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": 9.625,
|
||
|
|
"learning_rate": 1.0227272727272728e-07,
|
||
|
|
"loss": 1.8086944580078126,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.04203888596952181,
|
||
|
|
"grad_norm": 10.5625,
|
||
|
|
"learning_rate": 2.159090909090909e-07,
|
||
|
|
"loss": 1.9563072204589844,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.0630583289542827,
|
||
|
|
"grad_norm": 8.375,
|
||
|
|
"learning_rate": 2.4993688579681983e-07,
|
||
|
|
"loss": 1.9191463470458985,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.08407777193904362,
|
||
|
|
"grad_norm": 5.21875,
|
||
|
|
"learning_rate": 2.496279084257832e-07,
|
||
|
|
"loss": 1.8105619430541993,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.10509721492380451,
|
||
|
|
"grad_norm": 7.15625,
|
||
|
|
"learning_rate": 2.490621113927919e-07,
|
||
|
|
"loss": 1.9305204391479491,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.1261166579085654,
|
||
|
|
"grad_norm": 5.21875,
|
||
|
|
"learning_rate": 2.4824066063093887e-07,
|
||
|
|
"loss": 1.9595895767211915,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.14713610089332632,
|
||
|
|
"grad_norm": 15.875,
|
||
|
|
"learning_rate": 2.4716524889676334e-07,
|
||
|
|
"loss": 1.9885068893432618,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.16815554387808723,
|
||
|
|
"grad_norm": 11.6875,
|
||
|
|
"learning_rate": 2.458380922820022e-07,
|
||
|
|
"loss": 1.9129520416259767,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.18917498686284814,
|
||
|
|
"grad_norm": 7.375,
|
||
|
|
"learning_rate": 2.442619256469084e-07,
|
||
|
|
"loss": 1.9894475936889648,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.21019442984760903,
|
||
|
|
"grad_norm": 9.25,
|
||
|
|
"learning_rate": 2.42439996984548e-07,
|
||
|
|
"loss": 1.8159450531005858,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.23121387283236994,
|
||
|
|
"grad_norm": 5.4375,
|
||
|
|
"learning_rate": 2.403760607276888e-07,
|
||
|
|
"loss": 1.9744218826293944,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.2522333158171308,
|
||
|
|
"grad_norm": 8.375,
|
||
|
|
"learning_rate": 2.3807437001207282e-07,
|
||
|
|
"loss": 1.8607925415039062,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.27325275880189176,
|
||
|
|
"grad_norm": 6.40625,
|
||
|
|
"learning_rate": 2.3553966791201608e-07,
|
||
|
|
"loss": 1.9678337097167968,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.29427220178665264,
|
||
|
|
"grad_norm": 7.84375,
|
||
|
|
"learning_rate": 2.3277717766639592e-07,
|
||
|
|
"loss": 1.905088233947754,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3152916447714136,
|
||
|
|
"grad_norm": 8.1875,
|
||
|
|
"learning_rate": 2.297925919151675e-07,
|
||
|
|
"loss": 1.8011585235595704,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.33631108775617446,
|
||
|
|
"grad_norm": 5.6875,
|
||
|
|
"learning_rate": 2.265920609685895e-07,
|
||
|
|
"loss": 1.847894287109375,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.35733053074093535,
|
||
|
|
"grad_norm": 4.625,
|
||
|
|
"learning_rate": 2.2318218013333245e-07,
|
||
|
|
"loss": 1.8336673736572267,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.3783499737256963,
|
||
|
|
"grad_norm": 15.375,
|
||
|
|
"learning_rate": 2.1956997612158683e-07,
|
||
|
|
"loss": 1.9188970565795898,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.39936941671045717,
|
||
|
|
"grad_norm": 5.1875,
|
||
|
|
"learning_rate": 2.157628925711777e-07,
|
||
|
|
"loss": 1.9967548370361328,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.42038885969521805,
|
||
|
|
"grad_norm": 6.84375,
|
||
|
|
"learning_rate": 2.117687747065239e-07,
|
||
|
|
"loss": 1.9001514434814453,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.441408302679979,
|
||
|
|
"grad_norm": 5.84375,
|
||
|
|
"learning_rate": 2.0759585317205137e-07,
|
||
|
|
"loss": 1.939328956604004,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4624277456647399,
|
||
|
|
"grad_norm": 12.3125,
|
||
|
|
"learning_rate": 2.0325272707137493e-07,
|
||
|
|
"loss": 1.9735946655273438,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4834471886495008,
|
||
|
|
"grad_norm": 5.34375,
|
||
|
|
"learning_rate": 1.9874834624719906e-07,
|
||
|
|
"loss": 1.8626848220825196,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5044666316342616,
|
||
|
|
"grad_norm": 6.4375,
|
||
|
|
"learning_rate": 1.9409199283845392e-07,
|
||
|
|
"loss": 1.746560287475586,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5254860746190226,
|
||
|
|
"grad_norm": 6.4375,
|
||
|
|
