yuzhounie's picture
End of training
8d0a1e3 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.982264665757162,
"eval_steps": 500,
"global_step": 366,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.008185538881309686,
"grad_norm": 5.0478727782480615,
"learning_rate": 0.0,
"loss": 1.0078,
"step": 1
},
{
"epoch": 0.01637107776261937,
"grad_norm": 5.297869728172454,
"learning_rate": 2.702702702702703e-07,
"loss": 1.0618,
"step": 2
},
{
"epoch": 0.02455661664392906,
"grad_norm": 5.2373720826529615,
"learning_rate": 5.405405405405406e-07,
"loss": 0.996,
"step": 3
},
{
"epoch": 0.03274215552523874,
"grad_norm": 5.1487966370839615,
"learning_rate": 8.108108108108109e-07,
"loss": 1.0566,
"step": 4
},
{
"epoch": 0.040927694406548434,
"grad_norm": 4.889603343820506,
"learning_rate": 1.0810810810810812e-06,
"loss": 1.0428,
"step": 5
},
{
"epoch": 0.04911323328785812,
"grad_norm": 5.010279773418308,
"learning_rate": 1.3513513513513515e-06,
"loss": 1.0379,
"step": 6
},
{
"epoch": 0.0572987721691678,
"grad_norm": 4.110386008020255,
"learning_rate": 1.6216216216216219e-06,
"loss": 1.0033,
"step": 7
},
{
"epoch": 0.06548431105047749,
"grad_norm": 3.7462198602177916,
"learning_rate": 1.8918918918918922e-06,
"loss": 0.968,
"step": 8
},
{
"epoch": 0.07366984993178717,
"grad_norm": 3.595416096229768,
"learning_rate": 2.1621621621621623e-06,
"loss": 0.9803,
"step": 9
},
{
"epoch": 0.08185538881309687,
"grad_norm": 2.533438078443084,
"learning_rate": 2.432432432432433e-06,
"loss": 0.9224,
"step": 10
},
{
"epoch": 0.09004092769440655,
"grad_norm": 2.320695272044533,
"learning_rate": 2.702702702702703e-06,
"loss": 0.9266,
"step": 11
},
{
"epoch": 0.09822646657571624,
"grad_norm": 2.2691993926294485,
"learning_rate": 2.9729729729729736e-06,
"loss": 0.9506,
"step": 12
},
{
"epoch": 0.10641200545702592,
"grad_norm": 1.6484336480613677,
"learning_rate": 3.2432432432432437e-06,
"loss": 0.8901,
"step": 13
},
{
"epoch": 0.1145975443383356,
"grad_norm": 1.587811768676501,
"learning_rate": 3.513513513513514e-06,
"loss": 0.8924,
"step": 14
},
{
"epoch": 0.12278308321964529,
"grad_norm": 1.4428141733888997,
"learning_rate": 3.7837837837837844e-06,
"loss": 0.8533,
"step": 15
},
{
"epoch": 0.13096862210095497,
"grad_norm": 1.327517776817959,
"learning_rate": 4.0540540540540545e-06,
"loss": 0.8403,
"step": 16
},
{
"epoch": 0.13915416098226466,
"grad_norm": 1.1903685597921168,
"learning_rate": 4.324324324324325e-06,
"loss": 0.8213,
"step": 17
},
{
"epoch": 0.14733969986357434,
"grad_norm": 1.1265141075408769,
"learning_rate": 4.594594594594596e-06,
"loss": 0.7893,
"step": 18
},
{
"epoch": 0.15552523874488403,
"grad_norm": 1.0112222898955754,
"learning_rate": 4.864864864864866e-06,
"loss": 0.7686,
"step": 19
},
{
"epoch": 0.16371077762619374,
"grad_norm": 1.0155475919941201,
"learning_rate": 5.135135135135135e-06,
"loss": 0.7895,
"step": 20
},
{
"epoch": 0.17189631650750342,
"grad_norm": 0.9424205847898997,
"learning_rate": 5.405405405405406e-06,
"loss": 0.7934,
"step": 21
},
{
"epoch": 0.1800818553888131,
"grad_norm": 0.9297919004627947,
"learning_rate": 5.675675675675676e-06,
"loss": 0.7704,
"step": 22
},
{
"epoch": 0.1882673942701228,
"grad_norm": 0.8942582616046999,
"learning_rate": 5.945945945945947e-06,
"loss": 0.771,
"step": 23
},
{
"epoch": 0.19645293315143247,
"grad_norm": 0.8790765346003704,
"learning_rate": 6.2162162162162164e-06,
"loss": 0.7519,
"step": 24
},
{
"epoch": 0.20463847203274216,
"grad_norm": 0.8704256340257236,
"learning_rate": 6.486486486486487e-06,
"loss": 0.7817,
"step": 25
},
{
"epoch": 0.21282401091405184,
"grad_norm": 0.8936039954661188,
"learning_rate": 6.7567567567567575e-06,
"loss": 0.7558,
"step": 26
},
{
"epoch": 0.22100954979536153,
"grad_norm": 0.9000294604512896,
"learning_rate": 7.027027027027028e-06,
"loss": 0.756,
"step": 27
},
{
"epoch": 0.2291950886766712,
"grad_norm": 0.760124422848503,
"learning_rate": 7.297297297297298e-06,
"loss": 0.6948,
"step": 28
},
{
"epoch": 0.2373806275579809,
"grad_norm": 0.8051399822377988,
"learning_rate": 7.567567567567569e-06,
"loss": 0.7303,
"step": 29
},
{
"epoch": 0.24556616643929058,
"grad_norm": 0.7986272722014214,
"learning_rate": 7.837837837837838e-06,
"loss": 0.7072,
"step": 30
},
{
"epoch": 0.25375170532060026,
"grad_norm": 0.7581553292292164,
"learning_rate": 8.108108108108109e-06,
"loss": 0.7516,
"step": 31
},
{
"epoch": 0.26193724420190995,
"grad_norm": 0.7494941699803703,
"learning_rate": 8.378378378378378e-06,
"loss": 0.6875,
"step": 32
},
{
"epoch": 0.27012278308321963,
"grad_norm": 0.7035656192285054,
"learning_rate": 8.64864864864865e-06,
"loss": 0.6868,
"step": 33
},
{
"epoch": 0.2783083219645293,
"grad_norm": 0.825065049654731,
"learning_rate": 8.91891891891892e-06,
"loss": 0.724,
"step": 34
},
{
"epoch": 0.286493860845839,
"grad_norm": 0.7398891146832497,
"learning_rate": 9.189189189189191e-06,
"loss": 0.6647,
"step": 35
},
{
"epoch": 0.2946793997271487,
"grad_norm": 0.7872339743993603,
"learning_rate": 9.45945945945946e-06,
"loss": 0.7306,
"step": 36
},
{
"epoch": 0.30286493860845837,
"grad_norm": 0.802374234041993,
"learning_rate": 9.729729729729732e-06,
"loss": 0.7196,
"step": 37
},
{
"epoch": 0.31105047748976805,
"grad_norm": 0.6743014958494054,
"learning_rate": 1e-05,
"loss": 0.6844,
"step": 38
},
{
"epoch": 0.31923601637107774,
"grad_norm": 0.7173190441882299,
"learning_rate": 9.999772047343259e-06,
"loss": 0.7104,
"step": 39
},
{
"epoch": 0.3274215552523875,
"grad_norm": 0.7316123657845623,
"learning_rate": 9.999088210158001e-06,
"loss": 0.7021,
"step": 40
},
{
"epoch": 0.33560709413369716,
"grad_norm": 0.7117684019510708,
"learning_rate": 9.997948550797227e-06,
"loss": 0.6858,
"step": 41
},
{
"epoch": 0.34379263301500684,
"grad_norm": 0.7188976086512107,
"learning_rate": 9.99635317317629e-06,
"loss": 0.7019,
"step": 42
},
{
"epoch": 0.3519781718963165,
"grad_norm": 0.7377050581756815,
"learning_rate": 9.994302222763415e-06,
"loss": 0.6814,
"step": 43
},
{
"epoch": 0.3601637107776262,
"grad_norm": 0.9135462047269537,
"learning_rate": 9.991795886566443e-06,
"loss": 0.6657,
"step": 44
},
{
"epoch": 0.3683492496589359,
"grad_norm": 0.7192062851816737,
"learning_rate": 9.988834393115768e-06,
"loss": 0.683,
"step": 45
},
{
