prxy5605's picture
Training in progress, step 200, checkpoint
67a3287 verified
{
"best_metric": 0.8946874737739563,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.6756756756756757,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0033783783783783786,
"grad_norm": 3.826683282852173,
"learning_rate": 5e-06,
"loss": 1.4948,
"step": 1
},
{
"epoch": 0.0033783783783783786,
"eval_loss": 2.366645336151123,
"eval_runtime": 45.2663,
"eval_samples_per_second": 11.024,
"eval_steps_per_second": 5.523,
"step": 1
},
{
"epoch": 0.006756756756756757,
"grad_norm": 4.3141398429870605,
"learning_rate": 1e-05,
"loss": 1.6839,
"step": 2
},
{
"epoch": 0.010135135135135136,
"grad_norm": 4.097876071929932,
"learning_rate": 1.5e-05,
"loss": 1.5752,
"step": 3
},
{
"epoch": 0.013513513513513514,
"grad_norm": 4.010673522949219,
"learning_rate": 2e-05,
"loss": 1.5405,
"step": 4
},
{
"epoch": 0.016891891891891893,
"grad_norm": 3.4538493156433105,
"learning_rate": 2.5e-05,
"loss": 1.5342,
"step": 5
},
{
"epoch": 0.02027027027027027,
"grad_norm": 2.8183417320251465,
"learning_rate": 3e-05,
"loss": 1.3748,
"step": 6
},
{
"epoch": 0.02364864864864865,
"grad_norm": 2.11971378326416,
"learning_rate": 3.5e-05,
"loss": 1.2566,
"step": 7
},
{
"epoch": 0.02702702702702703,
"grad_norm": 1.5489553213119507,
"learning_rate": 4e-05,
"loss": 1.2766,
"step": 8
},
{
"epoch": 0.030405405405405407,
"grad_norm": 1.3374286890029907,
"learning_rate": 4.5e-05,
"loss": 1.1642,
"step": 9
},
{
"epoch": 0.033783783783783786,
"grad_norm": 1.4814637899398804,
"learning_rate": 5e-05,
"loss": 1.1382,
"step": 10
},
{
"epoch": 0.037162162162162164,
"grad_norm": 1.3145912885665894,
"learning_rate": 5.500000000000001e-05,
"loss": 1.0861,
"step": 11
},
{
"epoch": 0.04054054054054054,
"grad_norm": 1.5343668460845947,
"learning_rate": 6e-05,
"loss": 1.1041,
"step": 12
},
{
"epoch": 0.04391891891891892,
"grad_norm": 1.3800190687179565,
"learning_rate": 6.500000000000001e-05,
"loss": 1.0442,
"step": 13
},
{
"epoch": 0.0472972972972973,
"grad_norm": 1.1731736660003662,
"learning_rate": 7e-05,
"loss": 1.025,
"step": 14
},
{
"epoch": 0.05067567567567568,
"grad_norm": 1.0756690502166748,
"learning_rate": 7.500000000000001e-05,
"loss": 1.077,
"step": 15
},
{
"epoch": 0.05405405405405406,
"grad_norm": 1.126670479774475,
"learning_rate": 8e-05,
"loss": 1.0699,
"step": 16
},
{
"epoch": 0.057432432432432436,
"grad_norm": 1.2052531242370605,
"learning_rate": 8.5e-05,
"loss": 1.0481,
"step": 17
},
{
"epoch": 0.060810810810810814,
"grad_norm": 1.0971605777740479,
"learning_rate": 9e-05,
"loss": 1.1747,
"step": 18
},
{
"epoch": 0.06418918918918919,
"grad_norm": 1.2357207536697388,
"learning_rate": 9.5e-05,
"loss": 1.2298,
"step": 19
},
{
"epoch": 0.06756756756756757,
"grad_norm": 1.0170912742614746,
"learning_rate": 0.0001,
"loss": 0.963,
"step": 20
},
{
"epoch": 0.07094594594594594,
"grad_norm": 1.040585994720459,
"learning_rate": 9.999238475781957e-05,
"loss": 1.0414,
"step": 21
},
{
"epoch": 0.07432432432432433,
"grad_norm": 1.0849173069000244,
"learning_rate": 9.99695413509548e-05,
"loss": 0.9838,
"step": 22
},
{
"epoch": 0.0777027027027027,
"grad_norm": 1.2504794597625732,
"learning_rate": 9.99314767377287e-05,
"loss": 1.132,
"step": 23
},
{
"epoch": 0.08108108108108109,
"grad_norm": 1.1654671430587769,
"learning_rate": 9.987820251299122e-05,
"loss": 1.1147,
"step": 24
},
{
"epoch": 0.08445945945945946,
"grad_norm": 1.2212613821029663,
"learning_rate": 9.980973490458728e-05,
