{
  "best_metric": 0.9115041494369507,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02817298211015636,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001408649105507818,
      "grad_norm": 10.031426429748535,
      "learning_rate": 1e-05,
      "loss": 2.3655,
      "step": 1
    },
    {
      "epoch": 0.0001408649105507818,
      "eval_loss": 4.294093608856201,
      "eval_runtime": 240.4456,
      "eval_samples_per_second": 49.729,
      "eval_steps_per_second": 12.435,
      "step": 1
    },
    {
      "epoch": 0.0002817298211015636,
      "grad_norm": 16.766931533813477,
      "learning_rate": 2e-05,
      "loss": 3.0245,
      "step": 2
    },
    {
      "epoch": 0.0004225947316523454,
      "grad_norm": 14.750626564025879,
      "learning_rate": 3e-05,
      "loss": 3.262,
      "step": 3
    },
    {
      "epoch": 0.0005634596422031273,
      "grad_norm": 13.338021278381348,
      "learning_rate": 4e-05,
      "loss": 3.3109,
      "step": 4
    },
    {
      "epoch": 0.000704324552753909,
      "grad_norm": 9.850285530090332,
      "learning_rate": 5e-05,
      "loss": 3.5079,
      "step": 5
    },
    {
      "epoch": 0.0008451894633046908,
      "grad_norm": 7.1621174812316895,
      "learning_rate": 6e-05,
      "loss": 2.8592,
      "step": 6
    },
    {
      "epoch": 0.0009860543738554725,
      "grad_norm": 13.172682762145996,
      "learning_rate": 7e-05,
      "loss": 2.8717,
      "step": 7
    },
    {
      "epoch": 0.0011269192844062545,
      "grad_norm": 5.506401538848877,
      "learning_rate": 8e-05,
      "loss": 2.6399,
      "step": 8
    },
    {
      "epoch": 0.0012677841949570363,
      "grad_norm": 3.732410192489624,
      "learning_rate": 9e-05,
      "loss": 2.4251,
      "step": 9
    },
    {
      "epoch": 0.001408649105507818,
      "grad_norm": 3.3708877563476562,
      "learning_rate": 0.0001,
      "loss": 2.3888,
      "step": 10
    },
    {
      "epoch": 0.0015495140160585999,
      "grad_norm": 5.507050037384033,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.2776,
      "step": 11
    },
    {
      "epoch": 0.0016903789266093816,
      "grad_norm": 5.705183506011963,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.2514,
      "step": 12
    },
    {
      "epoch": 0.0018312438371601634,
      "grad_norm": 8.796576499938965,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.1019,
      "step": 13
    },
    {
      "epoch": 0.001972108747710945,
      "grad_norm": 3.9234306812286377,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7961,
      "step": 14
    },
    {
      "epoch": 0.002112973658261727,
      "grad_norm": 2.623748302459717,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.3583,
      "step": 15
    },
    {
      "epoch": 0.002253838568812509,
      "grad_norm": 4.477276802062988,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.4632,
      "step": 16
    },
    {
      "epoch": 0.0023947034793632906,
      "grad_norm": 5.722939968109131,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4597,
      "step": 17
    },
    {
      "epoch": 0.0025355683899140726,
      "grad_norm": 3.1406970024108887,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1818,
      "step": 18
    },
    {
      "epoch": 0.002676433300464854,
      "grad_norm": 3.0936570167541504,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0524,
      "step": 19
    },
    {
      "epoch": 0.002817298211015636,
      "grad_norm": 2.623175859451294,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2207,
      "step": 20
    },
    {
      "epoch": 0.0029581631215664177,
      "grad_norm": 7.455384731292725,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0805,
      "step": 21
    },
    {
      "epoch": 0.0030990280321171997,
      "grad_norm": 2.4907939434051514,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0991,
      "step": 22
    },
    {
      "epoch": 0.0032398929426679813,
      "grad_norm": 2.3516669273376465,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0731,
      "step": 23
    },
    {
      "epoch": 0.0033807578532187633,
      "grad_norm": 1.8740895986557007,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0548,
      "step": 24
    },
    {
      "epoch": 0.003521622763769545,
      "grad_norm": 2.03414249420166,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0929,
      "step": 25
    },
    {
      "epoch": 0.003662487674320327,
      "grad_norm": 2.503605365753174,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8563,
      "step": 26
    },
    {
      "epoch": 0.0038033525848711084,
      "grad_norm": 2.086621046066284,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8946,
      "step": 27
    },
    {
      "epoch": 0.00394421749542189,
      "grad_norm": 2.400827646255493,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8641,
      "step": 28
