{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23392692918652286,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000836050497450046,
      "grad_norm": 5.8952789306640625,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.5346,
      "step": 10
    },
    {
      "epoch": 0.001672100994900092,
      "grad_norm": 2.239838123321533,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.3887,
      "step": 20
    },
    {
      "epoch": 0.002508151492350138,
      "grad_norm": 1.8720221519470215,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.2524,
      "step": 30
    },
    {
      "epoch": 0.003344201989800184,
      "grad_norm": 1.1449085474014282,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.0681,
      "step": 40
    },
    {
      "epoch": 0.0041802524872502295,
      "grad_norm": 1.360563039779663,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.8906,
      "step": 50
    },
    {
      "epoch": 0.005016302984700276,
      "grad_norm": 0.8737388849258423,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.8052,
      "step": 60
    },
    {
      "epoch": 0.005852353482150322,
      "grad_norm": 0.50184565782547,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.7827,
      "step": 70
    },
    {
      "epoch": 0.006688403979600368,
      "grad_norm": 0.4593908190727234,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.7758,
      "step": 80
    },
    {
      "epoch": 0.007524454477050414,
      "grad_norm": 0.5259537100791931,
      "learning_rate": 1.005e-05,
      "loss": 0.7545,
      "step": 90
    },
    {
      "epoch": 0.008360504974500459,
      "grad_norm": 0.5117310285568237,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.7779,
      "step": 100
    },
    {
      "epoch": 0.009196555471950505,
      "grad_norm": 0.46054765582084656,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7623,
      "step": 110
    },
    {
      "epoch": 0.010032605969400551,
      "grad_norm": 0.6909846067428589,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.7352,
      "step": 120
    },
    {
      "epoch": 0.010868656466850597,
      "grad_norm": 0.4003996253013611,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.7429,
      "step": 130
    },
    {
      "epoch": 0.011704706964300643,
      "grad_norm": 0.47065919637680054,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.7416,
      "step": 140
    },
    {
      "epoch": 0.01254075746175069,
      "grad_norm": 0.5040171146392822,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.7821,
      "step": 150
    },
    {
      "epoch": 0.013376807959200735,
      "grad_norm": 0.396039217710495,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.6167,
      "step": 160
    },
    {
      "epoch": 0.014212858456650782,
      "grad_norm": 0.42775487899780273,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.703,
      "step": 170
    },
    {
      "epoch": 0.015048908954100828,
      "grad_norm": 0.5157128572463989,
      "learning_rate": 2e-05,
      "loss": 0.7219,
      "step": 180
    },
    {
      "epoch": 0.015884959451550874,
      "grad_norm": 0.5191335082054138,
      "learning_rate": 2e-05,
      "loss": 0.6895,
      "step": 190
    },
    {
      "epoch": 0.016721009949000918,
      "grad_norm": 0.44552481174468994,
      "learning_rate": 2e-05,
      "loss": 0.7773,
      "step": 200
    },
    {
      "epoch": 0.017557060446450966,
      "grad_norm": 0.3954372704029083,
      "learning_rate": 2e-05,
      "loss": 0.7441,
      "step": 210
    },
    {
      "epoch": 0.01839311094390101,
      "grad_norm": 0.45830389857292175,
      "learning_rate": 2e-05,
      "loss": 0.7504,
      "step": 220
    },
    {
      "epoch": 0.019229161441351058,
      "grad_norm": 0.4249721169471741,
      "learning_rate": 2e-05,
      "loss": 0.7186,
      "step": 230
    },
    {
      "epoch": 0.020065211938801102,
      "grad_norm": 0.4513215720653534,
      "learning_rate": 2e-05,
      "loss": 0.745,
      "step": 240
    },
    {
      "epoch": 0.02090126243625115,
      "grad_norm": 0.43894580006599426,
      "learning_rate": 2e-05,
      "loss": 0.76,
      "step": 250
    },
    {
      "epoch": 0.021737312933701194,
      "grad_norm": 7.123316287994385,
      "learning_rate": 2e-05,
      "loss": 0.7635,
      "step": 260
    },
    {
      "epoch": 0.022573363431151242,
      "grad_norm": 0.4213659465312958,
      "learning_rate": 2e-05,
      "loss": 0.7474,
      "step": 270
    },
    {
      "epoch": 0.023409413928601287,
      "grad_norm": 0.4028798043727875,
      "learning_rate": 2e-05,
      "loss": 0.7168,
      "step": 280
    },
    {
      "epoch": 0.024245464426051334,
      "grad_norm": 0.3978917598724365,
      "learning_rate": 2e-05,
      "loss": 0.7272,
      "step": 290
    },
    {
      "epoch": 0.02508151492350138,
      "grad_norm": 0.45915454626083374,
      "learning_rate": 2e-05,
      "loss": 0.7791,
      "step": 300
    },
    {
      "epoch": 0.025917565420951427,
      "grad_norm": 0.44984596967697144,
      "learning_rate": 2e-05,
      "loss": 0.7934,
      "step": 310
    },
    {
      "epoch": 0.02675361591840147,
      "grad_norm": 0.43878060579299927,
      "learning_rate": 2e-05,
      "loss": 0.7644,
      "step": 320
    },
    {
      "epoch": 0.02758966641585152,
      "grad_norm": 0.4639083743095398,
      "learning_rate": 2e-05,
      "loss": 0.7801,
      "step": 330
    },
    {
      "epoch": 0.028425716913301563,
      "grad_norm": 0.43591466546058655,
      "learning_rate": 2e-05,
      "loss": 0.7261,
      "step": 340
    },
    {
