{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07272727272727272,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003636363636363636,
      "grad_norm": 0.47871133685112,
      "learning_rate": 4.999090909090909e-05,
      "loss": 1.4412,
      "step": 10
    },
    {
      "epoch": 0.0007272727272727272,
      "grad_norm": 0.4764420688152313,
      "learning_rate": 4.998181818181818e-05,
      "loss": 1.3082,
      "step": 20
    },
    {
      "epoch": 0.001090909090909091,
      "grad_norm": 0.6560420989990234,
      "learning_rate": 4.997272727272728e-05,
      "loss": 1.3592,
      "step": 30
    },
    {
      "epoch": 0.0014545454545454545,
      "grad_norm": 0.7296062111854553,
      "learning_rate": 4.996363636363637e-05,
      "loss": 1.1219,
      "step": 40
    },
    {
      "epoch": 0.0018181818181818182,
      "grad_norm": 0.46472349762916565,
      "learning_rate": 4.995454545454546e-05,
      "loss": 1.0707,
      "step": 50
    },
    {
      "epoch": 0.002181818181818182,
      "grad_norm": 0.5377005338668823,
      "learning_rate": 4.994545454545454e-05,
      "loss": 1.1453,
      "step": 60
    },
    {
      "epoch": 0.0025454545454545456,
      "grad_norm": 0.5077579021453857,
      "learning_rate": 4.993636363636364e-05,
      "loss": 1.1129,
      "step": 70
    },
    {
      "epoch": 0.002909090909090909,
      "grad_norm": 0.5722835063934326,
      "learning_rate": 4.992727272727273e-05,
      "loss": 1.1029,
      "step": 80
    },
    {
      "epoch": 0.0032727272727272726,
      "grad_norm": 0.5486398339271545,
      "learning_rate": 4.991818181818182e-05,
      "loss": 1.0021,
      "step": 90
    },
    {
      "epoch": 0.0036363636363636364,
      "grad_norm": 0.6710432171821594,
      "learning_rate": 4.990909090909091e-05,
      "loss": 1.0766,
      "step": 100
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.45256921648979187,
      "learning_rate": 4.99e-05,
      "loss": 1.0424,
      "step": 110
    },
    {
      "epoch": 0.004363636363636364,
      "grad_norm": 0.5884903073310852,
      "learning_rate": 4.98909090909091e-05,
      "loss": 1.1271,
      "step": 120
    },
    {
      "epoch": 0.0047272727272727275,
      "grad_norm": 0.8489357233047485,
      "learning_rate": 4.988181818181819e-05,
      "loss": 1.1285,
      "step": 130
    },
    {
      "epoch": 0.005090909090909091,
      "grad_norm": 0.6435407996177673,
      "learning_rate": 4.987272727272728e-05,
      "loss": 1.1967,
      "step": 140
    },
    {
      "epoch": 0.005454545454545455,
      "grad_norm": 0.5722768306732178,
      "learning_rate": 4.986363636363637e-05,
      "loss": 1.0342,
      "step": 150
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 0.4862392544746399,
      "learning_rate": 4.985454545454546e-05,
      "loss": 0.9976,
      "step": 160
    },
    {
      "epoch": 0.0061818181818181816,
      "grad_norm": 0.7204858064651489,
      "learning_rate": 4.984545454545455e-05,
      "loss": 1.0818,
      "step": 170
    },
    {
      "epoch": 0.006545454545454545,
      "grad_norm": 0.727836549282074,
      "learning_rate": 4.983636363636364e-05,
      "loss": 1.0893,
      "step": 180
    },
    {
      "epoch": 0.006909090909090909,
      "grad_norm": 0.4965401589870453,
      "learning_rate": 4.982727272727273e-05,
      "loss": 1.01,
      "step": 190
    },
    {
      "epoch": 0.007272727272727273,
      "grad_norm": 0.6770114898681641,
      "learning_rate": 4.981818181818182e-05,
      "loss": 0.9949,
      "step": 200
    },
    {
      "epoch": 0.0076363636363636364,
      "grad_norm": 0.795165479183197,
      "learning_rate": 4.980909090909091e-05,
      "loss": 1.1506,
      "step": 210
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.7894571423530579,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 1.0309,
      "step": 220
    },
    {
      "epoch": 0.008363636363636363,
      "grad_norm": 0.9198132753372192,
      "learning_rate": 4.9790909090909094e-05,
      "loss": 0.9611,
      "step": 230
    },
    {
      "epoch": 0.008727272727272728,
      "grad_norm": 0.8672171831130981,
      "learning_rate": 4.9781818181818184e-05,
      "loss": 1.1689,
      "step": 240
    },
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 0.6119312644004822,
