{
  "best_metric": 1.5025569200515747,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10038900740368929,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005019450370184465,
      "grad_norm": 0.07296106219291687,
      "learning_rate": 1e-05,
      "loss": 1.7602,
      "step": 1
    },
    {
      "epoch": 0.0005019450370184465,
      "eval_loss": 1.7801587581634521,
      "eval_runtime": 53.2276,
      "eval_samples_per_second": 63.05,
      "eval_steps_per_second": 15.762,
      "step": 1
    },
    {
      "epoch": 0.001003890074036893,
      "grad_norm": 0.0851474478840828,
      "learning_rate": 2e-05,
      "loss": 1.8502,
      "step": 2
    },
    {
      "epoch": 0.0015058351110553395,
      "grad_norm": 0.08229213207960129,
      "learning_rate": 3e-05,
      "loss": 1.795,
      "step": 3
    },
    {
      "epoch": 0.002007780148073786,
      "grad_norm": 0.08867861330509186,
      "learning_rate": 4e-05,
      "loss": 1.8198,
      "step": 4
    },
    {
      "epoch": 0.0025097251850922323,
      "grad_norm": 0.0856841430068016,
      "learning_rate": 5e-05,
      "loss": 1.8206,
      "step": 5
    },
    {
      "epoch": 0.003011670222110679,
      "grad_norm": 0.08929572999477386,
      "learning_rate": 6e-05,
      "loss": 1.8081,
      "step": 6
    },
    {
      "epoch": 0.003513615259129125,
      "grad_norm": 0.08427106589078903,
      "learning_rate": 7e-05,
      "loss": 1.795,
      "step": 7
    },
    {
      "epoch": 0.004015560296147572,
      "grad_norm": 0.0823453962802887,
      "learning_rate": 8e-05,
      "loss": 1.8024,
      "step": 8
    },
    {
      "epoch": 0.004517505333166018,
      "grad_norm": 0.07958869636058807,
      "learning_rate": 9e-05,
      "loss": 1.7476,
      "step": 9
    },
    {
      "epoch": 0.005019450370184465,
      "grad_norm": 0.08200295269489288,
      "learning_rate": 0.0001,
      "loss": 1.86,
      "step": 10
    },
    {
      "epoch": 0.005521395407202911,
      "grad_norm": 0.08035029470920563,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.7657,
      "step": 11
    },
    {
      "epoch": 0.006023340444221358,
      "grad_norm": 0.08940239250659943,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.6889,
      "step": 12
    },
    {
      "epoch": 0.0065252854812398045,
      "grad_norm": 0.09897463023662567,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7125,
      "step": 13
    },
    {
      "epoch": 0.00702723051825825,
      "grad_norm": 0.10487006604671478,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7871,
      "step": 14
    },
    {
      "epoch": 0.007529175555276697,
      "grad_norm": 0.1053759902715683,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7418,
      "step": 15
    },
    {
      "epoch": 0.008031120592295144,
      "grad_norm": 0.09569960832595825,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.7551,
      "step": 16
    },
    {
      "epoch": 0.00853306562931359,
      "grad_norm": 0.09858033061027527,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.7291,
      "step": 17
    },
    {
      "epoch": 0.009035010666332036,
      "grad_norm": 0.09192463755607605,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7054,
      "step": 18
    },
    {
      "epoch": 0.009536955703350483,
      "grad_norm": 0.09821785241365433,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6091,
      "step": 19
    },
    {
      "epoch": 0.01003890074036893,
      "grad_norm": 0.09714392572641373,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.66,
      "step": 20
    },
    {
      "epoch": 0.010540845777387377,
      "grad_norm": 0.09310352802276611,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.6323,
      "step": 21
    },
    {
      "epoch": 0.011042790814405823,
      "grad_norm": 0.10379514843225479,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.6855,
      "step": 22
    },
    {
      "epoch": 0.011544735851424268,
      "grad_norm": 0.10913398861885071,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.6992,
      "step": 23
    },
    {
      "epoch": 0.012046680888442716,
      "grad_norm": 0.11285462230443954,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5895,
      "step": 24
    },
    {
      "epoch": 0.012548625925461162,
      "grad_norm": 0.11898660659790039,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.7166,
      "step": 25
    },
    {
      "epoch": 0.013050570962479609,
      "grad_norm": 0.10823231190443039,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6012,
      "step": 26
    },
    {
      "epoch": 0.013552515999498055,
      "grad_norm": 0.12227211147546768,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.7774,
      "step": 27
    },
    {
      "epoch": 0.0140544610365165,
      "grad_norm": 0.10430971533060074,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.5973,
      "step": 28
