masatochi's picture
Training in progress, step 200, checkpoint
be9b0e0 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.09780548933308882,
"eval_steps": 34,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004890274466654441,
"grad_norm": Infinity,
"learning_rate": 6.666666666666667e-06,
"loss": 9.0513,
"step": 1
},
{
"epoch": 0.0004890274466654441,
"eval_loss": 9.337614059448242,
"eval_runtime": 876.8823,
"eval_samples_per_second": 2.946,
"eval_steps_per_second": 0.982,
"step": 1
},
{
"epoch": 0.0009780548933308881,
"grad_norm": Infinity,
"learning_rate": 1.3333333333333333e-05,
"loss": 9.4794,
"step": 2
},
{
"epoch": 0.0014670823399963323,
"grad_norm": Infinity,
"learning_rate": 2e-05,
"loss": 8.6541,
"step": 3
},
{
"epoch": 0.0019561097866617762,
"grad_norm": Infinity,
"learning_rate": 2.6666666666666667e-05,
"loss": 10.0028,
"step": 4
},
{
"epoch": 0.0024451372333272204,
"grad_norm": Infinity,
"learning_rate": 3.3333333333333335e-05,
"loss": 8.8885,
"step": 5
},
{
"epoch": 0.0029341646799926646,
"grad_norm": 8.087092190490132e+18,
"learning_rate": 4e-05,
"loss": 9.0537,
"step": 6
},
{
"epoch": 0.0034231921266581087,
"grad_norm": Infinity,
"learning_rate": 4.666666666666667e-05,
"loss": 8.6808,
"step": 7
},
{
"epoch": 0.0039122195733235525,
"grad_norm": Infinity,
"learning_rate": 5.333333333333333e-05,
"loss": 8.8092,
"step": 8
},
{
"epoch": 0.004401247019988997,
"grad_norm": Infinity,
"learning_rate": 6e-05,
"loss": 9.7075,
"step": 9
},
{
"epoch": 0.004890274466654441,
"grad_norm": Infinity,
"learning_rate": 6.666666666666667e-05,
"loss": 9.2624,
"step": 10
},
{
"epoch": 0.005379301913319885,
"grad_norm": Infinity,
"learning_rate": 7.333333333333333e-05,
"loss": 8.4931,
"step": 11
},
{
"epoch": 0.005868329359985329,
"grad_norm": Infinity,
"learning_rate": 8e-05,
"loss": 9.3205,
"step": 12
},
{
"epoch": 0.006357356806650773,
"grad_norm": Infinity,
"learning_rate": 8.666666666666667e-05,
"loss": 9.8934,
"step": 13
},
{
"epoch": 0.0068463842533162175,
"grad_norm": Infinity,
"learning_rate": 9.333333333333334e-05,
"loss": 9.1796,
"step": 14
},
{
"epoch": 0.007335411699981661,
"grad_norm": 1.2167695950759854e+19,
"learning_rate": 0.0001,
"loss": 9.3987,
"step": 15
},
{
"epoch": 0.007824439146647105,
"grad_norm": 5.4412064499695616e+17,
"learning_rate": 0.00010666666666666667,
"loss": 9.0077,
"step": 16
},
{
"epoch": 0.00831346659331255,
"grad_norm": Infinity,
"learning_rate": 0.00011333333333333334,
"loss": 9.8072,
"step": 17
},
{
"epoch": 0.008802494039977994,
"grad_norm": Infinity,
"learning_rate": 0.00012,
"loss": 9.2775,
"step": 18
},
{
"epoch": 0.009291521486643438,
"grad_norm": 9.411642512390488e+18,
"learning_rate": 0.00012666666666666666,
"loss": 9.1326,
"step": 19
},
{
"epoch": 0.009780548933308882,
"grad_norm": 1.3229755463714734e+18,
"learning_rate": 0.00013333333333333334,
"loss": 8.2326,
"step": 20
},
{
"epoch": 0.010269576379974325,
"grad_norm": Infinity,
"learning_rate": 0.00014,
"loss": 9.7804,
"step": 21
},
{
"epoch": 0.01075860382663977,
"grad_norm": Infinity,
"learning_rate": 0.00014666666666666666,
"loss": 9.2763,
"step": 22
},
{
"epoch": 0.011247631273305215,
"grad_norm": Infinity,
"learning_rate": 0.00015333333333333334,
"loss": 9.1653,
"step": 23
},
{
"epoch": 0.011736658719970658,
"grad_norm": Infinity,
"learning_rate": 0.00016,
"loss": 8.6687,
"step": 24
},
{
