{
  "best_metric": 11.858244895935059,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.13527223537368954,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006763611768684477,
      "grad_norm": 0.21101497113704681,
      "learning_rate": 1e-05,
      "loss": 11.9403,
      "step": 1
    },
    {
      "epoch": 0.0006763611768684477,
      "eval_loss": 11.937972068786621,
      "eval_runtime": 29.2821,
      "eval_samples_per_second": 85.035,
      "eval_steps_per_second": 21.276,
      "step": 1
    },
    {
      "epoch": 0.0013527223537368955,
      "grad_norm": 0.2204475849866867,
      "learning_rate": 2e-05,
      "loss": 11.9339,
      "step": 2
    },
    {
      "epoch": 0.002029083530605343,
      "grad_norm": 0.1861288845539093,
      "learning_rate": 3e-05,
      "loss": 11.9398,
      "step": 3
    },
    {
      "epoch": 0.002705444707473791,
      "grad_norm": 0.1883319616317749,
      "learning_rate": 4e-05,
      "loss": 11.9352,
      "step": 4
    },
    {
      "epoch": 0.0033818058843422386,
      "grad_norm": 0.23109620809555054,
      "learning_rate": 5e-05,
      "loss": 11.9368,
      "step": 5
    },
    {
      "epoch": 0.004058167061210686,
      "grad_norm": 0.21260319650173187,
      "learning_rate": 6e-05,
      "loss": 11.9395,
      "step": 6
    },
    {
      "epoch": 0.0047345282380791345,
      "grad_norm": 0.21474258601665497,
      "learning_rate": 7e-05,
      "loss": 11.9362,
      "step": 7
    },
    {
      "epoch": 0.005410889414947582,
      "grad_norm": 0.26996690034866333,
      "learning_rate": 8e-05,
      "loss": 11.9354,
      "step": 8
    },
    {
      "epoch": 0.00608725059181603,
      "grad_norm": 0.2380349040031433,
      "learning_rate": 9e-05,
      "loss": 11.9321,
      "step": 9
    },
    {
      "epoch": 0.006763611768684477,
      "grad_norm": 0.33884358406066895,
      "learning_rate": 0.0001,
      "loss": 11.9303,
      "step": 10
    },
    {
      "epoch": 0.0074399729455529254,
      "grad_norm": 0.3404984474182129,
      "learning_rate": 9.999316524962345e-05,
      "loss": 11.9295,
      "step": 11
    },
    {
      "epoch": 0.008116334122421373,
      "grad_norm": 0.3546094000339508,
      "learning_rate": 9.997266286704631e-05,
      "loss": 11.924,
      "step": 12
    },
    {
      "epoch": 0.00879269529928982,
      "grad_norm": 0.3775385916233063,
      "learning_rate": 9.993849845741524e-05,
      "loss": 11.9344,
      "step": 13
    },
    {
      "epoch": 0.009469056476158269,
      "grad_norm": 0.4600640535354614,
      "learning_rate": 9.989068136093873e-05,
      "loss": 11.9166,
      "step": 14
    },
    {
      "epoch": 0.010145417653026716,
      "grad_norm": 0.4656665027141571,
      "learning_rate": 9.98292246503335e-05,
      "loss": 11.9212,
      "step": 15
    },
    {
      "epoch": 0.010821778829895164,
      "grad_norm": 0.44481852650642395,
      "learning_rate": 9.975414512725057e-05,
      "loss": 11.9153,
      "step": 16
    },
    {
      "epoch": 0.011498140006763611,
      "grad_norm": 0.5396250486373901,
      "learning_rate": 9.966546331768191e-05,
      "loss": 11.9046,
      "step": 17
    },
    {
      "epoch": 0.01217450118363206,
      "grad_norm": 0.4205581843852997,
      "learning_rate": 9.956320346634876e-05,
      "loss": 11.9078,
      "step": 18
    },
    {
      "epoch": 0.012850862360500507,
      "grad_norm": 0.4282219707965851,
      "learning_rate": 9.944739353007344e-05,
      "loss": 11.8997,
      "step": 19
    },
    {
      "epoch": 0.013527223537368955,
      "grad_norm": 0.42262178659439087,
      "learning_rate": 9.931806517013612e-05,
      "loss": 11.8986,
      "step": 20
    },
    {
      "epoch": 0.014203584714237404,
      "grad_norm": 0.4101008474826813,
      "learning_rate": 9.917525374361912e-05,
      "loss": 11.8946,
      "step": 21
    },
    {
      "epoch": 0.014879945891105851,
      "grad_norm": 0.39269983768463135,
      "learning_rate": 9.901899829374047e-05,
      "loss": 11.8948,
      "step": 22
    },
    {
      "epoch": 0.015556307067974298,
      "grad_norm": 0.40336206555366516,
      "learning_rate": 9.884934153917997e-05,
      "loss": 11.8847,
      "step": 23
    },
    {
      "epoch": 0.016232668244842745,
      "grad_norm": 0.3113878667354584,
      "learning_rate": 9.86663298624003e-05,
      "loss": 11.8893,
      "step": 24
    },
    {
      "epoch": 0.016909029421711193,
      "grad_norm": 0.323789119720459,
