{
  "best_metric": 12.402924537658691,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 2.1621621621621623,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 0.011207693256437778,
      "learning_rate": 1e-05,
      "loss": 12.4555,
      "step": 1
    },
    {
      "epoch": 0.010810810810810811,
      "eval_loss": 12.456661224365234,
      "eval_runtime": 1.1835,
      "eval_samples_per_second": 131.817,
      "eval_steps_per_second": 32.954,
      "step": 1
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 0.012961424887180328,
      "learning_rate": 2e-05,
      "loss": 12.4583,
      "step": 2
    },
    {
      "epoch": 0.032432432432432434,
      "grad_norm": 0.013010692782700062,
      "learning_rate": 3e-05,
      "loss": 12.4565,
      "step": 3
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 0.012649844400584698,
      "learning_rate": 4e-05,
      "loss": 12.4564,
      "step": 4
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.014114424586296082,
      "learning_rate": 5e-05,
      "loss": 12.4551,
      "step": 5
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 0.013082235120236874,
      "learning_rate": 6e-05,
      "loss": 12.456,
      "step": 6
    },
    {
      "epoch": 0.07567567567567568,
      "grad_norm": 0.012963609769940376,
      "learning_rate": 7e-05,
      "loss": 12.4583,
      "step": 7
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 0.014116719365119934,
      "learning_rate": 8e-05,
      "loss": 12.4584,
      "step": 8
    },
    {
      "epoch": 0.0972972972972973,
      "grad_norm": 0.013101985678076744,
      "learning_rate": 9e-05,
      "loss": 12.458,
      "step": 9
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.016027623787522316,
      "learning_rate": 0.0001,
      "loss": 12.459,
      "step": 10
    },
    {
      "epoch": 0.11891891891891893,
      "grad_norm": 0.014532581903040409,
      "learning_rate": 9.999316524962345e-05,
      "loss": 12.4565,
      "step": 11
    },
    {
      "epoch": 0.12972972972972974,
      "grad_norm": 0.016159769147634506,
      "learning_rate": 9.997266286704631e-05,
      "loss": 12.4564,
      "step": 12
    },
    {
      "epoch": 0.14054054054054055,
      "grad_norm": 0.01740213669836521,
      "learning_rate": 9.993849845741524e-05,
      "loss": 12.4581,
      "step": 13
    },
    {
      "epoch": 0.15135135135135136,
      "grad_norm": 0.017189739271998405,
      "learning_rate": 9.989068136093873e-05,
      "loss": 12.4592,
      "step": 14
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 0.017148399725556374,
      "learning_rate": 9.98292246503335e-05,
      "loss": 12.4575,
      "step": 15
    },
    {
      "epoch": 0.17297297297297298,
      "grad_norm": 0.019100384786725044,
      "learning_rate": 9.975414512725057e-05,
      "loss": 12.4532,
      "step": 16
    },
    {
      "epoch": 0.1837837837837838,
      "grad_norm": 0.02053026109933853,
      "learning_rate": 9.966546331768191e-05,
      "loss": 12.4537,
      "step": 17
    },
    {
      "epoch": 0.1945945945945946,
      "grad_norm": 0.024311017245054245,
      "learning_rate": 9.956320346634876e-05,
      "loss": 12.4532,
      "step": 18
    },
    {
      "epoch": 0.20540540540540542,
      "grad_norm": 0.023085476830601692,
      "learning_rate": 9.944739353007344e-05,
      "loss": 12.4586,
      "step": 19
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.02692628838121891,
      "learning_rate": 9.931806517013612e-05,
      "loss": 12.4549,
      "step": 20
    },
    {
      "epoch": 0.22702702702702704,
      "grad_norm": 0.026808330789208412,
      "learning_rate": 9.917525374361912e-05,
      "loss": 12.4549,
      "step": 21
    },
    {
      "epoch": 0.23783783783783785,
      "grad_norm": 0.02519167587161064,
      "learning_rate": 9.901899829374047e-05,
      "loss": 12.456,
      "step": 22
    },
    {
      "epoch": 0.24864864864864866,
      "grad_norm": 0.027301128953695297,
      "learning_rate": 9.884934153917997e-05,
      "loss": 12.4501,
      "step": 23
    },
    {
      "epoch": 0.2594594594594595,
      "grad_norm": 0.022348005324602127,
      "learning_rate": 9.86663298624003e-05,
      "loss": 12.4562,
      "step": 24
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.022255470976233482,
      "learning_rate": 9.847001329696653e-05,
      "loss": 12.4577,
