{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 528,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028409090909090908,
      "grad_norm": 10.896637192000782,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.6734,
      "step": 5
    },
    {
      "epoch": 0.056818181818181816,
      "grad_norm": 1.5163857276357569,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.2095,
      "step": 10
    },
    {
      "epoch": 0.08522727272727272,
      "grad_norm": 0.6030083388420293,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.8954,
      "step": 15
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.4146436929136456,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.7715,
      "step": 20
    },
    {
      "epoch": 0.14204545454545456,
      "grad_norm": 0.2636145188710264,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.7127,
      "step": 25
    },
    {
      "epoch": 0.17045454545454544,
      "grad_norm": 0.2023043123134589,
      "learning_rate": 4.99982305792533e-05,
      "loss": 0.6778,
      "step": 30
    },
    {
      "epoch": 0.19886363636363635,
      "grad_norm": 0.16510970301238276,
      "learning_rate": 4.997832779179051e-05,
      "loss": 0.6409,
      "step": 35
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.13082269602718508,
      "learning_rate": 4.993633006948142e-05,
      "loss": 0.6336,
      "step": 40
    },
    {
      "epoch": 0.2556818181818182,
      "grad_norm": 0.14831898432802543,
      "learning_rate": 4.987227869373036e-05,
      "loss": 0.6166,
      "step": 45
    },
    {
      "epoch": 0.2840909090909091,
      "grad_norm": 0.10897233346547917,
      "learning_rate": 4.9786236623445434e-05,
      "loss": 0.6118,
      "step": 50
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.11184138744287996,
      "learning_rate": 4.967828843315348e-05,
      "loss": 0.5983,
      "step": 55
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.11134807726458239,
      "learning_rate": 4.954854022986805e-05,
      "loss": 0.5891,
      "step": 60
    },
    {
      "epoch": 0.3693181818181818,
      "grad_norm": 0.09921365604301072,
      "learning_rate": 4.939711954879211e-05,
      "loss": 0.5876,
      "step": 65
    },
    {
      "epoch": 0.3977272727272727,
      "grad_norm": 0.1055432451773935,
      "learning_rate": 4.922417522795821e-05,
      "loss": 0.5801,
      "step": 70
    },
    {
      "epoch": 0.42613636363636365,
      "grad_norm": 0.09914093623755263,
      "learning_rate": 4.902987726192893e-05,
      "loss": 0.5781,
      "step": 75
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.08828127246038743,
      "learning_rate": 4.881441663470182e-05,
      "loss": 0.5649,
      "step": 80
    },
    {
      "epoch": 0.48295454545454547,
      "grad_norm": 0.10055317591789738,
      "learning_rate": 4.857800513198288e-05,
      "loss": 0.5625,
      "step": 85
    },
    {
      "epoch": 0.5113636363636364,
      "grad_norm": 0.08874927350125936,
      "learning_rate": 4.832087513301302e-05,
      "loss": 0.5631,
      "step": 90
    },
    {
      "epoch": 0.5397727272727273,
      "grad_norm": 0.1118239441455913,
      "learning_rate": 4.804327938215235e-05,
      "loss": 0.5591,
      "step": 95
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.09351012207556161,
      "learning_rate": 4.7745490740446676e-05,
      "loss": 0.5566,
      "step": 100
    },
    {
      "epoch": 0.5965909090909091,
      "grad_norm": 0.10852517138960499,
      "learning_rate": 4.742780191742036e-05,
      "loss": 0.5607,
      "step": 105
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.11702640688817323,