      "learning_rate": 9.847001329696653e-05,
      "loss": 11.8827,
      "step": 25
    },
    {
      "epoch": 0.01758539059857964,
      "grad_norm": 0.3201078474521637,
      "learning_rate": 9.826044551386744e-05,
      "loss": 11.8866,
      "step": 26
    },
    {
      "epoch": 0.01826175177544809,
      "grad_norm": 0.32661673426628113,
      "learning_rate": 9.803768380684242e-05,
      "loss": 11.8827,
      "step": 27
    },
    {
      "epoch": 0.018938112952316538,
      "grad_norm": 0.24808771908283234,
      "learning_rate": 9.780178907671789e-05,
      "loss": 11.8789,
      "step": 28
    },
    {
      "epoch": 0.019614474129184985,
      "grad_norm": 0.25119903683662415,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.8833,
      "step": 29
    },
    {
      "epoch": 0.020290835306053433,
      "grad_norm": 0.21726010739803314,
      "learning_rate": 9.729086208503174e-05,
      "loss": 11.8758,
      "step": 30
    },
    {
      "epoch": 0.02096719648292188,
      "grad_norm": 0.252247154712677,
      "learning_rate": 9.701596950580806e-05,
      "loss": 11.8789,
      "step": 31
    },
    {
      "epoch": 0.021643557659790327,
      "grad_norm": 0.2480008453130722,
      "learning_rate": 9.672822322997305e-05,
      "loss": 11.8777,
      "step": 32
    },
    {
      "epoch": 0.022319918836658775,
      "grad_norm": 0.20785893499851227,
      "learning_rate": 9.642770192448536e-05,
      "loss": 11.8761,
      "step": 33
    },
    {
      "epoch": 0.022996280013527222,
      "grad_norm": 0.18308520317077637,
      "learning_rate": 9.611448774886924e-05,
      "loss": 11.8783,
      "step": 34
    },
    {
      "epoch": 0.023672641190395673,
      "grad_norm": 0.19104455411434174,
      "learning_rate": 9.578866633275288e-05,
      "loss": 11.8695,
      "step": 35
    },
    {
      "epoch": 0.02434900236726412,
      "grad_norm": 0.14406198263168335,
      "learning_rate": 9.545032675245813e-05,
      "loss": 11.8719,
      "step": 36
    },
    {
      "epoch": 0.025025363544132567,
      "grad_norm": 0.16278310120105743,
      "learning_rate": 9.509956150664796e-05,
      "loss": 11.868,
      "step": 37
    },
    {
      "epoch": 0.025701724721001015,
      "grad_norm": 0.18022064864635468,
      "learning_rate": 9.473646649103818e-05,
      "loss": 11.876,
      "step": 38
    },
    {
      "epoch": 0.026378085897869462,
      "grad_norm": 0.17300967872142792,
      "learning_rate": 9.43611409721806e-05,
      "loss": 11.8716,
      "step": 39
    },
    {
      "epoch": 0.02705444707473791,
      "grad_norm": 0.13449062407016754,
      "learning_rate": 9.397368756032445e-05,
      "loss": 11.8739,
      "step": 40
    },
    {
      "epoch": 0.027730808251606356,
      "grad_norm": 0.13816285133361816,
      "learning_rate": 9.357421218136386e-05,
      "loss": 11.871,
      "step": 41
    },
    {
      "epoch": 0.028407169428474807,
      "grad_norm": 0.1892579197883606,
      "learning_rate": 9.316282404787871e-05,
      "loss": 11.871,
      "step": 42
    },
    {
      "epoch": 0.029083530605343254,
      "grad_norm": 0.15245799720287323,
      "learning_rate": 9.273963562927695e-05,
      "loss": 11.8678,
      "step": 43
    },
    {
      "epoch": 0.029759891782211702,
      "grad_norm": 0.16466772556304932,
      "learning_rate": 9.230476262104677e-05,
      "loss": 11.8643,
      "step": 44
    },
    {
      "epoch": 0.03043625295908015,
      "grad_norm": 0.14556123316287994,
      "learning_rate": 9.185832391312644e-05,
      "loss": 11.8588,
      "step": 45
    },
    {
      "epoch": 0.031112614135948596,
      "grad_norm": 0.1307539939880371,
      "learning_rate": 9.140044155740101e-05,
      "loss": 11.8668,
      "step": 46
    },
    {
      "epoch": 0.03178897531281705,
      "grad_norm": 0.16094844043254852,
      "learning_rate": 9.093124073433463e-05,
      "loss": 11.8672,
      "step": 47
    },
    {
      "epoch": 0.03246533648968549,
      "grad_norm": 0.1284143328666687,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.8725,
      "step": 48
    },
    {
      "epoch": 0.03314169766655394,
      "grad_norm": 0.15144309401512146,
      "learning_rate": 8.995939984474624e-05,
      "loss": 11.8648,
      "step": 49
    },
    {
      "epoch": 0.033818058843422386,
      "grad_norm": 0.12769220769405365,
      "learning_rate": 8.945702546981969e-05,
      "loss": 11.8628,
      "step": 50
    },
    {
      "epoch": 0.033818058843422386,
