R1-Qwen2.5-1.5B-Instruct / trainer_state.json
alex-chiu's picture
Upload folder using huggingface_hub
07463d2 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9990426041168023,
"eval_steps": 500,
"global_step": 348,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0057443752991862135,
"grad_norm": 2.3415639400482178,
"learning_rate": 5.714285714285715e-07,
"loss": 0.9401,
"step": 1
},
{
"epoch": 0.011488750598372427,
"grad_norm": 2.4453043937683105,
"learning_rate": 1.142857142857143e-06,
"loss": 0.9748,
"step": 2
},
{
"epoch": 0.01723312589755864,
"grad_norm": 2.4993081092834473,
"learning_rate": 1.7142857142857145e-06,
"loss": 1.0062,
"step": 3
},
{
"epoch": 0.022977501196744854,
"grad_norm": 2.389991283416748,
"learning_rate": 2.285714285714286e-06,
"loss": 0.9669,
"step": 4
},
{
"epoch": 0.028721876495931067,
"grad_norm": 2.3091812133789062,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.9599,
"step": 5
},
{
"epoch": 0.03446625179511728,
"grad_norm": 2.33378005027771,
"learning_rate": 3.428571428571429e-06,
"loss": 0.9387,
"step": 6
},
{
"epoch": 0.040210627094303494,
"grad_norm": 1.7867075204849243,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9544,
"step": 7
},
{
"epoch": 0.04595500239348971,
"grad_norm": 1.6889110803604126,
"learning_rate": 4.571428571428572e-06,
"loss": 0.9329,
"step": 8
},
{
"epoch": 0.05169937769267592,
"grad_norm": 1.312399983406067,
"learning_rate": 5.142857142857142e-06,
"loss": 0.8812,
"step": 9
},
{
"epoch": 0.057443752991862135,
"grad_norm": 1.330713152885437,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.9434,
"step": 10
},
{
"epoch": 0.06318812829104835,
"grad_norm": 1.222688913345337,
"learning_rate": 6.285714285714286e-06,
"loss": 0.9299,
"step": 11
},
{
"epoch": 0.06893250359023456,
"grad_norm": 0.9597654938697815,
"learning_rate": 6.857142857142858e-06,
"loss": 0.8267,
"step": 12
},
{
"epoch": 0.07467687888942078,
"grad_norm": 1.4648733139038086,
"learning_rate": 7.428571428571429e-06,
"loss": 0.9062,
"step": 13
},
{
"epoch": 0.08042125418860699,
"grad_norm": 1.3538185358047485,
"learning_rate": 8.000000000000001e-06,
"loss": 0.8824,
"step": 14
},
{
"epoch": 0.0861656294877932,
"grad_norm": 1.204816460609436,
"learning_rate": 8.571428571428571e-06,
"loss": 0.8973,
"step": 15
},
{
"epoch": 0.09191000478697942,
"grad_norm": 0.9612676501274109,
"learning_rate": 9.142857142857144e-06,
"loss": 0.8962,
"step": 16
},
{
"epoch": 0.09765438008616563,
"grad_norm": 1.2647408246994019,
"learning_rate": 9.714285714285715e-06,
"loss": 0.8473,
"step": 17
},
{
"epoch": 0.10339875538535184,
"grad_norm": 1.111392855644226,
"learning_rate": 1.0285714285714285e-05,
"loss": 0.8617,
"step": 18
},
{
"epoch": 0.10914313068453806,
"grad_norm": 0.9279037714004517,
"learning_rate": 1.0857142857142858e-05,
"loss": 0.7841,
"step": 19
},
{
"epoch": 0.11488750598372427,
"grad_norm": 0.8200046420097351,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.823,
"step": 20
},
{
"epoch": 0.12063188128291048,
"grad_norm": 0.7917659282684326,
"learning_rate": 1.2e-05,
"loss": 0.8065,
"step": 21
},
{
"epoch": 0.1263762565820967,
"grad_norm": 0.7997102737426758,
"learning_rate": 1.2571428571428572e-05,
"loss": 0.7953,
"step": 22
},
{
"epoch": 0.13212063188128292,
"grad_norm": 0.7637982368469238,
"learning_rate": 1.3142857142857145e-05,
"loss": 0.7559,
"step": 23
},
{
"epoch": 0.13786500718046912,
"grad_norm": 0.6843277215957642,
"learning_rate": 1.3714285714285716e-05,
"loss": 0.7994,
"step": 24
},
{
"epoch": 0.14360938247965535,
"grad_norm": 0.5938118100166321,
"learning_rate": 1.4285714285714287e-05,
"loss": 0.7868,
"step": 25
},
{
"epoch": 0.14935375777884155,
"grad_norm": 0.6095629930496216,
"learning_rate": 1.4857142857142858e-05,
"loss": 0.7764,
"step": 26
},
{
"epoch": 0.15509813307802778,
"grad_norm": 0.7267497777938843,
"learning_rate": 1.542857142857143e-05,
"loss": 0.82,
"step": 27
},
{
"epoch": 0.16084250837721398,
"grad_norm": 0.6032124757766724,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.777,
"step": 28
},
{
"epoch": 0.1665868836764002,
"grad_norm": 0.5352451801300049,
"learning_rate": 1.6571428571428574e-05,
"loss": 0.7643,
"step": 29
},
{
"epoch": 0.1723312589755864,
"grad_norm": 0.6523836851119995,
"learning_rate": 1.7142857142857142e-05,
"loss": 0.7727,
"step": 30
},
{
"epoch": 0.17807563427477263,
"grad_norm": 0.5683100819587708,
"learning_rate": 1.7714285714285717e-05,
"loss": 0.7241,
"step": 31
},
{
"epoch": 0.18382000957395883,
"grad_norm": 0.5439429879188538,
"learning_rate": 1.8285714285714288e-05,
"loss": 0.7011,
"step": 32
},
{
"epoch": 0.18956438487314506,
"grad_norm": 0.5817928314208984,
"learning_rate": 1.885714285714286e-05,
"loss": 0.7521,
"step": 33
},
{
"epoch": 0.19530876017233126,
"grad_norm": 0.5671186447143555,
"learning_rate": 1.942857142857143e-05,
"loss": 0.7757,
"step": 34
},
{
"epoch": 0.20105313547151749,
"grad_norm": 0.5008598566055298,
"learning_rate": 2e-05,
"loss": 0.7618,
"step": 35
},
{
"epoch": 0.20679751077070369,
"grad_norm": 0.4747866988182068,
"learning_rate": 1.9999496293646753e-05,
"loss": 0.7546,
"step": 36
},
{
"epoch": 0.2125418860698899,
"grad_norm": 0.5479198694229126,
"learning_rate": 1.999798522533102e-05,
"loss": 0.7362,
"step": 37
},
{
"epoch": 0.2182862613690761,
"grad_norm": 0.4488674998283386,
"learning_rate": 1.9995466947279753e-05,
"loss": 0.751,
"step": 38
},
{
"epoch": 0.22403063666826234,
"grad_norm": 0.4446718692779541,
"learning_rate": 1.9991941713187477e-05,
"loss": 0.7554,
"step": 39
},
{
"epoch": 0.22977501196744854,
"grad_norm": 0.49354538321495056,
"learning_rate": 1.9987409878190752e-05,
"loss": 0.7234,
"step": 40
},
{
"epoch": 0.23551938726663477,
"grad_norm": 0.4710958003997803,
"learning_rate": 1.99818718988324e-05,
"loss": 0.7789,
"step": 41
},
{
"epoch": 0.24126376256582097,
"grad_norm": 0.43605947494506836,
"learning_rate": 1.9975328333015497e-05,
"loss": 0.7061,
"step": 42
},
{
"epoch": 0.2470081378650072,
"grad_norm": 0.45247551798820496,