      "learning_rate": 4.7090525183359297e-05,
      "loss": 0.5539,
      "step": 110
    },
    {
      "epoch": 0.6534090909090909,
      "grad_norm": 0.09785419980049836,
      "learning_rate": 4.6733992062366766e-05,
      "loss": 0.5419,
      "step": 115
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.10711167883214251,
      "learning_rate": 4.635855300649382e-05,
      "loss": 0.5445,
      "step": 120
    },
    {
      "epoch": 0.7102272727272727,
      "grad_norm": 0.10796834846017456,
      "learning_rate": 4.596457705126459e-05,
      "loss": 0.5448,
      "step": 125
    },
    {
      "epoch": 0.7386363636363636,
      "grad_norm": 0.11744855439211235,
      "learning_rate": 4.555245145293509e-05,
      "loss": 0.5411,
      "step": 130
    },
    {
      "epoch": 0.7670454545454546,
      "grad_norm": 0.11356156360640139,
      "learning_rate": 4.512258130784199e-05,
      "loss": 0.5434,
      "step": 135
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.12169855888778969,
      "learning_rate": 4.4675389154215744e-05,
      "loss": 0.5421,
      "step": 140
    },
    {
      "epoch": 0.8238636363636364,
      "grad_norm": 0.10341006801601364,
      "learning_rate": 4.4211314556849136e-05,
      "loss": 0.5355,
      "step": 145
    },
    {
      "epoch": 0.8522727272727273,
      "grad_norm": 0.10759924912275785,
      "learning_rate": 4.373081367502981e-05,
      "loss": 0.5326,
      "step": 150
    },
    {
      "epoch": 0.8806818181818182,
      "grad_norm": 0.10861205860545389,
      "learning_rate": 4.323435881416124e-05,
      "loss": 0.537,
      "step": 155
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.09957047692339929,
      "learning_rate": 4.272243796151305e-05,
      "loss": 0.533,
      "step": 160
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.12359375999999637,
      "learning_rate": 4.219555430655693e-05,
      "loss": 0.5351,
      "step": 165
    },
    {
      "epoch": 0.9659090909090909,
      "grad_norm": 0.09258501782228747,
      "learning_rate": 4.165422574635959e-05,
      "loss": 0.5317,
      "step": 170
    },
    {
      "epoch": 0.9943181818181818,
      "grad_norm": 0.11203309080231412,
      "learning_rate": 4.1098984376519e-05,
      "loss": 0.5292,
      "step": 175
    },
    {
      "epoch": 1.0227272727272727,
      "grad_norm": 0.08337277679519309,
      "learning_rate": 4.053037596814432e-05,
      "loss": 0.5205,
      "step": 180
    },
    {
      "epoch": 1.0511363636363635,
      "grad_norm": 0.08922972769023695,
      "learning_rate": 3.9948959431393454e-05,
      "loss": 0.5107,
      "step": 185
    },
    {
      "epoch": 1.0795454545454546,
      "grad_norm": 0.09256444997193415,
      "learning_rate": 3.935530626609582e-05,
      "loss": 0.5091,
      "step": 190
    },
    {
      "epoch": 1.1079545454545454,
      "grad_norm": 0.08761092083420882,
      "learning_rate": 3.875e-05,
      "loss": 0.5118,
      "step": 195
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.09766222638240604,
      "learning_rate": 3.813363561519876e-05,
      "loss": 0.5086,
      "step": 200
    },
    {
      "epoch": 1.1647727272727273,
      "grad_norm": 0.08469321954291688,
      "learning_rate": 3.750681896329504e-05,
      "loss": 0.5106,
      "step": 205
    },
    {
      "epoch": 1.1931818181818181,
      "grad_norm": 0.0961560094422636,
      "learning_rate": 3.687016616988379e-05,
      "loss": 0.51,
      "step": 210
    },
    {
      "epoch": 1.2215909090909092,
      "grad_norm": 0.0862194194928744,
      "learning_rate": 3.6224303028935106e-05,
      "loss": 0.5103,
      "step": 215
