{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1232,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008121827411167513,
      "grad_norm": 99.87779235839844,
      "learning_rate": 7.258064516129033e-07,
      "loss": 10.897,
      "step": 10
    },
    {
      "epoch": 0.016243654822335026,
      "grad_norm": 5142.27978515625,
      "learning_rate": 1.5322580645161292e-06,
      "loss": 9.5965,
      "step": 20
    },
    {
      "epoch": 0.024365482233502538,
      "grad_norm": 127.83818817138672,
      "learning_rate": 2.338709677419355e-06,
      "loss": 7.0387,
      "step": 30
    },
    {
      "epoch": 0.03248730964467005,
      "grad_norm": 822.1220092773438,
      "learning_rate": 3.145161290322581e-06,
      "loss": 5.9009,
      "step": 40
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 52.892913818359375,
      "learning_rate": 3.951612903225807e-06,
      "loss": 5.0498,
      "step": 50
    },
    {
      "epoch": 0.048730964467005075,
      "grad_norm": 66.35478210449219,
      "learning_rate": 4.758064516129033e-06,
      "loss": 4.8549,
      "step": 60
    },
    {
      "epoch": 0.05685279187817259,
      "grad_norm": 37.79729080200195,
      "learning_rate": 5.564516129032258e-06,
      "loss": 4.8198,
      "step": 70
    },
    {
      "epoch": 0.0649746192893401,
      "grad_norm": 29.62307357788086,
      "learning_rate": 6.370967741935485e-06,
      "loss": 4.7959,
      "step": 80
    },
    {
      "epoch": 0.07309644670050762,
      "grad_norm": 122.16439819335938,
      "learning_rate": 7.177419354838711e-06,
      "loss": 4.9298,
      "step": 90
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 2490.642822265625,
      "learning_rate": 7.983870967741935e-06,
      "loss": 4.6711,
      "step": 100
    },
    {
      "epoch": 0.08934010152284264,
      "grad_norm": 25.623624801635742,
      "learning_rate": 8.790322580645163e-06,
      "loss": 4.6562,
      "step": 110
    },
    {
      "epoch": 0.09746192893401015,
      "grad_norm": 52.004798889160156,
      "learning_rate": 9.596774193548389e-06,
      "loss": 4.588,
      "step": 120
    },
    {
      "epoch": 0.10558375634517767,
      "grad_norm": 66.47474670410156,
      "learning_rate": 1e-05,
      "loss": 4.4285,
      "step": 130
    },
    {
      "epoch": 0.11370558375634518,
      "grad_norm": 41.5251350402832,
      "learning_rate": 1e-05,
      "loss": 4.647,
      "step": 140
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 23.846986770629883,
      "learning_rate": 1e-05,
      "loss": 4.5701,
      "step": 150
    },
    {
      "epoch": 0.1299492385786802,
      "grad_norm": 19.366769790649414,
      "learning_rate": 1e-05,
      "loss": 4.7528,
      "step": 160
    },
    {
      "epoch": 0.13807106598984772,
      "grad_norm": 27.284719467163086,
      "learning_rate": 1e-05,
      "loss": 4.4179,
      "step": 170
    },
    {
      "epoch": 0.14619289340101524,
      "grad_norm": 18.394161224365234,
      "learning_rate": 1e-05,
      "loss": 4.1698,
      "step": 180
    },
    {
      "epoch": 0.15431472081218275,
      "grad_norm": 36.81582260131836,
      "learning_rate": 1e-05,
      "loss": 4.5016,
      "step": 190
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 24.884918212890625,
      "learning_rate": 1e-05,
      "loss": 4.6164,
      "step": 200
    },
    {
      "epoch": 0.17055837563451776,
      "grad_norm": 25.368017196655273,
      "learning_rate": 1e-05,
      "loss": 4.5693,
      "step": 210
    },
    {
      "epoch": 0.17868020304568527,
      "grad_norm": 23.78508949279785,
      "learning_rate": 1e-05,
      "loss": 4.1313,
      "step": 220
    },
    {
      "epoch": 0.18680203045685279,
      "grad_norm": 45.04022216796875,
      "learning_rate": 1e-05,
      "loss": 3.9489,
      "step": 230
    },
    {
      "epoch": 0.1949238578680203,
      "grad_norm": 71.63549041748047,