"learning_rate": 1.9967779839947172e-05,
"loss": 0.7491,
"step": 43
},
{
"epoch": 0.2527525131641934,
"grad_norm": 0.46377840638160706,
"learning_rate": 1.9959227180072216e-05,
"loss": 0.7646,
"step": 44
},
{
"epoch": 0.2584968884633796,
"grad_norm": 0.43657904863357544,
"learning_rate": 1.9949671214996448e-05,
"loss": 0.7471,
"step": 45
},
{
"epoch": 0.26424126376256585,
"grad_norm": 0.45506250858306885,
"learning_rate": 1.993911290739993e-05,
"loss": 0.6914,
"step": 46
},
{
"epoch": 0.26998563906175205,
"grad_norm": 0.43989095091819763,
"learning_rate": 1.992755332093999e-05,
"loss": 0.7263,
"step": 47
},
{
"epoch": 0.27573001436093825,
"grad_norm": 0.42011386156082153,
"learning_rate": 1.9914993620144055e-05,
"loss": 0.7128,
"step": 48
},
{
"epoch": 0.28147438966012445,
"grad_norm": 0.5503424406051636,
"learning_rate": 1.990143507029234e-05,
"loss": 0.7515,
"step": 49
},
{
"epoch": 0.2872187649593107,
"grad_norm": 0.40828776359558105,
"learning_rate": 1.9886879037290385e-05,
"loss": 0.7013,
"step": 50
},
{
"epoch": 0.2929631402584969,
"grad_norm": 0.476153165102005,
"learning_rate": 1.9871326987531453e-05,
"loss": 0.6848,
"step": 51
},
{
"epoch": 0.2987075155576831,
"grad_norm": 0.49468863010406494,
"learning_rate": 1.98547804877488e-05,
"loss": 0.7401,
"step": 52
},
{
"epoch": 0.3044518908568693,
"grad_norm": 0.42131319642066956,
"learning_rate": 1.983724120485783e-05,
"loss": 0.7085,
"step": 53
},
{
"epoch": 0.31019626615605556,
"grad_norm": 0.4671567976474762,
"learning_rate": 1.9818710905788195e-05,
"loss": 0.6934,
"step": 54
},
{
"epoch": 0.31594064145524176,
"grad_norm": 0.4545610249042511,
"learning_rate": 1.9799191457305767e-05,
"loss": 0.6978,
"step": 55
},
{
"epoch": 0.32168501675442795,
"grad_norm": 0.4409993290901184,
"learning_rate": 1.977868482582459e-05,
"loss": 0.7105,
"step": 56
},
{
"epoch": 0.32742939205361415,
"grad_norm": 0.42373812198638916,
"learning_rate": 1.9757193077208776e-05,
"loss": 0.7167,
"step": 57
},
{
"epoch": 0.3331737673528004,
"grad_norm": 0.47674381732940674,
"learning_rate": 1.9734718376564386e-05,
"loss": 0.714,
"step": 58
},
{
"epoch": 0.3389181426519866,
"grad_norm": 0.42494723200798035,
"learning_rate": 1.9711262988021322e-05,
"loss": 0.684,
"step": 59
},
{
"epoch": 0.3446625179511728,
"grad_norm": 0.42938312888145447,
"learning_rate": 1.968682927450523e-05,
"loss": 0.6904,
"step": 60
},
{
"epoch": 0.350406893250359,
"grad_norm": 0.4486340880393982,
"learning_rate": 1.9661419697499455e-05,
"loss": 0.7125,
"step": 61
},
{
"epoch": 0.35615126854954526,
"grad_norm": 0.39026889204978943,
"learning_rate": 1.9635036816797072e-05,
"loss": 0.7237,
"step": 62
},
{
"epoch": 0.36189564384873146,
"grad_norm": 0.39467936754226685,
"learning_rate": 1.960768329024301e-05,
"loss": 0.7073,
"step": 63
},
{
"epoch": 0.36764001914791766,
"grad_norm": 0.48663580417633057,
"learning_rate": 1.957936187346628e-05,
"loss": 0.6869,
"step": 64
},
{
"epoch": 0.37338439444710386,
"grad_norm": 0.39954885840415955,
"learning_rate": 1.955007541960241e-05,
"loss": 0.7127,
"step": 65
},
{
"epoch": 0.3791287697462901,
"grad_norm": 0.4239981770515442,
"learning_rate": 1.9519826879005964e-05,
"loss": 0.7028,
"step": 66
},
{
"epoch": 0.3848731450454763,
"grad_norm": 0.40746739506721497,
"learning_rate": 1.948861929895336e-05,
"loss": 0.6578,
"step": 67
},
{
"epoch": 0.3906175203446625,
"grad_norm": 0.4423011541366577,
"learning_rate": 1.945645582333587e-05,
"loss": 0.6866,
"step": 68
},
{
"epoch": 0.3963618956438487,
"grad_norm": 0.45761850476264954,
"learning_rate": 1.9423339692342885e-05,
"loss": 0.7173,
"step": 69
},
{
"epoch": 0.40210627094303497,
"grad_norm": 0.3713398575782776,
"learning_rate": 1.9389274242135528e-05,
"loss": 0.6318,
"step": 70
},
{
"epoch": 0.40785064624222117,
"grad_norm": 0.43260371685028076,
"learning_rate": 1.9354262904510544e-05,
"loss": 0.6907,
"step": 71
},
{
"epoch": 0.41359502154140737,
"grad_norm": 0.3918673098087311,
"learning_rate": 1.9318309206554567e-05,
"loss": 0.666,
"step": 72
},
{
"epoch": 0.41933939684059357,
"grad_norm": 0.4002845585346222,
"learning_rate": 1.9281416770288806e-05,
"loss": 0.6948,
"step": 73
},
{
"epoch": 0.4250837721397798,
"grad_norm": 0.4247376024723053,
"learning_rate": 1.924358931230418e-05,
"loss": 0.696,
"step": 74
},
{
"epoch": 0.430828147438966,
"grad_norm": 0.3774103820323944,
"learning_rate": 1.920483064338687e-05,
"loss": 0.7083,
"step": 75
},
{
"epoch": 0.4365725227381522,
"grad_norm": 0.4032825231552124,
"learning_rate": 1.9165144668134426e-05,
"loss": 0.6791,
"step": 76
},
{
"epoch": 0.4423168980373384,
"grad_norm": 0.3765489459037781,
"learning_rate": 1.9124535384562423e-05,
"loss": 0.7115,
"step": 77
},
{
"epoch": 0.4480612733365247,
"grad_norm": 0.3774646520614624,
"learning_rate": 1.9083006883701688e-05,
"loss": 0.6839,
"step": 78
},
{
"epoch": 0.4538056486357109,
"grad_norm": 0.4303993880748749,
"learning_rate": 1.904056334918617e-05,
"loss": 0.6983,
"step": 79
},
{
"epoch": 0.4595500239348971,
"grad_norm": 0.37852737307548523,
"learning_rate": 1.8997209056831462e-05,
"loss": 0.673,
"step": 80
},
{
"epoch": 0.4652943992340833,
"grad_norm": 0.4081466794013977,
"learning_rate": 1.8952948374204066e-05,
"loss": 0.6806,
"step": 81
},
{
"epoch": 0.47103877453326953,
"grad_norm": 0.4459618330001831,
"learning_rate": 1.8907785760181392e-05,
"loss": 0.7013,
"step": 82
},
{
"epoch": 0.47678314983245573,
"grad_norm": 0.4105455279350281,
"learning_rate": 1.8861725764502557e-05,
"loss": 0.6836,
"step": 83
},
{
"epoch": 0.48252752513164193,
"grad_norm": 0.4865868091583252,
"learning_rate": 1.881477302731006e-05,
"loss": 0.7153,
"step": 84
},
{
"epoch": 0.48827190043082813,
"grad_norm": 0.38876765966415405,
"learning_rate": 1.87669322786823e-05,
"loss": 0.6666,
"step": 85
},
{
"epoch": 0.4940162757300144,
"grad_norm": 0.4097835421562195,
"learning_rate": 1.8718208338157082e-05,
"loss": 0.686,
"step": 86
},
{
"epoch": 0.4997606510292006,
"grad_norm": 0.3842048645019531,
