{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003333333333333333,
      "grad_norm": 243.78553771972656,
      "learning_rate": 5.95e-06,
      "loss": 166.0732177734375,
      "original_ce_loss": 10.3789,
      "step": 10
    },
    {
      "epoch": 0.0006666666666666666,
      "grad_norm": 239.2476348876953,
      "learning_rate": 1.445e-05,
      "loss": 165.82977294921875,
      "original_ce_loss": 10.3637,
      "step": 20
    },
    {
      "epoch": 0.001,
      "grad_norm": 244.72525024414062,
      "learning_rate": 2.295e-05,
      "loss": 165.18355712890624,
      "original_ce_loss": 10.3233,
      "step": 30
    },
    {
      "epoch": 0.0013333333333333333,
      "grad_norm": 270.7417297363281,
      "learning_rate": 3.145e-05,
      "loss": 163.79927978515624,
      "original_ce_loss": 10.2368,
      "step": 40
    },
    {
      "epoch": 0.0016666666666666668,
      "grad_norm": 326.618408203125,
      "learning_rate": 3.9949999999999995e-05,
      "loss": 160.3599365234375,
      "original_ce_loss": 10.0218,
      "step": 50
    },
    {
      "epoch": 0.002,
      "grad_norm": 166.10595703125,
      "learning_rate": 4.845e-05,
      "loss": 151.0793212890625,
      "original_ce_loss": 9.4418,
      "step": 60
    },
    {
      "epoch": 0.0023333333333333335,
      "grad_norm": 54.51128387451172,
      "learning_rate": 5.695e-05,
      "loss": 142.18406982421874,
      "original_ce_loss": 8.8858,
      "step": 70
    },
    {
      "epoch": 0.0026666666666666666,
      "grad_norm": 45.69681930541992,
      "learning_rate": 6.544999999999999e-05,
      "loss": 135.513818359375,
      "original_ce_loss": 8.4689,
      "step": 80
    },
    {
      "epoch": 0.003,
      "grad_norm": 44.38578414916992,
      "learning_rate": 7.395e-05,
      "loss": 129.2341796875,
      "original_ce_loss": 8.0765,
      "step": 90
    },
    {
      "epoch": 0.0033333333333333335,
      "grad_norm": 36.00300979614258,
      "learning_rate": 8.245e-05,
      "loss": 123.0133544921875,
      "original_ce_loss": 7.6877,
      "step": 100
    },
    {
      "epoch": 0.0036666666666666666,
      "grad_norm": 32.789207458496094,
      "learning_rate": 9.094999999999999e-05,
      "loss": 117.155908203125,
      "original_ce_loss": 7.3216,
      "step": 110
    },
    {
      "epoch": 0.004,
      "grad_norm": 26.692514419555664,
      "learning_rate": 9.86e-05,
      "loss": 112.15670166015624,
      "original_ce_loss": 7.0091,
      "step": 120
    },
    {
      "epoch": 0.004333333333333333,
      "grad_norm": 20.985740661621094,
      "learning_rate": 0.0001071,
      "loss": 108.44638671875,
      "original_ce_loss": 6.7772,
      "step": 130
    },
    {
      "epoch": 0.004666666666666667,
      "grad_norm": NaN,
      "learning_rate": 0.00011475,
      "loss": 105.64476318359375,
      "original_ce_loss": 6.6021,
      "step": 140
    },
    {
      "epoch": 0.005,
      "grad_norm": 47.759765625,
      "learning_rate": 0.000119,
      "loss": 104.857763671875,
      "original_ce_loss": 6.5529,
      "step": 150
    },
    {
      "epoch": 0.005333333333333333,
      "grad_norm": 164.30889892578125,
      "learning_rate": 0.00012749999999999998,
      "loss": 103.3579833984375,
      "original_ce_loss": 6.4592,
      "step": 160
    },
    {
      "epoch": 0.005666666666666667,
      "grad_norm": 11.574602127075195,
      "learning_rate": 0.000136,
      "loss": 103.28526611328125,
      "original_ce_loss": 6.4547,
      "step": 170
    },
    {
      "epoch": 0.006,
      "grad_norm": 13.660222053527832,
      "learning_rate": 0.00014450000000000002,
      "loss": 103.16549072265624,
      "original_ce_loss": 6.4472,
      "step": 180
    },
    {
      "epoch": 0.006333333333333333,
      "grad_norm": 15.656424522399902,
      "learning_rate": 0.00015299999999999998,
      "loss": 102.62147216796875,
      "original_ce_loss": 6.4132,
      "step": 190
    },
    {
      "epoch": 0.006666666666666667,
      "grad_norm": 18.646780014038086,
      "learning_rate": 0.0001615,
      "loss": 101.59368896484375,
      "original_ce_loss": 6.3489,
      "step": 200
    },
    {
      "epoch": 0.007,
      "grad_norm": 39.721866607666016,
