0x1202's picture
Training in progress, step 200, checkpoint
0359cc4 verified
{
"best_metric": 11.812334060668945,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.13527223537368954,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006763611768684477,
"grad_norm": 0.237967386841774,
"learning_rate": 1e-05,
"loss": 11.9355,
"step": 1
},
{
"epoch": 0.0006763611768684477,
"eval_loss": 11.938315391540527,
"eval_runtime": 26.8727,
"eval_samples_per_second": 92.659,
"eval_steps_per_second": 23.183,
"step": 1
},
{
"epoch": 0.0013527223537368955,
"grad_norm": 0.28053900599479675,
"learning_rate": 2e-05,
"loss": 11.9364,
"step": 2
},
{
"epoch": 0.002029083530605343,
"grad_norm": 0.31019994616508484,
"learning_rate": 3e-05,
"loss": 11.9386,
"step": 3
},
{
"epoch": 0.002705444707473791,
"grad_norm": 0.2719208896160126,
"learning_rate": 4e-05,
"loss": 11.9342,
"step": 4
},
{
"epoch": 0.0033818058843422386,
"grad_norm": 0.3062686622142792,
"learning_rate": 5e-05,
"loss": 11.9376,
"step": 5
},
{
"epoch": 0.004058167061210686,
"grad_norm": 0.27971747517585754,
"learning_rate": 6e-05,
"loss": 11.9377,
"step": 6
},
{
"epoch": 0.0047345282380791345,
"grad_norm": 0.2822919487953186,
"learning_rate": 7e-05,
"loss": 11.9344,
"step": 7
},
{
"epoch": 0.005410889414947582,
"grad_norm": 0.3050798773765564,
"learning_rate": 8e-05,
"loss": 11.9363,
"step": 8
},
{
"epoch": 0.00608725059181603,
"grad_norm": 0.3154335618019104,
"learning_rate": 9e-05,
"loss": 11.9289,
"step": 9
},
{
"epoch": 0.006763611768684477,
"grad_norm": 0.32183581590652466,
"learning_rate": 0.0001,
"loss": 11.9297,
"step": 10
},
{
"epoch": 0.0074399729455529254,
"grad_norm": 0.40921348333358765,
"learning_rate": 9.999316524962345e-05,
"loss": 11.9259,
"step": 11
},
{
"epoch": 0.008116334122421373,
"grad_norm": 0.39508408308029175,
"learning_rate": 9.997266286704631e-05,
"loss": 11.9236,
"step": 12
},
{
"epoch": 0.00879269529928982,
"grad_norm": 0.43999671936035156,
"learning_rate": 9.993849845741524e-05,
"loss": 11.92,
"step": 13
},
{
"epoch": 0.009469056476158269,
"grad_norm": 0.518696129322052,
"learning_rate": 9.989068136093873e-05,
"loss": 11.9121,
"step": 14
},
{
"epoch": 0.010145417653026716,
"grad_norm": 0.4608118534088135,
"learning_rate": 9.98292246503335e-05,
"loss": 11.9123,
"step": 15
},
{
"epoch": 0.010821778829895164,
"grad_norm": 0.5465185642242432,
"learning_rate": 9.975414512725057e-05,
"loss": 11.9092,
"step": 16
},
{
"epoch": 0.011498140006763611,
"grad_norm": 0.5319470763206482,
"learning_rate": 9.966546331768191e-05,
"loss": 11.9089,
"step": 17
},
{
"epoch": 0.01217450118363206,
"grad_norm": 0.5313976407051086,
"learning_rate": 9.956320346634876e-05,
"loss": 11.9018,
"step": 18
},
{
"epoch": 0.012850862360500507,
"grad_norm": 0.4947742819786072,
"learning_rate": 9.944739353007344e-05,
"loss": 11.8951,
"step": 19
},
{
"epoch": 0.013527223537368955,
"grad_norm": 0.47573626041412354,
"learning_rate": 9.931806517013612e-05,
"loss": 11.8882,
"step": 20
},
{
"epoch": 0.014203584714237404,
"grad_norm": 0.46421724557876587,
"learning_rate": 9.917525374361912e-05,
"loss": 11.8886,
"step": 21
},
{
"epoch": 0.014879945891105851,
"grad_norm": 0.43358805775642395,
"learning_rate": 9.901899829374047e-05,
"loss": 11.8814,
"step": 22
},
{
"epoch": 0.015556307067974298,
"grad_norm": 0.38888272643089294,
"learning_rate": 9.884934153917997e-05,
"loss": 11.8805,
"step": 23
},
{
"epoch": 0.016232668244842745,
"grad_norm": 0.40890392661094666,
"learning_rate": 9.86663298624003e-05,
"loss": 11.8733,
"step": 24
},
{
"epoch": 0.016909029421711193,
