Qwen2.5-7B-sft-ultrachat-safeRLHF / trainer_state.json
AmberYifan's picture
Model save
a41c7bd verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1563,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006397952655150352,
"grad_norm": 8.557194262017578,
"learning_rate": 1.2738853503184715e-07,
"loss": 2.0432,
"step": 1
},
{
"epoch": 0.003198976327575176,
"grad_norm": 7.168845650993062,
"learning_rate": 6.369426751592357e-07,
"loss": 1.9538,
"step": 5
},
{
"epoch": 0.006397952655150352,
"grad_norm": 8.065982197340965,
"learning_rate": 1.2738853503184715e-06,
"loss": 2.0349,
"step": 10
},
{
"epoch": 0.009596928982725527,
"grad_norm": 6.290735834401221,
"learning_rate": 1.9108280254777074e-06,
"loss": 1.9124,
"step": 15
},
{
"epoch": 0.012795905310300703,
"grad_norm": 4.973274763596367,
"learning_rate": 2.547770700636943e-06,
"loss": 1.9049,
"step": 20
},
{
"epoch": 0.01599488163787588,
"grad_norm": 5.176905055023329,
"learning_rate": 3.1847133757961785e-06,
"loss": 1.8208,
"step": 25
},
{
"epoch": 0.019193857965451054,
"grad_norm": 6.309236772398139,
"learning_rate": 3.821656050955415e-06,
"loss": 1.8131,
"step": 30
},
{
"epoch": 0.022392834293026232,
"grad_norm": 4.199864900523197,
"learning_rate": 4.45859872611465e-06,
"loss": 1.7264,
"step": 35
},
{
"epoch": 0.025591810620601407,
"grad_norm": 5.022105406412313,
"learning_rate": 5.095541401273886e-06,
"loss": 1.7085,
"step": 40
},
{
"epoch": 0.028790786948176585,
"grad_norm": 4.5174043424103685,
"learning_rate": 5.732484076433121e-06,
"loss": 1.6624,
"step": 45
},
{
"epoch": 0.03198976327575176,
"grad_norm": 4.3300145496731215,
"learning_rate": 6.369426751592357e-06,
"loss": 1.6825,
"step": 50
},
{
"epoch": 0.035188739603326934,
"grad_norm": 3.794347041073854,
"learning_rate": 7.006369426751593e-06,
"loss": 1.6846,
"step": 55
},
{
"epoch": 0.03838771593090211,
"grad_norm": 3.802484854288831,
"learning_rate": 7.64331210191083e-06,
"loss": 1.6738,
"step": 60
},
{
"epoch": 0.04158669225847729,
"grad_norm": 3.7790548942544664,
"learning_rate": 8.280254777070064e-06,
"loss": 1.6897,
"step": 65
},
{
"epoch": 0.044785668586052464,
"grad_norm": 3.8318913612512127,
"learning_rate": 8.9171974522293e-06,
"loss": 1.6498,
"step": 70
},
{
"epoch": 0.04798464491362764,
"grad_norm": 4.486141166866438,
"learning_rate": 9.554140127388536e-06,
"loss": 1.6251,
"step": 75
},
{
"epoch": 0.05118362124120281,
"grad_norm": 3.7966646356196634,
"learning_rate": 1.0191082802547772e-05,
"loss": 1.6787,
"step": 80
},
{
"epoch": 0.05438259756877799,
"grad_norm": 4.015240064460886,
"learning_rate": 1.0828025477707008e-05,
"loss": 1.6373,
"step": 85
},
{
"epoch": 0.05758157389635317,
"grad_norm": 3.9271843790429717,
"learning_rate": 1.1464968152866242e-05,
"loss": 1.6241,
"step": 90
},
{
"epoch": 0.060780550223928344,
"grad_norm": 3.996656519840015,
"learning_rate": 1.2101910828025478e-05,
"loss": 1.6128,
"step": 95
},
{
"epoch": 0.06397952655150352,
"grad_norm": 4.254476942836661,
"learning_rate": 1.2738853503184714e-05,
"loss": 1.632,
"step": 100
},
{
"epoch": 0.0671785028790787,
"grad_norm": 3.960145653465224,
"learning_rate": 1.337579617834395e-05,
"loss": 1.6325,
"step": 105
},
{
"epoch": 0.07037747920665387,
"grad_norm": 4.2530304479749965,
"learning_rate": 1.4012738853503186e-05,
"loss": 1.6208,
"step": 110
},
{
"epoch": 0.07357645553422905,
"grad_norm": 3.7537798327795477,
"learning_rate": 1.464968152866242e-05,
"loss": 1.6089,
"step": 115
},
{
"epoch": 0.07677543186180422,
"grad_norm": 3.7687659782987866,
"learning_rate": 1.528662420382166e-05,
"loss": 1.6164,
"step": 120
},
{
"epoch": 0.0799744081893794,
"grad_norm": 3.685834335118057,
"learning_rate": 1.5923566878980894e-05,
"loss": 1.6283,
"step": 125
},
{
"epoch": 0.08317338451695458,
"grad_norm": 3.697525223440911,
"learning_rate": 1.6560509554140128e-05,
"loss": 1.6206,
"step": 130
},
{
"epoch": 0.08637236084452975,
"grad_norm": 3.8268308426440565,
"learning_rate": 1.7197452229299365e-05,
"loss": 1.6333,
"step": 135
},
{
"epoch": 0.08957133717210493,
"grad_norm": 3.6563345299850463,
"learning_rate": 1.78343949044586e-05,
"loss": 1.675,
"step": 140
},
{
"epoch": 0.0927703134996801,
"grad_norm": 3.6849267294362464,
"learning_rate": 1.8471337579617837e-05,
"loss": 1.6583,
"step": 145
},
{
"epoch": 0.09596928982725528,
"grad_norm": 3.5138963267115324,
"learning_rate": 1.910828025477707e-05,
"loss": 1.6161,
"step": 150
},
{
"epoch": 0.09916826615483046,
"grad_norm": 3.5909566388072407,
"learning_rate": 1.9745222929936306e-05,
"loss": 1.6804,
"step": 155
},
{
"epoch": 0.10236724248240563,
"grad_norm": 3.599403002421182,
"learning_rate": 1.9999775332635076e-05,
"loss": 1.6134,
"step": 160
},
{
"epoch": 0.10556621880998081,
"grad_norm": 3.8176081053178996,
"learning_rate": 1.999840240196313e-05,
"loss": 1.5822,
"step": 165
},
{
"epoch": 0.10876519513755598,
"grad_norm": 3.465176818490385,
"learning_rate": 1.9995781526975738e-05,
"loss": 1.6274,
"step": 170
},
{
"epoch": 0.11196417146513116,
"grad_norm": 3.5656092209776453,
"learning_rate": 1.9991913034795768e-05,
"loss": 1.6646,
"step": 175
},
{
"epoch": 0.11516314779270634,
"grad_norm": 3.3302032083057087,
"learning_rate": 1.9986797408266636e-05,
"loss": 1.6421,
"step": 180
},
{
"epoch": 0.1183621241202815,
"grad_norm": 3.5207207882328273,
"learning_rate": 1.9980435285892056e-05,
"loss": 1.6973,
"step": 185
},
{
"epoch": 0.12156110044785669,
