Mistral-Chem-v1-1.6B / trainer_state.json
RaphaelMourad's picture
Upload 9 files
565219c verified
{
"best_metric": 1.3314919471740723,
"best_model_checkpoint": "./results/models/mistral-chem/checkpoint-384480",
"epoch": 11.0,
"eval_steps": 500,
"global_step": 422928,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013004577611319184,
"grad_norm": 1.2890625,
"learning_rate": 0.001999479816895547,
"loss": 2.4533,
"step": 500
},
{
"epoch": 0.02600915522263837,
"grad_norm": 0.95703125,
"learning_rate": 0.0019989596337910945,
"loss": 2.116,
"step": 1000
},
{
"epoch": 0.03901373283395755,
"grad_norm": 1.6171875,
"learning_rate": 0.0019984394506866415,
"loss": 2.0364,
"step": 1500
},
{
"epoch": 0.05201831044527674,
"grad_norm": 1.6796875,
"learning_rate": 0.001997919267582189,
"loss": 1.9539,
"step": 2000
},
{
"epoch": 0.06502288805659592,
"grad_norm": 0.421875,
"learning_rate": 0.001997399084477736,
"loss": 1.9176,
"step": 2500
},
{
"epoch": 0.0780274656679151,
"grad_norm": 0.75390625,
"learning_rate": 0.0019968789013732834,
"loss": 1.8701,
"step": 3000
},
{
"epoch": 0.0910320432792343,
"grad_norm": 0.56640625,
"learning_rate": 0.001996358718268831,
"loss": 1.8383,
"step": 3500
},
{
"epoch": 0.10403662089055347,
"grad_norm": 0.515625,
"learning_rate": 0.001995838535164378,
"loss": 1.8133,
"step": 4000
},
{
"epoch": 0.11704119850187265,
"grad_norm": 1.2578125,
"learning_rate": 0.0019953183520599253,
"loss": 1.7976,
"step": 4500
},
{
"epoch": 0.13004577611319185,
"grad_norm": 0.53515625,
"learning_rate": 0.0019947981689554723,
"loss": 1.7758,
"step": 5000
},
{
"epoch": 0.14305035372451103,
"grad_norm": 0.451171875,
"learning_rate": 0.0019942779858510198,
"loss": 1.7529,
"step": 5500
},
{
"epoch": 0.1560549313358302,
"grad_norm": 18.0,
"learning_rate": 0.001993757802746567,
"loss": 1.7465,
"step": 6000
},
{
"epoch": 0.16905950894714938,
"grad_norm": 0.51953125,
"learning_rate": 0.0019932376196421142,
"loss": 1.7295,
"step": 6500
},
{
"epoch": 0.1820640865584686,
"grad_norm": 0.474609375,
"learning_rate": 0.0019927174365376612,
"loss": 1.7239,
"step": 7000
},
{
"epoch": 0.19506866416978777,
"grad_norm": 0.7734375,
"learning_rate": 0.0019921972534332083,
"loss": 1.7067,
"step": 7500
},
{
"epoch": 0.20807324178110695,
"grad_norm": 0.7421875,
"learning_rate": 0.0019916770703287557,
"loss": 1.6868,
"step": 8000
},
{
"epoch": 0.22107781939242613,
"grad_norm": 0.486328125,
"learning_rate": 0.001991156887224303,
"loss": 1.6772,
"step": 8500
},
{
"epoch": 0.2340823970037453,
"grad_norm": 1.4375,
"learning_rate": 0.00199063670411985,
"loss": 1.6766,
"step": 9000
},
{
"epoch": 0.24708697461506451,
"grad_norm": 1.09375,
"learning_rate": 0.0019901165210153976,
"loss": 1.6677,
"step": 9500
},
{
"epoch": 0.2600915522263837,
"grad_norm": 0.72265625,
"learning_rate": 0.0019895963379109446,
"loss": 1.6503,
"step": 10000
},
{
"epoch": 0.2730961298377029,
"grad_norm": 0.578125,
"learning_rate": 0.001989076154806492,
"loss": 1.6424,
"step": 10500
},
{
"epoch": 0.28610070744902205,
"grad_norm": 0.5390625,
"learning_rate": 0.001988555971702039,
"loss": 1.6428,
"step": 11000
},
{
"epoch": 0.29910528506034123,
"grad_norm": 0.78125,
"learning_rate": 0.0019880357885975865,
"loss": 1.6369,
"step": 11500
},
{
"epoch": 0.3121098626716604,
"grad_norm": 2.03125,
"learning_rate": 0.0019875156054931335,
"loss": 1.6402,
"step": 12000
},
{
"epoch": 0.3251144402829796,
"grad_norm": 0.56640625,
"learning_rate": 0.001986995422388681,
"loss": 1.6318,
"step": 12500
},
{
"epoch": 0.33811901789429877,
"grad_norm": 0.46875,
"learning_rate": 0.001986475239284228,
"loss": 1.62,
"step": 13000
},
{
"epoch": 0.351123595505618,
"grad_norm": 0.57421875,
"learning_rate": 0.0019859550561797754,
"loss": 1.6149,
"step": 13500
},
{
"epoch": 0.3641281731169372,
"grad_norm": 0.5703125,
"learning_rate": 0.0019854348730753224,
"loss": 1.612,
"step": 14000
},
{
"epoch": 0.37713275072825636,
"grad_norm": 0.408203125,
"learning_rate": 0.00198491468997087,
"loss": 1.5996,
"step": 14500
},
{
"epoch": 0.39013732833957554,
"grad_norm": 0.453125,
"learning_rate": 0.001984394506866417,
"loss": 1.5997,
"step": 15000
},
{
"epoch": 0.4031419059508947,
"grad_norm": 0.6640625,
"learning_rate": 0.0019838743237619643,
"loss": 1.5949,
"step": 15500
},
{
"epoch": 0.4161464835622139,
"grad_norm": 0.447265625,
"learning_rate": 0.0019833541406575114,
"loss": 1.5923,
"step": 16000
},
{
"epoch": 0.4291510611735331,
"grad_norm": 2.59375,
"learning_rate": 0.001982833957553059,
"loss": 1.596,
"step": 16500
},
{
"epoch": 0.44215563878485226,
"grad_norm": 0.427734375,
"learning_rate": 0.001982313774448606,
"loss": 1.5886,
"step": 17000
},
{
"epoch": 0.45516021639617144,
"grad_norm": 0.75,
"learning_rate": 0.0019817935913441533,
"loss": 1.5848,
"step": 17500
},
{
"epoch": 0.4681647940074906,
"grad_norm": 0.609375,
"learning_rate": 0.0019812734082397003,
"loss": 1.5799,
"step": 18000
},
{
"epoch": 0.4811693716188098,
"grad_norm": 0.359375,
"learning_rate": 0.0019807532251352477,
"loss": 1.5777,
"step": 18500
},
{
"epoch": 0.49417394923012903,
"grad_norm": 0.8203125,
"learning_rate": 0.0019802330420307947,
"loss": 1.5786,
"step": 19000
},
{
"epoch": 0.5071785268414482,
"grad_norm": 0.62890625,
"learning_rate": 0.001979712858926342,
"loss": 1.5661,
"step": 19500
},
{
"epoch": 0.5201831044527674,
"grad_norm": 0.76953125,
"learning_rate": 0.0019791926758218896,
"loss": 1.5727,
"step": 20000
},
{
"epoch": 0.5331876820640865,
"grad_norm": 0.404296875,
"learning_rate": 0.0019786724927174366,
"loss": 1.5709,
"step": 20500
},
{
"epoch": 0.5461922596754057,
"grad_norm": 0.400390625,
"learning_rate": 0.001978152309612984,
"loss": 1.5684,
"step": 21000
},
{
"epoch": 0.559196837286725,
"grad_norm": 0.5390625,
"learning_rate": 0.001977632126508531,
"loss": 1.5595,
"step": 21500
},
{
"epoch": 0.5722014148980441,
"grad_norm": 0.5234375,
"learning_rate": 0.001977111943404078,
"loss": 1.5566,
"step": 22000
},
{
"epoch": 0.5852059925093633,
"grad_norm": 0.455078125,
"learning_rate": 0.0019765917602996255,
"loss": 1.5531,
"step": 22500
},
{
"epoch": 0.5982105701206825,
"grad_norm": 0.41015625,
"learning_rate": 0.0019760715771951726,
"loss": 1.5465,
"step": 23000
},
{
"epoch": 0.6112151477320017,
"grad_norm": 0.609375,
"learning_rate": 0.00197555139409072,
"loss": 1.5437,
"step": 23500
},
{
"epoch": 0.6242197253433208,
"grad_norm": 0.37109375,
"learning_rate": 0.001975031210986267,
"loss": 1.539,
"step": 24000
},
{
"epoch": 0.63722430295464,
"grad_norm": 0.37890625,
"learning_rate": 0.0019745110278818145,
"loss": 1.5365,
"step": 24500
},
{
"epoch": 0.6502288805659592,
"grad_norm": 0.6171875,
"learning_rate": 0.0019739908447773615,
"loss": 1.5384,
"step": 25000
},
{
"epoch": 0.6632334581772784,
"grad_norm": 0.38671875,
"learning_rate": 0.001973470661672909,
"loss": 1.5352,
"step": 25500
},
{
"epoch": 0.6762380357885975,
"grad_norm": 0.453125,
"learning_rate": 0.0019729504785684564,
"loss": 1.5328,
"step": 26000
},
{
"epoch": 0.6892426133999168,
"grad_norm": 0.7890625,
"learning_rate": 0.0019724302954640034,
"loss": 1.5405,
"step": 26500
},
{
"epoch": 0.702247191011236,
"grad_norm": 0.62890625,
"learning_rate": 0.001971910112359551,
"loss": 1.5336,
"step": 27000
},
{
"epoch": 0.7152517686225551,
"grad_norm": 0.435546875,
"learning_rate": 0.001971389929255098,
"loss": 1.5275,
"step": 27500
},
{
"epoch": 0.7282563462338744,
"grad_norm": 0.419921875,
"learning_rate": 0.0019708697461506453,
"loss": 1.5269,
"step": 28000
},
{
"epoch": 0.7412609238451935,
"grad_norm": 0.365234375,
"learning_rate": 0.0019703495630461923,
"loss": 1.5259,
"step": 28500
},
{
"epoch": 0.7542655014565127,
"grad_norm": 0.486328125,
"learning_rate": 0.0019698293799417393,
"loss": 1.526,
"step": 29000
},
{
"epoch": 0.7672700790678318,
"grad_norm": 0.388671875,
"learning_rate": 0.0019693091968372867,
"loss": 1.5232,
"step": 29500
},
{
"epoch": 0.7802746566791511,
"grad_norm": 0.412109375,
"learning_rate": 0.0019687890137328337,
"loss": 1.515,
"step": 30000
},
{
"epoch": 0.7932792342904702,
"grad_norm": 2.78125,
"learning_rate": 0.001968268830628381,
"loss": 1.5135,
"step": 30500
},
{
"epoch": 0.8062838119017894,
"grad_norm": 0.546875,
"learning_rate": 0.0019677486475239286,
"loss": 1.5105,
"step": 31000
},
{
"epoch": 0.8192883895131086,
"grad_norm": 0.384765625,
"learning_rate": 0.0019672284644194757,
"loss": 1.5049,
"step": 31500
},
{
"epoch": 0.8322929671244278,
"grad_norm": 0.353515625,
"learning_rate": 0.001966708281315023,
"loss": 1.5068,
"step": 32000
},
{
"epoch": 0.845297544735747,
"grad_norm": 0.33203125,
"learning_rate": 0.00196618809821057,
"loss": 1.5106,
"step": 32500
},
{
"epoch": 0.8583021223470662,
"grad_norm": 0.46484375,
"learning_rate": 0.0019656679151061176,
"loss": 1.5025,
"step": 33000
},
{
"epoch": 0.8713066999583854,
"grad_norm": 0.357421875,
"learning_rate": 0.0019651477320016646,
"loss": 1.5003,
"step": 33500
},
{
"epoch": 0.8843112775697045,
"grad_norm": 0.51953125,
"learning_rate": 0.001964627548897212,
"loss": 1.5008,
"step": 34000
},
{
"epoch": 0.8973158551810237,
"grad_norm": 0.43359375,
"learning_rate": 0.001964107365792759,
"loss": 1.4981,
"step": 34500
},
{
"epoch": 0.9103204327923429,
"grad_norm": 0.345703125,
"learning_rate": 0.0019635871826883065,
"loss": 1.5051,
"step": 35000
},
{
"epoch": 0.9233250104036621,
"grad_norm": 0.451171875,
"learning_rate": 0.0019630669995838535,
"loss": 1.497,
"step": 35500
},
{
"epoch": 0.9363295880149812,
"grad_norm": 0.30859375,
"learning_rate": 0.0019625468164794005,
"loss": 1.4988,
"step": 36000
},
{
"epoch": 0.9493341656263005,
"grad_norm": 0.3984375,
"learning_rate": 0.001962026633374948,
"loss": 1.4969,
"step": 36500
},
{
"epoch": 0.9623387432376196,
"grad_norm": 0.49609375,
"learning_rate": 0.0019615064502704954,
"loss": 1.4962,
"step": 37000
},
{
"epoch": 0.9753433208489388,
"grad_norm": 0.369140625,
"learning_rate": 0.0019609862671660424,
"loss": 1.4917,
"step": 37500
},
{
"epoch": 0.9883478984602581,
"grad_norm": 0.376953125,
"learning_rate": 0.00196046608406159,
"loss": 1.4911,
"step": 38000
},
{
"epoch": 1.0,
"eval_loss": 1.4885175228118896,
"eval_runtime": 0.5947,
"eval_samples_per_second": 1681.496,
"eval_steps_per_second": 6.726,
"step": 38448
},
{
"epoch": 1.0013524760715773,
"grad_norm": 0.546875,
"learning_rate": 0.001959945900957137,
"loss": 1.4874,
"step": 38500
},
{
"epoch": 1.0143570536828963,
"grad_norm": 4.15625,
"learning_rate": 0.0019594257178526843,
"loss": 1.4894,
"step": 39000
},
{
"epoch": 1.0273616312942155,
"grad_norm": 0.390625,
"learning_rate": 0.0019589055347482313,
"loss": 1.4833,
"step": 39500
},
{
"epoch": 1.0403662089055348,
"grad_norm": 0.40625,
"learning_rate": 0.0019583853516437788,
"loss": 1.4811,
"step": 40000
},
{
"epoch": 1.053370786516854,
"grad_norm": 0.40234375,
"learning_rate": 0.0019578651685393258,
"loss": 1.4804,
"step": 40500
},
{
"epoch": 1.066375364128173,
"grad_norm": 1.515625,
"learning_rate": 0.001957344985434873,
"loss": 1.4834,
"step": 41000
},
{
"epoch": 1.0793799417394923,
"grad_norm": 0.345703125,
"learning_rate": 0.0019568248023304202,
"loss": 1.4792,
"step": 41500
},
{
"epoch": 1.0923845193508115,
"grad_norm": 0.455078125,
"learning_rate": 0.0019563046192259677,
"loss": 1.4794,
"step": 42000
},
{
"epoch": 1.1053890969621307,
"grad_norm": 0.435546875,
"learning_rate": 0.001955784436121515,
"loss": 1.4749,
"step": 42500
},
{
"epoch": 1.1183936745734497,
"grad_norm": 0.6953125,
"learning_rate": 0.001955264253017062,
"loss": 1.4761,
"step": 43000
},
{
"epoch": 1.131398252184769,
"grad_norm": 0.8359375,
"learning_rate": 0.001954744069912609,
"loss": 1.4754,
"step": 43500
},
{
"epoch": 1.1444028297960882,
"grad_norm": 0.44921875,
"learning_rate": 0.0019542238868081566,
"loss": 1.4757,
"step": 44000
},
{
"epoch": 1.1574074074074074,
"grad_norm": 0.5078125,
"learning_rate": 0.0019537037037037036,
"loss": 1.4703,
"step": 44500
},
{
"epoch": 1.1704119850187267,
"grad_norm": 0.546875,
"learning_rate": 0.001953183520599251,
"loss": 1.472,
"step": 45000
},
{
"epoch": 1.1834165626300457,
"grad_norm": 0.4453125,
"learning_rate": 0.0019526633374947983,
"loss": 1.4684,
"step": 45500
},
{
"epoch": 1.196421140241365,
"grad_norm": 0.49609375,
"learning_rate": 0.0019521431543903455,
"loss": 1.467,
"step": 46000
},
{
"epoch": 1.2094257178526842,
"grad_norm": 0.6640625,
"learning_rate": 0.0019516229712858925,
"loss": 1.4632,
"step": 46500
},
{
"epoch": 1.2224302954640034,
"grad_norm": 0.609375,
"learning_rate": 0.0019511027881814397,
"loss": 1.4652,
"step": 47000
},
{
"epoch": 1.2354348730753224,
"grad_norm": 0.376953125,
"learning_rate": 0.001950582605076987,
"loss": 1.4627,
"step": 47500
},
{
"epoch": 1.2484394506866416,
"grad_norm": 0.400390625,
"learning_rate": 0.0019500624219725344,
"loss": 1.463,
"step": 48000
},
{
"epoch": 1.2614440282979609,
"grad_norm": 0.71875,
"learning_rate": 0.0019495422388680816,
"loss": 1.4594,
"step": 48500
},
{
"epoch": 1.27444860590928,
"grad_norm": 0.443359375,
"learning_rate": 0.0019490220557636289,
"loss": 1.4627,
"step": 49000
},
{
"epoch": 1.2874531835205993,
"grad_norm": 0.412109375,
"learning_rate": 0.001948501872659176,
"loss": 1.4643,
"step": 49500
},
{
"epoch": 1.3004577611319184,
"grad_norm": 0.578125,
"learning_rate": 0.0019479816895547233,
"loss": 1.4599,
"step": 50000
},
{
"epoch": 1.3134623387432376,
"grad_norm": 0.546875,
"learning_rate": 0.0019474615064502706,
"loss": 1.4617,
"step": 50500
},
{
"epoch": 1.3264669163545568,
"grad_norm": 0.9296875,
"learning_rate": 0.0019469413233458178,
"loss": 1.4599,
"step": 51000
},
{
"epoch": 1.339471493965876,
"grad_norm": 0.400390625,
"learning_rate": 0.001946421140241365,
"loss": 1.4571,
"step": 51500
},
{
"epoch": 1.352476071577195,
"grad_norm": 0.474609375,
"learning_rate": 0.0019459009571369122,
"loss": 1.4584,
"step": 52000
},
{
"epoch": 1.3654806491885143,
"grad_norm": 0.482421875,
