terry69's picture
Model save
097b259 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1862,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005370569280343716,
"grad_norm": 23.24650194199282,
"learning_rate": 5.3475935828877005e-08,
"loss": 1.3311,
"step": 1
},
{
"epoch": 0.0026852846401718583,
"grad_norm": 22.330898818261065,
"learning_rate": 2.6737967914438503e-07,
"loss": 1.3253,
"step": 5
},
{
"epoch": 0.0053705692803437165,
"grad_norm": 14.30106930070543,
"learning_rate": 5.347593582887701e-07,
"loss": 1.2789,
"step": 10
},
{
"epoch": 0.008055853920515575,
"grad_norm": 11.64556494145369,
"learning_rate": 8.021390374331551e-07,
"loss": 1.1368,
"step": 15
},
{
"epoch": 0.010741138560687433,
"grad_norm": 8.118501955109776,
"learning_rate": 1.0695187165775401e-06,
"loss": 1.0241,
"step": 20
},
{
"epoch": 0.01342642320085929,
"grad_norm": 3.566122504006401,
"learning_rate": 1.3368983957219254e-06,
"loss": 0.9222,
"step": 25
},
{
"epoch": 0.01611170784103115,
"grad_norm": 3.564539213552227,
"learning_rate": 1.6042780748663103e-06,
"loss": 0.8845,
"step": 30
},
{
"epoch": 0.018796992481203006,
"grad_norm": 2.9457915861316155,
"learning_rate": 1.8716577540106954e-06,
"loss": 0.8579,
"step": 35
},
{
"epoch": 0.021482277121374866,
"grad_norm": 3.0197703703854537,
"learning_rate": 2.1390374331550802e-06,
"loss": 0.8413,
"step": 40
},
{
"epoch": 0.024167561761546726,
"grad_norm": 2.9791028835834266,
"learning_rate": 2.4064171122994653e-06,
"loss": 0.8496,
"step": 45
},
{
"epoch": 0.02685284640171858,
"grad_norm": 2.9387475547868447,
"learning_rate": 2.673796791443851e-06,
"loss": 0.8364,
"step": 50
},
{
"epoch": 0.02953813104189044,
"grad_norm": 2.983217345827822,
"learning_rate": 2.9411764705882355e-06,
"loss": 0.815,
"step": 55
},
{
"epoch": 0.0322234156820623,
"grad_norm": 3.0043440099698655,
"learning_rate": 3.2085561497326205e-06,
"loss": 0.8054,
"step": 60
},
{
"epoch": 0.03490870032223416,
"grad_norm": 2.964431518597424,
"learning_rate": 3.4759358288770056e-06,
"loss": 0.7908,
"step": 65
},
{
"epoch": 0.03759398496240601,
"grad_norm": 2.997893325231212,
"learning_rate": 3.7433155080213907e-06,
"loss": 0.7655,
"step": 70
},
{
"epoch": 0.040279269602577876,
"grad_norm": 2.913048077444334,
"learning_rate": 4.010695187165775e-06,
"loss": 0.7604,
"step": 75
},
{
"epoch": 0.04296455424274973,
"grad_norm": 3.2965192153249134,
"learning_rate": 4.2780748663101604e-06,
"loss": 0.7677,
"step": 80
},
{
"epoch": 0.04564983888292159,
"grad_norm": 3.2484711409260134,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.7529,
"step": 85
},
{
"epoch": 0.04833512352309345,
"grad_norm": 3.078770088924231,
"learning_rate": 4.812834224598931e-06,
"loss": 0.7516,
"step": 90
},
{
"epoch": 0.05102040816326531,
"grad_norm": 3.2096043661064857,
"learning_rate": 5.0802139037433165e-06,
"loss": 0.7418,
"step": 95
},
{
"epoch": 0.05370569280343716,
"grad_norm": 3.085147306021244,
"learning_rate": 5.347593582887702e-06,
"loss": 0.7395,
"step": 100
},
{
"epoch": 0.05639097744360902,
"grad_norm": 3.2358521727601124,
"learning_rate": 5.614973262032086e-06,
"loss": 0.7186,
"step": 105
},
{
"epoch": 0.05907626208378088,
"grad_norm": 3.569462119925773,
"learning_rate": 5.882352941176471e-06,
"loss": 0.7371,
"step": 110
},
{
"epoch": 0.06176154672395274,
"grad_norm": 3.1935948386934236,
"learning_rate": 6.149732620320856e-06,
"loss": 0.7268,
"step": 115
},
{
"epoch": 0.0644468313641246,
"grad_norm": 3.0094330504675337,
"learning_rate": 6.417112299465241e-06,
"loss": 0.7282,
"step": 120
},
{
"epoch": 0.06713211600429646,
"grad_norm": 2.9768248913925706,
"learning_rate": 6.684491978609626e-06,
"loss": 0.7199,
"step": 125
},
{
"epoch": 0.06981740064446831,
"grad_norm": 2.985384542106191,
"learning_rate": 6.951871657754011e-06,
"loss": 0.7098,
"step": 130
},
{
"epoch": 0.07250268528464017,
"grad_norm": 3.1114657869255193,
"learning_rate": 7.219251336898396e-06,
"loss": 0.7092,
"step": 135
},
{
"epoch": 0.07518796992481203,
"grad_norm": 2.9538001755436722,
"learning_rate": 7.486631016042781e-06,
"loss": 0.7117,
"step": 140
},
{
"epoch": 0.07787325456498388,
"grad_norm": 3.0383720885798025,
"learning_rate": 7.754010695187166e-06,
"loss": 0.7109,
"step": 145
},
{
"epoch": 0.08055853920515575,
"grad_norm": 3.050688164634261,
"learning_rate": 8.02139037433155e-06,
"loss": 0.6994,
"step": 150
},
{
"epoch": 0.08324382384532761,
"grad_norm": 3.0901228534462644,
"learning_rate": 8.288770053475937e-06,
"loss": 0.6972,
"step": 155
},
{
"epoch": 0.08592910848549946,
"grad_norm": 2.990685793532457,
"learning_rate": 8.556149732620321e-06,
"loss": 0.6968,
"step": 160
},
{
"epoch": 0.08861439312567132,
"grad_norm": 2.9238275896438823,
"learning_rate": 8.823529411764707e-06,
"loss": 0.6999,
"step": 165
},
{
"epoch": 0.09129967776584318,
"grad_norm": 2.833089479559651,
"learning_rate": 9.090909090909091e-06,
"loss": 0.711,
"step": 170
},
{
"epoch": 0.09398496240601503,
"grad_norm": 2.7451133989854117,
"learning_rate": 9.358288770053477e-06,
"loss": 0.6809,
"step": 175
},
{
"epoch": 0.0966702470461869,
"grad_norm": 2.96205914599503,
"learning_rate": 9.625668449197861e-06,
"loss": 0.6963,
"step": 180
},
{
"epoch": 0.09935553168635876,
"grad_norm": 2.8833710853055807,
"learning_rate": 9.893048128342247e-06,
"loss": 0.7014,
"step": 185
},
{
"epoch": 0.10204081632653061,
"grad_norm": 2.7179464277865057,
"learning_rate": 9.999920849895074e-06,
"loss": 0.7068,
"step": 190
},
{
"epoch": 0.10472610096670247,
"grad_norm": 2.7241236140469702,
"learning_rate": 9.99943716388422e-06,
"loss": 0.6948,
"step": 195
},
{
"epoch": 0.10741138560687433,
"grad_norm": 2.692817542319411,
"learning_rate": 9.998513806628825e-06,
"loss": 0.6919,
"step": 200
},
{
"epoch": 0.11009667024704618,
"grad_norm": 2.7364707686472216,
"learning_rate": 9.997150859332753e-06,
"loss": 0.6915,
"step": 205
},
{
"epoch": 0.11278195488721804,
"grad_norm": 2.748436249436038,
"learning_rate": 9.995348441859243e-06,
"loss": 0.6897,
"step": 210
},
{
"epoch": 0.11546723952738991,
"grad_norm": 2.8496184261090303,
"learning_rate": 9.993106712720367e-06,
"loss": 0.7082,
"step": 215
},
{
"epoch": 0.11815252416756176,
"grad_norm": 2.7886558511457293,
"learning_rate": 9.990425869063085e-06,
"loss": 0.6877,
"step": 220
},
{
"epoch": 0.12083780880773362,
"grad_norm": 2.925725103275169,
"learning_rate": 9.987306146651908e-06,
"loss": 0.6893,
"step": 225
},
{
"epoch": 0.12352309344790548,