      "step": 25
    },
    {
      "epoch": 0.2810810810810811,
      "grad_norm": 0.03000296838581562,
      "learning_rate": 9.826044551386744e-05,
      "loss": 12.457,
      "step": 26
    },
    {
      "epoch": 0.2918918918918919,
      "grad_norm": 0.026758888736367226,
      "learning_rate": 9.803768380684242e-05,
      "loss": 12.455,
      "step": 27
    },
    {
      "epoch": 0.3027027027027027,
      "grad_norm": 0.03207822144031525,
      "learning_rate": 9.780178907671789e-05,
      "loss": 12.4565,
      "step": 28
    },
    {
      "epoch": 0.31351351351351353,
      "grad_norm": 0.03209357336163521,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.4563,
      "step": 29
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.034616194665431976,
      "learning_rate": 9.729086208503174e-05,
      "loss": 12.4561,
      "step": 30
    },
    {
      "epoch": 0.33513513513513515,
      "grad_norm": 0.036717452108860016,
      "learning_rate": 9.701596950580806e-05,
      "loss": 12.4554,
      "step": 31
    },
    {
      "epoch": 0.34594594594594597,
      "grad_norm": 0.032075218856334686,
      "learning_rate": 9.672822322997305e-05,
      "loss": 12.4576,
      "step": 32
    },
    {
      "epoch": 0.3567567567567568,
      "grad_norm": 0.04166813939809799,
      "learning_rate": 9.642770192448536e-05,
      "loss": 12.4564,
      "step": 33
    },
    {
      "epoch": 0.3675675675675676,
      "grad_norm": 0.04541519656777382,
      "learning_rate": 9.611448774886924e-05,
      "loss": 12.4558,
      "step": 34
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.04335350543260574,
      "learning_rate": 9.578866633275288e-05,
      "loss": 12.4565,
      "step": 35
    },
    {
      "epoch": 0.3891891891891892,
      "grad_norm": 0.04407484084367752,
      "learning_rate": 9.545032675245813e-05,
      "loss": 12.4544,
      "step": 36
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.04892905056476593,
      "learning_rate": 9.509956150664796e-05,
      "loss": 12.4544,
      "step": 37
    },
    {
      "epoch": 0.41081081081081083,
      "grad_norm": 0.04902025684714317,
      "learning_rate": 9.473646649103818e-05,
      "loss": 12.4552,
      "step": 38
    },
    {
      "epoch": 0.42162162162162165,
      "grad_norm": 0.05262954160571098,
      "learning_rate": 9.43611409721806e-05,
      "loss": 12.4516,
      "step": 39
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.05762867256999016,
      "learning_rate": 9.397368756032445e-05,
      "loss": 12.4526,
      "step": 40
    },
    {
      "epoch": 0.44324324324324327,
      "grad_norm": 0.06008000671863556,
      "learning_rate": 9.357421218136386e-05,
      "loss": 12.4505,
      "step": 41
    },
    {
      "epoch": 0.4540540540540541,
      "grad_norm": 0.07089274376630783,
      "learning_rate": 9.316282404787871e-05,
      "loss": 12.4494,
      "step": 42
    },
    {
      "epoch": 0.4648648648648649,
      "grad_norm": 0.05926710367202759,
      "learning_rate": 9.273963562927695e-05,
      "loss": 12.4543,
      "step": 43
    },
    {
      "epoch": 0.4756756756756757,
      "grad_norm": 0.0717070996761322,
      "learning_rate": 9.230476262104677e-05,
      "loss": 12.4535,
      "step": 44
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 0.07837062329053879,
      "learning_rate": 9.185832391312644e-05,
      "loss": 12.4501,
      "step": 45
    },
    {
      "epoch": 0.4972972972972973,
      "grad_norm": 0.0792049989104271,
      "learning_rate": 9.140044155740101e-05,
      "loss": 12.45,
      "step": 46
    },
    {
      "epoch": 0.5081081081081081,
      "grad_norm": 0.05156276002526283,
      "learning_rate": 9.093124073433463e-05,
      "loss": 12.4516,
      "step": 47
    },
    {
      "epoch": 0.518918918918919,
      "grad_norm": 0.06293857097625732,
      "learning_rate": 9.045084971874738e-05,
      "loss": 12.4506,
      "step": 48
    },
    {
      "epoch": 0.5297297297297298,
      "grad_norm": 0.07377424091100693,
      "learning_rate": 8.995939984474624e-05,
      "loss": 12.449,
      "step": 49
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.070464126765728,
      "learning_rate": 8.945702546981969e-05,
      "loss": 12.4499,
      "step": 50
    },
    {
      "epoch": 0.5405405405405406,
      "eval_loss": 12.449003219604492,
      "eval_runtime": 1.1905,
