{
  "best_global_step": 3300,
  "best_metric": 1.3866829872131348,
  "best_model_checkpoint": "/content/assets/train/checkpoint-3300",
  "epoch": 3.0,
  "eval_steps": 150,
  "global_step": 3465,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008658008658008658,
      "grad_norm": 3.2492330074310303,
      "learning_rate": 2.3054755043227664e-06,
      "loss": 10.0227,
      "step": 10
    },
    {
      "epoch": 0.017316017316017316,
      "grad_norm": 4.142112731933594,
      "learning_rate": 5.187319884726225e-06,
      "loss": 10.0855,
      "step": 20
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 3.908407211303711,
      "learning_rate": 8.069164265129683e-06,
      "loss": 9.9533,
      "step": 30
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 3.6949715614318848,
      "learning_rate": 1.0951008645533143e-05,
      "loss": 9.8609,
      "step": 40
    },
    {
      "epoch": 0.04329004329004329,
      "grad_norm": 4.507739067077637,
      "learning_rate": 1.3832853025936602e-05,
      "loss": 9.6329,
      "step": 50
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.086377143859863,
      "learning_rate": 1.6714697406340058e-05,
      "loss": 9.0217,
      "step": 60
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 3.342482328414917,
      "learning_rate": 1.9596541786743517e-05,
      "loss": 8.7152,
      "step": 70
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.084209442138672,
      "learning_rate": 2.2478386167146976e-05,
      "loss": 7.9165,
      "step": 80
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 3.369382619857788,
      "learning_rate": 2.5360230547550436e-05,
      "loss": 7.3733,
      "step": 90
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 2.953098773956299,
      "learning_rate": 2.824207492795389e-05,
      "loss": 6.7771,
      "step": 100
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 2.8739757537841797,
      "learning_rate": 3.112391930835735e-05,
      "loss": 6.2224,
      "step": 110
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.5711309909820557,
      "learning_rate": 3.4005763688760814e-05,
      "loss": 5.5781,
      "step": 120
    },
    {
      "epoch": 0.11255411255411256,
      "grad_norm": 2.599085807800293,
      "learning_rate": 3.688760806916426e-05,
      "loss": 5.096,
      "step": 130
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.363588333129883,
      "learning_rate": 3.9769452449567725e-05,
      "loss": 4.391,
      "step": 140
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 2.858348846435547,
      "learning_rate": 4.265129682997118e-05,
      "loss": 3.9469,
      "step": 150
    },
    {
      "epoch": 0.12987012987012986,
      "eval_loss": 3.228956460952759,
      "eval_runtime": 7.8231,
      "eval_samples_per_second": 14.828,
      "eval_steps_per_second": 14.828,
      "step": 150
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.251692056655884,
      "learning_rate": 4.5533141210374644e-05,
      "loss": 3.5343,
      "step": 160
    },
    {
      "epoch": 0.1471861471861472,
      "grad_norm": 4.488837242126465,
      "learning_rate": 4.84149855907781e-05,
      "loss": 3.1367,
      "step": 170
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 1.685425043106079,
      "learning_rate": 5.1296829971181556e-05,
      "loss": 2.7944,
      "step": 180
    },
    {
      "epoch": 0.1645021645021645,
      "grad_norm": 1.291522741317749,
      "learning_rate": 5.417867435158501e-05,
      "loss": 2.5554,
      "step": 190
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 4.081550598144531,
      "learning_rate": 5.7060518731988474e-05,
      "loss": 2.2346,
      "step": 200
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.1544710397720337,
      "learning_rate": 5.994236311239193e-05,
      "loss": 2.1949,
      "step": 210
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.0788459777832031,
      "learning_rate": 6.28242074927954e-05,
      "loss": 2.032,
      "step": 220
    },
    {
      "epoch": 0.19913419913419914,
      "grad_norm": 0.9550963044166565,
      "learning_rate": 6.570605187319885e-05,
      "loss": 1.9622,
      "step": 230
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 1.2657291889190674,
      "learning_rate": 6.858789625360231e-05,
      "loss": 1.9345,
      "step": 240
    },
    {
      "epoch": 0.21645021645021645,
      "grad_norm": 0.8013891577720642,
      "learning_rate": 7.146974063400576e-05,
      "loss": 1.8761,
      "step": 250
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 0.7717137336730957,
      "learning_rate": 7.435158501440924e-05,
      "loss": 1.7893,
      "step": 260
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 1.0486984252929688,
      "learning_rate": 7.723342939481269e-05,
      "loss": 1.8113,
      "step": 270
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.8140750527381897,
      "learning_rate": 8.011527377521614e-05,
      "loss": 1.7928,
      "step": 280
    },
    {
      "epoch": 0.2510822510822511,
      "grad_norm": 0.6925544142723083,
      "learning_rate": 8.29971181556196e-05,
      "loss": 1.7529,
      "step": 290
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.5724755525588989,
      "learning_rate": 8.587896253602306e-05,
      "loss": 1.6537,
      "step": 300
    },
    {
      "epoch": 0.2597402597402597,
      "eval_loss": 1.7084261178970337,
      "eval_runtime": 7.8209,
      "eval_samples_per_second": 14.832,
      "eval_steps_per_second": 14.832,
      "step": 300
    },
    {
      "epoch": 0.2683982683982684,
      "grad_norm": 0.4527546763420105,
      "learning_rate": 8.876080691642652e-05,
      "loss": 1.7249,
      "step": 310
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 0.5245671272277832,
      "learning_rate": 9.164265129682997e-05,
      "loss": 1.6762,
      "step": 320
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.6595690846443176,
      "learning_rate": 9.452449567723344e-05,
      "loss": 1.6373,
      "step": 330
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 0.5773497223854065,
      "learning_rate": 9.74063400576369e-05,
      "loss": 1.669,
      "step": 340
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.5453928112983704,
      "learning_rate": 9.996792815907634e-05,
      "loss": 1.6387,
      "step": 350
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.6853697896003723,
      "learning_rate": 9.964720974983964e-05,
      "loss": 1.6445,
      "step": 360
    },
    {
      "epoch": 0.3203463203463203,
      "grad_norm": 0.44910380244255066,
      "learning_rate": 9.932649134060296e-05,
      "loss": 1.6044,
      "step": 370
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 0.6204536557197571,
      "learning_rate": 9.900577293136627e-05,
      "loss": 1.5821,
      "step": 380
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 0.45651766657829285,
      "learning_rate": 9.868505452212958e-05,
      "loss": 1.6211,
      "step": 390
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 0.8843691945075989,
      "learning_rate": 9.836433611289288e-05,
      "loss": 1.638,
      "step": 400
    },
    {
      "epoch": 0.354978354978355,
      "grad_norm": 0.4958537817001343,
      "learning_rate": 9.804361770365619e-05,
      "loss": 1.5992,
      "step": 410
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.4527323246002197,
      "learning_rate": 9.77228992944195e-05,
      "loss": 1.575,
      "step": 420
    },
    {
      "epoch": 0.3722943722943723,
      "grad_norm": 0.6142332553863525,
      "learning_rate": 9.740218088518281e-05,
      "loss": 1.5653,
      "step": 430
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.5613299012184143,
      "learning_rate": 9.708146247594613e-05,
      "loss": 1.5683,
      "step": 440
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.5093253254890442,
      "learning_rate": 9.676074406670943e-05,
      "loss": 1.5821,
