{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1045,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009569377990430622,
      "grad_norm": 948.5667114257812,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 46.4048,
      "step": 1
    },
    {
      "epoch": 0.004784688995215311,
      "grad_norm": 579.7166137695312,
      "learning_rate": 1.4285714285714284e-05,
      "loss": 42.2625,
      "step": 5
    },
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 96.71955871582031,
      "learning_rate": 2.8571428571428567e-05,
      "loss": 24.8784,
      "step": 10
    },
    {
      "epoch": 0.014354066985645933,
      "grad_norm": 14.768364906311035,
      "learning_rate": 4.285714285714285e-05,
      "loss": 20.4002,
      "step": 15
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 12.786796569824219,
      "learning_rate": 5.7142857142857135e-05,
      "loss": 18.6753,
      "step": 20
    },
    {
      "epoch": 0.023923444976076555,
      "grad_norm": 46.72217559814453,
      "learning_rate": 7.142857142857142e-05,
      "loss": 15.9881,
      "step": 25
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 16.096284866333008,
      "learning_rate": 8.57142857142857e-05,
      "loss": 7.4899,
      "step": 30
    },
    {
      "epoch": 0.03349282296650718,
      "grad_norm": 6.774743556976318,
      "learning_rate": 9.999999999999999e-05,
      "loss": 2.28,
      "step": 35
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 25.32003402709961,
      "learning_rate": 0.00011428571428571427,
      "loss": 1.816,
      "step": 40
    },
    {
      "epoch": 0.0430622009569378,
      "grad_norm": 4.912317276000977,
      "learning_rate": 0.00012857142857142855,
      "loss": 1.6463,
      "step": 45
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 3.605388879776001,
      "learning_rate": 0.00014285714285714284,
      "loss": 1.5122,
      "step": 50
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 5.295993328094482,
      "learning_rate": 0.00015714285714285713,
      "loss": 1.419,
      "step": 55
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 9.990426063537598,
      "learning_rate": 0.0001714285714285714,
      "loss": 1.3221,
      "step": 60
    },
    {
      "epoch": 0.06220095693779904,
      "grad_norm": 28.818571090698242,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.2352,
      "step": 65
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 5.248025417327881,
      "learning_rate": 0.00019999999999999998,
      "loss": 1.2013,
      "step": 70
    },
    {
      "epoch": 0.07177033492822966,
      "grad_norm": 4.098865509033203,
      "learning_rate": 0.00021428571428571427,
      "loss": 1.1641,
      "step": 75
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 1.8723022937774658,
      "learning_rate": 0.00022857142857142854,
      "loss": 1.1404,
      "step": 80
    },
    {
      "epoch": 0.08133971291866028,
      "grad_norm": 20.416040420532227,
      "learning_rate": 0.00024285714285714283,
      "loss": 1.1758,
      "step": 85
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 2.548046112060547,
      "learning_rate": 0.0002571428571428571,
      "loss": 1.1864,
      "step": 90
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 10.036776542663574,
      "learning_rate": 0.0002714285714285714,
      "loss": 1.1193,
      "step": 95
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 7.473161697387695,
      "learning_rate": 0.0002857142857142857,
      "loss": 1.1753,
      "step": 100
    },
    {
      "epoch": 0.10047846889952153,
      "grad_norm": 1.7201554775238037,
      "learning_rate": 0.0003,
      "loss": 1.1511,
      "step": 105
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 22.742843627929688,
      "learning_rate": 0.00029997905717787856,
      "loss": 1.1194,
      "step": 110
    },
    {
      "epoch": 0.11004784688995216,
      "grad_norm": 4.5689191818237305,
      "learning_rate": 0.00029991623455953814,
      "loss": 1.1401,
      "step": 115
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 4.430986404418945,
      "learning_rate": 0.00029981154968741785,
      "loss": 1.1312,
      "step": 120
    },
    {
      "epoch": 0.11961722488038277,
      "grad_norm": 9.391127586364746,
      "learning_rate": 0.000299665031793473,
      "loss": 1.0676,
      "step": 125
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 10.183479309082031,
      "learning_rate": 0.0002994767217910127,
      "loss": 1.1184,
      "step": 130
