{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992821249102656,
  "eval_steps": 500,
  "global_step": 696,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 1.7519,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.7506,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.7565,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.7016,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.6424,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.5629,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.4719,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.4184,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.3769,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012857142857142858,
      "loss": 1.3403,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.3172,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015714285714285716,
      "loss": 1.2753,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.2784,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.2564,
      "step": 65
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 1.2147,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001999685197404432,
      "loss": 1.1353,
      "step": 75
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019987409878190752,
      "loss": 1.0273,
      "step": 80
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019971679657231872,
      "loss": 1.0207,
      "step": 85
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019949671214996445,
      "loss": 1.0054,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019921398408113955,
      "loss": 0.9751,
      "step": 95
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019886879037290384,
      "loss": 0.9702,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019846134836100796,
      "loss": 0.9702,
      "step": 105
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019799191457305768,
      "loss": 0.9506,
      "step": 110
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001974607845670028,
      "loss": 0.938,
      "step": 115
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001968682927450523,
      "loss": 0.948,
      "step": 120
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019621481214313297,
      "loss": 0.9369,
      "step": 125
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019550075419602408,
      "loss": 0.9349,
      "step": 130
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019472656847831595,
      "loss": 0.9434,
      "step": 135
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001938927424213553,
      "loss": 0.933,
      "step": 140
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019299980100635612,
      "loss": 0.9293,
      "step": 145
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019204830643386868,
      "loss": 0.9368,
      "step": 150
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019103885776981515,
      "loss": 0.936,
      "step": 155
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018997209056831462,
      "loss": 0.9275,
      "step": 160
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018884867647153483,
      "loss": 0.9281,
      "step": 165
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000187669322786823,
      "loss": 0.9405,
      "step": 170
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018643477204138113,
      "loss": 0.9332,
      "step": 175
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001851458015147673,
      "loss": 0.9252,
      "step": 180
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001838032227495163,
      "loss": 0.9356,
      "step": 185
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018240788104018822,
      "loss": 0.9296,
      "step": 190
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001809606549011667,
      "loss": 0.9186,
      "step": 195
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017946245551354157,
      "loss": 0.9185,
      "step": 200
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017791422615142467,
      "loss": 0.9257,
      "step": 205
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017631694158805946,
      "loss": 0.9197,
      "step": 210
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017467160748209872,
      "loss": 0.9177,
      "step": 215
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017297925974443673,
      "loss": 0.9119,
      "step": 220
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017124096388599437,
      "loss": 0.9127,
      "step": 225
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016945781434686783,
      "loss": 0.9173,
      "step": 230
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016763093380726347,
      "loss": 0.9088,
      "step": 235
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016576147248065267,
      "loss": 0.9163,
      "step": 240
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001638506073895912,
      "loss": 0.9356,
      "step": 245
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016189954162466012,
      "loss": 0.9207,
      "step": 250
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001599095035869931,
      "loss": 0.8999,
      "step": 255
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015788174621486934,
      "loss": 0.9062,
      "step": 260
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015581754619485664,
      "loss": 0.9154,
      "step": 265
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015371820315800315,
      "loss": 0.9107,
      "step": 270
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001515850388615829,
      "loss": 0.9128,
      "step": 275
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014941939635691035,
      "loss": 0.9175,
      "step": 280
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001472226391437487,
      "loss": 0.912,
      "step": 285
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014499615031184296,
      "loss": 0.9009,
      "step": 290
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014274133167011975,
      "loss": 0.8795,
      "step": 295
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001404596028641009,
      "loss": 0.9032,
      "step": 300
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013815240048208752,
      "loss": 0.9191,
      "step": 305
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001358211771506763,
      "loss": 0.9191,
      "step": 310
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013346740062017838,
      "loss": 0.9069,
      "step": 315
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013109255284051615,
      "loss": 0.9149,
      "step": 320
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001286981290281798,
      "loss": 0.9084,
      "step": 325
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012628563672483146,
      "loss": 0.9009,
      "step": 330
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012385659484814883,
      "loss": 0.8942,
      "step": 335
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012141253273550696,
      "loss": 0.8829,
      "step": 340
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011895498918109944,
      "loss": 0.8982,
      "step": 345
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011648551146710556,
      "loss": 0.8976,
      "step": 350
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011400565438951343,
      "loss": 0.9095,
      "step": 355
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001115169792792124,
      "loss": 0.9031,
      "step": 360
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010902105301897098,
      "loss": 0.884,
      "step": 365
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001065194470569193,
      "loss": 0.9121,
      "step": 370
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010401373641715724,
      "loss": 0.9012,
      "step": 375