"grad_norm": 3.5533442251824634,
"learning_rate": 1.9972827461756335e-05,
"loss": 1.6365,
"step": 190
},
{
"epoch": 0.12476007677543186,
"grad_norm": 3.3243186303121948,
"learning_rate": 1.9963974885425267e-05,
"loss": 1.5795,
"step": 195
},
{
"epoch": 0.12795905310300704,
"grad_norm": 3.3487919633682726,
"learning_rate": 1.9953878661827603e-05,
"loss": 1.6474,
"step": 200
},
{
"epoch": 0.13115802943058222,
"grad_norm": 3.242336250993276,
"learning_rate": 1.994254005111715e-05,
"loss": 1.636,
"step": 205
},
{
"epoch": 0.1343570057581574,
"grad_norm": 3.173792458371255,
"learning_rate": 1.992996046851548e-05,
"loss": 1.616,
"step": 210
},
{
"epoch": 0.13755598208573255,
"grad_norm": 3.3299670491780646,
"learning_rate": 1.9916141484135297e-05,
"loss": 1.6634,
"step": 215
},
{
"epoch": 0.14075495841330773,
"grad_norm": 3.36368536908733,
"learning_rate": 1.990108482278446e-05,
"loss": 1.6432,
"step": 220
},
{
"epoch": 0.14395393474088292,
"grad_norm": 3.3251859465787046,
"learning_rate": 1.9884792363750684e-05,
"loss": 1.6709,
"step": 225
},
{
"epoch": 0.1471529110684581,
"grad_norm": 3.102386276571743,
"learning_rate": 1.9867266140567024e-05,
"loss": 1.6415,
"step": 230
},
{
"epoch": 0.15035188739603328,
"grad_norm": 3.3174253860977365,
"learning_rate": 1.9848508340758014e-05,
"loss": 1.6635,
"step": 235
},
{
"epoch": 0.15355086372360843,
"grad_norm": 3.312550584124557,
"learning_rate": 1.9828521305566647e-05,
"loss": 1.6573,
"step": 240
},
{
"epoch": 0.15674984005118361,
"grad_norm": 3.2267882077539722,
"learning_rate": 1.9807307529662175e-05,
"loss": 1.7259,
"step": 245
},
{
"epoch": 0.1599488163787588,
"grad_norm": 3.3340916386819472,
"learning_rate": 1.9784869660828708e-05,
"loss": 1.6317,
"step": 250
},
{
"epoch": 0.16314779270633398,
"grad_norm": 3.52528353307843,
"learning_rate": 1.9761210499634754e-05,
"loss": 1.6258,
"step": 255
},
{
"epoch": 0.16634676903390916,
"grad_norm": 3.4158604367890404,
"learning_rate": 1.973633299908365e-05,
"loss": 1.5955,
"step": 260
},
{
"epoch": 0.1695457453614843,
"grad_norm": 3.2974321567758773,
"learning_rate": 1.9710240264245005e-05,
"loss": 1.6867,
"step": 265
},
{
"epoch": 0.1727447216890595,
"grad_norm": 3.082593081376396,
"learning_rate": 1.9682935551867132e-05,
"loss": 1.611,
"step": 270
},
{
"epoch": 0.17594369801663468,
"grad_norm": 2.9246732858906754,
"learning_rate": 1.9654422269970545e-05,
"loss": 1.6379,
"step": 275
},
{
"epoch": 0.17914267434420986,
"grad_norm": 3.1477425965953034,
"learning_rate": 1.9624703977422624e-05,
"loss": 1.6206,
"step": 280
},
{
"epoch": 0.18234165067178504,
"grad_norm": 3.4756906983116487,
"learning_rate": 1.959378438349338e-05,
"loss": 1.6179,
"step": 285
},
{
"epoch": 0.1855406269993602,
"grad_norm": 3.1254114065928276,
"learning_rate": 1.956166734739251e-05,
"loss": 1.6312,
"step": 290
},
{
"epoch": 0.18873960332693537,
"grad_norm": 3.2909797328261816,
"learning_rate": 1.95283568777877e-05,
"loss": 1.636,
"step": 295
},
{
"epoch": 0.19193857965451055,
"grad_norm": 3.1693694159644332,
"learning_rate": 1.9493857132304295e-05,
"loss": 1.6035,
"step": 300
},
{
"epoch": 0.19513755598208574,
"grad_norm": 2.974139247790458,
"learning_rate": 1.9458172417006347e-05,
"loss": 1.7238,
"step": 305
},
{
"epoch": 0.19833653230966092,
"grad_norm": 3.0040579933657265,
"learning_rate": 1.942130718585919e-05,
"loss": 1.5947,
"step": 310
},
{
"epoch": 0.20153550863723607,
"grad_norm": 3.241345908595884,
"learning_rate": 1.938326604017349e-05,
"loss": 1.625,
"step": 315
},
{
"epoch": 0.20473448496481125,
"grad_norm": 3.1605704875054514,
"learning_rate": 1.9344053728030952e-05,
"loss": 1.6329,
"step": 320
},
{
"epoch": 0.20793346129238643,
"grad_norm": 3.0155271164409214,
"learning_rate": 1.9303675143691683e-05,
"loss": 1.653,
"step": 325
},
{
"epoch": 0.21113243761996162,
"grad_norm": 3.133069541053234,
"learning_rate": 1.9262135326983326e-05,
"loss": 1.6805,
"step": 330
},
{
"epoch": 0.2143314139475368,
"grad_norm": 3.19313647418372,
"learning_rate": 1.921943946267201e-05,
"loss": 1.6003,
"step": 335
},
{
"epoch": 0.21753039027511195,
"grad_norm": 3.237127118135618,
"learning_rate": 1.9175592879815217e-05,
"loss": 1.6702,
"step": 340
},
{
"epoch": 0.22072936660268713,
"grad_norm": 3.1481875415297886,
"learning_rate": 1.9130601051096655e-05,
"loss": 1.6015,
"step": 345
},
{
"epoch": 0.22392834293026231,
"grad_norm": 3.12526224068583,
"learning_rate": 1.9084469592143154e-05,
"loss": 1.6248,
"step": 350
},
{
"epoch": 0.2271273192578375,
"grad_norm": 3.106767075086588,
"learning_rate": 1.9037204260823788e-05,
"loss": 1.5752,
"step": 355
},
{
"epoch": 0.23032629558541268,
"grad_norm": 3.0437376827653413,
"learning_rate": 1.89888109565312e-05,
"loss": 1.7072,
"step": 360
},
{
"epoch": 0.23352527191298783,
"grad_norm": 2.966074158910365,
"learning_rate": 1.893929571944527e-05,
"loss": 1.6499,
"step": 365
},
{
"epoch": 0.236724248240563,
"grad_norm": 3.0622642071979627,
"learning_rate": 1.8888664729779205e-05,
"loss": 1.6566,
"step": 370
},
{
"epoch": 0.2399232245681382,
"grad_norm": 3.1519051199400936,
"learning_rate": 1.883692430700818e-05,
"loss": 1.619,
"step": 375
},
{
"epoch": 0.24312220089571338,
"grad_norm": 3.431719331199434,
"learning_rate": 1.8784080909080568e-05,
"loss": 1.6062,
"step": 380
},
{
"epoch": 0.24632117722328856,
"grad_norm": 3.1037976334582322,
"learning_rate": 1.8730141131611882e-05,
"loss": 1.6333,
"step": 385
},
{