      "step": 450
    },
    {
      "epoch": 0.38961038961038963,
      "eval_loss": 1.5493597984313965,
      "eval_runtime": 7.5671,
      "eval_samples_per_second": 15.329,
      "eval_steps_per_second": 15.329,
      "step": 450
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 0.6183823943138123,
      "learning_rate": 9.644002565747275e-05,
      "loss": 1.5586,
      "step": 460
    },
    {
      "epoch": 0.4069264069264069,
      "grad_norm": 0.40400201082229614,
      "learning_rate": 9.611930724823606e-05,
      "loss": 1.5051,
      "step": 470
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.41863498091697693,
      "learning_rate": 9.579858883899936e-05,
      "loss": 1.5788,
      "step": 480
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.4935775101184845,
      "learning_rate": 9.547787042976267e-05,
      "loss": 1.507,
      "step": 490
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 0.4260643422603607,
      "learning_rate": 9.515715202052598e-05,
      "loss": 1.518,
      "step": 500
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 0.5746622681617737,
      "learning_rate": 9.483643361128929e-05,
      "loss": 1.5765,
      "step": 510
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 0.5225964784622192,
      "learning_rate": 9.45157152020526e-05,
      "loss": 1.5021,
      "step": 520
    },
    {
      "epoch": 0.4588744588744589,
      "grad_norm": 0.5609281659126282,
      "learning_rate": 9.419499679281592e-05,
      "loss": 1.5553,
      "step": 530
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.47306525707244873,
      "learning_rate": 9.387427838357921e-05,
      "loss": 1.5425,
      "step": 540
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.4314194321632385,
      "learning_rate": 9.355355997434253e-05,
      "loss": 1.4717,
      "step": 550
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.8003149032592773,
      "learning_rate": 9.323284156510584e-05,
      "loss": 1.5112,
      "step": 560
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 0.5599727034568787,
      "learning_rate": 9.291212315586915e-05,
      "loss": 1.5184,
      "step": 570
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 0.42898404598236084,
      "learning_rate": 9.259140474663246e-05,
      "loss": 1.4819,
      "step": 580
    },
    {
      "epoch": 0.5108225108225108,
      "grad_norm": 0.4543690085411072,
      "learning_rate": 9.227068633739577e-05,
      "loss": 1.5148,
      "step": 590
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.42663097381591797,
      "learning_rate": 9.194996792815907e-05,
      "loss": 1.5006,
      "step": 600
    },
    {
      "epoch": 0.5194805194805194,
      "eval_loss": 1.4994107484817505,
      "eval_runtime": 7.7698,
      "eval_samples_per_second": 14.93,
      "eval_steps_per_second": 14.93,
      "step": 600
    },
    {
      "epoch": 0.5281385281385281,
      "grad_norm": 0.5133946537971497,
      "learning_rate": 9.162924951892238e-05,
      "loss": 1.4678,
      "step": 610
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 0.4722423553466797,
      "learning_rate": 9.13085311096857e-05,
      "loss": 1.4334,
      "step": 620
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.43144020438194275,
      "learning_rate": 9.098781270044901e-05,
      "loss": 1.544,
      "step": 630
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.7946276664733887,
      "learning_rate": 9.066709429121232e-05,
      "loss": 1.518,
      "step": 640
    },
    {
      "epoch": 0.5627705627705628,
      "grad_norm": 0.5020509958267212,
      "learning_rate": 9.034637588197563e-05,
      "loss": 1.4587,
      "step": 650
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.39891430735588074,
      "learning_rate": 9.002565747273895e-05,
      "loss": 1.5042,
      "step": 660
    },
    {
      "epoch": 0.5800865800865801,
      "grad_norm": 0.4414899945259094,
      "learning_rate": 8.970493906350225e-05,
      "loss": 1.4729,
      "step": 670
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 0.5268612504005432,
      "learning_rate": 8.938422065426555e-05,
      "loss": 1.4627,
      "step": 680
    },
    {
      "epoch": 0.5974025974025974,
      "grad_norm": 0.3689039349555969,
      "learning_rate": 8.906350224502888e-05,
      "loss": 1.4954,
      "step": 690
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.5123299956321716,
      "learning_rate": 8.874278383579217e-05,
      "loss": 1.4886,
      "step": 700
    },
    {
      "epoch": 0.6147186147186147,
      "grad_norm": 0.41066890954971313,
      "learning_rate": 8.842206542655549e-05,
      "loss": 1.4847,
      "step": 710
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 0.4995342791080475,
      "learning_rate": 8.81013470173188e-05,
      "loss": 1.4533,
      "step": 720
    },
    {
      "epoch": 0.6320346320346321,
      "grad_norm": 0.75323486328125,
      "learning_rate": 8.778062860808211e-05,
      "loss": 1.5261,
      "step": 730
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 0.4391060173511505,
      "learning_rate": 8.745991019884542e-05,
      "loss": 1.4441,
      "step": 740
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 0.6707803606987,
      "learning_rate": 8.713919178960874e-05,
      "loss": 1.4817,
      "step": 750
    },
    {
      "epoch": 0.6493506493506493,
      "eval_loss": 1.4739664793014526,
      "eval_runtime": 7.8538,
      "eval_samples_per_second": 14.77,
      "eval_steps_per_second": 14.77,
      "step": 750
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 0.39276689291000366,
      "learning_rate": 8.681847338037203e-05,
      "loss": 1.4755,
      "step": 760
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5317443013191223,
      "learning_rate": 8.649775497113535e-05,
      "loss": 1.4851,
      "step": 770
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 0.41005635261535645,
      "learning_rate": 8.617703656189866e-05,
      "loss": 1.4603,
      "step": 780
    },
    {
      "epoch": 0.683982683982684,
      "grad_norm": 0.4464978277683258,
      "learning_rate": 8.585631815266196e-05,
      "loss": 1.4544,
      "step": 790
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 0.5416218638420105,
      "learning_rate": 8.553559974342528e-05,
      "loss": 1.4643,
      "step": 800
    },
    {
      "epoch": 0.7012987012987013,
      "grad_norm": 0.461434930562973,
      "learning_rate": 8.521488133418859e-05,
      "loss": 1.4672,
      "step": 810
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 0.4783085882663727,
      "learning_rate": 8.48941629249519e-05,
      "loss": 1.4392,
      "step": 820
    },
    {
      "epoch": 0.7186147186147186,
      "grad_norm": 0.49549704790115356,
      "learning_rate": 8.45734445157152e-05,
      "loss": 1.4643,
      "step": 830
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4395453929901123,
      "learning_rate": 8.425272610647852e-05,
      "loss": 1.4702,
      "step": 840
    },
    {
      "epoch": 0.7359307359307359,
      "grad_norm": 0.4826950430870056,
      "learning_rate": 8.393200769724182e-05,
      "loss": 1.4785,
      "step": 850
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 0.43482276797294617,
      "learning_rate": 8.361128928800514e-05,
      "loss": 1.4846,
      "step": 860
    },
    {
      "epoch": 0.7532467532467533,
      "grad_norm": 0.4471447765827179,
      "learning_rate": 8.329057087876845e-05,
      "loss": 1.4608,
      "step": 870
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.4189813733100891,
      "learning_rate": 8.296985246953174e-05,
      "loss": 1.4744,
      "step": 880
    },
    {
      "epoch": 0.7705627705627706,
      "grad_norm": 0.4434950649738312,
      "learning_rate": 8.264913406029507e-05,
      "loss": 1.4339,
      "step": 890
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 0.47065186500549316,
      "learning_rate": 8.232841565105837e-05,
