }, { "epoch": 0.006188696870621205, "grad_norm": 0.802747368812561, "learning_rate": 6.158785755983655e-07, "loss": 0.2742, "step": 212 }, { "epoch": 0.006217888836992059, "grad_norm": 0.7838931679725647, "learning_rate": 6.187974314068886e-07, "loss": 0.3113, "step": 213 }, { "epoch": 0.006247080803362915, "grad_norm": 1.0596017837524414, "learning_rate": 6.217162872154116e-07, "loss": 0.2779, "step": 214 }, { "epoch": 0.006276272769733769, "grad_norm": 1.0373151302337646, "learning_rate": 6.246351430239346e-07, "loss": 0.3336, "step": 215 }, { "epoch": 0.006305464736104624, "grad_norm": 0.8187100887298584, "learning_rate": 6.275539988324578e-07, "loss": 0.239, "step": 216 }, { "epoch": 0.006334656702475479, "grad_norm": 0.7277623414993286, "learning_rate": 6.304728546409808e-07, "loss": 0.3141, "step": 217 }, { "epoch": 0.006363848668846333, "grad_norm": 0.9251918196678162, "learning_rate": 6.333917104495038e-07, "loss": 0.3264, "step": 218 }, { "epoch": 0.006393040635217188, "grad_norm": 0.7817749381065369, "learning_rate": 6.363105662580268e-07, "loss": 0.2935, "step": 219 }, { "epoch": 0.006422232601588043, "grad_norm": 0.904636800289154, "learning_rate": 6.3922942206655e-07, "loss": 0.3209, "step": 220 }, { "epoch": 0.006451424567958898, "grad_norm": 0.8504090309143066, "learning_rate": 6.42148277875073e-07, "loss": 0.3153, "step": 221 }, { "epoch": 0.006480616534329752, "grad_norm": 2.0124049186706543, "learning_rate": 6.45067133683596e-07, "loss": 0.3244, "step": 222 }, { "epoch": 0.0065098085007006075, "grad_norm": 0.8407703638076782, "learning_rate": 6.47985989492119e-07, "loss": 0.321, "step": 223 }, { "epoch": 0.006539000467071462, "grad_norm": 0.9511666297912598, "learning_rate": 6.509048453006423e-07, "loss": 0.3562, "step": 224 }, { "epoch": 0.006568192433442316, "grad_norm": 0.6590362191200256, "learning_rate": 6.538237011091653e-07, "loss": 0.2756, "step": 225 }, { "epoch": 0.006597384399813172, "grad_norm": 1.0739803314208984, "learning_rate": 6.567425569176883e-07, "loss": 0.2416, "step": 226 }, { "epoch": 0.006626576366184026, "grad_norm": 0.7024247050285339, "learning_rate": 6.596614127262113e-07, "loss": 0.2975, "step": 227 }, { "epoch": 0.006655768332554881, "grad_norm": 1.2972664833068848, "learning_rate": 6.625802685347345e-07, "loss": 0.2898, "step": 228 }, { "epoch": 0.006684960298925736, "grad_norm": 1.4556267261505127, "learning_rate": 6.654991243432575e-07, "loss": 0.3133, "step": 229 }, { "epoch": 0.00671415226529659, "grad_norm": 1.0583109855651855, "learning_rate": 6.684179801517805e-07, "loss": 0.3646, "step": 230 }, { "epoch": 0.006743344231667445, "grad_norm": 1.1192712783813477, "learning_rate": 6.713368359603035e-07, "loss": 0.345, "step": 231 }, { "epoch": 0.0067725361980383, "grad_norm": 0.8593578934669495, "learning_rate": 6.742556917688268e-07, "loss": 0.3376, "step": 232 }, { "epoch": 0.006801728164409155, "grad_norm": 0.5778508186340332, "learning_rate": 6.771745475773498e-07, "loss": 0.2377, "step": 233 }, { "epoch": 0.006830920130780009, "grad_norm": 0.7493040561676025, "learning_rate": 6.800934033858728e-07, "loss": 0.278, "step": 234 }, { "epoch": 0.006860112097150864, "grad_norm": 1.2016149759292603, "learning_rate": 6.830122591943958e-07, "loss": 0.3022, "step": 235 }, { "epoch": 0.006889304063521719, "grad_norm": 1.2308056354522705, "learning_rate": 6.85931115002919e-07, "loss": 0.3379, "step": 236 }, { "epoch": 0.006918496029892573, "grad_norm": 1.4189995527267456, "learning_rate": 6.88849970811442e-07, "loss": 0.3338, "step": 237 }, { "epoch": 0.006947687996263429, "grad_norm": 1.483320951461792, "learning_rate": 6.91768826619965e-07, "loss": 0.3385, "step": 238 }, { "epoch": 0.006976879962634283, "grad_norm": 0.7089532017707825, "learning_rate": 6.94687682428488e-07, "loss": 0.3048, "step": 239 }, { "epoch": 0.007006071929005138, "grad_norm": 1.9768375158309937, "learning_rate": 6.976065382370111e-07, "loss": 0.3215, "step": 240 }, { "epoch": 0.007035263895375993, "grad_norm": 0.8070523738861084, "learning_rate": 7.005253940455342e-07, "loss": 0.345, "step": 241 }, { "epoch": 0.007064455861746847, "grad_norm": 0.9407985806465149, "learning_rate": 7.034442498540572e-07, "loss": 0.3314, "step": 242 }, { "epoch": 0.007093647828117702, "grad_norm": 0.7194987535476685, "learning_rate": 7.063631056625802e-07, "loss": 0.2765, "step": 243 }, { "epoch": 0.007122839794488557, "grad_norm": 1.8499643802642822, "learning_rate": 7.092819614711034e-07, "loss": 0.2462, "step": 244 }, { "epoch": 0.007152031760859412, "grad_norm": 0.6153528690338135, "learning_rate": 7.122008172796265e-07, "loss": 0.2158, "step": 245 }, { "epoch": 0.007181223727230266, "grad_norm": 0.7088429927825928, "learning_rate": 7.151196730881495e-07, "loss": 0.2674, "step": 246 }, { "epoch": 0.007210415693601121, "grad_norm": 0.5921630263328552, "learning_rate": 7.180385288966725e-07, "loss": 0.2751, "step": 247 }, { "epoch": 0.007239607659971976, "grad_norm": 0.6849388480186462, "learning_rate": 7.209573847051956e-07, "loss": 0.3168, "step": 248 }, { "epoch": 0.00726879962634283, "grad_norm": 0.6876950263977051, "learning_rate": 7.238762405137187e-07, "loss": 0.2814, "step": 249 }, { "epoch": 0.007297991592713686, "grad_norm": 1.221883773803711, "learning_rate": 7.267950963222417e-07, "loss": 0.2732, "step": 250 }, { "epoch": 0.00732718355908454, "grad_norm": 0.7054675817489624, "learning_rate": 7.297139521307647e-07, "loss": 0.3378, "step": 251 }, { "epoch": 0.0073563755254553945, "grad_norm": 0.7365065217018127, "learning_rate": 7.326328079392879e-07, "loss": 0.2859, "step": 252 }, { "epoch": 0.007385567491826249, "grad_norm": 0.7528605461120605, "learning_rate": 7.35551663747811e-07, "loss": 0.3173, "step": 253 }, { "epoch": 0.007414759458197104, "grad_norm": 0.998782753944397, "learning_rate": 7.38470519556334e-07, "loss": 0.3098, "step": 254 }, { "epoch": 0.007443951424567959, "grad_norm": 0.6801927089691162, "learning_rate": 7.41389375364857e-07, "loss": 0.3086, "step": 255 }, { "epoch": 0.007473143390938813, "grad_norm": 0.8796200156211853, "learning_rate": 7.443082311733801e-07, "loss": 0.3011, "step": 256 }, { "epoch": 0.0075023353573096686, "grad_norm": 0.7280615568161011, "learning_rate": 7.472270869819032e-07, "loss": 0.3056, "step": 257 }, { "epoch": 0.007531527323680523, "grad_norm": 0.9629148244857788, "learning_rate": 7.501459427904262e-07, "loss": 0.2884, "step": 258 }, { "epoch": 0.0075607192900513775, "grad_norm": 0.7705072164535522, "learning_rate": 7.530647985989492e-07, "loss": 0.2862, "step": 259 }, { "epoch": 0.007589911256422233, "grad_norm": 0.8461706042289734, "learning_rate": 7.559836544074723e-07, "loss": 0.3197, "step": 260 }, { "epoch": 0.007619103222793087, "grad_norm": 1.8972752094268799, "learning_rate": 7.589025102159954e-07, "loss": 0.3046, "step": 261 }, { "epoch": 0.007648295189163942, "grad_norm": 0.4997410476207733, "learning_rate": 7.618213660245184e-07, "loss": 0.2256, "step": 262 }, { "epoch": 0.007677487155534797, "grad_norm": 0.6859931945800781, "learning_rate": 7.647402218330414e-07, "loss": 0.2303, "step": 263 }, { "epoch": 0.0077066791219056515, "grad_norm": 0.6741688847541809, "learning_rate": 7.676590776415646e-07, "loss": 0.2282, "step": 264 }, { "epoch": 0.007735871088276506, "grad_norm": 1.1798663139343262, "learning_rate": 7.705779334500877e-07, "loss": 0.3065, "step": 265 }, { "epoch": 0.007765063054647361, "grad_norm": 1.247315526008606, "learning_rate": 7.734967892586107e-07, "loss": 0.2958, "step": 266 }, { "epoch": 0.007794255021018216, "grad_norm": 0.7195435762405396, "learning_rate": 7.764156450671337e-07, "loss": 0.3012, "step": 267 }, { "epoch": 0.007823446987389071, "grad_norm": 0.9292770624160767, "learning_rate": 7.793345008756568e-07, "loss": 0.3425, "step": 268 }, { "epoch": 0.007852638953759926, "grad_norm": 1.1149007081985474, "learning_rate": 7.822533566841799e-07, "loss": 0.2831, "step": 269 }, { "epoch": 0.00788183092013078, "grad_norm": 0.7083069682121277, "learning_rate": 7.851722124927029e-07, "loss": 0.275, "step": 270 }, { "epoch": 0.007911022886501634, "grad_norm": 0.9613978862762451, "learning_rate": 7.880910683012259e-07, "loss": 0.2612, "step": 271 }, { "epoch": 0.007940214852872489, "grad_norm": 0.823359489440918, "learning_rate": 7.910099241097491e-07, "loss": 0.3287, "step": 272 }, { "epoch": 0.007969406819243345, "grad_norm": 0.7788481116294861, "learning_rate": 7.939287799182722e-07, "loss": 0.2717, "step": 273 }, { "epoch": 0.0079985987856142, "grad_norm": 0.9120495319366455, "learning_rate": 7.968476357267952e-07, "loss": 0.2724, "step": 274 }, { "epoch": 0.008027790751985054, "grad_norm": 1.6399158239364624, "learning_rate": 7.997664915353182e-07, "loss": 0.2924, "step": 275 }, { "epoch": 0.008056982718355908, "grad_norm": 0.6664943695068359, "learning_rate": 8.026853473438413e-07, "loss": 0.2942, "step": 276 }, { "epoch": 0.008086174684726763, "grad_norm": 0.6490132212638855, "learning_rate": 8.056042031523644e-07, "loss": 0.26, "step": 277 }, { "epoch": 0.008115366651097617, "grad_norm": 1.5552364587783813, "learning_rate": 8.085230589608874e-07, "loss": 0.292, "step": 278 }, { "epoch": 0.008144558617468472, "grad_norm": 0.7825798988342285, "learning_rate": 8.114419147694104e-07, "loss": 0.3033, "step": 279 }, { "epoch": 0.008173750583839328, "grad_norm": 0.6622434854507446, "learning_rate": 8.143607705779335e-07, "loss": 0.3011, "step": 280 }, { "epoch": 0.008202942550210182, "grad_norm": 0.7466982007026672, "learning_rate": 8.172796263864565e-07, "loss": 0.2741, "step": 281 }, { "epoch": 0.008232134516581037, "grad_norm": 0.8227627277374268, "learning_rate": 8.201984821949796e-07, "loss": 0.2786, "step": 282 }, { "epoch": 0.008261326482951891, "grad_norm": 0.8095334768295288, "learning_rate": 8.231173380035026e-07, "loss": 0.258, "step": 283 }, { "epoch": 0.008290518449322746, "grad_norm": 0.7518879771232605, "learning_rate": 8.260361938120258e-07, "loss": 0.2559, "step": 284 }, { "epoch": 0.0083197104156936, "grad_norm": 0.8108356595039368, "learning_rate": 8.289550496205489e-07, "loss": 0.2537, "step": 285 }, { "epoch": 0.008348902382064457, "grad_norm": 1.0148894786834717, "learning_rate": 8.318739054290719e-07, "loss": 0.2678, "step": 286 }, { "epoch": 0.008378094348435311, "grad_norm": 0.6661762595176697, "learning_rate": 8.347927612375949e-07, "loss": 0.2779, "step": 287 }, { "epoch": 0.008407286314806165, "grad_norm": 0.9146678447723389, "learning_rate": 8.37711617046118e-07, "loss": 0.3084, "step": 288 }, { "epoch": 0.00843647828117702, "grad_norm": 0.9395344853401184, "learning_rate": 8.40630472854641e-07, "loss": 0.2838, "step": 289 }, { "epoch": 0.008465670247547874, "grad_norm": 1.3520128726959229, "learning_rate": 8.435493286631641e-07, "loss": 0.3497, "step": 290 }, { "epoch": 0.008494862213918729, "grad_norm": 0.6555407047271729, "learning_rate": 8.464681844716871e-07, "loss": 0.3005, "step": 291 }, { "epoch": 0.008524054180289585, "grad_norm": 0.6324545741081238, "learning_rate": 8.493870402802102e-07, "loss": 0.2265, "step": 292 }, { "epoch": 0.00855324614666044, "grad_norm": 0.7173523306846619, "learning_rate": 8.523058960887332e-07, "loss": 0.2741, "step": 293 }, { "epoch": 0.008582438113031294, "grad_norm": 0.6344001889228821, "learning_rate": 8.552247518972564e-07, "loss": 0.3012, "step": 294 }, { "epoch": 0.008611630079402148, "grad_norm": 0.7683945894241333, "learning_rate": 8.581436077057794e-07, "loss": 0.2688, "step": 295 }, { "epoch": 0.008640822045773003, "grad_norm": 0.7082907557487488, "learning_rate": 8.610624635143025e-07, "loss": 0.278, "step": 296 }, { "epoch": 0.008670014012143857, "grad_norm": 1.0008420944213867, "learning_rate": 8.639813193228255e-07, "loss": 0.2446, "step": 297 }, { "epoch": 0.008699205978514713, "grad_norm": 1.3691608905792236, "learning_rate": 8.669001751313486e-07, "loss": 0.2782, "step": 298 }, { "epoch": 0.008728397944885568, "grad_norm": 0.9400314092636108, "learning_rate": 8.698190309398716e-07, "loss": 0.2837, "step": 299 }, { "epoch": 0.008757589911256422, "grad_norm": 0.6880818009376526, "learning_rate": 8.727378867483947e-07, "loss": 0.2997, "step": 300 }, { "epoch": 0.008786781877627277, "grad_norm": 0.889866828918457, "learning_rate": 8.756567425569177e-07, "loss": 0.2971, "step": 301 }, { "epoch": 0.008815973843998131, "grad_norm": 0.8652124404907227, "learning_rate": 8.785755983654408e-07, "loss": 0.3506, "step": 302 }, { "epoch": 0.008845165810368986, "grad_norm": 0.751167893409729, "learning_rate": 8.814944541739638e-07, "loss": 0.277, "step": 303 }, { "epoch": 0.008874357776739842, "grad_norm": 0.7411856651306152, "learning_rate": 8.84413309982487e-07, "loss": 0.2802, "step": 304 }, { "epoch": 0.008903549743110696, "grad_norm": 1.1640340089797974, "learning_rate": 8.8733216579101e-07, "loss": 0.2881, "step": 305 }, { "epoch": 0.008932741709481551, "grad_norm": 0.8269346952438354, "learning_rate": 8.902510215995331e-07, "loss": 0.2563, "step": 306 }, { "epoch": 0.008961933675852405, "grad_norm": 0.6907421946525574, "learning_rate": 8.931698774080561e-07, "loss": 0.3191, "step": 307 }, { "epoch": 0.00899112564222326, "grad_norm": 0.9920339584350586, "learning_rate": 8.960887332165792e-07, "loss": 0.3031, "step": 308 }, { "epoch": 0.009020317608594114, "grad_norm": 14.09976863861084, "learning_rate": 8.990075890251022e-07, "loss": 0.2936, "step": 309 }, { "epoch": 0.00904950957496497, "grad_norm": 0.8302566409111023, "learning_rate": 9.019264448336253e-07, "loss": 0.2769, "step": 310 }, { "epoch": 0.009078701541335825, "grad_norm": 0.7116841673851013, "learning_rate": 9.048453006421483e-07, "loss": 0.3052, "step": 311 }, { "epoch": 0.00910789350770668, "grad_norm": 0.6163344383239746, "learning_rate": 9.077641564506714e-07, "loss": 0.2627, "step": 312 }, { "epoch": 0.009137085474077534, "grad_norm": 0.7701386213302612, "learning_rate": 9.106830122591944e-07, "loss": 0.3139, "step": 313 }, { "epoch": 0.009166277440448388, "grad_norm": 0.7820231914520264, "learning_rate": 9.136018680677175e-07, "loss": 0.3197, "step": 314 }, { "epoch": 0.009195469406819243, "grad_norm": 1.5264325141906738, "learning_rate": 9.165207238762405e-07, "loss": 0.2636, "step": 315 }, { "epoch": 0.009224661373190099, "grad_norm": 0.8174229264259338, "learning_rate": 9.194395796847637e-07, "loss": 0.3042, "step": 316 }, { "epoch": 0.009253853339560953, "grad_norm": 0.8924728035926819, "learning_rate": 9.223584354932867e-07, "loss": 0.2818, "step": 317 }, { "epoch": 0.009283045305931808, "grad_norm": 0.7203507423400879, "learning_rate": 9.252772913018098e-07, "loss": 0.2768, "step": 318 }, { "epoch": 0.009312237272302662, "grad_norm": 0.8100606203079224, "learning_rate": 9.281961471103328e-07, "loss": 0.2984, "step": 319 }, { "epoch": 0.009341429238673517, "grad_norm": 0.7229321599006653, "learning_rate": 9.311150029188559e-07, "loss": 0.2632, "step": 320 }, { "epoch": 0.009370621205044371, "grad_norm": 0.6815540790557861, "learning_rate": 9.340338587273789e-07, "loss": 0.2533, "step": 321 }, { "epoch": 0.009399813171415226, "grad_norm": 1.0034596920013428, "learning_rate": 9.36952714535902e-07, "loss": 0.3247, "step": 322 }, { "epoch": 0.009429005137786082, "grad_norm": 0.6958652138710022, "learning_rate": 9.39871570344425e-07, "loss": 0.2787, "step": 323 }, { "epoch": 0.009458197104156936, "grad_norm": 0.7483996748924255, "learning_rate": 9.427904261529482e-07, "loss": 0.2479, "step": 324 }, { "epoch": 0.00948738907052779, "grad_norm": 0.9079541563987732, "learning_rate": 9.457092819614712e-07, "loss": 0.3127, "step": 325 }, { "epoch": 0.009516581036898645, "grad_norm": 1.4656933546066284, "learning_rate": 9.486281377699943e-07, "loss": 0.3171, "step": 326 }, { "epoch": 0.0095457730032695, "grad_norm": 0.5971149206161499, "learning_rate": 9.515469935785173e-07, "loss": 0.2325, "step": 327 }, { "epoch": 0.009574964969640354, "grad_norm": 0.595319926738739, "learning_rate": 9.544658493870403e-07, "loss": 0.2932, "step": 328 }, { "epoch": 0.00960415693601121, "grad_norm": 0.7024241089820862, "learning_rate": 9.573847051955634e-07, "loss": 0.2548, "step": 329 }, { "epoch": 0.009633348902382065, "grad_norm": 0.7254247069358826, "learning_rate": 9.603035610040866e-07, "loss": 0.2912, "step": 330 }, { "epoch": 0.00966254086875292, "grad_norm": 0.708659827709198, "learning_rate": 9.632224168126095e-07, "loss": 0.283, "step": 331 }, { "epoch": 0.009691732835123774, "grad_norm": 0.814634382724762, "learning_rate": 9.661412726211326e-07, "loss": 0.3631, "step": 332 }, { "epoch": 0.009720924801494628, "grad_norm": 1.0627566576004028, "learning_rate": 9.690601284296557e-07, "loss": 0.3272, "step": 333 }, { "epoch": 0.009750116767865483, "grad_norm": 6.772002220153809, "learning_rate": 9.719789842381786e-07, "loss": 0.2737, "step": 334 }, { "epoch": 0.009779308734236339, "grad_norm": 0.9530158638954163, "learning_rate": 9.748978400467018e-07, "loss": 0.2878, "step": 335 }, { "epoch": 0.009808500700607193, "grad_norm": 0.691473126411438, "learning_rate": 9.77816695855225e-07, "loss": 0.2982, "step": 336 }, { "epoch": 0.009837692666978048, "grad_norm": 0.6706142425537109, "learning_rate": 9.807355516637478e-07, "loss": 0.3401, "step": 337 }, { "epoch": 0.009866884633348902, "grad_norm": 1.1859698295593262, "learning_rate": 9.83654407472271e-07, "loss": 0.298, "step": 338 }, { "epoch": 0.009896076599719757, "grad_norm": 1.1892173290252686, "learning_rate": 9.865732632807939e-07, "loss": 0.297, "step": 339 }, { "epoch": 0.009925268566090611, "grad_norm": 0.6831076145172119, "learning_rate": 9.894921190893172e-07, "loss": 0.3016, "step": 340 }, { "epoch": 0.009954460532461467, "grad_norm": 0.9495557546615601, "learning_rate": 9.924109748978401e-07, "loss": 0.3677, "step": 341 }, { "epoch": 0.009983652498832322, "grad_norm": 0.8085536956787109, "learning_rate": 9.953298307063632e-07, "loss": 0.2997, "step": 342 }, { "epoch": 0.010012844465203176, "grad_norm": 0.6241188645362854, "learning_rate": 9.982486865148862e-07, "loss": 0.2951, "step": 343 }, { "epoch": 0.01004203643157403, "grad_norm": 0.846206784248352, "learning_rate": 1.0011675423234093e-06, "loss": 0.3079, "step": 344 }, { "epoch": 0.010071228397944885, "grad_norm": 0.6606466770172119, "learning_rate": 1.0040863981319324e-06, "loss": 0.2498, "step": 345 }, { "epoch": 0.01010042036431574, "grad_norm": 1.413507342338562, "learning_rate": 1.0070052539404553e-06, "loss": 0.3259, "step": 346 }, { "epoch": 0.010129612330686596, "grad_norm": 0.6979807019233704, "learning_rate": 1.0099241097489785e-06, "loss": 0.3061, "step": 347 }, { "epoch": 0.01015880429705745, "grad_norm": 1.0315650701522827, "learning_rate": 1.0128429655575016e-06, "loss": 0.3049, "step": 348 }, { "epoch": 0.010187996263428305, "grad_norm": 0.5763014554977417, "learning_rate": 1.0157618213660245e-06, "loss": 0.2618, "step": 349 }, { "epoch": 0.01021718822979916, "grad_norm": 0.6016502380371094, "learning_rate": 1.0186806771745476e-06, "loss": 0.2644, "step": 350 }, { "epoch": 0.010246380196170014, "grad_norm": 0.8544628024101257, "learning_rate": 1.0215995329830706e-06, "loss": 0.2553, "step": 351 }, { "epoch": 0.010275572162540868, "grad_norm": 0.9520359635353088, "learning_rate": 1.0245183887915939e-06, "loss": 0.3403, "step": 352 }, { "epoch": 0.010304764128911724, "grad_norm": 0.6822605729103088, "learning_rate": 1.0274372446001168e-06, "loss": 0.3237, "step": 353 }, { "epoch": 0.010333956095282579, "grad_norm": 0.6373287439346313, "learning_rate": 1.03035610040864e-06, "loss": 0.2766, "step": 354 }, { "epoch": 0.010363148061653433, "grad_norm": 1.2530357837677002, "learning_rate": 1.0332749562171629e-06, "loss": 0.2807, "step": 355 }, { "epoch": 0.010392340028024288, "grad_norm": 0.6255794167518616, "learning_rate": 1.036193812025686e-06, "loss": 0.2636, "step": 356 }, { "epoch": 0.010421531994395142, "grad_norm": 0.7232959866523743, "learning_rate": 1.0391126678342091e-06, "loss": 0.3347, "step": 357 }, { "epoch": 0.010450723960765997, "grad_norm": 1.034412145614624, "learning_rate": 1.042031523642732e-06, "loss": 0.2686, "step": 358 }, { "epoch": 0.010479915927136853, "grad_norm": 0.8360500335693359, "learning_rate": 1.0449503794512552e-06, "loss": 0.2878, "step": 359 }, { "epoch": 0.010509107893507707, "grad_norm": 1.0093377828598022, "learning_rate": 1.0478692352597783e-06, "loss": 0.3243, "step": 360 }, { "epoch": 0.010538299859878562, "grad_norm": 0.7226967215538025, "learning_rate": 1.0507880910683014e-06, "loss": 0.3178, "step": 361 }, { "epoch": 0.010567491826249416, "grad_norm": 0.8673776388168335, "learning_rate": 1.0537069468768243e-06, "loss": 0.3197, "step": 362 }, { "epoch": 0.01059668379262027, "grad_norm": 1.0697392225265503, "learning_rate": 1.0566258026853475e-06, "loss": 0.3047, "step": 363 }, { "epoch": 0.010625875758991125, "grad_norm": 0.5817053914070129, "learning_rate": 1.0595446584938706e-06, "loss": 0.2642, "step": 364 }, { "epoch": 0.01065506772536198, "grad_norm": 0.54036945104599, "learning_rate": 1.0624635143023935e-06, "loss": 0.2463, "step": 365 }, { "epoch": 0.010684259691732836, "grad_norm": 0.928781270980835, "learning_rate": 1.0653823701109166e-06, "loss": 0.3172, "step": 366 }, { "epoch": 0.01071345165810369, "grad_norm": 0.8396477699279785, "learning_rate": 1.0683012259194395e-06, "loss": 0.3481, "step": 367 }, { "epoch": 0.010742643624474545, "grad_norm": 1.836045265197754, "learning_rate": 1.0712200817279627e-06, "loss": 0.2407, "step": 368 }, { "epoch": 0.010771835590845399, "grad_norm": 0.7796801924705505, "learning_rate": 1.0741389375364858e-06, "loss": 0.2679, "step": 369 }, { "epoch": 0.010801027557216254, "grad_norm": 0.8607455492019653, "learning_rate": 1.0770577933450087e-06, "loss": 0.3139, "step": 370 }, { "epoch": 0.010830219523587108, "grad_norm": 0.7355309724807739, "learning_rate": 1.0799766491535318e-06, "loss": 0.2956, "step": 371 }, { "epoch": 0.010859411489957964, "grad_norm": 0.6138611435890198, "learning_rate": 1.082895504962055e-06, "loss": 0.2898, "step": 372 }, { "epoch": 0.010888603456328819, "grad_norm": 0.6740755438804626, "learning_rate": 1.085814360770578e-06, "loss": 0.2628, "step": 373 }, { "epoch": 0.010917795422699673, "grad_norm": 0.7478241920471191, "learning_rate": 1.088733216579101e-06, "loss": 0.2785, "step": 374 }, { "epoch": 0.010946987389070528, "grad_norm": 0.6758588552474976, "learning_rate": 1.0916520723876242e-06, "loss": 0.3068, "step": 375 }, { "epoch": 0.010976179355441382, "grad_norm": 0.7070645093917847, "learning_rate": 1.0945709281961473e-06, "loss": 0.2932, "step": 376 }, { "epoch": 0.011005371321812236, "grad_norm": 0.7265928983688354, "learning_rate": 1.0974897840046702e-06, "loss": 0.359, "step": 377 }, { "epoch": 0.011034563288183093, "grad_norm": 0.9170693755149841, "learning_rate": 1.1004086398131933e-06, "loss": 0.3431, "step": 378 }, { "epoch": 0.011063755254553947, "grad_norm": 0.7732980847358704, "learning_rate": 1.1033274956217162e-06, "loss": 0.2964, "step": 379 }, { "epoch": 0.011092947220924802, "grad_norm": 1.0365886688232422, "learning_rate": 1.1062463514302396e-06, "loss": 0.2692, "step": 380 }, { "epoch": 0.011122139187295656, "grad_norm": 0.6484991312026978, "learning_rate": 1.1091652072387625e-06, "loss": 0.1991, "step": 381 }, { "epoch": 0.01115133115366651, "grad_norm": 0.7463474869728088, "learning_rate": 1.1120840630472856e-06, "loss": 0.2833, "step": 382 }, { "epoch": 0.011180523120037365, "grad_norm": 0.6710392832756042, "learning_rate": 1.1150029188558085e-06, "loss": 0.2525, "step": 383 }, { "epoch": 0.011209715086408221, "grad_norm": 1.0328960418701172, "learning_rate": 1.1179217746643317e-06, "loss": 0.2416, "step": 384 }, { "epoch": 0.011238907052779076, "grad_norm": 0.8745959401130676, "learning_rate": 1.1208406304728548e-06, "loss": 0.2717, "step": 385 }, { "epoch": 0.01126809901914993, "grad_norm": 0.5982735753059387, "learning_rate": 1.1237594862813777e-06, "loss": 0.2484, "step": 386 }, { "epoch": 0.011297290985520785, "grad_norm": 0.6567667126655579, "learning_rate": 1.1266783420899008e-06, "loss": 0.2796, "step": 387 }, { "epoch": 0.011326482951891639, "grad_norm": 1.616905689239502, "learning_rate": 1.129597197898424e-06, "loss": 0.3079, "step": 388 }, { "epoch": 0.011355674918262493, "grad_norm": 0.8249164819717407, "learning_rate": 1.1325160537069469e-06, "loss": 0.3177, "step": 389 }, { "epoch": 0.01138486688463335, "grad_norm": 0.8386092782020569, "learning_rate": 1.13543490951547e-06, "loss": 0.2783, "step": 390 }, { "epoch": 0.011414058851004204, "grad_norm": 0.6719471216201782, "learning_rate": 1.138353765323993e-06, "loss": 0.2554, "step": 391 }, { "epoch": 0.011443250817375059, "grad_norm": 0.7144614458084106, "learning_rate": 1.1412726211325163e-06, "loss": 0.2763, "step": 392 }, { "epoch": 0.011472442783745913, "grad_norm": 0.8647100329399109, "learning_rate": 1.1441914769410392e-06, "loss": 0.3057, "step": 393 }, { "epoch": 0.011501634750116767, "grad_norm": 3.1451070308685303, "learning_rate": 1.1471103327495623e-06, "loss": 0.2743, "step": 394 }, { "epoch": 0.011530826716487622, "grad_norm": 0.6725150346755981, "learning_rate": 1.1500291885580852e-06, "loss": 0.2907, "step": 395 }, { "epoch": 0.011560018682858478, "grad_norm": 0.6113927960395813, "learning_rate": 1.1529480443666084e-06, "loss": 0.3097, "step": 396 }, { "epoch": 0.011589210649229333, "grad_norm": 0.5733587145805359, "learning_rate": 1.1558669001751315e-06, "loss": 0.2788, "step": 397 }, { "epoch": 0.011618402615600187, "grad_norm": 0.7424669861793518, "learning_rate": 1.1587857559836544e-06, "loss": 0.2559, "step": 398 }, { "epoch": 0.011647594581971041, "grad_norm": 0.6519526839256287, "learning_rate": 1.1617046117921775e-06, "loss": 0.3028, "step": 399 }, { "epoch": 0.011676786548341896, "grad_norm": 0.6108338236808777, "learning_rate": 1.1646234676007007e-06, "loss": 0.3585, "step": 400 }, { "epoch": 0.01170597851471275, "grad_norm": 0.8607822060585022, "learning_rate": 1.1675423234092238e-06, "loss": 0.3218, "step": 401 }, { "epoch": 0.011735170481083607, "grad_norm": 0.982127845287323, "learning_rate": 1.1704611792177467e-06, "loss": 0.2955, "step": 402 }, { "epoch": 0.011764362447454461, "grad_norm": 0.7911099791526794, "learning_rate": 1.1733800350262698e-06, "loss": 0.2649, "step": 403 }, { "epoch": 0.011793554413825316, "grad_norm": 0.6793727874755859, "learning_rate": 1.176298890834793e-06, "loss": 0.2735, "step": 404 }, { "epoch": 0.01182274638019617, "grad_norm": 1.0973843336105347, "learning_rate": 1.1792177466433159e-06, "loss": 0.3636, "step": 405 }, { "epoch": 0.011851938346567024, "grad_norm": 0.9784681797027588, "learning_rate": 1.182136602451839e-06, "loss": 0.3244, "step": 406 }, { "epoch": 0.011881130312937879, "grad_norm": 0.6776605248451233, "learning_rate": 1.185055458260362e-06, "loss": 0.3239, "step": 407 }, { "epoch": 0.011910322279308735, "grad_norm": 0.651526689529419, "learning_rate": 1.187974314068885e-06, "loss": 0.2439, "step": 408 }, { "epoch": 0.01193951424567959, "grad_norm": 3.1436667442321777, "learning_rate": 1.1908931698774082e-06, "loss": 0.2714, "step": 409 }, { "epoch": 0.011968706212050444, "grad_norm": 1.101279854774475, "learning_rate": 1.193812025685931e-06, "loss": 0.2767, "step": 410 }, { "epoch": 0.011997898178421298, "grad_norm": 0.8619902729988098, "learning_rate": 1.1967308814944542e-06, "loss": 0.2567, "step": 411 }, { "epoch": 0.012027090144792153, "grad_norm": 1.0203163623809814, "learning_rate": 1.1996497373029774e-06, "loss": 0.2623, "step": 412 }, { "epoch": 0.012056282111163007, "grad_norm": 17.86199378967285, "learning_rate": 1.2025685931115005e-06, "loss": 0.2325, "step": 413 }, { "epoch": 0.012085474077533862, "grad_norm": 0.973302960395813, "learning_rate": 1.2054874489200234e-06, "loss": 0.2505, "step": 414 }, { "epoch": 0.012114666043904718, "grad_norm": 0.7318580746650696, "learning_rate": 1.2084063047285465e-06, "loss": 0.2772, "step": 415 }, { "epoch": 0.012143858010275572, "grad_norm": 0.6601394414901733, "learning_rate": 1.2113251605370697e-06, "loss": 0.2762, "step": 416 }, { "epoch": 0.012173049976646427, "grad_norm": 1.0443512201309204, "learning_rate": 1.2142440163455926e-06, "loss": 0.2471, "step": 417 }, { "epoch": 0.012202241943017281, "grad_norm": 0.577165424823761, "learning_rate": 1.2171628721541157e-06, "loss": 0.2603, "step": 418 }, { "epoch": 0.012231433909388136, "grad_norm": 0.907265841960907, "learning_rate": 1.2200817279626386e-06, "loss": 0.2817, "step": 419 }, { "epoch": 0.01226062587575899, "grad_norm": 1.1102408170700073, "learning_rate": 1.2230005837711617e-06, "loss": 0.2606, "step": 420 }, { "epoch": 0.012289817842129847, "grad_norm": 1.6896483898162842, "learning_rate": 1.2259194395796849e-06, "loss": 0.264, "step": 421 }, { "epoch": 0.012319009808500701, "grad_norm": 0.6543264985084534, "learning_rate": 1.2288382953882078e-06, "loss": 0.2588, "step": 422 }, { "epoch": 0.012348201774871555, "grad_norm": 0.5815913677215576, "learning_rate": 1.231757151196731e-06, "loss": 0.2318, "step": 423 }, { "epoch": 0.01237739374124241, "grad_norm": 0.803937554359436, "learning_rate": 1.234676007005254e-06, "loss": 0.2813, "step": 424 }, { "epoch": 0.012406585707613264, "grad_norm": 0.661034882068634, "learning_rate": 1.2375948628137772e-06, "loss": 0.2627, "step": 425 }, { "epoch": 0.012435777673984119, "grad_norm": 0.6521763205528259, "learning_rate": 1.2405137186223e-06, "loss": 0.2326, "step": 426 }, { "epoch": 0.012464969640354975, "grad_norm": 1.2458516359329224, "learning_rate": 1.2434325744308232e-06, "loss": 0.2773, "step": 427 }, { "epoch": 0.01249416160672583, "grad_norm": 0.6658322811126709, "learning_rate": 1.2463514302393464e-06, "loss": 0.2845, "step": 428 }, { "epoch": 0.012523353573096684, "grad_norm": 0.6613122820854187, "learning_rate": 1.2492702860478693e-06, "loss": 0.2927, "step": 429 }, { "epoch": 0.012552545539467538, "grad_norm": 0.6244262456893921, "learning_rate": 1.2521891418563926e-06, "loss": 0.2664, "step": 430 }, { "epoch": 0.012581737505838393, "grad_norm": 0.8054784536361694, "learning_rate": 1.2551079976649155e-06, "loss": 0.294, "step": 431 }, { "epoch": 0.012610929472209247, "grad_norm": 0.8685522675514221, "learning_rate": 1.2580268534734387e-06, "loss": 0.2597, "step": 432 }, { "epoch": 0.012640121438580103, "grad_norm": 0.7677276134490967, "learning_rate": 1.2609457092819616e-06, "loss": 0.2591, "step": 433 }, { "epoch": 0.012669313404950958, "grad_norm": 1.3467170000076294, "learning_rate": 1.2638645650904847e-06, "loss": 0.2533, "step": 434 }, { "epoch": 0.012698505371321812, "grad_norm": 0.6795380115509033, "learning_rate": 1.2667834208990076e-06, "loss": 0.2894, "step": 435 }, { "epoch": 0.012727697337692667, "grad_norm": 0.7034056782722473, "learning_rate": 1.2697022767075307e-06, "loss": 0.303, "step": 436 }, { "epoch": 0.012756889304063521, "grad_norm": 0.5700642466545105, "learning_rate": 1.2726211325160537e-06, "loss": 0.2501, "step": 437 }, { "epoch": 0.012786081270434376, "grad_norm": 0.8244123458862305, "learning_rate": 1.275539988324577e-06, "loss": 0.2528, "step": 438 }, { "epoch": 0.012815273236805232, "grad_norm": 0.9164974689483643, "learning_rate": 1.2784588441331e-06, "loss": 0.2487, "step": 439 }, { "epoch": 0.012844465203176086, "grad_norm": 0.6804303526878357, "learning_rate": 1.281377699941623e-06, "loss": 0.296, "step": 440 }, { "epoch": 0.012873657169546941, "grad_norm": 0.61387038230896, "learning_rate": 1.284296555750146e-06, "loss": 0.2789, "step": 441 }, { "epoch": 0.012902849135917795, "grad_norm": 0.7383361458778381, "learning_rate": 1.287215411558669e-06, "loss": 0.2399, "step": 442 }, { "epoch": 0.01293204110228865, "grad_norm": 0.6450729370117188, "learning_rate": 1.290134267367192e-06, "loss": 0.2611, "step": 443 }, { "epoch": 0.012961233068659504, "grad_norm": 0.6695459485054016, "learning_rate": 1.2930531231757151e-06, "loss": 0.2888, "step": 444 }, { "epoch": 0.01299042503503036, "grad_norm": 3.0578908920288086, "learning_rate": 1.295971978984238e-06, "loss": 0.2798, "step": 445 }, { "epoch": 0.013019617001401215, "grad_norm": 0.553157389163971, "learning_rate": 1.2988908347927614e-06, "loss": 0.2367, "step": 446 }, { "epoch": 0.01304880896777207, "grad_norm": 0.6996678113937378, "learning_rate": 1.3018096906012845e-06, "loss": 0.2367, "step": 447 }, { "epoch": 0.013078000934142924, "grad_norm": 1.0251246690750122, "learning_rate": 1.3047285464098074e-06, "loss": 0.2964, "step": 448 }, { "epoch": 0.013107192900513778, "grad_norm": 1.0244419574737549, "learning_rate": 1.3076474022183306e-06, "loss": 0.2433, "step": 449 }, { "epoch": 0.013136384866884633, "grad_norm": 1.1226023435592651, "learning_rate": 1.3105662580268535e-06, "loss": 0.2735, "step": 450 }, { "epoch": 0.013165576833255489, "grad_norm": 0.8091144561767578, "learning_rate": 1.3134851138353766e-06, "loss": 0.2932, "step": 451 }, { "epoch": 0.013194768799626343, "grad_norm": 1.0471702814102173, "learning_rate": 1.3164039696438995e-06, "loss": 0.2857, "step": 452 }, { "epoch": 0.013223960765997198, "grad_norm": 0.9679293632507324, "learning_rate": 1.3193228254524227e-06, "loss": 0.2886, "step": 453 }, { "epoch": 0.013253152732368052, "grad_norm": 0.6472281217575073, "learning_rate": 1.322241681260946e-06, "loss": 0.2305, "step": 454 }, { "epoch": 0.013282344698738907, "grad_norm": 1.129378318786621, "learning_rate": 1.325160537069469e-06, "loss": 0.3539, "step": 455 }, { "epoch": 0.013311536665109761, "grad_norm": 0.5827157497406006, "learning_rate": 1.328079392877992e-06, "loss": 0.236, "step": 456 }, { "epoch": 0.013340728631480616, "grad_norm": 1.7998621463775635, "learning_rate": 1.330998248686515e-06, "loss": 0.2573, "step": 457 }, { "epoch": 0.013369920597851472, "grad_norm": 0.7008837461471558, "learning_rate": 1.333917104495038e-06, "loss": 0.268, "step": 458 }, { "epoch": 0.013399112564222326, "grad_norm": 1.0489002466201782, "learning_rate": 1.336835960303561e-06, "loss": 0.3175, "step": 459 }, { "epoch": 0.01342830453059318, "grad_norm": 0.7136147618293762, "learning_rate": 1.3397548161120841e-06, "loss": 0.3051, "step": 460 }, { "epoch": 0.013457496496964035, "grad_norm": 0.7204222679138184, "learning_rate": 1.342673671920607e-06, "loss": 0.3294, "step": 461 }, { "epoch": 0.01348668846333489, "grad_norm": 0.9319116473197937, "learning_rate": 1.3455925277291304e-06, "loss": 0.2585, "step": 462 }, { "epoch": 0.013515880429705744, "grad_norm": 0.799772322177887, "learning_rate": 1.3485113835376535e-06, "loss": 0.3074, "step": 463 }, { "epoch": 0.0135450723960766, "grad_norm": 3.4128103256225586, "learning_rate": 1.3514302393461764e-06, "loss": 0.2868, "step": 464 }, { "epoch": 0.013574264362447455, "grad_norm": 0.9284300804138184, "learning_rate": 1.3543490951546996e-06, "loss": 0.2746, "step": 465 }, { "epoch": 0.01360345632881831, "grad_norm": 1.0497853755950928, "learning_rate": 1.3572679509632225e-06, "loss": 0.2784, "step": 466 }, { "epoch": 0.013632648295189164, "grad_norm": 1.2636089324951172, "learning_rate": 1.3601868067717456e-06, "loss": 0.2844, "step": 467 }, { "epoch": 0.013661840261560018, "grad_norm": 0.9726134538650513, "learning_rate": 1.3631056625802685e-06, "loss": 0.2913, "step": 468 }, { "epoch": 0.013691032227930873, "grad_norm": 0.6332557797431946, "learning_rate": 1.3660245183887916e-06, "loss": 0.3062, "step": 469 }, { "epoch": 0.013720224194301729, "grad_norm": 0.9201659560203552, "learning_rate": 1.3689433741973148e-06, "loss": 0.2992, "step": 470 }, { "epoch": 0.013749416160672583, "grad_norm": 0.7040758728981018, "learning_rate": 1.371862230005838e-06, "loss": 0.2358, "step": 471 }, { "epoch": 0.013778608127043438, "grad_norm": 1.076590895652771, "learning_rate": 1.374781085814361e-06, "loss": 0.2686, "step": 472 }, { "epoch": 0.013807800093414292, "grad_norm": 0.7712363600730896, "learning_rate": 1.377699941622884e-06, "loss": 0.2902, "step": 473 }, { "epoch": 0.013836992059785147, "grad_norm": 0.7412001490592957, "learning_rate": 1.380618797431407e-06, "loss": 0.2729, "step": 474 }, { "epoch": 0.013866184026156001, "grad_norm": 1.366166353225708, "learning_rate": 1.38353765323993e-06, "loss": 0.2552, "step": 475 }, { "epoch": 0.013895375992526857, "grad_norm": 0.904152512550354, "learning_rate": 1.3864565090484531e-06, "loss": 0.261, "step": 476 }, { "epoch": 0.013924567958897712, "grad_norm": 0.503882646560669, "learning_rate": 1.389375364856976e-06, "loss": 0.2431, "step": 477 }, { "epoch": 0.013953759925268566, "grad_norm": 0.6423302292823792, "learning_rate": 1.3922942206654994e-06, "loss": 0.2974, "step": 478 }, { "epoch": 0.01398295189163942, "grad_norm": 0.8287842869758606, "learning_rate": 1.3952130764740223e-06, "loss": 0.2617, "step": 479 }, { "epoch": 0.014012143858010275, "grad_norm": 0.7085167765617371, "learning_rate": 1.3981319322825454e-06, "loss": 0.3586, "step": 480 }, { "epoch": 0.01404133582438113, "grad_norm": 9.678640365600586, "learning_rate": 1.4010507880910683e-06, "loss": 0.267, "step": 481 }, { "epoch": 0.014070527790751986, "grad_norm": 1.6714389324188232, "learning_rate": 1.4039696438995915e-06, "loss": 0.2662, "step": 482 }, { "epoch": 0.01409971975712284, "grad_norm": 0.6470839381217957, "learning_rate": 1.4068884997081144e-06, "loss": 0.2726, "step": 483 }, { "epoch": 0.014128911723493695, "grad_norm": 0.6321594715118408, "learning_rate": 1.4098073555166375e-06, "loss": 0.3348, "step": 484 }, { "epoch": 0.01415810368986455, "grad_norm": 0.811446487903595, "learning_rate": 1.4127262113251604e-06, "loss": 0.2629, "step": 485 }, { "epoch": 0.014187295656235404, "grad_norm": 1.142481803894043, "learning_rate": 1.4156450671336838e-06, "loss": 0.2583, "step": 486 }, { "epoch": 0.014216487622606258, "grad_norm": 0.6211776733398438, "learning_rate": 1.418563922942207e-06, "loss": 0.3052, "step": 487 }, { "epoch": 0.014245679588977114, "grad_norm": 1.2892937660217285, "learning_rate": 1.4214827787507298e-06, "loss": 0.3079, "step": 488 }, { "epoch": 0.014274871555347969, "grad_norm": 0.7147728800773621, "learning_rate": 1.424401634559253e-06, "loss": 0.2694, "step": 489 }, { "epoch": 0.014304063521718823, "grad_norm": 0.7934185266494751, "learning_rate": 1.4273204903677759e-06, "loss": 0.2984, "step": 490 }, { "epoch": 0.014333255488089678, "grad_norm": 1.0170239210128784, "learning_rate": 1.430239346176299e-06, "loss": 0.3063, "step": 491 }, { "epoch": 0.014362447454460532, "grad_norm": 0.6234959363937378, "learning_rate": 1.433158201984822e-06, "loss": 0.2792, "step": 492 }, { "epoch": 0.014391639420831387, "grad_norm": 1.1056525707244873, "learning_rate": 1.436077057793345e-06, "loss": 0.284, "step": 493 }, { "epoch": 0.014420831387202243, "grad_norm": 1.2709505558013916, "learning_rate": 1.4389959136018684e-06, "loss": 0.2724, "step": 494 }, { "epoch": 0.014450023353573097, "grad_norm": 1.1037774085998535, "learning_rate": 1.4419147694103913e-06, "loss": 0.2597, "step": 495 }, { "epoch": 0.014479215319943952, "grad_norm": 0.8061040639877319, "learning_rate": 1.4448336252189144e-06, "loss": 0.2657, "step": 496 }, { "epoch": 0.014508407286314806, "grad_norm": 0.5869560241699219, "learning_rate": 1.4477524810274373e-06, "loss": 0.297, "step": 497 }, { "epoch": 0.01453759925268566, "grad_norm": 0.717027485370636, "learning_rate": 1.4506713368359605e-06, "loss": 0.2786, "step": 498 }, { "epoch": 0.014566791219056515, "grad_norm": 0.6634339094161987, "learning_rate": 1.4535901926444834e-06, "loss": 0.2411, "step": 499 }, { "epoch": 0.014595983185427371, "grad_norm": 0.6497923135757446, "learning_rate": 1.4565090484530065e-06, "loss": 0.3143, "step": 500 }, { "epoch": 0.014625175151798226, "grad_norm": 0.6140262484550476, "learning_rate": 1.4594279042615294e-06, "loss": 0.2634, "step": 501 }, { "epoch": 0.01465436711816908, "grad_norm": 0.6981409192085266, "learning_rate": 1.4623467600700528e-06, "loss": 0.295, "step": 502 }, { "epoch": 0.014683559084539935, "grad_norm": 1.3851064443588257, "learning_rate": 1.4652656158785759e-06, "loss": 0.2577, "step": 503 }, { "epoch": 0.014712751050910789, "grad_norm": 0.7335472106933594, "learning_rate": 1.4681844716870988e-06, "loss": 0.2729, "step": 504 }, { "epoch": 0.014741943017281644, "grad_norm": 0.6511871814727783, "learning_rate": 1.471103327495622e-06, "loss": 0.297, "step": 505 }, { "epoch": 0.014771134983652498, "grad_norm": 0.9701840281486511, "learning_rate": 1.4740221833041449e-06, "loss": 0.2943, "step": 506 }, { "epoch": 0.014800326950023354, "grad_norm": 0.8399590849876404, "learning_rate": 1.476941039112668e-06, "loss": 0.2665, "step": 507 }, { "epoch": 0.014829518916394209, "grad_norm": 0.8021056056022644, "learning_rate": 1.479859894921191e-06, "loss": 0.2114, "step": 508 }, { "epoch": 0.014858710882765063, "grad_norm": 0.7029216289520264, "learning_rate": 1.482778750729714e-06, "loss": 0.278, "step": 509 }, { "epoch": 0.014887902849135918, "grad_norm": 0.7964077591896057, "learning_rate": 1.4856976065382372e-06, "loss": 0.2548, "step": 510 }, { "epoch": 0.014917094815506772, "grad_norm": 0.8404961824417114, "learning_rate": 1.4886164623467603e-06, "loss": 0.2841, "step": 511 }, { "epoch": 0.014946286781877626, "grad_norm": 0.801141619682312, "learning_rate": 1.4915353181552832e-06, "loss": 0.2807, "step": 512 }, { "epoch": 0.014975478748248483, "grad_norm": 0.6241012215614319, "learning_rate": 1.4944541739638063e-06, "loss": 0.2483, "step": 513 }, { "epoch": 0.015004670714619337, "grad_norm": 0.9223431348800659, "learning_rate": 1.4973730297723292e-06, "loss": 0.2434, "step": 514 }, { "epoch": 0.015033862680990192, "grad_norm": 0.8605660796165466, "learning_rate": 1.5002918855808524e-06, "loss": 0.2843, "step": 515 }, { "epoch": 0.015063054647361046, "grad_norm": 0.8673115372657776, "learning_rate": 1.5032107413893753e-06, "loss": 0.3334, "step": 516 }, { "epoch": 0.0150922466137319, "grad_norm": 0.7275378108024597, "learning_rate": 1.5061295971978984e-06, "loss": 0.2482, "step": 517 }, { "epoch": 0.015121438580102755, "grad_norm": 0.6998602151870728, "learning_rate": 1.5090484530064218e-06, "loss": 0.247, "step": 518 }, { "epoch": 0.015150630546473611, "grad_norm": 0.7906604409217834, "learning_rate": 1.5119673088149447e-06, "loss": 0.2456, "step": 519 }, { "epoch": 0.015179822512844466, "grad_norm": 0.6632605195045471, "learning_rate": 1.5148861646234678e-06, "loss": 0.2651, "step": 520 }, { "epoch": 0.01520901447921532, "grad_norm": 0.6603840589523315, "learning_rate": 1.5178050204319907e-06, "loss": 0.2196, "step": 521 }, { "epoch": 0.015238206445586175, "grad_norm": 0.7788634896278381, "learning_rate": 1.5207238762405138e-06, "loss": 0.3008, "step": 522 }, { "epoch": 0.015267398411957029, "grad_norm": 0.8454463481903076, "learning_rate": 1.5236427320490368e-06, "loss": 0.2981, "step": 523 }, { "epoch": 0.015296590378327883, "grad_norm": 15.214061737060547, "learning_rate": 1.5265615878575599e-06, "loss": 0.3087, "step": 524 }, { "epoch": 0.01532578234469874, "grad_norm": 0.804986834526062, "learning_rate": 1.5294804436660828e-06, "loss": 0.2678, "step": 525 }, { "epoch": 0.015354974311069594, "grad_norm": 0.9046737551689148, "learning_rate": 1.5323992994746061e-06, "loss": 0.2922, "step": 526 }, { "epoch": 0.015384166277440449, "grad_norm": 1.345935583114624, "learning_rate": 1.5353181552831293e-06, "loss": 0.2627, "step": 527 }, { "epoch": 0.015413358243811303, "grad_norm": 1.1210567951202393, "learning_rate": 1.5382370110916522e-06, "loss": 0.2524, "step": 528 }, { "epoch": 0.015442550210182157, "grad_norm": 0.5794903039932251, "learning_rate": 1.5411558669001753e-06, "loss": 0.2434, "step": 529 }, { "epoch": 0.015471742176553012, "grad_norm": 0.8245623707771301, "learning_rate": 1.5440747227086982e-06, "loss": 0.2425, "step": 530 }, { "epoch": 0.015500934142923868, "grad_norm": 0.5687342286109924, "learning_rate": 1.5469935785172214e-06, "loss": 0.2434, "step": 531 }, { "epoch": 0.015530126109294723, "grad_norm": 0.8250827193260193, "learning_rate": 1.5499124343257443e-06, "loss": 0.3041, "step": 532 }, { "epoch": 0.015559318075665577, "grad_norm": 0.8127528429031372, "learning_rate": 1.5528312901342674e-06, "loss": 0.3002, "step": 533 }, { "epoch": 0.015588510042036431, "grad_norm": 0.7258909344673157, "learning_rate": 1.5557501459427908e-06, "loss": 0.2294, "step": 534 }, { "epoch": 0.015617702008407286, "grad_norm": 0.8988394737243652, "learning_rate": 1.5586690017513137e-06, "loss": 0.2911, "step": 535 }, { "epoch": 0.015646893974778142, "grad_norm": 0.7205225825309753, "learning_rate": 1.5615878575598368e-06, "loss": 0.2386, "step": 536 }, { "epoch": 0.015676085941148995, "grad_norm": 0.9326334595680237, "learning_rate": 1.5645067133683597e-06, "loss": 0.2503, "step": 537 }, { "epoch": 0.01570527790751985, "grad_norm": 0.7219685912132263, "learning_rate": 1.5674255691768828e-06, "loss": 0.3163, "step": 538 }, { "epoch": 0.015734469873890704, "grad_norm": 0.9074805974960327, "learning_rate": 1.5703444249854058e-06, "loss": 0.2661, "step": 539 }, { "epoch": 0.01576366184026156, "grad_norm": 0.6810081005096436, "learning_rate": 1.5732632807939289e-06, "loss": 0.3319, "step": 540 }, { "epoch": 0.015792853806632416, "grad_norm": 0.5805920362472534, "learning_rate": 1.5761821366024518e-06, "loss": 0.2953, "step": 541 }, { "epoch": 0.01582204577300327, "grad_norm": 0.8611071705818176, "learning_rate": 1.5791009924109751e-06, "loss": 0.2577, "step": 542 }, { "epoch": 0.015851237739374125, "grad_norm": 0.8273828625679016, "learning_rate": 1.5820198482194983e-06, "loss": 0.3391, "step": 543 }, { "epoch": 0.015880429705744978, "grad_norm": 0.9587908387184143, "learning_rate": 1.5849387040280212e-06, "loss": 0.2249, "step": 544 }, { "epoch": 0.015909621672115834, "grad_norm": 0.9559302926063538, "learning_rate": 1.5878575598365443e-06, "loss": 0.2471, "step": 545 }, { "epoch": 0.01593881363848669, "grad_norm": 0.8134982585906982, "learning_rate": 1.5907764156450672e-06, "loss": 0.2822, "step": 546 }, { "epoch": 0.015968005604857543, "grad_norm": 0.8997788429260254, "learning_rate": 1.5936952714535904e-06, "loss": 0.2634, "step": 547 }, { "epoch": 0.0159971975712284, "grad_norm": 0.5914014577865601, "learning_rate": 1.5966141272621133e-06, "loss": 0.2488, "step": 548 }, { "epoch": 0.016026389537599252, "grad_norm": 0.6838382482528687, "learning_rate": 1.5995329830706364e-06, "loss": 0.2699, "step": 549 }, { "epoch": 0.016055581503970108, "grad_norm": 1.543350100517273, "learning_rate": 1.6024518388791595e-06, "loss": 0.2583, "step": 550 }, { "epoch": 0.01608477347034096, "grad_norm": 1.102961540222168, "learning_rate": 1.6053706946876827e-06, "loss": 0.2793, "step": 551 }, { "epoch": 0.016113965436711817, "grad_norm": 0.7651376128196716, "learning_rate": 1.6082895504962056e-06, "loss": 0.3217, "step": 552 }, { "epoch": 0.016143157403082673, "grad_norm": 0.6704403162002563, "learning_rate": 1.6112084063047287e-06, "loss": 0.2674, "step": 553 }, { "epoch": 0.016172349369453526, "grad_norm": 0.8795967698097229, "learning_rate": 1.6141272621132516e-06, "loss": 0.2736, "step": 554 }, { "epoch": 0.016201541335824382, "grad_norm": 0.7153691649436951, "learning_rate": 1.6170461179217748e-06, "loss": 0.3089, "step": 555 }, { "epoch": 0.016230733302195235, "grad_norm": 0.6462613344192505, "learning_rate": 1.6199649737302977e-06, "loss": 0.2528, "step": 556 }, { "epoch": 0.01625992526856609, "grad_norm": 0.8326774835586548, "learning_rate": 1.6228838295388208e-06, "loss": 0.2079, "step": 557 }, { "epoch": 0.016289117234936944, "grad_norm": 0.9320446848869324, "learning_rate": 1.6258026853473441e-06, "loss": 0.3082, "step": 558 }, { "epoch": 0.0163183092013078, "grad_norm": 1.168584942817688, "learning_rate": 1.628721541155867e-06, "loss": 0.2788, "step": 559 }, { "epoch": 0.016347501167678656, "grad_norm": 0.6632365584373474, "learning_rate": 1.6316403969643902e-06, "loss": 0.2585, "step": 560 }, { "epoch": 0.01637669313404951, "grad_norm": 0.822705864906311, "learning_rate": 1.634559252772913e-06, "loss": 0.3085, "step": 561 }, { "epoch": 0.016405885100420365, "grad_norm": 1.492363452911377, "learning_rate": 1.6374781085814362e-06, "loss": 0.2843, "step": 562 }, { "epoch": 0.016435077066791218, "grad_norm": 0.8802257180213928, "learning_rate": 1.6403969643899591e-06, "loss": 0.2857, "step": 563 }, { "epoch": 0.016464269033162074, "grad_norm": 0.7082200050354004, "learning_rate": 1.6433158201984823e-06, "loss": 0.2694, "step": 564 }, { "epoch": 0.01649346099953293, "grad_norm": 0.677329957485199, "learning_rate": 1.6462346760070052e-06, "loss": 0.2451, "step": 565 }, { "epoch": 0.016522652965903783, "grad_norm": 1.7587590217590332, "learning_rate": 1.6491535318155285e-06, "loss": 0.2578, "step": 566 }, { "epoch": 0.01655184493227464, "grad_norm": 0.6737069487571716, "learning_rate": 1.6520723876240517e-06, "loss": 0.2357, "step": 567 }, { "epoch": 0.016581036898645492, "grad_norm": 0.7681375741958618, "learning_rate": 1.6549912434325746e-06, "loss": 0.3069, "step": 568 }, { "epoch": 0.016610228865016348, "grad_norm": 0.8162296414375305, "learning_rate": 1.6579100992410977e-06, "loss": 0.2753, "step": 569 }, { "epoch": 0.0166394208313872, "grad_norm": 0.6440860033035278, "learning_rate": 1.6608289550496206e-06, "loss": 0.3015, "step": 570 }, { "epoch": 0.016668612797758057, "grad_norm": 0.9233183860778809, "learning_rate": 1.6637478108581437e-06, "loss": 0.3161, "step": 571 }, { "epoch": 0.016697804764128913, "grad_norm": 4.699238300323486, "learning_rate": 1.6666666666666667e-06, "loss": 0.2696, "step": 572 }, { "epoch": 0.016726996730499766, "grad_norm": 2.3124184608459473, "learning_rate": 1.6695855224751898e-06, "loss": 0.281, "step": 573 }, { "epoch": 0.016756188696870622, "grad_norm": 1.5874414443969727, "learning_rate": 1.6725043782837131e-06, "loss": 0.281, "step": 574 }, { "epoch": 0.016785380663241475, "grad_norm": 0.8989226818084717, "learning_rate": 1.675423234092236e-06, "loss": 0.2623, "step": 575 }, { "epoch": 0.01681457262961233, "grad_norm": 0.659877359867096, "learning_rate": 1.6783420899007592e-06, "loss": 0.269, "step": 576 }, { "epoch": 0.016843764595983187, "grad_norm": 1.8409004211425781, "learning_rate": 1.681260945709282e-06, "loss": 0.2901, "step": 577 }, { "epoch": 0.01687295656235404, "grad_norm": 0.6888791918754578, "learning_rate": 1.6841798015178052e-06, "loss": 0.2515, "step": 578 }, { "epoch": 0.016902148528724896, "grad_norm": 0.6786807179450989, "learning_rate": 1.6870986573263281e-06, "loss": 0.231, "step": 579 }, { "epoch": 0.01693134049509575, "grad_norm": 2.0943052768707275, "learning_rate": 1.6900175131348513e-06, "loss": 0.3114, "step": 580 }, { "epoch": 0.016960532461466605, "grad_norm": 0.7642979025840759, "learning_rate": 1.6929363689433742e-06, "loss": 0.2672, "step": 581 }, { "epoch": 0.016989724427837458, "grad_norm": 0.6994286179542542, "learning_rate": 1.6958552247518975e-06, "loss": 0.286, "step": 582 }, { "epoch": 0.017018916394208314, "grad_norm": 0.6819736957550049, "learning_rate": 1.6987740805604204e-06, "loss": 0.3015, "step": 583 }, { "epoch": 0.01704810836057917, "grad_norm": 0.7599068880081177, "learning_rate": 1.7016929363689436e-06, "loss": 0.2336, "step": 584 }, { "epoch": 0.017077300326950023, "grad_norm": 0.6559334397315979, "learning_rate": 1.7046117921774665e-06, "loss": 0.3006, "step": 585 }, { "epoch": 0.01710649229332088, "grad_norm": 0.7553215622901917, "learning_rate": 1.7075306479859896e-06, "loss": 0.2803, "step": 586 }, { "epoch": 0.01713568425969173, "grad_norm": 0.9913178086280823, "learning_rate": 1.7104495037945127e-06, "loss": 0.2506, "step": 587 }, { "epoch": 0.017164876226062588, "grad_norm": 0.6303195357322693, "learning_rate": 1.7133683596030357e-06, "loss": 0.2702, "step": 588 }, { "epoch": 0.017194068192433444, "grad_norm": 0.7937769889831543, "learning_rate": 1.7162872154115588e-06, "loss": 0.3366, "step": 589 }, { "epoch": 0.017223260158804297, "grad_norm": 1.0203707218170166, "learning_rate": 1.719206071220082e-06, "loss": 0.3198, "step": 590 }, { "epoch": 0.017252452125175153, "grad_norm": 0.6934217214584351, "learning_rate": 1.722124927028605e-06, "loss": 0.2661, "step": 591 }, { "epoch": 0.017281644091546006, "grad_norm": 0.9086501598358154, "learning_rate": 1.725043782837128e-06, "loss": 0.2621, "step": 592 }, { "epoch": 0.017310836057916862, "grad_norm": 0.9322716593742371, "learning_rate": 1.727962638645651e-06, "loss": 0.2818, "step": 593 }, { "epoch": 0.017340028024287715, "grad_norm": 0.7407519817352295, "learning_rate": 1.730881494454174e-06, "loss": 0.2806, "step": 594 }, { "epoch": 0.01736921999065857, "grad_norm": 0.7748797535896301, "learning_rate": 1.7338003502626971e-06, "loss": 0.287, "step": 595 }, { "epoch": 0.017398411957029427, "grad_norm": 1.069310188293457, "learning_rate": 1.73671920607122e-06, "loss": 0.2816, "step": 596 }, { "epoch": 0.01742760392340028, "grad_norm": 0.7855096459388733, "learning_rate": 1.7396380618797432e-06, "loss": 0.3125, "step": 597 }, { "epoch": 0.017456795889771136, "grad_norm": 0.9397386908531189, "learning_rate": 1.7425569176882665e-06, "loss": 0.2974, "step": 598 }, { "epoch": 0.01748598785614199, "grad_norm": 1.765734314918518, "learning_rate": 1.7454757734967894e-06, "loss": 0.2937, "step": 599 }, { "epoch": 0.017515179822512845, "grad_norm": 0.6770528554916382, "learning_rate": 1.7483946293053126e-06, "loss": 0.2528, "step": 600 }, { "epoch": 0.017544371788883698, "grad_norm": 1.0887349843978882, "learning_rate": 1.7513134851138355e-06, "loss": 0.2496, "step": 601 }, { "epoch": 0.017573563755254554, "grad_norm": 0.688243567943573, "learning_rate": 1.7542323409223586e-06, "loss": 0.2679, "step": 602 }, { "epoch": 0.01760275572162541, "grad_norm": 0.946229875087738, "learning_rate": 1.7571511967308815e-06, "loss": 0.3177, "step": 603 }, { "epoch": 0.017631947687996263, "grad_norm": 1.0416284799575806, "learning_rate": 1.7600700525394046e-06, "loss": 0.3098, "step": 604 }, { "epoch": 0.01766113965436712, "grad_norm": 1.0023747682571411, "learning_rate": 1.7629889083479276e-06, "loss": 0.2828, "step": 605 }, { "epoch": 0.01769033162073797, "grad_norm": 1.0074700117111206, "learning_rate": 1.765907764156451e-06, "loss": 0.2745, "step": 606 }, { "epoch": 0.017719523587108828, "grad_norm": 1.0555726289749146, "learning_rate": 1.768826619964974e-06, "loss": 0.2986, "step": 607 }, { "epoch": 0.017748715553479684, "grad_norm": 0.6465082764625549, "learning_rate": 1.771745475773497e-06, "loss": 0.2134, "step": 608 }, { "epoch": 0.017777907519850537, "grad_norm": 0.926420271396637, "learning_rate": 1.77466433158202e-06, "loss": 0.3051, "step": 609 }, { "epoch": 0.017807099486221393, "grad_norm": 0.6266963481903076, "learning_rate": 1.777583187390543e-06, "loss": 0.2552, "step": 610 }, { "epoch": 0.017836291452592246, "grad_norm": 0.9962296485900879, "learning_rate": 1.7805020431990661e-06, "loss": 0.2864, "step": 611 }, { "epoch": 0.017865483418963102, "grad_norm": 0.7207348942756653, "learning_rate": 1.783420899007589e-06, "loss": 0.2701, "step": 612 }, { "epoch": 0.017894675385333954, "grad_norm": 0.8162289261817932, "learning_rate": 1.7863397548161122e-06, "loss": 0.3182, "step": 613 }, { "epoch": 0.01792386735170481, "grad_norm": 0.7068377137184143, "learning_rate": 1.7892586106246355e-06, "loss": 0.2768, "step": 614 }, { "epoch": 0.017953059318075667, "grad_norm": 0.7817624807357788, "learning_rate": 1.7921774664331584e-06, "loss": 0.3077, "step": 615 }, { "epoch": 0.01798225128444652, "grad_norm": 0.7608832716941833, "learning_rate": 1.7950963222416816e-06, "loss": 0.285, "step": 616 }, { "epoch": 0.018011443250817376, "grad_norm": 0.827566921710968, "learning_rate": 1.7980151780502045e-06, "loss": 0.2532, "step": 617 }, { "epoch": 0.01804063521718823, "grad_norm": 0.7308710217475891, "learning_rate": 1.8009340338587276e-06, "loss": 0.2681, "step": 618 }, { "epoch": 0.018069827183559085, "grad_norm": 1.134116768836975, "learning_rate": 1.8038528896672505e-06, "loss": 0.295, "step": 619 }, { "epoch": 0.01809901914992994, "grad_norm": 0.795295000076294, "learning_rate": 1.8067717454757736e-06, "loss": 0.2803, "step": 620 }, { "epoch": 0.018128211116300794, "grad_norm": 1.3458253145217896, "learning_rate": 1.8096906012842966e-06, "loss": 0.2368, "step": 621 }, { "epoch": 0.01815740308267165, "grad_norm": 0.8243628740310669, "learning_rate": 1.81260945709282e-06, "loss": 0.2624, "step": 622 }, { "epoch": 0.018186595049042503, "grad_norm": 0.7814077734947205, "learning_rate": 1.8155283129013428e-06, "loss": 0.2752, "step": 623 }, { "epoch": 0.01821578701541336, "grad_norm": 1.4408787488937378, "learning_rate": 1.818447168709866e-06, "loss": 0.3144, "step": 624 }, { "epoch": 0.01824497898178421, "grad_norm": 0.9676704406738281, "learning_rate": 1.8213660245183889e-06, "loss": 0.2746, "step": 625 }, { "epoch": 0.018274170948155068, "grad_norm": 0.6607152223587036, "learning_rate": 1.824284880326912e-06, "loss": 0.2112, "step": 626 }, { "epoch": 0.018303362914525924, "grad_norm": 1.1185005903244019, "learning_rate": 1.827203736135435e-06, "loss": 0.3015, "step": 627 }, { "epoch": 0.018332554880896777, "grad_norm": 0.8892969489097595, "learning_rate": 1.830122591943958e-06, "loss": 0.3123, "step": 628 }, { "epoch": 0.018361746847267633, "grad_norm": 0.8825914859771729, "learning_rate": 1.833041447752481e-06, "loss": 0.2781, "step": 629 }, { "epoch": 0.018390938813638485, "grad_norm": 0.8323768377304077, "learning_rate": 1.8359603035610043e-06, "loss": 0.3172, "step": 630 }, { "epoch": 0.01842013078000934, "grad_norm": 0.7763574123382568, "learning_rate": 1.8388791593695274e-06, "loss": 0.2348, "step": 631 }, { "epoch": 0.018449322746380198, "grad_norm": 0.8132169842720032, "learning_rate": 1.8417980151780503e-06, "loss": 0.292, "step": 632 }, { "epoch": 0.01847851471275105, "grad_norm": 1.1855337619781494, "learning_rate": 1.8447168709865735e-06, "loss": 0.2865, "step": 633 }, { "epoch": 0.018507706679121907, "grad_norm": 0.7910639047622681, "learning_rate": 1.8476357267950964e-06, "loss": 0.2585, "step": 634 }, { "epoch": 0.01853689864549276, "grad_norm": 0.8691161870956421, "learning_rate": 1.8505545826036195e-06, "loss": 0.2679, "step": 635 }, { "epoch": 0.018566090611863616, "grad_norm": 0.6608052849769592, "learning_rate": 1.8534734384121424e-06, "loss": 0.3109, "step": 636 }, { "epoch": 0.01859528257823447, "grad_norm": 0.6236014366149902, "learning_rate": 1.8563922942206656e-06, "loss": 0.296, "step": 637 }, { "epoch": 0.018624474544605325, "grad_norm": 0.7737935185432434, "learning_rate": 1.859311150029189e-06, "loss": 0.2842, "step": 638 }, { "epoch": 0.01865366651097618, "grad_norm": 0.6849144697189331, "learning_rate": 1.8622300058377118e-06, "loss": 0.2664, "step": 639 }, { "epoch": 0.018682858477347034, "grad_norm": 0.6961067914962769, "learning_rate": 1.865148861646235e-06, "loss": 0.2522, "step": 640 }, { "epoch": 0.01871205044371789, "grad_norm": 0.8694955706596375, "learning_rate": 1.8680677174547579e-06, "loss": 0.2698, "step": 641 }, { "epoch": 0.018741242410088742, "grad_norm": 0.7796080112457275, "learning_rate": 1.870986573263281e-06, "loss": 0.3177, "step": 642 }, { "epoch": 0.0187704343764596, "grad_norm": 0.9186857342720032, "learning_rate": 1.873905429071804e-06, "loss": 0.2858, "step": 643 }, { "epoch": 0.01879962634283045, "grad_norm": 0.990131676197052, "learning_rate": 1.876824284880327e-06, "loss": 0.3066, "step": 644 }, { "epoch": 0.018828818309201308, "grad_norm": 0.7169500589370728, "learning_rate": 1.87974314068885e-06, "loss": 0.3014, "step": 645 }, { "epoch": 0.018858010275572164, "grad_norm": 0.6963884234428406, "learning_rate": 1.8826619964973733e-06, "loss": 0.2494, "step": 646 }, { "epoch": 0.018887202241943016, "grad_norm": 1.2253340482711792, "learning_rate": 1.8855808523058964e-06, "loss": 0.2531, "step": 647 }, { "epoch": 0.018916394208313873, "grad_norm": 0.9046421051025391, "learning_rate": 1.8884997081144193e-06, "loss": 0.2545, "step": 648 }, { "epoch": 0.018945586174684725, "grad_norm": 1.0692216157913208, "learning_rate": 1.8914185639229425e-06, "loss": 0.301, "step": 649 }, { "epoch": 0.01897477814105558, "grad_norm": 0.8382568359375, "learning_rate": 1.8943374197314654e-06, "loss": 0.2623, "step": 650 }, { "epoch": 0.019003970107426438, "grad_norm": 0.7519186735153198, "learning_rate": 1.8972562755399885e-06, "loss": 0.2761, "step": 651 }, { "epoch": 0.01903316207379729, "grad_norm": 0.9496391415596008, "learning_rate": 1.9001751313485114e-06, "loss": 0.2479, "step": 652 }, { "epoch": 0.019062354040168147, "grad_norm": 1.0461069345474243, "learning_rate": 1.9030939871570345e-06, "loss": 0.2907, "step": 653 }, { "epoch": 0.019091546006539, "grad_norm": 0.9422182440757751, "learning_rate": 1.9060128429655577e-06, "loss": 0.2649, "step": 654 }, { "epoch": 0.019120737972909856, "grad_norm": 0.8061745762825012, "learning_rate": 1.9089316987740806e-06, "loss": 0.2782, "step": 655 }, { "epoch": 0.01914992993928071, "grad_norm": 0.7784531712532043, "learning_rate": 1.911850554582604e-06, "loss": 0.2724, "step": 656 }, { "epoch": 0.019179121905651565, "grad_norm": 1.252249836921692, "learning_rate": 1.914769410391127e-06, "loss": 0.2532, "step": 657 }, { "epoch": 0.01920831387202242, "grad_norm": 1.7698204517364502, "learning_rate": 1.9176882661996498e-06, "loss": 0.2934, "step": 658 }, { "epoch": 0.019237505838393273, "grad_norm": 0.6974249482154846, "learning_rate": 1.920607122008173e-06, "loss": 0.2752, "step": 659 }, { "epoch": 0.01926669780476413, "grad_norm": 0.901716411113739, "learning_rate": 1.923525977816696e-06, "loss": 0.3071, "step": 660 }, { "epoch": 0.019295889771134982, "grad_norm": 2.118553638458252, "learning_rate": 1.926444833625219e-06, "loss": 0.3456, "step": 661 }, { "epoch": 0.01932508173750584, "grad_norm": 1.3188799619674683, "learning_rate": 1.9293636894337423e-06, "loss": 0.2791, "step": 662 }, { "epoch": 0.019354273703876695, "grad_norm": 0.7943978905677795, "learning_rate": 1.932282545242265e-06, "loss": 0.2876, "step": 663 }, { "epoch": 0.019383465670247547, "grad_norm": 0.6507450342178345, "learning_rate": 1.935201401050788e-06, "loss": 0.2401, "step": 664 }, { "epoch": 0.019412657636618404, "grad_norm": 7.0794854164123535, "learning_rate": 1.9381202568593115e-06, "loss": 0.3214, "step": 665 }, { "epoch": 0.019441849602989256, "grad_norm": 0.6870044469833374, "learning_rate": 1.9410391126678344e-06, "loss": 0.2689, "step": 666 }, { "epoch": 0.019471041569360113, "grad_norm": 1.0985251665115356, "learning_rate": 1.9439579684763573e-06, "loss": 0.294, "step": 667 }, { "epoch": 0.019500233535730965, "grad_norm": 1.4351065158843994, "learning_rate": 1.94687682428488e-06, "loss": 0.2285, "step": 668 }, { "epoch": 0.01952942550210182, "grad_norm": 0.7348394989967346, "learning_rate": 1.9497956800934035e-06, "loss": 0.274, "step": 669 }, { "epoch": 0.019558617468472678, "grad_norm": 1.3417061567306519, "learning_rate": 1.952714535901927e-06, "loss": 0.2907, "step": 670 }, { "epoch": 0.01958780943484353, "grad_norm": 0.7314900755882263, "learning_rate": 1.95563339171045e-06, "loss": 0.2388, "step": 671 }, { "epoch": 0.019617001401214387, "grad_norm": 1.0078363418579102, "learning_rate": 1.9585522475189727e-06, "loss": 0.2477, "step": 672 }, { "epoch": 0.01964619336758524, "grad_norm": 0.7355387210845947, "learning_rate": 1.9614711033274956e-06, "loss": 0.2883, "step": 673 }, { "epoch": 0.019675385333956096, "grad_norm": 0.7317847013473511, "learning_rate": 1.964389959136019e-06, "loss": 0.2644, "step": 674 }, { "epoch": 0.01970457730032695, "grad_norm": 1.3410682678222656, "learning_rate": 1.967308814944542e-06, "loss": 0.3062, "step": 675 }, { "epoch": 0.019733769266697804, "grad_norm": 0.6873302459716797, "learning_rate": 1.970227670753065e-06, "loss": 0.2971, "step": 676 }, { "epoch": 0.01976296123306866, "grad_norm": 1.282454013824463, "learning_rate": 1.9731465265615877e-06, "loss": 0.2572, "step": 677 }, { "epoch": 0.019792153199439513, "grad_norm": 0.8579092025756836, "learning_rate": 1.976065382370111e-06, "loss": 0.2533, "step": 678 }, { "epoch": 0.01982134516581037, "grad_norm": 0.697985053062439, "learning_rate": 1.9789842381786344e-06, "loss": 0.3825, "step": 679 }, { "epoch": 0.019850537132181222, "grad_norm": 0.8005879521369934, "learning_rate": 1.9819030939871573e-06, "loss": 0.2299, "step": 680 }, { "epoch": 0.01987972909855208, "grad_norm": 2.133565902709961, "learning_rate": 1.9848219497956802e-06, "loss": 0.2604, "step": 681 }, { "epoch": 0.019908921064922935, "grad_norm": 1.1783949136734009, "learning_rate": 1.987740805604203e-06, "loss": 0.2465, "step": 682 }, { "epoch": 0.019938113031293787, "grad_norm": 0.8572841286659241, "learning_rate": 1.9906596614127265e-06, "loss": 0.2574, "step": 683 }, { "epoch": 0.019967304997664644, "grad_norm": 0.7803316712379456, "learning_rate": 1.9935785172212494e-06, "loss": 0.2592, "step": 684 }, { "epoch": 0.019996496964035496, "grad_norm": 4.6782684326171875, "learning_rate": 1.9964973730297723e-06, "loss": 0.2452, "step": 685 }, { "epoch": 0.020025688930406352, "grad_norm": 0.9829795956611633, "learning_rate": 1.9994162288382957e-06, "loss": 0.2675, "step": 686 }, { "epoch": 0.020054880896777205, "grad_norm": 0.8540976047515869, "learning_rate": 2.0023350846468186e-06, "loss": 0.2933, "step": 687 }, { "epoch": 0.02008407286314806, "grad_norm": 1.0613253116607666, "learning_rate": 2.005253940455342e-06, "loss": 0.2499, "step": 688 }, { "epoch": 0.020113264829518918, "grad_norm": 0.6105601787567139, "learning_rate": 2.008172796263865e-06, "loss": 0.2486, "step": 689 }, { "epoch": 0.02014245679588977, "grad_norm": 1.0446902513504028, "learning_rate": 2.0110916520723878e-06, "loss": 0.2522, "step": 690 }, { "epoch": 0.020171648762260627, "grad_norm": 0.733888566493988, "learning_rate": 2.0140105078809107e-06, "loss": 0.2754, "step": 691 }, { "epoch": 0.02020084072863148, "grad_norm": 0.6968584656715393, "learning_rate": 2.016929363689434e-06, "loss": 0.2336, "step": 692 }, { "epoch": 0.020230032695002335, "grad_norm": 0.6252506971359253, "learning_rate": 2.019848219497957e-06, "loss": 0.2623, "step": 693 }, { "epoch": 0.02025922466137319, "grad_norm": 1.5119869709014893, "learning_rate": 2.0227670753064803e-06, "loss": 0.2425, "step": 694 }, { "epoch": 0.020288416627744044, "grad_norm": 0.6921567916870117, "learning_rate": 2.025685931115003e-06, "loss": 0.2281, "step": 695 }, { "epoch": 0.0203176085941149, "grad_norm": 1.042282223701477, "learning_rate": 2.028604786923526e-06, "loss": 0.2249, "step": 696 }, { "epoch": 0.020346800560485753, "grad_norm": 0.745025098323822, "learning_rate": 2.031523642732049e-06, "loss": 0.2723, "step": 697 }, { "epoch": 0.02037599252685661, "grad_norm": 0.9066844582557678, "learning_rate": 2.0344424985405724e-06, "loss": 0.2339, "step": 698 }, { "epoch": 0.020405184493227462, "grad_norm": 0.6962234973907471, "learning_rate": 2.0373613543490953e-06, "loss": 0.2726, "step": 699 }, { "epoch": 0.02043437645959832, "grad_norm": 0.8258652091026306, "learning_rate": 2.040280210157618e-06, "loss": 0.3304, "step": 700 }, { "epoch": 0.020463568425969175, "grad_norm": 0.9436120390892029, "learning_rate": 2.043199065966141e-06, "loss": 0.2953, "step": 701 }, { "epoch": 0.020492760392340027, "grad_norm": 1.6605278253555298, "learning_rate": 2.0461179217746644e-06, "loss": 0.2855, "step": 702 }, { "epoch": 0.020521952358710883, "grad_norm": 1.1340409517288208, "learning_rate": 2.0490367775831878e-06, "loss": 0.2375, "step": 703 }, { "epoch": 0.020551144325081736, "grad_norm": 0.793755292892456, "learning_rate": 2.0519556333917107e-06, "loss": 0.2858, "step": 704 }, { "epoch": 0.020580336291452592, "grad_norm": 0.5863512754440308, "learning_rate": 2.0548744892002336e-06, "loss": 0.2654, "step": 705 }, { "epoch": 0.02060952825782345, "grad_norm": 0.6426361799240112, "learning_rate": 2.0577933450087565e-06, "loss": 0.2617, "step": 706 }, { "epoch": 0.0206387202241943, "grad_norm": 0.6100160479545593, "learning_rate": 2.06071220081728e-06, "loss": 0.2596, "step": 707 }, { "epoch": 0.020667912190565157, "grad_norm": 0.8827059864997864, "learning_rate": 2.063631056625803e-06, "loss": 0.3148, "step": 708 }, { "epoch": 0.02069710415693601, "grad_norm": 0.6310570240020752, "learning_rate": 2.0665499124343257e-06, "loss": 0.2166, "step": 709 }, { "epoch": 0.020726296123306866, "grad_norm": 0.6489300727844238, "learning_rate": 2.069468768242849e-06, "loss": 0.2628, "step": 710 }, { "epoch": 0.02075548808967772, "grad_norm": 0.9179422855377197, "learning_rate": 2.072387624051372e-06, "loss": 0.2658, "step": 711 }, { "epoch": 0.020784680056048575, "grad_norm": 0.6433684825897217, "learning_rate": 2.0753064798598953e-06, "loss": 0.2272, "step": 712 }, { "epoch": 0.02081387202241943, "grad_norm": 0.6859923005104065, "learning_rate": 2.0782253356684182e-06, "loss": 0.246, "step": 713 }, { "epoch": 0.020843063988790284, "grad_norm": 0.8874054551124573, "learning_rate": 2.081144191476941e-06, "loss": 0.2506, "step": 714 }, { "epoch": 0.02087225595516114, "grad_norm": 2.296815872192383, "learning_rate": 2.084063047285464e-06, "loss": 0.2746, "step": 715 }, { "epoch": 0.020901447921531993, "grad_norm": 1.2709120512008667, "learning_rate": 2.0869819030939874e-06, "loss": 0.3076, "step": 716 }, { "epoch": 0.02093063988790285, "grad_norm": 2.518179416656494, "learning_rate": 2.0899007589025103e-06, "loss": 0.2494, "step": 717 }, { "epoch": 0.020959831854273706, "grad_norm": 0.7082214951515198, "learning_rate": 2.0928196147110337e-06, "loss": 0.244, "step": 718 }, { "epoch": 0.02098902382064456, "grad_norm": 0.6551937460899353, "learning_rate": 2.0957384705195566e-06, "loss": 0.3062, "step": 719 }, { "epoch": 0.021018215787015414, "grad_norm": 0.704580545425415, "learning_rate": 2.0986573263280795e-06, "loss": 0.2442, "step": 720 }, { "epoch": 0.021047407753386267, "grad_norm": 0.7255812883377075, "learning_rate": 2.101576182136603e-06, "loss": 0.299, "step": 721 }, { "epoch": 0.021076599719757123, "grad_norm": 0.689263105392456, "learning_rate": 2.1044950379451257e-06, "loss": 0.2966, "step": 722 }, { "epoch": 0.021105791686127976, "grad_norm": 0.7709303498268127, "learning_rate": 2.1074138937536487e-06, "loss": 0.2799, "step": 723 }, { "epoch": 0.021134983652498832, "grad_norm": 0.618709921836853, "learning_rate": 2.1103327495621716e-06, "loss": 0.2352, "step": 724 }, { "epoch": 0.02116417561886969, "grad_norm": 0.6639534831047058, "learning_rate": 2.113251605370695e-06, "loss": 0.2717, "step": 725 }, { "epoch": 0.02119336758524054, "grad_norm": 0.6515131592750549, "learning_rate": 2.116170461179218e-06, "loss": 0.2709, "step": 726 }, { "epoch": 0.021222559551611397, "grad_norm": 0.7203176021575928, "learning_rate": 2.119089316987741e-06, "loss": 0.292, "step": 727 }, { "epoch": 0.02125175151798225, "grad_norm": 0.6298820972442627, "learning_rate": 2.122008172796264e-06, "loss": 0.2653, "step": 728 }, { "epoch": 0.021280943484353106, "grad_norm": 0.7868027091026306, "learning_rate": 2.124927028604787e-06, "loss": 0.2709, "step": 729 }, { "epoch": 0.02131013545072396, "grad_norm": 0.6085988283157349, "learning_rate": 2.1278458844133103e-06, "loss": 0.2202, "step": 730 }, { "epoch": 0.021339327417094815, "grad_norm": 0.6533672213554382, "learning_rate": 2.1307647402218333e-06, "loss": 0.2036, "step": 731 }, { "epoch": 0.02136851938346567, "grad_norm": 0.8361082673072815, "learning_rate": 2.133683596030356e-06, "loss": 0.2771, "step": 732 }, { "epoch": 0.021397711349836524, "grad_norm": 0.775014340877533, "learning_rate": 2.136602451838879e-06, "loss": 0.2813, "step": 733 }, { "epoch": 0.02142690331620738, "grad_norm": 0.7616864442825317, "learning_rate": 2.1395213076474024e-06, "loss": 0.2739, "step": 734 }, { "epoch": 0.021456095282578233, "grad_norm": 0.8635480403900146, "learning_rate": 2.1424401634559254e-06, "loss": 0.2713, "step": 735 }, { "epoch": 0.02148528724894909, "grad_norm": 0.6438086032867432, "learning_rate": 2.1453590192644487e-06, "loss": 0.3359, "step": 736 }, { "epoch": 0.021514479215319945, "grad_norm": 0.7017611861228943, "learning_rate": 2.1482778750729716e-06, "loss": 0.3425, "step": 737 }, { "epoch": 0.021543671181690798, "grad_norm": 0.7886499762535095, "learning_rate": 2.1511967308814945e-06, "loss": 0.2583, "step": 738 }, { "epoch": 0.021572863148061654, "grad_norm": 0.6961781978607178, "learning_rate": 2.1541155866900174e-06, "loss": 0.3052, "step": 739 }, { "epoch": 0.021602055114432507, "grad_norm": 0.8280938267707825, "learning_rate": 2.1570344424985408e-06, "loss": 0.2635, "step": 740 }, { "epoch": 0.021631247080803363, "grad_norm": 0.6927745938301086, "learning_rate": 2.1599532983070637e-06, "loss": 0.2806, "step": 741 }, { "epoch": 0.021660439047174216, "grad_norm": 0.8797507286071777, "learning_rate": 2.162872154115587e-06, "loss": 0.2636, "step": 742 }, { "epoch": 0.021689631013545072, "grad_norm": 0.6949967741966248, "learning_rate": 2.16579100992411e-06, "loss": 0.2992, "step": 743 }, { "epoch": 0.02171882297991593, "grad_norm": 0.9647451639175415, "learning_rate": 2.168709865732633e-06, "loss": 0.2737, "step": 744 }, { "epoch": 0.02174801494628678, "grad_norm": 0.6437510251998901, "learning_rate": 2.171628721541156e-06, "loss": 0.2696, "step": 745 }, { "epoch": 0.021777206912657637, "grad_norm": 0.7152248024940491, "learning_rate": 2.174547577349679e-06, "loss": 0.2644, "step": 746 }, { "epoch": 0.02180639887902849, "grad_norm": 1.0679596662521362, "learning_rate": 2.177466433158202e-06, "loss": 0.2347, "step": 747 }, { "epoch": 0.021835590845399346, "grad_norm": 1.3238459825515747, "learning_rate": 2.180385288966725e-06, "loss": 0.2396, "step": 748 }, { "epoch": 0.021864782811770202, "grad_norm": 0.8952926397323608, "learning_rate": 2.1833041447752483e-06, "loss": 0.298, "step": 749 }, { "epoch": 0.021893974778141055, "grad_norm": 0.7531613111495972, "learning_rate": 2.1862230005837716e-06, "loss": 0.245, "step": 750 }, { "epoch": 0.02192316674451191, "grad_norm": 0.8151116371154785, "learning_rate": 2.1891418563922946e-06, "loss": 0.2652, "step": 751 }, { "epoch": 0.021952358710882764, "grad_norm": 0.6858235001564026, "learning_rate": 2.1920607122008175e-06, "loss": 0.2255, "step": 752 }, { "epoch": 0.02198155067725362, "grad_norm": 0.729012668132782, "learning_rate": 2.1949795680093404e-06, "loss": 0.2488, "step": 753 }, { "epoch": 0.022010742643624473, "grad_norm": 0.8891887664794922, "learning_rate": 2.1978984238178637e-06, "loss": 0.2548, "step": 754 }, { "epoch": 0.02203993460999533, "grad_norm": 0.6759095788002014, "learning_rate": 2.2008172796263866e-06, "loss": 0.2768, "step": 755 }, { "epoch": 0.022069126576366185, "grad_norm": 0.6419289112091064, "learning_rate": 2.2037361354349096e-06, "loss": 0.2967, "step": 756 }, { "epoch": 0.022098318542737038, "grad_norm": 0.7146408557891846, "learning_rate": 2.2066549912434325e-06, "loss": 0.2377, "step": 757 }, { "epoch": 0.022127510509107894, "grad_norm": 0.6200879812240601, "learning_rate": 2.209573847051956e-06, "loss": 0.2054, "step": 758 }, { "epoch": 0.022156702475478747, "grad_norm": 0.9552193284034729, "learning_rate": 2.212492702860479e-06, "loss": 0.2646, "step": 759 }, { "epoch": 0.022185894441849603, "grad_norm": 1.1351326704025269, "learning_rate": 2.215411558669002e-06, "loss": 0.2885, "step": 760 }, { "epoch": 0.02221508640822046, "grad_norm": 1.124153971672058, "learning_rate": 2.218330414477525e-06, "loss": 0.2963, "step": 761 }, { "epoch": 0.022244278374591312, "grad_norm": 2.931394577026367, "learning_rate": 2.221249270286048e-06, "loss": 0.2803, "step": 762 }, { "epoch": 0.02227347034096217, "grad_norm": 0.9433314204216003, "learning_rate": 2.2241681260945713e-06, "loss": 0.2436, "step": 763 }, { "epoch": 0.02230266230733302, "grad_norm": 0.591712236404419, "learning_rate": 2.227086981903094e-06, "loss": 0.2491, "step": 764 }, { "epoch": 0.022331854273703877, "grad_norm": 0.7630010843276978, "learning_rate": 2.230005837711617e-06, "loss": 0.2587, "step": 765 }, { "epoch": 0.02236104624007473, "grad_norm": 0.6574616432189941, "learning_rate": 2.2329246935201404e-06, "loss": 0.2824, "step": 766 }, { "epoch": 0.022390238206445586, "grad_norm": 1.9435666799545288, "learning_rate": 2.2358435493286633e-06, "loss": 0.2409, "step": 767 }, { "epoch": 0.022419430172816442, "grad_norm": 0.8592404127120972, "learning_rate": 2.2387624051371863e-06, "loss": 0.2382, "step": 768 }, { "epoch": 0.022448622139187295, "grad_norm": 0.9213184714317322, "learning_rate": 2.2416812609457096e-06, "loss": 0.2882, "step": 769 }, { "epoch": 0.02247781410555815, "grad_norm": 0.5791005492210388, "learning_rate": 2.2446001167542325e-06, "loss": 0.3172, "step": 770 }, { "epoch": 0.022507006071929004, "grad_norm": 0.6376338601112366, "learning_rate": 2.2475189725627554e-06, "loss": 0.2715, "step": 771 }, { "epoch": 0.02253619803829986, "grad_norm": 0.9406659007072449, "learning_rate": 2.2504378283712783e-06, "loss": 0.2422, "step": 772 }, { "epoch": 0.022565390004670716, "grad_norm": 1.1346890926361084, "learning_rate": 2.2533566841798017e-06, "loss": 0.3024, "step": 773 }, { "epoch": 0.02259458197104157, "grad_norm": 0.6284245848655701, "learning_rate": 2.256275539988325e-06, "loss": 0.2556, "step": 774 }, { "epoch": 0.022623773937412425, "grad_norm": 0.9752086997032166, "learning_rate": 2.259194395796848e-06, "loss": 0.2612, "step": 775 }, { "epoch": 0.022652965903783278, "grad_norm": 1.0834112167358398, "learning_rate": 2.262113251605371e-06, "loss": 0.2696, "step": 776 }, { "epoch": 0.022682157870154134, "grad_norm": 0.970538854598999, "learning_rate": 2.2650321074138938e-06, "loss": 0.2637, "step": 777 }, { "epoch": 0.022711349836524987, "grad_norm": 0.6823408007621765, "learning_rate": 2.267950963222417e-06, "loss": 0.2756, "step": 778 }, { "epoch": 0.022740541802895843, "grad_norm": 0.7194157838821411, "learning_rate": 2.27086981903094e-06, "loss": 0.2619, "step": 779 }, { "epoch": 0.0227697337692667, "grad_norm": 0.6985321044921875, "learning_rate": 2.273788674839463e-06, "loss": 0.2934, "step": 780 }, { "epoch": 0.022798925735637552, "grad_norm": 0.6893346309661865, "learning_rate": 2.276707530647986e-06, "loss": 0.2825, "step": 781 }, { "epoch": 0.022828117702008408, "grad_norm": 0.6192165017127991, "learning_rate": 2.279626386456509e-06, "loss": 0.2595, "step": 782 }, { "epoch": 0.02285730966837926, "grad_norm": 0.8244407176971436, "learning_rate": 2.2825452422650325e-06, "loss": 0.2766, "step": 783 }, { "epoch": 0.022886501634750117, "grad_norm": 0.6750024557113647, "learning_rate": 2.2854640980735555e-06, "loss": 0.2547, "step": 784 }, { "epoch": 0.02291569360112097, "grad_norm": 0.5940267443656921, "learning_rate": 2.2883829538820784e-06, "loss": 0.2381, "step": 785 }, { "epoch": 0.022944885567491826, "grad_norm": 0.8778386116027832, "learning_rate": 2.2913018096906013e-06, "loss": 0.2748, "step": 786 }, { "epoch": 0.022974077533862682, "grad_norm": 0.7067516446113586, "learning_rate": 2.2942206654991246e-06, "loss": 0.2078, "step": 787 }, { "epoch": 0.023003269500233535, "grad_norm": 0.6144875288009644, "learning_rate": 2.2971395213076476e-06, "loss": 0.2319, "step": 788 }, { "epoch": 0.02303246146660439, "grad_norm": 1.1536132097244263, "learning_rate": 2.3000583771161705e-06, "loss": 0.2371, "step": 789 }, { "epoch": 0.023061653432975244, "grad_norm": 1.3816277980804443, "learning_rate": 2.302977232924694e-06, "loss": 0.2859, "step": 790 }, { "epoch": 0.0230908453993461, "grad_norm": 0.63425612449646, "learning_rate": 2.3058960887332167e-06, "loss": 0.2571, "step": 791 }, { "epoch": 0.023120037365716956, "grad_norm": 0.9364064335823059, "learning_rate": 2.30881494454174e-06, "loss": 0.2595, "step": 792 }, { "epoch": 0.02314922933208781, "grad_norm": 0.722260057926178, "learning_rate": 2.311733800350263e-06, "loss": 0.2855, "step": 793 }, { "epoch": 0.023178421298458665, "grad_norm": 0.9036427140235901, "learning_rate": 2.314652656158786e-06, "loss": 0.2615, "step": 794 }, { "epoch": 0.023207613264829518, "grad_norm": 0.6980794072151184, "learning_rate": 2.317571511967309e-06, "loss": 0.2834, "step": 795 }, { "epoch": 0.023236805231200374, "grad_norm": 1.0563374757766724, "learning_rate": 2.320490367775832e-06, "loss": 0.2937, "step": 796 }, { "epoch": 0.023265997197571227, "grad_norm": 0.5500457286834717, "learning_rate": 2.323409223584355e-06, "loss": 0.2537, "step": 797 }, { "epoch": 0.023295189163942083, "grad_norm": 0.6565116047859192, "learning_rate": 2.3263280793928784e-06, "loss": 0.2925, "step": 798 }, { "epoch": 0.02332438113031294, "grad_norm": 0.6858528852462769, "learning_rate": 2.3292469352014013e-06, "loss": 0.2625, "step": 799 }, { "epoch": 0.023353573096683792, "grad_norm": 0.7145271897315979, "learning_rate": 2.3321657910099242e-06, "loss": 0.2752, "step": 800 }, { "epoch": 0.023382765063054648, "grad_norm": 0.5657581090927124, "learning_rate": 2.3350846468184476e-06, "loss": 0.2175, "step": 801 }, { "epoch": 0.0234119570294255, "grad_norm": 0.6825459003448486, "learning_rate": 2.3380035026269705e-06, "loss": 0.2672, "step": 802 }, { "epoch": 0.023441148995796357, "grad_norm": 0.8629727363586426, "learning_rate": 2.3409223584354934e-06, "loss": 0.3068, "step": 803 }, { "epoch": 0.023470340962167213, "grad_norm": 0.6853780746459961, "learning_rate": 2.3438412142440163e-06, "loss": 0.2684, "step": 804 }, { "epoch": 0.023499532928538066, "grad_norm": 0.6431028842926025, "learning_rate": 2.3467600700525397e-06, "loss": 0.245, "step": 805 }, { "epoch": 0.023528724894908922, "grad_norm": 1.177758812904358, "learning_rate": 2.3496789258610626e-06, "loss": 0.2146, "step": 806 }, { "epoch": 0.023557916861279775, "grad_norm": 0.5641828179359436, "learning_rate": 2.352597781669586e-06, "loss": 0.2362, "step": 807 }, { "epoch": 0.02358710882765063, "grad_norm": 0.6900002360343933, "learning_rate": 2.355516637478109e-06, "loss": 0.2895, "step": 808 }, { "epoch": 0.023616300794021484, "grad_norm": 0.6214496493339539, "learning_rate": 2.3584354932866318e-06, "loss": 0.2722, "step": 809 }, { "epoch": 0.02364549276039234, "grad_norm": 0.8165213465690613, "learning_rate": 2.3613543490951547e-06, "loss": 0.3211, "step": 810 }, { "epoch": 0.023674684726763196, "grad_norm": 0.6382678151130676, "learning_rate": 2.364273204903678e-06, "loss": 0.2679, "step": 811 }, { "epoch": 0.02370387669313405, "grad_norm": 0.7585796117782593, "learning_rate": 2.367192060712201e-06, "loss": 0.2409, "step": 812 }, { "epoch": 0.023733068659504905, "grad_norm": 1.0328975915908813, "learning_rate": 2.370110916520724e-06, "loss": 0.2561, "step": 813 }, { "epoch": 0.023762260625875758, "grad_norm": 1.1452442407608032, "learning_rate": 2.373029772329247e-06, "loss": 0.2704, "step": 814 }, { "epoch": 0.023791452592246614, "grad_norm": 0.6887352466583252, "learning_rate": 2.37594862813777e-06, "loss": 0.2831, "step": 815 }, { "epoch": 0.02382064455861747, "grad_norm": 0.6013804078102112, "learning_rate": 2.3788674839462935e-06, "loss": 0.2759, "step": 816 }, { "epoch": 0.023849836524988323, "grad_norm": 0.6674723625183105, "learning_rate": 2.3817863397548164e-06, "loss": 0.2703, "step": 817 }, { "epoch": 0.02387902849135918, "grad_norm": 0.6557148098945618, "learning_rate": 2.3847051955633393e-06, "loss": 0.2343, "step": 818 }, { "epoch": 0.023908220457730032, "grad_norm": 1.0475596189498901, "learning_rate": 2.387624051371862e-06, "loss": 0.27, "step": 819 }, { "epoch": 0.023937412424100888, "grad_norm": 1.1505030393600464, "learning_rate": 2.3905429071803855e-06, "loss": 0.2483, "step": 820 }, { "epoch": 0.02396660439047174, "grad_norm": 0.6251376271247864, "learning_rate": 2.3934617629889085e-06, "loss": 0.2358, "step": 821 }, { "epoch": 0.023995796356842597, "grad_norm": 0.5998872518539429, "learning_rate": 2.396380618797432e-06, "loss": 0.2549, "step": 822 }, { "epoch": 0.024024988323213453, "grad_norm": 1.0383175611495972, "learning_rate": 2.3992994746059547e-06, "loss": 0.3157, "step": 823 }, { "epoch": 0.024054180289584306, "grad_norm": 0.7561010122299194, "learning_rate": 2.4022183304144776e-06, "loss": 0.2901, "step": 824 }, { "epoch": 0.024083372255955162, "grad_norm": 0.6650879383087158, "learning_rate": 2.405137186223001e-06, "loss": 0.2735, "step": 825 }, { "epoch": 0.024112564222326015, "grad_norm": 0.7340614199638367, "learning_rate": 2.408056042031524e-06, "loss": 0.3068, "step": 826 }, { "epoch": 0.02414175618869687, "grad_norm": 0.8546027541160583, "learning_rate": 2.410974897840047e-06, "loss": 0.2443, "step": 827 }, { "epoch": 0.024170948155067724, "grad_norm": 0.700517475605011, "learning_rate": 2.4138937536485697e-06, "loss": 0.3094, "step": 828 }, { "epoch": 0.02420014012143858, "grad_norm": 0.7933600544929504, "learning_rate": 2.416812609457093e-06, "loss": 0.3317, "step": 829 }, { "epoch": 0.024229332087809436, "grad_norm": 0.6192914247512817, "learning_rate": 2.4197314652656164e-06, "loss": 0.2398, "step": 830 }, { "epoch": 0.02425852405418029, "grad_norm": 0.6738988161087036, "learning_rate": 2.4226503210741393e-06, "loss": 0.2778, "step": 831 }, { "epoch": 0.024287716020551145, "grad_norm": 0.5855032205581665, "learning_rate": 2.4255691768826622e-06, "loss": 0.2392, "step": 832 }, { "epoch": 0.024316907986921998, "grad_norm": 0.6800257563591003, "learning_rate": 2.428488032691185e-06, "loss": 0.2795, "step": 833 }, { "epoch": 0.024346099953292854, "grad_norm": 0.6521876454353333, "learning_rate": 2.4314068884997085e-06, "loss": 0.2914, "step": 834 }, { "epoch": 0.02437529191966371, "grad_norm": 0.9237068295478821, "learning_rate": 2.4343257443082314e-06, "loss": 0.2495, "step": 835 }, { "epoch": 0.024404483886034563, "grad_norm": 0.6165127754211426, "learning_rate": 2.4372446001167543e-06, "loss": 0.2845, "step": 836 }, { "epoch": 0.02443367585240542, "grad_norm": 0.6796885132789612, "learning_rate": 2.4401634559252772e-06, "loss": 0.2614, "step": 837 }, { "epoch": 0.02446286781877627, "grad_norm": 0.8288146257400513, "learning_rate": 2.4430823117338006e-06, "loss": 0.3658, "step": 838 }, { "epoch": 0.024492059785147128, "grad_norm": 0.6388978958129883, "learning_rate": 2.4460011675423235e-06, "loss": 0.2705, "step": 839 }, { "epoch": 0.02452125175151798, "grad_norm": 0.6282212734222412, "learning_rate": 2.448920023350847e-06, "loss": 0.2498, "step": 840 }, { "epoch": 0.024550443717888837, "grad_norm": 0.689423143863678, "learning_rate": 2.4518388791593698e-06, "loss": 0.287, "step": 841 }, { "epoch": 0.024579635684259693, "grad_norm": 0.5414408445358276, "learning_rate": 2.4547577349678927e-06, "loss": 0.229, "step": 842 }, { "epoch": 0.024608827650630546, "grad_norm": 0.8632596731185913, "learning_rate": 2.4576765907764156e-06, "loss": 0.2988, "step": 843 }, { "epoch": 0.024638019617001402, "grad_norm": 0.7805605530738831, "learning_rate": 2.460595446584939e-06, "loss": 0.253, "step": 844 }, { "epoch": 0.024667211583372255, "grad_norm": 0.5707309246063232, "learning_rate": 2.463514302393462e-06, "loss": 0.2534, "step": 845 }, { "epoch": 0.02469640354974311, "grad_norm": 0.5275145769119263, "learning_rate": 2.466433158201985e-06, "loss": 0.2278, "step": 846 }, { "epoch": 0.024725595516113967, "grad_norm": 0.7434000372886658, "learning_rate": 2.469352014010508e-06, "loss": 0.2776, "step": 847 }, { "epoch": 0.02475478748248482, "grad_norm": 0.6599705815315247, "learning_rate": 2.472270869819031e-06, "loss": 0.2824, "step": 848 }, { "epoch": 0.024783979448855676, "grad_norm": 1.2701810598373413, "learning_rate": 2.4751897256275544e-06, "loss": 0.2222, "step": 849 }, { "epoch": 0.02481317141522653, "grad_norm": 0.8316946029663086, "learning_rate": 2.4781085814360773e-06, "loss": 0.2325, "step": 850 }, { "epoch": 0.024842363381597385, "grad_norm": 0.7210825681686401, "learning_rate": 2.4810274372446e-06, "loss": 0.2697, "step": 851 }, { "epoch": 0.024871555347968238, "grad_norm": 1.4047353267669678, "learning_rate": 2.483946293053123e-06, "loss": 0.2582, "step": 852 }, { "epoch": 0.024900747314339094, "grad_norm": 0.8082929849624634, "learning_rate": 2.4868651488616464e-06, "loss": 0.3138, "step": 853 }, { "epoch": 0.02492993928070995, "grad_norm": 0.7295948266983032, "learning_rate": 2.4897840046701698e-06, "loss": 0.2566, "step": 854 }, { "epoch": 0.024959131247080803, "grad_norm": 0.7856608629226685, "learning_rate": 2.4927028604786927e-06, "loss": 0.2713, "step": 855 }, { "epoch": 0.02498832321345166, "grad_norm": 0.5766000747680664, "learning_rate": 2.4956217162872156e-06, "loss": 0.2824, "step": 856 }, { "epoch": 0.02501751517982251, "grad_norm": 0.6990286707878113, "learning_rate": 2.4985405720957385e-06, "loss": 0.3185, "step": 857 }, { "epoch": 0.025046707146193368, "grad_norm": 0.5923239588737488, "learning_rate": 2.501459427904262e-06, "loss": 0.2695, "step": 858 }, { "epoch": 0.025075899112564224, "grad_norm": 0.6113525629043579, "learning_rate": 2.5043782837127852e-06, "loss": 0.2708, "step": 859 }, { "epoch": 0.025105091078935077, "grad_norm": 0.7920759320259094, "learning_rate": 2.507297139521308e-06, "loss": 0.3018, "step": 860 }, { "epoch": 0.025134283045305933, "grad_norm": 0.6091545820236206, "learning_rate": 2.510215995329831e-06, "loss": 0.255, "step": 861 }, { "epoch": 0.025163475011676786, "grad_norm": 0.7249767780303955, "learning_rate": 2.513134851138354e-06, "loss": 0.2683, "step": 862 }, { "epoch": 0.025192666978047642, "grad_norm": 0.569972574710846, "learning_rate": 2.5160537069468773e-06, "loss": 0.218, "step": 863 }, { "epoch": 0.025221858944418495, "grad_norm": 0.6776538491249084, "learning_rate": 2.5189725627554002e-06, "loss": 0.3085, "step": 864 }, { "epoch": 0.02525105091078935, "grad_norm": 1.0676790475845337, "learning_rate": 2.521891418563923e-06, "loss": 0.3157, "step": 865 }, { "epoch": 0.025280242877160207, "grad_norm": 0.6969829797744751, "learning_rate": 2.524810274372446e-06, "loss": 0.2763, "step": 866 }, { "epoch": 0.02530943484353106, "grad_norm": 0.8361960649490356, "learning_rate": 2.5277291301809694e-06, "loss": 0.2468, "step": 867 }, { "epoch": 0.025338626809901916, "grad_norm": 0.6603217720985413, "learning_rate": 2.5306479859894923e-06, "loss": 0.2453, "step": 868 }, { "epoch": 0.02536781877627277, "grad_norm": 0.9464702010154724, "learning_rate": 2.5335668417980152e-06, "loss": 0.302, "step": 869 }, { "epoch": 0.025397010742643625, "grad_norm": 0.7484486103057861, "learning_rate": 2.536485697606538e-06, "loss": 0.2859, "step": 870 }, { "epoch": 0.025426202709014478, "grad_norm": 0.5698336958885193, "learning_rate": 2.5394045534150615e-06, "loss": 0.2762, "step": 871 }, { "epoch": 0.025455394675385334, "grad_norm": 0.6229810118675232, "learning_rate": 2.5423234092235844e-06, "loss": 0.2688, "step": 872 }, { "epoch": 0.02548458664175619, "grad_norm": 1.0850276947021484, "learning_rate": 2.5452422650321073e-06, "loss": 0.2448, "step": 873 }, { "epoch": 0.025513778608127043, "grad_norm": 0.5591463446617126, "learning_rate": 2.548161120840631e-06, "loss": 0.2392, "step": 874 }, { "epoch": 0.0255429705744979, "grad_norm": 0.48588863015174866, "learning_rate": 2.551079976649154e-06, "loss": 0.2163, "step": 875 }, { "epoch": 0.02557216254086875, "grad_norm": 1.654880404472351, "learning_rate": 2.553998832457677e-06, "loss": 0.263, "step": 876 }, { "epoch": 0.025601354507239608, "grad_norm": 0.7599248290061951, "learning_rate": 2.5569176882662e-06, "loss": 0.3064, "step": 877 }, { "epoch": 0.025630546473610464, "grad_norm": 0.63886559009552, "learning_rate": 2.559836544074723e-06, "loss": 0.2968, "step": 878 }, { "epoch": 0.025659738439981317, "grad_norm": 0.5814223885536194, "learning_rate": 2.562755399883246e-06, "loss": 0.272, "step": 879 }, { "epoch": 0.025688930406352173, "grad_norm": 1.255150556564331, "learning_rate": 2.565674255691769e-06, "loss": 0.2311, "step": 880 }, { "epoch": 0.025718122372723026, "grad_norm": 0.5934061408042908, "learning_rate": 2.568593111500292e-06, "loss": 0.2625, "step": 881 }, { "epoch": 0.025747314339093882, "grad_norm": 1.108185052871704, "learning_rate": 2.5715119673088153e-06, "loss": 0.2883, "step": 882 }, { "epoch": 0.025776506305464734, "grad_norm": 0.9498577117919922, "learning_rate": 2.574430823117338e-06, "loss": 0.2475, "step": 883 }, { "epoch": 0.02580569827183559, "grad_norm": 0.577785074710846, "learning_rate": 2.577349678925861e-06, "loss": 0.2478, "step": 884 }, { "epoch": 0.025834890238206447, "grad_norm": 1.655592441558838, "learning_rate": 2.580268534734384e-06, "loss": 0.3051, "step": 885 }, { "epoch": 0.0258640822045773, "grad_norm": 0.6724304556846619, "learning_rate": 2.5831873905429073e-06, "loss": 0.2634, "step": 886 }, { "epoch": 0.025893274170948156, "grad_norm": 1.139691710472107, "learning_rate": 2.5861062463514303e-06, "loss": 0.2798, "step": 887 }, { "epoch": 0.02592246613731901, "grad_norm": 0.6036343574523926, "learning_rate": 2.589025102159953e-06, "loss": 0.2553, "step": 888 }, { "epoch": 0.025951658103689865, "grad_norm": 0.7364935278892517, "learning_rate": 2.591943957968476e-06, "loss": 0.305, "step": 889 }, { "epoch": 0.02598085007006072, "grad_norm": 0.9103686213493347, "learning_rate": 2.594862813777e-06, "loss": 0.2701, "step": 890 }, { "epoch": 0.026010042036431574, "grad_norm": 0.731653094291687, "learning_rate": 2.5977816695855228e-06, "loss": 0.3092, "step": 891 }, { "epoch": 0.02603923400280243, "grad_norm": 0.7130997180938721, "learning_rate": 2.600700525394046e-06, "loss": 0.2713, "step": 892 }, { "epoch": 0.026068425969173283, "grad_norm": 0.8136972188949585, "learning_rate": 2.603619381202569e-06, "loss": 0.2427, "step": 893 }, { "epoch": 0.02609761793554414, "grad_norm": 0.6040281057357788, "learning_rate": 2.606538237011092e-06, "loss": 0.2699, "step": 894 }, { "epoch": 0.02612680990191499, "grad_norm": 0.689906895160675, "learning_rate": 2.609457092819615e-06, "loss": 0.2218, "step": 895 }, { "epoch": 0.026156001868285848, "grad_norm": 1.8604296445846558, "learning_rate": 2.612375948628138e-06, "loss": 0.2382, "step": 896 }, { "epoch": 0.026185193834656704, "grad_norm": 0.5141023993492126, "learning_rate": 2.615294804436661e-06, "loss": 0.2473, "step": 897 }, { "epoch": 0.026214385801027557, "grad_norm": 0.6734094619750977, "learning_rate": 2.618213660245184e-06, "loss": 0.2567, "step": 898 }, { "epoch": 0.026243577767398413, "grad_norm": 0.8151511549949646, "learning_rate": 2.621132516053707e-06, "loss": 0.3122, "step": 899 }, { "epoch": 0.026272769733769265, "grad_norm": 0.7875377535820007, "learning_rate": 2.6240513718622303e-06, "loss": 0.2461, "step": 900 }, { "epoch": 0.02630196170014012, "grad_norm": 0.619288444519043, "learning_rate": 2.6269702276707532e-06, "loss": 0.2749, "step": 901 }, { "epoch": 0.026331153666510978, "grad_norm": 0.7240700721740723, "learning_rate": 2.629889083479276e-06, "loss": 0.2466, "step": 902 }, { "epoch": 0.02636034563288183, "grad_norm": 1.6719423532485962, "learning_rate": 2.632807939287799e-06, "loss": 0.2572, "step": 903 }, { "epoch": 0.026389537599252687, "grad_norm": 1.5915549993515015, "learning_rate": 2.6357267950963224e-06, "loss": 0.2808, "step": 904 }, { "epoch": 0.02641872956562354, "grad_norm": 0.9563435912132263, "learning_rate": 2.6386456509048453e-06, "loss": 0.3044, "step": 905 }, { "epoch": 0.026447921531994396, "grad_norm": 0.6129550933837891, "learning_rate": 2.6415645067133686e-06, "loss": 0.2118, "step": 906 }, { "epoch": 0.02647711349836525, "grad_norm": 0.6942821741104126, "learning_rate": 2.644483362521892e-06, "loss": 0.272, "step": 907 }, { "epoch": 0.026506305464736105, "grad_norm": 0.7674027681350708, "learning_rate": 2.647402218330415e-06, "loss": 0.2243, "step": 908 }, { "epoch": 0.02653549743110696, "grad_norm": 0.5975706577301025, "learning_rate": 2.650321074138938e-06, "loss": 0.2751, "step": 909 }, { "epoch": 0.026564689397477814, "grad_norm": 0.5953163504600525, "learning_rate": 2.6532399299474607e-06, "loss": 0.2734, "step": 910 }, { "epoch": 0.02659388136384867, "grad_norm": 1.0166312456130981, "learning_rate": 2.656158785755984e-06, "loss": 0.29, "step": 911 }, { "epoch": 0.026623073330219522, "grad_norm": 0.6486395597457886, "learning_rate": 2.659077641564507e-06, "loss": 0.306, "step": 912 }, { "epoch": 0.02665226529659038, "grad_norm": 0.6919006109237671, "learning_rate": 2.66199649737303e-06, "loss": 0.2654, "step": 913 }, { "epoch": 0.02668145726296123, "grad_norm": 0.6822469830513, "learning_rate": 2.664915353181553e-06, "loss": 0.2857, "step": 914 }, { "epoch": 0.026710649229332088, "grad_norm": 0.7547165155410767, "learning_rate": 2.667834208990076e-06, "loss": 0.2592, "step": 915 }, { "epoch": 0.026739841195702944, "grad_norm": 1.1540814638137817, "learning_rate": 2.670753064798599e-06, "loss": 0.2562, "step": 916 }, { "epoch": 0.026769033162073796, "grad_norm": 0.8386058211326599, "learning_rate": 2.673671920607122e-06, "loss": 0.2665, "step": 917 }, { "epoch": 0.026798225128444653, "grad_norm": 0.612320065498352, "learning_rate": 2.6765907764156453e-06, "loss": 0.2943, "step": 918 }, { "epoch": 0.026827417094815505, "grad_norm": 0.7188367247581482, "learning_rate": 2.6795096322241683e-06, "loss": 0.28, "step": 919 }, { "epoch": 0.02685660906118636, "grad_norm": 1.0213226079940796, "learning_rate": 2.682428488032691e-06, "loss": 0.268, "step": 920 }, { "epoch": 0.026885801027557218, "grad_norm": 0.8642094135284424, "learning_rate": 2.685347343841214e-06, "loss": 0.2499, "step": 921 }, { "epoch": 0.02691499299392807, "grad_norm": 0.7615217566490173, "learning_rate": 2.688266199649738e-06, "loss": 0.2969, "step": 922 }, { "epoch": 0.026944184960298927, "grad_norm": 0.5737387537956238, "learning_rate": 2.6911850554582608e-06, "loss": 0.2085, "step": 923 }, { "epoch": 0.02697337692666978, "grad_norm": 0.6898486614227295, "learning_rate": 2.6941039112667837e-06, "loss": 0.2457, "step": 924 }, { "epoch": 0.027002568893040636, "grad_norm": 0.9503934383392334, "learning_rate": 2.697022767075307e-06, "loss": 0.2559, "step": 925 }, { "epoch": 0.02703176085941149, "grad_norm": 0.9519321322441101, "learning_rate": 2.69994162288383e-06, "loss": 0.2477, "step": 926 }, { "epoch": 0.027060952825782345, "grad_norm": 0.6989906430244446, "learning_rate": 2.702860478692353e-06, "loss": 0.2491, "step": 927 }, { "epoch": 0.0270901447921532, "grad_norm": 0.6764732599258423, "learning_rate": 2.7057793345008758e-06, "loss": 0.2203, "step": 928 }, { "epoch": 0.027119336758524053, "grad_norm": 0.48489922285079956, "learning_rate": 2.708698190309399e-06, "loss": 0.2224, "step": 929 }, { "epoch": 0.02714852872489491, "grad_norm": 0.675293505191803, "learning_rate": 2.711617046117922e-06, "loss": 0.2744, "step": 930 }, { "epoch": 0.027177720691265762, "grad_norm": 0.8919585347175598, "learning_rate": 2.714535901926445e-06, "loss": 0.2615, "step": 931 }, { "epoch": 0.02720691265763662, "grad_norm": 0.8039907217025757, "learning_rate": 2.717454757734968e-06, "loss": 0.2686, "step": 932 }, { "epoch": 0.027236104624007475, "grad_norm": 0.6710110306739807, "learning_rate": 2.720373613543491e-06, "loss": 0.2689, "step": 933 }, { "epoch": 0.027265296590378327, "grad_norm": 0.8153388500213623, "learning_rate": 2.723292469352014e-06, "loss": 0.2978, "step": 934 }, { "epoch": 0.027294488556749184, "grad_norm": 0.6278548836708069, "learning_rate": 2.726211325160537e-06, "loss": 0.237, "step": 935 }, { "epoch": 0.027323680523120036, "grad_norm": 0.8235316276550293, "learning_rate": 2.72913018096906e-06, "loss": 0.2945, "step": 936 }, { "epoch": 0.027352872489490893, "grad_norm": 1.1187292337417603, "learning_rate": 2.7320490367775833e-06, "loss": 0.3062, "step": 937 }, { "epoch": 0.027382064455861745, "grad_norm": 0.9113869667053223, "learning_rate": 2.7349678925861066e-06, "loss": 0.285, "step": 938 }, { "epoch": 0.0274112564222326, "grad_norm": 0.6233710050582886, "learning_rate": 2.7378867483946295e-06, "loss": 0.2303, "step": 939 }, { "epoch": 0.027440448388603458, "grad_norm": 0.6315010786056519, "learning_rate": 2.740805604203153e-06, "loss": 0.2372, "step": 940 }, { "epoch": 0.02746964035497431, "grad_norm": 0.734587550163269, "learning_rate": 2.743724460011676e-06, "loss": 0.2453, "step": 941 }, { "epoch": 0.027498832321345167, "grad_norm": 0.5832258462905884, "learning_rate": 2.7466433158201987e-06, "loss": 0.2361, "step": 942 }, { "epoch": 0.02752802428771602, "grad_norm": 0.9417452812194824, "learning_rate": 2.749562171628722e-06, "loss": 0.2535, "step": 943 }, { "epoch": 0.027557216254086876, "grad_norm": 0.8529187440872192, "learning_rate": 2.752481027437245e-06, "loss": 0.2893, "step": 944 }, { "epoch": 0.02758640822045773, "grad_norm": 0.9428001642227173, "learning_rate": 2.755399883245768e-06, "loss": 0.3892, "step": 945 }, { "epoch": 0.027615600186828584, "grad_norm": 0.6856834292411804, "learning_rate": 2.758318739054291e-06, "loss": 0.218, "step": 946 }, { "epoch": 0.02764479215319944, "grad_norm": 0.7997137904167175, "learning_rate": 2.761237594862814e-06, "loss": 0.2655, "step": 947 }, { "epoch": 0.027673984119570293, "grad_norm": 0.5866235494613647, "learning_rate": 2.764156450671337e-06, "loss": 0.2751, "step": 948 }, { "epoch": 0.02770317608594115, "grad_norm": 0.703010618686676, "learning_rate": 2.76707530647986e-06, "loss": 0.2566, "step": 949 }, { "epoch": 0.027732368052312002, "grad_norm": 0.6971365809440613, "learning_rate": 2.769994162288383e-06, "loss": 0.2699, "step": 950 }, { "epoch": 0.02776156001868286, "grad_norm": 0.6996588110923767, "learning_rate": 2.7729130180969062e-06, "loss": 0.2097, "step": 951 }, { "epoch": 0.027790751985053715, "grad_norm": 0.7331510782241821, "learning_rate": 2.775831873905429e-06, "loss": 0.2304, "step": 952 }, { "epoch": 0.027819943951424567, "grad_norm": 0.6635194420814514, "learning_rate": 2.778750729713952e-06, "loss": 0.2542, "step": 953 }, { "epoch": 0.027849135917795424, "grad_norm": 0.8471614122390747, "learning_rate": 2.781669585522476e-06, "loss": 0.2957, "step": 954 }, { "epoch": 0.027878327884166276, "grad_norm": 0.7967818975448608, "learning_rate": 2.7845884413309988e-06, "loss": 0.2498, "step": 955 }, { "epoch": 0.027907519850537132, "grad_norm": 0.6588839888572693, "learning_rate": 2.7875072971395217e-06, "loss": 0.2557, "step": 956 }, { "epoch": 0.027936711816907985, "grad_norm": 0.7587175965309143, "learning_rate": 2.7904261529480446e-06, "loss": 0.2308, "step": 957 }, { "epoch": 0.02796590378327884, "grad_norm": 0.9519162178039551, "learning_rate": 2.793345008756568e-06, "loss": 0.2769, "step": 958 }, { "epoch": 0.027995095749649698, "grad_norm": 0.6067529916763306, "learning_rate": 2.796263864565091e-06, "loss": 0.2185, "step": 959 }, { "epoch": 0.02802428771602055, "grad_norm": 0.7311866283416748, "learning_rate": 2.7991827203736138e-06, "loss": 0.3326, "step": 960 }, { "epoch": 0.028053479682391406, "grad_norm": 0.7793200612068176, "learning_rate": 2.8021015761821367e-06, "loss": 0.2523, "step": 961 }, { "epoch": 0.02808267164876226, "grad_norm": 0.6862403154373169, "learning_rate": 2.80502043199066e-06, "loss": 0.2575, "step": 962 }, { "epoch": 0.028111863615133115, "grad_norm": 1.115133285522461, "learning_rate": 2.807939287799183e-06, "loss": 0.3028, "step": 963 }, { "epoch": 0.02814105558150397, "grad_norm": 0.7058566808700562, "learning_rate": 2.810858143607706e-06, "loss": 0.2754, "step": 964 }, { "epoch": 0.028170247547874824, "grad_norm": 0.9124411344528198, "learning_rate": 2.8137769994162288e-06, "loss": 0.283, "step": 965 }, { "epoch": 0.02819943951424568, "grad_norm": 1.6797722578048706, "learning_rate": 2.816695855224752e-06, "loss": 0.2689, "step": 966 }, { "epoch": 0.028228631480616533, "grad_norm": 0.7095997333526611, "learning_rate": 2.819614711033275e-06, "loss": 0.2476, "step": 967 }, { "epoch": 0.02825782344698739, "grad_norm": 0.6316807270050049, "learning_rate": 2.822533566841798e-06, "loss": 0.2372, "step": 968 }, { "epoch": 0.028287015413358242, "grad_norm": 0.7196025848388672, "learning_rate": 2.825452422650321e-06, "loss": 0.2883, "step": 969 }, { "epoch": 0.0283162073797291, "grad_norm": 0.7149882912635803, "learning_rate": 2.8283712784588446e-06, "loss": 0.2518, "step": 970 }, { "epoch": 0.028345399346099955, "grad_norm": 0.8113337159156799, "learning_rate": 2.8312901342673675e-06, "loss": 0.264, "step": 971 }, { "epoch": 0.028374591312470807, "grad_norm": 0.611339271068573, "learning_rate": 2.834208990075891e-06, "loss": 0.2745, "step": 972 }, { "epoch": 0.028403783278841663, "grad_norm": 0.7164582014083862, "learning_rate": 2.837127845884414e-06, "loss": 0.278, "step": 973 }, { "epoch": 0.028432975245212516, "grad_norm": 0.6942234039306641, "learning_rate": 2.8400467016929367e-06, "loss": 0.2905, "step": 974 }, { "epoch": 0.028462167211583372, "grad_norm": 0.5457978844642639, "learning_rate": 2.8429655575014596e-06, "loss": 0.2664, "step": 975 }, { "epoch": 0.02849135917795423, "grad_norm": 0.6209812760353088, "learning_rate": 2.845884413309983e-06, "loss": 0.2706, "step": 976 }, { "epoch": 0.02852055114432508, "grad_norm": 0.6918172240257263, "learning_rate": 2.848803269118506e-06, "loss": 0.2412, "step": 977 }, { "epoch": 0.028549743110695937, "grad_norm": 0.666390061378479, "learning_rate": 2.851722124927029e-06, "loss": 0.3046, "step": 978 }, { "epoch": 0.02857893507706679, "grad_norm": 0.72007155418396, "learning_rate": 2.8546409807355517e-06, "loss": 0.2604, "step": 979 }, { "epoch": 0.028608127043437646, "grad_norm": 0.5916531085968018, "learning_rate": 2.857559836544075e-06, "loss": 0.2648, "step": 980 }, { "epoch": 0.0286373190098085, "grad_norm": 0.5374948382377625, "learning_rate": 2.860478692352598e-06, "loss": 0.27, "step": 981 }, { "epoch": 0.028666510976179355, "grad_norm": 1.0457940101623535, "learning_rate": 2.863397548161121e-06, "loss": 0.2798, "step": 982 }, { "epoch": 0.02869570294255021, "grad_norm": 0.7569371461868286, "learning_rate": 2.866316403969644e-06, "loss": 0.2594, "step": 983 }, { "epoch": 0.028724894908921064, "grad_norm": 0.5904086232185364, "learning_rate": 2.869235259778167e-06, "loss": 0.2407, "step": 984 }, { "epoch": 0.02875408687529192, "grad_norm": 0.596069872379303, "learning_rate": 2.87215411558669e-06, "loss": 0.2897, "step": 985 }, { "epoch": 0.028783278841662773, "grad_norm": 0.5512086749076843, "learning_rate": 2.8750729713952134e-06, "loss": 0.2399, "step": 986 }, { "epoch": 0.02881247080803363, "grad_norm": 0.6040316820144653, "learning_rate": 2.8779918272037367e-06, "loss": 0.3176, "step": 987 }, { "epoch": 0.028841662774404486, "grad_norm": 0.8208381533622742, "learning_rate": 2.8809106830122597e-06, "loss": 0.2587, "step": 988 }, { "epoch": 0.028870854740775338, "grad_norm": 0.6185209155082703, "learning_rate": 2.8838295388207826e-06, "loss": 0.3105, "step": 989 }, { "epoch": 0.028900046707146194, "grad_norm": 0.5776681900024414, "learning_rate": 2.8867483946293055e-06, "loss": 0.2243, "step": 990 }, { "epoch": 0.028929238673517047, "grad_norm": 0.8650928735733032, "learning_rate": 2.889667250437829e-06, "loss": 0.2946, "step": 991 }, { "epoch": 0.028958430639887903, "grad_norm": 0.6053735613822937, "learning_rate": 2.8925861062463517e-06, "loss": 0.2928, "step": 992 }, { "epoch": 0.028987622606258756, "grad_norm": 0.7471405267715454, "learning_rate": 2.8955049620548747e-06, "loss": 0.2885, "step": 993 }, { "epoch": 0.029016814572629612, "grad_norm": 0.9902225136756897, "learning_rate": 2.8984238178633976e-06, "loss": 0.2365, "step": 994 }, { "epoch": 0.02904600653900047, "grad_norm": 0.544470489025116, "learning_rate": 2.901342673671921e-06, "loss": 0.2689, "step": 995 }, { "epoch": 0.02907519850537132, "grad_norm": 0.5768752694129944, "learning_rate": 2.904261529480444e-06, "loss": 0.2489, "step": 996 }, { "epoch": 0.029104390471742177, "grad_norm": 1.3921034336090088, "learning_rate": 2.9071803852889668e-06, "loss": 0.3035, "step": 997 }, { "epoch": 0.02913358243811303, "grad_norm": 0.6779526472091675, "learning_rate": 2.9100992410974897e-06, "loss": 0.2682, "step": 998 }, { "epoch": 0.029162774404483886, "grad_norm": 0.856377899646759, "learning_rate": 2.913018096906013e-06, "loss": 0.2777, "step": 999 }, { "epoch": 0.029191966370854742, "grad_norm": 0.7735098600387573, "learning_rate": 2.915936952714536e-06, "loss": 0.2694, "step": 1000 }, { "epoch": 0.029221158337225595, "grad_norm": 0.7219677567481995, "learning_rate": 2.918855808523059e-06, "loss": 0.2285, "step": 1001 }, { "epoch": 0.02925035030359645, "grad_norm": 0.6877197623252869, "learning_rate": 2.9217746643315826e-06, "loss": 0.297, "step": 1002 }, { "epoch": 0.029279542269967304, "grad_norm": 0.9319356083869934, "learning_rate": 2.9246935201401055e-06, "loss": 0.2912, "step": 1003 }, { "epoch": 0.02930873423633816, "grad_norm": 0.5836535692214966, "learning_rate": 2.9276123759486284e-06, "loss": 0.329, "step": 1004 }, { "epoch": 0.029337926202709013, "grad_norm": 0.7190091609954834, "learning_rate": 2.9305312317571518e-06, "loss": 0.2674, "step": 1005 }, { "epoch": 0.02936711816907987, "grad_norm": 0.5915114283561707, "learning_rate": 2.9334500875656747e-06, "loss": 0.2773, "step": 1006 }, { "epoch": 0.029396310135450725, "grad_norm": 0.8068286776542664, "learning_rate": 2.9363689433741976e-06, "loss": 0.2511, "step": 1007 }, { "epoch": 0.029425502101821578, "grad_norm": 0.6932069659233093, "learning_rate": 2.9392877991827205e-06, "loss": 0.2256, "step": 1008 }, { "epoch": 0.029454694068192434, "grad_norm": 0.5345923900604248, "learning_rate": 2.942206654991244e-06, "loss": 0.2307, "step": 1009 }, { "epoch": 0.029483886034563287, "grad_norm": 0.5655198097229004, "learning_rate": 2.945125510799767e-06, "loss": 0.2555, "step": 1010 }, { "epoch": 0.029513078000934143, "grad_norm": 0.6577056050300598, "learning_rate": 2.9480443666082897e-06, "loss": 0.2871, "step": 1011 }, { "epoch": 0.029542269967304996, "grad_norm": 0.5852928757667542, "learning_rate": 2.9509632224168126e-06, "loss": 0.2413, "step": 1012 }, { "epoch": 0.029571461933675852, "grad_norm": 0.8501983880996704, "learning_rate": 2.953882078225336e-06, "loss": 0.3064, "step": 1013 }, { "epoch": 0.02960065390004671, "grad_norm": 0.6969757676124573, "learning_rate": 2.956800934033859e-06, "loss": 0.2699, "step": 1014 }, { "epoch": 0.02962984586641756, "grad_norm": 0.5450948476791382, "learning_rate": 2.959719789842382e-06, "loss": 0.2706, "step": 1015 }, { "epoch": 0.029659037832788417, "grad_norm": 0.7124611735343933, "learning_rate": 2.9626386456509047e-06, "loss": 0.2705, "step": 1016 }, { "epoch": 0.02968822979915927, "grad_norm": 0.5935656428337097, "learning_rate": 2.965557501459428e-06, "loss": 0.2414, "step": 1017 }, { "epoch": 0.029717421765530126, "grad_norm": 0.5499153733253479, "learning_rate": 2.9684763572679514e-06, "loss": 0.2525, "step": 1018 }, { "epoch": 0.029746613731900982, "grad_norm": 0.6184799671173096, "learning_rate": 2.9713952130764743e-06, "loss": 0.2809, "step": 1019 }, { "epoch": 0.029775805698271835, "grad_norm": 0.5466409921646118, "learning_rate": 2.9743140688849976e-06, "loss": 0.298, "step": 1020 }, { "epoch": 0.02980499766464269, "grad_norm": 0.6783432364463806, "learning_rate": 2.9772329246935206e-06, "loss": 0.3108, "step": 1021 }, { "epoch": 0.029834189631013544, "grad_norm": 0.7649757862091064, "learning_rate": 2.9801517805020435e-06, "loss": 0.2682, "step": 1022 }, { "epoch": 0.0298633815973844, "grad_norm": 0.6034682989120483, "learning_rate": 2.9830706363105664e-06, "loss": 0.2364, "step": 1023 }, { "epoch": 0.029892573563755253, "grad_norm": 0.8001195788383484, "learning_rate": 2.9859894921190897e-06, "loss": 0.2521, "step": 1024 }, { "epoch": 0.02992176553012611, "grad_norm": 0.6490921974182129, "learning_rate": 2.9889083479276127e-06, "loss": 0.3261, "step": 1025 }, { "epoch": 0.029950957496496965, "grad_norm": 0.6432263851165771, "learning_rate": 2.9918272037361356e-06, "loss": 0.2637, "step": 1026 }, { "epoch": 0.029980149462867818, "grad_norm": 1.0412720441818237, "learning_rate": 2.9947460595446585e-06, "loss": 0.2627, "step": 1027 }, { "epoch": 0.030009341429238674, "grad_norm": 0.6353621482849121, "learning_rate": 2.997664915353182e-06, "loss": 0.2818, "step": 1028 }, { "epoch": 0.030038533395609527, "grad_norm": 0.9082673192024231, "learning_rate": 3.0005837711617047e-06, "loss": 0.2739, "step": 1029 }, { "epoch": 0.030067725361980383, "grad_norm": 0.5284113883972168, "learning_rate": 3.0035026269702277e-06, "loss": 0.2482, "step": 1030 }, { "epoch": 0.03009691732835124, "grad_norm": 1.3684659004211426, "learning_rate": 3.0064214827787506e-06, "loss": 0.2346, "step": 1031 }, { "epoch": 0.030126109294722092, "grad_norm": 1.1234381198883057, "learning_rate": 3.009340338587274e-06, "loss": 0.2475, "step": 1032 }, { "epoch": 0.03015530126109295, "grad_norm": 0.9363643527030945, "learning_rate": 3.012259194395797e-06, "loss": 0.2827, "step": 1033 }, { "epoch": 0.0301844932274638, "grad_norm": 0.62890625, "learning_rate": 3.0151780502043206e-06, "loss": 0.222, "step": 1034 }, { "epoch": 0.030213685193834657, "grad_norm": 0.7656568288803101, "learning_rate": 3.0180969060128435e-06, "loss": 0.3076, "step": 1035 }, { "epoch": 0.03024287716020551, "grad_norm": 0.672965407371521, "learning_rate": 3.0210157618213664e-06, "loss": 0.2328, "step": 1036 }, { "epoch": 0.030272069126576366, "grad_norm": 0.7133659720420837, "learning_rate": 3.0239346176298893e-06, "loss": 0.2509, "step": 1037 }, { "epoch": 0.030301261092947222, "grad_norm": 0.8695511221885681, "learning_rate": 3.0268534734384127e-06, "loss": 0.2706, "step": 1038 }, { "epoch": 0.030330453059318075, "grad_norm": 0.7093313932418823, "learning_rate": 3.0297723292469356e-06, "loss": 0.3008, "step": 1039 }, { "epoch": 0.03035964502568893, "grad_norm": 0.574664831161499, "learning_rate": 3.0326911850554585e-06, "loss": 0.3052, "step": 1040 }, { "epoch": 0.030388836992059784, "grad_norm": 0.6310436129570007, "learning_rate": 3.0356100408639814e-06, "loss": 0.2593, "step": 1041 }, { "epoch": 0.03041802895843064, "grad_norm": 1.5989696979522705, "learning_rate": 3.0385288966725048e-06, "loss": 0.231, "step": 1042 }, { "epoch": 0.030447220924801496, "grad_norm": 0.5693421363830566, "learning_rate": 3.0414477524810277e-06, "loss": 0.226, "step": 1043 }, { "epoch": 0.03047641289117235, "grad_norm": 0.624183177947998, "learning_rate": 3.0443666082895506e-06, "loss": 0.2632, "step": 1044 }, { "epoch": 0.030505604857543205, "grad_norm": 0.623053252696991, "learning_rate": 3.0472854640980735e-06, "loss": 0.2963, "step": 1045 }, { "epoch": 0.030534796823914058, "grad_norm": 0.5428891777992249, "learning_rate": 3.050204319906597e-06, "loss": 0.264, "step": 1046 }, { "epoch": 0.030563988790284914, "grad_norm": 0.741475522518158, "learning_rate": 3.0531231757151198e-06, "loss": 0.2868, "step": 1047 }, { "epoch": 0.030593180756655767, "grad_norm": 0.6097524762153625, "learning_rate": 3.0560420315236427e-06, "loss": 0.2583, "step": 1048 }, { "epoch": 0.030622372723026623, "grad_norm": 0.7864190340042114, "learning_rate": 3.0589608873321656e-06, "loss": 0.2715, "step": 1049 }, { "epoch": 0.03065156468939748, "grad_norm": 0.7460563778877258, "learning_rate": 3.0618797431406894e-06, "loss": 0.2811, "step": 1050 }, { "epoch": 0.030680756655768332, "grad_norm": 0.7080952525138855, "learning_rate": 3.0647985989492123e-06, "loss": 0.2195, "step": 1051 }, { "epoch": 0.030709948622139188, "grad_norm": 0.5813731551170349, "learning_rate": 3.0677174547577352e-06, "loss": 0.245, "step": 1052 }, { "epoch": 0.03073914058851004, "grad_norm": 0.508057713508606, "learning_rate": 3.0706363105662586e-06, "loss": 0.2629, "step": 1053 }, { "epoch": 0.030768332554880897, "grad_norm": 0.5920312404632568, "learning_rate": 3.0735551663747815e-06, "loss": 0.2496, "step": 1054 }, { "epoch": 0.03079752452125175, "grad_norm": 0.9058916568756104, "learning_rate": 3.0764740221833044e-06, "loss": 0.2536, "step": 1055 }, { "epoch": 0.030826716487622606, "grad_norm": 0.6557114124298096, "learning_rate": 3.0793928779918273e-06, "loss": 0.2493, "step": 1056 }, { "epoch": 0.030855908453993462, "grad_norm": 1.7105785608291626, "learning_rate": 3.0823117338003506e-06, "loss": 0.2948, "step": 1057 }, { "epoch": 0.030885100420364315, "grad_norm": 0.8103343844413757, "learning_rate": 3.0852305896088736e-06, "loss": 0.284, "step": 1058 }, { "epoch": 0.03091429238673517, "grad_norm": 0.7623259425163269, "learning_rate": 3.0881494454173965e-06, "loss": 0.2904, "step": 1059 }, { "epoch": 0.030943484353106024, "grad_norm": 0.5993109345436096, "learning_rate": 3.09106830122592e-06, "loss": 0.2342, "step": 1060 }, { "epoch": 0.03097267631947688, "grad_norm": 0.7131768465042114, "learning_rate": 3.0939871570344427e-06, "loss": 0.286, "step": 1061 }, { "epoch": 0.031001868285847736, "grad_norm": 1.3123301267623901, "learning_rate": 3.0969060128429656e-06, "loss": 0.2293, "step": 1062 }, { "epoch": 0.03103106025221859, "grad_norm": 0.9001116156578064, "learning_rate": 3.0998248686514886e-06, "loss": 0.2521, "step": 1063 }, { "epoch": 0.031060252218589445, "grad_norm": 0.7792380452156067, "learning_rate": 3.102743724460012e-06, "loss": 0.232, "step": 1064 }, { "epoch": 0.031089444184960298, "grad_norm": 0.528335452079773, "learning_rate": 3.105662580268535e-06, "loss": 0.2276, "step": 1065 }, { "epoch": 0.031118636151331154, "grad_norm": 0.6340272426605225, "learning_rate": 3.108581436077058e-06, "loss": 0.2609, "step": 1066 }, { "epoch": 0.031147828117702007, "grad_norm": 0.9799456000328064, "learning_rate": 3.1115002918855815e-06, "loss": 0.3141, "step": 1067 }, { "epoch": 0.031177020084072863, "grad_norm": 0.7416012287139893, "learning_rate": 3.1144191476941044e-06, "loss": 0.2549, "step": 1068 }, { "epoch": 0.03120621205044372, "grad_norm": 0.745395839214325, "learning_rate": 3.1173380035026273e-06, "loss": 0.3665, "step": 1069 }, { "epoch": 0.031235404016814572, "grad_norm": 0.7828651070594788, "learning_rate": 3.1202568593111503e-06, "loss": 0.2817, "step": 1070 }, { "epoch": 0.03126459598318543, "grad_norm": 0.5431921482086182, "learning_rate": 3.1231757151196736e-06, "loss": 0.2557, "step": 1071 }, { "epoch": 0.031293787949556284, "grad_norm": 0.7653155326843262, "learning_rate": 3.1260945709281965e-06, "loss": 0.2269, "step": 1072 }, { "epoch": 0.031322979915927134, "grad_norm": 0.5358496308326721, "learning_rate": 3.1290134267367194e-06, "loss": 0.2571, "step": 1073 }, { "epoch": 0.03135217188229799, "grad_norm": 0.6866558790206909, "learning_rate": 3.1319322825452423e-06, "loss": 0.277, "step": 1074 }, { "epoch": 0.031381363848668846, "grad_norm": 0.7545403838157654, "learning_rate": 3.1348511383537657e-06, "loss": 0.2599, "step": 1075 }, { "epoch": 0.0314105558150397, "grad_norm": 3.114048480987549, "learning_rate": 3.1377699941622886e-06, "loss": 0.2696, "step": 1076 }, { "epoch": 0.03143974778141056, "grad_norm": 0.8579685091972351, "learning_rate": 3.1406888499708115e-06, "loss": 0.2317, "step": 1077 }, { "epoch": 0.03146893974778141, "grad_norm": 0.7658801674842834, "learning_rate": 3.1436077057793344e-06, "loss": 0.2714, "step": 1078 }, { "epoch": 0.031498131714152264, "grad_norm": 0.9719153642654419, "learning_rate": 3.1465265615878578e-06, "loss": 0.2462, "step": 1079 }, { "epoch": 0.03152732368052312, "grad_norm": 0.8593485951423645, "learning_rate": 3.1494454173963807e-06, "loss": 0.2916, "step": 1080 }, { "epoch": 0.031556515646893976, "grad_norm": 0.6438561081886292, "learning_rate": 3.1523642732049036e-06, "loss": 0.2577, "step": 1081 }, { "epoch": 0.03158570761326483, "grad_norm": 1.098232626914978, "learning_rate": 3.1552831290134274e-06, "loss": 0.3177, "step": 1082 }, { "epoch": 0.03161489957963568, "grad_norm": 0.6176438927650452, "learning_rate": 3.1582019848219503e-06, "loss": 0.2798, "step": 1083 }, { "epoch": 0.03164409154600654, "grad_norm": 0.5368120074272156, "learning_rate": 3.161120840630473e-06, "loss": 0.2378, "step": 1084 }, { "epoch": 0.031673283512377394, "grad_norm": 0.6855921149253845, "learning_rate": 3.1640396964389965e-06, "loss": 0.3421, "step": 1085 }, { "epoch": 0.03170247547874825, "grad_norm": 0.5573244690895081, "learning_rate": 3.1669585522475195e-06, "loss": 0.2927, "step": 1086 }, { "epoch": 0.031731667445119106, "grad_norm": 1.0422170162200928, "learning_rate": 3.1698774080560424e-06, "loss": 0.246, "step": 1087 }, { "epoch": 0.031760859411489956, "grad_norm": 0.6114378571510315, "learning_rate": 3.1727962638645653e-06, "loss": 0.2655, "step": 1088 }, { "epoch": 0.03179005137786081, "grad_norm": 0.6219998002052307, "learning_rate": 3.1757151196730886e-06, "loss": 0.2887, "step": 1089 }, { "epoch": 0.03181924334423167, "grad_norm": 0.6715273261070251, "learning_rate": 3.1786339754816115e-06, "loss": 0.3268, "step": 1090 }, { "epoch": 0.031848435310602524, "grad_norm": 0.541528582572937, "learning_rate": 3.1815528312901345e-06, "loss": 0.1911, "step": 1091 }, { "epoch": 0.03187762727697338, "grad_norm": 0.5671232342720032, "learning_rate": 3.1844716870986574e-06, "loss": 0.2222, "step": 1092 }, { "epoch": 0.03190681924334423, "grad_norm": 0.8350130319595337, "learning_rate": 3.1873905429071807e-06, "loss": 0.2402, "step": 1093 }, { "epoch": 0.031936011209715086, "grad_norm": 0.926233172416687, "learning_rate": 3.1903093987157036e-06, "loss": 0.2678, "step": 1094 }, { "epoch": 0.03196520317608594, "grad_norm": 1.0148792266845703, "learning_rate": 3.1932282545242266e-06, "loss": 0.3012, "step": 1095 }, { "epoch": 0.0319943951424568, "grad_norm": 0.6263900995254517, "learning_rate": 3.1961471103327495e-06, "loss": 0.2428, "step": 1096 }, { "epoch": 0.03202358710882765, "grad_norm": 0.5799058079719543, "learning_rate": 3.199065966141273e-06, "loss": 0.2738, "step": 1097 }, { "epoch": 0.032052779075198504, "grad_norm": 0.523815393447876, "learning_rate": 3.201984821949796e-06, "loss": 0.2414, "step": 1098 }, { "epoch": 0.03208197104156936, "grad_norm": 0.6885871887207031, "learning_rate": 3.204903677758319e-06, "loss": 0.2713, "step": 1099 }, { "epoch": 0.032111163007940216, "grad_norm": 0.6114309430122375, "learning_rate": 3.2078225335668424e-06, "loss": 0.247, "step": 1100 }, { "epoch": 0.03214035497431107, "grad_norm": 0.9117933511734009, "learning_rate": 3.2107413893753653e-06, "loss": 0.3261, "step": 1101 }, { "epoch": 0.03216954694068192, "grad_norm": 0.6595732569694519, "learning_rate": 3.2136602451838882e-06, "loss": 0.2353, "step": 1102 }, { "epoch": 0.03219873890705278, "grad_norm": 1.0207054615020752, "learning_rate": 3.216579100992411e-06, "loss": 0.2769, "step": 1103 }, { "epoch": 0.032227930873423634, "grad_norm": 0.6638264060020447, "learning_rate": 3.2194979568009345e-06, "loss": 0.2636, "step": 1104 }, { "epoch": 0.03225712283979449, "grad_norm": 0.7036494612693787, "learning_rate": 3.2224168126094574e-06, "loss": 0.2844, "step": 1105 }, { "epoch": 0.032286314806165346, "grad_norm": 1.0682486295700073, "learning_rate": 3.2253356684179803e-06, "loss": 0.2599, "step": 1106 }, { "epoch": 0.032315506772536196, "grad_norm": 0.569105327129364, "learning_rate": 3.2282545242265032e-06, "loss": 0.2994, "step": 1107 }, { "epoch": 0.03234469873890705, "grad_norm": 0.5744232535362244, "learning_rate": 3.2311733800350266e-06, "loss": 0.261, "step": 1108 }, { "epoch": 0.03237389070527791, "grad_norm": 0.5710498690605164, "learning_rate": 3.2340922358435495e-06, "loss": 0.2333, "step": 1109 }, { "epoch": 0.032403082671648764, "grad_norm": 0.8193321228027344, "learning_rate": 3.2370110916520724e-06, "loss": 0.2809, "step": 1110 }, { "epoch": 0.03243227463801962, "grad_norm": 0.5298006534576416, "learning_rate": 3.2399299474605953e-06, "loss": 0.2209, "step": 1111 }, { "epoch": 0.03246146660439047, "grad_norm": 0.6313120126724243, "learning_rate": 3.2428488032691187e-06, "loss": 0.3044, "step": 1112 }, { "epoch": 0.032490658570761326, "grad_norm": 0.6563692092895508, "learning_rate": 3.2457676590776416e-06, "loss": 0.2466, "step": 1113 }, { "epoch": 0.03251985053713218, "grad_norm": 0.6877367496490479, "learning_rate": 3.2486865148861654e-06, "loss": 0.2285, "step": 1114 }, { "epoch": 0.03254904250350304, "grad_norm": 0.6135945916175842, "learning_rate": 3.2516053706946883e-06, "loss": 0.3123, "step": 1115 }, { "epoch": 0.03257823446987389, "grad_norm": 0.7089772820472717, "learning_rate": 3.254524226503211e-06, "loss": 0.2538, "step": 1116 }, { "epoch": 0.032607426436244744, "grad_norm": 1.0254759788513184, "learning_rate": 3.257443082311734e-06, "loss": 0.2425, "step": 1117 }, { "epoch": 0.0326366184026156, "grad_norm": 0.7205994129180908, "learning_rate": 3.2603619381202574e-06, "loss": 0.266, "step": 1118 }, { "epoch": 0.032665810368986456, "grad_norm": 0.6920617818832397, "learning_rate": 3.2632807939287804e-06, "loss": 0.2576, "step": 1119 }, { "epoch": 0.03269500233535731, "grad_norm": 0.7878667116165161, "learning_rate": 3.2661996497373033e-06, "loss": 0.2941, "step": 1120 }, { "epoch": 0.03272419430172816, "grad_norm": 0.9398682713508606, "learning_rate": 3.269118505545826e-06, "loss": 0.3412, "step": 1121 }, { "epoch": 0.03275338626809902, "grad_norm": 0.5853355526924133, "learning_rate": 3.2720373613543495e-06, "loss": 0.2912, "step": 1122 }, { "epoch": 0.032782578234469874, "grad_norm": 0.8859756588935852, "learning_rate": 3.2749562171628725e-06, "loss": 0.2189, "step": 1123 }, { "epoch": 0.03281177020084073, "grad_norm": 0.65904700756073, "learning_rate": 3.2778750729713954e-06, "loss": 0.2534, "step": 1124 }, { "epoch": 0.032840962167211586, "grad_norm": 0.5407125353813171, "learning_rate": 3.2807939287799183e-06, "loss": 0.2551, "step": 1125 }, { "epoch": 0.032870154133582435, "grad_norm": 0.743739128112793, "learning_rate": 3.2837127845884416e-06, "loss": 0.2485, "step": 1126 }, { "epoch": 0.03289934609995329, "grad_norm": 0.5532652139663696, "learning_rate": 3.2866316403969645e-06, "loss": 0.2477, "step": 1127 }, { "epoch": 0.03292853806632415, "grad_norm": 0.6368823647499084, "learning_rate": 3.2895504962054875e-06, "loss": 0.275, "step": 1128 }, { "epoch": 0.032957730032695004, "grad_norm": 0.7128353118896484, "learning_rate": 3.2924693520140104e-06, "loss": 0.2467, "step": 1129 }, { "epoch": 0.03298692199906586, "grad_norm": 1.665433406829834, "learning_rate": 3.295388207822534e-06, "loss": 0.2909, "step": 1130 }, { "epoch": 0.03301611396543671, "grad_norm": 0.7007399201393127, "learning_rate": 3.298307063631057e-06, "loss": 0.2928, "step": 1131 }, { "epoch": 0.033045305931807566, "grad_norm": 0.5473955273628235, "learning_rate": 3.30122591943958e-06, "loss": 0.2146, "step": 1132 }, { "epoch": 0.03307449789817842, "grad_norm": 0.9398009181022644, "learning_rate": 3.3041447752481033e-06, "loss": 0.2438, "step": 1133 }, { "epoch": 0.03310368986454928, "grad_norm": 0.5711359977722168, "learning_rate": 3.3070636310566262e-06, "loss": 0.2747, "step": 1134 }, { "epoch": 0.033132881830920134, "grad_norm": 0.7944397926330566, "learning_rate": 3.309982486865149e-06, "loss": 0.2722, "step": 1135 }, { "epoch": 0.033162073797290983, "grad_norm": 0.8569290637969971, "learning_rate": 3.312901342673672e-06, "loss": 0.3518, "step": 1136 }, { "epoch": 0.03319126576366184, "grad_norm": 0.6127541065216064, "learning_rate": 3.3158201984821954e-06, "loss": 0.3007, "step": 1137 }, { "epoch": 0.033220457730032696, "grad_norm": 0.7033496499061584, "learning_rate": 3.3187390542907183e-06, "loss": 0.2474, "step": 1138 }, { "epoch": 0.03324964969640355, "grad_norm": 0.5763451457023621, "learning_rate": 3.3216579100992412e-06, "loss": 0.2419, "step": 1139 }, { "epoch": 0.0332788416627744, "grad_norm": 0.6350521445274353, "learning_rate": 3.324576765907764e-06, "loss": 0.2684, "step": 1140 }, { "epoch": 0.03330803362914526, "grad_norm": 0.9187911152839661, "learning_rate": 3.3274956217162875e-06, "loss": 0.3214, "step": 1141 }, { "epoch": 0.033337225595516114, "grad_norm": 0.9367279410362244, "learning_rate": 3.3304144775248104e-06, "loss": 0.2635, "step": 1142 }, { "epoch": 0.03336641756188697, "grad_norm": 0.6201584339141846, "learning_rate": 3.3333333333333333e-06, "loss": 0.2165, "step": 1143 }, { "epoch": 0.033395609528257826, "grad_norm": 0.6595151424407959, "learning_rate": 3.3362521891418562e-06, "loss": 0.2737, "step": 1144 }, { "epoch": 0.033424801494628675, "grad_norm": 0.5849860310554504, "learning_rate": 3.3391710449503796e-06, "loss": 0.2554, "step": 1145 }, { "epoch": 0.03345399346099953, "grad_norm": 0.5918682813644409, "learning_rate": 3.342089900758903e-06, "loss": 0.2253, "step": 1146 }, { "epoch": 0.03348318542737039, "grad_norm": 0.5599484443664551, "learning_rate": 3.3450087565674263e-06, "loss": 0.2579, "step": 1147 }, { "epoch": 0.033512377393741244, "grad_norm": 0.7853882908821106, "learning_rate": 3.347927612375949e-06, "loss": 0.283, "step": 1148 }, { "epoch": 0.0335415693601121, "grad_norm": 0.7272131443023682, "learning_rate": 3.350846468184472e-06, "loss": 0.2859, "step": 1149 }, { "epoch": 0.03357076132648295, "grad_norm": 0.5977720618247986, "learning_rate": 3.353765323992995e-06, "loss": 0.3254, "step": 1150 }, { "epoch": 0.033599953292853806, "grad_norm": 0.7936562895774841, "learning_rate": 3.3566841798015184e-06, "loss": 0.2235, "step": 1151 }, { "epoch": 0.03362914525922466, "grad_norm": 0.6836292743682861, "learning_rate": 3.3596030356100413e-06, "loss": 0.2906, "step": 1152 }, { "epoch": 0.03365833722559552, "grad_norm": 0.643365740776062, "learning_rate": 3.362521891418564e-06, "loss": 0.2264, "step": 1153 }, { "epoch": 0.033687529191966374, "grad_norm": 0.49980002641677856, "learning_rate": 3.365440747227087e-06, "loss": 0.2031, "step": 1154 }, { "epoch": 0.03371672115833722, "grad_norm": 0.6975603103637695, "learning_rate": 3.3683596030356104e-06, "loss": 0.2666, "step": 1155 }, { "epoch": 0.03374591312470808, "grad_norm": 1.6186408996582031, "learning_rate": 3.3712784588441334e-06, "loss": 0.2744, "step": 1156 }, { "epoch": 0.033775105091078936, "grad_norm": 0.6279740929603577, "learning_rate": 3.3741973146526563e-06, "loss": 0.2653, "step": 1157 }, { "epoch": 0.03380429705744979, "grad_norm": 1.176329255104065, "learning_rate": 3.377116170461179e-06, "loss": 0.2406, "step": 1158 }, { "epoch": 0.03383348902382064, "grad_norm": 0.8313259482383728, "learning_rate": 3.3800350262697025e-06, "loss": 0.263, "step": 1159 }, { "epoch": 0.0338626809901915, "grad_norm": 1.6292668581008911, "learning_rate": 3.3829538820782254e-06, "loss": 0.2348, "step": 1160 }, { "epoch": 0.033891872956562354, "grad_norm": 0.7091835737228394, "learning_rate": 3.3858727378867484e-06, "loss": 0.2496, "step": 1161 }, { "epoch": 0.03392106492293321, "grad_norm": 0.6865967512130737, "learning_rate": 3.388791593695272e-06, "loss": 0.2197, "step": 1162 }, { "epoch": 0.033950256889304066, "grad_norm": 0.7818773984909058, "learning_rate": 3.391710449503795e-06, "loss": 0.2247, "step": 1163 }, { "epoch": 0.033979448855674915, "grad_norm": 0.5447686910629272, "learning_rate": 3.394629305312318e-06, "loss": 0.2665, "step": 1164 }, { "epoch": 0.03400864082204577, "grad_norm": 0.7871919870376587, "learning_rate": 3.397548161120841e-06, "loss": 0.2313, "step": 1165 }, { "epoch": 0.03403783278841663, "grad_norm": 0.7073301076889038, "learning_rate": 3.4004670169293642e-06, "loss": 0.2488, "step": 1166 }, { "epoch": 0.034067024754787484, "grad_norm": 0.7013928294181824, "learning_rate": 3.403385872737887e-06, "loss": 0.2485, "step": 1167 }, { "epoch": 0.03409621672115834, "grad_norm": 1.5420514345169067, "learning_rate": 3.40630472854641e-06, "loss": 0.2213, "step": 1168 }, { "epoch": 0.03412540868752919, "grad_norm": 0.6286233067512512, "learning_rate": 3.409223584354933e-06, "loss": 0.2644, "step": 1169 }, { "epoch": 0.034154600653900045, "grad_norm": 0.9241833686828613, "learning_rate": 3.4121424401634563e-06, "loss": 0.2606, "step": 1170 }, { "epoch": 0.0341837926202709, "grad_norm": 0.7562866806983948, "learning_rate": 3.4150612959719792e-06, "loss": 0.3163, "step": 1171 }, { "epoch": 0.03421298458664176, "grad_norm": 0.550752580165863, "learning_rate": 3.417980151780502e-06, "loss": 0.2324, "step": 1172 }, { "epoch": 0.034242176553012614, "grad_norm": 0.7327567338943481, "learning_rate": 3.4208990075890255e-06, "loss": 0.2724, "step": 1173 }, { "epoch": 0.03427136851938346, "grad_norm": 0.6460875272750854, "learning_rate": 3.4238178633975484e-06, "loss": 0.2731, "step": 1174 }, { "epoch": 0.03430056048575432, "grad_norm": 0.5943291187286377, "learning_rate": 3.4267367192060713e-06, "loss": 0.2812, "step": 1175 }, { "epoch": 0.034329752452125176, "grad_norm": 0.6065140962600708, "learning_rate": 3.4296555750145942e-06, "loss": 0.2791, "step": 1176 }, { "epoch": 0.03435894441849603, "grad_norm": 1.5755231380462646, "learning_rate": 3.4325744308231176e-06, "loss": 0.2752, "step": 1177 }, { "epoch": 0.03438813638486689, "grad_norm": 0.688665509223938, "learning_rate": 3.435493286631641e-06, "loss": 0.2588, "step": 1178 }, { "epoch": 0.03441732835123774, "grad_norm": 0.8729178309440613, "learning_rate": 3.438412142440164e-06, "loss": 0.2816, "step": 1179 }, { "epoch": 0.034446520317608594, "grad_norm": 0.6707572340965271, "learning_rate": 3.441330998248687e-06, "loss": 0.2764, "step": 1180 }, { "epoch": 0.03447571228397945, "grad_norm": 0.5810070633888245, "learning_rate": 3.44424985405721e-06, "loss": 0.2557, "step": 1181 }, { "epoch": 0.034504904250350306, "grad_norm": 0.7508068084716797, "learning_rate": 3.447168709865733e-06, "loss": 0.2886, "step": 1182 }, { "epoch": 0.034534096216721155, "grad_norm": 0.6616237759590149, "learning_rate": 3.450087565674256e-06, "loss": 0.3336, "step": 1183 }, { "epoch": 0.03456328818309201, "grad_norm": 0.7419545650482178, "learning_rate": 3.4530064214827793e-06, "loss": 0.2539, "step": 1184 }, { "epoch": 0.03459248014946287, "grad_norm": 0.619817852973938, "learning_rate": 3.455925277291302e-06, "loss": 0.2004, "step": 1185 }, { "epoch": 0.034621672115833724, "grad_norm": 0.6090641617774963, "learning_rate": 3.458844133099825e-06, "loss": 0.312, "step": 1186 }, { "epoch": 0.03465086408220458, "grad_norm": 0.5776286125183105, "learning_rate": 3.461762988908348e-06, "loss": 0.2249, "step": 1187 }, { "epoch": 0.03468005604857543, "grad_norm": 0.6694672107696533, "learning_rate": 3.4646818447168713e-06, "loss": 0.299, "step": 1188 }, { "epoch": 0.034709248014946285, "grad_norm": 0.6446837782859802, "learning_rate": 3.4676007005253943e-06, "loss": 0.2763, "step": 1189 }, { "epoch": 0.03473843998131714, "grad_norm": 0.756971538066864, "learning_rate": 3.470519556333917e-06, "loss": 0.2385, "step": 1190 }, { "epoch": 0.034767631947688, "grad_norm": 0.6714991927146912, "learning_rate": 3.47343841214244e-06, "loss": 0.2911, "step": 1191 }, { "epoch": 0.034796823914058854, "grad_norm": 0.5963791012763977, "learning_rate": 3.4763572679509634e-06, "loss": 0.2651, "step": 1192 }, { "epoch": 0.0348260158804297, "grad_norm": 0.6025741100311279, "learning_rate": 3.4792761237594864e-06, "loss": 0.2181, "step": 1193 }, { "epoch": 0.03485520784680056, "grad_norm": 0.7741943001747131, "learning_rate": 3.4821949795680097e-06, "loss": 0.2473, "step": 1194 }, { "epoch": 0.034884399813171416, "grad_norm": 0.6751134991645813, "learning_rate": 3.485113835376533e-06, "loss": 0.2417, "step": 1195 }, { "epoch": 0.03491359177954227, "grad_norm": 0.4930124878883362, "learning_rate": 3.488032691185056e-06, "loss": 0.215, "step": 1196 }, { "epoch": 0.03494278374591313, "grad_norm": 0.6261811256408691, "learning_rate": 3.490951546993579e-06, "loss": 0.2494, "step": 1197 }, { "epoch": 0.03497197571228398, "grad_norm": 0.6399199962615967, "learning_rate": 3.4938704028021018e-06, "loss": 0.2594, "step": 1198 }, { "epoch": 0.03500116767865483, "grad_norm": 0.5655600428581238, "learning_rate": 3.496789258610625e-06, "loss": 0.2496, "step": 1199 }, { "epoch": 0.03503035964502569, "grad_norm": 0.6607506275177002, "learning_rate": 3.499708114419148e-06, "loss": 0.2343, "step": 1200 }, { "epoch": 0.035059551611396546, "grad_norm": 0.840646505355835, "learning_rate": 3.502626970227671e-06, "loss": 0.3092, "step": 1201 }, { "epoch": 0.035088743577767395, "grad_norm": 0.6125404834747314, "learning_rate": 3.5055458260361943e-06, "loss": 0.261, "step": 1202 }, { "epoch": 0.03511793554413825, "grad_norm": 0.770391047000885, "learning_rate": 3.508464681844717e-06, "loss": 0.2763, "step": 1203 }, { "epoch": 0.03514712751050911, "grad_norm": 0.6417145133018494, "learning_rate": 3.51138353765324e-06, "loss": 0.3198, "step": 1204 }, { "epoch": 0.035176319476879964, "grad_norm": 0.967345654964447, "learning_rate": 3.514302393461763e-06, "loss": 0.3101, "step": 1205 }, { "epoch": 0.03520551144325082, "grad_norm": 0.5812071561813354, "learning_rate": 3.5172212492702864e-06, "loss": 0.27, "step": 1206 }, { "epoch": 0.03523470340962167, "grad_norm": 1.7794586420059204, "learning_rate": 3.5201401050788093e-06, "loss": 0.2639, "step": 1207 }, { "epoch": 0.035263895375992525, "grad_norm": 0.8004682064056396, "learning_rate": 3.5230589608873322e-06, "loss": 0.2318, "step": 1208 }, { "epoch": 0.03529308734236338, "grad_norm": 0.6065839529037476, "learning_rate": 3.525977816695855e-06, "loss": 0.273, "step": 1209 }, { "epoch": 0.03532227930873424, "grad_norm": 0.7571098804473877, "learning_rate": 3.528896672504379e-06, "loss": 0.2888, "step": 1210 }, { "epoch": 0.035351471275105094, "grad_norm": 0.6454493403434753, "learning_rate": 3.531815528312902e-06, "loss": 0.2133, "step": 1211 }, { "epoch": 0.03538066324147594, "grad_norm": 0.6641614437103271, "learning_rate": 3.5347343841214247e-06, "loss": 0.2687, "step": 1212 }, { "epoch": 0.0354098552078468, "grad_norm": 0.6341044306755066, "learning_rate": 3.537653239929948e-06, "loss": 0.2641, "step": 1213 }, { "epoch": 0.035439047174217655, "grad_norm": 0.7356577515602112, "learning_rate": 3.540572095738471e-06, "loss": 0.3174, "step": 1214 }, { "epoch": 0.03546823914058851, "grad_norm": 0.576485812664032, "learning_rate": 3.543490951546994e-06, "loss": 0.2544, "step": 1215 }, { "epoch": 0.03549743110695937, "grad_norm": 0.7160353064537048, "learning_rate": 3.546409807355517e-06, "loss": 0.243, "step": 1216 }, { "epoch": 0.03552662307333022, "grad_norm": 1.1813150644302368, "learning_rate": 3.54932866316404e-06, "loss": 0.2556, "step": 1217 }, { "epoch": 0.03555581503970107, "grad_norm": 0.6079777479171753, "learning_rate": 3.552247518972563e-06, "loss": 0.2489, "step": 1218 }, { "epoch": 0.03558500700607193, "grad_norm": 0.7801462411880493, "learning_rate": 3.555166374781086e-06, "loss": 0.3043, "step": 1219 }, { "epoch": 0.035614198972442786, "grad_norm": 0.5371313095092773, "learning_rate": 3.558085230589609e-06, "loss": 0.2641, "step": 1220 }, { "epoch": 0.03564339093881364, "grad_norm": 0.5974947810173035, "learning_rate": 3.5610040863981322e-06, "loss": 0.2414, "step": 1221 }, { "epoch": 0.03567258290518449, "grad_norm": 0.8209773898124695, "learning_rate": 3.563922942206655e-06, "loss": 0.272, "step": 1222 }, { "epoch": 0.03570177487155535, "grad_norm": 0.662837564945221, "learning_rate": 3.566841798015178e-06, "loss": 0.2493, "step": 1223 }, { "epoch": 0.035730966837926204, "grad_norm": 0.7376241087913513, "learning_rate": 3.569760653823701e-06, "loss": 0.3202, "step": 1224 }, { "epoch": 0.03576015880429706, "grad_norm": 0.8432675004005432, "learning_rate": 3.5726795096322243e-06, "loss": 0.2045, "step": 1225 }, { "epoch": 0.03578935077066791, "grad_norm": 0.6540022492408752, "learning_rate": 3.5755983654407477e-06, "loss": 0.2325, "step": 1226 }, { "epoch": 0.035818542737038765, "grad_norm": 0.8195127844810486, "learning_rate": 3.578517221249271e-06, "loss": 0.2526, "step": 1227 }, { "epoch": 0.03584773470340962, "grad_norm": 0.5158239006996155, "learning_rate": 3.581436077057794e-06, "loss": 0.2161, "step": 1228 }, { "epoch": 0.03587692666978048, "grad_norm": 0.5682434439659119, "learning_rate": 3.584354932866317e-06, "loss": 0.2468, "step": 1229 }, { "epoch": 0.035906118636151334, "grad_norm": 0.6544743776321411, "learning_rate": 3.5872737886748398e-06, "loss": 0.2277, "step": 1230 }, { "epoch": 0.03593531060252218, "grad_norm": 0.6275551319122314, "learning_rate": 3.590192644483363e-06, "loss": 0.2257, "step": 1231 }, { "epoch": 0.03596450256889304, "grad_norm": 1.0246964693069458, "learning_rate": 3.593111500291886e-06, "loss": 0.2542, "step": 1232 }, { "epoch": 0.035993694535263895, "grad_norm": 2.0443594455718994, "learning_rate": 3.596030356100409e-06, "loss": 0.2816, "step": 1233 }, { "epoch": 0.03602288650163475, "grad_norm": 0.7405754923820496, "learning_rate": 3.598949211908932e-06, "loss": 0.3012, "step": 1234 }, { "epoch": 0.03605207846800561, "grad_norm": 0.6858054399490356, "learning_rate": 3.601868067717455e-06, "loss": 0.2354, "step": 1235 }, { "epoch": 0.03608127043437646, "grad_norm": 0.8828311562538147, "learning_rate": 3.604786923525978e-06, "loss": 0.2336, "step": 1236 }, { "epoch": 0.03611046240074731, "grad_norm": 0.7414107322692871, "learning_rate": 3.607705779334501e-06, "loss": 0.2319, "step": 1237 }, { "epoch": 0.03613965436711817, "grad_norm": 0.7233486771583557, "learning_rate": 3.610624635143024e-06, "loss": 0.2051, "step": 1238 }, { "epoch": 0.036168846333489026, "grad_norm": 0.9098436236381531, "learning_rate": 3.6135434909515473e-06, "loss": 0.2636, "step": 1239 }, { "epoch": 0.03619803829985988, "grad_norm": 0.7380335330963135, "learning_rate": 3.61646234676007e-06, "loss": 0.2946, "step": 1240 }, { "epoch": 0.03622723026623073, "grad_norm": 1.0002163648605347, "learning_rate": 3.619381202568593e-06, "loss": 0.3382, "step": 1241 }, { "epoch": 0.03625642223260159, "grad_norm": 0.7916613817214966, "learning_rate": 3.622300058377117e-06, "loss": 0.3346, "step": 1242 }, { "epoch": 0.03628561419897244, "grad_norm": 0.6397849321365356, "learning_rate": 3.62521891418564e-06, "loss": 0.2324, "step": 1243 }, { "epoch": 0.0363148061653433, "grad_norm": 0.5466078519821167, "learning_rate": 3.6281377699941627e-06, "loss": 0.2459, "step": 1244 }, { "epoch": 0.03634399813171415, "grad_norm": 0.7612577676773071, "learning_rate": 3.6310566258026856e-06, "loss": 0.2431, "step": 1245 }, { "epoch": 0.036373190098085005, "grad_norm": 