{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2883922134102379,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 4.551077290670946e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0014419610670511895,
      "eval_loss": 11.5,
      "eval_runtime": 6.5915,
      "eval_samples_per_second": 177.349,
      "eval_steps_per_second": 44.451,
      "step": 1
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 2.4219067199737765e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.004325883201153569,
      "grad_norm": 3.92902220482938e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.005767844268204758,
      "grad_norm": 2.3436263290932402e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.007209805335255948,
      "grad_norm": 2.706063060031738e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.008651766402307137,
      "grad_norm": 2.5919249310391024e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.010093727469358327,
      "grad_norm": 3.103033304796554e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.011535688536409516,
      "grad_norm": 2.729930383793544e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.012977649603460706,
      "grad_norm": 2.600135121610947e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.014419610670511895,
      "grad_norm": 4.012700810562819e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.015861571737563085,
      "grad_norm": 3.073212428716943e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.017303532804614274,
      "grad_norm": 5.821282684337348e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.018745493871665464,
      "grad_norm": 5.5768283345969394e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.020187454938716654,
      "grad_norm": 6.005035902489908e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.021629416005767843,
      "grad_norm": 6.563588976860046e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.023071377072819033,
      "grad_norm": 6.29853384452872e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.024513338139870222,
      "grad_norm": 9.260119986720383e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.02595529920692141,
      "grad_norm": 6.250675505725667e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 7.49466780689545e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.02883922134102379,
      "grad_norm": 5.8534747950034216e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.03028118240807498,
      "grad_norm": 5.025664358981885e-05,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.03172314347512617,
      "grad_norm": 3.9194019336719066e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.03316510454217736,
      "grad_norm": 5.6159224186558276e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.03460706560922855,
      "grad_norm": 7.44333301554434e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.03604902667627974,
      "grad_norm": 5.360547220334411e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.03749098774333093,
      "grad_norm": 6.715447671012953e-05,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.03893294881038212,
      "grad_norm": 5.926714220549911e-05,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.04037490987743331,
      "grad_norm": 6.435975956264883e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.0418168709444845,
      "grad_norm": 5.97175931034144e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.043258832011535686,
      "grad_norm": 5.983871960779652e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.044700793078586876,
      "grad_norm": 6.905582995386794e-05,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.046142754145638065,
      "grad_norm": 8.603069727541879e-05,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.047584715212689255,
      "grad_norm": 0.00010996026685461402,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.049026676279740444,
      "grad_norm": 0.00011664038902381435,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.050468637346791634,
      "grad_norm": 5.231019895290956e-05,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.05191059841384282,
      "grad_norm": 0.00012090209202142432,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.05335255948089401,
      "grad_norm": 8.062404958764091e-05,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 9.336588846053928e-05,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.05623648161499639,
      "grad_norm": 8.884619455784559e-05,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.05767844268204758,
      "grad_norm": 9.600253542885184e-05,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.05912040374909877,
      "grad_norm": 0.00015312367759179324,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.06056236481614996,
      "grad_norm": 8.023295231396332e-05,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.06200432588320115,
      "grad_norm": 8.562370931031182e-05,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.06344628695025234,
      "grad_norm": 0.00015367928426712751,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.06488824801730353,
      "grad_norm": 0.00016452718409709632,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.06633020908435472,
      "grad_norm": 0.00010999064397765324,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.06777217015140591,
      "grad_norm": 0.00016317500558216125,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.0692141312184571,
      "grad_norm": 0.00016825605416670442,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.07065609228550829,
      "grad_norm": 0.0001684524759184569,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.07209805335255948,
      "grad_norm": 0.00018130935495719314,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.07209805335255948,
      "eval_loss": 11.5,
      "eval_runtime": 6.5542,
      "eval_samples_per_second": 178.358,
      "eval_steps_per_second": 44.704,
      "step": 50
    },
    {
      "epoch": 0.07354001441961067,
      "grad_norm": 0.00014630900113843381,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.07498197548666186,
      "grad_norm": 0.00016575051995459944,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.07642393655371305,
      "grad_norm": 9.503810724709183e-05,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.07786589762076424,
      "grad_norm": 0.00010648839815985411,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.07930785868781542,
      "grad_norm": 0.00011491494660731405,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.08074981975486661,
      "grad_norm": 0.00013562277308665216,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.0821917808219178,
      "grad_norm": 0.00015486359188798815,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.083633741888969,
      "grad_norm": 0.00012581907503772527,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.08507570295602018,
      "grad_norm": 0.00029646081384271383,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.08651766402307137,
      "grad_norm": 0.00019654743664432317,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.08795962509012256,
      "grad_norm": 0.0001651565107749775,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.08940158615717375,
      "grad_norm": 0.0001822762133087963,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.09084354722422494,
      "grad_norm": 0.00013959217176306993,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.09228550829127613,
      "grad_norm": 0.00022408162476494908,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.09372746935832732,
      "grad_norm": 0.00035673525417223573,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.09516943042537851,
      "grad_norm": 0.00041785562643781304,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.0966113914924297,