      "loss": 1.463,
      "step": 900
    },
    {
      "epoch": 0.7792207792207793,
      "eval_loss": 1.4551337957382202,
      "eval_runtime": 7.6143,
      "eval_samples_per_second": 15.235,
      "eval_steps_per_second": 15.235,
      "step": 900
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.6143885850906372,
      "learning_rate": 8.200769724182168e-05,
      "loss": 1.4465,
      "step": 910
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 0.4523776173591614,
      "learning_rate": 8.168697883258499e-05,
      "loss": 1.483,
      "step": 920
    },
    {
      "epoch": 0.8051948051948052,
      "grad_norm": 0.4819616377353668,
      "learning_rate": 8.136626042334831e-05,
      "loss": 1.4685,
      "step": 930
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 0.44892895221710205,
      "learning_rate": 8.10455420141116e-05,
      "loss": 1.4753,
      "step": 940
    },
    {
      "epoch": 0.8225108225108225,
      "grad_norm": 0.401432603597641,
      "learning_rate": 8.072482360487493e-05,
      "loss": 1.4652,
      "step": 950
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 0.6020355820655823,
      "learning_rate": 8.040410519563824e-05,
      "loss": 1.4731,
      "step": 960
    },
    {
      "epoch": 0.8398268398268398,
      "grad_norm": 0.43847760558128357,
      "learning_rate": 8.008338678640154e-05,
      "loss": 1.4475,
      "step": 970
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.5052961111068726,
      "learning_rate": 7.976266837716485e-05,
      "loss": 1.478,
      "step": 980
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.49521583318710327,
      "learning_rate": 7.944194996792816e-05,
      "loss": 1.4718,
      "step": 990
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 0.5364260673522949,
      "learning_rate": 7.912123155869148e-05,
      "loss": 1.4448,
      "step": 1000
    },
    {
      "epoch": 0.8744588744588745,
      "grad_norm": 0.5025216937065125,
      "learning_rate": 7.880051314945478e-05,
      "loss": 1.4412,
      "step": 1010
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 0.5361949801445007,
      "learning_rate": 7.84797947402181e-05,
      "loss": 1.466,
      "step": 1020
    },
    {
      "epoch": 0.8917748917748918,
      "grad_norm": 0.4959454834461212,
      "learning_rate": 7.81590763309814e-05,
      "loss": 1.4497,
      "step": 1030
    },
    {
      "epoch": 0.9004329004329005,
      "grad_norm": 0.4520016014575958,
      "learning_rate": 7.783835792174471e-05,
      "loss": 1.4696,
      "step": 1040
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.4341891407966614,
      "learning_rate": 7.751763951250802e-05,
      "loss": 1.4861,
      "step": 1050
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 1.445294737815857,
      "eval_runtime": 7.7407,
      "eval_samples_per_second": 14.986,
      "eval_steps_per_second": 14.986,
      "step": 1050
    },
    {
      "epoch": 0.9177489177489178,
      "grad_norm": 0.4321749210357666,
      "learning_rate": 7.719692110327133e-05,
      "loss": 1.4709,
      "step": 1060
    },
    {
      "epoch": 0.9264069264069265,
      "grad_norm": 0.4757050573825836,
      "learning_rate": 7.687620269403464e-05,
      "loss": 1.4358,
      "step": 1070
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 0.44605541229248047,
      "learning_rate": 7.655548428479795e-05,
      "loss": 1.4582,
      "step": 1080
    },
    {
      "epoch": 0.9437229437229437,
      "grad_norm": 0.9228002429008484,
      "learning_rate": 7.623476587556127e-05,
      "loss": 1.4346,
      "step": 1090
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.49421215057373047,
      "learning_rate": 7.591404746632456e-05,
      "loss": 1.4995,
      "step": 1100
    },
    {
      "epoch": 0.961038961038961,
      "grad_norm": 0.47634872794151306,
      "learning_rate": 7.559332905708789e-05,
      "loss": 1.4572,
      "step": 1110
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.42080676555633545,
      "learning_rate": 7.52726106478512e-05,
      "loss": 1.4603,
      "step": 1120
    },
    {
      "epoch": 0.9783549783549783,
      "grad_norm": 0.7112604975700378,
      "learning_rate": 7.49518922386145e-05,
      "loss": 1.4131,
      "step": 1130
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 0.4389120638370514,
      "learning_rate": 7.463117382937781e-05,
      "loss": 1.4665,
      "step": 1140
    },
    {
      "epoch": 0.9956709956709957,
      "grad_norm": 0.43562325835227966,
      "learning_rate": 7.431045542014112e-05,
      "loss": 1.4105,
      "step": 1150
    },
    {
      "epoch": 1.0043290043290043,
      "grad_norm": 0.5207663178443909,
      "learning_rate": 7.398973701090443e-05,
      "loss": 1.4138,
      "step": 1160
    },
    {
      "epoch": 1.0129870129870129,
      "grad_norm": 0.458304226398468,
      "learning_rate": 7.366901860166773e-05,
      "loss": 1.4037,
      "step": 1170
    },
    {
      "epoch": 1.0216450216450217,
      "grad_norm": 0.44204622507095337,
      "learning_rate": 7.334830019243106e-05,
      "loss": 1.45,
      "step": 1180
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 0.4411581754684448,
      "learning_rate": 7.302758178319435e-05,
      "loss": 1.4178,
      "step": 1190
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 0.4655054807662964,
      "learning_rate": 7.270686337395767e-05,
      "loss": 1.435,
      "step": 1200
    },
    {
      "epoch": 1.0389610389610389,
      "eval_loss": 1.4338457584381104,
      "eval_runtime": 7.5729,
      "eval_samples_per_second": 15.318,
      "eval_steps_per_second": 15.318,
      "step": 1200
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.46722933650016785,
      "learning_rate": 7.238614496472098e-05,
      "loss": 1.4056,
      "step": 1210
    },
    {
      "epoch": 1.0562770562770563,
      "grad_norm": 0.43104156851768494,
      "learning_rate": 7.206542655548429e-05,
      "loss": 1.425,
      "step": 1220
    },
    {
      "epoch": 1.0649350649350648,
      "grad_norm": 0.45806413888931274,
      "learning_rate": 7.17447081462476e-05,
      "loss": 1.415,
      "step": 1230
    },
    {
      "epoch": 1.0735930735930737,
      "grad_norm": 0.4905741512775421,
      "learning_rate": 7.14239897370109e-05,
      "loss": 1.4251,
      "step": 1240
    },
    {
      "epoch": 1.0822510822510822,
      "grad_norm": 0.5820769667625427,
      "learning_rate": 7.110327132777421e-05,
      "loss": 1.4423,
      "step": 1250
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.4339599907398224,
      "learning_rate": 7.078255291853752e-05,
      "loss": 1.3944,
      "step": 1260
    },
    {
      "epoch": 1.0995670995670996,
      "grad_norm": 0.4569433331489563,
      "learning_rate": 7.046183450930084e-05,
      "loss": 1.4425,
      "step": 1270
    },
    {
      "epoch": 1.1082251082251082,
      "grad_norm": 0.43175208568573,
      "learning_rate": 7.014111610006415e-05,
      "loss": 1.4413,
      "step": 1280
    },
    {
      "epoch": 1.1168831168831168,
      "grad_norm": 0.4652206003665924,
      "learning_rate": 6.982039769082746e-05,
      "loss": 1.4131,
      "step": 1290
    },
    {
      "epoch": 1.1255411255411256,
      "grad_norm": 0.5452226996421814,
      "learning_rate": 6.949967928159077e-05,
      "loss": 1.3971,
      "step": 1300
    },
    {
      "epoch": 1.1341991341991342,
      "grad_norm": 0.48716047406196594,
      "learning_rate": 6.917896087235408e-05,
      "loss": 1.4121,
      "step": 1310
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.495291143655777,
      "learning_rate": 6.885824246311738e-05,
      "loss": 1.4392,
      "step": 1320
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 0.7268972396850586,
      "learning_rate": 6.853752405388069e-05,
      "loss": 1.448,
      "step": 1330
    },
    {
      "epoch": 1.1601731601731602,
      "grad_norm": 0.5051429271697998,
