{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991537376586743,
  "eval_steps": 500,
  "global_step": 2658,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011283497884344146,
      "grad_norm": 1.3125232159346416,
      "learning_rate": 5e-06,
      "loss": 0.7474,
      "step": 10
    },
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 0.9167355748966123,
      "learning_rate": 5e-06,
      "loss": 0.6794,
      "step": 20
    },
    {
      "epoch": 0.03385049365303244,
      "grad_norm": 0.8469930147086754,
      "learning_rate": 5e-06,
      "loss": 0.6697,
      "step": 30
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.8935332426600987,
      "learning_rate": 5e-06,
      "loss": 0.6592,
      "step": 40
    },
    {
      "epoch": 0.056417489421720736,
      "grad_norm": 0.7558955578947845,
      "learning_rate": 5e-06,
      "loss": 0.6527,
      "step": 50
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.8864690987221431,
      "learning_rate": 5e-06,
      "loss": 0.6546,
      "step": 60
    },
    {
      "epoch": 0.07898448519040903,
      "grad_norm": 0.7695810970926475,
      "learning_rate": 5e-06,
      "loss": 0.632,
      "step": 70
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.7714248271685794,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 80
    },
    {
      "epoch": 0.10155148095909731,
      "grad_norm": 0.8886760851072192,
      "learning_rate": 5e-06,
      "loss": 0.6225,
      "step": 90
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.8974890384086033,
      "learning_rate": 5e-06,
      "loss": 0.6362,
      "step": 100
    },
    {
      "epoch": 0.12411847672778561,
      "grad_norm": 0.8819677575312233,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 110
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.9251296507200821,
      "learning_rate": 5e-06,
      "loss": 0.6271,
      "step": 120
    },
    {
      "epoch": 0.1466854724964739,
      "grad_norm": 0.7702797791218077,
      "learning_rate": 5e-06,
      "loss": 0.6273,
      "step": 130
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.8095360026454328,
      "learning_rate": 5e-06,
      "loss": 0.6252,
      "step": 140
    },
    {
      "epoch": 0.1692524682651622,
      "grad_norm": 0.8204620911060526,
      "learning_rate": 5e-06,
      "loss": 0.6287,
      "step": 150
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.8182785549342615,
      "learning_rate": 5e-06,
      "loss": 0.6284,
      "step": 160
    },
    {
      "epoch": 0.1918194640338505,
      "grad_norm": 0.7445113899986885,
      "learning_rate": 5e-06,
      "loss": 0.6264,
      "step": 170
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.7873061135697372,
      "learning_rate": 5e-06,
      "loss": 0.6253,
      "step": 180
    },
    {
      "epoch": 0.2143864598025388,
      "grad_norm": 0.7956486177510658,
      "learning_rate": 5e-06,
      "loss": 0.6264,
      "step": 190
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.7746629467371798,
      "learning_rate": 5e-06,
      "loss": 0.6238,
      "step": 200
    },
    {
      "epoch": 0.23695345557122707,
      "grad_norm": 0.7345245715769874,
      "learning_rate": 5e-06,
      "loss": 0.619,
      "step": 210
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.8349914408696147,
      "learning_rate": 5e-06,
      "loss": 0.6145,
      "step": 220
    },
    {
      "epoch": 0.25952045133991536,
      "grad_norm": 0.7331223816734604,
      "learning_rate": 5e-06,
      "loss": 0.6179,
      "step": 230
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.7535227854265615,
      "learning_rate": 5e-06,
      "loss": 0.615,
      "step": 240
    },
    {
      "epoch": 0.2820874471086037,
      "grad_norm": 0.9217132891288368,
      "learning_rate": 5e-06,
      "loss": 0.614,
      "step": 250
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 0.7626220728005123,
      "learning_rate": 5e-06,
      "loss": 0.6207,
      "step": 260
    },
    {
      "epoch": 0.304654442877292,
      "grad_norm": 0.7567534233021369,
      "learning_rate": 5e-06,
      "loss": 0.6138,
      "step": 270
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.7740686670455319,
      "learning_rate": 5e-06,
      "loss": 0.6107,
      "step": 280
    },
    {
      "epoch": 0.32722143864598024,
      "grad_norm": 0.7577709244521811,
      "learning_rate": 5e-06,
      "loss": 0.614,
      "step": 290
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.7294703403964556,
      "learning_rate": 5e-06,
      "loss": 0.6113,
      "step": 300
    },
    {
      "epoch": 0.34978843441466856,
      "grad_norm": 0.7503750502849057,
      "learning_rate": 5e-06,
      "loss": 0.6122,
      "step": 310
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.7103206649111901,
      "learning_rate": 5e-06,
      "loss": 0.6167,
      "step": 320
    },
    {
      "epoch": 0.3723554301833568,
      "grad_norm": 0.7626842348184225,
      "learning_rate": 5e-06,
      "loss": 0.606,
      "step": 330
