{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99867197875166,
  "eval_steps": 1000,
  "global_step": 376,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026560424966799467,
      "grad_norm": 1402.69921875,
      "learning_rate": 0.0,
      "loss": 52.5156,
      "step": 1
    },
    {
      "epoch": 0.013280212483399735,
      "grad_norm": 636.0113525390625,
      "learning_rate": 3.1578947368421045e-05,
      "loss": 32.8066,
      "step": 5
    },
    {
      "epoch": 0.02656042496679947,
      "grad_norm": 475.96771240234375,
      "learning_rate": 7.105263157894735e-05,
      "loss": 8.907,
      "step": 10
    },
    {
      "epoch": 0.0398406374501992,
      "grad_norm": 109.1396713256836,
      "learning_rate": 0.00011052631578947366,
      "loss": 6.3063,
      "step": 15
    },
    {
      "epoch": 0.05312084993359894,
      "grad_norm": 12.496488571166992,
      "learning_rate": 0.00015,
      "loss": 4.4115,
      "step": 20
    },
    {
      "epoch": 0.06640106241699867,
      "grad_norm": 88.81600952148438,
      "learning_rate": 0.0001894736842105263,
      "loss": 3.3893,
      "step": 25
    },
    {
      "epoch": 0.0796812749003984,
      "grad_norm": 107.62394714355469,
      "learning_rate": 0.00022894736842105263,
      "loss": 9.3801,
      "step": 30
    },
    {
      "epoch": 0.09296148738379814,
      "grad_norm": 7.125447750091553,
      "learning_rate": 0.0002684210526315789,
      "loss": 4.3988,
      "step": 35
    },
    {
      "epoch": 0.10624169986719788,
      "grad_norm": 15.962409973144531,
      "learning_rate": 0.0002999935207538156,
      "loss": 4.009,
      "step": 40
    },
    {
      "epoch": 0.11952191235059761,
      "grad_norm": 11.288817405700684,
      "learning_rate": 0.00029976680590482896,
      "loss": 3.0982,
      "step": 45
    },
    {
      "epoch": 0.13280212483399734,
      "grad_norm": 9.365798950195312,
      "learning_rate": 0.0002992166882710483,
      "loss": 5.2771,
      "step": 50
    },
    {
      "epoch": 0.1460823373173971,
      "grad_norm": 52.74184036254883,
      "learning_rate": 0.0002983443557630634,
      "loss": 6.7707,
      "step": 55
    },
    {
      "epoch": 0.1593625498007968,
      "grad_norm": 5.0402116775512695,
      "learning_rate": 0.00029715169207439795,
      "loss": 4.2547,
      "step": 60
    },
    {
      "epoch": 0.17264276228419656,
      "grad_norm": 5.552392482757568,
      "learning_rate": 0.00029564127261390776,
      "loss": 2.7717,
      "step": 65
    },
    {
      "epoch": 0.18592297476759628,
      "grad_norm": 3.872722864151001,
      "learning_rate": 0.0002938163589445058,
      "loss": 2.6939,
      "step": 70
    },
    {
      "epoch": 0.199203187250996,
      "grad_norm": 5.162952899932861,
      "learning_rate": 0.0002916808917402228,
      "loss": 2.6598,
      "step": 75
    },
    {
      "epoch": 0.21248339973439576,
      "grad_norm": 4.01698637008667,
      "learning_rate": 0.0002892394822768119,
      "loss": 2.6768,
      "step": 80
    },
    {
      "epoch": 0.22576361221779548,
      "grad_norm": 3.66325306892395,
      "learning_rate": 0.0002864974024742725,
      "loss": 2.6551,
      "step": 85
    },
    {
      "epoch": 0.23904382470119523,
      "grad_norm": 3.5804343223571777,
      "learning_rate": 0.00028346057351279474,
      "loss": 2.6633,