"learning_rate": 0.0019453807740324595,
"loss": 1.4572,
"step": 52500
},
{
"epoch": 1.3784852267998335,
"grad_norm": 0.40625,
"learning_rate": 0.0019448605909280067,
"loss": 1.4542,
"step": 53000
},
{
"epoch": 1.3914898044111528,
"grad_norm": 0.443359375,
"learning_rate": 0.0019443404078235541,
"loss": 1.4551,
"step": 53500
},
{
"epoch": 1.404494382022472,
"grad_norm": 0.44140625,
"learning_rate": 0.0019438202247191011,
"loss": 1.4539,
"step": 54000
},
{
"epoch": 1.417498959633791,
"grad_norm": 2.9375,
"learning_rate": 0.0019433000416146484,
"loss": 1.4542,
"step": 54500
},
{
"epoch": 1.4305035372451103,
"grad_norm": 0.703125,
"learning_rate": 0.0019427798585101956,
"loss": 1.4509,
"step": 55000
},
{
"epoch": 1.4435081148564295,
"grad_norm": 0.373046875,
"learning_rate": 0.0019422596754057428,
"loss": 1.4532,
"step": 55500
},
{
"epoch": 1.4565126924677487,
"grad_norm": 0.33203125,
"learning_rate": 0.00194173949230129,
"loss": 1.4533,
"step": 56000
},
{
"epoch": 1.4695172700790677,
"grad_norm": 0.3828125,
"learning_rate": 0.0019412193091968373,
"loss": 1.4516,
"step": 56500
},
{
"epoch": 1.482521847690387,
"grad_norm": 0.6875,
"learning_rate": 0.0019406991260923845,
"loss": 1.4513,
"step": 57000
},
{
"epoch": 1.4955264253017062,
"grad_norm": 0.357421875,
"learning_rate": 0.0019401789429879317,
"loss": 1.4496,
"step": 57500
},
{
"epoch": 1.5085310029130254,
"grad_norm": 0.400390625,
"learning_rate": 0.001939658759883479,
"loss": 1.4431,
"step": 58000
},
{
"epoch": 1.5215355805243447,
"grad_norm": 0.6875,
"learning_rate": 0.0019391385767790262,
"loss": 1.4508,
"step": 58500
},
{
"epoch": 1.534540158135664,
"grad_norm": 0.6484375,
"learning_rate": 0.0019386183936745737,
"loss": 1.4533,
"step": 59000
},
{
"epoch": 1.547544735746983,
"grad_norm": 0.345703125,
"learning_rate": 0.0019380982105701209,
"loss": 1.4468,
"step": 59500
},
{
"epoch": 1.5605493133583022,
"grad_norm": 0.404296875,
"learning_rate": 0.001937578027465668,
"loss": 1.4448,
"step": 60000
},
{
"epoch": 1.5735538909696212,
"grad_norm": 0.443359375,
"learning_rate": 0.0019370578443612153,
"loss": 1.4444,
"step": 60500
},
{
"epoch": 1.5865584685809404,
"grad_norm": 0.375,
"learning_rate": 0.0019365376612567623,
"loss": 1.4446,
"step": 61000
},
{
"epoch": 1.5995630461922596,
"grad_norm": 1.375,
"learning_rate": 0.0019360174781523096,
"loss": 1.4445,
"step": 61500
},
{
"epoch": 1.6125676238035789,
"grad_norm": 0.47265625,
"learning_rate": 0.0019354972950478568,
"loss": 1.4412,
"step": 62000
},
{
"epoch": 1.625572201414898,
"grad_norm": 0.408203125,
"learning_rate": 0.001934977111943404,
"loss": 1.443,
"step": 62500
},
{
"epoch": 1.6385767790262173,
"grad_norm": 0.41015625,
"learning_rate": 0.0019344569288389513,
"loss": 1.4407,
"step": 63000
},
{
"epoch": 1.6515813566375364,
"grad_norm": 0.455078125,
"learning_rate": 0.0019339367457344985,
"loss": 1.4373,
"step": 63500
},
{
"epoch": 1.6645859342488556,
"grad_norm": 0.7578125,
"learning_rate": 0.0019334165626300457,
"loss": 1.434,
"step": 64000
},
{
"epoch": 1.6775905118601748,
"grad_norm": 0.38671875,
"learning_rate": 0.001932896379525593,
"loss": 1.4394,
"step": 64500
},
{
"epoch": 1.6905950894714938,
"grad_norm": 0.388671875,
"learning_rate": 0.0019323761964211404,
"loss": 1.4383,
"step": 65000
},
{
"epoch": 1.703599667082813,
"grad_norm": 0.44140625,
"learning_rate": 0.0019318560133166876,
"loss": 1.4376,
"step": 65500
},
{
"epoch": 1.7166042446941323,
"grad_norm": 0.41796875,
"learning_rate": 0.0019313358302122348,
"loss": 1.4382,
"step": 66000
},
{
"epoch": 1.7296088223054515,
"grad_norm": 0.34765625,
"learning_rate": 0.001930815647107782,
"loss": 1.437,
"step": 66500
},
{
"epoch": 1.7426133999167708,
"grad_norm": 0.3828125,
"learning_rate": 0.0019302954640033293,
"loss": 1.4395,
"step": 67000
},
{
"epoch": 1.75561797752809,
"grad_norm": 0.421875,
"learning_rate": 0.0019297752808988765,
"loss": 1.4351,
"step": 67500
},
{
"epoch": 1.768622555139409,
"grad_norm": 2.4375,
"learning_rate": 0.0019292550977944235,
"loss": 1.4419,
"step": 68000
},
{
"epoch": 1.7816271327507283,
"grad_norm": 0.427734375,
"learning_rate": 0.0019287349146899708,
"loss": 1.4385,
"step": 68500
},
{
"epoch": 1.7946317103620475,
"grad_norm": 1.359375,
"learning_rate": 0.001928214731585518,
"loss": 1.4342,
"step": 69000
},
{
"epoch": 1.8076362879733665,
"grad_norm": 0.69140625,
"learning_rate": 0.0019276945484810652,
"loss": 1.4363,
"step": 69500
},
{
"epoch": 1.8206408655846857,
"grad_norm": 0.447265625,
"learning_rate": 0.0019271743653766125,
"loss": 1.4361,
"step": 70000
},
{
"epoch": 1.833645443196005,
"grad_norm": 0.453125,
"learning_rate": 0.00192665418227216,
"loss": 1.4333,
"step": 70500
},
{
"epoch": 1.8466500208073242,
"grad_norm": 1.21875,
"learning_rate": 0.0019261339991677071,
"loss": 1.4342,
"step": 71000
},
{
"epoch": 1.8596545984186434,
"grad_norm": 0.447265625,
"learning_rate": 0.0019256138160632544,
"loss": 1.4334,
"step": 71500
},
{
"epoch": 1.8726591760299627,
"grad_norm": 0.4453125,
"learning_rate": 0.0019250936329588016,
"loss": 1.433,
"step": 72000
},
{
"epoch": 1.8856637536412817,
"grad_norm": 0.640625,
"learning_rate": 0.0019245734498543488,
"loss": 1.4269,
"step": 72500
},
{
"epoch": 1.898668331252601,
"grad_norm": 0.490234375,
"learning_rate": 0.001924053266749896,
"loss": 1.4313,
"step": 73000
},
{
"epoch": 1.91167290886392,
"grad_norm": 0.4609375,
"learning_rate": 0.0019235330836454433,
"loss": 1.4354,
"step": 73500
},
{
"epoch": 1.9246774864752392,
"grad_norm": 0.412109375,
"learning_rate": 0.0019230129005409905,
"loss": 1.4304,
"step": 74000
},
{
"epoch": 1.9376820640865584,
"grad_norm": 0.94140625,
"learning_rate": 0.0019224927174365377,
"loss": 1.4238,
"step": 74500
},
{
"epoch": 1.9506866416978776,
"grad_norm": 0.40625,
"learning_rate": 0.001921972534332085,
"loss": 1.4313,
"step": 75000
},
{
"epoch": 1.9636912193091969,
"grad_norm": 0.369140625,
"learning_rate": 0.001921452351227632,
"loss": 1.4266,
"step": 75500
},
{
"epoch": 1.9766957969205161,
"grad_norm": 0.44921875,
"learning_rate": 0.0019209321681231794,
"loss": 1.425,
"step": 76000
},
{
"epoch": 1.9897003745318353,
"grad_norm": 2.75,
"learning_rate": 0.0019204119850187266,
"loss": 1.4248,
"step": 76500
},
{
"epoch": 2.0,
"eval_loss": 1.4245445728302002,
"eval_runtime": 0.5732,
"eval_samples_per_second": 1744.482,
"eval_steps_per_second": 6.978,
"step": 76896
},
{
"epoch": 2.0027049521431546,
"grad_norm": 20.5,
"learning_rate": 0.0019198918019142739,
"loss": 1.424,
"step": 77000
},
{
"epoch": 2.0157095297544734,
"grad_norm": 0.578125,
"learning_rate": 0.001919371618809821,
"loss": 1.4238,
"step": 77500
},
{
"epoch": 2.0287141073657926,
"grad_norm": 0.404296875,
"learning_rate": 0.0019188514357053683,
"loss": 1.421,
"step": 78000
},
{
"epoch": 2.041718684977112,
"grad_norm": 0.365234375,
"learning_rate": 0.0019183312526009156,
"loss": 1.4216,
"step": 78500
},
{
"epoch": 2.054723262588431,
"grad_norm": 0.7890625,
"learning_rate": 0.0019178110694964628,
"loss": 1.4202,
"step": 79000
},
{
"epoch": 2.0677278401997503,
"grad_norm": 0.330078125,
"learning_rate": 0.00191729088639201,
"loss": 1.4181,
"step": 79500
},
{
"epoch": 2.0807324178110695,
"grad_norm": 0.328125,
"learning_rate": 0.0019167707032875572,
"loss": 1.4194,
"step": 80000
},
{
"epoch": 2.093736995422389,
"grad_norm": 0.72265625,
"learning_rate": 0.0019162505201831045,
"loss": 1.4196,
"step": 80500
},
{
"epoch": 2.106741573033708,
"grad_norm": 0.33984375,
"learning_rate": 0.0019157303370786517,
"loss": 1.4172,
"step": 81000
},
{
"epoch": 2.1197461506450272,
"grad_norm": 0.345703125,
"learning_rate": 0.0019152101539741991,
"loss": 1.4181,
"step": 81500
},
{
"epoch": 2.132750728256346,
"grad_norm": 0.353515625,
"learning_rate": 0.0019146899708697464,
"loss": 1.4152,
"step": 82000
},
{
"epoch": 2.1457553058676653,
"grad_norm": 0.431640625,
"learning_rate": 0.0019141697877652934,
"loss": 1.4141,
"step": 82500
},
{
"epoch": 2.1587598834789845,
"grad_norm": 0.345703125,
"learning_rate": 0.0019136496046608406,
"loss": 1.417,
"step": 83000
},
{
"epoch": 2.1717644610903037,
"grad_norm": 6.96875,
"learning_rate": 0.0019131294215563878,
"loss": 1.4131,
"step": 83500
},
{
"epoch": 2.184769038701623,
"grad_norm": 0.44140625,
"learning_rate": 0.001912609238451935,
"loss": 1.4168,
"step": 84000
},
{
"epoch": 2.197773616312942,
"grad_norm": 0.44140625,
"learning_rate": 0.0019120890553474823,
"loss": 1.4158,
"step": 84500
},
{
"epoch": 2.2107781939242614,
"grad_norm": 0.43359375,
"learning_rate": 0.0019115688722430295,
"loss": 1.4125,
"step": 85000
},
{
"epoch": 2.2237827715355807,
"grad_norm": 1.5390625,
"learning_rate": 0.0019110486891385768,
"loss": 1.4114,
"step": 85500
},
{
"epoch": 2.2367873491468995,
"grad_norm": 0.69140625,
"learning_rate": 0.001910528506034124,
"loss": 1.4156,
"step": 86000
},
{
"epoch": 2.2497919267582187,
"grad_norm": 0.42578125,
"learning_rate": 0.0019100083229296712,
"loss": 1.4146,
"step": 86500
},
{
"epoch": 2.262796504369538,
"grad_norm": 0.392578125,
"learning_rate": 0.0019094881398252184,
"loss": 1.4142,
"step": 87000
},
{
"epoch": 2.275801081980857,
"grad_norm": 0.421875,
"learning_rate": 0.0019089679567207659,
"loss": 1.4153,
"step": 87500
},
{
"epoch": 2.2888056595921764,
"grad_norm": 0.376953125,
"learning_rate": 0.0019084477736163131,
"loss": 1.4189,
"step": 88000
},
{
"epoch": 2.3018102372034956,
"grad_norm": 4.875,
"learning_rate": 0.0019079275905118603,
"loss": 1.4152,
"step": 88500
},
{
"epoch": 2.314814814814815,
"grad_norm": 0.94921875,
"learning_rate": 0.0019074074074074076,
"loss": 1.4148,
"step": 89000
},
{
"epoch": 2.327819392426134,
"grad_norm": 0.435546875,
"learning_rate": 0.0019068872243029546,
"loss": 1.4115,
"step": 89500
},
{
"epoch": 2.3408239700374533,
"grad_norm": 0.69140625,
"learning_rate": 0.0019063670411985018,
"loss": 1.4131,
"step": 90000
},
{
"epoch": 2.3538285476487726,
"grad_norm": 0.515625,
"learning_rate": 0.001905846858094049,
"loss": 1.4085,
"step": 90500
},
{
"epoch": 2.3668331252600914,
"grad_norm": 0.52734375,
"learning_rate": 0.0019053266749895963,
"loss": 1.4096,
"step": 91000
},
{
"epoch": 2.3798377028714106,
"grad_norm": 0.373046875,
"learning_rate": 0.0019048064918851435,
"loss": 1.4128,
"step": 91500
},
{
"epoch": 2.39284228048273,
"grad_norm": 0.451171875,
"learning_rate": 0.0019042863087806907,
"loss": 1.4102,
"step": 92000
},
{
"epoch": 2.405846858094049,
"grad_norm": 0.57421875,
"learning_rate": 0.001903766125676238,
"loss": 1.405,
"step": 92500
},
{
"epoch": 2.4188514357053683,
"grad_norm": 0.59765625,
"learning_rate": 0.0019032459425717854,
"loss": 1.4061,
"step": 93000
},
{
"epoch": 2.4318560133166875,
"grad_norm": 1.1953125,
"learning_rate": 0.0019027257594673326,
"loss": 1.4051,
"step": 93500
},
{
"epoch": 2.444860590928007,
"grad_norm": 0.400390625,
"learning_rate": 0.0019022055763628799,
"loss": 1.4044,
"step": 94000
},
{
"epoch": 2.457865168539326,
"grad_norm": 0.54296875,
"learning_rate": 0.001901685393258427,
"loss": 1.403,
"step": 94500
},
{
"epoch": 2.470869746150645,
"grad_norm": 0.6015625,
"learning_rate": 0.0019011652101539743,
"loss": 1.4064,
"step": 95000
},
{
"epoch": 2.483874323761964,
"grad_norm": 0.47265625,
"learning_rate": 0.0019006450270495215,
"loss": 1.4027,
"step": 95500
},
{
"epoch": 2.4968789013732833,
"grad_norm": 0.47265625,
"learning_rate": 0.0019001248439450688,
"loss": 1.4034,
"step": 96000
},
{
"epoch": 2.5098834789846025,
"grad_norm": 0.42578125,
"learning_rate": 0.001899604660840616,
"loss": 1.4037,
"step": 96500
},
{
"epoch": 2.5228880565959217,
"grad_norm": 0.37109375,
"learning_rate": 0.001899084477736163,
"loss": 1.4087,
"step": 97000
},
{
"epoch": 2.535892634207241,
"grad_norm": 0.953125,
"learning_rate": 0.0018985642946317102,
"loss": 1.4119,
"step": 97500
},
{
"epoch": 2.54889721181856,
"grad_norm": 0.484375,
"learning_rate": 0.0018980441115272575,
"loss": 1.409,
"step": 98000
},
{
"epoch": 2.5619017894298795,
"grad_norm": 0.494140625,
"learning_rate": 0.001897523928422805,
"loss": 1.4066,
"step": 98500
},
{
"epoch": 2.5749063670411987,
"grad_norm": 0.421875,
"learning_rate": 0.0018970037453183521,
"loss": 1.4026,
"step": 99000
},
{
"epoch": 2.587910944652518,
"grad_norm": 0.7421875,
"learning_rate": 0.0018964835622138994,
"loss": 1.4052,
"step": 99500
},
{
"epoch": 2.6009155222638367,
"grad_norm": 0.65234375,
"learning_rate": 0.0018959633791094466,
"loss": 1.4065,
"step": 100000
},
{
"epoch": 2.613920099875156,
"grad_norm": 0.52734375,
"learning_rate": 0.0018954431960049938,
"loss": 1.4009,
"step": 100500
},
{
"epoch": 2.626924677486475,
"grad_norm": 0.7421875,
"learning_rate": 0.001894923012900541,
"loss": 1.4077,
"step": 101000
},
{
"epoch": 2.6399292550977944,
"grad_norm": 0.333984375,
"learning_rate": 0.0018944028297960883,
"loss": 1.4046,
"step": 101500
},
{
"epoch": 2.6529338327091136,
"grad_norm": 0.5234375,
"learning_rate": 0.0018938826466916355,
"loss": 1.4058,
"step": 102000
},
{
"epoch": 2.665938410320433,
"grad_norm": 0.80859375,
"learning_rate": 0.0018933624635871827,
"loss": 1.4028,
"step": 102500
},
{
"epoch": 2.678942987931752,
"grad_norm": 0.40234375,
"learning_rate": 0.00189284228048273,
"loss": 1.3995,
"step": 103000
},
{
"epoch": 2.691947565543071,
"grad_norm": 0.671875,
"learning_rate": 0.0018923220973782772,
"loss": 1.4054,
"step": 103500
},
{
"epoch": 2.70495214315439,
"grad_norm": 0.369140625,
"learning_rate": 0.0018918019142738244,
"loss": 1.407,
"step": 104000
},
{
"epoch": 2.7179567207657094,
"grad_norm": 0.396484375,
"learning_rate": 0.0018912817311693717,
"loss": 1.4034,
"step": 104500
},
{
"epoch": 2.7309612983770286,
"grad_norm": 0.412109375,
"learning_rate": 0.0018907615480649189,
"loss": 1.4037,
"step": 105000
},
{
"epoch": 2.743965875988348,
"grad_norm": 0.443359375,
"learning_rate": 0.0018902413649604661,
"loss": 1.4019,
"step": 105500
},
{
"epoch": 2.756970453599667,
"grad_norm": 0.38671875,
