fengyao1909's picture
Upload folder using huggingface_hub
8bdc92e verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.33408,
"eval_steps": 500,
"global_step": 522,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00064,
"grad_norm": 2.3657337561838188,
"learning_rate": 0.0,
"loss": 0.5764,
"step": 1
},
{
"epoch": 0.00128,
"grad_norm": 2.577238188562681,
"learning_rate": 6.329113924050633e-07,
"loss": 0.6154,
"step": 2
},
{
"epoch": 0.00192,
"grad_norm": 2.486400760684678,
"learning_rate": 1.2658227848101265e-06,
"loss": 0.5765,
"step": 3
},
{
"epoch": 0.00256,
"grad_norm": 2.427317708214583,
"learning_rate": 1.8987341772151901e-06,
"loss": 0.5898,
"step": 4
},
{
"epoch": 0.0032,
"grad_norm": 2.3689778807783104,
"learning_rate": 2.531645569620253e-06,
"loss": 0.5846,
"step": 5
},
{
"epoch": 0.00384,
"grad_norm": 2.533864042007203,
"learning_rate": 3.1645569620253167e-06,
"loss": 0.6002,
"step": 6
},
{
"epoch": 0.00448,
"grad_norm": 1.879595075845785,
"learning_rate": 3.7974683544303802e-06,
"loss": 0.5581,
"step": 7
},
{
"epoch": 0.00512,
"grad_norm": 2.056563531274739,
"learning_rate": 4.430379746835443e-06,
"loss": 0.5859,
"step": 8
},
{
"epoch": 0.00576,
"grad_norm": 1.4703684433180533,
"learning_rate": 5.063291139240506e-06,
"loss": 0.5479,
"step": 9
},
{
"epoch": 0.0064,
"grad_norm": 1.2614967629103893,
"learning_rate": 5.69620253164557e-06,
"loss": 0.5303,
"step": 10
},
{
"epoch": 0.00704,
"grad_norm": 1.1460599905324345,
"learning_rate": 6.329113924050633e-06,
"loss": 0.5568,
"step": 11
},
{
"epoch": 0.00768,
"grad_norm": 1.6204644872566638,
"learning_rate": 6.9620253164556965e-06,
"loss": 0.5111,
"step": 12
},
{
"epoch": 0.00832,
"grad_norm": 1.6361395875225335,
"learning_rate": 7.5949367088607605e-06,
"loss": 0.4678,
"step": 13
},
{
"epoch": 0.00896,
"grad_norm": 1.6402122162855226,
"learning_rate": 8.227848101265822e-06,
"loss": 0.4811,
"step": 14
},
{
"epoch": 0.0096,
"grad_norm": 1.2490639825476322,
"learning_rate": 8.860759493670886e-06,
"loss": 0.442,
"step": 15
},
{
"epoch": 0.01024,
"grad_norm": 1.0588915477376701,
"learning_rate": 9.49367088607595e-06,
"loss": 0.4263,
"step": 16
},
{
"epoch": 0.01088,
"grad_norm": 1.40604786962106,
"learning_rate": 1.0126582278481012e-05,
"loss": 0.4549,
"step": 17
},
{
"epoch": 0.01152,
"grad_norm": 1.242365760774633,
"learning_rate": 1.0759493670886076e-05,
"loss": 0.4531,
"step": 18
},
{
"epoch": 0.01216,
"grad_norm": 0.9396101260126887,
"learning_rate": 1.139240506329114e-05,
"loss": 0.415,
"step": 19
},
{
"epoch": 0.0128,
"grad_norm": 0.7578271337493023,
"learning_rate": 1.2025316455696203e-05,
"loss": 0.4268,
"step": 20
},
{
"epoch": 0.01344,
"grad_norm": 0.7671817679988738,
"learning_rate": 1.2658227848101267e-05,
"loss": 0.4314,
"step": 21
},
{
"epoch": 0.01408,
"grad_norm": 0.6494114557426621,
"learning_rate": 1.3291139240506329e-05,
"loss": 0.3666,
"step": 22
},
{
"epoch": 0.01472,
"grad_norm": 0.6806456497077759,
"learning_rate": 1.3924050632911393e-05,
"loss": 0.3823,
"step": 23
},
{
"epoch": 0.01536,
"grad_norm": 0.6595430154008608,
"learning_rate": 1.4556962025316457e-05,
"loss": 0.3529,
"step": 24
},
{
"epoch": 0.016,
"grad_norm": 0.7689071362735744,
"learning_rate": 1.5189873417721521e-05,
"loss": 0.3932,
"step": 25
},
{
"epoch": 0.01664,
"grad_norm": 0.6854685982052705,
"learning_rate": 1.5822784810126583e-05,
"loss": 0.3738,
"step": 26
},
{
"epoch": 0.01728,
"grad_norm": 0.558852717411362,
"learning_rate": 1.6455696202531644e-05,
"loss": 0.3708,
"step": 27
},
{
"epoch": 0.01792,
"grad_norm": 0.49876042518765007,
"learning_rate": 1.7088607594936708e-05,
"loss": 0.3696,
"step": 28
},
{
"epoch": 0.01856,
"grad_norm": 0.5271567613623678,
"learning_rate": 1.7721518987341772e-05,
"loss": 0.3558,
"step": 29
},
{
"epoch": 0.0192,
"grad_norm": 0.5978920045933569,
"learning_rate": 1.8354430379746836e-05,
"loss": 0.3827,
"step": 30
},
{
"epoch": 0.01984,
"grad_norm": 0.4975313988318536,
"learning_rate": 1.89873417721519e-05,
"loss": 0.3772,
"step": 31
},
{
"epoch": 0.02048,
"grad_norm": 0.5766330443378189,
"learning_rate": 1.962025316455696e-05,
"loss": 0.3832,
"step": 32
},
{
"epoch": 0.02112,
"grad_norm": 0.5567055560538855,
"learning_rate": 2.0253164556962025e-05,
"loss": 0.3477,
"step": 33
},
{
"epoch": 0.02176,
"grad_norm": 0.46871971492473,
"learning_rate": 2.088607594936709e-05,
"loss": 0.3604,
"step": 34
},
{
"epoch": 0.0224,
"grad_norm": 0.43316810660778116,
"learning_rate": 2.1518987341772153e-05,
"loss": 0.3592,
"step": 35
},
{
"epoch": 0.02304,
"grad_norm": 0.4312186195231089,
"learning_rate": 2.2151898734177217e-05,
"loss": 0.3711,
"step": 36
},
{
"epoch": 0.02368,
"grad_norm": 0.46951838290882675,
"learning_rate": 2.278481012658228e-05,
"loss": 0.3618,
"step": 37
},
{
"epoch": 0.02432,
"grad_norm": 0.468516818608629,
"learning_rate": 2.341772151898734e-05,
"loss": 0.3578,
"step": 38
},
{
"epoch": 0.02496,
"grad_norm": 0.45909911923620816,
"learning_rate": 2.4050632911392405e-05,
"loss": 0.3521,
"step": 39
},
{
"epoch": 0.0256,
"grad_norm": 0.36223572387755915,
"learning_rate": 2.468354430379747e-05,
"loss": 0.3439,
"step": 40
},
{
"epoch": 0.02624,
"grad_norm": 0.41920026035277985,
"learning_rate": 2.5316455696202533e-05,
"loss": 0.3052,
"step": 41
},
{
"epoch": 0.02688,
"grad_norm": 0.46410873807902825,
"learning_rate": 2.5949367088607597e-05,
"loss": 0.3324,
"step": 42
},
{
"epoch": 0.02752,
"grad_norm": 0.44804958203514283,
"learning_rate": 2.6582278481012658e-05,
"loss": 0.322,
"step": 43
},
{
"epoch": 0.02816,
"grad_norm": 0.4408934955100543,
"learning_rate": 2.7215189873417722e-05,
"loss": 0.3399,
"step": 44
},
{
"epoch": 0.0288,
"grad_norm": 0.4536362310706478,
"learning_rate": 2.7848101265822786e-05,
"loss": 0.3508,
"step": 45
},
{
"epoch": 0.02944,
"grad_norm": 0.4735438789842479,
"learning_rate": 2.848101265822785e-05,
"loss": 0.3431,
"step": 46
},
{
"epoch": 0.03008,
"grad_norm": 0.3960360490220664,
"learning_rate": 2.9113924050632914e-05,
"loss": 0.3358,
"step": 47
},
{
"epoch": 0.03072,
"grad_norm": 0.4449245975582831,
"learning_rate": 2.9746835443037974e-05,
"loss": 0.3472,
"step": 48
},
{
"epoch": 0.03136,
"grad_norm": 0.41598379019590886,
"learning_rate": 3.0379746835443042e-05,
"loss": 0.3295,
"step": 49
},
{
"epoch": 0.032,
"grad_norm": 0.39770652562313213,
"learning_rate": 3.10126582278481e-05,
"loss": 0.339,
"step": 50
},
{
"epoch": 0.03264,
"grad_norm": 0.4036450937079526,
"learning_rate": 3.1645569620253167e-05,
"loss": 0.326,
"step": 51
},
{
"epoch": 0.03328,
"grad_norm": 0.43082778666471144,
"learning_rate": 3.227848101265823e-05,
"loss": 0.3258,
"step": 52
},
{
"epoch": 0.03392,
"grad_norm": 0.402275292978643,
"learning_rate": 3.291139240506329e-05,
"loss": 0.2905,
"step": 53
},
{
"epoch": 0.03456,
"grad_norm": 0.43612618786182106,
"learning_rate": 3.354430379746836e-05,
"loss": 0.334,
"step": 54
},
{
"epoch": 0.0352,
"grad_norm": 0.45984837714015897,
"learning_rate": 3.4177215189873416e-05,
"loss": 0.3283,
"step": 55
},
{
"epoch": 0.03584,
"grad_norm": 0.4484461315187549,
"learning_rate": 3.4810126582278487e-05,
"loss": 0.3277,
"step": 56
},
{
"epoch": 0.03648,
"grad_norm": 0.4052074034352622,
"learning_rate": 3.5443037974683544e-05,
"loss": 0.3271,
"step": 57
},
{
"epoch": 0.03712,
"grad_norm": 0.46620186767863914,
"learning_rate": 3.607594936708861e-05,
"loss": 0.3464,
"step": 58
},
{
"epoch": 0.03776,
"grad_norm": 0.42593292833096424,
"learning_rate": 3.670886075949367e-05,
"loss": 0.3331,
"step": 59
},
{
"epoch": 0.0384,
"grad_norm": 0.4815687673225032,
"learning_rate": 3.7341772151898736e-05,
"loss": 0.3269,
"step": 60
},
{
"epoch": 0.03904,
"grad_norm": 0.455342196474994,
"learning_rate": 3.79746835443038e-05,
"loss": 0.3343,
"step": 61
},
{
"epoch": 0.03968,
"grad_norm": 0.4316078425366754,
"learning_rate": 3.8607594936708864e-05,
"loss": 0.3145,
"step": 62
},
{
"epoch": 0.04032,
"grad_norm": 0.4604468007808017,
"learning_rate": 3.924050632911392e-05,
"loss": 0.3206,
"step": 63
},
{
"epoch": 0.04096,
"grad_norm": 0.516259514156323,
"learning_rate": 3.987341772151899e-05,
"loss": 0.3538,
"step": 64
},
{
"epoch": 0.0416,
"grad_norm": 0.3911206186305256,
"learning_rate": 4.050632911392405e-05,
