{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2786873824287605,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027868738242876052,
      "grad_norm": 3.341921806335449,
      "learning_rate": 2.2222222222222225e-06,
      "loss": 3.1415,
      "step": 5
    },
    {
      "epoch": 0.0055737476485752105,
      "grad_norm": 3.4862101078033447,
      "learning_rate": 5e-06,
      "loss": 3.04,
      "step": 10
    },
    {
      "epoch": 0.008360621472862817,
      "grad_norm": 3.363572597503662,
      "learning_rate": 7.777777777777777e-06,
      "loss": 3.019,
      "step": 15
    },
    {
      "epoch": 0.011147495297150421,
      "grad_norm": 3.5916693210601807,
      "learning_rate": 1.0555555555555555e-05,
      "loss": 3.073,
      "step": 20
    },
    {
      "epoch": 0.013934369121438027,
      "grad_norm": 3.8997910022735596,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.0359,
      "step": 25
    },
    {
      "epoch": 0.016721242945725634,
      "grad_norm": 3.789405345916748,
      "learning_rate": 1.6111111111111115e-05,
      "loss": 2.9568,
      "step": 30
    },
    {
      "epoch": 0.019508116770013236,
      "grad_norm": 2.785924196243286,
      "learning_rate": 1.888888888888889e-05,
      "loss": 2.6633,
      "step": 35
    },
    {
      "epoch": 0.022294990594300842,
      "grad_norm": 2.715925693511963,
      "learning_rate": 2.1666666666666667e-05,
      "loss": 2.3416,
      "step": 40
    },
    {
      "epoch": 0.025081864418588447,
      "grad_norm": 1.851042628288269,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 2.304,
      "step": 45
    },
    {
      "epoch": 0.027868738242876053,
      "grad_norm": 1.1627306938171387,
      "learning_rate": 2.7222222222222223e-05,
      "loss": 2.0913,
      "step": 50
    },
    {
      "epoch": 0.03065561206716366,
      "grad_norm": 0.8980898857116699,
      "learning_rate": 3e-05,
      "loss": 1.9108,
      "step": 55
    },
    {
      "epoch": 0.03344248589145127,
      "grad_norm": 0.741324245929718,
      "learning_rate": 3.277777777777778e-05,
      "loss": 1.989,
      "step": 60
    },
    {
      "epoch": 0.03622935971573887,
      "grad_norm": 0.6890819668769836,
      "learning_rate": 3.555555555555556e-05,
      "loss": 1.8792,
      "step": 65
    },
    {
      "epoch": 0.03901623354002647,
      "grad_norm": 0.6898017525672913,
      "learning_rate": 3.8333333333333334e-05,
      "loss": 1.7895,
      "step": 70
    },
    {
      "epoch": 0.04180310736431408,
      "grad_norm": 0.6752148866653442,
      "learning_rate": 4.111111111111111e-05,
      "loss": 1.8742,
      "step": 75
    },
    {
      "epoch": 0.044589981188601684,
      "grad_norm": 0.6477967500686646,
      "learning_rate": 4.388888888888889e-05,
      "loss": 1.7473,
      "step": 80
    },
    {
      "epoch": 0.04737685501288929,
      "grad_norm": 0.6459152698516846,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.8558,
      "step": 85
    },
    {
      "epoch": 0.050163728837176895,
      "grad_norm": 0.6237108707427979,
      "learning_rate": 4.9444444444444446e-05,
      "loss": 1.7931,
      "step": 90
    },
    {
      "epoch": 0.0529506026614645,
      "grad_norm": 0.6388494968414307,
      "learning_rate": 5.222222222222223e-05,
      "loss": 1.7712,
      "step": 95
    },
    {
      "epoch": 0.055737476485752106,
      "grad_norm": 0.686677098274231,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.7316,
      "step": 100
