Starkdoorstep12's picture
Upload folder using huggingface_hub
7b0e569 verified
Raw History Blame Contribute Delete
77 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 500,
"global_step": 19496,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0051292572835453425,
"grad_norm": 5.146663188934326,
"learning_rate": 5.025641025641026e-07,
"loss": 0.20988283157348633,
"step": 50
},
{
"epoch": 0.010258514567090685,
"grad_norm": 1.9344255924224854,
"learning_rate": 1.0153846153846155e-06,
"loss": 0.08006068229675294,
"step": 100
},
{
"epoch": 0.015387771850636028,
"grad_norm": 0.7599691152572632,
"learning_rate": 1.5282051282051283e-06,
"loss": 0.025034008026123048,
"step": 150
},
{
"epoch": 0.02051702913418137,
"grad_norm": 2.4555349349975586,
"learning_rate": 2.041025641025641e-06,
"loss": 0.019598073959350586,
"step": 200
},
{
"epoch": 0.02564628641772671,
"grad_norm": 0.22511054575443268,
"learning_rate": 2.5538461538461538e-06,
"loss": 0.01550939679145813,
"step": 250
},
{
"epoch": 0.030775543701272057,
"grad_norm": 1.7008031606674194,
"learning_rate": 3.066666666666667e-06,
"loss": 0.015118303298950196,
"step": 300
},
{
"epoch": 0.0359048009848174,
"grad_norm": 0.2420973777770996,
"learning_rate": 3.57948717948718e-06,
"loss": 0.0150359308719635,
"step": 350
},
{
"epoch": 0.04103405826836274,
"grad_norm": 0.07540615648031235,
"learning_rate": 4.0923076923076925e-06,
"loss": 0.011664544343948363,
"step": 400
},
{
"epoch": 0.046163315551908085,
"grad_norm": 0.33558762073516846,
"learning_rate": 4.605128205128205e-06,
"loss": 0.012408304214477538,
"step": 450
},
{
"epoch": 0.05129257283545342,
"grad_norm": 1.9506994485855103,
"learning_rate": 5.1179487179487186e-06,
"loss": 0.01108514666557312,
"step": 500
},
{
"epoch": 0.05642183011899877,
"grad_norm": 2.12082576751709,
"learning_rate": 5.63076923076923e-06,
"loss": 0.007002769708633423,
"step": 550
},
{
"epoch": 0.061551087402544113,
"grad_norm": 0.08876100182533264,
"learning_rate": 6.143589743589744e-06,
"loss": 0.010732929706573486,
"step": 600
},
{
"epoch": 0.06668034468608945,
"grad_norm": 0.06329763680696487,
"learning_rate": 6.656410256410257e-06,
"loss": 0.009123514890670776,
"step": 650
},
{
"epoch": 0.0718096019696348,
"grad_norm": 0.10696346312761307,
"learning_rate": 7.169230769230769e-06,
"loss": 0.006033726930618286,
"step": 700
},
{
"epoch": 0.07693885925318014,
"grad_norm": 0.18690240383148193,
"learning_rate": 7.682051282051283e-06,
"loss": 0.009448485970497132,
"step": 750
},
{
"epoch": 0.08206811653672548,
"grad_norm": 0.13596756756305695,
"learning_rate": 8.194871794871795e-06,
"loss": 0.006707255840301514,
"step": 800
},
{
"epoch": 0.08719737382027082,
"grad_norm": 0.32657232880592346,
"learning_rate": 8.707692307692309e-06,
"loss": 0.006077980995178223,
"step": 850
},
{
"epoch": 0.09232663110381617,
"grad_norm": 0.5776617527008057,
"learning_rate": 9.220512820512822e-06,
"loss": 0.0075683963298797605,
"step": 900
},
{
"epoch": 0.09745588838736151,
"grad_norm": 0.24212700128555298,
"learning_rate": 9.733333333333334e-06,
"loss": 0.005986063480377197,
"step": 950
},
{
"epoch": 0.10258514567090685,
"grad_norm": 0.5887935161590576,
"learning_rate": 1.0246153846153847e-05,
"loss": 0.004652740359306335,
"step": 1000
},
{
"epoch": 0.1077144029544522,
"grad_norm": 1.7308635711669922,
"learning_rate": 1.0758974358974359e-05,
"loss": 0.0070805585384368895,
"step": 1050
},
{
"epoch": 0.11284366023799754,
"grad_norm": 0.3150564134120941,
"learning_rate": 1.1271794871794873e-05,
"loss": 0.006270056962966919,
"step": 1100
},
{
"epoch": 0.11797291752154287,
"grad_norm": 0.1266297996044159,
"learning_rate": 1.1784615384615386e-05,
"loss": 0.004561504721641541,
"step": 1150
},
{
"epoch": 0.12310217480508823,
"grad_norm": 0.1587323397397995,
"learning_rate": 1.22974358974359e-05,
"loss": 0.003875747323036194,
"step": 1200
},
{
"epoch": 0.12823143208863358,
"grad_norm": 1.8177411556243896,
"learning_rate": 1.2810256410256411e-05,
"loss": 0.004878196120262146,
"step": 1250
},
{
"epoch": 0.1333606893721789,
"grad_norm": 0.07512801885604858,
"learning_rate": 1.3323076923076925e-05,
"loss": 0.005473270416259766,
"step": 1300
},
{
"epoch": 0.13848994665572426,
"grad_norm": 0.09478379040956497,
"learning_rate": 1.3835897435897437e-05,
"loss": 0.003836294412612915,
"step": 1350
},
{
"epoch": 0.1436192039392696,
"grad_norm": 0.20241230726242065,
"learning_rate": 1.434871794871795e-05,
"loss": 0.004140390455722809,
"step": 1400
},
{
"epoch": 0.14874846122281493,
"grad_norm": 0.28742000460624695,
"learning_rate": 1.4861538461538464e-05,
"loss": 0.005977784991264343,
"step": 1450
},
{
"epoch": 0.15387771850636028,
"grad_norm": 1.9182926416397095,
"learning_rate": 1.5374358974358975e-05,
"loss": 0.00550079345703125,
"step": 1500
},
{
"epoch": 0.1590069757899056,
"grad_norm": 0.23799288272857666,
"learning_rate": 1.588717948717949e-05,
"loss": 0.00528115451335907,
"step": 1550
},
{
"epoch": 0.16413623307345096,
"grad_norm": 0.18093019723892212,
"learning_rate": 1.64e-05,
"loss": 0.004683617353439331,
"step": 1600
},
{
"epoch": 0.1692654903569963,
"grad_norm": 0.6764870882034302,
"learning_rate": 1.6912820512820512e-05,
"loss": 0.004430403709411621,
"step": 1650
},
{
"epoch": 0.17439474764054164,
"grad_norm": 0.030442317947745323,
"learning_rate": 1.7425641025641026e-05,
"loss": 0.007149366140365601,
"step": 1700
},
{
"epoch": 0.179524004924087,
"grad_norm": 0.12910808622837067,
"learning_rate": 1.793846153846154e-05,
"loss": 0.004426850080490112,
"step": 1750
},
{
"epoch": 0.18465326220763234,
"grad_norm": 0.03711940720677376,
"learning_rate": 1.8451282051282053e-05,
"loss": 0.002525296211242676,
"step": 1800
},
{
"epoch": 0.18978251949117766,
"grad_norm": 0.209708109498024,
"learning_rate": 1.8964102564102566e-05,
"loss": 0.005534772872924805,
"step": 1850
},
{
"epoch": 0.19491177677472302,
"grad_norm": 0.07900407165288925,
"learning_rate": 1.9476923076923076e-05,
"loss": 0.00532868504524231,
"step": 1900
},
{
"epoch": 0.20004103405826837,
"grad_norm": 0.04088887572288513,
"learning_rate": 1.998974358974359e-05,
"loss": 0.004520394206047058,
"step": 1950
},
{
"epoch": 0.2051702913418137,
"grad_norm": 0.044649723917245865,
"learning_rate": 1.9944146814088682e-05,
"loss": 0.004650795459747314,
"step": 2000
},
{
"epoch": 0.21029954862535905,
"grad_norm": 0.36089038848876953,
"learning_rate": 1.98871537672404e-05,
"loss": 0.004750135838985443,
"step": 2050
},
{
"epoch": 0.2154288059089044,
"grad_norm": 0.2627781331539154,
"learning_rate": 1.9830160720392112e-05,
"loss": 0.004101980328559875,
"step": 2100
},
{
"epoch": 0.22055806319244972,
"grad_norm": 0.0719594806432724,
"learning_rate": 1.977316767354383e-05,
"loss": 0.002980492115020752,
"step": 2150
},
{
"epoch": 0.22568732047599507,
"grad_norm": 0.027993543073534966,
"learning_rate": 1.9716174626695546e-05,
"loss": 0.0036524400115013123,
"step": 2200
},
{
"epoch": 0.23081657775954043,
"grad_norm": 0.020856564864516258,
"learning_rate": 1.965918157984726e-05,
"loss": 0.004709515571594238,
"step": 2250
},
{
"epoch": 0.23594583504308575,
"grad_norm": 0.7141599655151367,
"learning_rate": 1.9602188532998976e-05,
"loss": 0.004219242334365845,
"step": 2300
},
{
"epoch": 0.2410750923266311,
"grad_norm": 0.6264314651489258,
"learning_rate": 1.954519548615069e-05,
"loss": 0.0027445003390312193,
"step": 2350
},
{
"epoch": 0.24620434961017645,
"grad_norm": 0.0843123346567154,
"learning_rate": 1.9488202439302406e-05,
"loss": 0.004736282825469971,
"step": 2400
},
{
"epoch": 0.2513336068937218,
"grad_norm": 0.03579830378293991,
"learning_rate": 1.943120939245412e-05,
"loss": 0.002808626592159271,
"step": 2450
},
{
"epoch": 0.25646286417726716,
"grad_norm": 1.2769086360931396,
