{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002343167068544227,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.9289588356802836e-05,
      "grad_norm": 43.412994384765625,
      "learning_rate": 4.8e-07,
      "loss": 9.4322,
      "step": 10
    },
    {
      "epoch": 5.857917671360567e-05,
      "grad_norm": 24.38200569152832,
      "learning_rate": 1.0799999999999998e-06,
      "loss": 9.4165,
      "step": 20
    },
    {
      "epoch": 8.786876507040851e-05,
      "grad_norm": 25.624269485473633,
      "learning_rate": 1.6799999999999998e-06,
      "loss": 9.3983,
      "step": 30
    },
    {
      "epoch": 0.00011715835342721134,
      "grad_norm": 25.8831729888916,
      "learning_rate": 2.2799999999999998e-06,
      "loss": 9.4015,
      "step": 40
    },
    {
      "epoch": 0.00014644794178401418,
      "grad_norm": 18.858943939208984,
      "learning_rate": 2.8799999999999995e-06,
      "loss": 9.369,
      "step": 50
    },
    {
      "epoch": 0.00017573753014081702,
      "grad_norm": 32.19478225708008,
      "learning_rate": 3.4799999999999993e-06,
      "loss": 9.3743,
      "step": 60
    },
    {
      "epoch": 0.00020502711849761985,
      "grad_norm": 29.089111328125,
      "learning_rate": 4.079999999999999e-06,
      "loss": 9.3628,
      "step": 70
    },
    {
      "epoch": 0.0002343167068544227,
      "grad_norm": 45.67530822753906,
      "learning_rate": 4.679999999999999e-06,
      "loss": 9.359,
      "step": 80
    },
    {
      "epoch": 0.0002636062952112255,
      "grad_norm": 33.06043243408203,
      "learning_rate": 5.28e-06,
      "loss": 9.3381,
      "step": 90
    },
    {
      "epoch": 0.00029289588356802836,
      "grad_norm": 32.19873809814453,
      "learning_rate": 5.88e-06,
      "loss": 9.3304,
      "step": 100
    },
    {
      "epoch": 0.0003221854719248312,
      "grad_norm": 39.30705261230469,
      "learning_rate": 6.48e-06,
      "loss": 9.3144,
      "step": 110
    },
    {
      "epoch": 0.00035147506028163403,
      "grad_norm": 42.05266189575195,
      "learning_rate": 7.079999999999999e-06,
      "loss": 9.3104,
      "step": 120
    },
    {
      "epoch": 0.00038076464863843687,
      "grad_norm": 33.91127014160156,
      "learning_rate": 7.68e-06,
      "loss": 9.3218,
      "step": 130
    },
    {
      "epoch": 0.0004100542369952397,
      "grad_norm": 31.721614837646484,
      "learning_rate": 8.279999999999999e-06,
      "loss": 9.3045,
      "step": 140
    },
    {
      "epoch": 0.00043934382535204254,
      "grad_norm": 59.37827682495117,
      "learning_rate": 8.88e-06,
      "loss": 9.3054,
      "step": 150
    },
    {
      "epoch": 0.0004686334137088454,
      "grad_norm": 74.16336059570312,
      "learning_rate": 9.48e-06,
      "loss": 9.2952,
      "step": 160
    },
    {
      "epoch": 0.0004979230020656483,
      "grad_norm": 33.57463836669922,
      "learning_rate": 1.0079999999999998e-05,
      "loss": 9.2887,
      "step": 170
    },
    {
      "epoch": 0.000527212590422451,
      "grad_norm": 37.42033386230469,
      "learning_rate": 1.068e-05,
      "loss": 9.2839,
      "step": 180
    },
    {
      "epoch": 0.0005565021787792539,
      "grad_norm": 33.58783721923828,
      "learning_rate": 1.1279999999999999e-05,
      "loss": 9.2869,
      "step": 190
    },
    {
      "epoch": 0.0005857917671360567,
      "grad_norm": 33.92068862915039,
      "learning_rate": 1.188e-05,
