Cosmos-Reason1-V6 / trainer_state.json
Mohammad Qazim Bhat
Initial model upload
7403ab4
Raw History Blame Contribute Delete
23.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9934640522875817,
"eval_steps": 500,
"global_step": 133,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007469654528478058,
"grad_norm": 83.66364350529639,
"learning_rate": 2.5e-06,
"loss": 0.3381,
"step": 1
},
{
"epoch": 0.014939309056956116,
"grad_norm": 81.53383839809602,
"learning_rate": 5e-06,
"loss": 0.3338,
"step": 2
},
{
"epoch": 0.022408963585434174,
"grad_norm": 29.93147736161266,
"learning_rate": 7.500000000000001e-06,
"loss": 0.1979,
"step": 3
},
{
"epoch": 0.029878618113912233,
"grad_norm": 14.501852071161805,
"learning_rate": 1e-05,
"loss": 0.1277,
"step": 4
},
{
"epoch": 0.03734827264239029,
"grad_norm": 19.31223622560412,
"learning_rate": 9.998517349225698e-06,
"loss": 0.1235,
"step": 5
},
{
"epoch": 0.04481792717086835,
"grad_norm": 12.533606746099842,
"learning_rate": 9.994070276204115e-06,
"loss": 0.1118,
"step": 6
},
{
"epoch": 0.05228758169934641,
"grad_norm": 3.4935259224198343,
"learning_rate": 9.986661418317759e-06,
"loss": 0.074,
"step": 7
},
{
"epoch": 0.059757236227824466,
"grad_norm": 3.1511487178404867,
"learning_rate": 9.97629516946618e-06,
"loss": 0.0731,
"step": 8
},
{
"epoch": 0.06722689075630252,
"grad_norm": 3.188494580729082,
"learning_rate": 9.962977677460132e-06,
"loss": 0.0742,
"step": 9
},
{
"epoch": 0.07469654528478058,
"grad_norm": 2.062432381693594,
"learning_rate": 9.946716840375552e-06,
"loss": 0.0647,
"step": 10
},
{
"epoch": 0.08216619981325864,
"grad_norm": 2.5750556720541655,
"learning_rate": 9.927522301869515e-06,
"loss": 0.0681,
"step": 11
},
{
"epoch": 0.0896358543417367,
"grad_norm": 2.4833345366140267,
"learning_rate": 9.905405445460972e-06,
"loss": 0.0678,
"step": 12
},
{
"epoch": 0.09710550887021475,
"grad_norm": 0.5466746949101294,
"learning_rate": 9.880379387779637e-06,
"loss": 0.0634,
"step": 13
},
{
"epoch": 0.10457516339869281,
"grad_norm": 1.299204160770093,
"learning_rate": 9.852458970787027e-06,
"loss": 0.0635,
"step": 14
},
{
"epoch": 0.11204481792717087,
"grad_norm": 1.0809447453974312,
"learning_rate": 9.821660752974294e-06,
"loss": 0.0626,
"step": 15
},
{
"epoch": 0.11951447245564893,
"grad_norm": 1.4638009957342324,
"learning_rate": 9.78800299954203e-06,
"loss": 0.061,
"step": 16
},
{
"epoch": 0.12698412698412698,
"grad_norm": 1.6270916493301357,
"learning_rate": 9.751505671567914e-06,
"loss": 0.0577,
"step": 17
},
{
"epoch": 0.13445378151260504,
"grad_norm": 1.4725560302600822,
"learning_rate": 9.712190414168573e-06,
"loss": 0.0543,
"step": 18
},
{
"epoch": 0.1419234360410831,
"grad_norm": 1.1616131047740985,
"learning_rate": 9.670080543662742e-06,
"loss": 0.0579,
"step": 19
},
{
"epoch": 0.14939309056956115,
"grad_norm": 1.4451104854633077,
"learning_rate": 9.625201033743262e-06,
"loss": 0.0542,
"step": 20
},
{
"epoch": 0.1568627450980392,
"grad_norm": 1.3046654857767965,
"learning_rate": 9.577578500666187e-06,
"loss": 0.0529,
"step": 21
},
{
"epoch": 0.16433239962651727,
