0x1202's picture
Training in progress, step 150, checkpoint
89ee062 verified
raw
history blame
27.7 kB
{
"best_metric": 0.8521701693534851,
"best_model_checkpoint": "miner_id_24/checkpoint-150",
"epoch": 0.042492917847025496,
"eval_steps": 50,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00028328611898016995,
"grad_norm": 2.4459738731384277,
"learning_rate": 5e-06,
"loss": 1.0328,
"step": 1
},
{
"epoch": 0.00028328611898016995,
"eval_loss": 1.364790678024292,
"eval_runtime": 485.4956,
"eval_samples_per_second": 12.247,
"eval_steps_per_second": 6.124,
"step": 1
},
{
"epoch": 0.0005665722379603399,
"grad_norm": 0.7349909543991089,
"learning_rate": 1e-05,
"loss": 1.044,
"step": 2
},
{
"epoch": 0.0008498583569405099,
"grad_norm": 0.5141507387161255,
"learning_rate": 1.5e-05,
"loss": 1.0227,
"step": 3
},
{
"epoch": 0.0011331444759206798,
"grad_norm": 1.156713604927063,
"learning_rate": 2e-05,
"loss": 1.0904,
"step": 4
},
{
"epoch": 0.00141643059490085,
"grad_norm": 0.7857816219329834,
"learning_rate": 2.5e-05,
"loss": 1.1226,
"step": 5
},
{
"epoch": 0.0016997167138810198,
"grad_norm": 0.5737718939781189,
"learning_rate": 3e-05,
"loss": 1.0554,
"step": 6
},
{
"epoch": 0.00198300283286119,
"grad_norm": 0.7259950637817383,
"learning_rate": 3.5e-05,
"loss": 1.0777,
"step": 7
},
{
"epoch": 0.0022662889518413596,
"grad_norm": 0.5065688490867615,
"learning_rate": 4e-05,
"loss": 1.0204,
"step": 8
},
{
"epoch": 0.0025495750708215297,
"grad_norm": 0.41538459062576294,
"learning_rate": 4.5e-05,
"loss": 1.04,
"step": 9
},
{
"epoch": 0.0028328611898017,
"grad_norm": 0.3766935467720032,
"learning_rate": 5e-05,
"loss": 0.9753,
"step": 10
},
{
"epoch": 0.0031161473087818695,
"grad_norm": 0.40806570649147034,
"learning_rate": 5.500000000000001e-05,
"loss": 0.9953,
"step": 11
},
{
"epoch": 0.0033994334277620396,
"grad_norm": 0.3899538218975067,
"learning_rate": 6e-05,
"loss": 1.0186,
"step": 12
},
{
"epoch": 0.0036827195467422098,
"grad_norm": 0.43268951773643494,
"learning_rate": 6.500000000000001e-05,
"loss": 0.9802,
"step": 13
},
{
"epoch": 0.00396600566572238,
"grad_norm": 0.42716556787490845,
"learning_rate": 7e-05,
"loss": 0.9618,
"step": 14
},
{
"epoch": 0.00424929178470255,
"grad_norm": 0.4129604697227478,
"learning_rate": 7.500000000000001e-05,
"loss": 0.9033,
"step": 15
},
{
"epoch": 0.004532577903682719,
"grad_norm": 0.40332239866256714,
"learning_rate": 8e-05,
"loss": 0.8851,
"step": 16
},
{
"epoch": 0.004815864022662889,
"grad_norm": 0.42246365547180176,
"learning_rate": 8.5e-05,
"loss": 0.995,
"step": 17
},
{
"epoch": 0.0050991501416430595,
"grad_norm": 0.40158501267433167,
"learning_rate": 9e-05,
"loss": 0.9784,
"step": 18
},
{
"epoch": 0.00538243626062323,
"grad_norm": 0.3314235210418701,
"learning_rate": 9.5e-05,
"loss": 0.8783,
"step": 19
},
{
"epoch": 0.0056657223796034,
"grad_norm": 0.30537742376327515,
"learning_rate": 0.0001,
"loss": 0.8774,
"step": 20
},
{
"epoch": 0.00594900849858357,
"grad_norm": 0.3494546711444855,
"learning_rate": 9.999238475781957e-05,
"loss": 0.8816,
