{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999253545658124,
  "eval_steps": 500,
  "global_step": 753,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013270299411130464,
      "grad_norm": 2.564515743911166,
      "learning_rate": 1.1842105263157895e-05,
      "loss": 0.9405,
      "step": 10
    },
    {
      "epoch": 0.026540598822260928,
      "grad_norm": 1.1273144189138777,
      "learning_rate": 2.5e-05,
      "loss": 0.4873,
      "step": 20
    },
    {
      "epoch": 0.039810898233391394,
      "grad_norm": 0.9655855896937451,
      "learning_rate": 3.815789473684211e-05,
      "loss": 0.4081,
      "step": 30
    },
    {
      "epoch": 0.053081197644521856,
      "grad_norm": 0.9922588910923523,
      "learning_rate": 5.131578947368422e-05,
      "loss": 0.3966,
      "step": 40
    },
    {
      "epoch": 0.06635149705565231,
      "grad_norm": 0.8968550265742283,
      "learning_rate": 6.447368421052632e-05,
      "loss": 0.4168,
      "step": 50
    },
    {
      "epoch": 0.07962179646678279,
      "grad_norm": 0.8429297473809728,
      "learning_rate": 7.763157894736843e-05,
      "loss": 0.4101,
      "step": 60
    },
    {
      "epoch": 0.09289209587791325,
      "grad_norm": 0.8862411812281032,
      "learning_rate": 9.078947368421054e-05,
      "loss": 0.4176,
      "step": 70
    },
    {
      "epoch": 0.10616239528904371,
      "grad_norm": 0.8738049606806837,
      "learning_rate": 9.999515495391765e-05,
      "loss": 0.4322,
      "step": 80
    },
    {
      "epoch": 0.11943269470017417,
      "grad_norm": 0.7328578846700591,
      "learning_rate": 9.990904692023604e-05,
      "loss": 0.4376,
      "step": 90
    },
    {
      "epoch": 0.13270299411130462,
      "grad_norm": 0.7558469169678371,
      "learning_rate": 9.971548459891113e-05,
      "loss": 0.4379,
      "step": 100
    },
    {
      "epoch": 0.1459732935224351,
      "grad_norm": 0.7794623609878979,
      "learning_rate": 9.941488473004595e-05,
      "loss": 0.4398,
      "step": 110
    },
    {
      "epoch": 0.15924359293356558,
      "grad_norm": 0.7167440932626373,
      "learning_rate": 9.900789450581836e-05,
      "loss": 0.4487,
      "step": 120
    },
    {
      "epoch": 0.17251389234469602,
      "grad_norm": 0.7496367898299724,
      "learning_rate": 9.849539017707508e-05,
      "loss": 0.4274,
      "step": 130
    },
    {
      "epoch": 0.1857841917558265,
      "grad_norm": 0.689841994373832,
      "learning_rate": 9.787847516676162e-05,
      "loss": 0.4224,
      "step": 140
    },
    {
      "epoch": 0.19905449116695695,
      "grad_norm": 0.7552110515614651,
      "learning_rate": 9.715847769425021e-05,
      "loss": 0.4365,
      "step": 150
    },
    {
      "epoch": 0.21232479057808742,
      "grad_norm": 0.6307269611978348,
      "learning_rate": 9.633694791568062e-05,
      "loss": 0.4347,
      "step": 160
    },
    {
      "epoch": 0.22559508998921787,
      "grad_norm": 2.235577934539042,
      "learning_rate": 9.541565458647059e-05,
      "loss": 0.4475,
      "step": 170
    },
    {
      "epoch": 0.23886538940034835,
      "grad_norm": 0.7608116446649408,
      "learning_rate": 9.439658125318151e-05,
      "loss": 0.4493,
      "step": 180
    },
    {
      "epoch": 0.2521356888114788,
      "grad_norm": 0.5736520072260313,
      "learning_rate": 9.328192198293831e-05,