    },
    {
      "epoch": 0.05852435031003971,
      "grad_norm": 0.612424910068512,
      "learning_rate": 5.7777777777777776e-05,
      "loss": 1.7602,
      "step": 105
    },
    {
      "epoch": 0.06131122413432732,
      "grad_norm": 0.8961934447288513,
      "learning_rate": 6.055555555555555e-05,
      "loss": 1.8706,
      "step": 110
    },
    {
      "epoch": 0.06409809795861493,
      "grad_norm": 0.7244030833244324,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.7701,
      "step": 115
    },
    {
      "epoch": 0.06688497178290254,
      "grad_norm": 0.6804441809654236,
      "learning_rate": 6.611111111111111e-05,
      "loss": 1.7833,
      "step": 120
    },
    {
      "epoch": 0.06967184560719013,
      "grad_norm": 0.6717159152030945,
      "learning_rate": 6.88888888888889e-05,
      "loss": 1.8445,
      "step": 125
    },
    {
      "epoch": 0.07245871943147773,
      "grad_norm": 0.6639799475669861,
      "learning_rate": 7.166666666666667e-05,
      "loss": 1.7847,
      "step": 130
    },
    {
      "epoch": 0.07524559325576534,
      "grad_norm": 0.7095969915390015,
      "learning_rate": 7.444444444444444e-05,
      "loss": 1.7281,
      "step": 135
    },
    {
      "epoch": 0.07803246708005294,
      "grad_norm": 0.8189035654067993,
      "learning_rate": 7.722222222222223e-05,
      "loss": 1.7678,
      "step": 140
    },
    {
      "epoch": 0.08081934090434055,
      "grad_norm": 0.6709702610969543,
      "learning_rate": 8e-05,
      "loss": 1.8645,
      "step": 145
    },
    {
      "epoch": 0.08360621472862816,
      "grad_norm": 0.743190348148346,
      "learning_rate": 8.277777777777778e-05,
      "loss": 1.8086,
      "step": 150
    },
    {
      "epoch": 0.08639308855291576,
      "grad_norm": 0.669023871421814,
      "learning_rate": 8.555555555555556e-05,
      "loss": 1.7844,
      "step": 155
    },
    {
      "epoch": 0.08917996237720337,
      "grad_norm": 0.8071898221969604,
      "learning_rate": 8.833333333333333e-05,
      "loss": 1.7379,
      "step": 160
    },
    {
      "epoch": 0.09196683620149097,
      "grad_norm": 0.7679445743560791,
      "learning_rate": 9.111111111111112e-05,
      "loss": 1.706,
      "step": 165
    },
    {
      "epoch": 0.09475371002577858,
      "grad_norm": 0.7896930575370789,
      "learning_rate": 9.388888888888889e-05,
      "loss": 1.7752,
      "step": 170
    },
    {
      "epoch": 0.09754058385006618,
      "grad_norm": 0.7258396744728088,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.7635,
      "step": 175
    },
    {
      "epoch": 0.10032745767435379,
      "grad_norm": 0.8085169196128845,
      "learning_rate": 9.944444444444446e-05,
      "loss": 1.7449,
      "step": 180
    },
    {
      "epoch": 0.1031143314986414,
      "grad_norm": 0.7673636674880981,
      "learning_rate": 9.999848639521432e-05,
      "loss": 1.7286,
      "step": 185
    },
    {
      "epoch": 0.105901205322929,
      "grad_norm": 0.7478857040405273,
      "learning_rate": 9.999233753283091e-05,
      "loss": 1.7203,
      "step": 190
    },
    {
      "epoch": 0.1086880791472166,
      "grad_norm": 0.8994764685630798,
      "learning_rate": 9.998145939378577e-05,
      "loss": 1.6964,
      "step": 195
    },
    {
      "epoch": 0.11147495297150421,
      "grad_norm": 0.7851970791816711,
      "learning_rate": 9.996585300715116e-05,
      "loss": 1.7513,
      "step": 200
    },
    {
      "epoch": 0.11426182679579182,
