541 lines
13 KiB
JSON
541 lines
13 KiB
JSON
|
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.5002627430373097,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 714,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"epoch": 0.021019442984760904,
|
||
|
|
"grad_norm": 7.8125,
|
||
|
|
"learning_rate": 1.2272727272727274e-06,
|
||
|
|
"loss": 2.139740753173828,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.04203888596952181,
|
||
|
|
"grad_norm": 5.96875,
|
||
|
|
"learning_rate": 2.590909090909091e-06,
|
||
|
|
"loss": 2.2081624984741213,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0630583289542827,
|
||
|
|
"grad_norm": 14.125,
|
||
|
|
"learning_rate": 2.999242629561838e-06,
|
||
|
|
"loss": 2.0339645385742187,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08407777193904362,
|
||
|
|
"grad_norm": 5.90625,
|
||
|
|
"learning_rate": 2.995534901109399e-06,
|
||
|
|
"loss": 2.0348079681396483,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.10509721492380451,
|
||
|
|
"grad_norm": 4.8125,
|
||
|
|
"learning_rate": 2.9887453367135033e-06,
|
||
|
|
"loss": 1.950754165649414,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1261166579085654,
|
||
|
|
"grad_norm": 6.09375,
|
||
|
|
"learning_rate": 2.9788879275712665e-06,
|
||
|
|
"loss": 1.9394699096679688,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14713610089332632,
|
||
|
|
"grad_norm": 2.921875,
|
||
|
|
"learning_rate": 2.9659829867611603e-06,
|
||
|
|
"loss": 1.880813980102539,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16815554387808723,
|
||
|
|
"grad_norm": 3.96875,
|
||
|
|
"learning_rate": 2.9500571073840264e-06,
|
||
|
|
"loss": 1.8970605850219726,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18917498686284814,
|
||
|
|
"grad_norm": 4.1875,
|
||
|
|
"learning_rate": 2.931143107762901e-06,
|
||
|
|
"loss": 1.8591070175170898,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.21019442984760903,
|
||
|
|
"grad_norm": 2.359375,
|
||
|
|
"learning_rate": 2.909279963814576e-06,
|
||
|
|
"loss": 1.892710304260254,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.23121387283236994,
|
||
|
|
"grad_norm": 3.125,
|
||
|
|
"learning_rate": 2.8845127287322656e-06,
|
||
|
|
"loss": 1.8118453979492188,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2522333158171308,
|
||
|
|
"grad_norm": 2.71875,
|
||
|
|
"learning_rate": 2.8568924401448738e-06,
|
||
|
|
"loss": 1.8849889755249023,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.27325275880189176,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 2.826476014944193e-06,
|
||
|
|
"loss": 1.8813108444213866,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.29427220178665264,
|
||
|
|
"grad_norm": 2.265625,
|
||
|
|
"learning_rate": 2.7933261319967516e-06,
|
||
|
|
"loss": 1.9071147918701172,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3152916447714136,
|
||
|
|
"grad_norm": 2.828125,
|
||
|
|
"learning_rate": 2.7575111029820103e-06,
|
||
|
|
"loss": 1.8963701248168945,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.33631108775617446,
|
||
|
|
"grad_norm": 2.953125,
|
||
|
|
"learning_rate": 2.7191047316230743e-06,
|
||
|
|
"loss": 1.9282533645629882,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.35733053074093535,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 2.6781861615999896e-06,
|
||
|
|
"loss": 1.7661924362182617,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3783499737256963,
|
||
|
|
"grad_norm": 2.078125,
|
||
|
|
"learning_rate": 2.6348397134590424e-06,
|
||
|
|
"loss": 1.784163475036621,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.39936941671045717,
|
||
|
|
"grad_norm": 1.765625,
|
||
|
|
"learning_rate": 2.5891547108541323e-06,
|
||
|
|
"loss": 1.8109502792358398,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.42038885969521805,
|
||
|
|
"grad_norm": 3.0625,
|
||
|
|
"learning_rate": 2.5412252964782867e-06,
|
||
|
|
"loss": 1.821950912475586,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.441408302679979,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 2.4911502380646164e-06,
|
||
|
|
"loss": 1.9059152603149414,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4624277456647399,
|
||
|
|
"grad_norm": 2.875,
|
||
|
|
"learning_rate": 2.4390327248564994e-06,
|
||
|
|
"loss": 1.8420991897583008,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4834471886495008,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 2.3849801549663886e-06,
|
||
|
|
"loss": 1.890372085571289,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5044666316342616,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 2.3291039140614475e-06,
|
||
|
|
