fats-fme's picture
Training in progress, step 141, checkpoint
8da97d6 verified
raw
history blame
25.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7535070140280561,
"eval_steps": 47,
"global_step": 141,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005344021376085505,
"grad_norm": 46.01194381713867,
"learning_rate": 1e-05,
"loss": 7.1426,
"step": 1
},
{
"epoch": 0.005344021376085505,
"eval_loss": 8.964194297790527,
"eval_runtime": 16.0493,
"eval_samples_per_second": 19.689,
"eval_steps_per_second": 4.922,
"step": 1
},
{
"epoch": 0.01068804275217101,
"grad_norm": 57.69265365600586,
"learning_rate": 2e-05,
"loss": 7.9573,
"step": 2
},
{
"epoch": 0.01603206412825651,
"grad_norm": 54.09745407104492,
"learning_rate": 3e-05,
"loss": 8.1933,
"step": 3
},
{
"epoch": 0.02137608550434202,
"grad_norm": 27.1943302154541,
"learning_rate": 4e-05,
"loss": 8.1016,
"step": 4
},
{
"epoch": 0.026720106880427523,
"grad_norm": 11.922409057617188,
"learning_rate": 5e-05,
"loss": 8.0041,
"step": 5
},
{
"epoch": 0.03206412825651302,
"grad_norm": 10.52867603302002,
"learning_rate": 6e-05,
"loss": 7.8208,
"step": 6
},
{
"epoch": 0.03740814963259853,
"grad_norm": 11.152423858642578,
"learning_rate": 7e-05,
"loss": 7.9175,
"step": 7
},
{
"epoch": 0.04275217100868404,
"grad_norm": 10.940130233764648,
"learning_rate": 8e-05,
"loss": 7.7791,
"step": 8
},
{
"epoch": 0.04809619238476954,
"grad_norm": 8.973886489868164,
"learning_rate": 9e-05,
"loss": 7.2009,
"step": 9
},
{
"epoch": 0.053440213760855046,
"grad_norm": 8.348847389221191,
"learning_rate": 0.0001,
"loss": 6.9716,
"step": 10
},
{
"epoch": 0.058784235136940546,
"grad_norm": 9.494211196899414,
"learning_rate": 0.00011000000000000002,
"loss": 6.6369,
"step": 11
},
{
"epoch": 0.06412825651302605,
"grad_norm": 16.81532859802246,
"learning_rate": 0.00012,
"loss": 6.4495,
"step": 12
},
{
"epoch": 0.06947227788911156,
"grad_norm": 10.698507308959961,
"learning_rate": 0.00013000000000000002,
"loss": 6.0936,
"step": 13
},
{
"epoch": 0.07481629926519706,
"grad_norm": 7.711328983306885,
"learning_rate": 0.00014,
"loss": 6.3677,
"step": 14
},
{
"epoch": 0.08016032064128256,
"grad_norm": 8.225103378295898,
"learning_rate": 0.00015000000000000001,
"loss": 6.071,
"step": 15
},
{
"epoch": 0.08550434201736808,
"grad_norm": 13.602970123291016,
"learning_rate": 0.00016,
"loss": 4.9781,
"step": 16
},
{
"epoch": 0.09084836339345358,
"grad_norm": 11.418010711669922,
"learning_rate": 0.00017,
"loss": 4.3076,
"step": 17
},
{
"epoch": 0.09619238476953908,
"grad_norm": 11.895493507385254,
"learning_rate": 0.00018,
"loss": 4.0822,
"step": 18
},
{
"epoch": 0.10153640614562458,
"grad_norm": 8.579840660095215,
"learning_rate": 0.00019,
"loss": 3.4058,
"step": 19
},
{
"epoch": 0.10688042752171009,
"grad_norm": 18.057723999023438,
"learning_rate": 0.0002,
"loss": 4.8878,
"step": 20
},
{
"epoch": 0.11222444889779559,
"grad_norm": 12.423249244689941,
"learning_rate": 0.00019998230608242915,
"loss": 5.1401,
"step": 21
},
{
"epoch": 0.11756847027388109,
"grad_norm": 9.204449653625488,
"learning_rate": 0.00019992923059121106,
"loss": 5.112,
"step": 22
},
{
"epoch": 0.1229124916499666,
"grad_norm": 15.079995155334473,
"learning_rate": 0.00019984079230861296,
"loss": 4.8558,
"step": 23
},
{
"epoch": 0.1282565130260521,
"grad_norm": 32.646522521972656,