    },
    {
      "epoch": 0.1291866028708134,
      "grad_norm": 1.511924147605896,
      "learning_rate": 0.00029924667226327557,
      "loss": 1.0999,
      "step": 135
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 8.494267463684082,
      "learning_rate": 0.0002989749474487461,
      "loss": 1.0913,
      "step": 140
    },
    {
      "epoch": 0.13875598086124402,
      "grad_norm": 2.4349634647369385,
      "learning_rate": 0.000298661623223217,
      "loss": 1.0802,
      "step": 145
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 1.914871096611023,
      "learning_rate": 0.0002983067870786019,
      "loss": 1.0589,
      "step": 150
    },
    {
      "epoch": 0.14832535885167464,
      "grad_norm": 8.084524154663086,
      "learning_rate": 0.00029791053809850426,
      "loss": 1.0661,
      "step": 155
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 15.332684516906738,
      "learning_rate": 0.0002974729869305495,
      "loss": 1.0688,
      "step": 160
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 30.3629207611084,
      "learning_rate": 0.000296994255755488,
      "loss": 1.0531,
      "step": 165
    },
    {
      "epoch": 0.16267942583732056,
      "grad_norm": 6.318498611450195,
      "learning_rate": 0.0002964744782530777,
      "loss": 1.0664,
      "step": 170
    },
    {
      "epoch": 0.1674641148325359,
      "grad_norm": 7.628419399261475,
      "learning_rate": 0.0002959137995647556,
      "loss": 1.1012,
      "step": 175
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 6.398703098297119,
      "learning_rate": 0.0002953123762531088,
      "loss": 1.1012,
      "step": 180
    },
    {
      "epoch": 0.17703349282296652,
      "grad_norm": 1.5758147239685059,
      "learning_rate": 0.00029467037625815644,
      "loss": 1.0655,
      "step": 185
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.354144811630249,
      "learning_rate": 0.0002939879788504546,
      "loss": 1.0405,
      "step": 190
    },
    {
      "epoch": 0.18660287081339713,
      "grad_norm": 7.777205467224121,
      "learning_rate": 0.00029326537458103683,
      "loss": 1.0575,
      "step": 195
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 3.233966588973999,
      "learning_rate": 0.0002925027652282056,
      "loss": 1.0519,
      "step": 200
    },
    {
      "epoch": 0.19617224880382775,
      "grad_norm": 5.466601848602295,
      "learning_rate": 0.00029170036374118777,
      "loss": 1.0377,
      "step": 205
    },
    {
      "epoch": 0.20095693779904306,
      "grad_norm": 2.6383893489837646,
      "learning_rate": 0.0002908583941806717,
      "loss": 1.0435,
      "step": 210
    },
    {
      "epoch": 0.20574162679425836,
      "grad_norm": 1.6238977909088135,
      "learning_rate": 0.00028997709165624034,
      "loss": 1.0098,
      "step": 215
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 4.616154193878174,
      "learning_rate": 0.0002890567022607206,
      "loss": 1.007,
      "step": 220
    },
    {
      "epoch": 0.215311004784689,
      "grad_norm": 3.3014893531799316,
      "learning_rate": 0.0002880974830014643,
      "loss": 1.0311,
      "step": 225
    },
    {
      "epoch": 0.22009569377990432,
      "grad_norm": 1.7747435569763184,
      "learning_rate": 0.0002870997017285824,
      "loss": 0.9898,
      "step": 230
    },
    {
      "epoch": 0.22488038277511962,
      "grad_norm": 2.502115488052368,
      "learning_rate": 0.0002860636370601511,
      "loss": 1.0031,
      "step": 235
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 2.33097767829895,
      "learning_rate": 0.00028498957830441117,
      "loss": 1.0175,
      "step": 240
    },
    {
      "epoch": 0.23444976076555024,
      "grad_norm": 2.667079448699951,
      "learning_rate": 0.00028387782537898215,
      "loss": 1.0102,
      "step": 245
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 5.493870735168457,
      "learning_rate": 0.0002827286887271143,
      "loss": 0.9815,
      "step": 250
    },
    {
      "epoch": 0.24401913875598086,
      "grad_norm": 1.950860619544983,
      "learning_rate": 0.0002815424892310007,
      "loss": 0.9865,
      "step": 255
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 1.8500947952270508,
      "learning_rate": 0.00028031955812217544,
      "loss": 0.9819,
      "step": 260
    },
    {
      "epoch": 0.2535885167464115,
      "grad_norm": 4.860908508300781,
      "learning_rate": 0.0002790602368890209,
      "loss": 0.9728,
      "step": 265
    },
