sedrickkeh's picture
End of training
b2f1253 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.997953488372093,
"eval_steps": 500,
"global_step": 2013,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.014883720930232559,
"grad_norm": 12.09994395919115,
"learning_rate": 1.655629139072848e-07,
"loss": 0.8894,
"step": 10
},
{
"epoch": 0.029767441860465118,
"grad_norm": 4.954666557139731,
"learning_rate": 3.311258278145696e-07,
"loss": 0.8403,
"step": 20
},
{
"epoch": 0.044651162790697675,
"grad_norm": 2.6897749196373066,
"learning_rate": 4.966887417218544e-07,
"loss": 0.7599,
"step": 30
},
{
"epoch": 0.059534883720930236,
"grad_norm": 1.6864897198632844,
"learning_rate": 6.622516556291392e-07,
"loss": 0.7065,
"step": 40
},
{
"epoch": 0.07441860465116279,
"grad_norm": 1.4408752436652603,
"learning_rate": 8.27814569536424e-07,
"loss": 0.6683,
"step": 50
},
{
"epoch": 0.08930232558139535,
"grad_norm": 1.531285186081538,
"learning_rate": 9.933774834437087e-07,
"loss": 0.6414,
"step": 60
},
{
"epoch": 0.10418604651162791,
"grad_norm": 1.3543454625606715,
"learning_rate": 1.1589403973509934e-06,
"loss": 0.6245,
"step": 70
},
{
"epoch": 0.11906976744186047,
"grad_norm": 1.6805043782242386,
"learning_rate": 1.3245033112582784e-06,
"loss": 0.6067,
"step": 80
},
{
"epoch": 0.13395348837209303,
"grad_norm": 1.622726415982876,
"learning_rate": 1.490066225165563e-06,
"loss": 0.6026,
"step": 90
},
{
"epoch": 0.14883720930232558,
"grad_norm": 1.5904822357469823,
"learning_rate": 1.655629139072848e-06,
"loss": 0.5879,
"step": 100
},
{
"epoch": 0.16372093023255813,
"grad_norm": 1.7535371189936502,
"learning_rate": 1.8211920529801325e-06,
"loss": 0.5868,
"step": 110
},
{
"epoch": 0.1786046511627907,
"grad_norm": 1.5177280883443078,
"learning_rate": 1.9867549668874175e-06,
"loss": 0.5737,
"step": 120
},
{
"epoch": 0.19348837209302325,
"grad_norm": 1.768921545248635,
"learning_rate": 2.152317880794702e-06,
"loss": 0.567,
"step": 130
},
{
"epoch": 0.20837209302325582,
"grad_norm": 2.312126734150201,
"learning_rate": 2.317880794701987e-06,
"loss": 0.5634,
"step": 140
},
{
"epoch": 0.22325581395348837,
"grad_norm": 2.28355122015822,
"learning_rate": 2.4834437086092716e-06,
"loss": 0.5624,
"step": 150
},
{
"epoch": 0.23813953488372094,
"grad_norm": 1.5684581849256145,
"learning_rate": 2.6490066225165567e-06,
"loss": 0.5577,
"step": 160
},
{
"epoch": 0.25302325581395346,
"grad_norm": 2.3117262356536763,
"learning_rate": 2.814569536423841e-06,
"loss": 0.5464,
"step": 170
},
{
"epoch": 0.26790697674418606,
"grad_norm": 1.5302515797600287,
"learning_rate": 2.980132450331126e-06,
"loss": 0.5475,
"step": 180
},
{
"epoch": 0.2827906976744186,
"grad_norm": 1.9345332085767333,
"learning_rate": 3.145695364238411e-06,
"loss": 0.5441,
"step": 190
},
{
"epoch": 0.29767441860465116,
"grad_norm": 2.9098962218672098,
"learning_rate": 3.311258278145696e-06,
"loss": 0.544,
"step": 200
},
{
"epoch": 0.3125581395348837,
"grad_norm": 2.6881740405161407,
"learning_rate": 3.4768211920529803e-06,
"loss": 0.5329,
"step": 210
},
{
"epoch": 0.32744186046511625,
"grad_norm": 2.3359559961757843,
"learning_rate": 3.642384105960265e-06,
"loss": 0.5314,
"step": 220
},
{
"epoch": 0.34232558139534885,
"grad_norm": 2.4955049636721216,
"learning_rate": 3.80794701986755e-06,
"loss": 0.529,
"step": 230
},
{
"epoch": 0.3572093023255814,
"grad_norm": 2.1711263753421632,
"learning_rate": 3.973509933774835e-06,
"loss": 0.5225,
"step": 240
},
{
"epoch": 0.37209302325581395,
"grad_norm": 2.694920018594133,