      "eval_loss": 11.869421005249023,
      "eval_runtime": 29.292,
      "eval_samples_per_second": 85.006,
      "eval_steps_per_second": 21.269,
      "step": 50
    },
    {
      "epoch": 0.034494420020290836,
      "grad_norm": 0.10370208323001862,
      "learning_rate": 8.894386393810563e-05,
      "loss": 11.8716,
      "step": 51
    },
    {
      "epoch": 0.03517078119715928,
      "grad_norm": 0.11750881373882294,
      "learning_rate": 8.842005554284296e-05,
      "loss": 11.8691,
      "step": 52
    },
    {
      "epoch": 0.03584714237402773,
      "grad_norm": 0.12145090848207474,
      "learning_rate": 8.788574348801675e-05,
      "loss": 11.8695,
      "step": 53
    },
    {
      "epoch": 0.03652350355089618,
      "grad_norm": 0.13088250160217285,
      "learning_rate": 8.73410738492077e-05,
      "loss": 11.8705,
      "step": 54
    },
    {
      "epoch": 0.037199864727764625,
      "grad_norm": 0.09613314270973206,
      "learning_rate": 8.678619553365659e-05,
      "loss": 11.8733,
      "step": 55
    },
    {
      "epoch": 0.037876225904633076,
      "grad_norm": 0.1183629110455513,
      "learning_rate": 8.622126023955446e-05,
      "loss": 11.8643,
      "step": 56
    },
    {
      "epoch": 0.03855258708150152,
      "grad_norm": 0.12383581697940826,
      "learning_rate": 8.564642241456986e-05,
      "loss": 11.8681,
      "step": 57
    },
    {
      "epoch": 0.03922894825836997,
      "grad_norm": 0.11309259384870529,
      "learning_rate": 8.506183921362443e-05,
      "loss": 11.875,
      "step": 58
    },
    {
      "epoch": 0.039905309435238415,
      "grad_norm": 0.11675012856721878,
      "learning_rate": 8.44676704559283e-05,
      "loss": 11.8738,
      "step": 59
    },
    {
      "epoch": 0.040581670612106865,
      "grad_norm": 0.10582835972309113,
      "learning_rate": 8.386407858128706e-05,
      "loss": 11.87,
      "step": 60
    },
    {
      "epoch": 0.041258031788975316,
      "grad_norm": 0.09874629229307175,
      "learning_rate": 8.32512286056924e-05,
      "loss": 11.8641,
      "step": 61
    },
    {
      "epoch": 0.04193439296584376,
      "grad_norm": 0.12302418053150177,
      "learning_rate": 8.262928807620843e-05,
      "loss": 11.8709,
      "step": 62
    },
    {
      "epoch": 0.04261075414271221,
      "grad_norm": 0.10224100947380066,
      "learning_rate": 8.199842702516583e-05,
      "loss": 11.8673,
      "step": 63
    },
    {
      "epoch": 0.043287115319580655,
      "grad_norm": 0.10085669159889221,
      "learning_rate": 8.135881792367686e-05,
      "loss": 11.8668,
      "step": 64
    },
    {
      "epoch": 0.043963476496449105,
      "grad_norm": 0.13070064783096313,
      "learning_rate": 8.07106356344834e-05,
      "loss": 11.8688,
      "step": 65
    },
    {
      "epoch": 0.04463983767331755,
      "grad_norm": 0.13864661753177643,
      "learning_rate": 8.005405736415126e-05,
      "loss": 11.8677,
      "step": 66
    },
    {
      "epoch": 0.045316198850186,
      "grad_norm": 0.09276090562343597,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.8625,
      "step": 67
    },
    {
      "epoch": 0.045992560027054444,
      "grad_norm": 0.09893247485160828,
      "learning_rate": 7.871643313414718e-05,
      "loss": 11.87,
      "step": 68
    },
    {
      "epoch": 0.046668921203922895,
      "grad_norm": 0.13095833361148834,
      "learning_rate": 7.803575286758364e-05,
      "loss": 11.8678,
      "step": 69
    },
    {
      "epoch": 0.047345282380791345,
      "grad_norm": 0.11731155961751938,
      "learning_rate": 7.734740790612136e-05,
      "loss": 11.8673,
      "step": 70
    },
    {
      "epoch": 0.04802164355765979,
      "grad_norm": 0.13166551291942596,
      "learning_rate": 7.66515864363997e-05,
      "loss": 11.8684,
      "step": 71
    },
    {
      "epoch": 0.04869800473452824,
      "grad_norm": 0.09939809143543243,
      "learning_rate": 7.594847868906076e-05,
      "loss": 11.8639,
      "step": 72
    },
    {
      "epoch": 0.049374365911396684,
      "grad_norm": 0.10804695636034012,
      "learning_rate": 7.52382768867422e-05,
      "loss": 11.8663,
      "step": 73
    },
    {
      "epoch": 0.050050727088265135,
      "grad_norm": 0.132675901055336,
      "learning_rate": 7.452117519152542e-05,
      "loss": 11.8729,
      "step": 74
    },
    {
      "epoch": 0.05072708826513358,
      "grad_norm": 0.07454847544431686,
