terry69's picture
Model save
f102f1b verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1871,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005344735435595938,
"grad_norm": 23.507986949982357,
"learning_rate": 5.319148936170213e-08,
"loss": 1.3627,
"step": 1
},
{
"epoch": 0.002672367717797969,
"grad_norm": 24.598576624276674,
"learning_rate": 2.6595744680851066e-07,
"loss": 1.3643,
"step": 5
},
{
"epoch": 0.005344735435595938,
"grad_norm": 15.530437303954583,
"learning_rate": 5.319148936170213e-07,
"loss": 1.3005,
"step": 10
},
{
"epoch": 0.008017103153393906,
"grad_norm": 11.93570126602586,
"learning_rate": 7.97872340425532e-07,
"loss": 1.1426,
"step": 15
},
{
"epoch": 0.010689470871191877,
"grad_norm": 6.9247543710518755,
"learning_rate": 1.0638297872340427e-06,
"loss": 1.0451,
"step": 20
},
{
"epoch": 0.013361838588989846,
"grad_norm": 3.4948052388946684,
"learning_rate": 1.3297872340425533e-06,
"loss": 0.9516,
"step": 25
},
{
"epoch": 0.016034206306787813,
"grad_norm": 3.5201446031892276,
"learning_rate": 1.595744680851064e-06,
"loss": 0.9042,
"step": 30
},
{
"epoch": 0.01870657402458578,
"grad_norm": 3.1131527320445778,
"learning_rate": 1.8617021276595745e-06,
"loss": 0.8847,
"step": 35
},
{
"epoch": 0.021378941742383754,
"grad_norm": 2.9333140907797937,
"learning_rate": 2.1276595744680853e-06,
"loss": 0.8717,
"step": 40
},
{
"epoch": 0.024051309460181722,
"grad_norm": 2.9373547357915273,
"learning_rate": 2.393617021276596e-06,
"loss": 0.8444,
"step": 45
},
{
"epoch": 0.02672367717797969,
"grad_norm": 3.0434311643420258,
"learning_rate": 2.6595744680851065e-06,
"loss": 0.8476,
"step": 50
},
{
"epoch": 0.02939604489577766,
"grad_norm": 2.9261239025852217,
"learning_rate": 2.9255319148936174e-06,
"loss": 0.8295,
"step": 55
},
{
"epoch": 0.032068412613575625,
"grad_norm": 3.0196930160596893,
"learning_rate": 3.191489361702128e-06,
"loss": 0.8092,
"step": 60
},
{
"epoch": 0.034740780331373594,
"grad_norm": 2.953469559874637,
"learning_rate": 3.457446808510639e-06,
"loss": 0.8012,
"step": 65
},
{
"epoch": 0.03741314804917156,
"grad_norm": 3.0685327832852014,
"learning_rate": 3.723404255319149e-06,
"loss": 0.7975,
"step": 70
},
{
"epoch": 0.04008551576696953,
"grad_norm": 3.279803777889419,
"learning_rate": 3.98936170212766e-06,
"loss": 0.7816,
"step": 75
},
{
"epoch": 0.04275788348476751,
"grad_norm": 3.1622522025196917,
"learning_rate": 4.255319148936171e-06,
"loss": 0.7824,
"step": 80
},
{
"epoch": 0.045430251202565476,
"grad_norm": 3.330650508238122,
"learning_rate": 4.521276595744681e-06,
"loss": 0.7695,
"step": 85
},
{
"epoch": 0.048102618920363445,
"grad_norm": 3.0704520451142225,
"learning_rate": 4.787234042553192e-06,
"loss": 0.7599,
"step": 90
},
{
"epoch": 0.050774986638161414,
"grad_norm": 3.101237960822243,
"learning_rate": 5.053191489361703e-06,
"loss": 0.7624,
"step": 95
},
{
"epoch": 0.05344735435595938,
"grad_norm": 3.1576030248912685,
"learning_rate": 5.319148936170213e-06,
"loss": 0.755,
"step": 100
},
{
"epoch": 0.05611972207375735,
"grad_norm": 3.1375152439302916,
"learning_rate": 5.5851063829787235e-06,
"loss": 0.7509,
"step": 105
},
{
"epoch": 0.05879208979155532,
"grad_norm": 3.347681082742772,
"learning_rate": 5.851063829787235e-06,
"loss": 0.7342,
"step": 110
},
{
"epoch": 0.06146445750935329,
"grad_norm": 3.0581130126710936,
"learning_rate": 6.117021276595745e-06,
"loss": 0.7445,
"step": 115
},
{
"epoch": 0.06413682522715125,
"grad_norm": 3.6835459139257436,
"learning_rate": 6.382978723404256e-06,
"loss": 0.7373,
"step": 120
},
{
"epoch": 0.06680919294494922,
"grad_norm": 3.001290017186477,
"learning_rate": 6.648936170212767e-06,
"loss": 0.7199,
"step": 125
},
{
"epoch": 0.06948156066274719,
"grad_norm": 3.166549369566557,
"learning_rate": 6.914893617021278e-06,
"loss": 0.7302,
"step": 130
},
{
"epoch": 0.07215392838054516,
"grad_norm": 2.976825714448153,
"learning_rate": 7.1808510638297875e-06,
"loss": 0.7151,
"step": 135
},
{
"epoch": 0.07482629609834313,
"grad_norm": 10.46792607372931,
"learning_rate": 7.446808510638298e-06,
"loss": 0.735,
"step": 140
},
{
"epoch": 0.0774986638161411,
"grad_norm": 2.9937659410364366,
"learning_rate": 7.71276595744681e-06,
"loss": 0.7216,
"step": 145
},
{
"epoch": 0.08017103153393906,
"grad_norm": 2.8456569961193394,
"learning_rate": 7.97872340425532e-06,
"loss": 0.7128,
"step": 150
},
{
"epoch": 0.08284339925173703,
"grad_norm": 2.8702252839691274,
"learning_rate": 8.24468085106383e-06,
"loss": 0.7134,
"step": 155
},
{
"epoch": 0.08551576696953501,
"grad_norm": 3.0045973129325003,
"learning_rate": 8.510638297872341e-06,
"loss": 0.7101,
"step": 160
},
{
"epoch": 0.08818813468733298,
"grad_norm": 3.0914370926022356,
"learning_rate": 8.776595744680852e-06,
"loss": 0.7233,
"step": 165
},
{
"epoch": 0.09086050240513095,
"grad_norm": 2.9050672041142,
"learning_rate": 9.042553191489362e-06,
"loss": 0.7181,
"step": 170
},
{
"epoch": 0.09353287012292892,
"grad_norm": 2.9572785204434817,
"learning_rate": 9.308510638297872e-06,
"loss": 0.7279,
"step": 175
},
{
"epoch": 0.09620523784072689,
"grad_norm": 2.8767794030301785,
"learning_rate": 9.574468085106385e-06,
"loss": 0.7164,
"step": 180
},
{
"epoch": 0.09887760555852486,
"grad_norm": 2.660052300201016,
"learning_rate": 9.840425531914895e-06,
"loss": 0.6984,
"step": 185
},
{
"epoch": 0.10154997327632283,
"grad_norm": 2.878335655264291,
"learning_rate": 9.99996515575899e-06,
"loss": 0.7226,
"step": 190
},
{
"epoch": 0.1042223409941208,
"grad_norm": 2.952547720515732,
"learning_rate": 9.99957316362496e-06,
"loss": 0.7128,
"step": 195
},
{
"epoch": 0.10689470871191876,
"grad_norm": 2.7946182203384393,
"learning_rate": 9.998745658315924e-06,
"loss": 0.705,
"step": 200
},
{
"epoch": 0.10956707642971673,
"grad_norm": 2.6240747857667963,
"learning_rate": 9.997482711915926e-06,
"loss": 0.6952,
"step": 205
},
{
"epoch": 0.1122394441475147,
"grad_norm": 2.8842386869626964,
"learning_rate": 9.99578443444032e-06,
"loss": 0.6946,
"step": 210
},
{
"epoch": 0.11491181186531267,
"grad_norm": 2.743809895131123,
"learning_rate": 9.993650973826177e-06,
"loss": 0.7194,
"step": 215
},
{
"epoch": 0.11758417958311064,
"grad_norm": 2.7122805763410156,
"learning_rate": 9.991082515919402e-06,
"loss": 0.7049,
"step": 220
},
{
"epoch": 0.12025654730090861,
"grad_norm": 3.185694679436466,
"learning_rate": 9.988079284458547e-06,
"loss": 0.6945,
"step": 225
},
{
"epoch": 0.12292891501870658,
"grad_norm": 2.7432180449917825,
