{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.02258547189520341,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011292735947601705,
      "grad_norm": 3.614788147388026e-05,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.00011292735947601705,
      "eval_loss": 11.5,
      "eval_runtime": 67.3019,
      "eval_samples_per_second": 221.613,
      "eval_steps_per_second": 55.407,
      "step": 1
    },
    {
      "epoch": 0.0002258547189520341,
      "grad_norm": 3.123121496173553e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.00033878207842805115,
      "grad_norm": 2.8957145332242362e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0004517094379040682,
      "grad_norm": 3.201327854185365e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.0005646367973800852,
      "grad_norm": 3.30324619426392e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0006775641568561023,
      "grad_norm": 1.9614395569078624e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0007904915163321194,
      "grad_norm": 2.3348015020019375e-05,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0009034188758081364,
      "grad_norm": 3.713077967404388e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0010163462352841535,
      "grad_norm": 2.811581907735672e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0011292735947601704,
      "grad_norm": 2.1962290702504106e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.0012422009542361876,
      "grad_norm": 3.7259764212649316e-05,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.0013551283137122046,
      "grad_norm": 1.6783784303697757e-05,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0014680556731882218,
      "grad_norm": 4.028781768283807e-05,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.0015809830326642387,
      "grad_norm": 3.867182749672793e-05,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.0016939103921402557,
      "grad_norm": 3.935163840651512e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0018068377516162728,
      "grad_norm": 3.734438359970227e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.0019197651110922898,
      "grad_norm": 3.779438338824548e-05,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.002032692470568307,
      "grad_norm": 3.9759692299412563e-05,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.002145619830044324,
      "grad_norm": 5.707326272386126e-05,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.002258547189520341,
      "grad_norm": 4.848073876928538e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.002371474548996358,
      "grad_norm": 4.8901285481406376e-05,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.0024844019084723752,
      "grad_norm": 5.652082109008916e-05,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.002597329267948392,
      "grad_norm": 9.701135422801599e-05,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.002710256627424409,
      "grad_norm": 5.8126366639044136e-05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0028231839869004263,
      "grad_norm": 6.462896999437362e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.0029361113463764435,
      "grad_norm": 5.241742110229097e-05,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.0030490387058524603,
      "grad_norm": 5.914594657951966e-05,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.0031619660653284774,
      "grad_norm": 5.9205271099926904e-05,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.0032748934248044946,
      "grad_norm": 8.066185546340421e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.0033878207842805113,
      "grad_norm": 8.380277722608298e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.0035007481437565285,
      "grad_norm": 5.8457095292396843e-05,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.0036136755032325457,
      "grad_norm": 8.569472265662625e-05,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.003726602862708563,
      "grad_norm": 8.675931894686073e-05,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.0038395302221845796,
      "grad_norm": 6.944208143977448e-05,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.003952457581660597,
      "grad_norm": 6.330825272016227e-05,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.004065384941136614,
      "grad_norm": 8.716557931620628e-05,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.004178312300612631,
      "grad_norm": 8.742913632886484e-05,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.004291239660088648,
      "grad_norm": 8.630647062091157e-05,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.004404167019564665,
      "grad_norm": 0.00016223177954088897,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.004517094379040682,
      "grad_norm": 0.00011058787640649825,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.004630021738516699,
      "grad_norm": 8.163695019902661e-05,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.004742949097992716,
      "grad_norm": 0.00010987564746756107,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.004855876457468733,
      "grad_norm": 0.0001059857604559511,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.0049688038169447505,
      "grad_norm": 9.816615784075111e-05,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.005081731176420768,
      "grad_norm": 0.00014900887617841363,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.005194658535896784,
      "grad_norm": 0.00011268858361290768,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.005307585895372801,
      "grad_norm": 7.1711816417519e-05,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.005420513254848818,
      "grad_norm": 9.647711704019457e-05,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.0055334406143248355,
      "grad_norm": 0.00010786413622554392,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.005646367973800853,
      "grad_norm": 0.00016665902512613684,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.005646367973800853,