      "learning_rate": 7.379736965185368e-05,
      "loss": 11.8687,
      "step": 75
    },
    {
      "epoch": 0.05140344944200203,
      "grad_norm": 0.0866214781999588,
      "learning_rate": 7.30670581489344e-05,
      "loss": 11.8705,
      "step": 76
    },
    {
      "epoch": 0.05207981061887048,
      "grad_norm": 0.10776250809431076,
      "learning_rate": 7.233044034264034e-05,
      "loss": 11.8614,
      "step": 77
    },
    {
      "epoch": 0.052756171795738924,
      "grad_norm": 0.10304714739322662,
      "learning_rate": 7.158771761692464e-05,
      "loss": 11.8647,
      "step": 78
    },
    {
      "epoch": 0.053432532972607374,
      "grad_norm": 0.1364087164402008,
      "learning_rate": 7.083909302476453e-05,
      "loss": 11.8626,
      "step": 79
    },
    {
      "epoch": 0.05410889414947582,
      "grad_norm": 0.10210411995649338,
      "learning_rate": 7.008477123264848e-05,
      "loss": 11.8653,
      "step": 80
    },
    {
      "epoch": 0.05478525532634427,
      "grad_norm": 0.11438775807619095,
      "learning_rate": 6.932495846462261e-05,
      "loss": 11.8666,
      "step": 81
    },
    {
      "epoch": 0.05546161650321271,
      "grad_norm": 0.10912539064884186,
      "learning_rate": 6.855986244591104e-05,
      "loss": 11.8596,
      "step": 82
    },
    {
      "epoch": 0.056137977680081164,
      "grad_norm": 0.09880189597606659,
      "learning_rate": 6.778969234612584e-05,
      "loss": 11.8633,
      "step": 83
    },
    {
      "epoch": 0.056814338856949614,
      "grad_norm": 0.12287990748882294,
      "learning_rate": 6.701465872208216e-05,
      "loss": 11.8604,
      "step": 84
    },
    {
      "epoch": 0.05749070003381806,
      "grad_norm": 0.09658095985651016,
      "learning_rate": 6.623497346023418e-05,
      "loss": 11.858,
      "step": 85
    },
    {
      "epoch": 0.05816706121068651,
      "grad_norm": 0.13980063796043396,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.8644,
      "step": 86
    },
    {
      "epoch": 0.05884342238755495,
      "grad_norm": 0.08649631589651108,
      "learning_rate": 6.466250186922325e-05,
      "loss": 11.8617,
      "step": 87
    },
    {
      "epoch": 0.059519783564423404,
      "grad_norm": 0.08612903207540512,
      "learning_rate": 6.387014543809223e-05,
      "loss": 11.8668,
      "step": 88
    },
    {
      "epoch": 0.06019614474129185,
      "grad_norm": 0.09304578602313995,
      "learning_rate": 6.307399704769099e-05,
      "loss": 11.8581,
      "step": 89
    },
    {
      "epoch": 0.0608725059181603,
      "grad_norm": 0.13147549331188202,
      "learning_rate": 6.227427435703997e-05,
      "loss": 11.8606,
      "step": 90
    },
    {
      "epoch": 0.06154886709502874,
      "grad_norm": 0.10700445622205734,
      "learning_rate": 6.147119600233758e-05,
      "loss": 11.8609,
      "step": 91
    },
    {
      "epoch": 0.06222522827189719,
      "grad_norm": 0.08180303126573563,
      "learning_rate": 6.066498153718735e-05,
      "loss": 11.8625,
      "step": 92
    },
    {
      "epoch": 0.06290158944876564,
      "grad_norm": 0.12455767393112183,
      "learning_rate": 5.985585137257401e-05,
      "loss": 11.8555,
      "step": 93
    },
    {
      "epoch": 0.0635779506256341,
      "grad_norm": 0.12393002957105637,
      "learning_rate": 5.90440267166055e-05,
      "loss": 11.856,
      "step": 94
    },
    {
      "epoch": 0.06425431180250253,
      "grad_norm": 0.11348329484462738,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 11.8579,
      "step": 95
    },
    {
      "epoch": 0.06493067297937098,
      "grad_norm": 0.1379508674144745,
      "learning_rate": 5.74131823855921e-05,
      "loss": 11.8601,
      "step": 96
    },
    {
      "epoch": 0.06560703415623943,
      "grad_norm": 0.12759019434452057,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 11.8519,
      "step": 97
    },
    {
      "epoch": 0.06628339533310788,
      "grad_norm": 0.11706313490867615,
      "learning_rate": 5.577423184847932e-05,
      "loss": 11.8518,
      "step": 98
    },
    {
      "epoch": 0.06695975650997633,
      "grad_norm": 0.11291486769914627,
      "learning_rate": 5.495227651252315e-05,
      "loss": 11.8508,
      "step": 99
    },
    {
      "epoch": 0.06763611768684477,
      "grad_norm": 0.3588656783103943,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 11.8606,
      "step": 100
    },
    {
      "epoch": 0.06763611768684477,
      "eval_loss": 11.861373901367188,