    {
      "epoch": 0.2583732057416268,
      "grad_norm": 2.0686490535736084,
      "learning_rate": 0.0002777648771814114,
      "loss": 1.02,
      "step": 270
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 3.445263624191284,
      "learning_rate": 0.00027643384071251954,
      "loss": 1.0279,
      "step": 275
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 1.4115147590637207,
      "learning_rate": 0.000275067499157812,
      "loss": 0.9813,
      "step": 280
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.2224127054214478,
      "learning_rate": 0.00027366623405126404,
      "loss": 0.9903,
      "step": 285
    },
    {
      "epoch": 0.27751196172248804,
      "grad_norm": 1.8986269235610962,
      "learning_rate": 0.0002722304366788205,
      "loss": 1.0094,
      "step": 290
    },
    {
      "epoch": 0.2822966507177033,
      "grad_norm": 4.729682445526123,
      "learning_rate": 0.0002707605079691344,
      "loss": 1.0046,
      "step": 295
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 2.3022851943969727,
      "learning_rate": 0.0002692568583816124,
      "loss": 1.0305,
      "step": 300
    },
    {
      "epoch": 0.291866028708134,
      "grad_norm": 2.677311658859253,
      "learning_rate": 0.0002677199077917991,
      "loss": 1.0308,
      "step": 305
    },
    {
      "epoch": 0.2966507177033493,
      "grad_norm": 1.3505252599716187,
      "learning_rate": 0.000266150085374132,
      "loss": 0.9911,
      "step": 310
    },
    {
      "epoch": 0.3014354066985646,
      "grad_norm": 1.311340093612671,
      "learning_rate": 0.00026454782948209983,
      "loss": 0.9897,
      "step": 315
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 1.3043484687805176,
      "learning_rate": 0.00026291358752583764,
      "loss": 0.9659,
      "step": 320
    },
    {
      "epoch": 0.31100478468899523,
      "grad_norm": 1.1022688150405884,
      "learning_rate": 0.0002612478158471936,
      "loss": 0.9852,
      "step": 325
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.8880759477615356,
      "learning_rate": 0.0002595509795923004,
      "loss": 0.9707,
      "step": 330
    },
    {
      "epoch": 0.32057416267942584,
      "grad_norm": 4.946929454803467,
      "learning_rate": 0.0002578235525816894,
      "loss": 1.0037,
      "step": 335
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 1.5874648094177246,
      "learning_rate": 0.00025606601717798207,
      "loss": 1.013,
      "step": 340
    },
    {
      "epoch": 0.33014354066985646,
      "grad_norm": 1.1188175678253174,
      "learning_rate": 0.0002542788641511963,
      "loss": 0.9814,
      "step": 345
    },
    {
      "epoch": 0.3349282296650718,
      "grad_norm": 1.3674702644348145,
      "learning_rate": 0.0002524625925417046,
      "loss": 0.9924,
      "step": 350
    },
    {
      "epoch": 0.3397129186602871,
      "grad_norm": 1.3748054504394531,
      "learning_rate": 0.0002506177095208835,
      "loss": 0.9952,
      "step": 355
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 1.4951032400131226,
      "learning_rate": 0.00024874473024949224,
      "loss": 0.9859,
      "step": 360
    },
    {
      "epoch": 0.3492822966507177,
      "grad_norm": 1.5338605642318726,
      "learning_rate": 0.0002468441777338203,
      "loss": 0.9986,
      "step": 365
    },
    {
      "epoch": 0.35406698564593303,
      "grad_norm": 2.292693614959717,
      "learning_rate": 0.00024491658267964474,
      "loss": 0.9815,
      "step": 370
    },
    {
      "epoch": 0.3588516746411483,
      "grad_norm": 3.6766607761383057,
      "learning_rate": 0.00024296248334403672,
      "loss": 0.9696,
      "step": 375
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.8351837396621704,
      "learning_rate": 0.00024098242538506007,
      "loss": 0.9806,
      "step": 380
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 3.7850887775421143,
      "learning_rate": 0.00023897696170940326,
      "loss": 0.9922,
      "step": 385
    },
    {
      "epoch": 0.37320574162679426,
      "grad_norm": 1.6278636455535889,
      "learning_rate": 0.0002369466523179866,
      "loss": 0.9524,
      "step": 390
    },
    {
      "epoch": 0.37799043062200954,
      "grad_norm": 2.634073495864868,
      "learning_rate": 0.0002348920641495893,
      "loss": 0.9721,
      "step": 395
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 1.0519402027130127,
      "learning_rate": 0.0002328137709225385,
      "loss": 0.9433,
      "step": 400
    },