      "grad_norm": 0.7743813395500183,
      "learning_rate": 9.994551984929175e-05,
      "loss": 1.7099,
      "step": 205
    },
    {
      "epoch": 0.11704870062007942,
      "grad_norm": 0.7080249786376953,
      "learning_rate": 9.992046184372492e-05,
      "loss": 1.7431,
      "step": 210
    },
    {
      "epoch": 0.11983557444436703,
      "grad_norm": 0.744627058506012,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7159,
      "step": 215
    },
    {
      "epoch": 0.12262244826865464,
      "grad_norm": 0.7715389132499695,
      "learning_rate": 9.985618121816779e-05,
      "loss": 1.7696,
      "step": 220
    },
    {
      "epoch": 0.12540932209294225,
      "grad_norm": 0.7663665413856506,
      "learning_rate": 9.981696467912664e-05,
      "loss": 1.7205,
      "step": 225
    },
    {
      "epoch": 0.12819619591722986,
      "grad_norm": 0.7923425436019897,
      "learning_rate": 9.97730354537011e-05,
      "loss": 1.7136,
      "step": 230
    },
    {
      "epoch": 0.13098306974151747,
      "grad_norm": 0.7929289937019348,
      "learning_rate": 9.972439769759722e-05,
      "loss": 1.6462,
      "step": 235
    },
    {
      "epoch": 0.13376994356580507,
      "grad_norm": 0.845177948474884,
      "learning_rate": 9.967105601194823e-05,
      "loss": 1.8031,
      "step": 240
    },
    {
      "epoch": 0.13655681739009268,
      "grad_norm": 0.7540026307106018,
      "learning_rate": 9.961301544287922e-05,
      "loss": 1.6899,
      "step": 245
    },
    {
      "epoch": 0.13934369121438026,
      "grad_norm": 0.8806189894676208,
      "learning_rate": 9.955028148102979e-05,
      "loss": 1.6526,
      "step": 250
    },
    {
      "epoch": 0.14213056503866786,
      "grad_norm": 0.8206574320793152,
      "learning_rate": 9.948286006103466e-05,
      "loss": 1.8233,
      "step": 255
    },
    {
      "epoch": 0.14491743886295547,
      "grad_norm": 0.8984567523002625,
      "learning_rate": 9.941075756096226e-05,
      "loss": 1.7252,
      "step": 260
    },
    {
      "epoch": 0.14770431268724307,
      "grad_norm": 0.7411919832229614,
      "learning_rate": 9.933398080171123e-05,
      "loss": 1.7339,
      "step": 265
    },
    {
      "epoch": 0.15049118651153068,
      "grad_norm": 0.8030174970626831,
      "learning_rate": 9.925253704636543e-05,
      "loss": 1.6934,
      "step": 270
    },
    {
      "epoch": 0.15327806033581828,
      "grad_norm": 0.7879084944725037,
      "learning_rate": 9.916643399950656e-05,
      "loss": 1.7197,
      "step": 275
    },
    {
      "epoch": 0.1560649341601059,
      "grad_norm": 0.8534114956855774,
      "learning_rate": 9.907567980648549e-05,
      "loss": 1.6941,
      "step": 280
    },
    {
      "epoch": 0.1588518079843935,
      "grad_norm": 0.74381023645401,
      "learning_rate": 9.898028305265169e-05,
      "loss": 1.7919,
      "step": 285
    },
    {
      "epoch": 0.1616386818086811,
      "grad_norm": 0.8476956486701965,
      "learning_rate": 9.888025276254096e-05,
      "loss": 1.7417,
      "step": 290
    },
    {
      "epoch": 0.1644255556329687,
      "grad_norm": 0.8212200403213501,
      "learning_rate": 9.877559839902184e-05,
      "loss": 1.7452,
      "step": 295
    },
    {
      "epoch": 0.1672124294572563,
      "grad_norm": 0.8340197801589966,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.6687,
      "step": 300
    },
    {
      "epoch": 0.16999930328154392,
      "grad_norm": 0.858363151550293,