"grad_norm": 0.35108765959739685,
"learning_rate": 9.847001329696653e-05,
"loss": 11.8728,
"step": 25
},
{
"epoch": 0.01758539059857964,
"grad_norm": 0.3009893298149109,
"learning_rate": 9.826044551386744e-05,
"loss": 11.8746,
"step": 26
},
{
"epoch": 0.01826175177544809,
"grad_norm": 0.34886860847473145,
"learning_rate": 9.803768380684242e-05,
"loss": 11.8686,
"step": 27
},
{
"epoch": 0.018938112952316538,
"grad_norm": 0.306910902261734,
"learning_rate": 9.780178907671789e-05,
"loss": 11.8742,
"step": 28
},
{
"epoch": 0.019614474129184985,
"grad_norm": 0.2792716920375824,
"learning_rate": 9.755282581475769e-05,
"loss": 11.8701,
"step": 29
},
{
"epoch": 0.020290835306053433,
"grad_norm": 0.2787064015865326,
"learning_rate": 9.729086208503174e-05,
"loss": 11.8662,
"step": 30
},
{
"epoch": 0.02096719648292188,
"grad_norm": 0.30096516013145447,
"learning_rate": 9.701596950580806e-05,
"loss": 11.8655,
"step": 31
},
{
"epoch": 0.021643557659790327,
"grad_norm": 0.22762198746204376,
"learning_rate": 9.672822322997305e-05,
"loss": 11.8657,
"step": 32
},
{
"epoch": 0.022319918836658775,
"grad_norm": 0.3060343265533447,
"learning_rate": 9.642770192448536e-05,
"loss": 11.8701,
"step": 33
},
{
"epoch": 0.022996280013527222,
"grad_norm": 0.19704139232635498,
"learning_rate": 9.611448774886924e-05,
"loss": 11.862,
"step": 34
},
{
"epoch": 0.023672641190395673,
"grad_norm": 0.22876790165901184,
"learning_rate": 9.578866633275288e-05,
"loss": 11.86,
"step": 35
},
{
"epoch": 0.02434900236726412,
"grad_norm": 0.19899700582027435,
"learning_rate": 9.545032675245813e-05,
"loss": 11.8585,
"step": 36
},
{
"epoch": 0.025025363544132567,
"grad_norm": 0.2102212905883789,
"learning_rate": 9.509956150664796e-05,
"loss": 11.8581,
"step": 37
},
{
"epoch": 0.025701724721001015,
"grad_norm": 0.1924590915441513,
"learning_rate": 9.473646649103818e-05,
"loss": 11.8572,
"step": 38
},
{
"epoch": 0.026378085897869462,
"grad_norm": 0.18657907843589783,
"learning_rate": 9.43611409721806e-05,
"loss": 11.8577,
"step": 39
},
{
"epoch": 0.02705444707473791,
"grad_norm": 0.16302761435508728,
"learning_rate": 9.397368756032445e-05,
"loss": 11.8621,
"step": 40
},
{
"epoch": 0.027730808251606356,
"grad_norm": 0.19990308582782745,
"learning_rate": 9.357421218136386e-05,
"loss": 11.8562,
"step": 41
},
{
"epoch": 0.028407169428474807,
"grad_norm": 0.1413186490535736,
"learning_rate": 9.316282404787871e-05,
"loss": 11.8555,
"step": 42
},
{
"epoch": 0.029083530605343254,
"grad_norm": 0.16784174740314484,
"learning_rate": 9.273963562927695e-05,
"loss": 11.8554,
"step": 43
},
{
"epoch": 0.029759891782211702,
"grad_norm": 0.13700395822525024,
"learning_rate": 9.230476262104677e-05,
"loss": 11.8546,
"step": 44
},
{
"epoch": 0.03043625295908015,
"grad_norm": 0.15509283542633057,
"learning_rate": 9.185832391312644e-05,
"loss": 11.852,
"step": 45
},
{
"epoch": 0.031112614135948596,
"grad_norm": 0.1586018204689026,
"learning_rate": 9.140044155740101e-05,
"loss": 11.8541,
"step": 46
},
{
"epoch": 0.03178897531281705,
"grad_norm": 0.14049869775772095,
"learning_rate": 9.093124073433463e-05,
"loss": 11.858,
"step": 47
},
{
"epoch": 0.03246533648968549,
"grad_norm": 0.15105028450489044,
"learning_rate": 9.045084971874738e-05,
"loss": 11.8494,
"step": 48
},
{
"epoch": 0.03314169766655394,
"grad_norm": 0.1613709181547165,
"learning_rate": 8.995939984474624e-05,
"loss": 11.8499,
"step": 49
},
{
"epoch": 0.033818058843422386,
"grad_norm": 0.15907692909240723,
"learning_rate": 8.945702546981969e-05,
"loss": 11.845,
"step": 50
},
{
"epoch": 0.033818058843422386,