    },
    {
      "epoch": 0.014556406073534948,
      "grad_norm": 0.10734613239765167,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6168,
      "step": 29
    },
    {
      "epoch": 0.015058351110553394,
      "grad_norm": 0.11208877712488174,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7179,
      "step": 30
    },
    {
      "epoch": 0.015560296147571841,
      "grad_norm": 0.11328504234552383,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.6174,
      "step": 31
    },
    {
      "epoch": 0.01606224118459029,
      "grad_norm": 0.11093199998140335,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.633,
      "step": 32
    },
    {
      "epoch": 0.016564186221608733,
      "grad_norm": 0.11688517779111862,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.5458,
      "step": 33
    },
    {
      "epoch": 0.01706613125862718,
      "grad_norm": 0.12270587682723999,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.5076,
      "step": 34
    },
    {
      "epoch": 0.017568076295645628,
      "grad_norm": 0.1240169107913971,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.5776,
      "step": 35
    },
    {
      "epoch": 0.018070021332664072,
      "grad_norm": 0.14317895472049713,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.6666,
      "step": 36
    },
    {
      "epoch": 0.01857196636968252,
      "grad_norm": 0.12534339725971222,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.524,
      "step": 37
    },
    {
      "epoch": 0.019073911406700967,
      "grad_norm": 0.13442187011241913,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.5716,
      "step": 38
    },
    {
      "epoch": 0.01957585644371941,
      "grad_norm": 0.13142892718315125,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.5241,
      "step": 39
    },
    {
      "epoch": 0.02007780148073786,
      "grad_norm": 0.13799482583999634,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.4813,
      "step": 40
    },
    {
      "epoch": 0.020579746517756306,
      "grad_norm": 0.14939914643764496,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.5414,
      "step": 41
    },
    {
      "epoch": 0.021081691554774754,
      "grad_norm": 0.14379847049713135,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.4946,
      "step": 42
    },
    {
      "epoch": 0.021583636591793198,
      "grad_norm": 0.1414833962917328,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5244,
      "step": 43
    },
    {
      "epoch": 0.022085581628811645,
      "grad_norm": 0.14794330298900604,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.4868,
      "step": 44
    },
    {
      "epoch": 0.022587526665830093,
      "grad_norm": 0.16133390367031097,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.5316,
      "step": 45
    },
    {
      "epoch": 0.023089471702848537,
      "grad_norm": 0.15960857272148132,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.4986,
      "step": 46
    },
    {
      "epoch": 0.023591416739866984,
      "grad_norm": 0.17676770687103271,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.4988,
      "step": 47
    },
    {
      "epoch": 0.02409336177688543,
      "grad_norm": 0.17546361684799194,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3993,
      "step": 48
    },
    {
      "epoch": 0.02459530681390388,
      "grad_norm": 0.20385445654392242,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.5089,
      "step": 49
    },
    {
      "epoch": 0.025097251850922323,
      "grad_norm": 0.2766834497451782,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.5569,
      "step": 50
    },
    {
      "epoch": 0.025097251850922323,
      "eval_loss": 1.592424988746643,
      "eval_runtime": 53.097,
      "eval_samples_per_second": 63.205,
      "eval_steps_per_second": 15.801,
      "step": 50
    },
    {
      "epoch": 0.02559919688794077,
      "grad_norm": 0.2575567662715912,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.6641,
      "step": 51
    },
    {
      "epoch": 0.026101141924959218,
      "grad_norm": 0.2523631155490875,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.7017,
      "step": 52
    },
    {
      "epoch": 0.026603086961977662,
      "grad_norm": 0.2228316366672516,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.7564,
      "step": 53
    },
    {
      "epoch": 0.02710503199899611,
      "grad_norm": 0.18977168202400208,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.7122,
      "step": 54
    },
    {
      "epoch": 0.027606977036014557,
      "grad_norm": 0.14850682020187378,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.7145,
      "step": 55
    },
    {
      "epoch": 0.028108922073033,
      "grad_norm": 0.12005205452442169,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.6623,
      "step": 56
    },
    {
      "epoch": 0.02861086711005145,