      "eval_runtime": 29.5448,
      "eval_samples_per_second": 84.279,
      "eval_steps_per_second": 21.087,
      "step": 100
    },
    {
      "epoch": 0.06831247886371322,
      "grad_norm": 0.15343239903450012,
      "learning_rate": 5.330452921628497e-05,
      "loss": 11.8615,
      "step": 101
    },
    {
      "epoch": 0.06898884004058167,
      "grad_norm": 0.08080801367759705,
      "learning_rate": 5.247918773366112e-05,
      "loss": 11.8668,
      "step": 102
    },
    {
      "epoch": 0.06966520121745012,
      "grad_norm": 0.08930213004350662,
      "learning_rate": 5.165316846586541e-05,
      "loss": 11.8624,
      "step": 103
    },
    {
      "epoch": 0.07034156239431856,
      "grad_norm": 0.08268989622592926,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 11.8545,
      "step": 104
    },
    {
      "epoch": 0.07101792357118701,
      "grad_norm": 0.13817404210567474,
      "learning_rate": 5e-05,
      "loss": 11.8679,
      "step": 105
    },
    {
      "epoch": 0.07169428474805546,
      "grad_norm": 0.1108119785785675,
      "learning_rate": 4.917330276168208e-05,
      "loss": 11.8619,
      "step": 106
    },
    {
      "epoch": 0.07237064592492391,
      "grad_norm": 0.13134723901748657,
      "learning_rate": 4.834683153413459e-05,
      "loss": 11.8574,
      "step": 107
    },
    {
      "epoch": 0.07304700710179236,
      "grad_norm": 0.11841795593500137,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 11.8564,
      "step": 108
    },
    {
      "epoch": 0.0737233682786608,
      "grad_norm": 0.15261241793632507,
      "learning_rate": 4.669547078371504e-05,
      "loss": 11.8646,
      "step": 109
    },
    {
      "epoch": 0.07439972945552925,
      "grad_norm": 0.14254596829414368,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 11.8574,
      "step": 110
    },
    {
      "epoch": 0.0750760906323977,
      "grad_norm": 0.1248069778084755,
      "learning_rate": 4.504772348747687e-05,
      "loss": 11.8638,
      "step": 111
    },
    {
      "epoch": 0.07575245180926615,
      "grad_norm": 0.09078558534383774,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 11.857,
      "step": 112
    },
    {
      "epoch": 0.07642881298613459,
      "grad_norm": 0.10824689269065857,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 11.8567,
      "step": 113
    },
    {
      "epoch": 0.07710517416300304,
      "grad_norm": 0.10614212602376938,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 11.8698,
      "step": 114
    },
    {
      "epoch": 0.07778153533987149,
      "grad_norm": 0.10335537046194077,
      "learning_rate": 4.17702704859633e-05,
      "loss": 11.8662,
      "step": 115
    },
    {
      "epoch": 0.07845789651673994,
      "grad_norm": 0.09204749017953873,
      "learning_rate": 4.095597328339452e-05,
      "loss": 11.8692,
      "step": 116
    },
    {
      "epoch": 0.07913425769360839,
      "grad_norm": 0.09570972621440887,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 11.8588,
      "step": 117
    },
    {
      "epoch": 0.07981061887047683,
      "grad_norm": 0.07798279076814651,
      "learning_rate": 3.933501846281267e-05,
      "loss": 11.8615,
      "step": 118
    },
    {
      "epoch": 0.08048698004734528,
      "grad_norm": 0.10017397999763489,
      "learning_rate": 3.852880399766243e-05,
      "loss": 11.8622,
      "step": 119
    },
    {
      "epoch": 0.08116334122421373,
      "grad_norm": 0.11533702909946442,
      "learning_rate": 3.772572564296005e-05,
      "loss": 11.8625,
      "step": 120
    },
    {
      "epoch": 0.08183970240108218,
      "grad_norm": 0.0675579160451889,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 11.8611,
      "step": 121
    },
    {
      "epoch": 0.08251606357795063,
      "grad_norm": 0.10587069392204285,
      "learning_rate": 3.612985456190778e-05,
      "loss": 11.8597,
      "step": 122
    },
    {
      "epoch": 0.08319242475481907,
      "grad_norm": 0.09893308579921722,
      "learning_rate": 3.533749813077677e-05,
      "loss": 11.8609,
      "step": 123
    },
    {
      "epoch": 0.08386878593168752,
      "grad_norm": 0.10195756703615189,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.8564,
      "step": 124
    },
    {
      "epoch": 0.08454514710855597,
      "grad_norm": 0.08373372256755829,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 11.8577,
      "step": 125
    },
    {
