gr1-groot-finetuned / trainer_state.json
YuhDuh's picture
Fine-tuned GR00T model for GR1 robot (checkpoint-1500)
aeedcff verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 11.194029850746269,
"eval_steps": 500,
"global_step": 1500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07462686567164178,
"grad_norm": 2.6359663009643555,
"learning_rate": 9e-07,
"loss": 0.2956,
"step": 10
},
{
"epoch": 0.14925373134328357,
"grad_norm": 4.154141426086426,
"learning_rate": 1.9e-06,
"loss": 0.3612,
"step": 20
},
{
"epoch": 0.22388059701492538,
"grad_norm": 2.7230818271636963,
"learning_rate": 2.9e-06,
"loss": 0.2889,
"step": 30
},
{
"epoch": 0.29850746268656714,
"grad_norm": 1.8438748121261597,
"learning_rate": 3.9e-06,
"loss": 0.2648,
"step": 40
},
{
"epoch": 0.373134328358209,
"grad_norm": 1.8854578733444214,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.2208,
"step": 50
},
{
"epoch": 0.44776119402985076,
"grad_norm": 1.1787480115890503,
"learning_rate": 5.9e-06,
"loss": 0.177,
"step": 60
},
{
"epoch": 0.5223880597014925,
"grad_norm": 0.8205132484436035,
"learning_rate": 6.900000000000001e-06,
"loss": 0.1031,
"step": 70
},
{
"epoch": 0.5970149253731343,
"grad_norm": 0.567926824092865,
"learning_rate": 7.9e-06,
"loss": 0.088,
"step": 80
},
{
"epoch": 0.6716417910447762,
"grad_norm": 0.570378839969635,
"learning_rate": 8.9e-06,
"loss": 0.0625,
"step": 90
},
{
"epoch": 0.746268656716418,
"grad_norm": 0.31382572650909424,
"learning_rate": 9.900000000000002e-06,
"loss": 0.0502,
"step": 100
},
{
"epoch": 0.8208955223880597,
"grad_norm": 0.4518411159515381,
"learning_rate": 1.09e-05,
"loss": 0.0448,
"step": 110
},
{
"epoch": 0.8955223880597015,
"grad_norm": 0.3404799997806549,
"learning_rate": 1.19e-05,
"loss": 0.0512,
"step": 120
},
{
"epoch": 0.9701492537313433,
"grad_norm": 0.195379838347435,
"learning_rate": 1.29e-05,
"loss": 0.0337,
"step": 130
},
{
"epoch": 1.044776119402985,
"grad_norm": 0.30482611060142517,
"learning_rate": 1.3900000000000002e-05,
"loss": 0.0367,
"step": 140
},
{
"epoch": 1.1194029850746268,
"grad_norm": 0.22756843268871307,
"learning_rate": 1.49e-05,
"loss": 0.0375,
"step": 150
},
{
"epoch": 1.1940298507462686,
"grad_norm": 0.33363619446754456,
"learning_rate": 1.59e-05,
"loss": 0.0374,
"step": 160
},
{
"epoch": 1.2686567164179103,
"grad_norm": 0.2732360064983368,
"learning_rate": 1.69e-05,
"loss": 0.0293,
"step": 170
},
{
"epoch": 1.3432835820895521,
"grad_norm": 0.16427411139011383,
"learning_rate": 1.79e-05,
"loss": 0.0294,
"step": 180
},
{
"epoch": 1.417910447761194,
"grad_norm": 0.21058405935764313,
"learning_rate": 1.8900000000000002e-05,
"loss": 0.0345,
"step": 190
},
{
"epoch": 1.4925373134328357,
"grad_norm": 0.27761879563331604,
"learning_rate": 1.9900000000000003e-05,
"loss": 0.0309,
"step": 200
},
{
"epoch": 1.5671641791044775,
"grad_norm": 0.16202031075954437,