"learning_rate": 1.937421634560584e-05,
"loss": 0.0043040883541107175,
"step": 2500
},
{
"epoch": 0.26159212146081245,
"grad_norm": 0.6006304621696472,
"learning_rate": 1.931722329875755e-05,
"loss": 0.00633010983467102,
"step": 2550
},
{
"epoch": 0.2667213787443578,
"grad_norm": 0.4219711422920227,
"learning_rate": 1.926023025190927e-05,
"loss": 0.002694355249404907,
"step": 2600
},
{
"epoch": 0.27185063602790316,
"grad_norm": 0.03629787266254425,
"learning_rate": 1.9203237205060985e-05,
"loss": 0.0020533058047294615,
"step": 2650
},
{
"epoch": 0.2769798933114485,
"grad_norm": 0.5271649360656738,
"learning_rate": 1.91462441582127e-05,
"loss": 0.002846062183380127,
"step": 2700
},
{
"epoch": 0.28210915059499386,
"grad_norm": 0.038686707615852356,
"learning_rate": 1.9089251111364415e-05,
"loss": 0.002439509928226471,
"step": 2750
},
{
"epoch": 0.2872384078785392,
"grad_norm": 0.0804801732301712,
"learning_rate": 1.903225806451613e-05,
"loss": 0.00447674959897995,
"step": 2800
},
{
"epoch": 0.2923676651620845,
"grad_norm": 0.11198680847883224,
"learning_rate": 1.8975265017667846e-05,
"loss": 0.0033469206094741823,
"step": 2850
},
{
"epoch": 0.29749692244562986,
"grad_norm": 0.2559853196144104,
"learning_rate": 1.891827197081956e-05,
"loss": 0.004776168465614319,
"step": 2900
},
{
"epoch": 0.3026261797291752,
"grad_norm": 0.9892205595970154,
"learning_rate": 1.886127892397128e-05,
"loss": 0.0021404142677783965,
"step": 2950
},
{
"epoch": 0.30775543701272057,
"grad_norm": 0.028234116733074188,
"learning_rate": 1.880428587712299e-05,
"loss": 0.0031156307458877564,
"step": 3000
},
{
"epoch": 0.3128846942962659,
"grad_norm": 0.08867978304624557,
"learning_rate": 1.874729283027471e-05,
"loss": 0.002720406651496887,
"step": 3050
},
{
"epoch": 0.3180139515798112,
"grad_norm": 0.4465535283088684,
"learning_rate": 1.8690299783426425e-05,
"loss": 0.0033028775453567503,
"step": 3100
},
{
"epoch": 0.32314320886335657,
"grad_norm": 0.11233843117952347,
"learning_rate": 1.863330673657814e-05,
"loss": 0.004013978838920593,
"step": 3150
},
{
"epoch": 0.3282724661469019,
"grad_norm": 0.06376665830612183,
"learning_rate": 1.8576313689729855e-05,
"loss": 0.0012492486834526063,
"step": 3200
},
{
"epoch": 0.33340172343044727,
"grad_norm": 0.03352602571249008,
"learning_rate": 1.851932064288157e-05,
"loss": 0.0030529314279556276,
"step": 3250
},
{
"epoch": 0.3385309807139926,
"grad_norm": 1.316901683807373,
"learning_rate": 1.8462327596033285e-05,
"loss": 0.003336084485054016,
"step": 3300
},
{
"epoch": 0.343660237997538,
"grad_norm": 0.5216875076293945,
"learning_rate": 1.8405334549185e-05,
"loss": 0.0019701987504959105,
"step": 3350
},
{
"epoch": 0.3487894952810833,
"grad_norm": 0.008256763219833374,
"learning_rate": 1.834834150233672e-05,
"loss": 0.002782421410083771,
"step": 3400
},
{
"epoch": 0.3539187525646286,
"grad_norm": 0.14605538547039032,
"learning_rate": 1.829134845548843e-05,
"loss": 0.0022422271966934205,
"step": 3450
},
{
"epoch": 0.359048009848174,
"grad_norm": 0.05085963010787964,
"learning_rate": 1.823435540864015e-05,
"loss": 0.002529405951499939,
"step": 3500
},
{
"epoch": 0.36417726713171933,
"grad_norm": 0.0359930619597435,
"learning_rate": 1.8177362361791864e-05,
"loss": 0.0026357889175415037,
"step": 3550
},
{
"epoch": 0.3693065244152647,
"grad_norm": 0.23114101588726044,
"learning_rate": 1.812036931494358e-05,
"loss": 0.0027996709942817687,
"step": 3600
},
{
"epoch": 0.37443578169881003,
"grad_norm": 0.021300168707966805,
"learning_rate": 1.8063376268095294e-05,
"loss": 0.0034693616628646852,
"step": 3650
},
{
"epoch": 0.37956503898235533,
"grad_norm": 0.11509425938129425,
"learning_rate": 1.800638322124701e-05,
"loss": 0.0023235560953617095,
"step": 3700
},
{
"epoch": 0.3846942962659007,
"grad_norm": 0.6359381079673767,
"learning_rate": 1.7949390174398724e-05,
"loss": 0.002906927764415741,
"step": 3750
},
{
"epoch": 0.38982355354944603,
"grad_norm": 0.030257439240813255,
"learning_rate": 1.789239712755044e-05,
"loss": 0.0030827236175537107,
"step": 3800
},
{
"epoch": 0.3949528108329914,
"grad_norm": 0.19199493527412415,
"learning_rate": 1.7835404080702158e-05,
"loss": 0.0042154985666275025,
"step": 3850
},
{
"epoch": 0.40008206811653674,
"grad_norm": 0.01845471002161503,
"learning_rate": 1.777841103385387e-05,
"loss": 0.002743417024612427,
"step": 3900
},
{
"epoch": 0.4052113254000821,
"grad_norm": 0.019544444978237152,
"learning_rate": 1.7721417987005588e-05,
"loss": 0.003500168323516846,
"step": 3950
},
{
"epoch": 0.4103405826836274,
"grad_norm": 1.0970685482025146,
"learning_rate": 1.7664424940157303e-05,
"loss": 0.0025902286171913145,
"step": 4000
},
{
"epoch": 0.41546983996717274,
"grad_norm": 0.0196465365588665,
"learning_rate": 1.760743189330902e-05,
"loss": 0.0017264434695243836,
"step": 4050
},
{
"epoch": 0.4205990972507181,
"grad_norm": 0.1122385635972023,
"learning_rate": 1.7550438846460734e-05,
"loss": 0.00217318132519722,
"step": 4100
},
{
"epoch": 0.42572835453426344,
"grad_norm": 0.24590978026390076,
"learning_rate": 1.749344579961245e-05,
"loss": 0.001975882798433304,
"step": 4150
},
{
"epoch": 0.4308576118178088,
"grad_norm": 0.033505771309137344,
"learning_rate": 1.7436452752764164e-05,
"loss": 0.002472508400678635,
"step": 4200
},
{
"epoch": 0.43598686910135415,
"grad_norm": 0.11213713139295578,
"learning_rate": 1.737945970591588e-05,
"loss": 0.002362338155508041,
"step": 4250
},
{
"epoch": 0.44111612638489944,
"grad_norm": 0.0998101606965065,
"learning_rate": 1.7322466659067597e-05,
"loss": 0.0025117507576942442,
"step": 4300
},
{
"epoch": 0.4462453836684448,
"grad_norm": 0.10846878588199615,
"learning_rate": 1.726547361221931e-05,
"loss": 0.002475926429033279,
"step": 4350
},
{
"epoch": 0.45137464095199015,
"grad_norm": 0.30236443877220154,
"learning_rate": 1.7208480565371028e-05,
"loss": 0.002092706859111786,
"step": 4400
},
{
"epoch": 0.4565038982355355,
"grad_norm": 0.020106056705117226,
"learning_rate": 1.7151487518522743e-05,
"loss": 0.0010956238210201264,
"step": 4450
},
{
"epoch": 0.46163315551908085,
"grad_norm": 0.06396861374378204,
"learning_rate": 1.7094494471674458e-05,
"loss": 0.0018238377571105956,
"step": 4500
},
{
"epoch": 0.4667624128026262,
"grad_norm": 0.4166419506072998,
"learning_rate": 1.7037501424826173e-05,
"loss": 0.003854023814201355,
"step": 4550
},
{
"epoch": 0.4718916700861715,
"grad_norm": 0.03014219179749489,
"learning_rate": 1.6980508377977888e-05,
"loss": 0.0016187562048435211,
"step": 4600
},
{
"epoch": 0.47702092736971685,
"grad_norm": 0.25602439045906067,
"learning_rate": 1.6923515331129603e-05,
"loss": 0.002320457398891449,
"step": 4650
},
{
"epoch": 0.4821501846532622,
"grad_norm": 0.02201703004539013,
"learning_rate": 1.686652228428132e-05,
"loss": 0.0012020480632781983,
"step": 4700
},
{
"epoch": 0.48727944193680756,
"grad_norm": 0.05641191452741623,
"learning_rate": 1.6809529237433037e-05,
"loss": 0.002663995623588562,
"step": 4750
},
{
"epoch": 0.4924086992203529,
"grad_norm": 0.06632937490940094,
"learning_rate": 1.675253619058475e-05,
"loss": 0.0020142243802547454,
"step": 4800
},
{
"epoch": 0.49753795650389826,
"grad_norm": 0.09227260202169418,
"learning_rate": 1.6695543143736467e-05,
"loss": 0.002214210033416748,
"step": 4850
},
{
"epoch": 0.5026672137874436,
"grad_norm": 0.04919379949569702,
"learning_rate": 1.6638550096888182e-05,
"loss": 0.0022323706746101377,
"step": 4900
},
{
"epoch": 0.5077964710709889,
"grad_norm": 0.05477536842226982,
"learning_rate": 1.6581557050039897e-05,
"loss": 0.0015611539781093598,
"step": 4950
},
{
"epoch": 0.5129257283545343,
"grad_norm": 0.07904011756181717,
"learning_rate": 1.6524564003191613e-05,
"loss": 0.0026751086115837097,
