Math_Version_9 / last-checkpoint /trainer_state.json
anhdai312's picture
Training in progress, step 180, checkpoint
29cbc58 verified
Raw
History Blame Contribute Delete
34.1 kB
{
"best_global_step": 180,
"best_metric": 0.7345618605613708,
"best_model_checkpoint": "/tmp/checkpoints_/job_0e64aa6d-d770-420a-8596-581259830426/checkpoint-180",
"epoch": 1.8818897637795275,
"eval_steps": 180,
"global_step": 180,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010498687664041995,
"grad_norm": 8.951988220214844,
"learning_rate": 0.0,
"loss": 3.249479055404663,
"step": 1
},
{
"epoch": 0.02099737532808399,
"grad_norm": 10.128303527832031,
"learning_rate": 1.388888888888889e-06,
"loss": 3.7097482681274414,
"step": 2
},
{
"epoch": 0.031496062992125984,
"grad_norm": 11.297329902648926,
"learning_rate": 2.777777777777778e-06,
"loss": 4.088885307312012,
"step": 3
},
{
"epoch": 0.04199475065616798,
"grad_norm": 10.444681167602539,
"learning_rate": 4.166666666666667e-06,
"loss": 3.485933303833008,
"step": 4
},
{
"epoch": 0.05249343832020997,
"grad_norm": 9.82193660736084,
"learning_rate": 5.555555555555556e-06,
"loss": 3.5621585845947266,
"step": 5
},
{
"epoch": 0.06299212598425197,
"grad_norm": 9.866586685180664,
"learning_rate": 6.944444444444445e-06,
"loss": 3.6951005458831787,
"step": 6
},
{
"epoch": 0.07349081364829396,
"grad_norm": 7.083434581756592,
"learning_rate": 8.333333333333334e-06,
"loss": 2.840730905532837,
"step": 7
},
{
"epoch": 0.08398950131233596,
"grad_norm": 6.84299373626709,
"learning_rate": 9.722222222222223e-06,
"loss": 2.666860342025757,
"step": 8
},
{
"epoch": 0.09448818897637795,
"grad_norm": 9.864928245544434,
"learning_rate": 1.1111111111111112e-05,
"loss": 3.023573875427246,
"step": 9
},
{
"epoch": 0.10498687664041995,
"grad_norm": 14.969345092773438,
"learning_rate": 1.25e-05,
"loss": 2.860168933868408,
"step": 10
},
{
"epoch": 0.11548556430446194,
"grad_norm": 11.013322830200195,
"learning_rate": 1.388888888888889e-05,
"loss": 2.6086080074310303,
"step": 11
},
{
"epoch": 0.12598425196850394,
"grad_norm": 4.521217346191406,
"learning_rate": 1.527777777777778e-05,
"loss": 2.150205135345459,
"step": 12
},
{
"epoch": 0.13648293963254593,
"grad_norm": 3.814413070678711,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.828367829322815,
"step": 13
},
{
"epoch": 0.14698162729658792,
"grad_norm": 4.641453266143799,
"learning_rate": 1.8055555555555555e-05,
"loss": 2.1309380531311035,
"step": 14
},
{
"epoch": 0.15748031496062992,
"grad_norm": 4.126307010650635,
"learning_rate": 1.9444444444444445e-05,
"loss": 1.9802217483520508,
"step": 15
},
{
"epoch": 0.1679790026246719,
"grad_norm": 4.218288898468018,
"learning_rate": 2.0833333333333336e-05,
"loss": 1.7591347694396973,
"step": 16
},
{
"epoch": 0.1784776902887139,
"grad_norm": 3.363419771194458,
"learning_rate": 2.2222222222222223e-05,
"loss": 1.7987712621688843,
"step": 17
},
{
"epoch": 0.1889763779527559,
"grad_norm": 4.657691955566406,
"learning_rate": 2.361111111111111e-05,
"loss": 1.66544508934021,
"step": 18
},
{
"epoch": 0.1994750656167979,
"grad_norm": 3.800804376602173,
"learning_rate": 2.5e-05,
"loss": 1.306773066520691,
"step": 19
},
{
"epoch": 0.2099737532808399,
"grad_norm": 3.2552781105041504,
"learning_rate": 2.6388888888888892e-05,
"loss": 1.4616773128509521,
"step": 20
},
{
"epoch": 0.2204724409448819,
"grad_norm": 3.3963801860809326,
