{
  "best_metric": 0.14020927250385284,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.043044694741373124,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028696463160915415,
      "grad_norm": 6.107472896575928,
      "learning_rate": 1e-05,
      "loss": 1.8053,
      "step": 1
    },
    {
      "epoch": 0.00028696463160915415,
      "eval_loss": 0.7423262596130371,
      "eval_runtime": 720.1799,
      "eval_samples_per_second": 8.149,
      "eval_steps_per_second": 2.038,
      "step": 1
    },
    {
      "epoch": 0.0005739292632183083,
      "grad_norm": 6.406822681427002,
      "learning_rate": 2e-05,
      "loss": 1.8688,
      "step": 2
    },
    {
      "epoch": 0.0008608938948274625,
      "grad_norm": 5.952510356903076,
      "learning_rate": 3e-05,
      "loss": 1.8366,
      "step": 3
    },
    {
      "epoch": 0.0011478585264366166,
      "grad_norm": 4.1655168533325195,
      "learning_rate": 4e-05,
      "loss": 1.3913,
      "step": 4
    },
    {
      "epoch": 0.001434823158045771,
      "grad_norm": 3.903394937515259,
      "learning_rate": 5e-05,
      "loss": 1.2198,
      "step": 5
    },
    {
      "epoch": 0.001721787789654925,
      "grad_norm": 3.62347674369812,
      "learning_rate": 6e-05,
      "loss": 1.096,
      "step": 6
    },
    {
      "epoch": 0.002008752421264079,
      "grad_norm": 3.4067769050598145,
      "learning_rate": 7e-05,
      "loss": 1.0305,
      "step": 7
    },
    {
      "epoch": 0.002295717052873233,
      "grad_norm": 2.630232095718384,
      "learning_rate": 8e-05,
      "loss": 0.8866,
      "step": 8
    },
    {
      "epoch": 0.0025826816844823877,
      "grad_norm": 2.9238791465759277,
      "learning_rate": 9e-05,
      "loss": 0.867,
      "step": 9
    },
    {
      "epoch": 0.002869646316091542,
      "grad_norm": 3.1443634033203125,
      "learning_rate": 0.0001,
      "loss": 0.8553,
      "step": 10
    },
    {
      "epoch": 0.003156610947700696,
      "grad_norm": 2.855330228805542,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7601,
      "step": 11
    },
    {
      "epoch": 0.00344357557930985,
      "grad_norm": 2.9211862087249756,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7308,
      "step": 12
    },
    {
      "epoch": 0.003730540210919004,
      "grad_norm": 1.9237487316131592,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7697,
      "step": 13
    },
    {
      "epoch": 0.004017504842528158,
      "grad_norm": 1.7326750755310059,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.697,
      "step": 14
    },
    {
      "epoch": 0.004304469474137313,
      "grad_norm": 2.202223300933838,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6996,
      "step": 15
    },
    {
      "epoch": 0.004591434105746466,
      "grad_norm": 2.1931440830230713,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6535,
      "step": 16
    },
    {
      "epoch": 0.004878398737355621,
      "grad_norm": 2.1476407051086426,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.7295,
      "step": 17
    },
    {
      "epoch": 0.0051653633689647755,
      "grad_norm": 2.0206854343414307,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7137,
      "step": 18
    },
    {
      "epoch": 0.005452328000573929,
      "grad_norm": 1.936160683631897,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6812,
      "step": 19
    },
    {
      "epoch": 0.005739292632183084,
      "grad_norm": 2.090653419494629,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6689,
      "step": 20
    },
    {
      "epoch": 0.006026257263792237,
      "grad_norm": 2.130981683731079,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6916,
      "step": 21
    },
    {
      "epoch": 0.006313221895401392,
      "grad_norm": 1.8139557838439941,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6941,
      "step": 22
    },
    {
      "epoch": 0.0066001865270105455,
      "grad_norm": 1.9705530405044556,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7833,
      "step": 23
    },
    {
      "epoch": 0.0068871511586197,
      "grad_norm": 1.6844342947006226,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7247,
      "step": 24
    },
    {
      "epoch": 0.007174115790228855,
      "grad_norm": 1.8876069784164429,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.712,
      "step": 25
    },
    {
      "epoch": 0.007461080421838008,
      "grad_norm": 2.166876792907715,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8327,
      "step": 26
    },
    {
      "epoch": 0.007748045053447163,
      "grad_norm": 2.3669426441192627,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8226,
      "step": 27
    },
    {
      "epoch": 0.008035009685056316,
      "grad_norm": 2.422419786453247,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.762,
      "step": 28
    },
    {
      "epoch": 0.008321974316665471,
      "grad_norm": 2.1446056365966797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7257,
      "step": 29
    },
    {
      "epoch": 0.008608938948274625,