      "learning_rate": 4.9772727272727275e-05,
      "loss": 0.9891,
      "step": 250
    },
    {
      "epoch": 0.009454545454545455,
      "grad_norm": 0.7098168134689331,
      "learning_rate": 4.9763636363636365e-05,
      "loss": 0.9369,
      "step": 260
    },
    {
      "epoch": 0.009818181818181818,
      "grad_norm": 0.7419410347938538,
      "learning_rate": 4.975454545454546e-05,
      "loss": 1.0293,
      "step": 270
    },
    {
      "epoch": 0.010181818181818183,
      "grad_norm": 0.6659941673278809,
      "learning_rate": 4.9745454545454545e-05,
      "loss": 1.0936,
      "step": 280
    },
    {
      "epoch": 0.010545454545454545,
      "grad_norm": 0.8974291682243347,
      "learning_rate": 4.9736363636363635e-05,
      "loss": 1.1088,
      "step": 290
    },
    {
      "epoch": 0.01090909090909091,
      "grad_norm": 0.7319221496582031,
      "learning_rate": 4.9727272727272725e-05,
      "loss": 0.9916,
      "step": 300
    },
    {
      "epoch": 0.011272727272727273,
      "grad_norm": 0.9040235280990601,
      "learning_rate": 4.971818181818182e-05,
      "loss": 1.1141,
      "step": 310
    },
    {
      "epoch": 0.011636363636363636,
      "grad_norm": 0.7666190266609192,
      "learning_rate": 4.970909090909091e-05,
      "loss": 1.0309,
      "step": 320
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.7975471615791321,
      "learning_rate": 4.97e-05,
      "loss": 1.0,
      "step": 330
    },
    {
      "epoch": 0.012363636363636363,
      "grad_norm": 0.7558386325836182,
      "learning_rate": 4.969090909090909e-05,
      "loss": 1.1283,
      "step": 340
    },
    {
      "epoch": 0.012727272727272728,
      "grad_norm": 0.76316899061203,
      "learning_rate": 4.968181818181818e-05,
      "loss": 1.01,
      "step": 350
    },
    {
      "epoch": 0.01309090909090909,
      "grad_norm": 0.5065900683403015,
      "learning_rate": 4.967272727272728e-05,
      "loss": 1.002,
      "step": 360
    },
    {
      "epoch": 0.013454545454545455,
      "grad_norm": 1.0256422758102417,
      "learning_rate": 4.966363636363637e-05,
      "loss": 1.0912,
      "step": 370
    },
    {
      "epoch": 0.013818181818181818,
      "grad_norm": 0.734935998916626,
      "learning_rate": 4.965454545454546e-05,
      "loss": 1.102,
      "step": 380
    },
    {
      "epoch": 0.014181818181818183,
      "grad_norm": 0.6911085844039917,
      "learning_rate": 4.964545454545455e-05,
      "loss": 1.0479,
      "step": 390
    },
    {
      "epoch": 0.014545454545454545,
      "grad_norm": 0.778714120388031,
      "learning_rate": 4.963636363636364e-05,
      "loss": 1.0379,
      "step": 400
    },
    {
      "epoch": 0.014909090909090908,
      "grad_norm": 0.6882097721099854,
      "learning_rate": 4.962727272727273e-05,
      "loss": 0.9732,
      "step": 410
    },
    {
      "epoch": 0.015272727272727273,
      "grad_norm": 0.747656524181366,
      "learning_rate": 4.961818181818182e-05,
      "loss": 1.0602,
      "step": 420
    },
    {
      "epoch": 0.015636363636363636,
      "grad_norm": 0.7968394160270691,
      "learning_rate": 4.960909090909091e-05,
      "loss": 1.1314,
      "step": 430
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.9477614760398865,
      "learning_rate": 4.96e-05,
      "loss": 1.0488,
      "step": 440
    },
    {
      "epoch": 0.016363636363636365,
      "grad_norm": 0.7730783820152283,
      "learning_rate": 4.9590909090909096e-05,
      "loss": 1.1314,
      "step": 450
    },
    {
      "epoch": 0.016727272727272726,
      "grad_norm": 1.1297029256820679,
      "learning_rate": 4.9581818181818186e-05,
      "loss": 1.0943,
      "step": 460
    },
    {
      "epoch": 0.01709090909090909,
      "grad_norm": 0.7387447357177734,
      "learning_rate": 4.9572727272727276e-05,
      "loss": 1.0711,
      "step": 470
    },
    {
      "epoch": 0.017454545454545455,
      "grad_norm": 0.5228479504585266,
      "learning_rate": 4.9563636363636367e-05,
      "loss": 1.0711,
      "step": 480
    },
    {
      "epoch": 0.01781818181818182,
      "grad_norm": 0.5137602090835571,
      "learning_rate": 4.9554545454545457e-05,
      "loss": 0.9242,
      "step": 490
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 0.859491229057312,
      "learning_rate": 4.9545454545454553e-05,
