TracyTank's picture
End of training
5e7ae5e verified
{
"best_metric": 0.9023734927177429,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.030716068343252065,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00015358034171626033,
"grad_norm": 0.8446609973907471,
"learning_rate": 1e-05,
"loss": 1.1502,
"step": 1
},
{
"epoch": 0.00015358034171626033,
"eval_loss": 1.2722595930099487,
"eval_runtime": 309.9834,
"eval_samples_per_second": 35.379,
"eval_steps_per_second": 8.846,
"step": 1
},
{
"epoch": 0.00030716068343252065,
"grad_norm": 0.8968664407730103,
"learning_rate": 2e-05,
"loss": 1.1235,
"step": 2
},
{
"epoch": 0.000460741025148781,
"grad_norm": 0.9639127850532532,
"learning_rate": 3e-05,
"loss": 1.1521,
"step": 3
},
{
"epoch": 0.0006143213668650413,
"grad_norm": 1.0027085542678833,
"learning_rate": 4e-05,
"loss": 1.1328,
"step": 4
},
{
"epoch": 0.0007679017085813016,
"grad_norm": 0.5970536470413208,
"learning_rate": 5e-05,
"loss": 1.0693,
"step": 5
},
{
"epoch": 0.000921482050297562,
"grad_norm": 0.4931555986404419,
"learning_rate": 6e-05,
"loss": 1.0419,
"step": 6
},
{
"epoch": 0.0010750623920138223,
"grad_norm": 0.4543219804763794,
"learning_rate": 7e-05,
"loss": 1.1038,
"step": 7
},
{
"epoch": 0.0012286427337300826,
"grad_norm": 0.456942081451416,
"learning_rate": 8e-05,
"loss": 1.0496,
"step": 8
},
{
"epoch": 0.0013822230754463429,
"grad_norm": 0.4754583239555359,
"learning_rate": 9e-05,
"loss": 1.0233,
"step": 9
},
{
"epoch": 0.0015358034171626032,
"grad_norm": 0.47682157158851624,
"learning_rate": 0.0001,
"loss": 1.0498,
"step": 10
},
{
"epoch": 0.0016893837588788634,
"grad_norm": 0.5109769105911255,
"learning_rate": 9.999316524962345e-05,
"loss": 0.9901,
"step": 11
},
{
"epoch": 0.001842964100595124,
"grad_norm": 0.4389522075653076,
"learning_rate": 9.997266286704631e-05,
"loss": 0.9863,
"step": 12
},
{
"epoch": 0.001996544442311384,
"grad_norm": 0.40280580520629883,
"learning_rate": 9.993849845741524e-05,
"loss": 0.9208,
"step": 13
},
{
"epoch": 0.0021501247840276447,
"grad_norm": 0.42473721504211426,
"learning_rate": 9.989068136093873e-05,
"loss": 1.0187,
"step": 14
},
{
"epoch": 0.002303705125743905,
"grad_norm": 0.4241027534008026,
"learning_rate": 9.98292246503335e-05,
"loss": 1.0257,
"step": 15
},
{
"epoch": 0.0024572854674601652,
"grad_norm": 0.3873891234397888,
"learning_rate": 9.975414512725057e-05,
"loss": 0.9442,
"step": 16
},
{
"epoch": 0.0026108658091764255,
"grad_norm": 0.3869728147983551,
"learning_rate": 9.966546331768191e-05,
"loss": 0.9011,
"step": 17
},
{
"epoch": 0.0027644461508926858,
"grad_norm": 0.34611836075782776,
"learning_rate": 9.956320346634876e-05,
"loss": 0.9138,
"step": 18
},
{
"epoch": 0.002918026492608946,
"grad_norm": 0.35446110367774963,
"learning_rate": 9.944739353007344e-05,
"loss": 0.8915,
"step": 19
},
{
"epoch": 0.0030716068343252063,
"grad_norm": 0.3475477695465088,
"learning_rate": 9.931806517013612e-05,
"loss": 0.927,
"step": 20
},
{
"epoch": 0.0032251871760414666,
"grad_norm": 0.3592182397842407,
"learning_rate": 9.917525374361912e-05,
"loss": 0.9331,
"step": 21
},
{
"epoch": 0.003378767517757727,
"grad_norm": 0.42147764563560486,
"learning_rate": 9.901899829374047e-05,
"loss": 1.0221,
"step": 22
},
{
"epoch": 0.003532347859473987,
"grad_norm": 0.39797714352607727,
"learning_rate": 9.884934153917997e-05,
"loss": 1.0908,
"step": 23
},
{
"epoch": 0.003685928201190248,
"grad_norm": 0.3612615466117859,
"learning_rate": 9.86663298624003e-05,
"loss": 0.9301,
"step": 24
},
{
"epoch": 0.003839508542906508,
"grad_norm": 0.3691578507423401,