      "grad_norm": 2.103520631790161,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7874,
      "step": 30
    },
    {
      "epoch": 0.00889590357988378,
      "grad_norm": 2.709944486618042,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.509,
      "step": 31
    },
    {
      "epoch": 0.009182868211492933,
      "grad_norm": 2.2960727214813232,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7139,
      "step": 32
    },
    {
      "epoch": 0.009469832843102087,
      "grad_norm": 2.0458426475524902,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7085,
      "step": 33
    },
    {
      "epoch": 0.009756797474711242,
      "grad_norm": 2.0571670532226562,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6307,
      "step": 34
    },
    {
      "epoch": 0.010043762106320396,
      "grad_norm": 2.2126307487487793,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5018,
      "step": 35
    },
    {
      "epoch": 0.010330726737929551,
      "grad_norm": 2.442605495452881,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.695,
      "step": 36
    },
    {
      "epoch": 0.010617691369538704,
      "grad_norm": 2.4225752353668213,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7264,
      "step": 37
    },
    {
      "epoch": 0.010904656001147858,
      "grad_norm": 2.646764039993286,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8216,
      "step": 38
    },
    {
      "epoch": 0.011191620632757013,
      "grad_norm": 2.6557486057281494,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8751,
      "step": 39
    },
    {
      "epoch": 0.011478585264366167,
      "grad_norm": 3.159886360168457,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7496,
      "step": 40
    },
    {
      "epoch": 0.011765549895975322,
      "grad_norm": 2.5904407501220703,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7672,
      "step": 41
    },
    {
      "epoch": 0.012052514527584475,
      "grad_norm": 3.488381862640381,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7988,
      "step": 42
    },
    {
      "epoch": 0.01233947915919363,
      "grad_norm": 3.635977029800415,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6629,
      "step": 43
    },
    {
      "epoch": 0.012626443790802784,
      "grad_norm": 4.169275760650635,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.961,
      "step": 44
    },
    {
      "epoch": 0.012913408422411938,
      "grad_norm": 4.143824577331543,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8885,
      "step": 45
    },
    {
      "epoch": 0.013200373054021091,
      "grad_norm": 5.253859519958496,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.1625,
      "step": 46
    },
    {
      "epoch": 0.013487337685630246,
      "grad_norm": 10.66401481628418,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7644,
      "step": 47
    },
    {
      "epoch": 0.0137743023172394,
      "grad_norm": 5.827920913696289,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3862,
      "step": 48
    },
    {
      "epoch": 0.014061266948848555,
      "grad_norm": 4.412258625030518,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7058,
      "step": 49
    },
    {
      "epoch": 0.01434823158045771,
      "grad_norm": 15.187542915344238,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5217,
      "step": 50
    },
    {
      "epoch": 0.01434823158045771,
      "eval_loss": 0.22727616131305695,
      "eval_runtime": 725.4858,
      "eval_samples_per_second": 8.09,
      "eval_steps_per_second": 2.023,
      "step": 50
    },
    {
      "epoch": 0.014635196212066862,
      "grad_norm": 3.483478307723999,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9512,
      "step": 51
    },
    {
      "epoch": 0.014922160843676016,
      "grad_norm": 2.334841251373291,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.9354,
      "step": 52
    },
    {
      "epoch": 0.015209125475285171,
      "grad_norm": 1.296568751335144,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7182,
      "step": 53
    },
    {
      "epoch": 0.015496090106894326,
      "grad_norm": 1.297927737236023,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7632,
      "step": 54
    },
    {
      "epoch": 0.01578305473850348,
      "grad_norm": 1.1643849611282349,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7002,
      "step": 55
    },
    {
      "epoch": 0.016070019370112633,
      "grad_norm": 0.9503101706504822,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6688,
      "step": 56
    },
    {
      "epoch": 0.016356984001721787,
      "grad_norm": 1.2467663288116455,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6973,
      "step": 57
    },
    {
      "epoch": 0.016643948633330942,
      "grad_norm": 1.115466594696045,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5741,
      "step": 58
    },
    {
      "epoch": 0.016930913264940096,
      "grad_norm": 1.1591720581054688,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6208,
      "step": 59
    },
    {
      "epoch": 0.01721787789654925,