"learning_rate": 2.777777777777778e-05,
"loss": 1.7249674797058105,
"step": 21
},
{
"epoch": 0.23097112860892388,
"grad_norm": 2.927400588989258,
"learning_rate": 2.916666666666667e-05,
"loss": 1.1973810195922852,
"step": 22
},
{
"epoch": 0.24146981627296588,
"grad_norm": 3.294121265411377,
"learning_rate": 3.055555555555556e-05,
"loss": 1.5330796241760254,
"step": 23
},
{
"epoch": 0.25196850393700787,
"grad_norm": 3.000525951385498,
"learning_rate": 3.194444444444444e-05,
"loss": 1.5339046716690063,
"step": 24
},
{
"epoch": 0.26246719160104987,
"grad_norm": 2.6179091930389404,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.376935362815857,
"step": 25
},
{
"epoch": 0.27296587926509186,
"grad_norm": 2.7590878009796143,
"learning_rate": 3.472222222222222e-05,
"loss": 1.0393620729446411,
"step": 26
},
{
"epoch": 0.28346456692913385,
"grad_norm": 2.995431661605835,
"learning_rate": 3.611111111111111e-05,
"loss": 1.0867018699645996,
"step": 27
},
{
"epoch": 0.29396325459317585,
"grad_norm": 3.041278600692749,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.433882474899292,
"step": 28
},
{
"epoch": 0.30446194225721784,
"grad_norm": 2.8220653533935547,
"learning_rate": 3.888888888888889e-05,
"loss": 1.365267038345337,
"step": 29
},
{
"epoch": 0.31496062992125984,
"grad_norm": 3.3981337547302246,
"learning_rate": 4.027777777777778e-05,
"loss": 1.263239860534668,
"step": 30
},
{
"epoch": 0.32545931758530183,
"grad_norm": 2.696167469024658,
"learning_rate": 4.166666666666667e-05,
"loss": 0.9025776386260986,
"step": 31
},
{
"epoch": 0.3359580052493438,
"grad_norm": 2.521253824234009,
"learning_rate": 4.305555555555556e-05,
"loss": 1.2447938919067383,
"step": 32
},
{
"epoch": 0.3464566929133858,
"grad_norm": 2.733062505722046,
"learning_rate": 4.4444444444444447e-05,
"loss": 1.2721298933029175,
"step": 33
},
{
"epoch": 0.3569553805774278,
"grad_norm": 2.8184359073638916,
"learning_rate": 4.5833333333333334e-05,
"loss": 1.1625587940216064,
"step": 34
},
{
"epoch": 0.3674540682414698,
"grad_norm": 2.8711488246917725,
"learning_rate": 4.722222222222222e-05,
"loss": 1.297273874282837,
"step": 35
},
{
"epoch": 0.3779527559055118,
"grad_norm": 2.5392374992370605,
"learning_rate": 4.8611111111111115e-05,
"loss": 1.092471718788147,
"step": 36
},
{
"epoch": 0.3884514435695538,
"grad_norm": 2.411024332046509,
"learning_rate": 5e-05,
"loss": 0.775846540927887,
"step": 37
},
{
"epoch": 0.3989501312335958,
"grad_norm": 2.7414016723632812,
"learning_rate": 5.138888888888889e-05,
"loss": 1.098214030265808,
"step": 38
},
{
"epoch": 0.4094488188976378,
"grad_norm": 2.321186065673828,
"learning_rate": 5.2777777777777784e-05,
"loss": 0.9746102094650269,
"step": 39
},
{
"epoch": 0.4199475065616798,
"grad_norm": 2.332367420196533,
"learning_rate": 5.4166666666666664e-05,
"loss": 1.1140830516815186,
"step": 40
},
{
"epoch": 0.4304461942257218,
"grad_norm": 2.3728103637695312,
"learning_rate": 5.555555555555556e-05,
"loss": 0.8862820863723755,
"step": 41
},
{
"epoch": 0.4409448818897638,
"grad_norm": 2.6133763790130615,
"learning_rate": 5.6944444444444445e-05,
"loss": 1.2858248949050903,
"step": 42
},
{
"epoch": 0.45144356955380577,
"grad_norm": 2.3347628116607666,
"learning_rate": 5.833333333333334e-05,
"loss": 0.8805493712425232,
"step": 43
},
{
"epoch": 0.46194225721784776,
"grad_norm": 2.458185911178589,
"learning_rate": 5.972222222222223e-05,
