{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.998053121958003,
  "eval_steps": 200,
  "global_step": 1796,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001112501738283966,
      "grad_norm": 0.6684235958622939,
      "learning_rate": 1.1111111111111112e-06,
      "loss": 1.1751,
      "step": 1
    },
    {
      "epoch": 0.00556250869141983,
      "grad_norm": 0.7610951352005912,
      "learning_rate": 5.555555555555556e-06,
      "loss": 1.2823,
      "step": 5
    },
    {
      "epoch": 0.01112501738283966,
      "grad_norm": 0.8690361671075456,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.2894,
      "step": 10
    },
    {
      "epoch": 0.016687526074259492,
      "grad_norm": 1.059736284119422,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.3166,
      "step": 15
    },
    {
      "epoch": 0.02225003476567932,
      "grad_norm": 0.4906355740047051,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.1771,
      "step": 20
    },
    {
      "epoch": 0.027812543457099152,
      "grad_norm": 1.04376108340149,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.1062,
      "step": 25
    },
    {
      "epoch": 0.033375052148518984,
      "grad_norm": 0.47593208759368216,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.014,
      "step": 30
    },
    {
      "epoch": 0.03893756083993881,
      "grad_norm": 0.2526378868894225,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.9027,
      "step": 35
    },
    {
      "epoch": 0.04450006953135864,
      "grad_norm": 0.2750620823042748,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.8556,
      "step": 40
    },
    {
      "epoch": 0.05006257822277847,
      "grad_norm": 0.22806716350963602,
      "learning_rate": 5e-05,
      "loss": 0.8714,
      "step": 45
    },
    {
      "epoch": 0.055625086914198305,
      "grad_norm": 0.31305577393443185,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.8431,
      "step": 50
    },
    {
      "epoch": 0.061187595605618136,
      "grad_norm": 0.3231781586973102,
      "learning_rate": 6.111111111111112e-05,
      "loss": 0.7896,
      "step": 55
    },
    {
      "epoch": 0.06675010429703797,
      "grad_norm": 0.2652381898767101,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8031,
      "step": 60
    },
    {
      "epoch": 0.0723126129884578,
      "grad_norm": 0.16353190746623922,
      "learning_rate": 7.222222222222222e-05,
      "loss": 0.798,
      "step": 65
    },
    {
      "epoch": 0.07787512167987762,
      "grad_norm": 0.14957803129107605,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.8214,
      "step": 70
    },
    {
      "epoch": 0.08343763037129745,
      "grad_norm": 0.1558832457817548,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.8046,
      "step": 75
    },
    {
      "epoch": 0.08900013906271728,
      "grad_norm": 0.15611943332427167,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.7725,
      "step": 80
    },
    {
      "epoch": 0.09456264775413711,
      "grad_norm": 0.17878911552246932,
      "learning_rate": 9.444444444444444e-05,
      "loss": 0.758,
      "step": 85
    },
    {
      "epoch": 0.10012515644555695,
      "grad_norm": 0.21152631925896626,
      "learning_rate": 0.0001,
      "loss": 0.7741,
      "step": 90
    },
    {
      "epoch": 0.10568766513697678,
      "grad_norm": 0.15798064484261687,
      "learning_rate": 0.00010555555555555557,
      "loss": 0.7411,
      "step": 95
    },
    {
      "epoch": 0.11125017382839661,
      "grad_norm": 0.1770136407809846,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.7582,
      "step": 100
    },
    {
      "epoch": 0.11681268251981644,
      "grad_norm": 0.1721697060786133,
      "learning_rate": 0.00011666666666666668,
      "loss": 0.7908,
      "step": 105
    },
    {
      "epoch": 0.12237519121123627,
      "grad_norm": 0.19163940220247466,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.7769,
      "step": 110
    },
    {
      "epoch": 0.1279376999026561,
      "grad_norm": 0.17258655274801674,
      "learning_rate": 0.00012777777777777776,
      "loss": 0.7291,
      "step": 115
    },
    {
      "epoch": 0.13350020859407594,
      "grad_norm": 0.14647192105198578,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.7147,
      "step": 120
    },
    {
      "epoch": 0.13906271728549577,
      "grad_norm": 0.15483066376892327,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.7253,
      "step": 125
    },
    {
      "epoch": 0.1446252259769156,
      "grad_norm": 0.15985722819525555,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.74,
      "step": 130
    },
    {
      "epoch": 0.15018773466833543,
      "grad_norm": 0.18677759796975052,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7578,
      "step": 135
    },
    {
      "epoch": 0.15575024335975524,
      "grad_norm": 0.1502765821288928,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.7541,
      "step": 140
    },
    {
      "epoch": 0.16131275205117507,
      "grad_norm": 0.16754721310239581,
      "learning_rate": 0.0001611111111111111,
      "loss": 0.7338,
      "step": 145
    },
    {
      "epoch": 0.1668752607425949,
      "grad_norm": 0.15603842447844732,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.7347,
      "step": 150
    },
    {
      "epoch": 0.17243776943401473,
      "grad_norm": 0.16036041756367805,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.7275,
      "step": 155
    },
    {
      "epoch": 0.17800027812543456,
      "grad_norm": 0.17275116566192827,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.7357,
      "step": 160
    },
    {
      "epoch": 0.1835627868168544,
      "grad_norm": 0.16362661400179987,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.7454,
      "step": 165
    },
    {
      "epoch": 0.18912529550827423,
      "grad_norm": 0.1529061378986909,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.7305,
      "step": 170
    },
    {
      "epoch": 0.19468780419969406,
      "grad_norm": 0.16390278757569096,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.7383,
      "step": 175
    },
    {
      "epoch": 0.2002503128911139,
      "grad_norm": 0.16834812585150158,
      "learning_rate": 0.0002,
      "loss": 0.7067,
      "step": 180
    },
    {
      "epoch": 0.20581282158253372,
      "grad_norm": 0.15601116057262598,
      "learning_rate": 0.0001999952758505736,
      "loss": 0.7567,
      "step": 185
    },
    {
      "epoch": 0.21137533027395355,
      "grad_norm": 0.15788111366123353,
      "learning_rate": 0.00019998110384864614,
      "loss": 0.7434,
      "step": 190
    },
    {
      "epoch": 0.2169378389653734,
      "grad_norm": 0.16327699685803637,
      "learning_rate": 0.00019995748533323075,
      "loss": 0.7087,
      "step": 195
    },
    {
      "epoch": 0.22250034765679322,
      "grad_norm": 0.14758830274997248,
      "learning_rate": 0.0001999244225358753,
      "loss": 0.718,
      "step": 200
    },
    {
      "epoch": 0.22250034765679322,
      "eval_loss": 0.7089951634407043,
      "eval_runtime": 38.6391,
      "eval_samples_per_second": 10.533,
      "eval_steps_per_second": 0.673,
      "step": 200
    },
    {
      "epoch": 0.22806285634821305,
      "grad_norm": 0.16285906061792327,
      "learning_rate": 0.00019988191858045178,
      "loss": 0.7323,
      "step": 205
    },
    {
      "epoch": 0.23362536503963288,
      "grad_norm": 0.15445314974456065,
      "learning_rate": 0.00019982997748286082,
      "loss": 0.7427,
      "step": 210
    },
    {
      "epoch": 0.2391878737310527,
      "grad_norm": 0.14969344173380988,
      "learning_rate": 0.00019976860415065256,
      "loss": 0.7171,
      "step": 215
    },
    {
      "epoch": 0.24475038242247255,
      "grad_norm": 0.15378571057430904,
      "learning_rate": 0.00019969780438256293,
      "loss": 0.726,
      "step": 220
    },
    {
      "epoch": 0.2503128911138924,
      "grad_norm": 0.1655361908944567,
      "learning_rate": 0.00019961758486796555,
      "loss": 0.7463,
      "step": 225