      "grad_norm": 1.2686914205551147,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6124,
      "step": 60
    },
    {
      "epoch": 0.017504842528158406,
      "grad_norm": 1.1492196321487427,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.5527,
      "step": 61
    },
    {
      "epoch": 0.01779180715976756,
      "grad_norm": 1.1260546445846558,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5776,
      "step": 62
    },
    {
      "epoch": 0.01807877179137671,
      "grad_norm": 1.1964120864868164,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6209,
      "step": 63
    },
    {
      "epoch": 0.018365736422985866,
      "grad_norm": 1.2629157304763794,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5498,
      "step": 64
    },
    {
      "epoch": 0.01865270105459502,
      "grad_norm": 1.1550707817077637,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5758,
      "step": 65
    },
    {
      "epoch": 0.018939665686204175,
      "grad_norm": 1.2339072227478027,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5411,
      "step": 66
    },
    {
      "epoch": 0.01922663031781333,
      "grad_norm": 1.242158055305481,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5601,
      "step": 67
    },
    {
      "epoch": 0.019513594949422484,
      "grad_norm": 1.1575692892074585,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5454,
      "step": 68
    },
    {
      "epoch": 0.01980055958103164,
      "grad_norm": 1.3557543754577637,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5641,
      "step": 69
    },
    {
      "epoch": 0.020087524212640793,
      "grad_norm": 1.464561939239502,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6146,
      "step": 70
    },
    {
      "epoch": 0.020374488844249947,
      "grad_norm": 1.2554397583007812,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5294,
      "step": 71
    },
    {
      "epoch": 0.020661453475859102,
      "grad_norm": 1.6599295139312744,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6095,
      "step": 72
    },
    {
      "epoch": 0.020948418107468253,
      "grad_norm": 1.4837092161178589,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5887,
      "step": 73
    },
    {
      "epoch": 0.021235382739077407,
      "grad_norm": 1.3760673999786377,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.587,
      "step": 74
    },
    {
      "epoch": 0.021522347370686562,
      "grad_norm": 1.4944982528686523,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.623,
      "step": 75
    },
    {
      "epoch": 0.021809312002295717,
      "grad_norm": 1.7354507446289062,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6535,
      "step": 76
    },
    {
      "epoch": 0.02209627663390487,
      "grad_norm": 1.5658936500549316,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6621,
      "step": 77
    },
    {
      "epoch": 0.022383241265514026,
      "grad_norm": 1.4880445003509521,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.612,
      "step": 78
    },
    {
      "epoch": 0.02267020589712318,
      "grad_norm": 1.5957709550857544,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6205,
      "step": 79
    },
    {
      "epoch": 0.022957170528732335,
      "grad_norm": 1.363569974899292,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.489,
      "step": 80
    },
    {
      "epoch": 0.02324413516034149,
      "grad_norm": 4.256164073944092,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5817,
      "step": 81
    },
    {
      "epoch": 0.023531099791950644,
      "grad_norm": 1.5727474689483643,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3951,
      "step": 82
    },
    {
      "epoch": 0.023818064423559795,
      "grad_norm": 1.3179304599761963,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.4876,
      "step": 83
    },
    {
      "epoch": 0.02410502905516895,
      "grad_norm": 1.5551384687423706,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.5004,
      "step": 84
    },
    {
      "epoch": 0.024391993686778104,
      "grad_norm": 1.9589033126831055,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4038,
      "step": 85
    },
    {
      "epoch": 0.02467895831838726,
      "grad_norm": 1.394819736480713,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3293,
      "step": 86
    },
    {
      "epoch": 0.024965922949996413,
      "grad_norm": 2.1548991203308105,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6905,
      "step": 87
    },
    {
      "epoch": 0.025252887581605567,
      "grad_norm": 2.0175275802612305,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.5663,
      "step": 88
    },
    {
      "epoch": 0.025539852213214722,
      "grad_norm": 3.7470855712890625,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6388,
      "step": 89
    },
    {
      "epoch": 0.025826816844823876,
      "grad_norm": 2.4227797985076904,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6016,
      "step": 90
    },
    {
      "epoch": 0.02611378147643303,
      "grad_norm": 2.369810104370117,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6815,