"learning_rate": 9.847001329696653e-05,
"loss": 0.8776,
"step": 25
},
{
"epoch": 0.003993088884622768,
"grad_norm": 0.3675132691860199,
"learning_rate": 9.826044551386744e-05,
"loss": 0.9989,
"step": 26
},
{
"epoch": 0.004146669226339029,
"grad_norm": 0.367730975151062,
"learning_rate": 9.803768380684242e-05,
"loss": 1.001,
"step": 27
},
{
"epoch": 0.004300249568055289,
"grad_norm": 0.37927061319351196,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9589,
"step": 28
},
{
"epoch": 0.004453829909771549,
"grad_norm": 0.38185304403305054,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9404,
"step": 29
},
{
"epoch": 0.00460741025148781,
"grad_norm": 0.3774837851524353,
"learning_rate": 9.729086208503174e-05,
"loss": 0.9638,
"step": 30
},
{
"epoch": 0.00476099059320407,
"grad_norm": 0.3884425759315491,
"learning_rate": 9.701596950580806e-05,
"loss": 0.8727,
"step": 31
},
{
"epoch": 0.0049145709349203304,
"grad_norm": 0.37998726963996887,
"learning_rate": 9.672822322997305e-05,
"loss": 1.0045,
"step": 32
},
{
"epoch": 0.00506815127663659,
"grad_norm": 0.405863881111145,
"learning_rate": 9.642770192448536e-05,
"loss": 1.0045,
"step": 33
},
{
"epoch": 0.005221731618352851,
"grad_norm": 0.39692771434783936,
"learning_rate": 9.611448774886924e-05,
"loss": 0.8966,
"step": 34
},
{
"epoch": 0.005375311960069111,
"grad_norm": 0.3983049988746643,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9499,
"step": 35
},
{
"epoch": 0.0055288923017853715,
"grad_norm": 0.4230270981788635,
"learning_rate": 9.545032675245813e-05,
"loss": 0.9401,
"step": 36
},
{
"epoch": 0.005682472643501631,
"grad_norm": 0.39218056201934814,
"learning_rate": 9.509956150664796e-05,
"loss": 0.8491,
"step": 37
},
{
"epoch": 0.005836052985217892,
"grad_norm": 0.4110160768032074,
"learning_rate": 9.473646649103818e-05,
"loss": 0.874,
"step": 38
},
{
"epoch": 0.005989633326934153,
"grad_norm": 0.44515305757522583,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9441,
"step": 39
},
{
"epoch": 0.006143213668650413,
"grad_norm": 0.43324553966522217,
"learning_rate": 9.397368756032445e-05,
"loss": 0.8713,
"step": 40
},
{
"epoch": 0.006296794010366673,
"grad_norm": 0.4449658691883087,
"learning_rate": 9.357421218136386e-05,
"loss": 0.8975,
"step": 41
},
{
"epoch": 0.006450374352082933,
"grad_norm": 0.440376877784729,
"learning_rate": 9.316282404787871e-05,
"loss": 0.8771,
"step": 42
},
{
"epoch": 0.006603954693799194,
"grad_norm": 0.4519074559211731,
"learning_rate": 9.273963562927695e-05,
"loss": 0.9543,
"step": 43
},
{
"epoch": 0.006757535035515454,
"grad_norm": 0.4827348291873932,
"learning_rate": 9.230476262104677e-05,
"loss": 0.9438,
"step": 44
},
{
"epoch": 0.006911115377231714,
"grad_norm": 0.46490582823753357,
"learning_rate": 9.185832391312644e-05,
"loss": 0.8824,
"step": 45
},
{
"epoch": 0.007064695718947974,
"grad_norm": 0.5066066384315491,
"learning_rate": 9.140044155740101e-05,
"loss": 0.8779,
"step": 46
},
{
"epoch": 0.007218276060664235,
"grad_norm": 0.5185495615005493,
"learning_rate": 9.093124073433463e-05,
"loss": 0.8551,
"step": 47
},
{
"epoch": 0.007371856402380496,
"grad_norm": 0.5769181847572327,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9174,
"step": 48
},
{
"epoch": 0.0075254367440967555,
"grad_norm": 0.5959956645965576,
"learning_rate": 8.995939984474624e-05,
"loss": 1.0132,
"step": 49
},
{
"epoch": 0.007679017085813016,
"grad_norm": 0.919772207736969,
"learning_rate": 8.945702546981969e-05,
"loss": 1.1408,
"step": 50
},
{
"epoch": 0.007679017085813016,