"epoch": 0.012225686166636102,
"grad_norm": Infinity,
"learning_rate": 0.0001666666666666667,
"loss": 9.1022,
"step": 25
},
{
"epoch": 0.012714713613301546,
"grad_norm": 3.8149141971211387e+18,
"learning_rate": 0.00017333333333333334,
"loss": 8.8296,
"step": 26
},
{
"epoch": 0.013203741059966991,
"grad_norm": Infinity,
"learning_rate": 0.00018,
"loss": 9.8113,
"step": 27
},
{
"epoch": 0.013692768506632435,
"grad_norm": Infinity,
"learning_rate": 0.0001866666666666667,
"loss": 9.417,
"step": 28
},
{
"epoch": 0.014181795953297879,
"grad_norm": Infinity,
"learning_rate": 0.00019333333333333333,
"loss": 9.168,
"step": 29
},
{
"epoch": 0.014670823399963322,
"grad_norm": Infinity,
"learning_rate": 0.0002,
"loss": 10.644,
"step": 30
},
{
"epoch": 0.015159850846628768,
"grad_norm": Infinity,
"learning_rate": 0.00019998292504580528,
"loss": 8.4753,
"step": 31
},
{
"epoch": 0.01564887829329421,
"grad_norm": Infinity,
"learning_rate": 0.0001999317060143023,
"loss": 9.0983,
"step": 32
},
{
"epoch": 0.016137905739959654,
"grad_norm": 1.1584913556352532e+18,
"learning_rate": 0.0001998463603967434,
"loss": 7.7383,
"step": 33
},
{
"epoch": 0.0166269331866251,
"grad_norm": Infinity,
"learning_rate": 0.00019972691733857883,
"loss": 9.1453,
"step": 34
},
{
"epoch": 0.0166269331866251,
"eval_loss": 9.285249710083008,
"eval_runtime": 881.9276,
"eval_samples_per_second": 2.929,
"eval_steps_per_second": 0.976,
"step": 34
},
{
"epoch": 0.017115960633290545,
"grad_norm": Infinity,
"learning_rate": 0.00019957341762950344,
"loss": 10.3859,
"step": 35
},
{
"epoch": 0.017604988079955988,
"grad_norm": Infinity,
"learning_rate": 0.0001993859136895274,
"loss": 8.1513,
"step": 36
},
{
"epoch": 0.018094015526621432,
"grad_norm": 7.999064190058758e+18,
"learning_rate": 0.00019916446955107428,
"loss": 9.6598,
"step": 37
},
{
"epoch": 0.018583042973286876,
"grad_norm": 2.2595998866116444e+18,
"learning_rate": 0.0001989091608371146,
"loss": 8.1904,
"step": 38
},
{
"epoch": 0.01907207041995232,
"grad_norm": Infinity,
"learning_rate": 0.00019862007473534025,
"loss": 9.4891,
"step": 39
},
{
"epoch": 0.019561097866617763,
"grad_norm": Infinity,
"learning_rate": 0.0001982973099683902,
"loss": 9.481,
"step": 40
},
{
"epoch": 0.020050125313283207,
"grad_norm": Infinity,
"learning_rate": 0.0001979409767601366,
"loss": 9.684,
"step": 41
},
{
"epoch": 0.02053915275994865,
"grad_norm": 1.0845123650277868e+18,
"learning_rate": 0.00019755119679804367,
"loss": 9.2871,
"step": 42
},
{
"epoch": 0.021028180206614098,
"grad_norm": Infinity,
"learning_rate": 0.0001971281031916114,
"loss": 9.423,
"step": 43
},
{
"epoch": 0.02151720765327954,
"grad_norm": Infinity,
"learning_rate": 0.00019667184042691875,
"loss": 8.6827,
"step": 44
},
{
"epoch": 0.022006235099944985,
"grad_norm": Infinity,
"learning_rate": 0.00019618256431728194,
"loss": 9.9237,
"step": 45
},
{
"epoch": 0.02249526254661043,
"grad_norm": 9.941431195118076e+18,
"learning_rate": 0.0001956604419500441,
"loss": 8.1136,
"step": 46
},
{
"epoch": 0.022984289993275873,
"grad_norm": Infinity,
"learning_rate": 0.00019510565162951537,
"loss": 9.7949,
"step": 47
},
{
"epoch": 0.023473317439941317,
"grad_norm": Infinity,
"learning_rate": 0.00019451838281608197,
"loss": 10.1889,
"step": 48
},
{
"epoch": 0.02396234488660676,
"grad_norm": Infinity,
"learning_rate": 0.00019389883606150566,
"loss": 8.871,