      "grad_norm": 0.12358347326517105,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.5897,
      "step": 57
    },
    {
      "epoch": 0.029112812147069896,
      "grad_norm": 0.12236808985471725,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5891,
      "step": 58
    },
    {
      "epoch": 0.029614757184088344,
      "grad_norm": 0.13312624394893646,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5256,
      "step": 59
    },
    {
      "epoch": 0.030116702221106788,
      "grad_norm": 0.13157588243484497,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6414,
      "step": 60
    },
    {
      "epoch": 0.030618647258125235,
      "grad_norm": 0.12960363924503326,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.6082,
      "step": 61
    },
    {
      "epoch": 0.031120592295143683,
      "grad_norm": 0.12395428866147995,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.6026,
      "step": 62
    },
    {
      "epoch": 0.03162253733216213,
      "grad_norm": 0.13215288519859314,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.6168,
      "step": 63
    },
    {
      "epoch": 0.03212448236918058,
      "grad_norm": 0.13177752494812012,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.5946,
      "step": 64
    },
    {
      "epoch": 0.03262642740619902,
      "grad_norm": 0.13062050938606262,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.5317,
      "step": 65
    },
    {
      "epoch": 0.033128372443217466,
      "grad_norm": 0.11641888320446014,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.5954,
      "step": 66
    },
    {
      "epoch": 0.03363031748023591,
      "grad_norm": 0.1156865730881691,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5936,
      "step": 67
    },
    {
      "epoch": 0.03413226251725436,
      "grad_norm": 0.10577995330095291,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.5043,
      "step": 68
    },
    {
      "epoch": 0.03463420755427281,
      "grad_norm": 0.11447162181138992,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.626,
      "step": 69
    },
    {
      "epoch": 0.035136152591291256,
      "grad_norm": 0.12066824734210968,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.5878,
      "step": 70
    },
    {
      "epoch": 0.0356380976283097,
      "grad_norm": 0.11131509393453598,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.5654,
      "step": 71
    },
    {
      "epoch": 0.036140042665328144,
      "grad_norm": 0.13203616440296173,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.6616,
      "step": 72
    },
    {
      "epoch": 0.03664198770234659,
      "grad_norm": 0.11260434240102768,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.4837,
      "step": 73
    },
    {
      "epoch": 0.03714393273936504,
      "grad_norm": 0.11951861530542374,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.5678,
      "step": 74
    },
    {
      "epoch": 0.037645877776383486,
      "grad_norm": 0.12348809093236923,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.5792,
      "step": 75
    },
    {
      "epoch": 0.038147822813401934,
      "grad_norm": 0.11773399263620377,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.5475,
      "step": 76
    },
    {
      "epoch": 0.03864976785042038,
      "grad_norm": 0.11817888915538788,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.5361,
      "step": 77
    },
    {
      "epoch": 0.03915171288743882,
      "grad_norm": 0.12896235287189484,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.4836,
      "step": 78
    },
    {
      "epoch": 0.03965365792445727,
      "grad_norm": 0.11642982810735703,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.5282,
      "step": 79
    },
    {
      "epoch": 0.04015560296147572,
      "grad_norm": 0.12688979506492615,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.5479,
      "step": 80
    },
    {
      "epoch": 0.040657547998494165,
      "grad_norm": 0.12967228889465332,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.4381,
      "step": 81
    },
    {
      "epoch": 0.04115949303551261,
      "grad_norm": 0.13121828436851501,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.4924,
      "step": 82
    },
    {
      "epoch": 0.04166143807253106,
      "grad_norm": 0.12845942378044128,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.4033,
      "step": 83
    },
    {
      "epoch": 0.04216338310954951,
      "grad_norm": 0.1304260641336441,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.5213,
      "step": 84
    },
    {
      "epoch": 0.04266532814656795,
      "grad_norm": 0.13304567337036133,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.4952,
      "step": 85
    },
    {
      "epoch": 0.043167273183586395,
      "grad_norm": 0.13689962029457092,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5147,
      "step": 86