    },
    {
      "epoch": 0.2558753998053122,
      "grad_norm": 0.1343012669489156,
      "learning_rate": 0.00019952795318623986,
      "loss": 0.7115,
      "step": 230
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 0.1597015078714079,
      "learning_rate": 0.00019942891780605512,
      "loss": 0.6901,
      "step": 235
    },
    {
      "epoch": 0.2670004171881519,
      "grad_norm": 0.13156659502510382,
      "learning_rate": 0.0001993204880845699,
      "loss": 0.6974,
      "step": 240
    },
    {
      "epoch": 0.2725629258795717,
      "grad_norm": 0.13487041292813268,
      "learning_rate": 0.0001992026742665484,
      "loss": 0.7264,
      "step": 245
    },
    {
      "epoch": 0.27812543457099154,
      "grad_norm": 0.1452928301770259,
      "learning_rate": 0.00019907548748339222,
      "loss": 0.7132,
      "step": 250
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.13005536436409637,
      "learning_rate": 0.00019893893975208874,
      "loss": 0.6924,
      "step": 255
    },
    {
      "epoch": 0.2892504519538312,
      "grad_norm": 0.15551390193086698,
      "learning_rate": 0.0001987930439740757,
      "loss": 0.7137,
      "step": 260
    },
    {
      "epoch": 0.29481296064525103,
      "grad_norm": 0.1411196790735591,
      "learning_rate": 0.0001986378139340222,
      "loss": 0.7003,
      "step": 265
    },
    {
      "epoch": 0.30037546933667086,
      "grad_norm": 0.16701635405751747,
      "learning_rate": 0.0001984732642985263,
      "loss": 0.7318,
      "step": 270
    },
    {
      "epoch": 0.3059379780280907,
      "grad_norm": 0.15781390142645427,
      "learning_rate": 0.00019829941061472943,
      "loss": 0.725,
      "step": 275
    },
    {
      "epoch": 0.31150048671951047,
      "grad_norm": 0.1276451211299801,
      "learning_rate": 0.0001981162693088471,
      "loss": 0.7008,
      "step": 280
    },
    {
      "epoch": 0.3170629954109303,
      "grad_norm": 0.14226714916323183,
      "learning_rate": 0.00019792385768461723,
      "loss": 0.7215,
      "step": 285
    },
    {
      "epoch": 0.32262550410235014,
      "grad_norm": 0.15169879239239556,
      "learning_rate": 0.00019772219392166519,
      "loss": 0.7298,
      "step": 290
    },
    {
      "epoch": 0.32818801279376997,
      "grad_norm": 0.13790872011113864,
      "learning_rate": 0.00019751129707378583,
      "loss": 0.7024,
      "step": 295
    },
    {
      "epoch": 0.3337505214851898,
      "grad_norm": 0.13510983391572584,
      "learning_rate": 0.00019729118706714375,
      "loss": 0.7301,
      "step": 300
    },
    {
      "epoch": 0.33931303017660963,
      "grad_norm": 0.13421290102386768,
      "learning_rate": 0.00019706188469839012,
      "loss": 0.6973,
      "step": 305
    },
    {
      "epoch": 0.34487553886802946,
      "grad_norm": 0.17987364390951446,
      "learning_rate": 0.000196823411632698,
      "loss": 0.7285,
      "step": 310
    },
    {
      "epoch": 0.3504380475594493,
      "grad_norm": 0.1463794049975603,
      "learning_rate": 0.00019657579040171537,
      "loss": 0.7474,
      "step": 315
    },
    {
      "epoch": 0.3560005562508691,
      "grad_norm": 0.14423415874709103,
      "learning_rate": 0.00019631904440143612,
      "loss": 0.6938,
      "step": 320
    },
    {
      "epoch": 0.36156306494228896,
      "grad_norm": 0.11858366900169025,
      "learning_rate": 0.00019605319788998965,
      "loss": 0.6845,
      "step": 325
    },
    {
      "epoch": 0.3671255736337088,
      "grad_norm": 0.14664958369445155,
      "learning_rate": 0.00019577827598534885,
      "loss": 0.7085,
      "step": 330
    },
    {
      "epoch": 0.3726880823251286,
      "grad_norm": 0.16873527257647247,
      "learning_rate": 0.0001954943046629569,
      "loss": 0.717,
      "step": 335
    },
    {
      "epoch": 0.37825059101654845,
      "grad_norm": 0.1486177299286815,
      "learning_rate": 0.00019520131075327298,
      "loss": 0.7321,
      "step": 340
    },
    {
      "epoch": 0.3838130997079683,
      "grad_norm": 0.13978486223349953,
      "learning_rate": 0.00019489932193923735,
      "loss": 0.7258,
      "step": 345
    },
    {
      "epoch": 0.3893756083993881,
      "grad_norm": 0.15478013993645653,
      "learning_rate": 0.00019458836675365556,
      "loss": 0.7147,
      "step": 350
    },
    {
      "epoch": 0.39493811709080795,
      "grad_norm": 0.1335712601381255,
      "learning_rate": 0.00019426847457650292,
      "loss": 0.705,
      "step": 355
    },
    {
      "epoch": 0.4005006257822278,
      "grad_norm": 0.14215220233504217,
      "learning_rate": 0.00019393967563214833,
      "loss": 0.7109,
      "step": 360
    },
    {
      "epoch": 0.4060631344736476,
      "grad_norm": 0.12737803269805706,
      "learning_rate": 0.00019360200098649864,
      "loss": 0.6759,
      "step": 365
    },
    {
      "epoch": 0.41162564316506745,
      "grad_norm": 0.14212696306551803,
      "learning_rate": 0.00019325548254406352,
      "loss": 0.6884,
      "step": 370
    },
    {
      "epoch": 0.4171881518564873,
      "grad_norm": 0.13427514345248226,
      "learning_rate": 0.00019290015304494103,
      "loss": 0.6997,
      "step": 375
    },
    {
      "epoch": 0.4227506605479071,
      "grad_norm": 0.13648211126654036,
      "learning_rate": 0.00019253604606172417,
      "loss": 0.7211,
      "step": 380
    },
    {
      "epoch": 0.42831316923932694,
      "grad_norm": 0.1328171684670597,
      "learning_rate": 0.0001921631959963288,
      "loss": 0.6879,
      "step": 385
    },
    {
      "epoch": 0.4338756779307468,
      "grad_norm": 0.13003415855983963,
      "learning_rate": 0.0001917816380767434,
      "loss": 0.7164,
      "step": 390
    },
    {
      "epoch": 0.4394381866221666,
      "grad_norm": 0.12331669293330129,
      "learning_rate": 0.00019139140835370053,
      "loss": 0.6782,
      "step": 395
    },
    {
      "epoch": 0.44500069531358644,
      "grad_norm": 0.12354925404653357,
      "learning_rate": 0.0001909925436972706,
      "loss": 0.7205,
      "step": 400
    },
    {
      "epoch": 0.44500069531358644,
      "eval_loss": 0.6896927952766418,
      "eval_runtime": 38.0771,
      "eval_samples_per_second": 10.689,
      "eval_steps_per_second": 0.683,
      "step": 400
    },
    {
      "epoch": 0.45056320400500627,
      "grad_norm": 0.12749730782556348,
      "learning_rate": 0.0001905850817933784,
      "loss": 0.7147,
      "step": 405
    },
    {
      "epoch": 0.4561257126964261,
      "grad_norm": 0.1290830353607145,
      "learning_rate": 0.0001901690611402423,
      "loss": 0.7147,
      "step": 410
    },
    {
      "epoch": 0.46168822138784593,
      "grad_norm": 0.14656956459115003,
      "learning_rate": 0.0001897445210447369,
      "loss": 0.7273,
      "step": 415
    },
    {
      "epoch": 0.46725073007926576,
      "grad_norm": 0.13591979089604955,
      "learning_rate": 0.00018931150161867916,
      "loss": 0.7233,
      "step": 420
    },
    {
      "epoch": 0.4728132387706856,
      "grad_norm": 0.14148246469362974,
      "learning_rate": 0.00018887004377503858,
      "loss": 0.6857,
      "step": 425
    },
    {
      "epoch": 0.4783757474621054,
      "grad_norm": 0.13172632177206697,
      "learning_rate": 0.0001884201892240715,
      "loss": 0.6954,
      "step": 430
    },
    {
      "epoch": 0.48393825615352526,
      "grad_norm": 0.15251049696040847,
      "learning_rate": 0.00018796198046938033,
      "loss": 0.7369,
      "step": 435
    },
    {
      "epoch": 0.4895007648449451,
      "grad_norm": 0.14157664597377279,
      "learning_rate": 0.00018749546080389757,
      "loss": 0.6988,
      "step": 440
    },
    {
      "epoch": 0.4950632735363649,
      "grad_norm": 0.14790889100169335,
      "learning_rate": 0.00018702067430579543,
      "loss": 0.7068,
      "step": 445
    },
    {
      "epoch": 0.5006257822277848,
      "grad_norm": 0.13754915966044653,
      "learning_rate": 0.00018653766583432113,
      "loss": 0.7226,
      "step": 450
    },
    {