0.6132680177688599, "learning_rate": 3.633975481611209e-06, "loss": 0.2512, "step": 1246 }, { "epoch": 0.03640238206445586, "grad_norm": 0.6469331383705139, "learning_rate": 3.636894337419732e-06, "loss": 0.2481, "step": 1247 }, { "epoch": 0.03643157403082672, "grad_norm": 0.7308911681175232, "learning_rate": 3.639813193228255e-06, "loss": 0.2646, "step": 1248 }, { "epoch": 0.036460765997197574, "grad_norm": 1.17155122756958, "learning_rate": 3.6427320490367777e-06, "loss": 0.2904, "step": 1249 }, { "epoch": 0.03648995796356842, "grad_norm": 0.600027859210968, "learning_rate": 3.645650904845301e-06, "loss": 0.229, "step": 1250 }, { "epoch": 0.03651914992993928, "grad_norm": 0.6002368927001953, "learning_rate": 3.648569760653824e-06, "loss": 0.2256, "step": 1251 }, { "epoch": 0.036548341896310135, "grad_norm": 0.7758608460426331, "learning_rate": 3.651488616462347e-06, "loss": 0.2545, "step": 1252 }, { "epoch": 0.03657753386268099, "grad_norm": 0.7174641489982605, "learning_rate": 3.65440747227087e-06, "loss": 0.2352, "step": 1253 }, { "epoch": 0.03660672582905185, "grad_norm": 0.5404579639434814, "learning_rate": 3.657326328079393e-06, "loss": 0.2228, "step": 1254 }, { "epoch": 0.0366359177954227, "grad_norm": 0.5491631031036377, "learning_rate": 3.660245183887916e-06, "loss": 0.1862, "step": 1255 }, { "epoch": 0.03666510976179355, "grad_norm": 0.6316103935241699, "learning_rate": 3.663164039696439e-06, "loss": 0.2333, "step": 1256 }, { "epoch": 0.03669430172816441, "grad_norm": 0.7375202178955078, "learning_rate": 3.666082895504962e-06, "loss": 0.259, "step": 1257 }, { "epoch": 0.036723493694535266, "grad_norm": 1.0751159191131592, "learning_rate": 3.6690017513134857e-06, "loss": 0.2771, "step": 1258 }, { "epoch": 0.03675268566090612, "grad_norm": 0.8306264281272888, "learning_rate": 3.6719206071220086e-06, "loss": 0.2865, "step": 1259 }, { "epoch": 0.03678187762727697, "grad_norm": 0.5721892714500427, "learning_rate": 3.674839462930532e-06, "loss": 0.215, "step": 1260 }, { "epoch": 0.03681106959364783, "grad_norm": 0.6702126860618591, "learning_rate": 3.677758318739055e-06, "loss": 0.2343, "step": 1261 }, { "epoch": 0.03684026156001868, "grad_norm": 0.583602786064148, "learning_rate": 3.6806771745475778e-06, "loss": 0.2467, "step": 1262 }, { "epoch": 0.03686945352638954, "grad_norm": 0.8860994577407837, "learning_rate": 3.6835960303561007e-06, "loss": 0.2592, "step": 1263 }, { "epoch": 0.036898645492760396, "grad_norm": 0.7239203453063965, "learning_rate": 3.686514886164624e-06, "loss": 0.2421, "step": 1264 }, { "epoch": 0.036927837459131245, "grad_norm": 0.5366103649139404, "learning_rate": 3.689433741973147e-06, "loss": 0.2369, "step": 1265 }, { "epoch": 0.0369570294255021, "grad_norm": 0.6505977511405945, "learning_rate": 3.69235259778167e-06, "loss": 0.2154, "step": 1266 }, { "epoch": 0.03698622139187296, "grad_norm": 0.8993584513664246, "learning_rate": 3.6952714535901928e-06, "loss": 0.2213, "step": 1267 }, { "epoch": 0.037015413358243814, "grad_norm": 0.695983350276947, "learning_rate": 3.698190309398716e-06, "loss": 0.2566, "step": 1268 }, { "epoch": 0.03704460532461466, "grad_norm": 0.668644368648529, "learning_rate": 3.701109165207239e-06, "loss": 0.2502, "step": 1269 }, { "epoch": 0.03707379729098552, "grad_norm": 1.2312848567962646, "learning_rate": 3.704028021015762e-06, "loss": 0.2858, "step": 1270 }, { "epoch": 0.037102989257356375, "grad_norm": 1.10320246219635, "learning_rate": 3.706946876824285e-06, "loss": 0.2557, "step": 1271 }, { "epoch": 0.03713218122372723, "grad_norm": 0.758047342300415, "learning_rate": 3.709865732632808e-06, "loss": 0.2631, "step": 1272 }, { "epoch": 0.03716137319009809, "grad_norm": 0.6988257765769958, "learning_rate": 3.712784588441331e-06, "loss": 0.2698, "step": 1273 }, { "epoch": 0.03719056515646894, "grad_norm": 0.7116532921791077, "learning_rate": 3.7157034442498544e-06, "loss": 0.2376, "step": 1274 }, { "epoch": 0.03721975712283979, "grad_norm": 0.702959418296814, "learning_rate": 3.718622300058378e-06, "loss": 0.2768, "step": 1275 }, { "epoch": 0.03724894908921065, "grad_norm": 0.9173882007598877, "learning_rate": 3.7215411558669007e-06, "loss": 0.27, "step": 1276 }, { "epoch": 0.037278141055581505, "grad_norm": 2.307175636291504, "learning_rate": 3.7244600116754236e-06, "loss": 0.2091, "step": 1277 }, { "epoch": 0.03730733302195236, "grad_norm": 0.7283646464347839, "learning_rate": 3.7273788674839465e-06, "loss": 0.2121, "step": 1278 }, { "epoch": 0.03733652498832321, "grad_norm": 0.8299439549446106, "learning_rate": 3.73029772329247e-06, "loss": 0.237, "step": 1279 }, { "epoch": 0.03736571695469407, "grad_norm": 0.48538458347320557, "learning_rate": 3.733216579100993e-06, "loss": 0.1755, "step": 1280 }, { "epoch": 0.03739490892106492, "grad_norm": 0.6599858403205872, "learning_rate": 3.7361354349095157e-06, "loss": 0.2737, "step": 1281 }, { "epoch": 0.03742410088743578, "grad_norm": 1.2551747560501099, "learning_rate": 3.7390542907180386e-06, "loss": 0.286, "step": 1282 }, { "epoch": 0.037453292853806636, "grad_norm": 0.6212884187698364, "learning_rate": 3.741973146526562e-06, "loss": 0.2687, "step": 1283 }, { "epoch": 0.037482484820177485, "grad_norm": 0.6699914932250977, "learning_rate": 3.744892002335085e-06, "loss": 0.2439, "step": 1284 }, { "epoch": 0.03751167678654834, "grad_norm": 0.651833713054657, "learning_rate": 3.747810858143608e-06, "loss": 0.2569, "step": 1285 }, { "epoch": 0.0375408687529192, "grad_norm": 0.8528442978858948, "learning_rate": 3.7507297139521307e-06, "loss": 0.2804, "step": 1286 }, { "epoch": 0.037570060719290053, "grad_norm": 0.8123040795326233, "learning_rate": 3.753648569760654e-06, "loss": 0.2309, "step": 1287 }, { "epoch": 0.0375992526856609, "grad_norm": 0.9139248132705688, "learning_rate": 3.756567425569177e-06, "loss": 0.2693, "step": 1288 }, { "epoch": 0.03762844465203176, "grad_norm": 0.5739780068397522, "learning_rate": 3.7594862813777e-06, "loss": 0.2674, "step": 1289 }, { "epoch": 0.037657636618402615, "grad_norm": 0.7160319089889526, "learning_rate": 3.7624051371862237e-06, "loss": 0.2557, "step": 1290 }, { "epoch": 0.03768682858477347, "grad_norm": 0.6361958980560303, "learning_rate": 3.7653239929947466e-06, "loss": 0.2345, "step": 1291 }, { "epoch": 0.03771602055114433, "grad_norm": 1.3186331987380981, "learning_rate": 3.7682428488032695e-06, "loss": 0.2436, "step": 1292 }, { "epoch": 0.03774521251751518, "grad_norm": 0.705010712146759, "learning_rate": 3.771161704611793e-06, "loss": 0.3034, "step": 1293 }, { "epoch": 0.03777440448388603, "grad_norm": 1.5360193252563477, "learning_rate": 3.7740805604203157e-06, "loss": 0.2561, "step": 1294 }, { "epoch": 0.03780359645025689, "grad_norm": 0.8917362093925476, "learning_rate": 3.7769994162288387e-06, "loss": 0.2865, "step": 1295 }, { "epoch": 0.037832788416627745, "grad_norm": 0.7650183439254761, "learning_rate": 3.7799182720373616e-06, "loss": 0.2715, "step": 1296 }, { "epoch": 0.0378619803829986, "grad_norm": 0.6395283937454224, "learning_rate": 3.782837127845885e-06, "loss": 0.2812, "step": 1297 }, { "epoch": 0.03789117234936945, "grad_norm": 0.8266571164131165, "learning_rate": 3.785755983654408e-06, "loss": 0.2735, "step": 1298 }, { "epoch": 0.03792036431574031, "grad_norm": 1.8120208978652954, "learning_rate": 3.7886748394629308e-06, "loss": 0.2997, "step": 1299 }, { "epoch": 0.03794955628211116, "grad_norm": 2.830197334289551, "learning_rate": 3.7915936952714537e-06, "loss": 0.2848, "step": 1300 }, { "epoch": 0.03797874824848202, "grad_norm": 1.6056610345840454, "learning_rate": 3.794512551079977e-06, "loss": 0.3209, "step": 1301 }, { "epoch": 0.038007940214852876, "grad_norm": 0.5952646732330322, "learning_rate": 3.7974314068885e-06, "loss": 0.2222, "step": 1302 }, { "epoch": 0.038037132181223725, "grad_norm": 0.5506329536437988, "learning_rate": 3.800350262697023e-06, "loss": 0.2542, "step": 1303 }, { "epoch": 0.03806632414759458, "grad_norm": 0.6937607526779175, "learning_rate": 3.8032691185055458e-06, "loss": 0.2323, "step": 1304 }, { "epoch": 0.03809551611396544, "grad_norm": 0.8306331038475037, "learning_rate": 3.806187974314069e-06, "loss": 0.3041, "step": 1305 }, { "epoch": 0.03812470808033629, "grad_norm": 0.9138373732566833, "learning_rate": 3.8091068301225924e-06, "loss": 0.229, "step": 1306 }, { "epoch": 0.03815390004670715, "grad_norm": 0.8583618998527527, "learning_rate": 3.8120256859311154e-06, "loss": 0.3072, "step": 1307 }, { "epoch": 0.038183092013078, "grad_norm": 0.8256165981292725, "learning_rate": 3.814944541739639e-06, "loss": 0.2492, "step": 1308 }, { "epoch": 0.038212283979448855, "grad_norm": 0.7949284911155701, "learning_rate": 3.817863397548161e-06, "loss": 0.2015, "step": 1309 }, { "epoch": 0.03824147594581971, "grad_norm": 0.7633950710296631, "learning_rate": 3.8207822533566845e-06, "loss": 0.2927, "step": 1310 }, { "epoch": 0.03827066791219057, "grad_norm": 1.0225733518600464, "learning_rate": 3.823701109165208e-06, "loss": 0.2608, "step": 1311 }, { "epoch": 0.03829985987856142, "grad_norm": 3.813934326171875, "learning_rate": 3.82661996497373e-06, "loss": 0.2651, "step": 1312 }, { "epoch": 0.03832905184493227, "grad_norm": 0.7120963335037231, "learning_rate": 3.829538820782254e-06, "loss": 0.2603, "step": 1313 }, { "epoch": 0.03835824381130313, "grad_norm": 0.9761554002761841, "learning_rate": 3.832457676590777e-06, "loss": 0.2613, "step": 1314 }, { "epoch": 0.038387435777673985, "grad_norm": 0.7344133257865906, "learning_rate": 3.8353765323992995e-06, "loss": 0.2893, "step": 1315 }, { "epoch": 0.03841662774404484, "grad_norm": 1.0042791366577148, "learning_rate": 3.838295388207823e-06, "loss": 0.2867, "step": 1316 }, { "epoch": 0.03844581971041569, "grad_norm": 0.6451325416564941, "learning_rate": 3.841214244016346e-06, "loss": 0.2518, "step": 1317 }, { "epoch": 0.03847501167678655, "grad_norm": 0.7965737581253052, "learning_rate": 3.844133099824869e-06, "loss": 0.1977, "step": 1318 }, { "epoch": 0.0385042036431574, "grad_norm": 0.8972351551055908, "learning_rate": 3.847051955633392e-06, "loss": 0.2353, "step": 1319 }, { "epoch": 0.03853339560952826, "grad_norm": 0.6325802206993103, "learning_rate": 3.8499708114419145e-06, "loss": 0.2664, "step": 1320 }, { "epoch": 0.038562587575899115, "grad_norm": 0.672202467918396, "learning_rate": 3.852889667250438e-06, "loss": 0.2482, "step": 1321 }, { "epoch": 0.038591779542269965, "grad_norm": 0.6882918477058411, "learning_rate": 3.855808523058961e-06, "loss": 0.2578, "step": 1322 }, { "epoch": 0.03862097150864082, "grad_norm": 0.7240579724311829, "learning_rate": 3.8587273788674846e-06, "loss": 0.2559, "step": 1323 }, { "epoch": 0.03865016347501168, "grad_norm": 0.8326563239097595, "learning_rate": 3.861646234676008e-06, "loss": 0.2744, "step": 1324 }, { "epoch": 0.03867935544138253, "grad_norm": 0.9905604124069214, "learning_rate": 3.86456509048453e-06, "loss": 0.3089, "step": 1325 }, { "epoch": 0.03870854740775339, "grad_norm": 0.8967849612236023, "learning_rate": 3.867483946293054e-06, "loss": 0.2556, "step": 1326 }, { "epoch": 0.03873773937412424, "grad_norm": 1.475478172302246, "learning_rate": 3.870402802101576e-06, "loss": 0.311, "step": 1327 }, { "epoch": 0.038766931340495095, "grad_norm": 1.033151626586914, "learning_rate": 3.8733216579100996e-06, "loss": 0.2668, "step": 1328 }, { "epoch": 0.03879612330686595, "grad_norm": 1.4345883131027222, "learning_rate": 3.876240513718623e-06, "loss": 0.3224, "step": 1329 }, { "epoch": 0.03882531527323681, "grad_norm": 2.1951303482055664, "learning_rate": 3.879159369527145e-06, "loss": 0.3048, "step": 1330 }, { "epoch": 0.03885450723960766, "grad_norm": 1.0919215679168701, "learning_rate": 3.882078225335669e-06, "loss": 0.2674, "step": 1331 }, { "epoch": 0.03888369920597851, "grad_norm": 0.7955617904663086, "learning_rate": 3.884997081144192e-06, "loss": 0.2257, "step": 1332 }, { "epoch": 0.03891289117234937, "grad_norm": 0.820132851600647, "learning_rate": 3.8879159369527146e-06, "loss": 0.2312, "step": 1333 }, { "epoch": 0.038942083138720225, "grad_norm": 0.6924084424972534, "learning_rate": 3.890834792761238e-06, "loss": 0.2806, "step": 1334 }, { "epoch": 0.03897127510509108, "grad_norm": 0.805083692073822, "learning_rate": 3.89375364856976e-06, "loss": 0.235, "step": 1335 }, { "epoch": 0.03900046707146193, "grad_norm": 0.8802233934402466, "learning_rate": 3.896672504378284e-06, "loss": 0.2785, "step": 1336 }, { "epoch": 0.03902965903783279, "grad_norm": 1.0880392789840698, "learning_rate": 3.899591360186807e-06, "loss": 0.3175, "step": 1337 }, { "epoch": 0.03905885100420364, "grad_norm": 0.975259006023407, "learning_rate": 3.9025102159953304e-06, "loss": 0.2494, "step": 1338 }, { "epoch": 0.0390880429705745, "grad_norm": 0.6295760869979858, "learning_rate": 3.905429071803854e-06, "loss": 0.2301, "step": 1339 }, { "epoch": 0.039117234936945355, "grad_norm": 0.764133870601654, "learning_rate": 3.908347927612376e-06, "loss": 0.249, "step": 1340 }, { "epoch": 0.039146426903316205, "grad_norm": 0.6408593058586121, "learning_rate": 3.9112667834209e-06, "loss": 0.2429, "step": 1341 }, { "epoch": 0.03917561886968706, "grad_norm": 0.8981755971908569, "learning_rate": 3.914185639229423e-06, "loss": 0.2515, "step": 1342 }, { "epoch": 0.03920481083605792, "grad_norm": 0.664496123790741, "learning_rate": 3.9171044950379454e-06, "loss": 0.2698, "step": 1343 }, { "epoch": 0.03923400280242877, "grad_norm": 0.7936316728591919, "learning_rate": 3.920023350846469e-06, "loss": 0.2177, "step": 1344 }, { "epoch": 0.03926319476879963, "grad_norm": 0.8782238364219666, "learning_rate": 3.922942206654991e-06, "loss": 0.2268, "step": 1345 }, { "epoch": 0.03929238673517048, "grad_norm": 0.6261479258537292, "learning_rate": 3.925861062463515e-06, "loss": 0.2296, "step": 1346 }, { "epoch": 0.039321578701541335, "grad_norm": 0.7767063975334167, "learning_rate": 3.928779918272038e-06, "loss": 0.2561, "step": 1347 }, { "epoch": 0.03935077066791219, "grad_norm": 0.8629996180534363, "learning_rate": 3.9316987740805604e-06, "loss": 0.2622, "step": 1348 }, { "epoch": 0.03937996263428305, "grad_norm": 0.8096489310264587, "learning_rate": 3.934617629889084e-06, "loss": 0.2094, "step": 1349 }, { "epoch": 0.0394091546006539, "grad_norm": 1.2400710582733154, "learning_rate": 3.937536485697607e-06, "loss": 0.3045, "step": 1350 }, { "epoch": 0.03943834656702475, "grad_norm": 0.7231318354606628, "learning_rate": 3.94045534150613e-06, "loss": 0.2872, "step": 1351 }, { "epoch": 0.03946753853339561, "grad_norm": 0.776343822479248, "learning_rate": 3.943374197314653e-06, "loss": 0.3074, "step": 1352 }, { "epoch": 0.039496730499766465, "grad_norm": 0.679623544216156, "learning_rate": 3.9462930531231754e-06, "loss": 0.2628, "step": 1353 }, { "epoch": 0.03952592246613732, "grad_norm": 0.7418889403343201, "learning_rate": 3.9492119089317e-06, "loss": 0.2793, "step": 1354 }, { "epoch": 0.03955511443250817, "grad_norm": 0.8842341303825378, "learning_rate": 3.952130764740222e-06, "loss": 0.2438, "step": 1355 }, { "epoch": 0.03958430639887903, "grad_norm": 0.9079101085662842, "learning_rate": 3.9550496205487455e-06, "loss": 0.2949, "step": 1356 }, { "epoch": 0.03961349836524988, "grad_norm": 0.9137316346168518, "learning_rate": 3.957968476357269e-06, "loss": 0.2765, "step": 1357 }, { "epoch": 0.03964269033162074, "grad_norm": 0.6815190315246582, "learning_rate": 3.960887332165791e-06, "loss": 0.2438, "step": 1358 }, { "epoch": 0.039671882297991595, "grad_norm": 0.670659065246582, "learning_rate": 3.963806187974315e-06, "loss": 0.2969, "step": 1359 }, { "epoch": 0.039701074264362445, "grad_norm": 0.6600425243377686, "learning_rate": 3.966725043782837e-06, "loss": 0.2662, "step": 1360 }, { "epoch": 0.0397302662307333, "grad_norm": 0.6831400990486145, "learning_rate": 3.9696438995913605e-06, "loss": 0.2721, "step": 1361 }, { "epoch": 0.03975945819710416, "grad_norm": 0.6457065343856812, "learning_rate": 3.972562755399884e-06, "loss": 0.3088, "step": 1362 }, { "epoch": 0.03978865016347501, "grad_norm": 0.7131325602531433, "learning_rate": 3.975481611208406e-06, "loss": 0.2349, "step": 1363 }, { "epoch": 0.03981784212984587, "grad_norm": 0.7017917037010193, "learning_rate": 3.97840046701693e-06, "loss": 0.2388, "step": 1364 }, { "epoch": 0.03984703409621672, "grad_norm": 0.7614160776138306, "learning_rate": 3.981319322825453e-06, "loss": 0.2853, "step": 1365 }, { "epoch": 0.039876226062587575, "grad_norm": 0.9969419240951538, "learning_rate": 3.9842381786339755e-06, "loss": 0.271, "step": 1366 }, { "epoch": 0.03990541802895843, "grad_norm": 0.8208183646202087, "learning_rate": 3.987157034442499e-06, "loss": 0.2503, "step": 1367 }, { "epoch": 0.03993460999532929, "grad_norm": 0.797612190246582, "learning_rate": 3.990075890251021e-06, "loss": 0.2189, "step": 1368 }, { "epoch": 0.03996380196170014, "grad_norm": 0.9428175687789917, "learning_rate": 3.992994746059545e-06, "loss": 0.2106, "step": 1369 }, { "epoch": 0.03999299392807099, "grad_norm": 0.8921414017677307, "learning_rate": 3.995913601868068e-06, "loss": 0.2999, "step": 1370 }, { "epoch": 0.04002218589444185, "grad_norm": 0.9570542573928833, "learning_rate": 3.998832457676591e-06, "loss": 0.2935, "step": 1371 }, { "epoch": 0.040051377860812705, "grad_norm": 0.7828667759895325, "learning_rate": 4.001751313485115e-06, "loss": 0.1935, "step": 1372 }, { "epoch": 0.04008056982718356, "grad_norm": 0.6376953125, "learning_rate": 4.004670169293637e-06, "loss": 0.2754, "step": 1373 }, { "epoch": 0.04010976179355441, "grad_norm": 1.1035168170928955, "learning_rate": 4.0075890251021605e-06, "loss": 0.3118, "step": 1374 }, { "epoch": 0.04013895375992527, "grad_norm": 0.7293027639389038, "learning_rate": 4.010507880910684e-06, "loss": 0.2846, "step": 1375 }, { "epoch": 0.04016814572629612, "grad_norm": 0.7360489964485168, "learning_rate": 4.013426736719206e-06, "loss": 0.2708, "step": 1376 }, { "epoch": 0.04019733769266698, "grad_norm": 0.9647752642631531, "learning_rate": 4.01634559252773e-06, "loss": 0.3024, "step": 1377 }, { "epoch": 0.040226529659037835, "grad_norm": 0.8187177777290344, "learning_rate": 4.019264448336252e-06, "loss": 0.2105, "step": 1378 }, { "epoch": 0.040255721625408684, "grad_norm": 0.7758957147598267, "learning_rate": 4.0221833041447755e-06, "loss": 0.2419, "step": 1379 }, { "epoch": 0.04028491359177954, "grad_norm": 1.1436028480529785, "learning_rate": 4.025102159953299e-06, "loss": 0.2879, "step": 1380 }, { "epoch": 0.0403141055581504, "grad_norm": 0.7350645661354065, "learning_rate": 4.028021015761821e-06, "loss": 0.3191, "step": 1381 }, { "epoch": 0.04034329752452125, "grad_norm": 0.9578595757484436, "learning_rate": 4.030939871570345e-06, "loss": 0.3142, "step": 1382 }, { "epoch": 0.04037248949089211, "grad_norm": 0.7976586222648621, "learning_rate": 4.033858727378868e-06, "loss": 0.343, "step": 1383 }, { "epoch": 0.04040168145726296, "grad_norm": 0.8036274909973145, "learning_rate": 4.0367775831873905e-06, "loss": 0.3129, "step": 1384 }, { "epoch": 0.040430873423633815, "grad_norm": 1.0035868883132935, "learning_rate": 4.039696438995914e-06, "loss": 0.2705, "step": 1385 }, { "epoch": 0.04046006539000467, "grad_norm": 0.739583432674408, "learning_rate": 4.042615294804437e-06, "loss": 0.3205, "step": 1386 }, { "epoch": 0.04048925735637553, "grad_norm": 0.5658490061759949, "learning_rate": 4.0455341506129605e-06, "loss": 0.2506, "step": 1387 }, { "epoch": 0.04051844932274638, "grad_norm": 0.840122640132904, "learning_rate": 4.048453006421483e-06, "loss": 0.2468, "step": 1388 }, { "epoch": 0.04054764128911723, "grad_norm": 0.8308492302894592, "learning_rate": 4.051371862230006e-06, "loss": 0.2952, "step": 1389 }, { "epoch": 0.04057683325548809, "grad_norm": 0.6646687984466553, "learning_rate": 4.05429071803853e-06, "loss": 0.2566, "step": 1390 }, { "epoch": 0.040606025221858945, "grad_norm": 0.7524445056915283, "learning_rate": 4.057209573847052e-06, "loss": 0.2803, "step": 1391 }, { "epoch": 0.0406352171882298, "grad_norm": 2.2371954917907715, "learning_rate": 4.0601284296555755e-06, "loss": 0.2675, "step": 1392 }, { "epoch": 0.04066440915460066, "grad_norm": 0.5940689444541931, "learning_rate": 4.063047285464098e-06, "loss": 0.2221, "step": 1393 }, { "epoch": 0.040693601120971507, "grad_norm": 0.5341134667396545, "learning_rate": 4.065966141272621e-06, "loss": 0.245, "step": 1394 }, { "epoch": 0.04072279308734236, "grad_norm": 0.9562422037124634, "learning_rate": 4.068884997081145e-06, "loss": 0.2605, "step": 1395 }, { "epoch": 0.04075198505371322, "grad_norm": 0.7835283875465393, "learning_rate": 4.071803852889667e-06, "loss": 0.2663, "step": 1396 }, { "epoch": 0.040781177020084075, "grad_norm": 0.5606222152709961, "learning_rate": 4.0747227086981905e-06, "loss": 0.2422, "step": 1397 }, { "epoch": 0.040810368986454924, "grad_norm": 0.6665201187133789, "learning_rate": 4.077641564506714e-06, "loss": 0.2536, "step": 1398 }, { "epoch": 0.04083956095282578, "grad_norm": 1.0141053199768066, "learning_rate": 4.080560420315236e-06, "loss": 0.2417, "step": 1399 }, { "epoch": 0.04086875291919664, "grad_norm": 0.6384795904159546, "learning_rate": 4.08347927612376e-06, "loss": 0.2462, "step": 1400 }, { "epoch": 0.04089794488556749, "grad_norm": 0.8197810053825378, "learning_rate": 4.086398131932282e-06, "loss": 0.3023, "step": 1401 }, { "epoch": 0.04092713685193835, "grad_norm": 0.8693575263023376, "learning_rate": 4.089316987740806e-06, "loss": 0.2903, "step": 1402 }, { "epoch": 0.0409563288183092, "grad_norm": 0.7041451930999756, "learning_rate": 4.092235843549329e-06, "loss": 0.271, "step": 1403 }, { "epoch": 0.040985520784680055, "grad_norm": 1.4420169591903687, "learning_rate": 4.095154699357852e-06, "loss": 0.2557, "step": 1404 }, { "epoch": 0.04101471275105091, "grad_norm": 0.7509667277336121, "learning_rate": 4.0980735551663756e-06, "loss": 0.2584, "step": 1405 }, { "epoch": 0.04104390471742177, "grad_norm": 0.7571094632148743, "learning_rate": 4.100992410974898e-06, "loss": 0.2443, "step": 1406 }, { "epoch": 0.04107309668379262, "grad_norm": 1.076670527458191, "learning_rate": 4.103911266783421e-06, "loss": 0.2491, "step": 1407 }, { "epoch": 0.04110228865016347, "grad_norm": 0.6876426935195923, "learning_rate": 4.106830122591945e-06, "loss": 0.2436, "step": 1408 }, { "epoch": 0.04113148061653433, "grad_norm": 0.7866666316986084, "learning_rate": 4.109748978400467e-06, "loss": 0.2816, "step": 1409 }, { "epoch": 0.041160672582905185, "grad_norm": 1.3242807388305664, "learning_rate": 4.112667834208991e-06, "loss": 0.2861, "step": 1410 }, { "epoch": 0.04118986454927604, "grad_norm": 0.8078485727310181, "learning_rate": 4.115586690017513e-06, "loss": 0.2825, "step": 1411 }, { "epoch": 0.0412190565156469, "grad_norm": 0.6325440406799316, "learning_rate": 4.118505545826036e-06, "loss": 0.2613, "step": 1412 }, { "epoch": 0.041248248482017746, "grad_norm": 0.7109373211860657, "learning_rate": 4.12142440163456e-06, "loss": 0.2595, "step": 1413 }, { "epoch": 0.0412774404483886, "grad_norm": 0.6766306161880493, "learning_rate": 4.124343257443082e-06, "loss": 0.2853, "step": 1414 }, { "epoch": 0.04130663241475946, "grad_norm": 0.6117640137672424, "learning_rate": 4.127262113251606e-06, "loss": 0.2745, "step": 1415 }, { "epoch": 0.041335824381130315, "grad_norm": 0.6242976188659668, "learning_rate": 4.130180969060129e-06, "loss": 0.2838, "step": 1416 }, { "epoch": 0.041365016347501164, "grad_norm": 0.7735099196434021, "learning_rate": 4.133099824868651e-06, "loss": 0.2234, "step": 1417 }, { "epoch": 0.04139420831387202, "grad_norm": 0.5482328534126282, "learning_rate": 4.136018680677175e-06, "loss": 0.2951, "step": 1418 }, { "epoch": 0.04142340028024288, "grad_norm": 0.9359428882598877, "learning_rate": 4.138937536485698e-06, "loss": 0.3415, "step": 1419 }, { "epoch": 0.04145259224661373, "grad_norm": 0.6630103588104248, "learning_rate": 4.1418563922942214e-06, "loss": 0.2964, "step": 1420 }, { "epoch": 0.04148178421298459, "grad_norm": 0.7226918339729309, "learning_rate": 4.144775248102744e-06, "loss": 0.3077, "step": 1421 }, { "epoch": 0.04151097617935544, "grad_norm": 0.6638982892036438, "learning_rate": 4.147694103911267e-06, "loss": 0.2346, "step": 1422 }, { "epoch": 0.041540168145726294, "grad_norm": 0.6884598731994629, "learning_rate": 4.150612959719791e-06, "loss": 0.3233, "step": 1423 }, { "epoch": 0.04156936011209715, "grad_norm": 0.7781869769096375, "learning_rate": 4.153531815528313e-06, "loss": 0.242, "step": 1424 }, { "epoch": 0.04159855207846801, "grad_norm": 0.5406455397605896, "learning_rate": 4.1564506713368364e-06, "loss": 0.2579, "step": 1425 }, { "epoch": 0.04162774404483886, "grad_norm": 0.655661940574646, "learning_rate": 4.159369527145359e-06, "loss": 0.2764, "step": 1426 }, { "epoch": 0.04165693601120971, "grad_norm": 1.9875470399856567, "learning_rate": 4.162288382953882e-06, "loss": 0.289, "step": 1427 }, { "epoch": 0.04168612797758057, "grad_norm": 0.8034581542015076, "learning_rate": 4.165207238762406e-06, "loss": 0.2769, "step": 1428 }, { "epoch": 0.041715319943951425, "grad_norm": 0.8466084003448486, "learning_rate": 4.168126094570928e-06, "loss": 0.2463, "step": 1429 }, { "epoch": 0.04174451191032228, "grad_norm": 0.6266846656799316, "learning_rate": 4.1710449503794515e-06, "loss": 0.2861, "step": 1430 }, { "epoch": 0.04177370387669314, "grad_norm": 0.8455002307891846, "learning_rate": 4.173963806187975e-06, "loss": 0.2826, "step": 1431 }, { "epoch": 0.041802895843063986, "grad_norm": 1.383252739906311, "learning_rate": 4.176882661996497e-06, "loss": 0.2514, "step": 1432 }, { "epoch": 0.04183208780943484, "grad_norm": 0.740601658821106, "learning_rate": 4.179801517805021e-06, "loss": 0.2862, "step": 1433 }, { "epoch": 0.0418612797758057, "grad_norm": 0.5531234741210938, "learning_rate": 4.182720373613544e-06, "loss": 0.2071, "step": 1434 }, { "epoch": 0.041890471742176555, "grad_norm": 1.474583625793457, "learning_rate": 4.185639229422067e-06, "loss": 0.2234, "step": 1435 }, { "epoch": 0.04191966370854741, "grad_norm": 0.9105049967765808, "learning_rate": 4.18855808523059e-06, "loss": 0.2899, "step": 1436 }, { "epoch": 0.04194885567491826, "grad_norm": 0.7255285382270813, "learning_rate": 4.191476941039113e-06, "loss": 0.2514, "step": 1437 }, { "epoch": 0.04197804764128912, "grad_norm": 0.6096013188362122, "learning_rate": 4.1943957968476365e-06, "loss": 0.2545, "step": 1438 }, { "epoch": 0.04200723960765997, "grad_norm": 0.5308489799499512, "learning_rate": 4.197314652656159e-06, "loss": 0.2207, "step": 1439 }, { "epoch": 0.04203643157403083, "grad_norm": 0.764522135257721, "learning_rate": 4.200233508464682e-06, "loss": 0.2804, "step": 1440 }, { "epoch": 0.04206562354040168, "grad_norm": 0.6919723153114319, "learning_rate": 4.203152364273206e-06, "loss": 0.2761, "step": 1441 }, { "epoch": 0.042094815506772534, "grad_norm": 0.8439251184463501, "learning_rate": 4.206071220081728e-06, "loss": 0.2847, "step": 1442 }, { "epoch": 0.04212400747314339, "grad_norm": 1.774158000946045, "learning_rate": 4.2089900758902515e-06, "loss": 0.3588, "step": 1443 }, { "epoch": 0.04215319943951425, "grad_norm": 0.5430887937545776, "learning_rate": 4.211908931698774e-06, "loss": 0.2473, "step": 1444 }, { "epoch": 0.0421823914058851, "grad_norm": 1.0557461977005005, "learning_rate": 4.214827787507297e-06, "loss": 0.2827, "step": 1445 }, { "epoch": 0.04221158337225595, "grad_norm": 0.5486223697662354, "learning_rate": 4.217746643315821e-06, "loss": 0.2018, "step": 1446 }, { "epoch": 0.04224077533862681, "grad_norm": 0.5723047256469727, "learning_rate": 4.220665499124343e-06, "loss": 0.2714, "step": 1447 }, { "epoch": 0.042269967304997665, "grad_norm": 0.6497229933738708, "learning_rate": 4.2235843549328665e-06, "loss": 0.2677, "step": 1448 }, { "epoch": 0.04229915927136852, "grad_norm": 0.6749289631843567, "learning_rate": 4.22650321074139e-06, "loss": 0.2569, "step": 1449 }, { "epoch": 0.04232835123773938, "grad_norm": 0.7685378789901733, "learning_rate": 4.229422066549913e-06, "loss": 0.2682, "step": 1450 }, { "epoch": 0.042357543204110226, "grad_norm": 0.5241769552230835, "learning_rate": 4.232340922358436e-06, "loss": 0.2975, "step": 1451 }, { "epoch": 0.04238673517048108, "grad_norm": 0.8142042756080627, "learning_rate": 4.235259778166959e-06, "loss": 0.2974, "step": 1452 }, { "epoch": 0.04241592713685194, "grad_norm": 0.5806944966316223, "learning_rate": 4.238178633975482e-06, "loss": 0.2385, "step": 1453 }, { "epoch": 0.042445119103222795, "grad_norm": 0.5609560608863831, "learning_rate": 4.241097489784005e-06, "loss": 0.223, "step": 1454 }, { "epoch": 0.04247431106959365, "grad_norm": 0.5359081625938416, "learning_rate": 4.244016345592528e-06, "loss": 0.2838, "step": 1455 }, { "epoch": 0.0425035030359645, "grad_norm": 0.7895520925521851, "learning_rate": 4.2469352014010515e-06, "loss": 0.2485, "step": 1456 }, { "epoch": 0.042532695002335356, "grad_norm": 1.3470120429992676, "learning_rate": 4.249854057209574e-06, "loss": 0.2374, "step": 1457 }, { "epoch": 0.04256188696870621, "grad_norm": 0.6571779847145081, "learning_rate": 4.252772913018097e-06, "loss": 0.2296, "step": 1458 }, { "epoch": 0.04259107893507707, "grad_norm": 0.6521427631378174, "learning_rate": 4.255691768826621e-06, "loss": 0.2561, "step": 1459 }, { "epoch": 0.04262027090144792, "grad_norm": 0.4988580048084259, "learning_rate": 4.258610624635143e-06, "loss": 0.2377, "step": 1460 }, { "epoch": 0.042649462867818774, "grad_norm": 0.6277069449424744, "learning_rate": 4.2615294804436665e-06, "loss": 0.2416, "step": 1461 }, { "epoch": 0.04267865483418963, "grad_norm": 0.5529517531394958, "learning_rate": 4.264448336252189e-06, "loss": 0.2653, "step": 1462 }, { "epoch": 0.04270784680056049, "grad_norm": 0.5832230448722839, "learning_rate": 4.267367192060712e-06, "loss": 0.2418, "step": 1463 }, { "epoch": 0.04273703876693134, "grad_norm": 0.6012144088745117, "learning_rate": 4.270286047869236e-06, "loss": 0.2161, "step": 1464 }, { "epoch": 0.04276623073330219, "grad_norm": 0.7748039364814758, "learning_rate": 4.273204903677758e-06, "loss": 0.2722, "step": 1465 }, { "epoch": 0.04279542269967305, "grad_norm": 0.6003648042678833, "learning_rate": 4.276123759486282e-06, "loss": 0.2283, "step": 1466 }, { "epoch": 0.042824614666043904, "grad_norm": 0.6665730476379395, "learning_rate": 4.279042615294805e-06, "loss": 0.2795, "step": 1467 }, { "epoch": 0.04285380663241476, "grad_norm": 0.5128280520439148, "learning_rate": 4.281961471103328e-06, "loss": 0.2041, "step": 1468 }, { "epoch": 0.04288299859878562, "grad_norm": 0.6114823222160339, "learning_rate": 4.284880326911851e-06, "loss": 0.2645, "step": 1469 }, { "epoch": 0.042912190565156466, "grad_norm": 1.3047242164611816, "learning_rate": 4.287799182720374e-06, "loss": 0.2883, "step": 1470 }, { "epoch": 0.04294138253152732, "grad_norm": 0.5866966843605042, "learning_rate": 4.290718038528897e-06, "loss": 0.2936, "step": 1471 }, { "epoch": 0.04297057449789818, "grad_norm": 0.6430572867393494, "learning_rate": 4.29363689433742e-06, "loss": 0.2554, "step": 1472 }, { "epoch": 0.042999766464269035, "grad_norm": 0.8677380681037903, "learning_rate": 4.296555750145943e-06, "loss": 0.2957, "step": 1473 }, { "epoch": 0.04302895843063989, "grad_norm": 0.7310620546340942, "learning_rate": 4.2994746059544666e-06, "loss": 0.2246, "step": 1474 }, { "epoch": 0.04305815039701074, "grad_norm": 0.7092506885528564, "learning_rate": 4.302393461762989e-06, "loss": 0.2659, "step": 1475 }, { "epoch": 0.043087342363381596, "grad_norm": 0.6571387648582458, "learning_rate": 4.305312317571512e-06, "loss": 0.256, "step": 1476 }, { "epoch": 0.04311653432975245, "grad_norm": 0.6561013460159302, "learning_rate": 4.308231173380035e-06, "loss": 0.298, "step": 1477 }, { "epoch": 0.04314572629612331, "grad_norm": 0.6589779257774353, "learning_rate": 4.311150029188558e-06, "loss": 0.2602, "step": 1478 }, { "epoch": 0.043174918262494165, "grad_norm": 0.53959721326828, "learning_rate": 4.3140688849970816e-06, "loss": 0.2983, "step": 1479 }, { "epoch": 0.043204110228865014, "grad_norm": 0.7218102216720581, "learning_rate": 4.316987740805604e-06, "loss": 0.2899, "step": 1480 }, { "epoch": 0.04323330219523587, "grad_norm": 0.6879385709762573, "learning_rate": 4.319906596614127e-06, "loss": 0.2536, "step": 1481 }, { "epoch": 0.04326249416160673, "grad_norm": 0.5267148017883301, "learning_rate": 4.322825452422651e-06, "loss": 0.2699, "step": 1482 }, { "epoch": 0.04329168612797758, "grad_norm": 0.5637660622596741, "learning_rate": 4.325744308231174e-06, "loss": 0.2314, "step": 1483 }, { "epoch": 0.04332087809434843, "grad_norm": 0.5602227449417114, "learning_rate": 4.328663164039697e-06, "loss": 0.2325, "step": 1484 }, { "epoch": 0.04335007006071929, "grad_norm": 0.7919492721557617, "learning_rate": 4.33158201984822e-06, "loss": 0.2686, "step": 1485 }, { "epoch": 0.043379262027090144, "grad_norm": 0.6562731862068176, "learning_rate": 4.334500875656743e-06, "loss": 0.3033, "step": 1486 }, { "epoch": 0.043408453993461, "grad_norm": 0.6554646492004395, "learning_rate": 4.337419731465266e-06, "loss": 0.2428, "step": 1487 }, { "epoch": 0.04343764595983186, "grad_norm": 0.615040123462677, "learning_rate": 4.340338587273789e-06, "loss": 0.2566, "step": 1488 }, { "epoch": 0.043466837926202706, "grad_norm": 0.7126705646514893, "learning_rate": 4.343257443082312e-06, "loss": 0.2299, "step": 1489 }, { "epoch": 0.04349602989257356, "grad_norm": 0.664545476436615, "learning_rate": 4.346176298890835e-06, "loss": 0.3073, "step": 1490 }, { "epoch": 0.04352522185894442, "grad_norm": 0.5767930150032043, "learning_rate": 4.349095154699358e-06, "loss": 0.2586, "step": 1491 }, { "epoch": 0.043554413825315275, "grad_norm": 0.7435709834098816, "learning_rate": 4.352014010507882e-06, "loss": 0.223, "step": 1492 }, { "epoch": 0.04358360579168613, "grad_norm": 0.6446989178657532, "learning_rate": 4.354932866316404e-06, "loss": 0.2587, "step": 1493 }, { "epoch": 0.04361279775805698, "grad_norm": 0.5523120164871216, "learning_rate": 4.3578517221249274e-06, "loss": 0.2303, "step": 1494 }, { "epoch": 0.043641989724427836, "grad_norm": 0.8358709812164307, "learning_rate": 4.36077057793345e-06, "loss": 0.2908, "step": 1495 }, { "epoch": 0.04367118169079869, "grad_norm": 0.5743159651756287, "learning_rate": 4.363689433741973e-06, "loss": 0.2404, "step": 1496 }, { "epoch": 0.04370037365716955, "grad_norm": 1.0667955875396729, "learning_rate": 4.366608289550497e-06, "loss": 0.25, "step": 1497 }, { "epoch": 0.043729565623540405, "grad_norm": 0.6429427862167358, "learning_rate": 4.36952714535902e-06, "loss": 0.256, "step": 1498 }, { "epoch": 0.043758757589911254, "grad_norm": 0.6175630688667297, "learning_rate": 4.372446001167543e-06, "loss": 0.2653, "step": 1499 }, { "epoch": 0.04378794955628211, "grad_norm": 0.9290846586227417, "learning_rate": 4.375364856976066e-06, "loss": 0.2493, "step": 1500 }, { "epoch": 0.043817141522652966, "grad_norm": 0.6546082496643066, "learning_rate": 4.378283712784589e-06, "loss": 0.254, "step": 1501 }, { "epoch": 0.04384633348902382, "grad_norm": 1.0379629135131836, "learning_rate": 4.381202568593112e-06, "loss": 0.3073, "step": 1502 }, { "epoch": 0.04387552545539468, "grad_norm": 0.6361823678016663, "learning_rate": 4.384121424401635e-06, "loss": 0.2138, "step": 1503 }, { "epoch": 0.04390471742176553, "grad_norm": 0.6322582960128784, "learning_rate": 4.387040280210158e-06, "loss": 0.2832, "step": 1504 }, { "epoch": 0.043933909388136384, "grad_norm": 0.9679371118545532, "learning_rate": 4.389959136018681e-06, "loss": 0.2295, "step": 1505 }, { "epoch": 0.04396310135450724, "grad_norm": 0.6420916318893433, "learning_rate": 4.392877991827204e-06, "loss": 0.2466, "step": 1506 }, { "epoch": 0.0439922933208781, "grad_norm": 0.6495078206062317, "learning_rate": 4.3957968476357275e-06, "loss": 0.2442, "step": 1507 }, { "epoch": 0.044021485287248946, "grad_norm": 0.6195148825645447, "learning_rate": 4.39871570344425e-06, "loss": 0.2687, "step": 1508 }, { "epoch": 0.0440506772536198, "grad_norm": 0.7299003005027771, "learning_rate": 4.401634559252773e-06, "loss": 0.2592, "step": 1509 }, { "epoch": 0.04407986921999066, "grad_norm": 0.5308722853660583, "learning_rate": 4.404553415061296e-06, "loss": 0.2134, "step": 1510 }, { "epoch": 0.044109061186361515, "grad_norm": 1.9345347881317139, "learning_rate": 4.407472270869819e-06, "loss": 0.288, "step": 1511 }, { "epoch": 0.04413825315273237, "grad_norm": 0.5565072894096375, "learning_rate": 4.4103911266783425e-06, "loss": 0.2632, "step": 1512 }, { "epoch": 0.04416744511910322, "grad_norm": 0.5631683468818665, "learning_rate": 4.413309982486865e-06, "loss": 0.2449, "step": 1513 }, { "epoch": 0.044196637085474076, "grad_norm": 0.63406902551651, "learning_rate": 4.416228838295389e-06, "loss": 0.26, "step": 1514 }, { "epoch": 0.04422582905184493, "grad_norm": 0.8561868667602539, "learning_rate": 4.419147694103912e-06, "loss": 0.2846, "step": 1515 }, { "epoch": 0.04425502101821579, "grad_norm": 0.6945813894271851, "learning_rate": 4.422066549912435e-06, "loss": 0.2605, "step": 1516 }, { "epoch": 0.044284212984586645, "grad_norm": 0.5662814974784851, "learning_rate": 4.424985405720958e-06, "loss": 0.2239, "step": 1517 }, { "epoch": 0.044313404950957494, "grad_norm": 0.6587706208229065, "learning_rate": 4.427904261529481e-06, "loss": 0.2707, "step": 1518 }, { "epoch": 0.04434259691732835, "grad_norm": 0.5969984531402588, "learning_rate": 4.430823117338004e-06, "loss": 0.2682, "step": 1519 }, { "epoch": 0.044371788883699206, "grad_norm": 0.5575631856918335, "learning_rate": 4.433741973146527e-06, "loss": 0.2598, "step": 1520 }, { "epoch": 0.04440098085007006, "grad_norm": 0.5249908566474915, "learning_rate": 4.43666082895505e-06, "loss": 0.217, "step": 1521 }, { "epoch": 0.04443017281644092, "grad_norm": 0.5825467109680176, "learning_rate": 4.439579684763573e-06, "loss": 0.2867, "step": 1522 }, { "epoch": 0.04445936478281177, "grad_norm": 0.5157190561294556, "learning_rate": 4.442498540572096e-06, "loss": 0.2583, "step": 1523 }, { "epoch": 0.044488556749182624, "grad_norm": 0.4961676597595215, "learning_rate": 4.445417396380619e-06, "loss": 0.2198, "step": 1524 }, { "epoch": 0.04451774871555348, "grad_norm": 0.5684533715248108, "learning_rate": 4.4483362521891425e-06, "loss": 0.261, "step": 1525 }, { "epoch": 0.04454694068192434, "grad_norm": 0.615780770778656, "learning_rate": 4.451255107997665e-06, "loss": 0.2021, "step": 1526 }, { "epoch": 0.044576132648295186, "grad_norm": 1.7040287256240845, "learning_rate": 4.454173963806188e-06, "loss": 0.2631, "step": 1527 }, { "epoch": 0.04460532461466604, "grad_norm": 0.749566912651062, "learning_rate": 4.457092819614711e-06, "loss": 0.264, "step": 1528 }, { "epoch": 0.0446345165810369, "grad_norm": 0.7538249492645264, "learning_rate": 4.460011675423234e-06, "loss": 0.2562, "step": 1529 }, { "epoch": 0.044663708547407754, "grad_norm": 0.4622276723384857, "learning_rate": 4.4629305312317575e-06, "loss": 0.2174, "step": 1530 }, { "epoch": 0.04469290051377861, "grad_norm": 0.5393751263618469, "learning_rate": 4.465849387040281e-06, "loss": 0.2434, "step": 1531 }, { "epoch": 0.04472209248014946, "grad_norm": 0.8197965025901794, "learning_rate": 4.468768242848804e-06, "loss": 0.2752, "step": 1532 }, { "epoch": 0.044751284446520316, "grad_norm": 0.6391374468803406, "learning_rate": 4.471687098657327e-06, "loss": 0.2543, "step": 1533 }, { "epoch": 0.04478047641289117, "grad_norm": 0.516251266002655, "learning_rate": 4.47460595446585e-06, "loss": 0.2574, "step": 1534 }, { "epoch": 0.04480966837926203, "grad_norm": 0.6995957493782043, "learning_rate": 4.4775248102743725e-06, "loss": 0.3219, "step": 1535 }, { "epoch": 0.044838860345632885, "grad_norm": 0.7605786323547363, "learning_rate": 4.480443666082896e-06, "loss": 0.275, "step": 1536 }, { "epoch": 0.044868052312003734, "grad_norm": 0.6189056038856506, "learning_rate": 4.483362521891419e-06, "loss": 0.2821, "step": 1537 }, { "epoch": 0.04489724427837459, "grad_norm": 0.7026090621948242, "learning_rate": 4.486281377699942e-06, "loss": 0.3226, "step": 1538 }, { "epoch": 0.044926436244745446, "grad_norm": 0.6784411072731018, "learning_rate": 4.489200233508465e-06, "loss": 0.2779, "step": 1539 }, { "epoch": 0.0449556282111163, "grad_norm": 0.5860919952392578, "learning_rate": 4.492119089316988e-06, "loss": 0.253, "step": 1540 }, { "epoch": 0.04498482017748716, "grad_norm": 0.7670789957046509, "learning_rate": 4.495037945125511e-06, "loss": 0.2591, "step": 1541 }, { "epoch": 0.04501401214385801, "grad_norm": 0.8078626394271851, "learning_rate": 4.497956800934034e-06, "loss": 0.2791, "step": 1542 }, { "epoch": 0.045043204110228864, "grad_norm": 0.5667933225631714, "learning_rate": 4.500875656742557e-06, "loss": 0.215, "step": 1543 }, { "epoch": 0.04507239607659972, "grad_norm": 0.7680216431617737, "learning_rate": 4.50379451255108e-06, "loss": 0.2687, "step": 1544 }, { "epoch": 0.045101588042970576, "grad_norm": 0.7506825923919678, "learning_rate": 4.506713368359603e-06, "loss": 0.2921, "step": 1545 }, { "epoch": 0.04513078000934143, "grad_norm": 0.7872316837310791, "learning_rate": 4.509632224168127e-06, "loss": 0.2745, "step": 1546 }, { "epoch": 0.04515997197571228, "grad_norm": 0.564350426197052, "learning_rate": 4.51255107997665e-06, "loss": 0.2644, "step": 1547 }, { "epoch": 0.04518916394208314, "grad_norm": 0.6052416563034058, "learning_rate": 4.5154699357851725e-06, "loss": 0.27, "step": 1548 }, { "epoch": 0.045218355908453994, "grad_norm": 0.9107329845428467, "learning_rate": 4.518388791593696e-06, "loss": 0.2522, "step": 1549 }, { "epoch": 0.04524754787482485, "grad_norm": 0.6294164061546326, "learning_rate": 4.521307647402219e-06, "loss": 0.2753, "step": 1550 }, { "epoch": 0.0452767398411957, "grad_norm": 0.649596631526947, "learning_rate": 4.524226503210742e-06, "loss": 0.2672, "step": 1551 }, { "epoch": 0.045305931807566556, "grad_norm": 0.7885779142379761, "learning_rate": 4.527145359019265e-06, "loss": 0.2416, "step": 1552 }, { "epoch": 0.04533512377393741, "grad_norm": 0.6408547163009644, "learning_rate": 4.5300642148277876e-06, "loss": 0.2342, "step": 1553 }, { "epoch": 0.04536431574030827, "grad_norm": 0.7055039405822754, "learning_rate": 4.532983070636311e-06, "loss": 0.2531, "step": 1554 }, { "epoch": 0.045393507706679125, "grad_norm": 0.5453196167945862, "learning_rate": 4.535901926444834e-06, "loss": 0.2713, "step": 1555 }, { "epoch": 0.045422699673049974, "grad_norm": 0.6114009022712708, "learning_rate": 4.538820782253357e-06, "loss": 0.2271, "step": 1556 }, { "epoch": 0.04545189163942083, "grad_norm": 2.663926124572754, "learning_rate": 4.54173963806188e-06, "loss": 0.3009, "step": 1557 }, { "epoch": 0.045481083605791686, "grad_norm": 0.615548849105835, "learning_rate": 4.544658493870403e-06, "loss": 0.2362, "step": 1558 }, { "epoch": 0.04551027557216254, "grad_norm": 0.7951820492744446, "learning_rate": 4.547577349678926e-06, "loss": 0.2687, "step": 1559 }, { "epoch": 0.0455394675385334, "grad_norm": 0.609737753868103, "learning_rate": 4.550496205487449e-06, "loss": 0.244, "step": 1560 }, { "epoch": 0.04556865950490425, "grad_norm": 0.6911963224411011, "learning_rate": 4.553415061295972e-06, "loss": 0.196, "step": 1561 }, { "epoch": 0.045597851471275104, "grad_norm": 0.7219465374946594, "learning_rate": 4.556333917104496e-06, "loss": 0.2953, "step": 1562 }, { "epoch": 0.04562704343764596, "grad_norm": 0.6040470600128174, "learning_rate": 4.559252772913018e-06, "loss": 0.2822, "step": 1563 }, { "epoch": 0.045656235404016816, "grad_norm": 0.4534539580345154, "learning_rate": 4.562171628721542e-06, "loss": 0.2418, "step": 1564 }, { "epoch": 0.04568542737038767, "grad_norm": 0.5063628554344177, "learning_rate": 4.565090484530065e-06, "loss": 0.2637, "step": 1565 }, { "epoch": 0.04571461933675852, "grad_norm": 1.07989501953125, "learning_rate": 4.568009340338588e-06, "loss": 0.2711, "step": 1566 }, { "epoch": 0.04574381130312938, "grad_norm": 0.5061838626861572, "learning_rate": 4.570928196147111e-06, "loss": 0.2295, "step": 1567 }, { "epoch": 0.045773003269500234, "grad_norm": 0.5332338213920593, "learning_rate": 4.573847051955633e-06, "loss": 0.2382, "step": 1568 }, { "epoch": 0.04580219523587109, "grad_norm": 0.6473053097724915, "learning_rate": 4.576765907764157e-06, "loss": 0.3214, "step": 1569 }, { "epoch": 0.04583138720224194, "grad_norm": 0.5314735174179077, "learning_rate": 4.57968476357268e-06, "loss": 0.2536, "step": 1570 }, { "epoch": 0.045860579168612796, "grad_norm": 0.5321048498153687, "learning_rate": 4.582603619381203e-06, "loss": 0.2128, "step": 1571 }, { "epoch": 0.04588977113498365, "grad_norm": 0.5688034296035767, "learning_rate": 4.585522475189726e-06, "loss": 0.2831, "step": 1572 }, { "epoch": 0.04591896310135451, "grad_norm": 0.5466676950454712, "learning_rate": 4.588441330998249e-06, "loss": 0.2382, "step": 1573 }, { "epoch": 0.045948155067725364, "grad_norm": 0.5495280027389526, "learning_rate": 4.591360186806772e-06, "loss": 0.2546, "step": 1574 }, { "epoch": 0.045977347034096214, "grad_norm": 0.5428436994552612, "learning_rate": 4.594279042615295e-06, "loss": 0.2534, "step": 1575 }, { "epoch": 0.04600653900046707, "grad_norm": 0.9740315675735474, "learning_rate": 4.5971978984238184e-06, "loss": 0.2847, "step": 1576 }, { "epoch": 0.046035730966837926, "grad_norm": 0.692699134349823, "learning_rate": 4.600116754232341e-06, "loss": 0.2797, "step": 1577 }, { "epoch": 0.04606492293320878, "grad_norm": 0.6044122576713562, "learning_rate": 4.603035610040864e-06, "loss": 0.3393, "step": 1578 }, { "epoch": 0.04609411489957964, "grad_norm": 0.5565891265869141, "learning_rate": 4.605954465849388e-06, "loss": 0.273, "step": 1579 }, { "epoch": 0.04612330686595049, "grad_norm": 0.7851797938346863, "learning_rate": 4.608873321657911e-06, "loss": 0.2633, "step": 1580 }, { "epoch": 0.046152498832321344, "grad_norm": 0.714654266834259, "learning_rate": 4.6117921774664335e-06, "loss": 0.3279, "step": 1581 }, { "epoch": 0.0461816907986922, "grad_norm": 0.5281979441642761, "learning_rate": 4.614711033274957e-06, "loss": 0.2301, "step": 1582 }, { "epoch": 0.046210882765063056, "grad_norm": 1.1633344888687134, "learning_rate": 4.61762988908348e-06, "loss": 0.2805, "step": 1583 }, { "epoch": 0.04624007473143391, "grad_norm": 0.6324998140335083, "learning_rate": 4.620548744892003e-06, "loss": 0.3081, "step": 1584 }, { "epoch": 0.04626926669780476, "grad_norm": 0.7189042568206787, "learning_rate": 4.623467600700526e-06, "loss": 0.2555, "step": 1585 }, { "epoch": 0.04629845866417562, "grad_norm": 0.8526767492294312, "learning_rate": 4.6263864565090485e-06, "loss": 0.2649, "step": 1586 }, { "epoch": 0.046327650630546474, "grad_norm": 0.5412688851356506, "learning_rate": 4.629305312317572e-06, "loss": 0.3004, "step": 1587 }, { "epoch": 0.04635684259691733, "grad_norm": 0.6121076345443726, "learning_rate": 4.632224168126095e-06, "loss": 0.2247, "step": 1588 }, { "epoch": 0.046386034563288187, "grad_norm": 0.5726518034934998, "learning_rate": 4.635143023934618e-06, "loss": 0.2383, "step": 1589 }, { "epoch": 0.046415226529659036, "grad_norm": 0.8295573592185974, "learning_rate": 4.638061879743141e-06, "loss": 0.3354, "step": 1590 }, { "epoch": 0.04644441849602989, "grad_norm": 0.7754232287406921, "learning_rate": 4.640980735551664e-06, "loss": 0.2744, "step": 1591 }, { "epoch": 0.04647361046240075, "grad_norm": 0.5921323299407959, "learning_rate": 4.643899591360187e-06, "loss": 0.2973, "step": 1592 }, { "epoch": 0.046502802428771604, "grad_norm": 1.0821300745010376, "learning_rate": 4.64681844716871e-06, "loss": 0.2121, "step": 1593 }, { "epoch": 0.046531994395142454, "grad_norm": 0.8049931526184082, "learning_rate": 4.6497373029772335e-06, "loss": 0.273, "step": 1594 }, { "epoch": 0.04656118636151331, "grad_norm": 1.4357101917266846, "learning_rate": 4.652656158785757e-06, "loss": 0.2664, "step": 1595 }, { "epoch": 0.046590378327884166, "grad_norm": 0.5054873824119568, "learning_rate": 4.655575014594279e-06, "loss": 0.256, "step": 1596 }, { "epoch": 0.04661957029425502, "grad_norm": 0.5839630961418152, "learning_rate": 4.658493870402803e-06, "loss": 0.2701, "step": 1597 }, { "epoch": 0.04664876226062588, "grad_norm": 0.5419100522994995, "learning_rate": 4.661412726211326e-06, "loss": 0.2482, "step": 1598 }, { "epoch": 0.04667795422699673, "grad_norm": 0.5188365578651428, "learning_rate": 4.6643315820198485e-06, "loss": 0.2519, "step": 1599 }, { "epoch": 0.046707146193367584, "grad_norm": 0.563689112663269, "learning_rate": 4.667250437828372e-06, "loss": 0.2507, "step": 1600 }, { "epoch": 0.04673633815973844, "grad_norm": 0.6296635270118713, "learning_rate": 4.670169293636895e-06, "loss": 0.2836, "step": 1601 }, { "epoch": 0.046765530126109296, "grad_norm": 0.747812807559967, "learning_rate": 4.673088149445418e-06, "loss": 0.2576, "step": 1602 }, { "epoch": 0.04679472209248015, "grad_norm": 0.5388004183769226, "learning_rate": 4.676007005253941e-06, "loss": 0.2619, "step": 1603 }, { "epoch": 0.046823914058851, "grad_norm": 0.6322676539421082, "learning_rate": 4.6789258610624635e-06, "loss": 0.262, "step": 1604 }, { "epoch": 0.04685310602522186, "grad_norm": 0.4865185022354126, "learning_rate": 4.681844716870987e-06, "loss": 0.232, "step": 1605 }, { "epoch": 0.046882297991592714, "grad_norm": 0.7513160109519958, "learning_rate": 4.68476357267951e-06, "loss": 0.2497, "step": 1606 }, { "epoch": 0.04691148995796357, "grad_norm": 0.5943982005119324, "learning_rate": 4.687682428488033e-06, "loss": 0.2535, "step": 1607 }, { "epoch": 0.046940681924334426, "grad_norm": 0.7336174249649048, "learning_rate": 4.690601284296556e-06, "loss": 0.2658, "step": 1608 }, { "epoch": 0.046969873890705276, "grad_norm": 0.480724036693573, "learning_rate": 4.693520140105079e-06, "loss": 0.21, "step": 1609 }, { "epoch": 0.04699906585707613, "grad_norm": 0.603253960609436, "learning_rate": 4.696438995913603e-06, "loss": 0.2381, "step": 1610 }, { "epoch": 0.04702825782344699, "grad_norm": 0.7350099682807922, "learning_rate": 4.699357851722125e-06, "loss": 0.2135, "step": 1611 }, { "epoch": 0.047057449789817844, "grad_norm": 0.7390801310539246, "learning_rate": 4.7022767075306485e-06, "loss": 0.3643, "step": 1612 }, { "epoch": 0.047086641756188694, "grad_norm": 0.6105063557624817, "learning_rate": 4.705195563339172e-06, "loss": 0.2155, "step": 1613 }, { "epoch": 0.04711583372255955, "grad_norm": 0.7078747749328613, "learning_rate": 4.708114419147694e-06, "loss": 0.314, "step": 1614 }, { "epoch": 0.047145025688930406, "grad_norm": 0.7713925242424011, "learning_rate": 4.711033274956218e-06, "loss": 0.2766, "step": 1615 }, { "epoch": 0.04717421765530126, "grad_norm": 0.5390685200691223, "learning_rate": 4.713952130764741e-06, "loss": 0.2079, "step": 1616 }, { "epoch": 0.04720340962167212, "grad_norm": 0.6250056624412537, "learning_rate": 4.7168709865732635e-06, "loss": 0.2894, "step": 1617 }, { "epoch": 0.04723260158804297, "grad_norm": 1.4274908304214478, "learning_rate": 4.719789842381787e-06, "loss": 0.2145, "step": 1618 }, { "epoch": 0.047261793554413824, "grad_norm": 0.9742424488067627, "learning_rate": 4.722708698190309e-06, "loss": 0.2542, "step": 1619 }, { "epoch": 0.04729098552078468, "grad_norm": 0.6558396816253662, "learning_rate": 4.725627553998833e-06, "loss": 0.2919, "step": 1620 }, { "epoch": 0.047320177487155536, "grad_norm": 0.5179500579833984, "learning_rate": 4.728546409807356e-06, "loss": 0.2429, "step": 1621 }, { "epoch": 0.04734936945352639, "grad_norm": 0.5597602725028992, "learning_rate": 4.7314652656158785e-06, "loss": 0.2718, "step": 1622 }, { "epoch": 0.04737856141989724, "grad_norm": 0.6015702486038208, "learning_rate": 4.734384121424402e-06, "loss": 0.2712, "step": 1623 }, { "epoch": 0.0474077533862681, "grad_norm": 0.5606504082679749, "learning_rate": 4.737302977232925e-06, "loss": 0.2518, "step": 1624 }, { "epoch": 0.047436945352638954, "grad_norm": 0.5815452337265015, "learning_rate": 4.740221833041448e-06, "loss": 0.2429, "step": 1625 }, { "epoch": 0.04746613731900981, "grad_norm": 0.6882293820381165, "learning_rate": 4.743140688849972e-06, "loss": 0.2954, "step": 1626 }, { "epoch": 0.047495329285380666, "grad_norm": 1.0782219171524048, "learning_rate": 4.746059544658494e-06, "loss": 0.257, "step": 1627 }, { "epoch": 0.047524521251751516, "grad_norm": 0.5759809613227844, "learning_rate": 4.748978400467018e-06, "loss": 0.3224, "step": 1628 }, { "epoch": 0.04755371321812237, "grad_norm": 0.8961030840873718, "learning_rate": 4.75189725627554e-06, "loss": 0.2887, "step": 1629 }, { "epoch": 0.04758290518449323, "grad_norm": 0.5316184163093567, "learning_rate": 4.7548161120840636e-06, "loss": 0.2393, "step": 1630 }, { "epoch": 0.047612097150864084, "grad_norm": 0.5726950764656067, "learning_rate": 4.757734967892587e-06, "loss": 0.2789, "step": 1631 }, { "epoch": 0.04764128911723494, "grad_norm": 0.7775495052337646, "learning_rate": 4.760653823701109e-06, "loss": 0.2892, "step": 1632 }, { "epoch": 0.04767048108360579, "grad_norm": 0.5004746317863464, "learning_rate": 4.763572679509633e-06, "loss": 0.2611, "step": 1633 }, { "epoch": 0.047699673049976646, "grad_norm": 0.4904175102710724, "learning_rate": 4.766491535318156e-06, "loss": 0.2591, "step": 1634 }, { "epoch": 0.0477288650163475, "grad_norm": 0.6871745586395264, "learning_rate": 4.7694103911266786e-06, "loss": 0.2883, "step": 1635 }, { "epoch": 0.04775805698271836, "grad_norm": 0.6266492605209351, "learning_rate": 4.772329246935202e-06, "loss": 0.291, "step": 1636 }, { "epoch": 0.04778724894908921, "grad_norm": 0.4539826810359955, "learning_rate": 4.775248102743724e-06, "loss": 0.2005, "step": 1637 }, { "epoch": 0.047816440915460064, "grad_norm": 0.5538692474365234, "learning_rate": 4.778166958552248e-06, "loss": 0.252, "step": 1638 }, { "epoch": 0.04784563288183092, "grad_norm": 0.8579726219177246, "learning_rate": 4.781085814360771e-06, "loss": 0.2773, "step": 1639 }, { "epoch": 0.047874824848201776, "grad_norm": 0.732215166091919, "learning_rate": 4.7840046701692936e-06, "loss": 0.3311, "step": 1640 }, { "epoch": 0.04790401681457263, "grad_norm": 1.0231080055236816, "learning_rate": 4.786923525977817e-06, "loss": 0.2958, "step": 1641 }, { "epoch": 0.04793320878094348, "grad_norm": 0.619674801826477, "learning_rate": 4.78984238178634e-06, "loss": 0.2197, "step": 1642 }, { "epoch": 0.04796240074731434, "grad_norm": 0.5033711791038513, "learning_rate": 4.792761237594864e-06, "loss": 0.2249, "step": 1643 }, { "epoch": 0.047991592713685194, "grad_norm": 0.5394318103790283, "learning_rate": 4.795680093403386e-06, "loss": 0.2765, "step": 1644 }, { "epoch": 0.04802078468005605, "grad_norm": 4.032418251037598, "learning_rate": 4.7985989492119094e-06, "loss": 0.2623, "step": 1645 }, { "epoch": 0.048049976646426906, "grad_norm": 0.6821284294128418, "learning_rate": 4.801517805020433e-06, "loss": 0.2142, "step": 1646 }, { "epoch": 0.048079168612797755, "grad_norm": 0.5970382690429688, "learning_rate": 4.804436660828955e-06, "loss": 0.2853, "step": 1647 }, { "epoch": 0.04810836057916861, "grad_norm": 0.5663349032402039, "learning_rate": 4.807355516637479e-06, "loss": 0.2709, "step": 1648 }, { "epoch": 0.04813755254553947, "grad_norm": 0.782393217086792, "learning_rate": 4.810274372446002e-06, "loss": 0.2961, "step": 1649 }, { "epoch": 0.048166744511910324, "grad_norm": 0.5090887546539307, "learning_rate": 4.8131932282545244e-06, "loss": 0.26, "step": 1650 }, { "epoch": 0.04819593647828118, "grad_norm": 0.5572957396507263, "learning_rate": 4.816112084063048e-06, "loss": 0.2733, "step": 1651 }, { "epoch": 0.04822512844465203, "grad_norm": 0.71962571144104, "learning_rate": 4.81903093987157e-06, "loss": 0.2518, "step": 1652 }, { "epoch": 0.048254320411022886, "grad_norm": 0.47036871314048767, "learning_rate": 4.821949795680094e-06, "loss": 0.192, "step": 1653 }, { "epoch": 0.04828351237739374, "grad_norm": 0.6699323654174805, "learning_rate": 4.824868651488617e-06, "loss": 0.2784, "step": 1654 }, { "epoch": 0.0483127043437646, "grad_norm": 0.6193002462387085, "learning_rate": 4.8277875072971394e-06, "loss": 0.2191, "step": 1655 }, { "epoch": 0.04834189631013545, "grad_norm": 0.5096866488456726, "learning_rate": 4.830706363105663e-06, "loss": 0.2274, "step": 1656 }, { "epoch": 0.048371088276506304, "grad_norm": 0.6408360004425049, "learning_rate": 4.833625218914186e-06, "loss": 0.2991, "step": 1657 }, { "epoch": 0.04840028024287716, "grad_norm": 0.5203664302825928, "learning_rate": 4.8365440747227095e-06, "loss": 0.2238, "step": 1658 }, { "epoch": 0.048429472209248016, "grad_norm": 0.5501306653022766, "learning_rate": 4.839462930531233e-06, "loss": 0.2105, "step": 1659 }, { "epoch": 0.04845866417561887, "grad_norm": 1.972617506980896, "learning_rate": 4.842381786339755e-06, "loss": 0.2958, "step": 1660 }, { "epoch": 0.04848785614198972, "grad_norm": 0.5514668822288513, "learning_rate": 4.845300642148279e-06, "loss": 0.2459, "step": 1661 }, { "epoch": 0.04851704810836058, "grad_norm": 0.6321591734886169, "learning_rate": 4.848219497956801e-06, "loss": 0.2597, "step": 1662 }, { "epoch": 0.048546240074731434, "grad_norm": 0.6585676074028015, "learning_rate": 4.8511383537653245e-06, "loss": 0.2443, "step": 1663 }, { "epoch": 0.04857543204110229, "grad_norm": 0.43946436047554016, "learning_rate": 4.854057209573848e-06, "loss": 0.221, "step": 1664 }, { "epoch": 0.048604624007473146, "grad_norm": 0.6563472151756287, "learning_rate": 4.85697606538237e-06, "loss": 0.3075, "step": 1665 }, { "epoch": 0.048633815973843995, "grad_norm": 0.573387086391449, "learning_rate": 4.859894921190894e-06, "loss": 0.2257, "step": 1666 }, { "epoch": 0.04866300794021485, "grad_norm": 0.5156608819961548, "learning_rate": 4.862813776999417e-06, "loss": 0.2441, "step": 1667 }, { "epoch": 0.04869219990658571, "grad_norm": 0.6964971423149109, "learning_rate": 4.8657326328079395e-06, "loss": 0.2699, "step": 1668 }, { "epoch": 0.048721391872956564, "grad_norm": 0.5878532528877258, "learning_rate": 4.868651488616463e-06, "loss": 0.2245, "step": 1669 }, { "epoch": 0.04875058383932742, "grad_norm": 0.512685239315033, "learning_rate": 4.871570344424985e-06, "loss": 0.298, "step": 1670 }, { "epoch": 0.04877977580569827, "grad_norm": 0.4820605516433716, "learning_rate": 4.874489200233509e-06, "loss": 0.2437, "step": 1671 }, { "epoch": 0.048808967772069126, "grad_norm": 0.5051032900810242, "learning_rate": 4.877408056042032e-06, "loss": 0.2079, "step": 1672 }, { "epoch": 0.04883815973843998, "grad_norm": 1.211311936378479, "learning_rate": 4.8803269118505545e-06, "loss": 0.2555, "step": 1673 }, { "epoch": 0.04886735170481084, "grad_norm": 0.5339981317520142, "learning_rate": 4.883245767659079e-06, "loss": 0.2545, "step": 1674 }, { "epoch": 0.048896543671181694, "grad_norm": 0.6316618919372559, "learning_rate": 4.886164623467601e-06, "loss": 0.3228, "step": 1675 }, { "epoch": 0.04892573563755254, "grad_norm": 0.6240411996841431, "learning_rate": 4.8890834792761245e-06, "loss": 0.2592, "step": 1676 }, { "epoch": 0.0489549276039234, "grad_norm": 0.5087401866912842, "learning_rate": 4.892002335084647e-06, "loss": 0.2656, "step": 1677 }, { "epoch": 0.048984119570294256, "grad_norm": 0.6183250546455383, "learning_rate": 4.89492119089317e-06, "loss": 0.2714, "step": 1678 }, { "epoch": 0.04901331153666511, "grad_norm": 0.5242025852203369, "learning_rate": 4.897840046701694e-06, "loss": 0.2744, "step": 1679 }, { "epoch": 0.04904250350303596, "grad_norm": 0.5401448607444763, "learning_rate": 4.900758902510216e-06, "loss": 0.2762, "step": 1680 }, { "epoch": 0.04907169546940682, "grad_norm": 0.5793387293815613, "learning_rate": 4.9036777583187395e-06, "loss": 0.2809, "step": 1681 }, { "epoch": 0.049100887435777674, "grad_norm": 0.48330336809158325, "learning_rate": 4.906596614127263e-06, "loss": 0.2179, "step": 1682 }, { "epoch": 0.04913007940214853, "grad_norm": 0.5063871741294861, "learning_rate": 4.909515469935785e-06, "loss": 0.2434, "step": 1683 }, { "epoch": 0.049159271368519386, "grad_norm": 0.6050793528556824, "learning_rate": 4.912434325744309e-06, "loss": 0.2758, "step": 1684 }, { "epoch": 0.049188463334890235, "grad_norm": 0.6766660809516907, "learning_rate": 4.915353181552831e-06, "loss": 0.3048, "step": 1685 }, { "epoch": 0.04921765530126109, "grad_norm": 0.717021107673645, "learning_rate": 4.9182720373613545e-06, "loss": 0.2706, "step": 1686 }, { "epoch": 0.04924684726763195, "grad_norm": 0.5762807130813599, "learning_rate": 4.921190893169878e-06, "loss": 0.2656, "step": 1687 }, { "epoch": 0.049276039234002804, "grad_norm": 0.5897207856178284, "learning_rate": 4.9241097489784e-06, "loss": 0.2842, "step": 1688 }, { "epoch": 0.04930523120037366, "grad_norm": 0.6857703924179077, "learning_rate": 4.927028604786924e-06, "loss": 0.2995, "step": 1689 }, { "epoch": 0.04933442316674451, "grad_norm": 0.6076372265815735, "learning_rate": 4.929947460595447e-06, "loss": 0.3019, "step": 1690 }, { "epoch": 0.049363615133115366, "grad_norm": 0.5891818404197693, "learning_rate": 4.93286631640397e-06, "loss": 0.2564, "step": 1691 }, { "epoch": 0.04939280709948622, "grad_norm": 0.6146661043167114, "learning_rate": 4.935785172212494e-06, "loss": 0.3101, "step": 1692 }, { "epoch": 0.04942199906585708, "grad_norm": 0.4894181787967682, "learning_rate": 4.938704028021016e-06, "loss": 0.2512, "step": 1693 }, { "epoch": 0.049451191032227934, "grad_norm": 0.5577490925788879, "learning_rate": 4.9416228838295395e-06, "loss": 0.2274, "step": 1694 }, { "epoch": 0.04948038299859878, "grad_norm": 0.5066959261894226, "learning_rate": 4.944541739638062e-06, "loss": 0.25, "step": 1695 }, { "epoch": 0.04950957496496964, "grad_norm": 0.608101487159729, "learning_rate": 4.947460595446585e-06, "loss": 0.2709, "step": 1696 }, { "epoch": 0.049538766931340496, "grad_norm": 0.6976808905601501, "learning_rate": 4.950379451255109e-06, "loss": 0.2601, "step": 1697 }, { "epoch": 0.04956795889771135, "grad_norm": 0.643957257270813, "learning_rate": 4.953298307063631e-06, "loss": 0.297, "step": 1698 }, { "epoch": 0.0495971508640822, "grad_norm": 0.8089472055435181, "learning_rate": 4.9562171628721545e-06, "loss": 0.2532, "step": 1699 }, { "epoch": 0.04962634283045306, "grad_norm": 0.5319665670394897, "learning_rate": 4.959136018680678e-06, "loss": 0.2321, "step": 1700 }, { "epoch": 0.049655534796823914, "grad_norm": 0.5696665644645691, "learning_rate": 4.9620548744892e-06, "loss": 0.2602, "step": 1701 }, { "epoch": 0.04968472676319477, "grad_norm": 0.5143440365791321, "learning_rate": 4.964973730297724e-06, "loss": 0.2326, "step": 1702 }, { "epoch": 0.049713918729565626, "grad_norm": 0.7050856947898865, "learning_rate": 4.967892586106246e-06, "loss": 0.2481, "step": 1703 }, { "epoch": 0.049743110695936475, "grad_norm": 0.6244530081748962, "learning_rate": 4.9708114419147695e-06, "loss": 0.3185, "step": 1704 }, { "epoch": 0.04977230266230733, "grad_norm": 0.8852602243423462, "learning_rate": 4.973730297723293e-06, "loss": 0.3057, "step": 1705 }, { "epoch": 0.04980149462867819, "grad_norm": 0.5913354158401489, "learning_rate": 4.976649153531816e-06, "loss": 0.2447, "step": 1706 }, { "epoch": 0.049830686595049044, "grad_norm": 0.6215046048164368, "learning_rate": 4.9795680093403396e-06, "loss": 0.2548, "step": 1707 }, { "epoch": 0.0498598785614199, "grad_norm": 0.6648038029670715, "learning_rate": 4.982486865148862e-06, "loss": 0.2695, "step": 1708 }, { "epoch": 0.04988907052779075, "grad_norm": 0.5976206064224243, "learning_rate": 4.985405720957385e-06, "loss": 0.2821, "step": 1709 }, { "epoch": 0.049918262494161605, "grad_norm": 0.48901572823524475, "learning_rate": 4.988324576765908e-06, "loss": 0.23, "step": 1710 }, { "epoch": 0.04994745446053246, "grad_norm": 0.5857312679290771, "learning_rate": 4.991243432574431e-06, "loss": 0.2716, "step": 1711 }, { "epoch": 0.04997664642690332, "grad_norm": 0.5418686866760254, "learning_rate": 4.9941622883829546e-06, "loss": 0.2951, "step": 1712 }, { "epoch": 0.050005838393274174, "grad_norm": 0.6427423357963562, "learning_rate": 4.997081144191477e-06, "loss": 0.2396, "step": 1713 }, { "epoch": 0.05003503035964502, "grad_norm": 0.5070982575416565, "learning_rate": 5e-06, "loss": 0.2497, "step": 1714 }, { "epoch": 0.05006422232601588, "grad_norm": 0.6176062822341919, "learning_rate": 5.002918855808524e-06, "loss": 0.2828, "step": 1715 }, { "epoch": 0.050093414292386736, "grad_norm": 0.8125278353691101, "learning_rate": 5.005837711617046e-06, "loss": 0.3042, "step": 1716 }, { "epoch": 0.05012260625875759, "grad_norm": 0.6439549922943115, "learning_rate": 5.0087565674255704e-06, "loss": 0.2872, "step": 1717 }, { "epoch": 0.05015179822512845, "grad_norm": 0.5400018692016602, "learning_rate": 5.011675423234093e-06, "loss": 0.3211, "step": 1718 }, { "epoch": 0.0501809901914993, "grad_norm": 0.7130987644195557, "learning_rate": 5.014594279042616e-06, "loss": 0.2716, "step": 1719 }, { "epoch": 0.050210182157870153, "grad_norm": 0.7728974223136902, "learning_rate": 5.017513134851139e-06, "loss": 0.2572, "step": 1720 }, { "epoch": 0.05023937412424101, "grad_norm": 0.6883394718170166, "learning_rate": 5.020431990659662e-06, "loss": 0.2579, "step": 1721 }, { "epoch": 0.050268566090611866, "grad_norm": 0.6519016623497009, "learning_rate": 5.023350846468185e-06, "loss": 0.3052, "step": 1722 }, { "epoch": 0.050297758056982715, "grad_norm": 0.7385308742523193, "learning_rate": 5.026269702276708e-06, "loss": 0.2637, "step": 1723 }, { "epoch": 0.05032695002335357, "grad_norm": 0.4762841761112213, "learning_rate": 5.02918855808523e-06, "loss": 0.23, "step": 1724 }, { "epoch": 0.05035614198972443, "grad_norm": 0.5483438372612, "learning_rate": 5.032107413893755e-06, "loss": 0.2455, "step": 1725 }, { "epoch": 0.050385333956095284, "grad_norm": 0.6353110671043396, "learning_rate": 5.035026269702277e-06, "loss": 0.3008, "step": 1726 }, { "epoch": 0.05041452592246614, "grad_norm": 0.6701146364212036, "learning_rate": 5.0379451255108004e-06, "loss": 0.2647, "step": 1727 }, { "epoch": 0.05044371788883699, "grad_norm": 0.4777502119541168, "learning_rate": 5.040863981319323e-06, "loss": 0.2243, "step": 1728 }, { "epoch": 0.050472909855207845, "grad_norm": 0.6259480118751526, "learning_rate": 5.043782837127846e-06, "loss": 0.2576, "step": 1729 }, { "epoch": 0.0505021018215787, "grad_norm": 0.5949993133544922, "learning_rate": 5.046701692936369e-06, "loss": 0.226, "step": 1730 }, { "epoch": 0.05053129378794956, "grad_norm": 0.664248526096344, "learning_rate": 5.049620548744892e-06, "loss": 0.2759, "step": 1731 }, { "epoch": 0.050560485754320414, "grad_norm": 0.7666652798652649, "learning_rate": 5.052539404553416e-06, "loss": 0.3289, "step": 1732 }, { "epoch": 0.05058967772069126, "grad_norm": 0.6488243341445923, "learning_rate": 5.055458260361939e-06, "loss": 0.2786, "step": 1733 }, { "epoch": 0.05061886968706212, "grad_norm": 0.5530169010162354, "learning_rate": 5.058377116170462e-06, "loss": 0.2153, "step": 1734 }, { "epoch": 0.050648061653432976, "grad_norm": 0.5648587346076965, "learning_rate": 5.061295971978985e-06, "loss": 0.219, "step": 1735 }, { "epoch": 0.05067725361980383, "grad_norm": 0.746489405632019, "learning_rate": 5.064214827787508e-06, "loss": 0.2418, "step": 1736 }, { "epoch": 0.05070644558617469, "grad_norm": 1.5016121864318848, "learning_rate": 5.0671336835960305e-06, "loss": 0.2676, "step": 1737 }, { "epoch": 0.05073563755254554, "grad_norm": 0.6152153611183167, "learning_rate": 5.070052539404554e-06, "loss": 0.2789, "step": 1738 }, { "epoch": 0.05076482951891639, "grad_norm": 0.698383092880249, "learning_rate": 5.072971395213076e-06, "loss": 0.2608, "step": 1739 }, { "epoch": 0.05079402148528725, "grad_norm": 0.5275134444236755, "learning_rate": 5.0758902510216005e-06, "loss": 0.2705, "step": 1740 }, { "epoch": 0.050823213451658106, "grad_norm": 0.5500186681747437, "learning_rate": 5.078809106830123e-06, "loss": 0.3143, "step": 1741 }, { "epoch": 0.050852405418028955, "grad_norm": 0.5877560377120972, "learning_rate": 5.081727962638646e-06, "loss": 0.2791, "step": 1742 }, { "epoch": 0.05088159738439981, "grad_norm": 0.7331012487411499, "learning_rate": 5.084646818447169e-06, "loss": 0.2036, "step": 1743 }, { "epoch": 0.05091078935077067, "grad_norm": 0.5050241351127625, "learning_rate": 5.087565674255692e-06, "loss": 0.1993, "step": 1744 }, { "epoch": 0.050939981317141524, "grad_norm": 0.6860399842262268, "learning_rate": 5.090484530064215e-06, "loss": 0.2969, "step": 1745 }, { "epoch": 0.05096917328351238, "grad_norm": 0.561659038066864, "learning_rate": 5.093403385872738e-06, "loss": 0.2847, "step": 1746 }, { "epoch": 0.05099836524988323, "grad_norm": 2.467365264892578, "learning_rate": 5.096322241681262e-06, "loss": 0.2206, "step": 1747 }, { "epoch": 0.051027557216254085, "grad_norm": 0.7069053649902344, "learning_rate": 5.099241097489785e-06, "loss": 0.25, "step": 1748 }, { "epoch": 0.05105674918262494, "grad_norm": 0.6676664352416992, "learning_rate": 5.102159953298308e-06, "loss": 0.2692, "step": 1749 }, { "epoch": 0.0510859411489958, "grad_norm": 0.5832396745681763, "learning_rate": 5.1050788091068305e-06, "loss": 0.2913, "step": 1750 }, { "epoch": 0.051115133115366654, "grad_norm": 1.2647318840026855, "learning_rate": 5.107997664915354e-06, "loss": 0.2954, "step": 1751 }, { "epoch": 0.0511443250817375, "grad_norm": 0.7617232203483582, "learning_rate": 5.110916520723876e-06, "loss": 0.2337, "step": 1752 }, { "epoch": 0.05117351704810836, "grad_norm": 0.6380087733268738, "learning_rate": 5.1138353765324e-06, "loss": 0.2495, "step": 1753 }, { "epoch": 0.051202709014479215, "grad_norm": 0.7826104164123535, "learning_rate": 5.116754232340922e-06, "loss": 0.2656, "step": 1754 }, { "epoch": 0.05123190098085007, "grad_norm": 0.7924278378486633, "learning_rate": 5.119673088149446e-06, "loss": 0.1931, "step": 1755 }, { "epoch": 0.05126109294722093, "grad_norm": 0.6662264466285706, "learning_rate": 5.122591943957969e-06, "loss": 0.2083, "step": 1756 }, { "epoch": 0.05129028491359178, "grad_norm": 0.5349158048629761, "learning_rate": 5.125510799766492e-06, "loss": 0.2022, "step": 1757 }, { "epoch": 0.05131947687996263, "grad_norm": 0.7007285952568054, "learning_rate": 5.128429655575015e-06, "loss": 0.2628, "step": 1758 }, { "epoch": 0.05134866884633349, "grad_norm": 0.6373351812362671, "learning_rate": 5.131348511383538e-06, "loss": 0.2338, "step": 1759 }, { "epoch": 0.051377860812704346, "grad_norm": 0.5251412987709045, "learning_rate": 5.1342673671920605e-06, "loss": 0.2406, "step": 1760 }, { "epoch": 0.0514070527790752, "grad_norm": 0.850844144821167, "learning_rate": 5.137186223000584e-06, "loss": 0.2488, "step": 1761 }, { "epoch": 0.05143624474544605, "grad_norm": 0.6281119585037231, "learning_rate": 5.140105078809106e-06, "loss": 0.2366, "step": 1762 }, { "epoch": 0.05146543671181691, "grad_norm": 0.7899474501609802, "learning_rate": 5.1430239346176305e-06, "loss": 0.2722, "step": 1763 }, { "epoch": 0.051494628678187764, "grad_norm": 0.6406708359718323, "learning_rate": 5.145942790426154e-06, "loss": 0.2406, "step": 1764 }, { "epoch": 0.05152382064455862, "grad_norm": 0.4996689260005951, "learning_rate": 5.148861646234676e-06, "loss": 0.2327, "step": 1765 }, { "epoch": 0.05155301261092947, "grad_norm": 0.5746073722839355, "learning_rate": 5.1517805020432e-06, "loss": 0.278, "step": 1766 }, { "epoch": 0.051582204577300325, "grad_norm": 0.657505989074707, "learning_rate": 5.154699357851722e-06, "loss": 0.2519, "step": 1767 }, { "epoch": 0.05161139654367118, "grad_norm": 0.8012462258338928, "learning_rate": 5.157618213660246e-06, "loss": 0.2431, "step": 1768 }, { "epoch": 0.05164058851004204, "grad_norm": 0.9993813633918762, "learning_rate": 5.160537069468768e-06, "loss": 0.2509, "step": 1769 }, { "epoch": 0.051669780476412894, "grad_norm": 0.8748289942741394, "learning_rate": 5.163455925277292e-06, "loss": 0.2868, "step": 1770 }, { "epoch": 0.05169897244278374, "grad_norm": 0.5081735849380493, "learning_rate": 5.166374781085815e-06, "loss": 0.243, "step": 1771 }, { "epoch": 0.0517281644091546, "grad_norm": 0.5206491947174072, "learning_rate": 5.169293636894338e-06, "loss": 0.2637, "step": 1772 }, { "epoch": 0.051757356375525455, "grad_norm": 0.5863891839981079, "learning_rate": 5.1722124927028605e-06, "loss": 0.2625, "step": 1773 }, { "epoch": 0.05178654834189631, "grad_norm": 0.5922278761863708, "learning_rate": 5.175131348511384e-06, "loss": 0.3134, "step": 1774 }, { "epoch": 0.05181574030826717, "grad_norm": 0.4954566955566406, "learning_rate": 5.178050204319906e-06, "loss": 0.2199, "step": 1775 }, { "epoch": 0.05184493227463802, "grad_norm": 0.6359997987747192, "learning_rate": 5.1809690601284306e-06, "loss": 0.2833, "step": 1776 }, { "epoch": 0.05187412424100887, "grad_norm": 0.6589102149009705, "learning_rate": 5.183887915936952e-06, "loss": 0.2762, "step": 1777 }, { "epoch": 0.05190331620737973, "grad_norm": 0.5763887166976929, "learning_rate": 5.186806771745476e-06, "loss": 0.2582, "step": 1778 }, { "epoch": 0.051932508173750586, "grad_norm": 0.5760633945465088, "learning_rate": 5.189725627554e-06, "loss": 0.2569, "step": 1779 }, { "epoch": 0.05196170014012144, "grad_norm": 0.7719629406929016, "learning_rate": 5.192644483362522e-06, "loss": 0.2639, "step": 1780 }, { "epoch": 0.05199089210649229, "grad_norm": 0.5268126726150513, "learning_rate": 5.1955633391710456e-06, "loss": 0.3349, "step": 1781 }, { "epoch": 0.05202008407286315, "grad_norm": 1.8182446956634521, "learning_rate": 5.198482194979568e-06, "loss": 0.2826, "step": 1782 }, { "epoch": 0.052049276039234, "grad_norm": 0.5405563712120056, "learning_rate": 5.201401050788092e-06, "loss": 0.2619, "step": 1783 }, { "epoch": 0.05207846800560486, "grad_norm": 0.6431841850280762, "learning_rate": 5.204319906596615e-06, "loss": 0.289, "step": 1784 }, { "epoch": 0.05210765997197571, "grad_norm": 0.5507051348686218, "learning_rate": 5.207238762405138e-06, "loss": 0.2312, "step": 1785 }, { "epoch": 0.052136851938346565, "grad_norm": 0.6442083120346069, "learning_rate": 5.2101576182136606e-06, "loss": 0.2739, "step": 1786 }, { "epoch": 0.05216604390471742, "grad_norm": 0.720536470413208, "learning_rate": 5.213076474022184e-06, "loss": 0.2686, "step": 1787 }, { "epoch": 0.05219523587108828, "grad_norm": 0.7358437180519104, "learning_rate": 5.215995329830706e-06, "loss": 0.3088, "step": 1788 }, { "epoch": 0.052224427837459134, "grad_norm": 0.4672977030277252, "learning_rate": 5.21891418563923e-06, "loss": 0.2227, "step": 1789 }, { "epoch": 0.05225361980382998, "grad_norm": 0.8741006255149841, "learning_rate": 5.221833041447752e-06, "loss": 0.263, "step": 1790 }, { "epoch": 0.05228281177020084, "grad_norm": 0.6076851487159729, "learning_rate": 5.224751897256276e-06, "loss": 0.2485, "step": 1791 }, { "epoch": 0.052312003736571695, "grad_norm": 0.9819853901863098, "learning_rate": 5.227670753064799e-06, "loss": 0.2411, "step": 1792 }, { "epoch": 0.05234119570294255, "grad_norm": 0.9697550535202026, "learning_rate": 5.230589608873322e-06, "loss": 0.2741, "step": 1793 }, { "epoch": 0.05237038766931341, "grad_norm": 0.6031134724617004, "learning_rate": 5.233508464681845e-06, "loss": 0.2634, "step": 1794 }, { "epoch": 0.05239957963568426, "grad_norm": 0.5886025428771973, "learning_rate": 5.236427320490368e-06, "loss": 0.3022, "step": 1795 }, { "epoch": 0.05242877160205511, "grad_norm": 0.6898776888847351, "learning_rate": 5.2393461762988914e-06, "loss": 0.2882, "step": 1796 }, { "epoch": 0.05245796356842597, "grad_norm": 0.4715491235256195, "learning_rate": 5.242265032107414e-06, "loss": 0.2111, "step": 1797 }, { "epoch": 0.052487155534796825, "grad_norm": 0.6732965111732483, "learning_rate": 5.245183887915938e-06, "loss": 0.2857, "step": 1798 }, { "epoch": 0.05251634750116768, "grad_norm": 0.9649286866188049, "learning_rate": 5.248102743724461e-06, "loss": 0.2609, "step": 1799 }, { "epoch": 0.05254553946753853, "grad_norm": 0.5946990847587585, "learning_rate": 5.251021599532984e-06, "loss": 0.2736, "step": 1800 }, { "epoch": 0.05257473143390939, "grad_norm": 0.5111039876937866, "learning_rate": 5.2539404553415064e-06, "loss": 0.2395, "step": 1801 }, { "epoch": 0.05260392340028024, "grad_norm": 0.8196814060211182, "learning_rate": 5.25685931115003e-06, "loss": 0.3082, "step": 1802 }, { "epoch": 0.0526331153666511, "grad_norm": 0.8080593943595886, "learning_rate": 5.259778166958552e-06, "loss": 0.2808, "step": 1803 }, { "epoch": 0.052662307333021956, "grad_norm": 0.6206244826316833, "learning_rate": 5.262697022767076e-06, "loss": 0.2654, "step": 1804 }, { "epoch": 0.052691499299392805, "grad_norm": 0.7023046016693115, "learning_rate": 5.265615878575598e-06, "loss": 0.1938, "step": 1805 }, { "epoch": 0.05272069126576366, "grad_norm": 0.6303793787956238, "learning_rate": 5.268534734384122e-06, "loss": 0.2536, "step": 1806 }, { "epoch": 0.05274988323213452, "grad_norm": 0.6122929453849792, "learning_rate": 5.271453590192645e-06, "loss": 0.2762, "step": 1807 }, { "epoch": 0.052779075198505374, "grad_norm": 0.5984117984771729, "learning_rate": 5.274372446001168e-06, "loss": 0.2826, "step": 1808 }, { "epoch": 0.05280826716487622, "grad_norm": 0.5365766286849976, "learning_rate": 5.277291301809691e-06, "loss": 0.2234, "step": 1809 }, { "epoch": 0.05283745913124708, "grad_norm": 0.645540714263916, "learning_rate": 5.280210157618214e-06, "loss": 0.247, "step": 1810 }, { "epoch": 0.052866651097617935, "grad_norm": 0.5763603448867798, "learning_rate": 5.283129013426737e-06, "loss": 0.2252, "step": 1811 }, { "epoch": 0.05289584306398879, "grad_norm": 0.6393614411354065, "learning_rate": 5.28604786923526e-06, "loss": 0.2586, "step": 1812 }, { "epoch": 0.05292503503035965, "grad_norm": 0.6680078506469727, "learning_rate": 5.288966725043784e-06, "loss": 0.2637, "step": 1813 }, { "epoch": 0.0529542269967305, "grad_norm": 0.6357575058937073, "learning_rate": 5.2918855808523065e-06, "loss": 0.2646, "step": 1814 }, { "epoch": 0.05298341896310135, "grad_norm": 0.6340821385383606, "learning_rate": 5.29480443666083e-06, "loss": 0.2674, "step": 1815 }, { "epoch": 0.05301261092947221, "grad_norm": 0.5608285069465637, "learning_rate": 5.297723292469352e-06, "loss": 0.2823, "step": 1816 }, { "epoch": 0.053041802895843065, "grad_norm": 0.5364668369293213, "learning_rate": 5.300642148277876e-06, "loss": 0.2919, "step": 1817 }, { "epoch": 0.05307099486221392, "grad_norm": 0.6915343999862671, "learning_rate": 5.303561004086398e-06, "loss": 0.2688, "step": 1818 }, { "epoch": 0.05310018682858477, "grad_norm": 0.6389735341072083, "learning_rate": 5.3064798598949215e-06, "loss": 0.2723, "step": 1819 }, { "epoch": 0.05312937879495563, "grad_norm": 0.5711616277694702, "learning_rate": 5.309398715703444e-06, "loss": 0.2139, "step": 1820 }, { "epoch": 0.05315857076132648, "grad_norm": 0.6762488484382629, "learning_rate": 5.312317571511968e-06, "loss": 0.2968, "step": 1821 }, { "epoch": 0.05318776272769734, "grad_norm": 0.6126360297203064, "learning_rate": 5.315236427320491e-06, "loss": 0.2013, "step": 1822 }, { "epoch": 0.053216954694068196, "grad_norm": 0.5648536086082458, "learning_rate": 5.318155283129014e-06, "loss": 0.2374, "step": 1823 }, { "epoch": 0.053246146660439045, "grad_norm": 0.5210053324699402, "learning_rate": 5.3210741389375365e-06, "loss": 0.2273, "step": 1824 }, { "epoch": 0.0532753386268099, "grad_norm": 0.6621649861335754, "learning_rate": 5.32399299474606e-06, "loss": 0.2714, "step": 1825 }, { "epoch": 0.05330453059318076, "grad_norm": 0.6644909977912903, "learning_rate": 5.326911850554582e-06, "loss": 0.2458, "step": 1826 }, { "epoch": 0.05333372255955161, "grad_norm": 0.6865484118461609, "learning_rate": 5.329830706363106e-06, "loss": 0.2723, "step": 1827 }, { "epoch": 0.05336291452592246, "grad_norm": 0.7789826989173889, "learning_rate": 5.33274956217163e-06, "loss": 0.2953, "step": 1828 }, { "epoch": 0.05339210649229332, "grad_norm": 0.5154176950454712, "learning_rate": 5.335668417980152e-06, "loss": 0.2342, "step": 1829 }, { "epoch": 0.053421298458664175, "grad_norm": 0.6792320013046265, "learning_rate": 5.338587273788676e-06, "loss": 0.2876, "step": 1830 }, { "epoch": 0.05345049042503503, "grad_norm": 0.5040192604064941, "learning_rate": 5.341506129597198e-06, "loss": 0.2511, "step": 1831 }, { "epoch": 0.05347968239140589, "grad_norm": 1.335506558418274, "learning_rate": 5.3444249854057215e-06, "loss": 0.2431, "step": 1832 }, { "epoch": 0.05350887435777674, "grad_norm": 0.6245937943458557, "learning_rate": 5.347343841214244e-06, "loss": 0.2187, "step": 1833 }, { "epoch": 0.05353806632414759, "grad_norm": 0.5774820446968079, "learning_rate": 5.350262697022768e-06, "loss": 0.2708, "step": 1834 }, { "epoch": 0.05356725829051845, "grad_norm": 0.6404261589050293, "learning_rate": 5.353181552831291e-06, "loss": 0.2517, "step": 1835 }, { "epoch": 0.053596450256889305, "grad_norm": 0.4969339370727539, "learning_rate": 5.356100408639814e-06, "loss": 0.2104, "step": 1836 }, { "epoch": 0.05362564222326016, "grad_norm": 0.488529235124588, "learning_rate": 5.3590192644483365e-06, "loss": 0.2526, "step": 1837 }, { "epoch": 0.05365483418963101, "grad_norm": 0.8886401057243347, "learning_rate": 5.36193812025686e-06, "loss": 0.2938, "step": 1838 }, { "epoch": 0.05368402615600187, "grad_norm": 0.5634939670562744, "learning_rate": 5.364856976065382e-06, "loss": 0.2319, "step": 1839 }, { "epoch": 0.05371321812237272, "grad_norm": 1.174768328666687, "learning_rate": 5.367775831873906e-06, "loss": 0.2584, "step": 1840 }, { "epoch": 0.05374241008874358, "grad_norm": 0.7864181399345398, "learning_rate": 5.370694687682428e-06, "loss": 0.267, "step": 1841 }, { "epoch": 0.053771602055114436, "grad_norm": 1.1186275482177734, "learning_rate": 5.373613543490952e-06, "loss": 0.2596, "step": 1842 }, { "epoch": 0.053800794021485285, "grad_norm": 0.6424497365951538, "learning_rate": 5.376532399299476e-06, "loss": 0.2909, "step": 1843 }, { "epoch": 0.05382998598785614, "grad_norm": 0.7346281409263611, "learning_rate": 5.379451255107998e-06, "loss": 0.2136, "step": 1844 }, { "epoch": 0.053859177954227, "grad_norm": 0.6370604634284973, "learning_rate": 5.3823701109165215e-06, "loss": 0.2682, "step": 1845 }, { "epoch": 0.05388836992059785, "grad_norm": 0.5099170207977295, "learning_rate": 5.385288966725044e-06, "loss": 0.264, "step": 1846 }, { "epoch": 0.05391756188696871, "grad_norm": 0.5212312936782837, "learning_rate": 5.388207822533567e-06, "loss": 0.2294, "step": 1847 }, { "epoch": 0.05394675385333956, "grad_norm": 0.5668215155601501, "learning_rate": 5.39112667834209e-06, "loss": 0.2689, "step": 1848 }, { "epoch": 0.053975945819710415, "grad_norm": 0.5883936285972595, "learning_rate": 5.394045534150614e-06, "loss": 0.2626, "step": 1849 }, { "epoch": 0.05400513778608127, "grad_norm": 1.8228724002838135, "learning_rate": 5.3969643899591365e-06, "loss": 0.3337, "step": 1850 }, { "epoch": 0.05403432975245213, "grad_norm": 0.5257090926170349, "learning_rate": 5.39988324576766e-06, "loss": 0.188, "step": 1851 }, { "epoch": 0.05406352171882298, "grad_norm": 0.6096670031547546, "learning_rate": 5.402802101576182e-06, "loss": 0.2752, "step": 1852 }, { "epoch": 0.05409271368519383, "grad_norm": 0.6975787281990051, "learning_rate": 5.405720957384706e-06, "loss": 0.21, "step": 1853 }, { "epoch": 0.05412190565156469, "grad_norm": 0.666495680809021, "learning_rate": 5.408639813193228e-06, "loss": 0.2554, "step": 1854 }, { "epoch": 0.054151097617935545, "grad_norm": 0.5858743786811829, "learning_rate": 5.4115586690017515e-06, "loss": 0.2956, "step": 1855 }, { "epoch": 0.0541802895843064, "grad_norm": 0.8370732665061951, "learning_rate": 5.414477524810274e-06, "loss": 0.2724, "step": 1856 }, { "epoch": 0.05420948155067725, "grad_norm": 0.5314933061599731, "learning_rate": 5.417396380618798e-06, "loss": 0.2568, "step": 1857 }, { "epoch": 0.05423867351704811, "grad_norm": 0.4981894791126251, "learning_rate": 5.420315236427321e-06, "loss": 0.2503, "step": 1858 }, { "epoch": 0.05426786548341896, "grad_norm": 0.530143678188324, "learning_rate": 5.423234092235844e-06, "loss": 0.2255, "step": 1859 }, { "epoch": 0.05429705744978982, "grad_norm": 1.1312834024429321, "learning_rate": 5.426152948044367e-06, "loss": 0.2115, "step": 1860 }, { "epoch": 0.054326249416160675, "grad_norm": 0.5800625085830688, "learning_rate": 5.42907180385289e-06, "loss": 0.2141, "step": 1861 }, { "epoch": 0.054355441382531525, "grad_norm": 0.5905659198760986, "learning_rate": 5.431990659661413e-06, "loss": 0.2513, "step": 1862 }, { "epoch": 0.05438463334890238, "grad_norm": 0.5580823421478271, "learning_rate": 5.434909515469936e-06, "loss": 0.248, "step": 1863 }, { "epoch": 0.05441382531527324, "grad_norm": 0.5410355925559998, "learning_rate": 5.43782837127846e-06, "loss": 0.2293, "step": 1864 }, { "epoch": 0.05444301728164409, "grad_norm": 0.5800713896751404, "learning_rate": 5.440747227086982e-06, "loss": 0.2101, "step": 1865 }, { "epoch": 0.05447220924801495, "grad_norm": 0.5453385710716248, "learning_rate": 5.443666082895506e-06, "loss": 0.2747, "step": 1866 }, { "epoch": 0.0545014012143858, "grad_norm": 0.6341221332550049, "learning_rate": 5.446584938704028e-06, "loss": 0.2849, "step": 1867 }, { "epoch": 0.054530593180756655, "grad_norm": 0.5300651788711548, "learning_rate": 5.449503794512552e-06, "loss": 0.2386, "step": 1868 }, { "epoch": 0.05455978514712751, "grad_norm": 0.6275367736816406, "learning_rate": 5.452422650321074e-06, "loss": 0.2985, "step": 1869 }, { "epoch": 0.05458897711349837, "grad_norm": 0.5071645379066467, "learning_rate": 5.455341506129597e-06, "loss": 0.2391, "step": 1870 }, { "epoch": 0.05461816907986922, "grad_norm": 0.6706771850585938, "learning_rate": 5.45826036193812e-06, "loss": 0.2219, "step": 1871 }, { "epoch": 0.05464736104624007, "grad_norm": 0.5593487024307251, "learning_rate": 5.461179217746644e-06, "loss": 0.2659, "step": 1872 }, { "epoch": 0.05467655301261093, "grad_norm": 0.5985656976699829, "learning_rate": 5.464098073555167e-06, "loss": 0.2466, "step": 1873 }, { "epoch": 0.054705744978981785, "grad_norm": 2.1823697090148926, "learning_rate": 5.46701692936369e-06, "loss": 0.2331, "step": 1874 }, { "epoch": 0.05473493694535264, "grad_norm": 0.5580748319625854, "learning_rate": 5.469935785172213e-06, "loss": 0.2407, "step": 1875 }, { "epoch": 0.05476412891172349, "grad_norm": 0.5587923526763916, "learning_rate": 5.472854640980736e-06, "loss": 0.2603, "step": 1876 }, { "epoch": 0.05479332087809435, "grad_norm": 0.630600094795227, "learning_rate": 5.475773496789259e-06, "loss": 0.3292, "step": 1877 }, { "epoch": 0.0548225128444652, "grad_norm": 0.4395383894443512, "learning_rate": 5.478692352597782e-06, "loss": 0.241, "step": 1878 }, { "epoch": 0.05485170481083606, "grad_norm": 0.5167782306671143, "learning_rate": 5.481611208406306e-06, "loss": 0.2633, "step": 1879 }, { "epoch": 0.054880896777206915, "grad_norm": 0.708795964717865, "learning_rate": 5.484530064214828e-06, "loss": 0.2603, "step": 1880 }, { "epoch": 0.054910088743577765, "grad_norm": 0.5109078288078308, "learning_rate": 5.487448920023352e-06, "loss": 0.2481, "step": 1881 }, { "epoch": 0.05493928070994862, "grad_norm": 0.6565085649490356, "learning_rate": 5.490367775831874e-06, "loss": 0.2703, "step": 1882 }, { "epoch": 0.05496847267631948, "grad_norm": 0.48096951842308044, "learning_rate": 5.4932866316403974e-06, "loss": 0.249, "step": 1883 }, { "epoch": 0.05499766464269033, "grad_norm": 0.6469887495040894, "learning_rate": 5.49620548744892e-06, "loss": 0.2222, "step": 1884 }, { "epoch": 0.05502685660906119, "grad_norm": 0.5549140572547913, "learning_rate": 5.499124343257444e-06, "loss": 0.2438, "step": 1885 }, { "epoch": 0.05505604857543204, "grad_norm": 0.5552184581756592, "learning_rate": 5.502043199065966e-06, "loss": 0.2526, "step": 1886 }, { "epoch": 0.055085240541802895, "grad_norm": 0.7718731760978699, "learning_rate": 5.50496205487449e-06, "loss": 0.2844, "step": 1887 }, { "epoch": 0.05511443250817375, "grad_norm": 0.48049047589302063, "learning_rate": 5.5078809106830125e-06, "loss": 0.2226, "step": 1888 }, { "epoch": 0.05514362447454461, "grad_norm": 0.5047045946121216, "learning_rate": 5.510799766491536e-06, "loss": 0.2347, "step": 1889 }, { "epoch": 0.05517281644091546, "grad_norm": 0.6013798713684082, "learning_rate": 5.513718622300058e-06, "loss": 0.2834, "step": 1890 }, { "epoch": 0.05520200840728631, "grad_norm": 0.9016333222389221, "learning_rate": 5.516637478108582e-06, "loss": 0.3144, "step": 1891 }, { "epoch": 0.05523120037365717, "grad_norm": 0.8777111768722534, "learning_rate": 5.519556333917106e-06, "loss": 0.248, "step": 1892 }, { "epoch": 0.055260392340028025, "grad_norm": 0.599420964717865, "learning_rate": 5.522475189725628e-06, "loss": 0.2391, "step": 1893 }, { "epoch": 0.05528958430639888, "grad_norm": 0.5439363718032837, "learning_rate": 5.525394045534152e-06, "loss": 0.2447, "step": 1894 }, { "epoch": 0.05531877627276973, "grad_norm": 0.5455084443092346, "learning_rate": 5.528312901342674e-06, "loss": 0.2652, "step": 1895 }, { "epoch": 0.05534796823914059, "grad_norm": 0.5575117468833923, "learning_rate": 5.5312317571511975e-06, "loss": 0.2156, "step": 1896 }, { "epoch": 0.05537716020551144, "grad_norm": 0.5031154751777649, "learning_rate": 5.53415061295972e-06, "loss": 0.2153, "step": 1897 }, { "epoch": 0.0554063521718823, "grad_norm": 0.4774068295955658, "learning_rate": 5.537069468768243e-06, "loss": 0.2285, "step": 1898 }, { "epoch": 0.055435544138253155, "grad_norm": 0.524399995803833, "learning_rate": 5.539988324576766e-06, "loss": 0.2422, "step": 1899 }, { "epoch": 0.055464736104624004, "grad_norm": 0.5625178813934326, "learning_rate": 5.54290718038529e-06, "loss": 0.2508, "step": 1900 }, { "epoch": 0.05549392807099486, "grad_norm": 0.5789896845817566, "learning_rate": 5.5458260361938125e-06, "loss": 0.287, "step": 1901 }, { "epoch": 0.05552312003736572, "grad_norm": 0.8592770099639893, "learning_rate": 5.548744892002336e-06, "loss": 0.3017, "step": 1902 }, { "epoch": 0.05555231200373657, "grad_norm": 0.5745100378990173, "learning_rate": 5.551663747810858e-06, "loss": 0.2404, "step": 1903 }, { "epoch": 0.05558150397010743, "grad_norm": 0.5600934028625488, "learning_rate": 5.554582603619382e-06, "loss": 0.262, "step": 1904 }, { "epoch": 0.05561069593647828, "grad_norm": 0.48319390416145325, "learning_rate": 5.557501459427904e-06, "loss": 0.2734, "step": 1905 }, { "epoch": 0.055639887902849135, "grad_norm": 0.5353744626045227, "learning_rate": 5.5604203152364275e-06, "loss": 0.2575, "step": 1906 }, { "epoch": 0.05566907986921999, "grad_norm": 0.5119473934173584, "learning_rate": 5.563339171044952e-06, "loss": 0.2842, "step": 1907 }, { "epoch": 0.05569827183559085, "grad_norm": 0.5941624641418457, "learning_rate": 5.566258026853474e-06, "loss": 0.2628, "step": 1908 }, { "epoch": 0.0557274638019617, "grad_norm": 0.5459749102592468, "learning_rate": 5.5691768826619975e-06, "loss": 0.2332, "step": 1909 }, { "epoch": 0.05575665576833255, "grad_norm": 0.5451940298080444, "learning_rate": 5.57209573847052e-06, "loss": 0.2945, "step": 1910 }, { "epoch": 0.05578584773470341, "grad_norm": 0.6766027212142944, "learning_rate": 5.575014594279043e-06, "loss": 0.3144, "step": 1911 }, { "epoch": 0.055815039701074265, "grad_norm": 0.47328662872314453, "learning_rate": 5.577933450087566e-06, "loss": 0.2227, "step": 1912 }, { "epoch": 0.05584423166744512, "grad_norm": 0.4889703094959259, "learning_rate": 5.580852305896089e-06, "loss": 0.2448, "step": 1913 }, { "epoch": 0.05587342363381597, "grad_norm": 0.5571102499961853, "learning_rate": 5.583771161704612e-06, "loss": 0.2699, "step": 1914 }, { "epoch": 0.05590261560018683, "grad_norm": 0.7022170424461365, "learning_rate": 5.586690017513136e-06, "loss": 0.2804, "step": 1915 }, { "epoch": 0.05593180756655768, "grad_norm": 0.7046165466308594, "learning_rate": 5.589608873321658e-06, "loss": 0.2997, "step": 1916 }, { "epoch": 0.05596099953292854, "grad_norm": 0.5403425097465515, "learning_rate": 5.592527729130182e-06, "loss": 0.3136, "step": 1917 }, { "epoch": 0.055990191499299395, "grad_norm": 0.8581954836845398, "learning_rate": 5.595446584938704e-06, "loss": 0.2947, "step": 1918 }, { "epoch": 0.056019383465670244, "grad_norm": 0.5716076493263245, "learning_rate": 5.5983654407472275e-06, "loss": 0.2513, "step": 1919 }, { "epoch": 0.0560485754320411, "grad_norm": 0.5331251621246338, "learning_rate": 5.60128429655575e-06, "loss": 0.2856, "step": 1920 }, { "epoch": 0.05607776739841196, "grad_norm": 0.5321516394615173, "learning_rate": 5.604203152364273e-06, "loss": 0.2757, "step": 1921 }, { "epoch": 0.05610695936478281, "grad_norm": 0.562964141368866, "learning_rate": 5.607122008172796e-06, "loss": 0.2951, "step": 1922 }, { "epoch": 0.05613615133115367, "grad_norm": 0.6024882197380066, "learning_rate": 5.61004086398132e-06, "loss": 0.2629, "step": 1923 }, { "epoch": 0.05616534329752452, "grad_norm": 0.7361101508140564, "learning_rate": 5.612959719789843e-06, "loss": 0.2488, "step": 1924 }, { "epoch": 0.056194535263895375, "grad_norm": 0.6444262862205505, "learning_rate": 5.615878575598366e-06, "loss": 0.2666, "step": 1925 }, { "epoch": 0.05622372723026623, "grad_norm": 1.046715259552002, "learning_rate": 5.618797431406889e-06, "loss": 0.2616, "step": 1926 }, { "epoch": 0.05625291919663709, "grad_norm": 0.4684789776802063, "learning_rate": 5.621716287215412e-06, "loss": 0.2312, "step": 1927 }, { "epoch": 0.05628211116300794, "grad_norm": 0.6941896677017212, "learning_rate": 5.624635143023935e-06, "loss": 0.2339, "step": 1928 }, { "epoch": 0.05631130312937879, "grad_norm": 0.6243686676025391, "learning_rate": 5.6275539988324575e-06, "loss": 0.2507, "step": 1929 }, { "epoch": 0.05634049509574965, "grad_norm": 0.798737108707428, "learning_rate": 5.630472854640982e-06, "loss": 0.2416, "step": 1930 }, { "epoch": 0.056369687062120505, "grad_norm": 0.7679521441459656, "learning_rate": 5.633391710449504e-06, "loss": 0.258, "step": 1931 }, { "epoch": 0.05639887902849136, "grad_norm": 0.5255827307701111, "learning_rate": 5.6363105662580276e-06, "loss": 0.1959, "step": 1932 }, { "epoch": 0.05642807099486222, "grad_norm": 0.5437749028205872, "learning_rate": 5.63922942206655e-06, "loss": 0.25, "step": 1933 }, { "epoch": 0.056457262961233066, "grad_norm": 1.8478213548660278, "learning_rate": 5.642148277875073e-06, "loss": 0.2949, "step": 1934 }, { "epoch": 0.05648645492760392, "grad_norm": 0.7685012221336365, "learning_rate": 5.645067133683596e-06, "loss": 0.267, "step": 1935 }, { "epoch": 0.05651564689397478, "grad_norm": 0.7328437566757202, "learning_rate": 5.647985989492119e-06, "loss": 0.2925, "step": 1936 }, { "epoch": 0.056544838860345635, "grad_norm": 0.663772702217102, "learning_rate": 5.650904845300642e-06, "loss": 0.2467, "step": 1937 }, { "epoch": 0.056574030826716484, "grad_norm": 0.6394564509391785, "learning_rate": 5.653823701109166e-06, "loss": 0.3035, "step": 1938 }, { "epoch": 0.05660322279308734, "grad_norm": 0.58306485414505, "learning_rate": 5.656742556917689e-06, "loss": 0.2632, "step": 1939 }, { "epoch": 0.0566324147594582, "grad_norm": 1.1296138763427734, "learning_rate": 5.659661412726212e-06, "loss": 0.237, "step": 1940 }, { "epoch": 0.05666160672582905, "grad_norm": 0.6414692401885986, "learning_rate": 5.662580268534735e-06, "loss": 0.2609, "step": 1941 }, { "epoch": 0.05669079869219991, "grad_norm": 0.8135405778884888, "learning_rate": 5.6654991243432576e-06, "loss": 0.2903, "step": 1942 }, { "epoch": 0.05671999065857076, "grad_norm": 0.7228553891181946, "learning_rate": 5.668417980151782e-06, "loss": 0.2394, "step": 1943 }, { "epoch": 0.056749182624941615, "grad_norm": 1.0017480850219727, "learning_rate": 5.671336835960303e-06, "loss": 0.2673, "step": 1944 }, { "epoch": 0.05677837459131247, "grad_norm": 0.6086404323577881, "learning_rate": 5.674255691768828e-06, "loss": 0.2514, "step": 1945 }, { "epoch": 0.05680756655768333, "grad_norm": 0.7238882184028625, "learning_rate": 5.67717454757735e-06, "loss": 0.2533, "step": 1946 }, { "epoch": 0.05683675852405418, "grad_norm": 0.7038702964782715, "learning_rate": 5.680093403385873e-06, "loss": 0.3075, "step": 1947 }, { "epoch": 0.05686595049042503, "grad_norm": 0.6342423558235168, "learning_rate": 5.683012259194396e-06, "loss": 0.2811, "step": 1948 }, { "epoch": 0.05689514245679589, "grad_norm": 1.022942066192627, "learning_rate": 5.685931115002919e-06, "loss": 0.2581, "step": 1949 }, { "epoch": 0.056924334423166745, "grad_norm": 0.9335459470748901, "learning_rate": 5.688849970811442e-06, "loss": 0.2937, "step": 1950 }, { "epoch": 0.0569535263895376, "grad_norm": 0.6312427520751953, "learning_rate": 5.691768826619966e-06, "loss": 0.2786, "step": 1951 }, { "epoch": 0.05698271835590846, "grad_norm": 0.9869177341461182, "learning_rate": 5.6946876824284884e-06, "loss": 0.2668, "step": 1952 }, { "epoch": 0.057011910322279306, "grad_norm": 0.5496444702148438, "learning_rate": 5.697606538237012e-06, "loss": 0.2293, "step": 1953 }, { "epoch": 0.05704110228865016, "grad_norm": 0.6658657193183899, "learning_rate": 5.700525394045534e-06, "loss": 0.2549, "step": 1954 }, { "epoch": 0.05707029425502102, "grad_norm": 0.8088894486427307, "learning_rate": 5.703444249854058e-06, "loss": 0.2268, "step": 1955 }, { "epoch": 0.057099486221391875, "grad_norm": 1.1986489295959473, "learning_rate": 5.706363105662581e-06, "loss": 0.2518, "step": 1956 }, { "epoch": 0.05712867818776273, "grad_norm": 0.8051032423973083, "learning_rate": 5.7092819614711034e-06, "loss": 0.2728, "step": 1957 }, { "epoch": 0.05715787015413358, "grad_norm": 0.6063074469566345, "learning_rate": 5.712200817279628e-06, "loss": 0.2507, "step": 1958 }, { "epoch": 0.05718706212050444, "grad_norm": 0.5459918975830078, "learning_rate": 5.71511967308815e-06, "loss": 0.2866, "step": 1959 }, { "epoch": 0.05721625408687529, "grad_norm": 0.6102331876754761, "learning_rate": 5.7180385288966735e-06, "loss": 0.2687, "step": 1960 }, { "epoch": 0.05724544605324615, "grad_norm": 0.9413481950759888, "learning_rate": 5.720957384705196e-06, "loss": 0.2068, "step": 1961 }, { "epoch": 0.057274638019617, "grad_norm": 0.7202967405319214, "learning_rate": 5.723876240513719e-06, "loss": 0.2559, "step": 1962 }, { "epoch": 0.057303829985987854, "grad_norm": 0.5556941628456116, "learning_rate": 5.726795096322242e-06, "loss": 0.1892, "step": 1963 }, { "epoch": 0.05733302195235871, "grad_norm": 0.5372432470321655, "learning_rate": 5.729713952130765e-06, "loss": 0.2386, "step": 1964 }, { "epoch": 0.05736221391872957, "grad_norm": 0.6150895357131958, "learning_rate": 5.732632807939288e-06, "loss": 0.2965, "step": 1965 }, { "epoch": 0.05739140588510042, "grad_norm": 0.5859733819961548, "learning_rate": 5.735551663747812e-06, "loss": 0.2631, "step": 1966 }, { "epoch": 0.05742059785147127, "grad_norm": 0.5362849831581116, "learning_rate": 5.738470519556334e-06, "loss": 0.2479, "step": 1967 }, { "epoch": 0.05744978981784213, "grad_norm": 0.8098215460777283, "learning_rate": 5.741389375364858e-06, "loss": 0.2979, "step": 1968 }, { "epoch": 0.057478981784212985, "grad_norm": 0.5639408230781555, "learning_rate": 5.74430823117338e-06, "loss": 0.2858, "step": 1969 }, { "epoch": 0.05750817375058384, "grad_norm": 0.539161741733551, "learning_rate": 5.7472270869819035e-06, "loss": 0.2236, "step": 1970 }, { "epoch": 0.0575373657169547, "grad_norm": 0.5822836756706238, "learning_rate": 5.750145942790427e-06, "loss": 0.2958, "step": 1971 }, { "epoch": 0.057566557683325546, "grad_norm": 1.8791170120239258, "learning_rate": 5.753064798598949e-06, "loss": 0.3026, "step": 1972 }, { "epoch": 0.0575957496496964, "grad_norm": 0.49531587958335876, "learning_rate": 5.7559836544074735e-06, "loss": 0.2233, "step": 1973 }, { "epoch": 0.05762494161606726, "grad_norm": 0.9464961290359497, "learning_rate": 5.758902510215996e-06, "loss": 0.2602, "step": 1974 }, { "epoch": 0.057654133582438115, "grad_norm": 0.5778748989105225, "learning_rate": 5.761821366024519e-06, "loss": 0.2734, "step": 1975 }, { "epoch": 0.05768332554880897, "grad_norm": 0.5136677622795105, "learning_rate": 5.764740221833042e-06, "loss": 0.2421, "step": 1976 }, { "epoch": 0.05771251751517982, "grad_norm": 0.5341424345970154, "learning_rate": 5.767659077641565e-06, "loss": 0.2566, "step": 1977 }, { "epoch": 0.057741709481550677, "grad_norm": 0.74080491065979, "learning_rate": 5.770577933450088e-06, "loss": 0.2242, "step": 1978 }, { "epoch": 0.05777090144792153, "grad_norm": 0.5923429131507874, "learning_rate": 5.773496789258611e-06, "loss": 0.3173, "step": 1979 }, { "epoch": 0.05780009341429239, "grad_norm": 1.2165395021438599, "learning_rate": 5.7764156450671335e-06, "loss": 0.3443, "step": 1980 }, { "epoch": 0.05782928538066324, "grad_norm": 0.767055869102478, "learning_rate": 5.779334500875658e-06, "loss": 0.3248, "step": 1981 }, { "epoch": 0.057858477347034094, "grad_norm": 0.4841633141040802, "learning_rate": 5.78225335668418e-06, "loss": 0.2433, "step": 1982 }, { "epoch": 0.05788766931340495, "grad_norm": 0.6962975263595581, "learning_rate": 5.7851722124927035e-06, "loss": 0.2692, "step": 1983 }, { "epoch": 0.05791686127977581, "grad_norm": 0.7203629612922668, "learning_rate": 5.788091068301226e-06, "loss": 0.2457, "step": 1984 }, { "epoch": 0.05794605324614666, "grad_norm": 0.7202246189117432, "learning_rate": 5.791009924109749e-06, "loss": 0.2329, "step": 1985 }, { "epoch": 0.05797524521251751, "grad_norm": 0.6879859566688538, "learning_rate": 5.793928779918272e-06, "loss": 0.227, "step": 1986 }, { "epoch": 0.05800443717888837, "grad_norm": 0.8954249620437622, "learning_rate": 5.796847635726795e-06, "loss": 0.2707, "step": 1987 }, { "epoch": 0.058033629145259225, "grad_norm": 0.9299938082695007, "learning_rate": 5.799766491535319e-06, "loss": 0.2699, "step": 1988 }, { "epoch": 0.05806282111163008, "grad_norm": 0.6056466698646545, "learning_rate": 5.802685347343842e-06, "loss": 0.263, "step": 1989 }, { "epoch": 0.05809201307800094, "grad_norm": 0.7595606446266174, "learning_rate": 5.805604203152365e-06, "loss": 0.2458, "step": 1990 }, { "epoch": 0.058121205044371786, "grad_norm": 0.5922844409942627, "learning_rate": 5.808523058960888e-06, "loss": 0.2767, "step": 1991 }, { "epoch": 0.05815039701074264, "grad_norm": 0.6462986469268799, "learning_rate": 5.811441914769411e-06, "loss": 0.2705, "step": 1992 }, { "epoch": 0.0581795889771135, "grad_norm": 0.7203077673912048, "learning_rate": 5.8143607705779335e-06, "loss": 0.2811, "step": 1993 }, { "epoch": 0.058208780943484355, "grad_norm": 0.4741477370262146, "learning_rate": 5.817279626386457e-06, "loss": 0.2724, "step": 1994 }, { "epoch": 0.05823797290985521, "grad_norm": 0.7230269312858582, "learning_rate": 5.820198482194979e-06, "loss": 0.3198, "step": 1995 }, { "epoch": 0.05826716487622606, "grad_norm": 0.5599480867385864, "learning_rate": 5.8231173380035035e-06, "loss": 0.2512, "step": 1996 }, { "epoch": 0.058296356842596916, "grad_norm": 0.886141836643219, "learning_rate": 5.826036193812026e-06, "loss": 0.2457, "step": 1997 }, { "epoch": 0.05832554880896777, "grad_norm": 0.47734034061431885, "learning_rate": 5.828955049620549e-06, "loss": 0.2657, "step": 1998 }, { "epoch": 0.05835474077533863, "grad_norm": 0.6332799196243286, "learning_rate": 5.831873905429072e-06, "loss": 0.2471, "step": 1999 }, { "epoch": 0.058383932741709485, "grad_norm": 0.6458041667938232, "learning_rate": 5.834792761237595e-06, "loss": 0.2512, "step": 2000 }, { "epoch": 0.058413124708080334, "grad_norm": 0.68195641040802, "learning_rate": 5.837711617046118e-06, "loss": 0.2549, "step": 2001 }, { "epoch": 0.05844231667445119, "grad_norm": 0.5839535593986511, "learning_rate": 5.840630472854642e-06, "loss": 0.2005, "step": 2002 }, { "epoch": 0.05847150864082205, "grad_norm": 0.5971456170082092, "learning_rate": 5.843549328663165e-06, "loss": 0.2508, "step": 2003 }, { "epoch": 0.0585007006071929, "grad_norm": 0.7567185759544373, "learning_rate": 5.846468184471688e-06, "loss": 0.3063, "step": 2004 }, { "epoch": 0.05852989257356375, "grad_norm": 0.7255865335464478, "learning_rate": 5.849387040280211e-06, "loss": 0.2312, "step": 2005 }, { "epoch": 0.05855908453993461, "grad_norm": 0.6639372706413269, "learning_rate": 5.8523058960887335e-06, "loss": 0.2525, "step": 2006 }, { "epoch": 0.058588276506305464, "grad_norm": 0.6583915948867798, "learning_rate": 5.855224751897257e-06, "loss": 0.2307, "step": 2007 }, { "epoch": 0.05861746847267632, "grad_norm": 0.5438715815544128, "learning_rate": 5.858143607705779e-06, "loss": 0.2231, "step": 2008 }, { "epoch": 0.05864666043904718, "grad_norm": 0.6346970796585083, "learning_rate": 5.8610624635143036e-06, "loss": 0.2488, "step": 2009 }, { "epoch": 0.058675852405418026, "grad_norm": 0.5700522065162659, "learning_rate": 5.863981319322826e-06, "loss": 0.2202, "step": 2010 }, { "epoch": 0.05870504437178888, "grad_norm": 0.7305081486701965, "learning_rate": 5.866900175131349e-06, "loss": 0.2381, "step": 2011 }, { "epoch": 0.05873423633815974, "grad_norm": 0.6915699243545532, "learning_rate": 5.869819030939872e-06, "loss": 0.2782, "step": 2012 }, { "epoch": 0.058763428304530595, "grad_norm": 0.8055484294891357, "learning_rate": 5.872737886748395e-06, "loss": 0.3078, "step": 2013 }, { "epoch": 0.05879262027090145, "grad_norm": 0.5706111788749695, "learning_rate": 5.875656742556918e-06, "loss": 0.2895, "step": 2014 }, { "epoch": 0.0588218122372723, "grad_norm": 0.7317488789558411, "learning_rate": 5.878575598365441e-06, "loss": 0.2405, "step": 2015 }, { "epoch": 0.058851004203643156, "grad_norm": 0.5622870326042175, "learning_rate": 5.8814944541739636e-06, "loss": 0.2841, "step": 2016 }, { "epoch": 0.05888019617001401, "grad_norm": 0.9508391618728638, "learning_rate": 5.884413309982488e-06, "loss": 0.2294, "step": 2017 }, { "epoch": 0.05890938813638487, "grad_norm": 0.6488655805587769, "learning_rate": 5.88733216579101e-06, "loss": 0.2571, "step": 2018 }, { "epoch": 0.058938580102755725, "grad_norm": 0.5632719397544861, "learning_rate": 5.890251021599534e-06, "loss": 0.2443, "step": 2019 }, { "epoch": 0.058967772069126574, "grad_norm": 0.7195238471031189, "learning_rate": 5.893169877408057e-06, "loss": 0.233, "step": 2020 }, { "epoch": 0.05899696403549743, "grad_norm": 0.5380380153656006, "learning_rate": 5.896088733216579e-06, "loss": 0.2589, "step": 2021 }, { "epoch": 0.05902615600186829, "grad_norm": 0.7481213212013245, "learning_rate": 5.899007589025103e-06, "loss": 0.3021, "step": 2022 }, { "epoch": 0.05905534796823914, "grad_norm": 0.5350088477134705, "learning_rate": 5.901926444833625e-06, "loss": 0.2652, "step": 2023 }, { "epoch": 0.05908453993460999, "grad_norm": 0.6690741181373596, "learning_rate": 5.9048453006421494e-06, "loss": 0.2381, "step": 2024 }, { "epoch": 0.05911373190098085, "grad_norm": 0.6031283736228943, "learning_rate": 5.907764156450672e-06, "loss": 0.2529, "step": 2025 }, { "epoch": 0.059142923867351704, "grad_norm": 0.6218852400779724, "learning_rate": 5.910683012259195e-06, "loss": 0.3292, "step": 2026 }, { "epoch": 0.05917211583372256, "grad_norm": 0.7706212401390076, "learning_rate": 5.913601868067718e-06, "loss": 0.3315, "step": 2027 }, { "epoch": 0.05920130780009342, "grad_norm": 0.5870899558067322, "learning_rate": 5.916520723876241e-06, "loss": 0.2273, "step": 2028 }, { "epoch": 0.059230499766464266, "grad_norm": 0.7616695165634155, "learning_rate": 5.919439579684764e-06, "loss": 0.2598, "step": 2029 }, { "epoch": 0.05925969173283512, "grad_norm": 0.5988597273826599, "learning_rate": 5.922358435493287e-06, "loss": 0.2536, "step": 2030 }, { "epoch": 0.05928888369920598, "grad_norm": 1.0531517267227173, "learning_rate": 5.925277291301809e-06, "loss": 0.245, "step": 2031 }, { "epoch": 0.059318075665576835, "grad_norm": 0.6834008097648621, "learning_rate": 5.928196147110334e-06, "loss": 0.2534, "step": 2032 }, { "epoch": 0.05934726763194769, "grad_norm": 0.6872082948684692, "learning_rate": 5.931115002918856e-06, "loss": 0.2623, "step": 2033 }, { "epoch": 0.05937645959831854, "grad_norm": 0.6258441209793091, "learning_rate": 5.9340338587273794e-06, "loss": 0.2641, "step": 2034 }, { "epoch": 0.059405651564689396, "grad_norm": 0.704154372215271, "learning_rate": 5.936952714535903e-06, "loss": 0.2702, "step": 2035 }, { "epoch": 0.05943484353106025, "grad_norm": 0.9117903113365173, "learning_rate": 5.939871570344425e-06, "loss": 0.2527, "step": 2036 }, { "epoch": 0.05946403549743111, "grad_norm": 0.583579421043396, "learning_rate": 5.942790426152949e-06, "loss": 0.3052, "step": 2037 }, { "epoch": 0.059493227463801965, "grad_norm": 0.8194114565849304, "learning_rate": 5.945709281961471e-06, "loss": 0.2989, "step": 2038 }, { "epoch": 0.059522419430172814, "grad_norm": 3.1126255989074707, "learning_rate": 5.948628137769995e-06, "loss": 0.2617, "step": 2039 }, { "epoch": 0.05955161139654367, "grad_norm": 0.584123969078064, "learning_rate": 5.951546993578518e-06, "loss": 0.2533, "step": 2040 }, { "epoch": 0.059580803362914526, "grad_norm": 0.6476612687110901, "learning_rate": 5.954465849387041e-06, "loss": 0.2541, "step": 2041 }, { "epoch": 0.05960999532928538, "grad_norm": 0.7100477814674377, "learning_rate": 5.957384705195564e-06, "loss": 0.2246, "step": 2042 }, { "epoch": 0.05963918729565624, "grad_norm": 0.726457953453064, "learning_rate": 5.960303561004087e-06, "loss": 0.2579, "step": 2043 }, { "epoch": 0.05966837926202709, "grad_norm": 1.1472225189208984, "learning_rate": 5.9632224168126095e-06, "loss": 0.2717, "step": 2044 }, { "epoch": 0.059697571228397944, "grad_norm": 0.6197600364685059, "learning_rate": 5.966141272621133e-06, "loss": 0.2458, "step": 2045 }, { "epoch": 0.0597267631947688, "grad_norm": 0.8766764402389526, "learning_rate": 5.969060128429655e-06, "loss": 0.2731, "step": 2046 }, { "epoch": 0.05975595516113966, "grad_norm": 0.7187486290931702, "learning_rate": 5.9719789842381795e-06, "loss": 0.281, "step": 2047 }, { "epoch": 0.059785147127510506, "grad_norm": 0.9543446898460388, "learning_rate": 5.974897840046702e-06, "loss": 0.2435, "step": 2048 }, { "epoch": 0.05981433909388136, "grad_norm": 0.7823283076286316, "learning_rate": 5.977816695855225e-06, "loss": 0.3204, "step": 2049 }, { "epoch": 0.05984353106025222, "grad_norm": 0.9110220670700073, "learning_rate": 5.980735551663748e-06, "loss": 0.2807, "step": 2050 }, { "epoch": 0.059872723026623074, "grad_norm": 0.7245125770568848, "learning_rate": 5.983654407472271e-06, "loss": 0.2481, "step": 2051 }, { "epoch": 0.05990191499299393, "grad_norm": 0.8913078308105469, "learning_rate": 5.986573263280795e-06, "loss": 0.2625, "step": 2052 }, { "epoch": 0.05993110695936478, "grad_norm": 0.7280236482620239, "learning_rate": 5.989492119089317e-06, "loss": 0.24, "step": 2053 }, { "epoch": 0.059960298925735636, "grad_norm": 0.5922946333885193, "learning_rate": 5.992410974897841e-06, "loss": 0.2223, "step": 2054 }, { "epoch": 0.05998949089210649, "grad_norm": 0.6675946116447449, "learning_rate": 5.995329830706364e-06, "loss": 0.2534, "step": 2055 }, { "epoch": 0.06001868285847735, "grad_norm": 1.2220319509506226, "learning_rate": 5.998248686514887e-06, "loss": 0.2508, "step": 2056 }, { "epoch": 0.060047874824848205, "grad_norm": 0.7590710520744324, "learning_rate": 6.0011675423234095e-06, "loss": 0.2387, "step": 2057 }, { "epoch": 0.060077066791219054, "grad_norm": 0.9545155167579651, "learning_rate": 6.004086398131933e-06, "loss": 0.2439, "step": 2058 }, { "epoch": 0.06010625875758991, "grad_norm": 0.7947294116020203, "learning_rate": 6.007005253940455e-06, "loss": 0.2643, "step": 2059 }, { "epoch": 0.060135450723960766, "grad_norm": 0.7913200855255127, "learning_rate": 6.0099241097489795e-06, "loss": 0.2576, "step": 2060 }, { "epoch": 0.06016464269033162, "grad_norm": 0.7252103090286255, "learning_rate": 6.012842965557501e-06, "loss": 0.2972, "step": 2061 }, { "epoch": 0.06019383465670248, "grad_norm": 0.7910796999931335, "learning_rate": 6.015761821366025e-06, "loss": 0.2863, "step": 2062 }, { "epoch": 0.06022302662307333, "grad_norm": 0.6227996945381165, "learning_rate": 6.018680677174548e-06, "loss": 0.2425, "step": 2063 }, { "epoch": 0.060252218589444184, "grad_norm": 0.9866163730621338, "learning_rate": 6.021599532983071e-06, "loss": 0.235, "step": 2064 }, { "epoch": 0.06028141055581504, "grad_norm": 0.9651665687561035, "learning_rate": 6.024518388791594e-06, "loss": 0.2097, "step": 2065 }, { "epoch": 0.0603106025221859, "grad_norm": 0.6599007844924927, "learning_rate": 6.027437244600117e-06, "loss": 0.2577, "step": 2066 }, { "epoch": 0.060339794488556746, "grad_norm": 0.5892040729522705, "learning_rate": 6.030356100408641e-06, "loss": 0.2592, "step": 2067 }, { "epoch": 0.0603689864549276, "grad_norm": 0.9377457499504089, "learning_rate": 6.033274956217164e-06, "loss": 0.2728, "step": 2068 }, { "epoch": 0.06039817842129846, "grad_norm": 1.2023162841796875, "learning_rate": 6.036193812025687e-06, "loss": 0.2485, "step": 2069 }, { "epoch": 0.060427370387669314, "grad_norm": 0.7132670283317566, "learning_rate": 6.0391126678342095e-06, "loss": 0.2158, "step": 2070 }, { "epoch": 0.06045656235404017, "grad_norm": 0.85966956615448, "learning_rate": 6.042031523642733e-06, "loss": 0.2598, "step": 2071 }, { "epoch": 0.06048575432041102, "grad_norm": 0.6482730507850647, "learning_rate": 6.044950379451255e-06, "loss": 0.2569, "step": 2072 }, { "epoch": 0.060514946286781876, "grad_norm": 1.2557307481765747, "learning_rate": 6.047869235259779e-06, "loss": 0.2884, "step": 2073 }, { "epoch": 0.06054413825315273, "grad_norm": 1.2906118631362915, "learning_rate": 6.050788091068301e-06, "loss": 0.2465, "step": 2074 }, { "epoch": 0.06057333021952359, "grad_norm": 1.1053740978240967, "learning_rate": 6.053706946876825e-06, "loss": 0.2885, "step": 2075 }, { "epoch": 0.060602522185894445, "grad_norm": 1.2956379652023315, "learning_rate": 6.056625802685348e-06, "loss": 0.2684, "step": 2076 }, { "epoch": 0.060631714152265294, "grad_norm": 0.7271356582641602, "learning_rate": 6.059544658493871e-06, "loss": 0.2745, "step": 2077 }, { "epoch": 0.06066090611863615, "grad_norm": 0.7869669795036316, "learning_rate": 6.062463514302394e-06, "loss": 0.2714, "step": 2078 }, { "epoch": 0.060690098085007006, "grad_norm": 0.8148546814918518, "learning_rate": 6.065382370110917e-06, "loss": 0.2518, "step": 2079 }, { "epoch": 0.06071929005137786, "grad_norm": 0.7892294526100159, "learning_rate": 6.0683012259194395e-06, "loss": 0.2976, "step": 2080 }, { "epoch": 0.06074848201774872, "grad_norm": 0.6831726431846619, "learning_rate": 6.071220081727963e-06, "loss": 0.2587, "step": 2081 }, { "epoch": 0.06077767398411957, "grad_norm": 1.1282105445861816, "learning_rate": 6.074138937536485e-06, "loss": 0.2614, "step": 2082 }, { "epoch": 0.060806865950490424, "grad_norm": 0.6638308167457581, "learning_rate": 6.0770577933450096e-06, "loss": 0.2844, "step": 2083 }, { "epoch": 0.06083605791686128, "grad_norm": 0.9430705308914185, "learning_rate": 6.079976649153533e-06, "loss": 0.3151, "step": 2084 }, { "epoch": 0.060865249883232136, "grad_norm": 1.0060368776321411, "learning_rate": 6.082895504962055e-06, "loss": 0.2854, "step": 2085 }, { "epoch": 0.06089444184960299, "grad_norm": 0.6660816669464111, "learning_rate": 6.085814360770579e-06, "loss": 0.2633, "step": 2086 }, { "epoch": 0.06092363381597384, "grad_norm": 0.651229202747345, "learning_rate": 6.088733216579101e-06, "loss": 0.2138, "step": 2087 }, { "epoch": 0.0609528257823447, "grad_norm": 0.6762715578079224, "learning_rate": 6.0916520723876246e-06, "loss": 0.2269, "step": 2088 }, { "epoch": 0.060982017748715554, "grad_norm": 0.8566461205482483, "learning_rate": 6.094570928196147e-06, "loss": 0.2016, "step": 2089 }, { "epoch": 0.06101120971508641, "grad_norm": 0.7760077118873596, "learning_rate": 6.097489784004671e-06, "loss": 0.267, "step": 2090 }, { "epoch": 0.06104040168145726, "grad_norm": 0.5961204171180725, "learning_rate": 6.100408639813194e-06, "loss": 0.2467, "step": 2091 }, { "epoch": 0.061069593647828116, "grad_norm": 0.6639033555984497, "learning_rate": 6.103327495621717e-06, "loss": 0.2507, "step": 2092 }, { "epoch": 0.06109878561419897, "grad_norm": 0.6547286510467529, "learning_rate": 6.1062463514302396e-06, "loss": 0.2264, "step": 2093 }, { "epoch": 0.06112797758056983, "grad_norm": 0.6023759841918945, "learning_rate": 6.109165207238763e-06, "loss": 0.2225, "step": 2094 }, { "epoch": 0.061157169546940685, "grad_norm": 0.9141576290130615, "learning_rate": 6.112084063047285e-06, "loss": 0.252, "step": 2095 }, { "epoch": 0.061186361513311534, "grad_norm": 0.6583338379859924, "learning_rate": 6.115002918855809e-06, "loss": 0.31, "step": 2096 }, { "epoch": 0.06121555347968239, "grad_norm": 0.758660614490509, "learning_rate": 6.117921774664331e-06, "loss": 0.2631, "step": 2097 }, { "epoch": 0.061244745446053246, "grad_norm": 0.8171547651290894, "learning_rate": 6.120840630472855e-06, "loss": 0.2957, "step": 2098 }, { "epoch": 0.0612739374124241, "grad_norm": 0.6338066458702087, "learning_rate": 6.123759486281379e-06, "loss": 0.2602, "step": 2099 }, { "epoch": 0.06130312937879496, "grad_norm": 0.5311875939369202, "learning_rate": 6.126678342089901e-06, "loss": 0.2327, "step": 2100 }, { "epoch": 0.06133232134516581, "grad_norm": 0.5551612377166748, "learning_rate": 6.129597197898425e-06, "loss": 0.2789, "step": 2101 }, { "epoch": 0.061361513311536664, "grad_norm": 0.7231436371803284, "learning_rate": 6.132516053706947e-06, "loss": 0.2501, "step": 2102 }, { "epoch": 0.06139070527790752, "grad_norm": 1.0294541120529175, "learning_rate": 6.1354349095154704e-06, "loss": 0.2367, "step": 2103 }, { "epoch": 0.061419897244278376, "grad_norm": 0.6335651874542236, "learning_rate": 6.138353765323993e-06, "loss": 0.282, "step": 2104 }, { "epoch": 0.06144908921064923, "grad_norm": 0.6077713966369629, "learning_rate": 6.141272621132517e-06, "loss": 0.2678, "step": 2105 }, { "epoch": 0.06147828117702008, "grad_norm": 0.5463460087776184, "learning_rate": 6.14419147694104e-06, "loss": 0.2381, "step": 2106 }, { "epoch": 0.06150747314339094, "grad_norm": 0.6452082395553589, "learning_rate": 6.147110332749563e-06, "loss": 0.2301, "step": 2107 }, { "epoch": 0.061536665109761794, "grad_norm": 0.5244091153144836, "learning_rate": 6.1500291885580854e-06, "loss": 0.2697, "step": 2108 }, { "epoch": 0.06156585707613265, "grad_norm": 0.6050287485122681, "learning_rate": 6.152948044366609e-06, "loss": 0.239, "step": 2109 }, { "epoch": 0.0615950490425035, "grad_norm": 0.5591124296188354, "learning_rate": 6.155866900175131e-06, "loss": 0.2783, "step": 2110 }, { "epoch": 0.061624241008874356, "grad_norm": 0.5787544846534729, "learning_rate": 6.158785755983655e-06, "loss": 0.284, "step": 2111 }, { "epoch": 0.06165343297524521, "grad_norm": 0.5086644291877747, "learning_rate": 6.161704611792177e-06, "loss": 0.2475, "step": 2112 }, { "epoch": 0.06168262494161607, "grad_norm": 0.6214174628257751, "learning_rate": 6.164623467600701e-06, "loss": 0.223, "step": 2113 }, { "epoch": 0.061711816907986924, "grad_norm": 0.5953869819641113, "learning_rate": 6.167542323409224e-06, "loss": 0.322, "step": 2114 }, { "epoch": 0.061741008874357774, "grad_norm": 0.7703368067741394, "learning_rate": 6.170461179217747e-06, "loss": 0.2097, "step": 2115 }, { "epoch": 0.06177020084072863, "grad_norm": 0.7017800807952881, "learning_rate": 6.1733800350262705e-06, "loss": 0.2698, "step": 2116 }, { "epoch": 0.061799392807099486, "grad_norm": 0.5354772210121155, "learning_rate": 6.176298890834793e-06, "loss": 0.2523, "step": 2117 }, { "epoch": 0.06182858477347034, "grad_norm": 0.615504264831543, "learning_rate": 6.179217746643317e-06, "loss": 0.2367, "step": 2118 }, { "epoch": 0.0618577767398412, "grad_norm": 0.5529905557632446, "learning_rate": 6.18213660245184e-06, "loss": 0.209, "step": 2119 }, { "epoch": 0.06188696870621205, "grad_norm": 0.4733959138393402, "learning_rate": 6.185055458260363e-06, "loss": 0.2482, "step": 2120 }, { "epoch": 0.061916160672582904, "grad_norm": 0.5797702670097351, "learning_rate": 6.1879743140688855e-06, "loss": 0.2396, "step": 2121 }, { "epoch": 0.06194535263895376, "grad_norm": 0.646837055683136, "learning_rate": 6.190893169877409e-06, "loss": 0.2931, "step": 2122 }, { "epoch": 0.061974544605324616, "grad_norm": 0.6126973628997803, "learning_rate": 6.193812025685931e-06, "loss": 0.2928, "step": 2123 }, { "epoch": 0.06200373657169547, "grad_norm": 0.5635348558425903, "learning_rate": 6.196730881494455e-06, "loss": 0.288, "step": 2124 }, { "epoch": 0.06203292853806632, "grad_norm": 0.5476264357566833, "learning_rate": 6.199649737302977e-06, "loss": 0.2995, "step": 2125 }, { "epoch": 0.06206212050443718, "grad_norm": 0.5227633714675903, "learning_rate": 6.202568593111501e-06, "loss": 0.2569, "step": 2126 }, { "epoch": 0.062091312470808034, "grad_norm": 0.8786168694496155, "learning_rate": 6.205487448920024e-06, "loss": 0.2567, "step": 2127 }, { "epoch": 0.06212050443717889, "grad_norm": 0.5918306112289429, "learning_rate": 6.208406304728547e-06, "loss": 0.2733, "step": 2128 }, { "epoch": 0.062149696403549747, "grad_norm": 0.4896838068962097, "learning_rate": 6.21132516053707e-06, "loss": 0.2019, "step": 2129 }, { "epoch": 0.062178888369920596, "grad_norm": 0.6733337044715881, "learning_rate": 6.214244016345593e-06, "loss": 0.2866, "step": 2130 }, { "epoch": 0.06220808033629145, "grad_norm": 0.6730101704597473, "learning_rate": 6.217162872154116e-06, "loss": 0.2813, "step": 2131 }, { "epoch": 0.06223727230266231, "grad_norm": 1.0307154655456543, "learning_rate": 6.220081727962639e-06, "loss": 0.3146, "step": 2132 }, { "epoch": 0.062266464269033164, "grad_norm": 1.6171929836273193, "learning_rate": 6.223000583771163e-06, "loss": 0.2553, "step": 2133 }, { "epoch": 0.062295656235404014, "grad_norm": 0.7260025143623352, "learning_rate": 6.2259194395796855e-06, "loss": 0.2332, "step": 2134 }, { "epoch": 0.06232484820177487, "grad_norm": 0.6909418106079102, "learning_rate": 6.228838295388209e-06, "loss": 0.2336, "step": 2135 }, { "epoch": 0.062354040168145726, "grad_norm": 0.7207086086273193, "learning_rate": 6.231757151196731e-06, "loss": 0.2838, "step": 2136 }, { "epoch": 0.06238323213451658, "grad_norm": 0.49841511249542236, "learning_rate": 6.234676007005255e-06, "loss": 0.2778, "step": 2137 }, { "epoch": 0.06241242410088744, "grad_norm": 0.5164035558700562, "learning_rate": 6.237594862813777e-06, "loss": 0.236, "step": 2138 }, { "epoch": 0.06244161606725829, "grad_norm": 0.5938177704811096, "learning_rate": 6.2405137186223005e-06, "loss": 0.2468, "step": 2139 }, { "epoch": 0.062470808033629144, "grad_norm": 0.5009316802024841, "learning_rate": 6.243432574430823e-06, "loss": 0.2259, "step": 2140 }, { "epoch": 0.0625, "grad_norm": 0.5569915175437927, "learning_rate": 6.246351430239347e-06, "loss": 0.2874, "step": 2141 }, { "epoch": 0.06252919196637086, "grad_norm": 0.5421040058135986, "learning_rate": 6.24927028604787e-06, "loss": 0.2566, "step": 2142 }, { "epoch": 0.06255838393274171, "grad_norm": 0.5666452050209045, "learning_rate": 6.252189141856393e-06, "loss": 0.2567, "step": 2143 }, { "epoch": 0.06258757589911257, "grad_norm": 0.674454391002655, "learning_rate": 6.2551079976649155e-06, "loss": 0.3491, "step": 2144 }, { "epoch": 0.06261676786548342, "grad_norm": 0.6321441531181335, "learning_rate": 6.258026853473439e-06, "loss": 0.2663, "step": 2145 }, { "epoch": 0.06264595983185427, "grad_norm": 0.4502045810222626, "learning_rate": 6.260945709281961e-06, "loss": 0.188, "step": 2146 }, { "epoch": 0.06267515179822512, "grad_norm": 0.5300590395927429, "learning_rate": 6.263864565090485e-06, "loss": 0.2697, "step": 2147 }, { "epoch": 0.06270434376459598, "grad_norm": 0.5562275648117065, "learning_rate": 6.266783420899009e-06, "loss": 0.234, "step": 2148 }, { "epoch": 0.06273353573096684, "grad_norm": 0.619989812374115, "learning_rate": 6.269702276707531e-06, "loss": 0.2774, "step": 2149 }, { "epoch": 0.06276272769733769, "grad_norm": 0.5299095511436462, "learning_rate": 6.272621132516055e-06, "loss": 0.2489, "step": 2150 }, { "epoch": 0.06279191966370855, "grad_norm": 0.5106103420257568, "learning_rate": 6.275539988324577e-06, "loss": 0.2397, "step": 2151 }, { "epoch": 0.0628211116300794, "grad_norm": 0.9360166788101196, "learning_rate": 6.2784588441331005e-06, "loss": 0.215, "step": 2152 }, { "epoch": 0.06285030359645026, "grad_norm": 0.8646975755691528, "learning_rate": 6.281377699941623e-06, "loss": 0.301, "step": 2153 }, { "epoch": 0.06287949556282112, "grad_norm": 0.5611501932144165, "learning_rate": 6.284296555750146e-06, "loss": 0.2713, "step": 2154 }, { "epoch": 0.06290868752919197, "grad_norm": 0.5041684508323669, "learning_rate": 6.287215411558669e-06, "loss": 0.2518, "step": 2155 }, { "epoch": 0.06293787949556282, "grad_norm": 0.5584927797317505, "learning_rate": 6.290134267367193e-06, "loss": 0.2418, "step": 2156 }, { "epoch": 0.06296707146193367, "grad_norm": 0.5753991603851318, "learning_rate": 6.2930531231757155e-06, "loss": 0.268, "step": 2157 }, { "epoch": 0.06299626342830453, "grad_norm": 0.5054754614830017, "learning_rate": 6.295971978984239e-06, "loss": 0.259, "step": 2158 }, { "epoch": 0.06302545539467538, "grad_norm": 0.6108953356742859, "learning_rate": 6.298890834792761e-06, "loss": 0.2514, "step": 2159 }, { "epoch": 0.06305464736104624, "grad_norm": 0.6593024134635925, "learning_rate": 6.301809690601285e-06, "loss": 0.268, "step": 2160 }, { "epoch": 0.0630838393274171, "grad_norm": 0.668484091758728, "learning_rate": 6.304728546409807e-06, "loss": 0.2405, "step": 2161 }, { "epoch": 0.06311303129378795, "grad_norm": 0.6430990099906921, "learning_rate": 6.3076474022183305e-06, "loss": 0.2285, "step": 2162 }, { "epoch": 0.06314222326015881, "grad_norm": 0.5607712268829346, "learning_rate": 6.310566258026855e-06, "loss": 0.2361, "step": 2163 }, { "epoch": 0.06317141522652966, "grad_norm": 0.5718329548835754, "learning_rate": 6.313485113835377e-06, "loss": 0.2973, "step": 2164 }, { "epoch": 0.06320060719290051, "grad_norm": 0.7846662402153015, "learning_rate": 6.3164039696439006e-06, "loss": 0.2885, "step": 2165 }, { "epoch": 0.06322979915927136, "grad_norm": 0.8148907423019409, "learning_rate": 6.319322825452423e-06, "loss": 0.2725, "step": 2166 }, { "epoch": 0.06325899112564222, "grad_norm": 0.8106731176376343, "learning_rate": 6.322241681260946e-06, "loss": 0.2805, "step": 2167 }, { "epoch": 0.06328818309201308, "grad_norm": 0.5393297672271729, "learning_rate": 6.325160537069469e-06, "loss": 0.2824, "step": 2168 }, { "epoch": 0.06331737505838393, "grad_norm": 0.5211692452430725, "learning_rate": 6.328079392877993e-06, "loss": 0.2751, "step": 2169 }, { "epoch": 0.06334656702475479, "grad_norm": 0.5398678183555603, "learning_rate": 6.330998248686515e-06, "loss": 0.2439, "step": 2170 }, { "epoch": 0.06337575899112564, "grad_norm": 0.5537934303283691, "learning_rate": 6.333917104495039e-06, "loss": 0.2416, "step": 2171 }, { "epoch": 0.0634049509574965, "grad_norm": 1.026787281036377, "learning_rate": 6.336835960303561e-06, "loss": 0.2307, "step": 2172 }, { "epoch": 0.06343414292386736, "grad_norm": 0.7130348682403564, "learning_rate": 6.339754816112085e-06, "loss": 0.311, "step": 2173 }, { "epoch": 0.06346333489023821, "grad_norm": 0.640302300453186, "learning_rate": 6.342673671920607e-06, "loss": 0.2705, "step": 2174 }, { "epoch": 0.06349252685660906, "grad_norm": 0.5411598086357117, "learning_rate": 6.345592527729131e-06, "loss": 0.2944, "step": 2175 }, { "epoch": 0.06352171882297991, "grad_norm": 0.6987738013267517, "learning_rate": 6.348511383537653e-06, "loss": 0.2931, "step": 2176 }, { "epoch": 0.06355091078935077, "grad_norm": 0.5558454394340515, "learning_rate": 6.351430239346177e-06, "loss": 0.3071, "step": 2177 }, { "epoch": 0.06358010275572162, "grad_norm": 0.5562194585800171, "learning_rate": 6.3543490951547e-06, "loss": 0.2764, "step": 2178 }, { "epoch": 0.06360929472209248, "grad_norm": 0.6247676610946655, "learning_rate": 6.357267950963223e-06, "loss": 0.2925, "step": 2179 }, { "epoch": 0.06363848668846334, "grad_norm": 0.536724865436554, "learning_rate": 6.3601868067717464e-06, "loss": 0.2436, "step": 2180 }, { "epoch": 0.06366767865483419, "grad_norm": 0.5536577701568604, "learning_rate": 6.363105662580269e-06, "loss": 0.2296, "step": 2181 }, { "epoch": 0.06369687062120505, "grad_norm": 0.6610092520713806, "learning_rate": 6.366024518388792e-06, "loss": 0.2507, "step": 2182 }, { "epoch": 0.0637260625875759, "grad_norm": 0.5458065867424011, "learning_rate": 6.368943374197315e-06, "loss": 0.2376, "step": 2183 }, { "epoch": 0.06375525455394676, "grad_norm": 0.5253275036811829, "learning_rate": 6.371862230005839e-06, "loss": 0.2724, "step": 2184 }, { "epoch": 0.0637844465203176, "grad_norm": 0.6275336146354675, "learning_rate": 6.3747810858143614e-06, "loss": 0.2442, "step": 2185 }, { "epoch": 0.06381363848668846, "grad_norm": 0.5723230838775635, "learning_rate": 6.377699941622885e-06, "loss": 0.2935, "step": 2186 }, { "epoch": 0.06384283045305932, "grad_norm": 1.2870160341262817, "learning_rate": 6.380618797431407e-06, "loss": 0.2398, "step": 2187 }, { "epoch": 0.06387202241943017, "grad_norm": 0.49141401052474976, "learning_rate": 6.383537653239931e-06, "loss": 0.2385, "step": 2188 }, { "epoch": 0.06390121438580103, "grad_norm": 0.6346365213394165, "learning_rate": 6.386456509048453e-06, "loss": 0.3081, "step": 2189 }, { "epoch": 0.06393040635217188, "grad_norm": 0.6885244846343994, "learning_rate": 6.3893753648569764e-06, "loss": 0.2543, "step": 2190 }, { "epoch": 0.06395959831854274, "grad_norm": 0.5610390305519104, "learning_rate": 6.392294220665499e-06, "loss": 0.2202, "step": 2191 }, { "epoch": 0.0639887902849136, "grad_norm": 0.7402514815330505, "learning_rate": 6.395213076474023e-06, "loss": 0.2855, "step": 2192 }, { "epoch": 0.06401798225128445, "grad_norm": 0.5109012722969055, "learning_rate": 6.398131932282546e-06, "loss": 0.22, "step": 2193 }, { "epoch": 0.0640471742176553, "grad_norm": 0.8645951151847839, "learning_rate": 6.401050788091069e-06, "loss": 0.2229, "step": 2194 }, { "epoch": 0.06407636618402615, "grad_norm": 0.5340754389762878, "learning_rate": 6.403969643899592e-06, "loss": 0.2544, "step": 2195 }, { "epoch": 0.06410555815039701, "grad_norm": 0.47605660557746887, "learning_rate": 6.406888499708115e-06, "loss": 0.2369, "step": 2196 }, { "epoch": 0.06413475011676786, "grad_norm": 0.4326966404914856, "learning_rate": 6.409807355516638e-06, "loss": 0.2328, "step": 2197 }, { "epoch": 0.06416394208313872, "grad_norm": 0.4819790720939636, "learning_rate": 6.412726211325161e-06, "loss": 0.2866, "step": 2198 }, { "epoch": 0.06419313404950958, "grad_norm": 0.4473424553871155, "learning_rate": 6.415645067133685e-06, "loss": 0.2181, "step": 2199 }, { "epoch": 0.06422232601588043, "grad_norm": 0.4596874713897705, "learning_rate": 6.418563922942207e-06, "loss": 0.2514, "step": 2200 }, { "epoch": 0.06425151798225129, "grad_norm": 0.5722934603691101, "learning_rate": 6.421482778750731e-06, "loss": 0.2681, "step": 2201 }, { "epoch": 0.06428070994862214, "grad_norm": 0.5471236109733582, "learning_rate": 6.424401634559253e-06, "loss": 0.2617, "step": 2202 }, { "epoch": 0.064309901914993, "grad_norm": 0.6719701886177063, "learning_rate": 6.4273204903677765e-06, "loss": 0.2793, "step": 2203 }, { "epoch": 0.06433909388136384, "grad_norm": 0.5164128541946411, "learning_rate": 6.430239346176299e-06, "loss": 0.2502, "step": 2204 }, { "epoch": 0.0643682858477347, "grad_norm": 0.5116222500801086, "learning_rate": 6.433158201984822e-06, "loss": 0.2446, "step": 2205 }, { "epoch": 0.06439747781410556, "grad_norm": 0.5081892609596252, "learning_rate": 6.436077057793345e-06, "loss": 0.2325, "step": 2206 }, { "epoch": 0.06442666978047641, "grad_norm": 0.5137704014778137, "learning_rate": 6.438995913601869e-06, "loss": 0.2248, "step": 2207 }, { "epoch": 0.06445586174684727, "grad_norm": 0.5576698780059814, "learning_rate": 6.4419147694103915e-06, "loss": 0.2603, "step": 2208 }, { "epoch": 0.06448505371321812, "grad_norm": 0.5440888404846191, "learning_rate": 6.444833625218915e-06, "loss": 0.2586, "step": 2209 }, { "epoch": 0.06451424567958898, "grad_norm": 0.5155889987945557, "learning_rate": 6.447752481027437e-06, "loss": 0.2643, "step": 2210 }, { "epoch": 0.06454343764595984, "grad_norm": 0.5719478726387024, "learning_rate": 6.450671336835961e-06, "loss": 0.2935, "step": 2211 }, { "epoch": 0.06457262961233069, "grad_norm": 0.5054373741149902, "learning_rate": 6.453590192644484e-06, "loss": 0.2848, "step": 2212 }, { "epoch": 0.06460182157870153, "grad_norm": 0.44563886523246765, "learning_rate": 6.4565090484530065e-06, "loss": 0.2222, "step": 2213 }, { "epoch": 0.06463101354507239, "grad_norm": 0.4652196168899536, "learning_rate": 6.459427904261531e-06, "loss": 0.2418, "step": 2214 }, { "epoch": 0.06466020551144325, "grad_norm": 0.5143457055091858, "learning_rate": 6.462346760070053e-06, "loss": 0.2687, "step": 2215 }, { "epoch": 0.0646893974778141, "grad_norm": 0.5016909241676331, "learning_rate": 6.4652656158785765e-06, "loss": 0.2296, "step": 2216 }, { "epoch": 0.06471858944418496, "grad_norm": 0.8059966564178467, "learning_rate": 6.468184471687099e-06, "loss": 0.2663, "step": 2217 }, { "epoch": 0.06474778141055582, "grad_norm": 0.4484406113624573, "learning_rate": 6.471103327495622e-06, "loss": 0.2133, "step": 2218 }, { "epoch": 0.06477697337692667, "grad_norm": 0.6046724319458008, "learning_rate": 6.474022183304145e-06, "loss": 0.2927, "step": 2219 }, { "epoch": 0.06480616534329753, "grad_norm": 0.47530433535575867, "learning_rate": 6.476941039112668e-06, "loss": 0.2447, "step": 2220 }, { "epoch": 0.06483535730966838, "grad_norm": 0.48747849464416504, "learning_rate": 6.479859894921191e-06, "loss": 0.2146, "step": 2221 }, { "epoch": 0.06486454927603924, "grad_norm": 0.5498703122138977, "learning_rate": 6.482778750729715e-06, "loss": 0.2789, "step": 2222 }, { "epoch": 0.06489374124241008, "grad_norm": 0.531877875328064, "learning_rate": 6.485697606538237e-06, "loss": 0.2857, "step": 2223 }, { "epoch": 0.06492293320878094, "grad_norm": 0.4854019284248352, "learning_rate": 6.488616462346761e-06, "loss": 0.2224, "step": 2224 }, { "epoch": 0.0649521251751518, "grad_norm": 0.5212834477424622, "learning_rate": 6.491535318155283e-06, "loss": 0.2558, "step": 2225 }, { "epoch": 0.06498131714152265, "grad_norm": 0.8311852216720581, "learning_rate": 6.4944541739638065e-06, "loss": 0.2489, "step": 2226 }, { "epoch": 0.06501050910789351, "grad_norm": 0.6199292540550232, "learning_rate": 6.497373029772331e-06, "loss": 0.2456, "step": 2227 }, { "epoch": 0.06503970107426436, "grad_norm": 0.5401322841644287, "learning_rate": 6.500291885580852e-06, "loss": 0.2599, "step": 2228 }, { "epoch": 0.06506889304063522, "grad_norm": 0.4414534270763397, "learning_rate": 6.5032107413893765e-06, "loss": 0.1975, "step": 2229 }, { "epoch": 0.06509808500700608, "grad_norm": 0.49323147535324097, "learning_rate": 6.506129597197899e-06, "loss": 0.268, "step": 2230 }, { "epoch": 0.06512727697337693, "grad_norm": 0.6041606664657593, "learning_rate": 6.509048453006422e-06, "loss": 0.2252, "step": 2231 }, { "epoch": 0.06515646893974777, "grad_norm": 0.6052529215812683, "learning_rate": 6.511967308814945e-06, "loss": 0.2945, "step": 2232 }, { "epoch": 0.06518566090611863, "grad_norm": 0.48248451948165894, "learning_rate": 6.514886164623468e-06, "loss": 0.2492, "step": 2233 }, { "epoch": 0.06521485287248949, "grad_norm": 0.5001586079597473, "learning_rate": 6.517805020431991e-06, "loss": 0.2848, "step": 2234 }, { "epoch": 0.06524404483886034, "grad_norm": 0.5042662620544434, "learning_rate": 6.520723876240515e-06, "loss": 0.2296, "step": 2235 }, { "epoch": 0.0652732368052312, "grad_norm": 0.7620274424552917, "learning_rate": 6.523642732049037e-06, "loss": 0.2226, "step": 2236 }, { "epoch": 0.06530242877160206, "grad_norm": 0.5674504041671753, "learning_rate": 6.526561587857561e-06, "loss": 0.258, "step": 2237 }, { "epoch": 0.06533162073797291, "grad_norm": 0.5613450407981873, "learning_rate": 6.529480443666083e-06, "loss": 0.2403, "step": 2238 }, { "epoch": 0.06536081270434377, "grad_norm": 0.4893435537815094, "learning_rate": 6.5323992994746066e-06, "loss": 0.2384, "step": 2239 }, { "epoch": 0.06539000467071462, "grad_norm": 0.4915223717689514, "learning_rate": 6.535318155283129e-06, "loss": 0.2448, "step": 2240 }, { "epoch": 0.06541919663708548, "grad_norm": 0.9011174440383911, "learning_rate": 6.538237011091652e-06, "loss": 0.2477, "step": 2241 }, { "epoch": 0.06544838860345632, "grad_norm": 0.48613303899765015, "learning_rate": 6.541155866900175e-06, "loss": 0.2036, "step": 2242 }, { "epoch": 0.06547758056982718, "grad_norm": 0.5322793126106262, "learning_rate": 6.544074722708699e-06, "loss": 0.2707, "step": 2243 }, { "epoch": 0.06550677253619804, "grad_norm": 0.6473625302314758, "learning_rate": 6.546993578517222e-06, "loss": 0.2813, "step": 2244 }, { "epoch": 0.06553596450256889, "grad_norm": 0.44106805324554443, "learning_rate": 6.549912434325745e-06, "loss": 0.2094, "step": 2245 }, { "epoch": 0.06556515646893975, "grad_norm": 0.45465895533561707, "learning_rate": 6.552831290134268e-06, "loss": 0.1886, "step": 2246 }, { "epoch": 0.0655943484353106, "grad_norm": 0.5103902816772461, "learning_rate": 6.555750145942791e-06, "loss": 0.2552, "step": 2247 }, { "epoch": 0.06562354040168146, "grad_norm": 0.6198323965072632, "learning_rate": 6.558669001751314e-06, "loss": 0.2383, "step": 2248 }, { "epoch": 0.06565273236805232, "grad_norm": 0.4734925627708435, "learning_rate": 6.5615878575598366e-06, "loss": 0.2338, "step": 2249 }, { "epoch": 0.06568192433442317, "grad_norm": 0.5208660364151001, "learning_rate": 6.564506713368361e-06, "loss": 0.3042, "step": 2250 }, { "epoch": 0.06571111630079401, "grad_norm": 0.4885018467903137, "learning_rate": 6.567425569176883e-06, "loss": 0.2454, "step": 2251 }, { "epoch": 0.06574030826716487, "grad_norm": 0.5867448449134827, "learning_rate": 6.570344424985407e-06, "loss": 0.3294, "step": 2252 }, { "epoch": 0.06576950023353573, "grad_norm": 0.49338245391845703, "learning_rate": 6.573263280793929e-06, "loss": 0.1967, "step": 2253 }, { "epoch": 0.06579869219990658, "grad_norm": 0.6009416580200195, "learning_rate": 6.576182136602452e-06, "loss": 0.2697, "step": 2254 }, { "epoch": 0.06582788416627744, "grad_norm": 0.554347038269043, "learning_rate": 6.579100992410975e-06, "loss": 0.2333, "step": 2255 }, { "epoch": 0.0658570761326483, "grad_norm": 0.49315932393074036, "learning_rate": 6.582019848219498e-06, "loss": 0.2451, "step": 2256 }, { "epoch": 0.06588626809901915, "grad_norm": 0.47815048694610596, "learning_rate": 6.584938704028021e-06, "loss": 0.2523, "step": 2257 }, { "epoch": 0.06591546006539001, "grad_norm": 0.5308454036712646, "learning_rate": 6.587857559836545e-06, "loss": 0.2778, "step": 2258 }, { "epoch": 0.06594465203176086, "grad_norm": 0.5436801314353943, "learning_rate": 6.590776415645068e-06, "loss": 0.1982, "step": 2259 }, { "epoch": 0.06597384399813172, "grad_norm": 0.6810914874076843, "learning_rate": 6.593695271453591e-06, "loss": 0.231, "step": 2260 }, { "epoch": 0.06600303596450256, "grad_norm": 0.7384486198425293, "learning_rate": 6.596614127262114e-06, "loss": 0.2368, "step": 2261 }, { "epoch": 0.06603222793087342, "grad_norm": 0.48720648884773254, "learning_rate": 6.599532983070637e-06, "loss": 0.2371, "step": 2262 }, { "epoch": 0.06606141989724428, "grad_norm": 0.5092225670814514, "learning_rate": 6.60245183887916e-06, "loss": 0.2392, "step": 2263 }, { "epoch": 0.06609061186361513, "grad_norm": 0.48499348759651184, "learning_rate": 6.6053706946876824e-06, "loss": 0.2185, "step": 2264 }, { "epoch": 0.06611980382998599, "grad_norm": 0.433901846408844, "learning_rate": 6.608289550496207e-06, "loss": 0.1737, "step": 2265 }, { "epoch": 0.06614899579635684, "grad_norm": 1.3667354583740234, "learning_rate": 6.611208406304729e-06, "loss": 0.2413, "step": 2266 }, { "epoch": 0.0661781877627277, "grad_norm": 0.6561352014541626, "learning_rate": 6.6141272621132525e-06, "loss": 0.2453, "step": 2267 }, { "epoch": 0.06620737972909856, "grad_norm": 0.4986129403114319, "learning_rate": 6.617046117921775e-06, "loss": 0.2449, "step": 2268 }, { "epoch": 0.06623657169546941, "grad_norm": 0.543491780757904, "learning_rate": 6.619964973730298e-06, "loss": 0.2467, "step": 2269 }, { "epoch": 0.06626576366184027, "grad_norm": 0.5439419150352478, "learning_rate": 6.622883829538821e-06, "loss": 0.2319, "step": 2270 }, { "epoch": 0.06629495562821111, "grad_norm": 0.5389357209205627, "learning_rate": 6.625802685347344e-06, "loss": 0.2622, "step": 2271 }, { "epoch": 0.06632414759458197, "grad_norm": 0.6407742500305176, "learning_rate": 6.628721541155867e-06, "loss": 0.3111, "step": 2272 }, { "epoch": 0.06635333956095282, "grad_norm": 1.4125992059707642, "learning_rate": 6.631640396964391e-06, "loss": 0.2802, "step": 2273 }, { "epoch": 0.06638253152732368, "grad_norm": 0.7462401986122131, "learning_rate": 6.634559252772913e-06, "loss": 0.2628, "step": 2274 }, { "epoch": 0.06641172349369454, "grad_norm": 0.5145115852355957, "learning_rate": 6.637478108581437e-06, "loss": 0.264, "step": 2275 }, { "epoch": 0.06644091546006539, "grad_norm": 0.5249309539794922, "learning_rate": 6.64039696438996e-06, "loss": 0.279, "step": 2276 }, { "epoch": 0.06647010742643625, "grad_norm": 0.6067543029785156, "learning_rate": 6.6433158201984825e-06, "loss": 0.3021, "step": 2277 }, { "epoch": 0.0664992993928071, "grad_norm": 0.5970820188522339, "learning_rate": 6.646234676007006e-06, "loss": 0.2521, "step": 2278 }, { "epoch": 0.06652849135917796, "grad_norm": 0.5948999524116516, "learning_rate": 6.649153531815528e-06, "loss": 0.2772, "step": 2279 }, { "epoch": 0.0665576833255488, "grad_norm": 0.49904924631118774, "learning_rate": 6.6520723876240525e-06, "loss": 0.2264, "step": 2280 }, { "epoch": 