{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 446,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02009545340366742,
      "grad_norm": 101.4629135131836,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.9256,
      "step": 5
    },
    {
      "epoch": 0.04019090680733484,
      "grad_norm": 83.51904296875,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.7459,
      "step": 10
    },
    {
      "epoch": 0.06028636021100226,
      "grad_norm": 25.10388946533203,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.637,
      "step": 15
    },
    {
      "epoch": 0.08038181361466969,
      "grad_norm": 13.024300575256348,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 1.1459,
      "step": 20
    },
    {
      "epoch": 0.1004772670183371,
      "grad_norm": 8.315956115722656,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.7456,
      "step": 25
    },
    {
      "epoch": 0.12057272042200452,
      "grad_norm": 8.930346488952637,
      "learning_rate": 2.9e-06,
      "loss": 0.5717,
      "step": 30
    },
    {
      "epoch": 0.14066817382567195,
      "grad_norm": 7.356456756591797,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.414,
      "step": 35
    },
    {
      "epoch": 0.16076362722933937,
      "grad_norm": 5.648008346557617,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.2577,
      "step": 40
    },
    {
      "epoch": 0.1808590806330068,
      "grad_norm": 6.329988956451416,
      "learning_rate": 4.4e-06,
      "loss": 0.2394,
      "step": 45
    },
    {
      "epoch": 0.2009545340366742,
      "grad_norm": 5.1738080978393555,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.1848,
      "step": 50
    },
    {
      "epoch": 0.22104998744034163,
      "grad_norm": 4.86478853225708,
      "learning_rate": 4.999016565957633e-06,
      "loss": 0.2195,
      "step": 55
    },
    {
      "epoch": 0.24114544084400905,
      "grad_norm": 4.442976474761963,
      "learning_rate": 4.995022691166621e-06,
      "loss": 0.1582,
      "step": 60
    },
    {
      "epoch": 0.26124089424767644,
      "grad_norm": 3.704345941543579,
      "learning_rate": 4.987961816680493e-06,
      "loss": 0.183,
      "step": 65
    },
    {
      "epoch": 0.2813363476513439,
      "grad_norm": 3.772160768508911,
      "learning_rate": 4.977842622059546e-06,
      "loss": 0.164,
      "step": 70
    },
    {
      "epoch": 0.30143180105501133,
      "grad_norm": 3.2532081604003906,
      "learning_rate": 4.96467754629559e-06,
      "loss": 0.1781,
      "step": 75
    },
    {
      "epoch": 0.32152725445867875,
      "grad_norm": 2.893615484237671,
      "learning_rate": 4.948482772521346e-06,
      "loss": 0.1288,
      "step": 80
    },
    {
      "epoch": 0.34162270786234616,
      "grad_norm": 4.654979705810547,
      "learning_rate": 4.929278208117378e-06,
      "loss": 0.1444,
      "step": 85
    },
    {
      "epoch": 0.3617181612660136,
      "grad_norm": 2.8989882469177246,
      "learning_rate": 4.907087460240999e-06,
      "loss": 0.1151,
      "step": 90
    },
    {
      "epoch": 0.381813614669681,
      "grad_norm": 3.7547988891601562,
      "learning_rate": 4.881937806807241e-06,
      "loss": 0.1197,
      "step": 95
    },
    {
      "epoch": 0.4019090680733484,
      "grad_norm": 2.273831605911255,
      "learning_rate": 4.8538601629575525e-06,
      "loss": 0.0966,
      "step": 100
    },
    {
      "epoch": 0.42200452147701584,
      "grad_norm": 2.4642996788024902,
      "learning_rate": 4.822889043057446e-06,
      "loss": 0.1088,
      "step": 105
    },
    {
      "epoch": 0.44209997488068326,
      "grad_norm": 3.29301381111145,
      "learning_rate": 4.789062518269812e-06,
      "loss": 0.1163,
      "step": 110
    },
    {
      "epoch": 0.4621954282843507,
      "grad_norm": 2.45603084564209,
      "learning_rate": 4.752422169756048e-06,
      "loss": 0.1151,
      "step": 115
