{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8561484918793503,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02320185614849188,
      "grad_norm": 26.745355095184312,
      "learning_rate": 5e-07,
      "loss": 1.6569,
      "step": 5
    },
    {
      "epoch": 0.04640371229698376,
      "grad_norm": 13.080188660738868,
      "learning_rate": 1e-06,
      "loss": 1.5099,
      "step": 10
    },
    {
      "epoch": 0.06960556844547564,
      "grad_norm": 7.775505635686351,
      "learning_rate": 9.998470286265414e-07,
      "loss": 1.2782,
      "step": 15
    },
    {
      "epoch": 0.09280742459396751,
      "grad_norm": 6.492859712313467,
      "learning_rate": 9.993882081071305e-07,
      "loss": 1.2359,
      "step": 20
    },
    {
      "epoch": 0.11600928074245939,
      "grad_norm": 5.355551984540261,
      "learning_rate": 9.986238191873872e-07,
      "loss": 1.204,
      "step": 25
    },
    {
      "epoch": 0.13921113689095127,
      "grad_norm": 5.125393165293572,
      "learning_rate": 9.975543295858033e-07,
      "loss": 1.1627,
      "step": 30
    },
    {
      "epoch": 0.16241299303944315,
      "grad_norm": 4.710071299991241,
      "learning_rate": 9.961803937075514e-07,
      "loss": 1.1463,
      "step": 35
    },
    {
      "epoch": 0.18561484918793503,
      "grad_norm": 5.029376799191572,
      "learning_rate": 9.945028522440653e-07,
      "loss": 1.1394,
      "step": 40
    },
    {
      "epoch": 0.2088167053364269,
      "grad_norm": 4.763291242870039,
      "learning_rate": 9.925227316586314e-07,
      "loss": 1.1371,
      "step": 45
    },
    {
      "epoch": 0.23201856148491878,
      "grad_norm": 4.903033982523367,
      "learning_rate": 9.902412435583125e-07,
      "loss": 1.1181,
      "step": 50
    },
    {
      "epoch": 0.23201856148491878,
      "eval_loss": 1.1214605569839478,
      "eval_runtime": 105.8329,
      "eval_samples_per_second": 57.912,
      "eval_steps_per_second": 0.907,
      "step": 50
    },
    {
      "epoch": 0.2552204176334107,
      "grad_norm": 4.785575700738186,
      "learning_rate": 9.876597839525813e-07,
      "loss": 1.1163,
      "step": 55
    },
    {
      "epoch": 0.27842227378190254,
      "grad_norm": 4.600727000401806,
      "learning_rate": 9.847799323991233e-07,
      "loss": 1.1232,
      "step": 60
    },
    {
      "epoch": 0.30162412993039445,
      "grad_norm": 4.8200416840356315,
      "learning_rate": 9.816034510373285e-07,
      "loss": 1.125,
      "step": 65
    },
    {
      "epoch": 0.3248259860788863,
      "grad_norm": 4.958997518359378,
      "learning_rate": 9.781322835100637e-07,
      "loss": 1.108,
      "step": 70
    },
    {
      "epoch": 0.3480278422273782,
      "grad_norm": 4.883541365508776,
      "learning_rate": 9.743685537743856e-07,
      "loss": 1.106,
      "step": 75
    },
    {
      "epoch": 0.37122969837587005,
      "grad_norm": 4.973507458353338,
      "learning_rate": 9.70314564801922e-07,
      "loss": 1.0973,
      "step": 80
    },
    {
      "epoch": 0.39443155452436196,
      "grad_norm": 4.704415990191669,
      "learning_rate": 9.659727971697173e-07,
      "loss": 1.0964,
      "step": 85
    },
    {
      "epoch": 0.4176334106728538,
      "grad_norm": 4.759885977268913,
      "learning_rate": 9.613459075424033e-07,
      "loss": 1.0956,
      "step": 90
    },
    {
      "epoch": 0.4408352668213457,
      "grad_norm": 4.868535908803129,
      "learning_rate": 9.564367270466245e-07,
      "loss": 1.0787,
      "step": 95
    },
    {
      "epoch": 0.46403712296983757,
      "grad_norm": 5.180286116736628,
      "learning_rate": 9.51248259538713e-07,
      "loss": 1.0765,
      "step": 100
    },
    {
      "epoch": 0.46403712296983757,
      "eval_loss": 1.0775035619735718,
      "eval_runtime": 105.5293,
      "eval_samples_per_second": 58.079,
      "eval_steps_per_second": 0.91,