"epoch": 0.3765347885402456,
"grad_norm": 0.7317307030654772,
"learning_rate": 9.98541801244351e-06,
"loss": 0.698,
"step": 46
},
{
"epoch": 0.38472032742155526,
"grad_norm": 0.7370617382707109,
"learning_rate": 9.981547056058893e-06,
"loss": 0.6974,
"step": 47
},
{
"epoch": 0.39290586630286495,
"grad_norm": 0.7213739361864256,
"learning_rate": 9.977221876919833e-06,
"loss": 0.6768,
"step": 48
},
{
"epoch": 0.40109140518417463,
"grad_norm": 0.7364591234843338,
"learning_rate": 9.97244286940076e-06,
"loss": 0.681,
"step": 49
},
{
"epoch": 0.4092769440654843,
"grad_norm": 0.6967769200295396,
"learning_rate": 9.967210469256657e-06,
"loss": 0.6871,
"step": 50
},
{
"epoch": 0.417462482946794,
"grad_norm": 0.7133269832692841,
"learning_rate": 9.961525153583327e-06,
"loss": 0.6727,
"step": 51
},
{
"epoch": 0.4256480218281037,
"grad_norm": 0.7593591165695961,
"learning_rate": 9.955387440773902e-06,
"loss": 0.6613,
"step": 52
},
{
"epoch": 0.43383356070941337,
"grad_norm": 0.7629742272484056,
"learning_rate": 9.948797890471552e-06,
"loss": 0.7059,
"step": 53
},
{
"epoch": 0.44201909959072305,
"grad_norm": 0.7869395014265814,
"learning_rate": 9.94175710351848e-06,
"loss": 0.6809,
"step": 54
},
{
"epoch": 0.45020463847203274,
"grad_norm": 0.7557966627645061,
"learning_rate": 9.93426572190112e-06,
"loss": 0.6888,
"step": 55
},
{
"epoch": 0.4583901773533424,
"grad_norm": 0.7627089251776806,
"learning_rate": 9.926324428691612e-06,
"loss": 0.6749,
"step": 56
},
{
"epoch": 0.4665757162346521,
"grad_norm": 0.7647324761458698,
"learning_rate": 9.917933947985508e-06,
"loss": 0.651,
"step": 57
},
{
"epoch": 0.4747612551159618,
"grad_norm": 0.7522615995282188,
"learning_rate": 9.909095044835755e-06,
"loss": 0.6634,
"step": 58
},
{
"epoch": 0.4829467939972715,
"grad_norm": 0.6975083371701567,
"learning_rate": 9.899808525182935e-06,
"loss": 0.673,
"step": 59
},
{
"epoch": 0.49113233287858116,
"grad_norm": 0.7388297177443647,
"learning_rate": 9.89007523578178e-06,
"loss": 0.672,
"step": 60
},
{
"epoch": 0.49931787175989084,
"grad_norm": 0.7399455004229146,
"learning_rate": 9.879896064123961e-06,
"loss": 0.6869,
"step": 61
},
{
"epoch": 0.5075034106412005,
"grad_norm": 0.641768950781225,
"learning_rate": 9.869271938357168e-06,
"loss": 0.6656,
"step": 62
},
{
"epoch": 0.5156889495225102,
"grad_norm": 0.6747503842637269,
"learning_rate": 9.858203827200477e-06,
"loss": 0.6681,
"step": 63
},
{
"epoch": 0.5238744884038199,
"grad_norm": 0.7083166062792678,
"learning_rate": 9.846692739856023e-06,
"loss": 0.6862,
"step": 64
},
{
"epoch": 0.5320600272851296,
"grad_norm": 0.6630698780804426,
"learning_rate": 9.834739725916988e-06,
"loss": 0.6975,
"step": 65
},
{
"epoch": 0.5402455661664393,
"grad_norm": 0.681533225253199,
"learning_rate": 9.822345875271884e-06,
"loss": 0.686,
"step": 66
},
{
"epoch": 0.548431105047749,
"grad_norm": 0.6840648475760192,
"learning_rate": 9.80951231800518e-06,
"loss": 0.6657,
"step": 67
},
{
"epoch": 0.5566166439290586,
"grad_norm": 0.6882516854997278,
"learning_rate": 9.79624022429427e-06,
"loss": 0.6674,
"step": 68
},
{
"epoch": 0.5648021828103683,
"grad_norm": 0.6673399727161186,
"learning_rate": 9.782530804302763e-06,
"loss": 0.6712,
"step": 69
},
{
"epoch": 0.572987721691678,
"grad_norm": 0.6523633450588768,
"learning_rate": 9.768385308070139e-06,
"loss": 0.6499,
"step": 70
},
{
"epoch": 0.5811732605729877,
"grad_norm": 0.6402501529233903,
"learning_rate": 9.75380502539778e-06,
"loss": 0.6376,
"step": 71
},
{
"epoch": 0.5893587994542974,
"grad_norm": 0.6636314846823285,
"learning_rate": 9.738791285731353e-06,
"loss": 0.6278,
"step": 72
},
{
"epoch": 0.597544338335607,
"grad_norm": 0.8003245675376227,
"learning_rate": 9.723345458039595e-06,
"loss": 0.6538,
"step": 73
},
{
"epoch": 0.6057298772169167,
"grad_norm": 0.7185853457714209,
"learning_rate": 9.70746895068949e-06,
"loss": 0.6439,
"step": 74
},
{
"epoch": 0.6139154160982264,
"grad_norm": 0.6699308724912499,
"learning_rate": 9.691163211317853e-06,
"loss": 0.6968,
"step": 75
},
{
"epoch": 0.6221009549795361,
"grad_norm": 0.6797018354628909,
"learning_rate": 9.674429726699324e-06,
"loss": 0.6633,
"step": 76
},
{
"epoch": 0.6302864938608458,
"grad_norm": 0.666380912419756,
"learning_rate": 9.657270022610814e-06,
"loss": 0.6652,
"step": 77
},
{
"epoch": 0.6384720327421555,
"grad_norm": 0.6433578757501699,
"learning_rate": 9.63968566369238e-06,
"loss": 0.6231,
"step": 78
},
{
"epoch": 0.6466575716234653,
"grad_norm": 0.697083409509591,
"learning_rate": 9.62167825330455e-06,
"loss": 0.6617,
"step": 79
},
{
"epoch": 0.654843110504775,
"grad_norm": 0.6824957117453533,
"learning_rate": 9.603249433382145e-06,
"loss": 0.6845,
"step": 80
},
{
"epoch": 0.6630286493860846,
"grad_norm": 0.6293701917757308,
"learning_rate": 9.584400884284546e-06,
"loss": 0.6451,
"step": 81
},
{
"epoch": 0.6712141882673943,
"grad_norm": 0.6562401782569836,
"learning_rate": 9.565134324642491e-06,
"loss": 0.6687,
"step": 82
},
{
"epoch": 0.679399727148704,
"grad_norm": 0.668101435033017,
"learning_rate": 9.545451511201365e-06,
"loss": 0.6653,
"step": 83
},
{
"epoch": 0.6875852660300137,
"grad_norm": 0.6897068006081355,
"learning_rate": 9.52535423866101e-06,
"loss": 0.6769,
"step": 84
},
{
"epoch": 0.6957708049113234,
"grad_norm": 0.6444378609992228,
"learning_rate": 9.504844339512096e-06,
"loss": 0.6255,
"step": 85
},
{
"epoch": 0.703956343792633,
"grad_norm": 0.6988896735645694,
"learning_rate": 9.483923683869025e-06,
"loss": 0.6273,
"step": 86
},
{
"epoch": 0.7121418826739427,
"grad_norm": 0.7291838388829389,
"learning_rate": 9.462594179299408e-06,
"loss": 0.6644,
"step": 87
},
{
"epoch": 0.7203274215552524,
"grad_norm": 0.6690961584546128,
"learning_rate": 9.440857770650139e-06,
"loss": 0.7172,
"step": 88
},
{
"epoch": 0.7285129604365621,
"grad_norm": 0.9091183830996429,
"learning_rate": 9.418716439870056e-06,
"loss": 0.6236,
"step": 89
},
{
"epoch": 0.7366984993178718,
"grad_norm": 0.7033410685474086,
"learning_rate": 9.396172205829235e-06,
"loss": 0.6735,
"step": 90
},
{
"epoch": 0.7448840381991815,
"grad_norm": 0.6845856558187914,
"learning_rate": 9.373227124134888e-06,
"loss": 0.6464,
"step": 91
},
{
"epoch": 0.7530695770804912,
"grad_norm": 0.6765703675484731,
"learning_rate": 9.349883286943951e-06,
