{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005,
      "grad_norm": 37.0,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.5359,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 45.5,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4797,
      "step": 20
    },
    {
      "epoch": 0.015,
      "grad_norm": 21.625,
      "learning_rate": 3e-06,
      "loss": 1.3793,
      "step": 30
    },
    {
      "epoch": 0.02,
      "grad_norm": 19.625,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.26,
      "step": 40
    },
    {
      "epoch": 0.025,
      "grad_norm": 12.375,
      "learning_rate": 5e-06,
      "loss": 1.2473,
      "step": 50
    },
    {
      "epoch": 0.03,
      "grad_norm": 9.75,
      "learning_rate": 6e-06,
      "loss": 1.132,
      "step": 60
    },
    {
      "epoch": 0.035,
      "grad_norm": 8.4375,
      "learning_rate": 7e-06,
      "loss": 1.1854,
      "step": 70
    },
    {
      "epoch": 0.04,
      "grad_norm": 9.25,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.1473,
      "step": 80
    },
    {
      "epoch": 0.045,
      "grad_norm": 5.5,
      "learning_rate": 9e-06,
      "loss": 1.1484,
      "step": 90
    },
    {
      "epoch": 0.05,
      "grad_norm": 4.71875,
      "learning_rate": 1e-05,
      "loss": 1.1352,
      "step": 100
    },
    {
      "epoch": 0.055,
      "grad_norm": 5.6875,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.0916,
      "step": 110
    },
    {
      "epoch": 0.06,
      "grad_norm": 4.90625,
      "learning_rate": 1.2e-05,
      "loss": 1.0473,
      "step": 120
    },
    {
      "epoch": 0.065,
      "grad_norm": 5.09375,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.0576,
      "step": 130
    },
    {
      "epoch": 0.07,
      "grad_norm": 5.6875,
      "learning_rate": 1.4e-05,
      "loss": 1.0014,
      "step": 140
    },
    {
      "epoch": 0.075,
      "grad_norm": 5.4375,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.015,
      "step": 150
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.0625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9674,
      "step": 160
    },
    {
      "epoch": 0.085,
      "grad_norm": 5.125,
      "learning_rate": 1.7e-05,
      "loss": 0.9754,
      "step": 170
    },
    {
      "epoch": 0.09,
      "grad_norm": 4.09375,
      "learning_rate": 1.8e-05,
      "loss": 0.9309,
      "step": 180
    },
    {
      "epoch": 0.095,
      "grad_norm": 4.875,
      "learning_rate": 1.9e-05,
      "loss": 0.9158,
      "step": 190
    },
    {
      "epoch": 0.1,
      "grad_norm": 117.5,
      "learning_rate": 2e-05,
      "loss": 0.9994,
      "step": 200
    },
    {
      "epoch": 0.105,
      "grad_norm": 5.34375,
      "learning_rate": 1.9998476951563914e-05,
      "loss": 1.0623,
      "step": 210
    },
    {
      "epoch": 0.11,
      "grad_norm": 19.0,
      "learning_rate": 1.999390827019096e-05,
      "loss": 1.007,
      "step": 220
    },
    {
      "epoch": 0.115,
      "grad_norm": 5.21875,
      "learning_rate": 1.9986295347545738e-05,
      "loss": 0.867,
      "step": 230
    },
    {
      "epoch": 0.12,
      "grad_norm": 3.640625,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 0.852,
      "step": 240
    },
    {
      "epoch": 0.125,
      "grad_norm": 4.40625,
      "learning_rate": 1.9961946980917457e-05,
      "loss": 0.8018,
      "step": 250
    },
    {
      "epoch": 0.13,
      "grad_norm": 5.125,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 0.9186,
      "step": 260
    },
    {
      "epoch": 0.135,
      "grad_norm": 4.875,
      "learning_rate": 1.9925461516413224e-05,
      "loss": 0.804,
      "step": 270
    },
    {
      "epoch": 0.14,
      "grad_norm": 3.71875,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 0.817,
      "step": 280
    },
    {
      "epoch": 0.145,
      "grad_norm": 4.125,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.7372,
      "step": 290
    },
    {
      "epoch": 0.15,
      "grad_norm": 3.5,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.7237,
      "step": 300
    },
    {
      "epoch": 0.155,
      "grad_norm": 3.375,
      "learning_rate": 1.9816271834476642e-05,
      "loss": 0.6707,
      "step": 310
    },
    {
      "epoch": 0.16,
      "grad_norm": 4.21875,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.7664,
      "step": 320
    },
    {
      "epoch": 0.165,
      "grad_norm": 3.640625,
      "learning_rate": 1.9743700647852356e-05,
      "loss": 0.6838,
      "step": 330
    },
    {
      "epoch": 0.17,
      "grad_norm": 4.25,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 0.7225,
      "step": 340
    },
    {
      "epoch": 0.175,
      "grad_norm": 3.625,
      "learning_rate": 1.9659258262890683e-05,
