{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01949769498511016,
  "global_step": 1120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 4.1497,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 3.7626,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 3.3202,
      "step": 30
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 3.1832,
      "step": 40
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 3.0717,
      "step": 50
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 2.9981,
      "step": 60
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00014000000000000001,
      "loss": 2.9461,
      "step": 70
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 2.9218,
      "step": 80
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.9574,
      "step": 90
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.9917,
      "step": 100
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00022,
      "loss": 2.9242,
      "step": 110
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00024,
      "loss": 2.9225,
      "step": 120
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.9253,
      "step": 130
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00028000000000000003,
      "loss": 2.8171,
      "step": 140
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0003,
      "loss": 2.9023,
      "step": 150
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00032,
      "loss": 2.809,
      "step": 160
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00034,
      "loss": 2.9079,
      "step": 170
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00035999999999999997,
      "loss": 2.7811,
      "step": 180
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00038,
      "loss": 2.8214,
      "step": 190
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0004,
      "loss": 2.821,
      "step": 200
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00042,
      "loss": 2.7647,
      "step": 210
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00044,
      "loss": 2.776,
      "step": 220
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00046,
      "loss": 2.8615,
      "step": 230
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00048,
      "loss": 2.7913,
      "step": 240
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0005,
      "loss": 2.7515,
      "step": 250
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0005200000000000001,
      "loss": 2.7199,
      "step": 260
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00054,
      "loss": 2.7464,
      "step": 270
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0005600000000000001,
      "loss": 2.7036,
      "step": 280
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00058,
      "loss": 2.8226,
      "step": 290
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0006,
      "loss": 2.6855,
      "step": 300
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00062,
      "loss": 2.7442,
      "step": 310
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00064,
      "loss": 2.7517,
      "step": 320
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00066,
      "loss": 2.6921,
      "step": 330
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00068,
      "loss": 2.7034,
      "step": 340
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0007,
      "loss": 2.7489,
      "step": 350
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0007199999999999999,
      "loss": 2.6452,
      "step": 360
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00074,
      "loss": 2.7452,
      "step": 370
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00076,
      "loss": 2.6834,
      "step": 380
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0007800000000000001,
      "loss": 2.6984,
      "step": 390
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0008,
      "loss": 2.6716,
      "step": 400
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00082,
      "loss": 2.7164,
      "step": 410
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00084,
      "loss": 2.634,
      "step": 420
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00086,
      "loss": 2.6932,
      "step": 430
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00088,
      "loss": 2.623,
      "step": 440
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.6827,
      "step": 450
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00092,
      "loss": 2.6558,
      "step": 460
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00094,
      "loss": 2.7282,
      "step": 470
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00096,
      "loss": 2.7123,
      "step": 480
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00098,
      "loss": 2.5858,
      "step": 490
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.001,
      "loss": 2.7641,
      "step": 500
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00102,
      "loss": 2.6606,
      "step": 510
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0010400000000000001,
      "loss": 2.7237,
      "step": 520
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0010600000000000002,
      "loss": 2.66,
      "step": 530
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00108,
      "loss": 2.6041,
      "step": 540
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0011,
      "loss": 2.608,
      "step": 550
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0011200000000000001,
      "loss": 2.63,
      "step": 560
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00114,
      "loss": 2.6255,
      "step": 570
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00116,
      "loss": 2.6602,
      "step": 580
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00118,
      "loss": 2.6522,
      "step": 590
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0012,
      "loss": 2.7137,
      "step": 600
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00122,
      "loss": 2.6914,
      "step": 610
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00124,
      "loss": 2.6888,
      "step": 620
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00126,
      "loss": 2.6398,
      "step": 630
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00128,
      "loss": 2.6058,
      "step": 640
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0013000000000000002,
      "loss": 2.7215,
      "step": 650
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00132,
      "loss": 2.5945,
      "step": 660
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00134,
      "loss": 2.6325,
      "step": 670
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00136,
      "loss": 2.6191,
      "step": 680
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00138,
      "loss": 2.5328,
      "step": 690
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0014,
      "loss": 2.562,
      "step": 700
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00142,
      "loss": 2.5454,
      "step": 710
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0014399999999999999,
      "loss": 2.5328,
      "step": 720
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00146,
      "loss": 2.5141,
      "step": 730
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00148,
      "loss": 2.5019,
      "step": 740
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0015,
      "loss": 2.4906,
      "step": 750
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00152,
      "loss": 2.5153,
      "step": 760
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0015400000000000001,
      "loss": 2.4857,
      "step": 770
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0015600000000000002,
      "loss": 2.5265,
      "step": 780
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00158,
      "loss": 2.4994,
      "step": 790
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0016,
      "loss": 2.4538,
      "step": 800
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0016200000000000001,
      "loss": 2.5823,
      "step": 810
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00164,
      "loss": 2.4527,
      "step": 820
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00166,
      "loss": 2.4914,
      "step": 830
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00168,
      "loss": 2.4307,
      "step": 840
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0017,
      "loss": 2.4795,
      "step": 850
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00172,
      "loss": 2.4245,
      "step": 860
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00174,
      "loss": 2.4751,
      "step": 870
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00176,
      "loss": 2.4705,
      "step": 880
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0017800000000000001,
      "loss": 2.4574,
      "step": 890
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0018000000000000002,
      "loss": 2.4271,
      "step": 900
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00182,
      "loss": 2.4609,
      "step": 910
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00184,
      "loss": 2.4255,
      "step": 920
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00186,
      "loss": 2.4151,
      "step": 930
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00188,
      "loss": 2.4331,
      "step": 940
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0019,
      "loss": 2.4576,
      "step": 950
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00192,
      "loss": 2.4156,
      "step": 960
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0019399999999999999,
      "loss": 2.417,
      "step": 970
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00196,
      "loss": 2.444,
      "step": 980
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00198,
      "loss": 2.5019,
      "step": 990
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.002,
      "loss": 2.4522,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00202,
      "loss": 2.4106,
      "step": 1010
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00204,
      "loss": 2.4295,
      "step": 1020
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00206,
      "loss": 2.4683,
      "step": 1030
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0020800000000000003,
      "loss": 2.4315,
      "step": 1040
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0021000000000000003,
      "loss": 2.41,
      "step": 1050
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0021200000000000004,
      "loss": 2.4551,
      "step": 1060
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00214,
      "loss": 2.4642,
      "step": 1070
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00216,
      "loss": 2.4526,
      "step": 1080
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00218,
      "loss": 2.3934,
      "step": 1090
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0022,
      "loss": 2.3918,
      "step": 1100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00222,
      "loss": 2.4356,
      "step": 1110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0022400000000000002,
      "loss": 2.4506,
      "step": 1120
    }
  ],
  "max_steps": 172326,
  "num_train_epochs": 3,
  "total_flos": 5.5330613854470144e+17,
  "trial_name": null,
  "trial_params": null
}