{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008,
      "grad_norm": 11.4375,
      "learning_rate": 0.0,
      "loss": 3.8345,
      "step": 1
    },
    {
      "epoch": 0.008,
      "grad_norm": 11.125,
      "learning_rate": 2.25e-06,
      "loss": 3.3934,
      "step": 10
    },
    {
      "epoch": 0.016,
      "grad_norm": 9.5,
      "learning_rate": 4.75e-06,
      "loss": 3.4002,
      "step": 20
    },
    {
      "epoch": 0.024,
      "grad_norm": 9.4375,
      "learning_rate": 7.25e-06,
      "loss": 3.4003,
      "step": 30
    },
    {
      "epoch": 0.032,
      "grad_norm": 11.1875,
      "learning_rate": 9.750000000000002e-06,
      "loss": 3.374,
      "step": 40
    },
    {
      "epoch": 0.04,
      "grad_norm": 10.625,
      "learning_rate": 1.225e-05,
      "loss": 3.4678,
      "step": 50
    },
    {
      "epoch": 0.048,
      "grad_norm": 11.0,
      "learning_rate": 1.475e-05,
      "loss": 3.4331,
      "step": 60
    },
    {
      "epoch": 0.056,
      "grad_norm": 10.6875,
      "learning_rate": 1.725e-05,
      "loss": 3.4722,
      "step": 70
    },
    {
      "epoch": 0.064,
      "grad_norm": 10.25,
      "learning_rate": 1.9750000000000002e-05,
      "loss": 3.2413,
      "step": 80
    },
    {
      "epoch": 0.072,
      "grad_norm": 10.8125,
      "learning_rate": 2.2250000000000002e-05,
      "loss": 3.1804,
      "step": 90
    },
    {
      "epoch": 0.08,
      "grad_norm": 10.1875,
      "learning_rate": 2.4750000000000002e-05,
      "loss": 3.1778,
      "step": 100
    },
    {
      "epoch": 0.088,
      "grad_norm": 8.4375,
      "learning_rate": 2.725e-05,
      "loss": 3.2479,
      "step": 110
    },
    {
      "epoch": 0.096,
      "grad_norm": 11.0,
      "learning_rate": 2.975e-05,
      "loss": 3.2259,
      "step": 120
    },
    {
      "epoch": 0.104,
      "grad_norm": 9.5625,
      "learning_rate": 3.2250000000000005e-05,
      "loss": 3.0845,
      "step": 130
    },
    {
      "epoch": 0.112,
      "grad_norm": 8.9375,
      "learning_rate": 3.475e-05,
      "loss": 3.1694,
      "step": 140
    },
    {
      "epoch": 0.12,
      "grad_norm": 8.4375,
      "learning_rate": 3.7250000000000004e-05,
      "loss": 3.1736,
      "step": 150
    },
    {
      "epoch": 0.128,
      "grad_norm": 9.5,
      "learning_rate": 3.9750000000000004e-05,
      "loss": 3.035,
      "step": 160
    },
    {
      "epoch": 0.136,
      "grad_norm": 9.8125,
      "learning_rate": 4.2250000000000004e-05,
      "loss": 3.1456,
      "step": 170
    },
    {
      "epoch": 0.144,
      "grad_norm": 9.25,
      "learning_rate": 4.4750000000000004e-05,
      "loss": 3.0917,
      "step": 180
    },
    {
      "epoch": 0.152,
      "grad_norm": 9.1875,
      "learning_rate": 4.7249999999999997e-05,
      "loss": 2.9948,
      "step": 190
    },
    {
      "epoch": 0.16,
      "grad_norm": 8.5625,
      "learning_rate": 4.975e-05,
      "loss": 3.0667,
      "step": 200
    },
    {
      "epoch": 0.168,
      "grad_norm": 8.125,
      "learning_rate": 4.957142857142857e-05,
      "loss": 2.9987,
      "step": 210
    },
    {
      "epoch": 0.176,
      "grad_norm": 7.875,
      "learning_rate": 4.90952380952381e-05,
      "loss": 2.9686,
      "step": 220
    },
    {
      "epoch": 0.184,
      "grad_norm": 9.1875,
      "learning_rate": 4.861904761904762e-05,
      "loss": 3.0708,
      "step": 230
    },
    {
      "epoch": 0.192,
      "grad_norm": 7.90625,
      "learning_rate": 4.8142857142857147e-05,
      "loss": 3.0676,
      "step": 240
    },
    {
      "epoch": 0.2,
      "grad_norm": 9.375,
      "learning_rate": 4.766666666666667e-05,
      "loss": 2.8833,
      "step": 250
    },