      "epoch": 0.02926176741075161,
      "grad_norm": 0.5230687260627747,
      "learning_rate": 2e-05,
      "loss": 0.7732,
      "step": 350
    },
    {
      "epoch": 0.030097817908201655,
      "grad_norm": 0.4230197072029114,
      "learning_rate": 2e-05,
      "loss": 0.7576,
      "step": 360
    },
    {
      "epoch": 0.030933868405651703,
      "grad_norm": 0.44197097420692444,
      "learning_rate": 2e-05,
      "loss": 0.7232,
      "step": 370
    },
    {
      "epoch": 0.03176991890310175,
      "grad_norm": 0.4144206643104553,
      "learning_rate": 2e-05,
      "loss": 0.7316,
      "step": 380
    },
    {
      "epoch": 0.03260596940055179,
      "grad_norm": 0.4325674772262573,
      "learning_rate": 2e-05,
      "loss": 0.7103,
      "step": 390
    },
    {
      "epoch": 0.033442019898001836,
      "grad_norm": 0.3876762390136719,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 400
    },
    {
      "epoch": 0.03427807039545189,
      "grad_norm": 0.4181121587753296,
      "learning_rate": 2e-05,
      "loss": 0.7415,
      "step": 410
    },
    {
      "epoch": 0.03511412089290193,
      "grad_norm": 0.6723706722259521,
      "learning_rate": 2e-05,
      "loss": 0.7408,
      "step": 420
    },
    {
      "epoch": 0.035950171390351976,
      "grad_norm": 0.42723605036735535,
      "learning_rate": 2e-05,
      "loss": 0.7381,
      "step": 430
    },
    {
      "epoch": 0.03678622188780202,
      "grad_norm": 0.40303024649620056,
      "learning_rate": 2e-05,
      "loss": 0.7108,
      "step": 440
    },
    {
      "epoch": 0.03762227238525207,
      "grad_norm": 0.4335564076900482,
      "learning_rate": 2e-05,
      "loss": 0.7368,
      "step": 450
    },
    {
      "epoch": 0.038458322882702116,
      "grad_norm": 0.4370777904987335,
      "learning_rate": 2e-05,
      "loss": 0.7813,
      "step": 460
    },
    {
      "epoch": 0.03929437338015216,
      "grad_norm": 0.4104174077510834,
      "learning_rate": 2e-05,
      "loss": 0.7359,
      "step": 470
    },
    {
      "epoch": 0.040130423877602205,
      "grad_norm": 0.4259282946586609,
      "learning_rate": 2e-05,
      "loss": 0.7206,
      "step": 480
    },
    {
      "epoch": 0.040966474375052256,
      "grad_norm": 0.39744478464126587,
      "learning_rate": 2e-05,
      "loss": 0.7245,
      "step": 490
    },
    {
      "epoch": 0.0418025248725023,
      "grad_norm": 0.42015591263771057,
      "learning_rate": 2e-05,
      "loss": 0.7416,
      "step": 500
    },
    {
      "epoch": 0.042638575369952345,
      "grad_norm": 0.379894882440567,
      "learning_rate": 2e-05,
      "loss": 0.7315,
      "step": 510
    },
    {
      "epoch": 0.04347462586740239,
      "grad_norm": 0.4095825254917145,
      "learning_rate": 2e-05,
      "loss": 0.7185,
      "step": 520
    },
    {
      "epoch": 0.04431067636485244,
      "grad_norm": 0.4044616222381592,
      "learning_rate": 2e-05,
      "loss": 0.7443,
      "step": 530
    },
    {
      "epoch": 0.045146726862302484,
      "grad_norm": 0.4145281910896301,
      "learning_rate": 2e-05,
      "loss": 0.7009,
      "step": 540
    },
    {
      "epoch": 0.04598277735975253,
      "grad_norm": 0.6660082936286926,
      "learning_rate": 2e-05,
      "loss": 0.7139,
      "step": 550
    },
    {
      "epoch": 0.04681882785720257,
      "grad_norm": 0.39196470379829407,
      "learning_rate": 2e-05,
      "loss": 0.6958,
      "step": 560
    },
    {
      "epoch": 0.047654878354652624,
      "grad_norm": 0.39314568042755127,
      "learning_rate": 2e-05,
      "loss": 0.7562,
      "step": 570
    },
    {
      "epoch": 0.04849092885210267,
      "grad_norm": 0.4184809923171997,
      "learning_rate": 2e-05,
      "loss": 0.7281,
      "step": 580
    },
    {
      "epoch": 0.04932697934955271,
      "grad_norm": 0.4390700161457062,
      "learning_rate": 2e-05,
      "loss": 0.7206,
      "step": 590
    },
    {
      "epoch": 0.05016302984700276,
      "grad_norm": 0.39948198199272156,
      "learning_rate": 2e-05,
      "loss": 0.7311,
      "step": 600
    },
    {
      "epoch": 0.0509990803444528,
      "grad_norm": 0.3739895820617676,
      "learning_rate": 2e-05,
      "loss": 0.7089,
      "step": 610
    },
    {
      "epoch": 0.05183513084190285,
      "grad_norm": 0.37271761894226074,
      "learning_rate": 2e-05,
      "loss": 0.7092,
      "step": 620
    },
    {
      "epoch": 0.0526711813393529,
      "grad_norm": 0.404062420129776,
      "learning_rate": 2e-05,
      "loss": 0.6953,
      "step": 630
    },
    {
      "epoch": 0.05350723183680294,
      "grad_norm": 0.4164421260356903,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 640
    },
    {
      "epoch": 0.054343282334252986,
      "grad_norm": 0.4303136169910431,
      "learning_rate": 2e-05,
      "loss": 0.7299,
      "step": 650
    },
    {
      "epoch": 0.05517933283170304,
      "grad_norm": 0.4234829843044281,
      "learning_rate": 2e-05,
      "loss": 0.7442,
      "step": 660
    },
    {
      "epoch": 0.05601538332915308,
      "grad_norm": 0.3876648545265198,
      "learning_rate": 2e-05,
      "loss": 0.7146,
      "step": 670
    },
    {
      "epoch": 0.056851433826603126,
      "grad_norm": 0.4167863726615906,
      "learning_rate": 2e-05,
      "loss": 0.7098,
      "step": 680
    },
    {
      "epoch": 0.05768748432405317,
      "grad_norm": 0.44938138127326965,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 690
    },
    {
      "epoch": 0.05852353482150322,
      "grad_norm": 0.4265012741088867,
      "learning_rate": 2e-05,
      "loss": 0.7091,
