{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 530,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037735849056603774,
      "grad_norm": 15.33187898922165,
      "learning_rate": 3.773584905660378e-07,
      "loss": 1.3947,
      "step": 1
    },
    {
      "epoch": 0.018867924528301886,
      "grad_norm": 14.587979298665214,
      "learning_rate": 1.8867924528301889e-06,
      "loss": 1.2879,
      "step": 5
    },
    {
      "epoch": 0.03773584905660377,
      "grad_norm": 5.156574643577073,
      "learning_rate": 3.7735849056603777e-06,
      "loss": 1.1356,
      "step": 10
    },
    {
      "epoch": 0.05660377358490566,
      "grad_norm": 2.4413584926483494,
      "learning_rate": 5.660377358490566e-06,
      "loss": 1.056,
      "step": 15
    },
    {
      "epoch": 0.07547169811320754,
      "grad_norm": 1.939557281184319,
      "learning_rate": 7.5471698113207555e-06,
      "loss": 1.0035,
      "step": 20
    },
    {
      "epoch": 0.09433962264150944,
      "grad_norm": 1.445408046384172,
      "learning_rate": 9.433962264150944e-06,
      "loss": 0.9666,
      "step": 25
    },
    {
      "epoch": 0.11320754716981132,
      "grad_norm": 1.5429900501633669,
      "learning_rate": 1.1320754716981132e-05,
      "loss": 0.9673,
      "step": 30
    },
    {
      "epoch": 0.1320754716981132,
      "grad_norm": 1.2999242817660164,
      "learning_rate": 1.320754716981132e-05,
      "loss": 0.9161,
      "step": 35
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 1.1690976259696864,
      "learning_rate": 1.5094339622641511e-05,
      "loss": 0.9029,
      "step": 40
    },
    {
      "epoch": 0.16981132075471697,
      "grad_norm": 1.2404008101715356,
      "learning_rate": 1.69811320754717e-05,
      "loss": 0.8976,
      "step": 45
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 1.2490209366453322,
      "learning_rate": 1.8867924528301888e-05,
      "loss": 0.9202,
      "step": 50
    },
    {
      "epoch": 0.20754716981132076,
      "grad_norm": 1.2687062081137546,
      "learning_rate": 1.9999132465602526e-05,
      "loss": 0.9125,
      "step": 55
    },
    {
      "epoch": 0.22641509433962265,
      "grad_norm": 1.2693770693981177,
      "learning_rate": 1.998937443221316e-05,
      "loss": 0.918,
      "step": 60
    },
    {
      "epoch": 0.24528301886792453,
      "grad_norm": 1.17511999372123,
      "learning_rate": 1.9968784563700586e-05,
      "loss": 0.8731,
      "step": 65
    },
    {
      "epoch": 0.2641509433962264,
      "grad_norm": 1.1148641046803303,
      "learning_rate": 1.9937385186393888e-05,
      "loss": 0.9063,
      "step": 70
    },
    {
      "epoch": 0.2830188679245283,
      "grad_norm": 1.2209470360517312,
      "learning_rate": 1.9895210347758233e-05,
      "loss": 0.8973,
      "step": 75
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": 1.2489264571555163,
      "learning_rate": 1.984230577947597e-05,
      "loss": 0.9086,
      "step": 80
    },
    {
      "epoch": 0.32075471698113206,
      "grad_norm": 1.7088824250739199,
      "learning_rate": 1.977872884785815e-05,
      "loss": 0.891,
      "step": 85
    },
    {
      "epoch": 0.33962264150943394,
      "grad_norm": 1.1609543047434623,
      "learning_rate": 1.9704548491640195e-05,
      "loss": 0.9064,
      "step": 90
    },
    {
      "epoch": 0.3584905660377358,
      "grad_norm": 1.1548579761616171,
      "learning_rate": 1.961984514722914e-05,
      "loss": 0.886,
      "step": 95
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 1.2072363172467877,
      "learning_rate": 1.9524710661483594e-05,
      "loss": 0.914,
      "step": 100
    },
    {
      "epoch": 0.39622641509433965,
      "grad_norm": 1.2486639912473576,
      "learning_rate": 1.94192481921209e-05,
      "loss": 0.8858,
      "step": 105
    },
    {