      "epoch": 0.5061882909192046,
      "grad_norm": 0.1459944140173946,
      "learning_rate": 0.00018604648102555856,
      "loss": 0.6998,
      "step": 455
    },
    {
      "epoch": 0.5117507996106244,
      "grad_norm": 0.14444314196036126,
      "learning_rate": 0.0001855471662881164,
      "loss": 0.7482,
      "step": 460
    },
    {
      "epoch": 0.5173133083020443,
      "grad_norm": 0.1434929187274412,
      "learning_rate": 0.00018503976879874322,
      "loss": 0.695,
      "step": 465
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 0.13128793518588147,
      "learning_rate": 0.0001845243364978702,
      "loss": 0.6895,
      "step": 470
    },
    {
      "epoch": 0.5284383256848839,
      "grad_norm": 0.12701476810931256,
      "learning_rate": 0.0001840009180850815,
      "loss": 0.7061,
      "step": 475
    },
    {
      "epoch": 0.5340008343763037,
      "grad_norm": 0.1264914632820831,
      "learning_rate": 0.00018346956301451304,
      "loss": 0.6962,
      "step": 480
    },
    {
      "epoch": 0.5395633430677236,
      "grad_norm": 0.13208739238621547,
      "learning_rate": 0.00018293032149017984,
      "loss": 0.6863,
      "step": 485
    },
    {
      "epoch": 0.5451258517591434,
      "grad_norm": 0.13323142479850197,
      "learning_rate": 0.00018238324446123266,
      "loss": 0.7039,
      "step": 490
    },
    {
      "epoch": 0.5506883604505632,
      "grad_norm": 0.1588926427932463,
      "learning_rate": 0.0001818283836171441,
      "loss": 0.6924,
      "step": 495
    },
    {
      "epoch": 0.5562508691419831,
      "grad_norm": 0.12667050310382044,
      "learning_rate": 0.00018126579138282503,
      "loss": 0.6991,
      "step": 500
    },
    {
      "epoch": 0.5618133778334029,
      "grad_norm": 0.13081757063531854,
      "learning_rate": 0.000180695520913671,
      "loss": 0.6909,
      "step": 505
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.13598420562667687,
      "learning_rate": 0.0001801176260905402,
      "loss": 0.7088,
      "step": 510
    },
    {
      "epoch": 0.5729383952162426,
      "grad_norm": 0.1300574822823029,
      "learning_rate": 0.00017953216151466263,
      "loss": 0.6821,
      "step": 515
    },
    {
      "epoch": 0.5785009039076624,
      "grad_norm": 0.14206907328811608,
      "learning_rate": 0.00017893918250248104,
      "loss": 0.6981,
      "step": 520
    },
    {
      "epoch": 0.5840634125990822,
      "grad_norm": 0.1557643228084498,
      "learning_rate": 0.00017833874508042466,
      "loss": 0.7018,
      "step": 525
    },
    {
      "epoch": 0.5896259212905021,
      "grad_norm": 0.13942706653578768,
      "learning_rate": 0.00017773090597961554,
      "loss": 0.6738,
      "step": 530
    },
    {
      "epoch": 0.5951884299819219,
      "grad_norm": 0.12004314100744409,
      "learning_rate": 0.00017711572263050845,
      "loss": 0.7039,
      "step": 535
    },
    {
      "epoch": 0.6007509386733417,
      "grad_norm": 0.12451500019905493,
      "learning_rate": 0.00017649325315746478,
      "loss": 0.7034,
      "step": 540
    },
    {
      "epoch": 0.6063134473647616,
      "grad_norm": 0.1225444976108732,
      "learning_rate": 0.00017586355637326054,
      "loss": 0.709,
      "step": 545
    },
    {
      "epoch": 0.6118759560561814,
      "grad_norm": 0.14795401636462246,
      "learning_rate": 0.00017522669177352977,
      "loss": 0.7415,
      "step": 550
    },
    {
      "epoch": 0.6174384647476012,
      "grad_norm": 0.13482563035315856,
      "learning_rate": 0.00017458271953114317,
      "loss": 0.7117,
      "step": 555
    },
    {
      "epoch": 0.6230009734390209,
      "grad_norm": 0.15422494211156157,
      "learning_rate": 0.0001739317004905227,
      "loss": 0.7027,
      "step": 560
    },
    {
      "epoch": 0.6285634821304408,
      "grad_norm": 0.15479270007272883,
      "learning_rate": 0.000173273696161893,
      "loss": 0.7174,
      "step": 565
    },
    {
      "epoch": 0.6341259908218606,
      "grad_norm": 0.13736882345033063,
      "learning_rate": 0.00017260876871546936,
      "loss": 0.7072,
      "step": 570
    },
    {
      "epoch": 0.6396884995132804,
      "grad_norm": 0.130113338971742,
      "learning_rate": 0.00017193698097558416,
      "loss": 0.6987,
      "step": 575
    },
    {
      "epoch": 0.6452510082047003,
      "grad_norm": 0.15120739345519632,
      "learning_rate": 0.00017125839641475072,
      "loss": 0.693,
      "step": 580
    },
    {
      "epoch": 0.6508135168961201,
      "grad_norm": 0.17345133663648482,
      "learning_rate": 0.00017057307914766624,
      "loss": 0.6933,
      "step": 585
    },
    {
      "epoch": 0.6563760255875399,
      "grad_norm": 0.14577660905768358,
      "learning_rate": 0.0001698810939251543,
      "loss": 0.6847,
      "step": 590
    },
    {
      "epoch": 0.6619385342789598,
      "grad_norm": 0.13729541550408036,
      "learning_rate": 0.00016918250612804673,
      "loss": 0.7058,
      "step": 595
    },
    {
      "epoch": 0.6675010429703796,
      "grad_norm": 0.12792609813747083,
      "learning_rate": 0.00016847738176100632,
      "loss": 0.7203,
      "step": 600
    },
    {
      "epoch": 0.6675010429703796,
      "eval_loss": 0.6808404326438904,
      "eval_runtime": 38.0896,
      "eval_samples_per_second": 10.685,
      "eval_steps_per_second": 0.683,
      "step": 600
    },
    {
      "epoch": 0.6730635516617994,
      "grad_norm": 0.12614147228685735,
      "learning_rate": 0.00016776578744629052,
      "loss": 0.6984,
      "step": 605
    },
    {
      "epoch": 0.6786260603532193,
      "grad_norm": 0.14053504602609868,
      "learning_rate": 0.00016704779041745686,
      "loss": 0.7017,
      "step": 610
    },
    {
      "epoch": 0.6841885690446391,
      "grad_norm": 0.144524525939437,
      "learning_rate": 0.00016632345851301031,
      "loss": 0.7031,
      "step": 615
    },
    {
      "epoch": 0.6897510777360589,
      "grad_norm": 0.1240886307637927,
      "learning_rate": 0.000165592860169994,
      "loss": 0.6856,
      "step": 620
    },
    {
      "epoch": 0.6953135864274788,
      "grad_norm": 0.12592281039225006,
      "learning_rate": 0.0001648560644175227,
      "loss": 0.6832,
      "step": 625
    },
    {
      "epoch": 0.7008760951188986,
      "grad_norm": 0.1312108925603738,
      "learning_rate": 0.00016411314087026106,
      "loss": 0.7266,
      "step": 630
    },
    {
      "epoch": 0.7064386038103184,
      "grad_norm": 0.12871371439878188,
      "learning_rate": 0.00016336415972184612,
      "loss": 0.6892,
      "step": 635
    },
    {
      "epoch": 0.7120011125017383,
      "grad_norm": 0.1423393128313328,
      "learning_rate": 0.00016260919173825508,
      "loss": 0.684,
      "step": 640
    },
    {
      "epoch": 0.7175636211931581,
      "grad_norm": 0.1452224910144209,
      "learning_rate": 0.00016184830825111924,
      "loss": 0.6824,
      "step": 645
    },
    {
      "epoch": 0.7231261298845779,
      "grad_norm": 0.12119255762333672,
      "learning_rate": 0.00016108158115098444,
      "loss": 0.686,
      "step": 650
    },
    {
      "epoch": 0.7286886385759977,
      "grad_norm": 0.1411776440916737,
      "learning_rate": 0.0001603090828805185,
      "loss": 0.6878,
      "step": 655
    },
    {
      "epoch": 0.7342511472674176,
      "grad_norm": 0.17300629248103022,
      "learning_rate": 0.0001595308864276666,
      "loss": 0.7139,
      "step": 660
    },
    {
      "epoch": 0.7398136559588374,
      "grad_norm": 0.1458091025518703,
      "learning_rate": 0.0001587470653187553,
      "loss": 0.729,
      "step": 665
    },
    {
      "epoch": 0.7453761646502572,
      "grad_norm": 0.14056535678032148,
      "learning_rate": 0.00015795769361154547,
      "loss": 0.6972,
      "step": 670
    },
    {
      "epoch": 0.7509386733416771,
      "grad_norm": 0.13734797531202647,
      "learning_rate": 0.000157162845888235,
      "loss": 0.6779,
      "step": 675
    },
    {
      "epoch": 0.7565011820330969,
      "grad_norm": 0.12703010084902983,
