{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9826119126896042,
  "eval_steps": 100,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.059193488716241215,
      "grad_norm": 0.19465851783752441,
      "learning_rate": 2e-05,
      "loss": 1.1117,
      "step": 10
    },
    {
      "epoch": 0.11838697743248243,
      "grad_norm": 0.21135994791984558,
      "learning_rate": 4e-05,
      "loss": 1.1022,
      "step": 20
    },
    {
      "epoch": 0.17758046614872364,
      "grad_norm": 0.2708509862422943,
      "learning_rate": 6e-05,
      "loss": 1.0546,
      "step": 30
    },
    {
      "epoch": 0.23677395486496486,
      "grad_norm": 0.21392174065113068,
      "learning_rate": 8e-05,
      "loss": 0.94,
      "step": 40
    },
    {
      "epoch": 0.2959674435812061,
      "grad_norm": 0.17460189759731293,
      "learning_rate": 0.0001,
      "loss": 0.8246,
      "step": 50
    },
    {
      "epoch": 0.3551609322974473,
      "grad_norm": 0.16554006934165955,
      "learning_rate": 0.00012,
      "loss": 0.7437,
      "step": 60
    },
    {
      "epoch": 0.41435442101368847,
      "grad_norm": 0.16454806923866272,
      "learning_rate": 0.00014,
      "loss": 0.6901,
      "step": 70
    },
    {
      "epoch": 0.4735479097299297,
      "grad_norm": 0.1758105754852295,
      "learning_rate": 0.00016,
      "loss": 0.6429,
      "step": 80
    },
    {
      "epoch": 0.532741398446171,
      "grad_norm": 0.1696159690618515,
      "learning_rate": 0.00018,
      "loss": 0.6319,
      "step": 90
    },
    {
      "epoch": 0.5919348871624122,
      "grad_norm": 0.17172178626060486,
      "learning_rate": 0.0002,
      "loss": 0.5995,
      "step": 100
    },
    {
      "epoch": 0.5919348871624122,
      "eval_loss": 0.5879706740379333,
      "eval_runtime": 186.3324,
      "eval_samples_per_second": 3.687,
      "eval_steps_per_second": 0.462,
      "step": 100
    },
    {
      "epoch": 0.6511283758786534,
      "grad_norm": 0.16957880556583405,
      "learning_rate": 0.00019504950495049505,
      "loss": 0.5913,
      "step": 110
    },
    {
      "epoch": 0.7103218645948945,
      "grad_norm": 0.17516390979290009,
      "learning_rate": 0.0001900990099009901,
      "loss": 0.5803,
      "step": 120
    },
    {
      "epoch": 0.7695153533111357,
      "grad_norm": 0.18869660794734955,
      "learning_rate": 0.00018514851485148517,
      "loss": 0.5631,
      "step": 130
    },
    {
      "epoch": 0.8287088420273769,
      "grad_norm": 0.18655870854854584,
      "learning_rate": 0.00018019801980198022,
      "loss": 0.5538,
      "step": 140
    },
    {
      "epoch": 0.8879023307436182,
      "grad_norm": 0.18268819153308868,
      "learning_rate": 0.00017524752475247526,
      "loss": 0.5475,
      "step": 150
    },
    {
      "epoch": 0.9470958194598594,
      "grad_norm": 0.1926167607307434,
      "learning_rate": 0.0001702970297029703,
      "loss": 0.5462,
      "step": 160
    },
    {
      "epoch": 1.005919348871624,
      "grad_norm": 0.19758427143096924,
      "learning_rate": 0.00016534653465346535,
      "loss": 0.5375,
      "step": 170
    },
    {
      "epoch": 1.0651128375878653,
      "grad_norm": 0.19379234313964844,
      "learning_rate": 0.00016039603960396042,
      "loss": 0.5234,
      "step": 180
    },
    {
      "epoch": 1.1243063263041067,
      "grad_norm": 0.19841700792312622,
      "learning_rate": 0.00015544554455445547,
      "loss": 0.5336,
      "step": 190
    },
    {
      "epoch": 1.1834998150203477,
      "grad_norm": 0.19659265875816345,
      "learning_rate": 0.00015049504950495051,
      "loss": 0.5265,
      "step": 200
    },
    {
      "epoch": 1.1834998150203477,
      "eval_loss": 0.5296523571014404,
      "eval_runtime": 186.0309,
      "eval_samples_per_second": 3.693,
      "eval_steps_per_second": 0.462,
      "step": 200
    },
    {
      "epoch": 1.242693303736589,
      "grad_norm": 0.2189786285161972,
      "learning_rate": 0.00014554455445544556,
      "loss": 0.5228,
      "step": 210
    },
    {
      "epoch": 1.3018867924528301,
      "grad_norm": 0.2317192554473877,
      "learning_rate": 0.0001405940594059406,
      "loss": 0.5219,
      "step": 220
    },
    {
      "epoch": 1.3610802811690714,
      "grad_norm": 0.20830461382865906,
      "learning_rate": 0.00013564356435643565,
      "loss": 0.5095,
      "step": 230
    },
    {
      "epoch": 1.4202737698853127,
      "grad_norm": 0.2214994877576828,
      "learning_rate": 0.0001306930693069307,
      "loss": 0.5192,
      "step": 240
    },
    {
      "epoch": 1.4794672586015538,
      "grad_norm": 0.21869614720344543,
      "learning_rate": 0.00012574257425742574,
      "loss": 0.5031,
      "step": 250
    },
    {
      "epoch": 1.538660747317795,
      "grad_norm": 0.21614821255207062,
      "learning_rate": 0.0001207920792079208,
      "loss": 0.5177,
      "step": 260