      "epoch": 0.41509433962264153,
      "grad_norm": 1.1907067530146591,
      "learning_rate": 1.9303572095859545e-05,
      "loss": 0.883,
      "step": 110
    },
    {
      "epoch": 0.4339622641509434,
      "grad_norm": 1.205701711118422,
      "learning_rate": 1.91778078044181e-05,
      "loss": 0.903,
      "step": 115
    },
    {
      "epoch": 0.4528301886792453,
      "grad_norm": 1.4297409544875106,
      "learning_rate": 1.9042091688505104e-05,
      "loss": 0.8903,
      "step": 120
    },
    {
      "epoch": 0.4716981132075472,
      "grad_norm": 1.3015347726404307,
      "learning_rate": 1.8896570909947477e-05,
      "loss": 0.8975,
      "step": 125
    },
    {
      "epoch": 0.49056603773584906,
      "grad_norm": 1.1056494521961182,
      "learning_rate": 1.874140326211766e-05,
      "loss": 0.8973,
      "step": 130
    },
    {
      "epoch": 0.5094339622641509,
      "grad_norm": 1.3117079939596017,
      "learning_rate": 1.8576756998832667e-05,
      "loss": 0.8665,
      "step": 135
    },
    {
      "epoch": 0.5283018867924528,
      "grad_norm": 1.0536496719085662,
      "learning_rate": 1.8402810651910444e-05,
      "loss": 0.8638,
      "step": 140
    },
    {
      "epoch": 0.5471698113207547,
      "grad_norm": 2.702397102319974,
      "learning_rate": 1.8219752837581466e-05,
      "loss": 0.882,
      "step": 145
    },
    {
      "epoch": 0.5660377358490566,
      "grad_norm": 1.0422440813400673,
      "learning_rate": 1.8027782051965408e-05,
      "loss": 0.8657,
      "step": 150
    },
    {
      "epoch": 0.5849056603773585,
      "grad_norm": 1.3024995956700887,
      "learning_rate": 1.782710645583473e-05,
      "loss": 0.8599,
      "step": 155
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 1.1482394390531847,
      "learning_rate": 1.761794364889855e-05,
      "loss": 0.8926,
      "step": 160
    },
    {
      "epoch": 0.6226415094339622,
      "grad_norm": 1.079599574770899,
      "learning_rate": 1.7400520433851457e-05,
      "loss": 0.8428,
      "step": 165
    },
    {
      "epoch": 0.6415094339622641,
      "grad_norm": 1.0901592446951243,
      "learning_rate": 1.717507257044331e-05,
      "loss": 0.8496,
      "step": 170
    },
    {
      "epoch": 0.660377358490566,
      "grad_norm": 1.1077239121822327,
      "learning_rate": 1.694184451983651e-05,
      "loss": 0.9012,
      "step": 175
    },
    {
      "epoch": 0.6792452830188679,
      "grad_norm": 1.0853595621923493,
      "learning_rate": 1.6701089179528032e-05,
      "loss": 0.8681,
      "step": 180
    },
    {
      "epoch": 0.6981132075471698,
      "grad_norm": 1.0734841287772214,
      "learning_rate": 1.6453067609123656e-05,
      "loss": 0.856,
      "step": 185
    },
    {
      "epoch": 0.7169811320754716,
      "grad_norm": 1.088487035960174,
      "learning_rate": 1.619804874726171e-05,
      "loss": 0.8652,
      "step": 190
    },
    {
      "epoch": 0.7358490566037735,
      "grad_norm": 1.0825029747031027,
      "learning_rate": 1.5936309119993333e-05,
      "loss": 0.8565,
      "step": 195
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 1.200978191088004,
      "learning_rate": 1.566813254093538e-05,
      "loss": 0.8438,
      "step": 200
    },
    {
      "epoch": 0.7735849056603774,
      "grad_norm": 1.0577639466302755,
      "learning_rate": 1.5393809803521213e-05,
      "loss": 0.8681,
      "step": 205
    },
    {
      "epoch": 0.7924528301886793,
      "grad_norm": 1.1116902648533118,
      "learning_rate": 1.5113638365682996e-05,
      "loss": 0.8534,
      "step": 210
    },
    {
      "epoch": 0.8113207547169812,
      "grad_norm": 1.0957222267960907,
      "learning_rate": 1.482792202730745e-05,
      "loss": 0.8598,
      "step": 215
    },
    {
      "epoch": 0.8301886792452831,
      "grad_norm": 1.0870428672337984,