      "loss": 1.124,
      "step": 500
    },
    {
      "epoch": 0.018545454545454546,
      "grad_norm": 0.7495261430740356,
      "learning_rate": 4.953636363636364e-05,
      "loss": 1.1184,
      "step": 510
    },
    {
      "epoch": 0.01890909090909091,
      "grad_norm": 0.8758722543716431,
      "learning_rate": 4.952727272727273e-05,
      "loss": 1.1215,
      "step": 520
    },
    {
      "epoch": 0.01927272727272727,
      "grad_norm": 0.7047644257545471,
      "learning_rate": 4.951818181818182e-05,
      "loss": 1.0416,
      "step": 530
    },
    {
      "epoch": 0.019636363636363636,
      "grad_norm": 0.9179386496543884,
      "learning_rate": 4.9509090909090914e-05,
      "loss": 1.0404,
      "step": 540
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.8945435881614685,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 1.0211,
      "step": 550
    },
    {
      "epoch": 0.020363636363636365,
      "grad_norm": 0.49766021966934204,
      "learning_rate": 4.9490909090909094e-05,
      "loss": 0.9262,
      "step": 560
    },
    {
      "epoch": 0.020727272727272726,
      "grad_norm": 0.8015190958976746,
      "learning_rate": 4.9481818181818184e-05,
      "loss": 1.085,
      "step": 570
    },
    {
      "epoch": 0.02109090909090909,
      "grad_norm": 0.8135480284690857,
      "learning_rate": 4.9472727272727274e-05,
      "loss": 0.9673,
      "step": 580
    },
    {
      "epoch": 0.021454545454545455,
      "grad_norm": 0.7892040610313416,
      "learning_rate": 4.946363636363637e-05,
      "loss": 1.0301,
      "step": 590
    },
    {
      "epoch": 0.02181818181818182,
      "grad_norm": 0.6644595265388489,
      "learning_rate": 4.945454545454546e-05,
      "loss": 0.9969,
      "step": 600
    },
    {
      "epoch": 0.02218181818181818,
      "grad_norm": 0.6504725813865662,
      "learning_rate": 4.944545454545455e-05,
      "loss": 1.0686,
      "step": 610
    },
    {
      "epoch": 0.022545454545454546,
      "grad_norm": 0.5474579930305481,
      "learning_rate": 4.9436363636363634e-05,
      "loss": 1.0338,
      "step": 620
    },
    {
      "epoch": 0.02290909090909091,
      "grad_norm": 1.133872151374817,
      "learning_rate": 4.9427272727272724e-05,
      "loss": 1.0355,
      "step": 630
    },
    {
      "epoch": 0.02327272727272727,
      "grad_norm": 0.9010602235794067,
      "learning_rate": 4.941818181818182e-05,
      "loss": 1.0205,
      "step": 640
    },
    {
      "epoch": 0.023636363636363636,
      "grad_norm": 0.6271716952323914,
      "learning_rate": 4.940909090909091e-05,
      "loss": 0.9688,
      "step": 650
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.7340686917304993,
      "learning_rate": 4.94e-05,
      "loss": 1.058,
      "step": 660
    },
    {
      "epoch": 0.024363636363636365,
      "grad_norm": 0.9811447262763977,
      "learning_rate": 4.939090909090909e-05,
      "loss": 1.0941,
      "step": 670
    },
    {
      "epoch": 0.024727272727272726,
      "grad_norm": 0.8026047348976135,
      "learning_rate": 4.938181818181818e-05,
      "loss": 1.0148,
      "step": 680
    },
    {
      "epoch": 0.02509090909090909,
      "grad_norm": 0.8320631980895996,
      "learning_rate": 4.937272727272728e-05,
      "loss": 1.0332,
      "step": 690
    },
    {
      "epoch": 0.025454545454545455,
      "grad_norm": 1.0077319145202637,
      "learning_rate": 4.936363636363637e-05,
      "loss": 0.882,
      "step": 700
    },
    {
      "epoch": 0.025818181818181817,
      "grad_norm": 0.792972981929779,
      "learning_rate": 4.935454545454546e-05,
      "loss": 0.9613,
      "step": 710
    },
    {
      "epoch": 0.02618181818181818,
      "grad_norm": 0.9640710353851318,
      "learning_rate": 4.934545454545455e-05,
      "loss": 0.9879,
      "step": 720
    },
    {
      "epoch": 0.026545454545454546,
      "grad_norm": 0.6762244701385498,
      "learning_rate": 4.933636363636364e-05,
      "loss": 0.9643,
      "step": 730
    },
    {
      "epoch": 0.02690909090909091,
      "grad_norm": 0.8114360570907593,
      "learning_rate": 4.932727272727273e-05,
      "loss": 1.0049,
      "step": 740
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 0.6531985998153687,
      "learning_rate": 4.931818181818182e-05,
      "loss": 0.9141,
