{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9734513274336285,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0058997050147492625,
      "grad_norm": 1.106083567904979,
      "learning_rate": 1.1764705882352942e-07,
      "loss": 0.7816,
      "step": 1
    },
    {
      "epoch": 0.029498525073746312,
      "grad_norm": 1.1433080381542629,
      "learning_rate": 5.882352941176471e-07,
      "loss": 0.7757,
      "step": 5
    },
    {
      "epoch": 0.058997050147492625,
      "grad_norm": 0.997014214705184,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 0.7736,
      "step": 10
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 1.304994737635826,
      "learning_rate": 1.7647058823529414e-06,
      "loss": 0.7594,
      "step": 15
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 0.5741459890364078,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.7332,
      "step": 20
    },
    {
      "epoch": 0.14749262536873156,
      "grad_norm": 0.4736057964790196,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 0.7054,
      "step": 25
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 0.28699264838960103,
      "learning_rate": 3.529411764705883e-06,
      "loss": 0.6613,
      "step": 30
    },
    {
      "epoch": 0.20648967551622419,
      "grad_norm": 1.92856903253004,
      "learning_rate": 4.11764705882353e-06,
      "loss": 0.6422,
      "step": 35
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 0.346137515731761,
      "learning_rate": 4.705882352941177e-06,
      "loss": 0.6165,
      "step": 40
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 0.17870145514430266,
      "learning_rate": 5.294117647058824e-06,
      "loss": 0.6133,
      "step": 45
    },
    {
      "epoch": 0.2949852507374631,
      "grad_norm": 0.1437606973005659,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.5986,
      "step": 50
    },
    {
      "epoch": 0.32448377581120946,
      "grad_norm": 0.2706264861398608,
      "learning_rate": 6.470588235294119e-06,
      "loss": 0.5884,
      "step": 55
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.6332617880988516,
      "learning_rate": 7.058823529411766e-06,
      "loss": 0.5818,
      "step": 60
    },
    {
      "epoch": 0.3834808259587021,
      "grad_norm": 0.1015116079049458,
      "learning_rate": 7.647058823529411e-06,
      "loss": 0.5798,
      "step": 65
    },
    {
      "epoch": 0.41297935103244837,
      "grad_norm": 0.12119348356809045,
      "learning_rate": 8.23529411764706e-06,
      "loss": 0.5751,
      "step": 70
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 0.07879965059698645,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.5708,
      "step": 75
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 0.05646247242948782,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.5683,
      "step": 80
    },
    {
      "epoch": 0.5014749262536873,
      "grad_norm": 0.25525240715915204,
      "learning_rate": 1e-05,
      "loss": 0.5662,
      "step": 85
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.05365048303720814,
      "learning_rate": 9.998932083939657e-06,
      "loss": 0.5598,
      "step": 90
    },
    {
      "epoch": 0.56047197640118,
      "grad_norm": 0.1595860307142945,
      "learning_rate": 9.995728791936505e-06,
      "loss": 0.5538,
      "step": 95
    },
    {
      "epoch": 0.5899705014749262,
      "grad_norm": 0.06609453133465848,
      "learning_rate": 9.990391492329341e-06,
      "loss": 0.5529,
      "step": 100
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 1.6293266027560704,