      "grad_norm": 0.00033946934854611754,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.09805335255948089,
      "grad_norm": 0.00011334617011016235,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.09949531362653208,
      "grad_norm": 0.00015962774341460317,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.10093727469358327,
      "grad_norm": 0.00016410488751716912,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.10237923576063446,
      "grad_norm": 0.0001240667625097558,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.10382119682768565,
      "grad_norm": 0.00020238997240085155,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.00023328776296693832,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.10670511896178803,
      "grad_norm": 0.00017381407087668777,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.10814708002883922,
      "grad_norm": 0.0003512923140078783,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.1095890410958904,
      "grad_norm": 0.000159394956426695,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.1110310021629416,
      "grad_norm": 0.0003031495143659413,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.11247296322999278,
      "grad_norm": 0.0002476269437465817,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.11391492429704397,
      "grad_norm": 0.0002291841374244541,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.11535688536409516,
      "grad_norm": 0.0004125789273530245,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.11679884643114635,
      "grad_norm": 0.000245795730734244,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.11824080749819754,
      "grad_norm": 0.00022407225333154202,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.11968276856524873,
      "grad_norm": 0.000303188367979601,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.12112472963229992,
      "grad_norm": 0.00023917999351397157,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.12256669069935111,
      "grad_norm": 0.00031476496951654553,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.1240086517664023,
      "grad_norm": 0.00023287246585823596,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.1254506128334535,
      "grad_norm": 0.0003421494329813868,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.12689257390050468,
      "grad_norm": 0.0002833238977473229,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.12833453496755587,
      "grad_norm": 0.0006084145279601216,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.12977649603460706,
      "grad_norm": 0.00033296371111646295,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.13121845710165825,
      "grad_norm": 0.00019833420810755342,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.13266041816870944,
      "grad_norm": 0.00040156146860681474,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.13410237923576063,
      "grad_norm": 0.00037203371175564826,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.13554434030281182,
      "grad_norm": 0.0004838180320803076,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.0003659892827272415,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.1384282624369142,
      "grad_norm": 0.0003629039856605232,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.13987022350396539,
      "grad_norm": 0.0003685996343847364,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.14131218457101657,
      "grad_norm": 0.0002297442697454244,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.14275414563806776,
      "grad_norm": 0.0004087391134817153,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.14419610670511895,
      "grad_norm": 0.0005655571003444493,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.14419610670511895,
      "eval_loss": 11.5,
      "eval_runtime": 6.6065,
      "eval_samples_per_second": 176.946,
      "eval_steps_per_second": 44.35,
      "step": 100
    },
    {
      "epoch": 0.14563806777217014,
      "grad_norm": 0.00042799723451025784,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.14708002883922133,
      "grad_norm": 0.0002950059133581817,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.14852198990627252,
      "grad_norm": 0.00034281116677448153,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.1499639509733237,
      "grad_norm": 0.0003310093597974628,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.1514059120403749,
      "grad_norm": 0.000291879172436893,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.1528478731074261,
      "grad_norm": 0.0002692980342544615,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.15428983417447728,
      "grad_norm": 0.00028849768568761647,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.15573179524152847,
      "grad_norm": 0.0005160836153663695,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.15717375630857966,
      "grad_norm": 0.00044572551269084215,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.15861571737563085,
      "grad_norm": 0.0004114356997888535,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.16005767844268204,
      "grad_norm": 0.0004075924807693809,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.16149963950973323,
      "grad_norm": 0.0002814109902828932,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.16294160057678442,
      "grad_norm": 0.00031008722726255655,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.1643835616438356,
      "grad_norm": 0.00041551413596607745,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.1658255227108868,
      "grad_norm": 0.0005826354026794434,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.167267483777938,
      "grad_norm": 0.0006468302453868091,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.16870944484498918,
      "grad_norm": 0.0007035377784632146,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.17015140591204037,
      "grad_norm": 0.0009079411393031478,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.17159336697909156,
      "grad_norm": 0.0007139816298149526,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.17303532804614274,
      "grad_norm": 0.000289363379124552,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.17447728911319393,
      "grad_norm": 0.00035587575985118747,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.17591925018024512,
      "grad_norm": 0.0002553342783357948,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.1773612112472963,
      "grad_norm": 0.0004354972916189581,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.1788031723143475,
      "grad_norm": 0.0004603854613378644,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.1802451333813987,
      "grad_norm": 0.00033851119223982096,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.18168709444844988,
      "grad_norm": 0.0004575979255605489,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.18312905551550107,
      "grad_norm": 0.0003578352043405175,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.18457101658255226,
      "grad_norm": 0.0005673786508850753,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.18601297764960345,
      "grad_norm": 0.00038473171298392117,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.18745493871665464,
      "grad_norm": 0.00029242614982649684,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.18889689978370583,
      "grad_norm": 0.00043768316390924156,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.19033886085075702,
      "grad_norm": 0.0003826096944976598,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.1917808219178082,
      "grad_norm": 0.00034478920861147344,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.1932227829848594,
      "grad_norm": 0.0005700316978618503,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.1946647440519106,