"loss": 1.8288061141967773,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5254860746190226,
|
||
|
|
"grad_norm": 3.109375,
|
||
|
|
"learning_rate": 2.2715191458320545e-06,
|
||
|
|
"loss": 1.8653709411621093,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5465055176037835,
|
||
|
|
"grad_norm": 2.109375,
|
||
|
|
"learning_rate": 2.212344514716194e-06,
|
||
|
|
"loss": 1.771567153930664,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5675249605885444,
|
||
|
|
"grad_norm": 1.953125,
|
||
|
|
"learning_rate": 2.151701961368664e-06,
|
||
|
|
"loss": 1.7724361419677734,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5885444035733053,
|
||
|
|
"grad_norm": 4.6875,
|
||
|
|
"learning_rate": 2.0897164513790135e-06,
|
||
|
|
"loss": 1.7283151626586915,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6095638465580662,
|
||
|
|
"grad_norm": 2.8125,
|
||
|
|
"learning_rate": 2.026515717756026e-06,
|
||
|
|
"loss": 1.7711864471435548,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6305832895428272,
|
||
|
|
"grad_norm": 5.0,
|
||
|
|
"learning_rate": 1.9622299977094044e-06,
|
||
|
|
"loss": 1.7970991134643555,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.651602732527588,
|
||
|
|
"grad_norm": 1.890625,
|
||
|
|
"learning_rate": 1.8969917642710664e-06,
|
||
|
|
"loss": 1.8020233154296874,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6726221755123489,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 1.830935453309108e-06,
|
||
|
|
"loss": 1.8001415252685546,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6936416184971098,
|
||
|
|
"grad_norm": 2.3125,
|
||
|
|
"learning_rate": 1.764197186496962e-06,
|
||
|
|
"loss": 1.75347843170166,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7146610614818707,
|
||
|
|
"grad_norm": 6.4375,
|
||
|
|
"learning_rate": 1.6969144908086306e-06,
|
||
|
|
"loss": 1.809716033935547,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7356805044666316,
|
||
|
|
"grad_norm": 1.9921875,
|
||
|
|
"learning_rate": 1.6292260151180326e-06,
|
||
|
|
"loss": 1.7866138458251952,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7566999474513926,
|
||
|
|
"grad_norm": 3.6875,
|
||
|
|
"learning_rate": 1.5612712444864579e-06,
|
||
|
|
"loss": 1.8378917694091796,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7777193904361535,
|
||
|
|
"grad_norm": 2.078125,
|
||
|
|
"learning_rate": 1.4931902127268951e-06,
|
||
|
|
"loss": 1.7029869079589843,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7987388334209143,
|
||
|
|
"grad_norm": 1.9453125,
|
||
|
|
"learning_rate": 1.4251232138375584e-06,
|
||
|
|
"loss": 1.7460771560668946,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8197582764056752,
|
||
|
|
"grad_norm": 2.359375,
|
||
|
|
"learning_rate": 1.3572105128992455e-06,
|
||
|
|
"loss": 1.7742759704589843,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8407777193904361,
|
||
|
|
"grad_norm": 3.78125,
|
||
|
|
"learning_rate": 1.2895920570322904e-06,
|
||
|
|
"loss": 1.8007017135620118,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8617971623751971,
|
||
|
|
"grad_norm": 2.484375,
|
||
|
|
"learning_rate": 1.2224071870087317e-06,
|
||
|
|
"loss": 1.7528308868408202,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.882816605359958,
|
||
|
|
"grad_norm": 2.375,
|
||
|
|
"learning_rate": 1.1557943501139813e-06,
|
||
|
|
"loss": 1.8043436050415038,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9038360483447189,
|
||
|
|
"grad_norm": 1.625,
|
||
|
|
"learning_rate": 1.0898908148496853e-06,
|
||
|
|
"loss": 1.7981443405151367,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9248554913294798,
|
||
|
|
"grad_norm": 3.390625,
|
||
|
|
"learning_rate": 1.0248323880657068e-06,
|
||
|
|
"loss": 1.7500328063964843,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9458749343142406,
|
||
|
|
"grad_norm": 3.0,
|
||
|
|
"learning_rate": 9.607531351041108e-07,
|
||
|
|
"loss": 1.7884363174438476,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9668943772990016,
|
||
|
|
"grad_norm": 2.859375,
|
||
|
|
"learning_rate": 8.977851035318654e-07,
|
||
|
|
"loss": 1.714197540283203,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9879138202837625,
|
||
|
|
"grad_norm": 2.125,
|
||
|
|
"learning_rate": 8.360580510315521e-07,
|
||
|
|
"loss": 1.7554092407226562,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0084077771939044,
|
||
|
|
"grad_norm": 2.421875,
|
||
|
|
"learning_rate": 7.756991780108238e-07,
|
||
|
|
"loss": 1.7379329681396485,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0294272201786652,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 7.168328654816127e-07,
|
||
|
|
