{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9992108378271736,
  "eval_steps": 500,
  "global_step": 1900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 21.429368641007674,
      "learning_rate": 7.017543859649123e-08,
      "loss": 1.3492,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 7.31312382727859,
      "learning_rate": 7.017543859649123e-07,
      "loss": 1.3613,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 3.007423000393036,
      "learning_rate": 1.4035087719298246e-06,
      "loss": 1.2748,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 2.0403045598401235,
      "learning_rate": 2.105263157894737e-06,
      "loss": 1.2139,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.0964386063482452,
      "learning_rate": 2.8070175438596493e-06,
      "loss": 1.1675,
      "step": 40
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.8673269208557858,
      "learning_rate": 3.5087719298245615e-06,
      "loss": 1.1426,
      "step": 50
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.9321512205829348,
      "learning_rate": 4.210526315789474e-06,
      "loss": 1.1429,
      "step": 60
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.8679633177498763,
      "learning_rate": 4.912280701754386e-06,
      "loss": 1.1172,
      "step": 70
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.8837362567367552,
      "learning_rate": 5.6140350877192985e-06,
      "loss": 1.1265,
      "step": 80
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.8764206258248486,
      "learning_rate": 6.31578947368421e-06,
      "loss": 1.1018,
      "step": 90
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.7946842003727972,
      "learning_rate": 7.017543859649123e-06,
      "loss": 1.0954,
      "step": 100
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.8556672031028142,
      "learning_rate": 7.719298245614036e-06,
      "loss": 1.1026,
      "step": 110
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9218462405321642,
      "learning_rate": 8.421052631578948e-06,
      "loss": 1.106,
      "step": 120
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.8068032094497395,
      "learning_rate": 9.12280701754386e-06,
      "loss": 1.09,
      "step": 130
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.8339454651398522,
      "learning_rate": 9.824561403508772e-06,
      "loss": 1.0831,
      "step": 140
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.9036107262137951,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 1.0992,
      "step": 150
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.9507432313402697,
      "learning_rate": 1.1228070175438597e-05,
      "loss": 1.0784,
      "step": 160
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.8907962932508753,
      "learning_rate": 1.192982456140351e-05,
      "loss": 1.0945,
      "step": 170
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.9738408667871853,
      "learning_rate": 1.263157894736842e-05,
      "loss": 1.0942,
      "step": 180
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9062994953351728,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.0805,
      "step": 190
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.876947526057646,
      "learning_rate": 1.4035087719298246e-05,
      "loss": 1.0913,
      "step": 200
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.0277290799105536,
      "learning_rate": 1.4736842105263159e-05,
      "loss": 1.0876,
      "step": 210
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.885527804467122,
      "learning_rate": 1.543859649122807e-05,
      "loss": 1.0815,
      "step": 220
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.9859422411610012,
      "learning_rate": 1.6140350877192984e-05,
      "loss": 1.0908,
      "step": 230
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0229418982903158,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 1.0791,
      "step": 240
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.8569947258085523,
      "learning_rate": 1.754385964912281e-05,
      "loss": 1.0853,
      "step": 250
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.8783916684369713,
      "learning_rate": 1.824561403508772e-05,
      "loss": 1.0941,
      "step": 260
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.8738383070305185,
      "learning_rate": 1.894736842105263e-05,
      "loss": 1.0838,
      "step": 270
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.9534322549204314,
      "learning_rate": 1.9649122807017544e-05,
      "loss": 1.0959,
      "step": 280
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.9650066100194556,
      "learning_rate": 1.9999812486015525e-05,
      "loss": 1.0874,
      "step": 290
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9216993889093766,
      "learning_rate": 1.999831241633323e-05,
      "loss": 1.1062,
      "step": 300
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.8877068992817276,
      "learning_rate": 1.9995312501993765e-05,
      "loss": 1.0869,
      "step": 310
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.7994033406223618,