"step": 5000
},
{
"epoch": 0.5180549856380796,
"grad_norm": 0.03175102546811104,
"learning_rate": 1.6467570956343328e-05,
"loss": 0.0017083890736103058,
"step": 5050
},
{
"epoch": 0.5231842429216249,
"grad_norm": 0.3278403878211975,
"learning_rate": 1.6410577909495043e-05,
"loss": 0.00195760115981102,
"step": 5100
},
{
"epoch": 0.5283135002051703,
"grad_norm": 0.21054060757160187,
"learning_rate": 1.6353584862646758e-05,
"loss": 0.002422951906919479,
"step": 5150
},
{
"epoch": 0.5334427574887156,
"grad_norm": 0.13860668241977692,
"learning_rate": 1.6296591815798476e-05,
"loss": 0.002446786016225815,
"step": 5200
},
{
"epoch": 0.538572014772261,
"grad_norm": 0.3238920569419861,
"learning_rate": 1.6239598768950188e-05,
"loss": 0.0024388924241065977,
"step": 5250
},
{
"epoch": 0.5437012720558063,
"grad_norm": 0.009936186484992504,
"learning_rate": 1.6182605722101907e-05,
"loss": 0.002167973667383194,
"step": 5300
},
{
"epoch": 0.5488305293393516,
"grad_norm": 0.10222964733839035,
"learning_rate": 1.6125612675253622e-05,
"loss": 0.002880829870700836,
"step": 5350
},
{
"epoch": 0.553959786622897,
"grad_norm": 0.006579564418643713,
"learning_rate": 1.6068619628405337e-05,
"loss": 0.0015730999410152435,
"step": 5400
},
{
"epoch": 0.5590890439064423,
"grad_norm": 0.013894481584429741,
"learning_rate": 1.6011626581557052e-05,
"loss": 0.0010276009142398835,
"step": 5450
},
{
"epoch": 0.5642183011899877,
"grad_norm": 0.1254359483718872,
"learning_rate": 1.5954633534708767e-05,
"loss": 0.0017169848084449767,
"step": 5500
},
{
"epoch": 0.569347558473533,
"grad_norm": 0.12541364133358002,
"learning_rate": 1.5897640487860482e-05,
"loss": 0.0028713226318359377,
"step": 5550
},
{
"epoch": 0.5744768157570784,
"grad_norm": 0.08445322513580322,
"learning_rate": 1.5840647441012197e-05,
"loss": 0.0016673532128334044,
"step": 5600
},
{
"epoch": 0.5796060730406237,
"grad_norm": 0.04391612112522125,
"learning_rate": 1.5783654394163916e-05,
"loss": 0.002128530740737915,
"step": 5650
},
{
"epoch": 0.584735330324169,
"grad_norm": 0.5561177134513855,
"learning_rate": 1.5726661347315628e-05,
"loss": 0.0019441001117229463,
"step": 5700
},
{
"epoch": 0.5898645876077144,
"grad_norm": 0.09118201583623886,
"learning_rate": 1.5669668300467346e-05,
"loss": 0.0021015436947345732,
"step": 5750
},
{
"epoch": 0.5949938448912597,
"grad_norm": 0.022824030369520187,
"learning_rate": 1.561267525361906e-05,
"loss": 0.002961210608482361,
"step": 5800
},
{
"epoch": 0.6001231021748051,
"grad_norm": 0.04558834061026573,
"learning_rate": 1.5555682206770776e-05,
"loss": 0.001471487581729889,
"step": 5850
},
{
"epoch": 0.6052523594583504,
"grad_norm": 0.031143372878432274,
"learning_rate": 1.549868915992249e-05,
"loss": 0.0027905339002609253,
"step": 5900
},
{
"epoch": 0.6103816167418957,
"grad_norm": 0.2602635324001312,
"learning_rate": 1.5441696113074207e-05,
"loss": 0.002177398204803467,
"step": 5950
},
{
"epoch": 0.6155108740254411,
"grad_norm": 0.008853335864841938,
"learning_rate": 1.538470306622592e-05,
"loss": 0.0020481890439987185,
"step": 6000
},
{
"epoch": 0.6206401313089864,
"grad_norm": 0.024634389206767082,
"learning_rate": 1.5327710019377637e-05,
"loss": 0.002121390849351883,
"step": 6050
},
{
"epoch": 0.6257693885925318,
"grad_norm": 0.009994241409003735,
"learning_rate": 1.5270716972529355e-05,
"loss": 0.001738632023334503,
"step": 6100
},
{
"epoch": 0.6308986458760771,
"grad_norm": 0.16715426743030548,
"learning_rate": 1.5213723925681067e-05,
"loss": 0.002144707888364792,
"step": 6150
},
{
"epoch": 0.6360279031596224,
"grad_norm": 0.05593431368470192,
"learning_rate": 1.5156730878832784e-05,
"loss": 0.0014984746277332305,
"step": 6200
},
{
"epoch": 0.6411571604431678,
"grad_norm": 0.030156264081597328,
"learning_rate": 1.50997378319845e-05,
"loss": 0.0010228657722473145,
"step": 6250
},
{
"epoch": 0.6462864177267131,
"grad_norm": 0.045500464737415314,
"learning_rate": 1.5042744785136214e-05,
"loss": 0.0017821905016899109,
"step": 6300
},
{
"epoch": 0.6514156750102585,
"grad_norm": 0.0190139077603817,
"learning_rate": 1.4985751738287931e-05,
"loss": 0.0011478330194950104,
"step": 6350
},
{
"epoch": 0.6565449322938038,
"grad_norm": 0.022497054189443588,
"learning_rate": 1.4928758691439646e-05,
"loss": 0.003517746925354004,
"step": 6400
},
{
"epoch": 0.6616741895773492,
"grad_norm": 0.03552277013659477,
"learning_rate": 1.4871765644591361e-05,
"loss": 0.0014983375370502471,
"step": 6450
},
{
"epoch": 0.6668034468608945,
"grad_norm": 0.012892907485365868,
"learning_rate": 1.4814772597743076e-05,
"loss": 0.0021820993721485137,
"step": 6500
},
{
"epoch": 0.6719327041444398,
"grad_norm": 0.0045395540073513985,
"learning_rate": 1.4757779550894793e-05,
"loss": 0.001870407611131668,
"step": 6550
},
{
"epoch": 0.6770619614279852,
"grad_norm": 0.054160960018634796,
"learning_rate": 1.4700786504046506e-05,
"loss": 0.0016691868007183074,
"step": 6600
},
{
"epoch": 0.6821912187115305,
"grad_norm": 0.021756375208497047,
"learning_rate": 1.4643793457198223e-05,
"loss": 0.0011199010908603667,
"step": 6650
},
{
"epoch": 0.687320475995076,
"grad_norm": 0.24180440604686737,
"learning_rate": 1.458680041034994e-05,
"loss": 0.002085486799478531,
"step": 6700
},
{
"epoch": 0.6924497332786212,
"grad_norm": 0.02364238165318966,
"learning_rate": 1.4529807363501653e-05,
"loss": 0.001655416041612625,
"step": 6750
},
{
"epoch": 0.6975789905621665,
"grad_norm": 0.013433502987027168,
"learning_rate": 1.447281431665337e-05,
"loss": 0.0014493338763713836,
"step": 6800
},
{
"epoch": 0.702708247845712,
"grad_norm": 0.09692008048295975,
"learning_rate": 1.4415821269805085e-05,
"loss": 0.002443571090698242,
"step": 6850
},
{
"epoch": 0.7078375051292572,
"grad_norm": 0.011011690832674503,
"learning_rate": 1.43588282229568e-05,
"loss": 0.0011622200906276703,
"step": 6900
},
{
"epoch": 0.7129667624128027,
"grad_norm": 0.03306994214653969,
"learning_rate": 1.4301835176108516e-05,
"loss": 0.003230692148208618,
"step": 6950
},
{
"epoch": 0.718096019696348,
"grad_norm": 0.08337920904159546,
"learning_rate": 1.4244842129260232e-05,
"loss": 0.001955211907625198,
"step": 7000
},
{
"epoch": 0.7232252769798934,
"grad_norm": 0.08515248447656631,
"learning_rate": 1.4187849082411946e-05,
"loss": 0.001256055235862732,
"step": 7050
},
{
"epoch": 0.7283545342634387,
"grad_norm": 0.11170300841331482,
"learning_rate": 1.4130856035563663e-05,
"loss": 0.0038022392988204955,
"step": 7100
},
{
"epoch": 0.733483791546984,
"grad_norm": 0.005572218913584948,
"learning_rate": 1.407386298871538e-05,
"loss": 0.0017911630868911743,
"step": 7150
},
{
"epoch": 0.7386130488305294,
"grad_norm": 0.008966299705207348,
"learning_rate": 1.4016869941867093e-05,
"loss": 0.0018778586387634278,
"step": 7200
},
{
"epoch": 0.7437423061140747,
"grad_norm": 0.21079233288764954,
"learning_rate": 1.395987689501881e-05,
"loss": 0.0037654682993888853,
"step": 7250
},
{
"epoch": 0.7488715633976201,
"grad_norm": 0.0403057225048542,
"learning_rate": 1.3902883848170525e-05,
"loss": 0.0012686464190483093,
"step": 7300
},
{
"epoch": 0.7540008206811654,
"grad_norm": 0.09920848160982132,
"learning_rate": 1.384589080132224e-05,
"loss": 0.002512713074684143,
"step": 7350
},
{
"epoch": 0.7591300779647107,
"grad_norm": 0.03594447299838066,
"learning_rate": 1.3788897754473955e-05,
"loss": 0.002175413519144058,
"step": 7400
},
{
"epoch": 0.7642593352482561,
"grad_norm": 0.012109672650694847,
"learning_rate": 1.3731904707625672e-05,
"loss": 0.0014021342992782593,
"step": 7450
},
{
"epoch": 0.7693885925318014,
"grad_norm": 0.055439919233322144,
"learning_rate": 1.3674911660777385e-05,
"loss": 0.0014539873600006104,
"step": 7500
},
{
"epoch": 0.7745178498153468,
"grad_norm": 0.03262806683778763,