      "step": 750
    },
    {
      "epoch": 0.027636363636363636,
      "grad_norm": 0.846741795539856,
      "learning_rate": 4.930909090909091e-05,
      "loss": 0.9738,
      "step": 760
    },
    {
      "epoch": 0.028,
      "grad_norm": 0.8146620392799377,
      "learning_rate": 4.93e-05,
      "loss": 1.0508,
      "step": 770
    },
    {
      "epoch": 0.028363636363636365,
      "grad_norm": 0.8905590176582336,
      "learning_rate": 4.9290909090909096e-05,
      "loss": 0.9883,
      "step": 780
    },
    {
      "epoch": 0.028727272727272726,
      "grad_norm": 0.820004403591156,
      "learning_rate": 4.9281818181818186e-05,
      "loss": 1.1111,
      "step": 790
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 0.6964171528816223,
      "learning_rate": 4.9272727272727276e-05,
      "loss": 0.9889,
      "step": 800
    },
    {
      "epoch": 0.029454545454545455,
      "grad_norm": 0.7463963627815247,
      "learning_rate": 4.9263636363636366e-05,
      "loss": 1.0017,
      "step": 810
    },
    {
      "epoch": 0.029818181818181817,
      "grad_norm": 1.1425820589065552,
      "learning_rate": 4.9254545454545456e-05,
      "loss": 1.0291,
      "step": 820
    },
    {
      "epoch": 0.03018181818181818,
      "grad_norm": 0.8121577501296997,
      "learning_rate": 4.924545454545455e-05,
      "loss": 1.1896,
      "step": 830
    },
    {
      "epoch": 0.030545454545454546,
      "grad_norm": 0.7760348320007324,
      "learning_rate": 4.9236363636363636e-05,
      "loss": 1.0086,
      "step": 840
    },
    {
      "epoch": 0.03090909090909091,
      "grad_norm": 1.0461779832839966,
      "learning_rate": 4.9227272727272726e-05,
      "loss": 1.067,
      "step": 850
    },
    {
      "epoch": 0.03127272727272727,
      "grad_norm": 0.7449011206626892,
      "learning_rate": 4.9218181818181816e-05,
      "loss": 0.9166,
      "step": 860
    },
    {
      "epoch": 0.031636363636363636,
      "grad_norm": 0.8614558577537537,
      "learning_rate": 4.920909090909091e-05,
      "loss": 1.0984,
      "step": 870
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.9124776721000671,
      "learning_rate": 4.92e-05,
      "loss": 0.9428,
      "step": 880
    },
    {
      "epoch": 0.032363636363636365,
      "grad_norm": 0.7346855998039246,
      "learning_rate": 4.919090909090909e-05,
      "loss": 0.9891,
      "step": 890
    },
    {
      "epoch": 0.03272727272727273,
      "grad_norm": 0.6888474822044373,
      "learning_rate": 4.9181818181818183e-05,
      "loss": 1.1186,
      "step": 900
    },
    {
      "epoch": 0.03309090909090909,
      "grad_norm": 0.5666208267211914,
      "learning_rate": 4.9172727272727273e-05,
      "loss": 0.9862,
      "step": 910
    },
    {
      "epoch": 0.03345454545454545,
      "grad_norm": 0.6969447731971741,
      "learning_rate": 4.916363636363637e-05,
      "loss": 1.09,
      "step": 920
    },
    {
      "epoch": 0.03381818181818182,
      "grad_norm": 0.7007094025611877,
      "learning_rate": 4.915454545454546e-05,
      "loss": 0.9951,
      "step": 930
    },
    {
      "epoch": 0.03418181818181818,
      "grad_norm": 0.8678598999977112,
      "learning_rate": 4.914545454545455e-05,
      "loss": 0.9574,
      "step": 940
    },
    {
      "epoch": 0.034545454545454546,
      "grad_norm": 0.6946694850921631,
      "learning_rate": 4.913636363636364e-05,
      "loss": 1.0867,
      "step": 950
    },
    {
      "epoch": 0.03490909090909091,
      "grad_norm": 0.7773414254188538,
      "learning_rate": 4.912727272727273e-05,
      "loss": 1.0025,
      "step": 960
    },
    {
      "epoch": 0.035272727272727275,
      "grad_norm": 0.8114984631538391,
      "learning_rate": 4.911818181818182e-05,
      "loss": 0.9855,
      "step": 970
    },
    {
      "epoch": 0.03563636363636364,
      "grad_norm": 0.6157673597335815,
      "learning_rate": 4.910909090909091e-05,
      "loss": 0.9988,
      "step": 980
    },
    {
      "epoch": 0.036,
      "grad_norm": 0.8051506280899048,
      "learning_rate": 4.91e-05,
      "loss": 0.9818,
      "step": 990
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.8241102695465088,
      "learning_rate": 4.909090909090909e-05,
      "loss": 0.9893,
      "step": 1000
    },
    {
      "epoch": 0.036727272727272726,
