{
  "best_metric": 0.8681402802467346,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.015182570409170272,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.591285204585137e-05,
      "grad_norm": 4.00889778137207,
      "learning_rate": 1.004e-05,
      "loss": 3.3766,
      "step": 1
    },
    {
      "epoch": 7.591285204585137e-05,
      "eval_loss": 3.8744077682495117,
      "eval_runtime": 240.3929,
      "eval_samples_per_second": 23.075,
      "eval_steps_per_second": 5.77,
      "step": 1
    },
    {
      "epoch": 0.00015182570409170274,
      "grad_norm": 4.259544849395752,
      "learning_rate": 2.008e-05,
      "loss": 3.129,
      "step": 2
    },
    {
      "epoch": 0.0002277385561375541,
      "grad_norm": 4.009559631347656,
      "learning_rate": 3.012e-05,
      "loss": 3.5625,
      "step": 3
    },
    {
      "epoch": 0.0003036514081834055,
      "grad_norm": 3.93902587890625,
      "learning_rate": 4.016e-05,
      "loss": 3.2738,
      "step": 4
    },
    {
      "epoch": 0.0003795642602292568,
      "grad_norm": 4.684957981109619,
      "learning_rate": 5.02e-05,
      "loss": 3.4879,
      "step": 5
    },
    {
      "epoch": 0.0004554771122751082,
      "grad_norm": 4.2233781814575195,
      "learning_rate": 6.024e-05,
      "loss": 3.6261,
      "step": 6
    },
    {
      "epoch": 0.0005313899643209595,
      "grad_norm": 4.0557332038879395,
      "learning_rate": 7.028e-05,
      "loss": 3.4864,
      "step": 7
    },
    {
      "epoch": 0.000607302816366811,
      "grad_norm": 4.355313777923584,
      "learning_rate": 8.032e-05,
      "loss": 2.8283,
      "step": 8
    },
    {
      "epoch": 0.0006832156684126623,
      "grad_norm": 4.009000301361084,
      "learning_rate": 9.036000000000001e-05,
      "loss": 3.1648,
      "step": 9
    },
    {
      "epoch": 0.0007591285204585136,
      "grad_norm": 3.8348472118377686,
      "learning_rate": 0.0001004,
      "loss": 2.9517,
      "step": 10
    },
    {
      "epoch": 0.0008350413725043649,
      "grad_norm": 7.264204978942871,
      "learning_rate": 9.987157894736842e-05,
      "loss": 2.7876,
      "step": 11
    },
    {
      "epoch": 0.0009109542245502164,
      "grad_norm": 8.179417610168457,
      "learning_rate": 9.934315789473684e-05,
      "loss": 1.9061,
      "step": 12
    },
    {
      "epoch": 0.0009868670765960678,
      "grad_norm": 6.091889381408691,
      "learning_rate": 9.881473684210525e-05,
      "loss": 1.6486,
      "step": 13
    },
    {
      "epoch": 0.001062779928641919,
      "grad_norm": 5.305070877075195,
      "learning_rate": 9.828631578947369e-05,
      "loss": 2.1729,
      "step": 14
    },
    {
      "epoch": 0.0011386927806877705,
      "grad_norm": 6.4168548583984375,
      "learning_rate": 9.77578947368421e-05,
      "loss": 1.7497,
      "step": 15
    },
    {
      "epoch": 0.001214605632733622,
      "grad_norm": 5.889248847961426,
      "learning_rate": 9.722947368421052e-05,
      "loss": 1.6712,
      "step": 16
    },
    {
      "epoch": 0.0012905184847794731,
      "grad_norm": 5.305861949920654,
      "learning_rate": 9.670105263157895e-05,
      "loss": 1.71,
      "step": 17
    },
    {
      "epoch": 0.0013664313368253246,
      "grad_norm": 5.730749607086182,
      "learning_rate": 9.617263157894737e-05,
      "loss": 1.5306,
      "step": 18
    },
    {
      "epoch": 0.001442344188871176,
      "grad_norm": 8.906538963317871,
      "learning_rate": 9.564421052631579e-05,
      "loss": 2.0866,
      "step": 19
    },
    {
      "epoch": 0.0015182570409170272,
      "grad_norm": 6.357343673706055,
      "learning_rate": 9.511578947368421e-05,
      "loss": 1.9055,
      "step": 20
    },
    {
      "epoch": 0.0015941698929628787,
      "grad_norm": 4.676600456237793,
      "learning_rate": 9.458736842105264e-05,
      "loss": 1.3255,
      "step": 21
    },
    {
      "epoch": 0.0016700827450087299,
      "grad_norm": 5.27098274230957,
      "learning_rate": 9.405894736842106e-05,
      "loss": 1.4943,
      "step": 22
    },
    {
      "epoch": 0.0017459955970545813,
      "grad_norm": 4.284830093383789,
      "learning_rate": 9.353052631578947e-05,
      "loss": 1.2089,
      "step": 23
    },
    {
      "epoch": 0.0018219084491004327,
      "grad_norm": 3.9922897815704346,
      "learning_rate": 9.300210526315789e-05,
      "loss": 1.2562,
      "step": 24
    },
    {
      "epoch": 0.001897821301146284,
      "grad_norm": 4.029862880706787,
