{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.977777777777778,
  "eval_steps": 500,
  "global_step": 630,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 7.769179709180454e-06,
      "loss": 1.3862,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.111518328538394e-05,
      "loss": 1.201,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.307246990474186e-05,
      "loss": 1.213,
      "step": 15
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.4461186861587421e-05,
      "loss": 1.2115,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.5538359418360907e-05,
      "loss": 1.1947,
      "step": 25
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.6418473480945343e-05,
      "loss": 1.1575,
      "step": 30
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.7162599318057647e-05,
      "loss": 1.1609,
      "step": 35
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.7807190437790904e-05,
      "loss": 1.1704,
      "step": 40
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.8375760100303265e-05,
      "loss": 1.1499,
      "step": 45
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.8884362994564394e-05,
      "loss": 1.1641,
      "step": 50
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.9344450276772258e-05,
      "loss": 1.1783,
      "step": 55
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.9764477057148826e-05,
      "loss": 1.1496,
      "step": 60
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 1.1579,
      "step": 65
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 1.1834,
      "step": 70
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 1.1981,
      "step": 75
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 1.1672,
      "step": 80
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 1.1731,
      "step": 85
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 1.1754,
      "step": 90
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 1.1599,
      "step": 95
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 1.1552,
      "step": 100
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 1.1653,
      "step": 105
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 1.1196,
      "step": 110
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 1.1786,
      "step": 115
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 1.1622,
      "step": 120
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 1.1342,
      "step": 125
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 0.8944,
      "step": 130
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.7323,
      "step": 135
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.7555,
      "step": 140
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 0.725,
      "step": 145
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.6937,
      "step": 150
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 155
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 160
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.7295,
      "step": 165
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 0.7126,
      "step": 170
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 0.7208,
      "step": 175
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.7109,
      "step": 180
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.7367,
      "step": 185
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.7144,
      "step": 190
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.7257,
      "step": 195
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.7346,
      "step": 200
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 0.7454,
      "step": 205
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.7115,
      "step": 210
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.7137,
      "step": 215
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.713,
      "step": 220
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.7364,
      "step": 225
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-05,
      "loss": 0.7385,
      "step": 230
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 0.7398,