0.06658687529191966, "grad_norm": 0.5712154507637024, "learning_rate": 6.654991243432575e-06, "loss": 0.2699, "step": 2281 }, { "epoch": 0.06661606725829052, "grad_norm": 0.59103924036026, "learning_rate": 6.657910099241098e-06, "loss": 0.2474, "step": 2282 }, { "epoch": 0.06664525922466137, "grad_norm": 0.5192981958389282, "learning_rate": 6.660828955049621e-06, "loss": 0.2555, "step": 2283 }, { "epoch": 0.06667445119103223, "grad_norm": 0.6976529359817505, "learning_rate": 6.663747810858144e-06, "loss": 0.3016, "step": 2284 }, { "epoch": 0.06670364315740308, "grad_norm": 0.4995901584625244, "learning_rate": 6.666666666666667e-06, "loss": 0.2758, "step": 2285 }, { "epoch": 0.06673283512377394, "grad_norm": 2.364893913269043, "learning_rate": 6.669585522475191e-06, "loss": 0.259, "step": 2286 }, { "epoch": 0.0667620270901448, "grad_norm": 0.6730560064315796, "learning_rate": 6.6725043782837125e-06, "loss": 0.3134, "step": 2287 }, { "epoch": 0.06679121905651565, "grad_norm": 0.553006112575531, "learning_rate": 6.675423234092237e-06, "loss": 0.2498, "step": 2288 }, { "epoch": 0.06682041102288651, "grad_norm": 1.2787479162216187, "learning_rate": 6.678342089900759e-06, "loss": 0.2414, "step": 2289 }, { "epoch": 0.06684960298925735, "grad_norm": 0.4681110382080078, "learning_rate": 6.6812609457092825e-06, "loss": 0.2501, "step": 2290 }, { "epoch": 0.0668787949556282, "grad_norm": 0.4668644368648529, "learning_rate": 6.684179801517806e-06, "loss": 0.2483, "step": 2291 }, { "epoch": 0.06690798692199906, "grad_norm": 0.43869903683662415, "learning_rate": 6.687098657326328e-06, "loss": 0.2496, "step": 2292 }, { "epoch": 0.06693717888836992, "grad_norm": 0.6610051989555359, "learning_rate": 6.6900175131348525e-06, "loss": 0.2559, "step": 2293 }, { "epoch": 0.06696637085474078, "grad_norm": 0.805399477481842, "learning_rate": 6.692936368943375e-06, "loss": 0.3008, "step": 2294 }, { "epoch": 0.06699556282111163, "grad_norm": 0.5725287795066833, "learning_rate": 6.695855224751898e-06, "loss": 0.2561, "step": 2295 }, { "epoch": 0.06702475478748249, "grad_norm": 0.5911308526992798, "learning_rate": 6.698774080560421e-06, "loss": 0.2859, "step": 2296 }, { "epoch": 0.06705394675385334, "grad_norm": 3.892345428466797, "learning_rate": 6.701692936368944e-06, "loss": 0.2867, "step": 2297 }, { "epoch": 0.0670831387202242, "grad_norm": 0.4705609381198883, "learning_rate": 6.704611792177467e-06, "loss": 0.2276, "step": 2298 }, { "epoch": 0.06711233068659504, "grad_norm": 0.46880391240119934, "learning_rate": 6.70753064798599e-06, "loss": 0.2138, "step": 2299 }, { "epoch": 0.0671415226529659, "grad_norm": 1.2375144958496094, "learning_rate": 6.7104495037945125e-06, "loss": 0.2655, "step": 2300 }, { "epoch": 0.06717071461933675, "grad_norm": 0.5060647130012512, "learning_rate": 6.713368359603037e-06, "loss": 0.2303, "step": 2301 }, { "epoch": 0.06719990658570761, "grad_norm": 0.7999690175056458, "learning_rate": 6.716287215411559e-06, "loss": 0.2295, "step": 2302 }, { "epoch": 0.06722909855207847, "grad_norm": 0.5124503374099731, "learning_rate": 6.7192060712200825e-06, "loss": 0.258, "step": 2303 }, { "epoch": 0.06725829051844932, "grad_norm": 0.5078410506248474, "learning_rate": 6.722124927028605e-06, "loss": 0.2427, "step": 2304 }, { "epoch": 0.06728748248482018, "grad_norm": 0.4626285135746002, "learning_rate": 6.725043782837128e-06, "loss": 0.242, "step": 2305 }, { "epoch": 0.06731667445119104, "grad_norm": 0.9448854327201843, "learning_rate": 6.727962638645651e-06, "loss": 0.2899, "step": 2306 }, { "epoch": 0.06734586641756189, "grad_norm": 0.5143653154373169, "learning_rate": 6.730881494454174e-06, "loss": 0.2585, "step": 2307 }, { "epoch": 0.06737505838393275, "grad_norm": 0.5006347894668579, "learning_rate": 6.733800350262698e-06, "loss": 0.2366, "step": 2308 }, { "epoch": 0.06740425035030359, "grad_norm": 0.5142946839332581, "learning_rate": 6.736719206071221e-06, "loss": 0.275, "step": 2309 }, { "epoch": 0.06743344231667445, "grad_norm": 0.5821255445480347, "learning_rate": 6.739638061879744e-06, "loss": 0.3087, "step": 2310 }, { "epoch": 0.0674626342830453, "grad_norm": 0.49615025520324707, "learning_rate": 6.742556917688267e-06, "loss": 0.2027, "step": 2311 }, { "epoch": 0.06749182624941616, "grad_norm": 0.5264782905578613, "learning_rate": 6.74547577349679e-06, "loss": 0.229, "step": 2312 }, { "epoch": 0.06752101821578702, "grad_norm": 0.48125654458999634, "learning_rate": 6.7483946293053125e-06, "loss": 0.2703, "step": 2313 }, { "epoch": 0.06755021018215787, "grad_norm": 0.4328177571296692, "learning_rate": 6.751313485113836e-06, "loss": 0.2584, "step": 2314 }, { "epoch": 0.06757940214852873, "grad_norm": 0.5854082107543945, "learning_rate": 6.754232340922358e-06, "loss": 0.2943, "step": 2315 }, { "epoch": 0.06760859411489958, "grad_norm": 0.5251768231391907, "learning_rate": 6.7571511967308826e-06, "loss": 0.2811, "step": 2316 }, { "epoch": 0.06763778608127044, "grad_norm": 0.8154075145721436, "learning_rate": 6.760070052539405e-06, "loss": 0.2503, "step": 2317 }, { "epoch": 0.06766697804764128, "grad_norm": 0.5008277297019958, "learning_rate": 6.762988908347928e-06, "loss": 0.2231, "step": 2318 }, { "epoch": 0.06769617001401214, "grad_norm": 0.5678429007530212, "learning_rate": 6.765907764156451e-06, "loss": 0.2532, "step": 2319 }, { "epoch": 0.067725361980383, "grad_norm": 0.7772154808044434, "learning_rate": 6.768826619964974e-06, "loss": 0.2707, "step": 2320 }, { "epoch": 0.06775455394675385, "grad_norm": 0.48784130811691284, "learning_rate": 6.771745475773497e-06, "loss": 0.2148, "step": 2321 }, { "epoch": 0.06778374591312471, "grad_norm": 0.5393653512001038, "learning_rate": 6.77466433158202e-06, "loss": 0.2385, "step": 2322 }, { "epoch": 0.06781293787949556, "grad_norm": 0.48575010895729065, "learning_rate": 6.777583187390544e-06, "loss": 0.2824, "step": 2323 }, { "epoch": 0.06784212984586642, "grad_norm": 0.5564472079277039, "learning_rate": 6.780502043199067e-06, "loss": 0.2358, "step": 2324 }, { "epoch": 0.06787132181223728, "grad_norm": 0.48235228657722473, "learning_rate": 6.78342089900759e-06, "loss": 0.2064, "step": 2325 }, { "epoch": 0.06790051377860813, "grad_norm": 0.6479169130325317, "learning_rate": 6.786339754816113e-06, "loss": 0.2835, "step": 2326 }, { "epoch": 0.06792970574497899, "grad_norm": 0.6478155851364136, "learning_rate": 6.789258610624636e-06, "loss": 0.2403, "step": 2327 }, { "epoch": 0.06795889771134983, "grad_norm": 0.5565845966339111, "learning_rate": 6.792177466433158e-06, "loss": 0.2933, "step": 2328 }, { "epoch": 0.06798808967772069, "grad_norm": 0.5080294609069824, "learning_rate": 6.795096322241682e-06, "loss": 0.2086, "step": 2329 }, { "epoch": 0.06801728164409154, "grad_norm": 0.5402171611785889, "learning_rate": 6.798015178050204e-06, "loss": 0.2535, "step": 2330 }, { "epoch": 0.0680464736104624, "grad_norm": 0.5110943913459778, "learning_rate": 6.8009340338587284e-06, "loss": 0.2632, "step": 2331 }, { "epoch": 0.06807566557683326, "grad_norm": 0.9465736150741577, "learning_rate": 6.803852889667251e-06, "loss": 0.2514, "step": 2332 }, { "epoch": 0.06810485754320411, "grad_norm": 0.6286576390266418, "learning_rate": 6.806771745475774e-06, "loss": 0.2387, "step": 2333 }, { "epoch": 0.06813404950957497, "grad_norm": 1.05435049533844, "learning_rate": 6.809690601284297e-06, "loss": 0.2466, "step": 2334 }, { "epoch": 0.06816324147594582, "grad_norm": 1.3091200590133667, "learning_rate": 6.81260945709282e-06, "loss": 0.2769, "step": 2335 }, { "epoch": 0.06819243344231668, "grad_norm": 0.49307817220687866, "learning_rate": 6.815528312901343e-06, "loss": 0.2367, "step": 2336 }, { "epoch": 0.06822162540868752, "grad_norm": 0.4812391400337219, "learning_rate": 6.818447168709866e-06, "loss": 0.2584, "step": 2337 }, { "epoch": 0.06825081737505838, "grad_norm": 0.4656430780887604, "learning_rate": 6.8213660245183884e-06, "loss": 0.2441, "step": 2338 }, { "epoch": 0.06828000934142923, "grad_norm": 0.49237197637557983, "learning_rate": 6.824284880326913e-06, "loss": 0.2507, "step": 2339 }, { "epoch": 0.06830920130780009, "grad_norm": 0.5620958209037781, "learning_rate": 6.827203736135436e-06, "loss": 0.2591, "step": 2340 }, { "epoch": 0.06833839327417095, "grad_norm": 0.5308941006660461, "learning_rate": 6.8301225919439584e-06, "loss": 0.2908, "step": 2341 }, { "epoch": 0.0683675852405418, "grad_norm": 0.5360224843025208, "learning_rate": 6.833041447752482e-06, "loss": 0.2151, "step": 2342 }, { "epoch": 0.06839677720691266, "grad_norm": 0.5004537105560303, "learning_rate": 6.835960303561004e-06, "loss": 0.2861, "step": 2343 }, { "epoch": 0.06842596917328352, "grad_norm": 0.6190569400787354, "learning_rate": 6.8388791593695285e-06, "loss": 0.2577, "step": 2344 }, { "epoch": 0.06845516113965437, "grad_norm": 0.5085038542747498, "learning_rate": 6.841798015178051e-06, "loss": 0.2203, "step": 2345 }, { "epoch": 0.06848435310602523, "grad_norm": 0.5671888589859009, "learning_rate": 6.844716870986574e-06, "loss": 0.2338, "step": 2346 }, { "epoch": 0.06851354507239607, "grad_norm": 0.8791368007659912, "learning_rate": 6.847635726795097e-06, "loss": 0.2187, "step": 2347 }, { "epoch": 0.06854273703876693, "grad_norm": 0.7760623097419739, "learning_rate": 6.85055458260362e-06, "loss": 0.3143, "step": 2348 }, { "epoch": 0.06857192900513778, "grad_norm": 0.8093807697296143, "learning_rate": 6.853473438412143e-06, "loss": 0.3105, "step": 2349 }, { "epoch": 0.06860112097150864, "grad_norm": 0.489755779504776, "learning_rate": 6.856392294220666e-06, "loss": 0.2369, "step": 2350 }, { "epoch": 0.0686303129378795, "grad_norm": 0.5475572347640991, "learning_rate": 6.8593111500291885e-06, "loss": 0.2012, "step": 2351 }, { "epoch": 0.06865950490425035, "grad_norm": 0.5928373336791992, "learning_rate": 6.862230005837713e-06, "loss": 0.2524, "step": 2352 }, { "epoch": 0.06868869687062121, "grad_norm": 1.3634895086288452, "learning_rate": 6.865148861646235e-06, "loss": 0.2285, "step": 2353 }, { "epoch": 0.06871788883699206, "grad_norm": 0.5182453393936157, "learning_rate": 6.8680677174547585e-06, "loss": 0.2413, "step": 2354 }, { "epoch": 0.06874708080336292, "grad_norm": 0.43948817253112793, "learning_rate": 6.870986573263282e-06, "loss": 0.2424, "step": 2355 }, { "epoch": 0.06877627276973378, "grad_norm": 1.0458874702453613, "learning_rate": 6.873905429071804e-06, "loss": 0.2399, "step": 2356 }, { "epoch": 0.06880546473610462, "grad_norm": 0.511170506477356, "learning_rate": 6.876824284880328e-06, "loss": 0.2262, "step": 2357 }, { "epoch": 0.06883465670247547, "grad_norm": 0.5763079524040222, "learning_rate": 6.87974314068885e-06, "loss": 0.2713, "step": 2358 }, { "epoch": 0.06886384866884633, "grad_norm": 0.5541249513626099, "learning_rate": 6.882661996497374e-06, "loss": 0.2795, "step": 2359 }, { "epoch": 0.06889304063521719, "grad_norm": 0.5274499654769897, "learning_rate": 6.885580852305897e-06, "loss": 0.2611, "step": 2360 }, { "epoch": 0.06892223260158804, "grad_norm": 0.5415547490119934, "learning_rate": 6.88849970811442e-06, "loss": 0.2753, "step": 2361 }, { "epoch": 0.0689514245679589, "grad_norm": 0.6445484757423401, "learning_rate": 6.891418563922943e-06, "loss": 0.2449, "step": 2362 }, { "epoch": 0.06898061653432976, "grad_norm": 0.9370831847190857, "learning_rate": 6.894337419731466e-06, "loss": 0.2623, "step": 2363 }, { "epoch": 0.06900980850070061, "grad_norm": 0.5697764754295349, "learning_rate": 6.8972562755399885e-06, "loss": 0.2435, "step": 2364 }, { "epoch": 0.06903900046707147, "grad_norm": 0.5060916543006897, "learning_rate": 6.900175131348512e-06, "loss": 0.2415, "step": 2365 }, { "epoch": 0.06906819243344231, "grad_norm": 0.5994442701339722, "learning_rate": 6.903093987157034e-06, "loss": 0.2398, "step": 2366 }, { "epoch": 0.06909738439981317, "grad_norm": 0.9407438039779663, "learning_rate": 6.9060128429655585e-06, "loss": 0.2443, "step": 2367 }, { "epoch": 0.06912657636618402, "grad_norm": 0.5049221515655518, "learning_rate": 6.908931698774081e-06, "loss": 0.2575, "step": 2368 }, { "epoch": 0.06915576833255488, "grad_norm": 0.5457097887992859, "learning_rate": 6.911850554582604e-06, "loss": 0.2518, "step": 2369 }, { "epoch": 0.06918496029892574, "grad_norm": 0.5230110287666321, "learning_rate": 6.914769410391127e-06, "loss": 0.2534, "step": 2370 }, { "epoch": 0.06921415226529659, "grad_norm": 0.6262863874435425, "learning_rate": 6.91768826619965e-06, "loss": 0.2733, "step": 2371 }, { "epoch": 0.06924334423166745, "grad_norm": 0.5858846306800842, "learning_rate": 6.9206071220081735e-06, "loss": 0.2644, "step": 2372 }, { "epoch": 0.0692725361980383, "grad_norm": 0.8532812595367432, "learning_rate": 6.923525977816696e-06, "loss": 0.236, "step": 2373 }, { "epoch": 0.06930172816440916, "grad_norm": 0.9901264905929565, "learning_rate": 6.92644483362522e-06, "loss": 0.2765, "step": 2374 }, { "epoch": 0.06933092013078002, "grad_norm": 0.5654813647270203, "learning_rate": 6.929363689433743e-06, "loss": 0.352, "step": 2375 }, { "epoch": 0.06936011209715086, "grad_norm": 0.5136642456054688, "learning_rate": 6.932282545242266e-06, "loss": 0.2265, "step": 2376 }, { "epoch": 0.06938930406352171, "grad_norm": 0.5614888668060303, "learning_rate": 6.9352014010507885e-06, "loss": 0.2501, "step": 2377 }, { "epoch": 0.06941849602989257, "grad_norm": 0.5110464692115784, "learning_rate": 6.938120256859312e-06, "loss": 0.2776, "step": 2378 }, { "epoch": 0.06944768799626343, "grad_norm": 0.45475247502326965, "learning_rate": 6.941039112667834e-06, "loss": 0.2045, "step": 2379 }, { "epoch": 0.06947687996263428, "grad_norm": 0.5729943513870239, "learning_rate": 6.943957968476358e-06, "loss": 0.2565, "step": 2380 }, { "epoch": 0.06950607192900514, "grad_norm": 0.5069729089736938, "learning_rate": 6.94687682428488e-06, "loss": 0.1926, "step": 2381 }, { "epoch": 0.069535263895376, "grad_norm": 0.5771003365516663, "learning_rate": 6.949795680093404e-06, "loss": 0.2701, "step": 2382 }, { "epoch": 0.06956445586174685, "grad_norm": 0.6339990496635437, "learning_rate": 6.952714535901927e-06, "loss": 0.25, "step": 2383 }, { "epoch": 0.06959364782811771, "grad_norm": 0.5378624200820923, "learning_rate": 6.95563339171045e-06, "loss": 0.2492, "step": 2384 }, { "epoch": 0.06962283979448855, "grad_norm": 0.5175235867500305, "learning_rate": 6.958552247518973e-06, "loss": 0.2466, "step": 2385 }, { "epoch": 0.0696520317608594, "grad_norm": 0.5025953054428101, "learning_rate": 6.961471103327496e-06, "loss": 0.2565, "step": 2386 }, { "epoch": 0.06968122372723026, "grad_norm": 0.6301305294036865, "learning_rate": 6.964389959136019e-06, "loss": 0.2347, "step": 2387 }, { "epoch": 0.06971041569360112, "grad_norm": 0.4861066937446594, "learning_rate": 6.967308814944542e-06, "loss": 0.2768, "step": 2388 }, { "epoch": 0.06973960765997197, "grad_norm": 0.45515167713165283, "learning_rate": 6.970227670753066e-06, "loss": 0.225, "step": 2389 }, { "epoch": 0.06976879962634283, "grad_norm": 0.7996245622634888, "learning_rate": 6.9731465265615886e-06, "loss": 0.2856, "step": 2390 }, { "epoch": 0.06979799159271369, "grad_norm": 0.4356876313686371, "learning_rate": 6.976065382370112e-06, "loss": 0.2679, "step": 2391 }, { "epoch": 0.06982718355908454, "grad_norm": 0.5183781981468201, "learning_rate": 6.978984238178634e-06, "loss": 0.2343, "step": 2392 }, { "epoch": 0.0698563755254554, "grad_norm": 0.6208577752113342, "learning_rate": 6.981903093987158e-06, "loss": 0.267, "step": 2393 }, { "epoch": 0.06988556749182626, "grad_norm": 0.5555099248886108, "learning_rate": 6.98482194979568e-06, "loss": 0.2462, "step": 2394 }, { "epoch": 0.0699147594581971, "grad_norm": 0.45447489619255066, "learning_rate": 6.9877408056042036e-06, "loss": 0.2452, "step": 2395 }, { "epoch": 0.06994395142456795, "grad_norm": 0.5801907777786255, "learning_rate": 6.990659661412726e-06, "loss": 0.2424, "step": 2396 }, { "epoch": 0.06997314339093881, "grad_norm": 0.5392014980316162, "learning_rate": 6.99357851722125e-06, "loss": 0.3077, "step": 2397 }, { "epoch": 0.07000233535730967, "grad_norm": 0.7181844711303711, "learning_rate": 6.996497373029773e-06, "loss": 0.3262, "step": 2398 }, { "epoch": 0.07003152732368052, "grad_norm": 0.5037083029747009, "learning_rate": 6.999416228838296e-06, "loss": 0.3076, "step": 2399 }, { "epoch": 0.07006071929005138, "grad_norm": 0.5886459946632385, "learning_rate": 7.0023350846468186e-06, "loss": 0.324, "step": 2400 }, { "epoch": 0.07008991125642224, "grad_norm": 0.5821066498756409, "learning_rate": 7.005253940455342e-06, "loss": 0.2504, "step": 2401 }, { "epoch": 0.07011910322279309, "grad_norm": 0.5901818871498108, "learning_rate": 7.008172796263864e-06, "loss": 0.2526, "step": 2402 }, { "epoch": 0.07014829518916395, "grad_norm": 0.593940258026123, "learning_rate": 7.011091652072389e-06, "loss": 0.3028, "step": 2403 }, { "epoch": 0.07017748715553479, "grad_norm": 0.6156941056251526, "learning_rate": 7.014010507880912e-06, "loss": 0.3316, "step": 2404 }, { "epoch": 0.07020667912190565, "grad_norm": 0.6238417625427246, "learning_rate": 7.016929363689434e-06, "loss": 0.287, "step": 2405 }, { "epoch": 0.0702358710882765, "grad_norm": 0.541853666305542, "learning_rate": 7.019848219497958e-06, "loss": 0.2465, "step": 2406 }, { "epoch": 0.07026506305464736, "grad_norm": 0.5099737048149109, "learning_rate": 7.02276707530648e-06, "loss": 0.2682, "step": 2407 }, { "epoch": 0.07029425502101821, "grad_norm": 0.6130724549293518, "learning_rate": 7.025685931115004e-06, "loss": 0.2845, "step": 2408 }, { "epoch": 0.07032344698738907, "grad_norm": 1.0275969505310059, "learning_rate": 7.028604786923526e-06, "loss": 0.2438, "step": 2409 }, { "epoch": 0.07035263895375993, "grad_norm": 0.4782167375087738, "learning_rate": 7.03152364273205e-06, "loss": 0.222, "step": 2410 }, { "epoch": 0.07038183092013078, "grad_norm": 0.5040349960327148, "learning_rate": 7.034442498540573e-06, "loss": 0.1967, "step": 2411 }, { "epoch": 0.07041102288650164, "grad_norm": 0.581731915473938, "learning_rate": 7.037361354349096e-06, "loss": 0.3142, "step": 2412 }, { "epoch": 0.0704402148528725, "grad_norm": 0.5839217901229858, "learning_rate": 7.040280210157619e-06, "loss": 0.2702, "step": 2413 }, { "epoch": 0.07046940681924334, "grad_norm": 0.5149084329605103, "learning_rate": 7.043199065966142e-06, "loss": 0.2567, "step": 2414 }, { "epoch": 0.0704985987856142, "grad_norm": 0.6613482236862183, "learning_rate": 7.0461179217746644e-06, "loss": 0.1975, "step": 2415 }, { "epoch": 0.07052779075198505, "grad_norm": 0.6530581712722778, "learning_rate": 7.049036777583188e-06, "loss": 0.2917, "step": 2416 }, { "epoch": 0.0705569827183559, "grad_norm": 0.8263397812843323, "learning_rate": 7.05195563339171e-06, "loss": 0.3064, "step": 2417 }, { "epoch": 0.07058617468472676, "grad_norm": 0.5355846881866455, "learning_rate": 7.0548744892002345e-06, "loss": 0.2713, "step": 2418 }, { "epoch": 0.07061536665109762, "grad_norm": 0.615761935710907, "learning_rate": 7.057793345008758e-06, "loss": 0.2248, "step": 2419 }, { "epoch": 0.07064455861746848, "grad_norm": 0.7306650280952454, "learning_rate": 7.06071220081728e-06, "loss": 0.2518, "step": 2420 }, { "epoch": 0.07067375058383933, "grad_norm": 0.45290082693099976, "learning_rate": 7.063631056625804e-06, "loss": 0.2345, "step": 2421 }, { "epoch": 0.07070294255021019, "grad_norm": 0.5098000168800354, "learning_rate": 7.066549912434326e-06, "loss": 0.2233, "step": 2422 }, { "epoch": 0.07073213451658103, "grad_norm": 0.6320041418075562, "learning_rate": 7.0694687682428495e-06, "loss": 0.3127, "step": 2423 }, { "epoch": 0.07076132648295189, "grad_norm": 0.7079439759254456, "learning_rate": 7.072387624051372e-06, "loss": 0.2711, "step": 2424 }, { "epoch": 0.07079051844932274, "grad_norm": 0.6704856753349304, "learning_rate": 7.075306479859896e-06, "loss": 0.2671, "step": 2425 }, { "epoch": 0.0708197104156936, "grad_norm": 0.5792983770370483, "learning_rate": 7.078225335668419e-06, "loss": 0.3205, "step": 2426 }, { "epoch": 0.07084890238206445, "grad_norm": 1.8867154121398926, "learning_rate": 7.081144191476942e-06, "loss": 0.2382, "step": 2427 }, { "epoch": 0.07087809434843531, "grad_norm": 0.6335678100585938, "learning_rate": 7.0840630472854645e-06, "loss": 0.2541, "step": 2428 }, { "epoch": 0.07090728631480617, "grad_norm": 0.861546516418457, "learning_rate": 7.086981903093988e-06, "loss": 0.244, "step": 2429 }, { "epoch": 0.07093647828117702, "grad_norm": 0.4715818762779236, "learning_rate": 7.08990075890251e-06, "loss": 0.2411, "step": 2430 }, { "epoch": 0.07096567024754788, "grad_norm": 0.5429691076278687, "learning_rate": 7.092819614711034e-06, "loss": 0.2576, "step": 2431 }, { "epoch": 0.07099486221391874, "grad_norm": 0.6151676774024963, "learning_rate": 7.095738470519556e-06, "loss": 0.2299, "step": 2432 }, { "epoch": 0.07102405418028958, "grad_norm": 0.46448227763175964, "learning_rate": 7.09865732632808e-06, "loss": 0.2396, "step": 2433 }, { "epoch": 0.07105324614666043, "grad_norm": 0.6233653426170349, "learning_rate": 7.101576182136603e-06, "loss": 0.2788, "step": 2434 }, { "epoch": 0.07108243811303129, "grad_norm": 0.9955313801765442, "learning_rate": 7.104495037945126e-06, "loss": 0.2366, "step": 2435 }, { "epoch": 0.07111163007940215, "grad_norm": 0.4455244243144989, "learning_rate": 7.1074138937536495e-06, "loss": 0.2453, "step": 2436 }, { "epoch": 0.071140822045773, "grad_norm": 0.5368526577949524, "learning_rate": 7.110332749562172e-06, "loss": 0.2422, "step": 2437 }, { "epoch": 0.07117001401214386, "grad_norm": 0.44756919145584106, "learning_rate": 7.113251605370695e-06, "loss": 0.2439, "step": 2438 }, { "epoch": 0.07119920597851472, "grad_norm": 0.5269371867179871, "learning_rate": 7.116170461179218e-06, "loss": 0.2609, "step": 2439 }, { "epoch": 0.07122839794488557, "grad_norm": 0.6077560782432556, "learning_rate": 7.119089316987742e-06, "loss": 0.2777, "step": 2440 }, { "epoch": 0.07125758991125643, "grad_norm": 0.43821632862091064, "learning_rate": 7.1220081727962645e-06, "loss": 0.2351, "step": 2441 }, { "epoch": 0.07128678187762728, "grad_norm": 0.7391597032546997, "learning_rate": 7.124927028604788e-06, "loss": 0.2628, "step": 2442 }, { "epoch": 0.07131597384399813, "grad_norm": 0.5529353618621826, "learning_rate": 7.12784588441331e-06, "loss": 0.2398, "step": 2443 }, { "epoch": 0.07134516581036898, "grad_norm": 0.5287386775016785, "learning_rate": 7.130764740221834e-06, "loss": 0.3291, "step": 2444 }, { "epoch": 0.07137435777673984, "grad_norm": 0.513247549533844, "learning_rate": 7.133683596030356e-06, "loss": 0.2713, "step": 2445 }, { "epoch": 0.0714035497431107, "grad_norm": 0.4420693814754486, "learning_rate": 7.1366024518388795e-06, "loss": 0.2626, "step": 2446 }, { "epoch": 0.07143274170948155, "grad_norm": 0.48185020685195923, "learning_rate": 7.139521307647402e-06, "loss": 0.254, "step": 2447 }, { "epoch": 0.07146193367585241, "grad_norm": 1.899137020111084, "learning_rate": 7.142440163455926e-06, "loss": 0.2868, "step": 2448 }, { "epoch": 0.07149112564222326, "grad_norm": 0.596165120601654, "learning_rate": 7.145359019264449e-06, "loss": 0.3118, "step": 2449 }, { "epoch": 0.07152031760859412, "grad_norm": 0.5958448052406311, "learning_rate": 7.148277875072972e-06, "loss": 0.3056, "step": 2450 }, { "epoch": 0.07154950957496498, "grad_norm": 0.543880820274353, "learning_rate": 7.151196730881495e-06, "loss": 0.3003, "step": 2451 }, { "epoch": 0.07157870154133582, "grad_norm": 0.49494707584381104, "learning_rate": 7.154115586690018e-06, "loss": 0.2491, "step": 2452 }, { "epoch": 0.07160789350770667, "grad_norm": 0.6799988150596619, "learning_rate": 7.157034442498542e-06, "loss": 0.2833, "step": 2453 }, { "epoch": 0.07163708547407753, "grad_norm": 0.46623364090919495, "learning_rate": 7.159953298307064e-06, "loss": 0.2611, "step": 2454 }, { "epoch": 0.07166627744044839, "grad_norm": 0.4658339321613312, "learning_rate": 7.162872154115588e-06, "loss": 0.2477, "step": 2455 }, { "epoch": 0.07169546940681924, "grad_norm": 0.598722517490387, "learning_rate": 7.16579100992411e-06, "loss": 0.3052, "step": 2456 }, { "epoch": 0.0717246613731901, "grad_norm": 0.46979793906211853, "learning_rate": 7.168709865732634e-06, "loss": 0.2442, "step": 2457 }, { "epoch": 0.07175385333956096, "grad_norm": 0.47028717398643494, "learning_rate": 7.171628721541156e-06, "loss": 0.2674, "step": 2458 }, { "epoch": 0.07178304530593181, "grad_norm": 0.4590519666671753, "learning_rate": 7.1745475773496795e-06, "loss": 0.2686, "step": 2459 }, { "epoch": 0.07181223727230267, "grad_norm": 0.4231121838092804, "learning_rate": 7.177466433158202e-06, "loss": 0.2354, "step": 2460 }, { "epoch": 0.07184142923867352, "grad_norm": 0.5177081823348999, "learning_rate": 7.180385288966726e-06, "loss": 0.2394, "step": 2461 }, { "epoch": 0.07187062120504437, "grad_norm": 0.4538494944572449, "learning_rate": 7.183304144775249e-06, "loss": 0.2319, "step": 2462 }, { "epoch": 0.07189981317141522, "grad_norm": 0.4529072344303131, "learning_rate": 7.186223000583772e-06, "loss": 0.2225, "step": 2463 }, { "epoch": 0.07192900513778608, "grad_norm": 0.4407099783420563, "learning_rate": 7.1891418563922945e-06, "loss": 0.2803, "step": 2464 }, { "epoch": 0.07195819710415693, "grad_norm": 0.5063228607177734, "learning_rate": 7.192060712200818e-06, "loss": 0.3, "step": 2465 }, { "epoch": 0.07198738907052779, "grad_norm": 0.4850766360759735, "learning_rate": 7.19497956800934e-06, "loss": 0.2147, "step": 2466 }, { "epoch": 0.07201658103689865, "grad_norm": 0.5993773341178894, "learning_rate": 7.197898423817864e-06, "loss": 0.2463, "step": 2467 }, { "epoch": 0.0720457730032695, "grad_norm": 0.4305115044116974, "learning_rate": 7.200817279626388e-06, "loss": 0.2172, "step": 2468 }, { "epoch": 0.07207496496964036, "grad_norm": 0.5438814163208008, "learning_rate": 7.20373613543491e-06, "loss": 0.2752, "step": 2469 }, { "epoch": 0.07210415693601122, "grad_norm": 0.49853265285491943, "learning_rate": 7.206654991243434e-06, "loss": 0.2639, "step": 2470 }, { "epoch": 0.07213334890238206, "grad_norm": 0.5566458106040955, "learning_rate": 7.209573847051956e-06, "loss": 0.2378, "step": 2471 }, { "epoch": 0.07216254086875291, "grad_norm": 0.5138834118843079, "learning_rate": 7.2124927028604796e-06, "loss": 0.3187, "step": 2472 }, { "epoch": 0.07219173283512377, "grad_norm": 0.49033671617507935, "learning_rate": 7.215411558669002e-06, "loss": 0.2788, "step": 2473 }, { "epoch": 0.07222092480149463, "grad_norm": 0.4717971682548523, "learning_rate": 7.218330414477525e-06, "loss": 0.2585, "step": 2474 }, { "epoch": 0.07225011676786548, "grad_norm": 0.5399343967437744, "learning_rate": 7.221249270286048e-06, "loss": 0.2676, "step": 2475 }, { "epoch": 0.07227930873423634, "grad_norm": 0.7027338147163391, "learning_rate": 7.224168126094572e-06, "loss": 0.2436, "step": 2476 }, { "epoch": 0.0723085007006072, "grad_norm": 0.39864203333854675, "learning_rate": 7.2270869819030946e-06, "loss": 0.2194, "step": 2477 }, { "epoch": 0.07233769266697805, "grad_norm": 0.5495070815086365, "learning_rate": 7.230005837711618e-06, "loss": 0.2906, "step": 2478 }, { "epoch": 0.07236688463334891, "grad_norm": 0.48919451236724854, "learning_rate": 7.23292469352014e-06, "loss": 0.2535, "step": 2479 }, { "epoch": 0.07239607659971976, "grad_norm": 1.1473751068115234, "learning_rate": 7.235843549328664e-06, "loss": 0.3123, "step": 2480 }, { "epoch": 0.0724252685660906, "grad_norm": 0.5037445425987244, "learning_rate": 7.238762405137186e-06, "loss": 0.2516, "step": 2481 }, { "epoch": 0.07245446053246146, "grad_norm": 0.4810103476047516, "learning_rate": 7.24168126094571e-06, "loss": 0.2419, "step": 2482 }, { "epoch": 0.07248365249883232, "grad_norm": 0.45919305086135864, "learning_rate": 7.244600116754234e-06, "loss": 0.3141, "step": 2483 }, { "epoch": 0.07251284446520317, "grad_norm": 0.49156203866004944, "learning_rate": 7.247518972562756e-06, "loss": 0.3116, "step": 2484 }, { "epoch": 0.07254203643157403, "grad_norm": 0.4972766041755676, "learning_rate": 7.25043782837128e-06, "loss": 0.2732, "step": 2485 }, { "epoch": 0.07257122839794489, "grad_norm": 0.5410658121109009, "learning_rate": 7.253356684179802e-06, "loss": 0.2746, "step": 2486 }, { "epoch": 0.07260042036431574, "grad_norm": 0.4954022467136383, "learning_rate": 7.2562755399883254e-06, "loss": 0.2653, "step": 2487 }, { "epoch": 0.0726296123306866, "grad_norm": 0.6173317432403564, "learning_rate": 7.259194395796848e-06, "loss": 0.3164, "step": 2488 }, { "epoch": 0.07265880429705746, "grad_norm": 1.7486011981964111, "learning_rate": 7.262113251605371e-06, "loss": 0.2682, "step": 2489 }, { "epoch": 0.0726879962634283, "grad_norm": 0.5388084650039673, "learning_rate": 7.265032107413894e-06, "loss": 0.2898, "step": 2490 }, { "epoch": 0.07271718822979915, "grad_norm": 0.6851823925971985, "learning_rate": 7.267950963222418e-06, "loss": 0.259, "step": 2491 }, { "epoch": 0.07274638019617001, "grad_norm": 0.5117090940475464, "learning_rate": 7.2708698190309404e-06, "loss": 0.274, "step": 2492 }, { "epoch": 0.07277557216254087, "grad_norm": 0.4677899181842804, "learning_rate": 7.273788674839464e-06, "loss": 0.2892, "step": 2493 }, { "epoch": 0.07280476412891172, "grad_norm": 0.46300405263900757, "learning_rate": 7.276707530647986e-06, "loss": 0.2712, "step": 2494 }, { "epoch": 0.07283395609528258, "grad_norm": 0.44554853439331055, "learning_rate": 7.27962638645651e-06, "loss": 0.257, "step": 2495 }, { "epoch": 0.07286314806165343, "grad_norm": 0.4602885842323303, "learning_rate": 7.282545242265032e-06, "loss": 0.2844, "step": 2496 }, { "epoch": 0.07289234002802429, "grad_norm": 0.43682512640953064, "learning_rate": 7.2854640980735554e-06, "loss": 0.2239, "step": 2497 }, { "epoch": 0.07292153199439515, "grad_norm": 0.48351773619651794, "learning_rate": 7.288382953882078e-06, "loss": 0.2167, "step": 2498 }, { "epoch": 0.072950723960766, "grad_norm": 0.7690754532814026, "learning_rate": 7.291301809690602e-06, "loss": 0.2682, "step": 2499 }, { "epoch": 0.07297991592713685, "grad_norm": 0.5546303987503052, "learning_rate": 7.2942206654991255e-06, "loss": 0.241, "step": 2500 }, { "epoch": 0.0730091078935077, "grad_norm": 0.4617074131965637, "learning_rate": 7.297139521307648e-06, "loss": 0.298, "step": 2501 }, { "epoch": 0.07303829985987856, "grad_norm": 0.48923051357269287, "learning_rate": 7.300058377116171e-06, "loss": 0.261, "step": 2502 }, { "epoch": 0.07306749182624941, "grad_norm": 0.46128806471824646, "learning_rate": 7.302977232924694e-06, "loss": 0.2464, "step": 2503 }, { "epoch": 0.07309668379262027, "grad_norm": 0.5367842316627502, "learning_rate": 7.305896088733217e-06, "loss": 0.2867, "step": 2504 }, { "epoch": 0.07312587575899113, "grad_norm": 0.6005479097366333, "learning_rate": 7.30881494454174e-06, "loss": 0.2547, "step": 2505 }, { "epoch": 0.07315506772536198, "grad_norm": 0.43913576006889343, "learning_rate": 7.311733800350264e-06, "loss": 0.2167, "step": 2506 }, { "epoch": 0.07318425969173284, "grad_norm": 0.5823619365692139, "learning_rate": 7.314652656158786e-06, "loss": 0.2616, "step": 2507 }, { "epoch": 0.0732134516581037, "grad_norm": 0.4694158732891083, "learning_rate": 7.31757151196731e-06, "loss": 0.2558, "step": 2508 }, { "epoch": 0.07324264362447454, "grad_norm": 0.48267316818237305, "learning_rate": 7.320490367775832e-06, "loss": 0.2513, "step": 2509 }, { "epoch": 0.0732718355908454, "grad_norm": 0.4602193832397461, "learning_rate": 7.3234092235843555e-06, "loss": 0.2758, "step": 2510 }, { "epoch": 0.07330102755721625, "grad_norm": 0.47570517659187317, "learning_rate": 7.326328079392878e-06, "loss": 0.2772, "step": 2511 }, { "epoch": 0.0733302195235871, "grad_norm": 0.6928088068962097, "learning_rate": 7.329246935201401e-06, "loss": 0.2352, "step": 2512 }, { "epoch": 0.07335941148995796, "grad_norm": 1.0287894010543823, "learning_rate": 7.332165791009924e-06, "loss": 0.2868, "step": 2513 }, { "epoch": 0.07338860345632882, "grad_norm": 0.562940776348114, "learning_rate": 7.335084646818448e-06, "loss": 0.3029, "step": 2514 }, { "epoch": 0.07341779542269967, "grad_norm": 0.5053021311759949, "learning_rate": 7.338003502626971e-06, "loss": 0.2588, "step": 2515 }, { "epoch": 0.07344698738907053, "grad_norm": 0.569093644618988, "learning_rate": 7.340922358435494e-06, "loss": 0.283, "step": 2516 }, { "epoch": 0.07347617935544139, "grad_norm": 0.493630975484848, "learning_rate": 7.343841214244017e-06, "loss": 0.2501, "step": 2517 }, { "epoch": 0.07350537132181224, "grad_norm": 0.47820261120796204, "learning_rate": 7.34676007005254e-06, "loss": 0.2615, "step": 2518 }, { "epoch": 0.07353456328818309, "grad_norm": 0.4958495795726776, "learning_rate": 7.349678925861064e-06, "loss": 0.2637, "step": 2519 }, { "epoch": 0.07356375525455394, "grad_norm": 0.44830554723739624, "learning_rate": 7.352597781669586e-06, "loss": 0.2409, "step": 2520 }, { "epoch": 0.0735929472209248, "grad_norm": 0.43386051058769226, "learning_rate": 7.35551663747811e-06, "loss": 0.235, "step": 2521 }, { "epoch": 0.07362213918729565, "grad_norm": 0.756689190864563, "learning_rate": 7.358435493286632e-06, "loss": 0.3478, "step": 2522 }, { "epoch": 0.07365133115366651, "grad_norm": 0.572430431842804, "learning_rate": 7.3613543490951555e-06, "loss": 0.252, "step": 2523 }, { "epoch": 0.07368052312003737, "grad_norm": 0.46195971965789795, "learning_rate": 7.364273204903678e-06, "loss": 0.2266, "step": 2524 }, { "epoch": 0.07370971508640822, "grad_norm": 2.286574125289917, "learning_rate": 7.367192060712201e-06, "loss": 0.2749, "step": 2525 }, { "epoch": 0.07373890705277908, "grad_norm": 0.619342565536499, "learning_rate": 7.370110916520724e-06, "loss": 0.2509, "step": 2526 }, { "epoch": 0.07376809901914994, "grad_norm": 0.5278092622756958, "learning_rate": 7.373029772329248e-06, "loss": 0.2819, "step": 2527 }, { "epoch": 0.07379729098552079, "grad_norm": 0.4672970473766327, "learning_rate": 7.3759486281377705e-06, "loss": 0.2185, "step": 2528 }, { "epoch": 0.07382648295189163, "grad_norm": 0.6835421323776245, "learning_rate": 7.378867483946294e-06, "loss": 0.3205, "step": 2529 }, { "epoch": 0.07385567491826249, "grad_norm": 0.4537481665611267, "learning_rate": 7.381786339754816e-06, "loss": 0.2969, "step": 2530 }, { "epoch": 0.07388486688463335, "grad_norm": 0.4887012243270874, "learning_rate": 7.38470519556334e-06, "loss": 0.2143, "step": 2531 }, { "epoch": 0.0739140588510042, "grad_norm": 0.6396028995513916, "learning_rate": 7.387624051371863e-06, "loss": 0.2873, "step": 2532 }, { "epoch": 0.07394325081737506, "grad_norm": 0.9588332772254944, "learning_rate": 7.3905429071803855e-06, "loss": 0.2281, "step": 2533 }, { "epoch": 0.07397244278374591, "grad_norm": 1.1215064525604248, "learning_rate": 7.39346176298891e-06, "loss": 0.2463, "step": 2534 }, { "epoch": 0.07400163475011677, "grad_norm": 0.5764405131340027, "learning_rate": 7.396380618797432e-06, "loss": 0.3078, "step": 2535 }, { "epoch": 0.07403082671648763, "grad_norm": 0.48706933856010437, "learning_rate": 7.3992994746059555e-06, "loss": 0.2315, "step": 2536 }, { "epoch": 0.07406001868285848, "grad_norm": 0.499484121799469, "learning_rate": 7.402218330414478e-06, "loss": 0.2529, "step": 2537 }, { "epoch": 0.07408921064922933, "grad_norm": 0.5071491599082947, "learning_rate": 7.405137186223001e-06, "loss": 0.2603, "step": 2538 }, { "epoch": 0.07411840261560018, "grad_norm": 0.5979954600334167, "learning_rate": 7.408056042031524e-06, "loss": 0.2055, "step": 2539 }, { "epoch": 0.07414759458197104, "grad_norm": 0.6746547818183899, "learning_rate": 7.410974897840047e-06, "loss": 0.2641, "step": 2540 }, { "epoch": 0.0741767865483419, "grad_norm": 0.54160475730896, "learning_rate": 7.41389375364857e-06, "loss": 0.223, "step": 2541 }, { "epoch": 0.07420597851471275, "grad_norm": 0.9065235257148743, "learning_rate": 7.416812609457094e-06, "loss": 0.3532, "step": 2542 }, { "epoch": 0.0742351704810836, "grad_norm": 1.3117103576660156, "learning_rate": 7.419731465265616e-06, "loss": 0.2041, "step": 2543 }, { "epoch": 0.07426436244745446, "grad_norm": 0.5698379874229431, "learning_rate": 7.42265032107414e-06, "loss": 0.2672, "step": 2544 }, { "epoch": 0.07429355441382532, "grad_norm": 0.4706619381904602, "learning_rate": 7.425569176882662e-06, "loss": 0.2319, "step": 2545 }, { "epoch": 0.07432274638019618, "grad_norm": 0.6345798969268799, "learning_rate": 7.4284880326911856e-06, "loss": 0.2481, "step": 2546 }, { "epoch": 0.07435193834656703, "grad_norm": 0.4789282977581024, "learning_rate": 7.431406888499709e-06, "loss": 0.2761, "step": 2547 }, { "epoch": 0.07438113031293787, "grad_norm": 0.5010669827461243, "learning_rate": 7.434325744308231e-06, "loss": 0.2623, "step": 2548 }, { "epoch": 0.07441032227930873, "grad_norm": 0.4605701267719269, "learning_rate": 7.437244600116756e-06, "loss": 0.2576, "step": 2549 }, { "epoch": 0.07443951424567959, "grad_norm": 0.5254011750221252, "learning_rate": 7.440163455925278e-06, "loss": 0.2406, "step": 2550 }, { "epoch": 0.07446870621205044, "grad_norm": 0.6146670579910278, "learning_rate": 7.443082311733801e-06, "loss": 0.2307, "step": 2551 }, { "epoch": 0.0744978981784213, "grad_norm": 0.46516209840774536, "learning_rate": 7.446001167542324e-06, "loss": 0.2442, "step": 2552 }, { "epoch": 0.07452709014479215, "grad_norm": 0.5521475076675415, "learning_rate": 7.448920023350847e-06, "loss": 0.2581, "step": 2553 }, { "epoch": 0.07455628211116301, "grad_norm": 0.5046169757843018, "learning_rate": 7.45183887915937e-06, "loss": 0.2271, "step": 2554 }, { "epoch": 0.07458547407753387, "grad_norm": 0.501873791217804, "learning_rate": 7.454757734967893e-06, "loss": 0.3422, "step": 2555 }, { "epoch": 0.07461466604390472, "grad_norm": 0.48536455631256104, "learning_rate": 7.4576765907764156e-06, "loss": 0.2578, "step": 2556 }, { "epoch": 0.07464385801027557, "grad_norm": 0.5709325671195984, "learning_rate": 7.46059544658494e-06, "loss": 0.2737, "step": 2557 }, { "epoch": 0.07467304997664642, "grad_norm": 0.4779796600341797, "learning_rate": 7.463514302393462e-06, "loss": 0.2166, "step": 2558 }, { "epoch": 0.07470224194301728, "grad_norm": 0.5382323861122131, "learning_rate": 7.466433158201986e-06, "loss": 0.244, "step": 2559 }, { "epoch": 0.07473143390938813, "grad_norm": 0.4623297452926636, "learning_rate": 7.469352014010508e-06, "loss": 0.2306, "step": 2560 }, { "epoch": 0.07476062587575899, "grad_norm": 0.45630356669425964, "learning_rate": 7.4722708698190314e-06, "loss": 0.2517, "step": 2561 }, { "epoch": 0.07478981784212985, "grad_norm": 0.8067754507064819, "learning_rate": 7.475189725627554e-06, "loss": 0.2287, "step": 2562 }, { "epoch": 0.0748190098085007, "grad_norm": 1.407050371170044, "learning_rate": 7.478108581436077e-06, "loss": 0.2563, "step": 2563 }, { "epoch": 0.07484820177487156, "grad_norm": 0.4669106900691986, "learning_rate": 7.4810274372446014e-06, "loss": 0.2597, "step": 2564 }, { "epoch": 0.07487739374124242, "grad_norm": 0.48426875472068787, "learning_rate": 7.483946293053124e-06, "loss": 0.2114, "step": 2565 }, { "epoch": 0.07490658570761327, "grad_norm": 0.5157690644264221, "learning_rate": 7.486865148861647e-06, "loss": 0.2708, "step": 2566 }, { "epoch": 0.07493577767398411, "grad_norm": 0.48377302289009094, "learning_rate": 7.48978400467017e-06, "loss": 0.2197, "step": 2567 }, { "epoch": 0.07496496964035497, "grad_norm": 0.5196710824966431, "learning_rate": 7.492702860478693e-06, "loss": 0.2624, "step": 2568 }, { "epoch": 0.07499416160672583, "grad_norm": 0.6308218240737915, "learning_rate": 7.495621716287216e-06, "loss": 0.2847, "step": 2569 }, { "epoch": 0.07502335357309668, "grad_norm": 1.2961307764053345, "learning_rate": 7.49854057209574e-06, "loss": 0.2306, "step": 2570 }, { "epoch": 0.07505254553946754, "grad_norm": 2.963527202606201, "learning_rate": 7.5014594279042614e-06, "loss": 0.2884, "step": 2571 }, { "epoch": 0.0750817375058384, "grad_norm": 1.019381046295166, "learning_rate": 7.504378283712786e-06, "loss": 0.2304, "step": 2572 }, { "epoch": 0.07511092947220925, "grad_norm": 0.5484263896942139, "learning_rate": 7.507297139521308e-06, "loss": 0.2847, "step": 2573 }, { "epoch": 0.07514012143858011, "grad_norm": 0.5289731025695801, "learning_rate": 7.5102159953298315e-06, "loss": 0.2851, "step": 2574 }, { "epoch": 0.07516931340495096, "grad_norm": 0.460025817155838, "learning_rate": 7.513134851138354e-06, "loss": 0.2475, "step": 2575 }, { "epoch": 0.0751985053713218, "grad_norm": 0.4301917552947998, "learning_rate": 7.516053706946877e-06, "loss": 0.243, "step": 2576 }, { "epoch": 0.07522769733769266, "grad_norm": 0.6804855465888977, "learning_rate": 7.5189725627554e-06, "loss": 0.2421, "step": 2577 }, { "epoch": 0.07525688930406352, "grad_norm": 0.4450618326663971, "learning_rate": 7.521891418563924e-06, "loss": 0.2559, "step": 2578 }, { "epoch": 0.07528608127043437, "grad_norm": 0.5030187368392944, "learning_rate": 7.524810274372447e-06, "loss": 0.2479, "step": 2579 }, { "epoch": 0.07531527323680523, "grad_norm": 0.4726808965206146, "learning_rate": 7.52772913018097e-06, "loss": 0.2326, "step": 2580 }, { "epoch": 0.07534446520317609, "grad_norm": 0.4236689507961273, "learning_rate": 7.530647985989493e-06, "loss": 0.2412, "step": 2581 }, { "epoch": 0.07537365716954694, "grad_norm": 0.5566467642784119, "learning_rate": 7.533566841798016e-06, "loss": 0.2852, "step": 2582 }, { "epoch": 0.0754028491359178, "grad_norm": 0.44207963347435, "learning_rate": 7.536485697606539e-06, "loss": 0.2177, "step": 2583 }, { "epoch": 0.07543204110228865, "grad_norm": 0.6089011430740356, "learning_rate": 7.5394045534150615e-06, "loss": 0.2909, "step": 2584 }, { "epoch": 0.07546123306865951, "grad_norm": 0.5566596984863281, "learning_rate": 7.542323409223586e-06, "loss": 0.2852, "step": 2585 }, { "epoch": 0.07549042503503035, "grad_norm": 0.6243871450424194, "learning_rate": 7.545242265032108e-06, "loss": 0.3084, "step": 2586 }, { "epoch": 0.07551961700140121, "grad_norm": 0.662285327911377, "learning_rate": 7.5481611208406315e-06, "loss": 0.2831, "step": 2587 }, { "epoch": 0.07554880896777207, "grad_norm": 0.48174184560775757, "learning_rate": 7.551079976649154e-06, "loss": 0.2714, "step": 2588 }, { "epoch": 0.07557800093414292, "grad_norm": 0.4977515935897827, "learning_rate": 7.553998832457677e-06, "loss": 0.2494, "step": 2589 }, { "epoch": 0.07560719290051378, "grad_norm": 0.5058172345161438, "learning_rate": 7.5569176882662e-06, "loss": 0.2571, "step": 2590 }, { "epoch": 0.07563638486688463, "grad_norm": 0.49070674180984497, "learning_rate": 7.559836544074723e-06, "loss": 0.2683, "step": 2591 }, { "epoch": 0.07566557683325549, "grad_norm": 0.5451750755310059, "learning_rate": 7.562755399883246e-06, "loss": 0.2544, "step": 2592 }, { "epoch": 0.07569476879962635, "grad_norm": 0.5149132609367371, "learning_rate": 7.56567425569177e-06, "loss": 0.2828, "step": 2593 }, { "epoch": 0.0757239607659972, "grad_norm": 0.5165387988090515, "learning_rate": 7.568593111500292e-06, "loss": 0.2626, "step": 2594 }, { "epoch": 0.07575315273236806, "grad_norm": 0.9088399410247803, "learning_rate": 7.571511967308816e-06, "loss": 0.2281, "step": 2595 }, { "epoch": 0.0757823446987389, "grad_norm": 0.5292368531227112, "learning_rate": 7.574430823117339e-06, "loss": 0.2315, "step": 2596 }, { "epoch": 0.07581153666510976, "grad_norm": 0.49134328961372375, "learning_rate": 7.5773496789258615e-06, "loss": 0.2694, "step": 2597 }, { "epoch": 0.07584072863148061, "grad_norm": 0.5074567198753357, "learning_rate": 7.580268534734385e-06, "loss": 0.2345, "step": 2598 }, { "epoch": 0.07586992059785147, "grad_norm": 0.6709491014480591, "learning_rate": 7.583187390542907e-06, "loss": 0.2523, "step": 2599 }, { "epoch": 0.07589911256422233, "grad_norm": 0.5711304545402527, "learning_rate": 7.5861062463514315e-06, "loss": 0.2484, "step": 2600 }, { "epoch": 0.07592830453059318, "grad_norm": 0.5369897484779358, "learning_rate": 7.589025102159954e-06, "loss": 0.2296, "step": 2601 }, { "epoch": 0.07595749649696404, "grad_norm": 0.49336716532707214, "learning_rate": 7.591943957968477e-06, "loss": 0.2875, "step": 2602 }, { "epoch": 0.0759866884633349, "grad_norm": 0.5418540239334106, "learning_rate": 7.594862813777e-06, "loss": 0.2716, "step": 2603 }, { "epoch": 0.07601588042970575, "grad_norm": 0.48142287135124207, "learning_rate": 7.597781669585523e-06, "loss": 0.2611, "step": 2604 }, { "epoch": 0.0760450723960766, "grad_norm": 0.49898678064346313, "learning_rate": 7.600700525394046e-06, "loss": 0.2485, "step": 2605 }, { "epoch": 0.07607426436244745, "grad_norm": 0.5204413533210754, "learning_rate": 7.603619381202569e-06, "loss": 0.2623, "step": 2606 }, { "epoch": 0.0761034563288183, "grad_norm": 0.6555725932121277, "learning_rate": 7.6065382370110915e-06, "loss": 0.258, "step": 2607 }, { "epoch": 0.07613264829518916, "grad_norm": 0.49789872765541077, "learning_rate": 7.609457092819616e-06, "loss": 0.2478, "step": 2608 }, { "epoch": 0.07616184026156002, "grad_norm": 0.4981542229652405, "learning_rate": 7.612375948628138e-06, "loss": 0.2273, "step": 2609 }, { "epoch": 0.07619103222793087, "grad_norm": 0.483876496553421, "learning_rate": 7.6152948044366615e-06, "loss": 0.276, "step": 2610 }, { "epoch": 0.07622022419430173, "grad_norm": 0.5645413398742676, "learning_rate": 7.618213660245185e-06, "loss": 0.2968, "step": 2611 }, { "epoch": 0.07624941616067259, "grad_norm": 0.9045692682266235, "learning_rate": 7.621132516053707e-06, "loss": 0.2408, "step": 2612 }, { "epoch": 0.07627860812704344, "grad_norm": 0.47469770908355713, "learning_rate": 7.624051371862231e-06, "loss": 0.2695, "step": 2613 }, { "epoch": 0.0763078000934143, "grad_norm": 0.4912949800491333, "learning_rate": 7.626970227670753e-06, "loss": 0.252, "step": 2614 }, { "epoch": 0.07633699205978514, "grad_norm": 0.5043293833732605, "learning_rate": 7.629889083479277e-06, "loss": 0.2544, "step": 2615 }, { "epoch": 0.076366184026156, "grad_norm": 0.598405659198761, "learning_rate": 7.6328079392878e-06, "loss": 0.2549, "step": 2616 }, { "epoch": 0.07639537599252685, "grad_norm": 0.505491316318512, "learning_rate": 7.635726795096322e-06, "loss": 0.2881, "step": 2617 }, { "epoch": 0.07642456795889771, "grad_norm": 0.526404857635498, "learning_rate": 7.638645650904845e-06, "loss": 0.2747, "step": 2618 }, { "epoch": 0.07645375992526857, "grad_norm": 0.537835419178009, "learning_rate": 7.641564506713369e-06, "loss": 0.2823, "step": 2619 }, { "epoch": 0.07648295189163942, "grad_norm": 0.49375492334365845, "learning_rate": 7.644483362521892e-06, "loss": 0.2638, "step": 2620 }, { "epoch": 0.07651214385801028, "grad_norm": 0.5568208694458008, "learning_rate": 7.647402218330416e-06, "loss": 0.2524, "step": 2621 }, { "epoch": 0.07654133582438113, "grad_norm": 0.5437344312667847, "learning_rate": 7.650321074138938e-06, "loss": 0.2742, "step": 2622 }, { "epoch": 0.07657052779075199, "grad_norm": 0.46909675002098083, "learning_rate": 7.65323992994746e-06, "loss": 0.2137, "step": 2623 }, { "epoch": 0.07659971975712283, "grad_norm": 0.5322498679161072, "learning_rate": 7.656158785755983e-06, "loss": 0.2636, "step": 2624 }, { "epoch": 0.07662891172349369, "grad_norm": 0.4398050308227539, "learning_rate": 7.659077641564507e-06, "loss": 0.221, "step": 2625 }, { "epoch": 0.07665810368986455, "grad_norm": 0.5627375841140747, "learning_rate": 7.66199649737303e-06, "loss": 0.3254, "step": 2626 }, { "epoch": 0.0766872956562354, "grad_norm": 0.4523298442363739, "learning_rate": 7.664915353181554e-06, "loss": 0.2604, "step": 2627 }, { "epoch": 0.07671648762260626, "grad_norm": 0.4616647958755493, "learning_rate": 7.667834208990077e-06, "loss": 0.23, "step": 2628 }, { "epoch": 0.07674567958897711, "grad_norm": 0.6703275442123413, "learning_rate": 7.670753064798599e-06, "loss": 0.3355, "step": 2629 }, { "epoch": 0.07677487155534797, "grad_norm": 0.4487026631832123, "learning_rate": 7.673671920607123e-06, "loss": 0.2184, "step": 2630 }, { "epoch": 0.07680406352171883, "grad_norm": 0.8963737487792969, "learning_rate": 7.676590776415646e-06, "loss": 0.2789, "step": 2631 }, { "epoch": 0.07683325548808968, "grad_norm": 0.49049240350723267, "learning_rate": 7.67950963222417e-06, "loss": 0.2609, "step": 2632 }, { "epoch": 0.07686244745446054, "grad_norm": 0.5849751234054565, "learning_rate": 7.682428488032692e-06, "loss": 0.2683, "step": 2633 }, { "epoch": 0.07689163942083138, "grad_norm": 0.5302005410194397, "learning_rate": 7.685347343841215e-06, "loss": 0.2633, "step": 2634 }, { "epoch": 0.07692083138720224, "grad_norm": 0.4716692268848419, "learning_rate": 7.688266199649737e-06, "loss": 0.2634, "step": 2635 }, { "epoch": 0.0769500233535731, "grad_norm": 0.50642329454422, "learning_rate": 7.691185055458262e-06, "loss": 0.3047, "step": 2636 }, { "epoch": 0.07697921531994395, "grad_norm": 0.9305334091186523, "learning_rate": 7.694103911266784e-06, "loss": 0.2601, "step": 2637 }, { "epoch": 0.0770084072863148, "grad_norm": 0.43831464648246765, "learning_rate": 7.697022767075307e-06, "loss": 0.1991, "step": 2638 }, { "epoch": 0.07703759925268566, "grad_norm": 0.4753414988517761, "learning_rate": 7.699941622883829e-06, "loss": 0.2653, "step": 2639 }, { "epoch": 0.07706679121905652, "grad_norm": 0.5314346551895142, "learning_rate": 7.702860478692353e-06, "loss": 0.2237, "step": 2640 }, { "epoch": 0.07709598318542737, "grad_norm": 0.7404055595397949, "learning_rate": 7.705779334500876e-06, "loss": 0.2877, "step": 2641 }, { "epoch": 0.07712517515179823, "grad_norm": 0.44503089785575867, "learning_rate": 7.7086981903094e-06, "loss": 0.1997, "step": 2642 }, { "epoch": 0.07715436711816907, "grad_norm": 0.4759228527545929, "learning_rate": 7.711617046117922e-06, "loss": 0.2375, "step": 2643 }, { "epoch": 0.07718355908453993, "grad_norm": 0.46160197257995605, "learning_rate": 7.714535901926445e-06, "loss": 0.2144, "step": 2644 }, { "epoch": 0.07721275105091079, "grad_norm": 0.48169252276420593, "learning_rate": 7.717454757734969e-06, "loss": 0.2181, "step": 2645 }, { "epoch": 0.07724194301728164, "grad_norm": 0.4689301550388336, "learning_rate": 7.720373613543492e-06, "loss": 0.2441, "step": 2646 }, { "epoch": 0.0772711349836525, "grad_norm": 0.5119760632514954, "learning_rate": 7.723292469352016e-06, "loss": 0.2289, "step": 2647 }, { "epoch": 0.07730032695002335, "grad_norm": 0.5170531868934631, "learning_rate": 7.726211325160538e-06, "loss": 0.2858, "step": 2648 }, { "epoch": 0.07732951891639421, "grad_norm": 0.4574498236179352, "learning_rate": 7.72913018096906e-06, "loss": 0.2815, "step": 2649 }, { "epoch": 0.07735871088276507, "grad_norm": 0.5571054220199585, "learning_rate": 7.732049036777583e-06, "loss": 0.2416, "step": 2650 }, { "epoch": 0.07738790284913592, "grad_norm": 0.495836079120636, "learning_rate": 7.734967892586107e-06, "loss": 0.2362, "step": 2651 }, { "epoch": 0.07741709481550678, "grad_norm": 0.5435232520103455, "learning_rate": 7.73788674839463e-06, "loss": 0.2859, "step": 2652 }, { "epoch": 0.07744628678187762, "grad_norm": 0.4473472237586975, "learning_rate": 7.740805604203152e-06, "loss": 0.2558, "step": 2653 }, { "epoch": 0.07747547874824848, "grad_norm": 0.4151935279369354, "learning_rate": 7.743724460011675e-06, "loss": 0.2224, "step": 2654 }, { "epoch": 0.07750467071461933, "grad_norm": 0.4854574501514435, "learning_rate": 7.746643315820199e-06, "loss": 0.2536, "step": 2655 }, { "epoch": 0.07753386268099019, "grad_norm": 0.7511892318725586, "learning_rate": 7.749562171628722e-06, "loss": 0.2312, "step": 2656 }, { "epoch": 0.07756305464736105, "grad_norm": 0.47243183851242065, "learning_rate": 7.752481027437246e-06, "loss": 0.2187, "step": 2657 }, { "epoch": 0.0775922466137319, "grad_norm": 0.515232503414154, "learning_rate": 7.755399883245768e-06, "loss": 0.2575, "step": 2658 }, { "epoch": 0.07762143858010276, "grad_norm": 0.5183717608451843, "learning_rate": 7.75831873905429e-06, "loss": 0.2894, "step": 2659 }, { "epoch": 0.07765063054647361, "grad_norm": 0.5021180510520935, "learning_rate": 7.761237594862815e-06, "loss": 0.279, "step": 2660 }, { "epoch": 0.07767982251284447, "grad_norm": 0.4611108601093292, "learning_rate": 7.764156450671337e-06, "loss": 0.245, "step": 2661 }, { "epoch": 0.07770901447921531, "grad_norm": 0.5147509574890137, "learning_rate": 7.767075306479862e-06, "loss": 0.278, "step": 2662 }, { "epoch": 0.07773820644558617, "grad_norm": 0.49777430295944214, "learning_rate": 7.769994162288384e-06, "loss": 0.2259, "step": 2663 }, { "epoch": 0.07776739841195703, "grad_norm": 0.6253204941749573, "learning_rate": 7.772913018096907e-06, "loss": 0.2229, "step": 2664 }, { "epoch": 0.07779659037832788, "grad_norm": 0.5880403518676758, "learning_rate": 7.775831873905429e-06, "loss": 0.2783, "step": 2665 }, { "epoch": 0.07782578234469874, "grad_norm": 0.4298058748245239, "learning_rate": 7.778750729713953e-06, "loss": 0.2086, "step": 2666 }, { "epoch": 0.0778549743110696, "grad_norm": 0.4323282837867737, "learning_rate": 7.781669585522476e-06, "loss": 0.1767, "step": 2667 }, { "epoch": 0.07788416627744045, "grad_norm": 0.48595359921455383, "learning_rate": 7.784588441330998e-06, "loss": 0.2479, "step": 2668 }, { "epoch": 0.0779133582438113, "grad_norm": 0.5756658911705017, "learning_rate": 7.78750729713952e-06, "loss": 0.2487, "step": 2669 }, { "epoch": 0.07794255021018216, "grad_norm": 0.4597357213497162, "learning_rate": 7.790426152948045e-06, "loss": 0.2676, "step": 2670 }, { "epoch": 0.07797174217655302, "grad_norm": 0.6690155863761902, "learning_rate": 7.793345008756567e-06, "loss": 0.3004, "step": 2671 }, { "epoch": 0.07800093414292386, "grad_norm": 0.552808940410614, "learning_rate": 7.796263864565092e-06, "loss": 0.244, "step": 2672 }, { "epoch": 0.07803012610929472, "grad_norm": 0.5374470353126526, "learning_rate": 7.799182720373614e-06, "loss": 0.2938, "step": 2673 }, { "epoch": 0.07805931807566557, "grad_norm": 0.5515209436416626, "learning_rate": 7.802101576182137e-06, "loss": 0.214, "step": 2674 }, { "epoch": 0.07808851004203643, "grad_norm": 0.5257934927940369, "learning_rate": 7.805020431990661e-06, "loss": 0.2929, "step": 2675 }, { "epoch": 0.07811770200840729, "grad_norm": 0.4844946265220642, "learning_rate": 7.807939287799183e-06, "loss": 0.2435, "step": 2676 }, { "epoch": 0.07814689397477814, "grad_norm": 0.8911114931106567, "learning_rate": 7.810858143607708e-06, "loss": 0.296, "step": 2677 }, { "epoch": 0.078176085941149, "grad_norm": 0.45578670501708984, "learning_rate": 7.81377699941623e-06, "loss": 0.2412, "step": 2678 }, { "epoch": 0.07820527790751985, "grad_norm": 0.4275745153427124, "learning_rate": 7.816695855224753e-06, "loss": 0.2424, "step": 2679 }, { "epoch": 0.07823446987389071, "grad_norm": 0.5793019533157349, "learning_rate": 7.819614711033275e-06, "loss": 0.2597, "step": 2680 }, { "epoch": 0.07826366184026157, "grad_norm": 0.4758716821670532, "learning_rate": 7.8225335668418e-06, "loss": 0.2823, "step": 2681 }, { "epoch": 0.07829285380663241, "grad_norm": 1.0682907104492188, "learning_rate": 7.825452422650322e-06, "loss": 0.3399, "step": 2682 }, { "epoch": 0.07832204577300327, "grad_norm": 0.4278445243835449, "learning_rate": 7.828371278458846e-06, "loss": 0.2274, "step": 2683 }, { "epoch": 0.07835123773937412, "grad_norm": 0.5427970290184021, "learning_rate": 7.831290134267367e-06, "loss": 0.315, "step": 2684 }, { "epoch": 0.07838042970574498, "grad_norm": 0.502297043800354, "learning_rate": 7.834208990075891e-06, "loss": 0.3014, "step": 2685 }, { "epoch": 0.07840962167211583, "grad_norm": 0.38574233651161194, "learning_rate": 7.837127845884413e-06, "loss": 0.2247, "step": 2686 }, { "epoch": 0.07843881363848669, "grad_norm": 0.4878087639808655, "learning_rate": 7.840046701692938e-06, "loss": 0.3318, "step": 2687 }, { "epoch": 0.07846800560485755, "grad_norm": 0.9039566516876221, "learning_rate": 7.84296555750146e-06, "loss": 0.2295, "step": 2688 }, { "epoch": 0.0784971975712284, "grad_norm": 0.46684813499450684, "learning_rate": 7.845884413309983e-06, "loss": 0.2663, "step": 2689 }, { "epoch": 0.07852638953759926, "grad_norm": 0.41304850578308105, "learning_rate": 7.848803269118505e-06, "loss": 0.2546, "step": 2690 }, { "epoch": 0.0785555815039701, "grad_norm": 0.4798588156700134, "learning_rate": 7.85172212492703e-06, "loss": 0.2558, "step": 2691 }, { "epoch": 0.07858477347034096, "grad_norm": 0.41293472051620483, "learning_rate": 7.854640980735553e-06, "loss": 0.235, "step": 2692 }, { "epoch": 0.07861396543671181, "grad_norm": 0.4906495213508606, "learning_rate": 7.857559836544076e-06, "loss": 0.2765, "step": 2693 }, { "epoch": 0.07864315740308267, "grad_norm": 0.6310531497001648, "learning_rate": 7.860478692352598e-06, "loss": 0.2531, "step": 2694 }, { "epoch": 0.07867234936945353, "grad_norm": 0.4336978793144226, "learning_rate": 7.863397548161121e-06, "loss": 0.2555, "step": 2695 }, { "epoch": 0.07870154133582438, "grad_norm": 0.5529845356941223, "learning_rate": 7.866316403969645e-06, "loss": 0.2489, "step": 2696 }, { "epoch": 0.07873073330219524, "grad_norm": 0.43406978249549866, "learning_rate": 7.869235259778168e-06, "loss": 0.2457, "step": 2697 }, { "epoch": 0.0787599252685661, "grad_norm": 0.5566697120666504, "learning_rate": 7.872154115586692e-06, "loss": 0.2968, "step": 2698 }, { "epoch": 0.07878911723493695, "grad_norm": 0.5053045749664307, "learning_rate": 7.875072971395214e-06, "loss": 0.2799, "step": 2699 }, { "epoch": 0.0788183092013078, "grad_norm": 0.5950333476066589, "learning_rate": 7.877991827203737e-06, "loss": 0.2877, "step": 2700 }, { "epoch": 0.07884750116767865, "grad_norm": 0.42932987213134766, "learning_rate": 7.88091068301226e-06, "loss": 0.2534, "step": 2701 }, { "epoch": 0.0788766931340495, "grad_norm": 0.9014973044395447, "learning_rate": 7.883829538820783e-06, "loss": 0.2735, "step": 2702 }, { "epoch": 0.07890588510042036, "grad_norm": 0.4816298186779022, "learning_rate": 7.886748394629306e-06, "loss": 0.2415, "step": 2703 }, { "epoch": 0.07893507706679122, "grad_norm": 0.4296509921550751, "learning_rate": 7.889667250437828e-06, "loss": 0.2396, "step": 2704 }, { "epoch": 0.07896426903316207, "grad_norm": 0.5890136957168579, "learning_rate": 7.892586106246351e-06, "loss": 0.2489, "step": 2705 }, { "epoch": 0.07899346099953293, "grad_norm": 0.6889787316322327, "learning_rate": 7.895504962054875e-06, "loss": 0.2513, "step": 2706 }, { "epoch": 0.07902265296590379, "grad_norm": 0.44509702920913696, "learning_rate": 7.8984238178634e-06, "loss": 0.2601, "step": 2707 }, { "epoch": 0.07905184493227464, "grad_norm": 0.5037034153938293, "learning_rate": 7.901342673671922e-06, "loss": 0.2519, "step": 2708 }, { "epoch": 0.0790810368986455, "grad_norm": 0.48526808619499207, "learning_rate": 7.904261529480444e-06, "loss": 0.2415, "step": 2709 }, { "epoch": 0.07911022886501634, "grad_norm": 0.43531352281570435, "learning_rate": 7.907180385288967e-06, "loss": 0.2143, "step": 2710 }, { "epoch": 0.0791394208313872, "grad_norm": 0.48279887437820435, "learning_rate": 7.910099241097491e-06, "loss": 0.2382, "step": 2711 }, { "epoch": 0.07916861279775805, "grad_norm": 0.4924471378326416, "learning_rate": 7.913018096906013e-06, "loss": 0.2269, "step": 2712 }, { "epoch": 0.07919780476412891, "grad_norm": 0.5259729027748108, "learning_rate": 7.915936952714538e-06, "loss": 0.2813, "step": 2713 }, { "epoch": 0.07922699673049977, "grad_norm": 0.5210674405097961, "learning_rate": 7.91885580852306e-06, "loss": 0.2856, "step": 2714 }, { "epoch": 0.07925618869687062, "grad_norm": 1.2345916032791138, "learning_rate": 7.921774664331583e-06, "loss": 0.2686, "step": 2715 }, { "epoch": 0.07928538066324148, "grad_norm": 0.5408028364181519, "learning_rate": 7.924693520140105e-06, "loss": 0.2728, "step": 2716 }, { "epoch": 0.07931457262961233, "grad_norm": 0.4025512635707855, "learning_rate": 7.92761237594863e-06, "loss": 0.2268, "step": 2717 }, { "epoch": 0.07934376459598319, "grad_norm": 0.5257952809333801, "learning_rate": 7.930531231757152e-06, "loss": 0.3013, "step": 2718 }, { "epoch": 0.07937295656235405, "grad_norm": 0.3913593888282776, "learning_rate": 7.933450087565674e-06, "loss": 0.2084, "step": 2719 }, { "epoch": 0.07940214852872489, "grad_norm": 0.4803072214126587, "learning_rate": 7.936368943374197e-06, "loss": 0.2391, "step": 2720 }, { "epoch": 0.07943134049509575, "grad_norm": 0.5194296836853027, "learning_rate": 7.939287799182721e-06, "loss": 0.2553, "step": 2721 }, { "epoch": 0.0794605324614666, "grad_norm": 0.4894026815891266, "learning_rate": 7.942206654991243e-06, "loss": 0.2962, "step": 2722 }, { "epoch": 0.07948972442783746, "grad_norm": 0.4271657466888428, "learning_rate": 7.945125510799768e-06, "loss": 0.2259, "step": 2723 }, { "epoch": 0.07951891639420831, "grad_norm": 0.444204181432724, "learning_rate": 7.94804436660829e-06, "loss": 0.2117, "step": 2724 }, { "epoch": 0.07954810836057917, "grad_norm": 0.4398866593837738, "learning_rate": 7.950963222416813e-06, "loss": 0.2525, "step": 2725 }, { "epoch": 0.07957730032695003, "grad_norm": 0.6637564301490784, "learning_rate": 7.953882078225337e-06, "loss": 0.2487, "step": 2726 }, { "epoch": 0.07960649229332088, "grad_norm": 0.4936584234237671, "learning_rate": 7.95680093403386e-06, "loss": 0.2856, "step": 2727 }, { "epoch": 0.07963568425969174, "grad_norm": 0.45726966857910156, "learning_rate": 7.959719789842383e-06, "loss": 0.2645, "step": 2728 }, { "epoch": 0.07966487622606258, "grad_norm": 0.6648007035255432, "learning_rate": 7.962638645650906e-06, "loss": 0.2875, "step": 2729 }, { "epoch": 0.07969406819243344, "grad_norm": 0.44782617688179016, "learning_rate": 7.965557501459428e-06, "loss": 0.2149, "step": 2730 }, { "epoch": 0.0797232601588043, "grad_norm": 0.4600614309310913, "learning_rate": 7.968476357267951e-06, "loss": 0.2498, "step": 2731 }, { "epoch": 0.07975245212517515, "grad_norm": 0.5276694297790527, "learning_rate": 7.971395213076475e-06, "loss": 0.3427, "step": 2732 }, { "epoch": 0.079781644091546, "grad_norm": 0.5711271166801453, "learning_rate": 7.974314068884998e-06, "loss": 0.2303, "step": 2733 }, { "epoch": 0.07981083605791686, "grad_norm": 0.49652236700057983, "learning_rate": 7.97723292469352e-06, "loss": 0.2513, "step": 2734 }, { "epoch": 0.07984002802428772, "grad_norm": 0.5656131505966187, "learning_rate": 7.980151780502043e-06, "loss": 0.2386, "step": 2735 }, { "epoch": 0.07986921999065857, "grad_norm": 1.041845679283142, "learning_rate": 7.983070636310567e-06, "loss": 0.3034, "step": 2736 }, { "epoch": 0.07989841195702943, "grad_norm": 0.38436201214790344, "learning_rate": 7.98598949211909e-06, "loss": 0.21, "step": 2737 }, { "epoch": 0.07992760392340029, "grad_norm": 0.4932571053504944, "learning_rate": 7.988908347927613e-06, "loss": 0.2872, "step": 2738 }, { "epoch": 0.07995679588977113, "grad_norm": 0.43979185819625854, "learning_rate": 7.991827203736136e-06, "loss": 0.3401, "step": 2739 }, { "epoch": 0.07998598785614199, "grad_norm": 0.5645153522491455, "learning_rate": 7.994746059544658e-06, "loss": 0.246, "step": 2740 }, { "epoch": 0.08001517982251284, "grad_norm": 0.6866587400436401, "learning_rate": 7.997664915353183e-06, "loss": 0.2432, "step": 2741 }, { "epoch": 0.0800443717888837, "grad_norm": 0.4656343460083008, "learning_rate": 8.000583771161705e-06, "loss": 0.2379, "step": 2742 }, { "epoch": 0.08007356375525455, "grad_norm": 0.4363041818141937, "learning_rate": 8.00350262697023e-06, "loss": 0.2816, "step": 2743 }, { "epoch": 0.08010275572162541, "grad_norm": 0.5152103304862976, "learning_rate": 8.006421482778752e-06, "loss": 0.2361, "step": 2744 }, { "epoch": 0.08013194768799627, "grad_norm": 0.4660474956035614, "learning_rate": 8.009340338587274e-06, "loss": 0.2472, "step": 2745 }, { "epoch": 0.08016113965436712, "grad_norm": 0.701163649559021, "learning_rate": 8.012259194395797e-06, "loss": 0.2805, "step": 2746 }, { "epoch": 0.08019033162073798, "grad_norm": 0.8504656553268433, "learning_rate": 8.015178050204321e-06, "loss": 0.2581, "step": 2747 }, { "epoch": 0.08021952358710882, "grad_norm": 0.5096801519393921, "learning_rate": 8.018096906012843e-06, "loss": 0.2689, "step": 2748 }, { "epoch": 0.08024871555347968, "grad_norm": 0.4599141776561737, "learning_rate": 8.021015761821368e-06, "loss": 0.2495, "step": 2749 }, { "epoch": 0.08027790751985053, "grad_norm": 0.5362011194229126, "learning_rate": 8.02393461762989e-06, "loss": 0.2656, "step": 2750 }, { "epoch": 0.08030709948622139, "grad_norm": 0.46311184763908386, "learning_rate": 8.026853473438413e-06, "loss": 0.22, "step": 2751 }, { "epoch": 0.08033629145259225, "grad_norm": 0.46175020933151245, "learning_rate": 8.029772329246935e-06, "loss": 0.2683, "step": 2752 }, { "epoch": 0.0803654834189631, "grad_norm": 0.5432437062263489, "learning_rate": 8.03269118505546e-06, "loss": 0.2517, "step": 2753 }, { "epoch": 0.08039467538533396, "grad_norm": 0.5200193524360657, "learning_rate": 8.035610040863982e-06, "loss": 0.2269, "step": 2754 }, { "epoch": 0.08042386735170481, "grad_norm": 0.49690571427345276, "learning_rate": 8.038528896672504e-06, "loss": 0.2292, "step": 2755 }, { "epoch": 0.08045305931807567, "grad_norm": 0.5360631942749023, "learning_rate": 8.041447752481029e-06, "loss": 0.2501, "step": 2756 }, { "epoch": 0.08048225128444653, "grad_norm": 0.41482996940612793, "learning_rate": 8.044366608289551e-06, "loss": 0.2177, "step": 2757 }, { "epoch": 0.08051144325081737, "grad_norm": 0.6039344072341919, "learning_rate": 8.047285464098075e-06, "loss": 0.2781, "step": 2758 }, { "epoch": 0.08054063521718823, "grad_norm": 0.485711932182312, "learning_rate": 8.050204319906598e-06, "loss": 0.2171, "step": 2759 }, { "epoch": 0.08056982718355908, "grad_norm": 0.5938586592674255, "learning_rate": 8.05312317571512e-06, "loss": 0.2304, "step": 2760 }, { "epoch": 0.08059901914992994, "grad_norm": 1.233354091644287, "learning_rate": 8.056042031523643e-06, "loss": 0.2823, "step": 2761 }, { "epoch": 0.0806282111163008, "grad_norm": 0.44280073046684265, "learning_rate": 8.058960887332167e-06, "loss": 0.2421, "step": 2762 }, { "epoch": 0.08065740308267165, "grad_norm": 0.5216030478477478, "learning_rate": 8.06187974314069e-06, "loss": 0.2876, "step": 2763 }, { "epoch": 0.0806865950490425, "grad_norm": 0.48255693912506104, "learning_rate": 8.064798598949214e-06, "loss": 0.2273, "step": 2764 }, { "epoch": 0.08071578701541336, "grad_norm": 0.46737441420555115, "learning_rate": 8.067717454757736e-06, "loss": 0.2668, "step": 2765 }, { "epoch": 0.08074497898178422, "grad_norm": 0.6570453643798828, "learning_rate": 8.070636310566259e-06, "loss": 0.2762, "step": 2766 }, { "epoch": 0.08077417094815507, "grad_norm": 0.43109700083732605, "learning_rate": 8.073555166374781e-06, "loss": 0.1973, "step": 2767 }, { "epoch": 0.08080336291452592, "grad_norm": 0.41651472449302673, "learning_rate": 8.076474022183305e-06, "loss": 0.2021, "step": 2768 }, { "epoch": 0.08083255488089677, "grad_norm": 0.6814332008361816, "learning_rate": 8.079392877991828e-06, "loss": 0.2266, "step": 2769 }, { "epoch": 0.08086174684726763, "grad_norm": 0.5536383986473083, "learning_rate": 8.08231173380035e-06, "loss": 0.2708, "step": 2770 }, { "epoch": 0.08089093881363849, "grad_norm": 0.4486265182495117, "learning_rate": 8.085230589608874e-06, "loss": 0.2443, "step": 2771 }, { "epoch": 0.08092013078000934, "grad_norm": 0.45163533091545105, "learning_rate": 8.088149445417397e-06, "loss": 0.2482, "step": 2772 }, { "epoch": 0.0809493227463802, "grad_norm": 0.53021240234375, "learning_rate": 8.091068301225921e-06, "loss": 0.2621, "step": 2773 }, { "epoch": 0.08097851471275105, "grad_norm": 0.520023763179779, "learning_rate": 8.093987157034444e-06, "loss": 0.2713, "step": 2774 }, { "epoch": 0.08100770667912191, "grad_norm": 0.5290404558181763, "learning_rate": 8.096906012842966e-06, "loss": 0.2585, "step": 2775 }, { "epoch": 0.08103689864549277, "grad_norm": 0.4716307520866394, "learning_rate": 8.099824868651489e-06, "loss": 0.2484, "step": 2776 }, { "epoch": 0.08106609061186361, "grad_norm": 0.43339458107948303, "learning_rate": 8.102743724460013e-06, "loss": 0.2129, "step": 2777 }, { "epoch": 0.08109528257823446, "grad_norm": 0.4765155613422394, "learning_rate": 8.105662580268535e-06, "loss": 0.2723, "step": 2778 }, { "epoch": 0.08112447454460532, "grad_norm": 0.6102232336997986, "learning_rate": 8.10858143607706e-06, "loss": 0.2327, "step": 2779 }, { "epoch": 0.08115366651097618, "grad_norm": 0.4703405201435089, "learning_rate": 8.111500291885582e-06, "loss": 0.2784, "step": 2780 }, { "epoch": 0.08118285847734703, "grad_norm": 0.4392419159412384, "learning_rate": 8.114419147694104e-06, "loss": 0.222, "step": 2781 }, { "epoch": 0.08121205044371789, "grad_norm": 0.6297116875648499, "learning_rate": 8.117338003502627e-06, "loss": 0.297, "step": 2782 }, { "epoch": 0.08124124241008875, "grad_norm": 0.6450963020324707, "learning_rate": 8.120256859311151e-06, "loss": 0.2367, "step": 2783 }, { "epoch": 0.0812704343764596, "grad_norm": 0.440104603767395, "learning_rate": 8.123175715119674e-06, "loss": 0.2852, "step": 2784 }, { "epoch": 0.08129962634283046, "grad_norm": 0.5936902165412903, "learning_rate": 8.126094570928196e-06, "loss": 0.2546, "step": 2785 }, { "epoch": 0.08132881830920131, "grad_norm": 0.4954015612602234, "learning_rate": 8.129013426736719e-06, "loss": 0.2045, "step": 2786 }, { "epoch": 0.08135801027557216, "grad_norm": 0.4323446750640869, "learning_rate": 8.131932282545243e-06, "loss": 0.2794, "step": 2787 }, { "epoch": 0.08138720224194301, "grad_norm": 0.6099599599838257, "learning_rate": 8.134851138353767e-06, "loss": 0.2474, "step": 2788 }, { "epoch": 0.08141639420831387, "grad_norm": 0.4745687246322632, "learning_rate": 8.13776999416229e-06, "loss": 0.2285, "step": 2789 }, { "epoch": 0.08144558617468473, "grad_norm": 0.5761895179748535, "learning_rate": 8.140688849970812e-06, "loss": 0.2684, "step": 2790 }, { "epoch": 0.08147477814105558, "grad_norm": 0.5430966019630432, "learning_rate": 8.143607705779334e-06, "loss": 0.2906, "step": 2791 }, { "epoch": 0.08150397010742644, "grad_norm": 0.41612887382507324, "learning_rate": 8.146526561587859e-06, "loss": 0.2228, "step": 2792 }, { "epoch": 0.0815331620737973, "grad_norm": 0.49427133798599243, "learning_rate": 8.149445417396381e-06, "loss": 0.2759, "step": 2793 }, { "epoch": 0.08156235404016815, "grad_norm": 0.46823644638061523, "learning_rate": 8.152364273204905e-06, "loss": 0.2575, "step": 2794 }, { "epoch": 0.081591546006539, "grad_norm": 0.5366201996803284, "learning_rate": 8.155283129013428e-06, "loss": 0.2844, "step": 2795 }, { "epoch": 0.08162073797290985, "grad_norm": 0.44898414611816406, "learning_rate": 8.15820198482195e-06, "loss": 0.2381, "step": 2796 }, { "epoch": 0.0816499299392807, "grad_norm": 0.5768049359321594, "learning_rate": 8.161120840630473e-06, "loss": 0.3056, "step": 2797 }, { "epoch": 0.08167912190565156, "grad_norm": 0.5587185025215149, "learning_rate": 8.164039696438997e-06, "loss": 0.218, "step": 2798 }, { "epoch": 0.08170831387202242, "grad_norm": 0.46864232420921326, "learning_rate": 8.16695855224752e-06, "loss": 0.2718, "step": 2799 }, { "epoch": 0.08173750583839327, "grad_norm": 0.7027875781059265, "learning_rate": 8.169877408056044e-06, "loss": 0.2516, "step": 2800 }, { "epoch": 0.08176669780476413, "grad_norm": 0.4701298475265503, "learning_rate": 8.172796263864564e-06, "loss": 0.226, "step": 2801 }, { "epoch": 0.08179588977113499, "grad_norm": 0.6081030368804932, "learning_rate": 8.175715119673089e-06, "loss": 0.2465, "step": 2802 }, { "epoch": 0.08182508173750584, "grad_norm": 0.5362954139709473, "learning_rate": 8.178633975481613e-06, "loss": 0.2623, "step": 2803 }, { "epoch": 0.0818542737038767, "grad_norm": 0.6335601210594177, "learning_rate": 8.181552831290135e-06, "loss": 0.2886, "step": 2804 }, { "epoch": 0.08188346567024755, "grad_norm": 0.5840851068496704, "learning_rate": 8.184471687098658e-06, "loss": 0.2822, "step": 2805 }, { "epoch": 0.0819126576366184, "grad_norm": 0.5105985403060913, "learning_rate": 8.18739054290718e-06, "loss": 0.2256, "step": 2806 }, { "epoch": 0.08194184960298925, "grad_norm": 0.49027499556541443, "learning_rate": 8.190309398715704e-06, "loss": 0.2647, "step": 2807 }, { "epoch": 0.08197104156936011, "grad_norm": 0.600304126739502, "learning_rate": 8.193228254524227e-06, "loss": 0.2546, "step": 2808 }, { "epoch": 0.08200023353573097, "grad_norm": 0.5405883193016052, "learning_rate": 8.196147110332751e-06, "loss": 0.2696, "step": 2809 }, { "epoch": 0.08202942550210182, "grad_norm": 0.7228883504867554, "learning_rate": 8.199065966141274e-06, "loss": 0.2265, "step": 2810 }, { "epoch": 0.08205861746847268, "grad_norm": 0.519286572933197, "learning_rate": 8.201984821949796e-06, "loss": 0.258, "step": 2811 }, { "epoch": 0.08208780943484353, "grad_norm": 1.1070274114608765, "learning_rate": 8.204903677758319e-06, "loss": 0.272, "step": 2812 }, { "epoch": 0.08211700140121439, "grad_norm": 0.527796745300293, "learning_rate": 8.207822533566843e-06, "loss": 0.3301, "step": 2813 }, { "epoch": 0.08214619336758525, "grad_norm": 0.5310290455818176, "learning_rate": 8.210741389375365e-06, "loss": 0.2529, "step": 2814 }, { "epoch": 0.08217538533395609, "grad_norm": 0.48599711060523987, "learning_rate": 8.21366024518389e-06, "loss": 0.2764, "step": 2815 }, { "epoch": 0.08220457730032694, "grad_norm": 0.4617638885974884, "learning_rate": 8.216579100992412e-06, "loss": 0.2325, "step": 2816 }, { "epoch": 0.0822337692666978, "grad_norm": 0.6847409605979919, "learning_rate": 8.219497956800934e-06, "loss": 0.2477, "step": 2817 }, { "epoch": 0.08226296123306866, "grad_norm": 0.454693466424942, "learning_rate": 8.222416812609457e-06, "loss": 0.2334, "step": 2818 }, { "epoch": 0.08229215319943951, "grad_norm": 0.48037153482437134, "learning_rate": 8.225335668417981e-06, "loss": 0.218, "step": 2819 }, { "epoch": 0.08232134516581037, "grad_norm": 0.4340381324291229, "learning_rate": 8.228254524226504e-06, "loss": 0.2425, "step": 2820 }, { "epoch": 0.08235053713218123, "grad_norm": 0.5625515580177307, "learning_rate": 8.231173380035026e-06, "loss": 0.2704, "step": 2821 }, { "epoch": 0.08237972909855208, "grad_norm": 0.46756717562675476, "learning_rate": 8.23409223584355e-06, "loss": 0.2807, "step": 2822 }, { "epoch": 0.08240892106492294, "grad_norm": 0.48365548253059387, "learning_rate": 8.237011091652073e-06, "loss": 0.2759, "step": 2823 }, { "epoch": 0.0824381130312938, "grad_norm": 0.4650028347969055, "learning_rate": 8.239929947460597e-06, "loss": 0.2745, "step": 2824 }, { "epoch": 0.08246730499766464, "grad_norm": 0.43093329668045044, "learning_rate": 8.24284880326912e-06, "loss": 0.2685, "step": 2825 }, { "epoch": 0.08249649696403549, "grad_norm": 0.5549624562263489, "learning_rate": 8.245767659077642e-06, "loss": 0.2309, "step": 2826 }, { "epoch": 0.08252568893040635, "grad_norm": 0.5201539397239685, "learning_rate": 8.248686514886164e-06, "loss": 0.2426, "step": 2827 }, { "epoch": 0.0825548808967772, "grad_norm": 0.491603285074234, "learning_rate": 8.251605370694689e-06, "loss": 0.2771, "step": 2828 }, { "epoch": 0.08258407286314806, "grad_norm": 0.5437238812446594, "learning_rate": 8.254524226503211e-06, "loss": 0.2522, "step": 2829 }, { "epoch": 0.08261326482951892, "grad_norm": 0.4654693007469177, "learning_rate": 8.257443082311735e-06, "loss": 0.1876, "step": 2830 }, { "epoch": 0.08264245679588977, "grad_norm": 0.4834074378013611, "learning_rate": 8.260361938120258e-06, "loss": 0.2903, "step": 2831 }, { "epoch": 0.08267164876226063, "grad_norm": 0.7716339230537415, "learning_rate": 8.26328079392878e-06, "loss": 0.2573, "step": 2832 }, { "epoch": 0.08270084072863149, "grad_norm": 0.8816748261451721, "learning_rate": 8.266199649737303e-06, "loss": 0.2645, "step": 2833 }, { "epoch": 0.08273003269500233, "grad_norm": 0.44493842124938965, "learning_rate": 8.269118505545827e-06, "loss": 0.2213, "step": 2834 }, { "epoch": 0.08275922466137318, "grad_norm": 0.5865681767463684, "learning_rate": 8.27203736135435e-06, "loss": 0.2505, "step": 2835 }, { "epoch": 0.08278841662774404, "grad_norm": 0.8768723607063293, "learning_rate": 8.274956217162872e-06, "loss": 0.2835, "step": 2836 }, { "epoch": 0.0828176085941149, "grad_norm": 0.5352628827095032, "learning_rate": 8.277875072971396e-06, "loss": 0.2754, "step": 2837 }, { "epoch": 0.08284680056048575, "grad_norm": 0.6707889437675476, "learning_rate": 8.280793928779919e-06, "loss": 0.3062, "step": 2838 }, { "epoch": 0.08287599252685661, "grad_norm": 0.6657377481460571, "learning_rate": 8.283712784588443e-06, "loss": 0.2025, "step": 2839 }, { "epoch": 0.08290518449322747, "grad_norm": 0.5710002183914185, "learning_rate": 8.286631640396965e-06, "loss": 0.2322, "step": 2840 }, { "epoch": 0.08293437645959832, "grad_norm": 0.4613596796989441, "learning_rate": 8.289550496205488e-06, "loss": 0.2167, "step": 2841 }, { "epoch": 0.08296356842596918, "grad_norm": 0.6136063933372498, "learning_rate": 8.29246935201401e-06, "loss": 0.2634, "step": 2842 }, { "epoch": 0.08299276039234003, "grad_norm": 0.5061696767807007, "learning_rate": 8.295388207822535e-06, "loss": 0.2241, "step": 2843 }, { "epoch": 0.08302195235871088, "grad_norm": 0.5813536047935486, "learning_rate": 8.298307063631057e-06, "loss": 0.3045, "step": 2844 }, { "epoch": 0.08305114432508173, "grad_norm": 1.6334160566329956, "learning_rate": 8.301225919439581e-06, "loss": 0.2589, "step": 2845 }, { "epoch": 0.08308033629145259, "grad_norm": 0.48263877630233765, "learning_rate": 8.304144775248104e-06, "loss": 0.2071, "step": 2846 }, { "epoch": 0.08310952825782345, "grad_norm": 0.9219799041748047, "learning_rate": 8.307063631056626e-06, "loss": 0.2742, "step": 2847 }, { "epoch": 0.0831387202241943, "grad_norm": 0.5495941042900085, "learning_rate": 8.309982486865149e-06, "loss": 0.3259, "step": 2848 }, { "epoch": 0.08316791219056516, "grad_norm": 0.6159777641296387, "learning_rate": 8.312901342673673e-06, "loss": 0.342, "step": 2849 }, { "epoch": 0.08319710415693601, "grad_norm": 0.5589180588722229, "learning_rate": 8.315820198482195e-06, "loss": 0.2477, "step": 2850 }, { "epoch": 0.08322629612330687, "grad_norm": 0.574047863483429, "learning_rate": 8.318739054290718e-06, "loss": 0.2566, "step": 2851 }, { "epoch": 0.08325548808967773, "grad_norm": 0.5287197232246399, "learning_rate": 8.321657910099242e-06, "loss": 0.3021, "step": 2852 }, { "epoch": 0.08328468005604858, "grad_norm": 0.4473514258861542, "learning_rate": 8.324576765907765e-06, "loss": 0.2011, "step": 2853 }, { "epoch": 0.08331387202241942, "grad_norm": 0.43120789527893066, "learning_rate": 8.327495621716289e-06, "loss": 0.2691, "step": 2854 }, { "epoch": 0.08334306398879028, "grad_norm": 0.6143951416015625, "learning_rate": 8.330414477524811e-06, "loss": 0.2794, "step": 2855 }, { "epoch": 0.08337225595516114, "grad_norm": 0.8910630941390991, "learning_rate": 8.333333333333334e-06, "loss": 0.254, "step": 2856 }, { "epoch": 0.083401447921532, "grad_norm": 0.5994424819946289, "learning_rate": 8.336252189141856e-06, "loss": 0.3084, "step": 2857 }, { "epoch": 0.08343063988790285, "grad_norm": 0.5972793102264404, "learning_rate": 8.33917104495038e-06, "loss": 0.2705, "step": 2858 }, { "epoch": 0.0834598318542737, "grad_norm": 0.5392452478408813, "learning_rate": 8.342089900758903e-06, "loss": 0.2646, "step": 2859 }, { "epoch": 0.08348902382064456, "grad_norm": 0.4861052334308624, "learning_rate": 8.345008756567427e-06, "loss": 0.253, "step": 2860 }, { "epoch": 0.08351821578701542, "grad_norm": 0.5420800447463989, "learning_rate": 8.34792761237595e-06, "loss": 0.2623, "step": 2861 }, { "epoch": 0.08354740775338627, "grad_norm": 0.5106733441352844, "learning_rate": 8.350846468184472e-06, "loss": 0.2655, "step": 2862 }, { "epoch": 0.08357659971975712, "grad_norm": 0.4861440062522888, "learning_rate": 8.353765323992995e-06, "loss": 0.2559, "step": 2863 }, { "epoch": 0.08360579168612797, "grad_norm": 0.4385695159435272, "learning_rate": 8.356684179801519e-06, "loss": 0.2283, "step": 2864 }, { "epoch": 0.08363498365249883, "grad_norm": 0.45936375856399536, "learning_rate": 8.359603035610041e-06, "loss": 0.2507, "step": 2865 }, { "epoch": 0.08366417561886969, "grad_norm": 0.5170976519584656, "learning_rate": 8.362521891418565e-06, "loss": 0.261, "step": 2866 }, { "epoch": 0.08369336758524054, "grad_norm": 0.5489141345024109, "learning_rate": 8.365440747227088e-06, "loss": 0.2964, "step": 2867 }, { "epoch": 0.0837225595516114, "grad_norm": 0.47468650341033936, "learning_rate": 8.36835960303561e-06, "loss": 0.2274, "step": 2868 }, { "epoch": 0.08375175151798225, "grad_norm": 0.4827100932598114, "learning_rate": 8.371278458844135e-06, "loss": 0.2344, "step": 2869 }, { "epoch": 0.08378094348435311, "grad_norm": 0.45578935742378235, "learning_rate": 8.374197314652657e-06, "loss": 0.2013, "step": 2870 }, { "epoch": 0.08381013545072397, "grad_norm": 0.44458243250846863, "learning_rate": 8.37711617046118e-06, "loss": 0.244, "step": 2871 }, { "epoch": 0.08383932741709482, "grad_norm": 0.5105695128440857, "learning_rate": 8.380035026269702e-06, "loss": 0.2294, "step": 2872 }, { "epoch": 0.08386851938346566, "grad_norm": 0.5154178142547607, "learning_rate": 8.382953882078226e-06, "loss": 0.2031, "step": 2873 }, { "epoch": 0.08389771134983652, "grad_norm": 0.5010836720466614, "learning_rate": 8.385872737886749e-06, "loss": 0.2548, "step": 2874 }, { "epoch": 0.08392690331620738, "grad_norm": 0.5203216671943665, "learning_rate": 8.388791593695273e-06, "loss": 0.2969, "step": 2875 }, { "epoch": 0.08395609528257823, "grad_norm": 0.4282419979572296, "learning_rate": 8.391710449503795e-06, "loss": 0.2073, "step": 2876 }, { "epoch": 0.08398528724894909, "grad_norm": 0.852224588394165, "learning_rate": 8.394629305312318e-06, "loss": 0.2753, "step": 2877 }, { "epoch": 0.08401447921531995, "grad_norm": 0.4634009897708893, "learning_rate": 8.39754816112084e-06, "loss": 0.2413, "step": 2878 }, { "epoch": 0.0840436711816908, "grad_norm": 0.6490116715431213, "learning_rate": 8.400467016929365e-06, "loss": 0.2573, "step": 2879 }, { "epoch": 0.08407286314806166, "grad_norm": 0.46479466557502747, "learning_rate": 8.403385872737887e-06, "loss": 0.2148, "step": 2880 }, { "epoch": 0.08410205511443251, "grad_norm": 0.486908495426178, "learning_rate": 8.406304728546411e-06, "loss": 0.2727, "step": 2881 }, { "epoch": 0.08413124708080336, "grad_norm": 0.5409364104270935, "learning_rate": 8.409223584354934e-06, "loss": 0.2415, "step": 2882 }, { "epoch": 0.08416043904717421, "grad_norm": 0.6510483622550964, "learning_rate": 8.412142440163456e-06, "loss": 0.2898, "step": 2883 }, { "epoch": 0.08418963101354507, "grad_norm": 0.4423368573188782, "learning_rate": 8.41506129597198e-06, "loss": 0.2355, "step": 2884 }, { "epoch": 0.08421882297991592, "grad_norm": 0.4820568859577179, "learning_rate": 8.417980151780503e-06, "loss": 0.2301, "step": 2885 }, { "epoch": 0.08424801494628678, "grad_norm": 0.4289892315864563, "learning_rate": 8.420899007589025e-06, "loss": 0.2423, "step": 2886 }, { "epoch": 0.08427720691265764, "grad_norm": 0.5562462210655212, "learning_rate": 8.423817863397548e-06, "loss": 0.2423, "step": 2887 }, { "epoch": 0.0843063988790285, "grad_norm": 0.4050891101360321, "learning_rate": 8.426736719206072e-06, "loss": 0.1705, "step": 2888 }, { "epoch": 0.08433559084539935, "grad_norm": 0.4876393973827362, "learning_rate": 8.429655575014595e-06, "loss": 0.2312, "step": 2889 }, { "epoch": 0.0843647828117702, "grad_norm": 0.4585226774215698, "learning_rate": 8.432574430823119e-06, "loss": 0.2574, "step": 2890 }, { "epoch": 0.08439397477814106, "grad_norm": 0.6360492706298828, "learning_rate": 8.435493286631641e-06, "loss": 0.3103, "step": 2891 }, { "epoch": 0.0844231667445119, "grad_norm": 0.5284892320632935, "learning_rate": 8.438412142440164e-06, "loss": 0.2284, "step": 2892 }, { "epoch": 0.08445235871088276, "grad_norm": 0.38842254877090454, "learning_rate": 8.441330998248686e-06, "loss": 0.2666, "step": 2893 }, { "epoch": 0.08448155067725362, "grad_norm": 0.4409704804420471, "learning_rate": 8.44424985405721e-06, "loss": 0.2369, "step": 2894 }, { "epoch": 0.08451074264362447, "grad_norm": 0.5329245924949646, "learning_rate": 8.447168709865733e-06, "loss": 0.3018, "step": 2895 }, { "epoch": 0.08453993460999533, "grad_norm": 0.5579510927200317, "learning_rate": 8.450087565674257e-06, "loss": 0.2442, "step": 2896 }, { "epoch": 0.08456912657636619, "grad_norm": 0.48256298899650574, "learning_rate": 8.45300642148278e-06, "loss": 0.268, "step": 2897 }, { "epoch": 0.08459831854273704, "grad_norm": 0.45973601937294006, "learning_rate": 8.455925277291302e-06, "loss": 0.2418, "step": 2898 }, { "epoch": 0.0846275105091079, "grad_norm": 0.4705235958099365, "learning_rate": 8.458844133099826e-06, "loss": 0.2761, "step": 2899 }, { "epoch": 0.08465670247547875, "grad_norm": 0.4504770338535309, "learning_rate": 8.461762988908349e-06, "loss": 0.2868, "step": 2900 }, { "epoch": 0.0846858944418496, "grad_norm": 0.5302143096923828, "learning_rate": 8.464681844716871e-06, "loss": 0.2615, "step": 2901 }, { "epoch": 0.08471508640822045, "grad_norm": 0.4400174915790558, "learning_rate": 8.467600700525394e-06, "loss": 0.2559, "step": 2902 }, { "epoch": 0.08474427837459131, "grad_norm": 0.5418529510498047, "learning_rate": 8.470519556333918e-06, "loss": 0.2502, "step": 2903 }, { "epoch": 0.08477347034096216, "grad_norm": 0.42220020294189453, "learning_rate": 8.47343841214244e-06, "loss": 0.1897, "step": 2904 }, { "epoch": 0.08480266230733302, "grad_norm": 0.4726533591747284, "learning_rate": 8.476357267950965e-06, "loss": 0.2438, "step": 2905 }, { "epoch": 0.08483185427370388, "grad_norm": 0.48740530014038086, "learning_rate": 8.479276123759487e-06, "loss": 0.2934, "step": 2906 }, { "epoch": 0.08486104624007473, "grad_norm": 0.5102987289428711, "learning_rate": 8.48219497956801e-06, "loss": 0.2866, "step": 2907 }, { "epoch": 0.08489023820644559, "grad_norm": 0.4545985162258148, "learning_rate": 8.485113835376532e-06, "loss": 0.2815, "step": 2908 }, { "epoch": 0.08491943017281645, "grad_norm": 0.5019395351409912, "learning_rate": 8.488032691185056e-06, "loss": 0.2779, "step": 2909 }, { "epoch": 0.0849486221391873, "grad_norm": 0.4128727316856384, "learning_rate": 8.490951546993579e-06, "loss": 0.2732, "step": 2910 }, { "epoch": 0.08497781410555814, "grad_norm": 0.45494532585144043, "learning_rate": 8.493870402802103e-06, "loss": 0.2375, "step": 2911 }, { "epoch": 0.085007006071929, "grad_norm": 0.38898396492004395, "learning_rate": 8.496789258610626e-06, "loss": 0.2276, "step": 2912 }, { "epoch": 0.08503619803829986, "grad_norm": 0.4356120228767395, "learning_rate": 8.499708114419148e-06, "loss": 0.2551, "step": 2913 }, { "epoch": 0.08506539000467071, "grad_norm": 0.7382121086120605, "learning_rate": 8.50262697022767e-06, "loss": 0.2359, "step": 2914 }, { "epoch": 0.08509458197104157, "grad_norm": 0.48262259364128113, "learning_rate": 8.505545826036195e-06, "loss": 0.2672, "step": 2915 }, { "epoch": 0.08512377393741243, "grad_norm": 0.46176230907440186, "learning_rate": 8.508464681844719e-06, "loss": 0.1963, "step": 2916 }, { "epoch": 0.08515296590378328, "grad_norm": 0.4152999818325043, "learning_rate": 8.511383537653241e-06, "loss": 0.2693, "step": 2917 }, { "epoch": 0.08518215787015414, "grad_norm": 0.41845718026161194, "learning_rate": 8.514302393461764e-06, "loss": 0.2194, "step": 2918 }, { "epoch": 0.085211349836525, "grad_norm": 0.6070670485496521, "learning_rate": 8.517221249270286e-06, "loss": 0.2564, "step": 2919 }, { "epoch": 0.08524054180289584, "grad_norm": 0.6542941927909851, "learning_rate": 8.52014010507881e-06, "loss": 0.244, "step": 2920 }, { "epoch": 0.08526973376926669, "grad_norm": 0.4413417875766754, "learning_rate": 8.523058960887333e-06, "loss": 0.2331, "step": 2921 }, { "epoch": 0.08529892573563755, "grad_norm": 0.4594513773918152, "learning_rate": 8.525977816695856e-06, "loss": 0.251, "step": 2922 }, { "epoch": 0.0853281177020084, "grad_norm": 0.3796181380748749, "learning_rate": 8.528896672504378e-06, "loss": 0.1995, "step": 2923 }, { "epoch": 0.08535730966837926, "grad_norm": 0.8174608945846558, "learning_rate": 8.531815528312902e-06, "loss": 0.2327, "step": 2924 }, { "epoch": 0.08538650163475012, "grad_norm": 0.5179173946380615, "learning_rate": 8.534734384121425e-06, "loss": 0.2457, "step": 2925 }, { "epoch": 0.08541569360112097, "grad_norm": 0.5348690152168274, "learning_rate": 8.537653239929949e-06, "loss": 0.2664, "step": 2926 }, { "epoch": 0.08544488556749183, "grad_norm": 0.446158230304718, "learning_rate": 8.540572095738471e-06, "loss": 0.2509, "step": 2927 }, { "epoch": 0.08547407753386269, "grad_norm": 0.5363523960113525, "learning_rate": 8.543490951546994e-06, "loss": 0.261, "step": 2928 }, { "epoch": 0.08550326950023354, "grad_norm": 0.478344589471817, "learning_rate": 8.546409807355516e-06, "loss": 0.2606, "step": 2929 }, { "epoch": 0.08553246146660438, "grad_norm": 0.5006062984466553, "learning_rate": 8.54932866316404e-06, "loss": 0.2409, "step": 2930 }, { "epoch": 0.08556165343297524, "grad_norm": 0.8124003410339355, "learning_rate": 8.552247518972565e-06, "loss": 0.2704, "step": 2931 }, { "epoch": 0.0855908453993461, "grad_norm": 0.4269866943359375, "learning_rate": 8.555166374781087e-06, "loss": 0.3049, "step": 2932 }, { "epoch": 0.08562003736571695, "grad_norm": 0.48170432448387146, "learning_rate": 8.55808523058961e-06, "loss": 0.3169, "step": 2933 }, { "epoch": 0.08564922933208781, "grad_norm": 0.5259625911712646, "learning_rate": 8.561004086398132e-06, "loss": 0.2056, "step": 2934 }, { "epoch": 0.08567842129845867, "grad_norm": 0.45721176266670227, "learning_rate": 8.563922942206656e-06, "loss": 0.26, "step": 2935 }, { "epoch": 0.08570761326482952, "grad_norm": 0.4622240364551544, "learning_rate": 8.566841798015179e-06, "loss": 0.2736, "step": 2936 }, { "epoch": 0.08573680523120038, "grad_norm": 0.49445289373397827, "learning_rate": 8.569760653823701e-06, "loss": 0.2586, "step": 2937 }, { "epoch": 0.08576599719757123, "grad_norm": 0.5232610106468201, "learning_rate": 8.572679509632224e-06, "loss": 0.2638, "step": 2938 }, { "epoch": 0.08579518916394209, "grad_norm": 0.48426342010498047, "learning_rate": 8.575598365440748e-06, "loss": 0.2887, "step": 2939 }, { "epoch": 0.08582438113031293, "grad_norm": 0.547318160533905, "learning_rate": 8.57851722124927e-06, "loss": 0.2734, "step": 2940 }, { "epoch": 0.08585357309668379, "grad_norm": 0.537713348865509, "learning_rate": 8.581436077057795e-06, "loss": 0.2452, "step": 2941 }, { "epoch": 0.08588276506305464, "grad_norm": 0.52251136302948, "learning_rate": 8.584354932866317e-06, "loss": 0.2617, "step": 2942 }, { "epoch": 0.0859119570294255, "grad_norm": 0.45462071895599365, "learning_rate": 8.58727378867484e-06, "loss": 0.2075, "step": 2943 }, { "epoch": 0.08594114899579636, "grad_norm": 0.3830241560935974, "learning_rate": 8.590192644483362e-06, "loss": 0.2319, "step": 2944 }, { "epoch": 0.08597034096216721, "grad_norm": 0.8962845206260681, "learning_rate": 8.593111500291886e-06, "loss": 0.2265, "step": 2945 }, { "epoch": 0.08599953292853807, "grad_norm": 0.5162209272384644, "learning_rate": 8.596030356100409e-06, "loss": 0.2763, "step": 2946 }, { "epoch": 0.08602872489490893, "grad_norm": 0.7441653609275818, "learning_rate": 8.598949211908933e-06, "loss": 0.2212, "step": 2947 }, { "epoch": 0.08605791686127978, "grad_norm": 0.507285475730896, "learning_rate": 8.601868067717456e-06, "loss": 0.2996, "step": 2948 }, { "epoch": 0.08608710882765062, "grad_norm": 0.4070165157318115, "learning_rate": 8.604786923525978e-06, "loss": 0.2126, "step": 2949 }, { "epoch": 0.08611630079402148, "grad_norm": 0.5036008358001709, "learning_rate": 8.607705779334502e-06, "loss": 0.2191, "step": 2950 }, { "epoch": 0.08614549276039234, "grad_norm": 0.4656262695789337, "learning_rate": 8.610624635143025e-06, "loss": 0.2221, "step": 2951 }, { "epoch": 0.08617468472676319, "grad_norm": 0.507318377494812, "learning_rate": 8.613543490951547e-06, "loss": 0.2992, "step": 2952 }, { "epoch": 0.08620387669313405, "grad_norm": 0.4850507378578186, "learning_rate": 8.61646234676007e-06, "loss": 0.2265, "step": 2953 }, { "epoch": 0.0862330686595049, "grad_norm": 0.8085854649543762, "learning_rate": 8.619381202568594e-06, "loss": 0.2799, "step": 2954 }, { "epoch": 0.08626226062587576, "grad_norm": 0.5682385563850403, "learning_rate": 8.622300058377116e-06, "loss": 0.3153, "step": 2955 }, { "epoch": 0.08629145259224662, "grad_norm": 0.456381618976593, "learning_rate": 8.62521891418564e-06, "loss": 0.2219, "step": 2956 }, { "epoch": 0.08632064455861747, "grad_norm": 0.44390979409217834, "learning_rate": 8.628137769994163e-06, "loss": 0.2279, "step": 2957 }, { "epoch": 0.08634983652498833, "grad_norm": 0.5502021312713623, "learning_rate": 8.631056625802686e-06, "loss": 0.2601, "step": 2958 }, { "epoch": 0.08637902849135917, "grad_norm": 0.47142621874809265, "learning_rate": 8.633975481611208e-06, "loss": 0.2492, "step": 2959 }, { "epoch": 0.08640822045773003, "grad_norm": 0.43093088269233704, "learning_rate": 8.636894337419732e-06, "loss": 0.2067, "step": 2960 }, { "epoch": 0.08643741242410088, "grad_norm": 0.6404740214347839, "learning_rate": 8.639813193228255e-06, "loss": 0.2831, "step": 2961 }, { "epoch": 0.08646660439047174, "grad_norm": 0.46287062764167786, "learning_rate": 8.642732049036779e-06, "loss": 0.2185, "step": 2962 }, { "epoch": 0.0864957963568426, "grad_norm": 0.46240442991256714, "learning_rate": 8.645650904845301e-06, "loss": 0.2451, "step": 2963 }, { "epoch": 0.08652498832321345, "grad_norm": 0.44517982006073, "learning_rate": 8.648569760653824e-06, "loss": 0.2082, "step": 2964 }, { "epoch": 0.08655418028958431, "grad_norm": 0.4541594684123993, "learning_rate": 8.651488616462348e-06, "loss": 0.2115, "step": 2965 }, { "epoch": 0.08658337225595517, "grad_norm": 0.5466781854629517, "learning_rate": 8.65440747227087e-06, "loss": 0.272, "step": 2966 }, { "epoch": 0.08661256422232602, "grad_norm": 0.5148000121116638, "learning_rate": 8.657326328079395e-06, "loss": 0.2609, "step": 2967 }, { "epoch": 0.08664175618869686, "grad_norm": 0.5073022842407227, "learning_rate": 8.660245183887916e-06, "loss": 0.3282, "step": 2968 }, { "epoch": 0.08667094815506772, "grad_norm": 0.5635277032852173, "learning_rate": 8.66316403969644e-06, "loss": 0.2821, "step": 2969 }, { "epoch": 0.08670014012143858, "grad_norm": 0.49108776450157166, "learning_rate": 8.666082895504962e-06, "loss": 0.2105, "step": 2970 }, { "epoch": 0.08672933208780943, "grad_norm": 0.46292582154273987, "learning_rate": 8.669001751313486e-06, "loss": 0.2322, "step": 2971 }, { "epoch": 0.08675852405418029, "grad_norm": 0.6121463775634766, "learning_rate": 8.671920607122009e-06, "loss": 0.2896, "step": 2972 }, { "epoch": 0.08678771602055114, "grad_norm": 0.47405770421028137, "learning_rate": 8.674839462930531e-06, "loss": 0.2537, "step": 2973 }, { "epoch": 0.086816907986922, "grad_norm": 0.6026052832603455, "learning_rate": 8.677758318739054e-06, "loss": 0.2255, "step": 2974 }, { "epoch": 0.08684609995329286, "grad_norm": 0.4046015739440918, "learning_rate": 8.680677174547578e-06, "loss": 0.1952, "step": 2975 }, { "epoch": 0.08687529191966371, "grad_norm": 0.5013411641120911, "learning_rate": 8.6835960303561e-06, "loss": 0.2579, "step": 2976 }, { "epoch": 0.08690448388603457, "grad_norm": 0.4399409592151642, "learning_rate": 8.686514886164625e-06, "loss": 0.2613, "step": 2977 }, { "epoch": 0.08693367585240541, "grad_norm": 0.443039208650589, "learning_rate": 8.689433741973147e-06, "loss": 0.2222, "step": 2978 }, { "epoch": 0.08696286781877627, "grad_norm": 0.4958497881889343, "learning_rate": 8.69235259778167e-06, "loss": 0.2356, "step": 2979 }, { "epoch": 0.08699205978514712, "grad_norm": 0.6909356713294983, "learning_rate": 8.695271453590194e-06, "loss": 0.2623, "step": 2980 }, { "epoch": 0.08702125175151798, "grad_norm": 0.6618146896362305, "learning_rate": 8.698190309398717e-06, "loss": 0.2611, "step": 2981 }, { "epoch": 0.08705044371788884, "grad_norm": 0.7998874187469482, "learning_rate": 8.70110916520724e-06, "loss": 0.2642, "step": 2982 }, { "epoch": 0.08707963568425969, "grad_norm": 0.6044370532035828, "learning_rate": 8.704028021015763e-06, "loss": 0.2563, "step": 2983 }, { "epoch": 0.08710882765063055, "grad_norm": 0.41808295249938965, "learning_rate": 8.706946876824286e-06, "loss": 0.2158, "step": 2984 }, { "epoch": 0.0871380196170014, "grad_norm": 0.5071430206298828, "learning_rate": 8.709865732632808e-06, "loss": 0.2762, "step": 2985 }, { "epoch": 0.08716721158337226, "grad_norm": 0.5104919075965881, "learning_rate": 8.712784588441332e-06, "loss": 0.2447, "step": 2986 }, { "epoch": 0.0871964035497431, "grad_norm": 0.4484914541244507, "learning_rate": 8.715703444249855e-06, "loss": 0.2394, "step": 2987 }, { "epoch": 0.08722559551611396, "grad_norm": 0.5754461884498596, "learning_rate": 8.718622300058377e-06, "loss": 0.2495, "step": 2988 }, { "epoch": 0.08725478748248482, "grad_norm": 0.5936976671218872, "learning_rate": 8.7215411558669e-06, "loss": 0.2698, "step": 2989 }, { "epoch": 0.08728397944885567, "grad_norm": 0.4449722170829773, "learning_rate": 8.724460011675424e-06, "loss": 0.2498, "step": 2990 }, { "epoch": 0.08731317141522653, "grad_norm": 0.7705547213554382, "learning_rate": 8.727378867483947e-06, "loss": 0.2731, "step": 2991 }, { "epoch": 0.08734236338159738, "grad_norm": 0.4083516299724579, "learning_rate": 8.73029772329247e-06, "loss": 0.2709, "step": 2992 }, { "epoch": 0.08737155534796824, "grad_norm": 0.39080551266670227, "learning_rate": 8.733216579100993e-06, "loss": 0.2335, "step": 2993 }, { "epoch": 0.0874007473143391, "grad_norm": 0.4318942427635193, "learning_rate": 8.736135434909516e-06, "loss": 0.2157, "step": 2994 }, { "epoch": 0.08742993928070995, "grad_norm": 0.7025747299194336, "learning_rate": 8.73905429071804e-06, "loss": 0.2289, "step": 2995 }, { "epoch": 0.08745913124708081, "grad_norm": 0.622031033039093, "learning_rate": 8.741973146526562e-06, "loss": 0.3075, "step": 2996 }, { "epoch": 0.08748832321345165, "grad_norm": 0.4877459704875946, "learning_rate": 8.744892002335087e-06, "loss": 0.2513, "step": 2997 }, { "epoch": 0.08751751517982251, "grad_norm": 0.5033924579620361, "learning_rate": 8.747810858143609e-06, "loss": 0.2686, "step": 2998 }, { "epoch": 0.08754670714619336, "grad_norm": 0.6722947955131531, "learning_rate": 8.750729713952132e-06, "loss": 0.2976, "step": 2999 }, { "epoch": 0.08757589911256422, "grad_norm": 0.4511929154396057, "learning_rate": 8.753648569760654e-06, "loss": 0.2532, "step": 3000 }, { "epoch": 0.08760509107893508, "grad_norm": 0.4369508624076843, "learning_rate": 8.756567425569178e-06, "loss": 0.2251, "step": 3001 }, { "epoch": 0.08763428304530593, "grad_norm": 0.4559178650379181, "learning_rate": 8.7594862813777e-06, "loss": 0.2885, "step": 3002 }, { "epoch": 0.08766347501167679, "grad_norm": 0.46219930052757263, "learning_rate": 8.762405137186223e-06, "loss": 0.2553, "step": 3003 }, { "epoch": 0.08769266697804765, "grad_norm": 0.602872908115387, "learning_rate": 8.765323992994746e-06, "loss": 0.3003, "step": 3004 }, { "epoch": 0.0877218589444185, "grad_norm": 0.39920511841773987, "learning_rate": 8.76824284880327e-06, "loss": 0.2338, "step": 3005 }, { "epoch": 0.08775105091078936, "grad_norm": 0.4903857707977295, "learning_rate": 8.771161704611792e-06, "loss": 0.2615, "step": 3006 }, { "epoch": 0.0877802428771602, "grad_norm": 0.5215909481048584, "learning_rate": 8.774080560420317e-06, "loss": 0.3006, "step": 3007 }, { "epoch": 0.08780943484353106, "grad_norm": 0.48051512241363525, "learning_rate": 8.776999416228839e-06, "loss": 0.3017, "step": 3008 }, { "epoch": 0.08783862680990191, "grad_norm": 0.44857877492904663, "learning_rate": 8.779918272037362e-06, "loss": 0.2295, "step": 3009 }, { "epoch": 0.08786781877627277, "grad_norm": 0.4902403652667999, "learning_rate": 8.782837127845884e-06, "loss": 0.2691, "step": 3010 }, { "epoch": 0.08789701074264362, "grad_norm": 0.48354923725128174, "learning_rate": 8.785755983654408e-06, "loss": 0.2581, "step": 3011 }, { "epoch": 0.08792620270901448, "grad_norm": 0.9056300520896912, "learning_rate": 8.788674839462932e-06, "loss": 0.2943, "step": 3012 }, { "epoch": 0.08795539467538534, "grad_norm": 0.43650388717651367, "learning_rate": 8.791593695271455e-06, "loss": 0.2395, "step": 3013 }, { "epoch": 0.0879845866417562, "grad_norm": 0.5205507874488831, "learning_rate": 8.794512551079977e-06, "loss": 0.2414, "step": 3014 }, { "epoch": 0.08801377860812705, "grad_norm": 0.46773940324783325, "learning_rate": 8.7974314068885e-06, "loss": 0.2527, "step": 3015 }, { "epoch": 0.08804297057449789, "grad_norm": 0.4075978994369507, "learning_rate": 8.800350262697024e-06, "loss": 0.2192, "step": 3016 }, { "epoch": 0.08807216254086875, "grad_norm": 0.4527623951435089, "learning_rate": 8.803269118505547e-06, "loss": 0.3109, "step": 3017 }, { "epoch": 0.0881013545072396, "grad_norm": 0.45724719762802124, "learning_rate": 8.806187974314069e-06, "loss": 0.223, "step": 3018 }, { "epoch": 0.08813054647361046, "grad_norm": 0.39154624938964844, "learning_rate": 8.809106830122592e-06, "loss": 0.1979, "step": 3019 }, { "epoch": 0.08815973843998132, "grad_norm": 0.6038931012153625, "learning_rate": 8.812025685931116e-06, "loss": 0.252, "step": 3020 }, { "epoch": 0.08818893040635217, "grad_norm": 0.47876688838005066, "learning_rate": 8.814944541739638e-06, "loss": 0.316, "step": 3021 }, { "epoch": 0.08821812237272303, "grad_norm": 0.45430973172187805, "learning_rate": 8.817863397548162e-06, "loss": 0.2564, "step": 3022 }, { "epoch": 0.08824731433909389, "grad_norm": 0.4739755690097809, "learning_rate": 8.820782253356685e-06, "loss": 0.2326, "step": 3023 }, { "epoch": 0.08827650630546474, "grad_norm": 0.4576970636844635, "learning_rate": 8.823701109165207e-06, "loss": 0.2601, "step": 3024 }, { "epoch": 0.0883056982718356, "grad_norm": 0.44889548420906067, "learning_rate": 8.82661996497373e-06, "loss": 0.248, "step": 3025 }, { "epoch": 0.08833489023820644, "grad_norm": 0.5420768857002258, "learning_rate": 8.829538820782254e-06, "loss": 0.277, "step": 3026 }, { "epoch": 0.0883640822045773, "grad_norm": 2.7366466522216797, "learning_rate": 8.832457676590778e-06, "loss": 0.2737, "step": 3027 }, { "epoch": 0.08839327417094815, "grad_norm": 0.4387436509132385, "learning_rate": 8.8353765323993e-06, "loss": 0.2693, "step": 3028 }, { "epoch": 0.08842246613731901, "grad_norm": 0.45922061800956726, "learning_rate": 8.838295388207823e-06, "loss": 0.2484, "step": 3029 }, { "epoch": 0.08845165810368986, "grad_norm": 0.49348184466362, "learning_rate": 8.841214244016346e-06, "loss": 0.2838, "step": 3030 }, { "epoch": 0.08848085007006072, "grad_norm": 0.45904606580734253, "learning_rate": 8.84413309982487e-06, "loss": 0.2314, "step": 3031 }, { "epoch": 0.08851004203643158, "grad_norm": 0.4504488408565521, "learning_rate": 8.847051955633392e-06, "loss": 0.2536, "step": 3032 }, { "epoch": 0.08853923400280243, "grad_norm": 0.44258788228034973, "learning_rate": 8.849970811441917e-06, "loss": 0.2688, "step": 3033 }, { "epoch": 0.08856842596917329, "grad_norm": 0.5086331367492676, "learning_rate": 8.852889667250439e-06, "loss": 0.2583, "step": 3034 }, { "epoch": 0.08859761793554413, "grad_norm": 0.47034934163093567, "learning_rate": 8.855808523058962e-06, "loss": 0.23, "step": 3035 }, { "epoch": 0.08862680990191499, "grad_norm": 0.39332011342048645, "learning_rate": 8.858727378867484e-06, "loss": 0.2287, "step": 3036 }, { "epoch": 0.08865600186828584, "grad_norm": 0.4508993923664093, "learning_rate": 8.861646234676008e-06, "loss": 0.3016, "step": 3037 }, { "epoch": 0.0886851938346567, "grad_norm": 0.4461565613746643, "learning_rate": 8.86456509048453e-06, "loss": 0.2667, "step": 3038 }, { "epoch": 0.08871438580102756, "grad_norm": 0.48242878913879395, "learning_rate": 8.867483946293053e-06, "loss": 0.2357, "step": 3039 }, { "epoch": 0.08874357776739841, "grad_norm": 0.554309070110321, "learning_rate": 8.870402802101576e-06, "loss": 0.2853, "step": 3040 }, { "epoch": 0.08877276973376927, "grad_norm": 0.4667466878890991, "learning_rate": 8.8733216579101e-06, "loss": 0.2439, "step": 3041 }, { "epoch": 0.08880196170014013, "grad_norm": 0.48767733573913574, "learning_rate": 8.876240513718622e-06, "loss": 0.2746, "step": 3042 }, { "epoch": 0.08883115366651098, "grad_norm": 0.6105336546897888, "learning_rate": 8.879159369527147e-06, "loss": 0.2272, "step": 3043 }, { "epoch": 0.08886034563288184, "grad_norm": 0.46214956045150757, "learning_rate": 8.882078225335669e-06, "loss": 0.2603, "step": 3044 }, { "epoch": 0.08888953759925268, "grad_norm": 0.46923068165779114, "learning_rate": 8.884997081144192e-06, "loss": 0.2147, "step": 3045 }, { "epoch": 0.08891872956562354, "grad_norm": 0.39373132586479187, "learning_rate": 8.887915936952716e-06, "loss": 0.2025, "step": 3046 }, { "epoch": 0.08894792153199439, "grad_norm": 0.5359212160110474, "learning_rate": 8.890834792761238e-06, "loss": 0.3323, "step": 3047 }, { "epoch": 0.08897711349836525, "grad_norm": 0.44154027104377747, "learning_rate": 8.893753648569763e-06, "loss": 0.27, "step": 3048 }, { "epoch": 0.0890063054647361, "grad_norm": 0.4746139645576477, "learning_rate": 8.896672504378285e-06, "loss": 0.2235, "step": 3049 }, { "epoch": 0.08903549743110696, "grad_norm": 0.502882182598114, "learning_rate": 8.899591360186807e-06, "loss": 0.267, "step": 3050 }, { "epoch": 0.08906468939747782, "grad_norm": 0.4239939749240875, "learning_rate": 8.90251021599533e-06, "loss": 0.2514, "step": 3051 }, { "epoch": 0.08909388136384867, "grad_norm": 0.46849802136421204, "learning_rate": 8.905429071803854e-06, "loss": 0.2438, "step": 3052 }, { "epoch": 0.08912307333021953, "grad_norm": 0.3903239369392395, "learning_rate": 8.908347927612377e-06, "loss": 0.2603, "step": 3053 }, { "epoch": 0.08915226529659037, "grad_norm": 0.43206357955932617, "learning_rate": 8.9112667834209e-06, "loss": 0.2597, "step": 3054 }, { "epoch": 0.08918145726296123, "grad_norm": 0.49428591132164, "learning_rate": 8.914185639229422e-06, "loss": 0.2919, "step": 3055 }, { "epoch": 0.08921064922933208, "grad_norm": 0.4315063953399658, "learning_rate": 8.917104495037946e-06, "loss": 0.2455, "step": 3056 }, { "epoch": 0.08923984119570294, "grad_norm": 0.4657186269760132, "learning_rate": 8.920023350846468e-06, "loss": 0.2649, "step": 3057 }, { "epoch": 0.0892690331620738, "grad_norm": 0.43242281675338745, "learning_rate": 8.922942206654993e-06, "loss": 0.243, "step": 3058 }, { "epoch": 0.08929822512844465, "grad_norm": 0.4011595547199249, "learning_rate": 8.925861062463515e-06, "loss": 0.2241, "step": 3059 }, { "epoch": 0.08932741709481551, "grad_norm": 0.4061715602874756, "learning_rate": 8.928779918272038e-06, "loss": 0.2399, "step": 3060 }, { "epoch": 0.08935660906118637, "grad_norm": 0.40183621644973755, "learning_rate": 8.931698774080562e-06, "loss": 0.2308, "step": 3061 }, { "epoch": 0.08938580102755722, "grad_norm": 0.571700930595398, "learning_rate": 8.934617629889084e-06, "loss": 0.2552, "step": 3062 }, { "epoch": 0.08941499299392808, "grad_norm": 0.4752659499645233, "learning_rate": 8.937536485697608e-06, "loss": 0.2383, "step": 3063 }, { "epoch": 0.08944418496029892, "grad_norm": 0.44675907492637634, "learning_rate": 8.940455341506131e-06, "loss": 0.2364, "step": 3064 }, { "epoch": 0.08947337692666978, "grad_norm": 0.44750264286994934, "learning_rate": 8.943374197314653e-06, "loss": 0.2608, "step": 3065 }, { "epoch": 0.08950256889304063, "grad_norm": 0.5464669466018677, "learning_rate": 8.946293053123176e-06, "loss": 0.2247, "step": 3066 }, { "epoch": 0.08953176085941149, "grad_norm": 0.46874937415122986, "learning_rate": 8.9492119089317e-06, "loss": 0.2275, "step": 3067 }, { "epoch": 0.08956095282578234, "grad_norm": 0.5204723477363586, "learning_rate": 8.952130764740223e-06, "loss": 0.2474, "step": 3068 }, { "epoch": 0.0895901447921532, "grad_norm": 0.6279264688491821, "learning_rate": 8.955049620548745e-06, "loss": 0.269, "step": 3069 }, { "epoch": 0.08961933675852406, "grad_norm": 0.404547780752182, "learning_rate": 8.957968476357268e-06, "loss": 0.2375, "step": 3070 }, { "epoch": 0.08964852872489491, "grad_norm": 0.6993761658668518, "learning_rate": 8.960887332165792e-06, "loss": 0.3042, "step": 3071 }, { "epoch": 0.08967772069126577, "grad_norm": 0.4356747567653656, "learning_rate": 8.963806187974314e-06, "loss": 0.272, "step": 3072 }, { "epoch": 0.08970691265763661, "grad_norm": 0.7418234348297119, "learning_rate": 8.966725043782838e-06, "loss": 0.2648, "step": 3073 }, { "epoch": 0.08973610462400747, "grad_norm": 0.5535861253738403, "learning_rate": 8.969643899591361e-06, "loss": 0.3019, "step": 3074 }, { "epoch": 0.08976529659037832, "grad_norm": 0.41572967171669006, "learning_rate": 8.972562755399883e-06, "loss": 0.3112, "step": 3075 }, { "epoch": 0.08979448855674918, "grad_norm": 0.41728904843330383, "learning_rate": 8.975481611208408e-06, "loss": 0.2787, "step": 3076 }, { "epoch": 0.08982368052312004, "grad_norm": 0.48563650250434875, "learning_rate": 8.97840046701693e-06, "loss": 0.2672, "step": 3077 }, { "epoch": 0.08985287248949089, "grad_norm": 0.42268624901771545, "learning_rate": 8.981319322825454e-06, "loss": 0.2428, "step": 3078 }, { "epoch": 0.08988206445586175, "grad_norm": 0.8768842816352844, "learning_rate": 8.984238178633977e-06, "loss": 0.2334, "step": 3079 }, { "epoch": 0.0899112564222326, "grad_norm": 0.4350997805595398, "learning_rate": 8.9871570344425e-06, "loss": 0.2967, "step": 3080 }, { "epoch": 0.08994044838860346, "grad_norm": 0.42432817816734314, "learning_rate": 8.990075890251022e-06, "loss": 0.2379, "step": 3081 }, { "epoch": 0.08996964035497432, "grad_norm": 0.5496994853019714, "learning_rate": 8.992994746059546e-06, "loss": 0.2295, "step": 3082 }, { "epoch": 0.08999883232134516, "grad_norm": 0.47077855467796326, "learning_rate": 8.995913601868068e-06, "loss": 0.2767, "step": 3083 }, { "epoch": 0.09002802428771602, "grad_norm": 0.46682867407798767, "learning_rate": 8.998832457676593e-06, "loss": 0.2744, "step": 3084 }, { "epoch": 0.09005721625408687, "grad_norm": 0.4379945695400238, "learning_rate": 9.001751313485113e-06, "loss": 0.215, "step": 3085 }, { "epoch": 0.09008640822045773, "grad_norm": 0.3924766778945923, "learning_rate": 9.004670169293638e-06, "loss": 0.2269, "step": 3086 }, { "epoch": 0.09011560018682858, "grad_norm": 0.4746670126914978, "learning_rate": 9.00758902510216e-06, "loss": 0.2425, "step": 3087 }, { "epoch": 0.09014479215319944, "grad_norm": 0.5048097968101501, "learning_rate": 9.010507880910684e-06, "loss": 0.2337, "step": 3088 }, { "epoch": 0.0901739841195703, "grad_norm": 0.43133804202079773, "learning_rate": 9.013426736719207e-06, "loss": 0.2232, "step": 3089 }, { "epoch": 0.09020317608594115, "grad_norm": 0.4638466238975525, "learning_rate": 9.01634559252773e-06, "loss": 0.2634, "step": 3090 }, { "epoch": 0.09023236805231201, "grad_norm": 0.4188927710056305, "learning_rate": 9.019264448336253e-06, "loss": 0.2264, "step": 3091 }, { "epoch": 0.09026156001868287, "grad_norm": 0.3773488998413086, "learning_rate": 9.022183304144776e-06, "loss": 0.2047, "step": 3092 }, { "epoch": 0.09029075198505371, "grad_norm": 0.4707257151603699, "learning_rate": 9.0251021599533e-06, "loss": 0.3015, "step": 3093 }, { "epoch": 0.09031994395142456, "grad_norm": 0.4182581603527069, "learning_rate": 9.028021015761823e-06, "loss": 0.2279, "step": 3094 }, { "epoch": 0.09034913591779542, "grad_norm": 0.4348205327987671, "learning_rate": 9.030939871570345e-06, "loss": 0.2837, "step": 3095 }, { "epoch": 0.09037832788416628, "grad_norm": 0.43431809544563293, "learning_rate": 9.033858727378868e-06, "loss": 0.2696, "step": 3096 }, { "epoch": 0.09040751985053713, "grad_norm": 0.4739440083503723, "learning_rate": 9.036777583187392e-06, "loss": 0.2762, "step": 3097 }, { "epoch": 0.09043671181690799, "grad_norm": 0.4321894347667694, "learning_rate": 9.039696438995914e-06, "loss": 0.2751, "step": 3098 }, { "epoch": 0.09046590378327884, "grad_norm": 0.4455794394016266, "learning_rate": 9.042615294804438e-06, "loss": 0.2392, "step": 3099 }, { "epoch": 0.0904950957496497, "grad_norm": 0.48734229803085327, "learning_rate": 9.045534150612961e-06, "loss": 0.2356, "step": 3100 }, { "epoch": 0.09052428771602056, "grad_norm": 0.5087803602218628, "learning_rate": 9.048453006421483e-06, "loss": 0.2422, "step": 3101 }, { "epoch": 0.0905534796823914, "grad_norm": 0.5518165230751038, "learning_rate": 9.051371862230006e-06, "loss": 0.2803, "step": 3102 }, { "epoch": 0.09058267164876226, "grad_norm": 0.4436402916908264, "learning_rate": 9.05429071803853e-06, "loss": 0.2457, "step": 3103 }, { "epoch": 0.09061186361513311, "grad_norm": 0.4724081754684448, "learning_rate": 9.057209573847053e-06, "loss": 0.297, "step": 3104 }, { "epoch": 0.09064105558150397, "grad_norm": 0.419867604970932, "learning_rate": 9.060128429655575e-06, "loss": 0.2857, "step": 3105 }, { "epoch": 0.09067024754787482, "grad_norm": 0.4883086085319519, "learning_rate": 9.063047285464098e-06, "loss": 0.2799, "step": 3106 }, { "epoch": 0.09069943951424568, "grad_norm": 0.4780181050300598, "learning_rate": 9.065966141272622e-06, "loss": 0.2498, "step": 3107 }, { "epoch": 0.09072863148061654, "grad_norm": 0.45164161920547485, "learning_rate": 9.068884997081146e-06, "loss": 0.2572, "step": 3108 }, { "epoch": 0.09075782344698739, "grad_norm": 0.4654071629047394, "learning_rate": 9.071803852889668e-06, "loss": 0.2469, "step": 3109 }, { "epoch": 0.09078701541335825, "grad_norm": 0.495560884475708, "learning_rate": 9.074722708698191e-06, "loss": 0.2636, "step": 3110 }, { "epoch": 0.0908162073797291, "grad_norm": 0.41795215010643005, "learning_rate": 9.077641564506713e-06, "loss": 0.2331, "step": 3111 }, { "epoch": 0.09084539934609995, "grad_norm": 0.5254979133605957, "learning_rate": 9.080560420315238e-06, "loss": 0.2659, "step": 3112 }, { "epoch": 0.0908745913124708, "grad_norm": 0.4733831286430359, "learning_rate": 9.08347927612376e-06, "loss": 0.2302, "step": 3113 }, { "epoch": 0.09090378327884166, "grad_norm": 0.7711973190307617, "learning_rate": 9.086398131932284e-06, "loss": 0.3558, "step": 3114 }, { "epoch": 0.09093297524521252, "grad_norm": 0.4832947552204132, "learning_rate": 9.089316987740807e-06, "loss": 0.2324, "step": 3115 }, { "epoch": 0.09096216721158337, "grad_norm": 0.9255148768424988, "learning_rate": 9.09223584354933e-06, "loss": 0.2504, "step": 3116 }, { "epoch": 0.09099135917795423, "grad_norm": 0.44190284609794617, "learning_rate": 9.095154699357852e-06, "loss": 0.2123, "step": 3117 }, { "epoch": 0.09102055114432508, "grad_norm": 0.4036891758441925, "learning_rate": 9.098073555166376e-06, "loss": 0.2404, "step": 3118 }, { "epoch": 0.09104974311069594, "grad_norm": 0.48230066895484924, "learning_rate": 9.100992410974898e-06, "loss": 0.2421, "step": 3119 }, { "epoch": 0.0910789350770668, "grad_norm": 0.5607301592826843, "learning_rate": 9.103911266783421e-06, "loss": 0.2967, "step": 3120 }, { "epoch": 0.09110812704343764, "grad_norm": 0.40371623635292053, "learning_rate": 9.106830122591943e-06, "loss": 0.2195, "step": 3121 }, { "epoch": 0.0911373190098085, "grad_norm": 0.582599937915802, "learning_rate": 9.109748978400468e-06, "loss": 0.2817, "step": 3122 }, { "epoch": 0.09116651097617935, "grad_norm": 0.5078862309455872, "learning_rate": 9.112667834208992e-06, "loss": 0.2634, "step": 3123 }, { "epoch": 0.09119570294255021, "grad_norm": 0.6470637321472168, "learning_rate": 9.115586690017514e-06, "loss": 0.2311, "step": 3124 }, { "epoch": 0.09122489490892106, "grad_norm": 0.4570905566215515, "learning_rate": 9.118505545826037e-06, "loss": 0.2757, "step": 3125 }, { "epoch": 0.09125408687529192, "grad_norm": 0.4481227993965149, "learning_rate": 9.12142440163456e-06, "loss": 0.254, "step": 3126 }, { "epoch": 0.09128327884166278, "grad_norm": 0.556119441986084, "learning_rate": 9.124343257443084e-06, "loss": 0.2602, "step": 3127 }, { "epoch": 0.09131247080803363, "grad_norm": 0.394477903842926, "learning_rate": 9.127262113251606e-06, "loss": 0.2333, "step": 3128 }, { "epoch": 0.09134166277440449, "grad_norm": 0.5950316786766052, "learning_rate": 9.13018096906013e-06, "loss": 0.2336, "step": 3129 }, { "epoch": 0.09137085474077535, "grad_norm": 0.4806632697582245, "learning_rate": 9.133099824868653e-06, "loss": 0.2345, "step": 3130 }, { "epoch": 0.09140004670714619, "grad_norm": 0.531643271446228, "learning_rate": 9.136018680677175e-06, "loss": 0.2509, "step": 3131 }, { "epoch": 0.09142923867351704, "grad_norm": 0.4126761555671692, "learning_rate": 9.138937536485698e-06, "loss": 0.2588, "step": 3132 }, { "epoch": 0.0914584306398879, "grad_norm": 1.305901288986206, "learning_rate": 9.141856392294222e-06, "loss": 0.2738, "step": 3133 }, { "epoch": 0.09148762260625876, "grad_norm": 0.5863299369812012, "learning_rate": 9.144775248102744e-06, "loss": 0.2646, "step": 3134 }, { "epoch": 0.09151681457262961, "grad_norm": 0.4015018343925476, "learning_rate": 9.147694103911267e-06, "loss": 0.2453, "step": 3135 }, { "epoch": 0.09154600653900047, "grad_norm": 0.4553831219673157, "learning_rate": 9.15061295971979e-06, "loss": 0.329, "step": 3136 }, { "epoch": 0.09157519850537132, "grad_norm": 0.47778838872909546, "learning_rate": 9.153531815528314e-06, "loss": 0.2337, "step": 3137 }, { "epoch": 0.09160439047174218, "grad_norm": 0.5478038787841797, "learning_rate": 9.156450671336836e-06, "loss": 0.2342, "step": 3138 }, { "epoch": 0.09163358243811304, "grad_norm": 0.5264385938644409, "learning_rate": 9.15936952714536e-06, "loss": 0.2668, "step": 3139 }, { "epoch": 0.09166277440448388, "grad_norm": 0.5544838905334473, "learning_rate": 9.162288382953883e-06, "loss": 0.2967, "step": 3140 }, { "epoch": 0.09169196637085474, "grad_norm": 0.5454257130622864, "learning_rate": 9.165207238762405e-06, "loss": 0.2567, "step": 3141 }, { "epoch": 0.09172115833722559, "grad_norm": 0.5311518311500549, "learning_rate": 9.16812609457093e-06, "loss": 0.2611, "step": 3142 }, { "epoch": 0.09175035030359645, "grad_norm": 0.46904560923576355, "learning_rate": 9.171044950379452e-06, "loss": 0.2078, "step": 3143 }, { "epoch": 0.0917795422699673, "grad_norm": 0.4636659324169159, "learning_rate": 9.173963806187976e-06, "loss": 0.2421, "step": 3144 }, { "epoch": 0.09180873423633816, "grad_norm": 0.507752001285553, "learning_rate": 9.176882661996499e-06, "loss": 0.2411, "step": 3145 }, { "epoch": 0.09183792620270902, "grad_norm": 0.5241687893867493, "learning_rate": 9.179801517805021e-06, "loss": 0.2537, "step": 3146 }, { "epoch": 0.09186711816907987, "grad_norm": 0.40447932481765747, "learning_rate": 9.182720373613544e-06, "loss": 0.2507, "step": 3147 }, { "epoch": 0.09189631013545073, "grad_norm": 0.5376127362251282, "learning_rate": 9.185639229422068e-06, "loss": 0.3435, "step": 3148 }, { "epoch": 0.09192550210182159, "grad_norm": 2.1313540935516357, "learning_rate": 9.18855808523059e-06, "loss": 0.2716, "step": 3149 }, { "epoch": 0.09195469406819243, "grad_norm": 0.4597998559474945, "learning_rate": 9.191476941039114e-06, "loss": 0.2659, "step": 3150 }, { "epoch": 0.09198388603456328, "grad_norm": 0.3568372130393982, "learning_rate": 9.194395796847637e-06, "loss": 0.1838, "step": 3151 }, { "epoch": 0.09201307800093414, "grad_norm": 0.45655855536460876, "learning_rate": 9.19731465265616e-06, "loss": 0.2613, "step": 3152 }, { "epoch": 0.092042269967305, "grad_norm": 0.4374048411846161, "learning_rate": 9.200233508464682e-06, "loss": 0.2191, "step": 3153 }, { "epoch": 0.09207146193367585, "grad_norm": 0.44759079813957214, "learning_rate": 9.203152364273206e-06, "loss": 0.2349, "step": 3154 }, { "epoch": 0.09210065390004671, "grad_norm": 0.49638837575912476, "learning_rate": 9.206071220081729e-06, "loss": 0.238, "step": 3155 }, { "epoch": 0.09212984586641756, "grad_norm": 0.43626952171325684, "learning_rate": 9.208990075890251e-06, "loss": 0.2314, "step": 3156 }, { "epoch": 0.09215903783278842, "grad_norm": 0.4377955198287964, "learning_rate": 9.211908931698775e-06, "loss": 0.2572, "step": 3157 }, { "epoch": 0.09218822979915928, "grad_norm": 0.6597496867179871, "learning_rate": 9.214827787507298e-06, "loss": 0.249, "step": 3158 }, { "epoch": 0.09221742176553012, "grad_norm": 0.4703201353549957, "learning_rate": 9.217746643315822e-06, "loss": 0.2227, "step": 3159 }, { "epoch": 0.09224661373190098, "grad_norm": 0.43788573145866394, "learning_rate": 9.220665499124344e-06, "loss": 0.2399, "step": 3160 }, { "epoch": 0.09227580569827183, "grad_norm": 0.4204678237438202, "learning_rate": 9.223584354932867e-06, "loss": 0.2188, "step": 3161 }, { "epoch": 0.09230499766464269, "grad_norm": 0.645001232624054, "learning_rate": 9.22650321074139e-06, "loss": 0.2228, "step": 3162 }, { "epoch": 0.09233418963101354, "grad_norm": 0.4562390148639679, "learning_rate": 9.229422066549914e-06, "loss": 0.2761, "step": 3163 }, { "epoch": 0.0923633815973844, "grad_norm": 0.40260568261146545, "learning_rate": 9.232340922358436e-06, "loss": 0.2274, "step": 3164 }, { "epoch": 0.09239257356375526, "grad_norm": 0.45148593187332153, "learning_rate": 9.23525977816696e-06, "loss": 0.2582, "step": 3165 }, { "epoch": 0.09242176553012611, "grad_norm": 0.43251511454582214, "learning_rate": 9.238178633975483e-06, "loss": 0.2132, "step": 3166 }, { "epoch": 0.09245095749649697, "grad_norm": 0.4440678060054779, "learning_rate": 9.241097489784005e-06, "loss": 0.2096, "step": 3167 }, { "epoch": 0.09248014946286783, "grad_norm": 0.43862998485565186, "learning_rate": 9.244016345592528e-06, "loss": 0.2562, "step": 3168 }, { "epoch": 0.09250934142923867, "grad_norm": 0.42653417587280273, "learning_rate": 9.246935201401052e-06, "loss": 0.2435, "step": 3169 }, { "epoch": 0.09253853339560952, "grad_norm": 0.46123266220092773, "learning_rate": 9.249854057209574e-06, "loss": 0.2744, "step": 3170 }, { "epoch": 0.09256772536198038, "grad_norm": 0.4843863844871521, "learning_rate": 9.252772913018097e-06, "loss": 0.2651, "step": 3171 }, { "epoch": 0.09259691732835124, "grad_norm": 0.5691631436347961, "learning_rate": 9.255691768826621e-06, "loss": 0.2312, "step": 3172 }, { "epoch": 0.09262610929472209, "grad_norm": 0.4481778144836426, "learning_rate": 9.258610624635144e-06, "loss": 0.2226, "step": 3173 }, { "epoch": 0.09265530126109295, "grad_norm": 0.4255611300468445, "learning_rate": 9.261529480443668e-06, "loss": 0.2672, "step": 3174 }, { "epoch": 0.0926844932274638, "grad_norm": 0.42667174339294434, "learning_rate": 9.26444833625219e-06, "loss": 0.2421, "step": 3175 }, { "epoch": 0.09271368519383466, "grad_norm": 0.41203194856643677, "learning_rate": 9.267367192060713e-06, "loss": 0.2503, "step": 3176 }, { "epoch": 0.09274287716020552, "grad_norm": 0.4581058919429779, "learning_rate": 9.270286047869235e-06, "loss": 0.2426, "step": 3177 }, { "epoch": 0.09277206912657637, "grad_norm": 0.523456335067749, "learning_rate": 9.27320490367776e-06, "loss": 0.2611, "step": 3178 }, { "epoch": 0.09280126109294722, "grad_norm": 0.4199705421924591, "learning_rate": 9.276123759486282e-06, "loss": 0.261, "step": 3179 }, { "epoch": 0.09283045305931807, "grad_norm": 0.4239489734172821, "learning_rate": 9.279042615294806e-06, "loss": 0.2184, "step": 3180 }, { "epoch": 0.09285964502568893, "grad_norm": 0.41640543937683105, "learning_rate": 9.281961471103329e-06, "loss": 0.2181, "step": 3181 }, { "epoch": 0.09288883699205978, "grad_norm": 0.42197510600090027, "learning_rate": 9.284880326911851e-06, "loss": 0.258, "step": 3182 }, { "epoch": 0.09291802895843064, "grad_norm": 0.4760691225528717, "learning_rate": 9.287799182720374e-06, "loss": 0.2944, "step": 3183 }, { "epoch": 0.0929472209248015, "grad_norm": 0.4037493169307709, "learning_rate": 9.290718038528898e-06, "loss": 0.2739, "step": 3184 }, { "epoch": 0.09297641289117235, "grad_norm": 0.4961647689342499, "learning_rate": 9.29363689433742e-06, "loss": 0.2771, "step": 3185 }, { "epoch": 0.09300560485754321, "grad_norm": 0.4703295826911926, "learning_rate": 9.296555750145943e-06, "loss": 0.2267, "step": 3186 }, { "epoch": 0.09303479682391406, "grad_norm": 0.5427634716033936, "learning_rate": 9.299474605954467e-06, "loss": 0.2736, "step": 3187 }, { "epoch": 0.09306398879028491, "grad_norm": 0.48104968667030334, "learning_rate": 9.30239346176299e-06, "loss": 0.2416, "step": 3188 }, { "epoch": 0.09309318075665576, "grad_norm": 0.5226127505302429, "learning_rate": 9.305312317571514e-06, "loss": 0.2779, "step": 3189 }, { "epoch": 0.09312237272302662, "grad_norm": 0.45195862650871277, "learning_rate": 9.308231173380036e-06, "loss": 0.2672, "step": 3190 }, { "epoch": 0.09315156468939748, "grad_norm": 0.3848157227039337, "learning_rate": 9.311150029188559e-06, "loss": 0.2657, "step": 3191 }, { "epoch": 0.09318075665576833, "grad_norm": 0.4468682110309601, "learning_rate": 9.314068884997081e-06, "loss": 0.2906, "step": 3192 }, { "epoch": 0.09320994862213919, "grad_norm": 0.5457403063774109, "learning_rate": 9.316987740805605e-06, "loss": 0.2838, "step": 3193 }, { "epoch": 0.09323914058851004, "grad_norm": 0.39566007256507874, "learning_rate": 9.319906596614128e-06, "loss": 0.2216, "step": 3194 }, { "epoch": 0.0932683325548809, "grad_norm": 0.41566231846809387, "learning_rate": 9.322825452422652e-06, "loss": 0.2567, "step": 3195 }, { "epoch": 0.09329752452125176, "grad_norm": 0.39255908131599426, "learning_rate": 9.325744308231174e-06, "loss": 0.2887, "step": 3196 }, { "epoch": 0.09332671648762261, "grad_norm": 0.4017615020275116, "learning_rate": 9.328663164039697e-06, "loss": 0.2421, "step": 3197 }, { "epoch": 0.09335590845399346, "grad_norm": 0.5284404754638672, "learning_rate": 9.33158201984822e-06, "loss": 0.2937, "step": 3198 }, { "epoch": 0.09338510042036431, "grad_norm": 0.4092339873313904, "learning_rate": 9.334500875656744e-06, "loss": 0.2425, "step": 3199 }, { "epoch": 0.09341429238673517, "grad_norm": 0.4128503203392029, "learning_rate": 9.337419731465266e-06, "loss": 0.2355, "step": 3200 }, { "epoch": 0.09344348435310602, "grad_norm": 0.4296952784061432, "learning_rate": 9.34033858727379e-06, "loss": 0.2371, "step": 3201 }, { "epoch": 0.09347267631947688, "grad_norm": 0.6355898976325989, "learning_rate": 9.343257443082311e-06, "loss": 0.2679, "step": 3202 }, { "epoch": 0.09350186828584774, "grad_norm": 0.4231798052787781, "learning_rate": 9.346176298890835e-06, "loss": 0.2616, "step": 3203 }, { "epoch": 0.09353106025221859, "grad_norm": 0.40948763489723206, "learning_rate": 9.34909515469936e-06, "loss": 0.2629, "step": 3204 }, { "epoch": 0.09356025221858945, "grad_norm": 0.41784852743148804, "learning_rate": 9.352014010507882e-06, "loss": 0.2841, "step": 3205 }, { "epoch": 0.0935894441849603, "grad_norm": 0.4419238567352295, "learning_rate": 9.354932866316404e-06, "loss": 0.201, "step": 3206 }, { "epoch": 0.09361863615133115, "grad_norm": 0.4414052665233612, "learning_rate": 9.357851722124927e-06, "loss": 0.2362, "step": 3207 }, { "epoch": 0.093647828117702, "grad_norm": 0.45718494057655334, "learning_rate": 9.360770577933451e-06, "loss": 0.2693, "step": 3208 }, { "epoch": 0.09367702008407286, "grad_norm": 0.4484004080295563, "learning_rate": 9.363689433741974e-06, "loss": 0.271, "step": 3209 }, { "epoch": 0.09370621205044372, "grad_norm": 0.4201865494251251, "learning_rate": 9.366608289550498e-06, "loss": 0.2525, "step": 3210 }, { "epoch": 0.09373540401681457, "grad_norm": 0.49439993500709534, "learning_rate": 9.36952714535902e-06, "loss": 0.2345, "step": 3211 }, { "epoch": 0.09376459598318543, "grad_norm": 0.4760245680809021, "learning_rate": 9.372446001167543e-06, "loss": 0.283, "step": 3212 }, { "epoch": 0.09379378794955628, "grad_norm": 0.4545104205608368, "learning_rate": 9.375364856976065e-06, "loss": 0.3263, "step": 3213 }, { "epoch": 0.09382297991592714, "grad_norm": 0.4279594421386719, "learning_rate": 9.37828371278459e-06, "loss": 0.267, "step": 3214 }, { "epoch": 0.093852171882298, "grad_norm": 0.4156229794025421, "learning_rate": 9.381202568593112e-06, "loss": 0.2287, "step": 3215 }, { "epoch": 0.09388136384866885, "grad_norm": 0.45533573627471924, "learning_rate": 9.384121424401636e-06, "loss": 0.2431, "step": 3216 }, { "epoch": 0.0939105558150397, "grad_norm": 0.4095018804073334, "learning_rate": 9.387040280210159e-06, "loss": 0.2791, "step": 3217 }, { "epoch": 0.09393974778141055, "grad_norm": 0.48288413882255554, "learning_rate": 9.389959136018681e-06, "loss": 0.2868, "step": 3218 }, { "epoch": 0.09396893974778141, "grad_norm": 0.38759446144104004, "learning_rate": 9.392877991827205e-06, "loss": 0.2315, "step": 3219 }, { "epoch": 0.09399813171415226, "grad_norm": 0.4599210321903229, "learning_rate": 9.395796847635728e-06, "loss": 0.3032, "step": 3220 }, { "epoch": 0.09402732368052312, "grad_norm": 0.42769020795822144, "learning_rate": 9.39871570344425e-06, "loss": 0.3031, "step": 3221 }, { "epoch": 0.09405651564689398, "grad_norm": 0.5035653710365295, "learning_rate": 9.401634559252773e-06, "loss": 0.2501, "step": 3222 }, { "epoch": 0.09408570761326483, "grad_norm": 0.4157058000564575, "learning_rate": 9.404553415061297e-06, "loss": 0.2147, "step": 3223 }, { "epoch": 0.09411489957963569, "grad_norm": 0.42756596207618713, "learning_rate": 9.40747227086982e-06, "loss": 0.269, "step": 3224 }, { "epoch": 0.09414409154600654, "grad_norm": 0.4930696189403534, "learning_rate": 9.410391126678344e-06, "loss": 0.2466, "step": 3225 }, { "epoch": 0.09417328351237739, "grad_norm": 0.3981771171092987, "learning_rate": 9.413309982486866e-06, "loss": 0.2636, "step": 3226 }, { "epoch": 0.09420247547874824, "grad_norm": 0.3730720281600952, "learning_rate": 9.416228838295389e-06, "loss": 0.1873, "step": 3227 }, { "epoch": 0.0942316674451191, "grad_norm": 0.45669758319854736, "learning_rate": 9.419147694103911e-06, "loss": 0.2579, "step": 3228 }, { "epoch": 0.09426085941148996, "grad_norm": 0.433750182390213, "learning_rate": 9.422066549912435e-06, "loss": 0.2782, "step": 3229 }, { "epoch": 0.09429005137786081, "grad_norm": 0.3982151746749878, "learning_rate": 9.424985405720958e-06, "loss": 0.2224, "step": 3230 }, { "epoch": 0.09431924334423167, "grad_norm": 0.43318673968315125, "learning_rate": 9.427904261529482e-06, "loss": 0.2044, "step": 3231 }, { "epoch": 0.09434843531060252, "grad_norm": 0.5699343085289001, "learning_rate": 9.430823117338005e-06, "loss": 0.3005, "step": 3232 }, { "epoch": 0.09437762727697338, "grad_norm": 0.48006394505500793, "learning_rate": 9.433741973146527e-06, "loss": 0.2671, "step": 3233 }, { "epoch": 0.09440681924334424, "grad_norm": 0.49979326128959656, "learning_rate": 9.43666082895505e-06, "loss": 0.3037, "step": 3234 }, { "epoch": 0.09443601120971509, "grad_norm": 0.4667934775352478, "learning_rate": 9.439579684763574e-06, "loss": 0.3176, "step": 3235 }, { "epoch": 0.09446520317608594, "grad_norm": 0.4070950448513031, "learning_rate": 9.442498540572096e-06, "loss": 0.2436, "step": 3236 }, { "epoch": 0.09449439514245679, "grad_norm": 0.43959474563598633, "learning_rate": 9.445417396380619e-06, "loss": 0.2519, "step": 3237 }, { "epoch": 0.09452358710882765, "grad_norm": 0.5821750164031982, "learning_rate": 9.448336252189143e-06, "loss": 0.3193, "step": 3238 }, { "epoch": 0.0945527790751985, "grad_norm": 0.4182613790035248, "learning_rate": 9.451255107997665e-06, "loss": 0.2363, "step": 3239 }, { "epoch": 0.09458197104156936, "grad_norm": 0.7665824294090271, "learning_rate": 9.45417396380619e-06, "loss": 0.2983, "step": 3240 }, { "epoch": 0.09461116300794022, "grad_norm": 0.4049777686595917, "learning_rate": 9.457092819614712e-06, "loss": 0.2376, "step": 3241 }, { "epoch": 0.09464035497431107, "grad_norm": 0.45530644059181213, "learning_rate": 9.460011675423235e-06, "loss": 0.2098, "step": 3242 }, { "epoch": 0.09466954694068193, "grad_norm": 0.4926212430000305, "learning_rate": 9.462930531231757e-06, "loss": 0.2661, "step": 3243 }, { "epoch": 0.09469873890705278, "grad_norm": 0.44675615429878235, "learning_rate": 9.465849387040281e-06, "loss": 0.2867, "step": 3244 }, { "epoch": 0.09472793087342363, "grad_norm": 0.42664459347724915, "learning_rate": 9.468768242848804e-06, "loss": 0.2375, "step": 3245 }, { "epoch": 0.09475712283979448, "grad_norm": 0.4322548806667328, "learning_rate": 9.471687098657328e-06, "loss": 0.2712, "step": 3246 }, { "epoch": 0.09478631480616534, "grad_norm": 2.2024600505828857, "learning_rate": 9.47460595446585e-06, "loss": 0.266, "step": 3247 }, { "epoch": 0.0948155067725362, "grad_norm": 0.41409537196159363, "learning_rate": 9.477524810274373e-06, "loss": 0.2536, "step": 3248 }, { "epoch": 0.09484469873890705, "grad_norm": 0.4434889853000641, "learning_rate": 9.480443666082895e-06, "loss": 0.2366, "step": 3249 }, { "epoch": 0.09487389070527791, "grad_norm": 0.7221367955207825, "learning_rate": 9.48336252189142e-06, "loss": 0.3025, "step": 3250 }, { "epoch": 0.09490308267164876, "grad_norm": 0.41275647282600403, "learning_rate": 9.486281377699944e-06, "loss": 0.2343, "step": 3251 }, { "epoch": 0.09493227463801962, "grad_norm": 0.4365827143192291, "learning_rate": 9.489200233508465e-06, "loss": 0.2742, "step": 3252 }, { "epoch": 0.09496146660439048, "grad_norm": 0.42717984318733215, "learning_rate": 9.492119089316989e-06, "loss": 0.2778, "step": 3253 }, { "epoch": 0.09499065857076133, "grad_norm": 0.4705805480480194, "learning_rate": 9.495037945125511e-06, "loss": 0.3111, "step": 3254 }, { "epoch": 0.09501985053713217, "grad_norm": 0.41774967312812805, "learning_rate": 9.497956800934035e-06, "loss": 0.261, "step": 3255 }, { "epoch": 0.09504904250350303, "grad_norm": 0.642509937286377, "learning_rate": 9.500875656742558e-06, "loss": 0.3056, "step": 3256 }, { "epoch": 0.09507823446987389, "grad_norm": 0.39699286222457886, "learning_rate": 9.50379451255108e-06, "loss": 0.2541, "step": 3257 }, { "epoch": 0.09510742643624474, "grad_norm": 0.5249390006065369, "learning_rate": 9.506713368359603e-06, "loss": 0.3089, "step": 3258 }, { "epoch": 0.0951366184026156, "grad_norm": 0.4126885235309601, "learning_rate": 9.509632224168127e-06, "loss": 0.237, "step": 3259 }, { "epoch": 0.09516581036898646, "grad_norm": 0.3973233997821808, "learning_rate": 9.51255107997665e-06, "loss": 0.2659, "step": 3260 }, { "epoch": 0.09519500233535731, "grad_norm": 0.43839505314826965, "learning_rate": 9.515469935785174e-06, "loss": 0.2998, "step": 3261 }, { "epoch": 0.09522419430172817, "grad_norm": 0.4253111481666565, "learning_rate": 9.518388791593696e-06, "loss": 0.2616, "step": 3262 }, { "epoch": 0.09525338626809902, "grad_norm": 0.5424553155899048, "learning_rate": 9.521307647402219e-06, "loss": 0.2509, "step": 3263 }, { "epoch": 0.09528257823446988, "grad_norm": 0.39916348457336426, "learning_rate": 9.524226503210741e-06, "loss": 0.2554, "step": 3264 }, { "epoch": 0.09531177020084072, "grad_norm": 0.425235778093338, "learning_rate": 9.527145359019265e-06, "loss": 0.2631, "step": 3265 }, { "epoch": 0.09534096216721158, "grad_norm": 0.4127315878868103, "learning_rate": 9.530064214827788e-06, "loss": 0.2516, "step": 3266 }, { "epoch": 0.09537015413358244, "grad_norm": 0.46392980217933655, "learning_rate": 9.532983070636312e-06, "loss": 0.2012, "step": 3267 }, { "epoch": 0.09539934609995329, "grad_norm": 0.4208127558231354, "learning_rate": 9.535901926444835e-06, "loss": 0.2244, "step": 3268 }, { "epoch": 0.09542853806632415, "grad_norm": 0.5367594957351685, "learning_rate": 9.538820782253357e-06, "loss": 0.2469, "step": 3269 }, { "epoch": 0.095457730032695, "grad_norm": 0.41148099303245544, "learning_rate": 9.541739638061881e-06, "loss": 0.2511, "step": 3270 }, { "epoch": 0.09548692199906586, "grad_norm": 0.4329022467136383, "learning_rate": 9.544658493870404e-06, "loss": 0.2492, "step": 3271 }, { "epoch": 0.09551611396543672, "grad_norm": 0.5587236881256104, "learning_rate": 9.547577349678926e-06, "loss": 0.2196, "step": 3272 }, { "epoch": 0.09554530593180757, "grad_norm": 0.3549915552139282, "learning_rate": 9.550496205487449e-06, "loss": 0.2084, "step": 3273 }, { "epoch": 0.09557449789817841, "grad_norm": 0.3626430630683899, "learning_rate": 9.553415061295973e-06, "loss": 0.2081, "step": 3274 }, { "epoch": 0.09560368986454927, "grad_norm": 0.4223390817642212, "learning_rate": 9.556333917104495e-06, "loss": 0.3032, "step": 3275 }, { "epoch": 0.09563288183092013, "grad_norm": 0.43319910764694214, "learning_rate": 9.55925277291302e-06, "loss": 0.2535, "step": 3276 }, { "epoch": 0.09566207379729098, "grad_norm": 0.505980372428894, "learning_rate": 9.562171628721542e-06, "loss": 0.2991, "step": 3277 }, { "epoch": 0.09569126576366184, "grad_norm": 0.4695679247379303, "learning_rate": 9.565090484530065e-06, "loss": 0.2482, "step": 3278 }, { "epoch": 0.0957204577300327, "grad_norm": 0.4332040846347809, "learning_rate": 9.568009340338587e-06, "loss": 0.3064, "step": 3279 }, { "epoch": 0.09574964969640355, "grad_norm": 0.47555094957351685, "learning_rate": 9.570928196147111e-06, "loss": 0.2632, "step": 3280 }, { "epoch": 0.09577884166277441, "grad_norm": 0.46230369806289673, "learning_rate": 9.573847051955634e-06, "loss": 0.2629, "step": 3281 }, { "epoch": 0.09580803362914526, "grad_norm": 0.3664672374725342, "learning_rate": 9.576765907764158e-06, "loss": 0.2185, "step": 3282 }, { "epoch": 0.09583722559551612, "grad_norm": 0.47053757309913635, "learning_rate": 9.57968476357268e-06, "loss": 0.274, "step": 3283 }, { "epoch": 0.09586641756188696, "grad_norm": 0.4324208199977875, "learning_rate": 9.582603619381203e-06, "loss": 0.3175, "step": 3284 }, { "epoch": 0.09589560952825782, "grad_norm": 0.42266494035720825, "learning_rate": 9.585522475189727e-06, "loss": 0.2622, "step": 3285 }, { "epoch": 0.09592480149462868, "grad_norm": 0.416701078414917, "learning_rate": 9.58844133099825e-06, "loss": 0.2932, "step": 3286 }, { "epoch": 0.09595399346099953, "grad_norm": 0.41769444942474365, "learning_rate": 9.591360186806772e-06, "loss": 0.2328, "step": 3287 }, { "epoch": 0.09598318542737039, "grad_norm": 0.41117262840270996, "learning_rate": 9.594279042615295e-06, "loss": 0.2611, "step": 3288 }, { "epoch": 0.09601237739374124, "grad_norm": 0.43827173113822937, "learning_rate": 9.597197898423819e-06, "loss": 0.2776, "step": 3289 }, { "epoch": 0.0960415693601121, "grad_norm": 0.4458533227443695, "learning_rate": 9.600116754232341e-06, "loss": 0.2413, "step": 3290 }, { "epoch": 0.09607076132648296, "grad_norm": 0.4169974625110626, "learning_rate": 9.603035610040866e-06, "loss": 0.241, "step": 3291 }, { "epoch": 0.09609995329285381, "grad_norm": 0.4318976104259491, "learning_rate": 9.605954465849388e-06, "loss": 0.298, "step": 3292 }, { "epoch": 0.09612914525922465, "grad_norm": 0.43723076581954956, "learning_rate": 9.60887332165791e-06, "loss": 0.2623, "step": 3293 }, { "epoch": 0.09615833722559551, "grad_norm": 0.39214423298835754, "learning_rate": 9.611792177466433e-06, "loss": 0.2466, "step": 3294 }, { "epoch": 0.09618752919196637, "grad_norm": 0.45870456099510193, "learning_rate": 9.614711033274957e-06, "loss": 0.2994, "step": 3295 }, { "epoch": 0.09621672115833722, "grad_norm": 0.6015138626098633, "learning_rate": 9.61762988908348e-06, "loss": 0.2683, "step": 3296 }, { "epoch": 0.09624591312470808, "grad_norm": 0.46116504073143005, "learning_rate": 9.620548744892004e-06, "loss": 0.2533, "step": 3297 }, { "epoch": 0.09627510509107894, "grad_norm": 0.4659525752067566, "learning_rate": 9.623467600700526e-06, "loss": 0.2743, "step": 3298 }, { "epoch": 0.09630429705744979, "grad_norm": 0.42252010107040405, "learning_rate": 9.626386456509049e-06, "loss": 0.2578, "step": 3299 }, { "epoch": 0.09633348902382065, "grad_norm": 0.4792361557483673, "learning_rate": 9.629305312317573e-06, "loss": 0.2652, "step": 3300 }, { "epoch": 0.0963626809901915, "grad_norm": 0.5103252530097961, "learning_rate": 9.632224168126096e-06, "loss": 0.255, "step": 3301 }, { "epoch": 0.09639187295656236, "grad_norm": 0.5299742817878723, "learning_rate": 9.635143023934618e-06, "loss": 0.269, "step": 3302 }, { "epoch": 0.0964210649229332, "grad_norm": 0.4702392518520355, "learning_rate": 9.63806187974314e-06, "loss": 0.2596, "step": 3303 }, { "epoch": 0.09645025688930406, "grad_norm": 0.46613988280296326, "learning_rate": 9.640980735551665e-06, "loss": 0.2365, "step": 3304 }, { "epoch": 0.09647944885567492, "grad_norm": 0.4359094202518463, "learning_rate": 9.643899591360187e-06, "loss": 0.2759, "step": 3305 }, { "epoch": 0.09650864082204577, "grad_norm": 0.6558358669281006, "learning_rate": 9.646818447168711e-06, "loss": 0.3049, "step": 3306 }, { "epoch": 0.09653783278841663, "grad_norm": 0.4740857779979706, "learning_rate": 9.649737302977234e-06, "loss": 0.2397, "step": 3307 }, { "epoch": 0.09656702475478748, "grad_norm": 0.9402581453323364, "learning_rate": 9.652656158785756e-06, "loss": 0.2443, "step": 3308 }, { "epoch": 0.09659621672115834, "grad_norm": 0.4712894856929779, "learning_rate": 9.655575014594279e-06, "loss": 0.3136, "step": 3309 }, { "epoch": 0.0966254086875292, "grad_norm": 0.4861309230327606, "learning_rate": 9.658493870402803e-06, "loss": 0.2404, "step": 3310 }, { "epoch": 0.09665460065390005, "grad_norm": 0.6182692646980286, "learning_rate": 9.661412726211326e-06, "loss": 0.2544, "step": 3311 }, { "epoch": 0.0966837926202709, "grad_norm": 0.460613876581192, "learning_rate": 9.66433158201985e-06, "loss": 0.2667, "step": 3312 }, { "epoch": 0.09671298458664175, "grad_norm": 0.39358216524124146, "learning_rate": 9.667250437828372e-06, "loss": 0.2093, "step": 3313 }, { "epoch": 0.09674217655301261, "grad_norm": 0.47275054454803467, "learning_rate": 9.670169293636895e-06, "loss": 0.2637, "step": 3314 }, { "epoch": 0.09677136851938346, "grad_norm": 0.4421367347240448, "learning_rate": 9.673088149445419e-06, "loss": 0.2855, "step": 3315 }, { "epoch": 0.09680056048575432, "grad_norm": 0.4026171863079071, "learning_rate": 9.676007005253941e-06, "loss": 0.1928, "step": 3316 }, { "epoch": 0.09682975245212518, "grad_norm": 2.2116405963897705, "learning_rate": 9.678925861062466e-06, "loss": 