adammandic87's picture
Training in progress, step 200, checkpoint
86d8df5 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.04366335552887239,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00021831677764436196,
"grad_norm": 0.22467271983623505,
"learning_rate": 2e-05,
"loss": 0.8333,
"step": 1
},
{
"epoch": 0.00021831677764436196,
"eval_loss": 0.9435501098632812,
"eval_runtime": 183.8328,
"eval_samples_per_second": 10.493,
"eval_steps_per_second": 5.249,
"step": 1
},
{
"epoch": 0.00043663355528872393,
"grad_norm": 0.24361670017242432,
"learning_rate": 4e-05,
"loss": 0.8638,
"step": 2
},
{
"epoch": 0.0006549503329330859,
"grad_norm": 0.2159741222858429,
"learning_rate": 6e-05,
"loss": 1.0183,
"step": 3
},
{
"epoch": 0.0008732671105774479,
"grad_norm": 0.28429126739501953,
"learning_rate": 8e-05,
"loss": 1.0131,
"step": 4
},
{
"epoch": 0.0010915838882218098,
"grad_norm": 0.2774108350276947,
"learning_rate": 0.0001,
"loss": 0.9979,
"step": 5
},
{
"epoch": 0.0013099006658661718,
"grad_norm": 0.34028008580207825,
"learning_rate": 0.00012,
"loss": 0.9189,
"step": 6
},
{
"epoch": 0.0015282174435105338,
"grad_norm": 0.48363491892814636,
"learning_rate": 0.00014,
"loss": 0.8468,
"step": 7
},
{
"epoch": 0.0017465342211548957,
"grad_norm": 0.4408450424671173,
"learning_rate": 0.00016,
"loss": 0.8258,
"step": 8
},
{
"epoch": 0.001964850998799258,
"grad_norm": 0.4010414183139801,
"learning_rate": 0.00018,
"loss": 0.7643,
"step": 9
},
{
"epoch": 0.0021831677764436196,
"grad_norm": 0.23370158672332764,
"learning_rate": 0.0002,
"loss": 0.8982,
"step": 10
},
{
"epoch": 0.002401484554087982,
"grad_norm": 0.2269158512353897,
"learning_rate": 0.0001999863304992469,
"loss": 0.7584,
"step": 11
},
{
"epoch": 0.0026198013317323436,
"grad_norm": 0.19322407245635986,
"learning_rate": 0.00019994532573409262,
"loss": 0.6418,
"step": 12
},
{
"epoch": 0.0028381181093767058,
"grad_norm": 0.22146472334861755,
"learning_rate": 0.00019987699691483048,
"loss": 0.5475,
"step": 13
},
{
"epoch": 0.0030564348870210675,
"grad_norm": 0.23509173095226288,
"learning_rate": 0.00019978136272187747,
"loss": 0.7627,
"step": 14
},
{
"epoch": 0.0032747516646654297,
"grad_norm": 0.2376999855041504,
"learning_rate": 0.000199658449300667,
"loss": 0.5551,
"step": 15
},
{
"epoch": 0.0034930684423097914,
"grad_norm": 0.24817153811454773,
"learning_rate": 0.00019950829025450114,
"loss": 0.7661,
"step": 16
},
{
"epoch": 0.0037113852199541536,
"grad_norm": 0.19188500940799713,
"learning_rate": 0.00019933092663536382,
"loss": 0.6419,
"step": 17
},
{
"epoch": 0.003929701997598516,
"grad_norm": 0.2121303379535675,
"learning_rate": 0.00019912640693269752,
"loss": 0.7369,
"step": 18
},
{
"epoch": 0.0041480187752428775,
"grad_norm": 0.21718432009220123,
"learning_rate": 0.00019889478706014687,
"loss": 0.6756,
"step": 19
},
{
"epoch": 0.004366335552887239,
"grad_norm": 0.1782589852809906,
"learning_rate": 0.00019863613034027224,
"loss": 0.6777,
"step": 20
},
{
"epoch": 0.004584652330531601,
"grad_norm": 0.16271273791790009,
"learning_rate": 0.00019835050748723824,
"loss": 0.7569,
"step": 21
},
{
"epoch": 0.004802969108175964,
"grad_norm": 0.14470206201076508,
"learning_rate": 0.00019803799658748094,
"loss": 0.4718,
"step": 22
},
{
"epoch": 0.005021285885820325,
"grad_norm": 0.1509976089000702,
"learning_rate": 0.00019769868307835994,
"loss": 0.7292,
"step": 23
},
{
"epoch": 0.005239602663464687,
"grad_norm": 0.15710937976837158,
"learning_rate": 0.0001973326597248006,
"loss": 0.5817,
"step": 24
},
{
"epoch": 0.005457919441109049,