"learning_rate": 9.98464154105532e-06,
"loss": 0.7131,
"step": 230
},
{
"epoch": 0.12560128273650453,
"grad_norm": 2.900135338830444,
"learning_rate": 9.980769585171795e-06,
"loss": 0.7211,
"step": 235
},
{
"epoch": 0.1282736504543025,
"grad_norm": 3.1004362591981076,
"learning_rate": 9.976463754094321e-06,
"loss": 0.6737,
"step": 240
},
{
"epoch": 0.13094601817210047,
"grad_norm": 2.766870655236161,
"learning_rate": 9.971724422904154e-06,
"loss": 0.6928,
"step": 245
},
{
"epoch": 0.13361838588989844,
"grad_norm": 2.597620688140956,
"learning_rate": 9.966552004444772e-06,
"loss": 0.7045,
"step": 250
},
{
"epoch": 0.1362907536076964,
"grad_norm": 2.6719752439386704,
"learning_rate": 9.960946949285915e-06,
"loss": 0.6896,
"step": 255
},
{
"epoch": 0.13896312132549438,
"grad_norm": 2.696881224222815,
"learning_rate": 9.954909745684339e-06,
"loss": 0.695,
"step": 260
},
{
"epoch": 0.14163548904329235,
"grad_norm": 2.489514725497346,
"learning_rate": 9.948440919541277e-06,
"loss": 0.6752,
"step": 265
},
{
"epoch": 0.14430785676109031,
"grad_norm": 2.5702514033071484,
"learning_rate": 9.94154103435664e-06,
"loss": 0.6979,
"step": 270
},
{
"epoch": 0.14698022447888828,
"grad_norm": 2.6897761190542866,
"learning_rate": 9.934210691179918e-06,
"loss": 0.6847,
"step": 275
},
{
"epoch": 0.14965259219668625,
"grad_norm": 2.523863970111887,
"learning_rate": 9.926450528557828e-06,
"loss": 0.6718,
"step": 280
},
{
"epoch": 0.15232495991448422,
"grad_norm": 2.462828628872149,
"learning_rate": 9.918261222478687e-06,
"loss": 0.7062,
"step": 285
},
{
"epoch": 0.1549973276322822,
"grad_norm": 2.5264396061786383,
"learning_rate": 9.909643486313533e-06,
"loss": 0.6723,
"step": 290
},
{
"epoch": 0.15766969535008016,
"grad_norm": 2.676467843498619,
"learning_rate": 9.900598070753981e-06,
"loss": 0.6752,
"step": 295
},
{
"epoch": 0.16034206306787813,
"grad_norm": 2.430155562876094,
"learning_rate": 9.891125763746824e-06,
"loss": 0.6814,
"step": 300
},
{
"epoch": 0.1630144307856761,
"grad_norm": 2.6008514719383755,
"learning_rate": 9.881227390425404e-06,
"loss": 0.6873,
"step": 305
},
{
"epoch": 0.16568679850347406,
"grad_norm": 2.8717084736190572,
"learning_rate": 9.87090381303772e-06,
"loss": 0.6845,
"step": 310
},
{
"epoch": 0.16835916622127206,
"grad_norm": 2.5783060345512516,
"learning_rate": 9.860155930871341e-06,
"loss": 0.6709,
"step": 315
},
{
"epoch": 0.17103153393907003,
"grad_norm": 2.450571872717288,
"learning_rate": 9.848984680175049e-06,
"loss": 0.6742,
"step": 320
},
{
"epoch": 0.173703901656868,
"grad_norm": 2.5464232605386248,
"learning_rate": 9.837391034077286e-06,
"loss": 0.6673,
"step": 325
},
{
"epoch": 0.17637626937466597,
"grad_norm": 2.455230168298457,
"learning_rate": 9.825376002501393e-06,
"loss": 0.6599,
"step": 330
},
{
"epoch": 0.17904863709246394,
"grad_norm": 2.405543632709517,
"learning_rate": 9.812940632077629e-06,
"loss": 0.6565,
"step": 335
},
{
"epoch": 0.1817210048102619,
"grad_norm": 2.6261255471329634,
"learning_rate": 9.800086006051996e-06,
"loss": 0.6706,
"step": 340
},
{
"epoch": 0.18439337252805987,
"grad_norm": 2.492237818044053,
"learning_rate": 9.786813244191885e-06,
"loss": 0.664,
"step": 345
},
{
"epoch": 0.18706574024585784,
"grad_norm": 2.461674707981306,
"learning_rate": 9.773123502688532e-06,
"loss": 0.6613,
"step": 350
},
{
"epoch": 0.1897381079636558,
"grad_norm": 2.4087083290786886,
"learning_rate": 9.759017974056292e-06,
"loss": 0.669,
"step": 355
},
{
"epoch": 0.19241047568145378,
"grad_norm": 2.3699762940762112,
"learning_rate": 9.744497887028774e-06,
"loss": 0.6513,
"step": 360
},
{
"epoch": 0.19508284339925175,
"grad_norm": 2.5103273833531894,
"learning_rate": 9.729564506451791e-06,
"loss": 0.6605,
"step": 365
},
{
"epoch": 0.19775521111704972,
"grad_norm": 2.811391637281001,
"learning_rate": 9.714219133173194e-06,
"loss": 0.6577,
"step": 370
},
{
"epoch": 0.20042757883484769,
"grad_norm": 2.4433957008456364,
"learning_rate": 9.698463103929542e-06,
"loss": 0.6483,
"step": 375
},
{
"epoch": 0.20309994655264565,
"grad_norm": 2.515593945036005,
"learning_rate": 9.682297791229668e-06,
"loss": 0.6518,
"step": 380
},
{
"epoch": 0.20577231427044362,
"grad_norm": 2.5920666669533654,
"learning_rate": 9.665724603235115e-06,
"loss": 0.623,
"step": 385
},
{
"epoch": 0.2084446819882416,
"grad_norm": 2.4427603396654756,
"learning_rate": 9.648744983637471e-06,
"loss": 0.6415,
"step": 390
},
{
"epoch": 0.21111704970603956,
"grad_norm": 2.4300710534012397,
"learning_rate": 9.631360411532609e-06,
"loss": 0.6483,
"step": 395
},
{
"epoch": 0.21378941742383753,
"grad_norm": 2.698023513313026,
"learning_rate": 9.61357240129185e-06,
"loss": 0.6507,
"step": 400
},
{
"epoch": 0.2164617851416355,
"grad_norm": 2.515109572478797,
"learning_rate": 9.59538250243003e-06,
"loss": 0.6342,
"step": 405
},
{
"epoch": 0.21913415285943347,
"grad_norm": 2.5415511117211196,
"learning_rate": 9.576792299470537e-06,
"loss": 0.6186,
"step": 410
},
{
"epoch": 0.22180652057723144,
"grad_norm": 2.4740412106242085,
"learning_rate": 9.557803411807283e-06,
"loss": 0.6629,
"step": 415
},
{
"epoch": 0.2244788882950294,
"grad_norm": 2.56186603448106,
"learning_rate": 9.538417493563621e-06,
"loss": 0.6433,
"step": 420
},
{
"epoch": 0.22715125601282737,
"grad_norm": 2.443484694350824,
"learning_rate": 9.518636233448276e-06,
"loss": 0.6335,
"step": 425
},
{
"epoch": 0.22982362373062534,
"grad_norm": 2.3114725088949655,
"learning_rate": 9.498461354608228e-06,
"loss": 0.6254,
"step": 430
},
{
"epoch": 0.2324959914484233,
"grad_norm": 2.5197267441606304,
"learning_rate": 9.47789461447861e-06,
"loss": 0.6312,
"step": 435
},
{
"epoch": 0.23516835916622128,
"grad_norm": 2.5154194908055976,
"learning_rate": 9.456937804629623e-06,
"loss": 0.634,
"step": 440
},
{
"epoch": 0.23784072688401925,
"grad_norm": 2.5245352230480513,
"learning_rate": 9.435592750610469e-06,
"loss": 0.6001,
"step": 445
},
{
"epoch": 0.24051309460181722,
"grad_norm": 2.711944191499036,
"learning_rate": 9.413861311790327e-06,
"loss": 0.6225,
"step": 450
},
{
"epoch": 0.2431854623196152,
"grad_norm": 2.54862704265095,
"learning_rate": 9.391745381196382e-06,
"loss": 0.635,
"step": 455
},
{
"epoch": 0.24585783003741316,
"grad_norm": 2.3855989168567815,
"learning_rate": 9.369246885348926e-06,
"loss": 0.6268,
"step": 460
},
{
"epoch": 0.24853019775521112,
"grad_norm": 2.4269409545196168,
"learning_rate": 9.346367784093538e-06,
"loss": 0.6173,
"step": 465
},
{