"eval_loss": 0.9860600233078003,
"eval_runtime": 311.1352,
"eval_samples_per_second": 35.248,
"eval_steps_per_second": 8.813,
"step": 50
},
{
"epoch": 0.007832597427529276,
"grad_norm": 0.7557655572891235,
"learning_rate": 8.894386393810563e-05,
"loss": 1.0282,
"step": 51
},
{
"epoch": 0.007986177769245536,
"grad_norm": 0.5945308208465576,
"learning_rate": 8.842005554284296e-05,
"loss": 1.1201,
"step": 52
},
{
"epoch": 0.008139758110961797,
"grad_norm": 0.40070173144340515,
"learning_rate": 8.788574348801675e-05,
"loss": 1.0474,
"step": 53
},
{
"epoch": 0.008293338452678057,
"grad_norm": 0.33662405610084534,
"learning_rate": 8.73410738492077e-05,
"loss": 0.9615,
"step": 54
},
{
"epoch": 0.008446918794394317,
"grad_norm": 0.3119973838329315,
"learning_rate": 8.678619553365659e-05,
"loss": 0.969,
"step": 55
},
{
"epoch": 0.008600499136110579,
"grad_norm": 0.30854901671409607,
"learning_rate": 8.622126023955446e-05,
"loss": 0.942,
"step": 56
},
{
"epoch": 0.008754079477826839,
"grad_norm": 0.2970249652862549,
"learning_rate": 8.564642241456986e-05,
"loss": 0.9672,
"step": 57
},
{
"epoch": 0.008907659819543098,
"grad_norm": 0.3055781424045563,
"learning_rate": 8.506183921362443e-05,
"loss": 0.9662,
"step": 58
},
{
"epoch": 0.009061240161259358,
"grad_norm": 0.2929782569408417,
"learning_rate": 8.44676704559283e-05,
"loss": 0.934,
"step": 59
},
{
"epoch": 0.00921482050297562,
"grad_norm": 0.30172696709632874,
"learning_rate": 8.386407858128706e-05,
"loss": 0.9256,
"step": 60
},
{
"epoch": 0.00936840084469188,
"grad_norm": 0.30131611227989197,
"learning_rate": 8.32512286056924e-05,
"loss": 0.8984,
"step": 61
},
{
"epoch": 0.00952198118640814,
"grad_norm": 0.27746856212615967,
"learning_rate": 8.262928807620843e-05,
"loss": 0.843,
"step": 62
},
{
"epoch": 0.0096755615281244,
"grad_norm": 0.2968168556690216,
"learning_rate": 8.199842702516583e-05,
"loss": 0.8744,
"step": 63
},
{
"epoch": 0.009829141869840661,
"grad_norm": 0.3145580291748047,
"learning_rate": 8.135881792367686e-05,
"loss": 0.9407,
"step": 64
},
{
"epoch": 0.00998272221155692,
"grad_norm": 0.29549792408943176,
"learning_rate": 8.07106356344834e-05,
"loss": 0.8435,
"step": 65
},
{
"epoch": 0.01013630255327318,
"grad_norm": 0.30365702509880066,
"learning_rate": 8.005405736415126e-05,
"loss": 0.9746,
"step": 66
},
{
"epoch": 0.010289882894989442,
"grad_norm": 0.29658281803131104,
"learning_rate": 7.938926261462366e-05,
"loss": 0.9426,
"step": 67
},
{
"epoch": 0.010443463236705702,
"grad_norm": 0.2878299653530121,
"learning_rate": 7.871643313414718e-05,
"loss": 0.9915,
"step": 68
},
{
"epoch": 0.010597043578421962,
"grad_norm": 0.28608471155166626,
"learning_rate": 7.803575286758364e-05,
"loss": 0.9078,
"step": 69
},
{
"epoch": 0.010750623920138222,
"grad_norm": 0.28498077392578125,
"learning_rate": 7.734740790612136e-05,
"loss": 0.8997,
"step": 70
},
{
"epoch": 0.010904204261854483,
"grad_norm": 0.3077279329299927,
"learning_rate": 7.66515864363997e-05,
"loss": 1.0122,
"step": 71
},
{
"epoch": 0.011057784603570743,
"grad_norm": 0.3035873472690582,
"learning_rate": 7.594847868906076e-05,
"loss": 0.9983,
"step": 72
},
{
"epoch": 0.011211364945287003,
"grad_norm": 0.30749794840812683,
"learning_rate": 7.52382768867422e-05,
"loss": 0.8822,
"step": 73
},
{
"epoch": 0.011364945287003263,
"grad_norm": 0.31012865900993347,
"learning_rate": 7.452117519152542e-05,
"loss": 0.9225,
"step": 74
},
{
"epoch": 0.011518525628719524,
"grad_norm": 0.3054855763912201,
"learning_rate": 7.379736965185368e-05,
"loss": 0.8481,
"step": 75
},
{
"epoch": 0.011672105970435784,