      "step": 235
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 0.7134,
      "step": 240
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.7282,
      "step": 245
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.7697,
      "step": 250
    },
    {
      "epoch": 2.01,
      "learning_rate": 2e-05,
      "loss": 0.5946,
      "step": 255
    },
    {
      "epoch": 2.05,
      "learning_rate": 2e-05,
      "loss": 0.3129,
      "step": 260
    },
    {
      "epoch": 2.09,
      "learning_rate": 2e-05,
      "loss": 0.2843,
      "step": 265
    },
    {
      "epoch": 2.13,
      "learning_rate": 2e-05,
      "loss": 0.276,
      "step": 270
    },
    {
      "epoch": 2.17,
      "learning_rate": 2e-05,
      "loss": 0.2661,
      "step": 275
    },
    {
      "epoch": 2.21,
      "learning_rate": 2e-05,
      "loss": 0.2728,
      "step": 280
    },
    {
      "epoch": 2.25,
      "learning_rate": 2e-05,
      "loss": 0.2701,
      "step": 285
    },
    {
      "epoch": 2.29,
      "learning_rate": 2e-05,
      "loss": 0.2752,
      "step": 290
    },
    {
      "epoch": 2.33,
      "learning_rate": 2e-05,
      "loss": 0.2667,
      "step": 295
    },
    {
      "epoch": 2.37,
      "learning_rate": 2e-05,
      "loss": 0.272,
      "step": 300
    },
    {
      "epoch": 2.41,
      "learning_rate": 2e-05,
      "loss": 0.2684,
      "step": 305
    },
    {
      "epoch": 2.45,
      "learning_rate": 2e-05,
      "loss": 0.2735,
      "step": 310
    },
    {
      "epoch": 2.49,
      "learning_rate": 2e-05,
      "loss": 0.2728,
      "step": 315
    },
    {
      "epoch": 2.53,
      "learning_rate": 2e-05,
      "loss": 0.28,
      "step": 320
    },
    {
      "epoch": 2.57,
      "learning_rate": 2e-05,
      "loss": 0.2989,
      "step": 325
    },
    {
      "epoch": 2.61,
      "learning_rate": 2e-05,
      "loss": 0.2837,
      "step": 330
    },
    {
      "epoch": 2.65,
      "learning_rate": 2e-05,
      "loss": 0.2823,
      "step": 335
    },
    {
      "epoch": 2.69,
      "learning_rate": 2e-05,
      "loss": 0.2947,
      "step": 340
    },
    {
      "epoch": 2.73,
      "learning_rate": 2e-05,
      "loss": 0.2859,
      "step": 345
    },
    {
      "epoch": 2.77,
      "learning_rate": 2e-05,
      "loss": 0.2936,
      "step": 350
    },
    {
      "epoch": 2.8,
      "learning_rate": 2e-05,
      "loss": 0.2924,
      "step": 355
    },
    {
      "epoch": 2.84,
      "learning_rate": 2e-05,
      "loss": 0.2818,
      "step": 360
    },
    {
      "epoch": 2.88,
      "learning_rate": 2e-05,
      "loss": 0.2869,
      "step": 365
    },
    {
      "epoch": 2.92,
      "learning_rate": 2e-05,
      "loss": 0.2992,
      "step": 370
    },
    {
      "epoch": 2.96,
      "learning_rate": 2e-05,
      "loss": 0.2946,
      "step": 375
    },
    {
      "epoch": 3.0,
      "learning_rate": 2e-05,
      "loss": 0.2801,
      "step": 380
    },
    {
      "epoch": 3.04,
      "learning_rate": 2e-05,
      "loss": 0.081,
      "step": 385
    },
    {
      "epoch": 3.08,
      "learning_rate": 2e-05,
      "loss": 0.0829,
      "step": 390
    },
    {
      "epoch": 3.12,
      "learning_rate": 2e-05,
      "loss": 0.077,
      "step": 395
    },
    {
      "epoch": 3.16,
      "learning_rate": 2e-05,
      "loss": 0.0764,
      "step": 400
    },
    {
      "epoch": 3.2,
      "learning_rate": 2e-05,
      "loss": 0.076,
      "step": 405
    },
    {
      "epoch": 3.24,
      "learning_rate": 2e-05,
      "loss": 0.0781,
      "step": 410
    },
    {
      "epoch": 3.28,
      "learning_rate": 2e-05,
      "loss": 0.074,
      "step": 415
    },
    {
      "epoch": 3.32,
      "learning_rate": 2e-05,
      "loss": 0.0779,
      "step": 420
    },
    {
      "epoch": 3.36,
      "learning_rate": 2e-05,
      "loss": 0.0754,
      "step": 425
    },
    {
      "epoch": 3.4,
      "learning_rate": 2e-05,
      "loss": 0.0795,
      "step": 430
    },
    {
      "epoch": 3.44,
      "learning_rate": 2e-05,
      "loss": 0.0747,
      "step": 435
    },
    {
      "epoch": 3.48,
      "learning_rate": 2e-05,