"learning_rate": 0.00019971702253102856,
"loss": 4.1068,
"step": 24
},
{
"epoch": 0.13360053440213762,
"grad_norm": 10.601286888122559,
"learning_rate": 0.00019955796505790268,
"loss": 3.5866,
"step": 25
},
{
"epoch": 0.13894455577822312,
"grad_norm": 9.367355346679688,
"learning_rate": 0.00019936367617623171,
"loss": 5.0576,
"step": 26
},
{
"epoch": 0.14428857715430862,
"grad_norm": 7.64223575592041,
"learning_rate": 0.0001991342246406448,
"loss": 5.3104,
"step": 27
},
{
"epoch": 0.14963259853039412,
"grad_norm": 6.789806842803955,
"learning_rate": 0.00019886969164907307,
"loss": 4.7237,
"step": 28
},
{
"epoch": 0.15497661990647962,
"grad_norm": 6.976108551025391,
"learning_rate": 0.00019857017081401548,
"loss": 4.3104,
"step": 29
},
{
"epoch": 0.16032064128256512,
"grad_norm": 4.512085914611816,
"learning_rate": 0.00019823576812941137,
"loss": 4.2295,
"step": 30
},
{
"epoch": 0.16566466265865062,
"grad_norm": 4.308312892913818,
"learning_rate": 0.00019786660193313148,
"loss": 4.3143,
"step": 31
},
{
"epoch": 0.17100868403473615,
"grad_norm": 3.4649343490600586,
"learning_rate": 0.0001974628028651007,
"loss": 4.1055,
"step": 32
},
{
"epoch": 0.17635270541082165,
"grad_norm": 4.710155963897705,
"learning_rate": 0.0001970245138210676,
"loss": 3.2729,
"step": 33
},
{
"epoch": 0.18169672678690715,
"grad_norm": 4.550477027893066,
"learning_rate": 0.00019655188990203647,
"loss": 3.0624,
"step": 34
},
{
"epoch": 0.18704074816299265,
"grad_norm": 4.579635143280029,
"learning_rate": 0.00019604509835938064,
"loss": 3.0187,
"step": 35
},
{
"epoch": 0.19238476953907815,
"grad_norm": 4.524958610534668,
"learning_rate": 0.00019550431853565577,
"loss": 3.6331,
"step": 36
},
{
"epoch": 0.19772879091516365,
"grad_norm": 3.702008008956909,
"learning_rate": 0.00019492974180113426,
"loss": 3.2045,
"step": 37
},
{
"epoch": 0.20307281229124916,
"grad_norm": 3.5903921127319336,
"learning_rate": 0.00019432157148608378,
"loss": 3.7639,
"step": 38
},
{
"epoch": 0.20841683366733466,
"grad_norm": 4.272071838378906,
"learning_rate": 0.00019368002280881278,
"loss": 3.5112,
"step": 39
},
{
"epoch": 0.21376085504342018,
"grad_norm": 7.924098968505859,
"learning_rate": 0.00019300532279950948,
"loss": 3.8263,
"step": 40
},
{
"epoch": 0.21910487641950568,
"grad_norm": 3.829366683959961,
"learning_rate": 0.00019229771021990095,
"loss": 2.9752,
"step": 41
},
{
"epoch": 0.22444889779559118,
"grad_norm": 10.562247276306152,
"learning_rate": 0.00019155743547876023,
"loss": 1.8046,
"step": 42
},
{
"epoch": 0.22979291917167669,
"grad_norm": 6.675294399261475,
"learning_rate": 0.00019078476054329237,
"loss": 1.5568,
"step": 43
},
{
"epoch": 0.23513694054776219,
"grad_norm": 22.542741775512695,
"learning_rate": 0.00018997995884642967,
"loss": 1.4916,
"step": 44
},
{
"epoch": 0.24048096192384769,
"grad_norm": 11.773090362548828,
"learning_rate": 0.00018914331519006986,
"loss": 2.6503,
"step": 45
},
{
"epoch": 0.2458249832999332,
"grad_norm": 7.742423057556152,
"learning_rate": 0.00018827512564429074,
"loss": 3.6861,
"step": 46
},
{
"epoch": 0.2511690046760187,
"grad_norm": 7.848352909088135,
"learning_rate": 0.00018737569744257756,
"loss": 3.7844,
"step": 47
},
{
"epoch": 0.2511690046760187,
"eval_loss": 3.2015836238861084,
"eval_runtime": 16.1976,
"eval_samples_per_second": 19.509,