"step": 49
},
{
"epoch": 0.024451372333272204,
"grad_norm": Infinity,
"learning_rate": 0.00019324722294043558,
"loss": 10.5181,
"step": 50
},
{
"epoch": 0.024940399779937648,
"grad_norm": Infinity,
"learning_rate": 0.00019256376597815564,
"loss": 9.8439,
"step": 51
},
{
"epoch": 0.02542942722660309,
"grad_norm": Infinity,
"learning_rate": 0.00019184869857459232,
"loss": 9.1904,
"step": 52
},
{
"epoch": 0.02591845467326854,
"grad_norm": Infinity,
"learning_rate": 0.00019110226492460885,
"loss": 8.9795,
"step": 53
},
{
"epoch": 0.026407482119933982,
"grad_norm": 1.3233301388714312e+18,
"learning_rate": 0.0001903247199346129,
"loss": 8.6349,
"step": 54
},
{
"epoch": 0.026896509566599426,
"grad_norm": Infinity,
"learning_rate": 0.00018951632913550626,
"loss": 9.4657,
"step": 55
},
{
"epoch": 0.02738553701326487,
"grad_norm": Infinity,
"learning_rate": 0.0001886773685920062,
"loss": 9.6723,
"step": 56
},
{
"epoch": 0.027874564459930314,
"grad_norm": Infinity,
"learning_rate": 0.0001878081248083698,
"loss": 9.0433,
"step": 57
},
{
"epoch": 0.028363591906595757,
"grad_norm": 1.9613526846529864e+18,
"learning_rate": 0.00018690889463055283,
"loss": 10.0059,
"step": 58
},
{
"epoch": 0.0288526193532612,
"grad_norm": 1.2876933177477693e+18,
"learning_rate": 0.00018597998514483725,
"loss": 8.5998,
"step": 59
},
{
"epoch": 0.029341646799926645,
"grad_norm": Infinity,
"learning_rate": 0.00018502171357296144,
"loss": 10.2129,
"step": 60
},
{
"epoch": 0.02983067424659209,
"grad_norm": Infinity,
"learning_rate": 0.00018403440716378928,
"loss": 8.8496,
"step": 61
},
{
"epoch": 0.030319701693257536,
"grad_norm": Infinity,
"learning_rate": 0.00018301840308155507,
"loss": 10.0162,
"step": 62
},
{
"epoch": 0.03080872913992298,
"grad_norm": 5.941328178675974e+18,
"learning_rate": 0.00018197404829072215,
"loss": 9.124,
"step": 63
},
{
"epoch": 0.03129775658658842,
"grad_norm": Infinity,
"learning_rate": 0.00018090169943749476,
"loss": 9.6824,
"step": 64
},
{
"epoch": 0.03178678403325386,
"grad_norm": Infinity,
"learning_rate": 0.000179801722728024,
"loss": 9.5723,
"step": 65
},
{
"epoch": 0.03227581147991931,
"grad_norm": Infinity,
"learning_rate": 0.00017867449380334834,
"loss": 9.943,
"step": 66
},
{
"epoch": 0.03276483892658476,
"grad_norm": 1.2884108865238467e+18,
"learning_rate": 0.00017752039761111297,
"loss": 7.8637,
"step": 67
},
{
"epoch": 0.0332538663732502,
"grad_norm": Infinity,
"learning_rate": 0.00017633982827411032,
"loss": 8.926,
"step": 68
},
{
"epoch": 0.0332538663732502,
"eval_loss": 9.323250770568848,
"eval_runtime": 881.1726,
"eval_samples_per_second": 2.931,
"eval_steps_per_second": 0.977,
"step": 68
},
{
"epoch": 0.033742893819915645,
"grad_norm": Infinity,
"learning_rate": 0.00017513318895568737,
"loss": 9.5527,
"step": 69
},
{
"epoch": 0.03423192126658109,
"grad_norm": 8.3439319219857e+17,
"learning_rate": 0.00017390089172206592,
"loss": 8.2968,
"step": 70
},
{
"epoch": 0.03472094871324653,
"grad_norm": Infinity,
"learning_rate": 0.00017264335740162242,
"loss": 9.469,
"step": 71
},
{
"epoch": 0.035209976159911976,
"grad_norm": Infinity,
"learning_rate": 0.00017136101544117525,
"loss": 9.3297,
"step": 72
},
{
"epoch": 0.03569900360657742,
"grad_norm": Infinity,
"learning_rate": 0.0001700543037593291,
"loss": 9.2072,
"step": 73
},
{
"epoch": 0.036188031053242864,
"grad_norm": Infinity,