      "loss": 0.6754,
      "step": 350
    },
    {
      "epoch": 0.18,
      "grad_norm": 3.546875,
      "learning_rate": 1.961261695938319e-05,
      "loss": 0.6344,
      "step": 360
    },
    {
      "epoch": 0.185,
      "grad_norm": 3.546875,
      "learning_rate": 1.9563047559630356e-05,
      "loss": 0.6728,
      "step": 370
    },
    {
      "epoch": 0.19,
      "grad_norm": 4.34375,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.7283,
      "step": 380
    },
    {
      "epoch": 0.195,
      "grad_norm": 3.671875,
      "learning_rate": 1.945518575599317e-05,
      "loss": 0.666,
      "step": 390
    },
    {
      "epoch": 0.2,
      "grad_norm": 4.4375,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.6756,
      "step": 400
    },
    {
      "epoch": 0.205,
      "grad_norm": 3.71875,
      "learning_rate": 1.9335804264972018e-05,
      "loss": 0.6558,
      "step": 410
    },
    {
      "epoch": 0.21,
      "grad_norm": 3.234375,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 0.6243,
      "step": 420
    },
    {
      "epoch": 0.215,
      "grad_norm": 3.90625,
      "learning_rate": 1.9205048534524405e-05,
      "loss": 0.6519,
      "step": 430
    },
    {
      "epoch": 0.22,
      "grad_norm": 3.375,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.626,
      "step": 440
    },
    {
      "epoch": 0.225,
      "grad_norm": 3.78125,
      "learning_rate": 1.9063077870366504e-05,
      "loss": 0.6592,
      "step": 450
    },
    {
      "epoch": 0.23,
      "grad_norm": 3.75,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 0.5869,
      "step": 460
    },
    {
      "epoch": 0.235,
      "grad_norm": 4.25,
      "learning_rate": 1.891006524188368e-05,
      "loss": 0.6157,
      "step": 470
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.78125,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 0.5537,
      "step": 480
    },
    {
      "epoch": 0.245,
      "grad_norm": 2.734375,
      "learning_rate": 1.874619707139396e-05,
      "loss": 0.631,
      "step": 490
    },
    {
      "epoch": 0.25,
      "grad_norm": 3.875,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.5853,
      "step": 500
    },
    {
      "epoch": 0.255,
      "grad_norm": 2.46875,
      "learning_rate": 1.8571673007021124e-05,
      "loss": 0.5669,
      "step": 510
    },
    {
      "epoch": 0.26,
      "grad_norm": 4.75,
      "learning_rate": 1.848048096156426e-05,
      "loss": 0.5251,
      "step": 520
    },
    {
      "epoch": 0.265,
      "grad_norm": 3.40625,
      "learning_rate": 1.8386705679454243e-05,
      "loss": 0.5188,
      "step": 530
    },
    {
      "epoch": 0.27,
      "grad_norm": 3.609375,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 0.5289,
      "step": 540
    },
    {
      "epoch": 0.275,
      "grad_norm": 2.953125,
      "learning_rate": 1.819152044288992e-05,
      "loss": 0.628,
      "step": 550
    },
    {
      "epoch": 0.28,
      "grad_norm": 2.484375,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.5611,
      "step": 560
    },
    {
      "epoch": 0.285,
      "grad_norm": 3.125,
      "learning_rate": 1.798635510047293e-05,
      "loss": 0.5497,
      "step": 570
    },
    {
      "epoch": 0.29,
      "grad_norm": 3.21875,
      "learning_rate": 1.788010753606722e-05,
      "loss": 0.5717,
      "step": 580
    },
    {
      "epoch": 0.295,
      "grad_norm": 3.15625,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.5497,
      "step": 590
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.25,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.543,
      "step": 600
    },
    {
      "epoch": 0.305,
      "grad_norm": 2.671875,
      "learning_rate": 1.7547095802227723e-05,
      "loss": 0.5547,
      "step": 610
    },
    {
      "epoch": 0.31,
      "grad_norm": 2.671875,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 0.5395,
      "step": 620
    },
    {
      "epoch": 0.315,
      "grad_norm": 3.390625,
      "learning_rate": 1.7313537016191706e-05,
      "loss": 0.5913,
      "step": 630
    },
    {
      "epoch": 0.32,
      "grad_norm": 2.640625,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 0.5385,
      "step": 640
    },
    {
      "epoch": 0.325,
      "grad_norm": 3.5,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.5522,
      "step": 650
    },
    {
      "epoch": 0.33,
      "grad_norm": 2.96875,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 0.5241,
      "step": 660
    },
    {
      "epoch": 0.335,
      "grad_norm": 3.40625,
      "learning_rate": 1.6819983600624986e-05,
      "loss": 0.4942,
      "step": 670
    },
    {
      "epoch": 0.34,
      "grad_norm": 2.765625,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.484,