    {
      "epoch": 0.208,
      "grad_norm": 8.75,
      "learning_rate": 4.719047619047619e-05,
      "loss": 3.0558,
      "step": 260
    },
    {
      "epoch": 0.216,
      "grad_norm": 9.375,
      "learning_rate": 4.671428571428571e-05,
      "loss": 3.0003,
      "step": 270
    },
    {
      "epoch": 0.224,
      "grad_norm": 8.25,
      "learning_rate": 4.623809523809524e-05,
      "loss": 2.9514,
      "step": 280
    },
    {
      "epoch": 0.232,
      "grad_norm": 7.15625,
      "learning_rate": 4.5761904761904765e-05,
      "loss": 2.984,
      "step": 290
    },
    {
      "epoch": 0.24,
      "grad_norm": 8.625,
      "learning_rate": 4.528571428571429e-05,
      "loss": 3.0273,
      "step": 300
    },
    {
      "epoch": 0.248,
      "grad_norm": 7.75,
      "learning_rate": 4.480952380952381e-05,
      "loss": 2.9437,
      "step": 310
    },
    {
      "epoch": 0.256,
      "grad_norm": 9.1875,
      "learning_rate": 4.433333333333334e-05,
      "loss": 3.0913,
      "step": 320
    },
    {
      "epoch": 0.264,
      "grad_norm": 8.5625,
      "learning_rate": 4.385714285714286e-05,
      "loss": 2.9659,
      "step": 330
    },
    {
      "epoch": 0.272,
      "grad_norm": 8.0625,
      "learning_rate": 4.338095238095238e-05,
      "loss": 2.854,
      "step": 340
    },
    {
      "epoch": 0.28,
      "grad_norm": 7.0,
      "learning_rate": 4.290476190476191e-05,
      "loss": 2.8936,
      "step": 350
    },
    {
      "epoch": 0.288,
      "grad_norm": 8.125,
      "learning_rate": 4.242857142857143e-05,
      "loss": 2.9805,
      "step": 360
    },
    {
      "epoch": 0.296,
      "grad_norm": 8.5,
      "learning_rate": 4.1952380952380956e-05,
      "loss": 2.9814,
      "step": 370
    },
    {
      "epoch": 0.304,
      "grad_norm": 7.25,
      "learning_rate": 4.147619047619048e-05,
      "loss": 2.8731,
      "step": 380
    },
    {
      "epoch": 0.312,
      "grad_norm": 7.4375,
      "learning_rate": 4.1e-05,
      "loss": 2.8186,
      "step": 390
    },
    {
      "epoch": 0.32,
      "grad_norm": 8.0,
      "learning_rate": 4.052380952380952e-05,
      "loss": 3.048,
      "step": 400
    },
    {
      "epoch": 0.328,
      "grad_norm": 8.5,
      "learning_rate": 4.004761904761905e-05,
      "loss": 2.8923,
      "step": 410
    },
    {
      "epoch": 0.336,
      "grad_norm": 7.96875,
      "learning_rate": 3.9571428571428574e-05,
      "loss": 2.8443,
      "step": 420
    },
    {
      "epoch": 0.344,
      "grad_norm": 7.75,
      "learning_rate": 3.9095238095238096e-05,
      "loss": 3.0182,
      "step": 430
    },
    {
      "epoch": 0.352,
      "grad_norm": 7.625,
      "learning_rate": 3.861904761904762e-05,
      "loss": 2.849,
      "step": 440
    },
    {
      "epoch": 0.36,
      "grad_norm": 8.125,
      "learning_rate": 3.814285714285715e-05,
      "loss": 2.8413,
      "step": 450
    },
    {
      "epoch": 0.368,
      "grad_norm": 7.6875,
      "learning_rate": 3.766666666666667e-05,
      "loss": 2.9321,
      "step": 460
    },
    {
      "epoch": 0.376,
      "grad_norm": 7.15625,
      "learning_rate": 3.719047619047619e-05,
      "loss": 2.9628,
      "step": 470
    },
    {
      "epoch": 0.384,
      "grad_norm": 8.0625,
      "learning_rate": 3.671428571428572e-05,
      "loss": 3.0175,
      "step": 480
    },
    {
      "epoch": 0.392,
      "grad_norm": 7.375,
      "learning_rate": 3.6238095238095236e-05,
      "loss": 2.9446,
      "step": 490
    },
    {
      "epoch": 0.4,
      "grad_norm": 7.625,
      "learning_rate": 3.5761904761904765e-05,
      "loss": 2.8095,
      "step": 500
    },
    {
      "epoch": 0.408,
      "grad_norm": 9.25,