      "step": 90
    },
    {
      "epoch": 0.25232403718459495,
      "grad_norm": 3.087800979614258,
      "learning_rate": 0.00028013555304670765,
      "loss": 2.632,
      "step": 95
    },
    {
      "epoch": 0.2656042496679947,
      "grad_norm": 3.0033605098724365,
      "learning_rate": 0.00027652952104404045,
      "loss": 2.5992,
      "step": 100
    },
    {
      "epoch": 0.2788844621513944,
      "grad_norm": 2.973752021789551,
      "learning_rate": 0.0002726502642822747,
      "loss": 2.552,
      "step": 105
    },
    {
      "epoch": 0.2921646746347942,
      "grad_norm": 2.6142959594726562,
      "learning_rate": 0.00026850615953376744,
      "loss": 2.582,
      "step": 110
    },
    {
      "epoch": 0.3054448871181939,
      "grad_norm": 2.8691508769989014,
      "learning_rate": 0.00026410615547715297,
      "loss": 2.5102,
      "step": 115
    },
    {
      "epoch": 0.3187250996015936,
      "grad_norm": 3.016436815261841,
      "learning_rate": 0.00025945975337378515,
      "loss": 2.5391,
      "step": 120
    },
    {
      "epoch": 0.33200531208499334,
      "grad_norm": 2.747736930847168,
      "learning_rate": 0.00025457698655094495,
      "loss": 2.5082,
      "step": 125
    },
    {
      "epoch": 0.3452855245683931,
      "grad_norm": 2.5107271671295166,
      "learning_rate": 0.00024946839873611924,
      "loss": 2.5054,
      "step": 130
    },
    {
      "epoch": 0.35856573705179284,
      "grad_norm": 2.436136484146118,
      "learning_rate": 0.00024414502128913227,
      "loss": 2.4813,
      "step": 135
    },
    {
      "epoch": 0.37184594953519257,
      "grad_norm": 2.58207631111145,
      "learning_rate": 0.00023861834938129696,
      "loss": 2.4547,
      "step": 140
    },
    {
      "epoch": 0.3851261620185923,
      "grad_norm": 2.4167120456695557,
      "learning_rate": 0.00023290031717302254,
      "loss": 2.4403,
      "step": 145
    },
    {
      "epoch": 0.398406374501992,
      "grad_norm": 2.3588924407958984,
      "learning_rate": 0.00022700327204347966,
      "loss": 2.4169,
      "step": 150
    },
    {
      "epoch": 0.4116865869853918,
      "grad_norm": 2.468594789505005,
      "learning_rate": 0.00022093994792797152,
      "loss": 2.3924,
      "step": 155
    },
    {
      "epoch": 0.4249667994687915,
      "grad_norm": 2.52724552154541,
      "learning_rate": 0.00021472343782058458,
      "loss": 2.3804,
      "step": 160
    },
    {
      "epoch": 0.43824701195219123,
      "grad_norm": 2.2549281120300293,
      "learning_rate": 0.00020836716550149683,
      "loss": 2.3681,
      "step": 165
    },
    {
      "epoch": 0.45152722443559096,
      "grad_norm": 2.3330459594726562,
      "learning_rate": 0.00020188485654999466,
      "loss": 2.3404,
      "step": 170
    },
    {
      "epoch": 0.4648074369189907,
      "grad_norm": 2.2739274501800537,
      "learning_rate": 0.0001952905087057917,
      "loss": 2.2986,
      "step": 175
    },
    {
      "epoch": 0.47808764940239046,
      "grad_norm": 2.257761001586914,
      "learning_rate": 0.00018859836164265164,
      "loss": 2.328,
      "step": 180
    },
    {
      "epoch": 0.4913678618857902,
      "grad_norm": 2.2927610874176025,
      "learning_rate": 0.00018182286621958436,
      "loss": 2.2641,
      "step": 185
    },
    {
      "epoch": 0.5046480743691899,
