{
  "best_metric": 0.8301867842674255,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.12556898446083817,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006278449223041908,
      "grad_norm": 0.29474231600761414,
      "learning_rate": 1e-05,
      "loss": 0.5215,
      "step": 1
    },
    {
      "epoch": 0.0006278449223041908,
      "eval_loss": 1.0530985593795776,
      "eval_runtime": 83.8983,
      "eval_samples_per_second": 31.979,
      "eval_steps_per_second": 7.998,
      "step": 1
    },
    {
      "epoch": 0.0012556898446083817,
      "grad_norm": 0.3529818058013916,
      "learning_rate": 2e-05,
      "loss": 0.6006,
      "step": 2
    },
    {
      "epoch": 0.0018835347669125726,
      "grad_norm": 0.33801841735839844,
      "learning_rate": 3e-05,
      "loss": 0.711,
      "step": 3
    },
    {
      "epoch": 0.0025113796892167633,
      "grad_norm": 0.3358214795589447,
      "learning_rate": 4e-05,
      "loss": 0.6543,
      "step": 4
    },
    {
      "epoch": 0.0031392246115209545,
      "grad_norm": 0.34503278136253357,
      "learning_rate": 5e-05,
      "loss": 0.7748,
      "step": 5
    },
    {
      "epoch": 0.003767069533825145,
      "grad_norm": 0.38686808943748474,
      "learning_rate": 6e-05,
      "loss": 0.7512,
      "step": 6
    },
    {
      "epoch": 0.004394914456129336,
      "grad_norm": 0.3241465985774994,
      "learning_rate": 7e-05,
      "loss": 0.7033,
      "step": 7
    },
    {
      "epoch": 0.005022759378433527,
      "grad_norm": 0.3426409065723419,
      "learning_rate": 8e-05,
      "loss": 0.6909,
      "step": 8
    },
    {
      "epoch": 0.005650604300737718,
      "grad_norm": 0.3962495028972626,
      "learning_rate": 9e-05,
      "loss": 0.7669,
      "step": 9
    },
    {
      "epoch": 0.006278449223041909,
      "grad_norm": 0.3876018226146698,
      "learning_rate": 0.0001,
      "loss": 0.798,
      "step": 10
    },
    {
      "epoch": 0.006906294145346099,
      "grad_norm": 0.4307634234428406,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7384,
      "step": 11
    },
    {
      "epoch": 0.00753413906765029,
      "grad_norm": 0.4623281955718994,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8388,
      "step": 12
    },
    {
      "epoch": 0.00816198398995448,
      "grad_norm": 0.4244893491268158,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8525,
      "step": 13
    },
    {
      "epoch": 0.008789828912258673,
      "grad_norm": 0.4223202168941498,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7995,
      "step": 14
    },
    {
      "epoch": 0.009417673834562863,
      "grad_norm": 0.4026021361351013,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8481,
      "step": 15
    },
    {
      "epoch": 0.010045518756867053,
      "grad_norm": 0.4413195252418518,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.916,
      "step": 16
    },
    {
      "epoch": 0.010673363679171245,
      "grad_norm": 0.4151124060153961,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8271,
      "step": 17
    },
    {
      "epoch": 0.011301208601475436,
      "grad_norm": 0.42092135548591614,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8536,
      "step": 18
    },
    {
      "epoch": 0.011929053523779626,
      "grad_norm": 0.4100762903690338,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.905,
      "step": 19
    },
    {
      "epoch": 0.012556898446083818,
      "grad_norm": 0.4030074179172516,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8836,
      "step": 20
    },
    {
      "epoch": 0.013184743368388008,
      "grad_norm": 0.4809715747833252,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0331,
      "step": 21
    },
    {
      "epoch": 0.013812588290692198,
      "grad_norm": 0.4507080912590027,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8735,
      "step": 22
    },
    {
      "epoch": 0.01444043321299639,
      "grad_norm": 0.44013890624046326,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8703,
      "step": 23
    },
    {
      "epoch": 0.01506827813530058,
      "grad_norm": 0.4327889680862427,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8117,
      "step": 24
    },
    {
      "epoch": 0.01569612305760477,
      "grad_norm": 0.4711591899394989,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8307,
      "step": 25
    },
    {
      "epoch": 0.01632396797990896,
      "grad_norm": 0.47128742933273315,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7942,
      "step": 26
    },
    {
      "epoch": 0.016951812902213155,
      "grad_norm": 0.484572172164917,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8771,
      "step": 27
    },
    {
      "epoch": 0.017579657824517345,
      "grad_norm": 0.4840153157711029,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7735,
