Orion-14B-dacon-qa / trainer_state.json
charlieCs's picture
upload model
26c65ff verified
raw
history blame
24.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 153,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"grad_norm": 5.049024000371086,
"learning_rate": 1.8181818181818183e-06,
"loss": 1.854,
"step": 1
},
{
"epoch": 0.04,
"grad_norm": 4.758646674230607,
"learning_rate": 3.6363636363636366e-06,
"loss": 1.8589,
"step": 2
},
{
"epoch": 0.06,
"grad_norm": 4.997532808044432,
"learning_rate": 5.4545454545454545e-06,
"loss": 1.8066,
"step": 3
},
{
"epoch": 0.08,
"grad_norm": 4.658976531052129,
"learning_rate": 7.272727272727273e-06,
"loss": 1.8039,
"step": 4
},
{
"epoch": 0.1,
"grad_norm": 3.2333098053485814,
"learning_rate": 9.090909090909091e-06,
"loss": 1.6903,
"step": 5
},
{
"epoch": 0.12,
"grad_norm": 2.672741130516915,
"learning_rate": 1.0909090909090909e-05,
"loss": 1.6346,
"step": 6
},
{
"epoch": 0.14,
"grad_norm": 1.8361460465829846,
"learning_rate": 1.2727272727272728e-05,
"loss": 1.5495,
"step": 7
},
{
"epoch": 0.16,
"grad_norm": 1.7045961378249597,
"learning_rate": 1.4545454545454546e-05,
"loss": 1.5097,
"step": 8
},
{
"epoch": 0.18,
"grad_norm": 1.635826359191631,
"learning_rate": 1.6363636363636366e-05,
"loss": 1.4721,
"step": 9
},
{
"epoch": 0.2,
"grad_norm": 1.578935320707837,
"learning_rate": 1.8181818181818182e-05,
"loss": 1.4229,
"step": 10
},
{
"epoch": 0.22,
"grad_norm": 1.5221044723806934,
"learning_rate": 2e-05,
"loss": 1.3793,
"step": 11
},
{
"epoch": 0.24,
"grad_norm": 1.4000849902377055,
"learning_rate": 1.999867521457224e-05,
"loss": 1.3113,
"step": 12
},
{
"epoch": 0.25,
"grad_norm": 1.575616258826214,
"learning_rate": 1.9994701209300245e-05,
"loss": 1.2887,
"step": 13
},
{
"epoch": 0.27,
"grad_norm": 1.3392980593157788,
"learning_rate": 1.9988079037124866e-05,
"loss": 1.2279,
"step": 14
},
{
"epoch": 0.29,
"grad_norm": 1.424201738399285,
"learning_rate": 1.9978810452637544e-05,
"loss": 1.1972,
"step": 15
},
{
"epoch": 0.31,
"grad_norm": 1.4523213122657395,
"learning_rate": 1.9966897911615417e-05,
"loss": 1.1793,
"step": 16
},
{
"epoch": 0.33,
"grad_norm": 1.3820011323242407,
"learning_rate": 1.995234457037063e-05,
"loss": 1.1211,
"step": 17
},
{
"epoch": 0.35,
"grad_norm": 1.2328298047764605,
"learning_rate": 1.9935154284914063e-05,
"loss": 1.0237,
"step": 18
},
{
"epoch": 0.37,
"grad_norm": 1.4014760682876144,
"learning_rate": 1.991533160993366e-05,
"loss": 1.084,
"step": 19
},
{
"epoch": 0.39,
"grad_norm": 1.304071018054968,
"learning_rate": 1.98928817975876e-05,
"loss": 1.0577,
"step": 20
},
{
"epoch": 0.41,
"grad_norm": 1.2396816193325995,
"learning_rate": 1.9867810796112742e-05,
"loss": 1.0534,
