{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.686635944700461,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04608294930875576,
      "grad_norm": 5.774722576141357,
      "learning_rate": 4.999970619519374e-05,
      "loss": 0.9942,
      "num_input_tokens_seen": 6072,
      "step": 5
    },
    {
      "epoch": 0.09216589861751152,
      "grad_norm": 4.252433776855469,
      "learning_rate": 4.9998824787680656e-05,
      "loss": 0.6317,
      "num_input_tokens_seen": 11928,
      "step": 10
    },
    {
      "epoch": 0.1382488479262673,
      "grad_norm": 1.8097654581069946,
      "learning_rate": 4.999735579817769e-05,
      "loss": 0.305,
      "num_input_tokens_seen": 18040,
      "step": 15
    },
    {
      "epoch": 0.18433179723502305,
      "grad_norm": 2.511850118637085,
      "learning_rate": 4.9995299261212536e-05,
      "loss": 0.1734,
      "num_input_tokens_seen": 24016,
      "step": 20
    },
    {
      "epoch": 0.2304147465437788,
      "grad_norm": 4.347301006317139,
      "learning_rate": 4.999265522512283e-05,
      "loss": 0.2654,
      "num_input_tokens_seen": 29848,
      "step": 25
    },
    {
      "epoch": 0.2764976958525346,
      "grad_norm": 1.3125089406967163,
      "learning_rate": 4.998942375205502e-05,
      "loss": 0.1326,
      "num_input_tokens_seen": 35440,
      "step": 30
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 2.6110188961029053,
      "learning_rate": 4.998560491796287e-05,
      "loss": 0.0996,
      "num_input_tokens_seen": 41360,
      "step": 35
    },
    {
      "epoch": 0.3686635944700461,
      "grad_norm": 2.0633397102355957,
      "learning_rate": 4.998119881260576e-05,
      "loss": 0.1085,
      "num_input_tokens_seen": 47016,
      "step": 40
    },
    {
      "epoch": 0.4147465437788018,
      "grad_norm": 1.6892552375793457,
      "learning_rate": 4.997620553954645e-05,
      "loss": 0.1384,
      "num_input_tokens_seen": 53056,
      "step": 45
    },
    {
      "epoch": 0.4608294930875576,
      "grad_norm": 2.2047786712646484,
      "learning_rate": 4.997062521614876e-05,
      "loss": 0.1176,
      "num_input_tokens_seen": 58952,
      "step": 50
    },
    {
      "epoch": 0.5069124423963134,
      "grad_norm": 2.8315374851226807,
      "learning_rate": 4.996445797357477e-05,
      "loss": 0.0888,
      "num_input_tokens_seen": 64760,
      "step": 55
    },
    {
      "epoch": 0.5529953917050692,
      "grad_norm": 2.423229932785034,
      "learning_rate": 4.995770395678171e-05,
      "loss": 0.0812,
      "num_input_tokens_seen": 70672,
      "step": 60
    },
    {
      "epoch": 0.5990783410138248,
      "grad_norm": 2.2459795475006104,
      "learning_rate": 4.9950363324518584e-05,
      "loss": 0.1233,
      "num_input_tokens_seen": 76608,
      "step": 65
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 2.267782211303711,
      "learning_rate": 4.9942436249322444e-05,
      "loss": 0.1446,
      "num_input_tokens_seen": 82336,
      "step": 70
    },
    {
      "epoch": 0.6912442396313364,
      "grad_norm": 2.2236413955688477,
      "learning_rate": 4.993392291751431e-05,
      "loss": 0.0736,
      "num_input_tokens_seen": 88120,
      "step": 75
    },
    {
      "epoch": 0.7373271889400922,
      "grad_norm": 1.833316683769226,
      "learning_rate": 4.99248235291948e-05,
      "loss": 0.1129,
      "num_input_tokens_seen": 93808,
      "step": 80
    },
    {
      "epoch": 0.783410138248848,
      "grad_norm": 2.8768177032470703,
      "learning_rate": 4.991513829823945e-05,
      "loss": 0.1426,
      "num_input_tokens_seen": 99928,
      "step": 85
    },
    {
      "epoch": 0.8294930875576036,
      "grad_norm": 2.096641778945923,
      "learning_rate": 4.990486745229364e-05,
      "loss": 0.1401,
      "num_input_tokens_seen": 106288,
      "step": 90
    },
    {
      "epoch": 0.8755760368663594,
      "grad_norm": 2.371711492538452,
      "learning_rate": 4.9894011232767294e-05,
      "loss": 0.1127,
      "num_input_tokens_seen": 112136,
      "step": 95
    },
    {
      "epoch": 0.9216589861751152,
      "grad_norm": 0.6439377665519714,
      "learning_rate": 4.9882569894829144e-05,
      "loss": 0.0524,
      "num_input_tokens_seen": 117936,
      "step": 100