"learning_rate": 0.0018897211818560133,
"loss": 1.3987,
"step": 106000
},
{
"epoch": 2.7699750312109863,
"grad_norm": 0.78515625,
"learning_rate": 0.0018892009987515606,
"loss": 1.4019,
"step": 106500
},
{
"epoch": 2.7829796088223056,
"grad_norm": 1.3984375,
"learning_rate": 0.0018886808156471078,
"loss": 1.4029,
"step": 107000
},
{
"epoch": 2.795984186433625,
"grad_norm": 0.609375,
"learning_rate": 0.001888160632542655,
"loss": 1.4018,
"step": 107500
},
{
"epoch": 2.808988764044944,
"grad_norm": 0.5859375,
"learning_rate": 0.0018876404494382023,
"loss": 1.3986,
"step": 108000
},
{
"epoch": 2.8219933416562633,
"grad_norm": 7.65625,
"learning_rate": 0.0018871202663337495,
"loss": 1.4031,
"step": 108500
},
{
"epoch": 2.834997919267582,
"grad_norm": 0.447265625,
"learning_rate": 0.0018866000832292967,
"loss": 1.4046,
"step": 109000
},
{
"epoch": 2.8480024968789013,
"grad_norm": 0.412109375,
"learning_rate": 0.0018860799001248442,
"loss": 1.4029,
"step": 109500
},
{
"epoch": 2.8610070744902205,
"grad_norm": 0.4609375,
"learning_rate": 0.0018855597170203914,
"loss": 1.399,
"step": 110000
},
{
"epoch": 2.8740116521015397,
"grad_norm": 0.361328125,
"learning_rate": 0.0018850395339159386,
"loss": 1.4,
"step": 110500
},
{
"epoch": 2.887016229712859,
"grad_norm": 0.47265625,
"learning_rate": 0.0018845193508114856,
"loss": 1.3969,
"step": 111000
},
{
"epoch": 2.900020807324178,
"grad_norm": 1.2578125,
"learning_rate": 0.0018839991677070329,
"loss": 1.3984,
"step": 111500
},
{
"epoch": 2.9130253849354975,
"grad_norm": 0.427734375,
"learning_rate": 0.00188347898460258,
"loss": 1.4017,
"step": 112000
},
{
"epoch": 2.9260299625468162,
"grad_norm": 0.7421875,
"learning_rate": 0.0018829588014981273,
"loss": 1.3957,
"step": 112500
},
{
"epoch": 2.9390345401581355,
"grad_norm": 0.37890625,
"learning_rate": 0.0018824386183936745,
"loss": 1.3974,
"step": 113000
},
{
"epoch": 2.9520391177694547,
"grad_norm": 0.486328125,
"learning_rate": 0.0018819184352892218,
"loss": 1.3972,
"step": 113500
},
{
"epoch": 2.965043695380774,
"grad_norm": 0.37109375,
"learning_rate": 0.001881398252184769,
"loss": 1.3994,
"step": 114000
},
{
"epoch": 2.978048272992093,
"grad_norm": 0.498046875,
"learning_rate": 0.0018808780690803162,
"loss": 1.3966,
"step": 114500
},
{
"epoch": 2.9910528506034124,
"grad_norm": 0.4296875,
"learning_rate": 0.0018803578859758635,
"loss": 1.3966,
"step": 115000
},
{
"epoch": 3.0,
"eval_loss": 1.3958898782730103,
"eval_runtime": 0.5647,
"eval_samples_per_second": 1770.912,
"eval_steps_per_second": 7.084,
"step": 115344
},
{
"epoch": 3.0040574282147317,
"grad_norm": 0.76171875,
"learning_rate": 0.001879837702871411,
"loss": 1.3932,
"step": 115500
},
{
"epoch": 3.017062005826051,
"grad_norm": 0.431640625,
"learning_rate": 0.0018793175197669581,
"loss": 1.3914,
"step": 116000
},
{
"epoch": 3.03006658343737,
"grad_norm": 0.56640625,
"learning_rate": 0.0018787973366625054,
"loss": 1.389,
"step": 116500
},
{
"epoch": 3.0430711610486894,
"grad_norm": 0.55078125,
"learning_rate": 0.0018782771535580526,
"loss": 1.3895,
"step": 117000
},
{
"epoch": 3.056075738660008,
"grad_norm": 0.50390625,
"learning_rate": 0.0018777569704535998,
"loss": 1.3904,
"step": 117500
},
{
"epoch": 3.0690803162713274,
"grad_norm": 0.423828125,
"learning_rate": 0.001877236787349147,
"loss": 1.3905,
"step": 118000
},
{
"epoch": 3.0820848938826466,
"grad_norm": 0.51953125,
"learning_rate": 0.001876716604244694,
"loss": 1.3899,
"step": 118500
},
{
"epoch": 3.095089471493966,
"grad_norm": 1.2265625,
"learning_rate": 0.0018761964211402413,
"loss": 1.386,
"step": 119000
},
{
"epoch": 3.108094049105285,
"grad_norm": 0.48046875,
"learning_rate": 0.0018756762380357885,
"loss": 1.3859,
"step": 119500
},
{
"epoch": 3.1210986267166043,
"grad_norm": 0.3984375,
"learning_rate": 0.0018751560549313357,
"loss": 1.3893,
"step": 120000
},
{
"epoch": 3.1341032043279236,
"grad_norm": 0.46875,
"learning_rate": 0.001874635871826883,
"loss": 1.3883,
"step": 120500
},
{
"epoch": 3.147107781939243,
"grad_norm": 0.359375,
"learning_rate": 0.0018741156887224304,
"loss": 1.3898,
"step": 121000
},
{
"epoch": 3.1601123595505616,
"grad_norm": 0.76953125,
"learning_rate": 0.0018735955056179776,
"loss": 1.3894,
"step": 121500
},
{
"epoch": 3.173116937161881,
"grad_norm": 0.46484375,
"learning_rate": 0.0018730753225135249,
"loss": 1.3903,
"step": 122000
},
{
"epoch": 3.1861215147732,
"grad_norm": 0.41015625,
"learning_rate": 0.001872555139409072,
"loss": 1.3873,
"step": 122500
},
{
"epoch": 3.1991260923845193,
"grad_norm": 0.365234375,
"learning_rate": 0.0018720349563046193,
"loss": 1.3857,
"step": 123000
},
{
"epoch": 3.2121306699958385,
"grad_norm": 0.5234375,
"learning_rate": 0.0018715147732001666,
"loss": 1.3907,
"step": 123500
},
{
"epoch": 3.2251352476071578,
"grad_norm": 0.380859375,
"learning_rate": 0.0018709945900957138,
"loss": 1.3858,
"step": 124000
},
{
"epoch": 3.238139825218477,
"grad_norm": 0.458984375,
"learning_rate": 0.001870474406991261,
"loss": 1.3873,
"step": 124500
},
{
"epoch": 3.251144402829796,
"grad_norm": 0.515625,
"learning_rate": 0.0018699542238868082,
"loss": 1.3846,
"step": 125000
},
{
"epoch": 3.2641489804411155,
"grad_norm": 0.6640625,
"learning_rate": 0.0018694340407823553,
"loss": 1.3891,
"step": 125500
},
{
"epoch": 3.2771535580524347,
"grad_norm": 7.5,
"learning_rate": 0.0018689138576779025,
"loss": 1.3882,
"step": 126000
},
{
"epoch": 3.2901581356637535,
"grad_norm": 0.48828125,
"learning_rate": 0.00186839367457345,
"loss": 1.3879,
"step": 126500
},
{
"epoch": 3.3031627132750727,
"grad_norm": 0.404296875,
"learning_rate": 0.0018678734914689972,
"loss": 1.3861,
"step": 127000
},
{
"epoch": 3.316167290886392,
"grad_norm": 3.21875,
"learning_rate": 0.0018673533083645444,
"loss": 1.3863,
"step": 127500
},
{
"epoch": 3.329171868497711,
"grad_norm": 0.40234375,
"learning_rate": 0.0018668331252600916,
"loss": 1.3832,
"step": 128000
},
{
"epoch": 3.3421764461090304,
"grad_norm": 0.5,
"learning_rate": 0.0018663129421556388,
"loss": 1.3859,
"step": 128500
},
{
"epoch": 3.3551810237203497,
"grad_norm": 0.48828125,
"learning_rate": 0.001865792759051186,
"loss": 1.3859,
"step": 129000
},
{
"epoch": 3.368185601331669,
"grad_norm": 0.7734375,
"learning_rate": 0.0018652725759467333,
"loss": 1.3882,
"step": 129500
},
{
"epoch": 3.381190178942988,
"grad_norm": 0.39453125,
"learning_rate": 0.0018647523928422805,
"loss": 1.3863,
"step": 130000
},
{
"epoch": 3.394194756554307,
"grad_norm": 0.357421875,
"learning_rate": 0.0018642322097378278,
"loss": 1.3866,
"step": 130500
},
{
"epoch": 3.407199334165626,
"grad_norm": 0.3828125,
"learning_rate": 0.001863712026633375,
"loss": 1.3863,
"step": 131000
},
{
"epoch": 3.4202039117769454,
"grad_norm": 0.57421875,
"learning_rate": 0.0018631918435289222,
"loss": 1.3839,
"step": 131500
},
{
"epoch": 3.4332084893882646,
"grad_norm": 0.9296875,
"learning_rate": 0.0018626716604244697,
"loss": 1.3842,
"step": 132000
},
{
"epoch": 3.446213066999584,
"grad_norm": 0.482421875,
"learning_rate": 0.0018621514773200167,
"loss": 1.384,
"step": 132500
},
{
"epoch": 3.459217644610903,
"grad_norm": 0.40234375,
"learning_rate": 0.001861631294215564,
"loss": 1.3835,
"step": 133000
},
{
"epoch": 3.4722222222222223,
"grad_norm": 0.400390625,
"learning_rate": 0.0018611111111111111,
"loss": 1.3857,
"step": 133500
},
{
"epoch": 3.4852267998335416,
"grad_norm": 0.416015625,
"learning_rate": 0.0018605909280066584,
"loss": 1.3822,
"step": 134000
},
{
"epoch": 3.498231377444861,
"grad_norm": 0.373046875,
"learning_rate": 0.0018600707449022056,
"loss": 1.3798,
"step": 134500
},
{
"epoch": 3.51123595505618,
"grad_norm": 0.39453125,
"learning_rate": 0.0018595505617977528,
"loss": 1.3806,
"step": 135000
},
{
"epoch": 3.524240532667499,
"grad_norm": 0.50390625,
"learning_rate": 0.0018590303786933,
"loss": 1.3825,
"step": 135500
},
{
"epoch": 3.537245110278818,
"grad_norm": 0.609375,
"learning_rate": 0.0018585101955888473,
"loss": 1.3822,
"step": 136000
},
{
"epoch": 3.5502496878901373,
"grad_norm": 0.40625,
"learning_rate": 0.0018579900124843945,
"loss": 1.3837,
"step": 136500
},
{
"epoch": 3.5632542655014565,
"grad_norm": 0.431640625,
"learning_rate": 0.0018574698293799417,
"loss": 1.3789,
"step": 137000
},
{
"epoch": 3.5762588431127758,
"grad_norm": 0.373046875,
"learning_rate": 0.001856949646275489,
"loss": 1.3798,
"step": 137500
},
{
"epoch": 3.589263420724095,
"grad_norm": 0.46875,
"learning_rate": 0.0018564294631710364,
"loss": 1.3812,
"step": 138000
},
{
"epoch": 3.6022679983354142,
"grad_norm": 3.21875,
"learning_rate": 0.0018559092800665836,
"loss": 1.3765,
"step": 138500
},
{
"epoch": 3.615272575946733,
"grad_norm": 0.37109375,
"learning_rate": 0.0018553890969621309,
"loss": 1.3759,
"step": 139000
},
{
"epoch": 3.6282771535580522,
"grad_norm": 0.435546875,
"learning_rate": 0.0018548689138576779,
"loss": 1.382,
"step": 139500
},
{
"epoch": 3.6412817311693715,
"grad_norm": 0.9921875,
"learning_rate": 0.001854348730753225,
"loss": 1.3796,
"step": 140000
},
{
"epoch": 3.6542863087806907,
"grad_norm": 14.375,
"learning_rate": 0.0018538285476487723,
"loss": 1.3818,
"step": 140500
},
{
"epoch": 3.66729088639201,
"grad_norm": 6.15625,
"learning_rate": 0.0018533083645443196,
"loss": 1.3825,
"step": 141000
},
{
"epoch": 3.680295464003329,
"grad_norm": 0.310546875,
"learning_rate": 0.0018527881814398668,
"loss": 1.3821,
"step": 141500
},
{
"epoch": 3.6933000416146484,
"grad_norm": 4.03125,
"learning_rate": 0.001852267998335414,
"loss": 1.3776,
"step": 142000
},
{
"epoch": 3.7063046192259677,
"grad_norm": 0.380859375,
"learning_rate": 0.0018517478152309612,
"loss": 1.3791,
"step": 142500
},
{
"epoch": 3.719309196837287,
"grad_norm": 0.73828125,
"learning_rate": 0.0018512276321265085,
"loss": 1.3764,
"step": 143000
},
{
"epoch": 3.732313774448606,
"grad_norm": 0.48046875,
"learning_rate": 0.001850707449022056,
"loss": 1.3773,
"step": 143500
},
{
"epoch": 3.7453183520599254,
"grad_norm": 0.435546875,
"learning_rate": 0.0018501872659176031,
"loss": 1.3803,
"step": 144000
},
{
"epoch": 3.758322929671244,
"grad_norm": 0.400390625,
"learning_rate": 0.0018496670828131504,
"loss": 1.3776,
"step": 144500
},
{
"epoch": 3.7713275072825634,
"grad_norm": 0.45703125,
"learning_rate": 0.0018491468997086976,
"loss": 1.3758,
"step": 145000
},
{
"epoch": 3.7843320848938826,
"grad_norm": 0.5625,
"learning_rate": 0.0018486267166042448,
"loss": 1.3779,
"step": 145500
},
{
"epoch": 3.797336662505202,
"grad_norm": 0.423828125,
"learning_rate": 0.001848106533499792,
"loss": 1.3788,
"step": 146000
},
{
"epoch": 3.810341240116521,
"grad_norm": 0.50390625,
"learning_rate": 0.0018475863503953393,
"loss": 1.3766,
"step": 146500
},
{
"epoch": 3.8233458177278403,
"grad_norm": 0.486328125,
"learning_rate": 0.0018470661672908863,
"loss": 1.3764,
"step": 147000
},
{
"epoch": 3.836350395339159,
"grad_norm": 0.421875,
"learning_rate": 0.0018465459841864335,
"loss": 1.378,
"step": 147500
},
{
"epoch": 3.8493549729504783,
"grad_norm": 0.34375,
"learning_rate": 0.0018460258010819808,
"loss": 1.3738,
"step": 148000
},
{
"epoch": 3.8623595505617976,
"grad_norm": 0.482421875,
"learning_rate": 0.001845505617977528,
"loss": 1.3739,
"step": 148500
},
{
"epoch": 3.875364128173117,
"grad_norm": 0.515625,
"learning_rate": 0.0018449854348730754,
"loss": 1.3743,
"step": 149000
},
{
"epoch": 3.888368705784436,
"grad_norm": 0.435546875,
"learning_rate": 0.0018444652517686227,
"loss": 1.3736,
"step": 149500
},
{
"epoch": 3.9013732833957553,
"grad_norm": 1.34375,
"learning_rate": 0.0018439450686641699,
"loss": 1.3727,
"step": 150000
},
{
"epoch": 3.9143778610070745,
"grad_norm": 0.478515625,
"learning_rate": 0.0018434248855597171,
"loss": 1.3772,
"step": 150500
},
{
"epoch": 3.9273824386183938,
"grad_norm": 1.171875,
"learning_rate": 0.0018429047024552643,
"loss": 1.3708,
"step": 151000
},
{
"epoch": 3.940387016229713,
"grad_norm": 0.5078125,
"learning_rate": 0.0018423845193508116,
"loss": 1.3735,
"step": 151500
},
{
"epoch": 3.9533915938410322,
"grad_norm": 0.875,
"learning_rate": 0.0018418643362463588,
"loss": 1.3735,
"step": 152000
},
{
"epoch": 3.9663961714523515,
"grad_norm": 0.439453125,
"learning_rate": 0.001841344153141906,
"loss": 1.3741,
"step": 152500
},
{
"epoch": 3.9794007490636703,
"grad_norm": 0.51171875,
"learning_rate": 0.0018408239700374533,
"loss": 1.3725,
"step": 153000
},
{
"epoch": 3.9924053266749895,
"grad_norm": 1.4921875,
"learning_rate": 0.0018403037869330005,
"loss": 1.3764,
"step": 153500
},
{
"epoch": 4.0,
"eval_loss": 1.380986213684082,
"eval_runtime": 0.7298,
"eval_samples_per_second": 1370.29,
"eval_steps_per_second": 5.481,
"step": 153792
},
{
"epoch": 4.005409904286309,
"grad_norm": 0.7890625,
"learning_rate": 0.0018397836038285475,
"loss": 1.3757,
"step": 154000
},
{
"epoch": 4.018414481897628,
"grad_norm": 0.953125,
"learning_rate": 0.001839263420724095,
"loss": 1.3727,
"step": 154500
},
{
"epoch": 4.031419059508947,
"grad_norm": 0.40234375,
"learning_rate": 0.0018387432376196422,
"loss": 1.3686,
"step": 155000
},
{
"epoch": 4.044423637120266,
"grad_norm": 0.5078125,
"learning_rate": 0.0018382230545151894,
"loss": 1.3683,
"step": 155500
},
{
"epoch": 4.057428214731585,
"grad_norm": 0.50390625,
"learning_rate": 0.0018377028714107366,
"loss": 1.371,
"step": 156000
},
{
"epoch": 4.0704327923429044,
"grad_norm": 0.51953125,
"learning_rate": 0.0018371826883062839,
"loss": 1.3706,
"step": 156500
},
{
"epoch": 4.083437369954224,
"grad_norm": 0.984375,
"learning_rate": 0.001836662505201831,
"loss": 1.3682,
"step": 157000
},
{
"epoch": 4.096441947565543,
"grad_norm": 0.384765625,
"learning_rate": 0.0018361423220973783,
"loss": 1.3709,
"step": 157500
},
{
"epoch": 4.109446525176862,
"grad_norm": 0.384765625,
"learning_rate": 0.0018356221389929255,
"loss": 1.3705,
"step": 158000
},
{
"epoch": 4.122451102788181,
"grad_norm": 0.373046875,