      "eval_samples_per_second": 131.035,
      "eval_steps_per_second": 32.759,
      "step": 50
    },
    {
      "epoch": 0.5513513513513514,
      "grad_norm": 0.0735025703907013,
      "learning_rate": 8.894386393810563e-05,
      "loss": 12.4514,
      "step": 51
    },
    {
      "epoch": 0.5621621621621622,
      "grad_norm": 0.07985434681177139,
      "learning_rate": 8.842005554284296e-05,
      "loss": 12.4507,
      "step": 52
    },
    {
      "epoch": 0.572972972972973,
      "grad_norm": 0.08980229496955872,
      "learning_rate": 8.788574348801675e-05,
      "loss": 12.4484,
      "step": 53
    },
    {
      "epoch": 0.5837837837837838,
      "grad_norm": 0.07783932238817215,
      "learning_rate": 8.73410738492077e-05,
      "loss": 12.4486,
      "step": 54
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 0.08867110311985016,
      "learning_rate": 8.678619553365659e-05,
      "loss": 12.4491,
      "step": 55
    },
    {
      "epoch": 0.6054054054054054,
      "grad_norm": 0.0953461155295372,
      "learning_rate": 8.622126023955446e-05,
      "loss": 12.4477,
      "step": 56
    },
    {
      "epoch": 0.6162162162162163,
      "grad_norm": 0.09138405323028564,
      "learning_rate": 8.564642241456986e-05,
      "loss": 12.4491,
      "step": 57
    },
    {
      "epoch": 0.6270270270270271,
      "grad_norm": 0.09887129813432693,
      "learning_rate": 8.506183921362443e-05,
      "loss": 12.4476,
      "step": 58
    },
    {
      "epoch": 0.6378378378378379,
      "grad_norm": 0.11293221265077591,
      "learning_rate": 8.44676704559283e-05,
      "loss": 12.4429,
      "step": 59
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.10253853350877762,
      "learning_rate": 8.386407858128706e-05,
      "loss": 12.4458,
      "step": 60
    },
    {
      "epoch": 0.6594594594594595,
      "grad_norm": 0.11118557304143906,
      "learning_rate": 8.32512286056924e-05,
      "loss": 12.4434,
      "step": 61
    },
    {
      "epoch": 0.6702702702702703,
      "grad_norm": 0.1151147112250328,
      "learning_rate": 8.262928807620843e-05,
      "loss": 12.4434,
      "step": 62
    },
    {
      "epoch": 0.6810810810810811,
      "grad_norm": 0.11826730519533157,
      "learning_rate": 8.199842702516583e-05,
      "loss": 12.4425,
      "step": 63
    },
    {
      "epoch": 0.6918918918918919,
      "grad_norm": 0.11428274214267731,
      "learning_rate": 8.135881792367686e-05,
      "loss": 12.4386,
      "step": 64
    },
    {
      "epoch": 0.7027027027027027,
      "grad_norm": 0.11284895986318588,
      "learning_rate": 8.07106356344834e-05,
      "loss": 12.4388,
      "step": 65
    },
    {
      "epoch": 0.7135135135135136,
      "grad_norm": 0.11779170483350754,
      "learning_rate": 8.005405736415126e-05,
      "loss": 12.4392,
      "step": 66
    },
    {
      "epoch": 0.7243243243243244,
      "grad_norm": 0.12751299142837524,
      "learning_rate": 7.938926261462366e-05,
      "loss": 12.4407,
      "step": 67
    },
    {
      "epoch": 0.7351351351351352,
      "grad_norm": 0.12842516601085663,
      "learning_rate": 7.871643313414718e-05,
      "loss": 12.436,
      "step": 68
    },
    {
      "epoch": 0.745945945945946,
      "grad_norm": 0.12036105245351791,
      "learning_rate": 7.803575286758364e-05,
      "loss": 12.4355,
      "step": 69
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 0.10449612140655518,
      "learning_rate": 7.734740790612136e-05,
      "loss": 12.4413,
      "step": 70
    },
    {
      "epoch": 0.7675675675675676,
      "grad_norm": 0.1084362119436264,
      "learning_rate": 7.66515864363997e-05,
      "loss": 12.444,
      "step": 71
    },
    {
      "epoch": 0.7783783783783784,
      "grad_norm": 0.11986015737056732,
      "learning_rate": 7.594847868906076e-05,
      "loss": 12.4397,
      "step": 72
    },
    {
      "epoch": 0.7891891891891892,
      "grad_norm": 0.1351478546857834,
      "learning_rate": 7.52382768867422e-05,
      "loss": 12.436,
      "step": 73
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.13137635588645935,
      "learning_rate": 7.452117519152542e-05,
      "loss": 12.4357,
      "step": 74
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.12069105356931686,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.4384,
      "step": 75
    },
    {