"learning_rate": 1.892932621526712e-07,
|
||
|
|
"loss": 1.920944595336914,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5465055176037835,
|
||
|
|
"grad_norm": 8.125,
|
||
|
|
"learning_rate": 1.8436204289301616e-07,
|
||
|
|
"loss": 1.9723596572875977,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5675249605885444,
|
||
|
|
"grad_norm": 5.8125,
|
||
|
|
"learning_rate": 1.79308496780722e-07,
|
||
|
|
"loss": 1.8008295059204102,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.5885444035733053,
|
||
|
|
"grad_norm": 6.5,
|
||
|
|
"learning_rate": 1.7414303761491778e-07,
|
||
|
|
"loss": 1.8942089080810547,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6095638465580662,
|
||
|
|
"grad_norm": 7.25,
|
||
|
|
"learning_rate": 1.6887630981300217e-07,
|
||
|
|
"loss": 1.9562250137329102,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6305832895428272,
|
||
|
|
"grad_norm": 4.5,
|
||
|
|
"learning_rate": 1.6351916647578366e-07,
|
||
|
|
"loss": 1.8874702453613281,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.651602732527588,
|
||
|
|
"grad_norm": 20.5,
|
||
|
|
"learning_rate": 1.5808264702258885e-07,
|
||
|
|
"loss": 1.82128849029541,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6726221755123489,
|
||
|
|
"grad_norm": 4.59375,
|
||
|
|
"learning_rate": 1.5257795444242566e-07,
|
||
|
|
"loss": 1.9460525512695312,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.6936416184971098,
|
||
|
|
"grad_norm": 12.875,
|
||
|
|
"learning_rate": 1.4701643220808016e-07,
|
||
|
|
"loss": 1.9333660125732421,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7146610614818707,
|
||
|
|
"grad_norm": 9.625,
|
||
|
|
"learning_rate": 1.414095409007192e-07,
|
||
|
|
"loss": 1.8776426315307617,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7356805044666316,
|
||
|
|
"grad_norm": 9.875,
|
||
|
|
"learning_rate": 1.3576883459316937e-07,
|
||
|
|
"loss": 1.8990169525146485,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7566999474513926,
|
||
|
|
"grad_norm": 6.15625,
|
||
|
|
"learning_rate": 1.3010593704053815e-07,
|
||
|
|
"loss": 1.9327930450439452,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7777193904361535,
|
||
|
|
"grad_norm": 5.65625,
|
||
|
|
"learning_rate": 1.2443251772724124e-07,
|
||
|
|
"loss": 1.9645748138427734,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.7987388334209143,
|
||
|
|
"grad_norm": 15.25,
|
||
|
|
"learning_rate": 1.1876026781979653e-07,
|
||
|
|
"loss": 1.9750782012939454,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8197582764056752,
|
||
|
|
"grad_norm": 9.3125,
|
||
|
|
"learning_rate": 1.1310087607493711e-07,
|
||
|
|
"loss": 1.9279960632324218,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8407777193904361,
|
||
|
|
"grad_norm": 9.1875,
|
||
|
|
"learning_rate": 1.0746600475269085e-07,
|
||
|
|
"loss": 1.9484302520751953,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8617971623751971,
|
||
|
|
"grad_norm": 4.53125,
|
||
|
|
"learning_rate": 1.0186726558406097e-07,
|
||
|
|
"loss": 1.9229631423950195,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.882816605359958,
|
||
|
|
"grad_norm": 7.96875,
|
||
|
|
"learning_rate": 9.631619584283176e-08,
|
||
|
|
"loss": 1.9820945739746094,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9038360483447189,
|
||
|
|
"grad_norm": 6.1875,
|
||
|
|
"learning_rate": 9.08242345708071e-08,
|
||
|
|
"loss": 2.0028038024902344,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9248554913294798,
|
||
|
|
"grad_norm": 6.28125,
|
||
|
|
"learning_rate": 8.540269900547556e-08,
|
||
|
|
"loss": 1.9427295684814454,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9458749343142406,
|
||
|
|
"grad_norm": 5.03125,
|
||
|
|
"learning_rate": 8.00627612586759e-08,
|
||
|
|
"loss": 1.8801141738891602,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9668943772990016,
|
||
|
|
"grad_norm": 12.5,
|
||
|
|
"learning_rate": 7.48154252943221e-08,
|
||
|
|
"loss": 1.7729660034179688,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.9879138202837625,
|
||
|
|
"grad_norm": 6.3125,
|
||
|
|
"learning_rate": 6.967150425262934e-08,
|
||
|
|
"loss": 2.0267822265625,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0084077771939044,
|
||
|
|
"grad_norm": 7.25,
|
||
|
|
"learning_rate": 6.464159816756865e-08,
|
||
|
|
"loss": 1.847897720336914,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0294272201786652,
|
||
|
|
"grad_norm": 6.46875,
|
||
|
|
"learning_rate": 5.973607212346771e-08,
|
||
|
|
"loss": 1.7879396438598634,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0504466631634262,