      "step": 100
    },
    {
      "epoch": 0.4872389791183295,
      "grad_norm": 5.290465762761348,
      "learning_rate": 9.457836797666721e-07,
      "loss": 1.0903,
      "step": 105
    },
    {
      "epoch": 0.5104408352668214,
      "grad_norm": 4.81291157554945,
      "learning_rate": 9.400463314275941e-07,
      "loss": 1.0697,
      "step": 110
    },
    {
      "epoch": 0.5336426914153132,
      "grad_norm": 4.914554202012043,
      "learning_rate": 9.340397251217008e-07,
      "loss": 1.0668,
      "step": 115
    },
    {
      "epoch": 0.5568445475638051,
      "grad_norm": 5.240457841494325,
      "learning_rate": 9.27767536204258e-07,
      "loss": 1.0676,
      "step": 120
    },
    {
      "epoch": 0.580046403712297,
      "grad_norm": 4.957459385263701,
      "learning_rate": 9.212336025366787e-07,
      "loss": 1.0746,
      "step": 125
    },
    {
      "epoch": 0.6032482598607889,
      "grad_norm": 5.29032668711839,
      "learning_rate": 9.144419221381918e-07,
      "loss": 1.0724,
      "step": 130
    },
    {
      "epoch": 0.6264501160092807,
      "grad_norm": 4.908560953587426,
      "learning_rate": 9.073966507395121e-07,
      "loss": 1.0745,
      "step": 135
    },
    {
      "epoch": 0.6496519721577726,
      "grad_norm": 4.912842113728852,
      "learning_rate": 9.001020992400085e-07,
      "loss": 1.0559,
      "step": 140
    },
    {
      "epoch": 0.6728538283062645,
      "grad_norm": 5.088585906783296,
      "learning_rate": 8.925627310699274e-07,
      "loss": 1.0705,
      "step": 145
    },
    {
      "epoch": 0.6960556844547564,
      "grad_norm": 5.140684832177941,
      "learning_rate": 8.84783159459285e-07,
      "loss": 1.0639,
      "step": 150
    },
    {
      "epoch": 0.6960556844547564,
      "eval_loss": 1.0501643419265747,
      "eval_runtime": 105.4561,
      "eval_samples_per_second": 58.119,
      "eval_steps_per_second": 0.91,
      "step": 150
    },
    {
      "epoch": 0.7192575406032483,
      "grad_norm": 5.311257433234373,
      "learning_rate": 8.767681446150976e-07,
      "loss": 1.0472,
      "step": 155
    },
    {
      "epoch": 0.7424593967517401,
      "grad_norm": 5.091539509688025,
      "learning_rate": 8.68522590808682e-07,
      "loss": 1.0645,
      "step": 160
    },
    {
      "epoch": 0.765661252900232,
      "grad_norm": 5.132013982763288,
      "learning_rate": 8.600515433748001e-07,
      "loss": 1.0416,
      "step": 165
    },
    {
      "epoch": 0.7888631090487239,
      "grad_norm": 4.753354098230195,
      "learning_rate": 8.51360185624495e-07,
      "loss": 1.0478,
      "step": 170
    },
    {
      "epoch": 0.8120649651972158,
      "grad_norm": 5.029473978539478,
      "learning_rate": 8.424538356734956e-07,
      "loss": 1.0383,
      "step": 175
    },
    {
      "epoch": 0.8352668213457076,
      "grad_norm": 4.9588553004593345,
      "learning_rate": 8.333379431881397e-07,
      "loss": 1.0342,
      "step": 180
    },
    {
      "epoch": 0.8584686774941995,
      "grad_norm": 5.234591483099779,
      "learning_rate": 8.240180860508026e-07,
      "loss": 1.0413,
      "step": 185
    },
    {
      "epoch": 0.8816705336426914,
      "grad_norm": 5.121566469508508,
      "learning_rate": 8.144999669468713e-07,
      "loss": 1.0264,
      "step": 190
    },
    {
      "epoch": 0.9048723897911833,
      "grad_norm": 5.0479045768726305,
      "learning_rate": 8.047894098753539e-07,
      "loss": 1.028,
      "step": 195
    },
    {
      "epoch": 0.9280742459396751,
      "grad_norm": 5.0838098259091185,
      "learning_rate": 7.948923565852597e-07,
      "loss": 1.0308,
      "step": 200
    },
    {
      "epoch": 0.9280742459396751,
      "eval_loss": 1.0281875133514404,
      "eval_runtime": 105.8568,
      "eval_samples_per_second": 57.899,
      "eval_steps_per_second": 0.907,
      "step": 200
    },
    {