      "learning_rate": 1.9990813193013625e-05,
      "loss": 1.1007,
      "step": 320
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.8897446412058863,
      "learning_rate": 1.9984815164333163e-05,
      "loss": 1.1015,
      "step": 330
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.8778722190072454,
      "learning_rate": 1.997731931571535e-05,
      "loss": 1.0809,
      "step": 340
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.8678685090268201,
      "learning_rate": 1.9968326771610797e-05,
      "loss": 1.0842,
      "step": 350
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.8650925218664476,
      "learning_rate": 1.9957838880989076e-05,
      "loss": 1.0873,
      "step": 360
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.8697128878351399,
      "learning_rate": 1.9945857217136365e-05,
      "loss": 1.09,
      "step": 370
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8530013045101023,
      "learning_rate": 1.9932383577419432e-05,
      "loss": 1.0796,
      "step": 380
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8894110888486104,
      "learning_rate": 1.9917419983016025e-05,
      "loss": 1.0865,
      "step": 390
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.741007374421567,
      "learning_rate": 1.9900968678611664e-05,
      "loss": 1.0737,
      "step": 400
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.8681690517112644,
      "learning_rate": 1.9883032132062926e-05,
      "loss": 1.0926,
      "step": 410
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.8833251327405618,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 1.0749,
      "step": 420
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.8981504263742338,
      "learning_rate": 1.9842714297559212e-05,
      "loss": 1.0816,
      "step": 430
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.978688604732774,
      "learning_rate": 1.9820339057673773e-05,
      "loss": 1.0935,
      "step": 440
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.8996937553022554,
      "learning_rate": 1.979649067087574e-05,
      "loss": 1.0826,
      "step": 450
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.8811418408051818,
      "learning_rate": 1.97711727146564e-05,
      "loss": 1.0879,
      "step": 460
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.0101190939103164,
      "learning_rate": 1.9744388986956824e-05,
      "loss": 1.0877,
      "step": 470
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.7613467454313384,
      "learning_rate": 1.971614350559814e-05,
      "loss": 1.0727,
      "step": 480
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.7703159126101999,
      "learning_rate": 1.9686440507678827e-05,
      "loss": 1.0733,
      "step": 490
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.7868241714503517,
      "learning_rate": 1.9655284448939094e-05,
      "loss": 1.0712,
      "step": 500
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.7897482799062521,
      "learning_rate": 1.9622680003092503e-05,
      "loss": 1.0802,
      "step": 510
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.7588882568608744,
      "learning_rate": 1.9588632061124837e-05,
      "loss": 1.0922,
      "step": 520
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.7382743506650484,
      "learning_rate": 1.9553145730560415e-05,
      "loss": 1.077,
      "step": 530
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.8453793493894306,
      "learning_rate": 1.951622633469592e-05,
      "loss": 1.0754,
      "step": 540
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.7110389209689899,
      "learning_rate": 1.9477879411801843e-05,
      "loss": 1.078,
      "step": 550
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.8056008052980671,
      "learning_rate": 1.9438110714291697e-05,
      "loss": 1.0728,
      "step": 560
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.9240547335105442,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 1.0653,
      "step": 570
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.781437426142816,
      "learning_rate": 1.935433207058281e-05,
      "loss": 1.0901,
      "step": 580
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.8686654994863429,
      "learning_rate": 1.9310334692000077e-05,
      "loss": 1.0983,
      "step": 590
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.7772396469297038,
      "learning_rate": 1.9264940672148018e-05,
      "loss": 1.0708,
      "step": 600
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7651697115565855,
      "learning_rate": 1.9218156820573618e-05,
      "loss": 1.0817,
      "step": 610
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.7565300585910141,
      "learning_rate": 1.916999015531221e-05,
      "loss": 1.0915,
      "step": 620
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.8420338788100721,
      "learning_rate": 1.9120447901834708e-05,
      "loss": 1.0719,
      "step": 630
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.7588794329097819,
      "learning_rate": 1.906953749196371e-05,
      "loss": 1.0698,
      "step": 640