"step": 21
},
{
"epoch": 0.43,
"grad_norm": 1.1906790092813893,
"learning_rate": 1.9840125248248564e-05,
"loss": 0.9375,
"step": 22
},
{
"epoch": 0.45,
"grad_norm": 1.2125922433431726,
"learning_rate": 1.9809832489477144e-05,
"loss": 0.907,
"step": 23
},
{
"epoch": 0.47,
"grad_norm": 1.3509732764627251,
"learning_rate": 1.9776940546079552e-05,
"loss": 0.8994,
"step": 24
},
{
"epoch": 0.49,
"grad_norm": 1.1575946721358368,
"learning_rate": 1.9741458133009258e-05,
"loss": 0.9001,
"step": 25
},
{
"epoch": 0.51,
"grad_norm": 1.0819155083735588,
"learning_rate": 1.970339465158301e-05,
"loss": 0.8853,
"step": 26
},
{
"epoch": 0.53,
"grad_norm": 1.1831054183701755,
"learning_rate": 1.9662760186989914e-05,
"loss": 0.8559,
"step": 27
},
{
"epoch": 0.55,
"grad_norm": 1.2787427328132572,
"learning_rate": 1.9619565505619288e-05,
"loss": 0.8908,
"step": 28
},
{
"epoch": 0.57,
"grad_norm": 1.1960513256280778,
"learning_rate": 1.9573822052208013e-05,
"loss": 0.8505,
"step": 29
},
{
"epoch": 0.59,
"grad_norm": 1.1882091713537735,
"learning_rate": 1.9525541946808187e-05,
"loss": 0.8252,
"step": 30
},
{
"epoch": 0.61,
"grad_norm": 1.1957026823405033,
"learning_rate": 1.9474737981575833e-05,
"loss": 0.8294,
"step": 31
},
{
"epoch": 0.63,
"grad_norm": 1.1235625302238945,
"learning_rate": 1.942142361738151e-05,
"loss": 0.7843,
"step": 32
},
{
"epoch": 0.65,
"grad_norm": 1.2129049745653777,
"learning_rate": 1.936561298024377e-05,
"loss": 0.7732,
"step": 33
},
{
"epoch": 0.67,
"grad_norm": 1.0546648941443104,
"learning_rate": 1.9307320857586377e-05,
"loss": 0.7081,
"step": 34
},
{
"epoch": 0.69,
"grad_norm": 1.099433031052361,
"learning_rate": 1.9246562694320258e-05,
"loss": 0.6877,
"step": 35
},
{
"epoch": 0.71,
"grad_norm": 1.3153258284792773,
"learning_rate": 1.9183354588751274e-05,
"loss": 0.7302,
"step": 36
},
{
"epoch": 0.73,
"grad_norm": 1.1045347116178383,
"learning_rate": 1.9117713288314864e-05,
"loss": 0.6839,
"step": 37
},
{
"epoch": 0.75,
"grad_norm": 1.1110989245435192,
"learning_rate": 1.904965618513868e-05,
"loss": 0.6519,
"step": 38
},
{
"epoch": 0.76,
"grad_norm": 1.094231744667558,
"learning_rate": 1.8979201311434434e-05,
"loss": 0.6653,
"step": 39
},
{
"epoch": 0.78,
"grad_norm": 1.1989962094861866,
"learning_rate": 1.8906367334720125e-05,
"loss": 0.664,
"step": 40
},
{
"epoch": 0.8,
"grad_norm": 2.0062427841484576,
"learning_rate": 1.8831173552873946e-05,
"loss": 0.7041,
"step": 41
},
{
"epoch": 0.82,
"grad_norm": 1.230679254842199,
"learning_rate": 1.8753639889021197e-05,
"loss": 0.6849,
"step": 42
},
{
"epoch": 0.84,
"grad_norm": 1.1625293133229038,
"learning_rate": 1.8673786886255478e-05,
"loss": 0.5871,
"step": 43
},
{
"epoch": 0.86,