"learning_rate": 2.09e-05,
"loss": 0.0306,
"step": 210
},
{
"epoch": 1.6417910447761193,
"grad_norm": 0.2178775519132614,
"learning_rate": 2.19e-05,
"loss": 0.0269,
"step": 220
},
{
"epoch": 1.716417910447761,
"grad_norm": 0.297981858253479,
"learning_rate": 2.29e-05,
"loss": 0.0277,
"step": 230
},
{
"epoch": 1.7910447761194028,
"grad_norm": 0.3659513592720032,
"learning_rate": 2.39e-05,
"loss": 0.027,
"step": 240
},
{
"epoch": 1.8656716417910446,
"grad_norm": 0.44367414712905884,
"learning_rate": 2.4900000000000002e-05,
"loss": 0.0277,
"step": 250
},
{
"epoch": 1.9402985074626866,
"grad_norm": 0.17233391106128693,
"learning_rate": 2.5900000000000003e-05,
"loss": 0.0261,
"step": 260
},
{
"epoch": 2.014925373134328,
"grad_norm": 0.6397565007209778,
"learning_rate": 2.6900000000000003e-05,
"loss": 0.027,
"step": 270
},
{
"epoch": 2.08955223880597,
"grad_norm": 0.24160514771938324,
"learning_rate": 2.7900000000000004e-05,
"loss": 0.0277,
"step": 280
},
{
"epoch": 2.1641791044776117,
"grad_norm": 0.20041881501674652,
"learning_rate": 2.8899999999999998e-05,
"loss": 0.0208,
"step": 290
},
{
"epoch": 2.2388059701492535,
"grad_norm": 0.2287420779466629,
"learning_rate": 2.9900000000000002e-05,
"loss": 0.0248,
"step": 300
},
{
"epoch": 2.3134328358208958,
"grad_norm": 0.2654382586479187,
"learning_rate": 3.09e-05,
"loss": 0.0235,
"step": 310
},
{
"epoch": 2.388059701492537,
"grad_norm": 0.2787795662879944,
"learning_rate": 3.19e-05,
"loss": 0.0222,
"step": 320
},
{
"epoch": 2.4626865671641793,
"grad_norm": 0.25142550468444824,
"learning_rate": 3.29e-05,
"loss": 0.0239,
"step": 330
},
{
"epoch": 2.5373134328358207,
"grad_norm": 0.37863755226135254,
"learning_rate": 3.3900000000000004e-05,
"loss": 0.0181,
"step": 340
},
{
"epoch": 2.611940298507463,
"grad_norm": 0.24035662412643433,
"learning_rate": 3.49e-05,
"loss": 0.0224,
"step": 350
},
{
"epoch": 2.6865671641791042,
"grad_norm": 0.2062656730413437,
"learning_rate": 3.59e-05,
"loss": 0.024,
"step": 360
},
{
"epoch": 2.7611940298507465,
"grad_norm": 0.2967865467071533,
"learning_rate": 3.69e-05,
"loss": 0.0159,
"step": 370
},
{
"epoch": 2.835820895522388,
"grad_norm": 0.19556978344917297,
"learning_rate": 3.79e-05,
"loss": 0.0172,
"step": 380
},
{
"epoch": 2.91044776119403,
"grad_norm": 0.20358707010746002,
"learning_rate": 3.8900000000000004e-05,
"loss": 0.0209,
"step": 390
},
{
"epoch": 2.9850746268656714,
"grad_norm": 0.2279907613992691,
"learning_rate": 3.99e-05,
"loss": 0.014,
"step": 400
},
{
"epoch": 3.0597014925373136,
"grad_norm": 0.23948746919631958,
"learning_rate": 4.09e-05,
"loss": 0.018,
"step": 410
},
{
"epoch": 3.1343283582089554,
"grad_norm": 0.10130123049020767,
"learning_rate": 4.19e-05,
"loss": 0.0209,
"step": 420
},
{
"epoch": 3.208955223880597,
"grad_norm": 0.21031032502651215,
"learning_rate": 4.29e-05,