    },
    {
      "epoch": 0.0040850824059726724,
      "grad_norm": 2.0889105796813965,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7307,
      "step": 29
    },
    {
      "epoch": 0.004225947316523454,
      "grad_norm": 1.8822883367538452,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7232,
      "step": 30
    },
    {
      "epoch": 0.004366812227074236,
      "grad_norm": 2.5694515705108643,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8975,
      "step": 31
    },
    {
      "epoch": 0.004507677137625018,
      "grad_norm": 3.4608964920043945,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6979,
      "step": 32
    },
    {
      "epoch": 0.0046485420481758,
      "grad_norm": 2.8889780044555664,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8112,
      "step": 33
    },
    {
      "epoch": 0.004789406958726581,
      "grad_norm": 3.957289218902588,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6703,
      "step": 34
    },
    {
      "epoch": 0.004930271869277363,
      "grad_norm": 1.575763463973999,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.473,
      "step": 35
    },
    {
      "epoch": 0.005071136779828145,
      "grad_norm": 1.765645146369934,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.4878,
      "step": 36
    },
    {
      "epoch": 0.005212001690378927,
      "grad_norm": 1.6332755088806152,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7539,
      "step": 37
    },
    {
      "epoch": 0.005352866600929708,
      "grad_norm": 2.3892107009887695,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7547,
      "step": 38
    },
    {
      "epoch": 0.00549373151148049,
      "grad_norm": 2.25726580619812,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5751,
      "step": 39
    },
    {
      "epoch": 0.005634596422031272,
      "grad_norm": 2.58968448638916,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7205,
      "step": 40
    },
    {
      "epoch": 0.005775461332582054,
      "grad_norm": 2.499601364135742,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6855,
      "step": 41
    },
    {
      "epoch": 0.0059163262431328354,
      "grad_norm": 6.7224273681640625,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9355,
      "step": 42
    },
    {
      "epoch": 0.006057191153683617,
      "grad_norm": 2.4964160919189453,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.965,
      "step": 43
    },
    {
      "epoch": 0.0061980560642343994,
      "grad_norm": 1.7799794673919678,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9326,
      "step": 44
    },
    {
      "epoch": 0.006338920974785181,
      "grad_norm": 2.3146729469299316,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3381,
      "step": 45
    },
    {
      "epoch": 0.006479785885335963,
      "grad_norm": 3.97938871383667,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.7827,
      "step": 46
    },
    {
      "epoch": 0.006620650795886745,
      "grad_norm": 3.983363628387451,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.7851,
      "step": 47
    },
    {
      "epoch": 0.006761515706437527,
      "grad_norm": 5.531325340270996,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2786,
      "step": 48
    },
    {
      "epoch": 0.006902380616988308,
      "grad_norm": 6.642470836639404,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.0166,
      "step": 49
    },
    {
      "epoch": 0.00704324552753909,
      "grad_norm": 7.111599445343018,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.3552,
      "step": 50
    },
    {
      "epoch": 0.00704324552753909,
      "eval_loss": 1.4570739269256592,
      "eval_runtime": 240.4101,
      "eval_samples_per_second": 49.736,
      "eval_steps_per_second": 12.437,
      "step": 50
    },
    {
      "epoch": 0.007184110438089872,
      "grad_norm": 11.111729621887207,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.4741,
      "step": 51
    },
    {
      "epoch": 0.007324975348640654,
      "grad_norm": 9.560843467712402,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.4055,
      "step": 52
    },
    {
      "epoch": 0.007465840259191435,
      "grad_norm": 5.6692280769348145,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.2072,
      "step": 53
    },
    {
      "epoch": 0.007606705169742217,
      "grad_norm": 3.938448190689087,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.0505,
      "step": 54
    },
    {
      "epoch": 0.007747570080292999,
      "grad_norm": 2.66489315032959,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.8585,
      "step": 55
    },
    {
      "epoch": 0.00788843499084378,
      "grad_norm": 1.8790820837020874,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.823,
      "step": 56
    },
    {
      "epoch": 0.008029299901394563,