      "epoch": 0.8216216216216217,
      "grad_norm": 0.12979835271835327,
      "learning_rate": 7.30670581489344e-05,
      "loss": 12.4366,
      "step": 76
    },
    {
      "epoch": 0.8324324324324325,
      "grad_norm": 0.12179984897375107,
      "learning_rate": 7.233044034264034e-05,
      "loss": 12.4382,
      "step": 77
    },
    {
      "epoch": 0.8432432432432433,
      "grad_norm": 0.13688722252845764,
      "learning_rate": 7.158771761692464e-05,
      "loss": 12.432,
      "step": 78
    },
    {
      "epoch": 0.8540540540540541,
      "grad_norm": 0.12091127783060074,
      "learning_rate": 7.083909302476453e-05,
      "loss": 12.4368,
      "step": 79
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.13260598480701447,
      "learning_rate": 7.008477123264848e-05,
      "loss": 12.4329,
      "step": 80
    },
    {
      "epoch": 0.8756756756756757,
      "grad_norm": 0.1272968053817749,
      "learning_rate": 6.932495846462261e-05,
      "loss": 12.4316,
      "step": 81
    },
    {
      "epoch": 0.8864864864864865,
      "grad_norm": 0.1377931386232376,
      "learning_rate": 6.855986244591104e-05,
      "loss": 12.4326,
      "step": 82
    },
    {
      "epoch": 0.8972972972972973,
      "grad_norm": 0.1360163390636444,
      "learning_rate": 6.778969234612584e-05,
      "loss": 12.4333,
      "step": 83
    },
    {
      "epoch": 0.9081081081081082,
      "grad_norm": 0.13974976539611816,
      "learning_rate": 6.701465872208216e-05,
      "loss": 12.4282,
      "step": 84
    },
    {
      "epoch": 0.918918918918919,
      "grad_norm": 0.1287413239479065,
      "learning_rate": 6.623497346023418e-05,
      "loss": 12.4318,
      "step": 85
    },
    {
      "epoch": 0.9297297297297298,
      "grad_norm": 0.13761818408966064,
      "learning_rate": 6.545084971874738e-05,
      "loss": 12.4252,
      "step": 86
    },
    {
      "epoch": 0.9405405405405406,
      "grad_norm": 0.14252682030200958,
      "learning_rate": 6.466250186922325e-05,
      "loss": 12.4243,
      "step": 87
    },
    {
      "epoch": 0.9513513513513514,
      "grad_norm": 0.156732976436615,
      "learning_rate": 6.387014543809223e-05,
      "loss": 12.4222,
      "step": 88
    },
    {
      "epoch": 0.9621621621621622,
      "grad_norm": 0.14607061445713043,
      "learning_rate": 6.307399704769099e-05,
      "loss": 12.4186,
      "step": 89
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 0.1456853151321411,
      "learning_rate": 6.227427435703997e-05,
      "loss": 12.4253,
      "step": 90
    },
    {
      "epoch": 0.9837837837837838,
      "grad_norm": 0.1473974883556366,
      "learning_rate": 6.147119600233758e-05,
      "loss": 12.4201,
      "step": 91
    },
    {
      "epoch": 0.9945945945945946,
      "grad_norm": 0.12719225883483887,
      "learning_rate": 6.066498153718735e-05,
      "loss": 12.4271,
      "step": 92
    },
    {
      "epoch": 1.0054054054054054,
      "grad_norm": 0.19562353193759918,
      "learning_rate": 5.985585137257401e-05,
      "loss": 19.2039,
      "step": 93
    },
    {
      "epoch": 1.0162162162162163,
      "grad_norm": 0.12855945527553558,
      "learning_rate": 5.90440267166055e-05,
      "loss": 12.2715,
      "step": 94
    },
    {
      "epoch": 1.027027027027027,
      "grad_norm": 0.13302083313465118,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 12.4569,
      "step": 95
    },
    {
      "epoch": 1.037837837837838,
      "grad_norm": 0.1305927187204361,
      "learning_rate": 5.74131823855921e-05,
      "loss": 12.014,
      "step": 96
    },
    {
      "epoch": 1.0486486486486486,
      "grad_norm": 0.1354302167892456,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 12.5739,
      "step": 97
    },
    {
      "epoch": 1.0594594594594595,
      "grad_norm": 0.12061326950788498,
      "learning_rate": 5.577423184847932e-05,
      "loss": 12.1448,
      "step": 98
    },
    {
      "epoch": 1.0702702702702702,
      "grad_norm": 0.129132941365242,
      "learning_rate": 5.495227651252315e-05,
      "loss": 12.5747,
      "step": 99
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.13309718668460846,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 12.5294,
      "step": 100
    },
    {
      "epoch": 1.0810810810810811,
      "eval_loss": 12.41977310180664,
      "eval_runtime": 1.1916,