"grad_norm": 1.2011252293407368,
"learning_rate": 1.8591635702195672e-05,
"loss": 0.5814,
"step": 44
},
{
"epoch": 0.88,
"grad_norm": 1.1548475575271413,
"learning_rate": 1.8507208103380093e-05,
"loss": 0.6028,
"step": 45
},
{
"epoch": 0.9,
"grad_norm": 1.3290758207520514,
"learning_rate": 1.8420526459499252e-05,
"loss": 0.5177,
"step": 46
},
{
"epoch": 0.92,
"grad_norm": 1.3961190552811622,
"learning_rate": 1.8331613737468888e-05,
"loss": 0.5327,
"step": 47
},
{
"epoch": 0.94,
"grad_norm": 1.1179664937015907,
"learning_rate": 1.8240493495344695e-05,
"loss": 0.5702,
"step": 48
},
{
"epoch": 0.96,
"grad_norm": 0.991786755708903,
"learning_rate": 1.8147189876080463e-05,
"loss": 0.5585,
"step": 49
},
{
"epoch": 0.98,
"grad_norm": 1.0511710425989889,
"learning_rate": 1.8051727601131228e-05,
"loss": 0.4897,
"step": 50
},
{
"epoch": 1.0,
"grad_norm": 0.9871728886473652,
"learning_rate": 1.7954131963903134e-05,
"loss": 0.5135,
"step": 51
},
{
"epoch": 1.02,
"grad_norm": 0.8724604948002991,
"learning_rate": 1.785442882305179e-05,
"loss": 0.3347,
"step": 52
},
{
"epoch": 1.04,
"grad_norm": 0.8838295943097,
"learning_rate": 1.775264459563081e-05,
"loss": 0.3181,
"step": 53
},
{
"epoch": 1.06,
"grad_norm": 0.9931815866970414,
"learning_rate": 1.764880625009245e-05,
"loss": 0.3026,
"step": 54
},
{
"epoch": 1.08,
"grad_norm": 1.0345742370865185,
"learning_rate": 1.7542941299142113e-05,
"loss": 0.3461,
"step": 55
},
{
"epoch": 1.1,
"grad_norm": 0.9441524354940148,
"learning_rate": 1.7435077792448666e-05,
"loss": 0.3211,
"step": 56
},
{
"epoch": 1.12,
"grad_norm": 0.8125450415231048,
"learning_rate": 1.7325244309212476e-05,
"loss": 0.276,
"step": 57
},
{
"epoch": 1.14,
"grad_norm": 0.8616036387498645,
"learning_rate": 1.7213469950593156e-05,
"loss": 0.3256,
"step": 58
},
{
"epoch": 1.16,
"grad_norm": 0.8037201705902857,
"learning_rate": 1.709978433199901e-05,
"loss": 0.2875,
"step": 59
},
{
"epoch": 1.18,
"grad_norm": 0.923293041412828,
"learning_rate": 1.6984217575240212e-05,
"loss": 0.3468,
"step": 60
},
{
"epoch": 1.2,
"grad_norm": 0.8864744076614339,
"learning_rate": 1.6866800300547814e-05,
"loss": 0.3045,
"step": 61
},
{
"epoch": 1.22,
"grad_norm": 0.8688649629779567,
"learning_rate": 1.674756361846071e-05,
"loss": 0.3243,
"step": 62
},
{
"epoch": 1.24,
"grad_norm": 0.77439697554644,
"learning_rate": 1.6626539121582687e-05,
"loss": 0.2579,
"step": 63
},
{
"epoch": 1.25,
"grad_norm": 0.8571490155577813,
"learning_rate": 1.650375887621171e-05,
"loss": 0.332,
"step": 64
},
{
"epoch": 1.27,
"grad_norm": 0.922211924907794,
"learning_rate": 1.637925541384375e-05,
"loss": 0.3416,
"step": 65
},
{
"epoch": 1.29,
"grad_norm": 0.8273052620873378,