"loss": 0.3116,
"step": 65
},
{
"epoch": 0.04224,
"grad_norm": 0.5059680673369054,
"learning_rate": 4.113924050632912e-05,
"loss": 0.3461,
"step": 66
},
{
"epoch": 0.04288,
"grad_norm": 0.4477077725372915,
"learning_rate": 4.177215189873418e-05,
"loss": 0.3142,
"step": 67
},
{
"epoch": 0.04352,
"grad_norm": 0.4568181894979607,
"learning_rate": 4.240506329113924e-05,
"loss": 0.3258,
"step": 68
},
{
"epoch": 0.04416,
"grad_norm": 0.436426112682463,
"learning_rate": 4.3037974683544305e-05,
"loss": 0.2942,
"step": 69
},
{
"epoch": 0.0448,
"grad_norm": 0.4130845172287253,
"learning_rate": 4.367088607594937e-05,
"loss": 0.3293,
"step": 70
},
{
"epoch": 0.04544,
"grad_norm": 0.4907470169969436,
"learning_rate": 4.430379746835443e-05,
"loss": 0.3152,
"step": 71
},
{
"epoch": 0.04608,
"grad_norm": 0.44557023947548996,
"learning_rate": 4.49367088607595e-05,
"loss": 0.323,
"step": 72
},
{
"epoch": 0.04672,
"grad_norm": 0.43347032964452825,
"learning_rate": 4.556962025316456e-05,
"loss": 0.3132,
"step": 73
},
{
"epoch": 0.04736,
"grad_norm": 0.41315778348357357,
"learning_rate": 4.6202531645569625e-05,
"loss": 0.3076,
"step": 74
},
{
"epoch": 0.048,
"grad_norm": 0.38689299616228223,
"learning_rate": 4.683544303797468e-05,
"loss": 0.2971,
"step": 75
},
{
"epoch": 0.04864,
"grad_norm": 0.6649393785343345,
"learning_rate": 4.7468354430379746e-05,
"loss": 0.3196,
"step": 76
},
{
"epoch": 0.04928,
"grad_norm": 0.4741860571119842,
"learning_rate": 4.810126582278481e-05,
"loss": 0.3261,
"step": 77
},
{
"epoch": 0.04992,
"grad_norm": 0.39850926668653464,
"learning_rate": 4.8734177215189874e-05,
"loss": 0.2909,
"step": 78
},
{
"epoch": 0.05056,
"grad_norm": 0.45993342960946926,
"learning_rate": 4.936708860759494e-05,
"loss": 0.3232,
"step": 79
},
{
"epoch": 0.0512,
"grad_norm": 0.41758744126936076,
"learning_rate": 5e-05,
"loss": 0.3138,
"step": 80
},
{
"epoch": 0.05184,
"grad_norm": 0.4190137054884969,
"learning_rate": 4.999994390459423e-05,
"loss": 0.324,
"step": 81
},
{
"epoch": 0.05248,
"grad_norm": 0.38007532443802017,
"learning_rate": 4.999977561862863e-05,
"loss": 0.3167,
"step": 82
},
{
"epoch": 0.05312,
"grad_norm": 0.3894813419979866,
"learning_rate": 4.999949514285842e-05,
"loss": 0.3169,
"step": 83
},
{
"epoch": 0.05376,
"grad_norm": 0.4646671073219221,
"learning_rate": 4.999910247854227e-05,
"loss": 0.3295,
"step": 84
},
{
"epoch": 0.0544,
"grad_norm": 0.46440352293136283,
"learning_rate": 4.99985976274423e-05,
"loss": 0.3259,
"step": 85
},
{
"epoch": 0.05504,
"grad_norm": 0.4754742191954697,
"learning_rate": 4.9997980591824126e-05,
"loss": 0.3073,
"step": 86
},
{
"epoch": 0.05568,
"grad_norm": 0.4102331568111904,
"learning_rate": 4.999725137445674e-05,
"loss": 0.3179,
"step": 87
},
{
"epoch": 0.05632,
"grad_norm": 0.49865407563428993,
"learning_rate": 4.999640997861264e-05,
"loss": 0.3198,
"step": 88
},
{
"epoch": 0.05696,
"grad_norm": 0.450995150648752,
"learning_rate": 4.999545640806766e-05,
"loss": 0.3215,
"step": 89
},
{
"epoch": 0.0576,
"grad_norm": 0.42715082345561,
"learning_rate": 4.999439066710111e-05,
"loss": 0.3406,
"step": 90
},
{
"epoch": 0.05824,
"grad_norm": 0.47007665924261693,
"learning_rate": 4.999321276049563e-05,
"loss": 0.3169,
"step": 91
},
{
"epoch": 0.05888,
"grad_norm": 0.37692477648671757,
"learning_rate": 4.9991922693537226e-05,
"loss": 0.3052,
"step": 92
},
{
"epoch": 0.05952,
"grad_norm": 0.5254380682221013,
"learning_rate": 4.9990520472015246e-05,
"loss": 0.2928,
"step": 93
},
{
"epoch": 0.06016,
"grad_norm": 0.4524991571079602,
"learning_rate": 4.998900610222236e-05,
"loss": 0.3035,
"step": 94
},
{
"epoch": 0.0608,
"grad_norm": 0.39419071585883453,
"learning_rate": 4.998737959095449e-05,
"loss": 0.2764,
"step": 95
},
{
"epoch": 0.06144,
"grad_norm": 0.44021580096048935,
"learning_rate": 4.998564094551081e-05,
"loss": 0.3137,
"step": 96
},
{
"epoch": 0.06208,
"grad_norm": 0.4397078772822271,
"learning_rate": 4.998379017369375e-05,
"loss": 0.3092,
"step": 97
},
{
"epoch": 0.06272,
"grad_norm": 0.4612518337175716,
"learning_rate": 4.9981827283808855e-05,
"loss": 0.3065,
"step": 98
},
{
"epoch": 0.06336,
"grad_norm": 0.4491229684653282,
"learning_rate": 4.997975228466489e-05,
"loss": 0.3327,
"step": 99
},
{
"epoch": 0.064,
"grad_norm": 0.40909998580765855,
"learning_rate": 4.997756518557368e-05,
"loss": 0.2787,
"step": 100
},
{
"epoch": 0.06464,
"grad_norm": 0.3785712105730604,
"learning_rate": 4.997526599635011e-05,
"loss": 0.2837,
"step": 101
},
{
"epoch": 0.06528,
"grad_norm": 0.5009245567404541,
"learning_rate": 4.997285472731211e-05,
"loss": 0.3325,
"step": 102
},
{
"epoch": 0.06592,
"grad_norm": 0.41940515716785753,
"learning_rate": 4.997033138928056e-05,
"loss": 0.3126,
"step": 103
},
{
"epoch": 0.06656,
"grad_norm": 0.4356254674524969,
"learning_rate": 4.996769599357927e-05,
"loss": 0.3079,
"step": 104
},
{
"epoch": 0.0672,
"grad_norm": 0.4485794513852225,
"learning_rate": 4.996494855203493e-05,
"loss": 0.3227,
"step": 105
},
{
"epoch": 0.06784,
"grad_norm": 0.5339271359603054,
"learning_rate": 4.996208907697706e-05,
"loss": 0.3197,
"step": 106
},
{
"epoch": 0.06848,
"grad_norm": 0.47913200680485823,
"learning_rate": 4.995911758123791e-05,
"loss": 0.2829,
"step": 107
},
{
"epoch": 0.06912,
"grad_norm": 0.48619705540043057,
"learning_rate": 4.995603407815249e-05,
"loss": 0.295,
"step": 108
},
{
"epoch": 0.06976,
"grad_norm": 0.44791381540090275,
"learning_rate": 4.9952838581558406e-05,
"loss": 0.3009,
"step": 109
},
{
"epoch": 0.0704,
"grad_norm": 0.4217427510368746,
"learning_rate": 4.994953110579588e-05,
"loss": 0.3124,
"step": 110
},
{
"epoch": 0.07104,
"grad_norm": 0.44605995933104997,
"learning_rate": 4.9946111665707645e-05,
"loss": 0.3232,
"step": 111
},
{
"epoch": 0.07168,
"grad_norm": 0.3580173680896881,
"learning_rate": 4.99425802766389e-05,
"loss": 0.288,
"step": 112
},
{
"epoch": 0.07232,
"grad_norm": 0.4281198427243427,
"learning_rate": 4.993893695443721e-05,
"loss": 0.3008,
"step": 113
},
{
"epoch": 0.07296,
"grad_norm": 0.3748012845273175,
"learning_rate": 4.993518171545247e-05,
"loss": 0.2898,
"step": 114
},
{
"epoch": 0.0736,
"grad_norm": 0.41133247941906176,
"learning_rate": 4.993131457653682e-05,
"loss": 0.3007,
"step": 115
},
{
"epoch": 0.07424,
"grad_norm": 0.4049279526177947,
"learning_rate": 4.992733555504454e-05,
"loss": 0.3156,
"step": 116
},
{
"epoch": 0.07488,
"grad_norm": 0.3907854290589919,
"learning_rate": 4.9923244668832025e-05,
"loss": 0.305,
"step": 117
},
{
"epoch": 0.07552,
"grad_norm": 3.3672297158831523,
"learning_rate": 4.991904193625768e-05,
"loss": 0.3099,
"step": 118
},
{
"epoch": 0.07616,
"grad_norm": 0.45896342700641674,
"learning_rate": 4.991472737618181e-05,
"loss": 0.2766,
"step": 119
},
{
"epoch": 0.0768,
"grad_norm": 0.41249483633287526,
"learning_rate": 4.991030100796659e-05,
"loss": 0.3026,
"step": 120
},
{
"epoch": 0.07744,
"grad_norm": 0.39435147330028136,
"learning_rate": 4.9905762851475915e-05,
"loss": 0.3151,
"step": 121
},
{
"epoch": 0.07808,
"grad_norm": 0.38174217860012233,
"learning_rate": 4.990111292707537e-05,
"loss": 0.3132,
"step": 122
},
{
"epoch": 0.07872,
"grad_norm": 0.4106762400890441,
"learning_rate": 4.989635125563211e-05,
"loss": 0.2883,
"step": 123
},
{
"epoch": 0.07936,
"grad_norm": 0.3777494709551966,
"learning_rate": 4.989147785851477e-05,
"loss": 0.3075,
"step": 124
},
{
"epoch": 0.08,
"grad_norm": 0.3812281839176885,
"learning_rate": 4.988649275759335e-05,
"loss": 0.3173,
"step": 125
},
{
"epoch": 0.08064,
"grad_norm": 0.3800442807387135,
"learning_rate": 4.988139597523916e-05,
"loss": 0.2897,
"step": 126
},
{
"epoch": 0.08128,
"grad_norm": 0.4101363073522896,
"learning_rate": 4.98761875343247e-05,
"loss": 0.2822,
"step": 127
},
{
"epoch": 0.08192,
"grad_norm": 0.3515414786001439,
"learning_rate": 4.987086745822352e-05,
"loss": 0.2831,
"step": 128
},
{
"epoch": 0.08256,
"grad_norm": 0.38143533758711873,
"learning_rate": 4.986543577081017e-05,
"loss": 0.3193,
"step": 129
},
{
"epoch": 0.0832,
"grad_norm": 0.44066201212578954,
"learning_rate": 4.985989249646007e-05,
"loss": 0.3006,
"step": 130
},
{
"epoch": 0.08384,
"grad_norm": 0.3699946189372801,
"learning_rate": 4.985423766004939e-05,