      "learning_rate": 9.247368421052631e-05,
      "loss": 1.504,
      "step": 25
    },
    {
      "epoch": 0.0019737341531921356,
      "grad_norm": 3.5687670707702637,
      "learning_rate": 9.194526315789473e-05,
      "loss": 1.4237,
      "step": 26
    },
    {
      "epoch": 0.0020496470052379866,
      "grad_norm": 3.2173025608062744,
      "learning_rate": 9.141684210526316e-05,
      "loss": 1.0595,
      "step": 27
    },
    {
      "epoch": 0.002125559857283838,
      "grad_norm": 3.408003568649292,
      "learning_rate": 9.088842105263158e-05,
      "loss": 0.7801,
      "step": 28
    },
    {
      "epoch": 0.0022014727093296895,
      "grad_norm": 3.468625068664551,
      "learning_rate": 9.036000000000001e-05,
      "loss": 1.2455,
      "step": 29
    },
    {
      "epoch": 0.002277385561375541,
      "grad_norm": 4.7892279624938965,
      "learning_rate": 8.983157894736843e-05,
      "loss": 1.3866,
      "step": 30
    },
    {
      "epoch": 0.0023532984134213924,
      "grad_norm": 3.3346621990203857,
      "learning_rate": 8.930315789473684e-05,
      "loss": 1.2134,
      "step": 31
    },
    {
      "epoch": 0.002429211265467244,
      "grad_norm": 3.797645092010498,
      "learning_rate": 8.877473684210526e-05,
      "loss": 1.3581,
      "step": 32
    },
    {
      "epoch": 0.002505124117513095,
      "grad_norm": 3.729444980621338,
      "learning_rate": 8.824631578947368e-05,
      "loss": 1.1622,
      "step": 33
    },
    {
      "epoch": 0.0025810369695589462,
      "grad_norm": 3.769681215286255,
      "learning_rate": 8.771789473684211e-05,
      "loss": 0.9735,
      "step": 34
    },
    {
      "epoch": 0.0026569498216047977,
      "grad_norm": 4.146418571472168,
      "learning_rate": 8.718947368421053e-05,
      "loss": 0.8318,
      "step": 35
    },
    {
      "epoch": 0.002732862673650649,
      "grad_norm": 3.002995491027832,
      "learning_rate": 8.666105263157895e-05,
      "loss": 0.7628,
      "step": 36
    },
    {
      "epoch": 0.0028087755256965006,
      "grad_norm": 3.8767268657684326,
      "learning_rate": 8.613263157894737e-05,
      "loss": 1.1052,
      "step": 37
    },
    {
      "epoch": 0.002884688377742352,
      "grad_norm": 5.0641069412231445,
      "learning_rate": 8.560421052631578e-05,
      "loss": 0.932,
      "step": 38
    },
    {
      "epoch": 0.002960601229788203,
      "grad_norm": 3.3671984672546387,
      "learning_rate": 8.50757894736842e-05,
      "loss": 0.9676,
      "step": 39
    },
    {
      "epoch": 0.0030365140818340544,
      "grad_norm": 4.778345584869385,
      "learning_rate": 8.454736842105263e-05,
      "loss": 0.9301,
      "step": 40
    },
    {
      "epoch": 0.003112426933879906,
      "grad_norm": 4.1439595222473145,
      "learning_rate": 8.401894736842106e-05,
      "loss": 0.8163,
      "step": 41
    },
    {
      "epoch": 0.0031883397859257573,
      "grad_norm": 2.6622302532196045,
      "learning_rate": 8.349052631578948e-05,
      "loss": 0.8257,
      "step": 42
    },
    {
      "epoch": 0.0032642526379716087,
      "grad_norm": 3.152009963989258,
      "learning_rate": 8.29621052631579e-05,
      "loss": 0.8255,
      "step": 43
    },
    {
      "epoch": 0.0033401654900174597,
      "grad_norm": 2.4167747497558594,
      "learning_rate": 8.243368421052632e-05,
      "loss": 0.7538,
      "step": 44
    },
    {
      "epoch": 0.003416078342063311,
      "grad_norm": 3.019895553588867,
      "learning_rate": 8.190526315789474e-05,
      "loss": 0.952,
      "step": 45
    },
    {
      "epoch": 0.0034919911941091626,
      "grad_norm": 3.5709264278411865,
      "learning_rate": 8.137684210526315e-05,
      "loss": 0.7851,
      "step": 46
    },
    {
      "epoch": 0.003567904046155014,
      "grad_norm": 3.9194111824035645,
      "learning_rate": 8.084842105263157e-05,
      "loss": 0.8724,
      "step": 47
    },
    {
      "epoch": 0.0036438168982008655,
      "grad_norm": 4.6772894859313965,
      "learning_rate": 8.032e-05,
      "loss": 0.8268,
      "step": 48
    },
    {
      "epoch": 0.003719729750246717,
      "grad_norm": 3.5549869537353516,
      "learning_rate": 7.979157894736842e-05,
      "loss": 0.7529,
      "step": 49
    },
    {
      "epoch": 0.003795642602292568,
      "grad_norm": 2.6311495304107666,
      "learning_rate": 7.926315789473684e-05,
      "loss": 0.7944,
      "step": 50
    },
    {
      "epoch": 0.003795642602292568,