"loss": 1.0757,
"step": 25
},
{
"epoch": 0.08783783783783784,
"grad_norm": 1.6377768516540527,
"learning_rate": 9.972609476841367e-05,
"loss": 1.1149,
"step": 26
},
{
"epoch": 0.09121621621621621,
"grad_norm": 1.4654461145401,
"learning_rate": 9.962730758206611e-05,
"loss": 1.0161,
"step": 27
},
{
"epoch": 0.0945945945945946,
"grad_norm": 1.5125370025634766,
"learning_rate": 9.951340343707852e-05,
"loss": 1.1866,
"step": 28
},
{
"epoch": 0.09797297297297297,
"grad_norm": 1.3907262086868286,
"learning_rate": 9.938441702975689e-05,
"loss": 1.0566,
"step": 29
},
{
"epoch": 0.10135135135135136,
"grad_norm": 1.5802035331726074,
"learning_rate": 9.924038765061042e-05,
"loss": 1.2932,
"step": 30
},
{
"epoch": 0.10472972972972973,
"grad_norm": 1.4079865217208862,
"learning_rate": 9.908135917238321e-05,
"loss": 1.1993,
"step": 31
},
{
"epoch": 0.10810810810810811,
"grad_norm": 1.471291184425354,
"learning_rate": 9.890738003669029e-05,
"loss": 1.2195,
"step": 32
},
{
"epoch": 0.11148648648648649,
"grad_norm": 1.8197413682937622,
"learning_rate": 9.871850323926177e-05,
"loss": 1.1169,
"step": 33
},
{
"epoch": 0.11486486486486487,
"grad_norm": 1.589645504951477,
"learning_rate": 9.851478631379982e-05,
"loss": 1.2959,
"step": 34
},
{
"epoch": 0.11824324324324324,
"grad_norm": 1.9382315874099731,
"learning_rate": 9.829629131445342e-05,
"loss": 1.1117,
"step": 35
},
{
"epoch": 0.12162162162162163,
"grad_norm": 1.9313946962356567,
"learning_rate": 9.806308479691595e-05,
"loss": 1.1987,
"step": 36
},
{
"epoch": 0.125,
"grad_norm": 1.8206257820129395,
"learning_rate": 9.781523779815179e-05,
"loss": 1.1417,
"step": 37
},
{
"epoch": 0.12837837837837837,
"grad_norm": 1.890135645866394,
"learning_rate": 9.755282581475769e-05,
"loss": 1.094,
"step": 38
},
{
"epoch": 0.13175675675675674,
"grad_norm": 2.088564872741699,
"learning_rate": 9.727592877996585e-05,
"loss": 1.2143,
"step": 39
},
{
"epoch": 0.13513513513513514,
"grad_norm": 1.9415384531021118,
"learning_rate": 9.698463103929542e-05,
"loss": 1.197,
"step": 40
},
{
"epoch": 0.13851351351351351,
"grad_norm": 1.7540833950042725,
"learning_rate": 9.667902132486009e-05,
"loss": 1.0637,
"step": 41
},
{
"epoch": 0.14189189189189189,
"grad_norm": 1.8551878929138184,
"learning_rate": 9.635919272833938e-05,
"loss": 1.0685,
"step": 42
},
{
"epoch": 0.14527027027027026,
"grad_norm": 1.9881539344787598,
"learning_rate": 9.602524267262203e-05,
"loss": 1.081,
"step": 43
},
{
"epoch": 0.14864864864864866,
"grad_norm": 2.670828104019165,
"learning_rate": 9.567727288213005e-05,
"loss": 1.2052,
"step": 44
},
{
"epoch": 0.15202702702702703,
"grad_norm": 2.176063060760498,
"learning_rate": 9.53153893518325e-05,
"loss": 0.856,
"step": 45
},
{
"epoch": 0.1554054054054054,
"grad_norm": 2.3070170879364014,
"learning_rate": 9.493970231495835e-05,
"loss": 0.9129,
"step": 46
},
{
"epoch": 0.15878378378378377,
"grad_norm": 2.7001495361328125,
"learning_rate": 9.45503262094184e-05,
"loss": 0.9219,
"step": 47
},
{
"epoch": 0.16216216216216217,
"grad_norm": 2.964418888092041,
"learning_rate": 9.414737964294636e-05,
"loss": 0.9442,
"step": 48
},
{
"epoch": 0.16554054054054054,
"grad_norm": 3.5293803215026855,
"learning_rate": 9.373098535696979e-05,
"loss": 1.1814,
"step": 49
},
{
"epoch": 0.16891891891891891,
"grad_norm": 3.7675538063049316,
"learning_rate": 9.330127018922194e-05,
"loss": 0.9654,
"step": 50
},
{
"epoch": 0.16891891891891891,
"eval_loss": 1.1298441886901855,
"eval_runtime": 46.0078,