"learning_rate": 1.866860611424609e-05,
"loss": 0.7049,
"step": 87
},
{
"epoch": 0.5055050263283868,
"grad_norm": 0.4164787530899048,
"learning_rate": 1.8618130603940386e-05,
"loss": 0.6875,
"step": 88
},
{
"epoch": 0.511249401627573,
"grad_norm": 0.3905528783798218,
"learning_rate": 1.856678689220701e-05,
"loss": 0.6863,
"step": 89
},
{
"epoch": 0.5169937769267592,
"grad_norm": 0.42154574394226074,
"learning_rate": 1.851458015147673e-05,
"loss": 0.696,
"step": 90
},
{
"epoch": 0.5227381522259454,
"grad_norm": 0.43495407700538635,
"learning_rate": 1.846151564112294e-05,
"loss": 0.67,
"step": 91
},
{
"epoch": 0.5284825275251317,
"grad_norm": 0.4206148684024811,
"learning_rate": 1.840759870693184e-05,
"loss": 0.6794,
"step": 92
},
{
"epoch": 0.5342269028243178,
"grad_norm": 0.37400227785110474,
"learning_rate": 1.8352834780563888e-05,
"loss": 0.6633,
"step": 93
},
{
"epoch": 0.5399712781235041,
"grad_norm": 0.43993040919303894,
"learning_rate": 1.8297229379006614e-05,
"loss": 0.6946,
"step": 94
},
{
"epoch": 0.5457156534226902,
"grad_norm": 0.42568662762641907,
"learning_rate": 1.8240788104018824e-05,
"loss": 0.685,
"step": 95
},
{
"epoch": 0.5514600287218765,
"grad_norm": 0.39264383912086487,
"learning_rate": 1.8183516641566278e-05,
"loss": 0.6972,
"step": 96
},
{
"epoch": 0.5572044040210627,
"grad_norm": 0.497275173664093,
"learning_rate": 1.8125420761248878e-05,
"loss": 0.6646,
"step": 97
},
{
"epoch": 0.5629487793202489,
"grad_norm": 0.47043195366859436,
"learning_rate": 1.806650631571943e-05,
"loss": 0.7161,
"step": 98
},
{
"epoch": 0.5686931546194351,
"grad_norm": 0.3922593295574188,
"learning_rate": 1.8006779240094024e-05,
"loss": 0.6633,
"step": 99
},
{
"epoch": 0.5744375299186214,
"grad_norm": 0.5541552305221558,
"learning_rate": 1.7946245551354156e-05,
"loss": 0.6671,
"step": 100
},
{
"epoch": 0.5801819052178075,
"grad_norm": 0.4806561768054962,
"learning_rate": 1.7884911347740556e-05,
"loss": 0.7065,
"step": 101
},
{
"epoch": 0.5859262805169938,
"grad_norm": 0.5252166986465454,
"learning_rate": 1.782278280813882e-05,
"loss": 0.6993,
"step": 102
},
{
"epoch": 0.59167065581618,
"grad_norm": 0.3711872696876526,
"learning_rate": 1.775986619145697e-05,
"loss": 0.6805,
"step": 103
},
{
"epoch": 0.5974150311153662,
"grad_norm": 0.4423963129520416,
"learning_rate": 1.7696167835994927e-05,
"loss": 0.6613,
"step": 104
},
{
"epoch": 0.6031594064145525,
"grad_norm": 0.455920934677124,
"learning_rate": 1.7631694158805945e-05,
"loss": 0.6647,
"step": 105
},
{
"epoch": 0.6089037817137386,
"grad_norm": 0.46443215012550354,
"learning_rate": 1.7566451655050197e-05,
"loss": 0.6931,
"step": 106
},
{
"epoch": 0.6146481570129249,
"grad_norm": 0.4322095811367035,
"learning_rate": 1.7500446897340408e-05,
"loss": 0.6849,
"step": 107
},
{
"epoch": 0.6203925323121111,
"grad_norm": 0.4423225522041321,
"learning_rate": 1.7433686535079736e-05,
"loss": 0.7008,
"step": 108
},
{
"epoch": 0.6261369076112973,
"grad_norm": 0.47950470447540283,
"learning_rate": 1.736617729379191e-05,
"loss": 0.6424,
"step": 109
},
{
"epoch": 0.6318812829104835,
"grad_norm": 0.4083796441555023,
"learning_rate": 1.7297925974443675e-05,
"loss": 0.7132,
"step": 110
},
{
"epoch": 0.6376256582096697,
"grad_norm": 0.5103936791419983,
"learning_rate": 1.7228939452759666e-05,
"loss": 0.6938,
"step": 111
},
{
"epoch": 0.6433700335088559,
"grad_norm": 0.44686976075172424,
"learning_rate": 1.7159224678529734e-05,
"loss": 0.7058,
"step": 112
},
{
"epoch": 0.6491144088080422,
"grad_norm": 0.43743202090263367,
"learning_rate": 1.7088788674908817e-05,
"loss": 0.6647,
"step": 113
},
{
"epoch": 0.6548587841072283,
"grad_norm": 0.4688310921192169,
"learning_rate": 1.7017638537709426e-05,
"loss": 0.6925,
"step": 114
},
{
"epoch": 0.6606031594064146,
"grad_norm": 0.46285468339920044,
"learning_rate": 1.6945781434686783e-05,
"loss": 0.7014,
"step": 115
},
{
"epoch": 0.6663475347056008,
"grad_norm": 0.45641931891441345,
"learning_rate": 1.6873224604816753e-05,
"loss": 0.6573,
"step": 116
},
{
"epoch": 0.672091910004787,
"grad_norm": 0.4532499611377716,
"learning_rate": 1.679997535756657e-05,
"loss": 0.6824,
"step": 117
},
{
"epoch": 0.6778362853039732,
"grad_norm": 0.4781695306301117,
"learning_rate": 1.672604107215848e-05,
"loss": 0.7109,
"step": 118
},
{
"epoch": 0.6835806606031594,
"grad_norm": 0.4657115638256073,
"learning_rate": 1.6651429196826337e-05,
"loss": 0.7126,
"step": 119
},
{
"epoch": 0.6893250359023456,
"grad_norm": 0.42937028408050537,
"learning_rate": 1.6576147248065268e-05,
"loss": 0.6648,
"step": 120
},
{
"epoch": 0.6950694112015319,
"grad_norm": 0.40193477272987366,
"learning_rate": 1.6500202809874446e-05,
"loss": 0.6911,
"step": 121
},
{
"epoch": 0.700813786500718,
"grad_norm": 0.40844428539276123,
"learning_rate": 1.6423603532993074e-05,
"loss": 0.6647,
"step": 122
},
{
"epoch": 0.7065581617999043,
"grad_norm": 0.4080415666103363,
"learning_rate": 1.634635713412964e-05,
"loss": 0.6576,
"step": 123
},
{
"epoch": 0.7123025370990905,
"grad_norm": 0.42746731638908386,
"learning_rate": 1.626847139518452e-05,
"loss": 0.7106,
"step": 124
},
{
"epoch": 0.7180469123982767,
"grad_norm": 0.43120649456977844,
"learning_rate": 1.618995416246601e-05,
"loss": 0.7052,
"step": 125
},
{
"epoch": 0.7237912876974629,
"grad_norm": 0.4337042570114136,
"learning_rate": 1.6110813345899914e-05,
"loss": 0.6595,
"step": 126
},
{
"epoch": 0.7295356629966491,
"grad_norm": 0.44476258754730225,
"learning_rate": 1.6031056918232642e-05,
"loss": 0.6587,
"step": 127
},
{
"epoch": 0.7352800382958353,
"grad_norm": 0.4917714297771454,
"learning_rate": 1.595069291422807e-05,
"loss": 0.6742,
"step": 128
},
{
"epoch": 0.7410244135950216,
"grad_norm": 0.4178856909275055,
"learning_rate": 1.586972942985807e-05,
"loss": 0.6836,
"step": 129
},
{
"epoch": 0.7467687888942077,
"grad_norm": 0.44966086745262146,
"learning_rate": 1.5788174621486936e-05,
"loss": 0.7005,
"step": 130
},
{
"epoch": 0.752513164193394,
"grad_norm": 0.3832118511199951,