"loss": 0.0195,
"step": 430
},
{
"epoch": 3.283582089552239,
"grad_norm": 0.18734681606292725,
"learning_rate": 4.39e-05,
"loss": 0.0179,
"step": 440
},
{
"epoch": 3.3582089552238807,
"grad_norm": 0.148833230137825,
"learning_rate": 4.49e-05,
"loss": 0.0172,
"step": 450
},
{
"epoch": 3.4328358208955225,
"grad_norm": 0.17836610972881317,
"learning_rate": 4.5900000000000004e-05,
"loss": 0.0149,
"step": 460
},
{
"epoch": 3.5074626865671643,
"grad_norm": 0.2201811820268631,
"learning_rate": 4.69e-05,
"loss": 0.0186,
"step": 470
},
{
"epoch": 3.582089552238806,
"grad_norm": 0.14344210922718048,
"learning_rate": 4.79e-05,
"loss": 0.0141,
"step": 480
},
{
"epoch": 3.656716417910448,
"grad_norm": 0.14173491299152374,
"learning_rate": 4.89e-05,
"loss": 0.0164,
"step": 490
},
{
"epoch": 3.7313432835820897,
"grad_norm": 0.10802058130502701,
"learning_rate": 4.99e-05,
"loss": 0.0116,
"step": 500
},
{
"epoch": 3.8059701492537314,
"grad_norm": 0.15126974880695343,
"learning_rate": 5.0900000000000004e-05,
"loss": 0.0141,
"step": 510
},
{
"epoch": 3.8805970149253732,
"grad_norm": 0.23868845403194427,
"learning_rate": 5.19e-05,
"loss": 0.014,
"step": 520
},
{
"epoch": 3.955223880597015,
"grad_norm": 0.3107485771179199,
"learning_rate": 5.2900000000000005e-05,
"loss": 0.0167,
"step": 530
},
{
"epoch": 4.029850746268656,
"grad_norm": 0.16036587953567505,
"learning_rate": 5.390000000000001e-05,
"loss": 0.0172,
"step": 540
},
{
"epoch": 4.104477611940299,
"grad_norm": 0.10766558349132538,
"learning_rate": 5.4900000000000006e-05,
"loss": 0.0123,
"step": 550
},
{
"epoch": 4.17910447761194,
"grad_norm": 0.15585613250732422,
"learning_rate": 5.590000000000001e-05,
"loss": 0.014,
"step": 560
},
{
"epoch": 4.253731343283582,
"grad_norm": 0.12563645839691162,
"learning_rate": 5.69e-05,
"loss": 0.0168,
"step": 570
},
{
"epoch": 4.3283582089552235,
"grad_norm": 0.2879914939403534,
"learning_rate": 5.79e-05,
"loss": 0.0172,
"step": 580
},
{
"epoch": 4.402985074626866,
"grad_norm": 0.3350052237510681,
"learning_rate": 5.89e-05,
"loss": 0.0133,
"step": 590
},
{
"epoch": 4.477611940298507,
"grad_norm": 0.20012852549552917,
"learning_rate": 5.99e-05,
"loss": 0.0132,
"step": 600
},
{
"epoch": 4.552238805970149,
"grad_norm": 0.18231847882270813,
"learning_rate": 6.09e-05,
"loss": 0.0183,
"step": 610
},
{
"epoch": 4.6268656716417915,
"grad_norm": 0.1492220014333725,
"learning_rate": 6.19e-05,
"loss": 0.0158,
"step": 620
},
{
"epoch": 4.701492537313433,
"grad_norm": 0.11610173434019089,
"learning_rate": 6.29e-05,
"loss": 0.0121,
"step": 630
},
{
"epoch": 4.776119402985074,
"grad_norm": 0.1784248948097229,
"learning_rate": 6.390000000000001e-05,
"loss": 0.0118,
"step": 640
},
{
"epoch": 4.850746268656716,
"grad_norm": 0.170172318816185,
"learning_rate": 6.49e-05,
"loss": 0.0122,
"step": 650
},
{
"epoch": 4.925373134328359,