"epoch": 0.2495201535508637,
"grad_norm": 3.268175679790816,
"learning_rate": 1.867511170706157e-05,
"loss": 1.5713,
"step": 390
},
{
"epoch": 0.2527191298784389,
"grad_norm": 2.9167898411021365,
"learning_rate": 1.861899950389269e-05,
"loss": 1.6532,
"step": 395
},
{
"epoch": 0.2559181062060141,
"grad_norm": 3.0277449312431726,
"learning_rate": 1.856181152571463e-05,
"loss": 1.5813,
"step": 400
},
{
"epoch": 0.2591170825335892,
"grad_norm": 3.2795041159269065,
"learning_rate": 1.850355491040897e-05,
"loss": 1.5863,
"step": 405
},
{
"epoch": 0.26231605886116444,
"grad_norm": 2.8691246301448414,
"learning_rate": 1.8444236929238556e-05,
"loss": 1.6227,
"step": 410
},
{
"epoch": 0.2655150351887396,
"grad_norm": 3.069643680215728,
"learning_rate": 1.8383864985939944e-05,
"loss": 1.5843,
"step": 415
},
{
"epoch": 0.2687140115163148,
"grad_norm": 3.0049575855018222,
"learning_rate": 1.8322446615799317e-05,
"loss": 1.5902,
"step": 420
},
{
"epoch": 0.27191298784388995,
"grad_norm": 2.9760192717671323,
"learning_rate": 1.825998948471197e-05,
"loss": 1.5627,
"step": 425
},
{
"epoch": 0.2751119641714651,
"grad_norm": 2.8099807180506007,
"learning_rate": 1.819650138822548e-05,
"loss": 1.618,
"step": 430
},
{
"epoch": 0.2783109404990403,
"grad_norm": 2.746446519949406,
"learning_rate": 1.8131990250566733e-05,
"loss": 1.4955,
"step": 435
},
{
"epoch": 0.28150991682661547,
"grad_norm": 2.9244825789414404,
"learning_rate": 1.8066464123652857e-05,
"loss": 1.6359,
"step": 440
},
{
"epoch": 0.2847088931541907,
"grad_norm": 2.7164843334529603,
"learning_rate": 1.7999931186086225e-05,
"loss": 1.5848,
"step": 445
},
{
"epoch": 0.28790786948176583,
"grad_norm": 2.9072519471574974,
"learning_rate": 1.793239974213364e-05,
"loss": 1.5542,
"step": 450
},
{
"epoch": 0.291106845809341,
"grad_norm": 3.168251246658964,
"learning_rate": 1.786387822068987e-05,
"loss": 1.6191,
"step": 455
},
{
"epoch": 0.2943058221369162,
"grad_norm": 3.2412066931732517,
"learning_rate": 1.7794375174225565e-05,
"loss": 1.634,
"step": 460
},
{
"epoch": 0.29750479846449135,
"grad_norm": 2.9282998892161918,
"learning_rate": 1.7723899277719815e-05,
"loss": 1.5951,
"step": 465
},
{
"epoch": 0.30070377479206656,
"grad_norm": 3.120120728893521,
"learning_rate": 1.7652459327577377e-05,
"loss": 1.5976,
"step": 470
},
{
"epoch": 0.3039027511196417,
"grad_norm": 2.8473524405665596,
"learning_rate": 1.7580064240530746e-05,
"loss": 1.5706,
"step": 475
},
{
"epoch": 0.30710172744721687,
"grad_norm": 2.9319991753167294,
"learning_rate": 1.7506723052527243e-05,
"loss": 1.5875,
"step": 480
},
{
"epoch": 0.3103007037747921,
"grad_norm": 3.077519173326514,
"learning_rate": 1.7432444917601183e-05,
"loss": 1.5981,
"step": 485
},
{
"epoch": 0.31349968010236723,
"grad_norm": 2.912507199999816,
"learning_rate": 1.735723910673132e-05,
"loss": 1.5707,
"step": 490
},
{
"epoch": 0.31669865642994244,
"grad_norm": 3.2113961395964146,
"learning_rate": 1.7281115006683687e-05,
"loss": 1.5593,
"step": 495
},
{
"epoch": 0.3198976327575176,
"grad_norm": 2.7491466611385853,
"learning_rate": 1.7204082118840035e-05,
"loss": 1.6032,
"step": 500
},
{
"epoch": 0.32309660908509275,
"grad_norm": 2.7684042016016615,
"learning_rate": 1.712615005801185e-05,
"loss": 1.6093,
"step": 505
},
{
"epoch": 0.32629558541266795,
"grad_norm": 2.915724474118878,
"learning_rate": 1.704732855124037e-05,
"loss": 1.6427,
"step": 510
},
{
"epoch": 0.3294945617402431,
"grad_norm": 2.9613347073093057,
"learning_rate": 1.6967627436582445e-05,
"loss": 1.6235,
"step": 515
},
{
"epoch": 0.3326935380678183,
"grad_norm": 3.0910817914002164,
"learning_rate": 1.6887056661882644e-05,
"loss": 1.6294,
"step": 520
},
{
"epoch": 0.33589251439539347,
"grad_norm": 3.000090940198684,
"learning_rate": 1.6805626283531592e-05,
"loss": 1.5619,
"step": 525
},
{
"epoch": 0.3390914907229686,
"grad_norm": 2.8786609439831548,
"learning_rate": 1.6723346465210815e-05,
"loss": 1.6197,
"step": 530
},
{
"epoch": 0.34229046705054383,
"grad_norm": 3.027454999439804,
"learning_rate": 1.6640227476624163e-05,
"loss": 1.6273,
"step": 535
},
{
"epoch": 0.345489443378119,
"grad_norm": 3.18224230209766,
"learning_rate": 1.655627969221598e-05,
"loss": 1.5518,
"step": 540
},
{
"epoch": 0.3486884197056942,
"grad_norm": 3.441475883060485,
"learning_rate": 1.6471513589876247e-05,
"loss": 1.5914,
"step": 545
},
{
"epoch": 0.35188739603326935,
"grad_norm": 2.779764601488237,
"learning_rate": 1.638593974963278e-05,
"loss": 1.5941,
"step": 550
},
{
"epoch": 0.3550863723608445,
"grad_norm": 2.9474461432085937,
"learning_rate": 1.6299568852330703e-05,
"loss": 1.6308,
"step": 555
},
{
"epoch": 0.3582853486884197,
"grad_norm": 2.9978355190495516,
"learning_rate": 1.6212411678299306e-05,
"loss": 1.5671,
"step": 560
},
{
"epoch": 0.36148432501599487,
"grad_norm": 2.784909890256646,
"learning_rate": 1.612447910600652e-05,
"loss": 1.5486,
"step": 565
},
{
"epoch": 0.3646833013435701,
"grad_norm": 2.8203457503842126,
"learning_rate": 1.6035782110701125e-05,
"loss": 1.5871,
"step": 570
},
{
"epoch": 0.36788227767114523,
"grad_norm": 2.648364503580562,
"learning_rate": 1.594633176304287e-05,
"loss": 1.5984,
"step": 575
},
{
"epoch": 0.3710812539987204,
"grad_norm": 3.0411727177491734,
"learning_rate": 1.5856139227720714e-05,
"loss": 1.6011,
"step": 580
},
{
"epoch": 0.3742802303262956,
"grad_norm": 2.9271779235986126,
"learning_rate": 1.5765215762059304e-05,