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.7621571567885804,
      "learning_rate": 5e-06,
      "loss": 0.6155,
      "step": 340
    },
    {
      "epoch": 0.39492242595204513,
      "grad_norm": 0.7549313486626996,
      "learning_rate": 5e-06,
      "loss": 0.6172,
      "step": 350
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.782988336813104,
      "learning_rate": 5e-06,
      "loss": 0.5985,
      "step": 360
    },
    {
      "epoch": 0.41748942172073344,
      "grad_norm": 0.7863471438503445,
      "learning_rate": 5e-06,
      "loss": 0.6154,
      "step": 370
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.7640237197989878,
      "learning_rate": 5e-06,
      "loss": 0.5897,
      "step": 380
    },
    {
      "epoch": 0.4400564174894217,
      "grad_norm": 0.8024119449518029,
      "learning_rate": 5e-06,
      "loss": 0.6157,
      "step": 390
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.720556179289527,
      "learning_rate": 5e-06,
      "loss": 0.603,
      "step": 400
    },
    {
      "epoch": 0.46262341325811,
      "grad_norm": 0.76294955883197,
      "learning_rate": 5e-06,
      "loss": 0.6061,
      "step": 410
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.8156507807690674,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 420
    },
    {
      "epoch": 0.48519040902679833,
      "grad_norm": 0.7521066252629773,
      "learning_rate": 5e-06,
      "loss": 0.5976,
      "step": 430
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.7133025964230046,
      "learning_rate": 5e-06,
      "loss": 0.5968,
      "step": 440
    },
    {
      "epoch": 0.5077574047954866,
      "grad_norm": 0.7925716834523774,
      "learning_rate": 5e-06,
      "loss": 0.6096,
      "step": 450
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.7100847121605542,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 460
    },
    {
      "epoch": 0.5303244005641748,
      "grad_norm": 0.6929396371646737,
      "learning_rate": 5e-06,
      "loss": 0.6002,
      "step": 470
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.6977506618129865,
      "learning_rate": 5e-06,
      "loss": 0.6104,
      "step": 480
    },
    {
      "epoch": 0.5528913963328632,
      "grad_norm": 0.7147611855456376,
      "learning_rate": 5e-06,
      "loss": 0.5912,
      "step": 490
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.7042203040407636,
      "learning_rate": 5e-06,
      "loss": 0.6079,
      "step": 500
    },
    {
      "epoch": 0.5754583921015515,
      "grad_norm": 0.7309189788815705,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 510
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.7248169421227385,
      "learning_rate": 5e-06,
      "loss": 0.6003,
      "step": 520
    },
    {
      "epoch": 0.5980253878702397,
      "grad_norm": 0.7572409467891201,
      "learning_rate": 5e-06,
      "loss": 0.5916,
      "step": 530
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.733437644851395,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 540
    },
    {
      "epoch": 0.6205923836389281,
      "grad_norm": 0.7131751072814058,
      "learning_rate": 5e-06,
      "loss": 0.6034,
      "step": 550
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.7360178195388309,
      "learning_rate": 5e-06,
      "loss": 0.605,
      "step": 560
    },
    {
      "epoch": 0.6431593794076164,
      "grad_norm": 1.1495804042684488,
      "learning_rate": 5e-06,
      "loss": 0.5974,
      "step": 570
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.6817754751813853,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 580
    },
    {
      "epoch": 0.6657263751763046,
      "grad_norm": 0.7044965353014948,
      "learning_rate": 5e-06,
      "loss": 0.607,
      "step": 590
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.7308565798791333,
      "learning_rate": 5e-06,
      "loss": 0.6015,
      "step": 600
    },
    {
      "epoch": 0.688293370944993,
      "grad_norm": 0.758452633023999,
      "learning_rate": 5e-06,
      "loss": 0.603,
      "step": 610
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.7778955204205954,
      "learning_rate": 5e-06,
      "loss": 0.5924,
      "step": 620
    },
    {
      "epoch": 0.7108603667136812,
      "grad_norm": 0.6757727892125893,
      "learning_rate": 5e-06,
      "loss": 0.5999,
      "step": 630
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.7690880111005869,
      "learning_rate": 5e-06,
      "loss": 0.6008,
      "step": 640
    },
    {
      "epoch": 0.7334273624823695,
      "grad_norm": 0.780886462765786,
      "learning_rate": 5e-06,
      "loss": 0.5954,
      "step": 650
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.7683226572424213,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 660
    },
    {
      "epoch": 0.7559943582510579,
      "grad_norm": 0.6840538894373641,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 670
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.6771027958757195,
      "learning_rate": 5e-06,
      "loss": 0.59,
      "step": 680