      "eval_loss": 1.2532055377960205,
      "eval_runtime": 242.1049,
      "eval_samples_per_second": 22.912,
      "eval_steps_per_second": 5.729,
      "step": 50
    },
    {
      "epoch": 0.0038715554543384194,
      "grad_norm": 3.332703113555908,
      "learning_rate": 7.873473684210526e-05,
      "loss": 1.4012,
      "step": 51
    },
    {
      "epoch": 0.003947468306384271,
      "grad_norm": 3.9371657371520996,
      "learning_rate": 7.820631578947369e-05,
      "loss": 2.001,
      "step": 52
    },
    {
      "epoch": 0.004023381158430122,
      "grad_norm": 2.853745460510254,
      "learning_rate": 7.76778947368421e-05,
      "loss": 1.3783,
      "step": 53
    },
    {
      "epoch": 0.004099294010475973,
      "grad_norm": 3.1998298168182373,
      "learning_rate": 7.714947368421052e-05,
      "loss": 1.8504,
      "step": 54
    },
    {
      "epoch": 0.004175206862521825,
      "grad_norm": 3.126289129257202,
      "learning_rate": 7.662105263157896e-05,
      "loss": 1.862,
      "step": 55
    },
    {
      "epoch": 0.004251119714567676,
      "grad_norm": 2.4768309593200684,
      "learning_rate": 7.609263157894737e-05,
      "loss": 1.3451,
      "step": 56
    },
    {
      "epoch": 0.0043270325666135276,
      "grad_norm": 2.919741630554199,
      "learning_rate": 7.556421052631579e-05,
      "loss": 1.4162,
      "step": 57
    },
    {
      "epoch": 0.004402945418659379,
      "grad_norm": 2.9070191383361816,
      "learning_rate": 7.503578947368421e-05,
      "loss": 1.3421,
      "step": 58
    },
    {
      "epoch": 0.00447885827070523,
      "grad_norm": 3.0319571495056152,
      "learning_rate": 7.450736842105263e-05,
      "loss": 1.7147,
      "step": 59
    },
    {
      "epoch": 0.004554771122751082,
      "grad_norm": 3.456721544265747,
      "learning_rate": 7.397894736842105e-05,
      "loss": 1.2985,
      "step": 60
    },
    {
      "epoch": 0.004630683974796933,
      "grad_norm": 3.245173215866089,
      "learning_rate": 7.345052631578948e-05,
      "loss": 1.7002,
      "step": 61
    },
    {
      "epoch": 0.004706596826842785,
      "grad_norm": 2.7266035079956055,
      "learning_rate": 7.29221052631579e-05,
      "loss": 1.527,
      "step": 62
    },
    {
      "epoch": 0.004782509678888636,
      "grad_norm": 3.55993914604187,
      "learning_rate": 7.239368421052631e-05,
      "loss": 1.9147,
      "step": 63
    },
    {
      "epoch": 0.004858422530934488,
      "grad_norm": 2.028764009475708,
      "learning_rate": 7.186526315789474e-05,
      "loss": 1.0744,
      "step": 64
    },
    {
      "epoch": 0.004934335382980338,
      "grad_norm": 3.0651049613952637,
      "learning_rate": 7.133684210526316e-05,
      "loss": 1.1072,
      "step": 65
    },
    {
      "epoch": 0.00501024823502619,
      "grad_norm": 2.8773818016052246,
      "learning_rate": 7.080842105263158e-05,
      "loss": 1.3428,
      "step": 66
    },
    {
      "epoch": 0.005086161087072041,
      "grad_norm": 2.439342737197876,
      "learning_rate": 7.028e-05,
      "loss": 0.9611,
      "step": 67
    },
    {
      "epoch": 0.0051620739391178925,
      "grad_norm": 3.0564000606536865,
      "learning_rate": 6.975157894736843e-05,
      "loss": 1.1857,
      "step": 68
    },
    {
      "epoch": 0.005237986791163744,
      "grad_norm": 5.345979690551758,
      "learning_rate": 6.922315789473685e-05,
      "loss": 1.4022,
      "step": 69
    },
    {
      "epoch": 0.005313899643209595,
      "grad_norm": 2.436023712158203,
      "learning_rate": 6.869473684210527e-05,
      "loss": 0.9688,
      "step": 70
    },
    {
      "epoch": 0.005389812495255447,
      "grad_norm": 3.2191972732543945,
      "learning_rate": 6.816631578947368e-05,
      "loss": 1.2126,
      "step": 71
    },
    {
      "epoch": 0.005465725347301298,
      "grad_norm": 1.942346215248108,
      "learning_rate": 6.76378947368421e-05,
      "loss": 0.8721,
      "step": 72
    },
    {
      "epoch": 0.00554163819934715,
      "grad_norm": 4.746232509613037,
      "learning_rate": 6.710947368421052e-05,
      "loss": 1.392,
      "step": 73
    },
    {
      "epoch": 0.005617551051393001,
      "grad_norm": 2.850257158279419,
      "learning_rate": 6.658105263157894e-05,
      "loss": 1.1243,
      "step": 74
    },
    {
      "epoch": 0.0056934639034388525,
      "grad_norm": 2.983518362045288,
      "learning_rate": 6.605263157894737e-05,
      "loss": 1.1275,
      "step": 75
    },
    {