"epoch": 0.25120256547300907,
"grad_norm": 2.354629778528703,
"learning_rate": 9.32311007043036e-06,
"loss": 0.6352,
"step": 470
},
{
"epoch": 0.25387493319080706,
"grad_norm": 2.2856207419466723,
"learning_rate": 9.299475770340492e-06,
"loss": 0.6166,
"step": 475
},
{
"epoch": 0.256547300908605,
"grad_norm": 2.5028072074559984,
"learning_rate": 9.275466942609495e-06,
"loss": 0.6201,
"step": 480
},
{
"epoch": 0.259219668626403,
"grad_norm": 2.632255503333007,
"learning_rate": 9.251085678648072e-06,
"loss": 0.6297,
"step": 485
},
{
"epoch": 0.26189203634420094,
"grad_norm": 2.3309785369163025,
"learning_rate": 9.226334102309862e-06,
"loss": 0.6169,
"step": 490
},
{
"epoch": 0.26456440406199894,
"grad_norm": 2.6274201563879327,
"learning_rate": 9.201214369706448e-06,
"loss": 0.6217,
"step": 495
},
{
"epoch": 0.2672367717797969,
"grad_norm": 2.461602172579734,
"learning_rate": 9.17572866901953e-06,
"loss": 0.5998,
"step": 500
},
{
"epoch": 0.2699091394975949,
"grad_norm": 2.370745341232591,
"learning_rate": 9.14987922031031e-06,
"loss": 0.6159,
"step": 505
},
{
"epoch": 0.2725815072153928,
"grad_norm": 2.3869890928752726,
"learning_rate": 9.123668275326113e-06,
"loss": 0.6167,
"step": 510
},
{
"epoch": 0.2752538749331908,
"grad_norm": 2.3715110034433136,
"learning_rate": 9.097098117304223e-06,
"loss": 0.5963,
"step": 515
},
{
"epoch": 0.27792624265098875,
"grad_norm": 2.4872047250955642,
"learning_rate": 9.070171060773007e-06,
"loss": 0.6097,
"step": 520
},
{
"epoch": 0.28059861036878675,
"grad_norm": 2.693619438715027,
"learning_rate": 9.042889451350274e-06,
"loss": 0.6057,
"step": 525
},
{
"epoch": 0.2832709780865847,
"grad_norm": 2.4907500937699023,
"learning_rate": 9.015255665538972e-06,
"loss": 0.5877,
"step": 530
},
{
"epoch": 0.2859433458043827,
"grad_norm": 2.351723360366639,
"learning_rate": 8.987272110520154e-06,
"loss": 0.5981,
"step": 535
},
{
"epoch": 0.28861571352218063,
"grad_norm": 2.4371174743815,
"learning_rate": 8.958941223943292e-06,
"loss": 0.6008,
"step": 540
},
{
"epoch": 0.2912880812399786,
"grad_norm": 2.2795154594015035,
"learning_rate": 8.930265473713939e-06,
"loss": 0.602,
"step": 545
},
{
"epoch": 0.29396044895777657,
"grad_norm": 2.5333818292953394,
"learning_rate": 8.901247357778742e-06,
"loss": 0.6082,
"step": 550
},
{
"epoch": 0.29663281667557456,
"grad_norm": 2.3808750173872983,
"learning_rate": 8.871889403907853e-06,
"loss": 0.5765,
"step": 555
},
{
"epoch": 0.2993051843933725,
"grad_norm": 2.666651632145617,
"learning_rate": 8.842194169474727e-06,
"loss": 0.6003,
"step": 560
},
{
"epoch": 0.3019775521111705,
"grad_norm": 2.297875592960391,
"learning_rate": 8.812164241233354e-06,
"loss": 0.6005,
"step": 565
},
{
"epoch": 0.30464991982896844,
"grad_norm": 2.411050832025356,
"learning_rate": 8.781802235092927e-06,
"loss": 0.5946,
"step": 570
},
{
"epoch": 0.30732228754676644,
"grad_norm": 2.5580178404257397,
"learning_rate": 8.751110795889966e-06,
"loss": 0.578,
"step": 575
},
{
"epoch": 0.3099946552645644,
"grad_norm": 2.6362986159048782,
"learning_rate": 8.72009259715793e-06,
"loss": 0.6059,
"step": 580
},
{
"epoch": 0.3126670229823624,
"grad_norm": 2.449903954917446,
"learning_rate": 8.688750340894324e-06,
"loss": 0.5828,
"step": 585
},
{
"epoch": 0.3153393907001603,
"grad_norm": 2.3135977646364534,
"learning_rate": 8.657086757325328e-06,
"loss": 0.5733,
"step": 590
},
{
"epoch": 0.3180117584179583,
"grad_norm": 2.4214504928479084,
"learning_rate": 8.625104604667965e-06,
"loss": 0.5902,
"step": 595
},
{
"epoch": 0.32068412613575625,
"grad_norm": 2.559001530266603,
"learning_rate": 8.592806668889835e-06,
"loss": 0.5665,
"step": 600
},
{
"epoch": 0.32335649385355425,
"grad_norm": 2.4497334826598416,
"learning_rate": 8.560195763466428e-06,
"loss": 0.5746,
"step": 605
},
{
"epoch": 0.3260288615713522,
"grad_norm": 2.5249472362021934,
"learning_rate": 8.527274729136042e-06,
"loss": 0.5758,
"step": 610
},
{
"epoch": 0.3287012292891502,
"grad_norm": 2.4265348529669297,
"learning_rate": 8.494046433652327e-06,
"loss": 0.5794,
"step": 615
},
{
"epoch": 0.33137359700694813,
"grad_norm": 2.356210761928139,
"learning_rate": 8.460513771534475e-06,
"loss": 0.5656,
"step": 620
},
{
"epoch": 0.3340459647247461,
"grad_norm": 2.4027996915809595,
"learning_rate": 8.426679663815073e-06,
"loss": 0.5661,
"step": 625
},
{
"epoch": 0.3367183324425441,
"grad_norm": 2.358042791921069,
"learning_rate": 8.392547057785662e-06,
"loss": 0.5681,
"step": 630
},
{
"epoch": 0.33939070016034206,
"grad_norm": 2.3705534846122904,
"learning_rate": 8.358118926739984e-06,
"loss": 0.5785,
"step": 635
},
{
"epoch": 0.34206306787814006,
"grad_norm": 2.493612430786549,
"learning_rate": 8.323398269714994e-06,
"loss": 0.5588,
"step": 640
},
{
"epoch": 0.344735435595938,
"grad_norm": 2.408717425911149,
"learning_rate": 8.288388111229601e-06,
"loss": 0.574,
"step": 645
},
{
"epoch": 0.347407803313736,
"grad_norm": 2.517068953132363,
"learning_rate": 8.25309150102121e-06,
"loss": 0.5834,
"step": 650
},
{
"epoch": 0.35008017103153394,
"grad_norm": 2.4823980933908634,
"learning_rate": 8.217511513780056e-06,
"loss": 0.5908,
"step": 655
},
{
"epoch": 0.35275253874933193,
"grad_norm": 2.346495656974075,
"learning_rate": 8.181651248881364e-06,
"loss": 0.5402,
"step": 660
},
{
"epoch": 0.3554249064671299,
"grad_norm": 2.4909322838339727,
"learning_rate": 8.145513830115367e-06,
"loss": 0.577,
"step": 665
},
{
"epoch": 0.35809727418492787,
"grad_norm": 2.3776955502468984,
"learning_rate": 8.109102405415195e-06,
"loss": 0.5535,
"step": 670
},
{
"epoch": 0.3607696419027258,
"grad_norm": 2.3430189919707582,
"learning_rate": 8.072420146582649e-06,
"loss": 0.5621,
"step": 675
},
{
"epoch": 0.3634420096205238,
"grad_norm": 2.330075343445073,
"learning_rate": 8.035470249011916e-06,
"loss": 0.5484,
"step": 680
},
{
"epoch": 0.36611437733832175,
"grad_norm": 2.4919992467451064,
"learning_rate": 7.998255931411208e-06,
"loss": 0.554,
"step": 685
},
{
"epoch": 0.36878674505611975,
"grad_norm": 2.542252247612576,
"learning_rate": 7.960780435522387e-06,
"loss": 0.537,
"step": 690
},
{
"epoch": 0.3714591127739177,
"grad_norm": 2.5230905178208234,
"learning_rate": 7.923047025838573e-06,
"loss": 0.5564,
"step": 695
},
{
"epoch": 0.3741314804917157,
"grad_norm": 2.3579212496480584,
"learning_rate": 7.885058989319776e-06,
"loss": 0.5443,
"step": 700
},
{
"epoch": 0.3768038482095136,
"grad_norm": 2.38513572052014,
"learning_rate": 7.846819635106569e-06,