      "learning_rate": 9.98292246503335e-06,
      "loss": 0.5527,
      "step": 105
    },
    {
      "epoch": 0.6489675516224189,
      "grad_norm": 1.050544643875783,
      "learning_rate": 9.973324900566214e-06,
      "loss": 0.5477,
      "step": 110
    },
    {
      "epoch": 0.6784660766961652,
      "grad_norm": 0.052879637742834044,
      "learning_rate": 9.961602898685225e-06,
      "loss": 0.5474,
      "step": 115
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.04928862663129842,
      "learning_rate": 9.947761466636014e-06,
      "loss": 0.5553,
      "step": 120
    },
    {
      "epoch": 0.7374631268436578,
      "grad_norm": 0.052753160381468045,
      "learning_rate": 9.931806517013612e-06,
      "loss": 0.5464,
      "step": 125
    },
    {
      "epoch": 0.7669616519174042,
      "grad_norm": 0.045802114899820966,
      "learning_rate": 9.913744865236798e-06,
      "loss": 0.5404,
      "step": 130
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 0.11489905003299361,
      "learning_rate": 9.893584226636773e-06,
      "loss": 0.5317,
      "step": 135
    },
    {
      "epoch": 0.8259587020648967,
      "grad_norm": 0.4919380291913098,
      "learning_rate": 9.871333213161438e-06,
      "loss": 0.5481,
      "step": 140
    },
    {
      "epoch": 0.855457227138643,
      "grad_norm": 0.3232334093103194,
      "learning_rate": 9.847001329696653e-06,
      "loss": 0.5339,
      "step": 145
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 0.05048150556921708,
      "learning_rate": 9.820598970006068e-06,
      "loss": 0.5325,
      "step": 150
    },
    {
      "epoch": 0.9144542772861357,
      "grad_norm": 0.058183934565565226,
      "learning_rate": 9.792137412291265e-06,
      "loss": 0.5373,
      "step": 155
    },
    {
      "epoch": 0.943952802359882,
      "grad_norm": 2.1026211814523927,
      "learning_rate": 9.761628814374074e-06,
      "loss": 0.535,
      "step": 160
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 0.05037291432057576,
      "learning_rate": 9.729086208503174e-06,
      "loss": 0.5392,
      "step": 165
    },
    {
      "epoch": 0.9970501474926253,
      "eval_loss": 0.5948278307914734,
      "eval_runtime": 7.8455,
      "eval_samples_per_second": 16.825,
      "eval_steps_per_second": 0.382,
      "step": 169
    },
    {
      "epoch": 1.0029498525073746,
      "grad_norm": 0.07970296331803481,
      "learning_rate": 9.694523495787149e-06,
      "loss": 0.5852,
      "step": 170
    },
    {
      "epoch": 1.0324483775811208,
      "grad_norm": 0.06217085534785087,
      "learning_rate": 9.657955440256396e-06,
      "loss": 0.5318,
      "step": 175
    },
    {
      "epoch": 1.0619469026548674,
      "grad_norm": 0.4533798599174413,
      "learning_rate": 9.619397662556434e-06,
      "loss": 0.5265,
      "step": 180
    },
    {
      "epoch": 1.0914454277286136,
      "grad_norm": 0.0843198746785751,
      "learning_rate": 9.578866633275289e-06,
      "loss": 0.525,
      "step": 185
    },
    {
      "epoch": 1.12094395280236,
      "grad_norm": 0.0514110786588162,
      "learning_rate": 9.536379665907801e-06,
      "loss": 0.5244,
      "step": 190
    },
    {
      "epoch": 1.1504424778761062,
      "grad_norm": 0.08421706916029806,
      "learning_rate": 9.491954909459895e-06,
      "loss": 0.5241,
      "step": 195
    },
    {
      "epoch": 1.1799410029498525,
      "grad_norm": 0.058452224546329916,
      "learning_rate": 9.445611340695926e-06,
      "loss": 0.5274,
      "step": 200
    },
    {
      "epoch": 1.2094395280235988,