"loss": 0.6328,
"step": 92
},
{
"epoch": 0.7612551159618008,
"grad_norm": 0.6753232110728814,
"learning_rate": 9.326142822772301e-06,
"loss": 0.6653,
"step": 93
},
{
"epoch": 0.7694406548431105,
"grad_norm": 0.6604394934259564,
"learning_rate": 9.302007896300697e-06,
"loss": 0.6174,
"step": 94
},
{
"epoch": 0.7776261937244202,
"grad_norm": 0.6607499407814651,
"learning_rate": 9.27748070817738e-06,
"loss": 0.6667,
"step": 95
},
{
"epoch": 0.7858117326057299,
"grad_norm": 0.6177046884395893,
"learning_rate": 9.252563494817426e-06,
"loss": 0.6644,
"step": 96
},
{
"epoch": 0.7939972714870396,
"grad_norm": 0.6532085389117603,
"learning_rate": 9.227258528198832e-06,
"loss": 0.6554,
"step": 97
},
{
"epoch": 0.8021828103683493,
"grad_norm": 0.6531878007459695,
"learning_rate": 9.201568115655343e-06,
"loss": 0.6624,
"step": 98
},
{
"epoch": 0.810368349249659,
"grad_norm": 0.7244203842003859,
"learning_rate": 9.175494599666078e-06,
"loss": 0.6599,
"step": 99
},
{
"epoch": 0.8185538881309686,
"grad_norm": 0.6581466542372403,
"learning_rate": 9.14904035764193e-06,
"loss": 0.6409,
"step": 100
},
{
"epoch": 0.8267394270122783,
"grad_norm": 0.6590221337516023,
"learning_rate": 9.122207801708802e-06,
"loss": 0.6955,
"step": 101
},
{
"epoch": 0.834924965893588,
"grad_norm": 0.6461062189640926,
"learning_rate": 9.094999378487659e-06,
"loss": 0.6558,
"step": 102
},
{
"epoch": 0.8431105047748977,
"grad_norm": 0.6574652022208926,
"learning_rate": 9.067417568871444e-06,
"loss": 0.6355,
"step": 103
},
{
"epoch": 0.8512960436562074,
"grad_norm": 0.6733446230502218,
"learning_rate": 9.03946488779887e-06,
"loss": 0.6442,
"step": 104
},
{
"epoch": 0.859481582537517,
"grad_norm": 0.6644073928901805,
"learning_rate": 9.0111438840251e-06,
"loss": 0.6401,
"step": 105
},
{
"epoch": 0.8676671214188267,
"grad_norm": 0.6258042538207641,
"learning_rate": 8.982457139889358e-06,
"loss": 0.623,
"step": 106
},
{
"epoch": 0.8758526603001364,
"grad_norm": 0.6262353607723671,
"learning_rate": 8.953407271079456e-06,
"loss": 0.6215,
"step": 107
},
{
"epoch": 0.8840381991814461,
"grad_norm": 0.7145148499205656,
"learning_rate": 8.923996926393306e-06,
"loss": 0.6434,
"step": 108
},
{
"epoch": 0.8922237380627558,
"grad_norm": 0.6514835061195294,
"learning_rate": 8.894228787497389e-06,
"loss": 0.6487,
"step": 109
},
{
"epoch": 0.9004092769440655,
"grad_norm": 0.6478318245257795,
"learning_rate": 8.864105568682245e-06,
"loss": 0.6165,
"step": 110
},
{
"epoch": 0.9085948158253752,
"grad_norm": 0.635966960589811,
"learning_rate": 8.833630016614976e-06,
"loss": 0.6593,
"step": 111
},
{
"epoch": 0.9167803547066848,
"grad_norm": 0.6188382437651978,
"learning_rate": 8.80280491008881e-06,
"loss": 0.6539,
"step": 112
},
{
"epoch": 0.9249658935879945,
"grad_norm": 0.6533555870938427,
"learning_rate": 8.771633059769712e-06,
"loss": 0.6471,
"step": 113
},
{
"epoch": 0.9331514324693042,
"grad_norm": 0.6172503829228955,
"learning_rate": 8.740117307940123e-06,
"loss": 0.6363,
"step": 114
},
{
"epoch": 0.9413369713506139,
"grad_norm": 0.6690820221849542,
"learning_rate": 8.708260528239788e-06,
"loss": 0.6833,
"step": 115
},
{
"epoch": 0.9495225102319236,
"grad_norm": 0.63570538453503,
"learning_rate": 8.676065625403733e-06,
"loss": 0.655,
"step": 116
},
{
"epoch": 0.9577080491132333,
"grad_norm": 0.6481910046193415,
"learning_rate": 8.64353553499741e-06,
"loss": 0.6274,
"step": 117
},
{
"epoch": 0.965893587994543,
"grad_norm": 0.6226429114821875,
"learning_rate": 8.610673223149036e-06,
"loss": 0.637,
"step": 118
},
{
"epoch": 0.9740791268758526,
"grad_norm": 0.6252222904571513,
"learning_rate": 8.577481686279123e-06,
"loss": 0.648,
"step": 119
},
{
"epoch": 0.9822646657571623,
"grad_norm": 0.6580747113143244,
"learning_rate": 8.543963950827279e-06,
"loss": 0.6461,
"step": 120
},
{
"epoch": 0.990450204638472,
"grad_norm": 0.6540805705810817,
"learning_rate": 8.51012307297624e-06,
"loss": 0.6625,
"step": 121
},
{
"epoch": 0.9986357435197817,
"grad_norm": 0.6802947249507815,
"learning_rate": 8.475962138373212e-06,
"loss": 0.6561,
"step": 122
},
{
"epoch": 1.0,
"grad_norm": 0.6802947249507815,
"learning_rate": 8.441484261848514e-06,
"loss": 0.6048,
"step": 123
},
{
"epoch": 1.0081855388813097,
"grad_norm": 1.4690540777621837,
"learning_rate": 8.406692587131569e-06,
"loss": 0.5364,
"step": 124
},
{
"epoch": 1.0163710777626194,
"grad_norm": 0.6668502929153187,
"learning_rate": 8.371590286564247e-06,
"loss": 0.5698,
"step": 125
},
{
"epoch": 1.024556616643929,
"grad_norm": 0.6630075245165461,
"learning_rate": 8.336180560811619e-06,
"loss": 0.5295,
"step": 126
},
{
"epoch": 1.0327421555252387,
"grad_norm": 0.628047334528465,
"learning_rate": 8.30046663857011e-06,
"loss": 0.5522,
"step": 127
},
{
"epoch": 1.0409276944065484,
"grad_norm": 0.6321367262570028,
"learning_rate": 8.264451776273104e-06,
"loss": 0.5328,
"step": 128
},
{
"epoch": 1.049113233287858,
"grad_norm": 0.6509232625662688,
"learning_rate": 8.228139257794012e-06,
"loss": 0.5293,
"step": 129
},
{
"epoch": 1.0572987721691678,
"grad_norm": 0.6653995825660356,
"learning_rate": 8.191532394146865e-06,
"loss": 0.5321,
"step": 130
},
{
"epoch": 1.0654843110504775,
"grad_norm": 0.6753798862378513,
"learning_rate": 8.154634523184389e-06,
"loss": 0.5501,
"step": 131
},
{
"epoch": 1.0736698499317872,
"grad_norm": 0.6925676306857319,
"learning_rate": 8.117449009293668e-06,
"loss": 0.5588,
"step": 132
},
{
"epoch": 1.0818553888130968,
"grad_norm": 0.6875121153461677,
"learning_rate": 8.07997924308938e-06,
"loss": 0.5169,
"step": 133
},
{
"epoch": 1.0900409276944065,
"grad_norm": 0.6635596925394057,
"learning_rate": 8.042228641104622e-06,
"loss": 0.5288,
"step": 134
},
{
"epoch": 1.0982264665757162,
"grad_norm": 0.659706003479899,
"learning_rate": 8.004200645479403e-06,
"loss": 0.5431,
"step": 135
},
{
"epoch": 1.106412005457026,
"grad_norm": 0.63943734644461,
"learning_rate": 7.965898723646777e-06,
"loss": 0.502,
"step": 136
},
{
"epoch": 1.1145975443383356,
"grad_norm": 0.6648591862403953,
"learning_rate": 7.927326368016677e-06,
"loss": 0.5207,
"step": 137
},
{
"epoch": 1.1227830832196453,
"grad_norm": 0.7024194556815612,
"learning_rate": 7.888487095657484e-06,
"loss": 0.5611,
"step": 138
},
{