"learning_rate": 1.6253061722553353e-05,
"loss": 0.3068,
"step": 66
},
{
"epoch": 1.31,
"grad_norm": 0.8095932095629248,
"learning_rate": 1.612521123825317e-05,
"loss": 0.3171,
"step": 67
},
{
"epoch": 1.33,
"grad_norm": 0.8019342077433093,
"learning_rate": 1.5995737835834905e-05,
"loss": 0.3117,
"step": 68
},
{
"epoch": 1.35,
"grad_norm": 0.7916383152619996,
"learning_rate": 1.586467582019392e-05,
"loss": 0.2724,
"step": 69
},
{
"epoch": 1.37,
"grad_norm": 0.8004248593606291,
"learning_rate": 1.5732059917139912e-05,
"loss": 0.2895,
"step": 70
},
{
"epoch": 1.39,
"grad_norm": 0.8986302044736728,
"learning_rate": 1.5597925264196048e-05,
"loss": 0.2968,
"step": 71
},
{
"epoch": 1.41,
"grad_norm": 0.9101368979823861,
"learning_rate": 1.546230740128904e-05,
"loss": 0.339,
"step": 72
},
{
"epoch": 1.43,
"grad_norm": 0.8045707914289225,
"learning_rate": 1.53252422613326e-05,
"loss": 0.2773,
"step": 73
},
{
"epoch": 1.45,
"grad_norm": 0.8169621304521563,
"learning_rate": 1.5186766160706738e-05,
"loss": 0.2971,
"step": 74
},
{
"epoch": 1.47,
"grad_norm": 0.7851894618359577,
"learning_rate": 1.504691578963549e-05,
"loss": 0.2505,
"step": 75
},
{
"epoch": 1.49,
"grad_norm": 0.7829032571228582,
"learning_rate": 1.4905728202465596e-05,
"loss": 0.2955,
"step": 76
},
{
"epoch": 1.51,
"grad_norm": 0.8280131066501262,
"learning_rate": 1.4763240807848667e-05,
"loss": 0.3118,
"step": 77
},
{
"epoch": 1.53,
"grad_norm": 0.7904115230357416,
"learning_rate": 1.4619491358829502e-05,
"loss": 0.2637,
"step": 78
},
{
"epoch": 1.55,
"grad_norm": 0.8576605948937364,
"learning_rate": 1.4474517942843173e-05,
"loss": 0.3111,
"step": 79
},
{
"epoch": 1.57,
"grad_norm": 0.771179138835728,
"learning_rate": 1.4328358971623455e-05,
"loss": 0.2625,
"step": 80
},
{
"epoch": 1.59,
"grad_norm": 0.7163659653314414,
"learning_rate": 1.4181053171025392e-05,
"loss": 0.2548,
"step": 81
},
{
"epoch": 1.61,
"grad_norm": 0.7449243778532777,
"learning_rate": 1.4032639570764595e-05,
"loss": 0.2548,
"step": 82
},
{
"epoch": 1.63,
"grad_norm": 0.7999629608162984,
"learning_rate": 1.3883157494076048e-05,
"loss": 0.2926,
"step": 83
},
{
"epoch": 1.65,
"grad_norm": 0.8217922125483811,
"learning_rate": 1.3732646547295128e-05,
"loss": 0.2938,
"step": 84
},
{
"epoch": 1.67,
"grad_norm": 0.8086828652630952,
"learning_rate": 1.358114660936364e-05,
"loss": 0.297,
"step": 85
},
{
"epoch": 1.69,
"grad_norm": 0.8194748734537538,
"learning_rate": 1.34286978212636e-05,
"loss": 0.2856,
"step": 86
},
{
"epoch": 1.71,
"grad_norm": 0.7858003470117391,
"learning_rate": 1.32753405753816e-05,
"loss": 0.2543,
"step": 87
},
{
"epoch": 1.73,
"grad_norm": 0.7826963768753953,
"learning_rate": 1.3121115504806554e-05,