"loss": 0.309,
"step": 131
},
{
"epoch": 0.08448,
"grad_norm": 0.4732003041900607,
"learning_rate": 4.9848471286954965e-05,
"loss": 0.3253,
"step": 132
},
{
"epoch": 0.08512,
"grad_norm": 0.35724915771132804,
"learning_rate": 4.984259340305416e-05,
"loss": 0.2876,
"step": 133
},
{
"epoch": 0.08576,
"grad_norm": 0.39925687072469707,
"learning_rate": 4.9836604034724753e-05,
"loss": 0.2906,
"step": 134
},
{
"epoch": 0.0864,
"grad_norm": 0.43582991089095635,
"learning_rate": 4.9830503208844835e-05,
"loss": 0.2928,
"step": 135
},
{
"epoch": 0.08704,
"grad_norm": 0.3638802742085539,
"learning_rate": 4.982429095279266e-05,
"loss": 0.2924,
"step": 136
},
{
"epoch": 0.08768,
"grad_norm": 0.44414884826796713,
"learning_rate": 4.981796729444655e-05,
"loss": 0.3225,
"step": 137
},
{
"epoch": 0.08832,
"grad_norm": 0.4179539121719692,
"learning_rate": 4.981153226218477e-05,
"loss": 0.3067,
"step": 138
},
{
"epoch": 0.08896,
"grad_norm": 0.3518602463362222,
"learning_rate": 4.9804985884885366e-05,
"loss": 0.2854,
"step": 139
},
{
"epoch": 0.0896,
"grad_norm": 0.4013030661247676,
"learning_rate": 4.979832819192608e-05,
"loss": 0.3113,
"step": 140
},
{
"epoch": 0.09024,
"grad_norm": 0.3700912839771966,
"learning_rate": 4.97915592131842e-05,
"loss": 0.2873,
"step": 141
},
{
"epoch": 0.09088,
"grad_norm": 0.41429834446700914,
"learning_rate": 4.97846789790364e-05,
"loss": 0.3064,
"step": 142
},
{
"epoch": 0.09152,
"grad_norm": 0.3743350290044281,
"learning_rate": 4.977768752035865e-05,
"loss": 0.311,
"step": 143
},
{
"epoch": 0.09216,
"grad_norm": 0.4436631708270473,
"learning_rate": 4.9770584868526046e-05,
"loss": 0.3105,
"step": 144
},
{
"epoch": 0.0928,
"grad_norm": 0.4341903366251428,
"learning_rate": 4.9763371055412685e-05,
"loss": 0.307,
"step": 145
},
{
"epoch": 0.09344,
"grad_norm": 0.4147022361169306,
"learning_rate": 4.9756046113391496e-05,
"loss": 0.3288,
"step": 146
},
{
"epoch": 0.09408,
"grad_norm": 0.3884970059580215,
"learning_rate": 4.974861007533413e-05,
"loss": 0.2847,
"step": 147
},
{
"epoch": 0.09472,
"grad_norm": 0.4258271028958422,
"learning_rate": 4.97410629746108e-05,
"loss": 0.2908,
"step": 148
},
{
"epoch": 0.09536,
"grad_norm": 0.41527352386736543,
"learning_rate": 4.9733404845090116e-05,
"loss": 0.2828,
"step": 149
},
{
"epoch": 0.096,
"grad_norm": 0.41352693469232554,
"learning_rate": 4.972563572113894e-05,
"loss": 0.2895,
"step": 150
},
{
"epoch": 0.09664,
"grad_norm": 0.4391732737160089,
"learning_rate": 4.971775563762226e-05,
"loss": 0.2908,
"step": 151
},
{
"epoch": 0.09728,
"grad_norm": 0.42637768991672836,
"learning_rate": 4.970976462990299e-05,
"loss": 0.3103,
"step": 152
},
{
"epoch": 0.09792,
"grad_norm": 0.38123935717217666,
"learning_rate": 4.970166273384183e-05,
"loss": 0.2859,
"step": 153
},
{
"epoch": 0.09856,
"grad_norm": 0.3432072306652636,
"learning_rate": 4.969344998579712e-05,
"loss": 0.2653,
"step": 154
},
{
"epoch": 0.0992,
"grad_norm": 0.38378318854854493,
"learning_rate": 4.9685126422624644e-05,
"loss": 0.3135,
"step": 155
},
{
"epoch": 0.09984,
"grad_norm": 0.3871767364493639,
"learning_rate": 4.96766920816775e-05,
"loss": 0.3129,
"step": 156
},
{
"epoch": 0.10048,
"grad_norm": 0.361665333999729,
"learning_rate": 4.966814700080592e-05,
"loss": 0.3175,
"step": 157
},
{
"epoch": 0.10112,
"grad_norm": 0.394466639141269,
"learning_rate": 4.965949121835707e-05,
"loss": 0.333,
"step": 158
},
{
"epoch": 0.10176,
"grad_norm": 0.396292343881353,
"learning_rate": 4.965072477317493e-05,
"loss": 0.3084,
"step": 159
},
{
"epoch": 0.1024,
"grad_norm": 0.3468981265806776,
"learning_rate": 4.964184770460007e-05,
"loss": 0.2927,
"step": 160
},
{
"epoch": 0.10304,
"grad_norm": 0.39865168519337385,
"learning_rate": 4.963286005246953e-05,
"loss": 0.2815,
"step": 161
},
{
"epoch": 0.10368,
"grad_norm": 0.37451640530098157,
"learning_rate": 4.9623761857116594e-05,
"loss": 0.3188,
"step": 162
},
{
"epoch": 0.10432,
"grad_norm": 0.37483826123841657,
"learning_rate": 4.961455315937059e-05,
"loss": 0.2813,
"step": 163
},
{
"epoch": 0.10496,
"grad_norm": 0.33130533329924106,
"learning_rate": 4.960523400055679e-05,
"loss": 0.2924,
"step": 164
},
{
"epoch": 0.1056,
"grad_norm": 0.3364997696428208,
"learning_rate": 4.959580442249615e-05,
"loss": 0.3001,
"step": 165
},
{
"epoch": 0.10624,
"grad_norm": 0.3183485250122132,
"learning_rate": 4.958626446750515e-05,
"loss": 0.3195,
"step": 166
},
{
"epoch": 0.10688,
"grad_norm": 0.3417933668875517,
"learning_rate": 4.9576614178395595e-05,
"loss": 0.2991,
"step": 167
},
{
"epoch": 0.10752,
"grad_norm": 0.3487109852934047,
"learning_rate": 4.956685359847445e-05,
"loss": 0.2959,
"step": 168
},
{
"epoch": 0.10816,
"grad_norm": 0.31315058374358634,
"learning_rate": 4.95569827715436e-05,
"loss": 0.2799,
"step": 169
},
{
"epoch": 0.1088,
"grad_norm": 0.35913320358975465,
"learning_rate": 4.9547001741899693e-05,
"loss": 0.297,
"step": 170
},
{
"epoch": 0.10944,
"grad_norm": 0.3331478821334656,
"learning_rate": 4.953691055433391e-05,
"loss": 0.2901,
"step": 171
},
{
"epoch": 0.11008,
"grad_norm": 0.39224813006559756,
"learning_rate": 4.952670925413182e-05,
"loss": 0.3026,
"step": 172
},
{
"epoch": 0.11072,
"grad_norm": 0.3480414792318722,
"learning_rate": 4.951639788707307e-05,
"loss": 0.2845,
"step": 173
},
{
"epoch": 0.11136,
"grad_norm": 0.34970614984057585,
"learning_rate": 4.950597649943132e-05,
"loss": 0.2775,
"step": 174
},
{
"epoch": 0.112,
"grad_norm": 0.347207358588287,
"learning_rate": 4.9495445137973905e-05,
"loss": 0.2923,
"step": 175
},
{
"epoch": 0.11264,
"grad_norm": 0.34884090954360897,
"learning_rate": 4.948480384996172e-05,
"loss": 0.2862,
"step": 176
},
{
"epoch": 0.11328,
"grad_norm": 0.32979237586574495,
"learning_rate": 4.947405268314894e-05,
"loss": 0.2983,
"step": 177
},
{
"epoch": 0.11392,
"grad_norm": 0.43991275496703847,
"learning_rate": 4.9463191685782865e-05,
"loss": 0.3068,
"step": 178
},
{
"epoch": 0.11456,
"grad_norm": 0.3039302314073942,
"learning_rate": 4.945222090660364e-05,
"loss": 0.2841,
"step": 179
},
{
"epoch": 0.1152,
"grad_norm": 0.38589337384034356,
"learning_rate": 4.944114039484411e-05,
"loss": 0.3091,
"step": 180
},
{
"epoch": 0.11584,
"grad_norm": 0.34105198100381573,
"learning_rate": 4.942995020022954e-05,
"loss": 0.3228,
"step": 181
},
{
"epoch": 0.11648,
"grad_norm": 0.34780611263986955,
"learning_rate": 4.9418650372977384e-05,
"loss": 0.2874,
"step": 182
},
{
"epoch": 0.11712,
"grad_norm": 0.32541445621708004,
"learning_rate": 4.940724096379714e-05,
"loss": 0.282,
"step": 183
},
{
"epoch": 0.11776,
"grad_norm": 0.3082894269244735,
"learning_rate": 4.9395722023890035e-05,
"loss": 0.2799,
"step": 184
},
{
"epoch": 0.1184,
"grad_norm": 0.32812745331187065,
"learning_rate": 4.938409360494883e-05,
"loss": 0.2827,
"step": 185
},
{
"epoch": 0.11904,
"grad_norm": 0.34755898651365463,
"learning_rate": 4.937235575915761e-05,
"loss": 0.2917,
"step": 186
},
{
"epoch": 0.11968,
"grad_norm": 0.3413504764617461,
"learning_rate": 4.93605085391915e-05,
"loss": 0.2918,
"step": 187
},
{
"epoch": 0.12032,
"grad_norm": 0.3705985820501455,
"learning_rate": 4.934855199821647e-05,
"loss": 0.2826,
"step": 188
},
{
"epoch": 0.12096,
"grad_norm": 0.3414000814514884,
"learning_rate": 4.93364861898891e-05,
"loss": 0.276,
"step": 189
},
{
"epoch": 0.1216,
"grad_norm": 0.3589734824395955,
"learning_rate": 4.932431116835628e-05,
"loss": 0.2959,
"step": 190
},
{
"epoch": 0.12224,
"grad_norm": 0.345670488984043,
"learning_rate": 4.931202698825503e-05,
"loss": 0.281,
"step": 191
},
{
"epoch": 0.12288,
"grad_norm": 0.3235692312545686,
"learning_rate": 4.929963370471226e-05,
"loss": 0.2886,
"step": 192
},
{
"epoch": 0.12352,
"grad_norm": 0.3034427958798936,
"learning_rate": 4.928713137334445e-05,
"loss": 0.2812,
"step": 193
},
{
"epoch": 0.12416,
"grad_norm": 0.34712496586477004,
"learning_rate": 4.927452005025748e-05,
"loss": 0.3018,
"step": 194
},
{
"epoch": 0.1248,
"grad_norm": 0.3222467927855389,
"learning_rate": 4.926179979204633e-05,
"loss": 0.3023,
"step": 195
},
{
"epoch": 0.12544,
"grad_norm": 0.3243348951725544,
"learning_rate": 4.9248970655794836e-05,
"loss": 0.2917,
"step": 196
},
{
"epoch": 0.12608,