      "learning_rate": 9.855245748948326e-05,
      "loss": 1.7669,
      "step": 305
    },
    {
      "epoch": 0.17278617710583152,
      "grad_norm": 0.8392812013626099,
      "learning_rate": 9.843399205260068e-05,
      "loss": 1.736,
      "step": 310
    },
    {
      "epoch": 0.17557305093011913,
      "grad_norm": 0.8345137238502502,
      "learning_rate": 9.831094475858652e-05,
      "loss": 1.7264,
      "step": 315
    },
    {
      "epoch": 0.17835992475440673,
      "grad_norm": 0.8243482708930969,
      "learning_rate": 9.818332724771857e-05,
      "loss": 1.7748,
      "step": 320
    },
    {
      "epoch": 0.18114679857869434,
      "grad_norm": 0.8255311846733093,
      "learning_rate": 9.805115159261726e-05,
      "loss": 1.6798,
      "step": 325
    },
    {
      "epoch": 0.18393367240298195,
      "grad_norm": 0.8170781135559082,
      "learning_rate": 9.791443029710361e-05,
      "loss": 1.6542,
      "step": 330
    },
    {
      "epoch": 0.18672054622726955,
      "grad_norm": 0.8476420044898987,
      "learning_rate": 9.777317629501636e-05,
      "loss": 1.6875,
      "step": 335
    },
    {
      "epoch": 0.18950742005155716,
      "grad_norm": 0.7547033429145813,
      "learning_rate": 9.762740294898846e-05,
      "loss": 1.646,
      "step": 340
    },
    {
      "epoch": 0.19229429387584476,
      "grad_norm": 0.826404869556427,
      "learning_rate": 9.747712404918286e-05,
      "loss": 1.6187,
      "step": 345
    },
    {
      "epoch": 0.19508116770013237,
      "grad_norm": 0.964885950088501,
      "learning_rate": 9.732235381198813e-05,
      "loss": 1.7507,
      "step": 350
    },
    {
      "epoch": 0.19786804152441997,
      "grad_norm": 0.8207951188087463,
      "learning_rate": 9.716310687867342e-05,
      "loss": 1.5745,
      "step": 355
    },
    {
      "epoch": 0.20065491534870758,
      "grad_norm": 0.8143700361251831,
      "learning_rate": 9.699939831400351e-05,
      "loss": 1.7754,
      "step": 360
    },
    {
      "epoch": 0.20344178917299519,
      "grad_norm": 0.811844527721405,
      "learning_rate": 9.683124360481364e-05,
      "loss": 1.6993,
      "step": 365
    },
    {
      "epoch": 0.2062286629972828,
      "grad_norm": 0.8975111842155457,
      "learning_rate": 9.665865865854445e-05,
      "loss": 1.6901,
      "step": 370
    },
    {
      "epoch": 0.2090155368215704,
      "grad_norm": 0.7903837561607361,
      "learning_rate": 9.648165980173712e-05,
      "loss": 1.6895,
      "step": 375
    },
    {
      "epoch": 0.211802410645858,
      "grad_norm": 0.8718327879905701,
      "learning_rate": 9.630026377848892e-05,
      "loss": 1.6725,
      "step": 380
    },
    {
      "epoch": 0.2145892844701456,
      "grad_norm": 0.8131148219108582,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.6874,
      "step": 385
    },
    {
      "epoch": 0.2173761582944332,
      "grad_norm": 0.8331175446510315,
      "learning_rate": 9.592434928729616e-05,
      "loss": 1.7542,
      "step": 390
    },
    {
      "epoch": 0.22016303211872082,
      "grad_norm": 0.792988121509552,
      "learning_rate": 9.572986638087396e-05,
      "loss": 1.7311,
      "step": 395
    },
    {
      "epoch": 0.22294990594300843,
      "grad_norm": 0.7799636721611023,
      "learning_rate": 9.553105742769154e-05,
      "loss": 1.6567,
      "step": 400
    },
    {
      "epoch": 0.22573677976729603,
      "grad_norm": 0.7864108085632324,
      "learning_rate": 9.532794123508197e-05,