      "grad_norm": 0.0005131760844960809,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.19610670511896178,
      "grad_norm": 0.0005202844040468335,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.19754866618601297,
      "grad_norm": 0.0008862287504598498,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.19899062725306416,
      "grad_norm": 0.0005221064784564078,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.20043258832011535,
      "grad_norm": 0.0005167109775356948,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.20187454938716654,
      "grad_norm": 0.0002810164005495608,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.20331651045421772,
      "grad_norm": 0.00046170668792910874,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.20475847152126891,
      "grad_norm": 0.0007621386321261525,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.2062004325883201,
      "grad_norm": 0.0005584614118561149,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.2076423936553713,
      "grad_norm": 0.0005563963786698878,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.20908435472242248,
      "grad_norm": 0.0005799828795716166,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.0006164291989989579,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.21196827685652486,
      "grad_norm": 0.00037999034975655377,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.21341023792357605,
      "grad_norm": 0.0004095716285519302,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.21485219899062724,
      "grad_norm": 0.0005592962261289358,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.21629416005767843,
      "grad_norm": 0.001089010969735682,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.21629416005767843,
      "eval_loss": 11.5,
      "eval_runtime": 6.5326,
      "eval_samples_per_second": 178.949,
      "eval_steps_per_second": 44.852,
      "step": 150
    },
    {
      "epoch": 0.21773612112472962,
      "grad_norm": 0.0004330429364927113,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.2191780821917808,
      "grad_norm": 0.0006008841446600854,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.220620043258832,
      "grad_norm": 0.0004464095691218972,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.2220620043258832,
      "grad_norm": 0.0003258266660850495,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.22350396539293438,
      "grad_norm": 0.0006869659409858286,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.22494592645998557,
      "grad_norm": 0.0004445877857506275,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.22638788752703676,
      "grad_norm": 0.00044769182568416,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.22782984859408795,
      "grad_norm": 0.0005077571258880198,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.22927180966113914,
      "grad_norm": 0.000598142680246383,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.23071377072819033,
      "grad_norm": 0.00041002294165082276,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.23215573179524152,
      "grad_norm": 0.0007013846770860255,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.2335976928622927,
      "grad_norm": 0.0006938255974091589,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.2350396539293439,
      "grad_norm": 0.0007473509176634252,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.23648161499639508,
      "grad_norm": 0.0006903844187036157,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.23792357606344627,
      "grad_norm": 0.0005135243409313262,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.23936553713049746,
      "grad_norm": 0.0006711554597131908,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.24080749819754865,
      "grad_norm": 0.0007500555948354304,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.24224945926459984,
      "grad_norm": 0.0010962215019389987,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.24369142033165103,
      "grad_norm": 0.0007046359241940081,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.24513338139870222,
      "grad_norm": 0.0005890610045753419,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.2465753424657534,
      "grad_norm": 0.0005561505677178502,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.2480173035328046,
      "grad_norm": 0.0005682391347363591,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.2494592645998558,
      "grad_norm": 0.0005149398930370808,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.250901225666907,
      "grad_norm": 0.0006176583119668067,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.25234318673395817,
      "grad_norm": 0.00039346740231849253,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.25378514780100936,
      "grad_norm": 0.00048698679893277586,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.25522710886806055,
      "grad_norm": 0.0005501548876054585,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.25666906993511174,
      "grad_norm": 0.0004938711645081639,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.2581110310021629,
      "grad_norm": 0.00038246065378189087,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.2595529920692141,
      "grad_norm": 0.0006007237825542688,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.2609949531362653,
      "grad_norm": 0.0005148351774550974,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.2624369142033165,
      "grad_norm": 0.0005921967094764113,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.2638788752703677,
      "grad_norm": 0.00034092890564352274,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.2653208363374189,
      "grad_norm": 0.0004231817729305476,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.26676279740447006,
      "grad_norm": 0.00067184615181759,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.26820475847152125,
      "grad_norm": 0.0006037729326635599,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.26964671953857244,
      "grad_norm": 0.0005864717531949282,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.27108868060562363,
      "grad_norm": 0.0005135570536367595,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.2725306416726748,
      "grad_norm": 0.0004054594610352069,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.00029847508994862437,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.2754145638067772,
      "grad_norm": 0.0003287815779913217,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.2768565248738284,
      "grad_norm": 0.00041132999467663467,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.2782984859408796,
      "grad_norm": 0.0006741007673554122,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.27974044700793077,
      "grad_norm": 0.0005194243276491761,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.28118240807498196,
      "grad_norm": 0.0006040112348273396,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.28262436914203315,
      "grad_norm": 0.0009013387025333941,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.28406633020908434,
      "grad_norm": 0.0007761934539303184,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.28550829127613553,
      "grad_norm": 0.0003540825273375958,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.2869502523431867,
      "grad_norm": 0.0007028038380667567,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.2883922134102379,
      "grad_norm": 0.0010711703216657043,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.2883922134102379,
      "eval_loss": 11.5,
      "eval_runtime": 6.5507,
      "eval_samples_per_second": 178.455,
      "eval_steps_per_second": 44.728,
      "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": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 43896301682688.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}