"learning_rate": 1.3617918613929102e-05,
"loss": 0.002966693043708801,
"step": 7550
},
{
"epoch": 0.7796471070988921,
"grad_norm": 0.6407725811004639,
"learning_rate": 1.3560925567080819e-05,
"loss": 0.0016460046172142029,
"step": 7600
},
{
"epoch": 0.7847763643824375,
"grad_norm": 0.07301273196935654,
"learning_rate": 1.3503932520232532e-05,
"loss": 0.001733643114566803,
"step": 7650
},
{
"epoch": 0.7899056216659828,
"grad_norm": 0.04729823023080826,
"learning_rate": 1.344693947338425e-05,
"loss": 0.0012972503900527954,
"step": 7700
},
{
"epoch": 0.7950348789495281,
"grad_norm": 0.055704180151224136,
"learning_rate": 1.3389946426535964e-05,
"loss": 0.0036036667227745058,
"step": 7750
},
{
"epoch": 0.8001641362330735,
"grad_norm": 0.04170205816626549,
"learning_rate": 1.333295337968768e-05,
"loss": 0.002159286290407181,
"step": 7800
},
{
"epoch": 0.8052933935166188,
"grad_norm": 0.03427044302225113,
"learning_rate": 1.3275960332839395e-05,
"loss": 0.001466388702392578,
"step": 7850
},
{
"epoch": 0.8104226508001642,
"grad_norm": 0.1446782499551773,
"learning_rate": 1.3218967285991111e-05,
"loss": 0.0009994275867938995,
"step": 7900
},
{
"epoch": 0.8155519080837095,
"grad_norm": 1.960245132446289,
"learning_rate": 1.3161974239142825e-05,
"loss": 0.002109799236059189,
"step": 7950
},
{
"epoch": 0.8206811653672548,
"grad_norm": 0.011322901584208012,
"learning_rate": 1.3104981192294542e-05,
"loss": 0.0019486966729164125,
"step": 8000
},
{
"epoch": 0.8258104226508002,
"grad_norm": 0.02532426454126835,
"learning_rate": 1.3047988145446258e-05,
"loss": 0.0010834269225597382,
"step": 8050
},
{
"epoch": 0.8309396799343455,
"grad_norm": 0.006674936041235924,
"learning_rate": 1.2990995098597972e-05,
"loss": 0.0012358775734901428,
"step": 8100
},
{
"epoch": 0.8360689372178909,
"grad_norm": 0.004865461494773626,
"learning_rate": 1.2934002051749689e-05,
"loss": 0.0026021018624305726,
"step": 8150
},
{
"epoch": 0.8411981945014362,
"grad_norm": 0.03563657030463219,
"learning_rate": 1.2877009004901404e-05,
"loss": 0.0010813122987747192,
"step": 8200
},
{
"epoch": 0.8463274517849816,
"grad_norm": 0.1195644959807396,
"learning_rate": 1.2820015958053119e-05,
"loss": 0.0018597865104675293,
"step": 8250
},
{
"epoch": 0.8514567090685269,
"grad_norm": 0.01012786477804184,
"learning_rate": 1.2763022911204834e-05,
"loss": 0.001704736053943634,
"step": 8300
},
{
"epoch": 0.8565859663520722,
"grad_norm": 0.02338203229010105,
"learning_rate": 1.270602986435655e-05,
"loss": 0.0011339907348155976,
"step": 8350
},
{
"epoch": 0.8617152236356176,
"grad_norm": 0.01370213832706213,
"learning_rate": 1.2649036817508264e-05,
"loss": 0.0012083581089973449,
"step": 8400
},
{
"epoch": 0.8668444809191629,
"grad_norm": 0.05253306403756142,
"learning_rate": 1.2592043770659981e-05,
"loss": 0.0018029493093490601,
"step": 8450
},
{
"epoch": 0.8719737382027083,
"grad_norm": 0.019181661307811737,
"learning_rate": 1.2535050723811696e-05,
"loss": 0.0008252602815628052,
"step": 8500
},
{
"epoch": 0.8771029954862536,
"grad_norm": 0.3479258716106415,
"learning_rate": 1.2478057676963411e-05,
"loss": 0.0017175833880901338,
"step": 8550
},
{
"epoch": 0.8822322527697989,
"grad_norm": 0.05874745175242424,
"learning_rate": 1.2421064630115126e-05,
"loss": 0.002253309488296509,
"step": 8600
},
{
"epoch": 0.8873615100533443,
"grad_norm": 0.025928650051355362,
"learning_rate": 1.2364071583266843e-05,
"loss": 0.0010428188741207123,
"step": 8650
},
{
"epoch": 0.8924907673368896,
"grad_norm": 0.02793911285698414,
"learning_rate": 1.2307078536418557e-05,
"loss": 0.0010901305079460144,
"step": 8700
},
{
"epoch": 0.897620024620435,
"grad_norm": 0.026237769052386284,
"learning_rate": 1.2250085489570273e-05,
"loss": 0.002191057354211807,
"step": 8750
},
{
"epoch": 0.9027492819039803,
"grad_norm": 0.026652701199054718,
"learning_rate": 1.219309244272199e-05,
"loss": 0.0022504705190658568,
"step": 8800
},
{
"epoch": 0.9078785391875257,
"grad_norm": 0.09745952486991882,
"learning_rate": 1.2136099395873704e-05,
"loss": 0.0013040122389793396,
"step": 8850
},
{
"epoch": 0.913007796471071,
"grad_norm": 0.3571895956993103,
"learning_rate": 1.207910634902542e-05,
"loss": 0.0015031418204307556,
"step": 8900
},
{
"epoch": 0.9181370537546163,
"grad_norm": 0.05399506166577339,
"learning_rate": 1.2022113302177136e-05,
"loss": 0.003377719819545746,
"step": 8950
},
{
"epoch": 0.9232663110381617,
"grad_norm": 0.017251811921596527,
"learning_rate": 1.196512025532885e-05,
"loss": 0.0010861025750637055,
"step": 9000
},
{
"epoch": 0.928395568321707,
"grad_norm": 0.01030634343624115,
"learning_rate": 1.1908127208480566e-05,
"loss": 0.0018379358947277068,
"step": 9050
},
{
"epoch": 0.9335248256052524,
"grad_norm": 0.04392435401678085,
"learning_rate": 1.1851134161632283e-05,
"loss": 0.0013357341289520265,
"step": 9100
},
{
"epoch": 0.9386540828887977,
"grad_norm": 0.009581666439771652,
"learning_rate": 1.1794141114783996e-05,
"loss": 0.0009307318925857544,
"step": 9150
},
{
"epoch": 0.943783340172343,
"grad_norm": 0.017958320677280426,
"learning_rate": 1.1737148067935713e-05,
"loss": 0.0008443382382392884,
"step": 9200
},
{
"epoch": 0.9489125974558884,
"grad_norm": 0.030002426356077194,
"learning_rate": 1.168015502108743e-05,
"loss": 0.0013130667805671692,
"step": 9250
},
{
"epoch": 0.9540418547394337,
"grad_norm": 0.05621248111128807,
"learning_rate": 1.1623161974239143e-05,
"loss": 0.0012183979153633118,
"step": 9300
},
{
"epoch": 0.9591711120229791,
"grad_norm": 0.015438093803822994,
"learning_rate": 1.156616892739086e-05,
"loss": 0.0012114503979682922,
"step": 9350
},
{
"epoch": 0.9643003693065244,
"grad_norm": 0.07112756371498108,
"learning_rate": 1.1509175880542575e-05,
"loss": 0.0007900720834732055,
"step": 9400
},
{
"epoch": 0.9694296265900697,
"grad_norm": 0.017932914197444916,
"learning_rate": 1.145218283369429e-05,
"loss": 0.0010725505650043487,
"step": 9450
},
{
"epoch": 0.9745588838736151,
"grad_norm": 0.021347526460886,
"learning_rate": 1.1395189786846005e-05,
"loss": 0.0007509399950504303,
"step": 9500
},
{
"epoch": 0.9796881411571604,
"grad_norm": 0.06269439309835434,
"learning_rate": 1.1338196739997722e-05,
"loss": 0.0014818912744522094,
"step": 9550
},
{
"epoch": 0.9848173984407058,
"grad_norm": 0.030811917036771774,
"learning_rate": 1.1281203693149435e-05,
"loss": 0.0014112085103988648,
"step": 9600
},
{
"epoch": 0.9899466557242511,
"grad_norm": 0.01883218064904213,
"learning_rate": 1.1224210646301152e-05,
"loss": 0.0012676098942756653,
"step": 9650
},
{
"epoch": 0.9950759130077965,
"grad_norm": 0.011095144785940647,
"learning_rate": 1.1167217599452869e-05,
"loss": 0.0006470730900764465,
"step": 9700
},
{
"epoch": 1.0,
"eval_biencoder-val_cosine_accuracy@1": 0.929,
"eval_biencoder-val_cosine_accuracy@10": 1.0,
"eval_biencoder-val_cosine_accuracy@30": 1.0,
"eval_biencoder-val_cosine_accuracy@5": 1.0,
"eval_biencoder-val_cosine_map@100": 0.9638333333333332,
"eval_biencoder-val_cosine_mrr@10": 0.9638333333333332,
"eval_biencoder-val_cosine_ndcg@10": 0.9732722934892877,
"eval_biencoder-val_cosine_precision@1": 0.929,
"eval_biencoder-val_cosine_precision@10": 0.10000000000000002,
"eval_biencoder-val_cosine_precision@3": 0.33333333333333326,
"eval_biencoder-val_cosine_precision@5": 0.20000000000000004,
"eval_biencoder-val_cosine_recall@1": 0.929,
"eval_biencoder-val_cosine_recall@10": 1.0,
"eval_biencoder-val_cosine_recall@3": 1.0,
"eval_biencoder-val_cosine_recall@5": 1.0,
"eval_runtime": 0.8723,
"eval_samples_per_second": 0.0,
"eval_steps_per_second": 0.0,
"step": 9748
},
{
"epoch": 1.0002051702913417,
"grad_norm": 0.020323621109128,
"learning_rate": 1.1110224552604583e-05,
"loss": 0.0013780112564563752,
"step": 9750
},