"eval_loss": 11.856270790100098,
"eval_runtime": 26.7197,
"eval_samples_per_second": 93.19,
"eval_steps_per_second": 23.316,
"step": 50
},
{
"epoch": 0.034494420020290836,
"grad_norm": 0.12236282974481583,
"learning_rate": 8.894386393810563e-05,
"loss": 11.8685,
"step": 51
},
{
"epoch": 0.03517078119715928,
"grad_norm": 0.12720054388046265,
"learning_rate": 8.842005554284296e-05,
"loss": 11.8591,
"step": 52
},
{
"epoch": 0.03584714237402773,
"grad_norm": 0.16211822628974915,
"learning_rate": 8.788574348801675e-05,
"loss": 11.8703,
"step": 53
},
{
"epoch": 0.03652350355089618,
"grad_norm": 0.14150767028331757,
"learning_rate": 8.73410738492077e-05,
"loss": 11.8609,
"step": 54
},
{
"epoch": 0.037199864727764625,
"grad_norm": 0.15406125783920288,
"learning_rate": 8.678619553365659e-05,
"loss": 11.8663,
"step": 55
},
{
"epoch": 0.037876225904633076,
"grad_norm": 0.12352842092514038,
"learning_rate": 8.622126023955446e-05,
"loss": 11.8592,
"step": 56
},
{
"epoch": 0.03855258708150152,
"grad_norm": 0.1002754420042038,
"learning_rate": 8.564642241456986e-05,
"loss": 11.8522,
"step": 57
},
{
"epoch": 0.03922894825836997,
"grad_norm": 0.10230956971645355,
"learning_rate": 8.506183921362443e-05,
"loss": 11.8572,
"step": 58
},
{
"epoch": 0.039905309435238415,
"grad_norm": 0.12960372865200043,
"learning_rate": 8.44676704559283e-05,
"loss": 11.8579,
"step": 59
},
{
"epoch": 0.040581670612106865,
"grad_norm": 0.10838139802217484,
"learning_rate": 8.386407858128706e-05,
"loss": 11.8576,
"step": 60
},
{
"epoch": 0.041258031788975316,
"grad_norm": 0.105787493288517,
"learning_rate": 8.32512286056924e-05,
"loss": 11.8572,
"step": 61
},
{
"epoch": 0.04193439296584376,
"grad_norm": 0.1399187594652176,
"learning_rate": 8.262928807620843e-05,
"loss": 11.8627,
"step": 62
},
{
"epoch": 0.04261075414271221,
"grad_norm": 0.09740117937326431,
"learning_rate": 8.199842702516583e-05,
"loss": 11.8538,
"step": 63
},
{
"epoch": 0.043287115319580655,
"grad_norm": 0.09678664058446884,
"learning_rate": 8.135881792367686e-05,
"loss": 11.8551,
"step": 64
},
{
"epoch": 0.043963476496449105,
"grad_norm": 0.1419193297624588,
"learning_rate": 8.07106356344834e-05,
"loss": 11.8626,
"step": 65
},
{
"epoch": 0.04463983767331755,
"grad_norm": 0.10920987278223038,
"learning_rate": 8.005405736415126e-05,
"loss": 11.855,
"step": 66
},
{
"epoch": 0.045316198850186,
"grad_norm": 0.1029559001326561,
"learning_rate": 7.938926261462366e-05,
"loss": 11.8509,
"step": 67
},
{
"epoch": 0.045992560027054444,
"grad_norm": 0.09123393893241882,
"learning_rate": 7.871643313414718e-05,
"loss": 11.8496,
"step": 68
},
{
"epoch": 0.046668921203922895,
"grad_norm": 0.11451267451047897,
"learning_rate": 7.803575286758364e-05,
"loss": 11.8539,
"step": 69
},
{
"epoch": 0.047345282380791345,
"grad_norm": 0.09488758444786072,
"learning_rate": 7.734740790612136e-05,
"loss": 11.8498,
"step": 70
},
{
"epoch": 0.04802164355765979,
"grad_norm": 0.09582668542861938,
"learning_rate": 7.66515864363997e-05,
"loss": 11.852,
"step": 71
},
{
"epoch": 0.04869800473452824,
"grad_norm": 0.12089107930660248,
"learning_rate": 7.594847868906076e-05,
"loss": 11.8517,
"step": 72
},
{
"epoch": 0.049374365911396684,
"grad_norm": 0.1057586744427681,
"learning_rate": 7.52382768867422e-05,
"loss": 11.8473,
"step": 73
},
{
"epoch": 0.050050727088265135,
"grad_norm": 0.10263911634683609,
"learning_rate": 7.452117519152542e-05,
"loss": 11.8475,
"step": 74
},
{
"epoch": 0.05072708826513358,
"grad_norm": 0.11932218819856644,
"learning_rate": 7.379736965185368e-05,
"loss": 11.8467,
"step": 75
},
{