    {
      "epoch": 0.3875598086124402,
      "grad_norm": 1.6269092559814453,
      "learning_rate": 0.00023071235297450588,
      "loss": 0.965,
      "step": 405
    },
    {
      "epoch": 0.3923444976076555,
      "grad_norm": 1.0608420372009277,
      "learning_rate": 0.0002285883971004553,
      "loss": 0.9458,
      "step": 410
    },
    {
      "epoch": 0.39712918660287083,
      "grad_norm": 1.1753120422363281,
      "learning_rate": 0.00022644249638878762,
      "loss": 0.9708,
      "step": 415
    },
    {
      "epoch": 0.4019138755980861,
      "grad_norm": 1.1925132274627686,
      "learning_rate": 0.000224275250055728,
      "loss": 0.9419,
      "step": 420
    },
    {
      "epoch": 0.40669856459330145,
      "grad_norm": 2.7282474040985107,
      "learning_rate": 0.00022208726327800255,
      "loss": 0.9776,
      "step": 425
    },
    {
      "epoch": 0.41148325358851673,
      "grad_norm": 1.2128546237945557,
      "learning_rate": 0.0002198791470238497,
      "loss": 0.9726,
      "step": 430
    },
    {
      "epoch": 0.41626794258373206,
      "grad_norm": 1.216680884361267,
      "learning_rate": 0.00021765151788241525,
      "loss": 0.965,
      "step": 435
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.2095612287521362,
      "learning_rate": 0.0002154049978915774,
      "loss": 0.9734,
      "step": 440
    },
    {
      "epoch": 0.4258373205741627,
      "grad_norm": 2.2863378524780273,
      "learning_rate": 0.00021314021436425024,
      "loss": 0.9668,
      "step": 445
    },
    {
      "epoch": 0.430622009569378,
      "grad_norm": 1.6475805044174194,
      "learning_rate": 0.00021085779971321454,
      "loss": 0.953,
      "step": 450
    },
    {
      "epoch": 0.4354066985645933,
      "grad_norm": 2.581031560897827,
      "learning_rate": 0.0002085583912745242,
      "loss": 0.9481,
      "step": 455
    },
    {
      "epoch": 0.44019138755980863,
      "grad_norm": 1.6886945962905884,
      "learning_rate": 0.00020624263112953815,
      "loss": 0.9521,
      "step": 460
    },
    {
      "epoch": 0.4449760765550239,
      "grad_norm": 1.6784495115280151,
      "learning_rate": 0.0002039111659256269,
      "loss": 0.9448,
      "step": 465
    },
    {
      "epoch": 0.44976076555023925,
      "grad_norm": 1.741603970527649,
      "learning_rate": 0.00020156464669560448,
      "loss": 0.9396,
      "step": 470
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.4577537775039673,
      "learning_rate": 0.00019920372867593533,
      "loss": 0.9381,
      "step": 475
    },
    {
      "epoch": 0.45933014354066987,
      "grad_norm": 1.2143363952636719,
      "learning_rate": 0.00019682907112376796,
      "loss": 0.942,
      "step": 480
    },
    {
      "epoch": 0.46411483253588515,
      "grad_norm": 1.133268117904663,
      "learning_rate": 0.0001944413371328451,
      "loss": 0.9307,
      "step": 485
    },
    {
      "epoch": 0.4688995215311005,
      "grad_norm": 1.3096511363983154,
      "learning_rate": 0.0001920411934483434,
      "loss": 0.9489,
      "step": 490
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 1.1326684951782227,
      "learning_rate": 0.00018962931028069293,
      "loss": 0.9481,
      "step": 495
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 1.435521125793457,
      "learning_rate": 0.00018720636111842898,
      "loss": 0.941,
      "step": 500
    },
    {
      "epoch": 0.48325358851674644,
      "grad_norm": 1.5249536037445068,
      "learning_rate": 0.00018477302254012924,
      "loss": 0.9466,
      "step": 505
    },
    {
      "epoch": 0.4880382775119617,
      "grad_norm": 1.5078822374343872,
      "learning_rate": 0.000182329974025487,
      "loss": 0.9407,
      "step": 510
    },
    {
      "epoch": 0.49282296650717705,
      "grad_norm": 1.1270455121994019,
      "learning_rate": 0.0001798778977655754,
      "loss": 0.9342,
      "step": 515
    },
    {
      "epoch": 0.49760765550239233,
      "grad_norm": 1.8892922401428223,
      "learning_rate": 0.00017741747847235353,
      "loss": 0.9215,
      "step": 520
    },
    {
      "epoch": 0.5023923444976076,
      "grad_norm": 1.1376285552978516,
      "learning_rate": 0.0001749494031874695,
      "loss": 0.941,
      "step": 525
    },
    {
      "epoch": 0.507177033492823,
      "grad_norm": 1.3463551998138428,
      "learning_rate": 0.0001724743610904122,
      "loss": 0.9494,
      "step": 530
    },
    {
      "epoch": 0.5119617224880383,
      "grad_norm": 2.9610071182250977,