      "eval_loss": 11.5,
      "eval_runtime": 67.5491,
      "eval_samples_per_second": 220.802,
      "eval_steps_per_second": 55.204,
      "step": 50
    },
    {
      "epoch": 0.00575929533327687,
      "grad_norm": 0.00012017812696285546,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.005872222692752887,
      "grad_norm": 0.0001343134936178103,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.005985150052228903,
      "grad_norm": 0.00015316739154513925,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.0060980774117049205,
      "grad_norm": 0.00017474868218414485,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.006211004771180938,
      "grad_norm": 0.00016668184252921492,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.006323932130656955,
      "grad_norm": 0.00015841574349906296,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.006436859490132972,
      "grad_norm": 0.0001790779788279906,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.006549786849608989,
      "grad_norm": 0.00017626842600293458,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.006662714209085006,
      "grad_norm": 0.0001485657412558794,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.006775641568561023,
      "grad_norm": 0.00014905091666150838,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.00688856892803704,
      "grad_norm": 0.0001529305154690519,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.007001496287513057,
      "grad_norm": 0.00014436226047109812,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.007114423646989074,
      "grad_norm": 0.0001759410952217877,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.007227351006465091,
      "grad_norm": 0.0001730956428218633,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.007340278365941109,
      "grad_norm": 0.00014131213538348675,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.007453205725417126,
      "grad_norm": 0.00015544843336101621,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.007566133084893142,
      "grad_norm": 0.00021280854707583785,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.007679060444369159,
      "grad_norm": 0.00018610603001434356,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.007791987803845176,
      "grad_norm": 0.00024964436306618154,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.007904915163321194,
      "grad_norm": 0.00019768517813645303,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.00801784252279721,
      "grad_norm": 0.000184554563020356,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.008130769882273228,
      "grad_norm": 0.0001460126368328929,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.008243697241749245,
      "grad_norm": 0.00013527653936762363,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.008356624601225262,
      "grad_norm": 0.00025912016280926764,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.00846955196070128,
      "grad_norm": 0.00016677695384714752,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.008582479320177297,
      "grad_norm": 0.00021515833213925362,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.008695406679653314,
      "grad_norm": 0.0001635932712815702,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.00880833403912933,
      "grad_norm": 0.00023186433827504516,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.008921261398605346,
      "grad_norm": 0.0002264918148284778,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.009034188758081364,
      "grad_norm": 0.00024249026319012046,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.00914711611755738,
      "grad_norm": 0.00018272663874085993,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.009260043477033398,
      "grad_norm": 0.00021202840434852988,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.009372970836509415,
      "grad_norm": 0.0002833819016814232,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.009485898195985432,
      "grad_norm": 0.00017938493692781776,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.00959882555546145,
      "grad_norm": 0.0002173448447138071,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.009711752914937467,
      "grad_norm": 0.0002737494942266494,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.009824680274413484,
      "grad_norm": 0.00017274862329941243,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.009937607633889501,
      "grad_norm": 0.0002653098199516535,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.010050534993365518,
      "grad_norm": 0.00022271896887104958,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.010163462352841535,
      "grad_norm": 0.00023912770848255605,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.010276389712317553,
      "grad_norm": 0.00016209685418289155,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.010389317071793568,
      "grad_norm": 0.00021656660828739405,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.010502244431269585,
      "grad_norm": 0.00018429952615406364,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.010615171790745602,
      "grad_norm": 0.0002193470427300781,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.01072809915022162,
      "grad_norm": 0.00018955218547489494,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.010841026509697637,
      "grad_norm": 0.0002180974988732487,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.010953953869173654,
      "grad_norm": 0.00031547690741717815,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.011066881228649671,
      "grad_norm": 0.00026234364486299455,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.011179808588125688,
      "grad_norm": 0.00021698707132600248,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.011292735947601705,
      "grad_norm": 0.00021808786550536752,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.011292735947601705,
      "eval_loss": 11.5,
      "eval_runtime": 67.3296,