      "learning_rate": 0.00015636259724841222,
      "loss": 0.7027,
      "step": 680
    },
    {
      "epoch": 0.7620636907245167,
      "grad_norm": 0.12697872232577906,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.7079,
      "step": 685
    },
    {
      "epoch": 0.7676261994159366,
      "grad_norm": 0.15015643114183339,
      "learning_rate": 0.00015474620016191294,
      "loss": 0.6938,
      "step": 690
    },
    {
      "epoch": 0.7731887081073564,
      "grad_norm": 0.1468310767380953,
      "learning_rate": 0.00015393020443726381,
      "loss": 0.7061,
      "step": 695
    },
    {
      "epoch": 0.7787512167987762,
      "grad_norm": 0.1178258952392868,
      "learning_rate": 0.00015310911322572753,
      "loss": 0.6635,
      "step": 700
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.1182521343472938,
      "learning_rate": 0.00015228300410645556,
      "loss": 0.6783,
      "step": 705
    },
    {
      "epoch": 0.7898762341816159,
      "grad_norm": 0.11865217322316654,
      "learning_rate": 0.00015145195513270644,
      "loss": 0.6822,
      "step": 710
    },
    {
      "epoch": 0.7954387428730357,
      "grad_norm": 0.11500353884529863,
      "learning_rate": 0.00015061604482447075,
      "loss": 0.6668,
      "step": 715
    },
    {
      "epoch": 0.8010012515644556,
      "grad_norm": 0.1314805700111582,
      "learning_rate": 0.0001497753521610526,
      "loss": 0.7105,
      "step": 720
    },
    {
      "epoch": 0.8065637602558754,
      "grad_norm": 0.14124896793550357,
      "learning_rate": 0.00014892995657360717,
      "loss": 0.7142,
      "step": 725
    },
    {
      "epoch": 0.8121262689472952,
      "grad_norm": 0.13739934885223082,
      "learning_rate": 0.00014807993793763619,
      "loss": 0.6815,
      "step": 730
    },
    {
      "epoch": 0.8176887776387151,
      "grad_norm": 0.13281564930523101,
      "learning_rate": 0.0001472253765654406,
      "loss": 0.67,
      "step": 735
    },
    {
      "epoch": 0.8232512863301349,
      "grad_norm": 0.11821804301835571,
      "learning_rate": 0.00014636635319853275,
      "loss": 0.6969,
      "step": 740
    },
    {
      "epoch": 0.8288137950215547,
      "grad_norm": 0.13929966861379298,
      "learning_rate": 0.00014550294900000753,
      "loss": 0.696,
      "step": 745
    },
    {
      "epoch": 0.8343763037129746,
      "grad_norm": 0.1358532247107506,
      "learning_rate": 0.00014463524554687399,
      "loss": 0.6987,
      "step": 750
    },
    {
      "epoch": 0.8399388124043944,
      "grad_norm": 0.14607145415562992,
      "learning_rate": 0.00014376332482234747,
      "loss": 0.6713,
      "step": 755
    },
    {
      "epoch": 0.8455013210958142,
      "grad_norm": 0.13045660818329083,
      "learning_rate": 0.0001428872692081038,
      "loss": 0.6782,
      "step": 760
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.14868265540995262,
      "learning_rate": 0.00014200716147649557,
      "loss": 0.6856,
      "step": 765
    },
    {
      "epoch": 0.8566263384786539,
      "grad_norm": 0.1523898280318719,
      "learning_rate": 0.00014112308478273145,
      "loss": 0.7077,
      "step": 770
    },
    {
      "epoch": 0.8621888471700737,
      "grad_norm": 0.14374188108756408,
      "learning_rate": 0.00014023512265701955,
      "loss": 0.6557,
      "step": 775
    },
    {
      "epoch": 0.8677513558614935,
      "grad_norm": 0.13285163140650738,
      "learning_rate": 0.00013934335899667527,
      "loss": 0.7028,
      "step": 780
    },
    {
      "epoch": 0.8733138645529134,
      "grad_norm": 0.12419599179555058,
      "learning_rate": 0.0001384478780581942,
      "loss": 0.6753,
      "step": 785
    },
    {
      "epoch": 0.8788763732443332,
      "grad_norm": 0.12619683911200477,
      "learning_rate": 0.00013754876444929166,
      "loss": 0.7033,
      "step": 790
    },
    {
      "epoch": 0.884438881935753,
      "grad_norm": 0.14380964532401144,
      "learning_rate": 0.00013664610312090838,
      "loss": 0.7022,
      "step": 795
    },
    {
      "epoch": 0.8900013906271729,
      "grad_norm": 0.13341619640026267,
      "learning_rate": 0.0001357399793591844,
      "loss": 0.703,
      "step": 800
    },
    {
      "epoch": 0.8900013906271729,
      "eval_loss": 0.6755693554878235,
      "eval_runtime": 38.0742,
      "eval_samples_per_second": 10.69,
      "eval_steps_per_second": 0.683,
      "step": 800
    },
    {
      "epoch": 0.8955638993185927,
      "grad_norm": 0.11373621352884696,
      "learning_rate": 0.00013483047877740055,
      "loss": 0.6554,
      "step": 805
    },
    {
      "epoch": 0.9011264080100125,
      "grad_norm": 0.1418177008323639,
      "learning_rate": 0.00013391768730789002,
      "loss": 0.7435,
      "step": 810
    },
    {
      "epoch": 0.9066889167014324,
      "grad_norm": 0.14095795493706695,
      "learning_rate": 0.00013300169119391864,
      "loss": 0.6856,
      "step": 815
    },
    {
      "epoch": 0.9122514253928522,
      "grad_norm": 0.13583867929382498,
      "learning_rate": 0.00013208257698153677,
      "loss": 0.6791,
      "step": 820
    },
    {
      "epoch": 0.917813934084272,
      "grad_norm": 0.13643641315332133,
      "learning_rate": 0.00013116043151140203,
      "loss": 0.6958,
      "step": 825
    },
    {
      "epoch": 0.9233764427756919,
      "grad_norm": 0.12156612730761757,
      "learning_rate": 0.00013023534191057426,
      "loss": 0.6912,
      "step": 830
    },
    {
      "epoch": 0.9289389514671117,
      "grad_norm": 0.14020483760043728,
      "learning_rate": 0.0001293073955842836,
      "loss": 0.7086,
      "step": 835
    },
    {
      "epoch": 0.9345014601585315,
      "grad_norm": 0.13715121587687112,
      "learning_rate": 0.0001283766802076722,
      "loss": 0.6804,
      "step": 840
    },
    {
      "epoch": 0.9400639688499514,
      "grad_norm": 0.12395531650931035,
      "learning_rate": 0.00012744328371751024,
      "loss": 0.7246,
      "step": 845
    },
    {
      "epoch": 0.9456264775413712,
      "grad_norm": 0.1351012642378018,
      "learning_rate": 0.00012650729430388764,
      "loss": 0.6695,
      "step": 850
    },
    {
      "epoch": 0.951188986232791,
      "grad_norm": 0.14258700665297835,
      "learning_rate": 0.00012556880040188144,
      "loss": 0.6844,
      "step": 855
    },
    {
      "epoch": 0.9567514949242109,
      "grad_norm": 0.14370950835852644,
      "learning_rate": 0.00012462789068320017,
      "loss": 0.7156,
      "step": 860
    },
    {
      "epoch": 0.9623140036156307,
      "grad_norm": 0.1390057701240165,
      "learning_rate": 0.00012368465404780598,
      "loss": 0.6652,
      "step": 865
    },
    {
      "epoch": 0.9678765123070505,
      "grad_norm": 0.127046163008197,
      "learning_rate": 0.00012273917961551513,
      "loss": 0.6641,
      "step": 870
    },
    {
      "epoch": 0.9734390209984704,
      "grad_norm": 0.14753709766070622,
      "learning_rate": 0.00012179155671757754,
      "loss": 0.689,
      "step": 875
    },
    {
      "epoch": 0.9790015296898902,
      "grad_norm": 0.13366681839894046,
      "learning_rate": 0.00012084187488823657,
      "loss": 0.6938,
      "step": 880
    },
    {
      "epoch": 0.98456403838131,
      "grad_norm": 0.14364888110758262,
      "learning_rate": 0.00011989022385626967,
      "loss": 0.6867,
      "step": 885
    },
    {
      "epoch": 0.9901265470727298,
      "grad_norm": 0.13750035239201705,
      "learning_rate": 0.00011893669353651031,
      "loss": 0.6926,
      "step": 890
    },
    {
      "epoch": 0.9956890557641497,
      "grad_norm": 0.12165819999979594,
      "learning_rate": 0.00011798137402135277,
      "loss": 0.6781,
      "step": 895
    },
    {
      "epoch": 1.0012515644555695,
      "grad_norm": 0.13460664662956676,
      "learning_rate": 0.00011702435557223987,
      "loss": 0.6907,
      "step": 900
    },
    {
      "epoch": 1.0068140731469892,
      "grad_norm": 0.14812357106021773,
      "learning_rate": 0.00011606572861113474,
      "loss": 0.6739,