      "epoch": 0.005769376755484704,
      "grad_norm": 2.9279556274414062,
      "learning_rate": 6.55242105263158e-05,
      "loss": 1.5262,
      "step": 76
    },
    {
      "epoch": 0.0058452896075305546,
      "grad_norm": 6.875275135040283,
      "learning_rate": 6.499578947368422e-05,
      "loss": 0.8056,
      "step": 77
    },
    {
      "epoch": 0.005921202459576406,
      "grad_norm": 2.7808749675750732,
      "learning_rate": 6.446736842105264e-05,
      "loss": 1.097,
      "step": 78
    },
    {
      "epoch": 0.005997115311622257,
      "grad_norm": 6.791175842285156,
      "learning_rate": 6.393894736842105e-05,
      "loss": 0.7137,
      "step": 79
    },
    {
      "epoch": 0.006073028163668109,
      "grad_norm": 3.0166051387786865,
      "learning_rate": 6.341052631578947e-05,
      "loss": 1.3371,
      "step": 80
    },
    {
      "epoch": 0.00614894101571396,
      "grad_norm": 5.060026168823242,
      "learning_rate": 6.288210526315789e-05,
      "loss": 0.8866,
      "step": 81
    },
    {
      "epoch": 0.006224853867759812,
      "grad_norm": 4.755941390991211,
      "learning_rate": 6.235368421052632e-05,
      "loss": 1.1797,
      "step": 82
    },
    {
      "epoch": 0.006300766719805663,
      "grad_norm": 2.5491960048675537,
      "learning_rate": 6.182526315789474e-05,
      "loss": 0.7077,
      "step": 83
    },
    {
      "epoch": 0.006376679571851515,
      "grad_norm": 2.4443137645721436,
      "learning_rate": 6.129684210526316e-05,
      "loss": 0.8194,
      "step": 84
    },
    {
      "epoch": 0.006452592423897366,
      "grad_norm": 2.4709208011627197,
      "learning_rate": 6.076842105263158e-05,
      "loss": 0.8501,
      "step": 85
    },
    {
      "epoch": 0.0065285052759432175,
      "grad_norm": 2.1877200603485107,
      "learning_rate": 6.024e-05,
      "loss": 0.768,
      "step": 86
    },
    {
      "epoch": 0.006604418127989069,
      "grad_norm": 3.9589478969573975,
      "learning_rate": 5.971157894736842e-05,
      "loss": 0.8284,
      "step": 87
    },
    {
      "epoch": 0.0066803309800349195,
      "grad_norm": 2.8392932415008545,
      "learning_rate": 5.9183157894736835e-05,
      "loss": 0.7405,
      "step": 88
    },
    {
      "epoch": 0.006756243832080771,
      "grad_norm": 4.0319318771362305,
      "learning_rate": 5.8654736842105267e-05,
      "loss": 0.9588,
      "step": 89
    },
    {
      "epoch": 0.006832156684126622,
      "grad_norm": 4.04771614074707,
      "learning_rate": 5.8126315789473684e-05,
      "loss": 1.0062,
      "step": 90
    },
    {
      "epoch": 0.006908069536172474,
      "grad_norm": 2.8250598907470703,
      "learning_rate": 5.759789473684211e-05,
      "loss": 0.7596,
      "step": 91
    },
    {
      "epoch": 0.006983982388218325,
      "grad_norm": 2.2574899196624756,
      "learning_rate": 5.706947368421053e-05,
      "loss": 0.6135,
      "step": 92
    },
    {
      "epoch": 0.007059895240264177,
      "grad_norm": 2.3029751777648926,
      "learning_rate": 5.6541052631578945e-05,
      "loss": 0.9518,
      "step": 93
    },
    {
      "epoch": 0.007135808092310028,
      "grad_norm": 5.060135364532471,
      "learning_rate": 5.601263157894736e-05,
      "loss": 1.0503,
      "step": 94
    },
    {
      "epoch": 0.0072117209443558795,
      "grad_norm": 2.9369940757751465,
      "learning_rate": 5.5484210526315794e-05,
      "loss": 0.7239,
      "step": 95
    },
    {
      "epoch": 0.007287633796401731,
      "grad_norm": 1.8883877992630005,
      "learning_rate": 5.495578947368421e-05,
      "loss": 0.6678,
      "step": 96
    },
    {
      "epoch": 0.007363546648447582,
      "grad_norm": 2.149679660797119,
      "learning_rate": 5.442736842105264e-05,
      "loss": 0.7075,
      "step": 97
    },
    {
      "epoch": 0.007439459500493434,
      "grad_norm": 3.17543888092041,
      "learning_rate": 5.3898947368421055e-05,
      "loss": 0.8025,
      "step": 98
    },
    {
      "epoch": 0.007515372352539285,
      "grad_norm": 4.000500679016113,
      "learning_rate": 5.337052631578947e-05,
      "loss": 0.742,
      "step": 99
    },
    {
      "epoch": 0.007591285204585136,
      "grad_norm": 2.3594398498535156,
      "learning_rate": 5.284210526315789e-05,
      "loss": 0.6751,
      "step": 100
    },
    {
      "epoch": 0.007591285204585136,
      "eval_loss": 1.0612136125564575,
      "eval_runtime": 241.2405,
      "eval_samples_per_second": 22.994,