      "grad_norm": 0.7396079897880554,
      "learning_rate": 4.908181818181818e-05,
      "loss": 0.9775,
      "step": 1010
    },
    {
      "epoch": 0.03709090909090909,
      "grad_norm": 0.730338454246521,
      "learning_rate": 4.907272727272728e-05,
      "loss": 1.0172,
      "step": 1020
    },
    {
      "epoch": 0.037454545454545456,
      "grad_norm": 0.9117375016212463,
      "learning_rate": 4.906363636363637e-05,
      "loss": 1.0273,
      "step": 1030
    },
    {
      "epoch": 0.03781818181818182,
      "grad_norm": 0.699874997138977,
      "learning_rate": 4.905454545454546e-05,
      "loss": 0.9398,
      "step": 1040
    },
    {
      "epoch": 0.038181818181818185,
      "grad_norm": 0.724445641040802,
      "learning_rate": 4.904545454545455e-05,
      "loss": 0.9617,
      "step": 1050
    },
    {
      "epoch": 0.03854545454545454,
      "grad_norm": 0.7848714590072632,
      "learning_rate": 4.903636363636364e-05,
      "loss": 1.0037,
      "step": 1060
    },
    {
      "epoch": 0.03890909090909091,
      "grad_norm": 1.0549767017364502,
      "learning_rate": 4.902727272727273e-05,
      "loss": 1.0691,
      "step": 1070
    },
    {
      "epoch": 0.03927272727272727,
      "grad_norm": 0.8227099776268005,
      "learning_rate": 4.901818181818182e-05,
      "loss": 1.0037,
      "step": 1080
    },
    {
      "epoch": 0.039636363636363636,
      "grad_norm": 1.0453096628189087,
      "learning_rate": 4.900909090909091e-05,
      "loss": 1.0145,
      "step": 1090
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.8218994140625,
      "learning_rate": 4.9e-05,
      "loss": 0.9857,
      "step": 1100
    },
    {
      "epoch": 0.040363636363636365,
      "grad_norm": 0.76604825258255,
      "learning_rate": 4.8990909090909095e-05,
      "loss": 0.9576,
      "step": 1110
    },
    {
      "epoch": 0.04072727272727273,
      "grad_norm": 0.7639636397361755,
      "learning_rate": 4.8981818181818185e-05,
      "loss": 1.0402,
      "step": 1120
    },
    {
      "epoch": 0.04109090909090909,
      "grad_norm": 0.8489947319030762,
      "learning_rate": 4.8972727272727275e-05,
      "loss": 1.023,
      "step": 1130
    },
    {
      "epoch": 0.04145454545454545,
      "grad_norm": 0.7406574487686157,
      "learning_rate": 4.8963636363636365e-05,
      "loss": 1.0324,
      "step": 1140
    },
    {
      "epoch": 0.04181818181818182,
      "grad_norm": 0.6394333243370056,
      "learning_rate": 4.8954545454545456e-05,
      "loss": 0.9831,
      "step": 1150
    },
    {
      "epoch": 0.04218181818181818,
      "grad_norm": 0.9677541851997375,
      "learning_rate": 4.894545454545455e-05,
      "loss": 0.9928,
      "step": 1160
    },
    {
      "epoch": 0.042545454545454546,
      "grad_norm": 0.7677833437919617,
      "learning_rate": 4.893636363636364e-05,
      "loss": 0.9301,
      "step": 1170
    },
    {
      "epoch": 0.04290909090909091,
      "grad_norm": 0.6206602454185486,
      "learning_rate": 4.8927272727272726e-05,
      "loss": 1.0012,
      "step": 1180
    },
    {
      "epoch": 0.043272727272727275,
      "grad_norm": 0.8425969481468201,
      "learning_rate": 4.8918181818181816e-05,
      "loss": 1.1275,
      "step": 1190
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": 0.7413673400878906,
      "learning_rate": 4.890909090909091e-05,
      "loss": 1.0117,
      "step": 1200
    },
    {
      "epoch": 0.044,
      "grad_norm": 0.9616818428039551,
      "learning_rate": 4.89e-05,
      "loss": 0.9658,
      "step": 1210
    },
    {
      "epoch": 0.04436363636363636,
      "grad_norm": 0.7987754344940186,
      "learning_rate": 4.889090909090909e-05,
      "loss": 0.9262,
      "step": 1220
    },
    {
      "epoch": 0.04472727272727273,
      "grad_norm": 0.8735281825065613,
      "learning_rate": 4.888181818181818e-05,
      "loss": 0.9414,
      "step": 1230
    },
    {
      "epoch": 0.04509090909090909,
      "grad_norm": 0.7942488789558411,
      "learning_rate": 4.887272727272727e-05,
      "loss": 1.0506,
      "step": 1240
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.8182056546211243,
      "learning_rate": 4.886363636363637e-05,
      "loss": 1.0721,
      "step": 1250
    },
    {
      "epoch": 0.04581818181818182,
      "grad_norm": 0.7209412455558777,