"grad_norm": 0.712285492293752,
"learning_rate": 9.527241187465735e-06,
"loss": 0.0508,
"step": 22
},
{
"epoch": 0.17180205415499533,
"grad_norm": 1.0670415513276432,
"learning_rate": 9.47421894720446e-06,
"loss": 0.0511,
"step": 23
},
{
"epoch": 0.1792717086834734,
"grad_norm": 1.089726845526318,
"learning_rate": 9.418543225268598e-06,
"loss": 0.045,
"step": 24
},
{
"epoch": 0.18674136321195145,
"grad_norm": 1.16876959730566,
"learning_rate": 9.36024704071904e-06,
"loss": 0.0497,
"step": 25
},
{
"epoch": 0.1942110177404295,
"grad_norm": 1.9432593166266714,
"learning_rate": 9.299364966709051e-06,
"loss": 0.0443,
"step": 26
},
{
"epoch": 0.20168067226890757,
"grad_norm": 1.3632218213525653,
"learning_rate": 9.235933109980302e-06,
"loss": 0.0412,
"step": 27
},
{
"epoch": 0.20915032679738563,
"grad_norm": 1.2118359142406354,
"learning_rate": 9.16998908944939e-06,
"loss": 0.0426,
"step": 28
},
{
"epoch": 0.2166199813258637,
"grad_norm": 1.5652682280880648,
"learning_rate": 9.101572013897555e-06,
"loss": 0.0484,
"step": 29
},
{
"epoch": 0.22408963585434175,
"grad_norm": 1.8811976122640937,
"learning_rate": 9.030722458776815e-06,
"loss": 0.0436,
"step": 30
},
{
"epoch": 0.2315592903828198,
"grad_norm": 2.033623634142626,
"learning_rate": 8.957482442146271e-06,
"loss": 0.0421,
"step": 31
},
{
"epoch": 0.23902894491129786,
"grad_norm": 0.9399191094852689,
"learning_rate": 8.881895399752873e-06,
"loss": 0.0429,
"step": 32
},
{
"epoch": 0.24649859943977592,
"grad_norm": 0.9086490759349591,
"learning_rate": 8.80400615927139e-06,
"loss": 0.0441,
"step": 33
},
{
"epoch": 0.25396825396825395,
"grad_norm": 1.4791341723174831,
"learning_rate": 8.72386091371891e-06,
"loss": 0.0378,
"step": 34
},
{
"epoch": 0.26143790849673204,
"grad_norm": 1.3044232726918747,
"learning_rate": 8.64150719405958e-06,
"loss": 0.0402,
"step": 35
},
{
"epoch": 0.2689075630252101,
"grad_norm": 2.019167394874401,
"learning_rate": 8.55699384101589e-06,
"loss": 0.035,
"step": 36
},
{
"epoch": 0.27637721755368816,
"grad_norm": 1.4240431435238001,
"learning_rate": 8.470370976103171e-06,
"loss": 0.0362,
"step": 37
},
{
"epoch": 0.2838468720821662,
"grad_norm": 2.4325880935203625,
"learning_rate": 8.381689971904514e-06,
"loss": 0.0357,
"step": 38
},
{
"epoch": 0.2913165266106443,
"grad_norm": 1.0795303141420276,
"learning_rate": 8.29100342160374e-06,
"loss": 0.0388,
"step": 39
},
{
"epoch": 0.2987861811391223,
"grad_norm": 1.4480266764788354,
"learning_rate": 8.198365107794457e-06,
"loss": 0.0395,
"step": 40
},
{
"epoch": 0.3062558356676004,
"grad_norm": 1.3303446578158185,
"learning_rate": 8.103829970583742e-06,
"loss": 0.0355,
"step": 41
},
{
"epoch": 0.3137254901960784,
"grad_norm": 1.2396051756024806,
"learning_rate": 8.007454075009352e-06,
"loss": 0.0366,
"step": 42
},
{
"epoch": 0.3211951447245565,
"grad_norm": 1.2051563596320944,
"learning_rate": 7.909294577789765e-06,
"loss": 0.0384,
"step": 43
},
{
"epoch": 0.32866479925303455,
"grad_norm": 1.5126478389671163,
"learning_rate": 7.809409693426803e-06,
"loss": 0.0318,
"step": 44
},
{
"epoch": 0.33613445378151263,