      "loss": 9.2636,
      "step": 200
    },
    {
      "epoch": 0.0006150813554928596,
      "grad_norm": 36.4366455078125,
      "learning_rate": 1.2479999999999999e-05,
      "loss": 9.2653,
      "step": 210
    },
    {
      "epoch": 0.0006443709438496624,
      "grad_norm": 27.894250869750977,
      "learning_rate": 1.3079999999999998e-05,
      "loss": 9.2699,
      "step": 220
    },
    {
      "epoch": 0.0006736605322064653,
      "grad_norm": 39.57080078125,
      "learning_rate": 1.3559999999999997e-05,
      "loss": 9.2491,
      "step": 230
    },
    {
      "epoch": 0.0007029501205632681,
      "grad_norm": 18.53085708618164,
      "learning_rate": 1.4159999999999998e-05,
      "loss": 9.2552,
      "step": 240
    },
    {
      "epoch": 0.000732239708920071,
      "grad_norm": 41.72337341308594,
      "learning_rate": 1.476e-05,
      "loss": 9.2611,
      "step": 250
    },
    {
      "epoch": 0.0007615292972768737,
      "grad_norm": 21.73541831970215,
      "learning_rate": 1.536e-05,
      "loss": 9.2928,
      "step": 260
    },
    {
      "epoch": 0.0007908188856336766,
      "grad_norm": 59.771385192871094,
      "learning_rate": 1.5959999999999996e-05,
      "loss": 9.2558,
      "step": 270
    },
    {
      "epoch": 0.0008201084739904794,
      "grad_norm": 75.89784240722656,
      "learning_rate": 1.6559999999999997e-05,
      "loss": 9.2438,
      "step": 280
    },
    {
      "epoch": 0.0008493980623472823,
      "grad_norm": 33.123294830322266,
      "learning_rate": 1.716e-05,
      "loss": 9.278,
      "step": 290
    },
    {
      "epoch": 0.0008786876507040851,
      "grad_norm": 39.20044708251953,
      "learning_rate": 1.776e-05,
      "loss": 9.2508,
      "step": 300
    },
    {
      "epoch": 0.000907977239060888,
      "grad_norm": 10.648369789123535,
      "learning_rate": 1.8359999999999997e-05,
      "loss": 9.2503,
      "step": 310
    },
    {
      "epoch": 0.0009372668274176908,
      "grad_norm": 44.026634216308594,
      "learning_rate": 1.896e-05,
      "loss": 9.2699,
      "step": 320
    },
    {
      "epoch": 0.0009665564157744936,
      "grad_norm": 45.130611419677734,
      "learning_rate": 1.9559999999999996e-05,
      "loss": 9.2433,
      "step": 330
    },
    {
      "epoch": 0.0009958460041312965,
      "grad_norm": 30.56162452697754,
      "learning_rate": 2.0159999999999997e-05,
      "loss": 9.2355,
      "step": 340
    },
    {
      "epoch": 0.0010251355924880993,
      "grad_norm": 15.57412052154541,
      "learning_rate": 2.0759999999999998e-05,
      "loss": 9.2367,
      "step": 350
    },
    {
      "epoch": 0.001054425180844902,
      "grad_norm": 33.53938674926758,
      "learning_rate": 2.136e-05,
      "loss": 9.2414,
      "step": 360
    },
    {
      "epoch": 0.0010837147692017049,
      "grad_norm": 15.654319763183594,
      "learning_rate": 2.196e-05,
      "loss": 9.2358,
      "step": 370
    },
    {
      "epoch": 0.0011130043575585079,
      "grad_norm": 17.77244758605957,
      "learning_rate": 2.2559999999999997e-05,
      "loss": 9.224,
      "step": 380
    },
    {
      "epoch": 0.0011422939459153107,
      "grad_norm": 13.026928901672363,
      "learning_rate": 2.316e-05,
      "loss": 9.2303,
      "step": 390
    },
    {
      "epoch": 0.0011715835342721134,
      "grad_norm": 25.018850326538086,
      "learning_rate": 2.376e-05,
      "loss": 9.2103,
      "step": 400
    },
    {