    },
    {
      "epoch": 0.7785613540197461,
      "grad_norm": 0.6681056791937571,
      "learning_rate": 5e-06,
      "loss": 0.5931,
      "step": 690
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.7086908628376102,
      "learning_rate": 5e-06,
      "loss": 0.6005,
      "step": 700
    },
    {
      "epoch": 0.8011283497884344,
      "grad_norm": 0.6592220118037463,
      "learning_rate": 5e-06,
      "loss": 0.5888,
      "step": 710
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.7384276235727564,
      "learning_rate": 5e-06,
      "loss": 0.6029,
      "step": 720
    },
    {
      "epoch": 0.8236953455571228,
      "grad_norm": 0.7153557202506454,
      "learning_rate": 5e-06,
      "loss": 0.6004,
      "step": 730
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.7412356079152558,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 740
    },
    {
      "epoch": 0.846262341325811,
      "grad_norm": 0.8186167983419891,
      "learning_rate": 5e-06,
      "loss": 0.6012,
      "step": 750
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.6956555496968945,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 760
    },
    {
      "epoch": 0.8688293370944993,
      "grad_norm": 0.6972125762170825,
      "learning_rate": 5e-06,
      "loss": 0.598,
      "step": 770
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.6554398016756771,
      "learning_rate": 5e-06,
      "loss": 0.5899,
      "step": 780
    },
    {
      "epoch": 0.8913963328631875,
      "grad_norm": 0.6816513719411913,
      "learning_rate": 5e-06,
      "loss": 0.5959,
      "step": 790
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.6802192397813065,
      "learning_rate": 5e-06,
      "loss": 0.5966,
      "step": 800
    },
    {
      "epoch": 0.9139633286318759,
      "grad_norm": 0.7297229988637639,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 810
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.6910581824985036,
      "learning_rate": 5e-06,
      "loss": 0.5903,
      "step": 820
    },
    {
      "epoch": 0.9365303244005642,
      "grad_norm": 0.7038633597805812,
      "learning_rate": 5e-06,
      "loss": 0.5926,
      "step": 830
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.7006043004126095,
      "learning_rate": 5e-06,
      "loss": 0.5968,
      "step": 840
    },
    {
      "epoch": 0.9590973201692524,
      "grad_norm": 0.7196243633360835,
      "learning_rate": 5e-06,
      "loss": 0.5946,
      "step": 850
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 1.0955172142857887,
      "learning_rate": 5e-06,
      "loss": 0.5837,
      "step": 860
    },
    {
      "epoch": 0.9816643159379408,
      "grad_norm": 0.6592667550168434,
      "learning_rate": 5e-06,
      "loss": 0.5998,
      "step": 870
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.7854190040474681,
      "learning_rate": 5e-06,
      "loss": 0.5875,
      "step": 880
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.5916627049446106,
      "eval_runtime": 700.0009,
      "eval_samples_per_second": 17.059,
      "eval_steps_per_second": 0.534,
      "step": 886
    },
    {
      "epoch": 1.004231311706629,
      "grad_norm": 1.3251196950195474,
      "learning_rate": 5e-06,
      "loss": 0.6038,
      "step": 890
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.833678301438908,
      "learning_rate": 5e-06,
      "loss": 0.5204,
      "step": 900
    },
    {
      "epoch": 1.0267983074753173,
      "grad_norm": 0.7372319799588725,
      "learning_rate": 5e-06,
      "loss": 0.5098,
      "step": 910
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.710656408718745,
      "learning_rate": 5e-06,
      "loss": 0.5147,
      "step": 920
    },
    {
      "epoch": 1.0493653032440056,
      "grad_norm": 0.7035392178179493,
      "learning_rate": 5e-06,
      "loss": 0.532,
      "step": 930
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.7419000790657035,
      "learning_rate": 5e-06,
      "loss": 0.5232,
      "step": 940
    },
    {
      "epoch": 1.071932299012694,
      "grad_norm": 0.7507810642090355,
      "learning_rate": 5e-06,
      "loss": 0.5182,
      "step": 950
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 0.7365569865429179,
      "learning_rate": 5e-06,
      "loss": 0.5156,
      "step": 960
    },
    {
      "epoch": 1.0944992947813823,
      "grad_norm": 0.6971352350986588,
      "learning_rate": 5e-06,
      "loss": 0.5255,
      "step": 970
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.769651560789747,
      "learning_rate": 5e-06,
      "loss": 0.5275,
      "step": 980
    },
    {
      "epoch": 1.1170662905500706,
      "grad_norm": 0.6835338919436766,
      "learning_rate": 5e-06,
      "loss": 0.5266,
      "step": 990
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.7080901866255427,
      "learning_rate": 5e-06,
      "loss": 0.5245,
      "step": 1000
    },
    {
      "epoch": 1.1396332863187588,
      "grad_norm": 0.6973746558937527,
      "learning_rate": 5e-06,
      "loss": 0.5272,
