{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 1065,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009396288466055908,
      "grad_norm": 77.32342529296875,
      "learning_rate": 8.411214953271029e-07,
      "loss": 1.6798,
      "step": 10
    },
    {
      "epoch": 0.018792576932111817,
      "grad_norm": 33.60771179199219,
      "learning_rate": 1.7757009345794394e-06,
      "loss": 1.4918,
      "step": 20
    },
    {
      "epoch": 0.028188865398167725,
      "grad_norm": 15.923619270324707,
      "learning_rate": 2.7102803738317757e-06,
      "loss": 0.832,
      "step": 30
    },
    {
      "epoch": 0.03758515386422363,
      "grad_norm": 25.03349494934082,
      "learning_rate": 3.6448598130841123e-06,
      "loss": 0.6918,
      "step": 40
    },
    {
      "epoch": 0.04698144233027954,
      "grad_norm": 10.101052284240723,
      "learning_rate": 4.579439252336449e-06,
      "loss": 0.5121,
      "step": 50
    },
    {
      "epoch": 0.04698144233027954,
      "eval_loss": 0.4876191020011902,
      "eval_runtime": 472.5825,
      "eval_samples_per_second": 2.002,
      "eval_steps_per_second": 1.001,
      "step": 50
    },
    {
      "epoch": 0.05637773079633545,
      "grad_norm": 8.925775527954102,
      "learning_rate": 5.514018691588785e-06,
      "loss": 0.4886,
      "step": 60
    },
    {
      "epoch": 0.06577401926239136,
      "grad_norm": 7.684209823608398,
      "learning_rate": 6.448598130841122e-06,
      "loss": 0.4985,
      "step": 70
    },
    {
      "epoch": 0.07517030772844727,
      "grad_norm": 14.134685516357422,
      "learning_rate": 7.383177570093458e-06,
      "loss": 0.3483,
      "step": 80
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 9.419997215270996,
      "learning_rate": 8.317757009345795e-06,
      "loss": 0.2995,
      "step": 90
    },
    {
      "epoch": 0.09396288466055908,
      "grad_norm": 9.725701332092285,
      "learning_rate": 9.252336448598132e-06,
      "loss": 0.4615,
      "step": 100
    },
    {
      "epoch": 0.09396288466055908,
      "eval_loss": 0.3848985433578491,
      "eval_runtime": 485.2521,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.975,
      "step": 100
    },
    {
      "epoch": 0.10335917312661498,
      "grad_norm": 7.37769889831543,
      "learning_rate": 9.999892460708615e-06,
      "loss": 0.372,
      "step": 110
    },
    {
      "epoch": 0.1127554615926709,
      "grad_norm": 5.251932144165039,
      "learning_rate": 9.996129071205167e-06,
      "loss": 0.3499,
      "step": 120
    },
    {
      "epoch": 0.1221517500587268,
      "grad_norm": 6.633662700653076,
      "learning_rate": 9.98699334211771e-06,
      "loss": 0.3497,
      "step": 130
    },
    {
      "epoch": 0.13154803852478272,
      "grad_norm": 9.925003051757812,
      "learning_rate": 9.972495097099379e-06,
      "loss": 0.3527,
      "step": 140
    },
    {
      "epoch": 0.14094432699083861,
      "grad_norm": 2.5581600666046143,
      "learning_rate": 9.952649926118827e-06,
      "loss": 0.37,
      "step": 150
    },
    {
      "epoch": 0.14094432699083861,
      "eval_loss": 0.32813695073127747,
      "eval_runtime": 450.9285,
      "eval_samples_per_second": 2.098,
      "eval_steps_per_second": 1.049,
      "step": 150
    },
    {
      "epoch": 0.15034061545689453,
      "grad_norm": 8.05836009979248,
      "learning_rate": 9.927479168696327e-06,
      "loss": 0.4364,
      "step": 160
    },
    {
      "epoch": 0.15973690392295042,
      "grad_norm": 8.204833984375,
      "learning_rate": 9.897009890957382e-06,
      "loss": 0.3828,
      "step": 170
    },
    {
      "epoch": 0.16913319238900634,
      "grad_norm": 4.883147716522217,
      "learning_rate": 9.861274856528504e-06,
      "loss": 0.3503,
      "step": 180
    },
    {
      "epoch": 0.17852948085506226,