"step": 21
},
{
"epoch": 0.006232294617563739,
"grad_norm": 0.3360932767391205,
"learning_rate": 9.99695413509548e-05,
"loss": 0.8611,
"step": 22
},
{
"epoch": 0.006515580736543909,
"grad_norm": 0.3689824044704437,
"learning_rate": 9.99314767377287e-05,
"loss": 0.8842,
"step": 23
},
{
"epoch": 0.006798866855524079,
"grad_norm": 0.37334781885147095,
"learning_rate": 9.987820251299122e-05,
"loss": 0.9124,
"step": 24
},
{
"epoch": 0.007082152974504249,
"grad_norm": 0.38459479808807373,
"learning_rate": 9.980973490458728e-05,
"loss": 0.8801,
"step": 25
},
{
"epoch": 0.0073654390934844195,
"grad_norm": 0.3251090943813324,
"learning_rate": 9.972609476841367e-05,
"loss": 0.8642,
"step": 26
},
{
"epoch": 0.00764872521246459,
"grad_norm": 0.3844033479690552,
"learning_rate": 9.962730758206611e-05,
"loss": 0.9023,
"step": 27
},
{
"epoch": 0.00793201133144476,
"grad_norm": 0.40686604380607605,
"learning_rate": 9.951340343707852e-05,
"loss": 0.9195,
"step": 28
},
{
"epoch": 0.00821529745042493,
"grad_norm": 0.30939722061157227,
"learning_rate": 9.938441702975689e-05,
"loss": 0.8657,
"step": 29
},
{
"epoch": 0.0084985835694051,
"grad_norm": 0.4041453003883362,
"learning_rate": 9.924038765061042e-05,
"loss": 0.9044,
"step": 30
},
{
"epoch": 0.008781869688385268,
"grad_norm": 0.4817129373550415,
"learning_rate": 9.908135917238321e-05,
"loss": 0.9488,
"step": 31
},
{
"epoch": 0.009065155807365438,
"grad_norm": 0.4093549847602844,
"learning_rate": 9.890738003669029e-05,
"loss": 0.9094,
"step": 32
},
{
"epoch": 0.009348441926345609,
"grad_norm": 0.43957093358039856,
"learning_rate": 9.871850323926177e-05,
"loss": 0.9521,
"step": 33
},
{
"epoch": 0.009631728045325779,
"grad_norm": 0.517327070236206,
"learning_rate": 9.851478631379982e-05,
"loss": 0.8606,
"step": 34
},
{
"epoch": 0.009915014164305949,
"grad_norm": 0.6792945861816406,
"learning_rate": 9.829629131445342e-05,
"loss": 1.0191,
"step": 35
},
{
"epoch": 0.010198300283286119,
"grad_norm": 0.5788185000419617,
"learning_rate": 9.806308479691595e-05,
"loss": 0.9683,
"step": 36
},
{
"epoch": 0.010481586402266289,
"grad_norm": 0.63746178150177,
"learning_rate": 9.781523779815179e-05,
"loss": 1.0815,
"step": 37
},
{
"epoch": 0.01076487252124646,
"grad_norm": 0.5034915208816528,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9157,
"step": 38
},
{
"epoch": 0.01104815864022663,
"grad_norm": 0.568718433380127,
"learning_rate": 9.727592877996585e-05,
"loss": 1.0136,
"step": 39
},
{
"epoch": 0.0113314447592068,
"grad_norm": 0.7134827971458435,
"learning_rate": 9.698463103929542e-05,
"loss": 0.9963,
"step": 40
},
{
"epoch": 0.01161473087818697,
"grad_norm": 0.6913411617279053,
"learning_rate": 9.667902132486009e-05,
"loss": 1.0246,
"step": 41
},
{
"epoch": 0.01189801699716714,
"grad_norm": 0.7879395484924316,
"learning_rate": 9.635919272833938e-05,
"loss": 1.1409,
"step": 42
},
{
"epoch": 0.012181303116147308,
"grad_norm": 0.6506746411323547,
"learning_rate": 9.602524267262203e-05,
"loss": 1.0367,
"step": 43
},
{
"epoch": 0.012464589235127478,