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 2.412799835205078,
      "learning_rate": 4.987054370740083e-05,
      "loss": 0.0728,
      "num_input_tokens_seen": 124152,
      "step": 105
    },
    {
      "epoch": 1.0138248847926268,
      "grad_norm": 2.985877513885498,
      "learning_rate": 4.9857932953150465e-05,
      "loss": 0.0449,
      "num_input_tokens_seen": 129872,
      "step": 110
    },
    {
      "epoch": 1.0599078341013826,
      "grad_norm": 3.5899670124053955,
      "learning_rate": 4.984473792848607e-05,
      "loss": 0.0506,
      "num_input_tokens_seen": 136080,
      "step": 115
    },
    {
      "epoch": 1.1059907834101383,
      "grad_norm": 2.940323829650879,
      "learning_rate": 4.983095894354858e-05,
      "loss": 0.0431,
      "num_input_tokens_seen": 141712,
      "step": 120
    },
    {
      "epoch": 1.1520737327188941,
      "grad_norm": 2.948409080505371,
      "learning_rate": 4.981659632220455e-05,
      "loss": 0.0318,
      "num_input_tokens_seen": 147544,
      "step": 125
    },
    {
      "epoch": 1.1981566820276497,
      "grad_norm": 1.2344759702682495,
      "learning_rate": 4.9801650402038555e-05,
      "loss": 0.0593,
      "num_input_tokens_seen": 153344,
      "step": 130
    },
    {
      "epoch": 1.2442396313364055,
      "grad_norm": 3.271662473678589,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 0.0617,
      "num_input_tokens_seen": 159160,
      "step": 135
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 3.5447471141815186,
      "learning_rate": 4.977001008412113e-05,
      "loss": 0.0456,
      "num_input_tokens_seen": 164760,
      "step": 140
    },
    {
      "epoch": 1.336405529953917,
      "grad_norm": 4.001632213592529,
      "learning_rate": 4.9753316430055894e-05,
      "loss": 0.068,
      "num_input_tokens_seen": 170624,
      "step": 145
    },
    {
      "epoch": 1.3824884792626728,
      "grad_norm": 1.6239632368087769,
      "learning_rate": 4.973604096452361e-05,
      "loss": 0.0383,
      "num_input_tokens_seen": 176480,
      "step": 150
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.19192902743816376,
      "learning_rate": 4.9718184093573475e-05,
      "loss": 0.0351,
      "num_input_tokens_seen": 182056,
      "step": 155
    },
    {
      "epoch": 1.4746543778801844,
      "grad_norm": 3.1995279788970947,
      "learning_rate": 4.969974623692023e-05,
      "loss": 0.1139,
      "num_input_tokens_seen": 188032,
      "step": 160
    },
    {
      "epoch": 1.52073732718894,
      "grad_norm": 2.926187038421631,
      "learning_rate": 4.9680727827934354e-05,
      "loss": 0.0738,
      "num_input_tokens_seen": 194112,
      "step": 165
    },
    {
      "epoch": 1.5668202764976957,
      "grad_norm": 1.8316713571548462,
      "learning_rate": 4.966112931363185e-05,
      "loss": 0.0567,
      "num_input_tokens_seen": 200368,
      "step": 170
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 2.283552885055542,
      "learning_rate": 4.964095115466373e-05,
      "loss": 0.0793,
      "num_input_tokens_seen": 206520,
      "step": 175
    },
    {
      "epoch": 1.6589861751152073,
      "grad_norm": 2.575171709060669,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.0564,
      "num_input_tokens_seen": 212328,
      "step": 180
    },
    {
      "epoch": 1.705069124423963,
      "grad_norm": 3.201814651489258,
      "learning_rate": 4.959885781344452e-05,
      "loss": 0.0677,
      "num_input_tokens_seen": 218456,
      "step": 185
    },
    {
      "epoch": 1.7511520737327189,
      "grad_norm": 2.607283592224121,
      "learning_rate": 4.9576943620571507e-05,
      "loss": 0.0474,
      "num_input_tokens_seen": 224240,
      "step": 190
    },
    {
      "epoch": 1.7972350230414746,
      "grad_norm": 1.2559226751327515,
      "learning_rate": 4.9554451761765766e-05,
      "loss": 0.053,
      "num_input_tokens_seen": 230456,
      "step": 195
    },
    {
      "epoch": 1.8433179723502304,
      "grad_norm": 1.7003673315048218,
      "learning_rate": 4.953138276568462e-05,
      "loss": 0.0477,
      "num_input_tokens_seen": 236448,
      "step": 200
    },
    {
      "epoch": 1.8894009216589862,
      "grad_norm": 2.2908496856689453,