      "learning_rate": 1.4536970600814789e-05,
      "loss": 0.8854,
      "step": 220
    },
    {
      "epoch": 0.8490566037735849,
      "grad_norm": 1.0340161162672956,
      "learning_rate": 1.424109957521806e-05,
      "loss": 0.865,
      "step": 225
    },
    {
      "epoch": 0.8679245283018868,
      "grad_norm": 1.062102724438973,
      "learning_rate": 1.394062977402717e-05,
      "loss": 0.8664,
      "step": 230
    },
    {
      "epoch": 0.8867924528301887,
      "grad_norm": 1.0590868294575073,
      "learning_rate": 1.3635887007368467e-05,
      "loss": 0.8419,
      "step": 235
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": 1.0864493134204916,
      "learning_rate": 1.3327201718697232e-05,
      "loss": 0.8519,
      "step": 240
    },
    {
      "epoch": 0.9245283018867925,
      "grad_norm": 1.0168196512793692,
      "learning_rate": 1.3014908626486032e-05,
      "loss": 0.8629,
      "step": 245
    },
    {
      "epoch": 0.9433962264150944,
      "grad_norm": 1.0404726364027557,
      "learning_rate": 1.2699346361277538e-05,
      "loss": 0.8337,
      "step": 250
    },
    {
      "epoch": 0.9622641509433962,
      "grad_norm": 1.018131650974526,
      "learning_rate": 1.2380857098495355e-05,
      "loss": 0.9745,
      "step": 255
    },
    {
      "epoch": 0.9811320754716981,
      "grad_norm": 1.0037862694896684,
      "learning_rate": 1.2059786187410984e-05,
      "loss": 0.8712,
      "step": 260
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.989425132088932,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.8495,
      "step": 265
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8464146852493286,
      "eval_runtime": 4.2653,
      "eval_samples_per_second": 40.091,
      "eval_steps_per_second": 0.703,
      "step": 265
    },
    {
      "epoch": 1.0188679245283019,
      "grad_norm": 3.0712777016007875,
      "learning_rate": 1.1411294436778562e-05,
      "loss": 0.5752,
      "step": 270
    },
    {
      "epoch": 1.0377358490566038,
      "grad_norm": 1.367908639519453,
      "learning_rate": 1.1084576779974257e-05,
      "loss": 0.5572,
      "step": 275
    },
    {
      "epoch": 1.0566037735849056,
      "grad_norm": 1.1027538267727532,
      "learning_rate": 1.0756683077869133e-05,
      "loss": 0.5489,
      "step": 280
    },
    {
      "epoch": 1.0754716981132075,
      "grad_norm": 1.1284473887078348,
      "learning_rate": 1.0427968877303809e-05,
      "loss": 0.549,
      "step": 285
    },
    {
      "epoch": 1.0943396226415094,
      "grad_norm": 1.0579765238733445,
      "learning_rate": 1.0098790614814658e-05,
      "loss": 0.5584,
      "step": 290
    },
    {
      "epoch": 1.1132075471698113,
      "grad_norm": 1.0510922170571144,
      "learning_rate": 9.769505230136962e-06,
      "loss": 0.5326,
      "step": 295
    },
    {
      "epoch": 1.1320754716981132,
      "grad_norm": 1.0257584558372113,
      "learning_rate": 9.440469779162407e-06,
      "loss": 0.5457,
      "step": 300
    },
    {
      "epoch": 1.150943396226415,
      "grad_norm": 1.0531732710979618,
      "learning_rate": 9.112041046770653e-06,
      "loss": 0.5378,
      "step": 305
    },
    {
      "epoch": 1.169811320754717,
      "grad_norm": 1.0708673795759969,
      "learning_rate": 8.784575159954748e-06,
      "loss": 0.5425,
      "step": 310
    },
    {
      "epoch": 1.1886792452830188,
      "grad_norm": 1.0132141363080573,
      "learning_rate": 8.458427201659926e-06,
      "loss": 0.5391,
      "step": 315
    },
    {
      "epoch": 1.2075471698113207,
      "grad_norm": 1.0680470294860878,
      "learning_rate": 8.133950825754511e-06,
      "loss": 0.5447,
      "step": 320
    },
    {
      "epoch": 1.2264150943396226,
      "grad_norm": 0.9666850547234715,
      "learning_rate": 7.81149787355039e-06,
      "loss": 0.5379,