"grad_norm": 0.1630478948354721,
"learning_rate": 0.00019694002659393305,
"loss": 0.728,
"step": 25
},
{
"epoch": 0.0056762362187534115,
"grad_norm": 0.12629622220993042,
"learning_rate": 0.00019652089102773488,
"loss": 0.4336,
"step": 26
},
{
"epoch": 0.005894552996397773,
"grad_norm": 0.14236295223236084,
"learning_rate": 0.00019607536761368484,
"loss": 0.5446,
"step": 27
},
{
"epoch": 0.006112869774042135,
"grad_norm": 0.1700434535741806,
"learning_rate": 0.00019560357815343577,
"loss": 0.7135,
"step": 28
},
{
"epoch": 0.006331186551686497,
"grad_norm": 0.14569510519504547,
"learning_rate": 0.00019510565162951537,
"loss": 0.6261,
"step": 29
},
{
"epoch": 0.006549503329330859,
"grad_norm": 0.16239100694656372,
"learning_rate": 0.00019458172417006347,
"loss": 0.6628,
"step": 30
},
{
"epoch": 0.006767820106975221,
"grad_norm": 0.14534121751785278,
"learning_rate": 0.00019403193901161613,
"loss": 0.5007,
"step": 31
},
{
"epoch": 0.006986136884619583,
"grad_norm": 0.16187363862991333,
"learning_rate": 0.0001934564464599461,
"loss": 0.6864,
"step": 32
},
{
"epoch": 0.007204453662263945,
"grad_norm": 0.13931529223918915,
"learning_rate": 0.00019285540384897073,
"loss": 0.6503,
"step": 33
},
{
"epoch": 0.007422770439908307,
"grad_norm": 0.14639389514923096,
"learning_rate": 0.00019222897549773848,
"loss": 0.7199,
"step": 34
},
{
"epoch": 0.007641087217552669,
"grad_norm": 0.15582042932510376,
"learning_rate": 0.00019157733266550575,
"loss": 0.6016,
"step": 35
},
{
"epoch": 0.007859403995197032,
"grad_norm": 0.15808553993701935,
"learning_rate": 0.00019090065350491626,
"loss": 0.6748,
"step": 36
},
{
"epoch": 0.008077720772841393,
"grad_norm": 0.14080394804477692,
"learning_rate": 0.00019019912301329592,
"loss": 0.5573,
"step": 37
},
{
"epoch": 0.008296037550485755,
"grad_norm": 0.16601316630840302,
"learning_rate": 0.00018947293298207635,
"loss": 0.7531,
"step": 38
},
{
"epoch": 0.008514354328130117,
"grad_norm": 0.15201738476753235,
"learning_rate": 0.0001887222819443612,
"loss": 0.6083,
"step": 39
},
{
"epoch": 0.008732671105774479,
"grad_norm": 0.16929268836975098,
"learning_rate": 0.0001879473751206489,
"loss": 0.7018,
"step": 40
},
{
"epoch": 0.00895098788341884,
"grad_norm": 0.1630568504333496,
"learning_rate": 0.00018714842436272773,
"loss": 0.6234,
"step": 41
},
{
"epoch": 0.009169304661063202,
"grad_norm": 0.1684565395116806,
"learning_rate": 0.00018632564809575742,
"loss": 0.7069,
"step": 42
},
{
"epoch": 0.009387621438707564,
"grad_norm": 0.2026190608739853,
"learning_rate": 0.0001854792712585539,
"loss": 0.6886,
"step": 43
},
{
"epoch": 0.009605938216351927,
"grad_norm": 0.17672273516654968,
"learning_rate": 0.00018460952524209355,
"loss": 0.8231,
"step": 44
},
{
"epoch": 0.009824254993996289,
"grad_norm": 0.16011355817317963,
"learning_rate": 0.00018371664782625287,
"loss": 0.5992,
"step": 45
},
{
"epoch": 0.01004257177164065,
"grad_norm": 0.1554107815027237,
"learning_rate": 0.00018280088311480201,
"loss": 0.5707,
"step": 46
},
{
"epoch": 0.010260888549285013,
"grad_norm": 0.17009565234184265,
"learning_rate": 0.00018186248146866927,
"loss": 0.5901,
"step": 47
},
{
"epoch": 0.010479205326929374,
"grad_norm": 0.15228688716888428,
"learning_rate": 0.00018090169943749476,
"loss": 0.6009,
"step": 48
},
{
"epoch": 0.010697522104573736,
"grad_norm": 0.18469072878360748,
"learning_rate": 0.0001799187996894925,
"loss": 0.685,
"step": 49
},
{
"epoch": 0.010915838882218098,
"grad_norm": 0.1757270246744156,
"learning_rate": 0.00017891405093963938,
"loss": 0.7538,
"step": 50
},
{
"epoch": 0.010915838882218098,