      "grad_norm": 4.023066520690918,
      "learning_rate": 9.820312491306471e-06,
      "loss": 0.4124,
      "step": 190
    },
    {
      "epoch": 0.18792576932111815,
      "grad_norm": 3.1607863903045654,
      "learning_rate": 9.77416684213896e-06,
      "loss": 0.3749,
      "step": 200
    },
    {
      "epoch": 0.18792576932111815,
      "eval_loss": 0.2891885042190552,
      "eval_runtime": 458.85,
      "eval_samples_per_second": 2.062,
      "eval_steps_per_second": 1.031,
      "step": 200
    },
    {
      "epoch": 0.19732205778717407,
      "grad_norm": 9.990116119384766,
      "learning_rate": 9.722887529460928e-06,
      "loss": 0.235,
      "step": 210
    },
    {
      "epoch": 0.20671834625322996,
      "grad_norm": 4.4412760734558105,
      "learning_rate": 9.666529693937763e-06,
      "loss": 0.2777,
      "step": 220
    },
    {
      "epoch": 0.21611463471928588,
      "grad_norm": 5.4278154373168945,
      "learning_rate": 9.605153937172495e-06,
      "loss": 0.3091,
      "step": 230
    },
    {
      "epoch": 0.2255109231853418,
      "grad_norm": 4.043374061584473,
      "learning_rate": 9.538826256540866e-06,
      "loss": 0.287,
      "step": 240
    },
    {
      "epoch": 0.2349072116513977,
      "grad_norm": 5.319589614868164,
      "learning_rate": 9.467617974224326e-06,
      "loss": 0.2863,
      "step": 250
    },
    {
      "epoch": 0.2349072116513977,
      "eval_loss": 0.2756798267364502,
      "eval_runtime": 504.1073,
      "eval_samples_per_second": 1.877,
      "eval_steps_per_second": 0.938,
      "step": 250
    },
    {
      "epoch": 0.2443035001174536,
      "grad_norm": 8.62342643737793,
      "learning_rate": 9.391605660517268e-06,
      "loss": 0.2357,
      "step": 260
    },
    {
      "epoch": 0.2536997885835095,
      "grad_norm": 2.7996938228607178,
      "learning_rate": 9.310871051490953e-06,
      "loss": 0.2237,
      "step": 270
    },
    {
      "epoch": 0.26309607704956545,
      "grad_norm": 4.890498638153076,
      "learning_rate": 9.225500961102685e-06,
      "loss": 0.2974,
      "step": 280
    },
    {
      "epoch": 0.27249236551562134,
      "grad_norm": 5.307254314422607,
      "learning_rate": 9.135587187844727e-06,
      "loss": 0.2556,
      "step": 290
    },
    {
      "epoch": 0.28188865398167723,
      "grad_norm": 4.411228656768799,
      "learning_rate": 9.041226416033344e-06,
      "loss": 0.3078,
      "step": 300
    },
    {
      "epoch": 0.28188865398167723,
      "eval_loss": 0.25494658946990967,
      "eval_runtime": 518.8808,
      "eval_samples_per_second": 1.823,
      "eval_steps_per_second": 0.912,
      "step": 300
    },
    {
      "epoch": 0.2912849424477331,
      "grad_norm": 2.772766351699829,
      "learning_rate": 8.942520111844117e-06,
      "loss": 0.2227,
      "step": 310
    },
    {
      "epoch": 0.30068123091378907,
      "grad_norm": 5.582266807556152,
      "learning_rate": 8.839574414205335e-06,
      "loss": 0.2668,
      "step": 320
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 4.721141815185547,
      "learning_rate": 8.732500020666748e-06,
      "loss": 0.2726,
      "step": 330
    },
    {
      "epoch": 0.31947380784590085,
      "grad_norm": 4.359829425811768,
      "learning_rate": 8.621412068366455e-06,
      "loss": 0.2807,
      "step": 340
    },
    {
      "epoch": 0.3288700963119568,
      "grad_norm": 2.9552581310272217,
      "learning_rate": 8.506430010223899e-06,
      "loss": 0.2921,
      "step": 350
    },
    {
      "epoch": 0.3288700963119568,
      "eval_loss": 0.23158399760723114,
      "eval_runtime": 528.3567,
      "eval_samples_per_second": 1.79,
      "eval_steps_per_second": 0.895,
      "step": 350
    },
    {
      "epoch": 0.3382663847780127,
      "grad_norm": 4.709650039672852,
      "learning_rate": 8.38767748649208e-06,
      "loss": 0.306,