      "learning_rate": 6.821680564464401e-05,
      "loss": 1.4455,
      "step": 1340
    },
    {
      "epoch": 1.1688311688311688,
      "grad_norm": 0.4902680218219757,
      "learning_rate": 6.789608723540731e-05,
      "loss": 1.4264,
      "step": 1350
    },
    {
      "epoch": 1.1688311688311688,
      "eval_loss": 1.4238612651824951,
      "eval_runtime": 7.7602,
      "eval_samples_per_second": 14.948,
      "eval_steps_per_second": 14.948,
      "step": 1350
    },
    {
      "epoch": 1.1774891774891776,
      "grad_norm": 0.4761177897453308,
      "learning_rate": 6.757536882617063e-05,
      "loss": 1.3901,
      "step": 1360
    },
    {
      "epoch": 1.1861471861471862,
      "grad_norm": 0.5615859031677246,
      "learning_rate": 6.725465041693394e-05,
      "loss": 1.452,
      "step": 1370
    },
    {
      "epoch": 1.1948051948051948,
      "grad_norm": 0.4387504458427429,
      "learning_rate": 6.693393200769725e-05,
      "loss": 1.4367,
      "step": 1380
    },
    {
      "epoch": 1.2034632034632033,
      "grad_norm": 0.45687058568000793,
      "learning_rate": 6.661321359846055e-05,
      "loss": 1.3763,
      "step": 1390
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.5605970621109009,
      "learning_rate": 6.629249518922386e-05,
      "loss": 1.4052,
      "step": 1400
    },
    {
      "epoch": 1.2207792207792207,
      "grad_norm": 0.486742228269577,
      "learning_rate": 6.597177677998717e-05,
      "loss": 1.3496,
      "step": 1410
    },
    {
      "epoch": 1.2294372294372296,
      "grad_norm": 0.5142826437950134,
      "learning_rate": 6.565105837075048e-05,
      "loss": 1.4467,
      "step": 1420
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.6005675792694092,
      "learning_rate": 6.53303399615138e-05,
      "loss": 1.4524,
      "step": 1430
    },
    {
      "epoch": 1.2467532467532467,
      "grad_norm": 0.45657065510749817,
      "learning_rate": 6.50096215522771e-05,
      "loss": 1.3833,
      "step": 1440
    },
    {
      "epoch": 1.2554112554112553,
      "grad_norm": 0.5361114144325256,
      "learning_rate": 6.468890314304042e-05,
      "loss": 1.4584,
      "step": 1450
    },
    {
      "epoch": 1.2640692640692641,
      "grad_norm": 0.41551673412323,
      "learning_rate": 6.436818473380373e-05,
      "loss": 1.4233,
      "step": 1460
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.9184830784797668,
      "learning_rate": 6.404746632456703e-05,
      "loss": 1.4636,
      "step": 1470
    },
    {
      "epoch": 1.2813852813852815,
      "grad_norm": 0.4942251145839691,
      "learning_rate": 6.372674791533034e-05,
      "loss": 1.4074,
      "step": 1480
    },
    {
      "epoch": 1.29004329004329,
      "grad_norm": 0.45169901847839355,
      "learning_rate": 6.340602950609365e-05,
      "loss": 1.4324,
      "step": 1490
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 0.47444090247154236,
      "learning_rate": 6.308531109685696e-05,
      "loss": 1.3932,
      "step": 1500
    },
    {
      "epoch": 1.2987012987012987,
      "eval_loss": 1.4216547012329102,
      "eval_runtime": 7.7823,
      "eval_samples_per_second": 14.906,
      "eval_steps_per_second": 14.906,
      "step": 1500
    },
    {
      "epoch": 1.3073593073593073,
      "grad_norm": 0.49456027150154114,
      "learning_rate": 6.276459268762027e-05,
      "loss": 1.4163,
      "step": 1510
    },
    {
      "epoch": 1.316017316017316,
      "grad_norm": 0.5237517356872559,
      "learning_rate": 6.244387427838359e-05,
      "loss": 1.4241,
      "step": 1520
    },
    {
      "epoch": 1.3246753246753247,
      "grad_norm": 0.467379629611969,
      "learning_rate": 6.212315586914688e-05,
      "loss": 1.3793,
      "step": 1530
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.44650447368621826,
      "learning_rate": 6.18024374599102e-05,
      "loss": 1.421,
      "step": 1540
    },
    {
      "epoch": 1.341991341991342,
      "grad_norm": 0.5066041350364685,
      "learning_rate": 6.148171905067351e-05,
      "loss": 1.4078,
      "step": 1550
    },
    {
      "epoch": 1.3506493506493507,
      "grad_norm": 0.49115797877311707,
      "learning_rate": 6.116100064143682e-05,
      "loss": 1.4364,
      "step": 1560
    },
    {
      "epoch": 1.3593073593073592,
      "grad_norm": 0.447895348072052,
      "learning_rate": 6.084028223220013e-05,
      "loss": 1.4204,
      "step": 1570
    },
    {
      "epoch": 1.3679653679653678,
      "grad_norm": 0.4935031831264496,
      "learning_rate": 6.0519563822963443e-05,
      "loss": 1.3989,
      "step": 1580
    },
    {
      "epoch": 1.3766233766233766,
      "grad_norm": 0.46873730421066284,
      "learning_rate": 6.0198845413726745e-05,
      "loss": 1.3977,
      "step": 1590
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 0.5020815134048462,
      "learning_rate": 5.987812700449006e-05,
      "loss": 1.396,
      "step": 1600
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 0.5052680373191833,
      "learning_rate": 5.9557408595253375e-05,
      "loss": 1.4509,
      "step": 1610
    },
    {
      "epoch": 1.4025974025974026,
      "grad_norm": 0.9146791100502014,
      "learning_rate": 5.923669018601668e-05,
      "loss": 1.4463,
      "step": 1620
    },
    {
      "epoch": 1.4112554112554112,
      "grad_norm": 0.6017730832099915,
      "learning_rate": 5.891597177677999e-05,
      "loss": 1.4418,
      "step": 1630
    },
    {
      "epoch": 1.4199134199134198,
      "grad_norm": 0.42603838443756104,
      "learning_rate": 5.85952533675433e-05,
      "loss": 1.3932,
      "step": 1640
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.44781237840652466,
      "learning_rate": 5.8274534958306614e-05,
      "loss": 1.4122,
      "step": 1650
    },
    {
      "epoch": 1.4285714285714286,
      "eval_loss": 1.4141463041305542,
      "eval_runtime": 7.5625,
      "eval_samples_per_second": 15.339,
      "eval_steps_per_second": 15.339,
      "step": 1650
    },
    {
      "epoch": 1.4372294372294372,
      "grad_norm": 0.545901358127594,
      "learning_rate": 5.7953816549069915e-05,
      "loss": 1.4365,
      "step": 1660
    },
    {
      "epoch": 1.445887445887446,
      "grad_norm": 0.6359984874725342,
      "learning_rate": 5.763309813983323e-05,
      "loss": 1.4015,
      "step": 1670
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.5338530540466309,
      "learning_rate": 5.7312379730596545e-05,
      "loss": 1.4229,
      "step": 1680
    },
    {
      "epoch": 1.4632034632034632,
      "grad_norm": 0.5224403142929077,
      "learning_rate": 5.699166132135985e-05,
      "loss": 1.4568,
      "step": 1690
    },
    {
      "epoch": 1.4718614718614718,
      "grad_norm": 0.4464894235134125,
      "learning_rate": 5.667094291212316e-05,
      "loss": 1.3786,
      "step": 1700
    },
    {
      "epoch": 1.4805194805194806,
      "grad_norm": 0.5031586289405823,
      "learning_rate": 5.635022450288647e-05,
      "loss": 1.4033,
      "step": 1710
    },
    {
      "epoch": 1.4891774891774892,
      "grad_norm": 0.4978921115398407,
      "learning_rate": 5.602950609364978e-05,
      "loss": 1.4008,
      "step": 1720
    },
    {
      "epoch": 1.497835497835498,
      "grad_norm": 0.4722082316875458,
      "learning_rate": 5.5708787684413086e-05,
      "loss": 1.4138,
      "step": 1730
    },
    {
      "epoch": 1.5064935064935066,
      "grad_norm": 0.49410945177078247,
      "learning_rate": 5.53880692751764e-05,
      "loss": 1.3493,
      "step": 1740
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.48314598202705383,
      "learning_rate": 5.50673508659397e-05,
      "loss": 1.4261,
      "step": 1750
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.4303835928440094,
      "learning_rate": 5.474663245670302e-05,
      "loss": 1.3669,
      "step": 1760
    },
    {
      "epoch": 1.5324675324675323,