"grad_norm": 0.31472447514533997,
"learning_rate": 7.30670581489344e-05,
"loss": 0.884,
"step": 76
},
{
"epoch": 0.011825686312152044,
"grad_norm": 0.31079375743865967,
"learning_rate": 7.233044034264034e-05,
"loss": 0.9154,
"step": 77
},
{
"epoch": 0.011979266653868306,
"grad_norm": 0.3226238787174225,
"learning_rate": 7.158771761692464e-05,
"loss": 1.0211,
"step": 78
},
{
"epoch": 0.012132846995584565,
"grad_norm": 0.33258116245269775,
"learning_rate": 7.083909302476453e-05,
"loss": 0.9296,
"step": 79
},
{
"epoch": 0.012286427337300825,
"grad_norm": 0.3158131241798401,
"learning_rate": 7.008477123264848e-05,
"loss": 0.8614,
"step": 80
},
{
"epoch": 0.012440007679017085,
"grad_norm": 0.31899961829185486,
"learning_rate": 6.932495846462261e-05,
"loss": 0.8936,
"step": 81
},
{
"epoch": 0.012593588020733347,
"grad_norm": 0.33689790964126587,
"learning_rate": 6.855986244591104e-05,
"loss": 0.8852,
"step": 82
},
{
"epoch": 0.012747168362449606,
"grad_norm": 0.33104169368743896,
"learning_rate": 6.778969234612584e-05,
"loss": 0.8782,
"step": 83
},
{
"epoch": 0.012900748704165866,
"grad_norm": 0.3336278796195984,
"learning_rate": 6.701465872208216e-05,
"loss": 0.8553,
"step": 84
},
{
"epoch": 0.013054329045882128,
"grad_norm": 0.37692487239837646,
"learning_rate": 6.623497346023418e-05,
"loss": 0.944,
"step": 85
},
{
"epoch": 0.013207909387598388,
"grad_norm": 0.3578270971775055,
"learning_rate": 6.545084971874738e-05,
"loss": 0.8983,
"step": 86
},
{
"epoch": 0.013361489729314648,
"grad_norm": 0.36193057894706726,
"learning_rate": 6.466250186922325e-05,
"loss": 0.9278,
"step": 87
},
{
"epoch": 0.013515070071030907,
"grad_norm": 0.35534438490867615,
"learning_rate": 6.387014543809223e-05,
"loss": 0.8527,
"step": 88
},
{
"epoch": 0.013668650412747169,
"grad_norm": 0.37666594982147217,
"learning_rate": 6.307399704769099e-05,
"loss": 0.8601,
"step": 89
},
{
"epoch": 0.013822230754463429,
"grad_norm": 0.38930463790893555,
"learning_rate": 6.227427435703997e-05,
"loss": 0.9448,
"step": 90
},
{
"epoch": 0.013975811096179689,
"grad_norm": 0.3877951204776764,
"learning_rate": 6.147119600233758e-05,
"loss": 0.9051,
"step": 91
},
{
"epoch": 0.014129391437895948,
"grad_norm": 0.4118521809577942,
"learning_rate": 6.066498153718735e-05,
"loss": 0.9445,
"step": 92
},
{
"epoch": 0.01428297177961221,
"grad_norm": 0.4061738848686218,
"learning_rate": 5.985585137257401e-05,
"loss": 0.8564,
"step": 93
},
{
"epoch": 0.01443655212132847,
"grad_norm": 0.4283972382545471,
"learning_rate": 5.90440267166055e-05,
"loss": 0.8951,
"step": 94
},
{
"epoch": 0.01459013246304473,
"grad_norm": 0.4695991575717926,
"learning_rate": 5.8229729514036705e-05,
"loss": 0.8199,
"step": 95
},
{
"epoch": 0.014743712804760991,
"grad_norm": 0.45762595534324646,
"learning_rate": 5.74131823855921e-05,
"loss": 0.8676,
"step": 96
},
{
"epoch": 0.014897293146477251,
"grad_norm": 0.5003182888031006,
"learning_rate": 5.6594608567103456e-05,
"loss": 0.8097,
"step": 97
},
{
"epoch": 0.015050873488193511,
"grad_norm": 0.5176870226860046,
"learning_rate": 5.577423184847932e-05,
"loss": 0.8637,
"step": 98
},
{
"epoch": 0.01520445382990977,
"grad_norm": 0.5762999057769775,
"learning_rate": 5.495227651252315e-05,
"loss": 0.9886,
"step": 99
},
{
"epoch": 0.015358034171626032,
"grad_norm": 0.7685824632644653,
"learning_rate": 5.4128967273616625e-05,
"loss": 1.0631,
"step": 100
},
{
"epoch": 0.015358034171626032,
"eval_loss": 0.9337338209152222,
"eval_runtime": 310.7348,
"eval_samples_per_second": 35.294,
"eval_steps_per_second": 8.824,