{
"epoch": 1.0053344275748872,
"grad_norm": 0.004307797644287348,
"learning_rate": 1.10532315057563e-05,
"loss": 0.0006412163376808167,
"step": 9800
},
{
"epoch": 1.0104636848584325,
"grad_norm": 0.009799239225685596,
"learning_rate": 1.0996238458908014e-05,
"loss": 0.0004977862536907196,
"step": 9850
},
{
"epoch": 1.0155929421419778,
"grad_norm": 0.022461585700511932,
"learning_rate": 1.093924541205973e-05,
"loss": 0.0010745452344417571,
"step": 9900
},
{
"epoch": 1.0207221994255231,
"grad_norm": 0.07712484151124954,
"learning_rate": 1.0882252365211445e-05,
"loss": 0.0010736149549484253,
"step": 9950
},
{
"epoch": 1.0258514567090686,
"grad_norm": 0.5892838835716248,
"learning_rate": 1.0825259318363162e-05,
"loss": 0.0008927598595619201,
"step": 10000
},
{
"epoch": 1.030980713992614,
"grad_norm": 0.017941532656550407,
"learning_rate": 1.0768266271514875e-05,
"loss": 0.0012636129558086396,
"step": 10050
},
{
"epoch": 1.0361099712761592,
"grad_norm": 0.01072506420314312,
"learning_rate": 1.0711273224666592e-05,
"loss": 0.0007530584931373596,
"step": 10100
},
{
"epoch": 1.0412392285597045,
"grad_norm": 0.0135742062702775,
"learning_rate": 1.0654280177818309e-05,
"loss": 0.0008298644423484803,
"step": 10150
},
{
"epoch": 1.0463684858432498,
"grad_norm": 0.004919547121971846,
"learning_rate": 1.0597287130970022e-05,
"loss": 0.0006191575527191162,
"step": 10200
},
{
"epoch": 1.0514977431267953,
"grad_norm": 0.006896316539496183,
"learning_rate": 1.0540294084121739e-05,
"loss": 0.0005970624089241028,
"step": 10250
},
{
"epoch": 1.0566270004103406,
"grad_norm": 0.017362670972943306,
"learning_rate": 1.0483301037273454e-05,
"loss": 0.0010388505458831787,
"step": 10300
},
{
"epoch": 1.061756257693886,
"grad_norm": 0.009948116727173328,
"learning_rate": 1.0426307990425169e-05,
"loss": 0.002600117623806,
"step": 10350
},
{
"epoch": 1.0668855149774312,
"grad_norm": 0.13733653724193573,
"learning_rate": 1.0369314943576884e-05,
"loss": 0.0006903569400310516,
"step": 10400
},
{
"epoch": 1.0720147722609765,
"grad_norm": 0.021996526047587395,
"learning_rate": 1.0312321896728601e-05,
"loss": 0.0006774544715881347,
"step": 10450
},
{
"epoch": 1.077144029544522,
"grad_norm": 0.019396133720874786,
"learning_rate": 1.0255328849880314e-05,
"loss": 0.001027439534664154,
"step": 10500
},
{
"epoch": 1.0822732868280673,
"grad_norm": 0.051219504326581955,
"learning_rate": 1.0198335803032031e-05,
"loss": 0.0016321080923080444,
"step": 10550
},
{
"epoch": 1.0874025441116126,
"grad_norm": 0.042537640780210495,
"learning_rate": 1.0141342756183748e-05,
"loss": 0.001430421769618988,
"step": 10600
},
{
"epoch": 1.092531801395158,
"grad_norm": 0.007988890632987022,
"learning_rate": 1.0084349709335461e-05,
"loss": 0.0007320943474769592,
"step": 10650
},
{
"epoch": 1.0976610586787032,
"grad_norm": 0.04716062545776367,
"learning_rate": 1.0027356662487178e-05,
"loss": 0.0006467428803443909,
"step": 10700
},
{
"epoch": 1.1027903159622487,
"grad_norm": 0.04211856424808502,
"learning_rate": 9.970363615638893e-06,
"loss": 0.0020744732022285463,
"step": 10750
},
{
"epoch": 1.107919573245794,
"grad_norm": 0.022933784872293472,
"learning_rate": 9.913370568790608e-06,
"loss": 0.002727853357791901,
"step": 10800
},
{
"epoch": 1.1130488305293393,
"grad_norm": 0.056059807538986206,
"learning_rate": 9.856377521942324e-06,
"loss": 0.0006137263774871827,
"step": 10850
},
{
"epoch": 1.1181780878128846,
"grad_norm": 0.010968386195600033,
"learning_rate": 9.799384475094039e-06,
"loss": 0.0006363588571548462,
"step": 10900
},
{
"epoch": 1.1233073450964302,
"grad_norm": 0.41986656188964844,
"learning_rate": 9.742391428245754e-06,
"loss": 0.0012197810411453246,
"step": 10950
},
{
"epoch": 1.1284366023799755,
"grad_norm": 0.03437654301524162,
"learning_rate": 9.68539838139747e-06,
"loss": 0.0016349181532859802,
"step": 11000
},
{
"epoch": 1.1335658596635207,
"grad_norm": 0.04348124563694,
"learning_rate": 9.628405334549186e-06,
"loss": 0.001471232771873474,
"step": 11050
},
{
"epoch": 1.138695116947066,
"grad_norm": 0.03468090295791626,
"learning_rate": 9.571412287700901e-06,
"loss": 0.0025710177421569822,
"step": 11100
},
{
"epoch": 1.1438243742306113,
"grad_norm": 0.007106569595634937,
"learning_rate": 9.514419240852618e-06,
"loss": 0.0008309808373451233,
"step": 11150
},
{
"epoch": 1.1489536315141566,
"grad_norm": 0.040379106998443604,
"learning_rate": 9.457426194004333e-06,
"loss": 0.0007265037298202514,
"step": 11200
},
{
"epoch": 1.1540828887977022,
"grad_norm": 0.07387026399374008,
"learning_rate": 9.400433147156048e-06,
"loss": 0.0007269151508808136,
"step": 11250
},
{
"epoch": 1.1592121460812475,
"grad_norm": 0.006104862317442894,
"learning_rate": 9.343440100307763e-06,
"loss": 0.0012055251002311706,
"step": 11300
},
{
"epoch": 1.1643414033647927,
"grad_norm": 0.026950648054480553,
"learning_rate": 9.286447053459478e-06,
"loss": 0.001047862470149994,
"step": 11350
},
{
"epoch": 1.169470660648338,
"grad_norm": 0.19440318644046783,
"learning_rate": 9.229454006611193e-06,
"loss": 0.0005311770737171173,
"step": 11400
},
{
"epoch": 1.1745999179318836,
"grad_norm": 0.06631787121295929,
"learning_rate": 9.17246095976291e-06,
"loss": 0.0007610043883323669,
"step": 11450
},
{
"epoch": 1.1797291752154289,
"grad_norm": 0.027273444458842278,
"learning_rate": 9.115467912914625e-06,
"loss": 0.000621786117553711,
"step": 11500
},
{
"epoch": 1.1848584324989742,
"grad_norm": 0.0168417040258646,
"learning_rate": 9.05847486606634e-06,
"loss": 0.0005212992429733277,
"step": 11550
},
{
"epoch": 1.1899876897825195,
"grad_norm": 0.12111318111419678,
"learning_rate": 9.001481819218057e-06,
"loss": 0.0016236424446105957,
"step": 11600
},
{
"epoch": 1.1951169470660647,
"grad_norm": 0.01940443180501461,
"learning_rate": 8.944488772369772e-06,
"loss": 0.0008924838900566101,
"step": 11650
},
{
"epoch": 1.2002462043496103,
"grad_norm": 0.009674574248492718,
"learning_rate": 8.887495725521487e-06,
"loss": 0.0011235535144805907,
"step": 11700
},
{
"epoch": 1.2053754616331556,
"grad_norm": 0.005509492009878159,
"learning_rate": 8.830502678673202e-06,
"loss": 0.0006038323044776917,
"step": 11750
},
{
"epoch": 1.2105047189167009,
"grad_norm": 0.23156745731830597,
"learning_rate": 8.773509631824918e-06,
"loss": 0.0013854414224624633,
"step": 11800
},
{
"epoch": 1.2156339762002462,
"grad_norm": 0.10829994827508926,
"learning_rate": 8.716516584976633e-06,
"loss": 0.000596238374710083,
"step": 11850
},
{
"epoch": 1.2207632334837915,
"grad_norm": 0.004275528248399496,
"learning_rate": 8.65952353812835e-06,
"loss": 0.0006009680032730102,
"step": 11900
},
{
"epoch": 1.225892490767337,
"grad_norm": 0.009944693185389042,
"learning_rate": 8.602530491280065e-06,
"loss": 0.0014707162976264954,
"step": 11950
},
{
"epoch": 1.2310217480508823,
"grad_norm": 0.013600296340882778,
"learning_rate": 8.54553744443178e-06,
"loss": 0.0005389291048049926,
"step": 12000
},
{
"epoch": 1.2361510053344276,
"grad_norm": 0.0223905798047781,
"learning_rate": 8.488544397583497e-06,
"loss": 0.003673248589038849,
"step": 12050
},
{
"epoch": 1.2412802626179729,
"grad_norm": 0.012790598906576633,
"learning_rate": 8.431551350735212e-06,
"loss": 0.000642637312412262,
"step": 12100
},
{
"epoch": 1.2464095199015182,
"grad_norm": 0.007352329324930906,
"learning_rate": 8.374558303886927e-06,
"loss": 0.0004784885048866272,
"step": 12150
},
{
"epoch": 1.2515387771850637,
"grad_norm": 0.44836658239364624,
"learning_rate": 8.317565257038642e-06,
"loss": 0.0007071253657341003,
"step": 12200
},
{
"epoch": 1.256668034468609,
"grad_norm": 0.06353507936000824,
"learning_rate": 8.260572210190357e-06,
"loss": 0.0015534579753875733,
"step": 12250
},
{
"epoch": 1.2617972917521543,
