{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13495589893228993,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006631739505272233,
      "grad_norm": 1.1596795320510864,
      "learning_rate": 2.910112359550562e-06,
      "loss": 0.9517,
      "step": 10
    },
    {
      "epoch": 0.0013263479010544466,
      "grad_norm": 1.0129684209823608,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.9185,
      "step": 20
    },
    {
      "epoch": 0.00198952185158167,
      "grad_norm": 1.0162608623504639,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.8679,
      "step": 30
    },
    {
      "epoch": 0.0026526958021088932,
      "grad_norm": 0.8911998271942139,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.8628,
      "step": 40
    },
    {
      "epoch": 0.0033158697526361166,
      "grad_norm": 0.8088529706001282,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.8746,
      "step": 50
    },
    {
      "epoch": 0.00397904370316334,
      "grad_norm": 0.8642328977584839,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.8327,
      "step": 60
    },
    {
      "epoch": 0.004642217653690563,
      "grad_norm": 0.8503588438034058,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.8412,
      "step": 70
    },
    {
      "epoch": 0.0053053916042177865,
      "grad_norm": 0.8862006664276123,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.8231,
      "step": 80
    },
    {
      "epoch": 0.00596856555474501,
      "grad_norm": 0.9262124300003052,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.8087,
      "step": 90
    },
    {
      "epoch": 0.006631739505272233,
      "grad_norm": 0.9693242907524109,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.8197,
      "step": 100
    },
    {
      "epoch": 0.007294913455799456,
      "grad_norm": 0.8964329361915588,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.7927,
      "step": 110
    },
    {
      "epoch": 0.00795808740632668,
      "grad_norm": 0.8408939838409424,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.8229,
      "step": 120
    },
    {
      "epoch": 0.008621261356853902,
      "grad_norm": 0.8564504981040955,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.7813,
      "step": 130
    },
    {
      "epoch": 0.009284435307381126,
      "grad_norm": 0.9394861459732056,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.8178,
      "step": 140
    },
    {
      "epoch": 0.009947609257908349,
      "grad_norm": 0.8412289023399353,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.7863,
      "step": 150
    },
    {
      "epoch": 0.010610783208435573,
      "grad_norm": 0.8816506266593933,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.7883,
      "step": 160
    },
    {
      "epoch": 0.011273957158962795,
      "grad_norm": 0.8023780584335327,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.7992,
      "step": 170
    },
    {
      "epoch": 0.01193713110949002,
      "grad_norm": 0.9203169941902161,
      "learning_rate": 2e-05,
      "loss": 0.8106,
      "step": 180
    },
    {
      "epoch": 0.012600305060017242,
      "grad_norm": 0.8466951251029968,
      "learning_rate": 2e-05,
      "loss": 0.7944,
      "step": 190
    },
    {
      "epoch": 0.013263479010544466,
      "grad_norm": 0.807468593120575,
      "learning_rate": 2e-05,
      "loss": 0.7964,
      "step": 200
    },
    {
      "epoch": 0.013926652961071689,
      "grad_norm": 0.74900221824646,
      "learning_rate": 2e-05,
      "loss": 0.7963,
      "step": 210
    },
    {
      "epoch": 0.014589826911598913,
      "grad_norm": 0.8038553595542908,
      "learning_rate": 2e-05,
      "loss": 0.7799,
      "step": 220
    },
    {
      "epoch": 0.015253000862126135,
      "grad_norm": 0.6701945662498474,
      "learning_rate": 2e-05,
      "loss": 0.8199,
      "step": 230
    },
    {
      "epoch": 0.01591617481265336,
      "grad_norm": 0.649372398853302,
      "learning_rate": 2e-05,
      "loss": 0.7925,
      "step": 240
    },
    {
      "epoch": 0.016579348763180582,