"eval_loss": 0.6739084720611572,
"eval_runtime": 181.9504,
"eval_samples_per_second": 10.602,
"eval_steps_per_second": 5.304,
"step": 50
},
{
"epoch": 0.011134155659862461,
"grad_norm": 0.16260926425457,
"learning_rate": 0.00017788772787621126,
"loss": 0.6544,
"step": 51
},
{
"epoch": 0.011352472437506823,
"grad_norm": 0.16436129808425903,
"learning_rate": 0.00017684011108568592,
"loss": 0.5796,
"step": 52
},
{
"epoch": 0.011570789215151185,
"grad_norm": 0.15874071419239044,
"learning_rate": 0.0001757714869760335,
"loss": 0.6229,
"step": 53
},
{
"epoch": 0.011789105992795547,
"grad_norm": 0.17372044920921326,
"learning_rate": 0.0001746821476984154,
"loss": 0.8861,
"step": 54
},
{
"epoch": 0.012007422770439908,
"grad_norm": 0.190564826130867,
"learning_rate": 0.00017357239106731317,
"loss": 0.779,
"step": 55
},
{
"epoch": 0.01222573954808427,
"grad_norm": 0.17491184175014496,
"learning_rate": 0.00017244252047910892,
"loss": 0.528,
"step": 56
},
{
"epoch": 0.012444056325728632,
"grad_norm": 0.1566992700099945,
"learning_rate": 0.00017129284482913972,
"loss": 0.5963,
"step": 57
},
{
"epoch": 0.012662373103372994,
"grad_norm": 0.15744012594223022,
"learning_rate": 0.00017012367842724887,
"loss": 0.5224,
"step": 58
},
{
"epoch": 0.012880689881017357,
"grad_norm": 0.1761963814496994,
"learning_rate": 0.0001689353409118566,
"loss": 0.8546,
"step": 59
},
{
"epoch": 0.013099006658661719,
"grad_norm": 0.16946905851364136,
"learning_rate": 0.00016772815716257412,
"loss": 0.7221,
"step": 60
},
{
"epoch": 0.01331732343630608,
"grad_norm": 0.17242185771465302,
"learning_rate": 0.0001665024572113848,
"loss": 0.7315,
"step": 61
},
{
"epoch": 0.013535640213950442,
"grad_norm": 0.14320792257785797,
"learning_rate": 0.00016525857615241687,
"loss": 0.5442,
"step": 62
},
{
"epoch": 0.013753956991594804,
"grad_norm": 0.14897648990154266,
"learning_rate": 0.00016399685405033167,
"loss": 0.6125,
"step": 63
},
{
"epoch": 0.013972273769239166,
"grad_norm": 0.16310685873031616,
"learning_rate": 0.0001627176358473537,
"loss": 0.6272,
"step": 64
},
{
"epoch": 0.014190590546883528,
"grad_norm": 0.15317314863204956,
"learning_rate": 0.0001614212712689668,
"loss": 0.5583,
"step": 65
},
{
"epoch": 0.01440890732452789,
"grad_norm": 0.15903247892856598,
"learning_rate": 0.00016010811472830252,
"loss": 0.5744,
"step": 66
},
{
"epoch": 0.014627224102172253,
"grad_norm": 0.14471517503261566,
"learning_rate": 0.00015877852522924732,
"loss": 0.4967,
"step": 67
},
{
"epoch": 0.014845540879816614,
"grad_norm": 0.1645640879869461,
"learning_rate": 0.00015743286626829437,
"loss": 0.8364,
"step": 68
},
{
"epoch": 0.015063857657460976,
"grad_norm": 0.2042667418718338,
"learning_rate": 0.0001560715057351673,
"loss": 0.5209,
"step": 69
},
{
"epoch": 0.015282174435105338,
"grad_norm": 0.18461734056472778,
"learning_rate": 0.00015469481581224272,
"loss": 0.8209,
"step": 70
},
{
"epoch": 0.0155004912127497,
"grad_norm": 0.17951343953609467,
"learning_rate": 0.0001533031728727994,
"loss": 0.7302,
"step": 71
},
{
"epoch": 0.015718807990394063,
"grad_norm": 0.17561626434326172,
"learning_rate": 0.00015189695737812152,
"loss": 0.7459,
"step": 72
},
{
"epoch": 0.015937124768038425,
"grad_norm": 0.17738279700279236,
"learning_rate": 0.0001504765537734844,
"loss": 0.7624,
"step": 73
},
{
"epoch": 0.016155441545682787,
"grad_norm": 0.14604610204696655,
"learning_rate": 0.00014904235038305083,
"loss": 0.5576,
"step": 74
},
{
"epoch": 0.01637375832332715,
"grad_norm": 0.162835031747818,
"learning_rate": 0.00014759473930370736,
"loss": 0.6048,