      "grad_norm": 0.6156985759735107,
      "learning_rate": 5.442591404746633e-05,
      "loss": 1.4068,
      "step": 1770
    },
    {
      "epoch": 1.5411255411255411,
      "grad_norm": 0.47915613651275635,
      "learning_rate": 5.4105195638229634e-05,
      "loss": 1.4086,
      "step": 1780
    },
    {
      "epoch": 1.54978354978355,
      "grad_norm": 0.5295699834823608,
      "learning_rate": 5.378447722899295e-05,
      "loss": 1.4269,
      "step": 1790
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 0.503179669380188,
      "learning_rate": 5.346375881975626e-05,
      "loss": 1.4062,
      "step": 1800
    },
    {
      "epoch": 1.5584415584415585,
      "eval_loss": 1.4098143577575684,
      "eval_runtime": 7.8033,
      "eval_samples_per_second": 14.865,
      "eval_steps_per_second": 14.865,
      "step": 1800
    },
    {
      "epoch": 1.567099567099567,
      "grad_norm": 0.5550847053527832,
      "learning_rate": 5.3143040410519565e-05,
      "loss": 1.4071,
      "step": 1810
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 0.4503953456878662,
      "learning_rate": 5.282232200128287e-05,
      "loss": 1.378,
      "step": 1820
    },
    {
      "epoch": 1.5844155844155843,
      "grad_norm": 0.47239604592323303,
      "learning_rate": 5.250160359204619e-05,
      "loss": 1.4089,
      "step": 1830
    },
    {
      "epoch": 1.593073593073593,
      "grad_norm": 0.49943140149116516,
      "learning_rate": 5.218088518280949e-05,
      "loss": 1.3666,
      "step": 1840
    },
    {
      "epoch": 1.601731601731602,
      "grad_norm": 0.45932552218437195,
      "learning_rate": 5.1860166773572804e-05,
      "loss": 1.3963,
      "step": 1850
    },
    {
      "epoch": 1.6103896103896105,
      "grad_norm": 0.4893176853656769,
      "learning_rate": 5.153944836433612e-05,
      "loss": 1.3855,
      "step": 1860
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.43340370059013367,
      "learning_rate": 5.121872995509942e-05,
      "loss": 1.3968,
      "step": 1870
    },
    {
      "epoch": 1.6277056277056277,
      "grad_norm": 0.5329946279525757,
      "learning_rate": 5.0898011545862735e-05,
      "loss": 1.3931,
      "step": 1880
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.5289266705513,
      "learning_rate": 5.057729313662605e-05,
      "loss": 1.3806,
      "step": 1890
    },
    {
      "epoch": 1.645021645021645,
      "grad_norm": 0.46577054262161255,
      "learning_rate": 5.025657472738935e-05,
      "loss": 1.3883,
      "step": 1900
    },
    {
      "epoch": 1.6536796536796536,
      "grad_norm": 0.6365689635276794,
      "learning_rate": 4.993585631815266e-05,
      "loss": 1.465,
      "step": 1910
    },
    {
      "epoch": 1.6623376623376624,
      "grad_norm": 0.4840717017650604,
      "learning_rate": 4.9615137908915975e-05,
      "loss": 1.4014,
      "step": 1920
    },
    {
      "epoch": 1.670995670995671,
      "grad_norm": 0.4716441035270691,
      "learning_rate": 4.929441949967928e-05,
      "loss": 1.3868,
      "step": 1930
    },
    {
      "epoch": 1.6796536796536796,
      "grad_norm": 0.5497351884841919,
      "learning_rate": 4.897370109044259e-05,
      "loss": 1.3977,
      "step": 1940
    },
    {
      "epoch": 1.6883116883116882,
      "grad_norm": 0.46503710746765137,
      "learning_rate": 4.8652982681205906e-05,
      "loss": 1.4178,
      "step": 1950
    },
    {
      "epoch": 1.6883116883116882,
      "eval_loss": 1.40426504611969,
      "eval_runtime": 7.8451,
      "eval_samples_per_second": 14.786,
      "eval_steps_per_second": 14.786,
      "step": 1950
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 0.46529683470726013,
      "learning_rate": 4.8332264271969214e-05,
      "loss": 1.4008,
      "step": 1960
    },
    {
      "epoch": 1.7056277056277056,
      "grad_norm": 0.4543629288673401,
      "learning_rate": 4.801154586273252e-05,
      "loss": 1.3743,
      "step": 1970
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.5630565881729126,
      "learning_rate": 4.769082745349584e-05,
      "loss": 1.4285,
      "step": 1980
    },
    {
      "epoch": 1.722943722943723,
      "grad_norm": 0.5113540887832642,
      "learning_rate": 4.7370109044259146e-05,
      "loss": 1.4613,
      "step": 1990
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 0.4659116864204407,
      "learning_rate": 4.704939063502245e-05,
      "loss": 1.3922,
      "step": 2000
    },
    {
      "epoch": 1.7402597402597402,
      "grad_norm": 0.517657995223999,
      "learning_rate": 4.672867222578576e-05,
      "loss": 1.418,
      "step": 2010
    },
    {
      "epoch": 1.7489177489177488,
      "grad_norm": 0.5077757239341736,
      "learning_rate": 4.640795381654907e-05,
      "loss": 1.427,
      "step": 2020
    },
    {
      "epoch": 1.7575757575757576,
      "grad_norm": 0.44553670287132263,
      "learning_rate": 4.6087235407312385e-05,
      "loss": 1.3995,
      "step": 2030
    },
    {
      "epoch": 1.7662337662337664,
      "grad_norm": 0.5303440690040588,
      "learning_rate": 4.576651699807569e-05,
      "loss": 1.4122,
      "step": 2040
    },
    {
      "epoch": 1.774891774891775,
      "grad_norm": 0.5498613715171814,
      "learning_rate": 4.5445798588839e-05,
      "loss": 1.349,
      "step": 2050
    },
    {
      "epoch": 1.7835497835497836,
      "grad_norm": 0.5696060061454773,
      "learning_rate": 4.5125080179602316e-05,
      "loss": 1.3798,
      "step": 2060
    },
    {
      "epoch": 1.7922077922077921,
      "grad_norm": 0.538739025592804,
      "learning_rate": 4.4804361770365624e-05,
      "loss": 1.3867,
      "step": 2070
    },
    {
      "epoch": 1.8008658008658007,
      "grad_norm": 0.5294226408004761,
      "learning_rate": 4.448364336112893e-05,
      "loss": 1.4102,
      "step": 2080
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.6144235134124756,
      "learning_rate": 4.416292495189224e-05,
      "loss": 1.4011,
      "step": 2090
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.45938369631767273,
      "learning_rate": 4.384220654265555e-05,
      "loss": 1.3728,
      "step": 2100
    },
    {
      "epoch": 1.8181818181818183,
      "eval_loss": 1.404729962348938,
      "eval_runtime": 7.7744,
      "eval_samples_per_second": 14.921,
      "eval_steps_per_second": 14.921,
      "step": 2100
    },
    {
      "epoch": 1.826839826839827,
      "grad_norm": 0.5399343371391296,
      "learning_rate": 4.352148813341886e-05,
      "loss": 1.4382,
      "step": 2110
    },
    {
      "epoch": 1.8354978354978355,
      "grad_norm": 0.5021647214889526,
      "learning_rate": 4.320076972418217e-05,
      "loss": 1.4053,
      "step": 2120
    },
    {
      "epoch": 1.844155844155844,
      "grad_norm": 0.5417078137397766,
      "learning_rate": 4.288005131494548e-05,
      "loss": 1.4171,
      "step": 2130
    },
    {
      "epoch": 1.8528138528138527,
      "grad_norm": 0.45010820031166077,
      "learning_rate": 4.255933290570879e-05,
      "loss": 1.4057,
      "step": 2140
    },
    {
      "epoch": 1.8614718614718615,
      "grad_norm": 0.5336911678314209,
      "learning_rate": 4.22386144964721e-05,
      "loss": 1.4232,
      "step": 2150
    },
    {
      "epoch": 1.87012987012987,
      "grad_norm": 0.49677231907844543,
      "learning_rate": 4.191789608723541e-05,
      "loss": 1.4024,
      "step": 2160
    },
    {
      "epoch": 1.878787878787879,
      "grad_norm": 0.626252293586731,
      "learning_rate": 4.159717767799872e-05,
      "loss": 1.4063,
      "step": 2170
    },
    {
      "epoch": 1.8874458874458875,
      "grad_norm": 0.6295285224914551,
      "learning_rate": 4.127645926876203e-05,
      "loss": 1.3892,
      "step": 2180
    },
    {
      "epoch": 1.896103896103896,
      "grad_norm": 0.422695517539978,
      "learning_rate": 4.0955740859525336e-05,
      "loss": 1.3829,
      "step": 2190