      "grad_norm": 2.0918898582458496,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.8211,
      "step": 57
    },
    {
      "epoch": 0.008170164811945345,
      "grad_norm": 2.090571165084839,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5641,
      "step": 58
    },
    {
      "epoch": 0.008311029722496126,
      "grad_norm": 2.2309327125549316,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.728,
      "step": 59
    },
    {
      "epoch": 0.008451894633046908,
      "grad_norm": 1.7858821153640747,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.699,
      "step": 60
    },
    {
      "epoch": 0.00859275954359769,
      "grad_norm": 1.542462706565857,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.4813,
      "step": 61
    },
    {
      "epoch": 0.008733624454148471,
      "grad_norm": 1.2382235527038574,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.4708,
      "step": 62
    },
    {
      "epoch": 0.008874489364699253,
      "grad_norm": 1.4558863639831543,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1363,
      "step": 63
    },
    {
      "epoch": 0.009015354275250036,
      "grad_norm": 1.6121326684951782,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.0638,
      "step": 64
    },
    {
      "epoch": 0.009156219185800818,
      "grad_norm": 1.290604829788208,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9822,
      "step": 65
    },
    {
      "epoch": 0.0092970840963516,
      "grad_norm": 1.4775842428207397,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.1594,
      "step": 66
    },
    {
      "epoch": 0.00943794900690238,
      "grad_norm": 1.4290190935134888,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8742,
      "step": 67
    },
    {
      "epoch": 0.009578813917453162,
      "grad_norm": 1.162203073501587,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7075,
      "step": 68
    },
    {
      "epoch": 0.009719678828003944,
      "grad_norm": 1.4816632270812988,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8478,
      "step": 69
    },
    {
      "epoch": 0.009860543738554725,
      "grad_norm": 1.1275964975357056,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7481,
      "step": 70
    },
    {
      "epoch": 0.010001408649105507,
      "grad_norm": 1.0901832580566406,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.771,
      "step": 71
    },
    {
      "epoch": 0.01014227355965629,
      "grad_norm": 1.3845051527023315,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8662,
      "step": 72
    },
    {
      "epoch": 0.010283138470207072,
      "grad_norm": 1.2006878852844238,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5596,
      "step": 73
    },
    {
      "epoch": 0.010424003380757853,
      "grad_norm": 1.6490373611450195,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8285,
      "step": 74
    },
    {
      "epoch": 0.010564868291308635,
      "grad_norm": 1.2739609479904175,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6566,
      "step": 75
    },
    {
      "epoch": 0.010705733201859417,
      "grad_norm": 1.1623024940490723,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6666,
      "step": 76
    },
    {
      "epoch": 0.010846598112410198,
      "grad_norm": 1.4328917264938354,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5614,
      "step": 77
    },
    {
      "epoch": 0.01098746302296098,
      "grad_norm": 1.2306725978851318,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5582,
      "step": 78
    },
    {
      "epoch": 0.011128327933511763,
      "grad_norm": 1.353375792503357,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6759,
      "step": 79
    },
    {
      "epoch": 0.011269192844062545,
      "grad_norm": 1.295104742050171,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6997,
      "step": 80
    },
    {
      "epoch": 0.011410057754613326,
      "grad_norm": 1.742098331451416,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6682,
      "step": 81
    },
    {
      "epoch": 0.011550922665164108,
      "grad_norm": 1.1515581607818604,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5445,
      "step": 82
    },
    {
      "epoch": 0.01169178757571489,
      "grad_norm": 1.251039981842041,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3921,
      "step": 83
    },
    {
      "epoch": 0.011832652486265671,
      "grad_norm": 1.612655520439148,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7296,
      "step": 84
    },
    {
      "epoch": 0.011973517396816452,
      "grad_norm": 1.2194619178771973,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.5372,
      "step": 85
    },
    {
      "epoch": 0.012114382307367234,
      "grad_norm": 1.538738489151001,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5495,
      "step": 86
    },
    {