      "learning_rate": 0.00016999304330606683,
      "loss": 0.9342,
      "step": 535
    },
    {
      "epoch": 0.5167464114832536,
      "grad_norm": 1.1553057432174683,
      "learning_rate": 0.00016750614271172643,
      "loss": 0.9421,
      "step": 540
    },
    {
      "epoch": 0.5215311004784688,
      "grad_norm": 1.025996446609497,
      "learning_rate": 0.00016501435374361475,
      "loss": 0.9165,
      "step": 545
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.1247053146362305,
      "learning_rate": 0.00016251837220297347,
      "loss": 0.9382,
      "step": 550
    },
    {
      "epoch": 0.5311004784688995,
      "grad_norm": 1.027742624282837,
      "learning_rate": 0.00016001889506176824,
      "loss": 0.9461,
      "step": 555
    },
    {
      "epoch": 0.5358851674641149,
      "grad_norm": 1.2423522472381592,
      "learning_rate": 0.00015751662026806788,
      "loss": 0.9411,
      "step": 560
    },
    {
      "epoch": 0.5406698564593302,
      "grad_norm": 1.5147805213928223,
      "learning_rate": 0.00015501224655115118,
      "loss": 0.9334,
      "step": 565
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.2580386400222778,
      "learning_rate": 0.00015250647322639512,
      "loss": 0.9258,
      "step": 570
    },
    {
      "epoch": 0.5502392344497608,
      "grad_norm": 1.1148898601531982,
      "learning_rate": 0.00015,
      "loss": 0.92,
      "step": 575
    },
    {
      "epoch": 0.5550239234449761,
      "grad_norm": 1.6557159423828125,
      "learning_rate": 0.00014749352677360483,
      "loss": 0.9124,
      "step": 580
    },
    {
      "epoch": 0.5598086124401914,
      "grad_norm": 1.3142054080963135,
      "learning_rate": 0.00014498775344884884,
      "loss": 0.9292,
      "step": 585
    },
    {
      "epoch": 0.5645933014354066,
      "grad_norm": 1.3109759092330933,
      "learning_rate": 0.00014248337973193212,
      "loss": 0.9075,
      "step": 590
    },
    {
      "epoch": 0.569377990430622,
      "grad_norm": 1.8519434928894043,
      "learning_rate": 0.00013998110493823176,
      "loss": 0.9334,
      "step": 595
    },
    {
      "epoch": 0.5741626794258373,
      "grad_norm": 1.467532992362976,
      "learning_rate": 0.00013748162779702653,
      "loss": 0.9038,
      "step": 600
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 1.2827484607696533,
      "learning_rate": 0.00013498564625638522,
      "loss": 0.9209,
      "step": 605
    },
    {
      "epoch": 0.583732057416268,
      "grad_norm": 2.0187387466430664,
      "learning_rate": 0.00013249385728827357,
      "loss": 0.909,
      "step": 610
    },
    {
      "epoch": 0.5885167464114832,
      "grad_norm": 1.0019465684890747,
      "learning_rate": 0.0001300069566939332,
      "loss": 0.9324,
      "step": 615
    },
    {
      "epoch": 0.5933014354066986,
      "grad_norm": 1.1702934503555298,
      "learning_rate": 0.00012752563890958778,
      "loss": 0.8818,
      "step": 620
    },
    {
      "epoch": 0.5980861244019139,
      "grad_norm": 1.1036059856414795,
      "learning_rate": 0.0001250505968125305,
      "loss": 0.9082,
      "step": 625
    },
    {
      "epoch": 0.6028708133971292,
      "grad_norm": 1.3649473190307617,
      "learning_rate": 0.00012258252152764647,
      "loss": 0.9077,
      "step": 630
    },
    {
      "epoch": 0.6076555023923444,
      "grad_norm": 1.2819594144821167,
      "learning_rate": 0.0001201221022344246,
      "loss": 0.899,
      "step": 635
    },
    {
      "epoch": 0.6124401913875598,
      "grad_norm": 1.1259446144104004,
      "learning_rate": 0.00011767002597451296,
      "loss": 0.8888,
      "step": 640
    },
    {
      "epoch": 0.6172248803827751,
      "grad_norm": 1.0908528566360474,
      "learning_rate": 0.00011522697745987075,
      "loss": 0.8954,
      "step": 645
    },
    {
      "epoch": 0.6220095693779905,
      "grad_norm": 1.0630327463150024,
      "learning_rate": 0.000112793638881571,
      "loss": 0.8974,
      "step": 650
    },
    {
      "epoch": 0.6267942583732058,
      "grad_norm": 1.2224838733673096,
      "learning_rate": 0.00011037068971930709,
      "loss": 0.8945,
      "step": 655
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.2856760025024414,
      "learning_rate": 0.00010795880655165656,
      "loss": 0.8994,
      "step": 660
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.0856343507766724,
      "learning_rate": 0.0001055586628671549,
      "loss": 0.8883,
      "step": 665
    },
    {