"learning_rate": 4.139072847682119e-06,
"loss": 0.5227,
"step": 250
},
{
"epoch": 0.3869767441860465,
"grad_norm": 3.0680068154611373,
"learning_rate": 4.304635761589404e-06,
"loss": 0.5238,
"step": 260
},
{
"epoch": 0.4018604651162791,
"grad_norm": 2.02557092483253,
"learning_rate": 4.4701986754966895e-06,
"loss": 0.517,
"step": 270
},
{
"epoch": 0.41674418604651164,
"grad_norm": 2.7310686859093916,
"learning_rate": 4.635761589403974e-06,
"loss": 0.5176,
"step": 280
},
{
"epoch": 0.4316279069767442,
"grad_norm": 2.0826169110471997,
"learning_rate": 4.801324503311259e-06,
"loss": 0.5184,
"step": 290
},
{
"epoch": 0.44651162790697674,
"grad_norm": 2.972052559490264,
"learning_rate": 4.966887417218543e-06,
"loss": 0.515,
"step": 300
},
{
"epoch": 0.4613953488372093,
"grad_norm": 2.612798976679404,
"learning_rate": 4.999757269464535e-06,
"loss": 0.5141,
"step": 310
},
{
"epoch": 0.4762790697674419,
"grad_norm": 2.5363200990684116,
"learning_rate": 4.998771266421582e-06,
"loss": 0.5087,
"step": 320
},
{
"epoch": 0.49116279069767443,
"grad_norm": 1.9683808505033924,
"learning_rate": 4.997027152360594e-06,
"loss": 0.5114,
"step": 330
},
{
"epoch": 0.5060465116279069,
"grad_norm": 2.154598782155924,
"learning_rate": 4.994525515261374e-06,
"loss": 0.509,
"step": 340
},
{
"epoch": 0.5209302325581395,
"grad_norm": 1.9161226824804498,
"learning_rate": 4.991267198481659e-06,
"loss": 0.5058,
"step": 350
},
{
"epoch": 0.5358139534883721,
"grad_norm": 2.2519599437510753,
"learning_rate": 4.987253300472809e-06,
"loss": 0.5038,
"step": 360
},
{
"epoch": 0.5506976744186046,
"grad_norm": 1.719862276545399,
"learning_rate": 4.982485174409488e-06,
"loss": 0.4994,
"step": 370
},
{
"epoch": 0.5655813953488372,
"grad_norm": 2.177940295574328,
"learning_rate": 4.976964427733482e-06,
"loss": 0.5016,
"step": 380
},
{
"epoch": 0.5804651162790697,
"grad_norm": 1.6346006458180546,
"learning_rate": 4.970692921611799e-06,
"loss": 0.4941,
"step": 390
},
{
"epoch": 0.5953488372093023,
"grad_norm": 1.7603844394703574,
"learning_rate": 4.963672770309218e-06,
"loss": 0.4994,
"step": 400
},
{
"epoch": 0.6102325581395349,
"grad_norm": 2.278283898845916,
"learning_rate": 4.955906340475533e-06,
"loss": 0.501,
"step": 410
},
{
"epoch": 0.6251162790697674,
"grad_norm": 1.5611721745461695,
"learning_rate": 4.947396250347695e-06,
"loss": 0.4963,
"step": 420
},
{
"epoch": 0.64,
"grad_norm": 1.9733224203680875,
"learning_rate": 4.938145368867153e-06,
"loss": 0.4939,
"step": 430
},
{
"epoch": 0.6548837209302325,
"grad_norm": 1.8779984579315334,
"learning_rate": 4.928156814712661e-06,
"loss": 0.4958,
"step": 440
},
{
"epoch": 0.6697674418604651,
"grad_norm": 1.9838008724267557,
"learning_rate": 4.917433955248912e-06,
"loss": 0.4882,
"step": 450
},
{
"epoch": 0.6846511627906977,
"grad_norm": 2.149542021168797,
"learning_rate": 4.905980405391312e-06,
"loss": 0.4934,
"step": 460
},
{
"epoch": 0.6995348837209302,
"grad_norm": 1.4353286450009755,
"learning_rate": 4.8938000263873265e-06,
"loss": 0.4872,
"step": 470
},
{
"epoch": 0.7144186046511628,
"grad_norm": 2.312227707270547,
"learning_rate": 4.880896924514751e-06,
"loss": 0.4846,
"step": 480
},
{
"epoch": 0.7293023255813953,
"grad_norm": 2.5246529283224337,
"learning_rate": 4.8672754496974064e-06,
"loss": 0.4847,
"step": 490
},
{
"epoch": 0.7441860465116279,
"grad_norm": 1.8274651189787874,
"learning_rate": 4.852940194038676e-06,
"loss": 0.4838,
"step": 500
},
{
"epoch": 0.7590697674418605,
"grad_norm": 2.8994680346266315,
"learning_rate": 4.837895990273408e-06,
"loss": 0.4875,