      "epoch": 0.0012008731226289162,
      "grad_norm": 30.319482803344727,
      "learning_rate": 2.4359999999999997e-05,
      "loss": 9.2371,
      "step": 410
    },
    {
      "epoch": 0.0012301627109857192,
      "grad_norm": 14.935267448425293,
      "learning_rate": 2.4959999999999998e-05,
      "loss": 9.2569,
      "step": 420
    },
    {
      "epoch": 0.001259452299342522,
      "grad_norm": 8.77879524230957,
      "learning_rate": 2.5559999999999996e-05,
      "loss": 9.241,
      "step": 430
    },
    {
      "epoch": 0.0012887418876993248,
      "grad_norm": 44.00795364379883,
      "learning_rate": 2.6159999999999997e-05,
      "loss": 9.2009,
      "step": 440
    },
    {
      "epoch": 0.0013180314760561276,
      "grad_norm": 27.51123046875,
      "learning_rate": 2.6759999999999998e-05,
      "loss": 9.2257,
      "step": 450
    },
    {
      "epoch": 0.0013473210644129306,
      "grad_norm": 25.604936599731445,
      "learning_rate": 2.736e-05,
      "loss": 9.2245,
      "step": 460
    },
    {
      "epoch": 0.0013766106527697333,
      "grad_norm": 16.147348403930664,
      "learning_rate": 2.796e-05,
      "loss": 9.2356,
      "step": 470
    },
    {
      "epoch": 0.0014059002411265361,
      "grad_norm": 10.082588195800781,
      "learning_rate": 2.856e-05,
      "loss": 9.2074,
      "step": 480
    },
    {
      "epoch": 0.001435189829483339,
      "grad_norm": 7.7481889724731445,
      "learning_rate": 2.9159999999999995e-05,
      "loss": 9.2339,
      "step": 490
    },
    {
      "epoch": 0.001464479417840142,
      "grad_norm": 12.886085510253906,
      "learning_rate": 2.9759999999999996e-05,
      "loss": 9.2148,
      "step": 500
    },
    {
      "epoch": 0.0014937690061969447,
      "grad_norm": 20.852745056152344,
      "learning_rate": 3.0359999999999997e-05,
      "loss": 9.1892,
      "step": 510
    },
    {
      "epoch": 0.0015230585945537475,
      "grad_norm": 11.238962173461914,
      "learning_rate": 3.0959999999999995e-05,
      "loss": 9.2012,
      "step": 520
    },
    {
      "epoch": 0.0015523481829105503,
      "grad_norm": 10.45230484008789,
      "learning_rate": 3.1559999999999996e-05,
      "loss": 9.2047,
      "step": 530
    },
    {
      "epoch": 0.0015816377712673533,
      "grad_norm": 9.272976875305176,
      "learning_rate": 3.216e-05,
      "loss": 9.1891,
      "step": 540
    },
    {
      "epoch": 0.001610927359624156,
      "grad_norm": 13.807792663574219,
      "learning_rate": 3.276e-05,
      "loss": 9.2122,
      "step": 550
    },
    {
      "epoch": 0.0016402169479809588,
      "grad_norm": 12.749746322631836,
      "learning_rate": 3.335999999999999e-05,
      "loss": 9.2192,
      "step": 560
    },
    {
      "epoch": 0.0016695065363377616,
      "grad_norm": 16.324674606323242,
      "learning_rate": 3.395999999999999e-05,
      "loss": 9.2025,
      "step": 570
    },
    {
      "epoch": 0.0016987961246945646,
      "grad_norm": 12.50004768371582,
      "learning_rate": 3.4559999999999994e-05,
      "loss": 9.189,
      "step": 580
    },
    {
      "epoch": 0.0017280857130513674,
      "grad_norm": 16.172029495239258,
      "learning_rate": 3.5159999999999995e-05,
      "loss": 9.1991,
      "step": 590
    },
    {
      "epoch": 0.0017573753014081702,
      "grad_norm": 6.533432483673096,
      "learning_rate": 3.5759999999999996e-05,
      "loss": 9.1912,
      "step": 600
    },
    {