|
||
|
|
"grad_norm": 10.0625,
|
||
|
|
"learning_rate": 5.496503489577081e-08,
|
||
|
|
"loss": 2.006256675720215,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0714661061481872,
|
||
|
|
"grad_norm": 19.125,
|
||
|
|
"learning_rate": 5.033831811997166e-08,
|
||
|
|
"loss": 1.9164451599121093,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.092485549132948,
|
||
|
|
"grad_norm": 5.34375,
|
||
|
|
"learning_rate": 4.5865456031646654e-08,
|
||
|
|
"loss": 1.7832933425903321,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.113504992117709,
|
||
|
|
"grad_norm": 5.75,
|
||
|
|
"learning_rate": 4.1555665819337293e-08,
|
||
|
|
"loss": 1.8139366149902343,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1345244351024697,
|
||
|
|
"grad_norm": 5.84375,
|
||
|
|
"learning_rate": 3.7417828630768835e-08,
|
||
|
|
"loss": 1.869268798828125,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1555438780872307,
|
||
|
|
"grad_norm": 6.46875,
|
||
|
|
"learning_rate": 3.346047127154539e-08,
|
||
|
|
"loss": 1.878763771057129,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1765633210719917,
|
||
|
|
"grad_norm": 10.0625,
|
||
|
|
"learning_rate": 2.9691748634034702e-08,
|
||
|
|
"loss": 1.8553329467773438,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.1975827640567525,
|
||
|
|
"grad_norm": 13.3125,
|
||
|
|
"learning_rate": 2.6119426892651426e-08,
|
||
|
|
"loss": 1.8416221618652344,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2186022070415135,
|
||
|
|
"grad_norm": 7.03125,
|
||
|
|
"learning_rate": 2.275086750016812e-08,
|
||
|
|
"loss": 1.9319948196411132,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2396216500262742,
|
||
|
|
"grad_norm": 5.53125,
|
||
|
|
"learning_rate": 1.959301201803254e-08,
|
||
|
|
"loss": 1.7423213958740233,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2606410930110352,
|
||
|
|
"grad_norm": 6.28125,
|
||
|
|
"learning_rate": 1.6652367811951715e-08,
|
||
|
|
"loss": 1.9869190216064454,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2816605359957962,
|
||
|
|
"grad_norm": 14.75,
|
||
|
|
"learning_rate": 1.3934994642219104e-08,
|
||
|
|
"loss": 1.8976511001586913,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.302679978980557,
|
||
|
|
"grad_norm": 9.375,
|
||
|
|
"learning_rate": 1.1446492176418563e-08,
|
||
|
|
"loss": 1.9856376647949219,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.323699421965318,
|
||
|
|
"grad_norm": 5.125,
|
||
|
|
"learning_rate": 9.191988450237387e-09,
|
||
|
|
"loss": 2.0055776596069337,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3447188649500788,
|
||
|
|
"grad_norm": 9.25,
|
||
|
|
"learning_rate": 7.1761293001671855e-09,
|
||
|
|
"loss": 1.9813310623168945,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3657383079348397,
|
||
|
|
"grad_norm": 7.1875,
|
||
|
|
"learning_rate": 5.403068789868334e-09,
|
||
|
|
"loss": 1.9645788192749023,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3867577509196005,
|
||
|
|
"grad_norm": 4.21875,
|
||
|
|
"learning_rate": 3.8764606499268606e-09,
|
||
|
|
"loss": 1.9697418212890625,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4077771939043615,
|
||
|
|
"grad_norm": 5.15625,
|
||
|
|
"learning_rate": 2.599450748642956e-09,
|
||
|
|
"loss": 1.8822681427001953,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4287966368891225,
|
||
|
|
"grad_norm": 6.9375,
|
||
|
|
"learning_rate": 1.5746706093672235e-09,
|
||
|
|
"loss": 1.9432037353515625,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4498160798738833,
|
||
|
|
"grad_norm": 7.09375,
|
||
|
|
"learning_rate": 8.042319877430981e-10,
|
||
|
|
"loss": 1.8227525711059571,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4708355228586443,
|
||
|
|
"grad_norm": 6.875,
|
||
|
|
"learning_rate": 2.897225200300807e-10,
|
||
|
|
"loss": 1.9617921829223632,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.4918549658434053,
|
||
|
|
"grad_norm": 11.1875,
|
||
|
|
"learning_rate": 3.220245147531053e-11,
|
||
|
|
"loss": 1.9124065399169923,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.5002627430373097,
|
||
|
|
"step": 714,
|
||
|
|
"total_flos": 3.414600284463329e+17,
|
||
|
|
"train_loss": 1.907181319736299,
|
||
|
|
"train_runtime": 5553.447,
|
||
|
|
"train_samples_per_second": 0.514,
|
||
|
|
"train_steps_per_second": 0.129
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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": 3.414600284463329e+17,
|
||
|
|
"train_batch_size": 1,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|