      "learning_rate": 4.950773717455061e-05,
      "loss": 0.0581,
      "num_input_tokens_seen": 242536,
      "step": 205
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 3.7818005084991455,
      "learning_rate": 4.948351554413879e-05,
      "loss": 0.0583,
      "num_input_tokens_seen": 248352,
      "step": 210
    },
    {
      "epoch": 1.9815668202764978,
      "grad_norm": 1.7777669429779053,
      "learning_rate": 4.945871844376369e-05,
      "loss": 0.0245,
      "num_input_tokens_seen": 253928,
      "step": 215
    },
    {
      "epoch": 2.0276497695852536,
      "grad_norm": 1.5329607725143433,
      "learning_rate": 4.94333464562659e-05,
      "loss": 0.0354,
      "num_input_tokens_seen": 259904,
      "step": 220
    },
    {
      "epoch": 2.0737327188940093,
      "grad_norm": 2.1847078800201416,
      "learning_rate": 4.940740017799833e-05,
      "loss": 0.0352,
      "num_input_tokens_seen": 265656,
      "step": 225
    },
    {
      "epoch": 2.119815668202765,
      "grad_norm": 1.6991156339645386,
      "learning_rate": 4.938088021881233e-05,
      "loss": 0.0416,
      "num_input_tokens_seen": 271576,
      "step": 230
    },
    {
      "epoch": 2.165898617511521,
      "grad_norm": 3.675462484359741,
      "learning_rate": 4.935378720204319e-05,
      "loss": 0.047,
      "num_input_tokens_seen": 277464,
      "step": 235
    },
    {
      "epoch": 2.2119815668202767,
      "grad_norm": 1.8100879192352295,
      "learning_rate": 4.9326121764495596e-05,
      "loss": 0.0454,
      "num_input_tokens_seen": 283592,
      "step": 240
    },
    {
      "epoch": 2.258064516129032,
      "grad_norm": 2.6867613792419434,
      "learning_rate": 4.929788455642864e-05,
      "loss": 0.0647,
      "num_input_tokens_seen": 289544,
      "step": 245
    },
    {
      "epoch": 2.3041474654377883,
      "grad_norm": 0.8391556143760681,
      "learning_rate": 4.9269076241540505e-05,
      "loss": 0.0283,
      "num_input_tokens_seen": 295480,
      "step": 250
    },
    {
      "epoch": 2.3502304147465436,
      "grad_norm": 3.0261058807373047,
      "learning_rate": 4.92396974969529e-05,
      "loss": 0.0301,
      "num_input_tokens_seen": 301680,
      "step": 255
    },
    {
      "epoch": 2.3963133640552994,
      "grad_norm": 1.320726990699768,
      "learning_rate": 4.920974901319515e-05,
      "loss": 0.0416,
      "num_input_tokens_seen": 307768,
      "step": 260
    },
    {
      "epoch": 2.442396313364055,
      "grad_norm": 3.625941753387451,
      "learning_rate": 4.917923149418792e-05,
      "loss": 0.0504,
      "num_input_tokens_seen": 313376,
      "step": 265
    },
    {
      "epoch": 2.488479262672811,
      "grad_norm": 1.6434024572372437,
      "learning_rate": 4.914814565722671e-05,
      "loss": 0.0499,
      "num_input_tokens_seen": 319592,
      "step": 270
    },
    {
      "epoch": 2.5345622119815667,
      "grad_norm": 2.392733573913574,
      "learning_rate": 4.911649223296499e-05,
      "loss": 0.03,
      "num_input_tokens_seen": 325392,
      "step": 275
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 3.644463539123535,
      "learning_rate": 4.9084271965397014e-05,
      "loss": 0.0416,
      "num_input_tokens_seen": 331264,
      "step": 280
    },
    {
      "epoch": 2.6267281105990783,
      "grad_norm": 1.160701870918274,
      "learning_rate": 4.905148561184033e-05,
      "loss": 0.0639,
      "num_input_tokens_seen": 337584,
      "step": 285
    },
    {
      "epoch": 2.672811059907834,
      "grad_norm": 2.189955711364746,
      "learning_rate": 4.901813394291801e-05,
      "loss": 0.048,
      "num_input_tokens_seen": 343632,
      "step": 290
    },
    {
      "epoch": 2.71889400921659,
      "grad_norm": 2.4015591144561768,
      "learning_rate": 4.898421774254051e-05,
      "loss": 0.0465,
      "num_input_tokens_seen": 349392,
      "step": 295
    },
    {
      "epoch": 2.7649769585253456,
      "grad_norm": 1.5051063299179077,
      "learning_rate": 4.894973780788722e-05,
      "loss": 0.0512,
      "num_input_tokens_seen": 355104,
      "step": 300
    },
    {
      "epoch": 2.8110599078341014,
      "grad_norm": 2.82021427154541,
      "learning_rate": 4.891469494938781e-05,
      "loss": 0.0412,