"grad_norm": 1.0047763542900747,
"learning_rate": 7.707858659680924e-06,
"loss": 0.0326,
"step": 45
},
{
"epoch": 0.34360410830999066,
"grad_norm": 0.863075668882881,
"learning_rate": 7.604701702439652e-06,
"loss": 0.0282,
"step": 46
},
{
"epoch": 0.3510737628384687,
"grad_norm": 0.7839352461771767,
"learning_rate": 7.500000000000001e-06,
"loss": 0.0315,
"step": 47
},
{
"epoch": 0.3585434173669468,
"grad_norm": 1.003514704408453,
"learning_rate": 7.393815646786047e-06,
"loss": 0.0268,
"step": 48
},
{
"epoch": 0.3660130718954248,
"grad_norm": 1.1264348712361474,
"learning_rate": 7.286211616523193e-06,
"loss": 0.0323,
"step": 49
},
{
"epoch": 0.3734827264239029,
"grad_norm": 0.910626023288495,
"learning_rate": 7.177251724890957e-06,
"loss": 0.0288,
"step": 50
},
{
"epoch": 0.38095238095238093,
"grad_norm": 1.2886335086866114,
"learning_rate": 7.067000591676416e-06,
"loss": 0.0282,
"step": 51
},
{
"epoch": 0.388422035480859,
"grad_norm": 0.9199687228420548,
"learning_rate": 6.95552360245078e-06,
"loss": 0.0289,
"step": 52
},
{
"epoch": 0.39589169000933705,
"grad_norm": 1.3123227383367062,
"learning_rate": 6.84288686979181e-06,
"loss": 0.0276,
"step": 53
},
{
"epoch": 0.40336134453781514,
"grad_norm": 3.294786479667714,
"learning_rate": 6.7291571940750575e-06,
"loss": 0.028,
"step": 54
},
{
"epoch": 0.41083099906629317,
"grad_norm": 1.036928978221735,
"learning_rate": 6.614402023857231e-06,
"loss": 0.0273,
"step": 55
},
{
"epoch": 0.41830065359477125,
"grad_norm": 1.1622762269264137,
"learning_rate": 6.498689415875121e-06,
"loss": 0.0261,
"step": 56
},
{
"epoch": 0.4257703081232493,
"grad_norm": 1.842352523302583,
"learning_rate": 6.3820879946838585e-06,
"loss": 0.0297,
"step": 57
},
{
"epoch": 0.4332399626517274,
"grad_norm": 1.3482601388052298,
"learning_rate": 6.264666911958404e-06,
"loss": 0.0255,
"step": 58
},
{
"epoch": 0.4407096171802054,
"grad_norm": 31.306919174967806,
"learning_rate": 6.146495805482451e-06,
"loss": 0.0297,
"step": 59
},
{
"epoch": 0.4481792717086835,
"grad_norm": 1.6495689196896057,
"learning_rate": 6.027644757849004e-06,
"loss": 0.0285,
"step": 60
},
{
"epoch": 0.4556489262371615,
"grad_norm": 1.9893856478261371,
"learning_rate": 5.908184254897183e-06,
"loss": 0.0311,
"step": 61
},
{
"epoch": 0.4631185807656396,
"grad_norm": 1.1544533503901309,
"learning_rate": 5.788185143909868e-06,
"loss": 0.0257,
"step": 62
},
{
"epoch": 0.47058823529411764,
"grad_norm": 1.102067086004079,
"learning_rate": 5.66771859159699e-06,
"loss": 0.0251,
"step": 63
},
{
"epoch": 0.4780578898225957,
"grad_norm": 0.9301551060612953,
"learning_rate": 5.546856041889374e-06,
"loss": 0.0284,
"step": 64
},
{
"epoch": 0.48552754435107376,
"grad_norm": 1.1299881503286255,
"learning_rate": 5.425669173568179e-06,
"loss": 0.0277,
"step": 65
},
{
"epoch": 0.49299719887955185,
"grad_norm": 1.6424508302389984,
"learning_rate": 5.30422985775507e-06,
"loss": 0.0286,
"step": 66
},
{
"epoch": 0.5004668534080299,
"grad_norm": 1.0059864897522226,
"learning_rate": 5.182610115288296e-06,
"loss": 0.0252,
"step": 67
},
{