      "step": 360
    },
    {
      "epoch": 0.3476626732440686,
      "grad_norm": 2.7597694396972656,
      "learning_rate": 8.26528219180716e-06,
      "loss": 0.2148,
      "step": 370
    },
    {
      "epoch": 0.3570589617101245,
      "grad_norm": 6.239573001861572,
      "learning_rate": 8.139375737878356e-06,
      "loss": 0.1558,
      "step": 380
    },
    {
      "epoch": 0.3664552501761804,
      "grad_norm": 2.6109910011291504,
      "learning_rate": 8.01009351196582e-06,
      "loss": 0.1945,
      "step": 390
    },
    {
      "epoch": 0.3758515386422363,
      "grad_norm": 5.080913543701172,
      "learning_rate": 7.877574531298666e-06,
      "loss": 0.3191,
      "step": 400
    },
    {
      "epoch": 0.3758515386422363,
      "eval_loss": 0.23533165454864502,
      "eval_runtime": 491.1933,
      "eval_samples_per_second": 1.926,
      "eval_steps_per_second": 0.963,
      "step": 400
    },
    {
      "epoch": 0.38524782710829225,
      "grad_norm": 3.903905153274536,
      "learning_rate": 7.741961293589693e-06,
      "loss": 0.2265,
      "step": 410
    },
    {
      "epoch": 0.39464411557434814,
      "grad_norm": 5.586989879608154,
      "learning_rate": 7.603399623807519e-06,
      "loss": 0.2608,
      "step": 420
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 3.9632835388183594,
      "learning_rate": 7.462038517370962e-06,
      "loss": 0.2456,
      "step": 430
    },
    {
      "epoch": 0.4134366925064599,
      "grad_norm": 7.482256889343262,
      "learning_rate": 7.318029979934181e-06,
      "loss": 0.2898,
      "step": 440
    },
    {
      "epoch": 0.42283298097251587,
      "grad_norm": 3.7885382175445557,
      "learning_rate": 7.17152886393495e-06,
      "loss": 0.313,
      "step": 450
    },
    {
      "epoch": 0.42283298097251587,
      "eval_loss": 0.22310128808021545,
      "eval_runtime": 516.4179,
      "eval_samples_per_second": 1.832,
      "eval_steps_per_second": 0.916,
      "step": 450
    },
    {
      "epoch": 0.43222926943857176,
      "grad_norm": 4.9588093757629395,
      "learning_rate": 7.022692702081766e-06,
      "loss": 0.2691,
      "step": 460
    },
    {
      "epoch": 0.44162555790462765,
      "grad_norm": 4.674664497375488,
      "learning_rate": 6.871681537958862e-06,
      "loss": 0.2254,
      "step": 470
    },
    {
      "epoch": 0.4510218463706836,
      "grad_norm": 5.224850654602051,
      "learning_rate": 6.718657753931284e-06,
      "loss": 0.2315,
      "step": 480
    },
    {
      "epoch": 0.4604181348367395,
      "grad_norm": 4.065497398376465,
      "learning_rate": 6.56378589653506e-06,
      "loss": 0.2944,
      "step": 490
    },
    {
      "epoch": 0.4698144233027954,
      "grad_norm": 4.546512603759766,
      "learning_rate": 6.40723249954025e-06,
      "loss": 0.2037,
      "step": 500
    },
    {
      "epoch": 0.4698144233027954,
      "eval_loss": 0.213790163397789,
      "eval_runtime": 486.7052,
      "eval_samples_per_second": 1.944,
      "eval_steps_per_second": 0.972,
      "step": 500
    },
    {
      "epoch": 0.4792107117688513,
      "grad_norm": 3.3908934593200684,
      "learning_rate": 6.2491659048771215e-06,
      "loss": 0.2189,
      "step": 510
    },
    {
      "epoch": 0.4886070002349072,
      "grad_norm": 4.911809921264648,
      "learning_rate": 6.089756081617987e-06,
      "loss": 0.222,
      "step": 520
    },
    {
      "epoch": 0.4980032887009631,
      "grad_norm": 2.711010694503784,
      "learning_rate": 5.929174443209416e-06,
      "loss": 0.2179,
      "step": 530
    },
    {
      "epoch": 0.507399577167019,
      "grad_norm": 3.0764307975769043,
      "learning_rate": 5.767593663151265e-06,
      "loss": 0.2111,
      "step": 540
    },
    {
      "epoch": 0.5167958656330749,
      "grad_norm": 4.922618389129639,