      "loss": 0.4223,
      "step": 190
    },
    {
      "epoch": 0.26540598822260925,
      "grad_norm": 0.6720976517168915,
      "learning_rate": 9.207407663959816e-05,
      "loss": 0.4481,
      "step": 200
    },
    {
      "epoch": 0.27867628763373975,
      "grad_norm": 0.6020758268188027,
      "learning_rate": 9.077564571683826e-05,
      "loss": 0.443,
      "step": 210
    },
    {
      "epoch": 0.2919465870448702,
      "grad_norm": 0.6025457234354933,
      "learning_rate": 8.938942473928729e-05,
      "loss": 0.41,
      "step": 220
    },
    {
      "epoch": 0.30521688645600065,
      "grad_norm": 0.6320902149161726,
      "learning_rate": 8.791839824375471e-05,
      "loss": 0.4244,
      "step": 230
    },
    {
      "epoch": 0.31848718586713115,
      "grad_norm": 0.5979940402051278,
      "learning_rate": 8.636573335351648e-05,
      "loss": 0.4219,
      "step": 240
    },
    {
      "epoch": 0.3317574852782616,
      "grad_norm": 0.5995490496010847,
      "learning_rate": 8.473477295949169e-05,
      "loss": 0.4212,
      "step": 250
    },
    {
      "epoch": 0.34502778468939205,
      "grad_norm": 0.6262074504506607,
      "learning_rate": 8.302902852299104e-05,
      "loss": 0.4232,
      "step": 260
    },
    {
      "epoch": 0.3582980841005225,
      "grad_norm": 0.6353404118238228,
      "learning_rate": 8.125217251553289e-05,
      "loss": 0.4065,
      "step": 270
    },
    {
      "epoch": 0.371568383511653,
      "grad_norm": 0.6179687781595031,
      "learning_rate": 7.940803051200419e-05,
      "loss": 0.4149,
      "step": 280
    },
    {
      "epoch": 0.38483868292278345,
      "grad_norm": 0.6110819598730759,
      "learning_rate": 7.750057295418911e-05,
      "loss": 0.4174,
      "step": 290
    },
    {
      "epoch": 0.3981089823339139,
      "grad_norm": 0.5881868138059606,
      "learning_rate": 7.553390660239932e-05,
      "loss": 0.4009,
      "step": 300
    },
    {
      "epoch": 0.41137928174504435,
      "grad_norm": 0.5503577948593137,
      "learning_rate": 7.351226569360996e-05,
      "loss": 0.4013,
      "step": 310
    },
    {
      "epoch": 0.42464958115617485,
      "grad_norm": 0.5132494359518306,
      "learning_rate": 7.144000282513812e-05,
      "loss": 0.4209,
      "step": 320
    },
    {
      "epoch": 0.4379198805673053,
      "grad_norm": 0.5103720905789203,
      "learning_rate": 6.932157958349133e-05,
      "loss": 0.3839,
      "step": 330
    },
    {
      "epoch": 0.45119017997843575,
      "grad_norm": 0.5495665822448719,
      "learning_rate": 6.716155693856188e-05,
      "loss": 0.4107,
      "step": 340
    },
    {
      "epoch": 0.46446047938956625,
      "grad_norm": 0.4970638300047456,
      "learning_rate": 6.496458542384877e-05,
      "loss": 0.3981,
      "step": 350
    },
    {
      "epoch": 0.4777307788006967,
      "grad_norm": 0.5490841978868565,
      "learning_rate": 6.273539512384879e-05,
      "loss": 0.394,
      "step": 360
    },
    {
      "epoch": 0.49100107821182715,
      "grad_norm": 0.6190608019556366,
      "learning_rate": 6.047878549017415e-05,
      "loss": 0.3931,
      "step": 370
    },
    {
      "epoch": 0.5042713776229576,
      "grad_norm": 0.5148976809599615,
      "learning_rate": 5.819961500832278e-05,
      "loss": 0.3823,
      "step": 380
    },
    {
      "epoch": 0.517541677034088,