"eval_samples_per_second": 10.846,
"eval_steps_per_second": 5.434,
"step": 50
},
{
"epoch": 0.17229729729729729,
"grad_norm": 1.6099838018417358,
"learning_rate": 9.285836503510562e-05,
"loss": 0.9751,
"step": 51
},
{
"epoch": 0.17567567567567569,
"grad_norm": 1.5371800661087036,
"learning_rate": 9.24024048078213e-05,
"loss": 1.0266,
"step": 52
},
{
"epoch": 0.17905405405405406,
"grad_norm": 0.87901771068573,
"learning_rate": 9.193352839727121e-05,
"loss": 0.918,
"step": 53
},
{
"epoch": 0.18243243243243243,
"grad_norm": 0.703105628490448,
"learning_rate": 9.145187862775209e-05,
"loss": 0.7213,
"step": 54
},
{
"epoch": 0.1858108108108108,
"grad_norm": 0.8392472863197327,
"learning_rate": 9.09576022144496e-05,
"loss": 0.99,
"step": 55
},
{
"epoch": 0.1891891891891892,
"grad_norm": 0.962077260017395,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9932,
"step": 56
},
{
"epoch": 0.19256756756756757,
"grad_norm": 1.064950942993164,
"learning_rate": 8.993177550236464e-05,
"loss": 0.9774,
"step": 57
},
{
"epoch": 0.19594594594594594,
"grad_norm": 1.1014493703842163,
"learning_rate": 8.940053768033609e-05,
"loss": 0.8928,
"step": 58
},
{
"epoch": 0.19932432432432431,
"grad_norm": 0.8882946372032166,
"learning_rate": 8.885729807284856e-05,
"loss": 0.8685,
"step": 59
},
{
"epoch": 0.20270270270270271,
"grad_norm": 0.7933914661407471,
"learning_rate": 8.83022221559489e-05,
"loss": 0.9081,
"step": 60
},
{
"epoch": 0.20608108108108109,
"grad_norm": 0.8522499203681946,
"learning_rate": 8.773547901113862e-05,
"loss": 0.966,
"step": 61
},
{
"epoch": 0.20945945945945946,
"grad_norm": 0.7208542823791504,
"learning_rate": 8.715724127386972e-05,
"loss": 0.8446,
"step": 62
},
{
"epoch": 0.21283783783783783,
"grad_norm": 0.8307358026504517,
"learning_rate": 8.656768508095853e-05,
"loss": 0.9462,
"step": 63
},
{
"epoch": 0.21621621621621623,
"grad_norm": 0.9621148109436035,
"learning_rate": 8.596699001693255e-05,
"loss": 0.9179,
"step": 64
},
{
"epoch": 0.2195945945945946,
"grad_norm": 0.836197018623352,
"learning_rate": 8.535533905932738e-05,
"loss": 0.8942,
"step": 65
},
{
"epoch": 0.22297297297297297,
"grad_norm": 0.8846750259399414,
"learning_rate": 8.473291852294987e-05,
"loss": 0.8464,
"step": 66
},
{
"epoch": 0.22635135135135134,
"grad_norm": 1.0545690059661865,
"learning_rate": 8.409991800312493e-05,
"loss": 0.9341,
"step": 67
},
{
"epoch": 0.22972972972972974,
"grad_norm": 0.8369587659835815,
"learning_rate": 8.345653031794292e-05,
"loss": 0.9228,
"step": 68
},
{
"epoch": 0.23310810810810811,
"grad_norm": 0.8992530703544617,
"learning_rate": 8.280295144952536e-05,
"loss": 0.933,
"step": 69
},
{
"epoch": 0.23648648648648649,
"grad_norm": 0.958665132522583,
"learning_rate": 8.213938048432697e-05,
"loss": 0.9219,
"step": 70
},
{
"epoch": 0.23986486486486486,
"grad_norm": 0.9970949292182922,
"learning_rate": 8.146601955249188e-05,
"loss": 1.0344,
"step": 71
},
{
"epoch": 0.24324324324324326,
"grad_norm": 0.9001803398132324,
"learning_rate": 8.07830737662829e-05,
"loss": 0.9763,
"step": 72
},
{
"epoch": 0.24662162162162163,
"grad_norm": 0.9444774985313416,
"learning_rate": 8.009075115760243e-05,
"loss": 0.9402,
"step": 73
},
{
"epoch": 0.25,
"grad_norm": 1.1478818655014038,
"learning_rate": 7.938926261462366e-05,
"loss": 0.9338,
"step": 74
},
{
"epoch": 0.2533783783783784,
"grad_norm": 1.1998094320297241,
"learning_rate": 7.86788218175523e-05,
"loss": 1.1677,
"step": 75
},
{
"epoch": 0.25675675675675674,
"grad_norm": 1.059282660484314,