      "learning_rate": 4.885454545454546e-05,
      "loss": 1.0205,
      "step": 1260
    },
    {
      "epoch": 0.046181818181818185,
      "grad_norm": 0.824597954750061,
      "learning_rate": 4.884545454545455e-05,
      "loss": 0.9563,
      "step": 1270
    },
    {
      "epoch": 0.04654545454545454,
      "grad_norm": 0.6784900426864624,
      "learning_rate": 4.883636363636364e-05,
      "loss": 1.0971,
      "step": 1280
    },
    {
      "epoch": 0.04690909090909091,
      "grad_norm": 0.680962324142456,
      "learning_rate": 4.882727272727273e-05,
      "loss": 1.0043,
      "step": 1290
    },
    {
      "epoch": 0.04727272727272727,
      "grad_norm": 0.7917009592056274,
      "learning_rate": 4.881818181818182e-05,
      "loss": 1.053,
      "step": 1300
    },
    {
      "epoch": 0.047636363636363636,
      "grad_norm": 0.8048487305641174,
      "learning_rate": 4.880909090909091e-05,
      "loss": 1.0842,
      "step": 1310
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.7836024165153503,
      "learning_rate": 4.88e-05,
      "loss": 1.0537,
      "step": 1320
    },
    {
      "epoch": 0.048363636363636366,
      "grad_norm": 0.6501603126525879,
      "learning_rate": 4.879090909090909e-05,
      "loss": 1.0084,
      "step": 1330
    },
    {
      "epoch": 0.04872727272727273,
      "grad_norm": 1.0370051860809326,
      "learning_rate": 4.878181818181819e-05,
      "loss": 0.9449,
      "step": 1340
    },
    {
      "epoch": 0.04909090909090909,
      "grad_norm": 0.8803650736808777,
      "learning_rate": 4.877272727272728e-05,
      "loss": 1.0154,
      "step": 1350
    },
    {
      "epoch": 0.04945454545454545,
      "grad_norm": 0.8375502824783325,
      "learning_rate": 4.876363636363637e-05,
      "loss": 0.9437,
      "step": 1360
    },
    {
      "epoch": 0.04981818181818182,
      "grad_norm": 0.8356055617332458,
      "learning_rate": 4.875454545454546e-05,
      "loss": 0.9443,
      "step": 1370
    },
    {
      "epoch": 0.05018181818181818,
      "grad_norm": 0.9145257472991943,
      "learning_rate": 4.874545454545455e-05,
      "loss": 1.0326,
      "step": 1380
    },
    {
      "epoch": 0.050545454545454546,
      "grad_norm": 0.7850838899612427,
      "learning_rate": 4.8736363636363644e-05,
      "loss": 0.9943,
      "step": 1390
    },
    {
      "epoch": 0.05090909090909091,
      "grad_norm": 0.8555696606636047,
      "learning_rate": 4.872727272727273e-05,
      "loss": 1.0791,
      "step": 1400
    },
    {
      "epoch": 0.051272727272727275,
      "grad_norm": 0.6297926306724548,
      "learning_rate": 4.871818181818182e-05,
      "loss": 0.9766,
      "step": 1410
    },
    {
      "epoch": 0.05163636363636363,
      "grad_norm": 0.7590431571006775,
      "learning_rate": 4.870909090909091e-05,
      "loss": 1.0184,
      "step": 1420
    },
    {
      "epoch": 0.052,
      "grad_norm": 0.7111615538597107,
      "learning_rate": 4.87e-05,
      "loss": 0.9545,
      "step": 1430
    },
    {
      "epoch": 0.05236363636363636,
      "grad_norm": 0.9266930222511292,
      "learning_rate": 4.8690909090909095e-05,
      "loss": 0.9373,
      "step": 1440
    },
    {
      "epoch": 0.05272727272727273,
      "grad_norm": 0.7775997519493103,
      "learning_rate": 4.8681818181818185e-05,
      "loss": 1.084,
      "step": 1450
    },
    {
      "epoch": 0.05309090909090909,
      "grad_norm": 0.7686333656311035,
      "learning_rate": 4.8672727272727275e-05,
      "loss": 0.9543,
      "step": 1460
    },
    {
      "epoch": 0.053454545454545456,
      "grad_norm": 0.8209460973739624,
      "learning_rate": 4.8663636363636365e-05,
      "loss": 1.0379,
      "step": 1470
    },
    {
      "epoch": 0.05381818181818182,
      "grad_norm": 0.5993338227272034,
      "learning_rate": 4.8654545454545455e-05,
      "loss": 0.9836,
      "step": 1480
    },
    {
      "epoch": 0.054181818181818185,
      "grad_norm": 0.8321117758750916,
      "learning_rate": 4.864545454545455e-05,
      "loss": 0.9789,
      "step": 1490
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.7136039733886719,
      "learning_rate": 4.863636363636364e-05,
      "loss": 0.941,
      "step": 1500
    },
    {
      "epoch": 0.05490909090909091,
      "grad_norm": 0.6142838001251221,