"loss": 0.7434869408607483,
"step": 44
},
{
"epoch": 0.47244094488188976,
"grad_norm": 3.8044676780700684,
"learning_rate": 6.111111111111112e-05,
"loss": 1.1476449966430664,
"step": 45
},
{
"epoch": 0.48293963254593175,
"grad_norm": 2.385948657989502,
"learning_rate": 6.25e-05,
"loss": 1.0679090023040771,
"step": 46
},
{
"epoch": 0.49343832020997375,
"grad_norm": 2.360832452774048,
"learning_rate": 6.388888888888888e-05,
"loss": 1.306788444519043,
"step": 47
},
{
"epoch": 0.5039370078740157,
"grad_norm": 2.7582314014434814,
"learning_rate": 6.527777777777778e-05,
"loss": 0.9781908988952637,
"step": 48
},
{
"epoch": 0.5144356955380578,
"grad_norm": 2.75345516204834,
"learning_rate": 6.666666666666667e-05,
"loss": 1.1039270162582397,
"step": 49
},
{
"epoch": 0.5249343832020997,
"grad_norm": 2.701941728591919,
"learning_rate": 6.805555555555556e-05,
"loss": 0.8450642824172974,
"step": 50
},
{
"epoch": 0.5354330708661418,
"grad_norm": 2.6181859970092773,
"learning_rate": 6.944444444444444e-05,
"loss": 1.1489506959915161,
"step": 51
},
{
"epoch": 0.5459317585301837,
"grad_norm": 2.5881521701812744,
"learning_rate": 7.083333333333334e-05,
"loss": 1.1173646450042725,
"step": 52
},
{
"epoch": 0.5564304461942258,
"grad_norm": 2.8784170150756836,
"learning_rate": 7.222222222222222e-05,
"loss": 1.0153920650482178,
"step": 53
},
{
"epoch": 0.5669291338582677,
"grad_norm": 2.656449317932129,
"learning_rate": 7.361111111111111e-05,
"loss": 0.7619301080703735,
"step": 54
},
{
"epoch": 0.5774278215223098,
"grad_norm": 2.858013153076172,
"learning_rate": 7.500000000000001e-05,
"loss": 0.9939401149749756,
"step": 55
},
{
"epoch": 0.5879265091863517,
"grad_norm": 2.6147100925445557,
"learning_rate": 7.638888888888889e-05,
"loss": 0.8214564919471741,
"step": 56
},
{
"epoch": 0.5984251968503937,
"grad_norm": 2.5389599800109863,
"learning_rate": 7.777777777777778e-05,
"loss": 1.1958118677139282,
"step": 57
},
{
"epoch": 0.6089238845144357,
"grad_norm": 2.347487688064575,
"learning_rate": 7.916666666666666e-05,
"loss": 0.8644261360168457,
"step": 58
},
{
"epoch": 0.6194225721784777,
"grad_norm": 2.565040111541748,
"learning_rate": 8.055555555555556e-05,
"loss": 0.7667118310928345,
"step": 59
},
{
"epoch": 0.6299212598425197,
"grad_norm": 2.8054683208465576,
"learning_rate": 8.194444444444445e-05,
"loss": 1.1510149240493774,
"step": 60
},
{
"epoch": 0.6404199475065617,
"grad_norm": 2.382753849029541,
"learning_rate": 8.333333333333334e-05,
"loss": 0.992143452167511,
"step": 61
},
{
"epoch": 0.6509186351706037,
"grad_norm": 2.7336316108703613,
"learning_rate": 8.472222222222222e-05,
"loss": 0.6995159387588501,
"step": 62
},
{
"epoch": 0.6614173228346457,
"grad_norm": 2.6157381534576416,
"learning_rate": 8.611111111111112e-05,
"loss": 0.9559763669967651,
"step": 63
},
{
"epoch": 0.6719160104986877,
"grad_norm": 2.595747947692871,
"learning_rate": 8.75e-05,
"loss": 0.8102397918701172,
"step": 64
},
{
"epoch": 0.6824146981627297,
"grad_norm": 3.133843421936035,
"learning_rate": 8.888888888888889e-05,
"loss": 1.2200690507888794,
"step": 65
},
{
"epoch": 0.6929133858267716,
"grad_norm": 2.650782346725464,
"learning_rate": 9.027777777777779e-05,
"loss": 1.1741877794265747,
"step": 66
},
{
"epoch": 0.7034120734908137,
"grad_norm": 2.95759654045105,
"learning_rate": 9.166666666666667e-05,
"loss": 0.7577806711196899,
"step": 67