"loss": 1.692732810974121,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0504466631634262,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 6.595804187492498e-07,
|
||
|
|
"loss": 1.8081771850585937,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0714661061481872,
|
||
|
|
"grad_norm": 2.71875,
|
||
|
|
"learning_rate": 6.0405981743966e-07,
|
||
|
|
"loss": 1.7980724334716798,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.092485549132948,
|
||
|
|
"grad_norm": 4.34375,
|
||
|
|
"learning_rate": 5.503854723797599e-07,
|
||
|
|
"loss": 1.764889907836914,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.113504992117709,
|
||
|
|
"grad_norm": 4.53125,
|
||
|
|
"learning_rate": 4.986679898320476e-07,
|
||
|
|
"loss": 1.7189857482910156,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1345244351024697,
|
||
|
|
"grad_norm": 3.296875,
|
||
|
|
"learning_rate": 4.490139435692261e-07,
|
||
|
|
"loss": 1.7537565231323242,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1555438780872307,
|
||
|
|
"grad_norm": 3.234375,
|
||
|
|
"learning_rate": 4.0152565525854467e-07,
|
||
|
|
"loss": 1.6921497344970704,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1765633210719917,
|
||
|
|
"grad_norm": 3.15625,
|
||
|
|
"learning_rate": 3.5630098360841646e-07,
|
||
|
|
"loss": 1.7711572647094727,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1975827640567525,
|
||
|
|
"grad_norm": 1.8671875,
|
||
|
|
"learning_rate": 3.134331227118171e-07,
|
||
|
|
"loss": 1.6838041305541993,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2186022070415135,
|
||
|
|
"grad_norm": 2.09375,
|
||
|
|
"learning_rate": 2.7301041000201746e-07,
|
||
|
|
"loss": 1.73205509185791,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2396216500262742,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 2.351161442163905e-07,
|
||
|
|
"loss": 1.7526542663574218,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2606410930110352,
|
||
|
|
"grad_norm": 1.5859375,
|
||
|
|
"learning_rate": 1.998284137434206e-07,
|
||
|
|
"loss": 1.7869752883911132,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2816605359957962,
|
||
|
|
"grad_norm": 2.375,
|
||
|
|
"learning_rate": 1.6721993570662926e-07,
|
||
|
|
"loss": 1.828580093383789,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.302679978980557,
|
||
|
|
"grad_norm": 2.609375,
|
||
|
|
"learning_rate": 1.3735790611702274e-07,
|
||
|
|
"loss": 1.7601003646850586,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.323699421965318,
|
||
|
|
"grad_norm": 3.59375,
|
||
|
|
"learning_rate": 1.1030386140284865e-07,
|
||
|
|
"loss": 1.7960094451904296,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3447188649500788,
|
||
|
|
"grad_norm": 3.046875,
|
||
|
|
"learning_rate": 8.611355160200623e-08,
|
||
|
|
"loss": 1.7016435623168946,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3657383079348397,
|
||
|
|
"grad_norm": 1.7890625,
|
||
|
|
"learning_rate": 6.483682547842001e-08,
|
||
|
|
"loss": 1.7239088058471679,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3867577509196005,
|
||
|
|
"grad_norm": 1.6796875,
|
||
|
|
"learning_rate": 4.651752779912233e-08,
|
||
|
|
"loss": 1.7699031829833984,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4077771939043615,
|
||
|
|
"grad_norm": 1.9140625,
|
||
|
|
"learning_rate": 3.1193408983715475e-08,
|
||
|
|
"loss": 1.8059171676635741,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4287966368891225,
|
||
|
|
"grad_norm": 3.25,
|
||
|
|
"learning_rate": 1.8896047312406683e-08,
|
||
|
|
"loss": 1.7002668380737305,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4498160798738833,
|
||
|
|
"grad_norm": 2.015625,
|
||
|
|
"learning_rate": 9.650783852917178e-09,
|
||
|
|
"loss": 1.7966609954833985,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4708355228586443,
|
||
|
|
"grad_norm": 2.328125,
|
||
|
|
"learning_rate": 3.4766702403609684e-09,
|
||
|
|
"loss": 1.7154333114624023,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4918549658434053,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 3.8642941770372644e-10,
|
||
|
|
"loss": 1.7977441787719726,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.5002627430373097,
|
||
|
|
"step": 714,
|
||
|
|
"total_flos": 3.4104097625680896e+17,
|
||
|
|
"train_loss": 1.8137206637224896,
|
||
|
|
"train_runtime": 5627.9871,
|
||
|
|
"train_samples_per_second": 0.507,
|
||
|
|
"train_steps_per_second": 0.127
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 10,
|
||
|
|
"max_steps": 714,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 2,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": false,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 3.4104097625680896e+17,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|