{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9994069974303224,
  "global_step": 632,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1.6398077091987075e-05,
      "loss": 2.639,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.3460344492986226e-05,
      "loss": 2.6696,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.7591506092636183e-05,
      "loss": 2.6473,
      "step": 15
    },
    {
      "epoch": 0.13,
      "learning_rate": 3e-05,
      "loss": 2.6481,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 3e-05,
      "loss": 2.641,
      "step": 25
    },
    {
      "epoch": 0.19,
      "learning_rate": 3e-05,
      "loss": 2.663,
      "step": 30
    },
    {
      "epoch": 0.22,
      "learning_rate": 3e-05,
      "loss": 2.6205,
      "step": 35
    },
    {
      "epoch": 0.25,
      "learning_rate": 3e-05,
      "loss": 2.6176,
      "step": 40
    },
    {
      "epoch": 0.28,
      "learning_rate": 3e-05,
      "loss": 2.6764,
      "step": 45
    },
    {
      "epoch": 0.32,
      "learning_rate": 3e-05,
      "loss": 2.6393,
      "step": 50
    },
    {
      "epoch": 0.35,
      "learning_rate": 3e-05,
      "loss": 2.6457,
      "step": 55
    },
    {
      "epoch": 0.38,
      "learning_rate": 3e-05,
      "loss": 2.6594,
      "step": 60
    },
    {
      "epoch": 0.41,
      "learning_rate": 3e-05,
      "loss": 2.6146,
      "step": 65
    },
    {
      "epoch": 0.44,
      "learning_rate": 3e-05,
      "loss": 2.6564,
      "step": 70
    },
    {
      "epoch": 0.47,
      "learning_rate": 3e-05,
      "loss": 2.6465,
      "step": 75
    },
    {
      "epoch": 0.51,
      "learning_rate": 3e-05,
      "loss": 2.6293,
      "step": 80
    },
    {
      "epoch": 0.54,
      "learning_rate": 3e-05,
      "loss": 2.6427,
      "step": 85
    },
    {
      "epoch": 0.57,
      "learning_rate": 3e-05,
      "loss": 2.6203,
      "step": 90
    },
    {
      "epoch": 0.6,
      "learning_rate": 3e-05,
      "loss": 2.6286,
      "step": 95
    },
    {
      "epoch": 0.63,
      "learning_rate": 3e-05,
      "loss": 2.6523,
      "step": 100
    },
    {
      "epoch": 0.66,
      "learning_rate": 3e-05,
      "loss": 2.6239,
      "step": 105
    },
    {
      "epoch": 0.7,
      "learning_rate": 3e-05,
      "loss": 2.6053,
      "step": 110
    },
    {
      "epoch": 0.73,
      "learning_rate": 3e-05,
      "loss": 2.6772,
      "step": 115
    },
    {
      "epoch": 0.76,
      "learning_rate": 3e-05,
      "loss": 2.6096,
      "step": 120
    },
    {
      "epoch": 0.79,
      "learning_rate": 3e-05,
      "loss": 2.6703,
      "step": 125
    },
    {
      "epoch": 0.82,
      "learning_rate": 3e-05,
      "loss": 2.6278,
      "step": 130
    },
    {
      "epoch": 0.85,
      "learning_rate": 3e-05,
      "loss": 2.6324,
      "step": 135
    },
    {
      "epoch": 0.89,
      "learning_rate": 3e-05,
      "loss": 2.6098,
      "step": 140
    },
    {
      "epoch": 0.92,
      "learning_rate": 3e-05,
      "loss": 2.6498,
      "step": 145
    },
    {
      "epoch": 0.95,
      "learning_rate": 3e-05,
      "loss": 2.6319,
      "step": 150
    },
    {
      "epoch": 0.98,
      "learning_rate": 3e-05,
      "loss": 2.6507,
      "step": 155
    },
    {
      "epoch": 1.01,
      "learning_rate": 3e-05,
      "loss": 2.6601,
      "step": 160
    },