      "eval_steps_per_second": 5.749,
      "step": 100
    },
    {
      "epoch": 0.007667198056630987,
      "grad_norm": 3.0699315071105957,
      "learning_rate": 5.231368421052631e-05,
      "loss": 1.173,
      "step": 101
    },
    {
      "epoch": 0.007743110908676839,
      "grad_norm": 4.866107940673828,
      "learning_rate": 5.178526315789474e-05,
      "loss": 1.7382,
      "step": 102
    },
    {
      "epoch": 0.007819023760722691,
      "grad_norm": 4.889467239379883,
      "learning_rate": 5.1256842105263165e-05,
      "loss": 1.4133,
      "step": 103
    },
    {
      "epoch": 0.007894936612768542,
      "grad_norm": 4.676548480987549,
      "learning_rate": 5.072842105263158e-05,
      "loss": 1.406,
      "step": 104
    },
    {
      "epoch": 0.007970849464814394,
      "grad_norm": 2.993145227432251,
      "learning_rate": 5.02e-05,
      "loss": 1.1335,
      "step": 105
    },
    {
      "epoch": 0.008046762316860244,
      "grad_norm": 2.76796555519104,
      "learning_rate": 4.967157894736842e-05,
      "loss": 1.154,
      "step": 106
    },
    {
      "epoch": 0.008122675168906095,
      "grad_norm": 3.4943559169769287,
      "learning_rate": 4.914315789473684e-05,
      "loss": 1.1565,
      "step": 107
    },
    {
      "epoch": 0.008198588020951946,
      "grad_norm": 3.7888946533203125,
      "learning_rate": 4.861473684210526e-05,
      "loss": 0.9767,
      "step": 108
    },
    {
      "epoch": 0.008274500872997798,
      "grad_norm": 3.349473237991333,
      "learning_rate": 4.8086315789473686e-05,
      "loss": 1.0981,
      "step": 109
    },
    {
      "epoch": 0.00835041372504365,
      "grad_norm": 2.571047782897949,
      "learning_rate": 4.7557894736842104e-05,
      "loss": 1.3569,
      "step": 110
    },
    {
      "epoch": 0.0084263265770895,
      "grad_norm": 3.6991724967956543,
      "learning_rate": 4.702947368421053e-05,
      "loss": 1.2374,
      "step": 111
    },
    {
      "epoch": 0.008502239429135352,
      "grad_norm": 3.694169282913208,
      "learning_rate": 4.6501052631578946e-05,
      "loss": 1.4054,
      "step": 112
    },
    {
      "epoch": 0.008578152281181204,
      "grad_norm": 3.4294185638427734,
      "learning_rate": 4.5972631578947364e-05,
      "loss": 1.5067,
      "step": 113
    },
    {
      "epoch": 0.008654065133227055,
      "grad_norm": 2.6580145359039307,
      "learning_rate": 4.544421052631579e-05,
      "loss": 0.9726,
      "step": 114
    },
    {
      "epoch": 0.008729977985272907,
      "grad_norm": 2.1301791667938232,
      "learning_rate": 4.4915789473684213e-05,
      "loss": 0.9786,
      "step": 115
    },
    {
      "epoch": 0.008805890837318758,
      "grad_norm": 2.001025438308716,
      "learning_rate": 4.438736842105263e-05,
      "loss": 0.6805,
      "step": 116
    },
    {
      "epoch": 0.00888180368936461,
      "grad_norm": 2.077392816543579,
      "learning_rate": 4.3858947368421056e-05,
      "loss": 0.8329,
      "step": 117
    },
    {
      "epoch": 0.00895771654141046,
      "grad_norm": 2.3383848667144775,
      "learning_rate": 4.3330526315789474e-05,
      "loss": 0.9665,
      "step": 118
    },
    {
      "epoch": 0.009033629393456312,
      "grad_norm": 2.4571051597595215,
      "learning_rate": 4.280210526315789e-05,
      "loss": 1.2276,
      "step": 119
    },
    {
      "epoch": 0.009109542245502164,
      "grad_norm": 1.6125465631484985,
      "learning_rate": 4.2273684210526317e-05,
      "loss": 0.6786,
      "step": 120
    },
    {
      "epoch": 0.009185455097548015,
      "grad_norm": 2.041332960128784,
      "learning_rate": 4.174526315789474e-05,
      "loss": 0.9306,
      "step": 121
    },
    {
      "epoch": 0.009261367949593867,
      "grad_norm": 2.873103380203247,
      "learning_rate": 4.121684210526316e-05,
      "loss": 1.0511,
      "step": 122
    },
    {
      "epoch": 0.009337280801639718,
      "grad_norm": 3.1347708702087402,
      "learning_rate": 4.068842105263158e-05,
      "loss": 0.9377,
      "step": 123
    },
    {
      "epoch": 0.00941319365368557,
      "grad_norm": 1.9942682981491089,
      "learning_rate": 4.016e-05,
      "loss": 0.8217,
      "step": 124
    },
    {
      "epoch": 0.009489106505731421,
      "grad_norm": 3.970079183578491,
      "learning_rate": 3.963157894736842e-05,
      "loss": 1.3267,
      "step": 125
    },
    {
      "epoch": 0.009565019357777272,
      "grad_norm": 2.6041419506073,
      "learning_rate": 3.9103157894736844e-05,