"grad_norm": 0.16932718455791473,
"learning_rate": 6.59e-05,
"loss": 0.0122,
"step": 660
},
{
"epoch": 5.0,
"grad_norm": 0.2288501113653183,
"learning_rate": 6.690000000000001e-05,
"loss": 0.0103,
"step": 670
},
{
"epoch": 5.074626865671641,
"grad_norm": 0.14068059623241425,
"learning_rate": 6.790000000000001e-05,
"loss": 0.0147,
"step": 680
},
{
"epoch": 5.149253731343284,
"grad_norm": 0.11700227111577988,
"learning_rate": 6.89e-05,
"loss": 0.009,
"step": 690
},
{
"epoch": 5.223880597014926,
"grad_norm": 0.1194658875465393,
"learning_rate": 6.99e-05,
"loss": 0.0094,
"step": 700
},
{
"epoch": 5.298507462686567,
"grad_norm": 0.13679799437522888,
"learning_rate": 7.09e-05,
"loss": 0.0148,
"step": 710
},
{
"epoch": 5.373134328358209,
"grad_norm": 0.13276909291744232,
"learning_rate": 7.19e-05,
"loss": 0.0118,
"step": 720
},
{
"epoch": 5.447761194029851,
"grad_norm": 0.094159796833992,
"learning_rate": 7.29e-05,
"loss": 0.0124,
"step": 730
},
{
"epoch": 5.522388059701493,
"grad_norm": 0.16352857649326324,
"learning_rate": 7.390000000000001e-05,
"loss": 0.0111,
"step": 740
},
{
"epoch": 5.597014925373134,
"grad_norm": 0.14447464048862457,
"learning_rate": 7.49e-05,
"loss": 0.0124,
"step": 750
},
{
"epoch": 5.6716417910447765,
"grad_norm": 0.16974638402462006,
"learning_rate": 7.59e-05,
"loss": 0.0099,
"step": 760
},
{
"epoch": 5.746268656716418,
"grad_norm": 0.1150907427072525,
"learning_rate": 7.69e-05,
"loss": 0.0104,
"step": 770
},
{
"epoch": 5.82089552238806,
"grad_norm": 0.17046909034252167,
"learning_rate": 7.790000000000001e-05,
"loss": 0.0126,
"step": 780
},
{
"epoch": 5.895522388059701,
"grad_norm": 0.10910604149103165,
"learning_rate": 7.890000000000001e-05,
"loss": 0.0074,
"step": 790
},
{
"epoch": 5.970149253731344,
"grad_norm": 0.11517564207315445,
"learning_rate": 7.99e-05,
"loss": 0.0116,
"step": 800
},
{
"epoch": 6.044776119402985,
"grad_norm": 0.18701259791851044,
"learning_rate": 8.090000000000001e-05,
"loss": 0.0072,
"step": 810
},
{
"epoch": 6.119402985074627,
"grad_norm": 0.18763042986392975,
"learning_rate": 8.19e-05,
"loss": 0.0143,
"step": 820
},
{
"epoch": 6.1940298507462686,
"grad_norm": 0.16200491786003113,
"learning_rate": 8.29e-05,
"loss": 0.0116,
"step": 830
},
{
"epoch": 6.268656716417911,
"grad_norm": 0.10211509466171265,
"learning_rate": 8.39e-05,
"loss": 0.0094,
"step": 840
},
{
"epoch": 6.343283582089552,
"grad_norm": 0.11517218500375748,
"learning_rate": 8.49e-05,
"loss": 0.01,
"step": 850
},
{
"epoch": 6.417910447761194,
"grad_norm": 0.11806347966194153,
"learning_rate": 8.59e-05,
"loss": 0.0128,
"step": 860
},
{
"epoch": 6.492537313432836,
"grad_norm": 0.1730322539806366,
"learning_rate": 8.69e-05,
"loss": 0.009,
"step": 870
},
{
"epoch": 6.567164179104478,
"grad_norm": 0.20324429869651794,
"learning_rate": 8.790000000000001e-05,
"loss": 0.0096,
"step": 880
},