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.8810609158187063,
      "learning_rate": 1.901726656275866e-05,
      "loss": 1.0734,
      "step": 650
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.848783007432763,
      "learning_rate": 1.8963642955370203e-05,
      "loss": 1.0761,
      "step": 660
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.8595204312733032,
      "learning_rate": 1.890867471386395e-05,
      "loss": 1.0751,
      "step": 670
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8035640869223637,
      "learning_rate": 1.8852370084013783e-05,
      "loss": 1.0674,
      "step": 680
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.7926712110270574,
      "learning_rate": 1.879473751206489e-05,
      "loss": 1.0788,
      "step": 690
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.7472134613955423,
      "learning_rate": 1.8735785643466786e-05,
      "loss": 1.0711,
      "step": 700
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.7535511662219013,
      "learning_rate": 1.867552332157637e-05,
      "loss": 1.0786,
      "step": 710
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.7620302080300618,
      "learning_rate": 1.8613959586331364e-05,
      "loss": 1.0748,
      "step": 720
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.7771293813366091,
      "learning_rate": 1.855110367289421e-05,
      "loss": 1.0734,
      "step": 730
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.7520618932539609,
      "learning_rate": 1.8486965010266726e-05,
      "loss": 1.0843,
      "step": 740
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.7523029137721694,
      "learning_rate": 1.842155321987566e-05,
      "loss": 1.0759,
      "step": 750
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7323944181966383,
      "learning_rate": 1.8354878114129368e-05,
      "loss": 1.0577,
      "step": 760
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.8216142632382807,
      "learning_rate": 1.8286949694945864e-05,
      "loss": 1.063,
      "step": 770
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.9331761680038722,
      "learning_rate": 1.821777815225245e-05,
      "loss": 1.0653,
      "step": 780
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.7463038001394499,
      "learning_rate": 1.8147373862457107e-05,
      "loss": 1.0796,
      "step": 790
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.8497591810239704,
      "learning_rate": 1.807574738689193e-05,
      "loss": 1.0646,
      "step": 800
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.7706758595869727,
      "learning_rate": 1.800290947022884e-05,
      "loss": 1.0751,
      "step": 810
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.7043413482735349,
      "learning_rate": 1.7928871038867785e-05,
      "loss": 1.0608,
      "step": 820
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.8329829504677462,
      "learning_rate": 1.7853643199297632e-05,
      "loss": 1.0809,
      "step": 830
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.749386798044592,
      "learning_rate": 1.777723723643014e-05,
      "loss": 1.0744,
      "step": 840
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.7517374580777705,
      "learning_rate": 1.769966461190707e-05,
      "loss": 1.0588,
      "step": 850
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.9289661993883984,
      "learning_rate": 1.762093696238086e-05,
      "loss": 1.0592,
      "step": 860
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.702861524628992,
      "learning_rate": 1.7541066097768965e-05,
      "loss": 1.0671,
      "step": 870
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.733335804526001,
      "learning_rate": 1.7460063999482314e-05,
      "loss": 1.0718,
      "step": 880
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.7062706365131609,
      "learning_rate": 1.737794281862794e-05,
      "loss": 1.0688,
      "step": 890
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.7356207256793295,
      "learning_rate": 1.729471487418621e-05,
      "loss": 1.0658,
      "step": 900
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7572566444671317,
      "learning_rate": 1.721039265116285e-05,
      "loss": 1.0655,
      "step": 910
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.735805885071863,
      "learning_rate": 1.7124988798716084e-05,
      "loss": 1.0545,
      "step": 920
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.7251156689638848,
      "learning_rate": 1.7038516128259118e-05,
      "loss": 1.0668,
      "step": 930
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.8306937180459297,
      "learning_rate": 1.695098761153832e-05,
      "loss": 1.0575,
      "step": 940
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7410203095059583,
      "learning_rate": 1.686241637868734e-05,
      "loss": 1.0608,
      "step": 950
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0695801973342896,
      "eval_runtime": 1107.1718,
      "eval_samples_per_second": 12.154,
      "eval_steps_per_second": 0.76,
      "step": 950
    },
    {
      "epoch": 1.01,