      "step": 700
    },
    {
      "epoch": 0.059359585318953266,
      "grad_norm": 0.42332151532173157,
      "learning_rate": 2e-05,
      "loss": 0.7499,
      "step": 710
    },
    {
      "epoch": 0.06019563581640331,
      "grad_norm": 0.4157474637031555,
      "learning_rate": 2e-05,
      "loss": 0.6786,
      "step": 720
    },
    {
      "epoch": 0.061031686313853355,
      "grad_norm": 0.370686799287796,
      "learning_rate": 2e-05,
      "loss": 0.7323,
      "step": 730
    },
    {
      "epoch": 0.061867736811303406,
      "grad_norm": 0.3953830599784851,
      "learning_rate": 2e-05,
      "loss": 0.7309,
      "step": 740
    },
    {
      "epoch": 0.06270378730875345,
      "grad_norm": 0.40635451674461365,
      "learning_rate": 2e-05,
      "loss": 0.732,
      "step": 750
    },
    {
      "epoch": 0.0635398378062035,
      "grad_norm": 0.4116203486919403,
      "learning_rate": 2e-05,
      "loss": 0.718,
      "step": 760
    },
    {
      "epoch": 0.06437588830365354,
      "grad_norm": 0.3634946048259735,
      "learning_rate": 2e-05,
      "loss": 0.679,
      "step": 770
    },
    {
      "epoch": 0.06521193880110358,
      "grad_norm": 0.4082890450954437,
      "learning_rate": 2e-05,
      "loss": 0.687,
      "step": 780
    },
    {
      "epoch": 0.06604798929855363,
      "grad_norm": 0.4118865728378296,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 790
    },
    {
      "epoch": 0.06688403979600367,
      "grad_norm": 0.40019503235816956,
      "learning_rate": 2e-05,
      "loss": 0.7234,
      "step": 800
    },
    {
      "epoch": 0.06772009029345373,
      "grad_norm": 0.41497135162353516,
      "learning_rate": 2e-05,
      "loss": 0.7026,
      "step": 810
    },
    {
      "epoch": 0.06855614079090377,
      "grad_norm": 0.37976041436195374,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 820
    },
    {
      "epoch": 0.06939219128835382,
      "grad_norm": 0.4239822030067444,
      "learning_rate": 2e-05,
      "loss": 0.7123,
      "step": 830
    },
    {
      "epoch": 0.07022824178580386,
      "grad_norm": 0.40763989090919495,
      "learning_rate": 2e-05,
      "loss": 0.6923,
      "step": 840
    },
    {
      "epoch": 0.07106429228325391,
      "grad_norm": 0.40808385610580444,
      "learning_rate": 2e-05,
      "loss": 0.7095,
      "step": 850
    },
    {
      "epoch": 0.07190034278070395,
      "grad_norm": 0.44947150349617004,
      "learning_rate": 2e-05,
      "loss": 0.7188,
      "step": 860
    },
    {
      "epoch": 0.072736393278154,
      "grad_norm": 0.3837183713912964,
      "learning_rate": 2e-05,
      "loss": 0.7442,
      "step": 870
    },
    {
      "epoch": 0.07357244377560404,
      "grad_norm": 0.4867953956127167,
      "learning_rate": 2e-05,
      "loss": 0.717,
      "step": 880
    },
    {
      "epoch": 0.0744084942730541,
      "grad_norm": 0.4862518310546875,
      "learning_rate": 2e-05,
      "loss": 0.6994,
      "step": 890
    },
    {
      "epoch": 0.07524454477050414,
      "grad_norm": 0.4381377398967743,
      "learning_rate": 2e-05,
      "loss": 0.7172,
      "step": 900
    },
    {
      "epoch": 0.07608059526795419,
      "grad_norm": 0.44232502579689026,
      "learning_rate": 2e-05,
      "loss": 0.7078,
      "step": 910
    },
    {
      "epoch": 0.07691664576540423,
      "grad_norm": 0.39795035123825073,
      "learning_rate": 2e-05,
      "loss": 0.7007,
      "step": 920
    },
    {
      "epoch": 0.07775269626285428,
      "grad_norm": 0.3873278796672821,
      "learning_rate": 2e-05,
      "loss": 0.7302,
      "step": 930
    },
    {
      "epoch": 0.07858874676030432,
      "grad_norm": 0.4043973684310913,
      "learning_rate": 2e-05,
      "loss": 0.7497,
      "step": 940
    },
    {
      "epoch": 0.07942479725775436,
      "grad_norm": 0.43075886368751526,
      "learning_rate": 2e-05,
      "loss": 0.726,
      "step": 950
    },
    {
      "epoch": 0.08026084775520441,
      "grad_norm": 0.4056244492530823,
      "learning_rate": 2e-05,
      "loss": 0.6807,
      "step": 960
    },
    {
      "epoch": 0.08109689825265445,
      "grad_norm": 0.4083726406097412,
      "learning_rate": 2e-05,
      "loss": 0.718,
      "step": 970
    },
    {
      "epoch": 0.08193294875010451,
      "grad_norm": 0.4576243460178375,
      "learning_rate": 2e-05,
      "loss": 0.6996,
      "step": 980
    },
    {
      "epoch": 0.08276899924755456,
      "grad_norm": 0.41480258107185364,
      "learning_rate": 2e-05,
      "loss": 0.6787,
      "step": 990
    },
    {
      "epoch": 0.0836050497450046,
      "grad_norm": 0.38216501474380493,
      "learning_rate": 2e-05,
      "loss": 0.7211,
      "step": 1000
    },
    {
      "epoch": 0.08444110024245464,
      "grad_norm": 0.37291425466537476,
      "learning_rate": 2e-05,
      "loss": 0.7013,
      "step": 1010
    },
    {
      "epoch": 0.08527715073990469,
      "grad_norm": 0.44588473439216614,
      "learning_rate": 2e-05,
      "loss": 0.7362,
      "step": 1020
    },
    {
      "epoch": 0.08611320123735473,
      "grad_norm": 0.38740336894989014,
      "learning_rate": 2e-05,
      "loss": 0.7268,
      "step": 1030
    },
    {
      "epoch": 0.08694925173480478,
      "grad_norm": 0.3775883913040161,
      "learning_rate": 2e-05,
      "loss": 0.693,
      "step": 1040
    },
    {
      "epoch": 0.08778530223225482,
      "grad_norm": 0.4709722399711609,
      "learning_rate": 2e-05,
      "loss": 0.731,
      "step": 1050
    },
    {
      "epoch": 0.08862135272970488,
      "grad_norm": 0.4146833121776581,