"grad_norm": 0.3096795363251828,
"learning_rate": 4.923603269907545e-05,
"loss": 0.2737,
"step": 197
},
{
"epoch": 0.12672,
"grad_norm": 0.31152060487499617,
"learning_rate": 4.922298597994897e-05,
"loss": 0.2828,
"step": 198
},
{
"epoch": 0.12736,
"grad_norm": 0.3405465489598549,
"learning_rate": 4.920983055696428e-05,
"loss": 0.2927,
"step": 199
},
{
"epoch": 0.128,
"grad_norm": 0.3423946912166355,
"learning_rate": 4.919656648915807e-05,
"loss": 0.2835,
"step": 200
},
{
"epoch": 0.12864,
"grad_norm": 0.3464727040800733,
"learning_rate": 4.918319383605462e-05,
"loss": 0.2575,
"step": 201
},
{
"epoch": 0.12928,
"grad_norm": 0.3620779326329196,
"learning_rate": 4.916971265766547e-05,
"loss": 0.2944,
"step": 202
},
{
"epoch": 0.12992,
"grad_norm": 0.3699616777622434,
"learning_rate": 4.915612301448919e-05,
"loss": 0.2942,
"step": 203
},
{
"epoch": 0.13056,
"grad_norm": 0.38798124559835534,
"learning_rate": 4.914242496751111e-05,
"loss": 0.2882,
"step": 204
},
{
"epoch": 0.1312,
"grad_norm": 0.4306348775923099,
"learning_rate": 4.912861857820303e-05,
"loss": 0.3026,
"step": 205
},
{
"epoch": 0.13184,
"grad_norm": 0.37275998073469474,
"learning_rate": 4.911470390852295e-05,
"loss": 0.3008,
"step": 206
},
{
"epoch": 0.13248,
"grad_norm": 0.33076859723493407,
"learning_rate": 4.91006810209148e-05,
"loss": 0.2881,
"step": 207
},
{
"epoch": 0.13312,
"grad_norm": 0.38285708110841127,
"learning_rate": 4.9086549978308125e-05,
"loss": 0.299,
"step": 208
},
{
"epoch": 0.13376,
"grad_norm": 0.3130925296009032,
"learning_rate": 4.9072310844117875e-05,
"loss": 0.2714,
"step": 209
},
{
"epoch": 0.1344,
"grad_norm": 0.3556404363171034,
"learning_rate": 4.9057963682244045e-05,
"loss": 0.291,
"step": 210
},
{
"epoch": 0.13504,
"grad_norm": 0.33759319834147206,
"learning_rate": 4.904350855707142e-05,
"loss": 0.2868,
"step": 211
},
{
"epoch": 0.13568,
"grad_norm": 0.3171722280640699,
"learning_rate": 4.9028945533469276e-05,
"loss": 0.2646,
"step": 212
},
{
"epoch": 0.13632,
"grad_norm": 0.39240914087101075,
"learning_rate": 4.9014274676791134e-05,
"loss": 0.302,
"step": 213
},
{
"epoch": 0.13696,
"grad_norm": 0.34184628116877047,
"learning_rate": 4.899949605287439e-05,
"loss": 0.2792,
"step": 214
},
{
"epoch": 0.1376,
"grad_norm": 0.3700664187254164,
"learning_rate": 4.898460972804009e-05,
"loss": 0.3088,
"step": 215
},
{
"epoch": 0.13824,
"grad_norm": 0.36421921549881453,
"learning_rate": 4.896961576909258e-05,
"loss": 0.2808,
"step": 216
},
{
"epoch": 0.13888,
"grad_norm": 0.3565240796039332,
"learning_rate": 4.895451424331924e-05,
"loss": 0.2714,
"step": 217
},
{
"epoch": 0.13952,
"grad_norm": 0.3396297883795516,
"learning_rate": 4.893930521849016e-05,
"loss": 0.267,
"step": 218
},
{
"epoch": 0.14016,
"grad_norm": 0.39278607376772506,
"learning_rate": 4.892398876285785e-05,
"loss": 0.2896,
"step": 219
},
{
"epoch": 0.1408,
"grad_norm": 0.38437399542076783,
"learning_rate": 4.890856494515696e-05,
"loss": 0.2875,
"step": 220
},
{
"epoch": 0.14144,
"grad_norm": 0.37920192384172824,
"learning_rate": 4.889303383460389e-05,
"loss": 0.2806,
"step": 221
},
{
"epoch": 0.14208,
"grad_norm": 0.35504283495161315,
"learning_rate": 4.887739550089656e-05,
"loss": 0.2781,
"step": 222
},
{
"epoch": 0.14272,
"grad_norm": 0.3866107761723795,
"learning_rate": 4.886165001421408e-05,
"loss": 0.3091,
"step": 223
},
{
"epoch": 0.14336,
"grad_norm": 0.30439690273605985,
"learning_rate": 4.884579744521638e-05,
"loss": 0.2842,
"step": 224
},
{
"epoch": 0.144,
"grad_norm": 0.3551417352689114,
"learning_rate": 4.8829837865043984e-05,
"loss": 0.2909,
"step": 225
},
{
"epoch": 0.14464,
"grad_norm": 0.309111612445454,
"learning_rate": 4.881377134531762e-05,
"loss": 0.268,
"step": 226
},
{
"epoch": 0.14528,
"grad_norm": 0.3282993602648903,
"learning_rate": 4.8797597958137914e-05,
"loss": 0.28,
"step": 227
},
{
"epoch": 0.14592,
"grad_norm": 0.3581890513495606,
"learning_rate": 4.878131777608509e-05,
"loss": 0.2842,
"step": 228
},
{
"epoch": 0.14656,
"grad_norm": 0.32315603560305584,
"learning_rate": 4.876493087221862e-05,
"loss": 0.2961,
"step": 229
},
{
"epoch": 0.1472,
"grad_norm": 0.33067996529729515,
"learning_rate": 4.87484373200769e-05,
"loss": 0.2891,
"step": 230
},
{
"epoch": 0.14784,
"grad_norm": 0.3178546016599421,
"learning_rate": 4.8731837193676944e-05,
"loss": 0.2781,
"step": 231
},
{
"epoch": 0.14848,
"grad_norm": 0.3414289060571217,
"learning_rate": 4.871513056751401e-05,
"loss": 0.2983,
"step": 232
},
{
"epoch": 0.14912,
"grad_norm": 0.3420355616767074,
"learning_rate": 4.8698317516561295e-05,
"loss": 0.2987,
"step": 233
},
{
"epoch": 0.14976,
"grad_norm": 0.347117902288678,
"learning_rate": 4.8681398116269596e-05,
"loss": 0.2857,
"step": 234
},
{
"epoch": 0.1504,
"grad_norm": 0.31648517023684664,
"learning_rate": 4.8664372442566954e-05,
"loss": 0.2921,
"step": 235
},
{
"epoch": 0.15104,
"grad_norm": 0.3308519821164363,
"learning_rate": 4.864724057185834e-05,
"loss": 0.2672,
"step": 236
},
{
"epoch": 0.15168,
"grad_norm": 0.31208238851833453,
"learning_rate": 4.86300025810253e-05,
"loss": 0.2798,
"step": 237
},
{
"epoch": 0.15232,
"grad_norm": 0.2945629591271816,
"learning_rate": 4.861265854742559e-05,
"loss": 0.2732,
"step": 238
},
{
"epoch": 0.15296,
"grad_norm": 0.3383764371143183,
"learning_rate": 4.859520854889287e-05,
"loss": 0.2923,
"step": 239
},
{
"epoch": 0.1536,
"grad_norm": 0.2935231514068793,
"learning_rate": 4.857765266373631e-05,
"loss": 0.2945,
"step": 240
},
{
"epoch": 0.15424,
"grad_norm": 0.3265200869108488,
"learning_rate": 4.855999097074027e-05,
"loss": 0.2925,
"step": 241
},
{
"epoch": 0.15488,
"grad_norm": 0.301565323998506,
"learning_rate": 4.8542223549163946e-05,
"loss": 0.271,
"step": 242
},
{
"epoch": 0.15552,
"grad_norm": 0.3121729061732836,
"learning_rate": 4.8524350478740985e-05,
"loss": 0.266,
"step": 243
},
{
"epoch": 0.15616,
"grad_norm": 0.3612945591439241,
"learning_rate": 4.850637183967917e-05,
"loss": 0.2825,
"step": 244
},
{
"epoch": 0.1568,
"grad_norm": 0.32526112140366076,
"learning_rate": 4.848828771266002e-05,
"loss": 0.2875,
"step": 245
},
{
"epoch": 0.15744,
"grad_norm": 0.3724034080949958,
"learning_rate": 4.847009817883844e-05,
"loss": 0.2829,
"step": 246
},
{
"epoch": 0.15808,
"grad_norm": 0.31233652215083263,
"learning_rate": 4.845180331984239e-05,
"loss": 0.2713,
"step": 247
},
{
"epoch": 0.15872,
"grad_norm": 0.3480570732169317,
"learning_rate": 4.843340321777246e-05,
"loss": 0.2641,
"step": 248
},
{
"epoch": 0.15936,
"grad_norm": 0.320447396199795,
"learning_rate": 4.8414897955201556e-05,
"loss": 0.261,
"step": 249
},
{
"epoch": 0.16,
"grad_norm": 0.30011124568595027,
"learning_rate": 4.8396287615174484e-05,
"loss": 0.2566,
"step": 250
},
{
"epoch": 0.16064,
"grad_norm": 0.3416591207698499,
"learning_rate": 4.837757228120762e-05,
"loss": 0.2886,
"step": 251
},
{
"epoch": 0.16128,
"grad_norm": 0.3347844484474534,
"learning_rate": 4.835875203728849e-05,
"loss": 0.2546,
"step": 252
},
{
"epoch": 0.16192,
"grad_norm": 0.3805038941147735,
"learning_rate": 4.8339826967875443e-05,
"loss": 0.2867,
"step": 253
},
{
"epoch": 0.16256,
"grad_norm": 0.36899369410322225,
"learning_rate": 4.832079715789724e-05,
"loss": 0.2969,
"step": 254
},
{
"epoch": 0.1632,
"grad_norm": 0.3671046083988311,
"learning_rate": 4.830166269275267e-05,
"loss": 0.2903,
"step": 255
},
{
"epoch": 0.16384,
"grad_norm": 0.3268166037896424,
"learning_rate": 4.828242365831016e-05,
"loss": 0.2744,
"step": 256
},
{
"epoch": 0.16448,
"grad_norm": 0.38930768380996184,
"learning_rate": 4.8263080140907455e-05,
"loss": 0.2898,
"step": 257
},
{
"epoch": 0.16512,
"grad_norm": 0.3527164726419632,
"learning_rate": 4.824363222735114e-05,
"loss": 0.2751,
"step": 258
},
{
"epoch": 0.16576,
"grad_norm": 0.3831694490194351,
"learning_rate": 4.82240800049163e-05,
"loss": 0.2797,
"step": 259
},
{
"epoch": 0.1664,
"grad_norm": 0.39066664017067054,
"learning_rate": 4.820442356134612e-05,
"loss": 0.2716,
"step": 260
},
{
"epoch": 0.16704,
"grad_norm": 0.36528936400377576,
"learning_rate": 4.8184662984851505e-05,
"loss": 0.3001,
"step": 261
},
{
"epoch": 0.16768,
"grad_norm": 0.3720797744652676,
"learning_rate": 4.816479836411065e-05,
"loss": 0.2819,