      "epoch": 0.012255247217918017,
      "grad_norm": 1.1339927911758423,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.4999,
      "step": 87
    },
    {
      "epoch": 0.012396112128468799,
      "grad_norm": 1.3610646724700928,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6225,
      "step": 88
    },
    {
      "epoch": 0.01253697703901958,
      "grad_norm": 1.2226330041885376,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.4756,
      "step": 89
    },
    {
      "epoch": 0.012677841949570362,
      "grad_norm": 1.316048264503479,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5727,
      "step": 90
    },
    {
      "epoch": 0.012818706860121144,
      "grad_norm": 1.595350980758667,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.0199,
      "step": 91
    },
    {
      "epoch": 0.012959571770671925,
      "grad_norm": 1.6149495840072632,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8526,
      "step": 92
    },
    {
      "epoch": 0.013100436681222707,
      "grad_norm": 1.4621623754501343,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5669,
      "step": 93
    },
    {
      "epoch": 0.01324130159177349,
      "grad_norm": 1.6394346952438354,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8591,
      "step": 94
    },
    {
      "epoch": 0.013382166502324272,
      "grad_norm": 2.0890185832977295,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.1071,
      "step": 95
    },
    {
      "epoch": 0.013523031412875053,
      "grad_norm": 1.8629014492034912,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1249,
      "step": 96
    },
    {
      "epoch": 0.013663896323425835,
      "grad_norm": 2.2603368759155273,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.3536,
      "step": 97
    },
    {
      "epoch": 0.013804761233976616,
      "grad_norm": 2.8389956951141357,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.5428,
      "step": 98
    },
    {
      "epoch": 0.013945626144527398,
      "grad_norm": 4.9247589111328125,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.1399,
      "step": 99
    },
    {
      "epoch": 0.01408649105507818,
      "grad_norm": 6.604344367980957,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.5073,
      "step": 100
    },
    {
      "epoch": 0.01408649105507818,
      "eval_loss": 1.0559614896774292,
      "eval_runtime": 240.4752,
      "eval_samples_per_second": 49.722,
      "eval_steps_per_second": 12.434,
      "step": 100
    },
    {
      "epoch": 0.014227355965628961,
      "grad_norm": 2.887002468109131,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.8021,
      "step": 101
    },
    {
      "epoch": 0.014368220876179744,
      "grad_norm": 2.8153011798858643,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.0186,
      "step": 102
    },
    {
      "epoch": 0.014509085786730526,
      "grad_norm": 2.0159571170806885,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.8548,
      "step": 103
    },
    {
      "epoch": 0.014649950697281307,
      "grad_norm": 1.593695044517517,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.6752,
      "step": 104
    },
    {
      "epoch": 0.014790815607832089,
      "grad_norm": 1.177317500114441,
      "learning_rate": 5e-05,
      "loss": 1.6363,
      "step": 105
    },
    {
      "epoch": 0.01493168051838287,
      "grad_norm": 1.0343564748764038,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.6538,
      "step": 106
    },
    {
      "epoch": 0.015072545428933652,
      "grad_norm": 1.4447541236877441,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6313,
      "step": 107
    },
    {
      "epoch": 0.015213410339484434,
      "grad_norm": 1.1493356227874756,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.5003,
      "step": 108
    },
    {
      "epoch": 0.015354275250035217,
      "grad_norm": 1.1778674125671387,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.581,
      "step": 109
    },
    {
      "epoch": 0.015495140160585999,
      "grad_norm": 1.0966111421585083,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4677,
      "step": 110
    },
    {
      "epoch": 0.01563600507113678,
      "grad_norm": 0.9785053730010986,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.5391,
      "step": 111
    },
    {
      "epoch": 0.01577686998168756,
      "grad_norm": 1.2195751667022705,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.5638,
      "step": 112
    },
    {
      "epoch": 0.015917734892238345,
      "grad_norm": 1.2555761337280273,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.3653,
      "step": 113
    },
    {
      "epoch": 0.016058599802789127,
      "grad_norm": 1.09703528881073,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.1986,
      "step": 114
    },
    {
      "epoch": 0.016199464713339908,