      "grad_norm": 1.2314254826441438,
      "learning_rate": 9.397368756032445e-06,
      "loss": 0.5247,
      "step": 205
    },
    {
      "epoch": 1.238938053097345,
      "grad_norm": 0.04772904502073005,
      "learning_rate": 9.347247763081834e-06,
      "loss": 0.5276,
      "step": 210
    },
    {
      "epoch": 1.2684365781710913,
      "grad_norm": 0.05022705703233357,
      "learning_rate": 9.295269771849426e-06,
      "loss": 0.5179,
      "step": 215
    },
    {
      "epoch": 1.2979351032448379,
      "grad_norm": 0.2724781073186335,
      "learning_rate": 9.241456985587868e-06,
      "loss": 0.5229,
      "step": 220
    },
    {
      "epoch": 1.3274336283185841,
      "grad_norm": 0.07955839264628826,
      "learning_rate": 9.185832391312644e-06,
      "loss": 0.5222,
      "step": 225
    },
    {
      "epoch": 1.3569321533923304,
      "grad_norm": 0.047043054214154625,
      "learning_rate": 9.12841974998278e-06,
      "loss": 0.5195,
      "step": 230
    },
    {
      "epoch": 1.3864306784660767,
      "grad_norm": 0.045497809508961325,
      "learning_rate": 9.069243586350976e-06,
      "loss": 0.5148,
      "step": 235
    },
    {
      "epoch": 1.415929203539823,
      "grad_norm": 0.8566869256944054,
      "learning_rate": 9.008329178487442e-06,
      "loss": 0.5207,
      "step": 240
    },
    {
      "epoch": 1.4454277286135693,
      "grad_norm": 0.06712694488880502,
      "learning_rate": 8.94570254698197e-06,
      "loss": 0.5219,
      "step": 245
    },
    {
      "epoch": 1.4749262536873156,
      "grad_norm": 0.134636628527114,
      "learning_rate": 8.881390443828788e-06,
      "loss": 0.5164,
      "step": 250
    },
    {
      "epoch": 1.504424778761062,
      "grad_norm": 1.017642297039446,
      "learning_rate": 8.815420340999034e-06,
      "loss": 0.5164,
      "step": 255
    },
    {
      "epoch": 1.5339233038348081,
      "grad_norm": 0.8748816419357938,
      "learning_rate": 8.747820418705632e-06,
      "loss": 0.519,
      "step": 260
    },
    {
      "epoch": 1.5634218289085546,
      "grad_norm": 0.05916211446645424,
      "learning_rate": 8.67861955336566e-06,
      "loss": 0.5132,
      "step": 265
    },
    {
      "epoch": 1.592920353982301,
      "grad_norm": 0.06267760570910012,
      "learning_rate": 8.607847305265312e-06,
      "loss": 0.5119,
      "step": 270
    },
    {
      "epoch": 1.6224188790560472,
      "grad_norm": 0.053722149220927,
      "learning_rate": 8.535533905932739e-06,
      "loss": 0.514,
      "step": 275
    },
    {
      "epoch": 1.6519174041297935,
      "grad_norm": 0.055409146579795114,
      "learning_rate": 8.461710245224149e-06,
      "loss": 0.5231,
      "step": 280
    },
    {
      "epoch": 1.6814159292035398,
      "grad_norm": 0.049718992850954775,
      "learning_rate": 8.386407858128707e-06,
      "loss": 0.5127,
      "step": 285
    },
    {
      "epoch": 1.7109144542772863,
      "grad_norm": 0.0443810313683345,
      "learning_rate": 8.309658911297833e-06,
      "loss": 0.5116,
      "step": 290
    },
    {
      "epoch": 1.7404129793510323,
      "grad_norm": 0.05127452771633588,
      "learning_rate": 8.231496189304704e-06,
      "loss": 0.5078,
      "step": 295
    },
    {
      "epoch": 1.7699115044247788,
      "grad_norm": 0.04591077767546143,
      "learning_rate": 8.151953080639777e-06,
      "loss": 0.5125,
      "step": 300
    },
    {
      "epoch": 1.799410029498525,
      "grad_norm": 0.04535715037949931,
      "learning_rate": 8.071063563448341e-06,
      "loss": 0.5131,