"epoch": 0.5079365079365079,
"grad_norm": 0.8027390248132119,
"learning_rate": 5.060882074009988e-06,
"loss": 0.0228,
"step": 68
},
{
"epoch": 0.5154061624649859,
"grad_norm": 4.470086793878035,
"learning_rate": 4.939117925990013e-06,
"loss": 0.0239,
"step": 69
},
{
"epoch": 0.5228758169934641,
"grad_norm": 1.2411271658452818,
"learning_rate": 4.817389884711706e-06,
"loss": 0.0272,
"step": 70
},
{
"epoch": 0.5303454715219421,
"grad_norm": 1.6277525081222284,
"learning_rate": 4.695770142244931e-06,
"loss": 0.0246,
"step": 71
},
{
"epoch": 0.5378151260504201,
"grad_norm": 1.0720372032984764,
"learning_rate": 4.574330826431822e-06,
"loss": 0.0245,
"step": 72
},
{
"epoch": 0.5452847805788982,
"grad_norm": 0.9746285789175358,
"learning_rate": 4.4531439581106295e-06,
"loss": 0.0234,
"step": 73
},
{
"epoch": 0.5527544351073763,
"grad_norm": 1.7044538601597283,
"learning_rate": 4.332281408403011e-06,
"loss": 0.0258,
"step": 74
},
{
"epoch": 0.5602240896358543,
"grad_norm": 1.332012702296044,
"learning_rate": 4.2118148560901325e-06,
"loss": 0.027,
"step": 75
},
{
"epoch": 0.5676937441643324,
"grad_norm": 0.961136449369872,
"learning_rate": 4.091815745102818e-06,
"loss": 0.0208,
"step": 76
},
{
"epoch": 0.5751633986928104,
"grad_norm": 1.4917157157155674,
"learning_rate": 3.9723552421509975e-06,
"loss": 0.0235,
"step": 77
},
{
"epoch": 0.5826330532212886,
"grad_norm": 1.7048789370960933,
"learning_rate": 3.853504194517551e-06,
"loss": 0.0255,
"step": 78
},
{
"epoch": 0.5901027077497666,
"grad_norm": 0.9806469294163478,
"learning_rate": 3.7353330880415963e-06,
"loss": 0.0214,
"step": 79
},
{
"epoch": 0.5975723622782446,
"grad_norm": 1.1532729397862154,
"learning_rate": 3.617912005316142e-06,
"loss": 0.0233,
"step": 80
},
{
"epoch": 0.6050420168067226,
"grad_norm": 1.7570384675271258,
"learning_rate": 3.5013105841248794e-06,
"loss": 0.0259,
"step": 81
},
{
"epoch": 0.6125116713352008,
"grad_norm": 1.235934728013138,
"learning_rate": 3.3855979761427705e-06,
"loss": 0.0239,
"step": 82
},
{
"epoch": 0.6199813258636788,
"grad_norm": 1.400889288226442,
"learning_rate": 3.2708428059249437e-06,
"loss": 0.0248,
"step": 83
},
{
"epoch": 0.6274509803921569,
"grad_norm": 1.0540335473032671,
"learning_rate": 3.1571131302081916e-06,
"loss": 0.0204,
"step": 84
},
{
"epoch": 0.6349206349206349,
"grad_norm": 1.8464055416919836,
"learning_rate": 3.044476397549221e-06,
"loss": 0.0233,
"step": 85
},
{
"epoch": 0.642390289449113,
"grad_norm": 1.1570125483834035,
"learning_rate": 2.9329994083235857e-06,
"loss": 0.0234,
"step": 86
},
{
"epoch": 0.6498599439775911,
"grad_norm": 1.7971253777302665,
"learning_rate": 2.8227482751090445e-06,
"loss": 0.0219,
"step": 87
},
{
"epoch": 0.6573295985060691,
"grad_norm": 1.294513314691015,
"learning_rate": 2.7137883834768076e-06,
"loss": 0.0211,
"step": 88
},
{
"epoch": 0.6647992530345471,
"grad_norm": 1.3986517611295475,
"learning_rate": 2.6061843532139563e-06,
"loss": 0.0173,
"step": 89
},
{
"epoch": 0.6722689075630253,
"grad_norm": 1.308783744565388,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.0178,
"step": 90