      "learning_rate": 2e-05,
      "loss": 0.7448,
      "step": 1060
    },
    {
      "epoch": 0.08945740322715492,
      "grad_norm": 0.39623764157295227,
      "learning_rate": 2e-05,
      "loss": 0.6927,
      "step": 1070
    },
    {
      "epoch": 0.09029345372460497,
      "grad_norm": 0.3726375102996826,
      "learning_rate": 2e-05,
      "loss": 0.7264,
      "step": 1080
    },
    {
      "epoch": 0.09112950422205501,
      "grad_norm": 0.3898238241672516,
      "learning_rate": 2e-05,
      "loss": 0.6968,
      "step": 1090
    },
    {
      "epoch": 0.09196555471950506,
      "grad_norm": 0.3660300076007843,
      "learning_rate": 2e-05,
      "loss": 0.7464,
      "step": 1100
    },
    {
      "epoch": 0.0928016052169551,
      "grad_norm": 0.43982595205307007,
      "learning_rate": 2e-05,
      "loss": 0.7031,
      "step": 1110
    },
    {
      "epoch": 0.09363765571440515,
      "grad_norm": 0.41887497901916504,
      "learning_rate": 2e-05,
      "loss": 0.6931,
      "step": 1120
    },
    {
      "epoch": 0.09447370621185519,
      "grad_norm": 0.3669204115867615,
      "learning_rate": 2e-05,
      "loss": 0.7256,
      "step": 1130
    },
    {
      "epoch": 0.09530975670930525,
      "grad_norm": 0.39729389548301697,
      "learning_rate": 2e-05,
      "loss": 0.7253,
      "step": 1140
    },
    {
      "epoch": 0.0961458072067553,
      "grad_norm": 0.3818066418170929,
      "learning_rate": 2e-05,
      "loss": 0.6842,
      "step": 1150
    },
    {
      "epoch": 0.09698185770420534,
      "grad_norm": 0.3896878659725189,
      "learning_rate": 2e-05,
      "loss": 0.6928,
      "step": 1160
    },
    {
      "epoch": 0.09781790820165538,
      "grad_norm": 0.37976863980293274,
      "learning_rate": 2e-05,
      "loss": 0.7184,
      "step": 1170
    },
    {
      "epoch": 0.09865395869910543,
      "grad_norm": 0.37471631169319153,
      "learning_rate": 2e-05,
      "loss": 0.6839,
      "step": 1180
    },
    {
      "epoch": 0.09949000919655547,
      "grad_norm": 0.3750368356704712,
      "learning_rate": 2e-05,
      "loss": 0.693,
      "step": 1190
    },
    {
      "epoch": 0.10032605969400551,
      "grad_norm": 0.37220221757888794,
      "learning_rate": 2e-05,
      "loss": 0.7175,
      "step": 1200
    },
    {
      "epoch": 0.10116211019145556,
      "grad_norm": 0.407367080450058,
      "learning_rate": 2e-05,
      "loss": 0.706,
      "step": 1210
    },
    {
      "epoch": 0.1019981606889056,
      "grad_norm": 0.35999026894569397,
      "learning_rate": 2e-05,
      "loss": 0.7197,
      "step": 1220
    },
    {
      "epoch": 0.10283421118635566,
      "grad_norm": 0.36594730615615845,
      "learning_rate": 2e-05,
      "loss": 0.6944,
      "step": 1230
    },
    {
      "epoch": 0.1036702616838057,
      "grad_norm": 0.3911300301551819,
      "learning_rate": 2e-05,
      "loss": 0.7117,
      "step": 1240
    },
    {
      "epoch": 0.10450631218125575,
      "grad_norm": 0.4042055010795593,
      "learning_rate": 2e-05,
      "loss": 0.7157,
      "step": 1250
    },
    {
      "epoch": 0.1053423626787058,
      "grad_norm": 0.4203055500984192,
      "learning_rate": 2e-05,
      "loss": 0.7426,
      "step": 1260
    },
    {
      "epoch": 0.10617841317615584,
      "grad_norm": 0.3811381459236145,
      "learning_rate": 2e-05,
      "loss": 0.699,
      "step": 1270
    },
    {
      "epoch": 0.10701446367360588,
      "grad_norm": 0.35855522751808167,
      "learning_rate": 2e-05,
      "loss": 0.7526,
      "step": 1280
    },
    {
      "epoch": 0.10785051417105593,
      "grad_norm": 0.3886844217777252,
      "learning_rate": 2e-05,
      "loss": 0.7052,
      "step": 1290
    },
    {
      "epoch": 0.10868656466850597,
      "grad_norm": 0.3775457739830017,
      "learning_rate": 2e-05,
      "loss": 0.71,
      "step": 1300
    },
    {
      "epoch": 0.10952261516595603,
      "grad_norm": 0.4011971652507782,
      "learning_rate": 2e-05,
      "loss": 0.6869,
      "step": 1310
    },
    {
      "epoch": 0.11035866566340607,
      "grad_norm": 0.40073534846305847,
      "learning_rate": 2e-05,
      "loss": 0.7294,
      "step": 1320
    },
    {
      "epoch": 0.11119471616085612,
      "grad_norm": 0.6666777729988098,
      "learning_rate": 2e-05,
      "loss": 0.7135,
      "step": 1330
    },
    {
      "epoch": 0.11203076665830616,
      "grad_norm": 0.40671786665916443,
      "learning_rate": 2e-05,
      "loss": 0.7055,
      "step": 1340
    },
    {
      "epoch": 0.11286681715575621,
      "grad_norm": 0.35212790966033936,
      "learning_rate": 2e-05,
      "loss": 0.7068,
      "step": 1350
    },
    {
      "epoch": 0.11370286765320625,
      "grad_norm": 0.39304518699645996,
      "learning_rate": 2e-05,
      "loss": 0.7132,
      "step": 1360
    },
    {
      "epoch": 0.1145389181506563,
      "grad_norm": 0.40921252965927124,
      "learning_rate": 2e-05,
      "loss": 0.7149,
      "step": 1370
    },
    {
      "epoch": 0.11537496864810634,
      "grad_norm": 0.3641948401927948,
      "learning_rate": 2e-05,
      "loss": 0.6947,
      "step": 1380
    },
    {
      "epoch": 0.11621101914555639,
      "grad_norm": 0.3776053786277771,
      "learning_rate": 2e-05,
      "loss": 0.7098,
      "step": 1390
    },
    {
      "epoch": 0.11704706964300644,
      "grad_norm": 0.40454384684562683,
      "learning_rate": 2e-05,
      "loss": 0.6876,
      "step": 1400
    },
    {
      "epoch": 0.11788312014045649,
      "grad_norm": 0.3694128692150116,
      "learning_rate": 2e-05,
      "loss": 0.7112,
      "step": 1410