      "learning_rate": 1e-05,
      "loss": 4.2415,
      "step": 240
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 26.323184967041016,
      "learning_rate": 1e-05,
      "loss": 4.0965,
      "step": 250
    },
    {
      "epoch": 0.21116751269035533,
      "grad_norm": 16.836837768554688,
      "learning_rate": 1e-05,
      "loss": 4.45,
      "step": 260
    },
    {
      "epoch": 0.21928934010152284,
      "grad_norm": 16.173458099365234,
      "learning_rate": 1e-05,
      "loss": 4.3143,
      "step": 270
    },
    {
      "epoch": 0.22741116751269036,
      "grad_norm": 21.401058197021484,
      "learning_rate": 1e-05,
      "loss": 4.1259,
      "step": 280
    },
    {
      "epoch": 0.23553299492385787,
      "grad_norm": 16.53544807434082,
      "learning_rate": 1e-05,
      "loss": 3.9455,
      "step": 290
    },
    {
      "epoch": 0.2436548223350254,
      "grad_norm": 41.04811477661133,
      "learning_rate": 1e-05,
      "loss": 4.2589,
      "step": 300
    },
    {
      "epoch": 0.2517766497461929,
      "grad_norm": 23.9962100982666,
      "learning_rate": 1e-05,
      "loss": 3.9387,
      "step": 310
    },
    {
      "epoch": 0.2598984771573604,
      "grad_norm": 17.39070701599121,
      "learning_rate": 1e-05,
      "loss": 3.9659,
      "step": 320
    },
    {
      "epoch": 0.26802030456852793,
      "grad_norm": 20.718320846557617,
      "learning_rate": 1e-05,
      "loss": 4.1939,
      "step": 330
    },
    {
      "epoch": 0.27614213197969545,
      "grad_norm": 21.084014892578125,
      "learning_rate": 1e-05,
      "loss": 4.0113,
      "step": 340
    },
    {
      "epoch": 0.28426395939086296,
      "grad_norm": 18.71249771118164,
      "learning_rate": 1e-05,
      "loss": 4.0938,
      "step": 350
    },
    {
      "epoch": 0.2923857868020305,
      "grad_norm": 19.675750732421875,
      "learning_rate": 1e-05,
      "loss": 4.0688,
      "step": 360
    },
    {
      "epoch": 0.300507614213198,
      "grad_norm": 15.646931648254395,
      "learning_rate": 1e-05,
      "loss": 4.0609,
      "step": 370
    },
    {
      "epoch": 0.3086294416243655,
      "grad_norm": 24.256332397460938,
      "learning_rate": 1e-05,
      "loss": 4.0713,
      "step": 380
    },
    {
      "epoch": 0.31675126903553297,
      "grad_norm": 24.5927791595459,
      "learning_rate": 1e-05,
      "loss": 4.3,
      "step": 390
    },
    {
      "epoch": 0.3248730964467005,
      "grad_norm": 46.62877655029297,
      "learning_rate": 1e-05,
      "loss": 4.0425,
      "step": 400
    },
    {
      "epoch": 0.332994923857868,
      "grad_norm": 24.026994705200195,
      "learning_rate": 1e-05,
      "loss": 3.8624,
      "step": 410
    },
    {
      "epoch": 0.3411167512690355,
      "grad_norm": 20.81216049194336,
      "learning_rate": 1e-05,
      "loss": 3.8984,
      "step": 420
    },
    {
      "epoch": 0.349238578680203,
      "grad_norm": 35.375,
      "learning_rate": 1e-05,
      "loss": 4.1193,
      "step": 430
    },
    {
      "epoch": 0.35736040609137054,
      "grad_norm": 21.53089714050293,
      "learning_rate": 1e-05,
      "loss": 4.1257,
      "step": 440
    },
    {
      "epoch": 0.36548223350253806,
      "grad_norm": 18.38172149658203,
      "learning_rate": 1e-05,
      "loss": 4.1783,
      "step": 450
    },
    {
      "epoch": 0.37360406091370557,
      "grad_norm": 16.278270721435547,
      "learning_rate": 1e-05,
      "loss": 4.2778,
      "step": 460
    },
    {
      "epoch": 0.3817258883248731,
      "grad_norm": 14.751913070678711,
      "learning_rate": 1e-05,
      "loss": 4.1427,
      "step": 470
    },
    {
      "epoch": 0.3898477157360406,
      "grad_norm": 15.302434921264648,
      "learning_rate": 1e-05,
      "loss": 4.0447,
      "step": 480
    },
    {
      "epoch": 0.3979695431472081,
      "grad_norm": 14.414872169494629,
      "learning_rate": 1e-05,