},
{
"epoch": 0.7139107611548556,
"grad_norm": 1.881460189819336,
"learning_rate": 9.305555555555556e-05,
"loss": 0.8405244946479797,
"step": 68
},
{
"epoch": 0.7244094488188977,
"grad_norm": 2.2031402587890625,
"learning_rate": 9.444444444444444e-05,
"loss": 0.7478643655776978,
"step": 69
},
{
"epoch": 0.7349081364829396,
"grad_norm": 2.117764949798584,
"learning_rate": 9.583333333333334e-05,
"loss": 0.7592930793762207,
"step": 70
},
{
"epoch": 0.7454068241469817,
"grad_norm": 2.677325487136841,
"learning_rate": 9.722222222222223e-05,
"loss": 0.7365151643753052,
"step": 71
},
{
"epoch": 0.7559055118110236,
"grad_norm": 2.6489365100860596,
"learning_rate": 9.861111111111112e-05,
"loss": 0.8592371940612793,
"step": 72
},
{
"epoch": 0.7664041994750657,
"grad_norm": 2.4191040992736816,
"learning_rate": 0.0001,
"loss": 1.1325792074203491,
"step": 73
},
{
"epoch": 0.7769028871391076,
"grad_norm": 1.958177089691162,
"learning_rate": 9.999986815387556e-05,
"loss": 0.8772994875907898,
"step": 74
},
{
"epoch": 0.7874015748031497,
"grad_norm": 2.1741156578063965,
"learning_rate": 9.999947261619758e-05,
"loss": 0.7361365556716919,
"step": 75
},
{
"epoch": 0.7979002624671916,
"grad_norm": 2.105767250061035,
"learning_rate": 9.999881338905204e-05,
"loss": 0.6588690876960754,
"step": 76
},
{
"epoch": 0.8083989501312336,
"grad_norm": 2.5501770973205566,
"learning_rate": 9.999789047591562e-05,
"loss": 0.7040117979049683,
"step": 77
},
{
"epoch": 0.8188976377952756,
"grad_norm": 2.5983259677886963,
"learning_rate": 9.999670388165563e-05,
"loss": 0.9301653504371643,
"step": 78
},
{
"epoch": 0.8293963254593176,
"grad_norm": 2.293205499649048,
"learning_rate": 9.999525361252996e-05,
"loss": 0.766013503074646,
"step": 79
},
{
"epoch": 0.8398950131233596,
"grad_norm": 2.1907846927642822,
"learning_rate": 9.999353967618712e-05,
"loss": 0.75275057554245,
"step": 80
},
{
"epoch": 0.8503937007874016,
"grad_norm": 2.2031643390655518,
"learning_rate": 9.999156208166614e-05,
"loss": 1.1576189994812012,
"step": 81
},
{
"epoch": 0.8608923884514436,
"grad_norm": 2.2831943035125732,
"learning_rate": 9.998932083939656e-05,
"loss": 0.9979517459869385,
"step": 82
},
{
"epoch": 0.8713910761154856,
"grad_norm": 2.230264186859131,
"learning_rate": 9.998681596119832e-05,
"loss": 0.8245838284492493,
"step": 83
},
{
"epoch": 0.8818897637795275,
"grad_norm": 1.797152042388916,
"learning_rate": 9.998404746028178e-05,
"loss": 0.7982699275016785,
"step": 84
},
{
"epoch": 0.8923884514435696,
"grad_norm": 2.533572196960449,
"learning_rate": 9.998101535124758e-05,
"loss": 0.8974773287773132,
"step": 85
},
{
"epoch": 0.9028871391076115,
"grad_norm": 2.42849063873291,
"learning_rate": 9.997771965008657e-05,
"loss": 0.7184922099113464,
"step": 86
},
{
"epoch": 0.9133858267716536,
"grad_norm": 1.8649266958236694,
"learning_rate": 9.997416037417981e-05,
"loss": 0.41620638966560364,
"step": 87
},
{
"epoch": 0.9238845144356955,
"grad_norm": 1.9906566143035889,
"learning_rate": 9.997033754229835e-05,
"loss": 0.7742212414741516,
"step": 88
},
{
"epoch": 0.9343832020997376,
"grad_norm": 2.9478235244750977,
"learning_rate": 9.996625117460318e-05,
"loss": 0.7733973860740662,
"step": 89
},
{
"epoch": 0.9448818897637795,
"grad_norm": 1.8301382064819336,
"learning_rate": 9.996190129264523e-05,
"loss": 0.6619459390640259,
"step": 90
},
{
"epoch": 0.9553805774278216,