"eval_steps_per_second": 4.877,
"step": 47
},
{
"epoch": 0.2565130260521042,
"grad_norm": 6.551794052124023,
"learning_rate": 0.00018644534887309944,
"loss": 3.9149,
"step": 48
},
{
"epoch": 0.2618570474281897,
"grad_norm": 6.568101406097412,
"learning_rate": 0.00018548440916607453,
"loss": 3.0155,
"step": 49
},
{
"epoch": 0.26720106880427524,
"grad_norm": 5.584553241729736,
"learning_rate": 0.00018449321837726208,
"loss": 2.9737,
"step": 50
},
{
"epoch": 0.2725450901803607,
"grad_norm": 17.561307907104492,
"learning_rate": 0.00018347212726762437,
"loss": 5.1934,
"step": 51
},
{
"epoch": 0.27788911155644624,
"grad_norm": 18.844377517700195,
"learning_rate": 0.00018242149717919993,
"loss": 5.1302,
"step": 52
},
{
"epoch": 0.2832331329325317,
"grad_norm": 10.627951622009277,
"learning_rate": 0.00018134169990723247,
"loss": 4.5663,
"step": 53
},
{
"epoch": 0.28857715430861725,
"grad_norm": 6.735750198364258,
"learning_rate": 0.00018023311756860038,
"loss": 3.7202,
"step": 54
},
{
"epoch": 0.2939211756847027,
"grad_norm": 4.434415817260742,
"learning_rate": 0.00017909614246659409,
"loss": 4.1791,
"step": 55
},
{
"epoch": 0.29926519706078825,
"grad_norm": 4.674170017242432,
"learning_rate": 0.00017793117695208828,
"loss": 3.8663,
"step": 56
},
{
"epoch": 0.3046092184368738,
"grad_norm": 5.160229206085205,
"learning_rate": 0.0001767386332811587,
"loss": 3.8715,
"step": 57
},
{
"epoch": 0.30995323981295925,
"grad_norm": 4.293652057647705,
"learning_rate": 0.00017551893346919362,
"loss": 2.5835,
"step": 58
},
{
"epoch": 0.3152972611890448,
"grad_norm": 4.6995625495910645,
"learning_rate": 0.0001742725091415517,
"loss": 2.7618,
"step": 59
},
{
"epoch": 0.32064128256513025,
"grad_norm": 5.258271217346191,
"learning_rate": 0.00017299980138081922,
"loss": 3.1181,
"step": 60
},
{
"epoch": 0.3259853039412158,
"grad_norm": 3.5829501152038574,
"learning_rate": 0.00017170126057072032,
"loss": 3.3912,
"step": 61
},
{
"epoch": 0.33132932531730125,
"grad_norm": 4.662436485290527,
"learning_rate": 0.00017037734623673615,
"loss": 3.1201,
"step": 62
},
{
"epoch": 0.3366733466933868,
"grad_norm": 4.6757307052612305,
"learning_rate": 0.00016902852688348866,
"loss": 3.1055,
"step": 63
},
{
"epoch": 0.3420173680694723,
"grad_norm": 3.675757884979248,
"learning_rate": 0.00016765527982894689,
"loss": 3.4294,
"step": 64
},
{
"epoch": 0.3473613894455578,
"grad_norm": 3.7871510982513428,
"learning_rate": 0.00016625809103551462,
"loss": 3.1576,
"step": 65
},
{
"epoch": 0.3527054108216433,
"grad_norm": 7.090997219085693,
"learning_rate": 0.0001648374549380587,
"loss": 1.9401,
"step": 66
},
{
"epoch": 0.3580494321977288,
"grad_norm": 5.046462535858154,
"learning_rate": 0.00016339387426893918,
"loss": 1.7757,
"step": 67
},
{
"epoch": 0.3633934535738143,
"grad_norm": 4.517994403839111,
"learning_rate": 0.00016192785988010353,
"loss": 1.3564,
"step": 68
},
{
"epoch": 0.3687374749498998,
"grad_norm": 3.0163919925689697,
"learning_rate": 0.0001604399305623067,
"loss": 1.3458,
"step": 69
},
{
"epoch": 0.3740814963259853,
"grad_norm": 4.087157249450684,
"learning_rate": 0.00015893061286152276,
"loss": 2.8926,
"step": 70
},
{
"epoch": 0.37942551770207084,
"grad_norm": 4.707438945770264,
"learning_rate": 0.00015740044089261138,
"loss": 3.0473,
"step": 71
},
{
"epoch": 0.3847695390781563,