"epoch": 1.130968622100955,
"grad_norm": 0.7739952225143985,
"learning_rate": 7.849384447975322e-06,
"loss": 0.5366,
"step": 139
},
{
"epoch": 1.1391541609822646,
"grad_norm": 0.6733083982037561,
"learning_rate": 7.810021990391163e-06,
"loss": 0.5338,
"step": 140
},
{
"epoch": 1.1473396998635743,
"grad_norm": 0.7631285514542114,
"learning_rate": 7.77040331201572e-06,
"loss": 0.5433,
"step": 141
},
{
"epoch": 1.155525238744884,
"grad_norm": 0.7358222036858854,
"learning_rate": 7.73053202532219e-06,
"loss": 0.5157,
"step": 142
},
{
"epoch": 1.1637107776261937,
"grad_norm": 0.7221523031273229,
"learning_rate": 7.690411765816864e-06,
"loss": 0.5195,
"step": 143
},
{
"epoch": 1.1718963165075034,
"grad_norm": 0.7073093802159716,
"learning_rate": 7.650046191707641e-06,
"loss": 0.52,
"step": 144
},
{
"epoch": 1.180081855388813,
"grad_norm": 0.6973266687976701,
"learning_rate": 7.609438983570461e-06,
"loss": 0.5377,
"step": 145
},
{
"epoch": 1.1882673942701227,
"grad_norm": 0.6972778402889085,
"learning_rate": 7.5685938440137185e-06,
"loss": 0.5331,
"step": 146
},
{
"epoch": 1.1964529331514324,
"grad_norm": 0.7015895074267741,
"learning_rate": 7.527514497340642e-06,
"loss": 0.5009,
"step": 147
},
{
"epoch": 1.204638472032742,
"grad_norm": 0.6741755282012447,
"learning_rate": 7.486204689209719e-06,
"loss": 0.5084,
"step": 148
},
{
"epoch": 1.2128240109140518,
"grad_norm": 0.6897917137599813,
"learning_rate": 7.444668186293153e-06,
"loss": 0.5325,
"step": 149
},
{
"epoch": 1.2210095497953615,
"grad_norm": 0.7009173085054421,
"learning_rate": 7.402908775933419e-06,
"loss": 0.5427,
"step": 150
},
{
"epoch": 1.2291950886766712,
"grad_norm": 0.6955840979269092,
"learning_rate": 7.360930265797934e-06,
"loss": 0.5142,
"step": 151
},
{
"epoch": 1.2373806275579808,
"grad_norm": 0.6959419263618837,
"learning_rate": 7.318736483531861e-06,
"loss": 0.503,
"step": 152
},
{
"epoch": 1.2455661664392905,
"grad_norm": 0.7795131376962834,
"learning_rate": 7.2763312764091055e-06,
"loss": 0.5145,
"step": 153
},
{
"epoch": 1.2537517053206002,
"grad_norm": 0.7429337505244488,
"learning_rate": 7.23371851098152e-06,
"loss": 0.5349,
"step": 154
},
{
"epoch": 1.26193724420191,
"grad_norm": 0.6965919792231839,
"learning_rate": 7.190902072726336e-06,
"loss": 0.5057,
"step": 155
},
{
"epoch": 1.2701227830832196,
"grad_norm": 0.6591537697874793,
"learning_rate": 7.147885865691899e-06,
"loss": 0.5061,
"step": 156
},
{
"epoch": 1.2783083219645293,
"grad_norm": 0.7634419632836582,
"learning_rate": 7.104673812141676e-06,
"loss": 0.5328,
"step": 157
},
{
"epoch": 1.286493860845839,
"grad_norm": 0.7183717648332919,
"learning_rate": 7.061269852196633e-06,
"loss": 0.5068,
"step": 158
},
{
"epoch": 1.2946793997271486,
"grad_norm": 0.7590687460497102,
"learning_rate": 7.017677943475962e-06,
"loss": 0.5506,
"step": 159
},
{
"epoch": 1.3028649386084583,
"grad_norm": 0.6686899677756686,
"learning_rate": 6.973902060736226e-06,
"loss": 0.5391,
"step": 160
},
{
"epoch": 1.311050477489768,
"grad_norm": 0.7109155867540288,
"learning_rate": 6.929946195508933e-06,
"loss": 0.5052,
"step": 161
},
{
"epoch": 1.3192360163710777,
"grad_norm": 0.7331433020230873,
"learning_rate": 6.8858143557365865e-06,
"loss": 0.527,
"step": 162
},
{
"epoch": 1.3274215552523874,
"grad_norm": 0.6475968556383218,
"learning_rate": 6.841510565407235e-06,
"loss": 0.5509,
"step": 163
},
{
"epoch": 1.3356070941336973,
"grad_norm": 0.6833703206105858,
"learning_rate": 6.797038864187564e-06,
"loss": 0.5464,
"step": 164
},
{
"epoch": 1.3437926330150067,
"grad_norm": 0.8467686230501152,
"learning_rate": 6.752403307054549e-06,
"loss": 0.5268,
"step": 165
},
{
"epoch": 1.3519781718963166,
"grad_norm": 0.7310142599724203,
"learning_rate": 6.707607963925725e-06,
"loss": 0.5025,
"step": 166
},
{
"epoch": 1.360163710777626,
"grad_norm": 0.6809585209898018,
"learning_rate": 6.66265691928808e-06,
"loss": 0.531,
"step": 167
},
{
"epoch": 1.368349249658936,
"grad_norm": 0.6815435370183068,
"learning_rate": 6.617554271825636e-06,
"loss": 0.4991,
"step": 168
},
{
"epoch": 1.3765347885402455,
"grad_norm": 0.6756734543791449,
"learning_rate": 6.5723041340457175e-06,
"loss": 0.5595,
"step": 169
},
{
"epoch": 1.3847203274215554,
"grad_norm": 0.6708184208199593,
"learning_rate": 6.526910631903973e-06,
"loss": 0.5183,
"step": 170
},
{
"epoch": 1.3929058663028648,
"grad_norm": 1.0088094436813815,
"learning_rate": 6.481377904428171e-06,
"loss": 0.544,
"step": 171
},
{
"epoch": 1.4010914051841747,
"grad_norm": 0.6756865297821381,
"learning_rate": 6.435710103340787e-06,
"loss": 0.5268,
"step": 172
},
{
"epoch": 1.4092769440654842,
"grad_norm": 0.6886939982043838,
"learning_rate": 6.3899113926804565e-06,
"loss": 0.5284,
"step": 173
},
{
"epoch": 1.4174624829467941,
"grad_norm": 0.6615078806376291,
"learning_rate": 6.3439859484222874e-06,
"loss": 0.5013,
"step": 174
},
{
"epoch": 1.4256480218281036,
"grad_norm": 0.695006380687812,
"learning_rate": 6.297937958097094e-06,
"loss": 0.5378,
"step": 175
},
{
"epoch": 1.4338335607094135,
"grad_norm": 0.6757415493057738,
"learning_rate": 6.251771620409563e-06,
"loss": 0.4894,
"step": 176
},
{
"epoch": 1.442019099590723,
"grad_norm": 0.9523879204893828,
"learning_rate": 6.205491144855432e-06,
"loss": 0.5159,
"step": 177
},
{
"epoch": 1.4502046384720328,
"grad_norm": 0.6817012112883398,
"learning_rate": 6.1591007513376425e-06,
"loss": 0.5389,
"step": 178
},
{
"epoch": 1.4583901773533423,
"grad_norm": 0.7378659676716955,
"learning_rate": 6.112604669781572e-06,
"loss": 0.5106,
"step": 179
},
{
"epoch": 1.4665757162346522,
"grad_norm": 0.70634706188791,
"learning_rate": 6.066007139749351e-06,
"loss": 0.5053,
"step": 180
},
{
"epoch": 1.4747612551159617,
"grad_norm": 0.6840751935196304,
"learning_rate": 6.019312410053286e-06,
"loss": 0.5361,
"step": 181
},
{
"epoch": 1.4829467939972716,
"grad_norm": 0.7055601714057114,
"learning_rate": 5.972524738368452e-06,
"loss": 0.5342,
"step": 182
},
{
"epoch": 1.491132332878581,
"grad_norm": 0.6549263427404644,
"learning_rate": 5.925648390844476e-06,
"loss": 0.524,
"step": 183
},
{
"epoch": 1.499317871759891,
"grad_norm": 0.7016637634242648,
"learning_rate": 5.878687641716539e-06,
"loss": 0.5413,
"step": 184
},
{
"epoch": 1.5075034106412004,