"grad_norm": 1.8731720447540283,
"learning_rate": 9.995728791936504e-05,
"loss": 0.4635842442512512,
"step": 91
},
{
"epoch": 0.9658792650918635,
"grad_norm": 2.601485252380371,
"learning_rate": 9.99524110790929e-05,
"loss": 0.7504260540008545,
"step": 92
},
{
"epoch": 0.9763779527559056,
"grad_norm": 2.9148600101470947,
"learning_rate": 9.994727079754844e-05,
"loss": 1.203503966331482,
"step": 93
},
{
"epoch": 0.9868766404199475,
"grad_norm": 1.9760212898254395,
"learning_rate": 9.994186710184074e-05,
"loss": 0.5922846794128418,
"step": 94
},
{
"epoch": 0.9973753280839895,
"grad_norm": 1.6480348110198975,
"learning_rate": 9.993620002046804e-05,
"loss": 0.641535758972168,
"step": 95
},
{
"epoch": 1.0,
"grad_norm": 4.311356544494629,
"learning_rate": 9.993026958331766e-05,
"loss": 0.8158049583435059,
"step": 96
},
{
"epoch": 1.010498687664042,
"grad_norm": 2.029083728790283,
"learning_rate": 9.992407582166581e-05,
"loss": 0.7990297079086304,
"step": 97
},
{
"epoch": 1.020997375328084,
"grad_norm": 1.6174428462982178,
"learning_rate": 9.991761876817743e-05,
"loss": 0.4130845069885254,
"step": 98
},
{
"epoch": 1.031496062992126,
"grad_norm": 1.7238414287567139,
"learning_rate": 9.9910898456906e-05,
"loss": 0.493324875831604,
"step": 99
},
{
"epoch": 1.041994750656168,
"grad_norm": 1.8164974451065063,
"learning_rate": 9.990391492329341e-05,
"loss": 0.882986843585968,
"step": 100
},
{
"epoch": 1.05249343832021,
"grad_norm": 1.5358636379241943,
"learning_rate": 9.989666820416974e-05,
"loss": 0.7046455144882202,
"step": 101
},
{
"epoch": 1.0629921259842519,
"grad_norm": 1.837370753288269,
"learning_rate": 9.988915833775306e-05,
"loss": 0.6996272802352905,
"step": 102
},
{
"epoch": 1.073490813648294,
"grad_norm": 1.946944236755371,
"learning_rate": 9.988138536364922e-05,
"loss": 0.8000504970550537,
"step": 103
},
{
"epoch": 1.083989501312336,
"grad_norm": 1.9082279205322266,
"learning_rate": 9.987334932285173e-05,
"loss": 0.5257124304771423,
"step": 104
},
{
"epoch": 1.094488188976378,
"grad_norm": 2.1394762992858887,
"learning_rate": 9.986505025774138e-05,
"loss": 0.5221662521362305,
"step": 105
},
{
"epoch": 1.10498687664042,
"grad_norm": 2.4781432151794434,
"learning_rate": 9.985648821208616e-05,
"loss": 0.6800025105476379,
"step": 106
},
{
"epoch": 1.1154855643044619,
"grad_norm": 2.2431700229644775,
"learning_rate": 9.984766323104098e-05,
"loss": 0.5910296440124512,
"step": 107
},
{
"epoch": 1.125984251968504,
"grad_norm": 1.9880001544952393,
"learning_rate": 9.983857536114743e-05,
"loss": 0.41105562448501587,
"step": 108
},
{
"epoch": 1.136482939632546,
"grad_norm": 2.035250425338745,
"learning_rate": 9.98292246503335e-05,
"loss": 0.5977977514266968,
"step": 109
},
{
"epoch": 1.1469816272965878,
"grad_norm": 2.538686752319336,
"learning_rate": 9.98196111479134e-05,
"loss": 0.9912805557250977,
"step": 110
},
{
"epoch": 1.1574803149606299,
"grad_norm": 1.6336387395858765,
"learning_rate": 9.980973490458728e-05,
"loss": 0.39054954051971436,
"step": 111
},
{
"epoch": 1.167979002624672,
"grad_norm": 3.1547133922576904,
"learning_rate": 9.979959597244088e-05,
"loss": 0.779079258441925,
"step": 112
},
{
"epoch": 1.178477690288714,
"grad_norm": 2.4110825061798096,
"learning_rate": 9.978919440494539e-05,
"loss": 0.6666456460952759,
"step": 113
},
{
"epoch": 1.188976377952756,
"grad_norm": 2.2546310424804688,
"learning_rate": 9.977853025695703e-05,