"grad_norm": 0.07285618782043457,
"learning_rate": 8.203579163342072e-06,
"loss": 0.0005829083919525146,
"step": 12300
},
{
"epoch": 1.2669265490356996,
"grad_norm": 0.004738403484225273,
"learning_rate": 8.146586116493789e-06,
"loss": 0.0015484358370304108,
"step": 12350
},
{
"epoch": 1.272055806319245,
"grad_norm": 0.01686130091547966,
"learning_rate": 8.089593069645504e-06,
"loss": 0.0004922723770141601,
"step": 12400
},
{
"epoch": 1.2771850636027904,
"grad_norm": 0.017023002728819847,
"learning_rate": 8.03260002279722e-06,
"loss": 0.000672076940536499,
"step": 12450
},
{
"epoch": 1.2823143208863357,
"grad_norm": 0.011692719534039497,
"learning_rate": 7.975606975948936e-06,
"loss": 0.0006229496002197266,
"step": 12500
},
{
"epoch": 1.287443578169881,
"grad_norm": 0.009096607565879822,
"learning_rate": 7.918613929100651e-06,
"loss": 0.0009301286935806274,
"step": 12550
},
{
"epoch": 1.2925728354534263,
"grad_norm": 0.055945273488759995,
"learning_rate": 7.861620882252366e-06,
"loss": 0.0004671996831893921,
"step": 12600
},
{
"epoch": 1.2977020927369716,
"grad_norm": 0.01874576508998871,
"learning_rate": 7.804627835404081e-06,
"loss": 0.00038488924503326415,
"step": 12650
},
{
"epoch": 1.302831350020517,
"grad_norm": 0.02037273906171322,
"learning_rate": 7.747634788555796e-06,
"loss": 0.001074599027633667,
"step": 12700
},
{
"epoch": 1.3079606073040624,
"grad_norm": 0.028113173320889473,
"learning_rate": 7.690641741707512e-06,
"loss": 0.0006131212413311005,
"step": 12750
},
{
"epoch": 1.3130898645876077,
"grad_norm": 0.007892386987805367,
"learning_rate": 7.633648694859228e-06,
"loss": 0.000581781268119812,
"step": 12800
},
{
"epoch": 1.318219121871153,
"grad_norm": 0.04557061940431595,
"learning_rate": 7.5766556480109435e-06,
"loss": 0.0005579075217247009,
"step": 12850
},
{
"epoch": 1.3233483791546985,
"grad_norm": 0.004758005030453205,
"learning_rate": 7.519662601162659e-06,
"loss": 0.00044855713844299316,
"step": 12900
},
{
"epoch": 1.3284776364382438,
"grad_norm": 0.053557779639959335,
"learning_rate": 7.462669554314375e-06,
"loss": 0.0014822837710380555,
"step": 12950
},
{
"epoch": 1.333606893721789,
"grad_norm": 0.013253672979772091,
"learning_rate": 7.40567650746609e-06,
"loss": 0.0013494199514389037,
"step": 13000
},
{
"epoch": 1.3387361510053344,
"grad_norm": 0.007712292950600386,
"learning_rate": 7.348683460617805e-06,
"loss": 0.0008460769057273865,
"step": 13050
},
{
"epoch": 1.3438654082888797,
"grad_norm": 0.028559701517224312,
"learning_rate": 7.291690413769521e-06,
"loss": 0.0009650763869285584,
"step": 13100
},
{
"epoch": 1.348994665572425,
"grad_norm": 0.03476807847619057,
"learning_rate": 7.234697366921236e-06,
"loss": 0.0006557583808898925,
"step": 13150
},
{
"epoch": 1.3541239228559705,
"grad_norm": 0.03715438395738602,
"learning_rate": 7.177704320072951e-06,
"loss": 0.001336461305618286,
"step": 13200
},
{
"epoch": 1.3592531801395158,
"grad_norm": 0.006591553334146738,
"learning_rate": 7.120711273224668e-06,
"loss": 0.0005404025316238404,
"step": 13250
},
{
"epoch": 1.364382437423061,
"grad_norm": 0.013354040682315826,
"learning_rate": 7.063718226376383e-06,
"loss": 0.0016759490966796874,
"step": 13300
},
{
"epoch": 1.3695116947066066,
"grad_norm": 0.004464422352612019,
"learning_rate": 7.006725179528098e-06,
"loss": 0.0020402561128139494,
"step": 13350
},
{
"epoch": 1.374640951990152,
"grad_norm": 0.0071783666498959064,
"learning_rate": 6.949732132679814e-06,
"loss": 0.00044939160346984863,
"step": 13400
},
{
"epoch": 1.3797702092736972,
"grad_norm": 0.04091225564479828,
"learning_rate": 6.892739085831529e-06,
"loss": 0.00044884562492370606,
"step": 13450
},
{
"epoch": 1.3848994665572425,
"grad_norm": 0.008949765004217625,
"learning_rate": 6.835746038983244e-06,
"loss": 0.0009319144487380982,
"step": 13500
},
{
"epoch": 1.3900287238407878,
"grad_norm": 0.016390034928917885,
"learning_rate": 6.77875299213496e-06,
"loss": 0.0004179143905639648,
"step": 13550
},
{
"epoch": 1.395157981124333,
"grad_norm": 0.044730667024850845,
"learning_rate": 6.721759945286675e-06,
"loss": 0.0008553892374038696,
"step": 13600
},
{
"epoch": 1.4002872384078786,
"grad_norm": 0.03032684326171875,
"learning_rate": 6.6647668984383905e-06,
"loss": 0.00040693581104278564,
"step": 13650
},
{
"epoch": 1.405416495691424,
"grad_norm": 0.00720440037548542,
"learning_rate": 6.6077738515901064e-06,
"loss": 0.0007417532801628113,
"step": 13700
},
{
"epoch": 1.4105457529749692,
"grad_norm": 0.043598294258117676,
"learning_rate": 6.5507808047418216e-06,
"loss": 0.001252269446849823,
"step": 13750
},
{
"epoch": 1.4156750102585145,
"grad_norm": 0.2630448043346405,
"learning_rate": 6.493787757893537e-06,
"loss": 0.0006510725617408752,
"step": 13800
},
{
"epoch": 1.42080426754206,
"grad_norm": 0.12175612151622772,
"learning_rate": 6.4367947110452535e-06,
"loss": 0.0009742790460586548,
"step": 13850
},
{
"epoch": 1.4259335248256053,
"grad_norm": 0.008543884381651878,
"learning_rate": 6.379801664196969e-06,
"loss": 0.0010201582312583924,
"step": 13900
},
{
"epoch": 1.4310627821091506,
"grad_norm": 0.011405929923057556,
"learning_rate": 6.322808617348684e-06,
"loss": 0.0008232490718364715,
"step": 13950
},
{
"epoch": 1.436192039392696,
"grad_norm": 0.006674911826848984,
"learning_rate": 6.2658155705004e-06,
"loss": 0.0009403946995735168,
"step": 14000
},
{
"epoch": 1.4413212966762412,
"grad_norm": 0.02636873908340931,
"learning_rate": 6.208822523652115e-06,
"loss": 0.0015288326144218445,
"step": 14050
},
{
"epoch": 1.4464505539597865,
"grad_norm": 0.010799755342304707,
"learning_rate": 6.15182947680383e-06,
"loss": 0.0008086912333965301,
"step": 14100
},
{
"epoch": 1.451579811243332,
"grad_norm": 0.00788508728146553,
"learning_rate": 6.094836429955546e-06,
"loss": 0.000679481029510498,
"step": 14150
},
{
"epoch": 1.4567090685268773,
"grad_norm": 0.1568962037563324,
"learning_rate": 6.037843383107261e-06,
"loss": 0.0006565728783607483,
"step": 14200
},
{
"epoch": 1.4618383258104226,
"grad_norm": 0.025997241958975792,
"learning_rate": 5.980850336258976e-06,
"loss": 0.0010558784008026123,
"step": 14250
},
{
"epoch": 1.4669675830939681,
"grad_norm": 0.013356027193367481,
"learning_rate": 5.923857289410693e-06,
"loss": 0.0022724229097366333,
"step": 14300
},
{
"epoch": 1.4720968403775134,
"grad_norm": 0.025233469903469086,
"learning_rate": 5.866864242562408e-06,
"loss": 0.0011099863052368164,
"step": 14350
},
{
"epoch": 1.4772260976610587,
"grad_norm": 0.00507698580622673,
"learning_rate": 5.809871195714123e-06,
"loss": 0.0004247647523880005,
"step": 14400
},
{
"epoch": 1.482355354944604,
"grad_norm": 0.005569028202444315,
"learning_rate": 5.752878148865839e-06,
"loss": 0.0008500492572784423,
"step": 14450
},
{
"epoch": 1.4874846122281493,
"grad_norm": 0.06364163011312485,
"learning_rate": 5.695885102017554e-06,
"loss": 0.0005384421348571777,
"step": 14500
},
{
"epoch": 1.4926138695116946,
"grad_norm": 0.0061021894216537476,
"learning_rate": 5.638892055169269e-06,
"loss": 0.0009390240907669067,
"step": 14550
},
{
"epoch": 1.4977431267952401,
"grad_norm": 0.06408653408288956,
"learning_rate": 5.581899008320985e-06,
"loss": 0.0003880223631858826,
"step": 14600
},
{
"epoch": 1.5028723840787854,
"grad_norm": 0.006361554842442274,
"learning_rate": 5.5249059614727005e-06,
"loss": 0.00038288965821266176,
"step": 14650
},
{
"epoch": 1.5080016413623307,
"grad_norm": 0.012359695509076118,
"learning_rate": 5.4679129146244156e-06,
"loss": 0.00042018115520477296,
"step": 14700
},
{
"epoch": 1.5131308986458762,
"grad_norm": 0.09342452883720398,
"learning_rate": 5.410919867776132e-06,
"loss": 0.0010700696706771851,
"step": 14750
},
{
"epoch": 1.5182601559294215,
"grad_norm": 0.011165376752614975,
