{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999360204734485,
  "eval_steps": 500,
  "global_step": 781,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 6.218732532974693,
      "learning_rate": 2.5316455696202533e-07,
      "loss": 1.0548,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 6.057508328025577,
      "learning_rate": 1.2658227848101267e-06,
      "loss": 1.0608,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 6.634383000711397,
      "learning_rate": 2.5316455696202535e-06,
      "loss": 1.0311,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 42.22599030062134,
      "learning_rate": 3.7974683544303802e-06,
      "loss": 0.9446,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.6255048263910823,
      "learning_rate": 5.063291139240507e-06,
      "loss": 0.855,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.223041853621419,
      "learning_rate": 6.329113924050634e-06,
      "loss": 0.8515,
      "step": 25
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.1499117468328068,
      "learning_rate": 7.5949367088607605e-06,
      "loss": 0.8538,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.9893284992712339,
      "learning_rate": 8.860759493670886e-06,
      "loss": 0.8499,
      "step": 35
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.0330597408673325,
      "learning_rate": 1.0126582278481014e-05,
      "loss": 0.8349,
      "step": 40
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.9454728301913932,
      "learning_rate": 1.139240506329114e-05,
      "loss": 0.8139,
      "step": 45
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.867009450049442,
      "learning_rate": 1.2658227848101268e-05,
      "loss": 0.7961,
      "step": 50
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.9233088577396095,
      "learning_rate": 1.3924050632911395e-05,
      "loss": 0.8041,
      "step": 55
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.897730187587102,
      "learning_rate": 1.5189873417721521e-05,
      "loss": 0.8009,
      "step": 60
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.9115211129634383,
      "learning_rate": 1.6455696202531647e-05,
      "loss": 0.7969,
      "step": 65
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.9078252304377841,
      "learning_rate": 1.7721518987341772e-05,
      "loss": 0.8128,
      "step": 70
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.8821431725791585,
      "learning_rate": 1.89873417721519e-05,
      "loss": 0.7563,
      "step": 75
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.8438829745337315,
      "learning_rate": 1.999989986294826e-05,
      "loss": 0.794,
      "step": 80
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.9429490146138716,
      "learning_rate": 1.9996395276708856e-05,
      "loss": 0.7879,
      "step": 85
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.0152173886159006,
      "learning_rate": 1.9987885843187717e-05,
      "loss": 0.788,
      "step": 90
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.9186368798898343,
      "learning_rate": 1.9974375822762117e-05,
      "loss": 0.7707,
      "step": 95
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.8971041378168991,
      "learning_rate": 1.9955871979429188e-05,
      "loss": 0.7664,
      "step": 100
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.9008904434552364,
      "learning_rate": 1.9932383577419432e-05,
      "loss": 0.8074,
      "step": 105
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.028657752464771,
      "learning_rate": 1.9903922376558432e-05,
      "loss": 0.7919,
      "step": 110
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.9517557420940557,
      "learning_rate": 1.9870502626379127e-05,
      "loss": 0.7998,
      "step": 115
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.9048840711577915,
      "learning_rate": 1.983214105898757e-05,
      "loss": 0.7804,
      "step": 120
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.9111504895861703,
      "learning_rate": 1.978885688068572e-05,
      "loss": 0.7538,
      "step": 125
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.902524854174019,
      "learning_rate": 1.9740671762355548e-05,
      "loss": 0.7566,
      "step": 130
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.9110302651471653,
      "learning_rate": 1.9687609828609156e-05,
      "loss": 0.7737,
      "step": 135
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.9438921387685624,
      "learning_rate": 1.9629697645710432e-05,
      "loss": 0.7561,
      "step": 140
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.8687548609010227,
      "learning_rate": 1.9566964208274254e-05,
      "loss": 0.7564,
      "step": 145
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.9360336326575724,
      "learning_rate": 1.9499440924749878e-05,
      "loss": 0.7616,
      "step": 150
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9291842110885165,
      "learning_rate": 1.9427161601695833e-05,
      "loss": 0.7587,
      "step": 155