"grad_norm": 8.234162330627441,
"learning_rate": 0.00015584995615030634,
"loss": 3.6788,
"step": 72
},
{
"epoch": 0.39011356045424184,
"grad_norm": 7.497130870819092,
"learning_rate": 0.00015427970731759212,
"loss": 4.081,
"step": 73
},
{
"epoch": 0.3954575818303273,
"grad_norm": 6.302802085876465,
"learning_rate": 0.000152690250071537,
"loss": 3.5992,
"step": 74
},
{
"epoch": 0.40080160320641284,
"grad_norm": 7.252871036529541,
"learning_rate": 0.0001510821468866508,
"loss": 3.1878,
"step": 75
},
{
"epoch": 0.4061456245824983,
"grad_norm": 4.067234516143799,
"learning_rate": 0.00014945596683583754,
"loss": 3.7711,
"step": 76
},
{
"epoch": 0.41148964595858384,
"grad_norm": 3.713172435760498,
"learning_rate": 0.00014781228538901267,
"loss": 3.8432,
"step": 77
},
{
"epoch": 0.4168336673346693,
"grad_norm": 3.5716781616210938,
"learning_rate": 0.00014615168420945688,
"loss": 3.6756,
"step": 78
},
{
"epoch": 0.42217768871075484,
"grad_norm": 3.4458560943603516,
"learning_rate": 0.00014447475094797797,
"loss": 3.1908,
"step": 79
},
{
"epoch": 0.42752171008684037,
"grad_norm": 2.959568500518799,
"learning_rate": 0.0001427820790349539,
"loss": 3.6547,
"step": 80
},
{
"epoch": 0.43286573146292584,
"grad_norm": 3.844724178314209,
"learning_rate": 0.00014107426747033075,
"loss": 3.4797,
"step": 81
},
{
"epoch": 0.43820975283901137,
"grad_norm": 3.2627336978912354,
"learning_rate": 0.00013935192061164956,
"loss": 3.4215,
"step": 82
},
{
"epoch": 0.44355377421509684,
"grad_norm": 3.0022361278533936,
"learning_rate": 0.00013761564796017724,
"loss": 2.3842,
"step": 83
},
{
"epoch": 0.44889779559118237,
"grad_norm": 2.4692890644073486,
"learning_rate": 0.0001358660639452173,
"loss": 2.2673,
"step": 84
},
{
"epoch": 0.45424181696726784,
"grad_norm": 2.601637363433838,
"learning_rate": 0.0001341037877066766,
"loss": 2.8049,
"step": 85
},
{
"epoch": 0.45958583834335337,
"grad_norm": 2.877810478210449,
"learning_rate": 0.00013232944287596522,
"loss": 2.9897,
"step": 86
},
{
"epoch": 0.4649298597194389,
"grad_norm": 2.801961898803711,
"learning_rate": 0.00013054365735530664,
"loss": 2.969,
"step": 87
},
{
"epoch": 0.47027388109552437,
"grad_norm": 3.4799296855926514,
"learning_rate": 0.00012874706309553698,
"loss": 2.7851,
"step": 88
},
{
"epoch": 0.4756179024716099,
"grad_norm": 3.7868473529815674,
"learning_rate": 0.00012694029587247095,
"loss": 3.4085,
"step": 89
},
{
"epoch": 0.48096192384769537,
"grad_norm": 3.071875810623169,
"learning_rate": 0.0001251239950619149,
"loss": 3.3867,
"step": 90
},
{
"epoch": 0.4863059452237809,
"grad_norm": 8.204347610473633,
"learning_rate": 0.0001232988034134053,
"loss": 1.6884,
"step": 91
},
{
"epoch": 0.4916499665998664,
"grad_norm": 5.938605785369873,
"learning_rate": 0.00012146536682275387,
"loss": 1.5711,
"step": 92
},
{
"epoch": 0.4969939879759519,
"grad_norm": 3.6202452182769775,
"learning_rate": 0.0001196243341034786,
"loss": 1.7918,
"step": 93
},
{
"epoch": 0.5023380093520374,
"grad_norm": 3.0969438552856445,
"learning_rate": 0.00011777635675720313,
"loss": 1.42,
"step": 94
},
{
"epoch": 0.5023380093520374,
"eval_loss": 2.7997498512268066,
"eval_runtime": 16.1659,
"eval_samples_per_second": 19.547,
"eval_steps_per_second": 4.887,
"step": 94
},
{
"epoch": 0.5076820307281229,
"grad_norm": 2.303241014480591,