"learning_rate": 0.0018351019558884728,
"loss": 1.3714,
"step": 158500
},
{
"epoch": 4.135455680399501,
"grad_norm": 1.46875,
"learning_rate": 0.00183458177278402,
"loss": 1.3688,
"step": 159000
},
{
"epoch": 4.14846025801082,
"grad_norm": 0.345703125,
"learning_rate": 0.0018340615896795672,
"loss": 1.3723,
"step": 159500
},
{
"epoch": 4.161464835622139,
"grad_norm": 0.8125,
"learning_rate": 0.0018335414065751145,
"loss": 1.3697,
"step": 160000
},
{
"epoch": 4.174469413233458,
"grad_norm": 0.3828125,
"learning_rate": 0.001833021223470662,
"loss": 1.3684,
"step": 160500
},
{
"epoch": 4.187473990844778,
"grad_norm": 0.396484375,
"learning_rate": 0.001832501040366209,
"loss": 1.3704,
"step": 161000
},
{
"epoch": 4.200478568456097,
"grad_norm": 0.400390625,
"learning_rate": 0.0018319808572617561,
"loss": 1.3705,
"step": 161500
},
{
"epoch": 4.213483146067416,
"grad_norm": 1.0703125,
"learning_rate": 0.0018314606741573034,
"loss": 1.3744,
"step": 162000
},
{
"epoch": 4.226487723678735,
"grad_norm": 0.40234375,
"learning_rate": 0.0018309404910528506,
"loss": 1.3663,
"step": 162500
},
{
"epoch": 4.2394923012900545,
"grad_norm": 0.451171875,
"learning_rate": 0.0018304203079483978,
"loss": 1.3706,
"step": 163000
},
{
"epoch": 4.252496878901374,
"grad_norm": 0.7890625,
"learning_rate": 0.001829900124843945,
"loss": 1.37,
"step": 163500
},
{
"epoch": 4.265501456512692,
"grad_norm": 0.9140625,
"learning_rate": 0.0018293799417394923,
"loss": 1.3669,
"step": 164000
},
{
"epoch": 4.278506034124011,
"grad_norm": 0.765625,
"learning_rate": 0.0018288597586350395,
"loss": 1.3674,
"step": 164500
},
{
"epoch": 4.2915106117353305,
"grad_norm": 0.4609375,
"learning_rate": 0.0018283395755305867,
"loss": 1.3672,
"step": 165000
},
{
"epoch": 4.30451518934665,
"grad_norm": 1.15625,
"learning_rate": 0.001827819392426134,
"loss": 1.37,
"step": 165500
},
{
"epoch": 4.317519766957969,
"grad_norm": 1.765625,
"learning_rate": 0.0018272992093216814,
"loss": 1.3724,
"step": 166000
},
{
"epoch": 4.330524344569288,
"grad_norm": 0.57421875,
"learning_rate": 0.0018267790262172286,
"loss": 1.3687,
"step": 166500
},
{
"epoch": 4.3435289221806075,
"grad_norm": 0.384765625,
"learning_rate": 0.0018262588431127759,
"loss": 1.3676,
"step": 167000
},
{
"epoch": 4.356533499791927,
"grad_norm": 0.4140625,
"learning_rate": 0.001825738660008323,
"loss": 1.3672,
"step": 167500
},
{
"epoch": 4.369538077403246,
"grad_norm": 1.7890625,
"learning_rate": 0.0018252184769038703,
"loss": 1.3675,
"step": 168000
},
{
"epoch": 4.382542655014565,
"grad_norm": 0.5234375,
"learning_rate": 0.0018246982937994173,
"loss": 1.3682,
"step": 168500
},
{
"epoch": 4.395547232625884,
"grad_norm": 0.78515625,
"learning_rate": 0.0018241781106949646,
"loss": 1.3675,
"step": 169000
},
{
"epoch": 4.408551810237204,
"grad_norm": 0.50390625,
"learning_rate": 0.0018236579275905118,
"loss": 1.3675,
"step": 169500
},
{
"epoch": 4.421556387848523,
"grad_norm": 0.427734375,
"learning_rate": 0.001823137744486059,
"loss": 1.367,
"step": 170000
},
{
"epoch": 4.434560965459842,
"grad_norm": 0.42578125,
"learning_rate": 0.0018226175613816062,
"loss": 1.3729,
"step": 170500
},
{
"epoch": 4.447565543071161,
"grad_norm": 0.546875,
"learning_rate": 0.0018220973782771535,
"loss": 1.3654,
"step": 171000
},
{
"epoch": 4.460570120682481,
"grad_norm": 0.625,
"learning_rate": 0.001821577195172701,
"loss": 1.3694,
"step": 171500
},
{
"epoch": 4.473574698293799,
"grad_norm": 0.80078125,
"learning_rate": 0.0018210570120682482,
"loss": 1.3647,
"step": 172000
},
{
"epoch": 4.486579275905118,
"grad_norm": 0.40625,
"learning_rate": 0.0018205368289637954,
"loss": 1.369,
"step": 172500
},
{
"epoch": 4.499583853516437,
"grad_norm": 0.427734375,
"learning_rate": 0.0018200166458593426,
"loss": 1.3665,
"step": 173000
},
{
"epoch": 4.512588431127757,
"grad_norm": 0.5625,
"learning_rate": 0.0018194964627548898,
"loss": 1.3661,
"step": 173500
},
{
"epoch": 4.525593008739076,
"grad_norm": 0.6796875,
"learning_rate": 0.001818976279650437,
"loss": 1.3649,
"step": 174000
},
{
"epoch": 4.538597586350395,
"grad_norm": 0.37890625,
"learning_rate": 0.0018184560965459843,
"loss": 1.3667,
"step": 174500
},
{
"epoch": 4.551602163961714,
"grad_norm": 0.439453125,
"learning_rate": 0.0018179359134415315,
"loss": 1.3658,
"step": 175000
},
{
"epoch": 4.564606741573034,
"grad_norm": 0.392578125,
"learning_rate": 0.0018174157303370785,
"loss": 1.3655,
"step": 175500
},
{
"epoch": 4.577611319184353,
"grad_norm": 0.416015625,
"learning_rate": 0.0018168955472326258,
"loss": 1.3638,
"step": 176000
},
{
"epoch": 4.590615896795672,
"grad_norm": 1.484375,
"learning_rate": 0.001816375364128173,
"loss": 1.3621,
"step": 176500
},
{
"epoch": 4.603620474406991,
"grad_norm": 0.349609375,
"learning_rate": 0.0018158551810237204,
"loss": 1.3649,
"step": 177000
},
{
"epoch": 4.6166250520183105,
"grad_norm": 0.41796875,
"learning_rate": 0.0018153349979192677,
"loss": 1.3616,
"step": 177500
},
{
"epoch": 4.62962962962963,
"grad_norm": 1.2890625,
"learning_rate": 0.001814814814814815,
"loss": 1.3617,
"step": 178000
},
{
"epoch": 4.642634207240949,
"grad_norm": 0.59765625,
"learning_rate": 0.0018142946317103621,
"loss": 1.3639,
"step": 178500
},
{
"epoch": 4.655638784852268,
"grad_norm": 1.0703125,
"learning_rate": 0.0018137744486059093,
"loss": 1.3641,
"step": 179000
},
{
"epoch": 4.6686433624635875,
"grad_norm": 0.375,
"learning_rate": 0.0018132542655014566,
"loss": 1.3652,
"step": 179500
},
{
"epoch": 4.681647940074907,
"grad_norm": 0.3984375,
"learning_rate": 0.0018127340823970038,
"loss": 1.3633,
"step": 180000
},
{
"epoch": 4.694652517686226,
"grad_norm": 2.578125,
"learning_rate": 0.001812213899292551,
"loss": 1.3624,
"step": 180500
},
{
"epoch": 4.707657095297545,
"grad_norm": 0.35546875,
"learning_rate": 0.0018116937161880983,
"loss": 1.3658,
"step": 181000
},
{
"epoch": 4.720661672908864,
"grad_norm": 0.43359375,
"learning_rate": 0.0018111735330836455,
"loss": 1.3636,
"step": 181500
},
{
"epoch": 4.733666250520183,
"grad_norm": 0.390625,
"learning_rate": 0.0018106533499791927,
"loss": 1.36,
"step": 182000
},
{
"epoch": 4.746670828131502,
"grad_norm": 0.419921875,
"learning_rate": 0.00181013316687474,
"loss": 1.3631,
"step": 182500
},
{
"epoch": 4.759675405742821,
"grad_norm": 1.5390625,
"learning_rate": 0.0018096129837702872,
"loss": 1.3647,
"step": 183000
},
{
"epoch": 4.7726799833541405,
"grad_norm": 0.376953125,
"learning_rate": 0.0018090928006658344,
"loss": 1.3589,
"step": 183500
},
{
"epoch": 4.78568456096546,
"grad_norm": 0.40234375,
"learning_rate": 0.0018085726175613816,
"loss": 1.3616,
"step": 184000
},
{
"epoch": 4.798689138576779,
"grad_norm": 0.447265625,
"learning_rate": 0.0018080524344569289,
"loss": 1.3632,
"step": 184500
},
{
"epoch": 4.811693716188098,
"grad_norm": 0.89453125,
"learning_rate": 0.001807532251352476,
"loss": 1.3643,
"step": 185000
},
{
"epoch": 4.824698293799417,
"grad_norm": 0.5859375,
"learning_rate": 0.0018070120682480233,
"loss": 1.3632,
"step": 185500
},
{
"epoch": 4.837702871410737,
"grad_norm": 0.48046875,
"learning_rate": 0.0018064918851435705,
"loss": 1.361,
"step": 186000
},
{
"epoch": 4.850707449022056,
"grad_norm": 0.396484375,
"learning_rate": 0.0018059717020391178,
"loss": 1.3622,
"step": 186500
},
{
"epoch": 4.863712026633375,
"grad_norm": 0.376953125,
"learning_rate": 0.001805451518934665,
"loss": 1.362,
"step": 187000
},
{
"epoch": 4.876716604244694,
"grad_norm": 0.5078125,
"learning_rate": 0.0018049313358302122,
"loss": 1.3623,
"step": 187500
},
{
"epoch": 4.889721181856014,
"grad_norm": 0.828125,
"learning_rate": 0.0018044111527257595,
"loss": 1.3599,
"step": 188000
},
{
"epoch": 4.902725759467333,
"grad_norm": 0.546875,
"learning_rate": 0.001803890969621307,
"loss": 1.3636,
"step": 188500
},
{
"epoch": 4.915730337078652,
"grad_norm": 0.4453125,
"learning_rate": 0.0018033707865168541,
"loss": 1.3609,
"step": 189000
},
{
"epoch": 4.92873491468997,
"grad_norm": 0.404296875,
"learning_rate": 0.0018028506034124014,
"loss": 1.3603,
"step": 189500
},
{
"epoch": 4.94173949230129,
"grad_norm": 0.6484375,
"learning_rate": 0.0018023304203079484,
"loss": 1.3601,
"step": 190000
},
{
"epoch": 4.954744069912609,
"grad_norm": 0.34765625,
"learning_rate": 0.0018018102372034956,
"loss": 1.3569,
"step": 190500
},
{
"epoch": 4.967748647523928,
"grad_norm": 0.451171875,
"learning_rate": 0.0018012900540990428,
"loss": 1.358,
"step": 191000
},
{
"epoch": 4.980753225135247,
"grad_norm": 0.92578125,
"learning_rate": 0.00180076987099459,
"loss": 1.3577,
"step": 191500
},
{
"epoch": 4.9937578027465666,
"grad_norm": 0.72265625,
"learning_rate": 0.0018002496878901373,
"loss": 1.3618,
"step": 192000
},
{
"epoch": 5.0,
"eval_loss": 1.3649697303771973,
"eval_runtime": 0.5987,
"eval_samples_per_second": 1670.164,
"eval_steps_per_second": 6.681,
"step": 192240
},
{
"epoch": 5.006762380357886,
"grad_norm": 0.3671875,
"learning_rate": 0.0017997295047856845,
"loss": 1.3587,
"step": 192500
},
{
"epoch": 5.019766957969205,
"grad_norm": 0.8046875,
"learning_rate": 0.0017992093216812317,
"loss": 1.3542,
"step": 193000
},
{
"epoch": 5.032771535580524,
"grad_norm": 0.353515625,
"learning_rate": 0.001798689138576779,
"loss": 1.3558,
"step": 193500
},
{
"epoch": 5.0457761131918435,
"grad_norm": 0.47265625,
"learning_rate": 0.0017981689554723264,
"loss": 1.3563,
"step": 194000
},
{
"epoch": 5.058780690803163,
"grad_norm": 0.337890625,
"learning_rate": 0.0017976487723678736,
"loss": 1.3549,
"step": 194500
},
{
"epoch": 5.071785268414482,
"grad_norm": 0.458984375,
"learning_rate": 0.0017971285892634209,
"loss": 1.3541,
"step": 195000
},
{
"epoch": 5.084789846025801,
"grad_norm": 0.38671875,
"learning_rate": 0.001796608406158968,
"loss": 1.3555,
"step": 195500
},
{
"epoch": 5.09779442363712,
"grad_norm": 0.68359375,
"learning_rate": 0.0017960882230545153,
"loss": 1.3536,
"step": 196000
},
{
"epoch": 5.11079900124844,
"grad_norm": 0.4140625,
"learning_rate": 0.0017955680399500626,
"loss": 1.3523,
"step": 196500
},
{
"epoch": 5.123803578859759,
"grad_norm": 0.46875,
"learning_rate": 0.0017950478568456096,
"loss": 1.3543,
"step": 197000
},
{
"epoch": 5.136808156471078,
"grad_norm": 0.44921875,
"learning_rate": 0.0017945276737411568,
"loss": 1.3544,
"step": 197500
},
{
"epoch": 5.149812734082397,
"grad_norm": 0.41796875,
"learning_rate": 0.001794007490636704,
"loss": 1.3546,
"step": 198000
},
{
"epoch": 5.162817311693717,
"grad_norm": 0.474609375,
"learning_rate": 0.0017934873075322513,
"loss": 1.3536,
"step": 198500
},
{
"epoch": 5.175821889305035,
"grad_norm": 0.453125,
"learning_rate": 0.0017929671244277985,
"loss": 1.3516,
"step": 199000
},
{
"epoch": 5.188826466916354,
"grad_norm": 0.3984375,
"learning_rate": 0.001792446941323346,
"loss": 1.353,
"step": 199500
},
{
"epoch": 5.201831044527673,
"grad_norm": 0.51171875,
"learning_rate": 0.0017919267582188932,
"loss": 1.3541,
"step": 200000
},
{
"epoch": 5.214835622138993,
"grad_norm": 0.392578125,
"learning_rate": 0.0017914065751144404,
"loss": 1.3511,
"step": 200500
},
{
"epoch": 5.227840199750312,
"grad_norm": 0.6953125,
"learning_rate": 0.0017908863920099876,
"loss": 1.3531,
"step": 201000
},
{
"epoch": 5.240844777361631,
"grad_norm": 0.6171875,
"learning_rate": 0.0017903662089055348,
"loss": 1.3527,
"step": 201500
},
{
"epoch": 5.25384935497295,
"grad_norm": 0.7265625,
"learning_rate": 0.001789846025801082,
"loss": 1.3544,
"step": 202000
},
{
"epoch": 5.26685393258427,
"grad_norm": 0.515625,
"learning_rate": 0.0017893258426966293,
"loss": 1.35,
"step": 202500
},
{
"epoch": 5.279858510195589,
"grad_norm": 0.5546875,
"learning_rate": 0.0017888056595921765,
"loss": 1.3526,
"step": 203000
},
{
"epoch": 5.292863087806908,
"grad_norm": 0.40625,
"learning_rate": 0.0017882854764877238,
"loss": 1.3583,
"step": 203500
},
{
"epoch": 5.305867665418227,
"grad_norm": 0.49609375,
"learning_rate": 0.0017877652933832708,
"loss": 1.3553,
"step": 204000
},
{
"epoch": 5.3188722430295465,
"grad_norm": 0.67578125,
"learning_rate": 0.001787245110278818,
"loss": 1.3526,
"step": 204500
},
{
"epoch": 5.331876820640866,
"grad_norm": 0.373046875,
"learning_rate": 0.0017867249271743654,
"loss": 1.3538,
"step": 205000
},
{
"epoch": 5.344881398252185,
"grad_norm": 0.384765625,
"learning_rate": 0.0017862047440699127,
"loss": 1.351,
"step": 205500
},
{
"epoch": 5.357885975863504,
"grad_norm": 0.59765625,
"learning_rate": 0.00178568456096546,
"loss": 1.3513,
"step": 206000
},
{
"epoch": 5.3708905534748235,
"grad_norm": 0.380859375,
"learning_rate": 0.0017851643778610071,
"loss": 1.3508,
"step": 206500
},
{
"epoch": 5.383895131086143,
"grad_norm": 0.419921875,
"learning_rate": 0.0017846441947565544,
"loss": 1.3511,
"step": 207000
},
{
"epoch": 5.396899708697461,
"grad_norm": 0.388671875,
"learning_rate": 0.0017841240116521016,
"loss": 1.3536,
"step": 207500
},
{
"epoch": 5.40990428630878,
"grad_norm": 0.384765625,
"learning_rate": 0.0017836038285476488,
"loss": 1.3534,
"step": 208000
},
{
"epoch": 5.4229088639200995,
"grad_norm": 0.390625,
"learning_rate": 0.001783083645443196,
"loss": 1.3532,
"step": 208500
},
{
"epoch": 5.435913441531419,
"grad_norm": 0.5,
"learning_rate": 0.0017825634623387433,
"loss": 1.3528,
"step": 209000
},
{
"epoch": 5.448918019142738,
"grad_norm": 0.7109375,
"learning_rate": 0.0017820432792342905,
"loss": 1.3511,
"step": 209500
},
{
"epoch": 5.461922596754057,
"grad_norm": 0.5546875,
"learning_rate": 0.0017815230961298377,
"loss": 1.3538,
"step": 210000
},
{
"epoch": 5.4749271743653765,
"grad_norm": 0.396484375,
"learning_rate": 0.001781002913025385,
"loss": 1.354,
"step": 210500
},
{
"epoch": 5.487931751976696,
"grad_norm": 0.455078125,
"learning_rate": 0.0017804827299209324,
"loss": 1.353,
"step": 211000
},
{
"epoch": 5.500936329588015,
"grad_norm": 16.875,
"learning_rate": 0.0017799625468164794,
"loss": 1.3542,
"step": 211500
},
{
"epoch": 5.513940907199334,