"step": 100
},
{
"epoch": 0.015511614513342292,
"grad_norm": 0.4081595838069916,
"learning_rate": 5.330452921628497e-05,
"loss": 0.9383,
"step": 101
},
{
"epoch": 0.015665194855058552,
"grad_norm": 0.3752840459346771,
"learning_rate": 5.247918773366112e-05,
"loss": 0.9247,
"step": 102
},
{
"epoch": 0.015818775196774812,
"grad_norm": 0.3718169629573822,
"learning_rate": 5.165316846586541e-05,
"loss": 0.8958,
"step": 103
},
{
"epoch": 0.015972355538491072,
"grad_norm": 0.3442371189594269,
"learning_rate": 5.0826697238317935e-05,
"loss": 1.0572,
"step": 104
},
{
"epoch": 0.016125935880207335,
"grad_norm": 0.2699859142303467,
"learning_rate": 5e-05,
"loss": 0.8729,
"step": 105
},
{
"epoch": 0.016279516221923595,
"grad_norm": 0.2720978856086731,
"learning_rate": 4.917330276168208e-05,
"loss": 0.9563,
"step": 106
},
{
"epoch": 0.016433096563639855,
"grad_norm": 0.2615968883037567,
"learning_rate": 4.834683153413459e-05,
"loss": 0.953,
"step": 107
},
{
"epoch": 0.016586676905356115,
"grad_norm": 0.26483407616615295,
"learning_rate": 4.7520812266338885e-05,
"loss": 0.919,
"step": 108
},
{
"epoch": 0.016740257247072374,
"grad_norm": 0.24970656633377075,
"learning_rate": 4.669547078371504e-05,
"loss": 0.9717,
"step": 109
},
{
"epoch": 0.016893837588788634,
"grad_norm": 0.2519916892051697,
"learning_rate": 4.5871032726383386e-05,
"loss": 0.8843,
"step": 110
},
{
"epoch": 0.017047417930504894,
"grad_norm": 0.25559002161026,
"learning_rate": 4.504772348747687e-05,
"loss": 0.8863,
"step": 111
},
{
"epoch": 0.017200998272221157,
"grad_norm": 0.2683105170726776,
"learning_rate": 4.4225768151520694e-05,
"loss": 0.8811,
"step": 112
},
{
"epoch": 0.017354578613937417,
"grad_norm": 0.2721691131591797,
"learning_rate": 4.3405391432896555e-05,
"loss": 0.9821,
"step": 113
},
{
"epoch": 0.017508158955653677,
"grad_norm": 0.27934569120407104,
"learning_rate": 4.2586817614407895e-05,
"loss": 0.958,
"step": 114
},
{
"epoch": 0.017661739297369937,
"grad_norm": 0.2696536183357239,
"learning_rate": 4.17702704859633e-05,
"loss": 0.8077,
"step": 115
},
{
"epoch": 0.017815319639086197,
"grad_norm": 0.2778107523918152,
"learning_rate": 4.095597328339452e-05,
"loss": 0.9588,
"step": 116
},
{
"epoch": 0.017968899980802457,
"grad_norm": 0.2798193097114563,
"learning_rate": 4.0144148627425993e-05,
"loss": 0.9622,
"step": 117
},
{
"epoch": 0.018122480322518716,
"grad_norm": 0.28140854835510254,
"learning_rate": 3.933501846281267e-05,
"loss": 0.8745,
"step": 118
},
{
"epoch": 0.018276060664234976,
"grad_norm": 0.2827307879924774,
"learning_rate": 3.852880399766243e-05,
"loss": 0.8482,
"step": 119
},
{
"epoch": 0.01842964100595124,
"grad_norm": 0.2829693853855133,
"learning_rate": 3.772572564296005e-05,
"loss": 0.8595,
"step": 120
},
{
"epoch": 0.0185832213476675,
"grad_norm": 0.29149293899536133,
"learning_rate": 3.6926002952309016e-05,
"loss": 0.9106,
"step": 121
},
{
"epoch": 0.01873680168938376,
"grad_norm": 0.29184380173683167,
"learning_rate": 3.612985456190778e-05,
"loss": 0.8796,
"step": 122
},
{
"epoch": 0.01889038203110002,
"grad_norm": 0.3013525605201721,
"learning_rate": 3.533749813077677e-05,
"loss": 0.9494,
"step": 123
},
{
"epoch": 0.01904396237281628,
"grad_norm": 0.28589993715286255,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.8215,
"step": 124
},
{
"epoch": 0.01919754271453254,
"grad_norm": 0.30020594596862793,
"learning_rate": 3.3765026539765834e-05,
"loss": 0.8866,
"step": 125
},
{
"epoch": 0.0193511230562488,
"grad_norm": 0.31164950132369995,
"learning_rate": 3.298534127791785e-05,