    },
    {
      "epoch": 0.11871917063790653,
      "grad_norm": 0.4031735956668854,
      "learning_rate": 2e-05,
      "loss": 0.6743,
      "step": 1420
    },
    {
      "epoch": 0.11955522113535658,
      "grad_norm": 0.36599618196487427,
      "learning_rate": 2e-05,
      "loss": 0.7177,
      "step": 1430
    },
    {
      "epoch": 0.12039127163280662,
      "grad_norm": 0.3794446587562561,
      "learning_rate": 2e-05,
      "loss": 0.7672,
      "step": 1440
    },
    {
      "epoch": 0.12122732213025667,
      "grad_norm": 0.42689165472984314,
      "learning_rate": 2e-05,
      "loss": 0.6943,
      "step": 1450
    },
    {
      "epoch": 0.12206337262770671,
      "grad_norm": 0.39176973700523376,
      "learning_rate": 2e-05,
      "loss": 0.7454,
      "step": 1460
    },
    {
      "epoch": 0.12289942312515675,
      "grad_norm": 0.38585641980171204,
      "learning_rate": 2e-05,
      "loss": 0.6796,
      "step": 1470
    },
    {
      "epoch": 0.12373547362260681,
      "grad_norm": 0.3828059434890747,
      "learning_rate": 2e-05,
      "loss": 0.7162,
      "step": 1480
    },
    {
      "epoch": 0.12457152412005686,
      "grad_norm": 0.36190828680992126,
      "learning_rate": 2e-05,
      "loss": 0.7189,
      "step": 1490
    },
    {
      "epoch": 0.1254075746175069,
      "grad_norm": 0.35898563265800476,
      "learning_rate": 2e-05,
      "loss": 0.6823,
      "step": 1500
    },
    {
      "epoch": 0.12624362511495693,
      "grad_norm": 0.3842126429080963,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 1510
    },
    {
      "epoch": 0.127079675612407,
      "grad_norm": 0.38555908203125,
      "learning_rate": 2e-05,
      "loss": 0.6886,
      "step": 1520
    },
    {
      "epoch": 0.12791572610985705,
      "grad_norm": 0.41499239206314087,
      "learning_rate": 2e-05,
      "loss": 0.7005,
      "step": 1530
    },
    {
      "epoch": 0.12875177660730708,
      "grad_norm": 0.3923279345035553,
      "learning_rate": 2e-05,
      "loss": 0.6807,
      "step": 1540
    },
    {
      "epoch": 0.12958782710475714,
      "grad_norm": 0.38119590282440186,
      "learning_rate": 2e-05,
      "loss": 0.7245,
      "step": 1550
    },
    {
      "epoch": 0.13042387760220717,
      "grad_norm": 0.44171908497810364,
      "learning_rate": 2e-05,
      "loss": 0.711,
      "step": 1560
    },
    {
      "epoch": 0.13125992809965722,
      "grad_norm": 0.3561314642429352,
      "learning_rate": 2e-05,
      "loss": 0.7106,
      "step": 1570
    },
    {
      "epoch": 0.13209597859710726,
      "grad_norm": 0.44831010699272156,
      "learning_rate": 2e-05,
      "loss": 0.7118,
      "step": 1580
    },
    {
      "epoch": 0.1329320290945573,
      "grad_norm": 0.42015114426612854,
      "learning_rate": 2e-05,
      "loss": 0.7072,
      "step": 1590
    },
    {
      "epoch": 0.13376807959200734,
      "grad_norm": 0.4430758059024811,
      "learning_rate": 2e-05,
      "loss": 0.7187,
      "step": 1600
    },
    {
      "epoch": 0.1346041300894574,
      "grad_norm": 0.37224727869033813,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 1610
    },
    {
      "epoch": 0.13544018058690746,
      "grad_norm": 0.3727637529373169,
      "learning_rate": 2e-05,
      "loss": 0.7151,
      "step": 1620
    },
    {
      "epoch": 0.1362762310843575,
      "grad_norm": 0.36329200863838196,
      "learning_rate": 2e-05,
      "loss": 0.7359,
      "step": 1630
    },
    {
      "epoch": 0.13711228158180755,
      "grad_norm": 0.36346569657325745,
      "learning_rate": 2e-05,
      "loss": 0.689,
      "step": 1640
    },
    {
      "epoch": 0.13794833207925758,
      "grad_norm": 0.3709527254104614,
      "learning_rate": 2e-05,
      "loss": 0.7124,
      "step": 1650
    },
    {
      "epoch": 0.13878438257670764,
      "grad_norm": 0.41566887497901917,
      "learning_rate": 2e-05,
      "loss": 0.708,
      "step": 1660
    },
    {
      "epoch": 0.13962043307415767,
      "grad_norm": 0.3450981378555298,
      "learning_rate": 2e-05,
      "loss": 0.7007,
      "step": 1670
    },
    {
      "epoch": 0.14045648357160773,
      "grad_norm": 0.3517451584339142,
      "learning_rate": 2e-05,
      "loss": 0.7031,
      "step": 1680
    },
    {
      "epoch": 0.14129253406905778,
      "grad_norm": 0.400630384683609,
      "learning_rate": 2e-05,
      "loss": 0.7124,
      "step": 1690
    },
    {
      "epoch": 0.14212858456650782,
      "grad_norm": 0.4013160765171051,
      "learning_rate": 2e-05,
      "loss": 0.7085,
      "step": 1700
    },
    {
      "epoch": 0.14296463506395787,
      "grad_norm": 0.3802119791507721,
      "learning_rate": 2e-05,
      "loss": 0.7056,
      "step": 1710
    },
    {
      "epoch": 0.1438006855614079,
      "grad_norm": 0.4005148112773895,
      "learning_rate": 2e-05,
      "loss": 0.7065,
      "step": 1720
    },
    {
      "epoch": 0.14463673605885796,
      "grad_norm": 0.36928942799568176,
      "learning_rate": 2e-05,
      "loss": 0.6813,
      "step": 1730
    },
    {
      "epoch": 0.145472786556308,
      "grad_norm": 0.37812256813049316,
      "learning_rate": 2e-05,
      "loss": 0.7049,
      "step": 1740
    },
    {
      "epoch": 0.14630883705375805,
      "grad_norm": 0.3583225607872009,
      "learning_rate": 2e-05,
      "loss": 0.7184,
      "step": 1750
    },
    {
      "epoch": 0.14714488755120808,
      "grad_norm": 0.3970085680484772,
      "learning_rate": 2e-05,
      "loss": 0.6873,
      "step": 1760
    },
    {
      "epoch": 0.14798093804865814,
      "grad_norm": 0.38219332695007324,