"grad_norm": 2.760427995587573,
"learning_rate": 9.983747819848168e-06,
"loss": 0.6857,
"step": 230
},
{
"epoch": 0.12620837808807733,
"grad_norm": 2.6882524904583938,
"learning_rate": 9.97975120158589e-06,
"loss": 0.6839,
"step": 235
},
{
"epoch": 0.1288936627282492,
"grad_norm": 2.5644520235016093,
"learning_rate": 9.975316643344257e-06,
"loss": 0.6853,
"step": 240
},
{
"epoch": 0.13157894736842105,
"grad_norm": 2.6983140410879205,
"learning_rate": 9.970444535116721e-06,
"loss": 0.678,
"step": 245
},
{
"epoch": 0.13426423200859292,
"grad_norm": 2.779736296533018,
"learning_rate": 9.965135305376694e-06,
"loss": 0.6848,
"step": 250
},
{
"epoch": 0.13694951664876476,
"grad_norm": 2.693104898923946,
"learning_rate": 9.959389421039863e-06,
"loss": 0.6638,
"step": 255
},
{
"epoch": 0.13963480128893663,
"grad_norm": 2.5868563232582864,
"learning_rate": 9.95320738742313e-06,
"loss": 0.672,
"step": 260
},
{
"epoch": 0.1423200859291085,
"grad_norm": 2.621495018630072,
"learning_rate": 9.946589748200185e-06,
"loss": 0.6484,
"step": 265
},
{
"epoch": 0.14500537056928034,
"grad_norm": 2.717320705292848,
"learning_rate": 9.939537085353668e-06,
"loss": 0.6695,
"step": 270
},
{
"epoch": 0.1476906552094522,
"grad_norm": 2.6563912931269793,
"learning_rate": 9.932050019124011e-06,
"loss": 0.6556,
"step": 275
},
{
"epoch": 0.15037593984962405,
"grad_norm": 2.542635572900079,
"learning_rate": 9.924129207954877e-06,
"loss": 0.6542,
"step": 280
},
{
"epoch": 0.15306122448979592,
"grad_norm": 2.5747252996045047,
"learning_rate": 9.915775348435266e-06,
"loss": 0.6651,
"step": 285
},
{
"epoch": 0.15574650912996776,
"grad_norm": 2.5190278227104907,
"learning_rate": 9.906989175238232e-06,
"loss": 0.6806,
"step": 290
},
{
"epoch": 0.15843179377013963,
"grad_norm": 2.7503122372827282,
"learning_rate": 9.8977714610563e-06,
"loss": 0.6689,
"step": 295
},
{
"epoch": 0.1611170784103115,
"grad_norm": 2.495962467536807,
"learning_rate": 9.888123016533496e-06,
"loss": 0.6697,
"step": 300
},
{
"epoch": 0.16380236305048335,
"grad_norm": 2.356547940500444,
"learning_rate": 9.878044690194055e-06,
"loss": 0.6393,
"step": 305
},
{
"epoch": 0.16648764769065522,
"grad_norm": 2.4683724447996753,
"learning_rate": 9.86753736836781e-06,
"loss": 0.6563,
"step": 310
},
{
"epoch": 0.16917293233082706,
"grad_norm": 2.4694368658924515,
"learning_rate": 9.856601975112227e-06,
"loss": 0.6625,
"step": 315
},
{
"epoch": 0.17185821697099893,
"grad_norm": 2.4804408432246268,
"learning_rate": 9.84523947213116e-06,
"loss": 0.6658,
"step": 320
},
{
"epoch": 0.17454350161117077,
"grad_norm": 2.5366406977907263,
"learning_rate": 9.833450858690257e-06,
"loss": 0.6577,
"step": 325
},
{
"epoch": 0.17722878625134264,
"grad_norm": 2.4959209862442666,
"learning_rate": 9.821237171529088e-06,
"loss": 0.6568,
"step": 330
},
{
"epoch": 0.1799140708915145,
"grad_norm": 2.436320069504647,
"learning_rate": 9.808599484769971e-06,
"loss": 0.6527,
"step": 335
},
{
"epoch": 0.18259935553168635,
"grad_norm": 2.408820245370078,
"learning_rate": 9.79553890982351e-06,
"loss": 0.6469,
"step": 340
},
{
"epoch": 0.18528464017185822,
"grad_norm": 2.3724792548565703,
"learning_rate": 9.782056595290848e-06,
"loss": 0.6466,
"step": 345
},
{
"epoch": 0.18796992481203006,
"grad_norm": 2.8644640360280804,
"learning_rate": 9.768153726862652e-06,
"loss": 0.6465,
"step": 350
},
{
"epoch": 0.19065520945220193,
"grad_norm": 2.4550993989860364,
"learning_rate": 9.753831527214854e-06,
"loss": 0.6382,
"step": 355
},
{
"epoch": 0.1933404940923738,
"grad_norm": 2.5293847474531774,
"learning_rate": 9.739091255901105e-06,
"loss": 0.6404,
"step": 360
},
{
"epoch": 0.19602577873254565,
"grad_norm": 2.4850628677242588,
"learning_rate": 9.723934209242015e-06,
"loss": 0.6535,
"step": 365
},
{
"epoch": 0.19871106337271752,
"grad_norm": 2.6683686695351483,
"learning_rate": 9.708361720211146e-06,
"loss": 0.6374,
"step": 370
},
{
"epoch": 0.20139634801288936,
"grad_norm": 2.637566511963867,
"learning_rate": 9.692375158317787e-06,
"loss": 0.6227,
"step": 375
},
{
"epoch": 0.20408163265306123,
"grad_norm": 2.6019921351676105,
"learning_rate": 9.675975929486512e-06,
"loss": 0.6417,
"step": 380
},
{
"epoch": 0.20676691729323307,
"grad_norm": 2.47881491966567,
"learning_rate": 9.659165475933537e-06,
"loss": 0.6299,
"step": 385
},
{
"epoch": 0.20945220193340494,
"grad_norm": 2.552762118416453,
"learning_rate": 9.641945276039885e-06,
"loss": 0.6257,
"step": 390
},
{
"epoch": 0.2121374865735768,
"grad_norm": 2.905755783083339,
"learning_rate": 9.624316844221376e-06,
"loss": 0.6353,
"step": 395
},
{
"epoch": 0.21482277121374865,
"grad_norm": 2.787014594047912,
"learning_rate": 9.606281730795435e-06,
"loss": 0.6346,
"step": 400
},
{
"epoch": 0.21750805585392052,
"grad_norm": 2.4267817090996076,
"learning_rate": 9.587841521844755e-06,
"loss": 0.629,
"step": 405
},
{
"epoch": 0.22019334049409237,
"grad_norm": 2.3521043249697575,
"learning_rate": 9.568997839077812e-06,
"loss": 0.6215,
"step": 410
},
{
"epoch": 0.22287862513426424,
"grad_norm": 2.420122955104665,
"learning_rate": 9.549752339686243e-06,
"loss": 0.6133,
"step": 415
},
{
"epoch": 0.22556390977443608,
"grad_norm": 2.472763345819507,
"learning_rate": 9.530106716199103e-06,
"loss": 0.6232,
"step": 420
},
{
"epoch": 0.22824919441460795,
"grad_norm": 2.408114715391977,
"learning_rate": 9.510062696334024e-06,
"loss": 0.6313,
"step": 425
},
{
"epoch": 0.23093447905477982,
"grad_norm": 2.345983524123704,
"learning_rate": 9.489622042845266e-06,
"loss": 0.6296,
"step": 430
},
{
"epoch": 0.23361976369495166,
"grad_norm": 2.5164199127720552,
"learning_rate": 9.468786553368694e-06,
"loss": 0.5911,
"step": 435
},
{
"epoch": 0.23630504833512353,
"grad_norm": 2.502719208388728,
"learning_rate": 9.447558060263693e-06,
"loss": 0.6373,
"step": 440
},
{
"epoch": 0.23899033297529537,
"grad_norm": 2.3972996560055964,
"learning_rate": 9.42593843045201e-06,
"loss": 0.6344,
"step": 445
},
{
"epoch": 0.24167561761546724,
"grad_norm": 2.533232452011481,
"learning_rate": 9.403929565253582e-06,
"loss": 0.6167,
"step": 450
},
{
"epoch": 0.24436090225563908,
"grad_norm": 2.3959318258617066,
"learning_rate": 9.381533400219319e-06,
"loss": 0.6197,
"step": 455
},
{
"epoch": 0.24704618689581095,
"grad_norm": 2.543030166531423,
"learning_rate": 9.358751904960885e-06,
"loss": 0.6104,
"step": 460
},
{
"epoch": 0.24973147153598282,
"grad_norm": 2.440979529961567,