"step": 75
},
{
"epoch": 0.01659207510097151,
"grad_norm": 0.16418945789337158,
"learning_rate": 0.0001461341162978688,
"loss": 0.5769,
"step": 76
},
{
"epoch": 0.016810391878615872,
"grad_norm": 0.19126634299755096,
"learning_rate": 0.00014466088068528068,
"loss": 0.7973,
"step": 77
},
{
"epoch": 0.017028708656260234,
"grad_norm": 0.1636025458574295,
"learning_rate": 0.00014317543523384928,
"loss": 0.6992,
"step": 78
},
{
"epoch": 0.017247025433904595,
"grad_norm": 0.1639864444732666,
"learning_rate": 0.00014167818604952906,
"loss": 0.6315,
"step": 79
},
{
"epoch": 0.017465342211548957,
"grad_norm": 0.20205020904541016,
"learning_rate": 0.00014016954246529696,
"loss": 1.0668,
"step": 80
},
{
"epoch": 0.01768365898919332,
"grad_norm": 0.16580188274383545,
"learning_rate": 0.00013864991692924523,
"loss": 0.7294,
"step": 81
},
{
"epoch": 0.01790197576683768,
"grad_norm": 0.17587777972221375,
"learning_rate": 0.00013711972489182208,
"loss": 0.6971,
"step": 82
},
{
"epoch": 0.018120292544482042,
"grad_norm": 0.18422681093215942,
"learning_rate": 0.00013557938469225167,
"loss": 0.7526,
"step": 83
},
{
"epoch": 0.018338609322126404,
"grad_norm": 0.16445504128932953,
"learning_rate": 0.00013402931744416433,
"loss": 0.6736,
"step": 84
},
{
"epoch": 0.018556926099770766,
"grad_norm": 0.14754797518253326,
"learning_rate": 0.00013246994692046836,
"loss": 0.4737,
"step": 85
},
{
"epoch": 0.018775242877415128,
"grad_norm": 0.19895146787166595,
"learning_rate": 0.00013090169943749476,
"loss": 0.7198,
"step": 86
},
{
"epoch": 0.018993559655059493,
"grad_norm": 0.16792307794094086,
"learning_rate": 0.0001293250037384465,
"loss": 0.7405,
"step": 87
},
{
"epoch": 0.019211876432703855,
"grad_norm": 0.1736898571252823,
"learning_rate": 0.00012774029087618446,
"loss": 0.6991,
"step": 88
},
{
"epoch": 0.019430193210348216,
"grad_norm": 0.19027847051620483,
"learning_rate": 0.00012614799409538198,
"loss": 0.8642,
"step": 89
},
{
"epoch": 0.019648509987992578,
"grad_norm": 0.16890498995780945,
"learning_rate": 0.00012454854871407994,
"loss": 0.5199,
"step": 90
},
{
"epoch": 0.01986682676563694,
"grad_norm": 0.17198000848293304,
"learning_rate": 0.00012294239200467516,
"loss": 0.6932,
"step": 91
},
{
"epoch": 0.0200851435432813,
"grad_norm": 0.17940305173397064,
"learning_rate": 0.0001213299630743747,
"loss": 0.5811,
"step": 92
},
{
"epoch": 0.020303460320925663,
"grad_norm": 0.17034873366355896,
"learning_rate": 0.00011971170274514802,
"loss": 0.6274,
"step": 93
},
{
"epoch": 0.020521777098570025,
"grad_norm": 0.17157679796218872,
"learning_rate": 0.000118088053433211,
"loss": 0.6947,
"step": 94
},
{
"epoch": 0.020740093876214387,
"grad_norm": 0.18038637936115265,
"learning_rate": 0.00011645945902807341,
"loss": 0.6019,
"step": 95
},
{
"epoch": 0.02095841065385875,
"grad_norm": 0.16414083540439606,
"learning_rate": 0.0001148263647711842,
"loss": 0.5772,
"step": 96
},
{
"epoch": 0.02117672743150311,
"grad_norm": 0.17010308802127838,
"learning_rate": 0.00011318921713420691,
"loss": 0.6766,
"step": 97
},
{
"epoch": 0.021395044209147472,
"grad_norm": 0.17190682888031006,
"learning_rate": 0.00011154846369695863,
"loss": 0.6057,
"step": 98
},
{
"epoch": 0.021613360986791834,
"grad_norm": 0.18158312141895294,
"learning_rate": 0.0001099045530250463,
"loss": 0.7767,
"step": 99
},
{
"epoch": 0.021831677764436196,
"grad_norm": 0.18446941673755646,
"learning_rate": 0.00010825793454723325,
"loss": 0.7482,
"step": 100
},
{
"epoch": 0.021831677764436196,
"eval_loss": 0.6601452231407166,
"eval_runtime": 181.8265,