      "epoch": 0.08522150828542442,
      "grad_norm": 0.09708812832832336,
      "learning_rate": 3.298534127791785e-05,
      "loss": 11.8549,
      "step": 126
    },
    {
      "epoch": 0.08589786946229286,
      "grad_norm": 0.10474452376365662,
      "learning_rate": 3.221030765387417e-05,
      "loss": 11.8549,
      "step": 127
    },
    {
      "epoch": 0.08657423063916131,
      "grad_norm": 0.10434427857398987,
      "learning_rate": 3.144013755408895e-05,
      "loss": 11.8637,
      "step": 128
    },
    {
      "epoch": 0.08725059181602976,
      "grad_norm": 0.09096544235944748,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 11.8557,
      "step": 129
    },
    {
      "epoch": 0.08792695299289821,
      "grad_norm": 0.10402948409318924,
      "learning_rate": 2.991522876735154e-05,
      "loss": 11.8584,
      "step": 130
    },
    {
      "epoch": 0.08860331416976666,
      "grad_norm": 0.09839261323213577,
      "learning_rate": 2.916090697523549e-05,
      "loss": 11.8565,
      "step": 131
    },
    {
      "epoch": 0.0892796753466351,
      "grad_norm": 0.13485582172870636,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 11.853,
      "step": 132
    },
    {
      "epoch": 0.08995603652350355,
      "grad_norm": 0.10964971780776978,
      "learning_rate": 2.766955965735968e-05,
      "loss": 11.8562,
      "step": 133
    },
    {
      "epoch": 0.090632397700372,
      "grad_norm": 0.09148603677749634,
      "learning_rate": 2.693294185106562e-05,
      "loss": 11.8551,
      "step": 134
    },
    {
      "epoch": 0.09130875887724045,
      "grad_norm": 0.09787771850824356,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 11.8583,
      "step": 135
    },
    {
      "epoch": 0.09198512005410889,
      "grad_norm": 0.09096968919038773,
      "learning_rate": 2.547882480847461e-05,
      "loss": 11.8558,
      "step": 136
    },
    {
      "epoch": 0.09266148123097734,
      "grad_norm": 0.08600819110870361,
      "learning_rate": 2.476172311325783e-05,
      "loss": 11.8589,
      "step": 137
    },
    {
      "epoch": 0.09333784240784579,
      "grad_norm": 0.11731515824794769,
      "learning_rate": 2.405152131093926e-05,
      "loss": 11.8542,
      "step": 138
    },
    {
      "epoch": 0.09401420358471424,
      "grad_norm": 0.11455315351486206,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 11.8532,
      "step": 139
    },
    {
      "epoch": 0.09469056476158269,
      "grad_norm": 0.10479317605495453,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 11.8509,
      "step": 140
    },
    {
      "epoch": 0.09536692593845113,
      "grad_norm": 0.10683844238519669,
      "learning_rate": 2.196424713241637e-05,
      "loss": 11.8492,
      "step": 141
    },
    {
      "epoch": 0.09604328711531958,
      "grad_norm": 0.09233700484037399,
      "learning_rate": 2.128356686585282e-05,
      "loss": 11.8562,
      "step": 142
    },
    {
      "epoch": 0.09671964829218803,
      "grad_norm": 0.1004570722579956,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.8555,
      "step": 143
    },
    {
      "epoch": 0.09739600946905648,
      "grad_norm": 0.08633947372436523,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 11.865,
      "step": 144
    },
    {
      "epoch": 0.09807237064592493,
      "grad_norm": 0.08929416537284851,
      "learning_rate": 1.928936436551661e-05,
      "loss": 11.8601,
      "step": 145
    },
    {
      "epoch": 0.09874873182279337,
      "grad_norm": 0.14196905493736267,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 11.8587,
      "step": 146
    },
    {
      "epoch": 0.09942509299966182,
      "grad_norm": 0.10563764721155167,
      "learning_rate": 1.800157297483417e-05,
      "loss": 11.8521,
      "step": 147
    },
    {
      "epoch": 0.10010145417653027,
      "grad_norm": 0.13027088344097137,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 11.8546,
      "step": 148
    },
    {
      "epoch": 0.10077781535339872,
      "grad_norm": 0.13313868641853333,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 11.8491,
      "step": 149
    },
    {
      "epoch": 0.10145417653026716,
      "grad_norm": 0.16967670619487762,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 11.8558,
      "step": 150
    },
    {
      "epoch": 0.10145417653026716,
      "eval_loss": 11.858529090881348,
      "eval_runtime": 29.1599,
      "eval_samples_per_second": 85.391,
      "eval_steps_per_second": 21.365,
