{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 372,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013458950201884253,
      "grad_norm": 1.00712251663208,
      "learning_rate": 1.2903225806451614e-06,
      "loss": 1.264,
      "step": 5
    },
    {
      "epoch": 0.026917900403768506,
      "grad_norm": 0.9430832266807556,
      "learning_rate": 2.9032258064516128e-06,
      "loss": 1.2378,
      "step": 10
    },
    {
      "epoch": 0.040376850605652756,
      "grad_norm": 0.6684543490409851,
      "learning_rate": 4.516129032258065e-06,
      "loss": 1.239,
      "step": 15
    },
    {
      "epoch": 0.05383580080753701,
      "grad_norm": 0.7191868424415588,
      "learning_rate": 6.129032258064517e-06,
      "loss": 1.2218,
      "step": 20
    },
    {
      "epoch": 0.06729475100942127,
      "grad_norm": 0.6867708563804626,
      "learning_rate": 7.741935483870968e-06,
      "loss": 1.2301,
      "step": 25
    },
    {
      "epoch": 0.08075370121130551,
      "grad_norm": 0.6379647254943848,
      "learning_rate": 9.35483870967742e-06,
      "loss": 1.2194,
      "step": 30
    },
    {
      "epoch": 0.09421265141318977,
      "grad_norm": 0.5798360109329224,
      "learning_rate": 1.0967741935483872e-05,
      "loss": 1.2002,
      "step": 35
    },
    {
      "epoch": 0.10767160161507403,
      "grad_norm": 0.5719746351242065,
      "learning_rate": 1.2580645161290324e-05,
      "loss": 1.1982,
      "step": 40
    },
    {
      "epoch": 0.12113055181695828,
      "grad_norm": 0.5450358390808105,
      "learning_rate": 1.4193548387096776e-05,
      "loss": 1.1986,
      "step": 45
    },
    {
      "epoch": 0.13458950201884254,
      "grad_norm": 0.5413178205490112,
      "learning_rate": 1.5806451612903226e-05,
      "loss": 1.1955,
      "step": 50
    },
    {
      "epoch": 0.1480484522207268,
      "grad_norm": 0.5677768588066101,
      "learning_rate": 1.741935483870968e-05,
      "loss": 1.1496,
      "step": 55
    },
    {
      "epoch": 0.16150740242261102,
      "grad_norm": 0.5705103278160095,
      "learning_rate": 1.903225806451613e-05,
      "loss": 1.1377,
      "step": 60
    },
    {
      "epoch": 0.17496635262449528,
      "grad_norm": 0.6191664934158325,
      "learning_rate": 2.0645161290322582e-05,
      "loss": 1.1242,
      "step": 65
    },
    {
      "epoch": 0.18842530282637954,
      "grad_norm": 0.41417160630226135,
      "learning_rate": 2.2258064516129034e-05,
      "loss": 1.0923,
      "step": 70
    },
    {
      "epoch": 0.2018842530282638,
      "grad_norm": 0.5877333283424377,
      "learning_rate": 2.3870967741935483e-05,
      "loss": 1.1575,
      "step": 75
    },
    {
      "epoch": 0.21534320323014805,
      "grad_norm": 0.5006933808326721,
      "learning_rate": 2.548387096774194e-05,
      "loss": 1.0873,
      "step": 80
    },
    {
      "epoch": 0.2288021534320323,
      "grad_norm": 0.5454208254814148,
      "learning_rate": 2.7096774193548387e-05,
      "loss": 1.073,
      "step": 85
    },
    {
      "epoch": 0.24226110363391656,
      "grad_norm": 0.4708370268344879,
      "learning_rate": 2.870967741935484e-05,
      "loss": 1.1246,
      "step": 90
    },
    {
      "epoch": 0.2557200538358008,
      "grad_norm": 0.7446239590644836,
      "learning_rate": 2.9999976292388853e-05,
      "loss": 1.0893,
      "step": 95
    },
    {
      "epoch": 0.2691790040376851,
      "grad_norm": 0.5205251574516296,
      "learning_rate": 2.999914653386729e-05,
      "loss": 1.0233,
      "step": 100
    },
    {
      "epoch": 0.28263795423956933,
      "grad_norm": 0.5542618632316589,
      "learning_rate": 2.9997131469727287e-05,
      "loss": 1.0534,
      "step": 105
    },
    {
      "epoch": 0.2960969044414536,
      "grad_norm": 0.5413870811462402,
      "learning_rate": 2.9993931259209015e-05,
      "loss": 1.0217,
      "step": 110
    },
    {
      "epoch": 0.30955585464333785,
      "grad_norm": 0.5619310736656189,
      "learning_rate": 2.998954615520871e-05,
      "loss": 1.0357,
      "step": 115
    },
    {
      "epoch": 0.32301480484522205,
      "grad_norm": 0.5382521152496338,
      "learning_rate": 2.998397650425863e-05,
      "loss": 1.0228,
      "step": 120
    },
    {
      "epoch": 0.3364737550471063,
      "grad_norm": 0.6172555088996887,
      "learning_rate": 2.997722274649974e-05,