"learning_rate": 7.795964517353735e-05,
"loss": 0.8556,
"step": 76
},
{
"epoch": 0.26013513513513514,
"grad_norm": 1.0620920658111572,
"learning_rate": 7.723195175075136e-05,
"loss": 0.9813,
"step": 77
},
{
"epoch": 0.2635135135135135,
"grad_norm": 1.2135953903198242,
"learning_rate": 7.649596321166024e-05,
"loss": 1.035,
"step": 78
},
{
"epoch": 0.2668918918918919,
"grad_norm": 1.229359745979309,
"learning_rate": 7.575190374550272e-05,
"loss": 1.0898,
"step": 79
},
{
"epoch": 0.2702702702702703,
"grad_norm": 1.1784802675247192,
"learning_rate": 7.500000000000001e-05,
"loss": 1.1225,
"step": 80
},
{
"epoch": 0.27364864864864863,
"grad_norm": 1.334152102470398,
"learning_rate": 7.424048101231686e-05,
"loss": 1.1676,
"step": 81
},
{
"epoch": 0.27702702702702703,
"grad_norm": 1.5334789752960205,
"learning_rate": 7.347357813929454e-05,
"loss": 1.2391,
"step": 82
},
{
"epoch": 0.28040540540540543,
"grad_norm": 1.2976105213165283,
"learning_rate": 7.269952498697734e-05,
"loss": 1.0586,
"step": 83
},
{
"epoch": 0.28378378378378377,
"grad_norm": 1.3772521018981934,
"learning_rate": 7.191855733945387e-05,
"loss": 1.0095,
"step": 84
},
{
"epoch": 0.28716216216216217,
"grad_norm": 1.498609185218811,
"learning_rate": 7.113091308703498e-05,
"loss": 1.0406,
"step": 85
},
{
"epoch": 0.2905405405405405,
"grad_norm": 1.2996132373809814,
"learning_rate": 7.033683215379002e-05,
"loss": 0.9952,
"step": 86
},
{
"epoch": 0.2939189189189189,
"grad_norm": 1.400256872177124,
"learning_rate": 6.953655642446368e-05,
"loss": 0.9913,
"step": 87
},
{
"epoch": 0.2972972972972973,
"grad_norm": 1.5387816429138184,
"learning_rate": 6.873032967079561e-05,
"loss": 1.0511,
"step": 88
},
{
"epoch": 0.30067567567567566,
"grad_norm": 1.6207197904586792,
"learning_rate": 6.7918397477265e-05,
"loss": 1.1016,
"step": 89
},
{
"epoch": 0.30405405405405406,
"grad_norm": 1.9668850898742676,
"learning_rate": 6.710100716628344e-05,
"loss": 1.1591,
"step": 90
},
{
"epoch": 0.30743243243243246,
"grad_norm": 1.7193620204925537,
"learning_rate": 6.627840772285784e-05,
"loss": 0.8671,
"step": 91
},
{
"epoch": 0.3108108108108108,
"grad_norm": 1.715350866317749,
"learning_rate": 6.545084971874738e-05,
"loss": 1.0375,
"step": 92
},
{
"epoch": 0.3141891891891892,
"grad_norm": 1.7534435987472534,
"learning_rate": 6.461858523613684e-05,
"loss": 0.9131,
"step": 93
},
{
"epoch": 0.31756756756756754,
"grad_norm": 1.7787106037139893,
"learning_rate": 6.378186779084995e-05,
"loss": 0.9613,
"step": 94
},
{
"epoch": 0.32094594594594594,
"grad_norm": 1.7678383588790894,
"learning_rate": 6.294095225512603e-05,
"loss": 0.9469,
"step": 95
},
{
"epoch": 0.32432432432432434,
"grad_norm": 2.5767292976379395,
"learning_rate": 6.209609477998338e-05,
"loss": 0.8733,
"step": 96
},
{
"epoch": 0.3277027027027027,
"grad_norm": 2.0000483989715576,
"learning_rate": 6.124755271719325e-05,
"loss": 0.7498,
"step": 97
},
{
"epoch": 0.3310810810810811,
"grad_norm": 2.2624642848968506,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.7368,
"step": 98
},
{
"epoch": 0.3344594594594595,
"grad_norm": 2.4766733646392822,
"learning_rate": 5.9540449768827246e-05,
"loss": 0.8139,
"step": 99
},
{
"epoch": 0.33783783783783783,
"grad_norm": 3.698124885559082,
"learning_rate": 5.868240888334653e-05,
"loss": 0.9995,
"step": 100
},
{
"epoch": 0.33783783783783783,
"eval_loss": 1.000538945198059,
"eval_runtime": 46.0594,
"eval_samples_per_second": 10.834,
"eval_steps_per_second": 5.428,
"step": 100
},
{