    },
    {
      "epoch": 0.04366921822060484,
      "grad_norm": 0.1497788280248642,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.5047,
      "step": 87
    },
    {
      "epoch": 0.04417116325762329,
      "grad_norm": 0.1499299556016922,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.5425,
      "step": 88
    },
    {
      "epoch": 0.04467310829464174,
      "grad_norm": 0.14489240944385529,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.5223,
      "step": 89
    },
    {
      "epoch": 0.045175053331660185,
      "grad_norm": 0.1607256531715393,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.4314,
      "step": 90
    },
    {
      "epoch": 0.04567699836867863,
      "grad_norm": 0.1491335779428482,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.496,
      "step": 91
    },
    {
      "epoch": 0.04617894340569707,
      "grad_norm": 0.14727848768234253,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.4209,
      "step": 92
    },
    {
      "epoch": 0.04668088844271552,
      "grad_norm": 0.16316618025302887,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5245,
      "step": 93
    },
    {
      "epoch": 0.04718283347973397,
      "grad_norm": 0.1668526977300644,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.3236,
      "step": 94
    },
    {
      "epoch": 0.047684778516752416,
      "grad_norm": 0.17080457508563995,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.4128,
      "step": 95
    },
    {
      "epoch": 0.04818672355377086,
      "grad_norm": 0.18224725127220154,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.4569,
      "step": 96
    },
    {
      "epoch": 0.04868866859078931,
      "grad_norm": 0.2030700296163559,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.435,
      "step": 97
    },
    {
      "epoch": 0.04919061362780776,
      "grad_norm": 0.20806589722633362,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.4549,
      "step": 98
    },
    {
      "epoch": 0.0496925586648262,
      "grad_norm": 0.24572226405143738,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.4768,
      "step": 99
    },
    {
      "epoch": 0.050194503701844646,
      "grad_norm": 0.389061838388443,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.4392,
      "step": 100
    },
    {
      "epoch": 0.050194503701844646,
      "eval_loss": 1.5331478118896484,
      "eval_runtime": 53.2923,
      "eval_samples_per_second": 62.973,
      "eval_steps_per_second": 15.743,
      "step": 100
    },
    {
      "epoch": 0.050696448738863094,
      "grad_norm": 0.17926350235939026,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.6952,
      "step": 101
    },
    {
      "epoch": 0.05119839377588154,
      "grad_norm": 0.18976978957653046,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.6903,
      "step": 102
    },
    {
      "epoch": 0.05170033881289999,
      "grad_norm": 0.18851731717586517,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.6089,
      "step": 103
    },
    {
      "epoch": 0.052202283849918436,
      "grad_norm": 0.17110303044319153,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.609,
      "step": 104
    },
    {
      "epoch": 0.052704228886936884,
      "grad_norm": 0.1712048053741455,
      "learning_rate": 5e-05,
      "loss": 1.5559,
      "step": 105
    },
    {
      "epoch": 0.053206173923955324,
      "grad_norm": 0.16159921884536743,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.6083,
      "step": 106
    },
    {
      "epoch": 0.05370811896097377,
      "grad_norm": 0.15413938462734222,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.7078,
      "step": 107
    },
    {
      "epoch": 0.05421006399799222,
      "grad_norm": 0.14476023614406586,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.6505,
      "step": 108
    },
    {
      "epoch": 0.05471200903501067,
      "grad_norm": 0.14083252847194672,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.6515,
      "step": 109
    },
    {
      "epoch": 0.055213954072029114,
      "grad_norm": 0.1273438036441803,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.5725,
      "step": 110
    },
    {
      "epoch": 0.05571589910904756,
      "grad_norm": 0.12302535772323608,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.6101,
      "step": 111
    },
    {
      "epoch": 0.056217844146066,
      "grad_norm": 0.11512967199087143,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.5636,
      "step": 112
    },
    {
      "epoch": 0.05671978918308445,
      "grad_norm": 0.12032189965248108,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.551,
      "step": 113
    },
    {
      "epoch": 0.0572217342201029,
      "grad_norm": 0.11898070573806763,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.5505,
      "step": 114
    },
    {
      "epoch": 0.057723679257121345,