"step": 262
},
{
"epoch": 0.16832,
"grad_norm": 0.4121620669424255,
"learning_rate": 4.8144829788268674e-05,
"loss": 0.2951,
"step": 263
},
{
"epoch": 0.16896,
"grad_norm": 0.3687003642746144,
"learning_rate": 4.8124757346937214e-05,
"loss": 0.2637,
"step": 264
},
{
"epoch": 0.1696,
"grad_norm": 0.3380727248902014,
"learning_rate": 4.810458113019401e-05,
"loss": 0.2749,
"step": 265
},
{
"epoch": 0.17024,
"grad_norm": 0.3295868074806808,
"learning_rate": 4.8084301228582485e-05,
"loss": 0.2579,
"step": 266
},
{
"epoch": 0.17088,
"grad_norm": 0.37764930926091167,
"learning_rate": 4.8063917733111406e-05,
"loss": 0.3095,
"step": 267
},
{
"epoch": 0.17152,
"grad_norm": 0.3403308904612826,
"learning_rate": 4.8043430735254404e-05,
"loss": 0.2806,
"step": 268
},
{
"epoch": 0.17216,
"grad_norm": 0.36741715154564875,
"learning_rate": 4.8022840326949595e-05,
"loss": 0.2806,
"step": 269
},
{
"epoch": 0.1728,
"grad_norm": 0.3915206701251456,
"learning_rate": 4.800214660059916e-05,
"loss": 0.2789,
"step": 270
},
{
"epoch": 0.17344,
"grad_norm": 0.3396593508328933,
"learning_rate": 4.798134964906894e-05,
"loss": 0.2865,
"step": 271
},
{
"epoch": 0.17408,
"grad_norm": 0.3711393932873003,
"learning_rate": 4.7960449565688e-05,
"loss": 0.263,
"step": 272
},
{
"epoch": 0.17472,
"grad_norm": 0.3481318617474482,
"learning_rate": 4.793944644424826e-05,
"loss": 0.285,
"step": 273
},
{
"epoch": 0.17536,
"grad_norm": 0.36766456982327766,
"learning_rate": 4.7918340379003985e-05,
"loss": 0.2872,
"step": 274
},
{
"epoch": 0.176,
"grad_norm": 0.3322741327391994,
"learning_rate": 4.7897131464671444e-05,
"loss": 0.2997,
"step": 275
},
{
"epoch": 0.17664,
"grad_norm": 0.3658059319194032,
"learning_rate": 4.787581979642845e-05,
"loss": 0.2557,
"step": 276
},
{
"epoch": 0.17728,
"grad_norm": 0.3273286462475089,
"learning_rate": 4.7854405469913944e-05,
"loss": 0.273,
"step": 277
},
{
"epoch": 0.17792,
"grad_norm": 0.3111759107193226,
"learning_rate": 4.7832888581227545e-05,
"loss": 0.2756,
"step": 278
},
{
"epoch": 0.17856,
"grad_norm": 0.3412050823331732,
"learning_rate": 4.7811269226929135e-05,
"loss": 0.2788,
"step": 279
},
{
"epoch": 0.1792,
"grad_norm": 0.34902342482932425,
"learning_rate": 4.7789547504038443e-05,
"loss": 0.269,
"step": 280
},
{
"epoch": 0.17984,
"grad_norm": 0.33701110337193746,
"learning_rate": 4.776772351003458e-05,
"loss": 0.2801,
"step": 281
},
{
"epoch": 0.18048,
"grad_norm": 0.34838767763355505,
"learning_rate": 4.774579734285559e-05,
"loss": 0.2872,
"step": 282
},
{
"epoch": 0.18112,
"grad_norm": 0.3268119544044272,
"learning_rate": 4.772376910089808e-05,
"loss": 0.2781,
"step": 283
},
{
"epoch": 0.18176,
"grad_norm": 0.3260714138226823,
"learning_rate": 4.770163888301668e-05,
"loss": 0.2696,
"step": 284
},
{
"epoch": 0.1824,
"grad_norm": 0.3263806440232551,
"learning_rate": 4.7679406788523685e-05,
"loss": 0.277,
"step": 285
},
{
"epoch": 0.18304,
"grad_norm": 0.3048596244321711,
"learning_rate": 4.765707291718856e-05,
"loss": 0.2748,
"step": 286
},
{
"epoch": 0.18368,
"grad_norm": 0.33173051881106563,
"learning_rate": 4.7634637369237526e-05,
"loss": 0.2765,
"step": 287
},
{
"epoch": 0.18432,
"grad_norm": 0.34287198001014474,
"learning_rate": 4.7612100245353045e-05,
"loss": 0.2865,
"step": 288
},
{
"epoch": 0.18496,
"grad_norm": 0.3273490271016689,
"learning_rate": 4.758946164667347e-05,
"loss": 0.2905,
"step": 289
},
{
"epoch": 0.1856,
"grad_norm": 0.3587640664765252,
"learning_rate": 4.7566721674792515e-05,
"loss": 0.2776,
"step": 290
},
{
"epoch": 0.18624,
"grad_norm": 0.31221104587356835,
"learning_rate": 4.7543880431758805e-05,
"loss": 0.2779,
"step": 291
},
{
"epoch": 0.18688,
"grad_norm": 0.30655584340609615,
"learning_rate": 4.752093802007543e-05,
"loss": 0.3008,
"step": 292
},
{
"epoch": 0.18752,
"grad_norm": 0.3017825263683308,
"learning_rate": 4.7497894542699534e-05,
"loss": 0.2607,
"step": 293
},
{
"epoch": 0.18816,
"grad_norm": 0.3262092930986735,
"learning_rate": 4.747475010304175e-05,
"loss": 0.2792,
"step": 294
},
{
"epoch": 0.1888,
"grad_norm": 0.2931602837859308,
"learning_rate": 4.745150480496583e-05,
"loss": 0.2965,
"step": 295
},
{
"epoch": 0.18944,
"grad_norm": 0.31963993149008735,
"learning_rate": 4.742815875278811e-05,
"loss": 0.2955,
"step": 296
},
{
"epoch": 0.19008,
"grad_norm": 0.3325849928268489,
"learning_rate": 4.7404712051277115e-05,
"loss": 0.2552,
"step": 297
},
{
"epoch": 0.19072,
"grad_norm": 0.34547053393459853,
"learning_rate": 4.738116480565301e-05,
"loss": 0.2944,
"step": 298
},
{
"epoch": 0.19136,
"grad_norm": 0.3085593082553946,
"learning_rate": 4.7357517121587183e-05,
"loss": 0.2778,
"step": 299
},
{
"epoch": 0.192,
"grad_norm": 0.31353055101488136,
"learning_rate": 4.7333769105201735e-05,
"loss": 0.2429,
"step": 300
},
{
"epoch": 0.19264,
"grad_norm": 0.31858274733561903,
"learning_rate": 4.730992086306906e-05,
"loss": 0.2829,
"step": 301
},
{
"epoch": 0.19328,
"grad_norm": 0.30709940331794794,
"learning_rate": 4.728597250221129e-05,
"loss": 0.2829,
"step": 302
},
{
"epoch": 0.19392,
"grad_norm": 0.32244914176650474,
"learning_rate": 4.726192413009986e-05,
"loss": 0.2951,
"step": 303
},
{
"epoch": 0.19456,
"grad_norm": 0.3227593884616251,
"learning_rate": 4.723777585465503e-05,
"loss": 0.2926,
"step": 304
},
{
"epoch": 0.1952,
"grad_norm": 0.3283415364290106,
"learning_rate": 4.7213527784245395e-05,
"loss": 0.2761,
"step": 305
},
{
"epoch": 0.19584,
"grad_norm": 0.3015938328335281,
"learning_rate": 4.718918002768738e-05,
"loss": 0.2762,
"step": 306
},
{
"epoch": 0.19648,
"grad_norm": 0.29949328240066386,
"learning_rate": 4.716473269424476e-05,
"loss": 0.2832,
"step": 307
},
{
"epoch": 0.19712,
"grad_norm": 0.3035478548839789,
"learning_rate": 4.714018589362818e-05,
"loss": 0.3102,
"step": 308
},
{
"epoch": 0.19776,
"grad_norm": 0.27507230052380166,
"learning_rate": 4.7115539735994666e-05,
"loss": 0.2732,
"step": 309
},
{
"epoch": 0.1984,
"grad_norm": 0.3311299038598881,
"learning_rate": 4.709079433194712e-05,
"loss": 0.2766,
"step": 310
},
{
"epoch": 0.19904,
"grad_norm": 0.37577322279526276,
"learning_rate": 4.7065949792533804e-05,
"loss": 0.2562,
"step": 311
},
{
"epoch": 0.19968,
"grad_norm": 0.38289115818879554,
"learning_rate": 4.70410062292479e-05,
"loss": 0.2932,
"step": 312
},
{
"epoch": 0.20032,
"grad_norm": 0.30727362022005966,
"learning_rate": 4.701596375402694e-05,
"loss": 0.2918,
"step": 313
},
{
"epoch": 0.20096,
"grad_norm": 0.5661606421554864,
"learning_rate": 4.699082247925234e-05,
"loss": 0.3,
"step": 314
},
{
"epoch": 0.2016,
"grad_norm": 0.3276893965611005,
"learning_rate": 4.6965582517748923e-05,
"loss": 0.2932,
"step": 315
},
{
"epoch": 0.20224,
"grad_norm": 0.3022909698773883,
"learning_rate": 4.694024398278434e-05,
"loss": 0.2889,
"step": 316
},
{
"epoch": 0.20288,
"grad_norm": 0.33933254250674033,
"learning_rate": 4.691480698806864e-05,
"loss": 0.3001,
"step": 317
},
{
"epoch": 0.20352,
"grad_norm": 0.2824673534404734,
"learning_rate": 4.6889271647753694e-05,
"loss": 0.2638,
"step": 318
},
{
"epoch": 0.20416,
"grad_norm": 0.3226521796493832,
"learning_rate": 4.686363807643272e-05,
"loss": 0.2565,
"step": 319
},
{
"epoch": 0.2048,
"grad_norm": 0.32498560490845607,
"learning_rate": 4.683790638913979e-05,
"loss": 0.2999,
"step": 320
},
{
"epoch": 0.20544,
"grad_norm": 0.3014466505484606,
"learning_rate": 4.681207670134923e-05,
"loss": 0.2852,
"step": 321
},
{
"epoch": 0.20608,
"grad_norm": 0.29666058601485484,
"learning_rate": 4.6786149128975196e-05,
"loss": 0.2779,
"step": 322
},
{
"epoch": 0.20672,
"grad_norm": 0.30132965740306905,
"learning_rate": 4.6760123788371114e-05,
"loss": 0.2824,
"step": 323
},
{
"epoch": 0.20736,
"grad_norm": 0.31127978685588065,
"learning_rate": 4.6734000796329125e-05,
"loss": 0.2847,
"step": 324
},
{
"epoch": 0.208,
"grad_norm": 0.29058258855782604,
"learning_rate": 4.670778027007964e-05,
"loss": 0.2971,
"step": 325
},
{
"epoch": 0.20864,
"grad_norm": 0.36291904279248527,
"learning_rate": 4.6681462327290725e-05,
"loss": 0.2675,
"step": 326
},
{
"epoch": 0.20928,
"grad_norm": 0.3079346495438994,
"learning_rate": 4.6655047086067636e-05,
"loss": 0.2788,
"step": 327
},
{
"epoch": 0.20992,
"grad_norm": 0.31244911680380855,