"epoch": 0.34121621621621623,
"grad_norm": 1.0186338424682617,
"learning_rate": 5.782172325201155e-05,
"loss": 0.8453,
"step": 101
},
{
"epoch": 0.34459459459459457,
"grad_norm": 0.9055783748626709,
"learning_rate": 5.695865504800327e-05,
"loss": 0.8377,
"step": 102
},
{
"epoch": 0.34797297297297297,
"grad_norm": 0.7225061655044556,
"learning_rate": 5.6093467170257374e-05,
"loss": 0.7756,
"step": 103
},
{
"epoch": 0.35135135135135137,
"grad_norm": 0.7119020223617554,
"learning_rate": 5.522642316338268e-05,
"loss": 0.8643,
"step": 104
},
{
"epoch": 0.3547297297297297,
"grad_norm": 0.734737753868103,
"learning_rate": 5.435778713738292e-05,
"loss": 0.8621,
"step": 105
},
{
"epoch": 0.3581081081081081,
"grad_norm": 0.7174225449562073,
"learning_rate": 5.348782368720626e-05,
"loss": 0.8912,
"step": 106
},
{
"epoch": 0.3614864864864865,
"grad_norm": 0.7153468728065491,
"learning_rate": 5.26167978121472e-05,
"loss": 0.8481,
"step": 107
},
{
"epoch": 0.36486486486486486,
"grad_norm": 4.239837646484375,
"learning_rate": 5.174497483512506e-05,
"loss": 0.8984,
"step": 108
},
{
"epoch": 0.36824324324324326,
"grad_norm": 0.7752804756164551,
"learning_rate": 5.0872620321864185e-05,
"loss": 0.874,
"step": 109
},
{
"epoch": 0.3716216216216216,
"grad_norm": 0.8758994340896606,
"learning_rate": 5e-05,
"loss": 0.9224,
"step": 110
},
{
"epoch": 0.375,
"grad_norm": 0.9191669225692749,
"learning_rate": 4.912737967813583e-05,
"loss": 0.9024,
"step": 111
},
{
"epoch": 0.3783783783783784,
"grad_norm": 0.774233341217041,
"learning_rate": 4.825502516487497e-05,
"loss": 0.88,
"step": 112
},
{
"epoch": 0.38175675675675674,
"grad_norm": 0.930934727191925,
"learning_rate": 4.738320218785281e-05,
"loss": 0.9401,
"step": 113
},
{
"epoch": 0.38513513513513514,
"grad_norm": 1.0761253833770752,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.9752,
"step": 114
},
{
"epoch": 0.3885135135135135,
"grad_norm": 1.0920004844665527,
"learning_rate": 4.564221286261709e-05,
"loss": 0.9969,
"step": 115
},
{
"epoch": 0.3918918918918919,
"grad_norm": 0.8273784518241882,
"learning_rate": 4.477357683661734e-05,
"loss": 0.906,
"step": 116
},
{
"epoch": 0.3952702702702703,
"grad_norm": 0.8484379053115845,
"learning_rate": 4.390653282974264e-05,
"loss": 0.9741,
"step": 117
},
{
"epoch": 0.39864864864864863,
"grad_norm": 1.1233879327774048,
"learning_rate": 4.3041344951996746e-05,
"loss": 1.0823,
"step": 118
},
{
"epoch": 0.40202702702702703,
"grad_norm": 0.8519387245178223,
"learning_rate": 4.2178276747988446e-05,
"loss": 0.9061,
"step": 119
},
{
"epoch": 0.40540540540540543,
"grad_norm": 0.8419652581214905,
"learning_rate": 4.131759111665349e-05,
"loss": 0.9646,
"step": 120
},
{
"epoch": 0.40878378378378377,
"grad_norm": 0.9039245247840881,
"learning_rate": 4.045955023117276e-05,
"loss": 0.9018,
"step": 121
},
{
"epoch": 0.41216216216216217,
"grad_norm": 0.9552401900291443,
"learning_rate": 3.960441545911204e-05,
"loss": 1.0726,
"step": 122
},
{
"epoch": 0.4155405405405405,
"grad_norm": 0.9580197334289551,
"learning_rate": 3.875244728280676e-05,
"loss": 1.0545,
"step": 123
},
{
"epoch": 0.4189189189189189,
"grad_norm": 1.032099962234497,
"learning_rate": 3.790390522001662e-05,
"loss": 0.9856,
"step": 124
},
{
"epoch": 0.4222972972972973,
"grad_norm": 0.9315150380134583,
"learning_rate": 3.705904774487396e-05,
"loss": 0.9124,
"step": 125
},
{
"epoch": 0.42567567567567566,
"grad_norm": 0.9994076490402222,
"learning_rate": 3.6218132209150045e-05,
"loss": 0.9127,
"step": 126