      "loss": 4.3692,
      "step": 490
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 24.612342834472656,
      "learning_rate": 1e-05,
      "loss": 3.8911,
      "step": 500
    },
    {
      "epoch": 0.41421319796954315,
      "grad_norm": 13.705610275268555,
      "learning_rate": 1e-05,
      "loss": 3.9259,
      "step": 510
    },
    {
      "epoch": 0.42233502538071066,
      "grad_norm": 17.179527282714844,
      "learning_rate": 1e-05,
      "loss": 4.0789,
      "step": 520
    },
    {
      "epoch": 0.4304568527918782,
      "grad_norm": 37.49785614013672,
      "learning_rate": 1e-05,
      "loss": 3.8981,
      "step": 530
    },
    {
      "epoch": 0.4385786802030457,
      "grad_norm": 16.19457244873047,
      "learning_rate": 1e-05,
      "loss": 3.8851,
      "step": 540
    },
    {
      "epoch": 0.4467005076142132,
      "grad_norm": 35.1661262512207,
      "learning_rate": 1e-05,
      "loss": 3.8972,
      "step": 550
    },
    {
      "epoch": 0.4548223350253807,
      "grad_norm": 20.685251235961914,
      "learning_rate": 1e-05,
      "loss": 4.1963,
      "step": 560
    },
    {
      "epoch": 0.46294416243654823,
      "grad_norm": 23.330116271972656,
      "learning_rate": 1e-05,
      "loss": 4.1061,
      "step": 570
    },
    {
      "epoch": 0.47106598984771575,
      "grad_norm": 21.28797149658203,
      "learning_rate": 1e-05,
      "loss": 4.0031,
      "step": 580
    },
    {
      "epoch": 0.47918781725888326,
      "grad_norm": 34.29547882080078,
      "learning_rate": 1e-05,
      "loss": 3.89,
      "step": 590
    },
    {
      "epoch": 0.4873096446700508,
      "grad_norm": 16.874467849731445,
      "learning_rate": 1e-05,
      "loss": 3.981,
      "step": 600
    },
    {
      "epoch": 0.4954314720812183,
      "grad_norm": 48.60663604736328,
      "learning_rate": 1e-05,
      "loss": 3.6474,
      "step": 610
    },
    {
      "epoch": 0.5035532994923858,
      "grad_norm": 17.85841941833496,
      "learning_rate": 1e-05,
      "loss": 3.8523,
      "step": 620
    },
    {
      "epoch": 0.5116751269035533,
      "grad_norm": 16.842727661132812,
      "learning_rate": 1e-05,
      "loss": 3.7662,
      "step": 630
    },
    {
      "epoch": 0.5197969543147208,
      "grad_norm": 13.67222785949707,
      "learning_rate": 1e-05,
      "loss": 3.9252,
      "step": 640
    },
    {
      "epoch": 0.5279187817258884,
      "grad_norm": 27.607187271118164,
      "learning_rate": 1e-05,
      "loss": 3.8711,
      "step": 650
    },
    {
      "epoch": 0.5360406091370559,
      "grad_norm": 16.094017028808594,
      "learning_rate": 1e-05,
      "loss": 3.8445,
      "step": 660
    },
    {
      "epoch": 0.5441624365482234,
      "grad_norm": 18.13494300842285,
      "learning_rate": 1e-05,
      "loss": 3.8238,
      "step": 670
    },
    {
      "epoch": 0.5522842639593909,
      "grad_norm": 19.074691772460938,
      "learning_rate": 1e-05,
      "loss": 3.8702,
      "step": 680
    },
    {
      "epoch": 0.5604060913705584,
      "grad_norm": 22.06578826904297,
      "learning_rate": 1e-05,
      "loss": 3.7489,
      "step": 690
    },
    {
      "epoch": 0.5685279187817259,
      "grad_norm": 26.354393005371094,
      "learning_rate": 1e-05,
      "loss": 3.9093,
      "step": 700
    },
    {
      "epoch": 0.5766497461928934,
      "grad_norm": 24.7266902923584,
      "learning_rate": 1e-05,
      "loss": 3.9081,
      "step": 710
    },
    {
      "epoch": 0.584771573604061,
      "grad_norm": 157.5274658203125,
      "learning_rate": 1e-05,
      "loss": 3.7991,
      "step": 720
    },
    {
      "epoch": 0.5928934010152285,
      "grad_norm": 13.977652549743652,
      "learning_rate": 1e-05,
      "loss": 3.8534,
      "step": 730
    },
    {
      "epoch": 0.601015228426396,
      "grad_norm": 23.18590545654297,
      "learning_rate": 1e-05,
      "loss": 3.7186,
      "step": 740