      "step": 325
    },
    {
      "epoch": 1.2452830188679245,
      "grad_norm": 0.9710527007406873,
      "learning_rate": 7.491417992288927e-06,
      "loss": 0.5326,
      "step": 330
    },
    {
      "epoch": 1.2641509433962264,
      "grad_norm": 1.1620230853698044,
      "learning_rate": 7.174058256006012e-06,
      "loss": 0.5458,
      "step": 335
    },
    {
      "epoch": 1.2830188679245282,
      "grad_norm": 1.0264570630272518,
      "learning_rate": 6.859762789187259e-06,
      "loss": 0.5521,
      "step": 340
    },
    {
      "epoch": 1.3018867924528301,
      "grad_norm": 1.0303843487410083,
      "learning_rate": 6.548872393621578e-06,
      "loss": 0.5465,
      "step": 345
    },
    {
      "epoch": 1.320754716981132,
      "grad_norm": 0.9494639965897911,
      "learning_rate": 6.241724178857621e-06,
      "loss": 0.5531,
      "step": 350
    },
    {
      "epoch": 1.3396226415094339,
      "grad_norm": 0.998464274247554,
      "learning_rate": 5.938651196663865e-06,
      "loss": 0.5528,
      "step": 355
    },
    {
      "epoch": 1.3584905660377358,
      "grad_norm": 0.9719381109648194,
      "learning_rate": 5.6399820798887266e-06,
      "loss": 0.5351,
      "step": 360
    },
    {
      "epoch": 1.3773584905660377,
      "grad_norm": 0.9816121465159701,
      "learning_rate": 5.346040686112189e-06,
      "loss": 0.551,
      "step": 365
    },
    {
      "epoch": 1.3962264150943398,
      "grad_norm": 0.9743057773598173,
      "learning_rate": 5.0571457464755226e-06,
      "loss": 0.5345,
      "step": 370
    },
    {
      "epoch": 1.4150943396226414,
      "grad_norm": 0.9293281745891194,
      "learning_rate": 4.773610520069706e-06,
      "loss": 0.5455,
      "step": 375
    },
    {
      "epoch": 1.4339622641509435,
      "grad_norm": 0.9573637805384148,
      "learning_rate": 4.495742454257418e-06,
      "loss": 0.546,
      "step": 380
    },
    {
      "epoch": 1.4528301886792452,
      "grad_norm": 0.9286559221860932,
      "learning_rate": 4.223842851296907e-06,
      "loss": 0.5179,
      "step": 385
    },
    {
      "epoch": 1.4716981132075473,
      "grad_norm": 0.9387936040725331,
      "learning_rate": 3.9582065416291926e-06,
      "loss": 0.5561,
      "step": 390
    },
    {
      "epoch": 1.490566037735849,
      "grad_norm": 0.9706784805714281,
      "learning_rate": 3.6991215641828903e-06,
      "loss": 0.5471,
      "step": 395
    },
    {
      "epoch": 1.509433962264151,
      "grad_norm": 0.998331330776895,
      "learning_rate": 3.4468688540433425e-06,
      "loss": 0.5462,
      "step": 400
    },
    {
      "epoch": 1.5283018867924527,
      "grad_norm": 0.9387337728890874,
      "learning_rate": 3.2017219378246734e-06,
      "loss": 0.5658,
      "step": 405
    },
    {
      "epoch": 1.5471698113207548,
      "grad_norm": 0.9419101032950977,
      "learning_rate": 2.963946637075107e-06,
      "loss": 0.5416,
      "step": 410
    },
    {
      "epoch": 1.5660377358490565,
      "grad_norm": 0.9575101628921765,
      "learning_rate": 2.7338007800372024e-06,
      "loss": 0.5323,
      "step": 415
    },
    {
      "epoch": 1.5849056603773586,
      "grad_norm": 1.0034727804533015,
      "learning_rate": 2.5115339220754796e-06,
      "loss": 0.5402,
      "step": 420
    },
    {
      "epoch": 1.6037735849056602,
      "grad_norm": 7.5029005576343195,
      "learning_rate": 2.2973870750746253e-06,
      "loss": 0.5655,
      "step": 425
    },
    {
      "epoch": 1.6226415094339623,
      "grad_norm": 1.0027923672255161,
      "learning_rate": 2.09159244610172e-06,
      "loss": 0.5542,
      "step": 430
    },
    {
      "epoch": 1.641509433962264,
      "grad_norm": 0.9357231473507377,
      "learning_rate": 1.8943731856158299e-06,
      "loss": 0.6383,
      "step": 435
    },
    {