"learning_rate": 9.335587082977484e-06,
"loss": 0.597,
"step": 465
},
{
"epoch": 0.25241675617615467,
"grad_norm": 2.3609227503767976,
"learning_rate": 9.312040971479663e-06,
"loss": 0.5918,
"step": 470
},
{
"epoch": 0.25510204081632654,
"grad_norm": 2.3675837988863973,
"learning_rate": 9.288115641210144e-06,
"loss": 0.6119,
"step": 475
},
{
"epoch": 0.2577873254564984,
"grad_norm": 2.3946127819918965,
"learning_rate": 9.26381319626173e-06,
"loss": 0.6145,
"step": 480
},
{
"epoch": 0.2604726100966702,
"grad_norm": 2.5704228346445253,
"learning_rate": 9.239135773892249e-06,
"loss": 0.607,
"step": 485
},
{
"epoch": 0.2631578947368421,
"grad_norm": 2.3244758583512812,
"learning_rate": 9.214085544336597e-06,
"loss": 0.5965,
"step": 490
},
{
"epoch": 0.26584317937701396,
"grad_norm": 2.5591933550816477,
"learning_rate": 9.188664710615886e-06,
"loss": 0.6006,
"step": 495
},
{
"epoch": 0.26852846401718583,
"grad_norm": 2.4296032203065425,
"learning_rate": 9.162875508343691e-06,
"loss": 0.5851,
"step": 500
},
{
"epoch": 0.2712137486573577,
"grad_norm": 2.296029683307929,
"learning_rate": 9.136720205529446e-06,
"loss": 0.5997,
"step": 505
},
{
"epoch": 0.2738990332975295,
"grad_norm": 2.3974631237841098,
"learning_rate": 9.110201102378991e-06,
"loss": 0.6086,
"step": 510
},
{
"epoch": 0.2765843179377014,
"grad_norm": 2.402339668666006,
"learning_rate": 9.083320531092268e-06,
"loss": 0.5752,
"step": 515
},
{
"epoch": 0.27926960257787325,
"grad_norm": 2.385424562143977,
"learning_rate": 9.056080855658233e-06,
"loss": 0.5933,
"step": 520
},
{
"epoch": 0.2819548872180451,
"grad_norm": 2.5254432858312454,
"learning_rate": 9.02848447164695e-06,
"loss": 0.5857,
"step": 525
},
{
"epoch": 0.284640171858217,
"grad_norm": 2.5910100026270295,
"learning_rate": 9.00053380599891e-06,
"loss": 0.5761,
"step": 530
},
{
"epoch": 0.2873254564983888,
"grad_norm": 2.476461377683874,
"learning_rate": 8.972231316811608e-06,
"loss": 0.5844,
"step": 535
},
{
"epoch": 0.2900107411385607,
"grad_norm": 2.4702789703549652,
"learning_rate": 8.943579493123354e-06,
"loss": 0.5901,
"step": 540
},
{
"epoch": 0.29269602577873255,
"grad_norm": 2.3593595834037577,
"learning_rate": 8.914580854694389e-06,
"loss": 0.5828,
"step": 545
},
{
"epoch": 0.2953813104189044,
"grad_norm": 2.410380206903673,
"learning_rate": 8.885237951785275e-06,
"loss": 0.5874,
"step": 550
},
{
"epoch": 0.2980665950590763,
"grad_norm": 2.3336432838340793,
"learning_rate": 8.855553364932628e-06,
"loss": 0.5728,
"step": 555
},
{
"epoch": 0.3007518796992481,
"grad_norm": 2.432916358546458,
"learning_rate": 8.82552970472216e-06,
"loss": 0.5774,
"step": 560
},
{
"epoch": 0.30343716433942,
"grad_norm": 2.249380319796683,
"learning_rate": 8.795169611559108e-06,
"loss": 0.5775,
"step": 565
},
{
"epoch": 0.30612244897959184,
"grad_norm": 2.3769101945850335,
"learning_rate": 8.764475755436011e-06,
"loss": 0.578,
"step": 570
},
{
"epoch": 0.3088077336197637,
"grad_norm": 2.299389674060058,
"learning_rate": 8.733450835697914e-06,
"loss": 0.5754,
"step": 575
},
{
"epoch": 0.31149301825993553,
"grad_norm": 2.500777546304969,
"learning_rate": 8.702097580804962e-06,
"loss": 0.5752,
"step": 580
},
{
"epoch": 0.3141783029001074,
"grad_norm": 2.360457853138563,
"learning_rate": 8.670418748092465e-06,
"loss": 0.566,
"step": 585
},
{
"epoch": 0.31686358754027927,
"grad_norm": 2.3487658574792887,
"learning_rate": 8.638417123528393e-06,
"loss": 0.5641,
"step": 590
},
{
"epoch": 0.31954887218045114,
"grad_norm": 2.337362864786151,
"learning_rate": 8.60609552146837e-06,
"loss": 0.5814,
"step": 595
},
{
"epoch": 0.322234156820623,
"grad_norm": 2.4659729067998044,
"learning_rate": 8.573456784408162e-06,
"loss": 0.5665,
"step": 600
},
{
"epoch": 0.3249194414607948,
"grad_norm": 2.3511534894932082,
"learning_rate": 8.540503782733718e-06,
"loss": 0.5564,
"step": 605
},
{
"epoch": 0.3276047261009667,
"grad_norm": 2.4955366711390905,
"learning_rate": 8.507239414468707e-06,
"loss": 0.5621,
"step": 610
},
{
"epoch": 0.33029001074113856,
"grad_norm": 2.222102137651061,
"learning_rate": 8.473666605019673e-06,
"loss": 0.5663,
"step": 615
},
{
"epoch": 0.33297529538131043,
"grad_norm": 2.348964509006807,
"learning_rate": 8.439788306918759e-06,
"loss": 0.5574,
"step": 620
},
{
"epoch": 0.3356605800214823,
"grad_norm": 2.5769335726202525,
"learning_rate": 8.405607499564044e-06,
"loss": 0.5655,
"step": 625
},
{
"epoch": 0.3383458646616541,
"grad_norm": 2.461512964554347,
"learning_rate": 8.371127188957527e-06,
"loss": 0.539,
"step": 630
},
{
"epoch": 0.341031149301826,
"grad_norm": 2.442035803808355,
"learning_rate": 8.336350407440766e-06,
"loss": 0.5531,
"step": 635
},
{
"epoch": 0.34371643394199786,
"grad_norm": 2.4353997367706435,
"learning_rate": 8.3012802134282e-06,
"loss": 0.5654,
"step": 640
},
{
"epoch": 0.3464017185821697,
"grad_norm": 2.3846416840897926,
"learning_rate": 8.26591969113818e-06,
"loss": 0.5562,
"step": 645
},
{
"epoch": 0.34908700322234154,
"grad_norm": 2.3460039237512027,
"learning_rate": 8.230271950321733e-06,
"loss": 0.5511,
"step": 650
},
{
"epoch": 0.3517722878625134,
"grad_norm": 2.4100978977449135,
"learning_rate": 8.194340125989068e-06,
"loss": 0.5474,
"step": 655
},
{
"epoch": 0.3544575725026853,
"grad_norm": 2.4151061568364742,
"learning_rate": 8.158127378133886e-06,
"loss": 0.5549,
"step": 660
},
{
"epoch": 0.35714285714285715,
"grad_norm": 2.3010627622117337,
"learning_rate": 8.121636891455462e-06,
"loss": 0.5356,
"step": 665
},
{
"epoch": 0.359828141783029,
"grad_norm": 2.3257663012732888,
"learning_rate": 8.084871875078574e-06,
"loss": 0.5463,
"step": 670
},
{
"epoch": 0.36251342642320084,
"grad_norm": 2.3421091431351972,
"learning_rate": 8.047835562271289e-06,
"loss": 0.5498,
"step": 675
},
{
"epoch": 0.3651987110633727,
"grad_norm": 2.376412445470513,
"learning_rate": 8.010531210160594e-06,
"loss": 0.544,
"step": 680
},
{
"epoch": 0.3678839957035446,
"grad_norm": 2.3699097244796343,
"learning_rate": 7.972962099445979e-06,
"loss": 0.5351,
"step": 685
},
{
"epoch": 0.37056928034371645,
"grad_norm": 2.348566511011727,
"learning_rate": 7.935131534110893e-06,
"loss": 0.547,
"step": 690
},
{
"epoch": 0.3732545649838883,
"grad_norm": 2.4665128277244266,
"learning_rate": 7.897042841132195e-06,
"loss": 0.5435,
"step": 695
},
{
"epoch": 0.37593984962406013,
"grad_norm": 2.419406228043383,
"learning_rate": 7.858699370187558e-06,
"loss": 0.5317,