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.48999500274658203,
      "learning_rate": 4.063502245028865e-05,
      "loss": 1.4659,
      "step": 2200
    },
    {
      "epoch": 1.9134199134199135,
      "grad_norm": 0.5450994372367859,
      "learning_rate": 4.031430404105196e-05,
      "loss": 1.3817,
      "step": 2210
    },
    {
      "epoch": 1.922077922077922,
      "grad_norm": 0.4830107092857361,
      "learning_rate": 3.999358563181527e-05,
      "loss": 1.368,
      "step": 2220
    },
    {
      "epoch": 1.9307359307359309,
      "grad_norm": 0.4606921672821045,
      "learning_rate": 3.967286722257858e-05,
      "loss": 1.415,
      "step": 2230
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.442903071641922,
      "learning_rate": 3.935214881334189e-05,
      "loss": 1.4027,
      "step": 2240
    },
    {
      "epoch": 1.948051948051948,
      "grad_norm": 0.6243829727172852,
      "learning_rate": 3.90314304041052e-05,
      "loss": 1.4393,
      "step": 2250
    },
    {
      "epoch": 1.948051948051948,
      "eval_loss": 1.3986151218414307,
      "eval_runtime": 7.815,
      "eval_samples_per_second": 14.843,
      "eval_steps_per_second": 14.843,
      "step": 2250
    },
    {
      "epoch": 1.9567099567099566,
      "grad_norm": 0.5800577402114868,
      "learning_rate": 3.8710711994868506e-05,
      "loss": 1.395,
      "step": 2260
    },
    {
      "epoch": 1.9653679653679652,
      "grad_norm": 0.47577986121177673,
      "learning_rate": 3.8389993585631815e-05,
      "loss": 1.3706,
      "step": 2270
    },
    {
      "epoch": 1.974025974025974,
      "grad_norm": 0.47002679109573364,
      "learning_rate": 3.806927517639512e-05,
      "loss": 1.4082,
      "step": 2280
    },
    {
      "epoch": 1.9826839826839828,
      "grad_norm": 0.5210914015769958,
      "learning_rate": 3.774855676715844e-05,
      "loss": 1.4035,
      "step": 2290
    },
    {
      "epoch": 1.9913419913419914,
      "grad_norm": 0.46940165758132935,
      "learning_rate": 3.7427838357921746e-05,
      "loss": 1.3688,
      "step": 2300
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.46823203563690186,
      "learning_rate": 3.7107119948685054e-05,
      "loss": 1.4031,
      "step": 2310
    },
    {
      "epoch": 2.0086580086580086,
      "grad_norm": 0.5137255787849426,
      "learning_rate": 3.678640153944837e-05,
      "loss": 1.3741,
      "step": 2320
    },
    {
      "epoch": 2.017316017316017,
      "grad_norm": 0.48361772298812866,
      "learning_rate": 3.646568313021168e-05,
      "loss": 1.4079,
      "step": 2330
    },
    {
      "epoch": 2.0259740259740258,
      "grad_norm": 0.46107912063598633,
      "learning_rate": 3.6144964720974985e-05,
      "loss": 1.3965,
      "step": 2340
    },
    {
      "epoch": 2.034632034632035,
      "grad_norm": 0.5398858785629272,
      "learning_rate": 3.582424631173829e-05,
      "loss": 1.3703,
      "step": 2350
    },
    {
      "epoch": 2.0432900432900434,
      "grad_norm": 0.4744202792644501,
      "learning_rate": 3.55035279025016e-05,
      "loss": 1.3912,
      "step": 2360
    },
    {
      "epoch": 2.051948051948052,
      "grad_norm": 0.48757973313331604,
      "learning_rate": 3.5182809493264916e-05,
      "loss": 1.3599,
      "step": 2370
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 0.45649003982543945,
      "learning_rate": 3.4862091084028225e-05,
      "loss": 1.3833,
      "step": 2380
    },
    {
      "epoch": 2.069264069264069,
      "grad_norm": 0.5607898235321045,
      "learning_rate": 3.454137267479153e-05,
      "loss": 1.3749,
      "step": 2390
    },
    {
      "epoch": 2.0779220779220777,
      "grad_norm": 0.5641899704933167,
      "learning_rate": 3.422065426555485e-05,
      "loss": 1.3525,
      "step": 2400
    },
    {
      "epoch": 2.0779220779220777,
      "eval_loss": 1.39604914188385,
      "eval_runtime": 7.7836,
      "eval_samples_per_second": 14.903,
      "eval_steps_per_second": 14.903,
      "step": 2400
    },
    {
      "epoch": 2.0865800865800868,
      "grad_norm": 0.5425224304199219,
      "learning_rate": 3.3899935856318156e-05,
      "loss": 1.3309,
      "step": 2410
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.5572715401649475,
      "learning_rate": 3.3579217447081464e-05,
      "loss": 1.3868,
      "step": 2420
    },
    {
      "epoch": 2.103896103896104,
      "grad_norm": 0.4905586242675781,
      "learning_rate": 3.325849903784478e-05,
      "loss": 1.3527,
      "step": 2430
    },
    {
      "epoch": 2.1125541125541125,
      "grad_norm": 0.5391650795936584,
      "learning_rate": 3.293778062860808e-05,
      "loss": 1.3944,
      "step": 2440
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 0.5208508372306824,
      "learning_rate": 3.261706221937139e-05,
      "loss": 1.3427,
      "step": 2450
    },
    {
      "epoch": 2.1298701298701297,
      "grad_norm": 0.5472680926322937,
      "learning_rate": 3.2296343810134703e-05,
      "loss": 1.3859,
      "step": 2460
    },
    {
      "epoch": 2.1385281385281387,
      "grad_norm": 0.607253909111023,
      "learning_rate": 3.197562540089801e-05,
      "loss": 1.4454,
      "step": 2470
    },
    {
      "epoch": 2.1471861471861473,
      "grad_norm": 0.49181562662124634,
      "learning_rate": 3.165490699166132e-05,
      "loss": 1.3663,
      "step": 2480
    },
    {
      "epoch": 2.155844155844156,
      "grad_norm": 0.5393516421318054,
      "learning_rate": 3.1334188582424635e-05,
      "loss": 1.4011,
      "step": 2490
    },
    {
      "epoch": 2.1645021645021645,
      "grad_norm": 0.5270664095878601,
      "learning_rate": 3.101347017318794e-05,
      "loss": 1.3797,
      "step": 2500
    },
    {
      "epoch": 2.173160173160173,
      "grad_norm": 0.49387580156326294,
      "learning_rate": 3.069275176395125e-05,
      "loss": 1.4065,
      "step": 2510
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.5828717947006226,
      "learning_rate": 3.0372033354714562e-05,
      "loss": 1.3756,
      "step": 2520
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.48174533247947693,
      "learning_rate": 3.005131494547787e-05,
      "loss": 1.3564,
      "step": 2530
    },
    {
      "epoch": 2.1991341991341993,
      "grad_norm": 0.48883873224258423,
      "learning_rate": 2.9730596536241186e-05,
      "loss": 1.3918,
      "step": 2540
    },
    {
      "epoch": 2.207792207792208,
      "grad_norm": 0.49527278542518616,
      "learning_rate": 2.9409878127004494e-05,
      "loss": 1.4049,
      "step": 2550
    },
    {
      "epoch": 2.207792207792208,
      "eval_loss": 1.39372980594635,
      "eval_runtime": 7.8154,
      "eval_samples_per_second": 14.843,
      "eval_steps_per_second": 14.843,
      "step": 2550
    },
    {
      "epoch": 2.2164502164502164,
      "grad_norm": 0.550302267074585,
      "learning_rate": 2.90891597177678e-05,
      "loss": 1.366,
      "step": 2560
    },
    {
      "epoch": 2.225108225108225,
      "grad_norm": 0.5304882526397705,
      "learning_rate": 2.8768441308531113e-05,
      "loss": 1.3969,
      "step": 2570
    },
    {
      "epoch": 2.2337662337662336,
      "grad_norm": 0.6370409727096558,
      "learning_rate": 2.844772289929442e-05,
      "loss": 1.4069,
      "step": 2580
    },
    {
      "epoch": 2.242424242424242,
      "grad_norm": 0.46794188022613525,
      "learning_rate": 2.812700449005773e-05,
      "loss": 1.3755,
      "step": 2590
    },
    {
      "epoch": 2.2510822510822512,
      "grad_norm": 0.5697752237319946,
      "learning_rate": 2.780628608082104e-05,
      "loss": 1.3703,
      "step": 2600
    },
    {
      "epoch": 2.25974025974026,
      "grad_norm": 0.532133936882019,
      "learning_rate": 2.748556767158435e-05,
      "loss": 1.3802,
      "step": 2610
    },
    {
      "epoch": 2.2683982683982684,
      "grad_norm": 0.5815490484237671,
      "learning_rate": 2.7164849262347658e-05,
      "loss": 1.4311,