      "eval_samples_per_second": 130.915,
      "eval_steps_per_second": 32.729,
      "step": 100
    },
    {
      "epoch": 1.0918918918918918,
      "grad_norm": 0.14122404158115387,
      "learning_rate": 5.330452921628497e-05,
      "loss": 12.2385,
      "step": 101
    },
    {
      "epoch": 1.1027027027027028,
      "grad_norm": 0.12666131556034088,
      "learning_rate": 5.247918773366112e-05,
      "loss": 12.5226,
      "step": 102
    },
    {
      "epoch": 1.1135135135135135,
      "grad_norm": 0.13096508383750916,
      "learning_rate": 5.165316846586541e-05,
      "loss": 12.4097,
      "step": 103
    },
    {
      "epoch": 1.1243243243243244,
      "grad_norm": 0.1371913105249405,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 12.4364,
      "step": 104
    },
    {
      "epoch": 1.135135135135135,
      "grad_norm": 0.1272585690021515,
      "learning_rate": 5e-05,
      "loss": 12.2685,
      "step": 105
    },
    {
      "epoch": 1.145945945945946,
      "grad_norm": 0.13281095027923584,
      "learning_rate": 4.917330276168208e-05,
      "loss": 12.6525,
      "step": 106
    },
    {
      "epoch": 1.1567567567567567,
      "grad_norm": 0.13233084976673126,
      "learning_rate": 4.834683153413459e-05,
      "loss": 12.41,
      "step": 107
    },
    {
      "epoch": 1.1675675675675676,
      "grad_norm": 0.12595127522945404,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 12.3187,
      "step": 108
    },
    {
      "epoch": 1.1783783783783783,
      "grad_norm": 0.13262464106082916,
      "learning_rate": 4.669547078371504e-05,
      "loss": 12.3318,
      "step": 109
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 0.1319066882133484,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 12.3832,
      "step": 110
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.13990837335586548,
      "learning_rate": 4.504772348747687e-05,
      "loss": 12.5546,
      "step": 111
    },
    {
      "epoch": 1.2108108108108109,
      "grad_norm": 0.15222130715847015,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 12.4865,
      "step": 112
    },
    {
      "epoch": 1.2216216216216216,
      "grad_norm": 0.13759095966815948,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 12.5329,
      "step": 113
    },
    {
      "epoch": 1.2324324324324325,
      "grad_norm": 0.1364748626947403,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 12.6826,
      "step": 114
    },
    {
      "epoch": 1.2432432432432432,
      "grad_norm": 0.15113554894924164,
      "learning_rate": 4.17702704859633e-05,
      "loss": 13.3067,
      "step": 115
    },
    {
      "epoch": 1.2540540540540541,
      "grad_norm": 0.11874595284461975,
      "learning_rate": 4.095597328339452e-05,
      "loss": 11.168,
      "step": 116
    },
    {
      "epoch": 1.2648648648648648,
      "grad_norm": 0.12837743759155273,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 12.5186,
      "step": 117
    },
    {
      "epoch": 1.2756756756756757,
      "grad_norm": 0.1281714290380478,
      "learning_rate": 3.933501846281267e-05,
      "loss": 12.1515,
      "step": 118
    },
    {
      "epoch": 1.2864864864864864,
      "grad_norm": 0.134039968252182,
      "learning_rate": 3.852880399766243e-05,
      "loss": 12.5158,
      "step": 119
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 0.12987154722213745,
      "learning_rate": 3.772572564296005e-05,
      "loss": 12.3258,
      "step": 120
    },
    {
      "epoch": 1.308108108108108,
      "grad_norm": 0.13608668744564056,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 12.4378,
      "step": 121
    },
    {
      "epoch": 1.318918918918919,
      "grad_norm": 0.12630510330200195,
      "learning_rate": 3.612985456190778e-05,
      "loss": 12.3976,
      "step": 122
    },
    {
      "epoch": 1.3297297297297297,
      "grad_norm": 0.1412682980298996,
      "learning_rate": 3.533749813077677e-05,
      "loss": 12.3064,
      "step": 123
    },
    {
      "epoch": 1.3405405405405406,
      "grad_norm": 0.13499215245246887,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.4562,
      "step": 124
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 0.13783645629882812,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 12.6002,
      "step": 125
    },
    {
      "epoch": 1.3621621621621622,
      "grad_norm": 0.13830523192882538,