"step": 700
},
{
"epoch": 0.378625134264232,
"grad_norm": 2.457065805114425,
"learning_rate": 7.820104493360883e-06,
"loss": 0.5271,
"step": 705
},
{
"epoch": 0.38131041890440387,
"grad_norm": 2.4257368466519305,
"learning_rate": 7.781261604845754e-06,
"loss": 0.5498,
"step": 710
},
{
"epoch": 0.38399570354457574,
"grad_norm": 2.2893159203981064,
"learning_rate": 7.742174120646929e-06,
"loss": 0.5383,
"step": 715
},
{
"epoch": 0.3866809881847476,
"grad_norm": 2.4452692956515096,
"learning_rate": 7.70284547827992e-06,
"loss": 0.5211,
"step": 720
},
{
"epoch": 0.3893662728249194,
"grad_norm": 2.3709311192856686,
"learning_rate": 7.663279136468696e-06,
"loss": 0.5453,
"step": 725
},
{
"epoch": 0.3920515574650913,
"grad_norm": 2.337548038820995,
"learning_rate": 7.623478574841499e-06,
"loss": 0.5308,
"step": 730
},
{
"epoch": 0.39473684210526316,
"grad_norm": 3.1483038312630383,
"learning_rate": 7.58344729362483e-06,
"loss": 0.5162,
"step": 735
},
{
"epoch": 0.39742212674543503,
"grad_norm": 2.2847515032866985,
"learning_rate": 7.5431888133356334e-06,
"loss": 0.5323,
"step": 740
},
{
"epoch": 0.40010741138560685,
"grad_norm": 2.376579590794952,
"learning_rate": 7.502706674471678e-06,
"loss": 0.5269,
"step": 745
},
{
"epoch": 0.4027926960257787,
"grad_norm": 2.451743591554685,
"learning_rate": 7.462004437200195e-06,
"loss": 0.5163,
"step": 750
},
{
"epoch": 0.4054779806659506,
"grad_norm": 2.3846328730903097,
"learning_rate": 7.42108568104479e-06,
"loss": 0.5267,
"step": 755
},
{
"epoch": 0.40816326530612246,
"grad_norm": 2.4692538986528647,
"learning_rate": 7.379954004570628e-06,
"loss": 0.5223,
"step": 760
},
{
"epoch": 0.41084854994629433,
"grad_norm": 2.432289092086297,
"learning_rate": 7.338613025067977e-06,
"loss": 0.5065,
"step": 765
},
{
"epoch": 0.41353383458646614,
"grad_norm": 2.373781407058759,
"learning_rate": 7.2970663782340765e-06,
"loss": 0.5124,
"step": 770
},
{
"epoch": 0.416219119226638,
"grad_norm": 2.3241744049098227,
"learning_rate": 7.25531771785341e-06,
"loss": 0.5226,
"step": 775
},
{
"epoch": 0.4189044038668099,
"grad_norm": 2.295153303941977,
"learning_rate": 7.2133707154763646e-06,
"loss": 0.5008,
"step": 780
},
{
"epoch": 0.42158968850698175,
"grad_norm": 2.2832092173310476,
"learning_rate": 7.17122906009635e-06,
"loss": 0.5315,
"step": 785
},
{
"epoch": 0.4242749731471536,
"grad_norm": 2.3670855467637137,
"learning_rate": 7.128896457825364e-06,
"loss": 0.4949,
"step": 790
},
{
"epoch": 0.42696025778732544,
"grad_norm": 2.3555918196295655,
"learning_rate": 7.08637663156807e-06,
"loss": 0.5161,
"step": 795
},
{
"epoch": 0.4296455424274973,
"grad_norm": 2.290951535562781,
"learning_rate": 7.043673320694386e-06,
"loss": 0.5179,
"step": 800
},
{
"epoch": 0.4323308270676692,
"grad_norm": 2.386655355396559,
"learning_rate": 7.000790280710625e-06,
"loss": 0.4933,
"step": 805
},
{
"epoch": 0.43501611170784105,
"grad_norm": 2.46762901959159,
"learning_rate": 6.957731282929224e-06,
"loss": 0.5066,
"step": 810
},
{
"epoch": 0.4377013963480129,
"grad_norm": 2.3719536460828934,
"learning_rate": 6.914500114137082e-06,
"loss": 0.5053,
"step": 815
},
{
"epoch": 0.44038668098818473,
"grad_norm": 2.5254586343768692,
"learning_rate": 6.871100576262526e-06,
"loss": 0.4964,
"step": 820
},
{
"epoch": 0.4430719656283566,
"grad_norm": 2.457774731404692,
"learning_rate": 6.827536486040964e-06,
"loss": 0.5083,
"step": 825
},
{
"epoch": 0.44575725026852847,
"grad_norm": 2.6799932658904297,
"learning_rate": 6.783811674679216e-06,
"loss": 0.4911,
"step": 830
},
{
"epoch": 0.44844253490870034,
"grad_norm": 2.4077776082559876,
"learning_rate": 6.7399299875185875e-06,
"loss": 0.4963,
"step": 835
},
{
"epoch": 0.45112781954887216,
"grad_norm": 2.3779199598320324,
"learning_rate": 6.695895283696691e-06,
"loss": 0.5014,
"step": 840
},
{
"epoch": 0.453813104189044,
"grad_norm": 2.3819440675964385,
"learning_rate": 6.651711435808061e-06,
"loss": 0.4919,
"step": 845
},
{
"epoch": 0.4564983888292159,
"grad_norm": 2.3042983128574055,
"learning_rate": 6.607382329563581e-06,
"loss": 0.5018,
"step": 850
},
{
"epoch": 0.45918367346938777,
"grad_norm": 2.3898486189900834,
"learning_rate": 6.562911863448752e-06,
"loss": 0.4895,
"step": 855
},
{
"epoch": 0.46186895810955964,
"grad_norm": 2.2310907658780796,
"learning_rate": 6.518303948380854e-06,
"loss": 0.4716,
"step": 860
},
{
"epoch": 0.46455424274973145,
"grad_norm": 2.330441405136215,
"learning_rate": 6.473562507364995e-06,
"loss": 0.4908,
"step": 865
},
{
"epoch": 0.4672395273899033,
"grad_norm": 2.3540604750111256,
"learning_rate": 6.428691475149107e-06,
"loss": 0.4927,
"step": 870
},
{
"epoch": 0.4699248120300752,
"grad_norm": 2.3418063700371317,
"learning_rate": 6.383694797877915e-06,
"loss": 0.4934,
"step": 875
},
{
"epoch": 0.47261009667024706,
"grad_norm": 2.4123703367373506,
"learning_rate": 6.338576432745891e-06,
"loss": 0.4807,
"step": 880
},
{
"epoch": 0.47529538131041893,
"grad_norm": 2.3995221539318976,
"learning_rate": 6.293340347649234e-06,
"loss": 0.473,
"step": 885
},
{
"epoch": 0.47798066595059074,
"grad_norm": 2.3050586922901153,
"learning_rate": 6.247990520836935e-06,
"loss": 0.4758,
"step": 890
},
{
"epoch": 0.4806659505907626,
"grad_norm": 2.3320878304798676,
"learning_rate": 6.202530940560897e-06,
"loss": 0.4755,
"step": 895
},
{
"epoch": 0.4833512352309345,
"grad_norm": 2.634905514274756,
"learning_rate": 6.156965604725202e-06,
"loss": 0.4873,
"step": 900
},
{
"epoch": 0.48603651987110635,
"grad_norm": 2.3310742683958927,
"learning_rate": 6.111298520534514e-06,
"loss": 0.4791,
"step": 905
},
{
"epoch": 0.48872180451127817,
"grad_norm": 2.4327937257979726,
"learning_rate": 6.065533704141666e-06,
"loss": 0.4817,
"step": 910
},
{
"epoch": 0.49140708915145004,
"grad_norm": 2.4924523181122837,
"learning_rate": 6.019675180294469e-06,
"loss": 0.4675,
"step": 915
},
{
"epoch": 0.4940923737916219,
"grad_norm": 2.2835219861581684,
"learning_rate": 5.973726981981756e-06,
"loss": 0.4899,
"step": 920
},
{
"epoch": 0.4967776584317938,
"grad_norm": 2.387787542241134,
"learning_rate": 5.9276931500787045e-06,
"loss": 0.4578,
"step": 925
},
{
"epoch": 0.49946294307196565,
"grad_norm": 2.4230757269856342,
"learning_rate": 5.8815777329914655e-06,
"loss": 0.4754,
"step": 930
},
{
"epoch": 0.5021482277121375,
"grad_norm": 2.2098938611260914,
"learning_rate": 5.83538478630113e-06,
"loss": 0.4658,
"step": 935
},
{
"epoch": 0.5048335123523093,