"grad_norm": 0.7825458645820618,
"learning_rate": 9.567727288213005e-05,
"loss": 1.0962,
"step": 44
},
{
"epoch": 0.012747875354107648,
"grad_norm": 0.8112017512321472,
"learning_rate": 9.53153893518325e-05,
"loss": 0.9379,
"step": 45
},
{
"epoch": 0.013031161473087818,
"grad_norm": 0.9518360495567322,
"learning_rate": 9.493970231495835e-05,
"loss": 1.2331,
"step": 46
},
{
"epoch": 0.013314447592067988,
"grad_norm": 1.0096303224563599,
"learning_rate": 9.45503262094184e-05,
"loss": 1.0212,
"step": 47
},
{
"epoch": 0.013597733711048159,
"grad_norm": 1.4635624885559082,
"learning_rate": 9.414737964294636e-05,
"loss": 1.18,
"step": 48
},
{
"epoch": 0.013881019830028329,
"grad_norm": 1.5704519748687744,
"learning_rate": 9.373098535696979e-05,
"loss": 1.0703,
"step": 49
},
{
"epoch": 0.014164305949008499,
"grad_norm": 2.2931337356567383,
"learning_rate": 9.330127018922194e-05,
"loss": 1.0591,
"step": 50
},
{
"epoch": 0.014164305949008499,
"eval_loss": 0.9707683324813843,
"eval_runtime": 488.0589,
"eval_samples_per_second": 12.183,
"eval_steps_per_second": 6.091,
"step": 50
},
{
"epoch": 0.014447592067988669,
"grad_norm": 0.31635814905166626,
"learning_rate": 9.285836503510562e-05,
"loss": 0.7657,
"step": 51
},
{
"epoch": 0.014730878186968839,
"grad_norm": 0.3915429711341858,
"learning_rate": 9.24024048078213e-05,
"loss": 0.8888,
"step": 52
},
{
"epoch": 0.01501416430594901,
"grad_norm": 0.37524592876434326,
"learning_rate": 9.193352839727121e-05,
"loss": 0.8045,
"step": 53
},
{
"epoch": 0.01529745042492918,
"grad_norm": 0.32623764872550964,
"learning_rate": 9.145187862775209e-05,
"loss": 0.8345,
"step": 54
},
{
"epoch": 0.015580736543909348,
"grad_norm": 0.2912946939468384,
"learning_rate": 9.09576022144496e-05,
"loss": 0.8638,
"step": 55
},
{
"epoch": 0.01586402266288952,
"grad_norm": 0.28338658809661865,
"learning_rate": 9.045084971874738e-05,
"loss": 0.8685,
"step": 56
},
{
"epoch": 0.01614730878186969,
"grad_norm": 0.2784612476825714,
"learning_rate": 8.993177550236464e-05,
"loss": 0.8542,
"step": 57
},
{
"epoch": 0.01643059490084986,
"grad_norm": 0.273578405380249,
"learning_rate": 8.940053768033609e-05,
"loss": 0.8186,
"step": 58
},
{
"epoch": 0.01671388101983003,
"grad_norm": 0.27225029468536377,
"learning_rate": 8.885729807284856e-05,
"loss": 0.8194,
"step": 59
},
{
"epoch": 0.0169971671388102,
"grad_norm": 0.2823231816291809,
"learning_rate": 8.83022221559489e-05,
"loss": 0.8064,
"step": 60
},
{
"epoch": 0.017280453257790367,
"grad_norm": 0.27315282821655273,
"learning_rate": 8.773547901113862e-05,
"loss": 0.7767,
"step": 61
},
{
"epoch": 0.017563739376770537,
"grad_norm": 0.3057181239128113,
"learning_rate": 8.715724127386972e-05,
"loss": 0.8559,
"step": 62
},
{
"epoch": 0.017847025495750707,
"grad_norm": 0.25322389602661133,
"learning_rate": 8.656768508095853e-05,
"loss": 0.7594,
"step": 63
},
{
"epoch": 0.018130311614730877,
"grad_norm": 0.2614225149154663,
"learning_rate": 8.596699001693255e-05,
"loss": 0.8225,
"step": 64
},
{
"epoch": 0.018413597733711047,
"grad_norm": 0.23576407134532928,