      "step": 2620
    },
    {
      "epoch": 2.277056277056277,
      "grad_norm": 1.1725358963012695,
      "learning_rate": 2.6844130853110973e-05,
      "loss": 1.407,
      "step": 2630
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.5177101492881775,
      "learning_rate": 2.652341244387428e-05,
      "loss": 1.3759,
      "step": 2640
    },
    {
      "epoch": 2.2943722943722946,
      "grad_norm": 0.504612922668457,
      "learning_rate": 2.6202694034637585e-05,
      "loss": 1.3887,
      "step": 2650
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 0.5126393437385559,
      "learning_rate": 2.58819756254009e-05,
      "loss": 1.3625,
      "step": 2660
    },
    {
      "epoch": 2.311688311688312,
      "grad_norm": 0.5162597894668579,
      "learning_rate": 2.556125721616421e-05,
      "loss": 1.3741,
      "step": 2670
    },
    {
      "epoch": 2.3203463203463204,
      "grad_norm": 0.5071930885314941,
      "learning_rate": 2.5240538806927517e-05,
      "loss": 1.353,
      "step": 2680
    },
    {
      "epoch": 2.329004329004329,
      "grad_norm": 0.5131155252456665,
      "learning_rate": 2.4919820397690828e-05,
      "loss": 1.3619,
      "step": 2690
    },
    {
      "epoch": 2.3376623376623376,
      "grad_norm": 0.5172668099403381,
      "learning_rate": 2.4599101988454136e-05,
      "loss": 1.361,
      "step": 2700
    },
    {
      "epoch": 2.3376623376623376,
      "eval_loss": 1.3935595750808716,
      "eval_runtime": 7.7819,
      "eval_samples_per_second": 14.906,
      "eval_steps_per_second": 14.906,
      "step": 2700
    },
    {
      "epoch": 2.346320346320346,
      "grad_norm": 0.49953222274780273,
      "learning_rate": 2.4278383579217448e-05,
      "loss": 1.3728,
      "step": 2710
    },
    {
      "epoch": 2.354978354978355,
      "grad_norm": 0.5227655172348022,
      "learning_rate": 2.395766516998076e-05,
      "loss": 1.3976,
      "step": 2720
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.5078625679016113,
      "learning_rate": 2.3636946760744068e-05,
      "loss": 1.3796,
      "step": 2730
    },
    {
      "epoch": 2.3722943722943723,
      "grad_norm": 0.5609903335571289,
      "learning_rate": 2.3316228351507376e-05,
      "loss": 1.356,
      "step": 2740
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.5937998294830322,
      "learning_rate": 2.2995509942270687e-05,
      "loss": 1.3559,
      "step": 2750
    },
    {
      "epoch": 2.3896103896103895,
      "grad_norm": 0.5346037149429321,
      "learning_rate": 2.2674791533034e-05,
      "loss": 1.4105,
      "step": 2760
    },
    {
      "epoch": 2.398268398268398,
      "grad_norm": 0.5979208946228027,
      "learning_rate": 2.2354073123797307e-05,
      "loss": 1.4008,
      "step": 2770
    },
    {
      "epoch": 2.4069264069264067,
      "grad_norm": 0.6183347105979919,
      "learning_rate": 2.2033354714560615e-05,
      "loss": 1.4082,
      "step": 2780
    },
    {
      "epoch": 2.4155844155844157,
      "grad_norm": 0.5043891668319702,
      "learning_rate": 2.1712636305323927e-05,
      "loss": 1.3702,
      "step": 2790
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.6056050062179565,
      "learning_rate": 2.1391917896087235e-05,
      "loss": 1.3674,
      "step": 2800
    },
    {
      "epoch": 2.432900432900433,
      "grad_norm": 0.47270849347114563,
      "learning_rate": 2.1071199486850546e-05,
      "loss": 1.406,
      "step": 2810
    },
    {
      "epoch": 2.4415584415584415,
      "grad_norm": 0.5534608960151672,
      "learning_rate": 2.0750481077613858e-05,
      "loss": 1.3391,
      "step": 2820
    },
    {
      "epoch": 2.45021645021645,
      "grad_norm": 0.49758604168891907,
      "learning_rate": 2.0429762668377166e-05,
      "loss": 1.3806,
      "step": 2830
    },
    {
      "epoch": 2.458874458874459,
      "grad_norm": 0.47173675894737244,
      "learning_rate": 2.0109044259140474e-05,
      "loss": 1.4138,
      "step": 2840
    },
    {
      "epoch": 2.4675324675324677,
      "grad_norm": 0.6245967745780945,
      "learning_rate": 1.9788325849903786e-05,
      "loss": 1.3951,
      "step": 2850
    },
    {
      "epoch": 2.4675324675324677,
      "eval_loss": 1.3923684358596802,
      "eval_runtime": 7.6685,
      "eval_samples_per_second": 15.127,
      "eval_steps_per_second": 15.127,
      "step": 2850
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.7148988842964172,
      "learning_rate": 1.9467607440667097e-05,
      "loss": 1.404,
      "step": 2860
    },
    {
      "epoch": 2.484848484848485,
      "grad_norm": 0.6005236506462097,
      "learning_rate": 1.9146889031430406e-05,
      "loss": 1.3621,
      "step": 2870
    },
    {
      "epoch": 2.4935064935064934,
      "grad_norm": 0.5608522891998291,
      "learning_rate": 1.8826170622193714e-05,
      "loss": 1.3523,
      "step": 2880
    },
    {
      "epoch": 2.502164502164502,
      "grad_norm": 0.48156052827835083,
      "learning_rate": 1.8505452212957025e-05,
      "loss": 1.3447,
      "step": 2890
    },
    {
      "epoch": 2.5108225108225106,
      "grad_norm": 0.49435439705848694,
      "learning_rate": 1.8184733803720337e-05,
      "loss": 1.3732,
      "step": 2900
    },
    {
      "epoch": 2.5194805194805197,
      "grad_norm": 0.5171784162521362,
      "learning_rate": 1.7864015394483645e-05,
      "loss": 1.3816,
      "step": 2910
    },
    {
      "epoch": 2.5281385281385282,
      "grad_norm": 0.5172585844993591,
      "learning_rate": 1.7543296985246953e-05,
      "loss": 1.3507,
      "step": 2920
    },
    {
      "epoch": 2.536796536796537,
      "grad_norm": 0.5661709308624268,
      "learning_rate": 1.7222578576010265e-05,
      "loss": 1.4172,
      "step": 2930
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.5081381797790527,
      "learning_rate": 1.6901860166773573e-05,
      "loss": 1.4172,
      "step": 2940
    },
    {
      "epoch": 2.554112554112554,
      "grad_norm": 0.6050851345062256,
      "learning_rate": 1.6581141757536884e-05,
      "loss": 1.4198,
      "step": 2950
    },
    {
      "epoch": 2.562770562770563,
      "grad_norm": 0.5615077614784241,
      "learning_rate": 1.6260423348300192e-05,
      "loss": 1.3538,
      "step": 2960
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.48784783482551575,
      "learning_rate": 1.59397049390635e-05,
      "loss": 1.361,
      "step": 2970
    },
    {
      "epoch": 2.58008658008658,
      "grad_norm": 0.5115649104118347,
      "learning_rate": 1.5618986529826812e-05,
      "loss": 1.3774,
      "step": 2980
    },
    {
      "epoch": 2.588744588744589,
      "grad_norm": 0.5294427871704102,
      "learning_rate": 1.5298268120590124e-05,
      "loss": 1.3469,
      "step": 2990
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 0.5069863796234131,
      "learning_rate": 1.4977549711353434e-05,
      "loss": 1.3643,
      "step": 3000
    },
    {
      "epoch": 2.5974025974025974,
      "eval_loss": 1.3886290788650513,
      "eval_runtime": 7.5687,
      "eval_samples_per_second": 15.326,
      "eval_steps_per_second": 15.326,
      "step": 3000
    },
    {
      "epoch": 2.606060606060606,
      "grad_norm": 0.5608567595481873,
      "learning_rate": 1.4656831302116742e-05,
      "loss": 1.3865,
      "step": 3010
    },
    {
      "epoch": 2.6147186147186146,
      "grad_norm": 0.5187973380088806,
      "learning_rate": 1.4336112892880052e-05,
      "loss": 1.3766,
      "step": 3020
    },
    {
      "epoch": 2.6233766233766236,
      "grad_norm": 0.5815955400466919,
      "learning_rate": 1.4015394483643363e-05,
      "loss": 1.3686,
      "step": 3030
    },
    {
      "epoch": 2.632034632034632,
      "grad_norm": 0.6289973855018616,
      "learning_rate": 1.3694676074406671e-05,
      "loss": 1.3718,
      "step": 3040
    },
    {
      "epoch": 2.6406926406926408,
      "grad_norm": 0.4538356363773346,