"grad_norm": 2.370395884409483,
"learning_rate": 5.789118372407061e-06,
"loss": 0.4644,
"step": 940
},
{
"epoch": 0.5075187969924813,
"grad_norm": 2.3045164969344434,
"learning_rate": 5.7427825601696376e-06,
"loss": 0.4468,
"step": 945
},
{
"epoch": 0.5102040816326531,
"grad_norm": 2.3192701854447018,
"learning_rate": 5.696381424552411e-06,
"loss": 0.4736,
"step": 950
},
{
"epoch": 0.5128893662728249,
"grad_norm": 2.312457744414422,
"learning_rate": 5.649919046263742e-06,
"loss": 0.5707,
"step": 955
},
{
"epoch": 0.5155746509129968,
"grad_norm": 2.243975997483289,
"learning_rate": 5.6033995113979336e-06,
"loss": 0.4506,
"step": 960
},
{
"epoch": 0.5182599355531686,
"grad_norm": 2.3613603860138657,
"learning_rate": 5.556826911075867e-06,
"loss": 0.4559,
"step": 965
},
{
"epoch": 0.5209452201933404,
"grad_norm": 2.356243424461813,
"learning_rate": 5.510205341085224e-06,
"loss": 0.4619,
"step": 970
},
{
"epoch": 0.5236305048335124,
"grad_norm": 2.28542532291045,
"learning_rate": 5.463538901520278e-06,
"loss": 0.4475,
"step": 975
},
{
"epoch": 0.5263157894736842,
"grad_norm": 2.5551015649940796,
"learning_rate": 5.416831696421325e-06,
"loss": 0.4565,
"step": 980
},
{
"epoch": 0.5290010741138561,
"grad_norm": 2.3941643466309404,
"learning_rate": 5.370087833413747e-06,
"loss": 0.462,
"step": 985
},
{
"epoch": 0.5316863587540279,
"grad_norm": 2.32017339568476,
"learning_rate": 5.323311423346775e-06,
"loss": 0.4443,
"step": 990
},
{
"epoch": 0.5343716433941997,
"grad_norm": 2.3845713293199826,
"learning_rate": 5.2765065799319646e-06,
"loss": 0.4579,
"step": 995
},
{
"epoch": 0.5370569280343717,
"grad_norm": 2.337943421964321,
"learning_rate": 5.229677419381417e-06,
"loss": 0.4451,
"step": 1000
},
{
"epoch": 0.5397422126745435,
"grad_norm": 2.464019322142833,
"learning_rate": 5.182828060045783e-06,
"loss": 0.4413,
"step": 1005
},
{
"epoch": 0.5424274973147154,
"grad_norm": 2.3241287449791592,
"learning_rate": 5.1359626220520804e-06,
"loss": 0.4479,
"step": 1010
},
{
"epoch": 0.5451127819548872,
"grad_norm": 2.271173118448707,
"learning_rate": 5.08908522694135e-06,
"loss": 0.4415,
"step": 1015
},
{
"epoch": 0.547798066595059,
"grad_norm": 2.489225550910605,
"learning_rate": 5.042199997306185e-06,
"loss": 0.4539,
"step": 1020
},
{
"epoch": 0.550483351235231,
"grad_norm": 2.2582284318591284,
"learning_rate": 4.995311056428192e-06,
"loss": 0.4539,
"step": 1025
},
{
"epoch": 0.5531686358754028,
"grad_norm": 2.2517978124456186,
"learning_rate": 4.948422527915348e-06,
"loss": 0.4484,
"step": 1030
},
{
"epoch": 0.5558539205155747,
"grad_norm": 2.310635339975432,
"learning_rate": 4.901538535339369e-06,
"loss": 0.4479,
"step": 1035
},
{
"epoch": 0.5585392051557465,
"grad_norm": 2.2076803900499264,
"learning_rate": 4.854663201873066e-06,
"loss": 0.4372,
"step": 1040
},
{
"epoch": 0.5612244897959183,
"grad_norm": 2.24361897412377,
"learning_rate": 4.807800649927723e-06,
"loss": 0.4389,
"step": 1045
},
{
"epoch": 0.5639097744360902,
"grad_norm": 2.1387839547724115,
"learning_rate": 4.760955000790572e-06,
"loss": 0.4338,
"step": 1050
},
{
"epoch": 0.5665950590762621,
"grad_norm": 2.2757758143291915,
"learning_rate": 4.714130374262339e-06,
"loss": 0.4366,
"step": 1055
},
{
"epoch": 0.569280343716434,
"grad_norm": 2.424393738390714,
"learning_rate": 4.667330888294934e-06,
"loss": 0.4274,
"step": 1060
},
{
"epoch": 0.5719656283566058,
"grad_norm": 2.274712388704807,
"learning_rate": 4.620560658629303e-06,
"loss": 0.4272,
"step": 1065
},
{
"epoch": 0.5746509129967776,
"grad_norm": 2.1856658672559575,
"learning_rate": 4.573823798433469e-06,
"loss": 0.4227,
"step": 1070
},
{
"epoch": 0.5773361976369495,
"grad_norm": 2.282369263325665,
"learning_rate": 4.527124417940812e-06,
"loss": 0.4165,
"step": 1075
},
{
"epoch": 0.5800214822771214,
"grad_norm": 2.200834408712462,
"learning_rate": 4.48046662408858e-06,
"loss": 0.4309,
"step": 1080
},
{
"epoch": 0.5827067669172933,
"grad_norm": 2.2059452770785457,
"learning_rate": 4.43385452015673e-06,
"loss": 0.4164,
"step": 1085
},
{
"epoch": 0.5853920515574651,
"grad_norm": 2.312194553489542,
"learning_rate": 4.387292205407055e-06,
"loss": 0.4409,
"step": 1090
},
{
"epoch": 0.5880773361976369,
"grad_norm": 2.2293120169589846,
"learning_rate": 4.3407837747226765e-06,
"loss": 0.4275,
"step": 1095
},
{
"epoch": 0.5907626208378088,
"grad_norm": 2.3047018034890163,
"learning_rate": 4.29433331824793e-06,
"loss": 0.4332,
"step": 1100
},
{
"epoch": 0.5934479054779807,
"grad_norm": 2.2626746293791418,
"learning_rate": 4.247944921028663e-06,
"loss": 0.4148,
"step": 1105
},
{
"epoch": 0.5961331901181526,
"grad_norm": 2.2531921338434904,
"learning_rate": 4.201622662652972e-06,
"loss": 0.4209,
"step": 1110
},
{
"epoch": 0.5988184747583244,
"grad_norm": 2.2373280335624703,
"learning_rate": 4.155370616892422e-06,
"loss": 0.4311,
"step": 1115
},
{
"epoch": 0.6015037593984962,
"grad_norm": 2.2553139742929553,
"learning_rate": 4.1091928513438005e-06,
"loss": 0.4257,
"step": 1120
},
{
"epoch": 0.6041890440386681,
"grad_norm": 2.2958062385600506,
"learning_rate": 4.063093427071376e-06,
"loss": 0.416,
"step": 1125
},
{
"epoch": 0.60687432867884,
"grad_norm": 2.3216604662037454,
"learning_rate": 4.0170763982497716e-06,
"loss": 0.422,
"step": 1130
},
{
"epoch": 0.6095596133190118,
"grad_norm": 2.2400135188380363,
"learning_rate": 3.971145811807397e-06,
"loss": 0.4043,
"step": 1135
},
{
"epoch": 0.6122448979591837,
"grad_norm": 2.250180111293208,
"learning_rate": 3.925305707070572e-06,
"loss": 0.4293,
"step": 1140
},
{
"epoch": 0.6149301825993555,
"grad_norm": 2.308237077571672,
"learning_rate": 3.879560115408279e-06,
"loss": 0.4124,
"step": 1145
},
{
"epoch": 0.6176154672395274,
"grad_norm": 2.2251177373468094,
"learning_rate": 3.833913059877622e-06,
"loss": 0.4021,
"step": 1150
},
{
"epoch": 0.6203007518796992,
"grad_norm": 2.354334150849922,
"learning_rate": 3.788368554870034e-06,
"loss": 0.4203,
"step": 1155
},
{
"epoch": 0.6229860365198711,
"grad_norm": 2.3534708581260966,
"learning_rate": 3.7429306057582306e-06,
"loss": 0.4189,
"step": 1160
},
{
"epoch": 0.625671321160043,
"grad_norm": 2.172702227946957,
"learning_rate": 3.6976032085439563e-06,
"loss": 0.4149,
"step": 1165
},
{
"epoch": 0.6283566058002148,
"grad_norm": 2.2243856540084144,
"learning_rate": 3.6523903495065634e-06,
"loss": 0.3989,
"step": 1170
},
{
"epoch": 0.6310418904403867,
"grad_norm": 2.355514273752082,