      "epoch": 0.951276102088167,
      "grad_norm": 5.3244675969022826,
      "learning_rate": 7.848148629399285e-07,
      "loss": 1.0262,
      "step": 205
    },
    {
      "epoch": 0.974477958236659,
      "grad_norm": 4.9307215762355305,
      "learning_rate": 7.745630952115363e-07,
      "loss": 1.0349,
      "step": 210
    },
    {
      "epoch": 0.9976798143851509,
      "grad_norm": 4.994203203030838,
      "learning_rate": 7.641433263080418e-07,
      "loss": 1.0216,
      "step": 215
    },
    {
      "epoch": 1.0208816705336428,
      "grad_norm": 5.112958880673586,
      "learning_rate": 7.535619319348865e-07,
      "loss": 0.9241,
      "step": 220
    },
    {
      "epoch": 1.0440835266821347,
      "grad_norm": 5.264187445397404,
      "learning_rate": 7.428253866937918e-07,
      "loss": 0.9001,
      "step": 225
    },
    {
      "epoch": 1.0672853828306264,
      "grad_norm": 5.645584402922182,
      "learning_rate": 7.319402601210447e-07,
      "loss": 0.8916,
      "step": 230
    },
    {
      "epoch": 1.0904872389791183,
      "grad_norm": 5.655360994963379,
      "learning_rate": 7.209132126676933e-07,
      "loss": 0.8876,
      "step": 235
    },
    {
      "epoch": 1.1136890951276102,
      "grad_norm": 5.3773890810778795,
      "learning_rate": 7.097509916241145e-07,
      "loss": 0.8931,
      "step": 240
    },
    {
      "epoch": 1.136890951276102,
      "grad_norm": 5.658881203794,
      "learning_rate": 6.984604269914436e-07,
      "loss": 0.905,
      "step": 245
    },
    {
      "epoch": 1.160092807424594,
      "grad_norm": 5.966282577193694,
      "learning_rate": 6.870484273023967e-07,
      "loss": 0.9038,
      "step": 250
    },
    {
      "epoch": 1.160092807424594,
      "eval_loss": 1.0220295190811157,
      "eval_runtime": 105.8362,
      "eval_samples_per_second": 57.91,
      "eval_steps_per_second": 0.907,
      "step": 250
    },
    {
      "epoch": 1.1832946635730859,
      "grad_norm": 5.794176185315156,
      "learning_rate": 6.755219753940388e-07,
      "loss": 0.8964,
      "step": 255
    },
    {
      "epoch": 1.2064965197215778,
      "grad_norm": 6.603391500331007,
      "learning_rate": 6.638881241350883e-07,
      "loss": 0.8898,
      "step": 260
    },
    {
      "epoch": 1.2296983758700697,
      "grad_norm": 5.5914639272443205,
      "learning_rate": 6.52153992110368e-07,
      "loss": 0.8951,
      "step": 265
    },
    {
      "epoch": 1.2529002320185616,
      "grad_norm": 5.339661007608592,
      "learning_rate": 6.403267592650466e-07,
      "loss": 0.8961,
      "step": 270
    },
    {
      "epoch": 1.2761020881670533,
      "grad_norm": 5.448280965038798,
      "learning_rate": 6.28413662511334e-07,
      "loss": 0.8919,
      "step": 275
    },
    {
      "epoch": 1.2993039443155452,
      "grad_norm": 5.476822697700394,
      "learning_rate": 6.164219913003207e-07,
      "loss": 0.8931,
      "step": 280
    },
    {
      "epoch": 1.322505800464037,
      "grad_norm": 5.783548079343189,
      "learning_rate": 6.043590831616676e-07,
      "loss": 0.8792,
      "step": 285
    },
    {
      "epoch": 1.345707656612529,
      "grad_norm": 5.59782698134665,
      "learning_rate": 5.92232319213878e-07,
      "loss": 0.8768,
      "step": 290
    },
    {
      "epoch": 1.368909512761021,
      "grad_norm": 5.193853086769952,
      "learning_rate": 5.800491196478988e-07,
      "loss": 0.8788,
      "step": 295
    },
    {
      "epoch": 1.3921113689095128,
      "grad_norm": 5.539347488257,
      "learning_rate": 5.678169391868127e-07,
      "loss": 0.8973,
      "step": 300
    },
    {
      "epoch": 1.3921113689095128,
      "eval_loss": 1.0114275217056274,
      "eval_runtime": 106.216,
      "eval_samples_per_second": 57.703,
      "eval_steps_per_second": 0.904,
      "step": 300
    },
    {
      "epoch": 1.4153132250580047,
      "grad_norm": 5.567338787725618,