      "step": 905
    },
    {
      "epoch": 1.0123765818384092,
      "grad_norm": 0.14414234656282895,
      "learning_rate": 0.00011510558371197753,
      "loss": 0.6581,
      "step": 910
    },
    {
      "epoch": 1.017939090529829,
      "grad_norm": 0.1417200021185479,
      "learning_rate": 0.00011414401159212778,
      "loss": 0.6886,
      "step": 915
    },
    {
      "epoch": 1.0235015992212488,
      "grad_norm": 0.13876983385482528,
      "learning_rate": 0.00011318110310379301,
      "loss": 0.6737,
      "step": 920
    },
    {
      "epoch": 1.0290641079126686,
      "grad_norm": 0.15251072221895987,
      "learning_rate": 0.00011221694922544491,
      "loss": 0.6692,
      "step": 925
    },
    {
      "epoch": 1.0346266166040885,
      "grad_norm": 0.14026789842910758,
      "learning_rate": 0.0001112516410532233,
      "loss": 0.6562,
      "step": 930
    },
    {
      "epoch": 1.0401891252955082,
      "grad_norm": 0.12707738202474425,
      "learning_rate": 0.00011028526979232913,
      "loss": 0.6618,
      "step": 935
    },
    {
      "epoch": 1.0457516339869282,
      "grad_norm": 0.14606846473361,
      "learning_rate": 0.00010931792674840718,
      "loss": 0.6746,
      "step": 940
    },
    {
      "epoch": 1.0513141426783479,
      "grad_norm": 0.14011972796939615,
      "learning_rate": 0.00010834970331891914,
      "loss": 0.6869,
      "step": 945
    },
    {
      "epoch": 1.0568766513697678,
      "grad_norm": 0.1563818365447484,
      "learning_rate": 0.0001073806909845082,
      "loss": 0.66,
      "step": 950
    },
    {
      "epoch": 1.0624391600611875,
      "grad_norm": 0.12113541850928697,
      "learning_rate": 0.00010641098130035562,
      "loss": 0.6567,
      "step": 955
    },
    {
      "epoch": 1.0680016687526075,
      "grad_norm": 0.12784803662349467,
      "learning_rate": 0.00010544066588753044,
      "loss": 0.6478,
      "step": 960
    },
    {
      "epoch": 1.0735641774440272,
      "grad_norm": 0.13555213849737605,
      "learning_rate": 0.00010446983642433259,
      "loss": 0.6423,
      "step": 965
    },
    {
      "epoch": 1.0791266861354472,
      "grad_norm": 0.14956837158318062,
      "learning_rate": 0.00010349858463763113,
      "loss": 0.6482,
      "step": 970
    },
    {
      "epoch": 1.0846891948268669,
      "grad_norm": 0.14302685723153047,
      "learning_rate": 0.0001025270022941975,
      "loss": 0.6619,
      "step": 975
    },
    {
      "epoch": 1.0902517035182868,
      "grad_norm": 0.1531273940282806,
      "learning_rate": 0.0001015551811920351,
      "loss": 0.6818,
      "step": 980
    },
    {
      "epoch": 1.0958142122097065,
      "grad_norm": 0.1431917561070241,
      "learning_rate": 0.00010058321315170596,
      "loss": 0.6597,
      "step": 985
    },
    {
      "epoch": 1.1013767209011265,
      "grad_norm": 0.14533278983667672,
      "learning_rate": 9.961119000765531e-05,
      "loss": 0.641,
      "step": 990
    },
    {
      "epoch": 1.1069392295925462,
      "grad_norm": 0.1426693103942941,
      "learning_rate": 9.863920359953474e-05,
      "loss": 0.6864,
      "step": 995
    },
    {
      "epoch": 1.1125017382839661,
      "grad_norm": 0.14515333605223138,
      "learning_rate": 9.766734576352478e-05,
      "loss": 0.6759,
      "step": 1000
    },
    {
      "epoch": 1.1125017382839661,
      "eval_loss": 0.6748408079147339,
      "eval_runtime": 38.0571,
      "eval_samples_per_second": 10.694,
      "eval_steps_per_second": 0.683,
      "step": 1000
    },
    {
      "epoch": 1.1180642469753859,
      "grad_norm": 0.13884691864173954,
      "learning_rate": 9.669570832365838e-05,
      "loss": 0.6536,
      "step": 1005
    },
    {
      "epoch": 1.1236267556668058,
      "grad_norm": 0.14190147387793983,
      "learning_rate": 9.572438308314446e-05,
      "loss": 0.6448,
      "step": 1010
    },
    {
      "epoch": 1.1291892643582255,
      "grad_norm": 0.1460356352229923,
      "learning_rate": 9.475346181569467e-05,
      "loss": 0.6709,
      "step": 1015
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 0.15004591423623692,
      "learning_rate": 9.378303625685195e-05,
      "loss": 0.6338,
      "step": 1020
    },
    {
      "epoch": 1.1403142817410652,
      "grad_norm": 0.14709044334780488,
      "learning_rate": 9.281319809532329e-05,
      "loss": 0.6482,
      "step": 1025
    },
    {
      "epoch": 1.1458767904324851,
      "grad_norm": 0.1339983467335465,
      "learning_rate": 9.18440389643165e-05,
      "loss": 0.6564,
      "step": 1030
    },
    {
      "epoch": 1.1514392991239049,
      "grad_norm": 0.15465369318467384,
      "learning_rate": 9.08756504328827e-05,
      "loss": 0.631,
      "step": 1035
    },
    {
      "epoch": 1.1570018078153248,
      "grad_norm": 0.14414339429238215,
      "learning_rate": 8.990812399726435e-05,
      "loss": 0.63,
      "step": 1040
    },
    {
      "epoch": 1.1625643165067445,
      "grad_norm": 0.1530406190835784,
      "learning_rate": 8.894155107225062e-05,
      "loss": 0.6599,
      "step": 1045
    },
    {
      "epoch": 1.1681268251981645,
      "grad_norm": 0.18004713578221632,
      "learning_rate": 8.797602298254004e-05,
      "loss": 0.6588,
      "step": 1050
    },
    {
      "epoch": 1.1736893338895842,
      "grad_norm": 0.1395761709805775,
      "learning_rate": 8.701163095411212e-05,
      "loss": 0.6388,
      "step": 1055
    },
    {
      "epoch": 1.1792518425810041,
      "grad_norm": 0.14800345539370582,
      "learning_rate": 8.604846610560771e-05,
      "loss": 0.6469,
      "step": 1060
    },
    {
      "epoch": 1.1848143512724238,
      "grad_norm": 0.18153262554102811,
      "learning_rate": 8.508661943972021e-05,
      "loss": 0.6476,
      "step": 1065
    },
    {
      "epoch": 1.1903768599638438,
      "grad_norm": 0.1460085066143512,
      "learning_rate": 8.412618183459708e-05,
      "loss": 0.6417,
      "step": 1070
    },
    {
      "epoch": 1.1959393686552635,
      "grad_norm": 0.1563928211034322,
      "learning_rate": 8.316724403525359e-05,
      "loss": 0.6655,
      "step": 1075
    },
    {
      "epoch": 1.2015018773466832,
      "grad_norm": 0.13021633068783775,
      "learning_rate": 8.220989664499878e-05,
      "loss": 0.6495,
      "step": 1080
    },
    {
      "epoch": 1.2070643860381032,
      "grad_norm": 0.15359952593058618,
      "learning_rate": 8.125423011687524e-05,
      "loss": 0.6518,
      "step": 1085
    },
    {
      "epoch": 1.2126268947295231,
      "grad_norm": 0.14327581045453255,
      "learning_rate": 8.030033474511249e-05,
      "loss": 0.6428,
      "step": 1090
    },
    {
      "epoch": 1.2181894034209428,
      "grad_norm": 0.14877277012088305,
      "learning_rate": 7.934830065659599e-05,
      "loss": 0.6823,
      "step": 1095
    },
    {
      "epoch": 1.2237519121123626,
      "grad_norm": 0.1350097173259691,
      "learning_rate": 7.839821780235168e-05,
      "loss": 0.6656,
      "step": 1100
    },
    {
      "epoch": 1.2293144208037825,
      "grad_norm": 0.14805261697578703,
      "learning_rate": 7.74501759490469e-05,
      "loss": 0.6649,
      "step": 1105
    },
    {
      "epoch": 1.2348769294952024,
      "grad_norm": 0.14241031431419957,
      "learning_rate": 7.650426467050926e-05,
      "loss": 0.645,
      "step": 1110
    },
    {
      "epoch": 1.2404394381866222,
      "grad_norm": 0.14677979540609026,
      "learning_rate": 7.556057333926318e-05,
      "loss": 0.6322,
      "step": 1115
    },
    {
      "epoch": 1.2460019468780419,
      "grad_norm": 0.1540439921077116,
      "learning_rate": 7.461919111808595e-05,
      "loss": 0.6425,
      "step": 1120
    },
    {
      "epoch": 1.2515644555694618,
      "grad_norm": 0.16093917993335288,
      "learning_rate": 7.368020695158312e-05,
      "loss": 0.6708,
      "step": 1125
    },
    {
      "epoch": 1.2571269642608818,
      "grad_norm": 0.14072702856543545,
      "learning_rate": 7.274370955778498e-05,
      "loss": 0.6412,
      "step": 1130
    },
    {