{
"epoch": 6.641791044776119,
"grad_norm": 0.22341865301132202,
"learning_rate": 8.89e-05,
"loss": 0.0108,
"step": 890
},
{
"epoch": 6.7164179104477615,
"grad_norm": 0.14523452520370483,
"learning_rate": 8.99e-05,
"loss": 0.0093,
"step": 900
},
{
"epoch": 6.791044776119403,
"grad_norm": 0.2617056369781494,
"learning_rate": 9.090000000000001e-05,
"loss": 0.0091,
"step": 910
},
{
"epoch": 6.865671641791045,
"grad_norm": 0.13474082946777344,
"learning_rate": 9.190000000000001e-05,
"loss": 0.0164,
"step": 920
},
{
"epoch": 6.940298507462686,
"grad_norm": 0.1422346830368042,
"learning_rate": 9.290000000000001e-05,
"loss": 0.0144,
"step": 930
},
{
"epoch": 7.014925373134329,
"grad_norm": 0.11779774725437164,
"learning_rate": 9.39e-05,
"loss": 0.0095,
"step": 940
},
{
"epoch": 7.08955223880597,
"grad_norm": 0.07547947764396667,
"learning_rate": 9.49e-05,
"loss": 0.0077,
"step": 950
},
{
"epoch": 7.164179104477612,
"grad_norm": 0.13442008197307587,
"learning_rate": 9.59e-05,
"loss": 0.0125,
"step": 960
},
{
"epoch": 7.2388059701492535,
"grad_norm": 0.1359054297208786,
"learning_rate": 9.69e-05,
"loss": 0.0069,
"step": 970
},
{
"epoch": 7.313432835820896,
"grad_norm": 0.15389667451381683,
"learning_rate": 9.790000000000001e-05,
"loss": 0.0091,
"step": 980
},
{
"epoch": 7.388059701492537,
"grad_norm": 0.15574434399604797,
"learning_rate": 9.89e-05,
"loss": 0.0079,
"step": 990
},
{
"epoch": 7.462686567164179,
"grad_norm": 0.15894819796085358,
"learning_rate": 9.99e-05,
"loss": 0.0108,
"step": 1000
},
{
"epoch": 7.537313432835821,
"grad_norm": 0.10361112654209137,
"learning_rate": 9.999994463727085e-05,
"loss": 0.0095,
"step": 1010
},
{
"epoch": 7.611940298507463,
"grad_norm": 0.11922885477542877,
"learning_rate": 9.999975326009292e-05,
"loss": 0.0068,
"step": 1020
},
{
"epoch": 7.686567164179104,
"grad_norm": 0.10447347909212112,
"learning_rate": 9.999942518549879e-05,
"loss": 0.0104,
"step": 1030
},
{
"epoch": 7.7611940298507465,
"grad_norm": 0.10702274739742279,
"learning_rate": 9.999896041438544e-05,
"loss": 0.0074,
"step": 1040
},
{
"epoch": 7.835820895522388,
"grad_norm": 0.0975528284907341,
"learning_rate": 9.999835894802353e-05,
"loss": 0.0077,
"step": 1050
},
{
"epoch": 7.91044776119403,
"grad_norm": 0.16120749711990356,
"learning_rate": 9.999762078805743e-05,
"loss": 0.0115,
"step": 1060
},
{
"epoch": 7.985074626865671,
"grad_norm": 0.12331589311361313,
"learning_rate": 9.999674593650526e-05,
"loss": 0.0078,
"step": 1070
},
{
"epoch": 8.059701492537313,
"grad_norm": 0.1256706714630127,
"learning_rate": 9.99957343957588e-05,
"loss": 0.008,
"step": 1080
},
{
"epoch": 8.134328358208956,
"grad_norm": 0.12802068889141083,
"learning_rate": 9.99945861685836e-05,
"loss": 0.0068,
"step": 1090
},
{
"epoch": 8.208955223880597,
"grad_norm": 0.1550874561071396,
"learning_rate": 9.999330125811884e-05,