      "epoch": 0.6411483253588517,
      "grad_norm": 1.063491940498352,
      "learning_rate": 0.00010317092887623205,
      "loss": 0.8866,
      "step": 670
    },
    {
      "epoch": 0.645933014354067,
      "grad_norm": 1.2210334539413452,
      "learning_rate": 0.00010079627132406462,
      "loss": 0.8902,
      "step": 675
    },
    {
      "epoch": 0.6507177033492823,
      "grad_norm": 0.9613766074180603,
      "learning_rate": 9.843535330439555e-05,
      "loss": 0.8748,
      "step": 680
    },
    {
      "epoch": 0.6555023923444976,
      "grad_norm": 0.9286556839942932,
      "learning_rate": 9.608883407437309e-05,
      "loss": 0.8824,
      "step": 685
    },
    {
      "epoch": 0.6602870813397129,
      "grad_norm": 1.13881254196167,
      "learning_rate": 9.375736887046185e-05,
      "loss": 0.8779,
      "step": 690
    },
    {
      "epoch": 0.6650717703349283,
      "grad_norm": 1.128664255142212,
      "learning_rate": 9.144160872547578e-05,
      "loss": 0.8623,
      "step": 695
    },
    {
      "epoch": 0.6698564593301436,
      "grad_norm": 1.3374972343444824,
      "learning_rate": 8.914220028678546e-05,
      "loss": 0.8831,
      "step": 700
    },
    {
      "epoch": 0.6746411483253588,
      "grad_norm": 1.5959270000457764,
      "learning_rate": 8.685978563574976e-05,
      "loss": 0.8956,
      "step": 705
    },
    {
      "epoch": 0.6794258373205742,
      "grad_norm": 1.582465410232544,
      "learning_rate": 8.459500210842261e-05,
      "loss": 0.8804,
      "step": 710
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 1.3153728246688843,
      "learning_rate": 8.23484821175847e-05,
      "loss": 0.8776,
      "step": 715
    },
    {
      "epoch": 0.6889952153110048,
      "grad_norm": 1.1769953966140747,
      "learning_rate": 8.012085297615027e-05,
      "loss": 0.8777,
      "step": 720
    },
    {
      "epoch": 0.69377990430622,
      "grad_norm": 1.1776398420333862,
      "learning_rate": 7.791273672199742e-05,
      "loss": 0.8866,
      "step": 725
    },
    {
      "epoch": 0.6985645933014354,
      "grad_norm": 1.0515143871307373,
      "learning_rate": 7.572474994427197e-05,
      "loss": 0.8887,
      "step": 730
    },
    {
      "epoch": 0.7033492822966507,
      "grad_norm": 1.0670396089553833,
      "learning_rate": 7.355750361121237e-05,
      "loss": 0.8631,
      "step": 735
    },
    {
      "epoch": 0.7081339712918661,
      "grad_norm": 1.3679234981536865,
      "learning_rate": 7.141160289954471e-05,
      "loss": 0.8701,
      "step": 740
    },
    {
      "epoch": 0.7129186602870813,
      "grad_norm": 1.0791184902191162,
      "learning_rate": 6.92876470254941e-05,
      "loss": 0.879,
      "step": 745
    },
    {
      "epoch": 0.7177033492822966,
      "grad_norm": 1.0610390901565552,
      "learning_rate": 6.718622907746151e-05,
      "loss": 0.8617,
      "step": 750
    },
    {
      "epoch": 0.722488038277512,
      "grad_norm": 1.062545657157898,
      "learning_rate": 6.51079358504107e-05,
      "loss": 0.8743,
      "step": 755
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.8820713758468628,
      "learning_rate": 6.305334768201336e-05,
      "loss": 0.8553,
      "step": 760
    },
    {
      "epoch": 0.7320574162679426,
      "grad_norm": 0.9072192311286926,
      "learning_rate": 6.1023038290596715e-05,
      "loss": 0.8613,
      "step": 765
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1.0919402837753296,
      "learning_rate": 5.901757461493988e-05,
      "loss": 0.8679,
      "step": 770
    },
    {
      "epoch": 0.7416267942583732,
      "grad_norm": 1.0981807708740234,
      "learning_rate": 5.703751665596328e-05,
      "loss": 0.8665,
      "step": 775
    },
    {
      "epoch": 0.7464114832535885,
      "grad_norm": 1.0239495038986206,
      "learning_rate": 5.50834173203552e-05,
      "loss": 0.8819,
      "step": 780
    },
    {
      "epoch": 0.7511961722488039,
      "grad_norm": 1.0707833766937256,
      "learning_rate": 5.315582226617963e-05,
      "loss": 0.8571,
      "step": 785
    },
    {
      "epoch": 0.7559808612440191,
      "grad_norm": 1.0176221132278442,
      "learning_rate": 5.125526975050776e-05,
      "loss": 0.8718,
      "step": 790
    },
    {
      "epoch": 0.7607655502392344,
      "grad_norm": 0.9414092898368835,
      "learning_rate": 4.938229047911651e-05,
      "loss": 0.8547,
      "step": 795
    },
    {
      "epoch": 0.7655502392344498,
      "grad_norm": 0.8967716097831726,