      "step": 305
    },
    {
      "epoch": 1.8289085545722714,
      "grad_norm": 0.045271495366352554,
      "learning_rate": 7.988862191016204e-06,
      "loss": 0.5123,
      "step": 310
    },
    {
      "epoch": 1.8584070796460177,
      "grad_norm": 0.056004335836578926,
      "learning_rate": 7.905384077009693e-06,
      "loss": 0.5097,
      "step": 315
    },
    {
      "epoch": 1.887905604719764,
      "grad_norm": 0.04430378987199138,
      "learning_rate": 7.820664880476257e-06,
      "loss": 0.5143,
      "step": 320
    },
    {
      "epoch": 1.9174041297935103,
      "grad_norm": 0.04609433007960605,
      "learning_rate": 7.734740790612137e-06,
      "loss": 0.5086,
      "step": 325
    },
    {
      "epoch": 1.9469026548672566,
      "grad_norm": 0.7820689144245092,
      "learning_rate": 7.647648511303545e-06,
      "loss": 0.5095,
      "step": 330
    },
    {
      "epoch": 1.976401179941003,
      "grad_norm": 0.049876695974305066,
      "learning_rate": 7.559425245448006e-06,
      "loss": 0.5116,
      "step": 335
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.569428026676178,
      "eval_runtime": 7.9223,
      "eval_samples_per_second": 16.662,
      "eval_steps_per_second": 0.379,
      "step": 339
    },
    {
      "epoch": 2.005899705014749,
      "grad_norm": 0.059860668705846505,
      "learning_rate": 7.470108679062521e-06,
      "loss": 0.5565,
      "step": 340
    },
    {
      "epoch": 2.0353982300884956,
      "grad_norm": 0.045373657400373905,
      "learning_rate": 7.379736965185369e-06,
      "loss": 0.5022,
      "step": 345
    },
    {
      "epoch": 2.0648967551622417,
      "grad_norm": 0.04575003134013503,
      "learning_rate": 7.288348707578409e-06,
      "loss": 0.5009,
      "step": 350
    },
    {
      "epoch": 2.094395280235988,
      "grad_norm": 0.0764963225778181,
      "learning_rate": 7.195982944236853e-06,
      "loss": 0.5023,
      "step": 355
    },
    {
      "epoch": 2.1238938053097347,
      "grad_norm": 0.2864046551111833,
      "learning_rate": 7.102679130713538e-06,
      "loss": 0.5027,
      "step": 360
    },
    {
      "epoch": 2.1533923303834808,
      "grad_norm": 0.0726950183868685,
      "learning_rate": 7.008477123264849e-06,
      "loss": 0.4995,
      "step": 365
    },
    {
      "epoch": 2.1828908554572273,
      "grad_norm": 0.047612550060808626,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.5073,
      "step": 370
    },
    {
      "epoch": 2.2123893805309733,
      "grad_norm": 0.045980323605959564,
      "learning_rate": 6.817539852819149e-06,
      "loss": 0.5066,
      "step": 375
    },
    {
      "epoch": 2.24188790560472,
      "grad_norm": 0.05019367448115624,
      "learning_rate": 6.720886151813194e-06,
      "loss": 0.5054,
      "step": 380
    },
    {
      "epoch": 2.271386430678466,
      "grad_norm": 0.04465323510528684,
      "learning_rate": 6.6234973460234184e-06,
      "loss": 0.5003,
      "step": 385
    },
    {
      "epoch": 2.3008849557522124,
      "grad_norm": 0.08235286259691993,
      "learning_rate": 6.525415036677745e-06,
      "loss": 0.5001,
      "step": 390
    },
    {
      "epoch": 2.330383480825959,
      "grad_norm": 0.050999382045359705,
      "learning_rate": 6.426681121245527e-06,
      "loss": 0.498,
      "step": 395
    },
    {
      "epoch": 2.359882005899705,
      "grad_norm": 0.04526036928138616,
      "learning_rate": 6.327337775540362e-06,
      "loss": 0.5018,
      "step": 400
    },
    {
      "epoch": 2.3893805309734515,
      "grad_norm": 0.05806925044679012,