"loss": 1.5788,
"step": 585
},
{
"epoch": 0.37747920665387075,
"grad_norm": 3.0611368707830975,
"learning_rate": 1.5673572714613886e-05,
"loss": 1.6257,
"step": 590
},
{
"epoch": 0.38067818298144596,
"grad_norm": 2.8794709774310996,
"learning_rate": 1.558122152375387e-05,
"loss": 1.5765,
"step": 595
},
{
"epoch": 0.3838771593090211,
"grad_norm": 2.7366528786349407,
"learning_rate": 1.548817371623513e-05,
"loss": 1.538,
"step": 600
},
{
"epoch": 0.38707613563659626,
"grad_norm": 2.6860631877916914,
"learning_rate": 1.539444090576132e-05,
"loss": 1.5859,
"step": 605
},
{
"epoch": 0.3902751119641715,
"grad_norm": 3.012236105518444,
"learning_rate": 1.5300034791534297e-05,
"loss": 1.5628,
"step": 610
},
{
"epoch": 0.3934740882917466,
"grad_norm": 2.7725119156725473,
"learning_rate": 1.520496715679391e-05,
"loss": 1.5557,
"step": 615
},
{
"epoch": 0.39667306461932184,
"grad_norm": 2.9325766561366984,
"learning_rate": 1.5109249867347276e-05,
"loss": 1.5736,
"step": 620
},
{
"epoch": 0.399872040946897,
"grad_norm": 2.571176112058893,
"learning_rate": 1.5012894870087751e-05,
"loss": 1.5886,
"step": 625
},
{
"epoch": 0.40307101727447214,
"grad_norm": 2.872319790499578,
"learning_rate": 1.4915914191503792e-05,
"loss": 1.6033,
"step": 630
},
{
"epoch": 0.40626999360204735,
"grad_norm": 2.985639218703229,
"learning_rate": 1.4818319936177885e-05,
"loss": 1.574,
"step": 635
},
{
"epoch": 0.4094689699296225,
"grad_norm": 2.860677975957467,
"learning_rate": 1.4720124285275703e-05,
"loss": 1.5633,
"step": 640
},
{
"epoch": 0.4126679462571977,
"grad_norm": 2.825311941618321,
"learning_rate": 1.4621339495025731e-05,
"loss": 1.5471,
"step": 645
},
{
"epoch": 0.41586692258477287,
"grad_norm": 2.9150202309024844,
"learning_rate": 1.4521977895189518e-05,
"loss": 1.5382,
"step": 650
},
{
"epoch": 0.419065898912348,
"grad_norm": 3.131529181763074,
"learning_rate": 1.4422051887522735e-05,
"loss": 1.5984,
"step": 655
},
{
"epoch": 0.42226487523992323,
"grad_norm": 2.6605800472086103,
"learning_rate": 1.4321573944227254e-05,
"loss": 1.5737,
"step": 660
},
{
"epoch": 0.4254638515674984,
"grad_norm": 2.944662238934973,
"learning_rate": 1.4220556606394465e-05,
"loss": 1.5855,
"step": 665
},
{
"epoch": 0.4286628278950736,
"grad_norm": 3.0504609906344173,
"learning_rate": 1.4119012482439929e-05,
"loss": 1.564,
"step": 670
},
{
"epoch": 0.43186180422264875,
"grad_norm": 2.805988252794016,
"learning_rate": 1.4016954246529697e-05,
"loss": 1.5118,
"step": 675
},
{
"epoch": 0.4350607805502239,
"grad_norm": 2.786269865387681,
"learning_rate": 1.3914394636998374e-05,
"loss": 1.5447,
"step": 680
},
{
"epoch": 0.4382597568777991,
"grad_norm": 2.8458724254371064,
"learning_rate": 1.3811346454759211e-05,
"loss": 1.596,
"step": 685
},
{
"epoch": 0.44145873320537427,
"grad_norm": 2.9255780377453067,
"learning_rate": 1.3707822561706336e-05,
"loss": 1.5943,
"step": 690
},
{
"epoch": 0.4446577095329495,
"grad_norm": 3.1537106252949907,
"learning_rate": 1.3603835879109442e-05,
"loss": 1.4963,
"step": 695
},
{
"epoch": 0.44785668586052463,
"grad_norm": 2.635217049328388,
"learning_rate": 1.349939938600099e-05,
"loss": 1.5705,
"step": 700
},
{
"epoch": 0.4510556621880998,
"grad_norm": 2.922587063417034,
"learning_rate": 1.3394526117556277e-05,
"loss": 1.5518,
"step": 705
},
{
"epoch": 0.454254638515675,
"grad_norm": 2.807359635537847,
"learning_rate": 1.3289229163466421e-05,
"loss": 1.5568,
"step": 710
},
{
"epoch": 0.45745361484325014,
"grad_norm": 2.931234500751365,
"learning_rate": 1.3183521666304611e-05,
"loss": 1.5254,
"step": 715
},
{
"epoch": 0.46065259117082535,
"grad_norm": 2.888485871147149,
"learning_rate": 1.3077416819885707e-05,
"loss": 1.5664,
"step": 720
},
{
"epoch": 0.4638515674984005,
"grad_norm": 2.9721361024671564,
"learning_rate": 1.297092786761946e-05,
"loss": 1.594,
"step": 725
},
{
"epoch": 0.46705054382597566,
"grad_norm": 2.8023380182627315,
"learning_rate": 1.2864068100857565e-05,
"loss": 1.5485,
"step": 730
},
{
"epoch": 0.47024952015355087,
"grad_norm": 2.6053459784808846,
"learning_rate": 1.2756850857234686e-05,
"loss": 1.4846,
"step": 735
},
{
"epoch": 0.473448496481126,
"grad_norm": 2.946713804424543,
"learning_rate": 1.2649289519003739e-05,
"loss": 1.5685,
"step": 740
},
{
"epoch": 0.47664747280870123,
"grad_norm": 3.1265447806548656,
"learning_rate": 1.2541397511365584e-05,
"loss": 1.5732,
"step": 745
},
{
"epoch": 0.4798464491362764,
"grad_norm": 2.773194480869555,
"learning_rate": 1.2433188300793399e-05,
"loss": 1.5775,
"step": 750
},
{
"epoch": 0.48304542546385154,
"grad_norm": 2.9306712944849007,
"learning_rate": 1.2324675393351818e-05,
"loss": 1.5981,
"step": 755
},
{
"epoch": 0.48624440179142675,
"grad_norm": 2.828506147564432,
"learning_rate": 1.221587233301123e-05,
"loss": 1.6012,
"step": 760
},
{
"epoch": 0.4894433781190019,
"grad_norm": 3.122644969081292,
"learning_rate": 1.2106792699957264e-05,
"loss": 1.5529,
"step": 765
},
{
"epoch": 0.4926423544465771,
"grad_norm": 2.8516675851476463,
"learning_rate": 1.1997450108895807e-05,
"loss": 1.5651,
"step": 770
},
{
"epoch": 0.49584133077415227,
"grad_norm": 2.79771041315179,
"learning_rate": 1.1887858207353678e-05,
"loss": 1.5471,
"step": 775
},
{
"epoch": 0.4990403071017274,
"grad_norm": 3.0118454884149637,
"learning_rate": 1.1778030673975227e-05,
"loss": 1.589,
"step": 780
},
{
"epoch": 0.5022392834293026,
"grad_norm": 2.769695350025131,