    {
      "epoch": 1.04,
      "learning_rate": 3e-05,
      "loss": 2.5753,
      "step": 165
    },
    {
      "epoch": 1.08,
      "learning_rate": 3e-05,
      "loss": 2.6221,
      "step": 170
    },
    {
      "epoch": 1.11,
      "learning_rate": 3e-05,
      "loss": 2.5597,
      "step": 175
    },
    {
      "epoch": 1.14,
      "learning_rate": 3e-05,
      "loss": 2.5934,
      "step": 180
    },
    {
      "epoch": 1.17,
      "learning_rate": 3e-05,
      "loss": 2.5633,
      "step": 185
    },
    {
      "epoch": 1.2,
      "learning_rate": 3e-05,
      "loss": 2.5715,
      "step": 190
    },
    {
      "epoch": 1.23,
      "learning_rate": 3e-05,
      "loss": 2.5809,
      "step": 195
    },
    {
      "epoch": 1.27,
      "learning_rate": 3e-05,
      "loss": 2.5561,
      "step": 200
    },
    {
      "epoch": 1.3,
      "learning_rate": 3e-05,
      "loss": 2.5633,
      "step": 205
    },
    {
      "epoch": 1.33,
      "learning_rate": 3e-05,
      "loss": 2.5526,
      "step": 210
    },
    {
      "epoch": 1.36,
      "learning_rate": 3e-05,
      "loss": 2.6323,
      "step": 215
    },
    {
      "epoch": 1.39,
      "learning_rate": 3e-05,
      "loss": 2.5679,
      "step": 220
    },
    {
      "epoch": 1.42,
      "learning_rate": 3e-05,
      "loss": 2.5805,
      "step": 225
    },
    {
      "epoch": 1.46,
      "learning_rate": 3e-05,
      "loss": 2.5833,
      "step": 230
    },
    {
      "epoch": 1.49,
      "learning_rate": 3e-05,
      "loss": 2.5859,
      "step": 235
    },
    {
      "epoch": 1.52,
      "learning_rate": 3e-05,
      "loss": 2.5947,
      "step": 240
    },
    {
      "epoch": 1.55,
      "learning_rate": 3e-05,
      "loss": 2.6159,
      "step": 245
    },
    {
      "epoch": 1.58,
      "learning_rate": 3e-05,
      "loss": 2.5969,
      "step": 250
    },
    {
      "epoch": 1.61,
      "learning_rate": 3e-05,
      "loss": 2.5649,
      "step": 255
    },
    {
      "epoch": 1.65,
      "learning_rate": 3e-05,
      "loss": 2.5304,
      "step": 260
    },
    {
      "epoch": 1.68,
      "learning_rate": 3e-05,
      "loss": 2.5628,
      "step": 265
    },
    {
      "epoch": 1.71,
      "learning_rate": 3e-05,
      "loss": 2.5857,
      "step": 270
    },
    {
      "epoch": 1.74,
      "learning_rate": 3e-05,
      "loss": 2.5914,
      "step": 275
    },
    {
      "epoch": 1.77,
      "learning_rate": 3e-05,
      "loss": 2.5572,
      "step": 280
    },
    {
      "epoch": 1.8,
      "learning_rate": 3e-05,
      "loss": 2.6037,
      "step": 285
    },
    {
      "epoch": 1.83,
      "learning_rate": 3e-05,
      "loss": 2.6095,
      "step": 290
    },
    {
      "epoch": 1.87,
      "learning_rate": 3e-05,
      "loss": 2.5787,
      "step": 295
    },
    {
      "epoch": 1.9,
      "learning_rate": 3e-05,
      "loss": 2.5881,
      "step": 300
    },
    {
      "epoch": 1.93,
      "learning_rate": 3e-05,
      "loss": 2.5706,
      "step": 305
    },
    {
      "epoch": 1.96,
      "learning_rate": 3e-05,
      "loss": 2.5636,
      "step": 310
    },
    {
      "epoch": 1.99,
      "learning_rate": 3e-05,
      "loss": 2.576,
      "step": 315
    },
    {
      "epoch": 2.03,
      "learning_rate": 3e-05,
      "loss": 2.5955,
      "step": 320
    },
    {
      "epoch": 2.06,
      "learning_rate": 3e-05,