"learning_rate": 0.00016872366859692627,
"loss": 8.5818,
"step": 74
},
{
"epoch": 0.03667705849990831,
"grad_norm": Infinity,
"learning_rate": 0.00016736956436465573,
"loss": 9.1275,
"step": 75
},
{
"epoch": 0.03716608594657375,
"grad_norm": Infinity,
"learning_rate": 0.0001659924534878723,
"loss": 8.57,
"step": 76
},
{
"epoch": 0.037655113393239195,
"grad_norm": Infinity,
"learning_rate": 0.00016459280624867874,
"loss": 8.7525,
"step": 77
},
{
"epoch": 0.03814414083990464,
"grad_norm": 1.074333141353418e+19,
"learning_rate": 0.0001631711006253251,
"loss": 8.9513,
"step": 78
},
{
"epoch": 0.03863316828657008,
"grad_norm": Infinity,
"learning_rate": 0.0001617278221289793,
"loss": 8.9845,
"step": 79
},
{
"epoch": 0.039122195733235526,
"grad_norm": Infinity,
"learning_rate": 0.00016026346363792567,
"loss": 9.2195,
"step": 80
},
{
"epoch": 0.03961122317990097,
"grad_norm": Infinity,
"learning_rate": 0.00015877852522924732,
"loss": 9.7124,
"step": 81
},
{
"epoch": 0.040100250626566414,
"grad_norm": Infinity,
"learning_rate": 0.00015727351400805052,
"loss": 9.2742,
"step": 82
},
{
"epoch": 0.04058927807323186,
"grad_norm": Infinity,
"learning_rate": 0.00015574894393428855,
"loss": 11.2145,
"step": 83
},
{
"epoch": 0.0410783055198973,
"grad_norm": Infinity,
"learning_rate": 0.00015420533564724495,
"loss": 8.6546,
"step": 84
},
{
"epoch": 0.041567332966562745,
"grad_norm": Infinity,
"learning_rate": 0.0001526432162877356,
"loss": 8.4331,
"step": 85
},
{
"epoch": 0.042056360413228196,
"grad_norm": Infinity,
"learning_rate": 0.0001510631193180907,
"loss": 10.0226,
"step": 86
},
{
"epoch": 0.04254538785989364,
"grad_norm": Infinity,
"learning_rate": 0.0001494655843399779,
"loss": 9.735,
"step": 87
},
{
"epoch": 0.04303441530655908,
"grad_norm": Infinity,
"learning_rate": 0.00014785115691012864,
"loss": 9.6042,
"step": 88
},
{
"epoch": 0.04352344275322453,
"grad_norm": Infinity,
"learning_rate": 0.00014622038835403133,
"loss": 8.4645,
"step": 89
},
{
"epoch": 0.04401247019988997,
"grad_norm": Infinity,
"learning_rate": 0.00014457383557765386,
"loss": 9.7034,
"step": 90
},
{
"epoch": 0.044501497646555414,
"grad_norm": 1.0282610752728596e+19,
"learning_rate": 0.0001429120608772609,
"loss": 9.0363,
"step": 91
},
{
"epoch": 0.04499052509322086,
"grad_norm": Infinity,
"learning_rate": 0.00014123563174739037,
"loss": 9.3536,
"step": 92
},
{
"epoch": 0.0454795525398863,
"grad_norm": Infinity,
"learning_rate": 0.00013954512068705424,
"loss": 10.7834,
"step": 93
},
{
"epoch": 0.045968579986551746,
"grad_norm": Infinity,
"learning_rate": 0.00013784110500423104,
"loss": 9.8873,
"step": 94
},
{
"epoch": 0.04645760743321719,
"grad_norm": Infinity,
"learning_rate": 0.00013612416661871533,
"loss": 8.2064,
"step": 95
},
{
"epoch": 0.04694663487988263,
"grad_norm": Infinity,
"learning_rate": 0.00013439489186339282,
"loss": 8.2788,
"step": 96
},
{
"epoch": 0.04743566232654808,
"grad_norm": Infinity,
"learning_rate": 0.0001326538712840083,
"loss": 10.1197,
"step": 97
},
{
"epoch": 0.04792468977321352,
"grad_norm": Infinity,
"learning_rate": 0.00013090169943749476,
"loss": 9.6074,
"step": 98
},
{
"epoch": 0.048413717219878964,
"grad_norm": Infinity,
"learning_rate": 0.00012913897468893248,
"loss": 8.1992,
"step": 99
},
{
"epoch": 0.04890274466654441,
"grad_norm": Infinity,
"learning_rate": 0.0001273662990072083,
"loss": 10.0557,