      "grad_norm": 0.5244464815113467,
      "learning_rate": 5.590279073734822e-05,
      "loss": 0.3876,
      "step": 390
    },
    {
      "epoch": 0.5308119764452185,
      "grad_norm": 0.5175467326545363,
      "learning_rate": 5.359325774495082e-05,
      "loss": 0.3842,
      "step": 400
    },
    {
      "epoch": 0.544082275856349,
      "grad_norm": 0.5292781127050901,
      "learning_rate": 5.1275988460736045e-05,
      "loss": 0.3906,
      "step": 410
    },
    {
      "epoch": 0.5573525752674795,
      "grad_norm": 0.5063495870152123,
      "learning_rate": 4.895597197056262e-05,
      "loss": 0.3982,
      "step": 420
    },
    {
      "epoch": 0.57062287467861,
      "grad_norm": 0.5228008236735917,
      "learning_rate": 4.663820327502975e-05,
      "loss": 0.3804,
      "step": 430
    },
    {
      "epoch": 0.5838931740897404,
      "grad_norm": 0.4554550909400395,
      "learning_rate": 4.432767253522987e-05,
      "loss": 0.3741,
      "step": 440
    },
    {
      "epoch": 0.5971634735008708,
      "grad_norm": 0.4858798211434955,
      "learning_rate": 4.202935432892075e-05,
      "loss": 0.3998,
      "step": 450
    },
    {
      "epoch": 0.6104337729120013,
      "grad_norm": 0.508196849358697,
      "learning_rate": 3.97481969402488e-05,
      "loss": 0.3869,
      "step": 460
    },
    {
      "epoch": 0.6237040723231317,
      "grad_norm": 0.4707811980816944,
      "learning_rate": 3.7489111706082325e-05,
      "loss": 0.3673,
      "step": 470
    },
    {
      "epoch": 0.6369743717342623,
      "grad_norm": 0.5053807020939688,
      "learning_rate": 3.5256962441892515e-05,
      "loss": 0.3666,
      "step": 480
    },
    {
      "epoch": 0.6502446711453927,
      "grad_norm": 0.5759147075328039,
      "learning_rate": 3.305655496994804e-05,
      "loss": 0.3595,
      "step": 490
    },
    {
      "epoch": 0.6635149705565232,
      "grad_norm": 0.5083257997464254,
      "learning_rate": 3.089262677236915e-05,
      "loss": 0.3627,
      "step": 500
    },
    {
      "epoch": 0.6767852699676536,
      "grad_norm": 0.45020107150061867,
      "learning_rate": 2.8769836791318215e-05,
      "loss": 0.3614,
      "step": 510
    },
    {
      "epoch": 0.6900555693787841,
      "grad_norm": 0.4727491134557738,
      "learning_rate": 2.6692755398287096e-05,
      "loss": 0.3787,
      "step": 520
    },
    {
      "epoch": 0.7033258687899145,
      "grad_norm": 0.45645829229700563,
      "learning_rate": 2.4665854554077283e-05,
      "loss": 0.355,
      "step": 530
    },
    {
      "epoch": 0.716596168201045,
      "grad_norm": 0.49663879168540986,
      "learning_rate": 2.269349818065838e-05,
      "loss": 0.3558,
      "step": 540
    },
    {
      "epoch": 0.7298664676121756,
      "grad_norm": 0.4791890844388542,
      "learning_rate": 2.077993276563457e-05,
      "loss": 0.3653,
      "step": 550
    },
    {
      "epoch": 0.743136767023306,
      "grad_norm": 0.4383731152016023,
      "learning_rate": 1.8929278219547537e-05,
      "loss": 0.3552,
      "step": 560
    },
    {
      "epoch": 0.7564070664344364,
      "grad_norm": 0.4520963322775716,
      "learning_rate": 1.7145519005699907e-05,
      "loss": 0.3492,
      "step": 570
    },
    {
      "epoch": 0.7696773658455669,
      "grad_norm": 0.4825112985774525,
      "learning_rate": 1.5432495561597072e-05,