"learning_rate": 1.570603670504969e-05,
"loss": 0.6582,
"step": 131
},
{
"epoch": 0.7582575394925802,
"grad_norm": 0.4839877188205719,
"learning_rate": 1.5623323955224404e-05,
"loss": 0.6633,
"step": 132
},
{
"epoch": 0.7640019147917664,
"grad_norm": 0.4487728774547577,
"learning_rate": 1.5540044704598588e-05,
"loss": 0.6549,
"step": 133
},
{
"epoch": 0.7697462900909526,
"grad_norm": 0.4354808032512665,
"learning_rate": 1.5456207342829777e-05,
"loss": 0.646,
"step": 134
},
{
"epoch": 0.7754906653901388,
"grad_norm": 0.5101595520973206,
"learning_rate": 1.5371820315800316e-05,
"loss": 0.6699,
"step": 135
},
{
"epoch": 0.781235040689325,
"grad_norm": 0.4810461103916168,
"learning_rate": 1.5286892124766546e-05,
"loss": 0.6794,
"step": 136
},
{
"epoch": 0.7869794159885113,
"grad_norm": 0.4083465039730072,
"learning_rate": 1.5201431325502332e-05,
"loss": 0.6381,
"step": 137
},
{
"epoch": 0.7927237912876974,
"grad_norm": 0.41611915826797485,
"learning_rate": 1.5115446527437193e-05,
"loss": 0.6881,
"step": 138
},
{
"epoch": 0.7984681665868837,
"grad_norm": 0.5111805200576782,
"learning_rate": 1.5028946392788934e-05,
"loss": 0.6979,
"step": 139
},
{
"epoch": 0.8042125418860699,
"grad_norm": 0.4130695164203644,
"learning_rate": 1.4941939635691036e-05,
"loss": 0.7042,
"step": 140
},
{
"epoch": 0.8099569171852561,
"grad_norm": 0.3808434307575226,
"learning_rate": 1.4854435021314766e-05,
"loss": 0.6561,
"step": 141
},
{
"epoch": 0.8157012924844423,
"grad_norm": 0.4564625918865204,
"learning_rate": 1.4766441364986162e-05,
"loss": 0.6984,
"step": 142
},
{
"epoch": 0.8214456677836285,
"grad_norm": 0.42112821340560913,
"learning_rate": 1.467796753129797e-05,
"loss": 0.6481,
"step": 143
},
{
"epoch": 0.8271900430828147,
"grad_norm": 0.4193544387817383,
"learning_rate": 1.4589022433216616e-05,
"loss": 0.6925,
"step": 144
},
{
"epoch": 0.832934418382001,
"grad_norm": 0.4384324252605438,
"learning_rate": 1.4499615031184297e-05,
"loss": 0.6748,
"step": 145
},
{
"epoch": 0.8386787936811871,
"grad_norm": 0.4146939218044281,
"learning_rate": 1.4409754332216303e-05,
"loss": 0.6733,
"step": 146
},
{
"epoch": 0.8444231689803734,
"grad_norm": 0.43513917922973633,
"learning_rate": 1.431944938899363e-05,
"loss": 0.6427,
"step": 147
},
{
"epoch": 0.8501675442795597,
"grad_norm": 0.4932457208633423,
"learning_rate": 1.4228709298950998e-05,
"loss": 0.6716,
"step": 148
},
{
"epoch": 0.8559119195787458,
"grad_norm": 0.41004639863967896,
"learning_rate": 1.4137543203360382e-05,
"loss": 0.6462,
"step": 149
},
{
"epoch": 0.861656294877932,
"grad_norm": 0.4532361328601837,
"learning_rate": 1.4045960286410093e-05,
"loss": 0.6759,
"step": 150
},
{
"epoch": 0.8674006701771182,
"grad_norm": 0.43148860335350037,
"learning_rate": 1.395396977427955e-05,
"loss": 0.6963,
"step": 151
},
{
"epoch": 0.8731450454763044,
"grad_norm": 0.49120664596557617,
"learning_rate": 1.3861580934209832e-05,
"loss": 0.6123,
"step": 152
},
{
"epoch": 0.8788894207754907,
"grad_norm": 0.41906511783599854,
"learning_rate": 1.376880307357009e-05,
"loss": 0.6903,
"step": 153
},
{
"epoch": 0.8846337960746768,
"grad_norm": 0.510985791683197,
"learning_rate": 1.3675645538919884e-05,
"loss": 0.6423,
"step": 154
},
{
"epoch": 0.8903781713738631,
"grad_norm": 0.4236752986907959,
"learning_rate": 1.3582117715067628e-05,
"loss": 0.6567,
"step": 155
},
{
"epoch": 0.8961225466730494,
"grad_norm": 0.4509469270706177,
"learning_rate": 1.3488229024125142e-05,
"loss": 0.6772,
"step": 156
},
{
"epoch": 0.9018669219722355,
"grad_norm": 0.43794822692871094,
"learning_rate": 1.3393988924558445e-05,
"loss": 0.6629,
"step": 157
},
{
"epoch": 0.9076112972714218,
"grad_norm": 0.4324384331703186,
"learning_rate": 1.3299406910234917e-05,
"loss": 0.6906,
"step": 158
},
{
"epoch": 0.9133556725706079,
"grad_norm": 0.43841367959976196,
"learning_rate": 1.3204492509466862e-05,
"loss": 0.6552,
"step": 159
},
{
"epoch": 0.9191000478697942,
"grad_norm": 0.4490503966808319,
"learning_rate": 1.3109255284051615e-05,
"loss": 0.6611,
"step": 160
},
{
"epoch": 0.9248444231689804,
"grad_norm": 0.42710503935813904,
"learning_rate": 1.3013704828308276e-05,
"loss": 0.6859,
"step": 161
},
{
"epoch": 0.9305887984681666,
"grad_norm": 0.43584081530570984,
"learning_rate": 1.2917850768111171e-05,
"loss": 0.6075,
"step": 162
},
{
"epoch": 0.9363331737673528,
"grad_norm": 0.5099417567253113,
"learning_rate": 1.282170275992012e-05,
"loss": 0.6776,
"step": 163
},
{
"epoch": 0.9420775490665391,
"grad_norm": 0.408748984336853,
"learning_rate": 1.2725270489807637e-05,
"loss": 0.6948,
"step": 164
},
{
"epoch": 0.9478219243657252,
"grad_norm": 0.4724796712398529,
"learning_rate": 1.2628563672483147e-05,
"loss": 0.6895,
"step": 165
},
{
"epoch": 0.9535662996649115,
"grad_norm": 0.46162188053131104,
"learning_rate": 1.2531592050314308e-05,
"loss": 0.6331,
"step": 166
},
{
"epoch": 0.9593106749640976,
"grad_norm": 0.5146743059158325,
"learning_rate": 1.2434365392345553e-05,
"loss": 0.6513,
"step": 167
},
{
"epoch": 0.9650550502632839,
"grad_norm": 0.45443448424339294,
"learning_rate": 1.2336893493313946e-05,
"loss": 0.6486,
"step": 168
},
{
"epoch": 0.9707994255624701,
"grad_norm": 0.45461684465408325,
"learning_rate": 1.223918617266245e-05,
"loss": 0.6673,
"step": 169
},
{
"epoch": 0.9765438008616563,
"grad_norm": 0.48310863971710205,
"learning_rate": 1.2141253273550698e-05,
"loss": 0.6593,
"step": 170
},
{
"epoch": 0.9822881761608425,
"grad_norm": 0.3722151517868042,
"learning_rate": 1.2043104661863386e-05,
"loss": 0.7001,
"step": 171
},
{
"epoch": 0.9880325514600288,
"grad_norm": 0.4841504395008087,
"learning_rate": 1.1944750225216363e-05,
"loss": 0.6606,
"step": 172
},
{
"epoch": 0.9937769267592149,
"grad_norm": 0.4420206546783447,
"learning_rate": 1.1846199871960557e-05,
"loss": 0.7026,
"step": 173
},
{
"epoch": 0.9995213020584012,
"grad_norm": 0.4380941689014435,
"learning_rate": 1.1747463530183781e-05,
"loss": 0.6817,
"step": 174
},
{
"epoch": 1.0052656773575874,