"loss": 0.0104,
"step": 1100
},
{
"epoch": 8.283582089552239,
"grad_norm": 0.10126641392707825,
"learning_rate": 9.999187966787744e-05,
"loss": 0.0064,
"step": 1110
},
{
"epoch": 8.35820895522388,
"grad_norm": 0.12046301364898682,
"learning_rate": 9.999032140174595e-05,
"loss": 0.0072,
"step": 1120
},
{
"epoch": 8.432835820895523,
"grad_norm": 0.21631024777889252,
"learning_rate": 9.998862646398464e-05,
"loss": 0.0091,
"step": 1130
},
{
"epoch": 8.507462686567164,
"grad_norm": 0.16928455233573914,
"learning_rate": 9.998679485922739e-05,
"loss": 0.006,
"step": 1140
},
{
"epoch": 8.582089552238806,
"grad_norm": 0.1493779420852661,
"learning_rate": 9.998482659248174e-05,
"loss": 0.009,
"step": 1150
},
{
"epoch": 8.656716417910447,
"grad_norm": 0.15652231872081757,
"learning_rate": 9.998272166912883e-05,
"loss": 0.0066,
"step": 1160
},
{
"epoch": 8.73134328358209,
"grad_norm": 0.1458636224269867,
"learning_rate": 9.998048009492347e-05,
"loss": 0.0079,
"step": 1170
},
{
"epoch": 8.805970149253731,
"grad_norm": 0.11824473738670349,
"learning_rate": 9.997810187599403e-05,
"loss": 0.0068,
"step": 1180
},
{
"epoch": 8.880597014925373,
"grad_norm": 0.09037546068429947,
"learning_rate": 9.997558701884249e-05,
"loss": 0.0089,
"step": 1190
},
{
"epoch": 8.955223880597014,
"grad_norm": 0.1596665233373642,
"learning_rate": 9.997293553034433e-05,
"loss": 0.0103,
"step": 1200
},
{
"epoch": 9.029850746268657,
"grad_norm": 0.1774168163537979,
"learning_rate": 9.997014741774866e-05,
"loss": 0.0098,
"step": 1210
},
{
"epoch": 9.104477611940299,
"grad_norm": 0.17946547269821167,
"learning_rate": 9.996722268867803e-05,
"loss": 0.0086,
"step": 1220
},
{
"epoch": 9.17910447761194,
"grad_norm": 0.1658417135477066,
"learning_rate": 9.996416135112858e-05,
"loss": 0.0073,
"step": 1230
},
{
"epoch": 9.253731343283581,
"grad_norm": 0.09881595522165298,
"learning_rate": 9.996096341346988e-05,
"loss": 0.007,
"step": 1240
},
{
"epoch": 9.328358208955224,
"grad_norm": 0.16437676548957825,
"learning_rate": 9.995762888444495e-05,
"loss": 0.0071,
"step": 1250
},
{
"epoch": 9.402985074626866,
"grad_norm": 0.13102124631404877,
"learning_rate": 9.995415777317027e-05,
"loss": 0.0054,
"step": 1260
},
{
"epoch": 9.477611940298507,
"grad_norm": 0.12780794501304626,
"learning_rate": 9.995055008913574e-05,
"loss": 0.0042,
"step": 1270
},
{
"epoch": 9.552238805970148,
"grad_norm": 0.13209404051303864,
"learning_rate": 9.994680584220463e-05,
"loss": 0.0082,
"step": 1280
},
{
"epoch": 9.626865671641792,
"grad_norm": 0.1280508041381836,
"learning_rate": 9.994292504261355e-05,
"loss": 0.0064,
"step": 1290
},
{
"epoch": 9.701492537313433,
"grad_norm": 0.1415010243654251,
"learning_rate": 9.993890770097247e-05,
"loss": 0.0077,
"step": 1300
},
{
"epoch": 9.776119402985074,
"grad_norm": 0.0671149417757988,
"learning_rate": 9.993475382826467e-05,