      "epoch": 1.2626894729523015,
      "grad_norm": 0.1372982963866414,
      "learning_rate": 7.180978741976397e-05,
      "loss": 0.6354,
      "step": 1135
    },
    {
      "epoch": 1.2682519816437212,
      "grad_norm": 0.1361010979443787,
      "learning_rate": 7.087852877727481e-05,
      "loss": 0.6297,
      "step": 1140
    },
    {
      "epoch": 1.2738144903351412,
      "grad_norm": 0.15152880519317802,
      "learning_rate": 6.995002161841708e-05,
      "loss": 0.6648,
      "step": 1145
    },
    {
      "epoch": 1.279376999026561,
      "grad_norm": 0.15111271273299604,
      "learning_rate": 6.902435367132208e-05,
      "loss": 0.6811,
      "step": 1150
    },
    {
      "epoch": 1.2849395077179808,
      "grad_norm": 0.1555612197330931,
      "learning_rate": 6.810161239586375e-05,
      "loss": 0.6639,
      "step": 1155
    },
    {
      "epoch": 1.2905020164094005,
      "grad_norm": 0.1404429960918057,
      "learning_rate": 6.718188497539554e-05,
      "loss": 0.6416,
      "step": 1160
    },
    {
      "epoch": 1.2960645251008205,
      "grad_norm": 0.1493351620856526,
      "learning_rate": 6.626525830851267e-05,
      "loss": 0.6284,
      "step": 1165
    },
    {
      "epoch": 1.3016270337922404,
      "grad_norm": 0.15944635272625493,
      "learning_rate": 6.535181900084206e-05,
      "loss": 0.6402,
      "step": 1170
    },
    {
      "epoch": 1.3071895424836601,
      "grad_norm": 0.1534235543873645,
      "learning_rate": 6.444165335685927e-05,
      "loss": 0.6373,
      "step": 1175
    },
    {
      "epoch": 1.3127520511750799,
      "grad_norm": 0.1404290668723592,
      "learning_rate": 6.35348473717345e-05,
      "loss": 0.6596,
      "step": 1180
    },
    {
      "epoch": 1.3183145598664998,
      "grad_norm": 0.15190370802350445,
      "learning_rate": 6.263148672320714e-05,
      "loss": 0.6519,
      "step": 1185
    },
    {
      "epoch": 1.3238770685579198,
      "grad_norm": 0.1396377515861422,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.6539,
      "step": 1190
    },
    {
      "epoch": 1.3294395772493395,
      "grad_norm": 0.1413554398489568,
      "learning_rate": 6.083544251120993e-05,
      "loss": 0.6436,
      "step": 1195
    },
    {
      "epoch": 1.3350020859407592,
      "grad_norm": 0.175529243963575,
      "learning_rate": 5.9942928643364724e-05,
      "loss": 0.6533,
      "step": 1200
    },
    {
      "epoch": 1.3350020859407592,
      "eval_loss": 0.6695060133934021,
      "eval_runtime": 38.0647,
      "eval_samples_per_second": 10.692,
      "eval_steps_per_second": 0.683,
      "step": 1200
    },
    {
      "epoch": 1.3405645946321791,
      "grad_norm": 0.16769090072157003,
      "learning_rate": 5.905419948733302e-05,
      "loss": 0.6434,
      "step": 1205
    },
    {
      "epoch": 1.3461271033235989,
      "grad_norm": 0.17558035684023568,
      "learning_rate": 5.816933901290136e-05,
      "loss": 0.6954,
      "step": 1210
    },
    {
      "epoch": 1.3516896120150188,
      "grad_norm": 0.15028360304997448,
      "learning_rate": 5.728843082433193e-05,
      "loss": 0.6563,
      "step": 1215
    },
    {
      "epoch": 1.3572521207064385,
      "grad_norm": 0.16888366454421866,
      "learning_rate": 5.6411558152462894e-05,
      "loss": 0.6383,
      "step": 1220
    },
    {
      "epoch": 1.3628146293978585,
      "grad_norm": 0.1507413542567497,
      "learning_rate": 5.553880384684493e-05,
      "loss": 0.6382,
      "step": 1225
    },
    {
      "epoch": 1.3683771380892782,
      "grad_norm": 0.15944821317229088,
      "learning_rate": 5.4670250367913023e-05,
      "loss": 0.6589,
      "step": 1230
    },
    {
      "epoch": 1.3739396467806981,
      "grad_norm": 0.14215107373647873,
      "learning_rate": 5.380597977919557e-05,
      "loss": 0.6346,
      "step": 1235
    },
    {
      "epoch": 1.3795021554721179,
      "grad_norm": 0.16243215498334238,
      "learning_rate": 5.2946073739560706e-05,
      "loss": 0.6527,
      "step": 1240
    },
    {
      "epoch": 1.3850646641635378,
      "grad_norm": 0.1562039482784561,
      "learning_rate": 5.209061349550095e-05,
      "loss": 0.66,
      "step": 1245
    },
    {
      "epoch": 1.3906271728549575,
      "grad_norm": 0.1680769018618033,
      "learning_rate": 5.1239679873456634e-05,
      "loss": 0.6699,
      "step": 1250
    },
    {
      "epoch": 1.3961896815463775,
      "grad_norm": 0.1478360199044516,
      "learning_rate": 5.039335327217951e-05,
      "loss": 0.6502,
      "step": 1255
    },
    {
      "epoch": 1.4017521902377972,
      "grad_norm": 0.14915391173643802,
      "learning_rate": 4.955171365513603e-05,
      "loss": 0.6143,
      "step": 1260
    },
    {
      "epoch": 1.4073146989292171,
      "grad_norm": 0.15851697773820939,
      "learning_rate": 4.871484054295258e-05,
      "loss": 0.6572,
      "step": 1265
    },
    {
      "epoch": 1.4128772076206368,
      "grad_norm": 0.15216697385980452,
      "learning_rate": 4.7882813005901696e-05,
      "loss": 0.657,
      "step": 1270
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 0.1437749041937587,
      "learning_rate": 4.705570965643176e-05,
      "loss": 0.6411,
      "step": 1275
    },
    {
      "epoch": 1.4240022250034765,
      "grad_norm": 0.16683978696735308,
      "learning_rate": 4.623360864173893e-05,
      "loss": 0.651,
      "step": 1280
    },
    {
      "epoch": 1.4295647336948965,
      "grad_norm": 0.1621572781654395,
      "learning_rate": 4.541658763638406e-05,
      "loss": 0.6492,
      "step": 1285
    },
    {
      "epoch": 1.4351272423863162,
      "grad_norm": 0.15994302691177126,
      "learning_rate": 4.460472383495331e-05,
      "loss": 0.6577,
      "step": 1290
    },
    {
      "epoch": 1.4406897510777361,
      "grad_norm": 0.14692563499946057,
      "learning_rate": 4.379809394476501e-05,
      "loss": 0.6496,
      "step": 1295
    },
    {
      "epoch": 1.4462522597691558,
      "grad_norm": 0.17176689432434047,
      "learning_rate": 4.2996774178621736e-05,
      "loss": 0.6433,
      "step": 1300
    },
    {
      "epoch": 1.4518147684605758,
      "grad_norm": 0.1446292926663316,
      "learning_rate": 4.220084024760982e-05,
      "loss": 0.6223,
      "step": 1305
    },
    {
      "epoch": 1.4573772771519955,
      "grad_norm": 0.15172393816056104,
      "learning_rate": 4.141036735394574e-05,
      "loss": 0.6481,
      "step": 1310
    },
    {
      "epoch": 1.4629397858434154,
      "grad_norm": 0.16544844619207105,
      "learning_rate": 4.0625430183870796e-05,
      "loss": 0.6411,
      "step": 1315
    },
    {
      "epoch": 1.4685022945348352,
      "grad_norm": 0.15934504430033075,
      "learning_rate": 3.984610290059467e-05,
      "loss": 0.6678,
      "step": 1320
    },
    {
      "epoch": 1.474064803226255,
      "grad_norm": 0.15204965773692086,
      "learning_rate": 3.907245913728807e-05,
      "loss": 0.6549,
      "step": 1325
    },
    {
      "epoch": 1.4796273119176748,
      "grad_norm": 0.15256724381583675,
      "learning_rate": 3.830457199012585e-05,
      "loss": 0.6478,
      "step": 1330
    },
    {
      "epoch": 1.4851898206090948,
      "grad_norm": 0.15150975920035156,
      "learning_rate": 3.754251401138051e-05,
      "loss": 0.6385,
      "step": 1335
    },
    {
      "epoch": 1.4907523293005145,
      "grad_norm": 0.17068279689989202,
      "learning_rate": 3.678635720256737e-05,
      "loss": 0.6659,
      "step": 1340
    },
    {
      "epoch": 1.4963148379919344,
      "grad_norm": 0.15001304767115145,
      "learning_rate": 3.6036173007641435e-05,
      "loss": 0.66,
      "step": 1345
    },
    {
      "epoch": 1.5018773466833542,
      "grad_norm": 0.14424590095876771,
      "learning_rate": 3.529203230624747e-05,
      "loss": 0.651,
      "step": 1350
    },
    {
      "epoch": 1.5074398553747739,
      "grad_norm": 0.16690307331407334,
      "learning_rate": 3.455400540702274e-05,
      "loss": 0.6508,
      "step": 1355
    },
    {
      "epoch": 1.5130023640661938,