      "grad_norm": 2.1379075050354004,
      "learning_rate": 0.00017497865327601326,
      "loss": 2.2607,
      "step": 190
    },
    {
      "epoch": 0.5179282868525896,
      "grad_norm": 2.1380867958068848,
      "learning_rate": 0.00016808050203829842,
      "loss": 2.2726,
      "step": 195
    },
    {
      "epoch": 0.5312084993359893,
      "grad_norm": 2.1610195636749268,
      "learning_rate": 0.00016114330820583557,
      "loss": 2.2329,
      "step": 200
    },
    {
      "epoch": 0.5444887118193891,
      "grad_norm": 2.081423044204712,
      "learning_rate": 0.00015418205178564621,
      "loss": 2.2403,
      "step": 205
    },
    {
      "epoch": 0.5577689243027888,
      "grad_norm": 2.0720622539520264,
      "learning_rate": 0.0001472117647449168,
      "loss": 2.2263,
      "step": 210
    },
    {
      "epoch": 0.5710491367861886,
      "grad_norm": 2.028615713119507,
      "learning_rate": 0.0001402474985513351,
      "loss": 2.1766,
      "step": 215
    },
    {
      "epoch": 0.5843293492695883,
      "grad_norm": 2.022357702255249,
      "learning_rate": 0.00013330429167131863,
      "loss": 2.1622,
      "step": 220
    },
    {
      "epoch": 0.5976095617529881,
      "grad_norm": 1.9566619396209717,
      "learning_rate": 0.00012639713709631706,
      "loss": 2.141,
      "step": 225
    },
    {
      "epoch": 0.6108897742363878,
      "grad_norm": 2.0382509231567383,
      "learning_rate": 0.000119540949967313,
      "loss": 2.1133,
      "step": 230
    },
    {
      "epoch": 0.6241699867197875,
      "grad_norm": 2.006354570388794,
      "learning_rate": 0.00011275053536743006,
      "loss": 2.0986,
      "step": 235
    },
    {
      "epoch": 0.6374501992031872,
      "grad_norm": 1.9956600666046143,
      "learning_rate": 0.00010604055635219803,
      "loss": 2.0761,
      "step": 240
    },
    {
      "epoch": 0.650730411686587,
      "grad_norm": 1.9418437480926514,
      "learning_rate": 9.942550228650876e-05,
      "loss": 2.0824,
      "step": 245
    },
    {
      "epoch": 0.6640106241699867,
      "grad_norm": 1.95418381690979,
      "learning_rate": 9.291965755663522e-05,
      "loss": 2.1084,
      "step": 250
    },
    {
      "epoch": 0.6772908366533864,
      "grad_norm": 1.961089849472046,
      "learning_rate": 8.653707072487629e-05,
      "loss": 2.053,
      "step": 255
    },
    {
      "epoch": 0.6905710491367862,
      "grad_norm": 1.9297434091567993,
      "learning_rate": 8.02915241934347e-05,
      "loss": 2.0788,
      "step": 260
    },
    {
      "epoch": 0.703851261620186,
      "grad_norm": 1.9308726787567139,
      "learning_rate": 7.419650444303376e-05,
      "loss": 2.0137,
      "step": 265
    },
    {
      "epoch": 0.7171314741035857,
      "grad_norm": 1.8884217739105225,
      "learning_rate": 6.82651729105402e-05,
      "loss": 2.025,
      "step": 270
    },
    {
      "epoch": 0.7304116865869854,
      "grad_norm": 1.9265509843826294,
      "learning_rate": 6.251033756847875e-05,
      "loss": 1.9988,
      "step": 275
    },
    {
      "epoch": 0.7436918990703851,
      "grad_norm": 1.8479654788970947,
      "learning_rate": 5.694442526780891e-05,
      "loss": 2.0355,
      "step": 280
    },
    {
      "epoch": 0.7569721115537849,
      "grad_norm": 1.915022850036621,
      "learning_rate": 5.157945490368621e-05,