    },
    {
      "epoch": 0.6091370558375635,
      "grad_norm": 21.272268295288086,
      "learning_rate": 1e-05,
      "loss": 3.6527,
      "step": 750
    },
    {
      "epoch": 0.617258883248731,
      "grad_norm": 12.396414756774902,
      "learning_rate": 1e-05,
      "loss": 3.8253,
      "step": 760
    },
    {
      "epoch": 0.6253807106598985,
      "grad_norm": 23.42069435119629,
      "learning_rate": 1e-05,
      "loss": 3.5519,
      "step": 770
    },
    {
      "epoch": 0.6335025380710659,
      "grad_norm": 37.46588134765625,
      "learning_rate": 1e-05,
      "loss": 4.0507,
      "step": 780
    },
    {
      "epoch": 0.6416243654822334,
      "grad_norm": 19.958589553833008,
      "learning_rate": 1e-05,
      "loss": 3.8356,
      "step": 790
    },
    {
      "epoch": 0.649746192893401,
      "grad_norm": 19.55034065246582,
      "learning_rate": 1e-05,
      "loss": 3.8896,
      "step": 800
    },
    {
      "epoch": 0.6578680203045685,
      "grad_norm": 26.097702026367188,
      "learning_rate": 1e-05,
      "loss": 3.6991,
      "step": 810
    },
    {
      "epoch": 0.665989847715736,
      "grad_norm": 11.718663215637207,
      "learning_rate": 1e-05,
      "loss": 3.8669,
      "step": 820
    },
    {
      "epoch": 0.6741116751269035,
      "grad_norm": 33.31325912475586,
      "learning_rate": 1e-05,
      "loss": 3.6552,
      "step": 830
    },
    {
      "epoch": 0.682233502538071,
      "grad_norm": 12.342451095581055,
      "learning_rate": 1e-05,
      "loss": 3.9127,
      "step": 840
    },
    {
      "epoch": 0.6903553299492385,
      "grad_norm": 24.607454299926758,
      "learning_rate": 1e-05,
      "loss": 3.962,
      "step": 850
    },
    {
      "epoch": 0.698477157360406,
      "grad_norm": 24.218826293945312,
      "learning_rate": 1e-05,
      "loss": 3.6696,
      "step": 860
    },
    {
      "epoch": 0.7065989847715736,
      "grad_norm": 32.117637634277344,
      "learning_rate": 1e-05,
      "loss": 3.7483,
      "step": 870
    },
    {
      "epoch": 0.7147208121827411,
      "grad_norm": 58.07627487182617,
      "learning_rate": 1e-05,
      "loss": 3.7235,
      "step": 880
    },
    {
      "epoch": 0.7228426395939086,
      "grad_norm": 11.99846363067627,
      "learning_rate": 1e-05,
      "loss": 3.8395,
      "step": 890
    },
    {
      "epoch": 0.7309644670050761,
      "grad_norm": 10.11760139465332,
      "learning_rate": 1e-05,
      "loss": 3.8185,
      "step": 900
    },
    {
      "epoch": 0.7390862944162436,
      "grad_norm": 24.675113677978516,
      "learning_rate": 1e-05,
      "loss": 3.6996,
      "step": 910
    },
    {
      "epoch": 0.7472081218274111,
      "grad_norm": 18.547998428344727,
      "learning_rate": 1e-05,
      "loss": 3.6897,
      "step": 920
    },
    {
      "epoch": 0.7553299492385787,
      "grad_norm": 13.198604583740234,
      "learning_rate": 1e-05,
      "loss": 3.8805,
      "step": 930
    },
    {
      "epoch": 0.7634517766497462,
      "grad_norm": 19.13780975341797,
      "learning_rate": 1e-05,
      "loss": 3.7328,
      "step": 940
    },
    {
      "epoch": 0.7715736040609137,
      "grad_norm": 31.780717849731445,
      "learning_rate": 1e-05,
      "loss": 3.7972,
      "step": 950
    },
    {
      "epoch": 0.7796954314720812,
      "grad_norm": 10.4293212890625,
      "learning_rate": 1e-05,
      "loss": 3.6281,
      "step": 960
    },
    {
      "epoch": 0.7878172588832487,
      "grad_norm": 11.859379768371582,
      "learning_rate": 1e-05,
      "loss": 3.6333,
      "step": 970
    },
    {
      "epoch": 0.7959390862944162,
      "grad_norm": 36.20627212524414,
      "learning_rate": 1e-05,
      "loss": 3.9035,
      "step": 980
    },
    {
      "epoch": 0.8040609137055837,
      "grad_norm": 10.703596115112305,
      "learning_rate": 1e-05,
      "loss": 3.7858,
      "step": 990