0.3111, "step": 3317 }, { "epoch": 0.09685894441849603, "grad_norm": 0.5044337511062622, "learning_rate": 9.681844716870988e-06, "loss": 0.3036, "step": 3318 }, { "epoch": 0.09688813638486689, "grad_norm": 0.5813032388687134, "learning_rate": 9.68476357267951e-06, "loss": 0.2279, "step": 3319 }, { "epoch": 0.09691732835123774, "grad_norm": 0.44640034437179565, "learning_rate": 9.687682428488033e-06, "loss": 0.2776, "step": 3320 }, { "epoch": 0.0969465203176086, "grad_norm": 0.46114206314086914, "learning_rate": 9.690601284296557e-06, "loss": 0.2548, "step": 3321 }, { "epoch": 0.09697571228397944, "grad_norm": 0.5121623277664185, "learning_rate": 9.69352014010508e-06, "loss": 0.2515, "step": 3322 }, { "epoch": 0.0970049042503503, "grad_norm": 0.4114983379840851, "learning_rate": 9.696438995913602e-06, "loss": 0.2775, "step": 3323 }, { "epoch": 0.09703409621672116, "grad_norm": 0.5419038534164429, "learning_rate": 9.699357851722125e-06, "loss": 0.2219, "step": 3324 }, { "epoch": 0.09706328818309201, "grad_norm": 0.41225430369377136, "learning_rate": 9.702276707530649e-06, "loss": 0.2269, "step": 3325 }, { "epoch": 0.09709248014946287, "grad_norm": 0.4596574306488037, "learning_rate": 9.705195563339171e-06, "loss": 0.2341, "step": 3326 }, { "epoch": 0.09712167211583372, "grad_norm": 0.4311198592185974, "learning_rate": 9.708114419147696e-06, "loss": 0.2679, "step": 3327 }, { "epoch": 0.09715086408220458, "grad_norm": 0.43396979570388794, "learning_rate": 9.711033274956218e-06, "loss": 0.2283, "step": 3328 }, { "epoch": 0.09718005604857544, "grad_norm": 0.5197816491127014, "learning_rate": 9.71395213076474e-06, "loss": 0.2941, "step": 3329 }, { "epoch": 0.09720924801494629, "grad_norm": 0.5931639075279236, "learning_rate": 9.716870986573263e-06, "loss": 0.3289, "step": 3330 }, { "epoch": 0.09723843998131713, "grad_norm": 0.46126633882522583, "learning_rate": 9.719789842381787e-06, "loss": 0.3048, "step": 3331 }, { "epoch": 0.09726763194768799, "grad_norm": 0.6066396236419678, "learning_rate": 9.722708698190311e-06, "loss": 0.2531, "step": 3332 }, { "epoch": 0.09729682391405885, "grad_norm": 0.6017450094223022, "learning_rate": 9.725627553998834e-06, "loss": 0.2927, "step": 3333 }, { "epoch": 0.0973260158804297, "grad_norm": 0.42154446244239807, "learning_rate": 9.728546409807356e-06, "loss": 0.2473, "step": 3334 }, { "epoch": 0.09735520784680056, "grad_norm": 0.38794049620628357, "learning_rate": 9.731465265615879e-06, "loss": 0.2172, "step": 3335 }, { "epoch": 0.09738439981317142, "grad_norm": 0.5433977246284485, "learning_rate": 9.734384121424403e-06, "loss": 0.2491, "step": 3336 }, { "epoch": 0.09741359177954227, "grad_norm": 0.48158207535743713, "learning_rate": 9.737302977232926e-06, "loss": 0.2695, "step": 3337 }, { "epoch": 0.09744278374591313, "grad_norm": 0.5139041543006897, "learning_rate": 9.740221833041448e-06, "loss": 0.276, "step": 3338 }, { "epoch": 0.09747197571228398, "grad_norm": 0.4761556088924408, "learning_rate": 9.74314068884997e-06, "loss": 0.2111, "step": 3339 }, { "epoch": 0.09750116767865484, "grad_norm": 0.4549259841442108, "learning_rate": 9.746059544658495e-06, "loss": 0.2205, "step": 3340 }, { "epoch": 0.09753035964502568, "grad_norm": 0.3753352463245392, "learning_rate": 9.748978400467017e-06, "loss": 0.2064, "step": 3341 }, { "epoch": 0.09755955161139654, "grad_norm": 0.9038015007972717, "learning_rate": 9.751897256275541e-06, "loss": 0.2867, "step": 3342 }, { "epoch": 0.0975887435777674, "grad_norm": 0.42771393060684204, "learning_rate": 9.754816112084064e-06, "loss": 0.2673, "step": 3343 }, { "epoch": 0.09761793554413825, "grad_norm": 0.47766268253326416, "learning_rate": 9.757734967892586e-06, "loss": 0.2552, "step": 3344 }, { "epoch": 0.09764712751050911, "grad_norm": 0.48970624804496765, "learning_rate": 9.760653823701109e-06, "loss": 0.2813, "step": 3345 }, { "epoch": 0.09767631947687996, "grad_norm": 0.5218026638031006, "learning_rate": 9.763572679509633e-06, "loss": 0.2568, "step": 3346 }, { "epoch": 0.09770551144325082, "grad_norm": 0.6418941617012024, "learning_rate": 9.766491535318157e-06, "loss": 0.2675, "step": 3347 }, { "epoch": 0.09773470340962168, "grad_norm": 0.4799194037914276, "learning_rate": 9.76941039112668e-06, "loss": 0.218, "step": 3348 }, { "epoch": 0.09776389537599253, "grad_norm": 0.48538893461227417, "learning_rate": 9.772329246935202e-06, "loss": 0.2674, "step": 3349 }, { "epoch": 0.09779308734236339, "grad_norm": 0.3654955327510834, "learning_rate": 9.775248102743725e-06, "loss": 0.2351, "step": 3350 }, { "epoch": 0.09782227930873423, "grad_norm": 0.5984623432159424, "learning_rate": 9.778166958552249e-06, "loss": 0.3166, "step": 3351 }, { "epoch": 0.09785147127510509, "grad_norm": 0.5727338194847107, "learning_rate": 9.781085814360771e-06, "loss": 0.2842, "step": 3352 }, { "epoch": 0.09788066324147594, "grad_norm": 0.4488503336906433, "learning_rate": 9.784004670169294e-06, "loss": 0.2385, "step": 3353 }, { "epoch": 0.0979098552078468, "grad_norm": 1.035618543624878, "learning_rate": 9.786923525977816e-06, "loss": 0.2851, "step": 3354 }, { "epoch": 0.09793904717421766, "grad_norm": 0.502804696559906, "learning_rate": 9.78984238178634e-06, "loss": 0.2642, "step": 3355 }, { "epoch": 0.09796823914058851, "grad_norm": 0.4485642910003662, "learning_rate": 9.792761237594863e-06, "loss": 0.2568, "step": 3356 }, { "epoch": 0.09799743110695937, "grad_norm": 0.45813456177711487, "learning_rate": 9.795680093403387e-06, "loss": 0.2606, "step": 3357 }, { "epoch": 0.09802662307333022, "grad_norm": 0.4648424983024597, "learning_rate": 9.79859894921191e-06, "loss": 0.3136, "step": 3358 }, { "epoch": 0.09805581503970108, "grad_norm": 0.4423172175884247, "learning_rate": 9.801517805020432e-06, "loss": 0.2711, "step": 3359 }, { "epoch": 0.09808500700607192, "grad_norm": 0.4456581175327301, "learning_rate": 9.804436660828955e-06, "loss": 0.28, "step": 3360 }, { "epoch": 0.09811419897244278, "grad_norm": 0.4043000340461731, "learning_rate": 9.807355516637479e-06, "loss": 0.2254, "step": 3361 }, { "epoch": 0.09814339093881363, "grad_norm": 0.3904891014099121, "learning_rate": 9.810274372446002e-06, "loss": 0.2299, "step": 3362 }, { "epoch": 0.09817258290518449, "grad_norm": 0.4474392235279083, "learning_rate": 9.813193228254526e-06, "loss": 0.2436, "step": 3363 }, { "epoch": 0.09820177487155535, "grad_norm": 0.46014904975891113, "learning_rate": 9.816112084063048e-06, "loss": 0.32, "step": 3364 }, { "epoch": 0.0982309668379262, "grad_norm": 0.419159859418869, "learning_rate": 9.81903093987157e-06, "loss": 0.2447, "step": 3365 }, { "epoch": 0.09826015880429706, "grad_norm": 0.4166618585586548, "learning_rate": 9.821949795680095e-06, "loss": 0.2609, "step": 3366 }, { "epoch": 0.09828935077066792, "grad_norm": 0.44370344281196594, "learning_rate": 9.824868651488617e-06, "loss": 0.2721, "step": 3367 }, { "epoch": 0.09831854273703877, "grad_norm": 0.4348679482936859, "learning_rate": 9.827787507297142e-06, "loss": 0.2565, "step": 3368 }, { "epoch": 0.09834773470340963, "grad_norm": 0.5823735594749451, "learning_rate": 9.830706363105662e-06, "loss": 0.2793, "step": 3369 }, { "epoch": 0.09837692666978047, "grad_norm": 0.5185854434967041, "learning_rate": 9.833625218914187e-06, "loss": 0.2996, "step": 3370 }, { "epoch": 0.09840611863615133, "grad_norm": 0.7175537347793579, "learning_rate": 9.836544074722709e-06, "loss": 0.2589, "step": 3371 }, { "epoch": 0.09843531060252218, "grad_norm": 0.4571104645729065, "learning_rate": 9.839462930531233e-06, "loss": 0.23, "step": 3372 }, { "epoch": 0.09846450256889304, "grad_norm": 0.42883583903312683, "learning_rate": 9.842381786339756e-06, "loss": 0.2256, "step": 3373 }, { "epoch": 0.0984936945352639, "grad_norm": 0.5753710269927979, "learning_rate": 9.845300642148278e-06, "loss": 0.2433, "step": 3374 }, { "epoch": 0.09852288650163475, "grad_norm": 0.5833526849746704, "learning_rate": 9.8482194979568e-06, "loss": 0.2729, "step": 3375 }, { "epoch": 0.09855207846800561, "grad_norm": 0.3992080092430115, "learning_rate": 9.851138353765325e-06, "loss": 0.2083, "step": 3376 }, { "epoch": 0.09858127043437646, "grad_norm": 0.6700959801673889, "learning_rate": 9.854057209573847e-06, "loss": 0.3257, "step": 3377 }, { "epoch": 0.09861046240074732, "grad_norm": 0.36777016520500183, "learning_rate": 9.856976065382372e-06, "loss": 0.2065, "step": 3378 }, { "epoch": 0.09863965436711816, "grad_norm": 0.39644476771354675, "learning_rate": 9.859894921190894e-06, "loss": 0.2323, "step": 3379 }, { "epoch": 0.09866884633348902, "grad_norm": 0.4256211817264557, "learning_rate": 9.862813776999417e-06, "loss": 0.2782, "step": 3380 }, { "epoch": 0.09869803829985987, "grad_norm": 0.42623379826545715, "learning_rate": 9.86573263280794e-06, "loss": 0.277, "step": 3381 }, { "epoch": 0.09872723026623073, "grad_norm": 0.4237101078033447, "learning_rate": 9.868651488616463e-06, "loss": 0.231, "step": 3382 }, { "epoch": 0.09875642223260159, "grad_norm": 0.42722976207733154, "learning_rate": 9.871570344424987e-06, "loss": 0.2564, "step": 3383 }, { "epoch": 0.09878561419897244, "grad_norm": 0.38922813534736633, "learning_rate": 9.87448920023351e-06, "loss": 0.2776, "step": 3384 }, { "epoch": 0.0988148061653433, "grad_norm": 0.4960545599460602, "learning_rate": 9.877408056042032e-06, "loss": 0.2794, "step": 3385 }, { "epoch": 0.09884399813171416, "grad_norm": 2.579085111618042, "learning_rate": 9.880326911850555e-06, "loss": 0.246, "step": 3386 }, { "epoch": 0.09887319009808501, "grad_norm": 0.4400703012943268, "learning_rate": 9.883245767659079e-06, "loss": 0.2611, "step": 3387 }, { "epoch": 0.09890238206445587, "grad_norm": 0.4061959981918335, "learning_rate": 9.886164623467602e-06, "loss": 0.2896, "step": 3388 }, { "epoch": 0.09893157403082671, "grad_norm": 0.37792661786079407, "learning_rate": 9.889083479276124e-06, "loss": 0.1919, "step": 3389 }, { "epoch": 0.09896076599719757, "grad_norm": 0.4052976369857788, "learning_rate": 9.892002335084647e-06, "loss": 0.2569, "step": 3390 }, { "epoch": 0.09898995796356842, "grad_norm": 0.3866827189922333, "learning_rate": 9.89492119089317e-06, "loss": 0.2502, "step": 3391 }, { "epoch": 0.09901914992993928, "grad_norm": 0.42156925797462463, "learning_rate": 9.897840046701693e-06, "loss": 0.2727, "step": 3392 }, { "epoch": 0.09904834189631014, "grad_norm": 0.46396270394325256, "learning_rate": 9.900758902510217e-06, "loss": 0.2416, "step": 3393 }, { "epoch": 0.09907753386268099, "grad_norm": 0.43554577231407166, "learning_rate": 9.90367775831874e-06, "loss": 0.2851, "step": 3394 }, { "epoch": 0.09910672582905185, "grad_norm": 0.4617561399936676, "learning_rate": 9.906596614127262e-06, "loss": 0.2603, "step": 3395 }, { "epoch": 0.0991359177954227, "grad_norm": 0.4653550684452057, "learning_rate": 9.909515469935787e-06, "loss": 0.2553, "step": 3396 }, { "epoch": 0.09916510976179356, "grad_norm": 1.4071621894836426, "learning_rate": 9.912434325744309e-06, "loss": 0.2855, "step": 3397 }, { "epoch": 0.0991943017281644, "grad_norm": 0.47541654109954834, "learning_rate": 9.915353181552833e-06, "loss": 0.2626, "step": 3398 }, { "epoch": 0.09922349369453526, "grad_norm": 0.40841802954673767, "learning_rate": 9.918272037361356e-06, "loss": 0.2523, "step": 3399 }, { "epoch": 0.09925268566090611, "grad_norm": 0.40980246663093567, "learning_rate": 9.921190893169878e-06, "loss": 0.2595, "step": 3400 }, { "epoch": 0.09928187762727697, "grad_norm": 0.3903588056564331, "learning_rate": 9.9241097489784e-06, "loss": 0.2021, "step": 3401 }, { "epoch": 0.09931106959364783, "grad_norm": 0.46978044509887695, "learning_rate": 9.927028604786925e-06, "loss": 0.2357, "step": 3402 }, { "epoch": 0.09934026156001868, "grad_norm": 0.4082478880882263, "learning_rate": 9.929947460595447e-06, "loss": 0.2147, "step": 3403 }, { "epoch": 0.09936945352638954, "grad_norm": 0.43842464685440063, "learning_rate": 9.93286631640397e-06, "loss": 0.242, "step": 3404 }, { "epoch": 0.0993986454927604, "grad_norm": 0.46988385915756226, "learning_rate": 9.935785172212492e-06, "loss": 0.2594, "step": 3405 }, { "epoch": 0.09942783745913125, "grad_norm": 0.4685498774051666, "learning_rate": 9.938704028021017e-06, "loss": 0.2628, "step": 3406 }, { "epoch": 0.09945702942550211, "grad_norm": 0.48974356055259705, "learning_rate": 9.941622883829539e-06, "loss": 0.2739, "step": 3407 }, { "epoch": 0.09948622139187295, "grad_norm": 0.7725608348846436, "learning_rate": 9.944541739638063e-06, "loss": 0.2889, "step": 3408 }, { "epoch": 0.0995154133582438, "grad_norm": 0.4563198685646057, "learning_rate": 9.947460595446586e-06, "loss": 0.3004, "step": 3409 }, { "epoch": 0.09954460532461466, "grad_norm": 0.43375611305236816, "learning_rate": 9.950379451255108e-06, "loss": 0.2751, "step": 3410 }, { "epoch": 0.09957379729098552, "grad_norm": 0.39453476667404175, "learning_rate": 9.953298307063632e-06, "loss": 0.2501, "step": 3411 }, { "epoch": 0.09960298925735638, "grad_norm": 0.5597988963127136, "learning_rate": 9.956217162872155e-06, "loss": 0.2317, "step": 3412 }, { "epoch": 0.09963218122372723, "grad_norm": 0.502343475818634, "learning_rate": 9.959136018680679e-06, "loss": 0.2812, "step": 3413 }, { "epoch": 0.09966137319009809, "grad_norm": 0.4244508743286133, "learning_rate": 9.962054874489202e-06, "loss": 0.2372, "step": 3414 }, { "epoch": 0.09969056515646894, "grad_norm": 0.6881104111671448, "learning_rate": 9.964973730297724e-06, "loss": 0.2927, "step": 3415 }, { "epoch": 0.0997197571228398, "grad_norm": 0.5579330325126648, "learning_rate": 9.967892586106247e-06, "loss": 0.2689, "step": 3416 }, { "epoch": 0.09974894908921064, "grad_norm": 0.4871680438518524, "learning_rate": 9.97081144191477e-06, "loss": 0.2361, "step": 3417 }, { "epoch": 0.0997781410555815, "grad_norm": 0.43077683448791504, "learning_rate": 9.973730297723293e-06, "loss": 0.2511, "step": 3418 }, { "epoch": 0.09980733302195235, "grad_norm": 0.4526030421257019, "learning_rate": 9.976649153531816e-06, "loss": 0.2312, "step": 3419 }, { "epoch": 0.09983652498832321, "grad_norm": 0.3749578297138214, "learning_rate": 9.979568009340338e-06, "loss": 0.1954, "step": 3420 }, { "epoch": 0.09986571695469407, "grad_norm": 0.4681192934513092, "learning_rate": 9.982486865148862e-06, "loss": 0.3312, "step": 3421 }, { "epoch": 0.09989490892106492, "grad_norm": 0.4180554151535034, "learning_rate": 9.985405720957385e-06, "loss": 0.2674, "step": 3422 }, { "epoch": 0.09992410088743578, "grad_norm": 0.4997295141220093, "learning_rate": 9.988324576765909e-06, "loss": 0.2315, "step": 3423 }, { "epoch": 0.09995329285380664, "grad_norm": 0.45281997323036194, "learning_rate": 9.991243432574432e-06, "loss": 0.2656, "step": 3424 }, { "epoch": 0.09998248482017749, "grad_norm": 0.5013462901115417, "learning_rate": 9.994162288382954e-06, "loss": 0.2696, "step": 3425 }, { "epoch": 0.10001167678654835, "grad_norm": 0.4607226252555847, "learning_rate": 9.997081144191477e-06, "loss": 0.281, "step": 3426 }, { "epoch": 0.10004086875291919, "grad_norm": 0.43226757645606995, "learning_rate": 1e-05, "loss": 0.3305, "step": 3427 }, { "epoch": 0.10007006071929005, "grad_norm": 0.7417443990707397, "learning_rate": 9.999999974040718e-06, "loss": 0.2651, "step": 3428 }, { "epoch": 0.1000992526856609, "grad_norm": 0.4533781409263611, "learning_rate": 9.999999896162867e-06, "loss": 0.3081, "step": 3429 }, { "epoch": 0.10012844465203176, "grad_norm": 0.47850218415260315, "learning_rate": 9.999999766366449e-06, "loss": 0.2935, "step": 3430 }, { "epoch": 0.10015763661840262, "grad_norm": 0.5229983925819397, "learning_rate": 9.999999584651468e-06, "loss": 0.266, "step": 3431 }, { "epoch": 0.10018682858477347, "grad_norm": 0.5658369660377502, "learning_rate": 9.999999351017922e-06, "loss": 0.2806, "step": 3432 }, { "epoch": 0.10021602055114433, "grad_norm": 0.4450022280216217, "learning_rate": 9.999999065465818e-06, "loss": 0.2462, "step": 3433 }, { "epoch": 0.10024521251751518, "grad_norm": 0.4779222011566162, "learning_rate": 9.999998727995154e-06, "loss": 0.2811, "step": 3434 }, { "epoch": 0.10027440448388604, "grad_norm": 0.388309508562088, "learning_rate": 9.999998338605936e-06, "loss": 0.2394, "step": 3435 }, { "epoch": 0.1003035964502569, "grad_norm": 0.5007010698318481, "learning_rate": 9.999997897298169e-06, "loss": 0.2569, "step": 3436 }, { "epoch": 0.10033278841662774, "grad_norm": 0.42961427569389343, "learning_rate": 9.999997404071856e-06, "loss": 0.2441, "step": 3437 }, { "epoch": 0.1003619803829986, "grad_norm": 0.4813310205936432, "learning_rate": 9.999996858927004e-06, "loss": 0.265, "step": 3438 }, { "epoch": 0.10039117234936945, "grad_norm": 0.8553277254104614, "learning_rate": 9.999996261863615e-06, "loss": 0.2929, "step": 3439 }, { "epoch": 0.10042036431574031, "grad_norm": 0.6732898950576782, "learning_rate": 9.9999956128817e-06, "loss": 0.2343, "step": 3440 }, { "epoch": 0.10044955628211116, "grad_norm": 0.424445241689682, "learning_rate": 9.99999491198126e-06, "loss": 0.2985, "step": 3441 }, { "epoch": 0.10047874824848202, "grad_norm": 0.4568530321121216, "learning_rate": 9.999994159162308e-06, "loss": 0.2367, "step": 3442 }, { "epoch": 0.10050794021485288, "grad_norm": 0.4831920564174652, "learning_rate": 9.999993354424847e-06, "loss": 0.2767, "step": 3443 }, { "epoch": 0.10053713218122373, "grad_norm": 0.7273368239402771, "learning_rate": 9.999992497768888e-06, "loss": 0.2509, "step": 3444 }, { "epoch": 0.10056632414759459, "grad_norm": 0.4916246235370636, "learning_rate": 9.999991589194442e-06, "loss": 0.2471, "step": 3445 }, { "epoch": 0.10059551611396543, "grad_norm": 0.4806671738624573, "learning_rate": 9.999990628701515e-06, "loss": 0.2543, "step": 3446 }, { "epoch": 0.10062470808033629, "grad_norm": 0.46213021874427795, "learning_rate": 9.999989616290118e-06, "loss": 0.275, "step": 3447 }, { "epoch": 0.10065390004670714, "grad_norm": 0.46491968631744385, "learning_rate": 9.99998855196026e-06, "loss": 0.2519, "step": 3448 }, { "epoch": 0.100683092013078, "grad_norm": 0.4881919026374817, "learning_rate": 9.999987435711956e-06, "loss": 0.266, "step": 3449 }, { "epoch": 0.10071228397944886, "grad_norm": 0.5337669253349304, "learning_rate": 9.999986267545213e-06, "loss": 0.2784, "step": 3450 }, { "epoch": 0.10074147594581971, "grad_norm": 0.4624902009963989, "learning_rate": 9.999985047460045e-06, "loss": 0.2506, "step": 3451 }, { "epoch": 0.10077066791219057, "grad_norm": 0.4414718449115753, "learning_rate": 9.999983775456467e-06, "loss": 0.218, "step": 3452 }, { "epoch": 0.10079985987856142, "grad_norm": 0.5352530479431152, "learning_rate": 9.999982451534489e-06, "loss": 0.2482, "step": 3453 }, { "epoch": 0.10082905184493228, "grad_norm": 0.515105128288269, "learning_rate": 9.999981075694126e-06, "loss": 0.2053, "step": 3454 }, { "epoch": 0.10085824381130314, "grad_norm": 0.5607273578643799, "learning_rate": 9.999979647935392e-06, "loss": 0.2445, "step": 3455 }, { "epoch": 0.10088743577767398, "grad_norm": 0.5155637860298157, "learning_rate": 9.999978168258301e-06, "loss": 0.2799, "step": 3456 }, { "epoch": 0.10091662774404483, "grad_norm": 0.5480974912643433, "learning_rate": 9.999976636662872e-06, "loss": 0.2607, "step": 3457 }, { "epoch": 0.10094581971041569, "grad_norm": 0.4968121349811554, "learning_rate": 9.999975053149116e-06, "loss": 0.2405, "step": 3458 }, { "epoch": 0.10097501167678655, "grad_norm": 0.45413878560066223, "learning_rate": 9.999973417717053e-06, "loss": 0.2633, "step": 3459 }, { "epoch": 0.1010042036431574, "grad_norm": 0.4397343099117279, "learning_rate": 9.999971730366698e-06, "loss": 0.2709, "step": 3460 }, { "epoch": 0.10103339560952826, "grad_norm": 0.48542582988739014, "learning_rate": 9.999969991098069e-06, "loss": 0.264, "step": 3461 }, { "epoch": 0.10106258757589912, "grad_norm": 0.4310370981693268, "learning_rate": 9.999968199911183e-06, "loss": 0.2896, "step": 3462 }, { "epoch": 0.10109177954226997, "grad_norm": 0.5202548503875732, "learning_rate": 9.999966356806064e-06, "loss": 0.2449, "step": 3463 }, { "epoch": 0.10112097150864083, "grad_norm": 0.5158066153526306, "learning_rate": 9.999964461782723e-06, "loss": 0.2533, "step": 3464 }, { "epoch": 0.10115016347501167, "grad_norm": 0.643765389919281, "learning_rate": 9.999962514841186e-06, "loss": 0.2123, "step": 3465 }, { "epoch": 0.10117935544138253, "grad_norm": 0.5214406251907349, "learning_rate": 9.99996051598147e-06, "loss": 0.2467, "step": 3466 }, { "epoch": 0.10120854740775338, "grad_norm": 0.5810046792030334, "learning_rate": 9.999958465203596e-06, "loss": 0.299, "step": 3467 }, { "epoch": 0.10123773937412424, "grad_norm": 0.4332024157047272, "learning_rate": 9.999956362507586e-06, "loss": 0.2617, "step": 3468 }, { "epoch": 0.1012669313404951, "grad_norm": 0.46486303210258484, "learning_rate": 9.999954207893463e-06, "loss": 0.262, "step": 3469 }, { "epoch": 0.10129612330686595, "grad_norm": 0.5402354598045349, "learning_rate": 9.999952001361248e-06, "loss": 0.2657, "step": 3470 }, { "epoch": 0.10132531527323681, "grad_norm": 0.6409156322479248, "learning_rate": 9.999949742910963e-06, "loss": 0.2254, "step": 3471 }, { "epoch": 0.10135450723960766, "grad_norm": 0.5257748961448669, "learning_rate": 9.999947432542632e-06, "loss": 0.2505, "step": 3472 }, { "epoch": 0.10138369920597852, "grad_norm": 0.7047845721244812, "learning_rate": 9.99994507025628e-06, "loss": 0.2672, "step": 3473 }, { "epoch": 0.10141289117234938, "grad_norm": 0.43321898579597473, "learning_rate": 9.999942656051933e-06, "loss": 0.2425, "step": 3474 }, { "epoch": 0.10144208313872022, "grad_norm": 0.4884166717529297, "learning_rate": 9.999940189929613e-06, "loss": 0.2796, "step": 3475 }, { "epoch": 0.10147127510509107, "grad_norm": 0.4531572759151459, "learning_rate": 9.999937671889346e-06, "loss": 0.2887, "step": 3476 }, { "epoch": 0.10150046707146193, "grad_norm": 0.4650074541568756, "learning_rate": 9.99993510193116e-06, "loss": 0.2203, "step": 3477 }, { "epoch": 0.10152965903783279, "grad_norm": 0.4666648805141449, "learning_rate": 9.999932480055079e-06, "loss": 0.2814, "step": 3478 }, { "epoch": 0.10155885100420364, "grad_norm": 0.6305480003356934, "learning_rate": 9.999929806261133e-06, "loss": 0.1966, "step": 3479 }, { "epoch": 0.1015880429705745, "grad_norm": 0.4538763165473938, "learning_rate": 9.999927080549348e-06, "loss": 0.2669, "step": 3480 }, { "epoch": 0.10161723493694536, "grad_norm": 0.4316699504852295, "learning_rate": 9.999924302919752e-06, "loss": 0.2539, "step": 3481 }, { "epoch": 0.10164642690331621, "grad_norm": 0.5068016648292542, "learning_rate": 9.999921473372375e-06, "loss": 0.2407, "step": 3482 }, { "epoch": 0.10167561886968707, "grad_norm": 0.4546736180782318, "learning_rate": 9.999918591907247e-06, "loss": 0.2288, "step": 3483 }, { "epoch": 0.10170481083605791, "grad_norm": 0.408786416053772, "learning_rate": 9.999915658524398e-06, "loss": 0.2475, "step": 3484 }, { "epoch": 0.10173400280242877, "grad_norm": 0.5390713214874268, "learning_rate": 9.999912673223855e-06, "loss": 0.2666, "step": 3485 }, { "epoch": 0.10176319476879962, "grad_norm": 0.5161710381507874, "learning_rate": 9.999909636005654e-06, "loss": 0.2586, "step": 3486 }, { "epoch": 0.10179238673517048, "grad_norm": 0.45037931203842163, "learning_rate": 9.999906546869823e-06, "loss": 0.2416, "step": 3487 }, { "epoch": 0.10182157870154133, "grad_norm": 0.4255348742008209, "learning_rate": 9.999903405816394e-06, "loss": 0.2765, "step": 3488 }, { "epoch": 0.10185077066791219, "grad_norm": 0.46304944157600403, "learning_rate": 9.9999002128454e-06, "loss": 0.2601, "step": 3489 }, { "epoch": 0.10187996263428305, "grad_norm": 0.5172858834266663, "learning_rate": 9.999896967956876e-06, "loss": 0.2892, "step": 3490 }, { "epoch": 0.1019091546006539, "grad_norm": 0.4571046233177185, "learning_rate": 9.999893671150855e-06, "loss": 0.2556, "step": 3491 }, { "epoch": 0.10193834656702476, "grad_norm": 0.5083812475204468, "learning_rate": 9.99989032242737e-06, "loss": 0.274, "step": 3492 }, { "epoch": 0.10196753853339562, "grad_norm": 0.4727131724357605, "learning_rate": 9.999886921786457e-06, "loss": 0.2612, "step": 3493 }, { "epoch": 0.10199673049976646, "grad_norm": 0.38893452286720276, "learning_rate": 9.99988346922815e-06, "loss": 0.2491, "step": 3494 }, { "epoch": 0.10202592246613731, "grad_norm": 0.48855963349342346, "learning_rate": 9.999879964752487e-06, "loss": 0.2684, "step": 3495 }, { "epoch": 0.10205511443250817, "grad_norm": 0.4406973719596863, "learning_rate": 9.999876408359502e-06, "loss": 0.2634, "step": 3496 }, { "epoch": 0.10208430639887903, "grad_norm": 0.48522424697875977, "learning_rate": 9.999872800049233e-06, "loss": 0.2976, "step": 3497 }, { "epoch": 0.10211349836524988, "grad_norm": 0.5327715873718262, "learning_rate": 9.999869139821718e-06, "loss": 0.2764, "step": 3498 }, { "epoch": 0.10214269033162074, "grad_norm": 0.41100582480430603, "learning_rate": 9.999865427676994e-06, "loss": 0.2151, "step": 3499 }, { "epoch": 0.1021718822979916, "grad_norm": 0.42336586117744446, "learning_rate": 9.9998616636151e-06, "loss": 0.2346, "step": 3500 }, { "epoch": 0.10220107426436245, "grad_norm": 0.4148586392402649, "learning_rate": 9.999857847636077e-06, "loss": 0.2414, "step": 3501 }, { "epoch": 0.10223026623073331, "grad_norm": 0.5983000993728638, "learning_rate": 9.99985397973996e-06, "loss": 0.256, "step": 3502 }, { "epoch": 0.10225945819710416, "grad_norm": 0.4473969638347626, "learning_rate": 9.999850059926794e-06, "loss": 0.2432, "step": 3503 }, { "epoch": 0.102288650163475, "grad_norm": 0.3952755331993103, "learning_rate": 9.999846088196616e-06, "loss": 0.2275, "step": 3504 }, { "epoch": 0.10231784212984586, "grad_norm": 0.4106093645095825, "learning_rate": 9.999842064549469e-06, "loss": 0.2392, "step": 3505 }, { "epoch": 0.10234703409621672, "grad_norm": 0.49082109332084656, "learning_rate": 9.999837988985396e-06, "loss": 0.2936, "step": 3506 }, { "epoch": 0.10237622606258757, "grad_norm": 0.38583725690841675, "learning_rate": 9.999833861504436e-06, "loss": 0.2111, "step": 3507 }, { "epoch": 0.10240541802895843, "grad_norm": 0.6518524289131165, "learning_rate": 9.999829682106635e-06, "loss": 0.2578, "step": 3508 }, { "epoch": 0.10243460999532929, "grad_norm": 0.5533523559570312, "learning_rate": 9.999825450792036e-06, "loss": 0.3161, "step": 3509 }, { "epoch": 0.10246380196170014, "grad_norm": 0.3682178258895874, "learning_rate": 9.99982116756068e-06, "loss": 0.2475, "step": 3510 }, { "epoch": 0.102492993928071, "grad_norm": 0.4929085671901703, "learning_rate": 9.999816832412614e-06, "loss": 0.2395, "step": 3511 }, { "epoch": 0.10252218589444186, "grad_norm": 0.424411416053772, "learning_rate": 9.999812445347885e-06, "loss": 0.2742, "step": 3512 }, { "epoch": 0.1025513778608127, "grad_norm": 0.4430729150772095, "learning_rate": 9.999808006366534e-06, "loss": 0.2772, "step": 3513 }, { "epoch": 0.10258056982718355, "grad_norm": 0.5010749101638794, "learning_rate": 9.999803515468609e-06, "loss": 0.2769, "step": 3514 }, { "epoch": 0.10260976179355441, "grad_norm": 0.44146856665611267, "learning_rate": 9.999798972654157e-06, "loss": 0.2535, "step": 3515 }, { "epoch": 0.10263895375992527, "grad_norm": 0.4625997841358185, "learning_rate": 9.999794377923227e-06, "loss": 0.2561, "step": 3516 }, { "epoch": 0.10266814572629612, "grad_norm": 0.4564024806022644, "learning_rate": 9.999789731275865e-06, "loss": 0.2612, "step": 3517 }, { "epoch": 0.10269733769266698, "grad_norm": 0.47320154309272766, "learning_rate": 9.999785032712115e-06, "loss": 0.2908, "step": 3518 }, { "epoch": 0.10272652965903784, "grad_norm": 0.46512657403945923, "learning_rate": 9.999780282232033e-06, "loss": 0.2459, "step": 3519 }, { "epoch": 0.10275572162540869, "grad_norm": 0.447064071893692, "learning_rate": 9.999775479835666e-06, "loss": 0.269, "step": 3520 }, { "epoch": 0.10278491359177955, "grad_norm": 0.41926226019859314, "learning_rate": 9.999770625523059e-06, "loss": 0.2221, "step": 3521 }, { "epoch": 0.1028141055581504, "grad_norm": 0.4129023551940918, "learning_rate": 9.99976571929427e-06, "loss": 0.2554, "step": 3522 }, { "epoch": 0.10284329752452125, "grad_norm": 0.5644981265068054, "learning_rate": 9.999760761149347e-06, "loss": 0.3216, "step": 3523 }, { "epoch": 0.1028724894908921, "grad_norm": 0.6159257888793945, "learning_rate": 9.999755751088338e-06, "loss": 0.2656, "step": 3524 }, { "epoch": 0.10290168145726296, "grad_norm": 0.3863726258277893, "learning_rate": 9.999750689111298e-06, "loss": 0.266, "step": 3525 }, { "epoch": 0.10293087342363381, "grad_norm": 0.4363173842430115, "learning_rate": 9.999745575218282e-06, "loss": 0.2714, "step": 3526 }, { "epoch": 0.10296006539000467, "grad_norm": 0.41319242119789124, "learning_rate": 9.999740409409338e-06, "loss": 0.2345, "step": 3527 }, { "epoch": 0.10298925735637553, "grad_norm": 0.45294153690338135, "learning_rate": 9.999735191684522e-06, "loss": 0.2194, "step": 3528 }, { "epoch": 0.10301844932274638, "grad_norm": 0.4138801693916321, "learning_rate": 9.99972992204389e-06, "loss": 0.2988, "step": 3529 }, { "epoch": 0.10304764128911724, "grad_norm": 0.4699990749359131, "learning_rate": 9.999724600487495e-06, "loss": 0.2791, "step": 3530 }, { "epoch": 0.1030768332554881, "grad_norm": 0.5266276597976685, "learning_rate": 9.999719227015393e-06, "loss": 0.2665, "step": 3531 }, { "epoch": 0.10310602522185894, "grad_norm": 0.48828378319740295, "learning_rate": 9.999713801627637e-06, "loss": 0.2511, "step": 3532 }, { "epoch": 0.1031352171882298, "grad_norm": 0.4613189399242401, "learning_rate": 9.999708324324286e-06, "loss": 0.2892, "step": 3533 }, { "epoch": 0.10316440915460065, "grad_norm": 0.5157930254936218, "learning_rate": 9.999702795105397e-06, "loss": 0.2929, "step": 3534 }, { "epoch": 0.1031936011209715, "grad_norm": 0.38616079092025757, "learning_rate": 9.999697213971028e-06, "loss": 0.2734, "step": 3535 }, { "epoch": 0.10322279308734236, "grad_norm": 0.4675627052783966, "learning_rate": 9.999691580921234e-06, "loss": 0.2731, "step": 3536 }, { "epoch": 0.10325198505371322, "grad_norm": 0.4215138852596283, "learning_rate": 9.999685895956075e-06, "loss": 0.2443, "step": 3537 }, { "epoch": 0.10328117702008408, "grad_norm": 0.44327303767204285, "learning_rate": 9.99968015907561e-06, "loss": 0.2866, "step": 3538 }, { "epoch": 0.10331036898645493, "grad_norm": 0.3624249994754791, "learning_rate": 9.9996743702799e-06, "loss": 0.2132, "step": 3539 }, { "epoch": 0.10333956095282579, "grad_norm": 0.4332255721092224, "learning_rate": 9.999668529569003e-06, "loss": 0.2735, "step": 3540 }, { "epoch": 0.10336875291919664, "grad_norm": 0.444635808467865, "learning_rate": 9.999662636942982e-06, "loss": 0.2671, "step": 3541 }, { "epoch": 0.10339794488556749, "grad_norm": 0.4332854747772217, "learning_rate": 9.999656692401895e-06, "loss": 0.2644, "step": 3542 }, { "epoch": 0.10342713685193834, "grad_norm": 0.482131689786911, "learning_rate": 9.999650695945807e-06, "loss": 0.298, "step": 3543 }, { "epoch": 0.1034563288183092, "grad_norm": 0.41215065121650696, "learning_rate": 9.999644647574778e-06, "loss": 0.2854, "step": 3544 }, { "epoch": 0.10348552078468005, "grad_norm": 0.4443771243095398, "learning_rate": 9.99963854728887e-06, "loss": 0.2471, "step": 3545 }, { "epoch": 0.10351471275105091, "grad_norm": 0.43936726450920105, "learning_rate": 9.99963239508815e-06, "loss": 0.2126, "step": 3546 }, { "epoch": 0.10354390471742177, "grad_norm": 0.48598340153694153, "learning_rate": 9.99962619097268e-06, "loss": 0.2597, "step": 3547 }, { "epoch": 0.10357309668379262, "grad_norm": 0.44938400387763977, "learning_rate": 9.999619934942521e-06, "loss": 0.3006, "step": 3548 }, { "epoch": 0.10360228865016348, "grad_norm": 0.4385665953159332, "learning_rate": 9.999613626997744e-06, "loss": 0.2356, "step": 3549 }, { "epoch": 0.10363148061653434, "grad_norm": 0.5090091824531555, "learning_rate": 9.999607267138412e-06, "loss": 0.2456, "step": 3550 }, { "epoch": 0.10366067258290518, "grad_norm": 0.5474019050598145, "learning_rate": 9.999600855364589e-06, "loss": 0.2017, "step": 3551 }, { "epoch": 0.10368986454927603, "grad_norm": 0.7132638096809387, "learning_rate": 9.999594391676344e-06, "loss": 0.27, "step": 3552 }, { "epoch": 0.10371905651564689, "grad_norm": 0.48981773853302, "learning_rate": 9.999587876073742e-06, "loss": 0.2207, "step": 3553 }, { "epoch": 0.10374824848201775, "grad_norm": 0.40824705362319946, "learning_rate": 9.999581308556853e-06, "loss": 0.2708, "step": 3554 }, { "epoch": 0.1037774404483886, "grad_norm": 0.6386356949806213, "learning_rate": 9.999574689125745e-06, "loss": 0.2569, "step": 3555 }, { "epoch": 0.10380663241475946, "grad_norm": 0.3845299482345581, "learning_rate": 9.999568017780486e-06, "loss": 0.2038, "step": 3556 }, { "epoch": 0.10383582438113031, "grad_norm": 0.4382086992263794, "learning_rate": 9.999561294521145e-06, "loss": 0.2199, "step": 3557 }, { "epoch": 0.10386501634750117, "grad_norm": 0.44965240359306335, "learning_rate": 9.999554519347792e-06, "loss": 0.2347, "step": 3558 }, { "epoch": 0.10389420831387203, "grad_norm": 0.43333739042282104, "learning_rate": 9.999547692260499e-06, "loss": 0.2633, "step": 3559 }, { "epoch": 0.10392340028024288, "grad_norm": 0.45460134744644165, "learning_rate": 9.999540813259332e-06, "loss": 0.2458, "step": 3560 }, { "epoch": 0.10395259224661373, "grad_norm": 0.4192745089530945, "learning_rate": 9.999533882344368e-06, "loss": 0.2551, "step": 3561 }, { "epoch": 0.10398178421298458, "grad_norm": 0.4205072522163391, "learning_rate": 9.999526899515675e-06, "loss": 0.2244, "step": 3562 }, { "epoch": 0.10401097617935544, "grad_norm": 0.39557787775993347, "learning_rate": 9.999519864773329e-06, "loss": 0.2144, "step": 3563 }, { "epoch": 0.1040401681457263, "grad_norm": 0.4025006890296936, "learning_rate": 9.999512778117399e-06, "loss": 0.2523, "step": 3564 }, { "epoch": 0.10406936011209715, "grad_norm": 0.42975011467933655, "learning_rate": 9.999505639547965e-06, "loss": 0.2432, "step": 3565 }, { "epoch": 0.104098552078468, "grad_norm": 0.42724964022636414, "learning_rate": 9.999498449065092e-06, "loss": 0.2021, "step": 3566 }, { "epoch": 0.10412774404483886, "grad_norm": 0.40712493658065796, "learning_rate": 9.999491206668861e-06, "loss": 0.2308, "step": 3567 }, { "epoch": 0.10415693601120972, "grad_norm": 0.45242637395858765, "learning_rate": 9.999483912359348e-06, "loss": 0.2496, "step": 3568 }, { "epoch": 0.10418612797758058, "grad_norm": 0.4517718255519867, "learning_rate": 9.999476566136626e-06, "loss": 0.2388, "step": 3569 }, { "epoch": 0.10421531994395142, "grad_norm": 0.4236917793750763, "learning_rate": 9.99946916800077e-06, "loss": 0.2121, "step": 3570 }, { "epoch": 0.10424451191032227, "grad_norm": 0.44784945249557495, "learning_rate": 9.99946171795186e-06, "loss": 0.2253, "step": 3571 }, { "epoch": 0.10427370387669313, "grad_norm": 0.421481728553772, "learning_rate": 9.999454215989972e-06, "loss": 0.2556, "step": 3572 }, { "epoch": 0.10430289584306399, "grad_norm": 0.38598644733428955, "learning_rate": 9.999446662115183e-06, "loss": 0.2337, "step": 3573 }, { "epoch": 0.10433208780943484, "grad_norm": 0.46155911684036255, "learning_rate": 9.999439056327574e-06, "loss": 0.2523, "step": 3574 }, { "epoch": 0.1043612797758057, "grad_norm": 0.4348217844963074, "learning_rate": 9.99943139862722e-06, "loss": 0.2564, "step": 3575 }, { "epoch": 0.10439047174217655, "grad_norm": 0.6364719867706299, "learning_rate": 9.999423689014205e-06, "loss": 0.2727, "step": 3576 }, { "epoch": 0.10441966370854741, "grad_norm": 0.4246271252632141, "learning_rate": 9.999415927488604e-06, "loss": 0.2951, "step": 3577 }, { "epoch": 0.10444885567491827, "grad_norm": 0.47250205278396606, "learning_rate": 9.999408114050504e-06, "loss": 0.2794, "step": 3578 }, { "epoch": 0.10447804764128912, "grad_norm": 0.4377366900444031, "learning_rate": 9.999400248699983e-06, "loss": 0.2855, "step": 3579 }, { "epoch": 0.10450723960765997, "grad_norm": 0.45332345366477966, "learning_rate": 9.999392331437119e-06, "loss": 0.266, "step": 3580 }, { "epoch": 0.10453643157403082, "grad_norm": 0.42368170619010925, "learning_rate": 9.999384362262e-06, "loss": 0.2749, "step": 3581 }, { "epoch": 0.10456562354040168, "grad_norm": 0.3994462490081787, "learning_rate": 9.999376341174704e-06, "loss": 0.2334, "step": 3582 }, { "epoch": 0.10459481550677253, "grad_norm": 0.39163872599601746, "learning_rate": 9.999368268175317e-06, "loss": 0.2524, "step": 3583 }, { "epoch": 0.10462400747314339, "grad_norm": 0.39242222905158997, "learning_rate": 9.999360143263924e-06, "loss": 0.2818, "step": 3584 }, { "epoch": 0.10465319943951425, "grad_norm": 0.4156961143016815, "learning_rate": 9.999351966440607e-06, "loss": 0.2668, "step": 3585 }, { "epoch": 0.1046823914058851, "grad_norm": 0.4245421588420868, "learning_rate": 9.999343737705451e-06, "loss": 0.2796, "step": 3586 }, { "epoch": 0.10471158337225596, "grad_norm": 0.39269939064979553, "learning_rate": 9.999335457058543e-06, "loss": 0.2371, "step": 3587 }, { "epoch": 0.10474077533862682, "grad_norm": 0.47227704524993896, "learning_rate": 9.999327124499969e-06, "loss": 0.2764, "step": 3588 }, { "epoch": 0.10476996730499767, "grad_norm": 0.4092908203601837, "learning_rate": 9.999318740029813e-06, "loss": 0.252, "step": 3589 }, { "epoch": 0.10479915927136851, "grad_norm": 0.36481449007987976, "learning_rate": 9.999310303648164e-06, "loss": 0.2211, "step": 3590 }, { "epoch": 0.10482835123773937, "grad_norm": 1.1107349395751953, "learning_rate": 9.99930181535511e-06, "loss": 0.2204, "step": 3591 }, { "epoch": 0.10485754320411023, "grad_norm": 0.43805089592933655, "learning_rate": 9.999293275150737e-06, "loss": 0.2317, "step": 3592 }, { "epoch": 0.10488673517048108, "grad_norm": 0.4364378750324249, "learning_rate": 9.999284683035135e-06, "loss": 0.2716, "step": 3593 }, { "epoch": 0.10491592713685194, "grad_norm": 0.4507754147052765, "learning_rate": 9.999276039008395e-06, "loss": 0.2396, "step": 3594 }, { "epoch": 0.1049451191032228, "grad_norm": 0.4560026228427887, "learning_rate": 9.999267343070604e-06, "loss": 0.3136, "step": 3595 }, { "epoch": 0.10497431106959365, "grad_norm": 0.5091542601585388, "learning_rate": 9.999258595221854e-06, "loss": 0.2484, "step": 3596 }, { "epoch": 0.10500350303596451, "grad_norm": 0.43983033299446106, "learning_rate": 9.999249795462235e-06, "loss": 0.2781, "step": 3597 }, { "epoch": 0.10503269500233536, "grad_norm": 0.4413314163684845, "learning_rate": 9.999240943791838e-06, "loss": 0.2561, "step": 3598 }, { "epoch": 0.1050618869687062, "grad_norm": 0.4019128680229187, "learning_rate": 9.999232040210756e-06, "loss": 0.2295, "step": 3599 }, { "epoch": 0.10509107893507706, "grad_norm": 0.38173484802246094, "learning_rate": 9.99922308471908e-06, "loss": 0.2422, "step": 3600 }, { "epoch": 0.10512027090144792, "grad_norm": 0.44397616386413574, "learning_rate": 9.999214077316906e-06, "loss": 0.2118, "step": 3601 }, { "epoch": 0.10514946286781877, "grad_norm": 0.6045162677764893, "learning_rate": 9.999205018004323e-06, "loss": 0.2503, "step": 3602 }, { "epoch": 0.10517865483418963, "grad_norm": 0.4510621428489685, "learning_rate": 9.999195906781429e-06, "loss": 0.3213, "step": 3603 }, { "epoch": 0.10520784680056049, "grad_norm": 0.4174247086048126, "learning_rate": 9.999186743648316e-06, "loss": 0.2513, "step": 3604 }, { "epoch": 0.10523703876693134, "grad_norm": 0.44664281606674194, "learning_rate": 9.999177528605081e-06, "loss": 0.2937, "step": 3605 }, { "epoch": 0.1052662307333022, "grad_norm": 1.9263927936553955, "learning_rate": 9.99916826165182e-06, "loss": 0.2525, "step": 3606 }, { "epoch": 0.10529542269967306, "grad_norm": 0.3750154376029968, "learning_rate": 9.999158942788627e-06, "loss": 0.2303, "step": 3607 }, { "epoch": 0.10532461466604391, "grad_norm": 0.3949945271015167, "learning_rate": 9.999149572015601e-06, "loss": 0.2443, "step": 3608 }, { "epoch": 0.10535380663241475, "grad_norm": 0.47516217827796936, "learning_rate": 9.999140149332837e-06, "loss": 0.255, "step": 3609 }, { "epoch": 0.10538299859878561, "grad_norm": 0.40659821033477783, "learning_rate": 9.999130674740434e-06, "loss": 0.2816, "step": 3610 }, { "epoch": 0.10541219056515647, "grad_norm": 0.4598807096481323, "learning_rate": 9.99912114823849e-06, "loss": 0.318, "step": 3611 }, { "epoch": 0.10544138253152732, "grad_norm": 0.4385799169540405, "learning_rate": 9.999111569827106e-06, "loss": 0.2394, "step": 3612 }, { "epoch": 0.10547057449789818, "grad_norm": 0.40681320428848267, "learning_rate": 9.99910193950638e-06, "loss": 0.2374, "step": 3613 }, { "epoch": 0.10549976646426903, "grad_norm": 0.4909695088863373, "learning_rate": 9.99909225727641e-06, "loss": 0.2419, "step": 3614 }, { "epoch": 0.10552895843063989, "grad_norm": 1.3628536462783813, "learning_rate": 9.9990825231373e-06, "loss": 0.2674, "step": 3615 }, { "epoch": 0.10555815039701075, "grad_norm": 0.3992079198360443, "learning_rate": 9.999072737089149e-06, "loss": 0.2393, "step": 3616 }, { "epoch": 0.1055873423633816, "grad_norm": 0.46889528632164, "learning_rate": 9.99906289913206e-06, "loss": 0.2312, "step": 3617 }, { "epoch": 0.10561653432975245, "grad_norm": 0.41351965069770813, "learning_rate": 9.999053009266132e-06, "loss": 0.245, "step": 3618 }, { "epoch": 0.1056457262961233, "grad_norm": 0.4825429320335388, "learning_rate": 9.999043067491471e-06, "loss": 0.2284, "step": 3619 }, { "epoch": 0.10567491826249416, "grad_norm": 0.43755877017974854, "learning_rate": 9.99903307380818e-06, "loss": 0.2284, "step": 3620 }, { "epoch": 0.10570411022886501, "grad_norm": 0.4144415557384491, "learning_rate": 9.999023028216361e-06, "loss": 0.2174, "step": 3621 }, { "epoch": 0.10573330219523587, "grad_norm": 0.46705785393714905, "learning_rate": 9.999012930716121e-06, "loss": 0.2416, "step": 3622 }, { "epoch": 0.10576249416160673, "grad_norm": 0.41682836413383484, "learning_rate": 9.99900278130756e-06, "loss": 0.2414, "step": 3623 }, { "epoch": 0.10579168612797758, "grad_norm": 0.40602612495422363, "learning_rate": 9.99899257999079e-06, "loss": 0.2384, "step": 3624 }, { "epoch": 0.10582087809434844, "grad_norm": 0.44657301902770996, "learning_rate": 9.998982326765912e-06, "loss": 0.2842, "step": 3625 }, { "epoch": 0.1058500700607193, "grad_norm": 0.47165557742118835, "learning_rate": 9.998972021633034e-06, "loss": 0.2349, "step": 3626 }, { "epoch": 0.10587926202709015, "grad_norm": 0.41238901019096375, "learning_rate": 9.998961664592261e-06, "loss": 0.2659, "step": 3627 }, { "epoch": 0.105908453993461, "grad_norm": 0.36660000681877136, "learning_rate": 9.998951255643703e-06, "loss": 0.2422, "step": 3628 }, { "epoch": 0.10593764595983185, "grad_norm": 0.3913704454898834, "learning_rate": 9.998940794787468e-06, "loss": 0.2156, "step": 3629 }, { "epoch": 0.1059668379262027, "grad_norm": 0.5767411589622498, "learning_rate": 9.998930282023666e-06, "loss": 0.2775, "step": 3630 }, { "epoch": 0.10599602989257356, "grad_norm": 0.4449446201324463, "learning_rate": 9.998919717352402e-06, "loss": 0.3017, "step": 3631 }, { "epoch": 0.10602522185894442, "grad_norm": 0.5071635246276855, "learning_rate": 9.99890910077379e-06, "loss": 0.2637, "step": 3632 }, { "epoch": 0.10605441382531527, "grad_norm": 0.45610252022743225, "learning_rate": 9.998898432287936e-06, "loss": 0.2698, "step": 3633 }, { "epoch": 0.10608360579168613, "grad_norm": 0.41237926483154297, "learning_rate": 9.998887711894954e-06, "loss": 0.2347, "step": 3634 }, { "epoch": 0.10611279775805699, "grad_norm": 0.7819029688835144, "learning_rate": 9.998876939594956e-06, "loss": 0.2713, "step": 3635 }, { "epoch": 0.10614198972442784, "grad_norm": 1.8159584999084473, "learning_rate": 9.99886611538805e-06, "loss": 0.2584, "step": 3636 }, { "epoch": 0.10617118169079869, "grad_norm": 0.5559753179550171, "learning_rate": 9.99885523927435e-06, "loss": 0.2198, "step": 3637 }, { "epoch": 0.10620037365716954, "grad_norm": 0.42517897486686707, "learning_rate": 9.998844311253971e-06, "loss": 0.2613, "step": 3638 }, { "epoch": 0.1062295656235404, "grad_norm": 0.7634128332138062, "learning_rate": 9.998833331327024e-06, "loss": 0.2773, "step": 3639 }, { "epoch": 0.10625875758991125, "grad_norm": 0.3750700354576111, "learning_rate": 9.998822299493625e-06, "loss": 0.2106, "step": 3640 }, { "epoch": 0.10628794955628211, "grad_norm": 0.4688824713230133, "learning_rate": 9.998811215753888e-06, "loss": 0.2485, "step": 3641 }, { "epoch": 0.10631714152265297, "grad_norm": 0.49570512771606445, "learning_rate": 9.998800080107927e-06, "loss": 0.2573, "step": 3642 }, { "epoch": 0.10634633348902382, "grad_norm": 0.40982767939567566, "learning_rate": 9.99878889255586e-06, "loss": 0.2404, "step": 3643 }, { "epoch": 0.10637552545539468, "grad_norm": 0.5432425141334534, "learning_rate": 9.998777653097797e-06, "loss": 0.2614, "step": 3644 }, { "epoch": 0.10640471742176554, "grad_norm": 0.41871246695518494, "learning_rate": 9.998766361733862e-06, "loss": 0.2756, "step": 3645 }, { "epoch": 0.10643390938813639, "grad_norm": 0.4402197599411011, "learning_rate": 9.99875501846417e-06, "loss": 0.2435, "step": 3646 }, { "epoch": 0.10646310135450723, "grad_norm": 0.4394550323486328, "learning_rate": 9.998743623288837e-06, "loss": 0.259, "step": 3647 }, { "epoch": 0.10649229332087809, "grad_norm": 0.4026239812374115, "learning_rate": 9.998732176207983e-06, "loss": 0.2393, "step": 3648 }, { "epoch": 0.10652148528724895, "grad_norm": 0.4449465870857239, "learning_rate": 9.998720677221728e-06, "loss": 0.2691, "step": 3649 }, { "epoch": 0.1065506772536198, "grad_norm": 0.48491400480270386, "learning_rate": 9.998709126330188e-06, "loss": 0.2438, "step": 3650 }, { "epoch": 0.10657986921999066, "grad_norm": 0.3962155878543854, "learning_rate": 9.998697523533483e-06, "loss": 0.275, "step": 3651 }, { "epoch": 0.10660906118636151, "grad_norm": 0.3988032937049866, "learning_rate": 9.998685868831739e-06, "loss": 0.242, "step": 3652 }, { "epoch": 0.10663825315273237, "grad_norm": 0.5572355389595032, "learning_rate": 9.99867416222507e-06, "loss": 0.2443, "step": 3653 }, { "epoch": 0.10666744511910323, "grad_norm": 1.03188157081604, "learning_rate": 9.998662403713601e-06, "loss": 0.2384, "step": 3654 }, { "epoch": 0.10669663708547408, "grad_norm": 0.4374540150165558, "learning_rate": 9.998650593297456e-06, "loss": 0.2859, "step": 3655 }, { "epoch": 0.10672582905184493, "grad_norm": 0.4263836741447449, "learning_rate": 9.998638730976755e-06, "loss": 0.2647, "step": 3656 }, { "epoch": 0.10675502101821578, "grad_norm": 0.48891568183898926, "learning_rate": 9.99862681675162e-06, "loss": 0.2695, "step": 3657 }, { "epoch": 0.10678421298458664, "grad_norm": 0.35723572969436646, "learning_rate": 9.998614850622178e-06, "loss": 0.2091, "step": 3658 }, { "epoch": 0.1068134049509575, "grad_norm": 19.445650100708008, "learning_rate": 9.99860283258855e-06, "loss": 0.2557, "step": 3659 }, { "epoch": 0.10684259691732835, "grad_norm": 0.6405857801437378, "learning_rate": 9.998590762650865e-06, "loss": 0.2353, "step": 3660 }, { "epoch": 0.1068717888836992, "grad_norm": 0.461211234331131, "learning_rate": 9.998578640809245e-06, "loss": 0.2602, "step": 3661 }, { "epoch": 0.10690098085007006, "grad_norm": 0.500028133392334, "learning_rate": 9.998566467063814e-06, "loss": 0.2388, "step": 3662 }, { "epoch": 0.10693017281644092, "grad_norm": 0.42969369888305664, "learning_rate": 9.998554241414704e-06, "loss": 0.2819, "step": 3663 }, { "epoch": 0.10695936478281177, "grad_norm": 0.43402788043022156, "learning_rate": 9.998541963862038e-06, "loss": 0.237, "step": 3664 }, { "epoch": 0.10698855674918263, "grad_norm": 0.42770764231681824, "learning_rate": 9.998529634405945e-06, "loss": 0.2287, "step": 3665 }, { "epoch": 0.10701774871555347, "grad_norm": 0.36504772305488586, "learning_rate": 9.998517253046552e-06, "loss": 0.2468, "step": 3666 }, { "epoch": 0.10704694068192433, "grad_norm": 0.36159875988960266, "learning_rate": 9.998504819783987e-06, "loss": 0.2446, "step": 3667 }, { "epoch": 0.10707613264829519, "grad_norm": 0.39302074909210205, "learning_rate": 9.998492334618381e-06, "loss": 0.2574, "step": 3668 }, { "epoch": 0.10710532461466604, "grad_norm": 0.4164632558822632, "learning_rate": 9.998479797549865e-06, "loss": 0.2407, "step": 3669 }, { "epoch": 0.1071345165810369, "grad_norm": 0.42760586738586426, "learning_rate": 9.998467208578564e-06, "loss": 0.2634, "step": 3670 }, { "epoch": 0.10716370854740775, "grad_norm": 0.4647599756717682, "learning_rate": 9.998454567704614e-06, "loss": 0.2231, "step": 3671 }, { "epoch": 0.10719290051377861, "grad_norm": 0.445755273103714, "learning_rate": 9.998441874928142e-06, "loss": 0.2833, "step": 3672 }, { "epoch": 0.10722209248014947, "grad_norm": 0.5688446164131165, "learning_rate": 9.998429130249283e-06, "loss": 0.265, "step": 3673 }, { "epoch": 0.10725128444652032, "grad_norm": 0.7423403263092041, "learning_rate": 9.998416333668168e-06, "loss": 0.2416, "step": 3674 }, { "epoch": 0.10728047641289118, "grad_norm": 0.42704230546951294, "learning_rate": 9.998403485184928e-06, "loss": 0.2483, "step": 3675 }, { "epoch": 0.10730966837926202, "grad_norm": 0.46130433678627014, "learning_rate": 9.998390584799702e-06, "loss": 0.249, "step": 3676 }, { "epoch": 0.10733886034563288, "grad_norm": 0.4724024534225464, "learning_rate": 9.998377632512618e-06, "loss": 0.2326, "step": 3677 }, { "epoch": 0.10736805231200373, "grad_norm": 0.4330774247646332, "learning_rate": 9.998364628323813e-06, "loss": 0.2678, "step": 3678 }, { "epoch": 0.10739724427837459, "grad_norm": 0.37408190965652466, "learning_rate": 9.998351572233423e-06, "loss": 0.2136, "step": 3679 }, { "epoch": 0.10742643624474545, "grad_norm": 0.4667198061943054, "learning_rate": 9.998338464241582e-06, "loss": 0.3154, "step": 3680 }, { "epoch": 0.1074556282111163, "grad_norm": 0.42095720767974854, "learning_rate": 9.998325304348427e-06, "loss": 0.2578, "step": 3681 }, { "epoch": 0.10748482017748716, "grad_norm": 0.4203747808933258, "learning_rate": 9.998312092554092e-06, "loss": 0.2389, "step": 3682 }, { "epoch": 0.10751401214385801, "grad_norm": 0.42378175258636475, "learning_rate": 9.998298828858719e-06, "loss": 0.2492, "step": 3683 }, { "epoch": 0.10754320411022887, "grad_norm": 0.35788553953170776, "learning_rate": 9.998285513262441e-06, "loss": 0.2034, "step": 3684 }, { "epoch": 0.10757239607659971, "grad_norm": 0.4114336669445038, "learning_rate": 9.998272145765399e-06, "loss": 0.2666, "step": 3685 }, { "epoch": 0.10760158804297057, "grad_norm": 0.40710365772247314, "learning_rate": 9.998258726367733e-06, "loss": 0.2774, "step": 3686 }, { "epoch": 0.10763078000934143, "grad_norm": 0.49680209159851074, "learning_rate": 9.99824525506958e-06, "loss": 0.2636, "step": 3687 }, { "epoch": 0.10765997197571228, "grad_norm": 0.40878674387931824, "learning_rate": 9.998231731871078e-06, "loss": 0.2637, "step": 3688 }, { "epoch": 0.10768916394208314, "grad_norm": 0.3760623335838318, "learning_rate": 9.998218156772373e-06, "loss": 0.2419, "step": 3689 }, { "epoch": 0.107718355908454, "grad_norm": 0.5701318383216858, "learning_rate": 9.9982045297736e-06, "loss": 0.2502, "step": 3690 }, { "epoch": 0.10774754787482485, "grad_norm": 0.4181508719921112, "learning_rate": 9.998190850874905e-06, "loss": 0.2387, "step": 3691 }, { "epoch": 0.1077767398411957, "grad_norm": 0.3883909285068512, "learning_rate": 9.998177120076428e-06, "loss": 0.2642, "step": 3692 }, { "epoch": 0.10780593180756656, "grad_norm": 0.4428211748600006, "learning_rate": 9.998163337378311e-06, "loss": 0.2519, "step": 3693 }, { "epoch": 0.10783512377393742, "grad_norm": 0.36830633878707886, "learning_rate": 9.998149502780698e-06, "loss": 0.1899, "step": 3694 }, { "epoch": 0.10786431574030826, "grad_norm": 0.6981502771377563, "learning_rate": 9.998135616283735e-06, "loss": 0.256, "step": 3695 }, { "epoch": 0.10789350770667912, "grad_norm": 0.36775752902030945, "learning_rate": 9.998121677887562e-06, "loss": 0.2205, "step": 3696 }, { "epoch": 0.10792269967304997, "grad_norm": 0.42892134189605713, "learning_rate": 9.998107687592326e-06, "loss": 0.2535, "step": 3697 }, { "epoch": 0.10795189163942083, "grad_norm": 0.40720435976982117, "learning_rate": 9.998093645398173e-06, "loss": 0.2379, "step": 3698 }, { "epoch": 0.10798108360579169, "grad_norm": 0.44576260447502136, "learning_rate": 9.998079551305247e-06, "loss": 0.2467, "step": 3699 }, { "epoch": 0.10801027557216254, "grad_norm": 0.43188780546188354, "learning_rate": 9.998065405313694e-06, "loss": 0.2992, "step": 3700 }, { "epoch": 0.1080394675385334, "grad_norm": 0.4501655697822571, "learning_rate": 9.998051207423662e-06, "loss": 0.2743, "step": 3701 }, { "epoch": 0.10806865950490425, "grad_norm": 0.4404711425304413, "learning_rate": 9.9980369576353e-06, "loss": 0.2931, "step": 3702 }, { "epoch": 0.10809785147127511, "grad_norm": 0.45360490679740906, "learning_rate": 9.998022655948752e-06, "loss": 0.2734, "step": 3703 }, { "epoch": 0.10812704343764595, "grad_norm": 0.40113651752471924, "learning_rate": 9.99800830236417e-06, "loss": 0.2842, "step": 3704 }, { "epoch": 0.10815623540401681, "grad_norm": 0.4109013080596924, "learning_rate": 9.997993896881704e-06, "loss": 0.2467, "step": 3705 }, { "epoch": 0.10818542737038767, "grad_norm": 0.3817395269870758, "learning_rate": 9.997979439501499e-06, "loss": 0.1926, "step": 3706 }, { "epoch": 0.10821461933675852, "grad_norm": 0.5036489367485046, "learning_rate": 9.997964930223707e-06, "loss": 0.236, "step": 3707 }, { "epoch": 0.10824381130312938, "grad_norm": 0.4316657781600952, "learning_rate": 9.997950369048482e-06, "loss": 0.3008, "step": 3708 }, { "epoch": 0.10827300326950023, "grad_norm": 0.4238260090351105, "learning_rate": 9.997935755975969e-06, "loss": 0.2529, "step": 3709 }, { "epoch": 0.10830219523587109, "grad_norm": 0.6079277992248535, "learning_rate": 9.997921091006326e-06, "loss": 0.2351, "step": 3710 }, { "epoch": 0.10833138720224195, "grad_norm": 1.1422349214553833, "learning_rate": 9.9979063741397e-06, "loss": 0.2444, "step": 3711 }, { "epoch": 0.1083605791686128, "grad_norm": 0.790774405002594, "learning_rate": 9.997891605376248e-06, "loss": 0.2586, "step": 3712 }, { "epoch": 0.10838977113498366, "grad_norm": 0.5037381649017334, "learning_rate": 9.997876784716122e-06, "loss": 0.2916, "step": 3713 }, { "epoch": 0.1084189631013545, "grad_norm": 0.5348021388053894, "learning_rate": 9.997861912159474e-06, "loss": 0.265, "step": 3714 }, { "epoch": 0.10844815506772536, "grad_norm": 0.39122843742370605, "learning_rate": 9.997846987706462e-06, "loss": 0.25, "step": 3715 }, { "epoch": 0.10847734703409621, "grad_norm": 0.3821473717689514, "learning_rate": 9.997832011357237e-06, "loss": 0.2514, "step": 3716 }, { "epoch": 0.10850653900046707, "grad_norm": 0.447231650352478, "learning_rate": 9.997816983111956e-06, "loss": 0.2666, "step": 3717 }, { "epoch": 0.10853573096683793, "grad_norm": 0.4473258852958679, "learning_rate": 9.997801902970777e-06, "loss": 0.2919, "step": 3718 }, { "epoch": 0.10856492293320878, "grad_norm": 0.5134027004241943, "learning_rate": 9.997786770933855e-06, "loss": 0.2344, "step": 3719 }, { "epoch": 0.10859411489957964, "grad_norm": 0.7042795419692993, "learning_rate": 9.997771587001347e-06, "loss": 0.2537, "step": 3720 }, { "epoch": 0.1086233068659505, "grad_norm": 0.507411003112793, "learning_rate": 9.997756351173411e-06, "loss": 0.2501, "step": 3721 }, { "epoch": 0.10865249883232135, "grad_norm": 0.45367664098739624, "learning_rate": 9.997741063450204e-06, "loss": 0.2581, "step": 3722 }, { "epoch": 0.1086816907986922, "grad_norm": 1.375377893447876, "learning_rate": 9.997725723831887e-06, "loss": 0.2659, "step": 3723 }, { "epoch": 0.10871088276506305, "grad_norm": 0.5396822690963745, "learning_rate": 9.997710332318618e-06, "loss": 0.2483, "step": 3724 }, { "epoch": 0.1087400747314339, "grad_norm": 0.4223117232322693, "learning_rate": 9.997694888910557e-06, "loss": 0.2287, "step": 3725 }, { "epoch": 0.10876926669780476, "grad_norm": 0.515257716178894, "learning_rate": 9.997679393607862e-06, "loss": 0.2518, "step": 3726 }, { "epoch": 0.10879845866417562, "grad_norm": 0.7344457507133484, "learning_rate": 9.9976638464107e-06, "loss": 0.2514, "step": 3727 }, { "epoch": 0.10882765063054647, "grad_norm": 0.6149193644523621, "learning_rate": 9.997648247319226e-06, "loss": 0.2506, "step": 3728 }, { "epoch": 0.10885684259691733, "grad_norm": 0.5405876636505127, "learning_rate": 9.997632596333605e-06, "loss": 0.3019, "step": 3729 }, { "epoch": 0.10888603456328819, "grad_norm": 0.3863801062107086, "learning_rate": 9.997616893453998e-06, "loss": 0.1802, "step": 3730 }, { "epoch": 0.10891522652965904, "grad_norm": 0.4619757831096649, "learning_rate": 9.997601138680571e-06, "loss": 0.2501, "step": 3731 }, { "epoch": 0.1089444184960299, "grad_norm": 0.4879187345504761, "learning_rate": 9.997585332013486e-06, "loss": 0.3116, "step": 3732 }, { "epoch": 0.10897361046240074, "grad_norm": 0.49030783772468567, "learning_rate": 9.997569473452905e-06, "loss": 0.2364, "step": 3733 }, { "epoch": 0.1090028024287716, "grad_norm": 0.4622943699359894, "learning_rate": 9.997553562998995e-06, "loss": 0.2762, "step": 3734 }, { "epoch": 0.10903199439514245, "grad_norm": 0.583864688873291, "learning_rate": 9.997537600651924e-06, "loss": 0.2713, "step": 3735 }, { "epoch": 0.10906118636151331, "grad_norm": 0.4628402292728424, "learning_rate": 9.997521586411851e-06, "loss": 0.2535, "step": 3736 }, { "epoch": 0.10909037832788417, "grad_norm": 0.5713205933570862, "learning_rate": 9.997505520278947e-06, "loss": 0.2048, "step": 3737 }, { "epoch": 0.10911957029425502, "grad_norm": 0.44682425260543823, "learning_rate": 9.997489402253377e-06, "loss": 0.2715, "step": 3738 }, { "epoch": 0.10914876226062588, "grad_norm": 0.524416983127594, "learning_rate": 9.997473232335308e-06, "loss": 0.2683, "step": 3739 }, { "epoch": 0.10917795422699673, "grad_norm": 1.742185115814209, "learning_rate": 9.99745701052491e-06, "loss": 0.2848, "step": 3740 }, { "epoch": 0.10920714619336759, "grad_norm": 0.4701519012451172, "learning_rate": 9.997440736822353e-06, "loss": 0.238, "step": 3741 }, { "epoch": 0.10923633815973843, "grad_norm": 0.545004665851593, "learning_rate": 9.9974244112278e-06, "loss": 0.2491, "step": 3742 }, { "epoch": 0.10926553012610929, "grad_norm": 0.4606473445892334, "learning_rate": 9.997408033741424e-06, "loss": 0.3122, "step": 3743 }, { "epoch": 0.10929472209248015, "grad_norm": 0.4442504346370697, "learning_rate": 9.997391604363396e-06, "loss": 0.2295, "step": 3744 }, { "epoch": 0.109323914058851, "grad_norm": 0.5173169374465942, "learning_rate": 9.997375123093884e-06, "loss": 0.2214, "step": 3745 }, { "epoch": 0.10935310602522186, "grad_norm": 0.4772104322910309, "learning_rate": 9.997358589933062e-06, "loss": 0.2641, "step": 3746 }, { "epoch": 0.10938229799159271, "grad_norm": 0.4280470013618469, "learning_rate": 9.997342004881102e-06, "loss": 0.2315, "step": 3747 }, { "epoch": 0.10941148995796357, "grad_norm": 0.6818153262138367, "learning_rate": 9.997325367938171e-06, "loss": 0.2958, "step": 3748 }, { "epoch": 0.10944068192433443, "grad_norm": 0.4791319668292999, "learning_rate": 9.997308679104447e-06, "loss": 0.2335, "step": 3749 }, { "epoch": 0.10946987389070528, "grad_norm": 0.6098110675811768, "learning_rate": 9.997291938380101e-06, "loss": 0.2907, "step": 3750 }, { "epoch": 0.10949906585707614, "grad_norm": 0.456355482339859, "learning_rate": 9.997275145765309e-06, "loss": 0.2778, "step": 3751 }, { "epoch": 0.10952825782344698, "grad_norm": 1.2828243970870972, "learning_rate": 9.997258301260243e-06, "loss": 0.2519, "step": 3752 }, { "epoch": 0.10955744978981784, "grad_norm": 0.46755099296569824, "learning_rate": 9.997241404865076e-06, "loss": 0.2462, "step": 3753 }, { "epoch": 0.1095866417561887, "grad_norm": 0.4439794719219208, "learning_rate": 9.997224456579988e-06, "loss": 0.2968, "step": 3754 }, { "epoch": 0.10961583372255955, "grad_norm": 0.4823683202266693, "learning_rate": 9.997207456405154e-06, "loss": 0.3109, "step": 3755 }, { "epoch": 0.1096450256889304, "grad_norm": 0.3897034227848053, "learning_rate": 9.997190404340748e-06, "loss": 0.2589, "step": 3756 }, { "epoch": 0.10967421765530126, "grad_norm": 0.46696844696998596, "learning_rate": 9.99717330038695e-06, "loss": 0.2477, "step": 3757 }, { "epoch": 0.10970340962167212, "grad_norm": 0.5748339891433716, "learning_rate": 9.997156144543937e-06, "loss": 0.2935, "step": 3758 }, { "epoch": 0.10973260158804297, "grad_norm": 0.5126253962516785, "learning_rate": 9.997138936811885e-06, "loss": 0.2366, "step": 3759 }, { "epoch": 0.10976179355441383, "grad_norm": 0.440312922000885, "learning_rate": 9.997121677190975e-06, "loss": 0.2703, "step": 3760 }, { "epoch": 0.10979098552078469, "grad_norm": 0.43881091475486755, "learning_rate": 9.997104365681385e-06, "loss": 0.3024, "step": 3761 }, { "epoch": 0.10982017748715553, "grad_norm": 0.5411916375160217, "learning_rate": 9.997087002283295e-06, "loss": 0.3272, "step": 3762 }, { "epoch": 0.10984936945352639, "grad_norm": 0.4279700219631195, "learning_rate": 9.997069586996885e-06, "loss": 0.2487, "step": 3763 }, { "epoch": 0.10987856141989724, "grad_norm": 0.4968114495277405, "learning_rate": 9.997052119822338e-06, "loss": 0.2237, "step": 3764 }, { "epoch": 0.1099077533862681, "grad_norm": 0.4445268511772156, "learning_rate": 9.997034600759831e-06, "loss": 0.2686, "step": 3765 }, { "epoch": 0.10993694535263895, "grad_norm": 0.45771127939224243, "learning_rate": 9.99701702980955e-06, "loss": 0.2953, "step": 3766 }, { "epoch": 0.10996613731900981, "grad_norm": 0.5422817468643188, "learning_rate": 9.996999406971675e-06, "loss": 0.317, "step": 3767 }, { "epoch": 0.10999532928538067, "grad_norm": 0.41895705461502075, "learning_rate": 9.996981732246392e-06, "loss": 0.2113, "step": 3768 }, { "epoch": 0.11002452125175152, "grad_norm": 0.6111109256744385, "learning_rate": 9.99696400563388e-06, "loss": 0.2239, "step": 3769 }, { "epoch": 0.11005371321812238, "grad_norm": 0.6826375126838684, "learning_rate": 9.996946227134326e-06, "loss": 0.2122, "step": 3770 }, { "epoch": 0.11008290518449322, "grad_norm": 0.5559632778167725, "learning_rate": 9.996928396747916e-06, "loss": 0.2368, "step": 3771 }, { "epoch": 0.11011209715086408, "grad_norm": 0.5183752775192261, "learning_rate": 9.996910514474832e-06, "loss": 0.3374, "step": 3772 }, { "epoch": 0.11014128911723493, "grad_norm": 0.4111359119415283, "learning_rate": 9.996892580315261e-06, "loss": 0.2487, "step": 3773 }, { "epoch": 0.11017048108360579, "grad_norm": 0.49193045496940613, "learning_rate": 9.99687459426939e-06, "loss": 0.3025, "step": 3774 }, { "epoch": 0.11019967304997665, "grad_norm": 0.5475666522979736, "learning_rate": 9.996856556337403e-06, "loss": 0.3123, "step": 3775 }, { "epoch": 0.1102288650163475, "grad_norm": 0.5756381750106812, "learning_rate": 9.99683846651949e-06, "loss": 0.2491, "step": 3776 }, { "epoch": 0.11025805698271836, "grad_norm": 0.46525177359580994, "learning_rate": 9.99682032481584e-06, "loss": 0.293, "step": 3777 }, { "epoch": 0.11028724894908921, "grad_norm": 0.5320350527763367, "learning_rate": 9.996802131226638e-06, "loss": 0.2692, "step": 3778 }, { "epoch": 0.11031644091546007, "grad_norm": 0.49396368861198425, "learning_rate": 9.996783885752074e-06, "loss": 0.3103, "step": 3779 }, { "epoch": 0.11034563288183093, "grad_norm": 2.416598081588745, "learning_rate": 9.996765588392338e-06, "loss": 0.2681, "step": 3780 }, { "epoch": 0.11037482484820177, "grad_norm": 0.45000502467155457, "learning_rate": 9.996747239147622e-06, "loss": 0.2253, "step": 3781 }, { "epoch": 0.11040401681457263, "grad_norm": 0.4972732663154602, "learning_rate": 9.996728838018113e-06, "loss": 0.2954, "step": 3782 }, { "epoch": 0.11043320878094348, "grad_norm": 0.45465293526649475, "learning_rate": 9.996710385004002e-06, "loss": 0.2812, "step": 3783 }, { "epoch": 0.11046240074731434, "grad_norm": 0.48420971632003784, "learning_rate": 9.996691880105483e-06, "loss": 0.2861, "step": 3784 }, { "epoch": 0.1104915927136852, "grad_norm": 0.43267345428466797, "learning_rate": 9.996673323322747e-06, "loss": 0.2485, "step": 3785 }, { "epoch": 0.11052078468005605, "grad_norm": 0.46438533067703247, "learning_rate": 9.996654714655988e-06, "loss": 0.2922, "step": 3786 }, { "epoch": 0.1105499766464269, "grad_norm": 0.47154149413108826, "learning_rate": 9.996636054105397e-06, "loss": 0.2628, "step": 3787 }, { "epoch": 0.11057916861279776, "grad_norm": 0.4420309066772461, "learning_rate": 9.996617341671171e-06, "loss": 0.2358, "step": 3788 }, { "epoch": 0.11060836057916862, "grad_norm": 0.4090379774570465, "learning_rate": 9.9965985773535e-06, "loss": 0.266, "step": 3789 }, { "epoch": 0.11063755254553946, "grad_norm": 0.3985457420349121, "learning_rate": 9.996579761152581e-06, "loss": 0.243, "step": 3790 }, { "epoch": 0.11066674451191032, "grad_norm": 0.4294227063655853, "learning_rate": 9.996560893068611e-06, "loss": 0.2673, "step": 3791 }, { "epoch": 0.11069593647828117, "grad_norm": 0.5236467719078064, "learning_rate": 9.996541973101782e-06, "loss": 0.3032, "step": 3792 }, { "epoch": 0.11072512844465203, "grad_norm": 0.4712691903114319, "learning_rate": 9.996523001252297e-06, "loss": 0.3055, "step": 3793 }, { "epoch": 0.11075432041102289, "grad_norm": 0.5000463128089905, "learning_rate": 9.996503977520344e-06, "loss": 0.2469, "step": 3794 }, { "epoch": 0.11078351237739374, "grad_norm": 0.4143258333206177, "learning_rate": 9.99648490190613e-06, "loss": 0.2766, "step": 3795 }, { "epoch": 0.1108127043437646, "grad_norm": 0.5031678676605225, "learning_rate": 9.996465774409844e-06, "loss": 0.2507, "step": 3796 }, { "epoch": 0.11084189631013545, "grad_norm": 0.4376506805419922, "learning_rate": 9.996446595031691e-06, "loss": 0.2374, "step": 3797 }, { "epoch": 0.11087108827650631, "grad_norm": 0.47864633798599243, "learning_rate": 9.996427363771869e-06, "loss": 0.2198, "step": 3798 }, { "epoch": 0.11090028024287717, "grad_norm": 0.4852351248264313, "learning_rate": 9.996408080630576e-06, "loss": 0.2532, "step": 3799 }, { "epoch": 0.11092947220924801, "grad_norm": 0.4865581691265106, "learning_rate": 9.996388745608013e-06, "loss": 0.2578, "step": 3800 }, { "epoch": 0.11095866417561887, "grad_norm": 0.44225770235061646, "learning_rate": 9.99636935870438e-06, "loss": 0.2706, "step": 3801 }, { "epoch": 0.11098785614198972, "grad_norm": 0.6141009330749512, "learning_rate": 9.996349919919882e-06, "loss": 0.2915, "step": 3802 }, { "epoch": 0.11101704810836058, "grad_norm": 0.44318079948425293, "learning_rate": 9.996330429254715e-06, "loss": 0.2444, "step": 3803 }, { "epoch": 0.11104624007473143, "grad_norm": 0.4730159640312195, "learning_rate": 9.996310886709087e-06, "loss": 0.2914, "step": 3804 }, { "epoch": 0.11107543204110229, "grad_norm": 1.1251068115234375, "learning_rate": 9.996291292283197e-06, "loss": 0.2371, "step": 3805 }, { "epoch": 0.11110462400747315, "grad_norm": 0.6073731184005737, "learning_rate": 9.99627164597725e-06, "loss": 0.2024, "step": 3806 }, { "epoch": 0.111133815973844, "grad_norm": 0.5430039763450623, "learning_rate": 9.996251947791449e-06, "loss": 0.2506, "step": 3807 }, { "epoch": 0.11116300794021486, "grad_norm": 0.5397825837135315, "learning_rate": 9.996232197726e-06, "loss": 0.2279, "step": 3808 }, { "epoch": 0.1111921999065857, "grad_norm": 0.47988978028297424, "learning_rate": 9.996212395781109e-06, "loss": 0.2367, "step": 3809 }, { "epoch": 0.11122139187295656, "grad_norm": 0.4172447621822357, "learning_rate": 9.996192541956978e-06, "loss": 0.2161, "step": 3810 }, { "epoch": 0.11125058383932741, "grad_norm": 0.48999112844467163, "learning_rate": 9.996172636253815e-06, "loss": 0.2446, "step": 3811 }, { "epoch": 0.11127977580569827, "grad_norm": 0.4185429811477661, "learning_rate": 9.996152678671828e-06, "loss": 0.2602, "step": 3812 }, { "epoch": 0.11130896777206913, "grad_norm": 0.515811026096344, "learning_rate": 9.996132669211223e-06, "loss": 0.2813, "step": 3813 }, { "epoch": 0.11133815973843998, "grad_norm": 0.4602183699607849, "learning_rate": 9.996112607872209e-06, "loss": 0.2473, "step": 3814 }, { "epoch": 0.11136735170481084, "grad_norm": 0.40306776762008667, "learning_rate": 9.99609249465499e-06, "loss": 0.2265, "step": 3815 }, { "epoch": 0.1113965436711817, "grad_norm": 0.46277570724487305, "learning_rate": 9.99607232955978e-06, "loss": 0.2308, "step": 3816 }, { "epoch": 0.11142573563755255, "grad_norm": 0.7214240431785583, "learning_rate": 9.996052112586787e-06, "loss": 0.226, "step": 3817 }, { "epoch": 0.1114549276039234, "grad_norm": 0.39952704310417175, "learning_rate": 9.99603184373622e-06, "loss": 0.2348, "step": 3818 }, { "epoch": 0.11148411957029425, "grad_norm": 0.5552005171775818, "learning_rate": 9.99601152300829e-06, "loss": 0.2927, "step": 3819 }, { "epoch": 0.1115133115366651, "grad_norm": 0.41557061672210693, "learning_rate": 9.995991150403208e-06, "loss": 0.2305, "step": 3820 }, { "epoch": 0.11154250350303596, "grad_norm": 0.4043848514556885, "learning_rate": 9.995970725921185e-06, "loss": 0.2027, "step": 3821 }, { "epoch": 0.11157169546940682, "grad_norm": 0.49527981877326965, "learning_rate": 9.995950249562434e-06, "loss": 0.2132, "step": 3822 }, { "epoch": 0.11160088743577767, "grad_norm": 0.36400508880615234, "learning_rate": 9.995929721327166e-06, "loss": 0.2414, "step": 3823 }, { "epoch": 0.11163007940214853, "grad_norm": 0.40483373403549194, "learning_rate": 9.995909141215596e-06, "loss": 0.2724, "step": 3824 }, { "epoch": 0.11165927136851939, "grad_norm": 0.3696451187133789, "learning_rate": 9.995888509227935e-06, "loss": 0.2449, "step": 3825 }, { "epoch": 0.11168846333489024, "grad_norm": 0.40445441007614136, "learning_rate": 9.995867825364403e-06, "loss": 0.2734, "step": 3826 }, { "epoch": 0.1117176553012611, "grad_norm": 0.3959990441799164, "learning_rate": 9.995847089625209e-06, "loss": 0.2774, "step": 3827 }, { "epoch": 0.11174684726763194, "grad_norm": 0.3767715394496918, "learning_rate": 9.99582630201057e-06, "loss": 0.2654, "step": 3828 }, { "epoch": 0.1117760392340028, "grad_norm": 0.4378301203250885, "learning_rate": 9.995805462520703e-06, "loss": 0.267, "step": 3829 }, { "epoch": 0.11180523120037365, "grad_norm": 0.46857717633247375, "learning_rate": 9.995784571155822e-06, "loss": 0.253, "step": 3830 }, { "epoch": 0.11183442316674451, "grad_norm": 0.3972941040992737, "learning_rate": 9.995763627916146e-06, "loss": 0.2319, "step": 3831 }, { "epoch": 0.11186361513311537, "grad_norm": 0.7863538861274719, "learning_rate": 9.995742632801892e-06, "loss": 0.3392, "step": 3832 }, { "epoch": 0.11189280709948622, "grad_norm": 0.3828398287296295, "learning_rate": 9.99572158581328e-06, "loss": 0.2499, "step": 3833 }, { "epoch": 0.11192199906585708, "grad_norm": 0.6585242748260498, "learning_rate": 9.995700486950524e-06, "loss": 0.2829, "step": 3834 }, { "epoch": 0.11195119103222793, "grad_norm": 0.4375379979610443, "learning_rate": 9.995679336213846e-06, "loss": 0.2156, "step": 3835 }, { "epoch": 0.11198038299859879, "grad_norm": 0.5746985673904419, "learning_rate": 9.995658133603466e-06, "loss": 0.2593, "step": 3836 }, { "epoch": 0.11200957496496965, "grad_norm": 0.4685077965259552, "learning_rate": 9.995636879119604e-06, "loss": 0.2218, "step": 3837 }, { "epoch": 0.11203876693134049, "grad_norm": 0.39523524045944214, "learning_rate": 9.995615572762479e-06, "loss": 0.2396, "step": 3838 }, { "epoch": 0.11206795889771135, "grad_norm": 0.49274376034736633, "learning_rate": 9.995594214532312e-06, "loss": 0.2984, "step": 3839 }, { "epoch": 0.1120971508640822, "grad_norm": 0.48759159445762634, "learning_rate": 9.995572804429328e-06, "loss": 0.257, "step": 3840 }, { "epoch": 0.11212634283045306, "grad_norm": 0.44047215580940247, "learning_rate": 9.995551342453746e-06, "loss": 0.2516, "step": 3841 }, { "epoch": 0.11215553479682391, "grad_norm": 0.43667519092559814, "learning_rate": 9.995529828605792e-06, "loss": 0.2964, "step": 3842 }, { "epoch": 0.11218472676319477, "grad_norm": 0.39962005615234375, "learning_rate": 9.995508262885686e-06, "loss": 0.2586, "step": 3843 }, { "epoch": 0.11221391872956563, "grad_norm": 0.5295295715332031, "learning_rate": 9.995486645293654e-06, "loss": 0.2482, "step": 3844 }, { "epoch": 0.11224311069593648, "grad_norm": 0.43275684118270874, "learning_rate": 9.99546497582992e-06, "loss": 0.2815, "step": 3845 }, { "epoch": 0.11227230266230734, "grad_norm": 0.3603335916996002, "learning_rate": 9.99544325449471e-06, "loss": 0.2093, "step": 3846 }, { "epoch": 0.1123014946286782, "grad_norm": 0.46072015166282654, "learning_rate": 9.995421481288247e-06, "loss": 0.2145, "step": 3847 }, { "epoch": 0.11233068659504904, "grad_norm": 0.4574524760246277, "learning_rate": 9.995399656210761e-06, "loss": 0.2877, "step": 3848 }, { "epoch": 0.11235987856141989, "grad_norm": 0.5015357136726379, "learning_rate": 9.995377779262474e-06, "loss": 0.2835, "step": 3849 }, { "epoch": 0.11238907052779075, "grad_norm": 0.4193636178970337, "learning_rate": 9.995355850443616e-06, "loss": 0.241, "step": 3850 }, { "epoch": 0.1124182624941616, "grad_norm": 0.3879193365573883, "learning_rate": 9.995333869754416e-06, "loss": 0.2319, "step": 3851 }, { "epoch": 0.11244745446053246, "grad_norm": 0.3935606777667999, "learning_rate": 9.995311837195099e-06, "loss": 0.2303, "step": 3852 }, { "epoch": 0.11247664642690332, "grad_norm": 0.3764417767524719, "learning_rate": 9.995289752765894e-06, "loss": 0.2615, "step": 3853 }, { "epoch": 0.11250583839327417, "grad_norm": 0.40624406933784485, "learning_rate": 9.995267616467032e-06, "loss": 0.2463, "step": 3854 }, { "epoch": 0.11253503035964503, "grad_norm": 0.7614998817443848, "learning_rate": 9.995245428298744e-06, "loss": 0.231, "step": 3855 }, { "epoch": 0.11256422232601589, "grad_norm": 0.465915709733963, "learning_rate": 9.995223188261257e-06, "loss": 0.2754, "step": 3856 }, { "epoch": 0.11259341429238673, "grad_norm": 0.39646250009536743, "learning_rate": 9.995200896354804e-06, "loss": 0.2432, "step": 3857 }, { "epoch": 0.11262260625875758, "grad_norm": 0.40051254630088806, "learning_rate": 9.995178552579618e-06, "loss": 0.2529, "step": 3858 }, { "epoch": 0.11265179822512844, "grad_norm": 0.3990066647529602, "learning_rate": 9.995156156935928e-06, "loss": 0.2872, "step": 3859 }, { "epoch": 0.1126809901914993, "grad_norm": 0.41327211260795593, "learning_rate": 9.995133709423968e-06, "loss": 0.2324, "step": 3860 }, { "epoch": 0.11271018215787015, "grad_norm": 0.5527649521827698, "learning_rate": 9.99511121004397e-06, "loss": 0.2937, "step": 3861 }, { "epoch": 0.11273937412424101, "grad_norm": 0.46192145347595215, "learning_rate": 9.995088658796169e-06, "loss": 0.2512, "step": 3862 }, { "epoch": 0.11276856609061187, "grad_norm": 0.457424134016037, "learning_rate": 9.995066055680797e-06, "loss": 0.2441, "step": 3863 }, { "epoch": 0.11279775805698272, "grad_norm": 0.5740571618080139, "learning_rate": 9.995043400698093e-06, "loss": 0.2538, "step": 3864 }, { "epoch": 0.11282695002335358, "grad_norm": 0.4805011749267578, "learning_rate": 9.995020693848287e-06, "loss": 0.2224, "step": 3865 }, { "epoch": 0.11285614198972443, "grad_norm": 0.4881517291069031, "learning_rate": 9.99499793513162e-06, "loss": 0.2833, "step": 3866 }, { "epoch": 0.11288533395609528, "grad_norm": 0.7666575312614441, "learning_rate": 9.994975124548324e-06, "loss": 0.2889, "step": 3867 }, { "epoch": 0.11291452592246613, "grad_norm": 0.397806316614151, "learning_rate": 9.994952262098639e-06, "loss": 0.2694, "step": 3868 }, { "epoch": 0.11294371788883699, "grad_norm": 0.37674596905708313, "learning_rate": 9.994929347782798e-06, "loss": 0.2682, "step": 3869 }, { "epoch": 0.11297290985520785, "grad_norm": 0.5009471774101257, "learning_rate": 9.994906381601044e-06, "loss": 0.3059, "step": 3870 }, { "epoch": 0.1130021018215787, "grad_norm": 0.49019479751586914, "learning_rate": 9.994883363553614e-06, "loss": 0.2327, "step": 3871 }, { "epoch": 0.11303129378794956, "grad_norm": 0.38905656337738037, "learning_rate": 9.994860293640745e-06, "loss": 0.2146, "step": 3872 }, { "epoch": 0.11306048575432041, "grad_norm": 0.39092734456062317, "learning_rate": 9.994837171862677e-06, "loss": 0.2512, "step": 3873 }, { "epoch": 0.11308967772069127, "grad_norm": 0.3975602090358734, "learning_rate": 9.994813998219653e-06, "loss": 0.2677, "step": 3874 }, { "epoch": 0.11311886968706213, "grad_norm": 0.5204201340675354, "learning_rate": 9.99479077271191e-06, "loss": 0.2504, "step": 3875 }, { "epoch": 0.11314806165343297, "grad_norm": 0.4208013117313385, "learning_rate": 9.994767495339691e-06, "loss": 0.2496, "step": 3876 }, { "epoch": 0.11317725361980382, "grad_norm": 0.4492029845714569, "learning_rate": 9.99474416610324e-06, "loss": 0.2646, "step": 3877 }, { "epoch": 0.11320644558617468, "grad_norm": 0.49705642461776733, "learning_rate": 9.994720785002794e-06, "loss": 0.278, "step": 3878 }, { "epoch": 0.11323563755254554, "grad_norm": 0.42732229828834534, "learning_rate": 9.9946973520386e-06, "loss": 0.2212, "step": 3879 }, { "epoch": 0.1132648295189164, "grad_norm": 0.47159963846206665, "learning_rate": 9.994673867210899e-06, "loss": 0.2607, "step": 3880 }, { "epoch": 0.11329402148528725, "grad_norm": 0.35720840096473694, "learning_rate": 9.994650330519936e-06, "loss": 0.1899, "step": 3881 }, { "epoch": 0.1133232134516581, "grad_norm": 0.547804057598114, "learning_rate": 9.994626741965954e-06, "loss": 0.2824, "step": 3882 }, { "epoch": 0.11335240541802896, "grad_norm": 0.4135458171367645, "learning_rate": 9.9946031015492e-06, "loss": 0.2508, "step": 3883 }, { "epoch": 0.11338159738439982, "grad_norm": 0.5993070602416992, "learning_rate": 9.99457940926992e-06, "loss": 0.2742, "step": 3884 }, { "epoch": 0.11341078935077067, "grad_norm": 0.49557867646217346, "learning_rate": 9.994555665128356e-06, "loss": 0.3179, "step": 3885 }, { "epoch": 0.11343998131714152, "grad_norm": 0.4095490872859955, "learning_rate": 9.99453186912476e-06, "loss": 0.2553, "step": 3886 }, { "epoch": 0.11346917328351237, "grad_norm": 0.38730406761169434, "learning_rate": 9.994508021259372e-06, "loss": 0.2319, "step": 3887 }, { "epoch": 0.11349836524988323, "grad_norm": 0.4961416721343994, "learning_rate": 9.994484121532447e-06, "loss": 0.2482, "step": 3888 }, { "epoch": 0.11352755721625409, "grad_norm": 0.5077348947525024, "learning_rate": 9.99446016994423e-06, "loss": 0.2807, "step": 3889 }, { "epoch": 0.11355674918262494, "grad_norm": 0.4303804636001587, "learning_rate": 9.994436166494967e-06, "loss": 0.2678, "step": 3890 }, { "epoch": 0.1135859411489958, "grad_norm": 1.3828248977661133, "learning_rate": 9.994412111184912e-06, "loss": 0.2675, "step": 3891 }, { "epoch": 0.11361513311536665, "grad_norm": 0.45127683877944946, "learning_rate": 9.994388004014312e-06, "loss": 0.2976, "step": 3892 }, { "epoch": 0.11364432508173751, "grad_norm": 0.39475777745246887, "learning_rate": 9.99436384498342e-06, "loss": 0.2982, "step": 3893 }, { "epoch": 0.11367351704810837, "grad_norm": 0.3927353024482727, "learning_rate": 9.994339634092483e-06, "loss": 0.2678, "step": 3894 }, { "epoch": 0.11370270901447921, "grad_norm": 0.4115566909313202, "learning_rate": 9.994315371341754e-06, "loss": 0.2798, "step": 3895 }, { "epoch": 0.11373190098085006, "grad_norm": 0.42047885060310364, "learning_rate": 9.994291056731486e-06, "loss": 0.2141, "step": 3896 }, { "epoch": 0.11376109294722092, "grad_norm": 0.43656250834465027, "learning_rate": 9.994266690261928e-06, "loss": 0.2107, "step": 3897 }, { "epoch": 0.11379028491359178, "grad_norm": 0.47970572113990784, "learning_rate": 9.99424227193334e-06, "loss": 0.2435, "step": 3898 }, { "epoch": 0.11381947687996263, "grad_norm": 0.38898396492004395, "learning_rate": 9.99421780174597e-06, "loss": 0.2587, "step": 3899 }, { "epoch": 0.11384866884633349, "grad_norm": 0.40073883533477783, "learning_rate": 9.994193279700072e-06, "loss": 0.2513, "step": 3900 }, { "epoch": 0.11387786081270435, "grad_norm": 0.3964472711086273, "learning_rate": 9.994168705795903e-06, "loss": 0.2277, "step": 3901 }, { "epoch": 0.1139070527790752, "grad_norm": 0.43430668115615845, "learning_rate": 9.994144080033716e-06, "loss": 0.2573, "step": 3902 }, { "epoch": 0.11393624474544606, "grad_norm": 0.42329439520835876, "learning_rate": 9.99411940241377e-06, "loss": 0.2705, "step": 3903 }, { "epoch": 0.11396543671181691, "grad_norm": 0.6119478344917297, "learning_rate": 9.994094672936316e-06, "loss": 0.2641, "step": 3904 }, { "epoch": 0.11399462867818776, "grad_norm": 0.37304234504699707, "learning_rate": 9.994069891601617e-06, "loss": 0.2476, "step": 3905 }, { "epoch": 0.11402382064455861, "grad_norm": 0.40186649560928345, "learning_rate": 9.994045058409924e-06, "loss": 0.2536, "step": 3906 }, { "epoch": 0.11405301261092947, "grad_norm": 0.37182360887527466, "learning_rate": 9.9940201733615e-06, "loss": 0.2387, "step": 3907 }, { "epoch": 0.11408220457730033, "grad_norm": 0.43707048892974854, "learning_rate": 9.993995236456602e-06, "loss": 0.2608, "step": 3908 }, { "epoch": 0.11411139654367118, "grad_norm": 0.46422120928764343, "learning_rate": 9.993970247695487e-06, "loss": 0.2526, "step": 3909 }, { "epoch": 0.11414058851004204, "grad_norm": 0.41315916180610657, "learning_rate": 9.993945207078418e-06, "loss": 0.2089, "step": 3910 }, { "epoch": 0.1141697804764129, "grad_norm": 0.39163368940353394, "learning_rate": 9.99392011460565e-06, "loss": 0.229, "step": 3911 }, { "epoch": 0.11419897244278375, "grad_norm": 0.40364575386047363, "learning_rate": 9.993894970277449e-06, "loss": 0.2785, "step": 3912 }, { "epoch": 0.1142281644091546, "grad_norm": 0.43904250860214233, "learning_rate": 9.993869774094072e-06, "loss": 0.2451, "step": 3913 }, { "epoch": 0.11425735637552546, "grad_norm": 0.3935973048210144, "learning_rate": 9.993844526055783e-06, "loss": 0.2731, "step": 3914 }, { "epoch": 0.1142865483418963, "grad_norm": 0.4003714621067047, "learning_rate": 9.993819226162843e-06, "loss": 0.2216, "step": 3915 }, { "epoch": 0.11431574030826716, "grad_norm": 0.3622840344905853, "learning_rate": 9.993793874415517e-06, "loss": 0.2206, "step": 3916 }, { "epoch": 0.11434493227463802, "grad_norm": 0.4401448965072632, "learning_rate": 9.993768470814063e-06, "loss": 0.3133, "step": 3917 }, { "epoch": 0.11437412424100887, "grad_norm": 0.4063674807548523, "learning_rate": 9.993743015358749e-06, "loss": 0.2322, "step": 3918 }, { "epoch": 0.11440331620737973, "grad_norm": 0.4238240420818329, "learning_rate": 9.993717508049839e-06, "loss": 0.3105, "step": 3919 }, { "epoch": 0.11443250817375059, "grad_norm": 0.40108123421669006, "learning_rate": 9.993691948887598e-06, "loss": 0.2706, "step": 3920 }, { "epoch": 0.11446170014012144, "grad_norm": 0.35033732652664185, "learning_rate": 9.993666337872289e-06, "loss": 0.2186, "step": 3921 }, { "epoch": 0.1144908921064923, "grad_norm": 0.46641501784324646, "learning_rate": 9.993640675004179e-06, "loss": 0.2616, "step": 3922 }, { "epoch": 0.11452008407286315, "grad_norm": 0.44711801409721375, "learning_rate": 9.993614960283538e-06, "loss": 0.2889, "step": 3923 }, { "epoch": 0.114549276039234, "grad_norm": 0.528488278388977, "learning_rate": 9.993589193710628e-06, "loss": 0.2353, "step": 3924 }, { "epoch": 0.11457846800560485, "grad_norm": 0.4013806879520416, "learning_rate": 9.993563375285719e-06, "loss": 0.2293, "step": 3925 }, { "epoch": 0.11460765997197571, "grad_norm": 0.4369736611843109, "learning_rate": 9.99353750500908e-06, "loss": 0.2692, "step": 3926 }, { "epoch": 0.11463685193834657, "grad_norm": 0.40169236063957214, "learning_rate": 9.993511582880976e-06, "loss": 0.2485, "step": 3927 }, { "epoch": 0.11466604390471742, "grad_norm": 0.5202195644378662, "learning_rate": 9.99348560890168e-06, "loss": 0.2922, "step": 3928 }, { "epoch": 0.11469523587108828, "grad_norm": 0.3877214789390564, "learning_rate": 9.993459583071458e-06, "loss": 0.249, "step": 3929 }, { "epoch": 0.11472442783745913, "grad_norm": 0.40743404626846313, "learning_rate": 9.993433505390587e-06, "loss": 0.2266, "step": 3930 }, { "epoch": 0.11475361980382999, "grad_norm": 0.38544341921806335, "learning_rate": 9.99340737585933e-06, "loss": 0.2272, "step": 3931 }, { "epoch": 0.11478281177020085, "grad_norm": 0.38010427355766296, "learning_rate": 9.993381194477963e-06, "loss": 0.2274, "step": 3932 }, { "epoch": 0.1148120037365717, "grad_norm": 0.36718785762786865, "learning_rate": 9.993354961246755e-06, "loss": 0.2631, "step": 3933 }, { "epoch": 0.11484119570294254, "grad_norm": 0.3930779993534088, "learning_rate": 9.99332867616598e-06, "loss": 0.2494, "step": 3934 }, { "epoch": 0.1148703876693134, "grad_norm": 0.39996209740638733, "learning_rate": 9.993302339235911e-06, "loss": 0.2817, "step": 3935 }, { "epoch": 0.11489957963568426, "grad_norm": 0.7533775568008423, "learning_rate": 9.993275950456822e-06, "loss": 0.2602, "step": 3936 }, { "epoch": 0.11492877160205511, "grad_norm": 0.3994196355342865, "learning_rate": 9.993249509828985e-06, "loss": 0.2309, "step": 3937 }, { "epoch": 0.11495796356842597, "grad_norm": 0.38485223054885864, "learning_rate": 9.993223017352679e-06, "loss": 0.234, "step": 3938 }, { "epoch": 0.11498715553479683, "grad_norm": 0.5121521353721619, "learning_rate": 9.993196473028172e-06, "loss": 0.2993, "step": 3939 }, { "epoch": 0.11501634750116768, "grad_norm": 0.39124777913093567, "learning_rate": 9.993169876855744e-06, "loss": 0.2344, "step": 3940 }, { "epoch": 0.11504553946753854, "grad_norm": 0.3915795385837555, "learning_rate": 9.993143228835671e-06, "loss": 0.2489, "step": 3941 }, { "epoch": 0.1150747314339094, "grad_norm": 0.3817547857761383, "learning_rate": 9.993116528968231e-06, "loss": 0.2279, "step": 3942 }, { "epoch": 0.11510392340028024, "grad_norm": 0.3482235372066498, "learning_rate": 9.9930897772537e-06, "loss": 0.2437, "step": 3943 }, { "epoch": 0.11513311536665109, "grad_norm": 0.41146472096443176, "learning_rate": 9.993062973692354e-06, "loss": 0.2538, "step": 3944 }, { "epoch": 0.11516230733302195, "grad_norm": 0.40220487117767334, "learning_rate": 9.993036118284472e-06, "loss": 0.2789, "step": 3945 }, { "epoch": 0.1151914992993928, "grad_norm": 0.40801694989204407, "learning_rate": 9.993009211030336e-06, "loss": 0.2756, "step": 3946 }, { "epoch": 0.11522069126576366, "grad_norm": 0.3471328318119049, "learning_rate": 9.992982251930221e-06, "loss": 0.204, "step": 3947 }, { "epoch": 0.11524988323213452, "grad_norm": 0.47114476561546326, "learning_rate": 9.992955240984408e-06, "loss": 0.2742, "step": 3948 }, { "epoch": 0.11527907519850537, "grad_norm": 0.42926570773124695, "learning_rate": 9.992928178193181e-06, "loss": 0.28, "step": 3949 }, { "epoch": 0.11530826716487623, "grad_norm": 0.47577252984046936, "learning_rate": 9.992901063556817e-06, "loss": 0.3227, "step": 3950 }, { "epoch": 0.11533745913124709, "grad_norm": 0.39401566982269287, "learning_rate": 9.9928738970756e-06, "loss": 0.2332, "step": 3951 }, { "epoch": 0.11536665109761794, "grad_norm": 0.4060130715370178, "learning_rate": 9.992846678749811e-06, "loss": 0.2666, "step": 3952 }, { "epoch": 0.11539584306398878, "grad_norm": 0.5260512828826904, "learning_rate": 9.992819408579731e-06, "loss": 0.2591, "step": 3953 }, { "epoch": 0.11542503503035964, "grad_norm": 0.32765188813209534, "learning_rate": 9.992792086565646e-06, "loss": 0.1778, "step": 3954 }, { "epoch": 0.1154542269967305, "grad_norm": 0.44146066904067993, "learning_rate": 9.992764712707839e-06, "loss": 0.2432, "step": 3955 }, { "epoch": 0.11548341896310135, "grad_norm": 0.3977898359298706, "learning_rate": 9.992737287006594e-06, "loss": 0.2267, "step": 3956 }, { "epoch": 0.11551261092947221, "grad_norm": 0.38427111506462097, "learning_rate": 9.992709809462194e-06, "loss": 0.2262, "step": 3957 }, { "epoch": 0.11554180289584307, "grad_norm": 0.36483046412467957, "learning_rate": 9.992682280074926e-06, "loss": 0.188, "step": 3958 }, { "epoch": 0.11557099486221392, "grad_norm": 0.39251935482025146, "learning_rate": 9.992654698845076e-06, "loss": 0.2433, "step": 3959 }, { "epoch": 0.11560018682858478, "grad_norm": 0.5129233002662659, "learning_rate": 9.992627065772934e-06, "loss": 0.2393, "step": 3960 }, { "epoch": 0.11562937879495563, "grad_norm": 0.3514626920223236, "learning_rate": 9.992599380858778e-06, "loss": 0.2077, "step": 3961 }, { "epoch": 0.11565857076132648, "grad_norm": 0.4473268389701843, "learning_rate": 9.992571644102902e-06, "loss": 0.2618, "step": 3962 }, { "epoch": 0.11568776272769733, "grad_norm": 0.35809823870658875, "learning_rate": 9.992543855505595e-06, "loss": 0.2028, "step": 3963 }, { "epoch": 0.11571695469406819, "grad_norm": 0.40232452750205994, "learning_rate": 9.992516015067139e-06, "loss": 0.2369, "step": 3964 }, { "epoch": 0.11574614666043904, "grad_norm": 0.47900617122650146, "learning_rate": 9.99248812278783e-06, "loss": 0.2523, "step": 3965 }, { "epoch": 0.1157753386268099, "grad_norm": 0.42098143696784973, "learning_rate": 9.992460178667955e-06, "loss": 0.3256, "step": 3966 }, { "epoch": 0.11580453059318076, "grad_norm": 0.41295525431632996, "learning_rate": 9.992432182707802e-06, "loss": 0.192, "step": 3967 }, { "epoch": 0.11583372255955161, "grad_norm": 0.3760359585285187, "learning_rate": 9.992404134907665e-06, "loss": 0.2534, "step": 3968 }, { "epoch": 0.11586291452592247, "grad_norm": 0.4341569244861603, "learning_rate": 9.992376035267835e-06, "loss": 0.2134, "step": 3969 }, { "epoch": 0.11589210649229333, "grad_norm": 0.44678768515586853, "learning_rate": 9.9923478837886e-06, "loss": 0.2491, "step": 3970 }, { "epoch": 0.11592129845866418, "grad_norm": 0.4302411377429962, "learning_rate": 9.992319680470257e-06, "loss": 0.233, "step": 3971 }, { "epoch": 0.11595049042503502, "grad_norm": 0.4814625084400177, "learning_rate": 9.992291425313096e-06, "loss": 0.3422, "step": 3972 }, { "epoch": 0.11597968239140588, "grad_norm": 0.5194507837295532, "learning_rate": 9.992263118317412e-06, "loss": 0.2705, "step": 3973 }, { "epoch": 0.11600887435777674, "grad_norm": 0.4565567374229431, "learning_rate": 9.992234759483498e-06, "loss": 0.237, "step": 3974 }, { "epoch": 0.11603806632414759, "grad_norm": 0.5637127757072449, "learning_rate": 9.99220634881165e-06, "loss": 0.3091, "step": 3975 }, { "epoch": 0.11606725829051845, "grad_norm": 0.55235755443573, "learning_rate": 9.99217788630216e-06, "loss": 0.264, "step": 3976 }, { "epoch": 0.1160964502568893, "grad_norm": 0.43174242973327637, "learning_rate": 9.992149371955324e-06, "loss": 0.2652, "step": 3977 }, { "epoch": 0.11612564222326016, "grad_norm": 0.5047963857650757, "learning_rate": 9.992120805771442e-06, "loss": 0.271, "step": 3978 }, { "epoch": 0.11615483418963102, "grad_norm": 0.434160441160202, "learning_rate": 9.992092187750808e-06, "loss": 0.2871, "step": 3979 }, { "epoch": 0.11618402615600187, "grad_norm": 0.40559640526771545, "learning_rate": 9.992063517893717e-06, "loss": 0.2311, "step": 3980 }, { "epoch": 0.11621321812237272, "grad_norm": 0.48829200863838196, "learning_rate": 9.992034796200469e-06, "loss": 0.2949, "step": 3981 }, { "epoch": 0.11624241008874357, "grad_norm": 0.5615059733390808, "learning_rate": 9.992006022671364e-06, "loss": 0.316, "step": 3982 }, { "epoch": 0.11627160205511443, "grad_norm": 0.4521310329437256, "learning_rate": 9.991977197306697e-06, "loss": 0.2614, "step": 3983 }, { "epoch": 0.11630079402148528, "grad_norm": 0.4365425407886505, "learning_rate": 9.991948320106771e-06, "loss": 0.2764, "step": 3984 }, { "epoch": 0.11632998598785614, "grad_norm": 0.3716062903404236, "learning_rate": 9.991919391071883e-06, "loss": 0.2012, "step": 3985 }, { "epoch": 0.116359177954227, "grad_norm": 0.3654353618621826, "learning_rate": 9.991890410202335e-06, "loss": 0.2518, "step": 3986 }, { "epoch": 0.11638836992059785, "grad_norm": 0.4463519752025604, "learning_rate": 9.991861377498425e-06, "loss": 0.2324, "step": 3987 }, { "epoch": 0.11641756188696871, "grad_norm": 0.4445708990097046, "learning_rate": 9.991832292960459e-06, "loss": 0.297, "step": 3988 }, { "epoch": 0.11644675385333957, "grad_norm": 0.6064642071723938, "learning_rate": 9.991803156588736e-06, "loss": 0.2167, "step": 3989 }, { "epoch": 0.11647594581971042, "grad_norm": 0.34941086173057556, "learning_rate": 9.991773968383559e-06, "loss": 0.2144, "step": 3990 }, { "epoch": 0.11650513778608126, "grad_norm": 0.38141557574272156, "learning_rate": 9.991744728345232e-06, "loss": 0.245, "step": 3991 }, { "epoch": 0.11653432975245212, "grad_norm": 0.3921942412853241, "learning_rate": 9.991715436474057e-06, "loss": 0.2486, "step": 3992 }, { "epoch": 0.11656352171882298, "grad_norm": 0.4264279007911682, "learning_rate": 9.991686092770341e-06, "loss": 0.3186, "step": 3993 }, { "epoch": 0.11659271368519383, "grad_norm": 0.3844578266143799, "learning_rate": 9.991656697234387e-06, "loss": 0.2282, "step": 3994 }, { "epoch": 0.11662190565156469, "grad_norm": 0.6528037190437317, "learning_rate": 9.991627249866498e-06, "loss": 0.262, "step": 3995 }, { "epoch": 0.11665109761793555, "grad_norm": 0.3834149241447449, "learning_rate": 9.991597750666984e-06, "loss": 0.2264, "step": 3996 }, { "epoch": 0.1166802895843064, "grad_norm": 0.4286477267742157, "learning_rate": 9.991568199636149e-06, "loss": 0.248, "step": 3997 }, { "epoch": 0.11670948155067726, "grad_norm": 0.4476921558380127, "learning_rate": 9.991538596774298e-06, "loss": 0.2697, "step": 3998 }, { "epoch": 0.11673867351704811, "grad_norm": 0.39573198556900024, "learning_rate": 9.99150894208174e-06, "loss": 0.2637, "step": 3999 }, { "epoch": 0.11676786548341897, "grad_norm": 0.39512577652931213, "learning_rate": 9.991479235558787e-06, "loss": 0.2277, "step": 4000 }, { "epoch": 0.11679705744978981, "grad_norm": 0.8365059494972229, "learning_rate": 9.991449477205741e-06, "loss": 0.2113, "step": 4001 }, { "epoch": 0.11682624941616067, "grad_norm": 0.40067464113235474, "learning_rate": 9.991419667022914e-06, "loss": 0.2048, "step": 4002 }, { "epoch": 0.11685544138253152, "grad_norm": 0.429399311542511, "learning_rate": 9.991389805010617e-06, "loss": 0.2775, "step": 4003 }, { "epoch": 0.11688463334890238, "grad_norm": 0.3845527768135071, "learning_rate": 9.991359891169158e-06, "loss": 0.2771, "step": 4004 }, { "epoch": 0.11691382531527324, "grad_norm": 0.3698119819164276, "learning_rate": 9.991329925498847e-06, "loss": 0.2233, "step": 4005 }, { "epoch": 0.1169430172816441, "grad_norm": 0.3908216655254364, "learning_rate": 9.991299907999998e-06, "loss": 0.2485, "step": 4006 }, { "epoch": 0.11697220924801495, "grad_norm": 0.3865780532360077, "learning_rate": 9.991269838672919e-06, "loss": 0.2713, "step": 4007 }, { "epoch": 0.1170014012143858, "grad_norm": 0.3747858703136444, "learning_rate": 9.991239717517924e-06, "loss": 0.2154, "step": 4008 }, { "epoch": 0.11703059318075666, "grad_norm": 0.42816874384880066, "learning_rate": 9.991209544535328e-06, "loss": 0.2825, "step": 4009 }, { "epoch": 0.1170597851471275, "grad_norm": 0.3284456729888916, "learning_rate": 9.991179319725442e-06, "loss": 0.2102, "step": 4010 }, { "epoch": 0.11708897711349836, "grad_norm": 0.3509351313114166, "learning_rate": 9.991149043088579e-06, "loss": 0.2565, "step": 4011 }, { "epoch": 0.11711816907986922, "grad_norm": 0.39071977138519287, "learning_rate": 9.991118714625054e-06, "loss": 0.2566, "step": 4012 }, { "epoch": 0.11714736104624007, "grad_norm": 0.3944714665412903, "learning_rate": 9.991088334335182e-06, "loss": 0.2921, "step": 4013 }, { "epoch": 0.11717655301261093, "grad_norm": 0.3793424963951111, "learning_rate": 9.99105790221928e-06, "loss": 0.266, "step": 4014 }, { "epoch": 0.11720574497898179, "grad_norm": 0.3715197443962097, "learning_rate": 9.991027418277663e-06, "loss": 0.3019, "step": 4015 }, { "epoch": 0.11723493694535264, "grad_norm": 0.4057025909423828, "learning_rate": 9.990996882510647e-06, "loss": 0.2391, "step": 4016 }, { "epoch": 0.1172641289117235, "grad_norm": 0.3754815459251404, "learning_rate": 9.99096629491855e-06, "loss": 0.1974, "step": 4017 }, { "epoch": 0.11729332087809435, "grad_norm": 0.4275881052017212, "learning_rate": 9.990935655501688e-06, "loss": 0.2676, "step": 4018 }, { "epoch": 0.11732251284446521, "grad_norm": 0.4017067551612854, "learning_rate": 9.990904964260381e-06, "loss": 0.3273, "step": 4019 }, { "epoch": 0.11735170481083605, "grad_norm": 0.3647809326648712, "learning_rate": 9.990874221194948e-06, "loss": 0.2165, "step": 4020 }, { "epoch": 0.11738089677720691, "grad_norm": 0.34044766426086426, "learning_rate": 9.990843426305706e-06, "loss": 0.2104, "step": 4021 }, { "epoch": 0.11741008874357776, "grad_norm": 0.4123997390270233, "learning_rate": 9.990812579592974e-06, "loss": 0.2674, "step": 4022 }, { "epoch": 0.11743928070994862, "grad_norm": 0.4396747052669525, "learning_rate": 9.990781681057077e-06, "loss": 0.2193, "step": 4023 }, { "epoch": 0.11746847267631948, "grad_norm": 0.5095478892326355, "learning_rate": 9.990750730698331e-06, "loss": 0.2857, "step": 4024 }, { "epoch": 0.11749766464269033, "grad_norm": 0.44744426012039185, "learning_rate": 9.99071972851706e-06, "loss": 0.2726, "step": 4025 }, { "epoch": 0.11752685660906119, "grad_norm": 0.3807077407836914, "learning_rate": 9.990688674513588e-06, "loss": 0.2872, "step": 4026 }, { "epoch": 0.11755604857543205, "grad_norm": 0.4788123369216919, "learning_rate": 9.99065756868823e-06, "loss": 0.3212, "step": 4027 }, { "epoch": 0.1175852405418029, "grad_norm": 0.4556816816329956, "learning_rate": 9.990626411041318e-06, "loss": 0.2619, "step": 4028 }, { "epoch": 0.11761443250817374, "grad_norm": 0.4339595139026642, "learning_rate": 9.99059520157317e-06, "loss": 0.2618, "step": 4029 }, { "epoch": 0.1176436244745446, "grad_norm": 0.4445286989212036, "learning_rate": 9.99056394028411e-06, "loss": 0.2972, "step": 4030 }, { "epoch": 0.11767281644091546, "grad_norm": 0.40364107489585876, "learning_rate": 9.990532627174464e-06, "loss": 0.2637, "step": 4031 }, { "epoch": 0.11770200840728631, "grad_norm": 0.3610723316669464, "learning_rate": 9.99050126224456e-06, "loss": 0.2219, "step": 4032 }, { "epoch": 0.11773120037365717, "grad_norm": 0.4212290346622467, "learning_rate": 9.990469845494719e-06, "loss": 0.2542, "step": 4033 }, { "epoch": 0.11776039234002803, "grad_norm": 0.4903879761695862, "learning_rate": 9.99043837692527e-06, "loss": 0.2789, "step": 4034 }, { "epoch": 0.11778958430639888, "grad_norm": 0.3809575140476227, "learning_rate": 9.990406856536536e-06, "loss": 0.255, "step": 4035 }, { "epoch": 0.11781877627276974, "grad_norm": 0.3863333463668823, "learning_rate": 9.990375284328848e-06, "loss": 0.2178, "step": 4036 }, { "epoch": 0.1178479682391406, "grad_norm": 0.49656620621681213, "learning_rate": 9.990343660302534e-06, "loss": 0.2606, "step": 4037 }, { "epoch": 0.11787716020551145, "grad_norm": 0.4050096273422241, "learning_rate": 9.990311984457922e-06, "loss": 0.2367, "step": 4038 }, { "epoch": 0.11790635217188229, "grad_norm": 0.3561425805091858, "learning_rate": 9.99028025679534e-06, "loss": 0.2505, "step": 4039 }, { "epoch": 0.11793554413825315, "grad_norm": 0.3657906949520111, "learning_rate": 9.990248477315117e-06, "loss": 0.2349, "step": 4040 }, { "epoch": 0.117964736104624, "grad_norm": 0.49095281958580017, "learning_rate": 9.990216646017584e-06, "loss": 0.2377, "step": 4041 }, { "epoch": 0.11799392807099486, "grad_norm": 0.5106359720230103, "learning_rate": 9.99018476290307e-06, "loss": 0.2666, "step": 4042 }, { "epoch": 0.11802312003736572, "grad_norm": 0.45662471652030945, "learning_rate": 9.990152827971909e-06, "loss": 0.2196, "step": 4043 }, { "epoch": 0.11805231200373657, "grad_norm": 0.9131811261177063, "learning_rate": 9.990120841224432e-06, "loss": 0.2287, "step": 4044 }, { "epoch": 0.11808150397010743, "grad_norm": 0.4543303847312927, "learning_rate": 9.990088802660967e-06, "loss": 0.2269, "step": 4045 }, { "epoch": 0.11811069593647829, "grad_norm": 0.4044543206691742, "learning_rate": 9.990056712281851e-06, "loss": 0.2404, "step": 4046 }, { "epoch": 0.11813988790284914, "grad_norm": 0.43315717577934265, "learning_rate": 9.990024570087416e-06, "loss": 0.2449, "step": 4047 }, { "epoch": 0.11816907986921998, "grad_norm": 0.4624362289905548, "learning_rate": 9.989992376077994e-06, "loss": 0.2726, "step": 4048 }, { "epoch": 0.11819827183559084, "grad_norm": 0.36222222447395325, "learning_rate": 9.989960130253923e-06, "loss": 0.2046, "step": 4049 }, { "epoch": 0.1182274638019617, "grad_norm": 0.6596997976303101, "learning_rate": 9.989927832615536e-06, "loss": 0.2799, "step": 4050 }, { "epoch": 0.11825665576833255, "grad_norm": 0.4091848134994507, "learning_rate": 9.989895483163167e-06, "loss": 0.2779, "step": 4051 }, { "epoch": 0.11828584773470341, "grad_norm": 0.3866885304450989, "learning_rate": 9.989863081897154e-06, "loss": 0.1995, "step": 4052 }, { "epoch": 0.11831503970107426, "grad_norm": 0.4677219092845917, "learning_rate": 9.989830628817832e-06, "loss": 0.2464, "step": 4053 }, { "epoch": 0.11834423166744512, "grad_norm": 0.47316664457321167, "learning_rate": 9.989798123925537e-06, "loss": 0.2809, "step": 4054 }, { "epoch": 0.11837342363381598, "grad_norm": 0.4889328181743622, "learning_rate": 9.98976556722061e-06, "loss": 0.2786, "step": 4055 }, { "epoch": 0.11840261560018683, "grad_norm": 0.3950876295566559, "learning_rate": 9.989732958703387e-06, "loss": 0.2303, "step": 4056 }, { "epoch": 0.11843180756655769, "grad_norm": 0.5024986267089844, "learning_rate": 9.989700298374205e-06, "loss": 0.2347, "step": 4057 }, { "epoch": 0.11846099953292853, "grad_norm": 0.4117615520954132, "learning_rate": 9.989667586233407e-06, "loss": 0.2194, "step": 4058 }, { "epoch": 0.11849019149929939, "grad_norm": 0.5237500071525574, "learning_rate": 9.98963482228133e-06, "loss": 0.2772, "step": 4059 }, { "epoch": 0.11851938346567024, "grad_norm": 0.5226225256919861, "learning_rate": 9.989602006518314e-06, "loss": 0.2687, "step": 4060 }, { "epoch": 0.1185485754320411, "grad_norm": 0.38113075494766235, "learning_rate": 9.9895691389447e-06, "loss": 0.2089, "step": 4061 }, { "epoch": 0.11857776739841196, "grad_norm": 0.5568991899490356, "learning_rate": 9.98953621956083e-06, "loss": 0.2343, "step": 4062 }, { "epoch": 0.11860695936478281, "grad_norm": 0.4519885182380676, "learning_rate": 9.989503248367045e-06, "loss": 0.2499, "step": 4063 }, { "epoch": 0.11863615133115367, "grad_norm": 0.5674224495887756, "learning_rate": 9.98947022536369e-06, "loss": 0.2665, "step": 4064 }, { "epoch": 0.11866534329752453, "grad_norm": 0.42131316661834717, "learning_rate": 9.989437150551105e-06, "loss": 0.2913, "step": 4065 }, { "epoch": 0.11869453526389538, "grad_norm": 0.3684716820716858, "learning_rate": 9.989404023929633e-06, "loss": 0.2146, "step": 4066 }, { "epoch": 0.11872372723026622, "grad_norm": 0.4152289927005768, "learning_rate": 9.98937084549962e-06, "loss": 0.2609, "step": 4067 }, { "epoch": 0.11875291919663708, "grad_norm": 0.46595868468284607, "learning_rate": 9.98933761526141e-06, "loss": 0.284, "step": 4068 }, { "epoch": 0.11878211116300794, "grad_norm": 0.5815571546554565, "learning_rate": 9.989304333215349e-06, "loss": 0.2359, "step": 4069 }, { "epoch": 0.11881130312937879, "grad_norm": 0.5275472402572632, "learning_rate": 9.98927099936178e-06, "loss": 0.2425, "step": 4070 }, { "epoch": 0.11884049509574965, "grad_norm": 0.4516274034976959, "learning_rate": 9.98923761370105e-06, "loss": 0.2812, "step": 4071 }, { "epoch": 0.1188696870621205, "grad_norm": 0.39017361402511597, "learning_rate": 9.989204176233507e-06, "loss": 0.2051, "step": 4072 }, { "epoch": 0.11889887902849136, "grad_norm": 0.6148287653923035, "learning_rate": 9.989170686959498e-06, "loss": 0.2517, "step": 4073 }, { "epoch": 0.11892807099486222, "grad_norm": 0.4713170826435089, "learning_rate": 9.989137145879369e-06, "loss": 0.2535, "step": 4074 }, { "epoch": 0.11895726296123307, "grad_norm": 0.7014240622520447, "learning_rate": 9.989103552993468e-06, "loss": 0.2914, "step": 4075 }, { "epoch": 0.11898645492760393, "grad_norm": 0.42992356419563293, "learning_rate": 9.989069908302146e-06, "loss": 0.2331, "step": 4076 }, { "epoch": 0.11901564689397477, "grad_norm": 0.47274160385131836, "learning_rate": 9.989036211805754e-06, "loss": 0.2046, "step": 4077 }, { "epoch": 0.11904483886034563, "grad_norm": 0.46824759244918823, "learning_rate": 9.989002463504637e-06, "loss": 0.2874, "step": 4078 }, { "epoch": 0.11907403082671648, "grad_norm": 0.38820382952690125, "learning_rate": 9.98896866339915e-06, "loss": 0.2493, "step": 4079 }, { "epoch": 0.11910322279308734, "grad_norm": 0.3795861005783081, "learning_rate": 9.98893481148964e-06, "loss": 0.233, "step": 4080 }, { "epoch": 0.1191324147594582, "grad_norm": 0.4535980522632599, "learning_rate": 9.988900907776462e-06, "loss": 0.383, "step": 4081 }, { "epoch": 0.11916160672582905, "grad_norm": 0.46427416801452637, "learning_rate": 9.988866952259966e-06, "loss": 0.2273, "step": 4082 }, { "epoch": 0.11919079869219991, "grad_norm": 0.38288000226020813, "learning_rate": 9.988832944940506e-06, "loss": 0.2337, "step": 4083 }, { "epoch": 0.11921999065857077, "grad_norm": 0.43517154455184937, "learning_rate": 9.988798885818431e-06, "loss": 0.2577, "step": 4084 }, { "epoch": 0.11924918262494162, "grad_norm": 0.3836679756641388, "learning_rate": 9.9887647748941e-06, "loss": 0.2236, "step": 4085 }, { "epoch": 0.11927837459131248, "grad_norm": 0.42254263162612915, "learning_rate": 9.988730612167865e-06, "loss": 0.2825, "step": 4086 }, { "epoch": 0.11930756655768332, "grad_norm": 0.41938120126724243, "learning_rate": 9.98869639764008e-06, "loss": 0.2464, "step": 4087 }, { "epoch": 0.11933675852405418, "grad_norm": 0.535233736038208, "learning_rate": 9.988662131311104e-06, "loss": 0.2611, "step": 4088 }, { "epoch": 0.11936595049042503, "grad_norm": 0.47658389806747437, "learning_rate": 9.988627813181286e-06, "loss": 0.2464, "step": 4089 }, { "epoch": 0.11939514245679589, "grad_norm": 0.45538008213043213, "learning_rate": 9.988593443250988e-06, "loss": 0.2906, "step": 4090 }, { "epoch": 0.11942433442316674, "grad_norm": 0.39781782031059265, "learning_rate": 9.988559021520565e-06, "loss": 0.2531, "step": 4091 }, { "epoch": 0.1194535263895376, "grad_norm": 1.9034610986709595, "learning_rate": 9.988524547990374e-06, "loss": 0.2347, "step": 4092 }, { "epoch": 0.11948271835590846, "grad_norm": 0.37115156650543213, "learning_rate": 9.988490022660773e-06, "loss": 0.183, "step": 4093 }, { "epoch": 0.11951191032227931, "grad_norm": 0.45832011103630066, "learning_rate": 9.988455445532122e-06, "loss": 0.2417, "step": 4094 }, { "epoch": 0.11954110228865017, "grad_norm": 0.6322723031044006, "learning_rate": 9.988420816604778e-06, "loss": 0.2464, "step": 4095 }, { "epoch": 0.11957029425502101, "grad_norm": 0.38374069333076477, "learning_rate": 9.988386135879102e-06, "loss": 0.241, "step": 4096 }, { "epoch": 0.11959948622139187, "grad_norm": 0.4892125725746155, "learning_rate": 9.988351403355455e-06, "loss": 0.286, "step": 4097 }, { "epoch": 0.11962867818776272, "grad_norm": 0.4126143157482147, "learning_rate": 9.988316619034195e-06, "loss": 0.2834, "step": 4098 }, { "epoch": 0.11965787015413358, "grad_norm": 0.4291587471961975, "learning_rate": 9.988281782915686e-06, "loss": 0.2115, "step": 4099 }, { "epoch": 0.11968706212050444, "grad_norm": 0.3976251184940338, "learning_rate": 9.988246895000287e-06, "loss": 0.2426, "step": 4100 }, { "epoch": 0.11971625408687529, "grad_norm": 0.37979093194007874, "learning_rate": 9.988211955288361e-06, "loss": 0.2145, "step": 4101 }, { "epoch": 0.11974544605324615, "grad_norm": 0.4546096622943878, "learning_rate": 9.988176963780272e-06, "loss": 0.2866, "step": 4102 }, { "epoch": 0.119774638019617, "grad_norm": 0.47342294454574585, "learning_rate": 9.988141920476381e-06, "loss": 0.2629, "step": 4103 }, { "epoch": 0.11980382998598786, "grad_norm": 0.5924100875854492, "learning_rate": 9.988106825377056e-06, "loss": 0.2488, "step": 4104 }, { "epoch": 0.11983302195235872, "grad_norm": 0.42642831802368164, "learning_rate": 9.988071678482658e-06, "loss": 0.2775, "step": 4105 }, { "epoch": 0.11986221391872956, "grad_norm": 0.38600894808769226, "learning_rate": 9.988036479793553e-06, "loss": 0.2453, "step": 4106 }, { "epoch": 0.11989140588510042, "grad_norm": 0.5064908266067505, "learning_rate": 9.988001229310107e-06, "loss": 0.3299, "step": 4107 }, { "epoch": 0.11992059785147127, "grad_norm": 0.3539981245994568, "learning_rate": 9.987965927032684e-06, "loss": 0.2599, "step": 4108 }, { "epoch": 0.11994978981784213, "grad_norm": 0.40380388498306274, "learning_rate": 9.987930572961653e-06, "loss": 0.2428, "step": 4109 }, { "epoch": 0.11997898178421298, "grad_norm": 0.4068005084991455, "learning_rate": 9.98789516709738e-06, "loss": 0.2784, "step": 4110 }, { "epoch": 0.12000817375058384, "grad_norm": 0.4169926047325134, "learning_rate": 9.987859709440233e-06, "loss": 0.2629, "step": 4111 }, { "epoch": 0.1200373657169547, "grad_norm": 0.36409786343574524, "learning_rate": 9.98782419999058e-06, "loss": 0.2084, "step": 4112 }, { "epoch": 0.12006655768332555, "grad_norm": 0.4732851982116699, "learning_rate": 9.98778863874879e-06, "loss": 0.3182, "step": 4113 }, { "epoch": 0.12009574964969641, "grad_norm": 0.4911387860774994, "learning_rate": 9.987753025715232e-06, "loss": 0.2349, "step": 4114 }, { "epoch": 0.12012494161606725, "grad_norm": 0.412626713514328, "learning_rate": 9.987717360890275e-06, "loss": 0.219, "step": 4115 }, { "epoch": 0.12015413358243811, "grad_norm": 0.6491528749465942, "learning_rate": 9.98768164427429e-06, "loss": 0.2822, "step": 4116 }, { "epoch": 0.12018332554880896, "grad_norm": 0.39986908435821533, "learning_rate": 9.987645875867647e-06, "loss": 0.2461, "step": 4117 }, { "epoch": 0.12021251751517982, "grad_norm": 0.35754555463790894, "learning_rate": 9.98761005567072e-06, "loss": 0.2384, "step": 4118 }, { "epoch": 0.12024170948155068, "grad_norm": 0.4676995277404785, "learning_rate": 9.98757418368388e-06, "loss": 0.2337, "step": 4119 }, { "epoch": 0.12027090144792153, "grad_norm": 0.4273027181625366, "learning_rate": 9.987538259907497e-06, "loss": 0.2813, "step": 4120 }, { "epoch": 0.12030009341429239, "grad_norm": 0.44930192828178406, "learning_rate": 9.987502284341946e-06, "loss": 0.2765, "step": 4121 }, { "epoch": 0.12032928538066325, "grad_norm": 0.40370243787765503, "learning_rate": 9.987466256987602e-06, "loss": 0.2468, "step": 4122 }, { "epoch": 0.1203584773470341, "grad_norm": 0.39101508259773254, "learning_rate": 9.987430177844834e-06, "loss": 0.2664, "step": 4123 }, { "epoch": 0.12038766931340496, "grad_norm": 0.3849363923072815, "learning_rate": 9.987394046914023e-06, "loss": 0.2345, "step": 4124 }, { "epoch": 0.1204168612797758, "grad_norm": 0.4216582775115967, "learning_rate": 9.98735786419554e-06, "loss": 0.2639, "step": 4125 }, { "epoch": 0.12044605324614666, "grad_norm": 0.3850148916244507, "learning_rate": 9.987321629689764e-06, "loss": 0.2609, "step": 4126 }, { "epoch": 0.12047524521251751, "grad_norm": 0.3896682858467102, "learning_rate": 9.987285343397066e-06, "loss": 0.2355, "step": 4127 }, { "epoch": 0.12050443717888837, "grad_norm": 0.4764021635055542, "learning_rate": 9.987249005317828e-06, "loss": 0.3252, "step": 4128 }, { "epoch": 0.12053362914525922, "grad_norm": 0.335543155670166, "learning_rate": 9.987212615452424e-06, "loss": 0.2027, "step": 4129 }, { "epoch": 0.12056282111163008, "grad_norm": 0.36796683073043823, "learning_rate": 9.987176173801236e-06, "loss": 0.2792, "step": 4130 }, { "epoch": 0.12059201307800094, "grad_norm": 0.38684314489364624, "learning_rate": 9.987139680364637e-06, "loss": 0.2253, "step": 4131 }, { "epoch": 0.1206212050443718, "grad_norm": 0.4632960557937622, "learning_rate": 9.98710313514301e-06, "loss": 0.2923, "step": 4132 }, { "epoch": 0.12065039701074265, "grad_norm": 0.36070379614830017, "learning_rate": 9.987066538136731e-06, "loss": 0.2462, "step": 4133 }, { "epoch": 0.12067958897711349, "grad_norm": 0.4520752727985382, "learning_rate": 9.987029889346185e-06, "loss": 0.2947, "step": 4134 }, { "epoch": 0.12070878094348435, "grad_norm": 0.38677114248275757, "learning_rate": 9.986993188771747e-06, "loss": 0.2302, "step": 4135 }, { "epoch": 0.1207379729098552, "grad_norm": 0.46603235602378845, "learning_rate": 9.986956436413801e-06, "loss": 0.2304, "step": 4136 }, { "epoch": 0.12076716487622606, "grad_norm": 0.3443570137023926, "learning_rate": 9.98691963227273e-06, "loss": 0.2171, "step": 4137 }, { "epoch": 0.12079635684259692, "grad_norm": 0.39650142192840576, "learning_rate": 9.986882776348913e-06, "loss": 0.213, "step": 4138 }, { "epoch": 0.12082554880896777, "grad_norm": 0.39965468645095825, "learning_rate": 9.986845868642735e-06, "loss": 0.2889, "step": 4139 }, { "epoch": 0.12085474077533863, "grad_norm": 0.6158609390258789, "learning_rate": 9.986808909154577e-06, "loss": 0.2283, "step": 4140 }, { "epoch": 0.12088393274170948, "grad_norm": 0.45941299200057983, "learning_rate": 9.986771897884826e-06, "loss": 0.2519, "step": 4141 }, { "epoch": 0.12091312470808034, "grad_norm": 0.3866821527481079, "learning_rate": 9.986734834833864e-06, "loss": 0.2527, "step": 4142 }, { "epoch": 0.1209423166744512, "grad_norm": 0.3748592436313629, "learning_rate": 9.986697720002075e-06, "loss": 0.2594, "step": 4143 }, { "epoch": 0.12097150864082204, "grad_norm": 0.391216903924942, "learning_rate": 9.986660553389846e-06, "loss": 0.2079, "step": 4144 }, { "epoch": 0.1210007006071929, "grad_norm": 0.49675095081329346, "learning_rate": 9.986623334997565e-06, "loss": 0.3243, "step": 4145 }, { "epoch": 0.12102989257356375, "grad_norm": 0.3863741159439087, "learning_rate": 9.986586064825614e-06, "loss": 0.2499, "step": 4146 }, { "epoch": 0.12105908453993461, "grad_norm": 0.39719754457473755, "learning_rate": 9.986548742874383e-06, "loss": 0.2631, "step": 4147 }, { "epoch": 0.12108827650630546, "grad_norm": 0.43283960223197937, "learning_rate": 9.986511369144257e-06, "loss": 0.2627, "step": 4148 }, { "epoch": 0.12111746847267632, "grad_norm": 0.41676416993141174, "learning_rate": 9.986473943635628e-06, "loss": 0.2532, "step": 4149 }, { "epoch": 0.12114666043904718, "grad_norm": 0.39572688937187195, "learning_rate": 9.98643646634888e-06, "loss": 0.2585, "step": 4150 }, { "epoch": 0.12117585240541803, "grad_norm": 0.543289840221405, "learning_rate": 9.986398937284405e-06, "loss": 0.2853, "step": 4151 }, { "epoch": 0.12120504437178889, "grad_norm": 0.40537500381469727, "learning_rate": 9.986361356442594e-06, "loss": 0.2611, "step": 4152 }, { "epoch": 0.12123423633815973, "grad_norm": 0.425273597240448, "learning_rate": 9.986323723823834e-06, "loss": 0.275, "step": 4153 }, { "epoch": 0.12126342830453059, "grad_norm": 0.6095098853111267, "learning_rate": 9.986286039428518e-06, "loss": 0.2476, "step": 4154 }, { "epoch": 0.12129262027090144, "grad_norm": 0.38965004682540894, "learning_rate": 9.986248303257035e-06, "loss": 0.2342, "step": 4155 }, { "epoch": 0.1213218122372723, "grad_norm": 0.3706378936767578, "learning_rate": 9.98621051530978e-06, "loss": 0.2047, "step": 4156 }, { "epoch": 0.12135100420364316, "grad_norm": 0.4318523705005646, "learning_rate": 9.986172675587142e-06, "loss": 0.2907, "step": 4157 }, { "epoch": 0.12138019617001401, "grad_norm": 0.4233377277851105, "learning_rate": 9.986134784089518e-06, "loss": 0.2693, "step": 4158 }, { "epoch": 0.12140938813638487, "grad_norm": 0.44930678606033325, "learning_rate": 9.986096840817297e-06, "loss": 0.2689, "step": 4159 }, { "epoch": 0.12143858010275572, "grad_norm": 0.4545186758041382, "learning_rate": 9.986058845770876e-06, "loss": 0.2148, "step": 4160 }, { "epoch": 0.12146777206912658, "grad_norm": 0.4135455787181854, "learning_rate": 9.986020798950648e-06, "loss": 0.2633, "step": 4161 }, { "epoch": 0.12149696403549744, "grad_norm": 0.6369903087615967, "learning_rate": 9.98598270035701e-06, "loss": 0.2842, "step": 4162 }, { "epoch": 0.12152615600186828, "grad_norm": 0.4063016176223755, "learning_rate": 9.985944549990357e-06, "loss": 0.2381, "step": 4163 }, { "epoch": 0.12155534796823914, "grad_norm": 0.39352136850357056, "learning_rate": 9.985906347851082e-06, "loss": 0.2547, "step": 4164 }, { "epoch": 0.12158453993460999, "grad_norm": 0.4278032183647156, "learning_rate": 9.985868093939585e-06, "loss": 0.2608, "step": 4165 }, { "epoch": 0.12161373190098085, "grad_norm": 0.4122917950153351, "learning_rate": 9.985829788256263e-06, "loss": 0.2284, "step": 4166 }, { "epoch": 0.1216429238673517, "grad_norm": 0.4417931139469147, "learning_rate": 9.985791430801511e-06, "loss": 0.2614, "step": 4167 }, { "epoch": 0.12167211583372256, "grad_norm": 0.39973920583724976, "learning_rate": 9.98575302157573e-06, "loss": 0.2316, "step": 4168 }, { "epoch": 0.12170130780009342, "grad_norm": 0.3831266462802887, "learning_rate": 9.98571456057932e-06, "loss": 0.243, "step": 4169 }, { "epoch": 0.12173049976646427, "grad_norm": 0.4106002151966095, "learning_rate": 9.985676047812678e-06, "loss": 0.2276, "step": 4170 }, { "epoch": 0.12175969173283513, "grad_norm": 0.43879061937332153, "learning_rate": 9.985637483276202e-06, "loss": 0.2402, "step": 4171 }, { "epoch": 0.12178888369920599, "grad_norm": 0.4002814292907715, "learning_rate": 9.985598866970298e-06, "loss": 0.2224, "step": 4172 }, { "epoch": 0.12181807566557683, "grad_norm": 0.42549052834510803, "learning_rate": 9.985560198895363e-06, "loss": 0.2347, "step": 4173 }, { "epoch": 0.12184726763194768, "grad_norm": 0.43753278255462646, "learning_rate": 9.9855214790518e-06, "loss": 0.2883, "step": 4174 }, { "epoch": 0.12187645959831854, "grad_norm": 0.4277642071247101, "learning_rate": 9.985482707440009e-06, "loss": 0.294, "step": 4175 }, { "epoch": 0.1219056515646894, "grad_norm": 0.3600499927997589, "learning_rate": 9.985443884060395e-06, "loss": 0.2664, "step": 4176 }, { "epoch": 0.12193484353106025, "grad_norm": 0.40779566764831543, "learning_rate": 9.98540500891336e-06, "loss": 0.2535, "step": 4177 }, { "epoch": 0.12196403549743111, "grad_norm": 0.5153986215591431, "learning_rate": 9.985366081999308e-06, "loss": 0.2794, "step": 4178 }, { "epoch": 0.12199322746380196, "grad_norm": 0.44043487310409546, "learning_rate": 9.985327103318642e-06, "loss": 0.2377, "step": 4179 }, { "epoch": 0.12202241943017282, "grad_norm": 0.35541293025016785, "learning_rate": 9.985288072871769e-06, "loss": 0.2122, "step": 4180 }, { "epoch": 0.12205161139654368, "grad_norm": 0.4113460183143616, "learning_rate": 9.985248990659093e-06, "loss": 0.2674, "step": 4181 }, { "epoch": 0.12208080336291452, "grad_norm": 0.4058769941329956, "learning_rate": 9.98520985668102e-06, "loss": 0.3327, "step": 4182 }, { "epoch": 0.12210999532928538, "grad_norm": 0.9303580522537231, "learning_rate": 9.985170670937955e-06, "loss": 0.2236, "step": 4183 }, { "epoch": 0.12213918729565623, "grad_norm": 0.5287530422210693, "learning_rate": 9.985131433430307e-06, "loss": 0.2694, "step": 4184 }, { "epoch": 0.12216837926202709, "grad_norm": 0.4927854537963867, "learning_rate": 9.985092144158484e-06, "loss": 0.2547, "step": 4185 }, { "epoch": 0.12219757122839794, "grad_norm": 0.4248034656047821, "learning_rate": 9.98505280312289e-06, "loss": 0.2847, "step": 4186 }, { "epoch": 0.1222267631947688, "grad_norm": 0.4269326329231262, "learning_rate": 9.985013410323938e-06, "loss": 0.2724, "step": 4187 }, { "epoch": 0.12225595516113966, "grad_norm": 0.49454349279403687, "learning_rate": 9.984973965762034e-06, "loss": 0.2667, "step": 4188 }, { "epoch": 0.12228514712751051, "grad_norm": 0.38572031259536743, "learning_rate": 9.984934469437589e-06, "loss": 0.252, "step": 4189 }, { "epoch": 0.12231433909388137, "grad_norm": 0.461245059967041, "learning_rate": 9.984894921351013e-06, "loss": 0.2873, "step": 4190 }, { "epoch": 0.12234353106025223, "grad_norm": 0.4195793569087982, "learning_rate": 9.984855321502717e-06, "loss": 0.1862, "step": 4191 }, { "epoch": 0.12237272302662307, "grad_norm": 0.6356202960014343, "learning_rate": 9.98481566989311e-06, "loss": 0.2576, "step": 4192 }, { "epoch": 0.12240191499299392, "grad_norm": 0.5037338137626648, "learning_rate": 9.984775966522607e-06, "loss": 0.2491, "step": 4193 }, { "epoch": 0.12243110695936478, "grad_norm": 0.6085221171379089, "learning_rate": 9.984736211391619e-06, "loss": 0.2636, "step": 4194 }, { "epoch": 0.12246029892573564, "grad_norm": 0.4240832030773163, "learning_rate": 9.984696404500557e-06, "loss": 0.259, "step": 4195 }, { "epoch": 0.12248949089210649, "grad_norm": 0.4359779357910156, "learning_rate": 9.984656545849836e-06, "loss": 0.2475, "step": 4196 }, { "epoch": 0.12251868285847735, "grad_norm": 0.38157615065574646, "learning_rate": 9.98461663543987e-06, "loss": 0.2939, "step": 4197 }, { "epoch": 0.1225478748248482, "grad_norm": 0.39299729466438293, "learning_rate": 9.984576673271074e-06, "loss": 0.2218, "step": 4198 }, { "epoch": 0.12257706679121906, "grad_norm": 0.44838789105415344, "learning_rate": 9.98453665934386e-06, "loss": 0.2728, "step": 4199 }, { "epoch": 0.12260625875758992, "grad_norm": 0.35561394691467285, "learning_rate": 9.984496593658648e-06, "loss": 0.2002, "step": 4200 }, { "epoch": 0.12263545072396076, "grad_norm": 0.42944201827049255, "learning_rate": 9.98445647621585e-06, "loss": 0.2656, "step": 4201 }, { "epoch": 0.12266464269033162, "grad_norm": 0.39601296186447144, "learning_rate": 9.984416307015885e-06, "loss": 0.2581, "step": 4202 }, { "epoch": 0.12269383465670247, "grad_norm": 0.39424633979797363, "learning_rate": 9.984376086059169e-06, "loss": 0.2, "step": 4203 }, { "epoch": 0.12272302662307333, "grad_norm": 0.39909127354621887, "learning_rate": 9.98433581334612e-06, "loss": 0.2784, "step": 4204 }, { "epoch": 0.12275221858944418, "grad_norm": 0.40346404910087585, "learning_rate": 9.984295488877156e-06, "loss": 0.2808, "step": 4205 }, { "epoch": 0.12278141055581504, "grad_norm": 0.45437175035476685, "learning_rate": 9.984255112652694e-06, "loss": 0.2275, "step": 4206 }, { "epoch": 0.1228106025221859, "grad_norm": 0.4089023768901825, "learning_rate": 9.984214684673157e-06, "loss": 0.229, "step": 4207 }, { "epoch": 0.12283979448855675, "grad_norm": 0.374577134847641, "learning_rate": 9.984174204938963e-06, "loss": 0.2363, "step": 4208 }, { "epoch": 0.12286898645492761, "grad_norm": 0.3737238943576813, "learning_rate": 9.984133673450531e-06, "loss": 0.2397, "step": 4209 }, { "epoch": 0.12289817842129847, "grad_norm": 0.3808799982070923, "learning_rate": 9.984093090208285e-06, "loss": 0.2189, "step": 4210 }, { "epoch": 0.12292737038766931, "grad_norm": 0.39618822932243347, "learning_rate": 9.984052455212643e-06, "loss": 0.2266, "step": 4211 }, { "epoch": 0.12295656235404016, "grad_norm": 0.4002831280231476, "learning_rate": 9.984011768464027e-06, "loss": 0.231, "step": 4212 }, { "epoch": 0.12298575432041102, "grad_norm": 0.3569035232067108, "learning_rate": 9.983971029962864e-06, "loss": 0.2226, "step": 4213 }, { "epoch": 0.12301494628678188, "grad_norm": 0.4679734408855438, "learning_rate": 9.983930239709572e-06, "loss": 0.2994, "step": 4214 }, { "epoch": 0.12304413825315273, "grad_norm": 0.5445477962493896, "learning_rate": 9.983889397704577e-06, "loss": 0.2729, "step": 4215 }, { "epoch": 0.12307333021952359, "grad_norm": 0.4267578423023224, "learning_rate": 9.983848503948302e-06, "loss": 0.2607, "step": 4216 }, { "epoch": 0.12310252218589444, "grad_norm": 0.4318603575229645, "learning_rate": 9.983807558441172e-06, "loss": 0.2149, "step": 4217 }, { "epoch": 0.1231317141522653, "grad_norm": 0.43489742279052734, "learning_rate": 9.983766561183613e-06, "loss": 0.272, "step": 4218 }, { "epoch": 0.12316090611863616, "grad_norm": 0.4355441927909851, "learning_rate": 9.98372551217605e-06, "loss": 0.2321, "step": 4219 }, { "epoch": 0.123190098085007, "grad_norm": 0.44890883564949036, "learning_rate": 9.98368441141891e-06, "loss": 0.305, "step": 4220 }, { "epoch": 0.12321929005137786, "grad_norm": 0.438382625579834, "learning_rate": 9.983643258912618e-06, "loss": 0.2397, "step": 4221 }, { "epoch": 0.12324848201774871, "grad_norm": 0.41922980546951294, "learning_rate": 9.983602054657602e-06, "loss": 0.2526, "step": 4222 }, { "epoch": 0.12327767398411957, "grad_norm": 0.5306196212768555, "learning_rate": 9.98356079865429e-06, "loss": 0.2827, "step": 4223 }, { "epoch": 0.12330686595049042, "grad_norm": 0.4558981955051422, "learning_rate": 9.983519490903114e-06, "loss": 0.2516, "step": 4224 }, { "epoch": 0.12333605791686128, "grad_norm": 0.4872758686542511, "learning_rate": 9.983478131404495e-06, "loss": 0.3016, "step": 4225 }, { "epoch": 0.12336524988323214, "grad_norm": 0.47023075819015503, "learning_rate": 9.98343672015887e-06, "loss": 0.24, "step": 4226 }, { "epoch": 0.12339444184960299, "grad_norm": 0.4161721467971802, "learning_rate": 9.983395257166663e-06, "loss": 0.2358, "step": 4227 }, { "epoch": 0.12342363381597385, "grad_norm": 0.4442063570022583, "learning_rate": 9.98335374242831e-06, "loss": 0.1996, "step": 4228 }, { "epoch": 0.1234528257823447, "grad_norm": 0.3981168866157532, "learning_rate": 9.98331217594424e-06, "loss": 0.2123, "step": 4229 }, { "epoch": 0.12348201774871555, "grad_norm": 0.43985599279403687, "learning_rate": 9.983270557714884e-06, "loss": 0.2502, "step": 4230 }, { "epoch": 0.1235112097150864, "grad_norm": 0.4913707971572876, "learning_rate": 9.983228887740673e-06, "loss": 0.3269, "step": 4231 }, { "epoch": 0.12354040168145726, "grad_norm": 0.5878499746322632, "learning_rate": 9.983187166022041e-06, "loss": 0.26, "step": 4232 }, { "epoch": 0.12356959364782812, "grad_norm": 0.7927348613739014, "learning_rate": 9.983145392559424e-06, "loss": 0.2831, "step": 4233 }, { "epoch": 0.12359878561419897, "grad_norm": 0.5267961025238037, "learning_rate": 9.98310356735325e-06, "loss": 0.2614, "step": 4234 }, { "epoch": 0.12362797758056983, "grad_norm": 0.44561704993247986, "learning_rate": 9.983061690403958e-06, "loss": 0.2686, "step": 4235 }, { "epoch": 0.12365716954694068, "grad_norm": 0.46564459800720215, "learning_rate": 9.98301976171198e-06, "loss": 0.2272, "step": 4236 }, { "epoch": 0.12368636151331154, "grad_norm": 0.8836482763290405, "learning_rate": 9.982977781277754e-06, "loss": 0.2379, "step": 4237 }, { "epoch": 0.1237155534796824, "grad_norm": 0.44539380073547363, "learning_rate": 9.982935749101715e-06, "loss": 0.2555, "step": 4238 }, { "epoch": 0.12374474544605324, "grad_norm": 0.5437080264091492, "learning_rate": 9.982893665184297e-06, "loss": 0.2457, "step": 4239 }, { "epoch": 0.1237739374124241, "grad_norm": 0.47335365414619446, "learning_rate": 9.982851529525938e-06, "loss": 0.2532, "step": 4240 }, { "epoch": 0.12380312937879495, "grad_norm": 0.5325204133987427, "learning_rate": 9.98280934212708e-06, "loss": 0.2684, "step": 4241 }, { "epoch": 0.12383232134516581, "grad_norm": 0.44308435916900635, "learning_rate": 9.982767102988156e-06, "loss": 0.2227, "step": 4242 }, { "epoch": 0.12386151331153666, "grad_norm": 0.5309776067733765, "learning_rate": 9.982724812109605e-06, "loss": 0.2484, "step": 4243 }, { "epoch": 0.12389070527790752, "grad_norm": 0.4794602692127228, "learning_rate": 9.98268246949187e-06, "loss": 0.29, "step": 4244 }, { "epoch": 0.12391989724427838, "grad_norm": 0.4473034739494324, "learning_rate": 9.982640075135384e-06, "loss": 0.2177, "step": 4245 }, { "epoch": 0.12394908921064923, "grad_norm": 0.7211771011352539, "learning_rate": 9.982597629040594e-06, "loss": 0.2592, "step": 4246 }, { "epoch": 0.12397828117702009, "grad_norm": 0.4361681640148163, "learning_rate": 9.982555131207936e-06, "loss": 0.2217, "step": 4247 }, { "epoch": 0.12400747314339094, "grad_norm": 0.4720495343208313, "learning_rate": 9.982512581637856e-06, "loss": 0.2822, "step": 4248 }, { "epoch": 0.12403666510976179, "grad_norm": 0.4311751425266266, "learning_rate": 9.982469980330791e-06, "loss": 0.2597, "step": 4249 }, { "epoch": 0.12406585707613264, "grad_norm": 0.41230645775794983, "learning_rate": 9.982427327287185e-06, "loss": 0.2377, "step": 4250 }, { "epoch": 0.1240950490425035, "grad_norm": 0.423096239566803, "learning_rate": 9.982384622507482e-06, "loss": 0.2739, "step": 4251 }, { "epoch": 0.12412424100887436, "grad_norm": 0.3808162808418274, "learning_rate": 9.982341865992124e-06, "loss": 0.2267, "step": 4252 }, { "epoch": 0.12415343297524521, "grad_norm": 0.4572027027606964, "learning_rate": 9.982299057741557e-06, "loss": 0.221, "step": 4253 }, { "epoch": 0.12418262494161607, "grad_norm": 0.4052355885505676, "learning_rate": 9.982256197756224e-06, "loss": 0.2137, "step": 4254 }, { "epoch": 0.12421181690798692, "grad_norm": 0.4366466999053955, "learning_rate": 9.982213286036568e-06, "loss": 0.2262, "step": 4255 }, { "epoch": 0.12424100887435778, "grad_norm": 0.47376003861427307, "learning_rate": 9.98217032258304e-06, "loss": 0.2145, "step": 4256 }, { "epoch": 0.12427020084072864, "grad_norm": 0.3705553114414215, "learning_rate": 9.98212730739608e-06, "loss": 0.2734, "step": 4257 }, { "epoch": 0.12429939280709949, "grad_norm": 0.5947606563568115, "learning_rate": 9.98208424047614e-06, "loss": 0.2742, "step": 4258 }, { "epoch": 0.12432858477347034, "grad_norm": 0.6730558276176453, "learning_rate": 9.982041121823664e-06, "loss": 0.2352, "step": 4259 }, { "epoch": 0.12435777673984119, "grad_norm": 0.46056368947029114, "learning_rate": 9.9819979514391e-06, "loss": 0.2373, "step": 4260 }, { "epoch": 0.12438696870621205, "grad_norm": 0.43497493863105774, "learning_rate": 9.981954729322897e-06, "loss": 0.2649, "step": 4261 }, { "epoch": 0.1244161606725829, "grad_norm": 0.4541893005371094, "learning_rate": 9.981911455475503e-06, "loss": 0.2133, "step": 4262 }, { "epoch": 0.12444535263895376, "grad_norm": 0.4585287272930145, "learning_rate": 9.981868129897369e-06, "loss": 0.2296, "step": 4263 }, { "epoch": 0.12447454460532462, "grad_norm": 0.48740196228027344, "learning_rate": 9.981824752588942e-06, "loss": 0.2697, "step": 4264 }, { "epoch": 0.12450373657169547, "grad_norm": 0.4973118305206299, "learning_rate": 9.981781323550676e-06, "loss": 0.2065, "step": 4265 }, { "epoch": 0.12453292853806633, "grad_norm": 0.5542885661125183, "learning_rate": 9.98173784278302e-06, "loss": 0.2435, "step": 4266 }, { "epoch": 0.12456212050443718, "grad_norm": 0.43699556589126587, "learning_rate": 9.981694310286425e-06, "loss": 0.3361, "step": 4267 }, { "epoch": 0.12459131247080803, "grad_norm": 0.5898782014846802, "learning_rate": 9.981650726061345e-06, "loss": 0.3058, "step": 4268 }, { "epoch": 0.12462050443717888, "grad_norm": 0.4292990565299988, "learning_rate": 9.98160709010823e-06, "loss": 0.2594, "step": 4269 }, { "epoch": 0.12464969640354974, "grad_norm": 0.5205754041671753, "learning_rate": 9.981563402427535e-06, "loss": 0.2467, "step": 4270 }, { "epoch": 0.1246788883699206, "grad_norm": 0.42471757531166077, "learning_rate": 9.981519663019711e-06, "loss": 0.2597, "step": 4271 }, { "epoch": 0.12470808033629145, "grad_norm": 0.4463109076023102, "learning_rate": 9.981475871885218e-06, "loss": 0.1927, "step": 4272 }, { "epoch": 0.12473727230266231, "grad_norm": 0.6134469509124756, "learning_rate": 9.981432029024504e-06, "loss": 0.2711, "step": 4273 }, { "epoch": 0.12476646426903316, "grad_norm": 0.4236753582954407, "learning_rate": 9.981388134438028e-06, "loss": 0.2559, "step": 4274 }, { "epoch": 0.12479565623540402, "grad_norm": 0.4680642783641815, "learning_rate": 9.981344188126245e-06, "loss": 0.2472, "step": 4275 }, { "epoch": 0.12482484820177488, "grad_norm": 0.41362127661705017, "learning_rate": 9.981300190089612e-06, "loss": 0.2262, "step": 4276 }, { "epoch": 0.12485404016814573, "grad_norm": 0.4624929130077362, "learning_rate": 9.981256140328584e-06, "loss": 0.3252, "step": 4277 }, { "epoch": 0.12488323213451658, "grad_norm": 0.4583200216293335, "learning_rate": 9.981212038843618e-06, "loss": 0.2499, "step": 4278 }, { "epoch": 0.12491242410088743, "grad_norm": 0.3788171708583832, "learning_rate": 9.981167885635176e-06, "loss": 0.2553, "step": 4279 }, { "epoch": 0.12494161606725829, "grad_norm": 0.5090329647064209, "learning_rate": 9.981123680703713e-06, "loss": 0.2402, "step": 4280 }, { "epoch": 0.12497080803362914, "grad_norm": 0.4943747818470001, "learning_rate": 9.981079424049689e-06, "loss": 0.2361, "step": 4281 }, { "epoch": 0.125, "grad_norm": 0.38438862562179565, "learning_rate": 9.981035115673563e-06, "loss": 0.226, "step": 4282 }, { "epoch": 0.12502919196637086, "grad_norm": 0.4442427456378937, "learning_rate": 9.980990755575797e-06, "loss": 0.2647, "step": 4283 }, { "epoch": 0.1250583839327417, "grad_norm": 0.5915377140045166, "learning_rate": 9.98094634375685e-06, "loss": 0.3226, "step": 4284 }, { "epoch": 0.12508757589911257, "grad_norm": 0.44750288128852844, "learning_rate": 9.980901880217181e-06, "loss": 0.2429, "step": 4285 }, { "epoch": 0.12511676786548342, "grad_norm": 0.4578176736831665, "learning_rate": 9.980857364957258e-06, "loss": 0.2459, "step": 4286 }, { "epoch": 0.12514595983185428, "grad_norm": 0.4279147982597351, "learning_rate": 9.980812797977536e-06, "loss": 0.2078, "step": 4287 }, { "epoch": 0.12517515179822514, "grad_norm": 0.45284175872802734, "learning_rate": 9.98076817927848e-06, "loss": 0.2545, "step": 4288 }, { "epoch": 0.125204343764596, "grad_norm": 0.42754682898521423, "learning_rate": 9.98072350886056e-06, "loss": 0.2736, "step": 4289 }, { "epoch": 0.12523353573096685, "grad_norm": 0.4339739978313446, "learning_rate": 9.98067878672423e-06, "loss": 0.2297, "step": 4290 }, { "epoch": 0.1252627276973377, "grad_norm": 0.4334447681903839, "learning_rate": 9.980634012869958e-06, "loss": 0.269, "step": 4291 }, { "epoch": 0.12529191966370853, "grad_norm": 0.37390533089637756, "learning_rate": 9.980589187298211e-06, "loss": 0.2054, "step": 4292 }, { "epoch": 0.1253211116300794, "grad_norm": 0.47446173429489136, "learning_rate": 9.980544310009453e-06, "loss": 0.2757, "step": 4293 }, { "epoch": 0.12535030359645025, "grad_norm": 0.43708497285842896, "learning_rate": 9.98049938100415e-06, "loss": 0.2764, "step": 4294 }, { "epoch": 0.1253794955628211, "grad_norm": 0.5359368324279785, "learning_rate": 9.98045440028277e-06, "loss": 0.2631, "step": 4295 }, { "epoch": 0.12540868752919196, "grad_norm": 0.43552854657173157, "learning_rate": 9.980409367845775e-06, "loss": 0.2164, "step": 4296 }, { "epoch": 0.12543787949556282, "grad_norm": 0.35794055461883545, "learning_rate": 9.980364283693638e-06, "loss": 0.1809, "step": 4297 }, { "epoch": 0.12546707146193367, "grad_norm": 0.4629276394844055, "learning_rate": 9.980319147826826e-06, "loss": 0.3024, "step": 4298 }, { "epoch": 0.12549626342830453, "grad_norm": 0.4447159767150879, "learning_rate": 9.980273960245805e-06, "loss": 0.3018, "step": 4299 }, { "epoch": 0.12552545539467538, "grad_norm": 0.4533510208129883, "learning_rate": 9.98022872095105e-06, "loss": 0.2473, "step": 4300 }, { "epoch": 0.12555464736104624, "grad_norm": 0.35239994525909424, "learning_rate": 9.980183429943023e-06, "loss": 0.2643, "step": 4301 }, { "epoch": 0.1255838393274171, "grad_norm": 0.3868016004562378, "learning_rate": 9.9801380872222e-06, "loss": 0.227, "step": 4302 }, { "epoch": 0.12561303129378795, "grad_norm": 1.0026171207427979, "learning_rate": 9.98009269278905e-06, "loss": 0.256, "step": 4303 }, { "epoch": 0.1256422232601588, "grad_norm": 0.4051210880279541, "learning_rate": 9.980047246644044e-06, "loss": 0.2413, "step": 4304 }, { "epoch": 0.12567141522652966, "grad_norm": 0.4221077561378479, "learning_rate": 9.980001748787656e-06, "loss": 0.2391, "step": 4305 }, { "epoch": 0.12570060719290052, "grad_norm": 0.516754686832428, "learning_rate": 9.979956199220354e-06, "loss": 0.2496, "step": 4306 }, { "epoch": 0.12572979915927138, "grad_norm": 0.4361283481121063, "learning_rate": 9.979910597942614e-06, "loss": 0.2252, "step": 4307 }, { "epoch": 0.12575899112564223, "grad_norm": 0.732230544090271, "learning_rate": 9.979864944954912e-06, "loss": 0.28, "step": 4308 }, { "epoch": 0.1257881830920131, "grad_norm": 0.3818286657333374, "learning_rate": 9.979819240257718e-06, "loss": 0.2218, "step": 4309 }, { "epoch": 0.12581737505838395, "grad_norm": 0.4217211902141571, "learning_rate": 9.979773483851506e-06, "loss": 0.2088, "step": 4310 }, { "epoch": 0.12584656702475477, "grad_norm": 0.45823076367378235, "learning_rate": 9.979727675736755e-06, "loss": 0.2592, "step": 4311 }, { "epoch": 0.12587575899112563, "grad_norm": 0.5309080481529236, "learning_rate": 9.97968181591394e-06, "loss": 0.271, "step": 4312 }, { "epoch": 0.1259049509574965, "grad_norm": 0.3753475844860077, "learning_rate": 9.979635904383533e-06, "loss": 0.2401, "step": 4313 }, { "epoch": 0.12593414292386734, "grad_norm": 0.3751346170902252, "learning_rate": 9.979589941146014e-06, "loss": 0.2364, "step": 4314 }, { "epoch": 0.1259633348902382, "grad_norm": 0.4239434003829956, "learning_rate": 9.97954392620186e-06, "loss": 0.3002, "step": 4315 }, { "epoch": 0.12599252685660906, "grad_norm": 0.400684118270874, "learning_rate": 9.97949785955155e-06, "loss": 0.2509, "step": 4316 }, { "epoch": 0.1260217188229799, "grad_norm": 0.4042419493198395, "learning_rate": 9.97945174119556e-06, "loss": 0.2047, "step": 4317 }, { "epoch": 0.12605091078935077, "grad_norm": 0.5725687742233276, "learning_rate": 9.97940557113437e-06, "loss": 0.2511, "step": 4318 }, { "epoch": 0.12608010275572162, "grad_norm": 0.4761427044868469, "learning_rate": 9.979359349368459e-06, "loss": 0.2977, "step": 4319 }, { "epoch": 0.12610929472209248, "grad_norm": 0.5189542770385742, "learning_rate": 9.979313075898308e-06, "loss": 0.2681, "step": 4320 }, { "epoch": 0.12613848668846334, "grad_norm": 0.4400547444820404, "learning_rate": 9.979266750724396e-06, "loss": 0.221, "step": 4321 }, { "epoch": 0.1261676786548342, "grad_norm": 0.3760754466056824, "learning_rate": 9.979220373847204e-06, "loss": 0.2247, "step": 4322 }, { "epoch": 0.12619687062120505, "grad_norm": 0.4314767122268677, "learning_rate": 9.979173945267218e-06, "loss": 0.2942, "step": 4323 }, { "epoch": 0.1262260625875759, "grad_norm": 0.49608445167541504, "learning_rate": 9.979127464984913e-06, "loss": 0.2773, "step": 4324 }, { "epoch": 0.12625525455394676, "grad_norm": 0.40806201100349426, "learning_rate": 9.979080933000775e-06, "loss": 0.2422, "step": 4325 }, { "epoch": 0.12628444652031762, "grad_norm": 0.4241520166397095, "learning_rate": 9.97903434931529e-06, "loss": 0.2834, "step": 4326 }, { "epoch": 0.12631363848668847, "grad_norm": 0.45400482416152954, "learning_rate": 9.978987713928936e-06, "loss": 0.3067, "step": 4327 }, { "epoch": 0.12634283045305933, "grad_norm": 0.40165165066719055, "learning_rate": 9.978941026842202e-06, "loss": 0.2671, "step": 4328 }, { "epoch": 0.12637202241943019, "grad_norm": 0.3882552683353424, "learning_rate": 9.97889428805557e-06, "loss": 0.258, "step": 4329 }, { "epoch": 0.12640121438580101, "grad_norm": 0.4450799822807312, "learning_rate": 9.978847497569529e-06, "loss": 0.2822, "step": 4330 }, { "epoch": 0.12643040635217187, "grad_norm": 0.38736993074417114, "learning_rate": 9.978800655384558e-06, "loss": 0.2444, "step": 4331 }, { "epoch": 0.12645959831854273, "grad_norm": 0.3996959626674652, "learning_rate": 9.978753761501149e-06, "loss": 0.2571, "step": 4332 }, { "epoch": 0.12648879028491358, "grad_norm": 0.4708392024040222, "learning_rate": 9.97870681591979e-06, "loss": 0.2787, "step": 4333 }, { "epoch": 0.12651798225128444, "grad_norm": 0.43665313720703125, "learning_rate": 9.978659818640963e-06, "loss": 0.242, "step": 4334 }, { "epoch": 0.1265471742176553, "grad_norm": 0.4534323811531067, "learning_rate": 9.97861276966516e-06, "loss": 0.2807, "step": 4335 }, { "epoch": 0.12657636618402615, "grad_norm": 0.4530999958515167, "learning_rate": 9.978565668992868e-06, "loss": 0.2758, "step": 4336 }, { "epoch": 0.126605558150397, "grad_norm": 0.4494663178920746, "learning_rate": 9.978518516624578e-06, "loss": 0.2276, "step": 4337 }, { "epoch": 0.12663475011676786, "grad_norm": 0.3801528215408325, "learning_rate": 9.978471312560779e-06, "loss": 0.2526, "step": 4338 }, { "epoch": 0.12666394208313872, "grad_norm": 0.4129658043384552, "learning_rate": 9.978424056801956e-06, "loss": 0.2738, "step": 4339 }, { "epoch": 0.12669313404950958, "grad_norm": 0.37606409192085266, "learning_rate": 9.978376749348609e-06, "loss": 0.2113, "step": 4340 }, { "epoch": 0.12672232601588043, "grad_norm": 0.4370483160018921, "learning_rate": 9.978329390201221e-06, "loss": 0.2668, "step": 4341 }, { "epoch": 0.1267515179822513, "grad_norm": 0.42230746150016785, "learning_rate": 9.978281979360289e-06, "loss": 0.2342, "step": 4342 }, { "epoch": 0.12678070994862214, "grad_norm": 0.36419886350631714, "learning_rate": 9.978234516826303e-06, "loss": 0.2409, "step": 4343 }, { "epoch": 0.126809901914993, "grad_norm": 0.4431465268135071, "learning_rate": 9.978187002599756e-06, "loss": 0.2601, "step": 4344 }, { "epoch": 0.12683909388136386, "grad_norm": 0.5656706690788269, "learning_rate": 9.97813943668114e-06, "loss": 0.2841, "step": 4345 }, { "epoch": 0.1268682858477347, "grad_norm": 0.3880535662174225, "learning_rate": 9.978091819070952e-06, "loss": 0.2824, "step": 4346 }, { "epoch": 0.12689747781410557, "grad_norm": 0.38251993060112, "learning_rate": 9.978044149769684e-06, "loss": 0.2074, "step": 4347 }, { "epoch": 0.12692666978047643, "grad_norm": 0.48402678966522217, "learning_rate": 9.977996428777833e-06, "loss": 0.2596, "step": 4348 }, { "epoch": 0.12695586174684725, "grad_norm": 0.42874181270599365, "learning_rate": 9.977948656095893e-06, "loss": 0.2447, "step": 4349 }, { "epoch": 0.1269850537132181, "grad_norm": 0.45371875166893005, "learning_rate": 9.977900831724361e-06, "loss": 0.2162, "step": 4350 }, { "epoch": 0.12701424567958897, "grad_norm": 0.4743434488773346, "learning_rate": 9.977852955663732e-06, "loss": 0.3134, "step": 4351 }, { "epoch": 0.12704343764595982, "grad_norm": 0.40733346343040466, "learning_rate": 9.977805027914506e-06, "loss": 0.2478, "step": 4352 }, { "epoch": 0.12707262961233068, "grad_norm": 0.3658022880554199, "learning_rate": 9.977757048477176e-06, "loss": 0.1944, "step": 4353 }, { "epoch": 0.12710182157870153, "grad_norm": 