      "learning_rate": 5.555432625244023e-07,
      "loss": 0.8831,
      "step": 305
    },
    {
      "epoch": 1.4385150812064964,
      "grad_norm": 5.412598997121907,
      "learning_rate": 5.432355997453728e-07,
      "loss": 0.8848,
      "step": 310
    },
    {
      "epoch": 1.4617169373549883,
      "grad_norm": 5.4356510240439775,
      "learning_rate": 5.309014817300421e-07,
      "loss": 0.8999,
      "step": 315
    },
    {
      "epoch": 1.4849187935034802,
      "grad_norm": 5.525607667062919,
      "learning_rate": 5.185484555463026e-07,
      "loss": 0.8901,
      "step": 320
    },
    {
      "epoch": 1.5081206496519721,
      "grad_norm": 5.583006624663847,
      "learning_rate": 5.061840798316814e-07,
      "loss": 0.8909,
      "step": 325
    },
    {
      "epoch": 1.531322505800464,
      "grad_norm": 5.822776934487761,
      "learning_rate": 4.938159201683186e-07,
      "loss": 0.8829,
      "step": 330
    },
    {
      "epoch": 1.554524361948956,
      "grad_norm": 5.427885443572571,
      "learning_rate": 4.814515444536974e-07,
      "loss": 0.8867,
      "step": 335
    },
    {
      "epoch": 1.5777262180974478,
      "grad_norm": 5.513594905050496,
      "learning_rate": 4.69098518269958e-07,
      "loss": 0.892,
      "step": 340
    },
    {
      "epoch": 1.6009280742459397,
      "grad_norm": 5.785273130658459,
      "learning_rate": 4.5676440025462726e-07,
      "loss": 0.8775,
      "step": 345
    },
    {
      "epoch": 1.6241299303944317,
      "grad_norm": 5.494906178164733,
      "learning_rate": 4.444567374755977e-07,
      "loss": 0.8747,
      "step": 350
    },
    {
      "epoch": 1.6241299303944317,
      "eval_loss": 1.0039345026016235,
      "eval_runtime": 105.8025,
      "eval_samples_per_second": 57.929,
      "eval_steps_per_second": 0.907,
      "step": 350
    },
    {
      "epoch": 1.6473317865429236,
      "grad_norm": 5.49251321009188,
      "learning_rate": 4.3218306081318713e-07,
      "loss": 0.884,
      "step": 355
    },
    {
      "epoch": 1.6705336426914155,
      "grad_norm": 5.618196571147986,
      "learning_rate": 4.199508803521012e-07,
      "loss": 0.8945,
      "step": 360
    },
    {
      "epoch": 1.6937354988399071,
      "grad_norm": 5.908619967180135,
      "learning_rate": 4.0776768078612207e-07,
      "loss": 0.8793,
      "step": 365
    },
    {
      "epoch": 1.716937354988399,
      "grad_norm": 5.822870470090775,
      "learning_rate": 3.9564091683833244e-07,
      "loss": 0.8785,
      "step": 370
    },
    {
      "epoch": 1.740139211136891,
      "grad_norm": 5.685661727934108,
      "learning_rate": 3.835780086996793e-07,
      "loss": 0.8772,
      "step": 375
    },
    {
      "epoch": 1.7633410672853829,
      "grad_norm": 5.692617224399981,
      "learning_rate": 3.7158633748866607e-07,
      "loss": 0.8701,
      "step": 380
    },
    {
      "epoch": 1.7865429234338746,
      "grad_norm": 5.6393286368292355,
      "learning_rate": 3.596732407349536e-07,
      "loss": 0.871,
      "step": 385
    },
    {
      "epoch": 1.8097447795823665,
      "grad_norm": 5.672110777773612,
      "learning_rate": 3.4784600788963193e-07,
      "loss": 0.8751,
      "step": 390
    },
    {
      "epoch": 1.8329466357308584,
      "grad_norm": 5.835389029793195,
      "learning_rate": 3.3611187586491157e-07,
      "loss": 0.8687,
      "step": 395
    },
    {
      "epoch": 1.8561484918793503,
      "grad_norm": 5.386053225084359,
      "learning_rate": 3.244780246059612e-07,
      "loss": 0.8818,
      "step": 400
    },
    {
      "epoch": 1.8561484918793503,
      "eval_loss": 0.996471107006073,
      "eval_runtime": 105.8008,
      "eval_samples_per_second": 57.93,
      "eval_steps_per_second": 0.907,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2358347349098496.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}