"epoch": 0.05140344944200203,
"grad_norm": 0.12284577637910843,
"learning_rate": 7.30670581489344e-05,
"loss": 11.8503,
"step": 76
},
{
"epoch": 0.05207981061887048,
"grad_norm": 0.11251188069581985,
"learning_rate": 7.233044034264034e-05,
"loss": 11.8469,
"step": 77
},
{
"epoch": 0.052756171795738924,
"grad_norm": 0.10874664783477783,
"learning_rate": 7.158771761692464e-05,
"loss": 11.8473,
"step": 78
},
{
"epoch": 0.053432532972607374,
"grad_norm": 0.10942290723323822,
"learning_rate": 7.083909302476453e-05,
"loss": 11.8435,
"step": 79
},
{
"epoch": 0.05410889414947582,
"grad_norm": 0.13836970925331116,
"learning_rate": 7.008477123264848e-05,
"loss": 11.8419,
"step": 80
},
{
"epoch": 0.05478525532634427,
"grad_norm": 0.13981105387210846,
"learning_rate": 6.932495846462261e-05,
"loss": 11.8396,
"step": 81
},
{
"epoch": 0.05546161650321271,
"grad_norm": 0.14469364285469055,
"learning_rate": 6.855986244591104e-05,
"loss": 11.8391,
"step": 82
},
{
"epoch": 0.056137977680081164,
"grad_norm": 0.13117651641368866,
"learning_rate": 6.778969234612584e-05,
"loss": 11.8449,
"step": 83
},
{
"epoch": 0.056814338856949614,
"grad_norm": 0.14704087376594543,
"learning_rate": 6.701465872208216e-05,
"loss": 11.8321,
"step": 84
},
{
"epoch": 0.05749070003381806,
"grad_norm": 0.12024803459644318,
"learning_rate": 6.623497346023418e-05,
"loss": 11.8412,
"step": 85
},
{
"epoch": 0.05816706121068651,
"grad_norm": 0.1284947395324707,
"learning_rate": 6.545084971874738e-05,
"loss": 11.8348,
"step": 86
},
{
"epoch": 0.05884342238755495,
"grad_norm": 0.14181016385555267,
"learning_rate": 6.466250186922325e-05,
"loss": 11.8368,
"step": 87
},
{
"epoch": 0.059519783564423404,
"grad_norm": 0.1240636482834816,
"learning_rate": 6.387014543809223e-05,
"loss": 11.8409,
"step": 88
},
{
"epoch": 0.06019614474129185,
"grad_norm": 0.12089544534683228,
"learning_rate": 6.307399704769099e-05,
"loss": 11.836,
"step": 89
},
{
"epoch": 0.0608725059181603,
"grad_norm": 0.11373209208250046,
"learning_rate": 6.227427435703997e-05,
"loss": 11.8301,
"step": 90
},
{
"epoch": 0.06154886709502874,
"grad_norm": 0.13441820442676544,
"learning_rate": 6.147119600233758e-05,
"loss": 11.8315,
"step": 91
},
{
"epoch": 0.06222522827189719,
"grad_norm": 0.1285131722688675,
"learning_rate": 6.066498153718735e-05,
"loss": 11.833,
"step": 92
},
{
"epoch": 0.06290158944876564,
"grad_norm": 0.11824572086334229,
"learning_rate": 5.985585137257401e-05,
"loss": 11.8267,
"step": 93
},
{
"epoch": 0.0635779506256341,
"grad_norm": 0.13153457641601562,
"learning_rate": 5.90440267166055e-05,
"loss": 11.8293,
"step": 94
},
{
"epoch": 0.06425431180250253,
"grad_norm": 0.11505523324012756,
"learning_rate": 5.8229729514036705e-05,
"loss": 11.8277,
"step": 95
},
{
"epoch": 0.06493067297937098,
"grad_norm": 0.11737044900655746,
"learning_rate": 5.74131823855921e-05,
"loss": 11.8256,
"step": 96
},
{
"epoch": 0.06560703415623943,
"grad_norm": 0.0985371544957161,
"learning_rate": 5.6594608567103456e-05,
"loss": 11.8243,
"step": 97
},
{
"epoch": 0.06628339533310788,
"grad_norm": 0.14630939066410065,
"learning_rate": 5.577423184847932e-05,
"loss": 11.8237,
"step": 98
},
{
"epoch": 0.06695975650997633,
"grad_norm": 0.12023121863603592,
"learning_rate": 5.495227651252315e-05,
"loss": 11.8298,
"step": 99
},
{
"epoch": 0.06763611768684477,
"grad_norm": 0.1514110267162323,
"learning_rate": 5.4128967273616625e-05,
"loss": 11.8302,
"step": 100
},
{
"epoch": 0.06763611768684477,
"eval_loss": 11.832171440124512,
"eval_runtime": 26.8217,
"eval_samples_per_second": 92.835,
"eval_steps_per_second": 23.227,