"loss": 0.8444710969924927,
"step": 114
},
{
"epoch": 1.1994750656167978,
"grad_norm": 2.101337432861328,
"learning_rate": 9.976760358471686e-05,
"loss": 0.6065786480903625,
"step": 115
},
{
"epoch": 1.20997375328084,
"grad_norm": 2.3106939792633057,
"learning_rate": 9.97564144458505e-05,
"loss": 0.6238447427749634,
"step": 116
},
{
"epoch": 1.220472440944882,
"grad_norm": 2.8519575595855713,
"learning_rate": 9.974496289936769e-05,
"loss": 0.7146114110946655,
"step": 117
},
{
"epoch": 1.2309711286089238,
"grad_norm": 2.3291711807250977,
"learning_rate": 9.973324900566213e-05,
"loss": 0.45184653997421265,
"step": 118
},
{
"epoch": 1.2414698162729658,
"grad_norm": 2.258467435836792,
"learning_rate": 9.972127282651109e-05,
"loss": 0.7285389304161072,
"step": 119
},
{
"epoch": 1.2519685039370079,
"grad_norm": 1.8876954317092896,
"learning_rate": 9.970903442507506e-05,
"loss": 0.5147162079811096,
"step": 120
},
{
"epoch": 1.26246719160105,
"grad_norm": 2.8735554218292236,
"learning_rate": 9.969653386589748e-05,
"loss": 0.7042726278305054,
"step": 121
},
{
"epoch": 1.272965879265092,
"grad_norm": 1.9612526893615723,
"learning_rate": 9.968377121490437e-05,
"loss": 0.604223906993866,
"step": 122
},
{
"epoch": 1.2834645669291338,
"grad_norm": 1.7743514776229858,
"learning_rate": 9.967074653940396e-05,
"loss": 0.5064398050308228,
"step": 123
},
{
"epoch": 1.2939632545931758,
"grad_norm": 2.4915013313293457,
"learning_rate": 9.965745990808637e-05,
"loss": 0.8269689083099365,
"step": 124
},
{
"epoch": 1.304461942257218,
"grad_norm": 1.8990368843078613,
"learning_rate": 9.964391139102325e-05,
"loss": 0.695353090763092,
"step": 125
},
{
"epoch": 1.3149606299212597,
"grad_norm": 1.8268736600875854,
"learning_rate": 9.963010105966736e-05,
"loss": 0.4549499452114105,
"step": 126
},
{
"epoch": 1.3254593175853018,
"grad_norm": 2.297168016433716,
"learning_rate": 9.961602898685226e-05,
"loss": 0.9653254747390747,
"step": 127
},
{
"epoch": 1.3359580052493438,
"grad_norm": 2.13908314704895,
"learning_rate": 9.960169524679187e-05,
"loss": 0.7483035326004028,
"step": 128
},
{
"epoch": 1.3464566929133859,
"grad_norm": 2.573976516723633,
"learning_rate": 9.958709991508012e-05,
"loss": 0.8642760515213013,
"step": 129
},
{
"epoch": 1.356955380577428,
"grad_norm": 1.9398455619812012,
"learning_rate": 9.957224306869053e-05,
"loss": 0.7447575926780701,
"step": 130
},
{
"epoch": 1.3674540682414698,
"grad_norm": 2.681727647781372,
"learning_rate": 9.955712478597579e-05,
"loss": 0.9864035844802856,
"step": 131
},
{
"epoch": 1.3779527559055118,
"grad_norm": 1.647387146949768,
"learning_rate": 9.954174514666739e-05,
"loss": 0.48753517866134644,
"step": 132
},
{
"epoch": 1.3884514435695539,
"grad_norm": 1.506446361541748,
"learning_rate": 9.952610423187516e-05,
"loss": 0.4021700918674469,
"step": 133
},
{
"epoch": 1.3989501312335957,
"grad_norm": 1.884376049041748,
"learning_rate": 9.951020212408688e-05,
"loss": 0.48823046684265137,
"step": 134
},
{
"epoch": 1.4094488188976377,
"grad_norm": 1.5182758569717407,
"learning_rate": 9.949403890716778e-05,
"loss": 0.5521265268325806,
"step": 135
},
{
"epoch": 1.4199475065616798,
"grad_norm": 1.7282530069351196,
"learning_rate": 9.947761466636014e-05,
"loss": 0.5894368290901184,
"step": 136
},
{
"epoch": 1.4304461942257218,
"grad_norm": 2.03877854347229,
"learning_rate": 9.946092948828289e-05,