      "learning_rate": 3.298534127791785e-05,
      "loss": 12.3276,
      "step": 126
    },
    {
      "epoch": 1.372972972972973,
      "grad_norm": 0.13799597322940826,
      "learning_rate": 3.221030765387417e-05,
      "loss": 12.4436,
      "step": 127
    },
    {
      "epoch": 1.3837837837837839,
      "grad_norm": 0.1256716549396515,
      "learning_rate": 3.144013755408895e-05,
      "loss": 12.3124,
      "step": 128
    },
    {
      "epoch": 1.3945945945945946,
      "grad_norm": 0.14087165892124176,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 12.2521,
      "step": 129
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 0.12737415730953217,
      "learning_rate": 2.991522876735154e-05,
      "loss": 12.621,
      "step": 130
    },
    {
      "epoch": 1.4162162162162162,
      "grad_norm": 0.13399814069271088,
      "learning_rate": 2.916090697523549e-05,
      "loss": 12.3941,
      "step": 131
    },
    {
      "epoch": 1.427027027027027,
      "grad_norm": 0.14206911623477936,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 12.5091,
      "step": 132
    },
    {
      "epoch": 1.4378378378378378,
      "grad_norm": 0.13293571770191193,
      "learning_rate": 2.766955965735968e-05,
      "loss": 12.201,
      "step": 133
    },
    {
      "epoch": 1.4486486486486487,
      "grad_norm": 0.1295592039823532,
      "learning_rate": 2.693294185106562e-05,
      "loss": 12.2648,
      "step": 134
    },
    {
      "epoch": 1.4594594594594594,
      "grad_norm": 0.14292557537555695,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 12.7591,
      "step": 135
    },
    {
      "epoch": 1.4702702702702704,
      "grad_norm": 0.13217291235923767,
      "learning_rate": 2.547882480847461e-05,
      "loss": 12.1812,
      "step": 136
    },
    {
      "epoch": 1.481081081081081,
      "grad_norm": 0.13620240986347198,
      "learning_rate": 2.476172311325783e-05,
      "loss": 12.6606,
      "step": 137
    },
    {
      "epoch": 1.491891891891892,
      "grad_norm": 0.1551385223865509,
      "learning_rate": 2.405152131093926e-05,
      "loss": 13.6809,
      "step": 138
    },
    {
      "epoch": 1.5027027027027027,
      "grad_norm": 0.12075534462928772,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 11.1072,
      "step": 139
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 0.13305996358394623,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 12.6012,
      "step": 140
    },
    {
      "epoch": 1.5243243243243243,
      "grad_norm": 0.13277041912078857,
      "learning_rate": 2.196424713241637e-05,
      "loss": 12.2127,
      "step": 141
    },
    {
      "epoch": 1.535135135135135,
      "grad_norm": 0.13404038548469543,
      "learning_rate": 2.128356686585282e-05,
      "loss": 12.2417,
      "step": 142
    },
    {
      "epoch": 1.545945945945946,
      "grad_norm": 0.1381426900625229,
      "learning_rate": 2.061073738537635e-05,
      "loss": 12.3441,
      "step": 143
    },
    {
      "epoch": 1.5567567567567568,
      "grad_norm": 0.13211677968502045,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 12.4459,
      "step": 144
    },
    {
      "epoch": 1.5675675675675675,
      "grad_norm": 0.14307326078414917,
      "learning_rate": 1.928936436551661e-05,
      "loss": 12.5049,
      "step": 145
    },
    {
      "epoch": 1.5783783783783782,
      "grad_norm": 0.12959998846054077,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 12.2587,
      "step": 146
    },
    {
      "epoch": 1.5891891891891892,
      "grad_norm": 0.13357719779014587,
      "learning_rate": 1.800157297483417e-05,
      "loss": 12.4177,
      "step": 147
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.13592791557312012,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 12.7112,
      "step": 148
    },
    {
      "epoch": 1.6108108108108108,
      "grad_norm": 0.1253482550382614,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 11.9976,
      "step": 149
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.13077537715435028,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 12.4394,
      "step": 150
    },
    {
      "epoch": 1.6216216216216215,
      "eval_loss": 12.404990196228027,
      "eval_runtime": 1.2008,
      "eval_samples_per_second": 129.913,
      "eval_steps_per_second": 32.478,
      "step": 150