      "grad_norm": 1.16058288449513,
      "learning_rate": 1.6772815716257414e-05,
      "loss": 0.9274,
      "step": 960
    },
    {
      "epoch": 1.02,
      "grad_norm": 1.0275862927417232,
      "learning_rate": 1.6682199065224307e-05,
      "loss": 0.9092,
      "step": 970
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.8572569275851243,
      "learning_rate": 1.6590580018972012e-05,
      "loss": 0.9214,
      "step": 980
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.8103196292462057,
      "learning_rate": 1.64979723212536e-05,
      "loss": 0.922,
      "step": 990
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.9343043639973103,
      "learning_rate": 1.6404389864129533e-05,
      "loss": 0.9143,
      "step": 1000
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.8577834657562019,
      "learning_rate": 1.6309846685883726e-05,
      "loss": 0.9108,
      "step": 1010
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.7694790034514357,
      "learning_rate": 1.621435696891765e-05,
      "loss": 0.9112,
      "step": 1020
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.7881582670286174,
      "learning_rate": 1.6117935037622848e-05,
      "loss": 0.9166,
      "step": 1030
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.8163445575344302,
      "learning_rate": 1.6020595356232137e-05,
      "loss": 0.9168,
      "step": 1040
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.7808590648116421,
      "learning_rate": 1.5922352526649803e-05,
      "loss": 0.9183,
      "step": 1050
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.8694235628482853,
      "learning_rate": 1.5823221286261217e-05,
      "loss": 0.9295,
      "step": 1060
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.7509497034921186,
      "learning_rate": 1.572321650572205e-05,
      "loss": 0.92,
      "step": 1070
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.8147167421280597,
      "learning_rate": 1.5622353186727542e-05,
      "loss": 0.9341,
      "step": 1080
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.8078856301262012,
      "learning_rate": 1.5520646459762102e-05,
      "loss": 0.9225,
      "step": 1090
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.7215279351968892,
      "learning_rate": 1.5418111581829575e-05,
      "loss": 0.9116,
      "step": 1100
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.7295126696154695,
      "learning_rate": 1.531476393416456e-05,
      "loss": 0.9104,
      "step": 1110
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.8135765592831766,
      "learning_rate": 1.5210619019925066e-05,
      "loss": 0.9315,
      "step": 1120
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.8840016217189187,
      "learning_rate": 1.5105692461866874e-05,
      "loss": 0.9197,
      "step": 1130
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.8104545240762417,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.9159,
      "step": 1140
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.7692322199629117,
      "learning_rate": 1.4893557489227518e-05,
      "loss": 0.9191,
      "step": 1150
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.8223799154663355,
      "learning_rate": 1.478638089696716e-05,
      "loss": 0.9102,
      "step": 1160
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.7443893394953662,
      "learning_rate": 1.467848630075608e-05,
      "loss": 0.9212,
      "step": 1170
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.7900297431396095,
      "learning_rate": 1.456988988583904e-05,
      "loss": 0.9274,
      "step": 1180
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.8344369201219162,
      "learning_rate": 1.4460607942740468e-05,
      "loss": 0.923,
      "step": 1190
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.9319670376335052,
      "learning_rate": 1.4350656864820733e-05,
      "loss": 0.9164,
      "step": 1200
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.7526336939340502,
      "learning_rate": 1.4240053145816968e-05,
      "loss": 0.9157,
      "step": 1210
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.9004879689820842,
      "learning_rate": 1.4128813377368851e-05,
      "loss": 0.9124,
      "step": 1220
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.7963894514570174,
      "learning_rate": 1.4016954246529697e-05,
      "loss": 0.9208,
      "step": 1230
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.867489112759267,
      "learning_rate": 1.3904492533263243e-05,
      "loss": 0.9257,
      "step": 1240
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.7815367295791487,
      "learning_rate": 1.3791445107926478e-05,
      "loss": 0.9182,
      "step": 1250
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.8678431722314973,
      "learning_rate": 1.3677828928738934e-05,
      "loss": 0.9218,
      "step": 1260
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.7941451121772987,
      "learning_rate": 1.3563661039238785e-05,
      "loss": 0.9304,
      "step": 1270
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.7742431211390169,