      "step": 28
    },
    {
      "epoch": 0.018207502746821536,
      "grad_norm": 0.48889270424842834,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8289,
      "step": 29
    },
    {
      "epoch": 0.018835347669125726,
      "grad_norm": 0.4968271255493164,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.869,
      "step": 30
    },
    {
      "epoch": 0.019463192591429916,
      "grad_norm": 0.5126733183860779,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7811,
      "step": 31
    },
    {
      "epoch": 0.020091037513734106,
      "grad_norm": 0.5412195920944214,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8547,
      "step": 32
    },
    {
      "epoch": 0.0207188824360383,
      "grad_norm": 0.5129484534263611,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8867,
      "step": 33
    },
    {
      "epoch": 0.02134672735834249,
      "grad_norm": 0.5988695025444031,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.7868,
      "step": 34
    },
    {
      "epoch": 0.02197457228064668,
      "grad_norm": 0.5805250406265259,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7404,
      "step": 35
    },
    {
      "epoch": 0.02260241720295087,
      "grad_norm": 0.5965076684951782,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9184,
      "step": 36
    },
    {
      "epoch": 0.02323026212525506,
      "grad_norm": 0.6509871482849121,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7976,
      "step": 37
    },
    {
      "epoch": 0.02385810704755925,
      "grad_norm": 0.622890830039978,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.9548,
      "step": 38
    },
    {
      "epoch": 0.024485951969863445,
      "grad_norm": 0.6913728713989258,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9519,
      "step": 39
    },
    {
      "epoch": 0.025113796892167636,
      "grad_norm": 0.6338409185409546,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8095,
      "step": 40
    },
    {
      "epoch": 0.025741641814471826,
      "grad_norm": 0.7815749645233154,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8146,
      "step": 41
    },
    {
      "epoch": 0.026369486736776016,
      "grad_norm": 0.7960447669029236,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8733,
      "step": 42
    },
    {
      "epoch": 0.026997331659080206,
      "grad_norm": 0.8016958236694336,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8721,
      "step": 43
    },
    {
      "epoch": 0.027625176581384397,
      "grad_norm": 0.9644938707351685,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0231,
      "step": 44
    },
    {
      "epoch": 0.02825302150368859,
      "grad_norm": 0.8886382579803467,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8915,
      "step": 45
    },
    {
      "epoch": 0.02888086642599278,
      "grad_norm": 1.0618637800216675,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.075,
      "step": 46
    },
    {
      "epoch": 0.02950871134829697,
      "grad_norm": 1.19996178150177,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9996,
      "step": 47
    },
    {
      "epoch": 0.03013655627060116,
      "grad_norm": 1.4232078790664673,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1055,
      "step": 48
    },
    {
      "epoch": 0.03076440119290535,
      "grad_norm": 1.5065048933029175,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.3109,
      "step": 49
    },
    {
      "epoch": 0.03139224611520954,
      "grad_norm": 1.9556245803833008,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0269,
      "step": 50
    },
    {
      "epoch": 0.03139224611520954,
      "eval_loss": 0.8842460513114929,
      "eval_runtime": 84.4095,
      "eval_samples_per_second": 31.786,
      "eval_steps_per_second": 7.949,
      "step": 50
    },
    {
      "epoch": 0.032020091037513736,
      "grad_norm": 0.3064557909965515,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5255,
      "step": 51
    },
    {
      "epoch": 0.03264793595981792,
      "grad_norm": 0.5814394354820251,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5061,
      "step": 52
    },
    {
      "epoch": 0.033275780882122116,
      "grad_norm": 0.3637872338294983,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6412,
      "step": 53
    },
    {
      "epoch": 0.03390362580442631,
      "grad_norm": 0.4275180399417877,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7904,
      "step": 54
    },
    {
      "epoch": 0.0345314707267305,
      "grad_norm": 0.3474939167499542,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7238,
      "step": 55
    },
    {
      "epoch": 0.03515931564903469,
      "grad_norm": 0.3170601427555084,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7328,
      "step": 56
    },
    {
      "epoch": 0.03578716057133888,