    },
    {
      "epoch": 0.4822908816880181,
      "grad_norm": 3.199894666671753,
      "learning_rate": 4.713013037562531e-06,
      "loss": 0.098,
      "step": 120
    },
    {
      "epoch": 0.5023863350916855,
      "grad_norm": 1.7128061056137085,
      "learning_rate": 4.670883565255264e-06,
      "loss": 0.0968,
      "step": 125
    },
    {
      "epoch": 0.5224817884953529,
      "grad_norm": 2.645235776901245,
      "learning_rate": 4.6260855403707625e-06,
      "loss": 0.1068,
      "step": 130
    },
    {
      "epoch": 0.5425772418990203,
      "grad_norm": 2.3140530586242676,
      "learning_rate": 4.578674030756364e-06,
      "loss": 0.0914,
      "step": 135
    },
    {
      "epoch": 0.5626726953026878,
      "grad_norm": 1.8588067293167114,
      "learning_rate": 4.528707316878233e-06,
      "loss": 0.0995,
      "step": 140
    },
    {
      "epoch": 0.5827681487063552,
      "grad_norm": 1.9172967672348022,
      "learning_rate": 4.476246820180259e-06,
      "loss": 0.08,
      "step": 145
    },
    {
      "epoch": 0.6028636021100227,
      "grad_norm": 2.9082584381103516,
      "learning_rate": 4.421357027581921e-06,
      "loss": 0.1066,
      "step": 150
    },
    {
      "epoch": 0.62295905551369,
      "grad_norm": 3.6944031715393066,
      "learning_rate": 4.364105412207914e-06,
      "loss": 0.1124,
      "step": 155
    },
    {
      "epoch": 0.6430545089173575,
      "grad_norm": 1.5622600317001343,
      "learning_rate": 4.304562350447008e-06,
      "loss": 0.0856,
      "step": 160
    },
    {
      "epoch": 0.6631499623210249,
      "grad_norm": 2.388239860534668,
      "learning_rate": 4.242801035442059e-06,
      "loss": 0.0766,
      "step": 165
    },
    {
      "epoch": 0.6832454157246923,
      "grad_norm": 1.7182718515396118,
      "learning_rate": 4.178897387117547e-06,
      "loss": 0.104,
      "step": 170
    },
    {
      "epoch": 0.7033408691283597,
      "grad_norm": 2.2367119789123535,
      "learning_rate": 4.11292995885522e-06,
      "loss": 0.0737,
      "step": 175
    },
    {
      "epoch": 0.7234363225320272,
      "grad_norm": 2.007200241088867,
      "learning_rate": 4.044979840932567e-06,
      "loss": 0.0893,
      "step": 180
    },
    {
      "epoch": 0.7435317759356945,
      "grad_norm": 2.6910905838012695,
      "learning_rate": 3.975130560842821e-06,
      "loss": 0.0944,
      "step": 185
    },
    {
      "epoch": 0.763627229339362,
      "grad_norm": 2.042320489883423,
      "learning_rate": 3.9034679806190204e-06,
      "loss": 0.0843,
      "step": 190
    },
    {
      "epoch": 0.7837226827430294,
      "grad_norm": 2.700977087020874,
      "learning_rate": 3.830080191288342e-06,
      "loss": 0.0669,
      "step": 195
    },
    {
      "epoch": 0.8038181361466968,
      "grad_norm": 3.0307390689849854,
      "learning_rate": 3.755057404586455e-06,
      "loss": 0.0955,
      "step": 200
    },
    {
      "epoch": 0.9197980931015143,
      "grad_norm": 1.7615673542022705,
      "learning_rate": 4.444444444444445e-07,
      "loss": 0.0637,
      "step": 205
    },
    {
      "epoch": 0.9422321929332585,
      "grad_norm": 0.7652507424354553,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0608,
      "step": 210
    },
    {
      "epoch": 0.9646662927650028,
      "grad_norm": 2.094982147216797,
      "learning_rate": 1.5555555555555558e-06,
      "loss": 0.0747,
      "step": 215
    },
    {
      "epoch": 0.9871003925967471,
      "grad_norm": 1.708694577217102,
      "learning_rate": 2.1111111111111114e-06,
      "loss": 0.0801,
      "step": 220
    },
    {
      "epoch": 1.0089736399326976,
      "grad_norm": 1.0560003519058228,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.0655,
      "step": 225
    },
    {
      "epoch": 1.0314077397644419,
      "grad_norm": 0.5668569207191467,
      "learning_rate": 3.2222222222222227e-06,
      "loss": 0.0574,