      "step": 1010
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.7328115120631007,
      "learning_rate": 5e-06,
      "loss": 0.5269,
      "step": 1020
    },
    {
      "epoch": 1.162200282087447,
      "grad_norm": 0.8161495623001298,
      "learning_rate": 5e-06,
      "loss": 0.5226,
      "step": 1030
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.8517029792820613,
      "learning_rate": 5e-06,
      "loss": 0.5175,
      "step": 1040
    },
    {
      "epoch": 1.1847672778561353,
      "grad_norm": 0.8438046028102798,
      "learning_rate": 5e-06,
      "loss": 0.5241,
      "step": 1050
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.7099751086024491,
      "learning_rate": 5e-06,
      "loss": 0.5291,
      "step": 1060
    },
    {
      "epoch": 1.2073342736248236,
      "grad_norm": 0.7580945476663854,
      "learning_rate": 5e-06,
      "loss": 0.5249,
      "step": 1070
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.7667303387873934,
      "learning_rate": 5e-06,
      "loss": 0.5235,
      "step": 1080
    },
    {
      "epoch": 1.229901269393512,
      "grad_norm": 0.8114242325537707,
      "learning_rate": 5e-06,
      "loss": 0.5283,
      "step": 1090
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.7131407385877792,
      "learning_rate": 5e-06,
      "loss": 0.5288,
      "step": 1100
    },
    {
      "epoch": 1.2524682651622003,
      "grad_norm": 0.685086959113009,
      "learning_rate": 5e-06,
      "loss": 0.5195,
      "step": 1110
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.7053119373842179,
      "learning_rate": 5e-06,
      "loss": 0.542,
      "step": 1120
    },
    {
      "epoch": 1.2750352609308886,
      "grad_norm": 0.7644874615248024,
      "learning_rate": 5e-06,
      "loss": 0.5287,
      "step": 1130
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.6883885545058486,
      "learning_rate": 5e-06,
      "loss": 0.5267,
      "step": 1140
    },
    {
      "epoch": 1.2976022566995769,
      "grad_norm": 0.7306504262086587,
      "learning_rate": 5e-06,
      "loss": 0.5289,
      "step": 1150
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.9640801871844217,
      "learning_rate": 5e-06,
      "loss": 0.5267,
      "step": 1160
    },
    {
      "epoch": 1.320169252468265,
      "grad_norm": 0.661755370313437,
      "learning_rate": 5e-06,
      "loss": 0.5305,
      "step": 1170
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.6875142102900156,
      "learning_rate": 5e-06,
      "loss": 0.5262,
      "step": 1180
    },
    {
      "epoch": 1.3427362482369536,
      "grad_norm": 0.7205563505642903,
      "learning_rate": 5e-06,
      "loss": 0.5391,
      "step": 1190
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.6599447213858599,
      "learning_rate": 5e-06,
      "loss": 0.5272,
      "step": 1200
    },
    {
      "epoch": 1.3653032440056418,
      "grad_norm": 0.6674411183277559,
      "learning_rate": 5e-06,
      "loss": 0.5294,
      "step": 1210
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.6760191535339451,
      "learning_rate": 5e-06,
      "loss": 0.5237,
      "step": 1220
    },
    {
      "epoch": 1.38787023977433,
      "grad_norm": 0.699499504851807,
      "learning_rate": 5e-06,
      "loss": 0.5239,
      "step": 1230
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.6949474979507084,
      "learning_rate": 5e-06,
      "loss": 0.5371,
      "step": 1240
    },
    {
      "epoch": 1.4104372355430184,
      "grad_norm": 0.6871033689397662,
      "learning_rate": 5e-06,
      "loss": 0.5346,
      "step": 1250
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.6742402949788701,
      "learning_rate": 5e-06,
      "loss": 0.5239,
      "step": 1260
    },
    {
      "epoch": 1.4330042313117066,
      "grad_norm": 0.6751463140934231,
      "learning_rate": 5e-06,
      "loss": 0.5266,
      "step": 1270
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.7142787617460878,
      "learning_rate": 5e-06,
      "loss": 0.5315,
      "step": 1280
    },
    {
      "epoch": 1.4555712270803949,
      "grad_norm": 0.7226332853252287,
      "learning_rate": 5e-06,
      "loss": 0.5275,
      "step": 1290
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.7145272993925487,
      "learning_rate": 5e-06,
      "loss": 0.5322,
      "step": 1300
    },
    {
      "epoch": 1.4781382228490831,
      "grad_norm": 0.6768426299144826,
      "learning_rate": 5e-06,
      "loss": 0.538,
      "step": 1310
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.7123747155692624,
      "learning_rate": 5e-06,
      "loss": 0.5289,
      "step": 1320
    },
    {
      "epoch": 1.5007052186177714,
      "grad_norm": 0.6786058643003756,
      "learning_rate": 5e-06,
      "loss": 0.5253,
      "step": 1330
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.7110831777325413,
      "learning_rate": 5e-06,
      "loss": 0.5324,
      "step": 1340
    },
    {
      "epoch": 1.5232722143864597,
      "grad_norm": 0.6695015578694526,
      "learning_rate": 5e-06,