"loss": 0.5592,
"step": 705
},
{
"epoch": 0.3794762159273116,
"grad_norm": 2.450727922457597,
"learning_rate": 7.808332294231824e-06,
"loss": 0.5482,
"step": 710
},
{
"epoch": 0.38214858364510956,
"grad_norm": 2.37296948185331,
"learning_rate": 7.769600319330553e-06,
"loss": 0.5398,
"step": 715
},
{
"epoch": 0.38482095136290756,
"grad_norm": 2.3827561228964314,
"learning_rate": 7.73062708434785e-06,
"loss": 0.5556,
"step": 720
},
{
"epoch": 0.3874933190807055,
"grad_norm": 2.356934550008653,
"learning_rate": 7.691415984244998e-06,
"loss": 0.5511,
"step": 725
},
{
"epoch": 0.3901656867985035,
"grad_norm": 2.674299703946237,
"learning_rate": 7.651970434703724e-06,
"loss": 0.5404,
"step": 730
},
{
"epoch": 0.39283805451630144,
"grad_norm": 2.339540635811581,
"learning_rate": 7.612293871828662e-06,
"loss": 0.5401,
"step": 735
},
{
"epoch": 0.39551042223409943,
"grad_norm": 2.4129636901400984,
"learning_rate": 7.572389751848037e-06,
"loss": 0.5072,
"step": 740
},
{
"epoch": 0.3981827899518974,
"grad_norm": 2.300825776025901,
"learning_rate": 7.532261550812585e-06,
"loss": 0.5534,
"step": 745
},
{
"epoch": 0.40085515766969537,
"grad_norm": 2.463133059671825,
"learning_rate": 7.491912764292764e-06,
"loss": 0.5292,
"step": 750
},
{
"epoch": 0.4035275253874933,
"grad_norm": 2.362657841744074,
"learning_rate": 7.451346907074245e-06,
"loss": 0.5508,
"step": 755
},
{
"epoch": 0.4061998931052913,
"grad_norm": 2.3773903457486627,
"learning_rate": 7.4105675128517456e-06,
"loss": 0.5196,
"step": 760
},
{
"epoch": 0.40887226082308925,
"grad_norm": 2.307400895275789,
"learning_rate": 7.369578133921205e-06,
"loss": 0.5254,
"step": 765
},
{
"epoch": 0.41154462854088725,
"grad_norm": 2.3665811291351417,
"learning_rate": 7.3283823408703466e-06,
"loss": 0.537,
"step": 770
},
{
"epoch": 0.4142169962586852,
"grad_norm": 2.3404707343584,
"learning_rate": 7.2869837222676445e-06,
"loss": 0.5194,
"step": 775
},
{
"epoch": 0.4168893639764832,
"grad_norm": 2.4827850035798673,
"learning_rate": 7.245385884349716e-06,
"loss": 0.5297,
"step": 780
},
{
"epoch": 0.4195617316942811,
"grad_norm": 2.2569025340676285,
"learning_rate": 7.203592450707193e-06,
"loss": 0.5124,
"step": 785
},
{
"epoch": 0.4222340994120791,
"grad_norm": 2.3521703360354063,
"learning_rate": 7.161607061969061e-06,
"loss": 0.5067,
"step": 790
},
{
"epoch": 0.42490646712987706,
"grad_norm": 2.3373772070153804,
"learning_rate": 7.119433375485527e-06,
"loss": 0.5241,
"step": 795
},
{
"epoch": 0.42757883484767506,
"grad_norm": 2.3202283160266535,
"learning_rate": 7.0770750650094335e-06,
"loss": 0.5122,
"step": 800
},
{
"epoch": 0.430251202565473,
"grad_norm": 2.4354078892900213,
"learning_rate": 7.034535820376225e-06,
"loss": 0.5204,
"step": 805
},
{
"epoch": 0.432923570283271,
"grad_norm": 2.337683624170886,
"learning_rate": 6.991819347182536e-06,
"loss": 0.5326,
"step": 810
},
{
"epoch": 0.43559593800106894,
"grad_norm": 2.5041156555886537,
"learning_rate": 6.948929366463397e-06,
"loss": 0.516,
"step": 815
},
{
"epoch": 0.43826830571886694,
"grad_norm": 2.3855655528135897,
"learning_rate": 6.9058696143680895e-06,
"loss": 0.5411,
"step": 820
},
{
"epoch": 0.4409406734366649,
"grad_norm": 2.4748606327473093,
"learning_rate": 6.862643841834686e-06,
"loss": 0.5161,
"step": 825
},
{
"epoch": 0.4436130411544629,
"grad_norm": 2.3330605260339237,
"learning_rate": 6.8192558142633215e-06,
"loss": 0.5204,
"step": 830
},
{
"epoch": 0.4462854088722608,
"grad_norm": 2.610975607944503,
"learning_rate": 6.77570931118817e-06,
"loss": 0.5063,
"step": 835
},
{
"epoch": 0.4489577765900588,
"grad_norm": 2.3326693640891567,
"learning_rate": 6.732008125948223e-06,
"loss": 0.5135,
"step": 840
},
{
"epoch": 0.45163014430785675,
"grad_norm": 2.440916637553331,
"learning_rate": 6.688156065356845e-06,
"loss": 0.5045,
"step": 845
},
{
"epoch": 0.45430251202565475,
"grad_norm": 2.5049568831678166,
"learning_rate": 6.644156949370162e-06,
"loss": 0.4942,
"step": 850
},
{
"epoch": 0.4569748797434527,
"grad_norm": 2.290782487834507,
"learning_rate": 6.600014610754306e-06,
"loss": 0.4927,
"step": 855
},
{
"epoch": 0.4596472474612507,
"grad_norm": 2.4291908558987605,
"learning_rate": 6.555732894751548e-06,
"loss": 0.5069,
"step": 860
},
{
"epoch": 0.4623196151790486,
"grad_norm": 2.361674253761817,
"learning_rate": 6.511315658745323e-06,
"loss": 0.5049,
"step": 865
},
{
"epoch": 0.4649919828968466,
"grad_norm": 2.288520696084285,
"learning_rate": 6.466766771924231e-06,
"loss": 0.5026,
"step": 870
},
{
"epoch": 0.46766435061464456,
"grad_norm": 2.465468747078048,
"learning_rate": 6.422090114944982e-06,
"loss": 0.4926,
"step": 875
},
{
"epoch": 0.47033671833244256,
"grad_norm": 2.3396585154379284,
"learning_rate": 6.377289579594355e-06,
"loss": 0.5024,
"step": 880
},
{
"epoch": 0.4730090860502405,
"grad_norm": 2.4311913153752363,
"learning_rate": 6.332369068450175e-06,
"loss": 0.4918,
"step": 885
},
{
"epoch": 0.4756814537680385,
"grad_norm": 2.43606468761285,
"learning_rate": 6.28733249454138e-06,
"loss": 0.4977,
"step": 890
},
{
"epoch": 0.47835382148583644,
"grad_norm": 2.5715319533580754,
"learning_rate": 6.242183781007132e-06,
"loss": 0.5106,
"step": 895
},
{
"epoch": 0.48102618920363444,
"grad_norm": 2.3002416779416244,
"learning_rate": 6.196926860755088e-06,
"loss": 0.4818,
"step": 900
},
{
"epoch": 0.4836985569214324,
"grad_norm": 2.408853868970678,
"learning_rate": 6.151565676118805e-06,
"loss": 0.4728,
"step": 905
},
{
"epoch": 0.4863709246392304,
"grad_norm": 2.391661135082459,
"learning_rate": 6.106104178514309e-06,
"loss": 0.4808,
"step": 910
},
{
"epoch": 0.4890432923570283,
"grad_norm": 2.267492009433351,
"learning_rate": 6.0605463280958995e-06,
"loss": 0.4853,
"step": 915
},
{
"epoch": 0.4917156600748263,
"grad_norm": 2.532184320072154,
"learning_rate": 6.014896093411181e-06,
"loss": 0.4705,
"step": 920
},
{
"epoch": 0.49438802779262425,
"grad_norm": 2.3547741775844266,
"learning_rate": 5.9691574510553505e-06,
"loss": 0.488,
"step": 925
},
{
"epoch": 0.49706039551042225,
"grad_norm": 2.3564391188380465,
"learning_rate": 5.923334385324809e-06,
"loss": 0.4731,
"step": 930
},
{
"epoch": 0.4997327632282202,
"grad_norm": 2.331600922423602,
"learning_rate": 5.877430887870081e-06,
"loss": 0.482,
"step": 935
},
{
"epoch": 0.5024051309460181,
"grad_norm": 2.326867622566387,
"learning_rate": 5.831450957348106e-06,
"loss": 0.4879,
"step": 940
},
{
"epoch": 0.5050774986638161,
"grad_norm": 2.3582016410430513,