"grad_norm": 0.6615116373276964,
"learning_rate": 5.831646772915651e-06,
"loss": 0.5294,
"step": 185
},
{
"epoch": 1.5156889495225103,
"grad_norm": 0.7070316346639182,
"learning_rate": 5.7845300736782205e-06,
"loss": 0.5594,
"step": 186
},
{
"epoch": 1.5238744884038198,
"grad_norm": 0.7195577910961622,
"learning_rate": 5.7373418401549565e-06,
"loss": 0.5132,
"step": 187
},
{
"epoch": 1.5320600272851297,
"grad_norm": 0.6883209321690876,
"learning_rate": 5.690086375019135e-06,
"loss": 0.5635,
"step": 188
},
{
"epoch": 1.5402455661664392,
"grad_norm": 0.6985266479941304,
"learning_rate": 5.642767987074288e-06,
"loss": 0.5112,
"step": 189
},
{
"epoch": 1.548431105047749,
"grad_norm": 0.674690351672937,
"learning_rate": 5.595390990861311e-06,
"loss": 0.5269,
"step": 190
},
{
"epoch": 1.5566166439290585,
"grad_norm": 0.6818863454446653,
"learning_rate": 5.547959706265068e-06,
"loss": 0.5097,
"step": 191
},
{
"epoch": 1.5648021828103684,
"grad_norm": 0.6629891853139933,
"learning_rate": 5.500478458120493e-06,
"loss": 0.5223,
"step": 192
},
{
"epoch": 1.5729877216916779,
"grad_norm": 0.6356895042570937,
"learning_rate": 5.45295157581825e-06,
"loss": 0.4993,
"step": 193
},
{
"epoch": 1.5811732605729878,
"grad_norm": 0.6628390830246884,
"learning_rate": 5.405383392909973e-06,
"loss": 0.5341,
"step": 194
},
{
"epoch": 1.5893587994542973,
"grad_norm": 0.6864305683806672,
"learning_rate": 5.357778246713131e-06,
"loss": 0.5005,
"step": 195
},
{
"epoch": 1.5975443383356072,
"grad_norm": 0.7040608166410719,
"learning_rate": 5.310140477915544e-06,
"loss": 0.5314,
"step": 196
},
{
"epoch": 1.6057298772169166,
"grad_norm": 0.6820604818315129,
"learning_rate": 5.262474430179597e-06,
"loss": 0.5104,
"step": 197
},
{
"epoch": 1.6139154160982265,
"grad_norm": 0.7090671749176974,
"learning_rate": 5.2147844497461745e-06,
"loss": 0.5229,
"step": 198
},
{
"epoch": 1.622100954979536,
"grad_norm": 0.7515147237804626,
"learning_rate": 5.1670748850383734e-06,
"loss": 0.531,
"step": 199
},
{
"epoch": 1.630286493860846,
"grad_norm": 0.6893223377834798,
"learning_rate": 5.1193500862650045e-06,
"loss": 0.5304,
"step": 200
},
{
"epoch": 1.6384720327421554,
"grad_norm": 0.7125759934041315,
"learning_rate": 5.071614405023938e-06,
"loss": 0.4967,
"step": 201
},
{
"epoch": 1.6466575716234653,
"grad_norm": 0.6732968194331714,
"learning_rate": 5.023872193905316e-06,
"loss": 0.5213,
"step": 202
},
{
"epoch": 1.654843110504775,
"grad_norm": 0.6741087890783836,
"learning_rate": 4.976127806094685e-06,
"loss": 0.5002,
"step": 203
},
{
"epoch": 1.6630286493860846,
"grad_norm": 0.6668306133525173,
"learning_rate": 4.928385594976063e-06,
"loss": 0.4974,
"step": 204
},
{
"epoch": 1.6712141882673943,
"grad_norm": 0.6678265510054164,
"learning_rate": 4.880649913734996e-06,
"loss": 0.5409,
"step": 205
},
{
"epoch": 1.679399727148704,
"grad_norm": 0.7139916457668897,
"learning_rate": 4.832925114961629e-06,
"loss": 0.5423,
"step": 206
},
{
"epoch": 1.6875852660300137,
"grad_norm": 0.6452652740953143,
"learning_rate": 4.785215550253826e-06,
"loss": 0.4958,
"step": 207
},
{
"epoch": 1.6957708049113234,
"grad_norm": 0.6573148425831011,
"learning_rate": 4.737525569820405e-06,
"loss": 0.5131,
"step": 208
},
{
"epoch": 1.703956343792633,
"grad_norm": 0.6505041626036248,
"learning_rate": 4.689859522084457e-06,
"loss": 0.5177,
"step": 209
},
{
"epoch": 1.7121418826739427,
"grad_norm": 0.6837935893705414,
"learning_rate": 4.64222175328687e-06,
"loss": 0.5103,
"step": 210
},
{
"epoch": 1.7203274215552524,
"grad_norm": 0.7126882310799999,
"learning_rate": 4.594616607090028e-06,
"loss": 0.5332,
"step": 211
},
{
"epoch": 1.728512960436562,
"grad_norm": 0.7721004643182724,
"learning_rate": 4.547048424181751e-06,
"loss": 0.5015,
"step": 212
},
{
"epoch": 1.7366984993178718,
"grad_norm": 0.6678185442268906,
"learning_rate": 4.499521541879508e-06,
"loss": 0.5343,
"step": 213
},
{
"epoch": 1.7448840381991815,
"grad_norm": 0.6752033479335326,
"learning_rate": 4.452040293734934e-06,
"loss": 0.5206,
"step": 214
},
{
"epoch": 1.7530695770804912,
"grad_norm": 0.9626993188200799,
"learning_rate": 4.40460900913869e-06,
"loss": 0.5419,
"step": 215
},
{
"epoch": 1.7612551159618008,
"grad_norm": 0.6806062145986467,
"learning_rate": 4.357232012925714e-06,
"loss": 0.5214,
"step": 216
},
{
"epoch": 1.7694406548431105,
"grad_norm": 0.6837895407788251,
"learning_rate": 4.309913624980866e-06,
"loss": 0.5125,
"step": 217
},
{
"epoch": 1.7776261937244202,
"grad_norm": 0.6886701406202698,
"learning_rate": 4.262658159845046e-06,
"loss": 0.5562,
"step": 218
},
{
"epoch": 1.78581173260573,
"grad_norm": 0.6605928299509395,
"learning_rate": 4.2154699263217794e-06,
"loss": 0.5372,
"step": 219
},
{
"epoch": 1.7939972714870396,
"grad_norm": 1.0325353508365365,
"learning_rate": 4.1683532270843505e-06,
"loss": 0.5242,
"step": 220
},
{
"epoch": 1.8021828103683493,
"grad_norm": 1.2024682114815595,
"learning_rate": 4.121312358283464e-06,
"loss": 0.5593,
"step": 221
},
{
"epoch": 1.810368349249659,
"grad_norm": 0.9054405970578053,
"learning_rate": 4.074351609155527e-06,
"loss": 0.5261,
"step": 222
},
{
"epoch": 1.8185538881309686,
"grad_norm": 0.6758636455040393,
"learning_rate": 4.0274752616315485e-06,
"loss": 0.5112,
"step": 223
},
{
"epoch": 1.8267394270122783,
"grad_norm": 0.6825912498379267,
"learning_rate": 3.980687589946715e-06,
"loss": 0.5445,
"step": 224
},
{
"epoch": 1.834924965893588,
"grad_norm": 0.6602675170538472,
"learning_rate": 3.9339928602506505e-06,
"loss": 0.5305,
"step": 225
},
{
"epoch": 1.8431105047748977,
"grad_norm": 0.6312647757728843,
"learning_rate": 3.887395330218429e-06,
"loss": 0.4989,
"step": 226
},
{
"epoch": 1.8512960436562074,
"grad_norm": 0.679901929082235,
"learning_rate": 3.840899248662358e-06,
"loss": 0.5445,
"step": 227
},
{
"epoch": 1.859481582537517,
"grad_norm": 0.6682843496384612,
"learning_rate": 3.7945088551445698e-06,
"loss": 0.5413,
"step": 228
},
{
"epoch": 1.8676671214188267,
"grad_norm": 0.6492016487295222,
"learning_rate": 3.748228379590438e-06,
"loss": 0.528,
"step": 229
},
{
"epoch": 1.8758526603001364,
"grad_norm": 0.6684595059784664,
"learning_rate": 3.7020620419029095e-06,
"loss": 0.5079,
"step": 230
},
{
"epoch": 1.884038199181446,
"grad_norm": 0.6925041008811655,