"grad_norm": 0.51953125,
"learning_rate": 0.0017794423637120266,
"loss": 1.3551,
"step": 212000
},
{
"epoch": 5.526945484810653,
"grad_norm": 0.48046875,
"learning_rate": 0.0017789221806075739,
"loss": 1.3531,
"step": 212500
},
{
"epoch": 5.539950062421973,
"grad_norm": 0.56640625,
"learning_rate": 0.001778401997503121,
"loss": 1.3545,
"step": 213000
},
{
"epoch": 5.552954640033292,
"grad_norm": 1.46875,
"learning_rate": 0.0017778818143986683,
"loss": 1.3521,
"step": 213500
},
{
"epoch": 5.565959217644611,
"grad_norm": 0.462890625,
"learning_rate": 0.0017773616312942156,
"loss": 1.3552,
"step": 214000
},
{
"epoch": 5.57896379525593,
"grad_norm": 0.55859375,
"learning_rate": 0.0017768414481897628,
"loss": 1.3549,
"step": 214500
},
{
"epoch": 5.59196837286725,
"grad_norm": 0.66015625,
"learning_rate": 0.00177632126508531,
"loss": 1.3519,
"step": 215000
},
{
"epoch": 5.604972950478569,
"grad_norm": 0.373046875,
"learning_rate": 0.0017758010819808572,
"loss": 1.351,
"step": 215500
},
{
"epoch": 5.617977528089888,
"grad_norm": 0.43359375,
"learning_rate": 0.0017752808988764045,
"loss": 1.3514,
"step": 216000
},
{
"epoch": 5.630982105701207,
"grad_norm": 0.427734375,
"learning_rate": 0.001774760715771952,
"loss": 1.3471,
"step": 216500
},
{
"epoch": 5.643986683312526,
"grad_norm": 0.400390625,
"learning_rate": 0.0017742405326674991,
"loss": 1.3486,
"step": 217000
},
{
"epoch": 5.656991260923845,
"grad_norm": 0.53515625,
"learning_rate": 0.0017737203495630464,
"loss": 1.3508,
"step": 217500
},
{
"epoch": 5.669995838535164,
"grad_norm": 0.67578125,
"learning_rate": 0.0017732001664585936,
"loss": 1.3506,
"step": 218000
},
{
"epoch": 5.683000416146483,
"grad_norm": 0.333984375,
"learning_rate": 0.0017726799833541406,
"loss": 1.3505,
"step": 218500
},
{
"epoch": 5.696004993757803,
"grad_norm": 0.4609375,
"learning_rate": 0.0017721598002496878,
"loss": 1.3473,
"step": 219000
},
{
"epoch": 5.709009571369122,
"grad_norm": 0.349609375,
"learning_rate": 0.001771639617145235,
"loss": 1.3509,
"step": 219500
},
{
"epoch": 5.722014148980441,
"grad_norm": 0.60546875,
"learning_rate": 0.0017711194340407823,
"loss": 1.3531,
"step": 220000
},
{
"epoch": 5.73501872659176,
"grad_norm": 0.37890625,
"learning_rate": 0.0017705992509363295,
"loss": 1.3525,
"step": 220500
},
{
"epoch": 5.7480233042030795,
"grad_norm": 0.765625,
"learning_rate": 0.0017700790678318768,
"loss": 1.3504,
"step": 221000
},
{
"epoch": 5.761027881814399,
"grad_norm": 0.37109375,
"learning_rate": 0.001769558884727424,
"loss": 1.3499,
"step": 221500
},
{
"epoch": 5.774032459425718,
"grad_norm": 0.86328125,
"learning_rate": 0.0017690387016229714,
"loss": 1.3504,
"step": 222000
},
{
"epoch": 5.787037037037037,
"grad_norm": 0.65625,
"learning_rate": 0.0017685185185185187,
"loss": 1.3496,
"step": 222500
},
{
"epoch": 5.800041614648356,
"grad_norm": 0.4609375,
"learning_rate": 0.0017679983354140659,
"loss": 1.3476,
"step": 223000
},
{
"epoch": 5.813046192259676,
"grad_norm": 0.419921875,
"learning_rate": 0.0017674781523096131,
"loss": 1.351,
"step": 223500
},
{
"epoch": 5.826050769870995,
"grad_norm": 0.408203125,
"learning_rate": 0.0017669579692051603,
"loss": 1.3493,
"step": 224000
},
{
"epoch": 5.839055347482314,
"grad_norm": 0.546875,
"learning_rate": 0.0017664377861007076,
"loss": 1.3475,
"step": 224500
},
{
"epoch": 5.8520599250936325,
"grad_norm": 0.423828125,
"learning_rate": 0.0017659176029962548,
"loss": 1.3501,
"step": 225000
},
{
"epoch": 5.865064502704952,
"grad_norm": 0.5078125,
"learning_rate": 0.0017653974198918018,
"loss": 1.3494,
"step": 225500
},
{
"epoch": 5.878069080316271,
"grad_norm": 0.43359375,
"learning_rate": 0.001764877236787349,
"loss": 1.3488,
"step": 226000
},
{
"epoch": 5.89107365792759,
"grad_norm": 0.443359375,
"learning_rate": 0.0017643570536828963,
"loss": 1.3511,
"step": 226500
},
{
"epoch": 5.904078235538909,
"grad_norm": 0.494140625,
"learning_rate": 0.0017638368705784435,
"loss": 1.3494,
"step": 227000
},
{
"epoch": 5.917082813150229,
"grad_norm": 0.46875,
"learning_rate": 0.001763316687473991,
"loss": 1.3492,
"step": 227500
},
{
"epoch": 5.930087390761548,
"grad_norm": 0.4140625,
"learning_rate": 0.0017627965043695382,
"loss": 1.3471,
"step": 228000
},
{
"epoch": 5.943091968372867,
"grad_norm": 0.408203125,
"learning_rate": 0.0017622763212650854,
"loss": 1.3481,
"step": 228500
},
{
"epoch": 5.956096545984186,
"grad_norm": 0.39453125,
"learning_rate": 0.0017617561381606326,
"loss": 1.3475,
"step": 229000
},
{
"epoch": 5.969101123595506,
"grad_norm": 0.412109375,
"learning_rate": 0.0017612359550561799,
"loss": 1.3471,
"step": 229500
},
{
"epoch": 5.982105701206825,
"grad_norm": 0.384765625,
"learning_rate": 0.001760715771951727,
"loss": 1.3469,
"step": 230000
},
{
"epoch": 5.995110278818144,
"grad_norm": 0.45703125,
"learning_rate": 0.0017601955888472743,
"loss": 1.3476,
"step": 230500
},
{
"epoch": 6.0,
"eval_loss": 1.3531179428100586,
"eval_runtime": 0.5767,
"eval_samples_per_second": 1734.115,
"eval_steps_per_second": 6.936,
"step": 230688
},
{
"epoch": 6.008114856429463,
"grad_norm": 0.388671875,
"learning_rate": 0.0017596754057428215,
"loss": 1.3445,
"step": 231000
},
{
"epoch": 6.0211194340407825,
"grad_norm": 0.4453125,
"learning_rate": 0.0017591552226383688,
"loss": 1.3454,
"step": 231500
},
{
"epoch": 6.034124011652102,
"grad_norm": 0.41796875,
"learning_rate": 0.001758635039533916,
"loss": 1.3453,
"step": 232000
},
{
"epoch": 6.047128589263421,
"grad_norm": 0.455078125,
"learning_rate": 0.001758114856429463,
"loss": 1.3443,
"step": 232500
},
{
"epoch": 6.06013316687474,
"grad_norm": 0.435546875,
"learning_rate": 0.0017575946733250102,
"loss": 1.3408,
"step": 233000
},
{
"epoch": 6.0731377444860595,
"grad_norm": 0.390625,
"learning_rate": 0.0017570744902205577,
"loss": 1.3445,
"step": 233500
},
{
"epoch": 6.086142322097379,
"grad_norm": 0.486328125,
"learning_rate": 0.001756554307116105,
"loss": 1.3459,
"step": 234000
},
{
"epoch": 6.099146899708697,
"grad_norm": 0.384765625,
"learning_rate": 0.0017560341240116521,
"loss": 1.3447,
"step": 234500
},
{
"epoch": 6.112151477320016,
"grad_norm": 0.55078125,
"learning_rate": 0.0017555139409071994,
"loss": 1.3434,
"step": 235000
},
{
"epoch": 6.1251560549313355,
"grad_norm": 0.36328125,
"learning_rate": 0.0017549937578027466,
"loss": 1.3462,
"step": 235500
},
{
"epoch": 6.138160632542655,
"grad_norm": 0.8046875,
"learning_rate": 0.0017544735746982938,
"loss": 1.345,
"step": 236000
},
{
"epoch": 6.151165210153974,
"grad_norm": 0.4375,
"learning_rate": 0.001753953391593841,
"loss": 1.3433,
"step": 236500
},
{
"epoch": 6.164169787765293,
"grad_norm": 0.431640625,
"learning_rate": 0.0017534332084893883,
"loss": 1.3421,
"step": 237000
},
{
"epoch": 6.1771743653766125,
"grad_norm": 0.421875,
"learning_rate": 0.0017529130253849355,
"loss": 1.3441,
"step": 237500
},
{
"epoch": 6.190178942987932,
"grad_norm": 0.42578125,
"learning_rate": 0.0017523928422804827,
"loss": 1.3456,
"step": 238000
},
{
"epoch": 6.203183520599251,
"grad_norm": 0.451171875,
"learning_rate": 0.00175187265917603,
"loss": 1.3457,
"step": 238500
},
{
"epoch": 6.21618809821057,
"grad_norm": 0.3671875,
"learning_rate": 0.0017513524760715774,
"loss": 1.3447,
"step": 239000
},
{
"epoch": 6.229192675821889,
"grad_norm": 0.3828125,
"learning_rate": 0.0017508322929671246,
"loss": 1.3445,
"step": 239500
},
{
"epoch": 6.242197253433209,
"grad_norm": 0.466796875,
"learning_rate": 0.0017503121098626717,
"loss": 1.3462,
"step": 240000
},
{
"epoch": 6.255201831044528,
"grad_norm": 0.3984375,
"learning_rate": 0.0017497919267582189,
"loss": 1.3478,
"step": 240500
},
{
"epoch": 6.268206408655847,
"grad_norm": 0.431640625,
"learning_rate": 0.0017492717436537661,
"loss": 1.3448,
"step": 241000
},
{
"epoch": 6.281210986267166,
"grad_norm": 0.474609375,
"learning_rate": 0.0017487515605493133,
"loss": 1.3425,
"step": 241500
},
{
"epoch": 6.294215563878486,
"grad_norm": 2.484375,
"learning_rate": 0.0017482313774448606,
"loss": 1.345,
"step": 242000
},
{
"epoch": 6.307220141489805,
"grad_norm": 0.6953125,
"learning_rate": 0.0017477111943404078,
"loss": 1.341,
"step": 242500
},
{
"epoch": 6.320224719101123,
"grad_norm": 0.384765625,
"learning_rate": 0.001747191011235955,
"loss": 1.3441,
"step": 243000
},
{
"epoch": 6.333229296712442,
"grad_norm": 0.431640625,
"learning_rate": 0.0017466708281315023,
"loss": 1.3427,
"step": 243500
},
{
"epoch": 6.346233874323762,
"grad_norm": 0.625,
"learning_rate": 0.0017461506450270495,
"loss": 1.3466,
"step": 244000
},
{
"epoch": 6.359238451935081,
"grad_norm": 0.4296875,
"learning_rate": 0.001745630461922597,
"loss": 1.3414,
"step": 244500
},
{
"epoch": 6.3722430295464,
"grad_norm": 0.40234375,
"learning_rate": 0.0017451102788181442,
"loss": 1.3433,
"step": 245000
},
{
"epoch": 6.385247607157719,
"grad_norm": 0.396484375,
"learning_rate": 0.0017445900957136914,
"loss": 1.3398,
"step": 245500
},
{
"epoch": 6.398252184769039,
"grad_norm": 0.44140625,
"learning_rate": 0.0017440699126092386,
"loss": 1.3425,
"step": 246000
},
{
"epoch": 6.411256762380358,
"grad_norm": 0.435546875,
"learning_rate": 0.0017435497295047858,
"loss": 1.3447,
"step": 246500
},
{
"epoch": 6.424261339991677,
"grad_norm": 0.5859375,
"learning_rate": 0.0017430295464003329,
"loss": 1.3427,
"step": 247000
},
{
"epoch": 6.437265917602996,
"grad_norm": 0.478515625,
"learning_rate": 0.00174250936329588,
"loss": 1.343,
"step": 247500
},
{
"epoch": 6.4502704952143155,
"grad_norm": 0.51953125,
"learning_rate": 0.0017419891801914273,
"loss": 1.3429,
"step": 248000
},
{
"epoch": 6.463275072825635,
"grad_norm": 0.408203125,
"learning_rate": 0.0017414689970869745,
"loss": 1.3439,
"step": 248500
},
{
"epoch": 6.476279650436954,
"grad_norm": 0.38671875,
"learning_rate": 0.0017409488139825218,
"loss": 1.3433,
"step": 249000
},
{
"epoch": 6.489284228048273,
"grad_norm": 0.400390625,
"learning_rate": 0.001740428630878069,
"loss": 1.344,
"step": 249500
},
{
"epoch": 6.502288805659592,
"grad_norm": 0.361328125,
"learning_rate": 0.0017399084477736164,
"loss": 1.3424,
"step": 250000
},
{
"epoch": 6.515293383270912,
"grad_norm": 0.5078125,
"learning_rate": 0.0017393882646691637,
"loss": 1.3416,
"step": 250500
},
{
"epoch": 6.528297960882231,
"grad_norm": 0.58203125,
"learning_rate": 0.001738868081564711,
"loss": 1.3417,
"step": 251000
},
{
"epoch": 6.54130253849355,
"grad_norm": 0.70703125,
"learning_rate": 0.0017383478984602581,
"loss": 1.3434,
"step": 251500
},
{
"epoch": 6.554307116104869,
"grad_norm": 0.61328125,
"learning_rate": 0.0017378277153558054,
"loss": 1.3395,
"step": 252000
},
{
"epoch": 6.567311693716188,
"grad_norm": 0.353515625,
"learning_rate": 0.0017373075322513526,
"loss": 1.3422,
"step": 252500
},
{
"epoch": 6.580316271327507,
"grad_norm": 1.5390625,
"learning_rate": 0.0017367873491468998,
"loss": 1.3405,
"step": 253000
},
{
"epoch": 6.593320848938826,
"grad_norm": 0.3984375,
"learning_rate": 0.001736267166042447,
"loss": 1.3418,
"step": 253500
},
{
"epoch": 6.606325426550145,
"grad_norm": 0.462890625,
"learning_rate": 0.001735746982937994,
"loss": 1.3412,
"step": 254000
},
{
"epoch": 6.619330004161465,
"grad_norm": 0.326171875,
"learning_rate": 0.0017352267998335413,
"loss": 1.3426,
"step": 254500
},
{
"epoch": 6.632334581772784,
"grad_norm": 0.51953125,
"learning_rate": 0.0017347066167290885,
"loss": 1.3434,
"step": 255000
},
{
"epoch": 6.645339159384103,
"grad_norm": 0.3671875,
"learning_rate": 0.001734186433624636,
"loss": 1.3441,
"step": 255500
},
{
"epoch": 6.658343736995422,
"grad_norm": 1.109375,
"learning_rate": 0.0017336662505201832,
"loss": 1.3421,
"step": 256000
},
{
"epoch": 6.671348314606742,
"grad_norm": 0.5859375,
"learning_rate": 0.0017331460674157304,
"loss": 1.3405,
"step": 256500
},
{
"epoch": 6.684352892218061,
"grad_norm": 0.388671875,
"learning_rate": 0.0017326258843112776,
"loss": 1.3409,
"step": 257000
},
{
"epoch": 6.69735746982938,
"grad_norm": 0.37109375,
"learning_rate": 0.0017321057012068249,
"loss": 1.3429,
"step": 257500
},
{
"epoch": 6.710362047440699,
"grad_norm": 0.357421875,
"learning_rate": 0.001731585518102372,
"loss": 1.3409,
"step": 258000
},
{
"epoch": 6.7233666250520185,
"grad_norm": 0.4453125,
"learning_rate": 0.0017310653349979193,
"loss": 1.3404,
"step": 258500
},
{
"epoch": 6.736371202663338,
"grad_norm": 0.65234375,
"learning_rate": 0.0017305451518934666,
"loss": 1.3406,
"step": 259000
},
{
"epoch": 6.749375780274657,
"grad_norm": 0.373046875,
"learning_rate": 0.0017300249687890138,
"loss": 1.341,
"step": 259500
},
{
"epoch": 6.762380357885976,
"grad_norm": 0.58203125,
"learning_rate": 0.001729504785684561,
"loss": 1.3382,
"step": 260000
},
{
"epoch": 6.775384935497295,
"grad_norm": 1.53125,
"learning_rate": 0.0017289846025801082,
"loss": 1.3411,
"step": 260500
},
{
"epoch": 6.788389513108614,
"grad_norm": 0.37109375,
"learning_rate": 0.0017284644194756553,
"loss": 1.3429,
"step": 261000
},
{
"epoch": 6.801394090719933,
"grad_norm": 0.44140625,
"learning_rate": 0.0017279442363712027,
"loss": 1.3427,
"step": 261500
},
{
"epoch": 6.814398668331252,
"grad_norm": 0.5390625,
"learning_rate": 0.00172742405326675,
"loss": 1.3411,
"step": 262000
},
{
"epoch": 6.8274032459425715,
"grad_norm": 0.54296875,
"learning_rate": 0.0017269038701622972,
"loss": 1.3397,
"step": 262500
},
{
"epoch": 6.840407823553891,
"grad_norm": 0.56640625,
"learning_rate": 0.0017263836870578444,
"loss": 1.3386,
"step": 263000
},
{
"epoch": 6.85341240116521,
"grad_norm": 0.369140625,
"learning_rate": 0.0017258635039533916,
"loss": 1.3392,
"step": 263500
},
{
"epoch": 6.866416978776529,
"grad_norm": 0.76953125,
"learning_rate": 0.0017253433208489388,
"loss": 1.3424,
"step": 264000
},
{
"epoch": 6.8794215563878485,
"grad_norm": 0.67578125,
"learning_rate": 0.001724823137744486,
"loss": 1.3418,
"step": 264500
},
{
"epoch": 6.892426133999168,
"grad_norm": 0.361328125,
"learning_rate": 0.0017243029546400333,