    },
    {
      "epoch": 1.6324324324324324,
      "grad_norm": 0.1465749591588974,
      "learning_rate": 1.553232954407171e-05,
      "loss": 12.593,
      "step": 151
    },
    {
      "epoch": 1.6432432432432433,
      "grad_norm": 0.13342374563217163,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 12.252,
      "step": 152
    },
    {
      "epoch": 1.654054054054054,
      "grad_norm": 0.1400250494480133,
      "learning_rate": 1.435357758543015e-05,
      "loss": 12.6112,
      "step": 153
    },
    {
      "epoch": 1.6648648648648647,
      "grad_norm": 0.13540081679821014,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 12.4411,
      "step": 154
    },
    {
      "epoch": 1.6756756756756757,
      "grad_norm": 0.12915897369384766,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 12.47,
      "step": 155
    },
    {
      "epoch": 1.6864864864864866,
      "grad_norm": 0.1291668564081192,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 12.3287,
      "step": 156
    },
    {
      "epoch": 1.6972972972972973,
      "grad_norm": 0.13144834339618683,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 12.3201,
      "step": 157
    },
    {
      "epoch": 1.708108108108108,
      "grad_norm": 0.13143691420555115,
      "learning_rate": 1.157994445715706e-05,
      "loss": 12.4064,
      "step": 158
    },
    {
      "epoch": 1.718918918918919,
      "grad_norm": 0.12904275953769684,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 12.2419,
      "step": 159
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 0.13684320449829102,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 12.6001,
      "step": 160
    },
    {
      "epoch": 1.7405405405405405,
      "grad_norm": 0.12015988677740097,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 13.8743,
      "step": 161
    },
    {
      "epoch": 1.7513513513513512,
      "grad_norm": 0.1071251854300499,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.9193,
      "step": 162
    },
    {
      "epoch": 1.7621621621621621,
      "grad_norm": 0.13339616358280182,
      "learning_rate": 9.068759265665384e-06,
      "loss": 12.3942,
      "step": 163
    },
    {
      "epoch": 1.772972972972973,
      "grad_norm": 0.12709708511829376,
      "learning_rate": 8.599558442598998e-06,
      "loss": 12.215,
      "step": 164
    },
    {
      "epoch": 1.7837837837837838,
      "grad_norm": 0.13096117973327637,
      "learning_rate": 8.141676086873572e-06,
      "loss": 12.6081,
      "step": 165
    },
    {
      "epoch": 1.7945945945945945,
      "grad_norm": 0.1304713487625122,
      "learning_rate": 7.695237378953223e-06,
      "loss": 12.3823,
      "step": 166
    },
    {
      "epoch": 1.8054054054054054,
      "grad_norm": 0.12706276774406433,
      "learning_rate": 7.260364370723044e-06,
      "loss": 12.1673,
      "step": 167
    },
    {
      "epoch": 1.8162162162162163,
      "grad_norm": 0.12586572766304016,
      "learning_rate": 6.837175952121306e-06,
      "loss": 12.5389,
      "step": 168
    },
    {
      "epoch": 1.827027027027027,
      "grad_norm": 0.12484031915664673,
      "learning_rate": 6.425787818636131e-06,
      "loss": 12.3335,
      "step": 169
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 0.12834767997264862,
      "learning_rate": 6.026312439675552e-06,
      "loss": 12.417,
      "step": 170
    },
    {
      "epoch": 1.8486486486486486,
      "grad_norm": 0.13207155466079712,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 12.2458,
      "step": 171
    },
    {
      "epoch": 1.8594594594594596,
      "grad_norm": 0.126329705119133,
      "learning_rate": 5.263533508961827e-06,
      "loss": 12.5581,
      "step": 172
    },
    {
      "epoch": 1.8702702702702703,
      "grad_norm": 0.127003476023674,
      "learning_rate": 4.900438493352055e-06,
      "loss": 12.3369,
      "step": 173
    },
    {
      "epoch": 1.881081081081081,
      "grad_norm": 0.13292762637138367,
      "learning_rate": 4.549673247541875e-06,
      "loss": 12.4922,
      "step": 174
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 0.12915314733982086,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 12.3831,
      "step": 175
    },
    {
      "epoch": 1.9027027027027028,
      "grad_norm": 0.1446133255958557,
      "learning_rate": 3.885512251130763e-06,