      "grad_norm": 0.1506720689857848,
      "learning_rate": 3.3822162040954354e-05,
      "loss": 0.6347,
      "step": 1360
    },
    {
      "epoch": 1.5185648727576138,
      "grad_norm": 0.15108676554413317,
      "learning_rate": 3.309657135479065e-05,
      "loss": 0.6449,
      "step": 1365
    },
    {
      "epoch": 1.5241273814490335,
      "grad_norm": 0.1397876543411103,
      "learning_rate": 3.237730190450816e-05,
      "loss": 0.6382,
      "step": 1370
    },
    {
      "epoch": 1.5296898901404532,
      "grad_norm": 0.15000237273739636,
      "learning_rate": 3.166442164883403e-05,
      "loss": 0.6607,
      "step": 1375
    },
    {
      "epoch": 1.5352523988318731,
      "grad_norm": 0.15901665795803346,
      "learning_rate": 3.0957997942825336e-05,
      "loss": 0.6403,
      "step": 1380
    },
    {
      "epoch": 1.540814907523293,
      "grad_norm": 0.1500239251091428,
      "learning_rate": 3.0258097531504937e-05,
      "loss": 0.6595,
      "step": 1385
    },
    {
      "epoch": 1.5463774162147128,
      "grad_norm": 0.16536122507336246,
      "learning_rate": 2.9564786543555388e-05,
      "loss": 0.6515,
      "step": 1390
    },
    {
      "epoch": 1.5519399249061325,
      "grad_norm": 0.14948767796744467,
      "learning_rate": 2.8878130485070852e-05,
      "loss": 0.6341,
      "step": 1395
    },
    {
      "epoch": 1.5575024335975525,
      "grad_norm": 0.16630242366164855,
      "learning_rate": 2.819819423336775e-05,
      "loss": 0.6458,
      "step": 1400
    },
    {
      "epoch": 1.5575024335975525,
      "eval_loss": 0.6669326424598694,
      "eval_runtime": 38.0635,
      "eval_samples_per_second": 10.693,
      "eval_steps_per_second": 0.683,
      "step": 1400
    },
    {
      "epoch": 1.5630649422889724,
      "grad_norm": 0.15092670649471096,
      "learning_rate": 2.7525042030855218e-05,
      "loss": 0.6285,
      "step": 1405
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.17817145439236162,
      "learning_rate": 2.6858737478965035e-05,
      "loss": 0.6786,
      "step": 1410
    },
    {
      "epoch": 1.5741899596718119,
      "grad_norm": 0.14411321645345596,
      "learning_rate": 2.6199343532142573e-05,
      "loss": 0.6487,
      "step": 1415
    },
    {
      "epoch": 1.5797524683632318,
      "grad_norm": 0.1729923377951436,
      "learning_rate": 2.5546922491898495e-05,
      "loss": 0.6466,
      "step": 1420
    },
    {
      "epoch": 1.5853149770546517,
      "grad_norm": 0.17040206170029934,
      "learning_rate": 2.4901536000922497e-05,
      "loss": 0.665,
      "step": 1425
    },
    {
      "epoch": 1.5908774857460715,
      "grad_norm": 0.16055497144569197,
      "learning_rate": 2.4263245037258995e-05,
      "loss": 0.6665,
      "step": 1430
    },
    {
      "epoch": 1.5964399944374912,
      "grad_norm": 0.1655874585771864,
      "learning_rate": 2.363210990854582e-05,
      "loss": 0.6734,
      "step": 1435
    },
    {
      "epoch": 1.6020025031289111,
      "grad_norm": 0.1651519002975595,
      "learning_rate": 2.300819024631603e-05,
      "loss": 0.6691,
      "step": 1440
    },
    {
      "epoch": 1.607565011820331,
      "grad_norm": 0.162990807682259,
      "learning_rate": 2.239154500036399e-05,
      "loss": 0.6805,
      "step": 1445
    },
    {
      "epoch": 1.6131275205117508,
      "grad_norm": 0.1717600360257139,
      "learning_rate": 2.178223243317532e-05,
      "loss": 0.6399,
      "step": 1450
    },
    {
      "epoch": 1.6186900292031705,
      "grad_norm": 0.1739831864715599,
      "learning_rate": 2.1180310114422362e-05,
      "loss": 0.6689,
      "step": 1455
    },
    {
      "epoch": 1.6242525378945905,
      "grad_norm": 0.15498282638359004,
      "learning_rate": 2.058583491552465e-05,
      "loss": 0.6675,
      "step": 1460
    },
    {
      "epoch": 1.6298150465860104,
      "grad_norm": 0.17242195548428726,
      "learning_rate": 1.9998863004275593e-05,
      "loss": 0.6618,
      "step": 1465
    },
    {
      "epoch": 1.6353775552774301,
      "grad_norm": 0.16154448145412242,
      "learning_rate": 1.941944983953552e-05,
      "loss": 0.6406,
      "step": 1470
    },
    {
      "epoch": 1.6409400639688498,
      "grad_norm": 0.1624668193562119,
      "learning_rate": 1.884765016599186e-05,
      "loss": 0.6223,
      "step": 1475
    },
    {
      "epoch": 1.6465025726602698,
      "grad_norm": 0.16026073767873994,
      "learning_rate": 1.8283518008986567e-05,
      "loss": 0.6424,
      "step": 1480
    },
    {
      "epoch": 1.6520650813516897,
      "grad_norm": 0.14391017994489602,
      "learning_rate": 1.7727106669411776e-05,
      "loss": 0.6323,
      "step": 1485
    },
    {
      "epoch": 1.6576275900431094,
      "grad_norm": 0.16566629921954873,
      "learning_rate": 1.7178468718673714e-05,
      "loss": 0.6605,
      "step": 1490
    },
    {
      "epoch": 1.6631900987345292,
      "grad_norm": 0.15202811145565842,
      "learning_rate": 1.6637655993725598e-05,
      "loss": 0.6745,
      "step": 1495
    },
    {
      "epoch": 1.668752607425949,
      "grad_norm": 0.14529589529297973,
      "learning_rate": 1.6104719592169902e-05,
      "loss": 0.6415,
      "step": 1500
    },
    {
      "epoch": 1.674315116117369,
      "grad_norm": 0.16206187759632693,
      "learning_rate": 1.5579709867430514e-05,
      "loss": 0.6757,
      "step": 1505
    },
    {
      "epoch": 1.6798776248087888,
      "grad_norm": 0.1689334880075168,
      "learning_rate": 1.5062676423995247e-05,
      "loss": 0.6648,
      "step": 1510
    },
    {
      "epoch": 1.6854401335002085,
      "grad_norm": 0.17002942586162523,
      "learning_rate": 1.4553668112729025e-05,
      "loss": 0.6593,
      "step": 1515
    },
    {
      "epoch": 1.6910026421916284,
      "grad_norm": 0.15390481859714705,
      "learning_rate": 1.4052733026258281e-05,
      "loss": 0.6337,
      "step": 1520
    },
    {
      "epoch": 1.6965651508830484,
      "grad_norm": 0.16322817116461236,
      "learning_rate": 1.3559918494427015e-05,
      "loss": 0.6671,
      "step": 1525
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 0.17381037300710486,
      "learning_rate": 1.3075271079825036e-05,
      "loss": 0.6452,
      "step": 1530
    },
    {
      "epoch": 1.7076901682658878,
      "grad_norm": 0.14385216586204455,
      "learning_rate": 1.2598836573388383e-05,
      "loss": 0.6517,
      "step": 1535
    },
    {
      "epoch": 1.7132526769573078,
      "grad_norm": 0.13695810287509047,
      "learning_rate": 1.2130659990073146e-05,
      "loss": 0.6115,
      "step": 1540
    },
    {
      "epoch": 1.7188151856487277,
      "grad_norm": 0.15619086164642515,
      "learning_rate": 1.1670785564601972e-05,
      "loss": 0.6592,
      "step": 1545
    },
    {
      "epoch": 1.7243776943401474,
      "grad_norm": 0.1359615918791439,
      "learning_rate": 1.1219256747285045e-05,
      "loss": 0.6489,
      "step": 1550
    },
    {
      "epoch": 1.7299402030315671,
      "grad_norm": 0.1530561734129938,
      "learning_rate": 1.0776116199914343e-05,
      "loss": 0.6341,
      "step": 1555
    },
    {
      "epoch": 1.735502711722987,
      "grad_norm": 0.1550580447696997,
      "learning_rate": 1.0341405791733183e-05,
      "loss": 0.679,
      "step": 1560
    },
    {
      "epoch": 1.741065220414407,
      "grad_norm": 0.15343391714899443,
      "learning_rate": 9.915166595480018e-06,
      "loss": 0.6174,
      "step": 1565
    },
    {
      "epoch": 1.7466277291058268,
      "grad_norm": 0.14886169752976763,
      "learning_rate": 9.49743888350798e-06,
      "loss": 0.658,
      "step": 1570
    },
    {
      "epoch": 1.7521902377972465,
      "grad_norm": 0.16009066506717334,
      "learning_rate": 9.088262123979652e-06,
      "loss": 0.6547,
      "step": 1575
    },
    {
      "epoch": 1.7577527464886664,
      "grad_norm": 0.1527884120085583,
      "learning_rate": 8.687674977138116e-06,
      "loss": 0.6355,
      "step": 1580
    },
    {
      "epoch": 1.7633152551800864,