"grad_norm": 1.3084274530410767,
"learning_rate": 1.1648551146710557e-05,
"loss": 1.1567,
"step": 175
},
{
"epoch": 1.0110100526567736,
"grad_norm": 0.38088297843933105,
"learning_rate": 1.1549472686100079e-05,
"loss": 0.6346,
"step": 176
},
{
"epoch": 1.0167544279559597,
"grad_norm": 0.4739629924297333,
"learning_rate": 1.145023812964237e-05,
"loss": 0.67,
"step": 177
},
{
"epoch": 1.022498803255146,
"grad_norm": 0.4583199620246887,
"learning_rate": 1.1350857474352734e-05,
"loss": 0.5971,
"step": 178
},
{
"epoch": 1.0282431785543322,
"grad_norm": 0.473290354013443,
"learning_rate": 1.1251340731964664e-05,
"loss": 0.5754,
"step": 179
},
{
"epoch": 1.0339875538535184,
"grad_norm": 0.5124115943908691,
"learning_rate": 1.1151697927921242e-05,
"loss": 0.6753,
"step": 180
},
{
"epoch": 1.0397319291527047,
"grad_norm": 0.46393120288848877,
"learning_rate": 1.1051939100365154e-05,
"loss": 0.6188,
"step": 181
},
{
"epoch": 1.0454763044518909,
"grad_norm": 0.45003098249435425,
"learning_rate": 1.0952074299127451e-05,
"loss": 0.612,
"step": 182
},
{
"epoch": 1.051220679751077,
"grad_norm": 0.5510356426239014,
"learning_rate": 1.0852113584715103e-05,
"loss": 0.6337,
"step": 183
},
{
"epoch": 1.0569650550502634,
"grad_norm": 0.4436226785182953,
"learning_rate": 1.0752067027297486e-05,
"loss": 0.6242,
"step": 184
},
{
"epoch": 1.0627094303494495,
"grad_norm": 0.5315257906913757,
"learning_rate": 1.065194470569193e-05,
"loss": 0.6423,
"step": 185
},
{
"epoch": 1.0684538056486357,
"grad_norm": 0.5305011868476868,
"learning_rate": 1.0551756706348331e-05,
"loss": 0.6507,
"step": 186
},
{
"epoch": 1.0741981809478218,
"grad_norm": 0.40931978821754456,
"learning_rate": 1.0451513122333042e-05,
"loss": 0.6502,
"step": 187
},
{
"epoch": 1.0799425562470082,
"grad_norm": 0.5216091871261597,
"learning_rate": 1.035122405231209e-05,
"loss": 0.6465,
"step": 188
},
{
"epoch": 1.0856869315461943,
"grad_norm": 0.4610161781311035,
"learning_rate": 1.0250899599533833e-05,
"loss": 0.5979,
"step": 189
},
{
"epoch": 1.0914313068453805,
"grad_norm": 0.4795741140842438,
"learning_rate": 1.0150549870811108e-05,
"loss": 0.6318,
"step": 190
},
{
"epoch": 1.0971756821445668,
"grad_norm": 0.5046423673629761,
"learning_rate": 1.0050184975503104e-05,
"loss": 0.6334,
"step": 191
},
{
"epoch": 1.102920057443753,
"grad_norm": 0.41843080520629883,
"learning_rate": 9.949815024496901e-06,
"loss": 0.5911,
"step": 192
},
{
"epoch": 1.1086644327429391,
"grad_norm": 0.4864475131034851,
"learning_rate": 9.849450129188895e-06,
"loss": 0.6293,
"step": 193
},
{
"epoch": 1.1144088080421255,
"grad_norm": 0.45488062500953674,
"learning_rate": 9.74910040046617e-06,
"loss": 0.6293,
"step": 194
},
{
"epoch": 1.1201531833413116,
"grad_norm": 0.5488528609275818,
"learning_rate": 9.648775947687914e-06,
"loss": 0.6601,
"step": 195
},
{
"epoch": 1.1258975586404978,
"grad_norm": 0.42538103461265564,
"learning_rate": 9.548486877666963e-06,
"loss": 0.5716,
"step": 196
},
{
"epoch": 1.1316419339396842,
"grad_norm": 0.4884817898273468,
"learning_rate": 9.448243293651676e-06,
"loss": 0.6445,
"step": 197
},
{
"epoch": 1.1373863092388703,
"grad_norm": 0.3766753375530243,
"learning_rate": 9.348055294308074e-06,
"loss": 0.6133,
"step": 198
},
{
"epoch": 1.1431306845380564,
"grad_norm": 0.37008681893348694,
"learning_rate": 9.247932972702514e-06,
"loss": 0.5788,
"step": 199
},
{
"epoch": 1.1488750598372426,
"grad_norm": 0.47232893109321594,
"learning_rate": 9.147886415284903e-06,
"loss": 0.6026,
"step": 200
},
{
"epoch": 1.154619435136429,
"grad_norm": 0.4648306667804718,
"learning_rate": 9.047925700872552e-06,
"loss": 0.6373,
"step": 201
},
{
"epoch": 1.160363810435615,
"grad_norm": 0.4872569739818573,
"learning_rate": 8.948060899634846e-06,
"loss": 0.6569,
"step": 202
},
{
"epoch": 1.1661081857348012,
"grad_norm": 0.4655154049396515,
"learning_rate": 8.848302072078762e-06,
"loss": 0.6041,
"step": 203
},
{
"epoch": 1.1718525610339876,
"grad_norm": 0.4330590069293976,
"learning_rate": 8.748659268035339e-06,
"loss": 0.6465,
"step": 204
},
{
"epoch": 1.1775969363331737,
"grad_norm": 0.5113588571548462,
"learning_rate": 8.649142525647271e-06,
"loss": 0.6658,
"step": 205
},
{
"epoch": 1.18334131163236,
"grad_norm": 0.4262521266937256,
"learning_rate": 8.549761870357633e-06,
"loss": 0.6033,
"step": 206
},
{
"epoch": 1.1890856869315463,
"grad_norm": 0.4430098831653595,
"learning_rate": 8.450527313899923e-06,
"loss": 0.6045,
"step": 207
},
{
"epoch": 1.1948300622307324,
"grad_norm": 0.4243098199367523,
"learning_rate": 8.351448853289448e-06,
"loss": 0.6256,
"step": 208
},
{
"epoch": 1.2005744375299185,
"grad_norm": 0.43001773953437805,
"learning_rate": 8.25253646981622e-06,
"loss": 0.588,
"step": 209
},
{
"epoch": 1.206318812829105,
"grad_norm": 0.41961541771888733,
"learning_rate": 8.153800128039441e-06,
"loss": 0.6633,
"step": 210
},
{
"epoch": 1.212063188128291,
"grad_norm": 0.4193902909755707,
"learning_rate": 8.05524977478364e-06,
"loss": 0.6335,
"step": 211
},
{
"epoch": 1.2178075634274772,
"grad_norm": 0.3996220529079437,
"learning_rate": 7.956895338136618e-06,
"loss": 0.6314,
"step": 212
},
{
"epoch": 1.2235519387266636,
"grad_norm": 0.4009437561035156,
"learning_rate": 7.858746726449309e-06,
"loss": 0.5935,
"step": 213
},
{
"epoch": 1.2292963140258497,
"grad_norm": 0.42584890127182007,
"learning_rate": 7.760813827337555e-06,
"loss": 0.5841,
"step": 214
},
{
"epoch": 1.2350406893250359,
"grad_norm": 0.47986069321632385,
"learning_rate": 7.663106506686057e-06,
"loss": 0.6383,
"step": 215
},
{
"epoch": 1.2407850646242222,
"grad_norm": 0.46123167872428894,
"learning_rate": 7.565634607654453e-06,
"loss": 0.6486,
"step": 216
},
{
"epoch": 1.2465294399234084,
"grad_norm": 0.41050809621810913,
"learning_rate": 7.468407949685695e-06,
"loss": 0.5783,
"step": 217
},
{
"epoch": 1.2522738152225945,
"grad_norm": 0.4934438169002533,
"learning_rate": 7.371436327516854e-06,
"loss": 0.623,
"step": 218
},
{
"epoch": 1.2580181905217809,
"grad_norm": 0.46547457575798035,