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.8992521463936806,
      "learning_rate": 1.9350162426854152e-05,
      "loss": 0.7923,
      "step": 160
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.9199465839289203,
      "learning_rate": 1.926848195103242e-05,
      "loss": 0.7567,
      "step": 165
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.9202340634296483,
      "learning_rate": 1.9182161068802742e-05,
      "loss": 0.7561,
      "step": 170
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.8815186951994902,
      "learning_rate": 1.909124299802724e-05,
      "loss": 0.7602,
      "step": 175
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.9374982372632831,
      "learning_rate": 1.8995773258220374e-05,
      "loss": 0.7726,
      "step": 180
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.8668215722574871,
      "learning_rate": 1.8895799647758912e-05,
      "loss": 0.7641,
      "step": 185
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.9704566556440527,
      "learning_rate": 1.879137221995095e-05,
      "loss": 0.7631,
      "step": 190
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.0765530525420333,
      "learning_rate": 1.868254325797594e-05,
      "loss": 0.7602,
      "step": 195
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.8477600964123878,
      "learning_rate": 1.8569367248708343e-05,
      "loss": 0.7696,
      "step": 200
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.8880373428392885,
      "learning_rate": 1.845190085543795e-05,
      "loss": 0.7717,
      "step": 205
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.9054121985443794,
      "learning_rate": 1.8330202889500518e-05,
      "loss": 0.7594,
      "step": 210
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.9241486536472063,
      "learning_rate": 1.8204334280833005e-05,
      "loss": 0.7461,
      "step": 215
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.8883815381945972,
      "learning_rate": 1.807435804746807e-05,
      "loss": 0.7244,
      "step": 220
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.954185859352863,
      "learning_rate": 1.7940339263983112e-05,
      "loss": 0.7546,
      "step": 225
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.9582618105947629,
      "learning_rate": 1.7802345028919728e-05,
      "loss": 0.7673,
      "step": 230
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9337180429875352,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.7371,
      "step": 235
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.0151633649691056,
      "learning_rate": 1.7514708515485002e-05,
      "loss": 0.7531,
      "step": 240
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.8996109508979938,
      "learning_rate": 1.736521024670737e-05,
      "loss": 0.7726,
      "step": 245
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9539154938066643,
      "learning_rate": 1.7212024473438145e-05,
      "loss": 0.7594,
      "step": 250
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.8527276784078115,
      "learning_rate": 1.705522789046377e-05,
      "loss": 0.7608,
      "step": 255
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.9081328398716373,
      "learning_rate": 1.6894899000377462e-05,
      "loss": 0.7626,
      "step": 260
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.8896600535495715,
      "learning_rate": 1.67311180742757e-05,
      "loss": 0.7633,
      "step": 265
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.8828152532467378,
      "learning_rate": 1.65639671115693e-05,
      "loss": 0.7314,
      "step": 270
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.91123554695286,
      "learning_rate": 1.6393529798929103e-05,
      "loss": 0.7568,
      "step": 275
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.7802151937182064,
      "learning_rate": 1.621989146838704e-05,
      "loss": 0.7301,
      "step": 280
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.8417341529900935,
      "learning_rate": 1.6043139054613326e-05,
      "loss": 0.7409,
      "step": 285
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.8874377472816912,
      "learning_rate": 1.586336105139127e-05,
      "loss": 0.7586,
      "step": 290
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.8993804934668429,
      "learning_rate": 1.568064746731156e-05,
      "loss": 0.7612,
      "step": 295
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.8743646519888882,
      "learning_rate": 1.5495089780708062e-05,
      "loss": 0.7208,
      "step": 300
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.8726571855013807,
      "learning_rate": 1.530678089385782e-05,
      "loss": 0.7296,
      "step": 305
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8216013695365607,
      "learning_rate": 1.5115815086468103e-05,
      "loss": 0.7194,
      "step": 310
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.911275664325399,
      "learning_rate": 1.492228796847385e-05,
      "loss": 0.7436,
      "step": 315
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8922331403520879,