      "step": 150
    },
    {
      "epoch": 0.10213053770713561,
      "grad_norm": 0.09511326253414154,
      "learning_rate": 1.553232954407171e-05,
      "loss": 11.8661,
      "step": 151
    },
    {
      "epoch": 0.10280689888400406,
      "grad_norm": 0.07359690219163895,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 11.8638,
      "step": 152
    },
    {
      "epoch": 0.10348326006087251,
      "grad_norm": 0.12254412472248077,
      "learning_rate": 1.435357758543015e-05,
      "loss": 11.8599,
      "step": 153
    },
    {
      "epoch": 0.10415962123774096,
      "grad_norm": 0.08350329101085663,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 11.8569,
      "step": 154
    },
    {
      "epoch": 0.1048359824146094,
      "grad_norm": 0.1110653281211853,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 11.8626,
      "step": 155
    },
    {
      "epoch": 0.10551234359147785,
      "grad_norm": 0.09689097106456757,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 11.8662,
      "step": 156
    },
    {
      "epoch": 0.1061887047683463,
      "grad_norm": 0.107973113656044,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 11.8569,
      "step": 157
    },
    {
      "epoch": 0.10686506594521475,
      "grad_norm": 0.09333381056785583,
      "learning_rate": 1.157994445715706e-05,
      "loss": 11.8582,
      "step": 158
    },
    {
      "epoch": 0.10754142712208319,
      "grad_norm": 0.10233953595161438,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 11.8587,
      "step": 159
    },
    {
      "epoch": 0.10821778829895164,
      "grad_norm": 0.07999734580516815,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 11.8605,
      "step": 160
    },
    {
      "epoch": 0.10889414947582009,
      "grad_norm": 0.10883399099111557,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 11.8532,
      "step": 161
    },
    {
      "epoch": 0.10957051065268854,
      "grad_norm": 0.10061144083738327,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.8562,
      "step": 162
    },
    {
      "epoch": 0.11024687182955699,
      "grad_norm": 0.10149991512298584,
      "learning_rate": 9.068759265665384e-06,
      "loss": 11.8616,
      "step": 163
    },
    {
      "epoch": 0.11092323300642543,
      "grad_norm": 0.1031358540058136,
      "learning_rate": 8.599558442598998e-06,
      "loss": 11.868,
      "step": 164
    },
    {
      "epoch": 0.11159959418329388,
      "grad_norm": 0.10467427968978882,
      "learning_rate": 8.141676086873572e-06,
      "loss": 11.8579,
      "step": 165
    },
    {
      "epoch": 0.11227595536016233,
      "grad_norm": 0.09357937425374985,
      "learning_rate": 7.695237378953223e-06,
      "loss": 11.8615,
      "step": 166
    },
    {
      "epoch": 0.11295231653703078,
      "grad_norm": 0.09121855348348618,
      "learning_rate": 7.260364370723044e-06,
      "loss": 11.8559,
      "step": 167
    },
    {
      "epoch": 0.11362867771389923,
      "grad_norm": 0.06593197584152222,
      "learning_rate": 6.837175952121306e-06,
      "loss": 11.8556,
      "step": 168
    },
    {
      "epoch": 0.11430503889076767,
      "grad_norm": 0.10744959861040115,
      "learning_rate": 6.425787818636131e-06,
      "loss": 11.8542,
      "step": 169
    },
    {
      "epoch": 0.11498140006763612,
      "grad_norm": 0.07398264110088348,
      "learning_rate": 6.026312439675552e-06,
      "loss": 11.8571,
      "step": 170
    },
    {
      "epoch": 0.11565776124450457,
      "grad_norm": 0.09938981384038925,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 11.8474,
      "step": 171
    },
    {
      "epoch": 0.11633412242137302,
      "grad_norm": 0.08217344433069229,
      "learning_rate": 5.263533508961827e-06,
      "loss": 11.8577,
      "step": 172
    },
    {
      "epoch": 0.11701048359824145,
      "grad_norm": 0.10250749439001083,
      "learning_rate": 4.900438493352055e-06,
      "loss": 11.856,
      "step": 173
    },
    {
      "epoch": 0.1176868447751099,
      "grad_norm": 0.07639428973197937,
      "learning_rate": 4.549673247541875e-06,
      "loss": 11.8601,
      "step": 174
    },
    {
      "epoch": 0.11836320595197836,
      "grad_norm": 0.1027349904179573,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 11.8577,
      "step": 175
    },
    {
      "epoch": 0.11903956712884681,
      "grad_norm": 0.07716778665781021,
      "learning_rate": 3.885512251130763e-06,