      "step": 91
    },
    {
      "epoch": 0.026400746108042182,
      "grad_norm": 2.3004965782165527,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4969,
      "step": 92
    },
    {
      "epoch": 0.026687710739651337,
      "grad_norm": 1.670210599899292,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4121,
      "step": 93
    },
    {
      "epoch": 0.02697467537126049,
      "grad_norm": 2.4153645038604736,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6185,
      "step": 94
    },
    {
      "epoch": 0.027261640002869646,
      "grad_norm": 2.248807668685913,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6728,
      "step": 95
    },
    {
      "epoch": 0.0275486046344788,
      "grad_norm": 2.8713765144348145,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7538,
      "step": 96
    },
    {
      "epoch": 0.027835569266087955,
      "grad_norm": 6.229552745819092,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6173,
      "step": 97
    },
    {
      "epoch": 0.02812253389769711,
      "grad_norm": 2.57981276512146,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.3001,
      "step": 98
    },
    {
      "epoch": 0.028409498529306264,
      "grad_norm": 3.5027661323547363,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5789,
      "step": 99
    },
    {
      "epoch": 0.02869646316091542,
      "grad_norm": 5.448148250579834,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9769,
      "step": 100
    },
    {
      "epoch": 0.02869646316091542,
      "eval_loss": 0.1931166648864746,
      "eval_runtime": 726.1739,
      "eval_samples_per_second": 8.082,
      "eval_steps_per_second": 2.022,
      "step": 100
    },
    {
      "epoch": 0.028983427792524573,
      "grad_norm": 2.585517168045044,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8062,
      "step": 101
    },
    {
      "epoch": 0.029270392424133724,
      "grad_norm": 1.9429270029067993,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8224,
      "step": 102
    },
    {
      "epoch": 0.02955735705574288,
      "grad_norm": 1.246541142463684,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7229,
      "step": 103
    },
    {
      "epoch": 0.029844321687352033,
      "grad_norm": 0.9692350029945374,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.6455,
      "step": 104
    },
    {
      "epoch": 0.030131286318961188,
      "grad_norm": 0.9777825474739075,
      "learning_rate": 5e-05,
      "loss": 0.652,
      "step": 105
    },
    {
      "epoch": 0.030418250950570342,
      "grad_norm": 0.9480687379837036,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6429,
      "step": 106
    },
    {
      "epoch": 0.030705215582179497,
      "grad_norm": 0.9986096620559692,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5534,
      "step": 107
    },
    {
      "epoch": 0.03099218021378865,
      "grad_norm": 0.8905943036079407,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6105,
      "step": 108
    },
    {
      "epoch": 0.0312791448453978,
      "grad_norm": 0.9737687110900879,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5536,
      "step": 109
    },
    {
      "epoch": 0.03156610947700696,
      "grad_norm": 1.0353845357894897,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.4446,
      "step": 110
    },
    {
      "epoch": 0.03185307410861611,
      "grad_norm": 1.0230631828308105,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5574,
      "step": 111
    },
    {
      "epoch": 0.032140038740225266,
      "grad_norm": 1.028673529624939,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5232,
      "step": 112
    },
    {
      "epoch": 0.03242700337183442,
      "grad_norm": 1.0488940477371216,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6019,
      "step": 113
    },
    {
      "epoch": 0.032713968003443575,
      "grad_norm": 0.9317765235900879,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5351,
      "step": 114
    },
    {
      "epoch": 0.03300093263505273,
      "grad_norm": 1.0550882816314697,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4921,
      "step": 115
    },
    {
      "epoch": 0.033287897266661884,
      "grad_norm": 0.9784736037254333,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5329,
      "step": 116
    },
    {
      "epoch": 0.03357486189827104,
      "grad_norm": 0.9534372091293335,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4718,
      "step": 117
    },
    {
      "epoch": 0.03386182652988019,
      "grad_norm": 0.9671270251274109,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5067,
      "step": 118
    },
    {
      "epoch": 0.03414879116148935,
      "grad_norm": 1.0344678163528442,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5029,
      "step": 119
    },
    {
      "epoch": 0.0344357557930985,
      "grad_norm": 1.0899558067321777,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5653,
      "step": 120
    },
    {
      "epoch": 0.034722720424707657,
      "grad_norm": 1.0599912405014038,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5656,