      "grad_norm": 0.3025910556316376,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7229,
      "step": 57
    },
    {
      "epoch": 0.03641500549364307,
      "grad_norm": 0.33307960629463196,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7689,
      "step": 58
    },
    {
      "epoch": 0.03704285041594726,
      "grad_norm": 0.3866959810256958,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7089,
      "step": 59
    },
    {
      "epoch": 0.03767069533825145,
      "grad_norm": 0.3711072504520416,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.711,
      "step": 60
    },
    {
      "epoch": 0.038298540260555645,
      "grad_norm": 0.3593451976776123,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7486,
      "step": 61
    },
    {
      "epoch": 0.03892638518285983,
      "grad_norm": 0.34750768542289734,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8219,
      "step": 62
    },
    {
      "epoch": 0.039554230105164026,
      "grad_norm": 0.32483235001564026,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7605,
      "step": 63
    },
    {
      "epoch": 0.04018207502746821,
      "grad_norm": 0.3605320155620575,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9071,
      "step": 64
    },
    {
      "epoch": 0.04080991994977241,
      "grad_norm": 0.3330734968185425,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.767,
      "step": 65
    },
    {
      "epoch": 0.0414377648720766,
      "grad_norm": 0.3530653119087219,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.811,
      "step": 66
    },
    {
      "epoch": 0.04206560979438079,
      "grad_norm": 0.37905681133270264,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8761,
      "step": 67
    },
    {
      "epoch": 0.04269345471668498,
      "grad_norm": 0.38746708631515503,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8722,
      "step": 68
    },
    {
      "epoch": 0.04332129963898917,
      "grad_norm": 0.40445587038993835,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8652,
      "step": 69
    },
    {
      "epoch": 0.04394914456129336,
      "grad_norm": 0.3931260406970978,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8637,
      "step": 70
    },
    {
      "epoch": 0.04457698948359755,
      "grad_norm": 0.38505905866622925,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.778,
      "step": 71
    },
    {
      "epoch": 0.04520483440590174,
      "grad_norm": 0.41518208384513855,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7828,
      "step": 72
    },
    {
      "epoch": 0.045832679328205936,
      "grad_norm": 0.4309608042240143,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9456,
      "step": 73
    },
    {
      "epoch": 0.04646052425051012,
      "grad_norm": 0.4033466577529907,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8607,
      "step": 74
    },
    {
      "epoch": 0.047088369172814316,
      "grad_norm": 0.4080653488636017,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8547,
      "step": 75
    },
    {
      "epoch": 0.0477162140951185,
      "grad_norm": 0.45925450325012207,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7668,
      "step": 76
    },
    {
      "epoch": 0.0483440590174227,
      "grad_norm": 0.4721239507198334,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7897,
      "step": 77
    },
    {
      "epoch": 0.04897190393972689,
      "grad_norm": 0.4305371046066284,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8035,
      "step": 78
    },
    {
      "epoch": 0.04959974886203108,
      "grad_norm": 0.4776322841644287,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8277,
      "step": 79
    },
    {
      "epoch": 0.05022759378433527,
      "grad_norm": 0.4314558804035187,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7437,
      "step": 80
    },
    {
      "epoch": 0.05085543870663946,
      "grad_norm": 0.49073314666748047,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.789,
      "step": 81
    },
    {
      "epoch": 0.05148328362894365,
      "grad_norm": 0.46452414989471436,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7861,
      "step": 82
    },
    {
      "epoch": 0.05211112855124784,
      "grad_norm": 0.46071621775627136,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.841,
      "step": 83
    },
    {
      "epoch": 0.05273897347355203,
      "grad_norm": 0.5624316930770874,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8978,
      "step": 84
    },
    {
      "epoch": 0.053366818395856226,
      "grad_norm": 0.5588775277137756,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9293,
      "step": 85
    },
    {
      "epoch": 0.05399466331816041,
      "grad_norm": 0.5270624160766602,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7834,
      "step": 86
    },