0.49626410007476807, "learning_rate": 9.977709017352246e-06, "loss": 0.2491, "step": 4354 }, { "epoch": 0.1271310135450724, "grad_norm": 0.37214574217796326, "learning_rate": 9.97766093454021e-06, "loss": 0.2264, "step": 4355 }, { "epoch": 0.12716020551144325, "grad_norm": 0.3967636227607727, "learning_rate": 9.97761280004157e-06, "loss": 0.277, "step": 4356 }, { "epoch": 0.1271893974778141, "grad_norm": 0.4230053722858429, "learning_rate": 9.977564613856826e-06, "loss": 0.2597, "step": 4357 }, { "epoch": 0.12721858944418496, "grad_norm": 0.35673755407333374, "learning_rate": 9.977516375986476e-06, "loss": 0.2276, "step": 4358 }, { "epoch": 0.12724778141055582, "grad_norm": 0.5203045010566711, "learning_rate": 9.977468086431021e-06, "loss": 0.2854, "step": 4359 }, { "epoch": 0.12727697337692667, "grad_norm": 0.36009663343429565, "learning_rate": 9.977419745190966e-06, "loss": 0.2392, "step": 4360 }, { "epoch": 0.12730616534329753, "grad_norm": 0.4664439558982849, "learning_rate": 9.97737135226681e-06, "loss": 0.2394, "step": 4361 }, { "epoch": 0.12733535730966838, "grad_norm": 0.3983575403690338, "learning_rate": 9.977322907659055e-06, "loss": 0.2227, "step": 4362 }, { "epoch": 0.12736454927603924, "grad_norm": 0.5041612982749939, "learning_rate": 9.977274411368206e-06, "loss": 0.2067, "step": 4363 }, { "epoch": 0.1273937412424101, "grad_norm": 0.45182281732559204, "learning_rate": 9.977225863394764e-06, "loss": 0.2752, "step": 4364 }, { "epoch": 0.12742293320878095, "grad_norm": 0.3796033561229706, "learning_rate": 9.977177263739235e-06, "loss": 0.2257, "step": 4365 }, { "epoch": 0.1274521251751518, "grad_norm": 0.33859768509864807, "learning_rate": 9.977128612402125e-06, "loss": 0.205, "step": 4366 }, { "epoch": 0.12748131714152267, "grad_norm": 0.3746010661125183, "learning_rate": 9.977079909383938e-06, "loss": 0.2222, "step": 4367 }, { "epoch": 0.12751050910789352, "grad_norm": 0.43809202313423157, "learning_rate": 9.977031154685176e-06, "loss": 0.2534, "step": 4368 }, { "epoch": 0.12753970107426435, "grad_norm": 0.9044849276542664, "learning_rate": 9.976982348306352e-06, "loss": 0.2732, "step": 4369 }, { "epoch": 0.1275688930406352, "grad_norm": 0.40806594491004944, "learning_rate": 9.976933490247968e-06, "loss": 0.2416, "step": 4370 }, { "epoch": 0.12759808500700606, "grad_norm": 0.43852075934410095, "learning_rate": 9.976884580510533e-06, "loss": 0.2448, "step": 4371 }, { "epoch": 0.12762727697337692, "grad_norm": 0.4007963538169861, "learning_rate": 9.976835619094553e-06, "loss": 0.2279, "step": 4372 }, { "epoch": 0.12765646893974777, "grad_norm": 0.3513282835483551, "learning_rate": 9.976786606000541e-06, "loss": 0.2012, "step": 4373 }, { "epoch": 0.12768566090611863, "grad_norm": 0.4194505214691162, "learning_rate": 9.976737541229002e-06, "loss": 0.2838, "step": 4374 }, { "epoch": 0.1277148528724895, "grad_norm": 0.38300246000289917, "learning_rate": 9.976688424780444e-06, "loss": 0.2673, "step": 4375 }, { "epoch": 0.12774404483886034, "grad_norm": 0.3867543637752533, "learning_rate": 9.976639256655381e-06, "loss": 0.2516, "step": 4376 }, { "epoch": 0.1277732368052312, "grad_norm": 0.44740161299705505, "learning_rate": 9.976590036854324e-06, "loss": 0.2757, "step": 4377 }, { "epoch": 0.12780242877160206, "grad_norm": 0.5643367767333984, "learning_rate": 9.976540765377778e-06, "loss": 0.2531, "step": 4378 }, { "epoch": 0.1278316207379729, "grad_norm": 0.46822237968444824, "learning_rate": 9.976491442226261e-06, "loss": 0.2465, "step": 4379 }, { "epoch": 0.12786081270434377, "grad_norm": 0.43990567326545715, "learning_rate": 9.976442067400283e-06, "loss": 0.2858, "step": 4380 }, { "epoch": 0.12789000467071462, "grad_norm": 0.6306549310684204, "learning_rate": 9.976392640900356e-06, "loss": 0.3689, "step": 4381 }, { "epoch": 0.12791919663708548, "grad_norm": 0.6276222467422485, "learning_rate": 9.976343162726992e-06, "loss": 0.3119, "step": 4382 }, { "epoch": 0.12794838860345634, "grad_norm": 0.47469860315322876, "learning_rate": 9.97629363288071e-06, "loss": 0.3037, "step": 4383 }, { "epoch": 0.1279775805698272, "grad_norm": 0.47534558176994324, "learning_rate": 9.976244051362018e-06, "loss": 0.3061, "step": 4384 }, { "epoch": 0.12800677253619805, "grad_norm": 0.3509116768836975, "learning_rate": 9.976194418171435e-06, "loss": 0.2026, "step": 4385 }, { "epoch": 0.1280359645025689, "grad_norm": 0.44923174381256104, "learning_rate": 9.976144733309473e-06, "loss": 0.2954, "step": 4386 }, { "epoch": 0.12806515646893976, "grad_norm": 0.3826487362384796, "learning_rate": 9.97609499677665e-06, "loss": 0.2522, "step": 4387 }, { "epoch": 0.1280943484353106, "grad_norm": 0.5367785692214966, "learning_rate": 9.976045208573485e-06, "loss": 0.2642, "step": 4388 }, { "epoch": 0.12812354040168145, "grad_norm": 0.3979142904281616, "learning_rate": 9.975995368700491e-06, "loss": 0.2665, "step": 4389 }, { "epoch": 0.1281527323680523, "grad_norm": 0.37093600630760193, "learning_rate": 9.975945477158186e-06, "loss": 0.2152, "step": 4390 }, { "epoch": 0.12818192433442316, "grad_norm": 0.36264050006866455, "learning_rate": 9.975895533947092e-06, "loss": 0.2308, "step": 4391 }, { "epoch": 0.12821111630079401, "grad_norm": 0.37525323033332825, "learning_rate": 9.97584553906772e-06, "loss": 0.2849, "step": 4392 }, { "epoch": 0.12824030826716487, "grad_norm": 0.4517882764339447, "learning_rate": 9.975795492520597e-06, "loss": 0.2716, "step": 4393 }, { "epoch": 0.12826950023353573, "grad_norm": 0.39690065383911133, "learning_rate": 9.975745394306237e-06, "loss": 0.2622, "step": 4394 }, { "epoch": 0.12829869219990658, "grad_norm": 0.43988093733787537, "learning_rate": 9.975695244425165e-06, "loss": 0.2414, "step": 4395 }, { "epoch": 0.12832788416627744, "grad_norm": 0.4700261354446411, "learning_rate": 9.975645042877898e-06, "loss": 0.2474, "step": 4396 }, { "epoch": 0.1283570761326483, "grad_norm": 0.44652023911476135, "learning_rate": 9.97559478966496e-06, "loss": 0.2315, "step": 4397 }, { "epoch": 0.12838626809901915, "grad_norm": 0.4678152799606323, "learning_rate": 9.97554448478687e-06, "loss": 0.2381, "step": 4398 }, { "epoch": 0.12841546006539, "grad_norm": 0.45544832944869995, "learning_rate": 9.97549412824415e-06, "loss": 0.2415, "step": 4399 }, { "epoch": 0.12844465203176086, "grad_norm": 1.8785324096679688, "learning_rate": 9.975443720037328e-06, "loss": 0.2199, "step": 4400 }, { "epoch": 0.12847384399813172, "grad_norm": 0.5161322951316833, "learning_rate": 9.97539326016692e-06, "loss": 0.2405, "step": 4401 }, { "epoch": 0.12850303596450258, "grad_norm": 0.46850356459617615, "learning_rate": 9.97534274863346e-06, "loss": 0.3155, "step": 4402 }, { "epoch": 0.12853222793087343, "grad_norm": 0.4180794656276703, "learning_rate": 9.975292185437461e-06, "loss": 0.2865, "step": 4403 }, { "epoch": 0.1285614198972443, "grad_norm": 0.61322021484375, "learning_rate": 9.975241570579455e-06, "loss": 0.254, "step": 4404 }, { "epoch": 0.12859061186361515, "grad_norm": 0.4745141565799713, "learning_rate": 9.975190904059967e-06, "loss": 0.2483, "step": 4405 }, { "epoch": 0.128619803829986, "grad_norm": 0.35384708642959595, "learning_rate": 9.975140185879522e-06, "loss": 0.1998, "step": 4406 }, { "epoch": 0.12864899579635683, "grad_norm": 0.34107744693756104, "learning_rate": 9.975089416038645e-06, "loss": 0.1911, "step": 4407 }, { "epoch": 0.12867818776272769, "grad_norm": 0.4109858572483063, "learning_rate": 9.975038594537868e-06, "loss": 0.2459, "step": 4408 }, { "epoch": 0.12870737972909854, "grad_norm": 0.4057052731513977, "learning_rate": 9.974987721377713e-06, "loss": 0.2766, "step": 4409 }, { "epoch": 0.1287365716954694, "grad_norm": 0.39016252756118774, "learning_rate": 9.974936796558715e-06, "loss": 0.2751, "step": 4410 }, { "epoch": 0.12876576366184025, "grad_norm": 0.3625458776950836, "learning_rate": 9.974885820081395e-06, "loss": 0.2302, "step": 4411 }, { "epoch": 0.1287949556282111, "grad_norm": 0.49016836285591125, "learning_rate": 9.974834791946286e-06, "loss": 0.3211, "step": 4412 }, { "epoch": 0.12882414759458197, "grad_norm": 0.5337784290313721, "learning_rate": 9.97478371215392e-06, "loss": 0.248, "step": 4413 }, { "epoch": 0.12885333956095282, "grad_norm": 0.36554259061813354, "learning_rate": 9.974732580704825e-06, "loss": 0.225, "step": 4414 }, { "epoch": 0.12888253152732368, "grad_norm": 0.32226133346557617, "learning_rate": 9.974681397599531e-06, "loss": 0.1852, "step": 4415 }, { "epoch": 0.12891172349369454, "grad_norm": 0.3957211375236511, "learning_rate": 9.974630162838572e-06, "loss": 0.238, "step": 4416 }, { "epoch": 0.1289409154600654, "grad_norm": 0.3993585407733917, "learning_rate": 9.974578876422479e-06, "loss": 0.2544, "step": 4417 }, { "epoch": 0.12897010742643625, "grad_norm": 0.432648241519928, "learning_rate": 9.974527538351784e-06, "loss": 0.2613, "step": 4418 }, { "epoch": 0.1289992993928071, "grad_norm": 0.5205774903297424, "learning_rate": 9.97447614862702e-06, "loss": 0.2727, "step": 4419 }, { "epoch": 0.12902849135917796, "grad_norm": 0.41331031918525696, "learning_rate": 9.97442470724872e-06, "loss": 0.2464, "step": 4420 }, { "epoch": 0.12905768332554882, "grad_norm": 0.4185827076435089, "learning_rate": 9.974373214217421e-06, "loss": 0.3012, "step": 4421 }, { "epoch": 0.12908687529191967, "grad_norm": 0.4223922789096832, "learning_rate": 9.974321669533655e-06, "loss": 0.2319, "step": 4422 }, { "epoch": 0.12911606725829053, "grad_norm": 0.41064155101776123, "learning_rate": 9.974270073197958e-06, "loss": 0.2116, "step": 4423 }, { "epoch": 0.12914525922466139, "grad_norm": 0.4114338755607605, "learning_rate": 9.974218425210866e-06, "loss": 0.2315, "step": 4424 }, { "epoch": 0.12917445119103224, "grad_norm": 0.4249192476272583, "learning_rate": 9.974166725572916e-06, "loss": 0.2749, "step": 4425 }, { "epoch": 0.12920364315740307, "grad_norm": 0.40124258399009705, "learning_rate": 9.974114974284643e-06, "loss": 0.2554, "step": 4426 }, { "epoch": 0.12923283512377393, "grad_norm": 0.4101465940475464, "learning_rate": 9.974063171346585e-06, "loss": 0.2582, "step": 4427 }, { "epoch": 0.12926202709014478, "grad_norm": 0.425167441368103, "learning_rate": 9.974011316759282e-06, "loss": 0.2362, "step": 4428 }, { "epoch": 0.12929121905651564, "grad_norm": 0.39751288294792175, "learning_rate": 9.973959410523269e-06, "loss": 0.236, "step": 4429 }, { "epoch": 0.1293204110228865, "grad_norm": 0.42195355892181396, "learning_rate": 9.973907452639086e-06, "loss": 0.2614, "step": 4430 }, { "epoch": 0.12934960298925735, "grad_norm": 0.4190908968448639, "learning_rate": 9.973855443107275e-06, "loss": 0.2725, "step": 4431 }, { "epoch": 0.1293787949556282, "grad_norm": 0.35474032163619995, "learning_rate": 9.973803381928373e-06, "loss": 0.2291, "step": 4432 }, { "epoch": 0.12940798692199906, "grad_norm": 0.4818907380104065, "learning_rate": 9.973751269102923e-06, "loss": 0.2605, "step": 4433 }, { "epoch": 0.12943717888836992, "grad_norm": 0.3835720717906952, "learning_rate": 9.973699104631464e-06, "loss": 0.2374, "step": 4434 }, { "epoch": 0.12946637085474078, "grad_norm": 0.6106879115104675, "learning_rate": 9.97364688851454e-06, "loss": 0.2381, "step": 4435 }, { "epoch": 0.12949556282111163, "grad_norm": 0.3923720717430115, "learning_rate": 9.97359462075269e-06, "loss": 0.2834, "step": 4436 }, { "epoch": 0.1295247547874825, "grad_norm": 0.6086568832397461, "learning_rate": 9.973542301346459e-06, "loss": 0.2744, "step": 4437 }, { "epoch": 0.12955394675385334, "grad_norm": 0.3856770992279053, "learning_rate": 9.973489930296391e-06, "loss": 0.2511, "step": 4438 }, { "epoch": 0.1295831387202242, "grad_norm": 0.3451370894908905, "learning_rate": 9.973437507603028e-06, "loss": 0.2442, "step": 4439 }, { "epoch": 0.12961233068659506, "grad_norm": 0.4257568120956421, "learning_rate": 9.973385033266915e-06, "loss": 0.2899, "step": 4440 }, { "epoch": 0.1296415226529659, "grad_norm": 0.4029482305049896, "learning_rate": 9.973332507288597e-06, "loss": 0.2838, "step": 4441 }, { "epoch": 0.12967071461933677, "grad_norm": 0.4660026431083679, "learning_rate": 9.973279929668618e-06, "loss": 0.2669, "step": 4442 }, { "epoch": 0.12969990658570762, "grad_norm": 0.46575817465782166, "learning_rate": 9.973227300407526e-06, "loss": 0.3072, "step": 4443 }, { "epoch": 0.12972909855207848, "grad_norm": 0.3754696249961853, "learning_rate": 9.973174619505868e-06, "loss": 0.2169, "step": 4444 }, { "epoch": 0.1297582905184493, "grad_norm": 0.4318040907382965, "learning_rate": 9.973121886964188e-06, "loss": 0.2213, "step": 4445 }, { "epoch": 0.12978748248482017, "grad_norm": 0.49416661262512207, "learning_rate": 9.973069102783035e-06, "loss": 0.2977, "step": 4446 }, { "epoch": 0.12981667445119102, "grad_norm": 0.4207712709903717, "learning_rate": 9.973016266962958e-06, "loss": 0.2661, "step": 4447 }, { "epoch": 0.12984586641756188, "grad_norm": 0.46736815571784973, "learning_rate": 9.972963379504506e-06, "loss": 0.2765, "step": 4448 }, { "epoch": 0.12987505838393273, "grad_norm": 0.44535842537879944, "learning_rate": 9.972910440408226e-06, "loss": 0.3049, "step": 4449 }, { "epoch": 0.1299042503503036, "grad_norm": 0.6125089526176453, "learning_rate": 9.97285744967467e-06, "loss": 0.2725, "step": 4450 }, { "epoch": 0.12993344231667445, "grad_norm": 0.3818577229976654, "learning_rate": 9.972804407304386e-06, "loss": 0.2205, "step": 4451 }, { "epoch": 0.1299626342830453, "grad_norm": 0.45251595973968506, "learning_rate": 9.972751313297926e-06, "loss": 0.2404, "step": 4452 }, { "epoch": 0.12999182624941616, "grad_norm": 0.43147560954093933, "learning_rate": 9.972698167655842e-06, "loss": 0.2422, "step": 4453 }, { "epoch": 0.13002101821578702, "grad_norm": 0.5104065537452698, "learning_rate": 9.972644970378685e-06, "loss": 0.266, "step": 4454 }, { "epoch": 0.13005021018215787, "grad_norm": 0.5740376114845276, "learning_rate": 9.972591721467006e-06, "loss": 0.3046, "step": 4455 }, { "epoch": 0.13007940214852873, "grad_norm": 0.3659835159778595, "learning_rate": 9.97253842092136e-06, "loss": 0.2422, "step": 4456 }, { "epoch": 0.13010859411489958, "grad_norm": 0.3884415924549103, "learning_rate": 9.972485068742301e-06, "loss": 0.221, "step": 4457 }, { "epoch": 0.13013778608127044, "grad_norm": 0.8301727771759033, "learning_rate": 9.972431664930382e-06, "loss": 0.2785, "step": 4458 }, { "epoch": 0.1301669780476413, "grad_norm": 0.4480973184108734, "learning_rate": 9.972378209486155e-06, "loss": 0.2408, "step": 4459 }, { "epoch": 0.13019617001401215, "grad_norm": 0.3590351343154907, "learning_rate": 9.97232470241018e-06, "loss": 0.2075, "step": 4460 }, { "epoch": 0.130225361980383, "grad_norm": 0.36954978108406067, "learning_rate": 9.972271143703009e-06, "loss": 0.2099, "step": 4461 }, { "epoch": 0.13025455394675386, "grad_norm": 0.47853654623031616, "learning_rate": 9.972217533365199e-06, "loss": 0.2949, "step": 4462 }, { "epoch": 0.13028374591312472, "grad_norm": 0.6757675409317017, "learning_rate": 9.972163871397307e-06, "loss": 0.2869, "step": 4463 }, { "epoch": 0.13031293787949555, "grad_norm": 0.395282119512558, "learning_rate": 9.97211015779989e-06, "loss": 0.2637, "step": 4464 }, { "epoch": 0.1303421298458664, "grad_norm": 0.3881179988384247, "learning_rate": 9.972056392573505e-06, "loss": 0.2315, "step": 4465 }, { "epoch": 0.13037132181223726, "grad_norm": 0.3855990171432495, "learning_rate": 9.972002575718712e-06, "loss": 0.2484, "step": 4466 }, { "epoch": 0.13040051377860812, "grad_norm": 0.4209620952606201, "learning_rate": 9.971948707236068e-06, "loss": 0.2307, "step": 4467 }, { "epoch": 0.13042970574497897, "grad_norm": 0.3996381163597107, "learning_rate": 9.971894787126134e-06, "loss": 0.2566, "step": 4468 }, { "epoch": 0.13045889771134983, "grad_norm": 0.3751451373100281, "learning_rate": 9.971840815389468e-06, "loss": 0.2327, "step": 4469 }, { "epoch": 0.1304880896777207, "grad_norm": 0.362845778465271, "learning_rate": 9.971786792026633e-06, "loss": 0.2246, "step": 4470 }, { "epoch": 0.13051728164409154, "grad_norm": 0.38487154245376587, "learning_rate": 9.971732717038188e-06, "loss": 0.264, "step": 4471 }, { "epoch": 0.1305464736104624, "grad_norm": 0.3430938422679901, "learning_rate": 9.971678590424697e-06, "loss": 0.2386, "step": 4472 }, { "epoch": 0.13057566557683326, "grad_norm": 0.3564288318157196, "learning_rate": 9.971624412186717e-06, "loss": 0.2282, "step": 4473 }, { "epoch": 0.1306048575432041, "grad_norm": 0.3832077085971832, "learning_rate": 9.971570182324815e-06, "loss": 0.2271, "step": 4474 }, { "epoch": 0.13063404950957497, "grad_norm": 0.3679256737232208, "learning_rate": 9.971515900839552e-06, "loss": 0.2403, "step": 4475 }, { "epoch": 0.13066324147594582, "grad_norm": 0.3641112744808197, "learning_rate": 9.971461567731493e-06, "loss": 0.2632, "step": 4476 }, { "epoch": 0.13069243344231668, "grad_norm": 0.37614601850509644, "learning_rate": 9.971407183001202e-06, "loss": 0.2647, "step": 4477 }, { "epoch": 0.13072162540868754, "grad_norm": 0.42965036630630493, "learning_rate": 9.971352746649243e-06, "loss": 0.27, "step": 4478 }, { "epoch": 0.1307508173750584, "grad_norm": 0.3759574890136719, "learning_rate": 9.971298258676181e-06, "loss": 0.233, "step": 4479 }, { "epoch": 0.13078000934142925, "grad_norm": 0.3695618510246277, "learning_rate": 9.971243719082583e-06, "loss": 0.2214, "step": 4480 }, { "epoch": 0.1308092013078001, "grad_norm": 0.4782216250896454, "learning_rate": 9.971189127869014e-06, "loss": 0.2382, "step": 4481 }, { "epoch": 0.13083839327417096, "grad_norm": 0.3895810842514038, "learning_rate": 9.971134485036041e-06, "loss": 0.2181, "step": 4482 }, { "epoch": 0.1308675852405418, "grad_norm": 0.37525632977485657, "learning_rate": 9.971079790584233e-06, "loss": 0.2518, "step": 4483 }, { "epoch": 0.13089677720691265, "grad_norm": 0.42014840245246887, "learning_rate": 9.971025044514155e-06, "loss": 0.2458, "step": 4484 }, { "epoch": 0.1309259691732835, "grad_norm": 0.36546874046325684, "learning_rate": 9.97097024682638e-06, "loss": 0.2235, "step": 4485 }, { "epoch": 0.13095516113965436, "grad_norm": 0.43557050824165344, "learning_rate": 9.970915397521472e-06, "loss": 0.2517, "step": 4486 }, { "epoch": 0.13098435310602521, "grad_norm": 0.38339290022850037, "learning_rate": 9.970860496600005e-06, "loss": 0.2719, "step": 4487 }, { "epoch": 0.13101354507239607, "grad_norm": 0.39222973585128784, "learning_rate": 9.970805544062545e-06, "loss": 0.2859, "step": 4488 }, { "epoch": 0.13104273703876693, "grad_norm": 0.36164548993110657, "learning_rate": 9.970750539909666e-06, "loss": 0.2018, "step": 4489 }, { "epoch": 0.13107192900513778, "grad_norm": 0.3675313889980316, "learning_rate": 9.970695484141938e-06, "loss": 0.2572, "step": 4490 }, { "epoch": 0.13110112097150864, "grad_norm": 0.3809718191623688, "learning_rate": 9.97064037675993e-06, "loss": 0.2395, "step": 4491 }, { "epoch": 0.1311303129378795, "grad_norm": 0.46078574657440186, "learning_rate": 9.970585217764218e-06, "loss": 0.2617, "step": 4492 }, { "epoch": 0.13115950490425035, "grad_norm": 0.5796247124671936, "learning_rate": 9.970530007155373e-06, "loss": 0.2798, "step": 4493 }, { "epoch": 0.1311886968706212, "grad_norm": 0.3953161835670471, "learning_rate": 9.970474744933969e-06, "loss": 0.246, "step": 4494 }, { "epoch": 0.13121788883699206, "grad_norm": 0.37280040979385376, "learning_rate": 9.97041943110058e-06, "loss": 0.2107, "step": 4495 }, { "epoch": 0.13124708080336292, "grad_norm": 0.4146190285682678, "learning_rate": 9.970364065655779e-06, "loss": 0.2752, "step": 4496 }, { "epoch": 0.13127627276973378, "grad_norm": 0.34859171509742737, "learning_rate": 9.970308648600142e-06, "loss": 0.2369, "step": 4497 }, { "epoch": 0.13130546473610463, "grad_norm": 0.32518306374549866, "learning_rate": 9.970253179934243e-06, "loss": 0.2185, "step": 4498 }, { "epoch": 0.1313346567024755, "grad_norm": 0.37922579050064087, "learning_rate": 9.97019765965866e-06, "loss": 0.2801, "step": 4499 }, { "epoch": 0.13136384866884634, "grad_norm": 0.480550080537796, "learning_rate": 9.970142087773968e-06, "loss": 0.2585, "step": 4500 }, { "epoch": 0.1313930406352172, "grad_norm": 0.35490021109580994, "learning_rate": 9.970086464280745e-06, "loss": 0.2344, "step": 4501 }, { "epoch": 0.13142223260158803, "grad_norm": 0.36643221974372864, "learning_rate": 9.97003078917957e-06, "loss": 0.2851, "step": 4502 }, { "epoch": 0.13145142456795889, "grad_norm": 0.3580283224582672, "learning_rate": 9.969975062471017e-06, "loss": 0.2575, "step": 4503 }, { "epoch": 0.13148061653432974, "grad_norm": 0.33128872513771057, "learning_rate": 9.969919284155669e-06, "loss": 0.211, "step": 4504 }, { "epoch": 0.1315098085007006, "grad_norm": 0.36429667472839355, "learning_rate": 9.969863454234103e-06, "loss": 0.243, "step": 4505 }, { "epoch": 0.13153900046707145, "grad_norm": 0.3574933111667633, "learning_rate": 9.969807572706897e-06, "loss": 0.2591, "step": 4506 }, { "epoch": 0.1315681924334423, "grad_norm": 0.3876488506793976, "learning_rate": 9.969751639574634e-06, "loss": 0.2581, "step": 4507 }, { "epoch": 0.13159738439981317, "grad_norm": 0.36617612838745117, "learning_rate": 9.969695654837894e-06, "loss": 0.2693, "step": 4508 }, { "epoch": 0.13162657636618402, "grad_norm": 0.3823294937610626, "learning_rate": 9.969639618497258e-06, "loss": 0.2626, "step": 4509 }, { "epoch": 0.13165576833255488, "grad_norm": 0.3608323633670807, "learning_rate": 9.96958353055331e-06, "loss": 0.2598, "step": 4510 }, { "epoch": 0.13168496029892574, "grad_norm": 0.38967445492744446, "learning_rate": 9.969527391006628e-06, "loss": 0.2285, "step": 4511 }, { "epoch": 0.1317141522652966, "grad_norm": 0.39520418643951416, "learning_rate": 9.969471199857799e-06, "loss": 0.2512, "step": 4512 }, { "epoch": 0.13174334423166745, "grad_norm": 0.37799569964408875, "learning_rate": 9.969414957107404e-06, "loss": 0.2738, "step": 4513 }, { "epoch": 0.1317725361980383, "grad_norm": 0.3496797978878021, "learning_rate": 9.96935866275603e-06, "loss": 0.2391, "step": 4514 }, { "epoch": 0.13180172816440916, "grad_norm": 0.36023545265197754, "learning_rate": 9.969302316804258e-06, "loss": 0.2493, "step": 4515 }, { "epoch": 0.13183092013078002, "grad_norm": 0.41678547859191895, "learning_rate": 9.969245919252675e-06, "loss": 0.2347, "step": 4516 }, { "epoch": 0.13186011209715087, "grad_norm": 0.3615708351135254, "learning_rate": 9.969189470101865e-06, "loss": 0.2684, "step": 4517 }, { "epoch": 0.13188930406352173, "grad_norm": 0.36462467908859253, "learning_rate": 9.969132969352418e-06, "loss": 0.2612, "step": 4518 }, { "epoch": 0.13191849602989258, "grad_norm": 0.4157581627368927, "learning_rate": 9.969076417004916e-06, "loss": 0.2124, "step": 4519 }, { "epoch": 0.13194768799626344, "grad_norm": 0.39588475227355957, "learning_rate": 9.969019813059947e-06, "loss": 0.2546, "step": 4520 }, { "epoch": 0.13197687996263427, "grad_norm": 0.3724140226840973, "learning_rate": 9.968963157518104e-06, "loss": 0.2106, "step": 4521 }, { "epoch": 0.13200607192900513, "grad_norm": 0.3842919170856476, "learning_rate": 9.968906450379968e-06, "loss": 0.2593, "step": 4522 }, { "epoch": 0.13203526389537598, "grad_norm": 0.37524542212486267, "learning_rate": 9.968849691646131e-06, "loss": 0.2535, "step": 4523 }, { "epoch": 0.13206445586174684, "grad_norm": 0.3853275179862976, "learning_rate": 9.968792881317185e-06, "loss": 0.2706, "step": 4524 }, { "epoch": 0.1320936478281177, "grad_norm": 0.41700246930122375, "learning_rate": 9.968736019393717e-06, "loss": 0.2806, "step": 4525 }, { "epoch": 0.13212283979448855, "grad_norm": 0.38153162598609924, "learning_rate": 9.968679105876317e-06, "loss": 0.2755, "step": 4526 }, { "epoch": 0.1321520317608594, "grad_norm": 0.38348090648651123, "learning_rate": 9.968622140765576e-06, "loss": 0.293, "step": 4527 }, { "epoch": 0.13218122372723026, "grad_norm": 0.3841070532798767, "learning_rate": 9.968565124062089e-06, "loss": 0.2482, "step": 4528 }, { "epoch": 0.13221041569360112, "grad_norm": 0.3443838953971863, "learning_rate": 9.968508055766443e-06, "loss": 0.2299, "step": 4529 }, { "epoch": 0.13223960765997197, "grad_norm": 0.3472372591495514, "learning_rate": 9.968450935879234e-06, "loss": 0.2102, "step": 4530 }, { "epoch": 0.13226879962634283, "grad_norm": 0.3779250681400299, "learning_rate": 9.968393764401055e-06, "loss": 0.2263, "step": 4531 }, { "epoch": 0.1322979915927137, "grad_norm": 0.3547939956188202, "learning_rate": 9.968336541332496e-06, "loss": 0.274, "step": 4532 }, { "epoch": 0.13232718355908454, "grad_norm": 0.39116671681404114, "learning_rate": 9.968279266674156e-06, "loss": 0.2374, "step": 4533 }, { "epoch": 0.1323563755254554, "grad_norm": 0.34734034538269043, "learning_rate": 9.968221940426627e-06, "loss": 0.219, "step": 4534 }, { "epoch": 0.13238556749182626, "grad_norm": 0.479855477809906, "learning_rate": 9.968164562590505e-06, "loss": 0.289, "step": 4535 }, { "epoch": 0.1324147594581971, "grad_norm": 0.3718016743659973, "learning_rate": 9.968107133166384e-06, "loss": 0.2599, "step": 4536 }, { "epoch": 0.13244395142456797, "grad_norm": 0.44215264916419983, "learning_rate": 9.968049652154865e-06, "loss": 0.23, "step": 4537 }, { "epoch": 0.13247314339093882, "grad_norm": 0.4071142375469208, "learning_rate": 9.96799211955654e-06, "loss": 0.253, "step": 4538 }, { "epoch": 0.13250233535730968, "grad_norm": 0.39118003845214844, "learning_rate": 9.96793453537201e-06, "loss": 0.2414, "step": 4539 }, { "epoch": 0.13253152732368054, "grad_norm": 0.37117812037467957, "learning_rate": 9.967876899601871e-06, "loss": 0.3015, "step": 4540 }, { "epoch": 0.13256071929005137, "grad_norm": 0.3852209746837616, "learning_rate": 9.96781921224672e-06, "loss": 0.2679, "step": 4541 }, { "epoch": 0.13258991125642222, "grad_norm": 0.38554349541664124, "learning_rate": 9.967761473307159e-06, "loss": 0.3067, "step": 4542 }, { "epoch": 0.13261910322279308, "grad_norm": 0.388170450925827, "learning_rate": 9.967703682783787e-06, "loss": 0.295, "step": 4543 }, { "epoch": 0.13264829518916393, "grad_norm": 0.38681766390800476, "learning_rate": 9.967645840677202e-06, "loss": 0.2709, "step": 4544 }, { "epoch": 0.1326774871555348, "grad_norm": 0.35588905215263367, "learning_rate": 9.967587946988007e-06, "loss": 0.26, "step": 4545 }, { "epoch": 0.13270667912190565, "grad_norm": 0.3616560697555542, "learning_rate": 9.967530001716801e-06, "loss": 0.3009, "step": 4546 }, { "epoch": 0.1327358710882765, "grad_norm": 0.3982312083244324, "learning_rate": 9.967472004864187e-06, "loss": 0.2479, "step": 4547 }, { "epoch": 0.13276506305464736, "grad_norm": 0.36771413683891296, "learning_rate": 9.967413956430767e-06, "loss": 0.259, "step": 4548 }, { "epoch": 0.13279425502101821, "grad_norm": 0.3888714611530304, "learning_rate": 9.967355856417145e-06, "loss": 0.2893, "step": 4549 }, { "epoch": 0.13282344698738907, "grad_norm": 0.38659361004829407, "learning_rate": 9.967297704823922e-06, "loss": 0.2642, "step": 4550 }, { "epoch": 0.13285263895375993, "grad_norm": 0.4395681917667389, "learning_rate": 9.967239501651704e-06, "loss": 0.319, "step": 4551 }, { "epoch": 0.13288183092013078, "grad_norm": 0.39344915747642517, "learning_rate": 9.967181246901093e-06, "loss": 0.2467, "step": 4552 }, { "epoch": 0.13291102288650164, "grad_norm": 0.37786388397216797, "learning_rate": 9.967122940572695e-06, "loss": 0.2821, "step": 4553 }, { "epoch": 0.1329402148528725, "grad_norm": 0.3524295687675476, "learning_rate": 9.967064582667117e-06, "loss": 0.2227, "step": 4554 }, { "epoch": 0.13296940681924335, "grad_norm": 0.35832878947257996, "learning_rate": 9.967006173184964e-06, "loss": 0.2234, "step": 4555 }, { "epoch": 0.1329985987856142, "grad_norm": 0.3928707540035248, "learning_rate": 9.96694771212684e-06, "loss": 0.2646, "step": 4556 }, { "epoch": 0.13302779075198506, "grad_norm": 0.3293362855911255, "learning_rate": 9.966889199493355e-06, "loss": 0.1762, "step": 4557 }, { "epoch": 0.13305698271835592, "grad_norm": 0.37876221537590027, "learning_rate": 9.966830635285117e-06, "loss": 0.2542, "step": 4558 }, { "epoch": 0.13308617468472678, "grad_norm": 0.31074339151382446, "learning_rate": 9.966772019502731e-06, "loss": 0.1905, "step": 4559 }, { "epoch": 0.1331153666510976, "grad_norm": 0.38506972789764404, "learning_rate": 9.966713352146809e-06, "loss": 0.2525, "step": 4560 }, { "epoch": 0.13314455861746846, "grad_norm": 0.34577566385269165, "learning_rate": 9.966654633217957e-06, "loss": 0.2289, "step": 4561 }, { "epoch": 0.13317375058383932, "grad_norm": 0.4015110731124878, "learning_rate": 9.966595862716787e-06, "loss": 0.2173, "step": 4562 }, { "epoch": 0.13320294255021017, "grad_norm": 0.4043750762939453, "learning_rate": 9.966537040643908e-06, "loss": 0.2801, "step": 4563 }, { "epoch": 0.13323213451658103, "grad_norm": 0.35492143034935, "learning_rate": 9.966478166999933e-06, "loss": 0.2594, "step": 4564 }, { "epoch": 0.1332613264829519, "grad_norm": 0.3761758506298065, "learning_rate": 9.966419241785472e-06, "loss": 0.2213, "step": 4565 }, { "epoch": 0.13329051844932274, "grad_norm": 0.3895348906517029, "learning_rate": 9.966360265001136e-06, "loss": 0.2476, "step": 4566 }, { "epoch": 0.1333197104156936, "grad_norm": 0.3644734025001526, "learning_rate": 9.966301236647537e-06, "loss": 0.2594, "step": 4567 }, { "epoch": 0.13334890238206445, "grad_norm": 0.3601871430873871, "learning_rate": 9.96624215672529e-06, "loss": 0.2779, "step": 4568 }, { "epoch": 0.1333780943484353, "grad_norm": 0.41619059443473816, "learning_rate": 9.966183025235007e-06, "loss": 0.2781, "step": 4569 }, { "epoch": 0.13340728631480617, "grad_norm": 0.39408835768699646, "learning_rate": 9.966123842177303e-06, "loss": 0.2621, "step": 4570 }, { "epoch": 0.13343647828117702, "grad_norm": 0.3766421377658844, "learning_rate": 9.966064607552792e-06, "loss": 0.3148, "step": 4571 }, { "epoch": 0.13346567024754788, "grad_norm": 0.3796692490577698, "learning_rate": 9.966005321362087e-06, "loss": 0.2747, "step": 4572 }, { "epoch": 0.13349486221391874, "grad_norm": 0.34725940227508545, "learning_rate": 9.965945983605807e-06, "loss": 0.252, "step": 4573 }, { "epoch": 0.1335240541802896, "grad_norm": 0.35211920738220215, "learning_rate": 9.96588659428457e-06, "loss": 0.2543, "step": 4574 }, { "epoch": 0.13355324614666045, "grad_norm": 0.3451639413833618, "learning_rate": 9.965827153398984e-06, "loss": 0.2276, "step": 4575 }, { "epoch": 0.1335824381130313, "grad_norm": 0.40415525436401367, "learning_rate": 9.965767660949675e-06, "loss": 0.2736, "step": 4576 }, { "epoch": 0.13361163007940216, "grad_norm": 0.3907616138458252, "learning_rate": 9.965708116937256e-06, "loss": 0.297, "step": 4577 }, { "epoch": 0.13364082204577302, "grad_norm": 0.37274202704429626, "learning_rate": 9.965648521362348e-06, "loss": 0.2678, "step": 4578 }, { "epoch": 0.13367001401214385, "grad_norm": 0.3766013979911804, "learning_rate": 9.965588874225568e-06, "loss": 0.2762, "step": 4579 }, { "epoch": 0.1336992059785147, "grad_norm": 0.3371346890926361, "learning_rate": 9.965529175527537e-06, "loss": 0.1946, "step": 4580 }, { "epoch": 0.13372839794488556, "grad_norm": 0.35059070587158203, "learning_rate": 9.965469425268873e-06, "loss": 0.254, "step": 4581 }, { "epoch": 0.1337575899112564, "grad_norm": 0.348230242729187, "learning_rate": 9.965409623450196e-06, "loss": 0.2236, "step": 4582 }, { "epoch": 0.13378678187762727, "grad_norm": 0.35255685448646545, "learning_rate": 9.965349770072128e-06, "loss": 0.2121, "step": 4583 }, { "epoch": 0.13381597384399813, "grad_norm": 0.3624362051486969, "learning_rate": 9.965289865135294e-06, "loss": 0.2722, "step": 4584 }, { "epoch": 0.13384516581036898, "grad_norm": 0.4341452121734619, "learning_rate": 9.96522990864031e-06, "loss": 0.25, "step": 4585 }, { "epoch": 0.13387435777673984, "grad_norm": 0.339194118976593, "learning_rate": 9.965169900587802e-06, "loss": 0.2562, "step": 4586 }, { "epoch": 0.1339035497431107, "grad_norm": 0.37310895323753357, "learning_rate": 9.965109840978393e-06, "loss": 0.2467, "step": 4587 }, { "epoch": 0.13393274170948155, "grad_norm": 0.3732256591320038, "learning_rate": 9.965049729812706e-06, "loss": 0.2258, "step": 4588 }, { "epoch": 0.1339619336758524, "grad_norm": 0.3440493047237396, "learning_rate": 9.964989567091364e-06, "loss": 0.2293, "step": 4589 }, { "epoch": 0.13399112564222326, "grad_norm": 0.4112726151943207, "learning_rate": 9.964929352814994e-06, "loss": 0.2373, "step": 4590 }, { "epoch": 0.13402031760859412, "grad_norm": 0.3606388568878174, "learning_rate": 9.96486908698422e-06, "loss": 0.2311, "step": 4591 }, { "epoch": 0.13404950957496498, "grad_norm": 0.38305947184562683, "learning_rate": 9.964808769599667e-06, "loss": 0.2375, "step": 4592 }, { "epoch": 0.13407870154133583, "grad_norm": 0.3720329999923706, "learning_rate": 9.964748400661964e-06, "loss": 0.2527, "step": 4593 }, { "epoch": 0.1341078935077067, "grad_norm": 0.4087333381175995, "learning_rate": 9.964687980171735e-06, "loss": 0.282, "step": 4594 }, { "epoch": 0.13413708547407754, "grad_norm": 0.4172658622264862, "learning_rate": 9.96462750812961e-06, "loss": 0.2806, "step": 4595 }, { "epoch": 0.1341662774404484, "grad_norm": 0.36081165075302124, "learning_rate": 9.964566984536215e-06, "loss": 0.2672, "step": 4596 }, { "epoch": 0.13419546940681926, "grad_norm": 0.4458163380622864, "learning_rate": 9.964506409392178e-06, "loss": 0.2725, "step": 4597 }, { "epoch": 0.13422466137319009, "grad_norm": 0.4294087886810303, "learning_rate": 9.964445782698129e-06, "loss": 0.2813, "step": 4598 }, { "epoch": 0.13425385333956094, "grad_norm": 0.3808492124080658, "learning_rate": 9.964385104454697e-06, "loss": 0.2339, "step": 4599 }, { "epoch": 0.1342830453059318, "grad_norm": 0.3349069356918335, "learning_rate": 9.964324374662515e-06, "loss": 0.2348, "step": 4600 }, { "epoch": 0.13431223727230265, "grad_norm": 0.38208237290382385, "learning_rate": 9.964263593322208e-06, "loss": 0.2496, "step": 4601 }, { "epoch": 0.1343414292386735, "grad_norm": 0.5240640044212341, "learning_rate": 9.964202760434412e-06, "loss": 0.2383, "step": 4602 }, { "epoch": 0.13437062120504437, "grad_norm": 0.5236194729804993, "learning_rate": 9.964141875999758e-06, "loss": 0.2967, "step": 4603 }, { "epoch": 0.13439981317141522, "grad_norm": 0.35693877935409546, "learning_rate": 9.964080940018874e-06, "loss": 0.2637, "step": 4604 }, { "epoch": 0.13442900513778608, "grad_norm": 0.41655290126800537, "learning_rate": 9.964019952492398e-06, "loss": 0.2367, "step": 4605 }, { "epoch": 0.13445819710415693, "grad_norm": 0.3965051770210266, "learning_rate": 9.963958913420962e-06, "loss": 0.2883, "step": 4606 }, { "epoch": 0.1344873890705278, "grad_norm": 0.3772360384464264, "learning_rate": 9.963897822805198e-06, "loss": 0.2581, "step": 4607 }, { "epoch": 0.13451658103689865, "grad_norm": 0.39286479353904724, "learning_rate": 9.96383668064574e-06, "loss": 0.2649, "step": 4608 }, { "epoch": 0.1345457730032695, "grad_norm": 0.3866594135761261, "learning_rate": 9.963775486943225e-06, "loss": 0.2319, "step": 4609 }, { "epoch": 0.13457496496964036, "grad_norm": 0.38995862007141113, "learning_rate": 9.963714241698287e-06, "loss": 0.2568, "step": 4610 }, { "epoch": 0.13460415693601122, "grad_norm": 0.3984450697898865, "learning_rate": 9.963652944911566e-06, "loss": 0.253, "step": 4611 }, { "epoch": 0.13463334890238207, "grad_norm": 0.35174331068992615, "learning_rate": 9.963591596583693e-06, "loss": 0.2418, "step": 4612 }, { "epoch": 0.13466254086875293, "grad_norm": 0.4021086096763611, "learning_rate": 9.963530196715305e-06, "loss": 0.2308, "step": 4613 }, { "epoch": 0.13469173283512378, "grad_norm": 0.4185044467449188, "learning_rate": 9.963468745307043e-06, "loss": 0.2417, "step": 4614 }, { "epoch": 0.13472092480149464, "grad_norm": 0.40523219108581543, "learning_rate": 9.963407242359546e-06, "loss": 0.2459, "step": 4615 }, { "epoch": 0.1347501167678655, "grad_norm": 0.39624035358428955, "learning_rate": 9.963345687873447e-06, "loss": 0.3012, "step": 4616 }, { "epoch": 0.13477930873423632, "grad_norm": 0.43009066581726074, "learning_rate": 9.96328408184939e-06, "loss": 0.2802, "step": 4617 }, { "epoch": 0.13480850070060718, "grad_norm": 0.3961954712867737, "learning_rate": 9.963222424288014e-06, "loss": 0.2588, "step": 4618 }, { "epoch": 0.13483769266697804, "grad_norm": 0.33104321360588074, "learning_rate": 9.963160715189957e-06, "loss": 0.2393, "step": 4619 }, { "epoch": 0.1348668846333489, "grad_norm": 0.3533610701560974, "learning_rate": 9.963098954555863e-06, "loss": 0.2435, "step": 4620 }, { "epoch": 0.13489607659971975, "grad_norm": 0.31847789883613586, "learning_rate": 9.96303714238637e-06, "loss": 0.2244, "step": 4621 }, { "epoch": 0.1349252685660906, "grad_norm": 0.8179333806037903, "learning_rate": 9.962975278682121e-06, "loss": 0.2451, "step": 4622 }, { "epoch": 0.13495446053246146, "grad_norm": 0.42174196243286133, "learning_rate": 9.96291336344376e-06, "loss": 0.2924, "step": 4623 }, { "epoch": 0.13498365249883232, "grad_norm": 0.35474666953086853, "learning_rate": 9.96285139667193e-06, "loss": 0.2241, "step": 4624 }, { "epoch": 0.13501284446520317, "grad_norm": 0.30582132935523987, "learning_rate": 9.96278937836727e-06, "loss": 0.2117, "step": 4625 }, { "epoch": 0.13504203643157403, "grad_norm": 0.4093947410583496, "learning_rate": 9.962727308530429e-06, "loss": 0.2394, "step": 4626 }, { "epoch": 0.1350712283979449, "grad_norm": 0.4650138318538666, "learning_rate": 9.962665187162048e-06, "loss": 0.2576, "step": 4627 }, { "epoch": 0.13510042036431574, "grad_norm": 0.3871780037879944, "learning_rate": 9.962603014262774e-06, "loss": 0.2373, "step": 4628 }, { "epoch": 0.1351296123306866, "grad_norm": 0.3565298616886139, "learning_rate": 9.962540789833255e-06, "loss": 0.2589, "step": 4629 }, { "epoch": 0.13515880429705746, "grad_norm": 0.3676038086414337, "learning_rate": 9.962478513874131e-06, "loss": 0.246, "step": 4630 }, { "epoch": 0.1351879962634283, "grad_norm": 0.38353875279426575, "learning_rate": 9.962416186386054e-06, "loss": 0.2698, "step": 4631 }, { "epoch": 0.13521718822979917, "grad_norm": 0.39173564314842224, "learning_rate": 9.962353807369668e-06, "loss": 0.2763, "step": 4632 }, { "epoch": 0.13524638019617002, "grad_norm": 0.3606978952884674, "learning_rate": 9.962291376825624e-06, "loss": 0.2789, "step": 4633 }, { "epoch": 0.13527557216254088, "grad_norm": 0.3705514967441559, "learning_rate": 9.962228894754566e-06, "loss": 0.2675, "step": 4634 }, { "epoch": 0.13530476412891174, "grad_norm": 0.3817254602909088, "learning_rate": 9.962166361157147e-06, "loss": 0.2144, "step": 4635 }, { "epoch": 0.13533395609528256, "grad_norm": 0.37356364727020264, "learning_rate": 9.962103776034011e-06, "loss": 0.2505, "step": 4636 }, { "epoch": 0.13536314806165342, "grad_norm": 0.3828548789024353, "learning_rate": 9.962041139385813e-06, "loss": 0.2909, "step": 4637 }, { "epoch": 0.13539234002802428, "grad_norm": 0.36502331495285034, "learning_rate": 9.961978451213203e-06, "loss": 0.2464, "step": 4638 }, { "epoch": 0.13542153199439513, "grad_norm": 0.36621958017349243, "learning_rate": 9.961915711516828e-06, "loss": 0.2509, "step": 4639 }, { "epoch": 0.135450723960766, "grad_norm": 0.970178484916687, "learning_rate": 9.961852920297344e-06, "loss": 0.2544, "step": 4640 }, { "epoch": 0.13547991592713685, "grad_norm": 0.3869377076625824, "learning_rate": 9.9617900775554e-06, "loss": 0.2399, "step": 4641 }, { "epoch": 0.1355091078935077, "grad_norm": 0.3735170364379883, "learning_rate": 9.96172718329165e-06, "loss": 0.2564, "step": 4642 }, { "epoch": 0.13553829985987856, "grad_norm": 0.6091150045394897, "learning_rate": 9.961664237506747e-06, "loss": 0.2396, "step": 4643 }, { "epoch": 0.13556749182624941, "grad_norm": 0.39098212122917175, "learning_rate": 9.961601240201345e-06, "loss": 0.2524, "step": 4644 }, { "epoch": 0.13559668379262027, "grad_norm": 0.4387320876121521, "learning_rate": 9.961538191376095e-06, "loss": 0.2222, "step": 4645 }, { "epoch": 0.13562587575899113, "grad_norm": 0.40870803594589233, "learning_rate": 9.961475091031655e-06, "loss": 0.2594, "step": 4646 }, { "epoch": 0.13565506772536198, "grad_norm": 0.34907084703445435, "learning_rate": 9.96141193916868e-06, "loss": 0.22, "step": 4647 }, { "epoch": 0.13568425969173284, "grad_norm": 0.3677637279033661, "learning_rate": 9.961348735787823e-06, "loss": 0.2354, "step": 4648 }, { "epoch": 0.1357134516581037, "grad_norm": 0.3884482979774475, "learning_rate": 9.961285480889743e-06, "loss": 0.2505, "step": 4649 }, { "epoch": 0.13574264362447455, "grad_norm": 0.3747529089450836, "learning_rate": 9.961222174475098e-06, "loss": 0.2528, "step": 4650 }, { "epoch": 0.1357718355908454, "grad_norm": 0.35276949405670166, "learning_rate": 9.961158816544542e-06, "loss": 0.2386, "step": 4651 }, { "epoch": 0.13580102755721626, "grad_norm": 0.34563833475112915, "learning_rate": 9.961095407098735e-06, "loss": 0.2286, "step": 4652 }, { "epoch": 0.13583021952358712, "grad_norm": 0.3521031439304352, "learning_rate": 9.961031946138335e-06, "loss": 0.2173, "step": 4653 }, { "epoch": 0.13585941148995798, "grad_norm": 0.4128028452396393, "learning_rate": 9.960968433664e-06, "loss": 0.2982, "step": 4654 }, { "epoch": 0.1358886034563288, "grad_norm": 0.36385688185691833, "learning_rate": 9.960904869676392e-06, "loss": 0.235, "step": 4655 }, { "epoch": 0.13591779542269966, "grad_norm": 0.42989203333854675, "learning_rate": 9.960841254176166e-06, "loss": 0.2251, "step": 4656 }, { "epoch": 0.13594698738907052, "grad_norm": 0.4210684597492218, "learning_rate": 9.960777587163988e-06, "loss": 0.2768, "step": 4657 }, { "epoch": 0.13597617935544137, "grad_norm": 0.35853222012519836, "learning_rate": 9.960713868640517e-06, "loss": 0.2176, "step": 4658 }, { "epoch": 0.13600537132181223, "grad_norm": 0.41923069953918457, "learning_rate": 9.960650098606415e-06, "loss": 0.222, "step": 4659 }, { "epoch": 0.13603456328818309, "grad_norm": 0.44374406337738037, "learning_rate": 9.960586277062343e-06, "loss": 0.3035, "step": 4660 }, { "epoch": 0.13606375525455394, "grad_norm": 0.4109242856502533, "learning_rate": 9.960522404008963e-06, "loss": 0.3135, "step": 4661 }, { "epoch": 0.1360929472209248, "grad_norm": 0.39537888765335083, "learning_rate": 9.960458479446942e-06, "loss": 0.2861, "step": 4662 }, { "epoch": 0.13612213918729565, "grad_norm": 0.39343371987342834, "learning_rate": 9.96039450337694e-06, "loss": 0.2493, "step": 4663 }, { "epoch": 0.1361513311536665, "grad_norm": 0.3337063789367676, "learning_rate": 9.960330475799625e-06, "loss": 0.2251, "step": 4664 }, { "epoch": 0.13618052312003737, "grad_norm": 0.36791110038757324, "learning_rate": 9.960266396715657e-06, "loss": 0.2318, "step": 4665 }, { "epoch": 0.13620971508640822, "grad_norm": 0.44151571393013, "learning_rate": 9.960202266125704e-06, "loss": 0.2276, "step": 4666 }, { "epoch": 0.13623890705277908, "grad_norm": 0.42153236269950867, "learning_rate": 9.960138084030436e-06, "loss": 0.2927, "step": 4667 }, { "epoch": 0.13626809901914994, "grad_norm": 0.38616713881492615, "learning_rate": 9.96007385043051e-06, "loss": 0.2977, "step": 4668 }, { "epoch": 0.1362972909855208, "grad_norm": 0.3719370663166046, "learning_rate": 9.960009565326602e-06, "loss": 0.2001, "step": 4669 }, { "epoch": 0.13632648295189165, "grad_norm": 0.4638797342777252, "learning_rate": 9.959945228719374e-06, "loss": 0.2508, "step": 4670 }, { "epoch": 0.1363556749182625, "grad_norm": 0.4341563880443573, "learning_rate": 9.959880840609498e-06, "loss": 0.2668, "step": 4671 }, { "epoch": 0.13638486688463336, "grad_norm": 0.433674693107605, "learning_rate": 9.959816400997638e-06, "loss": 0.2968, "step": 4672 }, { "epoch": 0.13641405885100422, "grad_norm": 0.33429470658302307, "learning_rate": 9.959751909884466e-06, "loss": 0.1947, "step": 4673 }, { "epoch": 0.13644325081737504, "grad_norm": 0.4150039553642273, "learning_rate": 9.959687367270652e-06, "loss": 0.2373, "step": 4674 }, { "epoch": 0.1364724427837459, "grad_norm": 0.4209302067756653, "learning_rate": 9.959622773156865e-06, "loss": 0.2383, "step": 4675 }, { "epoch": 0.13650163475011676, "grad_norm": 0.3916756510734558, "learning_rate": 9.959558127543779e-06, "loss": 0.2291, "step": 4676 }, { "epoch": 0.1365308267164876, "grad_norm": 0.3620530366897583, "learning_rate": 9.959493430432058e-06, "loss": 0.2234, "step": 4677 }, { "epoch": 0.13656001868285847, "grad_norm": 0.7316539883613586, "learning_rate": 9.959428681822381e-06, "loss": 0.2566, "step": 4678 }, { "epoch": 0.13658921064922933, "grad_norm": 0.5279098153114319, "learning_rate": 9.959363881715416e-06, "loss": 0.2949, "step": 4679 }, { "epoch": 0.13661840261560018, "grad_norm": 0.389445036649704, "learning_rate": 9.95929903011184e-06, "loss": 0.2888, "step": 4680 }, { "epoch": 0.13664759458197104, "grad_norm": 0.38465023040771484, "learning_rate": 9.959234127012322e-06, "loss": 0.2185, "step": 4681 }, { "epoch": 0.1366767865483419, "grad_norm": 0.383648544549942, "learning_rate": 9.959169172417537e-06, "loss": 0.2233, "step": 4682 }, { "epoch": 0.13670597851471275, "grad_norm": 0.4926452338695526, "learning_rate": 9.959104166328162e-06, "loss": 0.2607, "step": 4683 }, { "epoch": 0.1367351704810836, "grad_norm": 0.38849976658821106, "learning_rate": 9.95903910874487e-06, "loss": 0.2249, "step": 4684 }, { "epoch": 0.13676436244745446, "grad_norm": 0.4175011217594147, "learning_rate": 9.958973999668337e-06, "loss": 0.2863, "step": 4685 }, { "epoch": 0.13679355441382532, "grad_norm": 0.40030354261398315, "learning_rate": 9.958908839099238e-06, "loss": 0.2603, "step": 4686 }, { "epoch": 0.13682274638019618, "grad_norm": 0.39970988035202026, "learning_rate": 9.95884362703825e-06, "loss": 0.2795, "step": 4687 }, { "epoch": 0.13685193834656703, "grad_norm": 0.4362557530403137, "learning_rate": 9.958778363486053e-06, "loss": 0.248, "step": 4688 }, { "epoch": 0.1368811303129379, "grad_norm": 0.4570876359939575, "learning_rate": 9.958713048443321e-06, "loss": 0.2823, "step": 4689 }, { "epoch": 0.13691032227930874, "grad_norm": 0.444654256105423, "learning_rate": 9.958647681910734e-06, "loss": 0.2473, "step": 4690 }, { "epoch": 0.1369395142456796, "grad_norm": 0.40947669744491577, "learning_rate": 9.95858226388897e-06, "loss": 0.2412, "step": 4691 }, { "epoch": 0.13696870621205046, "grad_norm": 0.4022562503814697, "learning_rate": 9.958516794378708e-06, "loss": 0.2893, "step": 4692 }, { "epoch": 0.13699789817842128, "grad_norm": 0.501257061958313, "learning_rate": 9.958451273380626e-06, "loss": 0.2939, "step": 4693 }, { "epoch": 0.13702709014479214, "grad_norm": 0.40019240975379944, "learning_rate": 9.958385700895412e-06, "loss": 0.3094, "step": 4694 }, { "epoch": 0.137056282111163, "grad_norm": 0.46742939949035645, "learning_rate": 9.958320076923738e-06, "loss": 0.283, "step": 4695 }, { "epoch": 0.13708547407753385, "grad_norm": 0.4233848750591278, "learning_rate": 9.95825440146629e-06, "loss": 0.2414, "step": 4696 }, { "epoch": 0.1371146660439047, "grad_norm": 0.48243677616119385, "learning_rate": 9.958188674523748e-06, "loss": 0.3207, "step": 4697 }, { "epoch": 0.13714385801027557, "grad_norm": 0.4163454473018646, "learning_rate": 9.958122896096798e-06, "loss": 0.219, "step": 4698 }, { "epoch": 0.13717304997664642, "grad_norm": 0.37613385915756226, "learning_rate": 9.958057066186119e-06, "loss": 0.2108, "step": 4699 }, { "epoch": 0.13720224194301728, "grad_norm": 0.3726320266723633, "learning_rate": 9.957991184792395e-06, "loss": 0.2156, "step": 4700 }, { "epoch": 0.13723143390938813, "grad_norm": 0.44080641865730286, "learning_rate": 9.957925251916313e-06, "loss": 0.2606, "step": 4701 }, { "epoch": 0.137260625875759, "grad_norm": 0.3804427683353424, "learning_rate": 9.957859267558554e-06, "loss": 0.295, "step": 4702 }, { "epoch": 0.13728981784212985, "grad_norm": 0.39170703291893005, "learning_rate": 9.957793231719807e-06, "loss": 0.2645, "step": 4703 }, { "epoch": 0.1373190098085007, "grad_norm": 0.32126384973526, "learning_rate": 9.957727144400756e-06, "loss": 0.2498, "step": 4704 }, { "epoch": 0.13734820177487156, "grad_norm": 0.394226610660553, "learning_rate": 9.957661005602084e-06, "loss": 0.2234, "step": 4705 }, { "epoch": 0.13737739374124242, "grad_norm": 0.41580453515052795, "learning_rate": 9.957594815324482e-06, "loss": 0.2343, "step": 4706 }, { "epoch": 0.13740658570761327, "grad_norm": 0.40772807598114014, "learning_rate": 9.957528573568635e-06, "loss": 0.2346, "step": 4707 }, { "epoch": 0.13743577767398413, "grad_norm": 0.3937142789363861, "learning_rate": 9.957462280335234e-06, "loss": 0.2734, "step": 4708 }, { "epoch": 0.13746496964035498, "grad_norm": 0.4338070750236511, "learning_rate": 9.957395935624964e-06, "loss": 0.274, "step": 4709 }, { "epoch": 0.13749416160672584, "grad_norm": 0.48783788084983826, "learning_rate": 9.957329539438516e-06, "loss": 0.2588, "step": 4710 }, { "epoch": 0.1375233535730967, "grad_norm": 0.5043854117393494, "learning_rate": 9.957263091776576e-06, "loss": 0.1989, "step": 4711 }, { "epoch": 0.13755254553946755, "grad_norm": 0.365008682012558, "learning_rate": 9.957196592639838e-06, "loss": 0.2137, "step": 4712 }, { "epoch": 0.13758173750583838, "grad_norm": 0.3806026577949524, "learning_rate": 9.95713004202899e-06, "loss": 0.219, "step": 4713 }, { "epoch": 0.13761092947220924, "grad_norm": 0.3973536789417267, "learning_rate": 9.957063439944727e-06, "loss": 0.282, "step": 4714 }, { "epoch": 0.1376401214385801, "grad_norm": 0.3536253869533539, "learning_rate": 9.956996786387735e-06, "loss": 0.247, "step": 4715 }, { "epoch": 0.13766931340495095, "grad_norm": 0.365725576877594, "learning_rate": 9.956930081358709e-06, "loss": 0.2371, "step": 4716 }, { "epoch": 0.1376985053713218, "grad_norm": 0.4561803638935089, "learning_rate": 9.956863324858342e-06, "loss": 0.253, "step": 4717 }, { "epoch": 0.13772769733769266, "grad_norm": 0.9164260029792786, "learning_rate": 9.956796516887326e-06, "loss": 0.2016, "step": 4718 }, { "epoch": 0.13775688930406352, "grad_norm": 0.3551006615161896, "learning_rate": 9.956729657446355e-06, "loss": 0.2346, "step": 4719 }, { "epoch": 0.13778608127043437, "grad_norm": 0.41042694449424744, "learning_rate": 9.956662746536124e-06, "loss": 0.2607, "step": 4720 }, { "epoch": 0.13781527323680523, "grad_norm": 0.3758023679256439, "learning_rate": 9.956595784157328e-06, "loss": 0.2646, "step": 4721 }, { "epoch": 0.1378444652031761, "grad_norm": 0.8942185640335083, "learning_rate": 9.95652877031066e-06, "loss": 0.3005, "step": 4722 }, { "epoch": 0.13787365716954694, "grad_norm": 0.4192190170288086, "learning_rate": 9.956461704996818e-06, "loss": 0.2655, "step": 4723 }, { "epoch": 0.1379028491359178, "grad_norm": 0.4078224003314972, "learning_rate": 9.956394588216498e-06, "loss": 0.3175, "step": 4724 }, { "epoch": 0.13793204110228865, "grad_norm": 0.41163408756256104, "learning_rate": 9.956327419970398e-06, "loss": 0.2712, "step": 4725 }, { "epoch": 0.1379612330686595, "grad_norm": 0.3525949716567993, "learning_rate": 9.956260200259213e-06, "loss": 0.1938, "step": 4726 }, { "epoch": 0.13799042503503037, "grad_norm": 0.4098288416862488, "learning_rate": 9.95619292908364e-06, "loss": 0.2872, "step": 4727 }, { "epoch": 0.13801961700140122, "grad_norm": 0.34618690609931946, "learning_rate": 9.956125606444385e-06, "loss": 0.228, "step": 4728 }, { "epoch": 0.13804880896777208, "grad_norm": 0.41935089230537415, "learning_rate": 9.956058232342138e-06, "loss": 0.2934, "step": 4729 }, { "epoch": 0.13807800093414294, "grad_norm": 0.4005049765110016, "learning_rate": 9.955990806777602e-06, "loss": 0.2908, "step": 4730 }, { "epoch": 0.1381071929005138, "grad_norm": 0.40135642886161804, "learning_rate": 9.95592332975148e-06, "loss": 0.2796, "step": 4731 }, { "epoch": 0.13813638486688462, "grad_norm": 0.7615215182304382, "learning_rate": 9.95585580126447e-06, "loss": 0.2599, "step": 4732 }, { "epoch": 0.13816557683325548, "grad_norm": 0.4198889136314392, "learning_rate": 9.95578822131727e-06, "loss": 0.3226, "step": 4733 }, { "epoch": 0.13819476879962633, "grad_norm": 0.41823533177375793, "learning_rate": 9.955720589910589e-06, "loss": 0.2738, "step": 4734 }, { "epoch": 0.1382239607659972, "grad_norm": 0.43650445342063904, "learning_rate": 9.955652907045124e-06, "loss": 0.258, "step": 4735 }, { "epoch": 0.13825315273236805, "grad_norm": 0.45063039660453796, "learning_rate": 9.955585172721577e-06, "loss": 0.2756, "step": 4736 }, { "epoch": 0.1382823446987389, "grad_norm": 0.3900439143180847, "learning_rate": 9.955517386940655e-06, "loss": 0.243, "step": 4737 }, { "epoch": 0.13831153666510976, "grad_norm": 0.3782496452331543, "learning_rate": 9.955449549703062e-06, "loss": 0.2798, "step": 4738 }, { "epoch": 0.13834072863148061, "grad_norm": 0.3606254458427429, "learning_rate": 9.9553816610095e-06, "loss": 0.2154, "step": 4739 }, { "epoch": 0.13836992059785147, "grad_norm": 0.375212162733078, "learning_rate": 9.955313720860673e-06, "loss": 0.2987, "step": 4740 }, { "epoch": 0.13839911256422233, "grad_norm": 0.35432425141334534, "learning_rate": 9.95524572925729e-06, "loss": 0.2195, "step": 4741 }, { "epoch": 0.13842830453059318, "grad_norm": 0.36930763721466064, "learning_rate": 9.955177686200055e-06, "loss": 0.2828, "step": 4742 }, { "epoch": 0.13845749649696404, "grad_norm": 0.34145405888557434, "learning_rate": 9.955109591689673e-06, "loss": 0.2118, "step": 4743 }, { "epoch": 0.1384866884633349, "grad_norm": 0.40291929244995117, "learning_rate": 9.955041445726854e-06, "loss": 0.2578, "step": 4744 }, { "epoch": 0.13851588042970575, "grad_norm": 0.3898693025112152, "learning_rate": 9.954973248312304e-06, "loss": 0.258, "step": 4745 }, { "epoch": 0.1385450723960766, "grad_norm": 0.36054080724716187, "learning_rate": 9.954904999446732e-06, "loss": 0.2108, "step": 4746 }, { "epoch": 0.13857426436244746, "grad_norm": 0.36723223328590393, "learning_rate": 9.954836699130847e-06, "loss": 0.2604, "step": 4747 }, { "epoch": 0.13860345632881832, "grad_norm": 0.3886626660823822, "learning_rate": 9.954768347365358e-06, "loss": 0.259, "step": 4748 }, { "epoch": 0.13863264829518918, "grad_norm": 0.40126562118530273, "learning_rate": 9.954699944150972e-06, "loss": 0.2709, "step": 4749 }, { "epoch": 0.13866184026156003, "grad_norm": 0.3586954176425934, "learning_rate": 9.954631489488401e-06, "loss": 0.2027, "step": 4750 }, { "epoch": 0.13869103222793086, "grad_norm": 0.372743159532547, "learning_rate": 9.954562983378359e-06, "loss": 0.328, "step": 4751 }, { "epoch": 0.13872022419430172, "grad_norm": 0.40753379464149475, "learning_rate": 9.954494425821553e-06, "loss": 0.2151, "step": 4752 }, { "epoch": 0.13874941616067257, "grad_norm": 0.3955787122249603, "learning_rate": 9.954425816818697e-06, "loss": 0.2362, "step": 4753 }, { "epoch": 0.13877860812704343, "grad_norm": 0.40065738558769226, "learning_rate": 9.954357156370501e-06, "loss": 0.2186, "step": 4754 }, { "epoch": 0.13880780009341429, "grad_norm": 0.3551454246044159, "learning_rate": 9.954288444477682e-06, "loss": 0.2332, "step": 4755 }, { "epoch": 0.13883699205978514, "grad_norm": 0.39557573199272156, "learning_rate": 9.95421968114095e-06, "loss": 0.2283, "step": 4756 }, { "epoch": 0.138866184026156, "grad_norm": 0.43465670943260193, "learning_rate": 9.954150866361023e-06, "loss": 0.2413, "step": 4757 }, { "epoch": 0.13889537599252685, "grad_norm": 0.3389537036418915, "learning_rate": 9.954082000138611e-06, "loss": 0.1859, "step": 4758 }, { "epoch": 0.1389245679588977, "grad_norm": 0.48748496174812317, "learning_rate": 9.954013082474431e-06, "loss": 0.2884, "step": 4759 }, { "epoch": 0.13895375992526857, "grad_norm": 0.40883782505989075, "learning_rate": 9.953944113369199e-06, "loss": 0.3462, "step": 4760 }, { "epoch": 0.13898295189163942, "grad_norm": 0.3942123353481293, "learning_rate": 9.95387509282363e-06, "loss": 0.2182, "step": 4761 }, { "epoch": 0.13901214385801028, "grad_norm": 0.4386310279369354, "learning_rate": 9.953806020838443e-06, "loss": 0.2634, "step": 4762 }, { "epoch": 0.13904133582438113, "grad_norm": 0.5264431238174438, "learning_rate": 9.953736897414353e-06, "loss": 0.2272, "step": 4763 }, { "epoch": 0.139070527790752, "grad_norm": 0.3962487578392029, "learning_rate": 9.953667722552078e-06, "loss": 0.2613, "step": 4764 }, { "epoch": 0.13909971975712285, "grad_norm": 0.37301045656204224, "learning_rate": 9.953598496252337e-06, "loss": 0.2332, "step": 4765 }, { "epoch": 0.1391289117234937, "grad_norm": 0.3394279479980469, "learning_rate": 9.953529218515847e-06, "loss": 0.2267, "step": 4766 }, { "epoch": 0.13915810368986456, "grad_norm": 0.4206644594669342, "learning_rate": 9.95345988934333e-06, "loss": 0.2536, "step": 4767 }, { "epoch": 0.13918729565623542, "grad_norm": 0.40357479453086853, "learning_rate": 9.953390508735506e-06, "loss": 0.2548, "step": 4768 }, { "epoch": 0.13921648762260627, "grad_norm": 0.393563836812973, "learning_rate": 9.953321076693095e-06, "loss": 0.2524, "step": 4769 }, { "epoch": 0.1392456795889771, "grad_norm": 0.41758832335472107, "learning_rate": 9.953251593216815e-06, "loss": 0.24, "step": 4770 }, { "epoch": 0.13927487155534796, "grad_norm": 0.40052226185798645, "learning_rate": 9.95318205830739e-06, "loss": 0.2804, "step": 4771 }, { "epoch": 0.1393040635217188, "grad_norm": 0.4021269679069519, "learning_rate": 9.953112471965543e-06, "loss": 0.2683, "step": 4772 }, { "epoch": 0.13933325548808967, "grad_norm": 0.3927551209926605, "learning_rate": 9.953042834191995e-06, "loss": 0.2348, "step": 4773 }, { "epoch": 0.13936244745446053, "grad_norm": 0.41916385293006897, "learning_rate": 9.952973144987467e-06, "loss": 0.2534, "step": 4774 }, { "epoch": 0.13939163942083138, "grad_norm": 0.5296506881713867, "learning_rate": 9.952903404352688e-06, "loss": 0.2763, "step": 4775 }, { "epoch": 0.13942083138720224, "grad_norm": 0.3870343267917633, "learning_rate": 9.952833612288378e-06, "loss": 0.2302, "step": 4776 }, { "epoch": 0.1394500233535731, "grad_norm": 0.42533788084983826, "learning_rate": 9.952763768795265e-06, "loss": 0.2508, "step": 4777 }, { "epoch": 0.13947921531994395, "grad_norm": 0.41262564063072205, "learning_rate": 9.952693873874069e-06, "loss": 0.2902, "step": 4778 }, { "epoch": 0.1395084072863148, "grad_norm": 0.3727496862411499, "learning_rate": 9.952623927525519e-06, "loss": 0.24, "step": 4779 }, { "epoch": 0.13953759925268566, "grad_norm": 0.39953312277793884, "learning_rate": 9.952553929750344e-06, "loss": 0.2886, "step": 4780 }, { "epoch": 0.13956679121905652, "grad_norm": 0.3916984796524048, "learning_rate": 9.952483880549267e-06, "loss": 0.2599, "step": 4781 }, { "epoch": 0.13959598318542737, "grad_norm": 0.4136018455028534, "learning_rate": 9.952413779923015e-06, "loss": 0.2508, "step": 4782 }, { "epoch": 0.13962517515179823, "grad_norm": 0.34987837076187134, "learning_rate": 9.952343627872319e-06, "loss": 0.2795, "step": 4783 }, { "epoch": 0.1396543671181691, "grad_norm": 0.47369149327278137, "learning_rate": 9.952273424397905e-06, "loss": 0.2902, "step": 4784 }, { "epoch": 0.13968355908453994, "grad_norm": 0.37507227063179016, "learning_rate": 9.952203169500503e-06, "loss": 0.2832, "step": 4785 }, { "epoch": 0.1397127510509108, "grad_norm": 0.32999372482299805, "learning_rate": 9.952132863180841e-06, "loss": 0.2092, "step": 4786 }, { "epoch": 0.13974194301728166, "grad_norm": 0.3572521209716797, "learning_rate": 9.95206250543965e-06, "loss": 0.2719, "step": 4787 }, { "epoch": 0.1397711349836525, "grad_norm": 0.3479417562484741, "learning_rate": 9.951992096277663e-06, "loss": 0.237, "step": 4788 }, { "epoch": 0.13980032695002334, "grad_norm": 0.3318038284778595, "learning_rate": 9.951921635695609e-06, "loss": 0.2137, "step": 4789 }, { "epoch": 0.1398295189163942, "grad_norm": 0.3513915538787842, "learning_rate": 9.951851123694218e-06, "loss": 0.2236, "step": 4790 }, { "epoch": 0.13985871088276505, "grad_norm": 0.3976452052593231, "learning_rate": 9.951780560274224e-06, "loss": 0.2808, "step": 4791 }, { "epoch": 0.1398879028491359, "grad_norm": 0.3419360816478729, "learning_rate": 9.95170994543636e-06, "loss": 0.2267, "step": 4792 }, { "epoch": 0.13991709481550677, "grad_norm": 0.39080923795700073, "learning_rate": 9.95163927918136e-06, "loss": 0.2637, "step": 4793 }, { "epoch": 0.13994628678187762, "grad_norm": 0.3610988259315491, "learning_rate": 9.951568561509956e-06, "loss": 0.2731, "step": 4794 }, { "epoch": 0.13997547874824848, "grad_norm": 0.40044257044792175, "learning_rate": 9.951497792422881e-06, "loss": 0.2636, "step": 4795 }, { "epoch": 0.14000467071461933, "grad_norm": 0.4083639085292816, "learning_rate": 9.951426971920873e-06, "loss": 0.277, "step": 4796 }, { "epoch": 0.1400338626809902, "grad_norm": 0.37336495518684387, "learning_rate": 9.951356100004666e-06, "loss": 0.2607, "step": 4797 }, { "epoch": 0.14006305464736105, "grad_norm": 0.3719767928123474, "learning_rate": 9.951285176674996e-06, "loss": 0.2513, "step": 4798 }, { "epoch": 0.1400922466137319, "grad_norm": 0.4547104835510254, "learning_rate": 9.9512142019326e-06, "loss": 0.2353, "step": 4799 }, { "epoch": 0.14012143858010276, "grad_norm": 0.3291674554347992, "learning_rate": 9.951143175778213e-06, "loss": 0.2111, "step": 4800 }, { "epoch": 0.14015063054647361, "grad_norm": 0.3825451731681824, "learning_rate": 9.951072098212574e-06, "loss": 0.2471, "step": 4801 }, { "epoch": 0.14017982251284447, "grad_norm": 0.38111627101898193, "learning_rate": 9.951000969236422e-06, "loss": 0.2545, "step": 4802 }, { "epoch": 0.14020901447921533, "grad_norm": 0.42745816707611084, "learning_rate": 9.950929788850494e-06, "loss": 0.2282, "step": 4803 }, { "epoch": 0.14023820644558618, "grad_norm": 0.40939566493034363, "learning_rate": 9.95085855705553e-06, "loss": 0.2616, "step": 4804 }, { "epoch": 0.14026739841195704, "grad_norm": 0.43037837743759155, "learning_rate": 9.95078727385227e-06, "loss": 0.2805, "step": 4805 }, { "epoch": 0.1402965903783279, "grad_norm": 0.4057445526123047, "learning_rate": 9.950715939241452e-06, "loss": 0.2668, "step": 4806 }, { "epoch": 0.14032578234469875, "grad_norm": 0.4453458786010742, "learning_rate": 9.95064455322382e-06, "loss": 0.265, "step": 4807 }, { "epoch": 0.14035497431106958, "grad_norm": 0.4092943072319031, "learning_rate": 9.950573115800112e-06, "loss": 0.2377, "step": 4808 }, { "epoch": 0.14038416627744044, "grad_norm": 0.387202650308609, "learning_rate": 9.950501626971072e-06, "loss": 0.2528, "step": 4809 }, { "epoch": 0.1404133582438113, "grad_norm": 0.43262815475463867, "learning_rate": 9.95043008673744e-06, "loss": 0.2273, "step": 4810 }, { "epoch": 0.14044255021018215, "grad_norm": 0.37377744913101196, "learning_rate": 9.950358495099962e-06, "loss": 0.2094, "step": 4811 }, { "epoch": 0.140471742176553, "grad_norm": 0.3962045907974243, "learning_rate": 9.950286852059378e-06, "loss": 0.2807, "step": 4812 }, { "epoch": 0.14050093414292386, "grad_norm": 0.3215886652469635, "learning_rate": 9.950215157616436e-06, "loss": 0.2064, "step": 4813 }, { "epoch": 0.14053012610929472, "grad_norm": 0.4455301761627197, "learning_rate": 9.950143411771878e-06, "loss": 0.2873, "step": 4814 }, { "epoch": 0.14055931807566557, "grad_norm": 0.3539147973060608, "learning_rate": 9.95007161452645e-06, "loss": 0.2526, "step": 4815 }, { "epoch": 0.14058851004203643, "grad_norm": 0.37260329723358154, "learning_rate": 9.949999765880893e-06, "loss": 0.2679, "step": 4816 }, { "epoch": 0.14061770200840729, "grad_norm": 0.4558771252632141, "learning_rate": 9.94992786583596e-06, "loss": 0.2507, "step": 4817 }, { "epoch": 0.14064689397477814, "grad_norm": 0.4245336651802063, "learning_rate": 9.949855914392393e-06, "loss": 0.2796, "step": 4818 }, { "epoch": 0.140676085941149, "grad_norm": 0.45931416749954224, "learning_rate": 9.949783911550941e-06, "loss": 0.2268, "step": 4819 }, { "epoch": 0.14070527790751985, "grad_norm": 0.3717748820781708, "learning_rate": 9.949711857312352e-06, "loss": 0.2463, "step": 4820 }, { "epoch": 0.1407344698738907, "grad_norm": 0.3957374095916748, "learning_rate": 9.949639751677372e-06, "loss": 0.2238, "step": 4821 }, { "epoch": 0.14076366184026157, "grad_norm": 0.37740182876586914, "learning_rate": 9.94956759464675e-06, "loss": 0.2406, "step": 4822 }, { "epoch": 0.14079285380663242, "grad_norm": 0.4374162256717682, "learning_rate": 9.949495386221238e-06, "loss": 0.2589, "step": 4823 }, { "epoch": 0.14082204577300328, "grad_norm": 0.43180400133132935, "learning_rate": 9.949423126401584e-06, "loss": 0.2264, "step": 4824 }, { "epoch": 0.14085123773937414, "grad_norm": 0.4247807562351227, "learning_rate": 9.949350815188538e-06, "loss": 0.2763, "step": 4825 }, { "epoch": 0.140880429705745, "grad_norm": 0.7828430533409119, "learning_rate": 9.949278452582853e-06, "loss": 0.2582, "step": 4826 }, { "epoch": 0.14090962167211582, "grad_norm": 0.35469216108322144, "learning_rate": 9.949206038585276e-06, "loss": 0.2098, "step": 4827 }, { "epoch": 0.14093881363848668, "grad_norm": 0.3738017678260803, "learning_rate": 9.949133573196563e-06, "loss": 0.2436, "step": 4828 }, { "epoch": 0.14096800560485753, "grad_norm": 0.38851630687713623, "learning_rate": 9.949061056417466e-06, "loss": 0.2371, "step": 4829 }, { "epoch": 0.1409971975712284, "grad_norm": 0.3493488132953644, "learning_rate": 9.948988488248733e-06, "loss": 0.2276, "step": 4830 }, { "epoch": 0.14102638953759924, "grad_norm": 0.4595312178134918, "learning_rate": 9.948915868691127e-06, "loss": 0.2752, "step": 4831 }, { "epoch": 0.1410555815039701, "grad_norm": 0.3725138008594513, "learning_rate": 9.948843197745393e-06, "loss": 0.2578, "step": 4832 }, { "epoch": 0.14108477347034096, "grad_norm": 0.39733973145484924, "learning_rate": 9.94877047541229e-06, "loss": 0.2292, "step": 4833 }, { "epoch": 0.1411139654367118, "grad_norm": 0.35541772842407227, "learning_rate": 9.948697701692573e-06, "loss": 0.2197, "step": 4834 }, { "epoch": 0.14114315740308267, "grad_norm": 0.37191009521484375, "learning_rate": 9.948624876586996e-06, "loss": 0.2729, "step": 4835 }, { "epoch": 0.14117234936945353, "grad_norm": 0.3965570628643036, "learning_rate": 9.948552000096318e-06, "loss": 0.2144, "step": 4836 }, { "epoch": 0.14120154133582438, "grad_norm": 0.41843143105506897, "learning_rate": 9.948479072221292e-06, "loss": 0.3108, "step": 4837 }, { "epoch": 0.14123073330219524, "grad_norm": 0.422178715467453, "learning_rate": 9.948406092962678e-06, "loss": 0.2733, "step": 4838 }, { "epoch": 0.1412599252685661, "grad_norm": 0.41433295607566833, "learning_rate": 9.948333062321233e-06, "loss": 0.2362, "step": 4839 }, { "epoch": 0.14128911723493695, "grad_norm": 0.3399387001991272, "learning_rate": 9.948259980297717e-06, "loss": 0.2279, "step": 4840 }, { "epoch": 0.1413183092013078, "grad_norm": 0.4051925837993622, "learning_rate": 9.948186846892884e-06, "loss": 0.2643, "step": 4841 }, { "epoch": 0.14134750116767866, "grad_norm": 0.4461507797241211, "learning_rate": 9.948113662107499e-06, "loss": 0.218, "step": 4842 }, { "epoch": 0.14137669313404952, "grad_norm": 0.40581223368644714, "learning_rate": 9.948040425942318e-06, "loss": 0.2279, "step": 4843 }, { "epoch": 0.14140588510042038, "grad_norm": 0.3638444244861603, "learning_rate": 9.947967138398104e-06, "loss": 0.253, "step": 4844 }, { "epoch": 0.14143507706679123, "grad_norm": 0.3924025595188141, "learning_rate": 9.947893799475618e-06, "loss": 0.2944, "step": 4845 }, { "epoch": 0.14146426903316206, "grad_norm": 0.5579185485839844, "learning_rate": 9.94782040917562e-06, "loss": 0.2915, "step": 4846 }, { "epoch": 0.14149346099953292, "grad_norm": 0.40536537766456604, "learning_rate": 9.94774696749887e-06, "loss": 0.2448, "step": 4847 }, { "epoch": 0.14152265296590377, "grad_norm": 0.3673543334007263, "learning_rate": 9.947673474446136e-06, "loss": 0.2545, "step": 4848 }, { "epoch": 0.14155184493227463, "grad_norm": 0.5139771103858948, "learning_rate": 9.947599930018176e-06, "loss": 0.2541, "step": 4849 }, { "epoch": 0.14158103689864548, "grad_norm": 0.3600218892097473, "learning_rate": 9.947526334215757e-06, "loss": 0.2501, "step": 4850 }, { "epoch": 0.14161022886501634, "grad_norm": 0.37253454327583313, "learning_rate": 9.947452687039643e-06, "loss": 0.2443, "step": 4851 }, { "epoch": 0.1416394208313872, "grad_norm": 0.49261024594306946, "learning_rate": 9.947378988490598e-06, "loss": 0.2339, "step": 4852 }, { "epoch": 0.14166861279775805, "grad_norm": 0.3911925256252289, "learning_rate": 9.947305238569385e-06, "loss": 0.2258, "step": 4853 }, { "epoch": 0.1416978047641289, "grad_norm": 0.3739619553089142, "learning_rate": 9.947231437276775e-06, "loss": 0.2155, "step": 4854 }, { "epoch": 0.14172699673049977, "grad_norm": 0.3836933374404907, "learning_rate": 9.947157584613529e-06, "loss": 0.2295, "step": 4855 }, { "epoch": 0.14175618869687062, "grad_norm": 0.3921583294868469, "learning_rate": 9.947083680580418e-06, "loss": 0.2519, "step": 4856 }, { "epoch": 0.14178538066324148, "grad_norm": 0.3530096113681793, "learning_rate": 9.947009725178204e-06, "loss": 0.2321, "step": 4857 }, { "epoch": 0.14181457262961233, "grad_norm": 0.45712143182754517, "learning_rate": 9.946935718407662e-06, "loss": 0.2608, "step": 4858 }, { "epoch": 0.1418437645959832, "grad_norm": 0.6874825358390808, "learning_rate": 9.946861660269556e-06, "loss": 0.2259, "step": 4859 }, { "epoch": 0.14187295656235405, "grad_norm": 0.5035957098007202, "learning_rate": 9.946787550764657e-06, "loss": 0.2929, "step": 4860 }, { "epoch": 0.1419021485287249, "grad_norm": 0.4069996178150177, "learning_rate": 9.946713389893733e-06, "loss": 0.2791, "step": 4861 }, { "epoch": 0.14193134049509576, "grad_norm": 0.5622721314430237, "learning_rate": 9.946639177657552e-06, "loss": 0.2547, "step": 4862 }, { "epoch": 0.14196053246146662, "grad_norm": 0.4019271731376648, "learning_rate": 9.94656491405689e-06, "loss": 0.2717, "step": 4863 }, { "epoch": 0.14198972442783747, "grad_norm": 0.4304873049259186, "learning_rate": 9.946490599092514e-06, "loss": 0.2918, "step": 4864 }, { "epoch": 0.14201891639420833, "grad_norm": 0.4984290897846222, "learning_rate": 9.946416232765197e-06, "loss": 0.2129, "step": 4865 }, { "epoch": 0.14204810836057916, "grad_norm": 0.4010401964187622, "learning_rate": 9.946341815075711e-06, "loss": 0.2612, "step": 4866 }, { "epoch": 0.14207730032695, "grad_norm": 0.426366925239563, "learning_rate": 9.946267346024829e-06, "loss": 0.2287, "step": 4867 }, { "epoch": 0.14210649229332087, "grad_norm": 0.5321485996246338, "learning_rate": 9.946192825613325e-06, "loss": 0.2546, "step": 4868 }, { "epoch": 0.14213568425969172, "grad_norm": 0.4487319588661194, "learning_rate": 9.946118253841971e-06, "loss": 0.2631, "step": 4869 }, { "epoch": 0.14216487622606258, "grad_norm": 0.5464597940444946, "learning_rate": 9.946043630711543e-06, "loss": 0.2412, "step": 4870 }, { "epoch": 0.14219406819243344, "grad_norm": 0.7327926158905029, "learning_rate": 9.945968956222814e-06, "loss": 0.2565, "step": 4871 }, { "epoch": 0.1422232601588043, "grad_norm": 0.4124886691570282, "learning_rate": 9.94589423037656e-06, "loss": 0.2913, "step": 4872 }, { "epoch": 0.14225245212517515, "grad_norm": 0.5164397954940796, "learning_rate": 9.945819453173561e-06, "loss": 0.2972, "step": 4873 }, { "epoch": 0.142281644091546, "grad_norm": 0.37150195240974426, "learning_rate": 9.945744624614588e-06, "loss": 0.2507, "step": 4874 }, { "epoch": 0.14231083605791686, "grad_norm": 0.41897186636924744, "learning_rate": 9.945669744700419e-06, "loss": 0.2174, "step": 4875 }, { "epoch": 0.14234002802428772, "grad_norm": 0.4270067512989044, "learning_rate": 9.945594813431833e-06, "loss": 0.2446, "step": 4876 }, { "epoch": 0.14236921999065857, "grad_norm": 0.4045505225658417, "learning_rate": 9.945519830809607e-06, "loss": 0.2394, "step": 4877 }, { "epoch": 0.14239841195702943, "grad_norm": 0.8531526923179626, "learning_rate": 9.94544479683452e-06, "loss": 0.237, "step": 4878 }, { "epoch": 0.1424276039234003, "grad_norm": 0.4569952189922333, "learning_rate": 9.945369711507354e-06, "loss": 0.2536, "step": 4879 }, { "epoch": 0.14245679588977114, "grad_norm": 0.4558291733264923, "learning_rate": 9.945294574828884e-06, "loss": 0.2925, "step": 4880 }, { "epoch": 0.142485987856142, "grad_norm": 0.4167793095111847, "learning_rate": 9.945219386799892e-06, "loss": 0.2323, "step": 4881 }, { "epoch": 0.14251517982251286, "grad_norm": 0.4736234247684479, "learning_rate": 9.945144147421158e-06, "loss": 0.2917, "step": 4882 }, { "epoch": 0.1425443717888837, "grad_norm": 0.38078293204307556, "learning_rate": 9.945068856693465e-06, "loss": 0.2427, "step": 4883 }, { "epoch": 0.14257356375525457, "grad_norm": 0.3214586079120636, "learning_rate": 9.944993514617594e-06, "loss": 0.1713, "step": 4884 }, { "epoch": 0.1426027557216254, "grad_norm": 0.48616448044776917, "learning_rate": 9.944918121194327e-06, "loss": 0.2735, "step": 4885 }, { "epoch": 0.14263194768799625, "grad_norm": 0.49444836378097534, "learning_rate": 9.944842676424447e-06, "loss": 0.2701, "step": 4886 }, { "epoch": 0.1426611396543671, "grad_norm": 0.5130218267440796, "learning_rate": 9.944767180308738e-06, "loss": 0.2602, "step": 4887 }, { "epoch": 0.14269033162073796, "grad_norm": 0.605202853679657, "learning_rate": 9.944691632847983e-06, "loss": 0.3112, "step": 4888 }, { "epoch": 0.14271952358710882, "grad_norm": 0.7027443647384644, "learning_rate": 9.944616034042966e-06, "loss": 0.2219, "step": 4889 }, { "epoch": 0.14274871555347968, "grad_norm": 0.7129645943641663, "learning_rate": 9.944540383894473e-06, "loss": 0.2364, "step": 4890 }, { "epoch": 0.14277790751985053, "grad_norm": 0.8875835537910461, "learning_rate": 9.944464682403293e-06, "loss": 0.2906, "step": 4891 }, { "epoch": 0.1428070994862214, "grad_norm": 0.44805091619491577, "learning_rate": 9.944388929570206e-06, "loss": 0.258, "step": 4892 }, { "epoch": 0.14283629145259225, "grad_norm": 0.49941331148147583, "learning_rate": 9.944313125396e-06, "loss": 0.2934, "step": 4893 }, { "epoch": 0.1428654834189631, "grad_norm": 0.38712477684020996, "learning_rate": 9.944237269881465e-06, "loss": 0.2483, "step": 4894 }, { "epoch": 0.14289467538533396, "grad_norm": 0.511820375919342, "learning_rate": 9.944161363027385e-06, "loss": 0.2352, "step": 4895 }, { "epoch": 0.14292386735170481, "grad_norm": 0.45626717805862427, "learning_rate": 9.944085404834551e-06, "loss": 0.2584, "step": 4896 }, { "epoch": 0.14295305931807567, "grad_norm": 0.4356173872947693, "learning_rate": 9.94400939530375e-06, "loss": 0.2786, "step": 4897 }, { "epoch": 0.14298225128444653, "grad_norm": 0.40379005670547485, "learning_rate": 9.943933334435774e-06, "loss": 0.2423, "step": 4898 }, { "epoch": 0.14301144325081738, "grad_norm": 0.7887982726097107, "learning_rate": 9.94385722223141e-06, "loss": 0.2433, "step": 4899 }, { "epoch": 0.14304063521718824, "grad_norm": 0.4299602806568146, "learning_rate": 9.94378105869145e-06, "loss": 0.2408, "step": 4900 }, { "epoch": 0.1430698271835591, "grad_norm": 0.4796057641506195, "learning_rate": 9.943704843816682e-06, "loss": 0.2182, "step": 4901 }, { "epoch": 0.14309901914992995, "grad_norm": 0.3989028036594391, "learning_rate": 9.9436285776079e-06, "loss": 0.2048, "step": 4902 }, { "epoch": 0.1431282111163008, "grad_norm": 0.41238299012184143, "learning_rate": 9.943552260065896e-06, "loss": 0.2257, "step": 4903 }, { "epoch": 0.14315740308267164, "grad_norm": 0.42095068097114563, "learning_rate": 9.94347589119146e-06, "loss": 0.2762, "step": 4904 }, { "epoch": 0.1431865950490425, "grad_norm": 0.3736395537853241, "learning_rate": 9.94339947098539e-06, "loss": 0.2385, "step": 4905 }, { "epoch": 0.14321578701541335, "grad_norm": 0.38113296031951904, "learning_rate": 9.943322999448475e-06, "loss": 0.2033, "step": 4906 }, { "epoch": 0.1432449789817842, "grad_norm": 0.3987865746021271, "learning_rate": 9.94324647658151e-06, "loss": 0.2372, "step": 4907 }, { "epoch": 0.14327417094815506, "grad_norm": 0.424444317817688, "learning_rate": 9.94316990238529e-06, "loss": 0.2594, "step": 4908 }, { "epoch": 0.14330336291452592, "grad_norm": 0.36995676159858704, "learning_rate": 9.94309327686061e-06, "loss": 0.2297, "step": 4909 }, { "epoch": 0.14333255488089677, "grad_norm": 0.42391839623451233, "learning_rate": 9.943016600008267e-06, "loss": 0.2244, "step": 4910 }, { "epoch": 0.14336174684726763, "grad_norm": 0.44658055901527405, "learning_rate": 9.942939871829053e-06, "loss": 0.2409, "step": 4911 }, { "epoch": 0.14339093881363849, "grad_norm": 0.39818644523620605, "learning_rate": 9.942863092323772e-06, "loss": 0.2101, "step": 4912 }, { "epoch": 0.14342013078000934, "grad_norm": 0.46175214648246765, "learning_rate": 9.942786261493214e-06, "loss": 0.2578, "step": 4913 }, { "epoch": 0.1434493227463802, "grad_norm": 0.3728830814361572, "learning_rate": 9.94270937933818e-06, "loss": 0.2278, "step": 4914 }, { "epoch": 0.14347851471275105, "grad_norm": 0.524810791015625, "learning_rate": 9.942632445859468e-06, "loss": 0.2039, "step": 4915 }, { "epoch": 0.1435077066791219, "grad_norm": 0.442234605550766, "learning_rate": 9.942555461057877e-06, "loss": 0.2921, "step": 4916 }, { "epoch": 0.14353689864549277, "grad_norm": 0.41893452405929565, "learning_rate": 9.942478424934207e-06, "loss": 0.2532, "step": 4917 }, { "epoch": 0.14356609061186362, "grad_norm": 0.38092902302742004, "learning_rate": 9.942401337489256e-06, "loss": 0.259, "step": 4918 }, { "epoch": 0.14359528257823448, "grad_norm": 0.5821654200553894, "learning_rate": 9.942324198723826e-06, "loss": 0.2913, "step": 4919 }, { "epoch": 0.14362447454460534, "grad_norm": 0.43063339591026306, "learning_rate": 9.94224700863872e-06, "loss": 0.2752, "step": 4920 }, { "epoch": 0.1436536665109762, "grad_norm": 0.6724597215652466, "learning_rate": 9.942169767234734e-06, "loss": 0.3086, "step": 4921 }, { "epoch": 0.14368285847734705, "grad_norm": 0.7377572059631348, "learning_rate": 9.942092474512674e-06, "loss": 0.2607, "step": 4922 }, { "epoch": 0.14371205044371788, "grad_norm": 0.6040372252464294, "learning_rate": 9.942015130473342e-06, "loss": 0.2532, "step": 4923 }, { "epoch": 0.14374124241008873, "grad_norm": 0.47590282559394836, "learning_rate": 9.941937735117542e-06, "loss": 0.2622, "step": 4924 }, { "epoch": 0.1437704343764596, "grad_norm": 0.4564136564731598, "learning_rate": 9.941860288446075e-06, "loss": 0.2729, "step": 4925 }, { "epoch": 0.14379962634283044, "grad_norm": 0.5147197246551514, "learning_rate": 9.941782790459748e-06, "loss": 0.2329, "step": 4926 }, { "epoch": 0.1438288183092013, "grad_norm": 0.35893139243125916, "learning_rate": 9.941705241159364e-06, "loss": 0.2527, "step": 4927 }, { "epoch": 0.14385801027557216, "grad_norm": 0.4816329777240753, "learning_rate": 9.941627640545727e-06, "loss": 0.2457, "step": 4928 }, { "epoch": 0.143887202241943, "grad_norm": 0.5187225937843323, "learning_rate": 9.941549988619648e-06, "loss": 0.2614, "step": 4929 }, { "epoch": 0.14391639420831387, "grad_norm": 0.34769007563591003, "learning_rate": 9.941472285381929e-06, "loss": 0.208, "step": 4930 }, { "epoch": 0.14394558617468473, "grad_norm": 0.3944368362426758, "learning_rate": 9.941394530833374e-06, "loss": 0.2762, "step": 4931 }, { "epoch": 0.14397477814105558, "grad_norm": 0.4265860915184021, "learning_rate": 9.9413167249748e-06, "loss": 0.2412, "step": 4932 }, { "epoch": 0.14400397010742644, "grad_norm": 0.3902556896209717, "learning_rate": 9.941238867807004e-06, "loss": 0.2737, "step": 4933 }, { "epoch": 0.1440331620737973, "grad_norm": 0.44846877455711365, "learning_rate": 9.941160959330801e-06, "loss": 0.3264, "step": 4934 }, { "epoch": 0.14406235404016815, "grad_norm": 0.4350963532924652, "learning_rate": 9.941082999546999e-06, "loss": 0.3023, "step": 4935 }, { "epoch": 0.144091546006539, "grad_norm": 0.4021434187889099, "learning_rate": 9.941004988456407e-06, "loss": 0.2538, "step": 4936 }, { "epoch": 0.14412073797290986, "grad_norm": 0.45092350244522095, "learning_rate": 9.940926926059833e-06, "loss": 0.2535, "step": 4937 }, { "epoch": 0.14414992993928072, "grad_norm": 0.5310030579566956, "learning_rate": 9.940848812358093e-06, "loss": 0.287, "step": 4938 }, { "epoch": 0.14417912190565157, "grad_norm": 0.46468523144721985, "learning_rate": 9.940770647351992e-06, "loss": 0.2408, "step": 4939 }, { "epoch": 0.14420831387202243, "grad_norm": 0.39071783423423767, "learning_rate": 9.940692431042345e-06, "loss": 0.2747, "step": 4940 }, { "epoch": 0.1442375058383933, "grad_norm": 0.5375117659568787, "learning_rate": 9.940614163429963e-06, "loss": 0.2894, "step": 4941 }, { "epoch": 0.14426669780476412, "grad_norm": 0.3793441653251648, "learning_rate": 9.94053584451566e-06, "loss": 0.2092, "step": 4942 }, { "epoch": 0.14429588977113497, "grad_norm": 0.4409846365451813, "learning_rate": 9.940457474300247e-06, "loss": 0.2808, "step": 4943 }, { "epoch": 0.14432508173750583, "grad_norm": 0.35748282074928284, "learning_rate": 9.94037905278454e-06, "loss": 0.2137, "step": 4944 }, { "epoch": 0.14435427370387668, "grad_norm": 0.45179253816604614, "learning_rate": 9.940300579969353e-06, "loss": 0.3311, "step": 4945 }, { "epoch": 0.14438346567024754, "grad_norm": 0.3559894859790802, "learning_rate": 9.9402220558555e-06, "loss": 0.2579, "step": 4946 }, { "epoch": 0.1444126576366184, "grad_norm": 0.3469238877296448, "learning_rate": 9.940143480443795e-06, "loss": 0.2934, "step": 4947 }, { "epoch": 0.14444184960298925, "grad_norm": 0.41461145877838135, "learning_rate": 9.940064853735058e-06, "loss": 0.2728, "step": 4948 }, { "epoch": 0.1444710415693601, "grad_norm": 0.43460196256637573, "learning_rate": 9.939986175730103e-06, "loss": 0.2808, "step": 4949 }, { "epoch": 0.14450023353573097, "grad_norm": 0.35954728722572327, "learning_rate": 9.939907446429747e-06, "loss": 0.2437, "step": 4950 }, { "epoch": 0.14452942550210182, "grad_norm": 0.3986732065677643, "learning_rate": 9.939828665834806e-06, "loss": 0.2571, "step": 4951 }, { "epoch": 0.14455861746847268, "grad_norm": 0.5614725351333618, "learning_rate": 9.9397498339461e-06, "loss": 0.2429, "step": 4952 }, { "epoch": 0.14458780943484353, "grad_norm": 0.43551895022392273, "learning_rate": 9.939670950764448e-06, "loss": 0.2906, "step": 4953 }, { "epoch": 0.1446170014012144, "grad_norm": 0.4159441292285919, "learning_rate": 9.939592016290668e-06, "loss": 0.233, "step": 4954 }, { "epoch": 0.14464619336758525, "grad_norm": 0.4262577295303345, "learning_rate": 9.93951303052558e-06, "loss": 0.2325, "step": 4955 }, { "epoch": 0.1446753853339561, "grad_norm": 0.33492186665534973, "learning_rate": 9.939433993470003e-06, "loss": 0.2115, "step": 4956 }, { "epoch": 0.14470457730032696, "grad_norm": 0.5052191615104675, "learning_rate": 9.939354905124758e-06, "loss": 0.2643, "step": 4957 }, { "epoch": 0.14473376926669781, "grad_norm": 0.3891700506210327, "learning_rate": 9.939275765490671e-06, "loss": 0.2481, "step": 4958 }, { "epoch": 0.14476296123306867, "grad_norm": 0.5467826724052429, "learning_rate": 9.939196574568554e-06, "loss": 0.1979, "step": 4959 }, { "epoch": 0.14479215319943953, "grad_norm": 0.5188420414924622, "learning_rate": 9.93911733235924e-06, "loss": 0.2465, "step": 4960 }, { "epoch": 0.14482134516581036, "grad_norm": 0.4336364269256592, "learning_rate": 9.939038038863545e-06, "loss": 0.2773, "step": 4961 }, { "epoch": 0.1448505371321812, "grad_norm": 0.35401207208633423, "learning_rate": 9.938958694082293e-06, "loss": 0.2119, "step": 4962 }, { "epoch": 0.14487972909855207, "grad_norm": 0.45189905166625977, "learning_rate": 9.938879298016311e-06, "loss": 0.2871, "step": 4963 }, { "epoch": 0.14490892106492292, "grad_norm": 0.43551790714263916, "learning_rate": 9.93879985066642e-06, "loss": 0.2126, "step": 4964 }, { "epoch": 0.14493811303129378, "grad_norm": 0.37972432374954224, "learning_rate": 9.938720352033447e-06, "loss": 0.2432, "step": 4965 }, { "epoch": 0.14496730499766464, "grad_norm": 0.3676701784133911, "learning_rate": 9.938640802118217e-06, "loss": 0.2501, "step": 4966 }, { "epoch": 0.1449964969640355, "grad_norm": 0.347257137298584, "learning_rate": 9.938561200921556e-06, "loss": 0.2058, "step": 4967 }, { "epoch": 0.14502568893040635, "grad_norm": 0.3374768793582916, "learning_rate": 9.93848154844429e-06, "loss": 0.2138, "step": 4968 }, { "epoch": 0.1450548808967772, "grad_norm": 0.40459367632865906, "learning_rate": 9.938401844687248e-06, "loss": 0.2543, "step": 4969 }, { "epoch": 0.14508407286314806, "grad_norm": 0.4410305917263031, "learning_rate": 9.938322089651256e-06, "loss": 0.2945, "step": 4970 }, { "epoch": 0.14511326482951892, "grad_norm": 0.4243561625480652, "learning_rate": 9.938242283337141e-06, "loss": 0.2632, "step": 4971 }, { "epoch": 0.14514245679588977, "grad_norm": 0.41728833317756653, "learning_rate": 9.938162425745734e-06, "loss": 0.2806, "step": 4972 }, { "epoch": 0.14517164876226063, "grad_norm": 0.44934046268463135, "learning_rate": 9.938082516877863e-06, "loss": 0.2575, "step": 4973 }, { "epoch": 0.1452008407286315, "grad_norm": 0.38984814286231995, "learning_rate": 9.938002556734359e-06, "loss": 0.2398, "step": 4974 }, { "epoch": 0.14523003269500234, "grad_norm": 0.6288592219352722, "learning_rate": 9.93792254531605e-06, "loss": 0.2157, "step": 4975 }, { "epoch": 0.1452592246613732, "grad_norm": 0.34940651059150696, "learning_rate": 9.937842482623769e-06, "loss": 0.1873, "step": 4976 }, { "epoch": 0.14528841662774405, "grad_norm": 0.32704252004623413, "learning_rate": 9.937762368658345e-06, "loss": 0.2177, "step": 4977 }, { "epoch": 0.1453176085941149, "grad_norm": 0.37418332695961, "learning_rate": 9.937682203420613e-06, "loss": 0.2447, "step": 4978 }, { "epoch": 0.14534680056048577, "grad_norm": 0.39398935437202454, "learning_rate": 9.937601986911405e-06, "loss": 0.2188, "step": 4979 }, { "epoch": 0.1453759925268566, "grad_norm": 0.3801549971103668, "learning_rate": 9.937521719131552e-06, "loss": 0.2861, "step": 4980 }, { "epoch": 0.14540518449322745, "grad_norm": 0.3545917272567749, "learning_rate": 9.937441400081887e-06, "loss": 0.2128, "step": 4981 }, { "epoch": 0.1454343764595983, "grad_norm": 0.4575676918029785, "learning_rate": 9.937361029763244e-06, "loss": 0.2605, "step": 4982 }, { "epoch": 0.14546356842596916, "grad_norm": 0.4133227467536926, "learning_rate": 9.93728060817646e-06, "loss": 0.2538, "step": 4983 }, { "epoch": 0.14549276039234002, "grad_norm": 0.4187399744987488, "learning_rate": 9.937200135322372e-06, "loss": 0.2127, "step": 4984 }, { "epoch": 0.14552195235871088, "grad_norm": 0.6196569204330444, "learning_rate": 9.93711961120181e-06, "loss": 0.2416, "step": 4985 }, { "epoch": 0.14555114432508173, "grad_norm": 0.4143854081630707, "learning_rate": 9.93703903581561e-06, "loss": 0.2509, "step": 4986 }, { "epoch": 0.1455803362914526, "grad_norm": 0.4238686263561249, "learning_rate": 9.936958409164615e-06, "loss": 0.2676, "step": 4987 }, { "epoch": 0.14560952825782345, "grad_norm": 1.4881335496902466, "learning_rate": 9.936877731249657e-06, "loss": 0.2159, "step": 4988 }, { "epoch": 0.1456387202241943, "grad_norm": 0.5691080093383789, "learning_rate": 9.936797002071575e-06, "loss": 0.3035, "step": 4989 }, { "epoch": 0.14566791219056516, "grad_norm": 0.4527413249015808, "learning_rate": 9.936716221631208e-06, "loss": 0.2618, "step": 4990 }, { "epoch": 0.145697104156936, "grad_norm": 0.5284292101860046, "learning_rate": 9.936635389929394e-06, "loss": 0.2179, "step": 4991 }, { "epoch": 0.14572629612330687, "grad_norm": 0.4679323136806488, "learning_rate": 9.936554506966973e-06, "loss": 0.2668, "step": 4992 }, { "epoch": 0.14575548808967773, "grad_norm": 0.41999351978302, "learning_rate": 9.936473572744783e-06, "loss": 0.278, "step": 4993 }, { "epoch": 0.14578468005604858, "grad_norm": 0.3843294680118561, "learning_rate": 9.936392587263668e-06, "loss": 0.2895, "step": 4994 }, { "epoch": 0.14581387202241944, "grad_norm": 0.3681362569332123, "learning_rate": 9.936311550524465e-06, "loss": 0.2357, "step": 4995 }, { "epoch": 0.1458430639887903, "grad_norm": 0.42265889048576355, "learning_rate": 9.936230462528018e-06, "loss": 0.2409, "step": 4996 }, { "epoch": 0.14587225595516115, "grad_norm": 0.6522837281227112, "learning_rate": 9.93614932327517e-06, "loss": 0.206, "step": 4997 }, { "epoch": 0.145901447921532, "grad_norm": 0.460858017206192, "learning_rate": 9.93606813276676e-06, "loss": 0.2537, "step": 4998 }, { "epoch": 0.14593063988790284, "grad_norm": 0.5316898822784424, "learning_rate": 9.935986891003633e-06, "loss": 0.2995, "step": 4999 }, { "epoch": 0.1459598318542737, "grad_norm": 0.4274997413158417, "learning_rate": 9.935905597986632e-06, "loss": 0.2417, "step": 5000 }, { "epoch": 0.14598902382064455, "grad_norm": 0.42341604828834534, "learning_rate": 9.935824253716601e-06, "loss": 0.2885, "step": 5001 }, { "epoch": 0.1460182157870154, "grad_norm": 0.432117223739624, "learning_rate": 9.935742858194389e-06, "loss": 0.2732, "step": 5002 }, { "epoch": 0.14604740775338626, "grad_norm": 0.3396936058998108, "learning_rate": 9.935661411420833e-06, "loss": 0.196, "step": 5003 }, { "epoch": 0.14607659971975712, "grad_norm": 0.367838591337204, "learning_rate": 9.935579913396784e-06, "loss": 0.2503, "step": 5004 }, { "epoch": 0.14610579168612797, "grad_norm": 0.45683643221855164, "learning_rate": 9.935498364123089e-06, "loss": 0.2343, "step": 5005 }, { "epoch": 0.14613498365249883, "grad_norm": 0.4445328712463379, "learning_rate": 9.935416763600593e-06, "loss": 0.2484, "step": 5006 }, { "epoch": 0.14616417561886969, "grad_norm": 0.43286412954330444, "learning_rate": 9.935335111830142e-06, "loss": 0.2598, "step": 5007 }, { "epoch": 0.14619336758524054, "grad_norm": 0.5093827247619629, "learning_rate": 9.935253408812586e-06, "loss": 0.3035, "step": 5008 }, { "epoch": 0.1462225595516114, "grad_norm": 0.39046943187713623, "learning_rate": 9.935171654548772e-06, "loss": 0.2573, "step": 5009 }, { "epoch": 0.14625175151798225, "grad_norm": 0.6186717748641968, "learning_rate": 9.935089849039552e-06, "loss": 0.2578, "step": 5010 }, { "epoch": 0.1462809434843531, "grad_norm": 1.6768556833267212, "learning_rate": 9.935007992285772e-06, "loss": 0.2723, "step": 5011 }, { "epoch": 0.14631013545072397, "grad_norm": 0.5625061988830566, "learning_rate": 9.93492608428828e-06, "loss": 0.2974, "step": 5012 }, { "epoch": 0.14633932741709482, "grad_norm": 0.4240890145301819, "learning_rate": 9.934844125047934e-06, "loss": 0.221, "step": 5013 }, { "epoch": 0.14636851938346568, "grad_norm": 0.4965384900569916, "learning_rate": 9.93476211456558e-06, "loss": 0.2203, "step": 5014 }, { "epoch": 0.14639771134983653, "grad_norm": 0.6307656168937683, "learning_rate": 9.934680052842068e-06, "loss": 0.2642, "step": 5015 }, { "epoch": 0.1464269033162074, "grad_norm": 0.5342821478843689, "learning_rate": 9.934597939878253e-06, "loss": 0.2607, "step": 5016 }, { "epoch": 0.14645609528257825, "grad_norm": 0.7710077166557312, "learning_rate": 9.934515775674986e-06, "loss": 0.2277, "step": 5017 }, { "epoch": 0.14648528724894908, "grad_norm": 0.45092928409576416, "learning_rate": 9.934433560233124e-06, "loss": 0.2217, "step": 5018 }, { "epoch": 0.14651447921531993, "grad_norm": 0.5656265020370483, "learning_rate": 9.934351293553515e-06, "loss": 0.2595, "step": 5019 }, { "epoch": 0.1465436711816908, "grad_norm": 0.35254600644111633, "learning_rate": 9.934268975637018e-06, "loss": 0.235, "step": 5020 }, { "epoch": 0.14657286314806164, "grad_norm": 0.41142454743385315, "learning_rate": 9.934186606484485e-06, "loss": 0.2673, "step": 5021 }, { "epoch": 0.1466020551144325, "grad_norm": 0.4195197820663452, "learning_rate": 9.934104186096772e-06, "loss": 0.3087, "step": 5022 }, { "epoch": 0.14663124708080336, "grad_norm": 0.6674725413322449, "learning_rate": 9.934021714474733e-06, "loss": 0.2536, "step": 5023 }, { "epoch": 0.1466604390471742, "grad_norm": 0.810923159122467, "learning_rate": 9.933939191619229e-06, "loss": 0.235, "step": 5024 }, { "epoch": 0.14668963101354507, "grad_norm": 0.3489001989364624, "learning_rate": 9.933856617531113e-06, "loss": 0.2347, "step": 5025 }, { "epoch": 0.14671882297991592, "grad_norm": 0.6447708606719971, "learning_rate": 9.933773992211243e-06, "loss": 0.2546, "step": 5026 }, { "epoch": 0.14674801494628678, "grad_norm": 0.4861018657684326, "learning_rate": 9.933691315660478e-06, "loss": 0.2691, "step": 5027 }, { "epoch": 0.14677720691265764, "grad_norm": 0.439953088760376, "learning_rate": 9.933608587879678e-06, "loss": 0.227, "step": 5028 }, { "epoch": 0.1468063988790285, "grad_norm": 0.3982437551021576, "learning_rate": 9.933525808869697e-06, "loss": 0.2499, "step": 5029 }, { "epoch": 0.14683559084539935, "grad_norm": 0.5197150111198425, "learning_rate": 9.9334429786314e-06, "loss": 0.2481, "step": 5030 }, { "epoch": 0.1468647828117702, "grad_norm": 0.4120342433452606, "learning_rate": 9.933360097165642e-06, "loss": 0.2554, "step": 5031 }, { "epoch": 0.14689397477814106, "grad_norm": 0.394611656665802, "learning_rate": 9.933277164473289e-06, "loss": 0.2638, "step": 5032 }, { "epoch": 0.14692316674451192, "grad_norm": 0.39793604612350464, "learning_rate": 9.933194180555198e-06, "loss": 0.3314, "step": 5033 }, { "epoch": 0.14695235871088277, "grad_norm": 0.34572604298591614, "learning_rate": 9.933111145412233e-06, "loss": 0.1981, "step": 5034 }, { "epoch": 0.14698155067725363, "grad_norm": 0.4969882667064667, "learning_rate": 9.933028059045255e-06, "loss": 0.2696, "step": 5035 }, { "epoch": 0.1470107426436245, "grad_norm": 0.7815942168235779, "learning_rate": 9.932944921455127e-06, "loss": 0.2454, "step": 5036 }, { "epoch": 0.14703993460999534, "grad_norm": 0.3977139890193939, "learning_rate": 9.932861732642714e-06, "loss": 0.2971, "step": 5037 }, { "epoch": 0.14706912657636617, "grad_norm": 0.4265452027320862, "learning_rate": 9.932778492608876e-06, "loss": 0.2147, "step": 5038 }, { "epoch": 0.14709831854273703, "grad_norm": 0.3232441842556, "learning_rate": 9.93269520135448e-06, "loss": 0.201, "step": 5039 }, { "epoch": 0.14712751050910788, "grad_norm": 0.4359668791294098, "learning_rate": 9.932611858880389e-06, "loss": 0.2704, "step": 5040 }, { "epoch": 0.14715670247547874, "grad_norm": 0.4998583495616913, "learning_rate": 9.932528465187473e-06, "loss": 0.2109, "step": 5041 }, { "epoch": 0.1471858944418496, "grad_norm": 0.3911781311035156, "learning_rate": 9.932445020276593e-06, "loss": 0.2719, "step": 5042 }, { "epoch": 0.14721508640822045, "grad_norm": 0.3940594792366028, "learning_rate": 9.932361524148618e-06, "loss": 0.2997, "step": 5043 }, { "epoch": 0.1472442783745913, "grad_norm": 0.4399801790714264, "learning_rate": 9.932277976804412e-06, "loss": 0.311, "step": 5044 }, { "epoch": 0.14727347034096216, "grad_norm": 0.3847845196723938, "learning_rate": 9.932194378244848e-06, "loss": 0.2427, "step": 5045 }, { "epoch": 0.14730266230733302, "grad_norm": 0.33743607997894287, "learning_rate": 9.932110728470788e-06, "loss": 0.1795, "step": 5046 }, { "epoch": 0.14733185427370388, "grad_norm": 0.4976024031639099, "learning_rate": 9.932027027483105e-06, "loss": 0.2552, "step": 5047 }, { "epoch": 0.14736104624007473, "grad_norm": 0.39142319560050964, "learning_rate": 9.931943275282665e-06, "loss": 0.238, "step": 5048 }, { "epoch": 0.1473902382064456, "grad_norm": 0.449106365442276, "learning_rate": 9.93185947187034e-06, "loss": 0.273, "step": 5049 }, { "epoch": 0.14741943017281645, "grad_norm": 0.5749124884605408, "learning_rate": 9.931775617247e-06, "loss": 0.2288, "step": 5050 }, { "epoch": 0.1474486221391873, "grad_norm": 0.39237460494041443, "learning_rate": 9.931691711413517e-06, "loss": 0.2779, "step": 5051 }, { "epoch": 0.14747781410555816, "grad_norm": 0.42851248383522034, "learning_rate": 9.931607754370756e-06, "loss": 0.2216, "step": 5052 }, { "epoch": 0.14750700607192901, "grad_norm": 0.4170534908771515, "learning_rate": 9.931523746119596e-06, "loss": 0.2866, "step": 5053 }, { "epoch": 0.14753619803829987, "grad_norm": 0.3715314269065857, "learning_rate": 9.931439686660904e-06, "loss": 0.2545, "step": 5054 }, { "epoch": 0.14756539000467073, "grad_norm": 0.4190535247325897, "learning_rate": 9.931355575995558e-06, "loss": 0.2584, "step": 5055 }, { "epoch": 0.14759458197104158, "grad_norm": 0.41235658526420593, "learning_rate": 9.931271414124428e-06, "loss": 0.2574, "step": 5056 }, { "epoch": 0.1476237739374124, "grad_norm": 0.36005541682243347, "learning_rate": 9.931187201048388e-06, "loss": 0.2256, "step": 5057 }, { "epoch": 0.14765296590378327, "grad_norm": 0.3853895962238312, "learning_rate": 9.931102936768313e-06, "loss": 0.2825, "step": 5058 }, { "epoch": 0.14768215787015412, "grad_norm": 0.39605867862701416, "learning_rate": 9.931018621285078e-06, "loss": 0.2206, "step": 5059 }, { "epoch": 0.14771134983652498, "grad_norm": 0.37583962082862854, "learning_rate": 9.930934254599559e-06, "loss": 0.2498, "step": 5060 }, { "epoch": 0.14774054180289584, "grad_norm": 0.4089283049106598, "learning_rate": 9.930849836712632e-06, "loss": 0.2839, "step": 5061 }, { "epoch": 0.1477697337692667, "grad_norm": 0.3713255226612091, "learning_rate": 9.930765367625173e-06, "loss": 0.2225, "step": 5062 }, { "epoch": 0.14779892573563755, "grad_norm": 0.36979782581329346, "learning_rate": 9.930680847338059e-06, "loss": 0.2446, "step": 5063 }, { "epoch": 0.1478281177020084, "grad_norm": 0.36864909529685974, "learning_rate": 9.930596275852166e-06, "loss": 0.2474, "step": 5064 }, { "epoch": 0.14785730966837926, "grad_norm": 0.38187411427497864, "learning_rate": 9.930511653168377e-06, "loss": 0.2005, "step": 5065 }, { "epoch": 0.14788650163475012, "grad_norm": 0.40493765473365784, "learning_rate": 9.930426979287566e-06, "loss": 0.2598, "step": 5066 }, { "epoch": 0.14791569360112097, "grad_norm": 0.48335587978363037, "learning_rate": 9.930342254210614e-06, "loss": 0.2588, "step": 5067 }, { "epoch": 0.14794488556749183, "grad_norm": 0.35264357924461365, "learning_rate": 9.930257477938401e-06, "loss": 0.2507, "step": 5068 }, { "epoch": 0.14797407753386269, "grad_norm": 0.47822925448417664, "learning_rate": 9.930172650471808e-06, "loss": 0.3008, "step": 5069 }, { "epoch": 0.14800326950023354, "grad_norm": 0.3555532395839691, "learning_rate": 9.930087771811713e-06, "loss": 0.2347, "step": 5070 }, { "epoch": 0.1480324614666044, "grad_norm": 0.3398798108100891, "learning_rate": 9.930002841959002e-06, "loss": 0.2303, "step": 5071 }, { "epoch": 0.14806165343297525, "grad_norm": 0.48227638006210327, "learning_rate": 9.929917860914551e-06, "loss": 0.3055, "step": 5072 }, { "epoch": 0.1480908453993461, "grad_norm": 0.682944118976593, "learning_rate": 9.929832828679246e-06, "loss": 0.2827, "step": 5073 }, { "epoch": 0.14812003736571697, "grad_norm": 0.3399845063686371, "learning_rate": 9.92974774525397e-06, "loss": 0.2516, "step": 5074 }, { "epoch": 0.14814922933208782, "grad_norm": 0.3568129241466522, "learning_rate": 9.929662610639608e-06, "loss": 0.2691, "step": 5075 }, { "epoch": 0.14817842129845865, "grad_norm": 0.3382587432861328, "learning_rate": 9.92957742483704e-06, "loss": 0.2554, "step": 5076 }, { "epoch": 0.1482076132648295, "grad_norm": 0.35185810923576355, "learning_rate": 9.929492187847152e-06, "loss": 0.2434, "step": 5077 }, { "epoch": 0.14823680523120036, "grad_norm": 0.5042532086372375, "learning_rate": 9.92940689967083e-06, "loss": 0.2631, "step": 5078 }, { "epoch": 0.14826599719757122, "grad_norm": 0.33060041069984436, "learning_rate": 9.92932156030896e-06, "loss": 0.2013, "step": 5079 }, { "epoch": 0.14829518916394208, "grad_norm": 0.3692657947540283, "learning_rate": 9.929236169762426e-06, "loss": 0.2493, "step": 5080 }, { "epoch": 0.14832438113031293, "grad_norm": 0.3713465929031372, "learning_rate": 9.929150728032118e-06, "loss": 0.2621, "step": 5081 }, { "epoch": 0.1483535730966838, "grad_norm": 0.3460969626903534, "learning_rate": 9.92906523511892e-06, "loss": 0.2175, "step": 5082 }, { "epoch": 0.14838276506305464, "grad_norm": 0.3651723265647888, "learning_rate": 9.92897969102372e-06, "loss": 0.2193, "step": 5083 }, { "epoch": 0.1484119570294255, "grad_norm": 0.3898742198944092, "learning_rate": 9.928894095747408e-06, "loss": 0.2784, "step": 5084 }, { "epoch": 0.14844114899579636, "grad_norm": 0.38625019788742065, "learning_rate": 9.928808449290872e-06, "loss": 0.2421, "step": 5085 }, { "epoch": 0.1484703409621672, "grad_norm": 0.3716466724872589, "learning_rate": 9.928722751655002e-06, "loss": 0.2751, "step": 5086 }, { "epoch": 0.14849953292853807, "grad_norm": 0.34605562686920166, "learning_rate": 9.928637002840687e-06, "loss": 0.199, "step": 5087 }, { "epoch": 0.14852872489490893, "grad_norm": 0.5800227522850037, "learning_rate": 9.928551202848817e-06, "loss": 0.3183, "step": 5088 }, { "epoch": 0.14855791686127978, "grad_norm": 0.4119013845920563, "learning_rate": 9.928465351680283e-06, "loss": 0.2588, "step": 5089 }, { "epoch": 0.14858710882765064, "grad_norm": 0.5901175141334534, "learning_rate": 9.928379449335978e-06, "loss": 0.2753, "step": 5090 }, { "epoch": 0.1486163007940215, "grad_norm": 0.3746106028556824, "learning_rate": 9.928293495816792e-06, "loss": 0.2812, "step": 5091 }, { "epoch": 0.14864549276039235, "grad_norm": 0.3607243299484253, "learning_rate": 9.92820749112362e-06, "loss": 0.2547, "step": 5092 }, { "epoch": 0.1486746847267632, "grad_norm": 0.37335139513015747, "learning_rate": 9.928121435257351e-06, "loss": 0.2535, "step": 5093 }, { "epoch": 0.14870387669313406, "grad_norm": 0.38548675179481506, "learning_rate": 9.928035328218883e-06, "loss": 0.2821, "step": 5094 }, { "epoch": 0.1487330686595049, "grad_norm": 0.38741612434387207, "learning_rate": 9.927949170009109e-06, "loss": 0.2884, "step": 5095 }, { "epoch": 0.14876226062587575, "grad_norm": 0.3672422468662262, "learning_rate": 9.927862960628922e-06, "loss": 0.2758, "step": 5096 }, { "epoch": 0.1487914525922466, "grad_norm": 0.3540051579475403, "learning_rate": 9.927776700079217e-06, "loss": 0.3171, "step": 5097 }, { "epoch": 0.14882064455861746, "grad_norm": 0.4408262073993683, "learning_rate": 9.92769038836089e-06, "loss": 0.2454, "step": 5098 }, { "epoch": 0.14884983652498832, "grad_norm": 0.38738811016082764, "learning_rate": 9.92760402547484e-06, "loss": 0.2992, "step": 5099 }, { "epoch": 0.14887902849135917, "grad_norm": 0.37151995301246643, "learning_rate": 9.927517611421962e-06, "loss": 0.2606, "step": 5100 }, { "epoch": 0.14890822045773003, "grad_norm": 0.3680857717990875, "learning_rate": 9.92743114620315e-06, "loss": 0.2343, "step": 5101 }, { "epoch": 0.14893741242410088, "grad_norm": 0.3824848532676697, "learning_rate": 9.927344629819308e-06, "loss": 0.2747, "step": 5102 }, { "epoch": 0.14896660439047174, "grad_norm": 0.39480921626091003, "learning_rate": 9.92725806227133e-06, "loss": 0.2729, "step": 5103 }, { "epoch": 0.1489957963568426, "grad_norm": 0.40637508034706116, "learning_rate": 9.927171443560115e-06, "loss": 0.2481, "step": 5104 }, { "epoch": 0.14902498832321345, "grad_norm": 0.360921710729599, "learning_rate": 9.927084773686567e-06, "loss": 0.2378, "step": 5105 }, { "epoch": 0.1490541802895843, "grad_norm": 0.3976863622665405, "learning_rate": 9.92699805265158e-06, "loss": 0.2236, "step": 5106 }, { "epoch": 0.14908337225595517, "grad_norm": 0.41905325651168823, "learning_rate": 9.926911280456054e-06, "loss": 0.234, "step": 5107 }, { "epoch": 0.14911256422232602, "grad_norm": 0.40649834275245667, "learning_rate": 9.926824457100898e-06, "loss": 0.2553, "step": 5108 }, { "epoch": 0.14914175618869688, "grad_norm": 0.3619222640991211, "learning_rate": 9.926737582587007e-06, "loss": 0.2537, "step": 5109 }, { "epoch": 0.14917094815506773, "grad_norm": 0.3705059587955475, "learning_rate": 9.926650656915285e-06, "loss": 0.2366, "step": 5110 }, { "epoch": 0.1492001401214386, "grad_norm": 0.39259687066078186, "learning_rate": 9.926563680086632e-06, "loss": 0.2678, "step": 5111 }, { "epoch": 0.14922933208780945, "grad_norm": 0.34924861788749695, "learning_rate": 9.926476652101955e-06, "loss": 0.239, "step": 5112 }, { "epoch": 0.1492585240541803, "grad_norm": 0.3569514751434326, "learning_rate": 9.926389572962156e-06, "loss": 0.2362, "step": 5113 }, { "epoch": 0.14928771602055113, "grad_norm": 0.39056697487831116, "learning_rate": 9.926302442668138e-06, "loss": 0.2756, "step": 5114 }, { "epoch": 0.149316907986922, "grad_norm": 0.36047202348709106, "learning_rate": 9.926215261220808e-06, "loss": 0.2625, "step": 5115 }, { "epoch": 0.14934609995329284, "grad_norm": 0.3553315997123718, "learning_rate": 9.926128028621072e-06, "loss": 0.287, "step": 5116 }, { "epoch": 0.1493752919196637, "grad_norm": 0.3631345331668854, "learning_rate": 9.92604074486983e-06, "loss": 0.2013, "step": 5117 }, { "epoch": 0.14940448388603456, "grad_norm": 0.31758517026901245, "learning_rate": 9.925953409967996e-06, "loss": 0.2272, "step": 5118 }, { "epoch": 0.1494336758524054, "grad_norm": 0.3822750747203827, "learning_rate": 9.925866023916471e-06, "loss": 0.2843, "step": 5119 }, { "epoch": 0.14946286781877627, "grad_norm": 0.4611244201660156, "learning_rate": 9.925778586716165e-06, "loss": 0.2888, "step": 5120 }, { "epoch": 0.14949205978514712, "grad_norm": 0.37074965238571167, "learning_rate": 9.925691098367987e-06, "loss": 0.286, "step": 5121 }, { "epoch": 0.14952125175151798, "grad_norm": 0.31463152170181274, "learning_rate": 9.925603558872844e-06, "loss": 0.2336, "step": 5122 }, { "epoch": 0.14955044371788884, "grad_norm": 0.3787901699542999, "learning_rate": 9.925515968231642e-06, "loss": 0.2868, "step": 5123 }, { "epoch": 0.1495796356842597, "grad_norm": 0.4074358642101288, "learning_rate": 9.925428326445297e-06, "loss": 0.2534, "step": 5124 }, { "epoch": 0.14960882765063055, "grad_norm": 0.35835331678390503, "learning_rate": 9.925340633514714e-06, "loss": 0.2315, "step": 5125 }, { "epoch": 0.1496380196170014, "grad_norm": 0.37525907158851624, "learning_rate": 9.925252889440805e-06, "loss": 0.2571, "step": 5126 }, { "epoch": 0.14966721158337226, "grad_norm": 0.37560978531837463, "learning_rate": 9.925165094224482e-06, "loss": 0.2383, "step": 5127 }, { "epoch": 0.14969640354974312, "grad_norm": 0.8227425813674927, "learning_rate": 9.925077247866655e-06, "loss": 0.2486, "step": 5128 }, { "epoch": 0.14972559551611397, "grad_norm": 0.338518351316452, "learning_rate": 9.924989350368237e-06, "loss": 0.2399, "step": 5129 }, { "epoch": 0.14975478748248483, "grad_norm": 0.3706510663032532, "learning_rate": 9.924901401730142e-06, "loss": 0.2653, "step": 5130 }, { "epoch": 0.1497839794488557, "grad_norm": 0.4104101359844208, "learning_rate": 9.924813401953282e-06, "loss": 0.2656, "step": 5131 }, { "epoch": 0.14981317141522654, "grad_norm": 0.40923815965652466, "learning_rate": 9.924725351038568e-06, "loss": 0.2463, "step": 5132 }, { "epoch": 0.14984236338159737, "grad_norm": 0.4356424808502197, "learning_rate": 9.92463724898692e-06, "loss": 0.2693, "step": 5133 }, { "epoch": 0.14987155534796823, "grad_norm": 0.4140888750553131, "learning_rate": 9.924549095799249e-06, "loss": 0.2836, "step": 5134 }, { "epoch": 0.14990074731433908, "grad_norm": 0.3871988356113434, "learning_rate": 9.924460891476471e-06, "loss": 0.1997, "step": 5135 }, { "epoch": 0.14992993928070994, "grad_norm": 0.3346761465072632, "learning_rate": 9.924372636019501e-06, "loss": 0.196, "step": 5136 }, { "epoch": 0.1499591312470808, "grad_norm": 0.41013193130493164, "learning_rate": 9.924284329429259e-06, "loss": 0.2526, "step": 5137 }, { "epoch": 0.14998832321345165, "grad_norm": 0.37186112999916077, "learning_rate": 9.924195971706658e-06, "loss": 0.2618, "step": 5138 }, { "epoch": 0.1500175151798225, "grad_norm": 0.3834967017173767, "learning_rate": 9.924107562852615e-06, "loss": 0.2353, "step": 5139 }, { "epoch": 0.15004670714619336, "grad_norm": 0.3656793534755707, "learning_rate": 9.924019102868054e-06, "loss": 0.2338, "step": 5140 }, { "epoch": 0.15007589911256422, "grad_norm": 0.396572470664978, "learning_rate": 9.923930591753887e-06, "loss": 0.2847, "step": 5141 }, { "epoch": 0.15010509107893508, "grad_norm": 0.6468153595924377, "learning_rate": 9.923842029511037e-06, "loss": 0.2855, "step": 5142 }, { "epoch": 0.15013428304530593, "grad_norm": 0.3777219355106354, "learning_rate": 9.92375341614042e-06, "loss": 0.2629, "step": 5143 }, { "epoch": 0.1501634750116768, "grad_norm": 0.3730189800262451, "learning_rate": 9.92366475164296e-06, "loss": 0.2428, "step": 5144 }, { "epoch": 0.15019266697804765, "grad_norm": 0.35205644369125366, "learning_rate": 9.923576036019577e-06, "loss": 0.2578, "step": 5145 }, { "epoch": 0.1502218589444185, "grad_norm": 0.38485658168792725, "learning_rate": 9.92348726927119e-06, "loss": 0.2777, "step": 5146 }, { "epoch": 0.15025105091078936, "grad_norm": 0.3726125955581665, "learning_rate": 9.923398451398721e-06, "loss": 0.2894, "step": 5147 }, { "epoch": 0.15028024287716021, "grad_norm": 0.4303008019924164, "learning_rate": 9.923309582403095e-06, "loss": 0.2936, "step": 5148 }, { "epoch": 0.15030943484353107, "grad_norm": 0.3831363618373871, "learning_rate": 9.92322066228523e-06, "loss": 0.2582, "step": 5149 }, { "epoch": 0.15033862680990193, "grad_norm": 0.3364075720310211, "learning_rate": 9.923131691046056e-06, "loss": 0.2571, "step": 5150 }, { "epoch": 0.15036781877627278, "grad_norm": 0.38402673602104187, "learning_rate": 9.92304266868649e-06, "loss": 0.2576, "step": 5151 }, { "epoch": 0.1503970107426436, "grad_norm": 0.3465467691421509, "learning_rate": 9.922953595207463e-06, "loss": 0.2627, "step": 5152 }, { "epoch": 0.15042620270901447, "grad_norm": 0.3675996959209442, "learning_rate": 9.922864470609894e-06, "loss": 0.2242, "step": 5153 }, { "epoch": 0.15045539467538532, "grad_norm": 0.8993785977363586, "learning_rate": 9.922775294894711e-06, "loss": 0.2057, "step": 5154 }, { "epoch": 0.15048458664175618, "grad_norm": 0.33235064148902893, "learning_rate": 9.922686068062842e-06, "loss": 0.2008, "step": 5155 }, { "epoch": 0.15051377860812704, "grad_norm": 0.34386929869651794, "learning_rate": 9.92259679011521e-06, "loss": 0.2265, "step": 5156 }, { "epoch": 0.1505429705744979, "grad_norm": 0.39888057112693787, "learning_rate": 9.922507461052741e-06, "loss": 0.3003, "step": 5157 }, { "epoch": 0.15057216254086875, "grad_norm": 0.34393495321273804, "learning_rate": 9.922418080876369e-06, "loss": 0.2337, "step": 5158 }, { "epoch": 0.1506013545072396, "grad_norm": 0.3589608371257782, "learning_rate": 9.922328649587014e-06, "loss": 0.2352, "step": 5159 }, { "epoch": 0.15063054647361046, "grad_norm": 0.38475772738456726, "learning_rate": 9.922239167185613e-06, "loss": 0.2406, "step": 5160 }, { "epoch": 0.15065973843998132, "grad_norm": 0.3494780957698822, "learning_rate": 9.922149633673086e-06, "loss": 0.2431, "step": 5161 }, { "epoch": 0.15068893040635217, "grad_norm": 0.44179970026016235, "learning_rate": 9.922060049050372e-06, "loss": 0.2258, "step": 5162 }, { "epoch": 0.15071812237272303, "grad_norm": 0.40570640563964844, "learning_rate": 9.921970413318394e-06, "loss": 0.2956, "step": 5163 }, { "epoch": 0.15074731433909389, "grad_norm": 0.549542248249054, "learning_rate": 9.921880726478086e-06, "loss": 0.3425, "step": 5164 }, { "epoch": 0.15077650630546474, "grad_norm": 0.36341455578804016, "learning_rate": 9.92179098853038e-06, "loss": 0.2676, "step": 5165 }, { "epoch": 0.1508056982718356, "grad_norm": 0.4123232066631317, "learning_rate": 9.921701199476206e-06, "loss": 0.2155, "step": 5166 }, { "epoch": 0.15083489023820645, "grad_norm": 0.34655171632766724, "learning_rate": 9.921611359316496e-06, "loss": 0.2302, "step": 5167 }, { "epoch": 0.1508640822045773, "grad_norm": 0.3412476181983948, "learning_rate": 9.921521468052186e-06, "loss": 0.2222, "step": 5168 }, { "epoch": 0.15089327417094817, "grad_norm": 0.3507964015007019, "learning_rate": 9.921431525684206e-06, "loss": 0.2631, "step": 5169 }, { "epoch": 0.15092246613731902, "grad_norm": 0.4213413596153259, "learning_rate": 9.921341532213491e-06, "loss": 0.258, "step": 5170 }, { "epoch": 0.15095165810368985, "grad_norm": 0.4124493896961212, "learning_rate": 9.921251487640976e-06, "loss": 0.2508, "step": 5171 }, { "epoch": 0.1509808500700607, "grad_norm": 0.4240124821662903, "learning_rate": 9.921161391967596e-06, "loss": 0.255, "step": 5172 }, { "epoch": 0.15101004203643156, "grad_norm": 0.33822426199913025, "learning_rate": 9.921071245194284e-06, "loss": 0.2144, "step": 5173 }, { "epoch": 0.15103923400280242, "grad_norm": 0.4024451673030853, "learning_rate": 9.920981047321981e-06, "loss": 0.2509, "step": 5174 }, { "epoch": 0.15106842596917328, "grad_norm": 0.37688305974006653, "learning_rate": 9.92089079835162e-06, "loss": 0.2514, "step": 5175 }, { "epoch": 0.15109761793554413, "grad_norm": 0.3866552412509918, "learning_rate": 9.92080049828414e-06, "loss": 0.2478, "step": 5176 }, { "epoch": 0.151126809901915, "grad_norm": 0.3947722613811493, "learning_rate": 9.920710147120475e-06, "loss": 0.2942, "step": 5177 }, { "epoch": 0.15115600186828584, "grad_norm": 0.367110937833786, "learning_rate": 9.920619744861566e-06, "loss": 0.2871, "step": 5178 }, { "epoch": 0.1511851938346567, "grad_norm": 0.4160899817943573, "learning_rate": 9.920529291508354e-06, "loss": 0.2812, "step": 5179 }, { "epoch": 0.15121438580102756, "grad_norm": 0.34657177329063416, "learning_rate": 9.920438787061774e-06, "loss": 0.2072, "step": 5180 }, { "epoch": 0.1512435777673984, "grad_norm": 0.379447877407074, "learning_rate": 9.920348231522767e-06, "loss": 0.2449, "step": 5181 }, { "epoch": 0.15127276973376927, "grad_norm": 0.48516249656677246, "learning_rate": 9.920257624892275e-06, "loss": 0.2368, "step": 5182 }, { "epoch": 0.15130196170014013, "grad_norm": 0.3457950949668884, "learning_rate": 9.920166967171236e-06, "loss": 0.2499, "step": 5183 }, { "epoch": 0.15133115366651098, "grad_norm": 0.36764174699783325, "learning_rate": 9.920076258360596e-06, "loss": 0.2465, "step": 5184 }, { "epoch": 0.15136034563288184, "grad_norm": 0.3584400713443756, "learning_rate": 9.91998549846129e-06, "loss": 0.237, "step": 5185 }, { "epoch": 0.1513895375992527, "grad_norm": 0.551397442817688, "learning_rate": 9.919894687474268e-06, "loss": 0.2365, "step": 5186 }, { "epoch": 0.15141872956562355, "grad_norm": 0.4187333285808563, "learning_rate": 9.919803825400467e-06, "loss": 0.2043, "step": 5187 }, { "epoch": 0.1514479215319944, "grad_norm": 0.4046616852283478, "learning_rate": 9.919712912240834e-06, "loss": 0.2793, "step": 5188 }, { "epoch": 0.15147711349836526, "grad_norm": 0.45236071944236755, "learning_rate": 9.919621947996311e-06, "loss": 0.2722, "step": 5189 }, { "epoch": 0.15150630546473612, "grad_norm": 0.3634308874607086, "learning_rate": 9.919530932667844e-06, "loss": 0.2343, "step": 5190 }, { "epoch": 0.15153549743110695, "grad_norm": 0.3917665481567383, "learning_rate": 9.919439866256376e-06, "loss": 0.2149, "step": 5191 }, { "epoch": 0.1515646893974778, "grad_norm": 0.34082838892936707, "learning_rate": 9.919348748762856e-06, "loss": 0.2327, "step": 5192 }, { "epoch": 0.15159388136384866, "grad_norm": 0.38916638493537903, "learning_rate": 9.919257580188227e-06, "loss": 0.283, "step": 5193 }, { "epoch": 0.15162307333021952, "grad_norm": 0.3809712827205658, "learning_rate": 9.919166360533437e-06, "loss": 0.2502, "step": 5194 }, { "epoch": 0.15165226529659037, "grad_norm": 0.37963590025901794, "learning_rate": 9.919075089799432e-06, "loss": 0.2231, "step": 5195 }, { "epoch": 0.15168145726296123, "grad_norm": 0.38423436880111694, "learning_rate": 9.918983767987161e-06, "loss": 0.2426, "step": 5196 }, { "epoch": 0.15171064922933208, "grad_norm": 0.3671989440917969, "learning_rate": 9.918892395097572e-06, "loss": 0.2252, "step": 5197 }, { "epoch": 0.15173984119570294, "grad_norm": 0.5414628982543945, "learning_rate": 9.918800971131616e-06, "loss": 0.2639, "step": 5198 }, { "epoch": 0.1517690331620738, "grad_norm": 0.9287201166152954, "learning_rate": 9.918709496090238e-06, "loss": 0.3168, "step": 5199 }, { "epoch": 0.15179822512844465, "grad_norm": 0.3730253577232361, "learning_rate": 9.91861796997439e-06, "loss": 0.2576, "step": 5200 }, { "epoch": 0.1518274170948155, "grad_norm": 0.5462364554405212, "learning_rate": 9.918526392785023e-06, "loss": 0.2467, "step": 5201 }, { "epoch": 0.15185660906118637, "grad_norm": 0.45172813534736633, "learning_rate": 9.918434764523088e-06, "loss": 0.2453, "step": 5202 }, { "epoch": 0.15188580102755722, "grad_norm": 0.41187551617622375, "learning_rate": 9.918343085189535e-06, "loss": 0.2425, "step": 5203 }, { "epoch": 0.15191499299392808, "grad_norm": 0.33661890029907227, "learning_rate": 9.918251354785315e-06, "loss": 0.2388, "step": 5204 }, { "epoch": 0.15194418496029893, "grad_norm": 0.3565053939819336, "learning_rate": 9.918159573311383e-06, "loss": 0.1914, "step": 5205 }, { "epoch": 0.1519733769266698, "grad_norm": 0.4027513563632965, "learning_rate": 9.918067740768694e-06, "loss": 0.2478, "step": 5206 }, { "epoch": 0.15200256889304065, "grad_norm": 0.3890742063522339, "learning_rate": 9.917975857158195e-06, "loss": 0.2388, "step": 5207 }, { "epoch": 0.1520317608594115, "grad_norm": 0.376099556684494, "learning_rate": 9.917883922480846e-06, "loss": 0.2369, "step": 5208 }, { "epoch": 0.15206095282578236, "grad_norm": 0.5927785038948059, "learning_rate": 9.9177919367376e-06, "loss": 0.2825, "step": 5209 }, { "epoch": 0.1520901447921532, "grad_norm": 0.41120731830596924, "learning_rate": 9.91769989992941e-06, "loss": 0.2681, "step": 5210 }, { "epoch": 0.15211933675852404, "grad_norm": 0.6078084707260132, "learning_rate": 9.917607812057233e-06, "loss": 0.2593, "step": 5211 }, { "epoch": 0.1521485287248949, "grad_norm": 0.4074888527393341, "learning_rate": 9.917515673122025e-06, "loss": 0.2239, "step": 5212 }, { "epoch": 0.15217772069126576, "grad_norm": 0.3962557911872864, "learning_rate": 9.917423483124746e-06, "loss": 0.2668, "step": 5213 }, { "epoch": 0.1522069126576366, "grad_norm": 0.5320345163345337, "learning_rate": 9.917331242066348e-06, "loss": 0.2929, "step": 5214 }, { "epoch": 0.15223610462400747, "grad_norm": 0.37714260816574097, "learning_rate": 9.917238949947794e-06, "loss": 0.251, "step": 5215 }, { "epoch": 0.15226529659037832, "grad_norm": 0.416635125875473, "learning_rate": 9.917146606770037e-06, "loss": 0.2305, "step": 5216 }, { "epoch": 0.15229448855674918, "grad_norm": 0.37574392557144165, "learning_rate": 9.91705421253404e-06, "loss": 0.2569, "step": 5217 }, { "epoch": 0.15232368052312004, "grad_norm": 0.43796923756599426, "learning_rate": 9.91696176724076e-06, "loss": 0.244, "step": 5218 }, { "epoch": 0.1523528724894909, "grad_norm": 0.38419386744499207, "learning_rate": 9.916869270891159e-06, "loss": 0.2369, "step": 5219 }, { "epoch": 0.15238206445586175, "grad_norm": 0.42781829833984375, "learning_rate": 9.916776723486196e-06, "loss": 0.2678, "step": 5220 }, { "epoch": 0.1524112564222326, "grad_norm": 0.36968210339546204, "learning_rate": 9.916684125026832e-06, "loss": 0.2246, "step": 5221 }, { "epoch": 0.15244044838860346, "grad_norm": 0.41195347905158997, "learning_rate": 9.916591475514028e-06, "loss": 0.2286, "step": 5222 }, { "epoch": 0.15246964035497432, "grad_norm": 0.3951184153556824, "learning_rate": 9.916498774948748e-06, "loss": 0.2637, "step": 5223 }, { "epoch": 0.15249883232134517, "grad_norm": 0.5194206237792969, "learning_rate": 9.916406023331955e-06, "loss": 0.263, "step": 5224 }, { "epoch": 0.15252802428771603, "grad_norm": 0.318848192691803, "learning_rate": 9.916313220664608e-06, "loss": 0.2154, "step": 5225 }, { "epoch": 0.15255721625408689, "grad_norm": 0.38806530833244324, "learning_rate": 9.916220366947676e-06, "loss": 0.229, "step": 5226 }, { "epoch": 0.15258640822045774, "grad_norm": 0.37517887353897095, "learning_rate": 9.916127462182117e-06, "loss": 0.2499, "step": 5227 }, { "epoch": 0.1526156001868286, "grad_norm": 0.41038525104522705, "learning_rate": 9.9160345063689e-06, "loss": 0.2468, "step": 5228 }, { "epoch": 0.15264479215319943, "grad_norm": 0.4235549867153168, "learning_rate": 9.91594149950899e-06, "loss": 0.2582, "step": 5229 }, { "epoch": 0.15267398411957028, "grad_norm": 0.3634898364543915, "learning_rate": 9.915848441603353e-06, "loss": 0.2393, "step": 5230 }, { "epoch": 0.15270317608594114, "grad_norm": 0.34937718510627747, "learning_rate": 9.915755332652952e-06, "loss": 0.268, "step": 5231 }, { "epoch": 0.152732368052312, "grad_norm": 0.3964542746543884, "learning_rate": 9.915662172658757e-06, "loss": 0.1949, "step": 5232 }, { "epoch": 0.15276156001868285, "grad_norm": 0.36512812972068787, "learning_rate": 9.915568961621736e-06, "loss": 0.2154, "step": 5233 }, { "epoch": 0.1527907519850537, "grad_norm": 0.35293933749198914, "learning_rate": 9.915475699542854e-06, "loss": 0.2404, "step": 5234 }, { "epoch": 0.15281994395142456, "grad_norm": 0.3379570543766022, "learning_rate": 9.91538238642308e-06, "loss": 0.2238, "step": 5235 }, { "epoch": 0.15284913591779542, "grad_norm": 0.4282354712486267, "learning_rate": 9.915289022263387e-06, "loss": 0.2819, "step": 5236 }, { "epoch": 0.15287832788416628, "grad_norm": 0.36567193269729614, "learning_rate": 9.915195607064738e-06, "loss": 0.2796, "step": 5237 }, { "epoch": 0.15290751985053713, "grad_norm": 0.39932388067245483, "learning_rate": 9.915102140828106e-06, "loss": 0.2564, "step": 5238 }, { "epoch": 0.152936711816908, "grad_norm": 0.3694112002849579, "learning_rate": 9.915008623554462e-06, "loss": 0.2686, "step": 5239 }, { "epoch": 0.15296590378327884, "grad_norm": 0.40596821904182434, "learning_rate": 9.914915055244778e-06, "loss": 0.2763, "step": 5240 }, { "epoch": 0.1529950957496497, "grad_norm": 0.362776517868042, "learning_rate": 9.914821435900024e-06, "loss": 0.2482, "step": 5241 }, { "epoch": 0.15302428771602056, "grad_norm": 0.36898934841156006, "learning_rate": 9.914727765521173e-06, "loss": 0.2527, "step": 5242 }, { "epoch": 0.1530534796823914, "grad_norm": 0.38891294598579407, "learning_rate": 9.914634044109196e-06, "loss": 0.2935, "step": 5243 }, { "epoch": 0.15308267164876227, "grad_norm": 0.8698969483375549, "learning_rate": 9.914540271665068e-06, "loss": 0.2571, "step": 5244 }, { "epoch": 0.15311186361513313, "grad_norm": 0.4082901179790497, "learning_rate": 9.914446448189761e-06, "loss": 0.2069, "step": 5245 }, { "epoch": 0.15314105558150398, "grad_norm": 0.41181516647338867, "learning_rate": 9.914352573684251e-06, "loss": 0.2122, "step": 5246 }, { "epoch": 0.15317024754787484, "grad_norm": 0.35031044483184814, "learning_rate": 9.914258648149512e-06, "loss": 0.2223, "step": 5247 }, { "epoch": 0.15319943951424567, "grad_norm": 0.659927487373352, "learning_rate": 9.914164671586519e-06, "loss": 0.279, "step": 5248 }, { "epoch": 0.15322863148061652, "grad_norm": 0.39273959398269653, "learning_rate": 9.914070643996248e-06, "loss": 0.238, "step": 5249 }, { "epoch": 0.15325782344698738, "grad_norm": 0.3486141562461853, "learning_rate": 9.913976565379677e-06, "loss": 0.2268, "step": 5250 }, { "epoch": 0.15328701541335824, "grad_norm": 0.37877362966537476, "learning_rate": 9.91388243573778e-06, "loss": 0.2518, "step": 5251 }, { "epoch": 0.1533162073797291, "grad_norm": 0.4297533631324768, "learning_rate": 9.913788255071535e-06, "loss": 0.2576, "step": 5252 }, { "epoch": 0.15334539934609995, "grad_norm": 0.43895596265792847, "learning_rate": 9.913694023381923e-06, "loss": 0.2316, "step": 5253 }, { "epoch": 0.1533745913124708, "grad_norm": 0.34473690390586853, "learning_rate": 9.913599740669917e-06, "loss": 0.1908, "step": 5254 }, { "epoch": 0.15340378327884166, "grad_norm": 0.6803795695304871, "learning_rate": 9.913505406936503e-06, "loss": 0.254, "step": 5255 }, { "epoch": 0.15343297524521252, "grad_norm": 0.3878808915615082, "learning_rate": 9.913411022182654e-06, "loss": 0.2377, "step": 5256 }, { "epoch": 0.15346216721158337, "grad_norm": 0.4255841374397278, "learning_rate": 9.913316586409353e-06, "loss": 0.2885, "step": 5257 }, { "epoch": 0.15349135917795423, "grad_norm": 0.33202511072158813, "learning_rate": 9.91322209961758e-06, "loss": 0.2274, "step": 5258 }, { "epoch": 0.15352055114432508, "grad_norm": 0.40692195296287537, "learning_rate": 9.913127561808318e-06, "loss": 0.2838, "step": 5259 }, { "epoch": 0.15354974311069594, "grad_norm": 0.3994904160499573, "learning_rate": 9.913032972982548e-06, "loss": 0.2419, "step": 5260 }, { "epoch": 0.1535789350770668, "grad_norm": 0.3589554727077484, "learning_rate": 9.912938333141248e-06, "loss": 0.2588, "step": 5261 }, { "epoch": 0.15360812704343765, "grad_norm": 0.35046622157096863, "learning_rate": 9.912843642285408e-06, "loss": 0.2245, "step": 5262 }, { "epoch": 0.1536373190098085, "grad_norm": 0.446897029876709, "learning_rate": 9.912748900416005e-06, "loss": 0.2496, "step": 5263 }, { "epoch": 0.15366651097617937, "grad_norm": 0.3764045834541321, "learning_rate": 9.912654107534024e-06, "loss": 0.2523, "step": 5264 }, { "epoch": 0.15369570294255022, "grad_norm": 0.41552138328552246, "learning_rate": 9.912559263640452e-06, "loss": 0.2806, "step": 5265 }, { "epoch": 0.15372489490892108, "grad_norm": 1.0236932039260864, "learning_rate": 9.912464368736271e-06, "loss": 0.3158, "step": 5266 }, { "epoch": 0.1537540868752919, "grad_norm": 0.4382303059101105, "learning_rate": 9.91236942282247e-06, "loss": 0.24, "step": 5267 }, { "epoch": 0.15378327884166276, "grad_norm": 0.4301716685295105, "learning_rate": 9.91227442590003e-06, "loss": 0.2501, "step": 5268 }, { "epoch": 0.15381247080803362, "grad_norm": 0.3800806999206543, "learning_rate": 9.912179377969942e-06, "loss": 0.2671, "step": 5269 }, { "epoch": 0.15384166277440448, "grad_norm": 0.3974703550338745, "learning_rate": 9.912084279033189e-06, "loss": 0.2391, "step": 5270 }, { "epoch": 0.15387085474077533, "grad_norm": 0.34146326780319214, "learning_rate": 9.911989129090761e-06, "loss": 0.2171, "step": 5271 }, { "epoch": 0.1539000467071462, "grad_norm": 0.3718494474887848, "learning_rate": 9.911893928143645e-06, "loss": 0.2071, "step": 5272 }, { "epoch": 0.15392923867351704, "grad_norm": 0.4407801926136017, "learning_rate": 9.91179867619283e-06, "loss": 0.2516, "step": 5273 }, { "epoch": 0.1539584306398879, "grad_norm": 0.3972082734107971, "learning_rate": 9.911703373239305e-06, "loss": 0.22, "step": 5274 }, { "epoch": 0.15398762260625876, "grad_norm": 0.3896668553352356, "learning_rate": 9.91160801928406e-06, "loss": 0.2349, "step": 5275 }, { "epoch": 0.1540168145726296, "grad_norm": 0.45504873991012573, "learning_rate": 9.911512614328085e-06, "loss": 0.2383, "step": 5276 }, { "epoch": 0.15404600653900047, "grad_norm": 0.3727554976940155, "learning_rate": 9.911417158372369e-06, "loss": 0.2422, "step": 5277 }, { "epoch": 0.15407519850537132, "grad_norm": 0.3156605660915375, "learning_rate": 9.911321651417905e-06, "loss": 0.1752, "step": 5278 }, { "epoch": 0.15410439047174218, "grad_norm": 0.4774426519870758, "learning_rate": 9.911226093465685e-06, "loss": 0.2409, "step": 5279 }, { "epoch": 0.15413358243811304, "grad_norm": 0.3435889184474945, "learning_rate": 9.9111304845167e-06, "loss": 0.2348, "step": 5280 }, { "epoch": 0.1541627744044839, "grad_norm": 0.39945927262306213, "learning_rate": 9.911034824571943e-06, "loss": 0.271, "step": 5281 }, { "epoch": 0.15419196637085475, "grad_norm": 0.3750808835029602, "learning_rate": 9.910939113632408e-06, "loss": 0.245, "step": 5282 }, { "epoch": 0.1542211583372256, "grad_norm": 0.4023251533508301, "learning_rate": 9.910843351699087e-06, "loss": 0.2876, "step": 5283 }, { "epoch": 0.15425035030359646, "grad_norm": 0.4406808018684387, "learning_rate": 9.910747538772979e-06, "loss": 0.1994, "step": 5284 }, { "epoch": 0.15427954226996732, "grad_norm": 0.43074098229408264, "learning_rate": 9.910651674855072e-06, "loss": 0.2432, "step": 5285 }, { "epoch": 0.15430873423633815, "grad_norm": 0.37873217463493347, "learning_rate": 9.910555759946366e-06, "loss": 0.2732, "step": 5286 }, { "epoch": 0.154337926202709, "grad_norm": 0.3961237967014313, "learning_rate": 9.910459794047857e-06, "loss": 0.2245, "step": 5287 }, { "epoch": 0.15436711816907986, "grad_norm": 0.34839412569999695, "learning_rate": 9.910363777160538e-06, "loss": 0.2311, "step": 5288 }, { "epoch": 0.15439631013545072, "grad_norm": 0.3973195254802704, "learning_rate": 9.910267709285412e-06, "loss": 0.2589, "step": 5289 }, { "epoch": 0.15442550210182157, "grad_norm": 0.3876636326313019, "learning_rate": 9.910171590423472e-06, "loss": 0.2309, "step": 5290 }, { "epoch": 0.15445469406819243, "grad_norm": 0.3696514368057251, "learning_rate": 9.910075420575716e-06, "loss": 0.2343, "step": 5291 }, { "epoch": 0.15448388603456328, "grad_norm": 0.35762354731559753, "learning_rate": 9.909979199743145e-06, "loss": 0.2198, "step": 5292 }, { "epoch": 0.15451307800093414, "grad_norm": 0.38611093163490295, "learning_rate": 9.909882927926754e-06, "loss": 0.1952, "step": 5293 }, { "epoch": 0.154542269967305, "grad_norm": 0.43616431951522827, "learning_rate": 9.909786605127549e-06, "loss": 0.2323, "step": 5294 }, { "epoch": 0.15457146193367585, "grad_norm": 0.3237277567386627, "learning_rate": 9.909690231346526e-06, "loss": 0.1943, "step": 5295 }, { "epoch": 0.1546006539000467, "grad_norm": 1.858238935470581, "learning_rate": 9.909593806584685e-06, "loss": 0.2494, "step": 5296 }, { "epoch": 0.15462984586641756, "grad_norm": 0.45311692357063293, "learning_rate": 9.90949733084303e-06, "loss": 0.2904, "step": 5297 }, { "epoch": 0.15465903783278842, "grad_norm": 0.42486268281936646, "learning_rate": 9.909400804122562e-06, "loss": 0.2799, "step": 5298 }, { "epoch": 0.15468822979915928, "grad_norm": 0.317197322845459, "learning_rate": 9.909304226424281e-06, "loss": 0.1943, "step": 5299 }, { "epoch": 0.15471742176553013, "grad_norm": 0.46970269083976746, "learning_rate": 9.909207597749193e-06, "loss": 0.219, "step": 5300 }, { "epoch": 0.154746613731901, "grad_norm": 0.3963544964790344, "learning_rate": 9.909110918098299e-06, "loss": 0.2427, "step": 5301 }, { "epoch": 0.15477580569827185, "grad_norm": 0.38016602396965027, "learning_rate": 9.909014187472604e-06, "loss": 0.2496, "step": 5302 }, { "epoch": 0.1548049976646427, "grad_norm": 0.36491650342941284, "learning_rate": 9.908917405873112e-06, "loss": 0.313, "step": 5303 }, { "epoch": 0.15483418963101356, "grad_norm": 0.40134090185165405, "learning_rate": 9.908820573300829e-06, "loss": 0.307, "step": 5304 }, { "epoch": 0.1548633815973844, "grad_norm": 0.38040614128112793, "learning_rate": 9.908723689756759e-06, "loss": 0.2327, "step": 5305 }, { "epoch": 0.15489257356375524, "grad_norm": 0.36793994903564453, "learning_rate": 9.90862675524191e-06, "loss": 0.2213, "step": 5306 }, { "epoch": 0.1549217655301261, "grad_norm": 0.3436267077922821, "learning_rate": 9.908529769757284e-06, "loss": 0.2444, "step": 5307 }, { "epoch": 0.15495095749649695, "grad_norm": 0.38196706771850586, "learning_rate": 9.908432733303894e-06, "loss": 0.2333, "step": 5308 }, { "epoch": 0.1549801494628678, "grad_norm": 0.37538522481918335, "learning_rate": 9.908335645882745e-06, "loss": 0.2977, "step": 5309 }, { "epoch": 0.15500934142923867, "grad_norm": 0.3586408197879791, "learning_rate": 9.908238507494845e-06, "loss": 0.2873, "step": 5310 }, { "epoch": 0.15503853339560952, "grad_norm": 0.38093799352645874, "learning_rate": 9.908141318141202e-06, "loss": 0.2408, "step": 5311 }, { "epoch": 0.15506772536198038, "grad_norm": 0.37987571954727173, "learning_rate": 9.908044077822825e-06, "loss": 0.2145, "step": 5312 }, { "epoch": 0.15509691732835124, "grad_norm": 0.34635886549949646, "learning_rate": 9.907946786540727e-06, "loss": 0.2619, "step": 5313 }, { "epoch": 0.1551261092947221, "grad_norm": 0.40378546714782715, "learning_rate": 9.907849444295914e-06, "loss": 0.2823, "step": 5314 }, { "epoch": 0.15515530126109295, "grad_norm": 0.3765743374824524, "learning_rate": 9.9077520510894e-06, "loss": 0.2431, "step": 5315 }, { "epoch": 0.1551844932274638, "grad_norm": 0.38213440775871277, "learning_rate": 9.907654606922194e-06, "loss": 0.2945, "step": 5316 }, { "epoch": 0.15521368519383466, "grad_norm": 0.4908757507801056, "learning_rate": 9.907557111795309e-06, "loss": 0.2246, "step": 5317 }, { "epoch": 0.15524287716020552, "grad_norm": 0.40515172481536865, "learning_rate": 9.907459565709755e-06, "loss": 0.2496, "step": 5318 }, { "epoch": 0.15527206912657637, "grad_norm": 0.3848896622657776, "learning_rate": 9.907361968666551e-06, "loss": 0.2396, "step": 5319 }, { "epoch": 0.15530126109294723, "grad_norm": 0.37867674231529236, "learning_rate": 9.907264320666705e-06, "loss": 0.2915, "step": 5320 }, { "epoch": 0.15533045305931809, "grad_norm": 0.35458141565322876, "learning_rate": 9.90716662171123e-06, "loss": 0.2841, "step": 5321 }, { "epoch": 0.15535964502568894, "grad_norm": 0.3617495000362396, "learning_rate": 9.907068871801146e-06, "loss": 0.2482, "step": 5322 }, { "epoch": 0.1553888369920598, "grad_norm": 0.36793288588523865, "learning_rate": 9.906971070937464e-06, "loss": 0.2338, "step": 5323 }, { "epoch": 0.15541802895843063, "grad_norm": 0.31982582807540894, "learning_rate": 9.906873219121199e-06, "loss": 0.219, "step": 5324 }, { "epoch": 0.15544722092480148, "grad_norm": 0.36301907896995544, "learning_rate": 9.90677531635337e-06, "loss": 0.2619, "step": 5325 }, { "epoch": 0.15547641289117234, "grad_norm": 0.35696521401405334, "learning_rate": 9.906677362634991e-06, "loss": 0.2548, "step": 5326 }, { "epoch": 0.1555056048575432, "grad_norm": 0.2976264953613281, "learning_rate": 9.906579357967081e-06, "loss": 0.1803, "step": 5327 }, { "epoch": 0.15553479682391405, "grad_norm": 0.33319327235221863, "learning_rate": 9.906481302350657e-06, "loss": 0.2046, "step": 5328 }, { "epoch": 0.1555639887902849, "grad_norm": 0.3510221242904663, "learning_rate": 9.906383195786735e-06, "loss": 0.257, "step": 5329 }, { "epoch": 0.15559318075665576, "grad_norm": 0.6244447827339172, "learning_rate": 9.906285038276337e-06, "loss": 0.2456, "step": 5330 }, { "epoch": 0.15562237272302662, "grad_norm": 0.41217681765556335, "learning_rate": 9.906186829820482e-06, "loss": 0.3262, "step": 5331 }, { "epoch": 0.15565156468939748, "grad_norm": 0.39894673228263855, "learning_rate": 9.906088570420188e-06, "loss": 0.2284, "step": 5332 }, { "epoch": 0.15568075665576833, "grad_norm": 0.3420012295246124, "learning_rate": 9.905990260076476e-06, "loss": 0.2779, "step": 5333 }, { "epoch": 0.1557099486221392, "grad_norm": 0.34591224789619446, "learning_rate": 9.905891898790367e-06, "loss": 0.2673, "step": 5334 }, { "epoch": 0.15573914058851004, "grad_norm": 0.37854379415512085, "learning_rate": 9.905793486562883e-06, "loss": 0.2823, "step": 5335 }, { "epoch": 0.1557683325548809, "grad_norm": 0.39500099420547485, "learning_rate": 9.905695023395044e-06, "loss": 0.2971, "step": 5336 }, { "epoch": 0.15579752452125176, "grad_norm": 0.3545851707458496, "learning_rate": 9.905596509287873e-06, "loss": 0.2851, "step": 5337 }, { "epoch": 0.1558267164876226, "grad_norm": 0.3591000437736511, "learning_rate": 9.905497944242394e-06, "loss": 0.2597, "step": 5338 }, { "epoch": 0.15585590845399347, "grad_norm": 0.3631269037723541, "learning_rate": 9.90539932825963e-06, "loss": 0.2497, "step": 5339 }, { "epoch": 0.15588510042036433, "grad_norm": 0.3382885456085205, "learning_rate": 9.905300661340604e-06, "loss": 0.2764, "step": 5340 }, { "epoch": 0.15591429238673518, "grad_norm": 0.37616607546806335, "learning_rate": 9.905201943486343e-06, "loss": 0.2419, "step": 5341 }, { "epoch": 0.15594348435310604, "grad_norm": 0.3998757600784302, "learning_rate": 9.90510317469787e-06, "loss": 0.2774, "step": 5342 }, { "epoch": 0.15597267631947687, "grad_norm": 0.3490614593029022, "learning_rate": 9.905004354976211e-06, "loss": 0.2516, "step": 5343 }, { "epoch": 0.15600186828584772, "grad_norm": 0.46210771799087524, "learning_rate": 9.904905484322393e-06, "loss": 0.2921, "step": 5344 }, { "epoch": 0.15603106025221858, "grad_norm": 0.4116307497024536, "learning_rate": 9.904806562737442e-06, "loss": 0.243, "step": 5345 }, { "epoch": 0.15606025221858943, "grad_norm": 0.4773152470588684, "learning_rate": 9.904707590222383e-06, "loss": 0.236, "step": 5346 }, { "epoch": 0.1560894441849603, "grad_norm": 0.3243151009082794, "learning_rate": 9.904608566778246e-06, "loss": 0.2029, "step": 5347 }, { "epoch": 0.15611863615133115, "grad_norm": 0.3809340000152588, "learning_rate": 9.90450949240606e-06, "loss": 0.2552, "step": 5348 }, { "epoch": 0.156147828117702, "grad_norm": 0.4171895980834961, "learning_rate": 9.904410367106854e-06, "loss": 0.2644, "step": 5349 }, { "epoch": 0.15617702008407286, "grad_norm": 0.3848971724510193, "learning_rate": 9.904311190881654e-06, "loss": 0.2195, "step": 5350 }, { "epoch": 0.15620621205044372, "grad_norm": 0.4080364406108856, "learning_rate": 9.904211963731491e-06, "loss": 0.3044, "step": 5351 }, { "epoch": 0.15623540401681457, "grad_norm": 0.39876872301101685, "learning_rate": 9.904112685657399e-06, "loss": 0.2322, "step": 5352 }, { "epoch": 0.15626459598318543, "grad_norm": 0.4108620285987854, "learning_rate": 9.904013356660405e-06, "loss": 0.2818, "step": 5353 }, { "epoch": 0.15629378794955628, "grad_norm": 0.3505694568157196, "learning_rate": 9.903913976741541e-06, "loss": 0.2277, "step": 5354 }, { "epoch": 0.15632297991592714, "grad_norm": 0.37575986981391907, "learning_rate": 9.90381454590184e-06, "loss": 0.2667, "step": 5355 }, { "epoch": 0.156352171882298, "grad_norm": 0.37897223234176636, "learning_rate": 9.903715064142331e-06, "loss": 0.2783, "step": 5356 }, { "epoch": 0.15638136384866885, "grad_norm": 0.4255344271659851, "learning_rate": 9.903615531464054e-06, "loss": 0.257, "step": 5357 }, { "epoch": 0.1564105558150397, "grad_norm": 0.4303790032863617, "learning_rate": 9.903515947868037e-06, "loss": 0.2931, "step": 5358 }, { "epoch": 0.15643974778141057, "grad_norm": 0.4228416383266449, "learning_rate": 9.903416313355313e-06, "loss": 0.2511, "step": 5359 }, { "epoch": 0.15646893974778142, "grad_norm": 0.4576827585697174, "learning_rate": 9.903316627926923e-06, "loss": 0.2132, "step": 5360 }, { "epoch": 0.15649813171415228, "grad_norm": 0.332295686006546, "learning_rate": 9.903216891583896e-06, "loss": 0.2035, "step": 5361 }, { "epoch": 0.15652732368052313, "grad_norm": 0.3570411801338196, "learning_rate": 9.90311710432727e-06, "loss": 0.2295, "step": 5362 }, { "epoch": 0.15655651564689396, "grad_norm": 0.35750532150268555, "learning_rate": 9.903017266158079e-06, "loss": 0.1855, "step": 5363 }, { "epoch": 0.15658570761326482, "grad_norm": 0.428817480802536, "learning_rate": 9.902917377077363e-06, "loss": 0.2752, "step": 5364 }, { "epoch": 0.15661489957963567, "grad_norm": 0.35371145606040955, "learning_rate": 9.90281743708616e-06, "loss": 0.221, "step": 5365 }, { "epoch": 0.15664409154600653, "grad_norm": 1.6588597297668457, "learning_rate": 9.902717446185504e-06, "loss": 0.3357, "step": 5366 }, { "epoch": 0.1566732835123774, "grad_norm": 0.36753690242767334, "learning_rate": 9.902617404376433e-06, "loss": 0.2382, "step": 5367 }, { "epoch": 0.15670247547874824, "grad_norm": 0.39533722400665283, "learning_rate": 9.90251731165999e-06, "loss": 0.282, "step": 5368 }, { "epoch": 0.1567316674451191, "grad_norm": 0.36021241545677185, "learning_rate": 9.90241716803721e-06, "loss": 0.2801, "step": 5369 }, { "epoch": 0.15676085941148996, "grad_norm": 0.34882137179374695, "learning_rate": 9.902316973509136e-06, "loss": 0.2148, "step": 5370 }, { "epoch": 0.1567900513778608, "grad_norm": 0.45972010493278503, "learning_rate": 9.902216728076808e-06, "loss": 0.2841, "step": 5371 }, { "epoch": 0.15681924334423167, "grad_norm": 0.38855186104774475, "learning_rate": 9.902116431741264e-06, "loss": 0.2102, "step": 5372 }, { "epoch": 0.15684843531060252, "grad_norm": 0.4614020586013794, "learning_rate": 9.902016084503549e-06, "loss": 0.2563, "step": 5373 }, { "epoch": 0.15687762727697338, "grad_norm": 0.40527209639549255, "learning_rate": 9.901915686364704e-06, "loss": 0.1968, "step": 5374 }, { "epoch": 0.15690681924334424, "grad_norm": 0.36340242624282837, "learning_rate": 9.901815237325769e-06, "loss": 0.2586, "step": 5375 }, { "epoch": 0.1569360112097151, "grad_norm": 0.3576134145259857, "learning_rate": 9.90171473738779e-06, "loss": 0.2256, "step": 5376 }, { "epoch": 0.15696520317608595, "grad_norm": 0.3520801365375519, "learning_rate": 9.90161418655181e-06, "loss": 0.2314, "step": 5377 }, { "epoch": 0.1569943951424568, "grad_norm": 0.47729775309562683, "learning_rate": 9.901513584818874e-06, "loss": 0.3018, "step": 5378 }, { "epoch": 0.15702358710882766, "grad_norm": 0.35778889060020447, "learning_rate": 9.901412932190024e-06, "loss": 0.2722, "step": 5379 }, { "epoch": 0.15705277907519852, "grad_norm": 0.46251964569091797, "learning_rate": 9.901312228666308e-06, "loss": 0.3099, "step": 5380 }, { "epoch": 0.15708197104156937, "grad_norm": 0.43329301476478577, "learning_rate": 9.90121147424877e-06, "loss": 0.2727, "step": 5381 }, { "epoch": 0.1571111630079402, "grad_norm": 0.4378613531589508, "learning_rate": 9.901110668938454e-06, "loss": 0.2948, "step": 5382 }, { "epoch": 0.15714035497431106, "grad_norm": 0.39821580052375793, "learning_rate": 9.90100981273641e-06, "loss": 0.233, "step": 5383 }, { "epoch": 0.15716954694068191, "grad_norm": 0.42319151759147644, "learning_rate": 9.900908905643684e-06, "loss": 0.2753, "step": 5384 }, { "epoch": 0.15719873890705277, "grad_norm": 0.38834747672080994, "learning_rate": 9.900807947661326e-06, "loss": 0.2286, "step": 5385 }, { "epoch": 0.15722793087342363, "grad_norm": 0.48280102014541626, "learning_rate": 9.900706938790383e-06, "loss": 0.2273, "step": 5386 }, { "epoch": 0.15725712283979448, "grad_norm": 0.3889092803001404, "learning_rate": 9.900605879031902e-06, "loss": 0.2593, "step": 5387 }, { "epoch": 0.15728631480616534, "grad_norm": 0.5341355800628662, "learning_rate": 9.900504768386933e-06, "loss": 0.262, "step": 5388 }, { "epoch": 0.1573155067725362, "grad_norm": 0.41564542055130005, "learning_rate": 9.900403606856527e-06, "loss": 0.2729, "step": 5389 }, { "epoch": 0.15734469873890705, "grad_norm": 0.33837345242500305, "learning_rate": 9.900302394441734e-06, "loss": 0.1859, "step": 5390 }, { "epoch": 0.1573738907052779, "grad_norm": 