      "loss": 1.5611,
      "step": 405
    },
    {
      "epoch": 0.22852365359158364,
      "grad_norm": 0.8886444568634033,
      "learning_rate": 9.512053701784329e-05,
      "loss": 1.6995,
      "step": 410
    },
    {
      "epoch": 0.23131052741587124,
      "grad_norm": 0.7999454736709595,
      "learning_rate": 9.490886439642081e-05,
      "loss": 1.6898,
      "step": 415
    },
    {
      "epoch": 0.23409740124015885,
      "grad_norm": 0.7729182243347168,
      "learning_rate": 9.469294339505098e-05,
      "loss": 1.7204,
      "step": 420
    },
    {
      "epoch": 0.23688427506444645,
      "grad_norm": 0.8300912380218506,
      "learning_rate": 9.447279443986716e-05,
      "loss": 1.6668,
      "step": 425
    },
    {
      "epoch": 0.23967114888873406,
      "grad_norm": 0.840481698513031,
      "learning_rate": 9.424843835696724e-05,
      "loss": 1.704,
      "step": 430
    },
    {
      "epoch": 0.24245802271302166,
      "grad_norm": 0.9396219253540039,
      "learning_rate": 9.401989637044355e-05,
      "loss": 1.6713,
      "step": 435
    },
    {
      "epoch": 0.24524489653730927,
      "grad_norm": 0.8775554299354553,
      "learning_rate": 9.3787190100375e-05,
      "loss": 1.6883,
      "step": 440
    },
    {
      "epoch": 0.24803177036159688,
      "grad_norm": 0.8623490333557129,
      "learning_rate": 9.355034156078188e-05,
      "loss": 1.6783,
      "step": 445
    },
    {
      "epoch": 0.2508186441858845,
      "grad_norm": 0.806533694267273,
      "learning_rate": 9.330937315754329e-05,
      "loss": 1.6853,
      "step": 450
    },
    {
      "epoch": 0.2536055180101721,
      "grad_norm": 0.8504590392112732,
      "learning_rate": 9.306430768627753e-05,
      "loss": 1.6594,
      "step": 455
    },
    {
      "epoch": 0.2563923918344597,
      "grad_norm": 0.9382562637329102,
      "learning_rate": 9.281516833018571e-05,
      "loss": 1.6827,
      "step": 460
    },
    {
      "epoch": 0.2591792656587473,
      "grad_norm": 0.821978747844696,
      "learning_rate": 9.256197865785854e-05,
      "loss": 1.752,
      "step": 465
    },
    {
      "epoch": 0.26196613948303493,
      "grad_norm": 0.8061692714691162,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.6773,
      "step": 470
    },
    {
      "epoch": 0.26475301330732254,
      "grad_norm": 0.8759399652481079,
      "learning_rate": 9.204354455239539e-05,
      "loss": 1.7003,
      "step": 475
    },
    {
      "epoch": 0.26753988713161014,
      "grad_norm": 0.8721809387207031,
      "learning_rate": 9.177834916314165e-05,
      "loss": 1.6898,
      "step": 480
    },
    {
      "epoch": 0.27032676095589775,
      "grad_norm": 0.7904046773910522,
      "learning_rate": 9.150920154077754e-05,
      "loss": 1.6636,
      "step": 485
    },
    {
      "epoch": 0.27311363478018535,
      "grad_norm": 0.8828450441360474,
      "learning_rate": 9.123612714667634e-05,
      "loss": 1.6945,
      "step": 490
    },
    {
      "epoch": 0.2759005086044729,
      "grad_norm": 0.7389103174209595,
      "learning_rate": 9.095915181368412e-05,
      "loss": 1.7459,
      "step": 495
    },
    {
      "epoch": 0.2786873824287605,
      "grad_norm": 0.975307285785675,
      "learning_rate": 9.067830174367586e-05,
      "loss": 1.7296,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 1795,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5663020915064832.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}