"loss": 0.0064,
"step": 1310
},
{
"epoch": 9.850746268656717,
"grad_norm": 0.08181161433458328,
"learning_rate": 9.993046343584664e-05,
"loss": 0.0057,
"step": 1320
},
{
"epoch": 9.925373134328359,
"grad_norm": 0.0873553529381752,
"learning_rate": 9.992603653544816e-05,
"loss": 0.0111,
"step": 1330
},
{
"epoch": 10.0,
"grad_norm": 0.1723933219909668,
"learning_rate": 9.992147313917222e-05,
"loss": 0.0099,
"step": 1340
},
{
"epoch": 10.074626865671641,
"grad_norm": 0.1347159594297409,
"learning_rate": 9.991677325949497e-05,
"loss": 0.0092,
"step": 1350
},
{
"epoch": 10.149253731343283,
"grad_norm": 0.12214215844869614,
"learning_rate": 9.991193690926568e-05,
"loss": 0.0064,
"step": 1360
},
{
"epoch": 10.223880597014926,
"grad_norm": 0.0954289585351944,
"learning_rate": 9.990696410170678e-05,
"loss": 0.0115,
"step": 1370
},
{
"epoch": 10.298507462686567,
"grad_norm": 0.12168958783149719,
"learning_rate": 9.990185485041371e-05,
"loss": 0.0068,
"step": 1380
},
{
"epoch": 10.373134328358208,
"grad_norm": 0.11939054727554321,
"learning_rate": 9.989660916935498e-05,
"loss": 0.0062,
"step": 1390
},
{
"epoch": 10.447761194029852,
"grad_norm": 0.09408388286828995,
"learning_rate": 9.989122707287208e-05,
"loss": 0.0089,
"step": 1400
},
{
"epoch": 10.522388059701493,
"grad_norm": 0.10327029973268509,
"learning_rate": 9.988570857567945e-05,
"loss": 0.0129,
"step": 1410
},
{
"epoch": 10.597014925373134,
"grad_norm": 0.17698495090007782,
"learning_rate": 9.988005369286446e-05,
"loss": 0.0082,
"step": 1420
},
{
"epoch": 10.671641791044776,
"grad_norm": 0.13924898207187653,
"learning_rate": 9.987426243988734e-05,
"loss": 0.0092,
"step": 1430
},
{
"epoch": 10.746268656716419,
"grad_norm": 0.12503832578659058,
"learning_rate": 9.986833483258114e-05,
"loss": 0.0065,
"step": 1440
},
{
"epoch": 10.82089552238806,
"grad_norm": 0.10239670425653458,
"learning_rate": 9.986227088715173e-05,
"loss": 0.0067,
"step": 1450
},
{
"epoch": 10.895522388059701,
"grad_norm": 0.09500975906848907,
"learning_rate": 9.98560706201777e-05,
"loss": 0.0112,
"step": 1460
},
{
"epoch": 10.970149253731343,
"grad_norm": 0.1916763335466385,
"learning_rate": 9.984973404861036e-05,
"loss": 0.0051,
"step": 1470
},
{
"epoch": 11.044776119402986,
"grad_norm": 0.15825192630290985,
"learning_rate": 9.984326118977361e-05,
"loss": 0.0079,
"step": 1480
},
{
"epoch": 11.119402985074627,
"grad_norm": 0.19664017856121063,
"learning_rate": 9.983665206136406e-05,
"loss": 0.0052,
"step": 1490
},
{
"epoch": 11.194029850746269,
"grad_norm": 0.12272711098194122,
"learning_rate": 9.982990668145075e-05,
"loss": 0.0086,
"step": 1500
}
],
"logging_steps": 10,
"max_steps": 20000,
"num_input_tokens_seen": 0,
"num_train_epochs": 150,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.3585337048988736e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}