{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025,
      "grad_norm": 70.88893127441406,
      "learning_rate": 2.6999999999999996e-05,
      "loss": 191.82691650390626,
      "step": 10
    },
    {
      "epoch": 0.005,
      "grad_norm": 34.866336822509766,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 181.0546630859375,
      "step": 20
    },
    {
      "epoch": 0.0075,
      "grad_norm": 26.507795333862305,
      "learning_rate": 8.699999999999999e-05,
      "loss": 168.4577392578125,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 26.122739791870117,
      "learning_rate": 0.000117,
      "loss": 155.47222900390625,
      "step": 40
    },
    {
      "epoch": 0.0125,
      "grad_norm": 16.647830963134766,
      "learning_rate": 0.000147,
      "loss": 140.944287109375,
      "step": 50
    },
    {
      "epoch": 0.015,
      "grad_norm": 13.81060791015625,
      "learning_rate": 0.00017699999999999997,
      "loss": 130.086962890625,
      "step": 60
    },
    {
      "epoch": 0.0175,
      "grad_norm": 17.337005615234375,
      "learning_rate": 0.00020699999999999996,
      "loss": 125.63973388671874,
      "step": 70
    },
    {
      "epoch": 0.02,
      "grad_norm": 20.01132583618164,
      "learning_rate": 0.000237,
      "loss": 124.44827880859376,
      "step": 80
    },
    {
      "epoch": 0.0225,
      "grad_norm": 22.17510986328125,
      "learning_rate": 0.000267,
      "loss": 123.71231689453126,
      "step": 90
    },
    {
      "epoch": 0.025,
      "grad_norm": 18.62161636352539,
      "learning_rate": 0.00029699999999999996,
      "loss": 121.8670166015625,
      "step": 100
    },
    {
      "epoch": 0.0275,
      "grad_norm": 13.885932922363281,
      "learning_rate": 0.00029930769230769225,
      "loss": 116.4902587890625,
      "step": 110
    },
    {
      "epoch": 0.03,
      "grad_norm": 14.237751960754395,
      "learning_rate": 0.0002985384615384615,
      "loss": 116.7521484375,
      "step": 120
    },
    {
      "epoch": 0.0325,
      "grad_norm": 15.035771369934082,
      "learning_rate": 0.00029776923076923074,
      "loss": 115.98536376953125,
      "step": 130
    },
    {
      "epoch": 0.035,
      "grad_norm": 14.973207473754883,
      "learning_rate": 0.00029699999999999996,
      "loss": 112.8994873046875,
      "step": 140
    },
    {
      "epoch": 0.0375,
      "grad_norm": 14.784521102905273,
      "learning_rate": 0.0002962307692307692,
      "loss": 111.29984130859376,
      "step": 150
    },
    {
      "epoch": 0.04,
      "grad_norm": 17.372440338134766,
      "learning_rate": 0.00029546153846153844,
      "loss": 109.04622802734374,
      "step": 160
    },
    {
      "epoch": 0.0425,
      "grad_norm": 14.24492073059082,
      "learning_rate": 0.00029469230769230766,
      "loss": 105.21751708984375,
      "step": 170
    },
    {
      "epoch": 0.045,
      "grad_norm": 14.290887832641602,
      "learning_rate": 0.00029392307692307693,
      "loss": 104.51602783203126,
      "step": 180
    },
    {
      "epoch": 0.0475,
      "grad_norm": 13.759570121765137,
      "learning_rate": 0.00029315384615384614,
      "loss": 106.98443603515625,
      "step": 190
    },
    {
      "epoch": 0.05,
      "grad_norm": 13.304281234741211,
      "learning_rate": 0.00029238461538461536,
      "loss": 104.3275146484375,
      "step": 200
    },
    {
      "epoch": 0.0525,
      "grad_norm": 13.086603164672852,