      "epoch": 1.6603773584905661,
      "grad_norm": 0.9686189698665412,
      "learning_rate": 1.7059431454979825e-06,
      "loss": 0.5562,
      "step": 440
    },
    {
      "epoch": 1.6792452830188678,
      "grad_norm": 0.9045883081564006,
      "learning_rate": 1.5265066471639701e-06,
      "loss": 0.5348,
      "step": 445
    },
    {
      "epoch": 1.6981132075471699,
      "grad_norm": 1.0056737797057134,
      "learning_rate": 1.3562582600113295e-06,
      "loss": 0.5352,
      "step": 450
    },
    {
      "epoch": 1.7169811320754715,
      "grad_norm": 0.9512535781198771,
      "learning_rate": 1.1953825904408033e-06,
      "loss": 0.5464,
      "step": 455
    },
    {
      "epoch": 1.7358490566037736,
      "grad_norm": 0.9930921183835165,
      "learning_rate": 1.0440540816810395e-06,
      "loss": 0.561,
      "step": 460
    },
    {
      "epoch": 1.7547169811320755,
      "grad_norm": 0.9410700940787784,
      "learning_rate": 9.024368246335735e-07,
      "loss": 0.5456,
      "step": 465
    },
    {
      "epoch": 1.7735849056603774,
      "grad_norm": 0.9323535925403078,
      "learning_rate": 7.706843799431985e-07,
      "loss": 0.5243,
      "step": 470
    },
    {
      "epoch": 1.7924528301886793,
      "grad_norm": 0.9689906420605915,
      "learning_rate": 6.489396114866942e-07,
      "loss": 0.5296,
      "step": 475
    },
    {
      "epoch": 1.8113207547169812,
      "grad_norm": 1.2229314873705728,
      "learning_rate": 5.373345314604206e-07,
      "loss": 0.53,
      "step": 480
    },
    {
      "epoch": 1.830188679245283,
      "grad_norm": 0.9545280104598107,
      "learning_rate": 4.359901572347758e-07,
      "loss": 0.5031,
      "step": 485
    },
    {
      "epoch": 1.849056603773585,
      "grad_norm": 0.9636644642636012,
      "learning_rate": 3.450163801307582e-07,
      "loss": 0.5159,
      "step": 490
    },
    {
      "epoch": 1.8679245283018868,
      "grad_norm": 0.9314616621215778,
      "learning_rate": 2.6451184626087646e-07,
      "loss": 0.5212,
      "step": 495
    },
    {
      "epoch": 1.8867924528301887,
      "grad_norm": 0.9019228681615893,
      "learning_rate": 1.9456384956365149e-07,
      "loss": 0.539,
      "step": 500
    },
    {
      "epoch": 1.9056603773584906,
      "grad_norm": 0.8782721096424342,
      "learning_rate": 1.3524823714768375e-07,
      "loss": 0.5462,
      "step": 505
    },
    {
      "epoch": 1.9245283018867925,
      "grad_norm": 0.9377029041620999,
      "learning_rate": 8.662932704792793e-08,
      "loss": 0.5352,
      "step": 510
    },
    {
      "epoch": 1.9433962264150944,
      "grad_norm": 0.9313929690259365,
      "learning_rate": 4.8759838483358745e-08,
      "loss": 0.5129,
      "step": 515
    },
    {
      "epoch": 1.9622641509433962,
      "grad_norm": 0.9729472297721098,
      "learning_rate": 2.1680834691628627e-08,
      "loss": 0.5358,
      "step": 520
    },
    {
      "epoch": 1.9811320754716981,
      "grad_norm": 0.9341412228490686,
      "learning_rate": 5.421678402741659e-09,
      "loss": 0.5717,
      "step": 525
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.945793151587699,
      "learning_rate": 0.0,
      "loss": 0.5006,
      "step": 530
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.852841854095459,
      "eval_runtime": 6.8692,
      "eval_samples_per_second": 24.894,
      "eval_steps_per_second": 0.437,
      "step": 530
    },
    {
      "epoch": 2.0,
      "step": 530,
      "total_flos": 110971217510400.0,
      "train_loss": 0.7231714307137256,
      "train_runtime": 3756.5168,
      "train_samples_per_second": 9.007,
      "train_steps_per_second": 0.141
    }
  ],
  "logging_steps": 5,
  "max_steps": 530,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 110971217510400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}