      "loss": 0.5214,
      "step": 1350
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.7459448089167867,
      "learning_rate": 5e-06,
      "loss": 0.5252,
      "step": 1360
    },
    {
      "epoch": 1.5458392101551481,
      "grad_norm": 0.6753928189856611,
      "learning_rate": 5e-06,
      "loss": 0.5251,
      "step": 1370
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.6996235594913326,
      "learning_rate": 5e-06,
      "loss": 0.5248,
      "step": 1380
    },
    {
      "epoch": 1.5684062059238364,
      "grad_norm": 0.7079009762601143,
      "learning_rate": 5e-06,
      "loss": 0.5323,
      "step": 1390
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.6924093724518422,
      "learning_rate": 5e-06,
      "loss": 0.5255,
      "step": 1400
    },
    {
      "epoch": 1.5909732016925247,
      "grad_norm": 0.6761094320283147,
      "learning_rate": 5e-06,
      "loss": 0.5339,
      "step": 1410
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.6809745203094293,
      "learning_rate": 5e-06,
      "loss": 0.5298,
      "step": 1420
    },
    {
      "epoch": 1.6135401974612131,
      "grad_norm": 0.7106432021864519,
      "learning_rate": 5e-06,
      "loss": 0.5478,
      "step": 1430
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.7187158548818587,
      "learning_rate": 5e-06,
      "loss": 0.531,
      "step": 1440
    },
    {
      "epoch": 1.6361071932299014,
      "grad_norm": 0.6596453734369295,
      "learning_rate": 5e-06,
      "loss": 0.5225,
      "step": 1450
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.7093693747872939,
      "learning_rate": 5e-06,
      "loss": 0.5257,
      "step": 1460
    },
    {
      "epoch": 1.6586741889985896,
      "grad_norm": 0.6944427657225931,
      "learning_rate": 5e-06,
      "loss": 0.5412,
      "step": 1470
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.6955533636685318,
      "learning_rate": 5e-06,
      "loss": 0.5367,
      "step": 1480
    },
    {
      "epoch": 1.681241184767278,
      "grad_norm": 0.6624317919452952,
      "learning_rate": 5e-06,
      "loss": 0.5293,
      "step": 1490
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.6778095946034755,
      "learning_rate": 5e-06,
      "loss": 0.5323,
      "step": 1500
    },
    {
      "epoch": 1.7038081805359662,
      "grad_norm": 0.7341427766426889,
      "learning_rate": 5e-06,
      "loss": 0.5263,
      "step": 1510
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.7432696239071007,
      "learning_rate": 5e-06,
      "loss": 0.5334,
      "step": 1520
    },
    {
      "epoch": 1.7263751763046544,
      "grad_norm": 0.6491261448207155,
      "learning_rate": 5e-06,
      "loss": 0.5305,
      "step": 1530
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.7486777638151452,
      "learning_rate": 5e-06,
      "loss": 0.5304,
      "step": 1540
    },
    {
      "epoch": 1.7489421720733427,
      "grad_norm": 0.7118918086770966,
      "learning_rate": 5e-06,
      "loss": 0.5216,
      "step": 1550
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.7038340173438765,
      "learning_rate": 5e-06,
      "loss": 0.5322,
      "step": 1560
    },
    {
      "epoch": 1.771509167842031,
      "grad_norm": 0.6539818459517368,
      "learning_rate": 5e-06,
      "loss": 0.5321,
      "step": 1570
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.658011536602541,
      "learning_rate": 5e-06,
      "loss": 0.5288,
      "step": 1580
    },
    {
      "epoch": 1.7940761636107192,
      "grad_norm": 0.6572168627274099,
      "learning_rate": 5e-06,
      "loss": 0.5219,
      "step": 1590
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.6648318139285605,
      "learning_rate": 5e-06,
      "loss": 0.5292,
      "step": 1600
    },
    {
      "epoch": 1.8166431593794075,
      "grad_norm": 0.6932570407391014,
      "learning_rate": 5e-06,
      "loss": 0.5381,
      "step": 1610
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.6710478896264537,
      "learning_rate": 5e-06,
      "loss": 0.5344,
      "step": 1620
    },
    {
      "epoch": 1.839210155148096,
      "grad_norm": 0.6710698360135149,
      "learning_rate": 5e-06,
      "loss": 0.5201,
      "step": 1630
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.6664339220436462,
      "learning_rate": 5e-06,
      "loss": 0.5272,
      "step": 1640
    },
    {
      "epoch": 1.8617771509167842,
      "grad_norm": 0.679324908548248,
      "learning_rate": 5e-06,
      "loss": 0.5381,
      "step": 1650
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.7203049853389839,
      "learning_rate": 5e-06,
      "loss": 0.5325,
      "step": 1660
    },
    {
      "epoch": 1.8843441466854725,
      "grad_norm": 0.671958846252959,
      "learning_rate": 5e-06,
      "loss": 0.5308,
      "step": 1670
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.6756200949168255,
      "learning_rate": 5e-06,
      "loss": 0.5401,
      "step": 1680
    },
    {
      "epoch": 1.906911142454161,
      "grad_norm": 0.6795733118816987,