    {
      "epoch": 0.05462250824046461,
      "grad_norm": 0.49282562732696533,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8024,
      "step": 87
    },
    {
      "epoch": 0.055250353162768794,
      "grad_norm": 0.6458669304847717,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.9619,
      "step": 88
    },
    {
      "epoch": 0.05587819808507299,
      "grad_norm": 0.6261863708496094,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8275,
      "step": 89
    },
    {
      "epoch": 0.05650604300737718,
      "grad_norm": 0.6104888319969177,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8617,
      "step": 90
    },
    {
      "epoch": 0.05713388792968137,
      "grad_norm": 0.6412619352340698,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7762,
      "step": 91
    },
    {
      "epoch": 0.05776173285198556,
      "grad_norm": 0.6976544857025146,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9369,
      "step": 92
    },
    {
      "epoch": 0.05838957777428975,
      "grad_norm": 0.8839225172996521,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.8236,
      "step": 93
    },
    {
      "epoch": 0.05901742269659394,
      "grad_norm": 0.7913328409194946,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.0054,
      "step": 94
    },
    {
      "epoch": 0.05964526761889813,
      "grad_norm": 0.9896240830421448,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.159,
      "step": 95
    },
    {
      "epoch": 0.06027311254120232,
      "grad_norm": 1.0347424745559692,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.9988,
      "step": 96
    },
    {
      "epoch": 0.060900957463506517,
      "grad_norm": 0.9619345664978027,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0012,
      "step": 97
    },
    {
      "epoch": 0.0615288023858107,
      "grad_norm": 1.298412561416626,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.9692,
      "step": 98
    },
    {
      "epoch": 0.0621566473081149,
      "grad_norm": 1.2043523788452148,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0544,
      "step": 99
    },
    {
      "epoch": 0.06278449223041908,
      "grad_norm": 1.8621759414672852,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8761,
      "step": 100
    },
    {
      "epoch": 0.06278449223041908,
      "eval_loss": 0.8422326445579529,
      "eval_runtime": 84.22,
      "eval_samples_per_second": 31.857,
      "eval_steps_per_second": 7.967,
      "step": 100
    },
    {
      "epoch": 0.06341233715272328,
      "grad_norm": 0.23397061228752136,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4862,
      "step": 101
    },
    {
      "epoch": 0.06404018207502747,
      "grad_norm": 0.2775203287601471,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5616,
      "step": 102
    },
    {
      "epoch": 0.06466802699733167,
      "grad_norm": 0.318746417760849,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5645,
      "step": 103
    },
    {
      "epoch": 0.06529587191963585,
      "grad_norm": 0.3719039559364319,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8024,
      "step": 104
    },
    {
      "epoch": 0.06592371684194004,
      "grad_norm": 0.3119391202926636,
      "learning_rate": 5e-05,
      "loss": 0.6561,
      "step": 105
    },
    {
      "epoch": 0.06655156176424423,
      "grad_norm": 0.30085885524749756,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7017,
      "step": 106
    },
    {
      "epoch": 0.06717940668654843,
      "grad_norm": 0.2912568151950836,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7187,
      "step": 107
    },
    {
      "epoch": 0.06780725160885262,
      "grad_norm": 0.28861185908317566,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7859,
      "step": 108
    },
    {
      "epoch": 0.0684350965311568,
      "grad_norm": 0.2815602123737335,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6562,
      "step": 109
    },
    {
      "epoch": 0.069062941453461,
      "grad_norm": 0.320718914270401,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8913,
      "step": 110
    },
    {
      "epoch": 0.06969078637576519,
      "grad_norm": 0.3043502867221832,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8133,
      "step": 111
    },
    {
      "epoch": 0.07031863129806938,
      "grad_norm": 0.3036293387413025,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6822,
      "step": 112
    },
    {
      "epoch": 0.07094647622037356,
      "grad_norm": 0.35792213678359985,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8031,
      "step": 113
    },
    {
      "epoch": 0.07157432114267775,
      "grad_norm": 0.3383018672466278,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7969,
      "step": 114
    },
    {
      "epoch": 0.07220216606498195,
