{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9986382206082615,
  "eval_steps": 500,
  "global_step": 550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.6363636363636366e-07,
      "loss": 1.6989,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.592,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.3096,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.1801,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.1065,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.0653,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 1.0523,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 1.0315,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 1.0111,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 1.0113,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.0169,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.998,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9994965423831853e-05,
      "loss": 1.0046,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9979866764718846e-05,
      "loss": 1.0102,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9954719225730847e-05,
      "loss": 1.012,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9919548128307954e-05,
      "loss": 1.0108,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9874388886763944e-05,
      "loss": 0.9918,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9819286972627066e-05,
      "loss": 0.9959,
      "step": 85
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.9754297868854075e-05,
      "loss": 1.0019,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9679487013963566e-05,
      "loss": 0.9897,
      "step": 95
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 1.004,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.9500711177409456e-05,
      "loss": 0.9838,
      "step": 105
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.9717,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9283679330160726e-05,
      "loss": 0.9931,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9161084574320696e-05,
      "loss": 0.9785,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9029265382866216e-05,
      "loss": 0.9876,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8888354486549238e-05,
      "loss": 0.9785,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.873849377069785e-05,
      "loss": 0.9739,
      "step": 135
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8579834132349773e-05,
      "loss": 0.9751,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 0.9923,
      "step": 145
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8236765814298328e-05,
      "loss": 0.9823,
      "step": 150
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8052702575310588e-05,
      "loss": 0.9691,
      "step": 155
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7860530947427878e-05,
      "loss": 0.98,
      "step": 160
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.978,
      "step": 165
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.745264449675755e-05,
      "loss": 0.9827,
      "step": 170
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.72373403810507e-05,
      "loss": 0.9785,
      "step": 175
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7014748877063212e-05,
      "loss": 0.9826,
      "step": 180
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.6785094115571323e-05,
      "loss": 0.9877,
      "step": 185
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.6548607339452853e-05,
      "loss": 0.982,
      "step": 190
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.6305526670845225e-05,
      "loss": 0.973,
      "step": 195
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6056096871376667e-05,
      "loss": 0.9737,
      "step": 200
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.5800569095711983e-05,
      "loss": 0.9677,
      "step": 205
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.5539200638661106e-05,
      "loss": 0.973,
      "step": 210
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.5272254676105026e-05,
      "loss": 0.9678,
      "step": 215
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.9669,
      "step": 220
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.472271074772683e-05,
      "loss": 0.9834,
      "step": 225
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.4440666126057743e-05,
      "loss": 0.9625,
      "step": 230
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.4154150130018867e-05,
      "loss": 0.9639,
      "step": 235
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.3863451256931286e-05,
      "loss": 0.9643,
      "step": 240
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.356886221591872e-05,
      "loss": 0.9601,
      "step": 245
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.3270679633174219e-05,
      "loss": 0.953,
      "step": 250
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.296920375328275e-05,
      "loss": 0.9619,
      "step": 255
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.266473813690035e-05,
      "loss": 0.9701,
      "step": 260
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.2357589355094275e-05,
      "loss": 0.9593,
      "step": 265
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.2048066680651908e-05,
      "loss": 0.9559,
      "step": 270
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.9474,
      "step": 275
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 0.9705,
      "step": 280
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.1108381999010111e-05,
      "loss": 0.9541,
      "step": 285
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.0792499568567885e-05,
      "loss": 0.9464,
      "step": 290
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.0475819158237426e-05,
      "loss": 0.9634,
      "step": 295
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.015865963834808e-05,
      "loss": 0.9418,
      "step": 300
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.841340361651921e-06,
      "loss": 0.9425,
