{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9993764290168364,
  "eval_steps": 500,
  "global_step": 1202,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020785699438786116,
      "grad_norm": 2.734440803527832,
      "learning_rate": 5e-06,
      "loss": 3.9975,
      "step": 25
    },
    {
      "epoch": 0.04157139887757223,
      "grad_norm": 2.1083433628082275,
      "learning_rate": 1e-05,
      "loss": 3.9298,
      "step": 50
    },
    {
      "epoch": 0.06235709831635834,
      "grad_norm": 1.990794062614441,
      "learning_rate": 9.782986111111113e-06,
      "loss": 3.7079,
      "step": 75
    },
    {
      "epoch": 0.08314279775514447,
      "grad_norm": 1.1073641777038574,
      "learning_rate": 9.565972222222222e-06,
      "loss": 3.4886,
      "step": 100
    },
    {
      "epoch": 0.10392849719393057,
      "grad_norm": 0.7308239340782166,
      "learning_rate": 9.348958333333335e-06,
      "loss": 3.286,
      "step": 125
    },
    {
      "epoch": 0.12471419663271668,
      "grad_norm": 0.6134746670722961,
      "learning_rate": 9.131944444444445e-06,
      "loss": 3.1505,
      "step": 150
    },
    {
      "epoch": 0.1454998960715028,
      "grad_norm": 0.5232350826263428,
      "learning_rate": 8.914930555555556e-06,
      "loss": 3.099,
      "step": 175
    },
    {
      "epoch": 0.16628559551028893,
      "grad_norm": 0.5310938954353333,
      "learning_rate": 8.697916666666667e-06,
      "loss": 3.0112,
      "step": 200
    },
    {
      "epoch": 0.18707129494907504,
      "grad_norm": 0.4157707095146179,
      "learning_rate": 8.48090277777778e-06,
      "loss": 2.8997,
      "step": 225
    },
    {
      "epoch": 0.20785699438786115,
      "grad_norm": 0.38247939944267273,
      "learning_rate": 8.263888888888888e-06,
      "loss": 2.8774,
      "step": 250
    },
    {
      "epoch": 0.22864269382664726,
      "grad_norm": 0.43697381019592285,
      "learning_rate": 8.046875e-06,
      "loss": 2.8397,
      "step": 275
    },
    {
      "epoch": 0.24942839326543337,
      "grad_norm": 0.43171486258506775,
      "learning_rate": 7.829861111111112e-06,
      "loss": 2.7897,
      "step": 300
    },
    {
      "epoch": 0.2702140927042195,
      "grad_norm": 0.35729026794433594,
      "learning_rate": 7.612847222222223e-06,
      "loss": 2.7498,
      "step": 325
    },
    {
      "epoch": 0.2909997921430056,
      "grad_norm": 0.4240734279155731,
      "learning_rate": 7.395833333333335e-06,
      "loss": 2.6836,
      "step": 350
    },
    {
      "epoch": 0.31178549158179175,
      "grad_norm": 0.3893283009529114,
      "learning_rate": 7.1788194444444445e-06,
      "loss": 2.7183,
      "step": 375
    },
    {
      "epoch": 0.33257119102057786,
      "grad_norm": 0.3917147219181061,
      "learning_rate": 6.961805555555556e-06,
      "loss": 2.6586,
      "step": 400
    },
    {
      "epoch": 0.35335689045936397,
      "grad_norm": 0.44135338068008423,
      "learning_rate": 6.744791666666667e-06,
      "loss": 2.653,
      "step": 425
    },
    {
      "epoch": 0.3741425898981501,
      "grad_norm": 0.3476935625076294,
      "learning_rate": 6.5277777777777784e-06,
      "loss": 2.5654,
      "step": 450
    },
    {
      "epoch": 0.3949282893369362,
      "grad_norm": 0.24660900235176086,
      "learning_rate": 6.310763888888889e-06,
      "loss": 2.5625,
      "step": 475
    },
    {
      "epoch": 0.4157139887757223,
      "grad_norm": 0.2546718716621399,
      "learning_rate": 6.093750000000001e-06,
      "loss": 2.5691,
      "step": 500
    },
    {
      "epoch": 0.4364996882145084,
      "grad_norm": 0.24869012832641602,
      "learning_rate": 5.876736111111112e-06,
      "loss": 2.5861,
      "step": 525
    },
    {
      "epoch": 0.4572853876532945,
      "grad_norm": 0.2396017462015152,
      "learning_rate": 5.659722222222222e-06,
      "loss": 2.565,
      "step": 550
    },
    {
      "epoch": 0.4780710870920806,
      "grad_norm": 0.26274845004081726,
      "learning_rate": 5.442708333333334e-06,
      "loss": 2.5191,
      "step": 575
    },
    {
      "epoch": 0.49885678653086674,
      "grad_norm": 0.24700729548931122,
      "learning_rate": 5.2256944444444445e-06,
      "loss": 2.486,
      "step": 600
    },
    {
      "epoch": 0.5196424859696529,