"eval_samples_per_second": 10.609,
"eval_steps_per_second": 5.307,
"step": 100
},
{
"epoch": 0.022049994542080557,
"grad_norm": 0.21762917935848236,
"learning_rate": 0.00010660905843256994,
"loss": 0.7735,
"step": 101
},
{
"epoch": 0.022268311319724923,
"grad_norm": 0.18513105809688568,
"learning_rate": 0.00010495837546732224,
"loss": 0.7981,
"step": 102
},
{
"epoch": 0.022486628097369284,
"grad_norm": 0.1725614219903946,
"learning_rate": 0.00010330633693173082,
"loss": 0.66,
"step": 103
},
{
"epoch": 0.022704944875013646,
"grad_norm": 0.18261019885540009,
"learning_rate": 0.00010165339447663587,
"loss": 0.8389,
"step": 104
},
{
"epoch": 0.022923261652658008,
"grad_norm": 0.16905616223812103,
"learning_rate": 0.0001,
"loss": 0.5165,
"step": 105
},
{
"epoch": 0.02314157843030237,
"grad_norm": 0.18981021642684937,
"learning_rate": 9.834660552336415e-05,
"loss": 0.8955,
"step": 106
},
{
"epoch": 0.02335989520794673,
"grad_norm": 0.18465036153793335,
"learning_rate": 9.669366306826919e-05,
"loss": 0.6604,
"step": 107
},
{
"epoch": 0.023578211985591093,
"grad_norm": 0.1783265918493271,
"learning_rate": 9.504162453267777e-05,
"loss": 0.6334,
"step": 108
},
{
"epoch": 0.023796528763235455,
"grad_norm": 0.16945728659629822,
"learning_rate": 9.339094156743007e-05,
"loss": 0.5026,
"step": 109
},
{
"epoch": 0.024014845540879817,
"grad_norm": 0.16877439618110657,
"learning_rate": 9.174206545276677e-05,
"loss": 0.6765,
"step": 110
},
{
"epoch": 0.02423316231852418,
"grad_norm": 0.18142911791801453,
"learning_rate": 9.009544697495374e-05,
"loss": 0.6832,
"step": 111
},
{
"epoch": 0.02445147909616854,
"grad_norm": 0.17140087485313416,
"learning_rate": 8.845153630304139e-05,
"loss": 0.6352,
"step": 112
},
{
"epoch": 0.024669795873812902,
"grad_norm": 0.16582410037517548,
"learning_rate": 8.681078286579311e-05,
"loss": 0.5553,
"step": 113
},
{
"epoch": 0.024888112651457264,
"grad_norm": 0.15053234994411469,
"learning_rate": 8.517363522881579e-05,
"loss": 0.5002,
"step": 114
},
{
"epoch": 0.025106429429101625,
"grad_norm": 0.17048825323581696,
"learning_rate": 8.35405409719266e-05,
"loss": 0.6109,
"step": 115
},
{
"epoch": 0.025324746206745987,
"grad_norm": 0.16614414751529694,
"learning_rate": 8.191194656678904e-05,
"loss": 0.6749,
"step": 116
},
{
"epoch": 0.02554306298439035,
"grad_norm": 0.17033010721206665,
"learning_rate": 8.028829725485199e-05,
"loss": 0.5342,
"step": 117
},
{
"epoch": 0.025761379762034714,
"grad_norm": 0.18463349342346191,
"learning_rate": 7.867003692562534e-05,
"loss": 0.7151,
"step": 118
},
{
"epoch": 0.025979696539679076,
"grad_norm": 0.15648098289966583,
"learning_rate": 7.705760799532485e-05,
"loss": 0.5211,
"step": 119
},
{
"epoch": 0.026198013317323438,
"grad_norm": 0.16885478794574738,
"learning_rate": 7.54514512859201e-05,
"loss": 0.6123,
"step": 120
},
{
"epoch": 0.0264163300949678,
"grad_norm": 0.16653332114219666,
"learning_rate": 7.385200590461803e-05,
"loss": 0.6589,
"step": 121
},
{
"epoch": 0.02663464687261216,
"grad_norm": 0.1621529459953308,
"learning_rate": 7.225970912381556e-05,
"loss": 0.5623,
"step": 122
},
{
"epoch": 0.026852963650256523,
"grad_norm": 0.17834222316741943,
"learning_rate": 7.067499626155354e-05,
"loss": 0.5837,
"step": 123
},
{
"epoch": 0.027071280427900885,
"grad_norm": 0.17469386756420135,
"learning_rate": 6.909830056250527e-05,
"loss": 0.7037,
"step": 124
},
{
"epoch": 0.027289597205545246,
"grad_norm": 0.16732703149318695,
"learning_rate": 6.753005307953167e-05,
"loss": 0.6519,
"step": 125
},
{
"epoch": 0.027507913983189608,
"grad_norm": 0.19885458052158356,