      "grad_norm": 0.6375704407691956,
      "learning_rate": 2e-05,
      "loss": 0.8243,
      "step": 250
    },
    {
      "epoch": 0.017242522713707804,
      "grad_norm": 0.660631537437439,
      "learning_rate": 2e-05,
      "loss": 0.7956,
      "step": 260
    },
    {
      "epoch": 0.01790569666423503,
      "grad_norm": 0.620918869972229,
      "learning_rate": 2e-05,
      "loss": 0.7858,
      "step": 270
    },
    {
      "epoch": 0.018568870614762253,
      "grad_norm": 0.5827407240867615,
      "learning_rate": 2e-05,
      "loss": 0.7998,
      "step": 280
    },
    {
      "epoch": 0.019232044565289475,
      "grad_norm": 0.578879177570343,
      "learning_rate": 2e-05,
      "loss": 0.7597,
      "step": 290
    },
    {
      "epoch": 0.019895218515816698,
      "grad_norm": 0.5654085874557495,
      "learning_rate": 2e-05,
      "loss": 0.7533,
      "step": 300
    },
    {
      "epoch": 0.020558392466343924,
      "grad_norm": 0.5633082985877991,
      "learning_rate": 2e-05,
      "loss": 0.7592,
      "step": 310
    },
    {
      "epoch": 0.021221566416871146,
      "grad_norm": 0.6228300333023071,
      "learning_rate": 2e-05,
      "loss": 0.7857,
      "step": 320
    },
    {
      "epoch": 0.02188474036739837,
      "grad_norm": 0.5642741918563843,
      "learning_rate": 2e-05,
      "loss": 0.7652,
      "step": 330
    },
    {
      "epoch": 0.02254791431792559,
      "grad_norm": 0.5845516920089722,
      "learning_rate": 2e-05,
      "loss": 0.7792,
      "step": 340
    },
    {
      "epoch": 0.023211088268452817,
      "grad_norm": 0.5533984899520874,
      "learning_rate": 2e-05,
      "loss": 0.7662,
      "step": 350
    },
    {
      "epoch": 0.02387426221898004,
      "grad_norm": 1.1515164375305176,
      "learning_rate": 2e-05,
      "loss": 0.7853,
      "step": 360
    },
    {
      "epoch": 0.02453743616950726,
      "grad_norm": 0.5596652030944824,
      "learning_rate": 2e-05,
      "loss": 0.7939,
      "step": 370
    },
    {
      "epoch": 0.025200610120034484,
      "grad_norm": 0.5617090463638306,
      "learning_rate": 2e-05,
      "loss": 0.7896,
      "step": 380
    },
    {
      "epoch": 0.02586378407056171,
      "grad_norm": 0.80217444896698,
      "learning_rate": 2e-05,
      "loss": 0.7616,
      "step": 390
    },
    {
      "epoch": 0.026526958021088932,
      "grad_norm": 0.8099656701087952,
      "learning_rate": 2e-05,
      "loss": 0.7716,
      "step": 400
    },
    {
      "epoch": 0.027190131971616155,
      "grad_norm": 0.5415481925010681,
      "learning_rate": 2e-05,
      "loss": 0.7764,
      "step": 410
    },
    {
      "epoch": 0.027853305922143377,
      "grad_norm": 0.7534944415092468,
      "learning_rate": 2e-05,
      "loss": 0.7879,
      "step": 420
    },
    {
      "epoch": 0.0285164798726706,
      "grad_norm": 0.602469801902771,
      "learning_rate": 2e-05,
      "loss": 0.771,
      "step": 430
    },
    {
      "epoch": 0.029179653823197826,
      "grad_norm": 0.5386860370635986,
      "learning_rate": 2e-05,
      "loss": 0.791,
      "step": 440
    },
    {
      "epoch": 0.029842827773725048,
      "grad_norm": 0.5772424936294556,
      "learning_rate": 2e-05,
      "loss": 0.7806,
      "step": 450
    },
    {
      "epoch": 0.03050600172425227,
      "grad_norm": 0.5686757564544678,
      "learning_rate": 2e-05,
      "loss": 0.7729,
      "step": 460
    },
    {
      "epoch": 0.031169175674779493,
      "grad_norm": 0.5157404541969299,
      "learning_rate": 2e-05,
      "loss": 0.7387,
      "step": 470
    },
    {
      "epoch": 0.03183234962530672,
      "grad_norm": 0.5490089654922485,
      "learning_rate": 2e-05,
      "loss": 0.7653,
      "step": 480
    },
    {
      "epoch": 0.03249552357583394,
      "grad_norm": 0.5582148432731628,
      "learning_rate": 2e-05,
      "loss": 0.7827,
      "step": 490
    },
    {
      "epoch": 0.033158697526361164,
      "grad_norm": 0.5726275444030762,
      "learning_rate": 2e-05,
      "loss": 0.7942,
      "step": 500
    },