"step": 100
},
{
"epoch": 0.06831247886371322,
"grad_norm": 0.12027816474437714,
"learning_rate": 5.330452921628497e-05,
"loss": 11.854,
"step": 101
},
{
"epoch": 0.06898884004058167,
"grad_norm": 0.20657968521118164,
"learning_rate": 5.247918773366112e-05,
"loss": 11.8513,
"step": 102
},
{
"epoch": 0.06966520121745012,
"grad_norm": 0.14324679970741272,
"learning_rate": 5.165316846586541e-05,
"loss": 11.8409,
"step": 103
},
{
"epoch": 0.07034156239431856,
"grad_norm": 0.1667536497116089,
"learning_rate": 5.0826697238317935e-05,
"loss": 11.8408,
"step": 104
},
{
"epoch": 0.07101792357118701,
"grad_norm": 0.13742108643054962,
"learning_rate": 5e-05,
"loss": 11.8433,
"step": 105
},
{
"epoch": 0.07169428474805546,
"grad_norm": 0.13735030591487885,
"learning_rate": 4.917330276168208e-05,
"loss": 11.8319,
"step": 106
},
{
"epoch": 0.07237064592492391,
"grad_norm": 0.09163592010736465,
"learning_rate": 4.834683153413459e-05,
"loss": 11.8332,
"step": 107
},
{
"epoch": 0.07304700710179236,
"grad_norm": 0.1583622843027115,
"learning_rate": 4.7520812266338885e-05,
"loss": 11.8349,
"step": 108
},
{
"epoch": 0.0737233682786608,
"grad_norm": 0.10508851706981659,
"learning_rate": 4.669547078371504e-05,
"loss": 11.8363,
"step": 109
},
{
"epoch": 0.07439972945552925,
"grad_norm": 0.15417686104774475,
"learning_rate": 4.5871032726383386e-05,
"loss": 11.8359,
"step": 110
},
{
"epoch": 0.0750760906323977,
"grad_norm": 0.10372468829154968,
"learning_rate": 4.504772348747687e-05,
"loss": 11.83,
"step": 111
},
{
"epoch": 0.07575245180926615,
"grad_norm": 0.09224109351634979,
"learning_rate": 4.4225768151520694e-05,
"loss": 11.8275,
"step": 112
},
{
"epoch": 0.07642881298613459,
"grad_norm": 0.1201566830277443,
"learning_rate": 4.3405391432896555e-05,
"loss": 11.8301,
"step": 113
},
{
"epoch": 0.07710517416300304,
"grad_norm": 0.09112562984228134,
"learning_rate": 4.2586817614407895e-05,
"loss": 11.8321,
"step": 114
},
{
"epoch": 0.07778153533987149,
"grad_norm": 0.10148422420024872,
"learning_rate": 4.17702704859633e-05,
"loss": 11.8325,
"step": 115
},
{
"epoch": 0.07845789651673994,
"grad_norm": 0.1041034460067749,
"learning_rate": 4.095597328339452e-05,
"loss": 11.8289,
"step": 116
},
{
"epoch": 0.07913425769360839,
"grad_norm": 0.11524149775505066,
"learning_rate": 4.0144148627425993e-05,
"loss": 11.8273,
"step": 117
},
{
"epoch": 0.07981061887047683,
"grad_norm": 0.1229957789182663,
"learning_rate": 3.933501846281267e-05,
"loss": 11.826,
"step": 118
},
{
"epoch": 0.08048698004734528,
"grad_norm": 0.09767038375139236,
"learning_rate": 3.852880399766243e-05,
"loss": 11.8268,
"step": 119
},
{
"epoch": 0.08116334122421373,
"grad_norm": 0.10564996302127838,
"learning_rate": 3.772572564296005e-05,
"loss": 11.8219,
"step": 120
},
{
"epoch": 0.08183970240108218,
"grad_norm": 0.11788948625326157,
"learning_rate": 3.6926002952309016e-05,
"loss": 11.8174,
"step": 121
},
{
"epoch": 0.08251606357795063,
"grad_norm": 0.0964515283703804,
"learning_rate": 3.612985456190778e-05,
"loss": 11.8217,
"step": 122
},
{
"epoch": 0.08319242475481907,
"grad_norm": 0.09519102424383163,
"learning_rate": 3.533749813077677e-05,
"loss": 11.8193,
"step": 123
},
{
"epoch": 0.08386878593168752,
"grad_norm": 0.10091554373502731,
"learning_rate": 3.4549150281252636e-05,
"loss": 11.8243,
"step": 124
},
{
"epoch": 0.08454514710855597,
"grad_norm": 0.12377063930034637,
"learning_rate": 3.3765026539765834e-05,
"loss": 11.8191,
"step": 125
},
{
"epoch": 0.08522150828542442,
"grad_norm": 0.09319707006216049,
"learning_rate": 3.298534127791785e-05,