      "grad_norm": 0.11670681089162827,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.6198,
      "step": 115
    },
    {
      "epoch": 0.05822562429413979,
      "grad_norm": 0.13141916692256927,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.5586,
      "step": 116
    },
    {
      "epoch": 0.05872756933115824,
      "grad_norm": 0.12518058717250824,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.5056,
      "step": 117
    },
    {
      "epoch": 0.05922951436817669,
      "grad_norm": 0.1268884837627411,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.5298,
      "step": 118
    },
    {
      "epoch": 0.05973145940519513,
      "grad_norm": 0.1348416805267334,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.4993,
      "step": 119
    },
    {
      "epoch": 0.060233404442213576,
      "grad_norm": 0.12875382602214813,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.5662,
      "step": 120
    },
    {
      "epoch": 0.06073534947923202,
      "grad_norm": 0.13624653220176697,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.5619,
      "step": 121
    },
    {
      "epoch": 0.06123729451625047,
      "grad_norm": 0.12442681193351746,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.5565,
      "step": 122
    },
    {
      "epoch": 0.06173923955326892,
      "grad_norm": 0.12977449595928192,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.5468,
      "step": 123
    },
    {
      "epoch": 0.062241184590287366,
      "grad_norm": 0.15271179378032684,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.639,
      "step": 124
    },
    {
      "epoch": 0.06274312962730581,
      "grad_norm": 0.13699905574321747,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.4776,
      "step": 125
    },
    {
      "epoch": 0.06324507466432426,
      "grad_norm": 0.13600459694862366,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.5585,
      "step": 126
    },
    {
      "epoch": 0.06374701970134271,
      "grad_norm": 0.13306847214698792,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.5948,
      "step": 127
    },
    {
      "epoch": 0.06424896473836116,
      "grad_norm": 0.12550170719623566,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.5542,
      "step": 128
    },
    {
      "epoch": 0.06475090977537959,
      "grad_norm": 0.12918497622013092,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.48,
      "step": 129
    },
    {
      "epoch": 0.06525285481239804,
      "grad_norm": 0.1272757351398468,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.4945,
      "step": 130
    },
    {
      "epoch": 0.06575479984941648,
      "grad_norm": 0.135182723402977,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.4991,
      "step": 131
    },
    {
      "epoch": 0.06625674488643493,
      "grad_norm": 0.1337868571281433,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.4231,
      "step": 132
    },
    {
      "epoch": 0.06675868992345338,
      "grad_norm": 0.14584700763225555,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.4928,
      "step": 133
    },
    {
      "epoch": 0.06726063496047183,
      "grad_norm": 0.13436287641525269,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.382,
      "step": 134
    },
    {
      "epoch": 0.06776257999749027,
      "grad_norm": 0.13868069648742676,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.4702,
      "step": 135
    },
    {
      "epoch": 0.06826452503450872,
      "grad_norm": 0.1353742927312851,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.4007,
      "step": 136
    },
    {
      "epoch": 0.06876647007152717,
      "grad_norm": 0.15316073596477509,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.4873,
      "step": 137
    },
    {
      "epoch": 0.06926841510854562,
      "grad_norm": 0.150549978017807,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.456,
      "step": 138
    },
    {
      "epoch": 0.06977036014556406,
      "grad_norm": 0.14454786479473114,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.3899,
      "step": 139
    },
    {
      "epoch": 0.07027230518258251,
      "grad_norm": 0.14709652960300446,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3309,
      "step": 140
    },
    {
      "epoch": 0.07077425021960096,
      "grad_norm": 0.1566169112920761,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.4361,
      "step": 141
    },
    {
      "epoch": 0.0712761952566194,
      "grad_norm": 0.15669690072536469,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.3231,
      "step": 142
    },
    {
      "epoch": 0.07177814029363784,
      "grad_norm": 0.17370188236236572,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4231,
      "step": 143
    },
    {
      "epoch": 0.07228008533065629,
      "grad_norm": 0.15915383398532867,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.3808,
      "step": 144