      "loss": 2.5293,
      "step": 325
    },
    {
      "epoch": 2.09,
      "learning_rate": 3e-05,
      "loss": 2.5107,
      "step": 330
    },
    {
      "epoch": 2.12,
      "learning_rate": 3e-05,
      "loss": 2.5378,
      "step": 335
    },
    {
      "epoch": 2.15,
      "learning_rate": 3e-05,
      "loss": 2.5262,
      "step": 340
    },
    {
      "epoch": 2.18,
      "learning_rate": 3e-05,
      "loss": 2.5485,
      "step": 345
    },
    {
      "epoch": 2.22,
      "learning_rate": 3e-05,
      "loss": 2.5123,
      "step": 350
    },
    {
      "epoch": 2.25,
      "learning_rate": 3e-05,
      "loss": 2.509,
      "step": 355
    },
    {
      "epoch": 2.28,
      "learning_rate": 3e-05,
      "loss": 2.4993,
      "step": 360
    },
    {
      "epoch": 2.31,
      "learning_rate": 3e-05,
      "loss": 2.5133,
      "step": 365
    },
    {
      "epoch": 2.34,
      "learning_rate": 3e-05,
      "loss": 2.5346,
      "step": 370
    },
    {
      "epoch": 2.37,
      "learning_rate": 3e-05,
      "loss": 2.5174,
      "step": 375
    },
    {
      "epoch": 2.4,
      "learning_rate": 3e-05,
      "loss": 2.5282,
      "step": 380
    },
    {
      "epoch": 2.44,
      "learning_rate": 3e-05,
      "loss": 2.5489,
      "step": 385
    },
    {
      "epoch": 2.47,
      "learning_rate": 3e-05,
      "loss": 2.4989,
      "step": 390
    },
    {
      "epoch": 2.5,
      "learning_rate": 3e-05,
      "loss": 2.5243,
      "step": 395
    },
    {
      "epoch": 2.53,
      "learning_rate": 3e-05,
      "loss": 2.5228,
      "step": 400
    },
    {
      "epoch": 2.56,
      "learning_rate": 3e-05,
      "loss": 2.5013,
      "step": 405
    },
    {
      "epoch": 2.59,
      "learning_rate": 3e-05,
      "loss": 2.509,
      "step": 410
    },
    {
      "epoch": 2.63,
      "learning_rate": 3e-05,
      "loss": 2.566,
      "step": 415
    },
    {
      "epoch": 2.66,
      "learning_rate": 3e-05,
      "loss": 2.5291,
      "step": 420
    },
    {
      "epoch": 2.69,
      "learning_rate": 3e-05,
      "loss": 2.5421,
      "step": 425
    },
    {
      "epoch": 2.72,
      "learning_rate": 3e-05,
      "loss": 2.5454,
      "step": 430
    },
    {
      "epoch": 2.75,
      "learning_rate": 3e-05,
      "loss": 2.5324,
      "step": 435
    },
    {
      "epoch": 2.78,
      "learning_rate": 3e-05,
      "loss": 2.5457,
      "step": 440
    },
    {
      "epoch": 2.82,
      "learning_rate": 3e-05,
      "loss": 2.5365,
      "step": 445
    },
    {
      "epoch": 2.85,
      "learning_rate": 3e-05,
      "loss": 2.5395,
      "step": 450
    },
    {
      "epoch": 2.88,
      "learning_rate": 3e-05,
      "loss": 2.5458,
      "step": 455
    },
    {
      "epoch": 2.91,
      "learning_rate": 3e-05,
      "loss": 2.4935,
      "step": 460
    },
    {
      "epoch": 2.94,
      "learning_rate": 3e-05,
      "loss": 2.5347,
      "step": 465
    },
    {
      "epoch": 2.97,
      "learning_rate": 3e-05,
      "loss": 2.5287,
      "step": 470
    },
    {
      "epoch": 3.01,
      "learning_rate": 3e-05,
      "loss": 2.5784,
      "step": 475
    },
    {
      "epoch": 3.04,
      "learning_rate": 3e-05,
      "loss": 2.4889,
      "step": 480
    },
    {
      "epoch": 3.07,
      "learning_rate": 3e-05,
      "loss": 2.4622,
      "step": 485
    },
    {