      "learning_rate": 0.00017,
      "loss": 100.74405517578126,
      "original_ce_loss": 6.2958,
      "step": 210
    },
    {
      "epoch": 0.007333333333333333,
      "grad_norm": 16.912254333496094,
      "learning_rate": 0.00017849999999999997,
      "loss": 99.42055053710938,
      "original_ce_loss": 6.2131,
      "step": 220
    },
    {
      "epoch": 0.007666666666666666,
      "grad_norm": 17.74278450012207,
      "learning_rate": 0.000187,
      "loss": 97.92646484375,
      "original_ce_loss": 6.1197,
      "step": 230
    },
    {
      "epoch": 0.008,
      "grad_norm": 18.32769775390625,
      "learning_rate": 0.0001955,
      "loss": 96.8761962890625,
      "original_ce_loss": 6.0541,
      "step": 240
    },
    {
      "epoch": 0.008333333333333333,
      "grad_norm": 16.8792781829834,
      "learning_rate": 0.00020399999999999997,
      "loss": 95.25513305664063,
      "original_ce_loss": 5.9528,
      "step": 250
    },
    {
      "epoch": 0.008666666666666666,
      "grad_norm": 12.205955505371094,
      "learning_rate": 0.0002125,
      "loss": 93.572900390625,
      "original_ce_loss": 5.8476,
      "step": 260
    },
    {
      "epoch": 0.009,
      "grad_norm": 13.931303024291992,
      "learning_rate": 0.000221,
      "loss": 91.66510009765625,
      "original_ce_loss": 5.7284,
      "step": 270
    },
    {
      "epoch": 0.009333333333333334,
      "grad_norm": 26.242258071899414,
      "learning_rate": 0.0002295,
      "loss": 90.45693969726562,
      "original_ce_loss": 5.6529,
      "step": 280
    },
    {
      "epoch": 0.009666666666666667,
      "grad_norm": 16.811609268188477,
      "learning_rate": 0.000238,
      "loss": 91.2010009765625,
      "original_ce_loss": 5.6994,
      "step": 290
    },
    {
      "epoch": 0.01,
      "grad_norm": 25.731582641601562,
      "learning_rate": 0.00024565,
      "loss": 97.92516479492187,
      "original_ce_loss": 6.1197,
      "step": 300
    },
    {
      "epoch": 0.010333333333333333,
      "grad_norm": 36.38114547729492,
      "learning_rate": 0.00025414999999999997,
      "loss": 98.45838623046875,
      "original_ce_loss": 6.153,
      "step": 310
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": NaN,
      "learning_rate": 0.00026179999999999997,
      "loss": 95.69706420898437,
      "original_ce_loss": 5.9804,
      "step": 320
    },
    {
      "epoch": 0.011,
      "grad_norm": 51.799739837646484,
      "learning_rate": 0.00026944999999999996,
      "loss": 91.98704223632812,
      "original_ce_loss": 5.7485,
      "step": 330
    },
    {
      "epoch": 0.011333333333333334,
      "grad_norm": 22.107471466064453,
      "learning_rate": 0.00027795,
      "loss": 85.44754028320312,
      "original_ce_loss": 5.3398,
      "step": 340
    },
    {
      "epoch": 0.011666666666666667,
      "grad_norm": 30.49631118774414,
      "learning_rate": 0.00028645,
      "loss": 82.21802978515625,
      "original_ce_loss": 5.138,
      "step": 350
    },
    {
      "epoch": 0.012,
      "grad_norm": 46.481483459472656,
      "learning_rate": 0.00029495,
      "loss": 81.45587768554688,
      "original_ce_loss": 5.0904,
      "step": 360
    },
    {
      "epoch": 0.012333333333333333,
      "grad_norm": 35.435367584228516,
      "learning_rate": 0.00030345,
      "loss": 80.58915405273437,
      "original_ce_loss": 5.0362,
      "step": 370
    },
    {
      "epoch": 0.012666666666666666,
      "grad_norm": 23.500009536743164,
      "learning_rate": 0.00031109999999999997,
      "loss": 79.21079711914062,
      "original_ce_loss": 4.95,
      "step": 380
    },
    {
      "epoch": 0.013,
      "grad_norm": 36.313453674316406,
      "learning_rate": 0.00031959999999999996,
      "loss": 77.30345458984375,
      "original_ce_loss": 4.8308,
      "step": 390
    },
    {
      "epoch": 0.013333333333333334,
      "grad_norm": 22.148427963256836,
      "learning_rate": 0.0003281,
      "loss": 75.77711181640625,
      "original_ce_loss": 4.7354,
      "step": 400
    },
    {
      "epoch": 0.013666666666666667,
      "grad_norm": 25.187255859375,
      "learning_rate": 0.0003366,
      "loss": 73.7842041015625,