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.07956278803606433,
      "learning_rate": 3.556986438767389e-05,
      "loss": 0.5037,
      "step": 220
    },
    {
      "epoch": 1.2784090909090908,
      "grad_norm": 0.0903181198584574,
      "learning_rate": 3.490749352256063e-05,
      "loss": 0.509,
      "step": 225
    },
    {
      "epoch": 1.3068181818181819,
      "grad_norm": 0.0944984329203277,
      "learning_rate": 3.4237841506986744e-05,
      "loss": 0.5027,
      "step": 230
    },
    {
      "epoch": 1.3352272727272727,
      "grad_norm": 0.08882033124741437,
      "learning_rate": 3.356156657130596e-05,
      "loss": 0.4961,
      "step": 235
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.09550461777333721,
      "learning_rate": 3.287933345583085e-05,
      "loss": 0.5069,
      "step": 240
    },
    {
      "epoch": 1.3920454545454546,
      "grad_norm": 0.08946536218539883,
      "learning_rate": 3.219181275743034e-05,
      "loss": 0.5086,
      "step": 245
    },
    {
      "epoch": 1.4204545454545454,
      "grad_norm": 0.09325584287334789,
      "learning_rate": 3.1499680270370706e-05,
      "loss": 0.5044,
      "step": 250
    },
    {
      "epoch": 1.4488636363636362,
      "grad_norm": 0.08223842512135068,
      "learning_rate": 3.0803616322047654e-05,
      "loss": 0.5052,
      "step": 255
    },
    {
      "epoch": 1.4772727272727273,
      "grad_norm": 0.08270798846301625,
      "learning_rate": 3.0104305104262698e-05,
      "loss": 0.4985,
      "step": 260
    },
    {
      "epoch": 1.5056818181818183,
      "grad_norm": 0.08262838460793459,
      "learning_rate": 2.940243400070103e-05,
      "loss": 0.4994,
      "step": 265
    },
    {
      "epoch": 1.5340909090909092,
      "grad_norm": 0.09058860519349171,
      "learning_rate": 2.8698692911271897e-05,
      "loss": 0.5023,
      "step": 270
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.09371800013120092,
      "learning_rate": 2.7993773573975728e-05,
      "loss": 0.4992,
      "step": 275
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.08456948817551574,
      "learning_rate": 2.7288368884964475e-05,
      "loss": 0.503,
      "step": 280
    },
    {
      "epoch": 1.6193181818181817,
      "grad_norm": 0.09101003159864386,
      "learning_rate": 2.658317221746361e-05,
      "loss": 0.4954,
      "step": 285
    },
    {
      "epoch": 1.6477272727272727,
      "grad_norm": 0.08160457721074796,
      "learning_rate": 2.5878876740225116e-05,
      "loss": 0.4986,
      "step": 290
    },
    {
      "epoch": 1.6761363636363638,
      "grad_norm": 0.08078176783826871,
      "learning_rate": 2.5176174736181536e-05,
      "loss": 0.4971,
      "step": 295
    },
    {
      "epoch": 1.7045454545454546,
      "grad_norm": 0.08864892274469409,
      "learning_rate": 2.4475756921970653e-05,
      "loss": 0.4988,
      "step": 300
    },
    {
      "epoch": 1.7329545454545454,
      "grad_norm": 0.09144520680898066,
      "learning_rate": 2.377831176899986e-05,
      "loss": 0.4987,
      "step": 305
    },
    {
      "epoch": 1.7613636363636362,
      "grad_norm": 0.0913519780551606,
      "learning_rate": 2.3084524826717317e-05,
      "loss": 0.4962,
      "step": 310
    },
    {
      "epoch": 1.7897727272727273,
      "grad_norm": 0.08330604163992984,
      "learning_rate": 2.23950780487554e-05,
      "loss": 0.5021,
      "step": 315
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.08280936051442833,
      "learning_rate": 2.171064912260849e-05,
      "loss": 0.4983,
      "step": 320
    },
    {
      "epoch": 1.8465909090909092,
      "grad_norm": 0.07571686269473353,