    },
    {
      "epoch": 0.07278203036767474,
      "grad_norm": 0.1726672649383545,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.4011,
      "step": 145
    },
    {
      "epoch": 0.07328397540469318,
      "grad_norm": 0.18088902533054352,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.3768,
      "step": 146
    },
    {
      "epoch": 0.07378592044171163,
      "grad_norm": 0.20029018819332123,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.4096,
      "step": 147
    },
    {
      "epoch": 0.07428786547873008,
      "grad_norm": 0.2143724262714386,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.4116,
      "step": 148
    },
    {
      "epoch": 0.07478981051574853,
      "grad_norm": 0.25855782628059387,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.3572,
      "step": 149
    },
    {
      "epoch": 0.07529175555276697,
      "grad_norm": 0.3963508903980255,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.3225,
      "step": 150
    },
    {
      "epoch": 0.07529175555276697,
      "eval_loss": 1.5071494579315186,
      "eval_runtime": 53.32,
      "eval_samples_per_second": 62.941,
      "eval_steps_per_second": 15.735,
      "step": 150
    },
    {
      "epoch": 0.07579370058978542,
      "grad_norm": 0.13290563225746155,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.7323,
      "step": 151
    },
    {
      "epoch": 0.07629564562680387,
      "grad_norm": 0.13692235946655273,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.6033,
      "step": 152
    },
    {
      "epoch": 0.07679759066382232,
      "grad_norm": 0.13843730092048645,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.6123,
      "step": 153
    },
    {
      "epoch": 0.07729953570084076,
      "grad_norm": 0.14614839851856232,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.6071,
      "step": 154
    },
    {
      "epoch": 0.07780148073785921,
      "grad_norm": 0.1357177048921585,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5993,
      "step": 155
    },
    {
      "epoch": 0.07830342577487764,
      "grad_norm": 0.15219849348068237,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.6501,
      "step": 156
    },
    {
      "epoch": 0.07880537081189609,
      "grad_norm": 0.13364705443382263,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.5978,
      "step": 157
    },
    {
      "epoch": 0.07930731584891454,
      "grad_norm": 0.1344233900308609,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.5689,
      "step": 158
    },
    {
      "epoch": 0.07980926088593299,
      "grad_norm": 0.1458059847354889,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.5264,
      "step": 159
    },
    {
      "epoch": 0.08031120592295143,
      "grad_norm": 0.13377611339092255,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.571,
      "step": 160
    },
    {
      "epoch": 0.08081315095996988,
      "grad_norm": 0.12416079640388489,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.5263,
      "step": 161
    },
    {
      "epoch": 0.08131509599698833,
      "grad_norm": 0.13272295892238617,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5244,
      "step": 162
    },
    {
      "epoch": 0.08181704103400678,
      "grad_norm": 0.13143539428710938,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.6031,
      "step": 163
    },
    {
      "epoch": 0.08231898607102522,
      "grad_norm": 0.1288091540336609,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.5845,
      "step": 164
    },
    {
      "epoch": 0.08282093110804367,
      "grad_norm": 0.1265120506286621,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.4437,
      "step": 165
    },
    {
      "epoch": 0.08332287614506212,
      "grad_norm": 0.12334231287240982,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.4578,
      "step": 166
    },
    {
      "epoch": 0.08382482118208057,
      "grad_norm": 0.13068102300167084,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.6028,
      "step": 167
    },
    {
      "epoch": 0.08432676621909901,
      "grad_norm": 0.1216667965054512,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.4209,
      "step": 168
    },
    {
      "epoch": 0.08482871125611746,
      "grad_norm": 0.1302245408296585,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.547,
      "step": 169
    },
    {
      "epoch": 0.0853306562931359,
      "grad_norm": 0.13136282563209534,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.6477,
      "step": 170
    },
    {
      "epoch": 0.08583260133015434,
      "grad_norm": 0.12917464971542358,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.5336,
      "step": 171
    },
    {
      "epoch": 0.08633454636717279,
      "grad_norm": 0.12647278606891632,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.5277,
      "step": 172
    },
    {
      "epoch": 0.08683649140419124,