"learning_rate": 1.166798121681505e-05,
"loss": 1.5049,
"step": 785
},
{
"epoch": 0.5054382597568778,
"grad_norm": 2.8340769775532664,
"learning_rate": 1.1557723571627016e-05,
"loss": 1.5411,
"step": 790
},
{
"epoch": 0.508637236084453,
"grad_norm": 2.750139717769645,
"learning_rate": 1.1447271500149849e-05,
"loss": 1.5642,
"step": 795
},
{
"epoch": 0.5118362124120281,
"grad_norm": 2.875040151356922,
"learning_rate": 1.1336638788389473e-05,
"loss": 1.5641,
"step": 800
},
{
"epoch": 0.5150351887396033,
"grad_norm": 2.751585918983617,
"learning_rate": 1.122583924489832e-05,
"loss": 1.522,
"step": 805
},
{
"epoch": 0.5182341650671785,
"grad_norm": 2.7957607756494354,
"learning_rate": 1.1114886699051803e-05,
"loss": 1.5684,
"step": 810
},
{
"epoch": 0.5214331413947537,
"grad_norm": 3.018448300935822,
"learning_rate": 1.1003794999322246e-05,
"loss": 1.5644,
"step": 815
},
{
"epoch": 0.5246321177223289,
"grad_norm": 2.833305209680887,
"learning_rate": 1.089257801155037e-05,
"loss": 1.5551,
"step": 820
},
{
"epoch": 0.527831094049904,
"grad_norm": 2.8051124688710187,
"learning_rate": 1.0781249617214642e-05,
"loss": 1.5526,
"step": 825
},
{
"epoch": 0.5310300703774792,
"grad_norm": 2.970008708784057,
"learning_rate": 1.0669823711698668e-05,
"loss": 1.5683,
"step": 830
},
{
"epoch": 0.5342290467050543,
"grad_norm": 2.9429042611125578,
"learning_rate": 1.0558314202556866e-05,
"loss": 1.547,
"step": 835
},
{
"epoch": 0.5374280230326296,
"grad_norm": 3.0145128665406093,
"learning_rate": 1.0446735007778563e-05,
"loss": 1.5721,
"step": 840
},
{
"epoch": 0.5406269993602048,
"grad_norm": 2.8199366350819557,
"learning_rate": 1.0335100054050877e-05,
"loss": 1.5137,
"step": 845
},
{
"epoch": 0.5438259756877799,
"grad_norm": 2.883058571653099,
"learning_rate": 1.0223423275020431e-05,
"loss": 1.5268,
"step": 850
},
{
"epoch": 0.5470249520153551,
"grad_norm": 2.8695090948484356,
"learning_rate": 1.0111718609554254e-05,
"loss": 1.5612,
"step": 855
},
{
"epoch": 0.5502239283429302,
"grad_norm": 2.840292039654959,
"learning_rate": 1e-05,
"loss": 1.5206,
"step": 860
},
{
"epoch": 0.5534229046705055,
"grad_norm": 2.9448801594067935,
"learning_rate": 9.888281390445747e-06,
"loss": 1.4688,
"step": 865
},
{
"epoch": 0.5566218809980806,
"grad_norm": 2.7726084893952017,
"learning_rate": 9.776576724979572e-06,
"loss": 1.4634,
"step": 870
},
{
"epoch": 0.5598208573256558,
"grad_norm": 2.926043434000589,
"learning_rate": 9.664899945949128e-06,
"loss": 1.6195,
"step": 875
},
{
"epoch": 0.5630198336532309,
"grad_norm": 2.6771555462563352,
"learning_rate": 9.553264992221442e-06,
"loss": 1.5128,
"step": 880
},
{
"epoch": 0.5662188099808061,
"grad_norm": 2.947093372690194,
"learning_rate": 9.441685797443138e-06,
"loss": 1.5762,
"step": 885
},
{
"epoch": 0.5694177863083814,
"grad_norm": 2.862147214119077,
"learning_rate": 9.330176288301332e-06,
"loss": 1.5518,
"step": 890
},
{
"epoch": 0.5726167626359565,
"grad_norm": 2.9082851625533728,
"learning_rate": 9.21875038278536e-06,
"loss": 1.6275,
"step": 895
},
{
"epoch": 0.5758157389635317,
"grad_norm": 2.896161142681693,
"learning_rate": 9.107421988449632e-06,
"loss": 1.4906,
"step": 900
},
{
"epoch": 0.5790147152911068,
"grad_norm": 2.958572021767601,
"learning_rate": 8.996205000677758e-06,
"loss": 1.5325,
"step": 905
},
{
"epoch": 0.582213691618682,
"grad_norm": 2.9475486505888004,
"learning_rate": 8.885113300948199e-06,
"loss": 1.5133,
"step": 910
},
{
"epoch": 0.5854126679462572,
"grad_norm": 2.9704884794760584,
"learning_rate": 8.774160755101685e-06,
"loss": 1.4918,
"step": 915
},
{
"epoch": 0.5886116442738324,
"grad_norm": 2.9833940683910187,
"learning_rate": 8.663361211610529e-06,
"loss": 1.492,
"step": 920
},
{
"epoch": 0.5918106206014075,
"grad_norm": 3.072957307509492,
"learning_rate": 8.552728499850153e-06,
"loss": 1.5105,
"step": 925
},
{
"epoch": 0.5950095969289827,
"grad_norm": 2.720493027907383,
"learning_rate": 8.442276428372986e-06,
"loss": 1.5727,
"step": 930
},
{
"epoch": 0.5982085732565579,
"grad_norm": 2.8343530510078696,
"learning_rate": 8.332018783184952e-06,
"loss": 1.5737,
"step": 935
},
{
"epoch": 0.6014075495841331,
"grad_norm": 2.736869895029898,
"learning_rate": 8.221969326024776e-06,
"loss": 1.4817,
"step": 940
},
{
"epoch": 0.6046065259117083,
"grad_norm": 2.9515686637484455,
"learning_rate": 8.112141792646326e-06,
"loss": 1.5827,
"step": 945
},
{
"epoch": 0.6078055022392834,
"grad_norm": 2.998496824719505,
"learning_rate": 8.002549891104196e-06,
"loss": 1.5098,
"step": 950
},
{
"epoch": 0.6110044785668586,
"grad_norm": 2.9290208992184468,
"learning_rate": 7.89320730004274e-06,
"loss": 1.5151,
"step": 955
},
{
"epoch": 0.6142034548944337,
"grad_norm": 2.8425267712019044,
"learning_rate": 7.784127666988774e-06,
"loss": 1.5691,
"step": 960
},
{
"epoch": 0.617402431222009,
"grad_norm": 2.774978059880357,
"learning_rate": 7.675324606648187e-06,
"loss": 1.4685,
"step": 965
},
{
"epoch": 0.6206014075495841,
"grad_norm": 3.2182013564031298,
"learning_rate": 7.566811699206604e-06,
"loss": 1.5308,
"step": 970
},
{
"epoch": 0.6238003838771593,
"grad_norm": 2.9391385630232914,
"learning_rate": 7.458602488634416e-06,
"loss": 1.5132,
"step": 975
},
{
"epoch": 0.6269993602047345,
"grad_norm": 2.8772833599792986,
"learning_rate": 7.350710480996266e-06,
"loss": 1.5446,
"step": 980
},
{
"epoch": 0.6301983365323096,
"grad_norm": 2.9609923922572694,
"learning_rate": 7.243149142765317e-06,