      "grad_norm": 1.1482305526733398,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9653,
      "step": 115
    },
    {
      "epoch": 0.01634032962389069,
      "grad_norm": 1.1685477495193481,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8309,
      "step": 116
    },
    {
      "epoch": 0.01648119453444147,
      "grad_norm": 1.2618950605392456,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7785,
      "step": 117
    },
    {
      "epoch": 0.016622059444992253,
      "grad_norm": 1.070701241493225,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7443,
      "step": 118
    },
    {
      "epoch": 0.016762924355543034,
      "grad_norm": 1.0922602415084839,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7625,
      "step": 119
    },
    {
      "epoch": 0.016903789266093816,
      "grad_norm": 1.0013766288757324,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6861,
      "step": 120
    },
    {
      "epoch": 0.017044654176644598,
      "grad_norm": 0.8868520259857178,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5199,
      "step": 121
    },
    {
      "epoch": 0.01718551908719538,
      "grad_norm": 1.3038041591644287,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7734,
      "step": 122
    },
    {
      "epoch": 0.01732638399774616,
      "grad_norm": 0.9778259992599487,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3785,
      "step": 123
    },
    {
      "epoch": 0.017467248908296942,
      "grad_norm": 1.215434193611145,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6427,
      "step": 124
    },
    {
      "epoch": 0.017608113818847724,
      "grad_norm": 1.095554232597351,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.681,
      "step": 125
    },
    {
      "epoch": 0.017748978729398505,
      "grad_norm": 0.9972038865089417,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5964,
      "step": 126
    },
    {
      "epoch": 0.017889843639949287,
      "grad_norm": 1.1521289348602295,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.635,
      "step": 127
    },
    {
      "epoch": 0.018030708550500072,
      "grad_norm": 1.0549938678741455,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5407,
      "step": 128
    },
    {
      "epoch": 0.018171573461050854,
      "grad_norm": 1.1805520057678223,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5329,
      "step": 129
    },
    {
      "epoch": 0.018312438371601635,
      "grad_norm": 0.9551267027854919,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5759,
      "step": 130
    },
    {
      "epoch": 0.018453303282152417,
      "grad_norm": 1.0043541193008423,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.4533,
      "step": 131
    },
    {
      "epoch": 0.0185941681927032,
      "grad_norm": 1.1569894552230835,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5385,
      "step": 132
    },
    {
      "epoch": 0.01873503310325398,
      "grad_norm": 1.168152928352356,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5891,
      "step": 133
    },
    {
      "epoch": 0.01887589801380476,
      "grad_norm": 1.546726107597351,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5819,
      "step": 134
    },
    {
      "epoch": 0.019016762924355543,
      "grad_norm": 1.0554989576339722,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4015,
      "step": 135
    },
    {
      "epoch": 0.019157627834906325,
      "grad_norm": 1.2026422023773193,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5737,
      "step": 136
    },
    {
      "epoch": 0.019298492745457106,
      "grad_norm": 1.1748453378677368,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.4456,
      "step": 137
    },
    {
      "epoch": 0.019439357656007888,
      "grad_norm": 1.128390908241272,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4957,
      "step": 138
    },
    {
      "epoch": 0.01958022256655867,
      "grad_norm": 1.0329426527023315,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4172,
      "step": 139
    },
    {
      "epoch": 0.01972108747710945,
      "grad_norm": 1.3100541830062866,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6806,
      "step": 140
    },
    {
      "epoch": 0.019861952387660232,
      "grad_norm": 1.3865808248519897,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6796,
      "step": 141
    },
    {
      "epoch": 0.020002817298211014,
      "grad_norm": 1.2001882791519165,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6636,
      "step": 142
    },
    {
      "epoch": 0.0201436822087618,
      "grad_norm": 1.2058801651000977,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4662,
      "step": 143
    },
    {
      "epoch": 0.02028454711931258,
      "grad_norm": 1.5428941249847412,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7921,
      "step": 144
    },
    {