      "learning_rate": 4.8627272727272725e-05,
      "loss": 1.0277,
      "step": 1510
    },
    {
      "epoch": 0.05527272727272727,
      "grad_norm": 0.7588635087013245,
      "learning_rate": 4.8618181818181815e-05,
      "loss": 1.0854,
      "step": 1520
    },
    {
      "epoch": 0.05563636363636364,
      "grad_norm": 0.9304160475730896,
      "learning_rate": 4.860909090909091e-05,
      "loss": 1.0713,
      "step": 1530
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.6855290532112122,
      "learning_rate": 4.86e-05,
      "loss": 0.9658,
      "step": 1540
    },
    {
      "epoch": 0.056363636363636366,
      "grad_norm": 0.7574965357780457,
      "learning_rate": 4.859090909090909e-05,
      "loss": 0.9271,
      "step": 1550
    },
    {
      "epoch": 0.05672727272727273,
      "grad_norm": 0.6834359765052795,
      "learning_rate": 4.858181818181818e-05,
      "loss": 0.9395,
      "step": 1560
    },
    {
      "epoch": 0.05709090909090909,
      "grad_norm": 0.5964385271072388,
      "learning_rate": 4.857272727272727e-05,
      "loss": 1.0156,
      "step": 1570
    },
    {
      "epoch": 0.05745454545454545,
      "grad_norm": 0.6349005699157715,
      "learning_rate": 4.856363636363637e-05,
      "loss": 0.9195,
      "step": 1580
    },
    {
      "epoch": 0.05781818181818182,
      "grad_norm": 0.7871122360229492,
      "learning_rate": 4.855454545454546e-05,
      "loss": 1.008,
      "step": 1590
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 0.743977427482605,
      "learning_rate": 4.854545454545455e-05,
      "loss": 1.0277,
      "step": 1600
    },
    {
      "epoch": 0.058545454545454546,
      "grad_norm": 0.8460306525230408,
      "learning_rate": 4.853636363636364e-05,
      "loss": 1.0178,
      "step": 1610
    },
    {
      "epoch": 0.05890909090909091,
      "grad_norm": 0.6202099323272705,
      "learning_rate": 4.852727272727273e-05,
      "loss": 0.9564,
      "step": 1620
    },
    {
      "epoch": 0.059272727272727276,
      "grad_norm": 0.6819918155670166,
      "learning_rate": 4.851818181818182e-05,
      "loss": 1.008,
      "step": 1630
    },
    {
      "epoch": 0.05963636363636363,
      "grad_norm": 0.8113404512405396,
      "learning_rate": 4.850909090909091e-05,
      "loss": 1.0469,
      "step": 1640
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.7554293274879456,
      "learning_rate": 4.85e-05,
      "loss": 0.9373,
      "step": 1650
    },
    {
      "epoch": 0.06036363636363636,
      "grad_norm": 0.7795326709747314,
      "learning_rate": 4.849090909090909e-05,
      "loss": 1.0633,
      "step": 1660
    },
    {
      "epoch": 0.06072727272727273,
      "grad_norm": 0.6483361721038818,
      "learning_rate": 4.848181818181819e-05,
      "loss": 1.0172,
      "step": 1670
    },
    {
      "epoch": 0.06109090909090909,
      "grad_norm": 0.7647920846939087,
      "learning_rate": 4.847272727272728e-05,
      "loss": 0.9861,
      "step": 1680
    },
    {
      "epoch": 0.061454545454545456,
      "grad_norm": 0.9443255066871643,
      "learning_rate": 4.846363636363637e-05,
      "loss": 1.0828,
      "step": 1690
    },
    {
      "epoch": 0.06181818181818182,
      "grad_norm": 0.8193866610527039,
      "learning_rate": 4.845454545454546e-05,
      "loss": 1.0604,
      "step": 1700
    },
    {
      "epoch": 0.06218181818181818,
      "grad_norm": 0.707897961139679,
      "learning_rate": 4.844545454545455e-05,
      "loss": 0.9975,
      "step": 1710
    },
    {
      "epoch": 0.06254545454545454,
      "grad_norm": 0.9864387512207031,
      "learning_rate": 4.8436363636363644e-05,
      "loss": 1.0488,
      "step": 1720
    },
    {
      "epoch": 0.06290909090909091,
      "grad_norm": 0.741073727607727,
      "learning_rate": 4.8427272727272734e-05,
      "loss": 0.9912,
      "step": 1730
    },
    {
      "epoch": 0.06327272727272727,
      "grad_norm": 0.6622138619422913,
      "learning_rate": 4.841818181818182e-05,
      "loss": 0.9904,
      "step": 1740
    },
    {
      "epoch": 0.06363636363636363,
      "grad_norm": 0.9334690570831299,
      "learning_rate": 4.840909090909091e-05,
      "loss": 0.9775,
      "step": 1750
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.5777163505554199,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 0.951,