"loss": 1.3378,
"step": 265000
},
{
"epoch": 6.905430711610487,
"grad_norm": 0.423828125,
"learning_rate": 0.0017237827715355805,
"loss": 1.3398,
"step": 265500
},
{
"epoch": 6.918435289221806,
"grad_norm": 3.5625,
"learning_rate": 0.0017232625884311278,
"loss": 1.3411,
"step": 266000
},
{
"epoch": 6.931439866833125,
"grad_norm": 0.353515625,
"learning_rate": 0.001722742405326675,
"loss": 1.3377,
"step": 266500
},
{
"epoch": 6.944444444444445,
"grad_norm": 0.498046875,
"learning_rate": 0.0017222222222222224,
"loss": 1.339,
"step": 267000
},
{
"epoch": 6.957449022055764,
"grad_norm": 0.73046875,
"learning_rate": 0.0017217020391177697,
"loss": 1.3398,
"step": 267500
},
{
"epoch": 6.970453599667083,
"grad_norm": 0.42578125,
"learning_rate": 0.0017211818560133169,
"loss": 1.3397,
"step": 268000
},
{
"epoch": 6.983458177278402,
"grad_norm": 0.333984375,
"learning_rate": 0.001720661672908864,
"loss": 1.3382,
"step": 268500
},
{
"epoch": 6.996462754889722,
"grad_norm": 0.318359375,
"learning_rate": 0.0017201414898044111,
"loss": 1.3396,
"step": 269000
},
{
"epoch": 7.0,
"eval_loss": 1.3440358638763428,
"eval_runtime": 0.7691,
"eval_samples_per_second": 1300.178,
"eval_steps_per_second": 5.201,
"step": 269136
},
{
"epoch": 7.00946733250104,
"grad_norm": 0.357421875,
"learning_rate": 0.0017196213066999584,
"loss": 1.3346,
"step": 269500
},
{
"epoch": 7.022471910112359,
"grad_norm": 0.6015625,
"learning_rate": 0.0017191011235955056,
"loss": 1.3376,
"step": 270000
},
{
"epoch": 7.035476487723678,
"grad_norm": 0.5078125,
"learning_rate": 0.0017185809404910528,
"loss": 1.3362,
"step": 270500
},
{
"epoch": 7.048481065334998,
"grad_norm": 0.447265625,
"learning_rate": 0.0017180607573866,
"loss": 1.3358,
"step": 271000
},
{
"epoch": 7.061485642946317,
"grad_norm": 0.3984375,
"learning_rate": 0.0017175405742821473,
"loss": 1.3352,
"step": 271500
},
{
"epoch": 7.074490220557636,
"grad_norm": 0.419921875,
"learning_rate": 0.0017170203911776945,
"loss": 1.3363,
"step": 272000
},
{
"epoch": 7.087494798168955,
"grad_norm": 0.71484375,
"learning_rate": 0.001716500208073242,
"loss": 1.3376,
"step": 272500
},
{
"epoch": 7.100499375780275,
"grad_norm": 0.400390625,
"learning_rate": 0.0017159800249687892,
"loss": 1.3359,
"step": 273000
},
{
"epoch": 7.113503953391594,
"grad_norm": 0.98046875,
"learning_rate": 0.0017154598418643364,
"loss": 1.3391,
"step": 273500
},
{
"epoch": 7.126508531002913,
"grad_norm": 0.40234375,
"learning_rate": 0.0017149396587598836,
"loss": 1.336,
"step": 274000
},
{
"epoch": 7.139513108614232,
"grad_norm": 0.341796875,
"learning_rate": 0.0017144194756554309,
"loss": 1.3396,
"step": 274500
},
{
"epoch": 7.1525176862255515,
"grad_norm": 0.57421875,
"learning_rate": 0.001713899292550978,
"loss": 1.3355,
"step": 275000
},
{
"epoch": 7.165522263836871,
"grad_norm": 0.353515625,
"learning_rate": 0.001713379109446525,
"loss": 1.3334,
"step": 275500
},
{
"epoch": 7.17852684144819,
"grad_norm": 0.40234375,
"learning_rate": 0.0017128589263420723,
"loss": 1.3366,
"step": 276000
},
{
"epoch": 7.191531419059509,
"grad_norm": 0.388671875,
"learning_rate": 0.0017123387432376196,
"loss": 1.3369,
"step": 276500
},
{
"epoch": 7.2045359966708284,
"grad_norm": 0.4453125,
"learning_rate": 0.0017118185601331668,
"loss": 1.3365,
"step": 277000
},
{
"epoch": 7.217540574282148,
"grad_norm": 0.3828125,
"learning_rate": 0.001711298377028714,
"loss": 1.3345,
"step": 277500
},
{
"epoch": 7.230545151893467,
"grad_norm": 0.404296875,
"learning_rate": 0.0017107781939242615,
"loss": 1.3364,
"step": 278000
},
{
"epoch": 7.243549729504785,
"grad_norm": 0.39453125,
"learning_rate": 0.0017102580108198087,
"loss": 1.3346,
"step": 278500
},
{
"epoch": 7.2565543071161045,
"grad_norm": 0.42578125,
"learning_rate": 0.001709737827715356,
"loss": 1.3363,
"step": 279000
},
{
"epoch": 7.269558884727424,
"grad_norm": 0.54296875,
"learning_rate": 0.0017092176446109031,
"loss": 1.3375,
"step": 279500
},
{
"epoch": 7.282563462338743,
"grad_norm": 0.423828125,
"learning_rate": 0.0017086974615064504,
"loss": 1.3349,
"step": 280000
},
{
"epoch": 7.295568039950062,
"grad_norm": 0.41796875,
"learning_rate": 0.0017081772784019976,
"loss": 1.3359,
"step": 280500
},
{
"epoch": 7.308572617561381,
"grad_norm": 0.37109375,
"learning_rate": 0.0017076570952975448,
"loss": 1.3331,
"step": 281000
},
{
"epoch": 7.321577195172701,
"grad_norm": 0.396484375,
"learning_rate": 0.001707136912193092,
"loss": 1.3355,
"step": 281500
},
{
"epoch": 7.33458177278402,
"grad_norm": 0.494140625,
"learning_rate": 0.0017066167290886393,
"loss": 1.3356,
"step": 282000
},
{
"epoch": 7.347586350395339,
"grad_norm": 0.474609375,
"learning_rate": 0.0017060965459841863,
"loss": 1.3329,
"step": 282500
},
{
"epoch": 7.360590928006658,
"grad_norm": 0.4140625,
"learning_rate": 0.0017055763628797335,
"loss": 1.3345,
"step": 283000
},
{
"epoch": 7.373595505617978,
"grad_norm": 0.35546875,
"learning_rate": 0.0017050561797752807,
"loss": 1.3375,
"step": 283500
},
{
"epoch": 7.386600083229297,
"grad_norm": 0.47265625,
"learning_rate": 0.0017045359966708282,
"loss": 1.337,
"step": 284000
},
{
"epoch": 7.399604660840616,
"grad_norm": 0.37109375,
"learning_rate": 0.0017040158135663754,
"loss": 1.3329,
"step": 284500
},
{
"epoch": 7.412609238451935,
"grad_norm": 0.4375,
"learning_rate": 0.0017034956304619227,
"loss": 1.3368,
"step": 285000
},
{
"epoch": 7.4256138160632545,
"grad_norm": 0.419921875,
"learning_rate": 0.0017029754473574699,
"loss": 1.3342,
"step": 285500
},
{
"epoch": 7.438618393674574,
"grad_norm": 0.4921875,
"learning_rate": 0.001702455264253017,
"loss": 1.3355,
"step": 286000
},
{
"epoch": 7.451622971285893,
"grad_norm": 0.373046875,
"learning_rate": 0.0017019350811485643,
"loss": 1.3323,
"step": 286500
},
{
"epoch": 7.464627548897212,
"grad_norm": 0.380859375,
"learning_rate": 0.0017014148980441116,
"loss": 1.3366,
"step": 287000
},
{
"epoch": 7.477632126508531,
"grad_norm": 0.9453125,
"learning_rate": 0.0017008947149396588,
"loss": 1.3364,
"step": 287500
},
{
"epoch": 7.49063670411985,
"grad_norm": 0.390625,
"learning_rate": 0.001700374531835206,
"loss": 1.334,
"step": 288000
},
{
"epoch": 7.503641281731169,
"grad_norm": 0.5625,
"learning_rate": 0.0016998543487307533,
"loss": 1.3348,
"step": 288500
},
{
"epoch": 7.516645859342488,
"grad_norm": 1.0859375,
"learning_rate": 0.0016993341656263005,
"loss": 1.3378,
"step": 289000
},
{
"epoch": 7.5296504369538075,
"grad_norm": 0.6015625,
"learning_rate": 0.001698813982521848,
"loss": 1.3348,
"step": 289500
},
{
"epoch": 7.542655014565127,
"grad_norm": 0.5078125,
"learning_rate": 0.001698293799417395,
"loss": 1.3327,
"step": 290000
},
{
"epoch": 7.555659592176446,
"grad_norm": 0.4375,
"learning_rate": 0.0016977736163129422,
"loss": 1.3348,
"step": 290500
},
{
"epoch": 7.568664169787765,
"grad_norm": 0.416015625,
"learning_rate": 0.0016972534332084894,
"loss": 1.3347,
"step": 291000
},
{
"epoch": 7.5816687473990845,
"grad_norm": 0.44921875,
"learning_rate": 0.0016967332501040366,
"loss": 1.3345,
"step": 291500
},
{
"epoch": 7.594673325010404,
"grad_norm": 0.3984375,
"learning_rate": 0.0016962130669995838,
"loss": 1.335,
"step": 292000
},
{
"epoch": 7.607677902621723,
"grad_norm": 0.51953125,
"learning_rate": 0.001695692883895131,
"loss": 1.3339,
"step": 292500
},
{
"epoch": 7.620682480233042,
"grad_norm": 0.4609375,
"learning_rate": 0.0016951727007906783,
"loss": 1.3355,
"step": 293000
},
{
"epoch": 7.633687057844361,
"grad_norm": 0.419921875,
"learning_rate": 0.0016946525176862255,
"loss": 1.334,
"step": 293500
},
{
"epoch": 7.646691635455681,
"grad_norm": 0.416015625,
"learning_rate": 0.0016941323345817728,
"loss": 1.332,
"step": 294000
},
{
"epoch": 7.659696213067,
"grad_norm": 0.44921875,
"learning_rate": 0.00169361215147732,
"loss": 1.3332,
"step": 294500
},
{
"epoch": 7.672700790678319,
"grad_norm": 0.51953125,
"learning_rate": 0.0016930919683728674,
"loss": 1.3336,
"step": 295000
},
{
"epoch": 7.6857053682896375,
"grad_norm": 0.53515625,
"learning_rate": 0.0016925717852684147,
"loss": 1.3318,
"step": 295500
},
{
"epoch": 7.698709945900957,
"grad_norm": 0.419921875,
"learning_rate": 0.001692051602163962,
"loss": 1.3365,
"step": 296000
},
{
"epoch": 7.711714523512276,
"grad_norm": 0.54296875,
"learning_rate": 0.0016915314190595091,
"loss": 1.3334,
"step": 296500
},
{
"epoch": 7.724719101123595,
"grad_norm": 0.34375,
"learning_rate": 0.0016910112359550561,
"loss": 1.3345,
"step": 297000
},
{
"epoch": 7.737723678734914,
"grad_norm": 0.7265625,
"learning_rate": 0.0016904910528506034,
"loss": 1.3349,
"step": 297500
},
{
"epoch": 7.750728256346234,
"grad_norm": 0.423828125,
"learning_rate": 0.0016899708697461506,
"loss": 1.334,
"step": 298000
},
{
"epoch": 7.763732833957553,
"grad_norm": 0.34765625,
"learning_rate": 0.0016894506866416978,
"loss": 1.3321,
"step": 298500
},
{
"epoch": 7.776737411568872,
"grad_norm": 0.458984375,
"learning_rate": 0.001688930503537245,
"loss": 1.333,
"step": 299000
},
{
"epoch": 7.789741989180191,
"grad_norm": 0.341796875,
"learning_rate": 0.0016884103204327923,
"loss": 1.3331,
"step": 299500
},
{
"epoch": 7.802746566791511,
"grad_norm": 0.439453125,
"learning_rate": 0.0016878901373283395,
"loss": 1.3346,
"step": 300000
},
{
"epoch": 7.81575114440283,
"grad_norm": 0.5546875,
"learning_rate": 0.001687369954223887,
"loss": 1.3325,
"step": 300500
},
{
"epoch": 7.828755722014149,
"grad_norm": 0.76171875,
"learning_rate": 0.0016868497711194342,
"loss": 1.3314,
"step": 301000
},
{
"epoch": 7.841760299625468,
"grad_norm": 0.349609375,
"learning_rate": 0.0016863295880149814,
"loss": 1.3336,
"step": 301500
},
{
"epoch": 7.8547648772367875,
"grad_norm": 0.431640625,
"learning_rate": 0.0016858094049105286,
"loss": 1.3378,
"step": 302000
},
{
"epoch": 7.867769454848107,
"grad_norm": 0.458984375,
"learning_rate": 0.0016852892218060759,
"loss": 1.33,
"step": 302500
},
{
"epoch": 7.880774032459426,
"grad_norm": 0.421875,
"learning_rate": 0.001684769038701623,
"loss": 1.3354,
"step": 303000
},
{
"epoch": 7.893778610070745,
"grad_norm": 0.46484375,
"learning_rate": 0.0016842488555971703,
"loss": 1.3348,
"step": 303500
},
{
"epoch": 7.9067831876820645,
"grad_norm": 0.380859375,
"learning_rate": 0.0016837286724927173,
"loss": 1.3333,
"step": 304000
},
{
"epoch": 7.919787765293384,
"grad_norm": 0.640625,
"learning_rate": 0.0016832084893882646,
"loss": 1.3345,
"step": 304500
},
{
"epoch": 7.932792342904703,
"grad_norm": 0.466796875,
"learning_rate": 0.0016826883062838118,
"loss": 1.333,
"step": 305000
},
{
"epoch": 7.945796920516021,
"grad_norm": 0.462890625,
"learning_rate": 0.001682168123179359,
"loss": 1.3348,
"step": 305500
},
{
"epoch": 7.9588014981273405,
"grad_norm": 0.37890625,
"learning_rate": 0.0016816479400749065,
"loss": 1.3343,
"step": 306000
},
{
"epoch": 7.97180607573866,
"grad_norm": 0.45703125,
"learning_rate": 0.0016811277569704537,
"loss": 1.3348,
"step": 306500
},
{
"epoch": 7.984810653349979,
"grad_norm": 1.0546875,
"learning_rate": 0.001680607573866001,
"loss": 1.3361,
"step": 307000
},
{
"epoch": 7.997815230961298,
"grad_norm": 0.431640625,
"learning_rate": 0.0016800873907615481,
"loss": 1.335,
"step": 307500
},
{
"epoch": 8.0,
"eval_loss": 1.3374426364898682,
"eval_runtime": 0.814,
"eval_samples_per_second": 1228.431,
"eval_steps_per_second": 4.914,
"step": 307584
},
{
"epoch": 8.010819808572618,
"grad_norm": 0.443359375,
"learning_rate": 0.0016795672076570954,
"loss": 1.3305,
"step": 308000
},
{
"epoch": 8.023824386183938,
"grad_norm": 0.50390625,
"learning_rate": 0.0016790470245526426,
"loss": 1.3302,
"step": 308500
},
{
"epoch": 8.036828963795257,
"grad_norm": 0.361328125,
"learning_rate": 0.0016785268414481898,
"loss": 1.3295,
"step": 309000
},
{
"epoch": 8.049833541406574,
"grad_norm": 0.63671875,
"learning_rate": 0.001678006658343737,
"loss": 1.331,
"step": 309500
},
{
"epoch": 8.062838119017893,
"grad_norm": 0.3203125,
"learning_rate": 0.0016774864752392843,
"loss": 1.3299,
"step": 310000
},
{
"epoch": 8.075842696629213,
"grad_norm": 0.72265625,
"learning_rate": 0.0016769662921348315,
"loss": 1.3321,
"step": 310500
},
{
"epoch": 8.088847274240532,
"grad_norm": 0.380859375,
"learning_rate": 0.0016764461090303787,
"loss": 1.3289,
"step": 311000
},
{
"epoch": 8.101851851851851,
"grad_norm": 1.7734375,
"learning_rate": 0.0016759259259259258,
"loss": 1.3318,
"step": 311500
},
{
"epoch": 8.11485642946317,
"grad_norm": 0.5234375,
"learning_rate": 0.0016754057428214732,
"loss": 1.3326,
"step": 312000
},
{
"epoch": 8.12786100707449,
"grad_norm": 0.4765625,
"learning_rate": 0.0016748855597170204,
"loss": 1.3277,
"step": 312500
},
{
"epoch": 8.140865584685809,
"grad_norm": 0.408203125,
"learning_rate": 0.0016743653766125677,
"loss": 1.3313,
"step": 313000
},
{
"epoch": 8.153870162297128,
"grad_norm": 1.1015625,
"learning_rate": 0.0016738451935081149,
"loss": 1.331,
"step": 313500
},
{
"epoch": 8.166874739908447,
"grad_norm": 0.349609375,
"learning_rate": 0.0016733250104036621,
"loss": 1.3296,
"step": 314000
},
{
"epoch": 8.179879317519767,
"grad_norm": 0.546875,
"learning_rate": 0.0016728048272992093,
"loss": 1.3291,
"step": 314500
},
{
"epoch": 8.192883895131086,
"grad_norm": 0.40234375,
"learning_rate": 0.0016722846441947566,
"loss": 1.3307,
"step": 315000
},
{
"epoch": 8.205888472742405,
"grad_norm": 0.546875,
"learning_rate": 0.0016717644610903038,
"loss": 1.3317,
"step": 315500
},
{
"epoch": 8.218893050353724,
"grad_norm": 0.396484375,
"learning_rate": 0.001671244277985851,
"loss": 1.3343,
"step": 316000
},
{
"epoch": 8.231897627965044,
"grad_norm": 0.53125,
"learning_rate": 0.0016707240948813983,
"loss": 1.3311,
"step": 316500
},
{
"epoch": 8.244902205576363,
"grad_norm": 0.423828125,
"learning_rate": 0.0016702039117769455,
"loss": 1.3301,
"step": 317000
},
{
"epoch": 8.257906783187682,
"grad_norm": 0.443359375,
"learning_rate": 0.001669683728672493,