"learning_rate": 3.6072960048524443e-06,
"loss": 0.4087,
"step": 1175
},
{
"epoch": 0.6337271750805585,
"grad_norm": 2.410723268973216,
"learning_rate": 3.562324140365343e-06,
"loss": 0.4202,
"step": 1180
},
{
"epoch": 0.6364124597207304,
"grad_norm": 2.231092942225664,
"learning_rate": 3.5174787110575904e-06,
"loss": 0.4077,
"step": 1185
},
{
"epoch": 0.6390977443609023,
"grad_norm": 2.251639598468074,
"learning_rate": 3.4727636608222813e-06,
"loss": 0.4045,
"step": 1190
},
{
"epoch": 0.6417830290010741,
"grad_norm": 2.300599200707737,
"learning_rate": 3.428182922086437e-06,
"loss": 0.416,
"step": 1195
},
{
"epoch": 0.644468313641246,
"grad_norm": 2.2895401157361213,
"learning_rate": 3.3837404154651677e-06,
"loss": 0.3996,
"step": 1200
},
{
"epoch": 0.6471535982814178,
"grad_norm": 2.144456039496495,
"learning_rate": 3.3394400494168745e-06,
"loss": 0.3936,
"step": 1205
},
{
"epoch": 0.6498388829215896,
"grad_norm": 2.3475018658103073,
"learning_rate": 3.2952857198995304e-06,
"loss": 0.3962,
"step": 1210
},
{
"epoch": 0.6525241675617616,
"grad_norm": 2.127548111149732,
"learning_rate": 3.2512813100280494e-06,
"loss": 0.396,
"step": 1215
},
{
"epoch": 0.6552094522019334,
"grad_norm": 2.2512911777556734,
"learning_rate": 3.2074306897327913e-06,
"loss": 0.3944,
"step": 1220
},
{
"epoch": 0.6578947368421053,
"grad_norm": 2.2652114439392017,
"learning_rate": 3.163737715419216e-06,
"loss": 0.3975,
"step": 1225
},
{
"epoch": 0.6605800214822771,
"grad_norm": 2.370455056617469,
"learning_rate": 3.1202062296287507e-06,
"loss": 0.4055,
"step": 1230
},
{
"epoch": 0.6632653061224489,
"grad_norm": 2.3834169278378234,
"learning_rate": 3.076840060700848e-06,
"loss": 0.4022,
"step": 1235
},
{
"epoch": 0.6659505907626209,
"grad_norm": 2.1507706926710206,
"learning_rate": 3.0336430224363067e-06,
"loss": 0.3991,
"step": 1240
},
{
"epoch": 0.6686358754027927,
"grad_norm": 2.4152686550811064,
"learning_rate": 2.990618913761876e-06,
"loss": 0.3902,
"step": 1245
},
{
"epoch": 0.6713211600429646,
"grad_norm": 2.336992344342627,
"learning_rate": 2.9477715183961634e-06,
"loss": 0.3979,
"step": 1250
},
{
"epoch": 0.6740064446831364,
"grad_norm": 2.3915302043954663,
"learning_rate": 2.905104604516872e-06,
"loss": 0.3798,
"step": 1255
},
{
"epoch": 0.6766917293233082,
"grad_norm": 2.254228693512719,
"learning_rate": 2.8626219244294074e-06,
"loss": 0.3936,
"step": 1260
},
{
"epoch": 0.6793770139634802,
"grad_norm": 2.165272848642074,
"learning_rate": 2.820327214236904e-06,
"loss": 0.3896,
"step": 1265
},
{
"epoch": 0.682062298603652,
"grad_norm": 2.4069092663220526,
"learning_rate": 2.7782241935116337e-06,
"loss": 0.3915,
"step": 1270
},
{
"epoch": 0.6847475832438239,
"grad_norm": 2.087308124871399,
"learning_rate": 2.7363165649679045e-06,
"loss": 0.3651,
"step": 1275
},
{
"epoch": 0.6874328678839957,
"grad_norm": 2.1470996155750575,
"learning_rate": 2.6946080141364295e-06,
"loss": 0.373,
"step": 1280
},
{
"epoch": 0.6901181525241675,
"grad_norm": 2.0260043604392175,
"learning_rate": 2.6531022090401946e-06,
"loss": 0.3838,
"step": 1285
},
{
"epoch": 0.6928034371643395,
"grad_norm": 2.112100193147629,
"learning_rate": 2.611802799871893e-06,
"loss": 0.3896,
"step": 1290
},
{
"epoch": 0.6954887218045113,
"grad_norm": 2.1596388125789536,
"learning_rate": 2.570713418672893e-06,
"loss": 0.3817,
"step": 1295
},
{
"epoch": 0.6981740064446831,
"grad_norm": 2.19128088827635,
"learning_rate": 2.529837679013841e-06,
"loss": 0.3829,
"step": 1300
},
{
"epoch": 0.700859291084855,
"grad_norm": 2.3174479805406882,
"learning_rate": 2.4891791756768587e-06,
"loss": 0.3855,
"step": 1305
},
{
"epoch": 0.7035445757250268,
"grad_norm": 2.1371440222674174,
"learning_rate": 2.4487414843394015e-06,
"loss": 0.3767,
"step": 1310
},
{
"epoch": 0.7062298603651987,
"grad_norm": 2.177549891184113,
"learning_rate": 2.4085281612598027e-06,
"loss": 0.3786,
"step": 1315
},
{
"epoch": 0.7089151450053706,
"grad_norm": 2.19679570444429,
"learning_rate": 2.368542742964519e-06,
"loss": 0.3861,
"step": 1320
},
{
"epoch": 0.7116004296455424,
"grad_norm": 2.400992903154791,
"learning_rate": 2.3287887459371193e-06,
"loss": 0.3821,
"step": 1325
},
{
"epoch": 0.7142857142857143,
"grad_norm": 2.3003498290947566,
"learning_rate": 2.2892696663090223e-06,
"loss": 0.3707,
"step": 1330
},
{
"epoch": 0.7169709989258861,
"grad_norm": 2.225143419133614,
"learning_rate": 2.2499889795520342e-06,
"loss": 0.3699,
"step": 1335
},
{
"epoch": 0.719656283566058,
"grad_norm": 2.182273951597591,
"learning_rate": 2.2109501401727097e-06,
"loss": 0.3904,
"step": 1340
},
{
"epoch": 0.7223415682062299,
"grad_norm": 2.21198794915305,
"learning_rate": 2.1721565814085355e-06,
"loss": 0.3728,
"step": 1345
},
{
"epoch": 0.7250268528464017,
"grad_norm": 2.023179303222013,
"learning_rate": 2.133611714926005e-06,
"loss": 0.3786,
"step": 1350
},
{
"epoch": 0.7277121374865736,
"grad_norm": 2.0061512767744953,
"learning_rate": 2.0953189305205847e-06,
"loss": 0.3641,
"step": 1355
},
{
"epoch": 0.7303974221267454,
"grad_norm": 2.171071173479305,
"learning_rate": 2.057281595818592e-06,
"loss": 0.3627,
"step": 1360
},
{
"epoch": 0.7330827067669173,
"grad_norm": 2.241339270453543,
"learning_rate": 2.0195030559810387e-06,
"loss": 0.3726,
"step": 1365
},
{
"epoch": 0.7357679914070892,
"grad_norm": 2.1344279068039027,
"learning_rate": 1.981986633409447e-06,
"loss": 0.3712,
"step": 1370
},
{
"epoch": 0.738453276047261,
"grad_norm": 2.163696384884419,
"learning_rate": 1.944735627453654e-06,
"loss": 0.3714,
"step": 1375
},
{
"epoch": 0.7411385606874329,
"grad_norm": 2.22057253802534,
"learning_rate": 1.907753314121662e-06,
"loss": 0.3751,
"step": 1380
},
{
"epoch": 0.7438238453276047,
"grad_norm": 2.1351657116142007,
"learning_rate": 1.8710429457915269e-06,
"loss": 0.3775,
"step": 1385
},
{
"epoch": 0.7465091299677766,
"grad_norm": 2.217214143261465,
"learning_rate": 1.834607750925333e-06,
"loss": 0.374,
"step": 1390
},
{
"epoch": 0.7491944146079484,
"grad_norm": 2.0708659017448263,
"learning_rate": 1.7984509337852724e-06,
"loss": 0.3639,
"step": 1395
},
{
"epoch": 0.7518796992481203,
"grad_norm": 2.0456629306105625,
"learning_rate": 1.7625756741518407e-06,
"loss": 0.3623,
"step": 1400
},
{
"epoch": 0.7545649838882922,
"grad_norm": 2.0672183752253646,
"learning_rate": 1.7269851270441978e-06,
"loss": 0.3642,
"step": 1405
},
{
"epoch": 0.757250268528464,
"grad_norm": 2.5296565959634627,