"loss": 0.8921,
"step": 126
},
{
"epoch": 0.019504703397965062,
"grad_norm": 0.32049575448036194,
"learning_rate": 3.221030765387417e-05,
"loss": 0.948,
"step": 127
},
{
"epoch": 0.019658283739681322,
"grad_norm": 0.31892746686935425,
"learning_rate": 3.144013755408895e-05,
"loss": 0.9127,
"step": 128
},
{
"epoch": 0.01981186408139758,
"grad_norm": 0.31716814637184143,
"learning_rate": 3.0675041535377405e-05,
"loss": 0.9002,
"step": 129
},
{
"epoch": 0.01996544442311384,
"grad_norm": 0.3231576383113861,
"learning_rate": 2.991522876735154e-05,
"loss": 0.8516,
"step": 130
},
{
"epoch": 0.0201190247648301,
"grad_norm": 0.33462443947792053,
"learning_rate": 2.916090697523549e-05,
"loss": 0.8804,
"step": 131
},
{
"epoch": 0.02027260510654636,
"grad_norm": 0.3158504068851471,
"learning_rate": 2.8412282383075363e-05,
"loss": 0.8838,
"step": 132
},
{
"epoch": 0.02042618544826262,
"grad_norm": 0.33228564262390137,
"learning_rate": 2.766955965735968e-05,
"loss": 0.9502,
"step": 133
},
{
"epoch": 0.020579765789978884,
"grad_norm": 0.3396526277065277,
"learning_rate": 2.693294185106562e-05,
"loss": 0.851,
"step": 134
},
{
"epoch": 0.020733346131695144,
"grad_norm": 0.3385181128978729,
"learning_rate": 2.6202630348146324e-05,
"loss": 0.8588,
"step": 135
},
{
"epoch": 0.020886926473411404,
"grad_norm": 0.35612183809280396,
"learning_rate": 2.547882480847461e-05,
"loss": 0.9294,
"step": 136
},
{
"epoch": 0.021040506815127664,
"grad_norm": 0.36082717776298523,
"learning_rate": 2.476172311325783e-05,
"loss": 1.0496,
"step": 137
},
{
"epoch": 0.021194087156843924,
"grad_norm": 0.3587377965450287,
"learning_rate": 2.405152131093926e-05,
"loss": 0.9305,
"step": 138
},
{
"epoch": 0.021347667498560183,
"grad_norm": 0.3695134222507477,
"learning_rate": 2.3348413563600325e-05,
"loss": 0.8291,
"step": 139
},
{
"epoch": 0.021501247840276443,
"grad_norm": 0.37007614970207214,
"learning_rate": 2.2652592093878666e-05,
"loss": 0.8571,
"step": 140
},
{
"epoch": 0.021654828181992707,
"grad_norm": 0.38133370876312256,
"learning_rate": 2.196424713241637e-05,
"loss": 0.8827,
"step": 141
},
{
"epoch": 0.021808408523708966,
"grad_norm": 0.3892364501953125,
"learning_rate": 2.128356686585282e-05,
"loss": 0.9467,
"step": 142
},
{
"epoch": 0.021961988865425226,
"grad_norm": 0.4190048575401306,
"learning_rate": 2.061073738537635e-05,
"loss": 0.9311,
"step": 143
},
{
"epoch": 0.022115569207141486,
"grad_norm": 0.412373423576355,
"learning_rate": 1.9945942635848748e-05,
"loss": 0.8774,
"step": 144
},
{
"epoch": 0.022269149548857746,
"grad_norm": 0.4040473997592926,
"learning_rate": 1.928936436551661e-05,
"loss": 0.7724,
"step": 145
},
{
"epoch": 0.022422729890574006,
"grad_norm": 0.42698028683662415,
"learning_rate": 1.8641182076323148e-05,
"loss": 0.8972,
"step": 146
},
{
"epoch": 0.022576310232290266,
"grad_norm": 0.44366565346717834,
"learning_rate": 1.800157297483417e-05,
"loss": 0.8514,
"step": 147
},
{
"epoch": 0.022729890574006525,
"grad_norm": 0.5251530408859253,
"learning_rate": 1.7370711923791567e-05,
"loss": 0.9656,
"step": 148
},
{
"epoch": 0.02288347091572279,
"grad_norm": 0.5596442818641663,
"learning_rate": 1.6748771394307585e-05,
"loss": 0.9594,
"step": 149
},
{
"epoch": 0.02303705125743905,
"grad_norm": 0.7752247452735901,
"learning_rate": 1.6135921418712956e-05,
"loss": 1.1948,
"step": 150
},
{
"epoch": 0.02303705125743905,
"eval_loss": 0.9077740907669067,
"eval_runtime": 310.4215,
"eval_samples_per_second": 35.329,
"eval_steps_per_second": 8.833,
"step": 150
},
{
"epoch": 0.02319063159915531,