},
{
"epoch": 0.42905405405405406,
"grad_norm": 1.0351167917251587,
"learning_rate": 3.5381414763863166e-05,
"loss": 0.9569,
"step": 127
},
{
"epoch": 0.43243243243243246,
"grad_norm": 1.2158526182174683,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.1573,
"step": 128
},
{
"epoch": 0.4358108108108108,
"grad_norm": 1.0816155672073364,
"learning_rate": 3.372159227714218e-05,
"loss": 0.9796,
"step": 129
},
{
"epoch": 0.4391891891891892,
"grad_norm": 1.2842680215835571,
"learning_rate": 3.289899283371657e-05,
"loss": 1.0394,
"step": 130
},
{
"epoch": 0.44256756756756754,
"grad_norm": 1.260899543762207,
"learning_rate": 3.2081602522734986e-05,
"loss": 0.9725,
"step": 131
},
{
"epoch": 0.44594594594594594,
"grad_norm": 1.2010434865951538,
"learning_rate": 3.12696703292044e-05,
"loss": 0.9668,
"step": 132
},
{
"epoch": 0.44932432432432434,
"grad_norm": 1.2263182401657104,
"learning_rate": 3.046344357553632e-05,
"loss": 0.9836,
"step": 133
},
{
"epoch": 0.4527027027027027,
"grad_norm": 1.2065541744232178,
"learning_rate": 2.9663167846209998e-05,
"loss": 1.0005,
"step": 134
},
{
"epoch": 0.4560810810810811,
"grad_norm": 1.3913743495941162,
"learning_rate": 2.886908691296504e-05,
"loss": 1.0954,
"step": 135
},
{
"epoch": 0.4594594594594595,
"grad_norm": 1.352413535118103,
"learning_rate": 2.8081442660546125e-05,
"loss": 1.0641,
"step": 136
},
{
"epoch": 0.46283783783783783,
"grad_norm": 1.6733180284500122,
"learning_rate": 2.7300475013022663e-05,
"loss": 1.1187,
"step": 137
},
{
"epoch": 0.46621621621621623,
"grad_norm": 1.5427696704864502,
"learning_rate": 2.6526421860705473e-05,
"loss": 1.0689,
"step": 138
},
{
"epoch": 0.46959459459459457,
"grad_norm": 1.6110302209854126,
"learning_rate": 2.575951898768315e-05,
"loss": 1.1388,
"step": 139
},
{
"epoch": 0.47297297297297297,
"grad_norm": 1.7520427703857422,
"learning_rate": 2.500000000000001e-05,
"loss": 1.0724,
"step": 140
},
{
"epoch": 0.47635135135135137,
"grad_norm": 1.4856688976287842,
"learning_rate": 2.4248096254497288e-05,
"loss": 0.9023,
"step": 141
},
{
"epoch": 0.4797297297297297,
"grad_norm": 1.7161723375320435,
"learning_rate": 2.350403678833976e-05,
"loss": 0.9077,
"step": 142
},
{
"epoch": 0.4831081081081081,
"grad_norm": 1.9696364402770996,
"learning_rate": 2.2768048249248648e-05,
"loss": 0.9744,
"step": 143
},
{
"epoch": 0.4864864864864865,
"grad_norm": 1.7188891172409058,
"learning_rate": 2.2040354826462668e-05,
"loss": 0.9735,
"step": 144
},
{
"epoch": 0.48986486486486486,
"grad_norm": 1.7963321208953857,
"learning_rate": 2.132117818244771e-05,
"loss": 0.9706,
"step": 145
},
{
"epoch": 0.49324324324324326,
"grad_norm": 1.8810453414916992,
"learning_rate": 2.061073738537635e-05,
"loss": 0.9385,
"step": 146
},
{
"epoch": 0.4966216216216216,
"grad_norm": 2.0969960689544678,
"learning_rate": 1.9909248842397584e-05,
"loss": 0.8197,
"step": 147
},
{
"epoch": 0.5,
"grad_norm": 2.593987226486206,
"learning_rate": 1.9216926233717085e-05,
"loss": 0.851,
"step": 148
},
{
"epoch": 0.5033783783783784,
"grad_norm": 2.9145469665527344,
"learning_rate": 1.8533980447508137e-05,
"loss": 1.0698,
"step": 149
},
{
"epoch": 0.5067567567567568,
"grad_norm": 3.953397750854492,
"learning_rate": 1.7860619515673033e-05,
"loss": 0.9446,
"step": 150
},
{
"epoch": 0.5067567567567568,
"eval_loss": 0.9126469492912292,
"eval_runtime": 46.0565,
"eval_samples_per_second": 10.835,
"eval_steps_per_second": 5.428,
"step": 150
},
{
"epoch": 0.5101351351351351,
"grad_norm": 0.6192936301231384,