      "loss": 1.034,
      "step": 126
    },
    {
      "epoch": 0.009640932209823124,
      "grad_norm": 2.5443952083587646,
      "learning_rate": 3.857473684210526e-05,
      "loss": 0.8037,
      "step": 127
    },
    {
      "epoch": 0.009716845061868975,
      "grad_norm": 2.3711419105529785,
      "learning_rate": 3.804631578947369e-05,
      "loss": 1.0528,
      "step": 128
    },
    {
      "epoch": 0.009792757913914825,
      "grad_norm": 1.946669101715088,
      "learning_rate": 3.7517894736842105e-05,
      "loss": 0.5657,
      "step": 129
    },
    {
      "epoch": 0.009868670765960676,
      "grad_norm": 4.314067363739014,
      "learning_rate": 3.698947368421052e-05,
      "loss": 0.9075,
      "step": 130
    },
    {
      "epoch": 0.009944583618006528,
      "grad_norm": 2.827471971511841,
      "learning_rate": 3.646105263157895e-05,
      "loss": 0.9609,
      "step": 131
    },
    {
      "epoch": 0.01002049647005238,
      "grad_norm": 2.264293909072876,
      "learning_rate": 3.593263157894737e-05,
      "loss": 0.8314,
      "step": 132
    },
    {
      "epoch": 0.01009640932209823,
      "grad_norm": 2.1921863555908203,
      "learning_rate": 3.540421052631579e-05,
      "loss": 0.8398,
      "step": 133
    },
    {
      "epoch": 0.010172322174144082,
      "grad_norm": 2.1233198642730713,
      "learning_rate": 3.4875789473684215e-05,
      "loss": 0.7514,
      "step": 134
    },
    {
      "epoch": 0.010248235026189934,
      "grad_norm": 2.6817049980163574,
      "learning_rate": 3.434736842105263e-05,
      "loss": 0.6174,
      "step": 135
    },
    {
      "epoch": 0.010324147878235785,
      "grad_norm": 1.518689513206482,
      "learning_rate": 3.381894736842105e-05,
      "loss": 0.6519,
      "step": 136
    },
    {
      "epoch": 0.010400060730281636,
      "grad_norm": 2.2906270027160645,
      "learning_rate": 3.329052631578947e-05,
      "loss": 0.6826,
      "step": 137
    },
    {
      "epoch": 0.010475973582327488,
      "grad_norm": 2.211939573287964,
      "learning_rate": 3.27621052631579e-05,
      "loss": 0.8501,
      "step": 138
    },
    {
      "epoch": 0.01055188643437334,
      "grad_norm": 4.645651340484619,
      "learning_rate": 3.223368421052632e-05,
      "loss": 0.6646,
      "step": 139
    },
    {
      "epoch": 0.01062779928641919,
      "grad_norm": 4.8494744300842285,
      "learning_rate": 3.1705263157894736e-05,
      "loss": 0.8638,
      "step": 140
    },
    {
      "epoch": 0.010703712138465042,
      "grad_norm": 1.5980870723724365,
      "learning_rate": 3.117684210526316e-05,
      "loss": 0.5841,
      "step": 141
    },
    {
      "epoch": 0.010779624990510894,
      "grad_norm": 1.9709309339523315,
      "learning_rate": 3.064842105263158e-05,
      "loss": 0.6271,
      "step": 142
    },
    {
      "epoch": 0.010855537842556745,
      "grad_norm": 2.970513105392456,
      "learning_rate": 3.012e-05,
      "loss": 0.9551,
      "step": 143
    },
    {
      "epoch": 0.010931450694602596,
      "grad_norm": 2.2817845344543457,
      "learning_rate": 2.9591578947368418e-05,
      "loss": 0.7009,
      "step": 144
    },
    {
      "epoch": 0.011007363546648448,
      "grad_norm": 2.4556617736816406,
      "learning_rate": 2.9063157894736842e-05,
      "loss": 0.7365,
      "step": 145
    },
    {
      "epoch": 0.0110832763986943,
      "grad_norm": 1.3741040229797363,
      "learning_rate": 2.8534736842105264e-05,
      "loss": 0.6872,
      "step": 146
    },
    {
      "epoch": 0.01115918925074015,
      "grad_norm": 1.5213168859481812,
      "learning_rate": 2.800631578947368e-05,
      "loss": 0.5938,
      "step": 147
    },
    {
      "epoch": 0.011235102102786002,
      "grad_norm": 1.7388572692871094,
      "learning_rate": 2.7477894736842106e-05,
      "loss": 0.639,
      "step": 148
    },
    {
      "epoch": 0.011311014954831854,
      "grad_norm": 1.9065625667572021,
      "learning_rate": 2.6949473684210527e-05,
      "loss": 0.6217,
      "step": 149
    },
    {
      "epoch": 0.011386927806877705,
      "grad_norm": 2.9357759952545166,
      "learning_rate": 2.6421052631578945e-05,
      "loss": 0.8997,
      "step": 150
    },
    {
      "epoch": 0.011386927806877705,
      "eval_loss": 0.9495816826820374,
      "eval_runtime": 241.9389,
      "eval_samples_per_second": 22.927,
      "eval_steps_per_second": 5.733,
      "step": 150
    },
    {
      "epoch": 0.011462840658923557,