      "epoch": 3.1,
      "learning_rate": 3e-05,
      "loss": 2.4628,
      "step": 490
    },
    {
      "epoch": 3.13,
      "learning_rate": 3e-05,
      "loss": 2.5204,
      "step": 495
    },
    {
      "epoch": 3.16,
      "learning_rate": 3e-05,
      "loss": 2.4543,
      "step": 500
    },
    {
      "epoch": 3.2,
      "learning_rate": 3e-05,
      "loss": 2.4717,
      "step": 505
    },
    {
      "epoch": 3.23,
      "learning_rate": 3e-05,
      "loss": 2.5113,
      "step": 510
    },
    {
      "epoch": 3.26,
      "learning_rate": 3e-05,
      "loss": 2.4838,
      "step": 515
    },
    {
      "epoch": 3.29,
      "learning_rate": 3e-05,
      "loss": 2.5224,
      "step": 520
    },
    {
      "epoch": 3.32,
      "learning_rate": 3e-05,
      "loss": 2.4858,
      "step": 525
    },
    {
      "epoch": 3.35,
      "learning_rate": 3e-05,
      "loss": 2.5227,
      "step": 530
    },
    {
      "epoch": 3.39,
      "learning_rate": 3e-05,
      "loss": 2.4824,
      "step": 535
    },
    {
      "epoch": 3.42,
      "learning_rate": 3e-05,
      "loss": 2.4836,
      "step": 540
    },
    {
      "epoch": 3.45,
      "learning_rate": 3e-05,
      "loss": 2.4968,
      "step": 545
    },
    {
      "epoch": 3.48,
      "learning_rate": 3e-05,
      "loss": 2.5004,
      "step": 550
    },
    {
      "epoch": 3.51,
      "learning_rate": 3e-05,
      "loss": 2.4756,
      "step": 555
    },
    {
      "epoch": 3.54,
      "learning_rate": 3e-05,
      "loss": 2.5068,
      "step": 560
    },
    {
      "epoch": 3.58,
      "learning_rate": 3e-05,
      "loss": 2.468,
      "step": 565
    },
    {
      "epoch": 3.61,
      "learning_rate": 3e-05,
      "loss": 2.4764,
      "step": 570
    },
    {
      "epoch": 3.64,
      "learning_rate": 3e-05,
      "loss": 2.4927,
      "step": 575
    },
    {
      "epoch": 3.67,
      "learning_rate": 3e-05,
      "loss": 2.4993,
      "step": 580
    },
    {
      "epoch": 3.7,
      "learning_rate": 3e-05,
      "loss": 2.4786,
      "step": 585
    },
    {
      "epoch": 3.73,
      "learning_rate": 3e-05,
      "loss": 2.489,
      "step": 590
    },
    {
      "epoch": 3.77,
      "learning_rate": 3e-05,
      "loss": 2.4271,
      "step": 595
    },
    {
      "epoch": 3.8,
      "learning_rate": 3e-05,
      "loss": 2.4502,
      "step": 600
    },
    {
      "epoch": 3.83,
      "learning_rate": 3e-05,
      "loss": 2.4682,
      "step": 605
    },
    {
      "epoch": 3.86,
      "learning_rate": 3e-05,
      "loss": 2.4702,
      "step": 610
    },
    {
      "epoch": 3.89,
      "learning_rate": 3e-05,
      "loss": 2.4722,
      "step": 615
    },
    {
      "epoch": 3.92,
      "learning_rate": 3e-05,
      "loss": 2.5132,
      "step": 620
    },
    {
      "epoch": 3.96,
      "learning_rate": 3e-05,
      "loss": 2.446,
      "step": 625
    },
    {
      "epoch": 3.99,
      "learning_rate": 3e-05,
      "loss": 2.4824,
      "step": 630
    },
    {
      "epoch": 4.0,
      "step": 632,
      "total_flos": 2.1853297764099686e+17,
      "train_loss": 2.5587786006022104,
      "train_runtime": 54071.5154,
      "train_samples_per_second": 0.748,
      "train_steps_per_second": 0.012
    }
  ],
  "max_steps": 632,
  "num_train_epochs": 4,
  "total_flos": 2.1853297764099686e+17,
  "trial_name": null,
  "trial_params": null
}