      "epoch": 0.001786664889764973,
      "grad_norm": 9.044073104858398,
      "learning_rate": 3.636e-05,
      "loss": 9.2153,
      "step": 610
    },
    {
      "epoch": 0.001815954478121776,
      "grad_norm": 8.341883659362793,
      "learning_rate": 3.696e-05,
      "loss": 9.1959,
      "step": 620
    },
    {
      "epoch": 0.0018452440664785787,
      "grad_norm": 9.400508880615234,
      "learning_rate": 3.756e-05,
      "loss": 9.1999,
      "step": 630
    },
    {
      "epoch": 0.0018745336548353815,
      "grad_norm": 7.31540060043335,
      "learning_rate": 3.816e-05,
      "loss": 9.188,
      "step": 640
    },
    {
      "epoch": 0.0019038232431921843,
      "grad_norm": 7.5716447830200195,
      "learning_rate": 3.876e-05,
      "loss": 9.2164,
      "step": 650
    },
    {
      "epoch": 0.0019331128315489873,
      "grad_norm": 20.86789894104004,
      "learning_rate": 3.936e-05,
      "loss": 9.1979,
      "step": 660
    },
    {
      "epoch": 0.00196240241990579,
      "grad_norm": 5.7517619132995605,
      "learning_rate": 3.9960000000000004e-05,
      "loss": 9.2087,
      "step": 670
    },
    {
      "epoch": 0.001991692008262593,
      "grad_norm": 7.843511581420898,
      "learning_rate": 4.055999999999999e-05,
      "loss": 9.2302,
      "step": 680
    },
    {
      "epoch": 0.0020209815966193956,
      "grad_norm": 7.3309221267700195,
      "learning_rate": 4.115999999999999e-05,
      "loss": 9.2107,
      "step": 690
    },
    {
      "epoch": 0.0020502711849761986,
      "grad_norm": 8.938128471374512,
      "learning_rate": 4.175999999999999e-05,
      "loss": 9.2085,
      "step": 700
    },
    {
      "epoch": 0.002079560773333001,
      "grad_norm": 6.703171253204346,
      "learning_rate": 4.2359999999999994e-05,
      "loss": 9.2239,
      "step": 710
    },
    {
      "epoch": 0.002108850361689804,
      "grad_norm": 5.233580589294434,
      "learning_rate": 4.2959999999999995e-05,
      "loss": 9.1488,
      "step": 720
    },
    {
      "epoch": 0.002138139950046607,
      "grad_norm": 5.606321334838867,
      "learning_rate": 4.3559999999999996e-05,
      "loss": 9.1963,
      "step": 730
    },
    {
      "epoch": 0.0021674295384034098,
      "grad_norm": 11.066495895385742,
      "learning_rate": 4.416e-05,
      "loss": 9.1978,
      "step": 740
    },
    {
      "epoch": 0.0021967191267602128,
      "grad_norm": 8.605512619018555,
      "learning_rate": 4.476e-05,
      "loss": 9.2056,
      "step": 750
    },
    {
      "epoch": 0.0022260087151170158,
      "grad_norm": 5.653399467468262,
      "learning_rate": 4.536e-05,
      "loss": 9.1998,
      "step": 760
    },
    {
      "epoch": 0.0022552983034738183,
      "grad_norm": 6.059122085571289,
      "learning_rate": 4.5959999999999994e-05,
      "loss": 9.1821,
      "step": 770
    },
    {
      "epoch": 0.0022845878918306213,
      "grad_norm": 5.728312969207764,
      "learning_rate": 4.6559999999999995e-05,
      "loss": 9.2025,
      "step": 780
    },
    {
      "epoch": 0.002313877480187424,
      "grad_norm": 6.319748401641846,
      "learning_rate": 4.7159999999999996e-05,
      "loss": 9.181,
      "step": 790
    },
    {
      "epoch": 0.002343167068544227,
      "grad_norm": 10.601261138916016,
      "learning_rate": 4.776e-05,
      "loss": 9.1806,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2087662798848000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}