      "learning_rate": 4.753740745829537e-05,
      "loss": 0.8385,
      "step": 800
    },
    {
      "epoch": 0.7703349282296651,
      "grad_norm": 1.160251498222351,
      "learning_rate": 4.5721135848803653e-05,
      "loss": 0.8471,
      "step": 805
    },
    {
      "epoch": 0.7751196172248804,
      "grad_norm": 0.9440346360206604,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 0.8526,
      "step": 810
    },
    {
      "epoch": 0.7799043062200957,
      "grad_norm": 0.9394163489341736,
      "learning_rate": 4.217644741831062e-05,
      "loss": 0.8661,
      "step": 815
    },
    {
      "epoch": 0.784688995215311,
      "grad_norm": 0.9960381388664246,
      "learning_rate": 4.044902040769963e-05,
      "loss": 0.8848,
      "step": 820
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.9392317533493042,
      "learning_rate": 3.875218415280636e-05,
      "loss": 0.8562,
      "step": 825
    },
    {
      "epoch": 0.7942583732057417,
      "grad_norm": 1.0181559324264526,
      "learning_rate": 3.708641247416229e-05,
      "loss": 0.854,
      "step": 830
    },
    {
      "epoch": 0.7990430622009569,
      "grad_norm": 1.1440843343734741,
      "learning_rate": 3.54521705179002e-05,
      "loss": 0.8597,
      "step": 835
    },
    {
      "epoch": 0.8038277511961722,
      "grad_norm": 1.0670745372772217,
      "learning_rate": 3.3849914625868004e-05,
      "loss": 0.8847,
      "step": 840
    },
    {
      "epoch": 0.8086124401913876,
      "grad_norm": 0.9774266481399536,
      "learning_rate": 3.228009220820085e-05,
      "loss": 0.8673,
      "step": 845
    },
    {
      "epoch": 0.8133971291866029,
      "grad_norm": 0.9691421389579773,
      "learning_rate": 3.074314161838754e-05,
      "loss": 0.8315,
      "step": 850
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.9607205986976624,
      "learning_rate": 2.923949203086557e-05,
      "loss": 0.862,
      "step": 855
    },
    {
      "epoch": 0.8229665071770335,
      "grad_norm": 1.0411772727966309,
      "learning_rate": 2.77695633211795e-05,
      "loss": 0.8659,
      "step": 860
    },
    {
      "epoch": 0.8277511961722488,
      "grad_norm": 1.090226173400879,
      "learning_rate": 2.6333765948735986e-05,
      "loss": 0.8491,
      "step": 865
    },
    {
      "epoch": 0.8325358851674641,
      "grad_norm": 0.8712325096130371,
      "learning_rate": 2.493250084218795e-05,
      "loss": 0.8626,
      "step": 870
    },
    {
      "epoch": 0.8373205741626795,
      "grad_norm": 0.8832561373710632,
      "learning_rate": 2.3566159287480447e-05,
      "loss": 0.8479,
      "step": 875
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.9606965184211731,
      "learning_rate": 2.2235122818588565e-05,
      "loss": 0.8625,
      "step": 880
    },
    {
      "epoch": 0.84688995215311,
      "grad_norm": 1.056420087814331,
      "learning_rate": 2.0939763110979125e-05,
      "loss": 0.863,
      "step": 885
    },
    {
      "epoch": 0.8516746411483254,
      "grad_norm": 0.9405905604362488,
      "learning_rate": 1.9680441877824527e-05,
      "loss": 0.853,
      "step": 890
    },
    {
      "epoch": 0.8564593301435407,
      "grad_norm": 0.8905633687973022,
      "learning_rate": 1.8457510768999273e-05,
      "loss": 0.8431,
      "step": 895
    },
    {
      "epoch": 0.861244019138756,
      "grad_norm": 0.981576144695282,
      "learning_rate": 1.727131127288572e-05,
      "loss": 0.8477,
      "step": 900
    },
    {
      "epoch": 0.8660287081339713,
      "grad_norm": 1.0129060745239258,
      "learning_rate": 1.612217462101783e-05,
      "loss": 0.8384,
      "step": 905
    },
    {
      "epoch": 0.8708133971291866,
      "grad_norm": 0.9811695218086243,
      "learning_rate": 1.5010421695588825e-05,
      "loss": 0.8573,
      "step": 910
    },
    {
      "epoch": 0.8755980861244019,
      "grad_norm": 0.9269863963127136,
      "learning_rate": 1.3936362939848893e-05,
      "loss": 0.8561,
      "step": 915
    },
    {
      "epoch": 0.8803827751196173,
      "grad_norm": 0.8773042559623718,
      "learning_rate": 1.2900298271417592e-05,
      "loss": 0.8203,
      "step": 920
    },
    {
      "epoch": 0.8851674641148325,
      "grad_norm": 0.9804287552833557,
      "learning_rate": 1.1902516998535666e-05,
      "loss": 0.8382,
      "step": 925
    },
    {
      "epoch": 0.8899521531100478,
      "grad_norm": 0.8934711217880249,
      "learning_rate": 1.0943297739279395e-05,
      "loss": 0.8416,
      "step": 930