    },
    {
      "epoch": 1.5978542360340362,
      "grad_norm": 0.2306758016347885,
      "learning_rate": 0.00011584158415841584,
      "loss": 0.5124,
      "step": 270
    },
    {
      "epoch": 1.6570477247502775,
      "grad_norm": 0.22710908949375153,
      "learning_rate": 0.0001108910891089109,
      "loss": 0.5025,
      "step": 280
    },
    {
      "epoch": 1.7162412134665188,
      "grad_norm": 0.22501707077026367,
      "learning_rate": 0.00010594059405940595,
      "loss": 0.5048,
      "step": 290
    },
    {
      "epoch": 1.77543470218276,
      "grad_norm": 0.22507990896701813,
      "learning_rate": 0.00010099009900990099,
      "loss": 0.5009,
      "step": 300
    },
    {
      "epoch": 1.77543470218276,
      "eval_loss": 0.508837103843689,
      "eval_runtime": 185.3987,
      "eval_samples_per_second": 3.706,
      "eval_steps_per_second": 0.464,
      "step": 300
    },
    {
      "epoch": 1.834628190899001,
      "grad_norm": 0.22626681625843048,
      "learning_rate": 9.603960396039604e-05,
      "loss": 0.5045,
      "step": 310
    },
    {
      "epoch": 1.8938216796152423,
      "grad_norm": 0.21802489459514618,
      "learning_rate": 9.10891089108911e-05,
      "loss": 0.5087,
      "step": 320
    },
    {
      "epoch": 1.9530151683314836,
      "grad_norm": 0.2331380993127823,
      "learning_rate": 8.613861386138614e-05,
      "loss": 0.5038,
      "step": 330
    },
    {
      "epoch": 2.011838697743248,
      "grad_norm": 0.21599650382995605,
      "learning_rate": 8.11881188118812e-05,
      "loss": 0.4912,
      "step": 340
    },
    {
      "epoch": 2.0710321864594894,
      "grad_norm": 0.24118073284626007,
      "learning_rate": 7.623762376237625e-05,
      "loss": 0.4842,
      "step": 350
    },
    {
      "epoch": 2.1302256751757307,
      "grad_norm": 0.232917919754982,
      "learning_rate": 7.128712871287129e-05,
      "loss": 0.4835,
      "step": 360
    },
    {
      "epoch": 2.189419163891972,
      "grad_norm": 0.23639123141765594,
      "learning_rate": 6.633663366336635e-05,
      "loss": 0.4786,
      "step": 370
    },
    {
      "epoch": 2.2486126526082133,
      "grad_norm": 0.2632993161678314,
      "learning_rate": 6.13861386138614e-05,
      "loss": 0.4824,
      "step": 380
    },
    {
      "epoch": 2.307806141324454,
      "grad_norm": 0.2573336064815521,
      "learning_rate": 5.643564356435643e-05,
      "loss": 0.4771,
      "step": 390
    },
    {
      "epoch": 2.3669996300406955,
      "grad_norm": 0.24001090228557587,
      "learning_rate": 5.148514851485149e-05,
      "loss": 0.4848,
      "step": 400
    },
    {
      "epoch": 2.3669996300406955,
      "eval_loss": 0.4998326301574707,
      "eval_runtime": 186.3844,
      "eval_samples_per_second": 3.686,
      "eval_steps_per_second": 0.461,
      "step": 400
    },
    {
      "epoch": 2.4261931187569368,
      "grad_norm": 0.2617679834365845,
      "learning_rate": 4.653465346534654e-05,
      "loss": 0.4854,
      "step": 410
    },
    {
      "epoch": 2.485386607473178,
      "grad_norm": 0.2378547489643097,
      "learning_rate": 4.158415841584158e-05,
      "loss": 0.4848,
      "step": 420
    },
    {
      "epoch": 2.544580096189419,
      "grad_norm": 0.2498575747013092,
      "learning_rate": 3.6633663366336634e-05,
      "loss": 0.4768,
      "step": 430
    },
    {
      "epoch": 2.6037735849056602,
      "grad_norm": 0.2568998336791992,
      "learning_rate": 3.1683168316831686e-05,
      "loss": 0.4863,
      "step": 440
    },
    {
      "epoch": 2.6629670736219015,
      "grad_norm": 0.25008225440979004,
      "learning_rate": 2.6732673267326734e-05,
      "loss": 0.4747,
      "step": 450
    },
    {
      "epoch": 2.722160562338143,
      "grad_norm": 0.24171195924282074,
      "learning_rate": 2.1782178217821783e-05,
      "loss": 0.4736,
      "step": 460
    },
    {
      "epoch": 2.781354051054384,
      "grad_norm": 0.2468671202659607,
      "learning_rate": 1.6831683168316834e-05,
      "loss": 0.4894,
      "step": 470
    },
    {
      "epoch": 2.8405475397706255,
      "grad_norm": 0.2496197372674942,
      "learning_rate": 1.1881188118811881e-05,
      "loss": 0.4798,
      "step": 480
    },
    {
      "epoch": 2.8997410284868663,
      "grad_norm": 0.24788333475589752,
      "learning_rate": 6.9306930693069314e-06,
      "loss": 0.4739,
      "step": 490
    },
    {
      "epoch": 2.9589345172031076,
      "grad_norm": 0.2498323768377304,
      "learning_rate": 1.9801980198019803e-06,
      "loss": 0.4718,
      "step": 500
    },
    {
      "epoch": 2.9589345172031076,
      "eval_loss": 0.49539193511009216,
      "eval_runtime": 185.1827,
      "eval_samples_per_second": 3.71,
      "eval_steps_per_second": 0.464,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.23509345222656e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}