},
{
"epoch": 0.6797385620915033,
"grad_norm": 1.1789820085405884,
"learning_rate": 2.3952982975603494e-06,
"loss": 0.0183,
"step": 91
},
{
"epoch": 0.6872082166199813,
"grad_norm": 1.3016082086665108,
"learning_rate": 2.2921413403190774e-06,
"loss": 0.022,
"step": 92
},
{
"epoch": 0.6946778711484594,
"grad_norm": 4.836628417776147,
"learning_rate": 2.190590306573198e-06,
"loss": 0.0233,
"step": 93
},
{
"epoch": 0.7021475256769374,
"grad_norm": 0.9429249212665084,
"learning_rate": 2.0907054222102367e-06,
"loss": 0.0188,
"step": 94
},
{
"epoch": 0.7096171802054155,
"grad_norm": 1.0918824541501555,
"learning_rate": 1.9925459249906488e-06,
"loss": 0.0186,
"step": 95
},
{
"epoch": 0.7170868347338936,
"grad_norm": 2.2468799179940935,
"learning_rate": 1.8961700294162578e-06,
"loss": 0.0184,
"step": 96
},
{
"epoch": 0.7245564892623716,
"grad_norm": 1.3646178676895373,
"learning_rate": 1.8016348922055448e-06,
"loss": 0.0219,
"step": 97
},
{
"epoch": 0.7320261437908496,
"grad_norm": 1.6113014973058408,
"learning_rate": 1.7089965783962608e-06,
"loss": 0.0185,
"step": 98
},
{
"epoch": 0.7394957983193278,
"grad_norm": 1.8055646361706916,
"learning_rate": 1.618310028095486e-06,
"loss": 0.0157,
"step": 99
},
{
"epoch": 0.7469654528478058,
"grad_norm": 1.7472482403296163,
"learning_rate": 1.5296290238968303e-06,
"loss": 0.0196,
"step": 100
},
{
"epoch": 0.7544351073762838,
"grad_norm": 1.50105291832547,
"learning_rate": 1.4430061589841122e-06,
"loss": 0.019,
"step": 101
},
{
"epoch": 0.7619047619047619,
"grad_norm": 1.8362154151888805,
"learning_rate": 1.3584928059404207e-06,
"loss": 0.0168,
"step": 102
},
{
"epoch": 0.76937441643324,
"grad_norm": 1.6136498172938172,
"learning_rate": 1.2761390862810907e-06,
"loss": 0.0169,
"step": 103
},
{
"epoch": 0.776844070961718,
"grad_norm": 1.5108460799012118,
"learning_rate": 1.1959938407286099e-06,
"loss": 0.0203,
"step": 104
},
{
"epoch": 0.7843137254901961,
"grad_norm": 1.1711543599524703,
"learning_rate": 1.1181046002471292e-06,
"loss": 0.0154,
"step": 105
},
{
"epoch": 0.7917833800186741,
"grad_norm": 3.008390629797517,
"learning_rate": 1.04251755785373e-06,
"loss": 0.0171,
"step": 106
},
{
"epoch": 0.7992530345471522,
"grad_norm": 3.2566251478304413,
"learning_rate": 9.692775412231863e-07,
"loss": 0.0131,
"step": 107
},
{
"epoch": 0.8067226890756303,
"grad_norm": 1.8480618834189009,
"learning_rate": 8.984279861024453e-07,
"loss": 0.0176,
"step": 108
},
{
"epoch": 0.8141923436041083,
"grad_norm": 1.5116623212452605,
"learning_rate": 8.30010910550611e-07,
"loss": 0.0199,
"step": 109
},
{
"epoch": 0.8216619981325863,
"grad_norm": 2.8539278588385817,
"learning_rate": 7.640668900196985e-07,
"loss": 0.0152,
"step": 110
},
{
"epoch": 0.8291316526610645,
"grad_norm": 1.1867706491507146,
"learning_rate": 7.006350332909495e-07,
"loss": 0.015,
"step": 111
},
{
"epoch": 0.8366013071895425,
"grad_norm": 1.7648976918411488,
"learning_rate": 6.397529592809615e-07,
"loss": 0.0217,
"step": 112
},
{
"epoch": 0.8440709617180205,
"grad_norm": 1.3551850765545266,
"learning_rate": 5.814567747314049e-07,