"learning_rate": 8.535533905932738e-05,
"loss": 0.8388,
"step": 65
},
{
"epoch": 0.018696883852691217,
"grad_norm": 0.24987991154193878,
"learning_rate": 8.473291852294987e-05,
"loss": 0.782,
"step": 66
},
{
"epoch": 0.018980169971671387,
"grad_norm": 0.2600783705711365,
"learning_rate": 8.409991800312493e-05,
"loss": 0.8176,
"step": 67
},
{
"epoch": 0.019263456090651557,
"grad_norm": 0.2444659173488617,
"learning_rate": 8.345653031794292e-05,
"loss": 0.8305,
"step": 68
},
{
"epoch": 0.019546742209631728,
"grad_norm": 0.2555049657821655,
"learning_rate": 8.280295144952536e-05,
"loss": 0.8203,
"step": 69
},
{
"epoch": 0.019830028328611898,
"grad_norm": 0.2540525496006012,
"learning_rate": 8.213938048432697e-05,
"loss": 0.7953,
"step": 70
},
{
"epoch": 0.020113314447592068,
"grad_norm": 0.2432480752468109,
"learning_rate": 8.146601955249188e-05,
"loss": 0.8103,
"step": 71
},
{
"epoch": 0.020396600566572238,
"grad_norm": 0.28842082619667053,
"learning_rate": 8.07830737662829e-05,
"loss": 0.7827,
"step": 72
},
{
"epoch": 0.020679886685552408,
"grad_norm": 0.258884996175766,
"learning_rate": 8.009075115760243e-05,
"loss": 0.7813,
"step": 73
},
{
"epoch": 0.020963172804532578,
"grad_norm": 0.28011828660964966,
"learning_rate": 7.938926261462366e-05,
"loss": 0.8511,
"step": 74
},
{
"epoch": 0.021246458923512748,
"grad_norm": 0.3141220211982727,
"learning_rate": 7.86788218175523e-05,
"loss": 0.8916,
"step": 75
},
{
"epoch": 0.02152974504249292,
"grad_norm": 0.31731855869293213,
"learning_rate": 7.795964517353735e-05,
"loss": 0.7985,
"step": 76
},
{
"epoch": 0.02181303116147309,
"grad_norm": 0.3145108222961426,
"learning_rate": 7.723195175075136e-05,
"loss": 0.8648,
"step": 77
},
{
"epoch": 0.02209631728045326,
"grad_norm": 0.33710357546806335,
"learning_rate": 7.649596321166024e-05,
"loss": 0.8102,
"step": 78
},
{
"epoch": 0.02237960339943343,
"grad_norm": 0.3097231090068817,
"learning_rate": 7.575190374550272e-05,
"loss": 0.8856,
"step": 79
},
{
"epoch": 0.0226628895184136,
"grad_norm": 0.33917585015296936,
"learning_rate": 7.500000000000001e-05,
"loss": 0.8405,
"step": 80
},
{
"epoch": 0.02294617563739377,
"grad_norm": 0.3195075988769531,
"learning_rate": 7.424048101231686e-05,
"loss": 0.8151,
"step": 81
},
{
"epoch": 0.02322946175637394,
"grad_norm": 0.4224698543548584,
"learning_rate": 7.347357813929454e-05,
"loss": 0.9041,
"step": 82
},
{
"epoch": 0.02351274787535411,
"grad_norm": 0.4021918475627899,
"learning_rate": 7.269952498697734e-05,
"loss": 0.9231,
"step": 83
},
{
"epoch": 0.02379603399433428,
"grad_norm": 0.4472004771232605,
"learning_rate": 7.191855733945387e-05,
"loss": 0.943,
"step": 84
},
{
"epoch": 0.024079320113314446,
"grad_norm": 0.5003901124000549,
"learning_rate": 7.113091308703498e-05,
"loss": 0.8979,
"step": 85
},
{
"epoch": 0.024362606232294616,
"grad_norm": 0.5862677097320557,
"learning_rate": 7.033683215379002e-05,
"loss": 1.0636,
"step": 86
},
{
"epoch": 0.024645892351274786,
"grad_norm": 0.4611576199531555,
"learning_rate": 6.953655642446368e-05,