"loss": 1.5186,
"step": 985
},
{
"epoch": 0.6333973128598849,
"grad_norm": 2.9050339268535734,
"learning_rate": 7.135931899142438e-06,
"loss": 1.5265,
"step": 990
},
{
"epoch": 0.63659628918746,
"grad_norm": 2.8553553938975362,
"learning_rate": 7.029072132380543e-06,
"loss": 1.5446,
"step": 995
},
{
"epoch": 0.6397952655150352,
"grad_norm": 2.8905623377823004,
"learning_rate": 6.922583180114299e-06,
"loss": 1.5403,
"step": 1000
},
{
"epoch": 0.6429942418426103,
"grad_norm": 3.064334779626001,
"learning_rate": 6.816478333695392e-06,
"loss": 1.4827,
"step": 1005
},
{
"epoch": 0.6461932181701855,
"grad_norm": 2.8732323238647424,
"learning_rate": 6.710770836533584e-06,
"loss": 1.5491,
"step": 1010
},
{
"epoch": 0.6493921944977608,
"grad_norm": 2.925690047754127,
"learning_rate": 6.605473882443725e-06,
"loss": 1.4563,
"step": 1015
},
{
"epoch": 0.6525911708253359,
"grad_norm": 2.7659749123153388,
"learning_rate": 6.5006006139990115e-06,
"loss": 1.5596,
"step": 1020
},
{
"epoch": 0.6557901471529111,
"grad_norm": 2.8517880123774377,
"learning_rate": 6.396164120890562e-06,
"loss": 1.5336,
"step": 1025
},
{
"epoch": 0.6589891234804862,
"grad_norm": 2.7182143838244053,
"learning_rate": 6.292177438293665e-06,
"loss": 1.5715,
"step": 1030
},
{
"epoch": 0.6621880998080614,
"grad_norm": 2.8942007565586456,
"learning_rate": 6.188653545240793e-06,
"loss": 1.4804,
"step": 1035
},
{
"epoch": 0.6653870761356366,
"grad_norm": 2.8706015223254515,
"learning_rate": 6.085605363001628e-06,
"loss": 1.4872,
"step": 1040
},
{
"epoch": 0.6685860524632118,
"grad_norm": 3.073092993550976,
"learning_rate": 5.983045753470308e-06,
"loss": 1.5443,
"step": 1045
},
{
"epoch": 0.6717850287907869,
"grad_norm": 2.969370140043883,
"learning_rate": 5.880987517560075e-06,
"loss": 1.4585,
"step": 1050
},
{
"epoch": 0.6749840051183621,
"grad_norm": 2.7750123138453997,
"learning_rate": 5.779443393605536e-06,
"loss": 1.4895,
"step": 1055
},
{
"epoch": 0.6781829814459372,
"grad_norm": 3.219255943862367,
"learning_rate": 5.678426055772746e-06,
"loss": 1.5289,
"step": 1060
},
{
"epoch": 0.6813819577735125,
"grad_norm": 2.8400549429245228,
"learning_rate": 5.577948112477271e-06,
"loss": 1.5421,
"step": 1065
},
{
"epoch": 0.6845809341010877,
"grad_norm": 3.1481123457663935,
"learning_rate": 5.478022104810483e-06,
"loss": 1.5034,
"step": 1070
},
{
"epoch": 0.6877799104286628,
"grad_norm": 2.8544263823046427,
"learning_rate": 5.378660504974271e-06,
"loss": 1.463,
"step": 1075
},
{
"epoch": 0.690978886756238,
"grad_norm": 2.9298014223513893,
"learning_rate": 5.2798757147242986e-06,
"loss": 1.5628,
"step": 1080
},
{
"epoch": 0.6941778630838131,
"grad_norm": 3.1149389988395373,
"learning_rate": 5.1816800638221176e-06,
"loss": 1.5174,
"step": 1085
},
{
"epoch": 0.6973768394113884,
"grad_norm": 2.917187672993627,
"learning_rate": 5.084085808496211e-06,
"loss": 1.5215,
"step": 1090
},
{
"epoch": 0.7005758157389635,
"grad_norm": 2.963114425511993,
"learning_rate": 4.987105129912252e-06,
"loss": 1.48,
"step": 1095
},
{
"epoch": 0.7037747920665387,
"grad_norm": 2.9831391059980303,
"learning_rate": 4.890750132652724e-06,
"loss": 1.514,
"step": 1100
},
{
"epoch": 0.7069737683941139,
"grad_norm": 3.0096475725136163,
"learning_rate": 4.795032843206091e-06,
"loss": 1.4868,
"step": 1105
},
{
"epoch": 0.710172744721689,
"grad_norm": 3.0132931997185923,
"learning_rate": 4.699965208465702e-06,
"loss": 1.5582,
"step": 1110
},
{
"epoch": 0.7133717210492643,
"grad_norm": 3.0669134476552973,
"learning_rate": 4.605559094238681e-06,
"loss": 1.5778,
"step": 1115
},
{
"epoch": 0.7165706973768394,
"grad_norm": 2.7026304976719735,
"learning_rate": 4.511826283764872e-06,
"loss": 1.5447,
"step": 1120
},
{
"epoch": 0.7197696737044146,
"grad_norm": 2.4264157327432567,
"learning_rate": 4.418778476246132e-06,
"loss": 1.4316,
"step": 1125
},
{
"epoch": 0.7229686500319897,
"grad_norm": 2.767093184272473,
"learning_rate": 4.326427285386118e-06,
"loss": 1.5045,
"step": 1130
},
{
"epoch": 0.7261676263595649,
"grad_norm": 2.7525423984037745,
"learning_rate": 4.234784237940705e-06,
"loss": 1.4692,
"step": 1135
},
{
"epoch": 0.7293666026871402,
"grad_norm": 2.8302392998586265,
"learning_rate": 4.143860772279287e-06,
"loss": 1.4915,
"step": 1140
},
{
"epoch": 0.7325655790147153,
"grad_norm": 3.086044746252559,
"learning_rate": 4.053668236957135e-06,
"loss": 1.5279,
"step": 1145
},
{
"epoch": 0.7357645553422905,
"grad_norm": 2.992189198294163,
"learning_rate": 3.964217889298882e-06,
"loss": 1.4963,
"step": 1150
},
{
"epoch": 0.7389635316698656,
"grad_norm": 2.8913624378602782,
"learning_rate": 3.875520893993482e-06,
"loss": 1.5224,
"step": 1155
},
{
"epoch": 0.7421625079974408,
"grad_norm": 2.966579181678815,
"learning_rate": 3.787588321700697e-06,
"loss": 1.5446,
"step": 1160
},
{
"epoch": 0.745361484325016,
"grad_norm": 2.7826554976617395,
"learning_rate": 3.7004311476692977e-06,
"loss": 1.5291,
"step": 1165
},
{
"epoch": 0.7485604606525912,
"grad_norm": 2.8741241950919587,
"learning_rate": 3.6140602503672217e-06,
"loss": 1.5155,
"step": 1170
},
{
"epoch": 0.7517594369801663,
"grad_norm": 3.2498424072079732,
"learning_rate": 3.528486410123758e-06,
"loss": 1.4732,
"step": 1175
},
{
"epoch": 0.7549584133077415,
"grad_norm": 2.889481003290222,
"learning_rate": 3.443720307784022e-06,
"loss": 1.4917,
"step": 1180
},
{
"epoch": 0.7581573896353166,
"grad_norm": 2.91590203305323,