"loss": 0.2677,
"step": 88
},
{
"epoch": 1.75,
"grad_norm": 0.7729735090495947,
"learning_rate": 1.2966063472563686e-05,
"loss": 0.2276,
"step": 89
},
{
"epoch": 1.76,
"grad_norm": 0.7157613149688595,
"learning_rate": 1.2810225560787561e-05,
"loss": 0.2236,
"step": 90
},
{
"epoch": 1.78,
"grad_norm": 0.8637010063044507,
"learning_rate": 1.2653643059837109e-05,
"loss": 0.2915,
"step": 91
},
{
"epoch": 1.8,
"grad_norm": 0.7449248979464137,
"learning_rate": 1.2496357457355423e-05,
"loss": 0.2476,
"step": 92
},
{
"epoch": 1.82,
"grad_norm": 0.7456800901872752,
"learning_rate": 1.2338410427277342e-05,
"loss": 0.276,
"step": 93
},
{
"epoch": 1.84,
"grad_norm": 0.6931855319587382,
"learning_rate": 1.2179843818787625e-05,
"loss": 0.2291,
"step": 94
},
{
"epoch": 1.86,
"grad_norm": 0.748062571866356,
"learning_rate": 1.202069964523272e-05,
"loss": 0.2484,
"step": 95
},
{
"epoch": 1.88,
"grad_norm": 0.7159809176976305,
"learning_rate": 1.186102007298904e-05,
"loss": 0.264,
"step": 96
},
{
"epoch": 1.9,
"grad_norm": 0.6999413576425992,
"learning_rate": 1.1700847410290667e-05,
"loss": 0.2569,
"step": 97
},
{
"epoch": 1.92,
"grad_norm": 0.7184171735319789,
"learning_rate": 1.1540224096019495e-05,
"loss": 0.2533,
"step": 98
},
{
"epoch": 1.94,
"grad_norm": 0.7498351154279366,
"learning_rate": 1.137919268846074e-05,
"loss": 0.2625,
"step": 99
},
{
"epoch": 1.96,
"grad_norm": 0.8195036397088564,
"learning_rate": 1.121779585402684e-05,
"loss": 0.2872,
"step": 100
},
{
"epoch": 1.98,
"grad_norm": 0.7239230213655573,
"learning_rate": 1.105607635595266e-05,
"loss": 0.2138,
"step": 101
},
{
"epoch": 2.0,
"grad_norm": 0.5927611951490782,
"learning_rate": 1.0894077042965084e-05,
"loss": 0.1527,
"step": 102
},
{
"epoch": 2.02,
"grad_norm": 0.5812390972468515,
"learning_rate": 1.0731840837929946e-05,
"loss": 0.0943,
"step": 103
},
{
"epoch": 2.04,
"grad_norm": 0.6457949647478547,
"learning_rate": 1.0569410726479301e-05,
"loss": 0.1276,
"step": 104
},
{
"epoch": 2.06,
"grad_norm": 0.6076599586709107,
"learning_rate": 1.0406829745622085e-05,
"loss": 0.1118,
"step": 105
},
{
"epoch": 2.08,
"grad_norm": 0.6580690196356788,
"learning_rate": 1.0244140972341155e-05,
"loss": 0.1266,
"step": 106
},
{
"epoch": 2.1,
"grad_norm": 0.6652391219627729,
"learning_rate": 1.008138751217973e-05,
"loss": 0.1061,
"step": 107
},
{
"epoch": 2.12,
"grad_norm": 0.8077871750305834,
"learning_rate": 9.918612487820274e-06,
"loss": 0.1372,
"step": 108
},
{
"epoch": 2.14,
"grad_norm": 0.7590982992651446,
"learning_rate": 9.755859027658848e-06,
"loss": 0.1108,
"step": 109
},
{
"epoch": 2.16,
"grad_norm": 0.8397462300303704,
"learning_rate": 9.593170254377915e-06,
"loss": 0.1289,