"learning_rate": 4.662853466495229e-05,
"loss": 0.271,
"step": 328
},
{
"epoch": 0.21056,
"grad_norm": 0.2892209625632523,
"learning_rate": 4.660192518292266e-05,
"loss": 0.27,
"step": 329
},
{
"epoch": 0.2112,
"grad_norm": 0.31939496738148104,
"learning_rate": 4.6575218759392336e-05,
"loss": 0.2698,
"step": 330
},
{
"epoch": 0.21184,
"grad_norm": 0.2982207659870602,
"learning_rate": 4.654841551420993e-05,
"loss": 0.2588,
"step": 331
},
{
"epoch": 0.21248,
"grad_norm": 0.3016620161751348,
"learning_rate": 4.6521515567658557e-05,
"loss": 0.2674,
"step": 332
},
{
"epoch": 0.21312,
"grad_norm": 0.33353697727099657,
"learning_rate": 4.6494519040455275e-05,
"loss": 0.2811,
"step": 333
},
{
"epoch": 0.21376,
"grad_norm": 0.2950010715216195,
"learning_rate": 4.6467426053750596e-05,
"loss": 0.2629,
"step": 334
},
{
"epoch": 0.2144,
"grad_norm": 0.3033055413044891,
"learning_rate": 4.644023672912788e-05,
"loss": 0.2774,
"step": 335
},
{
"epoch": 0.21504,
"grad_norm": 0.3008702820111445,
"learning_rate": 4.641295118860281e-05,
"loss": 0.2864,
"step": 336
},
{
"epoch": 0.21568,
"grad_norm": 0.26879685510955026,
"learning_rate": 4.638556955462289e-05,
"loss": 0.2597,
"step": 337
},
{
"epoch": 0.21632,
"grad_norm": 0.3532124447567259,
"learning_rate": 4.635809195006681e-05,
"loss": 0.2897,
"step": 338
},
{
"epoch": 0.21696,
"grad_norm": 0.31251314292012317,
"learning_rate": 4.633051849824396e-05,
"loss": 0.2571,
"step": 339
},
{
"epoch": 0.2176,
"grad_norm": 0.34552541821349914,
"learning_rate": 4.630284932289386e-05,
"loss": 0.2835,
"step": 340
},
{
"epoch": 0.21824,
"grad_norm": 0.32731628909864535,
"learning_rate": 4.6275084548185605e-05,
"loss": 0.2939,
"step": 341
},
{
"epoch": 0.21888,
"grad_norm": 0.32841586223389657,
"learning_rate": 4.6247224298717294e-05,
"loss": 0.2547,
"step": 342
},
{
"epoch": 0.21952,
"grad_norm": 0.30505092898032665,
"learning_rate": 4.621926869951549e-05,
"loss": 0.2452,
"step": 343
},
{
"epoch": 0.22016,
"grad_norm": 0.410868336628806,
"learning_rate": 4.619121787603464e-05,
"loss": 0.2757,
"step": 344
},
{
"epoch": 0.2208,
"grad_norm": 0.30578794712173124,
"learning_rate": 4.6163071954156546e-05,
"loss": 0.2756,
"step": 345
},
{
"epoch": 0.22144,
"grad_norm": 0.3180588945483863,
"learning_rate": 4.6134831060189743e-05,
"loss": 0.2817,
"step": 346
},
{
"epoch": 0.22208,
"grad_norm": 0.306137612796177,
"learning_rate": 4.610649532086899e-05,
"loss": 0.2727,
"step": 347
},
{
"epoch": 0.22272,
"grad_norm": 0.33496927815217786,
"learning_rate": 4.607806486335468e-05,
"loss": 0.2885,
"step": 348
},
{
"epoch": 0.22336,
"grad_norm": 0.3034108440418061,
"learning_rate": 4.604953981523225e-05,
"loss": 0.2875,
"step": 349
},
{
"epoch": 0.224,
"grad_norm": 0.30668021026111714,
"learning_rate": 4.602092030451162e-05,
"loss": 0.2695,
"step": 350
},
{
"epoch": 0.22464,
"grad_norm": 0.33000274101961585,
"learning_rate": 4.599220645962665e-05,
"loss": 0.285,
"step": 351
},
{
"epoch": 0.22528,
"grad_norm": 0.29230078568083745,
"learning_rate": 4.596339840943452e-05,
"loss": 0.2678,
"step": 352
},
{
"epoch": 0.22592,
"grad_norm": 0.29979922728628944,
"learning_rate": 4.5934496283215164e-05,
"loss": 0.2669,
"step": 353
},
{
"epoch": 0.22656,
"grad_norm": 0.2754120967287155,
"learning_rate": 4.590550021067072e-05,
"loss": 0.2573,
"step": 354
},
{
"epoch": 0.2272,
"grad_norm": 0.31544489465932246,
"learning_rate": 4.587641032192488e-05,
"loss": 0.2661,
"step": 355
},
{
"epoch": 0.22784,
"grad_norm": 0.3153056590013689,
"learning_rate": 4.58472267475224e-05,
"loss": 0.2808,
"step": 356
},
{
"epoch": 0.22848,
"grad_norm": 0.3283844022151439,
"learning_rate": 4.5817949618428405e-05,
"loss": 0.2674,
"step": 357
},
{
"epoch": 0.22912,
"grad_norm": 0.2988840679235592,
"learning_rate": 4.578857906602791e-05,
"loss": 0.267,
"step": 358
},
{
"epoch": 0.22976,
"grad_norm": 0.3081169219238215,
"learning_rate": 4.575911522212516e-05,
"loss": 0.2842,
"step": 359
},
{
"epoch": 0.2304,
"grad_norm": 0.26927718261630545,
"learning_rate": 4.572955821894305e-05,
"loss": 0.2701,
"step": 360
},
{
"epoch": 0.23104,
"grad_norm": 0.28195917447085084,
"learning_rate": 4.5699908189122556e-05,
"loss": 0.2356,
"step": 361
},
{
"epoch": 0.23168,
"grad_norm": 0.31290690820988126,
"learning_rate": 4.5670165265722096e-05,
"loss": 0.2551,
"step": 362
},
{
"epoch": 0.23232,
"grad_norm": 0.333293969770491,
"learning_rate": 4.5640329582217004e-05,
"loss": 0.2838,
"step": 363
},
{
"epoch": 0.23296,
"grad_norm": 0.322941638451104,
"learning_rate": 4.5610401272498836e-05,
"loss": 0.2544,
"step": 364
},
{
"epoch": 0.2336,
"grad_norm": 0.28399822125645957,
"learning_rate": 4.558038047087486e-05,
"loss": 0.2635,
"step": 365
},
{
"epoch": 0.23424,
"grad_norm": 0.295506533919543,
"learning_rate": 4.555026731206741e-05,
"loss": 0.2482,
"step": 366
},
{
"epoch": 0.23488,
"grad_norm": 0.28684742571759847,
"learning_rate": 4.5520061931213255e-05,
"loss": 0.2789,
"step": 367
},
{
"epoch": 0.23552,
"grad_norm": 0.2736033024469486,
"learning_rate": 4.548976446386305e-05,
"loss": 0.2725,
"step": 368
},
{
"epoch": 0.23616,
"grad_norm": 0.2893642157562684,
"learning_rate": 4.545937504598069e-05,
"loss": 0.2716,
"step": 369
},
{
"epoch": 0.2368,
"grad_norm": 0.27790560741339493,
"learning_rate": 4.5428893813942727e-05,
"loss": 0.2683,
"step": 370
},
{
"epoch": 0.23744,
"grad_norm": 0.26374492858298765,
"learning_rate": 4.539832090453771e-05,
"loss": 0.2652,
"step": 371
},
{
"epoch": 0.23808,
"grad_norm": 0.317165806439944,
"learning_rate": 4.536765645496564e-05,
"loss": 0.2614,
"step": 372
},
{
"epoch": 0.23872,
"grad_norm": 0.2832889981603846,
"learning_rate": 4.533690060283727e-05,
"loss": 0.2655,
"step": 373
},
{
"epoch": 0.23936,
"grad_norm": 0.2835605762763791,
"learning_rate": 4.530605348617357e-05,
"loss": 0.2742,
"step": 374
},
{
"epoch": 0.24,
"grad_norm": 0.30420408773631924,
"learning_rate": 4.527511524340508e-05,
"loss": 0.2644,
"step": 375
},
{
"epoch": 0.24064,
"grad_norm": 0.2969985444201941,
"learning_rate": 4.5244086013371246e-05,
"loss": 0.2638,
"step": 376
},
{
"epoch": 0.24128,
"grad_norm": 0.29308018866051944,
"learning_rate": 4.521296593531985e-05,
"loss": 0.2611,
"step": 377
},
{
"epoch": 0.24192,
"grad_norm": 0.2643945857889153,
"learning_rate": 4.518175514890636e-05,
"loss": 0.265,
"step": 378
},
{
"epoch": 0.24256,
"grad_norm": 0.32678388186327273,
"learning_rate": 4.515045379419332e-05,
"loss": 0.279,
"step": 379
},
{
"epoch": 0.2432,
"grad_norm": 0.2804538570907157,
"learning_rate": 4.5119062011649714e-05,
"loss": 0.2734,
"step": 380
},
{
"epoch": 0.24384,
"grad_norm": 0.3334812457840943,
"learning_rate": 4.508757994215031e-05,
"loss": 0.2811,
"step": 381
},
{
"epoch": 0.24448,
"grad_norm": 0.34946434978677615,
"learning_rate": 4.505600772697507e-05,
"loss": 0.2775,
"step": 382
},
{
"epoch": 0.24512,
"grad_norm": 0.3199621771747357,
"learning_rate": 4.5024345507808495e-05,
"loss": 0.2654,
"step": 383
},
{
"epoch": 0.24576,
"grad_norm": 0.31901998740646675,
"learning_rate": 4.499259342673898e-05,
"loss": 0.2764,
"step": 384
},
{
"epoch": 0.2464,
"grad_norm": 0.29597971799372186,
"learning_rate": 4.4960751626258205e-05,
"loss": 0.263,
"step": 385
},
{
"epoch": 0.24704,
"grad_norm": 0.3404264921907249,
"learning_rate": 4.492882024926046e-05,
"loss": 0.2724,
"step": 386
},
{
"epoch": 0.24768,
"grad_norm": 0.3139861943992207,
"learning_rate": 4.489679943904203e-05,
"loss": 0.2926,
"step": 387
},
{
"epoch": 0.24832,
"grad_norm": 0.2916841972443679,
"learning_rate": 4.486468933930055e-05,
"loss": 0.2799,
"step": 388
},
{
"epoch": 0.24896,
"grad_norm": 0.31153621464751174,
"learning_rate": 4.483249009413433e-05,
"loss": 0.2586,
"step": 389
},
{
"epoch": 0.2496,
"grad_norm": 0.3093059584707331,
"learning_rate": 4.4800201848041765e-05,
"loss": 0.2882,
"step": 390
},
{
"epoch": 0.25024,
"grad_norm": 0.3136725266830641,
"learning_rate": 4.476782474592062e-05,
"loss": 0.2624,
"step": 391
},
{
"epoch": 0.25088,
"grad_norm": 0.29406434454627556,
"learning_rate": 4.473535893306744e-05,
"loss": 0.2688,
"step": 392
},
{
"epoch": 0.25152,
"grad_norm": 0.2875071393783711,
"learning_rate": 4.470280455517687e-05,
"loss": 0.2611,