"loss": 11.8191,
"step": 126
},
{
"epoch": 0.08589786946229286,
"grad_norm": 0.0966852530837059,
"learning_rate": 3.221030765387417e-05,
"loss": 11.8229,
"step": 127
},
{
"epoch": 0.08657423063916131,
"grad_norm": 0.09921374171972275,
"learning_rate": 3.144013755408895e-05,
"loss": 11.8186,
"step": 128
},
{
"epoch": 0.08725059181602976,
"grad_norm": 0.08391332626342773,
"learning_rate": 3.0675041535377405e-05,
"loss": 11.8265,
"step": 129
},
{
"epoch": 0.08792695299289821,
"grad_norm": 0.10751412808895111,
"learning_rate": 2.991522876735154e-05,
"loss": 11.816,
"step": 130
},
{
"epoch": 0.08860331416976666,
"grad_norm": 0.11316145211458206,
"learning_rate": 2.916090697523549e-05,
"loss": 11.8241,
"step": 131
},
{
"epoch": 0.0892796753466351,
"grad_norm": 0.09601719677448273,
"learning_rate": 2.8412282383075363e-05,
"loss": 11.8176,
"step": 132
},
{
"epoch": 0.08995603652350355,
"grad_norm": 0.11552033573389053,
"learning_rate": 2.766955965735968e-05,
"loss": 11.8153,
"step": 133
},
{
"epoch": 0.090632397700372,
"grad_norm": 0.09254191070795059,
"learning_rate": 2.693294185106562e-05,
"loss": 11.8124,
"step": 134
},
{
"epoch": 0.09130875887724045,
"grad_norm": 0.10105631500482559,
"learning_rate": 2.6202630348146324e-05,
"loss": 11.8104,
"step": 135
},
{
"epoch": 0.09198512005410889,
"grad_norm": 0.09207307547330856,
"learning_rate": 2.547882480847461e-05,
"loss": 11.8158,
"step": 136
},
{
"epoch": 0.09266148123097734,
"grad_norm": 0.11376768350601196,
"learning_rate": 2.476172311325783e-05,
"loss": 11.8165,
"step": 137
},
{
"epoch": 0.09333784240784579,
"grad_norm": 0.11263630539178848,
"learning_rate": 2.405152131093926e-05,
"loss": 11.8093,
"step": 138
},
{
"epoch": 0.09401420358471424,
"grad_norm": 0.11241159588098526,
"learning_rate": 2.3348413563600325e-05,
"loss": 11.8116,
"step": 139
},
{
"epoch": 0.09469056476158269,
"grad_norm": 0.09340821206569672,
"learning_rate": 2.2652592093878666e-05,
"loss": 11.8168,
"step": 140
},
{
"epoch": 0.09536692593845113,
"grad_norm": 0.09616852551698685,
"learning_rate": 2.196424713241637e-05,
"loss": 11.8109,
"step": 141
},
{
"epoch": 0.09604328711531958,
"grad_norm": 0.10595780611038208,
"learning_rate": 2.128356686585282e-05,
"loss": 11.8105,
"step": 142
},
{
"epoch": 0.09671964829218803,
"grad_norm": 0.12038301676511765,
"learning_rate": 2.061073738537635e-05,
"loss": 11.8137,
"step": 143
},
{
"epoch": 0.09739600946905648,
"grad_norm": 0.08127898722887039,
"learning_rate": 1.9945942635848748e-05,
"loss": 11.8064,
"step": 144
},
{
"epoch": 0.09807237064592493,
"grad_norm": 0.09854679554700851,
"learning_rate": 1.928936436551661e-05,
"loss": 11.8088,
"step": 145
},
{
"epoch": 0.09874873182279337,
"grad_norm": 0.12643414735794067,
"learning_rate": 1.8641182076323148e-05,
"loss": 11.8133,
"step": 146
},
{
"epoch": 0.09942509299966182,
"grad_norm": 0.11658405512571335,
"learning_rate": 1.800157297483417e-05,
"loss": 11.8071,
"step": 147
},
{
"epoch": 0.10010145417653027,
"grad_norm": 0.14468736946582794,
"learning_rate": 1.7370711923791567e-05,
"loss": 11.7987,
"step": 148
},
{
"epoch": 0.10077781535339872,
"grad_norm": 0.14392907917499542,
"learning_rate": 1.6748771394307585e-05,
"loss": 11.8163,
"step": 149
},
{
"epoch": 0.10145417653026716,
"grad_norm": 0.1634630709886551,
"learning_rate": 1.6135921418712956e-05,
"loss": 11.808,
"step": 150
},
{
"epoch": 0.10145417653026716,
"eval_loss": 11.815106391906738,
"eval_runtime": 26.7353,
"eval_samples_per_second": 93.135,
"eval_steps_per_second": 23.303,
"step": 150
},
{
"epoch": 0.10213053770713561,