"step": 510
},
{
"epoch": 0.773953488372093,
"grad_norm": 1.8666092756187436,
"learning_rate": 4.822147910138687e-06,
"loss": 0.4873,
"step": 520
},
{
"epoch": 0.7888372093023256,
"grad_norm": 1.9992173556155106,
"learning_rate": 4.8057012626640435e-06,
"loss": 0.4741,
"step": 530
},
{
"epoch": 0.8037209302325582,
"grad_norm": 2.057376829586277,
"learning_rate": 4.788561592381664e-06,
"loss": 0.4814,
"step": 540
},
{
"epoch": 0.8186046511627907,
"grad_norm": 2.6795388861334515,
"learning_rate": 4.770734677457199e-06,
"loss": 0.4775,
"step": 550
},
{
"epoch": 0.8334883720930233,
"grad_norm": 2.7439384401468776,
"learning_rate": 4.752226527741813e-06,
"loss": 0.4789,
"step": 560
},
{
"epoch": 0.8483720930232558,
"grad_norm": 1.8800574954738543,
"learning_rate": 4.733043382746139e-06,
"loss": 0.4764,
"step": 570
},
{
"epoch": 0.8632558139534884,
"grad_norm": 1.9323414743910012,
"learning_rate": 4.713191709536792e-06,
"loss": 0.4712,
"step": 580
},
{
"epoch": 0.878139534883721,
"grad_norm": 2.3312096463084,
"learning_rate": 4.692678200556178e-06,
"loss": 0.4735,
"step": 590
},
{
"epoch": 0.8930232558139535,
"grad_norm": 2.159350507916537,
"learning_rate": 4.671509771366324e-06,
"loss": 0.4746,
"step": 600
},
{
"epoch": 0.9079069767441861,
"grad_norm": 1.7675503743690197,
"learning_rate": 4.649693558317485e-06,
"loss": 0.4698,
"step": 610
},
{
"epoch": 0.9227906976744186,
"grad_norm": 2.2459263091128685,
"learning_rate": 4.627236916142326e-06,
"loss": 0.4678,
"step": 620
},
{
"epoch": 0.9376744186046512,
"grad_norm": 2.005145073353852,
"learning_rate": 4.604147415476471e-06,
"loss": 0.4716,
"step": 630
},
{
"epoch": 0.9525581395348838,
"grad_norm": 2.5633576833945257,
"learning_rate": 4.5804328403062735e-06,
"loss": 0.4712,
"step": 640
},
{
"epoch": 0.9674418604651163,
"grad_norm": 2.1030324239259937,
"learning_rate": 4.5561011853446686e-06,
"loss": 0.469,
"step": 650
},
{
"epoch": 0.9823255813953489,
"grad_norm": 2.5648420297297814,
"learning_rate": 4.5311606533359665e-06,
"loss": 0.4661,
"step": 660
},
{
"epoch": 0.9972093023255814,
"grad_norm": 1.6917829294317552,
"learning_rate": 4.50561965229053e-06,
"loss": 0.4722,
"step": 670
},
{
"epoch": 0.9986976744186047,
"eval_loss": 0.058389123529195786,
"eval_runtime": 468.1425,
"eval_samples_per_second": 38.67,
"eval_steps_per_second": 0.605,
"step": 671
},
{
"epoch": 1.0130232558139536,
"grad_norm": 2.2119223606388143,
"learning_rate": 4.479486792650245e-06,
"loss": 0.4052,
"step": 680
},
{
"epoch": 1.027906976744186,
"grad_norm": 1.7284245139555596,
"learning_rate": 4.452770884385747e-06,
"loss": 0.3906,
"step": 690
},
{
"epoch": 1.0427906976744186,
"grad_norm": 1.9008131985343542,
"learning_rate": 4.4254809340263875e-06,
"loss": 0.393,
"step": 700
},
{
"epoch": 1.0576744186046512,
"grad_norm": 1.687438841502772,
"learning_rate": 4.397626141623928e-06,
"loss": 0.3946,
"step": 710
},
{
"epoch": 1.0725581395348838,
"grad_norm": 1.531354838860777,
"learning_rate": 4.369215897650995e-06,
"loss": 0.3944,
"step": 720
},
{
"epoch": 1.0874418604651164,
"grad_norm": 1.5159046604752562,
"learning_rate": 4.340259779835348e-06,
"loss": 0.3921,
"step": 730
},
{
"epoch": 1.1023255813953488,
"grad_norm": 2.2360180914056,
"learning_rate": 4.310767549931009e-06,
"loss": 0.3977,
"step": 740
},
{
"epoch": 1.1172093023255814,
"grad_norm": 2.0669891250338037,
"learning_rate": 4.28074915042736e-06,
"loss": 0.394,
"step": 750
},
{
"epoch": 1.132093023255814,
"grad_norm": 2.072678701441777,
"learning_rate": 4.250214701197305e-06,
"loss": 0.3972,