      "learning_rate": 2e-05,
      "loss": 0.6963,
      "step": 1770
    },
    {
      "epoch": 0.1488169885461082,
      "grad_norm": 0.362723171710968,
      "learning_rate": 2e-05,
      "loss": 0.7162,
      "step": 1780
    },
    {
      "epoch": 0.14965303904355823,
      "grad_norm": 0.43519818782806396,
      "learning_rate": 2e-05,
      "loss": 0.7274,
      "step": 1790
    },
    {
      "epoch": 0.1504890895410083,
      "grad_norm": 0.36672765016555786,
      "learning_rate": 2e-05,
      "loss": 0.746,
      "step": 1800
    },
    {
      "epoch": 0.15132514003845832,
      "grad_norm": 0.34433141350746155,
      "learning_rate": 2e-05,
      "loss": 0.6847,
      "step": 1810
    },
    {
      "epoch": 0.15216119053590837,
      "grad_norm": 0.3767019510269165,
      "learning_rate": 2e-05,
      "loss": 0.7217,
      "step": 1820
    },
    {
      "epoch": 0.1529972410333584,
      "grad_norm": 0.3689115047454834,
      "learning_rate": 2e-05,
      "loss": 0.7378,
      "step": 1830
    },
    {
      "epoch": 0.15383329153080846,
      "grad_norm": 0.36576899886131287,
      "learning_rate": 2e-05,
      "loss": 0.7198,
      "step": 1840
    },
    {
      "epoch": 0.1546693420282585,
      "grad_norm": 0.4920649230480194,
      "learning_rate": 2e-05,
      "loss": 0.6827,
      "step": 1850
    },
    {
      "epoch": 0.15550539252570855,
      "grad_norm": 0.35931605100631714,
      "learning_rate": 2e-05,
      "loss": 0.7097,
      "step": 1860
    },
    {
      "epoch": 0.1563414430231586,
      "grad_norm": 0.36113813519477844,
      "learning_rate": 2e-05,
      "loss": 0.7307,
      "step": 1870
    },
    {
      "epoch": 0.15717749352060864,
      "grad_norm": 0.3809521496295929,
      "learning_rate": 2e-05,
      "loss": 0.7038,
      "step": 1880
    },
    {
      "epoch": 0.1580135440180587,
      "grad_norm": 0.4045011103153229,
      "learning_rate": 2e-05,
      "loss": 0.7031,
      "step": 1890
    },
    {
      "epoch": 0.15884959451550873,
      "grad_norm": 0.3887285590171814,
      "learning_rate": 2e-05,
      "loss": 0.6739,
      "step": 1900
    },
    {
      "epoch": 0.1596856450129588,
      "grad_norm": 0.4463697671890259,
      "learning_rate": 2e-05,
      "loss": 0.7147,
      "step": 1910
    },
    {
      "epoch": 0.16052169551040882,
      "grad_norm": 0.3879319131374359,
      "learning_rate": 2e-05,
      "loss": 0.7375,
      "step": 1920
    },
    {
      "epoch": 0.16135774600785888,
      "grad_norm": 0.35314497351646423,
      "learning_rate": 2e-05,
      "loss": 0.6811,
      "step": 1930
    },
    {
      "epoch": 0.1621937965053089,
      "grad_norm": 0.4394693970680237,
      "learning_rate": 2e-05,
      "loss": 0.7156,
      "step": 1940
    },
    {
      "epoch": 0.16302984700275897,
      "grad_norm": 0.3700949549674988,
      "learning_rate": 2e-05,
      "loss": 0.7054,
      "step": 1950
    },
    {
      "epoch": 0.16386589750020902,
      "grad_norm": 0.3599170446395874,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 1960
    },
    {
      "epoch": 0.16470194799765905,
      "grad_norm": 0.41550520062446594,
      "learning_rate": 2e-05,
      "loss": 0.6874,
      "step": 1970
    },
    {
      "epoch": 0.1655379984951091,
      "grad_norm": 0.4028865694999695,
      "learning_rate": 2e-05,
      "loss": 0.7222,
      "step": 1980
    },
    {
      "epoch": 0.16637404899255914,
      "grad_norm": 0.3849325478076935,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 1990
    },
    {
      "epoch": 0.1672100994900092,
      "grad_norm": 0.34337013959884644,
      "learning_rate": 2e-05,
      "loss": 0.6604,
      "step": 2000
    },
    {
      "epoch": 0.16804614998745923,
      "grad_norm": 0.3867923319339752,
      "learning_rate": 2e-05,
      "loss": 0.6965,
      "step": 2010
    },
    {
      "epoch": 0.1688822004849093,
      "grad_norm": 0.3923274874687195,
      "learning_rate": 2e-05,
      "loss": 0.7098,
      "step": 2020
    },
    {
      "epoch": 0.16971825098235935,
      "grad_norm": 0.3679618239402771,
      "learning_rate": 2e-05,
      "loss": 0.6978,
      "step": 2030
    },
    {
      "epoch": 0.17055430147980938,
      "grad_norm": 0.39310866594314575,
      "learning_rate": 2e-05,
      "loss": 0.71,
      "step": 2040
    },
    {
      "epoch": 0.17139035197725944,
      "grad_norm": 0.3967050313949585,
      "learning_rate": 2e-05,
      "loss": 0.7243,
      "step": 2050
    },
    {
      "epoch": 0.17222640247470947,
      "grad_norm": 0.40121224522590637,
      "learning_rate": 2e-05,
      "loss": 0.6967,
      "step": 2060
    },
    {
      "epoch": 0.17306245297215953,
      "grad_norm": 0.38088318705558777,
      "learning_rate": 2e-05,
      "loss": 0.6401,
      "step": 2070
    },
    {
      "epoch": 0.17389850346960956,
      "grad_norm": 0.3435222804546356,
      "learning_rate": 2e-05,
      "loss": 0.6647,
      "step": 2080
    },
    {
      "epoch": 0.1747345539670596,
      "grad_norm": 0.4220814108848572,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 2090
    },
    {
      "epoch": 0.17557060446450964,
      "grad_norm": 0.35260170698165894,
      "learning_rate": 2e-05,
      "loss": 0.6713,
      "step": 2100
    },
    {
      "epoch": 0.1764066549619597,
      "grad_norm": 0.40899789333343506,
      "learning_rate": 2e-05,
      "loss": 0.7129,
      "step": 2110
    },
    {
      "epoch": 0.17724270545940976,
      "grad_norm": 0.4075130522251129,
      "learning_rate": 2e-05,
      "loss": 0.6915,
      "step": 2120
    },
    {