      "learning_rate": 3.528571428571429e-05,
      "loss": 2.9347,
      "step": 510
    },
    {
      "epoch": 0.416,
      "grad_norm": 7.875,
      "learning_rate": 3.480952380952381e-05,
      "loss": 2.7751,
      "step": 520
    },
    {
      "epoch": 0.424,
      "grad_norm": 8.5625,
      "learning_rate": 3.433333333333333e-05,
      "loss": 2.8434,
      "step": 530
    },
    {
      "epoch": 0.432,
      "grad_norm": 7.71875,
      "learning_rate": 3.385714285714286e-05,
      "loss": 2.869,
      "step": 540
    },
    {
      "epoch": 0.44,
      "grad_norm": 6.75,
      "learning_rate": 3.338095238095238e-05,
      "loss": 2.8466,
      "step": 550
    },
    {
      "epoch": 0.448,
      "grad_norm": 7.4375,
      "learning_rate": 3.2904761904761906e-05,
      "loss": 2.7286,
      "step": 560
    },
    {
      "epoch": 0.456,
      "grad_norm": 8.4375,
      "learning_rate": 3.242857142857143e-05,
      "loss": 2.9655,
      "step": 570
    },
    {
      "epoch": 0.464,
      "grad_norm": 7.3125,
      "learning_rate": 3.195238095238096e-05,
      "loss": 2.7955,
      "step": 580
    },
    {
      "epoch": 0.472,
      "grad_norm": 9.25,
      "learning_rate": 3.147619047619048e-05,
      "loss": 2.8469,
      "step": 590
    },
    {
      "epoch": 0.48,
      "grad_norm": 8.25,
      "learning_rate": 3.1e-05,
      "loss": 2.9423,
      "step": 600
    },
    {
      "epoch": 0.488,
      "grad_norm": 8.0625,
      "learning_rate": 3.0523809523809524e-05,
      "loss": 2.9848,
      "step": 610
    },
    {
      "epoch": 0.496,
      "grad_norm": 7.25,
      "learning_rate": 3.0047619047619046e-05,
      "loss": 2.8185,
      "step": 620
    },
    {
      "epoch": 0.504,
      "grad_norm": 8.3125,
      "learning_rate": 2.957142857142857e-05,
      "loss": 2.7036,
      "step": 630
    },
    {
      "epoch": 0.512,
      "grad_norm": 7.5625,
      "learning_rate": 2.9095238095238097e-05,
      "loss": 2.6809,
      "step": 640
    },
    {
      "epoch": 0.52,
      "grad_norm": 8.3125,
      "learning_rate": 2.8619047619047623e-05,
      "loss": 2.8011,
      "step": 650
    },
    {
      "epoch": 0.528,
      "grad_norm": 7.40625,
      "learning_rate": 2.814285714285714e-05,
      "loss": 2.7213,
      "step": 660
    },
    {
      "epoch": 0.536,
      "grad_norm": 7.15625,
      "learning_rate": 2.7666666666666667e-05,
      "loss": 2.8342,
      "step": 670
    },
    {
      "epoch": 0.544,
      "grad_norm": 6.625,
      "learning_rate": 2.7190476190476193e-05,
      "loss": 2.7829,
      "step": 680
    },
    {
      "epoch": 0.552,
      "grad_norm": 7.5625,
      "learning_rate": 2.6714285714285715e-05,
      "loss": 2.7949,
      "step": 690
    },
    {
      "epoch": 0.56,
      "grad_norm": 7.5625,
      "learning_rate": 2.623809523809524e-05,
      "loss": 2.7692,
      "step": 700
    },
    {
      "epoch": 0.568,
      "grad_norm": 8.25,
      "learning_rate": 2.5761904761904766e-05,
      "loss": 2.8251,
      "step": 710
    },
    {
      "epoch": 0.576,
      "grad_norm": 7.15625,
      "learning_rate": 2.5285714285714285e-05,
      "loss": 2.7056,
      "step": 720
    },
    {
      "epoch": 0.584,
      "grad_norm": 8.8125,
      "learning_rate": 2.480952380952381e-05,
      "loss": 2.8116,
      "step": 730
    },
    {
      "epoch": 0.592,
      "grad_norm": 8.125,
      "learning_rate": 2.4333333333333336e-05,
      "loss": 2.6844,
      "step": 740
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.5625,
      "learning_rate": 2.385714285714286e-05,
      "loss": 2.7657,
      "step": 750
    },
    {
      "epoch": 0.608,
      "grad_norm": 8.1875,
      "learning_rate": 2.338095238095238e-05,