      "step": 230
    },
    {
      "epoch": 1.0538418395961862,
      "grad_norm": 1.4594504833221436,
      "learning_rate": 3.777777777777778e-06,
      "loss": 0.0608,
      "step": 235
    },
    {
      "epoch": 1.0762759394279304,
      "grad_norm": 1.9404547214508057,
      "learning_rate": 4.333333333333334e-06,
      "loss": 0.0568,
      "step": 240
    },
    {
      "epoch": 1.0987100392596747,
      "grad_norm": 1.714486002922058,
      "learning_rate": 4.888888888888889e-06,
      "loss": 0.0525,
      "step": 245
    },
    {
      "epoch": 1.121144139091419,
      "grad_norm": 1.0862603187561035,
      "learning_rate": 4.998772545353743e-06,
      "loss": 0.0593,
      "step": 250
    },
    {
      "epoch": 1.1435782389231632,
      "grad_norm": 1.032120704650879,
      "learning_rate": 4.99378807653289e-06,
      "loss": 0.049,
      "step": 255
    },
    {
      "epoch": 1.1660123387549075,
      "grad_norm": 1.2163769006729126,
      "learning_rate": 4.984977519145677e-06,
      "loss": 0.0569,
      "step": 260
    },
    {
      "epoch": 1.1884464385866518,
      "grad_norm": 1.6339250802993774,
      "learning_rate": 4.9723543907693185e-06,
      "loss": 0.0542,
      "step": 265
    },
    {
      "epoch": 1.210880538418396,
      "grad_norm": 0.9572290182113647,
      "learning_rate": 4.955938058409217e-06,
      "loss": 0.0548,
      "step": 270
    },
    {
      "epoch": 1.2333146382501403,
      "grad_norm": 1.0672987699508667,
      "learning_rate": 4.935753708785181e-06,
      "loss": 0.0538,
      "step": 275
    },
    {
      "epoch": 1.2557487380818846,
      "grad_norm": 0.6455779671669006,
      "learning_rate": 4.911832309688758e-06,
      "loss": 0.0594,
      "step": 280
    },
    {
      "epoch": 1.2781828379136286,
      "grad_norm": 1.5325645208358765,
      "learning_rate": 4.884210562470972e-06,
      "loss": 0.061,
      "step": 285
    },
    {
      "epoch": 1.300616937745373,
      "grad_norm": 0.7859523892402649,
      "learning_rate": 4.852930845733358e-06,
      "loss": 0.0643,
      "step": 290
    },
    {
      "epoch": 1.3230510375771172,
      "grad_norm": 1.0552711486816406,
      "learning_rate": 4.818041150308695e-06,
      "loss": 0.0572,
      "step": 295
    },
    {
      "epoch": 1.3454851374088614,
      "grad_norm": 1.5569571256637573,
      "learning_rate": 4.779595005631185e-06,
      "loss": 0.0606,
      "step": 300
    },
    {
      "epoch": 1.3679192372406057,
      "grad_norm": 1.921815037727356,
      "learning_rate": 4.737651397609031e-06,
      "loss": 0.0658,
      "step": 305
    },
    {
      "epoch": 1.39035333707235,
      "grad_norm": 2.8975815773010254,
      "learning_rate": 4.692274678125461e-06,
      "loss": 0.0625,
      "step": 310
    },
    {
      "epoch": 1.4127874369040943,
      "grad_norm": 2.124173164367676,
      "learning_rate": 4.643534466306983e-06,
      "loss": 0.049,
      "step": 315
    },
    {
      "epoch": 1.4352215367358385,
      "grad_norm": 2.736834764480591,
      "learning_rate": 4.591505541710419e-06,
      "loss": 0.0551,
      "step": 320
    },
    {
      "epoch": 1.4576556365675828,
      "grad_norm": 0.8361607789993286,
      "learning_rate": 4.536267729592529e-06,
      "loss": 0.0553,
      "step": 325
    },
    {
      "epoch": 1.4800897363993268,
      "grad_norm": 1.3630151748657227,
      "learning_rate": 4.477905778438303e-06,
      "loss": 0.0585,
      "step": 330
    },
    {
      "epoch": 1.502523836231071,
      "grad_norm": 1.0196648836135864,
      "learning_rate": 4.416509229935797e-06,
      "loss": 0.051,
      "step": 335
    },
    {
      "epoch": 1.5249579360628154,
      "grad_norm": 1.5100717544555664,
      "learning_rate": 4.352172281596999e-06,
      "loss": 0.0618,
      "step": 340
    },
    {
      "epoch": 1.5473920358945596,
      "grad_norm": 1.5592113733291626,
      "learning_rate": 4.2849936422355235e-06,