"step": 760
},
{
"epoch": 1.1469767441860466,
"grad_norm": 1.637900992094672,
"learning_rate": 4.219174496085636e-06,
"loss": 0.3983,
"step": 770
},
{
"epoch": 1.1618604651162792,
"grad_norm": 1.4911303829134943,
"learning_rate": 4.18763899943875e-06,
"loss": 0.3976,
"step": 780
},
{
"epoch": 1.1767441860465115,
"grad_norm": 1.4717948476323155,
"learning_rate": 4.155618842576882e-06,
"loss": 0.3946,
"step": 790
},
{
"epoch": 1.1916279069767441,
"grad_norm": 2.1096638906121017,
"learning_rate": 4.1231248202100474e-06,
"loss": 0.395,
"step": 800
},
{
"epoch": 1.2065116279069767,
"grad_norm": 1.7307582159948425,
"learning_rate": 4.09016788679891e-06,
"loss": 0.3991,
"step": 810
},
{
"epoch": 1.2213953488372093,
"grad_norm": 1.8188324807887766,
"learning_rate": 4.056759152861782e-06,
"loss": 0.4013,
"step": 820
},
{
"epoch": 1.236279069767442,
"grad_norm": 1.6311500740393643,
"learning_rate": 4.022909881229028e-06,
"loss": 0.3951,
"step": 830
},
{
"epoch": 1.2511627906976743,
"grad_norm": 1.532434286126909,
"learning_rate": 3.988631483246104e-06,
"loss": 0.3981,
"step": 840
},
{
"epoch": 1.266046511627907,
"grad_norm": 1.5195258602788826,
"learning_rate": 3.953935514926546e-06,
"loss": 0.3962,
"step": 850
},
{
"epoch": 1.2809302325581395,
"grad_norm": 1.5512026772569776,
"learning_rate": 3.9188336730561745e-06,
"loss": 0.3951,
"step": 860
},
{
"epoch": 1.2958139534883721,
"grad_norm": 1.5805766911542627,
"learning_rate": 3.8833377912498494e-06,
"loss": 0.3934,
"step": 870
},
{
"epoch": 1.3106976744186047,
"grad_norm": 1.4470120259789245,
"learning_rate": 3.847459835962095e-06,
"loss": 0.3959,
"step": 880
},
{
"epoch": 1.3255813953488373,
"grad_norm": 1.4153491164463297,
"learning_rate": 3.8112119024529367e-06,
"loss": 0.3926,
"step": 890
},
{
"epoch": 1.3404651162790697,
"grad_norm": 1.5623580611007561,
"learning_rate": 3.774606210710323e-06,
"loss": 0.3966,
"step": 900
},
{
"epoch": 1.3553488372093023,
"grad_norm": 2.0061828482545208,
"learning_rate": 3.737655101330493e-06,
"loss": 0.3963,
"step": 910
},
{
"epoch": 1.370232558139535,
"grad_norm": 1.6752845300217272,
"learning_rate": 3.700371031357687e-06,
"loss": 0.3982,
"step": 920
},
{
"epoch": 1.3851162790697673,
"grad_norm": 1.453648031726924,
"learning_rate": 3.6627665700845944e-06,
"loss": 0.3933,
"step": 930
},
{
"epoch": 1.4,
"grad_norm": 1.604604958585821,
"learning_rate": 3.624854394814972e-06,
"loss": 0.3983,
"step": 940
},
{
"epoch": 1.4148837209302325,
"grad_norm": 1.5686410800038224,
"learning_rate": 3.5866472865898326e-06,
"loss": 0.3947,
"step": 950
},
{
"epoch": 1.4297674418604651,
"grad_norm": 1.4681023810304712,
"learning_rate": 3.5481581258786783e-06,
"loss": 0.3923,
"step": 960
},
{
"epoch": 1.4446511627906977,
"grad_norm": 1.5058117091538117,
"learning_rate": 3.5093998882372038e-06,
"loss": 0.3888,
"step": 970
},
{
"epoch": 1.4595348837209303,
"grad_norm": 1.5292352650200591,
"learning_rate": 3.470385639932944e-06,
"loss": 0.3949,
"step": 980
},
{
"epoch": 1.474418604651163,
"grad_norm": 1.5178272188443236,
"learning_rate": 3.4311285335403495e-06,
"loss": 0.3928,
"step": 990
},
{
"epoch": 1.4893023255813953,
"grad_norm": 1.5454271963199493,
"learning_rate": 3.3916418035067527e-06,
"loss": 0.3912,
"step": 1000
},
{
"epoch": 1.504186046511628,
"grad_norm": 1.5155446625582503,
"learning_rate": 3.3519387616907477e-06,
"loss": 0.3938,
"step": 1010
},
{
"epoch": 1.5190697674418605,
"grad_norm": 1.4857502104949298,
"learning_rate": 3.312032792874458e-06,
"loss": 0.3911,
"step": 1020
},
{
"epoch": 1.5339534883720929,
