{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7266610597140453,
  "global_step": 810,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.6216,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.301029995663981e-05,
      "loss": 1.285,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.4771212547196623e-05,
      "loss": 1.2164,
      "step": 30
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.6020599913279622e-05,
      "loss": 1.1761,
      "step": 40
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.6989700043360187e-05,
      "loss": 1.1658,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.7781512503836432e-05,
      "loss": 1.1914,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8450980400142568e-05,
      "loss": 1.1324,
      "step": 70
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9030899869919434e-05,
      "loss": 1.1571,
      "step": 80
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9542425094393246e-05,
      "loss": 1.1633,
      "step": 90
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 1.1991,
      "step": 100
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 1.1653,
      "step": 110
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 1.1272,
      "step": 120
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 1.1054,
      "step": 130
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 1.1359,
      "step": 140
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 1.12,
      "step": 150
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 1.0979,
      "step": 160
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 1.1227,
      "step": 170
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 1.1003,
      "step": 180
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 1.0942,
      "step": 190
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 1.1098,
      "step": 200
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 1.0949,
      "step": 210
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 1.056,
      "step": 220
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 1.0822,
      "step": 230
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 1.1038,
      "step": 240
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 1.0813,
      "step": 250
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 1.0721,
      "step": 260
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 1.0604,
      "step": 270
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 1.1054,
      "step": 280
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 1.1074,
      "step": 290
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 1.0971,
      "step": 300
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 1.0838,
      "step": 310
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 1.0419,
      "step": 320
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 1.0528,
      "step": 330
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 1.0475,
      "step": 340
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 1.036,
      "step": 350
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 1.0341,
      "step": 360
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 1.0354,
      "step": 370
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 1.0481,
      "step": 380
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 1.0248,
      "step": 390
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 1.0237,
      "step": 400
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 1.052,
      "step": 410
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 1.0383,
      "step": 420
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 1.0423,
      "step": 430
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 1.0181,
      "step": 440
    },
    {
      "epoch": 1.51,
      "learning_rate": 2e-05,
      "loss": 1.0059,
      "step": 450
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 1.0392,
      "step": 460
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.9981,
      "step": 470
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 1.0486,
      "step": 480
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 1.0198,
      "step": 490
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 1.039,
      "step": 500
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 1.0518,
      "step": 510
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 1.0497,
      "step": 520
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 1.0346,
      "step": 530
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-05,
      "loss": 1.046,
      "step": 540
    },
    {
      "epoch": 1.85,
      "learning_rate": 2e-05,
      "loss": 1.0148,
      "step": 550
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 1.0166,
      "step": 560
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 1.0207,
      "step": 570
    },
    {
      "epoch": 1.95,
      "learning_rate": 2e-05,
      "loss": 1.0118,
      "step": 580
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 1.052,
      "step": 590
    },
    {
      "epoch": 2.02,
      "learning_rate": 2e-05,
      "loss": 1.0217,
      "step": 600
    },
    {
      "epoch": 2.05,
      "learning_rate": 2e-05,
      "loss": 1.0094,
      "step": 610
    },
    {
      "epoch": 2.09,
      "learning_rate": 2e-05,
      "loss": 1.0067,
      "step": 620
    },
    {
      "epoch": 2.12,
      "learning_rate": 2e-05,
      "loss": 1.0122,
      "step": 630
    },
    {
      "epoch": 2.15,
      "learning_rate": 2e-05,
      "loss": 0.9602,
      "step": 640
    },
    {
      "epoch": 2.19,
      "learning_rate": 2e-05,
      "loss": 0.9589,
      "step": 650
    },
    {
      "epoch": 2.22,
      "learning_rate": 2e-05,
      "loss": 0.9808,
      "step": 660
    },
    {
      "epoch": 2.26,
      "learning_rate": 2e-05,
      "loss": 1.0098,
      "step": 670
    },
    {
      "epoch": 2.29,
      "learning_rate": 2e-05,
      "loss": 1.0272,
      "step": 680
    },
    {
      "epoch": 2.32,
      "learning_rate": 2e-05,
      "loss": 0.996,
      "step": 690
    },
    {
      "epoch": 2.36,
      "learning_rate": 2e-05,
      "loss": 1.005,
      "step": 700
    },
    {
      "epoch": 2.39,
      "learning_rate": 2e-05,
      "loss": 1.0229,
      "step": 710
    },
    {
      "epoch": 2.42,
      "learning_rate": 2e-05,
      "loss": 1.0058,
      "step": 720
    },
    {
      "epoch": 2.46,
      "learning_rate": 2e-05,
      "loss": 1.0254,
      "step": 730
    },
    {
      "epoch": 2.49,
      "learning_rate": 2e-05,
      "loss": 1.0081,
      "step": 740
    },
    {
      "epoch": 2.52,
      "learning_rate": 2e-05,
      "loss": 1.0074,
      "step": 750
    },
    {
      "epoch": 2.56,
      "learning_rate": 2e-05,
      "loss": 1.0385,
      "step": 760
    },
    {
      "epoch": 2.59,
      "learning_rate": 2e-05,
      "loss": 1.0092,
      "step": 770
    },
    {
      "epoch": 2.63,
      "learning_rate": 2e-05,
      "loss": 0.9963,
      "step": 780
    },
    {
      "epoch": 2.66,
      "learning_rate": 2e-05,
      "loss": 1.0051,
      "step": 790
    },
    {
      "epoch": 2.69,
      "learning_rate": 2e-05,
      "loss": 0.9937,
      "step": 800
    },
    {
      "epoch": 2.73,
      "learning_rate": 2e-05,
      "loss": 1.0372,
      "step": 810
    }
  ],
  "max_steps": 891,
  "num_train_epochs": 3,
  "total_flos": 1.1487001401653985e+19,
  "trial_name": null,
  "trial_params": null
}