"step": 100
},
{
"epoch": 0.04939177211320985,
"grad_norm": Infinity,
"learning_rate": 0.00012558427775944357,
"loss": 9.5867,
"step": 101
},
{
"epoch": 0.049880799559875295,
"grad_norm": Infinity,
"learning_rate": 0.00012379351950426187,
"loss": 9.1872,
"step": 102
},
{
"epoch": 0.049880799559875295,
"eval_loss": 9.34984302520752,
"eval_runtime": 881.2965,
"eval_samples_per_second": 2.931,
"eval_steps_per_second": 0.977,
"step": 102
},
{
"epoch": 0.05036982700654074,
"grad_norm": Infinity,
"learning_rate": 0.00012199463578396688,
"loss": 10.3933,
"step": 103
},
{
"epoch": 0.05085885445320618,
"grad_norm": Infinity,
"learning_rate": 0.00012018824091570103,
"loss": 8.6169,
"step": 104
},
{
"epoch": 0.051347881899871634,
"grad_norm": Infinity,
"learning_rate": 0.00011837495178165706,
"loss": 10.1478,
"step": 105
},
{
"epoch": 0.05183690934653708,
"grad_norm": Infinity,
"learning_rate": 0.000116555387618413,
"loss": 10.6195,
"step": 106
},
{
"epoch": 0.05232593679320252,
"grad_norm": Infinity,
"learning_rate": 0.00011473016980546377,
"loss": 9.3004,
"step": 107
},
{
"epoch": 0.052814964239867965,
"grad_norm": Infinity,
"learning_rate": 0.00011289992165302035,
"loss": 10.7517,
"step": 108
},
{
"epoch": 0.05330399168653341,
"grad_norm": Infinity,
"learning_rate": 0.00011106526818915008,
"loss": 9.5077,
"step": 109
},
{
"epoch": 0.05379301913319885,
"grad_norm": Infinity,
"learning_rate": 0.00010922683594633021,
"loss": 8.693,
"step": 110
},
{
"epoch": 0.054282046579864296,
"grad_norm": Infinity,
"learning_rate": 0.00010738525274748741,
"loss": 10.5717,
"step": 111
},
{
"epoch": 0.05477107402652974,
"grad_norm": Infinity,
"learning_rate": 0.000105541147491597,
"loss": 8.062,
"step": 112
},
{
"epoch": 0.05526010147319518,
"grad_norm": Infinity,
"learning_rate": 0.00010369514993891452,
"loss": 9.9227,
"step": 113
},
{
"epoch": 0.05574912891986063,
"grad_norm": Infinity,
"learning_rate": 0.00010184789049591299,
"loss": 9.0195,
"step": 114
},
{
"epoch": 0.05623815636652607,
"grad_norm": Infinity,
"learning_rate": 0.0001,
"loss": 8.6766,
"step": 115
},
{
"epoch": 0.056727183813191515,
"grad_norm": Infinity,
"learning_rate": 9.815210950408704e-05,
"loss": 9.2254,
"step": 116
},
{
"epoch": 0.05721621125985696,
"grad_norm": 1.6816025393206133e+19,
"learning_rate": 9.630485006108553e-05,
"loss": 8.8447,
"step": 117
},
{
"epoch": 0.0577052387065224,
"grad_norm": Infinity,
"learning_rate": 9.4458852508403e-05,
"loss": 9.6149,
"step": 118
},
{
"epoch": 0.058194266153187846,
"grad_norm": Infinity,
"learning_rate": 9.261474725251261e-05,
"loss": 9.6149,
"step": 119
},
{
"epoch": 0.05868329359985329,
"grad_norm": Infinity,
"learning_rate": 9.077316405366981e-05,
"loss": 9.4713,
"step": 120
},
{
"epoch": 0.05917232104651873,
"grad_norm": Infinity,
"learning_rate": 8.893473181084994e-05,
"loss": 8.8276,
"step": 121
},
{
"epoch": 0.05966134849318418,
"grad_norm": Infinity,
"learning_rate": 8.710007834697969e-05,
"loss": 8.9863,
"step": 122
},
{
"epoch": 0.06015037593984962,
"grad_norm": Infinity,
"learning_rate": 8.526983019453623e-05,
"loss": 9.3632,
"step": 123
},
{
"epoch": 0.06063940338651507,
"grad_norm": Infinity,
"learning_rate": 8.344461238158699e-05,
"loss": 9.7675,
"step": 124
},
{
"epoch": 0.061128430833180515,
"grad_norm": 2.9368804950629417e+18,
"learning_rate": 8.162504821834295e-05,
"loss": 8.2794,