      "learning_rate": 1.4726296432169095e-05,
      "loss": 0.7009,
      "step": 320
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.8415314327536128,
      "learning_rate": 1.4527938603696376e-05,
      "loss": 0.7563,
      "step": 325
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.8469607469311058,
      "learning_rate": 1.4327313793918362e-05,
      "loss": 0.7254,
      "step": 330
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.8834979947462068,
      "learning_rate": 1.4124522448696407e-05,
      "loss": 0.7516,
      "step": 335
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.8544733801934922,
      "learning_rate": 1.3919666098600753e-05,
      "loss": 0.7511,
      "step": 340
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.8997621369784197,
      "learning_rate": 1.3712847308077737e-05,
      "loss": 0.7395,
      "step": 345
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.8650786485343112,
      "learning_rate": 1.350416962409934e-05,
      "loss": 0.733,
      "step": 350
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.8646529478803704,
      "learning_rate": 1.3293737524320798e-05,
      "loss": 0.7319,
      "step": 355
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.9052937039545919,
      "learning_rate": 1.3081656364772308e-05,
      "loss": 0.7474,
      "step": 360
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.869464472615771,
      "learning_rate": 1.2868032327110904e-05,
      "loss": 0.7373,
      "step": 365
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.8872298202760914,
      "learning_rate": 1.2652972365459008e-05,
      "loss": 0.7178,
      "step": 370
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.9203346359488073,
      "learning_rate": 1.243658415285622e-05,
      "loss": 0.7384,
      "step": 375
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.8282910946726554,
      "learning_rate": 1.2218976027351177e-05,
      "loss": 0.7138,
      "step": 380
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.8872272744445378,
      "learning_rate": 1.2000256937760446e-05,
      "loss": 0.706,
      "step": 385
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.84010568628107,
      "learning_rate": 1.1780536389121668e-05,
      "loss": 0.7217,
      "step": 390
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.8336774434546579,
      "learning_rate": 1.155992438786818e-05,
      "loss": 0.7431,
      "step": 395
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.8842944246611821,
      "learning_rate": 1.1338531386752618e-05,
      "loss": 0.7203,
      "step": 400
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.898037732512393,
      "learning_rate": 1.1116468229547079e-05,
      "loss": 0.7497,
      "step": 405
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.8824051684243204,
      "learning_rate": 1.0893846095547493e-05,
      "loss": 0.7424,
      "step": 410
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.8537154820589267,
      "learning_rate": 1.0670776443910024e-05,
      "loss": 0.7391,
      "step": 415
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.9527482786635838,
      "learning_rate": 1.0447370957847343e-05,
      "loss": 0.7288,
      "step": 420
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.8801360044023759,
      "learning_rate": 1.0223741488712732e-05,
      "loss": 0.7177,
      "step": 425
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.9017111738645169,
      "learning_rate": 1e-05,
      "loss": 0.7279,
      "step": 430
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.8799316098800196,
      "learning_rate": 9.776258511287271e-06,
      "loss": 0.7172,
      "step": 435
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.8727504370270498,
      "learning_rate": 9.55262904215266e-06,
      "loss": 0.7424,
      "step": 440
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.852138299323907,
      "learning_rate": 9.329223556089976e-06,
      "loss": 0.743,
      "step": 445
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8429170905572736,
      "learning_rate": 9.10615390445251e-06,
      "loss": 0.7311,
      "step": 450
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.8715107251678864,
      "learning_rate": 8.883531770452924e-06,
      "loss": 0.733,
      "step": 455
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.8309750831558879,
      "learning_rate": 8.661468613247387e-06,
      "loss": 0.726,
      "step": 460
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.8594819292949775,
      "learning_rate": 8.440075612131823e-06,
      "loss": 0.7387,
      "step": 465
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.8578509085890005,
      "learning_rate": 8.219463610878336e-06,
      "loss": 0.7154,
      "step": 470
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.8406550181595651,
      "learning_rate": 7.999743062239557e-06,
      "loss": 0.7044,
      "step": 475
    },
    {
      "epoch": 0.61,
      "grad_norm": 1.1106794650945297,