      "step": 680
    },
    {
      "epoch": 0.345,
      "grad_norm": 2.671875,
      "learning_rate": 1.6560590289905074e-05,
      "loss": 0.463,
      "step": 690
    },
    {
      "epoch": 0.35,
      "grad_norm": 3.34375,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 0.4791,
      "step": 700
    },
    {
      "epoch": 0.355,
      "grad_norm": 3.1875,
      "learning_rate": 1.6293203910498375e-05,
      "loss": 0.4977,
      "step": 710
    },
    {
      "epoch": 0.36,
      "grad_norm": 2.421875,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 0.5117,
      "step": 720
    },
    {
      "epoch": 0.365,
      "grad_norm": 3.46875,
      "learning_rate": 1.6018150231520486e-05,
      "loss": 0.5095,
      "step": 730
    },
    {
      "epoch": 0.37,
      "grad_norm": 2.53125,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.4845,
      "step": 740
    },
    {
      "epoch": 0.375,
      "grad_norm": 2.75,
      "learning_rate": 1.573576436351046e-05,
      "loss": 0.4809,
      "step": 750
    },
    {
      "epoch": 0.38,
      "grad_norm": 3.453125,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 0.4588,
      "step": 760
    },
    {
      "epoch": 0.385,
      "grad_norm": 2.9375,
      "learning_rate": 1.5446390350150272e-05,
      "loss": 0.5021,
      "step": 770
    },
    {
      "epoch": 0.39,
      "grad_norm": 2.421875,
      "learning_rate": 1.529919264233205e-05,
      "loss": 0.5011,
      "step": 780
    },
    {
      "epoch": 0.395,
      "grad_norm": 2.59375,
      "learning_rate": 1.5150380749100545e-05,
      "loss": 0.4935,
      "step": 790
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.4375,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.5083,
      "step": 800
    },
    {
      "epoch": 0.405,
      "grad_norm": 2.78125,
      "learning_rate": 1.4848096202463373e-05,
      "loss": 0.4488,
      "step": 810
    },
    {
      "epoch": 0.41,
      "grad_norm": 2.625,
      "learning_rate": 1.469471562785891e-05,
      "loss": 0.4308,
      "step": 820
    },
    {
      "epoch": 0.415,
      "grad_norm": 3.453125,
      "learning_rate": 1.4539904997395468e-05,
      "loss": 0.443,
      "step": 830
    },
    {
      "epoch": 0.42,
      "grad_norm": 3.15625,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 0.4832,
      "step": 840
    },
    {
      "epoch": 0.425,
      "grad_norm": 2.625,
      "learning_rate": 1.4226182617406996e-05,
      "loss": 0.4688,
      "step": 850
    },
    {
      "epoch": 0.43,
      "grad_norm": 3.1875,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 0.4534,
      "step": 860
    },
    {
      "epoch": 0.435,
      "grad_norm": 2.921875,
      "learning_rate": 1.3907311284892737e-05,
      "loss": 0.422,
      "step": 870
    },
    {
      "epoch": 0.44,
      "grad_norm": 3.296875,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 0.4677,
      "step": 880
    },
    {
      "epoch": 0.445,
      "grad_norm": 3.1875,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.4743,
      "step": 890
    },
    {
      "epoch": 0.45,
      "grad_norm": 2.859375,
      "learning_rate": 1.342020143325669e-05,
      "loss": 0.4639,
      "step": 900
    },
    {
      "epoch": 0.455,
      "grad_norm": 4.28125,
      "learning_rate": 1.3255681544571568e-05,
      "loss": 0.4374,
      "step": 910
    },
    {
      "epoch": 0.46,
      "grad_norm": 2.546875,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.4294,
      "step": 920
    },
    {
      "epoch": 0.465,
      "grad_norm": 2.890625,
      "learning_rate": 1.2923717047227368e-05,
      "loss": 0.4604,
      "step": 930
    },
    {
      "epoch": 0.47,
      "grad_norm": 2.90625,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 0.4341,
      "step": 940
    },
    {
      "epoch": 0.475,
      "grad_norm": 3.46875,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 0.4212,
      "step": 950
    },
    {
      "epoch": 0.48,
      "grad_norm": 3.109375,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 0.4391,
      "step": 960
    },
    {
      "epoch": 0.485,
      "grad_norm": 2.609375,
      "learning_rate": 1.2249510543438652e-05,
      "loss": 0.4442,
      "step": 970
    },
    {
      "epoch": 0.49,
      "grad_norm": 3.1875,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 0.4612,
      "step": 980
    },
    {
      "epoch": 0.495,
      "grad_norm": 3.375,
      "learning_rate": 1.190808995376545e-05,
      "loss": 0.4126,
      "step": 990
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.71875,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.4042,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.5664155394048e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}