"loss": 0.8857,
"step": 87
},
{
"epoch": 0.024929178470254956,
"grad_norm": 0.6086900234222412,
"learning_rate": 6.873032967079561e-05,
"loss": 0.9394,
"step": 88
},
{
"epoch": 0.025212464589235126,
"grad_norm": 0.5702813863754272,
"learning_rate": 6.7918397477265e-05,
"loss": 0.8928,
"step": 89
},
{
"epoch": 0.025495750708215296,
"grad_norm": 0.5099334716796875,
"learning_rate": 6.710100716628344e-05,
"loss": 0.9919,
"step": 90
},
{
"epoch": 0.025779036827195467,
"grad_norm": 0.6126192212104797,
"learning_rate": 6.627840772285784e-05,
"loss": 0.9299,
"step": 91
},
{
"epoch": 0.026062322946175637,
"grad_norm": 0.6228667497634888,
"learning_rate": 6.545084971874738e-05,
"loss": 0.9997,
"step": 92
},
{
"epoch": 0.026345609065155807,
"grad_norm": 0.6684215068817139,
"learning_rate": 6.461858523613684e-05,
"loss": 0.9355,
"step": 93
},
{
"epoch": 0.026628895184135977,
"grad_norm": 0.7169914841651917,
"learning_rate": 6.378186779084995e-05,
"loss": 1.0057,
"step": 94
},
{
"epoch": 0.026912181303116147,
"grad_norm": 0.7495495080947876,
"learning_rate": 6.294095225512603e-05,
"loss": 0.843,
"step": 95
},
{
"epoch": 0.027195467422096317,
"grad_norm": 1.0023761987686157,
"learning_rate": 6.209609477998338e-05,
"loss": 0.9734,
"step": 96
},
{
"epoch": 0.027478753541076487,
"grad_norm": 0.9798507690429688,
"learning_rate": 6.124755271719325e-05,
"loss": 1.0046,
"step": 97
},
{
"epoch": 0.027762039660056657,
"grad_norm": 0.9909435510635376,
"learning_rate": 6.0395584540887963e-05,
"loss": 0.9592,
"step": 98
},
{
"epoch": 0.028045325779036828,
"grad_norm": 1.6045634746551514,
"learning_rate": 5.9540449768827246e-05,
"loss": 1.0293,
"step": 99
},
{
"epoch": 0.028328611898016998,
"grad_norm": 3.4821736812591553,
"learning_rate": 5.868240888334653e-05,
"loss": 0.9679,
"step": 100
},
{
"epoch": 0.028328611898016998,
"eval_loss": 0.8943002223968506,
"eval_runtime": 487.973,
"eval_samples_per_second": 12.185,
"eval_steps_per_second": 6.093,
"step": 100
},
{
"epoch": 0.028611898016997168,
"grad_norm": 0.26681363582611084,
"learning_rate": 5.782172325201155e-05,
"loss": 0.7179,
"step": 101
},
{
"epoch": 0.028895184135977338,
"grad_norm": 0.27887067198753357,
"learning_rate": 5.695865504800327e-05,
"loss": 0.7854,
"step": 102
},
{
"epoch": 0.029178470254957508,
"grad_norm": 0.2766787111759186,
"learning_rate": 5.6093467170257374e-05,
"loss": 0.7794,
"step": 103
},
{
"epoch": 0.029461756373937678,
"grad_norm": 0.2650505304336548,
"learning_rate": 5.522642316338268e-05,
"loss": 0.7821,
"step": 104
},
{
"epoch": 0.029745042492917848,
"grad_norm": 0.25711944699287415,
"learning_rate": 5.435778713738292e-05,
"loss": 0.7428,
"step": 105
},
{
"epoch": 0.03002832861189802,
"grad_norm": 0.23184049129486084,
"learning_rate": 5.348782368720626e-05,
"loss": 0.7789,
"step": 106
},
{
"epoch": 0.03031161473087819,
"grad_norm": 0.23433373868465424,
"learning_rate": 5.26167978121472e-05,
"loss": 0.8222,
"step": 107
},
{
"epoch": 0.03059490084985836,
"grad_norm": 0.23752881586551666,
"learning_rate": 5.174497483512506e-05,