    {
      "epoch": 0.033821871476888386,
      "grad_norm": 1.6204034090042114,
      "learning_rate": 2e-05,
      "loss": 0.7893,
      "step": 510
    },
    {
      "epoch": 0.03448504542741561,
      "grad_norm": 0.5208715796470642,
      "learning_rate": 2e-05,
      "loss": 0.7714,
      "step": 520
    },
    {
      "epoch": 0.03514821937794283,
      "grad_norm": 0.5310713052749634,
      "learning_rate": 2e-05,
      "loss": 0.7802,
      "step": 530
    },
    {
      "epoch": 0.03581139332847006,
      "grad_norm": 0.5323279500007629,
      "learning_rate": 2e-05,
      "loss": 0.7548,
      "step": 540
    },
    {
      "epoch": 0.03647456727899728,
      "grad_norm": 0.48549482226371765,
      "learning_rate": 2e-05,
      "loss": 0.7649,
      "step": 550
    },
    {
      "epoch": 0.037137741229524505,
      "grad_norm": 0.5288492441177368,
      "learning_rate": 2e-05,
      "loss": 0.7777,
      "step": 560
    },
    {
      "epoch": 0.03780091518005173,
      "grad_norm": 0.4877089560031891,
      "learning_rate": 2e-05,
      "loss": 0.7802,
      "step": 570
    },
    {
      "epoch": 0.03846408913057895,
      "grad_norm": 0.5317091345787048,
      "learning_rate": 2e-05,
      "loss": 0.7833,
      "step": 580
    },
    {
      "epoch": 0.03912726308110617,
      "grad_norm": 0.5533668994903564,
      "learning_rate": 2e-05,
      "loss": 0.7702,
      "step": 590
    },
    {
      "epoch": 0.039790437031633395,
      "grad_norm": 0.5711390972137451,
      "learning_rate": 2e-05,
      "loss": 0.7801,
      "step": 600
    },
    {
      "epoch": 0.04045361098216062,
      "grad_norm": 0.5276714563369751,
      "learning_rate": 2e-05,
      "loss": 0.7846,
      "step": 610
    },
    {
      "epoch": 0.04111678493268785,
      "grad_norm": 0.5505608320236206,
      "learning_rate": 2e-05,
      "loss": 0.7575,
      "step": 620
    },
    {
      "epoch": 0.04177995888321507,
      "grad_norm": 0.49005311727523804,
      "learning_rate": 2e-05,
      "loss": 0.7698,
      "step": 630
    },
    {
      "epoch": 0.04244313283374229,
      "grad_norm": 0.4874991178512573,
      "learning_rate": 2e-05,
      "loss": 0.7716,
      "step": 640
    },
    {
      "epoch": 0.043106306784269514,
      "grad_norm": 0.5269560217857361,
      "learning_rate": 2e-05,
      "loss": 0.7607,
      "step": 650
    },
    {
      "epoch": 0.04376948073479674,
      "grad_norm": 0.50971519947052,
      "learning_rate": 2e-05,
      "loss": 0.7473,
      "step": 660
    },
    {
      "epoch": 0.04443265468532396,
      "grad_norm": 0.6813302636146545,
      "learning_rate": 2e-05,
      "loss": 0.7437,
      "step": 670
    },
    {
      "epoch": 0.04509582863585118,
      "grad_norm": 0.4699794352054596,
      "learning_rate": 2e-05,
      "loss": 0.7794,
      "step": 680
    },
    {
      "epoch": 0.045759002586378404,
      "grad_norm": 0.4931847155094147,
      "learning_rate": 2e-05,
      "loss": 0.7788,
      "step": 690
    },
    {
      "epoch": 0.046422176536905634,
      "grad_norm": 0.527800977230072,
      "learning_rate": 2e-05,
      "loss": 0.788,
      "step": 700
    },
    {
      "epoch": 0.047085350487432856,
      "grad_norm": 0.48107194900512695,
      "learning_rate": 2e-05,
      "loss": 0.763,
      "step": 710
    },
    {
      "epoch": 0.04774852443796008,
      "grad_norm": 0.48204314708709717,
      "learning_rate": 2e-05,
      "loss": 0.7595,
      "step": 720
    },
    {
      "epoch": 0.0484116983884873,
      "grad_norm": 0.48960623145103455,
      "learning_rate": 2e-05,
      "loss": 0.7647,
      "step": 730
    },
    {
      "epoch": 0.04907487233901452,
      "grad_norm": 0.4727330505847931,
      "learning_rate": 2e-05,
      "loss": 0.7618,
      "step": 740
    },
    {
      "epoch": 0.049738046289541746,
      "grad_norm": 0.48611021041870117,
      "learning_rate": 2e-05,
      "loss": 0.7773,
      "step": 750
    },
    {
      "epoch": 0.05040122024006897,
      "grad_norm": 0.481209397315979,
      "learning_rate": 2e-05,