"learning_rate": 5.3539268209278475e-06,
"loss": 0.002023402750492096,
"step": 14800
},
{
"epoch": 1.5233894132129668,
"grad_norm": 0.04357055202126503,
"learning_rate": 5.296933774079563e-06,
"loss": 0.0007374601066112518,
"step": 14850
},
{
"epoch": 1.5285186704965121,
"grad_norm": 0.004575764294713736,
"learning_rate": 5.239940727231279e-06,
"loss": 0.0004954004287719727,
"step": 14900
},
{
"epoch": 1.5336479277800574,
"grad_norm": 0.01638239435851574,
"learning_rate": 5.182947680382994e-06,
"loss": 0.0004453620314598084,
"step": 14950
},
{
"epoch": 1.5387771850636027,
"grad_norm": 0.020702429115772247,
"learning_rate": 5.125954633534709e-06,
"loss": 0.0004130262136459351,
"step": 15000
},
{
"epoch": 1.543906442347148,
"grad_norm": 0.036988165229558945,
"learning_rate": 5.068961586686425e-06,
"loss": 0.0008672660589218139,
"step": 15050
},
{
"epoch": 1.5490356996306933,
"grad_norm": 0.006969288922846317,
"learning_rate": 5.01196853983814e-06,
"loss": 0.0005355362594127656,
"step": 15100
},
{
"epoch": 1.5541649569142388,
"grad_norm": 0.0261154156178236,
"learning_rate": 4.954975492989856e-06,
"loss": 0.0006160007417201996,
"step": 15150
},
{
"epoch": 1.5592942141977841,
"grad_norm": 0.003943952731788158,
"learning_rate": 4.897982446141571e-06,
"loss": 0.0008477187156677246,
"step": 15200
},
{
"epoch": 1.5644234714813297,
"grad_norm": 0.01097947172820568,
"learning_rate": 4.840989399293287e-06,
"loss": 0.000611473023891449,
"step": 15250
},
{
"epoch": 1.569552728764875,
"grad_norm": 0.2929246425628662,
"learning_rate": 4.783996352445002e-06,
"loss": 0.0022622349858283995,
"step": 15300
},
{
"epoch": 1.5746819860484202,
"grad_norm": 0.020579788833856583,
"learning_rate": 4.727003305596717e-06,
"loss": 0.000628172755241394,
"step": 15350
},
{
"epoch": 1.5798112433319655,
"grad_norm": 0.04158257693052292,
"learning_rate": 4.670010258748433e-06,
"loss": 0.0005809402465820312,
"step": 15400
},
{
"epoch": 1.5849405006155108,
"grad_norm": 0.030321037396788597,
"learning_rate": 4.613017211900149e-06,
"loss": 0.0012504719197750092,
"step": 15450
},
{
"epoch": 1.5900697578990561,
"grad_norm": 0.003760402789339423,
"learning_rate": 4.556024165051864e-06,
"loss": 0.0005912356078624726,
"step": 15500
},
{
"epoch": 1.5951990151826014,
"grad_norm": 0.007559386547654867,
"learning_rate": 4.499031118203579e-06,
"loss": 0.00040479302406311036,
"step": 15550
},
{
"epoch": 1.600328272466147,
"grad_norm": 0.03453294560313225,
"learning_rate": 4.442038071355295e-06,
"loss": 0.0020462825894355776,
"step": 15600
},
{
"epoch": 1.6054575297496922,
"grad_norm": 0.020316729322075844,
"learning_rate": 4.38504502450701e-06,
"loss": 0.0016433340311050415,
"step": 15650
},
{
"epoch": 1.6105867870332375,
"grad_norm": 0.01812104694545269,
"learning_rate": 4.328051977658726e-06,
"loss": 0.0004745867848396301,
"step": 15700
},
{
"epoch": 1.615716044316783,
"grad_norm": 0.018005484715104103,
"learning_rate": 4.2710589308104415e-06,
"loss": 0.0004400739073753357,
"step": 15750
},
{
"epoch": 1.6208453016003284,
"grad_norm": 0.1476868987083435,
"learning_rate": 4.214065883962157e-06,
"loss": 0.0010610869526863098,
"step": 15800
},
{
"epoch": 1.6259745588838737,
"grad_norm": 0.2994936406612396,
"learning_rate": 4.157072837113873e-06,
"loss": 0.001360025405883789,
"step": 15850
},
{
"epoch": 1.631103816167419,
"grad_norm": 0.002983258804306388,
"learning_rate": 4.100079790265588e-06,
"loss": 0.0005485677719116211,
"step": 15900
},
{
"epoch": 1.6362330734509642,
"grad_norm": 0.005654474720358849,
"learning_rate": 4.043086743417303e-06,
"loss": 0.001110573410987854,
"step": 15950
},
{
"epoch": 1.6413623307345095,
"grad_norm": 0.019883785396814346,
"learning_rate": 3.986093696569019e-06,
"loss": 0.0007011586427688599,
"step": 16000
},
{
"epoch": 1.6464915880180548,
"grad_norm": 0.04697249457240105,
"learning_rate": 3.929100649720735e-06,
"loss": 0.0005320942401885986,
"step": 16050
},
{
"epoch": 1.6516208453016004,
"grad_norm": 0.004929785616695881,
"learning_rate": 3.87210760287245e-06,
"loss": 0.0008407318592071533,
"step": 16100
},
{
"epoch": 1.6567501025851457,
"grad_norm": 0.03038635477423668,
"learning_rate": 3.815114556024165e-06,
"loss": 0.00030867159366607664,
"step": 16150
},
{
"epoch": 1.6618793598686912,
"grad_norm": 0.06552842259407043,
"learning_rate": 3.758121509175881e-06,
"loss": 0.0011920902132987977,
"step": 16200
},
{
"epoch": 1.6670086171522365,
"grad_norm": 0.013011803850531578,
"learning_rate": 3.701128462327596e-06,
"loss": 0.000447293221950531,
"step": 16250
},
{
"epoch": 1.6721378744357818,
"grad_norm": 0.00991652812808752,
"learning_rate": 3.644135415479312e-06,
"loss": 0.00033876419067382815,
"step": 16300
},
{
"epoch": 1.677267131719327,
"grad_norm": 0.025500046089291573,
"learning_rate": 3.5871423686310276e-06,
"loss": 0.0002862626314163208,
"step": 16350
},
{
"epoch": 1.6823963890028724,
"grad_norm": 0.054780106991529465,
"learning_rate": 3.5301493217827427e-06,
"loss": 0.0022387760877609253,
"step": 16400
},
{
"epoch": 1.6875256462864177,
"grad_norm": 0.009139726869761944,
"learning_rate": 3.4731562749344582e-06,
"loss": 0.0004343575239181519,
"step": 16450
},
{
"epoch": 1.692654903569963,
"grad_norm": 0.005948680453002453,
"learning_rate": 3.4161632280861738e-06,
"loss": 0.000540688931941986,
"step": 16500
},
{
"epoch": 1.6977841608535083,
"grad_norm": 0.028869858011603355,
"learning_rate": 3.359170181237889e-06,
"loss": 0.00035138726234436036,
"step": 16550
},
{
"epoch": 1.7029134181370538,
"grad_norm": 0.0448104664683342,
"learning_rate": 3.302177134389605e-06,
"loss": 0.0005932286381721497,
"step": 16600
},
{
"epoch": 1.708042675420599,
"grad_norm": 0.09236075729131699,
"learning_rate": 3.2451840875413204e-06,
"loss": 0.0006601068377494812,
"step": 16650
},
{
"epoch": 1.7131719327041446,
"grad_norm": 0.014860023744404316,
"learning_rate": 3.1881910406930355e-06,
"loss": 0.0008951804041862488,
"step": 16700
},
{
"epoch": 1.7183011899876899,
"grad_norm": 0.019764918833971024,
"learning_rate": 3.131197993844751e-06,
"loss": 0.00040823638439178465,
"step": 16750
},
{
"epoch": 1.7234304472712352,
"grad_norm": 0.008326166309416294,
"learning_rate": 3.074204946996467e-06,
"loss": 0.001432819664478302,
"step": 16800
},
{
"epoch": 1.7285597045547805,
"grad_norm": 0.0029986989684402943,
"learning_rate": 3.017211900148182e-06,
"loss": 0.0012194857001304627,
"step": 16850
},
{
"epoch": 1.7336889618383258,
"grad_norm": 0.09672784060239792,
"learning_rate": 2.9602188532998977e-06,
"loss": 0.00047722727060317994,
"step": 16900
},
{
"epoch": 1.738818219121871,
"grad_norm": 0.0037852392997592688,
"learning_rate": 2.903225806451613e-06,
"loss": 0.0008305265009403229,
"step": 16950
},
{
"epoch": 1.7439474764054164,
"grad_norm": 0.36351898312568665,
"learning_rate": 2.8462327596033283e-06,
"loss": 0.0005665953457355499,
"step": 17000
},
{
"epoch": 1.7490767336889619,
"grad_norm": 0.006676111835986376,
"learning_rate": 2.7892397127550443e-06,
"loss": 0.0007315759360790253,
"step": 17050
},
{
"epoch": 1.7542059909725072,
"grad_norm": 0.07323434203863144,
"learning_rate": 2.73224666590676e-06,
"loss": 0.00037639960646629333,
"step": 17100
},
{
"epoch": 1.7593352482560525,
"grad_norm": 0.013121088966727257,
"learning_rate": 2.675253619058475e-06,
"loss": 0.0011937808990478515,
"step": 17150
},
{
"epoch": 1.764464505539598,
"grad_norm": 0.03192434832453728,
"learning_rate": 2.6182605722101905e-06,
"loss": 0.0013308241963386537,
"step": 17200
},
{
"epoch": 1.7695937628231433,
"grad_norm": 0.014523284509778023,
"learning_rate": 2.5612675253619065e-06,
"loss": 0.0010080689191818237,
"step": 17250
},
{
"epoch": 1.7747230201066886,
"grad_norm": 0.003345728386193514,