"learning_rate": 0.00011592208874310426,
"loss": 1.4493,
"step": 95
},
{
"epoch": 0.5130260521042084,
"grad_norm": 4.363836288452148,
"learning_rate": 0.00011406218624648985,
"loss": 3.1983,
"step": 96
},
{
"epoch": 0.518370073480294,
"grad_norm": 6.261653423309326,
"learning_rate": 0.00011219730744658921,
"loss": 3.5712,
"step": 97
},
{
"epoch": 0.5237140948563794,
"grad_norm": 6.892831802368164,
"learning_rate": 0.00011032811228363766,
"loss": 3.5572,
"step": 98
},
{
"epoch": 0.5290581162324649,
"grad_norm": 5.144479751586914,
"learning_rate": 0.00010845526222533791,
"loss": 3.1015,
"step": 99
},
{
"epoch": 0.5344021376085505,
"grad_norm": 7.790161609649658,
"learning_rate": 0.00010657942003278107,
"loss": 2.8553,
"step": 100
},
{
"epoch": 0.539746158984636,
"grad_norm": 7.2072434425354,
"learning_rate": 0.00010470124952590977,
"loss": 3.8293,
"step": 101
},
{
"epoch": 0.5450901803607214,
"grad_norm": 6.349959850311279,
"learning_rate": 0.0001028214153486066,
"loss": 3.9364,
"step": 102
},
{
"epoch": 0.5504342017368069,
"grad_norm": 6.868096351623535,
"learning_rate": 0.00010094058273349125,
"loss": 3.3003,
"step": 103
},
{
"epoch": 0.5557782231128925,
"grad_norm": 5.542849063873291,
"learning_rate": 9.90594172665088e-05,
"loss": 2.9885,
"step": 104
},
{
"epoch": 0.561122244488978,
"grad_norm": 3.5966439247131348,
"learning_rate": 9.717858465139342e-05,
"loss": 3.389,
"step": 105
},
{
"epoch": 0.5664662658650634,
"grad_norm": 3.587754726409912,
"learning_rate": 9.529875047409027e-05,
"loss": 3.3237,
"step": 106
},
{
"epoch": 0.571810287241149,
"grad_norm": 2.8883140087127686,
"learning_rate": 9.342057996721894e-05,
"loss": 2.8259,
"step": 107
},
{
"epoch": 0.5771543086172345,
"grad_norm": 3.080749988555908,
"learning_rate": 9.15447377746621e-05,
"loss": 2.0154,
"step": 108
},
{
"epoch": 0.58249832999332,
"grad_norm": 3.2097012996673584,
"learning_rate": 8.967188771636236e-05,
"loss": 2.4829,
"step": 109
},
{
"epoch": 0.5878423513694054,
"grad_norm": 2.596616268157959,
"learning_rate": 8.78026925534108e-05,
"loss": 2.9976,
"step": 110
},
{
"epoch": 0.593186372745491,
"grad_norm": 2.7296924591064453,
"learning_rate": 8.59378137535102e-05,
"loss": 3.1661,
"step": 111
},
{
"epoch": 0.5985303941215765,
"grad_norm": 2.597951889038086,
"learning_rate": 8.407791125689578e-05,
"loss": 2.9017,
"step": 112
},
{
"epoch": 0.603874415497662,
"grad_norm": 2.5481317043304443,
"learning_rate": 8.222364324279689e-05,
"loss": 3.0536,
"step": 113
},
{
"epoch": 0.6092184368737475,
"grad_norm": 3.0392074584960938,
"learning_rate": 8.037566589652141e-05,
"loss": 3.2358,
"step": 114
},
{
"epoch": 0.614562458249833,
"grad_norm": 2.675720453262329,
"learning_rate": 7.853463317724614e-05,
"loss": 2.8082,
"step": 115
},
{
"epoch": 0.6199064796259185,
"grad_norm": 3.3868227005004883,
"learning_rate": 7.67011965865947e-05,
"loss": 1.7784,
"step": 116
},
{
"epoch": 0.625250501002004,
"grad_norm": 3.886552572250366,
"learning_rate": 7.487600493808513e-05,
"loss": 1.4271,
"step": 117
},
{
"epoch": 0.6305945223780896,
"grad_norm": 3.350705862045288,
"learning_rate": 7.305970412752909e-05,
"loss": 1.421,
"step": 118
},
{
"epoch": 0.635938543754175,
"grad_norm": 2.7557640075683594,
"learning_rate": 7.125293690446306e-05,
"loss": 1.2332,
"step": 119
},
{
"epoch": 0.6412825651302605,