"learning_rate": 3.359772523375837e-06,
"loss": 1.5481,
"step": 1185
},
{
"epoch": 0.7613563659628919,
"grad_norm": 2.9904843978709406,
"learning_rate": 3.276653534789185e-06,
"loss": 1.5098,
"step": 1190
},
{
"epoch": 0.7645553422904671,
"grad_norm": 3.0417192905803416,
"learning_rate": 3.1943737164684094e-06,
"loss": 1.5058,
"step": 1195
},
{
"epoch": 0.7677543186180422,
"grad_norm": 2.928336132975389,
"learning_rate": 3.11294333811736e-06,
"loss": 1.4466,
"step": 1200
},
{
"epoch": 0.7709532949456174,
"grad_norm": 2.9614436889799296,
"learning_rate": 3.032372563417556e-06,
"loss": 1.5117,
"step": 1205
},
{
"epoch": 0.7741522712731925,
"grad_norm": 3.0765832757123373,
"learning_rate": 2.952671448759631e-06,
"loss": 1.5068,
"step": 1210
},
{
"epoch": 0.7773512476007678,
"grad_norm": 2.8889529624782027,
"learning_rate": 2.8738499419881517e-06,
"loss": 1.5149,
"step": 1215
},
{
"epoch": 0.780550223928343,
"grad_norm": 3.033338590523889,
"learning_rate": 2.795917881159973e-06,
"loss": 1.4582,
"step": 1220
},
{
"epoch": 0.7837492002559181,
"grad_norm": 3.122248429780225,
"learning_rate": 2.718884993316311e-06,
"loss": 1.5254,
"step": 1225
},
{
"epoch": 0.7869481765834933,
"grad_norm": 2.8620612033770048,
"learning_rate": 2.642760893268684e-06,
"loss": 1.4926,
"step": 1230
},
{
"epoch": 0.7901471529110684,
"grad_norm": 2.957494409747179,
"learning_rate": 2.5675550823988184e-06,
"loss": 1.5024,
"step": 1235
},
{
"epoch": 0.7933461292386437,
"grad_norm": 2.9507185427703164,
"learning_rate": 2.493276947472756e-06,
"loss": 1.5038,
"step": 1240
},
{
"epoch": 0.7965451055662188,
"grad_norm": 3.1468644000814665,
"learning_rate": 2.4199357594692564e-06,
"loss": 1.4553,
"step": 1245
},
{
"epoch": 0.799744081893794,
"grad_norm": 3.020046365559696,
"learning_rate": 2.347540672422627e-06,
"loss": 1.4488,
"step": 1250
},
{
"epoch": 0.8029430582213691,
"grad_norm": 3.0758818025981,
"learning_rate": 2.2761007222801866e-06,
"loss": 1.4925,
"step": 1255
},
{
"epoch": 0.8061420345489443,
"grad_norm": 3.0147595677345542,
"learning_rate": 2.2056248257744383e-06,
"loss": 1.4815,
"step": 1260
},
{
"epoch": 0.8093410108765196,
"grad_norm": 2.734206633065449,
"learning_rate": 2.136121779310132e-06,
"loss": 1.4939,
"step": 1265
},
{
"epoch": 0.8125399872040947,
"grad_norm": 3.02643548047932,
"learning_rate": 2.067600257866358e-06,
"loss": 1.508,
"step": 1270
},
{
"epoch": 0.8157389635316699,
"grad_norm": 3.125756359469005,
"learning_rate": 2.000068813913777e-06,
"loss": 1.5049,
"step": 1275
},
{
"epoch": 0.818937939859245,
"grad_norm": 2.837342662182425,
"learning_rate": 1.933535876347141e-06,
"loss": 1.5284,
"step": 1280
},
{
"epoch": 0.8221369161868202,
"grad_norm": 3.0307641378967536,
"learning_rate": 1.8680097494332682e-06,
"loss": 1.4999,
"step": 1285
},
{
"epoch": 0.8253358925143954,
"grad_norm": 2.801930434751216,
"learning_rate": 1.8034986117745245e-06,
"loss": 1.4563,
"step": 1290
},
{
"epoch": 0.8285348688419706,
"grad_norm": 3.0342605155241213,
"learning_rate": 1.7400105152880331e-06,
"loss": 1.4706,
"step": 1295
},
{
"epoch": 0.8317338451695457,
"grad_norm": 2.981972081491564,
"learning_rate": 1.6775533842006853e-06,
"loss": 1.5812,
"step": 1300
},
{
"epoch": 0.8349328214971209,
"grad_norm": 2.95896665427553,
"learning_rate": 1.6161350140600606e-06,
"loss": 1.4774,
"step": 1305
},
{
"epoch": 0.838131797824696,
"grad_norm": 2.8462517601587503,
"learning_rate": 1.555763070761448e-06,
"loss": 1.5473,
"step": 1310
},
{
"epoch": 0.8413307741522713,
"grad_norm": 2.8561706155053552,
"learning_rate": 1.496445089591031e-06,
"loss": 1.5234,
"step": 1315
},
{
"epoch": 0.8445297504798465,
"grad_norm": 3.3872912897412983,
"learning_rate": 1.4381884742853723e-06,
"loss": 1.5102,
"step": 1320
},
{
"epoch": 0.8477287268074216,
"grad_norm": 3.0883959119755464,
"learning_rate": 1.381000496107313e-06,
"loss": 1.4682,
"step": 1325
},
{
"epoch": 0.8509277031349968,
"grad_norm": 3.086585424865861,
"learning_rate": 1.3248882929384321e-06,
"loss": 1.4491,
"step": 1330
},
{
"epoch": 0.8541266794625719,
"grad_norm": 2.8090437396140326,
"learning_rate": 1.2698588683881185e-06,
"loss": 1.521,
"step": 1335
},
{
"epoch": 0.8573256557901472,
"grad_norm": 2.9900037626653257,
"learning_rate": 1.215919090919434e-06,
"loss": 1.556,
"step": 1340
},
{
"epoch": 0.8605246321177223,
"grad_norm": 3.167648071542424,
"learning_rate": 1.1630756929918218e-06,
"loss": 1.3722,
"step": 1345
},
{
"epoch": 0.8637236084452975,
"grad_norm": 3.1006715482553213,
"learning_rate": 1.111335270220798e-06,
"loss": 1.4499,
"step": 1350
},
{
"epoch": 0.8669225847728727,
"grad_norm": 3.1182518143820515,
"learning_rate": 1.060704280554733e-06,
"loss": 1.4923,
"step": 1355
},
{
"epoch": 0.8701215611004478,
"grad_norm": 2.8077044413187777,
"learning_rate": 1.0111890434688009e-06,
"loss": 1.5196,
"step": 1360
},
{
"epoch": 0.8733205374280231,
"grad_norm": 3.021623866473881,
"learning_rate": 9.62795739176212e-07,
"loss": 1.5857,
"step": 1365
},
{
"epoch": 0.8765195137555982,
"grad_norm": 2.917831434671116,
"learning_rate": 9.155304078568495e-07,
"loss": 1.4386,
"step": 1370
},
{
"epoch": 0.8797184900831734,
"grad_norm": 3.1639039913208444,
"learning_rate": 8.693989489033494e-07,
"loss": 1.4134,
"step": 1375
},
{
"epoch": 0.8829174664107485,
"grad_norm": 3.004158580298322,
"learning_rate": 8.244071201847826e-07,
"loss": 1.4527,
"step": 1380
},
{