"learning_rate": 5.7853985990739115e-06,
"loss": 0.4612,
"step": 945
},
{
"epoch": 0.5077498663816141,
"grad_norm": 2.411375764117975,
"learning_rate": 5.739277824671711e-06,
"loss": 0.4656,
"step": 950
},
{
"epoch": 0.5104222340994121,
"grad_norm": 2.222559680578657,
"learning_rate": 5.693092651725457e-06,
"loss": 0.4681,
"step": 955
},
{
"epoch": 0.51309460181721,
"grad_norm": 2.397132369899048,
"learning_rate": 5.646847103428859e-06,
"loss": 0.4821,
"step": 960
},
{
"epoch": 0.515766969535008,
"grad_norm": 2.2243743133208054,
"learning_rate": 5.600545208234927e-06,
"loss": 0.4557,
"step": 965
},
{
"epoch": 0.518439337252806,
"grad_norm": 2.4529293346548475,
"learning_rate": 5.5541909995050554e-06,
"loss": 0.4688,
"step": 970
},
{
"epoch": 0.521111704970604,
"grad_norm": 2.349677634358367,
"learning_rate": 5.507788515157677e-06,
"loss": 0.4784,
"step": 975
},
{
"epoch": 0.5237840726884019,
"grad_norm": 2.3481918199565017,
"learning_rate": 5.46134179731651e-06,
"loss": 0.4668,
"step": 980
},
{
"epoch": 0.5264564404061999,
"grad_norm": 2.2568787632195138,
"learning_rate": 5.414854891958464e-06,
"loss": 0.4866,
"step": 985
},
{
"epoch": 0.5291288081239979,
"grad_norm": 2.270618683683588,
"learning_rate": 5.368331848561178e-06,
"loss": 0.4681,
"step": 990
},
{
"epoch": 0.5318011758417959,
"grad_norm": 2.400587986798466,
"learning_rate": 5.321776719750283e-06,
"loss": 0.4632,
"step": 995
},
{
"epoch": 0.5344735435595938,
"grad_norm": 2.4046807644199344,
"learning_rate": 5.275193560946372e-06,
"loss": 0.4822,
"step": 1000
},
{
"epoch": 0.5371459112773918,
"grad_norm": 2.301368345186627,
"learning_rate": 5.228586430011732e-06,
"loss": 0.456,
"step": 1005
},
{
"epoch": 0.5398182789951897,
"grad_norm": 2.398493533420555,
"learning_rate": 5.181959386896862e-06,
"loss": 0.4595,
"step": 1010
},
{
"epoch": 0.5424906467129877,
"grad_norm": 2.4695921566874173,
"learning_rate": 5.135316493286818e-06,
"loss": 0.4644,
"step": 1015
},
{
"epoch": 0.5451630144307856,
"grad_norm": 2.3696576185132048,
"learning_rate": 5.088661812247389e-06,
"loss": 0.4458,
"step": 1020
},
{
"epoch": 0.5478353821485836,
"grad_norm": 2.3464731556110303,
"learning_rate": 5.041999407871168e-06,
"loss": 0.455,
"step": 1025
},
{
"epoch": 0.5505077498663816,
"grad_norm": 2.26833277884023,
"learning_rate": 4.995333344923531e-06,
"loss": 0.4417,
"step": 1030
},
{
"epoch": 0.5531801175841796,
"grad_norm": 2.23341195819364,
"learning_rate": 4.948667688488552e-06,
"loss": 0.4498,
"step": 1035
},
{
"epoch": 0.5558524853019775,
"grad_norm": 2.350623017299231,
"learning_rate": 4.9020065036148885e-06,
"loss": 0.4476,
"step": 1040
},
{
"epoch": 0.5585248530197755,
"grad_norm": 2.305025381255869,
"learning_rate": 4.85535385496169e-06,
"loss": 0.4423,
"step": 1045
},
{
"epoch": 0.5611972207375735,
"grad_norm": 2.216182560140296,
"learning_rate": 4.808713806444506e-06,
"loss": 0.4499,
"step": 1050
},
{
"epoch": 0.5638695884553715,
"grad_norm": 2.393927415399474,
"learning_rate": 4.762090420881289e-06,
"loss": 0.437,
"step": 1055
},
{
"epoch": 0.5665419561731694,
"grad_norm": 2.369542446425221,
"learning_rate": 4.715487759638486e-06,
"loss": 0.4511,
"step": 1060
},
{
"epoch": 0.5692143238909674,
"grad_norm": 2.3320344155659454,
"learning_rate": 4.66890988227724e-06,
"loss": 0.4424,
"step": 1065
},
{
"epoch": 0.5718866916087654,
"grad_norm": 2.2966460484680526,
"learning_rate": 4.622360846199772e-06,
"loss": 0.453,
"step": 1070
},
{
"epoch": 0.5745590593265634,
"grad_norm": 2.2174193833591027,
"learning_rate": 4.575844706295938e-06,
"loss": 0.4275,
"step": 1075
},
{
"epoch": 0.5772314270443613,
"grad_norm": 2.1791480693201213,
"learning_rate": 4.529365514590002e-06,
"loss": 0.4396,
"step": 1080
},
{
"epoch": 0.5799037947621593,
"grad_norm": 2.2705808564677095,
"learning_rate": 4.482927319887669e-06,
"loss": 0.455,
"step": 1085
},
{
"epoch": 0.5825761624799572,
"grad_norm": 2.2966057317596538,
"learning_rate": 4.436534167423395e-06,
"loss": 0.4401,
"step": 1090
},
{
"epoch": 0.5852485301977552,
"grad_norm": 2.434444132621627,
"learning_rate": 4.390190098508001e-06,
"loss": 0.4385,
"step": 1095
},
{
"epoch": 0.5879208979155531,
"grad_norm": 2.2942323509737665,
"learning_rate": 4.343899150176635e-06,
"loss": 0.4406,
"step": 1100
},
{
"epoch": 0.5905932656333511,
"grad_norm": 2.3267061268462377,
"learning_rate": 4.2976653548371115e-06,
"loss": 0.419,
"step": 1105
},
{
"epoch": 0.5932656333511491,
"grad_norm": 2.3265749333122034,
"learning_rate": 4.251492739918641e-06,
"loss": 0.4308,
"step": 1110
},
{
"epoch": 0.5959380010689471,
"grad_norm": 2.3194338695979924,
"learning_rate": 4.205385327521002e-06,
"loss": 0.4209,
"step": 1115
},
{
"epoch": 0.598610368786745,
"grad_norm": 2.262528326657035,
"learning_rate": 4.159347134064177e-06,
"loss": 0.4331,
"step": 1120
},
{
"epoch": 0.601282736504543,
"grad_norm": 2.2493576306346243,
"learning_rate": 4.113382169938488e-06,
"loss": 0.4267,
"step": 1125
},
{
"epoch": 0.603955104222341,
"grad_norm": 2.2071826110407637,
"learning_rate": 4.067494439155236e-06,
"loss": 0.4207,
"step": 1130
},
{
"epoch": 0.606627471940139,
"grad_norm": 2.376562409081072,
"learning_rate": 4.021687938997923e-06,
"loss": 0.4447,
"step": 1135
},
{
"epoch": 0.6092998396579369,
"grad_norm": 2.2481954819166807,
"learning_rate": 3.975966659674048e-06,
"loss": 0.4227,
"step": 1140
},
{
"epoch": 0.6119722073757349,
"grad_norm": 2.263685650735154,
"learning_rate": 3.930334583967514e-06,
"loss": 0.4258,
"step": 1145
},
{
"epoch": 0.6146445750935329,
"grad_norm": 2.2929510875578414,
"learning_rate": 3.884795686891692e-06,
"loss": 0.4131,
"step": 1150
},
{
"epoch": 0.6173169428113309,
"grad_norm": 2.183279451529703,
"learning_rate": 3.839353935343156e-06,
"loss": 0.4185,
"step": 1155
},
{
"epoch": 0.6199893105291288,
"grad_norm": 2.4141644984025756,
"learning_rate": 3.794013287756125e-06,
"loss": 0.441,
"step": 1160
},
{
"epoch": 0.6226616782469268,
"grad_norm": 2.2424721976205615,
"learning_rate": 3.748777693757646e-06,
"loss": 0.4261,
"step": 1165
},
{
"epoch": 0.6253340459647247,
"grad_norm": 2.434773344097218,
"learning_rate": 3.7036510938235394e-06,
"loss": 0.4225,
"step": 1170
},
{
"epoch": 0.6280064136825227,
"grad_norm": 2.30007197884754,
"learning_rate": 3.658637418935146e-06,
"loss": 0.4346,
"step": 1175
},
{
"epoch": 0.6306787814003206,
"grad_norm": 2.2912273584685443,
"learning_rate": 3.613740590236895e-06,
"loss": 0.4082,
"step": 1180
},