      "learning_rate": 5e-06,
      "loss": 0.5209,
      "step": 1690
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.6875411881069398,
      "learning_rate": 5e-06,
      "loss": 0.5274,
      "step": 1700
    },
    {
      "epoch": 1.9294781382228492,
      "grad_norm": 0.6539417007788165,
      "learning_rate": 5e-06,
      "loss": 0.5293,
      "step": 1710
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.7131644844536464,
      "learning_rate": 5e-06,
      "loss": 0.5288,
      "step": 1720
    },
    {
      "epoch": 1.9520451339915375,
      "grad_norm": 0.6498878256598866,
      "learning_rate": 5e-06,
      "loss": 0.5289,
      "step": 1730
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.6843667341548544,
      "learning_rate": 5e-06,
      "loss": 0.5418,
      "step": 1740
    },
    {
      "epoch": 1.9746121297602257,
      "grad_norm": 0.6650168678603656,
      "learning_rate": 5e-06,
      "loss": 0.5402,
      "step": 1750
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.6825312514425923,
      "learning_rate": 5e-06,
      "loss": 0.5268,
      "step": 1760
    },
    {
      "epoch": 1.997179125528914,
      "grad_norm": 0.6765862874969008,
      "learning_rate": 5e-06,
      "loss": 0.5215,
      "step": 1770
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5913873910903931,
      "eval_runtime": 698.2566,
      "eval_samples_per_second": 17.101,
      "eval_steps_per_second": 0.536,
      "step": 1772
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 0.9398660673562257,
      "learning_rate": 5e-06,
      "loss": 0.5208,
      "step": 1780
    },
    {
      "epoch": 2.0197461212976022,
      "grad_norm": 0.7762940970041788,
      "learning_rate": 5e-06,
      "loss": 0.4524,
      "step": 1790
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.8552156108609141,
      "learning_rate": 5e-06,
      "loss": 0.4428,
      "step": 1800
    },
    {
      "epoch": 2.0423131170662905,
      "grad_norm": 0.7759834543073888,
      "learning_rate": 5e-06,
      "loss": 0.4497,
      "step": 1810
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.813460157749594,
      "learning_rate": 5e-06,
      "loss": 0.4501,
      "step": 1820
    },
    {
      "epoch": 2.0648801128349787,
      "grad_norm": 0.7555915322851285,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 1830
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.778910984127173,
      "learning_rate": 5e-06,
      "loss": 0.45,
      "step": 1840
    },
    {
      "epoch": 2.087447108603667,
      "grad_norm": 0.7823483784772997,
      "learning_rate": 5e-06,
      "loss": 0.4487,
      "step": 1850
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.7451819548464573,
      "learning_rate": 5e-06,
      "loss": 0.4524,
      "step": 1860
    },
    {
      "epoch": 2.1100141043723553,
      "grad_norm": 0.7366797047615511,
      "learning_rate": 5e-06,
      "loss": 0.4554,
      "step": 1870
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.7739116377396993,
      "learning_rate": 5e-06,
      "loss": 0.4545,
      "step": 1880
    },
    {
      "epoch": 2.1325811001410435,
      "grad_norm": 0.7393809355678413,
      "learning_rate": 5e-06,
      "loss": 0.4576,
      "step": 1890
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.7783700395003256,
      "learning_rate": 5e-06,
      "loss": 0.456,
      "step": 1900
    },
    {
      "epoch": 2.155148095909732,
      "grad_norm": 0.7655026275655048,
      "learning_rate": 5e-06,
      "loss": 0.4555,
      "step": 1910
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.7308671453948609,
      "learning_rate": 5e-06,
      "loss": 0.4516,
      "step": 1920
    },
    {
      "epoch": 2.1777150916784205,
      "grad_norm": 0.7548898417368491,
      "learning_rate": 5e-06,
      "loss": 0.4554,
      "step": 1930
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.7422727245259925,
      "learning_rate": 5e-06,
      "loss": 0.4501,
      "step": 1940
    },
    {
      "epoch": 2.2002820874471087,
      "grad_norm": 0.787975192132044,
      "learning_rate": 5e-06,
      "loss": 0.4439,
      "step": 1950
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.7365878952628802,
      "learning_rate": 5e-06,
      "loss": 0.4514,
      "step": 1960
    },
    {
      "epoch": 2.222849083215797,
      "grad_norm": 0.7259152335914627,
      "learning_rate": 5e-06,
      "loss": 0.4443,
      "step": 1970
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.7305442934832262,
      "learning_rate": 5e-06,
      "loss": 0.4508,
      "step": 1980
    },
    {
      "epoch": 2.2454160789844853,
      "grad_norm": 0.752378808107532,
      "learning_rate": 5e-06,
      "loss": 0.4533,
      "step": 1990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.7662288679828292,
      "learning_rate": 5e-06,
      "loss": 0.4591,
      "step": 2000
    },
    {
      "epoch": 2.2679830747531735,
      "grad_norm": 0.7571986629865566,
      "learning_rate": 5e-06,
      "loss": 0.4583,
      "step": 2010