"step": 393
},
{
"epoch": 0.25216,
"grad_norm": 0.32671818220693416,
"learning_rate": 4.4670161758340966e-05,
"loss": 0.2726,
"step": 394
},
{
"epoch": 0.2528,
"grad_norm": 0.325381652042734,
"learning_rate": 4.4637430689048634e-05,
"loss": 0.2594,
"step": 395
},
{
"epoch": 0.25344,
"grad_norm": 0.3191566413040394,
"learning_rate": 4.460461149418486e-05,
"loss": 0.2553,
"step": 396
},
{
"epoch": 0.25408,
"grad_norm": 0.33203616250805296,
"learning_rate": 4.4571704321030125e-05,
"loss": 0.2898,
"step": 397
},
{
"epoch": 0.25472,
"grad_norm": 0.32044203951382094,
"learning_rate": 4.4538709317259754e-05,
"loss": 0.2471,
"step": 398
},
{
"epoch": 0.25536,
"grad_norm": 0.5990730119683106,
"learning_rate": 4.4505626630943174e-05,
"loss": 0.2879,
"step": 399
},
{
"epoch": 0.256,
"grad_norm": 0.3623407001600211,
"learning_rate": 4.447245641054334e-05,
"loss": 0.2729,
"step": 400
},
{
"epoch": 0.25664,
"grad_norm": 0.3038880359459755,
"learning_rate": 4.443919880491598e-05,
"loss": 0.2531,
"step": 401
},
{
"epoch": 0.25728,
"grad_norm": 0.2900829076508625,
"learning_rate": 4.440585396330904e-05,
"loss": 0.268,
"step": 402
},
{
"epoch": 0.25792,
"grad_norm": 0.31975046352986625,
"learning_rate": 4.437242203536189e-05,
"loss": 0.2714,
"step": 403
},
{
"epoch": 0.25856,
"grad_norm": 0.31641840526539994,
"learning_rate": 4.433890317110475e-05,
"loss": 0.2834,
"step": 404
},
{
"epoch": 0.2592,
"grad_norm": 0.2921767184505357,
"learning_rate": 4.430529752095795e-05,
"loss": 0.2701,
"step": 405
},
{
"epoch": 0.25984,
"grad_norm": 0.2808718335043851,
"learning_rate": 4.427160523573131e-05,
"loss": 0.279,
"step": 406
},
{
"epoch": 0.26048,
"grad_norm": 0.3016336985564651,
"learning_rate": 4.4237826466623406e-05,
"loss": 0.2873,
"step": 407
},
{
"epoch": 0.26112,
"grad_norm": 0.31431578482180944,
"learning_rate": 4.420396136522095e-05,
"loss": 0.2727,
"step": 408
},
{
"epoch": 0.26176,
"grad_norm": 0.27780637237792005,
"learning_rate": 4.417001008349807e-05,
"loss": 0.2579,
"step": 409
},
{
"epoch": 0.2624,
"grad_norm": 0.32993357310014576,
"learning_rate": 4.413597277381564e-05,
"loss": 0.2698,
"step": 410
},
{
"epoch": 0.26304,
"grad_norm": 0.2801299554162777,
"learning_rate": 4.410184958892059e-05,
"loss": 0.2651,
"step": 411
},
{
"epoch": 0.26368,
"grad_norm": 0.29257626461413505,
"learning_rate": 4.4067640681945244e-05,
"loss": 0.2626,
"step": 412
},
{
"epoch": 0.26432,
"grad_norm": 0.3357411211678043,
"learning_rate": 4.403334620640659e-05,
"loss": 0.2605,
"step": 413
},
{
"epoch": 0.26496,
"grad_norm": 0.30154707776244105,
"learning_rate": 4.3998966316205636e-05,
"loss": 0.2534,
"step": 414
},
{
"epoch": 0.2656,
"grad_norm": 0.25345682609356646,
"learning_rate": 4.396450116562669e-05,
"loss": 0.2444,
"step": 415
},
{
"epoch": 0.26624,
"grad_norm": 0.2721282547677732,
"learning_rate": 4.392995090933669e-05,
"loss": 0.2517,
"step": 416
},
{
"epoch": 0.26688,
"grad_norm": 0.28639350362828037,
"learning_rate": 4.389531570238448e-05,
"loss": 0.2416,
"step": 417
},
{
"epoch": 0.26752,
"grad_norm": 0.3414448358787958,
"learning_rate": 4.386059570020015e-05,
"loss": 0.277,
"step": 418
},
{
"epoch": 0.26816,
"grad_norm": 0.26641259434816816,
"learning_rate": 4.382579105859428e-05,
"loss": 0.2737,
"step": 419
},
{
"epoch": 0.2688,
"grad_norm": 0.3117899630025732,
"learning_rate": 4.379090193375735e-05,
"loss": 0.2684,
"step": 420
},
{
"epoch": 0.26944,
"grad_norm": 0.29638243573776074,
"learning_rate": 4.375592848225889e-05,
"loss": 0.2499,
"step": 421
},
{
"epoch": 0.27008,
"grad_norm": 0.28547284987584026,
"learning_rate": 4.372087086104692e-05,
"loss": 0.2767,
"step": 422
},
{
"epoch": 0.27072,
"grad_norm": 0.2997096365805738,
"learning_rate": 4.368572922744715e-05,
"loss": 0.2703,
"step": 423
},
{
"epoch": 0.27136,
"grad_norm": 0.30017436052612945,
"learning_rate": 4.365050373916233e-05,
"loss": 0.2753,
"step": 424
},
{
"epoch": 0.272,
"grad_norm": 0.29858890262572624,
"learning_rate": 4.3615194554271485e-05,
"loss": 0.2337,
"step": 425
},
{
"epoch": 0.27264,
"grad_norm": 0.29100268820291153,
"learning_rate": 4.357980183122927e-05,
"loss": 0.2722,
"step": 426
},
{
"epoch": 0.27328,
"grad_norm": 0.3031136982843706,
"learning_rate": 4.354432572886522e-05,
"loss": 0.2705,
"step": 427
},
{
"epoch": 0.27392,
"grad_norm": 0.27735280662106965,
"learning_rate": 4.3508766406383036e-05,
"loss": 0.2773,
"step": 428
},
{
"epoch": 0.27456,
"grad_norm": 0.287598645255541,
"learning_rate": 4.347312402335989e-05,
"loss": 0.2683,
"step": 429
},
{
"epoch": 0.2752,
"grad_norm": 0.29025080310739393,
"learning_rate": 4.34373987397457e-05,
"loss": 0.2775,
"step": 430
},
{
"epoch": 0.27584,
"grad_norm": 0.27374139232520084,
"learning_rate": 4.340159071586241e-05,
"loss": 0.2447,
"step": 431
},
{
"epoch": 0.27648,
"grad_norm": 0.30499106877780574,
"learning_rate": 4.336570011240326e-05,
"loss": 0.245,
"step": 432
},
{
"epoch": 0.27712,
"grad_norm": 0.2789830538820019,
"learning_rate": 4.33297270904321e-05,
"loss": 0.2667,
"step": 433
},
{
"epoch": 0.27776,
"grad_norm": 0.27918341247404516,
"learning_rate": 4.329367181138262e-05,
"loss": 0.2756,
"step": 434
},
{
"epoch": 0.2784,
"grad_norm": 0.29003519846284037,
"learning_rate": 4.3257534437057674e-05,
"loss": 0.2567,
"step": 435
},
{
"epoch": 0.27904,
"grad_norm": 0.28216675485922665,
"learning_rate": 4.3221315129628506e-05,
"loss": 0.2481,
"step": 436
},
{
"epoch": 0.27968,
"grad_norm": 0.30220665750339526,
"learning_rate": 4.318501405163406e-05,
"loss": 0.2616,
"step": 437
},
{
"epoch": 0.28032,
"grad_norm": 0.2634822858500782,
"learning_rate": 4.314863136598022e-05,
"loss": 0.2462,
"step": 438
},
{
"epoch": 0.28096,
"grad_norm": 0.3161113446906667,
"learning_rate": 4.311216723593913e-05,
"loss": 0.286,
"step": 439
},
{
"epoch": 0.2816,
"grad_norm": 0.3222940745311678,
"learning_rate": 4.307562182514838e-05,
"loss": 0.2609,
"step": 440
},
{
"epoch": 0.28224,
"grad_norm": 0.3187572190375552,
"learning_rate": 4.3038995297610364e-05,
"loss": 0.2478,
"step": 441
},
{
"epoch": 0.28288,
"grad_norm": 0.2928301432408682,
"learning_rate": 4.3002287817691466e-05,
"loss": 0.2855,
"step": 442
},
{
"epoch": 0.28352,
"grad_norm": 0.32965679351152233,
"learning_rate": 4.2965499550121354e-05,
"loss": 0.2682,
"step": 443
},
{
"epoch": 0.28416,
"grad_norm": 0.3349054379926969,
"learning_rate": 4.2928630659992267e-05,
"loss": 0.2708,
"step": 444
},
{
"epoch": 0.2848,
"grad_norm": 0.3409906128958908,
"learning_rate": 4.2891681312758225e-05,
"loss": 0.2589,
"step": 445
},
{
"epoch": 0.28544,
"grad_norm": 0.29301815221408106,
"learning_rate": 4.285465167423432e-05,
"loss": 0.2712,
"step": 446
},
{
"epoch": 0.28608,
"grad_norm": 0.3151776631679768,
"learning_rate": 4.281754191059596e-05,
"loss": 0.2609,
"step": 447
},
{
"epoch": 0.28672,
"grad_norm": 0.3210236670212237,
"learning_rate": 4.278035218837813e-05,
"loss": 0.2877,
"step": 448
},
{
"epoch": 0.28736,
"grad_norm": 0.32717066085861096,
"learning_rate": 4.274308267447463e-05,
"loss": 0.2511,
"step": 449
},
{
"epoch": 0.288,
"grad_norm": 0.30041723762252004,
"learning_rate": 4.270573353613734e-05,
"loss": 0.2697,
"step": 450
},
{
"epoch": 0.28864,
"grad_norm": 0.2806245348619511,
"learning_rate": 4.266830494097546e-05,
"loss": 0.2535,
"step": 451
},
{
"epoch": 0.28928,
"grad_norm": 0.30866632722556286,
"learning_rate": 4.263079705695478e-05,
"loss": 0.2627,
"step": 452
},
{
"epoch": 0.28992,
"grad_norm": 0.3481734862540506,
"learning_rate": 4.2593210052396894e-05,
"loss": 0.2529,
"step": 453
},
{
"epoch": 0.29056,
"grad_norm": 0.3002149800768276,
"learning_rate": 4.255554409597846e-05,
"loss": 0.2446,
"step": 454
},
{
"epoch": 0.2912,
"grad_norm": 0.33721972074704143,
"learning_rate": 4.2517799356730445e-05,
"loss": 0.2682,
"step": 455
},
{
"epoch": 0.29184,
"grad_norm": 0.29436884923501094,
"learning_rate": 4.247997600403737e-05,
"loss": 0.2582,
"step": 456
},
{
"epoch": 0.29248,
"grad_norm": 0.2967220259575209,
"learning_rate": 4.244207420763655e-05,
"loss": 0.2494,
"step": 457
},
{
"epoch": 0.29312,
"grad_norm": 0.2705548005196565,
"learning_rate": 4.240409413761731e-05,
"loss": 0.2545,
"step": 458
},
{
"epoch": 0.29376,