0.41059309244155884, "learning_rate": 9.900201131143606e-06, "loss": 0.2388, "step": 5391 }, { "epoch": 0.15740308267164876, "grad_norm": 0.354462206363678, "learning_rate": 9.900099816963194e-06, "loss": 0.1927, "step": 5392 }, { "epoch": 0.15743227463801962, "grad_norm": 0.3466532230377197, "learning_rate": 9.899998451901547e-06, "loss": 0.2499, "step": 5393 }, { "epoch": 0.15746146660439048, "grad_norm": 0.4887927174568176, "learning_rate": 9.899897035959722e-06, "loss": 0.2998, "step": 5394 }, { "epoch": 0.15749065857076133, "grad_norm": 0.4613937437534332, "learning_rate": 9.89979556913877e-06, "loss": 0.2305, "step": 5395 }, { "epoch": 0.1575198505371322, "grad_norm": 0.37547287344932556, "learning_rate": 9.899694051439745e-06, "loss": 0.2501, "step": 5396 }, { "epoch": 0.15754904250350305, "grad_norm": 0.374162882566452, "learning_rate": 9.8995924828637e-06, "loss": 0.2316, "step": 5397 }, { "epoch": 0.1575782344698739, "grad_norm": 0.33304643630981445, "learning_rate": 9.899490863411691e-06, "loss": 0.2271, "step": 5398 }, { "epoch": 0.15760742643624476, "grad_norm": 0.3551325500011444, "learning_rate": 9.899389193084772e-06, "loss": 0.2694, "step": 5399 }, { "epoch": 0.1576366184026156, "grad_norm": 1.7127487659454346, "learning_rate": 9.899287471884001e-06, "loss": 0.2536, "step": 5400 }, { "epoch": 0.15766581036898644, "grad_norm": 0.37850433588027954, "learning_rate": 9.899185699810433e-06, "loss": 0.265, "step": 5401 }, { "epoch": 0.1576950023353573, "grad_norm": 0.43787845969200134, "learning_rate": 9.89908387686512e-06, "loss": 0.2869, "step": 5402 }, { "epoch": 0.15772419430172815, "grad_norm": 0.3959367275238037, "learning_rate": 9.89898200304913e-06, "loss": 0.2346, "step": 5403 }, { "epoch": 0.157753386268099, "grad_norm": 0.35539373755455017, "learning_rate": 9.89888007836351e-06, "loss": 0.2835, "step": 5404 }, { "epoch": 0.15778257823446987, "grad_norm": 0.4151530861854553, "learning_rate": 9.898778102809326e-06, "loss": 0.2684, "step": 5405 }, { "epoch": 0.15781177020084072, "grad_norm": 0.32616493105888367, "learning_rate": 9.898676076387632e-06, "loss": 0.2447, "step": 5406 }, { "epoch": 0.15784096216721158, "grad_norm": 0.4907291531562805, "learning_rate": 9.89857399909949e-06, "loss": 0.2451, "step": 5407 }, { "epoch": 0.15787015413358244, "grad_norm": 0.3574472665786743, "learning_rate": 9.898471870945959e-06, "loss": 0.2202, "step": 5408 }, { "epoch": 0.1578993460999533, "grad_norm": 0.4847332835197449, "learning_rate": 9.898369691928098e-06, "loss": 0.2419, "step": 5409 }, { "epoch": 0.15792853806632415, "grad_norm": 0.4441661834716797, "learning_rate": 9.89826746204697e-06, "loss": 0.2573, "step": 5410 }, { "epoch": 0.157957730032695, "grad_norm": 0.3915395140647888, "learning_rate": 9.898165181303639e-06, "loss": 0.3209, "step": 5411 }, { "epoch": 0.15798692199906586, "grad_norm": 0.5105979442596436, "learning_rate": 9.898062849699163e-06, "loss": 0.2425, "step": 5412 }, { "epoch": 0.15801611396543672, "grad_norm": 0.3738287687301636, "learning_rate": 9.897960467234603e-06, "loss": 0.2049, "step": 5413 }, { "epoch": 0.15804530593180757, "grad_norm": 0.4455154836177826, "learning_rate": 9.897858033911029e-06, "loss": 0.2235, "step": 5414 }, { "epoch": 0.15807449789817843, "grad_norm": 0.4471141993999481, "learning_rate": 9.8977555497295e-06, "loss": 0.2251, "step": 5415 }, { "epoch": 0.15810368986454928, "grad_norm": 0.3955352306365967, "learning_rate": 9.897653014691078e-06, "loss": 0.2395, "step": 5416 }, { "epoch": 0.15813288183092014, "grad_norm": 0.3809660077095032, "learning_rate": 9.897550428796833e-06, "loss": 0.2262, "step": 5417 }, { "epoch": 0.158162073797291, "grad_norm": 0.369148313999176, "learning_rate": 9.897447792047827e-06, "loss": 0.2192, "step": 5418 }, { "epoch": 0.15819126576366185, "grad_norm": 0.622744619846344, "learning_rate": 9.897345104445126e-06, "loss": 0.2293, "step": 5419 }, { "epoch": 0.15822045773003268, "grad_norm": 0.3427455723285675, "learning_rate": 9.897242365989796e-06, "loss": 0.206, "step": 5420 }, { "epoch": 0.15824964969640354, "grad_norm": 0.37280014157295227, "learning_rate": 9.897139576682906e-06, "loss": 0.2549, "step": 5421 }, { "epoch": 0.1582788416627744, "grad_norm": 0.4373774528503418, "learning_rate": 9.897036736525521e-06, "loss": 0.2187, "step": 5422 }, { "epoch": 0.15830803362914525, "grad_norm": 0.35114002227783203, "learning_rate": 9.896933845518708e-06, "loss": 0.2613, "step": 5423 }, { "epoch": 0.1583372255955161, "grad_norm": 0.37092921137809753, "learning_rate": 9.896830903663541e-06, "loss": 0.2558, "step": 5424 }, { "epoch": 0.15836641756188696, "grad_norm": 0.31380894780158997, "learning_rate": 9.896727910961082e-06, "loss": 0.2031, "step": 5425 }, { "epoch": 0.15839560952825782, "grad_norm": 0.3798656165599823, "learning_rate": 9.896624867412404e-06, "loss": 0.2687, "step": 5426 }, { "epoch": 0.15842480149462868, "grad_norm": 0.39007699489593506, "learning_rate": 9.896521773018576e-06, "loss": 0.2838, "step": 5427 }, { "epoch": 0.15845399346099953, "grad_norm": 0.3759281039237976, "learning_rate": 9.896418627780671e-06, "loss": 0.2401, "step": 5428 }, { "epoch": 0.1584831854273704, "grad_norm": 0.5182591080665588, "learning_rate": 9.896315431699757e-06, "loss": 0.2691, "step": 5429 }, { "epoch": 0.15851237739374124, "grad_norm": 0.4439866244792938, "learning_rate": 9.896212184776905e-06, "loss": 0.2872, "step": 5430 }, { "epoch": 0.1585415693601121, "grad_norm": 0.3921807110309601, "learning_rate": 9.896108887013189e-06, "loss": 0.2462, "step": 5431 }, { "epoch": 0.15857076132648296, "grad_norm": 0.34572112560272217, "learning_rate": 9.896005538409683e-06, "loss": 0.2127, "step": 5432 }, { "epoch": 0.1585999532928538, "grad_norm": 0.358048677444458, "learning_rate": 9.895902138967458e-06, "loss": 0.2808, "step": 5433 }, { "epoch": 0.15862914525922467, "grad_norm": 0.36866968870162964, "learning_rate": 9.895798688687585e-06, "loss": 0.2528, "step": 5434 }, { "epoch": 0.15865833722559552, "grad_norm": 0.35237637162208557, "learning_rate": 9.895695187571145e-06, "loss": 0.2347, "step": 5435 }, { "epoch": 0.15868752919196638, "grad_norm": 0.42637982964515686, "learning_rate": 9.895591635619207e-06, "loss": 0.2735, "step": 5436 }, { "epoch": 0.15871672115833724, "grad_norm": 0.37105756998062134, "learning_rate": 9.89548803283285e-06, "loss": 0.2106, "step": 5437 }, { "epoch": 0.1587459131247081, "grad_norm": 0.394107848405838, "learning_rate": 9.895384379213145e-06, "loss": 0.2594, "step": 5438 }, { "epoch": 0.15877510509107892, "grad_norm": 0.3422209918498993, "learning_rate": 9.895280674761173e-06, "loss": 0.2412, "step": 5439 }, { "epoch": 0.15880429705744978, "grad_norm": 0.3609887659549713, "learning_rate": 9.895176919478009e-06, "loss": 0.243, "step": 5440 }, { "epoch": 0.15883348902382063, "grad_norm": 0.37777289748191833, "learning_rate": 9.89507311336473e-06, "loss": 0.3004, "step": 5441 }, { "epoch": 0.1588626809901915, "grad_norm": 0.39302900433540344, "learning_rate": 9.894969256422416e-06, "loss": 0.2557, "step": 5442 }, { "epoch": 0.15889187295656235, "grad_norm": 0.3298996686935425, "learning_rate": 9.894865348652143e-06, "loss": 0.2463, "step": 5443 }, { "epoch": 0.1589210649229332, "grad_norm": 0.36308491230010986, "learning_rate": 9.89476139005499e-06, "loss": 0.2373, "step": 5444 }, { "epoch": 0.15895025688930406, "grad_norm": 0.35580992698669434, "learning_rate": 9.894657380632038e-06, "loss": 0.2305, "step": 5445 }, { "epoch": 0.15897944885567492, "grad_norm": 0.3742526173591614, "learning_rate": 9.894553320384366e-06, "loss": 0.2469, "step": 5446 }, { "epoch": 0.15900864082204577, "grad_norm": 0.33573922514915466, "learning_rate": 9.894449209313055e-06, "loss": 0.1957, "step": 5447 }, { "epoch": 0.15903783278841663, "grad_norm": 0.34631240367889404, "learning_rate": 9.894345047419185e-06, "loss": 0.2168, "step": 5448 }, { "epoch": 0.15906702475478748, "grad_norm": 0.3934668004512787, "learning_rate": 9.89424083470384e-06, "loss": 0.2606, "step": 5449 }, { "epoch": 0.15909621672115834, "grad_norm": 0.5082058310508728, "learning_rate": 9.894136571168098e-06, "loss": 0.2449, "step": 5450 }, { "epoch": 0.1591254086875292, "grad_norm": 0.4085044264793396, "learning_rate": 9.894032256813044e-06, "loss": 0.2797, "step": 5451 }, { "epoch": 0.15915460065390005, "grad_norm": 0.3708791136741638, "learning_rate": 9.893927891639765e-06, "loss": 0.2774, "step": 5452 }, { "epoch": 0.1591837926202709, "grad_norm": 0.4042510986328125, "learning_rate": 9.893823475649339e-06, "loss": 0.2194, "step": 5453 }, { "epoch": 0.15921298458664176, "grad_norm": 0.8070899248123169, "learning_rate": 9.893719008842851e-06, "loss": 0.2747, "step": 5454 }, { "epoch": 0.15924217655301262, "grad_norm": 0.3842538297176361, "learning_rate": 9.893614491221389e-06, "loss": 0.2702, "step": 5455 }, { "epoch": 0.15927136851938348, "grad_norm": 0.3809678256511688, "learning_rate": 9.893509922786035e-06, "loss": 0.2602, "step": 5456 }, { "epoch": 0.15930056048575433, "grad_norm": 0.3582351803779602, "learning_rate": 9.893405303537876e-06, "loss": 0.1983, "step": 5457 }, { "epoch": 0.15932975245212516, "grad_norm": 0.38915443420410156, "learning_rate": 9.893300633478e-06, "loss": 0.2313, "step": 5458 }, { "epoch": 0.15935894441849602, "grad_norm": 0.3752717673778534, "learning_rate": 9.893195912607492e-06, "loss": 0.2176, "step": 5459 }, { "epoch": 0.15938813638486687, "grad_norm": 0.42603933811187744, "learning_rate": 9.893091140927438e-06, "loss": 0.2704, "step": 5460 }, { "epoch": 0.15941732835123773, "grad_norm": 0.370083212852478, "learning_rate": 9.892986318438928e-06, "loss": 0.2368, "step": 5461 }, { "epoch": 0.1594465203176086, "grad_norm": 0.41572093963623047, "learning_rate": 9.892881445143052e-06, "loss": 0.2689, "step": 5462 }, { "epoch": 0.15947571228397944, "grad_norm": 0.42353692650794983, "learning_rate": 9.892776521040895e-06, "loss": 0.2583, "step": 5463 }, { "epoch": 0.1595049042503503, "grad_norm": 0.3476749658584595, "learning_rate": 9.89267154613355e-06, "loss": 0.2109, "step": 5464 }, { "epoch": 0.15953409621672116, "grad_norm": 0.3392156958580017, "learning_rate": 9.892566520422104e-06, "loss": 0.2269, "step": 5465 }, { "epoch": 0.159563288183092, "grad_norm": 0.3550477921962738, "learning_rate": 9.89246144390765e-06, "loss": 0.2389, "step": 5466 }, { "epoch": 0.15959248014946287, "grad_norm": 0.37121233344078064, "learning_rate": 9.892356316591278e-06, "loss": 0.2391, "step": 5467 }, { "epoch": 0.15962167211583372, "grad_norm": 0.3427291512489319, "learning_rate": 9.89225113847408e-06, "loss": 0.2103, "step": 5468 }, { "epoch": 0.15965086408220458, "grad_norm": 0.3534789979457855, "learning_rate": 9.89214590955715e-06, "loss": 0.2856, "step": 5469 }, { "epoch": 0.15968005604857544, "grad_norm": 0.3786002993583679, "learning_rate": 9.892040629841576e-06, "loss": 0.231, "step": 5470 }, { "epoch": 0.1597092480149463, "grad_norm": 0.38648515939712524, "learning_rate": 9.891935299328455e-06, "loss": 0.2907, "step": 5471 }, { "epoch": 0.15973843998131715, "grad_norm": 0.3475557863712311, "learning_rate": 9.891829918018879e-06, "loss": 0.2564, "step": 5472 }, { "epoch": 0.159767631947688, "grad_norm": 0.41081589460372925, "learning_rate": 9.891724485913943e-06, "loss": 0.2733, "step": 5473 }, { "epoch": 0.15979682391405886, "grad_norm": 0.3706474304199219, "learning_rate": 9.89161900301474e-06, "loss": 0.2438, "step": 5474 }, { "epoch": 0.15982601588042972, "grad_norm": 0.34219875931739807, "learning_rate": 9.89151346932237e-06, "loss": 0.2327, "step": 5475 }, { "epoch": 0.15985520784680057, "grad_norm": 0.34719330072402954, "learning_rate": 9.891407884837922e-06, "loss": 0.2052, "step": 5476 }, { "epoch": 0.1598843998131714, "grad_norm": 0.39941737055778503, "learning_rate": 9.891302249562498e-06, "loss": 0.2146, "step": 5477 }, { "epoch": 0.15991359177954226, "grad_norm": 0.44313013553619385, "learning_rate": 9.891196563497195e-06, "loss": 0.2781, "step": 5478 }, { "epoch": 0.15994278374591311, "grad_norm": 0.3730098307132721, "learning_rate": 9.891090826643106e-06, "loss": 0.2727, "step": 5479 }, { "epoch": 0.15997197571228397, "grad_norm": 0.3333521783351898, "learning_rate": 9.89098503900133e-06, "loss": 0.2226, "step": 5480 }, { "epoch": 0.16000116767865483, "grad_norm": 0.3524441719055176, "learning_rate": 9.89087920057297e-06, "loss": 0.2106, "step": 5481 }, { "epoch": 0.16003035964502568, "grad_norm": 0.36738571524620056, "learning_rate": 9.89077331135912e-06, "loss": 0.2353, "step": 5482 }, { "epoch": 0.16005955161139654, "grad_norm": 0.3736124038696289, "learning_rate": 9.890667371360882e-06, "loss": 0.2282, "step": 5483 }, { "epoch": 0.1600887435777674, "grad_norm": 0.3887513279914856, "learning_rate": 9.890561380579353e-06, "loss": 0.2879, "step": 5484 }, { "epoch": 0.16011793554413825, "grad_norm": 0.3527967929840088, "learning_rate": 9.890455339015638e-06, "loss": 0.2279, "step": 5485 }, { "epoch": 0.1601471275105091, "grad_norm": 0.30731409788131714, "learning_rate": 9.890349246670836e-06, "loss": 0.19, "step": 5486 }, { "epoch": 0.16017631947687996, "grad_norm": 0.32545480132102966, "learning_rate": 9.890243103546049e-06, "loss": 0.2299, "step": 5487 }, { "epoch": 0.16020551144325082, "grad_norm": 0.3581066429615021, "learning_rate": 9.890136909642377e-06, "loss": 0.2485, "step": 5488 }, { "epoch": 0.16023470340962168, "grad_norm": 0.3799624443054199, "learning_rate": 9.890030664960927e-06, "loss": 0.284, "step": 5489 }, { "epoch": 0.16026389537599253, "grad_norm": 0.38806095719337463, "learning_rate": 9.8899243695028e-06, "loss": 0.282, "step": 5490 }, { "epoch": 0.1602930873423634, "grad_norm": 0.3750087320804596, "learning_rate": 9.889818023269097e-06, "loss": 0.2619, "step": 5491 }, { "epoch": 0.16032227930873424, "grad_norm": 0.3848132789134979, "learning_rate": 9.889711626260924e-06, "loss": 0.2805, "step": 5492 }, { "epoch": 0.1603514712751051, "grad_norm": 0.32179757952690125, "learning_rate": 9.88960517847939e-06, "loss": 0.2496, "step": 5493 }, { "epoch": 0.16038066324147596, "grad_norm": 0.36073383688926697, "learning_rate": 9.889498679925595e-06, "loss": 0.2557, "step": 5494 }, { "epoch": 0.1604098552078468, "grad_norm": 0.3731522858142853, "learning_rate": 9.889392130600646e-06, "loss": 0.2631, "step": 5495 }, { "epoch": 0.16043904717421764, "grad_norm": 0.36075669527053833, "learning_rate": 9.889285530505652e-06, "loss": 0.2377, "step": 5496 }, { "epoch": 0.1604682391405885, "grad_norm": 0.3368247151374817, "learning_rate": 9.889178879641717e-06, "loss": 0.2128, "step": 5497 }, { "epoch": 0.16049743110695935, "grad_norm": 0.3097856938838959, "learning_rate": 9.889072178009949e-06, "loss": 0.2595, "step": 5498 }, { "epoch": 0.1605266230733302, "grad_norm": 0.36066901683807373, "learning_rate": 9.888965425611456e-06, "loss": 0.2561, "step": 5499 }, { "epoch": 0.16055581503970107, "grad_norm": 0.32023146748542786, "learning_rate": 9.888858622447348e-06, "loss": 0.202, "step": 5500 }, { "epoch": 0.16058500700607192, "grad_norm": 0.3599381446838379, "learning_rate": 9.888751768518731e-06, "loss": 0.2206, "step": 5501 }, { "epoch": 0.16061419897244278, "grad_norm": 0.38770410418510437, "learning_rate": 9.88864486382672e-06, "loss": 0.3032, "step": 5502 }, { "epoch": 0.16064339093881363, "grad_norm": 0.3549189567565918, "learning_rate": 9.888537908372419e-06, "loss": 0.2228, "step": 5503 }, { "epoch": 0.1606725829051845, "grad_norm": 0.44322648644447327, "learning_rate": 9.88843090215694e-06, "loss": 0.2733, "step": 5504 }, { "epoch": 0.16070177487155535, "grad_norm": 0.43220654129981995, "learning_rate": 9.888323845181399e-06, "loss": 0.2558, "step": 5505 }, { "epoch": 0.1607309668379262, "grad_norm": 0.35661250352859497, "learning_rate": 9.888216737446901e-06, "loss": 0.22, "step": 5506 }, { "epoch": 0.16076015880429706, "grad_norm": 0.36256641149520874, "learning_rate": 9.88810957895456e-06, "loss": 0.2319, "step": 5507 }, { "epoch": 0.16078935077066792, "grad_norm": 0.5943101048469543, "learning_rate": 9.888002369705492e-06, "loss": 0.2749, "step": 5508 }, { "epoch": 0.16081854273703877, "grad_norm": 0.38991600275039673, "learning_rate": 9.887895109700808e-06, "loss": 0.2394, "step": 5509 }, { "epoch": 0.16084773470340963, "grad_norm": 0.4875633120536804, "learning_rate": 9.88778779894162e-06, "loss": 0.2604, "step": 5510 }, { "epoch": 0.16087692666978048, "grad_norm": 0.47511589527130127, "learning_rate": 9.887680437429045e-06, "loss": 0.3062, "step": 5511 }, { "epoch": 0.16090611863615134, "grad_norm": 0.35316532850265503, "learning_rate": 9.887573025164196e-06, "loss": 0.2206, "step": 5512 }, { "epoch": 0.1609353106025222, "grad_norm": 0.3780098855495453, "learning_rate": 9.88746556214819e-06, "loss": 0.2379, "step": 5513 }, { "epoch": 0.16096450256889305, "grad_norm": 0.6111043095588684, "learning_rate": 9.887358048382142e-06, "loss": 0.2705, "step": 5514 }, { "epoch": 0.16099369453526388, "grad_norm": 0.37879878282546997, "learning_rate": 9.887250483867167e-06, "loss": 0.2338, "step": 5515 }, { "epoch": 0.16102288650163474, "grad_norm": 0.35405975580215454, "learning_rate": 9.887142868604387e-06, "loss": 0.2346, "step": 5516 }, { "epoch": 0.1610520784680056, "grad_norm": 0.4076078534126282, "learning_rate": 9.887035202594912e-06, "loss": 0.2431, "step": 5517 }, { "epoch": 0.16108127043437645, "grad_norm": 0.3600206673145294, "learning_rate": 9.886927485839866e-06, "loss": 0.2548, "step": 5518 }, { "epoch": 0.1611104624007473, "grad_norm": 0.4042678773403168, "learning_rate": 9.886819718340364e-06, "loss": 0.2329, "step": 5519 }, { "epoch": 0.16113965436711816, "grad_norm": 0.37016522884368896, "learning_rate": 9.886711900097528e-06, "loss": 0.2327, "step": 5520 }, { "epoch": 0.16116884633348902, "grad_norm": 0.33853879570961, "learning_rate": 9.886604031112473e-06, "loss": 0.2416, "step": 5521 }, { "epoch": 0.16119803829985987, "grad_norm": 0.37363672256469727, "learning_rate": 9.886496111386323e-06, "loss": 0.2944, "step": 5522 }, { "epoch": 0.16122723026623073, "grad_norm": 0.35914286971092224, "learning_rate": 9.886388140920198e-06, "loss": 0.236, "step": 5523 }, { "epoch": 0.1612564222326016, "grad_norm": 0.39290520548820496, "learning_rate": 9.88628011971522e-06, "loss": 0.2212, "step": 5524 }, { "epoch": 0.16128561419897244, "grad_norm": 0.3634202182292938, "learning_rate": 9.886172047772506e-06, "loss": 0.2508, "step": 5525 }, { "epoch": 0.1613148061653433, "grad_norm": 0.5141888856887817, "learning_rate": 9.886063925093185e-06, "loss": 0.2734, "step": 5526 }, { "epoch": 0.16134399813171416, "grad_norm": 0.4439672827720642, "learning_rate": 9.885955751678373e-06, "loss": 0.2404, "step": 5527 }, { "epoch": 0.161373190098085, "grad_norm": 0.479036420583725, "learning_rate": 9.885847527529199e-06, "loss": 0.238, "step": 5528 }, { "epoch": 0.16140238206445587, "grad_norm": 0.3531356155872345, "learning_rate": 9.885739252646783e-06, "loss": 0.2652, "step": 5529 }, { "epoch": 0.16143157403082672, "grad_norm": 0.3937666714191437, "learning_rate": 9.88563092703225e-06, "loss": 0.227, "step": 5530 }, { "epoch": 0.16146076599719758, "grad_norm": 0.3843978941440582, "learning_rate": 9.885522550686726e-06, "loss": 0.2308, "step": 5531 }, { "epoch": 0.16148995796356844, "grad_norm": 0.41006261110305786, "learning_rate": 9.885414123611337e-06, "loss": 0.2348, "step": 5532 }, { "epoch": 0.1615191499299393, "grad_norm": 0.39789247512817383, "learning_rate": 9.885305645807206e-06, "loss": 0.225, "step": 5533 }, { "epoch": 0.16154834189631015, "grad_norm": 0.4253871440887451, "learning_rate": 9.88519711727546e-06, "loss": 0.2262, "step": 5534 }, { "epoch": 0.16157753386268098, "grad_norm": 0.36358603835105896, "learning_rate": 9.885088538017229e-06, "loss": 0.2375, "step": 5535 }, { "epoch": 0.16160672582905183, "grad_norm": 0.3676287531852722, "learning_rate": 9.884979908033638e-06, "loss": 0.2494, "step": 5536 }, { "epoch": 0.1616359177954227, "grad_norm": 0.3219679892063141, "learning_rate": 9.884871227325815e-06, "loss": 0.2699, "step": 5537 }, { "epoch": 0.16166510976179355, "grad_norm": 0.3823200762271881, "learning_rate": 9.884762495894888e-06, "loss": 0.2508, "step": 5538 }, { "epoch": 0.1616943017281644, "grad_norm": 0.35829928517341614, "learning_rate": 9.884653713741988e-06, "loss": 0.2283, "step": 5539 }, { "epoch": 0.16172349369453526, "grad_norm": 0.42007946968078613, "learning_rate": 9.884544880868243e-06, "loss": 0.2707, "step": 5540 }, { "epoch": 0.16175268566090611, "grad_norm": 0.3867291212081909, "learning_rate": 9.884435997274783e-06, "loss": 0.2429, "step": 5541 }, { "epoch": 0.16178187762727697, "grad_norm": 0.3228040933609009, "learning_rate": 9.88432706296274e-06, "loss": 0.2133, "step": 5542 }, { "epoch": 0.16181106959364783, "grad_norm": 0.3591139018535614, "learning_rate": 9.884218077933245e-06, "loss": 0.2113, "step": 5543 }, { "epoch": 0.16184026156001868, "grad_norm": 0.3900845944881439, "learning_rate": 9.884109042187428e-06, "loss": 0.2507, "step": 5544 }, { "epoch": 0.16186945352638954, "grad_norm": 0.3685475289821625, "learning_rate": 9.883999955726422e-06, "loss": 0.238, "step": 5545 }, { "epoch": 0.1618986454927604, "grad_norm": 0.3962872624397278, "learning_rate": 9.88389081855136e-06, "loss": 0.2647, "step": 5546 }, { "epoch": 0.16192783745913125, "grad_norm": 0.3742412328720093, "learning_rate": 9.883781630663377e-06, "loss": 0.2978, "step": 5547 }, { "epoch": 0.1619570294255021, "grad_norm": 0.3755556344985962, "learning_rate": 9.883672392063601e-06, "loss": 0.2472, "step": 5548 }, { "epoch": 0.16198622139187296, "grad_norm": 0.4060307741165161, "learning_rate": 9.883563102753172e-06, "loss": 0.2458, "step": 5549 }, { "epoch": 0.16201541335824382, "grad_norm": 0.3867338299751282, "learning_rate": 9.883453762733224e-06, "loss": 0.2389, "step": 5550 }, { "epoch": 0.16204460532461468, "grad_norm": 0.3487466275691986, "learning_rate": 9.883344372004891e-06, "loss": 0.2236, "step": 5551 }, { "epoch": 0.16207379729098553, "grad_norm": 0.363057404756546, "learning_rate": 9.88323493056931e-06, "loss": 0.2505, "step": 5552 }, { "epoch": 0.1621029892573564, "grad_norm": 0.4364473521709442, "learning_rate": 9.883125438427615e-06, "loss": 0.2498, "step": 5553 }, { "epoch": 0.16213218122372722, "grad_norm": 0.4231235980987549, "learning_rate": 9.883015895580945e-06, "loss": 0.2402, "step": 5554 }, { "epoch": 0.16216137319009807, "grad_norm": 0.39708906412124634, "learning_rate": 9.882906302030437e-06, "loss": 0.2377, "step": 5555 }, { "epoch": 0.16219056515646893, "grad_norm": 0.41868600249290466, "learning_rate": 9.882796657777229e-06, "loss": 0.2444, "step": 5556 }, { "epoch": 0.16221975712283979, "grad_norm": 0.4200860261917114, "learning_rate": 9.88268696282246e-06, "loss": 0.2702, "step": 5557 }, { "epoch": 0.16224894908921064, "grad_norm": 0.3579959571361542, "learning_rate": 9.88257721716727e-06, "loss": 0.222, "step": 5558 }, { "epoch": 0.1622781410555815, "grad_norm": 0.4134002923965454, "learning_rate": 9.882467420812796e-06, "loss": 0.2763, "step": 5559 }, { "epoch": 0.16230733302195235, "grad_norm": 0.37813037633895874, "learning_rate": 9.882357573760179e-06, "loss": 0.2429, "step": 5560 }, { "epoch": 0.1623365249883232, "grad_norm": 0.3758077919483185, "learning_rate": 9.88224767601056e-06, "loss": 0.2579, "step": 5561 }, { "epoch": 0.16236571695469407, "grad_norm": 0.36847034096717834, "learning_rate": 9.88213772756508e-06, "loss": 0.2297, "step": 5562 }, { "epoch": 0.16239490892106492, "grad_norm": 0.3965757191181183, "learning_rate": 9.88202772842488e-06, "loss": 0.2624, "step": 5563 }, { "epoch": 0.16242410088743578, "grad_norm": 0.4673477113246918, "learning_rate": 9.881917678591104e-06, "loss": 0.2731, "step": 5564 }, { "epoch": 0.16245329285380664, "grad_norm": 0.38196220993995667, "learning_rate": 9.881807578064894e-06, "loss": 0.2632, "step": 5565 }, { "epoch": 0.1624824848201775, "grad_norm": 0.3821713328361511, "learning_rate": 9.881697426847392e-06, "loss": 0.231, "step": 5566 }, { "epoch": 0.16251167678654835, "grad_norm": 0.35588306188583374, "learning_rate": 9.881587224939743e-06, "loss": 0.1965, "step": 5567 }, { "epoch": 0.1625408687529192, "grad_norm": 0.362346887588501, "learning_rate": 9.88147697234309e-06, "loss": 0.2441, "step": 5568 }, { "epoch": 0.16257006071929006, "grad_norm": 0.3697637617588043, "learning_rate": 9.881366669058581e-06, "loss": 0.2492, "step": 5569 }, { "epoch": 0.16259925268566092, "grad_norm": 0.40454456210136414, "learning_rate": 9.881256315087357e-06, "loss": 0.2613, "step": 5570 }, { "epoch": 0.16262844465203177, "grad_norm": 0.35281646251678467, "learning_rate": 9.881145910430567e-06, "loss": 0.2343, "step": 5571 }, { "epoch": 0.16265763661840263, "grad_norm": 0.3474698066711426, "learning_rate": 9.881035455089356e-06, "loss": 0.2519, "step": 5572 }, { "epoch": 0.16268682858477346, "grad_norm": 0.4354577660560608, "learning_rate": 9.880924949064872e-06, "loss": 0.2759, "step": 5573 }, { "epoch": 0.1627160205511443, "grad_norm": 0.34155333042144775, "learning_rate": 9.880814392358262e-06, "loss": 0.2224, "step": 5574 }, { "epoch": 0.16274521251751517, "grad_norm": 1.2558441162109375, "learning_rate": 9.880703784970674e-06, "loss": 0.2139, "step": 5575 }, { "epoch": 0.16277440448388603, "grad_norm": 0.35926204919815063, "learning_rate": 9.880593126903254e-06, "loss": 0.2209, "step": 5576 }, { "epoch": 0.16280359645025688, "grad_norm": 0.37098315358161926, "learning_rate": 9.880482418157158e-06, "loss": 0.2733, "step": 5577 }, { "epoch": 0.16283278841662774, "grad_norm": 0.39125409722328186, "learning_rate": 9.880371658733527e-06, "loss": 0.2649, "step": 5578 }, { "epoch": 0.1628619803829986, "grad_norm": 0.3383130729198456, "learning_rate": 9.880260848633517e-06, "loss": 0.2356, "step": 5579 }, { "epoch": 0.16289117234936945, "grad_norm": 0.47125741839408875, "learning_rate": 9.880149987858276e-06, "loss": 0.2488, "step": 5580 }, { "epoch": 0.1629203643157403, "grad_norm": 0.40997785329818726, "learning_rate": 9.880039076408955e-06, "loss": 0.2532, "step": 5581 }, { "epoch": 0.16294955628211116, "grad_norm": 0.8855392932891846, "learning_rate": 9.879928114286708e-06, "loss": 0.2144, "step": 5582 }, { "epoch": 0.16297874824848202, "grad_norm": 0.4354466199874878, "learning_rate": 9.879817101492685e-06, "loss": 0.3135, "step": 5583 }, { "epoch": 0.16300794021485288, "grad_norm": 0.3379516005516052, "learning_rate": 9.879706038028042e-06, "loss": 0.234, "step": 5584 }, { "epoch": 0.16303713218122373, "grad_norm": 0.3542879521846771, "learning_rate": 9.879594923893926e-06, "loss": 0.2304, "step": 5585 }, { "epoch": 0.1630663241475946, "grad_norm": 0.3691854178905487, "learning_rate": 9.879483759091496e-06, "loss": 0.2749, "step": 5586 }, { "epoch": 0.16309551611396544, "grad_norm": 0.3496808707714081, "learning_rate": 9.879372543621904e-06, "loss": 0.2069, "step": 5587 }, { "epoch": 0.1631247080803363, "grad_norm": 0.4959600269794464, "learning_rate": 9.879261277486307e-06, "loss": 0.2607, "step": 5588 }, { "epoch": 0.16315390004670716, "grad_norm": 0.3676203191280365, "learning_rate": 9.879149960685857e-06, "loss": 0.2184, "step": 5589 }, { "epoch": 0.163183092013078, "grad_norm": 0.33432361483573914, "learning_rate": 9.879038593221712e-06, "loss": 0.2245, "step": 5590 }, { "epoch": 0.16321228397944887, "grad_norm": 0.38753175735473633, "learning_rate": 9.87892717509503e-06, "loss": 0.2948, "step": 5591 }, { "epoch": 0.1632414759458197, "grad_norm": 0.3609175980091095, "learning_rate": 9.878815706306965e-06, "loss": 0.2781, "step": 5592 }, { "epoch": 0.16327066791219055, "grad_norm": 0.3544887900352478, "learning_rate": 9.878704186858677e-06, "loss": 0.2344, "step": 5593 }, { "epoch": 0.1632998598785614, "grad_norm": 0.37333056330680847, "learning_rate": 9.878592616751322e-06, "loss": 0.2672, "step": 5594 }, { "epoch": 0.16332905184493227, "grad_norm": 0.4525066614151001, "learning_rate": 9.878480995986058e-06, "loss": 0.3055, "step": 5595 }, { "epoch": 0.16335824381130312, "grad_norm": 0.37473830580711365, "learning_rate": 9.878369324564045e-06, "loss": 0.2326, "step": 5596 }, { "epoch": 0.16338743577767398, "grad_norm": 0.40225058794021606, "learning_rate": 9.878257602486445e-06, "loss": 0.2357, "step": 5597 }, { "epoch": 0.16341662774404483, "grad_norm": 0.3090166747570038, "learning_rate": 9.878145829754415e-06, "loss": 0.1932, "step": 5598 }, { "epoch": 0.1634458197104157, "grad_norm": 0.38902029395103455, "learning_rate": 9.878034006369114e-06, "loss": 0.2668, "step": 5599 }, { "epoch": 0.16347501167678655, "grad_norm": 0.32632309198379517, "learning_rate": 9.87792213233171e-06, "loss": 0.1822, "step": 5600 }, { "epoch": 0.1635042036431574, "grad_norm": 0.36633139848709106, "learning_rate": 9.877810207643357e-06, "loss": 0.2098, "step": 5601 }, { "epoch": 0.16353339560952826, "grad_norm": 0.4094710350036621, "learning_rate": 9.877698232305221e-06, "loss": 0.296, "step": 5602 }, { "epoch": 0.16356258757589912, "grad_norm": 0.4384460747241974, "learning_rate": 9.877586206318464e-06, "loss": 0.2715, "step": 5603 }, { "epoch": 0.16359177954226997, "grad_norm": 0.35939928889274597, "learning_rate": 9.87747412968425e-06, "loss": 0.1866, "step": 5604 }, { "epoch": 0.16362097150864083, "grad_norm": 0.3455398678779602, "learning_rate": 9.877362002403743e-06, "loss": 0.1991, "step": 5605 }, { "epoch": 0.16365016347501168, "grad_norm": 0.3815980553627014, "learning_rate": 9.877249824478106e-06, "loss": 0.2314, "step": 5606 }, { "epoch": 0.16367935544138254, "grad_norm": 0.3851417303085327, "learning_rate": 9.877137595908504e-06, "loss": 0.2786, "step": 5607 }, { "epoch": 0.1637085474077534, "grad_norm": 0.40246710181236267, "learning_rate": 9.877025316696102e-06, "loss": 0.275, "step": 5608 }, { "epoch": 0.16373773937412425, "grad_norm": 0.37086808681488037, "learning_rate": 9.876912986842067e-06, "loss": 0.2351, "step": 5609 }, { "epoch": 0.1637669313404951, "grad_norm": 0.36311575770378113, "learning_rate": 9.876800606347565e-06, "loss": 0.3005, "step": 5610 }, { "epoch": 0.16379612330686594, "grad_norm": 0.36072105169296265, "learning_rate": 9.876688175213763e-06, "loss": 0.2463, "step": 5611 }, { "epoch": 0.1638253152732368, "grad_norm": 0.37683355808258057, "learning_rate": 9.876575693441828e-06, "loss": 0.2366, "step": 5612 }, { "epoch": 0.16385450723960765, "grad_norm": 0.3853118419647217, "learning_rate": 9.876463161032928e-06, "loss": 0.2317, "step": 5613 }, { "epoch": 0.1638836992059785, "grad_norm": 0.3385404348373413, "learning_rate": 9.876350577988231e-06, "loss": 0.2042, "step": 5614 }, { "epoch": 0.16391289117234936, "grad_norm": 0.3582015633583069, "learning_rate": 9.876237944308908e-06, "loss": 0.2794, "step": 5615 }, { "epoch": 0.16394208313872022, "grad_norm": 0.3530372679233551, "learning_rate": 9.876125259996128e-06, "loss": 0.236, "step": 5616 }, { "epoch": 0.16397127510509107, "grad_norm": 0.39063793420791626, "learning_rate": 9.876012525051061e-06, "loss": 0.2634, "step": 5617 }, { "epoch": 0.16400046707146193, "grad_norm": 0.36291301250457764, "learning_rate": 9.875899739474876e-06, "loss": 0.2377, "step": 5618 }, { "epoch": 0.1640296590378328, "grad_norm": 0.32908153533935547, "learning_rate": 9.875786903268745e-06, "loss": 0.2311, "step": 5619 }, { "epoch": 0.16405885100420364, "grad_norm": 0.38587677478790283, "learning_rate": 9.87567401643384e-06, "loss": 0.2344, "step": 5620 }, { "epoch": 0.1640880429705745, "grad_norm": 0.32803910970687866, "learning_rate": 9.875561078971334e-06, "loss": 0.2206, "step": 5621 }, { "epoch": 0.16411723493694536, "grad_norm": 0.4538179337978363, "learning_rate": 9.875448090882397e-06, "loss": 0.2603, "step": 5622 }, { "epoch": 0.1641464269033162, "grad_norm": 0.34923213720321655, "learning_rate": 9.875335052168204e-06, "loss": 0.2257, "step": 5623 }, { "epoch": 0.16417561886968707, "grad_norm": 0.3429395258426666, "learning_rate": 9.875221962829931e-06, "loss": 0.2028, "step": 5624 }, { "epoch": 0.16420481083605792, "grad_norm": 0.40057820081710815, "learning_rate": 9.875108822868749e-06, "loss": 0.1883, "step": 5625 }, { "epoch": 0.16423400280242878, "grad_norm": 0.5251536965370178, "learning_rate": 9.874995632285834e-06, "loss": 0.2198, "step": 5626 }, { "epoch": 0.16426319476879964, "grad_norm": 0.34583696722984314, "learning_rate": 9.874882391082359e-06, "loss": 0.2319, "step": 5627 }, { "epoch": 0.1642923867351705, "grad_norm": 0.37626340985298157, "learning_rate": 9.874769099259504e-06, "loss": 0.2338, "step": 5628 }, { "epoch": 0.16432157870154135, "grad_norm": 0.34818097949028015, "learning_rate": 9.874655756818444e-06, "loss": 0.252, "step": 5629 }, { "epoch": 0.16435077066791218, "grad_norm": 0.3661971986293793, "learning_rate": 9.874542363760354e-06, "loss": 0.2245, "step": 5630 }, { "epoch": 0.16437996263428303, "grad_norm": 0.36571019887924194, "learning_rate": 9.874428920086413e-06, "loss": 0.2328, "step": 5631 }, { "epoch": 0.1644091546006539, "grad_norm": 0.32721051573753357, "learning_rate": 9.874315425797798e-06, "loss": 0.2253, "step": 5632 }, { "epoch": 0.16443834656702475, "grad_norm": 0.3162340819835663, "learning_rate": 9.87420188089569e-06, "loss": 0.2788, "step": 5633 }, { "epoch": 0.1644675385333956, "grad_norm": 0.45227372646331787, "learning_rate": 9.874088285381266e-06, "loss": 0.2423, "step": 5634 }, { "epoch": 0.16449673049976646, "grad_norm": 4.041067600250244, "learning_rate": 9.873974639255706e-06, "loss": 0.273, "step": 5635 }, { "epoch": 0.16452592246613731, "grad_norm": 0.39791619777679443, "learning_rate": 9.873860942520189e-06, "loss": 0.2681, "step": 5636 }, { "epoch": 0.16455511443250817, "grad_norm": 0.3728101849555969, "learning_rate": 9.873747195175898e-06, "loss": 0.2065, "step": 5637 }, { "epoch": 0.16458430639887903, "grad_norm": 0.3726769983768463, "learning_rate": 9.87363339722401e-06, "loss": 0.2767, "step": 5638 }, { "epoch": 0.16461349836524988, "grad_norm": 0.39760154485702515, "learning_rate": 9.873519548665712e-06, "loss": 0.2527, "step": 5639 }, { "epoch": 0.16464269033162074, "grad_norm": 0.37803205847740173, "learning_rate": 9.873405649502182e-06, "loss": 0.273, "step": 5640 }, { "epoch": 0.1646718822979916, "grad_norm": 0.36534127593040466, "learning_rate": 9.873291699734603e-06, "loss": 0.273, "step": 5641 }, { "epoch": 0.16470107426436245, "grad_norm": 0.36861297488212585, "learning_rate": 9.873177699364162e-06, "loss": 0.2063, "step": 5642 }, { "epoch": 0.1647302662307333, "grad_norm": 0.3869031071662903, "learning_rate": 9.873063648392038e-06, "loss": 0.2607, "step": 5643 }, { "epoch": 0.16475945819710416, "grad_norm": 0.34608277678489685, "learning_rate": 9.872949546819418e-06, "loss": 0.2149, "step": 5644 }, { "epoch": 0.16478865016347502, "grad_norm": 0.4871911108493805, "learning_rate": 9.872835394647487e-06, "loss": 0.2645, "step": 5645 }, { "epoch": 0.16481784212984588, "grad_norm": 0.32763198018074036, "learning_rate": 9.872721191877429e-06, "loss": 0.2489, "step": 5646 }, { "epoch": 0.16484703409621673, "grad_norm": 0.3787272274494171, "learning_rate": 9.87260693851043e-06, "loss": 0.3225, "step": 5647 }, { "epoch": 0.1648762260625876, "grad_norm": 0.3982228636741638, "learning_rate": 9.872492634547677e-06, "loss": 0.2715, "step": 5648 }, { "epoch": 0.16490541802895842, "grad_norm": 0.3618912994861603, "learning_rate": 9.872378279990356e-06, "loss": 0.2887, "step": 5649 }, { "epoch": 0.16493460999532927, "grad_norm": 0.4632430672645569, "learning_rate": 9.872263874839656e-06, "loss": 0.2483, "step": 5650 }, { "epoch": 0.16496380196170013, "grad_norm": 0.33670327067375183, "learning_rate": 9.872149419096761e-06, "loss": 0.2351, "step": 5651 }, { "epoch": 0.16499299392807099, "grad_norm": 0.396935373544693, "learning_rate": 9.872034912762866e-06, "loss": 0.2565, "step": 5652 }, { "epoch": 0.16502218589444184, "grad_norm": 0.3346981108188629, "learning_rate": 9.871920355839155e-06, "loss": 0.1989, "step": 5653 }, { "epoch": 0.1650513778608127, "grad_norm": 0.32106441259384155, "learning_rate": 9.871805748326819e-06, "loss": 0.2137, "step": 5654 }, { "epoch": 0.16508056982718355, "grad_norm": 1.433119297027588, "learning_rate": 9.871691090227048e-06, "loss": 0.2572, "step": 5655 }, { "epoch": 0.1651097617935544, "grad_norm": 0.3616636395454407, "learning_rate": 9.871576381541034e-06, "loss": 0.2368, "step": 5656 }, { "epoch": 0.16513895375992527, "grad_norm": 0.317107230424881, "learning_rate": 9.871461622269965e-06, "loss": 0.2065, "step": 5657 }, { "epoch": 0.16516814572629612, "grad_norm": 0.3981776833534241, "learning_rate": 9.871346812415035e-06, "loss": 0.2371, "step": 5658 }, { "epoch": 0.16519733769266698, "grad_norm": 0.3755050599575043, "learning_rate": 9.871231951977435e-06, "loss": 0.2622, "step": 5659 }, { "epoch": 0.16522652965903784, "grad_norm": 0.3576641380786896, "learning_rate": 9.87111704095836e-06, "loss": 0.2218, "step": 5660 }, { "epoch": 0.1652557216254087, "grad_norm": 0.4186430275440216, "learning_rate": 9.871002079359e-06, "loss": 0.2382, "step": 5661 }, { "epoch": 0.16528491359177955, "grad_norm": 0.32140910625457764, "learning_rate": 9.87088706718055e-06, "loss": 0.2393, "step": 5662 }, { "epoch": 0.1653141055581504, "grad_norm": 0.39724481105804443, "learning_rate": 9.870772004424204e-06, "loss": 0.2353, "step": 5663 }, { "epoch": 0.16534329752452126, "grad_norm": 0.3688586354255676, "learning_rate": 9.870656891091157e-06, "loss": 0.2373, "step": 5664 }, { "epoch": 0.16537248949089212, "grad_norm": 0.3524506688117981, "learning_rate": 9.870541727182605e-06, "loss": 0.2128, "step": 5665 }, { "epoch": 0.16540168145726297, "grad_norm": 0.37909117341041565, "learning_rate": 9.870426512699745e-06, "loss": 0.2368, "step": 5666 }, { "epoch": 0.16543087342363383, "grad_norm": 0.4383576512336731, "learning_rate": 9.87031124764377e-06, "loss": 0.3023, "step": 5667 }, { "epoch": 0.16546006539000466, "grad_norm": 0.4305744469165802, "learning_rate": 9.870195932015879e-06, "loss": 0.3287, "step": 5668 }, { "epoch": 0.1654892573563755, "grad_norm": 0.470462441444397, "learning_rate": 9.870080565817268e-06, "loss": 0.2581, "step": 5669 }, { "epoch": 0.16551844932274637, "grad_norm": 0.3995879292488098, "learning_rate": 9.869965149049135e-06, "loss": 0.2665, "step": 5670 }, { "epoch": 0.16554764128911723, "grad_norm": 0.38770928978919983, "learning_rate": 9.869849681712681e-06, "loss": 0.2379, "step": 5671 }, { "epoch": 0.16557683325548808, "grad_norm": 0.3539842665195465, "learning_rate": 9.869734163809102e-06, "loss": 0.2193, "step": 5672 }, { "epoch": 0.16560602522185894, "grad_norm": 0.3468116521835327, "learning_rate": 9.869618595339601e-06, "loss": 0.2275, "step": 5673 }, { "epoch": 0.1656352171882298, "grad_norm": 0.34702953696250916, "learning_rate": 9.869502976305374e-06, "loss": 0.236, "step": 5674 }, { "epoch": 0.16566440915460065, "grad_norm": 0.3729865849018097, "learning_rate": 9.869387306707623e-06, "loss": 0.2288, "step": 5675 }, { "epoch": 0.1656936011209715, "grad_norm": 0.3965055048465729, "learning_rate": 9.86927158654755e-06, "loss": 0.2484, "step": 5676 }, { "epoch": 0.16572279308734236, "grad_norm": 0.3857606053352356, "learning_rate": 9.869155815826357e-06, "loss": 0.2728, "step": 5677 }, { "epoch": 0.16575198505371322, "grad_norm": 0.34551316499710083, "learning_rate": 9.869039994545244e-06, "loss": 0.1864, "step": 5678 }, { "epoch": 0.16578117702008408, "grad_norm": 0.36623716354370117, "learning_rate": 9.868924122705415e-06, "loss": 0.2048, "step": 5679 }, { "epoch": 0.16581036898645493, "grad_norm": 0.3708086311817169, "learning_rate": 9.868808200308074e-06, "loss": 0.2647, "step": 5680 }, { "epoch": 0.1658395609528258, "grad_norm": 0.3707043528556824, "learning_rate": 9.868692227354421e-06, "loss": 0.2628, "step": 5681 }, { "epoch": 0.16586875291919664, "grad_norm": 0.39213675260543823, "learning_rate": 9.868576203845665e-06, "loss": 0.2599, "step": 5682 }, { "epoch": 0.1658979448855675, "grad_norm": 0.38145875930786133, "learning_rate": 9.86846012978301e-06, "loss": 0.2193, "step": 5683 }, { "epoch": 0.16592713685193836, "grad_norm": 0.37047064304351807, "learning_rate": 9.868344005167659e-06, "loss": 0.3116, "step": 5684 }, { "epoch": 0.1659563288183092, "grad_norm": 0.33215227723121643, "learning_rate": 9.868227830000818e-06, "loss": 0.2477, "step": 5685 }, { "epoch": 0.16598552078468007, "grad_norm": 0.41090887784957886, "learning_rate": 9.868111604283694e-06, "loss": 0.2276, "step": 5686 }, { "epoch": 0.16601471275105092, "grad_norm": 0.3708434998989105, "learning_rate": 9.867995328017494e-06, "loss": 0.297, "step": 5687 }, { "epoch": 0.16604390471742175, "grad_norm": 0.3304678499698639, "learning_rate": 9.867879001203427e-06, "loss": 0.2541, "step": 5688 }, { "epoch": 0.1660730966837926, "grad_norm": 0.39145535230636597, "learning_rate": 9.867762623842696e-06, "loss": 0.2324, "step": 5689 }, { "epoch": 0.16610228865016347, "grad_norm": 0.4137992858886719, "learning_rate": 9.867646195936516e-06, "loss": 0.2568, "step": 5690 }, { "epoch": 0.16613148061653432, "grad_norm": 0.3647124469280243, "learning_rate": 9.867529717486091e-06, "loss": 0.2851, "step": 5691 }, { "epoch": 0.16616067258290518, "grad_norm": 0.32998305559158325, "learning_rate": 9.867413188492632e-06, "loss": 0.2116, "step": 5692 }, { "epoch": 0.16618986454927603, "grad_norm": 0.3886692225933075, "learning_rate": 9.867296608957351e-06, "loss": 0.2752, "step": 5693 }, { "epoch": 0.1662190565156469, "grad_norm": 0.3339649736881256, "learning_rate": 9.867179978881454e-06, "loss": 0.2502, "step": 5694 }, { "epoch": 0.16624824848201775, "grad_norm": 0.3066997528076172, "learning_rate": 9.867063298266157e-06, "loss": 0.2119, "step": 5695 }, { "epoch": 0.1662774404483886, "grad_norm": 0.34477540850639343, "learning_rate": 9.866946567112668e-06, "loss": 0.2402, "step": 5696 }, { "epoch": 0.16630663241475946, "grad_norm": 0.844340980052948, "learning_rate": 9.866829785422201e-06, "loss": 0.2513, "step": 5697 }, { "epoch": 0.16633582438113031, "grad_norm": 0.3404916524887085, "learning_rate": 9.866712953195967e-06, "loss": 0.2025, "step": 5698 }, { "epoch": 0.16636501634750117, "grad_norm": 0.38461461663246155, "learning_rate": 9.866596070435181e-06, "loss": 0.2631, "step": 5699 }, { "epoch": 0.16639420831387203, "grad_norm": 0.3513292372226715, "learning_rate": 9.866479137141055e-06, "loss": 0.2791, "step": 5700 }, { "epoch": 0.16642340028024288, "grad_norm": 0.42931461334228516, "learning_rate": 9.866362153314805e-06, "loss": 0.3067, "step": 5701 }, { "epoch": 0.16645259224661374, "grad_norm": 0.4077410399913788, "learning_rate": 9.866245118957644e-06, "loss": 0.309, "step": 5702 }, { "epoch": 0.1664817842129846, "grad_norm": 0.3696530759334564, "learning_rate": 9.86612803407079e-06, "loss": 0.2994, "step": 5703 }, { "epoch": 0.16651097617935545, "grad_norm": 0.528140664100647, "learning_rate": 9.866010898655454e-06, "loss": 0.3289, "step": 5704 }, { "epoch": 0.1665401681457263, "grad_norm": 0.37459835410118103, "learning_rate": 9.865893712712857e-06, "loss": 0.2601, "step": 5705 }, { "epoch": 0.16656936011209716, "grad_norm": 0.3677349090576172, "learning_rate": 9.865776476244213e-06, "loss": 0.2401, "step": 5706 }, { "epoch": 0.166598552078468, "grad_norm": 0.35872727632522583, "learning_rate": 9.86565918925074e-06, "loss": 0.2697, "step": 5707 }, { "epoch": 0.16662774404483885, "grad_norm": 0.399972140789032, "learning_rate": 9.865541851733656e-06, "loss": 0.2958, "step": 5708 }, { "epoch": 0.1666569360112097, "grad_norm": 0.4449617266654968, "learning_rate": 9.86542446369418e-06, "loss": 0.2855, "step": 5709 }, { "epoch": 0.16668612797758056, "grad_norm": 0.3626452386379242, "learning_rate": 9.86530702513353e-06, "loss": 0.2689, "step": 5710 }, { "epoch": 0.16671531994395142, "grad_norm": 0.35795027017593384, "learning_rate": 9.865189536052929e-06, "loss": 0.2012, "step": 5711 }, { "epoch": 0.16674451191032227, "grad_norm": 0.45408180356025696, "learning_rate": 9.86507199645359e-06, "loss": 0.2092, "step": 5712 }, { "epoch": 0.16677370387669313, "grad_norm": 0.37364181876182556, "learning_rate": 9.86495440633674e-06, "loss": 0.2411, "step": 5713 }, { "epoch": 0.166802895843064, "grad_norm": 0.35772478580474854, "learning_rate": 9.864836765703596e-06, "loss": 0.2285, "step": 5714 }, { "epoch": 0.16683208780943484, "grad_norm": 0.4814978539943695, "learning_rate": 9.86471907455538e-06, "loss": 0.2356, "step": 5715 }, { "epoch": 0.1668612797758057, "grad_norm": 0.37791669368743896, "learning_rate": 9.864601332893316e-06, "loss": 0.2604, "step": 5716 }, { "epoch": 0.16689047174217655, "grad_norm": 0.40508612990379333, "learning_rate": 9.864483540718625e-06, "loss": 0.3047, "step": 5717 }, { "epoch": 0.1669196637085474, "grad_norm": 0.36826252937316895, "learning_rate": 9.864365698032533e-06, "loss": 0.2457, "step": 5718 }, { "epoch": 0.16694885567491827, "grad_norm": 0.37061500549316406, "learning_rate": 9.86424780483626e-06, "loss": 0.2271, "step": 5719 }, { "epoch": 0.16697804764128912, "grad_norm": 0.3848637044429779, "learning_rate": 9.864129861131032e-06, "loss": 0.2942, "step": 5720 }, { "epoch": 0.16700723960765998, "grad_norm": 0.389019638299942, "learning_rate": 9.864011866918073e-06, "loss": 0.2432, "step": 5721 }, { "epoch": 0.16703643157403084, "grad_norm": 0.3885013163089752, "learning_rate": 9.863893822198607e-06, "loss": 0.2323, "step": 5722 }, { "epoch": 0.1670656235404017, "grad_norm": 0.36493492126464844, "learning_rate": 9.863775726973864e-06, "loss": 0.2743, "step": 5723 }, { "epoch": 0.16709481550677255, "grad_norm": 0.44653332233428955, "learning_rate": 9.863657581245065e-06, "loss": 0.2584, "step": 5724 }, { "epoch": 0.1671240074731434, "grad_norm": 0.4893183708190918, "learning_rate": 9.86353938501344e-06, "loss": 0.2565, "step": 5725 }, { "epoch": 0.16715319943951423, "grad_norm": 0.41440531611442566, "learning_rate": 9.863421138280216e-06, "loss": 0.2204, "step": 5726 }, { "epoch": 0.1671823914058851, "grad_norm": 0.3739166557788849, "learning_rate": 9.86330284104662e-06, "loss": 0.1923, "step": 5727 }, { "epoch": 0.16721158337225595, "grad_norm": 0.5665526390075684, "learning_rate": 9.863184493313881e-06, "loss": 0.2107, "step": 5728 }, { "epoch": 0.1672407753386268, "grad_norm": 0.3765982389450073, "learning_rate": 9.863066095083227e-06, "loss": 0.2669, "step": 5729 }, { "epoch": 0.16726996730499766, "grad_norm": 0.4009424149990082, "learning_rate": 9.862947646355889e-06, "loss": 0.2518, "step": 5730 }, { "epoch": 0.1672991592713685, "grad_norm": 0.39761075377464294, "learning_rate": 9.862829147133097e-06, "loss": 0.2348, "step": 5731 }, { "epoch": 0.16732835123773937, "grad_norm": 0.4525940418243408, "learning_rate": 9.862710597416079e-06, "loss": 0.3054, "step": 5732 }, { "epoch": 0.16735754320411023, "grad_norm": 0.43866410851478577, "learning_rate": 9.862591997206066e-06, "loss": 0.2793, "step": 5733 }, { "epoch": 0.16738673517048108, "grad_norm": 0.3146584630012512, "learning_rate": 9.862473346504293e-06, "loss": 0.1827, "step": 5734 }, { "epoch": 0.16741592713685194, "grad_norm": 0.38757428526878357, "learning_rate": 9.862354645311991e-06, "loss": 0.2436, "step": 5735 }, { "epoch": 0.1674451191032228, "grad_norm": 0.35088860988616943, "learning_rate": 9.862235893630389e-06, "loss": 0.2418, "step": 5736 }, { "epoch": 0.16747431106959365, "grad_norm": 0.3691183626651764, "learning_rate": 9.862117091460725e-06, "loss": 0.248, "step": 5737 }, { "epoch": 0.1675035030359645, "grad_norm": 0.418782114982605, "learning_rate": 9.861998238804229e-06, "loss": 0.2549, "step": 5738 }, { "epoch": 0.16753269500233536, "grad_norm": 0.4229492247104645, "learning_rate": 9.861879335662137e-06, "loss": 0.2161, "step": 5739 }, { "epoch": 0.16756188696870622, "grad_norm": 0.43944960832595825, "learning_rate": 9.861760382035683e-06, "loss": 0.278, "step": 5740 }, { "epoch": 0.16759107893507708, "grad_norm": 0.41448259353637695, "learning_rate": 9.8616413779261e-06, "loss": 0.2462, "step": 5741 }, { "epoch": 0.16762027090144793, "grad_norm": 0.3836265504360199, "learning_rate": 9.86152232333463e-06, "loss": 0.2957, "step": 5742 }, { "epoch": 0.1676494628678188, "grad_norm": 0.4584037661552429, "learning_rate": 9.861403218262501e-06, "loss": 0.3053, "step": 5743 }, { "epoch": 0.16767865483418964, "grad_norm": 0.41657644510269165, "learning_rate": 9.861284062710958e-06, "loss": 0.27, "step": 5744 }, { "epoch": 0.16770784680056047, "grad_norm": 0.49823087453842163, "learning_rate": 9.861164856681231e-06, "loss": 0.3284, "step": 5745 }, { "epoch": 0.16773703876693133, "grad_norm": 0.3087967336177826, "learning_rate": 9.861045600174564e-06, "loss": 0.1775, "step": 5746 }, { "epoch": 0.16776623073330219, "grad_norm": 0.4333990216255188, "learning_rate": 9.86092629319219e-06, "loss": 0.3217, "step": 5747 }, { "epoch": 0.16779542269967304, "grad_norm": 0.3115239143371582, "learning_rate": 9.860806935735349e-06, "loss": 0.1927, "step": 5748 }, { "epoch": 0.1678246146660439, "grad_norm": 0.3944535255432129, "learning_rate": 9.860687527805284e-06, "loss": 0.3017, "step": 5749 }, { "epoch": 0.16785380663241475, "grad_norm": 0.3706987202167511, "learning_rate": 9.860568069403233e-06, "loss": 0.2499, "step": 5750 }, { "epoch": 0.1678829985987856, "grad_norm": 0.5674363374710083, "learning_rate": 9.860448560530434e-06, "loss": 0.2366, "step": 5751 }, { "epoch": 0.16791219056515647, "grad_norm": 0.3737957775592804, "learning_rate": 9.86032900118813e-06, "loss": 0.2871, "step": 5752 }, { "epoch": 0.16794138253152732, "grad_norm": 0.35973766446113586, "learning_rate": 9.860209391377564e-06, "loss": 0.2501, "step": 5753 }, { "epoch": 0.16797057449789818, "grad_norm": 0.47201502323150635, "learning_rate": 9.860089731099974e-06, "loss": 0.2636, "step": 5754 }, { "epoch": 0.16799976646426903, "grad_norm": 0.34646111726760864, "learning_rate": 9.859970020356606e-06, "loss": 0.2608, "step": 5755 }, { "epoch": 0.1680289584306399, "grad_norm": 0.36486348509788513, "learning_rate": 9.8598502591487e-06, "loss": 0.2778, "step": 5756 }, { "epoch": 0.16805815039701075, "grad_norm": 0.5585585832595825, "learning_rate": 9.859730447477504e-06, "loss": 0.2296, "step": 5757 }, { "epoch": 0.1680873423633816, "grad_norm": 0.33569273352622986, "learning_rate": 9.85961058534426e-06, "loss": 0.2137, "step": 5758 }, { "epoch": 0.16811653432975246, "grad_norm": 0.34142690896987915, "learning_rate": 9.85949067275021e-06, "loss": 0.2189, "step": 5759 }, { "epoch": 0.16814572629612332, "grad_norm": 0.9201494455337524, "learning_rate": 9.859370709696601e-06, "loss": 0.2624, "step": 5760 }, { "epoch": 0.16817491826249417, "grad_norm": 0.8457196950912476, "learning_rate": 9.85925069618468e-06, "loss": 0.2701, "step": 5761 }, { "epoch": 0.16820411022886503, "grad_norm": 0.35863998532295227, "learning_rate": 9.859130632215692e-06, "loss": 0.2314, "step": 5762 }, { "epoch": 0.16823330219523588, "grad_norm": 0.6372201442718506, "learning_rate": 9.859010517790884e-06, "loss": 0.2616, "step": 5763 }, { "epoch": 0.1682624941616067, "grad_norm": 0.35321202874183655, "learning_rate": 9.858890352911503e-06, "loss": 0.2396, "step": 5764 }, { "epoch": 0.16829168612797757, "grad_norm": 0.368419885635376, "learning_rate": 9.858770137578797e-06, "loss": 0.2686, "step": 5765 }, { "epoch": 0.16832087809434843, "grad_norm": 0.3782636225223541, "learning_rate": 9.858649871794012e-06, "loss": 0.2701, "step": 5766 }, { "epoch": 0.16835007006071928, "grad_norm": 0.3735816180706024, "learning_rate": 9.858529555558402e-06, "loss": 0.2314, "step": 5767 }, { "epoch": 0.16837926202709014, "grad_norm": 0.4428650736808777, "learning_rate": 9.85840918887321e-06, "loss": 0.2797, "step": 5768 }, { "epoch": 0.168408453993461, "grad_norm": 0.5293373465538025, "learning_rate": 9.858288771739693e-06, "loss": 0.2683, "step": 5769 }, { "epoch": 0.16843764595983185, "grad_norm": 0.3749667704105377, "learning_rate": 9.858168304159095e-06, "loss": 0.2304, "step": 5770 }, { "epoch": 0.1684668379262027, "grad_norm": 0.4136238992214203, "learning_rate": 9.858047786132669e-06, "loss": 0.2486, "step": 5771 }, { "epoch": 0.16849602989257356, "grad_norm": 0.4062165319919586, "learning_rate": 9.857927217661667e-06, "loss": 0.2638, "step": 5772 }, { "epoch": 0.16852522185894442, "grad_norm": 0.40433192253112793, "learning_rate": 9.857806598747342e-06, "loss": 0.287, "step": 5773 }, { "epoch": 0.16855441382531527, "grad_norm": 0.37029585242271423, "learning_rate": 9.857685929390944e-06, "loss": 0.2551, "step": 5774 }, { "epoch": 0.16858360579168613, "grad_norm": 0.38483765721321106, "learning_rate": 9.857565209593727e-06, "loss": 0.2615, "step": 5775 }, { "epoch": 0.168612797758057, "grad_norm": 0.4196484684944153, "learning_rate": 9.857444439356945e-06, "loss": 0.2168, "step": 5776 }, { "epoch": 0.16864198972442784, "grad_norm": 0.45362529158592224, "learning_rate": 9.857323618681853e-06, "loss": 0.262, "step": 5777 }, { "epoch": 0.1686711816907987, "grad_norm": 0.3907710611820221, "learning_rate": 9.857202747569704e-06, "loss": 0.2588, "step": 5778 }, { "epoch": 0.16870037365716956, "grad_norm": 0.34480375051498413, "learning_rate": 9.857081826021753e-06, "loss": 0.2125, "step": 5779 }, { "epoch": 0.1687295656235404, "grad_norm": 0.36163824796676636, "learning_rate": 9.856960854039254e-06, "loss": 0.2605, "step": 5780 }, { "epoch": 0.16875875758991127, "grad_norm": 0.3876838684082031, "learning_rate": 9.856839831623468e-06, "loss": 0.2475, "step": 5781 }, { "epoch": 0.16878794955628212, "grad_norm": 0.49013736844062805, "learning_rate": 9.856718758775647e-06, "loss": 0.3433, "step": 5782 }, { "epoch": 0.16881714152265295, "grad_norm": 0.3402310609817505, "learning_rate": 9.856597635497051e-06, "loss": 0.2212, "step": 5783 }, { "epoch": 0.1688463334890238, "grad_norm": 0.4136098027229309, "learning_rate": 9.856476461788936e-06, "loss": 0.2346, "step": 5784 }, { "epoch": 0.16887552545539466, "grad_norm": 0.4133526086807251, "learning_rate": 9.856355237652562e-06, "loss": 0.27, "step": 5785 }, { "epoch": 0.16890471742176552, "grad_norm": 0.3694087564945221, "learning_rate": 9.856233963089186e-06, "loss": 0.2049, "step": 5786 }, { "epoch": 0.16893390938813638, "grad_norm": 0.40649473667144775, "learning_rate": 9.856112638100068e-06, "loss": 0.2455, "step": 5787 }, { "epoch": 0.16896310135450723, "grad_norm": 0.3560042381286621, "learning_rate": 9.855991262686468e-06, "loss": 0.2318, "step": 5788 }, { "epoch": 0.1689922933208781, "grad_norm": 0.6438620686531067, "learning_rate": 9.855869836849645e-06, "loss": 0.2634, "step": 5789 }, { "epoch": 0.16902148528724895, "grad_norm": 0.4366737902164459, "learning_rate": 9.855748360590863e-06, "loss": 0.2813, "step": 5790 }, { "epoch": 0.1690506772536198, "grad_norm": 0.4133366346359253, "learning_rate": 9.85562683391138e-06, "loss": 0.2816, "step": 5791 }, { "epoch": 0.16907986921999066, "grad_norm": 0.39529645442962646, "learning_rate": 9.855505256812459e-06, "loss": 0.247, "step": 5792 }, { "epoch": 0.16910906118636151, "grad_norm": 0.3853701651096344, "learning_rate": 9.855383629295365e-06, "loss": 0.237, "step": 5793 }, { "epoch": 0.16913825315273237, "grad_norm": 0.3798966705799103, "learning_rate": 9.855261951361357e-06, "loss": 0.2796, "step": 5794 }, { "epoch": 0.16916744511910323, "grad_norm": 0.3889104425907135, "learning_rate": 9.855140223011699e-06, "loss": 0.2413, "step": 5795 }, { "epoch": 0.16919663708547408, "grad_norm": 0.3572200536727905, "learning_rate": 9.855018444247656e-06, "loss": 0.2505, "step": 5796 }, { "epoch": 0.16922582905184494, "grad_norm": 0.3564649224281311, "learning_rate": 9.854896615070495e-06, "loss": 0.2384, "step": 5797 }, { "epoch": 0.1692550210182158, "grad_norm": 0.3765699565410614, "learning_rate": 9.854774735481478e-06, "loss": 0.1878, "step": 5798 }, { "epoch": 0.16928421298458665, "grad_norm": 0.34590256214141846, "learning_rate": 9.85465280548187e-06, "loss": 0.2569, "step": 5799 }, { "epoch": 0.1693134049509575, "grad_norm": 0.3800309896469116, "learning_rate": 9.85453082507294e-06, "loss": 0.2934, "step": 5800 }, { "epoch": 0.16934259691732836, "grad_norm": 0.41087764501571655, "learning_rate": 9.85440879425595e-06, "loss": 0.254, "step": 5801 }, { "epoch": 0.1693717888836992, "grad_norm": 0.3856433928012848, "learning_rate": 9.854286713032172e-06, "loss": 0.2576, "step": 5802 }, { "epoch": 0.16940098085007005, "grad_norm": 0.32519131898880005, "learning_rate": 9.85416458140287e-06, "loss": 0.1992, "step": 5803 }, { "epoch": 0.1694301728164409, "grad_norm": 0.32811421155929565, "learning_rate": 9.854042399369317e-06, "loss": 0.2158, "step": 5804 }, { "epoch": 0.16945936478281176, "grad_norm": 0.3962342441082001, "learning_rate": 9.853920166932776e-06, "loss": 0.2379, "step": 5805 }, { "epoch": 0.16948855674918262, "grad_norm": 0.37002018094062805, "learning_rate": 9.853797884094519e-06, "loss": 0.2399, "step": 5806 }, { "epoch": 0.16951774871555347, "grad_norm": 0.44050633907318115, "learning_rate": 9.853675550855817e-06, "loss": 0.2817, "step": 5807 }, { "epoch": 0.16954694068192433, "grad_norm": 0.3489953279495239, "learning_rate": 9.853553167217937e-06, "loss": 0.2097, "step": 5808 }, { "epoch": 0.16957613264829519, "grad_norm": 0.3824370205402374, "learning_rate": 9.853430733182153e-06, "loss": 0.2479, "step": 5809 }, { "epoch": 0.16960532461466604, "grad_norm": 0.41036203503608704, "learning_rate": 9.853308248749734e-06, "loss": 0.2427, "step": 5810 }, { "epoch": 0.1696345165810369, "grad_norm": 0.3971814215183258, "learning_rate": 9.853185713921953e-06, "loss": 0.2282, "step": 5811 }, { "epoch": 0.16966370854740775, "grad_norm": 0.3692556917667389, "learning_rate": 9.853063128700083e-06, "loss": 0.2318, "step": 5812 }, { "epoch": 0.1696929005137786, "grad_norm": 0.346373051404953, "learning_rate": 9.852940493085395e-06, "loss": 0.2421, "step": 5813 }, { "epoch": 0.16972209248014947, "grad_norm": 0.405859112739563, "learning_rate": 9.852817807079165e-06, "loss": 0.2117, "step": 5814 }, { "epoch": 0.16975128444652032, "grad_norm": 0.4071277678012848, "learning_rate": 9.852695070682663e-06, "loss": 0.3142, "step": 5815 }, { "epoch": 0.16978047641289118, "grad_norm": 0.42290109395980835, "learning_rate": 9.852572283897168e-06, "loss": 0.2924, "step": 5816 }, { "epoch": 0.16980966837926204, "grad_norm": 0.3663732707500458, "learning_rate": 9.852449446723951e-06, "loss": 0.2331, "step": 5817 }, { "epoch": 0.1698388603456329, "grad_norm": 0.35139209032058716, "learning_rate": 9.85232655916429e-06, "loss": 0.2389, "step": 5818 }, { "epoch": 0.16986805231200375, "grad_norm": 0.37385088205337524, "learning_rate": 9.852203621219461e-06, "loss": 0.266, "step": 5819 }, { "epoch": 0.1698972442783746, "grad_norm": 0.2992192804813385, "learning_rate": 9.85208063289074e-06, "loss": 0.1825, "step": 5820 }, { "epoch": 0.16992643624474543, "grad_norm": 0.3591594696044922, "learning_rate": 9.851957594179402e-06, "loss": 0.2181, "step": 5821 }, { "epoch": 0.1699556282111163, "grad_norm": 0.3752632737159729, "learning_rate": 9.851834505086728e-06, "loss": 0.2539, "step": 5822 }, { "epoch": 0.16998482017748714, "grad_norm": 0.48214805126190186, "learning_rate": 9.851711365613995e-06, "loss": 0.2657, "step": 5823 }, { "epoch": 0.170014012143858, "grad_norm": 0.37270796298980713, "learning_rate": 9.85158817576248e-06, "loss": 0.2023, "step": 5824 }, { "epoch": 0.17004320411022886, "grad_norm": 0.3524751663208008, "learning_rate": 9.851464935533466e-06, "loss": 0.2529, "step": 5825 }, { "epoch": 0.1700723960765997, "grad_norm": 0.3562328815460205, "learning_rate": 9.851341644928229e-06, "loss": 0.2234, "step": 5826 }, { "epoch": 0.17010158804297057, "grad_norm": 0.369781494140625, "learning_rate": 9.85121830394805e-06, "loss": 0.2233, "step": 5827 }, { "epoch": 0.17013078000934143, "grad_norm": 0.46591508388519287, "learning_rate": 9.85109491259421e-06, "loss": 0.2592, "step": 5828 }, { "epoch": 0.17015997197571228, "grad_norm": 0.3619404137134552, "learning_rate": 9.85097147086799e-06, "loss": 0.2595, "step": 5829 }, { "epoch": 0.17018916394208314, "grad_norm": 0.36893609166145325, "learning_rate": 9.850847978770673e-06, "loss": 0.2661, "step": 5830 }, { "epoch": 0.170218355908454, "grad_norm": 0.36645713448524475, "learning_rate": 9.85072443630354e-06, "loss": 0.2181, "step": 5831 }, { "epoch": 0.17024754787482485, "grad_norm": 0.6921669840812683, "learning_rate": 9.850600843467876e-06, "loss": 0.2249, "step": 5832 }, { "epoch": 0.1702767398411957, "grad_norm": 0.3648401200771332, "learning_rate": 9.85047720026496e-06, "loss": 0.2909, "step": 5833 }, { "epoch": 0.17030593180756656, "grad_norm": 0.3713054060935974, "learning_rate": 9.850353506696083e-06, "loss": 0.2897, "step": 5834 }, { "epoch": 0.17033512377393742, "grad_norm": 0.37350142002105713, "learning_rate": 9.85022976276252e-06, "loss": 0.2706, "step": 5835 }, { "epoch": 0.17036431574030828, "grad_norm": 0.38529685139656067, "learning_rate": 9.850105968465564e-06, "loss": 0.2292, "step": 5836 }, { "epoch": 0.17039350770667913, "grad_norm": 0.3632667660713196, "learning_rate": 9.849982123806496e-06, "loss": 0.2305, "step": 5837 }, { "epoch": 0.17042269967305, "grad_norm": 0.31438198685646057, "learning_rate": 9.849858228786603e-06, "loss": 0.2044, "step": 5838 }, { "epoch": 0.17045189163942084, "grad_norm": 0.3865368664264679, "learning_rate": 9.849734283407173e-06, "loss": 0.1961, "step": 5839 }, { "epoch": 0.17048108360579167, "grad_norm": 0.35683467984199524, "learning_rate": 9.849610287669491e-06, "loss": 0.2755, "step": 5840 }, { "epoch": 0.17051027557216253, "grad_norm": 0.4044800400733948, "learning_rate": 9.849486241574845e-06, "loss": 0.2069, "step": 5841 }, { "epoch": 0.17053946753853338, "grad_norm": 0.37795132398605347, "learning_rate": 9.849362145124523e-06, "loss": 0.1958, "step": 5842 }, { "epoch": 0.17056865950490424, "grad_norm": 0.2919192910194397, "learning_rate": 9.849237998319816e-06, "loss": 0.1773, "step": 5843 }, { "epoch": 0.1705978514712751, "grad_norm": 0.34600961208343506, "learning_rate": 9.84911380116201e-06, "loss": 0.2577, "step": 5844 }, { "epoch": 0.17062704343764595, "grad_norm": 0.39072275161743164, "learning_rate": 9.848989553652395e-06, "loss": 0.2415, "step": 5845 }, { "epoch": 0.1706562354040168, "grad_norm": 0.4302222430706024, "learning_rate": 9.848865255792262e-06, "loss": 0.322, "step": 5846 }, { "epoch": 0.17068542737038767, "grad_norm": 0.33449482917785645, "learning_rate": 9.848740907582903e-06, "loss": 0.2591, "step": 5847 }, { "epoch": 0.17071461933675852, "grad_norm": 0.3765369653701782, "learning_rate": 9.848616509025606e-06, "loss": 0.2716, "step": 5848 }, { "epoch": 0.17074381130312938, "grad_norm": 0.3490040898323059, "learning_rate": 9.848492060121666e-06, "loss": 0.2128, "step": 5849 }, { "epoch": 0.17077300326950023, "grad_norm": 0.34899935126304626, "learning_rate": 9.848367560872373e-06, "loss": 0.2385, "step": 5850 }, { "epoch": 0.1708021952358711, "grad_norm": 0.3519740700721741, "learning_rate": 9.848243011279019e-06, "loss": 0.2544, "step": 5851 }, { "epoch": 0.17083138720224195, "grad_norm": 0.36495697498321533, "learning_rate": 9.848118411342902e-06, "loss": 0.2754, "step": 5852 }, { "epoch": 0.1708605791686128, "grad_norm": 0.3648940622806549, "learning_rate": 9.84799376106531e-06, "loss": 0.2159, "step": 5853 }, { "epoch": 0.17088977113498366, "grad_norm": 0.374472051858902, "learning_rate": 9.847869060447542e-06, "loss": 0.2811, "step": 5854 }, { "epoch": 0.17091896310135452, "grad_norm": 0.34892475605010986, "learning_rate": 9.847744309490888e-06, "loss": 0.2297, "step": 5855 }, { "epoch": 0.17094815506772537, "grad_norm": 0.35417917370796204, "learning_rate": 9.847619508196647e-06, "loss": 0.2344, "step": 5856 }, { "epoch": 0.17097734703409623, "grad_norm": 0.3635896146297455, "learning_rate": 9.847494656566114e-06, "loss": 0.2723, "step": 5857 }, { "epoch": 0.17100653900046708, "grad_norm": 0.4343005418777466, "learning_rate": 9.847369754600587e-06, "loss": 0.3003, "step": 5858 }, { "epoch": 0.17103573096683794, "grad_norm": 0.398476779460907, "learning_rate": 9.84724480230136e-06, "loss": 0.2902, "step": 5859 }, { "epoch": 0.17106492293320877, "grad_norm": 0.365262508392334, "learning_rate": 9.847119799669732e-06, "loss": 0.2264, "step": 5860 }, { "epoch": 0.17109411489957962, "grad_norm": 0.39342445135116577, "learning_rate": 9.846994746707002e-06, "loss": 0.3132, "step": 5861 }, { "epoch": 0.17112330686595048, "grad_norm": 0.29688531160354614, "learning_rate": 9.846869643414466e-06, "loss": 0.1942, "step": 5862 }, { "epoch": 0.17115249883232134, "grad_norm": 0.34081801772117615, "learning_rate": 9.846744489793424e-06, "loss": 0.2529, "step": 5863 }, { "epoch": 0.1711816907986922, "grad_norm": 0.36548030376434326, "learning_rate": 9.846619285845177e-06, "loss": 0.2296, "step": 5864 }, { "epoch": 0.17121088276506305, "grad_norm": 0.37958255410194397, "learning_rate": 9.846494031571024e-06, "loss": 0.2789, "step": 5865 }, { "epoch": 0.1712400747314339, "grad_norm": 0.6980586051940918, "learning_rate": 9.846368726972265e-06, "loss": 0.2564, "step": 5866 }, { "epoch": 0.17126926669780476, "grad_norm": 0.35034215450286865, "learning_rate": 9.846243372050203e-06, "loss": 0.2659, "step": 5867 }, { "epoch": 0.17129845866417562, "grad_norm": 0.36109355092048645, "learning_rate": 9.846117966806137e-06, "loss": 0.2121, "step": 5868 }, { "epoch": 0.17132765063054647, "grad_norm": 0.3275224566459656, "learning_rate": 9.84599251124137e-06, "loss": 0.2644, "step": 5869 }, { "epoch": 0.17135684259691733, "grad_norm": 0.431180864572525, "learning_rate": 9.845867005357209e-06, "loss": 0.2256, "step": 5870 }, { "epoch": 0.1713860345632882, "grad_norm": 0.38636472821235657, "learning_rate": 9.845741449154951e-06, "loss": 0.2011, "step": 5871 }, { "epoch": 0.17141522652965904, "grad_norm": 0.3501206338405609, "learning_rate": 9.845615842635901e-06, "loss": 0.2996, "step": 5872 }, { "epoch": 0.1714444184960299, "grad_norm": 0.33617520332336426, "learning_rate": 9.845490185801366e-06, "loss": 0.2188, "step": 5873 }, { "epoch": 0.17147361046240076, "grad_norm": 0.4000872075557709, "learning_rate": 9.845364478652649e-06, "loss": 0.2886, "step": 5874 }, { "epoch": 0.1715028024287716, "grad_norm": 0.3509872257709503, "learning_rate": 9.845238721191055e-06, "loss": 0.2227, "step": 5875 }, { "epoch": 0.17153199439514247, "grad_norm": 0.3819586932659149, "learning_rate": 9.845112913417892e-06, "loss": 0.2726, "step": 5876 }, { "epoch": 0.17156118636151332, "grad_norm": 0.3436245322227478, "learning_rate": 9.844987055334464e-06, "loss": 0.2304, "step": 5877 }, { "epoch": 0.17159037832788418, "grad_norm": 0.3396916687488556, "learning_rate": 9.84486114694208e-06, "loss": 0.2285, "step": 5878 }, { "epoch": 0.171619570294255, "grad_norm": 0.3544590175151825, "learning_rate": 9.844735188242042e-06, "loss": 0.2088, "step": 5879 }, { "epoch": 0.17164876226062586, "grad_norm": 0.42159345746040344, "learning_rate": 9.844609179235667e-06, "loss": 0.3094, "step": 5880 }, { "epoch": 0.17167795422699672, "grad_norm": 0.35222354531288147, "learning_rate": 9.844483119924255e-06, "loss": 0.2494, "step": 5881 }, { "epoch": 0.17170714619336758, "grad_norm": 0.33220258355140686, "learning_rate": 9.84435701030912e-06, "loss": 0.2612, "step": 5882 }, { "epoch": 0.17173633815973843, "grad_norm": 0.4142720401287079, "learning_rate": 9.84423085039157e-06, "loss": 0.2344, "step": 5883 }, { "epoch": 0.1717655301261093, "grad_norm": 0.35476648807525635, "learning_rate": 9.844104640172913e-06, "loss": 0.2591, "step": 5884 }, { "epoch": 0.17179472209248015, "grad_norm": 0.3793242871761322, "learning_rate": 9.843978379654462e-06, "loss": 0.2783, "step": 5885 }, { "epoch": 0.171823914058851, "grad_norm": 0.3401639759540558, "learning_rate": 9.843852068837528e-06, "loss": 0.217, "step": 5886 }, { "epoch": 0.17185310602522186, "grad_norm": 0.3235505223274231, "learning_rate": 9.843725707723423e-06, "loss": 0.2544, "step": 5887 }, { "epoch": 0.17188229799159271, "grad_norm": 0.3434911072254181, "learning_rate": 9.843599296313457e-06, "loss": 0.2369, "step": 5888 }, { "epoch": 0.17191148995796357, "grad_norm": 0.35032886266708374, "learning_rate": 9.843472834608944e-06, "loss": 0.2263, "step": 5889 }, { "epoch": 0.17194068192433443, "grad_norm": 0.46401447057724, "learning_rate": 9.843346322611196e-06, "loss": 0.2495, "step": 5890 }, { "epoch": 0.17196987389070528, "grad_norm": 0.3396805226802826, "learning_rate": 9.84321976032153e-06, "loss": 0.2339, "step": 5891 }, { "epoch": 0.17199906585707614, "grad_norm": 0.317653626203537, "learning_rate": 9.843093147741255e-06, "loss": 0.2334, "step": 5892 }, { "epoch": 0.172028257823447, "grad_norm": 0.33054912090301514, "learning_rate": 9.84296648487169e-06, "loss": 0.2278, "step": 5893 }, { "epoch": 0.17205744978981785, "grad_norm": 0.3529880940914154, "learning_rate": 9.842839771714147e-06, "loss": 0.2569, "step": 5894 }, { "epoch": 0.1720866417561887, "grad_norm": 0.4357850253582001, "learning_rate": 9.842713008269946e-06, "loss": 0.2756, "step": 5895 }, { "epoch": 0.17211583372255956, "grad_norm": 0.38792818784713745, "learning_rate": 9.8425861945404e-06, "loss": 0.317, "step": 5896 }, { "epoch": 0.17214502568893042, "grad_norm": 0.3790002763271332, "learning_rate": 9.842459330526826e-06, "loss": 0.219, "step": 5897 }, { "epoch": 0.17217421765530125, "grad_norm": 0.33670544624328613, "learning_rate": 9.84233241623054e-06, "loss": 0.2114, "step": 5898 }, { "epoch": 0.1722034096216721, "grad_norm": 0.4076324701309204, "learning_rate": 9.842205451652864e-06, "loss": 0.2502, "step": 5899 }, { "epoch": 0.17223260158804296, "grad_norm": 0.3438786268234253, "learning_rate": 9.842078436795113e-06, "loss": 0.2362, "step": 5900 }, { "epoch": 0.17226179355441382, "grad_norm": 0.3613925278186798, "learning_rate": 9.841951371658609e-06, "loss": 0.2333, "step": 5901 }, { "epoch": 0.17229098552078467, "grad_norm": 0.39692091941833496, "learning_rate": 9.841824256244667e-06, "loss": 0.2917, "step": 5902 }, { "epoch": 0.17232017748715553, "grad_norm": 0.39877912402153015, "learning_rate": 9.84169709055461e-06, "loss": 0.2192, "step": 5903 }, { "epoch": 0.17234936945352639, "grad_norm": 0.37006640434265137, "learning_rate": 9.841569874589757e-06, "loss": 0.215, "step": 5904 }, { "epoch": 0.17237856141989724, "grad_norm": 0.3542163372039795, "learning_rate": 9.84144260835143e-06, "loss": 0.2105, "step": 5905 }, { "epoch": 0.1724077533862681, "grad_norm": 0.34276294708251953, "learning_rate": 9.841315291840951e-06, "loss": 0.236, "step": 5906 }, { "epoch": 0.17243694535263895, "grad_norm": 0.3677482604980469, "learning_rate": 9.841187925059641e-06, "loss": 0.2154, "step": 5907 }, { "epoch": 0.1724661373190098, "grad_norm": 0.34486424922943115, "learning_rate": 9.841060508008822e-06, "loss": 0.2466, "step": 5908 }, { "epoch": 0.17249532928538067, "grad_norm": 0.3472020924091339, "learning_rate": 9.840933040689819e-06, "loss": 0.2278, "step": 5909 }, { "epoch": 0.17252452125175152, "grad_norm": 0.4169604480266571, "learning_rate": 9.840805523103953e-06, "loss": 0.2936, "step": 5910 }, { "epoch": 0.17255371321812238, "grad_norm": 0.3353227376937866, "learning_rate": 9.84067795525255e-06, "loss": 0.2792, "step": 5911 }, { "epoch": 0.17258290518449323, "grad_norm": 0.34150463342666626, "learning_rate": 9.840550337136935e-06, "loss": 0.2242, "step": 5912 }, { "epoch": 0.1726120971508641, "grad_norm": 0.38890036940574646, "learning_rate": 9.840422668758431e-06, "loss": 0.2415, "step": 5913 }, { "epoch": 0.17264128911723495, "grad_norm": 0.39590781927108765, "learning_rate": 9.840294950118365e-06, "loss": 0.2798, "step": 5914 }, { "epoch": 0.1726704810836058, "grad_norm": 0.34061774611473083, "learning_rate": 9.840167181218065e-06, "loss": 0.2714, "step": 5915 }, { "epoch": 0.17269967304997666, "grad_norm": 0.31559547781944275, "learning_rate": 9.840039362058854e-06, "loss": 0.2607, "step": 5916 }, { "epoch": 0.1727288650163475, "grad_norm": 0.3317153751850128, "learning_rate": 9.839911492642062e-06, "loss": 0.2234, "step": 5917 }, { "epoch": 0.17275805698271834, "grad_norm": 0.3288109004497528, "learning_rate": 9.839783572969015e-06, "loss": 0.2714, "step": 5918 }, { "epoch": 0.1727872489490892, "grad_norm": 0.40996497869491577, "learning_rate": 9.839655603041043e-06, "loss": 0.274, "step": 5919 }, { "epoch": 0.17281644091546006, "grad_norm": 0.33921900391578674, "learning_rate": 9.839527582859473e-06, "loss": 0.2831, "step": 5920 }, { "epoch": 0.1728456328818309, "grad_norm": 0.4022150933742523, "learning_rate": 9.839399512425636e-06, "loss": 0.2696, "step": 5921 }, { "epoch": 0.17287482484820177, "grad_norm": 0.3280971348285675, "learning_rate": 9.83927139174086e-06, "loss": 0.2266, "step": 5922 }, { "epoch": 0.17290401681457263, "grad_norm": 0.8237663507461548, "learning_rate": 9.839143220806478e-06, "loss": 0.2799, "step": 5923 }, { "epoch": 0.17293320878094348, "grad_norm": 0.3560483753681183, "learning_rate": 9.839014999623819e-06, "loss": 0.262, "step": 5924 }, { "epoch": 0.17296240074731434, "grad_norm": 0.3270917236804962, "learning_rate": 9.838886728194215e-06, "loss": 0.2223, "step": 5925 }, { "epoch": 0.1729915927136852, "grad_norm": 0.37707120180130005, "learning_rate": 9.838758406518996e-06, "loss": 0.2226, "step": 5926 }, { "epoch": 0.17302078468005605, "grad_norm": 0.341262549161911, "learning_rate": 9.838630034599496e-06, "loss": 0.2281, "step": 5927 }, { "epoch": 0.1730499766464269, "grad_norm": 0.37747517228126526, "learning_rate": 9.83850161243705e-06, "loss": 0.2529, "step": 5928 }, { "epoch": 0.17307916861279776, "grad_norm": 0.34731847047805786, "learning_rate": 9.838373140032991e-06, "loss": 0.2683, "step": 5929 }, { "epoch": 0.17310836057916862, "grad_norm": 0.39130666851997375, "learning_rate": 9.838244617388648e-06, "loss": 0.2566, "step": 5930 }, { "epoch": 0.17313755254553947, "grad_norm": 0.3742479681968689, "learning_rate": 9.838116044505361e-06, "loss": 0.2176, "step": 5931 }, { "epoch": 0.17316674451191033, "grad_norm": 0.3351251184940338, "learning_rate": 9.837987421384464e-06, "loss": 0.2789, "step": 5932 }, { "epoch": 0.1731959364782812, "grad_norm": 0.5138500332832336, "learning_rate": 9.83785874802729e-06, "loss": 0.2603, "step": 5933 }, { "epoch": 0.17322512844465204, "grad_norm": 0.4703466296195984, "learning_rate": 9.837730024435179e-06, "loss": 0.2752, "step": 5934 }, { "epoch": 0.1732543204110229, "grad_norm": 0.522929310798645, "learning_rate": 9.837601250609466e-06, "loss": 0.2034, "step": 5935 }, { "epoch": 0.17328351237739373, "grad_norm": 0.32115641236305237, "learning_rate": 9.837472426551484e-06, "loss": 0.2244, "step": 5936 }, { "epoch": 0.17331270434376458, "grad_norm": 0.3434072434902191, "learning_rate": 9.837343552262577e-06, "loss": 0.2468, "step": 5937 }, { "epoch": 0.17334189631013544, "grad_norm": 0.3170584440231323, "learning_rate": 9.83721462774408e-06, "loss": 0.2203, "step": 5938 }, { "epoch": 0.1733710882765063, "grad_norm": 0.3726261556148529, "learning_rate": 9.837085652997333e-06, "loss": 0.2721, "step": 5939 }, { "epoch": 0.17340028024287715, "grad_norm": 0.3353911340236664, "learning_rate": 9.836956628023675e-06, "loss": 0.281, "step": 5940 }, { "epoch": 0.173429472209248, "grad_norm": 0.37866103649139404, "learning_rate": 9.836827552824445e-06, "loss": 0.2628, "step": 5941 }, { "epoch": 0.17345866417561887, "grad_norm": 0.45462849736213684, "learning_rate": 9.836698427400983e-06, "loss": 0.2792, "step": 5942 }, { "epoch": 0.17348785614198972, "grad_norm": 0.3609941601753235, "learning_rate": 9.836569251754631e-06, "loss": 0.2263, "step": 5943 }, { "epoch": 0.17351704810836058, "grad_norm": 0.34339484572410583, "learning_rate": 9.836440025886729e-06, "loss": 0.2459, "step": 5944 }, { "epoch": 0.17354624007473143, "grad_norm": 0.36264684796333313, "learning_rate": 9.836310749798618e-06, "loss": 0.2378, "step": 5945 }, { "epoch": 0.1735754320411023, "grad_norm": 0.3707607090473175, "learning_rate": 9.836181423491646e-06, "loss": 0.2847, "step": 5946 }, { "epoch": 0.17360462400747315, "grad_norm": 0.5009554624557495, "learning_rate": 9.836052046967148e-06, "loss": 0.2662, "step": 5947 }, { "epoch": 0.173633815973844, "grad_norm": 0.34221383929252625, "learning_rate": 9.835922620226474e-06, "loss": 0.2069, "step": 5948 }, { "epoch": 0.17366300794021486, "grad_norm": 0.38453444838523865, "learning_rate": 9.835793143270963e-06, "loss": 0.2362, "step": 5949 }, { "epoch": 0.17369219990658571, "grad_norm": 0.3626887798309326, "learning_rate": 9.835663616101962e-06, "loss": 0.2466, "step": 5950 }, { "epoch": 0.17372139187295657, "grad_norm": 0.32834869623184204, "learning_rate": 9.835534038720818e-06, "loss": 0.2501, "step": 5951 }, { "epoch": 0.17375058383932743, "grad_norm": 0.3975251615047455, "learning_rate": 9.835404411128871e-06, "loss": 0.2551, "step": 5952 }, { "epoch": 0.17377977580569828, "grad_norm": 0.3654007017612457, "learning_rate": 9.835274733327472e-06, "loss": 0.2457, "step": 5953 }, { "epoch": 0.17380896777206914, "grad_norm": 0.3470443785190582, "learning_rate": 9.835145005317966e-06, "loss": 0.2183, "step": 5954 }, { "epoch": 0.17383815973843997, "grad_norm": 0.3415882885456085, "learning_rate": 9.835015227101697e-06, "loss": 0.2634, "step": 5955 }, { "epoch": 0.17386735170481082, "grad_norm": 0.3958148956298828, "learning_rate": 9.834885398680018e-06, "loss": 0.262, "step": 5956 }, { "epoch": 0.17389654367118168, "grad_norm": 0.38140133023262024, "learning_rate": 9.834755520054273e-06, "loss": 0.2484, "step": 5957 }, { "epoch": 0.17392573563755254, "grad_norm": 0.35753268003463745, "learning_rate": 9.834625591225813e-06, "loss": 0.267, "step": 5958 }, { "epoch": 0.1739549276039234, "grad_norm": 0.38045045733451843, "learning_rate": 9.834495612195985e-06, "loss": 0.2593, "step": 5959 }, { "epoch": 0.17398411957029425, "grad_norm": 0.2942357361316681, "learning_rate": 9.83436558296614e-06, "loss": 0.2011, "step": 5960 }, { "epoch": 0.1740133115366651, "grad_norm": 0.3419192135334015, "learning_rate": 9.834235503537628e-06, "loss": 0.2699, "step": 5961 }, { "epoch": 0.17404250350303596, "grad_norm": 0.3446478247642517, "learning_rate": 9.8341053739118e-06, "loss": 0.2513, "step": 5962 }, { "epoch": 0.17407169546940682, "grad_norm": 0.3854847550392151, "learning_rate": 9.833975194090006e-06, "loss": 0.2806, "step": 5963 }, { "epoch": 0.17410088743577767, "grad_norm": 0.3247230350971222, "learning_rate": 9.8338449640736e-06, "loss": 0.2552, "step": 5964 }, { "epoch": 0.17413007940214853, "grad_norm": 0.35713985562324524, "learning_rate": 9.833714683863933e-06, "loss": 0.2693, "step": 5965 }, { "epoch": 0.17415927136851939, "grad_norm": 0.32262206077575684, "learning_rate": 9.833584353462356e-06, "loss": 0.2259, "step": 5966 }, { "epoch": 0.17418846333489024, "grad_norm": 0.3422575891017914, "learning_rate": 9.833453972870227e-06, "loss": 0.2417, "step": 5967 }, { "epoch": 0.1742176553012611, "grad_norm": 0.3796158730983734, "learning_rate": 9.833323542088893e-06, "loss": 0.2503, "step": 5968 }, { "epoch": 0.17424684726763195, "grad_norm": 0.34150588512420654, "learning_rate": 9.833193061119714e-06, "loss": 0.2371, "step": 5969 }, { "epoch": 0.1742760392340028, "grad_norm": 0.3165051341056824, "learning_rate": 9.833062529964044e-06, "loss": 0.2486, "step": 5970 }, { "epoch": 0.17430523120037367, "grad_norm": 0.3983754515647888, "learning_rate": 9.832931948623238e-06, "loss": 0.2827, "step": 5971 }, { "epoch": 0.17433442316674452, "grad_norm": 0.32708463072776794, "learning_rate": 9.83280131709865e-06, "loss": 0.2249, "step": 5972 }, { "epoch": 0.17436361513311538, "grad_norm": 0.34877628087997437, "learning_rate": 9.832670635391638e-06, "loss": 0.2492, "step": 5973 }, { "epoch": 0.1743928070994862, "grad_norm": 0.4064958095550537, "learning_rate": 9.83253990350356e-06, "loss": 0.2807, "step": 5974 }, { "epoch": 0.17442199906585706, "grad_norm": 0.33492204546928406, "learning_rate": 9.83240912143577e-06, "loss": 0.2281, "step": 5975 }, { "epoch": 0.17445119103222792, "grad_norm": 0.33290353417396545, "learning_rate": 9.83227828918963e-06, "loss": 0.2443, "step": 5976 }, { "epoch": 0.17448038299859878, "grad_norm": 0.31384000182151794, "learning_rate": 9.832147406766498e-06, "loss": 0.2015, "step": 5977 }, { "epoch": 0.17450957496496963, "grad_norm": 0.3604603111743927, "learning_rate": 9.83201647416773e-06, "loss": 0.2518, "step": 5978 }, { "epoch": 0.1745387669313405, "grad_norm": 0.3251144587993622, "learning_rate": 9.831885491394688e-06, "loss": 0.2064, "step": 5979 }, { "epoch": 0.17456795889771135, "grad_norm": 0.3839867115020752, "learning_rate": 9.83175445844873e-06, "loss": 0.2841, "step": 5980 }, { "epoch": 0.1745971508640822, "grad_norm": 0.33596333861351013, "learning_rate": 9.831623375331221e-06, "loss": 0.2646, "step": 5981 }, { "epoch": 0.17462634283045306, "grad_norm": 0.33194413781166077, "learning_rate": 9.831492242043517e-06, "loss": 0.2507, "step": 5982 }, { "epoch": 0.1746555347968239, "grad_norm": 0.3569190800189972, "learning_rate": 9.831361058586984e-06, "loss": 0.2571, "step": 5983 }, { "epoch": 0.17468472676319477, "grad_norm": 0.32950419187545776, "learning_rate": 9.83122982496298e-06, "loss": 0.2274, "step": 5984 }, { "epoch": 0.17471391872956563, "grad_norm": 0.33815646171569824, "learning_rate": 9.831098541172871e-06, "loss": 0.2363, "step": 5985 }, { "epoch": 0.17474311069593648, "grad_norm": 0.3394589424133301, "learning_rate": 9.83096720721802e-06, "loss": 0.2461, "step": 5986 }, { "epoch": 0.17477230266230734, "grad_norm": 0.2992366552352905, "learning_rate": 9.830835823099787e-06, "loss": 0.2308, "step": 5987 }, { "epoch": 0.1748014946286782, "grad_norm": 0.37776637077331543, "learning_rate": 9.83070438881954e-06, "loss": 0.2467, "step": 5988 }, { "epoch": 0.17483068659504905, "grad_norm": 0.4154837429523468, "learning_rate": 9.830572904378644e-06, "loss": 0.2275, "step": 5989 }, { "epoch": 0.1748598785614199, "grad_norm": 0.4039034843444824, "learning_rate": 9.830441369778463e-06, "loss": 0.2591, "step": 5990 }, { "epoch": 0.17488907052779076, "grad_norm": 0.33445310592651367, "learning_rate": 9.830309785020362e-06, "loss": 0.2863, "step": 5991 }, { "epoch": 0.17491826249416162, "grad_norm": 0.5039597153663635, "learning_rate": 9.830178150105708e-06, "loss": 0.2669, "step": 5992 }, { "epoch": 0.17494745446053245, "grad_norm": 0.3480200469493866, "learning_rate": 9.830046465035869e-06, "loss": 0.2914, "step": 5993 }, { "epoch": 0.1749766464269033, "grad_norm": 0.36901766061782837, "learning_rate": 9.82991472981221e-06, "loss": 0.2565, "step": 5994 }, { "epoch": 0.17500583839327416, "grad_norm": 0.35604336857795715, "learning_rate": 9.829782944436101e-06, "loss": 0.2483, "step": 5995 }, { "epoch": 0.17503503035964502, "grad_norm": 0.3735916316509247, "learning_rate": 9.82965110890891e-06, "loss": 0.2645, "step": 5996 }, { "epoch": 0.17506422232601587, "grad_norm": 0.33730536699295044, "learning_rate": 9.829519223232006e-06, "loss": 0.2362, "step": 5997 }, { "epoch": 0.17509341429238673, "grad_norm": 0.39418235421180725, "learning_rate": 9.82938728740676e-06, "loss": 0.2776, "step": 5998 }, { "epoch": 0.17512260625875758, "grad_norm": 0.35651475191116333, "learning_rate": 9.829255301434538e-06, "loss": 0.2209, "step": 5999 }, { "epoch": 0.17515179822512844, "grad_norm": 0.34294241666793823, "learning_rate": 9.829123265316713e-06, "loss": 0.265, "step": 6000 }, { "epoch": 0.1751809901914993, "grad_norm": 0.323222815990448, "learning_rate": 9.828991179054655e-06, "loss": 0.197, "step": 6001 }, { "epoch": 0.17521018215787015, "grad_norm": 0.3421569764614105, "learning_rate": 9.828859042649736e-06, "loss": 0.2593, "step": 6002 }, { "epoch": 0.175239374124241, "grad_norm": 0.37557095289230347, "learning_rate": 9.82872685610333e-06, "loss": 0.2841, "step": 6003 }, { "epoch": 0.17526856609061187, "grad_norm": 0.3161599040031433, "learning_rate": 9.828594619416807e-06, "loss": 0.2375, "step": 6004 }, { "epoch": 0.17529775805698272, "grad_norm": 0.32670673727989197, "learning_rate": 9.828462332591543e-06, "loss": 0.2457, "step": 6005 }, { "epoch": 0.17532695002335358, "grad_norm": 0.3450542986392975, "learning_rate": 9.828329995628908e-06, "loss": 0.2654, "step": 6006 }, { "epoch": 0.17535614198972443, "grad_norm": 0.3352234959602356, "learning_rate": 9.828197608530277e-06, "loss": 0.2354, "step": 6007 }, { "epoch": 0.1753853339560953, "grad_norm": 0.3434920012950897, "learning_rate": 9.828065171297026e-06, "loss": 0.2717, "step": 6008 }, { "epoch": 0.17541452592246615, "grad_norm": 0.38995909690856934, "learning_rate": 9.827932683930528e-06, "loss": 0.2442, "step": 6009 }, { "epoch": 0.175443717888837, "grad_norm": 0.31753769516944885, "learning_rate": 9.827800146432163e-06, "loss": 0.2005, "step": 6010 }, { "epoch": 0.17547290985520786, "grad_norm": 0.41023844480514526, "learning_rate": 9.827667558803303e-06, "loss": 0.2487, "step": 6011 }, { "epoch": 0.17550210182157872, "grad_norm": 0.33558493852615356, "learning_rate": 9.827534921045328e-06, "loss": 0.196, "step": 6012 }, { "epoch": 0.17553129378794954, "grad_norm": 0.3078063726425171, "learning_rate": 9.827402233159612e-06, "loss": 0.2417, "step": 6013 }, { "epoch": 0.1755604857543204, "grad_norm": 0.36336904764175415, "learning_rate": 9.827269495147536e-06, "loss": 0.2513, "step": 6014 }, { "epoch": 0.17558967772069126, "grad_norm": 0.33643409609794617, "learning_rate": 9.827136707010476e-06, "loss": 0.3105, "step": 6015 }, { "epoch": 0.1756188696870621, "grad_norm": 0.40792036056518555, "learning_rate": 9.82700386874981e-06, "loss": 0.2752, "step": 6016 }, { "epoch": 0.17564806165343297, "grad_norm": 0.3131808340549469, "learning_rate": 9.826870980366921e-06, "loss": 0.2342, "step": 6017 }, { "epoch": 0.17567725361980382, "grad_norm": 0.3340066373348236, "learning_rate": 9.826738041863186e-06, "loss": 0.2508, "step": 6018 }, { "epoch": 0.17570644558617468, "grad_norm": 0.4216330051422119, "learning_rate": 9.826605053239985e-06, "loss": 0.2596, "step": 6019 }, { "epoch": 0.17573563755254554, "grad_norm": 0.3274863064289093, "learning_rate": 9.826472014498702e-06, "loss": 0.2133, "step": 6020 }, { "epoch": 0.1757648295189164, "grad_norm": 0.3755006194114685, "learning_rate": 9.826338925640717e-06, "loss": 0.2868, "step": 6021 }, { "epoch": 0.17579402148528725, "grad_norm": 0.3530025780200958, "learning_rate": 9.826205786667409e-06, "loss": 0.2487, "step": 6022 }, { "epoch": 0.1758232134516581, "grad_norm": 0.34525081515312195, "learning_rate": 9.826072597580164e-06, "loss": 0.2661, "step": 6023 }, { "epoch": 0.17585240541802896, "grad_norm": 0.3352433443069458, "learning_rate": 9.825939358380365e-06, "loss": 0.255, "step": 6024 }, { "epoch": 0.17588159738439982, "grad_norm": 0.33994776010513306, "learning_rate": 9.825806069069394e-06, "loss": 0.2248, "step": 6025 }, { "epoch": 0.17591078935077067, "grad_norm": 0.36753717064857483, "learning_rate": 9.825672729648636e-06, "loss": 0.2821, "step": 6026 }, { "epoch": 0.17593998131714153, "grad_norm": 0.3127255439758301, "learning_rate": 9.825539340119474e-06, "loss": 0.2331, "step": 6027 }, { "epoch": 0.1759691732835124, "grad_norm": 0.3394196033477783, "learning_rate": 9.825405900483294e-06, "loss": 0.2478, "step": 6028 }, { "epoch": 0.17599836524988324, "grad_norm": 0.3272722065448761, "learning_rate": 9.825272410741483e-06, "loss": 0.2382, "step": 6029 }, { "epoch": 0.1760275572162541, "grad_norm": 0.3629751205444336, "learning_rate": 9.825138870895425e-06, "loss": 0.2393, "step": 6030 }, { "epoch": 0.17605674918262496, "grad_norm": 0.3685038387775421, "learning_rate": 9.825005280946507e-06, "loss": 0.2939, "step": 6031 }, { "epoch": 0.17608594114899578, "grad_norm": 0.4035274088382721, "learning_rate": 9.824871640896118e-06, "loss": 0.2553, "step": 6032 }, { "epoch": 0.17611513311536664, "grad_norm": 0.3575400412082672, "learning_rate": 9.824737950745644e-06, "loss": 0.2096, "step": 6033 }, { "epoch": 0.1761443250817375, "grad_norm": 0.35038530826568604, "learning_rate": 9.824604210496473e-06, "loss": 0.2708, "step": 6034 }, { "epoch": 0.17617351704810835, "grad_norm": 0.3504578173160553, "learning_rate": 9.824470420149994e-06, "loss": 0.2418, "step": 6035 }, { "epoch": 0.1762027090144792, "grad_norm": 0.3700982928276062, "learning_rate": 9.824336579707598e-06, "loss": 0.2385, "step": 6036 }, { "epoch": 0.17623190098085006, "grad_norm": 0.36719560623168945, "learning_rate": 9.824202689170672e-06, "loss": 0.2426, "step": 6037 }, { "epoch": 0.17626109294722092, "grad_norm": 0.3609688878059387, "learning_rate": 9.824068748540609e-06, "loss": 0.2801, "step": 6038 }, { "epoch": 0.17629028491359178, "grad_norm": 0.3401261866092682, "learning_rate": 9.823934757818796e-06, "loss": 0.2049, "step": 6039 }, { "epoch": 0.17631947687996263, "grad_norm": 0.325732558965683, "learning_rate": 9.823800717006628e-06, "loss": 0.2672, "step": 6040 }, { "epoch": 0.1763486688463335, "grad_norm": 0.332377165555954, "learning_rate": 9.823666626105497e-06, "loss": 0.2336, "step": 6041 }, { "epoch": 0.17637786081270435, "grad_norm": 0.3520449995994568, "learning_rate": 9.823532485116791e-06, "loss": 0.3048, "step": 6042 }, { "epoch": 0.1764070527790752, "grad_norm": 0.3368121087551117, "learning_rate": 9.823398294041908e-06, "loss": 0.2084, "step": 6043 }, { "epoch": 0.17643624474544606, "grad_norm": 0.3123088479042053, "learning_rate": 9.823264052882238e-06, "loss": 0.233, "step": 6044 }, { "epoch": 0.17646543671181691, "grad_norm": 0.33468830585479736, "learning_rate": 9.823129761639177e-06, "loss": 0.2357, "step": 6045 }, { "epoch": 0.17649462867818777, "grad_norm": 0.3537633419036865, "learning_rate": 9.822995420314117e-06, "loss": 0.2537, "step": 6046 }, { "epoch": 0.17652382064455863, "grad_norm": 0.3586012125015259, "learning_rate": 9.822861028908457e-06, "loss": 0.3017, "step": 6047 }, { "epoch": 0.17655301261092948, "grad_norm": 0.3248779773712158, "learning_rate": 9.822726587423588e-06, "loss": 0.1909, "step": 6048 }, { "epoch": 0.17658220457730034, "grad_norm": 0.3689509332180023, "learning_rate": 9.822592095860909e-06, "loss": 0.333, "step": 6049 }, { "epoch": 0.1766113965436712, "grad_norm": 0.6206469535827637, "learning_rate": 9.822457554221813e-06, "loss": 0.2712, "step": 6050 }, { "epoch": 0.17664058851004202, "grad_norm": 0.3767576217651367, "learning_rate": 9.822322962507701e-06, "loss": 0.2353, "step": 6051 }, { "epoch": 0.17666978047641288, "grad_norm": 0.3402138650417328, "learning_rate": 9.822188320719972e-06, "loss": 0.2493, "step": 6052 }, { "epoch": 0.17669897244278374, "grad_norm": 0.36116865277290344, "learning_rate": 9.822053628860018e-06, "loss": 0.2327, "step": 6053 }, { "epoch": 0.1767281644091546, "grad_norm": 0.3823138177394867, "learning_rate": 9.821918886929242e-06, "loss": 0.2571, "step": 6054 }, { "epoch": 0.17675735637552545, "grad_norm": 0.3823018968105316, "learning_rate": 9.821784094929042e-06, "loss": 0.262, "step": 6055 }, { "epoch": 0.1767865483418963, "grad_norm": 0.36757466197013855, "learning_rate": 9.821649252860817e-06, "loss": 0.2688, "step": 6056 }, { "epoch": 0.17681574030826716, "grad_norm": 0.3433048725128174, "learning_rate": 9.821514360725968e-06, "loss": 0.2537, "step": 6057 }, { "epoch": 0.17684493227463802, "grad_norm": 0.38473445177078247, "learning_rate": 9.821379418525894e-06, "loss": 0.2062, "step": 6058 }, { "epoch": 0.17687412424100887, "grad_norm": 0.32514360547065735, "learning_rate": 9.821244426262e-06, "loss": 0.2192, "step": 6059 }, { "epoch": 0.17690331620737973, "grad_norm": 0.3897475600242615, "learning_rate": 9.821109383935682e-06, "loss": 0.2731, "step": 6060 }, { "epoch": 0.17693250817375059, "grad_norm": 0.3211880922317505, "learning_rate": 9.82097429154835e-06, "loss": 0.2158, "step": 6061 }, { "epoch": 0.17696170014012144, "grad_norm": 0.2994421720504761, "learning_rate": 9.820839149101398e-06, "loss": 0.208, "step": 6062 }, { "epoch": 0.1769908921064923, "grad_norm": 0.33751001954078674, "learning_rate": 9.820703956596236e-06, "loss": 0.255, "step": 6063 }, { "epoch": 0.17702008407286315, "grad_norm": 0.34340301156044006, "learning_rate": 9.820568714034264e-06, "loss": 0.231, "step": 6064 }, { "epoch": 0.177049276039234, "grad_norm": 0.35391923785209656, "learning_rate": 9.82043342141689e-06, "loss": 0.2442, "step": 6065 }, { "epoch": 0.17707846800560487, "grad_norm": 0.3343670666217804, "learning_rate": 9.820298078745515e-06, "loss": 0.292, "step": 6066 }, { "epoch": 0.17710765997197572, "grad_norm": 0.3089423179626465, "learning_rate": 9.820162686021546e-06, "loss": 0.2356, "step": 6067 }, { "epoch": 0.17713685193834658, "grad_norm": 0.3912503123283386, "learning_rate": 9.820027243246388e-06, "loss": 0.3172, "step": 6068 }, { "epoch": 0.17716604390471744, "grad_norm": 0.39520347118377686, "learning_rate": 9.819891750421451e-06, "loss": 0.2756, "step": 6069 }, { "epoch": 0.17719523587108826, "grad_norm": 0.31742367148399353, "learning_rate": 9.819756207548138e-06, "loss": 0.1896, "step": 6070 }, { "epoch": 0.17722442783745912, "grad_norm": 0.33278876543045044, "learning_rate": 9.819620614627855e-06, "loss": 0.2282, "step": 6071 }, { "epoch": 0.17725361980382998, "grad_norm": 0.3703414797782898, "learning_rate": 9.819484971662015e-06, "loss": 0.2636, "step": 6072 }, { "epoch": 0.17728281177020083, "grad_norm": 0.3334070146083832, "learning_rate": 9.819349278652023e-06, "loss": 0.2312, "step": 6073 }, { "epoch": 0.1773120037365717, "grad_norm": 0.3575531542301178, "learning_rate": 9.81921353559929e-06, "loss": 0.2512, "step": 6074 }, { "epoch": 0.17734119570294254, "grad_norm": 0.35437673330307007, "learning_rate": 9.819077742505223e-06, "loss": 0.2109, "step": 6075 }, { "epoch": 0.1773703876693134, "grad_norm": 0.30024704337120056, "learning_rate": 9.818941899371236e-06, "loss": 0.2103, "step": 6076 }, { "epoch": 0.17739957963568426, "grad_norm": 0.425049751996994, "learning_rate": 9.818806006198734e-06, "loss": 0.2379, "step": 6077 }, { "epoch": 0.1774287716020551, "grad_norm": 0.3073277771472931, "learning_rate": 9.818670062989132e-06, "loss": 0.2113, "step": 6078 }, { "epoch": 0.17745796356842597, "grad_norm": 0.3581830561161041, "learning_rate": 9.818534069743841e-06, "loss": 0.3163, "step": 6079 }, { "epoch": 0.17748715553479683, "grad_norm": 0.36861857771873474, "learning_rate": 9.818398026464272e-06, "loss": 0.2149, "step": 6080 }, { "epoch": 0.17751634750116768, "grad_norm": 0.40347251296043396, "learning_rate": 9.818261933151841e-06, "loss": 0.2576, "step": 6081 }, { "epoch": 0.17754553946753854, "grad_norm": 0.42599430680274963, "learning_rate": 9.818125789807957e-06, "loss": 0.271, "step": 6082 }, { "epoch": 0.1775747314339094, "grad_norm": 0.41355201601982117, "learning_rate": 9.817989596434036e-06, "loss": 0.2441, "step": 6083 }, { "epoch": 0.17760392340028025, "grad_norm": 0.36482590436935425, "learning_rate": 9.817853353031492e-06, "loss": 0.2333, "step": 6084 }, { "epoch": 0.1776331153666511, "grad_norm": 0.3367854952812195, "learning_rate": 9.817717059601738e-06, "loss": 0.2229, "step": 6085 }, { "epoch": 0.17766230733302196, "grad_norm": 0.33061906695365906, "learning_rate": 9.817580716146192e-06, "loss": 0.2109, "step": 6086 }, { "epoch": 0.17769149929939282, "grad_norm": 0.4477727711200714, "learning_rate": 9.817444322666267e-06, "loss": 0.256, "step": 6087 }, { "epoch": 0.17772069126576368, "grad_norm": 0.33704617619514465, "learning_rate": 9.81730787916338e-06, "loss": 0.2212, "step": 6088 }, { "epoch": 0.1777498832321345, "grad_norm": 0.3541891574859619, "learning_rate": 9.81717138563895e-06, "loss": 0.2392, "step": 6089 }, { "epoch": 0.17777907519850536, "grad_norm": 0.3532079756259918, "learning_rate": 9.81703484209439e-06, "loss": 0.2467, "step": 6090 }, { "epoch": 0.17780826716487622, "grad_norm": 0.38487154245376587, "learning_rate": 9.816898248531124e-06, "loss": 0.2565, "step": 6091 }, { "epoch": 0.17783745913124707, "grad_norm": 0.3520795404911041, "learning_rate": 9.816761604950564e-06, "loss": 0.2499, "step": 6092 }, { "epoch": 0.17786665109761793, "grad_norm": 0.34489721059799194, "learning_rate": 9.816624911354133e-06, "loss": 0.2381, "step": 6093 }, { "epoch": 0.17789584306398878, "grad_norm": 0.3657504916191101, "learning_rate": 9.816488167743248e-06, "loss": 0.283, "step": 6094 }, { "epoch": 0.17792503503035964, "grad_norm": 0.3393939733505249, "learning_rate": 9.81635137411933e-06, "loss": 0.2763, "step": 6095 }, { "epoch": 0.1779542269967305, "grad_norm": 0.3518415689468384, "learning_rate": 9.816214530483802e-06, "loss": 0.2246, "step": 6096 }, { "epoch": 0.17798341896310135, "grad_norm": 0.35806235671043396, "learning_rate": 9.816077636838079e-06, "loss": 0.1973, "step": 6097 }, { "epoch": 0.1780126109294722, "grad_norm": 0.36423808336257935, "learning_rate": 9.815940693183588e-06, "loss": 0.2708, "step": 6098 }, { "epoch": 0.17804180289584307, "grad_norm": 0.3968832492828369, "learning_rate": 9.815803699521746e-06, "loss": 0.3146, "step": 6099 }, { "epoch": 0.17807099486221392, "grad_norm": 0.35417166352272034, "learning_rate": 9.815666655853981e-06, "loss": 0.2297, "step": 6100 }, { "epoch": 0.17810018682858478, "grad_norm": 0.3597155213356018, "learning_rate": 9.815529562181712e-06, "loss": 0.2889, "step": 6101 }, { "epoch": 0.17812937879495563, "grad_norm": 0.4175320267677307, "learning_rate": 9.815392418506364e-06, "loss": 0.2492, "step": 6102 }, { "epoch": 0.1781585707613265, "grad_norm": 0.3526213765144348, "learning_rate": 9.81525522482936e-06, "loss": 0.2709, "step": 6103 }, { "epoch": 0.17818776272769735, "grad_norm": 0.5510465502738953, "learning_rate": 9.815117981152127e-06, "loss": 0.2478, "step": 6104 }, { "epoch": 0.1782169546940682, "grad_norm": 0.37279853224754333, "learning_rate": 9.814980687476088e-06, "loss": 0.2235, "step": 6105 }, { "epoch": 0.17824614666043906, "grad_norm": 0.35165995359420776, "learning_rate": 9.81484334380267e-06, "loss": 0.2317, "step": 6106 }, { "epoch": 0.17827533862680991, "grad_norm": 0.39260637760162354, "learning_rate": 9.814705950133296e-06, "loss": 0.2972, "step": 6107 }, { "epoch": 0.17830453059318074, "grad_norm": 0.34167200326919556, "learning_rate": 9.814568506469397e-06, "loss": 0.2071, "step": 6108 }, { "epoch": 0.1783337225595516, "grad_norm": 0.3093780279159546, "learning_rate": 9.814431012812398e-06, "loss": 0.2019, "step": 6109 }, { "epoch": 0.17836291452592246, "grad_norm": 0.39703288674354553, "learning_rate": 9.814293469163727e-06, "loss": 0.245, "step": 6110 }, { "epoch": 0.1783921064922933, "grad_norm": 0.3876029849052429, "learning_rate": 9.814155875524812e-06, "loss": 0.2824, "step": 6111 }, { "epoch": 0.17842129845866417, "grad_norm": 0.37177836894989014, "learning_rate": 9.81401823189708e-06, "loss": 0.2472, "step": 6112 }, { "epoch": 0.17845049042503502, "grad_norm": 0.3229348659515381, "learning_rate": 9.813880538281963e-06, "loss": 0.1921, "step": 6113 }, { "epoch": 0.17847968239140588, "grad_norm": 0.4006757140159607, "learning_rate": 9.813742794680892e-06, "loss": 0.2607, "step": 6114 }, { "epoch": 0.17850887435777674, "grad_norm": 0.35718202590942383, "learning_rate": 9.813605001095292e-06, "loss": 0.2882, "step": 6115 }, { "epoch": 0.1785380663241476, "grad_norm": 0.3736015260219574, "learning_rate": 9.8134671575266e-06, "loss": 0.2558, "step": 6116 }, { "epoch": 0.17856725829051845, "grad_norm": 0.3822135329246521, "learning_rate": 9.813329263976242e-06, "loss": 0.2729, "step": 6117 }, { "epoch": 0.1785964502568893, "grad_norm": 0.34115785360336304, "learning_rate": 9.813191320445652e-06, "loss": 0.2781, "step": 6118 }, { "epoch": 0.17862564222326016, "grad_norm": 0.3541542589664459, "learning_rate": 9.813053326936263e-06, "loss": 0.2234, "step": 6119 }, { "epoch": 0.17865483418963102, "grad_norm": 0.35016700625419617, "learning_rate": 9.812915283449508e-06, "loss": 0.2262, "step": 6120 }, { "epoch": 0.17868402615600187, "grad_norm": 0.3551297187805176, "learning_rate": 9.81277718998682e-06, "loss": 0.2401, "step": 6121 }, { "epoch": 0.17871321812237273, "grad_norm": 0.335223525762558, "learning_rate": 9.81263904654963e-06, "loss": 0.2088, "step": 6122 }, { "epoch": 0.1787424100887436, "grad_norm": 0.42766937613487244, "learning_rate": 9.812500853139377e-06, "loss": 0.2173, "step": 6123 }, { "epoch": 0.17877160205511444, "grad_norm": 0.33650287985801697, "learning_rate": 9.812362609757496e-06, "loss": 0.2384, "step": 6124 }, { "epoch": 0.1788007940214853, "grad_norm": 0.40227970480918884, "learning_rate": 9.812224316405417e-06, "loss": 0.2812, "step": 6125 }, { "epoch": 0.17882998598785615, "grad_norm": 0.33112984895706177, "learning_rate": 9.812085973084582e-06, "loss": 0.2297, "step": 6126 }, { "epoch": 0.17885917795422698, "grad_norm": 0.33623093366622925, "learning_rate": 9.811947579796424e-06, "loss": 0.2727, "step": 6127 }, { "epoch": 0.17888836992059784, "grad_norm": 0.3237757384777069, "learning_rate": 9.811809136542381e-06, "loss": 0.2377, "step": 6128 }, { "epoch": 0.1789175618869687, "grad_norm": 0.3654336631298065, "learning_rate": 9.811670643323891e-06, "loss": 0.2422, "step": 6129 }, { "epoch": 0.17894675385333955, "grad_norm": 0.32617878913879395, "learning_rate": 9.811532100142391e-06, "loss": 0.2503, "step": 6130 }, { "epoch": 0.1789759458197104, "grad_norm": 0.3260139226913452, "learning_rate": 9.811393506999322e-06, "loss": 0.2244, "step": 6131 }, { "epoch": 0.17900513778608126, "grad_norm": 0.3376670181751251, "learning_rate": 9.811254863896121e-06, "loss": 0.2759, "step": 6132 }, { "epoch": 0.17903432975245212, "grad_norm": 0.28345683217048645, "learning_rate": 9.811116170834227e-06, "loss": 0.2024, "step": 6133 }, { "epoch": 0.17906352171882298, "grad_norm": 0.5318046808242798, "learning_rate": 9.81097742781508e-06, "loss": 0.2088, "step": 6134 }, { "epoch": 0.17909271368519383, "grad_norm": 0.48843976855278015, "learning_rate": 9.810838634840125e-06, "loss": 0.2269, "step": 6135 }, { "epoch": 0.1791219056515647, "grad_norm": 0.30588099360466003, "learning_rate": 9.810699791910799e-06, "loss": 0.2142, "step": 6136 }, { "epoch": 0.17915109761793555, "grad_norm": 0.36983558535575867, "learning_rate": 9.810560899028544e-06, "loss": 0.2899, "step": 6137 }, { "epoch": 0.1791802895843064, "grad_norm": 0.4479617476463318, "learning_rate": 9.810421956194804e-06, "loss": 0.312, "step": 6138 }, { "epoch": 0.17920948155067726, "grad_norm": 0.40065276622772217, "learning_rate": 9.81028296341102e-06, "loss": 0.2654, "step": 6139 }, { "epoch": 0.1792386735170481, "grad_norm": 0.36298125982284546, "learning_rate": 9.810143920678636e-06, "loss": 0.2593, "step": 6140 }, { "epoch": 0.17926786548341897, "grad_norm": 0.3973153233528137, "learning_rate": 9.810004827999096e-06, "loss": 0.2279, "step": 6141 }, { "epoch": 0.17929705744978983, "grad_norm": 0.3647828996181488, "learning_rate": 9.809865685373845e-06, "loss": 0.2347, "step": 6142 }, { "epoch": 0.17932624941616068, "grad_norm": 0.3592453598976135, "learning_rate": 9.809726492804326e-06, "loss": 0.2283, "step": 6143 }, { "epoch": 0.17935544138253154, "grad_norm": 0.4687066972255707, "learning_rate": 9.809587250291984e-06, "loss": 0.2641, "step": 6144 }, { "epoch": 0.1793846333489024, "grad_norm": 0.3750671148300171, "learning_rate": 9.809447957838267e-06, "loss": 0.2597, "step": 6145 }, { "epoch": 0.17941382531527322, "grad_norm": 0.5339097380638123, "learning_rate": 9.809308615444622e-06, "loss": 0.2608, "step": 6146 }, { "epoch": 0.17944301728164408, "grad_norm": 0.3281913101673126, "learning_rate": 9.809169223112494e-06, "loss": 0.2075, "step": 6147 }, { "epoch": 0.17947220924801494, "grad_norm": 0.33038127422332764, "learning_rate": 9.80902978084333e-06, "loss": 0.2146, "step": 6148 }, { "epoch": 0.1795014012143858, "grad_norm": 0.38446101546287537, "learning_rate": 9.808890288638577e-06, "loss": 0.2551, "step": 6149 }, { "epoch": 0.17953059318075665, "grad_norm": 0.335683673620224, "learning_rate": 9.808750746499687e-06, "loss": 0.2171, "step": 6150 }, { "epoch": 0.1795597851471275, "grad_norm": 0.3694993257522583, "learning_rate": 9.808611154428107e-06, "loss": 0.2286, "step": 6151 }, { "epoch": 0.17958897711349836, "grad_norm": 0.36581072211265564, "learning_rate": 9.808471512425285e-06, "loss": 0.232, "step": 6152 }, { "epoch": 0.17961816907986922, "grad_norm": 0.5994096398353577, "learning_rate": 9.808331820492676e-06, "loss": 0.2076, "step": 6153 }, { "epoch": 0.17964736104624007, "grad_norm": 0.3997214734554291, "learning_rate": 9.808192078631724e-06, "loss": 0.2491, "step": 6154 }, { "epoch": 0.17967655301261093, "grad_norm": 0.3700020909309387, "learning_rate": 9.808052286843885e-06, "loss": 0.2539, "step": 6155 }, { "epoch": 0.17970574497898179, "grad_norm": 0.360385537147522, "learning_rate": 9.807912445130607e-06, "loss": 0.238, "step": 6156 }, { "epoch": 0.17973493694535264, "grad_norm": 0.3661346435546875, "learning_rate": 9.807772553493347e-06, "loss": 0.2493, "step": 6157 }, { "epoch": 0.1797641289117235, "grad_norm": 0.36136308312416077, "learning_rate": 9.80763261193355e-06, "loss": 0.2915, "step": 6158 }, { "epoch": 0.17979332087809435, "grad_norm": 0.35236603021621704, "learning_rate": 9.807492620452676e-06, "loss": 0.2656, "step": 6159 }, { "epoch": 0.1798225128444652, "grad_norm": 0.35136058926582336, "learning_rate": 9.807352579052176e-06, "loss": 0.2321, "step": 6160 }, { "epoch": 0.17985170481083607, "grad_norm": 0.3730336129665375, "learning_rate": 9.807212487733503e-06, "loss": 0.2047, "step": 6161 }, { "epoch": 0.17988089677720692, "grad_norm": 0.36158066987991333, "learning_rate": 9.807072346498115e-06, "loss": 0.2658, "step": 6162 }, { "epoch": 0.17991008874357778, "grad_norm": 0.4025478661060333, "learning_rate": 9.806932155347466e-06, "loss": 0.232, "step": 6163 }, { "epoch": 0.17993928070994863, "grad_norm": 0.4285135269165039, "learning_rate": 9.806791914283009e-06, "loss": 0.2583, "step": 6164 }, { "epoch": 0.17996847267631946, "grad_norm": 0.3653489053249359, "learning_rate": 9.8066516233062e-06, "loss": 0.2891, "step": 6165 }, { "epoch": 0.17999766464269032, "grad_norm": 0.3736364543437958, "learning_rate": 9.806511282418501e-06, "loss": 0.2737, "step": 6166 }, { "epoch": 0.18002685660906118, "grad_norm": 0.3766864836215973, "learning_rate": 9.806370891621366e-06, "loss": 0.2287, "step": 6167 }, { "epoch": 0.18005604857543203, "grad_norm": 0.378278911113739, "learning_rate": 9.806230450916251e-06, "loss": 0.2819, "step": 6168 }, { "epoch": 0.1800852405418029, "grad_norm": 0.33906909823417664, "learning_rate": 9.806089960304616e-06, "loss": 0.2029, "step": 6169 }, { "epoch": 0.18011443250817374, "grad_norm": 0.3414263427257538, "learning_rate": 9.80594941978792e-06, "loss": 0.265, "step": 6170 }, { "epoch": 0.1801436244745446, "grad_norm": 0.338351309299469, "learning_rate": 9.805808829367625e-06, "loss": 0.2467, "step": 6171 }, { "epoch": 0.18017281644091546, "grad_norm": 0.40308329463005066, "learning_rate": 9.805668189045185e-06, "loss": 0.2302, "step": 6172 }, { "epoch": 0.1802020084072863, "grad_norm": 0.3918466567993164, "learning_rate": 9.805527498822065e-06, "loss": 0.2727, "step": 6173 }, { "epoch": 0.18023120037365717, "grad_norm": 0.3879706561565399, "learning_rate": 9.805386758699724e-06, "loss": 0.2363, "step": 6174 }, { "epoch": 0.18026039234002803, "grad_norm": 0.35856348276138306, "learning_rate": 9.805245968679625e-06, "loss": 0.2635, "step": 6175 }, { "epoch": 0.18028958430639888, "grad_norm": 0.3414096236228943, "learning_rate": 9.805105128763229e-06, "loss": 0.2325, "step": 6176 }, { "epoch": 0.18031877627276974, "grad_norm": 0.38281601667404175, "learning_rate": 9.804964238951996e-06, "loss": 0.2351, "step": 6177 }, { "epoch": 0.1803479682391406, "grad_norm": 0.3979818522930145, "learning_rate": 9.804823299247392e-06, "loss": 0.2938, "step": 6178 }, { "epoch": 0.18037716020551145, "grad_norm": 0.40413200855255127, "learning_rate": 9.80468230965088e-06, "loss": 0.3125, "step": 6179 }, { "epoch": 0.1804063521718823, "grad_norm": 0.3857654631137848, "learning_rate": 9.804541270163923e-06, "loss": 0.2303, "step": 6180 }, { "epoch": 0.18043554413825316, "grad_norm": 0.4155735373497009, "learning_rate": 9.804400180787985e-06, "loss": 0.2515, "step": 6181 }, { "epoch": 0.18046473610462402, "grad_norm": 0.35798054933547974, "learning_rate": 9.804259041524533e-06, "loss": 0.2459, "step": 6182 }, { "epoch": 0.18049392807099487, "grad_norm": 0.3920709490776062, "learning_rate": 9.804117852375033e-06, "loss": 0.2559, "step": 6183 }, { "epoch": 0.18052312003736573, "grad_norm": 0.3996751606464386, "learning_rate": 9.803976613340949e-06, "loss": 0.2399, "step": 6184 }, { "epoch": 0.18055231200373656, "grad_norm": 0.35678642988204956, "learning_rate": 9.803835324423748e-06, "loss": 0.2363, "step": 6185 }, { "epoch": 0.18058150397010742, "grad_norm": 0.37990978360176086, "learning_rate": 9.803693985624896e-06, "loss": 0.2395, "step": 6186 }, { "epoch": 0.18061069593647827, "grad_norm": 0.326262891292572, "learning_rate": 9.803552596945864e-06, "loss": 0.2186, "step": 6187 }, { "epoch": 0.18063988790284913, "grad_norm": 0.35748976469039917, "learning_rate": 9.803411158388119e-06, "loss": 0.2423, "step": 6188 }, { "epoch": 0.18066907986921998, "grad_norm": 0.3677699863910675, "learning_rate": 9.803269669953127e-06, "loss": 0.2079, "step": 6189 }, { "epoch": 0.18069827183559084, "grad_norm": 0.4053000509738922, "learning_rate": 9.80312813164236e-06, "loss": 0.2801, "step": 6190 }, { "epoch": 0.1807274638019617, "grad_norm": 0.3460026681423187, "learning_rate": 9.802986543457287e-06, "loss": 0.2461, "step": 6191 }, { "epoch": 0.18075665576833255, "grad_norm": 0.3561721444129944, "learning_rate": 9.802844905399376e-06, "loss": 0.2077, "step": 6192 }, { "epoch": 0.1807858477347034, "grad_norm": 0.34122058749198914, "learning_rate": 9.802703217470102e-06, "loss": 0.2026, "step": 6193 }, { "epoch": 0.18081503970107426, "grad_norm": 0.4763704538345337, "learning_rate": 9.802561479670933e-06, "loss": 0.2284, "step": 6194 }, { "epoch": 0.18084423166744512, "grad_norm": 0.3183155059814453, "learning_rate": 9.802419692003343e-06, "loss": 0.1956, "step": 6195 }, { "epoch": 0.18087342363381598, "grad_norm": 0.36322635412216187, "learning_rate": 9.8022778544688e-06, "loss": 0.2326, "step": 6196 }, { "epoch": 0.18090261560018683, "grad_norm": 0.38006049394607544, "learning_rate": 9.802135967068783e-06, "loss": 0.2232, "step": 6197 }, { "epoch": 0.1809318075665577, "grad_norm": 0.3541429042816162, "learning_rate": 9.80199402980476e-06, "loss": 0.2482, "step": 6198 }, { "epoch": 0.18096099953292855, "grad_norm": 0.3900998532772064, "learning_rate": 9.801852042678206e-06, "loss": 0.2363, "step": 6199 }, { "epoch": 0.1809901914992994, "grad_norm": 0.634541392326355, "learning_rate": 9.801710005690598e-06, "loss": 0.2931, "step": 6200 }, { "epoch": 0.18101938346567026, "grad_norm": 0.40511009097099304, "learning_rate": 9.801567918843409e-06, "loss": 0.2581, "step": 6201 }, { "epoch": 0.18104857543204111, "grad_norm": 0.3833525478839874, "learning_rate": 9.801425782138115e-06, "loss": 0.2728, "step": 6202 }, { "epoch": 0.18107776739841197, "grad_norm": 0.5759568810462952, "learning_rate": 9.80128359557619e-06, "loss": 0.2482, "step": 6203 }, { "epoch": 0.1811069593647828, "grad_norm": 0.44199812412261963, "learning_rate": 9.801141359159112e-06, "loss": 0.3304, "step": 6204 }, { "epoch": 0.18113615133115366, "grad_norm": 0.3447859287261963, "learning_rate": 9.80099907288836e-06, "loss": 0.2424, "step": 6205 }, { "epoch": 0.1811653432975245, "grad_norm": 1.9474475383758545, "learning_rate": 9.800856736765408e-06, "loss": 0.2486, "step": 6206 }, { "epoch": 0.18119453526389537, "grad_norm": 0.36650487780570984, "learning_rate": 9.800714350791733e-06, "loss": 0.2314, "step": 6207 }, { "epoch": 0.18122372723026622, "grad_norm": 0.3630463182926178, "learning_rate": 9.80057191496882e-06, "loss": 0.2515, "step": 6208 }, { "epoch": 0.18125291919663708, "grad_norm": 0.3646429777145386, "learning_rate": 9.800429429298139e-06, "loss": 0.2759, "step": 6209 }, { "epoch": 0.18128211116300794, "grad_norm": 0.4097089171409607, "learning_rate": 9.800286893781178e-06, "loss": 0.2685, "step": 6210 }, { "epoch": 0.1813113031293788, "grad_norm": 0.3185012638568878, "learning_rate": 9.800144308419412e-06, "loss": 0.2514, "step": 6211 }, { "epoch": 0.18134049509574965, "grad_norm": 0.3510875701904297, "learning_rate": 9.800001673214323e-06, "loss": 0.2579, "step": 6212 }, { "epoch": 0.1813696870621205, "grad_norm": 0.4172602891921997, "learning_rate": 9.799858988167392e-06, "loss": 0.2783, "step": 6213 }, { "epoch": 0.18139887902849136, "grad_norm": 0.37108540534973145, "learning_rate": 9.799716253280101e-06, "loss": 0.2072, "step": 6214 }, { "epoch": 0.18142807099486222, "grad_norm": 0.3325287103652954, "learning_rate": 9.799573468553932e-06, "loss": 0.2594, "step": 6215 }, { "epoch": 0.18145726296123307, "grad_norm": 0.35460567474365234, "learning_rate": 9.799430633990366e-06, "loss": 0.2827, "step": 6216 }, { "epoch": 0.18148645492760393, "grad_norm": 0.34162551164627075, "learning_rate": 9.799287749590887e-06, "loss": 0.2348, "step": 6217 }, { "epoch": 0.18151564689397479, "grad_norm": 0.331965833902359, "learning_rate": 9.79914481535698e-06, "loss": 0.2559, "step": 6218 }, { "epoch": 0.18154483886034564, "grad_norm": 0.3508068323135376, "learning_rate": 9.799001831290128e-06, "loss": 0.2977, "step": 6219 }, { "epoch": 0.1815740308267165, "grad_norm": 0.359980970621109, "learning_rate": 9.798858797391818e-06, "loss": 0.2448, "step": 6220 }, { "epoch": 0.18160322279308735, "grad_norm": 0.35425886511802673, "learning_rate": 9.798715713663531e-06, "loss": 0.2815, "step": 6221 }, { "epoch": 0.1816324147594582, "grad_norm": 0.3593652844429016, "learning_rate": 9.798572580106755e-06, "loss": 0.238, "step": 6222 }, { "epoch": 0.18166160672582904, "grad_norm": 0.4201969504356384, "learning_rate": 9.798429396722979e-06, "loss": 0.2344, "step": 6223 }, { "epoch": 0.1816907986921999, "grad_norm": 0.5325909852981567, "learning_rate": 9.798286163513684e-06, "loss": 0.2976, "step": 6224 }, { "epoch": 0.18171999065857075, "grad_norm": 0.5168341994285583, "learning_rate": 9.79814288048036e-06, "loss": 0.3, "step": 6225 }, { "epoch": 0.1817491826249416, "grad_norm": 0.3072693347930908, "learning_rate": 9.797999547624499e-06, "loss": 0.2277, "step": 6226 }, { "epoch": 0.18177837459131246, "grad_norm": 0.36942222714424133, "learning_rate": 9.797856164947584e-06, "loss": 0.2658, "step": 6227 }, { "epoch": 0.18180756655768332, "grad_norm": 0.3957902193069458, "learning_rate": 9.797712732451103e-06, "loss": 0.2478, "step": 6228 }, { "epoch": 0.18183675852405418, "grad_norm": 0.33970344066619873, "learning_rate": 9.797569250136549e-06, "loss": 0.267, "step": 6229 }, { "epoch": 0.18186595049042503, "grad_norm": 0.33131644129753113, "learning_rate": 9.797425718005412e-06, "loss": 0.2341, "step": 6230 }, { "epoch": 0.1818951424567959, "grad_norm": 0.3745546042919159, "learning_rate": 9.797282136059178e-06, "loss": 0.2845, "step": 6231 }, { "epoch": 0.18192433442316674, "grad_norm": 0.3474904000759125, "learning_rate": 9.797138504299345e-06, "loss": 0.2865, "step": 6232 }, { "epoch": 0.1819535263895376, "grad_norm": 0.33343929052352905, "learning_rate": 9.796994822727396e-06, "loss": 0.2271, "step": 6233 }, { "epoch": 0.18198271835590846, "grad_norm": 0.39425742626190186, "learning_rate": 9.79685109134483e-06, "loss": 0.2439, "step": 6234 }, { "epoch": 0.1820119103222793, "grad_norm": 0.3366488814353943, "learning_rate": 9.796707310153134e-06, "loss": 0.2488, "step": 6235 }, { "epoch": 0.18204110228865017, "grad_norm": 0.3793829083442688, "learning_rate": 9.796563479153806e-06, "loss": 0.261, "step": 6236 }, { "epoch": 0.18207029425502103, "grad_norm": 0.45080867409706116, "learning_rate": 9.796419598348336e-06, "loss": 0.266, "step": 6237 }, { "epoch": 0.18209948622139188, "grad_norm": 0.33631783723831177, "learning_rate": 9.79627566773822e-06, "loss": 0.2484, "step": 6238 }, { "epoch": 0.18212867818776274, "grad_norm": 0.36892858147621155, "learning_rate": 9.796131687324952e-06, "loss": 0.2633, "step": 6239 }, { "epoch": 0.1821578701541336, "grad_norm": 0.343727707862854, "learning_rate": 9.795987657110027e-06, "loss": 0.2825, "step": 6240 }, { "epoch": 0.18218706212050445, "grad_norm": 0.387563019990921, "learning_rate": 9.79584357709494e-06, "loss": 0.2428, "step": 6241 }, { "epoch": 0.18221625408687528, "grad_norm": 0.6482494473457336, "learning_rate": 9.795699447281186e-06, "loss": 0.2694, "step": 6242 }, { "epoch": 0.18224544605324614, "grad_norm": 0.3713424503803253, "learning_rate": 9.795555267670265e-06, "loss": 0.2567, "step": 6243 }, { "epoch": 0.182274638019617, "grad_norm": 0.4311516582965851, "learning_rate": 9.795411038263673e-06, "loss": 0.2398, "step": 6244 }, { "epoch": 0.18230382998598785, "grad_norm": 0.3507223427295685, "learning_rate": 9.795266759062905e-06, "loss": 0.2283, "step": 6245 }, { "epoch": 0.1823330219523587, "grad_norm": 0.3436986804008484, "learning_rate": 9.795122430069462e-06, "loss": 0.238, "step": 6246 }, { "epoch": 0.18236221391872956, "grad_norm": 0.38713452219963074, "learning_rate": 9.79497805128484e-06, "loss": 0.2832, "step": 6247 }, { "epoch": 0.18239140588510042, "grad_norm": 0.379941463470459, "learning_rate": 9.79483362271054e-06, "loss": 0.2493, "step": 6248 }, { "epoch": 0.18242059785147127, "grad_norm": 0.48045700788497925, "learning_rate": 9.794689144348063e-06, "loss": 0.265, "step": 6249 }, { "epoch": 0.18244978981784213, "grad_norm": 0.36916542053222656, "learning_rate": 9.794544616198906e-06, "loss": 0.2374, "step": 6250 }, { "epoch": 0.18247898178421298, "grad_norm": 0.41741257905960083, "learning_rate": 9.794400038264573e-06, "loss": 0.264, "step": 6251 }, { "epoch": 0.18250817375058384, "grad_norm": 0.3799446225166321, "learning_rate": 9.794255410546563e-06, "loss": 0.2518, "step": 6252 }, { "epoch": 0.1825373657169547, "grad_norm": 0.401967853307724, "learning_rate": 9.79411073304638e-06, "loss": 0.3032, "step": 6253 }, { "epoch": 0.18256655768332555, "grad_norm": 0.3566736876964569, "learning_rate": 9.793966005765523e-06, "loss": 0.265, "step": 6254 }, { "epoch": 0.1825957496496964, "grad_norm": 0.4487605392932892, "learning_rate": 9.793821228705498e-06, "loss": 0.2535, "step": 6255 }, { "epoch": 0.18262494161606727, "grad_norm": 0.43394312262535095, "learning_rate": 9.793676401867806e-06, "loss": 0.2083, "step": 6256 }, { "epoch": 0.18265413358243812, "grad_norm": 0.3630366027355194, "learning_rate": 9.793531525253952e-06, "loss": 0.2151, "step": 6257 }, { "epoch": 0.18268332554880898, "grad_norm": 0.42169299721717834, "learning_rate": 9.79338659886544e-06, "loss": 0.2443, "step": 6258 }, { "epoch": 0.18271251751517983, "grad_norm": 0.3982347548007965, "learning_rate": 9.793241622703774e-06, "loss": 0.2382, "step": 6259 }, { "epoch": 0.1827417094815507, "grad_norm": 0.36536896228790283, "learning_rate": 9.793096596770463e-06, "loss": 0.2525, "step": 6260 }, { "epoch": 0.18277090144792152, "grad_norm": 0.3967713713645935, "learning_rate": 9.792951521067009e-06, "loss": 0.2355, "step": 6261 }, { "epoch": 0.18280009341429238, "grad_norm": 0.4944133162498474, "learning_rate": 9.792806395594919e-06, "loss": 0.2774, "step": 6262 }, { "epoch": 0.18282928538066323, "grad_norm": 0.3668217658996582, "learning_rate": 9.792661220355701e-06, "loss": 0.2195, "step": 6263 }, { "epoch": 0.1828584773470341, "grad_norm": 0.38208943605422974, "learning_rate": 9.792515995350862e-06, "loss": 0.2594, "step": 6264 }, { "epoch": 0.18288766931340494, "grad_norm": 0.3884294927120209, "learning_rate": 9.792370720581912e-06, "loss": 0.2695, "step": 6265 }, { "epoch": 0.1829168612797758, "grad_norm": 0.3458036184310913, "learning_rate": 9.792225396050356e-06, "loss": 0.2824, "step": 6266 }, { "epoch": 0.18294605324614666, "grad_norm": 0.4393964111804962, "learning_rate": 9.792080021757704e-06, "loss": 0.2686, "step": 6267 }, { "epoch": 0.1829752452125175, "grad_norm": 0.3846651017665863, "learning_rate": 9.791934597705467e-06, "loss": 0.2594, "step": 6268 }, { "epoch": 0.18300443717888837, "grad_norm": 0.33305609226226807, "learning_rate": 9.791789123895155e-06, "loss": 0.202, "step": 6269 }, { "epoch": 0.18303362914525922, "grad_norm": 0.42052286863327026, "learning_rate": 9.791643600328276e-06, "loss": 0.2782, "step": 6270 }, { "epoch": 0.18306282111163008, "grad_norm": 0.3406224548816681, "learning_rate": 9.791498027006343e-06, "loss": 0.2225, "step": 6271 }, { "epoch": 0.18309201307800094, "grad_norm": 0.38642174005508423, "learning_rate": 9.791352403930869e-06, "loss": 0.2696, "step": 6272 }, { "epoch": 0.1831212050443718, "grad_norm": 0.3804677724838257, "learning_rate": 9.791206731103363e-06, "loss": 0.2093, "step": 6273 }, { "epoch": 0.18315039701074265, "grad_norm": 0.39194455742836, "learning_rate": 9.79106100852534e-06, "loss": 0.2419, "step": 6274 }, { "epoch": 0.1831795889771135, "grad_norm": 0.48183757066726685, "learning_rate": 9.790915236198311e-06, "loss": 0.2733, "step": 6275 }, { "epoch": 0.18320878094348436, "grad_norm": 0.37230953574180603, "learning_rate": 9.790769414123793e-06, "loss": 0.2995, "step": 6276 }, { "epoch": 0.18323797290985522, "grad_norm": 0.38582223653793335, "learning_rate": 9.790623542303297e-06, "loss": 0.2981, "step": 6277 }, { "epoch": 0.18326716487622607, "grad_norm": 0.3980771005153656, "learning_rate": 9.790477620738339e-06, "loss": 0.2623, "step": 6278 }, { "epoch": 0.18329635684259693, "grad_norm": 0.39400404691696167, "learning_rate": 9.790331649430433e-06, "loss": 0.2573, "step": 6279 }, { "epoch": 0.18332554880896776, "grad_norm": 0.31657031178474426, "learning_rate": 9.790185628381098e-06, "loss": 0.2601, "step": 6280 }, { "epoch": 0.18335474077533861, "grad_norm": 0.3457869589328766, "learning_rate": 9.790039557591844e-06, "loss": 0.2483, "step": 6281 }, { "epoch": 0.18338393274170947, "grad_norm": 0.342173308134079, "learning_rate": 9.789893437064195e-06, "loss": 0.2361, "step": 6282 }, { "epoch": 0.18341312470808033, "grad_norm": 0.39414626359939575, "learning_rate": 9.789747266799665e-06, "loss": 0.2694, "step": 6283 }, { "epoch": 0.18344231667445118, "grad_norm": 0.35863059759140015, "learning_rate": 9.789601046799771e-06, "loss": 0.2273, "step": 6284 }, { "epoch": 0.18347150864082204, "grad_norm": 0.3199862241744995, "learning_rate": 9.789454777066033e-06, "loss": 0.2657, "step": 6285 }, { "epoch": 0.1835007006071929, "grad_norm": 0.3935571610927582, "learning_rate": 9.789308457599966e-06, "loss": 0.2219, "step": 6286 }, { "epoch": 0.18352989257356375, "grad_norm": 0.4356200098991394, "learning_rate": 9.789162088403094e-06, "loss": 0.2888, "step": 6287 }, { "epoch": 0.1835590845399346, "grad_norm": 0.509965717792511, "learning_rate": 9.789015669476935e-06, "loss": 0.2841, "step": 6288 }, { "epoch": 0.18358827650630546, "grad_norm": 0.3997196555137634, "learning_rate": 9.788869200823012e-06, "loss": 0.2968, "step": 6289 }, { "epoch": 0.18361746847267632, "grad_norm": 0.332335501909256, "learning_rate": 9.78872268244284e-06, "loss": 0.2535, "step": 6290 }, { "epoch": 0.18364666043904718, "grad_norm": 0.5080004930496216, "learning_rate": 9.788576114337946e-06, "loss": 0.2249, "step": 6291 }, { "epoch": 0.18367585240541803, "grad_norm": 0.3739566504955292, "learning_rate": 9.788429496509848e-06, "loss": 0.2373, "step": 6292 }, { "epoch": 0.1837050443717889, "grad_norm": 0.3490816652774811, "learning_rate": 9.788282828960071e-06, "loss": 0.2313, "step": 6293 }, { "epoch": 0.18373423633815975, "grad_norm": 0.3770480155944824, "learning_rate": 9.788136111690138e-06, "loss": 0.2578, "step": 6294 }, { "epoch": 0.1837634283045306, "grad_norm": 0.3568320572376251, "learning_rate": 9.787989344701569e-06, "loss": 0.2253, "step": 6295 }, { "epoch": 0.18379262027090146, "grad_norm": 0.38351520895957947, "learning_rate": 9.787842527995893e-06, "loss": 0.2446, "step": 6296 }, { "epoch": 0.18382181223727231, "grad_norm": 0.357544869184494, "learning_rate": 9.787695661574632e-06, "loss": 0.2189, "step": 6297 }, { "epoch": 0.18385100420364317, "grad_norm": 0.32290810346603394, "learning_rate": 9.787548745439311e-06, "loss": 0.174, "step": 6298 }, { "epoch": 0.183880196170014, "grad_norm": 0.6088727116584778, "learning_rate": 9.787401779591454e-06, "loss": 0.2542, "step": 6299 }, { "epoch": 0.18390938813638485, "grad_norm": 0.31490686535835266, "learning_rate": 9.78725476403259e-06, "loss": 0.2401, "step": 6300 }, { "epoch": 0.1839385801027557, "grad_norm": 0.3560406267642975, "learning_rate": 9.787107698764244e-06, "loss": 0.2607, "step": 6301 }, { "epoch": 0.18396777206912657, "grad_norm": 0.40634503960609436, "learning_rate": 9.786960583787942e-06, "loss": 0.2464, "step": 6302 }, { "epoch": 0.18399696403549742, "grad_norm": 0.34045493602752686, "learning_rate": 9.786813419105214e-06, "loss": 0.2438, "step": 6303 }, { "epoch": 0.18402615600186828, "grad_norm": 0.365565687417984, "learning_rate": 9.786666204717588e-06, "loss": 0.2077, "step": 6304 }, { "epoch": 0.18405534796823914, "grad_norm": 0.35305196046829224, "learning_rate": 9.78651894062659e-06, "loss": 0.1813, "step": 6305 }, { "epoch": 0.18408453993461, "grad_norm": 0.36990809440612793, "learning_rate": 9.786371626833752e-06, "loss": 0.2352, "step": 6306 }, { "epoch": 0.18411373190098085, "grad_norm": 0.35272130370140076, "learning_rate": 9.7862242633406e-06, "loss": 0.2496, "step": 6307 }, { "epoch": 0.1841429238673517, "grad_norm": 0.3600452244281769, "learning_rate": 9.78607685014867e-06, "loss": 0.2521, "step": 6308 }, { "epoch": 0.18417211583372256, "grad_norm": 0.33479273319244385, "learning_rate": 9.785929387259487e-06, "loss": 0.2071, "step": 6309 }, { "epoch": 0.18420130780009342, "grad_norm": 0.3993024528026581, "learning_rate": 9.785781874674587e-06, "loss": 0.2312, "step": 6310 }, { "epoch": 0.18423049976646427, "grad_norm": 0.3879915475845337, "learning_rate": 9.785634312395498e-06, "loss": 0.243, "step": 6311 }, { "epoch": 0.18425969173283513, "grad_norm": 0.3892894387245178, "learning_rate": 9.785486700423753e-06, "loss": 0.2435, "step": 6312 }, { "epoch": 0.18428888369920599, "grad_norm": 0.4077260494232178, "learning_rate": 9.785339038760886e-06, "loss": 0.2515, "step": 6313 }, { "epoch": 0.18431807566557684, "grad_norm": 0.40897998213768005, "learning_rate": 9.785191327408429e-06, "loss": 0.2398, "step": 6314 }, { "epoch": 0.1843472676319477, "grad_norm": 0.43271923065185547, "learning_rate": 9.785043566367917e-06, "loss": 0.247, "step": 6315 }, { "epoch": 0.18437645959831855, "grad_norm": 0.3602563440799713, "learning_rate": 9.784895755640884e-06, "loss": 0.2593, "step": 6316 }, { "epoch": 0.1844056515646894, "grad_norm": 0.3906986713409424, "learning_rate": 9.784747895228863e-06, "loss": 0.2213, "step": 6317 }, { "epoch": 0.18443484353106024, "grad_norm": 0.3024875521659851, "learning_rate": 9.784599985133392e-06, "loss": 0.19, "step": 6318 }, { "epoch": 0.1844640354974311, "grad_norm": 0.4073423445224762, "learning_rate": 9.784452025356004e-06, "loss": 0.2554, "step": 6319 }, { "epoch": 0.18449322746380195, "grad_norm": 0.4089225232601166, "learning_rate": 9.784304015898239e-06, "loss": 0.1761, "step": 6320 }, { "epoch": 0.1845224194301728, "grad_norm": 0.366716206073761, "learning_rate": 9.784155956761631e-06, "loss": 0.2501, "step": 6321 }, { "epoch": 0.18455161139654366, "grad_norm": 0.3795565962791443, "learning_rate": 9.784007847947718e-06, "loss": 0.2752, "step": 6322 }, { "epoch": 0.18458080336291452, "grad_norm": 0.42487505078315735, "learning_rate": 9.78385968945804e-06, "loss": 0.212, "step": 6323 }, { "epoch": 0.18460999532928538, "grad_norm": 0.36937078833580017, "learning_rate": 9.783711481294132e-06, "loss": 0.2544, "step": 6324 }, { "epoch": 0.18463918729565623, "grad_norm": 0.37344831228256226, "learning_rate": 9.783563223457537e-06, "loss": 0.2165, "step": 6325 }, { "epoch": 0.1846683792620271, "grad_norm": 0.38235002756118774, "learning_rate": 9.78341491594979e-06, "loss": 0.2181, "step": 6326 }, { "epoch": 0.18469757122839794, "grad_norm": 0.36907172203063965, "learning_rate": 9.783266558772433e-06, "loss": 0.2595, "step": 6327 }, { "epoch": 0.1847267631947688, "grad_norm": 0.5101222991943359, "learning_rate": 9.783118151927006e-06, "loss": 0.2721, "step": 6328 }, { "epoch": 0.18475595516113966, "grad_norm": 0.32982006669044495, "learning_rate": 9.782969695415054e-06, "loss": 0.1986, "step": 6329 }, { "epoch": 0.1847851471275105, "grad_norm": 0.3336210548877716, "learning_rate": 9.782821189238112e-06, "loss": 0.2197, "step": 6330 }, { "epoch": 0.18481433909388137, "grad_norm": 0.45266565680503845, "learning_rate": 9.782672633397727e-06, "loss": 0.2802, "step": 6331 }, { "epoch": 0.18484353106025223, "grad_norm": 0.44189736247062683, "learning_rate": 9.782524027895438e-06, "loss": 0.2845, "step": 6332 }, { "epoch": 0.18487272302662308, "grad_norm": 0.3095911145210266, "learning_rate": 9.78237537273279e-06, "loss": 0.1684, "step": 6333 }, { "epoch": 0.18490191499299394, "grad_norm": 0.3850722312927246, "learning_rate": 9.782226667911327e-06, "loss": 0.2143, "step": 6334 }, { "epoch": 0.1849311069593648, "grad_norm": 0.3971644639968872, "learning_rate": 9.782077913432593e-06, "loss": 0.2645, "step": 6335 }, { "epoch": 0.18496029892573565, "grad_norm": 0.3360534608364105, "learning_rate": 9.781929109298133e-06, "loss": 0.2327, "step": 6336 }, { "epoch": 0.18498949089210648, "grad_norm": 0.40373435616493225, "learning_rate": 9.78178025550949e-06, "loss": 0.2462, "step": 6337 }, { "epoch": 0.18501868285847733, "grad_norm": 0.37001174688339233, "learning_rate": 9.78163135206821e-06, "loss": 0.2537, "step": 6338 }, { "epoch": 0.1850478748248482, "grad_norm": 0.35455086827278137, "learning_rate": 9.781482398975842e-06, "loss": 0.2155, "step": 6339 }, { "epoch": 0.18507706679121905, "grad_norm": 0.393206387758255, "learning_rate": 9.781333396233931e-06, "loss": 0.2172, "step": 6340 }, { "epoch": 0.1851062587575899, "grad_norm": 0.32271048426628113, "learning_rate": 9.781184343844023e-06, "loss": 0.2134, "step": 6341 }, { "epoch": 0.18513545072396076, "grad_norm": 0.3616890013217926, "learning_rate": 9.781035241807667e-06, "loss": 0.2256, "step": 6342 }, { "epoch": 0.18516464269033162, "grad_norm": 0.373384565114975, "learning_rate": 9.780886090126411e-06, "loss": 0.2426, "step": 6343 }, { "epoch": 0.18519383465670247, "grad_norm": 0.35023555159568787, "learning_rate": 9.780736888801803e-06, "loss": 0.2471, "step": 6344 }, { "epoch": 0.18522302662307333, "grad_norm": 0.4536324441432953, "learning_rate": 9.780587637835393e-06, "loss": 0.2708, "step": 6345 }, { "epoch": 0.18525221858944418, "grad_norm": 0.5910372734069824, "learning_rate": 9.780438337228732e-06, "loss": 0.2435, "step": 6346 }, { "epoch": 0.18528141055581504, "grad_norm": 0.3437686860561371, "learning_rate": 9.780288986983369e-06, "loss": 0.2302, "step": 6347 }, { "epoch": 0.1853106025221859, "grad_norm": 0.49750617146492004, "learning_rate": 9.780139587100855e-06, "loss": 0.254, "step": 6348 }, { "epoch": 0.18533979448855675, "grad_norm": 0.4510223865509033, "learning_rate": 9.779990137582739e-06, "loss": 0.2986, "step": 6349 }, { "epoch": 0.1853689864549276, "grad_norm": 0.34657377004623413, "learning_rate": 9.779840638430576e-06, "loss": 0.2258, "step": 6350 }, { "epoch": 0.18539817842129847, "grad_norm": 0.35304874181747437, "learning_rate": 9.779691089645918e-06, "loss": 0.2121, "step": 6351 }, { "epoch": 0.18542737038766932, "grad_norm": 0.3868499994277954, "learning_rate": 9.779541491230318e-06, "loss": 0.2269, "step": 6352 }, { "epoch": 0.18545656235404018, "grad_norm": 0.3668693006038666, "learning_rate": 9.779391843185326e-06, "loss": 0.2812, "step": 6353 }, { "epoch": 0.18548575432041103, "grad_norm": 0.36272943019866943, "learning_rate": 9.779242145512501e-06, "loss": 0.2354, "step": 6354 }, { "epoch": 0.1855149462867819, "grad_norm": 0.3261744976043701, "learning_rate": 9.779092398213395e-06, "loss": 0.2433, "step": 6355 }, { "epoch": 0.18554413825315275, "grad_norm": 0.3772183656692505, "learning_rate": 9.778942601289562e-06, "loss": 0.235, "step": 6356 }, { "epoch": 0.18557333021952357, "grad_norm": 0.3687112629413605, "learning_rate": 9.778792754742558e-06, "loss": 0.2628, "step": 6357 }, { "epoch": 0.18560252218589443, "grad_norm": 0.39416956901550293, "learning_rate": 9.778642858573939e-06, "loss": 0.2415, "step": 6358 }, { "epoch": 0.1856317141522653, "grad_norm": 0.3335961103439331, "learning_rate": 9.778492912785262e-06, "loss": 0.2133, "step": 6359 }, { "epoch": 0.18566090611863614, "grad_norm": 0.4079527258872986, "learning_rate": 9.778342917378086e-06, "loss": 0.2228, "step": 6360 }, { "epoch": 0.185690098085007, "grad_norm": 0.36375194787979126, "learning_rate": 9.778192872353964e-06, "loss": 0.2359, "step": 6361 }, { "epoch": 0.18571929005137786, "grad_norm": 0.3996090292930603, "learning_rate": 9.778042777714458e-06, "loss": 0.2703, "step": 6362 }, { "epoch": 0.1857484820177487, "grad_norm": 0.37721967697143555, "learning_rate": 9.777892633461123e-06, "loss": 0.2395, "step": 6363 }, { "epoch": 0.18577767398411957, "grad_norm": 0.6270485520362854, "learning_rate": 9.777742439595522e-06, "loss": 0.205, "step": 6364 }, { "epoch": 0.18580686595049042, "grad_norm": 0.4109143614768982, "learning_rate": 9.777592196119209e-06, "loss": 0.2629, "step": 6365 }, { "epoch": 0.18583605791686128, "grad_norm": 0.7452895641326904, "learning_rate": 9.77744190303375e-06, "loss": 0.2734, "step": 6366 }, { "epoch": 0.18586524988323214, "grad_norm": 0.3989940285682678, "learning_rate": 9.777291560340703e-06, "loss": 0.2374, "step": 6367 }, { "epoch": 0.185894441849603, "grad_norm": 0.427425354719162, "learning_rate": 9.77714116804163e-06, "loss": 0.2242, "step": 6368 }, { "epoch": 0.18592363381597385, "grad_norm": 0.5170623064041138, "learning_rate": 9.776990726138092e-06, "loss": 0.2857, "step": 6369 }, { "epoch": 0.1859528257823447, "grad_norm": 0.4862145185470581, "learning_rate": 9.776840234631649e-06, "loss": 0.3072, "step": 6370 }, { "epoch": 0.18598201774871556, "grad_norm": 0.3985474407672882, "learning_rate": 9.776689693523866e-06, "loss": 0.2341, "step": 6371 }, { "epoch": 0.18601120971508642, "grad_norm": 0.3695310056209564, "learning_rate": 9.776539102816307e-06, "loss": 0.2438, "step": 6372 }, { "epoch": 0.18604040168145727, "grad_norm": 0.4014784097671509, "learning_rate": 9.776388462510536e-06, "loss": 0.2464, "step": 6373 }, { "epoch": 0.18606959364782813, "grad_norm": 0.42246589064598083, "learning_rate": 9.776237772608112e-06, "loss": 0.2749, "step": 6374 }, { "epoch": 0.18609878561419899, "grad_norm": 0.4327665865421295, "learning_rate": 9.776087033110607e-06, "loss": 0.231, "step": 6375 }, { "epoch": 0.18612797758056981, "grad_norm": 0.3546793758869171, "learning_rate": 9.775936244019581e-06, "loss": 0.2348, "step": 6376 }, { "epoch": 0.18615716954694067, "grad_norm": 0.3592979609966278, "learning_rate": 9.775785405336602e-06, "loss": 0.2252, "step": 6377 }, { "epoch": 0.18618636151331153, "grad_norm": 0.4356691241264343, "learning_rate": 9.775634517063236e-06, "loss": 0.2576, "step": 6378 }, { "epoch": 0.18621555347968238, "grad_norm": 0.3861750364303589, "learning_rate": 9.77548357920105e-06, "loss": 0.2594, "step": 6379 }, { "epoch": 0.18624474544605324, "grad_norm": 0.3571781814098358, "learning_rate": 9.77533259175161e-06, "loss": 0.238, "step": 6380 }, { "epoch": 0.1862739374124241, "grad_norm": 0.33911648392677307, "learning_rate": 9.775181554716484e-06, "loss": 0.2336, "step": 6381 }, { "epoch": 0.18630312937879495, "grad_norm": 0.3795052170753479, "learning_rate": 9.775030468097241e-06, "loss": 0.2328, "step": 6382 }, { "epoch": 0.1863323213451658, "grad_norm": 0.3347170352935791, "learning_rate": 9.77487933189545e-06, "loss": 0.2338, "step": 6383 }, { "epoch": 0.18636151331153666, "grad_norm": 0.35951685905456543, "learning_rate": 9.774728146112682e-06, "loss": 0.2086, "step": 6384 }, { "epoch": 0.18639070527790752, "grad_norm": 0.35867181420326233, "learning_rate": 9.774576910750503e-06, "loss": 0.1996, "step": 6385 }, { "epoch": 0.18641989724427838, "grad_norm": 0.3797098994255066, "learning_rate": 9.774425625810487e-06, "loss": 0.184, "step": 6386 }, { "epoch": 0.18644908921064923, "grad_norm": 0.366983026266098, "learning_rate": 9.774274291294203e-06, "loss": 0.2799, "step": 6387 }, { "epoch": 0.1864782811770201, "grad_norm": 0.343401163816452, "learning_rate": 9.774122907203222e-06, "loss": 0.2181, "step": 6388 }, { "epoch": 0.18650747314339094, "grad_norm": 0.4646754860877991, "learning_rate": 9.773971473539116e-06, "loss": 0.2557, "step": 6389 }, { "epoch": 0.1865366651097618, "grad_norm": 0.435476690530777, "learning_rate": 9.773819990303459e-06, "loss": 0.2018, "step": 6390 }, { "epoch": 0.18656585707613266, "grad_norm": 0.42169055342674255, "learning_rate": 9.773668457497823e-06, "loss": 0.2422, "step": 6391 }, { "epoch": 0.1865950490425035, "grad_norm": 0.37596407532691956, "learning_rate": 9.773516875123781e-06, "loss": 0.2215, "step": 6392 }, { "epoch": 0.18662424100887437, "grad_norm": 0.40692538022994995, "learning_rate": 9.77336524318291e-06, "loss": 0.2842, "step": 6393 }, { "epoch": 0.18665343297524523, "grad_norm": 0.49096381664276123, "learning_rate": 9.77321356167678e-06, "loss": 0.2975, "step": 6394 }, { "epoch": 0.18668262494161605, "grad_norm": 0.4224018156528473, "learning_rate": 9.773061830606967e-06, "loss": 0.2513, "step": 6395 }, { "epoch": 0.1867118169079869, "grad_norm": 0.33458811044692993, "learning_rate": 9.772910049975049e-06, "loss": 0.2204, "step": 6396 }, { "epoch": 0.18674100887435777, "grad_norm": 0.3852250576019287, "learning_rate": 9.772758219782601e-06, "loss": 0.248, "step": 6397 }, { "epoch": 0.18677020084072862, "grad_norm": 0.41717398166656494, "learning_rate": 9.772606340031199e-06, "loss": 0.2329, "step": 6398 }, { "epoch": 0.18679939280709948, "grad_norm": 0.3638336658477783, "learning_rate": 9.77245441072242e-06, "loss": 0.2608, "step": 6399 }, { "epoch": 0.18682858477347034, "grad_norm": 0.3563765287399292, "learning_rate": 9.77230243185784e-06, "loss": 0.2845, "step": 6400 }, { "epoch": 0.1868577767398412, "grad_norm": 0.34442099928855896, "learning_rate": 9.772150403439043e-06, "loss": 0.2414, "step": 6401 }, { "epoch": 0.18688696870621205, "grad_norm": 0.35731539130210876, "learning_rate": 9.7719983254676e-06, "loss": 0.2117, "step": 6402 }, { "epoch": 0.1869161606725829, "grad_norm": 0.6264081597328186, "learning_rate": 9.771846197945096e-06, "loss": 0.2363, "step": 6403 }, { "epoch": 0.18694535263895376, "grad_norm": 0.4852183759212494, "learning_rate": 9.771694020873106e-06, "loss": 0.2921, "step": 6404 }, { "epoch": 0.18697454460532462, "grad_norm": 0.39140212535858154, "learning_rate": 9.771541794253215e-06, "loss": 0.2816, "step": 6405 }, { "epoch": 0.18700373657169547, "grad_norm": 0.3468967080116272, "learning_rate": 9.771389518087e-06, "loss": 0.2596, "step": 6406 }, { "epoch": 0.18703292853806633, "grad_norm": 0.29210567474365234, "learning_rate": 9.771237192376044e-06, "loss": 0.1795, "step": 6407 }, { "epoch": 0.18706212050443718, "grad_norm": 0.43094202876091003, "learning_rate": 9.771084817121927e-06, "loss": 0.2774, "step": 6408 }, { "epoch": 0.18709131247080804, "grad_norm": 0.43542927503585815, "learning_rate": 9.770932392326233e-06, "loss": 0.2686, "step": 6409 }, { "epoch": 0.1871205044371789, "grad_norm": 0.47366970777511597, "learning_rate": 9.770779917990544e-06, "loss": 0.2367, "step": 6410 }, { "epoch": 0.18714969640354975, "grad_norm": 0.3622855544090271, "learning_rate": 9.770627394116443e-06, "loss": 0.268, "step": 6411 }, { "epoch": 0.1871788883699206, "grad_norm": 0.43485087156295776, "learning_rate": 9.770474820705516e-06, "loss": 0.2443, "step": 6412 }, { "epoch": 0.18720808033629147, "grad_norm": 0.3912428617477417, "learning_rate": 9.770322197759342e-06, "loss": 0.2783, "step": 6413 }, { "epoch": 0.1872372723026623, "grad_norm": 0.3859592080116272, "learning_rate": 9.770169525279512e-06, "loss": 0.2616, "step": 6414 }, { "epoch": 0.18726646426903315, "grad_norm": 0.3700386583805084, "learning_rate": 9.770016803267607e-06, "loss": 0.2161, "step": 6415 }, { "epoch": 0.187295656235404, "grad_norm": 0.3396282494068146, "learning_rate": 9.769864031725215e-06, "loss": 0.221, "step": 6416 }, { "epoch": 0.18732484820177486, "grad_norm": 0.43437784910202026, "learning_rate": 9.76971121065392e-06, "loss": 0.2654, "step": 6417 }, { "epoch": 0.18735404016814572, "grad_norm": 0.40324947237968445, "learning_rate": 9.769558340055313e-06, "loss": 0.2021, "step": 6418 }, { "epoch": 0.18738323213451658, "grad_norm": 0.3652461767196655, "learning_rate": 9.769405419930977e-06, "loss": 0.2529, "step": 6419 }, { "epoch": 0.18741242410088743, "grad_norm": 0.42374807596206665, "learning_rate": 9.769252450282503e-06, "loss": 0.2566, "step": 6420 }, { "epoch": 0.1874416160672583, "grad_norm": 0.4381139874458313, "learning_rate": 9.769099431111478e-06, "loss": 0.2441, "step": 6421 }, { "epoch": 0.18747080803362914, "grad_norm": 0.4180394113063812, "learning_rate": 9.768946362419489e-06, "loss": 0.2816, "step": 6422 }, { "epoch": 0.1875, "grad_norm": 0.3594055771827698, "learning_rate": 9.768793244208128e-06, "loss": 0.226, "step": 6423 }, { "epoch": 0.18752919196637086, "grad_norm": 0.37698572874069214, "learning_rate": 9.768640076478985e-06, "loss": 0.25, "step": 6424 }, { "epoch": 0.1875583839327417, "grad_norm": 0.5050490498542786, "learning_rate": 9.76848685923365e-06, "loss": 0.2164, "step": 6425 }, { "epoch": 0.18758757589911257, "grad_norm": 0.41724157333374023, "learning_rate": 9.768333592473715e-06, "loss": 0.2722, "step": 6426 }, { "epoch": 0.18761676786548342, "grad_norm": 0.3375992178916931, "learning_rate": 9.768180276200769e-06, "loss": 0.2013, "step": 6427 }, { "epoch": 0.18764595983185428, "grad_norm": 