      "loss": 11.8597,
      "step": 176
    },
    {
      "epoch": 0.11971592830571526,
      "grad_norm": 0.06251972913742065,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 11.8634,
      "step": 177
    },
    {
      "epoch": 0.1203922894825837,
      "grad_norm": 0.10872653871774673,
      "learning_rate": 3.271776770026963e-06,
      "loss": 11.8615,
      "step": 178
    },
    {
      "epoch": 0.12106865065945215,
      "grad_norm": 0.08073310554027557,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 11.8569,
      "step": 179
    },
    {
      "epoch": 0.1217450118363206,
      "grad_norm": 0.10839758068323135,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 11.8545,
      "step": 180
    },
    {
      "epoch": 0.12242137301318905,
      "grad_norm": 0.1029672771692276,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 11.8605,
      "step": 181
    },
    {
      "epoch": 0.12309773419005748,
      "grad_norm": 0.08460096269845963,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 11.8566,
      "step": 182
    },
    {
      "epoch": 0.12377409536692593,
      "grad_norm": 0.10531960427761078,
      "learning_rate": 1.962316193157593e-06,
      "loss": 11.8603,
      "step": 183
    },
    {
      "epoch": 0.12445045654379439,
      "grad_norm": 0.11051426827907562,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 11.8657,
      "step": 184
    },
    {
      "epoch": 0.12512681772066284,
      "grad_norm": 0.08552934229373932,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 11.8555,
      "step": 185
    },
    {
      "epoch": 0.1258031788975313,
      "grad_norm": 0.1120235025882721,
      "learning_rate": 1.333670137599713e-06,
      "loss": 11.8535,
      "step": 186
    },
    {
      "epoch": 0.12647954007439974,
      "grad_norm": 0.10637915879487991,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 11.8591,
      "step": 187
    },
    {
      "epoch": 0.1271559012512682,
      "grad_norm": 0.10562892258167267,
      "learning_rate": 9.810017062595322e-07,
      "loss": 11.8583,
      "step": 188
    },
    {
      "epoch": 0.1278322624281366,
      "grad_norm": 0.09353561699390411,
      "learning_rate": 8.247462563808817e-07,
      "loss": 11.8524,
      "step": 189
    },
    {
      "epoch": 0.12850862360500506,
      "grad_norm": 0.08732261508703232,
      "learning_rate": 6.819348298638839e-07,
      "loss": 11.864,
      "step": 190
    },
    {
      "epoch": 0.1291849847818735,
      "grad_norm": 0.13068413734436035,
      "learning_rate": 5.526064699265753e-07,
      "loss": 11.8568,
      "step": 191
    },
    {
      "epoch": 0.12986134595874196,
      "grad_norm": 0.10250502824783325,
      "learning_rate": 4.367965336512403e-07,
      "loss": 11.8541,
      "step": 192
    },
    {
      "epoch": 0.13053770713561041,
      "grad_norm": 0.11080504208803177,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 11.8585,
      "step": 193
    },
    {
      "epoch": 0.13121406831247887,
      "grad_norm": 0.09342342615127563,
      "learning_rate": 2.458548727494292e-07,
      "loss": 11.8486,
      "step": 194
    },
    {
      "epoch": 0.13189042948934732,
      "grad_norm": 0.09933999925851822,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 11.8514,
      "step": 195
    },
    {
      "epoch": 0.13256679066621577,
      "grad_norm": 0.09887896478176117,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 11.8508,
      "step": 196
    },
    {
      "epoch": 0.13324315184308422,
      "grad_norm": 0.10011352598667145,
      "learning_rate": 6.150154258476315e-08,
      "loss": 11.8552,
      "step": 197
    },
    {
      "epoch": 0.13391951301995267,
      "grad_norm": 0.0968865305185318,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 11.854,
      "step": 198
    },
    {
      "epoch": 0.1345958741968211,
      "grad_norm": 0.09329472482204437,
      "learning_rate": 6.834750376549792e-09,
      "loss": 11.8477,
      "step": 199
    },
    {
      "epoch": 0.13527223537368954,
      "grad_norm": 0.12064272165298462,
      "learning_rate": 0.0,
      "loss": 11.8508,
      "step": 200
    },
    {
      "epoch": 0.13527223537368954,
      "eval_loss": 11.858244895935059,
      "eval_runtime": 29.7723,
      "eval_samples_per_second": 83.635,
      "eval_steps_per_second": 20.925,
      "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": 289771094016000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}