"loss": 0.7548,
"step": 108
},
{
"epoch": 0.030878186968838525,
"grad_norm": 0.23099955916404724,
"learning_rate": 5.0872620321864185e-05,
"loss": 0.8607,
"step": 109
},
{
"epoch": 0.031161473087818695,
"grad_norm": 0.2357034683227539,
"learning_rate": 5e-05,
"loss": 0.8765,
"step": 110
},
{
"epoch": 0.031444759206798865,
"grad_norm": 0.2469700574874878,
"learning_rate": 4.912737967813583e-05,
"loss": 0.825,
"step": 111
},
{
"epoch": 0.03172804532577904,
"grad_norm": 0.24967269599437714,
"learning_rate": 4.825502516487497e-05,
"loss": 0.7931,
"step": 112
},
{
"epoch": 0.032011331444759206,
"grad_norm": 0.25203588604927063,
"learning_rate": 4.738320218785281e-05,
"loss": 0.7875,
"step": 113
},
{
"epoch": 0.03229461756373938,
"grad_norm": 0.25249430537223816,
"learning_rate": 4.6512176312793736e-05,
"loss": 0.8702,
"step": 114
},
{
"epoch": 0.032577903682719546,
"grad_norm": 0.2569659948348999,
"learning_rate": 4.564221286261709e-05,
"loss": 0.8997,
"step": 115
},
{
"epoch": 0.03286118980169972,
"grad_norm": 0.2416309267282486,
"learning_rate": 4.477357683661734e-05,
"loss": 0.7305,
"step": 116
},
{
"epoch": 0.033144475920679886,
"grad_norm": 0.24729342758655548,
"learning_rate": 4.390653282974264e-05,
"loss": 0.8049,
"step": 117
},
{
"epoch": 0.03342776203966006,
"grad_norm": 0.27604395151138306,
"learning_rate": 4.3041344951996746e-05,
"loss": 0.8112,
"step": 118
},
{
"epoch": 0.033711048158640226,
"grad_norm": 0.27382591366767883,
"learning_rate": 4.2178276747988446e-05,
"loss": 0.8149,
"step": 119
},
{
"epoch": 0.0339943342776204,
"grad_norm": 0.25334885716438293,
"learning_rate": 4.131759111665349e-05,
"loss": 0.8281,
"step": 120
},
{
"epoch": 0.03427762039660057,
"grad_norm": 0.2882319390773773,
"learning_rate": 4.045955023117276e-05,
"loss": 0.8037,
"step": 121
},
{
"epoch": 0.03456090651558073,
"grad_norm": 0.28409236669540405,
"learning_rate": 3.960441545911204e-05,
"loss": 0.8182,
"step": 122
},
{
"epoch": 0.03484419263456091,
"grad_norm": 0.2688352167606354,
"learning_rate": 3.875244728280676e-05,
"loss": 0.7252,
"step": 123
},
{
"epoch": 0.03512747875354107,
"grad_norm": 0.3232026994228363,
"learning_rate": 3.790390522001662e-05,
"loss": 0.8757,
"step": 124
},
{
"epoch": 0.03541076487252125,
"grad_norm": 0.3008348345756531,
"learning_rate": 3.705904774487396e-05,
"loss": 0.8151,
"step": 125
},
{
"epoch": 0.035694050991501414,
"grad_norm": 0.2845551073551178,
"learning_rate": 3.6218132209150045e-05,
"loss": 0.8039,
"step": 126
},
{
"epoch": 0.03597733711048159,
"grad_norm": 0.30033618211746216,
"learning_rate": 3.5381414763863166e-05,
"loss": 0.8236,
"step": 127
},
{
"epoch": 0.036260623229461754,
"grad_norm": 0.2865908145904541,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.8584,
"step": 128
},
{
"epoch": 0.03654390934844193,
"grad_norm": 0.3274208903312683,
"learning_rate": 3.372159227714218e-05,
"loss": 0.8048,
"step": 129
},
{
"epoch": 0.036827195467422094,
"grad_norm": 0.32286253571510315,
"learning_rate": 3.289899283371657e-05,
"loss": 0.8669,