"loss": 1.3313,
"step": 317500
},
{
"epoch": 8.270911360799001,
"grad_norm": 0.47265625,
"learning_rate": 0.0016691635455680402,
"loss": 1.3322,
"step": 318000
},
{
"epoch": 8.28391593841032,
"grad_norm": 0.400390625,
"learning_rate": 0.0016686433624635872,
"loss": 1.3309,
"step": 318500
},
{
"epoch": 8.29692051602164,
"grad_norm": 0.53515625,
"learning_rate": 0.0016681231793591344,
"loss": 1.3299,
"step": 319000
},
{
"epoch": 8.309925093632959,
"grad_norm": 0.5546875,
"learning_rate": 0.0016676029962546816,
"loss": 1.3295,
"step": 319500
},
{
"epoch": 8.322929671244278,
"grad_norm": 0.404296875,
"learning_rate": 0.0016670828131502289,
"loss": 1.3312,
"step": 320000
},
{
"epoch": 8.335934248855597,
"grad_norm": 0.357421875,
"learning_rate": 0.001666562630045776,
"loss": 1.329,
"step": 320500
},
{
"epoch": 8.348938826466917,
"grad_norm": 0.408203125,
"learning_rate": 0.0016660424469413233,
"loss": 1.3312,
"step": 321000
},
{
"epoch": 8.361943404078236,
"grad_norm": 0.52734375,
"learning_rate": 0.0016655222638368705,
"loss": 1.3298,
"step": 321500
},
{
"epoch": 8.374947981689555,
"grad_norm": 0.3828125,
"learning_rate": 0.0016650020807324178,
"loss": 1.3282,
"step": 322000
},
{
"epoch": 8.387952559300874,
"grad_norm": 0.578125,
"learning_rate": 0.001664481897627965,
"loss": 1.3293,
"step": 322500
},
{
"epoch": 8.400957136912194,
"grad_norm": 0.427734375,
"learning_rate": 0.0016639617145235124,
"loss": 1.333,
"step": 323000
},
{
"epoch": 8.413961714523513,
"grad_norm": 0.4765625,
"learning_rate": 0.0016634415314190597,
"loss": 1.3282,
"step": 323500
},
{
"epoch": 8.426966292134832,
"grad_norm": 0.671875,
"learning_rate": 0.001662921348314607,
"loss": 1.3279,
"step": 324000
},
{
"epoch": 8.439970869746151,
"grad_norm": 0.38671875,
"learning_rate": 0.0016624011652101541,
"loss": 1.3314,
"step": 324500
},
{
"epoch": 8.45297544735747,
"grad_norm": 0.5234375,
"learning_rate": 0.0016618809821057014,
"loss": 1.33,
"step": 325000
},
{
"epoch": 8.46598002496879,
"grad_norm": 0.470703125,
"learning_rate": 0.0016613607990012484,
"loss": 1.3287,
"step": 325500
},
{
"epoch": 8.478984602580109,
"grad_norm": 0.4296875,
"learning_rate": 0.0016608406158967956,
"loss": 1.331,
"step": 326000
},
{
"epoch": 8.491989180191428,
"grad_norm": 0.6484375,
"learning_rate": 0.0016603204327923428,
"loss": 1.3306,
"step": 326500
},
{
"epoch": 8.504993757802747,
"grad_norm": 0.43359375,
"learning_rate": 0.00165980024968789,
"loss": 1.3311,
"step": 327000
},
{
"epoch": 8.517998335414065,
"grad_norm": 0.5234375,
"learning_rate": 0.0016592800665834373,
"loss": 1.3315,
"step": 327500
},
{
"epoch": 8.531002913025384,
"grad_norm": 0.466796875,
"learning_rate": 0.0016587598834789845,
"loss": 1.3307,
"step": 328000
},
{
"epoch": 8.544007490636703,
"grad_norm": 0.76953125,
"learning_rate": 0.001658239700374532,
"loss": 1.3323,
"step": 328500
},
{
"epoch": 8.557012068248023,
"grad_norm": 0.412109375,
"learning_rate": 0.0016577195172700792,
"loss": 1.3308,
"step": 329000
},
{
"epoch": 8.570016645859342,
"grad_norm": 0.7421875,
"learning_rate": 0.0016571993341656264,
"loss": 1.3297,
"step": 329500
},
{
"epoch": 8.583021223470661,
"grad_norm": 0.462890625,
"learning_rate": 0.0016566791510611736,
"loss": 1.3301,
"step": 330000
},
{
"epoch": 8.59602580108198,
"grad_norm": 0.458984375,
"learning_rate": 0.0016561589679567209,
"loss": 1.3297,
"step": 330500
},
{
"epoch": 8.6090303786933,
"grad_norm": 0.361328125,
"learning_rate": 0.001655638784852268,
"loss": 1.3292,
"step": 331000
},
{
"epoch": 8.622034956304619,
"grad_norm": 0.322265625,
"learning_rate": 0.0016551186017478153,
"loss": 1.3295,
"step": 331500
},
{
"epoch": 8.635039533915938,
"grad_norm": 0.451171875,
"learning_rate": 0.0016545984186433626,
"loss": 1.3291,
"step": 332000
},
{
"epoch": 8.648044111527257,
"grad_norm": 0.396484375,
"learning_rate": 0.0016540782355389098,
"loss": 1.3296,
"step": 332500
},
{
"epoch": 8.661048689138577,
"grad_norm": 0.72265625,
"learning_rate": 0.0016535580524344568,
"loss": 1.3273,
"step": 333000
},
{
"epoch": 8.674053266749896,
"grad_norm": 0.546875,
"learning_rate": 0.001653037869330004,
"loss": 1.3299,
"step": 333500
},
{
"epoch": 8.687057844361215,
"grad_norm": 0.416015625,
"learning_rate": 0.0016525176862255513,
"loss": 1.3287,
"step": 334000
},
{
"epoch": 8.700062421972534,
"grad_norm": 0.462890625,
"learning_rate": 0.0016519975031210987,
"loss": 1.3295,
"step": 334500
},
{
"epoch": 8.713066999583853,
"grad_norm": 0.35546875,
"learning_rate": 0.001651477320016646,
"loss": 1.3264,
"step": 335000
},
{
"epoch": 8.726071577195173,
"grad_norm": 0.44140625,
"learning_rate": 0.0016509571369121932,
"loss": 1.3281,
"step": 335500
},
{
"epoch": 8.739076154806492,
"grad_norm": 0.5,
"learning_rate": 0.0016504369538077404,
"loss": 1.3295,
"step": 336000
},
{
"epoch": 8.752080732417811,
"grad_norm": 0.7890625,
"learning_rate": 0.0016499167707032876,
"loss": 1.3286,
"step": 336500
},
{
"epoch": 8.76508531002913,
"grad_norm": 0.6640625,
"learning_rate": 0.0016493965875988348,
"loss": 1.327,
"step": 337000
},
{
"epoch": 8.77808988764045,
"grad_norm": 0.466796875,
"learning_rate": 0.001648876404494382,
"loss": 1.3269,
"step": 337500
},
{
"epoch": 8.791094465251769,
"grad_norm": 0.36328125,
"learning_rate": 0.0016483562213899293,
"loss": 1.3287,
"step": 338000
},
{
"epoch": 8.804099042863088,
"grad_norm": 0.37890625,
"learning_rate": 0.0016478360382854765,
"loss": 1.3279,
"step": 338500
},
{
"epoch": 8.817103620474407,
"grad_norm": 0.400390625,
"learning_rate": 0.0016473158551810238,
"loss": 1.3304,
"step": 339000
},
{
"epoch": 8.830108198085727,
"grad_norm": 0.412109375,
"learning_rate": 0.001646795672076571,
"loss": 1.3286,
"step": 339500
},
{
"epoch": 8.843112775697046,
"grad_norm": 1.9296875,
"learning_rate": 0.0016462754889721182,
"loss": 1.3299,
"step": 340000
},
{
"epoch": 8.856117353308365,
"grad_norm": 0.640625,
"learning_rate": 0.0016457553058676654,
"loss": 1.3283,
"step": 340500
},
{
"epoch": 8.869121930919684,
"grad_norm": 0.53125,
"learning_rate": 0.0016452351227632127,
"loss": 1.3289,
"step": 341000
},
{
"epoch": 8.882126508531003,
"grad_norm": 0.427734375,
"learning_rate": 0.00164471493965876,
"loss": 1.3299,
"step": 341500
},
{
"epoch": 8.895131086142323,
"grad_norm": 0.408203125,
"learning_rate": 0.0016441947565543071,
"loss": 1.3291,
"step": 342000
},
{
"epoch": 8.908135663753642,
"grad_norm": 0.96875,
"learning_rate": 0.0016436745734498544,
"loss": 1.3321,
"step": 342500
},
{
"epoch": 8.921140241364961,
"grad_norm": 0.44921875,
"learning_rate": 0.0016431543903454016,
"loss": 1.3266,
"step": 343000
},
{
"epoch": 8.93414481897628,
"grad_norm": 0.40625,
"learning_rate": 0.0016426342072409488,
"loss": 1.3289,
"step": 343500
},
{
"epoch": 8.947149396587598,
"grad_norm": 0.39453125,
"learning_rate": 0.001642114024136496,
"loss": 1.3273,
"step": 344000
},
{
"epoch": 8.960153974198917,
"grad_norm": 0.61328125,
"learning_rate": 0.0016415938410320433,
"loss": 1.3283,
"step": 344500
},
{
"epoch": 8.973158551810236,
"grad_norm": 1.5859375,
"learning_rate": 0.0016410736579275905,
"loss": 1.3267,
"step": 345000
},
{
"epoch": 8.986163129421556,
"grad_norm": 0.3515625,
"learning_rate": 0.001640553474823138,
"loss": 1.3272,
"step": 345500
},
{
"epoch": 8.999167707032875,
"grad_norm": 0.369140625,
"learning_rate": 0.0016400332917186852,
"loss": 1.3262,
"step": 346000
},
{
"epoch": 9.0,
"eval_loss": 1.3324060440063477,
"eval_runtime": 0.7089,
"eval_samples_per_second": 1410.561,
"eval_steps_per_second": 5.642,
"step": 346032
},
{
"epoch": 9.012172284644194,
"grad_norm": 0.462890625,
"learning_rate": 0.0016395131086142324,
"loss": 1.3265,
"step": 346500
},
{
"epoch": 9.025176862255513,
"grad_norm": 0.46875,
"learning_rate": 0.0016389929255097794,
"loss": 1.3243,
"step": 347000
},
{
"epoch": 9.038181439866833,
"grad_norm": 0.50390625,
"learning_rate": 0.0016384727424053266,
"loss": 1.3273,
"step": 347500
},
{
"epoch": 9.051186017478152,
"grad_norm": 0.85546875,
"learning_rate": 0.0016379525593008739,
"loss": 1.3269,
"step": 348000
},
{
"epoch": 9.064190595089471,
"grad_norm": 0.59765625,
"learning_rate": 0.001637432376196421,
"loss": 1.3264,
"step": 348500
},
{
"epoch": 9.07719517270079,
"grad_norm": 0.50390625,
"learning_rate": 0.0016369121930919683,
"loss": 1.3274,
"step": 349000
},
{
"epoch": 9.09019975031211,
"grad_norm": 0.458984375,
"learning_rate": 0.0016363920099875156,
"loss": 1.3251,
"step": 349500
},
{
"epoch": 9.103204327923429,
"grad_norm": 0.48828125,
"learning_rate": 0.0016358718268830628,
"loss": 1.3239,
"step": 350000
},
{
"epoch": 9.116208905534748,
"grad_norm": 0.416015625,
"learning_rate": 0.00163535164377861,
"loss": 1.3263,
"step": 350500
},
{
"epoch": 9.129213483146067,
"grad_norm": 0.3828125,
"learning_rate": 0.0016348314606741575,
"loss": 1.3257,
"step": 351000
},
{
"epoch": 9.142218060757386,
"grad_norm": 0.46484375,
"learning_rate": 0.0016343112775697047,
"loss": 1.327,
"step": 351500
},
{
"epoch": 9.155222638368706,
"grad_norm": 0.376953125,
"learning_rate": 0.001633791094465252,
"loss": 1.3262,
"step": 352000
},
{
"epoch": 9.168227215980025,
"grad_norm": 0.423828125,
"learning_rate": 0.0016332709113607991,
"loss": 1.327,
"step": 352500
},
{
"epoch": 9.181231793591344,
"grad_norm": 0.4765625,
"learning_rate": 0.0016327507282563464,
"loss": 1.3247,
"step": 353000
},
{
"epoch": 9.194236371202663,
"grad_norm": 0.51171875,
"learning_rate": 0.0016322305451518936,
"loss": 1.3278,
"step": 353500
},
{
"epoch": 9.207240948813983,
"grad_norm": 0.38671875,
"learning_rate": 0.0016317103620474408,
"loss": 1.3253,
"step": 354000
},
{
"epoch": 9.220245526425302,
"grad_norm": 0.375,
"learning_rate": 0.0016311901789429878,
"loss": 1.3275,
"step": 354500
},
{
"epoch": 9.233250104036621,
"grad_norm": 0.447265625,
"learning_rate": 0.001630669995838535,
"loss": 1.328,
"step": 355000
},
{
"epoch": 9.24625468164794,
"grad_norm": 0.427734375,
"learning_rate": 0.0016301498127340823,
"loss": 1.3296,
"step": 355500
},
{
"epoch": 9.25925925925926,
"grad_norm": 0.35546875,
"learning_rate": 0.0016296296296296295,
"loss": 1.3279,
"step": 356000
},
{
"epoch": 9.272263836870579,
"grad_norm": 0.470703125,
"learning_rate": 0.0016291094465251768,
"loss": 1.3281,
"step": 356500
},
{
"epoch": 9.285268414481898,
"grad_norm": 0.3828125,
"learning_rate": 0.0016285892634207242,
"loss": 1.3286,
"step": 357000
},
{
"epoch": 9.298272992093217,
"grad_norm": 0.38671875,
"learning_rate": 0.0016280690803162714,
"loss": 1.325,
"step": 357500
},
{
"epoch": 9.311277569704536,
"grad_norm": 0.392578125,
"learning_rate": 0.0016275488972118187,
"loss": 1.3296,
"step": 358000
},
{
"epoch": 9.324282147315856,
"grad_norm": 0.466796875,
"learning_rate": 0.0016270287141073659,
"loss": 1.3267,
"step": 358500
},
{
"epoch": 9.337286724927175,
"grad_norm": 0.4375,
"learning_rate": 0.0016265085310029131,
"loss": 1.3264,
"step": 359000
},
{
"epoch": 9.350291302538494,
"grad_norm": 0.625,
"learning_rate": 0.0016259883478984603,
"loss": 1.3284,
"step": 359500
},
{
"epoch": 9.363295880149813,
"grad_norm": 0.47265625,
"learning_rate": 0.0016254681647940076,
"loss": 1.3278,
"step": 360000
},
{
"epoch": 9.376300457761133,
"grad_norm": 0.48828125,
"learning_rate": 0.0016249479816895548,
"loss": 1.3286,
"step": 360500
},
{
"epoch": 9.389305035372452,
"grad_norm": 0.37890625,
"learning_rate": 0.001624427798585102,
"loss": 1.3271,
"step": 361000
},
{
"epoch": 9.402309612983771,
"grad_norm": 0.484375,
"learning_rate": 0.001623907615480649,
"loss": 1.3302,
"step": 361500
},
{
"epoch": 9.41531419059509,
"grad_norm": 0.640625,
"learning_rate": 0.0016233874323761963,
"loss": 1.328,
"step": 362000
},
{
"epoch": 9.428318768206408,
"grad_norm": 1.5546875,
"learning_rate": 0.0016228672492717437,
"loss": 1.329,
"step": 362500
},
{
"epoch": 9.441323345817727,
"grad_norm": 1.0390625,
"learning_rate": 0.001622347066167291,
"loss": 1.3263,
"step": 363000
},
{
"epoch": 9.454327923429046,
"grad_norm": 0.54296875,
"learning_rate": 0.0016218268830628382,
"loss": 1.3274,
"step": 363500
},
{
"epoch": 9.467332501040365,
"grad_norm": 2.40625,
"learning_rate": 0.0016213066999583854,
"loss": 1.3277,
"step": 364000
},
{
"epoch": 9.480337078651685,
"grad_norm": 0.412109375,
"learning_rate": 0.0016207865168539326,
"loss": 1.3267,
"step": 364500
},
{
"epoch": 9.493341656263004,
"grad_norm": 0.59375,
"learning_rate": 0.0016202663337494799,
"loss": 1.328,
"step": 365000
},
{
"epoch": 9.506346233874323,
"grad_norm": 0.390625,
"learning_rate": 0.001619746150645027,
"loss": 1.325,
"step": 365500
},
{
"epoch": 9.519350811485642,
"grad_norm": 0.357421875,
"learning_rate": 0.0016192259675405743,
"loss": 1.3243,
"step": 366000
},
{
"epoch": 9.532355389096962,
"grad_norm": 0.51171875,
"learning_rate": 0.0016187057844361215,
"loss": 1.3275,
"step": 366500
},
{
"epoch": 9.545359966708281,
"grad_norm": 0.40234375,
"learning_rate": 0.0016181856013316688,
"loss": 1.327,
"step": 367000
},
{
"epoch": 9.5583645443196,
"grad_norm": 0.99609375,
"learning_rate": 0.001617665418227216,
"loss": 1.3273,
"step": 367500
},
{
"epoch": 9.57136912193092,
"grad_norm": 0.4453125,
"learning_rate": 0.0016171452351227634,
"loss": 1.3253,
"step": 368000
},
{
"epoch": 9.584373699542239,
"grad_norm": 0.498046875,
"learning_rate": 0.0016166250520183105,
"loss": 1.3245,
"step": 368500
},
{
"epoch": 9.597378277153558,
"grad_norm": 0.5625,
"learning_rate": 0.0016161048689138577,
"loss": 1.3262,
"step": 369000
},
{
"epoch": 9.610382854764877,
"grad_norm": 0.9140625,
"learning_rate": 0.001615584685809405,
"loss": 1.3269,
"step": 369500
},
{
"epoch": 9.623387432376196,
"grad_norm": 0.578125,
"learning_rate": 0.0016150645027049521,
"loss": 1.3265,
"step": 370000
},
{
"epoch": 9.636392009987516,
"grad_norm": 0.5390625,
"learning_rate": 0.0016145443196004994,
"loss": 1.3274,
"step": 370500
},
{
"epoch": 9.649396587598835,
"grad_norm": 0.53125,