"learning_rate": 6.59706825558357e-05,
"loss": 0.637,
"step": 126
},
{
"epoch": 0.02772623076083397,
"grad_norm": 0.15952806174755096,
"learning_rate": 6.442061530774834e-05,
"loss": 0.5294,
"step": 127
},
{
"epoch": 0.02794454753847833,
"grad_norm": 0.18024499714374542,
"learning_rate": 6.28802751081779e-05,
"loss": 0.7163,
"step": 128
},
{
"epoch": 0.028162864316122693,
"grad_norm": 0.1813889443874359,
"learning_rate": 6.135008307075481e-05,
"loss": 0.8399,
"step": 129
},
{
"epoch": 0.028381181093767055,
"grad_norm": 0.16543258726596832,
"learning_rate": 5.983045753470308e-05,
"loss": 0.6442,
"step": 130
},
{
"epoch": 0.028599497871411417,
"grad_norm": 0.21711844205856323,
"learning_rate": 5.832181395047098e-05,
"loss": 0.9936,
"step": 131
},
{
"epoch": 0.02881781464905578,
"grad_norm": 0.16442720592021942,
"learning_rate": 5.6824564766150726e-05,
"loss": 0.5848,
"step": 132
},
{
"epoch": 0.02903613142670014,
"grad_norm": 0.16723956167697906,
"learning_rate": 5.533911931471936e-05,
"loss": 0.6755,
"step": 133
},
{
"epoch": 0.029254448204344505,
"grad_norm": 0.16711710393428802,
"learning_rate": 5.386588370213124e-05,
"loss": 0.6657,
"step": 134
},
{
"epoch": 0.029472764981988867,
"grad_norm": 0.16483482718467712,
"learning_rate": 5.240526069629265e-05,
"loss": 0.6668,
"step": 135
},
{
"epoch": 0.02969108175963323,
"grad_norm": 0.17765454947948456,
"learning_rate": 5.095764961694922e-05,
"loss": 0.6791,
"step": 136
},
{
"epoch": 0.02990939853727759,
"grad_norm": 0.18251171708106995,
"learning_rate": 4.952344622651566e-05,
"loss": 0.7367,
"step": 137
},
{
"epoch": 0.030127715314921952,
"grad_norm": 0.17135152220726013,
"learning_rate": 4.810304262187852e-05,
"loss": 0.6704,
"step": 138
},
{
"epoch": 0.030346032092566314,
"grad_norm": 0.194648876786232,
"learning_rate": 4.669682712720065e-05,
"loss": 0.9007,
"step": 139
},
{
"epoch": 0.030564348870210676,
"grad_norm": 0.14134380221366882,
"learning_rate": 4.530518418775733e-05,
"loss": 0.4324,
"step": 140
},
{
"epoch": 0.030782665647855038,
"grad_norm": 0.16082902252674103,
"learning_rate": 4.392849426483274e-05,
"loss": 0.5531,
"step": 141
},
{
"epoch": 0.0310009824254994,
"grad_norm": 0.185900017619133,
"learning_rate": 4.256713373170564e-05,
"loss": 0.8044,
"step": 142
},
{
"epoch": 0.03121929920314376,
"grad_norm": 0.16822083294391632,
"learning_rate": 4.12214747707527e-05,
"loss": 0.63,
"step": 143
},
{
"epoch": 0.031437615980788126,
"grad_norm": 0.1961585134267807,
"learning_rate": 3.9891885271697496e-05,
"loss": 0.7769,
"step": 144
},
{
"epoch": 0.03165593275843249,
"grad_norm": 0.17126162350177765,
"learning_rate": 3.857872873103322e-05,
"loss": 0.5417,
"step": 145
},
{
"epoch": 0.03187424953607685,
"grad_norm": 0.17973680794239044,
"learning_rate": 3.7282364152646297e-05,
"loss": 0.6837,
"step": 146
},
{
"epoch": 0.03209256631372121,
"grad_norm": 0.18085865676403046,
"learning_rate": 3.600314594966834e-05,
"loss": 0.7359,
"step": 147
},
{
"epoch": 0.03231088309136557,
"grad_norm": 0.1475389152765274,
"learning_rate": 3.4741423847583134e-05,
"loss": 0.4654,
"step": 148
},
{
"epoch": 0.032529199869009935,
"grad_norm": 0.1810745894908905,
"learning_rate": 3.349754278861517e-05,
"loss": 0.7939,
"step": 149
},
{
"epoch": 0.0327475166466543,
"grad_norm": 0.18114720284938812,
"learning_rate": 3.227184283742591e-05,
"loss": 0.6863,
"step": 150
},
{
"epoch": 0.0327475166466543,
"eval_loss": 0.6545336842536926,
"eval_runtime": 181.8183,
"eval_samples_per_second": 10.609,
"eval_steps_per_second": 5.307,
"step": 150
},
{
"epoch": 0.03296583342429866,