      "learning_rate": 1.3448958565726144e-05,
      "loss": 0.9234,
      "step": 1280
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.7634049344229958,
      "learning_rate": 1.3333738714693958e-05,
      "loss": 0.9176,
      "step": 1290
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.8108629000712599,
      "learning_rate": 1.3218018770246858e-05,
      "loss": 0.9035,
      "step": 1300
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.747630866975614,
      "learning_rate": 1.3101816091508389e-05,
      "loss": 0.9125,
      "step": 1310
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.7793584345888945,
      "learning_rate": 1.2985148110016947e-05,
      "loss": 0.9128,
      "step": 1320
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.788003717890724,
      "learning_rate": 1.2868032327110904e-05,
      "loss": 0.9156,
      "step": 1330
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.7602070916944652,
      "learning_rate": 1.2750486311303218e-05,
      "loss": 0.9178,
      "step": 1340
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.7526823803299355,
      "learning_rate": 1.2632527695645993e-05,
      "loss": 0.9275,
      "step": 1350
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.7855296800390148,
      "learning_rate": 1.2514174175085346e-05,
      "loss": 0.9248,
      "step": 1360
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.7554953629554423,
      "learning_rate": 1.239544350380699e-05,
      "loss": 0.9173,
      "step": 1370
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.8450238703674462,
      "learning_rate": 1.2276353492572937e-05,
      "loss": 0.9053,
      "step": 1380
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.7798006206733635,
      "learning_rate": 1.2156922006049703e-05,
      "loss": 0.9198,
      "step": 1390
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.8364819432425579,
      "learning_rate": 1.2037166960128443e-05,
      "loss": 0.9223,
      "step": 1400
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.7977694082425033,
      "learning_rate": 1.1917106319237386e-05,
      "loss": 0.9295,
      "step": 1410
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.7952817409309066,
      "learning_rate": 1.1796758093646989e-05,
      "loss": 0.9049,
      "step": 1420
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.7515124212430284,
      "learning_rate": 1.1676140336768236e-05,
      "loss": 0.9161,
      "step": 1430
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.8244844518102562,
      "learning_rate": 1.1555271142444433e-05,
      "loss": 0.9306,
      "step": 1440
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.7369175193722303,
      "learning_rate": 1.1434168642236964e-05,
      "loss": 0.9038,
      "step": 1450
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.8027738354510138,
      "learning_rate": 1.1312851002705383e-05,
      "loss": 0.9158,
      "step": 1460
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.7062360581582109,
      "learning_rate": 1.1191336422682237e-05,
      "loss": 0.9089,
      "step": 1470
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.8268879803104501,
      "learning_rate": 1.1069643130543084e-05,
      "loss": 0.9092,
      "step": 1480
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.8718489443695471,
      "learning_rate": 1.0947789381472035e-05,
      "loss": 0.9198,
      "step": 1490
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.8442661853821835,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 0.9103,
      "step": 1500
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.7829036502503139,
      "learning_rate": 1.0703673650879219e-05,
      "loss": 0.9113,
      "step": 1510
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.8311518421239111,
      "learning_rate": 1.0581448289104759e-05,
      "loss": 0.9136,
      "step": 1520
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.7744326648665285,
      "learning_rate": 1.045913570439972e-05,
      "loss": 0.9151,
      "step": 1530
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.7826514271975142,
      "learning_rate": 1.0336754244848156e-05,
      "loss": 0.9121,
      "step": 1540
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.7486809723755371,
      "learning_rate": 1.0214322268866033e-05,
      "loss": 0.912,
      "step": 1550
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.7664528918396255,
      "learning_rate": 1.0091858142447266e-05,
      "loss": 0.9127,
      "step": 1560
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.7472624299086522,
      "learning_rate": 9.969380236408656e-06,
      "loss": 0.908,
      "step": 1570
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.7555438137387003,
      "learning_rate": 9.846906923634079e-06,
      "loss": 0.9116,
      "step": 1580
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.7650426487217997,
      "learning_rate": 9.724456576318383e-06,
      "loss": 0.9105,
      "step": 1590
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.7159833295095184,
      "learning_rate": 9.602047563211359e-06,
      "loss": 0.9063,