"grad_norm": 0.3046845043984032,
"learning_rate": 4.236603596442023e-05,
"loss": 0.2623,
"step": 459
},
{
"epoch": 0.2944,
"grad_norm": 0.293075805394358,
"learning_rate": 4.232789985883642e-05,
"loss": 0.2692,
"step": 460
},
{
"epoch": 0.29504,
"grad_norm": 0.2934980535483767,
"learning_rate": 4.2289685992006704e-05,
"loss": 0.2768,
"step": 461
},
{
"epoch": 0.29568,
"grad_norm": 0.3000713141045476,
"learning_rate": 4.225139453542087e-05,
"loss": 0.2605,
"step": 462
},
{
"epoch": 0.29632,
"grad_norm": 0.2930768123609869,
"learning_rate": 4.2213025660916904e-05,
"loss": 0.2661,
"step": 463
},
{
"epoch": 0.29696,
"grad_norm": 0.3178121108720456,
"learning_rate": 4.21745795406802e-05,
"loss": 0.2461,
"step": 464
},
{
"epoch": 0.2976,
"grad_norm": 0.26800811778086625,
"learning_rate": 4.2136056347242835e-05,
"loss": 0.2494,
"step": 465
},
{
"epoch": 0.29824,
"grad_norm": 0.3137325849551812,
"learning_rate": 4.209745625348273e-05,
"loss": 0.2839,
"step": 466
},
{
"epoch": 0.29888,
"grad_norm": 0.32102282561988843,
"learning_rate": 4.205877943262291e-05,
"loss": 0.2452,
"step": 467
},
{
"epoch": 0.29952,
"grad_norm": 0.26576307125167287,
"learning_rate": 4.2020026058230756e-05,
"loss": 0.2675,
"step": 468
},
{
"epoch": 0.30016,
"grad_norm": 0.3003922078840633,
"learning_rate": 4.1981196304217154e-05,
"loss": 0.2625,
"step": 469
},
{
"epoch": 0.3008,
"grad_norm": 0.2929467586131004,
"learning_rate": 4.1942290344835765e-05,
"loss": 0.2635,
"step": 470
},
{
"epoch": 0.30144,
"grad_norm": 0.28946698136298926,
"learning_rate": 4.190330835468224e-05,
"loss": 0.2666,
"step": 471
},
{
"epoch": 0.30208,
"grad_norm": 0.3054605229887845,
"learning_rate": 4.1864250508693424e-05,
"loss": 0.2782,
"step": 472
},
{
"epoch": 0.30272,
"grad_norm": 0.30853302514826486,
"learning_rate": 4.182511698214657e-05,
"loss": 0.271,
"step": 473
},
{
"epoch": 0.30336,
"grad_norm": 0.28096000312894664,
"learning_rate": 4.1785907950658573e-05,
"loss": 0.2585,
"step": 474
},
{
"epoch": 0.304,
"grad_norm": 0.3125936908697687,
"learning_rate": 4.1746623590185155e-05,
"loss": 0.2524,
"step": 475
},
{
"epoch": 0.30464,
"grad_norm": 0.29712867964294787,
"learning_rate": 4.170726407702008e-05,
"loss": 0.2461,
"step": 476
},
{
"epoch": 0.30528,
"grad_norm": 0.32449012009401823,
"learning_rate": 4.1667829587794374e-05,
"loss": 0.2822,
"step": 477
},
{
"epoch": 0.30592,
"grad_norm": 0.3218131224973865,
"learning_rate": 4.162832029947553e-05,
"loss": 0.2725,
"step": 478
},
{
"epoch": 0.30656,
"grad_norm": 0.2804231247197045,
"learning_rate": 4.158873638936672e-05,
"loss": 0.2471,
"step": 479
},
{
"epoch": 0.3072,
"grad_norm": 0.31284785097448237,
"learning_rate": 4.154907803510599e-05,
"loss": 0.252,
"step": 480
},
{
"epoch": 0.30784,
"grad_norm": 0.2994921809896846,
"learning_rate": 4.150934541466545e-05,
"loss": 0.2614,
"step": 481
},
{
"epoch": 0.30848,
"grad_norm": 0.296657249343442,
"learning_rate": 4.146953870635049e-05,
"loss": 0.2722,
"step": 482
},
{
"epoch": 0.30912,
"grad_norm": 0.28293479502038055,
"learning_rate": 4.1429658088798996e-05,
"loss": 0.2634,
"step": 483
},
{
"epoch": 0.30976,
"grad_norm": 0.2910484344542188,
"learning_rate": 4.138970374098052e-05,
"loss": 0.2486,
"step": 484
},
{
"epoch": 0.3104,
"grad_norm": 0.3146840001735881,
"learning_rate": 4.1349675842195494e-05,
"loss": 0.2661,
"step": 485
},
{
"epoch": 0.31104,
"grad_norm": 0.2746027576599675,
"learning_rate": 4.130957457207441e-05,
"loss": 0.2501,
"step": 486
},
{
"epoch": 0.31168,
"grad_norm": 0.3051892164851984,
"learning_rate": 4.126940011057703e-05,
"loss": 0.2404,
"step": 487
},
{
"epoch": 0.31232,
"grad_norm": 0.30592656911462335,
"learning_rate": 4.1229152637991576e-05,
"loss": 0.2673,
"step": 488
},
{
"epoch": 0.31296,
"grad_norm": 0.31633018710097294,
"learning_rate": 4.1188832334933906e-05,
"loss": 0.2475,
"step": 489
},
{
"epoch": 0.3136,
"grad_norm": 0.274585788639711,
"learning_rate": 4.114843938234673e-05,
"loss": 0.2753,
"step": 490
},
{
"epoch": 0.31424,
"grad_norm": 0.3287109219068746,
"learning_rate": 4.1107973961498763e-05,
"loss": 0.2582,
"step": 491
},
{
"epoch": 0.31488,
"grad_norm": 0.3167546562615222,
"learning_rate": 4.106743625398395e-05,
"loss": 0.2662,
"step": 492
},
{
"epoch": 0.31552,
"grad_norm": 0.32410088907898493,
"learning_rate": 4.102682644172061e-05,
"loss": 0.2869,
"step": 493
},
{
"epoch": 0.31616,
"grad_norm": 0.3355149408031651,
"learning_rate": 4.0986144706950677e-05,
"loss": 0.2746,
"step": 494
},
{
"epoch": 0.3168,
"grad_norm": 0.3074689123409369,
"learning_rate": 4.094539123223881e-05,
"loss": 0.2433,
"step": 495
},
{
"epoch": 0.31744,
"grad_norm": 0.29842413604098983,
"learning_rate": 4.090456620047162e-05,
"loss": 0.2435,
"step": 496
},
{
"epoch": 0.31808,
"grad_norm": 0.3414546216468358,
"learning_rate": 4.086366979485685e-05,
"loss": 0.2796,
"step": 497
},
{
"epoch": 0.31872,
"grad_norm": 0.3150858918248773,
"learning_rate": 4.082270219892254e-05,
"loss": 0.2633,
"step": 498
},
{
"epoch": 0.31936,
"grad_norm": 0.2786327977030963,
"learning_rate": 4.0781663596516206e-05,
"loss": 0.2419,
"step": 499
},
{
"epoch": 0.32,
"grad_norm": 0.29092976216281774,
"learning_rate": 4.074055417180401e-05,
"loss": 0.2697,
"step": 500
},
{
"epoch": 0.32064,
"grad_norm": 0.32610697106570463,
"learning_rate": 4.069937410926994e-05,
"loss": 0.2537,
"step": 501
},
{
"epoch": 0.32128,
"grad_norm": 0.30608850743455823,
"learning_rate": 4.0658123593714984e-05,
"loss": 0.264,
"step": 502
},
{
"epoch": 0.32192,
"grad_norm": 0.2824318843825735,
"learning_rate": 4.061680281025628e-05,
"loss": 0.2474,
"step": 503
},
{
"epoch": 0.32256,
"grad_norm": 0.29399230400886783,
"learning_rate": 4.057541194432634e-05,
"loss": 0.2413,
"step": 504
},
{
"epoch": 0.3232,
"grad_norm": 0.6605989874825366,
"learning_rate": 4.053395118167214e-05,
"loss": 0.2581,
"step": 505
},
{
"epoch": 0.32384,
"grad_norm": 0.30398550676295183,
"learning_rate": 4.049242070835435e-05,
"loss": 0.2864,
"step": 506
},
{
"epoch": 0.32448,
"grad_norm": 0.32844118327083244,
"learning_rate": 4.0450820710746475e-05,
"loss": 0.2595,
"step": 507
},
{
"epoch": 0.32512,
"grad_norm": 0.29753850766246936,
"learning_rate": 4.0409151375534014e-05,
"loss": 0.2627,
"step": 508
},
{
"epoch": 0.32576,
"grad_norm": 0.32997195633690085,
"learning_rate": 4.036741288971362e-05,
"loss": 0.2552,
"step": 509
},
{
"epoch": 0.3264,
"grad_norm": 0.31989725360404464,
"learning_rate": 4.032560544059228e-05,
"loss": 0.2543,
"step": 510
},
{
"epoch": 0.32704,
"grad_norm": 0.2734053342728525,
"learning_rate": 4.028372921578647e-05,
"loss": 0.2636,
"step": 511
},
{
"epoch": 0.32768,
"grad_norm": 0.3076390699096864,
"learning_rate": 4.024178440322128e-05,
"loss": 0.251,
"step": 512
},
{
"epoch": 0.32832,
"grad_norm": 0.27589462055645664,
"learning_rate": 4.019977119112962e-05,
"loss": 0.2599,
"step": 513
},
{
"epoch": 0.32896,
"grad_norm": 0.3152240440071727,
"learning_rate": 4.015768976805135e-05,
"loss": 0.303,
"step": 514
},
{
"epoch": 0.3296,
"grad_norm": 0.30486982512783595,
"learning_rate": 4.011554032283242e-05,
"loss": 0.2339,
"step": 515
},
{
"epoch": 0.33024,
"grad_norm": 0.334048138143333,
"learning_rate": 4.007332304462406e-05,
"loss": 0.2494,
"step": 516
},
{
"epoch": 0.33088,
"grad_norm": 0.2995442580330488,
"learning_rate": 4.003103812288189e-05,
"loss": 0.267,
"step": 517
},
{
"epoch": 0.33152,
"grad_norm": 0.2706177023809212,
"learning_rate": 3.99886857473651e-05,
"loss": 0.2523,
"step": 518
},
{
"epoch": 0.33216,
"grad_norm": 0.3532067575064781,
"learning_rate": 3.9946266108135575e-05,
"loss": 0.2767,
"step": 519
},
{
"epoch": 0.3328,
"grad_norm": 0.3067722195105639,
"learning_rate": 3.9903779395557087e-05,
"loss": 0.2606,
"step": 520
},
{
"epoch": 0.33344,
"grad_norm": 0.26860794555811235,
"learning_rate": 3.9861225800294366e-05,
"loss": 0.2295,
"step": 521
},
{
"epoch": 0.33408,
"grad_norm": 0.34447335382371475,
"learning_rate": 3.981860551331232e-05,
"loss": 0.2665,
"step": 522
}
],
"logging_steps": 1,
"max_steps": 1562,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 261,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 238263678074880.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}