      "learning_rate": 5.605187489320815e-06,
      "loss": 0.1729,
      "step": 550
    },
    {
      "epoch": 0.5167958656330749,
      "eval_loss": 0.20741979777812958,
      "eval_runtime": 508.5854,
      "eval_samples_per_second": 1.86,
      "eval_steps_per_second": 0.93,
      "step": 550
    },
    {
      "epoch": 0.5261921540991309,
      "grad_norm": 3.6055169105529785,
      "learning_rate": 5.442130557141595e-06,
      "loss": 0.1785,
      "step": 560
    },
    {
      "epoch": 0.5355884425651868,
      "grad_norm": 4.116625785827637,
      "learning_rate": 5.278598201797844e-06,
      "loss": 0.1761,
      "step": 570
    },
    {
      "epoch": 0.5449847310312427,
      "grad_norm": 6.054320335388184,
      "learning_rate": 5.1147662696965254e-06,
      "loss": 0.2185,
      "step": 580
    },
    {
      "epoch": 0.5543810194972986,
      "grad_norm": 3.523534059524536,
      "learning_rate": 4.9508109293796015e-06,
      "loss": 0.211,
      "step": 590
    },
    {
      "epoch": 0.5637773079633545,
      "grad_norm": 6.204962730407715,
      "learning_rate": 4.7869084820899455e-06,
      "loss": 0.289,
      "step": 600
    },
    {
      "epoch": 0.5637773079633545,
      "eval_loss": 0.1954464614391327,
      "eval_runtime": 498.5386,
      "eval_samples_per_second": 1.898,
      "eval_steps_per_second": 0.949,
      "step": 600
    },
    {
      "epoch": 0.5731735964294103,
      "grad_norm": 4.921229839324951,
      "learning_rate": 4.623235172194532e-06,
      "loss": 0.2154,
      "step": 610
    },
    {
      "epoch": 0.5825698848954662,
      "grad_norm": 4.28684139251709,
      "learning_rate": 4.459966997668812e-06,
      "loss": 0.2147,
      "step": 620
    },
    {
      "epoch": 0.5919661733615222,
      "grad_norm": 4.43740177154541,
      "learning_rate": 4.297279520846002e-06,
      "loss": 0.1491,
      "step": 630
    },
    {
      "epoch": 0.6013624618275781,
      "grad_norm": 6.9565863609313965,
      "learning_rate": 4.135347679634849e-06,
      "loss": 0.2285,
      "step": 640
    },
    {
      "epoch": 0.610758750293634,
      "grad_norm": 1.496799349784851,
      "learning_rate": 3.974345599408833e-06,
      "loss": 0.2775,
      "step": 650
    },
    {
      "epoch": 0.610758750293634,
      "eval_loss": 0.18974561989307404,
      "eval_runtime": 488.3923,
      "eval_samples_per_second": 1.937,
      "eval_steps_per_second": 0.968,
      "step": 650
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 2.838442087173462,
      "learning_rate": 3.814446405769069e-06,
      "loss": 0.214,
      "step": 660
    },
    {
      "epoch": 0.6295513272257458,
      "grad_norm": 7.474781513214111,
      "learning_rate": 3.6558220383822824e-06,
      "loss": 0.2392,
      "step": 670
    },
    {
      "epoch": 0.6389476156918017,
      "grad_norm": 5.7680511474609375,
      "learning_rate": 3.4986430660940283e-06,
      "loss": 0.2062,
      "step": 680
    },
    {
      "epoch": 0.6483439041578577,
      "grad_norm": 3.3340532779693604,
      "learning_rate": 3.3430785035159297e-06,
      "loss": 0.1738,
      "step": 690
    },
    {
      "epoch": 0.6577401926239136,
      "grad_norm": 2.487337350845337,
      "learning_rate": 3.1892956292842103e-06,
      "loss": 0.1546,
      "step": 700
    },
    {
      "epoch": 0.6577401926239136,
      "eval_loss": 0.18141551315784454,
      "eval_runtime": 504.0426,
      "eval_samples_per_second": 1.877,
      "eval_steps_per_second": 0.938,
      "step": 700
    },
    {
      "epoch": 0.6671364810899695,
      "grad_norm": 4.324577331542969,
      "learning_rate": 3.0374598061848936e-06,
      "loss": 0.2037,
      "step": 710
    },
    {
      "epoch": 0.6765327695560254,
      "grad_norm": 3.728818893432617,
      "learning_rate": 2.8877343033391523e-06,
      "loss": 0.14,
      "step": 720
    },
    {