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010150549870811107,
      "loss": 0.8929,
      "step": 380
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.899631312926302e-05,
      "loss": 0.8894,
      "step": 385
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.648775947687912e-05,
      "loss": 0.897,
      "step": 390
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.398141714936103e-05,
      "loss": 0.9,
      "step": 395
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.147886415284903e-05,
      "loss": 0.9047,
      "step": 400
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.898167610770076e-05,
      "loss": 0.8909,
      "step": 405
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.649142525647272e-05,
      "loss": 0.8981,
      "step": 410
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.400967947402802e-05,
      "loss": 0.8939,
      "step": 415
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.153800128039441e-05,
      "loss": 0.897,
      "step": 420
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.907794685699346e-05,
      "loss": 0.8875,
      "step": 425
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.663106506686057e-05,
      "loss": 0.8817,
      "step": 430
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.419889647947293e-05,
      "loss": 0.8855,
      "step": 435
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.178297240079882e-05,
      "loss": 0.8979,
      "step": 440
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.938481390917966e-05,
      "loss": 0.9036,
      "step": 445
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.700593089765086e-05,
      "loss": 0.9007,
      "step": 450
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.46478211233056e-05,
      "loss": 0.892,
      "step": 455
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.231196926429913e-05,
      "loss": 0.8998,
      "step": 460
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.999984598508756e-05,
      "loss": 0.8866,
      "step": 465
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.7712907010490036e-05,
      "loss": 0.9021,
      "step": 470
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.54525922091568e-05,
      "loss": 0.8825,
      "step": 475
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.322032468702036e-05,
      "loss": 0.8957,
      "step": 480
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.1017509891300605e-05,
      "loss": 0.8824,
      "step": 485
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.8845534725628086e-05,
      "loss": 0.9008,
      "step": 490
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.6705766676842164e-05,
      "loss": 0.9084,
      "step": 495
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.4599552954014145e-05,
      "loss": 0.8933,
      "step": 500
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.252821964023757e-05,
      "loss": 0.8908,
      "step": 505
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.049307085771931e-05,
      "loss": 0.8978,
      "step": 510
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.849538794669767e-05,
      "loss": 0.9073,
      "step": 515
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.653642865870359e-05,
      "loss": 0.8674,
      "step": 520
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.461742636467409e-05,
      "loss": 0.8867,
      "step": 525
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.273958927841525e-05,
      "loss": 0.9034,
      "step": 530
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.090409969590468e-05,
      "loss": 0.8864,
      "step": 535
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.9112113250911844e-05,
      "loss": 0.8897,
      "step": 540
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7364758187404892e-05,
      "loss": 0.8996,
      "step": 545
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5663134649202647e-05,
      "loss": 0.8953,
      "step": 550
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.4008313987318053e-05,
      "loss": 0.8849,
      "step": 555
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2401338085430323e-05,
      "loss": 0.8805,
      "step": 560
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0843218703909194e-05,
      "loss": 0.8845,
      "step": 565
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.933493684280574e-05,
      "loss": 0.8797,
      "step": 570
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7877442124209454e-05,
      "loss": 0.8839,
      "step": 575
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.647165219436113e-05,
      "loss": 0.8952,
      "step": 580
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5118452145898331e-05,
      "loss": 0.8777,
      "step": 585
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3818693960596185e-05,
      "loss": 0.8757,
      "step": 590
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2573195972955365e-05,
      "loss": 0.9027,
      "step": 595
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1382742354974429e-05,
      "loss": 0.8923,
      "step": 600
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0248082622431087e-05,
      "loss": 0.889,
      "step": 605
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.169931162983137e-06,
      "loss": 0.9013,
      "step": 610
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.148966786386269e-06,
      "loss": 0.8847,
      "step": 615
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.185832297111938e-06,
      "loss": 0.8829,
      "step": 620
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.281134089634344e-06,
      "loss": 0.8866,
      "step": 625
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.435441766641369e-06,
      "loss": 0.8926,
      "step": 630
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.649287780409639e-06,
      "loss": 0.8915,
      "step": 635
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.923167097569935e-06,
      "loss": 0.8806,
      "step": 640
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.2575368874735446e-06,
      "loss": 0.8876,
      "step": 645
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.652816234356159e-06,
      "loss": 0.8796,
      "step": 650
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.109385873480141e-06,
      "loss": 0.8857,
      "step": 655
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6275879514217052e-06,
      "loss": 0.8826,
      "step": 660
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2077258106536925e-06,
      "loss": 0.8796,
      "step": 665
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.50063798559475e-07,
      "loss": 0.8886,
      "step": 670
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.54827100998534e-07,
      "loss": 0.8973,
      "step": 675
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.222016005282824e-07,
      "loss": 0.8975,
      "step": 680
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5233375937140358e-07,
      "loss": 0.8847,
      "step": 685
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.5330527202480654e-08,
      "loss": 0.8973,
      "step": 690
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.2592738119709958e-09,
      "loss": 0.8947,
      "step": 695
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8894284963607788,
      "eval_runtime": 454.212,
      "eval_samples_per_second": 1.367,
      "eval_steps_per_second": 0.172,
      "step": 696
    },
    {
      "epoch": 1.0,
      "step": 696,
      "total_flos": 8.836123491796255e+17,
      "train_loss": 0.9641761271090343,
      "train_runtime": 14026.4016,
      "train_samples_per_second": 0.397,
      "train_steps_per_second": 0.05
    }
  ],
  "logging_steps": 5,
  "max_steps": 696,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 8.836123491796255e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}