"loss": 0.4593750238418579,
"step": 137
},
{
"epoch": 1.4409448818897639,
"grad_norm": 1.7829371690750122,
"learning_rate": 9.944398346093109e-05,
"loss": 0.36810481548309326,
"step": 138
},
{
"epoch": 1.4514435695538057,
"grad_norm": 2.3328187465667725,
"learning_rate": 9.942677667367541e-05,
"loss": 0.8222928643226624,
"step": 139
},
{
"epoch": 1.4619422572178478,
"grad_norm": 2.3425021171569824,
"learning_rate": 9.940930921726183e-05,
"loss": 0.6731731295585632,
"step": 140
},
{
"epoch": 1.4724409448818898,
"grad_norm": 2.0964698791503906,
"learning_rate": 9.939158118381098e-05,
"loss": 0.6109187006950378,
"step": 141
},
{
"epoch": 1.4829396325459316,
"grad_norm": 2.1594483852386475,
"learning_rate": 9.937359266681775e-05,
"loss": 0.6047559976577759,
"step": 142
},
{
"epoch": 1.4934383202099737,
"grad_norm": 2.070279121398926,
"learning_rate": 9.935534376115081e-05,
"loss": 0.7203357219696045,
"step": 143
},
{
"epoch": 1.5039370078740157,
"grad_norm": 1.9704307317733765,
"learning_rate": 9.933683456305205e-05,
"loss": 0.5379390716552734,
"step": 144
},
{
"epoch": 1.5144356955380578,
"grad_norm": 1.8411766290664673,
"learning_rate": 9.931806517013612e-05,
"loss": 0.4170542359352112,
"step": 145
},
{
"epoch": 1.5249343832020998,
"grad_norm": 2.163189649581909,
"learning_rate": 9.929903568138989e-05,
"loss": 0.7208942770957947,
"step": 146
},
{
"epoch": 1.5354330708661417,
"grad_norm": 2.2285706996917725,
"learning_rate": 9.92797461971719e-05,
"loss": 0.5548675060272217,
"step": 147
},
{
"epoch": 1.5459317585301837,
"grad_norm": 2.329015016555786,
"learning_rate": 9.926019681921196e-05,
"loss": 0.8331425189971924,
"step": 148
},
{
"epoch": 1.5564304461942258,
"grad_norm": 1.8218705654144287,
"learning_rate": 9.924038765061042e-05,
"loss": 0.5436433553695679,
"step": 149
},
{
"epoch": 1.5669291338582676,
"grad_norm": 1.9812806844711304,
"learning_rate": 9.922031879583775e-05,
"loss": 0.4912114143371582,
"step": 150
},
{
"epoch": 1.5774278215223099,
"grad_norm": 1.8581124544143677,
"learning_rate": 9.9199990360734e-05,
"loss": 0.5493149161338806,
"step": 151
},
{
"epoch": 1.5879265091863517,
"grad_norm": 1.4794453382492065,
"learning_rate": 9.91794024525082e-05,
"loss": 0.6008919477462769,
"step": 152
},
{
"epoch": 1.5984251968503937,
"grad_norm": 1.8988139629364014,
"learning_rate": 9.915855517973776e-05,
"loss": 0.5643243789672852,
"step": 153
},
{
"epoch": 1.6089238845144358,
"grad_norm": 2.0036725997924805,
"learning_rate": 9.913744865236798e-05,
"loss": 0.5755444169044495,
"step": 154
},
{
"epoch": 1.6194225721784776,
"grad_norm": 1.9662656784057617,
"learning_rate": 9.91160829817114e-05,
"loss": 0.8958609700202942,
"step": 155
},
{
"epoch": 1.6299212598425197,
"grad_norm": 1.9017679691314697,
"learning_rate": 9.909445828044727e-05,
"loss": 0.7920309901237488,
"step": 156
},
{
"epoch": 1.6404199475065617,
"grad_norm": 1.993668794631958,
"learning_rate": 9.90725746626209e-05,
"loss": 0.7448785305023193,
"step": 157
},
{
"epoch": 1.6509186351706036,
"grad_norm": 2.0651910305023193,
"learning_rate": 9.90504322436431e-05,
"loss": 0.6014621257781982,
"step": 158
},
{
"epoch": 1.6614173228346458,
"grad_norm": 1.681986689567566,
"learning_rate": 9.902803114028958e-05,
"loss": 0.5465738773345947,
"step": 159
},
{
"epoch": 1.6719160104986877,
"grad_norm": 2.022700548171997,
"learning_rate": 9.900537147070023e-05,