      "loss": 0.0793,
      "step": 440
    },
    {
      "epoch": 3.52,
      "learning_rate": 2e-05,
      "loss": 0.0838,
      "step": 445
    },
    {
      "epoch": 3.56,
      "learning_rate": 2e-05,
      "loss": 0.0773,
      "step": 450
    },
    {
      "epoch": 3.6,
      "learning_rate": 2e-05,
      "loss": 0.0735,
      "step": 455
    },
    {
      "epoch": 3.63,
      "learning_rate": 2e-05,
      "loss": 0.0787,
      "step": 460
    },
    {
      "epoch": 3.67,
      "learning_rate": 2e-05,
      "loss": 0.0863,
      "step": 465
    },
    {
      "epoch": 3.71,
      "learning_rate": 2e-05,
      "loss": 0.085,
      "step": 470
    },
    {
      "epoch": 3.75,
      "learning_rate": 2e-05,
      "loss": 0.0791,
      "step": 475
    },
    {
      "epoch": 3.79,
      "learning_rate": 2e-05,
      "loss": 0.0795,
      "step": 480
    },
    {
      "epoch": 3.83,
      "learning_rate": 2e-05,
      "loss": 0.0844,
      "step": 485
    },
    {
      "epoch": 3.87,
      "learning_rate": 2e-05,
      "loss": 0.0839,
      "step": 490
    },
    {
      "epoch": 3.91,
      "learning_rate": 2e-05,
      "loss": 0.0845,
      "step": 495
    },
    {
      "epoch": 3.95,
      "learning_rate": 2e-05,
      "loss": 0.0816,
      "step": 500
    },
    {
      "epoch": 3.99,
      "learning_rate": 2e-05,
      "loss": 0.09,
      "step": 505
    },
    {
      "epoch": 4.03,
      "learning_rate": 2e-05,
      "loss": 0.0484,
      "step": 510
    },
    {
      "epoch": 4.07,
      "learning_rate": 2e-05,
      "loss": 0.033,
      "step": 515
    },
    {
      "epoch": 4.11,
      "learning_rate": 2e-05,
      "loss": 0.0322,
      "step": 520
    },
    {
      "epoch": 4.15,
      "learning_rate": 2e-05,
      "loss": 0.0298,
      "step": 525
    },
    {
      "epoch": 4.19,
      "learning_rate": 2e-05,
      "loss": 0.0342,
      "step": 530
    },
    {
      "epoch": 4.23,
      "learning_rate": 2e-05,
      "loss": 0.0327,
      "step": 535
    },
    {
      "epoch": 4.27,
      "learning_rate": 2e-05,
      "loss": 0.0345,
      "step": 540
    },
    {
      "epoch": 4.31,
      "learning_rate": 2e-05,
      "loss": 0.0301,
      "step": 545
    },
    {
      "epoch": 4.35,
      "learning_rate": 2e-05,
      "loss": 0.0312,
      "step": 550
    },
    {
      "epoch": 4.39,
      "learning_rate": 2e-05,
      "loss": 0.0321,
      "step": 555
    },
    {
      "epoch": 4.42,
      "learning_rate": 2e-05,
      "loss": 0.0298,
      "step": 560
    },
    {
      "epoch": 4.46,
      "learning_rate": 2e-05,
      "loss": 0.0315,
      "step": 565
    },
    {
      "epoch": 4.5,
      "learning_rate": 2e-05,
      "loss": 0.0319,
      "step": 570
    },
    {
      "epoch": 4.54,
      "learning_rate": 2e-05,
      "loss": 0.0331,
      "step": 575
    },
    {
      "epoch": 4.58,
      "learning_rate": 2e-05,
      "loss": 0.0322,
      "step": 580
    },
    {
      "epoch": 4.62,
      "learning_rate": 2e-05,
      "loss": 0.0326,
      "step": 585
    },
    {
      "epoch": 4.66,
      "learning_rate": 2e-05,
      "loss": 0.0333,
      "step": 590
    },
    {
      "epoch": 4.7,
      "learning_rate": 2e-05,
      "loss": 0.0322,
      "step": 595
    },
    {
      "epoch": 4.74,
      "learning_rate": 2e-05,
      "loss": 0.0309,
      "step": 600
    },
    {
      "epoch": 4.78,
      "learning_rate": 2e-05,
      "loss": 0.0312,
      "step": 605
    },
    {
      "epoch": 4.82,
      "learning_rate": 2e-05,
      "loss": 0.0296,
      "step": 610
    },
    {
      "epoch": 4.86,
      "learning_rate": 2e-05,
      "loss": 0.0316,
      "step": 615
    },
    {
      "epoch": 4.9,
      "learning_rate": 2e-05,
      "loss": 0.0325,
      "step": 620
    },
    {
      "epoch": 4.94,
      "learning_rate": 2e-05,
      "loss": 0.0299,
      "step": 625
    },
    {
      "epoch": 4.98,
      "learning_rate": 2e-05,
      "loss": 0.0305,
      "step": 630
    }
  ],
  "logging_steps": 5,
  "max_steps": 630,
  "num_train_epochs": 5,
  "save_steps": 100,
  "total_flos": 519292402286592.0,
  "trial_name": null,
  "trial_params": null
}