      "loss": 0.7909,
      "step": 760
    },
    {
      "epoch": 0.05106439419059619,
      "grad_norm": 0.5047401785850525,
      "learning_rate": 2e-05,
      "loss": 0.7613,
      "step": 770
    },
    {
      "epoch": 0.05172756814112342,
      "grad_norm": 0.5307384729385376,
      "learning_rate": 2e-05,
      "loss": 0.7672,
      "step": 780
    },
    {
      "epoch": 0.05239074209165064,
      "grad_norm": 0.5360110402107239,
      "learning_rate": 2e-05,
      "loss": 0.7441,
      "step": 790
    },
    {
      "epoch": 0.053053916042177865,
      "grad_norm": 0.4864613711833954,
      "learning_rate": 2e-05,
      "loss": 0.7748,
      "step": 800
    },
    {
      "epoch": 0.05371708999270509,
      "grad_norm": 0.4954187572002411,
      "learning_rate": 2e-05,
      "loss": 0.7528,
      "step": 810
    },
    {
      "epoch": 0.05438026394323231,
      "grad_norm": 0.504557192325592,
      "learning_rate": 2e-05,
      "loss": 0.7494,
      "step": 820
    },
    {
      "epoch": 0.05504343789375953,
      "grad_norm": 0.48328864574432373,
      "learning_rate": 2e-05,
      "loss": 0.7764,
      "step": 830
    },
    {
      "epoch": 0.055706611844286755,
      "grad_norm": 0.47445255517959595,
      "learning_rate": 2e-05,
      "loss": 0.754,
      "step": 840
    },
    {
      "epoch": 0.05636978579481398,
      "grad_norm": 0.5029422044754028,
      "learning_rate": 2e-05,
      "loss": 0.77,
      "step": 850
    },
    {
      "epoch": 0.0570329597453412,
      "grad_norm": 0.5073195695877075,
      "learning_rate": 2e-05,
      "loss": 0.7597,
      "step": 860
    },
    {
      "epoch": 0.05769613369586843,
      "grad_norm": 0.4880322813987732,
      "learning_rate": 2e-05,
      "loss": 0.7595,
      "step": 870
    },
    {
      "epoch": 0.05835930764639565,
      "grad_norm": 0.513581395149231,
      "learning_rate": 2e-05,
      "loss": 0.7818,
      "step": 880
    },
    {
      "epoch": 0.059022481596922874,
      "grad_norm": 0.4951395094394684,
      "learning_rate": 2e-05,
      "loss": 0.7881,
      "step": 890
    },
    {
      "epoch": 0.059685655547450096,
      "grad_norm": 0.45365604758262634,
      "learning_rate": 2e-05,
      "loss": 0.7577,
      "step": 900
    },
    {
      "epoch": 0.06034882949797732,
      "grad_norm": 0.4641544818878174,
      "learning_rate": 2e-05,
      "loss": 0.7685,
      "step": 910
    },
    {
      "epoch": 0.06101200344850454,
      "grad_norm": 0.48189839720726013,
      "learning_rate": 2e-05,
      "loss": 0.7767,
      "step": 920
    },
    {
      "epoch": 0.061675177399031764,
      "grad_norm": 0.4569750428199768,
      "learning_rate": 2e-05,
      "loss": 0.7469,
      "step": 930
    },
    {
      "epoch": 0.062338351349558986,
      "grad_norm": 0.4633541703224182,
      "learning_rate": 2e-05,
      "loss": 0.76,
      "step": 940
    },
    {
      "epoch": 0.06300152530008621,
      "grad_norm": 0.4753730595111847,
      "learning_rate": 2e-05,
      "loss": 0.7528,
      "step": 950
    },
    {
      "epoch": 0.06366469925061344,
      "grad_norm": 0.4677918553352356,
      "learning_rate": 2e-05,
      "loss": 0.7569,
      "step": 960
    },
    {
      "epoch": 0.06432787320114065,
      "grad_norm": 0.4754522442817688,
      "learning_rate": 2e-05,
      "loss": 0.7659,
      "step": 970
    },
    {
      "epoch": 0.06499104715166788,
      "grad_norm": 0.5752569437026978,
      "learning_rate": 2e-05,
      "loss": 0.7599,
      "step": 980
    },
    {
      "epoch": 0.06565422110219511,
      "grad_norm": 0.5086958408355713,
      "learning_rate": 2e-05,
      "loss": 0.7631,
      "step": 990
    },
    {
      "epoch": 0.06631739505272233,
      "grad_norm": 0.5891866087913513,
      "learning_rate": 2e-05,
      "loss": 0.7597,
      "step": 1000
    },
    {
      "epoch": 0.06698056900324956,
      "grad_norm": 0.46219590306282043,
      "learning_rate": 2e-05,
      "loss": 0.7579,
      "step": 1010
    },
    {
      "epoch": 0.06764374295377677,
      "grad_norm": 0.4759126305580139,