      "grad_norm": 0.15622894390259232,
      "learning_rate": 8.295715291654205e-06,
      "loss": 0.6415,
      "step": 1585
    },
    {
      "epoch": 1.768877763871506,
      "grad_norm": 0.13821573876875842,
      "learning_rate": 7.912420101050367e-06,
      "loss": 0.6386,
      "step": 1590
    },
    {
      "epoch": 1.7744402725629258,
      "grad_norm": 0.1605607168007031,
      "learning_rate": 7.537825620201699e-06,
      "loss": 0.6395,
      "step": 1595
    },
    {
      "epoch": 1.7800027812543457,
      "grad_norm": 0.14785735762140897,
      "learning_rate": 7.171967241914224e-06,
      "loss": 0.632,
      "step": 1600
    },
    {
      "epoch": 1.7800027812543457,
      "eval_loss": 0.6654813289642334,
      "eval_runtime": 38.0745,
      "eval_samples_per_second": 10.69,
      "eval_steps_per_second": 0.683,
      "step": 1600
    },
    {
      "epoch": 1.7855652899457657,
      "grad_norm": 0.15930848069616485,
      "learning_rate": 6.814879533580898e-06,
      "loss": 0.6298,
      "step": 1605
    },
    {
      "epoch": 1.7911277986371854,
      "grad_norm": 0.16408233749219603,
      "learning_rate": 6.4665962339156005e-06,
      "loss": 0.6383,
      "step": 1610
    },
    {
      "epoch": 1.7966903073286051,
      "grad_norm": 0.1507405199602565,
      "learning_rate": 6.127150249765335e-06,
      "loss": 0.6538,
      "step": 1615
    },
    {
      "epoch": 1.802252816020025,
      "grad_norm": 0.15449896745701766,
      "learning_rate": 5.7965736530010916e-06,
      "loss": 0.6443,
      "step": 1620
    },
    {
      "epoch": 1.807815324711445,
      "grad_norm": 0.15430381806456947,
      "learning_rate": 5.474897677487711e-06,
      "loss": 0.6714,
      "step": 1625
    },
    {
      "epoch": 1.8133778334028647,
      "grad_norm": 0.1522219198315468,
      "learning_rate": 5.162152716132662e-06,
      "loss": 0.6462,
      "step": 1630
    },
    {
      "epoch": 1.8189403420942845,
      "grad_norm": 0.14950817969442623,
      "learning_rate": 4.858368318014572e-06,
      "loss": 0.6309,
      "step": 1635
    },
    {
      "epoch": 1.8245028507857044,
      "grad_norm": 0.16343103461857358,
      "learning_rate": 4.563573185591219e-06,
      "loss": 0.6229,
      "step": 1640
    },
    {
      "epoch": 1.8300653594771243,
      "grad_norm": 0.16046392285596128,
      "learning_rate": 4.2777951719877415e-06,
      "loss": 0.6526,
      "step": 1645
    },
    {
      "epoch": 1.835627868168544,
      "grad_norm": 0.16358481948661036,
      "learning_rate": 4.0010612783648925e-06,
      "loss": 0.6407,
      "step": 1650
    },
    {
      "epoch": 1.8411903768599638,
      "grad_norm": 0.15364511127769814,
      "learning_rate": 3.7333976513680093e-06,
      "loss": 0.6375,
      "step": 1655
    },
    {
      "epoch": 1.8467528855513837,
      "grad_norm": 0.1582298293905816,
      "learning_rate": 3.4748295806564356e-06,
      "loss": 0.6486,
      "step": 1660
    },
    {
      "epoch": 1.8523153942428037,
      "grad_norm": 0.1626273297442105,
      "learning_rate": 3.2253814965142683e-06,
      "loss": 0.6682,
      "step": 1665
    },
    {
      "epoch": 1.8578779029342232,
      "grad_norm": 0.15566169967079257,
      "learning_rate": 2.9850769675419774e-06,
      "loss": 0.6531,
      "step": 1670
    },
    {
      "epoch": 1.8634404116256431,
      "grad_norm": 0.1785306629362279,
      "learning_rate": 2.7539386984296147e-06,
      "loss": 0.6406,
      "step": 1675
    },
    {
      "epoch": 1.869002920317063,
      "grad_norm": 0.14973888951794095,
      "learning_rate": 2.5319885278115906e-06,
      "loss": 0.6441,
      "step": 1680
    },
    {
      "epoch": 1.8745654290084828,
      "grad_norm": 0.1493522152423315,
      "learning_rate": 2.3192474262033638e-06,
      "loss": 0.6377,
      "step": 1685
    },
    {
      "epoch": 1.8801279376999025,
      "grad_norm": 0.1611037940241023,
      "learning_rate": 2.115735494019966e-06,
      "loss": 0.6785,
      "step": 1690
    },
    {
      "epoch": 1.8856904463913224,
      "grad_norm": 0.15767721827989367,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.667,
      "step": 1695
    },
    {
      "epoch": 1.8912529550827424,
      "grad_norm": 0.15987860636699017,
      "learning_rate": 1.7364751777736332e-06,
      "loss": 0.6374,
      "step": 1700
    },
    {
      "epoch": 1.896815463774162,
      "grad_norm": 0.14274620551242612,
      "learning_rate": 1.5607626273588138e-06,
      "loss": 0.6305,
      "step": 1705
    },
    {
      "epoch": 1.9023779724655818,
      "grad_norm": 0.1539956730318316,
      "learning_rate": 1.394350910279385e-06,
      "loss": 0.6446,
      "step": 1710
    },
    {
      "epoch": 1.9079404811570018,
      "grad_norm": 0.16255063308547452,
      "learning_rate": 1.2372557496116877e-06,
      "loss": 0.6577,
      "step": 1715
    },
    {
      "epoch": 1.9135029898484217,
      "grad_norm": 0.1457148304946188,
      "learning_rate": 1.089491988176017e-06,
      "loss": 0.6671,
      "step": 1720
    },
    {
      "epoch": 1.9190654985398414,
      "grad_norm": 0.16991284681377727,
      "learning_rate": 9.510735871341103e-07,
      "loss": 0.6693,
      "step": 1725
    },
    {
      "epoch": 1.9246280072312612,
      "grad_norm": 0.15748923168566117,
      "learning_rate": 8.220136246701926e-07,
      "loss": 0.6491,
      "step": 1730
    },
    {
      "epoch": 1.930190515922681,
      "grad_norm": 0.15744123180048702,
      "learning_rate": 7.023242947552078e-07,
      "loss": 0.6366,
      "step": 1735
    },
    {
      "epoch": 1.935753024614101,
      "grad_norm": 0.15109132227982583,
      "learning_rate": 5.920169059947411e-07,
      "loss": 0.6553,
      "step": 1740
    },
    {
      "epoch": 1.9413155333055208,
      "grad_norm": 0.16542652334128852,
      "learning_rate": 4.911018805605406e-07,
      "loss": 0.6395,
      "step": 1745
    },
    {
      "epoch": 1.9468780419969405,
      "grad_norm": 0.15918345337184334,
      "learning_rate": 3.9958875320580404e-07,
      "loss": 0.6502,
      "step": 1750
    },
    {
      "epoch": 1.9524405506883604,
      "grad_norm": 0.17686582944306006,
      "learning_rate": 3.1748617036427843e-07,
      "loss": 0.6586,
      "step": 1755
    },
    {
      "epoch": 1.9580030593797804,
      "grad_norm": 0.1426907741483869,
      "learning_rate": 2.448018893333681e-07,
      "loss": 0.6345,
      "step": 1760
    },
    {
      "epoch": 1.9635655680712,
      "grad_norm": 0.14223763889913488,
      "learning_rate": 1.815427775411549e-07,
      "loss": 0.6296,
      "step": 1765
    },
    {
      "epoch": 1.9691280767626198,
      "grad_norm": 0.14802968415791257,
      "learning_rate": 1.277148118975835e-07,
      "loss": 0.6167,
      "step": 1770
    },
    {
      "epoch": 1.9746905854540397,
      "grad_norm": 0.16664999019696625,
      "learning_rate": 8.332307822971342e-08,
      "loss": 0.6522,
      "step": 1775
    },
    {
      "epoch": 1.9802530941454597,
      "grad_norm": 0.15531644850942158,
      "learning_rate": 4.837177080119215e-08,
      "loss": 0.6587,
      "step": 1780
    },
    {
      "epoch": 1.9858156028368794,
      "grad_norm": 0.17774727599107124,
      "learning_rate": 2.286419191601663e-08,
      "loss": 0.6634,
      "step": 1785
    },
    {
      "epoch": 1.9913781115282991,
      "grad_norm": 0.1591360139721982,
      "learning_rate": 6.8027516064606e-09,
      "loss": 0.6466,
      "step": 1790
    },
    {
      "epoch": 1.996940620219719,
      "grad_norm": 0.1816483541352177,
      "learning_rate": 1.8896740540119696e-10,
      "loss": 0.6307,
      "step": 1795
    },
    {
      "epoch": 1.998053121958003,
      "step": 1796,
      "total_flos": 7795310658584576.0,
      "train_loss": 0.6907267017260957,
      "train_runtime": 37673.7111,
      "train_samples_per_second": 3.054,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 5,
  "max_steps": 1796,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 7795310658584576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}