"step": 125
},
{
"epoch": 0.06161745827984596,
"grad_norm": 4.274295618404352e+16,
"learning_rate": 7.9811759084299e-05,
"loss": 8.0011,
"step": 126
},
{
"epoch": 0.0621064857265114,
"grad_norm": Infinity,
"learning_rate": 7.800536421603317e-05,
"loss": 8.6106,
"step": 127
},
{
"epoch": 0.06259551317317684,
"grad_norm": Infinity,
"learning_rate": 7.620648049573815e-05,
"loss": 8.0169,
"step": 128
},
{
"epoch": 0.06308454061984228,
"grad_norm": Infinity,
"learning_rate": 7.441572224055644e-05,
"loss": 9.039,
"step": 129
},
{
"epoch": 0.06357356806650773,
"grad_norm": Infinity,
"learning_rate": 7.263370099279172e-05,
"loss": 8.755,
"step": 130
},
{
"epoch": 0.06406259551317317,
"grad_norm": Infinity,
"learning_rate": 7.086102531106754e-05,
"loss": 10.3864,
"step": 131
},
{
"epoch": 0.06455162295983861,
"grad_norm": Infinity,
"learning_rate": 6.909830056250527e-05,
"loss": 8.9227,
"step": 132
},
{
"epoch": 0.06504065040650407,
"grad_norm": Infinity,
"learning_rate": 6.734612871599168e-05,
"loss": 7.8021,
"step": 133
},
{
"epoch": 0.06552967785316952,
"grad_norm": Infinity,
"learning_rate": 6.560510813660719e-05,
"loss": 9.1572,
"step": 134
},
{
"epoch": 0.06601870529983496,
"grad_norm": Infinity,
"learning_rate": 6.387583338128471e-05,
"loss": 9.7205,
"step": 135
},
{
"epoch": 0.0665077327465004,
"grad_norm": 9.914893519909028e+17,
"learning_rate": 6.215889499576898e-05,
"loss": 8.1576,
"step": 136
},
{
"epoch": 0.0665077327465004,
"eval_loss": 9.333438873291016,
"eval_runtime": 880.1222,
"eval_samples_per_second": 2.935,
"eval_steps_per_second": 0.978,
"step": 136
},
{
"epoch": 0.06699676019316585,
"grad_norm": Infinity,
"learning_rate": 6.0454879312945754e-05,
"loss": 9.5434,
"step": 137
},
{
"epoch": 0.06748578763983129,
"grad_norm": Infinity,
"learning_rate": 5.876436825260967e-05,
"loss": 9.9258,
"step": 138
},
{
"epoch": 0.06797481508649673,
"grad_norm": Infinity,
"learning_rate": 5.708793912273911e-05,
"loss": 8.8349,
"step": 139
},
{
"epoch": 0.06846384253316218,
"grad_norm": Infinity,
"learning_rate": 5.542616442234618e-05,
"loss": 10.4222,
"step": 140
},
{
"epoch": 0.06895286997982762,
"grad_norm": Infinity,
"learning_rate": 5.37796116459687e-05,
"loss": 9.8649,
"step": 141
},
{
"epoch": 0.06944189742649307,
"grad_norm": Infinity,
"learning_rate": 5.214884308987136e-05,
"loss": 10.3785,
"step": 142
},
{
"epoch": 0.06993092487315851,
"grad_norm": Infinity,
"learning_rate": 5.0534415660022136e-05,
"loss": 9.2483,
"step": 143
},
{
"epoch": 0.07041995231982395,
"grad_norm": Infinity,
"learning_rate": 4.893688068190932e-05,
"loss": 10.5841,
"step": 144
},
{
"epoch": 0.0709089797664894,
"grad_norm": Infinity,
"learning_rate": 4.735678371226441e-05,
"loss": 8.9077,
"step": 145
},
{
"epoch": 0.07139800721315484,
"grad_norm": Infinity,
"learning_rate": 4.5794664352755055e-05,
"loss": 8.9045,
"step": 146
},
{
"epoch": 0.07188703465982028,
"grad_norm": Infinity,
"learning_rate": 4.425105606571145e-05,
"loss": 10.4432,
"step": 147
},
{
"epoch": 0.07237606210648573,
"grad_norm": Infinity,
"learning_rate": 4.272648599194948e-05,
"loss": 10.0172,
"step": 148
},
{
"epoch": 0.07286508955315117,
"grad_norm": Infinity,
"learning_rate": 4.12214747707527e-05,
"loss": 9.1662,
"step": 149
},
{
"epoch": 0.07335411699981662,
"grad_norm": Infinity,
"learning_rate": 3.973653636207437e-05,
"loss": 8.9558,
"step": 150