      "learning_rate": 6.227427435703997e-06,
      "loss": 0.4955,
      "step": 405
    },
    {
      "epoch": 2.4188790560471976,
      "grad_norm": 0.06164688967940204,
      "learning_rate": 6.126992780079032e-06,
      "loss": 0.4971,
      "step": 410
    },
    {
      "epoch": 2.448377581120944,
      "grad_norm": 0.5078396005551373,
      "learning_rate": 6.026076710978172e-06,
      "loss": 0.5015,
      "step": 415
    },
    {
      "epoch": 2.47787610619469,
      "grad_norm": 0.046783560822131726,
      "learning_rate": 5.924722336357793e-06,
      "loss": 0.4975,
      "step": 420
    },
    {
      "epoch": 2.5073746312684366,
      "grad_norm": 0.04594136178012529,
      "learning_rate": 5.82297295140367e-06,
      "loss": 0.4996,
      "step": 425
    },
    {
      "epoch": 2.5368731563421827,
      "grad_norm": 0.05594049666474868,
      "learning_rate": 5.720872020036734e-06,
      "loss": 0.5001,
      "step": 430
    },
    {
      "epoch": 2.566371681415929,
      "grad_norm": 0.04465947789722648,
      "learning_rate": 5.61846315634674e-06,
      "loss": 0.4924,
      "step": 435
    },
    {
      "epoch": 2.5958702064896757,
      "grad_norm": 0.060580400184871375,
      "learning_rate": 5.515790105961785e-06,
      "loss": 0.5022,
      "step": 440
    },
    {
      "epoch": 2.6253687315634218,
      "grad_norm": 0.12381786538248248,
      "learning_rate": 5.412896727361663e-06,
      "loss": 0.4972,
      "step": 445
    },
    {
      "epoch": 2.6548672566371683,
      "grad_norm": 0.05202660251491312,
      "learning_rate": 5.309826973142974e-06,
      "loss": 0.5071,
      "step": 450
    },
    {
      "epoch": 2.6843657817109143,
      "grad_norm": 0.10377000214654016,
      "learning_rate": 5.206624871244066e-06,
      "loss": 0.4995,
      "step": 455
    },
    {
      "epoch": 2.713864306784661,
      "grad_norm": 0.044378951816130024,
      "learning_rate": 5.103334506137773e-06,
      "loss": 0.4974,
      "step": 460
    },
    {
      "epoch": 2.7433628318584073,
      "grad_norm": 0.04467225886658485,
      "learning_rate": 5e-06,
      "loss": 0.497,
      "step": 465
    },
    {
      "epoch": 2.7728613569321534,
      "grad_norm": 0.051986874546360556,
      "learning_rate": 4.89666549386223e-06,
      "loss": 0.4971,
      "step": 470
    },
    {
      "epoch": 2.8023598820058995,
      "grad_norm": 0.12453400877778924,
      "learning_rate": 4.793375128755934e-06,
      "loss": 0.4989,
      "step": 475
    },
    {
      "epoch": 2.831858407079646,
      "grad_norm": 0.04420192438109124,
      "learning_rate": 4.690173026857028e-06,
      "loss": 0.4965,
      "step": 480
    },
    {
      "epoch": 2.8613569321533925,
      "grad_norm": 0.043489134164912784,
      "learning_rate": 4.587103272638339e-06,
      "loss": 0.5001,
      "step": 485
    },
    {
      "epoch": 2.8908554572271385,
      "grad_norm": 0.057345889273731514,
      "learning_rate": 4.4842098940382155e-06,
      "loss": 0.4965,
      "step": 490
    },
    {
      "epoch": 2.920353982300885,
      "grad_norm": 0.04346872325174773,
      "learning_rate": 4.381536843653262e-06,
      "loss": 0.4973,
      "step": 495
    },
    {
      "epoch": 2.949852507374631,
      "grad_norm": 0.05768914593482109,
      "learning_rate": 4.279127979963266e-06,
      "loss": 0.5033,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 845,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 56,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1688018784092160.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}