"step": 130
},
{
"epoch": 0.03711048158640227,
"grad_norm": 0.32492363452911377,
"learning_rate": 3.2081602522734986e-05,
"loss": 0.8294,
"step": 131
},
{
"epoch": 0.037393767705382434,
"grad_norm": 0.3788565993309021,
"learning_rate": 3.12696703292044e-05,
"loss": 0.9411,
"step": 132
},
{
"epoch": 0.03767705382436261,
"grad_norm": 0.3922273516654968,
"learning_rate": 3.046344357553632e-05,
"loss": 0.896,
"step": 133
},
{
"epoch": 0.037960339943342775,
"grad_norm": 0.4324563443660736,
"learning_rate": 2.9663167846209998e-05,
"loss": 0.8272,
"step": 134
},
{
"epoch": 0.03824362606232295,
"grad_norm": 0.4802010655403137,
"learning_rate": 2.886908691296504e-05,
"loss": 0.7869,
"step": 135
},
{
"epoch": 0.038526912181303115,
"grad_norm": 0.5401066541671753,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.8878,
"step": 136
},
{
"epoch": 0.03881019830028329,
"grad_norm": 0.49897003173828125,
"learning_rate": 2.7300475013022663e-05,
"loss": 0.9156,
"step": 137
},
{
"epoch": 0.039093484419263455,
"grad_norm": 0.5094231963157654,
"learning_rate": 2.6526421860705473e-05,
"loss": 0.8411,
"step": 138
},
{
"epoch": 0.03937677053824363,
"grad_norm": 0.5654172897338867,
"learning_rate": 2.575951898768315e-05,
"loss": 0.9716,
"step": 139
},
{
"epoch": 0.039660056657223795,
"grad_norm": 0.5526919960975647,
"learning_rate": 2.500000000000001e-05,
"loss": 0.9828,
"step": 140
},
{
"epoch": 0.03994334277620397,
"grad_norm": 0.5752049088478088,
"learning_rate": 2.4248096254497288e-05,
"loss": 0.9976,
"step": 141
},
{
"epoch": 0.040226628895184136,
"grad_norm": 0.6576734781265259,
"learning_rate": 2.350403678833976e-05,
"loss": 0.9673,
"step": 142
},
{
"epoch": 0.04050991501416431,
"grad_norm": 0.7551366090774536,
"learning_rate": 2.2768048249248648e-05,
"loss": 0.9781,
"step": 143
},
{
"epoch": 0.040793201133144476,
"grad_norm": 0.7085397839546204,
"learning_rate": 2.2040354826462668e-05,
"loss": 1.0065,
"step": 144
},
{
"epoch": 0.04107648725212465,
"grad_norm": 0.7727219462394714,
"learning_rate": 2.132117818244771e-05,
"loss": 0.8517,
"step": 145
},
{
"epoch": 0.041359773371104816,
"grad_norm": 0.8478469848632812,
"learning_rate": 2.061073738537635e-05,
"loss": 0.9225,
"step": 146
},
{
"epoch": 0.04164305949008498,
"grad_norm": 0.9258629083633423,
"learning_rate": 1.9909248842397584e-05,
"loss": 0.9349,
"step": 147
},
{
"epoch": 0.041926345609065156,
"grad_norm": 1.0141416788101196,
"learning_rate": 1.9216926233717085e-05,
"loss": 0.8708,
"step": 148
},
{
"epoch": 0.04220963172804532,
"grad_norm": 1.2329179048538208,
"learning_rate": 1.8533980447508137e-05,
"loss": 0.855,
"step": 149
},
{
"epoch": 0.042492917847025496,
"grad_norm": 2.4406769275665283,
"learning_rate": 1.7860619515673033e-05,
"loss": 0.868,
"step": 150
},
{
"epoch": 0.042492917847025496,
"eval_loss": 0.8521701693534851,
"eval_runtime": 487.8912,
"eval_samples_per_second": 12.187,
"eval_steps_per_second": 6.094,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.06575327248384e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}