      "loss": 2.8522,
      "step": 760
    },
    {
      "epoch": 0.616,
      "grad_norm": 7.71875,
      "learning_rate": 2.2904761904761906e-05,
      "loss": 2.8368,
      "step": 770
    },
    {
      "epoch": 0.624,
      "grad_norm": 7.71875,
      "learning_rate": 2.242857142857143e-05,
      "loss": 2.6978,
      "step": 780
    },
    {
      "epoch": 0.632,
      "grad_norm": 7.25,
      "learning_rate": 2.195238095238095e-05,
      "loss": 2.8267,
      "step": 790
    },
    {
      "epoch": 0.64,
      "grad_norm": 8.1875,
      "learning_rate": 2.1476190476190477e-05,
      "loss": 2.7188,
      "step": 800
    },
    {
      "epoch": 0.648,
      "grad_norm": 7.78125,
      "learning_rate": 2.1e-05,
      "loss": 2.8553,
      "step": 810
    },
    {
      "epoch": 0.656,
      "grad_norm": 7.25,
      "learning_rate": 2.0523809523809524e-05,
      "loss": 2.675,
      "step": 820
    },
    {
      "epoch": 0.664,
      "grad_norm": 6.9375,
      "learning_rate": 2.004761904761905e-05,
      "loss": 2.7901,
      "step": 830
    },
    {
      "epoch": 0.672,
      "grad_norm": 8.4375,
      "learning_rate": 1.9571428571428572e-05,
      "loss": 2.6719,
      "step": 840
    },
    {
      "epoch": 0.68,
      "grad_norm": 7.8125,
      "learning_rate": 1.9095238095238098e-05,
      "loss": 2.6436,
      "step": 850
    },
    {
      "epoch": 0.688,
      "grad_norm": 7.71875,
      "learning_rate": 1.861904761904762e-05,
      "loss": 2.8045,
      "step": 860
    },
    {
      "epoch": 0.696,
      "grad_norm": 8.75,
      "learning_rate": 1.8142857142857146e-05,
      "loss": 2.802,
      "step": 870
    },
    {
      "epoch": 0.704,
      "grad_norm": 8.0,
      "learning_rate": 1.7666666666666668e-05,
      "loss": 2.807,
      "step": 880
    },
    {
      "epoch": 0.712,
      "grad_norm": 8.75,
      "learning_rate": 1.719047619047619e-05,
      "loss": 2.7425,
      "step": 890
    },
    {
      "epoch": 0.72,
      "grad_norm": 7.40625,
      "learning_rate": 1.6714285714285716e-05,
      "loss": 2.8515,
      "step": 900
    },
    {
      "epoch": 0.728,
      "grad_norm": 7.0625,
      "learning_rate": 1.6238095238095238e-05,
      "loss": 2.7694,
      "step": 910
    },
    {
      "epoch": 0.736,
      "grad_norm": 8.0,
      "learning_rate": 1.5761904761904764e-05,
      "loss": 2.6311,
      "step": 920
    },
    {
      "epoch": 0.744,
      "grad_norm": 6.6875,
      "learning_rate": 1.5285714285714286e-05,
      "loss": 2.6884,
      "step": 930
    },
    {
      "epoch": 0.752,
      "grad_norm": 6.9375,
      "learning_rate": 1.480952380952381e-05,
      "loss": 2.8331,
      "step": 940
    },
    {
      "epoch": 0.76,
      "grad_norm": 7.75,
      "learning_rate": 1.4333333333333334e-05,
      "loss": 2.7617,
      "step": 950
    },
    {
      "epoch": 0.768,
      "grad_norm": 7.1875,
      "learning_rate": 1.3857142857142858e-05,
      "loss": 2.6287,
      "step": 960
    },
    {
      "epoch": 0.776,
      "grad_norm": 7.71875,
      "learning_rate": 1.3380952380952383e-05,
      "loss": 2.8381,
      "step": 970
    },
    {
      "epoch": 0.784,
      "grad_norm": 7.625,
      "learning_rate": 1.2904761904761906e-05,
      "loss": 2.6136,
      "step": 980
    },
    {
      "epoch": 0.792,
      "grad_norm": 7.40625,
      "learning_rate": 1.242857142857143e-05,
      "loss": 2.7682,
      "step": 990
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.71875,
      "learning_rate": 1.1952380952380952e-05,
      "loss": 2.6878,
      "step": 1000
    },
    {
      "epoch": 0.808,
      "grad_norm": 8.0,
      "learning_rate": 1.1476190476190476e-05,
      "loss": 2.5709,
      "step": 1010