      "num_input_tokens_seen": 360824,
      "step": 305
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 1.578285574913025,
      "learning_rate": 4.887908999070308e-05,
      "loss": 0.0292,
      "num_input_tokens_seen": 366792,
      "step": 310
    },
    {
      "epoch": 2.903225806451613,
      "grad_norm": 2.392061710357666,
      "learning_rate": 4.884292376870567e-05,
      "loss": 0.0264,
      "num_input_tokens_seen": 372536,
      "step": 315
    },
    {
      "epoch": 2.9493087557603688,
      "grad_norm": 0.46661177277565,
      "learning_rate": 4.880619713346039e-05,
      "loss": 0.0402,
      "num_input_tokens_seen": 378472,
      "step": 320
    },
    {
      "epoch": 2.9953917050691246,
      "grad_norm": 2.8422093391418457,
      "learning_rate": 4.876891094820417e-05,
      "loss": 0.0214,
      "num_input_tokens_seen": 383984,
      "step": 325
    },
    {
      "epoch": 3.0414746543778803,
      "grad_norm": 1.581181526184082,
      "learning_rate": 4.873106608932585e-05,
      "loss": 0.0536,
      "num_input_tokens_seen": 389896,
      "step": 330
    },
    {
      "epoch": 3.087557603686636,
      "grad_norm": 2.1210877895355225,
      "learning_rate": 4.869266344634556e-05,
      "loss": 0.0295,
      "num_input_tokens_seen": 395848,
      "step": 335
    },
    {
      "epoch": 3.133640552995392,
      "grad_norm": 0.6473267078399658,
      "learning_rate": 4.8653703921893766e-05,
      "loss": 0.0209,
      "num_input_tokens_seen": 401784,
      "step": 340
    },
    {
      "epoch": 3.1797235023041477,
      "grad_norm": 3.651721239089966,
      "learning_rate": 4.8614188431690125e-05,
      "loss": 0.0348,
      "num_input_tokens_seen": 407656,
      "step": 345
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 1.2039521932601929,
      "learning_rate": 4.85741179045219e-05,
      "loss": 0.0167,
      "num_input_tokens_seen": 413344,
      "step": 350
    },
    {
      "epoch": 3.271889400921659,
      "grad_norm": 2.5414485931396484,
      "learning_rate": 4.853349328222219e-05,
      "loss": 0.0567,
      "num_input_tokens_seen": 419112,
      "step": 355
    },
    {
      "epoch": 3.3179723502304146,
      "grad_norm": 0.12772409617900848,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.0483,
      "num_input_tokens_seen": 425104,
      "step": 360
    },
    {
      "epoch": 3.3640552995391704,
      "grad_norm": 1.686139702796936,
      "learning_rate": 4.845058558465645e-05,
      "loss": 0.0379,
      "num_input_tokens_seen": 430920,
      "step": 365
    },
    {
      "epoch": 3.410138248847926,
      "grad_norm": 1.3768738508224487,
      "learning_rate": 4.840830445808483e-05,
      "loss": 0.0447,
      "num_input_tokens_seen": 436864,
      "step": 370
    },
    {
      "epoch": 3.456221198156682,
      "grad_norm": 1.8329992294311523,
      "learning_rate": 4.836547313372471e-05,
      "loss": 0.0417,
      "num_input_tokens_seen": 442880,
      "step": 375
    },
    {
      "epoch": 3.5023041474654377,
      "grad_norm": 2.0811145305633545,
      "learning_rate": 4.832209261830002e-05,
      "loss": 0.0368,
      "num_input_tokens_seen": 448536,
      "step": 380
    },
    {
      "epoch": 3.5483870967741935,
      "grad_norm": 0.14438925683498383,
      "learning_rate": 4.827816393144305e-05,
      "loss": 0.0269,
      "num_input_tokens_seen": 454664,
      "step": 385
    },
    {
      "epoch": 3.5944700460829493,
      "grad_norm": 2.131544828414917,
      "learning_rate": 4.823368810567056e-05,
      "loss": 0.0387,
      "num_input_tokens_seen": 460584,
      "step": 390
    },
    {
      "epoch": 3.640552995391705,
      "grad_norm": 2.2278664112091064,
      "learning_rate": 4.818866618635947e-05,
      "loss": 0.0365,
      "num_input_tokens_seen": 466352,
      "step": 395
    },
    {
      "epoch": 3.686635944700461,
      "grad_norm": 0.2778138220310211,
      "learning_rate": 4.814309923172227e-05,
      "loss": 0.0394,
      "num_input_tokens_seen": 472288,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 3240,
  "num_input_tokens_seen": 472288,
  "num_train_epochs": 30,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5598346769498112.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}