      "epoch": 0.020425412029863362,
      "grad_norm": 1.979830265045166,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.0626,
      "step": 145
    },
    {
      "epoch": 0.020566276940414144,
      "grad_norm": 1.9408612251281738,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2731,
      "step": 146
    },
    {
      "epoch": 0.020707141850964925,
      "grad_norm": 2.5928618907928467,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.6249,
      "step": 147
    },
    {
      "epoch": 0.020848006761515707,
      "grad_norm": 3.2012157440185547,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.8548,
      "step": 148
    },
    {
      "epoch": 0.02098887167206649,
      "grad_norm": 3.9775068759918213,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.2191,
      "step": 149
    },
    {
      "epoch": 0.02112973658261727,
      "grad_norm": 4.948117256164551,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.9147,
      "step": 150
    },
    {
      "epoch": 0.02112973658261727,
      "eval_loss": 0.9419289827346802,
      "eval_runtime": 240.6256,
      "eval_samples_per_second": 49.691,
      "eval_steps_per_second": 12.426,
      "step": 150
    },
    {
      "epoch": 0.02127060149316805,
      "grad_norm": 1.0878514051437378,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.6726,
      "step": 151
    },
    {
      "epoch": 0.021411466403718833,
      "grad_norm": 1.0623815059661865,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.6916,
      "step": 152
    },
    {
      "epoch": 0.021552331314269615,
      "grad_norm": 1.0711852312088013,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.6456,
      "step": 153
    },
    {
      "epoch": 0.021693196224820396,
      "grad_norm": 1.095349907875061,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.5386,
      "step": 154
    },
    {
      "epoch": 0.021834061135371178,
      "grad_norm": 1.117181658744812,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5603,
      "step": 155
    },
    {
      "epoch": 0.02197492604592196,
      "grad_norm": 1.0599151849746704,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.5758,
      "step": 156
    },
    {
      "epoch": 0.02211579095647274,
      "grad_norm": 1.238513469696045,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.4477,
      "step": 157
    },
    {
      "epoch": 0.022256655867023526,
      "grad_norm": 1.0846638679504395,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.4935,
      "step": 158
    },
    {
      "epoch": 0.022397520777574308,
      "grad_norm": 0.9871233105659485,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.4659,
      "step": 159
    },
    {
      "epoch": 0.02253838568812509,
      "grad_norm": 0.8809639811515808,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.4388,
      "step": 160
    },
    {
      "epoch": 0.02267925059867587,
      "grad_norm": 1.06869637966156,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.411,
      "step": 161
    },
    {
      "epoch": 0.022820115509226652,
      "grad_norm": 1.0334460735321045,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.3922,
      "step": 162
    },
    {
      "epoch": 0.022960980419777434,
      "grad_norm": 1.0815767049789429,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.2353,
      "step": 163
    },
    {
      "epoch": 0.023101845330328215,
      "grad_norm": 1.011731505393982,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.0058,
      "step": 164
    },
    {
      "epoch": 0.023242710240878997,
      "grad_norm": 1.0561490058898926,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.9795,
      "step": 165
    },
    {
      "epoch": 0.02338357515142978,
      "grad_norm": 1.0829837322235107,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7604,
      "step": 166
    },
    {
      "epoch": 0.02352444006198056,
      "grad_norm": 1.061506748199463,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7537,
      "step": 167
    },
    {
      "epoch": 0.023665304972531342,
      "grad_norm": 1.2192951440811157,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7691,
      "step": 168
    },
    {
      "epoch": 0.023806169883082123,
      "grad_norm": 0.9931419491767883,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6925,
      "step": 169
    },
    {
      "epoch": 0.023947034793632905,
      "grad_norm": 1.1237553358078003,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6607,
      "step": 170
    },
    {
      "epoch": 0.024087899704183686,
      "grad_norm": 0.9475985169410706,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4728,
      "step": 171
    },
    {
      "epoch": 0.024228764614734468,
      "grad_norm": 0.9906058311462402,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4381,
      "step": 172
    },
    {
      "epoch": 0.024369629525285253,