"grad_norm": 1.5313728464277128,
"learning_rate": 3.2719373502512326e-06,
"loss": 0.3913,
"step": 1030
},
{
"epoch": 1.5488372093023255,
"grad_norm": 1.4680834760988197,
"learning_rate": 3.231665950890274e-06,
"loss": 0.3884,
"step": 1040
},
{
"epoch": 1.563720930232558,
"grad_norm": 1.4590605145952864,
"learning_rate": 3.1912321711797285e-06,
"loss": 0.3897,
"step": 1050
},
{
"epoch": 1.5786046511627907,
"grad_norm": 1.6407130925832443,
"learning_rate": 3.1506496422497856e-06,
"loss": 0.3926,
"step": 1060
},
{
"epoch": 1.5934883720930233,
"grad_norm": 1.600536994156853,
"learning_rate": 3.1099320453773195e-06,
"loss": 0.3918,
"step": 1070
},
{
"epoch": 1.608372093023256,
"grad_norm": 1.5393558781139518,
"learning_rate": 3.0690931073736233e-06,
"loss": 0.3849,
"step": 1080
},
{
"epoch": 1.6232558139534885,
"grad_norm": 1.477302583613782,
"learning_rate": 3.0281465959567974e-06,
"loss": 0.3926,
"step": 1090
},
{
"epoch": 1.6381395348837209,
"grad_norm": 1.6623553818348256,
"learning_rate": 2.9871063151103395e-06,
"loss": 0.3912,
"step": 1100
},
{
"epoch": 1.6530232558139535,
"grad_norm": 1.9690646932475977,
"learning_rate": 2.945986100429519e-06,
"loss": 0.3883,
"step": 1110
},
{
"epoch": 1.667906976744186,
"grad_norm": 1.8207999668811277,
"learning_rate": 2.9047998144570836e-06,
"loss": 0.3852,
"step": 1120
},
{
"epoch": 1.6827906976744185,
"grad_norm": 1.882433398444346,
"learning_rate": 2.8635613420098922e-06,
"loss": 0.389,
"step": 1130
},
{
"epoch": 1.697674418604651,
"grad_norm": 1.7892281887915626,
"learning_rate": 2.8222845854980257e-06,
"loss": 0.387,
"step": 1140
},
{
"epoch": 1.7125581395348837,
"grad_norm": 1.5794335002166047,
"learning_rate": 2.7809834602379822e-06,
"loss": 0.3883,
"step": 1150
},
{
"epoch": 1.7274418604651163,
"grad_norm": 1.5231365105574948,
"learning_rate": 2.739671889761507e-06,
"loss": 0.3889,
"step": 1160
},
{
"epoch": 1.7423255813953489,
"grad_norm": 1.5759952031593878,
"learning_rate": 2.698363801121661e-06,
"loss": 0.3824,
"step": 1170
},
{
"epoch": 1.7572093023255815,
"grad_norm": 1.6498265119319904,
"learning_rate": 2.657073120197702e-06,
"loss": 0.3874,
"step": 1180
},
{
"epoch": 1.772093023255814,
"grad_norm": 1.5972767247924684,
"learning_rate": 2.6158137670003563e-06,
"loss": 0.383,
"step": 1190
},
{
"epoch": 1.7869767441860465,
"grad_norm": 1.3189887482016291,
"learning_rate": 2.574599650979073e-06,
"loss": 0.382,
"step": 1200
},
{
"epoch": 1.801860465116279,
"grad_norm": 1.403465850397339,
"learning_rate": 2.5334446663328414e-06,
"loss": 0.3847,
"step": 1210
},
{
"epoch": 1.8167441860465117,
"grad_norm": 1.338762290831888,
"learning_rate": 2.492362687326143e-06,
"loss": 0.3836,
"step": 1220
},
{
"epoch": 1.831627906976744,
"grad_norm": 1.3565518289445442,
"learning_rate": 2.4513675636116257e-06,
"loss": 0.3848,
"step": 1230
},
{
"epoch": 1.8465116279069766,
"grad_norm": 1.4242607844677293,
"learning_rate": 2.4104731155610806e-06,
"loss": 0.3796,
"step": 1240
},
{
"epoch": 1.8613953488372093,
"grad_norm": 1.2675438338602558,
"learning_rate": 2.369693129606284e-06,
"loss": 0.3824,
"step": 1250
},
{
"epoch": 1.8762790697674419,
"grad_norm": 1.4458262899421106,
"learning_rate": 2.329041353591282e-06,
"loss": 0.3871,
"step": 1260
},
{
"epoch": 1.8911627906976745,
"grad_norm": 1.331432154246179,
"learning_rate": 2.288531492137687e-06,
"loss": 0.3805,
"step": 1270
},
{
"epoch": 1.906046511627907,
"grad_norm": 1.51201037304163,
"learning_rate": 2.248177202024544e-06,
"loss": 0.382,
"step": 1280
},
{