"learning_rate": 0.0016140241364960466,
"loss": 1.3255,
"step": 371000
},
{
"epoch": 9.662401165210154,
"grad_norm": 0.6171875,
"learning_rate": 0.0016135039533915938,
"loss": 1.3281,
"step": 371500
},
{
"epoch": 9.675405742821473,
"grad_norm": 0.4765625,
"learning_rate": 0.001612983770287141,
"loss": 1.3255,
"step": 372000
},
{
"epoch": 9.688410320432792,
"grad_norm": 0.96484375,
"learning_rate": 0.0016124635871826883,
"loss": 1.3243,
"step": 372500
},
{
"epoch": 9.701414898044112,
"grad_norm": 0.369140625,
"learning_rate": 0.0016119434040782355,
"loss": 1.3219,
"step": 373000
},
{
"epoch": 9.714419475655431,
"grad_norm": 0.453125,
"learning_rate": 0.001611423220973783,
"loss": 1.3245,
"step": 373500
},
{
"epoch": 9.72742405326675,
"grad_norm": 0.78515625,
"learning_rate": 0.0016109030378693302,
"loss": 1.3235,
"step": 374000
},
{
"epoch": 9.74042863087807,
"grad_norm": 0.359375,
"learning_rate": 0.0016103828547648774,
"loss": 1.3249,
"step": 374500
},
{
"epoch": 9.753433208489389,
"grad_norm": 0.384765625,
"learning_rate": 0.0016098626716604246,
"loss": 1.3235,
"step": 375000
},
{
"epoch": 9.766437786100708,
"grad_norm": 1.078125,
"learning_rate": 0.0016093424885559717,
"loss": 1.3246,
"step": 375500
},
{
"epoch": 9.779442363712027,
"grad_norm": 0.396484375,
"learning_rate": 0.0016088223054515189,
"loss": 1.3261,
"step": 376000
},
{
"epoch": 9.792446941323346,
"grad_norm": 0.3515625,
"learning_rate": 0.0016083021223470661,
"loss": 1.3246,
"step": 376500
},
{
"epoch": 9.805451518934666,
"grad_norm": 0.69140625,
"learning_rate": 0.0016077819392426133,
"loss": 1.3242,
"step": 377000
},
{
"epoch": 9.818456096545985,
"grad_norm": 0.40234375,
"learning_rate": 0.0016072617561381606,
"loss": 1.3268,
"step": 377500
},
{
"epoch": 9.831460674157304,
"grad_norm": 0.36328125,
"learning_rate": 0.0016067415730337078,
"loss": 1.327,
"step": 378000
},
{
"epoch": 9.844465251768623,
"grad_norm": 0.369140625,
"learning_rate": 0.001606221389929255,
"loss": 1.3246,
"step": 378500
},
{
"epoch": 9.857469829379943,
"grad_norm": 0.361328125,
"learning_rate": 0.0016057012068248025,
"loss": 1.323,
"step": 379000
},
{
"epoch": 9.87047440699126,
"grad_norm": 0.357421875,
"learning_rate": 0.0016051810237203497,
"loss": 1.3247,
"step": 379500
},
{
"epoch": 9.88347898460258,
"grad_norm": 0.6953125,
"learning_rate": 0.001604660840615897,
"loss": 1.3228,
"step": 380000
},
{
"epoch": 9.896483562213898,
"grad_norm": 0.390625,
"learning_rate": 0.0016041406575114442,
"loss": 1.3268,
"step": 380500
},
{
"epoch": 9.909488139825218,
"grad_norm": 0.390625,
"learning_rate": 0.0016036204744069914,
"loss": 1.3253,
"step": 381000
},
{
"epoch": 9.922492717436537,
"grad_norm": 0.40234375,
"learning_rate": 0.0016031002913025386,
"loss": 1.3239,
"step": 381500
},
{
"epoch": 9.935497295047856,
"grad_norm": 0.6328125,
"learning_rate": 0.0016025801081980858,
"loss": 1.3257,
"step": 382000
},
{
"epoch": 9.948501872659175,
"grad_norm": 0.34765625,
"learning_rate": 0.001602059925093633,
"loss": 1.3239,
"step": 382500
},
{
"epoch": 9.961506450270495,
"grad_norm": 0.421875,
"learning_rate": 0.00160153974198918,
"loss": 1.3247,
"step": 383000
},
{
"epoch": 9.974511027881814,
"grad_norm": 1.1328125,
"learning_rate": 0.0016010195588847273,
"loss": 1.3239,
"step": 383500
},
{
"epoch": 9.987515605493133,
"grad_norm": 0.435546875,
"learning_rate": 0.0016004993757802745,
"loss": 1.3226,
"step": 384000
},
{
"epoch": 10.0,
"eval_loss": 1.3314919471740723,
"eval_runtime": 0.597,
"eval_samples_per_second": 1675.105,
"eval_steps_per_second": 6.7,
"step": 384480
},
{
"epoch": 10.000520183104452,
"grad_norm": 0.60546875,
"learning_rate": 0.0015999791926758218,
"loss": 1.3244,
"step": 384500
},
{
"epoch": 10.013524760715772,
"grad_norm": 0.34375,
"learning_rate": 0.0015994590095713692,
"loss": 1.3234,
"step": 385000
},
{
"epoch": 10.02652933832709,
"grad_norm": 0.4296875,
"learning_rate": 0.0015989388264669164,
"loss": 1.3219,
"step": 385500
},
{
"epoch": 10.03953391593841,
"grad_norm": 0.404296875,
"learning_rate": 0.0015984186433624637,
"loss": 1.3208,
"step": 386000
},
{
"epoch": 10.05253849354973,
"grad_norm": 0.39453125,
"learning_rate": 0.001597898460258011,
"loss": 1.3214,
"step": 386500
},
{
"epoch": 10.065543071161049,
"grad_norm": 0.52734375,
"learning_rate": 0.0015973782771535581,
"loss": 1.3264,
"step": 387000
},
{
"epoch": 10.078547648772368,
"grad_norm": 0.419921875,
"learning_rate": 0.0015968580940491054,
"loss": 1.3225,
"step": 387500
},
{
"epoch": 10.091552226383687,
"grad_norm": 0.453125,
"learning_rate": 0.0015963379109446526,
"loss": 1.324,
"step": 388000
},
{
"epoch": 10.104556803995006,
"grad_norm": 0.8046875,
"learning_rate": 0.0015958177278401998,
"loss": 1.322,
"step": 388500
},
{
"epoch": 10.117561381606325,
"grad_norm": 0.46484375,
"learning_rate": 0.001595297544735747,
"loss": 1.322,
"step": 389000
},
{
"epoch": 10.130565959217645,
"grad_norm": 0.349609375,
"learning_rate": 0.0015947773616312943,
"loss": 1.3236,
"step": 389500
},
{
"epoch": 10.143570536828964,
"grad_norm": 0.73046875,
"learning_rate": 0.0015942571785268413,
"loss": 1.3237,
"step": 390000
},
{
"epoch": 10.156575114440283,
"grad_norm": 0.380859375,
"learning_rate": 0.0015937369954223887,
"loss": 1.3214,
"step": 390500
},
{
"epoch": 10.169579692051602,
"grad_norm": 0.478515625,
"learning_rate": 0.001593216812317936,
"loss": 1.3217,
"step": 391000
},
{
"epoch": 10.182584269662922,
"grad_norm": 0.49609375,
"learning_rate": 0.0015926966292134832,
"loss": 1.3234,
"step": 391500
},
{
"epoch": 10.19558884727424,
"grad_norm": 1.421875,
"learning_rate": 0.0015921764461090304,
"loss": 1.3241,
"step": 392000
},
{
"epoch": 10.20859342488556,
"grad_norm": 0.400390625,
"learning_rate": 0.0015916562630045776,
"loss": 1.3219,
"step": 392500
},
{
"epoch": 10.22159800249688,
"grad_norm": 0.486328125,
"learning_rate": 0.0015911360799001249,
"loss": 1.3233,
"step": 393000
},
{
"epoch": 10.234602580108199,
"grad_norm": 0.40234375,
"learning_rate": 0.001590615896795672,
"loss": 1.3239,
"step": 393500
},
{
"epoch": 10.247607157719518,
"grad_norm": 0.3671875,
"learning_rate": 0.0015900957136912193,
"loss": 1.3235,
"step": 394000
},
{
"epoch": 10.260611735330837,
"grad_norm": 0.443359375,
"learning_rate": 0.0015895755305867666,
"loss": 1.3228,
"step": 394500
},
{
"epoch": 10.273616312942156,
"grad_norm": 0.384765625,
"learning_rate": 0.0015890553474823138,
"loss": 1.3249,
"step": 395000
},
{
"epoch": 10.286620890553476,
"grad_norm": 0.408203125,
"learning_rate": 0.001588535164377861,
"loss": 1.323,
"step": 395500
},
{
"epoch": 10.299625468164795,
"grad_norm": 0.41796875,
"learning_rate": 0.0015880149812734085,
"loss": 1.3216,
"step": 396000
},
{
"epoch": 10.312630045776114,
"grad_norm": 0.396484375,
"learning_rate": 0.0015874947981689557,
"loss": 1.3242,
"step": 396500
},
{
"epoch": 10.325634623387433,
"grad_norm": 0.37890625,
"learning_rate": 0.0015869746150645027,
"loss": 1.3236,
"step": 397000
},
{
"epoch": 10.338639200998752,
"grad_norm": 0.5703125,
"learning_rate": 0.00158645443196005,
"loss": 1.3207,
"step": 397500
},
{
"epoch": 10.35164377861007,
"grad_norm": 0.390625,
"learning_rate": 0.0015859342488555972,
"loss": 1.3215,
"step": 398000
},
{
"epoch": 10.36464835622139,
"grad_norm": 0.43359375,
"learning_rate": 0.0015854140657511444,
"loss": 1.3216,
"step": 398500
},
{
"epoch": 10.377652933832708,
"grad_norm": 0.39453125,
"learning_rate": 0.0015848938826466916,
"loss": 1.3223,
"step": 399000
},
{
"epoch": 10.390657511444028,
"grad_norm": 0.6484375,
"learning_rate": 0.0015843736995422388,
"loss": 1.3195,
"step": 399500
},
{
"epoch": 10.403662089055347,
"grad_norm": 0.40625,
"learning_rate": 0.001583853516437786,
"loss": 1.3197,
"step": 400000
},
{
"epoch": 10.416666666666666,
"grad_norm": 0.515625,
"learning_rate": 0.0015833333333333333,
"loss": 1.3225,
"step": 400500
},
{
"epoch": 10.429671244277985,
"grad_norm": 0.36328125,
"learning_rate": 0.0015828131502288805,
"loss": 1.3223,
"step": 401000
},
{
"epoch": 10.442675821889305,
"grad_norm": 0.455078125,
"learning_rate": 0.001582292967124428,
"loss": 1.3231,
"step": 401500
},
{
"epoch": 10.455680399500624,
"grad_norm": 0.384765625,
"learning_rate": 0.0015817727840199752,
"loss": 1.324,
"step": 402000
},
{
"epoch": 10.468684977111943,
"grad_norm": 0.486328125,
"learning_rate": 0.0015812526009155224,
"loss": 1.3217,
"step": 402500
},
{
"epoch": 10.481689554723262,
"grad_norm": 1.6796875,
"learning_rate": 0.0015807324178110697,
"loss": 1.3238,
"step": 403000
},
{
"epoch": 10.494694132334581,
"grad_norm": 0.4453125,
"learning_rate": 0.0015802122347066169,
"loss": 1.3235,
"step": 403500
},
{
"epoch": 10.5076987099459,
"grad_norm": 0.41796875,
"learning_rate": 0.0015796920516021641,
"loss": 1.3233,
"step": 404000
},
{
"epoch": 10.52070328755722,
"grad_norm": 0.373046875,
"learning_rate": 0.0015791718684977111,
"loss": 1.3209,
"step": 404500
},
{
"epoch": 10.53370786516854,
"grad_norm": 0.427734375,
"learning_rate": 0.0015786516853932584,
"loss": 1.3207,
"step": 405000
},
{
"epoch": 10.546712442779858,
"grad_norm": 0.490234375,
"learning_rate": 0.0015781315022888056,
"loss": 1.3225,
"step": 405500
},
{
"epoch": 10.559717020391178,
"grad_norm": 2.203125,
"learning_rate": 0.0015776113191843528,
"loss": 1.3186,
"step": 406000
},
{
"epoch": 10.572721598002497,
"grad_norm": 5.0625,
"learning_rate": 0.0015770911360799,
"loss": 1.3233,
"step": 406500
},
{
"epoch": 10.585726175613816,
"grad_norm": 0.353515625,
"learning_rate": 0.0015765709529754473,
"loss": 1.324,
"step": 407000
},
{
"epoch": 10.598730753225135,
"grad_norm": 0.6171875,
"learning_rate": 0.0015760507698709947,
"loss": 1.3247,
"step": 407500
},
{
"epoch": 10.611735330836455,
"grad_norm": 1.421875,
"learning_rate": 0.001575530586766542,
"loss": 1.3247,
"step": 408000
},
{
"epoch": 10.624739908447774,
"grad_norm": 0.5078125,
"learning_rate": 0.0015750104036620892,
"loss": 1.3217,
"step": 408500
},
{
"epoch": 10.637744486059093,
"grad_norm": 0.55859375,
"learning_rate": 0.0015744902205576364,
"loss": 1.3215,
"step": 409000
},
{
"epoch": 10.650749063670412,
"grad_norm": 0.486328125,
"learning_rate": 0.0015739700374531836,
"loss": 1.3236,
"step": 409500
},
{
"epoch": 10.663753641281732,
"grad_norm": 2.796875,
"learning_rate": 0.0015734498543487309,
"loss": 1.3252,
"step": 410000
},
{
"epoch": 10.67675821889305,
"grad_norm": 0.380859375,
"learning_rate": 0.001572929671244278,
"loss": 1.3238,
"step": 410500
},
{
"epoch": 10.68976279650437,
"grad_norm": 0.7578125,
"learning_rate": 0.0015724094881398253,
"loss": 1.3225,
"step": 411000
},
{
"epoch": 10.70276737411569,
"grad_norm": 2.984375,
"learning_rate": 0.0015718893050353723,
"loss": 1.3195,
"step": 411500
},
{
"epoch": 10.715771951727008,
"grad_norm": 0.3984375,
"learning_rate": 0.0015713691219309195,
"loss": 1.3218,
"step": 412000
},
{
"epoch": 10.728776529338328,
"grad_norm": 0.431640625,
"learning_rate": 0.0015708489388264668,
"loss": 1.3224,
"step": 412500
},
{
"epoch": 10.741781106949647,
"grad_norm": 0.4453125,
"learning_rate": 0.0015703287557220142,
"loss": 1.3203,
"step": 413000
},
{
"epoch": 10.754785684560966,
"grad_norm": 0.40625,
"learning_rate": 0.0015698085726175615,
"loss": 1.3207,
"step": 413500
},
{
"epoch": 10.767790262172285,
"grad_norm": 0.578125,
"learning_rate": 0.0015692883895131087,
"loss": 1.3208,
"step": 414000
},
{
"epoch": 10.780794839783605,
"grad_norm": 0.408203125,
"learning_rate": 0.001568768206408656,
"loss": 1.3225,
"step": 414500
},
{
"epoch": 10.793799417394922,
"grad_norm": 0.609375,
"learning_rate": 0.0015682480233042031,
"loss": 1.326,
"step": 415000
},
{
"epoch": 10.806803995006241,
"grad_norm": 0.423828125,
"learning_rate": 0.0015677278401997504,
"loss": 1.3212,
"step": 415500
},
{
"epoch": 10.81980857261756,
"grad_norm": 0.57421875,
"learning_rate": 0.0015672076570952976,
"loss": 1.3227,
"step": 416000
},
{
"epoch": 10.83281315022888,
"grad_norm": 0.39453125,
"learning_rate": 0.0015666874739908448,
"loss": 1.3217,
"step": 416500
},
{
"epoch": 10.845817727840199,
"grad_norm": 0.4921875,
"learning_rate": 0.001566167290886392,
"loss": 1.3217,
"step": 417000
},
{
"epoch": 10.858822305451518,
"grad_norm": 0.388671875,
"learning_rate": 0.0015656471077819393,
"loss": 1.3227,
"step": 417500
},
{
"epoch": 10.871826883062838,
"grad_norm": 0.51953125,
"learning_rate": 0.0015651269246774865,
"loss": 1.3235,
"step": 418000
},
{
"epoch": 10.884831460674157,
"grad_norm": 1.1171875,
"learning_rate": 0.0015646067415730337,
"loss": 1.3217,
"step": 418500
},
{
"epoch": 10.897836038285476,
"grad_norm": 0.416015625,
"learning_rate": 0.001564086558468581,
"loss": 1.3208,
"step": 419000
},
{
"epoch": 10.910840615896795,
"grad_norm": 0.65625,
"learning_rate": 0.0015635663753641282,
"loss": 1.3222,
"step": 419500
},
{
"epoch": 10.923845193508114,
"grad_norm": 0.546875,
"learning_rate": 0.0015630461922596754,
"loss": 1.3214,
"step": 420000
},
{
"epoch": 10.936849771119434,
"grad_norm": 0.640625,
"learning_rate": 0.0015625260091552226,
"loss": 1.3254,
"step": 420500
},
{
"epoch": 10.949854348730753,
"grad_norm": 0.38671875,
"learning_rate": 0.0015620058260507699,
"loss": 1.3233,
"step": 421000
},
{
"epoch": 10.962858926342072,
"grad_norm": 0.5078125,
"learning_rate": 0.001561485642946317,
"loss": 1.3219,
"step": 421500
},
{
"epoch": 10.975863503953391,
"grad_norm": 1.1875,
"learning_rate": 0.0015609654598418643,
"loss": 1.3225,
"step": 422000
},
{
"epoch": 10.98886808156471,
"grad_norm": 0.96484375,
"learning_rate": 0.0015604452767374116,
"loss": 1.3211,
"step": 422500
},
{
"epoch": 11.0,
"eval_loss": 1.3315958976745605,
"eval_runtime": 0.7007,
"eval_samples_per_second": 1427.058,
"eval_steps_per_second": 5.708,
"step": 422928
}
],
"logging_steps": 500,
"max_steps": 1922400,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8.879327056150544e+19,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}