      "step": 1600
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.7715082848797897,
      "learning_rate": 9.479698246862277e-06,
      "loss": 0.8971,
      "step": 1610
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.7894584602411355,
      "learning_rate": 9.3574269808653e-06,
      "loss": 0.9016,
      "step": 1620
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.7317225702124043,
      "learning_rate": 9.23525210710628e-06,
      "loss": 0.8926,
      "step": 1630
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.752304934068834,
      "learning_rate": 9.113191953011287e-06,
      "loss": 0.9186,
      "step": 1640
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.7875568347573355,
      "learning_rate": 8.991264828797319e-06,
      "loss": 0.9127,
      "step": 1650
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.8678707556431731,
      "learning_rate": 8.869489024725595e-06,
      "loss": 0.9058,
      "step": 1660
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.7381008984105847,
      "learning_rate": 8.747882808357828e-06,
      "loss": 0.9021,
      "step": 1670
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.7113811353954564,
      "learning_rate": 8.626464421815919e-06,
      "loss": 0.9098,
      "step": 1680
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.767953884904161,
      "learning_rate": 8.505252079045459e-06,
      "loss": 0.8992,
      "step": 1690
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.7985189315270093,
      "learning_rate": 8.384263963083453e-06,
      "loss": 0.9252,
      "step": 1700
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.7698958288877892,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.9103,
      "step": 1710
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.7090644308000087,
      "learning_rate": 8.143032972829184e-06,
      "loss": 0.8954,
      "step": 1720
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.7912315130376889,
      "learning_rate": 8.022826285544967e-06,
      "loss": 0.9055,
      "step": 1730
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.7324512866653731,
      "learning_rate": 7.902916193656898e-06,
      "loss": 0.905,
      "step": 1740
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.7403537916049381,
      "learning_rate": 7.783320684851613e-06,
      "loss": 0.9078,
      "step": 1750
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.7614179219478668,
      "learning_rate": 7.664057699625215e-06,
      "loss": 0.8939,
      "step": 1760
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.7487787946919199,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.9038,
      "step": 1770
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.7493118620205345,
      "learning_rate": 7.426600809800753e-06,
      "loss": 0.8987,
      "step": 1780
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.7660149988776317,
      "learning_rate": 7.308442526058757e-06,
      "loss": 0.9103,
      "step": 1790
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.75782079047253,
      "learning_rate": 7.190688002264308e-06,
      "loss": 0.8889,
      "step": 1800
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.7314903237351683,
      "learning_rate": 7.073354902747742e-06,
      "loss": 0.8971,
      "step": 1810
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.7196432526110507,
      "learning_rate": 6.956460828621641e-06,
      "loss": 0.9006,
      "step": 1820
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.7534330383661013,
      "learning_rate": 6.840023315140476e-06,
      "loss": 0.906,
      "step": 1830
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.7482833703640341,
      "learning_rate": 6.7240598290701585e-06,
      "loss": 0.9039,
      "step": 1840
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.7448122469908642,
      "learning_rate": 6.608587766067853e-06,
      "loss": 0.8922,
      "step": 1850
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.8717367397632231,
      "learning_rate": 6.4936244480724575e-06,
      "loss": 0.9057,
      "step": 1860
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.7109756502386223,
      "learning_rate": 6.379187120706138e-06,
      "loss": 0.9042,
      "step": 1870
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.7373476878859979,
      "learning_rate": 6.265292950687329e-06,
      "loss": 0.9013,
      "step": 1880
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.7521628525759111,
      "learning_rate": 6.151959023255545e-06,
      "loss": 0.8942,
      "step": 1890
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7784149654946333,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.9014,
      "step": 1900
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0405230522155762,
      "eval_runtime": 1106.6966,
      "eval_samples_per_second": 12.16,
      "eval_steps_per_second": 0.761,
      "step": 1900
    }
  ],
  "logging_steps": 10,
  "max_steps": 2850,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 795904416153600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}