"learning_rate": 7.274729510192367e-06,
"loss": 0.6213,
"step": 219
},
{
"epoch": 1.263762565820967,
"grad_norm": 0.47149044275283813,
"learning_rate": 7.1782972400798825e-06,
"loss": 0.6722,
"step": 220
},
{
"epoch": 1.2695069411201532,
"grad_norm": 0.4751822054386139,
"learning_rate": 7.082149231888833e-06,
"loss": 0.6478,
"step": 221
},
{
"epoch": 1.2752513164193395,
"grad_norm": 0.5404048562049866,
"learning_rate": 6.986295171691727e-06,
"loss": 0.6141,
"step": 222
},
{
"epoch": 1.2809956917185257,
"grad_norm": 0.4342450201511383,
"learning_rate": 6.890744715948388e-06,
"loss": 0.6657,
"step": 223
},
{
"epoch": 1.2867400670177118,
"grad_norm": 0.47704020142555237,
"learning_rate": 6.795507490533142e-06,
"loss": 0.6069,
"step": 224
},
{
"epoch": 1.292484442316898,
"grad_norm": 0.44684454798698425,
"learning_rate": 6.700593089765086e-06,
"loss": 0.5871,
"step": 225
},
{
"epoch": 1.2982288176160843,
"grad_norm": 0.4461020827293396,
"learning_rate": 6.606011075441556e-06,
"loss": 0.599,
"step": 226
},
{
"epoch": 1.3039731929152705,
"grad_norm": 0.5140913724899292,
"learning_rate": 6.511770975874862e-06,
"loss": 0.6503,
"step": 227
},
{
"epoch": 1.3097175682144566,
"grad_norm": 0.48571696877479553,
"learning_rate": 6.417882284932373e-06,
"loss": 0.6956,
"step": 228
},
{
"epoch": 1.3154619435136428,
"grad_norm": 0.4735938012599945,
"learning_rate": 6.324354461080121e-06,
"loss": 0.6384,
"step": 229
},
{
"epoch": 1.3212063188128291,
"grad_norm": 0.42931807041168213,
"learning_rate": 6.231196926429913e-06,
"loss": 0.6187,
"step": 230
},
{
"epoch": 1.3269506941120153,
"grad_norm": 0.43366044759750366,
"learning_rate": 6.138419065790169e-06,
"loss": 0.5666,
"step": 231
},
{
"epoch": 1.3326950694112014,
"grad_norm": 0.5050100684165955,
"learning_rate": 6.046030225720456e-06,
"loss": 0.6884,
"step": 232
},
{
"epoch": 1.3384394447103878,
"grad_norm": 0.4541442394256592,
"learning_rate": 5.95403971358991e-06,
"loss": 0.6237,
"step": 233
},
{
"epoch": 1.344183820009574,
"grad_norm": 0.4040675163269043,
"learning_rate": 5.86245679663962e-06,
"loss": 0.6313,
"step": 234
},
{
"epoch": 1.34992819530876,
"grad_norm": 0.40203991532325745,
"learning_rate": 5.7712907010490036e-06,
"loss": 0.6074,
"step": 235
},
{
"epoch": 1.3556725706079464,
"grad_norm": 0.42576372623443604,
"learning_rate": 5.680550611006372e-06,
"loss": 0.6887,
"step": 236
},
{
"epoch": 1.3614169459071326,
"grad_norm": 0.41085827350616455,
"learning_rate": 5.590245667783701e-06,
"loss": 0.585,
"step": 237
},
{
"epoch": 1.3671613212063187,
"grad_norm": 0.4034533202648163,
"learning_rate": 5.5003849688157075e-06,
"loss": 0.6249,
"step": 238
},
{
"epoch": 1.372905696505505,
"grad_norm": 0.3949970006942749,
"learning_rate": 5.4109775667833866e-06,
"loss": 0.6494,
"step": 239
},
{
"epoch": 1.3786500718046912,
"grad_norm": 0.3907564580440521,
"learning_rate": 5.322032468702037e-06,
"loss": 0.6499,
"step": 240
},
{
"epoch": 1.3843944471038774,
"grad_norm": 0.3859156370162964,
"learning_rate": 5.233558635013842e-06,
"loss": 0.6042,
"step": 241
},
{
"epoch": 1.3901388224030637,
"grad_norm": 0.39453139901161194,
"learning_rate": 5.145564978685234e-06,
"loss": 0.5661,
"step": 242
},
{
"epoch": 1.39588319770225,
"grad_norm": 0.4323676526546478,
"learning_rate": 5.058060364308965e-06,
"loss": 0.6489,
"step": 243
},
{
"epoch": 1.401627573001436,
"grad_norm": 0.4358120560646057,
"learning_rate": 4.971053607211069e-06,
"loss": 0.6446,
"step": 244
},
{
"epoch": 1.4073719483006224,
"grad_norm": 0.47731679677963257,
"learning_rate": 4.884553472562809e-06,
"loss": 0.6493,
"step": 245
},
{
"epoch": 1.4131163235998085,
"grad_norm": 0.4385620355606079,
"learning_rate": 4.7985686744976714e-06,
"loss": 0.6128,
"step": 246
},
{
"epoch": 1.4188606988989947,
"grad_norm": 0.49015676975250244,
"learning_rate": 4.713107875233459e-06,
"loss": 0.6496,
"step": 247
},
{
"epoch": 1.424605074198181,
"grad_norm": 0.4335099160671234,
"learning_rate": 4.628179684199685e-06,
"loss": 0.6078,
"step": 248
},
{
"epoch": 1.4303494494973672,
"grad_norm": 0.4025087058544159,
"learning_rate": 4.543792657170228e-06,
"loss": 0.6226,
"step": 249
},
{
"epoch": 1.4360938247965533,
"grad_norm": 0.37157928943634033,
"learning_rate": 4.459955295401415e-06,
"loss": 0.606,
"step": 250
},
{
"epoch": 1.4418382000957397,
"grad_norm": 0.46268367767333984,
"learning_rate": 4.376676044775601e-06,
"loss": 0.6484,
"step": 251
},
{
"epoch": 1.4475825753949259,
"grad_norm": 0.3992196321487427,
"learning_rate": 4.293963294950313e-06,
"loss": 0.6726,
"step": 252
},
{
"epoch": 1.453326950694112,
"grad_norm": 0.3783876597881317,
"learning_rate": 4.211825378513066e-06,
"loss": 0.5912,
"step": 253
},
{
"epoch": 1.4590713259932984,
"grad_norm": 0.4121813178062439,
"learning_rate": 4.130270570141931e-06,
"loss": 0.6252,
"step": 254
},
{
"epoch": 1.4648157012924845,
"grad_norm": 0.363212913274765,
"learning_rate": 4.0493070857719305e-06,
"loss": 0.6383,
"step": 255
},
{
"epoch": 1.4705600765916707,
"grad_norm": 0.37992483377456665,
"learning_rate": 3.968943081767358e-06,
"loss": 0.6271,
"step": 256
},
{
"epoch": 1.4763044518908568,
"grad_norm": 0.4617908000946045,
"learning_rate": 3.889186654100089e-06,
"loss": 0.6601,
"step": 257
},
{
"epoch": 1.4820488271900432,
"grad_norm": 0.3424414396286011,
"learning_rate": 3.81004583753399e-06,
"loss": 0.5911,
"step": 258
},
{
"epoch": 1.4877932024892293,
"grad_norm": 0.41951489448547363,
"learning_rate": 3.7315286048154862e-06,
"loss": 0.6659,
"step": 259
},
{
"epoch": 1.4935375777884154,
"grad_norm": 0.42662620544433594,
"learning_rate": 3.6536428658703594e-06,
"loss": 0.6263,
"step": 260
},
{
"epoch": 1.4992819530876016,
"grad_norm": 0.3791210651397705,
"learning_rate": 3.576396467006925e-06,
"loss": 0.5559,
"step": 261
},
{
"epoch": 1.505026328386788,
"grad_norm": 0.3816741406917572,
"learning_rate": 3.4997971901255588e-06,
"loss": 0.5874,
"step": 262
},
{
"epoch": 1.510770703685974,
"grad_norm": 0.41983887553215027,