    },
    {
      "epoch": 0.816,
      "grad_norm": 8.0625,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 2.7941,
      "step": 1020
    },
    {
      "epoch": 0.824,
      "grad_norm": 8.1875,
      "learning_rate": 1.0523809523809525e-05,
      "loss": 2.6739,
      "step": 1030
    },
    {
      "epoch": 0.832,
      "grad_norm": 7.59375,
      "learning_rate": 1.004761904761905e-05,
      "loss": 2.6953,
      "step": 1040
    },
    {
      "epoch": 0.84,
      "grad_norm": 7.3125,
      "learning_rate": 9.571428571428572e-06,
      "loss": 2.6107,
      "step": 1050
    },
    {
      "epoch": 0.848,
      "grad_norm": 7.59375,
      "learning_rate": 9.095238095238095e-06,
      "loss": 2.7805,
      "step": 1060
    },
    {
      "epoch": 0.856,
      "grad_norm": 9.0625,
      "learning_rate": 8.61904761904762e-06,
      "loss": 2.7856,
      "step": 1070
    },
    {
      "epoch": 0.864,
      "grad_norm": 7.75,
      "learning_rate": 8.142857142857143e-06,
      "loss": 2.6762,
      "step": 1080
    },
    {
      "epoch": 0.872,
      "grad_norm": 7.625,
      "learning_rate": 7.666666666666667e-06,
      "loss": 2.7825,
      "step": 1090
    },
    {
      "epoch": 0.88,
      "grad_norm": 7.0,
      "learning_rate": 7.19047619047619e-06,
      "loss": 2.7893,
      "step": 1100
    },
    {
      "epoch": 0.888,
      "grad_norm": 6.9375,
      "learning_rate": 6.714285714285714e-06,
      "loss": 2.7058,
      "step": 1110
    },
    {
      "epoch": 0.896,
      "grad_norm": 7.03125,
      "learning_rate": 6.238095238095239e-06,
      "loss": 2.7899,
      "step": 1120
    },
    {
      "epoch": 0.904,
      "grad_norm": 6.9375,
      "learning_rate": 5.761904761904762e-06,
      "loss": 2.6251,
      "step": 1130
    },
    {
      "epoch": 0.912,
      "grad_norm": 6.84375,
      "learning_rate": 5.285714285714286e-06,
      "loss": 2.7011,
      "step": 1140
    },
    {
      "epoch": 0.92,
      "grad_norm": 6.78125,
      "learning_rate": 4.80952380952381e-06,
      "loss": 2.6375,
      "step": 1150
    },
    {
      "epoch": 0.928,
      "grad_norm": 8.5625,
      "learning_rate": 4.333333333333334e-06,
      "loss": 2.7994,
      "step": 1160
    },
    {
      "epoch": 0.936,
      "grad_norm": 6.59375,
      "learning_rate": 3.857142857142857e-06,
      "loss": 2.7145,
      "step": 1170
    },
    {
      "epoch": 0.944,
      "grad_norm": 7.0625,
      "learning_rate": 3.3809523809523814e-06,
      "loss": 2.6465,
      "step": 1180
    },
    {
      "epoch": 0.952,
      "grad_norm": 8.3125,
      "learning_rate": 2.904761904761905e-06,
      "loss": 2.7466,
      "step": 1190
    },
    {
      "epoch": 0.96,
      "grad_norm": 7.84375,
      "learning_rate": 2.428571428571429e-06,
      "loss": 2.76,
      "step": 1200
    },
    {
      "epoch": 0.968,
      "grad_norm": 7.78125,
      "learning_rate": 1.9523809523809523e-06,
      "loss": 2.7507,
      "step": 1210
    },
    {
      "epoch": 0.976,
      "grad_norm": 7.4375,
      "learning_rate": 1.4761904761904762e-06,
      "loss": 2.7197,
      "step": 1220
    },
    {
      "epoch": 0.984,
      "grad_norm": 7.96875,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.7261,
      "step": 1230
    },
    {
      "epoch": 0.992,
      "grad_norm": 5.90625,
      "learning_rate": 5.238095238095238e-07,
      "loss": 2.6812,
      "step": 1240
    },
    {
      "epoch": 1.0,
      "grad_norm": 8.125,
      "learning_rate": 4.761904761904762e-08,
      "loss": 2.6935,
      "step": 1250
    }
  ],
  "logging_steps": 10,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.443927710242921e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}