      "learning_rate": 2e-05,
      "loss": 0.7554,
      "step": 1020
    },
    {
      "epoch": 0.068306916904304,
      "grad_norm": 0.5318647027015686,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 1030
    },
    {
      "epoch": 0.06897009085483122,
      "grad_norm": 0.4814603924751282,
      "learning_rate": 2e-05,
      "loss": 0.7729,
      "step": 1040
    },
    {
      "epoch": 0.06963326480535845,
      "grad_norm": 0.5173375010490417,
      "learning_rate": 2e-05,
      "loss": 0.7589,
      "step": 1050
    },
    {
      "epoch": 0.07029643875588566,
      "grad_norm": 0.5993748903274536,
      "learning_rate": 2e-05,
      "loss": 0.7736,
      "step": 1060
    },
    {
      "epoch": 0.07095961270641289,
      "grad_norm": 0.5081777572631836,
      "learning_rate": 2e-05,
      "loss": 0.7522,
      "step": 1070
    },
    {
      "epoch": 0.07162278665694012,
      "grad_norm": 0.45993325114250183,
      "learning_rate": 2e-05,
      "loss": 0.7801,
      "step": 1080
    },
    {
      "epoch": 0.07228596060746734,
      "grad_norm": 0.4642050564289093,
      "learning_rate": 2e-05,
      "loss": 0.7594,
      "step": 1090
    },
    {
      "epoch": 0.07294913455799457,
      "grad_norm": 0.45918765664100647,
      "learning_rate": 2e-05,
      "loss": 0.7292,
      "step": 1100
    },
    {
      "epoch": 0.07361230850852178,
      "grad_norm": 0.4907342493534088,
      "learning_rate": 2e-05,
      "loss": 0.768,
      "step": 1110
    },
    {
      "epoch": 0.07427548245904901,
      "grad_norm": 0.46477046608924866,
      "learning_rate": 2e-05,
      "loss": 0.7546,
      "step": 1120
    },
    {
      "epoch": 0.07493865640957623,
      "grad_norm": 0.5048196911811829,
      "learning_rate": 2e-05,
      "loss": 0.7762,
      "step": 1130
    },
    {
      "epoch": 0.07560183036010346,
      "grad_norm": 0.48439109325408936,
      "learning_rate": 2e-05,
      "loss": 0.7385,
      "step": 1140
    },
    {
      "epoch": 0.07626500431063069,
      "grad_norm": 0.47210803627967834,
      "learning_rate": 2e-05,
      "loss": 0.7694,
      "step": 1150
    },
    {
      "epoch": 0.0769281782611579,
      "grad_norm": 0.4778144359588623,
      "learning_rate": 2e-05,
      "loss": 0.7382,
      "step": 1160
    },
    {
      "epoch": 0.07759135221168513,
      "grad_norm": 0.5094350576400757,
      "learning_rate": 2e-05,
      "loss": 0.7488,
      "step": 1170
    },
    {
      "epoch": 0.07825452616221235,
      "grad_norm": 0.5327107310295105,
      "learning_rate": 2e-05,
      "loss": 0.7457,
      "step": 1180
    },
    {
      "epoch": 0.07891770011273957,
      "grad_norm": 0.4854157567024231,
      "learning_rate": 2e-05,
      "loss": 0.7531,
      "step": 1190
    },
    {
      "epoch": 0.07958087406326679,
      "grad_norm": 0.8898469805717468,
      "learning_rate": 2e-05,
      "loss": 0.7552,
      "step": 1200
    },
    {
      "epoch": 0.08024404801379402,
      "grad_norm": 0.4582747519016266,
      "learning_rate": 2e-05,
      "loss": 0.7346,
      "step": 1210
    },
    {
      "epoch": 0.08090722196432124,
      "grad_norm": 0.4968053102493286,
      "learning_rate": 2e-05,
      "loss": 0.7464,
      "step": 1220
    },
    {
      "epoch": 0.08157039591484846,
      "grad_norm": 0.5363363027572632,
      "learning_rate": 2e-05,
      "loss": 0.7607,
      "step": 1230
    },
    {
      "epoch": 0.0822335698653757,
      "grad_norm": 0.5088996887207031,
      "learning_rate": 2e-05,
      "loss": 0.7482,
      "step": 1240
    },
    {
      "epoch": 0.08289674381590291,
      "grad_norm": 0.4793884754180908,
      "learning_rate": 2e-05,
      "loss": 0.7469,
      "step": 1250
    },
    {
      "epoch": 0.08355991776643014,
      "grad_norm": 1.361615538597107,
      "learning_rate": 2e-05,
      "loss": 0.7451,
      "step": 1260
    },
    {
      "epoch": 0.08422309171695735,
      "grad_norm": 0.47477322816848755,
      "learning_rate": 2e-05,
      "loss": 0.7631,
      "step": 1270
    },
    {
      "epoch": 0.08488626566748458,