"grad_norm": 0.2524168789386749,
"learning_rate": 1.553232954407171e-05,
"loss": 0.9806,
"step": 151
},
{
"epoch": 0.02334421194087157,
"grad_norm": 0.26341086626052856,
"learning_rate": 1.4938160786375572e-05,
"loss": 0.9452,
"step": 152
},
{
"epoch": 0.023497792282587828,
"grad_norm": 0.2745681405067444,
"learning_rate": 1.435357758543015e-05,
"loss": 0.9411,
"step": 153
},
{
"epoch": 0.023651372624304088,
"grad_norm": 0.26520130038261414,
"learning_rate": 1.3778739760445552e-05,
"loss": 0.9249,
"step": 154
},
{
"epoch": 0.023804952966020348,
"grad_norm": 0.2728784382343292,
"learning_rate": 1.3213804466343421e-05,
"loss": 0.8954,
"step": 155
},
{
"epoch": 0.02395853330773661,
"grad_norm": 0.26284217834472656,
"learning_rate": 1.2658926150792322e-05,
"loss": 0.8894,
"step": 156
},
{
"epoch": 0.02411211364945287,
"grad_norm": 0.25816696882247925,
"learning_rate": 1.2114256511983274e-05,
"loss": 0.8279,
"step": 157
},
{
"epoch": 0.02426569399116913,
"grad_norm": 0.25154533982276917,
"learning_rate": 1.157994445715706e-05,
"loss": 0.8978,
"step": 158
},
{
"epoch": 0.02441927433288539,
"grad_norm": 0.2440907508134842,
"learning_rate": 1.1056136061894384e-05,
"loss": 0.8014,
"step": 159
},
{
"epoch": 0.02457285467460165,
"grad_norm": 0.25713929533958435,
"learning_rate": 1.0542974530180327e-05,
"loss": 0.8452,
"step": 160
},
{
"epoch": 0.02472643501631791,
"grad_norm": 0.2546810507774353,
"learning_rate": 1.0040600155253765e-05,
"loss": 0.8385,
"step": 161
},
{
"epoch": 0.02488001535803417,
"grad_norm": 0.2612011730670929,
"learning_rate": 9.549150281252633e-06,
"loss": 0.8819,
"step": 162
},
{
"epoch": 0.025033595699750433,
"grad_norm": 0.2723248600959778,
"learning_rate": 9.068759265665384e-06,
"loss": 0.9673,
"step": 163
},
{
"epoch": 0.025187176041466693,
"grad_norm": 0.2660354971885681,
"learning_rate": 8.599558442598998e-06,
"loss": 0.8495,
"step": 164
},
{
"epoch": 0.025340756383182953,
"grad_norm": 0.26562562584877014,
"learning_rate": 8.141676086873572e-06,
"loss": 0.8766,
"step": 165
},
{
"epoch": 0.025494336724899213,
"grad_norm": 0.28423336148262024,
"learning_rate": 7.695237378953223e-06,
"loss": 0.9406,
"step": 166
},
{
"epoch": 0.025647917066615473,
"grad_norm": 0.275634765625,
"learning_rate": 7.260364370723044e-06,
"loss": 0.9522,
"step": 167
},
{
"epoch": 0.025801497408331733,
"grad_norm": 0.26597291231155396,
"learning_rate": 6.837175952121306e-06,
"loss": 0.8675,
"step": 168
},
{
"epoch": 0.025955077750047992,
"grad_norm": 0.2768835127353668,
"learning_rate": 6.425787818636131e-06,
"loss": 0.915,
"step": 169
},
{
"epoch": 0.026108658091764256,
"grad_norm": 0.2831278145313263,
"learning_rate": 6.026312439675552e-06,
"loss": 0.9647,
"step": 170
},
{
"epoch": 0.026262238433480516,
"grad_norm": 0.2722913324832916,
"learning_rate": 5.6388590278194096e-06,
"loss": 0.9044,
"step": 171
},
{
"epoch": 0.026415818775196775,
"grad_norm": 0.28955158591270447,
"learning_rate": 5.263533508961827e-06,
"loss": 0.931,
"step": 172
},
{
"epoch": 0.026569399116913035,
"grad_norm": 0.29196467995643616,
"learning_rate": 4.900438493352055e-06,
"loss": 0.9528,
"step": 173
},
{
"epoch": 0.026722979458629295,
"grad_norm": 0.2934655547142029,
"learning_rate": 4.549673247541875e-06,
"loss": 0.8888,
"step": 174
},
{
"epoch": 0.026876559800345555,
"grad_norm": 0.3072153329849243,
"learning_rate": 4.2113336672471245e-06,
"loss": 0.9641,
"step": 175
},
{
"epoch": 0.027030140142061815,
"grad_norm": 0.3084641695022583,
"learning_rate": 3.885512251130763e-06,
"loss": 0.9223,
"step": 176
},
{
"epoch": 0.027183720483778078,