      "grad_norm": 3.5921010971069336,
      "learning_rate": 2.589263157894737e-05,
      "loss": 1.2644,
      "step": 151
    },
    {
      "epoch": 0.011538753510969408,
      "grad_norm": 3.2092552185058594,
      "learning_rate": 2.536421052631579e-05,
      "loss": 1.2191,
      "step": 152
    },
    {
      "epoch": 0.011614666363015258,
      "grad_norm": 2.973201274871826,
      "learning_rate": 2.483578947368421e-05,
      "loss": 1.1479,
      "step": 153
    },
    {
      "epoch": 0.011690579215061109,
      "grad_norm": 3.493716239929199,
      "learning_rate": 2.430736842105263e-05,
      "loss": 1.1697,
      "step": 154
    },
    {
      "epoch": 0.01176649206710696,
      "grad_norm": 4.421971321105957,
      "learning_rate": 2.3778947368421052e-05,
      "loss": 1.5826,
      "step": 155
    },
    {
      "epoch": 0.011842404919152812,
      "grad_norm": 2.4853765964508057,
      "learning_rate": 2.3250526315789473e-05,
      "loss": 1.1794,
      "step": 156
    },
    {
      "epoch": 0.011918317771198663,
      "grad_norm": 2.4261560440063477,
      "learning_rate": 2.2722105263157894e-05,
      "loss": 1.292,
      "step": 157
    },
    {
      "epoch": 0.011994230623244515,
      "grad_norm": 5.322474956512451,
      "learning_rate": 2.2193684210526316e-05,
      "loss": 1.646,
      "step": 158
    },
    {
      "epoch": 0.012070143475290366,
      "grad_norm": 3.1633529663085938,
      "learning_rate": 2.1665263157894737e-05,
      "loss": 1.1791,
      "step": 159
    },
    {
      "epoch": 0.012146056327336218,
      "grad_norm": 2.1817359924316406,
      "learning_rate": 2.1136842105263158e-05,
      "loss": 1.0074,
      "step": 160
    },
    {
      "epoch": 0.01222196917938207,
      "grad_norm": 3.437952995300293,
      "learning_rate": 2.060842105263158e-05,
      "loss": 0.7742,
      "step": 161
    },
    {
      "epoch": 0.01229788203142792,
      "grad_norm": 2.556812286376953,
      "learning_rate": 2.008e-05,
      "loss": 1.1099,
      "step": 162
    },
    {
      "epoch": 0.012373794883473772,
      "grad_norm": 2.865772247314453,
      "learning_rate": 1.9551578947368422e-05,
      "loss": 0.9289,
      "step": 163
    },
    {
      "epoch": 0.012449707735519623,
      "grad_norm": 2.2131378650665283,
      "learning_rate": 1.9023157894736843e-05,
      "loss": 0.8616,
      "step": 164
    },
    {
      "epoch": 0.012525620587565475,
      "grad_norm": 3.6415939331054688,
      "learning_rate": 1.849473684210526e-05,
      "loss": 1.019,
      "step": 165
    },
    {
      "epoch": 0.012601533439611326,
      "grad_norm": 2.7384023666381836,
      "learning_rate": 1.7966315789473686e-05,
      "loss": 1.1348,
      "step": 166
    },
    {
      "epoch": 0.012677446291657178,
      "grad_norm": 2.291468620300293,
      "learning_rate": 1.7437894736842107e-05,
      "loss": 0.6625,
      "step": 167
    },
    {
      "epoch": 0.01275335914370303,
      "grad_norm": 2.5546927452087402,
      "learning_rate": 1.6909473684210525e-05,
      "loss": 1.1038,
      "step": 168
    },
    {
      "epoch": 0.01282927199574888,
      "grad_norm": 2.0928328037261963,
      "learning_rate": 1.638105263157895e-05,
      "loss": 1.008,
      "step": 169
    },
    {
      "epoch": 0.012905184847794732,
      "grad_norm": 3.695002794265747,
      "learning_rate": 1.5852631578947368e-05,
      "loss": 1.49,
      "step": 170
    },
    {
      "epoch": 0.012981097699840584,
      "grad_norm": 1.8197062015533447,
      "learning_rate": 1.532421052631579e-05,
      "loss": 0.7948,
      "step": 171
    },
    {
      "epoch": 0.013057010551886435,
      "grad_norm": 2.0145041942596436,
      "learning_rate": 1.4795789473684209e-05,
      "loss": 0.6828,
      "step": 172
    },
    {
      "epoch": 0.013132923403932286,
      "grad_norm": 2.345130681991577,
      "learning_rate": 1.4267368421052632e-05,
      "loss": 0.847,
      "step": 173
    },
    {
      "epoch": 0.013208836255978138,
      "grad_norm": 2.0856807231903076,
      "learning_rate": 1.3738947368421053e-05,
      "loss": 0.7226,
      "step": 174
    },
    {
      "epoch": 0.01328474910802399,
      "grad_norm": 2.411574363708496,
      "learning_rate": 1.3210526315789473e-05,
      "loss": 0.8916,
      "step": 175
    },
    {
      "epoch": 0.013360661960069839,
      "grad_norm": 2.695683240890503,
      "learning_rate": 1.2682105263157896e-05,
      "loss": 1.1231,