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.7853445680318998,
      "learning_rate": 5e-06,
      "loss": 0.4665,
      "step": 2020
    },
    {
      "epoch": 2.2905500705218618,
      "grad_norm": 0.8056666478419078,
      "learning_rate": 5e-06,
      "loss": 0.4626,
      "step": 2030
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.7705827370447227,
      "learning_rate": 5e-06,
      "loss": 0.4529,
      "step": 2040
    },
    {
      "epoch": 2.31311706629055,
      "grad_norm": 0.952209351698993,
      "learning_rate": 5e-06,
      "loss": 0.4533,
      "step": 2050
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.7437396447699182,
      "learning_rate": 5e-06,
      "loss": 0.4694,
      "step": 2060
    },
    {
      "epoch": 2.3356840620592383,
      "grad_norm": 0.7507184464222211,
      "learning_rate": 5e-06,
      "loss": 0.4571,
      "step": 2070
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.7538037629123275,
      "learning_rate": 5e-06,
      "loss": 0.4637,
      "step": 2080
    },
    {
      "epoch": 2.3582510578279265,
      "grad_norm": 0.7207349348209307,
      "learning_rate": 5e-06,
      "loss": 0.454,
      "step": 2090
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.7732963363098568,
      "learning_rate": 5e-06,
      "loss": 0.4621,
      "step": 2100
    },
    {
      "epoch": 2.380818053596615,
      "grad_norm": 0.7733305143075813,
      "learning_rate": 5e-06,
      "loss": 0.4616,
      "step": 2110
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.7317816197062187,
      "learning_rate": 5e-06,
      "loss": 0.4544,
      "step": 2120
    },
    {
      "epoch": 2.403385049365303,
      "grad_norm": 0.7387742831088012,
      "learning_rate": 5e-06,
      "loss": 0.4612,
      "step": 2130
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.7855904874369565,
      "learning_rate": 5e-06,
      "loss": 0.4567,
      "step": 2140
    },
    {
      "epoch": 2.4259520451339913,
      "grad_norm": 0.7237436303435315,
      "learning_rate": 5e-06,
      "loss": 0.4624,
      "step": 2150
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.8184805263780661,
      "learning_rate": 5e-06,
      "loss": 0.4621,
      "step": 2160
    },
    {
      "epoch": 2.44851904090268,
      "grad_norm": 0.760755214994802,
      "learning_rate": 5e-06,
      "loss": 0.4602,
      "step": 2170
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.7634415569046652,
      "learning_rate": 5e-06,
      "loss": 0.461,
      "step": 2180
    },
    {
      "epoch": 2.4710860366713683,
      "grad_norm": 0.725712122867678,
      "learning_rate": 5e-06,
      "loss": 0.4631,
      "step": 2190
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.7540090450075305,
      "learning_rate": 5e-06,
      "loss": 0.4638,
      "step": 2200
    },
    {
      "epoch": 2.4936530324400565,
      "grad_norm": 0.7217092577620574,
      "learning_rate": 5e-06,
      "loss": 0.4702,
      "step": 2210
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.7316510601952371,
      "learning_rate": 5e-06,
      "loss": 0.4636,
      "step": 2220
    },
    {
      "epoch": 2.516220028208745,
      "grad_norm": 0.7769888826201891,
      "learning_rate": 5e-06,
      "loss": 0.457,
      "step": 2230
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.6872130661688746,
      "learning_rate": 5e-06,
      "loss": 0.4603,
      "step": 2240
    },
    {
      "epoch": 2.538787023977433,
      "grad_norm": 0.7809947622038785,
      "learning_rate": 5e-06,
      "loss": 0.4598,
      "step": 2250
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.7128936960294685,
      "learning_rate": 5e-06,
      "loss": 0.4665,
      "step": 2260
    },
    {
      "epoch": 2.5613540197461213,
      "grad_norm": 0.7343811921788322,
      "learning_rate": 5e-06,
      "loss": 0.4612,
      "step": 2270
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.7390667339205597,
      "learning_rate": 5e-06,
      "loss": 0.4607,
      "step": 2280
    },
    {
      "epoch": 2.5839210155148096,
      "grad_norm": 0.726032460592344,
      "learning_rate": 5e-06,
      "loss": 0.4549,
      "step": 2290
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.7524597049646161,
      "learning_rate": 5e-06,
      "loss": 0.4694,
      "step": 2300
    },
    {
      "epoch": 2.606488011283498,
      "grad_norm": 0.7858250860151663,
      "learning_rate": 5e-06,
      "loss": 0.4663,
      "step": 2310
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.7293613916851106,
      "learning_rate": 5e-06,
      "loss": 0.4664,
      "step": 2320
    },
    {
      "epoch": 2.629055007052186,
      "grad_norm": 0.7290633000536495,
      "learning_rate": 5e-06,
      "loss": 0.4543,
      "step": 2330
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.7091768581049495,
      "learning_rate": 5e-06,
      "loss": 0.4559,
      "step": 2340
    },
    {
      "epoch": 2.6516220028208743,
      "grad_norm": 0.7087926245008993,
      "learning_rate": 5e-06,
      "loss": 0.4635,
      "step": 2350