"epoch": 0.8861164427383237,
"grad_norm": 3.0065051769894358,
"learning_rate": 7.805605373279934e-07,
"loss": 1.4655,
"step": 1385
},
{
"epoch": 0.889315419065899,
"grad_norm": 2.771127515593038,
"learning_rate": 7.378646730166783e-07,
"loss": 1.4788,
"step": 1390
},
{
"epoch": 0.8925143953934741,
"grad_norm": 3.035838391028782,
"learning_rate": 6.963248563083203e-07,
"loss": 1.4977,
"step": 1395
},
{
"epoch": 0.8957133717210493,
"grad_norm": 2.8916082991419776,
"learning_rate": 6.559462719690501e-07,
"loss": 1.4785,
"step": 1400
},
{
"epoch": 0.8989123480486244,
"grad_norm": 2.883458011693006,
"learning_rate": 6.167339598265109e-07,
"loss": 1.4753,
"step": 1405
},
{
"epoch": 0.9021113243761996,
"grad_norm": 3.0406171251728242,
"learning_rate": 5.78692814140811e-07,
"loss": 1.4516,
"step": 1410
},
{
"epoch": 0.9053103007037748,
"grad_norm": 2.896215057217351,
"learning_rate": 5.418275829936537e-07,
"loss": 1.4805,
"step": 1415
},
{
"epoch": 0.90850927703135,
"grad_norm": 3.0263277055612123,
"learning_rate": 5.06142867695708e-07,
"loss": 1.4574,
"step": 1420
},
{
"epoch": 0.9117082533589251,
"grad_norm": 2.9240236260600843,
"learning_rate": 4.716431222122997e-07,
"loss": 1.4998,
"step": 1425
},
{
"epoch": 0.9149072296865003,
"grad_norm": 3.0684358127407254,
"learning_rate": 4.3833265260749157e-07,
"loss": 1.4883,
"step": 1430
},
{
"epoch": 0.9181062060140754,
"grad_norm": 3.0229386052146068,
"learning_rate": 4.062156165066211e-07,
"loss": 1.5184,
"step": 1435
},
{
"epoch": 0.9213051823416507,
"grad_norm": 2.993215240222199,
"learning_rate": 3.752960225773772e-07,
"loss": 1.4656,
"step": 1440
},
{
"epoch": 0.9245041586692259,
"grad_norm": 2.8375909059845075,
"learning_rate": 3.4557773002945607e-07,
"loss": 1.4481,
"step": 1445
},
{
"epoch": 0.927703134996801,
"grad_norm": 2.8676821088917284,
"learning_rate": 3.170644481328711e-07,
"loss": 1.4774,
"step": 1450
},
{
"epoch": 0.9309021113243762,
"grad_norm": 3.093581781769162,
"learning_rate": 2.8975973575499526e-07,
"loss": 1.4958,
"step": 1455
},
{
"epoch": 0.9341010876519513,
"grad_norm": 2.921596866453042,
"learning_rate": 2.636670009163522e-07,
"loss": 1.5072,
"step": 1460
},
{
"epoch": 0.9373000639795266,
"grad_norm": 2.915634124882459,
"learning_rate": 2.3878950036524963e-07,
"loss": 1.4001,
"step": 1465
},
{
"epoch": 0.9404990403071017,
"grad_norm": 2.9949792867089267,
"learning_rate": 2.1513033917129334e-07,
"loss": 1.4909,
"step": 1470
},
{
"epoch": 0.9436980166346769,
"grad_norm": 3.237875827515494,
"learning_rate": 1.9269247033782744e-07,
"loss": 1.4821,
"step": 1475
},
{
"epoch": 0.946896992962252,
"grad_norm": 2.8350786807512005,
"learning_rate": 1.7147869443335463e-07,
"loss": 1.4834,
"step": 1480
},
{
"epoch": 0.9500959692898272,
"grad_norm": 2.836916452386956,
"learning_rate": 1.5149165924199016e-07,
"loss": 1.4725,
"step": 1485
},
{
"epoch": 0.9532949456174025,
"grad_norm": 2.9144755189548257,
"learning_rate": 1.3273385943297746e-07,
"loss": 1.45,
"step": 1490
},
{
"epoch": 0.9564939219449776,
"grad_norm": 3.073942638939728,
"learning_rate": 1.1520763624931597e-07,
"loss": 1.6223,
"step": 1495
},
{
"epoch": 0.9596928982725528,
"grad_norm": 3.032206669875784,
"learning_rate": 9.891517721554499e-08,
"loss": 1.4349,
"step": 1500
},
{
"epoch": 0.9628918746001279,
"grad_norm": 2.955714005801713,
"learning_rate": 8.385851586470318e-08,
"loss": 1.4398,
"step": 1505
},
{
"epoch": 0.9660908509277031,
"grad_norm": 3.0917574540101835,
"learning_rate": 7.003953148452036e-08,
"loss": 1.5322,
"step": 1510
},
{
"epoch": 0.9692898272552783,
"grad_norm": 2.8583565158367126,
"learning_rate": 5.745994888285311e-08,
"loss": 1.4905,
"step": 1515
},
{
"epoch": 0.9724888035828535,
"grad_norm": 3.0580164488934667,
"learning_rate": 4.612133817239905e-08,
"loss": 1.4884,
"step": 1520
},
{
"epoch": 0.9756877799104287,
"grad_norm": 3.217782652408035,
"learning_rate": 3.602511457473479e-08,
"loss": 1.4992,
"step": 1525
},
{
"epoch": 0.9788867562380038,
"grad_norm": 2.7243818878695465,
"learning_rate": 2.7172538243666057e-08,
"loss": 1.4353,
"step": 1530
},
{
"epoch": 0.982085732565579,
"grad_norm": 2.895493061043642,
"learning_rate": 1.9564714107945804e-08,
"loss": 1.5436,
"step": 1535
},
{
"epoch": 0.9852847088931542,
"grad_norm": 2.9802671522029742,
"learning_rate": 1.3202591733365577e-08,
"loss": 1.4379,
"step": 1540
},
{
"epoch": 0.9884836852207294,
"grad_norm": 2.9884671963598284,
"learning_rate": 8.086965204233688e-09,
"loss": 1.5177,
"step": 1545
},
{
"epoch": 0.9916826615483045,
"grad_norm": 3.4092231126752415,
"learning_rate": 4.218473024261149e-09,
"loss": 1.5238,
"step": 1550
},
{
"epoch": 0.9948816378758797,
"grad_norm": 2.865378574655855,
"learning_rate": 1.5975980368709843e-09,
"loss": 1.4348,
"step": 1555
},
{
"epoch": 0.9980806142034548,
"grad_norm": 2.9847533922224017,
"learning_rate": 2.2466736492643416e-10,
"loss": 1.4252,
"step": 1560
},
{
"epoch": 1.0,
"eval_loss": 1.5372248888015747,
"eval_runtime": 19.0671,
"eval_samples_per_second": 26.223,
"eval_steps_per_second": 0.839,
"step": 1563
},
{
"epoch": 1.0,
"step": 1563,
"total_flos": 22001167835136.0,
"train_loss": 1.5636964343102102,
"train_runtime": 6788.8098,
"train_samples_per_second": 7.365,
"train_steps_per_second": 0.23
}
],
"logging_steps": 5,
"max_steps": 1563,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 22001167835136.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}