      "loss": 12.8847,
      "step": 176
    },
    {
      "epoch": 1.9135135135135135,
      "grad_norm": 0.11417820304632187,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 12.0486,
      "step": 177
    },
    {
      "epoch": 1.9243243243243242,
      "grad_norm": 0.13507616519927979,
      "learning_rate": 3.271776770026963e-06,
      "loss": 12.5523,
      "step": 178
    },
    {
      "epoch": 1.9351351351351351,
      "grad_norm": 0.10952456295490265,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 12.334,
      "step": 179
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 0.11600298434495926,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 12.3677,
      "step": 180
    },
    {
      "epoch": 1.9567567567567568,
      "grad_norm": 0.11178916692733765,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 12.3311,
      "step": 181
    },
    {
      "epoch": 1.9675675675675675,
      "grad_norm": 0.12201208621263504,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 12.6021,
      "step": 182
    },
    {
      "epoch": 1.9783783783783784,
      "grad_norm": 0.12970903515815735,
      "learning_rate": 1.962316193157593e-06,
      "loss": 12.5962,
      "step": 183
    },
    {
      "epoch": 1.9891891891891893,
      "grad_norm": 0.14982154965400696,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 13.5821,
      "step": 184
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.18340377509593964,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 16.944,
      "step": 185
    },
    {
      "epoch": 2.0108108108108107,
      "grad_norm": 0.11652179062366486,
      "learning_rate": 1.333670137599713e-06,
      "loss": 12.4083,
      "step": 186
    },
    {
      "epoch": 2.0216216216216214,
      "grad_norm": 0.13282690942287445,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 12.4074,
      "step": 187
    },
    {
      "epoch": 2.0324324324324325,
      "grad_norm": 0.12091400474309921,
      "learning_rate": 9.810017062595322e-07,
      "loss": 12.4018,
      "step": 188
    },
    {
      "epoch": 2.0432432432432432,
      "grad_norm": 0.12270679324865341,
      "learning_rate": 8.247462563808817e-07,
      "loss": 12.4044,
      "step": 189
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 0.12140685319900513,
      "learning_rate": 6.819348298638839e-07,
      "loss": 12.4022,
      "step": 190
    },
    {
      "epoch": 2.064864864864865,
      "grad_norm": 0.12446163594722748,
      "learning_rate": 5.526064699265753e-07,
      "loss": 12.4028,
      "step": 191
    },
    {
      "epoch": 2.075675675675676,
      "grad_norm": 0.12257818877696991,
      "learning_rate": 4.367965336512403e-07,
      "loss": 12.4032,
      "step": 192
    },
    {
      "epoch": 2.0864864864864865,
      "grad_norm": 0.13448520004749298,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 12.406,
      "step": 193
    },
    {
      "epoch": 2.097297297297297,
      "grad_norm": 0.13731332123279572,
      "learning_rate": 2.458548727494292e-07,
      "loss": 12.4044,
      "step": 194
    },
    {
      "epoch": 2.108108108108108,
      "grad_norm": 0.13274356722831726,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 12.4052,
      "step": 195
    },
    {
      "epoch": 2.118918918918919,
      "grad_norm": 0.12331502884626389,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 12.4018,
      "step": 196
    },
    {
      "epoch": 2.1297297297297297,
      "grad_norm": 0.13163962960243225,
      "learning_rate": 6.150154258476315e-08,
      "loss": 12.3991,
      "step": 197
    },
    {
      "epoch": 2.1405405405405404,
      "grad_norm": 0.13687770068645477,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 12.4009,
      "step": 198
    },
    {
      "epoch": 2.1513513513513516,
      "grad_norm": 0.1390213519334793,
      "learning_rate": 6.834750376549792e-09,
      "loss": 12.4061,
      "step": 199
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.11568073183298111,
      "learning_rate": 0.0,
      "loss": 12.4,
      "step": 200
    },
    {
      "epoch": 2.1621621621621623,
      "eval_loss": 12.402924537658691,
      "eval_runtime": 1.2045,
      "eval_samples_per_second": 129.517,
      "eval_steps_per_second": 32.379,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 778804789248.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}