"learning_rate": 1.7197048550474643e-05,
"loss": 0.7285,
"step": 151
},
{
"epoch": 0.5135135135135135,
"grad_norm": 0.8343040943145752,
"learning_rate": 1.6543469682057106e-05,
"loss": 0.9547,
"step": 152
},
{
"epoch": 0.5168918918918919,
"grad_norm": 0.6406455039978027,
"learning_rate": 1.5900081996875083e-05,
"loss": 0.7517,
"step": 153
},
{
"epoch": 0.5202702702702703,
"grad_norm": 0.6541436314582825,
"learning_rate": 1.526708147705013e-05,
"loss": 0.8019,
"step": 154
},
{
"epoch": 0.5236486486486487,
"grad_norm": 0.6828504800796509,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.8282,
"step": 155
},
{
"epoch": 0.527027027027027,
"grad_norm": 0.6948606371879578,
"learning_rate": 1.4033009983067452e-05,
"loss": 0.8516,
"step": 156
},
{
"epoch": 0.5304054054054054,
"grad_norm": 0.6775002479553223,
"learning_rate": 1.3432314919041478e-05,
"loss": 0.8515,
"step": 157
},
{
"epoch": 0.5337837837837838,
"grad_norm": 0.7388585805892944,
"learning_rate": 1.2842758726130283e-05,
"loss": 0.839,
"step": 158
},
{
"epoch": 0.5371621621621622,
"grad_norm": 0.703622579574585,
"learning_rate": 1.22645209888614e-05,
"loss": 0.8792,
"step": 159
},
{
"epoch": 0.5405405405405406,
"grad_norm": 0.7253432273864746,
"learning_rate": 1.1697777844051105e-05,
"loss": 0.8923,
"step": 160
},
{
"epoch": 0.543918918918919,
"grad_norm": 0.7747262120246887,
"learning_rate": 1.1142701927151456e-05,
"loss": 0.8322,
"step": 161
},
{
"epoch": 0.5472972972972973,
"grad_norm": 0.8062132596969604,
"learning_rate": 1.0599462319663905e-05,
"loss": 0.9219,
"step": 162
},
{
"epoch": 0.5506756756756757,
"grad_norm": 0.7724130749702454,
"learning_rate": 1.006822449763537e-05,
"loss": 0.8436,
"step": 163
},
{
"epoch": 0.5540540540540541,
"grad_norm": 0.8472839593887329,
"learning_rate": 9.549150281252633e-06,
"loss": 0.8944,
"step": 164
},
{
"epoch": 0.5574324324324325,
"grad_norm": 0.8941476941108704,
"learning_rate": 9.042397785550405e-06,
"loss": 0.9064,
"step": 165
},
{
"epoch": 0.5608108108108109,
"grad_norm": 0.7640281915664673,
"learning_rate": 8.548121372247918e-06,
"loss": 0.8781,
"step": 166
},
{
"epoch": 0.5641891891891891,
"grad_norm": 0.8833121061325073,
"learning_rate": 8.066471602728803e-06,
"loss": 0.9255,
"step": 167
},
{
"epoch": 0.5675675675675675,
"grad_norm": 0.851347029209137,
"learning_rate": 7.597595192178702e-06,
"loss": 0.9322,
"step": 168
},
{
"epoch": 0.5709459459459459,
"grad_norm": 0.810321033000946,
"learning_rate": 7.1416349648943894e-06,
"loss": 0.8471,
"step": 169
},
{
"epoch": 0.5743243243243243,
"grad_norm": 0.8614704012870789,
"learning_rate": 6.698729810778065e-06,
"loss": 0.9367,
"step": 170
},
{
"epoch": 0.5777027027027027,
"grad_norm": 0.9150679111480713,
"learning_rate": 6.269014643030213e-06,
"loss": 0.9969,
"step": 171
},
{
"epoch": 0.581081081081081,
"grad_norm": 0.8605937957763672,
"learning_rate": 5.852620357053651e-06,
"loss": 0.8607,
"step": 172
},
{
"epoch": 0.5844594594594594,
"grad_norm": 1.0481038093566895,
"learning_rate": 5.449673790581611e-06,
"loss": 1.0093,
"step": 173
},
{
"epoch": 0.5878378378378378,
"grad_norm": 0.9464783072471619,
"learning_rate": 5.060297685041659e-06,
"loss": 0.9167,
"step": 174
},
{
"epoch": 0.5912162162162162,
"grad_norm": 0.9964919090270996,
"learning_rate": 4.684610648167503e-06,
"loss": 0.9825,
"step": 175
},
{
"epoch": 0.5945945945945946,
"grad_norm": 1.2046271562576294,
"learning_rate": 4.322727117869951e-06,
"loss": 1.1144,
"step": 176
},
{