      "learning_rate": 7.781023972648826e-06,
      "loss": 0.7529,
      "step": 480
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.8787480716579242,
      "learning_rate": 7.563415847143782e-06,
      "loss": 0.7416,
      "step": 485
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.8856437968758147,
      "learning_rate": 7.347027634540993e-06,
      "loss": 0.7234,
      "step": 490
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.9115469753409513,
      "learning_rate": 7.131967672889101e-06,
      "loss": 0.7189,
      "step": 495
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.8461806387832909,
      "learning_rate": 6.918343635227694e-06,
      "loss": 0.739,
      "step": 500
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.8797246523561782,
      "learning_rate": 6.706262475679205e-06,
      "loss": 0.7212,
      "step": 505
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.8833725465549789,
      "learning_rate": 6.495830375900665e-06,
      "loss": 0.7344,
      "step": 510
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.90720732768669,
      "learning_rate": 6.287152691922264e-06,
      "loss": 0.7363,
      "step": 515
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.8562580507509661,
      "learning_rate": 6.080333901399252e-06,
      "loss": 0.714,
      "step": 520
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.8368554839429542,
      "learning_rate": 5.875477551303596e-06,
      "loss": 0.6968,
      "step": 525
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.8551918920773244,
      "learning_rate": 5.672686206081638e-06,
      "loss": 0.7354,
      "step": 530
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.8806502111077001,
      "learning_rate": 5.47206139630363e-06,
      "loss": 0.7009,
      "step": 535
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.8432642364408135,
      "learning_rate": 5.273703567830908e-06,
      "loss": 0.7256,
      "step": 540
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.8082119727212804,
      "learning_rate": 5.077712031526153e-06,
      "loss": 0.7113,
      "step": 545
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.8840305956304885,
      "learning_rate": 4.8841849135319015e-06,
      "loss": 0.7125,
      "step": 550
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.8512866204723579,
      "learning_rate": 4.693219106142186e-06,
      "loss": 0.7077,
      "step": 555
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8690925493996771,
      "learning_rate": 4.504910219291941e-06,
      "loss": 0.7265,
      "step": 560
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8486039006714249,
      "learning_rate": 4.319352532688444e-06,
      "loss": 0.7045,
      "step": 565
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.8343157357633112,
      "learning_rate": 4.13663894860873e-06,
      "loss": 0.7081,
      "step": 570
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.8517869372115919,
      "learning_rate": 3.956860945386677e-06,
      "loss": 0.7099,
      "step": 575
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.8810686746902263,
      "learning_rate": 3.7801085316129615e-06,
      "loss": 0.7184,
      "step": 580
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.8303217013600214,
      "learning_rate": 3.606470201070904e-06,
      "loss": 0.7046,
      "step": 585
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.8143514289362858,
      "learning_rate": 3.4360328884307058e-06,
      "loss": 0.7301,
      "step": 590
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.8919694336829919,
      "learning_rate": 3.2688819257242963e-06,
      "loss": 0.7077,
      "step": 595
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.8712369558568198,
      "learning_rate": 3.1051009996225434e-06,
      "loss": 0.7289,
      "step": 600
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.9359803251828337,
      "learning_rate": 2.9447721095362325e-06,
      "loss": 0.7222,
      "step": 605
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.8118275265180527,
      "learning_rate": 2.7879755265618558e-06,
      "loss": 0.6989,
      "step": 610
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.8993664919932826,
      "learning_rate": 2.6347897532926293e-06,
      "loss": 0.7301,
      "step": 615
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.8299858708500569,
      "learning_rate": 2.485291484515e-06,
      "loss": 0.7282,
      "step": 620
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9509542819405852,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.7321,
      "step": 625
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.8207790304441084,
      "learning_rate": 2.1976549710802754e-06,
      "loss": 0.704,
      "step": 630
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.8915125592646993,
      "learning_rate": 2.0596607360168897e-06,
      "loss": 0.7155,
      "step": 635
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.893971232650736,
      "learning_rate": 1.9256419525319316e-06,