"grad_norm": 0.12364402413368225,
"learning_rate": 1.553232954407171e-05,
"loss": 11.8364,
"step": 151
},
{
"epoch": 0.10280689888400406,
"grad_norm": 0.14670921862125397,
"learning_rate": 1.4938160786375572e-05,
"loss": 11.8244,
"step": 152
},
{
"epoch": 0.10348326006087251,
"grad_norm": 0.15578173100948334,
"learning_rate": 1.435357758543015e-05,
"loss": 11.8291,
"step": 153
},
{
"epoch": 0.10415962123774096,
"grad_norm": 0.11311216652393341,
"learning_rate": 1.3778739760445552e-05,
"loss": 11.819,
"step": 154
},
{
"epoch": 0.1048359824146094,
"grad_norm": 0.10323286056518555,
"learning_rate": 1.3213804466343421e-05,
"loss": 11.8224,
"step": 155
},
{
"epoch": 0.10551234359147785,
"grad_norm": 0.10400164872407913,
"learning_rate": 1.2658926150792322e-05,
"loss": 11.825,
"step": 156
},
{
"epoch": 0.1061887047683463,
"grad_norm": 0.12253665179014206,
"learning_rate": 1.2114256511983274e-05,
"loss": 11.8254,
"step": 157
},
{
"epoch": 0.10686506594521475,
"grad_norm": 0.10653354227542877,
"learning_rate": 1.157994445715706e-05,
"loss": 11.8256,
"step": 158
},
{
"epoch": 0.10754142712208319,
"grad_norm": 0.08306068181991577,
"learning_rate": 1.1056136061894384e-05,
"loss": 11.8163,
"step": 159
},
{
"epoch": 0.10821778829895164,
"grad_norm": 0.1301080584526062,
"learning_rate": 1.0542974530180327e-05,
"loss": 11.8163,
"step": 160
},
{
"epoch": 0.10889414947582009,
"grad_norm": 0.16152924299240112,
"learning_rate": 1.0040600155253765e-05,
"loss": 11.8233,
"step": 161
},
{
"epoch": 0.10957051065268854,
"grad_norm": 0.11118094623088837,
"learning_rate": 9.549150281252633e-06,
"loss": 11.8112,
"step": 162
},
{
"epoch": 0.11024687182955699,
"grad_norm": 0.11803340166807175,
"learning_rate": 9.068759265665384e-06,
"loss": 11.8132,
"step": 163
},
{
"epoch": 0.11092323300642543,
"grad_norm": 0.14186394214630127,
"learning_rate": 8.599558442598998e-06,
"loss": 11.821,
"step": 164
},
{
"epoch": 0.11159959418329388,
"grad_norm": 0.09932221472263336,
"learning_rate": 8.141676086873572e-06,
"loss": 11.8188,
"step": 165
},
{
"epoch": 0.11227595536016233,
"grad_norm": 0.09359414130449295,
"learning_rate": 7.695237378953223e-06,
"loss": 11.8192,
"step": 166
},
{
"epoch": 0.11295231653703078,
"grad_norm": 0.09659715741872787,
"learning_rate": 7.260364370723044e-06,
"loss": 11.81,
"step": 167
},
{
"epoch": 0.11362867771389923,
"grad_norm": 0.08525815606117249,
"learning_rate": 6.837175952121306e-06,
"loss": 11.8111,
"step": 168
},
{
"epoch": 0.11430503889076767,
"grad_norm": 0.118387371301651,
"learning_rate": 6.425787818636131e-06,
"loss": 11.817,
"step": 169
},
{
"epoch": 0.11498140006763612,
"grad_norm": 0.0936487466096878,
"learning_rate": 6.026312439675552e-06,
"loss": 11.8126,
"step": 170
},
{
"epoch": 0.11565776124450457,
"grad_norm": 0.08769124746322632,
"learning_rate": 5.6388590278194096e-06,
"loss": 11.8088,
"step": 171
},
{
"epoch": 0.11633412242137302,
"grad_norm": 0.08036208152770996,
"learning_rate": 5.263533508961827e-06,
"loss": 11.8174,
"step": 172
},
{
"epoch": 0.11701048359824145,
"grad_norm": 0.16039589047431946,
"learning_rate": 4.900438493352055e-06,
"loss": 11.813,
"step": 173
},
{
"epoch": 0.1176868447751099,
"grad_norm": 0.1090821698307991,
"learning_rate": 4.549673247541875e-06,
"loss": 11.8169,
"step": 174
},
{
"epoch": 0.11836320595197836,
"grad_norm": 0.08368097245693207,
"learning_rate": 4.2113336672471245e-06,
"loss": 11.8134,
"step": 175
},
{
"epoch": 0.11903956712884681,
"grad_norm": 0.11224495619535446,
"learning_rate": 3.885512251130763e-06,
"loss": 11.8095,
"step": 176
},
{