"learning_rate": 2.5042744785136216e-06,
"loss": 0.0009157347679138183,
"step": 17300
},
{
"epoch": 1.7798522773902339,
"grad_norm": 0.011479219421744347,
"learning_rate": 2.447281431665337e-06,
"loss": 0.00039456844329833986,
"step": 17350
},
{
"epoch": 1.7849815346737792,
"grad_norm": 0.00539002101868391,
"learning_rate": 2.3902883848170527e-06,
"loss": 0.0003252148628234863,
"step": 17400
},
{
"epoch": 1.7901107919573245,
"grad_norm": 0.0179832074791193,
"learning_rate": 2.333295337968768e-06,
"loss": 0.0006710499525070191,
"step": 17450
},
{
"epoch": 1.7952400492408698,
"grad_norm": 0.019012339413166046,
"learning_rate": 2.2763022911204833e-06,
"loss": 0.0003579908609390259,
"step": 17500
},
{
"epoch": 1.8003693065244153,
"grad_norm": 0.021011650562286377,
"learning_rate": 2.219309244272199e-06,
"loss": 0.0003782680630683899,
"step": 17550
},
{
"epoch": 1.8054985638079606,
"grad_norm": 0.008447716012597084,
"learning_rate": 2.1623161974239144e-06,
"loss": 0.0005027109384536743,
"step": 17600
},
{
"epoch": 1.810627821091506,
"grad_norm": 0.07184159755706787,
"learning_rate": 2.10532315057563e-06,
"loss": 0.00039920926094055175,
"step": 17650
},
{
"epoch": 1.8157570783750514,
"grad_norm": 0.009770162403583527,
"learning_rate": 2.0483301037273455e-06,
"loss": 0.0002949029207229614,
"step": 17700
},
{
"epoch": 1.8208863356585967,
"grad_norm": 0.02992192842066288,
"learning_rate": 1.991337056879061e-06,
"loss": 0.0003519010543823242,
"step": 17750
},
{
"epoch": 1.826015592942142,
"grad_norm": 0.007283203303813934,
"learning_rate": 1.9343440100307766e-06,
"loss": 0.001447817087173462,
"step": 17800
},
{
"epoch": 1.8311448502256873,
"grad_norm": 0.0020318494644016027,
"learning_rate": 1.8773509631824919e-06,
"loss": 0.0003602537512779236,
"step": 17850
},
{
"epoch": 1.8362741075092326,
"grad_norm": 0.008025232702493668,
"learning_rate": 1.8203579163342074e-06,
"loss": 0.0007793241739273071,
"step": 17900
},
{
"epoch": 1.8414033647927779,
"grad_norm": 0.024956921115517616,
"learning_rate": 1.763364869485923e-06,
"loss": 0.00035044103860855104,
"step": 17950
},
{
"epoch": 1.8465326220763232,
"grad_norm": 0.005003917030990124,
"learning_rate": 1.7063718226376383e-06,
"loss": 0.000377134382724762,
"step": 18000
},
{
"epoch": 1.8516618793598687,
"grad_norm": 0.006638799328356981,
"learning_rate": 1.649378775789354e-06,
"loss": 0.0006813791394233704,
"step": 18050
},
{
"epoch": 1.856791136643414,
"grad_norm": 0.023331264033913612,
"learning_rate": 1.5923857289410694e-06,
"loss": 0.0003337270021438599,
"step": 18100
},
{
"epoch": 1.8619203939269595,
"grad_norm": 0.01474565640091896,
"learning_rate": 1.5353926820927847e-06,
"loss": 0.0003927820920944214,
"step": 18150
},
{
"epoch": 1.8670496512105048,
"grad_norm": 0.004943469073623419,
"learning_rate": 1.4783996352445005e-06,
"loss": 0.0019324821233749389,
"step": 18200
},
{
"epoch": 1.87217890849405,
"grad_norm": 0.006063356995582581,
"learning_rate": 1.4214065883962158e-06,
"loss": 0.0004604470729827881,
"step": 18250
},
{
"epoch": 1.8773081657775954,
"grad_norm": 0.00663331663236022,
"learning_rate": 1.3644135415479311e-06,
"loss": 0.0006617265939712525,
"step": 18300
},
{
"epoch": 1.8824374230611407,
"grad_norm": 0.006572545040398836,
"learning_rate": 1.3074204946996469e-06,
"loss": 0.00035414040088653563,
"step": 18350
},
{
"epoch": 1.887566680344686,
"grad_norm": 0.03555886074900627,
"learning_rate": 1.2504274478513622e-06,
"loss": 0.0013728688657283783,
"step": 18400
},
{
"epoch": 1.8926959376282313,
"grad_norm": 0.00993818137794733,
"learning_rate": 1.1934344010030777e-06,
"loss": 0.0005572491884231567,
"step": 18450
},
{
"epoch": 1.8978251949117768,
"grad_norm": 0.04966617748141289,
"learning_rate": 1.1364413541547933e-06,
"loss": 0.0003973785042762756,
"step": 18500
},
{
"epoch": 1.902954452195322,
"grad_norm": 0.0040567717514932156,
"learning_rate": 1.0794483073065088e-06,
"loss": 0.00035895496606826784,
"step": 18550
},
{
"epoch": 1.9080837094788674,
"grad_norm": 0.007941263727843761,
"learning_rate": 1.0224552604582241e-06,
"loss": 0.00032996714115142824,
"step": 18600
},
{
"epoch": 1.913212966762413,
"grad_norm": 0.04344106465578079,
"learning_rate": 9.654622136099397e-07,
"loss": 0.0006199817359447479,
"step": 18650
},
{
"epoch": 1.9183422240459582,
"grad_norm": 0.0051651448011398315,
"learning_rate": 9.084691667616552e-07,
"loss": 0.0008288529515266418,
"step": 18700
},
{
"epoch": 1.9234714813295035,
"grad_norm": 0.007254309486597776,
"learning_rate": 8.514761199133706e-07,
"loss": 0.00048538297414779663,
"step": 18750
},
{
"epoch": 1.9286007386130488,
"grad_norm": 0.09651651978492737,
"learning_rate": 7.944830730650861e-07,
"loss": 0.00031837493181228636,
"step": 18800
},
{
"epoch": 1.9337299958965941,
"grad_norm": 0.0036208152305334806,
"learning_rate": 7.374900262168016e-07,
"loss": 0.0003172314167022705,
"step": 18850
},
{
"epoch": 1.9388592531801394,
"grad_norm": 0.010356809943914413,
"learning_rate": 6.804969793685171e-07,
"loss": 0.000322052538394928,
"step": 18900
},
{
"epoch": 1.9439885104636847,
"grad_norm": 0.008326847106218338,
"learning_rate": 6.235039325202326e-07,
"loss": 0.0007110384106636048,
"step": 18950
},
{
"epoch": 1.9491177677472302,
"grad_norm": 0.02525205910205841,
"learning_rate": 5.66510885671948e-07,
"loss": 0.0003109830617904663,
"step": 19000
},
{
"epoch": 1.9542470250307755,
"grad_norm": 0.01355426199734211,
"learning_rate": 5.095178388236636e-07,
"loss": 0.0008139577507972717,
"step": 19050
},
{
"epoch": 1.959376282314321,
"grad_norm": 0.008329730480909348,
"learning_rate": 4.52524791975379e-07,
"loss": 0.0007415449619293213,
"step": 19100
},
{
"epoch": 1.9645055395978663,
"grad_norm": 0.0014810786815360188,
"learning_rate": 3.955317451270945e-07,
"loss": 0.0003853049874305725,
"step": 19150
},
{
"epoch": 1.9696347968814116,
"grad_norm": 0.03657092899084091,
"learning_rate": 3.3853869827881005e-07,
"loss": 0.0003694988787174225,
"step": 19200
},
{
"epoch": 1.974764054164957,
"grad_norm": 0.0059157381765544415,
"learning_rate": 2.815456514305255e-07,
"loss": 0.0013805073499679565,
"step": 19250
},
{
"epoch": 1.9798933114485022,
"grad_norm": 0.0027979083824902773,
"learning_rate": 2.2455260458224098e-07,
"loss": 0.0008595210313796998,
"step": 19300
},
{
"epoch": 1.9850225687320475,
"grad_norm": 0.009878180921077728,
"learning_rate": 1.6755955773395646e-07,
"loss": 0.0003620834648609161,
"step": 19350
},
{
"epoch": 1.9901518260155928,
"grad_norm": 0.004368235357105732,
"learning_rate": 1.1056651088567195e-07,
"loss": 0.0012495499849319459,
"step": 19400
},
{
"epoch": 1.9952810832991383,
"grad_norm": 0.025456879287958145,
"learning_rate": 5.357346403738744e-08,
"loss": 0.0009994500875473023,
"step": 19450
},
{
"epoch": 2.0,
"eval_biencoder-val_cosine_accuracy@1": 0.929,
"eval_biencoder-val_cosine_accuracy@10": 1.0,
"eval_biencoder-val_cosine_accuracy@30": 1.0,
"eval_biencoder-val_cosine_accuracy@5": 1.0,
"eval_biencoder-val_cosine_map@100": 0.9638333333333332,
"eval_biencoder-val_cosine_mrr@10": 0.9638333333333332,
"eval_biencoder-val_cosine_ndcg@10": 0.9732722934892877,
"eval_biencoder-val_cosine_precision@1": 0.929,
"eval_biencoder-val_cosine_precision@10": 0.10000000000000002,
"eval_biencoder-val_cosine_precision@3": 0.33333333333333326,
"eval_biencoder-val_cosine_precision@5": 0.20000000000000004,
"eval_biencoder-val_cosine_recall@1": 0.929,
"eval_biencoder-val_cosine_recall@10": 1.0,
"eval_biencoder-val_cosine_recall@3": 1.0,
"eval_biencoder-val_cosine_recall@5": 1.0,
"eval_runtime": 0.9214,
"eval_samples_per_second": 0.0,
"eval_steps_per_second": 0.0,
"step": 19496
}
],
"logging_steps": 50,
"max_steps": 19496,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": null
}