0.43828511238098145, "learning_rate": 9.768026910416404e-06, "loss": 0.2112, "step": 6428 }, { "epoch": 0.18767515179822514, "grad_norm": 0.3669489920139313, "learning_rate": 9.767873495122216e-06, "loss": 0.2124, "step": 6429 }, { "epoch": 0.187704343764596, "grad_norm": 0.3452184498310089, "learning_rate": 9.767720030319794e-06, "loss": 0.2253, "step": 6430 }, { "epoch": 0.18773353573096685, "grad_norm": 0.3599213659763336, "learning_rate": 9.767566516010733e-06, "loss": 0.239, "step": 6431 }, { "epoch": 0.1877627276973377, "grad_norm": 0.35752031207084656, "learning_rate": 9.76741295219663e-06, "loss": 0.3175, "step": 6432 }, { "epoch": 0.18779191966370853, "grad_norm": 0.35787421464920044, "learning_rate": 9.767259338879075e-06, "loss": 0.2411, "step": 6433 }, { "epoch": 0.1878211116300794, "grad_norm": 0.4762904942035675, "learning_rate": 9.767105676059666e-06, "loss": 0.2499, "step": 6434 }, { "epoch": 0.18785030359645025, "grad_norm": 0.4191032350063324, "learning_rate": 9.766951963739997e-06, "loss": 0.3012, "step": 6435 }, { "epoch": 0.1878794955628211, "grad_norm": 0.8812612295150757, "learning_rate": 9.766798201921664e-06, "loss": 0.2634, "step": 6436 }, { "epoch": 0.18790868752919196, "grad_norm": 0.36929070949554443, "learning_rate": 9.766644390606265e-06, "loss": 0.2556, "step": 6437 }, { "epoch": 0.18793787949556282, "grad_norm": 0.4143214821815491, "learning_rate": 9.766490529795396e-06, "loss": 0.2837, "step": 6438 }, { "epoch": 0.18796707146193367, "grad_norm": 0.36324629187583923, "learning_rate": 9.766336619490655e-06, "loss": 0.2515, "step": 6439 }, { "epoch": 0.18799626342830453, "grad_norm": 0.3617609143257141, "learning_rate": 9.766182659693641e-06, "loss": 0.2602, "step": 6440 }, { "epoch": 0.18802545539467538, "grad_norm": 0.33991894125938416, "learning_rate": 9.766028650405952e-06, "loss": 0.2299, "step": 6441 }, { "epoch": 0.18805464736104624, "grad_norm": 0.353087455034256, "learning_rate": 9.765874591629186e-06, "loss": 0.267, "step": 6442 }, { "epoch": 0.1880838393274171, "grad_norm": 0.3696243464946747, "learning_rate": 9.765720483364944e-06, "loss": 0.2922, "step": 6443 }, { "epoch": 0.18811303129378795, "grad_norm": 0.446029931306839, "learning_rate": 9.765566325614829e-06, "loss": 0.2481, "step": 6444 }, { "epoch": 0.1881422232601588, "grad_norm": 0.36960887908935547, "learning_rate": 9.765412118380435e-06, "loss": 0.2695, "step": 6445 }, { "epoch": 0.18817141522652966, "grad_norm": 0.3455078899860382, "learning_rate": 9.765257861663368e-06, "loss": 0.2525, "step": 6446 }, { "epoch": 0.18820060719290052, "grad_norm": 0.3672651946544647, "learning_rate": 9.765103555465229e-06, "loss": 0.2518, "step": 6447 }, { "epoch": 0.18822979915927138, "grad_norm": 0.3273748457431793, "learning_rate": 9.764949199787621e-06, "loss": 0.2463, "step": 6448 }, { "epoch": 0.18825899112564223, "grad_norm": 0.36502835154533386, "learning_rate": 9.764794794632144e-06, "loss": 0.2737, "step": 6449 }, { "epoch": 0.1882881830920131, "grad_norm": 0.7579159736633301, "learning_rate": 9.764640340000405e-06, "loss": 0.253, "step": 6450 }, { "epoch": 0.18831737505838395, "grad_norm": 0.3875485062599182, "learning_rate": 9.764485835894005e-06, "loss": 0.2765, "step": 6451 }, { "epoch": 0.18834656702475477, "grad_norm": 0.3782401382923126, "learning_rate": 9.764331282314549e-06, "loss": 0.2691, "step": 6452 }, { "epoch": 0.18837575899112563, "grad_norm": 0.3587515354156494, "learning_rate": 9.764176679263642e-06, "loss": 0.276, "step": 6453 }, { "epoch": 0.1884049509574965, "grad_norm": 0.4742752015590668, "learning_rate": 9.76402202674289e-06, "loss": 0.2452, "step": 6454 }, { "epoch": 0.18843414292386734, "grad_norm": 0.40272945165634155, "learning_rate": 9.763867324753897e-06, "loss": 0.2651, "step": 6455 }, { "epoch": 0.1884633348902382, "grad_norm": 0.3275497555732727, "learning_rate": 9.763712573298272e-06, "loss": 0.2251, "step": 6456 }, { "epoch": 0.18849252685660906, "grad_norm": 0.35179126262664795, "learning_rate": 9.763557772377621e-06, "loss": 0.2445, "step": 6457 }, { "epoch": 0.1885217188229799, "grad_norm": 0.36041200160980225, "learning_rate": 9.76340292199355e-06, "loss": 0.2332, "step": 6458 }, { "epoch": 0.18855091078935077, "grad_norm": 0.35632407665252686, "learning_rate": 9.763248022147668e-06, "loss": 0.2591, "step": 6459 }, { "epoch": 0.18858010275572162, "grad_norm": 0.3421032130718231, "learning_rate": 9.763093072841585e-06, "loss": 0.2272, "step": 6460 }, { "epoch": 0.18860929472209248, "grad_norm": 0.33324170112609863, "learning_rate": 9.762938074076907e-06, "loss": 0.2237, "step": 6461 }, { "epoch": 0.18863848668846334, "grad_norm": 0.29656150937080383, "learning_rate": 9.762783025855245e-06, "loss": 0.1839, "step": 6462 }, { "epoch": 0.1886676786548342, "grad_norm": 0.5155889391899109, "learning_rate": 9.762627928178208e-06, "loss": 0.2555, "step": 6463 }, { "epoch": 0.18869687062120505, "grad_norm": 0.3824368715286255, "learning_rate": 9.762472781047407e-06, "loss": 0.3167, "step": 6464 }, { "epoch": 0.1887260625875759, "grad_norm": 0.33569830656051636, "learning_rate": 9.762317584464454e-06, "loss": 0.2183, "step": 6465 }, { "epoch": 0.18875525455394676, "grad_norm": 0.3986464738845825, "learning_rate": 9.762162338430961e-06, "loss": 0.2192, "step": 6466 }, { "epoch": 0.18878444652031762, "grad_norm": 0.31896644830703735, "learning_rate": 9.762007042948536e-06, "loss": 0.1827, "step": 6467 }, { "epoch": 0.18881363848668847, "grad_norm": 0.35744917392730713, "learning_rate": 9.761851698018796e-06, "loss": 0.2315, "step": 6468 }, { "epoch": 0.18884283045305933, "grad_norm": 0.4656210243701935, "learning_rate": 9.761696303643354e-06, "loss": 0.2336, "step": 6469 }, { "epoch": 0.18887202241943019, "grad_norm": 0.40123382210731506, "learning_rate": 9.76154085982382e-06, "loss": 0.2489, "step": 6470 }, { "epoch": 0.18890121438580101, "grad_norm": 0.37848401069641113, "learning_rate": 9.761385366561809e-06, "loss": 0.2723, "step": 6471 }, { "epoch": 0.18893040635217187, "grad_norm": 0.3511746823787689, "learning_rate": 9.761229823858937e-06, "loss": 0.2463, "step": 6472 }, { "epoch": 0.18895959831854273, "grad_norm": 0.36689308285713196, "learning_rate": 9.761074231716821e-06, "loss": 0.2908, "step": 6473 }, { "epoch": 0.18898879028491358, "grad_norm": 0.31806641817092896, "learning_rate": 9.760918590137071e-06, "loss": 0.2187, "step": 6474 }, { "epoch": 0.18901798225128444, "grad_norm": 0.31947875022888184, "learning_rate": 9.76076289912131e-06, "loss": 0.2437, "step": 6475 }, { "epoch": 0.1890471742176553, "grad_norm": 0.3589481711387634, "learning_rate": 9.76060715867115e-06, "loss": 0.2217, "step": 6476 }, { "epoch": 0.18907636618402615, "grad_norm": 0.3946361839771271, "learning_rate": 9.760451368788208e-06, "loss": 0.2447, "step": 6477 }, { "epoch": 0.189105558150397, "grad_norm": 0.3796304166316986, "learning_rate": 9.760295529474104e-06, "loss": 0.2154, "step": 6478 }, { "epoch": 0.18913475011676786, "grad_norm": 0.37216344475746155, "learning_rate": 9.760139640730456e-06, "loss": 0.2422, "step": 6479 }, { "epoch": 0.18916394208313872, "grad_norm": 0.4015357792377472, "learning_rate": 9.759983702558881e-06, "loss": 0.2212, "step": 6480 }, { "epoch": 0.18919313404950958, "grad_norm": 0.4147947430610657, "learning_rate": 9.759827714960998e-06, "loss": 0.2897, "step": 6481 }, { "epoch": 0.18922232601588043, "grad_norm": 0.5809265971183777, "learning_rate": 9.75967167793843e-06, "loss": 0.234, "step": 6482 }, { "epoch": 0.1892515179822513, "grad_norm": 0.3765757381916046, "learning_rate": 9.759515591492793e-06, "loss": 0.239, "step": 6483 }, { "epoch": 0.18928070994862214, "grad_norm": 0.3487776517868042, "learning_rate": 9.759359455625712e-06, "loss": 0.2452, "step": 6484 }, { "epoch": 0.189309901914993, "grad_norm": 0.42895424365997314, "learning_rate": 9.759203270338806e-06, "loss": 0.2403, "step": 6485 }, { "epoch": 0.18933909388136386, "grad_norm": 0.3951483368873596, "learning_rate": 9.759047035633695e-06, "loss": 0.2329, "step": 6486 }, { "epoch": 0.1893682858477347, "grad_norm": 0.3706570267677307, "learning_rate": 9.758890751512005e-06, "loss": 0.2283, "step": 6487 }, { "epoch": 0.18939747781410557, "grad_norm": 0.39077138900756836, "learning_rate": 9.758734417975357e-06, "loss": 0.2367, "step": 6488 }, { "epoch": 0.18942666978047643, "grad_norm": 0.6172865629196167, "learning_rate": 9.758578035025373e-06, "loss": 0.2289, "step": 6489 }, { "epoch": 0.18945586174684725, "grad_norm": 0.3352609872817993, "learning_rate": 9.75842160266368e-06, "loss": 0.2893, "step": 6490 }, { "epoch": 0.1894850537132181, "grad_norm": 0.4613243639469147, "learning_rate": 9.758265120891899e-06, "loss": 0.2196, "step": 6491 }, { "epoch": 0.18951424567958897, "grad_norm": 0.4619273841381073, "learning_rate": 9.758108589711655e-06, "loss": 0.2897, "step": 6492 }, { "epoch": 0.18954343764595982, "grad_norm": 0.38480472564697266, "learning_rate": 9.757952009124577e-06, "loss": 0.1907, "step": 6493 }, { "epoch": 0.18957262961233068, "grad_norm": 0.32481372356414795, "learning_rate": 9.757795379132289e-06, "loss": 0.2225, "step": 6494 }, { "epoch": 0.18960182157870153, "grad_norm": 0.4504830837249756, "learning_rate": 9.757638699736417e-06, "loss": 0.266, "step": 6495 }, { "epoch": 0.1896310135450724, "grad_norm": 0.3537639081478119, "learning_rate": 9.757481970938584e-06, "loss": 0.2589, "step": 6496 }, { "epoch": 0.18966020551144325, "grad_norm": 0.5107530951499939, "learning_rate": 9.757325192740425e-06, "loss": 0.283, "step": 6497 }, { "epoch": 0.1896893974778141, "grad_norm": 0.31036123633384705, "learning_rate": 9.757168365143565e-06, "loss": 0.2481, "step": 6498 }, { "epoch": 0.18971858944418496, "grad_norm": 0.341533362865448, "learning_rate": 9.757011488149631e-06, "loss": 0.233, "step": 6499 }, { "epoch": 0.18974778141055582, "grad_norm": 0.3817116618156433, "learning_rate": 9.756854561760252e-06, "loss": 0.2486, "step": 6500 }, { "epoch": 0.18977697337692667, "grad_norm": 0.38398975133895874, "learning_rate": 9.756697585977057e-06, "loss": 0.2495, "step": 6501 }, { "epoch": 0.18980616534329753, "grad_norm": 0.3485758304595947, "learning_rate": 9.75654056080168e-06, "loss": 0.2226, "step": 6502 }, { "epoch": 0.18983535730966838, "grad_norm": 0.3568089008331299, "learning_rate": 9.756383486235747e-06, "loss": 0.2234, "step": 6503 }, { "epoch": 0.18986454927603924, "grad_norm": 0.5291005969047546, "learning_rate": 9.756226362280892e-06, "loss": 0.2264, "step": 6504 }, { "epoch": 0.1898937412424101, "grad_norm": 0.3469464182853699, "learning_rate": 9.756069188938744e-06, "loss": 0.2518, "step": 6505 }, { "epoch": 0.18992293320878095, "grad_norm": 0.4151594936847687, "learning_rate": 9.755911966210936e-06, "loss": 0.2957, "step": 6506 }, { "epoch": 0.1899521251751518, "grad_norm": 0.421017587184906, "learning_rate": 9.755754694099102e-06, "loss": 0.2069, "step": 6507 }, { "epoch": 0.18998131714152267, "grad_norm": 0.3757709562778473, "learning_rate": 9.755597372604873e-06, "loss": 0.2926, "step": 6508 }, { "epoch": 0.19001050910789352, "grad_norm": 0.378546804189682, "learning_rate": 9.755440001729883e-06, "loss": 0.2221, "step": 6509 }, { "epoch": 0.19003970107426435, "grad_norm": 0.35189154744148254, "learning_rate": 9.755282581475769e-06, "loss": 0.2788, "step": 6510 }, { "epoch": 0.1900688930406352, "grad_norm": 0.3753871023654938, "learning_rate": 9.75512511184416e-06, "loss": 0.2343, "step": 6511 }, { "epoch": 0.19009808500700606, "grad_norm": 0.37847957015037537, "learning_rate": 9.754967592836697e-06, "loss": 0.3127, "step": 6512 }, { "epoch": 0.19012727697337692, "grad_norm": 0.4975011348724365, "learning_rate": 9.754810024455013e-06, "loss": 0.2582, "step": 6513 }, { "epoch": 0.19015646893974777, "grad_norm": 0.3064933121204376, "learning_rate": 9.754652406700744e-06, "loss": 0.1998, "step": 6514 }, { "epoch": 0.19018566090611863, "grad_norm": 0.34667307138442993, "learning_rate": 9.754494739575525e-06, "loss": 0.3072, "step": 6515 }, { "epoch": 0.1902148528724895, "grad_norm": 0.3707663118839264, "learning_rate": 9.754337023080996e-06, "loss": 0.2421, "step": 6516 }, { "epoch": 0.19024404483886034, "grad_norm": 0.5016624331474304, "learning_rate": 9.754179257218793e-06, "loss": 0.2405, "step": 6517 }, { "epoch": 0.1902732368052312, "grad_norm": 0.34477388858795166, "learning_rate": 9.754021441990556e-06, "loss": 0.2365, "step": 6518 }, { "epoch": 0.19030242877160206, "grad_norm": 0.3769782781600952, "learning_rate": 9.753863577397922e-06, "loss": 0.2569, "step": 6519 }, { "epoch": 0.1903316207379729, "grad_norm": 0.3912689983844757, "learning_rate": 9.75370566344253e-06, "loss": 0.2554, "step": 6520 }, { "epoch": 0.19036081270434377, "grad_norm": 0.3651483654975891, "learning_rate": 9.753547700126022e-06, "loss": 0.2392, "step": 6521 }, { "epoch": 0.19039000467071462, "grad_norm": 0.3836153447628021, "learning_rate": 9.753389687450036e-06, "loss": 0.235, "step": 6522 }, { "epoch": 0.19041919663708548, "grad_norm": 0.3531953692436218, "learning_rate": 9.753231625416212e-06, "loss": 0.2405, "step": 6523 }, { "epoch": 0.19044838860345634, "grad_norm": 3.9570372104644775, "learning_rate": 9.753073514026194e-06, "loss": 0.2116, "step": 6524 }, { "epoch": 0.1904775805698272, "grad_norm": 0.42134350538253784, "learning_rate": 9.752915353281624e-06, "loss": 0.3009, "step": 6525 }, { "epoch": 0.19050677253619805, "grad_norm": 0.4172406494617462, "learning_rate": 9.75275714318414e-06, "loss": 0.2948, "step": 6526 }, { "epoch": 0.1905359645025689, "grad_norm": 0.3647933900356293, "learning_rate": 9.75259888373539e-06, "loss": 0.2644, "step": 6527 }, { "epoch": 0.19056515646893976, "grad_norm": 0.32280856370925903, "learning_rate": 9.752440574937014e-06, "loss": 0.2174, "step": 6528 }, { "epoch": 0.1905943484353106, "grad_norm": 0.3698002099990845, "learning_rate": 9.752282216790657e-06, "loss": 0.3216, "step": 6529 }, { "epoch": 0.19062354040168145, "grad_norm": 0.34490853548049927, "learning_rate": 9.752123809297962e-06, "loss": 0.2202, "step": 6530 }, { "epoch": 0.1906527323680523, "grad_norm": 0.7093064188957214, "learning_rate": 9.751965352460577e-06, "loss": 0.2376, "step": 6531 }, { "epoch": 0.19068192433442316, "grad_norm": 0.37336862087249756, "learning_rate": 9.751806846280143e-06, "loss": 0.2337, "step": 6532 }, { "epoch": 0.19071111630079401, "grad_norm": 0.41202664375305176, "learning_rate": 9.751648290758311e-06, "loss": 0.2037, "step": 6533 }, { "epoch": 0.19074030826716487, "grad_norm": 0.3406767249107361, "learning_rate": 9.751489685896723e-06, "loss": 0.2005, "step": 6534 }, { "epoch": 0.19076950023353573, "grad_norm": 0.35701775550842285, "learning_rate": 9.751331031697027e-06, "loss": 0.2287, "step": 6535 }, { "epoch": 0.19079869219990658, "grad_norm": 0.384826123714447, "learning_rate": 9.751172328160871e-06, "loss": 0.2734, "step": 6536 }, { "epoch": 0.19082788416627744, "grad_norm": 0.4194990396499634, "learning_rate": 9.751013575289905e-06, "loss": 0.2603, "step": 6537 }, { "epoch": 0.1908570761326483, "grad_norm": 0.3748137354850769, "learning_rate": 9.750854773085774e-06, "loss": 0.236, "step": 6538 }, { "epoch": 0.19088626809901915, "grad_norm": 0.3810509741306305, "learning_rate": 9.750695921550128e-06, "loss": 0.263, "step": 6539 }, { "epoch": 0.19091546006539, "grad_norm": 0.37773701548576355, "learning_rate": 9.750537020684618e-06, "loss": 0.2603, "step": 6540 }, { "epoch": 0.19094465203176086, "grad_norm": 0.3746749758720398, "learning_rate": 9.75037807049089e-06, "loss": 0.2613, "step": 6541 }, { "epoch": 0.19097384399813172, "grad_norm": 0.35179007053375244, "learning_rate": 9.750219070970601e-06, "loss": 0.2422, "step": 6542 }, { "epoch": 0.19100303596450258, "grad_norm": 0.38749930262565613, "learning_rate": 9.750060022125396e-06, "loss": 0.2965, "step": 6543 }, { "epoch": 0.19103222793087343, "grad_norm": 0.37981829047203064, "learning_rate": 9.74990092395693e-06, "loss": 0.2513, "step": 6544 }, { "epoch": 0.1910614198972443, "grad_norm": 0.3713802099227905, "learning_rate": 9.749741776466852e-06, "loss": 0.232, "step": 6545 }, { "epoch": 0.19109061186361515, "grad_norm": 0.4011744558811188, "learning_rate": 9.749582579656818e-06, "loss": 0.2585, "step": 6546 }, { "epoch": 0.191119803829986, "grad_norm": 0.44804924726486206, "learning_rate": 9.749423333528477e-06, "loss": 0.2394, "step": 6547 }, { "epoch": 0.19114899579635683, "grad_norm": 1.6163617372512817, "learning_rate": 9.749264038083487e-06, "loss": 0.2369, "step": 6548 }, { "epoch": 0.19117818776272769, "grad_norm": 0.37859317660331726, "learning_rate": 9.7491046933235e-06, "loss": 0.2277, "step": 6549 }, { "epoch": 0.19120737972909854, "grad_norm": 0.37803414463996887, "learning_rate": 9.74894529925017e-06, "loss": 0.2378, "step": 6550 }, { "epoch": 0.1912365716954694, "grad_norm": 0.3976091146469116, "learning_rate": 9.748785855865154e-06, "loss": 0.233, "step": 6551 }, { "epoch": 0.19126576366184025, "grad_norm": 0.3727542757987976, "learning_rate": 9.748626363170106e-06, "loss": 0.2594, "step": 6552 }, { "epoch": 0.1912949556282111, "grad_norm": 0.3636379837989807, "learning_rate": 9.74846682116668e-06, "loss": 0.2728, "step": 6553 }, { "epoch": 0.19132414759458197, "grad_norm": 0.44092339277267456, "learning_rate": 9.748307229856538e-06, "loss": 0.2754, "step": 6554 }, { "epoch": 0.19135333956095282, "grad_norm": 0.45571169257164, "learning_rate": 9.748147589241332e-06, "loss": 0.2146, "step": 6555 }, { "epoch": 0.19138253152732368, "grad_norm": 0.36555203795433044, "learning_rate": 9.747987899322724e-06, "loss": 0.2284, "step": 6556 }, { "epoch": 0.19141172349369454, "grad_norm": 0.514759361743927, "learning_rate": 9.74782816010237e-06, "loss": 0.2555, "step": 6557 }, { "epoch": 0.1914409154600654, "grad_norm": 0.3599149286746979, "learning_rate": 9.747668371581928e-06, "loss": 0.255, "step": 6558 }, { "epoch": 0.19147010742643625, "grad_norm": 0.43270084261894226, "learning_rate": 9.747508533763058e-06, "loss": 0.2926, "step": 6559 }, { "epoch": 0.1914992993928071, "grad_norm": 0.3206977844238281, "learning_rate": 9.747348646647419e-06, "loss": 0.215, "step": 6560 }, { "epoch": 0.19152849135917796, "grad_norm": 0.3303459584712982, "learning_rate": 9.747188710236673e-06, "loss": 0.2309, "step": 6561 }, { "epoch": 0.19155768332554882, "grad_norm": 0.38104432821273804, "learning_rate": 9.74702872453248e-06, "loss": 0.2956, "step": 6562 }, { "epoch": 0.19158687529191967, "grad_norm": 0.3379904627799988, "learning_rate": 9.746868689536499e-06, "loss": 0.2204, "step": 6563 }, { "epoch": 0.19161606725829053, "grad_norm": 0.38036346435546875, "learning_rate": 9.746708605250396e-06, "loss": 0.2653, "step": 6564 }, { "epoch": 0.19164525922466139, "grad_norm": 0.4295516610145569, "learning_rate": 9.74654847167583e-06, "loss": 0.2998, "step": 6565 }, { "epoch": 0.19167445119103224, "grad_norm": 0.41274338960647583, "learning_rate": 9.746388288814463e-06, "loss": 0.2696, "step": 6566 }, { "epoch": 0.19170364315740307, "grad_norm": 0.34194979071617126, "learning_rate": 9.746228056667963e-06, "loss": 0.23, "step": 6567 }, { "epoch": 0.19173283512377393, "grad_norm": 0.5488176345825195, "learning_rate": 9.746067775237989e-06, "loss": 0.273, "step": 6568 }, { "epoch": 0.19176202709014478, "grad_norm": 0.3588455617427826, "learning_rate": 9.745907444526206e-06, "loss": 0.2555, "step": 6569 }, { "epoch": 0.19179121905651564, "grad_norm": 0.3125591278076172, "learning_rate": 9.745747064534284e-06, "loss": 0.2159, "step": 6570 }, { "epoch": 0.1918204110228865, "grad_norm": 0.3985902965068817, "learning_rate": 9.745586635263879e-06, "loss": 0.3489, "step": 6571 }, { "epoch": 0.19184960298925735, "grad_norm": 0.453460693359375, "learning_rate": 9.745426156716666e-06, "loss": 0.2555, "step": 6572 }, { "epoch": 0.1918787949556282, "grad_norm": 0.3910512924194336, "learning_rate": 9.745265628894307e-06, "loss": 0.2778, "step": 6573 }, { "epoch": 0.19190798692199906, "grad_norm": 0.3794967830181122, "learning_rate": 9.745105051798468e-06, "loss": 0.269, "step": 6574 }, { "epoch": 0.19193717888836992, "grad_norm": 0.3374544680118561, "learning_rate": 9.744944425430818e-06, "loss": 0.2098, "step": 6575 }, { "epoch": 0.19196637085474078, "grad_norm": 0.3914649784564972, "learning_rate": 9.744783749793025e-06, "loss": 0.2854, "step": 6576 }, { "epoch": 0.19199556282111163, "grad_norm": 0.4000844359397888, "learning_rate": 9.744623024886757e-06, "loss": 0.2079, "step": 6577 }, { "epoch": 0.1920247547874825, "grad_norm": 0.38875842094421387, "learning_rate": 9.744462250713684e-06, "loss": 0.2422, "step": 6578 }, { "epoch": 0.19205394675385334, "grad_norm": 0.40635043382644653, "learning_rate": 9.744301427275474e-06, "loss": 0.2283, "step": 6579 }, { "epoch": 0.1920831387202242, "grad_norm": 0.3756241500377655, "learning_rate": 9.744140554573797e-06, "loss": 0.2296, "step": 6580 }, { "epoch": 0.19211233068659506, "grad_norm": 0.3597274720668793, "learning_rate": 9.743979632610324e-06, "loss": 0.2345, "step": 6581 }, { "epoch": 0.1921415226529659, "grad_norm": 0.365814745426178, "learning_rate": 9.743818661386726e-06, "loss": 0.254, "step": 6582 }, { "epoch": 0.19217071461933677, "grad_norm": 0.3645194172859192, "learning_rate": 9.743657640904673e-06, "loss": 0.295, "step": 6583 }, { "epoch": 0.19219990658570762, "grad_norm": 0.3485175371170044, "learning_rate": 9.74349657116584e-06, "loss": 0.2433, "step": 6584 }, { "epoch": 0.19222909855207848, "grad_norm": 0.3393150866031647, "learning_rate": 9.743335452171896e-06, "loss": 0.2424, "step": 6585 }, { "epoch": 0.1922582905184493, "grad_norm": 0.39059263467788696, "learning_rate": 9.743174283924516e-06, "loss": 0.2621, "step": 6586 }, { "epoch": 0.19228748248482017, "grad_norm": 0.35596325993537903, "learning_rate": 9.743013066425376e-06, "loss": 0.2621, "step": 6587 }, { "epoch": 0.19231667445119102, "grad_norm": 0.434745192527771, "learning_rate": 9.742851799676144e-06, "loss": 0.2053, "step": 6588 }, { "epoch": 0.19234586641756188, "grad_norm": 0.3309856057167053, "learning_rate": 9.742690483678498e-06, "loss": 0.2374, "step": 6589 }, { "epoch": 0.19237505838393273, "grad_norm": 0.44955143332481384, "learning_rate": 9.742529118434115e-06, "loss": 0.2341, "step": 6590 }, { "epoch": 0.1924042503503036, "grad_norm": 0.3819284439086914, "learning_rate": 9.742367703944669e-06, "loss": 0.2494, "step": 6591 }, { "epoch": 0.19243344231667445, "grad_norm": 0.3537968397140503, "learning_rate": 9.742206240211833e-06, "loss": 0.2962, "step": 6592 }, { "epoch": 0.1924626342830453, "grad_norm": 0.41757023334503174, "learning_rate": 9.742044727237287e-06, "loss": 0.2851, "step": 6593 }, { "epoch": 0.19249182624941616, "grad_norm": 0.3106223940849304, "learning_rate": 9.741883165022709e-06, "loss": 0.1898, "step": 6594 }, { "epoch": 0.19252101821578702, "grad_norm": 0.3692888915538788, "learning_rate": 9.741721553569774e-06, "loss": 0.239, "step": 6595 }, { "epoch": 0.19255021018215787, "grad_norm": 0.35260432958602905, "learning_rate": 9.74155989288016e-06, "loss": 0.2603, "step": 6596 }, { "epoch": 0.19257940214852873, "grad_norm": 0.3193448483943939, "learning_rate": 9.741398182955548e-06, "loss": 0.2385, "step": 6597 }, { "epoch": 0.19260859411489958, "grad_norm": 0.4145711362361908, "learning_rate": 9.741236423797615e-06, "loss": 0.2779, "step": 6598 }, { "epoch": 0.19263778608127044, "grad_norm": 0.3734317719936371, "learning_rate": 9.741074615408042e-06, "loss": 0.2676, "step": 6599 }, { "epoch": 0.1926669780476413, "grad_norm": 0.39136651158332825, "learning_rate": 9.740912757788507e-06, "loss": 0.2744, "step": 6600 }, { "epoch": 0.19269617001401215, "grad_norm": 0.3276832401752472, "learning_rate": 9.740750850940695e-06, "loss": 0.2423, "step": 6601 }, { "epoch": 0.192725361980383, "grad_norm": 0.3076396882534027, "learning_rate": 9.740588894866284e-06, "loss": 0.2511, "step": 6602 }, { "epoch": 0.19275455394675386, "grad_norm": 0.37103259563446045, "learning_rate": 9.740426889566954e-06, "loss": 0.2329, "step": 6603 }, { "epoch": 0.19278374591312472, "grad_norm": 0.40647855401039124, "learning_rate": 9.74026483504439e-06, "loss": 0.235, "step": 6604 }, { "epoch": 0.19281293787949555, "grad_norm": 0.44059303402900696, "learning_rate": 9.740102731300277e-06, "loss": 0.2789, "step": 6605 }, { "epoch": 0.1928421298458664, "grad_norm": 0.36664247512817383, "learning_rate": 9.739940578336293e-06, "loss": 0.2138, "step": 6606 }, { "epoch": 0.19287132181223726, "grad_norm": 0.37810665369033813, "learning_rate": 9.739778376154126e-06, "loss": 0.2696, "step": 6607 }, { "epoch": 0.19290051377860812, "grad_norm": 0.3514869213104248, "learning_rate": 9.739616124755455e-06, "loss": 0.2024, "step": 6608 }, { "epoch": 0.19292970574497897, "grad_norm": 0.4792584478855133, "learning_rate": 9.739453824141972e-06, "loss": 0.2434, "step": 6609 }, { "epoch": 0.19295889771134983, "grad_norm": 0.40961161255836487, "learning_rate": 9.739291474315357e-06, "loss": 0.2416, "step": 6610 }, { "epoch": 0.1929880896777207, "grad_norm": 0.3788232207298279, "learning_rate": 9.739129075277296e-06, "loss": 0.2093, "step": 6611 }, { "epoch": 0.19301728164409154, "grad_norm": 0.42027121782302856, "learning_rate": 9.738966627029478e-06, "loss": 0.2543, "step": 6612 }, { "epoch": 0.1930464736104624, "grad_norm": 0.4604361057281494, "learning_rate": 9.73880412957359e-06, "loss": 0.2745, "step": 6613 }, { "epoch": 0.19307566557683326, "grad_norm": 0.36869022250175476, "learning_rate": 9.738641582911314e-06, "loss": 0.2319, "step": 6614 }, { "epoch": 0.1931048575432041, "grad_norm": 0.3413669466972351, "learning_rate": 9.738478987044344e-06, "loss": 0.2622, "step": 6615 }, { "epoch": 0.19313404950957497, "grad_norm": 0.3887220621109009, "learning_rate": 9.738316341974365e-06, "loss": 0.2459, "step": 6616 }, { "epoch": 0.19316324147594582, "grad_norm": 0.3668568432331085, "learning_rate": 9.738153647703068e-06, "loss": 0.2301, "step": 6617 }, { "epoch": 0.19319243344231668, "grad_norm": 0.3540036678314209, "learning_rate": 9.73799090423214e-06, "loss": 0.2162, "step": 6618 }, { "epoch": 0.19322162540868754, "grad_norm": 0.3413531482219696, "learning_rate": 9.737828111563272e-06, "loss": 0.2488, "step": 6619 }, { "epoch": 0.1932508173750584, "grad_norm": 0.3505931496620178, "learning_rate": 9.737665269698156e-06, "loss": 0.2685, "step": 6620 }, { "epoch": 0.19328000934142925, "grad_norm": 0.40710437297821045, "learning_rate": 9.73750237863848e-06, "loss": 0.2343, "step": 6621 }, { "epoch": 0.1933092013078001, "grad_norm": 0.3486175835132599, "learning_rate": 9.737339438385936e-06, "loss": 0.2621, "step": 6622 }, { "epoch": 0.19333839327417096, "grad_norm": 0.3680081367492676, "learning_rate": 9.737176448942219e-06, "loss": 0.2797, "step": 6623 }, { "epoch": 0.1933675852405418, "grad_norm": 0.46625596284866333, "learning_rate": 9.737013410309017e-06, "loss": 0.2348, "step": 6624 }, { "epoch": 0.19339677720691265, "grad_norm": 0.40844041109085083, "learning_rate": 9.736850322488025e-06, "loss": 0.2275, "step": 6625 }, { "epoch": 0.1934259691732835, "grad_norm": 0.37825533747673035, "learning_rate": 9.736687185480938e-06, "loss": 0.2191, "step": 6626 }, { "epoch": 0.19345516113965436, "grad_norm": 0.3789046108722687, "learning_rate": 9.736523999289447e-06, "loss": 0.2436, "step": 6627 }, { "epoch": 0.19348435310602521, "grad_norm": 0.340822696685791, "learning_rate": 9.736360763915248e-06, "loss": 0.2312, "step": 6628 }, { "epoch": 0.19351354507239607, "grad_norm": 0.3530195951461792, "learning_rate": 9.736197479360038e-06, "loss": 0.195, "step": 6629 }, { "epoch": 0.19354273703876693, "grad_norm": 0.4120710790157318, "learning_rate": 9.736034145625509e-06, "loss": 0.2396, "step": 6630 }, { "epoch": 0.19357192900513778, "grad_norm": 0.46490561962127686, "learning_rate": 9.735870762713357e-06, "loss": 0.3071, "step": 6631 }, { "epoch": 0.19360112097150864, "grad_norm": 0.3435313403606415, "learning_rate": 9.735707330625282e-06, "loss": 0.2345, "step": 6632 }, { "epoch": 0.1936303129378795, "grad_norm": 0.41821378469467163, "learning_rate": 9.735543849362979e-06, "loss": 0.2729, "step": 6633 }, { "epoch": 0.19365950490425035, "grad_norm": 0.3436386287212372, "learning_rate": 9.735380318928146e-06, "loss": 0.2234, "step": 6634 }, { "epoch": 0.1936886968706212, "grad_norm": 0.3838374614715576, "learning_rate": 9.73521673932248e-06, "loss": 0.2889, "step": 6635 }, { "epoch": 0.19371788883699206, "grad_norm": 0.41550007462501526, "learning_rate": 9.735053110547679e-06, "loss": 0.2578, "step": 6636 }, { "epoch": 0.19374708080336292, "grad_norm": 0.397140234708786, "learning_rate": 9.734889432605443e-06, "loss": 0.2414, "step": 6637 }, { "epoch": 0.19377627276973378, "grad_norm": 0.4308267831802368, "learning_rate": 9.734725705497474e-06, "loss": 0.2499, "step": 6638 }, { "epoch": 0.19380546473610463, "grad_norm": 0.35174593329429626, "learning_rate": 9.734561929225469e-06, "loss": 0.2656, "step": 6639 }, { "epoch": 0.1938346567024755, "grad_norm": 0.37854376435279846, "learning_rate": 9.734398103791129e-06, "loss": 0.3045, "step": 6640 }, { "epoch": 0.19386384866884634, "grad_norm": 0.3718471825122833, "learning_rate": 9.734234229196155e-06, "loss": 0.277, "step": 6641 }, { "epoch": 0.1938930406352172, "grad_norm": 0.38365352153778076, "learning_rate": 9.734070305442251e-06, "loss": 0.2762, "step": 6642 }, { "epoch": 0.19392223260158803, "grad_norm": 0.3600471019744873, "learning_rate": 9.733906332531117e-06, "loss": 0.2838, "step": 6643 }, { "epoch": 0.19395142456795889, "grad_norm": 0.41696879267692566, "learning_rate": 9.733742310464456e-06, "loss": 0.2561, "step": 6644 }, { "epoch": 0.19398061653432974, "grad_norm": 0.3857124149799347, "learning_rate": 9.73357823924397e-06, "loss": 0.2843, "step": 6645 }, { "epoch": 0.1940098085007006, "grad_norm": 0.3895578384399414, "learning_rate": 9.733414118871364e-06, "loss": 0.2224, "step": 6646 }, { "epoch": 0.19403900046707145, "grad_norm": 0.376846581697464, "learning_rate": 9.733249949348345e-06, "loss": 0.2415, "step": 6647 }, { "epoch": 0.1940681924334423, "grad_norm": 0.31197628378868103, "learning_rate": 9.733085730676611e-06, "loss": 0.2254, "step": 6648 }, { "epoch": 0.19409738439981317, "grad_norm": 0.4329550266265869, "learning_rate": 9.732921462857875e-06, "loss": 0.2192, "step": 6649 }, { "epoch": 0.19412657636618402, "grad_norm": 0.4034329354763031, "learning_rate": 9.732757145893834e-06, "loss": 0.2555, "step": 6650 }, { "epoch": 0.19415576833255488, "grad_norm": 0.5417038798332214, "learning_rate": 9.7325927797862e-06, "loss": 0.288, "step": 6651 }, { "epoch": 0.19418496029892574, "grad_norm": 0.41804346442222595, "learning_rate": 9.732428364536682e-06, "loss": 0.2619, "step": 6652 }, { "epoch": 0.1942141522652966, "grad_norm": 0.4126884639263153, "learning_rate": 9.73226390014698e-06, "loss": 0.2007, "step": 6653 }, { "epoch": 0.19424334423166745, "grad_norm": 0.4155741035938263, "learning_rate": 9.732099386618807e-06, "loss": 0.2597, "step": 6654 }, { "epoch": 0.1942725361980383, "grad_norm": 0.36583876609802246, "learning_rate": 9.73193482395387e-06, "loss": 0.2464, "step": 6655 }, { "epoch": 0.19430172816440916, "grad_norm": 0.4565148949623108, "learning_rate": 9.73177021215388e-06, "loss": 0.2652, "step": 6656 }, { "epoch": 0.19433092013078002, "grad_norm": 0.44895365834236145, "learning_rate": 9.73160555122054e-06, "loss": 0.2321, "step": 6657 }, { "epoch": 0.19436011209715087, "grad_norm": 0.3672676086425781, "learning_rate": 9.731440841155566e-06, "loss": 0.2479, "step": 6658 }, { "epoch": 0.19438930406352173, "grad_norm": 0.3828488886356354, "learning_rate": 9.731276081960665e-06, "loss": 0.2489, "step": 6659 }, { "epoch": 0.19441849602989258, "grad_norm": 0.4521454870700836, "learning_rate": 9.731111273637549e-06, "loss": 0.2785, "step": 6660 }, { "epoch": 0.19444768799626344, "grad_norm": 0.3973206579685211, "learning_rate": 9.73094641618793e-06, "loss": 0.2981, "step": 6661 }, { "epoch": 0.19447687996263427, "grad_norm": 0.39552298188209534, "learning_rate": 9.730781509613518e-06, "loss": 0.2417, "step": 6662 }, { "epoch": 0.19450607192900513, "grad_norm": 0.46150392293930054, "learning_rate": 9.730616553916025e-06, "loss": 0.25, "step": 6663 }, { "epoch": 0.19453526389537598, "grad_norm": 0.40779849886894226, "learning_rate": 9.730451549097169e-06, "loss": 0.2395, "step": 6664 }, { "epoch": 0.19456445586174684, "grad_norm": 0.3536681830883026, "learning_rate": 9.730286495158657e-06, "loss": 0.2495, "step": 6665 }, { "epoch": 0.1945936478281177, "grad_norm": 0.3848932981491089, "learning_rate": 9.730121392102205e-06, "loss": 0.2277, "step": 6666 }, { "epoch": 0.19462283979448855, "grad_norm": 0.35379287600517273, "learning_rate": 9.729956239929529e-06, "loss": 0.2394, "step": 6667 }, { "epoch": 0.1946520317608594, "grad_norm": 0.45767298340797424, "learning_rate": 9.729791038642343e-06, "loss": 0.2961, "step": 6668 }, { "epoch": 0.19468122372723026, "grad_norm": 0.45081114768981934, "learning_rate": 9.72962578824236e-06, "loss": 0.3019, "step": 6669 }, { "epoch": 0.19471041569360112, "grad_norm": 0.3959459066390991, "learning_rate": 9.7294604887313e-06, "loss": 0.2637, "step": 6670 }, { "epoch": 0.19473960765997197, "grad_norm": 0.4320027530193329, "learning_rate": 9.729295140110876e-06, "loss": 0.2524, "step": 6671 }, { "epoch": 0.19476879962634283, "grad_norm": 0.49291807413101196, "learning_rate": 9.729129742382808e-06, "loss": 0.2697, "step": 6672 }, { "epoch": 0.1947979915927137, "grad_norm": 0.4157429337501526, "learning_rate": 9.72896429554881e-06, "loss": 0.2904, "step": 6673 }, { "epoch": 0.19482718355908454, "grad_norm": 0.44958755373954773, "learning_rate": 9.728798799610602e-06, "loss": 0.2673, "step": 6674 }, { "epoch": 0.1948563755254554, "grad_norm": 0.3967241048812866, "learning_rate": 9.728633254569903e-06, "loss": 0.2485, "step": 6675 }, { "epoch": 0.19488556749182626, "grad_norm": 0.6423739790916443, "learning_rate": 9.728467660428431e-06, "loss": 0.253, "step": 6676 }, { "epoch": 0.1949147594581971, "grad_norm": 0.3985019326210022, "learning_rate": 9.728302017187908e-06, "loss": 0.2433, "step": 6677 }, { "epoch": 0.19494395142456797, "grad_norm": 0.47295263409614563, "learning_rate": 9.728136324850049e-06, "loss": 0.2642, "step": 6678 }, { "epoch": 0.19497314339093882, "grad_norm": 0.4300834834575653, "learning_rate": 9.727970583416575e-06, "loss": 0.2378, "step": 6679 }, { "epoch": 0.19500233535730968, "grad_norm": 0.37922924757003784, "learning_rate": 9.727804792889213e-06, "loss": 0.2407, "step": 6680 }, { "epoch": 0.19503152732368054, "grad_norm": 0.37275004386901855, "learning_rate": 9.72763895326968e-06, "loss": 0.2892, "step": 6681 }, { "epoch": 0.19506071929005137, "grad_norm": 0.5690059661865234, "learning_rate": 9.727473064559698e-06, "loss": 0.2391, "step": 6682 }, { "epoch": 0.19508991125642222, "grad_norm": 0.4270382523536682, "learning_rate": 9.72730712676099e-06, "loss": 0.2907, "step": 6683 }, { "epoch": 0.19511910322279308, "grad_norm": 0.40409788489341736, "learning_rate": 9.72714113987528e-06, "loss": 0.2782, "step": 6684 }, { "epoch": 0.19514829518916393, "grad_norm": 0.35763201117515564, "learning_rate": 9.72697510390429e-06, "loss": 0.211, "step": 6685 }, { "epoch": 0.1951774871555348, "grad_norm": 0.4424523115158081, "learning_rate": 9.726809018849745e-06, "loss": 0.2714, "step": 6686 }, { "epoch": 0.19520667912190565, "grad_norm": 0.4385976493358612, "learning_rate": 9.726642884713371e-06, "loss": 0.25, "step": 6687 }, { "epoch": 0.1952358710882765, "grad_norm": 0.4129277169704437, "learning_rate": 9.726476701496892e-06, "loss": 0.2772, "step": 6688 }, { "epoch": 0.19526506305464736, "grad_norm": 0.44510969519615173, "learning_rate": 9.72631046920203e-06, "loss": 0.1851, "step": 6689 }, { "epoch": 0.19529425502101821, "grad_norm": 0.35384634137153625, "learning_rate": 9.726144187830517e-06, "loss": 0.2542, "step": 6690 }, { "epoch": 0.19532344698738907, "grad_norm": 0.4841039478778839, "learning_rate": 9.725977857384076e-06, "loss": 0.282, "step": 6691 }, { "epoch": 0.19535263895375993, "grad_norm": 0.4006151556968689, "learning_rate": 9.725811477864435e-06, "loss": 0.2789, "step": 6692 }, { "epoch": 0.19538183092013078, "grad_norm": 0.35865968465805054, "learning_rate": 9.725645049273323e-06, "loss": 0.217, "step": 6693 }, { "epoch": 0.19541102288650164, "grad_norm": 0.3643456995487213, "learning_rate": 9.725478571612465e-06, "loss": 0.2577, "step": 6694 }, { "epoch": 0.1954402148528725, "grad_norm": 0.6231946349143982, "learning_rate": 9.725312044883593e-06, "loss": 0.2562, "step": 6695 }, { "epoch": 0.19546940681924335, "grad_norm": 0.327852725982666, "learning_rate": 9.725145469088433e-06, "loss": 0.2573, "step": 6696 }, { "epoch": 0.1954985987856142, "grad_norm": 0.418057918548584, "learning_rate": 9.724978844228717e-06, "loss": 0.2578, "step": 6697 }, { "epoch": 0.19552779075198506, "grad_norm": 0.39408618211746216, "learning_rate": 9.724812170306176e-06, "loss": 0.289, "step": 6698 }, { "epoch": 0.19555698271835592, "grad_norm": 0.447650283575058, "learning_rate": 9.724645447322538e-06, "loss": 0.2409, "step": 6699 }, { "epoch": 0.19558617468472678, "grad_norm": 0.32722365856170654, "learning_rate": 9.724478675279536e-06, "loss": 0.2191, "step": 6700 }, { "epoch": 0.1956153666510976, "grad_norm": 0.39238813519477844, "learning_rate": 9.724311854178901e-06, "loss": 0.2591, "step": 6701 }, { "epoch": 0.19564455861746846, "grad_norm": 0.3594982624053955, "learning_rate": 9.724144984022364e-06, "loss": 0.2511, "step": 6702 }, { "epoch": 0.19567375058383932, "grad_norm": 0.3676995635032654, "learning_rate": 9.72397806481166e-06, "loss": 0.269, "step": 6703 }, { "epoch": 0.19570294255021017, "grad_norm": 0.32418110966682434, "learning_rate": 9.72381109654852e-06, "loss": 0.2397, "step": 6704 }, { "epoch": 0.19573213451658103, "grad_norm": 0.3596475422382355, "learning_rate": 9.723644079234682e-06, "loss": 0.2224, "step": 6705 }, { "epoch": 0.1957613264829519, "grad_norm": 0.35606715083122253, "learning_rate": 9.723477012871877e-06, "loss": 0.2904, "step": 6706 }, { "epoch": 0.19579051844932274, "grad_norm": 0.45276758074760437, "learning_rate": 9.723309897461838e-06, "loss": 0.2472, "step": 6707 }, { "epoch": 0.1958197104156936, "grad_norm": 0.35376694798469543, "learning_rate": 9.723142733006304e-06, "loss": 0.2259, "step": 6708 }, { "epoch": 0.19584890238206445, "grad_norm": 0.3833131790161133, "learning_rate": 9.722975519507009e-06, "loss": 0.2364, "step": 6709 }, { "epoch": 0.1958780943484353, "grad_norm": 0.37559887766838074, "learning_rate": 9.722808256965688e-06, "loss": 0.2465, "step": 6710 }, { "epoch": 0.19590728631480617, "grad_norm": 0.3628079295158386, "learning_rate": 9.72264094538408e-06, "loss": 0.3, "step": 6711 }, { "epoch": 0.19593647828117702, "grad_norm": 0.3741379380226135, "learning_rate": 9.722473584763923e-06, "loss": 0.2785, "step": 6712 }, { "epoch": 0.19596567024754788, "grad_norm": 0.3371981084346771, "learning_rate": 9.722306175106953e-06, "loss": 0.2339, "step": 6713 }, { "epoch": 0.19599486221391874, "grad_norm": 0.41842493414878845, "learning_rate": 9.722138716414909e-06, "loss": 0.247, "step": 6714 }, { "epoch": 0.1960240541802896, "grad_norm": 0.40699368715286255, "learning_rate": 9.721971208689526e-06, "loss": 0.2837, "step": 6715 }, { "epoch": 0.19605324614666045, "grad_norm": 0.35375064611434937, "learning_rate": 9.72180365193255e-06, "loss": 0.249, "step": 6716 }, { "epoch": 0.1960824381130313, "grad_norm": 0.46114811301231384, "learning_rate": 9.72163604614572e-06, "loss": 0.249, "step": 6717 }, { "epoch": 0.19611163007940216, "grad_norm": 0.3991622030735016, "learning_rate": 9.72146839133077e-06, "loss": 0.3348, "step": 6718 }, { "epoch": 0.19614082204577302, "grad_norm": 0.3734075725078583, "learning_rate": 9.721300687489448e-06, "loss": 0.2872, "step": 6719 }, { "epoch": 0.19617001401214385, "grad_norm": 0.3958618938922882, "learning_rate": 9.721132934623491e-06, "loss": 0.276, "step": 6720 }, { "epoch": 0.1961992059785147, "grad_norm": 0.3454136848449707, "learning_rate": 9.720965132734643e-06, "loss": 0.2603, "step": 6721 }, { "epoch": 0.19622839794488556, "grad_norm": 0.4518577456474304, "learning_rate": 9.720797281824645e-06, "loss": 0.281, "step": 6722 }, { "epoch": 0.1962575899112564, "grad_norm": 0.4643746018409729, "learning_rate": 9.72062938189524e-06, "loss": 0.2771, "step": 6723 }, { "epoch": 0.19628678187762727, "grad_norm": 0.40293261408805847, "learning_rate": 9.720461432948175e-06, "loss": 0.2349, "step": 6724 }, { "epoch": 0.19631597384399813, "grad_norm": 0.31149229407310486, "learning_rate": 9.72029343498519e-06, "loss": 0.1933, "step": 6725 }, { "epoch": 0.19634516581036898, "grad_norm": 0.3862058222293854, "learning_rate": 9.72012538800803e-06, "loss": 0.242, "step": 6726 }, { "epoch": 0.19637435777673984, "grad_norm": 0.44518211483955383, "learning_rate": 9.71995729201844e-06, "loss": 0.2691, "step": 6727 }, { "epoch": 0.1964035497431107, "grad_norm": 0.41414815187454224, "learning_rate": 9.719789147018167e-06, "loss": 0.2557, "step": 6728 }, { "epoch": 0.19643274170948155, "grad_norm": 0.39014390110969543, "learning_rate": 9.719620953008953e-06, "loss": 0.2829, "step": 6729 }, { "epoch": 0.1964619336758524, "grad_norm": 0.40046536922454834, "learning_rate": 9.71945270999255e-06, "loss": 0.2345, "step": 6730 }, { "epoch": 0.19649112564222326, "grad_norm": 0.48448193073272705, "learning_rate": 9.719284417970703e-06, "loss": 0.2641, "step": 6731 }, { "epoch": 0.19652031760859412, "grad_norm": 0.39351072907447815, "learning_rate": 9.719116076945156e-06, "loss": 0.2322, "step": 6732 }, { "epoch": 0.19654950957496498, "grad_norm": 0.3671741783618927, "learning_rate": 9.718947686917662e-06, "loss": 0.2098, "step": 6733 }, { "epoch": 0.19657870154133583, "grad_norm": 0.37622085213661194, "learning_rate": 9.718779247889967e-06, "loss": 0.2302, "step": 6734 }, { "epoch": 0.1966078935077067, "grad_norm": 0.45839181542396545, "learning_rate": 9.71861075986382e-06, "loss": 0.2781, "step": 6735 }, { "epoch": 0.19663708547407754, "grad_norm": 0.3659852147102356, "learning_rate": 9.718442222840972e-06, "loss": 0.2766, "step": 6736 }, { "epoch": 0.1966662774404484, "grad_norm": 0.5470106601715088, "learning_rate": 9.71827363682317e-06, "loss": 0.2698, "step": 6737 }, { "epoch": 0.19669546940681926, "grad_norm": 0.4005920886993408, "learning_rate": 9.718105001812167e-06, "loss": 0.2661, "step": 6738 }, { "epoch": 0.19672466137319009, "grad_norm": 0.6070814728736877, "learning_rate": 9.717936317809714e-06, "loss": 0.2371, "step": 6739 }, { "epoch": 0.19675385333956094, "grad_norm": 0.36075183749198914, "learning_rate": 9.717767584817561e-06, "loss": 0.2742, "step": 6740 }, { "epoch": 0.1967830453059318, "grad_norm": 0.38365596532821655, "learning_rate": 9.717598802837463e-06, "loss": 0.2814, "step": 6741 }, { "epoch": 0.19681223727230265, "grad_norm": 0.38293465971946716, "learning_rate": 9.71742997187117e-06, "loss": 0.2054, "step": 6742 }, { "epoch": 0.1968414292386735, "grad_norm": 0.39285942912101746, "learning_rate": 9.717261091920437e-06, "loss": 0.2658, "step": 6743 }, { "epoch": 0.19687062120504437, "grad_norm": 0.41219764947891235, "learning_rate": 9.717092162987013e-06, "loss": 0.255, "step": 6744 }, { "epoch": 0.19689981317141522, "grad_norm": 0.36823728680610657, "learning_rate": 9.71692318507266e-06, "loss": 0.2792, "step": 6745 }, { "epoch": 0.19692900513778608, "grad_norm": 0.3653411865234375, "learning_rate": 9.716754158179126e-06, "loss": 0.2334, "step": 6746 }, { "epoch": 0.19695819710415693, "grad_norm": 0.45180633664131165, "learning_rate": 9.716585082308167e-06, "loss": 0.2581, "step": 6747 }, { "epoch": 0.1969873890705278, "grad_norm": 0.3476479947566986, "learning_rate": 9.716415957461542e-06, "loss": 0.194, "step": 6748 }, { "epoch": 0.19701658103689865, "grad_norm": 0.37045344710350037, "learning_rate": 9.716246783641006e-06, "loss": 0.2432, "step": 6749 }, { "epoch": 0.1970457730032695, "grad_norm": 0.3751957416534424, "learning_rate": 9.716077560848311e-06, "loss": 0.258, "step": 6750 }, { "epoch": 0.19707496496964036, "grad_norm": 0.3705456852912903, "learning_rate": 9.715908289085221e-06, "loss": 0.2914, "step": 6751 }, { "epoch": 0.19710415693601122, "grad_norm": 0.4246443212032318, "learning_rate": 9.71573896835349e-06, "loss": 0.254, "step": 6752 }, { "epoch": 0.19713334890238207, "grad_norm": 0.37521421909332275, "learning_rate": 9.715569598654877e-06, "loss": 0.2308, "step": 6753 }, { "epoch": 0.19716254086875293, "grad_norm": 0.7017475962638855, "learning_rate": 9.715400179991139e-06, "loss": 0.2379, "step": 6754 }, { "epoch": 0.19719173283512378, "grad_norm": 0.45307672023773193, "learning_rate": 9.715230712364038e-06, "loss": 0.2994, "step": 6755 }, { "epoch": 0.19722092480149464, "grad_norm": 0.47320014238357544, "learning_rate": 9.715061195775333e-06, "loss": 0.3014, "step": 6756 }, { "epoch": 0.1972501167678655, "grad_norm": 0.45110124349594116, "learning_rate": 9.714891630226781e-06, "loss": 0.2986, "step": 6757 }, { "epoch": 0.19727930873423632, "grad_norm": 0.3624534606933594, "learning_rate": 9.714722015720148e-06, "loss": 0.2522, "step": 6758 }, { "epoch": 0.19730850070060718, "grad_norm": 0.493364155292511, "learning_rate": 9.714552352257191e-06, "loss": 0.2505, "step": 6759 }, { "epoch": 0.19733769266697804, "grad_norm": 0.34831732511520386, "learning_rate": 9.714382639839673e-06, "loss": 0.2727, "step": 6760 }, { "epoch": 0.1973668846333489, "grad_norm": 0.32199305295944214, "learning_rate": 9.714212878469357e-06, "loss": 0.2301, "step": 6761 }, { "epoch": 0.19739607659971975, "grad_norm": 0.36059942841529846, "learning_rate": 9.714043068148005e-06, "loss": 0.2639, "step": 6762 }, { "epoch": 0.1974252685660906, "grad_norm": 0.3783547580242157, "learning_rate": 9.713873208877381e-06, "loss": 0.2613, "step": 6763 }, { "epoch": 0.19745446053246146, "grad_norm": 0.3389143645763397, "learning_rate": 9.713703300659249e-06, "loss": 0.2667, "step": 6764 }, { "epoch": 0.19748365249883232, "grad_norm": 0.3514691889286041, "learning_rate": 9.713533343495372e-06, "loss": 0.2558, "step": 6765 }, { "epoch": 0.19751284446520317, "grad_norm": 0.37210363149642944, "learning_rate": 9.713363337387514e-06, "loss": 0.284, "step": 6766 }, { "epoch": 0.19754203643157403, "grad_norm": 0.3479747772216797, "learning_rate": 9.713193282337443e-06, "loss": 0.2857, "step": 6767 }, { "epoch": 0.1975712283979449, "grad_norm": 0.3165397644042969, "learning_rate": 9.713023178346924e-06, "loss": 0.2144, "step": 6768 }, { "epoch": 0.19760042036431574, "grad_norm": 0.3660036027431488, "learning_rate": 9.712853025417722e-06, "loss": 0.2207, "step": 6769 }, { "epoch": 0.1976296123306866, "grad_norm": 0.37609630823135376, "learning_rate": 9.712682823551602e-06, "loss": 0.2608, "step": 6770 }, { "epoch": 0.19765880429705746, "grad_norm": 0.33138447999954224, "learning_rate": 9.712512572750337e-06, "loss": 0.2325, "step": 6771 }, { "epoch": 0.1976879962634283, "grad_norm": 0.3483498692512512, "learning_rate": 9.712342273015692e-06, "loss": 0.2014, "step": 6772 }, { "epoch": 0.19771718822979917, "grad_norm": 0.35905298590660095, "learning_rate": 9.712171924349433e-06, "loss": 0.2771, "step": 6773 }, { "epoch": 0.19774638019617002, "grad_norm": 0.35354506969451904, "learning_rate": 9.712001526753333e-06, "loss": 0.264, "step": 6774 }, { "epoch": 0.19777557216254088, "grad_norm": 0.3419366478919983, "learning_rate": 9.711831080229157e-06, "loss": 0.2274, "step": 6775 }, { "epoch": 0.19780476412891174, "grad_norm": 0.3091903328895569, "learning_rate": 9.711660584778678e-06, "loss": 0.1786, "step": 6776 }, { "epoch": 0.19783395609528256, "grad_norm": 0.3489105999469757, "learning_rate": 9.711490040403666e-06, "loss": 0.2448, "step": 6777 }, { "epoch": 0.19786314806165342, "grad_norm": 0.3475589156150818, "learning_rate": 9.71131944710589e-06, "loss": 0.2816, "step": 6778 }, { "epoch": 0.19789234002802428, "grad_norm": 0.45189258456230164, "learning_rate": 9.711148804887124e-06, "loss": 0.2348, "step": 6779 }, { "epoch": 0.19792153199439513, "grad_norm": 0.3437902331352234, "learning_rate": 9.710978113749141e-06, "loss": 0.2311, "step": 6780 }, { "epoch": 0.197950723960766, "grad_norm": 0.36258095502853394, "learning_rate": 9.710807373693709e-06, "loss": 0.2085, "step": 6781 }, { "epoch": 0.19797991592713685, "grad_norm": 0.3392387926578522, "learning_rate": 9.710636584722602e-06, "loss": 0.2951, "step": 6782 }, { "epoch": 0.1980091078935077, "grad_norm": 0.36025479435920715, "learning_rate": 9.710465746837597e-06, "loss": 0.2587, "step": 6783 }, { "epoch": 0.19803829985987856, "grad_norm": 0.3786512017250061, "learning_rate": 9.710294860040462e-06, "loss": 0.267, "step": 6784 }, { "epoch": 0.19806749182624941, "grad_norm": 0.348065048456192, "learning_rate": 9.710123924332978e-06, "loss": 0.2883, "step": 6785 }, { "epoch": 0.19809668379262027, "grad_norm": 0.3316531777381897, "learning_rate": 9.709952939716914e-06, "loss": 0.2053, "step": 6786 }, { "epoch": 0.19812587575899113, "grad_norm": 0.4058777987957001, "learning_rate": 9.70978190619405e-06, "loss": 0.195, "step": 6787 }, { "epoch": 0.19815506772536198, "grad_norm": 0.3331693708896637, "learning_rate": 9.70961082376616e-06, "loss": 0.2669, "step": 6788 }, { "epoch": 0.19818425969173284, "grad_norm": 0.3773692846298218, "learning_rate": 9.70943969243502e-06, "loss": 0.2648, "step": 6789 }, { "epoch": 0.1982134516581037, "grad_norm": 0.34482094645500183, "learning_rate": 9.709268512202408e-06, "loss": 0.2667, "step": 6790 }, { "epoch": 0.19824264362447455, "grad_norm": 0.4492971897125244, "learning_rate": 9.709097283070102e-06, "loss": 0.2579, "step": 6791 }, { "epoch": 0.1982718355908454, "grad_norm": 0.4163256287574768, "learning_rate": 9.708926005039879e-06, "loss": 0.2609, "step": 6792 }, { "epoch": 0.19830102755721626, "grad_norm": 0.377993643283844, "learning_rate": 9.708754678113515e-06, "loss": 0.2611, "step": 6793 }, { "epoch": 0.19833021952358712, "grad_norm": 0.44332316517829895, "learning_rate": 9.708583302292793e-06, "loss": 0.2733, "step": 6794 }, { "epoch": 0.19835941148995798, "grad_norm": 0.4276373088359833, "learning_rate": 9.708411877579493e-06, "loss": 0.2735, "step": 6795 }, { "epoch": 0.1983886034563288, "grad_norm": 0.3678727149963379, "learning_rate": 9.70824040397539e-06, "loss": 0.2379, "step": 6796 }, { "epoch": 0.19841779542269966, "grad_norm": 0.41394585371017456, "learning_rate": 9.70806888148227e-06, "loss": 0.2349, "step": 6797 }, { "epoch": 0.19844698738907052, "grad_norm": 0.3351174294948578, "learning_rate": 9.707897310101912e-06, "loss": 0.2558, "step": 6798 }, { "epoch": 0.19847617935544137, "grad_norm": 0.3543277382850647, "learning_rate": 9.707725689836097e-06, "loss": 0.2464, "step": 6799 }, { "epoch": 0.19850537132181223, "grad_norm": 0.36736956238746643, "learning_rate": 9.707554020686607e-06, "loss": 0.2828, "step": 6800 }, { "epoch": 0.19853456328818309, "grad_norm": 0.34369561076164246, "learning_rate": 9.707382302655225e-06, "loss": 0.2089, "step": 6801 }, { "epoch": 0.19856375525455394, "grad_norm": 0.3342786133289337, "learning_rate": 9.707210535743735e-06, "loss": 0.2243, "step": 6802 }, { "epoch": 0.1985929472209248, "grad_norm": 0.36285194754600525, "learning_rate": 9.707038719953917e-06, "loss": 0.2263, "step": 6803 }, { "epoch": 0.19862213918729565, "grad_norm": 0.35266461968421936, "learning_rate": 9.70686685528756e-06, "loss": 0.1899, "step": 6804 }, { "epoch": 0.1986513311536665, "grad_norm": 0.37920287251472473, "learning_rate": 9.706694941746443e-06, "loss": 0.2616, "step": 6805 }, { "epoch": 0.19868052312003737, "grad_norm": 0.3371821343898773, "learning_rate": 9.706522979332358e-06, "loss": 0.1968, "step": 6806 }, { "epoch": 0.19870971508640822, "grad_norm": 0.44703876972198486, "learning_rate": 9.706350968047087e-06, "loss": 0.2453, "step": 6807 }, { "epoch": 0.19873890705277908, "grad_norm": 0.3868524730205536, "learning_rate": 9.706178907892414e-06, "loss": 0.1877, "step": 6808 }, { "epoch": 0.19876809901914994, "grad_norm": 0.3833818733692169, "learning_rate": 9.706006798870128e-06, "loss": 0.2613, "step": 6809 }, { "epoch": 0.1987972909855208, "grad_norm": 0.4154384136199951, "learning_rate": 9.705834640982016e-06, "loss": 0.2781, "step": 6810 }, { "epoch": 0.19882648295189165, "grad_norm": 0.35258379578590393, "learning_rate": 9.705662434229865e-06, "loss": 0.249, "step": 6811 }, { "epoch": 0.1988556749182625, "grad_norm": 0.36521637439727783, "learning_rate": 9.705490178615464e-06, "loss": 0.2369, "step": 6812 }, { "epoch": 0.19888486688463336, "grad_norm": 0.44394221901893616, "learning_rate": 9.705317874140604e-06, "loss": 0.2713, "step": 6813 }, { "epoch": 0.19891405885100422, "grad_norm": 0.43366357684135437, "learning_rate": 9.705145520807067e-06, "loss": 0.2526, "step": 6814 }, { "epoch": 0.19894325081737504, "grad_norm": 0.3551023602485657, "learning_rate": 9.70497311861665e-06, "loss": 0.2289, "step": 6815 }, { "epoch": 0.1989724427837459, "grad_norm": 0.35851922631263733, "learning_rate": 9.704800667571139e-06, "loss": 0.1916, "step": 6816 }, { "epoch": 0.19900163475011676, "grad_norm": 0.3852291703224182, "learning_rate": 9.704628167672325e-06, "loss": 0.2147, "step": 6817 }, { "epoch": 0.1990308267164876, "grad_norm": 0.3315938115119934, "learning_rate": 9.704455618922001e-06, "loss": 0.2422, "step": 6818 }, { "epoch": 0.19906001868285847, "grad_norm": 0.3568069636821747, "learning_rate": 9.704283021321959e-06, "loss": 0.2296, "step": 6819 }, { "epoch": 0.19908921064922933, "grad_norm": 0.37285661697387695, "learning_rate": 9.70411037487399e-06, "loss": 0.2459, "step": 6820 }, { "epoch": 0.19911840261560018, "grad_norm": 0.5269218683242798, "learning_rate": 9.703937679579885e-06, "loss": 0.2322, "step": 6821 }, { "epoch": 0.19914759458197104, "grad_norm": 0.4598013460636139, "learning_rate": 9.70376493544144e-06, "loss": 0.3119, "step": 6822 }, { "epoch": 0.1991767865483419, "grad_norm": 0.3033618628978729, "learning_rate": 9.703592142460446e-06, "loss": 0.2146, "step": 6823 }, { "epoch": 0.19920597851471275, "grad_norm": 0.6951395273208618, "learning_rate": 9.703419300638703e-06, "loss": 0.2621, "step": 6824 }, { "epoch": 0.1992351704810836, "grad_norm": 1.0809723138809204, "learning_rate": 9.703246409977998e-06, "loss": 0.2549, "step": 6825 }, { "epoch": 0.19926436244745446, "grad_norm": 0.4253847002983093, "learning_rate": 9.70307347048013e-06, "loss": 0.2841, "step": 6826 }, { "epoch": 0.19929355441382532, "grad_norm": 0.5267060399055481, "learning_rate": 9.702900482146898e-06, "loss": 0.2895, "step": 6827 }, { "epoch": 0.19932274638019618, "grad_norm": 0.38508644700050354, "learning_rate": 9.702727444980092e-06, "loss": 0.2444, "step": 6828 }, { "epoch": 0.19935193834656703, "grad_norm": 0.34454214572906494, "learning_rate": 9.702554358981513e-06, "loss": 0.2275, "step": 6829 }, { "epoch": 0.1993811303129379, "grad_norm": 0.3152579367160797, "learning_rate": 9.702381224152955e-06, "loss": 0.2494, "step": 6830 }, { "epoch": 0.19941032227930874, "grad_norm": 0.3242945075035095, "learning_rate": 9.702208040496219e-06, "loss": 0.2627, "step": 6831 }, { "epoch": 0.1994395142456796, "grad_norm": 0.3923026919364929, "learning_rate": 9.702034808013103e-06, "loss": 0.2633, "step": 6832 }, { "epoch": 0.19946870621205046, "grad_norm": 0.66987144947052, "learning_rate": 9.701861526705403e-06, "loss": 0.239, "step": 6833 }, { "epoch": 0.19949789817842128, "grad_norm": 0.31626421213150024, "learning_rate": 9.701688196574922e-06, "loss": 0.2126, "step": 6834 }, { "epoch": 0.19952709014479214, "grad_norm": 0.33894985914230347, "learning_rate": 9.701514817623457e-06, "loss": 0.2521, "step": 6835 }, { "epoch": 0.199556282111163, "grad_norm": 0.33238485455513, "learning_rate": 9.70134138985281e-06, "loss": 0.2487, "step": 6836 }, { "epoch": 0.19958547407753385, "grad_norm": 0.3668294847011566, "learning_rate": 9.70116791326478e-06, "loss": 0.2527, "step": 6837 }, { "epoch": 0.1996146660439047, "grad_norm": 0.35593822598457336, "learning_rate": 9.700994387861168e-06, "loss": 0.2548, "step": 6838 }, { "epoch": 0.19964385801027557, "grad_norm": 0.36628881096839905, "learning_rate": 9.700820813643781e-06, "loss": 0.3004, "step": 6839 }, { "epoch": 0.19967304997664642, "grad_norm": 0.3404565453529358, "learning_rate": 9.700647190614416e-06, "loss": 0.2507, "step": 6840 }, { "epoch": 0.19970224194301728, "grad_norm": 0.3470979928970337, "learning_rate": 9.700473518774875e-06, "loss": 0.2156, "step": 6841 }, { "epoch": 0.19973143390938813, "grad_norm": 0.32180047035217285, "learning_rate": 9.700299798126966e-06, "loss": 0.2064, "step": 6842 }, { "epoch": 0.199760625875759, "grad_norm": 0.3139914572238922, "learning_rate": 9.700126028672492e-06, "loss": 0.2265, "step": 6843 }, { "epoch": 0.19978981784212985, "grad_norm": 0.3410169780254364, "learning_rate": 9.699952210413254e-06, "loss": 0.2433, "step": 6844 }, { "epoch": 0.1998190098085007, "grad_norm": 0.3222774863243103, "learning_rate": 9.69977834335106e-06, "loss": 0.2384, "step": 6845 }, { "epoch": 0.19984820177487156, "grad_norm": 0.35577157139778137, "learning_rate": 9.699604427487715e-06, "loss": 0.2387, "step": 6846 }, { "epoch": 0.19987739374124242, "grad_norm": 0.32854536175727844, "learning_rate": 9.69943046282502e-06, "loss": 0.2233, "step": 6847 }, { "epoch": 0.19990658570761327, "grad_norm": 0.4072129726409912, "learning_rate": 9.69925644936479e-06, "loss": 0.2364, "step": 6848 }, { "epoch": 0.19993577767398413, "grad_norm": 0.3019082546234131, "learning_rate": 9.699082387108827e-06, "loss": 0.2432, "step": 6849 }, { "epoch": 0.19996496964035498, "grad_norm": 0.38383135199546814, "learning_rate": 9.698908276058939e-06, "loss": 0.2521, "step": 6850 }, { "epoch": 0.19999416160672584, "grad_norm": 0.39246776700019836, "learning_rate": 9.698734116216932e-06, "loss": 0.2689, "step": 6851 }, { "epoch": 0.2000233535730967, "grad_norm": 0.3240610957145691, "learning_rate": 9.698559907584617e-06, "loss": 0.2287, "step": 6852 }, { "epoch": 0.20005254553946755, "grad_norm": 0.3965640068054199, "learning_rate": 9.698385650163802e-06, "loss": 0.2348, "step": 6853 }, { "epoch": 0.20008173750583838, "grad_norm": 0.31439387798309326, "learning_rate": 9.698211343956298e-06, "loss": 0.2362, "step": 6854 }, { "epoch": 0.20011092947220924, "grad_norm": 0.3635161221027374, "learning_rate": 9.698036988963912e-06, "loss": 0.2649, "step": 6855 }, { "epoch": 0.2001401214385801, "grad_norm": 0.3717177212238312, "learning_rate": 9.697862585188458e-06, "loss": 0.3043, "step": 6856 }, { "epoch": 0.20016931340495095, "grad_norm": 0.33361777663230896, "learning_rate": 9.697688132631743e-06, "loss": 0.2541, "step": 6857 }, { "epoch": 0.2001985053713218, "grad_norm": 0.344620943069458, "learning_rate": 9.69751363129558e-06, "loss": 0.2976, "step": 6858 }, { "epoch": 0.20022769733769266, "grad_norm": 0.3731277883052826, "learning_rate": 9.697339081181785e-06, "loss": 0.2808, "step": 6859 }, { "epoch": 0.20025688930406352, "grad_norm": 0.3786296546459198, "learning_rate": 9.697164482292163e-06, "loss": 0.2201, "step": 6860 }, { "epoch": 0.20028608127043437, "grad_norm": 0.3853732943534851, "learning_rate": 9.696989834628533e-06, "loss": 0.2797, "step": 6861 }, { "epoch": 0.20031527323680523, "grad_norm": 0.3373364210128784, "learning_rate": 9.696815138192705e-06, "loss": 0.2651, "step": 6862 }, { "epoch": 0.2003444652031761, "grad_norm": 0.3629675805568695, "learning_rate": 9.696640392986497e-06, "loss": 0.2659, "step": 6863 }, { "epoch": 0.20037365716954694, "grad_norm": 0.3459867537021637, "learning_rate": 9.69646559901172e-06, "loss": 0.2574, "step": 6864 }, { "epoch": 0.2004028491359178, "grad_norm": 0.37812331318855286, "learning_rate": 9.696290756270189e-06, "loss": 0.2557, "step": 6865 }, { "epoch": 0.20043204110228865, "grad_norm": 0.4069576859474182, "learning_rate": 9.69611586476372e-06, "loss": 0.2715, "step": 6866 }, { "epoch": 0.2004612330686595, "grad_norm": 0.36391550302505493, "learning_rate": 9.69594092449413e-06, "loss": 0.1961, "step": 6867 }, { "epoch": 0.20049042503503037, "grad_norm": 0.5749496221542358, "learning_rate": 9.695765935463233e-06, "loss": 0.2212, "step": 6868 }, { "epoch": 0.20051961700140122, "grad_norm": 0.39281728863716125, "learning_rate": 9.695590897672851e-06, "loss": 0.2224, "step": 6869 }, { "epoch": 0.20054880896777208, "grad_norm": 0.3336028456687927, "learning_rate": 9.695415811124798e-06, "loss": 0.2088, "step": 6870 }, { "epoch": 0.20057800093414294, "grad_norm": 0.39003947377204895, "learning_rate": 9.695240675820891e-06, "loss": 0.2436, "step": 6871 }, { "epoch": 0.2006071929005138, "grad_norm": 0.3253677487373352, "learning_rate": 9.695065491762952e-06, "loss": 0.2043, "step": 6872 }, { "epoch": 0.20063638486688462, "grad_norm": 0.36328133940696716, "learning_rate": 9.694890258952797e-06, "loss": 0.2233, "step": 6873 }, { "epoch": 0.20066557683325548, "grad_norm": 0.41779521107673645, "learning_rate": 9.694714977392248e-06, "loss": 0.2299, "step": 6874 }, { "epoch": 0.20069476879962633, "grad_norm": 0.38373178243637085, "learning_rate": 9.694539647083124e-06, "loss": 0.2595, "step": 6875 }, { "epoch": 0.2007239607659972, "grad_norm": 0.3266247808933258, "learning_rate": 9.694364268027243e-06, "loss": 0.199, "step": 6876 }, { "epoch": 0.20075315273236805, "grad_norm": 0.6158602833747864, "learning_rate": 9.694188840226431e-06, "loss": 0.2345, "step": 6877 }, { "epoch": 0.2007823446987389, "grad_norm": 0.3809558153152466, "learning_rate": 9.694013363682506e-06, "loss": 0.2474, "step": 6878 }, { "epoch": 0.20081153666510976, "grad_norm": 0.36630716919898987, "learning_rate": 9.69383783839729e-06, "loss": 0.2546, "step": 6879 }, { "epoch": 0.20084072863148061, "grad_norm": 0.5120422840118408, "learning_rate": 9.69366226437261e-06, "loss": 0.2638, "step": 6880 }, { "epoch": 0.20086992059785147, "grad_norm": 0.3904069662094116, "learning_rate": 9.693486641610283e-06, "loss": 0.2353, "step": 6881 }, { "epoch": 0.20089911256422233, "grad_norm": 0.37853148579597473, "learning_rate": 9.693310970112137e-06, "loss": 0.2428, "step": 6882 }, { "epoch": 0.20092830453059318, "grad_norm": 0.3670777380466461, "learning_rate": 9.693135249879994e-06, "loss": 0.2487, "step": 6883 }, { "epoch": 0.20095749649696404, "grad_norm": 0.3339903950691223, "learning_rate": 9.69295948091568e-06, "loss": 0.2472, "step": 6884 }, { "epoch": 0.2009866884633349, "grad_norm": 0.35998648405075073, "learning_rate": 9.69278366322102e-06, "loss": 0.2268, "step": 6885 }, { "epoch": 0.20101588042970575, "grad_norm": 0.3580496609210968, "learning_rate": 9.692607796797837e-06, "loss": 0.273, "step": 6886 }, { "epoch": 0.2010450723960766, "grad_norm": 0.36573541164398193, "learning_rate": 9.692431881647962e-06, "loss": 0.2393, "step": 6887 }, { "epoch": 0.20107426436244746, "grad_norm": 0.3421266973018646, "learning_rate": 9.692255917773216e-06, "loss": 0.2343, "step": 6888 }, { "epoch": 0.20110345632881832, "grad_norm": 0.4117218255996704, "learning_rate": 9.69207990517543e-06, "loss": 0.2221, "step": 6889 }, { "epoch": 0.20113264829518918, "grad_norm": 0.35912641882896423, "learning_rate": 9.691903843856432e-06, "loss": 0.2476, "step": 6890 }, { "epoch": 0.20116184026156003, "grad_norm": 0.34891974925994873, "learning_rate": 9.691727733818047e-06, "loss": 0.2702, "step": 6891 }, { "epoch": 0.20119103222793086, "grad_norm": 0.37673112750053406, "learning_rate": 9.691551575062106e-06, "loss": 0.266, "step": 6892 }, { "epoch": 0.20122022419430172, "grad_norm": 0.38344481587409973, "learning_rate": 9.691375367590439e-06, "loss": 0.3038, "step": 6893 }, { "epoch": 0.20124941616067257, "grad_norm": 0.32992926239967346, "learning_rate": 9.691199111404874e-06, "loss": 0.2254, "step": 6894 }, { "epoch": 0.20127860812704343, "grad_norm": 0.4159269332885742, "learning_rate": 9.69102280650724e-06, "loss": 0.255, "step": 6895 }, { "epoch": 0.20130780009341429, "grad_norm": 0.33064785599708557, "learning_rate": 9.69084645289937e-06, "loss": 0.2491, "step": 6896 }, { "epoch": 0.20133699205978514, "grad_norm": 0.3800034821033478, "learning_rate": 9.690670050583095e-06, "loss": 0.2625, "step": 6897 }, { "epoch": 0.201366184026156, "grad_norm": 0.3358978033065796, "learning_rate": 9.690493599560246e-06, "loss": 0.2856, "step": 6898 }, { "epoch": 0.20139537599252685, "grad_norm": 0.3160296082496643, "learning_rate": 9.690317099832656e-06, "loss": 0.2424, "step": 6899 }, { "epoch": 0.2014245679588977, "grad_norm": 0.346665620803833, "learning_rate": 9.690140551402157e-06, "loss": 0.2055, "step": 6900 }, { "epoch": 0.20145375992526857, "grad_norm": 0.36722227931022644, "learning_rate": 9.689963954270582e-06, "loss": 0.2387, "step": 6901 }, { "epoch": 0.20148295189163942, "grad_norm": 0.3779531717300415, "learning_rate": 9.689787308439766e-06, "loss": 0.2789, "step": 6902 }, { "epoch": 0.20151214385801028, "grad_norm": 0.33899828791618347, "learning_rate": 9.68961061391154e-06, "loss": 0.2188, "step": 6903 }, { "epoch": 0.20154133582438113, "grad_norm": 0.3511110544204712, "learning_rate": 9.689433870687743e-06, "loss": 0.2573, "step": 6904 }, { "epoch": 0.201570527790752, "grad_norm": 0.35436591506004333, "learning_rate": 9.68925707877021e-06, "loss": 0.2586, "step": 6905 }, { "epoch": 0.20159971975712285, "grad_norm": 0.3436535596847534, "learning_rate": 9.689080238160773e-06, "loss": 0.2128, "step": 6906 }, { "epoch": 0.2016289117234937, "grad_norm": 0.3295525014400482, "learning_rate": 9.68890334886127e-06, "loss": 0.2416, "step": 6907 }, { "epoch": 0.20165810368986456, "grad_norm": 0.3739350736141205, "learning_rate": 9.688726410873538e-06, "loss": 0.2552, "step": 6908 }, { "epoch": 0.20168729565623542, "grad_norm": 0.2968701422214508, "learning_rate": 9.688549424199415e-06, "loss": 0.2127, "step": 6909 }, { "epoch": 0.20171648762260627, "grad_norm": 0.36693182587623596, "learning_rate": 9.688372388840739e-06, "loss": 0.2364, "step": 6910 }, { "epoch": 0.2017456795889771, "grad_norm": 0.3560112416744232, "learning_rate": 9.688195304799346e-06, "loss": 0.2117, "step": 6911 }, { "epoch": 0.20177487155534796, "grad_norm": 0.47875410318374634, "learning_rate": 9.688018172077078e-06, "loss": 0.2837, "step": 6912 }, { "epoch": 0.2018040635217188, "grad_norm": 0.3763631582260132, "learning_rate": 9.687840990675771e-06, "loss": 0.3082, "step": 6913 }, { "epoch": 0.20183325548808967, "grad_norm": 0.38996708393096924, "learning_rate": 9.687663760597268e-06, "loss": 0.3359, "step": 6914 }, { "epoch": 0.20186244745446053, "grad_norm": 0.33067160844802856, "learning_rate": 9.687486481843406e-06, "loss": 0.263, "step": 6915 }, { "epoch": 0.20189163942083138, "grad_norm": 0.6546348929405212, "learning_rate": 9.687309154416028e-06, "loss": 0.2559, "step": 6916 }, { "epoch": 0.20192083138720224, "grad_norm": 0.4084334671497345, "learning_rate": 9.687131778316975e-06, "loss": 0.2613, "step": 6917 }, { "epoch": 0.2019500233535731, "grad_norm": 0.44434255361557007, "learning_rate": 9.686954353548088e-06, "loss": 0.2511, "step": 6918 }, { "epoch": 0.20197921531994395, "grad_norm": 0.3123241066932678, "learning_rate": 9.686776880111211e-06, "loss": 0.2406, "step": 6919 }, { "epoch": 0.2020084072863148, "grad_norm": 0.338510662317276, "learning_rate": 9.686599358008186e-06, "loss": 0.2428, "step": 6920 }, { "epoch": 0.20203759925268566, "grad_norm": 0.30029740929603577, "learning_rate": 9.686421787240854e-06, "loss": 0.2381, "step": 6921 }, { "epoch": 0.20206679121905652, "grad_norm": 0.31509506702423096, "learning_rate": 9.686244167811063e-06, "loss": 0.2539, "step": 6922 }, { "epoch": 0.20209598318542737, "grad_norm": 0.35330110788345337, "learning_rate": 9.686066499720654e-06, "loss": 0.236, "step": 6923 }, { "epoch": 0.20212517515179823, "grad_norm": 0.3656529188156128, "learning_rate": 9.685888782971475e-06, "loss": 0.2203, "step": 6924 }, { "epoch": 0.2021543671181691, "grad_norm": 0.33587270975112915, "learning_rate": 9.685711017565369e-06, "loss": 0.2178, "step": 6925 }, { "epoch": 0.20218355908453994, "grad_norm": 0.38972944021224976, "learning_rate": 9.685533203504181e-06, "loss": 0.2279, "step": 6926 }, { "epoch": 0.2022127510509108, "grad_norm": 0.3680919110774994, "learning_rate": 9.68535534078976e-06, "loss": 0.2254, "step": 6927 }, { "epoch": 0.20224194301728166, "grad_norm": 0.3138231635093689, "learning_rate": 9.685177429423951e-06, "loss": 0.262, "step": 6928 }, { "epoch": 0.2022711349836525, "grad_norm": 0.3301776051521301, "learning_rate": 9.684999469408602e-06, "loss": 0.2593, "step": 6929 }, { "epoch": 0.20230032695002334, "grad_norm": 0.3724166452884674, "learning_rate": 9.684821460745562e-06, "loss": 0.2964, "step": 6930 }, { "epoch": 0.2023295189163942, "grad_norm": 0.36892062425613403, "learning_rate": 9.684643403436678e-06, "loss": 0.2898, "step": 6931 }, { "epoch": 0.20235871088276505, "grad_norm": 0.33374395966529846, "learning_rate": 9.684465297483798e-06, "loss": 0.2254, "step": 6932 }, { "epoch": 0.2023879028491359, "grad_norm": 0.36570119857788086, "learning_rate": 9.684287142888774e-06, "loss": 0.289, "step": 6933 }, { "epoch": 0.20241709481550677, "grad_norm": 0.36353862285614014, "learning_rate": 9.684108939653453e-06, "loss": 0.2578, "step": 6934 }, { "epoch": 0.20244628678187762, "grad_norm": 0.37081941962242126, "learning_rate": 9.683930687779689e-06, "loss": 0.2503, "step": 6935 }, { "epoch": 0.20247547874824848, "grad_norm": 0.360828161239624, "learning_rate": 9.683752387269329e-06, "loss": 0.2874, "step": 6936 }, { "epoch": 0.20250467071461933, "grad_norm": 0.31745514273643494, "learning_rate": 9.683574038124227e-06, "loss": 0.229, "step": 6937 }, { "epoch": 0.2025338626809902, "grad_norm": 0.30940499901771545, "learning_rate": 9.683395640346233e-06, "loss": 0.2205, "step": 6938 }, { "epoch": 0.20256305464736105, "grad_norm": 0.3855888843536377, "learning_rate": 9.683217193937203e-06, "loss": 0.24, "step": 6939 }, { "epoch": 0.2025922466137319, "grad_norm": 0.36410391330718994, "learning_rate": 9.683038698898985e-06, "loss": 0.2335, "step": 6940 }, { "epoch": 0.20262143858010276, "grad_norm": 0.29841849207878113, "learning_rate": 9.682860155233435e-06, "loss": 0.2061, "step": 6941 }, { "epoch": 0.20265063054647361, "grad_norm": 0.4586760997772217, "learning_rate": 9.68268156294241e-06, "loss": 0.2868, "step": 6942 }, { "epoch": 0.20267982251284447, "grad_norm": 0.33630773425102234, "learning_rate": 9.682502922027758e-06, "loss": 0.291, "step": 6943 }, { "epoch": 0.20270901447921533, "grad_norm": 0.36889520287513733, "learning_rate": 9.68232423249134e-06, "loss": 0.255, "step": 6944 }, { "epoch": 0.20273820644558618, "grad_norm": 0.3560740351676941, "learning_rate": 9.682145494335008e-06, "loss": 0.3157, "step": 6945 }, { "epoch": 0.20276739841195704, "grad_norm": 0.41297057271003723, "learning_rate": 9.681966707560617e-06, "loss": 0.2566, "step": 6946 }, { "epoch": 0.2027965903783279, "grad_norm": 0.43335044384002686, "learning_rate": 9.681787872170026e-06, "loss": 0.2403, "step": 6947 }, { "epoch": 0.20282578234469875, "grad_norm": 0.3801306486129761, "learning_rate": 9.681608988165092e-06, "loss": 0.2499, "step": 6948 }, { "epoch": 0.20285497431106958, "grad_norm": 0.3743300437927246, "learning_rate": 9.68143005554767e-06, "loss": 0.2519, "step": 6949 }, { "epoch": 0.20288416627744044, "grad_norm": 0.5632094144821167, "learning_rate": 9.681251074319624e-06, "loss": 0.2653, "step": 6950 }, { "epoch": 0.2029133582438113, "grad_norm": 0.33362144231796265, "learning_rate": 9.681072044482804e-06, "loss": 0.2332, "step": 6951 }, { "epoch": 0.20294255021018215, "grad_norm": 0.32805249094963074, "learning_rate": 9.680892966039075e-06, "loss": 0.2292, "step": 6952 }, { "epoch": 0.202971742176553, "grad_norm": 0.5466203093528748, "learning_rate": 9.680713838990294e-06, "loss": 0.2246, "step": 6953 }, { "epoch": 0.20300093414292386, "grad_norm": 0.3463086783885956, "learning_rate": 9.680534663338323e-06, "loss": 0.2603, "step": 6954 }, { "epoch": 0.20303012610929472, "grad_norm": 0.35256513953208923, "learning_rate": 9.680355439085019e-06, "loss": 0.2728, "step": 6955 }, { "epoch": 0.20305931807566557, "grad_norm": 0.4052296578884125, "learning_rate": 9.680176166232247e-06, "loss": 0.2885, "step": 6956 }, { "epoch": 0.20308851004203643, "grad_norm": 0.3888484835624695, "learning_rate": 9.679996844781865e-06, "loss": 0.2791, "step": 6957 }, { "epoch": 0.20311770200840729, "grad_norm": 0.3830011785030365, "learning_rate": 9.679817474735738e-06, "loss": 0.2086, "step": 6958 }, { "epoch": 0.20314689397477814, "grad_norm": 0.39414042234420776, "learning_rate": 9.679638056095728e-06, "loss": 0.2981, "step": 6959 }, { "epoch": 0.203176085941149, "grad_norm": 0.36645519733428955, "learning_rate": 9.679458588863694e-06, "loss": 0.2661, "step": 6960 }, { "epoch": 0.20320527790751985, "grad_norm": 0.41413018107414246, "learning_rate": 9.679279073041506e-06, "loss": 0.2904, "step": 6961 }, { "epoch": 0.2032344698738907, "grad_norm": 0.4142140746116638, "learning_rate": 9.679099508631024e-06, "loss": 0.2166, "step": 6962 }, { "epoch": 0.20326366184026157, "grad_norm": 0.38683316111564636, "learning_rate": 9.678919895634114e-06, "loss": 0.2827, "step": 6963 }, { "epoch": 0.20329285380663242, "grad_norm": 0.3604408800601959, "learning_rate": 9.678740234052639e-06, "loss": 0.2403, "step": 6964 }, { "epoch": 0.20332204577300328, "grad_norm": 0.4181203544139862, "learning_rate": 9.678560523888466e-06, "loss": 0.2602, "step": 6965 }, { "epoch": 0.20335123773937414, "grad_norm": 0.344711035490036, "learning_rate": 9.678380765143463e-06, "loss": 0.2424, "step": 6966 }, { "epoch": 0.203380429705745, "grad_norm": 0.3473672568798065, "learning_rate": 9.678200957819493e-06, "loss": 0.229, "step": 6967 }, { "epoch": 0.20340962167211582, "grad_norm": 0.3474368453025818, "learning_rate": 9.678021101918425e-06, "loss": 0.2237, "step": 6968 }, { "epoch": 0.20343881363848668, "grad_norm": 0.35906559228897095, "learning_rate": 9.677841197442128e-06, "loss": 0.2417, "step": 6969 }, { "epoch": 0.20346800560485753, "grad_norm": 0.5663869380950928, "learning_rate": 9.677661244392467e-06, "loss": 0.317, "step": 6970 }, { "epoch": 0.2034971975712284, "grad_norm": 0.4771016240119934, "learning_rate": 9.677481242771311e-06, "loss": 0.1903, "step": 6971 }, { "epoch": 0.20352638953759924, "grad_norm": 0.35377809405326843, "learning_rate": 9.67730119258053e-06, "loss": 0.2497, "step": 6972 }, { "epoch": 0.2035555815039701, "grad_norm": 0.29056158661842346, "learning_rate": 9.677121093821996e-06, "loss": 0.211, "step": 6973 }, { "epoch": 0.20358477347034096, "grad_norm": 0.4072232246398926, "learning_rate": 9.676940946497573e-06, "loss": 0.273, "step": 6974 }, { "epoch": 0.2036139654367118, "grad_norm": 0.35895103216171265, "learning_rate": 9.676760750609138e-06, "loss": 0.2484, "step": 6975 }, { "epoch": 0.20364315740308267, "grad_norm": 0.3478968143463135, "learning_rate": 9.67658050615856e-06, "loss": 0.2221, "step": 6976 }, { "epoch": 0.20367234936945353, "grad_norm": 0.3724886476993561, "learning_rate": 9.676400213147707e-06, "loss": 0.31, "step": 6977 }, { "epoch": 0.20370154133582438, "grad_norm": 0.5881481170654297, "learning_rate": 9.676219871578457e-06, "loss": 0.2719, "step": 6978 }, { "epoch": 0.20373073330219524, "grad_norm": 0.3330943286418915, "learning_rate": 9.676039481452679e-06, "loss": 0.2412, "step": 6979 }, { "epoch": 0.2037599252685661, "grad_norm": 0.40267035365104675, "learning_rate": 9.675859042772246e-06, "loss": 0.2383, "step": 6980 }, { "epoch": 0.20378911723493695, "grad_norm": 0.3703726530075073, "learning_rate": 9.675678555539035e-06, "loss": 0.2345, "step": 6981 }, { "epoch": 0.2038183092013078, "grad_norm": 0.40715301036834717, "learning_rate": 9.675498019754914e-06, "loss": 0.2739, "step": 6982 }, { "epoch": 0.20384750116767866, "grad_norm": 0.4335385262966156, "learning_rate": 9.675317435421762e-06, "loss": 0.2463, "step": 6983 }, { "epoch": 0.20387669313404952, "grad_norm": 0.33211028575897217, "learning_rate": 9.675136802541456e-06, "loss": 0.2236, "step": 6984 }, { "epoch": 0.20390588510042038, "grad_norm": 0.38250744342803955, "learning_rate": 9.674956121115867e-06, "loss": 0.2548, "step": 6985 }, { "epoch": 0.20393507706679123, "grad_norm": 0.3585374355316162, "learning_rate": 9.674775391146873e-06, "loss": 0.2251, "step": 6986 }, { "epoch": 0.20396426903316206, "grad_norm": 0.35884419083595276, "learning_rate": 9.674594612636351e-06, "loss": 0.2611, "step": 6987 }, { "epoch": 0.20399346099953292, "grad_norm": 0.3874155580997467, "learning_rate": 9.67441378558618e-06, "loss": 0.2365, "step": 6988 }, { "epoch": 0.20402265296590377, "grad_norm": 0.33172592520713806, "learning_rate": 9.674232909998233e-06, "loss": 0.2337, "step": 6989 }, { "epoch": 0.20405184493227463, "grad_norm": 0.3779711127281189, "learning_rate": 9.67405198587439e-06, "loss": 0.2488, "step": 6990 }, { "epoch": 0.20408103689864548, "grad_norm": 0.3868961036205292, "learning_rate": 9.673871013216534e-06, "loss": 0.254, "step": 6991 }, { "epoch": 0.20411022886501634, "grad_norm": 0.3408436179161072, "learning_rate": 9.673689992026538e-06, "loss": 0.2244, "step": 6992 }, { "epoch": 0.2041394208313872, "grad_norm": 0.3614867329597473, "learning_rate": 9.673508922306285e-06, "loss": 0.2529, "step": 6993 }, { "epoch": 0.20416861279775805, "grad_norm": 0.37210550904273987, "learning_rate": 9.673327804057653e-06, "loss": 0.257, "step": 6994 }, { "epoch": 0.2041978047641289, "grad_norm": 0.36795616149902344, "learning_rate": 9.673146637282527e-06, "loss": 0.2617, "step": 6995 }, { "epoch": 0.20422699673049977, "grad_norm": 0.3723100423812866, "learning_rate": 9.672965421982783e-06, "loss": 0.2782, "step": 6996 }, { "epoch": 0.20425618869687062, "grad_norm": 0.3319961130619049, "learning_rate": 9.672784158160307e-06, "loss": 0.2153, "step": 6997 }, { "epoch": 0.20428538066324148, "grad_norm": 0.3721180558204651, "learning_rate": 9.672602845816977e-06, "loss": 0.2848, "step": 6998 }, { "epoch": 0.20431457262961233, "grad_norm": 0.3722114861011505, "learning_rate": 9.67242148495468e-06, "loss": 0.1922, "step": 6999 }, { "epoch": 0.2043437645959832, "grad_norm": 1.699088454246521, "learning_rate": 9.672240075575295e-06, "loss": 0.2813, "step": 7000 }, { "epoch": 0.20437295656235405, "grad_norm": 0.3816893398761749, "learning_rate": 9.672058617680708e-06, "loss": 0.2562, "step": 7001 }, { "epoch": 0.2044021485287249, "grad_norm": 0.5941359996795654, "learning_rate": 9.671877111272804e-06, "loss": 0.2259, "step": 7002 }, { "epoch": 0.20443134049509576, "grad_norm": 0.40129339694976807, "learning_rate": 9.671695556353468e-06, "loss": 0.2577, "step": 7003 }, { "epoch": 0.20446053246146662, "grad_norm": 0.3946828246116638, "learning_rate": 9.671513952924582e-06, "loss": 0.2283, "step": 7004 }, { "epoch": 0.20448972442783747, "grad_norm": 0.3334875702857971, "learning_rate": 9.671332300988034e-06, "loss": 0.2463, "step": 7005 }, { "epoch": 0.20451891639420833, "grad_norm": 0.36036303639411926, "learning_rate": 9.67115060054571e-06, "loss": 0.2145, "step": 7006 }, { "epoch": 0.20454810836057916, "grad_norm": 0.374296635389328, "learning_rate": 9.670968851599497e-06, "loss": 0.2163, "step": 7007 }, { "epoch": 0.20457730032695, "grad_norm": 0.45117083191871643, "learning_rate": 9.670787054151282e-06, "loss": 0.2364, "step": 7008 }, { "epoch": 0.20460649229332087, "grad_norm": 0.3256058692932129, "learning_rate": 9.670605208202952e-06, "loss": 0.2207, "step": 7009 }, { "epoch": 0.20463568425969172, "grad_norm": 0.3540988862514496, "learning_rate": 9.670423313756395e-06, "loss": 0.2422, "step": 7010 }, { "epoch": 0.20466487622606258, "grad_norm": 0.36635032296180725, "learning_rate": 9.670241370813502e-06, "loss": 0.2456, "step": 7011 }, { "epoch": 0.20469406819243344, "grad_norm": 0.38071855902671814, "learning_rate": 9.67005937937616e-06, "loss": 0.237, "step": 7012 }, { "epoch": 0.2047232601588043, "grad_norm": 0.5206364393234253, "learning_rate": 9.669877339446259e-06, "loss": 0.2884, "step": 7013 }, { "epoch": 0.20475245212517515, "grad_norm": 0.440512478351593, "learning_rate": 9.669695251025691e-06, "loss": 0.2584, "step": 7014 }, { "epoch": 0.204781644091546, "grad_norm": 0.3552367687225342, "learning_rate": 9.669513114116344e-06, "loss": 0.214, "step": 7015 }, { "epoch": 0.20481083605791686, "grad_norm": 0.3445724844932556, "learning_rate": 9.669330928720113e-06, "loss": 0.2581, "step": 7016 }, { "epoch": 0.20484002802428772, "grad_norm": 0.3217979967594147, "learning_rate": 9.669148694838885e-06, "loss": 0.2217, "step": 7017 }, { "epoch": 0.20486921999065857, "grad_norm": 0.3708525598049164, "learning_rate": 9.668966412474556e-06, "loss": 0.249, "step": 7018 }, { "epoch": 0.20489841195702943, "grad_norm": 0.3986947536468506, "learning_rate": 9.668784081629018e-06, "loss": 0.2838, "step": 7019 }, { "epoch": 0.2049276039234003, "grad_norm": 0.3314889371395111, "learning_rate": 9.668601702304163e-06, "loss": 0.2516, "step": 7020 }, { "epoch": 0.20495679588977114, "grad_norm": 0.31672927737236023, "learning_rate": 9.668419274501888e-06, "loss": 0.2364, "step": 7021 }, { "epoch": 0.204985987856142, "grad_norm": 0.3598286509513855, "learning_rate": 9.668236798224082e-06, "loss": 0.2302, "step": 7022 }, { "epoch": 0.20501517982251286, "grad_norm": 0.35539671778678894, "learning_rate": 9.668054273472645e-06, "loss": 0.2606, "step": 7023 }, { "epoch": 0.2050443717888837, "grad_norm": 0.3441159725189209, "learning_rate": 9.667871700249468e-06, "loss": 0.2004, "step": 7024 }, { "epoch": 0.20507356375525457, "grad_norm": 0.3945101499557495, "learning_rate": 9.66768907855645e-06, "loss": 0.2765, "step": 7025 }, { "epoch": 0.2051027557216254, "grad_norm": 0.35073256492614746, "learning_rate": 9.667506408395484e-06, "loss": 0.2363, "step": 7026 }, { "epoch": 0.20513194768799625, "grad_norm": 0.3139561116695404, "learning_rate": 9.667323689768471e-06, "loss": 0.2231, "step": 7027 }, { "epoch": 0.2051611396543671, "grad_norm": 0.37422680854797363, "learning_rate": 9.667140922677305e-06, "loss": 0.2608, "step": 7028 }, { "epoch": 0.20519033162073796, "grad_norm": 0.3385443687438965, "learning_rate": 9.666958107123887e-06, "loss": 0.2492, "step": 7029 }, { "epoch": 0.20521952358710882, "grad_norm": 0.3820025324821472, "learning_rate": 9.666775243110111e-06, "loss": 0.2325, "step": 7030 }, { "epoch": 0.20524871555347968, "grad_norm": 0.32775431871414185, "learning_rate": 9.66659233063788e-06, "loss": 0.2231, "step": 7031 }, { "epoch": 0.20527790751985053, "grad_norm": 0.3840872347354889, "learning_rate": 9.66640936970909e-06, "loss": 0.2619, "step": 7032 }, { "epoch": 0.2053070994862214, "grad_norm": 1.4560126066207886, "learning_rate": 9.66622636032564e-06, "loss": 0.2175, "step": 7033 }, { "epoch": 0.20533629145259225, "grad_norm": 0.31613585352897644, "learning_rate": 9.666043302489436e-06, "loss": 0.1898, "step": 7034 }, { "epoch": 0.2053654834189631, "grad_norm": 0.3349343240261078, "learning_rate": 9.665860196202374e-06, "loss": 0.2456, "step": 7035 }, { "epoch": 0.20539467538533396, "grad_norm": 0.33362168073654175, "learning_rate": 9.665677041466357e-06, "loss": 0.2374, "step": 7036 }, { "epoch": 0.20542386735170481, "grad_norm": 0.30044829845428467, "learning_rate": 9.665493838283287e-06, "loss": 0.2015, "step": 7037 }, { "epoch": 0.20545305931807567, "grad_norm": 0.355880469083786, "learning_rate": 9.665310586655063e-06, "loss": 0.2374, "step": 7038 }, { "epoch": 0.20548225128444653, "grad_norm": 0.31401878595352173, "learning_rate": 9.665127286583593e-06, "loss": 0.2222, "step": 7039 }, { "epoch": 0.20551144325081738, "grad_norm": 0.431937575340271, "learning_rate": 9.664943938070778e-06, "loss": 0.2726, "step": 7040 }, { "epoch": 0.20554063521718824, "grad_norm": 0.3682416081428528, "learning_rate": 9.664760541118521e-06, "loss": 0.2409, "step": 7041 }, { "epoch": 0.2055698271835591, "grad_norm": 0.35229218006134033, "learning_rate": 9.664577095728727e-06, "loss": 0.2151, "step": 7042 }, { "epoch": 0.20559901914992995, "grad_norm": 0.3018306791782379, "learning_rate": 9.6643936019033e-06, "loss": 0.2286, "step": 7043 }, { "epoch": 0.2056282111163008, "grad_norm": 0.39121901988983154, "learning_rate": 9.66421005964415e-06, "loss": 0.252, "step": 7044 }, { "epoch": 0.20565740308267164, "grad_norm": 0.3784930408000946, "learning_rate": 9.664026468953176e-06, "loss": 0.2166, "step": 7045 }, { "epoch": 0.2056865950490425, "grad_norm": 0.3641083836555481, "learning_rate": 9.66384282983229e-06, "loss": 0.2328, "step": 7046 }, { "epoch": 0.20571578701541335, "grad_norm": 0.36779388785362244, "learning_rate": 9.663659142283395e-06, "loss": 0.2368, "step": 7047 }, { "epoch": 0.2057449789817842, "grad_norm": 0.4926815927028656, "learning_rate": 9.6634754063084e-06, "loss": 0.2658, "step": 7048 }, { "epoch": 0.20577417094815506, "grad_norm": 0.47209635376930237, "learning_rate": 9.663291621909211e-06, "loss": 0.2335, "step": 7049 }, { "epoch": 0.20580336291452592, "grad_norm": 0.4040999114513397, "learning_rate": 9.66310778908774e-06, "loss": 0.2845, "step": 7050 }, { "epoch": 0.20583255488089677, "grad_norm": 0.3756648898124695, "learning_rate": 9.662923907845894e-06, "loss": 0.3439, "step": 7051 }, { "epoch": 0.20586174684726763, "grad_norm": 0.3309776782989502, "learning_rate": 9.66273997818558e-06, "loss": 0.2133, "step": 7052 }, { "epoch": 0.20589093881363849, "grad_norm": 0.38580217957496643, "learning_rate": 9.66255600010871e-06, "loss": 0.2625, "step": 7053 }, { "epoch": 0.20592013078000934, "grad_norm": 0.3703549802303314, "learning_rate": 9.662371973617198e-06, "loss": 0.2524, "step": 7054 }, { "epoch": 0.2059493227463802, "grad_norm": 0.3193339705467224, "learning_rate": 9.66218789871295e-06, "loss": 0.2017, "step": 7055 }, { "epoch": 0.20597851471275105, "grad_norm": 0.3944259583950043, "learning_rate": 9.662003775397877e-06, "loss": 0.3079, "step": 7056 }, { "epoch": 0.2060077066791219, "grad_norm": 0.38991186022758484, "learning_rate": 9.661819603673895e-06, "loss": 0.2827, "step": 7057 }, { "epoch": 0.20603689864549277, "grad_norm": 0.31820982694625854, "learning_rate": 9.661635383542912e-06, "loss": 0.2265, "step": 7058 }, { "epoch": 0.20606609061186362, "grad_norm": 0.3487234115600586, "learning_rate": 9.661451115006842e-06, "loss": 0.2493, "step": 7059 }, { "epoch": 0.20609528257823448, "grad_norm": 0.3428126275539398, "learning_rate": 9.661266798067601e-06, "loss": 0.2192, "step": 7060 }, { "epoch": 0.20612447454460534, "grad_norm": 0.3788500130176544, "learning_rate": 9.661082432727102e-06, "loss": 0.2643, "step": 7061 }, { "epoch": 0.2061536665109762, "grad_norm": 0.4512960612773895, "learning_rate": 9.660898018987257e-06, "loss": 0.2745, "step": 7062 }, { "epoch": 0.20618285847734705, "grad_norm": 0.3709007501602173, "learning_rate": 9.660713556849982e-06, "loss": 0.2573, "step": 7063 }, { "epoch": 0.20621205044371788, "grad_norm": 0.3555487394332886, "learning_rate": 9.660529046317194e-06, "loss": 0.2523, "step": 7064 }, { "epoch": 0.20624124241008873, "grad_norm": 0.35444900393486023, "learning_rate": 9.660344487390808e-06, "loss": 0.2054, "step": 7065 }, { "epoch": 0.2062704343764596, "grad_norm": 0.3673021197319031, "learning_rate": 9.660159880072739e-06, "loss": 0.2223, "step": 7066 }, { "epoch": 0.20629962634283044, "grad_norm": 0.36271026730537415, "learning_rate": 9.659975224364907e-06, "loss": 0.2484, "step": 7067 }, { "epoch": 0.2063288183092013, "grad_norm": 0.5780568718910217, "learning_rate": 9.659790520269225e-06, "loss": 0.2636, "step": 7068 }, { "epoch": 0.20635801027557216, "grad_norm": 0.33544015884399414, "learning_rate": 9.659605767787616e-06, "loss": 0.2125, "step": 7069 }, { "epoch": 0.206387202241943, "grad_norm": 0.3435184955596924, "learning_rate": 9.659420966921995e-06, "loss": 0.2302, "step": 7070 }, { "epoch": 0.20641639420831387, "grad_norm": 0.39188796281814575, "learning_rate": 9.65923611767428e-06, "loss": 0.2579, "step": 7071 }, { "epoch": 0.20644558617468473, "grad_norm": 0.3331761360168457, "learning_rate": 9.659051220046393e-06, "loss": 0.2445, "step": 7072 }, { "epoch": 0.20647477814105558, "grad_norm": 0.31731224060058594, "learning_rate": 9.658866274040255e-06, "loss": 0.2148, "step": 7073 }, { "epoch": 0.20650397010742644, "grad_norm": 0.42122069001197815, "learning_rate": 9.658681279657783e-06, "loss": 0.2725, "step": 7074 }, { "epoch": 0.2065331620737973, "grad_norm": 0.3536010682582855, "learning_rate": 9.6584962369009e-06, "loss": 0.2463, "step": 7075 }, { "epoch": 0.20656235404016815, "grad_norm": 0.32021886110305786, "learning_rate": 9.658311145771526e-06, "loss": 0.1964, "step": 7076 }, { "epoch": 0.206591546006539, "grad_norm": 0.4009406864643097, "learning_rate": 9.658126006271584e-06, "loss": 0.2683, "step": 7077 }, { "epoch": 0.20662073797290986, "grad_norm": 0.4588920474052429, "learning_rate": 9.657940818402997e-06, "loss": 0.2826, "step": 7078 }, { "epoch": 0.20664992993928072, "grad_norm": 0.35526159405708313, "learning_rate": 9.657755582167687e-06, "loss": 0.2782, "step": 7079 }, { "epoch": 0.20667912190565157, "grad_norm": 0.35131868720054626, "learning_rate": 9.657570297567577e-06, "loss": 0.2353, "step": 7080 }, { "epoch": 0.20670831387202243, "grad_norm": 0.3268301486968994, "learning_rate": 9.657384964604591e-06, "loss": 0.2034, "step": 7081 }, { "epoch": 0.2067375058383933, "grad_norm": 0.3665391206741333, "learning_rate": 9.657199583280655e-06, "loss": 0.2418, "step": 7082 }, { "epoch": 0.20676669780476412, "grad_norm": 0.3585248291492462, "learning_rate": 9.657014153597693e-06, "loss": 0.2616, "step": 7083 }, { "epoch": 0.20679588977113497, "grad_norm": 0.3206944167613983, "learning_rate": 9.656828675557631e-06, "loss": 0.2222, "step": 7084 }, { "epoch": 0.20682508173750583, "grad_norm": 0.35897839069366455, "learning_rate": 9.656643149162393e-06, "loss": 0.2084, "step": 7085 }, { "epoch": 0.20685427370387668, "grad_norm": 0.3112660348415375, "learning_rate": 9.656457574413908e-06, "loss": 0.2298, "step": 7086 }, { "epoch": 0.20688346567024754, "grad_norm": 0.40397119522094727, "learning_rate": 9.6562719513141e-06, "loss": 0.198, "step": 7087 }, { "epoch": 0.2069126576366184, "grad_norm": 0.37398797273635864, "learning_rate": 9.6560862798649e-06, "loss": 0.2137, "step": 7088 }, { "epoch": 0.20694184960298925, "grad_norm": 0.35360270738601685, "learning_rate": 9.655900560068234e-06, "loss": 0.2704, "step": 7089 }, { "epoch": 0.2069710415693601, "grad_norm": 0.456805020570755, "learning_rate": 9.65571479192603e-06, "loss": 0.2088, "step": 7090 }, { "epoch": 0.20700023353573097, "grad_norm": 0.41828837990760803, "learning_rate": 9.655528975440219e-06, "loss": 0.3276, "step": 7091 }, { "epoch": 0.20702942550210182, "grad_norm": 0.34237730503082275, "learning_rate": 9.655343110612726e-06, "loss": 0.2539, "step": 7092 }, { "epoch": 0.20705861746847268, "grad_norm": 0.31674468517303467, "learning_rate": 9.655157197445488e-06, "loss": 0.243, "step": 7093 }, { "epoch": 0.20708780943484353, "grad_norm": 0.35381266474723816, "learning_rate": 9.654971235940428e-06, "loss": 0.3064, "step": 7094 }, { "epoch": 0.2071170014012144, "grad_norm": 0.3523823320865631, "learning_rate": 9.654785226099484e-06, "loss": 0.2618, "step": 7095 }, { "epoch": 0.20714619336758525, "grad_norm": 0.4064989984035492, "learning_rate": 9.654599167924581e-06, "loss": 0.2709, "step": 7096 }, { "epoch": 0.2071753853339561, "grad_norm": 0.3450506329536438, "learning_rate": 9.654413061417655e-06, "loss": 0.2563, "step": 7097 }, { "epoch": 0.20720457730032696, "grad_norm": 0.40810734033584595, "learning_rate": 9.654226906580637e-06, "loss": 0.2518, "step": 7098 }, { "epoch": 0.20723376926669781, "grad_norm": 0.4858858585357666, "learning_rate": 9.654040703415462e-06, "loss": 0.2136, "step": 7099 }, { "epoch": 0.20726296123306867, "grad_norm": 0.32885584235191345, "learning_rate": 9.65385445192406e-06, "loss": 0.2234, "step": 7100 }, { "epoch": 0.20729215319943953, "grad_norm": 0.33504900336265564, "learning_rate": 9.653668152108367e-06, "loss": 0.2196, "step": 7101 }, { "epoch": 0.20732134516581036, "grad_norm": 0.33818861842155457, "learning_rate": 9.653481803970317e-06, "loss": 0.25, "step": 7102 }, { "epoch": 0.2073505371321812, "grad_norm": 0.3224240839481354, "learning_rate": 9.653295407511846e-06, "loss": 0.2335, "step": 7103 }, { "epoch": 0.20737972909855207, "grad_norm": 0.3164059817790985, "learning_rate": 9.65310896273489e-06, "loss": 0.2141, "step": 7104 }, { "epoch": 0.20740892106492292, "grad_norm": 0.3909723162651062, "learning_rate": 9.652922469641382e-06, "loss": 0.2458, "step": 7105 }, { "epoch": 0.20743811303129378, "grad_norm": 0.32763493061065674, "learning_rate": 9.652735928233262e-06, "loss": 0.2291, "step": 7106 }, { "epoch": 0.20746730499766464, "grad_norm": 0.35993653535842896, "learning_rate": 9.652549338512464e-06, "loss": 0.2843, "step": 7107 }, { "epoch": 0.2074964969640355, "grad_norm": 0.37609559297561646, "learning_rate": 9.652362700480927e-06, "loss": 0.2599, "step": 7108 }, { "epoch": 0.20752568893040635, "grad_norm": 0.292297899723053, "learning_rate": 9.652176014140588e-06, "loss": 0.1998, "step": 7109 }, { "epoch": 0.2075548808967772, "grad_norm": 0.3787758946418762, "learning_rate": 9.651989279493388e-06, "loss": 0.2717, "step": 7110 }, { "epoch": 0.20758407286314806, "grad_norm": 0.4441898763179779, "learning_rate": 9.651802496541263e-06, "loss": 0.2669, "step": 7111 }, { "epoch": 0.20761326482951892, "grad_norm": 0.34449756145477295, "learning_rate": 9.651615665286154e-06, "loss": 0.2183, "step": 7112 }, { "epoch": 0.20764245679588977, "grad_norm": 0.35602784156799316, "learning_rate": 9.65142878573e-06, "loss": 0.2324, "step": 7113 }, { "epoch": 0.20767164876226063, "grad_norm": 0.33330249786376953, "learning_rate": 9.651241857874744e-06, "loss": 0.2476, "step": 7114 }, { "epoch": 0.2077008407286315, "grad_norm": 0.35440364480018616, "learning_rate": 9.651054881722323e-06, "loss": 0.2501, "step": 7115 }, { "epoch": 0.20773003269500234, "grad_norm": 1.0094739198684692, "learning_rate": 9.650867857274683e-06, "loss": 0.2946, "step": 7116 }, { "epoch": 0.2077592246613732, "grad_norm": 0.3935985863208771, "learning_rate": 9.650680784533763e-06, "loss": 0.2655, "step": 7117 }, { "epoch": 0.20778841662774405, "grad_norm": 0.3559314012527466, "learning_rate": 9.650493663501505e-06, "loss": 0.2138, "step": 7118 }, { "epoch": 0.2078176085941149, "grad_norm": 0.3796117305755615, "learning_rate": 9.650306494179855e-06, "loss": 0.2135, "step": 7119 }, { "epoch": 0.20784680056048577, "grad_norm": 0.42051953077316284, "learning_rate": 9.650119276570755e-06, "loss": 0.2561, "step": 7120 }, { "epoch": 0.2078759925268566, "grad_norm": 0.42292845249176025, "learning_rate": 9.649932010676149e-06, "loss": 0.2315, "step": 7121 }, { "epoch": 0.20790518449322745, "grad_norm": 0.34360450506210327, "learning_rate": 9.64974469649798e-06, "loss": 0.2056, "step": 7122 }, { "epoch": 0.2079343764595983, "grad_norm": 0.369484543800354, "learning_rate": 9.649557334038196e-06, "loss": 0.2536, "step": 7123 }, { "epoch": 0.20796356842596916, "grad_norm": 0.3655523955821991, "learning_rate": 9.64936992329874e-06, "loss": 0.2931, "step": 7124 }, { "epoch": 0.20799276039234002, "grad_norm": 0.36603298783302307, "learning_rate": 9.649182464281557e-06, "loss": 0.2134, "step": 7125 }, { "epoch": 0.20802195235871088, "grad_norm": 0.6591435670852661, "learning_rate": 9.648994956988597e-06, "loss": 0.1947, "step": 7126 }, { "epoch": 0.20805114432508173, "grad_norm": 0.3912147581577301, "learning_rate": 9.648807401421806e-06, "loss": 0.2791, "step": 7127 }, { "epoch": 0.2080803362914526, "grad_norm": 0.40609434247016907, "learning_rate": 9.648619797583131e-06, "loss": 0.2989, "step": 7128 }, { "epoch": 0.20810952825782345, "grad_norm": 0.3815343677997589, "learning_rate": 9.64843214547452e-06, "loss": 0.2396, "step": 7129 }, { "epoch": 0.2081387202241943, "grad_norm": 0.517799437046051, "learning_rate": 9.64824444509792e-06, "loss": 0.2437, "step": 7130 }, { "epoch": 0.20816791219056516, "grad_norm": 0.3600314259529114, "learning_rate": 9.648056696455283e-06, "loss": 0.2225, "step": 7131 }, { "epoch": 0.208197104156936, "grad_norm": 0.40421611070632935, "learning_rate": 9.647868899548557e-06, "loss": 0.251, "step": 7132 }, { "epoch": 0.20822629612330687, "grad_norm": 0.33915138244628906, "learning_rate": 9.647681054379692e-06, "loss": 0.2401, "step": 7133 }, { "epoch": 0.20825548808967773, "grad_norm": 0.31865817308425903, "learning_rate": 9.647493160950639e-06, "loss": 0.2429, "step": 7134 }, { "epoch": 0.20828468005604858, "grad_norm": 0.38195350766181946, "learning_rate": 9.647305219263347e-06, "loss": 0.2125, "step": 7135 }, { "epoch": 0.20831387202241944, "grad_norm": 0.35988467931747437, "learning_rate": 9.647117229319772e-06, "loss": 0.2082, "step": 7136 }, { "epoch": 0.2083430639887903, "grad_norm": 0.3464283049106598, "learning_rate": 9.646929191121861e-06, "loss": 0.2152, "step": 7137 }, { "epoch": 0.20837225595516115, "grad_norm": 0.32853418588638306, "learning_rate": 9.646741104671569e-06, "loss": 0.2871, "step": 7138 }, { "epoch": 0.208401447921532, "grad_norm": 0.37776193022727966, "learning_rate": 9.646552969970849e-06, "loss": 0.2261, "step": 7139 }, { "epoch": 0.20843063988790284, "grad_norm": 0.37419337034225464, "learning_rate": 9.646364787021653e-06, "loss": 0.257, "step": 7140 }, { "epoch": 0.2084598318542737, "grad_norm": 0.412838339805603, "learning_rate": 9.646176555825939e-06, "loss": 0.2428, "step": 7141 }, { "epoch": 0.20848902382064455, "grad_norm": 0.35066500306129456, "learning_rate": 9.645988276385659e-06, "loss": 0.2306, "step": 7142 }, { "epoch": 0.2085182157870154, "grad_norm": 0.3383638858795166, "learning_rate": 9.645799948702765e-06, "loss": 0.2353, "step": 7143 }, { "epoch": 0.20854740775338626, "grad_norm": 0.3876475393772125, "learning_rate": 9.645611572779218e-06, "loss": 0.2829, "step": 7144 }, { "epoch": 0.20857659971975712, "grad_norm": 0.3060165047645569, "learning_rate": 9.645423148616971e-06, "loss": 0.2254, "step": 7145 }, { "epoch": 0.20860579168612797, "grad_norm": 0.41948264837265015, "learning_rate": 9.645234676217981e-06, "loss": 0.2441, "step": 7146 }, { "epoch": 0.20863498365249883, "grad_norm": 0.30953001976013184, "learning_rate": 9.645046155584205e-06, "loss": 0.2365, "step": 7147 }, { "epoch": 0.20866417561886969, "grad_norm": 0.32485783100128174, "learning_rate": 9.6448575867176e-06, "loss": 0.222, "step": 7148 }, { "epoch": 0.20869336758524054, "grad_norm": 0.32129591703414917, "learning_rate": 9.644668969620126e-06, "loss": 0.2219, "step": 7149 }, { "epoch": 0.2087225595516114, "grad_norm": 0.36541834473609924, "learning_rate": 9.64448030429374e-06, "loss": 0.2707, "step": 7150 }, { "epoch": 0.20875175151798225, "grad_norm": 0.3415868580341339, "learning_rate": 9.6442915907404e-06, "loss": 0.2765, "step": 7151 }, { "epoch": 0.2087809434843531, "grad_norm": 0.34294015169143677, "learning_rate": 9.644102828962069e-06, "loss": 0.2149, "step": 7152 }, { "epoch": 0.20881013545072397, "grad_norm": 0.32838794589042664, "learning_rate": 9.643914018960703e-06, "loss": 0.246, "step": 7153 }, { "epoch": 0.20883932741709482, "grad_norm": 0.3739073574542999, "learning_rate": 9.643725160738265e-06, "loss": 0.2372, "step": 7154 }, { "epoch": 0.20886851938346568, "grad_norm": 0.3703373670578003, "learning_rate": 9.643536254296716e-06, "loss": 0.243, "step": 7155 }, { "epoch": 0.20889771134983653, "grad_norm": 0.4017525911331177, "learning_rate": 9.643347299638017e-06, "loss": 0.2582, "step": 7156 }, { "epoch": 0.2089269033162074, "grad_norm": 0.6003826856613159, "learning_rate": 9.64315829676413e-06, "loss": 0.2333, "step": 7157 }, { "epoch": 0.20895609528257825, "grad_norm": 0.3072463274002075, "learning_rate": 9.642969245677018e-06, "loss": 0.2101, "step": 7158 }, { "epoch": 0.20898528724894908, "grad_norm": 0.36020031571388245, "learning_rate": 9.642780146378642e-06, "loss": 0.2788, "step": 7159 }, { "epoch": 0.20901447921531993, "grad_norm": 0.34210625290870667, "learning_rate": 9.642590998870968e-06, "loss": 0.225, "step": 7160 }, { "epoch": 0.2090436711816908, "grad_norm": 0.4231514036655426, "learning_rate": 9.64240180315596e-06, "loss": 0.276, "step": 7161 }, { "epoch": 0.20907286314806164, "grad_norm": 0.42283856868743896, "learning_rate": 9.642212559235582e-06, "loss": 0.2548, "step": 7162 }, { "epoch": 0.2091020551144325, "grad_norm": 0.369001567363739, "learning_rate": 9.642023267111799e-06, "loss": 0.2428, "step": 7163 }, { "epoch": 0.20913124708080336, "grad_norm": 0.3575781285762787, "learning_rate": 9.641833926786576e-06, "loss": 0.2353, "step": 7164 }, { "epoch": 0.2091604390471742, "grad_norm": 0.34975916147232056, "learning_rate": 9.64164453826188e-06, "loss": 0.2134, "step": 7165 }, { "epoch": 0.20918963101354507, "grad_norm": 0.41092029213905334, "learning_rate": 9.641455101539676e-06, "loss": 0.2742, "step": 7166 }, { "epoch": 0.20921882297991592, "grad_norm": 0.33755970001220703, "learning_rate": 9.641265616621933e-06, "loss": 0.2112, "step": 7167 }, { "epoch": 0.20924801494628678, "grad_norm": 0.3884139358997345, "learning_rate": 9.641076083510619e-06, "loss": 0.246, "step": 7168 }, { "epoch": 0.20927720691265764, "grad_norm": 0.34615379571914673, "learning_rate": 9.640886502207697e-06, "loss": 0.2488, "step": 7169 }, { "epoch": 0.2093063988790285, "grad_norm": 0.33190202713012695, "learning_rate": 9.640696872715144e-06, "loss": 0.2364, "step": 7170 }, { "epoch": 0.20933559084539935, "grad_norm": 0.33780479431152344, "learning_rate": 9.640507195034921e-06, "loss": 0.2253, "step": 7171 }, { "epoch": 0.2093647828117702, "grad_norm": 0.34371697902679443, "learning_rate": 9.640317469169003e-06, "loss": 0.2627, "step": 7172 }, { "epoch": 0.20939397477814106, "grad_norm": 0.30873903632164, "learning_rate": 9.640127695119357e-06, "loss": 0.2072, "step": 7173 }, { "epoch": 0.20942316674451192, "grad_norm": 0.37041160464286804, "learning_rate": 9.639937872887954e-06, "loss": 0.2509, "step": 7174 }, { "epoch": 0.20945235871088277, "grad_norm": 0.3628028333187103, "learning_rate": 9.639748002476765e-06, "loss": 0.2365, "step": 7175 }, { "epoch": 0.20948155067725363, "grad_norm": 0.30472683906555176, "learning_rate": 9.639558083887763e-06, "loss": 0.2299, "step": 7176 }, { "epoch": 0.2095107426436245, "grad_norm": 0.31167498230934143, "learning_rate": 9.63936811712292e-06, "loss": 0.218, "step": 7177 }, { "epoch": 0.20953993460999534, "grad_norm": 0.3461417853832245, "learning_rate": 9.639178102184207e-06, "loss": 0.2832, "step": 7178 }, { "epoch": 0.20956912657636617, "grad_norm": 0.9069285988807678, "learning_rate": 9.6389880390736e-06, "loss": 0.2472, "step": 7179 }, { "epoch": 0.20959831854273703, "grad_norm": 0.36455804109573364, "learning_rate": 9.638797927793068e-06, "loss": 0.2556, "step": 7180 }, { "epoch": 0.20962751050910788, "grad_norm": 0.41528183221817017, "learning_rate": 9.638607768344588e-06, "loss": 0.2872, "step": 7181 }, { "epoch": 0.20965670247547874, "grad_norm": 0.3524264693260193, "learning_rate": 9.638417560730135e-06, "loss": 0.2407, "step": 7182 }, { "epoch": 0.2096858944418496, "grad_norm": 0.334949791431427, "learning_rate": 9.638227304951682e-06, "loss": 0.2347, "step": 7183 }, { "epoch": 0.20971508640822045, "grad_norm": 0.37641555070877075, "learning_rate": 9.638037001011206e-06, "loss": 0.2536, "step": 7184 }, { "epoch": 0.2097442783745913, "grad_norm": 0.3138974905014038, "learning_rate": 9.637846648910682e-06, "loss": 0.2383, "step": 7185 }, { "epoch": 0.20977347034096216, "grad_norm": 0.3303220272064209, "learning_rate": 9.637656248652087e-06, "loss": 0.2542, "step": 7186 }, { "epoch": 0.20980266230733302, "grad_norm": 0.34884005784988403, "learning_rate": 9.6374658002374e-06, "loss": 0.2361, "step": 7187 }, { "epoch": 0.20983185427370388, "grad_norm": 0.34924352169036865, "learning_rate": 9.637275303668596e-06, "loss": 0.2614, "step": 7188 }, { "epoch": 0.20986104624007473, "grad_norm": 0.40408286452293396, "learning_rate": 9.637084758947654e-06, "loss": 0.2421, "step": 7189 }, { "epoch": 0.2098902382064456, "grad_norm": 0.34801456332206726, "learning_rate": 9.636894166076553e-06, "loss": 0.2424, "step": 7190 }, { "epoch": 0.20991943017281645, "grad_norm": 0.39286255836486816, "learning_rate": 9.63670352505727e-06, "loss": 0.24, "step": 7191 }, { "epoch": 0.2099486221391873, "grad_norm": 0.38503292202949524, "learning_rate": 9.636512835891789e-06, "loss": 0.2903, "step": 7192 }, { "epoch": 0.20997781410555816, "grad_norm": 0.3535799980163574, "learning_rate": 9.636322098582087e-06, "loss": 0.2467, "step": 7193 }, { "epoch": 0.21000700607192901, "grad_norm": 0.3664451241493225, "learning_rate": 9.636131313130143e-06, "loss": 0.2565, "step": 7194 }, { "epoch": 0.21003619803829987, "grad_norm": 0.354973703622818, "learning_rate": 9.63594047953794e-06, "loss": 0.2129, "step": 7195 }, { "epoch": 0.21006539000467073, "grad_norm": 0.3212624192237854, "learning_rate": 9.63574959780746e-06, "loss": 0.2486, "step": 7196 }, { "epoch": 0.21009458197104158, "grad_norm": 0.40807220339775085, "learning_rate": 9.635558667940683e-06, "loss": 0.2648, "step": 7197 }, { "epoch": 0.2101237739374124, "grad_norm": 0.31971311569213867, "learning_rate": 9.635367689939593e-06, "loss": 0.2114, "step": 7198 }, { "epoch": 0.21015296590378327, "grad_norm": 0.3200208246707916, "learning_rate": 9.635176663806177e-06, "loss": 0.2641, "step": 7199 }, { "epoch": 0.21018215787015412, "grad_norm": 0.33269253373146057, "learning_rate": 9.634985589542411e-06, "loss": 0.2668, "step": 7200 }, { "epoch": 0.21021134983652498, "grad_norm": 0.3502924144268036, "learning_rate": 9.634794467150283e-06, "loss": 0.2223, "step": 7201 }, { "epoch": 0.21024054180289584, "grad_norm": 0.33203965425491333, "learning_rate": 9.634603296631779e-06, "loss": 0.2609, "step": 7202 }, { "epoch": 0.2102697337692667, "grad_norm": 0.3590388894081116, "learning_rate": 9.63441207798888e-06, "loss": 0.2445, "step": 7203 }, { "epoch": 0.21029892573563755, "grad_norm": 0.33207282423973083, "learning_rate": 9.634220811223575e-06, "loss": 0.2116, "step": 7204 }, { "epoch": 0.2103281177020084, "grad_norm": 0.34154629707336426, "learning_rate": 9.63402949633785e-06, "loss": 0.2649, "step": 7205 }, { "epoch": 0.21035730966837926, "grad_norm": 0.31139591336250305, "learning_rate": 9.633838133333689e-06, "loss": 0.2329, "step": 7206 }, { "epoch": 0.21038650163475012, "grad_norm": 0.3056720793247223, "learning_rate": 9.63364672221308e-06, "loss": 0.2198, "step": 7207 }, { "epoch": 0.21041569360112097, "grad_norm": 0.35257285833358765, "learning_rate": 9.633455262978015e-06, "loss": 0.2668, "step": 7208 }, { "epoch": 0.21044488556749183, "grad_norm": 0.3604077100753784, "learning_rate": 9.633263755630474e-06, "loss": 0.2313, "step": 7209 }, { "epoch": 0.21047407753386269, "grad_norm": 0.361556738615036, "learning_rate": 9.63307220017245e-06, "loss": 0.2297, "step": 7210 }, { "epoch": 0.21050326950023354, "grad_norm": 0.35660412907600403, "learning_rate": 9.632880596605934e-06, "loss": 0.2687, "step": 7211 }, { "epoch": 0.2105324614666044, "grad_norm": 0.35054248571395874, "learning_rate": 9.632688944932913e-06, "loss": 0.2385, "step": 7212 }, { "epoch": 0.21056165343297525, "grad_norm": 0.33674386143684387, "learning_rate": 9.632497245155377e-06, "loss": 0.2008, "step": 7213 }, { "epoch": 0.2105908453993461, "grad_norm": 0.37998443841934204, "learning_rate": 9.632305497275316e-06, "loss": 0.2389, "step": 7214 }, { "epoch": 0.21062003736571697, "grad_norm": 0.32419735193252563, "learning_rate": 9.632113701294723e-06, "loss": 0.2307, "step": 7215 }, { "epoch": 0.21064922933208782, "grad_norm": 0.3445306420326233, "learning_rate": 9.631921857215589e-06, "loss": 0.2332, "step": 7216 }, { "epoch": 0.21067842129845865, "grad_norm": 0.4238359034061432, "learning_rate": 9.631729965039904e-06, "loss": 0.2625, "step": 7217 }, { "epoch": 0.2107076132648295, "grad_norm": 0.3332466185092926, "learning_rate": 9.631538024769664e-06, "loss": 0.2378, "step": 7218 }, { "epoch": 0.21073680523120036, "grad_norm": 0.3164192736148834, "learning_rate": 9.63134603640686e-06, "loss": 0.2068, "step": 7219 }, { "epoch": 0.21076599719757122, "grad_norm": 0.3214268684387207, "learning_rate": 9.631153999953484e-06, "loss": 0.1873, "step": 7220 }, { "epoch": 0.21079518916394208, "grad_norm": 0.3575713336467743, "learning_rate": 9.630961915411532e-06, "loss": 0.2377, "step": 7221 }, { "epoch": 0.21082438113031293, "grad_norm": 0.37748944759368896, "learning_rate": 9.630769782783e-06, "loss": 0.227, "step": 7222 }, { "epoch": 0.2108535730966838, "grad_norm": 0.4414173364639282, "learning_rate": 9.630577602069882e-06, "loss": 0.228, "step": 7223 }, { "epoch": 0.21088276506305464, "grad_norm": 0.3157416880130768, "learning_rate": 9.63038537327417e-06, "loss": 0.1905, "step": 7224 }, { "epoch": 0.2109119570294255, "grad_norm": 0.3216918706893921, "learning_rate": 9.630193096397866e-06, "loss": 0.2431, "step": 7225 }, { "epoch": 0.21094114899579636, "grad_norm": 0.415955513715744, "learning_rate": 9.630000771442962e-06, "loss": 0.229, "step": 7226 }, { "epoch": 0.2109703409621672, "grad_norm": 0.36892008781433105, "learning_rate": 9.629808398411456e-06, "loss": 0.2827, "step": 7227 }, { "epoch": 0.21099953292853807, "grad_norm": 0.36503076553344727, "learning_rate": 9.629615977305349e-06, "loss": 0.2258, "step": 7228 }, { "epoch": 0.21102872489490893, "grad_norm": 0.38736197352409363, "learning_rate": 9.629423508126635e-06, "loss": 0.2759, "step": 7229 }, { "epoch": 0.21105791686127978, "grad_norm": 0.3360264301300049, "learning_rate": 9.629230990877312e-06, "loss": 0.2262, "step": 7230 }, { "epoch": 0.21108710882765064, "grad_norm": 0.34198373556137085, "learning_rate": 9.629038425559381e-06, "loss": 0.2465, "step": 7231 }, { "epoch": 0.2111163007940215, "grad_norm": 0.44616737961769104, "learning_rate": 9.628845812174843e-06, "loss": 0.2824, "step": 7232 }, { "epoch": 0.21114549276039235, "grad_norm": 0.4497382640838623, "learning_rate": 9.628653150725696e-06, "loss": 0.2439, "step": 7233 }, { "epoch": 0.2111746847267632, "grad_norm": 0.32472264766693115, "learning_rate": 9.628460441213941e-06, "loss": 0.2097, "step": 7234 }, { "epoch": 0.21120387669313406, "grad_norm": 0.4519490599632263, "learning_rate": 9.628267683641578e-06, "loss": 0.2884, "step": 7235 }, { "epoch": 0.2112330686595049, "grad_norm": 0.331653892993927, "learning_rate": 9.62807487801061e-06, "loss": 0.2736, "step": 7236 }, { "epoch": 0.21126226062587575, "grad_norm": 0.32100847363471985, "learning_rate": 9.627882024323038e-06, "loss": 0.2289, "step": 7237 }, { "epoch": 0.2112914525922466, "grad_norm": 0.3734094798564911, "learning_rate": 9.627689122580866e-06, "loss": 0.2314, "step": 7238 }, { "epoch": 0.21132064455861746, "grad_norm": 0.3349069356918335, "learning_rate": 9.627496172786096e-06, "loss": 0.2223, "step": 7239 }, { "epoch": 0.21134983652498832, "grad_norm": 0.3327920734882355, "learning_rate": 9.627303174940732e-06, "loss": 0.2503, "step": 7240 }, { "epoch": 0.21137902849135917, "grad_norm": 0.3481312692165375, "learning_rate": 9.627110129046778e-06, "loss": 0.2607, "step": 7241 }, { "epoch": 0.21140822045773003, "grad_norm": 0.3483259081840515, "learning_rate": 9.626917035106237e-06, "loss": 0.2672, "step": 7242 }, { "epoch": 0.21143741242410088, "grad_norm": 0.3113023042678833, "learning_rate": 9.626723893121116e-06, "loss": 0.2617, "step": 7243 }, { "epoch": 0.21146660439047174, "grad_norm": 0.3510556221008301, "learning_rate": 9.62653070309342e-06, "loss": 0.2287, "step": 7244 }, { "epoch": 0.2114957963568426, "grad_norm": 0.3846985697746277, "learning_rate": 9.626337465025155e-06, "loss": 0.3073, "step": 7245 }, { "epoch": 0.21152498832321345, "grad_norm": 0.3407473862171173, "learning_rate": 9.626144178918327e-06, "loss": 0.2295, "step": 7246 }, { "epoch": 0.2115541802895843, "grad_norm": 0.3818904459476471, "learning_rate": 9.625950844774941e-06, "loss": 0.3087, "step": 7247 }, { "epoch": 0.21158337225595517, "grad_norm": 0.2699102461338043, "learning_rate": 9.62575746259701e-06, "loss": 0.1928, "step": 7248 }, { "epoch": 0.21161256422232602, "grad_norm": 0.33118578791618347, "learning_rate": 9.625564032386538e-06, "loss": 0.2128, "step": 7249 }, { "epoch": 0.21164175618869688, "grad_norm": 0.3332606554031372, "learning_rate": 9.625370554145535e-06, "loss": 0.2285, "step": 7250 }, { "epoch": 0.21167094815506773, "grad_norm": 0.41100484132766724, "learning_rate": 9.62517702787601e-06, "loss": 0.2562, "step": 7251 }, { "epoch": 0.2117001401214386, "grad_norm": 0.3879980146884918, "learning_rate": 9.62498345357997e-06, "loss": 0.2187, "step": 7252 }, { "epoch": 0.21172933208780945, "grad_norm": 0.30789685249328613, "learning_rate": 9.624789831259427e-06, "loss": 0.2342, "step": 7253 }, { "epoch": 0.2117585240541803, "grad_norm": 0.4310339689254761, "learning_rate": 9.624596160916394e-06, "loss": 0.2382, "step": 7254 }, { "epoch": 0.21178771602055113, "grad_norm": 0.3518937826156616, "learning_rate": 9.624402442552878e-06, "loss": 0.2218, "step": 7255 }, { "epoch": 0.211816907986922, "grad_norm": 0.38412711024284363, "learning_rate": 9.624208676170891e-06, "loss": 0.2933, "step": 7256 }, { "epoch": 0.21184609995329284, "grad_norm": 0.3732443153858185, "learning_rate": 9.624014861772447e-06, "loss": 0.2687, "step": 7257 }, { "epoch": 0.2118752919196637, "grad_norm": 0.3732035458087921, "learning_rate": 9.623820999359558e-06, "loss": 0.2842, "step": 7258 }, { "epoch": 0.21190448388603456, "grad_norm": 0.33760812878608704, "learning_rate": 9.623627088934237e-06, "loss": 0.2868, "step": 7259 }, { "epoch": 0.2119336758524054, "grad_norm": 0.30659812688827515, "learning_rate": 9.623433130498496e-06, "loss": 0.282, "step": 7260 }, { "epoch": 0.21196286781877627, "grad_norm": 0.34641146659851074, "learning_rate": 9.623239124054351e-06, "loss": 0.2072, "step": 7261 }, { "epoch": 0.21199205978514712, "grad_norm": 0.31349506974220276, "learning_rate": 9.623045069603815e-06, "loss": 0.2137, "step": 7262 }, { "epoch": 0.21202125175151798, "grad_norm": 0.4428998827934265, "learning_rate": 9.622850967148905e-06, "loss": 0.2846, "step": 7263 }, { "epoch": 0.21205044371788884, "grad_norm": 0.3415469825267792, "learning_rate": 9.622656816691634e-06, "loss": 0.2814, "step": 7264 }, { "epoch": 0.2120796356842597, "grad_norm": 0.3965241611003876, "learning_rate": 9.62246261823402e-06, "loss": 0.2847, "step": 7265 }, { "epoch": 0.21210882765063055, "grad_norm": 0.31208503246307373, "learning_rate": 9.622268371778077e-06, "loss": 0.2484, "step": 7266 }, { "epoch": 0.2121380196170014, "grad_norm": 0.3198363184928894, "learning_rate": 9.622074077325825e-06, "loss": 0.2151, "step": 7267 }, { "epoch": 0.21216721158337226, "grad_norm": 0.3010473847389221, "learning_rate": 9.62187973487928e-06, "loss": 0.2741, "step": 7268 }, { "epoch": 0.21219640354974312, "grad_norm": 0.3365691304206848, "learning_rate": 9.62168534444046e-06, "loss": 0.2617, "step": 7269 }, { "epoch": 0.21222559551611397, "grad_norm": 0.33132797479629517, "learning_rate": 9.621490906011382e-06, "loss": 0.2496, "step": 7270 }, { "epoch": 0.21225478748248483, "grad_norm": 0.3846307694911957, "learning_rate": 9.621296419594069e-06, "loss": 0.3428, "step": 7271 }, { "epoch": 0.2122839794488557, "grad_norm": 0.31180569529533386, "learning_rate": 9.621101885190538e-06, "loss": 0.1946, "step": 7272 }, { "epoch": 0.21231317141522654, "grad_norm": 0.34772858023643494, "learning_rate": 9.620907302802807e-06, "loss": 0.2847, "step": 7273 }, { "epoch": 0.21234236338159737, "grad_norm": 0.35707250237464905, "learning_rate": 9.620712672432901e-06, "loss": 0.2493, "step": 7274 }, { "epoch": 0.21237155534796823, "grad_norm": 0.3506356477737427, "learning_rate": 9.620517994082836e-06, "loss": 0.2544, "step": 7275 }, { "epoch": 0.21240074731433908, "grad_norm": 0.3338937759399414, "learning_rate": 9.62032326775464e-06, "loss": 0.2424, "step": 7276 }, { "epoch": 0.21242993928070994, "grad_norm": 0.3617934286594391, "learning_rate": 9.620128493450327e-06, "loss": 0.2275, "step": 7277 }, { "epoch": 0.2124591312470808, "grad_norm": 0.3383987247943878, "learning_rate": 9.619933671171926e-06, "loss": 0.2409, "step": 7278 }, { "epoch": 0.21248832321345165, "grad_norm": 0.3220048248767853, "learning_rate": 9.619738800921457e-06, "loss": 0.2628, "step": 7279 }, { "epoch": 0.2125175151798225, "grad_norm": 0.3255223333835602, "learning_rate": 9.619543882700943e-06, "loss": 0.2529, "step": 7280 }, { "epoch": 0.21254670714619336, "grad_norm": 0.3202689290046692, "learning_rate": 9.61934891651241e-06, "loss": 0.2598, "step": 7281 }, { "epoch": 0.21257589911256422, "grad_norm": 0.44618460536003113, "learning_rate": 9.61915390235788e-06, "loss": 0.2935, "step": 7282 }, { "epoch": 0.21260509107893508, "grad_norm": 0.3192383646965027, "learning_rate": 9.618958840239381e-06, "loss": 0.2878, "step": 7283 }, { "epoch": 0.21263428304530593, "grad_norm": 0.3573266267776489, "learning_rate": 9.618763730158937e-06, "loss": 0.2841, "step": 7284 }, { "epoch": 0.2126634750116768, "grad_norm": 0.31770163774490356, "learning_rate": 9.618568572118574e-06, "loss": 0.2112, "step": 7285 }, { "epoch": 0.21269266697804765, "grad_norm": 0.3085816204547882, "learning_rate": 9.618373366120317e-06, "loss": 0.2209, "step": 7286 }, { "epoch": 0.2127218589444185, "grad_norm": 0.3613125681877136, "learning_rate": 9.618178112166195e-06, "loss": 0.2527, "step": 7287 }, { "epoch": 0.21275105091078936, "grad_norm": 0.32410651445388794, "learning_rate": 9.617982810258235e-06, "loss": 0.2186, "step": 7288 }, { "epoch": 0.21278024287716021, "grad_norm": 0.32912519574165344, "learning_rate": 9.617787460398464e-06, "loss": 0.2402, "step": 7289 }, { "epoch": 0.21280943484353107, "grad_norm": 0.36350855231285095, "learning_rate": 9.617592062588912e-06, "loss": 0.2715, "step": 7290 }, { "epoch": 0.21283862680990193, "grad_norm": 0.41374659538269043, "learning_rate": 9.617396616831608e-06, "loss": 0.2365, "step": 7291 }, { "epoch": 0.21286781877627278, "grad_norm": 0.36305704712867737, "learning_rate": 9.617201123128578e-06, "loss": 0.2318, "step": 7292 }, { "epoch": 0.2128970107426436, "grad_norm": 0.338382363319397, "learning_rate": 9.617005581481855e-06, "loss": 0.2803, "step": 7293 }, { "epoch": 0.21292620270901447, "grad_norm": 0.31770089268684387, "learning_rate": 9.61680999189347e-06, "loss": 0.2638, "step": 7294 }, { "epoch": 0.21295539467538532, "grad_norm": 0.32640430331230164, "learning_rate": 9.616614354365453e-06, "loss": 0.2306, "step": 7295 }, { "epoch": 0.21298458664175618, "grad_norm": 0.3518548905849457, "learning_rate": 9.616418668899834e-06, "loss": 0.2289, "step": 7296 }, { "epoch": 0.21301377860812704, "grad_norm": 0.32645490765571594, "learning_rate": 9.616222935498647e-06, "loss": 0.2499, "step": 7297 }, { "epoch": 0.2130429705744979, "grad_norm": 0.34727856516838074, "learning_rate": 9.616027154163925e-06, "loss": 0.2337, "step": 7298 }, { "epoch": 0.21307216254086875, "grad_norm": 0.4227864444255829, "learning_rate": 9.615831324897698e-06, "loss": 0.2639, "step": 7299 }, { "epoch": 0.2131013545072396, "grad_norm": 0.39113855361938477, "learning_rate": 9.615635447702003e-06, "loss": 0.27, "step": 7300 }, { "epoch": 0.21313054647361046, "grad_norm": 0.36799436807632446, "learning_rate": 9.61543952257887e-06, "loss": 0.2379, "step": 7301 }, { "epoch": 0.21315973843998132, "grad_norm": 0.3872268795967102, "learning_rate": 9.615243549530336e-06, "loss": 0.2609, "step": 7302 }, { "epoch": 0.21318893040635217, "grad_norm": 0.3699398338794708, "learning_rate": 9.615047528558436e-06, "loss": 0.2818, "step": 7303 }, { "epoch": 0.21321812237272303, "grad_norm": 0.3784722685813904, "learning_rate": 9.614851459665205e-06, "loss": 0.2518, "step": 7304 }, { "epoch": 0.21324731433909389, "grad_norm": 0.32061126828193665, "learning_rate": 9.614655342852677e-06, "loss": 0.1953, "step": 7305 }, { "epoch": 0.21327650630546474, "grad_norm": 0.4333018660545349, "learning_rate": 9.614459178122891e-06, "loss": 0.2297, "step": 7306 }, { "epoch": 0.2133056982718356, "grad_norm": 0.6315233707427979, "learning_rate": 9.614262965477882e-06, "loss": 0.2526, "step": 7307 }, { "epoch": 0.21333489023820645, "grad_norm": 0.8277124166488647, "learning_rate": 9.614066704919691e-06, "loss": 0.2602, "step": 7308 }, { "epoch": 0.2133640822045773, "grad_norm": 0.33263012766838074, "learning_rate": 9.613870396450353e-06, "loss": 0.2588, "step": 7309 }, { "epoch": 0.21339327417094817, "grad_norm": 0.3526003062725067, "learning_rate": 9.613674040071905e-06, "loss": 0.2447, "step": 7310 }, { "epoch": 0.21342246613731902, "grad_norm": 0.29976239800453186, "learning_rate": 9.61347763578639e-06, "loss": 0.244, "step": 7311 }, { "epoch": 0.21345165810368985, "grad_norm": 0.38939476013183594, "learning_rate": 9.613281183595844e-06, "loss": 0.273, "step": 7312 }, { "epoch": 0.2134808500700607, "grad_norm": 0.3803790509700775, "learning_rate": 9.613084683502307e-06, "loss": 0.2696, "step": 7313 }, { "epoch": 0.21351004203643156, "grad_norm": 0.35529711842536926, "learning_rate": 9.612888135507822e-06, "loss": 0.2671, "step": 7314 }, { "epoch": 0.21353923400280242, "grad_norm": 0.31096717715263367, "learning_rate": 9.612691539614429e-06, "loss": 0.2225, "step": 7315 }, { "epoch": 0.21356842596917328, "grad_norm": 0.3808014988899231, "learning_rate": 9.612494895824168e-06, "loss": 0.296, "step": 7316 }, { "epoch": 0.21359761793554413, "grad_norm": 0.31694671511650085, "learning_rate": 9.61229820413908e-06, "loss": 0.2366, "step": 7317 }, { "epoch": 0.213626809901915, "grad_norm": 0.3548440933227539, "learning_rate": 9.61210146456121e-06, "loss": 0.2542, "step": 7318 }, { "epoch": 0.21365600186828584, "grad_norm": 0.3063213527202606, "learning_rate": 9.611904677092601e-06, "loss": 0.2301, "step": 7319 }, { "epoch": 0.2136851938346567, "grad_norm": 0.3429889380931854, "learning_rate": 9.611707841735294e-06, "loss": 0.2837, "step": 7320 }, { "epoch": 0.21371438580102756, "grad_norm": 0.3722803592681885, "learning_rate": 9.611510958491335e-06, "loss": 0.3206, "step": 7321 }, { "epoch": 0.2137435777673984, "grad_norm": 0.31477090716362, "learning_rate": 9.611314027362766e-06, "loss": 0.2691, "step": 7322 }, { "epoch": 0.21377276973376927, "grad_norm": 0.3312753736972809, "learning_rate": 9.611117048351634e-06, "loss": 0.2162, "step": 7323 }, { "epoch": 0.21380196170014013, "grad_norm": 0.37015557289123535, "learning_rate": 9.610920021459986e-06, "loss": 0.244, "step": 7324 }, { "epoch": 0.21383115366651098, "grad_norm": 0.29135629534721375, "learning_rate": 9.610722946689863e-06, "loss": 0.1976, "step": 7325 }, { "epoch": 0.21386034563288184, "grad_norm": 0.3503647446632385, "learning_rate": 9.610525824043315e-06, "loss": 0.2694, "step": 7326 }, { "epoch": 0.2138895375992527, "grad_norm": 0.3197654187679291, "learning_rate": 9.610328653522389e-06, "loss": 0.1958, "step": 7327 }, { "epoch": 0.21391872956562355, "grad_norm": 0.333659291267395, "learning_rate": 9.61013143512913e-06, "loss": 0.2677, "step": 7328 }, { "epoch": 0.2139479215319944, "grad_norm": 0.29862523078918457, "learning_rate": 9.609934168865587e-06, "loss": 0.2127, "step": 7329 }, { "epoch": 0.21397711349836526, "grad_norm": 0.3313959538936615, "learning_rate": 9.609736854733809e-06, "loss": 0.2995, "step": 7330 }, { "epoch": 0.21400630546473612, "grad_norm": 0.34012192487716675, "learning_rate": 9.609539492735844e-06, "loss": 0.2348, "step": 7331 }, { "epoch": 0.21403549743110695, "grad_norm": 0.33990657329559326, "learning_rate": 9.609342082873742e-06, "loss": 0.2161, "step": 7332 }, { "epoch": 0.2140646893974778, "grad_norm": 0.3423140048980713, "learning_rate": 9.609144625149553e-06, "loss": 0.2356, "step": 7333 }, { "epoch": 0.21409388136384866, "grad_norm": 0.3509714603424072, "learning_rate": 9.608947119565327e-06, "loss": 0.2486, "step": 7334 }, { "epoch": 0.21412307333021952, "grad_norm": 0.3646893799304962, "learning_rate": 9.608749566123112e-06, "loss": 0.2603, "step": 7335 }, { "epoch": 0.21415226529659037, "grad_norm": 0.2962580919265747, "learning_rate": 9.608551964824963e-06, "loss": 0.2191, "step": 7336 }, { "epoch": 0.21418145726296123, "grad_norm": 0.3685359060764313, "learning_rate": 9.608354315672934e-06, "loss": 0.2891, "step": 7337 }, { "epoch": 0.21421064922933208, "grad_norm": 0.3520479202270508, "learning_rate": 9.608156618669072e-06, "loss": 0.2158, "step": 7338 }, { "epoch": 0.21423984119570294, "grad_norm": 0.6917908787727356, "learning_rate": 9.607958873815431e-06, "loss": 0.2475, "step": 7339 }, { "epoch": 0.2142690331620738, "grad_norm": 0.3149833083152771, "learning_rate": 9.607761081114067e-06, "loss": 0.2776, "step": 7340 }, { "epoch": 0.21429822512844465, "grad_norm": 0.31958717107772827, "learning_rate": 9.607563240567033e-06, "loss": 0.2235, "step": 7341 }, { "epoch": 0.2143274170948155, "grad_norm": 0.3092733323574066, "learning_rate": 9.60736535217638e-06, "loss": 0.2238, "step": 7342 }, { "epoch": 0.21435660906118637, "grad_norm": 0.3523903489112854, "learning_rate": 9.607167415944167e-06, "loss": 0.2783, "step": 7343 }, { "epoch": 0.21438580102755722, "grad_norm": 0.36233484745025635, "learning_rate": 9.606969431872448e-06, "loss": 0.2866, "step": 7344 }, { "epoch": 0.21441499299392808, "grad_norm": 0.3316750228404999, "learning_rate": 9.606771399963277e-06, "loss": 0.2271, "step": 7345 }, { "epoch": 0.21444418496029893, "grad_norm": 0.3739025294780731, "learning_rate": 9.606573320218713e-06, "loss": 0.2812, "step": 7346 }, { "epoch": 0.2144733769266698, "grad_norm": 0.32667961716651917, "learning_rate": 9.606375192640812e-06, "loss": 0.2129, "step": 7347 }, { "epoch": 0.21450256889304065, "grad_norm": 0.3609132468700409, "learning_rate": 9.606177017231628e-06, "loss": 0.2574, "step": 7348 }, { "epoch": 0.2145317608594115, "grad_norm": 0.3620678186416626, "learning_rate": 9.605978793993225e-06, "loss": 0.2389, "step": 7349 }, { "epoch": 0.21456095282578236, "grad_norm": 0.3553786873817444, "learning_rate": 9.605780522927658e-06, "loss": 0.3031, "step": 7350 }, { "epoch": 0.2145901447921532, "grad_norm": 0.37706610560417175, "learning_rate": 9.605582204036983e-06, "loss": 0.2349, "step": 7351 }, { "epoch": 0.21461933675852404, "grad_norm": 0.3178531229496002, "learning_rate": 9.605383837323263e-06, "loss": 0.1951, "step": 7352 }, { "epoch": 0.2146485287248949, "grad_norm": 0.34386691451072693, "learning_rate": 9.605185422788557e-06, "loss": 0.282, "step": 7353 }, { "epoch": 0.21467772069126576, "grad_norm": 0.3629271686077118, "learning_rate": 9.604986960434925e-06, "loss": 0.2785, "step": 7354 }, { "epoch": 0.2147069126576366, "grad_norm": 0.505649209022522, "learning_rate": 9.604788450264428e-06, "loss": 0.2483, "step": 7355 }, { "epoch": 0.21473610462400747, "grad_norm": 0.7508007884025574, "learning_rate": 9.604589892279128e-06, "loss": 0.2578, "step": 7356 }, { "epoch": 0.21476529659037832, "grad_norm": 0.38482385873794556, "learning_rate": 9.604391286481086e-06, "loss": 0.2782, "step": 7357 }, { "epoch": 0.21479448855674918, "grad_norm": 0.3162800073623657, "learning_rate": 9.604192632872362e-06, "loss": 0.2423, "step": 7358 }, { "epoch": 0.21482368052312004, "grad_norm": 0.40138253569602966, "learning_rate": 9.603993931455023e-06, "loss": 0.3013, "step": 7359 }, { "epoch": 0.2148528724894909, "grad_norm": 0.36892497539520264, "learning_rate": 9.60379518223113e-06, "loss": 0.3092, "step": 7360 }, { "epoch": 0.21488206445586175, "grad_norm": 0.38910219073295593, "learning_rate": 9.603596385202747e-06, "loss": 0.2667, "step": 7361 }, { "epoch": 0.2149112564222326, "grad_norm": 0.4219993054866791, "learning_rate": 9.603397540371937e-06, "loss": 0.2282, "step": 7362 }, { "epoch": 0.21494044838860346, "grad_norm": 0.3708246648311615, "learning_rate": 9.603198647740766e-06, "loss": 0.2487, "step": 7363 }, { "epoch": 0.21496964035497432, "grad_norm": 0.32337436079978943, "learning_rate": 9.6029997073113e-06, "loss": 0.246, "step": 7364 }, { "epoch": 0.21499883232134517, "grad_norm": 0.45446228981018066, "learning_rate": 9.602800719085606e-06, "loss": 0.2575, "step": 7365 }, { "epoch": 0.21502802428771603, "grad_norm": 0.39305269718170166, "learning_rate": 9.602601683065744e-06, "loss": 0.2305, "step": 7366 }, { "epoch": 0.21505721625408689, "grad_norm": 0.31619390845298767, "learning_rate": 9.602402599253788e-06, "loss": 0.236, "step": 7367 }, { "epoch": 0.21508640822045774, "grad_norm": 0.3697967529296875, "learning_rate": 9.6022034676518e-06, "loss": 0.2687, "step": 7368 }, { "epoch": 0.2151156001868286, "grad_norm": 0.3416047692298889, "learning_rate": 9.602004288261853e-06, "loss": 0.2522, "step": 7369 }, { "epoch": 0.21514479215319943, "grad_norm": 0.31121236085891724, "learning_rate": 9.60180506108601e-06, "loss": 0.2517, "step": 7370 }, { "epoch": 0.21517398411957028, "grad_norm": 0.40684637427330017, "learning_rate": 9.60160578612634e-06, "loss": 0.356, "step": 7371 }, { "epoch": 0.21520317608594114, "grad_norm": 0.4197036623954773, "learning_rate": 9.601406463384918e-06, "loss": 0.2957, "step": 7372 }, { "epoch": 0.215232368052312, "grad_norm": 0.3651437759399414, "learning_rate": 9.601207092863806e-06, "loss": 0.2456, "step": 7373 }, { "epoch": 0.21526156001868285, "grad_norm": 0.36015868186950684, "learning_rate": 9.60100767456508e-06, "loss": 0.2466, "step": 7374 }, { "epoch": 0.2152907519850537, "grad_norm": 0.4011261761188507, "learning_rate": 9.600808208490809e-06, "loss": 0.2719, "step": 7375 }, { "epoch": 0.21531994395142456, "grad_norm": 0.36535030603408813, "learning_rate": 9.600608694643063e-06, "loss": 0.2495, "step": 7376 }, { "epoch": 0.21534913591779542, "grad_norm": 0.39601632952690125, "learning_rate": 9.600409133023914e-06, "loss": 0.2453, "step": 7377 }, { "epoch": 0.21537832788416628, "grad_norm": 0.8914932012557983, "learning_rate": 9.600209523635436e-06, "loss": 0.2377, "step": 7378 }, { "epoch": 0.21540751985053713, "grad_norm": 0.3175492286682129, "learning_rate": 9.600009866479698e-06, "loss": 0.24, "step": 7379 }, { "epoch": 0.215436711816908, "grad_norm": 0.5371947288513184, "learning_rate": 9.599810161558778e-06, "loss": 0.2164, "step": 7380 }, { "epoch": 0.21546590378327884, "grad_norm": 0.38237202167510986, "learning_rate": 9.599610408874746e-06, "loss": 0.2647, "step": 7381 }, { "epoch": 0.2154950957496497, "grad_norm": 0.35253769159317017, "learning_rate": 9.599410608429679e-06, "loss": 0.223, "step": 7382 }, { "epoch": 0.21552428771602056, "grad_norm": 0.47545644640922546, "learning_rate": 9.599210760225648e-06, "loss": 0.245, "step": 7383 }, { "epoch": 0.2155534796823914, "grad_norm": 0.5302823185920715, "learning_rate": 9.599010864264733e-06, "loss": 0.2367, "step": 7384 }, { "epoch": 0.21558267164876227, "grad_norm": 0.32595962285995483, "learning_rate": 9.598810920549005e-06, "loss": 0.2199, "step": 7385 }, { "epoch": 0.21561186361513313, "grad_norm": 0.45832329988479614, "learning_rate": 9.598610929080544e-06, "loss": 0.285, "step": 7386 }, { "epoch": 0.21564105558150398, "grad_norm": 0.35461828112602234, "learning_rate": 9.598410889861422e-06, "loss": 0.24, "step": 7387 }, { "epoch": 0.21567024754787484, "grad_norm": 0.3201104402542114, "learning_rate": 9.59821080289372e-06, "loss": 0.2611, "step": 7388 }, { "epoch": 0.21569943951424567, "grad_norm": 0.378475546836853, "learning_rate": 9.598010668179514e-06, "loss": 0.2615, "step": 7389 }, { "epoch": 0.21572863148061652, "grad_norm": 0.34865131974220276, "learning_rate": 9.597810485720885e-06, "loss": 0.2521, "step": 7390 }, { "epoch": 0.21575782344698738, "grad_norm": 0.3835638165473938, "learning_rate": 9.597610255519906e-06, "loss": 0.2669, "step": 7391 }, { "epoch": 0.21578701541335824, "grad_norm": 0.31862786412239075, "learning_rate": 9.597409977578661e-06, "loss": 0.2682, "step": 7392 }, { "epoch": 0.2158162073797291, "grad_norm": 0.27938053011894226, "learning_rate": 9.59720965189923e-06, "loss": 0.1993, "step": 7393 }, { "epoch": 0.21584539934609995, "grad_norm": 0.3150196373462677, "learning_rate": 9.597009278483689e-06, "loss": 0.2332, "step": 7394 }, { "epoch": 0.2158745913124708, "grad_norm": 0.3501228392124176, "learning_rate": 9.596808857334121e-06, "loss": 0.2354, "step": 7395 }, { "epoch": 0.21590378327884166, "grad_norm": 0.3267855644226074, "learning_rate": 9.596608388452607e-06, "loss": 0.2312, "step": 7396 }, { "epoch": 0.21593297524521252, "grad_norm": 0.36110925674438477, "learning_rate": 9.596407871841229e-06, "loss": 0.2169, "step": 7397 }, { "epoch": 0.21596216721158337, "grad_norm": 0.42352646589279175, "learning_rate": 9.59620730750207e-06, "loss": 0.2709, "step": 7398 }, { "epoch": 0.21599135917795423, "grad_norm": 0.361918181180954, "learning_rate": 9.596006695437208e-06, "loss": 0.2529, "step": 7399 }, { "epoch": 0.21602055114432508, "grad_norm": 0.3449021279811859, "learning_rate": 9.595806035648732e-06, "loss": 0.2585, "step": 7400 }, { "epoch": 0.21604974311069594, "grad_norm": 0.36332955956459045, "learning_rate": 9.595605328138721e-06, "loss": 0.2237, "step": 7401 }, { "epoch": 0.2160789350770668, "grad_norm": 0.36214372515678406, "learning_rate": 9.595404572909264e-06, "loss": 0.2371, "step": 7402 }, { "epoch": 0.21610812704343765, "grad_norm": 0.393559068441391, "learning_rate": 9.59520376996244e-06, "loss": 0.2329, "step": 7403 }, { "epoch": 0.2161373190098085, "grad_norm": 0.33951276540756226, "learning_rate": 9.595002919300337e-06, "loss": 0.2577, "step": 7404 }, { "epoch": 0.21616651097617937, "grad_norm": 0.3741952180862427, "learning_rate": 9.594802020925043e-06, "loss": 0.294, "step": 7405 }, { "epoch": 0.21619570294255022, "grad_norm": 0.33302047848701477, "learning_rate": 9.594601074838638e-06, "loss": 0.2166, "step": 7406 }, { "epoch": 0.21622489490892108, "grad_norm": 0.3365084230899811, "learning_rate": 9.594400081043214e-06, "loss": 0.234, "step": 7407 }, { "epoch": 0.2162540868752919, "grad_norm": 0.38470762968063354, "learning_rate": 9.594199039540854e-06, "loss": 0.2717, "step": 7408 }, { "epoch": 0.21628327884166276, "grad_norm": 0.3229826092720032, "learning_rate": 9.593997950333648e-06, "loss": 0.208, "step": 7409 }, { "epoch": 0.21631247080803362, "grad_norm": 0.3165633976459503, "learning_rate": 9.593796813423686e-06, "loss": 0.2114, "step": 7410 }, { "epoch": 0.21634166277440448, "grad_norm": 0.4099729359149933, "learning_rate": 9.593595628813052e-06, "loss": 0.2593, "step": 7411 }, { "epoch": 0.21637085474077533, "grad_norm": 0.32775506377220154, "learning_rate": 9.59339439650384e-06, "loss": 0.216, "step": 7412 }, { "epoch": 0.2164000467071462, "grad_norm": 0.35862383246421814, "learning_rate": 9.593193116498132e-06, "loss": 0.2501, "step": 7413 }, { "epoch": 0.21642923867351704, "grad_norm": 0.34366729855537415, "learning_rate": 9.592991788798026e-06, "loss": 0.2439, "step": 7414 }, { "epoch": 0.2164584306398879, "grad_norm": 0.3550211489200592, "learning_rate": 9.592790413405609e-06, "loss": 0.2361, "step": 7415 }, { "epoch": 0.21648762260625876, "grad_norm": 0.3402293622493744, "learning_rate": 9.59258899032297e-06, "loss": 0.2275, "step": 7416 }, { "epoch": 0.2165168145726296, "grad_norm": 0.39699485898017883, "learning_rate": 9.592387519552206e-06, "loss": 0.3188, "step": 7417 }, { "epoch": 0.21654600653900047, "grad_norm": 0.3525044023990631, "learning_rate": 9.592186001095404e-06, "loss": 0.243, "step": 7418 }, { "epoch": 0.21657519850537132, "grad_norm": 0.3662148416042328, "learning_rate": 9.59198443495466e-06, "loss": 0.2668, "step": 7419 }, { "epoch": 0.21660439047174218, "grad_norm": 0.2972138226032257, "learning_rate": 9.591782821132065e-06, "loss": 0.2249, "step": 7420 }, { "epoch": 0.21663358243811304, "grad_norm": 0.3564540147781372, "learning_rate": 9.591581159629711e-06, "loss": 0.241, "step": 7421 }, { "epoch": 0.2166627744044839, "grad_norm": 0.7089563012123108, "learning_rate": 9.591379450449696e-06, "loss": 0.2735, "step": 7422 }, { "epoch": 0.21669196637085475, "grad_norm": 0.3442919850349426, "learning_rate": 9.59117769359411e-06, "loss": 0.2106, "step": 7423 }, { "epoch": 0.2167211583372256, "grad_norm": 0.37934473156929016, "learning_rate": 9.590975889065053e-06, "loss": 0.2481, "step": 7424 }, { "epoch": 0.21675035030359646, "grad_norm": 0.38246408104896545, "learning_rate": 9.590774036864616e-06, "loss": 0.3175, "step": 7425 }, { "epoch": 0.21677954226996732, "grad_norm": 0.3112587034702301, "learning_rate": 9.590572136994898e-06, "loss": 0.2452, "step": 7426 }, { "epoch": 0.21680873423633815, "grad_norm": 0.3229367434978485, "learning_rate": 9.590370189457994e-06, "loss": 0.2322, "step": 7427 }, { "epoch": 0.216837926202709, "grad_norm": 0.36326679587364197, "learning_rate": 9.590168194256e-06, "loss": 0.2779, "step": 7428 }, { "epoch": 0.21686711816907986, "grad_norm": 0.35878896713256836, "learning_rate": 9.589966151391017e-06, "loss": 0.287, "step": 7429 }, { "epoch": 0.21689631013545072, "grad_norm": 0.3234846591949463, "learning_rate": 9.589764060865139e-06, "loss": 0.2424, "step": 7430 }, { "epoch": 0.21692550210182157, "grad_norm": 0.3291749656200409, "learning_rate": 9.589561922680466e-06, "loss": 0.2513, "step": 7431 }, { "epoch": 0.21695469406819243, "grad_norm": 0.3421425521373749, "learning_rate": 9.589359736839097e-06, "loss": 0.2352, "step": 7432 }, { "epoch": 0.21698388603456328, "grad_norm": 0.3222099542617798, "learning_rate": 9.589157503343132e-06, "loss": 0.2036, "step": 7433 }, { "epoch": 0.21701307800093414, "grad_norm": 0.3309755325317383, "learning_rate": 9.588955222194671e-06, "loss": 0.2036, "step": 7434 }, { "epoch": 0.217042269967305, "grad_norm": 0.34059423208236694, "learning_rate": 9.588752893395813e-06, "loss": 0.2865, "step": 7435 }, { "epoch": 0.21707146193367585, "grad_norm": 0.37868815660476685, "learning_rate": 9.58855051694866e-06, "loss": 0.2461, "step": 7436 }, { "epoch": 0.2171006539000467, "grad_norm": 0.32930028438568115, "learning_rate": 9.588348092855313e-06, "loss": 0.2415, "step": 7437 }, { "epoch": 0.21712984586641756, "grad_norm": 0.30375510454177856, "learning_rate": 9.588145621117875e-06, "loss": 0.2093, "step": 7438 }, { "epoch": 0.21715903783278842, "grad_norm": 0.2956978380680084, "learning_rate": 9.587943101738446e-06, "loss": 0.2255, "step": 7439 }, { "epoch": 0.21718822979915928, "grad_norm": 0.3068855404853821, "learning_rate": 9.587740534719132e-06, "loss": 0.2484, "step": 7440 }, { "epoch": 0.21721742176553013, "grad_norm": 0.3321721851825714, "learning_rate": 9.587537920062033e-06, "loss": 0.2453, "step": 7441 }, { "epoch": 0.217246613731901, "grad_norm": 0.34445714950561523, "learning_rate": 9.587335257769258e-06, "loss": 0.2656, "step": 7442 }, { "epoch": 0.21727580569827185, "grad_norm": 0.35139307379722595, "learning_rate": 9.587132547842903e-06, "loss": 0.2238, "step": 7443 }, { "epoch": 0.2173049976646427, "grad_norm": 0.31673166155815125, "learning_rate": 9.586929790285083e-06, "loss": 0.2172, "step": 7444 }, { "epoch": 0.21733418963101356, "grad_norm": 0.3192225396633148, "learning_rate": 9.586726985097895e-06, "loss": 0.2233, "step": 7445 }, { "epoch": 0.2173633815973844, "grad_norm": 0.30295297503471375, "learning_rate": 9.58652413228345e-06, "loss": 0.2322, "step": 7446 }, { "epoch": 0.21739257356375524, "grad_norm": 0.3563956022262573, "learning_rate": 9.586321231843852e-06, "loss": 0.256, "step": 7447 }, { "epoch": 0.2174217655301261, "grad_norm": 0.31269142031669617, "learning_rate": 9.586118283781208e-06, "loss": 0.2482, "step": 7448 }, { "epoch": 0.21745095749649695, "grad_norm": 0.3060864508152008, "learning_rate": 9.585915288097627e-06, "loss": 0.1985, "step": 7449 }, { "epoch": 0.2174801494628678, "grad_norm": 0.38162028789520264, "learning_rate": 9.585712244795215e-06, "loss": 0.2303, "step": 7450 }, { "epoch": 0.21750934142923867, "grad_norm": 0.3707403838634491, "learning_rate": 9.58550915387608e-06, "loss": 0.2736, "step": 7451 }, { "epoch": 0.21753853339560952, "grad_norm": 0.3187187910079956, "learning_rate": 9.585306015342332e-06, "loss": 0.2242, "step": 7452 }, { "epoch": 0.21756772536198038, "grad_norm": 0.367549866437912, "learning_rate": 9.585102829196083e-06, "loss": 0.2851, "step": 7453 }, { "epoch": 0.21759691732835124, "grad_norm": 0.3387696444988251, "learning_rate": 9.584899595439436e-06, "loss": 0.2433, "step": 7454 }, { "epoch": 0.2176261092947221, "grad_norm": 0.3790561258792877, "learning_rate": 9.584696314074508e-06, "loss": 0.2757, "step": 7455 }, { "epoch": 0.21765530126109295, "grad_norm": 0.3254820704460144, "learning_rate": 9.584492985103406e-06, "loss": 0.2543, "step": 7456 }, { "epoch": 0.2176844932274638, "grad_norm": 0.34697791934013367, "learning_rate": 9.584289608528243e-06, "loss": 0.2932, "step": 7457 }, { "epoch": 0.21771368519383466, "grad_norm": 0.3283807337284088, "learning_rate": 9.584086184351131e-06, "loss": 0.2448, "step": 7458 }, { "epoch": 0.21774287716020552, "grad_norm": 0.35038959980010986, "learning_rate": 9.58388271257418e-06, "loss": 0.2558, "step": 7459 }, { "epoch": 0.21777206912657637, "grad_norm": 0.33103662729263306, "learning_rate": 9.583679193199505e-06, "loss": 0.2245, "step": 7460 }, { "epoch": 0.21780126109294723, "grad_norm": 0.3498882055282593, "learning_rate": 9.583475626229219e-06, "loss": 0.2934, "step": 7461 }, { "epoch": 0.21783045305931809, "grad_norm": 0.3269921541213989, "learning_rate": 9.583272011665435e-06, "loss": 0.2315, "step": 7462 }, { "epoch": 0.21785964502568894, "grad_norm": 0.36082369089126587, "learning_rate": 9.583068349510267e-06, "loss": 0.2541, "step": 7463 }, { "epoch": 0.2178888369920598, "grad_norm": 0.33478084206581116, "learning_rate": 9.582864639765832e-06, "loss": 0.2556, "step": 7464 }, { "epoch": 