      "learning_rate": 1.3373957665169981e-05,
      "loss": 1.3807,
      "step": 3050
    },
    {
      "epoch": 2.6493506493506493,
      "grad_norm": 0.4869168996810913,
      "learning_rate": 1.3053239255933291e-05,
      "loss": 1.3828,
      "step": 3060
    },
    {
      "epoch": 2.658008658008658,
      "grad_norm": 0.49561557173728943,
      "learning_rate": 1.2732520846696603e-05,
      "loss": 1.3629,
      "step": 3070
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.5569724440574646,
      "learning_rate": 1.241180243745991e-05,
      "loss": 1.3523,
      "step": 3080
    },
    {
      "epoch": 2.675324675324675,
      "grad_norm": 0.5685627460479736,
      "learning_rate": 1.209108402822322e-05,
      "loss": 1.334,
      "step": 3090
    },
    {
      "epoch": 2.683982683982684,
      "grad_norm": 0.6472695469856262,
      "learning_rate": 1.177036561898653e-05,
      "loss": 1.3661,
      "step": 3100
    },
    {
      "epoch": 2.6926406926406927,
      "grad_norm": 0.5198913216590881,
      "learning_rate": 1.144964720974984e-05,
      "loss": 1.3965,
      "step": 3110
    },
    {
      "epoch": 2.7012987012987013,
      "grad_norm": 0.4987531900405884,
      "learning_rate": 1.112892880051315e-05,
      "loss": 1.3748,
      "step": 3120
    },
    {
      "epoch": 2.70995670995671,
      "grad_norm": 0.5096495747566223,
      "learning_rate": 1.080821039127646e-05,
      "loss": 1.332,
      "step": 3130
    },
    {
      "epoch": 2.7186147186147185,
      "grad_norm": 0.5957316160202026,
      "learning_rate": 1.048749198203977e-05,
      "loss": 1.3886,
      "step": 3140
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.5314722061157227,
      "learning_rate": 1.016677357280308e-05,
      "loss": 1.4061,
      "step": 3150
    },
    {
      "epoch": 2.7272727272727275,
      "eval_loss": 1.3869280815124512,
      "eval_runtime": 7.6381,
      "eval_samples_per_second": 15.187,
      "eval_steps_per_second": 15.187,
      "step": 3150
    },
    {
      "epoch": 2.7359307359307357,
      "grad_norm": 0.4673473536968231,
      "learning_rate": 9.84605516356639e-06,
      "loss": 1.3534,
      "step": 3160
    },
    {
      "epoch": 2.7445887445887447,
      "grad_norm": 0.5401672720909119,
      "learning_rate": 9.5253367543297e-06,
      "loss": 1.3426,
      "step": 3170
    },
    {
      "epoch": 2.7532467532467533,
      "grad_norm": 0.8116175532341003,
      "learning_rate": 9.20461834509301e-06,
      "loss": 1.4182,
      "step": 3180
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.48323142528533936,
      "learning_rate": 8.883899935856319e-06,
      "loss": 1.3711,
      "step": 3190
    },
    {
      "epoch": 2.7705627705627704,
      "grad_norm": 0.48122236132621765,
      "learning_rate": 8.563181526619627e-06,
      "loss": 1.4349,
      "step": 3200
    },
    {
      "epoch": 2.779220779220779,
      "grad_norm": 0.5143867135047913,
      "learning_rate": 8.242463117382939e-06,
      "loss": 1.3888,
      "step": 3210
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 0.5092139840126038,
      "learning_rate": 7.921744708146247e-06,
      "loss": 1.364,
      "step": 3220
    },
    {
      "epoch": 2.7965367965367967,
      "grad_norm": 0.5889108180999756,
      "learning_rate": 7.6010262989095584e-06,
      "loss": 1.3903,
      "step": 3230
    },
    {
      "epoch": 2.8051948051948052,
      "grad_norm": 0.5337643623352051,
      "learning_rate": 7.2803078896728674e-06,
      "loss": 1.3593,
      "step": 3240
    },
    {
      "epoch": 2.813852813852814,
      "grad_norm": 0.5285552740097046,
      "learning_rate": 6.959589480436178e-06,
      "loss": 1.3478,
      "step": 3250
    },
    {
      "epoch": 2.8225108225108224,
      "grad_norm": 0.540852427482605,
      "learning_rate": 6.638871071199487e-06,
      "loss": 1.4235,
      "step": 3260
    },
    {
      "epoch": 2.8311688311688314,
      "grad_norm": 0.5818207263946533,
      "learning_rate": 6.318152661962796e-06,
      "loss": 1.3333,
      "step": 3270
    },
    {
      "epoch": 2.8398268398268396,
      "grad_norm": 0.5971714854240417,
      "learning_rate": 5.997434252726107e-06,
      "loss": 1.3919,
      "step": 3280
    },
    {
      "epoch": 2.8484848484848486,
      "grad_norm": 0.5817723274230957,
      "learning_rate": 5.676715843489417e-06,
      "loss": 1.4027,
      "step": 3290
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.8135156035423279,
      "learning_rate": 5.3559974342527265e-06,
      "loss": 1.4073,
      "step": 3300
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 1.3866829872131348,
      "eval_runtime": 7.8013,
      "eval_samples_per_second": 14.869,
      "eval_steps_per_second": 14.869,
      "step": 3300
    },
    {
      "epoch": 2.865800865800866,
      "grad_norm": 0.5037099719047546,
      "learning_rate": 5.035279025016036e-06,
      "loss": 1.3707,
      "step": 3310
    },
    {
      "epoch": 2.8744588744588744,
      "grad_norm": 0.5332845449447632,
      "learning_rate": 4.714560615779346e-06,
      "loss": 1.3677,
      "step": 3320
    },
    {
      "epoch": 2.883116883116883,
      "grad_norm": 0.5143232941627502,
      "learning_rate": 4.393842206542656e-06,
      "loss": 1.375,
      "step": 3330
    },
    {
      "epoch": 2.891774891774892,
      "grad_norm": 0.5839101672172546,
      "learning_rate": 4.073123797305965e-06,
      "loss": 1.3671,
      "step": 3340
    },
    {
      "epoch": 2.9004329004329006,
      "grad_norm": 0.559463620185852,
      "learning_rate": 3.752405388069275e-06,
      "loss": 1.3806,
      "step": 3350
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.541130781173706,
      "learning_rate": 3.431686978832585e-06,
      "loss": 1.3764,
      "step": 3360
    },
    {
      "epoch": 2.9177489177489178,
      "grad_norm": 0.5569273233413696,
      "learning_rate": 3.110968569595895e-06,
      "loss": 1.3454,
      "step": 3370
    },
    {
      "epoch": 2.9264069264069263,
      "grad_norm": 0.530331552028656,
      "learning_rate": 2.790250160359205e-06,
      "loss": 1.3539,
      "step": 3380
    },
    {
      "epoch": 2.935064935064935,
      "grad_norm": 0.6500270366668701,
      "learning_rate": 2.4695317511225143e-06,
      "loss": 1.3368,
      "step": 3390
    },
    {
      "epoch": 2.9437229437229435,
      "grad_norm": 0.5059459805488586,
      "learning_rate": 2.148813341885824e-06,
      "loss": 1.3411,
      "step": 3400
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.511215329170227,
      "learning_rate": 1.8280949326491342e-06,
      "loss": 1.3461,
      "step": 3410
    },
    {
      "epoch": 2.961038961038961,
      "grad_norm": 0.5307567119598389,
      "learning_rate": 1.5073765234124439e-06,
      "loss": 1.3705,
      "step": 3420
    },
    {
      "epoch": 2.9696969696969697,
      "grad_norm": 0.5198990702629089,
      "learning_rate": 1.1866581141757537e-06,
      "loss": 1.3744,
      "step": 3430
    },
    {
      "epoch": 2.9783549783549783,
      "grad_norm": 0.4826680123806,
      "learning_rate": 8.659397049390636e-07,
      "loss": 1.3278,
      "step": 3440
    },
    {
      "epoch": 2.987012987012987,
      "grad_norm": 0.5612112283706665,
      "learning_rate": 5.452212957023733e-07,
      "loss": 1.3663,
      "step": 3450
    },
    {
      "epoch": 2.987012987012987,
      "eval_loss": 1.3869423866271973,
      "eval_runtime": 7.5995,
      "eval_samples_per_second": 15.264,
      "eval_steps_per_second": 15.264,
      "step": 3450
    },
    {
      "epoch": 2.995670995670996,
      "grad_norm": 0.5130652189254761,
      "learning_rate": 2.2450288646568314e-07,
      "loss": 1.3678,
      "step": 3460
    }
  ],
  "logging_steps": 10,
  "max_steps": 3465,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 150,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.870615814733824e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}