"step": 110
},
{
"epoch": 2.18,
"grad_norm": 0.7003906062775592,
"learning_rate": 9.430589273520704e-06,
"loss": 0.1058,
"step": 111
},
{
"epoch": 2.2,
"grad_norm": 0.7088357228372557,
"learning_rate": 9.268159162070058e-06,
"loss": 0.1135,
"step": 112
},
{
"epoch": 2.22,
"grad_norm": 0.7000401962183394,
"learning_rate": 9.105922957034921e-06,
"loss": 0.1096,
"step": 113
},
{
"epoch": 2.24,
"grad_norm": 0.5830640142754188,
"learning_rate": 8.943923644047343e-06,
"loss": 0.096,
"step": 114
},
{
"epoch": 2.25,
"grad_norm": 0.7040673193362394,
"learning_rate": 8.782204145973162e-06,
"loss": 0.126,
"step": 115
},
{
"epoch": 2.27,
"grad_norm": 0.5883035825262033,
"learning_rate": 8.620807311539258e-06,
"loss": 0.1046,
"step": 116
},
{
"epoch": 2.29,
"grad_norm": 0.5889783156569407,
"learning_rate": 8.45977590398051e-06,
"loss": 0.1099,
"step": 117
},
{
"epoch": 2.31,
"grad_norm": 0.5746493638760929,
"learning_rate": 8.299152589709336e-06,
"loss": 0.0998,
"step": 118
},
{
"epoch": 2.33,
"grad_norm": 0.5063169905997035,
"learning_rate": 8.138979927010964e-06,
"loss": 0.0829,
"step": 119
},
{
"epoch": 2.35,
"grad_norm": 0.561526728081391,
"learning_rate": 7.979300354767282e-06,
"loss": 0.099,
"step": 120
},
{
"epoch": 2.37,
"grad_norm": 0.6140392260229752,
"learning_rate": 7.82015618121238e-06,
"loss": 0.112,
"step": 121
},
{
"epoch": 2.39,
"grad_norm": 0.6024756993343563,
"learning_rate": 7.66158957272266e-06,
"loss": 0.0924,
"step": 122
},
{
"epoch": 2.41,
"grad_norm": 0.6149831107386897,
"learning_rate": 7.503642542644581e-06,
"loss": 0.1056,
"step": 123
},
{
"epoch": 2.43,
"grad_norm": 0.6268831968674875,
"learning_rate": 7.346356940162895e-06,
"loss": 0.1109,
"step": 124
},
{
"epoch": 2.45,
"grad_norm": 0.5774013268612427,
"learning_rate": 7.189774439212442e-06,
"loss": 0.095,
"step": 125
},
{
"epoch": 2.47,
"grad_norm": 0.5981672010212989,
"learning_rate": 7.033936527436318e-06,
"loss": 0.1028,
"step": 126
},
{
"epoch": 2.49,
"grad_norm": 0.6129772623459513,
"learning_rate": 6.878884495193448e-06,
"loss": 0.0945,
"step": 127
},
{
"epoch": 2.51,
"grad_norm": 0.5804441177255439,
"learning_rate": 6.724659424618401e-06,
"loss": 0.099,
"step": 128
},
{
"epoch": 2.53,
"grad_norm": 0.6592505296857643,
"learning_rate": 6.571302178736404e-06,
"loss": 0.1119,
"step": 129
},
{
"epoch": 2.55,
"grad_norm": 0.5876228001270772,
"learning_rate": 6.418853390636363e-06,
"loss": 0.1066,
"step": 130
},
{
"epoch": 2.57,
"grad_norm": 0.5711848758996622,
"learning_rate": 6.267353452704876e-06,
"loss": 0.0939,
"step": 131
},
{
"epoch": 2.59,
"grad_norm": 0.5276470301226159,
"learning_rate": 6.116842505923955e-06,
"loss": 0.086,
"step": 132
},
{
"epoch": 2.61,