      "original_ce_loss": 4.6109,
      "step": 410
    },
    {
      "epoch": 0.014,
      "grad_norm": 36.26912307739258,
      "learning_rate": 0.0003451,
      "loss": 71.966650390625,
      "original_ce_loss": 4.4973,
      "step": 420
    },
    {
      "epoch": 0.014333333333333333,
      "grad_norm": 43.76127624511719,
      "learning_rate": 0.0003536,
      "loss": 70.83294677734375,
      "original_ce_loss": 4.4264,
      "step": 430
    },
    {
      "epoch": 0.014666666666666666,
      "grad_norm": 26.379560470581055,
      "learning_rate": 0.00036209999999999997,
      "loss": 69.33712158203124,
      "original_ce_loss": 4.333,
      "step": 440
    },
    {
      "epoch": 0.015,
      "grad_norm": 34.02827453613281,
      "learning_rate": 0.00037059999999999996,
      "loss": 67.307373046875,
      "original_ce_loss": 4.2061,
      "step": 450
    },
    {
      "epoch": 0.015333333333333332,
      "grad_norm": 86.85484313964844,
      "learning_rate": 0.0003791,
      "loss": 65.93311767578125,
      "original_ce_loss": 4.1202,
      "step": 460
    },
    {
      "epoch": 0.015666666666666666,
      "grad_norm": 39.64079666137695,
      "learning_rate": 0.0003876,
      "loss": 64.83297729492188,
      "original_ce_loss": 4.0515,
      "step": 470
    },
    {
      "epoch": 0.016,
      "grad_norm": 27.540979385375977,
      "learning_rate": 0.0003961,
      "loss": 63.43541259765625,
      "original_ce_loss": 3.9641,
      "step": 480
    },
    {
      "epoch": 0.01633333333333333,
      "grad_norm": 66.87540435791016,
      "learning_rate": 0.00040459999999999997,
      "loss": 62.5385986328125,
      "original_ce_loss": 3.9081,
      "step": 490
    },
    {
      "epoch": 0.016666666666666666,
      "grad_norm": 43.895957946777344,
      "learning_rate": 0.00041309999999999996,
      "loss": 61.425079345703125,
      "original_ce_loss": 3.8385,
      "step": 500
    },
    {
      "epoch": 0.017,
      "grad_norm": 29.485631942749023,
      "learning_rate": 0.00042159999999999995,
      "loss": 60.54182739257813,
      "original_ce_loss": 3.7833,
      "step": 510
    },
    {
      "epoch": 0.017333333333333333,
      "grad_norm": 39.4123649597168,
      "learning_rate": 0.0004249999566202406,
      "loss": 59.02940673828125,
      "original_ce_loss": 3.6887,
      "step": 520
    },
    {
      "epoch": 0.017666666666666667,
      "grad_norm": 29.954763412475586,
      "learning_rate": 0.0004249996915217756,
      "loss": 58.09852294921875,
      "original_ce_loss": 3.6306,
      "step": 530
    },
    {
      "epoch": 0.018,
      "grad_norm": 23.342824935913086,
      "learning_rate": 0.00042499918542501206,
      "loss": 57.1560546875,
      "original_ce_loss": 3.5717,
      "step": 540
    },
    {
      "epoch": 0.018333333333333333,
      "grad_norm": 28.458494186401367,
      "learning_rate": 0.00042499843833052406,
      "loss": 56.211798095703124,
      "original_ce_loss": 3.5127,
      "step": 550
    },
    {
      "epoch": 0.018666666666666668,
      "grad_norm": 22.47995948791504,
      "learning_rate": 0.0004249974502391588,
      "loss": 55.34743041992188,
      "original_ce_loss": 3.4586,
      "step": 560
    },
    {
      "epoch": 0.019,
      "grad_norm": 25.036964416503906,
      "learning_rate": 0.00042499622115203697,
      "loss": 54.5650390625,
      "original_ce_loss": 3.4097,
      "step": 570
    },
    {
      "epoch": 0.019333333333333334,
      "grad_norm": 19.473806381225586,
      "learning_rate": 0.0004249947510705524,
      "loss": 54.05086059570313,
      "original_ce_loss": 3.3776,
      "step": 580
    },
    {
      "epoch": 0.019666666666666666,
      "grad_norm": 31.730932235717773,
      "learning_rate": 0.0004249930399963724,
      "loss": 53.475189208984375,
      "original_ce_loss": 3.3416,
      "step": 590
    },
    {
      "epoch": 0.02,
      "grad_norm": 161.93760681152344,
      "learning_rate": 0.0004249910879314376,
      "loss": 52.975347900390624,
      "original_ce_loss": 3.3104,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 30000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.42118754533376e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}