"grad_norm": 0.17468896508216858,
"learning_rate": 3.106465908814342e-05,
"loss": 0.6614,
"step": 151
},
{
"epoch": 0.03318415020194302,
"grad_norm": 0.15946292877197266,
"learning_rate": 2.9876321572751144e-05,
"loss": 0.5086,
"step": 152
},
{
"epoch": 0.03340246697958738,
"grad_norm": 0.17035330832004547,
"learning_rate": 2.87071551708603e-05,
"loss": 0.6278,
"step": 153
},
{
"epoch": 0.033620783757231744,
"grad_norm": 0.18423694372177124,
"learning_rate": 2.7557479520891104e-05,
"loss": 0.6574,
"step": 154
},
{
"epoch": 0.033839100534876106,
"grad_norm": 0.17745865881443024,
"learning_rate": 2.6427608932686843e-05,
"loss": 0.7644,
"step": 155
},
{
"epoch": 0.03405741731252047,
"grad_norm": 0.23100459575653076,
"learning_rate": 2.5317852301584643e-05,
"loss": 0.8962,
"step": 156
},
{
"epoch": 0.03427573409016483,
"grad_norm": 0.2258739024400711,
"learning_rate": 2.422851302396655e-05,
"loss": 0.7379,
"step": 157
},
{
"epoch": 0.03449405086780919,
"grad_norm": 0.189512699842453,
"learning_rate": 2.315988891431412e-05,
"loss": 0.8372,
"step": 158
},
{
"epoch": 0.03471236764545355,
"grad_norm": 0.18781927227973938,
"learning_rate": 2.2112272123788768e-05,
"loss": 0.6743,
"step": 159
},
{
"epoch": 0.034930684423097914,
"grad_norm": 0.15858572721481323,
"learning_rate": 2.1085949060360654e-05,
"loss": 0.4646,
"step": 160
},
{
"epoch": 0.035149001200742276,
"grad_norm": 0.18067395687103271,
"learning_rate": 2.008120031050753e-05,
"loss": 0.6516,
"step": 161
},
{
"epoch": 0.03536731797838664,
"grad_norm": 0.1741492599248886,
"learning_rate": 1.9098300562505266e-05,
"loss": 0.6783,
"step": 162
},
{
"epoch": 0.035585634756031,
"grad_norm": 0.17116688191890717,
"learning_rate": 1.8137518531330767e-05,
"loss": 0.582,
"step": 163
},
{
"epoch": 0.03580395153367536,
"grad_norm": 0.19832322001457214,
"learning_rate": 1.7199116885197995e-05,
"loss": 0.838,
"step": 164
},
{
"epoch": 0.03602226831131972,
"grad_norm": 0.1676938533782959,
"learning_rate": 1.6283352173747145e-05,
"loss": 0.5495,
"step": 165
},
{
"epoch": 0.036240585088964085,
"grad_norm": 0.16515184938907623,
"learning_rate": 1.5390474757906446e-05,
"loss": 0.5651,
"step": 166
},
{
"epoch": 0.03645890186660845,
"grad_norm": 0.20315131545066833,
"learning_rate": 1.4520728741446089e-05,
"loss": 0.77,
"step": 167
},
{
"epoch": 0.03667721864425281,
"grad_norm": 0.18013328313827515,
"learning_rate": 1.3674351904242611e-05,
"loss": 0.7325,
"step": 168
},
{
"epoch": 0.03689553542189717,
"grad_norm": 0.18683043122291565,
"learning_rate": 1.2851575637272262e-05,
"loss": 0.6805,
"step": 169
},
{
"epoch": 0.03711385219954153,
"grad_norm": 0.18305127322673798,
"learning_rate": 1.2052624879351104e-05,
"loss": 0.7239,
"step": 170
},
{
"epoch": 0.037332168977185894,
"grad_norm": 0.19132886826992035,
"learning_rate": 1.1277718055638819e-05,
"loss": 0.746,
"step": 171
},
{
"epoch": 0.037550485754830255,
"grad_norm": 0.18872715532779694,
"learning_rate": 1.0527067017923654e-05,
"loss": 0.8513,
"step": 172
},
{
"epoch": 0.037768802532474624,
"grad_norm": 0.18976855278015137,
"learning_rate": 9.80087698670411e-06,
"loss": 0.8007,
"step": 173
},
{
"epoch": 0.037987119310118986,
"grad_norm": 0.1643442064523697,
"learning_rate": 9.09934649508375e-06,
"loss": 0.4781,
"step": 174
},
{
"epoch": 0.03820543608776335,
"grad_norm": 0.17088055610656738,
"learning_rate": 8.422667334494249e-06,
"loss": 0.5486,
"step": 175
},
{
"epoch": 0.03842375286540771,
"grad_norm": 0.16870273649692535,
"learning_rate": 7.771024502261526e-06,
"loss": 0.5814,
"step": 176
},
{