      "learning_rate": 0.00029161538461538463,
      "loss": 105.60206298828125,
      "step": 210
    },
    {
      "epoch": 0.055,
      "grad_norm": 17.55739402770996,
      "learning_rate": 0.0002908461538461538,
      "loss": 102.73480224609375,
      "step": 220
    },
    {
      "epoch": 0.0575,
      "grad_norm": 18.34480094909668,
      "learning_rate": 0.00029007692307692306,
      "loss": 100.7387939453125,
      "step": 230
    },
    {
      "epoch": 0.06,
      "grad_norm": 13.852744102478027,
      "learning_rate": 0.0002893076923076923,
      "loss": 101.04940795898438,
      "step": 240
    },
    {
      "epoch": 0.0625,
      "grad_norm": 13.510031700134277,
      "learning_rate": 0.0002885384615384615,
      "loss": 101.42539672851562,
      "step": 250
    },
    {
      "epoch": 0.065,
      "grad_norm": 15.467084884643555,
      "learning_rate": 0.00028776923076923077,
      "loss": 99.12225341796875,
      "step": 260
    },
    {
      "epoch": 0.0675,
      "grad_norm": 15.127578735351562,
      "learning_rate": 0.000287,
      "loss": 96.99212646484375,
      "step": 270
    },
    {
      "epoch": 0.07,
      "grad_norm": 13.582677841186523,
      "learning_rate": 0.0002862307692307692,
      "loss": 99.32898559570313,
      "step": 280
    },
    {
      "epoch": 0.0725,
      "grad_norm": 14.728398323059082,
      "learning_rate": 0.0002854615384615384,
      "loss": 97.85962524414063,
      "step": 290
    },
    {
      "epoch": 0.075,
      "grad_norm": 14.059552192687988,
      "learning_rate": 0.0002846923076923077,
      "loss": 97.9947509765625,
      "step": 300
    },
    {
      "epoch": 0.0775,
      "grad_norm": 14.236120223999023,
      "learning_rate": 0.0002839230769230769,
      "loss": 95.77266845703124,
      "step": 310
    },
    {
      "epoch": 0.08,
      "grad_norm": 13.736848831176758,
      "learning_rate": 0.0002831538461538461,
      "loss": 95.71461791992188,
      "step": 320
    },
    {
      "epoch": 0.0825,
      "grad_norm": 13.170111656188965,
      "learning_rate": 0.0002823846153846154,
      "loss": 94.3592529296875,
      "step": 330
    },
    {
      "epoch": 0.085,
      "grad_norm": 13.982166290283203,
      "learning_rate": 0.00028161538461538455,
      "loss": 94.82847900390625,
      "step": 340
    },
    {
      "epoch": 0.0875,
      "grad_norm": 14.830900192260742,
      "learning_rate": 0.0002808461538461538,
      "loss": 95.237646484375,
      "step": 350
    },
    {
      "epoch": 0.09,
      "grad_norm": 11.988094329833984,
      "learning_rate": 0.00028007692307692304,
      "loss": 92.2238525390625,
      "step": 360
    },
    {
      "epoch": 0.0925,
      "grad_norm": 13.272656440734863,
      "learning_rate": 0.00027930769230769225,
      "loss": 92.32516479492188,
      "step": 370
    },
    {
      "epoch": 0.095,
      "grad_norm": 14.191997528076172,
      "learning_rate": 0.0002785384615384615,
      "loss": 92.53778686523438,
      "step": 380
    },
    {
      "epoch": 0.0975,
      "grad_norm": 16.8336124420166,
      "learning_rate": 0.00027776923076923074,
      "loss": 92.81129760742188,
      "step": 390
    },
    {
      "epoch": 0.1,
      "grad_norm": 11.903277397155762,
      "learning_rate": 0.00027699999999999996,
      "loss": 89.13013305664063,
      "step": 400
    },
    {
      "epoch": 0.1025,
      "grad_norm": 13.759241104125977,