      "grad_norm": 0.35960108041763306,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.816,
      "step": 115
    },
    {
      "epoch": 0.07283001098728614,
      "grad_norm": 0.38822585344314575,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8257,
      "step": 116
    },
    {
      "epoch": 0.07345785590959034,
      "grad_norm": 0.33852046728134155,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8031,
      "step": 117
    },
    {
      "epoch": 0.07408570083189452,
      "grad_norm": 0.3631170690059662,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7859,
      "step": 118
    },
    {
      "epoch": 0.07471354575419871,
      "grad_norm": 0.3615998327732086,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.765,
      "step": 119
    },
    {
      "epoch": 0.0753413906765029,
      "grad_norm": 0.36010733246803284,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7993,
      "step": 120
    },
    {
      "epoch": 0.0759692355988071,
      "grad_norm": 0.37302523851394653,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8699,
      "step": 121
    },
    {
      "epoch": 0.07659708052111129,
      "grad_norm": 0.3582797348499298,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8097,
      "step": 122
    },
    {
      "epoch": 0.07722492544341547,
      "grad_norm": 0.3625119924545288,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.729,
      "step": 123
    },
    {
      "epoch": 0.07785277036571966,
      "grad_norm": 0.34591352939605713,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7895,
      "step": 124
    },
    {
      "epoch": 0.07848061528802386,
      "grad_norm": 0.3652077913284302,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8239,
      "step": 125
    },
    {
      "epoch": 0.07910846021032805,
      "grad_norm": 0.41401562094688416,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.8613,
      "step": 126
    },
    {
      "epoch": 0.07973630513263225,
      "grad_norm": 0.4083777368068695,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7527,
      "step": 127
    },
    {
      "epoch": 0.08036415005493643,
      "grad_norm": 0.458921879529953,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8719,
      "step": 128
    },
    {
      "epoch": 0.08099199497724062,
      "grad_norm": 0.39596283435821533,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6868,
      "step": 129
    },
    {
      "epoch": 0.08161983989954481,
      "grad_norm": 0.4229189157485962,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7541,
      "step": 130
    },
    {
      "epoch": 0.08224768482184901,
      "grad_norm": 0.4303133487701416,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.858,
      "step": 131
    },
    {
      "epoch": 0.0828755297441532,
      "grad_norm": 0.49071618914604187,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.797,
      "step": 132
    },
    {
      "epoch": 0.08350337466645738,
      "grad_norm": 0.5432262420654297,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7748,
      "step": 133
    },
    {
      "epoch": 0.08413121958876157,
      "grad_norm": 0.5409960746765137,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8297,
      "step": 134
    },
    {
      "epoch": 0.08475906451106577,
      "grad_norm": 0.5111663341522217,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7591,
      "step": 135
    },
    {
      "epoch": 0.08538690943336996,
      "grad_norm": 0.5009549260139465,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6663,
      "step": 136
    },
    {
      "epoch": 0.08601475435567414,
      "grad_norm": 0.6032416224479675,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8271,
      "step": 137
    },
    {
      "epoch": 0.08664259927797834,
      "grad_norm": 0.659298837184906,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.9255,
      "step": 138
    },
    {
      "epoch": 0.08727044420028253,
      "grad_norm": 0.6872729063034058,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.96,
      "step": 139
    },
    {
      "epoch": 0.08789828912258672,
      "grad_norm": 0.7141663432121277,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8313,
      "step": 140
    },
    {
      "epoch": 0.08852613404489092,
      "grad_norm": 0.7283548712730408,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7979,
      "step": 141
    },
    {
      "epoch": 0.0891539789671951,
      "grad_norm": 0.8707422614097595,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8227,
      "step": 142
    },
    {
      "epoch": 0.08978182388949929,
      "grad_norm": 0.71211838722229,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6971,
      "step": 143
    },
    {
      "epoch": 0.09040966881180348,
      "grad_norm": 0.9144647121429443,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7838,
      "step": 144
    },
    {
      "epoch": 0.09103751373410768,
      "grad_norm": 1.0228855609893799,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.0748,
      "step": 145
    },
    {
      "epoch": 0.09166535865641187,
      "grad_norm": 1.038773536682129,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.0712,
      "step": 146
    },
    {
      "epoch": 0.09229320357871605,
      "grad_norm": 1.02202308177948,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.0736,
      "step": 147
    },
    {
      "epoch": 0.09292104850102025,
      "grad_norm": 1.08366858959198,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.0181,
      "step": 148
    },
    {
      "epoch": 0.09354889342332444,
      "grad_norm": 1.3679362535476685,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.043,
      "step": 149
    },
    {
      "epoch": 0.09417673834562863,
      "grad_norm": 2.17260479927063,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.059,
      "step": 150
    },
    {
      "epoch": 0.09417673834562863,
      "eval_loss": 0.8301867842674255,
      "eval_runtime": 84.5942,
      "eval_samples_per_second": 31.716,
      "eval_steps_per_second": 7.932,
      "step": 150
    },
    {
      "epoch": 0.09480458326793283,
      "grad_norm": 0.2317795604467392,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.55,
      "step": 151
    },
    {
      "epoch": 0.095432428190237,
      "grad_norm": 0.23509512841701508,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5249,
      "step": 152
    },
    {
      "epoch": 0.0960602731125412,
      "grad_norm": 0.2779792249202728,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5407,
      "step": 153
    },
    {
      "epoch": 0.0966881180348454,
      "grad_norm": 0.2548755705356598,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.702,
      "step": 154
    },
    {
      "epoch": 0.09731596295714959,
      "grad_norm": 0.28282254934310913,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7475,
      "step": 155
    },
    {
      "epoch": 0.09794380787945378,
      "grad_norm": 0.2646379768848419,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7023,
      "step": 156
    },
    {
      "epoch": 0.09857165280175796,
      "grad_norm": 0.2654716372489929,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6547,
      "step": 157
    },
    {
      "epoch": 0.09919949772406216,
      "grad_norm": 0.26182040572166443,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6721,
      "step": 158
    },
    {
      "epoch": 0.09982734264636635,
      "grad_norm": 0.32432517409324646,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8435,
      "step": 159
    },
    {
      "epoch": 0.10045518756867054,
      "grad_norm": 0.31359827518463135,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7421,
      "step": 160
    },
    {
      "epoch": 0.10108303249097472,
      "grad_norm": 0.29712405800819397,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6999,
      "step": 161
    },
    {
      "epoch": 0.10171087741327892,
      "grad_norm": 0.32419276237487793,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7901,
      "step": 162
    },
    {
      "epoch": 0.10233872233558311,
      "grad_norm": 0.29091787338256836,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7202,
      "step": 163
    },
    {
      "epoch": 0.1029665672578873,
      "grad_norm": 0.3498837351799011,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.888,
      "step": 164
    },
    {
      "epoch": 0.1035944121801915,
      "grad_norm": 0.33074867725372314,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7871,
      "step": 165
    },
    {
      "epoch": 0.10422225710249568,
      "grad_norm": 0.36717310547828674,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.9063,
      "step": 166
    },
    {
      "epoch": 0.10485010202479987,
      "grad_norm": 0.3641189932823181,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7957,
      "step": 167
    },
    {
      "epoch": 0.10547794694710406,
      "grad_norm": 0.35571953654289246,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8116,
      "step": 168
    },
    {
      "epoch": 0.10610579186940826,
      "grad_norm": 0.3522847890853882,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8232,
      "step": 169
    },
    {
      "epoch": 0.10673363679171245,
      "grad_norm": 0.36481091380119324,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.8195,
      "step": 170
    },
    {
      "epoch": 0.10736148171401663,
      "grad_norm": 0.34471359848976135,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7798,
      "step": 171
    },
    {
      "epoch": 0.10798932663632083,
      "grad_norm": 0.343343585729599,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7824,
      "step": 172
    },
    {
      "epoch": 0.10861717155862502,
      "grad_norm": 0.3544749617576599,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8236,
      "step": 173
    },
    {
      "epoch": 0.10924501648092921,
      "grad_norm": 0.38760459423065186,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7756,
      "step": 174
    },
    {
      "epoch": 0.10987286140323341,
      "grad_norm": 0.3799603581428528,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8512,
      "step": 175
    },
    {
      "epoch": 0.11050070632553759,
      "grad_norm": 0.39610785245895386,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6284,
      "step": 176
    },
    {
      "epoch": 0.11112855124784178,
      "grad_norm": 0.4424748420715332,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7852,
      "step": 177
    },
    {
      "epoch": 0.11175639617014597,
      "grad_norm": 0.4629611372947693,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.8857,
      "step": 178
    },
    {
      "epoch": 0.11238424109245017,
      "grad_norm": 0.4276205897331238,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8421,
      "step": 179
    },
    {
      "epoch": 0.11301208601475436,
      "grad_norm": 0.516444742679596,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7521,
      "step": 180
    },
    {
      "epoch": 0.11363993093705854,
      "grad_norm": 0.43327686190605164,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6802,
      "step": 181
    },
    {
      "epoch": 0.11426777585936274,
      "grad_norm": 0.48601460456848145,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7673,
      "step": 182
    },
    {
      "epoch": 0.11489562078166693,
      "grad_norm": 0.5008496642112732,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7807,
      "step": 183
    },
    {
      "epoch": 0.11552346570397112,
      "grad_norm": 0.6235164403915405,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.8758,
      "step": 184
    },
    {
      "epoch": 0.1161513106262753,
      "grad_norm": 0.581714928150177,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7932,
      "step": 185
    },
    {
      "epoch": 0.1167791555485795,
      "grad_norm": 0.5634011626243591,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.9109,
      "step": 186
    },
    {
      "epoch": 0.11740700047088369,
      "grad_norm": 0.627421498298645,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8334,
      "step": 187
    },
    {
      "epoch": 0.11803484539318788,
      "grad_norm": 0.882683515548706,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8584,
      "step": 188
    },
    {
      "epoch": 0.11866269031549208,
      "grad_norm": 0.7387759685516357,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8658,
      "step": 189
    },
    {
      "epoch": 0.11929053523779626,
      "grad_norm": 0.7666494846343994,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.0099,
      "step": 190
    },
    {
      "epoch": 0.11991838016010045,
      "grad_norm": 0.7859662771224976,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9175,
      "step": 191
    },
    {
      "epoch": 0.12054622508240465,
      "grad_norm": 0.8232308030128479,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.9784,
      "step": 192
    },
    {
      "epoch": 0.12117407000470884,
      "grad_norm": 0.7969563603401184,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8614,
      "step": 193
    },
    {
      "epoch": 0.12180191492701303,
      "grad_norm": 0.9747658967971802,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.9497,
      "step": 194
    },
    {
      "epoch": 0.12242975984931721,
      "grad_norm": 0.8652091026306152,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.941,
      "step": 195
    },
    {
      "epoch": 0.1230576047716214,
      "grad_norm": 1.0952799320220947,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.3195,
      "step": 196
    },
    {
      "epoch": 0.1236854496939256,
      "grad_norm": 1.0180470943450928,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.047,
      "step": 197
    },
    {
      "epoch": 0.1243132946162298,
      "grad_norm": 1.1498470306396484,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.1476,
      "step": 198
    },
    {
      "epoch": 0.12494113953853399,
      "grad_norm": 1.3460142612457275,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.9823,
      "step": 199
    },
    {
      "epoch": 0.12556898446083817,
      "grad_norm": 1.7192878723144531,
      "learning_rate": 0.0,
      "loss": 0.9939,
      "step": 200
    },
    {
      "epoch": 0.12556898446083817,
      "eval_loss": 0.8316019177436829,
      "eval_runtime": 84.2744,
      "eval_samples_per_second": 31.836,
      "eval_steps_per_second": 7.962,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.742253817462784e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}