      "loss": 0.347,
      "step": 580
    },
    {
      "epoch": 0.7829476652566973,
      "grad_norm": 0.48418239016974585,
      "learning_rate": 1.3793896030476794e-05,
      "loss": 0.3571,
      "step": 590
    },
    {
      "epoch": 0.7962179646678278,
      "grad_norm": 0.48310791104838363,
      "learning_rate": 1.223324832072874e-05,
      "loss": 0.3502,
      "step": 600
    },
    {
      "epoch": 0.8094882640789582,
      "grad_norm": 0.4353221983576734,
      "learning_rate": 1.0753912510299914e-05,
      "loss": 0.3553,
      "step": 610
    },
    {
      "epoch": 0.8227585634900887,
      "grad_norm": 0.46790234111723333,
      "learning_rate": 9.359073612439479e-06,
      "loss": 0.3519,
      "step": 620
    },
    {
      "epoch": 0.8360288629012192,
      "grad_norm": 0.41559816617683076,
      "learning_rate": 8.051734718358294e-06,
      "loss": 0.3483,
      "step": 630
    },
    {
      "epoch": 0.8492991623123497,
      "grad_norm": 0.4799175672540264,
      "learning_rate": 6.834710531566813e-06,
      "loss": 0.3575,
      "step": 640
    },
    {
      "epoch": 0.8625694617234801,
      "grad_norm": 0.43496600338444424,
      "learning_rate": 5.710621307812386e-06,
      "loss": 0.3527,
      "step": 650
    },
    {
      "epoch": 0.8758397611346106,
      "grad_norm": 0.45899202179509424,
      "learning_rate": 4.681887213662789e-06,
      "loss": 0.3528,
      "step": 660
    },
    {
      "epoch": 0.889110060545741,
      "grad_norm": 0.4505075287108172,
      "learning_rate": 3.7507231158823043e-06,
      "loss": 0.349,
      "step": 670
    },
    {
      "epoch": 0.9023803599568715,
      "grad_norm": 0.483137333927585,
      "learning_rate": 2.9191338128187475e-06,
      "loss": 0.3364,
      "step": 680
    },
    {
      "epoch": 0.9156506593680019,
      "grad_norm": 0.43930917960276566,
      "learning_rate": 2.188909718068166e-06,
      "loss": 0.3468,
      "step": 690
    },
    {
      "epoch": 0.9289209587791325,
      "grad_norm": 0.4506613367649586,
      "learning_rate": 1.5616230057104996e-06,
      "loss": 0.357,
      "step": 700
    },
    {
      "epoch": 0.942191258190263,
      "grad_norm": 0.42992688796344924,
      "learning_rate": 1.0386242254152467e-06,
      "loss": 0.342,
      "step": 710
    },
    {
      "epoch": 0.9554615576013934,
      "grad_norm": 0.4543528928052219,
      "learning_rate": 6.21039394705153e-07,
      "loss": 0.3562,
      "step": 720
    },
    {
      "epoch": 0.9687318570125238,
      "grad_norm": 0.4227861781724582,
      "learning_rate": 3.0976757463795916e-07,
      "loss": 0.341,
      "step": 730
    },
    {
      "epoch": 0.9820021564236543,
      "grad_norm": 0.4533519740020808,
      "learning_rate": 1.054789341259521e-07,
      "loss": 0.3285,
      "step": 740
    },
    {
      "epoch": 0.9952724558347847,
      "grad_norm": 0.4585388500863688,
      "learning_rate": 8.613307060878484e-09,
      "loss": 0.3452,
      "step": 750
    },
    {
      "epoch": 0.999253545658124,
      "step": 753,
      "total_flos": 104678168920064.0,
      "train_loss": 0.3982392142651724,
      "train_runtime": 21757.2776,
      "train_samples_per_second": 2.217,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 753,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 104678168920064.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}