"epoch": 1.9209302325581397,
"grad_norm": 1.32189658216536,
"learning_rate": 2.207992087584323e-06,
"loss": 0.3807,
"step": 1290
},
{
"epoch": 1.935813953488372,
"grad_norm": 1.3385233652650261,
"learning_rate": 2.167989696116599e-06,
"loss": 0.3849,
"step": 1300
},
{
"epoch": 1.9506976744186046,
"grad_norm": 1.4812331676972927,
"learning_rate": 2.1281835133209493e-06,
"loss": 0.3823,
"step": 1310
},
{
"epoch": 1.9655813953488372,
"grad_norm": 1.2877441615477965,
"learning_rate": 2.0885869587506267e-06,
"loss": 0.3811,
"step": 1320
},
{
"epoch": 1.9804651162790696,
"grad_norm": 1.3833520048613848,
"learning_rate": 2.0492133812885277e-06,
"loss": 0.3784,
"step": 1330
},
{
"epoch": 1.9953488372093022,
"grad_norm": 1.4660482978156375,
"learning_rate": 2.0100760546469864e-06,
"loss": 0.3816,
"step": 1340
},
{
"epoch": 1.9983255813953489,
"eval_loss": 0.05558985471725464,
"eval_runtime": 459.9835,
"eval_samples_per_second": 39.356,
"eval_steps_per_second": 0.615,
"step": 1342
},
{
"epoch": 2.0111627906976746,
"grad_norm": 1.8852621531035139,
"learning_rate": 1.9711881728929063e-06,
"loss": 0.3147,
"step": 1350
},
{
"epoch": 2.026046511627907,
"grad_norm": 1.5742414705077779,
"learning_rate": 1.93256284599975e-06,
"loss": 0.2856,
"step": 1360
},
{
"epoch": 2.0409302325581393,
"grad_norm": 1.5835034555715797,
"learning_rate": 1.8942130954278742e-06,
"loss": 0.287,
"step": 1370
},
{
"epoch": 2.055813953488372,
"grad_norm": 1.4838228071676645,
"learning_rate": 1.8561518497346986e-06,
"loss": 0.2865,
"step": 1380
},
{
"epoch": 2.0706976744186045,
"grad_norm": 1.498870672430201,
"learning_rate": 1.8183919402162088e-06,
"loss": 0.2832,
"step": 1390
},
{
"epoch": 2.085581395348837,
"grad_norm": 1.541904110678706,
"learning_rate": 1.7809460965812341e-06,
"loss": 0.2869,
"step": 1400
},
{
"epoch": 2.1004651162790697,
"grad_norm": 1.4561848736193037,
"learning_rate": 1.7438269426599806e-06,
"loss": 0.2835,
"step": 1410
},
{
"epoch": 2.1153488372093023,
"grad_norm": 1.4220192506403004,
"learning_rate": 1.7070469921482557e-06,
"loss": 0.2814,
"step": 1420
},
{
"epoch": 2.130232558139535,
"grad_norm": 1.4385076328435982,
"learning_rate": 1.6706186443888218e-06,
"loss": 0.2853,
"step": 1430
},
{
"epoch": 2.1451162790697675,
"grad_norm": 1.6761700740327472,
"learning_rate": 1.6345541801912975e-06,
"loss": 0.2824,
"step": 1440
},
{
"epoch": 2.16,
"grad_norm": 1.4615800646871493,
"learning_rate": 1.598865757692033e-06,
"loss": 0.2838,
"step": 1450
},
{
"epoch": 2.1748837209302327,
"grad_norm": 1.5221607059340931,
"learning_rate": 1.5635654082553159e-06,
"loss": 0.2861,
"step": 1460
},
{
"epoch": 2.1897674418604653,
"grad_norm": 1.4695991331643223,
"learning_rate": 1.5286650324173402e-06,
"loss": 0.2815,
"step": 1470
},
{
"epoch": 2.2046511627906975,
"grad_norm": 1.5130331041622915,
"learning_rate": 1.49417639587427e-06,
"loss": 0.285,
"step": 1480
},
{
"epoch": 2.21953488372093,
"grad_norm": 1.4147707905859286,
"learning_rate": 1.4601111255157516e-06,
"loss": 0.2861,
"step": 1490
},
{
"epoch": 2.2344186046511627,
"grad_norm": 1.515339784306767,
"learning_rate": 1.426480705505238e-06,
"loss": 0.2864,
"step": 1500
},
{
"epoch": 2.2493023255813953,
"grad_norm": 1.343709147071654,
"learning_rate": 1.3932964734084178e-06,
"loss": 0.2859,
"step": 1510
},
{
"epoch": 2.264186046511628,
"grad_norm": 1.5685605135233283,
"learning_rate": 1.3605696163710685e-06,
"loss": 0.2851,
"step": 1520
},
{
"epoch": 2.2790697674418605,
"grad_norm": 1.3902994790791074,
"learning_rate": 1.3283111673476198e-06,
"loss": 0.2819,