      "loss": 0.0601,
      "step": 345
    },
    {
      "epoch": 1.569826135726304,
      "grad_norm": 1.8587521314620972,
      "learning_rate": 4.215076380522832e-06,
      "loss": 0.0585,
      "step": 350
    },
    {
      "epoch": 1.5922602355580482,
      "grad_norm": 0.962103009223938,
      "learning_rate": 4.142527766855376e-06,
      "loss": 0.0531,
      "step": 355
    },
    {
      "epoch": 1.6146943353897925,
      "grad_norm": 0.5082327127456665,
      "learning_rate": 4.067459108775233e-06,
      "loss": 0.0505,
      "step": 360
    },
    {
      "epoch": 1.6371284352215367,
      "grad_norm": 1.0577619075775146,
      "learning_rate": 3.989985580196767e-06,
      "loss": 0.0519,
      "step": 365
    },
    {
      "epoch": 1.659562535053281,
      "grad_norm": 1.6792018413543701,
      "learning_rate": 3.910226044701323e-06,
      "loss": 0.0639,
      "step": 370
    },
    {
      "epoch": 1.6819966348850253,
      "grad_norm": 1.4290854930877686,
      "learning_rate": 3.828302873171048e-06,
      "loss": 0.0576,
      "step": 375
    },
    {
      "epoch": 1.7044307347167695,
      "grad_norm": 2.5092132091522217,
      "learning_rate": 3.744341756041655e-06,
      "loss": 0.0569,
      "step": 380
    },
    {
      "epoch": 1.7268648345485138,
      "grad_norm": 0.4947376251220703,
      "learning_rate": 3.65847151046216e-06,
      "loss": 0.0458,
      "step": 385
    },
    {
      "epoch": 1.749298934380258,
      "grad_norm": 1.1118119955062866,
      "learning_rate": 3.5708238826574693e-06,
      "loss": 0.0649,
      "step": 390
    },
    {
      "epoch": 1.7717330342120023,
      "grad_norm": 1.0865488052368164,
      "learning_rate": 3.4815333457970425e-06,
      "loss": 0.048,
      "step": 395
    },
    {
      "epoch": 1.7941671340437466,
      "grad_norm": 1.0736117362976074,
      "learning_rate": 3.3907368936797443e-06,
      "loss": 0.055,
      "step": 400
    },
    {
      "epoch": 1.8166012338754909,
      "grad_norm": 2.9955170154571533,
      "learning_rate": 3.2985738305514246e-06,
      "loss": 0.0548,
      "step": 405
    },
    {
      "epoch": 1.8390353337072352,
      "grad_norm": 2.0711355209350586,
      "learning_rate": 3.2051855573777045e-06,
      "loss": 0.0517,
      "step": 410
    },
    {
      "epoch": 1.8614694335389792,
      "grad_norm": 1.2565196752548218,
      "learning_rate": 3.110715354899873e-06,
      "loss": 0.0506,
      "step": 415
    },
    {
      "epoch": 1.8839035333707235,
      "grad_norm": 0.7193956971168518,
      "learning_rate": 3.015308163806741e-06,
      "loss": 0.0479,
      "step": 420
    },
    {
      "epoch": 1.9063376332024677,
      "grad_norm": 0.479004442691803,
      "learning_rate": 2.919110362359727e-06,
      "loss": 0.0521,
      "step": 425
    },
    {
      "epoch": 1.928771733034212,
      "grad_norm": 0.9451120495796204,
      "learning_rate": 2.8222695418123508e-06,
      "loss": 0.0487,
      "step": 430
    },
    {
      "epoch": 1.9512058328659563,
      "grad_norm": 1.3489652872085571,
      "learning_rate": 2.724934279968692e-06,
      "loss": 0.0525,
      "step": 435
    },
    {
      "epoch": 1.9736399326977005,
      "grad_norm": 0.9737146496772766,
      "learning_rate": 2.6272539132282413e-06,
      "loss": 0.048,
      "step": 440
    },
    {
      "epoch": 1.9960740325294446,
      "grad_norm": 1.2973988056182861,
      "learning_rate": 2.5293783074668787e-06,
      "loss": 0.0482,
      "step": 445
    },
    {
      "epoch": 2.0,
      "step": 446,
      "total_flos": 1.161930774044971e+18,
      "train_loss": 0.03131445960012252,
      "train_runtime": 5241.0605,
      "train_samples_per_second": 5.442,
      "train_steps_per_second": 0.085
    }
  ],
  "logging_steps": 5,
  "max_steps": 446,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.161930774044971e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}