      "loss": 0.9711,
      "step": 125
    },
    {
      "epoch": 0.34993270524899056,
      "grad_norm": 0.6441250443458557,
      "learning_rate": 2.9969285415646874e-05,
      "loss": 0.9977,
      "step": 130
    },
    {
      "epoch": 0.3633916554508748,
      "grad_norm": 0.5927826166152954,
      "learning_rate": 2.9960165138946572e-05,
      "loss": 0.9778,
      "step": 135
    },
    {
      "epoch": 0.3768506056527591,
      "grad_norm": 0.6550005078315735,
      "learning_rate": 2.9949862637127523e-05,
      "loss": 0.9335,
      "step": 140
    },
    {
      "epoch": 0.39030955585464333,
      "grad_norm": 0.5886467099189758,
      "learning_rate": 2.9938378724343604e-05,
      "loss": 0.9681,
      "step": 145
    },
    {
      "epoch": 0.4037685060565276,
      "grad_norm": 0.7246305346488953,
      "learning_rate": 2.992571430810954e-05,
      "loss": 0.9701,
      "step": 150
    },
    {
      "epoch": 0.41722745625841184,
      "grad_norm": 0.7467737197875977,
      "learning_rate": 2.9911870389229192e-05,
      "loss": 0.9141,
      "step": 155
    },
    {
      "epoch": 0.4306864064602961,
      "grad_norm": 0.7680078744888306,
      "learning_rate": 2.9896848061716456e-05,
      "loss": 0.8685,
      "step": 160
    },
    {
      "epoch": 0.44414535666218036,
      "grad_norm": 0.7801365256309509,
      "learning_rate": 2.9880648512708834e-05,
      "loss": 0.9138,
      "step": 165
    },
    {
      "epoch": 0.4576043068640646,
      "grad_norm": 0.6462291479110718,
      "learning_rate": 2.9863273022373585e-05,
      "loss": 0.9223,
      "step": 170
    },
    {
      "epoch": 0.47106325706594887,
      "grad_norm": 0.6398594975471497,
      "learning_rate": 2.9844722963806592e-05,
      "loss": 0.9021,
      "step": 175
    },
    {
      "epoch": 0.4845222072678331,
      "grad_norm": 0.683367133140564,
      "learning_rate": 2.9824999802923846e-05,
      "loss": 0.8599,
      "step": 180
    },
    {
      "epoch": 0.4979811574697174,
      "grad_norm": 0.7672361731529236,
      "learning_rate": 2.9804105098345575e-05,
      "loss": 0.9282,
      "step": 185
    },
    {
      "epoch": 0.5114401076716016,
      "grad_norm": 0.6266528367996216,
      "learning_rate": 2.9782040501273126e-05,
      "loss": 0.8664,
      "step": 190
    },
    {
      "epoch": 0.5248990578734859,
      "grad_norm": 0.7748366594314575,
      "learning_rate": 2.975880775535843e-05,
      "loss": 0.8588,
      "step": 195
    },
    {
      "epoch": 0.5383580080753702,
      "grad_norm": 0.892792820930481,
      "learning_rate": 2.9734408696566224e-05,
      "loss": 0.8517,
      "step": 200
    },
    {
      "epoch": 0.5518169582772544,
      "grad_norm": 0.8755563497543335,
      "learning_rate": 2.9708845253028988e-05,
      "loss": 0.9136,
      "step": 205
    },
    {
      "epoch": 0.5652759084791387,
      "grad_norm": 0.7859370708465576,
      "learning_rate": 2.9682119444894545e-05,
      "loss": 0.7955,
      "step": 210
    },
    {
      "epoch": 0.5787348586810229,
      "grad_norm": 0.7947808504104614,
      "learning_rate": 2.9654233384166435e-05,
      "loss": 0.8695,
      "step": 215
    },
    {
      "epoch": 0.5921938088829072,
      "grad_norm": 0.7226110696792603,
      "learning_rate": 2.9625189274537004e-05,
      "loss": 0.7672,
      "step": 220
    },
    {
      "epoch": 0.6056527590847914,
      "grad_norm": 1.0677162408828735,
      "learning_rate": 2.9594989411213266e-05,
      "loss": 0.816,
      "step": 225
    },
    {
      "epoch": 0.6191117092866757,
      "grad_norm": 0.8201079964637756,
      "learning_rate": 2.9563636180735524e-05,
      "loss": 0.7877,
      "step": 230
    },
    {
      "epoch": 0.6325706594885598,
      "grad_norm": 0.961162805557251,
      "learning_rate": 2.9531132060788763e-05,
      "loss": 0.7566,
      "step": 235
    },
    {
      "epoch": 0.6460296096904441,
      "grad_norm": 0.9038267731666565,
      "learning_rate": 2.9497479620006873e-05,
      "loss": 0.8061,
      "step": 240
    },
    {
      "epoch": 0.6594885598923284,
      "grad_norm": 0.9068340063095093,
      "learning_rate": 2.9462681517769638e-05,
      "loss": 0.787,
      "step": 245
    },
    {
      "epoch": 0.6729475100942126,
      "grad_norm": 0.8361156582832336,
      "learning_rate": 2.94267405039926e-05,