"step": 1530
},
{
"epoch": 2.293953488372093,
"grad_norm": 1.4043809415014048,
"learning_rate": 1.2965320013816992e-06,
"loss": 0.284,
"step": 1540
},
{
"epoch": 2.3088372093023257,
"grad_norm": 1.3928586506764522,
"learning_rate": 1.2652428319399101e-06,
"loss": 0.2834,
"step": 1550
},
{
"epoch": 2.3237209302325583,
"grad_norm": 1.4659553086533261,
"learning_rate": 1.2344542073000847e-06,
"loss": 0.2847,
"step": 1560
},
{
"epoch": 2.3386046511627905,
"grad_norm": 1.422957011958867,
"learning_rate": 1.2041765069952232e-06,
"loss": 0.2819,
"step": 1570
},
{
"epoch": 2.353488372093023,
"grad_norm": 1.465284377414126,
"learning_rate": 1.1744199383143215e-06,
"loss": 0.2809,
"step": 1580
},
{
"epoch": 2.3683720930232557,
"grad_norm": 1.4400767691991236,
"learning_rate": 1.1451945328612658e-06,
"loss": 0.2834,
"step": 1590
},
{
"epoch": 2.3832558139534883,
"grad_norm": 1.3521728187942337,
"learning_rate": 1.1165101431729562e-06,
"loss": 0.282,
"step": 1600
},
{
"epoch": 2.398139534883721,
"grad_norm": 1.3847828855675668,
"learning_rate": 1.0883764393977927e-06,
"loss": 0.2825,
"step": 1610
},
{
"epoch": 2.4130232558139535,
"grad_norm": 1.3575203139903693,
"learning_rate": 1.0608029060356588e-06,
"loss": 0.2839,
"step": 1620
},
{
"epoch": 2.427906976744186,
"grad_norm": 1.4058947311018655,
"learning_rate": 1.0337988387404791e-06,
"loss": 0.2806,
"step": 1630
},
{
"epoch": 2.4427906976744187,
"grad_norm": 1.4641846648455186,
"learning_rate": 1.0073733411864462e-06,
"loss": 0.2829,
"step": 1640
},
{
"epoch": 2.4576744186046513,
"grad_norm": 1.3649324864016108,
"learning_rate": 9.815353219989754e-07,
"loss": 0.2827,
"step": 1650
},
{
"epoch": 2.472558139534884,
"grad_norm": 1.350449271286142,
"learning_rate": 9.562934917514021e-07,
"loss": 0.282,
"step": 1660
},
{
"epoch": 2.4874418604651165,
"grad_norm": 1.3972117947740512,
"learning_rate": 9.316563600284535e-07,
"loss": 0.2822,
"step": 1670
},
{
"epoch": 2.5023255813953487,
"grad_norm": 1.4565576079970999,
"learning_rate": 9.076322325574793e-07,
"loss": 0.2832,
"step": 1680
},
{
"epoch": 2.5172093023255813,
"grad_norm": 1.4043152891357864,
"learning_rate": 8.842292084084076e-07,
"loss": 0.2833,
"step": 1690
},
{
"epoch": 2.532093023255814,
"grad_norm": 1.3896394291435263,
"learning_rate": 8.614551772633615e-07,
"loss": 0.2832,
"step": 1700
},
{
"epoch": 2.5469767441860465,
"grad_norm": 1.4258374826387117,
"learning_rate": 8.393178167568755e-07,
"loss": 0.2827,
"step": 1710
},
{
"epoch": 2.561860465116279,
"grad_norm": 1.407749674891561,
"learning_rate": 8.178245898875936e-07,
"loss": 0.2825,
"step": 1720
},
{
"epoch": 2.5767441860465117,
"grad_norm": 1.413125902188421,
"learning_rate": 7.969827425023237e-07,
"loss": 0.2872,
"step": 1730
},
{
"epoch": 2.5916279069767443,
"grad_norm": 1.3473962411110556,
"learning_rate": 7.767993008533013e-07,
"loss": 0.2844,
"step": 1740
},
{
"epoch": 2.606511627906977,
"grad_norm": 1.404106793744438,
"learning_rate": 7.572810692294846e-07,
"loss": 0.2825,
"step": 1750
},
{
"epoch": 2.6213953488372095,
"grad_norm": 1.3805216307523198,
"learning_rate": 7.384346276626742e-07,
"loss": 0.2816,
"step": 1760
},
{
"epoch": 2.6362790697674416,
"grad_norm": 1.3718811044132653,
"learning_rate": 7.202663297092399e-07,
"loss": 0.2815,
"step": 1770
},
{
"epoch": 2.6511627906976747,
"grad_norm": 1.4225261849028261,
"learning_rate": 7.027823003081922e-07,
"loss": 0.2842,
"step": 1780
},
{
"epoch": 2.666046511627907,
"grad_norm": 1.4054086415352616,
"learning_rate": 6.859884337163317e-07,
"loss": 0.2825,