"epoch": 0.03864206964305207,
"grad_norm": 0.19257135689258575,
"learning_rate": 7.144596151029303e-06,
"loss": 0.615,
"step": 177
},
{
"epoch": 0.03886038642069643,
"grad_norm": 0.16927644610404968,
"learning_rate": 6.543553540053926e-06,
"loss": 0.6345,
"step": 178
},
{
"epoch": 0.039078703198340795,
"grad_norm": 0.16874222457408905,
"learning_rate": 5.968060988383883e-06,
"loss": 0.4597,
"step": 179
},
{
"epoch": 0.039297019975985156,
"grad_norm": 0.16570569574832916,
"learning_rate": 5.418275829936537e-06,
"loss": 0.6071,
"step": 180
},
{
"epoch": 0.03951533675362952,
"grad_norm": 0.17248547077178955,
"learning_rate": 4.8943483704846475e-06,
"loss": 0.6086,
"step": 181
},
{
"epoch": 0.03973365353127388,
"grad_norm": 0.17762534320354462,
"learning_rate": 4.3964218465642355e-06,
"loss": 0.6477,
"step": 182
},
{
"epoch": 0.03995197030891824,
"grad_norm": 0.2004290670156479,
"learning_rate": 3.924632386315186e-06,
"loss": 0.7786,
"step": 183
},
{
"epoch": 0.0401702870865626,
"grad_norm": 0.17008547484874725,
"learning_rate": 3.4791089722651436e-06,
"loss": 0.6086,
"step": 184
},
{
"epoch": 0.040388603864206965,
"grad_norm": 0.17387335002422333,
"learning_rate": 3.059973406066963e-06,
"loss": 0.6396,
"step": 185
},
{
"epoch": 0.04060692064185133,
"grad_norm": 0.16781817376613617,
"learning_rate": 2.667340275199426e-06,
"loss": 0.4575,
"step": 186
},
{
"epoch": 0.04082523741949569,
"grad_norm": 0.17695757746696472,
"learning_rate": 2.3013169216400733e-06,
"loss": 0.7397,
"step": 187
},
{
"epoch": 0.04104355419714005,
"grad_norm": 0.1608322560787201,
"learning_rate": 1.9620034125190644e-06,
"loss": 0.4613,
"step": 188
},
{
"epoch": 0.04126187097478441,
"grad_norm": 0.17157816886901855,
"learning_rate": 1.6494925127617634e-06,
"loss": 0.6781,
"step": 189
},
{
"epoch": 0.041480187752428774,
"grad_norm": 0.18058647215366364,
"learning_rate": 1.3638696597277679e-06,
"loss": 0.7726,
"step": 190
},
{
"epoch": 0.041698504530073136,
"grad_norm": 0.1864567995071411,
"learning_rate": 1.1052129398531507e-06,
"loss": 0.7157,
"step": 191
},
{
"epoch": 0.0419168213077175,
"grad_norm": 0.1998099386692047,
"learning_rate": 8.735930673024806e-07,
"loss": 0.6688,
"step": 192
},
{
"epoch": 0.04213513808536186,
"grad_norm": 0.17582550644874573,
"learning_rate": 6.690733646361857e-07,
"loss": 0.6509,
"step": 193
},
{
"epoch": 0.04235345486300622,
"grad_norm": 0.19661235809326172,
"learning_rate": 4.917097454988584e-07,
"loss": 0.6709,
"step": 194
},
{
"epoch": 0.04257177164065058,
"grad_norm": 0.1901334822177887,
"learning_rate": 3.415506993330153e-07,
"loss": 0.7045,
"step": 195
},
{
"epoch": 0.042790088418294944,
"grad_norm": 0.1601884961128235,
"learning_rate": 2.1863727812254653e-07,
"loss": 0.5396,
"step": 196
},
{
"epoch": 0.043008405195939306,
"grad_norm": 0.1761172115802765,
"learning_rate": 1.230030851695263e-07,
"loss": 0.7687,
"step": 197
},
{
"epoch": 0.04322672197358367,
"grad_norm": 0.1702435463666916,
"learning_rate": 5.467426590739511e-08,
"loss": 0.6001,
"step": 198
},
{
"epoch": 0.04344503875122803,
"grad_norm": 0.16501539945602417,
"learning_rate": 1.3669500753099585e-08,
"loss": 0.5596,
"step": 199
},
{
"epoch": 0.04366335552887239,
"grad_norm": 0.19477379322052002,
"learning_rate": 0.0,
"loss": 0.7117,
"step": 200
},
{
"epoch": 0.04366335552887239,
"eval_loss": 0.6532227993011475,
"eval_runtime": 181.8705,
"eval_samples_per_second": 10.606,
"eval_steps_per_second": 5.306,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.3142821265473536e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}