      "grad_norm": 1.1014072895050049,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7566,
      "step": 173
    },
    {
      "epoch": 0.024510494435836035,
      "grad_norm": 0.8619956970214844,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.542,
      "step": 174
    },
    {
      "epoch": 0.024651359346386816,
      "grad_norm": 1.0860676765441895,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6004,
      "step": 175
    },
    {
      "epoch": 0.024792224256937598,
      "grad_norm": 0.81134033203125,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3481,
      "step": 176
    },
    {
      "epoch": 0.02493308916748838,
      "grad_norm": 0.9432341456413269,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.4651,
      "step": 177
    },
    {
      "epoch": 0.02507395407803916,
      "grad_norm": 1.0585299730300903,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4727,
      "step": 178
    },
    {
      "epoch": 0.025214818988589943,
      "grad_norm": 1.0892884731292725,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5738,
      "step": 179
    },
    {
      "epoch": 0.025355683899140724,
      "grad_norm": 1.020096778869629,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.4461,
      "step": 180
    },
    {
      "epoch": 0.025496548809691506,
      "grad_norm": 1.0234267711639404,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7116,
      "step": 181
    },
    {
      "epoch": 0.025637413720242287,
      "grad_norm": 1.179887056350708,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5594,
      "step": 182
    },
    {
      "epoch": 0.02577827863079307,
      "grad_norm": 1.141302227973938,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.5245,
      "step": 183
    },
    {
      "epoch": 0.02591914354134385,
      "grad_norm": 1.1566119194030762,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6137,
      "step": 184
    },
    {
      "epoch": 0.026060008451894632,
      "grad_norm": 1.1616133451461792,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6218,
      "step": 185
    },
    {
      "epoch": 0.026200873362445413,
      "grad_norm": 1.0435168743133545,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.4814,
      "step": 186
    },
    {
      "epoch": 0.026341738272996195,
      "grad_norm": 1.2150477170944214,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5318,
      "step": 187
    },
    {
      "epoch": 0.02648260318354698,
      "grad_norm": 1.2159531116485596,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6269,
      "step": 188
    },
    {
      "epoch": 0.02662346809409776,
      "grad_norm": 1.1057060956954956,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4851,
      "step": 189
    },
    {
      "epoch": 0.026764333004648543,
      "grad_norm": 1.1494845151901245,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.575,
      "step": 190
    },
    {
      "epoch": 0.026905197915199325,
      "grad_norm": 1.2840725183486938,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6747,
      "step": 191
    },
    {
      "epoch": 0.027046062825750106,
      "grad_norm": 1.4548262357711792,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6246,
      "step": 192
    },
    {
      "epoch": 0.027186927736300888,
      "grad_norm": 1.720304250717163,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9237,
      "step": 193
    },
    {
      "epoch": 0.02732779264685167,
      "grad_norm": 1.5628831386566162,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.838,
      "step": 194
    },
    {
      "epoch": 0.02746865755740245,
      "grad_norm": 2.1154491901397705,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.6394,
      "step": 195
    },
    {
      "epoch": 0.027609522467953233,
      "grad_norm": 2.5567712783813477,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2338,
      "step": 196
    },
    {
      "epoch": 0.027750387378504014,
      "grad_norm": 3.1548426151275635,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.6897,
      "step": 197
    },
    {
      "epoch": 0.027891252289054796,
      "grad_norm": 3.1215031147003174,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.555,
      "step": 198
    },
    {
      "epoch": 0.028032117199605577,
      "grad_norm": 3.6758432388305664,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.4616,
      "step": 199
    },
    {
      "epoch": 0.02817298211015636,
      "grad_norm": 4.911721229553223,
      "learning_rate": 0.0,
      "loss": 1.4568,
      "step": 200
    },
    {
      "epoch": 0.02817298211015636,
      "eval_loss": 0.9115041494369507,
      "eval_runtime": 240.4958,
      "eval_samples_per_second": 49.718,
      "eval_steps_per_second": 12.433,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.287627183469363e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}