      "step": 176
    },
    {
      "epoch": 0.01343657481211569,
      "grad_norm": 1.4786357879638672,
      "learning_rate": 1.2153684210526315e-05,
      "loss": 0.5941,
      "step": 177
    },
    {
      "epoch": 0.013512487664161542,
      "grad_norm": 4.206338405609131,
      "learning_rate": 1.1625263157894737e-05,
      "loss": 1.0503,
      "step": 178
    },
    {
      "epoch": 0.013588400516207393,
      "grad_norm": 2.2319929599761963,
      "learning_rate": 1.1096842105263158e-05,
      "loss": 0.9548,
      "step": 179
    },
    {
      "epoch": 0.013664313368253245,
      "grad_norm": 2.599853754043579,
      "learning_rate": 1.0568421052631579e-05,
      "loss": 1.1055,
      "step": 180
    },
    {
      "epoch": 0.013740226220299096,
      "grad_norm": 3.016218900680542,
      "learning_rate": 1.004e-05,
      "loss": 0.9452,
      "step": 181
    },
    {
      "epoch": 0.013816139072344948,
      "grad_norm": 1.2228299379348755,
      "learning_rate": 9.511578947368422e-06,
      "loss": 0.5985,
      "step": 182
    },
    {
      "epoch": 0.013892051924390799,
      "grad_norm": 1.9623208045959473,
      "learning_rate": 8.983157894736843e-06,
      "loss": 0.6597,
      "step": 183
    },
    {
      "epoch": 0.01396796477643665,
      "grad_norm": 1.9517189264297485,
      "learning_rate": 8.454736842105263e-06,
      "loss": 0.8533,
      "step": 184
    },
    {
      "epoch": 0.014043877628482502,
      "grad_norm": 2.120260715484619,
      "learning_rate": 7.926315789473684e-06,
      "loss": 0.6754,
      "step": 185
    },
    {
      "epoch": 0.014119790480528353,
      "grad_norm": 1.2935106754302979,
      "learning_rate": 7.397894736842104e-06,
      "loss": 0.6595,
      "step": 186
    },
    {
      "epoch": 0.014195703332574205,
      "grad_norm": 1.396093487739563,
      "learning_rate": 6.8694736842105265e-06,
      "loss": 0.5343,
      "step": 187
    },
    {
      "epoch": 0.014271616184620056,
      "grad_norm": 1.5129783153533936,
      "learning_rate": 6.341052631578948e-06,
      "loss": 0.6226,
      "step": 188
    },
    {
      "epoch": 0.014347529036665908,
      "grad_norm": 1.9444491863250732,
      "learning_rate": 5.812631578947368e-06,
      "loss": 0.5968,
      "step": 189
    },
    {
      "epoch": 0.014423441888711759,
      "grad_norm": 1.6097540855407715,
      "learning_rate": 5.2842105263157896e-06,
      "loss": 0.6399,
      "step": 190
    },
    {
      "epoch": 0.01449935474075761,
      "grad_norm": 1.4663927555084229,
      "learning_rate": 4.755789473684211e-06,
      "loss": 0.5655,
      "step": 191
    },
    {
      "epoch": 0.014575267592803462,
      "grad_norm": 3.137894630432129,
      "learning_rate": 4.227368421052631e-06,
      "loss": 1.1191,
      "step": 192
    },
    {
      "epoch": 0.014651180444849313,
      "grad_norm": 1.831155776977539,
      "learning_rate": 3.698947368421052e-06,
      "loss": 0.5518,
      "step": 193
    },
    {
      "epoch": 0.014727093296895165,
      "grad_norm": 1.731117606163025,
      "learning_rate": 3.170526315789474e-06,
      "loss": 0.618,
      "step": 194
    },
    {
      "epoch": 0.014803006148941016,
      "grad_norm": 2.330756664276123,
      "learning_rate": 2.6421052631578948e-06,
      "loss": 0.8381,
      "step": 195
    },
    {
      "epoch": 0.014878919000986868,
      "grad_norm": 1.4650490283966064,
      "learning_rate": 2.1136842105263157e-06,
      "loss": 0.5935,
      "step": 196
    },
    {
      "epoch": 0.01495483185303272,
      "grad_norm": 2.078733444213867,
      "learning_rate": 1.585263157894737e-06,
      "loss": 0.67,
      "step": 197
    },
    {
      "epoch": 0.01503074470507857,
      "grad_norm": 2.2000510692596436,
      "learning_rate": 1.0568421052631578e-06,
      "loss": 0.6887,
      "step": 198
    },
    {
      "epoch": 0.015106657557124422,
      "grad_norm": 1.6938163042068481,
      "learning_rate": 5.284210526315789e-07,
      "loss": 0.6497,
      "step": 199
    },
    {
      "epoch": 0.015182570409170272,
      "grad_norm": 1.2051751613616943,
      "learning_rate": 0.0,
      "loss": 0.5418,
      "step": 200
    },
    {
      "epoch": 0.015182570409170272,
      "eval_loss": 0.8681402802467346,
      "eval_runtime": 241.2771,
      "eval_samples_per_second": 22.99,
      "eval_steps_per_second": 5.749,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3607236534272e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}