"grad_norm": 0.3008544147014618,
"learning_rate": 3.5722980755146517e-06,
"loss": 0.9513,
"step": 177
},
{
"epoch": 0.027337300825494338,
"grad_norm": 0.29867640137672424,
"learning_rate": 3.271776770026963e-06,
"loss": 0.881,
"step": 178
},
{
"epoch": 0.027490881167210598,
"grad_norm": 0.32133713364601135,
"learning_rate": 2.9840304941919415e-06,
"loss": 0.961,
"step": 179
},
{
"epoch": 0.027644461508926858,
"grad_norm": 0.31610262393951416,
"learning_rate": 2.7091379149682685e-06,
"loss": 0.9524,
"step": 180
},
{
"epoch": 0.027798041850643117,
"grad_norm": 0.3256909251213074,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.8562,
"step": 181
},
{
"epoch": 0.027951622192359377,
"grad_norm": 0.3165225386619568,
"learning_rate": 2.1982109232821178e-06,
"loss": 0.91,
"step": 182
},
{
"epoch": 0.028105202534075637,
"grad_norm": 0.32926908135414124,
"learning_rate": 1.962316193157593e-06,
"loss": 0.9166,
"step": 183
},
{
"epoch": 0.028258782875791897,
"grad_norm": 0.3199353516101837,
"learning_rate": 1.7395544861325718e-06,
"loss": 0.7614,
"step": 184
},
{
"epoch": 0.02841236321750816,
"grad_norm": 0.3421376645565033,
"learning_rate": 1.5299867030334814e-06,
"loss": 0.8961,
"step": 185
},
{
"epoch": 0.02856594355922442,
"grad_norm": 0.33078110218048096,
"learning_rate": 1.333670137599713e-06,
"loss": 0.8498,
"step": 186
},
{
"epoch": 0.02871952390094068,
"grad_norm": 0.33130109310150146,
"learning_rate": 1.1506584608200367e-06,
"loss": 0.8003,
"step": 187
},
{
"epoch": 0.02887310424265694,
"grad_norm": 0.350922554731369,
"learning_rate": 9.810017062595322e-07,
"loss": 0.8685,
"step": 188
},
{
"epoch": 0.0290266845843732,
"grad_norm": 0.3530254662036896,
"learning_rate": 8.247462563808817e-07,
"loss": 0.8183,
"step": 189
},
{
"epoch": 0.02918026492608946,
"grad_norm": 0.3643895983695984,
"learning_rate": 6.819348298638839e-07,
"loss": 0.8964,
"step": 190
},
{
"epoch": 0.02933384526780572,
"grad_norm": 0.37137266993522644,
"learning_rate": 5.526064699265753e-07,
"loss": 0.8907,
"step": 191
},
{
"epoch": 0.029487425609521983,
"grad_norm": 0.3754010796546936,
"learning_rate": 4.367965336512403e-07,
"loss": 0.8113,
"step": 192
},
{
"epoch": 0.029641005951238242,
"grad_norm": 0.3807097375392914,
"learning_rate": 3.3453668231809286e-07,
"loss": 0.8948,
"step": 193
},
{
"epoch": 0.029794586292954502,
"grad_norm": 0.39577069878578186,
"learning_rate": 2.458548727494292e-07,
"loss": 1.0013,
"step": 194
},
{
"epoch": 0.029948166634670762,
"grad_norm": 0.3868197798728943,
"learning_rate": 1.7077534966650766e-07,
"loss": 0.808,
"step": 195
},
{
"epoch": 0.030101746976387022,
"grad_norm": 0.41734009981155396,
"learning_rate": 1.0931863906127327e-07,
"loss": 0.8744,
"step": 196
},
{
"epoch": 0.030255327318103282,
"grad_norm": 0.46737056970596313,
"learning_rate": 6.150154258476315e-08,
"loss": 0.8407,
"step": 197
},
{
"epoch": 0.03040890765981954,
"grad_norm": 0.5090513825416565,
"learning_rate": 2.7337132953697554e-08,
"loss": 0.9043,
"step": 198
},
{
"epoch": 0.030562488001535805,
"grad_norm": 0.5291383862495422,
"learning_rate": 6.834750376549792e-09,
"loss": 0.8607,
"step": 199
},
{
"epoch": 0.030716068343252065,
"grad_norm": 0.7475754618644714,
"learning_rate": 0.0,
"loss": 1.1954,
"step": 200
},
{
"epoch": 0.030716068343252065,
"eval_loss": 0.9023734927177429,
"eval_runtime": 311.0382,
"eval_samples_per_second": 35.259,
"eval_steps_per_second": 8.816,
"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": 6.266122390418227e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}