"learning_rate": 1.6916824224427098e-06,
"loss": 0.3687,
"step": 1410
},
{
"epoch": 0.7599355531686359,
"grad_norm": 2.362083067895626,
"learning_rate": 1.6566706650136704e-06,
"loss": 0.3703,
"step": 1415
},
{
"epoch": 0.7626208378088077,
"grad_norm": 2.025587816341609,
"learning_rate": 1.6219529338362756e-06,
"loss": 0.372,
"step": 1420
},
{
"epoch": 0.7653061224489796,
"grad_norm": 2.2100412754278875,
"learning_rate": 1.587532282131835e-06,
"loss": 0.3601,
"step": 1425
},
{
"epoch": 0.7679914070891515,
"grad_norm": 2.099345141591793,
"learning_rate": 1.5534117369952523e-06,
"loss": 0.3648,
"step": 1430
},
{
"epoch": 0.7706766917293233,
"grad_norm": 2.165307327151688,
"learning_rate": 1.5195942991288214e-06,
"loss": 0.3603,
"step": 1435
},
{
"epoch": 0.7733619763694952,
"grad_norm": 2.2867351350138616,
"learning_rate": 1.4860829425783151e-06,
"loss": 0.3738,
"step": 1440
},
{
"epoch": 0.776047261009667,
"grad_norm": 2.0144904930374126,
"learning_rate": 1.4528806144714546e-06,
"loss": 0.3575,
"step": 1445
},
{
"epoch": 0.7787325456498388,
"grad_norm": 2.073630490862424,
"learning_rate": 1.4199902347587186e-06,
"loss": 0.36,
"step": 1450
},
{
"epoch": 0.7814178302900108,
"grad_norm": 2.255236821273668,
"learning_rate": 1.3874146959565387e-06,
"loss": 0.3652,
"step": 1455
},
{
"epoch": 0.7841031149301826,
"grad_norm": 2.105473936710428,
"learning_rate": 1.3551568628929434e-06,
"loss": 0.3643,
"step": 1460
},
{
"epoch": 0.7867883995703545,
"grad_norm": 2.123383620300908,
"learning_rate": 1.3232195724555919e-06,
"loss": 0.3474,
"step": 1465
},
{
"epoch": 0.7894736842105263,
"grad_norm": 2.166678103799633,
"learning_rate": 1.291605633342301e-06,
"loss": 0.3445,
"step": 1470
},
{
"epoch": 0.7921589688506981,
"grad_norm": 2.172080523120847,
"learning_rate": 1.2603178258140264e-06,
"loss": 0.3603,
"step": 1475
},
{
"epoch": 0.7948442534908701,
"grad_norm": 1.9987808693365328,
"learning_rate": 1.22935890145036e-06,
"loss": 0.3452,
"step": 1480
},
{
"epoch": 0.7975295381310419,
"grad_norm": 2.085350965759781,
"learning_rate": 1.198731582907547e-06,
"loss": 0.3632,
"step": 1485
},
{
"epoch": 0.8002148227712137,
"grad_norm": 2.1571884689811935,
"learning_rate": 1.1684385636790368e-06,
"loss": 0.352,
"step": 1490
},
{
"epoch": 0.8029001074113856,
"grad_norm": 2.2199306995675157,
"learning_rate": 1.1384825078586114e-06,
"loss": 0.3643,
"step": 1495
},
{
"epoch": 0.8055853920515574,
"grad_norm": 2.0910740409401583,
"learning_rate": 1.108866049906096e-06,
"loss": 0.3547,
"step": 1500
},
{
"epoch": 0.8082706766917294,
"grad_norm": 2.1293324067907444,
"learning_rate": 1.079591794415667e-06,
"loss": 0.3653,
"step": 1505
},
{
"epoch": 0.8109559613319012,
"grad_norm": 1.9778580971514406,
"learning_rate": 1.0506623158867952e-06,
"loss": 0.3582,
"step": 1510
},
{
"epoch": 0.813641245972073,
"grad_norm": 2.028637968721407,
"learning_rate": 1.0220801584978408e-06,
"loss": 0.3428,
"step": 1515
},
{
"epoch": 0.8163265306122449,
"grad_norm": 1.9402937539604412,
"learning_rate": 9.93847835882296e-07,
"loss": 0.3517,
"step": 1520
},
{
"epoch": 0.8190118152524167,
"grad_norm": 2.142441029769215,
"learning_rate": 9.659678309077374e-07,
"loss": 0.3483,
"step": 1525
},
{
"epoch": 0.8216970998925887,
"grad_norm": 2.15067736344149,
"learning_rate": 9.384425954574617e-07,
"loss": 0.3439,
"step": 1530
},
{
"epoch": 0.8243823845327605,
"grad_norm": 2.026028998610704,
"learning_rate": 9.112745502148629e-07,
"loss": 0.3457,
"step": 1535
},
{
"epoch": 0.8270676691729323,
"grad_norm": 2.1915001000999856,
"learning_rate": 8.844660844505498e-07,
"loss": 0.349,
"step": 1540
},
{
"epoch": 0.8297529538131042,
"grad_norm": 2.1199655511504805,
"learning_rate": 8.580195558122167e-07,
"loss": 0.3564,
"step": 1545
},
{
"epoch": 0.832438238453276,
"grad_norm": 2.151498859311399,
"learning_rate": 8.319372901173045e-07,
"loss": 0.3569,
"step": 1550
},
{
"epoch": 0.835123523093448,
"grad_norm": 2.00708607078457,
"learning_rate": 8.062215811484652e-07,
"loss": 0.3376,
"step": 1555
},
{
"epoch": 0.8378088077336198,
"grad_norm": 2.078669088279395,
"learning_rate": 7.808746904518261e-07,
"loss": 0.3564,
"step": 1560
},
{
"epoch": 0.8404940923737916,
"grad_norm": 1.9966152127777401,
"learning_rate": 7.558988471381063e-07,
"loss": 0.3452,
"step": 1565
},
{
"epoch": 0.8431793770139635,
"grad_norm": 1.9730936813082844,
"learning_rate": 7.312962476865831e-07,
"loss": 0.3397,
"step": 1570
},
{
"epoch": 0.8458646616541353,
"grad_norm": 2.1210106539433533,
"learning_rate": 7.070690557519139e-07,
"loss": 0.3519,
"step": 1575
},
{
"epoch": 0.8485499462943072,
"grad_norm": 2.005129568791031,
"learning_rate": 6.832194019738686e-07,
"loss": 0.3429,
"step": 1580
},
{
"epoch": 0.8512352309344791,
"grad_norm": 2.0717199936092503,
"learning_rate": 6.597493837899377e-07,
"loss": 0.3485,
"step": 1585
},
{
"epoch": 0.8539205155746509,
"grad_norm": 2.1194492918650023,
"learning_rate": 6.366610652508875e-07,
"loss": 0.3461,
"step": 1590
},
{
"epoch": 0.8566058002148228,
"grad_norm": 1.9539012346236104,
"learning_rate": 6.13956476839237e-07,
"loss": 0.3498,
"step": 1595
},
{
"epoch": 0.8592910848549946,
"grad_norm": 1.8596630660949547,
"learning_rate": 5.916376152906761e-07,
"loss": 0.3469,
"step": 1600
},
{
"epoch": 0.8619763694951665,
"grad_norm": 2.3202167511582923,
"learning_rate": 5.697064434184835e-07,
"loss": 0.3464,
"step": 1605
},
{
"epoch": 0.8646616541353384,
"grad_norm": 2.1094098610703003,
"learning_rate": 5.481648899408943e-07,
"loss": 0.3427,
"step": 1610
},
{
"epoch": 0.8673469387755102,
"grad_norm": 1.9183803711537597,
"learning_rate": 5.270148493114896e-07,
"loss": 0.3552,
"step": 1615
},
{
"epoch": 0.8700322234156821,
"grad_norm": 1.9373953545925435,
"learning_rate": 5.062581815525819e-07,
"loss": 0.3426,
"step": 1620
},
{
"epoch": 0.8727175080558539,
"grad_norm": 2.1256232990594066,
"learning_rate": 4.858967120916436e-07,
"loss": 0.3454,
"step": 1625
},
{
"epoch": 0.8754027926960258,
"grad_norm": 2.075516281907829,
"learning_rate": 4.659322316007714e-07,
"loss": 0.3507,
"step": 1630
},
{
"epoch": 0.8780880773361976,
"grad_norm": 2.272064974411147,
"learning_rate": 4.463664958392017e-07,
"loss": 0.3549,
"step": 1635
},
{
"epoch": 0.8807733619763695,
"grad_norm": 2.0144845164750476,
"learning_rate": 4.2720122549890607e-07,
"loss": 0.3382,
"step": 1640
},
{
"epoch": 0.8834586466165414,
"grad_norm": 1.9797033177279142,