      "epoch": 0.6859290580220813,
      "grad_norm": 3.1286537647247314,
      "learning_rate": 2.7402801206399454e-06,
      "loss": 0.1721,
      "step": 730
    },
    {
      "epoch": 0.6953253464881372,
      "grad_norm": 7.396164417266846,
      "learning_rate": 2.595255815628774e-06,
      "loss": 0.2586,
      "step": 740
    },
    {
      "epoch": 0.704721634954193,
      "grad_norm": 1.8540730476379395,
      "learning_rate": 2.4528173329986855e-06,
      "loss": 0.1613,
      "step": 750
    },
    {
      "epoch": 0.704721634954193,
      "eval_loss": 0.1746373176574707,
      "eval_runtime": 482.272,
      "eval_samples_per_second": 1.962,
      "eval_steps_per_second": 0.981,
      "step": 750
    },
    {
      "epoch": 0.714117923420249,
      "grad_norm": 1.6450875997543335,
      "learning_rate": 2.313117836906897e-06,
      "loss": 0.2041,
      "step": 760
    },
    {
      "epoch": 0.7235142118863049,
      "grad_norm": 1.6683011054992676,
      "learning_rate": 2.1763075462773002e-06,
      "loss": 0.2033,
      "step": 770
    },
    {
      "epoch": 0.7329105003523608,
      "grad_norm": 5.101831912994385,
      "learning_rate": 2.0425335732700075e-06,
      "loss": 0.2497,
      "step": 780
    },
    {
      "epoch": 0.7423067888184167,
      "grad_norm": 10.428893089294434,
      "learning_rate": 1.9119397650915774e-06,
      "loss": 0.2354,
      "step": 790
    },
    {
      "epoch": 0.7517030772844726,
      "grad_norm": 3.380574941635132,
      "learning_rate": 1.7846665493160548e-06,
      "loss": 0.0956,
      "step": 800
    },
    {
      "epoch": 0.7517030772844726,
      "eval_loss": 0.1724964827299118,
      "eval_runtime": 494.611,
      "eval_samples_per_second": 1.913,
      "eval_steps_per_second": 0.956,
      "step": 800
    },
    {
      "epoch": 0.7610993657505285,
      "grad_norm": 3.29054594039917,
      "learning_rate": 1.6608507828831572e-06,
      "loss": 0.1711,
      "step": 810
    },
    {
      "epoch": 0.7704956542165845,
      "grad_norm": 1.7452706098556519,
      "learning_rate": 1.5406256049359359e-06,
      "loss": 0.2362,
      "step": 820
    },
    {
      "epoch": 0.7798919426826404,
      "grad_norm": 3.282259464263916,
      "learning_rate": 1.4241202936562164e-06,
      "loss": 0.1692,
      "step": 830
    },
    {
      "epoch": 0.7892882311486963,
      "grad_norm": 2.6481103897094727,
      "learning_rate": 1.311460127251708e-06,
      "loss": 0.1608,
      "step": 840
    },
    {
      "epoch": 0.7986845196147522,
      "grad_norm": 4.806708335876465,
      "learning_rate": 1.202766249244306e-06,
      "loss": 0.1692,
      "step": 850
    },
    {
      "epoch": 0.7986845196147522,
      "eval_loss": 0.1683204621076584,
      "eval_runtime": 536.8401,
      "eval_samples_per_second": 1.762,
      "eval_steps_per_second": 0.881,
      "step": 850
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 3.949918031692505,
      "learning_rate": 1.098155538204404e-06,
      "loss": 0.1718,
      "step": 860
    },
    {
      "epoch": 0.817477096546864,
      "grad_norm": 4.87109899520874,
      "learning_rate": 9.977404820713315e-07,
      "loss": 0.1425,
      "step": 870
    },
    {
      "epoch": 0.8268733850129198,
      "grad_norm": 2.2142727375030518,
      "learning_rate": 9.016290571950171e-07,
      "loss": 0.1196,
      "step": 880
    },
    {
      "epoch": 0.8362696734789759,
      "grad_norm": 1.4838513135910034,
      "learning_rate": 8.099246122289861e-07,
      "loss": 0.2077,
      "step": 890
    },
    {
      "epoch": 0.8456659619450317,
      "grad_norm": 3.8143913745880127,
      "learning_rate": 7.227257569995061e-07,
      "loss": 0.1885,
      "step": 900
    },
    {
      "epoch": 0.8456659619450317,
      "eval_loss": 0.16525517404079437,
      "eval_runtime": 525.2309,
      "eval_samples_per_second": 1.801,