      "step": 305
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.524180841762577e-06,
      "loss": 0.945,
      "step": 310
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.207500431432115e-06,
      "loss": 0.9463,
      "step": 315
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.89161800098989e-06,
      "loss": 0.9514,
      "step": 320
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.576851617267151e-06,
      "loss": 0.937,
      "step": 325
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.9444,
      "step": 330
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.951933319348095e-06,
      "loss": 0.9529,
      "step": 335
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.642410644905726e-06,
      "loss": 0.9397,
      "step": 340
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.335261863099652e-06,
      "loss": 0.9284,
      "step": 345
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.0307962467172555e-06,
      "loss": 0.936,
      "step": 350
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.729320366825785e-06,
      "loss": 0.9419,
      "step": 355
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.431137784081283e-06,
      "loss": 0.9369,
      "step": 360
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.136548743068713e-06,
      "loss": 0.9404,
      "step": 365
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.845849869981137e-06,
      "loss": 0.9283,
      "step": 370
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.559333873942259e-06,
      "loss": 0.9346,
      "step": 375
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.277289252273175e-06,
      "loss": 0.927,
      "step": 380
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.9362,
      "step": 385
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.727745323894976e-06,
      "loss": 0.947,
      "step": 390
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.460799361338898e-06,
      "loss": 0.9318,
      "step": 395
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.19943090428802e-06,
      "loss": 0.924,
      "step": 400
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.943903128623336e-06,
      "loss": 0.9372,
      "step": 405
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.6944733291547784e-06,
      "loss": 0.9273,
      "step": 410
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.4513926605471504e-06,
      "loss": 0.9325,
      "step": 415
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.2149058844286796e-06,
      "loss": 0.9203,
      "step": 420
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.9852511229367862e-06,
      "loss": 0.9248,
      "step": 425
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7626596189492983e-06,
      "loss": 0.9276,
      "step": 430
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5473555032424534e-06,
      "loss": 0.9228,
      "step": 435
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.9284,
      "step": 440
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1394690525721275e-06,
      "loss": 0.9285,
      "step": 445
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.947297424689414e-06,
      "loss": 0.9314,
      "step": 450
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7632341857016733e-06,
      "loss": 0.9163,
      "step": 455
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.587464671688187e-06,
      "loss": 0.9263,
      "step": 460
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4201658676502294e-06,
      "loss": 0.9303,
      "step": 465
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2615062293021508e-06,
      "loss": 0.9202,
      "step": 470
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1116455134507665e-06,
      "loss": 0.9149,
      "step": 475
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.707346171337895e-07,
      "loss": 0.9147,
      "step": 480
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.389154256793042e-07,
      "loss": 0.9155,
      "step": 485
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.163206698392744e-07,
      "loss": 0.9227,
      "step": 490
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.9236,
      "step": 495
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.992888225905467e-07,
      "loss": 0.9196,
      "step": 500
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.0507026385502747e-07,
      "loss": 0.928,
      "step": 505
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.2051298603643754e-07,
      "loss": 0.9164,
      "step": 510
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.4570213114592957e-07,
      "loss": 0.9266,
      "step": 515
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8071302737293294e-07,
      "loss": 0.9243,
      "step": 520
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2561111323605714e-07,
      "loss": 0.9185,
      "step": 525
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.04518716920466e-08,
      "loss": 0.9124,
      "step": 530
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.528077426915412e-08,
      "loss": 0.9208,
      "step": 535
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.013323528115674e-08,
      "loss": 0.9314,
      "step": 540
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.034576168149175e-09,
      "loss": 0.9243,
      "step": 545
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.9241,
      "step": 550
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9343938231468201,
      "eval_runtime": 144.3354,
      "eval_samples_per_second": 107.479,
      "eval_steps_per_second": 1.684,
      "step": 550
    },
    {
      "epoch": 1.0,
      "step": 550,
      "total_flos": 460425862840320.0,
      "train_loss": 0.9703456902503967,
      "train_runtime": 5589.9273,
      "train_samples_per_second": 25.215,
      "train_steps_per_second": 0.098
    }
  ],
  "logging_steps": 5,
  "max_steps": 550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 460425862840320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}