      "grad_norm": 0.12907974421977997,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.5428,
      "step": 173
    },
    {
      "epoch": 0.08733843644120969,
      "grad_norm": 0.12588739395141602,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.5315,
      "step": 174
    },
    {
      "epoch": 0.08784038147822813,
      "grad_norm": 0.13183537125587463,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.4712,
      "step": 175
    },
    {
      "epoch": 0.08834232651524658,
      "grad_norm": 0.13010796904563904,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.4549,
      "step": 176
    },
    {
      "epoch": 0.08884427155226503,
      "grad_norm": 0.13396143913269043,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.4503,
      "step": 177
    },
    {
      "epoch": 0.08934621658928348,
      "grad_norm": 0.13536867499351501,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.5664,
      "step": 178
    },
    {
      "epoch": 0.08984816162630192,
      "grad_norm": 0.13426436483860016,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.5738,
      "step": 179
    },
    {
      "epoch": 0.09035010666332037,
      "grad_norm": 0.13680560886859894,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4273,
      "step": 180
    },
    {
      "epoch": 0.09085205170033882,
      "grad_norm": 0.1387549191713333,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.3781,
      "step": 181
    },
    {
      "epoch": 0.09135399673735727,
      "grad_norm": 0.13565517961978912,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3839,
      "step": 182
    },
    {
      "epoch": 0.0918559417743757,
      "grad_norm": 0.1516047865152359,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.515,
      "step": 183
    },
    {
      "epoch": 0.09235788681139415,
      "grad_norm": 0.13879139721393585,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.5415,
      "step": 184
    },
    {
      "epoch": 0.0928598318484126,
      "grad_norm": 0.14901812374591827,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.4236,
      "step": 185
    },
    {
      "epoch": 0.09336177688543104,
      "grad_norm": 0.15422768890857697,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3855,
      "step": 186
    },
    {
      "epoch": 0.09386372192244949,
      "grad_norm": 0.15200434625148773,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.58,
      "step": 187
    },
    {
      "epoch": 0.09436566695946794,
      "grad_norm": 0.1472344547510147,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.4906,
      "step": 188
    },
    {
      "epoch": 0.09486761199648638,
      "grad_norm": 0.15768340229988098,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.4676,
      "step": 189
    },
    {
      "epoch": 0.09536955703350483,
      "grad_norm": 0.15619274973869324,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.523,
      "step": 190
    },
    {
      "epoch": 0.09587150207052328,
      "grad_norm": 0.14795450866222382,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.3395,
      "step": 191
    },
    {
      "epoch": 0.09637344710754173,
      "grad_norm": 0.1591450273990631,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.4654,
      "step": 192
    },
    {
      "epoch": 0.09687539214456017,
      "grad_norm": 0.15962278842926025,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.3888,
      "step": 193
    },
    {
      "epoch": 0.09737733718157862,
      "grad_norm": 0.18199214339256287,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.4398,
      "step": 194
    },
    {
      "epoch": 0.09787928221859707,
      "grad_norm": 0.17493945360183716,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.3995,
      "step": 195
    },
    {
      "epoch": 0.09838122725561552,
      "grad_norm": 0.18033245205879211,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.4371,
      "step": 196
    },
    {
      "epoch": 0.09888317229263395,
      "grad_norm": 0.21050624549388885,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.4723,
      "step": 197
    },
    {
      "epoch": 0.0993851173296524,
      "grad_norm": 0.24466587603092194,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.3665,
      "step": 198
    },
    {
      "epoch": 0.09988706236667085,
      "grad_norm": 0.25309520959854126,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.4357,
      "step": 199
    },
    {
      "epoch": 0.10038900740368929,
      "grad_norm": 0.3790328800678253,
      "learning_rate": 0.0,
      "loss": 1.4673,
      "step": 200
    },
    {
      "epoch": 0.10038900740368929,
      "eval_loss": 1.5025569200515747,
      "eval_runtime": 53.1317,
      "eval_samples_per_second": 63.164,
      "eval_steps_per_second": 15.791,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.380644787585024e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}