"learning_rate": 3.4238527519347353e-06,
"loss": 0.6062,
"step": 263
},
{
"epoch": 1.5165150789851602,
"grad_norm": 0.4243004620075226,
"learning_rate": 3.3485708031736698e-06,
"loss": 0.6598,
"step": 264
},
{
"epoch": 1.5222594542843466,
"grad_norm": 0.38482630252838135,
"learning_rate": 3.2739589278415252e-06,
"loss": 0.5887,
"step": 265
},
{
"epoch": 1.5280038295835328,
"grad_norm": 0.44671764969825745,
"learning_rate": 3.2000246424334315e-06,
"loss": 0.6041,
"step": 266
},
{
"epoch": 1.533748204882719,
"grad_norm": 0.4712686836719513,
"learning_rate": 3.1267753951832523e-06,
"loss": 0.6144,
"step": 267
},
{
"epoch": 1.5394925801819053,
"grad_norm": 0.4231863021850586,
"learning_rate": 3.0542185653132216e-06,
"loss": 0.63,
"step": 268
},
{
"epoch": 1.5452369554810914,
"grad_norm": 0.4306733310222626,
"learning_rate": 2.982361462290575e-06,
"loss": 0.6251,
"step": 269
},
{
"epoch": 1.5509813307802776,
"grad_norm": 0.3925183117389679,
"learning_rate": 2.9112113250911844e-06,
"loss": 0.6039,
"step": 270
},
{
"epoch": 1.556725706079464,
"grad_norm": 0.3975939452648163,
"learning_rate": 2.8407753214702694e-06,
"loss": 0.7012,
"step": 271
},
{
"epoch": 1.56247008137865,
"grad_norm": 0.42296043038368225,
"learning_rate": 2.7710605472403373e-06,
"loss": 0.6065,
"step": 272
},
{
"epoch": 1.5682144566778362,
"grad_norm": 0.3874426782131195,
"learning_rate": 2.702074025556327e-06,
"loss": 0.6414,
"step": 273
},
{
"epoch": 1.5739588319770226,
"grad_norm": 0.4664260745048523,
"learning_rate": 2.6338227062080924e-06,
"loss": 0.6497,
"step": 274
},
{
"epoch": 1.5797032072762087,
"grad_norm": 0.4342009127140045,
"learning_rate": 2.566313464920265e-06,
"loss": 0.6364,
"step": 275
},
{
"epoch": 1.5854475825753949,
"grad_norm": 0.47467392683029175,
"learning_rate": 2.4995531026595952e-06,
"loss": 0.6311,
"step": 276
},
{
"epoch": 1.5911919578745812,
"grad_norm": 0.42795056104660034,
"learning_rate": 2.4335483449498053e-06,
"loss": 0.6331,
"step": 277
},
{
"epoch": 1.5969363331737674,
"grad_norm": 0.41573217511177063,
"learning_rate": 2.3683058411940563e-06,
"loss": 0.545,
"step": 278
},
{
"epoch": 1.6026807084729535,
"grad_norm": 0.475724995136261,
"learning_rate": 2.3038321640050763e-06,
"loss": 0.6338,
"step": 279
},
{
"epoch": 1.6084250837721399,
"grad_norm": 0.41712650656700134,
"learning_rate": 2.2401338085430326e-06,
"loss": 0.6337,
"step": 280
},
{
"epoch": 1.614169459071326,
"grad_norm": 0.4464361071586609,
"learning_rate": 2.177217191861183e-06,
"loss": 0.6455,
"step": 281
},
{
"epoch": 1.6199138343705122,
"grad_norm": 0.3937479555606842,
"learning_rate": 2.115088652259446e-06,
"loss": 0.6257,
"step": 282
},
{
"epoch": 1.6256582096696985,
"grad_norm": 0.41509386897087097,
"learning_rate": 2.053754448645846e-06,
"loss": 0.6399,
"step": 283
},
{
"epoch": 1.6314025849688847,
"grad_norm": 0.39400720596313477,
"learning_rate": 1.9932207599059782e-06,
"loss": 0.6712,
"step": 284
},
{
"epoch": 1.6371469602680708,
"grad_norm": 0.4166524112224579,
"learning_rate": 1.933493684280574e-06,
"loss": 0.596,
"step": 285
},
{
"epoch": 1.6428913355672572,
"grad_norm": 0.39237356185913086,
"learning_rate": 1.8745792387511241e-06,
"loss": 0.6154,
"step": 286
},
{
"epoch": 1.6486357108664431,
"grad_norm": 0.44719427824020386,
"learning_rate": 1.8164833584337216e-06,
"loss": 0.6634,
"step": 287
},
{
"epoch": 1.6543800861656295,
"grad_norm": 0.4033436179161072,
"learning_rate": 1.75921189598118e-06,
"loss": 0.5736,
"step": 288
},
{
"epoch": 1.6601244614648158,
"grad_norm": 0.3653382956981659,
"learning_rate": 1.7027706209933903e-06,
"loss": 0.6452,
"step": 289
},
{
"epoch": 1.6658688367640018,
"grad_norm": 0.47097504138946533,
"learning_rate": 1.6471652194361131e-06,
"loss": 0.6236,
"step": 290
},
{
"epoch": 1.6716132120631881,
"grad_norm": 0.401380330324173,
"learning_rate": 1.5924012930681643e-06,
"loss": 0.5874,
"step": 291
},
{
"epoch": 1.6773575873623745,
"grad_norm": 0.48601004481315613,
"learning_rate": 1.5384843588770626e-06,
"loss": 0.6091,
"step": 292
},
{
"epoch": 1.6831019626615604,
"grad_norm": 0.3870960772037506,
"learning_rate": 1.4854198485232696e-06,
"loss": 0.6612,
"step": 293
},
{
"epoch": 1.6888463379607468,
"grad_norm": 0.4852856993675232,
"learning_rate": 1.433213107792991e-06,
"loss": 0.6921,
"step": 294
},
{
"epoch": 1.694590713259933,
"grad_norm": 0.404511958360672,
"learning_rate": 1.3818693960596186e-06,
"loss": 0.6112,
"step": 295
},
{
"epoch": 1.700335088559119,
"grad_norm": 0.37528789043426514,
"learning_rate": 1.3313938857539133e-06,
"loss": 0.5827,
"step": 296
},
{
"epoch": 1.7060794638583054,
"grad_norm": 0.44467613101005554,
"learning_rate": 1.2817916618429194e-06,
"loss": 0.6202,
"step": 297
},
{
"epoch": 1.7118238391574916,
"grad_norm": 0.4253291189670563,
"learning_rate": 1.2330677213177034e-06,
"loss": 0.6565,
"step": 298
},
{
"epoch": 1.7175682144566777,
"grad_norm": 0.4275934100151062,
"learning_rate": 1.1852269726899423e-06,
"loss": 0.6204,
"step": 299
},
{
"epoch": 1.723312589755864,
"grad_norm": 0.3519365191459656,
"learning_rate": 1.138274235497443e-06,
"loss": 0.5743,
"step": 300
},
{
"epoch": 1.7290569650550502,
"grad_norm": 0.4690391719341278,
"learning_rate": 1.0922142398186097e-06,
"loss": 0.6739,
"step": 301
},
{
"epoch": 1.7348013403542364,
"grad_norm": 0.34954187273979187,
"learning_rate": 1.0470516257959351e-06,
"loss": 0.5869,
"step": 302
},
{
"epoch": 1.7405457156534228,
"grad_norm": 0.4536847174167633,
"learning_rate": 1.00279094316854e-06,
"loss": 0.5976,
"step": 303
},
{
"epoch": 1.746290090952609,
"grad_norm": 0.46374931931495667,
"learning_rate": 9.594366508138352e-07,
"loss": 0.6411,
"step": 304
},
{
"epoch": 1.752034466251795,
"grad_norm": 0.3895288109779358,
"learning_rate": 9.169931162983137e-07,
"loss": 0.6613,
"step": 305
},
{
"epoch": 1.7577788415509814,
"grad_norm": 0.49768176674842834,
"learning_rate": 8.754646154375801e-07,
"loss": 0.626,
"step": 306
},
{
"epoch": 1.7635232168501676,
"grad_norm": 0.40564650297164917,