0.21791802895843063, "grad_norm": 0.3201022148132324, "learning_rate": 9.582660882434243e-06, "loss": 0.2367, "step": 7465 }, { "epoch": 0.21794722092480148, "grad_norm": 0.33634403347969055, "learning_rate": 9.582457077517617e-06, "loss": 0.1936, "step": 7466 }, { "epoch": 0.21797641289117234, "grad_norm": 0.3838071823120117, "learning_rate": 9.582253225018068e-06, "loss": 0.2595, "step": 7467 }, { "epoch": 0.2180056048575432, "grad_norm": 0.32669031620025635, "learning_rate": 9.582049324937717e-06, "loss": 0.2484, "step": 7468 }, { "epoch": 0.21803479682391405, "grad_norm": 0.374697208404541, "learning_rate": 9.581845377278676e-06, "loss": 0.2869, "step": 7469 }, { "epoch": 0.2180639887902849, "grad_norm": 0.34264668822288513, "learning_rate": 9.581641382043068e-06, "loss": 0.2759, "step": 7470 }, { "epoch": 0.21809318075665576, "grad_norm": 0.33766165375709534, "learning_rate": 9.581437339233006e-06, "loss": 0.2223, "step": 7471 }, { "epoch": 0.21812237272302662, "grad_norm": 0.37979352474212646, "learning_rate": 9.581233248850614e-06, "loss": 0.2598, "step": 7472 }, { "epoch": 0.21815156468939748, "grad_norm": 0.36306408047676086, "learning_rate": 9.581029110898005e-06, "loss": 0.2319, "step": 7473 }, { "epoch": 0.21818075665576833, "grad_norm": 0.35451874136924744, "learning_rate": 9.580824925377305e-06, "loss": 0.2455, "step": 7474 }, { "epoch": 0.2182099486221392, "grad_norm": 0.36406269669532776, "learning_rate": 9.580620692290632e-06, "loss": 0.2594, "step": 7475 }, { "epoch": 0.21823914058851004, "grad_norm": 0.37029609084129333, "learning_rate": 9.580416411640105e-06, "loss": 0.2673, "step": 7476 }, { "epoch": 0.2182683325548809, "grad_norm": 0.38489314913749695, "learning_rate": 9.580212083427847e-06, "loss": 0.2384, "step": 7477 }, { "epoch": 0.21829752452125176, "grad_norm": 0.3483816981315613, "learning_rate": 9.58000770765598e-06, "loss": 0.2316, "step": 7478 }, { "epoch": 0.2183267164876226, "grad_norm": 0.33836930990219116, "learning_rate": 9.579803284326625e-06, "loss": 0.2957, "step": 7479 }, { "epoch": 0.21835590845399347, "grad_norm": 0.40562862157821655, "learning_rate": 9.579598813441904e-06, "loss": 0.2747, "step": 7480 }, { "epoch": 0.21838510042036433, "grad_norm": 0.3590954542160034, "learning_rate": 9.57939429500394e-06, "loss": 0.256, "step": 7481 }, { "epoch": 0.21841429238673518, "grad_norm": 0.35467764735221863, "learning_rate": 9.579189729014859e-06, "loss": 0.2417, "step": 7482 }, { "epoch": 0.21844348435310604, "grad_norm": 0.35200512409210205, "learning_rate": 9.578985115476784e-06, "loss": 0.2498, "step": 7483 }, { "epoch": 0.21847267631947687, "grad_norm": 0.38554656505584717, "learning_rate": 9.57878045439184e-06, "loss": 0.3018, "step": 7484 }, { "epoch": 0.21850186828584772, "grad_norm": 0.3487464487552643, "learning_rate": 9.578575745762152e-06, "loss": 0.2342, "step": 7485 }, { "epoch": 0.21853106025221858, "grad_norm": 0.2960692346096039, "learning_rate": 9.578370989589845e-06, "loss": 0.2077, "step": 7486 }, { "epoch": 0.21856025221858943, "grad_norm": 0.35586732625961304, "learning_rate": 9.578166185877045e-06, "loss": 0.2538, "step": 7487 }, { "epoch": 0.2185894441849603, "grad_norm": 0.3563401699066162, "learning_rate": 9.577961334625879e-06, "loss": 0.2818, "step": 7488 }, { "epoch": 0.21861863615133115, "grad_norm": 1.2452691793441772, "learning_rate": 9.577756435838475e-06, "loss": 0.2428, "step": 7489 }, { "epoch": 0.218647828117702, "grad_norm": 0.345257967710495, "learning_rate": 9.577551489516958e-06, "loss": 0.2261, "step": 7490 }, { "epoch": 0.21867702008407286, "grad_norm": 5.887795448303223, "learning_rate": 9.57734649566346e-06, "loss": 0.2967, "step": 7491 }, { "epoch": 0.21870621205044372, "grad_norm": 0.36200231313705444, "learning_rate": 9.577141454280108e-06, "loss": 0.2359, "step": 7492 }, { "epoch": 0.21873540401681457, "grad_norm": 0.427631676197052, "learning_rate": 9.576936365369029e-06, "loss": 0.204, "step": 7493 }, { "epoch": 0.21876459598318543, "grad_norm": 0.39393350481987, "learning_rate": 9.576731228932354e-06, "loss": 0.2294, "step": 7494 }, { "epoch": 0.21879378794955628, "grad_norm": 0.38373520970344543, "learning_rate": 9.576526044972215e-06, "loss": 0.2577, "step": 7495 }, { "epoch": 0.21882297991592714, "grad_norm": 0.33711346983909607, "learning_rate": 9.57632081349074e-06, "loss": 0.2809, "step": 7496 }, { "epoch": 0.218852171882298, "grad_norm": 0.7538163065910339, "learning_rate": 9.57611553449006e-06, "loss": 0.2609, "step": 7497 }, { "epoch": 0.21888136384866885, "grad_norm": 0.35406267642974854, "learning_rate": 9.57591020797231e-06, "loss": 0.2402, "step": 7498 }, { "epoch": 0.2189105558150397, "grad_norm": 2.6969666481018066, "learning_rate": 9.575704833939617e-06, "loss": 0.2482, "step": 7499 }, { "epoch": 0.21893974778141057, "grad_norm": 0.3272912800312042, "learning_rate": 9.575499412394115e-06, "loss": 0.2438, "step": 7500 }, { "epoch": 0.21896893974778142, "grad_norm": 0.3318590521812439, "learning_rate": 9.575293943337943e-06, "loss": 0.278, "step": 7501 }, { "epoch": 0.21899813171415228, "grad_norm": 0.3484188914299011, "learning_rate": 9.575088426773225e-06, "loss": 0.2788, "step": 7502 }, { "epoch": 0.21902732368052313, "grad_norm": 0.3488676846027374, "learning_rate": 9.574882862702103e-06, "loss": 0.2524, "step": 7503 }, { "epoch": 0.21905651564689396, "grad_norm": 0.36131778359413147, "learning_rate": 9.574677251126706e-06, "loss": 0.2993, "step": 7504 }, { "epoch": 0.21908570761326482, "grad_norm": 0.30506667494773865, "learning_rate": 9.574471592049171e-06, "loss": 0.2691, "step": 7505 }, { "epoch": 0.21911489957963567, "grad_norm": 0.3343842327594757, "learning_rate": 9.574265885471634e-06, "loss": 0.2017, "step": 7506 }, { "epoch": 0.21914409154600653, "grad_norm": 0.3187927305698395, "learning_rate": 9.574060131396233e-06, "loss": 0.1971, "step": 7507 }, { "epoch": 0.2191732835123774, "grad_norm": 0.3137190341949463, "learning_rate": 9.5738543298251e-06, "loss": 0.2564, "step": 7508 }, { "epoch": 0.21920247547874824, "grad_norm": 0.3565291464328766, "learning_rate": 9.573648480760374e-06, "loss": 0.2924, "step": 7509 }, { "epoch": 0.2192316674451191, "grad_norm": 0.31562453508377075, "learning_rate": 9.573442584204193e-06, "loss": 0.2244, "step": 7510 }, { "epoch": 0.21926085941148996, "grad_norm": 0.4296773076057434, "learning_rate": 9.573236640158696e-06, "loss": 0.2282, "step": 7511 }, { "epoch": 0.2192900513778608, "grad_norm": 0.35800814628601074, "learning_rate": 9.573030648626018e-06, "loss": 0.2685, "step": 7512 }, { "epoch": 0.21931924334423167, "grad_norm": 0.34087565541267395, "learning_rate": 9.572824609608303e-06, "loss": 0.2736, "step": 7513 }, { "epoch": 0.21934843531060252, "grad_norm": 0.3752702474594116, "learning_rate": 9.572618523107683e-06, "loss": 0.2458, "step": 7514 }, { "epoch": 0.21937762727697338, "grad_norm": 0.28354185819625854, "learning_rate": 9.572412389126307e-06, "loss": 0.2364, "step": 7515 }, { "epoch": 0.21940681924334424, "grad_norm": 0.32557910680770874, "learning_rate": 9.57220620766631e-06, "loss": 0.2343, "step": 7516 }, { "epoch": 0.2194360112097151, "grad_norm": 0.3682548403739929, "learning_rate": 9.571999978729831e-06, "loss": 0.2995, "step": 7517 }, { "epoch": 0.21946520317608595, "grad_norm": 0.3232848644256592, "learning_rate": 9.571793702319016e-06, "loss": 0.2197, "step": 7518 }, { "epoch": 0.2194943951424568, "grad_norm": 0.3491024672985077, "learning_rate": 9.571587378436007e-06, "loss": 0.2198, "step": 7519 }, { "epoch": 0.21952358710882766, "grad_norm": 0.3905539810657501, "learning_rate": 9.571381007082943e-06, "loss": 0.2548, "step": 7520 }, { "epoch": 0.21955277907519852, "grad_norm": 0.3463728427886963, "learning_rate": 9.571174588261967e-06, "loss": 0.2373, "step": 7521 }, { "epoch": 0.21958197104156937, "grad_norm": 0.3371032178401947, "learning_rate": 9.570968121975226e-06, "loss": 0.2425, "step": 7522 }, { "epoch": 0.2196111630079402, "grad_norm": 0.3465426564216614, "learning_rate": 9.57076160822486e-06, "loss": 0.268, "step": 7523 }, { "epoch": 0.21964035497431106, "grad_norm": 0.346919447183609, "learning_rate": 9.570555047013017e-06, "loss": 0.2739, "step": 7524 }, { "epoch": 0.21966954694068191, "grad_norm": 0.3521059453487396, "learning_rate": 9.570348438341839e-06, "loss": 0.2687, "step": 7525 }, { "epoch": 0.21969873890705277, "grad_norm": 0.31137076020240784, "learning_rate": 9.570141782213472e-06, "loss": 0.27, "step": 7526 }, { "epoch": 0.21972793087342363, "grad_norm": 0.3110334575176239, "learning_rate": 9.569935078630062e-06, "loss": 0.2127, "step": 7527 }, { "epoch": 0.21975712283979448, "grad_norm": 0.3718216121196747, "learning_rate": 9.569728327593757e-06, "loss": 0.21, "step": 7528 }, { "epoch": 0.21978631480616534, "grad_norm": 0.2919258773326874, "learning_rate": 9.5695215291067e-06, "loss": 0.2064, "step": 7529 }, { "epoch": 0.2198155067725362, "grad_norm": 0.35875824093818665, "learning_rate": 9.569314683171044e-06, "loss": 0.2918, "step": 7530 }, { "epoch": 0.21984469873890705, "grad_norm": 0.32135632634162903, "learning_rate": 9.569107789788931e-06, "loss": 0.219, "step": 7531 }, { "epoch": 0.2198738907052779, "grad_norm": 0.31267619132995605, "learning_rate": 9.568900848962513e-06, "loss": 0.2333, "step": 7532 }, { "epoch": 0.21990308267164876, "grad_norm": 0.350522518157959, "learning_rate": 9.568693860693938e-06, "loss": 0.2669, "step": 7533 }, { "epoch": 0.21993227463801962, "grad_norm": 0.3671213984489441, "learning_rate": 9.568486824985354e-06, "loss": 0.2457, "step": 7534 }, { "epoch": 0.21996146660439048, "grad_norm": 0.3329993486404419, "learning_rate": 9.568279741838913e-06, "loss": 0.267, "step": 7535 }, { "epoch": 0.21999065857076133, "grad_norm": 0.3153631091117859, "learning_rate": 9.568072611256763e-06, "loss": 0.2603, "step": 7536 }, { "epoch": 0.2200198505371322, "grad_norm": 0.3380701541900635, "learning_rate": 9.567865433241057e-06, "loss": 0.2683, "step": 7537 }, { "epoch": 0.22004904250350305, "grad_norm": 0.7680970430374146, "learning_rate": 9.567658207793945e-06, "loss": 0.2797, "step": 7538 }, { "epoch": 0.2200782344698739, "grad_norm": 0.3247202932834625, "learning_rate": 9.567450934917578e-06, "loss": 0.2346, "step": 7539 }, { "epoch": 0.22010742643624476, "grad_norm": 0.3671671748161316, "learning_rate": 9.56724361461411e-06, "loss": 0.3099, "step": 7540 }, { "epoch": 0.2201366184026156, "grad_norm": 0.38475096225738525, "learning_rate": 9.567036246885693e-06, "loss": 0.3243, "step": 7541 }, { "epoch": 0.22016581036898644, "grad_norm": 0.3545600473880768, "learning_rate": 9.56682883173448e-06, "loss": 0.2788, "step": 7542 }, { "epoch": 0.2201950023353573, "grad_norm": 0.3433000445365906, "learning_rate": 9.566621369162623e-06, "loss": 0.2346, "step": 7543 }, { "epoch": 0.22022419430172815, "grad_norm": 0.3389420211315155, "learning_rate": 9.56641385917228e-06, "loss": 0.2592, "step": 7544 }, { "epoch": 0.220253386268099, "grad_norm": 0.33258986473083496, "learning_rate": 9.566206301765606e-06, "loss": 0.2679, "step": 7545 }, { "epoch": 0.22028257823446987, "grad_norm": 0.36015504598617554, "learning_rate": 9.56599869694475e-06, "loss": 0.2251, "step": 7546 }, { "epoch": 0.22031177020084072, "grad_norm": 0.3436717689037323, "learning_rate": 9.565791044711875e-06, "loss": 0.2688, "step": 7547 }, { "epoch": 0.22034096216721158, "grad_norm": 0.33165428042411804, "learning_rate": 9.565583345069134e-06, "loss": 0.2681, "step": 7548 }, { "epoch": 0.22037015413358244, "grad_norm": 0.3274027109146118, "learning_rate": 9.565375598018683e-06, "loss": 0.2686, "step": 7549 }, { "epoch": 0.2203993460999533, "grad_norm": 0.3658014237880707, "learning_rate": 9.565167803562679e-06, "loss": 0.2633, "step": 7550 }, { "epoch": 0.22042853806632415, "grad_norm": 0.31864041090011597, "learning_rate": 9.56495996170328e-06, "loss": 0.2009, "step": 7551 }, { "epoch": 0.220457730032695, "grad_norm": 0.36464089155197144, "learning_rate": 9.564752072442648e-06, "loss": 0.2279, "step": 7552 }, { "epoch": 0.22048692199906586, "grad_norm": 0.480448454618454, "learning_rate": 9.564544135782936e-06, "loss": 0.3051, "step": 7553 }, { "epoch": 0.22051611396543672, "grad_norm": 0.3292026221752167, "learning_rate": 9.564336151726306e-06, "loss": 0.2115, "step": 7554 }, { "epoch": 0.22054530593180757, "grad_norm": 0.3540532886981964, "learning_rate": 9.564128120274916e-06, "loss": 0.2367, "step": 7555 }, { "epoch": 0.22057449789817843, "grad_norm": 0.36718693375587463, "learning_rate": 9.563920041430929e-06, "loss": 0.2546, "step": 7556 }, { "epoch": 0.22060368986454928, "grad_norm": 0.3476053476333618, "learning_rate": 9.563711915196504e-06, "loss": 0.28, "step": 7557 }, { "epoch": 0.22063288183092014, "grad_norm": 0.31679514050483704, "learning_rate": 9.5635037415738e-06, "loss": 0.245, "step": 7558 }, { "epoch": 0.220662073797291, "grad_norm": 0.33671948313713074, "learning_rate": 9.563295520564984e-06, "loss": 0.244, "step": 7559 }, { "epoch": 0.22069126576366185, "grad_norm": 0.33706238865852356, "learning_rate": 9.563087252172214e-06, "loss": 0.2557, "step": 7560 }, { "epoch": 0.22072045773003268, "grad_norm": 0.3328551650047302, "learning_rate": 9.562878936397653e-06, "loss": 0.2083, "step": 7561 }, { "epoch": 0.22074964969640354, "grad_norm": 0.34999340772628784, "learning_rate": 9.562670573243462e-06, "loss": 0.2714, "step": 7562 }, { "epoch": 0.2207788416627744, "grad_norm": 0.32640567421913147, "learning_rate": 9.56246216271181e-06, "loss": 0.2482, "step": 7563 }, { "epoch": 0.22080803362914525, "grad_norm": 0.36899054050445557, "learning_rate": 9.562253704804858e-06, "loss": 0.2317, "step": 7564 }, { "epoch": 0.2208372255955161, "grad_norm": 0.3621792495250702, "learning_rate": 9.56204519952477e-06, "loss": 0.2515, "step": 7565 }, { "epoch": 0.22086641756188696, "grad_norm": 0.43826165795326233, "learning_rate": 9.561836646873713e-06, "loss": 0.2546, "step": 7566 }, { "epoch": 0.22089560952825782, "grad_norm": 0.32353514432907104, "learning_rate": 9.561628046853851e-06, "loss": 0.2752, "step": 7567 }, { "epoch": 0.22092480149462868, "grad_norm": 0.35140877962112427, "learning_rate": 9.561419399467348e-06, "loss": 0.2668, "step": 7568 }, { "epoch": 0.22095399346099953, "grad_norm": 0.3151058554649353, "learning_rate": 9.561210704716375e-06, "loss": 0.2529, "step": 7569 }, { "epoch": 0.2209831854273704, "grad_norm": 0.3508627414703369, "learning_rate": 9.561001962603098e-06, "loss": 0.2812, "step": 7570 }, { "epoch": 0.22101237739374124, "grad_norm": 0.5261040329933167, "learning_rate": 9.560793173129681e-06, "loss": 0.2555, "step": 7571 }, { "epoch": 0.2210415693601121, "grad_norm": 0.43122318387031555, "learning_rate": 9.560584336298298e-06, "loss": 0.2198, "step": 7572 }, { "epoch": 0.22107076132648296, "grad_norm": 0.3541078269481659, "learning_rate": 9.56037545211111e-06, "loss": 0.2963, "step": 7573 }, { "epoch": 0.2210999532928538, "grad_norm": 0.2998630702495575, "learning_rate": 9.560166520570294e-06, "loss": 0.1954, "step": 7574 }, { "epoch": 0.22112914525922467, "grad_norm": 0.3162672817707062, "learning_rate": 9.559957541678011e-06, "loss": 0.2659, "step": 7575 }, { "epoch": 0.22115833722559552, "grad_norm": 0.36361515522003174, "learning_rate": 9.559748515436437e-06, "loss": 0.215, "step": 7576 }, { "epoch": 0.22118752919196638, "grad_norm": 0.3996107876300812, "learning_rate": 9.559539441847743e-06, "loss": 0.2297, "step": 7577 }, { "epoch": 0.22121672115833724, "grad_norm": 0.3291932940483093, "learning_rate": 9.559330320914098e-06, "loss": 0.2408, "step": 7578 }, { "epoch": 0.2212459131247081, "grad_norm": 0.3635397255420685, "learning_rate": 9.559121152637672e-06, "loss": 0.302, "step": 7579 }, { "epoch": 0.22127510509107892, "grad_norm": 0.32613739371299744, "learning_rate": 9.558911937020636e-06, "loss": 0.2764, "step": 7580 }, { "epoch": 0.22130429705744978, "grad_norm": 0.32921984791755676, "learning_rate": 9.558702674065168e-06, "loss": 0.2126, "step": 7581 }, { "epoch": 0.22133348902382063, "grad_norm": 0.37666401267051697, "learning_rate": 9.558493363773435e-06, "loss": 0.253, "step": 7582 }, { "epoch": 0.2213626809901915, "grad_norm": 0.32850396633148193, "learning_rate": 9.558284006147615e-06, "loss": 0.2221, "step": 7583 }, { "epoch": 0.22139187295656235, "grad_norm": 0.3096311688423157, "learning_rate": 9.55807460118988e-06, "loss": 0.2161, "step": 7584 }, { "epoch": 0.2214210649229332, "grad_norm": 0.311306893825531, "learning_rate": 9.557865148902405e-06, "loss": 0.1956, "step": 7585 }, { "epoch": 0.22145025688930406, "grad_norm": 0.4157552421092987, "learning_rate": 9.557655649287363e-06, "loss": 0.292, "step": 7586 }, { "epoch": 0.22147944885567492, "grad_norm": 0.36193758249282837, "learning_rate": 9.55744610234693e-06, "loss": 0.2573, "step": 7587 }, { "epoch": 0.22150864082204577, "grad_norm": 0.36226794123649597, "learning_rate": 9.557236508083283e-06, "loss": 0.2151, "step": 7588 }, { "epoch": 0.22153783278841663, "grad_norm": 0.3872903287410736, "learning_rate": 9.557026866498599e-06, "loss": 0.2846, "step": 7589 }, { "epoch": 0.22156702475478748, "grad_norm": 0.33984851837158203, "learning_rate": 9.556817177595053e-06, "loss": 0.2684, "step": 7590 }, { "epoch": 0.22159621672115834, "grad_norm": 0.34627655148506165, "learning_rate": 9.556607441374823e-06, "loss": 0.2551, "step": 7591 }, { "epoch": 0.2216254086875292, "grad_norm": 0.9978604912757874, "learning_rate": 9.556397657840089e-06, "loss": 0.2227, "step": 7592 }, { "epoch": 0.22165460065390005, "grad_norm": 0.31951791048049927, "learning_rate": 9.556187826993025e-06, "loss": 0.2374, "step": 7593 }, { "epoch": 0.2216837926202709, "grad_norm": 0.2959618866443634, "learning_rate": 9.555977948835811e-06, "loss": 0.1941, "step": 7594 }, { "epoch": 0.22171298458664176, "grad_norm": 0.35268887877464294, "learning_rate": 9.55576802337063e-06, "loss": 0.2706, "step": 7595 }, { "epoch": 0.22174217655301262, "grad_norm": 0.31316179037094116, "learning_rate": 9.555558050599658e-06, "loss": 0.211, "step": 7596 }, { "epoch": 0.22177136851938348, "grad_norm": 0.32090049982070923, "learning_rate": 9.555348030525076e-06, "loss": 0.2508, "step": 7597 }, { "epoch": 0.22180056048575433, "grad_norm": 0.31122568249702454, "learning_rate": 9.555137963149066e-06, "loss": 0.1707, "step": 7598 }, { "epoch": 0.22182975245212516, "grad_norm": 0.3579767346382141, "learning_rate": 9.554927848473809e-06, "loss": 0.2166, "step": 7599 }, { "epoch": 0.22185894441849602, "grad_norm": 0.33043375611305237, "learning_rate": 9.554717686501486e-06, "loss": 0.2499, "step": 7600 }, { "epoch": 0.22188813638486687, "grad_norm": 0.37640535831451416, "learning_rate": 9.554507477234279e-06, "loss": 0.2764, "step": 7601 }, { "epoch": 0.22191732835123773, "grad_norm": 0.4602411687374115, "learning_rate": 9.554297220674371e-06, "loss": 0.2523, "step": 7602 }, { "epoch": 0.2219465203176086, "grad_norm": 0.3345274329185486, "learning_rate": 9.554086916823946e-06, "loss": 0.2813, "step": 7603 }, { "epoch": 0.22197571228397944, "grad_norm": 0.32089683413505554, "learning_rate": 9.55387656568519e-06, "loss": 0.269, "step": 7604 }, { "epoch": 0.2220049042503503, "grad_norm": 0.36306166648864746, "learning_rate": 9.55366616726028e-06, "loss": 0.2497, "step": 7605 }, { "epoch": 0.22203409621672116, "grad_norm": 0.32916370034217834, "learning_rate": 9.553455721551409e-06, "loss": 0.2393, "step": 7606 }, { "epoch": 0.222063288183092, "grad_norm": 0.3309694826602936, "learning_rate": 9.553245228560757e-06, "loss": 0.1827, "step": 7607 }, { "epoch": 0.22209248014946287, "grad_norm": 0.36204594373703003, "learning_rate": 9.553034688290512e-06, "loss": 0.2393, "step": 7608 }, { "epoch": 0.22212167211583372, "grad_norm": 0.3702116012573242, "learning_rate": 9.552824100742858e-06, "loss": 0.2621, "step": 7609 }, { "epoch": 0.22215086408220458, "grad_norm": 0.35287243127822876, "learning_rate": 9.552613465919984e-06, "loss": 0.2442, "step": 7610 }, { "epoch": 0.22218005604857544, "grad_norm": 0.3484584391117096, "learning_rate": 9.552402783824076e-06, "loss": 0.2373, "step": 7611 }, { "epoch": 0.2222092480149463, "grad_norm": 0.31712397933006287, "learning_rate": 9.552192054457322e-06, "loss": 0.2226, "step": 7612 }, { "epoch": 0.22223843998131715, "grad_norm": 0.3430194556713104, "learning_rate": 9.55198127782191e-06, "loss": 0.2545, "step": 7613 }, { "epoch": 0.222267631947688, "grad_norm": 0.3789754807949066, "learning_rate": 9.551770453920029e-06, "loss": 0.32, "step": 7614 }, { "epoch": 0.22229682391405886, "grad_norm": 0.34717294573783875, "learning_rate": 9.551559582753866e-06, "loss": 0.2163, "step": 7615 }, { "epoch": 0.22232601588042972, "grad_norm": 0.3774245083332062, "learning_rate": 9.551348664325615e-06, "loss": 0.2174, "step": 7616 }, { "epoch": 0.22235520784680057, "grad_norm": 0.36093592643737793, "learning_rate": 9.551137698637463e-06, "loss": 0.2619, "step": 7617 }, { "epoch": 0.2223843998131714, "grad_norm": 0.38006141781806946, "learning_rate": 9.550926685691599e-06, "loss": 0.316, "step": 7618 }, { "epoch": 0.22241359177954226, "grad_norm": 0.7049009203910828, "learning_rate": 9.550715625490219e-06, "loss": 0.2109, "step": 7619 }, { "epoch": 0.22244278374591311, "grad_norm": 0.3155277669429779, "learning_rate": 9.55050451803551e-06, "loss": 0.2547, "step": 7620 }, { "epoch": 0.22247197571228397, "grad_norm": 0.3319212794303894, "learning_rate": 9.550293363329668e-06, "loss": 0.2543, "step": 7621 }, { "epoch": 0.22250116767865483, "grad_norm": 0.3572867810726166, "learning_rate": 9.550082161374883e-06, "loss": 0.2407, "step": 7622 }, { "epoch": 0.22253035964502568, "grad_norm": 0.27678459882736206, "learning_rate": 9.549870912173346e-06, "loss": 0.2114, "step": 7623 }, { "epoch": 0.22255955161139654, "grad_norm": 0.3154875934123993, "learning_rate": 9.549659615727256e-06, "loss": 0.2276, "step": 7624 }, { "epoch": 0.2225887435777674, "grad_norm": 0.36643800139427185, "learning_rate": 9.549448272038804e-06, "loss": 0.2923, "step": 7625 }, { "epoch": 0.22261793554413825, "grad_norm": 0.3276243507862091, "learning_rate": 9.549236881110184e-06, "loss": 0.2195, "step": 7626 }, { "epoch": 0.2226471275105091, "grad_norm": 0.3293069303035736, "learning_rate": 9.54902544294359e-06, "loss": 0.2309, "step": 7627 }, { "epoch": 0.22267631947687996, "grad_norm": 0.3957381248474121, "learning_rate": 9.548813957541222e-06, "loss": 0.2943, "step": 7628 }, { "epoch": 0.22270551144325082, "grad_norm": 0.3383151888847351, "learning_rate": 9.548602424905271e-06, "loss": 0.2441, "step": 7629 }, { "epoch": 0.22273470340962168, "grad_norm": 0.40846943855285645, "learning_rate": 9.548390845037938e-06, "loss": 0.205, "step": 7630 }, { "epoch": 0.22276389537599253, "grad_norm": 0.518121063709259, "learning_rate": 9.548179217941415e-06, "loss": 0.2944, "step": 7631 }, { "epoch": 0.2227930873423634, "grad_norm": 0.4793962240219116, "learning_rate": 9.547967543617906e-06, "loss": 0.2565, "step": 7632 }, { "epoch": 0.22282227930873424, "grad_norm": 0.4012224078178406, "learning_rate": 9.547755822069603e-06, "loss": 0.2609, "step": 7633 }, { "epoch": 0.2228514712751051, "grad_norm": 0.3413980007171631, "learning_rate": 9.547544053298705e-06, "loss": 0.2556, "step": 7634 }, { "epoch": 0.22288066324147596, "grad_norm": 0.3405749797821045, "learning_rate": 9.547332237307414e-06, "loss": 0.2554, "step": 7635 }, { "epoch": 0.2229098552078468, "grad_norm": 0.3419049382209778, "learning_rate": 9.547120374097929e-06, "loss": 0.2204, "step": 7636 }, { "epoch": 0.22293904717421764, "grad_norm": 0.3698585033416748, "learning_rate": 9.54690846367245e-06, "loss": 0.2619, "step": 7637 }, { "epoch": 0.2229682391405885, "grad_norm": 0.33711129426956177, "learning_rate": 9.546696506033173e-06, "loss": 0.2473, "step": 7638 }, { "epoch": 0.22299743110695935, "grad_norm": 0.3698928654193878, "learning_rate": 9.546484501182302e-06, "loss": 0.286, "step": 7639 }, { "epoch": 0.2230266230733302, "grad_norm": 0.3677555024623871, "learning_rate": 9.546272449122041e-06, "loss": 0.2274, "step": 7640 }, { "epoch": 0.22305581503970107, "grad_norm": 0.36271932721138, "learning_rate": 9.54606034985459e-06, "loss": 0.2629, "step": 7641 }, { "epoch": 0.22308500700607192, "grad_norm": 0.31625235080718994, "learning_rate": 9.545848203382149e-06, "loss": 0.2408, "step": 7642 }, { "epoch": 0.22311419897244278, "grad_norm": 0.31603702902793884, "learning_rate": 9.545636009706924e-06, "loss": 0.2614, "step": 7643 }, { "epoch": 0.22314339093881363, "grad_norm": 0.3485662639141083, "learning_rate": 9.545423768831116e-06, "loss": 0.2438, "step": 7644 }, { "epoch": 0.2231725829051845, "grad_norm": 0.3625990152359009, "learning_rate": 9.54521148075693e-06, "loss": 0.2548, "step": 7645 }, { "epoch": 0.22320177487155535, "grad_norm": 0.3063869774341583, "learning_rate": 9.544999145486572e-06, "loss": 0.2116, "step": 7646 }, { "epoch": 0.2232309668379262, "grad_norm": 0.371905118227005, "learning_rate": 9.544786763022245e-06, "loss": 0.2771, "step": 7647 }, { "epoch": 0.22326015880429706, "grad_norm": 0.38515135645866394, "learning_rate": 9.544574333366153e-06, "loss": 0.2488, "step": 7648 }, { "epoch": 0.22328935077066792, "grad_norm": 0.31971830129623413, "learning_rate": 9.544361856520504e-06, "loss": 0.2643, "step": 7649 }, { "epoch": 0.22331854273703877, "grad_norm": 0.33919236063957214, "learning_rate": 9.544149332487503e-06, "loss": 0.245, "step": 7650 }, { "epoch": 0.22334773470340963, "grad_norm": 0.3395634591579437, "learning_rate": 9.543936761269357e-06, "loss": 0.2502, "step": 7651 }, { "epoch": 0.22337692666978048, "grad_norm": 0.41533133387565613, "learning_rate": 9.543724142868275e-06, "loss": 0.2485, "step": 7652 }, { "epoch": 0.22340611863615134, "grad_norm": 0.3743550479412079, "learning_rate": 9.543511477286463e-06, "loss": 0.3172, "step": 7653 }, { "epoch": 0.2234353106025222, "grad_norm": 0.30264681577682495, "learning_rate": 9.54329876452613e-06, "loss": 0.2182, "step": 7654 }, { "epoch": 0.22346450256889305, "grad_norm": 0.3436886966228485, "learning_rate": 9.543086004589484e-06, "loss": 0.2928, "step": 7655 }, { "epoch": 0.22349369453526388, "grad_norm": 0.36529549956321716, "learning_rate": 9.542873197478734e-06, "loss": 0.2379, "step": 7656 }, { "epoch": 0.22352288650163474, "grad_norm": 0.370809406042099, "learning_rate": 9.542660343196093e-06, "loss": 0.2867, "step": 7657 }, { "epoch": 0.2235520784680056, "grad_norm": 0.3355494439601898, "learning_rate": 9.542447441743764e-06, "loss": 0.2725, "step": 7658 }, { "epoch": 0.22358127043437645, "grad_norm": 0.31975898146629333, "learning_rate": 9.542234493123967e-06, "loss": 0.2474, "step": 7659 }, { "epoch": 0.2236104624007473, "grad_norm": 0.3338335156440735, "learning_rate": 9.542021497338907e-06, "loss": 0.2006, "step": 7660 }, { "epoch": 0.22363965436711816, "grad_norm": 0.4407750964164734, "learning_rate": 9.541808454390797e-06, "loss": 0.2434, "step": 7661 }, { "epoch": 0.22366884633348902, "grad_norm": 0.5289799571037292, "learning_rate": 9.541595364281848e-06, "loss": 0.2404, "step": 7662 }, { "epoch": 0.22369803829985987, "grad_norm": 0.38242438435554504, "learning_rate": 9.541382227014275e-06, "loss": 0.2935, "step": 7663 }, { "epoch": 0.22372723026623073, "grad_norm": 0.3440239727497101, "learning_rate": 9.541169042590292e-06, "loss": 0.2248, "step": 7664 }, { "epoch": 0.2237564222326016, "grad_norm": 0.3743947446346283, "learning_rate": 9.54095581101211e-06, "loss": 0.2281, "step": 7665 }, { "epoch": 0.22378561419897244, "grad_norm": 0.323598176240921, "learning_rate": 9.540742532281941e-06, "loss": 0.2455, "step": 7666 }, { "epoch": 0.2238148061653433, "grad_norm": 0.3234040141105652, "learning_rate": 9.540529206402004e-06, "loss": 0.2481, "step": 7667 }, { "epoch": 0.22384399813171416, "grad_norm": 0.37750154733657837, "learning_rate": 9.540315833374516e-06, "loss": 0.2552, "step": 7668 }, { "epoch": 0.223873190098085, "grad_norm": 0.3062644302845001, "learning_rate": 9.540102413201687e-06, "loss": 0.2311, "step": 7669 }, { "epoch": 0.22390238206445587, "grad_norm": 0.30624765157699585, "learning_rate": 9.539888945885735e-06, "loss": 0.2105, "step": 7670 }, { "epoch": 0.22393157403082672, "grad_norm": 0.3659078776836395, "learning_rate": 9.539675431428877e-06, "loss": 0.2657, "step": 7671 }, { "epoch": 0.22396076599719758, "grad_norm": 0.3572016656398773, "learning_rate": 9.53946186983333e-06, "loss": 0.2355, "step": 7672 }, { "epoch": 0.22398995796356844, "grad_norm": 0.30740082263946533, "learning_rate": 9.539248261101312e-06, "loss": 0.2396, "step": 7673 }, { "epoch": 0.2240191499299393, "grad_norm": 0.3508795499801636, "learning_rate": 9.539034605235042e-06, "loss": 0.2516, "step": 7674 }, { "epoch": 0.22404834189631015, "grad_norm": 0.30927178263664246, "learning_rate": 9.538820902236735e-06, "loss": 0.2386, "step": 7675 }, { "epoch": 0.22407753386268098, "grad_norm": 0.3251926302909851, "learning_rate": 9.538607152108613e-06, "loss": 0.2409, "step": 7676 }, { "epoch": 0.22410672582905183, "grad_norm": 0.2951952815055847, "learning_rate": 9.538393354852896e-06, "loss": 0.248, "step": 7677 }, { "epoch": 0.2241359177954227, "grad_norm": 0.35633477568626404, "learning_rate": 9.5381795104718e-06, "loss": 0.3231, "step": 7678 }, { "epoch": 0.22416510976179355, "grad_norm": 0.3500309884548187, "learning_rate": 9.537965618967551e-06, "loss": 0.2563, "step": 7679 }, { "epoch": 0.2241943017281644, "grad_norm": 0.3517718017101288, "learning_rate": 9.537751680342367e-06, "loss": 0.3389, "step": 7680 }, { "epoch": 0.22422349369453526, "grad_norm": 0.3887028992176056, "learning_rate": 9.537537694598468e-06, "loss": 0.2521, "step": 7681 }, { "epoch": 0.22425268566090611, "grad_norm": 0.34919124841690063, "learning_rate": 9.53732366173808e-06, "loss": 0.2994, "step": 7682 }, { "epoch": 0.22428187762727697, "grad_norm": 0.3355570137500763, "learning_rate": 9.537109581763421e-06, "loss": 0.1954, "step": 7683 }, { "epoch": 0.22431106959364783, "grad_norm": 0.35609740018844604, "learning_rate": 9.536895454676718e-06, "loss": 0.2294, "step": 7684 }, { "epoch": 0.22434026156001868, "grad_norm": 0.3300478458404541, "learning_rate": 9.536681280480193e-06, "loss": 0.2686, "step": 7685 }, { "epoch": 0.22436945352638954, "grad_norm": 0.3203061521053314, "learning_rate": 9.536467059176067e-06, "loss": 0.2531, "step": 7686 }, { "epoch": 0.2243986454927604, "grad_norm": 0.30423951148986816, "learning_rate": 9.536252790766569e-06, "loss": 0.2166, "step": 7687 }, { "epoch": 0.22442783745913125, "grad_norm": 0.3736148476600647, "learning_rate": 9.53603847525392e-06, "loss": 0.2502, "step": 7688 }, { "epoch": 0.2244570294255021, "grad_norm": 0.35271134972572327, "learning_rate": 9.535824112640349e-06, "loss": 0.2331, "step": 7689 }, { "epoch": 0.22448622139187296, "grad_norm": 0.33921492099761963, "learning_rate": 9.53560970292808e-06, "loss": 0.2603, "step": 7690 }, { "epoch": 0.22451541335824382, "grad_norm": 0.3474528193473816, "learning_rate": 9.535395246119338e-06, "loss": 0.2413, "step": 7691 }, { "epoch": 0.22454460532461468, "grad_norm": 0.3479418158531189, "learning_rate": 9.535180742216352e-06, "loss": 0.2423, "step": 7692 }, { "epoch": 0.22457379729098553, "grad_norm": 0.36306464672088623, "learning_rate": 9.534966191221348e-06, "loss": 0.2722, "step": 7693 }, { "epoch": 0.2246029892573564, "grad_norm": 0.3215900957584381, "learning_rate": 9.534751593136556e-06, "loss": 0.2293, "step": 7694 }, { "epoch": 0.22463218122372722, "grad_norm": 0.33909326791763306, "learning_rate": 9.5345369479642e-06, "loss": 0.2359, "step": 7695 }, { "epoch": 0.22466137319009807, "grad_norm": 0.3941580653190613, "learning_rate": 9.534322255706514e-06, "loss": 0.2874, "step": 7696 }, { "epoch": 0.22469056515646893, "grad_norm": 0.3443453311920166, "learning_rate": 9.534107516365725e-06, "loss": 0.2289, "step": 7697 }, { "epoch": 0.22471975712283979, "grad_norm": 0.31380510330200195, "learning_rate": 9.533892729944063e-06, "loss": 0.2184, "step": 7698 }, { "epoch": 0.22474894908921064, "grad_norm": 0.35102933645248413, "learning_rate": 9.533677896443756e-06, "loss": 0.2407, "step": 7699 }, { "epoch": 0.2247781410555815, "grad_norm": 0.31940072774887085, "learning_rate": 9.533463015867038e-06, "loss": 0.271, "step": 7700 }, { "epoch": 0.22480733302195235, "grad_norm": 0.3236786127090454, "learning_rate": 9.533248088216139e-06, "loss": 0.2553, "step": 7701 }, { "epoch": 0.2248365249883232, "grad_norm": 0.3329913914203644, "learning_rate": 9.533033113493291e-06, "loss": 0.2281, "step": 7702 }, { "epoch": 0.22486571695469407, "grad_norm": 0.32591110467910767, "learning_rate": 9.532818091700726e-06, "loss": 0.2413, "step": 7703 }, { "epoch": 0.22489490892106492, "grad_norm": 0.32605794072151184, "learning_rate": 9.532603022840676e-06, "loss": 0.2127, "step": 7704 }, { "epoch": 0.22492410088743578, "grad_norm": 0.339739054441452, "learning_rate": 9.532387906915376e-06, "loss": 0.2625, "step": 7705 }, { "epoch": 0.22495329285380664, "grad_norm": 0.3256422281265259, "learning_rate": 9.532172743927057e-06, "loss": 0.2243, "step": 7706 }, { "epoch": 0.2249824848201775, "grad_norm": 0.296457439661026, "learning_rate": 9.531957533877957e-06, "loss": 0.2208, "step": 7707 }, { "epoch": 0.22501167678654835, "grad_norm": 0.3198815584182739, "learning_rate": 9.531742276770306e-06, "loss": 0.2123, "step": 7708 }, { "epoch": 0.2250408687529192, "grad_norm": 0.3810249865055084, "learning_rate": 9.531526972606344e-06, "loss": 0.2795, "step": 7709 }, { "epoch": 0.22507006071929006, "grad_norm": 0.3807614743709564, "learning_rate": 9.531311621388305e-06, "loss": 0.2329, "step": 7710 }, { "epoch": 0.22509925268566092, "grad_norm": 0.3014737665653229, "learning_rate": 9.53109622311842e-06, "loss": 0.1972, "step": 7711 }, { "epoch": 0.22512844465203177, "grad_norm": 0.33069008588790894, "learning_rate": 9.530880777798935e-06, "loss": 0.2201, "step": 7712 }, { "epoch": 0.22515763661840263, "grad_norm": 0.3404880464076996, "learning_rate": 9.53066528543208e-06, "loss": 0.2785, "step": 7713 }, { "epoch": 0.22518682858477346, "grad_norm": 0.3772502541542053, "learning_rate": 9.530449746020094e-06, "loss": 0.22, "step": 7714 }, { "epoch": 0.2252160205511443, "grad_norm": 0.33905184268951416, "learning_rate": 9.530234159565219e-06, "loss": 0.2156, "step": 7715 }, { "epoch": 0.22524521251751517, "grad_norm": 0.32539281249046326, "learning_rate": 9.530018526069688e-06, "loss": 0.2315, "step": 7716 }, { "epoch": 0.22527440448388603, "grad_norm": 0.38882148265838623, "learning_rate": 9.529802845535742e-06, "loss": 0.2415, "step": 7717 }, { "epoch": 0.22530359645025688, "grad_norm": 0.350240021944046, "learning_rate": 9.529587117965623e-06, "loss": 0.2229, "step": 7718 }, { "epoch": 0.22533278841662774, "grad_norm": 0.3017672598361969, "learning_rate": 9.52937134336157e-06, "loss": 0.2391, "step": 7719 }, { "epoch": 0.2253619803829986, "grad_norm": 0.37984809279441833, "learning_rate": 9.529155521725821e-06, "loss": 0.2505, "step": 7720 }, { "epoch": 0.22539117234936945, "grad_norm": 0.32720059156417847, "learning_rate": 9.528939653060618e-06, "loss": 0.2311, "step": 7721 }, { "epoch": 0.2254203643157403, "grad_norm": 0.45162442326545715, "learning_rate": 9.528723737368205e-06, "loss": 0.2919, "step": 7722 }, { "epoch": 0.22544955628211116, "grad_norm": 0.31079837679862976, "learning_rate": 9.528507774650822e-06, "loss": 0.2153, "step": 7723 }, { "epoch": 0.22547874824848202, "grad_norm": 0.31855136156082153, "learning_rate": 9.528291764910711e-06, "loss": 0.2548, "step": 7724 }, { "epoch": 0.22550794021485288, "grad_norm": 0.3188813626766205, "learning_rate": 9.528075708150118e-06, "loss": 0.2472, "step": 7725 }, { "epoch": 0.22553713218122373, "grad_norm": 0.30143362283706665, "learning_rate": 9.527859604371283e-06, "loss": 0.2389, "step": 7726 }, { "epoch": 0.2255663241475946, "grad_norm": 0.33439624309539795, "learning_rate": 9.52764345357645e-06, "loss": 0.2718, "step": 7727 }, { "epoch": 0.22559551611396544, "grad_norm": 0.32927465438842773, "learning_rate": 9.527427255767867e-06, "loss": 0.2297, "step": 7728 }, { "epoch": 0.2256247080803363, "grad_norm": 0.3616590201854706, "learning_rate": 9.527211010947775e-06, "loss": 0.2598, "step": 7729 }, { "epoch": 0.22565390004670716, "grad_norm": 0.3087165057659149, "learning_rate": 9.526994719118422e-06, "loss": 0.2251, "step": 7730 }, { "epoch": 0.225683092013078, "grad_norm": 0.35319891571998596, "learning_rate": 9.526778380282052e-06, "loss": 0.2762, "step": 7731 }, { "epoch": 0.22571228397944887, "grad_norm": 0.32760027050971985, "learning_rate": 9.526561994440913e-06, "loss": 0.2395, "step": 7732 }, { "epoch": 0.2257414759458197, "grad_norm": 0.3367574214935303, "learning_rate": 9.52634556159725e-06, "loss": 0.2252, "step": 7733 }, { "epoch": 0.22577066791219055, "grad_norm": 0.32119956612586975, "learning_rate": 9.526129081753312e-06, "loss": 0.2376, "step": 7734 }, { "epoch": 0.2257998598785614, "grad_norm": 0.3291226625442505, "learning_rate": 9.52591255491135e-06, "loss": 0.2458, "step": 7735 }, { "epoch": 0.22582905184493227, "grad_norm": 0.3976910412311554, "learning_rate": 9.525695981073604e-06, "loss": 0.2305, "step": 7736 }, { "epoch": 0.22585824381130312, "grad_norm": 0.3270459473133087, "learning_rate": 9.52547936024233e-06, "loss": 0.2369, "step": 7737 }, { "epoch": 0.22588743577767398, "grad_norm": 0.31854385137557983, "learning_rate": 9.525262692419774e-06, "loss": 0.2641, "step": 7738 }, { "epoch": 0.22591662774404483, "grad_norm": 0.3430456221103668, "learning_rate": 9.525045977608188e-06, "loss": 0.233, "step": 7739 }, { "epoch": 0.2259458197104157, "grad_norm": 0.35506266355514526, "learning_rate": 9.52482921580982e-06, "loss": 0.2554, "step": 7740 }, { "epoch": 0.22597501167678655, "grad_norm": 0.35559016466140747, "learning_rate": 9.524612407026924e-06, "loss": 0.2545, "step": 7741 }, { "epoch": 0.2260042036431574, "grad_norm": 0.3264683485031128, "learning_rate": 9.524395551261747e-06, "loss": 0.2203, "step": 7742 }, { "epoch": 0.22603339560952826, "grad_norm": 0.3798953592777252, "learning_rate": 9.524178648516545e-06, "loss": 0.2665, "step": 7743 }, { "epoch": 0.22606258757589912, "grad_norm": 0.5273901224136353, "learning_rate": 9.523961698793566e-06, "loss": 0.2568, "step": 7744 }, { "epoch": 0.22609177954226997, "grad_norm": 0.30898478627204895, "learning_rate": 9.523744702095066e-06, "loss": 0.2287, "step": 7745 }, { "epoch": 0.22612097150864083, "grad_norm": 0.4352670907974243, "learning_rate": 9.523527658423298e-06, "loss": 0.2359, "step": 7746 }, { "epoch": 0.22615016347501168, "grad_norm": 0.35115155577659607, "learning_rate": 9.523310567780514e-06, "loss": 0.2252, "step": 7747 }, { "epoch": 0.22617935544138254, "grad_norm": 0.308650940656662, "learning_rate": 9.523093430168968e-06, "loss": 0.2267, "step": 7748 }, { "epoch": 0.2262085474077534, "grad_norm": 0.3352367579936981, "learning_rate": 9.522876245590917e-06, "loss": 0.2162, "step": 7749 }, { "epoch": 0.22623773937412425, "grad_norm": 0.45812320709228516, "learning_rate": 9.522659014048616e-06, "loss": 0.2828, "step": 7750 }, { "epoch": 0.2262669313404951, "grad_norm": 0.37042391300201416, "learning_rate": 9.522441735544319e-06, "loss": 0.2687, "step": 7751 }, { "epoch": 0.22629612330686594, "grad_norm": 0.30695250630378723, "learning_rate": 9.522224410080284e-06, "loss": 0.2197, "step": 7752 }, { "epoch": 0.2263253152732368, "grad_norm": 0.4612251818180084, "learning_rate": 9.522007037658763e-06, "loss": 0.2325, "step": 7753 }, { "epoch": 0.22635450723960765, "grad_norm": 0.34097543358802795, "learning_rate": 9.52178961828202e-06, "loss": 0.2471, "step": 7754 }, { "epoch": 0.2263836992059785, "grad_norm": 0.5384661555290222, "learning_rate": 9.521572151952307e-06, "loss": 0.2347, "step": 7755 }, { "epoch": 0.22641289117234936, "grad_norm": 0.33307623863220215, "learning_rate": 9.521354638671886e-06, "loss": 0.253, "step": 7756 }, { "epoch": 0.22644208313872022, "grad_norm": 1.6115485429763794, "learning_rate": 9.521137078443012e-06, "loss": 0.2223, "step": 7757 }, { "epoch": 0.22647127510509107, "grad_norm": 0.31475067138671875, "learning_rate": 9.520919471267948e-06, "loss": 0.2186, "step": 7758 }, { "epoch": 0.22650046707146193, "grad_norm": 0.4489818811416626, "learning_rate": 9.520701817148952e-06, "loss": 0.2293, "step": 7759 }, { "epoch": 0.2265296590378328, "grad_norm": 0.37130916118621826, "learning_rate": 9.520484116088282e-06, "loss": 0.2518, "step": 7760 }, { "epoch": 0.22655885100420364, "grad_norm": 0.34756144881248474, "learning_rate": 9.5202663680882e-06, "loss": 0.2819, "step": 7761 }, { "epoch": 0.2265880429705745, "grad_norm": 0.2859685719013214, "learning_rate": 9.520048573150968e-06, "loss": 0.2072, "step": 7762 }, { "epoch": 0.22661723493694536, "grad_norm": 0.31676119565963745, "learning_rate": 9.519830731278848e-06, "loss": 0.2196, "step": 7763 }, { "epoch": 0.2266464269033162, "grad_norm": 0.32783713936805725, "learning_rate": 9.519612842474098e-06, "loss": 0.2413, "step": 7764 }, { "epoch": 0.22667561886968707, "grad_norm": 0.29955294728279114, "learning_rate": 9.519394906738986e-06, "loss": 0.2391, "step": 7765 }, { "epoch": 0.22670481083605792, "grad_norm": 0.385325163602829, "learning_rate": 9.51917692407577e-06, "loss": 0.2303, "step": 7766 }, { "epoch": 0.22673400280242878, "grad_norm": 0.4633744955062866, "learning_rate": 9.518958894486718e-06, "loss": 0.2577, "step": 7767 }, { "epoch": 0.22676319476879964, "grad_norm": 0.3736688196659088, "learning_rate": 9.51874081797409e-06, "loss": 0.2693, "step": 7768 }, { "epoch": 0.2267923867351705, "grad_norm": 0.33286094665527344, "learning_rate": 9.518522694540153e-06, "loss": 0.2403, "step": 7769 }, { "epoch": 0.22682157870154135, "grad_norm": 0.31683310866355896, "learning_rate": 9.51830452418717e-06, "loss": 0.2236, "step": 7770 }, { "epoch": 0.22685077066791218, "grad_norm": 0.3192872405052185, "learning_rate": 9.518086306917407e-06, "loss": 0.2183, "step": 7771 }, { "epoch": 0.22687996263428303, "grad_norm": 0.3081037104129791, "learning_rate": 9.517868042733132e-06, "loss": 0.2382, "step": 7772 }, { "epoch": 0.2269091546006539, "grad_norm": 0.3515409529209137, "learning_rate": 9.517649731636608e-06, "loss": 0.2048, "step": 7773 }, { "epoch": 0.22693834656702475, "grad_norm": 0.34274405241012573, "learning_rate": 9.517431373630107e-06, "loss": 0.2496, "step": 7774 }, { "epoch": 0.2269675385333956, "grad_norm": 0.3601492643356323, "learning_rate": 9.51721296871589e-06, "loss": 0.2944, "step": 7775 }, { "epoch": 0.22699673049976646, "grad_norm": 0.31168466806411743, "learning_rate": 9.516994516896227e-06, "loss": 0.2153, "step": 7776 }, { "epoch": 0.22702592246613731, "grad_norm": 0.3310409486293793, "learning_rate": 9.516776018173391e-06, "loss": 0.2057, "step": 7777 }, { "epoch": 0.22705511443250817, "grad_norm": 0.3462832272052765, "learning_rate": 9.516557472549644e-06, "loss": 0.227, "step": 7778 }, { "epoch": 0.22708430639887903, "grad_norm": 0.36501404643058777, "learning_rate": 9.516338880027259e-06, "loss": 0.31, "step": 7779 }, { "epoch": 0.22711349836524988, "grad_norm": 0.36557456851005554, "learning_rate": 9.516120240608506e-06, "loss": 0.2391, "step": 7780 }, { "epoch": 0.22714269033162074, "grad_norm": 0.3462577760219574, "learning_rate": 9.515901554295653e-06, "loss": 0.2388, "step": 7781 }, { "epoch": 0.2271718822979916, "grad_norm": 0.3309468626976013, "learning_rate": 9.515682821090973e-06, "loss": 0.2548, "step": 7782 }, { "epoch": 0.22720107426436245, "grad_norm": 0.358286589384079, "learning_rate": 9.515464040996736e-06, "loss": 0.2617, "step": 7783 }, { "epoch": 0.2272302662307333, "grad_norm": 0.2998371124267578, "learning_rate": 9.515245214015213e-06, "loss": 0.2019, "step": 7784 }, { "epoch": 0.22725945819710416, "grad_norm": 0.34760621190071106, "learning_rate": 9.515026340148681e-06, "loss": 0.2275, "step": 7785 }, { "epoch": 0.22728865016347502, "grad_norm": 0.4105677008628845, "learning_rate": 9.514807419399407e-06, "loss": 0.2539, "step": 7786 }, { "epoch": 0.22731784212984588, "grad_norm": 0.4042660892009735, "learning_rate": 9.514588451769667e-06, "loss": 0.2696, "step": 7787 }, { "epoch": 0.22734703409621673, "grad_norm": 0.32234734296798706, "learning_rate": 9.514369437261733e-06, "loss": 0.2163, "step": 7788 }, { "epoch": 0.2273762260625876, "grad_norm": 0.3239162266254425, "learning_rate": 9.514150375877881e-06, "loss": 0.2139, "step": 7789 }, { "epoch": 0.22740541802895842, "grad_norm": 0.3047119975090027, "learning_rate": 9.513931267620385e-06, "loss": 0.2248, "step": 7790 }, { "epoch": 0.22743460999532927, "grad_norm": 0.3420160412788391, "learning_rate": 9.51371211249152e-06, "loss": 0.2966, "step": 7791 }, { "epoch": 0.22746380196170013, "grad_norm": 0.3227601647377014, "learning_rate": 9.513492910493563e-06, "loss": 0.2518, "step": 7792 }, { "epoch": 0.22749299392807099, "grad_norm": 0.7300201654434204, "learning_rate": 9.513273661628787e-06, "loss": 0.2582, "step": 7793 }, { "epoch": 0.22752218589444184, "grad_norm": 0.31477853655815125, "learning_rate": 9.513054365899471e-06, "loss": 0.191, "step": 7794 }, { "epoch": 0.2275513778608127, "grad_norm": 0.3902938961982727, "learning_rate": 9.512835023307891e-06, "loss": 0.2483, "step": 7795 }, { "epoch": 0.22758056982718355, "grad_norm": 0.3862443268299103, "learning_rate": 9.512615633856327e-06, "loss": 0.2563, "step": 7796 }, { "epoch": 0.2276097617935544, "grad_norm": 0.32657021284103394, "learning_rate": 9.512396197547053e-06, "loss": 0.2185, "step": 7797 }, { "epoch": 0.22763895375992527, "grad_norm": 0.3428439795970917, "learning_rate": 9.512176714382353e-06, "loss": 0.2466, "step": 7798 }, { "epoch": 0.22766814572629612, "grad_norm": 0.30296608805656433, "learning_rate": 9.5119571843645e-06, "loss": 0.2382, "step": 7799 }, { "epoch": 0.22769733769266698, "grad_norm": 0.3323427736759186, "learning_rate": 9.511737607495777e-06, "loss": 0.2925, "step": 7800 }, { "epoch": 0.22772652965903784, "grad_norm": 0.3210586905479431, "learning_rate": 9.511517983778465e-06, "loss": 0.2729, "step": 7801 }, { "epoch": 0.2277557216254087, "grad_norm": 0.3330722749233246, "learning_rate": 9.511298313214841e-06, "loss": 0.2373, "step": 7802 }, { "epoch": 0.22778491359177955, "grad_norm": 0.3028549253940582, "learning_rate": 9.511078595807188e-06, "loss": 0.2304, "step": 7803 }, { "epoch": 0.2278141055581504, "grad_norm": 0.34145721793174744, "learning_rate": 9.510858831557788e-06, "loss": 0.2444, "step": 7804 }, { "epoch": 0.22784329752452126, "grad_norm": 0.3005520701408386, "learning_rate": 9.510639020468924e-06, "loss": 0.2149, "step": 7805 }, { "epoch": 0.22787248949089212, "grad_norm": 0.30974504351615906, "learning_rate": 9.510419162542875e-06, "loss": 0.2252, "step": 7806 }, { "epoch": 0.22790168145726297, "grad_norm": 0.3408486843109131, "learning_rate": 9.510199257781926e-06, "loss": 0.2207, "step": 7807 }, { "epoch": 0.22793087342363383, "grad_norm": 0.2985399663448334, "learning_rate": 9.50997930618836e-06, "loss": 0.2207, "step": 7808 }, { "epoch": 0.22796006539000466, "grad_norm": 0.3040449321269989, "learning_rate": 9.50975930776446e-06, "loss": 0.2073, "step": 7809 }, { "epoch": 0.2279892573563755, "grad_norm": 0.32892271876335144, "learning_rate": 9.509539262512515e-06, "loss": 0.2471, "step": 7810 }, { "epoch": 0.22801844932274637, "grad_norm": 0.3866499662399292, "learning_rate": 9.509319170434804e-06, "loss": 0.207, "step": 7811 }, { "epoch": 0.22804764128911723, "grad_norm": 0.33623287081718445, "learning_rate": 9.509099031533614e-06, "loss": 0.2677, "step": 7812 }, { "epoch": 0.22807683325548808, "grad_norm": 0.3235015571117401, "learning_rate": 9.508878845811234e-06, "loss": 0.2458, "step": 7813 }, { "epoch": 0.22810602522185894, "grad_norm": 0.30514058470726013, "learning_rate": 9.508658613269948e-06, "loss": 0.2301, "step": 7814 }, { "epoch": 0.2281352171882298, "grad_norm": 0.3417869508266449, "learning_rate": 9.50843833391204e-06, "loss": 0.2715, "step": 7815 }, { "epoch": 0.22816440915460065, "grad_norm": 0.46708089113235474, "learning_rate": 9.508218007739802e-06, "loss": 0.2589, "step": 7816 }, { "epoch": 0.2281936011209715, "grad_norm": 0.3824869692325592, "learning_rate": 9.507997634755521e-06, "loss": 0.2666, "step": 7817 }, { "epoch": 0.22822279308734236, "grad_norm": 0.3372228443622589, "learning_rate": 9.507777214961483e-06, "loss": 0.2412, "step": 7818 }, { "epoch": 0.22825198505371322, "grad_norm": 0.31176841259002686, "learning_rate": 9.507556748359978e-06, "loss": 0.2082, "step": 7819 }, { "epoch": 0.22828117702008408, "grad_norm": 0.3645198941230774, "learning_rate": 9.507336234953295e-06, "loss": 0.2232, "step": 7820 }, { "epoch": 0.22831036898645493, "grad_norm": 0.37260493636131287, "learning_rate": 9.507115674743725e-06, "loss": 0.2382, "step": 7821 }, { "epoch": 0.2283395609528258, "grad_norm": 0.3298977315425873, "learning_rate": 9.506895067733557e-06, "loss": 0.2411, "step": 7822 }, { "epoch": 0.22836875291919664, "grad_norm": 0.37862062454223633, "learning_rate": 9.506674413925081e-06, "loss": 0.243, "step": 7823 }, { "epoch": 0.2283979448855675, "grad_norm": 0.353145956993103, "learning_rate": 9.50645371332059e-06, "loss": 0.256, "step": 7824 }, { "epoch": 0.22842713685193836, "grad_norm": 0.3283884525299072, "learning_rate": 9.506232965922375e-06, "loss": 0.2137, "step": 7825 }, { "epoch": 0.2284563288183092, "grad_norm": 0.3202418088912964, "learning_rate": 9.506012171732728e-06, "loss": 0.2062, "step": 7826 }, { "epoch": 0.22848552078468007, "grad_norm": 0.349881649017334, "learning_rate": 9.505791330753942e-06, "loss": 0.25, "step": 7827 }, { "epoch": 0.22851471275105092, "grad_norm": 0.43954998254776, "learning_rate": 9.505570442988308e-06, "loss": 0.2215, "step": 7828 }, { "epoch": 0.22854390471742175, "grad_norm": 0.3117862343788147, "learning_rate": 9.505349508438124e-06, "loss": 0.2142, "step": 7829 }, { "epoch": 0.2285730966837926, "grad_norm": 0.34565308690071106, "learning_rate": 9.50512852710568e-06, "loss": 0.277, "step": 7830 }, { "epoch": 0.22860228865016347, "grad_norm": 0.31597888469696045, "learning_rate": 9.504907498993272e-06, "loss": 0.2554, "step": 7831 }, { "epoch": 0.22863148061653432, "grad_norm": 0.3365635573863983, "learning_rate": 9.504686424103197e-06, "loss": 0.1966, "step": 7832 }, { "epoch": 0.22866067258290518, "grad_norm": 0.366193026304245, "learning_rate": 9.504465302437748e-06, "loss": 0.299, "step": 7833 }, { "epoch": 0.22868986454927603, "grad_norm": 0.33775317668914795, "learning_rate": 9.504244133999221e-06, "loss": 0.248, "step": 7834 }, { "epoch": 0.2287190565156469, "grad_norm": 0.2849871516227722, "learning_rate": 9.504022918789915e-06, "loss": 0.2617, "step": 7835 }, { "epoch": 0.22874824848201775, "grad_norm": 0.3994264602661133, "learning_rate": 9.503801656812125e-06, "loss": 0.2718, "step": 7836 }, { "epoch": 0.2287774404483886, "grad_norm": 0.30856063961982727, "learning_rate": 9.503580348068149e-06, "loss": 0.2253, "step": 7837 }, { "epoch": 0.22880663241475946, "grad_norm": 0.3479083180427551, "learning_rate": 9.503358992560285e-06, "loss": 0.2266, "step": 7838 }, { "epoch": 0.22883582438113031, "grad_norm": 0.3648260831832886, "learning_rate": 9.503137590290832e-06, "loss": 0.2567, "step": 7839 }, { "epoch": 0.22886501634750117, "grad_norm": 0.2962208688259125, "learning_rate": 9.502916141262089e-06, "loss": 0.1961, "step": 7840 }, { "epoch": 0.22889420831387203, "grad_norm": 0.326401948928833, "learning_rate": 9.502694645476353e-06, "loss": 0.2522, "step": 7841 }, { "epoch": 0.22892340028024288, "grad_norm": 0.3197563886642456, "learning_rate": 9.502473102935928e-06, "loss": 0.2314, "step": 7842 }, { "epoch": 0.22895259224661374, "grad_norm": 0.2911073863506317, "learning_rate": 9.502251513643113e-06, "loss": 0.1875, "step": 7843 }, { "epoch": 0.2289817842129846, "grad_norm": 0.3359382748603821, "learning_rate": 9.502029877600206e-06, "loss": 0.2917, "step": 7844 }, { "epoch": 0.22901097617935545, "grad_norm": 0.3562709391117096, "learning_rate": 9.501808194809512e-06, "loss": 0.2788, "step": 7845 }, { "epoch": 0.2290401681457263, "grad_norm": 0.36035680770874023, "learning_rate": 9.501586465273332e-06, "loss": 0.2735, "step": 7846 }, { "epoch": 0.22906936011209716, "grad_norm": 0.32185304164886475, "learning_rate": 9.501364688993967e-06, "loss": 0.2616, "step": 7847 }, { "epoch": 0.229098552078468, "grad_norm": 0.34506142139434814, "learning_rate": 9.501142865973721e-06, "loss": 0.2346, "step": 7848 }, { "epoch": 0.22912774404483885, "grad_norm": 0.36238786578178406, "learning_rate": 9.500920996214898e-06, "loss": 0.2668, "step": 7849 }, { "epoch": 0.2291569360112097, "grad_norm": 0.30226173996925354, "learning_rate": 9.5006990797198e-06, "loss": 0.1975, "step": 7850 }, { "epoch": 0.22918612797758056, "grad_norm": 0.329099178314209, "learning_rate": 9.500477116490734e-06, "loss": 0.2638, "step": 7851 }, { "epoch": 0.22921531994395142, "grad_norm": 0.34473586082458496, "learning_rate": 9.50025510653e-06, "loss": 0.2791, "step": 7852 }, { "epoch": 0.22924451191032227, "grad_norm": 0.3276797831058502, "learning_rate": 9.500033049839909e-06, "loss": 0.2468, "step": 7853 }, { "epoch": 0.22927370387669313, "grad_norm": 0.3227551281452179, "learning_rate": 9.499810946422764e-06, "loss": 0.2446, "step": 7854 }, { "epoch": 0.229302895843064, "grad_norm": 0.3186319172382355, "learning_rate": 9.499588796280871e-06, "loss": 0.2577, "step": 7855 }, { "epoch": 0.22933208780943484, "grad_norm": 0.33107149600982666, "learning_rate": 9.499366599416537e-06, "loss": 0.2631, "step": 7856 }, { "epoch": 0.2293612797758057, "grad_norm": 0.3253772556781769, "learning_rate": 9.49914435583207e-06, "loss": 0.2428, "step": 7857 }, { "epoch": 0.22939047174217655, "grad_norm": 0.3584006130695343, "learning_rate": 9.498922065529777e-06, "loss": 0.2504, "step": 7858 }, { "epoch": 0.2294196637085474, "grad_norm": 0.34474894404411316, "learning_rate": 9.498699728511967e-06, "loss": 0.2322, "step": 7859 }, { "epoch": 0.22944885567491827, "grad_norm": 0.323717325925827, "learning_rate": 9.498477344780947e-06, "loss": 0.2386, "step": 7860 }, { "epoch": 0.22947804764128912, "grad_norm": 0.34381136298179626, "learning_rate": 9.498254914339027e-06, "loss": 0.2747, "step": 7861 }, { "epoch": 0.22950723960765998, "grad_norm": 0.46326762437820435, "learning_rate": 9.498032437188518e-06, "loss": 0.3201, "step": 7862 }, { "epoch": 0.22953643157403084, "grad_norm": 0.35174012184143066, "learning_rate": 9.497809913331728e-06, "loss": 0.2253, "step": 7863 }, { "epoch": 0.2295656235404017, "grad_norm": 0.36384931206703186, "learning_rate": 9.497587342770969e-06, "loss": 0.2738, "step": 7864 }, { "epoch": 0.22959481550677255, "grad_norm": 0.3299652934074402, "learning_rate": 9.49736472550855e-06, "loss": 0.2746, "step": 7865 }, { "epoch": 0.2296240074731434, "grad_norm": 0.3187304437160492, "learning_rate": 9.497142061546787e-06, "loss": 0.2803, "step": 7866 }, { "epoch": 0.22965319943951423, "grad_norm": 0.32072561979293823, "learning_rate": 9.49691935088799e-06, "loss": 0.2733, "step": 7867 }, { "epoch": 0.2296823914058851, "grad_norm": 0.3158060312271118, "learning_rate": 9.49669659353447e-06, "loss": 0.2927, "step": 7868 }, { "epoch": 0.22971158337225595, "grad_norm": 0.3423312306404114, "learning_rate": 9.496473789488538e-06, "loss": 0.2195, "step": 7869 }, { "epoch": 0.2297407753386268, "grad_norm": 0.3683565557003021, "learning_rate": 9.496250938752513e-06, "loss": 0.2631, "step": 7870 }, { "epoch": 0.22976996730499766, "grad_norm": 0.38055360317230225, "learning_rate": 9.496028041328708e-06, "loss": 0.2526, "step": 7871 }, { "epoch": 0.2297991592713685, "grad_norm": 0.3565632104873657, "learning_rate": 9.495805097219433e-06, "loss": 0.2395, "step": 7872 }, { "epoch": 0.22982835123773937, "grad_norm": 0.31021928787231445, "learning_rate": 9.495582106427008e-06, "loss": 0.2245, "step": 7873 }, { "epoch": 0.22985754320411023, "grad_norm": 0.34005236625671387, "learning_rate": 9.495359068953747e-06, "loss": 0.2748, "step": 7874 }, { "epoch": 0.22988673517048108, "grad_norm": 0.41182953119277954, "learning_rate": 9.495135984801964e-06, "loss": 0.2386, "step": 7875 }, { "epoch": 0.22991592713685194, "grad_norm": 0.3180534839630127, "learning_rate": 9.494912853973978e-06, "loss": 0.2015, "step": 7876 }, { "epoch": 0.2299451191032228, "grad_norm": 0.35476645827293396, "learning_rate": 9.494689676472105e-06, "loss": 0.2391, "step": 7877 }, { "epoch": 0.22997431106959365, "grad_norm": 0.3051711916923523, "learning_rate": 9.494466452298662e-06, "loss": 0.2008, "step": 7878 }, { "epoch": 0.2300035030359645, "grad_norm": 0.3278757929801941, "learning_rate": 9.494243181455966e-06, "loss": 0.2659, "step": 7879 }, { "epoch": 0.23003269500233536, "grad_norm": 0.3695177733898163, "learning_rate": 9.494019863946338e-06, "loss": 0.2866, "step": 7880 }, { "epoch": 0.23006188696870622, "grad_norm": 0.28665509819984436, "learning_rate": 9.493796499772095e-06, "loss": 0.2182, "step": 7881 }, { "epoch": 0.23009107893507708, "grad_norm": 0.3270384967327118, "learning_rate": 9.493573088935557e-06, "loss": 0.2207, "step": 7882 }, { "epoch": 0.23012027090144793, "grad_norm": 0.34806621074676514, "learning_rate": 9.493349631439042e-06, "loss": 0.2317, "step": 7883 }, { "epoch": 0.2301494628678188, "grad_norm": 0.30108171701431274, "learning_rate": 9.493126127284874e-06, "loss": 0.2073, "step": 7884 }, { "epoch": 0.23017865483418964, "grad_norm": 0.34794679284095764, "learning_rate": 9.492902576475371e-06, "loss": 0.322, "step": 7885 }, { "epoch": 0.23020784680056047, "grad_norm": 0.34730803966522217, "learning_rate": 9.492678979012855e-06, "loss": 0.2444, "step": 7886 }, { "epoch": 0.23023703876693133, "grad_norm": 0.3517780303955078, "learning_rate": 9.492455334899647e-06, "loss": 0.2242, "step": 7887 }, { "epoch": 0.23026623073330219, "grad_norm": 0.3602946698665619, "learning_rate": 9.492231644138072e-06, "loss": 0.2361, "step": 7888 }, { "epoch": 0.23029542269967304, "grad_norm": 0.37640371918678284, "learning_rate": 9.49200790673045e-06, "loss": 0.2566, "step": 7889 }, { "epoch": 0.2303246146660439, "grad_norm": 0.30345916748046875, "learning_rate": 9.491784122679103e-06, "loss": 0.195, "step": 7890 }, { "epoch": 0.23035380663241475, "grad_norm": 0.3351280987262726, "learning_rate": 9.491560291986358e-06, "loss": 0.2479, "step": 7891 }, { "epoch": 0.2303829985987856, "grad_norm": 0.37636658549308777, "learning_rate": 9.491336414654539e-06, "loss": 0.2732, "step": 7892 }, { "epoch": 0.23041219056515647, "grad_norm": 0.3455844223499298, "learning_rate": 9.491112490685967e-06, "loss": 0.251, "step": 7893 }, { "epoch": 0.23044138253152732, "grad_norm": 0.3692418038845062, "learning_rate": 9.490888520082973e-06, "loss": 0.265, "step": 7894 }, { "epoch": 0.23047057449789818, "grad_norm": 0.312764972448349, "learning_rate": 9.490664502847877e-06, "loss": 0.3133, "step": 7895 }, { "epoch": 0.23049976646426903, "grad_norm": 0.32971206307411194, "learning_rate": 9.490440438983008e-06, "loss": 0.2807, "step": 7896 }, { "epoch": 0.2305289584306399, "grad_norm": 0.3835921287536621, "learning_rate": 9.490216328490693e-06, "loss": 0.2703, "step": 7897 }, { "epoch": 0.23055815039701075, "grad_norm": 0.35665130615234375, "learning_rate": 9.489992171373258e-06, "loss": 0.243, "step": 7898 }, { "epoch": 0.2305873423633816, "grad_norm": 0.313616544008255, "learning_rate": 9.48976796763303e-06, "loss": 0.2429, "step": 7899 }, { "epoch": 0.23061653432975246, "grad_norm": 0.32477909326553345, "learning_rate": 9.489543717272338e-06, "loss": 0.226, "step": 7900 }, { "epoch": 0.23064572629612332, "grad_norm": 0.3178761601448059, "learning_rate": 9.489319420293511e-06, "loss": 0.2022, "step": 7901 }, { "epoch": 0.23067491826249417, "grad_norm": 0.3405560553073883, "learning_rate": 9.489095076698877e-06, "loss": 0.2217, "step": 7902 }, { "epoch": 0.23070411022886503, "grad_norm": 0.33687546849250793, "learning_rate": 9.488870686490767e-06, "loss": 0.2808, "step": 7903 }, { "epoch": 0.23073330219523588, "grad_norm": 0.3260849118232727, "learning_rate": 9.48864624967151e-06, "loss": 0.2385, "step": 7904 }, { "epoch": 0.2307624941616067, "grad_norm": 0.32317668199539185, "learning_rate": 9.488421766243436e-06, "loss": 0.2609, "step": 7905 }, { "epoch": 0.23079168612797757, "grad_norm": 0.36126846075057983, "learning_rate": 9.488197236208876e-06, "loss": 0.2657, "step": 7906 }, { "epoch": 0.23082087809434843, "grad_norm": 0.44527509808540344, "learning_rate": 9.487972659570161e-06, "loss": 0.2569, "step": 7907 }, { "epoch": 0.23085007006071928, "grad_norm": 0.3670669198036194, "learning_rate": 9.487748036329625e-06, "loss": 0.2736, "step": 7908 }, { "epoch": 0.23087926202709014, "grad_norm": 0.35588783025741577, "learning_rate": 9.487523366489599e-06, "loss": 0.2257, "step": 7909 }, { "epoch": 0.230908453993461, "grad_norm": 0.3353785276412964, "learning_rate": 9.487298650052416e-06, "loss": 0.2298, "step": 7910 }, { "epoch": 0.23093764595983185, "grad_norm": 0.3586708903312683, "learning_rate": 9.487073887020411e-06, "loss": 0.2573, "step": 7911 }, { "epoch": 0.2309668379262027, "grad_norm": 0.29212167859077454, "learning_rate": 9.486849077395915e-06, "loss": 0.2147, "step": 7912 }, { "epoch": 0.23099602989257356, "grad_norm": 0.34953635931015015, "learning_rate": 9.486624221181264e-06, "loss": 0.2562, "step": 7913 }, { "epoch": 0.23102522185894442, "grad_norm": 0.34873488545417786, "learning_rate": 9.486399318378794e-06, "loss": 0.245, "step": 7914 }, { "epoch": 0.23105441382531527, "grad_norm": 0.40162089467048645, "learning_rate": 9.486174368990836e-06, "loss": 0.2306, "step": 7915 }, { "epoch": 0.23108360579168613, "grad_norm": 0.35685834288597107, "learning_rate": 9.485949373019731e-06, "loss": 0.2189, "step": 7916 }, { "epoch": 0.231112797758057, "grad_norm": 0.2855674922466278, "learning_rate": 9.485724330467814e-06, "loss": 0.1989, "step": 7917 }, { "epoch": 0.23114198972442784, "grad_norm": 0.30548277497291565, "learning_rate": 9.48549924133742e-06, "loss": 0.219, "step": 7918 }, { "epoch": 0.2311711816907987, "grad_norm": 0.3130269944667816, "learning_rate": 9.485274105630886e-06, "loss": 0.2547, "step": 7919 }, { "epoch": 0.23120037365716956, "grad_norm": 0.34902605414390564, "learning_rate": 9.485048923350551e-06, "loss": 0.3086, "step": 7920 }, { "epoch": 0.2312295656235404, "grad_norm": 0.33148300647735596, "learning_rate": 9.484823694498755e-06, "loss": 0.2291, "step": 7921 }, { "epoch": 0.23125875758991127, "grad_norm": 0.3704402446746826, "learning_rate": 9.484598419077833e-06, "loss": 0.2041, "step": 7922 }, { "epoch": 0.23128794955628212, "grad_norm": 0.3238549530506134, "learning_rate": 9.484373097090126e-06, "loss": 0.2633, "step": 7923 }, { "epoch": 0.23131714152265295, "grad_norm": 0.378248006105423, "learning_rate": 9.484147728537974e-06, "loss": 0.2625, "step": 7924 }, { "epoch": 0.2313463334890238, "grad_norm": 0.28521496057510376, "learning_rate": 9.483922313423716e-06, "loss": 0.2278, "step": 7925 }, { "epoch": 0.23137552545539466, "grad_norm": 0.32832348346710205, "learning_rate": 9.483696851749695e-06, "loss": 0.258, "step": 7926 }, { "epoch": 0.23140471742176552, "grad_norm": 0.36686715483665466, "learning_rate": 9.483471343518251e-06, "loss": 0.258, "step": 7927 }, { "epoch": 0.23143390938813638, "grad_norm": 0.8982532024383545, "learning_rate": 9.483245788731723e-06, "loss": 0.2124, "step": 7928 }, { "epoch": 0.23146310135450723, "grad_norm": 0.3421676456928253, "learning_rate": 9.483020187392458e-06, "loss": 0.2391, "step": 7929 }, { "epoch": 0.2314922933208781, "grad_norm": 0.3069465160369873, "learning_rate": 9.482794539502794e-06, "loss": 0.225, "step": 7930 }, { "epoch": 0.23152148528724895, "grad_norm": 0.3676420748233795, "learning_rate": 9.482568845065077e-06, "loss": 0.2734, "step": 7931 }, { "epoch": 0.2315506772536198, "grad_norm": 0.29618942737579346, "learning_rate": 9.482343104081648e-06, "loss": 0.2554, "step": 7932 }, { "epoch": 0.23157986921999066, "grad_norm": 0.3464727997779846, "learning_rate": 9.482117316554854e-06, "loss": 0.2199, "step": 7933 }, { "epoch": 0.23160906118636151, "grad_norm": 0.3413640856742859, "learning_rate": 9.481891482487038e-06, "loss": 0.2952, "step": 7934 }, { "epoch": 0.23163825315273237, "grad_norm": 0.32639598846435547, "learning_rate": 9.481665601880544e-06, "loss": 0.2179, "step": 7935 }, { "epoch": 0.23166744511910323, "grad_norm": 0.3541750907897949, "learning_rate": 9.481439674737718e-06, "loss": 0.2171, "step": 7936 }, { "epoch": 0.23169663708547408, "grad_norm": 0.38369545340538025, "learning_rate": 9.481213701060909e-06, "loss": 0.298, "step": 7937 }, { "epoch": 0.23172582905184494, "grad_norm": 0.41286778450012207, "learning_rate": 9.48098768085246e-06, "loss": 0.254, "step": 7938 }, { "epoch": 0.2317550210182158, "grad_norm": 0.31925350427627563, "learning_rate": 9.480761614114717e-06, "loss": 0.226, "step": 7939 }, { "epoch": 0.23178421298458665, "grad_norm": 0.3231814205646515, "learning_rate": 9.48053550085003e-06, "loss": 0.2535, "step": 7940 }, { "epoch": 0.2318134049509575, "grad_norm": 0.3523409962654114, "learning_rate": 9.480309341060748e-06, "loss": 0.2242, "step": 7941 }, { "epoch": 0.23184259691732836, "grad_norm": 0.336916983127594, "learning_rate": 9.480083134749216e-06, "loss": 0.2417, "step": 7942 }, { "epoch": 0.2318717888836992, "grad_norm": 0.4676887094974518, "learning_rate": 9.479856881917786e-06, "loss": 0.2712, "step": 7943 }, { "epoch": 0.23190098085007005, "grad_norm": 0.36549025774002075, "learning_rate": 9.479630582568804e-06, "loss": 0.2257, "step": 7944 }, { "epoch": 0.2319301728164409, "grad_norm": 0.3471188545227051, "learning_rate": 9.479404236704623e-06, "loss": 0.2437, "step": 7945 }, { "epoch": 0.23195936478281176, "grad_norm": 0.31891271471977234, "learning_rate": 9.479177844327591e-06, "loss": 0.2409, "step": 7946 }, { "epoch": 0.23198855674918262, "grad_norm": 0.3234790861606598, "learning_rate": 9.47895140544006e-06, "loss": 0.2229, "step": 7947 }, { "epoch": 0.23201774871555347, "grad_norm": 0.3382355570793152, "learning_rate": 9.47872492004438e-06, "loss": 0.2324, "step": 7948 }, { "epoch": 0.23204694068192433, "grad_norm": 0.32072657346725464, "learning_rate": 9.478498388142904e-06, "loss": 0.2314, "step": 7949 }, { "epoch": 0.23207613264829519, "grad_norm": 0.3108186721801758, "learning_rate": 9.478271809737984e-06, "loss": 0.1945, "step": 7950 }, { "epoch": 0.23210532461466604, "grad_norm": 0.3409828245639801, "learning_rate": 9.478045184831974e-06, "loss": 0.2894, "step": 7951 }, { "epoch": 0.2321345165810369, "grad_norm": 0.34301695227622986, "learning_rate": 9.477818513427225e-06, "loss": 0.2404, "step": 7952 }, { "epoch": 0.23216370854740775, "grad_norm": 0.4051453471183777, "learning_rate": 9.477591795526091e-06, "loss": 0.2761, "step": 7953 }, { "epoch": 0.2321929005137786, "grad_norm": 0.3837266266345978, "learning_rate": 9.477365031130927e-06, "loss": 0.2736, "step": 7954 }, { "epoch": 0.23222209248014947, "grad_norm": 0.33349305391311646, "learning_rate": 9.477138220244089e-06, "loss": 0.2645, "step": 7955 }, { "epoch": 0.23225128444652032, "grad_norm": 0.3985256850719452, "learning_rate": 9.47691136286793e-06, "loss": 0.2898, "step": 7956 }, { "epoch": 0.23228047641289118, "grad_norm": 0.3108658492565155, "learning_rate": 9.476684459004804e-06, "loss": 0.2376, "step": 7957 }, { "epoch": 0.23230966837926204, "grad_norm": 0.3697768449783325, "learning_rate": 9.476457508657072e-06, "loss": 0.2313, "step": 7958 }, { "epoch": 0.2323388603456329, "grad_norm": 0.3279794156551361, "learning_rate": 9.476230511827086e-06, "loss": 0.273, "step": 7959 }, { "epoch": 0.23236805231200375, "grad_norm": 0.33608102798461914, "learning_rate": 9.476003468517205e-06, "loss": 0.2141, "step": 7960 }, { "epoch": 0.2323972442783746, "grad_norm": 0.3218281865119934, "learning_rate": 9.475776378729789e-06, "loss": 0.1978, "step": 7961 }, { "epoch": 0.23242643624474543, "grad_norm": 0.36626893281936646, "learning_rate": 9.475549242467191e-06, "loss": 0.2369, "step": 7962 }, { "epoch": 0.2324556282111163, "grad_norm": 0.36078184843063354, "learning_rate": 9.475322059731773e-06, "loss": 0.2091, "step": 7963 }, { "epoch": 0.23248482017748714, "grad_norm": 0.3665177524089813, "learning_rate": 9.475094830525893e-06, "loss": 0.2565, "step": 7964 }, { "epoch": 0.232514012143858, "grad_norm": 0.37706002593040466, "learning_rate": 9.47486755485191e-06, "loss": 0.3208, "step": 7965 }, { "epoch": 0.23254320411022886, "grad_norm": 0.36572885513305664, "learning_rate": 9.474640232712184e-06, "loss": 0.2428, "step": 7966 }, { "epoch": 0.2325723960765997, "grad_norm": 0.39725810289382935, "learning_rate": 9.474412864109077e-06, "loss": 0.2319, "step": 7967 }, { "epoch": 0.23260158804297057, "grad_norm": 0.3593047857284546, "learning_rate": 9.47418544904495e-06, "loss": 0.2734, "step": 7968 }, { "epoch": 0.23263078000934143, "grad_norm": 0.3405405580997467, "learning_rate": 9.47395798752216e-06, "loss": 0.253, "step": 7969 }, { "epoch": 0.23265997197571228, "grad_norm": 0.36397603154182434, "learning_rate": 9.473730479543076e-06, "loss": 0.2308, "step": 7970 }, { "epoch": 0.23268916394208314, "grad_norm": 0.3832651674747467, "learning_rate": 9.473502925110054e-06, "loss": 0.2359, "step": 7971 }, { "epoch": 0.232718355908454, "grad_norm": 0.454382985830307, "learning_rate": 9.47327532422546e-06, "loss": 0.261, "step": 7972 }, { "epoch": 0.23274754787482485, "grad_norm": 0.3517704904079437, "learning_rate": 9.473047676891658e-06, "loss": 0.2336, "step": 7973 }, { "epoch": 0.2327767398411957, "grad_norm": 0.41916921734809875, "learning_rate": 9.472819983111008e-06, "loss": 0.2611, "step": 7974 }, { "epoch": 0.23280593180756656, "grad_norm": 0.35424908995628357, "learning_rate": 9.472592242885879e-06, "loss": 0.2591, "step": 7975 }, { "epoch": 0.23283512377393742, "grad_norm": 0.3576474189758301, "learning_rate": 9.472364456218633e-06, "loss": 0.2844, "step": 7976 }, { "epoch": 0.23286431574030828, "grad_norm": 0.3902401328086853, "learning_rate": 9.472136623111636e-06, "loss": 0.2509, "step": 7977 }, { "epoch": 0.23289350770667913, "grad_norm": 0.4214377701282501, "learning_rate": 9.471908743567255e-06, "loss": 0.2542, "step": 7978 }, { "epoch": 0.23292269967305, "grad_norm": 0.33498263359069824, "learning_rate": 9.471680817587852e-06, "loss": 0.2585, "step": 7979 }, { "epoch": 0.23295189163942084, "grad_norm": 0.36703744530677795, "learning_rate": 9.4714528451758e-06, "loss": 0.2322, "step": 7980 }, { "epoch": 0.23298108360579167, "grad_norm": 0.3365519940853119, "learning_rate": 9.47122482633346e-06, "loss": 0.2578, "step": 7981 }, { "epoch": 0.23301027557216253, "grad_norm": 0.36316126585006714, "learning_rate": 9.470996761063205e-06, "loss": 0.2586, "step": 7982 }, { "epoch": 0.23303946753853338, "grad_norm": 0.42816492915153503, "learning_rate": 9.470768649367399e-06, "loss": 0.2244, "step": 7983 }, { "epoch": 0.23306865950490424, "grad_norm": 0.32274898886680603, "learning_rate": 9.470540491248413e-06, "loss": 0.1865, "step": 7984 }, { "epoch": 0.2330978514712751, "grad_norm": 0.3635193705558777, "learning_rate": 9.470312286708616e-06, "loss": 0.2633, "step": 7985 }, { "epoch": 0.23312704343764595, "grad_norm": 0.3888424038887024, "learning_rate": 9.470084035750375e-06, "loss": 0.2374, "step": 7986 }, { "epoch": 0.2331562354040168, "grad_norm": 0.3133409917354584, "learning_rate": 9.469855738376063e-06, "loss": 0.196, "step": 7987 }, { "epoch": 0.23318542737038767, "grad_norm": 0.36715203523635864, "learning_rate": 9.469627394588051e-06, "loss": 0.233, "step": 7988 }, { "epoch": 0.23321461933675852, "grad_norm": 0.39859017729759216, "learning_rate": 9.469399004388708e-06, "loss": 0.3319, "step": 7989 }, { "epoch": 0.23324381130312938, "grad_norm": 0.3426528573036194, "learning_rate": 9.469170567780408e-06, "loss": 0.2635, "step": 7990 }, { "epoch": 0.23327300326950023, "grad_norm": 0.35161903500556946, "learning_rate": 9.46894208476552e-06, "loss": 0.2535, "step": 7991 }, { "epoch": 0.2333021952358711, "grad_norm": 0.43826255202293396, "learning_rate": 9.468713555346417e-06, "loss": 0.2758, "step": 7992 }, { "epoch": 0.23333138720224195, "grad_norm": 0.35771727561950684, "learning_rate": 9.468484979525474e-06, "loss": 0.2351, "step": 7993 }, { "epoch": 0.2333605791686128, "grad_norm": 0.3678596019744873, "learning_rate": 9.468256357305064e-06, "loss": 0.2399, "step": 7994 }, { "epoch": 0.23338977113498366, "grad_norm": 0.36962875723838806, "learning_rate": 9.468027688687558e-06, "loss": 0.2395, "step": 7995 }, { "epoch": 0.23341896310135452, "grad_norm": 0.29657337069511414, "learning_rate": 9.467798973675336e-06, "loss": 0.2004, "step": 7996 }, { "epoch": 0.23344815506772537, "grad_norm": 0.37078404426574707, "learning_rate": 9.467570212270767e-06, "loss": 0.2617, "step": 7997 }, { "epoch": 0.23347734703409623, "grad_norm": 0.3658255934715271, "learning_rate": 9.467341404476229e-06, "loss": 0.2486, "step": 7998 }, { "epoch": 0.23350653900046708, "grad_norm": 0.31853529810905457, "learning_rate": 9.467112550294098e-06, "loss": 0.2336, "step": 7999 }, { "epoch": 0.23353573096683794, "grad_norm": 0.3200796842575073, "learning_rate": 9.466883649726752e-06, "loss": 0.2397, "step": 8000 }, { "epoch": 0.23356492293320877, "grad_norm": 0.2993181645870209, "learning_rate": 9.466654702776565e-06, "loss": 0.2218, "step": 8001 }, { "epoch": 0.23359411489957962, "grad_norm": 0.39829689264297485, "learning_rate": 9.466425709445914e-06, "loss": 0.2558, "step": 8002 }, { "epoch": 0.23362330686595048, "grad_norm": 0.4307648539543152, "learning_rate": 9.46619666973718e-06, "loss": 0.255, "step": 8003 }, { "epoch": 0.23365249883232134, "grad_norm": 0.3102843761444092, "learning_rate": 9.46596758365274e-06, "loss": 0.2295, "step": 8004 }, { "epoch": 0.2336816907986922, "grad_norm": 0.35558271408081055, "learning_rate": 9.46573845119497e-06, "loss": 0.2053, "step": 8005 }, { "epoch": 0.23371088276506305, "grad_norm": 0.3057485818862915, "learning_rate": 9.465509272366254e-06, "loss": 0.205, "step": 8006 }, { "epoch": 0.2337400747314339, "grad_norm": 0.3283844590187073, "learning_rate": 9.465280047168967e-06, "loss": 0.2585, "step": 8007 }, { "epoch": 0.23376926669780476, "grad_norm": 0.31069865822792053, "learning_rate": 9.465050775605493e-06, "loss": 0.1911, "step": 8008 }, { "epoch": 0.23379845866417562, "grad_norm": 0.33050161600112915, "learning_rate": 9.46482145767821e-06, "loss": 0.2291, "step": 8009 }, { "epoch": 0.23382765063054647, "grad_norm": 0.56352299451828, "learning_rate": 9.464592093389501e-06, "loss": 0.2878, "step": 8010 }, { "epoch": 0.23385684259691733, "grad_norm": 0.33549585938453674, "learning_rate": 9.464362682741747e-06, "loss": 0.2929, "step": 8011 }, { "epoch": 0.2338860345632882, "grad_norm": 0.3515753448009491, "learning_rate": 9.46413322573733e-06, "loss": 0.3163, "step": 8012 }, { "epoch": 0.23391522652965904, "grad_norm": 0.33223122358322144, "learning_rate": 9.463903722378633e-06, "loss": 0.2501, "step": 8013 }, { "epoch": 0.2339444184960299, "grad_norm": 0.48368871212005615, "learning_rate": 9.463674172668038e-06, "loss": 0.285, "step": 8014 }, { "epoch": 0.23397361046240076, "grad_norm": 0.3717721700668335, "learning_rate": 9.46344457660793e-06, "loss": 0.2772, "step": 8015 }, { "epoch": 0.2340028024287716, "grad_norm": 0.32621803879737854, "learning_rate": 9.463214934200692e-06, "loss": 0.2238, "step": 8016 }, { "epoch": 0.23403199439514247, "grad_norm": 0.3431102931499481, "learning_rate": 9.462985245448708e-06, "loss": 0.2314, "step": 8017 }, { "epoch": 0.23406118636151332, "grad_norm": 0.35397061705589294, "learning_rate": 9.462755510354366e-06, "loss": 0.2746, "step": 8018 }, { "epoch": 0.23409037832788418, "grad_norm": 0.33527734875679016, "learning_rate": 9.462525728920049e-06, "loss": 0.238, "step": 8019 }, { "epoch": 0.234119570294255, "grad_norm": 0.3927624821662903, "learning_rate": 9.462295901148143e-06, "loss": 0.2441, "step": 8020 }, { "epoch": 0.23414876226062586, "grad_norm": 0.3080955445766449, "learning_rate": 9.462066027041035e-06, "loss": 0.2392, "step": 8021 }, { "epoch": 0.23417795422699672, "grad_norm": 0.31382685899734497, "learning_rate": 9.461836106601112e-06, "loss": 0.2257, "step": 8022 }, { "epoch": 0.23420714619336758, "grad_norm": 0.3857259452342987, "learning_rate": 9.461606139830761e-06, "loss": 0.2504, "step": 8023 }, { "epoch": 0.23423633815973843, "grad_norm": 0.3840412497520447, "learning_rate": 9.461376126732372e-06, "loss": 0.2563, "step": 8024 }, { "epoch": 0.2342655301261093, "grad_norm": 0.37418875098228455, "learning_rate": 9.461146067308329e-06, "loss": 0.2525, "step": 8025 }, { "epoch": 0.23429472209248015, "grad_norm": 0.33525028824806213, "learning_rate": 9.460915961561025e-06, "loss": 0.2428, "step": 8026 }, { "epoch": 0.234323914058851, "grad_norm": 0.3372066617012024, "learning_rate": 9.460685809492847e-06, "loss": 0.2656, "step": 8027 }, { "epoch": 0.23435310602522186, "grad_norm": 0.33404800295829773, "learning_rate": 9.460455611106188e-06, "loss": 0.2278, "step": 8028 }, { "epoch": 0.23438229799159271, "grad_norm": 0.3369136154651642, "learning_rate": 9.460225366403432e-06, "loss": 0.2458, "step": 8029 }, { "epoch": 0.23441148995796357, "grad_norm": 0.3304196894168854, "learning_rate": 9.459995075386976e-06, "loss": 0.2157, "step": 8030 }, { "epoch": 0.23444068192433443, "grad_norm": 0.29133865237236023, "learning_rate": 9.45976473805921e-06, "loss": 0.223, "step": 8031 }, { "epoch": 0.23446987389070528, "grad_norm": 0.365058034658432, "learning_rate": 9.459534354422523e-06, "loss": 0.2702, "step": 8032 }, { "epoch": 0.23449906585707614, "grad_norm": 0.3370908498764038, "learning_rate": 9.45930392447931e-06, "loss": 0.2251, "step": 8033 }, { "epoch": 0.234528257823447, "grad_norm": 0.3589530289173126, "learning_rate": 9.459073448231963e-06, "loss": 0.2531, "step": 8034 }, { "epoch": 0.23455744978981785, "grad_norm": 0.3045882284641266, "learning_rate": 9.458842925682875e-06, "loss": 0.2261, "step": 8035 }, { "epoch": 0.2345866417561887, "grad_norm": 0.34089431166648865, "learning_rate": 9.45861235683444e-06, "loss": 0.2705, "step": 8036 }, { "epoch": 0.23461583372255956, "grad_norm": 0.4742153584957123, "learning_rate": 9.45838174168905e-06, "loss": 0.2992, "step": 8037 }, { "epoch": 0.23464502568893042, "grad_norm": 0.3081030249595642, "learning_rate": 9.458151080249102e-06, "loss": 0.2213, "step": 8038 }, { "epoch": 0.23467421765530125, "grad_norm": 0.318809449672699, "learning_rate": 9.457920372516994e-06, "loss": 0.231, "step": 8039 }, { "epoch": 0.2347034096216721, "grad_norm": 0.657748818397522, "learning_rate": 9.457689618495114e-06, "loss": 0.2246, "step": 8040 }, { "epoch": 0.23473260158804296, "grad_norm": 0.345293790102005, "learning_rate": 9.457458818185864e-06, "loss": 0.2109, "step": 8041 }, { "epoch": 0.23476179355441382, "grad_norm": 0.5003930330276489, "learning_rate": 9.457227971591638e-06, "loss": 0.2162, "step": 8042 }, { "epoch": 0.23479098552078467, "grad_norm": 0.3809434175491333, "learning_rate": 9.456997078714834e-06, "loss": 0.2541, "step": 8043 }, { "epoch": 0.23482017748715553, "grad_norm": 0.41834238171577454, "learning_rate": 9.45676613955785e-06, "loss": 0.2556, "step": 8044 }, { "epoch": 0.23484936945352639, "grad_norm": 0.3260231018066406, "learning_rate": 9.456535154123083e-06, "loss": 0.2392, "step": 8045 }, { "epoch": 0.23487856141989724, "grad_norm": 0.3696591854095459, "learning_rate": 9.456304122412933e-06, "loss": 0.2773, "step": 8046 }, { "epoch": 0.2349077533862681, "grad_norm": 0.4425363540649414, "learning_rate": 9.456073044429797e-06, "loss": 0.2999, "step": 8047 }, { "epoch": 0.23493694535263895, "grad_norm": 0.30465301871299744, "learning_rate": 9.455841920176074e-06, "loss": 0.2483, "step": 8048 }, { "epoch": 0.2349661373190098, "grad_norm": 0.3383420407772064, "learning_rate": 9.455610749654167e-06, "loss": 0.3311, "step": 8049 }, { "epoch": 0.23499532928538067, "grad_norm": 0.30139458179473877, "learning_rate": 9.455379532866476e-06, "loss": 0.2095, "step": 8050 }, { "epoch": 0.23502452125175152, "grad_norm": 0.3280426561832428, "learning_rate": 9.455148269815398e-06, "loss": 0.2377, "step": 8051 }, { "epoch": 0.23505371321812238, "grad_norm": 0.3540661633014679, "learning_rate": 9.454916960503338e-06, "loss": 0.2421, "step": 8052 }, { "epoch": 0.23508290518449323, "grad_norm": 0.4235255718231201, "learning_rate": 9.454685604932696e-06, "loss": 0.2568, "step": 8053 }, { "epoch": 0.2351120971508641, "grad_norm": 0.34480229020118713, "learning_rate": 9.454454203105875e-06, "loss": 0.2741, "step": 8054 }, { "epoch": 0.23514128911723495, "grad_norm": 0.3151942193508148, "learning_rate": 9.454222755025278e-06, "loss": 0.2104, "step": 8055 }, { "epoch": 0.2351704810836058, "grad_norm": 0.5061025619506836, "learning_rate": 9.453991260693309e-06, "loss": 0.2171, "step": 8056 }, { "epoch": 0.23519967304997666, "grad_norm": 0.38458213210105896, "learning_rate": 9.45375972011237e-06, "loss": 0.2276, "step": 8057 }, { "epoch": 0.2352288650163475, "grad_norm": 0.6953428387641907, "learning_rate": 9.453528133284868e-06, "loss": 0.2964, "step": 8058 }, { "epoch": 0.23525805698271834, "grad_norm": 0.3341714143753052, "learning_rate": 9.453296500213203e-06, "loss": 0.275, "step": 8059 }, { "epoch": 0.2352872489490892, "grad_norm": 0.3455781638622284, "learning_rate": 9.453064820899786e-06, "loss": 0.2553, "step": 8060 }, { "epoch": 0.23531644091546006, "grad_norm": 0.3384297788143158, "learning_rate": 9.452833095347018e-06, "loss": 0.2563, "step": 8061 }, { "epoch": 0.2353456328818309, "grad_norm": 0.3761158585548401, "learning_rate": 9.452601323557308e-06, "loss": 0.2324, "step": 8062 }, { "epoch": 0.23537482484820177, "grad_norm": 0.32073476910591125, "learning_rate": 9.452369505533061e-06, "loss": 0.2629, "step": 8063 }, { "epoch": 0.23540401681457263, "grad_norm": 0.386062353849411, "learning_rate": 9.452137641276686e-06, "loss": 0.2148, "step": 8064 }, { "epoch": 0.23543320878094348, "grad_norm": 0.3891949951648712, "learning_rate": 9.451905730790588e-06, "loss": 0.211, "step": 8065 }, { "epoch": 0.23546240074731434, "grad_norm": 0.5049017071723938, "learning_rate": 9.451673774077177e-06, "loss": 0.2721, "step": 8066 }, { "epoch": 0.2354915927136852, "grad_norm": 0.2922757863998413, "learning_rate": 9.45144177113886e-06, "loss": 0.2209, "step": 8067 }, { "epoch": 0.23552078468005605, "grad_norm": 0.3611844480037689, "learning_rate": 9.45120972197805e-06, "loss": 0.2585, "step": 8068 }, { "epoch": 0.2355499766464269, "grad_norm": 0.30439844727516174, "learning_rate": 9.450977626597151e-06, "loss": 0.2219, "step": 8069 }, { "epoch": 0.23557916861279776, "grad_norm": 0.47207555174827576, "learning_rate": 9.450745484998578e-06, "loss": 0.2493, "step": 8070 }, { "epoch": 0.23560836057916862, "grad_norm": 0.39540958404541016, "learning_rate": 9.450513297184738e-06, "loss": 0.2721, "step": 8071 }, { "epoch": 0.23563755254553947, "grad_norm": 0.34793123602867126, "learning_rate": 9.450281063158042e-06, "loss": 0.2396, "step": 8072 }, { "epoch": 0.23566674451191033, "grad_norm": 0.33462804555892944, "learning_rate": 9.450048782920904e-06, "loss": 0.236, "step": 8073 }, { "epoch": 0.2356959364782812, "grad_norm": 0.33880192041397095, "learning_rate": 9.449816456475733e-06, "loss": 0.2474, "step": 8074 }, { "epoch": 0.23572512844465204, "grad_norm": 0.37401947379112244, "learning_rate": 9.449584083824945e-06, "loss": 0.2267, "step": 8075 }, { "epoch": 0.2357543204110229, "grad_norm": 0.32670101523399353, "learning_rate": 9.44935166497095e-06, "loss": 0.2045, "step": 8076 }, { "epoch": 0.23578351237739373, "grad_norm": 0.38006842136383057, "learning_rate": 9.449119199916162e-06, "loss": 0.2376, "step": 8077 }, { "epoch": 0.23581270434376458, "grad_norm": 0.34048187732696533, "learning_rate": 9.448886688662994e-06, "loss": 0.2134, "step": 8078 }, { "epoch": 0.23584189631013544, "grad_norm": 0.3731239140033722, "learning_rate": 9.448654131213861e-06, "loss": 0.2631, "step": 8079 }, { "epoch": 0.2358710882765063, "grad_norm": 0.3414044976234436, "learning_rate": 9.448421527571181e-06, "loss": 0.2952, "step": 8080 }, { "epoch": 0.23590028024287715, "grad_norm": 0.34494921565055847, "learning_rate": 9.448188877737364e-06, "loss": 0.2241, "step": 8081 }, { "epoch": 0.235929472209248, "grad_norm": 0.35709550976753235, "learning_rate": 9.44795618171483e-06, "loss": 0.2503, "step": 8082 }, { "epoch": 0.23595866417561887, "grad_norm": 0.3313763737678528, "learning_rate": 9.447723439505993e-06, "loss": 0.2147, "step": 8083 }, { "epoch": 0.23598785614198972, "grad_norm": 0.3336758017539978, "learning_rate": 9.44749065111327e-06, "loss": 0.3015, "step": 8084 }, { "epoch": 0.23601704810836058, "grad_norm": 0.3756922781467438, "learning_rate": 9.447257816539078e-06, "loss": 0.3254, "step": 8085 }, { "epoch": 0.23604624007473143, "grad_norm": 0.32256585359573364, "learning_rate": 9.447024935785836e-06, "loss": 0.2381, "step": 8086 }, { "epoch": 0.2360754320411023, "grad_norm": 0.4015427529811859, "learning_rate": 9.44679200885596e-06, "loss": 0.2296, "step": 8087 }, { "epoch": 0.23610462400747315, "grad_norm": 0.376295268535614, "learning_rate": 9.44655903575187e-06, "loss": 0.2984, "step": 8088 }, { "epoch": 0.236133815973844, "grad_norm": 0.3437384068965912, "learning_rate": 9.446326016475986e-06, "loss": 0.248, "step": 8089 }, { "epoch": 0.23616300794021486, "grad_norm": 0.40764153003692627, "learning_rate": 9.446092951030727e-06, "loss": 0.2295, "step": 8090 }, { "epoch": 0.23619219990658571, "grad_norm": 0.3821893334388733, "learning_rate": 9.445859839418512e-06, "loss": 0.2582, "step": 8091 }, { "epoch": 0.23622139187295657, "grad_norm": 0.37965524196624756, "learning_rate": 9.445626681641763e-06, "loss": 0.2656, "step": 8092 }, { "epoch": 0.23625058383932743, "grad_norm": 0.35110747814178467, "learning_rate": 9.4453934777029e-06, "loss": 0.2142, "step": 8093 }, { "epoch": 0.23627977580569828, "grad_norm": 0.4935617446899414, "learning_rate": 9.445160227604344e-06, "loss": 0.3018, "step": 8094 }, { "epoch": 0.23630896777206914, "grad_norm": 0.4611004889011383, "learning_rate": 9.444926931348519e-06, "loss": 0.2422, "step": 8095 }, { "epoch": 0.23633815973843997, "grad_norm": 0.37375861406326294, "learning_rate": 9.444693588937846e-06, "loss": 0.2977, "step": 8096 }, { "epoch": 0.23636735170481082, "grad_norm": 0.3850947618484497, "learning_rate": 9.444460200374747e-06, "loss": 0.2335, "step": 8097 }, { "epoch": 0.23639654367118168, "grad_norm": 0.3689201772212982, "learning_rate": 9.444226765661648e-06, "loss": 0.2474, "step": 8098 }, { "epoch": 0.23642573563755254, "grad_norm": 0.3482452630996704, "learning_rate": 9.443993284800972e-06, "loss": 0.2466, "step": 8099 }, { "epoch": 0.2364549276039234, "grad_norm": 0.33755409717559814, "learning_rate": 9.443759757795142e-06, "loss": 0.2401, "step": 8100 }, { "epoch": 0.23648411957029425, "grad_norm": 0.33506283164024353, "learning_rate": 9.443526184646586e-06, "loss": 0.256, "step": 8101 }, { "epoch": 0.2365133115366651, "grad_norm": 0.4296518564224243, "learning_rate": 9.443292565357724e-06, "loss": 0.2901, "step": 8102 }, { "epoch": 0.23654250350303596, "grad_norm": 0.33959662914276123, "learning_rate": 9.443058899930988e-06, "loss": 0.2509, "step": 8103 }, { "epoch": 0.23657169546940682, "grad_norm": 0.314395934343338, "learning_rate": 9.4428251883688e-06, "loss": 0.218, "step": 8104 }, { "epoch": 0.23660088743577767, "grad_norm": 0.3389822840690613, "learning_rate": 9.44259143067359e-06, "loss": 0.2161, "step": 8105 }, { "epoch": 0.23663007940214853, "grad_norm": 0.37730586528778076, "learning_rate": 9.442357626847782e-06, "loss": 0.2644, "step": 8106 }, { "epoch": 0.23665927136851939, "grad_norm": 0.30484315752983093, "learning_rate": 9.442123776893805e-06, "loss": 0.2287, "step": 8107 }, { "epoch": 0.23668846333489024, "grad_norm": 0.34135884046554565, "learning_rate": 9.441889880814088e-06, "loss": 0.2291, "step": 8108 }, { "epoch": 0.2367176553012611, "grad_norm": 0.3644741177558899, "learning_rate": 9.441655938611061e-06, "loss": 0.243, "step": 8109 }, { "epoch": 0.23674684726763195, "grad_norm": 0.6224737167358398, "learning_rate": 9.441421950287148e-06, "loss": 0.2483, "step": 8110 }, { "epoch": 0.2367760392340028, "grad_norm": 0.3405124843120575, "learning_rate": 9.441187915844786e-06, "loss": 0.2044, "step": 8111 }, { "epoch": 0.23680523120037367, "grad_norm": 0.3448275029659271, "learning_rate": 9.440953835286397e-06, "loss": 0.217, "step": 8112 }, { "epoch": 0.23683442316674452, "grad_norm": 0.3244805634021759, "learning_rate": 9.440719708614419e-06, "loss": 0.2082, "step": 8113 }, { "epoch": 0.23686361513311538, "grad_norm": 0.8011053204536438, "learning_rate": 9.440485535831278e-06, "loss": 0.2283, "step": 8114 }, { "epoch": 0.2368928070994862, "grad_norm": 0.38502445816993713, "learning_rate": 9.44025131693941e-06, "loss": 0.2623, "step": 8115 }, { "epoch": 0.23692199906585706, "grad_norm": 0.36993420124053955, "learning_rate": 9.440017051941242e-06, "loss": 0.2315, "step": 8116 }, { "epoch": 0.23695119103222792, "grad_norm": 0.37895822525024414, "learning_rate": 9.43978274083921e-06, "loss": 0.2291, "step": 8117 }, { "epoch": 0.23698038299859878, "grad_norm": 0.3271367847919464, "learning_rate": 9.439548383635746e-06, "loss": 0.2555, "step": 8118 }, { "epoch": 0.23700957496496963, "grad_norm": 0.30263590812683105, "learning_rate": 9.439313980333285e-06, "loss": 0.2372, "step": 8119 }, { "epoch": 0.2370387669313405, "grad_norm": 0.3824286460876465, "learning_rate": 9.439079530934258e-06, "loss": 0.2306, "step": 8120 }, { "epoch": 0.23706795889771135, "grad_norm": 0.3072246015071869, "learning_rate": 9.438845035441102e-06, "loss": 0.2093, "step": 8121 }, { "epoch": 0.2370971508640822, "grad_norm": 0.37148818373680115, "learning_rate": 9.43861049385625e-06, "loss": 0.2694, "step": 8122 }, { "epoch": 0.23712634283045306, "grad_norm": 0.4222774803638458, "learning_rate": 9.43837590618214e-06, "loss": 0.2366, "step": 8123 }, { "epoch": 0.2371555347968239, "grad_norm": 0.3996955454349518, "learning_rate": 9.438141272421206e-06, "loss": 0.2616, "step": 8124 }, { "epoch": 0.23718472676319477, "grad_norm": 0.3134467899799347, "learning_rate": 9.437906592575883e-06, "loss": 0.2332, "step": 8125 }, { "epoch": 0.23721391872956563, "grad_norm": 0.34969794750213623, "learning_rate": 9.437671866648611e-06, "loss": 0.2855, "step": 8126 }, { "epoch": 0.23724311069593648, "grad_norm": 0.3335971534252167, "learning_rate": 9.437437094641825e-06, "loss": 0.2412, "step": 8127 }, { "epoch": 0.23727230266230734, "grad_norm": 0.37223124504089355, "learning_rate": 9.437202276557965e-06, "loss": 0.2411, "step": 8128 }, { "epoch": 0.2373014946286782, "grad_norm": 0.3713492155075073, "learning_rate": 9.436967412399467e-06, "loss": 0.3058, "step": 8129 }, { "epoch": 0.23733068659504905, "grad_norm": 0.3500787913799286, "learning_rate": 9.43673250216877e-06, "loss": 0.2133, "step": 8130 }, { "epoch": 0.2373598785614199, "grad_norm": 0.3335404098033905, "learning_rate": 9.436497545868316e-06, "loss": 0.2027, "step": 8131 }, { "epoch": 0.23738907052779076, "grad_norm": 0.3116203844547272, "learning_rate": 9.436262543500541e-06, "loss": 0.2077, "step": 8132 }, { "epoch": 0.23741826249416162, "grad_norm": 0.3711353838443756, "learning_rate": 9.436027495067887e-06, "loss": 0.2329, "step": 8133 }, { "epoch": 0.23744745446053245, "grad_norm": 0.3256533443927765, "learning_rate": 9.435792400572796e-06, "loss": 0.2544, "step": 8134 }, { "epoch": 0.2374766464269033, "grad_norm": 0.34438589215278625, "learning_rate": 9.435557260017708e-06, "loss": 0.2846, "step": 8135 }, { "epoch": 0.23750583839327416, "grad_norm": 0.31846997141838074, "learning_rate": 9.435322073405062e-06, "loss": 0.1721, "step": 8136 }, { "epoch": 0.23753503035964502, "grad_norm": 0.36059167981147766, "learning_rate": 9.435086840737303e-06, "loss": 0.2584, "step": 8137 }, { "epoch": 0.23756422232601587, "grad_norm": 0.36803096532821655, "learning_rate": 9.434851562016873e-06, "loss": 0.2675, "step": 8138 }, { "epoch": 0.23759341429238673, "grad_norm": 0.3426344692707062, "learning_rate": 9.434616237246217e-06, "loss": 0.24, "step": 8139 }, { "epoch": 0.23762260625875758, "grad_norm": 0.33415597677230835, "learning_rate": 9.434380866427775e-06, "loss": 0.2157, "step": 8140 }, { "epoch": 0.23765179822512844, "grad_norm": 0.40449798107147217, "learning_rate": 9.434145449563992e-06, "loss": 0.2461, "step": 8141 }, { "epoch": 0.2376809901914993, "grad_norm": 0.48229992389678955, "learning_rate": 9.433909986657315e-06, "loss": 0.2457, "step": 8142 }, { "epoch": 0.23771018215787015, "grad_norm": 0.3536199629306793, "learning_rate": 9.433674477710187e-06, "loss": 0.2482, "step": 8143 }, { "epoch": 0.237739374124241, "grad_norm": 0.30357494950294495, "learning_rate": 9.43343892272505e-06, "loss": 0.239, "step": 8144 }, { "epoch": 0.23776856609061187, "grad_norm": 0.3912428021430969, "learning_rate": 9.433203321704358e-06, "loss": 0.2818, "step": 8145 }, { "epoch": 0.23779775805698272, "grad_norm": 0.3064288794994354, "learning_rate": 9.432967674650552e-06, "loss": 0.2167, "step": 8146 }, { "epoch": 0.23782695002335358, "grad_norm": 0.34585362672805786, "learning_rate": 9.432731981566079e-06, "loss": 0.2289, "step": 8147 }, { "epoch": 0.23785614198972443, "grad_norm": 0.3522467613220215, "learning_rate": 9.432496242453387e-06, "loss": 0.3044, "step": 8148 }, { "epoch": 0.2378853339560953, "grad_norm": 0.2775211036205292, "learning_rate": 9.432260457314926e-06, "loss": 0.2229, "step": 8149 }, { "epoch": 0.23791452592246615, "grad_norm": 0.3068786859512329, "learning_rate": 9.43202462615314e-06, "loss": 0.2543, "step": 8150 }, { "epoch": 0.237943717888837, "grad_norm": 0.3547200560569763, "learning_rate": 9.43178874897048e-06, "loss": 0.2653, "step": 8151 }, { "epoch": 0.23797290985520786, "grad_norm": 0.3167104721069336, "learning_rate": 9.431552825769396e-06, "loss": 0.2349, "step": 8152 }, { "epoch": 0.23800210182157872, "grad_norm": 0.6250479221343994, "learning_rate": 9.43131685655234e-06, "loss": 0.2427, "step": 8153 }, { "epoch": 0.23803129378794954, "grad_norm": 0.3137602210044861, "learning_rate": 9.431080841321757e-06, "loss": 0.2681, "step": 8154 }, { "epoch": 0.2380604857543204, "grad_norm": 0.3336685597896576, "learning_rate": 9.4308447800801e-06, "loss": 0.2485, "step": 8155 }, { "epoch": 0.23808967772069126, "grad_norm": 0.3125229477882385, "learning_rate": 9.430608672829821e-06, "loss": 0.2427, "step": 8156 }, { "epoch": 0.2381188696870621, "grad_norm": 0.31846827268600464, "learning_rate": 9.430372519573371e-06, "loss": 0.2515, "step": 8157 }, { "epoch": 0.23814806165343297, "grad_norm": 0.3292516767978668, "learning_rate": 9.430136320313202e-06, "loss": 0.2629, "step": 8158 }, { "epoch": 0.23817725361980382, "grad_norm": 0.35647428035736084, "learning_rate": 9.429900075051767e-06, "loss": 0.2183, "step": 8159 }, { "epoch": 0.23820644558617468, "grad_norm": 0.3359028697013855, "learning_rate": 9.429663783791519e-06, "loss": 0.2717, "step": 8160 }, { "epoch": 0.23823563755254554, "grad_norm": 0.3040851950645447, "learning_rate": 9.429427446534911e-06, "loss": 0.2183, "step": 8161 }, { "epoch": 0.2382648295189164, "grad_norm": 0.3026842772960663, "learning_rate": 9.429191063284398e-06, "loss": 0.2592, "step": 8162 }, { "epoch": 0.23829402148528725, "grad_norm": 0.30032509565353394, "learning_rate": 9.428954634042435e-06, "loss": 0.2067, "step": 8163 }, { "epoch": 0.2383232134516581, "grad_norm": 0.3303161859512329, "learning_rate": 9.428718158811474e-06, "loss": 0.2397, "step": 8164 }, { "epoch": 0.23835240541802896, "grad_norm": 0.2968933582305908, "learning_rate": 9.428481637593974e-06, "loss": 0.2292, "step": 8165 }, { "epoch": 0.23838159738439982, "grad_norm": 0.31172460317611694, "learning_rate": 9.42824507039239e-06, "loss": 0.2251, "step": 8166 }, { "epoch": 0.23841078935077067, "grad_norm": 0.29276496171951294, "learning_rate": 9.428008457209176e-06, "loss": 0.2518, "step": 8167 }, { "epoch": 0.23843998131714153, "grad_norm": 0.3523522615432739, "learning_rate": 9.427771798046793e-06, "loss": 0.22, "step": 8168 }, { "epoch": 0.2384691732835124, "grad_norm": 0.322464257478714, "learning_rate": 9.427535092907696e-06, "loss": 0.2263, "step": 8169 }, { "epoch": 0.23849836524988324, "grad_norm": 0.33022791147232056, "learning_rate": 9.427298341794343e-06, "loss": 0.2834, "step": 8170 }, { "epoch": 0.2385275572162541, "grad_norm": 0.31682518124580383, "learning_rate": 9.427061544709192e-06, "loss": 0.2684, "step": 8171 }, { "epoch": 0.23855674918262496, "grad_norm": 0.333871454000473, "learning_rate": 9.426824701654704e-06, "loss": 0.2961, "step": 8172 }, { "epoch": 0.23858594114899578, "grad_norm": 0.38269221782684326, "learning_rate": 9.426587812633335e-06, "loss": 0.2121, "step": 8173 }, { "epoch": 0.23861513311536664, "grad_norm": 0.285952627658844, "learning_rate": 9.426350877647547e-06, "loss": 0.1819, "step": 8174 }, { "epoch": 0.2386443250817375, "grad_norm": 0.3778785765171051, "learning_rate": 9.4261138966998e-06, "loss": 0.2648, "step": 8175 }, { "epoch": 0.23867351704810835, "grad_norm": 0.2952156364917755, "learning_rate": 9.425876869792555e-06, "loss": 0.2125, "step": 8176 }, { "epoch": 0.2387027090144792, "grad_norm": 0.31984183192253113, "learning_rate": 9.425639796928272e-06, "loss": 0.2773, "step": 8177 }, { "epoch": 0.23873190098085006, "grad_norm": 0.3262731432914734, "learning_rate": 9.425402678109414e-06, "loss": 0.2711, "step": 8178 }, { "epoch": 0.23876109294722092, "grad_norm": 0.30973199009895325, "learning_rate": 9.425165513338441e-06, "loss": 0.2229, "step": 8179 }, { "epoch": 0.23879028491359178, "grad_norm": 0.3178035616874695, "learning_rate": 9.42492830261782e-06, "loss": 0.291, "step": 8180 }, { "epoch": 0.23881947687996263, "grad_norm": 0.3236691653728485, "learning_rate": 9.424691045950008e-06, "loss": 0.2836, "step": 8181 }, { "epoch": 0.2388486688463335, "grad_norm": 0.3835706114768982, "learning_rate": 9.424453743337474e-06, "loss": 0.3349, "step": 8182 }, { "epoch": 0.23887786081270435, "grad_norm": 0.3474198877811432, "learning_rate": 9.42421639478268e-06, "loss": 0.2881, "step": 8183 }, { "epoch": 0.2389070527790752, "grad_norm": 0.357706755399704, "learning_rate": 9.42397900028809e-06, "loss": 0.291, "step": 8184 }, { "epoch": 0.23893624474544606, "grad_norm": 0.3576372563838959, "learning_rate": 9.42374155985617e-06, "loss": 0.2554, "step": 8185 }, { "epoch": 0.23896543671181691, "grad_norm": 0.3433026969432831, "learning_rate": 9.423504073489386e-06, "loss": 0.2375, "step": 8186 }, { "epoch": 0.23899462867818777, "grad_norm": 0.3507944345474243, "learning_rate": 9.423266541190204e-06, "loss": 0.26, "step": 8187 }, { "epoch": 0.23902382064455863, "grad_norm": 0.355984091758728, "learning_rate": 9.423028962961088e-06, "loss": 0.2687, "step": 8188 }, { "epoch": 0.23905301261092948, "grad_norm": 0.32584241032600403, "learning_rate": 9.422791338804506e-06, "loss": 0.2223, "step": 8189 }, { "epoch": 0.23908220457730034, "grad_norm": 0.3224005401134491, "learning_rate": 9.422553668722927e-06, "loss": 0.2177, "step": 8190 }, { "epoch": 0.2391113965436712, "grad_norm": 0.3042241930961609, "learning_rate": 9.422315952718817e-06, "loss": 0.2458, "step": 8191 }, { "epoch": 0.23914058851004202, "grad_norm": 0.30202409625053406, "learning_rate": 9.422078190794646e-06, "loss": 0.2474, "step": 8192 }, { "epoch": 0.23916978047641288, "grad_norm": 0.3430411219596863, "learning_rate": 9.421840382952882e-06, "loss": 0.2782, "step": 8193 }, { "epoch": 0.23919897244278374, "grad_norm": 0.347709059715271, "learning_rate": 9.421602529195994e-06, "loss": 0.2493, "step": 8194 }, { "epoch": 0.2392281644091546, "grad_norm": 0.36392295360565186, "learning_rate": 9.421364629526454e-06, "loss": 0.2702, "step": 8195 }, { "epoch": 0.23925735637552545, "grad_norm": 0.35980817675590515, "learning_rate": 9.42112668394673e-06, "loss": 0.2502, "step": 8196 }, { "epoch": 0.2392865483418963, "grad_norm": 0.33751019835472107, "learning_rate": 9.42088869245929e-06, "loss": 0.2339, "step": 8197 }, { "epoch": 0.23931574030826716, "grad_norm": 0.5543847680091858, "learning_rate": 9.420650655066614e-06, "loss": 0.2765, "step": 8198 }, { "epoch": 0.23934493227463802, "grad_norm": 0.33785703778266907, "learning_rate": 9.420412571771165e-06, "loss": 0.2532, "step": 8199 }, { "epoch": 0.23937412424100887, "grad_norm": 0.33247289061546326, "learning_rate": 9.420174442575419e-06, "loss": 0.2902, "step": 8200 }, { "epoch": 0.23940331620737973, "grad_norm": 0.3526739776134491, "learning_rate": 9.419936267481849e-06, "loss": 0.189, "step": 8201 }, { "epoch": 0.23943250817375059, "grad_norm": 0.3690943717956543, "learning_rate": 9.419698046492924e-06, "loss": 0.2851, "step": 8202 }, { "epoch": 0.23946170014012144, "grad_norm": 0.3491789698600769, "learning_rate": 9.419459779611125e-06, "loss": 0.2462, "step": 8203 }, { "epoch": 0.2394908921064923, "grad_norm": 0.28689703345298767, "learning_rate": 9.41922146683892e-06, "loss": 0.1945, "step": 8204 }, { "epoch": 0.23952008407286315, "grad_norm": 0.4568687975406647, "learning_rate": 9.418983108178785e-06, "loss": 0.2954, "step": 8205 }, { "epoch": 0.239549276039234, "grad_norm": 0.32758820056915283, "learning_rate": 9.418744703633195e-06, "loss": 0.2377, "step": 8206 }, { "epoch": 0.23957846800560487, "grad_norm": 0.34924155473709106, "learning_rate": 9.418506253204629e-06, "loss": 0.2342, "step": 8207 }, { "epoch": 0.23960765997197572, "grad_norm": 0.3652196526527405, "learning_rate": 9.418267756895559e-06, "loss": 0.2831, "step": 8208 }, { "epoch": 0.23963685193834658, "grad_norm": 0.368452787399292, "learning_rate": 9.418029214708462e-06, "loss": 0.2645, "step": 8209 }, { "epoch": 0.23966604390471744, "grad_norm": 0.35296830534935, "learning_rate": 9.417790626645816e-06, "loss": 0.2134, "step": 8210 }, { "epoch": 0.23969523587108826, "grad_norm": 0.3533911108970642, "learning_rate": 9.417551992710097e-06, "loss": 0.2405, "step": 8211 }, { "epoch": 0.23972442783745912, "grad_norm": 0.3550668954849243, "learning_rate": 9.417313312903784e-06, "loss": 0.2586, "step": 8212 }, { "epoch": 0.23975361980382998, "grad_norm": 0.3279767334461212, "learning_rate": 9.417074587229356e-06, "loss": 0.248, "step": 8213 }, { "epoch": 0.23978281177020083, "grad_norm": 0.44858574867248535, "learning_rate": 9.416835815689291e-06, "loss": 0.2391, "step": 8214 }, { "epoch": 0.2398120037365717, "grad_norm": 0.30988380312919617, "learning_rate": 9.416596998286067e-06, "loss": 0.1858, "step": 8215 }, { "epoch": 0.23984119570294254, "grad_norm": 0.35272416472435, "learning_rate": 9.416358135022166e-06, "loss": 0.2582, "step": 8216 }, { "epoch": 0.2398703876693134, "grad_norm": 0.31409013271331787, "learning_rate": 9.416119225900068e-06, "loss": 0.2417, "step": 8217 }, { "epoch": 0.23989957963568426, "grad_norm": 0.39042460918426514, "learning_rate": 9.415880270922256e-06, "loss": 0.2638, "step": 8218 }, { "epoch": 0.2399287716020551, "grad_norm": 0.49020716547966003, "learning_rate": 9.415641270091204e-06, "loss": 0.2851, "step": 8219 }, { "epoch": 0.23995796356842597, "grad_norm": 0.3628256022930145, "learning_rate": 9.4154022234094e-06, "loss": 0.264, "step": 8220 }, { "epoch": 0.23998715553479683, "grad_norm": 0.7084362506866455, "learning_rate": 9.415163130879326e-06, "loss": 0.2204, "step": 8221 }, { "epoch": 0.24001634750116768, "grad_norm": 0.3264804780483246, "learning_rate": 9.414923992503461e-06, "loss": 0.2362, "step": 8222 }, { "epoch": 0.24004553946753854, "grad_norm": 0.3420352637767792, "learning_rate": 9.414684808284291e-06, "loss": 0.2221, "step": 8223 }, { "epoch": 0.2400747314339094, "grad_norm": 0.36008068919181824, "learning_rate": 9.414445578224298e-06, "loss": 0.273, "step": 8224 }, { "epoch": 0.24010392340028025, "grad_norm": 0.35860148072242737, "learning_rate": 9.41420630232597e-06, "loss": 0.2761, "step": 8225 }, { "epoch": 0.2401331153666511, "grad_norm": 0.3530060946941376, "learning_rate": 9.413966980591785e-06, "loss": 0.2319, "step": 8226 }, { "epoch": 0.24016230733302196, "grad_norm": 0.2916196286678314, "learning_rate": 9.413727613024234e-06, "loss": 0.1829, "step": 8227 }, { "epoch": 0.24019149929939282, "grad_norm": 0.3238281011581421, "learning_rate": 9.413488199625799e-06, "loss": 0.2562, "step": 8228 }, { "epoch": 0.24022069126576368, "grad_norm": 0.3346211314201355, "learning_rate": 9.413248740398968e-06, "loss": 0.2343, "step": 8229 }, { "epoch": 0.2402498832321345, "grad_norm": 0.4587861895561218, "learning_rate": 9.413009235346225e-06, "loss": 0.2188, "step": 8230 }, { "epoch": 0.24027907519850536, "grad_norm": 0.38300150632858276, "learning_rate": 9.41276968447006e-06, "loss": 0.272, "step": 8231 }, { "epoch": 0.24030826716487622, "grad_norm": 0.3409744203090668, "learning_rate": 9.41253008777296e-06, "loss": 0.2127, "step": 8232 }, { "epoch": 0.24033745913124707, "grad_norm": 0.33887481689453125, "learning_rate": 9.41229044525741e-06, "loss": 0.2199, "step": 8233 }, { "epoch": 0.24036665109761793, "grad_norm": 0.35587939620018005, "learning_rate": 9.4120507569259e-06, "loss": 0.2726, "step": 8234 }, { "epoch": 0.24039584306398878, "grad_norm": 0.34453532099723816, "learning_rate": 9.41181102278092e-06, "loss": 0.2599, "step": 8235 }, { "epoch": 0.24042503503035964, "grad_norm": 0.3885751962661743, "learning_rate": 9.411571242824958e-06, "loss": 0.2601, "step": 8236 }, { "epoch": 0.2404542269967305, "grad_norm": 0.32817062735557556, "learning_rate": 9.411331417060506e-06, "loss": 0.2386, "step": 8237 }, { "epoch": 0.24048341896310135, "grad_norm": 0.3242265284061432, "learning_rate": 9.41109154549005e-06, "loss": 0.2665, "step": 8238 }, { "epoch": 0.2405126109294722, "grad_norm": 0.37384232878685, "learning_rate": 9.410851628116085e-06, "loss": 0.2076, "step": 8239 }, { "epoch": 0.24054180289584307, "grad_norm": 0.3366762697696686, "learning_rate": 9.4106116649411e-06, "loss": 0.2856, "step": 8240 }, { "epoch": 0.24057099486221392, "grad_norm": 0.4461609721183777, "learning_rate": 9.410371655967588e-06, "loss": 0.2941, "step": 8241 }, { "epoch": 0.24060018682858478, "grad_norm": 0.5754302740097046, "learning_rate": 9.410131601198038e-06, "loss": 0.2299, "step": 8242 }, { "epoch": 0.24062937879495563, "grad_norm": 0.3431137502193451, "learning_rate": 9.409891500634947e-06, "loss": 0.2449, "step": 8243 }, { "epoch": 0.2406585707613265, "grad_norm": 0.3841384947299957, "learning_rate": 9.409651354280807e-06, "loss": 0.2217, "step": 8244 }, { "epoch": 0.24068776272769735, "grad_norm": 0.38637351989746094, "learning_rate": 9.409411162138108e-06, "loss": 0.2311, "step": 8245 }, { "epoch": 0.2407169546940682, "grad_norm": 0.3845319151878357, "learning_rate": 9.40917092420935e-06, "loss": 0.3036, "step": 8246 }, { "epoch": 0.24074614666043906, "grad_norm": 0.39200347661972046, "learning_rate": 9.408930640497024e-06, "loss": 0.256, "step": 8247 }, { "epoch": 0.24077533862680991, "grad_norm": 0.3127330541610718, "learning_rate": 9.408690311003625e-06, "loss": 0.2656, "step": 8248 }, { "epoch": 0.24080453059318074, "grad_norm": 0.3666972815990448, "learning_rate": 9.408449935731648e-06, "loss": 0.2821, "step": 8249 }, { "epoch": 0.2408337225595516, "grad_norm": 0.3207510709762573, "learning_rate": 9.40820951468359e-06, "loss": 0.227, "step": 8250 }, { "epoch": 0.24086291452592246, "grad_norm": 0.3734821081161499, "learning_rate": 9.40796904786195e-06, "loss": 0.2603, "step": 8251 }, { "epoch": 0.2408921064922933, "grad_norm": 0.3173532485961914, "learning_rate": 9.40772853526922e-06, "loss": 0.2027, "step": 8252 }, { "epoch": 0.24092129845866417, "grad_norm": 0.40915805101394653, "learning_rate": 9.407487976907901e-06, "loss": 0.337, "step": 8253 }, { "epoch": 0.24095049042503502, "grad_norm": 0.30456089973449707, "learning_rate": 9.40724737278049e-06, "loss": 0.1886, "step": 8254 }, { "epoch": 0.24097968239140588, "grad_norm": 0.31627416610717773, "learning_rate": 9.407006722889484e-06, "loss": 0.2399, "step": 8255 }, { "epoch": 0.24100887435777674, "grad_norm": 0.3456462323665619, "learning_rate": 9.406766027237384e-06, "loss": 0.2369, "step": 8256 }, { "epoch": 0.2410380663241476, "grad_norm": 0.3353029489517212, "learning_rate": 9.406525285826686e-06, "loss": 0.2342, "step": 8257 }, { "epoch": 0.24106725829051845, "grad_norm": 0.3396267592906952, "learning_rate": 9.406284498659895e-06, "loss": 0.2417, "step": 8258 }, { "epoch": 0.2410964502568893, "grad_norm": 0.34706419706344604, "learning_rate": 9.406043665739508e-06, "loss": 0.2529, "step": 8259 }, { "epoch": 0.24112564222326016, "grad_norm": 0.29758521914482117, "learning_rate": 9.405802787068023e-06, "loss": 0.1949, "step": 8260 }, { "epoch": 0.24115483418963102, "grad_norm": 0.3858920931816101, "learning_rate": 9.405561862647947e-06, "loss": 0.2829, "step": 8261 }, { "epoch": 0.24118402615600187, "grad_norm": 0.3784865438938141, "learning_rate": 9.40532089248178e-06, "loss": 0.2552, "step": 8262 }, { "epoch": 0.24121321812237273, "grad_norm": 0.35639795660972595, "learning_rate": 9.40507987657202e-06, "loss": 0.2777, "step": 8263 }, { "epoch": 0.2412424100887436, "grad_norm": 0.44872865080833435, "learning_rate": 9.404838814921175e-06, "loss": 0.2427, "step": 8264 }, { "epoch": 0.24127160205511444, "grad_norm": 0.33902648091316223, "learning_rate": 9.404597707531744e-06, "loss": 0.2282, "step": 8265 }, { "epoch": 0.2413007940214853, "grad_norm": 0.36026471853256226, "learning_rate": 9.404356554406233e-06, "loss": 0.2547, "step": 8266 }, { "epoch": 0.24132998598785615, "grad_norm": 0.873605489730835, "learning_rate": 9.404115355547148e-06, "loss": 0.2354, "step": 8267 }, { "epoch": 0.24135917795422698, "grad_norm": 0.31934303045272827, "learning_rate": 9.403874110956988e-06, "loss": 0.2358, "step": 8268 }, { "epoch": 0.24138836992059784, "grad_norm": 0.35268327593803406, "learning_rate": 9.403632820638262e-06, "loss": 0.2654, "step": 8269 }, { "epoch": 0.2414175618869687, "grad_norm": 0.3240366280078888, "learning_rate": 9.403391484593474e-06, "loss": 0.2393, "step": 8270 }, { "epoch": 0.24144675385333955, "grad_norm": 0.37129268050193787, "learning_rate": 9.403150102825131e-06, "loss": 0.2609, "step": 8271 }, { "epoch": 0.2414759458197104, "grad_norm": 0.31024324893951416, "learning_rate": 9.40290867533574e-06, "loss": 0.2426, "step": 8272 }, { "epoch": 0.24150513778608126, "grad_norm": 0.3514021337032318, "learning_rate": 9.402667202127806e-06, "loss": 0.2652, "step": 8273 }, { "epoch": 0.24153432975245212, "grad_norm": 0.32705989480018616, "learning_rate": 9.402425683203838e-06, "loss": 0.2655, "step": 8274 }, { "epoch": 0.24156352171882298, "grad_norm": 0.3278718888759613, "learning_rate": 9.402184118566343e-06, "loss": 0.2564, "step": 8275 }, { "epoch": 0.24159271368519383, "grad_norm": 0.31574952602386475, "learning_rate": 9.401942508217829e-06, "loss": 0.2415, "step": 8276 }, { "epoch": 0.2416219056515647, "grad_norm": 0.31818878650665283, "learning_rate": 9.401700852160805e-06, "loss": 0.2306, "step": 8277 }, { "epoch": 0.24165109761793555, "grad_norm": 0.3134782314300537, "learning_rate": 9.40145915039778e-06, "loss": 0.2378, "step": 8278 }, { "epoch": 0.2416802895843064, "grad_norm": 0.3330112099647522, "learning_rate": 9.401217402931266e-06, "loss": 0.2572, "step": 8279 }, { "epoch": 0.24170948155067726, "grad_norm": 0.5131314992904663, "learning_rate": 9.40097560976377e-06, "loss": 0.2632, "step": 8280 }, { "epoch": 0.2417386735170481, "grad_norm": 0.38229045271873474, "learning_rate": 9.400733770897806e-06, "loss": 0.2603, "step": 8281 }, { "epoch": 0.24176786548341897, "grad_norm": 0.3503148555755615, "learning_rate": 9.400491886335884e-06, "loss": 0.2774, "step": 8282 }, { "epoch": 0.24179705744978983, "grad_norm": 0.370342880487442, "learning_rate": 9.400249956080512e-06, "loss": 0.2469, "step": 8283 }, { "epoch": 0.24182624941616068, "grad_norm": 0.33411622047424316, "learning_rate": 9.400007980134208e-06, "loss": 0.2472, "step": 8284 }, { "epoch": 0.24185544138253154, "grad_norm": 0.3418601155281067, "learning_rate": 9.39976595849948e-06, "loss": 0.2231, "step": 8285 }, { "epoch": 0.2418846333489024, "grad_norm": 0.3353823125362396, "learning_rate": 9.399523891178844e-06, "loss": 0.2558, "step": 8286 }, { "epoch": 0.24191382531527322, "grad_norm": 0.6017096042633057, "learning_rate": 9.399281778174811e-06, "loss": 0.2479, "step": 8287 }, { "epoch": 0.24194301728164408, "grad_norm": 0.35302460193634033, "learning_rate": 9.399039619489898e-06, "loss": 0.2753, "step": 8288 }, { "epoch": 0.24197220924801494, "grad_norm": 0.32459548115730286, "learning_rate": 9.39879741512662e-06, "loss": 0.219, "step": 8289 }, { "epoch": 0.2420014012143858, "grad_norm": 0.4555983245372772, "learning_rate": 9.398555165087486e-06, "loss": 0.2329, "step": 8290 }, { "epoch": 0.24203059318075665, "grad_norm": 0.3454322814941406, "learning_rate": 9.398312869375017e-06, "loss": 0.223, "step": 8291 }, { "epoch": 0.2420597851471275, "grad_norm": 0.3270604908466339, "learning_rate": 9.39807052799173e-06, "loss": 0.1907, "step": 8292 }, { "epoch": 0.24208897711349836, "grad_norm": 0.37451329827308655, "learning_rate": 9.397828140940135e-06, "loss": 0.2322, "step": 8293 }, { "epoch": 0.24211816907986922, "grad_norm": 0.3184490501880646, "learning_rate": 9.397585708222755e-06, "loss": 0.2218, "step": 8294 }, { "epoch": 0.24214736104624007, "grad_norm": 0.30510303378105164, "learning_rate": 9.397343229842104e-06, "loss": 0.2339, "step": 8295 }, { "epoch": 0.24217655301261093, "grad_norm": 0.3224931061267853, "learning_rate": 9.397100705800702e-06, "loss": 0.2431, "step": 8296 }, { "epoch": 0.24220574497898179, "grad_norm": 0.3315437436103821, "learning_rate": 9.396858136101066e-06, "loss": 0.2578, "step": 8297 }, { "epoch": 0.24223493694535264, "grad_norm": 0.38295778632164, "learning_rate": 9.396615520745714e-06, "loss": 0.2249, "step": 8298 }, { "epoch": 0.2422641289117235, "grad_norm": 0.348927766084671, "learning_rate": 9.396372859737166e-06, "loss": 0.277, "step": 8299 }, { "epoch": 0.24229332087809435, "grad_norm": 0.31470340490341187, "learning_rate": 9.396130153077942e-06, "loss": 0.2335, "step": 8300 }, { "epoch": 0.2423225128444652, "grad_norm": 0.40304455161094666, "learning_rate": 9.395887400770563e-06, "loss": 0.244, "step": 8301 }, { "epoch": 0.24235170481083607, "grad_norm": 0.3775362968444824, "learning_rate": 9.395644602817549e-06, "loss": 0.2338, "step": 8302 }, { "epoch": 0.24238089677720692, "grad_norm": 0.3068006634712219, "learning_rate": 9.39540175922142e-06, "loss": 0.2147, "step": 8303 }, { "epoch": 0.24241008874357778, "grad_norm": 0.37230783700942993, "learning_rate": 9.3951588699847e-06, "loss": 0.2374, "step": 8304 }, { "epoch": 0.24243928070994863, "grad_norm": 0.3241908550262451, "learning_rate": 9.394915935109908e-06, "loss": 0.2021, "step": 8305 }, { "epoch": 0.24246847267631946, "grad_norm": 0.33402127027511597, "learning_rate": 9.394672954599569e-06, "loss": 0.269, "step": 8306 }, { "epoch": 0.24249766464269032, "grad_norm": 0.33297884464263916, "learning_rate": 9.394429928456206e-06, "loss": 0.2726, "step": 8307 }, { "epoch": 0.24252685660906118, "grad_norm": 0.32985273003578186, "learning_rate": 9.39418685668234e-06, "loss": 0.2296, "step": 8308 }, { "epoch": 0.24255604857543203, "grad_norm": 0.34690576791763306, "learning_rate": 9.393943739280498e-06, "loss": 0.2722, "step": 8309 }, { "epoch": 0.2425852405418029, "grad_norm": 0.34135040640830994, "learning_rate": 9.393700576253202e-06, "loss": 0.2775, "step": 8310 }, { "epoch": 0.24261443250817374, "grad_norm": 0.29626840353012085, "learning_rate": 9.39345736760298e-06, "loss": 0.2076, "step": 8311 }, { "epoch": 0.2426436244745446, "grad_norm": 0.41591763496398926, "learning_rate": 9.393214113332355e-06, "loss": 0.2887, "step": 8312 }, { "epoch": 0.24267281644091546, "grad_norm": 0.36785945296287537, "learning_rate": 9.392970813443852e-06, "loss": 0.2524, "step": 8313 }, { "epoch": 0.2427020084072863, "grad_norm": 0.3350487947463989, "learning_rate": 9.392727467939999e-06, "loss": 0.2259, "step": 8314 }, { "epoch": 0.24273120037365717, "grad_norm": 0.32341691851615906, "learning_rate": 9.392484076823325e-06, "loss": 0.2284, "step": 8315 }, { "epoch": 0.24276039234002803, "grad_norm": 0.32070842385292053, "learning_rate": 9.392240640096353e-06, "loss": 0.2405, "step": 8316 }, { "epoch": 0.24278958430639888, "grad_norm": 0.32872048020362854, "learning_rate": 9.391997157761612e-06, "loss": 0.2575, "step": 8317 }, { "epoch": 0.24281877627276974, "grad_norm": 0.40433183312416077, "learning_rate": 9.391753629821633e-06, "loss": 0.2685, "step": 8318 }, { "epoch": 0.2428479682391406, "grad_norm": 0.3486144542694092, "learning_rate": 9.391510056278941e-06, "loss": 0.2221, "step": 8319 }, { "epoch": 0.24287716020551145, "grad_norm": 0.3512171804904938, "learning_rate": 9.391266437136069e-06, "loss": 0.2423, "step": 8320 }, { "epoch": 0.2429063521718823, "grad_norm": 0.3473149240016937, "learning_rate": 9.391022772395542e-06, "loss": 0.2221, "step": 8321 }, { "epoch": 0.24293554413825316, "grad_norm": 0.38404783606529236, "learning_rate": 9.390779062059894e-06, "loss": 0.2728, "step": 8322 }, { "epoch": 0.24296473610462402, "grad_norm": 0.3587456941604614, "learning_rate": 9.390535306131654e-06, "loss": 0.2484, "step": 8323 }, { "epoch": 0.24299392807099487, "grad_norm": 0.3859853744506836, "learning_rate": 9.390291504613354e-06, "loss": 0.2558, "step": 8324 }, { "epoch": 0.24302312003736573, "grad_norm": 0.385490357875824, "learning_rate": 9.390047657507525e-06, "loss": 0.2525, "step": 8325 }, { "epoch": 0.24305231200373656, "grad_norm": 0.3686811625957489, "learning_rate": 9.389803764816698e-06, "loss": 0.2461, "step": 8326 }, { "epoch": 0.24308150397010742, "grad_norm": 0.36901867389678955, "learning_rate": 9.389559826543407e-06, "loss": 0.2522, "step": 8327 }, { "epoch": 0.24311069593647827, "grad_norm": 0.3742803633213043, "learning_rate": 9.389315842690185e-06, "loss": 0.2793, "step": 8328 }, { "epoch": 0.24313988790284913, "grad_norm": 0.42020362615585327, "learning_rate": 9.389071813259564e-06, "loss": 0.251, "step": 8329 }, { "epoch": 0.24316907986921998, "grad_norm": 0.36886274814605713, "learning_rate": 9.388827738254079e-06, "loss": 0.2606, "step": 8330 }, { "epoch": 0.24319827183559084, "grad_norm": 0.34734269976615906, "learning_rate": 9.388583617676265e-06, "loss": 0.2229, "step": 8331 }, { "epoch": 0.2432274638019617, "grad_norm": 0.36868909001350403, "learning_rate": 9.388339451528656e-06, "loss": 0.2318, "step": 8332 }, { "epoch": 0.24325665576833255, "grad_norm": 0.3518023192882538, "learning_rate": 9.388095239813786e-06, "loss": 0.2405, "step": 8333 }, { "epoch": 0.2432858477347034, "grad_norm": 0.3419235050678253, "learning_rate": 9.387850982534194e-06, "loss": 0.271, "step": 8334 }, { "epoch": 0.24331503970107426, "grad_norm": 0.3312421441078186, "learning_rate": 9.387606679692416e-06, "loss": 0.2518, "step": 8335 }, { "epoch": 0.24334423166744512, "grad_norm": 0.3806789219379425, "learning_rate": 9.387362331290986e-06, "loss": 0.2384, "step": 8336 }, { "epoch": 0.24337342363381598, "grad_norm": 0.3398585021495819, "learning_rate": 9.387117937332441e-06, "loss": 0.2204, "step": 8337 }, { "epoch": 0.24340261560018683, "grad_norm": 0.34874701499938965, "learning_rate": 9.386873497819323e-06, "loss": 0.2599, "step": 8338 }, { "epoch": 0.2434318075665577, "grad_norm": 0.3641451895236969, "learning_rate": 9.386629012754167e-06, "loss": 0.2729, "step": 8339 }, { "epoch": 0.24346099953292855, "grad_norm": 0.3339400887489319, "learning_rate": 9.38638448213951e-06, "loss": 0.2551, "step": 8340 }, { "epoch": 0.2434901914992994, "grad_norm": 0.35920199751853943, "learning_rate": 9.386139905977895e-06, "loss": 0.2072, "step": 8341 }, { "epoch": 0.24351938346567026, "grad_norm": 0.312163770198822, "learning_rate": 9.385895284271862e-06, "loss": 0.2479, "step": 8342 }, { "epoch": 0.24354857543204111, "grad_norm": 0.3670368790626526, "learning_rate": 9.385650617023946e-06, "loss": 0.2818, "step": 8343 }, { "epoch": 0.24357776739841197, "grad_norm": 0.2859475016593933, "learning_rate": 9.385405904236693e-06, "loss": 0.2113, "step": 8344 }, { "epoch": 0.2436069593647828, "grad_norm": 0.36118224263191223, "learning_rate": 9.38516114591264e-06, "loss": 0.268, "step": 8345 }, { "epoch": 0.24363615133115366, "grad_norm": 0.3382274806499481, "learning_rate": 9.384916342054331e-06, "loss": 0.2378, "step": 8346 }, { "epoch": 0.2436653432975245, "grad_norm": 0.32278507947921753, "learning_rate": 9.384671492664306e-06, "loss": 0.2725, "step": 8347 }, { "epoch": 0.24369453526389537, "grad_norm": 0.3419265151023865, "learning_rate": 9.384426597745109e-06, "loss": 0.24, "step": 8348 }, { "epoch": 0.24372372723026622, "grad_norm": 0.354076623916626, "learning_rate": 9.384181657299284e-06, "loss": 0.202, "step": 8349 }, { "epoch": 0.24375291919663708, "grad_norm": 0.31496554613113403, "learning_rate": 9.38393667132937e-06, "loss": 0.2283, "step": 8350 }, { "epoch": 0.24378211116300794, "grad_norm": 0.3899843096733093, "learning_rate": 9.383691639837916e-06, "loss": 0.2635, "step": 8351 }, { "epoch": 0.2438113031293788, "grad_norm": 0.3440299332141876, "learning_rate": 9.383446562827462e-06, "loss": 0.2709, "step": 8352 }, { "epoch": 0.24384049509574965, "grad_norm": 0.3577499985694885, "learning_rate": 9.383201440300558e-06, "loss": 0.2767, "step": 8353 }, { "epoch": 0.2438696870621205, "grad_norm": 0.32496175169944763, "learning_rate": 9.382956272259745e-06, "loss": 0.2706, "step": 8354 }, { "epoch": 0.24389887902849136, "grad_norm": 0.35303544998168945, "learning_rate": 9.382711058707568e-06, "loss": 0.2712, "step": 8355 }, { "epoch": 0.24392807099486222, "grad_norm": 0.3638770878314972, "learning_rate": 9.382465799646578e-06, "loss": 0.2693, "step": 8356 }, { "epoch": 0.24395726296123307, "grad_norm": 0.34862038493156433, "learning_rate": 9.382220495079317e-06, "loss": 0.2189, "step": 8357 }, { "epoch": 0.24398645492760393, "grad_norm": 0.3551633954048157, "learning_rate": 9.381975145008335e-06, "loss": 0.2342, "step": 8358 }, { "epoch": 0.24401564689397479, "grad_norm": 0.35123211145401, "learning_rate": 9.381729749436178e-06, "loss": 0.2445, "step": 8359 }, { "epoch": 0.24404483886034564, "grad_norm": 0.28436750173568726, "learning_rate": 9.381484308365393e-06, "loss": 0.1971, "step": 8360 }, { "epoch": 0.2440740308267165, "grad_norm": 0.42616748809814453, "learning_rate": 9.381238821798533e-06, "loss": 0.2432, "step": 8361 }, { "epoch": 0.24410322279308735, "grad_norm": 0.4047122895717621, "learning_rate": 9.380993289738144e-06, "loss": 0.2741, "step": 8362 }, { "epoch": 0.2441324147594582, "grad_norm": 0.3552830219268799, "learning_rate": 9.380747712186776e-06, "loss": 0.1974, "step": 8363 }, { "epoch": 0.24416160672582904, "grad_norm": 0.3700730502605438, "learning_rate": 9.380502089146979e-06, "loss": 0.2589, "step": 8364 }, { "epoch": 0.2441907986921999, "grad_norm": 0.3106541633605957, "learning_rate": 9.380256420621303e-06, "loss": 0.2044, "step": 8365 }, { "epoch": 0.24421999065857075, "grad_norm": 0.3205084502696991, "learning_rate": 9.380010706612299e-06, "loss": 0.2798, "step": 8366 }, { "epoch": 0.2442491826249416, "grad_norm": 0.29469189047813416, "learning_rate": 9.37976494712252e-06, "loss": 0.1943, "step": 8367 }, { "epoch": 0.24427837459131246, "grad_norm": 0.3935413062572479, "learning_rate": 9.379519142154517e-06, "loss": 0.2524, "step": 8368 }, { "epoch": 0.24430756655768332, "grad_norm": 0.29499807953834534, "learning_rate": 9.37927329171084e-06, "loss": 0.2159, "step": 8369 }, { "epoch": 0.24433675852405418, "grad_norm": 0.34759417176246643, "learning_rate": 9.379027395794044e-06, "loss": 0.2231, "step": 8370 }, { "epoch": 0.24436595049042503, "grad_norm": 0.44541454315185547, "learning_rate": 9.378781454406685e-06, "loss": 0.2533, "step": 8371 }, { "epoch": 0.2443951424567959, "grad_norm": 0.36875954270362854, "learning_rate": 9.378535467551314e-06, "loss": 0.267, "step": 8372 }, { "epoch": 0.24442433442316674, "grad_norm": 0.3352745771408081, "learning_rate": 9.378289435230481e-06, "loss": 0.2447, "step": 8373 }, { "epoch": 0.2444535263895376, "grad_norm": 0.3207005560398102, "learning_rate": 9.378043357446748e-06, "loss": 0.2488, "step": 8374 }, { "epoch": 0.24448271835590846, "grad_norm": 0.3022220730781555, "learning_rate": 9.377797234202667e-06, "loss": 0.2697, "step": 8375 }, { "epoch": 0.2445119103222793, "grad_norm": 0.35599637031555176, "learning_rate": 9.377551065500794e-06, "loss": 0.2509, "step": 8376 }, { "epoch": 0.24454110228865017, "grad_norm": 0.3434915840625763, "learning_rate": 9.377304851343684e-06, "loss": 0.2565, "step": 8377 }, { "epoch": 0.24457029425502103, "grad_norm": 0.32540279626846313, "learning_rate": 9.377058591733897e-06, "loss": 0.2119, "step": 8378 }, { "epoch": 0.24459948622139188, "grad_norm": 0.3200509250164032, "learning_rate": 9.376812286673987e-06, "loss": 0.2223, "step": 8379 }, { "epoch": 0.24462867818776274, "grad_norm": 0.3607370853424072, "learning_rate": 9.37656593616651e-06, "loss": 0.2978, "step": 8380 }, { "epoch": 0.2446578701541336, "grad_norm": 0.3238118290901184, "learning_rate": 9.37631954021403e-06, "loss": 0.225, "step": 8381 }, { "epoch": 0.24468706212050445, "grad_norm": 0.38072264194488525, "learning_rate": 9.376073098819098e-06, "loss": 0.2411, "step": 8382 }, { "epoch": 0.24471625408687528, "grad_norm": 0.3530888557434082, "learning_rate": 9.37582661198428e-06, "loss": 0.2118, "step": 8383 }, { "epoch": 0.24474544605324614, "grad_norm": 0.36379605531692505, "learning_rate": 9.37558007971213e-06, "loss": 0.2207, "step": 8384 }, { "epoch": 0.244774638019617, "grad_norm": 0.4207952618598938, "learning_rate": 9.37533350200521e-06, "loss": 0.2547, "step": 8385 }, { "epoch": 0.24480382998598785, "grad_norm": 0.35663843154907227, "learning_rate": 9.375086878866083e-06, "loss": 0.1868, "step": 8386 }, { "epoch": 0.2448330219523587, "grad_norm": 0.3421179950237274, "learning_rate": 9.374840210297306e-06, "loss": 0.3023, "step": 8387 }, { "epoch": 0.24486221391872956, "grad_norm": 0.3190397024154663, "learning_rate": 9.374593496301443e-06, "loss": 0.2221, "step": 8388 }, { "epoch": 0.24489140588510042, "grad_norm": 0.3729342520236969, "learning_rate": 9.374346736881053e-06, "loss": 0.2555, "step": 8389 }, { "epoch": 0.24492059785147127, "grad_norm": 0.3250165581703186, "learning_rate": 9.3740999320387e-06, "loss": 0.1994, "step": 8390 }, { "epoch": 0.24494978981784213, "grad_norm": 0.3471952974796295, "learning_rate": 9.373853081776947e-06, "loss": 0.281, "step": 8391 }, { "epoch": 0.24497898178421298, "grad_norm": 0.37401509284973145, "learning_rate": 9.373606186098357e-06, "loss": 0.2821, "step": 8392 }, { "epoch": 0.24500817375058384, "grad_norm": 0.3590412437915802, "learning_rate": 9.373359245005493e-06, "loss": 0.2689, "step": 8393 }, { "epoch": 0.2450373657169547, "grad_norm": 0.3211280107498169, "learning_rate": 9.373112258500921e-06, "loss": 0.282, "step": 8394 }, { "epoch": 0.24506655768332555, "grad_norm": 0.31673523783683777, "learning_rate": 9.372865226587203e-06, "loss": 0.2455, "step": 8395 }, { "epoch": 0.2450957496496964, "grad_norm": 0.3875628709793091, "learning_rate": 9.372618149266906e-06, "loss": 0.2182, "step": 8396 }, { "epoch": 0.24512494161606727, "grad_norm": 0.31775227189064026, "learning_rate": 9.372371026542595e-06, "loss": 0.244, "step": 8397 }, { "epoch": 0.24515413358243812, "grad_norm": 0.354875385761261, "learning_rate": 9.372123858416835e-06, "loss": 0.2847, "step": 8398 }, { "epoch": 0.24518332554880898, "grad_norm": 0.3668723702430725, "learning_rate": 9.371876644892195e-06, "loss": 0.2316, "step": 8399 }, { "epoch": 0.24521251751517983, "grad_norm": 0.4131525158882141, "learning_rate": 9.371629385971241e-06, "loss": 0.2541, "step": 8400 }, { "epoch": 0.2452417094815507, "grad_norm": 0.39435550570487976, "learning_rate": 9.37138208165654e-06, "loss": 0.2342, "step": 8401 }, { "epoch": 0.24527090144792152, "grad_norm": 0.38121917843818665, "learning_rate": 9.371134731950659e-06, "loss": 0.264, "step": 8402 }, { "epoch": 0.24530009341429238, "grad_norm": 0.3339526355266571, "learning_rate": 9.370887336856167e-06, "loss": 0.2552, "step": 8403 }, { "epoch": 0.24532928538066323, "grad_norm": 0.3810053765773773, "learning_rate": 9.370639896375635e-06, "loss": 0.2427, "step": 8404 }, { "epoch": 0.2453584773470341, "grad_norm": 0.467517226934433, "learning_rate": 9.370392410511629e-06, "loss": 0.2325, "step": 8405 }, { "epoch": 0.24538766931340494, "grad_norm": 0.37355750799179077, "learning_rate": 9.37014487926672e-06, "loss": 0.2521, "step": 8406 }, { "epoch": 0.2454168612797758, "grad_norm": 0.3571937680244446, "learning_rate": 9.36989730264348e-06, "loss": 0.2342, "step": 8407 }, { "epoch": 0.24544605324614666, "grad_norm": 0.46272051334381104, "learning_rate": 9.369649680644478e-06, "loss": 0.2199, "step": 8408 }, { "epoch": 0.2454752452125175, "grad_norm": 0.31921982765197754, "learning_rate": 9.369402013272287e-06, "loss": 0.268, "step": 8409 }, { "epoch": 0.24550443717888837, "grad_norm": 0.47600439190864563, "learning_rate": 9.369154300529478e-06, "loss": 0.2029, "step": 8410 }, { "epoch": 0.24553362914525922, "grad_norm": 0.3665120303630829, "learning_rate": 9.368906542418621e-06, "loss": 0.2423, "step": 8411 }, { "epoch": 0.24556282111163008, "grad_norm": 0.4269295334815979, "learning_rate": 9.36865873894229e-06, "loss": 0.2119, "step": 8412 }, { "epoch": 0.24559201307800094, "grad_norm": 0.3586752414703369, "learning_rate": 9.368410890103059e-06, "loss": 0.262, "step": 8413 }, { "epoch": 0.2456212050443718, "grad_norm": 0.5494045615196228, "learning_rate": 9.3681629959035e-06, "loss": 0.2485, "step": 8414 }, { "epoch": 0.24565039701074265, "grad_norm": 0.33148279786109924, "learning_rate": 9.36791505634619e-06, "loss": 0.214, "step": 8415 }, { "epoch": 0.2456795889771135, "grad_norm": 0.38064590096473694, "learning_rate": 9.3676670714337e-06, "loss": 0.2727, "step": 8416 }, { "epoch": 0.24570878094348436, "grad_norm": 0.3704124987125397, "learning_rate": 9.367419041168608e-06, "loss": 0.239, "step": 8417 }, { "epoch": 0.24573797290985522, "grad_norm": 0.376869797706604, "learning_rate": 9.367170965553487e-06, "loss": 0.2402, "step": 8418 }, { "epoch": 0.24576716487622607, "grad_norm": 0.2753894627094269, "learning_rate": 9.366922844590914e-06, "loss": 0.1676, "step": 8419 }, { "epoch": 0.24579635684259693, "grad_norm": 0.3068990111351013, "learning_rate": 9.366674678283467e-06, "loss": 0.2091, "step": 8420 }, { "epoch": 0.24582554880896776, "grad_norm": 0.357287734746933, "learning_rate": 9.36642646663372e-06, "loss": 0.213, "step": 8421 }, { "epoch": 0.24585474077533861, "grad_norm": 0.37577611207962036, "learning_rate": 9.366178209644251e-06, "loss": 0.2722, "step": 8422 }, { "epoch": 0.24588393274170947, "grad_norm": 0.31737881898880005, "learning_rate": 9.36592990731764e-06, "loss": 0.2754, "step": 8423 }, { "epoch": 0.24591312470808033, "grad_norm": 0.3137073814868927, "learning_rate": 9.365681559656463e-06, "loss": 0.2133, "step": 8424 }, { "epoch": 0.24594231667445118, "grad_norm": 0.36682558059692383, "learning_rate": 9.3654331666633e-06, "loss": 0.2582, "step": 8425 }, { "epoch": 0.24597150864082204, "grad_norm": 0.6330970525741577, "learning_rate": 9.365184728340729e-06, "loss": 0.2488, "step": 8426 }, { "epoch": 0.2460007006071929, "grad_norm": 0.353112131357193, "learning_rate": 9.364936244691331e-06, "loss": 0.2807, "step": 8427 }, { "epoch": 0.24602989257356375, "grad_norm": 0.35533905029296875, "learning_rate": 9.364687715717687e-06, "loss": 0.2758, "step": 8428 }, { "epoch": 0.2460590845399346, "grad_norm": 0.3435046374797821, "learning_rate": 9.364439141422374e-06, "loss": 0.2563, "step": 8429 }, { "epoch": 0.24608827650630546, "grad_norm": 0.3158283233642578, "learning_rate": 9.364190521807976e-06, "loss": 0.1968, "step": 8430 }, { "epoch": 0.24611746847267632, "grad_norm": 0.400846391916275, "learning_rate": 9.363941856877075e-06, "loss": 0.2811, "step": 8431 }, { "epoch": 0.24614666043904718, "grad_norm": 0.3827801048755646, "learning_rate": 9.363693146632253e-06, "loss": 0.2225, "step": 8432 }, { "epoch": 0.24617585240541803, "grad_norm": 0.3536645770072937, "learning_rate": 9.36344439107609e-06, "loss": 0.2958, "step": 8433 }, { "epoch": 0.2462050443717889, "grad_norm": 0.35089820623397827, "learning_rate": 9.363195590211172e-06, "loss": 0.2272, "step": 8434 }, { "epoch": 0.24623423633815975, "grad_norm": 0.3542938828468323, "learning_rate": 9.36294674404008e-06, "loss": 0.2259, "step": 8435 }, { "epoch": 0.2462634283045306, "grad_norm": 0.3400218188762665, "learning_rate": 9.3626978525654e-06, "loss": 0.258, "step": 8436 }, { "epoch": 0.24629262027090146, "grad_norm": 0.3465825319290161, "learning_rate": 9.362448915789715e-06, "loss": 0.2868, "step": 8437 }, { "epoch": 0.24632181223727231, "grad_norm": 0.3301713764667511, "learning_rate": 9.362199933715611e-06, "loss": 0.274, "step": 8438 }, { "epoch": 0.24635100420364317, "grad_norm": 0.2949705421924591, "learning_rate": 9.361950906345673e-06, "loss": 0.2236, "step": 8439 }, { "epoch": 0.246380196170014, "grad_norm": 0.3568045496940613, "learning_rate": 9.361701833682486e-06, "loss": 0.242, "step": 8440 }, { "epoch": 0.24640938813638485, "grad_norm": 0.3763832747936249, "learning_rate": 9.361452715728636e-06, "loss": 0.291, "step": 8441 }, { "epoch": 0.2464385801027557, "grad_norm": 0.3343360722064972, "learning_rate": 9.361203552486712e-06, "loss": 0.301, "step": 8442 }, { "epoch": 0.24646777206912657, "grad_norm": 0.425540030002594, "learning_rate": 9.3609543439593e-06, "loss": 0.234, "step": 8443 }, { "epoch": 0.24649696403549742, "grad_norm": 0.4242743253707886, "learning_rate": 9.360705090148987e-06, "loss": 0.2936, "step": 8444 }, { "epoch": 0.24652615600186828, "grad_norm": 0.333962082862854, "learning_rate": 9.360455791058362e-06, "loss": 0.2422, "step": 8445 }, { "epoch": 0.24655534796823914, "grad_norm": 0.3546157777309418, "learning_rate": 9.360206446690015e-06, "loss": 0.2227, "step": 8446 }, { "epoch": 0.24658453993461, "grad_norm": 0.3800351917743683, "learning_rate": 9.359957057046531e-06, "loss": 0.2409, "step": 8447 }, { "epoch": 0.24661373190098085, "grad_norm": 0.35960331559181213, "learning_rate": 9.359707622130504e-06, "loss": 0.2133, "step": 8448 }, { "epoch": 0.2466429238673517, "grad_norm": 0.41623473167419434, "learning_rate": 9.359458141944522e-06, "loss": 0.2156, "step": 8449 }, { "epoch": 0.24667211583372256, "grad_norm": 0.3800749182701111, "learning_rate": 9.359208616491176e-06, "loss": 0.287, "step": 8450 }, { "epoch": 0.24670130780009342, "grad_norm": 0.3550225496292114, "learning_rate": 9.358959045773055e-06, "loss": 0.2646, "step": 8451 }, { "epoch": 0.24673049976646427, "grad_norm": 0.5097379684448242, "learning_rate": 9.358709429792754e-06, "loss": 0.2291, "step": 8452 }, { "epoch": 0.24675969173283513, "grad_norm": 0.34849992394447327, "learning_rate": 9.358459768552863e-06, "loss": 0.2199, "step": 8453 }, { "epoch": 0.24678888369920599, "grad_norm": 0.33196961879730225, "learning_rate": 9.358210062055974e-06, "loss": 0.2313, "step": 8454 }, { "epoch": 0.24681807566557684, "grad_norm": 0.3370923399925232, "learning_rate": 9.35796031030468e-06, "loss": 0.2308, "step": 8455 }, { "epoch": 0.2468472676319477, "grad_norm": 0.35903799533843994, "learning_rate": 9.357710513301577e-06, "loss": 0.2189, "step": 8456 }, { "epoch": 0.24687645959831855, "grad_norm": 0.8199422955513, "learning_rate": 9.357460671049254e-06, "loss": 0.2483, "step": 8457 }, { "epoch": 0.2469056515646894, "grad_norm": 0.3640841245651245, "learning_rate": 9.35721078355031e-06, "loss": 0.2426, "step": 8458 }, { "epoch": 0.24693484353106024, "grad_norm": 0.3475359082221985, "learning_rate": 9.356960850807335e-06, "loss": 0.2528, "step": 8459 }, { "epoch": 0.2469640354974311, "grad_norm": 0.306579053401947, "learning_rate": 9.356710872822929e-06, "loss": 0.2409, "step": 8460 }, { "epoch": 0.24699322746380195, "grad_norm": 0.3956083059310913, "learning_rate": 9.356460849599687e-06, "loss": 0.2568, "step": 8461 }, { "epoch": 0.2470224194301728, "grad_norm": 0.3120144307613373, "learning_rate": 9.356210781140202e-06, "loss": 0.269, "step": 8462 }, { "epoch": 0.24705161139654366, "grad_norm": 0.3809744715690613, "learning_rate": 9.355960667447072e-06, "loss": 0.2659, "step": 8463 }, { "epoch": 0.24708080336291452, "grad_norm": 0.30277377367019653, "learning_rate": 9.355710508522894e-06, "loss": 0.2243, "step": 8464 }, { "epoch": 0.24710999532928538, "grad_norm": 0.34917792677879333, "learning_rate": 9.355460304370269e-06, "loss": 0.2694, "step": 8465 }, { "epoch": 0.24713918729565623, "grad_norm": 0.3785240054130554, "learning_rate": 9.35521005499179e-06, "loss": 0.2852, "step": 8466 }, { "epoch": 0.2471683792620271, "grad_norm": 0.3033565580844879, "learning_rate": 9.35495976039006e-06, "loss": 0.1748, "step": 8467 }, { "epoch": 0.24719757122839794, "grad_norm": 0.35411548614501953, "learning_rate": 9.35470942056767e-06, "loss": 0.2367, "step": 8468 }, { "epoch": 0.2472267631947688, "grad_norm": 0.31883499026298523, "learning_rate": 9.354459035527231e-06, "loss": 0.27, "step": 8469 }, { "epoch": 0.24725595516113966, "grad_norm": 0.485463947057724, "learning_rate": 9.354208605271336e-06, "loss": 0.271, "step": 8470 }, { "epoch": 0.2472851471275105, "grad_norm": 0.3168570399284363, "learning_rate": 9.353958129802586e-06, "loss": 0.2401, "step": 8471 }, { "epoch": 0.24731433909388137, "grad_norm": 0.48643815517425537, "learning_rate": 9.353707609123582e-06, "loss": 0.1784, "step": 8472 }, { "epoch": 0.24734353106025223, "grad_norm": 0.35142508149147034, "learning_rate": 9.353457043236924e-06, "loss": 0.2857, "step": 8473 }, { "epoch": 0.24737272302662308, "grad_norm": 0.3732592463493347, "learning_rate": 9.353206432145217e-06, "loss": 0.296, "step": 8474 }, { "epoch": 0.24740191499299394, "grad_norm": 0.4848564863204956, "learning_rate": 9.352955775851062e-06, "loss": 0.2336, "step": 8475 }, { "epoch": 0.2474311069593648, "grad_norm": 0.3919280469417572, "learning_rate": 9.352705074357061e-06, "loss": 0.2235, "step": 8476 }, { "epoch": 0.24746029892573565, "grad_norm": 0.3693249225616455, "learning_rate": 9.352454327665819e-06, "loss": 0.2882, "step": 8477 }, { "epoch": 0.24748949089210648, "grad_norm": 0.4596109390258789, "learning_rate": 9.352203535779935e-06, "loss": 0.2288, "step": 8478 }, { "epoch": 0.24751868285847733, "grad_norm": 0.3338886499404907, "learning_rate": 9.35195269870202e-06, "loss": 0.2491, "step": 8479 }, { "epoch": 0.2475478748248482, "grad_norm": 0.32194405794143677, "learning_rate": 9.351701816434673e-06, "loss": 0.2245, "step": 8480 }, { "epoch": 0.24757706679121905, "grad_norm": 0.44387713074684143, "learning_rate": 9.351450888980504e-06, "loss": 0.258, "step": 8481 }, { "epoch": 0.2476062587575899, "grad_norm": 0.3512513339519501, "learning_rate": 9.351199916342113e-06, "loss": 0.2258, "step": 8482 }, { "epoch": 0.24763545072396076, "grad_norm": 0.3692154586315155, "learning_rate": 9.35094889852211e-06, "loss": 0.2788, "step": 8483 }, { "epoch": 0.24766464269033162, "grad_norm": 0.48593518137931824, "learning_rate": 9.3506978355231e-06, "loss": 0.2882, "step": 8484 }, { "epoch": 0.24769383465670247, "grad_norm": 0.3989924192428589, "learning_rate": 9.35044672734769e-06, "loss": 0.2774, "step": 8485 }, { "epoch": 0.24772302662307333, "grad_norm": 0.393876314163208, "learning_rate": 9.350195573998489e-06, "loss": 0.2348, "step": 8486 }, { "epoch": 0.24775221858944418, "grad_norm": 0.35045117139816284, "learning_rate": 9.349944375478103e-06, "loss": 0.2928, "step": 8487 }, { "epoch": 0.24778141055581504, "grad_norm": 0.3080371022224426, "learning_rate": 9.34969313178914e-06, "loss": 0.2146, "step": 8488 }, { "epoch": 0.2478106025221859, "grad_norm": 0.3959081172943115, "learning_rate": 9.34944184293421e-06, "loss": 0.2516, "step": 8489 }, { "epoch": 0.24783979448855675, "grad_norm": 0.34127628803253174, "learning_rate": 9.349190508915924e-06, "loss": 0.2264, "step": 8490 }, { "epoch": 0.2478689864549276, "grad_norm": 0.5313479900360107, "learning_rate": 9.348939129736889e-06, "loss": 0.2638, "step": 8491 }, { "epoch": 0.24789817842129847, "grad_norm": 0.3866939842700958, "learning_rate": 9.348687705399715e-06, "loss": 0.2482, "step": 8492 }, { "epoch": 0.24792737038766932, "grad_norm": 0.36611244082450867, "learning_rate": 9.348436235907014e-06, "loss": 0.2482, "step": 8493 }, { "epoch": 0.24795656235404018, "grad_norm": 0.4196736216545105, "learning_rate": 9.3481847212614e-06, "loss": 0.3066, "step": 8494 }, { "epoch": 0.24798575432041103, "grad_norm": 0.40013861656188965, "learning_rate": 9.347933161465479e-06, "loss": 0.258, "step": 8495 }, { "epoch": 0.2480149462867819, "grad_norm": 0.3387187123298645, "learning_rate": 9.347681556521866e-06, "loss": 0.2538, "step": 8496 }, { "epoch": 0.24804413825315275, "grad_norm": 0.2979341149330139, "learning_rate": 9.347429906433175e-06, "loss": 0.2336, "step": 8497 }, { "epoch": 0.24807333021952357, "grad_norm": 0.4794046878814697, "learning_rate": 9.347178211202016e-06, "loss": 0.2566, "step": 8498 }, { "epoch": 0.24810252218589443, "grad_norm": 0.34975412487983704, "learning_rate": 9.346926470831005e-06, "loss": 0.2089, "step": 8499 }, { "epoch": 0.2481317141522653, "grad_norm": 0.3672179579734802, "learning_rate": 9.346674685322754e-06, "loss": 0.2779, "step": 8500 } ], "logging_steps": 1, "max_steps": 34256, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7.308384426105242e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }