zephyr-phi-1_5-sft-qlora / trainer_state.json
Ritvik19's picture
Upload 15 files
a2d8bbc verified
raw
history blame
34.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.99981234753237,
"eval_steps": 500,
"global_step": 999,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010008131606930632,
"grad_norm": 0.09912109375,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.7364,
"step": 1
},
{
"epoch": 0.005004065803465315,
"grad_norm": 0.09228515625,
"learning_rate": 1e-05,
"loss": 1.7255,
"step": 5
},
{
"epoch": 0.01000813160693063,
"grad_norm": 0.10009765625,
"learning_rate": 2e-05,
"loss": 1.693,
"step": 10
},
{
"epoch": 0.015012197410395946,
"grad_norm": 0.10546875,
"learning_rate": 3e-05,
"loss": 1.7131,
"step": 15
},
{
"epoch": 0.02001626321386126,
"grad_norm": 0.1298828125,
"learning_rate": 4e-05,
"loss": 1.6944,
"step": 20
},
{
"epoch": 0.02502032901732658,
"grad_norm": 0.162109375,
"learning_rate": 5e-05,
"loss": 1.6902,
"step": 25
},
{
"epoch": 0.030024394820791892,
"grad_norm": 0.1982421875,
"learning_rate": 6e-05,
"loss": 1.6689,
"step": 30
},
{
"epoch": 0.035028460624257206,
"grad_norm": 0.173828125,
"learning_rate": 7e-05,
"loss": 1.6255,
"step": 35
},
{
"epoch": 0.04003252642772252,
"grad_norm": 0.1611328125,
"learning_rate": 8e-05,
"loss": 1.5785,
"step": 40
},
{
"epoch": 0.04503659223118784,
"grad_norm": 0.1357421875,
"learning_rate": 9e-05,
"loss": 1.5011,
"step": 45
},
{
"epoch": 0.05004065803465316,
"grad_norm": 0.1376953125,
"learning_rate": 0.0001,
"loss": 1.4936,
"step": 50
},
{
"epoch": 0.055044723838118474,
"grad_norm": 0.08740234375,
"learning_rate": 0.00011000000000000002,
"loss": 1.48,
"step": 55
},
{
"epoch": 0.060048789641583784,
"grad_norm": 0.06591796875,
"learning_rate": 0.00012,
"loss": 1.4597,
"step": 60
},
{
"epoch": 0.0650528554450491,
"grad_norm": 0.04345703125,
"learning_rate": 0.00013000000000000002,
"loss": 1.4573,
"step": 65
},
{
"epoch": 0.07005692124851441,
"grad_norm": 0.0322265625,
"learning_rate": 0.00014,
"loss": 1.4094,
"step": 70
},
{
"epoch": 0.07506098705197974,
"grad_norm": 0.037353515625,
"learning_rate": 0.00015000000000000001,
"loss": 1.4073,
"step": 75
},
{
"epoch": 0.08006505285544505,
"grad_norm": 0.0277099609375,
"learning_rate": 0.00016,
"loss": 1.4222,
"step": 80
},
{
"epoch": 0.08506911865891037,
"grad_norm": 0.0230712890625,
"learning_rate": 0.00017,
"loss": 1.4125,
"step": 85
},
{
"epoch": 0.09007318446237568,
"grad_norm": 0.021728515625,
"learning_rate": 0.00018,
"loss": 1.3956,
"step": 90
},
{
"epoch": 0.09507725026584099,
"grad_norm": 0.0211181640625,
"learning_rate": 0.00019,
"loss": 1.4091,
"step": 95
},
{
"epoch": 0.10008131606930631,
"grad_norm": 0.0198974609375,
"learning_rate": 0.0002,
"loss": 1.368,
"step": 100
},
{
"epoch": 0.10508538187277162,
"grad_norm": 0.0196533203125,
"learning_rate": 0.00019998473561448797,
"loss": 1.381,
"step": 105
},
{
"epoch": 0.11008944767623695,
"grad_norm": 0.01806640625,
"learning_rate": 0.0001999389471179811,
"loss": 1.3798,
"step": 110
},
{
"epoch": 0.11509351347970226,
"grad_norm": 0.017333984375,
"learning_rate": 0.00019986264848914474,
"loss": 1.3918,
"step": 115
},
{
"epoch": 0.12009757928316757,
"grad_norm": 0.017578125,
"learning_rate": 0.00019975586302101248,
"loss": 1.3851,
"step": 120
},
{
"epoch": 0.12510164508663288,
"grad_norm": 0.017578125,
"learning_rate": 0.00019961862331387543,
"loss": 1.3727,
"step": 125
},
{
"epoch": 0.1301057108900982,
"grad_norm": 0.0169677734375,
"learning_rate": 0.00019945097126532955,
"loss": 1.3798,
"step": 130
},
{
"epoch": 0.13510977669356353,
"grad_norm": 0.016357421875,
"learning_rate": 0.0001992529580574848,
"loss": 1.3553,
"step": 135
},
{
"epoch": 0.14011384249702882,
"grad_norm": 0.01953125,
"learning_rate": 0.00019902464414134005,
"loss": 1.3801,
"step": 140
},
{
"epoch": 0.14511790830049415,
"grad_norm": 0.0203857421875,
"learning_rate": 0.000198766099218328,
"loss": 1.354,
"step": 145
},
{
"epoch": 0.15012197410395947,
"grad_norm": 0.01806640625,
"learning_rate": 0.0001984774022190361,
"loss": 1.3874,
"step": 150
},
{
"epoch": 0.1551260399074248,
"grad_norm": 0.0166015625,
"learning_rate": 0.0001981586412791103,
"loss": 1.3565,
"step": 155
},
{
"epoch": 0.1601301057108901,
"grad_norm": 0.0177001953125,
"learning_rate": 0.00019780991371234801,
"loss": 1.3525,
"step": 160
},
{
"epoch": 0.16513417151435542,
"grad_norm": 0.01806640625,
"learning_rate": 0.00019743132598098963,
"loss": 1.3537,
"step": 165
},
{
"epoch": 0.17013823731782074,
"grad_norm": 0.02734375,
"learning_rate": 0.00019702299366321677,
"loss": 1.3681,
"step": 170
},
{
"epoch": 0.17514230312128604,
"grad_norm": 0.0201416015625,
"learning_rate": 0.00019658504141786774,
"loss": 1.3453,
"step": 175
},
{
"epoch": 0.18014636892475136,
"grad_norm": 0.0184326171875,
"learning_rate": 0.0001961176029463807,
"loss": 1.3701,
"step": 180
},
{
"epoch": 0.18515043472821668,
"grad_norm": 0.021240234375,
"learning_rate": 0.00019562082095197632,
"loss": 1.3525,
"step": 185
},
{
"epoch": 0.19015450053168198,
"grad_norm": 0.02001953125,
"learning_rate": 0.00019509484709609215,
"loss": 1.3427,
"step": 190
},
{
"epoch": 0.1951585663351473,
"grad_norm": 0.02001953125,
"learning_rate": 0.0001945398419520823,
"loss": 1.3469,
"step": 195
},
{
"epoch": 0.20016263213861263,
"grad_norm": 0.021484375,
"learning_rate": 0.00019395597495619634,
"loss": 1.3413,
"step": 200
},
{
"epoch": 0.20516669794207792,
"grad_norm": 0.0230712890625,
"learning_rate": 0.00019334342435585255,
"loss": 1.3604,
"step": 205
},
{
"epoch": 0.21017076374554325,
"grad_norm": 0.0211181640625,
"learning_rate": 0.00019270237715522112,
"loss": 1.3695,
"step": 210
},
{
"epoch": 0.21517482954900857,
"grad_norm": 0.02197265625,
"learning_rate": 0.00019203302905813406,
"loss": 1.3443,
"step": 215
},
{
"epoch": 0.2201788953524739,
"grad_norm": 0.0211181640625,
"learning_rate": 0.00019133558440833926,
"loss": 1.336,
"step": 220
},
{
"epoch": 0.2251829611559392,
"grad_norm": 0.0234375,
"learning_rate": 0.00019061025612711699,
"loss": 1.373,
"step": 225
},
{
"epoch": 0.23018702695940452,
"grad_norm": 0.021728515625,
"learning_rate": 0.00018985726564827728,
"loss": 1.3571,
"step": 230
},
{
"epoch": 0.23519109276286984,
"grad_norm": 0.0218505859375,
"learning_rate": 0.0001890768428505593,
"loss": 1.3279,
"step": 235
},
{
"epoch": 0.24019515856633514,
"grad_norm": 0.023193359375,
"learning_rate": 0.00018826922598745197,
"loss": 1.358,
"step": 240
},
{
"epoch": 0.24519922436980046,
"grad_norm": 0.0250244140625,
"learning_rate": 0.00018743466161445823,
"loss": 1.3361,
"step": 245
},
{
"epoch": 0.25020329017326576,
"grad_norm": 0.02197265625,
"learning_rate": 0.00018657340451382447,
"loss": 1.3324,
"step": 250
},
{
"epoch": 0.2552073559767311,
"grad_norm": 0.0213623046875,
"learning_rate": 0.00018568571761675893,
"loss": 1.3304,
"step": 255
},
{
"epoch": 0.2602114217801964,
"grad_norm": 0.0225830078125,
"learning_rate": 0.00018477187192316184,
"loss": 1.3585,
"step": 260
},
{
"epoch": 0.2652154875836617,
"grad_norm": 0.0250244140625,
"learning_rate": 0.00018383214641889243,
"loss": 1.3295,
"step": 265
},
{
"epoch": 0.27021955338712705,
"grad_norm": 0.024658203125,
"learning_rate": 0.00018286682799059824,
"loss": 1.3565,
"step": 270
},
{
"epoch": 0.27522361919059235,
"grad_norm": 0.0223388671875,
"learning_rate": 0.00018187621133813187,
"loss": 1.3314,
"step": 275
},
{
"epoch": 0.28022768499405765,
"grad_norm": 0.0228271484375,
"learning_rate": 0.00018086059888458288,
"loss": 1.3395,
"step": 280
},
{
"epoch": 0.285231750797523,
"grad_norm": 0.0218505859375,
"learning_rate": 0.0001798203006839517,
"loss": 1.3486,
"step": 285
},
{
"epoch": 0.2902358166009883,
"grad_norm": 0.022216796875,
"learning_rate": 0.00017875563432649392,
"loss": 1.3341,
"step": 290
},
{
"epoch": 0.29523988240445365,
"grad_norm": 0.0245361328125,
"learning_rate": 0.0001776669248417641,
"loss": 1.3409,
"step": 295
},
{
"epoch": 0.30024394820791894,
"grad_norm": 0.0235595703125,
"learning_rate": 0.00017655450459938784,
"loss": 1.3506,
"step": 300
},
{
"epoch": 0.30524801401138424,
"grad_norm": 0.0242919921875,
"learning_rate": 0.00017541871320759378,
"loss": 1.3523,
"step": 305
},
{
"epoch": 0.3102520798148496,
"grad_norm": 0.0230712890625,
"learning_rate": 0.0001742598974095353,
"loss": 1.3328,
"step": 310
},
{
"epoch": 0.3152561456183149,
"grad_norm": 0.0220947265625,
"learning_rate": 0.0001730784109774339,
"loss": 1.3394,
"step": 315
},
{
"epoch": 0.3202602114217802,
"grad_norm": 0.0224609375,
"learning_rate": 0.00017187461460457717,
"loss": 1.3379,
"step": 320
},
{
"epoch": 0.32526427722524553,
"grad_norm": 0.0233154296875,
"learning_rate": 0.00017064887579520334,
"loss": 1.317,
"step": 325
},
{
"epoch": 0.33026834302871083,
"grad_norm": 0.02197265625,
"learning_rate": 0.00016940156875230687,
"loss": 1.3257,
"step": 330
},
{
"epoch": 0.3352724088321761,
"grad_norm": 0.0220947265625,
"learning_rate": 0.00016813307426339892,
"loss": 1.3265,
"step": 335
},
{
"epoch": 0.3402764746356415,
"grad_norm": 0.0235595703125,
"learning_rate": 0.0001668437795842574,
"loss": 1.3372,
"step": 340
},
{
"epoch": 0.3452805404391068,
"grad_norm": 0.024658203125,
"learning_rate": 0.00016553407832070277,
"loss": 1.3559,
"step": 345
},
{
"epoch": 0.35028460624257207,
"grad_norm": 0.02490234375,
"learning_rate": 0.00016420437030843484,
"loss": 1.3396,
"step": 350
},
{
"epoch": 0.3552886720460374,
"grad_norm": 0.025634765625,
"learning_rate": 0.00016285506149096794,
"loss": 1.3437,
"step": 355
},
{
"epoch": 0.3602927378495027,
"grad_norm": 0.0269775390625,
"learning_rate": 0.00016148656379570144,
"loss": 1.3409,
"step": 360
},
{
"epoch": 0.365296803652968,
"grad_norm": 0.029052734375,
"learning_rate": 0.0001600992950081632,
"loss": 1.3445,
"step": 365
},
{
"epoch": 0.37030086945643337,
"grad_norm": 0.026123046875,
"learning_rate": 0.0001586936786444648,
"loss": 1.3533,
"step": 370
},
{
"epoch": 0.37530493525989866,
"grad_norm": 0.0234375,
"learning_rate": 0.0001572701438220074,
"loss": 1.343,
"step": 375
},
{
"epoch": 0.38030900106336396,
"grad_norm": 0.026611328125,
"learning_rate": 0.0001558291251284774,
"loss": 1.3617,
"step": 380
},
{
"epoch": 0.3853130668668293,
"grad_norm": 0.0274658203125,
"learning_rate": 0.00015437106248917217,
"loss": 1.323,
"step": 385
},
{
"epoch": 0.3903171326702946,
"grad_norm": 0.0235595703125,
"learning_rate": 0.00015289640103269625,
"loss": 1.3186,
"step": 390
},
{
"epoch": 0.3953211984737599,
"grad_norm": 0.0262451171875,
"learning_rate": 0.00015140559095506908,
"loss": 1.3228,
"step": 395
},
{
"epoch": 0.40032526427722526,
"grad_norm": 0.02685546875,
"learning_rate": 0.00014989908738228567,
"loss": 1.3341,
"step": 400
},
{
"epoch": 0.40532933008069055,
"grad_norm": 0.024658203125,
"learning_rate": 0.00014837735023137216,
"loss": 1.3479,
"step": 405
},
{
"epoch": 0.41033339588415585,
"grad_norm": 0.0267333984375,
"learning_rate": 0.00014684084406997903,
"loss": 1.3272,
"step": 410
},
{
"epoch": 0.4153374616876212,
"grad_norm": 0.0262451171875,
"learning_rate": 0.00014529003797455402,
"loss": 1.338,
"step": 415
},
{
"epoch": 0.4203415274910865,
"grad_norm": 0.024658203125,
"learning_rate": 0.000143725405387139,
"loss": 1.3344,
"step": 420
},
{
"epoch": 0.42534559329455185,
"grad_norm": 0.023681640625,
"learning_rate": 0.000142147423970834,
"loss": 1.3262,
"step": 425
},
{
"epoch": 0.43034965909801715,
"grad_norm": 0.024658203125,
"learning_rate": 0.0001405565754639724,
"loss": 1.3282,
"step": 430
},
{
"epoch": 0.43535372490148244,
"grad_norm": 0.0238037109375,
"learning_rate": 0.00013895334553305216,
"loss": 1.3363,
"step": 435
},
{
"epoch": 0.4403577907049478,
"grad_norm": 0.0281982421875,
"learning_rate": 0.0001373382236244679,
"loss": 1.3365,
"step": 440
},
{
"epoch": 0.4453618565084131,
"grad_norm": 0.0242919921875,
"learning_rate": 0.0001357117028150889,
"loss": 1.338,
"step": 445
},
{
"epoch": 0.4503659223118784,
"grad_norm": 0.0240478515625,
"learning_rate": 0.00013407427966172865,
"loss": 1.3344,
"step": 450
},
{
"epoch": 0.45536998811534374,
"grad_norm": 0.0257568359375,
"learning_rate": 0.00013242645404955237,
"loss": 1.3576,
"step": 455
},
{
"epoch": 0.46037405391880903,
"grad_norm": 0.02734375,
"learning_rate": 0.00013076872903946806,
"loss": 1.3258,
"step": 460
},
{
"epoch": 0.46537811972227433,
"grad_norm": 0.02490234375,
"learning_rate": 0.0001291016107145483,
"loss": 1.3441,
"step": 465
},
{
"epoch": 0.4703821855257397,
"grad_norm": 0.02490234375,
"learning_rate": 0.00012742560802552912,
"loss": 1.3255,
"step": 470
},
{
"epoch": 0.475386251329205,
"grad_norm": 0.0272216796875,
"learning_rate": 0.00012574123263543388,
"loss": 1.3483,
"step": 475
},
{
"epoch": 0.4803903171326703,
"grad_norm": 0.025146484375,
"learning_rate": 0.0001240489987633686,
"loss": 1.3465,
"step": 480
},
{
"epoch": 0.4853943829361356,
"grad_norm": 0.0247802734375,
"learning_rate": 0.0001223494230275372,
"loss": 1.3419,
"step": 485
},
{
"epoch": 0.4903984487396009,
"grad_norm": 0.0244140625,
"learning_rate": 0.0001206430242875246,
"loss": 1.3168,
"step": 490
},
{
"epoch": 0.4954025145430662,
"grad_norm": 0.0247802734375,
"learning_rate": 0.00011893032348589478,
"loss": 1.3379,
"step": 495
},
{
"epoch": 0.5004065803465315,
"grad_norm": 0.025390625,
"learning_rate": 0.00011721184348915384,
"loss": 1.3195,
"step": 500
},
{
"epoch": 0.5054106461499969,
"grad_norm": 0.024169921875,
"learning_rate": 0.00011548810892812505,
"loss": 1.3169,
"step": 505
},
{
"epoch": 0.5104147119534622,
"grad_norm": 0.0245361328125,
"learning_rate": 0.00011375964603778561,
"loss": 1.3208,
"step": 510
},
{
"epoch": 0.5154187777569275,
"grad_norm": 0.025390625,
"learning_rate": 0.00011202698249661364,
"loss": 1.3139,
"step": 515
},
{
"epoch": 0.5204228435603928,
"grad_norm": 0.0238037109375,
"learning_rate": 0.00011029064726549412,
"loss": 1.3217,
"step": 520
},
{
"epoch": 0.5254269093638582,
"grad_norm": 0.025634765625,
"learning_rate": 0.000108551170426234,
"loss": 1.3115,
"step": 525
},
{
"epoch": 0.5304309751673234,
"grad_norm": 0.0272216796875,
"learning_rate": 0.0001068090830197346,
"loss": 1.3709,
"step": 530
},
{
"epoch": 0.5354350409707888,
"grad_norm": 0.0257568359375,
"learning_rate": 0.00010506491688387127,
"loss": 1.3332,
"step": 535
},
{
"epoch": 0.5404391067742541,
"grad_norm": 0.025634765625,
"learning_rate": 0.00010331920449112991,
"loss": 1.3496,
"step": 540
},
{
"epoch": 0.5454431725777193,
"grad_norm": 0.0260009765625,
"learning_rate": 0.00010157247878604961,
"loss": 1.3611,
"step": 545
},
{
"epoch": 0.5504472383811847,
"grad_norm": 0.024658203125,
"learning_rate": 9.982527302252135e-05,
"loss": 1.3502,
"step": 550
},
{
"epoch": 0.55545130418465,
"grad_norm": 0.0235595703125,
"learning_rate": 9.807812060099191e-05,
"loss": 1.3278,
"step": 555
},
{
"epoch": 0.5604553699881153,
"grad_norm": 0.0244140625,
"learning_rate": 9.633155490562358e-05,
"loss": 1.3605,
"step": 560
},
{
"epoch": 0.5654594357915806,
"grad_norm": 0.0235595703125,
"learning_rate": 9.458610914145826e-05,
"loss": 1.3379,
"step": 565
},
{
"epoch": 0.570463501595046,
"grad_norm": 0.0257568359375,
"learning_rate": 9.284231617163666e-05,
"loss": 1.3085,
"step": 570
},
{
"epoch": 0.5754675673985112,
"grad_norm": 0.0252685546875,
"learning_rate": 9.11007083547216e-05,
"loss": 1.3415,
"step": 575
},
{
"epoch": 0.5804716332019766,
"grad_norm": 0.0252685546875,
"learning_rate": 8.936181738217571e-05,
"loss": 1.3251,
"step": 580
},
{
"epoch": 0.5854756990054419,
"grad_norm": 0.0262451171875,
"learning_rate": 8.762617411604235e-05,
"loss": 1.3519,
"step": 585
},
{
"epoch": 0.5904797648089073,
"grad_norm": 0.0252685546875,
"learning_rate": 8.589430842688001e-05,
"loss": 1.3148,
"step": 590
},
{
"epoch": 0.5954838306123725,
"grad_norm": 0.02685546875,
"learning_rate": 8.41667490319994e-05,
"loss": 1.3169,
"step": 595
},
{
"epoch": 0.6004878964158379,
"grad_norm": 0.024658203125,
"learning_rate": 8.244402333405252e-05,
"loss": 1.3561,
"step": 600
},
{
"epoch": 0.6054919622193032,
"grad_norm": 0.025146484375,
"learning_rate": 8.0726657260023e-05,
"loss": 1.3059,
"step": 605
},
{
"epoch": 0.6104960280227685,
"grad_norm": 0.0245361328125,
"learning_rate": 7.901517510066724e-05,
"loss": 1.329,
"step": 610
},
{
"epoch": 0.6155000938262338,
"grad_norm": 0.0250244140625,
"learning_rate": 7.73100993504548e-05,
"loss": 1.3412,
"step": 615
},
{
"epoch": 0.6205041596296992,
"grad_norm": 0.025146484375,
"learning_rate": 7.561195054805729e-05,
"loss": 1.3447,
"step": 620
},
{
"epoch": 0.6255082254331644,
"grad_norm": 0.02392578125,
"learning_rate": 7.392124711743422e-05,
"loss": 1.3445,
"step": 625
},
{
"epoch": 0.6305122912366298,
"grad_norm": 0.025634765625,
"learning_rate": 7.223850520956457e-05,
"loss": 1.3078,
"step": 630
},
{
"epoch": 0.6355163570400951,
"grad_norm": 0.026123046875,
"learning_rate": 7.056423854487236e-05,
"loss": 1.3427,
"step": 635
},
{
"epoch": 0.6405204228435604,
"grad_norm": 0.0244140625,
"learning_rate": 6.889895825639401e-05,
"loss": 1.3364,
"step": 640
},
{
"epoch": 0.6455244886470257,
"grad_norm": 0.0263671875,
"learning_rate": 6.724317273373563e-05,
"loss": 1.3555,
"step": 645
},
{
"epoch": 0.6505285544504911,
"grad_norm": 0.02587890625,
"learning_rate": 6.55973874678682e-05,
"loss": 1.3542,
"step": 650
},
{
"epoch": 0.6555326202539563,
"grad_norm": 0.025390625,
"learning_rate": 6.396210489680699e-05,
"loss": 1.3421,
"step": 655
},
{
"epoch": 0.6605366860574217,
"grad_norm": 0.0240478515625,
"learning_rate": 6.23378242522237e-05,
"loss": 1.3395,
"step": 660
},
{
"epoch": 0.665540751860887,
"grad_norm": 0.02490234375,
"learning_rate": 6.072504140703714e-05,
"loss": 1.3291,
"step": 665
},
{
"epoch": 0.6705448176643523,
"grad_norm": 0.0255126953125,
"learning_rate": 5.912424872402927e-05,
"loss": 1.33,
"step": 670
},
{
"epoch": 0.6755488834678176,
"grad_norm": 0.0257568359375,
"learning_rate": 5.7535934905532816e-05,
"loss": 1.3547,
"step": 675
},
{
"epoch": 0.680552949271283,
"grad_norm": 0.02490234375,
"learning_rate": 5.596058484423656e-05,
"loss": 1.344,
"step": 680
},
{
"epoch": 0.6855570150747482,
"grad_norm": 0.025390625,
"learning_rate": 5.43986794751536e-05,
"loss": 1.3617,
"step": 685
},
{
"epoch": 0.6905610808782136,
"grad_norm": 0.023193359375,
"learning_rate": 5.285069562879758e-05,
"loss": 1.3275,
"step": 690
},
{
"epoch": 0.6955651466816789,
"grad_norm": 0.0245361328125,
"learning_rate": 5.1317105885612524e-05,
"loss": 1.3459,
"step": 695
},
{
"epoch": 0.7005692124851441,
"grad_norm": 0.026123046875,
"learning_rate": 4.9798378431699585e-05,
"loss": 1.3345,
"step": 700
},
{
"epoch": 0.7055732782886095,
"grad_norm": 0.0260009765625,
"learning_rate": 4.829497691588557e-05,
"loss": 1.3208,
"step": 705
},
{
"epoch": 0.7105773440920748,
"grad_norm": 0.02587890625,
"learning_rate": 4.680736030817687e-05,
"loss": 1.3546,
"step": 710
},
{
"epoch": 0.7155814098955401,
"grad_norm": 0.0240478515625,
"learning_rate": 4.533598275964139e-05,
"loss": 1.326,
"step": 715
},
{
"epoch": 0.7205854756990054,
"grad_norm": 0.0250244140625,
"learning_rate": 4.388129346376178e-05,
"loss": 1.3337,
"step": 720
},
{
"epoch": 0.7255895415024708,
"grad_norm": 0.025390625,
"learning_rate": 4.2443736519302314e-05,
"loss": 1.3264,
"step": 725
},
{
"epoch": 0.730593607305936,
"grad_norm": 0.0250244140625,
"learning_rate": 4.102375079473087e-05,
"loss": 1.3214,
"step": 730
},
{
"epoch": 0.7355976731094014,
"grad_norm": 0.0255126953125,
"learning_rate": 3.9621769794237894e-05,
"loss": 1.3318,
"step": 735
},
{
"epoch": 0.7406017389128667,
"grad_norm": 0.0247802734375,
"learning_rate": 3.823822152539286e-05,
"loss": 1.3327,
"step": 740
},
{
"epoch": 0.745605804716332,
"grad_norm": 0.025146484375,
"learning_rate": 3.687352836847874e-05,
"loss": 1.3486,
"step": 745
},
{
"epoch": 0.7506098705197973,
"grad_norm": 0.0252685546875,
"learning_rate": 3.552810694754463e-05,
"loss": 1.329,
"step": 750
},
{
"epoch": 0.7556139363232627,
"grad_norm": 0.025634765625,
"learning_rate": 3.42023680032154e-05,
"loss": 1.3553,
"step": 755
},
{
"epoch": 0.7606180021267279,
"grad_norm": 0.0240478515625,
"learning_rate": 3.289671626729772e-05,
"loss": 1.3087,
"step": 760
},
{
"epoch": 0.7656220679301933,
"grad_norm": 0.0244140625,
"learning_rate": 3.161155033922045e-05,
"loss": 1.3299,
"step": 765
},
{
"epoch": 0.7706261337336586,
"grad_norm": 0.02392578125,
"learning_rate": 3.0347262564347057e-05,
"loss": 1.3156,
"step": 770
},
{
"epoch": 0.7756301995371239,
"grad_norm": 0.02587890625,
"learning_rate": 2.9104238914197445e-05,
"loss": 1.3171,
"step": 775
},
{
"epoch": 0.7806342653405892,
"grad_norm": 0.02392578125,
"learning_rate": 2.7882858868615467e-05,
"loss": 1.3415,
"step": 780
},
{
"epoch": 0.7856383311440546,
"grad_norm": 0.023193359375,
"learning_rate": 2.6683495299918648e-05,
"loss": 1.3576,
"step": 785
},
{
"epoch": 0.7906423969475198,
"grad_norm": 0.025146484375,
"learning_rate": 2.550651435906456e-05,
"loss": 1.309,
"step": 790
},
{
"epoch": 0.7956464627509852,
"grad_norm": 0.0272216796875,
"learning_rate": 2.435227536386967e-05,
"loss": 1.3299,
"step": 795
},
{
"epoch": 0.8006505285544505,
"grad_norm": 0.0240478515625,
"learning_rate": 2.3221130689313907e-05,
"loss": 1.3354,
"step": 800
},
{
"epoch": 0.8056545943579158,
"grad_norm": 0.023681640625,
"learning_rate": 2.211342565996487e-05,
"loss": 1.3262,
"step": 805
},
{
"epoch": 0.8106586601613811,
"grad_norm": 0.025390625,
"learning_rate": 2.1029498444554618e-05,
"loss": 1.3339,
"step": 810
},
{
"epoch": 0.8156627259648465,
"grad_norm": 0.02490234375,
"learning_rate": 1.9969679952740805e-05,
"loss": 1.3516,
"step": 815
},
{
"epoch": 0.8206667917683117,
"grad_norm": 0.0234375,
"learning_rate": 1.893429373408411e-05,
"loss": 1.3399,
"step": 820
},
{
"epoch": 0.825670857571777,
"grad_norm": 0.0242919921875,
"learning_rate": 1.7923655879272393e-05,
"loss": 1.3149,
"step": 825
},
{
"epoch": 0.8306749233752424,
"grad_norm": 0.0242919921875,
"learning_rate": 1.6938074923622227e-05,
"loss": 1.3292,
"step": 830
},
{
"epoch": 0.8356789891787078,
"grad_norm": 0.0242919921875,
"learning_rate": 1.597785175288683e-05,
"loss": 1.3325,
"step": 835
},
{
"epoch": 0.840683054982173,
"grad_norm": 0.0245361328125,
"learning_rate": 1.5043279511399333e-05,
"loss": 1.3544,
"step": 840
},
{
"epoch": 0.8456871207856383,
"grad_norm": 0.0245361328125,
"learning_rate": 1.4134643512579382e-05,
"loss": 1.3601,
"step": 845
},
{
"epoch": 0.8506911865891037,
"grad_norm": 0.0238037109375,
"learning_rate": 1.3252221151830513e-05,
"loss": 1.3447,
"step": 850
},
{
"epoch": 0.8556952523925689,
"grad_norm": 0.0238037109375,
"learning_rate": 1.2396281821854683e-05,
"loss": 1.3296,
"step": 855
},
{
"epoch": 0.8606993181960343,
"grad_norm": 0.024169921875,
"learning_rate": 1.156708683041008e-05,
"loss": 1.3187,
"step": 860
},
{
"epoch": 0.8657033839994996,
"grad_norm": 0.024169921875,
"learning_rate": 1.0764889320536931e-05,
"loss": 1.3136,
"step": 865
},
{
"epoch": 0.8707074498029649,
"grad_norm": 0.023193359375,
"learning_rate": 9.989934193276219e-06,
"loss": 1.323,
"step": 870
},
{
"epoch": 0.8757115156064302,
"grad_norm": 0.024658203125,
"learning_rate": 9.242458032904311e-06,
"loss": 1.3221,
"step": 875
},
{
"epoch": 0.8807155814098956,
"grad_norm": 0.02587890625,
"learning_rate": 8.52268903470661e-06,
"loss": 1.3413,
"step": 880
},
{
"epoch": 0.8857196472133608,
"grad_norm": 0.0242919921875,
"learning_rate": 7.830846935312509e-06,
"loss": 1.3342,
"step": 885
},
{
"epoch": 0.8907237130168262,
"grad_norm": 0.0245361328125,
"learning_rate": 7.167142945612393e-06,
"loss": 1.3265,
"step": 890
},
{
"epoch": 0.8957277788202915,
"grad_norm": 0.0238037109375,
"learning_rate": 6.531779686277528e-06,
"loss": 1.3387,
"step": 895
},
{
"epoch": 0.9007318446237568,
"grad_norm": 0.02392578125,
"learning_rate": 5.924951125902545e-06,
"loss": 1.3167,
"step": 900
},
{
"epoch": 0.9057359104272221,
"grad_norm": 0.0235595703125,
"learning_rate": 5.346842521789141e-06,
"loss": 1.3465,
"step": 905
},
{
"epoch": 0.9107399762306875,
"grad_norm": 0.0244140625,
"learning_rate": 4.7976303633893384e-06,
"loss": 1.3396,
"step": 910
},
{
"epoch": 0.9157440420341527,
"grad_norm": 0.0250244140625,
"learning_rate": 4.277482318425408e-06,
"loss": 1.3569,
"step": 915
},
{
"epoch": 0.9207481078376181,
"grad_norm": 0.025390625,
"learning_rate": 3.7865571817029877e-06,
"loss": 1.3265,
"step": 920
},
{
"epoch": 0.9257521736410834,
"grad_norm": 0.025390625,
"learning_rate": 3.3250048266329825e-06,
"loss": 1.3392,
"step": 925
},
{
"epoch": 0.9307562394445487,
"grad_norm": 0.024658203125,
"learning_rate": 2.8929661594770174e-06,
"loss": 1.3597,
"step": 930
},
{
"epoch": 0.935760305248014,
"grad_norm": 0.0257568359375,
"learning_rate": 2.4905730763305047e-06,
"loss": 1.3329,
"step": 935
},
{
"epoch": 0.9407643710514794,
"grad_norm": 0.025146484375,
"learning_rate": 2.1179484228564305e-06,
"loss": 1.3497,
"step": 940
},
{
"epoch": 0.9457684368549446,
"grad_norm": 0.02392578125,
"learning_rate": 1.7752059567820333e-06,
"loss": 1.3367,
"step": 945
},
{
"epoch": 0.95077250265841,
"grad_norm": 0.0245361328125,
"learning_rate": 1.4624503131699828e-06,
"loss": 1.3459,
"step": 950
},
{
"epoch": 0.9557765684618753,
"grad_norm": 0.02490234375,
"learning_rate": 1.1797769724745888e-06,
"loss": 1.3326,
"step": 955
},
{
"epoch": 0.9607806342653405,
"grad_norm": 0.024169921875,
"learning_rate": 9.272722313927617e-07,
"loss": 1.3487,
"step": 960
},
{
"epoch": 0.9657847000688059,
"grad_norm": 0.0247802734375,
"learning_rate": 7.05013176518754e-07,
"loss": 1.3647,
"step": 965
},
{
"epoch": 0.9707887658722713,
"grad_norm": 0.0233154296875,
"learning_rate": 5.130676608104845e-07,
"loss": 1.3482,
"step": 970
},
{
"epoch": 0.9757928316757365,
"grad_norm": 0.0247802734375,
"learning_rate": 3.5149428287495343e-07,
"loss": 1.3423,
"step": 975
},
{
"epoch": 0.9807968974792018,
"grad_norm": 0.02587890625,
"learning_rate": 2.2034236907874094e-07,
"loss": 1.3267,
"step": 980
},
{
"epoch": 0.9858009632826672,
"grad_norm": 0.0238037109375,
"learning_rate": 1.1965195848929745e-07,
"loss": 1.3185,
"step": 985
},
{
"epoch": 0.9908050290861324,
"grad_norm": 0.02392578125,
"learning_rate": 4.945379065152134e-08,
"loss": 1.3129,
"step": 990
},
{
"epoch": 0.9958090948895978,
"grad_norm": 0.024658203125,
"learning_rate": 9.769296203332446e-09,
"loss": 1.3423,
"step": 995
},
{
"epoch": 0.99981234753237,
"eval_loss": 1.343445897102356,
"eval_runtime": 1960.9798,
"eval_samples_per_second": 7.216,
"eval_steps_per_second": 7.216,
"step": 999
},
{
"epoch": 0.99981234753237,
"step": 999,
"total_flos": 2.0711686751461048e+18,
"train_loss": 0.052138939037456644,
"train_runtime": 4093.6241,
"train_samples_per_second": 31.243,
"train_steps_per_second": 0.244
}
],
"logging_steps": 5,
"max_steps": 999,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 20,
"total_flos": 2.0711686751461048e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}