"loss": 0.9149788618087769,
"step": 160
},
{
"epoch": 1.6824146981627297,
"grad_norm": 2.1584994792938232,
"learning_rate": 9.89824533543787e-05,
"loss": 0.7571656703948975,
"step": 161
},
{
"epoch": 1.6929133858267718,
"grad_norm": 2.0340495109558105,
"learning_rate": 9.895927691219154e-05,
"loss": 0.6292194724082947,
"step": 162
},
{
"epoch": 1.7034120734908136,
"grad_norm": 1.8737069368362427,
"learning_rate": 9.893584226636772e-05,
"loss": 0.7888870239257812,
"step": 163
},
{
"epoch": 1.7139107611548556,
"grad_norm": 2.0777649879455566,
"learning_rate": 9.891214954049795e-05,
"loss": 0.7083946466445923,
"step": 164
},
{
"epoch": 1.7244094488188977,
"grad_norm": 1.8575576543807983,
"learning_rate": 9.888819885953398e-05,
"loss": 0.6909530162811279,
"step": 165
},
{
"epoch": 1.7349081364829395,
"grad_norm": 1.9132843017578125,
"learning_rate": 9.886399034978797e-05,
"loss": 0.6255837082862854,
"step": 166
},
{
"epoch": 1.7454068241469818,
"grad_norm": 1.5684483051300049,
"learning_rate": 9.883952413893188e-05,
"loss": 0.7542819380760193,
"step": 167
},
{
"epoch": 1.7559055118110236,
"grad_norm": 1.778061032295227,
"learning_rate": 9.881480035599667e-05,
"loss": 0.5502336025238037,
"step": 168
},
{
"epoch": 1.7664041994750657,
"grad_norm": 1.5060420036315918,
"learning_rate": 9.878981913137179e-05,
"loss": 0.3928365707397461,
"step": 169
},
{
"epoch": 1.7769028871391077,
"grad_norm": 1.986333966255188,
"learning_rate": 9.876458059680431e-05,
"loss": 0.6346912384033203,
"step": 170
},
{
"epoch": 1.7874015748031495,
"grad_norm": 1.9319500923156738,
"learning_rate": 9.873908488539836e-05,
"loss": 0.6179134845733643,
"step": 171
},
{
"epoch": 1.7979002624671916,
"grad_norm": 2.078474283218384,
"learning_rate": 9.871333213161438e-05,
"loss": 0.4551183581352234,
"step": 172
},
{
"epoch": 1.8083989501312336,
"grad_norm": 2.0203495025634766,
"learning_rate": 9.86873224712684e-05,
"loss": 0.5493985414505005,
"step": 173
},
{
"epoch": 1.8188976377952755,
"grad_norm": 2.0541930198669434,
"learning_rate": 9.86610560415313e-05,
"loss": 0.9282588958740234,
"step": 174
},
{
"epoch": 1.8293963254593177,
"grad_norm": 2.073341131210327,
"learning_rate": 9.86345329809282e-05,
"loss": 0.7578333616256714,
"step": 175
},
{
"epoch": 1.8398950131233596,
"grad_norm": 1.977852463722229,
"learning_rate": 9.86077534293376e-05,
"loss": 0.518857479095459,
"step": 176
},
{
"epoch": 1.8503937007874016,
"grad_norm": 1.8464434146881104,
"learning_rate": 9.85807175279907e-05,
"loss": 0.6166715621948242,
"step": 177
},
{
"epoch": 1.8608923884514437,
"grad_norm": 1.8009787797927856,
"learning_rate": 9.855342541947065e-05,
"loss": 0.6155322790145874,
"step": 178
},
{
"epoch": 1.8713910761154855,
"grad_norm": 1.5863672494888306,
"learning_rate": 9.852587724771179e-05,
"loss": 0.431957483291626,
"step": 179
},
{
"epoch": 1.8818897637795275,
"grad_norm": 1.7776707410812378,
"learning_rate": 9.849807315799894e-05,
"loss": 0.7111772894859314,
"step": 180
},
{
"epoch": 1.8818897637795275,
"eval_loss": 0.7345618605613708,
"eval_runtime": 8.4131,
"eval_samples_per_second": 5.111,
"eval_steps_per_second": 1.307,
"step": 180
}
],
"logging_steps": 1,
"max_steps": 1440,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"save_steps": 180,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.2304729254085632e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}