      "step": 1760
    },
    {
      "epoch": 0.06436363636363636,
      "grad_norm": 0.9769054651260376,
      "learning_rate": 4.8390909090909094e-05,
      "loss": 0.9883,
      "step": 1770
    },
    {
      "epoch": 0.06472727272727273,
      "grad_norm": 0.8204796314239502,
      "learning_rate": 4.8381818181818184e-05,
      "loss": 0.9746,
      "step": 1780
    },
    {
      "epoch": 0.06509090909090909,
      "grad_norm": 0.8641470670700073,
      "learning_rate": 4.8372727272727274e-05,
      "loss": 1.0391,
      "step": 1790
    },
    {
      "epoch": 0.06545454545454546,
      "grad_norm": 0.732994794845581,
      "learning_rate": 4.8363636363636364e-05,
      "loss": 0.9494,
      "step": 1800
    },
    {
      "epoch": 0.06581818181818182,
      "grad_norm": 0.5632991194725037,
      "learning_rate": 4.835454545454546e-05,
      "loss": 1.1303,
      "step": 1810
    },
    {
      "epoch": 0.06618181818181817,
      "grad_norm": 0.6839861869812012,
      "learning_rate": 4.834545454545455e-05,
      "loss": 0.9652,
      "step": 1820
    },
    {
      "epoch": 0.06654545454545455,
      "grad_norm": 0.5407667756080627,
      "learning_rate": 4.833636363636364e-05,
      "loss": 0.9885,
      "step": 1830
    },
    {
      "epoch": 0.0669090909090909,
      "grad_norm": 0.8409451246261597,
      "learning_rate": 4.832727272727273e-05,
      "loss": 1.0197,
      "step": 1840
    },
    {
      "epoch": 0.06727272727272728,
      "grad_norm": 0.8460031151771545,
      "learning_rate": 4.8318181818181815e-05,
      "loss": 1.0137,
      "step": 1850
    },
    {
      "epoch": 0.06763636363636363,
      "grad_norm": 0.6154618859291077,
      "learning_rate": 4.830909090909091e-05,
      "loss": 0.9316,
      "step": 1860
    },
    {
      "epoch": 0.068,
      "grad_norm": 0.7288620471954346,
      "learning_rate": 4.83e-05,
      "loss": 0.957,
      "step": 1870
    },
    {
      "epoch": 0.06836363636363636,
      "grad_norm": 0.6734368205070496,
      "learning_rate": 4.829090909090909e-05,
      "loss": 0.9178,
      "step": 1880
    },
    {
      "epoch": 0.06872727272727273,
      "grad_norm": 0.5886709690093994,
      "learning_rate": 4.828181818181818e-05,
      "loss": 0.8715,
      "step": 1890
    },
    {
      "epoch": 0.06909090909090909,
      "grad_norm": 0.6626171469688416,
      "learning_rate": 4.827272727272727e-05,
      "loss": 1.0303,
      "step": 1900
    },
    {
      "epoch": 0.06945454545454545,
      "grad_norm": 0.6848061680793762,
      "learning_rate": 4.826363636363637e-05,
      "loss": 0.9477,
      "step": 1910
    },
    {
      "epoch": 0.06981818181818182,
      "grad_norm": 0.9979369640350342,
      "learning_rate": 4.825454545454546e-05,
      "loss": 1.1021,
      "step": 1920
    },
    {
      "epoch": 0.07018181818181818,
      "grad_norm": 0.8587698340415955,
      "learning_rate": 4.824545454545455e-05,
      "loss": 0.9975,
      "step": 1930
    },
    {
      "epoch": 0.07054545454545455,
      "grad_norm": 0.7505869269371033,
      "learning_rate": 4.823636363636364e-05,
      "loss": 0.902,
      "step": 1940
    },
    {
      "epoch": 0.07090909090909091,
      "grad_norm": 1.0160633325576782,
      "learning_rate": 4.822727272727273e-05,
      "loss": 1.0432,
      "step": 1950
    },
    {
      "epoch": 0.07127272727272728,
      "grad_norm": 0.6609899401664734,
      "learning_rate": 4.821818181818182e-05,
      "loss": 0.9576,
      "step": 1960
    },
    {
      "epoch": 0.07163636363636364,
      "grad_norm": 0.8230269551277161,
      "learning_rate": 4.820909090909091e-05,
      "loss": 1.0172,
      "step": 1970
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.7711009979248047,
      "learning_rate": 4.82e-05,
      "loss": 1.133,
      "step": 1980
    },
    {
      "epoch": 0.07236363636363637,
      "grad_norm": 0.8839887380599976,
      "learning_rate": 4.819090909090909e-05,
      "loss": 1.0662,
      "step": 1990
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.6672515869140625,
      "learning_rate": 4.8181818181818186e-05,
      "loss": 0.9764,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 55000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2566081788222917e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}