"grad_norm": 1.7134552001953125,
"learning_rate": 6.945634264469339e-05,
"loss": 1.9718,
"step": 120
},
{
"epoch": 0.6466265865063461,
"grad_norm": 2.961225748062134,
"learning_rate": 6.76705571240348e-05,
"loss": 3.0191,
"step": 121
},
{
"epoch": 0.6519706078824316,
"grad_norm": 4.059014320373535,
"learning_rate": 6.58962122933234e-05,
"loss": 3.1156,
"step": 122
},
{
"epoch": 0.657314629258517,
"grad_norm": 4.71870231628418,
"learning_rate": 6.413393605478275e-05,
"loss": 3.3435,
"step": 123
},
{
"epoch": 0.6626586506346025,
"grad_norm": 5.368070125579834,
"learning_rate": 6.238435203982278e-05,
"loss": 3.0588,
"step": 124
},
{
"epoch": 0.6680026720106881,
"grad_norm": 7.744447708129883,
"learning_rate": 6.0648079388350466e-05,
"loss": 3.0363,
"step": 125
},
{
"epoch": 0.6733466933867736,
"grad_norm": 2.309891700744629,
"learning_rate": 5.892573252966926e-05,
"loss": 3.3485,
"step": 126
},
{
"epoch": 0.678690714762859,
"grad_norm": 3.1183762550354004,
"learning_rate": 5.721792096504611e-05,
"loss": 3.7819,
"step": 127
},
{
"epoch": 0.6840347361389446,
"grad_norm": 3.1708717346191406,
"learning_rate": 5.5525249052022076e-05,
"loss": 2.6204,
"step": 128
},
{
"epoch": 0.6893787575150301,
"grad_norm": 2.9361085891723633,
"learning_rate": 5.3848315790543126e-05,
"loss": 2.9473,
"step": 129
},
{
"epoch": 0.6947227788911156,
"grad_norm": 2.8519327640533447,
"learning_rate": 5.218771461098733e-05,
"loss": 3.3713,
"step": 130
},
{
"epoch": 0.700066800267201,
"grad_norm": 3.078104019165039,
"learning_rate": 5.054403316416247e-05,
"loss": 3.2767,
"step": 131
},
{
"epoch": 0.7054108216432866,
"grad_norm": 2.610368013381958,
"learning_rate": 4.891785311334923e-05,
"loss": 3.1482,
"step": 132
},
{
"epoch": 0.7107548430193721,
"grad_norm": 2.4465456008911133,
"learning_rate": 4.7309749928463035e-05,
"loss": 2.4185,
"step": 133
},
{
"epoch": 0.7160988643954576,
"grad_norm": 2.264397621154785,
"learning_rate": 4.5720292682407874e-05,
"loss": 2.0626,
"step": 134
},
{
"epoch": 0.7214428857715431,
"grad_norm": 2.2613508701324463,
"learning_rate": 4.41500438496937e-05,
"loss": 2.7535,
"step": 135
},
{
"epoch": 0.7267869071476286,
"grad_norm": 2.047032356262207,
"learning_rate": 4.2599559107388645e-05,
"loss": 2.9348,
"step": 136
},
{
"epoch": 0.7321309285237141,
"grad_norm": 2.202378273010254,
"learning_rate": 4.10693871384773e-05,
"loss": 2.674,
"step": 137
},
{
"epoch": 0.7374749498997996,
"grad_norm": 2.3247923851013184,
"learning_rate": 3.95600694376933e-05,
"loss": 3.1481,
"step": 138
},
{
"epoch": 0.7428189712758851,
"grad_norm": 2.374443531036377,
"learning_rate": 3.8072140119896504e-05,
"loss": 3.0967,
"step": 139
},
{
"epoch": 0.7481629926519706,
"grad_norm": 2.3245203495025635,
"learning_rate": 3.660612573106081e-05,
"loss": 2.9844,
"step": 140
},
{
"epoch": 0.7535070140280561,
"grad_norm": 2.2515153884887695,
"learning_rate": 3.5162545061941335e-05,
"loss": 1.9046,
"step": 141
},
{
"epoch": 0.7535070140280561,
"eval_loss": 2.6246707439422607,
"eval_runtime": 15.9998,
"eval_samples_per_second": 19.75,
"eval_steps_per_second": 4.938,
"step": 141
}
],
"logging_steps": 1,
"max_steps": 187,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 47,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1611279748549837e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}