      "eval_samples_per_second": 221.522,
      "eval_steps_per_second": 55.384,
      "step": 100
    },
    {
      "epoch": 0.011405663307077723,
      "grad_norm": 0.00020273785048630089,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.01151859066655374,
      "grad_norm": 0.00018752928008325398,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.011631518026029757,
      "grad_norm": 0.00024807575391605496,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.011744445385505774,
      "grad_norm": 0.00029868530691601336,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.011857372744981791,
      "grad_norm": 0.0001731940865283832,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.011970300104457807,
      "grad_norm": 0.00019566631817724556,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.012083227463933824,
      "grad_norm": 0.000265254988335073,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.012196154823409841,
      "grad_norm": 0.00025869469391182065,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.012309082182885858,
      "grad_norm": 0.0002323861262993887,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.012422009542361875,
      "grad_norm": 0.00026914261979982257,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.012534936901837893,
      "grad_norm": 0.00024509779177606106,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.01264786426131391,
      "grad_norm": 0.0002930598857346922,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.012760791620789927,
      "grad_norm": 0.00033543931203894317,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.012873718980265944,
      "grad_norm": 0.00026181910652667284,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.012986646339741961,
      "grad_norm": 0.00019415067799855024,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.013099573699217978,
      "grad_norm": 0.00027309541474096477,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.013212501058693996,
      "grad_norm": 0.0002228021330665797,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.013325428418170013,
      "grad_norm": 0.00025557493790984154,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.01343835577764603,
      "grad_norm": 0.00028617956559173763,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.013551283137122045,
      "grad_norm": 0.00027835150831378996,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.013664210496598063,
      "grad_norm": 0.0003506547072902322,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.01377713785607408,
      "grad_norm": 0.00029180655837990344,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.013890065215550097,
      "grad_norm": 0.00034192061866633594,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.014002992575026114,
      "grad_norm": 0.0003464849723968655,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.014115919934502131,
      "grad_norm": 0.00037444758345372975,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.014228847293978148,
      "grad_norm": 0.0003205283428542316,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.014341774653454166,
      "grad_norm": 0.000297871301881969,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.014454702012930183,
      "grad_norm": 0.0002908136521000415,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.0145676293724062,
      "grad_norm": 0.0004460868949536234,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.014680556731882217,
      "grad_norm": 0.00029642146546393633,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.014793484091358234,
      "grad_norm": 0.0004096778866369277,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.014906411450834251,
      "grad_norm": 0.0003805152664426714,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.015019338810310269,
      "grad_norm": 0.0002970382629428059,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.015132266169786284,
      "grad_norm": 0.00027175122522749007,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.015245193529262301,
      "grad_norm": 0.00040949141839519143,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.015358120888738318,
      "grad_norm": 0.0002882351109292358,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.015471048248214336,
      "grad_norm": 0.0002739099145401269,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.015583975607690353,
      "grad_norm": 0.00025052292039617896,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.01569690296716637,
      "grad_norm": 0.00036617598379962146,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.015809830326642387,
      "grad_norm": 0.00031820579897612333,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.015922757686118404,
      "grad_norm": 0.000301756284898147,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.01603568504559442,
      "grad_norm": 0.0002617697464302182,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.01614861240507044,
      "grad_norm": 0.0002809892175719142,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.016261539764546456,
      "grad_norm": 0.00029954491765238345,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.016374467124022473,
      "grad_norm": 0.0003878922143485397,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.01648739448349849,
      "grad_norm": 0.0002571862132754177,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.016600321842974507,
      "grad_norm": 0.0002629749069456011,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.016713249202450525,
      "grad_norm": 0.000236553096328862,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.016826176561926542,
      "grad_norm": 0.0002887703012675047,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.01693910392140256,
      "grad_norm": 0.00024253812443930656,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.01693910392140256,
      "eval_loss": 11.5,
      "eval_runtime": 67.6518,
      "eval_samples_per_second": 220.467,
      "eval_steps_per_second": 55.121,
      "step": 150