      "grad_norm": 0.2400694340467453,
      "learning_rate": 5.008680555555556e-06,
      "loss": 2.4332,
      "step": 625
    },
    {
      "epoch": 0.540428185408439,
      "grad_norm": 0.23329533636569977,
      "learning_rate": 4.791666666666668e-06,
      "loss": 2.5027,
      "step": 650
    },
    {
      "epoch": 0.5612138848472251,
      "grad_norm": 0.2405698299407959,
      "learning_rate": 4.574652777777778e-06,
      "loss": 2.4649,
      "step": 675
    },
    {
      "epoch": 0.5819995842860112,
      "grad_norm": 0.2957931458950043,
      "learning_rate": 4.357638888888889e-06,
      "loss": 2.4246,
      "step": 700
    },
    {
      "epoch": 0.6027852837247973,
      "grad_norm": 0.2754002511501312,
      "learning_rate": 4.140625000000001e-06,
      "loss": 2.5025,
      "step": 725
    },
    {
      "epoch": 0.6235709831635835,
      "grad_norm": 0.2665573060512543,
      "learning_rate": 3.9236111111111114e-06,
      "loss": 2.4752,
      "step": 750
    },
    {
      "epoch": 0.6443566826023696,
      "grad_norm": 0.26163598895072937,
      "learning_rate": 3.7065972222222226e-06,
      "loss": 2.4401,
      "step": 775
    },
    {
      "epoch": 0.6651423820411557,
      "grad_norm": 0.25856491923332214,
      "learning_rate": 3.4895833333333333e-06,
      "loss": 2.4005,
      "step": 800
    },
    {
      "epoch": 0.6859280814799418,
      "grad_norm": 0.2826252579689026,
      "learning_rate": 3.2725694444444445e-06,
      "loss": 2.4668,
      "step": 825
    },
    {
      "epoch": 0.7067137809187279,
      "grad_norm": 0.23859556019306183,
      "learning_rate": 3.055555555555556e-06,
      "loss": 2.4815,
      "step": 850
    },
    {
      "epoch": 0.727499480357514,
      "grad_norm": 0.1961268186569214,
      "learning_rate": 2.838541666666667e-06,
      "loss": 2.4864,
      "step": 875
    },
    {
      "epoch": 0.7482851797963002,
      "grad_norm": 0.23380087316036224,
      "learning_rate": 2.621527777777778e-06,
      "loss": 2.445,
      "step": 900
    },
    {
      "epoch": 0.7690708792350862,
      "grad_norm": 0.181913822889328,
      "learning_rate": 2.404513888888889e-06,
      "loss": 2.4395,
      "step": 925
    },
    {
      "epoch": 0.7898565786738724,
      "grad_norm": 0.1909315139055252,
      "learning_rate": 2.1875000000000002e-06,
      "loss": 2.48,
      "step": 950
    },
    {
      "epoch": 0.8106422781126585,
      "grad_norm": 0.2427852749824524,
      "learning_rate": 1.9704861111111114e-06,
      "loss": 2.4229,
      "step": 975
    },
    {
      "epoch": 0.8314279775514446,
      "grad_norm": 0.2102808803319931,
      "learning_rate": 1.7534722222222223e-06,
      "loss": 2.4376,
      "step": 1000
    },
    {
      "epoch": 0.8522136769902308,
      "grad_norm": 0.2348516285419464,
      "learning_rate": 1.5364583333333335e-06,
      "loss": 2.4957,
      "step": 1025
    },
    {
      "epoch": 0.8729993764290168,
      "grad_norm": 0.24628274142742157,
      "learning_rate": 1.3194444444444446e-06,
      "loss": 2.4533,
      "step": 1050
    },
    {
      "epoch": 0.893785075867803,
      "grad_norm": 0.19529680907726288,
      "learning_rate": 1.1024305555555556e-06,
      "loss": 2.5214,
      "step": 1075
    },
    {
      "epoch": 0.914570775306589,
      "grad_norm": 0.21463939547538757,
      "learning_rate": 8.854166666666668e-07,
      "loss": 2.4413,
      "step": 1100
    },
    {
      "epoch": 0.9353564747453752,
      "grad_norm": 0.20561440289020538,
      "learning_rate": 6.684027777777778e-07,
      "loss": 2.42,
      "step": 1125
    },
    {
      "epoch": 0.9561421741841613,
      "grad_norm": 0.21936245262622833,
      "learning_rate": 4.5138888888888893e-07,
      "loss": 2.5077,
      "step": 1150
    },
    {
      "epoch": 0.9769278736229474,
      "grad_norm": 0.20694172382354736,
      "learning_rate": 2.3437500000000003e-07,
      "loss": 2.4735,
      "step": 1175
    },
    {
      "epoch": 0.9977135730617335,
      "grad_norm": 0.23707596957683563,
      "learning_rate": 1.736111111111111e-08,
      "loss": 2.4102,
      "step": 1200
    }
  ],
  "logging_steps": 25,
  "max_steps": 1202,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.61064189789568e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}