"learning_rate": 4.084381060532672e-07,
"loss": 0.3373,
"step": 1645
},
{
"epoch": 0.8861439312567132,
"grad_norm": 2.224282029664362,
"learning_rate": 3.9007878760884856e-07,
"loss": 0.3501,
"step": 1650
},
{
"epoch": 0.888829215896885,
"grad_norm": 2.08709377887094,
"learning_rate": 3.721248847602771e-07,
"loss": 0.3339,
"step": 1655
},
{
"epoch": 0.8915145005370569,
"grad_norm": 1.9285645160582954,
"learning_rate": 3.5457797644825376e-07,
"loss": 0.3373,
"step": 1660
},
{
"epoch": 0.8941997851772288,
"grad_norm": 2.0209517153428034,
"learning_rate": 3.3743960582068745e-07,
"loss": 0.325,
"step": 1665
},
{
"epoch": 0.8968850698174007,
"grad_norm": 2.0658672212016906,
"learning_rate": 3.207112800969925e-07,
"loss": 0.3437,
"step": 1670
},
{
"epoch": 0.8995703544575725,
"grad_norm": 2.1512568166619412,
"learning_rate": 3.0439447043553005e-07,
"loss": 0.3503,
"step": 1675
},
{
"epoch": 0.9022556390977443,
"grad_norm": 2.2252938500393626,
"learning_rate": 2.884906118042313e-07,
"loss": 0.3433,
"step": 1680
},
{
"epoch": 0.9049409237379162,
"grad_norm": 1.9450802863352654,
"learning_rate": 2.730011028544044e-07,
"loss": 0.3423,
"step": 1685
},
{
"epoch": 0.907626208378088,
"grad_norm": 2.065707260844985,
"learning_rate": 2.579273057977244e-07,
"loss": 0.343,
"step": 1690
},
{
"epoch": 0.91031149301826,
"grad_norm": 2.117471910952635,
"learning_rate": 2.4327054628643764e-07,
"loss": 0.3414,
"step": 1695
},
{
"epoch": 0.9129967776584318,
"grad_norm": 1.9430680169627381,
"learning_rate": 2.29032113296781e-07,
"loss": 0.3469,
"step": 1700
},
{
"epoch": 0.9156820622986036,
"grad_norm": 2.0502070545950626,
"learning_rate": 2.1521325901561918e-07,
"loss": 0.3434,
"step": 1705
},
{
"epoch": 0.9183673469387755,
"grad_norm": 1.9323796972970009,
"learning_rate": 2.018151987303263e-07,
"loss": 0.3389,
"step": 1710
},
{
"epoch": 0.9210526315789473,
"grad_norm": 2.100572047126027,
"learning_rate": 1.8883911072190619e-07,
"loss": 0.3423,
"step": 1715
},
{
"epoch": 0.9237379162191193,
"grad_norm": 2.056180712445984,
"learning_rate": 1.7628613616137048e-07,
"loss": 0.3334,
"step": 1720
},
{
"epoch": 0.9264232008592911,
"grad_norm": 1.9023383366215192,
"learning_rate": 1.6415737900937811e-07,
"loss": 0.3458,
"step": 1725
},
{
"epoch": 0.9291084854994629,
"grad_norm": 2.0530711536344257,
"learning_rate": 1.5245390591914877e-07,
"loss": 0.3438,
"step": 1730
},
{
"epoch": 0.9317937701396348,
"grad_norm": 2.2102378955284507,
"learning_rate": 1.4117674614265885e-07,
"loss": 0.3433,
"step": 1735
},
{
"epoch": 0.9344790547798066,
"grad_norm": 2.207161004371043,
"learning_rate": 1.3032689144012457e-07,
"loss": 0.3522,
"step": 1740
},
{
"epoch": 0.9371643394199786,
"grad_norm": 1.9905994793772492,
"learning_rate": 1.1990529599277656e-07,
"loss": 0.3326,
"step": 1745
},
{
"epoch": 0.9398496240601504,
"grad_norm": 2.0584452458406775,
"learning_rate": 1.0991287631895498e-07,
"loss": 0.3403,
"step": 1750
},
{
"epoch": 0.9425349087003222,
"grad_norm": 2.0242292696461424,
"learning_rate": 1.0035051119349881e-07,
"loss": 0.3272,
"step": 1755
},
{
"epoch": 0.9452201933404941,
"grad_norm": 2.011726742194304,
"learning_rate": 9.121904157046779e-08,
"loss": 0.3374,
"step": 1760
},
{
"epoch": 0.9479054779806659,
"grad_norm": 2.038558298106363,
"learning_rate": 8.251927050918262e-08,
"loss": 0.3471,
"step": 1765
},
{
"epoch": 0.9505907626208379,
"grad_norm": 2.068707550995904,
"learning_rate": 7.425196310360094e-08,
"loss": 0.331,
"step": 1770
},
{
"epoch": 0.9532760472610097,
"grad_norm": 2.1678970025064817,
"learning_rate": 6.64178464150339e-08,
"loss": 0.3446,
"step": 1775
},
{
"epoch": 0.9559613319011815,
"grad_norm": 2.0378128563489715,
"learning_rate": 5.9017609408203445e-08,
"loss": 0.3377,
"step": 1780
},
{
"epoch": 0.9586466165413534,
"grad_norm": 1.965229547995082,
"learning_rate": 5.2051902890651316e-08,
"loss": 0.334,
"step": 1785
},
{
"epoch": 0.9613319011815252,
"grad_norm": 1.9286453240978654,
"learning_rate": 4.5521339455507075e-08,
"loss": 0.3408,
"step": 1790
},
{
"epoch": 0.9640171858216972,
"grad_norm": 1.9918772283562163,
"learning_rate": 3.9426493427611177e-08,
"loss": 0.3413,
"step": 1795
},
{
"epoch": 0.966702470461869,
"grad_norm": 1.9428865966324997,
"learning_rate": 3.3767900813007623e-08,
"loss": 0.3374,
"step": 1800
},
{
"epoch": 0.9693877551020408,
"grad_norm": 1.8964808172463887,
"learning_rate": 2.8546059251806092e-08,
"loss": 0.3365,
"step": 1805
},
{
"epoch": 0.9720730397422127,
"grad_norm": 2.090051081282145,
"learning_rate": 2.3761427974416383e-08,
"loss": 0.3433,
"step": 1810
},
{
"epoch": 0.9747583243823845,
"grad_norm": 2.0777864096193,
"learning_rate": 1.9414427761162423e-08,
"loss": 0.3434,
"step": 1815
},
{
"epoch": 0.9774436090225563,
"grad_norm": 1.938379416201655,
"learning_rate": 1.5505440905276835e-08,
"loss": 0.34,
"step": 1820
},
{
"epoch": 0.9801288936627283,
"grad_norm": 2.1816688655707446,
"learning_rate": 1.203481117928007e-08,
"loss": 0.3421,
"step": 1825
},
{
"epoch": 0.9828141783029001,
"grad_norm": 2.215005685012668,
"learning_rate": 9.002843804748473e-09,
"loss": 0.3424,
"step": 1830
},
{
"epoch": 0.985499462943072,
"grad_norm": 1.9595027005248324,
"learning_rate": 6.409805425470761e-09,
"loss": 0.3436,
"step": 1835
},
{
"epoch": 0.9881847475832438,
"grad_norm": 1.958542069219831,
"learning_rate": 4.255924083999552e-09,
"loss": 0.3357,
"step": 1840
},
{
"epoch": 0.9908700322234156,
"grad_norm": 1.952371770337845,
"learning_rate": 2.5413892015951903e-09,
"loss": 0.3301,
"step": 1845
},
{
"epoch": 0.9935553168635876,
"grad_norm": 1.942753364149899,
"learning_rate": 1.266351561568513e-09,
"loss": 0.3409,
"step": 1850
},
{
"epoch": 0.9962406015037594,
"grad_norm": 2.0122123484343004,
"learning_rate": 4.3092329601923664e-10,
"loss": 0.3361,
"step": 1855
},
{
"epoch": 0.9989258861439313,
"grad_norm": 1.9846539012340674,
"learning_rate": 3.517787597440148e-11,
"loss": 0.3341,
"step": 1860
},
{
"epoch": 1.0,
"eval_runtime": 3.5565,
"eval_samples_per_second": 2.812,
"eval_steps_per_second": 0.844,
"step": 1862
},
{
"epoch": 1.0,
"step": 1862,
"total_flos": 194932459438080.0,
"train_loss": 0.5024159621731423,
"train_runtime": 16684.743,
"train_samples_per_second": 1.785,
"train_steps_per_second": 0.112
}
],
"logging_steps": 5,
"max_steps": 1862,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 194932459438080.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}