{
"epoch": 0.6333511491181186,
"grad_norm": 2.2455803386255213,
"learning_rate": 3.56896451869474e-06,
"loss": 0.422,
"step": 1185
},
{
"epoch": 0.6360235168359166,
"grad_norm": 2.183514807256048,
"learning_rate": 3.524313104755468e-06,
"loss": 0.4162,
"step": 1190
},
{
"epoch": 0.6386958845537146,
"grad_norm": 2.3569554872139227,
"learning_rate": 3.4797902380069305e-06,
"loss": 0.4029,
"step": 1195
},
{
"epoch": 0.6413682522715125,
"grad_norm": 2.365651681741471,
"learning_rate": 3.4353997968392295e-06,
"loss": 0.4116,
"step": 1200
},
{
"epoch": 0.6440406199893105,
"grad_norm": 2.4313464159199616,
"learning_rate": 3.3911456481068613e-06,
"loss": 0.4321,
"step": 1205
},
{
"epoch": 0.6467129877071085,
"grad_norm": 2.4029788639326988,
"learning_rate": 3.3470316467918785e-06,
"loss": 0.4163,
"step": 1210
},
{
"epoch": 0.6493853554249065,
"grad_norm": 2.227746603559888,
"learning_rate": 3.3030616356680854e-06,
"loss": 0.4068,
"step": 1215
},
{
"epoch": 0.6520577231427044,
"grad_norm": 2.1651867549706214,
"learning_rate": 3.2592394449662867e-06,
"loss": 0.4064,
"step": 1220
},
{
"epoch": 0.6547300908605024,
"grad_norm": 2.436072560140991,
"learning_rate": 3.2155688920406415e-06,
"loss": 0.4202,
"step": 1225
},
{
"epoch": 0.6574024585783004,
"grad_norm": 2.396630440584044,
"learning_rate": 3.172053781036132e-06,
"loss": 0.4127,
"step": 1230
},
{
"epoch": 0.6600748262960984,
"grad_norm": 2.26775393177631,
"learning_rate": 3.1286979025571817e-06,
"loss": 0.4044,
"step": 1235
},
{
"epoch": 0.6627471940138963,
"grad_norm": 2.279042289947522,
"learning_rate": 3.0855050333374574e-06,
"loss": 0.4118,
"step": 1240
},
{
"epoch": 0.6654195617316943,
"grad_norm": 2.3353783811633417,
"learning_rate": 3.042478935910881e-06,
"loss": 0.3982,
"step": 1245
},
{
"epoch": 0.6680919294494923,
"grad_norm": 2.287894124394364,
"learning_rate": 2.9996233582838686e-06,
"loss": 0.4037,
"step": 1250
},
{
"epoch": 0.6707642971672902,
"grad_norm": 2.232614005180025,
"learning_rate": 2.956942033608843e-06,
"loss": 0.424,
"step": 1255
},
{
"epoch": 0.6734366648850882,
"grad_norm": 2.212465940891605,
"learning_rate": 2.914438679859046e-06,
"loss": 0.4011,
"step": 1260
},
{
"epoch": 0.6761090326028861,
"grad_norm": 2.237377634440734,
"learning_rate": 2.8721169995046503e-06,
"loss": 0.4095,
"step": 1265
},
{
"epoch": 0.6787814003206841,
"grad_norm": 2.204723055159894,
"learning_rate": 2.829980679190254e-06,
"loss": 0.4006,
"step": 1270
},
{
"epoch": 0.6814537680384821,
"grad_norm": 2.142590575818092,
"learning_rate": 2.788033389413729e-06,
"loss": 0.4185,
"step": 1275
},
{
"epoch": 0.6841261357562801,
"grad_norm": 2.108891858503545,
"learning_rate": 2.7462787842064753e-06,
"loss": 0.3897,
"step": 1280
},
{
"epoch": 0.686798503474078,
"grad_norm": 2.3410566026299637,
"learning_rate": 2.7047205008151332e-06,
"loss": 0.3949,
"step": 1285
},
{
"epoch": 0.689470871191876,
"grad_norm": 2.4176280537106276,
"learning_rate": 2.6633621593847387e-06,
"loss": 0.3934,
"step": 1290
},
{
"epoch": 0.692143238909674,
"grad_norm": 2.1430191084509556,
"learning_rate": 2.6222073626433587e-06,
"loss": 0.392,
"step": 1295
},
{
"epoch": 0.694815606627472,
"grad_norm": 2.1489554898503034,
"learning_rate": 2.5812596955882756e-06,
"loss": 0.3928,
"step": 1300
},
{
"epoch": 0.6974879743452699,
"grad_norm": 2.146053345860412,
"learning_rate": 2.540522725173692e-06,
"loss": 0.3983,
"step": 1305
},
{
"epoch": 0.7001603420630679,
"grad_norm": 2.222342858457763,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.3902,
"step": 1310
},
{
"epoch": 0.7028327097808659,
"grad_norm": 2.5586473746176757,
"learning_rate": 2.459695050004688e-06,
"loss": 0.3917,
"step": 1315
},
{
"epoch": 0.7055050774986639,
"grad_norm": 2.208219420319392,
"learning_rate": 2.4196113861548233e-06,
"loss": 0.3842,
"step": 1320
},
{
"epoch": 0.7081774452164618,
"grad_norm": 2.1077247250552107,
"learning_rate": 2.379752500141222e-06,
"loss": 0.3863,
"step": 1325
},
{
"epoch": 0.7108498129342598,
"grad_norm": 2.2022799294300612,
"learning_rate": 2.3401218640742894e-06,
"loss": 0.3859,
"step": 1330
},
{
"epoch": 0.7135221806520577,
"grad_norm": 2.2382487651969645,
"learning_rate": 2.3007229301815643e-06,
"loss": 0.3836,
"step": 1335
},
{
"epoch": 0.7161945483698557,
"grad_norm": 2.154198997980066,
"learning_rate": 2.2615591305069846e-06,
"loss": 0.39,
"step": 1340
},
{
"epoch": 0.7188669160876536,
"grad_norm": 2.245560231513789,
"learning_rate": 2.2226338766119366e-06,
"loss": 0.3765,
"step": 1345
},
{
"epoch": 0.7215392838054516,
"grad_norm": 2.4396557453542447,
"learning_rate": 2.1839505592780658e-06,
"loss": 0.4076,
"step": 1350
},
{
"epoch": 0.7242116515232496,
"grad_norm": 2.2273193277716468,
"learning_rate": 2.145512548211902e-06,
"loss": 0.3833,
"step": 1355
},
{
"epoch": 0.7268840192410476,
"grad_norm": 2.133389321978994,
"learning_rate": 2.1073231917513336e-06,
"loss": 0.3748,
"step": 1360
},
{
"epoch": 0.7295563869588455,
"grad_norm": 2.4818219843856943,
"learning_rate": 2.069385816573928e-06,
"loss": 0.399,
"step": 1365
},
{
"epoch": 0.7322287546766435,
"grad_norm": 2.1823563541738746,
"learning_rate": 2.0317037274071412e-06,
"loss": 0.3822,
"step": 1370
},
{
"epoch": 0.7349011223944415,
"grad_norm": 2.2273588376450477,
"learning_rate": 1.99428020674045e-06,
"loss": 0.3769,
"step": 1375
},
{
"epoch": 0.7375734901122395,
"grad_norm": 2.1480513045059713,
"learning_rate": 1.9571185145394117e-06,
"loss": 0.377,
"step": 1380
},
{
"epoch": 0.7402458578300374,
"grad_norm": 2.2592778819512693,
"learning_rate": 1.9202218879616824e-06,
"loss": 0.401,
"step": 1385
},
{
"epoch": 0.7429182255478354,
"grad_norm": 2.236298004568426,
"learning_rate": 1.8835935410750372e-06,
"loss": 0.386,
"step": 1390
},
{
"epoch": 0.7455905932656334,
"grad_norm": 2.0840694866461393,
"learning_rate": 1.8472366645773892e-06,
"loss": 0.3828,
"step": 1395
},
{
"epoch": 0.7482629609834314,
"grad_norm": 2.188364212229032,
"learning_rate": 1.8111544255188402e-06,
"loss": 0.388,
"step": 1400
},
{
"epoch": 0.7509353287012293,
"grad_norm": 2.158800110753583,
"learning_rate": 1.7753499670258106e-06,
"loss": 0.3801,
"step": 1405
},
{
"epoch": 0.7536076964190273,
"grad_norm": 2.186867715541052,
"learning_rate": 1.7398264080272371e-06,
"loss": 0.3827,
"step": 1410
},
{
"epoch": 0.7562800641368252,
"grad_norm": 2.1233004021574233,
"learning_rate": 1.7045868429828745e-06,
"loss": 0.3859,
"step": 1415
},
{
"epoch": 0.7589524318546232,