"grad_norm": 0.5743382647434178,
"learning_rate": 5.967360429235407e-06,
"loss": 0.0976,
"step": 133
},
{
"epoch": 2.63,
"grad_norm": 0.5502701680994874,
"learning_rate": 5.8189468289746075e-06,
"loss": 0.0925,
"step": 134
},
{
"epoch": 2.65,
"grad_norm": 0.6137369248887328,
"learning_rate": 5.671641028376547e-06,
"loss": 0.1014,
"step": 135
},
{
"epoch": 2.67,
"grad_norm": 0.5582863288518123,
"learning_rate": 5.525482057156833e-06,
"loss": 0.0977,
"step": 136
},
{
"epoch": 2.69,
"grad_norm": 0.5454192540734187,
"learning_rate": 5.380508641170499e-06,
"loss": 0.0904,
"step": 137
},
{
"epoch": 2.71,
"grad_norm": 0.5209533902715616,
"learning_rate": 5.236759192151336e-06,
"loss": 0.0866,
"step": 138
},
{
"epoch": 2.73,
"grad_norm": 0.5717122393516525,
"learning_rate": 5.094271797534404e-06,
"loss": 0.0996,
"step": 139
},
{
"epoch": 2.75,
"grad_norm": 0.6064773526535152,
"learning_rate": 4.953084210364508e-06,
"loss": 0.104,
"step": 140
},
{
"epoch": 2.76,
"grad_norm": 0.5691234525814087,
"learning_rate": 4.813233839293265e-06,
"loss": 0.1015,
"step": 141
},
{
"epoch": 2.78,
"grad_norm": 0.5208562146564856,
"learning_rate": 4.674757738667405e-06,
"loss": 0.0851,
"step": 142
},
{
"epoch": 2.8,
"grad_norm": 0.5729654869317482,
"learning_rate": 4.537692598710962e-06,
"loss": 0.0999,
"step": 143
},
{
"epoch": 2.82,
"grad_norm": 0.5098181803420644,
"learning_rate": 4.402074735803955e-06,
"loss": 0.0811,
"step": 144
},
{
"epoch": 2.84,
"grad_norm": 0.5599902642629923,
"learning_rate": 4.267940082860088e-06,
"loss": 0.0859,
"step": 145
},
{
"epoch": 2.86,
"grad_norm": 0.6128082395071871,
"learning_rate": 4.135324179806079e-06,
"loss": 0.1044,
"step": 146
},
{
"epoch": 2.88,
"grad_norm": 0.6027252305351385,
"learning_rate": 4.004262164165098e-06,
"loss": 0.101,
"step": 147
},
{
"epoch": 2.9,
"grad_norm": 0.6114396307412036,
"learning_rate": 3.874788761746836e-06,
"loss": 0.1008,
"step": 148
},
{
"epoch": 2.92,
"grad_norm": 0.5382288139061067,
"learning_rate": 3.74693827744665e-06,
"loss": 0.0846,
"step": 149
},
{
"epoch": 2.94,
"grad_norm": 0.680532062269904,
"learning_rate": 3.6207445861562497e-06,
"loss": 0.1155,
"step": 150
},
{
"epoch": 2.96,
"grad_norm": 0.5889312810479405,
"learning_rate": 3.4962411237882945e-06,
"loss": 0.0916,
"step": 151
},
{
"epoch": 2.98,
"grad_norm": 0.5564936393621064,
"learning_rate": 3.373460878417315e-06,
"loss": 0.0937,
"step": 152
},
{
"epoch": 3.0,
"grad_norm": 0.4415683617442384,
"learning_rate": 3.252436381539291e-06,
"loss": 0.0547,
"step": 153
}
],
"logging_steps": 1,
"max_steps": 204,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 37890624061440.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}