},
{
"epoch": 0.07384314444648206,
"grad_norm": 9.168760943570584e+18,
"learning_rate": 3.8272177871020723e-05,
"loss": 9.9009,
"step": 151
},
{
"epoch": 0.0743321718931475,
"grad_norm": Infinity,
"learning_rate": 3.682889937467493e-05,
"loss": 9.1193,
"step": 152
},
{
"epoch": 0.07482119933981295,
"grad_norm": Infinity,
"learning_rate": 3.540719375132129e-05,
"loss": 9.1242,
"step": 153
},
{
"epoch": 0.07531022678647839,
"grad_norm": Infinity,
"learning_rate": 3.400754651212776e-05,
"loss": 9.2777,
"step": 154
},
{
"epoch": 0.07579925423314383,
"grad_norm": Infinity,
"learning_rate": 3.263043563534428e-05,
"loss": 10.0257,
"step": 155
},
{
"epoch": 0.07628828167980928,
"grad_norm": Infinity,
"learning_rate": 3.1276331403073735e-05,
"loss": 9.0075,
"step": 156
},
{
"epoch": 0.07677730912647472,
"grad_norm": Infinity,
"learning_rate": 2.9945696240670906e-05,
"loss": 9.2834,
"step": 157
},
{
"epoch": 0.07726633657314017,
"grad_norm": Infinity,
"learning_rate": 2.8638984558824777e-05,
"loss": 9.9998,
"step": 158
},
{
"epoch": 0.07775536401980561,
"grad_norm": 6.262369407729664e+16,
"learning_rate": 2.7356642598377603e-05,
"loss": 9.3281,
"step": 159
},
{
"epoch": 0.07824439146647105,
"grad_norm": Infinity,
"learning_rate": 2.6099108277934103e-05,
"loss": 10.5182,
"step": 160
},
{
"epoch": 0.0787334189131365,
"grad_norm": 1.8735052790064742e+18,
"learning_rate": 2.4866811044312665e-05,
"loss": 9.7353,
"step": 161
},
{
"epoch": 0.07922244635980194,
"grad_norm": 1.1486916833747927e+19,
"learning_rate": 2.36601717258897e-05,
"loss": 8.3726,
"step": 162
},
{
"epoch": 0.07971147380646738,
"grad_norm": Infinity,
"learning_rate": 2.2479602388887012e-05,
"loss": 9.6089,
"step": 163
},
{
"epoch": 0.08020050125313283,
"grad_norm": Infinity,
"learning_rate": 2.132550619665168e-05,
"loss": 8.7235,
"step": 164
},
{
"epoch": 0.08068952869979827,
"grad_norm": Infinity,
"learning_rate": 2.0198277271976052e-05,
"loss": 8.9486,
"step": 165
},
{
"epoch": 0.08117855614646372,
"grad_norm": Infinity,
"learning_rate": 1.9098300562505266e-05,
"loss": 8.5101,
"step": 166
},
{
"epoch": 0.08166758359312916,
"grad_norm": Infinity,
"learning_rate": 1.8025951709277898e-05,
"loss": 8.4037,
"step": 167
},
{
"epoch": 0.0821566110397946,
"grad_norm": 1.4232143381118583e+19,
"learning_rate": 1.6981596918444953e-05,
"loss": 10.2633,
"step": 168
},
{
"epoch": 0.08264563848646005,
"grad_norm": Infinity,
"learning_rate": 1.5965592836210743e-05,
"loss": 9.3424,
"step": 169
},
{
"epoch": 0.08313466593312549,
"grad_norm": Infinity,
"learning_rate": 1.4978286427038601e-05,
"loss": 8.9031,
"step": 170
},
{
"epoch": 0.08313466593312549,
"eval_loss": 9.365218162536621,
"eval_runtime": 880.7771,
"eval_samples_per_second": 2.933,
"eval_steps_per_second": 0.978,
"step": 170
},
{
"epoch": 0.08362369337979095,
"grad_norm": Infinity,
"learning_rate": 1.4020014855162755e-05,
"loss": 8.3255,
"step": 171
},
{
"epoch": 0.08411272082645639,
"grad_norm": Infinity,
"learning_rate": 1.3091105369447165e-05,
"loss": 9.7255,
"step": 172
},
{
"epoch": 0.08460174827312184,
"grad_norm": 7.069207206448595e+18,
"learning_rate": 1.2191875191630209e-05,
"loss": 9.0893,
"step": 173
},
{
"epoch": 0.08509077571978728,
"grad_norm": Infinity,
"learning_rate": 1.1322631407993811e-05,
"loss": 9.1109,
"step": 174
},
{
"epoch": 0.08557980316645272,
"grad_norm": Infinity,