"grad_norm": 2.2860681163503123,
"learning_rate": 1.6696343416137495e-06,
"loss": 0.3792,
"step": 1420
},
{
"epoch": 0.7616247995724211,
"grad_norm": 2.2053652070917447,
"learning_rate": 1.6349719486347533e-06,
"loss": 0.3763,
"step": 1425
},
{
"epoch": 0.7642971672902191,
"grad_norm": 2.142110937503417,
"learning_rate": 1.6006026834894068e-06,
"loss": 0.3728,
"step": 1430
},
{
"epoch": 0.7669695350080171,
"grad_norm": 2.102049608237232,
"learning_rate": 1.5665295400868513e-06,
"loss": 0.3727,
"step": 1435
},
{
"epoch": 0.7696419027258151,
"grad_norm": 2.2937100156195163,
"learning_rate": 1.5327554865410415e-06,
"loss": 0.3677,
"step": 1440
},
{
"epoch": 0.772314270443613,
"grad_norm": 2.0960313868976175,
"learning_rate": 1.499283464912188e-06,
"loss": 0.3597,
"step": 1445
},
{
"epoch": 0.774986638161411,
"grad_norm": 2.127048297305918,
"learning_rate": 1.4661163909504855e-06,
"loss": 0.3788,
"step": 1450
},
{
"epoch": 0.777659005879209,
"grad_norm": 2.2553155220452537,
"learning_rate": 1.4332571538421136e-06,
"loss": 0.3678,
"step": 1455
},
{
"epoch": 0.780331373597007,
"grad_norm": 2.212390746080692,
"learning_rate": 1.4007086159575595e-06,
"loss": 0.3784,
"step": 1460
},
{
"epoch": 0.7830037413148049,
"grad_norm": 2.052293984029166,
"learning_rate": 1.3684736126022812e-06,
"loss": 0.3687,
"step": 1465
},
{
"epoch": 0.7856761090326029,
"grad_norm": 2.231444311381863,
"learning_rate": 1.3365549517697234e-06,
"loss": 0.3714,
"step": 1470
},
{
"epoch": 0.7883484767504009,
"grad_norm": 2.115795094536637,
"learning_rate": 1.3049554138967052e-06,
"loss": 0.3755,
"step": 1475
},
{
"epoch": 0.7910208444681989,
"grad_norm": 1.9857252769460916,
"learning_rate": 1.2736777516212267e-06,
"loss": 0.3699,
"step": 1480
},
{
"epoch": 0.7936932121859968,
"grad_norm": 2.1542840319145147,
"learning_rate": 1.2427246895426826e-06,
"loss": 0.3623,
"step": 1485
},
{
"epoch": 0.7963655799037948,
"grad_norm": 2.0646559618489513,
"learning_rate": 1.2120989239845149e-06,
"loss": 0.3626,
"step": 1490
},
{
"epoch": 0.7990379476215927,
"grad_norm": 2.3185239311763883,
"learning_rate": 1.1818031227593491e-06,
"loss": 0.3763,
"step": 1495
},
{
"epoch": 0.8017103153393907,
"grad_norm": 2.2065800294677493,
"learning_rate": 1.1518399249365924e-06,
"loss": 0.3721,
"step": 1500
},
{
"epoch": 0.8043826830571886,
"grad_norm": 2.0498511458197353,
"learning_rate": 1.1222119406125426e-06,
"loss": 0.3749,
"step": 1505
},
{
"epoch": 0.8070550507749866,
"grad_norm": 2.1099301962454735,
"learning_rate": 1.0929217506830292e-06,
"loss": 0.3795,
"step": 1510
},
{
"epoch": 0.8097274184927846,
"grad_norm": 2.098240231784591,
"learning_rate": 1.0639719066185867e-06,
"loss": 0.3776,
"step": 1515
},
{
"epoch": 0.8123997862105826,
"grad_norm": 2.213732309208511,
"learning_rate": 1.0353649302421982e-06,
"loss": 0.3654,
"step": 1520
},
{
"epoch": 0.8150721539283805,
"grad_norm": 2.1163942857377935,
"learning_rate": 1.007103313509617e-06,
"loss": 0.3704,
"step": 1525
},
{
"epoch": 0.8177445216461785,
"grad_norm": 2.0777306876402117,
"learning_rate": 9.791895182922911e-07,
"loss": 0.3729,
"step": 1530
},
{
"epoch": 0.8204168893639765,
"grad_norm": 1.9873211592792865,
"learning_rate": 9.516259761629148e-07,
"loss": 0.3673,
"step": 1535
},
{
"epoch": 0.8230892570817745,
"grad_norm": 2.2236156974225203,
"learning_rate": 9.244150881836117e-07,
"loss": 0.3696,
"step": 1540
},
{
"epoch": 0.8257616247995724,
"grad_norm": 2.22717136010219,
"learning_rate": 8.975592246967713e-07,
"loss": 0.3595,
"step": 1545
},
{
"epoch": 0.8284339925173704,
"grad_norm": 2.1659147264471286,
"learning_rate": 8.710607251185799e-07,
"loss": 0.3599,
"step": 1550
},
{
"epoch": 0.8311063602351684,
"grad_norm": 2.0676184956103993,
"learning_rate": 8.449218977352281e-07,
"loss": 0.3517,
"step": 1555
},
{
"epoch": 0.8337787279529664,
"grad_norm": 2.1674702101703494,
"learning_rate": 8.191450195018313e-07,
"loss": 0.3806,
"step": 1560
},
{
"epoch": 0.8364510956707643,
"grad_norm": 1.9549545408259852,
"learning_rate": 7.937323358440935e-07,
"loss": 0.356,
"step": 1565
},
{
"epoch": 0.8391234633885623,
"grad_norm": 2.0080946444810133,
"learning_rate": 7.686860604627022e-07,
"loss": 0.3807,
"step": 1570
},
{
"epoch": 0.8417958311063602,
"grad_norm": 2.21542238656484,
"learning_rate": 7.440083751404902e-07,
"loss": 0.3565,
"step": 1575
},
{
"epoch": 0.8444681988241582,
"grad_norm": 2.45811726867115,
"learning_rate": 7.197014295523879e-07,
"loss": 0.3608,
"step": 1580
},
{
"epoch": 0.8471405665419561,
"grad_norm": 2.384844603298332,
"learning_rate": 6.957673410781617e-07,
"loss": 0.3559,
"step": 1585
},
{
"epoch": 0.8498129342597541,
"grad_norm": 2.0979990994693583,
"learning_rate": 6.722081946179631e-07,
"loss": 0.3528,
"step": 1590
},
{
"epoch": 0.8524853019775521,
"grad_norm": 2.049629473325055,
"learning_rate": 6.490260424107231e-07,
"loss": 0.3732,
"step": 1595
},
{
"epoch": 0.8551576696953501,
"grad_norm": 2.1414391930102954,
"learning_rate": 6.262229038553752e-07,
"loss": 0.3594,
"step": 1600
},
{
"epoch": 0.857830037413148,
"grad_norm": 1.9884240369961335,
"learning_rate": 6.038007653349437e-07,
"loss": 0.3526,
"step": 1605
},
{
"epoch": 0.860502405130946,
"grad_norm": 2.147568608512386,
"learning_rate": 5.817615800435167e-07,
"loss": 0.3598,
"step": 1610
},
{
"epoch": 0.863174772848744,
"grad_norm": 2.2741927858237725,
"learning_rate": 5.60107267816098e-07,
"loss": 0.353,
"step": 1615
},
{
"epoch": 0.865847140566542,
"grad_norm": 2.052958674087618,
"learning_rate": 5.388397149613683e-07,
"loss": 0.3635,
"step": 1620
},
{
"epoch": 0.8685195082843399,
"grad_norm": 2.00667543539292,
"learning_rate": 5.179607740973764e-07,
"loss": 0.3583,
"step": 1625
},
{
"epoch": 0.8711918760021379,
"grad_norm": 2.0303583872396547,
"learning_rate": 4.974722639901503e-07,
"loss": 0.3553,
"step": 1630
},
{
"epoch": 0.8738642437199359,
"grad_norm": 2.1674210284215505,
"learning_rate": 4.773759693952662e-07,
"loss": 0.3477,
"step": 1635
},
{
"epoch": 0.8765366114377339,
"grad_norm": 2.109618296740792,
"learning_rate": 4.576736409023813e-07,
"loss": 0.3664,
"step": 1640
},
{
"epoch": 0.8792089791555318,
"grad_norm": 2.0478212094903236,
"learning_rate": 4.383669947827368e-07,
"loss": 0.3675,
"step": 1645
},
{
"epoch": 0.8818813468733298,
"grad_norm": 2.1212898904117945,
"learning_rate": 4.194577128396521e-07,
"loss": 0.3584,
"step": 1650
},
{
"epoch": 0.8845537145911277,
"grad_norm": 2.0897807643835558,