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 14.754021644592285,
      "learning_rate": 1e-05,
      "loss": 3.9461,
      "step": 1000
    },
    {
      "epoch": 0.8203045685279188,
      "grad_norm": 15.9295072555542,
      "learning_rate": 1e-05,
      "loss": 3.7131,
      "step": 1010
    },
    {
      "epoch": 0.8284263959390863,
      "grad_norm": 29.08304214477539,
      "learning_rate": 1e-05,
      "loss": 3.9495,
      "step": 1020
    },
    {
      "epoch": 0.8365482233502538,
      "grad_norm": 11.569452285766602,
      "learning_rate": 1e-05,
      "loss": 3.9859,
      "step": 1030
    },
    {
      "epoch": 0.8446700507614213,
      "grad_norm": 40.327369689941406,
      "learning_rate": 1e-05,
      "loss": 3.8321,
      "step": 1040
    },
    {
      "epoch": 0.8527918781725888,
      "grad_norm": 14.902921676635742,
      "learning_rate": 1e-05,
      "loss": 3.5383,
      "step": 1050
    },
    {
      "epoch": 0.8609137055837564,
      "grad_norm": 19.582128524780273,
      "learning_rate": 1e-05,
      "loss": 3.721,
      "step": 1060
    },
    {
      "epoch": 0.8690355329949239,
      "grad_norm": 12.84428596496582,
      "learning_rate": 1e-05,
      "loss": 3.6479,
      "step": 1070
    },
    {
      "epoch": 0.8771573604060914,
      "grad_norm": 11.455567359924316,
      "learning_rate": 1e-05,
      "loss": 3.7444,
      "step": 1080
    },
    {
      "epoch": 0.8852791878172589,
      "grad_norm": 17.67003631591797,
      "learning_rate": 1e-05,
      "loss": 3.889,
      "step": 1090
    },
    {
      "epoch": 0.8934010152284264,
      "grad_norm": 155.48483276367188,
      "learning_rate": 1e-05,
      "loss": 3.8639,
      "step": 1100
    },
    {
      "epoch": 0.9015228426395939,
      "grad_norm": 17.0788516998291,
      "learning_rate": 1e-05,
      "loss": 3.5827,
      "step": 1110
    },
    {
      "epoch": 0.9096446700507614,
      "grad_norm": 10.695856094360352,
      "learning_rate": 1e-05,
      "loss": 4.028,
      "step": 1120
    },
    {
      "epoch": 0.917766497461929,
      "grad_norm": 10.334482192993164,
      "learning_rate": 1e-05,
      "loss": 3.8132,
      "step": 1130
    },
    {
      "epoch": 0.9258883248730965,
      "grad_norm": 31.564964294433594,
      "learning_rate": 1e-05,
      "loss": 3.65,
      "step": 1140
    },
    {
      "epoch": 0.934010152284264,
      "grad_norm": 26.028892517089844,
      "learning_rate": 1e-05,
      "loss": 3.9489,
      "step": 1150
    },
    {
      "epoch": 0.9421319796954315,
      "grad_norm": 12.927952766418457,
      "learning_rate": 1e-05,
      "loss": 3.9559,
      "step": 1160
    },
    {
      "epoch": 0.950253807106599,
      "grad_norm": 16.242618560791016,
      "learning_rate": 1e-05,
      "loss": 4.0574,
      "step": 1170
    },
    {
      "epoch": 0.9583756345177665,
      "grad_norm": 20.16547393798828,
      "learning_rate": 1e-05,
      "loss": 3.7308,
      "step": 1180
    },
    {
      "epoch": 0.966497461928934,
      "grad_norm": 11.609495162963867,
      "learning_rate": 1e-05,
      "loss": 3.8302,
      "step": 1190
    },
    {
      "epoch": 0.9746192893401016,
      "grad_norm": 21.92005729675293,
      "learning_rate": 1e-05,
      "loss": 3.8263,
      "step": 1200
    },
    {
      "epoch": 0.9827411167512691,
      "grad_norm": 19.72293472290039,
      "learning_rate": 1e-05,
      "loss": 3.689,
      "step": 1210
    },
    {
      "epoch": 0.9908629441624366,
      "grad_norm": 13.63465404510498,
      "learning_rate": 1e-05,
      "loss": 3.6632,
      "step": 1220
    },
    {
      "epoch": 0.9989847715736041,
      "grad_norm": 9.8516263961792,
      "learning_rate": 1e-05,
      "loss": 3.6582,
      "step": 1230
    }
  ],
  "logging_steps": 10,
  "max_steps": 1232,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.0915783012382147e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}