      "eval_steps_per_second": 0.901,
      "step": 900
    },
    {
      "epoch": 0.8550622504110876,
      "grad_norm": 4.804526329040527,
      "learning_rate": 6.401262564704019e-07,
      "loss": 0.2379,
      "step": 910
    },
    {
      "epoch": 0.8644585388771435,
      "grad_norm": 4.881964683532715,
      "learning_rate": 5.622149299175539e-07,
      "loss": 0.2253,
      "step": 920
    },
    {
      "epoch": 0.8738548273431994,
      "grad_norm": 3.667691230773926,
      "learning_rate": 4.890755554214954e-07,
      "loss": 0.1952,
      "step": 930
    },
    {
      "epoch": 0.8832511158092553,
      "grad_norm": 2.946258306503296,
      "learning_rate": 4.207867797808102e-07,
      "loss": 0.1522,
      "step": 940
    },
    {
      "epoch": 0.8926474042753113,
      "grad_norm": 6.754327774047852,
      "learning_rate": 3.5742203394319606e-07,
      "loss": 0.2799,
      "step": 950
    },
    {
      "epoch": 0.8926474042753113,
      "eval_loss": 0.163659006357193,
      "eval_runtime": 541.8924,
      "eval_samples_per_second": 1.746,
      "eval_steps_per_second": 0.873,
      "step": 950
    },
    {
      "epoch": 0.9020436927413672,
      "grad_norm": 6.084792137145996,
      "learning_rate": 2.9904945404513606e-07,
      "loss": 0.173,
      "step": 960
    },
    {
      "epoch": 0.9114399812074231,
      "grad_norm": 7.379616737365723,
      "learning_rate": 2.457318081450899e-07,
      "loss": 0.184,
      "step": 970
    },
    {
      "epoch": 0.920836269673479,
      "grad_norm": 1.6431665420532227,
      "learning_rate": 1.9752642872897078e-07,
      "loss": 0.1533,
      "step": 980
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 2.5774223804473877,
      "learning_rate": 1.5448515106050165e-07,
      "loss": 0.2073,
      "step": 990
    },
    {
      "epoch": 0.9396288466055908,
      "grad_norm": 3.7589077949523926,
      "learning_rate": 1.166542574427354e-07,
      "loss": 0.1971,
      "step": 1000
    },
    {
      "epoch": 0.9396288466055908,
      "eval_loss": 0.16281382739543915,
      "eval_runtime": 517.5907,
      "eval_samples_per_second": 1.828,
      "eval_steps_per_second": 0.914,
      "step": 1000
    },
    {
      "epoch": 0.9490251350716467,
      "grad_norm": 2.6644127368927,
      "learning_rate": 8.407442745067552e-08,
      "loss": 0.1787,
      "step": 1010
    },
    {
      "epoch": 0.9584214235377027,
      "grad_norm": 2.4552407264709473,
      "learning_rate": 5.678069418851351e-08,
      "loss": 0.1581,
      "step": 1020
    },
    {
      "epoch": 0.9678177120037585,
      "grad_norm": 4.062498569488525,
      "learning_rate": 3.4802406618518195e-08,
      "loss": 0.1776,
      "step": 1030
    },
    {
      "epoch": 0.9772140004698144,
      "grad_norm": 5.595784664154053,
      "learning_rate": 1.816319800208466e-08,
      "loss": 0.1669,
      "step": 1040
    },
    {
      "epoch": 0.9866102889358703,
      "grad_norm": 3.4040722846984863,
      "learning_rate": 6.880960486877475e-09,
      "loss": 0.1464,
      "step": 1050
    },
    {
      "epoch": 0.9866102889358703,
      "eval_loss": 0.16257165372371674,
      "eval_runtime": 534.9845,
      "eval_samples_per_second": 1.768,
      "eval_steps_per_second": 0.884,
      "step": 1050
    },
    {
      "epoch": 0.9960065774019262,
      "grad_norm": 2.6516175270080566,
      "learning_rate": 9.678258673995189e-10,
      "loss": 0.2124,
      "step": 1060
    },
    {
      "epoch": 1.0,
      "step": 1065,
      "total_flos": 57141526265856.0,
      "train_loss": 0.2802479102018294,
      "train_runtime": 34553.4877,
      "train_samples_per_second": 0.246,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 1065,
  "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": 57141526265856.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}