      "grad_norm": 0.49219903349876404,
      "learning_rate": 2e-05,
      "loss": 0.7709,
      "step": 1280
    },
    {
      "epoch": 0.0855494396180118,
      "grad_norm": 0.46074602007865906,
      "learning_rate": 2e-05,
      "loss": 0.75,
      "step": 1290
    },
    {
      "epoch": 0.08621261356853903,
      "grad_norm": 0.4657946228981018,
      "learning_rate": 2e-05,
      "loss": 0.7494,
      "step": 1300
    },
    {
      "epoch": 0.08687578751906624,
      "grad_norm": 1.8625658750534058,
      "learning_rate": 2e-05,
      "loss": 0.7213,
      "step": 1310
    },
    {
      "epoch": 0.08753896146959347,
      "grad_norm": 0.4719648063182831,
      "learning_rate": 2e-05,
      "loss": 0.7651,
      "step": 1320
    },
    {
      "epoch": 0.0882021354201207,
      "grad_norm": 0.45125117897987366,
      "learning_rate": 2e-05,
      "loss": 0.7575,
      "step": 1330
    },
    {
      "epoch": 0.08886530937064792,
      "grad_norm": 0.4656333029270172,
      "learning_rate": 2e-05,
      "loss": 0.7473,
      "step": 1340
    },
    {
      "epoch": 0.08952848332117515,
      "grad_norm": 0.4801299273967743,
      "learning_rate": 2e-05,
      "loss": 0.7496,
      "step": 1350
    },
    {
      "epoch": 0.09019165727170236,
      "grad_norm": 0.4366644620895386,
      "learning_rate": 2e-05,
      "loss": 0.7361,
      "step": 1360
    },
    {
      "epoch": 0.09085483122222959,
      "grad_norm": 0.43298009037971497,
      "learning_rate": 2e-05,
      "loss": 0.7358,
      "step": 1370
    },
    {
      "epoch": 0.09151800517275681,
      "grad_norm": 0.45950010418891907,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 1380
    },
    {
      "epoch": 0.09218117912328404,
      "grad_norm": 0.4419451057910919,
      "learning_rate": 2e-05,
      "loss": 0.7559,
      "step": 1390
    },
    {
      "epoch": 0.09284435307381127,
      "grad_norm": 0.5011473894119263,
      "learning_rate": 2e-05,
      "loss": 0.747,
      "step": 1400
    },
    {
      "epoch": 0.09350752702433848,
      "grad_norm": 0.4722769260406494,
      "learning_rate": 2e-05,
      "loss": 0.7598,
      "step": 1410
    },
    {
      "epoch": 0.09417070097486571,
      "grad_norm": 0.4498542547225952,
      "learning_rate": 2e-05,
      "loss": 0.7429,
      "step": 1420
    },
    {
      "epoch": 0.09483387492539293,
      "grad_norm": 0.464199960231781,
      "learning_rate": 2e-05,
      "loss": 0.7684,
      "step": 1430
    },
    {
      "epoch": 0.09549704887592016,
      "grad_norm": 0.5018302202224731,
      "learning_rate": 2e-05,
      "loss": 0.7698,
      "step": 1440
    },
    {
      "epoch": 0.09616022282644737,
      "grad_norm": 0.4524178206920624,
      "learning_rate": 2e-05,
      "loss": 0.7644,
      "step": 1450
    },
    {
      "epoch": 0.0968233967769746,
      "grad_norm": 0.46702370047569275,
      "learning_rate": 2e-05,
      "loss": 0.7526,
      "step": 1460
    },
    {
      "epoch": 0.09748657072750182,
      "grad_norm": 0.4664076864719391,
      "learning_rate": 2e-05,
      "loss": 0.7638,
      "step": 1470
    },
    {
      "epoch": 0.09814974467802905,
      "grad_norm": 0.48490601778030396,
      "learning_rate": 2e-05,
      "loss": 0.7535,
      "step": 1480
    },
    {
      "epoch": 0.09881291862855628,
      "grad_norm": 0.5127236247062683,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 1490
    },
    {
      "epoch": 0.09947609257908349,
      "grad_norm": 0.46068698167800903,
      "learning_rate": 2e-05,
      "loss": 0.735,
      "step": 1500
    },
    {
      "epoch": 0.10013926652961072,
      "grad_norm": 0.44757401943206787,
      "learning_rate": 2e-05,
      "loss": 0.7587,
      "step": 1510
    },
    {
      "epoch": 0.10080244048013794,
      "grad_norm": 0.475946843624115,
      "learning_rate": 2e-05,
      "loss": 0.7474,
      "step": 1520
    },
    {
      "epoch": 0.10146561443066517,
      "grad_norm": 0.4839072823524475,
      "learning_rate": 2e-05,
      "loss": 0.75,
      "step": 1530