    },
    {
      "epoch": 0.017052031280878576,
      "grad_norm": 0.00022687959426548332,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.017164958640354593,
      "grad_norm": 0.00025120441569015384,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.01727788599983061,
      "grad_norm": 0.0002398672659182921,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.017390813359306628,
      "grad_norm": 0.00023704004706814885,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.017503740718782645,
      "grad_norm": 0.00026754479040391743,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.01761666807825866,
      "grad_norm": 0.0002529373741708696,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.017729595437734676,
      "grad_norm": 0.00032713040127418935,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.017842522797210693,
      "grad_norm": 0.00031030309037305415,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.01795545015668671,
      "grad_norm": 0.00032333206036128104,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.018068377516162727,
      "grad_norm": 0.00028134314925409853,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.018181304875638744,
      "grad_norm": 0.000390295113902539,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.01829423223511476,
      "grad_norm": 0.0002561201108619571,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.01840715959459078,
      "grad_norm": 0.000311757146846503,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.018520086954066796,
      "grad_norm": 0.00025277171516790986,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.018633014313542813,
      "grad_norm": 0.0003587704268284142,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.01874594167301883,
      "grad_norm": 0.00032000569626688957,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.018858869032494847,
      "grad_norm": 0.0003866164479404688,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.018971796391970865,
      "grad_norm": 0.00030903815058991313,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.019084723751446882,
      "grad_norm": 0.00035700431908480823,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.0191976511109229,
      "grad_norm": 0.00036900988197885454,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.019310578470398916,
      "grad_norm": 0.0003007377963513136,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.019423505829874933,
      "grad_norm": 0.0003097676963079721,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.01953643318935095,
      "grad_norm": 0.00035511297755874693,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.019649360548826968,
      "grad_norm": 0.0003163871879223734,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.019762287908302985,
      "grad_norm": 0.00040754114161245525,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.019875215267779002,
      "grad_norm": 0.00029164121951907873,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.01998814262725502,
      "grad_norm": 0.0003299713716842234,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.020101069986731036,
      "grad_norm": 0.0004000996705144644,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.020213997346207054,
      "grad_norm": 0.0002446115540806204,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.02032692470568307,
      "grad_norm": 0.0003760512627195567,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.020439852065159088,
      "grad_norm": 0.0003339052200317383,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.020552779424635105,
      "grad_norm": 0.00032041073427535594,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.020665706784111122,
      "grad_norm": 0.00033732884912751615,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.020778634143587136,
      "grad_norm": 0.0002904120774473995,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.020891561503063153,
      "grad_norm": 0.0002944996813312173,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.02100448886253917,
      "grad_norm": 0.0003913106338586658,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.021117416222015187,
      "grad_norm": 0.00030264805536717176,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.021230343581491205,
      "grad_norm": 0.0003101128386333585,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.021343270940967222,
      "grad_norm": 0.00043780505075119436,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.02145619830044324,
      "grad_norm": 0.0003100104513578117,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.021569125659919256,
      "grad_norm": 0.0003175575693603605,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.021682053019395273,
      "grad_norm": 0.00034154922468587756,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.02179498037887129,
      "grad_norm": 0.00029154884396120906,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.021907907738347308,
      "grad_norm": 0.0002526903699617833,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.022020835097823325,
      "grad_norm": 0.00047206023009493947,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.022133762457299342,
      "grad_norm": 0.0002853488549590111,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.02224668981677536,
      "grad_norm": 0.0003255183401051909,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.022359617176251376,
      "grad_norm": 0.00031697956728748977,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.022472544535727394,
      "grad_norm": 0.00035115343052893877,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.02258547189520341,
      "grad_norm": 0.00033498730044811964,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.02258547189520341,
      "eval_loss": 11.5,
      "eval_runtime": 67.5521,
      "eval_samples_per_second": 220.792,
      "eval_steps_per_second": 55.202,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32158462771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}