      "epoch": 0.1780787559568598,
      "grad_norm": 0.4192414879798889,
      "learning_rate": 2e-05,
      "loss": 0.6905,
      "step": 2130
    },
    {
      "epoch": 0.17891480645430985,
      "grad_norm": 0.38824033737182617,
      "learning_rate": 2e-05,
      "loss": 0.7058,
      "step": 2140
    },
    {
      "epoch": 0.17975085695175988,
      "grad_norm": 0.3785799443721771,
      "learning_rate": 2e-05,
      "loss": 0.7003,
      "step": 2150
    },
    {
      "epoch": 0.18058690744920994,
      "grad_norm": 0.3589932322502136,
      "learning_rate": 2e-05,
      "loss": 0.6703,
      "step": 2160
    },
    {
      "epoch": 0.18142295794665997,
      "grad_norm": 0.36105579137802124,
      "learning_rate": 2e-05,
      "loss": 0.6972,
      "step": 2170
    },
    {
      "epoch": 0.18225900844411003,
      "grad_norm": 0.3652353584766388,
      "learning_rate": 2e-05,
      "loss": 0.6906,
      "step": 2180
    },
    {
      "epoch": 0.18309505894156006,
      "grad_norm": 0.40131404995918274,
      "learning_rate": 2e-05,
      "loss": 0.7082,
      "step": 2190
    },
    {
      "epoch": 0.18393110943901012,
      "grad_norm": 0.40471386909484863,
      "learning_rate": 2e-05,
      "loss": 0.696,
      "step": 2200
    },
    {
      "epoch": 0.18476715993646017,
      "grad_norm": 0.3407021462917328,
      "learning_rate": 2e-05,
      "loss": 0.653,
      "step": 2210
    },
    {
      "epoch": 0.1856032104339102,
      "grad_norm": 0.37151047587394714,
      "learning_rate": 2e-05,
      "loss": 0.6928,
      "step": 2220
    },
    {
      "epoch": 0.18643926093136026,
      "grad_norm": 0.3697320818901062,
      "learning_rate": 2e-05,
      "loss": 0.692,
      "step": 2230
    },
    {
      "epoch": 0.1872753114288103,
      "grad_norm": 0.3968718349933624,
      "learning_rate": 2e-05,
      "loss": 0.6909,
      "step": 2240
    },
    {
      "epoch": 0.18811136192626035,
      "grad_norm": 0.3623242676258087,
      "learning_rate": 2e-05,
      "loss": 0.7195,
      "step": 2250
    },
    {
      "epoch": 0.18894741242371038,
      "grad_norm": 0.3716718852519989,
      "learning_rate": 2e-05,
      "loss": 0.7327,
      "step": 2260
    },
    {
      "epoch": 0.18978346292116044,
      "grad_norm": 0.38747113943099976,
      "learning_rate": 2e-05,
      "loss": 0.7033,
      "step": 2270
    },
    {
      "epoch": 0.1906195134186105,
      "grad_norm": 0.3699060380458832,
      "learning_rate": 2e-05,
      "loss": 0.7035,
      "step": 2280
    },
    {
      "epoch": 0.19145556391606053,
      "grad_norm": 0.3485587239265442,
      "learning_rate": 2e-05,
      "loss": 0.6982,
      "step": 2290
    },
    {
      "epoch": 0.1922916144135106,
      "grad_norm": 0.35775020718574524,
      "learning_rate": 2e-05,
      "loss": 0.6977,
      "step": 2300
    },
    {
      "epoch": 0.19312766491096062,
      "grad_norm": 0.386114239692688,
      "learning_rate": 2e-05,
      "loss": 0.6901,
      "step": 2310
    },
    {
      "epoch": 0.19396371540841068,
      "grad_norm": 0.4111344814300537,
      "learning_rate": 2e-05,
      "loss": 0.7134,
      "step": 2320
    },
    {
      "epoch": 0.1947997659058607,
      "grad_norm": 0.3693266212940216,
      "learning_rate": 2e-05,
      "loss": 0.6793,
      "step": 2330
    },
    {
      "epoch": 0.19563581640331076,
      "grad_norm": 0.3926129639148712,
      "learning_rate": 2e-05,
      "loss": 0.6856,
      "step": 2340
    },
    {
      "epoch": 0.1964718669007608,
      "grad_norm": 0.38753512501716614,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 2350
    },
    {
      "epoch": 0.19730791739821085,
      "grad_norm": 0.3788638710975647,
      "learning_rate": 2e-05,
      "loss": 0.6795,
      "step": 2360
    },
    {
      "epoch": 0.1981439678956609,
      "grad_norm": 0.3338569104671478,
      "learning_rate": 2e-05,
      "loss": 0.6775,
      "step": 2370
    },
    {
      "epoch": 0.19898001839311094,
      "grad_norm": 0.366208016872406,
      "learning_rate": 2e-05,
      "loss": 0.7282,
      "step": 2380
    },
    {
      "epoch": 0.199816068890561,
      "grad_norm": 0.379518985748291,
      "learning_rate": 2e-05,
      "loss": 0.6781,
      "step": 2390
    },
    {
      "epoch": 0.20065211938801103,
      "grad_norm": 0.3841893970966339,
      "learning_rate": 2e-05,
      "loss": 0.7026,
      "step": 2400
    },
    {
      "epoch": 0.2014881698854611,
      "grad_norm": 0.3684847950935364,
      "learning_rate": 2e-05,
      "loss": 0.6626,
      "step": 2410
    },
    {
      "epoch": 0.20232422038291112,
      "grad_norm": 0.3933838903903961,
      "learning_rate": 2e-05,
      "loss": 0.7178,
      "step": 2420
    },
    {
      "epoch": 0.20316027088036118,
      "grad_norm": 0.3518088757991791,
      "learning_rate": 2e-05,
      "loss": 0.6663,
      "step": 2430
    },
    {
      "epoch": 0.2039963213778112,
      "grad_norm": 0.383081316947937,
      "learning_rate": 2e-05,
      "loss": 0.6947,
      "step": 2440
    },
    {
      "epoch": 0.20483237187526127,
      "grad_norm": 0.34842392802238464,
      "learning_rate": 2e-05,
      "loss": 0.6893,
      "step": 2450
    },
    {
      "epoch": 0.20566842237271132,
      "grad_norm": 0.36848798394203186,
      "learning_rate": 2e-05,
      "loss": 0.6873,
      "step": 2460
    },
    {
      "epoch": 0.20650447287016135,
      "grad_norm": 0.36847376823425293,
      "learning_rate": 2e-05,
      "loss": 0.73,
      "step": 2470
    },
    {
      "epoch": 0.2073405233676114,
      "grad_norm": 0.4002387523651123,