"learning_rate": 4.009474422620269e-07,
"loss": 0.3561,
"step": 1655
},
{
"epoch": 0.8872260823089257,
"grad_norm": 2.2137058162114984,
"learning_rate": 3.828377954808538e-07,
"loss": 0.3668,
"step": 1660
},
{
"epoch": 0.8898984500267236,
"grad_norm": 2.0621182228376016,
"learning_rate": 3.651303500287534e-07,
"loss": 0.3584,
"step": 1665
},
{
"epoch": 0.8925708177445216,
"grad_norm": 1.9763619146865647,
"learning_rate": 3.4782664840256387e-07,
"loss": 0.3523,
"step": 1670
},
{
"epoch": 0.8952431854623196,
"grad_norm": 2.2354539247913943,
"learning_rate": 3.3092819792896913e-07,
"loss": 0.3573,
"step": 1675
},
{
"epoch": 0.8979155531801176,
"grad_norm": 2.1687124103358175,
"learning_rate": 3.1443647063319425e-07,
"loss": 0.3621,
"step": 1680
},
{
"epoch": 0.9005879208979155,
"grad_norm": 2.2466445370083106,
"learning_rate": 2.9835290311078123e-07,
"loss": 0.3474,
"step": 1685
},
{
"epoch": 0.9032602886157135,
"grad_norm": 2.2174579555309406,
"learning_rate": 2.8267889640244516e-07,
"loss": 0.3509,
"step": 1690
},
{
"epoch": 0.9059326563335115,
"grad_norm": 1.906344336758653,
"learning_rate": 2.6741581587202747e-07,
"loss": 0.3503,
"step": 1695
},
{
"epoch": 0.9086050240513095,
"grad_norm": 2.2167462208206588,
"learning_rate": 2.525649910875627e-07,
"loss": 0.3531,
"step": 1700
},
{
"epoch": 0.9112773917691074,
"grad_norm": 2.012247754130522,
"learning_rate": 2.3812771570545846e-07,
"loss": 0.3571,
"step": 1705
},
{
"epoch": 0.9139497594869054,
"grad_norm": 2.0072281723087055,
"learning_rate": 2.2410524735780205e-07,
"loss": 0.3446,
"step": 1710
},
{
"epoch": 0.9166221272047034,
"grad_norm": 1.983425601980138,
"learning_rate": 2.104988075428127e-07,
"loss": 0.3595,
"step": 1715
},
{
"epoch": 0.9192944949225014,
"grad_norm": 1.9720893643166868,
"learning_rate": 1.9730958151843282e-07,
"loss": 0.3606,
"step": 1720
},
{
"epoch": 0.9219668626402993,
"grad_norm": 1.9727579534799584,
"learning_rate": 1.845387181990821e-07,
"loss": 0.3387,
"step": 1725
},
{
"epoch": 0.9246392303580973,
"grad_norm": 2.104825529914431,
"learning_rate": 1.7218733005557707e-07,
"loss": 0.3562,
"step": 1730
},
{
"epoch": 0.9273115980758952,
"grad_norm": 1.9710924119424453,
"learning_rate": 1.6025649301821877e-07,
"loss": 0.362,
"step": 1735
},
{
"epoch": 0.9299839657936932,
"grad_norm": 2.1804990908528987,
"learning_rate": 1.4874724638307303e-07,
"loss": 0.3578,
"step": 1740
},
{
"epoch": 0.9326563335114911,
"grad_norm": 2.008917568622848,
"learning_rate": 1.376605927214364e-07,
"loss": 0.3445,
"step": 1745
},
{
"epoch": 0.9353287012292891,
"grad_norm": 2.0407884448922364,
"learning_rate": 1.2699749779249926e-07,
"loss": 0.3546,
"step": 1750
},
{
"epoch": 0.9380010689470871,
"grad_norm": 2.2230446678966587,
"learning_rate": 1.1675889045922151e-07,
"loss": 0.357,
"step": 1755
},
{
"epoch": 0.9406734366648851,
"grad_norm": 2.029326477832939,
"learning_rate": 1.0694566260742001e-07,
"loss": 0.3446,
"step": 1760
},
{
"epoch": 0.943345804382683,
"grad_norm": 1.9454325237170078,
"learning_rate": 9.755866906807188e-08,
"loss": 0.3404,
"step": 1765
},
{
"epoch": 0.946018172100481,
"grad_norm": 2.1853515352562605,
"learning_rate": 8.859872754285403e-08,
"loss": 0.3557,
"step": 1770
},
{
"epoch": 0.948690539818279,
"grad_norm": 2.1169073640896183,
"learning_rate": 8.006661853291298e-08,
"loss": 0.3588,
"step": 1775
},
{
"epoch": 0.951362907536077,
"grad_norm": 1.9299668813663102,
"learning_rate": 7.196308527087192e-08,
"loss": 0.3529,
"step": 1780
},
{
"epoch": 0.9540352752538749,
"grad_norm": 2.2042681754338282,
"learning_rate": 6.428883365609261e-08,
"loss": 0.3548,
"step": 1785
},
{
"epoch": 0.9567076429716729,
"grad_norm": 1.9009648054194321,
"learning_rate": 5.704453219318118e-08,
"loss": 0.3476,
"step": 1790
},
{
"epoch": 0.9593800106894709,
"grad_norm": 1.964186081597576,
"learning_rate": 5.023081193375357e-08,
"loss": 0.3476,
"step": 1795
},
{
"epoch": 0.9620523784072689,
"grad_norm": 2.0939521595441586,
"learning_rate": 4.384826642146844e-08,
"loss": 0.3614,
"step": 1800
},
{
"epoch": 0.9647247461250668,
"grad_norm": 2.1269484808182546,
"learning_rate": 3.7897451640321326e-08,
"loss": 0.3447,
"step": 1805
},
{
"epoch": 0.9673971138428648,
"grad_norm": 1.93031268408877,
"learning_rate": 3.2378885966211636e-08,
"loss": 0.3566,
"step": 1810
},
{
"epoch": 0.9700694815606627,
"grad_norm": 2.0577180051749213,
"learning_rate": 2.7293050121788843e-08,
"loss": 0.3482,
"step": 1815
},
{
"epoch": 0.9727418492784607,
"grad_norm": 2.1110303342177303,
"learning_rate": 2.264038713457706e-08,
"loss": 0.3577,
"step": 1820
},
{
"epoch": 0.9754142169962586,
"grad_norm": 1.9659843852644756,
"learning_rate": 1.842130229838035e-08,
"loss": 0.35,
"step": 1825
},
{
"epoch": 0.9780865847140566,
"grad_norm": 1.9251005331305897,
"learning_rate": 1.4636163137980441e-08,
"loss": 0.3545,
"step": 1830
},
{
"epoch": 0.9807589524318546,
"grad_norm": 2.1961120036714195,
"learning_rate": 1.1285299377118974e-08,
"loss": 0.3554,
"step": 1835
},
{
"epoch": 0.9834313201496526,
"grad_norm": 1.9827027705246492,
"learning_rate": 8.369002909777713e-09,
"loss": 0.3688,
"step": 1840
},
{
"epoch": 0.9861036878674505,
"grad_norm": 2.1906918950566916,
"learning_rate": 5.88752777474999e-09,
"loss": 0.3512,
"step": 1845
},
{
"epoch": 0.9887760555852485,
"grad_norm": 1.9684719857212658,
"learning_rate": 3.841090133511749e-09,
"loss": 0.3489,
"step": 1850
},
{
"epoch": 0.9914484233030465,
"grad_norm": 2.1798562911903097,
"learning_rate": 2.229868251391598e-09,
"loss": 0.3684,
"step": 1855
},
{
"epoch": 0.9941207910208445,
"grad_norm": 2.057557423902706,
"learning_rate": 1.054002482043237e-09,
"loss": 0.3567,
"step": 1860
},
{
"epoch": 0.9967931587386424,
"grad_norm": 1.9236023488910832,
"learning_rate": 3.1359525521801326e-10,
"loss": 0.3443,
"step": 1865
},
{
"epoch": 0.9994655264564404,
"grad_norm": 2.098257280647918,
"learning_rate": 8.711067840949661e-12,
"loss": 0.3431,
"step": 1870
},
{
"epoch": 1.0,
"eval_loss": 0.29403093457221985,
"eval_runtime": 0.9784,
"eval_samples_per_second": 2.044,
"eval_steps_per_second": 1.022,
"step": 1871
},
{
"epoch": 1.0,
"step": 1871,
"total_flos": 195874667888640.0,
"train_loss": 0.515247056504611,
"train_runtime": 22871.536,
"train_samples_per_second": 1.309,
"train_steps_per_second": 0.082
}
],
"logging_steps": 5,
"max_steps": 1871,
"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": 195874667888640.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}