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 1.0209717750549316,
      "learning_rate": 1.0022908343759616e-05,
      "loss": 0.8595,
      "step": 935
    },
    {
      "epoch": 0.8995215311004785,
      "grad_norm": 0.8881580829620361,
      "learning_rate": 9.141605819328318e-06,
      "loss": 0.8332,
      "step": 940
    },
    {
      "epoch": 0.9043062200956937,
      "grad_norm": 0.8664154410362244,
      "learning_rate": 8.299636258812197e-06,
      "loss": 0.8437,
      "step": 945
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.8912498950958252,
      "learning_rate": 7.4972347717943916e-06,
      "loss": 0.8485,
      "step": 950
    },
    {
      "epoch": 0.9138755980861244,
      "grad_norm": 0.9088477492332458,
      "learning_rate": 6.734625418963135e-06,
      "loss": 0.8472,
      "step": 955
    },
    {
      "epoch": 0.9186602870813397,
      "grad_norm": 0.9696795344352722,
      "learning_rate": 6.012021149545382e-06,
      "loss": 0.8548,
      "step": 960
    },
    {
      "epoch": 0.9234449760765551,
      "grad_norm": 0.9158973097801208,
      "learning_rate": 5.329623741843531e-06,
      "loss": 0.8333,
      "step": 965
    },
    {
      "epoch": 0.9282296650717703,
      "grad_norm": 0.9025459289550781,
      "learning_rate": 4.6876237468912e-06,
      "loss": 0.8422,
      "step": 970
    },
    {
      "epoch": 0.9330143540669856,
      "grad_norm": 0.8703954815864563,
      "learning_rate": 4.086200435244441e-06,
      "loss": 0.8265,
      "step": 975
    },
    {
      "epoch": 0.937799043062201,
      "grad_norm": 0.9033318161964417,
      "learning_rate": 3.5255217469222942e-06,
      "loss": 0.8203,
      "step": 980
    },
    {
      "epoch": 0.9425837320574163,
      "grad_norm": 1.0247541666030884,
      "learning_rate": 3.0057442445119872e-06,
      "loss": 0.8296,
      "step": 985
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.9569628238677979,
      "learning_rate": 2.5270130694504733e-06,
      "loss": 0.8644,
      "step": 990
    },
    {
      "epoch": 0.9521531100478469,
      "grad_norm": 0.8948321342468262,
      "learning_rate": 2.089461901495715e-06,
      "loss": 0.8278,
      "step": 995
    },
    {
      "epoch": 0.9569377990430622,
      "grad_norm": 0.969680666923523,
      "learning_rate": 1.6932129213980793e-06,
      "loss": 0.8452,
      "step": 1000
    },
    {
      "epoch": 0.9617224880382775,
      "grad_norm": 0.9193556904792786,
      "learning_rate": 1.3383767767829956e-06,
      "loss": 0.8341,
      "step": 1005
    },
    {
      "epoch": 0.9665071770334929,
      "grad_norm": 0.9120749235153198,
      "learning_rate": 1.0250525512538855e-06,
      "loss": 0.8359,
      "step": 1010
    },
    {
      "epoch": 0.9712918660287081,
      "grad_norm": 0.8678485155105591,
      "learning_rate": 7.533277367243795e-07,
      "loss": 0.8187,
      "step": 1015
    },
    {
      "epoch": 0.9760765550239234,
      "grad_norm": 1.054465889930725,
      "learning_rate": 5.232782089872601e-07,
      "loss": 0.8487,
      "step": 1020
    },
    {
      "epoch": 0.9808612440191388,
      "grad_norm": 0.8861187696456909,
      "learning_rate": 3.349682065270254e-07,
      "loss": 0.8504,
      "step": 1025
    },
    {
      "epoch": 0.9856459330143541,
      "grad_norm": 0.9375335574150085,
      "learning_rate": 1.8845031258213905e-07,
      "loss": 0.8459,
      "step": 1030
    },
    {
      "epoch": 0.9904306220095693,
      "grad_norm": 0.9127489924430847,
      "learning_rate": 8.376544046180822e-08,
      "loss": 0.8447,
      "step": 1035
    },
    {
      "epoch": 0.9952153110047847,
      "grad_norm": 0.8907783031463623,
      "learning_rate": 2.0942822121439164e-08,
      "loss": 0.8246,
      "step": 1040
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9073578715324402,
      "learning_rate": 0.0,
      "loss": 0.8382,
      "step": 1045
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4202542304992676,
      "eval_runtime": 1.1602,
      "eval_samples_per_second": 8.619,
      "eval_steps_per_second": 0.862,
      "step": 1045
    },
    {
      "epoch": 1.0,
      "step": 1045,
      "total_flos": 6.049215074407547e+17,
      "train_loss": 1.5597172723432478,
      "train_runtime": 7161.753,
      "train_samples_per_second": 1.751,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 5,
  "max_steps": 1045,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 6.049215074407547e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}