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.7590073933828212,
      "learning_rate": 5e-06,
      "loss": 0.4686,
      "step": 2360
    },
    {
      "epoch": 2.6741889985895626,
      "grad_norm": 0.7267770663460916,
      "learning_rate": 5e-06,
      "loss": 0.46,
      "step": 2370
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.7248345474556908,
      "learning_rate": 5e-06,
      "loss": 0.4727,
      "step": 2380
    },
    {
      "epoch": 2.6967559943582513,
      "grad_norm": 0.7498626285953574,
      "learning_rate": 5e-06,
      "loss": 0.4667,
      "step": 2390
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.7438411024370735,
      "learning_rate": 5e-06,
      "loss": 0.465,
      "step": 2400
    },
    {
      "epoch": 2.7193229901269396,
      "grad_norm": 0.7551882708372384,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 2410
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.7575954402507921,
      "learning_rate": 5e-06,
      "loss": 0.4679,
      "step": 2420
    },
    {
      "epoch": 2.741889985895628,
      "grad_norm": 0.7276043657180276,
      "learning_rate": 5e-06,
      "loss": 0.4628,
      "step": 2430
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.7154984668294021,
      "learning_rate": 5e-06,
      "loss": 0.4654,
      "step": 2440
    },
    {
      "epoch": 2.764456981664316,
      "grad_norm": 0.7203876412478339,
      "learning_rate": 5e-06,
      "loss": 0.4697,
      "step": 2450
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.7653450966118911,
      "learning_rate": 5e-06,
      "loss": 0.4705,
      "step": 2460
    },
    {
      "epoch": 2.7870239774330043,
      "grad_norm": 0.7371256159182112,
      "learning_rate": 5e-06,
      "loss": 0.4641,
      "step": 2470
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.7334765675316313,
      "learning_rate": 5e-06,
      "loss": 0.4726,
      "step": 2480
    },
    {
      "epoch": 2.8095909732016926,
      "grad_norm": 0.7255504755388352,
      "learning_rate": 5e-06,
      "loss": 0.4734,
      "step": 2490
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.721440148744813,
      "learning_rate": 5e-06,
      "loss": 0.4644,
      "step": 2500
    },
    {
      "epoch": 2.832157968970381,
      "grad_norm": 0.748754622356668,
      "learning_rate": 5e-06,
      "loss": 0.4794,
      "step": 2510
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.7463238131630598,
      "learning_rate": 5e-06,
      "loss": 0.4628,
      "step": 2520
    },
    {
      "epoch": 2.854724964739069,
      "grad_norm": 0.7220764644154523,
      "learning_rate": 5e-06,
      "loss": 0.4715,
      "step": 2530
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.7116624476538259,
      "learning_rate": 5e-06,
      "loss": 0.4633,
      "step": 2540
    },
    {
      "epoch": 2.8772919605077574,
      "grad_norm": 0.7567720887800601,
      "learning_rate": 5e-06,
      "loss": 0.4689,
      "step": 2550
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.7311117433105612,
      "learning_rate": 5e-06,
      "loss": 0.4659,
      "step": 2560
    },
    {
      "epoch": 2.8998589562764456,
      "grad_norm": 0.6857771399213093,
      "learning_rate": 5e-06,
      "loss": 0.4668,
      "step": 2570
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.7603898848747829,
      "learning_rate": 5e-06,
      "loss": 0.4723,
      "step": 2580
    },
    {
      "epoch": 2.922425952045134,
      "grad_norm": 0.7346850752363808,
      "learning_rate": 5e-06,
      "loss": 0.4631,
      "step": 2590
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.7524612932802797,
      "learning_rate": 5e-06,
      "loss": 0.4686,
      "step": 2600
    },
    {
      "epoch": 2.944992947813822,
      "grad_norm": 0.7353041598333038,
      "learning_rate": 5e-06,
      "loss": 0.4641,
      "step": 2610
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.7285422773911787,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 2620
    },
    {
      "epoch": 2.9675599435825104,
      "grad_norm": 0.7448074753267844,
      "learning_rate": 5e-06,
      "loss": 0.472,
      "step": 2630
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.705662537995191,
      "learning_rate": 5e-06,
      "loss": 0.4627,
      "step": 2640
    },
    {
      "epoch": 2.9901269393511987,
      "grad_norm": 0.7412402310259647,
      "learning_rate": 5e-06,
      "loss": 0.4672,
      "step": 2650
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.6162799000740051,
      "eval_runtime": 701.2713,
      "eval_samples_per_second": 17.028,
      "eval_steps_per_second": 0.533,
      "step": 2658
    },
    {
      "epoch": 2.9991537376586743,
      "step": 2658,
      "total_flos": 5064195066298368.0,
      "train_loss": 0.5339989464833739,
      "train_runtime": 122516.7944,
      "train_samples_per_second": 5.555,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 10,
  "max_steps": 2658,
  "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": 5064195066298368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}