"epoch": 0.11971592830571526,
"grad_norm": 0.09706952422857285,
"learning_rate": 3.5722980755146517e-06,
"loss": 11.8147,
"step": 177
},
{
"epoch": 0.1203922894825837,
"grad_norm": 0.10664808750152588,
"learning_rate": 3.271776770026963e-06,
"loss": 11.8086,
"step": 178
},
{
"epoch": 0.12106865065945215,
"grad_norm": 0.08623246848583221,
"learning_rate": 2.9840304941919415e-06,
"loss": 11.8058,
"step": 179
},
{
"epoch": 0.1217450118363206,
"grad_norm": 0.10342194885015488,
"learning_rate": 2.7091379149682685e-06,
"loss": 11.8074,
"step": 180
},
{
"epoch": 0.12242137301318905,
"grad_norm": 0.13990060985088348,
"learning_rate": 2.4471741852423237e-06,
"loss": 11.813,
"step": 181
},
{
"epoch": 0.12309773419005748,
"grad_norm": 0.091579370200634,
"learning_rate": 2.1982109232821178e-06,
"loss": 11.8068,
"step": 182
},
{
"epoch": 0.12377409536692593,
"grad_norm": 0.09613227099180222,
"learning_rate": 1.962316193157593e-06,
"loss": 11.8104,
"step": 183
},
{
"epoch": 0.12445045654379439,
"grad_norm": 0.09183893352746964,
"learning_rate": 1.7395544861325718e-06,
"loss": 11.8131,
"step": 184
},
{
"epoch": 0.12512681772066284,
"grad_norm": 0.10165531933307648,
"learning_rate": 1.5299867030334814e-06,
"loss": 11.8055,
"step": 185
},
{
"epoch": 0.1258031788975313,
"grad_norm": 0.09357872605323792,
"learning_rate": 1.333670137599713e-06,
"loss": 11.8052,
"step": 186
},
{
"epoch": 0.12647954007439974,
"grad_norm": 0.10960277915000916,
"learning_rate": 1.1506584608200367e-06,
"loss": 11.8104,
"step": 187
},
{
"epoch": 0.1271559012512682,
"grad_norm": 0.0910443365573883,
"learning_rate": 9.810017062595322e-07,
"loss": 11.8112,
"step": 188
},
{
"epoch": 0.1278322624281366,
"grad_norm": 0.09133151173591614,
"learning_rate": 8.247462563808817e-07,
"loss": 11.8053,
"step": 189
},
{
"epoch": 0.12850862360500506,
"grad_norm": 0.09930140525102615,
"learning_rate": 6.819348298638839e-07,
"loss": 11.8097,
"step": 190
},
{
"epoch": 0.1291849847818735,
"grad_norm": 0.11062054336071014,
"learning_rate": 5.526064699265753e-07,
"loss": 11.808,
"step": 191
},
{
"epoch": 0.12986134595874196,
"grad_norm": 0.09233880788087845,
"learning_rate": 4.367965336512403e-07,
"loss": 11.8089,
"step": 192
},
{
"epoch": 0.13053770713561041,
"grad_norm": 0.11389517784118652,
"learning_rate": 3.3453668231809286e-07,
"loss": 11.8107,
"step": 193
},
{
"epoch": 0.13121406831247887,
"grad_norm": 0.0986950471997261,
"learning_rate": 2.458548727494292e-07,
"loss": 11.807,
"step": 194
},
{
"epoch": 0.13189042948934732,
"grad_norm": 0.12876228988170624,
"learning_rate": 1.7077534966650766e-07,
"loss": 11.8078,
"step": 195
},
{
"epoch": 0.13256679066621577,
"grad_norm": 0.10200181603431702,
"learning_rate": 1.0931863906127327e-07,
"loss": 11.8043,
"step": 196
},
{
"epoch": 0.13324315184308422,
"grad_norm": 0.10950302332639694,
"learning_rate": 6.150154258476315e-08,
"loss": 11.8137,
"step": 197
},
{
"epoch": 0.13391951301995267,
"grad_norm": 0.16454032063484192,
"learning_rate": 2.7337132953697554e-08,
"loss": 11.8077,
"step": 198
},
{
"epoch": 0.1345958741968211,
"grad_norm": 0.1470460742712021,
"learning_rate": 6.834750376549792e-09,
"loss": 11.8041,
"step": 199
},
{
"epoch": 0.13527223537368954,
"grad_norm": 0.21941329538822174,
"learning_rate": 0.0,
"loss": 11.8214,
"step": 200
},
{
"epoch": 0.13527223537368954,
"eval_loss": 11.812334060668945,
"eval_runtime": 26.7726,
"eval_samples_per_second": 93.005,
"eval_steps_per_second": 23.27,
"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": 250932953088000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}