      "loss": 0.7108,
      "step": 640
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.8642943561769831,
      "learning_rate": 1.7956657191669969e-06,
      "loss": 0.7254,
      "step": 645
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.7620702133454862,
      "learning_rate": 1.6697971104994847e-06,
      "loss": 0.701,
      "step": 650
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.9164562019661466,
      "learning_rate": 1.5480991445620541e-06,
      "loss": 0.7252,
      "step": 655
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.86265325973436,
      "learning_rate": 1.4306327512916574e-06,
      "loss": 0.7207,
      "step": 660
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.8591146598972604,
      "learning_rate": 1.3174567420240647e-06,
      "loss": 0.7459,
      "step": 665
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.8261037051966178,
      "learning_rate": 1.2086277800490554e-06,
      "loss": 0.7142,
      "step": 670
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.820114794330799,
      "learning_rate": 1.1042003522410882e-06,
      "loss": 0.7358,
      "step": 675
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.86546920512789,
      "learning_rate": 1.0042267417796292e-06,
      "loss": 0.7088,
      "step": 680
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.8769857056502491,
      "learning_rate": 9.08757001972762e-07,
      "loss": 0.7036,
      "step": 685
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.8727105004473635,
      "learning_rate": 8.178389311972612e-07,
      "loss": 0.7352,
      "step": 690
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.8878216519646419,
      "learning_rate": 7.315180489675822e-07,
      "loss": 0.7161,
      "step": 695
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.8073527792911568,
      "learning_rate": 6.498375731458529e-07,
      "loss": 0.7157,
      "step": 700
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.8674439240960509,
      "learning_rate": 5.728383983041696e-07,
      "loss": 0.6966,
      "step": 705
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.8270417868101663,
      "learning_rate": 5.005590752501244e-07,
      "loss": 0.7165,
      "step": 710
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.8133004838860258,
      "learning_rate": 4.3303579172574884e-07,
      "loss": 0.7161,
      "step": 715
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.835774320081132,
      "learning_rate": 3.7030235428956895e-07,
      "loss": 0.7052,
      "step": 720
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.8786655763475584,
      "learning_rate": 3.1239017139084725e-07,
      "loss": 0.712,
      "step": 725
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.7922242941846357,
      "learning_rate": 2.593282376444539e-07,
      "loss": 0.7145,
      "step": 730
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.8040418257479052,
      "learning_rate": 2.11143119314281e-07,
      "loss": 0.7076,
      "step": 735
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.8478224913150121,
      "learning_rate": 1.6785894101243205e-07,
      "loss": 0.7232,
      "step": 740
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.8323563837704016,
      "learning_rate": 1.2949737362087156e-07,
      "loss": 0.7098,
      "step": 745
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.8756057853063033,
      "learning_rate": 9.607762344156946e-08,
      "loss": 0.734,
      "step": 750
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.8581279382569037,
      "learning_rate": 6.761642258056977e-08,
      "loss": 0.7192,
      "step": 755
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.8325693456753873,
      "learning_rate": 4.412802057081278e-08,
      "loss": 0.7203,
      "step": 760
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.8361298423651424,
      "learning_rate": 2.5624177237884017e-08,
      "loss": 0.7164,
      "step": 765
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.7881888700108141,
      "learning_rate": 1.2114156812284006e-08,
      "loss": 0.715,
      "step": 770
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.8284253094519822,
      "learning_rate": 3.6047232911462506e-09,
      "loss": 0.7185,
      "step": 775
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8527930204989956,
      "learning_rate": 1.0013705174061195e-10,
      "loss": 0.735,
      "step": 780
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7233731150627136,
      "eval_runtime": 630.7835,
      "eval_samples_per_second": 68.169,
      "eval_steps_per_second": 2.131,
      "step": 781
    },
    {
      "epoch": 1.0,
      "step": 781,
      "total_flos": 80937303736320.0,
      "train_loss": 0.7476945167619654,
      "train_runtime": 7284.6392,
      "train_samples_per_second": 13.727,
      "train_steps_per_second": 0.107
    }
  ],
  "logging_steps": 5,
  "max_steps": 781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 80937303736320.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}