"learning_rate": 3.656014051577713e-06,
"loss": 0.4863,
"step": 231
},
{
"epoch": 1.8922237380627558,
"grad_norm": 0.6934722383156499,
"learning_rate": 3.610088607319544e-06,
"loss": 0.5311,
"step": 232
},
{
"epoch": 1.9004092769440655,
"grad_norm": 0.6700713862638494,
"learning_rate": 3.5642898966592145e-06,
"loss": 0.5267,
"step": 233
},
{
"epoch": 1.9085948158253752,
"grad_norm": 0.6675855588895423,
"learning_rate": 3.518622095571831e-06,
"loss": 0.5157,
"step": 234
},
{
"epoch": 1.9167803547066848,
"grad_norm": 0.7287813948503299,
"learning_rate": 3.4730893680960267e-06,
"loss": 0.5167,
"step": 235
},
{
"epoch": 1.9249658935879945,
"grad_norm": 0.6983347879001167,
"learning_rate": 3.4276958659542838e-06,
"loss": 0.5032,
"step": 236
},
{
"epoch": 1.9331514324693042,
"grad_norm": 0.6875622079627788,
"learning_rate": 3.382445728174365e-06,
"loss": 0.5354,
"step": 237
},
{
"epoch": 1.941336971350614,
"grad_norm": 0.7213008732695624,
"learning_rate": 3.3373430807119212e-06,
"loss": 0.5246,
"step": 238
},
{
"epoch": 1.9495225102319236,
"grad_norm": 0.707171568997416,
"learning_rate": 3.292392036074277e-06,
"loss": 0.5572,
"step": 239
},
{
"epoch": 1.9577080491132333,
"grad_norm": 0.6831140788449497,
"learning_rate": 3.2475966929454505e-06,
"loss": 0.525,
"step": 240
},
{
"epoch": 1.965893587994543,
"grad_norm": 0.6709288897249476,
"learning_rate": 3.202961135812437e-06,
"loss": 0.5047,
"step": 241
},
{
"epoch": 1.9740791268758526,
"grad_norm": 0.630389852839246,
"learning_rate": 3.1584894345927663e-06,
"loss": 0.4997,
"step": 242
},
{
"epoch": 1.9822646657571623,
"grad_norm": 0.6597569020078831,
"learning_rate": 3.114185644263415e-06,
"loss": 0.5359,
"step": 243
},
{
"epoch": 1.990450204638472,
"grad_norm": 0.7340456758824426,
"learning_rate": 3.0700538044910684e-06,
"loss": 0.5239,
"step": 244
},
{
"epoch": 1.9986357435197817,
"grad_norm": 0.6785372793547849,
"learning_rate": 3.0260979392637753e-06,
"loss": 0.5093,
"step": 245
},
{
"epoch": 2.0,
"grad_norm": 0.6785372793547849,
"learning_rate": 2.9823220565240396e-06,
"loss": 0.4999,
"step": 246
},
{
"epoch": 2.00818553888131,
"grad_norm": 1.8279474055803957,
"learning_rate": 2.9387301478033694e-06,
"loss": 0.4133,
"step": 247
},
{
"epoch": 2.0163710777626194,
"grad_norm": 0.7778576282194246,
"learning_rate": 2.8953261878583263e-06,
"loss": 0.4113,
"step": 248
},
{
"epoch": 2.0245566166439293,
"grad_norm": 0.7947084402075207,
"learning_rate": 2.852114134308104e-06,
"loss": 0.4277,
"step": 249
},
{
"epoch": 2.0327421555252387,
"grad_norm": 0.8407711968632838,
"learning_rate": 2.8090979272736663e-06,
"loss": 0.4181,
"step": 250
},
{
"epoch": 2.0409276944065486,
"grad_norm": 0.8070071079726969,
"learning_rate": 2.766281489018482e-06,
"loss": 0.414,
"step": 251
},
{
"epoch": 2.049113233287858,
"grad_norm": 0.7504845165785325,
"learning_rate": 2.7236687235908953e-06,
"loss": 0.4264,
"step": 252
},
{
"epoch": 2.057298772169168,
"grad_norm": 0.7484637498779095,
"learning_rate": 2.681263516468139e-06,
"loss": 0.424,
"step": 253
},
{
"epoch": 2.0654843110504775,
"grad_norm": 0.7672301449846941,
"learning_rate": 2.6390697342020665e-06,
"loss": 0.418,
"step": 254
},
{
"epoch": 2.0736698499317874,
"grad_norm": 0.8252088950713669,
"learning_rate": 2.5970912240665815e-06,
"loss": 0.4351,
"step": 255
},
{
"epoch": 2.081855388813097,
"grad_norm": 0.9368985866664803,
"learning_rate": 2.5553318137068473e-06,
"loss": 0.4047,
"step": 256
},
{
"epoch": 2.0900409276944067,
"grad_norm": 0.892666476951023,
"learning_rate": 2.5137953107902814e-06,
"loss": 0.4103,
"step": 257
},
{
"epoch": 2.098226466575716,
"grad_norm": 0.81654627837115,
"learning_rate": 2.472485502659358e-06,
"loss": 0.4098,
"step": 258
},
{
"epoch": 2.106412005457026,
"grad_norm": 0.7640263710507721,
"learning_rate": 2.4314061559862836e-06,
"loss": 0.3979,
"step": 259
},
{
"epoch": 2.1145975443383356,
"grad_norm": 0.7707988225465455,
"learning_rate": 2.3905610164295394e-06,
"loss": 0.4001,
"step": 260
},
{
"epoch": 2.1227830832196455,
"grad_norm": 0.7384332255225988,
"learning_rate": 2.3499538082923607e-06,
"loss": 0.424,
"step": 261
},
{
"epoch": 2.130968622100955,
"grad_norm": 0.7717039023517804,
"learning_rate": 2.309588234183137e-06,
"loss": 0.4116,
"step": 262
},
{
"epoch": 2.139154160982265,
"grad_norm": 0.774162944001744,
"learning_rate": 2.2694679746778116e-06,
"loss": 0.3698,
"step": 263
},
{
"epoch": 2.1473396998635743,
"grad_norm": 0.7788823100928985,
"learning_rate": 2.22959668798428e-06,
"loss": 0.3919,
"step": 264
},
{
"epoch": 2.155525238744884,
"grad_norm": 0.8632537243107956,
"learning_rate": 2.1899780096088375e-06,
"loss": 0.407,
"step": 265
},
{
"epoch": 2.1637107776261937,
"grad_norm": 0.7677472904066729,
"learning_rate": 2.1506155520246795e-06,
"loss": 0.4097,
"step": 266
},
{
"epoch": 2.1718963165075036,
"grad_norm": 0.8292963201693136,
"learning_rate": 2.1115129043425188e-06,
"loss": 0.4161,
"step": 267
},
{
"epoch": 2.180081855388813,
"grad_norm": 0.7630554646262787,
"learning_rate": 2.072673631983323e-06,
"loss": 0.3763,
"step": 268
},
{
"epoch": 2.188267394270123,
"grad_norm": 0.7431688030641092,
"learning_rate": 2.0341012763532243e-06,
"loss": 0.379,
"step": 269
},
{
"epoch": 2.1964529331514324,
"grad_norm": 0.8283857532938996,
"learning_rate": 1.995799354520598e-06,
"loss": 0.3986,
"step": 270
},
{
"epoch": 2.2046384720327423,
"grad_norm": 0.7664654913892277,
"learning_rate": 1.9577713588953797e-06,
"loss": 0.3874,
"step": 271
},
{
"epoch": 2.212824010914052,
"grad_norm": 0.7821218387875882,
"learning_rate": 1.9200207569106216e-06,
"loss": 0.3946,
"step": 272
},
{
"epoch": 2.2210095497953617,
"grad_norm": 0.8359718127109106,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.4007,
"step": 273
},
{
"epoch": 2.229195088676671,
"grad_norm": 0.7827350042496607,
"learning_rate": 1.8453654768156138e-06,
"loss": 0.4269,
"step": 274
},
{
"epoch": 2.237380627557981,
"grad_norm": 0.841679648376414,
"learning_rate": 1.8084676058531376e-06,
"loss": 0.3932,
"step": 275
},
{
"epoch": 2.2455661664392905,
"grad_norm": 0.839943238676734,
"learning_rate": 1.771860742205988e-06,
"loss": 0.4322,
"step": 276
},
{
"epoch": 2.2537517053206004,
"grad_norm": 0.829532308903955,