"learning_rate": 1.0483670864493778e-05,
"loss": 10.0142,
"step": 175
},
{
"epoch": 0.08606883061311817,
"grad_norm": 2.5997136051379896e+18,
"learning_rate": 9.675280065387116e-06,
"loss": 7.8569,
"step": 176
},
{
"epoch": 0.08655785805978361,
"grad_norm": Infinity,
"learning_rate": 8.897735075391155e-06,
"loss": 10.2652,
"step": 177
},
{
"epoch": 0.08704688550644905,
"grad_norm": Infinity,
"learning_rate": 8.151301425407699e-06,
"loss": 9.1787,
"step": 178
},
{
"epoch": 0.0875359129531145,
"grad_norm": Infinity,
"learning_rate": 7.43623402184438e-06,
"loss": 9.7712,
"step": 179
},
{
"epoch": 0.08802494039977994,
"grad_norm": Infinity,
"learning_rate": 6.75277705956443e-06,
"loss": 9.1567,
"step": 180
},
{
"epoch": 0.08851396784644538,
"grad_norm": Infinity,
"learning_rate": 6.1011639384943585e-06,
"loss": 9.415,
"step": 181
},
{
"epoch": 0.08900299529311083,
"grad_norm": Infinity,
"learning_rate": 5.481617183918053e-06,
"loss": 9.3436,
"step": 182
},
{
"epoch": 0.08949202273977627,
"grad_norm": Infinity,
"learning_rate": 4.8943483704846475e-06,
"loss": 8.6002,
"step": 183
},
{
"epoch": 0.08998105018644172,
"grad_norm": Infinity,
"learning_rate": 4.339558049955927e-06,
"loss": 9.525,
"step": 184
},
{
"epoch": 0.09047007763310716,
"grad_norm": Infinity,
"learning_rate": 3.817435682718096e-06,
"loss": 9.866,
"step": 185
},
{
"epoch": 0.0909591050797726,
"grad_norm": Infinity,
"learning_rate": 3.3281595730812575e-06,
"loss": 9.7505,
"step": 186
},
{
"epoch": 0.09144813252643805,
"grad_norm": Infinity,
"learning_rate": 2.8718968083886075e-06,
"loss": 9.0712,
"step": 187
},
{
"epoch": 0.09193715997310349,
"grad_norm": Infinity,
"learning_rate": 2.4488032019563402e-06,
"loss": 10.2603,
"step": 188
},
{
"epoch": 0.09242618741976893,
"grad_norm": Infinity,
"learning_rate": 2.0590232398634114e-06,
"loss": 8.6586,
"step": 189
},
{
"epoch": 0.09291521486643438,
"grad_norm": Infinity,
"learning_rate": 1.7026900316098215e-06,
"loss": 9.2198,
"step": 190
},
{
"epoch": 0.09340424231309982,
"grad_norm": Infinity,
"learning_rate": 1.3799252646597426e-06,
"loss": 9.557,
"step": 191
},
{
"epoch": 0.09389326975976527,
"grad_norm": Infinity,
"learning_rate": 1.0908391628854041e-06,
"loss": 9.7618,
"step": 192
},
{
"epoch": 0.09438229720643071,
"grad_norm": Infinity,
"learning_rate": 8.355304489257254e-07,
"loss": 9.523,
"step": 193
},
{
"epoch": 0.09487132465309615,
"grad_norm": 1.2673946288560013e+19,
"learning_rate": 6.140863104726391e-07,
"loss": 9.4956,
"step": 194
},
{
"epoch": 0.0953603520997616,
"grad_norm": Infinity,
"learning_rate": 4.2658237049655323e-07,
"loss": 9.7404,
"step": 195
},
{
"epoch": 0.09584937954642704,
"grad_norm": Infinity,
"learning_rate": 2.7308266142119785e-07,
"loss": 8.6763,
"step": 196
},
{
"epoch": 0.09633840699309248,
"grad_norm": Infinity,
"learning_rate": 1.5363960325660565e-07,
"loss": 9.8882,
"step": 197
},
{
"epoch": 0.09682743443975793,
"grad_norm": Infinity,
"learning_rate": 6.829398569770939e-08,
"loss": 8.5344,
"step": 198
},
{
"epoch": 0.09731646188642337,
"grad_norm": Infinity,
"learning_rate": 1.7074954194729044e-08,
"loss": 8.5774,
"step": 199
},
{
"epoch": 0.09780548933308882,
"grad_norm": Infinity,
"learning_rate": 0.0,
"loss": 8.7934,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.408959351914496e+17,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}