{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3476115990855493,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.8039,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.5296,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.4058,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.7512,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 3.1858,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.6959,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.3857,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.4002,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.6352,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.2968,
      "step": 100
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.6599,
      "step": 110
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.3366,
      "step": 120
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.328,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.4935,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 0.9529,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.7595,
      "step": 160
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.2889,
      "step": 170
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.4179,
      "step": 180
    },
    {
      "epoch": 0.18,
      "eval_loss": 1.4205673933029175,
      "eval_runtime": 459.5127,
      "eval_samples_per_second": 2.176,
      "eval_steps_per_second": 2.176,
      "step": 187
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.5063,
      "step": 190
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 0.8211,
      "step": 200
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.6684,
      "step": 210
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.3234,
      "step": 220
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.266,
      "step": 230
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.6375,
      "step": 240
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.3117,
      "step": 250
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.6006,
      "step": 260
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.1979,
      "step": 270
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.2507,
      "step": 280
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.4834,
      "step": 290
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 0.9825,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 1.5844,
      "step": 310
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.3353,
      "step": 320
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.4011,
      "step": 330
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.5332,
      "step": 340
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 0.9384,
      "step": 350
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.7105,
      "step": 360
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.3547,
      "step": 370
    },
    {
      "epoch": 0.36,
      "eval_loss": 1.3805837631225586,
      "eval_runtime": 459.6147,
      "eval_samples_per_second": 2.176,
      "eval_steps_per_second": 2.176,
      "step": 374
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.3614,
      "step": 380
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.4958,
      "step": 390
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 0.8492,
      "step": 400
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.63,
      "step": 410
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.2732,
      "step": 420
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.2632,
      "step": 430
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.5877,
      "step": 440
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.2191,
      "step": 450
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.7254,
      "step": 460
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.2964,
      "step": 470
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.2615,
      "step": 480
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.5623,
      "step": 490
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 0.9829,
      "step": 500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.7679,
      "step": 510
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.2568,
      "step": 520
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.3312,
      "step": 530
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.4983,
      "step": 540
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 0.8519,
      "step": 550
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.6,
      "step": 560
    },
    {
      "epoch": 0.54,
      "eval_loss": 1.3750680685043335,
      "eval_runtime": 459.6344,
      "eval_samples_per_second": 2.176,
      "eval_steps_per_second": 2.176,
      "step": 561
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.1999,
      "step": 570
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.2681,
      "step": 580
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.5114,
      "step": 590
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 0.9807,
      "step": 600
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.6088,
      "step": 610
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.3286,
      "step": 620
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.2899,
      "step": 630
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.4971,
      "step": 640
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.0092,
      "step": 650
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.7029,
      "step": 660
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.2639,
      "step": 670
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.2426,
      "step": 680
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.4332,
      "step": 690
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.0605,
      "step": 700
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.647,
      "step": 710
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.2945,
      "step": 720
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.2847,
      "step": 730
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.445,
      "step": 740
    },
    {
      "epoch": 0.72,
      "eval_loss": 1.3464467525482178,
      "eval_runtime": 459.8714,
      "eval_samples_per_second": 2.175,
      "eval_steps_per_second": 2.175,
      "step": 748
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 0.8241,
      "step": 750
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.5372,
      "step": 760
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.2967,
      "step": 770
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.3492,
      "step": 780
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.4763,
      "step": 790
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 0.8793,
      "step": 800
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.7086,
      "step": 810
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.2769,
      "step": 820
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.2934,
      "step": 830
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001,
      "loss": 1.5392,
      "step": 840
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001,
      "loss": 1.0612,
      "step": 850
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001,
      "loss": 1.5972,
      "step": 860
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 1.2147,
      "step": 870
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 1.3145,
      "step": 880
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001,
      "loss": 1.497,
      "step": 890
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001,
      "loss": 0.9062,
      "step": 900
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001,
      "loss": 1.6361,
      "step": 910
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 1.2367,
      "step": 920
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 1.2854,
      "step": 930
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.357669711112976,
      "eval_runtime": 459.873,
      "eval_samples_per_second": 2.175,
      "eval_steps_per_second": 2.175,
      "step": 935
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 1.5667,
      "step": 940
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 0.9746,
      "step": 950
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001,
      "loss": 1.6803,
      "step": 960
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001,
      "loss": 1.2543,
      "step": 970
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 1.2687,
      "step": 980
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001,
      "loss": 1.4981,
      "step": 990
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001,
      "loss": 0.8578,
      "step": 1000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001,
      "loss": 1.5761,
      "step": 1010
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001,
      "loss": 1.2506,
      "step": 1020
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001,
      "loss": 1.4618,
      "step": 1030
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 1.0891,
      "step": 1040
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 1.3781,
      "step": 1050
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001,
      "loss": 0.9435,
      "step": 1060
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001,
      "loss": 1.1106,
      "step": 1070
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 1.034,
      "step": 1080
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001,
      "loss": 0.7563,
      "step": 1090
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001,
      "loss": 1.3576,
      "step": 1100
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001,
      "loss": 0.9077,
      "step": 1110
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001,
      "loss": 0.9946,
      "step": 1120
    },
    {
      "epoch": 1.08,
      "eval_loss": 1.448190450668335,
      "eval_runtime": 459.9335,
      "eval_samples_per_second": 2.174,
      "eval_steps_per_second": 2.174,
      "step": 1122
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001,
      "loss": 1.0803,
      "step": 1130
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 0.9244,
      "step": 1140
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001,
      "loss": 1.3301,
      "step": 1150
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001,
      "loss": 0.994,
      "step": 1160
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001,
      "loss": 0.9597,
      "step": 1170
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001,
      "loss": 1.077,
      "step": 1180
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001,
      "loss": 0.8099,
      "step": 1190
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 1.3388,
      "step": 1200
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 0.9822,
      "step": 1210
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 0.9254,
      "step": 1220
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001,
      "loss": 1.0194,
      "step": 1230
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001,
      "loss": 0.8094,
      "step": 1240
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001,
      "loss": 1.2964,
      "step": 1250
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001,
      "loss": 0.9678,
      "step": 1260
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001,
      "loss": 0.9391,
      "step": 1270
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001,
      "loss": 0.9972,
      "step": 1280
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001,
      "loss": 0.7331,
      "step": 1290
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 1.3809,
      "step": 1300
    },
    {
      "epoch": 1.26,
      "eval_loss": 1.4262446165084839,
      "eval_runtime": 460.0379,
      "eval_samples_per_second": 2.174,
      "eval_steps_per_second": 2.174,
      "step": 1309
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001,
      "loss": 1.0378,
      "step": 1310
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001,
      "loss": 0.8997,
      "step": 1320
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 1.1066,
      "step": 1330
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001,
      "loss": 0.9112,
      "step": 1340
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001,
      "loss": 1.2313,
      "step": 1350
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001,
      "loss": 0.9425,
      "step": 1360
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001,
      "loss": 1.0515,
      "step": 1370
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001,
      "loss": 1.0183,
      "step": 1380
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 0.7825,
      "step": 1390
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001,
      "loss": 1.3411,
      "step": 1400
    }
  ],
  "max_steps": 1875,
  "num_train_epochs": 2,
  "total_flos": 6.253115028990198e+17,
  "trial_name": null,
  "trial_params": null
}