    },
    {
      "epoch": 0.10212878838119238,
      "grad_norm": 0.477365106344223,
      "learning_rate": 2e-05,
      "loss": 0.7487,
      "step": 1540
    },
    {
      "epoch": 0.10279196233171961,
      "grad_norm": 0.48756539821624756,
      "learning_rate": 2e-05,
      "loss": 0.7446,
      "step": 1550
    },
    {
      "epoch": 0.10345513628224684,
      "grad_norm": 0.46172550320625305,
      "learning_rate": 2e-05,
      "loss": 0.7336,
      "step": 1560
    },
    {
      "epoch": 0.10411831023277406,
      "grad_norm": 0.4753364026546478,
      "learning_rate": 2e-05,
      "loss": 0.7267,
      "step": 1570
    },
    {
      "epoch": 0.10478148418330128,
      "grad_norm": 0.4389295279979706,
      "learning_rate": 2e-05,
      "loss": 0.7494,
      "step": 1580
    },
    {
      "epoch": 0.1054446581338285,
      "grad_norm": 0.44949832558631897,
      "learning_rate": 2e-05,
      "loss": 0.7334,
      "step": 1590
    },
    {
      "epoch": 0.10610783208435573,
      "grad_norm": 0.46615809202194214,
      "learning_rate": 2e-05,
      "loss": 0.7669,
      "step": 1600
    },
    {
      "epoch": 0.10677100603488295,
      "grad_norm": 0.4528898000717163,
      "learning_rate": 2e-05,
      "loss": 0.7503,
      "step": 1610
    },
    {
      "epoch": 0.10743417998541017,
      "grad_norm": 0.571483314037323,
      "learning_rate": 2e-05,
      "loss": 0.7383,
      "step": 1620
    },
    {
      "epoch": 0.10809735393593739,
      "grad_norm": 0.4646868109703064,
      "learning_rate": 2e-05,
      "loss": 0.7512,
      "step": 1630
    },
    {
      "epoch": 0.10876052788646462,
      "grad_norm": 0.4529063105583191,
      "learning_rate": 2e-05,
      "loss": 0.7255,
      "step": 1640
    },
    {
      "epoch": 0.10942370183699185,
      "grad_norm": 0.5024081468582153,
      "learning_rate": 2e-05,
      "loss": 0.739,
      "step": 1650
    },
    {
      "epoch": 0.11008687578751906,
      "grad_norm": 0.4648872911930084,
      "learning_rate": 2e-05,
      "loss": 0.746,
      "step": 1660
    },
    {
      "epoch": 0.1107500497380463,
      "grad_norm": 0.488041490316391,
      "learning_rate": 2e-05,
      "loss": 0.738,
      "step": 1670
    },
    {
      "epoch": 0.11141322368857351,
      "grad_norm": 0.4653259515762329,
      "learning_rate": 2e-05,
      "loss": 0.7256,
      "step": 1680
    },
    {
      "epoch": 0.11207639763910074,
      "grad_norm": 0.48732203245162964,
      "learning_rate": 2e-05,
      "loss": 0.7429,
      "step": 1690
    },
    {
      "epoch": 0.11273957158962795,
      "grad_norm": 0.572994589805603,
      "learning_rate": 2e-05,
      "loss": 0.7573,
      "step": 1700
    },
    {
      "epoch": 0.11340274554015518,
      "grad_norm": 0.4531424045562744,
      "learning_rate": 2e-05,
      "loss": 0.7422,
      "step": 1710
    },
    {
      "epoch": 0.1140659194906824,
      "grad_norm": 0.512623131275177,
      "learning_rate": 2e-05,
      "loss": 0.7292,
      "step": 1720
    },
    {
      "epoch": 0.11472909344120963,
      "grad_norm": 0.4822714328765869,
      "learning_rate": 2e-05,
      "loss": 0.7415,
      "step": 1730
    },
    {
      "epoch": 0.11539226739173686,
      "grad_norm": 0.4871460497379303,
      "learning_rate": 2e-05,
      "loss": 0.7417,
      "step": 1740
    },
    {
      "epoch": 0.11605544134226407,
      "grad_norm": 1.012222409248352,
      "learning_rate": 2e-05,
      "loss": 0.736,
      "step": 1750
    },
    {
      "epoch": 0.1167186152927913,
      "grad_norm": 0.530349612236023,
      "learning_rate": 2e-05,
      "loss": 0.728,
      "step": 1760
    },
    {
      "epoch": 0.11738178924331852,
      "grad_norm": 0.46132221817970276,
      "learning_rate": 2e-05,
      "loss": 0.7216,
      "step": 1770
    },
    {
      "epoch": 0.11804496319384575,
      "grad_norm": 0.4651985168457031,
      "learning_rate": 2e-05,
      "loss": 0.7562,
      "step": 1780
    },
    {
      "epoch": 0.11870813714437296,
      "grad_norm": 0.44336026906967163,
      "learning_rate": 2e-05,