"loss": 0.0137,
"step": 113
},
{
"epoch": 0.8515406162464986,
"grad_norm": 1.2689041285151215,
"learning_rate": 5.25781052795541e-07,
"loss": 0.0183,
"step": 114
},
{
"epoch": 0.8590102707749766,
"grad_norm": 2.4407151532105873,
"learning_rate": 4.727588125342669e-07,
"loss": 0.014,
"step": 115
},
{
"epoch": 0.8664799253034547,
"grad_norm": 1.87008755040254,
"learning_rate": 4.224214993338149e-07,
"loss": 0.012,
"step": 116
},
{
"epoch": 0.8739495798319328,
"grad_norm": 1.6933717617298023,
"learning_rate": 3.747989662567403e-07,
"loss": 0.0186,
"step": 117
},
{
"epoch": 0.8814192343604108,
"grad_norm": 2.279395535584551,
"learning_rate": 3.299194563372604e-07,
"loss": 0.0165,
"step": 118
},
{
"epoch": 0.8888888888888888,
"grad_norm": 1.330948242570783,
"learning_rate": 2.878095858314278e-07,
"loss": 0.0142,
"step": 119
},
{
"epoch": 0.896358543417367,
"grad_norm": 1.5953398025945043,
"learning_rate": 2.4849432843208786e-07,
"loss": 0.0203,
"step": 120
},
{
"epoch": 0.903828197945845,
"grad_norm": 1.504486435416967,
"learning_rate": 2.1199700045797077e-07,
"loss": 0.0187,
"step": 121
},
{
"epoch": 0.911297852474323,
"grad_norm": 1.414835808261487,
"learning_rate": 1.7833924702570725e-07,
"loss": 0.017,
"step": 122
},
{
"epoch": 0.9187675070028011,
"grad_norm": 1.4840532194331355,
"learning_rate": 1.4754102921297363e-07,
"loss": 0.0162,
"step": 123
},
{
"epoch": 0.9262371615312792,
"grad_norm": 1.8901504732653944,
"learning_rate": 1.196206122203647e-07,
"loss": 0.0184,
"step": 124
},
{
"epoch": 0.9337068160597572,
"grad_norm": 1.0017751998500017,
"learning_rate": 9.459455453902866e-08,
"loss": 0.0156,
"step": 125
},
{
"epoch": 0.9411764705882353,
"grad_norm": 1.5973769542464928,
"learning_rate": 7.247769813048644e-08,
"loss": 0.0219,
"step": 126
},
{
"epoch": 0.9486461251167133,
"grad_norm": 1.3512733799900647,
"learning_rate": 5.3283159624448745e-08,
"loss": 0.0157,
"step": 127
},
{
"epoch": 0.9561157796451915,
"grad_norm": 1.4833059272610134,
"learning_rate": 3.702232253986804e-08,
"loss": 0.0172,
"step": 128
},
{
"epoch": 0.9635854341736695,
"grad_norm": 1.4267506749896919,
"learning_rate": 2.370483053382111e-08,
"loss": 0.0238,
"step": 129
},
{
"epoch": 0.9710550887021475,
"grad_norm": 1.2145001010078258,
"learning_rate": 1.333858168224178e-08,
"loss": 0.0155,
"step": 130
},
{
"epoch": 0.9785247432306255,
"grad_norm": 1.747922912239647,
"learning_rate": 5.929723795884967e-09,
"loss": 0.0209,
"step": 131
},
{
"epoch": 0.9859943977591037,
"grad_norm": 1.625434620669095,
"learning_rate": 1.4826507743032071e-09,
"loss": 0.0189,
"step": 132
},
{
"epoch": 0.9934640522875817,
"grad_norm": 1.19653514330039,
"learning_rate": 0.0,
"loss": 0.013,
"step": 133
},
{
"epoch": 0.9934640522875817,
"step": 133,
"total_flos": 9978460449538048.0,
"train_loss": 0.0,
"train_runtime": 0.0048,
"train_samples_per_second": 14180249.327,
"train_steps_per_second": 27526.025
}
],
"logging_steps": 1.0,
"max_steps": 133,
"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": 9978460449538048.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}