      "learning_rate": 2e-05,
      "loss": 0.6958,
      "step": 2480
    },
    {
      "epoch": 0.20817657386506144,
      "grad_norm": 0.383114755153656,
      "learning_rate": 2e-05,
      "loss": 0.704,
      "step": 2490
    },
    {
      "epoch": 0.2090126243625115,
      "grad_norm": 0.3491422235965729,
      "learning_rate": 2e-05,
      "loss": 0.6831,
      "step": 2500
    },
    {
      "epoch": 0.20984867485996153,
      "grad_norm": 0.3453516364097595,
      "learning_rate": 2e-05,
      "loss": 0.6988,
      "step": 2510
    },
    {
      "epoch": 0.2106847253574116,
      "grad_norm": 0.3652738332748413,
      "learning_rate": 2e-05,
      "loss": 0.7116,
      "step": 2520
    },
    {
      "epoch": 0.21152077585486162,
      "grad_norm": 0.3410079777240753,
      "learning_rate": 2e-05,
      "loss": 0.7418,
      "step": 2530
    },
    {
      "epoch": 0.21235682635231168,
      "grad_norm": 0.38150179386138916,
      "learning_rate": 2e-05,
      "loss": 0.6719,
      "step": 2540
    },
    {
      "epoch": 0.21319287684976174,
      "grad_norm": 0.33761629462242126,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.6723,
      "step": 2550
    },
    {
      "epoch": 0.21402892734721177,
      "grad_norm": 0.41216763854026794,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.709,
      "step": 2560
    },
    {
      "epoch": 0.21486497784466183,
      "grad_norm": 0.3730127811431885,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.7023,
      "step": 2570
    },
    {
      "epoch": 0.21570102834211186,
      "grad_norm": 0.3858484923839569,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7028,
      "step": 2580
    },
    {
      "epoch": 0.21653707883956191,
      "grad_norm": 0.3435647189617157,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.6942,
      "step": 2590
    },
    {
      "epoch": 0.21737312933701194,
      "grad_norm": 0.351238876581192,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.6825,
      "step": 2600
    },
    {
      "epoch": 0.218209179834462,
      "grad_norm": 0.41351938247680664,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7196,
      "step": 2610
    },
    {
      "epoch": 0.21904523033191206,
      "grad_norm": 0.3725132942199707,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.6905,
      "step": 2620
    },
    {
      "epoch": 0.2198812808293621,
      "grad_norm": 0.39480119943618774,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.6866,
      "step": 2630
    },
    {
      "epoch": 0.22071733132681215,
      "grad_norm": 0.380398154258728,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.6673,
      "step": 2640
    },
    {
      "epoch": 0.22155338182426218,
      "grad_norm": 0.32893604040145874,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.6967,
      "step": 2650
    },
    {
      "epoch": 0.22238943232171224,
      "grad_norm": 0.3431414067745209,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.6836,
      "step": 2660
    },
    {
      "epoch": 0.22322548281916227,
      "grad_norm": 0.5396410226821899,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.6746,
      "step": 2670
    },
    {
      "epoch": 0.22406153331661233,
      "grad_norm": 0.3738407790660858,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.6638,
      "step": 2680
    },
    {
      "epoch": 0.22489758381406236,
      "grad_norm": 0.3568935692310333,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.6573,
      "step": 2690
    },
    {
      "epoch": 0.22573363431151242,
      "grad_norm": 0.35957688093185425,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.677,
      "step": 2700
    },
    {
      "epoch": 0.22656968480896247,
      "grad_norm": 0.37855178117752075,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.6973,
      "step": 2710
    },
    {
      "epoch": 0.2274057353064125,
      "grad_norm": 0.36090126633644104,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.6775,
      "step": 2720
    },
    {
      "epoch": 0.22824178580386256,
      "grad_norm": 0.400646448135376,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.689,
      "step": 2730
    },
    {
      "epoch": 0.2290778363013126,
      "grad_norm": 0.3885079622268677,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.6764,
      "step": 2740
    },
    {
      "epoch": 0.22991388679876265,
      "grad_norm": 0.35182249546051025,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.6831,
      "step": 2750
    },
    {
      "epoch": 0.23074993729621268,
      "grad_norm": 0.35367506742477417,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.6926,
      "step": 2760
    },
    {
      "epoch": 0.23158598779366274,
      "grad_norm": 0.3641999065876007,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.666,
      "step": 2770
    },
    {
      "epoch": 0.23242203829111277,
      "grad_norm": 0.3287544548511505,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.6928,
      "step": 2780
    },
    {
      "epoch": 0.23325808878856283,
      "grad_norm": 0.3601919412612915,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.6812,
      "step": 2790
    },
    {
      "epoch": 0.23392692918652286,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.062139396244837095,
      "train_runtime": 2634.7252,
      "train_samples_per_second": 12.744,
      "train_steps_per_second": 1.062
    }
  ],
  "logging_steps": 10,
  "max_steps": 2798,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 159,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1366756130249245e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}