      "loss": 1.9948,
      "step": 285
    },
    {
      "epoch": 0.7702523240371846,
      "grad_norm": 1.9624898433685303,
      "learning_rate": 4.6427011462153554e-05,
      "loss": 1.9742,
      "step": 290
    },
    {
      "epoch": 0.7835325365205843,
      "grad_norm": 1.8428194522857666,
      "learning_rate": 4.149822100380507e-05,
      "loss": 1.9431,
      "step": 295
    },
    {
      "epoch": 0.796812749003984,
      "grad_norm": 1.8078436851501465,
      "learning_rate": 3.680372663844246e-05,
      "loss": 1.9428,
      "step": 300
    },
    {
      "epoch": 0.8100929614873837,
      "grad_norm": 1.8866031169891357,
      "learning_rate": 3.235366554260351e-05,
      "loss": 1.9581,
      "step": 305
    },
    {
      "epoch": 0.8233731739707836,
      "grad_norm": 1.9002296924591064,
      "learning_rate": 2.8157647069590534e-05,
      "loss": 1.9669,
      "step": 310
    },
    {
      "epoch": 0.8366533864541833,
      "grad_norm": 1.8117656707763672,
      "learning_rate": 2.422473199926742e-05,
      "loss": 1.9113,
      "step": 315
    },
    {
      "epoch": 0.849933598937583,
      "grad_norm": 1.7977352142333984,
      "learning_rate": 2.056341297243272e-05,
      "loss": 1.9298,
      "step": 320
    },
    {
      "epoch": 0.8632138114209827,
      "grad_norm": 1.824103593826294,
      "learning_rate": 1.718159615201853e-05,
      "loss": 1.8986,
      "step": 325
    },
    {
      "epoch": 0.8764940239043825,
      "grad_norm": 1.8645001649856567,
      "learning_rate": 1.4086584150715103e-05,
      "loss": 1.9055,
      "step": 330
    },
    {
      "epoch": 0.8897742363877822,
      "grad_norm": 1.8154819011688232,
      "learning_rate": 1.1285060261887419e-05,
      "loss": 1.9125,
      "step": 335
    },
    {
      "epoch": 0.9030544488711819,
      "grad_norm": 1.8848274946212769,
      "learning_rate": 8.783074027834514e-06,
      "loss": 1.9312,
      "step": 340
    },
    {
      "epoch": 0.9163346613545816,
      "grad_norm": 1.8445605039596558,
      "learning_rate": 6.586028176555536e-06,
      "loss": 1.9288,
      "step": 345
    },
    {
      "epoch": 0.9296148738379814,
      "grad_norm": 1.8792498111724854,
      "learning_rate": 4.698666955230862e-06,
      "loss": 1.8988,
      "step": 350
    },
    {
      "epoch": 0.9428950863213812,
      "grad_norm": 1.8407002687454224,
      "learning_rate": 3.125065885610456e-06,
      "loss": 1.8648,
      "step": 355
    },
    {
      "epoch": 0.9561752988047809,
      "grad_norm": 1.7950658798217773,
      "learning_rate": 1.8686229634317206e-06,
      "loss": 1.9352,
      "step": 360
    },
    {
      "epoch": 0.9694555112881806,
      "grad_norm": 1.8157298564910889,
      "learning_rate": 9.320513208704638e-07,
      "loss": 1.8703,
      "step": 365
    },
    {
      "epoch": 0.9827357237715804,
      "grad_norm": 1.839713454246521,
      "learning_rate": 3.173733678694834e-07,
      "loss": 1.8878,
      "step": 370
    },
    {
      "epoch": 0.9960159362549801,
      "grad_norm": 1.858101487159729,
      "learning_rate": 2.5916424995919837e-08,
      "loss": 1.9159,
      "step": 375
    }
  ],
  "logging_steps": 5,
  "max_steps": 376,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 4.656989204616577e+18,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}