"learning_rate": 8.348553318655795e-07,
"loss": 0.5868,
"step": 307
},
{
"epoch": 1.7692675921493537,
"grad_norm": 0.42296889424324036,
"learning_rate": 7.951693566131325e-07,
"loss": 0.6417,
"step": 308
},
{
"epoch": 1.77501196744854,
"grad_norm": 0.4061867892742157,
"learning_rate": 7.564106876958188e-07,
"loss": 0.5981,
"step": 309
},
{
"epoch": 1.7807563427477262,
"grad_norm": 0.39801332354545593,
"learning_rate": 7.185832297111939e-07,
"loss": 0.5885,
"step": 310
},
{
"epoch": 1.7865007180469124,
"grad_norm": 0.4562993049621582,
"learning_rate": 6.816907934454353e-07,
"loss": 0.6611,
"step": 311
},
{
"epoch": 1.7922450933460987,
"grad_norm": 0.426230788230896,
"learning_rate": 6.457370954894582e-07,
"loss": 0.6083,
"step": 312
},
{
"epoch": 1.7979894686452849,
"grad_norm": 0.432153582572937,
"learning_rate": 6.107257578644721e-07,
"loss": 0.5977,
"step": 313
},
{
"epoch": 1.803733843944471,
"grad_norm": 0.3961557447910309,
"learning_rate": 5.766603076571164e-07,
"loss": 0.5776,
"step": 314
},
{
"epoch": 1.8094782192436574,
"grad_norm": 0.406272828578949,
"learning_rate": 5.43544176664137e-07,
"loss": 0.6229,
"step": 315
},
{
"epoch": 1.8152225945428435,
"grad_norm": 0.4153190851211548,
"learning_rate": 5.113807010466432e-07,
"loss": 0.6814,
"step": 316
},
{
"epoch": 1.8209669698420297,
"grad_norm": 0.467479407787323,
"learning_rate": 4.801731209940375e-07,
"loss": 0.624,
"step": 317
},
{
"epoch": 1.826711345141216,
"grad_norm": 0.40130171179771423,
"learning_rate": 4.499245803975927e-07,
"loss": 0.6028,
"step": 318
},
{
"epoch": 1.832455720440402,
"grad_norm": 0.40247321128845215,
"learning_rate": 4.206381265337189e-07,
"loss": 0.6034,
"step": 319
},
{
"epoch": 1.8382000957395883,
"grad_norm": 0.5517602562904358,
"learning_rate": 3.9231670975699354e-07,
"loss": 0.6168,
"step": 320
},
{
"epoch": 1.8439444710387747,
"grad_norm": 0.3919602036476135,
"learning_rate": 3.649631832029288e-07,
"loss": 0.6464,
"step": 321
},
{
"epoch": 1.8496888463379606,
"grad_norm": 0.4361954927444458,
"learning_rate": 3.385803025005463e-07,
"loss": 0.5725,
"step": 322
},
{
"epoch": 1.855433221637147,
"grad_norm": 0.4158506393432617,
"learning_rate": 3.1317072549477246e-07,
"loss": 0.6419,
"step": 323
},
{
"epoch": 1.8611775969363333,
"grad_norm": 0.40699517726898193,
"learning_rate": 2.887370119786792e-07,
"loss": 0.6496,
"step": 324
},
{
"epoch": 1.8669219722355193,
"grad_norm": 0.42238280177116394,
"learning_rate": 2.6528162343561593e-07,
"loss": 0.6192,
"step": 325
},
{
"epoch": 1.8726663475347056,
"grad_norm": 0.4099232256412506,
"learning_rate": 2.4280692279122554e-07,
"loss": 0.6027,
"step": 326
},
{
"epoch": 1.8784107228338918,
"grad_norm": 0.4579300284385681,
"learning_rate": 2.2131517417540937e-07,
"loss": 0.6208,
"step": 327
},
{
"epoch": 1.884155098133078,
"grad_norm": 0.4043782353401184,
"learning_rate": 2.00808542694233e-07,
"loss": 0.6455,
"step": 328
},
{
"epoch": 1.8898994734322643,
"grad_norm": 0.4796655476093292,
"learning_rate": 1.8128909421180506e-07,
"loss": 0.5887,
"step": 329
},
{
"epoch": 1.8956438487314504,
"grad_norm": 0.42188167572021484,
"learning_rate": 1.6275879514217052e-07,
"loss": 0.59,
"step": 330
},
{
"epoch": 1.9013882240306366,
"grad_norm": 0.44038787484169006,
"learning_rate": 1.4521951225120345e-07,
"loss": 0.6184,
"step": 331
},
{
"epoch": 1.907132599329823,
"grad_norm": 0.43046262860298157,
"learning_rate": 1.2867301246854757e-07,
"loss": 0.559,
"step": 332
},
{
"epoch": 1.912876974629009,
"grad_norm": 0.37012651562690735,
"learning_rate": 1.1312096270961525e-07,
"loss": 0.5971,
"step": 333
},
{
"epoch": 1.9186213499281952,
"grad_norm": 0.4588046967983246,
"learning_rate": 9.856492970766296e-08,
"loss": 0.6449,
"step": 334
},
{
"epoch": 1.9243657252273816,
"grad_norm": 0.3975079357624054,
"learning_rate": 8.50063798559475e-08,
"loss": 0.6467,
"step": 335
},
{
"epoch": 1.9301101005265677,
"grad_norm": 0.4464259445667267,
"learning_rate": 7.244667906001202e-08,
"loss": 0.5781,
"step": 336
},
{
"epoch": 1.9358544758257539,
"grad_norm": 0.3905969262123108,
"learning_rate": 6.088709260007153e-08,
"loss": 0.5607,
"step": 337
},
{
"epoch": 1.9415988511249402,
"grad_norm": 0.3919637203216553,
"learning_rate": 5.032878500355498e-08,
"loss": 0.592,
"step": 338
},
{
"epoch": 1.9473432264241264,
"grad_norm": 0.41406241059303284,
"learning_rate": 4.07728199277857e-08,
"loss": 0.6728,
"step": 339
},
{
"epoch": 1.9530876017233125,
"grad_norm": 0.40807828307151794,
"learning_rate": 3.2220160052828245e-08,
"loss": 0.622,
"step": 340
},
{
"epoch": 1.958831977022499,
"grad_norm": 0.4522593319416046,
"learning_rate": 2.467166698450485e-08,
"loss": 0.6369,
"step": 341
},
{
"epoch": 1.964576352321685,
"grad_norm": 0.46903252601623535,
"learning_rate": 1.812810116760044e-08,
"loss": 0.6429,
"step": 342
},
{
"epoch": 1.9703207276208712,
"grad_norm": 0.429757684469223,
"learning_rate": 1.2590121809247235e-08,
"loss": 0.5928,
"step": 343
},
{
"epoch": 1.9760651029200575,
"grad_norm": 0.4194485545158386,
"learning_rate": 8.05828681252452e-09,
"loss": 0.6151,
"step": 344
},
{
"epoch": 1.9818094782192437,
"grad_norm": 0.4075304865837097,
"learning_rate": 4.5330527202480656e-09,
"loss": 0.6248,
"step": 345
},
{
"epoch": 1.9875538535184298,
"grad_norm": 0.3920026421546936,
"learning_rate": 2.014774668979147e-09,
"loss": 0.6467,
"step": 346
},
{
"epoch": 1.9932982288176162,
"grad_norm": 0.4989790916442871,
"learning_rate": 5.037063532498109e-10,
"loss": 0.6511,
"step": 347
},
{
"epoch": 1.9990426041168023,
"grad_norm": 0.4017556607723236,
"learning_rate": 0.0,
"loss": 0.5548,
"step": 348
},
{
"epoch": 1.9990426041168023,
"step": 348,
"total_flos": 155889590697984.0,
"train_loss": 0.45673759161740884,
"train_runtime": 8023.7095,
"train_samples_per_second": 4.165,
"train_steps_per_second": 0.043
}
],
"logging_steps": 1,
"max_steps": 348,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 155889590697984.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}