      "loss": 0.7441,
      "step": 1790
    },
    {
      "epoch": 0.11937131109490019,
      "grad_norm": 0.4634976089000702,
      "learning_rate": 2e-05,
      "loss": 0.7746,
      "step": 1800
    },
    {
      "epoch": 0.12003448504542742,
      "grad_norm": 0.6048588752746582,
      "learning_rate": 2e-05,
      "loss": 0.7485,
      "step": 1810
    },
    {
      "epoch": 0.12069765899595464,
      "grad_norm": 0.47721830010414124,
      "learning_rate": 2e-05,
      "loss": 0.7484,
      "step": 1820
    },
    {
      "epoch": 0.12136083294648187,
      "grad_norm": 0.464031457901001,
      "learning_rate": 2e-05,
      "loss": 0.7176,
      "step": 1830
    },
    {
      "epoch": 0.12202400689700908,
      "grad_norm": 0.4706140458583832,
      "learning_rate": 2e-05,
      "loss": 0.7097,
      "step": 1840
    },
    {
      "epoch": 0.12268718084753631,
      "grad_norm": 0.4383341670036316,
      "learning_rate": 2e-05,
      "loss": 0.7444,
      "step": 1850
    },
    {
      "epoch": 0.12335035479806353,
      "grad_norm": 0.4670451581478119,
      "learning_rate": 2e-05,
      "loss": 0.7596,
      "step": 1860
    },
    {
      "epoch": 0.12401352874859076,
      "grad_norm": 0.4673280417919159,
      "learning_rate": 2e-05,
      "loss": 0.7292,
      "step": 1870
    },
    {
      "epoch": 0.12467670269911797,
      "grad_norm": 0.49208033084869385,
      "learning_rate": 2e-05,
      "loss": 0.7655,
      "step": 1880
    },
    {
      "epoch": 0.12533987664964522,
      "grad_norm": 0.44742557406425476,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 1890
    },
    {
      "epoch": 0.12600305060017242,
      "grad_norm": 0.47594326734542847,
      "learning_rate": 2e-05,
      "loss": 0.7524,
      "step": 1900
    },
    {
      "epoch": 0.12666622455069965,
      "grad_norm": 0.49186161160469055,
      "learning_rate": 2e-05,
      "loss": 0.7371,
      "step": 1910
    },
    {
      "epoch": 0.12732939850122688,
      "grad_norm": 0.455226331949234,
      "learning_rate": 2e-05,
      "loss": 0.7535,
      "step": 1920
    },
    {
      "epoch": 0.1279925724517541,
      "grad_norm": 0.49632561206817627,
      "learning_rate": 2e-05,
      "loss": 0.7362,
      "step": 1930
    },
    {
      "epoch": 0.1286557464022813,
      "grad_norm": 0.4459867477416992,
      "learning_rate": 2e-05,
      "loss": 0.7312,
      "step": 1940
    },
    {
      "epoch": 0.12931892035280854,
      "grad_norm": 0.48936307430267334,
      "learning_rate": 2e-05,
      "loss": 0.7296,
      "step": 1950
    },
    {
      "epoch": 0.12998209430333577,
      "grad_norm": 0.46001771092414856,
      "learning_rate": 2e-05,
      "loss": 0.7452,
      "step": 1960
    },
    {
      "epoch": 0.130645268253863,
      "grad_norm": 0.4681333601474762,
      "learning_rate": 2e-05,
      "loss": 0.73,
      "step": 1970
    },
    {
      "epoch": 0.13130844220439022,
      "grad_norm": 0.476224422454834,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 1980
    },
    {
      "epoch": 0.13197161615491743,
      "grad_norm": 0.45250940322875977,
      "learning_rate": 2e-05,
      "loss": 0.7424,
      "step": 1990
    },
    {
      "epoch": 0.13263479010544466,
      "grad_norm": 0.49830418825149536,
      "learning_rate": 2e-05,
      "loss": 0.7553,
      "step": 2000
    },
    {
      "epoch": 0.13329796405597188,
      "grad_norm": 0.4795004725456238,
      "learning_rate": 2e-05,
      "loss": 0.7209,
      "step": 2010
    },
    {
      "epoch": 0.13396113800649911,
      "grad_norm": 0.805539608001709,
      "learning_rate": 2e-05,
      "loss": 0.7467,
      "step": 2020
    },
    {
      "epoch": 0.13462431195702632,
      "grad_norm": 0.6310796737670898,
      "learning_rate": 2e-05,
      "loss": 0.7566,
      "step": 2030
    }
  ],
  "logging_steps": 10,
  "max_steps": 5935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2035,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.084295122442519e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}