      "step": 121
    },
    {
      "epoch": 0.03500968505631681,
      "grad_norm": 1.252654790878296,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5418,
      "step": 122
    },
    {
      "epoch": 0.035296649687925966,
      "grad_norm": 1.2622045278549194,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5896,
      "step": 123
    },
    {
      "epoch": 0.03558361431953512,
      "grad_norm": 1.1633052825927734,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4994,
      "step": 124
    },
    {
      "epoch": 0.035870578951144275,
      "grad_norm": 1.3786684274673462,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5667,
      "step": 125
    },
    {
      "epoch": 0.03615754358275342,
      "grad_norm": 1.3860639333724976,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5886,
      "step": 126
    },
    {
      "epoch": 0.03644450821436258,
      "grad_norm": 1.2784900665283203,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5276,
      "step": 127
    },
    {
      "epoch": 0.03673147284597173,
      "grad_norm": 1.337878942489624,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5393,
      "step": 128
    },
    {
      "epoch": 0.037018437477580886,
      "grad_norm": 1.301600694656372,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4695,
      "step": 129
    },
    {
      "epoch": 0.03730540210919004,
      "grad_norm": 1.561050534248352,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3082,
      "step": 130
    },
    {
      "epoch": 0.037592366740799195,
      "grad_norm": 1.1425620317459106,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4026,
      "step": 131
    },
    {
      "epoch": 0.03787933137240835,
      "grad_norm": 1.365915060043335,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.4593,
      "step": 132
    },
    {
      "epoch": 0.038166296004017504,
      "grad_norm": 1.1435322761535645,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3934,
      "step": 133
    },
    {
      "epoch": 0.03845326063562666,
      "grad_norm": 1.5968090295791626,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3488,
      "step": 134
    },
    {
      "epoch": 0.03874022526723581,
      "grad_norm": 1.5644590854644775,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3628,
      "step": 135
    },
    {
      "epoch": 0.03902718989884497,
      "grad_norm": 1.8397178649902344,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.4692,
      "step": 136
    },
    {
      "epoch": 0.03931415453045412,
      "grad_norm": 1.4935563802719116,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5686,
      "step": 137
    },
    {
      "epoch": 0.03960111916206328,
      "grad_norm": 1.9233158826828003,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.5452,
      "step": 138
    },
    {
      "epoch": 0.03988808379367243,
      "grad_norm": 1.8936307430267334,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5089,
      "step": 139
    },
    {
      "epoch": 0.040175048425281586,
      "grad_norm": 1.919930338859558,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.4878,
      "step": 140
    },
    {
      "epoch": 0.04046201305689074,
      "grad_norm": 1.8204017877578735,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5574,
      "step": 141
    },
    {
      "epoch": 0.040748977688499895,
      "grad_norm": 2.484811305999756,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.4824,
      "step": 142
    },
    {
      "epoch": 0.04103594232010905,
      "grad_norm": 1.700395107269287,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2798,
      "step": 143
    },
    {
      "epoch": 0.041322906951718204,
      "grad_norm": 2.000028610229492,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4922,
      "step": 144
    },
    {
      "epoch": 0.04160987158332736,
      "grad_norm": 2.1531145572662354,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5552,
      "step": 145
    },
    {
      "epoch": 0.041896836214936506,
      "grad_norm": 2.3488152027130127,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5224,
      "step": 146
    },
    {
      "epoch": 0.04218380084654566,
      "grad_norm": 2.974459409713745,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5267,
      "step": 147
    },
    {
      "epoch": 0.042470765478154815,
      "grad_norm": 3.0844335556030273,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2509,
      "step": 148
    },
    {
      "epoch": 0.04275773010976397,
      "grad_norm": 1.7252553701400757,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1987,
      "step": 149
    },
    {
      "epoch": 0.043044694741373124,
      "grad_norm": 3.4111781120300293,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6157,
      "step": 150
    },
    {
      "epoch": 0.043044694741373124,
      "eval_loss": 0.14020927250385284,
      "eval_runtime": 726.2241,
      "eval_samples_per_second": 8.082,
      "eval_steps_per_second": 2.021,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5181975101138534e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}