      "loss": 0.7835,
      "step": 250
    },
    {
      "epoch": 0.6864064602960969,
      "grad_norm": 0.8174508213996887,
      "learning_rate": 2.938965941890972e-05,
      "loss": 0.7641,
      "step": 255
    },
    {
      "epoch": 0.6998654104979811,
      "grad_norm": 0.8101845383644104,
      "learning_rate": 2.9351441192848972e-05,
      "loss": 0.76,
      "step": 260
    },
    {
      "epoch": 0.7133243606998654,
      "grad_norm": 0.8047847747802734,
      "learning_rate": 2.9312088846000733e-05,
      "loss": 0.7404,
      "step": 265
    },
    {
      "epoch": 0.7267833109017496,
      "grad_norm": 0.8787263035774231,
      "learning_rate": 2.927160548817913e-05,
      "loss": 0.7335,
      "step": 270
    },
    {
      "epoch": 0.7402422611036339,
      "grad_norm": 0.9566526412963867,
      "learning_rate": 2.9229994318576295e-05,
      "loss": 0.7546,
      "step": 275
    },
    {
      "epoch": 0.7537012113055181,
      "grad_norm": 0.9340652227401733,
      "learning_rate": 2.9187258625509518e-05,
      "loss": 0.6814,
      "step": 280
    },
    {
      "epoch": 0.7671601615074024,
      "grad_norm": 1.0249980688095093,
      "learning_rate": 2.9143401786161445e-05,
      "loss": 0.7116,
      "step": 285
    },
    {
      "epoch": 0.7806191117092867,
      "grad_norm": 0.8947973847389221,
      "learning_rate": 2.9098427266313138e-05,
      "loss": 0.6845,
      "step": 290
    },
    {
      "epoch": 0.7940780619111709,
      "grad_norm": 0.9918004274368286,
      "learning_rate": 2.9052338620070215e-05,
      "loss": 0.7287,
      "step": 295
    },
    {
      "epoch": 0.8075370121130552,
      "grad_norm": 0.9002223610877991,
      "learning_rate": 2.9005139489582002e-05,
      "loss": 0.7129,
      "step": 300
    },
    {
      "epoch": 0.8209959623149394,
      "grad_norm": 0.8825509548187256,
      "learning_rate": 2.8956833604753688e-05,
      "loss": 0.6633,
      "step": 305
    },
    {
      "epoch": 0.8344549125168237,
      "grad_norm": 0.8505289554595947,
      "learning_rate": 2.8907424782951587e-05,
      "loss": 0.6826,
      "step": 310
    },
    {
      "epoch": 0.847913862718708,
      "grad_norm": 1.0375418663024902,
      "learning_rate": 2.8856916928701467e-05,
      "loss": 0.7003,
      "step": 315
    },
    {
      "epoch": 0.8613728129205922,
      "grad_norm": 1.0597079992294312,
      "learning_rate": 2.8805314033379985e-05,
      "loss": 0.7151,
      "step": 320
    },
    {
      "epoch": 0.8748317631224765,
      "grad_norm": 1.1800124645233154,
      "learning_rate": 2.8752620174899284e-05,
      "loss": 0.6594,
      "step": 325
    },
    {
      "epoch": 0.8882907133243607,
      "grad_norm": 0.9276929497718811,
      "learning_rate": 2.8698839517384726e-05,
      "loss": 0.651,
      "step": 330
    },
    {
      "epoch": 0.901749663526245,
      "grad_norm": 1.094962239265442,
      "learning_rate": 2.8643976310845828e-05,
      "loss": 0.6412,
      "step": 335
    },
    {
      "epoch": 0.9152086137281292,
      "grad_norm": 0.9263754487037659,
      "learning_rate": 2.8588034890840408e-05,
      "loss": 0.6269,
      "step": 340
    },
    {
      "epoch": 0.9286675639300135,
      "grad_norm": 0.9816908240318298,
      "learning_rate": 2.8531019678131952e-05,
      "loss": 0.6577,
      "step": 345
    },
    {
      "epoch": 0.9421265141318977,
      "grad_norm": 1.0188283920288086,
      "learning_rate": 2.847293517834029e-05,
      "loss": 0.66,
      "step": 350
    },
    {
      "epoch": 0.955585464333782,
      "grad_norm": 1.0503355264663696,
      "learning_rate": 2.8413785981585518e-05,
      "loss": 0.621,
      "step": 355
    },
    {
      "epoch": 0.9690444145356663,
      "grad_norm": 0.9092134237289429,
      "learning_rate": 2.8353576762125274e-05,
      "loss": 0.6343,
      "step": 360
    },
    {
      "epoch": 0.9825033647375505,
      "grad_norm": 0.9565970301628113,
      "learning_rate": 2.8292312277985354e-05,
      "loss": 0.6538,
      "step": 365
    },
    {
      "epoch": 0.9959623149394348,
      "grad_norm": 1.014952301979065,
      "learning_rate": 2.82299973705837e-05,
      "loss": 0.6081,
      "step": 370
    }
  ],
  "logging_steps": 5,
  "max_steps": 1860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.29235739645313e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}