"learning_rate": 1.7355482237268983e-06,
"loss": 0.436,
"step": 277
},
{
"epoch": 2.26193724420191,
"grad_norm": 0.8372210579762943,
"learning_rate": 1.6995333614298908e-06,
"loss": 0.4093,
"step": 278
},
{
"epoch": 2.27012278308322,
"grad_norm": 0.8081527770715485,
"learning_rate": 1.6638194391883822e-06,
"loss": 0.3858,
"step": 279
},
{
"epoch": 2.2783083219645293,
"grad_norm": 0.769954474277968,
"learning_rate": 1.6284097134357535e-06,
"loss": 0.3954,
"step": 280
},
{
"epoch": 2.286493860845839,
"grad_norm": 0.8260850385707194,
"learning_rate": 1.5933074128684333e-06,
"loss": 0.4086,
"step": 281
},
{
"epoch": 2.2946793997271486,
"grad_norm": 0.7953598123135504,
"learning_rate": 1.5585157381514875e-06,
"loss": 0.4159,
"step": 282
},
{
"epoch": 2.3028649386084585,
"grad_norm": 0.786859054444193,
"learning_rate": 1.5240378616267887e-06,
"loss": 0.4176,
"step": 283
},
{
"epoch": 2.311050477489768,
"grad_norm": 0.7969101629502529,
"learning_rate": 1.4898769270237611e-06,
"loss": 0.389,
"step": 284
},
{
"epoch": 2.319236016371078,
"grad_norm": 0.833189518702729,
"learning_rate": 1.4560360491727233e-06,
"loss": 0.3908,
"step": 285
},
{
"epoch": 2.3274215552523874,
"grad_norm": 0.7732573237876273,
"learning_rate": 1.4225183137208775e-06,
"loss": 0.4133,
"step": 286
},
{
"epoch": 2.3356070941336973,
"grad_norm": 0.7473413525545317,
"learning_rate": 1.389326776850966e-06,
"loss": 0.4233,
"step": 287
},
{
"epoch": 2.3437926330150067,
"grad_norm": 0.7491139940557698,
"learning_rate": 1.3564644650025894e-06,
"loss": 0.4123,
"step": 288
},
{
"epoch": 2.3519781718963166,
"grad_norm": 0.7874918542020864,
"learning_rate": 1.323934374596268e-06,
"loss": 0.3924,
"step": 289
},
{
"epoch": 2.360163710777626,
"grad_norm": 0.7090630129353084,
"learning_rate": 1.2917394717602123e-06,
"loss": 0.3871,
"step": 290
},
{
"epoch": 2.368349249658936,
"grad_norm": 0.7464575367696425,
"learning_rate": 1.2598826920598773e-06,
"loss": 0.3864,
"step": 291
},
{
"epoch": 2.3765347885402455,
"grad_norm": 0.7631727170097402,
"learning_rate": 1.2283669402302878e-06,
"loss": 0.4317,
"step": 292
},
{
"epoch": 2.3847203274215554,
"grad_norm": 0.766457447194422,
"learning_rate": 1.197195089911191e-06,
"loss": 0.3923,
"step": 293
},
{
"epoch": 2.392905866302865,
"grad_norm": 0.7813349442160811,
"learning_rate": 1.166369983385024e-06,
"loss": 0.3893,
"step": 294
},
{
"epoch": 2.4010914051841747,
"grad_norm": 0.7760077699058369,
"learning_rate": 1.1358944313177566e-06,
"loss": 0.419,
"step": 295
},
{
"epoch": 2.409276944065484,
"grad_norm": 0.8611771806504117,
"learning_rate": 1.1057712125026116e-06,
"loss": 0.4134,
"step": 296
},
{
"epoch": 2.417462482946794,
"grad_norm": 0.8715690874271717,
"learning_rate": 1.0760030736066952e-06,
"loss": 0.4299,
"step": 297
},
{
"epoch": 2.4256480218281036,
"grad_norm": 0.738527625183462,
"learning_rate": 1.0465927289205452e-06,
"loss": 0.3721,
"step": 298
},
{
"epoch": 2.4338335607094135,
"grad_norm": 0.7364008623286723,
"learning_rate": 1.0175428601106441e-06,
"loss": 0.4164,
"step": 299
},
{
"epoch": 2.442019099590723,
"grad_norm": 0.7606943953483646,
"learning_rate": 9.888561159748995e-07,
"loss": 0.3968,
"step": 300
},
{
"epoch": 2.450204638472033,
"grad_norm": 0.7936868365174442,
"learning_rate": 9.605351122011308e-07,
"loss": 0.417,
"step": 301
},
{
"epoch": 2.4583901773533423,
"grad_norm": 0.9111596760359036,
"learning_rate": 9.325824311285564e-07,
"loss": 0.3973,
"step": 302
},
{
"epoch": 2.466575716234652,
"grad_norm": 0.7528178925904793,
"learning_rate": 9.050006215123419e-07,
"loss": 0.4261,
"step": 303
},
{
"epoch": 2.4747612551159617,
"grad_norm": 0.7830814196247444,
"learning_rate": 8.777921982911996e-07,
"loss": 0.4053,
"step": 304
},
{
"epoch": 2.4829467939972716,
"grad_norm": 0.7602680477272743,
"learning_rate": 8.509596423580712e-07,
"loss": 0.4035,
"step": 305
},
{
"epoch": 2.491132332878581,
"grad_norm": 0.7415953605335074,
"learning_rate": 8.245054003339247e-07,
"loss": 0.3895,
"step": 306
},
{
"epoch": 2.499317871759891,
"grad_norm": 0.7570773863255101,
"learning_rate": 7.984318843446593e-07,
"loss": 0.4015,
"step": 307
},
{
"epoch": 2.5075034106412004,
"grad_norm": 0.7948263347472059,
"learning_rate": 7.727414718011706e-07,
"loss": 0.4006,
"step": 308
},
{
"epoch": 2.5156889495225103,
"grad_norm": 0.7441713828948021,
"learning_rate": 7.474365051825749e-07,
"loss": 0.4164,
"step": 309
},
{
"epoch": 2.52387448840382,
"grad_norm": 0.8318405222511415,
"learning_rate": 7.225192918226215e-07,
"loss": 0.3882,
"step": 310
},
{
"epoch": 2.5320600272851297,
"grad_norm": 0.7576816109290357,
"learning_rate": 6.979921036993042e-07,
"loss": 0.4149,
"step": 311
},
{
"epoch": 2.540245566166439,
"grad_norm": 0.7368181687339158,
"learning_rate": 6.738571772276997e-07,
"loss": 0.4117,
"step": 312
},
{
"epoch": 2.548431105047749,
"grad_norm": 0.7336446538957092,
"learning_rate": 6.501167130560515e-07,
"loss": 0.3916,
"step": 313
},
{
"epoch": 2.5566166439290585,
"grad_norm": 0.7740723418782292,
"learning_rate": 6.267728758651131e-07,
"loss": 0.411,
"step": 314
},
{
"epoch": 2.5648021828103684,
"grad_norm": 0.7461817145842243,
"learning_rate": 6.038277941707671e-07,
"loss": 0.3826,
"step": 315
},
{
"epoch": 2.572987721691678,
"grad_norm": 0.7518750830999247,
"learning_rate": 5.812835601299438e-07,
"loss": 0.4027,
"step": 316
},
{
"epoch": 2.581173260572988,
"grad_norm": 0.7838442075363712,
"learning_rate": 5.591422293498633e-07,
"loss": 0.4123,
"step": 317
},
{
"epoch": 2.5893587994542973,
"grad_norm": 0.8197901275460071,
"learning_rate": 5.374058207005945e-07,
"loss": 0.3929,
"step": 318
},
{
"epoch": 2.597544338335607,
"grad_norm": 0.756093939796975,
"learning_rate": 5.160763161309768e-07,
"loss": 0.3874,
"step": 319
},
{
"epoch": 2.6057298772169166,
"grad_norm": 0.7750985666461455,
"learning_rate": 4.951556604879049e-07,
"loss": 0.4153,
"step": 320
},
{
"epoch": 2.6139154160982265,
"grad_norm": 0.7232020878395763,
"learning_rate": 4.7464576133899043e-07,
"loss": 0.3866,
"step": 321
},
{
"epoch": 2.622100954979536,
"grad_norm": 0.7528175373532525,
"learning_rate": 4.545484887986368e-07,
"loss": 0.4131,
"step": 322
},
{
"epoch": 2.630286493860846,
"grad_norm": 0.7641457571529617,
"learning_rate": 4.348656753575092e-07,