      "learning_rate": 2.103191080350419e-05,
      "loss": 0.499,
      "step": 325
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.08525336953750823,
      "learning_rate": 2.0359530253122738e-05,
      "loss": 0.4923,
      "step": 330
    },
    {
      "epoch": 1.9034090909090908,
      "grad_norm": 0.10358699532249785,
      "learning_rate": 1.9694168383814492e-05,
      "loss": 0.5043,
      "step": 335
    },
    {
      "epoch": 1.9318181818181817,
      "grad_norm": 0.08301020877209554,
      "learning_rate": 1.9036479208960127e-05,
      "loss": 0.4946,
      "step": 340
    },
    {
      "epoch": 1.9602272727272727,
      "grad_norm": 0.08553632563551307,
      "learning_rate": 1.838710920011227e-05,
      "loss": 0.4969,
      "step": 345
    },
    {
      "epoch": 1.9886363636363638,
      "grad_norm": 0.08303295503235186,
      "learning_rate": 1.7746696651550143e-05,
      "loss": 0.4997,
      "step": 350
    },
    {
      "epoch": 2.0170454545454546,
      "grad_norm": 0.08033143740448973,
      "learning_rate": 1.7115871052872204e-05,
      "loss": 0.4867,
      "step": 355
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 0.08063264186240293,
      "learning_rate": 1.6495252470243134e-05,
      "loss": 0.487,
      "step": 360
    },
    {
      "epoch": 2.0738636363636362,
      "grad_norm": 0.07841584895617655,
      "learning_rate": 1.5885450936903586e-05,
      "loss": 0.4837,
      "step": 365
    },
    {
      "epoch": 2.102272727272727,
      "grad_norm": 0.07460661702402475,
      "learning_rate": 1.528706585354177e-05,
      "loss": 0.4788,
      "step": 370
    },
    {
      "epoch": 2.1306818181818183,
      "grad_norm": 0.08030048639361652,
      "learning_rate": 1.4700685399116238e-05,
      "loss": 0.4803,
      "step": 375
    },
    {
      "epoch": 2.159090909090909,
      "grad_norm": 0.07655857860636041,
      "learning_rate": 1.412688595270887e-05,
      "loss": 0.4782,
      "step": 380
    },
    {
      "epoch": 2.1875,
      "grad_norm": 0.0741239677057519,
      "learning_rate": 1.3566231526976714e-05,
      "loss": 0.4833,
      "step": 385
    },
    {
      "epoch": 2.215909090909091,
      "grad_norm": 0.07552080480637674,
      "learning_rate": 1.3019273213759081e-05,
      "loss": 0.4817,
      "step": 390
    },
    {
      "epoch": 2.2443181818181817,
      "grad_norm": 0.087506481602976,
      "learning_rate": 1.2486548642385274e-05,
      "loss": 0.4855,
      "step": 395
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.07825929401017973,
      "learning_rate": 1.1968581451215065e-05,
      "loss": 0.4783,
      "step": 400
    },
    {
      "epoch": 2.3011363636363638,
      "grad_norm": 0.07347633398325569,
      "learning_rate": 1.1465880772931601e-05,
      "loss": 0.484,
      "step": 405
    },
    {
      "epoch": 2.3295454545454546,
      "grad_norm": 0.07075822069959536,
      "learning_rate": 1.0978940734092554e-05,
      "loss": 0.478,
      "step": 410
    },
    {
      "epoch": 2.3579545454545454,
      "grad_norm": 0.07267042198965988,
      "learning_rate": 1.050823996943144e-05,
      "loss": 0.4783,
      "step": 415
    },
    {
      "epoch": 2.3863636363636362,
      "grad_norm": 0.07341626200460101,
      "learning_rate": 1.0054241151386492e-05,
      "loss": 0.4756,
      "step": 420
    },
    {
      "epoch": 2.4147727272727275,
      "grad_norm": 0.0706063205931748,
      "learning_rate": 9.617390535319684e-06,
      "loss": 0.4772,
      "step": 425
    },
    {
      "epoch": 2.4431818181818183,
      "grad_norm": 0.06987948971233222,
      "learning_rate": 9.198117520872698e-06,
      "loss": 0.477,