"epoch": 0.597972972972973,
"grad_norm": 1.106284737586975,
"learning_rate": 3.974757327377981e-06,
"loss": 0.9407,
"step": 177
},
{
"epoch": 0.6013513513513513,
"grad_norm": 1.0823030471801758,
"learning_rate": 3.6408072716606346e-06,
"loss": 1.0768,
"step": 178
},
{
"epoch": 0.6047297297297297,
"grad_norm": 1.0691875219345093,
"learning_rate": 3.3209786751399187e-06,
"loss": 0.9842,
"step": 179
},
{
"epoch": 0.6081081081081081,
"grad_norm": 1.1368988752365112,
"learning_rate": 3.0153689607045845e-06,
"loss": 0.9887,
"step": 180
},
{
"epoch": 0.6114864864864865,
"grad_norm": 1.2653436660766602,
"learning_rate": 2.724071220034158e-06,
"loss": 0.9896,
"step": 181
},
{
"epoch": 0.6148648648648649,
"grad_norm": 1.2516238689422607,
"learning_rate": 2.4471741852423237e-06,
"loss": 1.0487,
"step": 182
},
{
"epoch": 0.6182432432432432,
"grad_norm": 1.3402917385101318,
"learning_rate": 2.1847622018482283e-06,
"loss": 1.0103,
"step": 183
},
{
"epoch": 0.6216216216216216,
"grad_norm": 1.262702465057373,
"learning_rate": 1.9369152030840556e-06,
"loss": 1.0372,
"step": 184
},
{
"epoch": 0.625,
"grad_norm": 1.4456307888031006,
"learning_rate": 1.70370868554659e-06,
"loss": 1.0428,
"step": 185
},
{
"epoch": 0.6283783783783784,
"grad_norm": 1.3446658849716187,
"learning_rate": 1.4852136862001764e-06,
"loss": 0.9193,
"step": 186
},
{
"epoch": 0.6317567567567568,
"grad_norm": 1.3438100814819336,
"learning_rate": 1.2814967607382432e-06,
"loss": 0.9874,
"step": 187
},
{
"epoch": 0.6351351351351351,
"grad_norm": 1.4625295400619507,
"learning_rate": 1.0926199633097157e-06,
"loss": 1.029,
"step": 188
},
{
"epoch": 0.6385135135135135,
"grad_norm": 1.483274221420288,
"learning_rate": 9.186408276168013e-07,
"loss": 1.0447,
"step": 189
},
{
"epoch": 0.6418918918918919,
"grad_norm": 1.465547800064087,
"learning_rate": 7.596123493895991e-07,
"loss": 0.942,
"step": 190
},
{
"epoch": 0.6452702702702703,
"grad_norm": 1.4706659317016602,
"learning_rate": 6.15582970243117e-07,
"loss": 0.9201,
"step": 191
},
{
"epoch": 0.6486486486486487,
"grad_norm": 1.6549694538116455,
"learning_rate": 4.865965629214819e-07,
"loss": 0.9416,
"step": 192
},
{
"epoch": 0.652027027027027,
"grad_norm": 1.8328434228897095,
"learning_rate": 3.7269241793390085e-07,
"loss": 0.8847,
"step": 193
},
{
"epoch": 0.6554054054054054,
"grad_norm": 1.9863508939743042,
"learning_rate": 2.7390523158633554e-07,
"loss": 1.0239,
"step": 194
},
{
"epoch": 0.6587837837837838,
"grad_norm": 2.24349045753479,
"learning_rate": 1.9026509541272275e-07,
"loss": 0.9537,
"step": 195
},
{
"epoch": 0.6621621621621622,
"grad_norm": 1.7743157148361206,
"learning_rate": 1.2179748700879012e-07,
"loss": 0.8168,
"step": 196
},
{
"epoch": 0.6655405405405406,
"grad_norm": 1.914005160331726,
"learning_rate": 6.852326227130834e-08,
"loss": 0.9011,
"step": 197
},
{
"epoch": 0.668918918918919,
"grad_norm": 2.189371347427368,
"learning_rate": 3.04586490452119e-08,
"loss": 0.7415,
"step": 198
},
{
"epoch": 0.6722972972972973,
"grad_norm": 2.4612550735473633,
"learning_rate": 7.615242180436522e-09,
"loss": 0.916,
"step": 199
},
{
"epoch": 0.6756756756756757,
"grad_norm": 4.088647842407227,
"learning_rate": 0.0,
"loss": 0.9358,
"step": 200
},
{
"epoch": 0.6756756756756757,
"eval_loss": 0.8946874737739563,
"eval_runtime": 46.0155,
"eval_samples_per_second": 10.844,
"eval_steps_per_second": 5.433,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.1421973496489574e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}