"loss": 0.4046,
"step": 323
},
{
"epoch": 2.6384720327421554,
"grad_norm": 0.7621065360883466,
"learning_rate": 4.1559911571545544e-07,
"loss": 0.4142,
"step": 324
},
{
"epoch": 2.6466575716234653,
"grad_norm": 0.7958121777976367,
"learning_rate": 3.9675056661785563e-07,
"loss": 0.405,
"step": 325
},
{
"epoch": 2.6548431105047747,
"grad_norm": 0.7837478689185601,
"learning_rate": 3.783217466954503e-07,
"loss": 0.3924,
"step": 326
},
{
"epoch": 2.6630286493860846,
"grad_norm": 0.7818466172691447,
"learning_rate": 3.603143363076217e-07,
"loss": 0.405,
"step": 327
},
{
"epoch": 2.6712141882673945,
"grad_norm": 0.737120843251674,
"learning_rate": 3.427299773891868e-07,
"loss": 0.3855,
"step": 328
},
{
"epoch": 2.679399727148704,
"grad_norm": 0.7930563359029547,
"learning_rate": 3.255702733006766e-07,
"loss": 0.3987,
"step": 329
},
{
"epoch": 2.6875852660300135,
"grad_norm": 0.8366985596667617,
"learning_rate": 3.088367886821481e-07,
"loss": 0.3946,
"step": 330
},
{
"epoch": 2.6957708049113234,
"grad_norm": 0.8193841638700755,
"learning_rate": 2.925310493105099e-07,
"loss": 0.4186,
"step": 331
},
{
"epoch": 2.7039563437926333,
"grad_norm": 0.7544220340235186,
"learning_rate": 2.7665454196040665e-07,
"loss": 0.4052,
"step": 332
},
{
"epoch": 2.7121418826739427,
"grad_norm": 0.8023433638285234,
"learning_rate": 2.6120871426864866e-07,
"loss": 0.3807,
"step": 333
},
{
"epoch": 2.720327421555252,
"grad_norm": 0.7406196915706266,
"learning_rate": 2.4619497460222184e-07,
"loss": 0.4101,
"step": 334
},
{
"epoch": 2.728512960436562,
"grad_norm": 0.737077976937547,
"learning_rate": 2.316146919298623e-07,
"loss": 0.3873,
"step": 335
},
{
"epoch": 2.736698499317872,
"grad_norm": 0.8083843749329572,
"learning_rate": 2.1746919569723858e-07,
"loss": 0.4159,
"step": 336
},
{
"epoch": 2.7448840381991815,
"grad_norm": 0.7932339569895047,
"learning_rate": 2.037597757057297e-07,
"loss": 0.4098,
"step": 337
},
{
"epoch": 2.753069577080491,
"grad_norm": 0.8580661081839333,
"learning_rate": 1.9048768199481983e-07,
"loss": 0.3932,
"step": 338
},
{
"epoch": 2.761255115961801,
"grad_norm": 0.8216483122178869,
"learning_rate": 1.776541247281177e-07,
"loss": 0.4107,
"step": 339
},
{
"epoch": 2.7694406548431107,
"grad_norm": 0.8116256278850041,
"learning_rate": 1.6526027408301227e-07,
"loss": 0.4037,
"step": 340
},
{
"epoch": 2.77762619372442,
"grad_norm": 0.8129785704080104,
"learning_rate": 1.5330726014397668e-07,
"loss": 0.4109,
"step": 341
},
{
"epoch": 2.7858117326057297,
"grad_norm": 0.756821439289195,
"learning_rate": 1.417961727995254e-07,
"loss": 0.411,
"step": 342
},
{
"epoch": 2.7939972714870396,
"grad_norm": 0.7776940434532348,
"learning_rate": 1.307280616428336e-07,
"loss": 0.4278,
"step": 343
},
{
"epoch": 2.8021828103683495,
"grad_norm": 0.7541646575501004,
"learning_rate": 1.2010393587603975e-07,
"loss": 0.4309,
"step": 344
},
{
"epoch": 2.810368349249659,
"grad_norm": 0.7615569057804531,
"learning_rate": 1.0992476421822052e-07,
"loss": 0.4018,
"step": 345
},
{
"epoch": 2.8185538881309684,
"grad_norm": 0.7326601732112479,
"learning_rate": 1.0019147481706626e-07,
"loss": 0.3798,
"step": 346
},
{
"epoch": 2.8267394270122783,
"grad_norm": 0.7558224410956776,
"learning_rate": 9.090495516424713e-08,
"loss": 0.3934,
"step": 347
},
{
"epoch": 2.8349249658935882,
"grad_norm": 0.7586566867615607,
"learning_rate": 8.206605201449447e-08,
"loss": 0.4083,
"step": 348
},
{
"epoch": 2.8431105047748977,
"grad_norm": 0.7756404145344101,
"learning_rate": 7.367557130838921e-08,
"loss": 0.4198,
"step": 349
},
{
"epoch": 2.851296043656207,
"grad_norm": 0.7619932836793645,
"learning_rate": 6.573427809888067e-08,
"loss": 0.4052,
"step": 350
},
{
"epoch": 2.859481582537517,
"grad_norm": 0.7864285751411372,
"learning_rate": 5.824289648152126e-08,
"loss": 0.4049,
"step": 351
},
{
"epoch": 2.867667121418827,
"grad_norm": 0.7724732501336614,
"learning_rate": 5.120210952844873e-08,
"loss": 0.4082,
"step": 352
},
{
"epoch": 2.8758526603001364,
"grad_norm": 0.7448742382267542,
"learning_rate": 4.461255922609986e-08,
"loss": 0.4097,
"step": 353
},
{
"epoch": 2.884038199181446,
"grad_norm": 0.7752438252600893,
"learning_rate": 3.8474846416672874e-08,
"loss": 0.399,
"step": 354
},
{
"epoch": 2.892223738062756,
"grad_norm": 0.8642432702205011,
"learning_rate": 3.278953074334512e-08,
"loss": 0.3937,
"step": 355
},
{
"epoch": 2.9004092769440657,
"grad_norm": 0.7501677664181151,
"learning_rate": 2.75571305992417e-08,
"loss": 0.3895,
"step": 356
},
{
"epoch": 2.908594815825375,
"grad_norm": 0.7336645310315806,
"learning_rate": 2.2778123080167136e-08,
"loss": 0.4154,
"step": 357
},
{
"epoch": 2.9167803547066846,
"grad_norm": 0.8016612426903582,
"learning_rate": 1.845294394110686e-08,
"loss": 0.3989,
"step": 358
},
{
"epoch": 2.9249658935879945,
"grad_norm": 0.7453209695510444,
"learning_rate": 1.4581987556490095e-08,
"loss": 0.4218,
"step": 359
},
{
"epoch": 2.9331514324693044,
"grad_norm": 0.7376596618566437,
"learning_rate": 1.1165606884234182e-08,
"loss": 0.4093,
"step": 360
},
{
"epoch": 2.941336971350614,
"grad_norm": 0.7581298522735148,
"learning_rate": 8.204113433559202e-09,
"loss": 0.3715,
"step": 361
},
{
"epoch": 2.9495225102319234,
"grad_norm": 0.7252182853236371,
"learning_rate": 5.6977772365857105e-09,
"loss": 0.3921,
"step": 362
},
{
"epoch": 2.9577080491132333,
"grad_norm": 0.7594004110808722,
"learning_rate": 3.6468268237105364e-09,
"loss": 0.4069,
"step": 363
},
{
"epoch": 2.965893587994543,
"grad_norm": 0.7885350379055207,
"learning_rate": 2.0514492027728928e-09,
"loss": 0.4078,
"step": 364
},
{
"epoch": 2.9740791268758526,
"grad_norm": 0.762337453867713,
"learning_rate": 9.117898419991333e-10,
"loss": 0.3989,
"step": 365
},
{
"epoch": 2.982264665757162,
"grad_norm": 0.7984650139098143,
"learning_rate": 2.2795265674113721e-10,
"loss": 0.3826,
"step": 366
},
{
"epoch": 2.982264665757162,
"step": 366,
"total_flos": 5.395725452134318e+17,
"train_loss": 0.5496462623441154,
"train_runtime": 28753.9424,
"train_samples_per_second": 0.612,
"train_steps_per_second": 0.013
}
],
"logging_steps": 1,
"max_steps": 366,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 5.395725452134318e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}