      "step": 430
    },
    {
      "epoch": 2.471590909090909,
      "grad_norm": 0.07780450930302736,
      "learning_rate": 8.796834229891206e-06,
      "loss": 0.4819,
      "step": 435
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.07385728736608703,
      "learning_rate": 8.413935101332198e-06,
      "loss": 0.476,
      "step": 440
    },
    {
      "epoch": 2.528409090909091,
      "grad_norm": 0.06912845080364564,
      "learning_rate": 8.049796503552626e-06,
      "loss": 0.4776,
      "step": 445
    },
    {
      "epoch": 2.5568181818181817,
      "grad_norm": 0.07115097048034667,
      "learning_rate": 7.704776364360454e-06,
      "loss": 0.4806,
      "step": 450
    },
    {
      "epoch": 2.5852272727272725,
      "grad_norm": 0.0719603929691263,
      "learning_rate": 7.379213819191676e-06,
      "loss": 0.4805,
      "step": 455
    },
    {
      "epoch": 2.6136363636363638,
      "grad_norm": 0.06733281311431526,
      "learning_rate": 7.07342887775922e-06,
      "loss": 0.4771,
      "step": 460
    },
    {
      "epoch": 2.6420454545454546,
      "grad_norm": 0.06812256929077086,
      "learning_rate": 6.787722109501379e-06,
      "loss": 0.4769,
      "step": 465
    },
    {
      "epoch": 2.6704545454545454,
      "grad_norm": 0.06945313043383605,
      "learning_rate": 6.522374348138882e-06,
      "loss": 0.4791,
      "step": 470
    },
    {
      "epoch": 2.6988636363636362,
      "grad_norm": 0.07082851639261782,
      "learning_rate": 6.277646415631148e-06,
      "loss": 0.4785,
      "step": 475
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.07019381014525443,
      "learning_rate": 6.053778865802907e-06,
      "loss": 0.4787,
      "step": 480
    },
    {
      "epoch": 2.7556818181818183,
      "grad_norm": 0.06814585572621572,
      "learning_rate": 5.850991747893292e-06,
      "loss": 0.4788,
      "step": 485
    },
    {
      "epoch": 2.784090909090909,
      "grad_norm": 0.06724675412918013,
      "learning_rate": 5.669484390259793e-06,
      "loss": 0.4744,
      "step": 490
    },
    {
      "epoch": 2.8125,
      "grad_norm": 0.06951904971525688,
      "learning_rate": 5.509435204449666e-06,
      "loss": 0.4852,
      "step": 495
    },
    {
      "epoch": 2.840909090909091,
      "grad_norm": 0.06771580623936355,
      "learning_rate": 5.37100150983139e-06,
      "loss": 0.4748,
      "step": 500
    },
    {
      "epoch": 2.8693181818181817,
      "grad_norm": 0.06692159909264785,
      "learning_rate": 5.254319378958563e-06,
      "loss": 0.475,
      "step": 505
    },
    {
      "epoch": 2.8977272727272725,
      "grad_norm": 0.06940269513307211,
      "learning_rate": 5.159503503818199e-06,
      "loss": 0.4809,
      "step": 510
    },
    {
      "epoch": 2.9261363636363638,
      "grad_norm": 0.06707771857169355,
      "learning_rate": 5.086647083094966e-06,
      "loss": 0.4793,
      "step": 515
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 0.06794955106454185,
      "learning_rate": 5.03582173056209e-06,
      "loss": 0.4781,
      "step": 520
    },
    {
      "epoch": 2.9829545454545454,
      "grad_norm": 0.06951889463364248,
      "learning_rate": 5.00707740468904e-06,
      "loss": 0.4807,
      "step": 525
    },
    {
      "epoch": 3.0,
      "step": 528,
      "total_flos": 962656789856256.0,
      "train_loss": 0.5394951967578946,
      "train_runtime": 11008.0222,
      "train_samples_per_second": 6.123,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 5,
  "max_steps": 528,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 962656789856256.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}