      "learning_rate": 0.00027623076923076923,
      "loss": 91.34515991210938,
      "step": 410
    },
    {
      "epoch": 0.105,
      "grad_norm": 12.553871154785156,
      "learning_rate": 0.00027546153846153844,
      "loss": 91.6295654296875,
      "step": 420
    },
    {
      "epoch": 0.1075,
      "grad_norm": 15.209941864013672,
      "learning_rate": 0.00027469230769230766,
      "loss": 91.69887084960938,
      "step": 430
    },
    {
      "epoch": 0.11,
      "grad_norm": 12.605022430419922,
      "learning_rate": 0.00027392307692307693,
      "loss": 90.24617919921874,
      "step": 440
    },
    {
      "epoch": 0.1125,
      "grad_norm": 14.718850135803223,
      "learning_rate": 0.00027315384615384615,
      "loss": 90.20364990234376,
      "step": 450
    },
    {
      "epoch": 0.115,
      "grad_norm": 12.55235767364502,
      "learning_rate": 0.00027238461538461536,
      "loss": 88.11900024414062,
      "step": 460
    },
    {
      "epoch": 0.1175,
      "grad_norm": 14.204663276672363,
      "learning_rate": 0.0002716153846153846,
      "loss": 90.44221801757813,
      "step": 470
    },
    {
      "epoch": 0.12,
      "grad_norm": 11.577082633972168,
      "learning_rate": 0.0002708461538461538,
      "loss": 88.5084716796875,
      "step": 480
    },
    {
      "epoch": 0.1225,
      "grad_norm": 10.324372291564941,
      "learning_rate": 0.00027007692307692307,
      "loss": 89.32081298828125,
      "step": 490
    },
    {
      "epoch": 0.125,
      "grad_norm": 13.348015785217285,
      "learning_rate": 0.0002693076923076923,
      "loss": 87.786767578125,
      "step": 500
    },
    {
      "epoch": 0.1275,
      "grad_norm": 12.950383186340332,
      "learning_rate": 0.0002685384615384615,
      "loss": 87.12896118164062,
      "step": 510
    },
    {
      "epoch": 0.13,
      "grad_norm": 12.832451820373535,
      "learning_rate": 0.00026776923076923077,
      "loss": 88.82958374023437,
      "step": 520
    },
    {
      "epoch": 0.1325,
      "grad_norm": 14.343534469604492,
      "learning_rate": 0.000267,
      "loss": 87.53173217773437,
      "step": 530
    },
    {
      "epoch": 0.135,
      "grad_norm": 11.609414100646973,
      "learning_rate": 0.0002662307692307692,
      "loss": 86.57319946289063,
      "step": 540
    },
    {
      "epoch": 0.1375,
      "grad_norm": 13.554574012756348,
      "learning_rate": 0.00026546153846153847,
      "loss": 87.31171264648438,
      "step": 550
    },
    {
      "epoch": 0.14,
      "grad_norm": 14.38441276550293,
      "learning_rate": 0.0002646923076923077,
      "loss": 85.79506225585938,
      "step": 560
    },
    {
      "epoch": 0.1425,
      "grad_norm": 12.652528762817383,
      "learning_rate": 0.0002639230769230769,
      "loss": 86.28104248046876,
      "step": 570
    },
    {
      "epoch": 0.145,
      "grad_norm": 12.158783912658691,
      "learning_rate": 0.0002631538461538461,
      "loss": 85.13269653320313,
      "step": 580
    },
    {
      "epoch": 0.1475,
      "grad_norm": 13.032898902893066,
      "learning_rate": 0.00026238461538461534,
      "loss": 85.8595458984375,
      "step": 590
    },
    {
      "epoch": 0.15,
      "grad_norm": 14.406429290771484,
      "learning_rate": 0.0002616153846153846,
      "loss": 86.73550415039062,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.00712760885504e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}