"step": 1790
},
{
"epoch": 2.6809302325581394,
"grad_norm": 1.4199694290168978,
"learning_rate": 6.698903915211616e-07,
"loss": 0.2813,
"step": 1800
},
{
"epoch": 2.695813953488372,
"grad_norm": 1.4944137400292614,
"learning_rate": 6.544936007322386e-07,
"loss": 0.2815,
"step": 1810
},
{
"epoch": 2.7106976744186047,
"grad_norm": 1.3783156351943808,
"learning_rate": 6.398032519516111e-07,
"loss": 0.2822,
"step": 1820
},
{
"epoch": 2.7255813953488373,
"grad_norm": 1.433571561201421,
"learning_rate": 6.258242976239481e-07,
"loss": 0.2838,
"step": 1830
},
{
"epoch": 2.74046511627907,
"grad_norm": 1.3514962485654185,
"learning_rate": 6.125614503669588e-07,
"loss": 0.2849,
"step": 1840
},
{
"epoch": 2.7553488372093025,
"grad_norm": 1.4597760031013953,
"learning_rate": 6.000191813826666e-07,
"loss": 0.2826,
"step": 1850
},
{
"epoch": 2.7702325581395346,
"grad_norm": 1.3371170140281539,
"learning_rate": 5.882017189500664e-07,
"loss": 0.282,
"step": 1860
},
{
"epoch": 2.7851162790697677,
"grad_norm": 1.3460302132963022,
"learning_rate": 5.771130469996746e-07,
"loss": 0.2817,
"step": 1870
},
{
"epoch": 2.8,
"grad_norm": 1.397811165218838,
"learning_rate": 5.667569037704612e-07,
"loss": 0.2806,
"step": 1880
},
{
"epoch": 2.8148837209302324,
"grad_norm": 1.3434330531321284,
"learning_rate": 5.571367805496029e-07,
"loss": 0.2828,
"step": 1890
},
{
"epoch": 2.829767441860465,
"grad_norm": 1.3531163030358948,
"learning_rate": 5.482559204954935e-07,
"loss": 0.2828,
"step": 1900
},
{
"epoch": 2.8446511627906976,
"grad_norm": 1.3428261741086946,
"learning_rate": 5.401173175444026e-07,
"loss": 0.281,
"step": 1910
},
{
"epoch": 2.8595348837209302,
"grad_norm": 1.3439493884557654,
"learning_rate": 5.327237154011533e-07,
"loss": 0.2811,
"step": 1920
},
{
"epoch": 2.874418604651163,
"grad_norm": 1.3575567573206913,
"learning_rate": 5.260776066141565e-07,
"loss": 0.2797,
"step": 1930
},
{
"epoch": 2.8893023255813954,
"grad_norm": 1.4000714352577568,
"learning_rate": 5.201812317351187e-07,
"loss": 0.2803,
"step": 1940
},
{
"epoch": 2.904186046511628,
"grad_norm": 1.3711991273663426,
"learning_rate": 5.150365785637017e-07,
"loss": 0.2798,
"step": 1950
},
{
"epoch": 2.9190697674418606,
"grad_norm": 1.373654423872898,
"learning_rate": 5.106453814773902e-07,
"loss": 0.2776,
"step": 1960
},
{
"epoch": 2.933953488372093,
"grad_norm": 1.3534625494022425,
"learning_rate": 5.070091208467953e-07,
"loss": 0.2835,
"step": 1970
},
{
"epoch": 2.948837209302326,
"grad_norm": 1.3254134088824696,
"learning_rate": 5.041290225365879e-07,
"loss": 0.2809,
"step": 1980
},
{
"epoch": 2.963720930232558,
"grad_norm": 1.306976854112462,
"learning_rate": 5.020060574922324e-07,
"loss": 0.279,
"step": 1990
},
{
"epoch": 2.9786046511627906,
"grad_norm": 1.3107886288482267,
"learning_rate": 5.006409414126598e-07,
"loss": 0.2807,
"step": 2000
},
{
"epoch": 2.993488372093023,
"grad_norm": 1.3832142175918538,
"learning_rate": 5.000341345089891e-07,
"loss": 0.2796,
"step": 2010
},
{
"epoch": 2.997953488372093,
"eval_loss": 0.05797627940773964,
"eval_runtime": 449.2792,
"eval_samples_per_second": 40.293,
"eval_steps_per_second": 0.63,
"step": 2013
},
{
"epoch": 2.997953488372093,
"step": 2013,
"total_flos": 3371640595415040.0,
"train_loss": 0.40245939461792873,
"train_runtime": 65376.8125,
"train_samples_per_second": 15.783,
"train_steps_per_second": 0.031
}
],
"logging_steps": 10,
"max_steps": 2013,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 3371640595415040.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}