{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.20714655618850336,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010357327809425167,
      "grad_norm": 0.00022799026919528842,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0010357327809425167,
      "eval_loss": 11.5,
      "eval_runtime": 7.3616,
      "eval_samples_per_second": 220.875,
      "eval_steps_per_second": 55.287,
      "step": 1
    },
    {
      "epoch": 0.0020714655618850335,
      "grad_norm": 0.0003189893322996795,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0031071983428275505,
      "grad_norm": 0.00030676033929921687,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.004142931123770067,
      "grad_norm": 0.0002737623290158808,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.005178663904712584,
      "grad_norm": 0.00020285221398808062,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.006214396685655101,
      "grad_norm": 0.00022217661899048835,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0072501294665976174,
      "grad_norm": 0.00033399168751202524,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.008285862247540134,
      "grad_norm": 0.00030777615029364824,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.009321595028482652,
      "grad_norm": 0.0003417783882468939,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.010357327809425169,
      "grad_norm": 0.00031432247487828135,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.011393060590367685,
      "grad_norm": 0.00041850405978038907,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.012428793371310202,
      "grad_norm": 0.00041423659422434866,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.013464526152252718,
      "grad_norm": 0.0004432552959769964,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.014500258933195235,
      "grad_norm": 0.0005180598236620426,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.015535991714137753,
      "grad_norm": 0.0005157229024916887,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.016571724495080268,
      "grad_norm": 0.00044451525900512934,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.017607457276022784,
      "grad_norm": 0.0006396652897819877,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.018643190056965304,
      "grad_norm": 0.0007490962743759155,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.01967892283790782,
      "grad_norm": 0.0007005695952102542,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.020714655618850338,
      "grad_norm": 0.0008960358682088554,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.021750388399792854,
      "grad_norm": 0.0007888373802416027,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.02278612118073537,
      "grad_norm": 0.0009302966063842177,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.023821853961677887,
      "grad_norm": 0.0008068131282925606,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.024857586742620404,
      "grad_norm": 0.0008582731243222952,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.02589331952356292,
      "grad_norm": 0.0009067477658390999,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.026929052304505437,
      "grad_norm": 0.0010893546277657151,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.027964785085447953,
      "grad_norm": 0.0012705965200439095,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.02900051786639047,
      "grad_norm": 0.0011961053824052215,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.03003625064733299,
      "grad_norm": 0.0012201120844110847,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.031071983428275506,
      "grad_norm": 0.001122495741583407,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.03210771620921802,
      "grad_norm": 0.0012052401434630156,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.033143448990160536,
      "grad_norm": 0.0011651843087747693,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.03417918177110305,
      "grad_norm": 0.001199314254336059,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.03521491455204557,
      "grad_norm": 0.0013839047169312835,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.03625064733298809,
      "grad_norm": 0.0015920372679829597,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.03728638011393061,
      "grad_norm": 0.0015730264130979776,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.038322112894873125,
      "grad_norm": 0.0017927673179656267,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.03935784567581564,
      "grad_norm": 0.0019403117476031184,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.04039357845675816,
      "grad_norm": 0.002109874738380313,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.041429311237700675,
      "grad_norm": 0.002235481981188059,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.04246504401864319,
      "grad_norm": 0.002273629419505596,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.04350077679958571,
      "grad_norm": 0.0018545888597145677,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.044536509580528225,
      "grad_norm": 0.0020099873654544353,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.04557224236147074,
      "grad_norm": 0.00231616897508502,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.04660797514241326,
      "grad_norm": 0.0018780629616230726,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.047643707923355774,
      "grad_norm": 0.002188002923503518,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.04867944070429829,
      "grad_norm": 0.0020396774634718895,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.04971517348524081,
      "grad_norm": 0.002246974967420101,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.050750906266183324,
      "grad_norm": 0.0026212125085294247,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.05178663904712584,
      "grad_norm": 0.001977828098461032,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.05178663904712584,
      "eval_loss": 11.5,
      "eval_runtime": 7.3394,
      "eval_samples_per_second": 221.544,
      "eval_steps_per_second": 55.454,
      "step": 50
    },
    {
      "epoch": 0.05282237182806836,
      "grad_norm": 0.0024861579295247793,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.05385810460901087,
      "grad_norm": 0.0019670119509100914,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.05489383738995339,
      "grad_norm": 0.0030989001970738173,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.055929570170895906,
      "grad_norm": 0.0015495226252824068,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.05696530295183842,
      "grad_norm": 0.0020954653155058622,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.05800103573278094,
      "grad_norm": 0.0029869244899600744,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.059036768513723456,
      "grad_norm": 0.002605810761451721,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.06007250129466598,
      "grad_norm": 0.003277063835412264,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.061108234075608496,
      "grad_norm": 0.0035896520130336285,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.06214396685655101,
      "grad_norm": 0.0036183360498398542,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.06317969963749352,
      "grad_norm": 0.0034529189579188824,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.06421543241843604,
      "grad_norm": 0.003610996762290597,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.06525116519937856,
      "grad_norm": 0.003862482961267233,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.06628689798032107,
      "grad_norm": 0.003459359984844923,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.06732263076126359,
      "grad_norm": 0.0038022405933588743,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.0683583635422061,
      "grad_norm": 0.003694936167448759,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.06939409632314862,
      "grad_norm": 0.0035661770962178707,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.07042982910409114,
      "grad_norm": 0.0036810808815062046,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.07146556188503367,
      "grad_norm": 0.004355982411652803,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.07250129466597618,
      "grad_norm": 0.0039038294926285744,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.0735370274469187,
      "grad_norm": 0.0036866485606878996,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.07457276022786122,
      "grad_norm": 0.003654521657153964,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.07560849300880373,
      "grad_norm": 0.003953153733164072,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.07664422578974625,
      "grad_norm": 0.0044088214635849,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.07767995857068877,
      "grad_norm": 0.005479032639414072,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.07871569135163128,
      "grad_norm": 0.00433605071157217,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.0797514241325738,
      "grad_norm": 0.004740381613373756,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.08078715691351632,
      "grad_norm": 0.0043846615590155125,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.08182288969445883,
      "grad_norm": 0.004115022253245115,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.08285862247540135,
      "grad_norm": 0.003538427408784628,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.08389435525634387,
      "grad_norm": 0.0038376604206860065,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.08493008803728638,
      "grad_norm": 0.003065840108320117,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.0859658208182289,
      "grad_norm": 0.003761674277484417,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.08700155359917142,
      "grad_norm": 0.004065261222422123,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.08803728638011393,
      "grad_norm": 0.005034289322793484,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.08907301916105645,
      "grad_norm": 0.004778858739882708,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.09010875194199897,
      "grad_norm": 0.005545433145016432,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.09114448472294148,
      "grad_norm": 0.0052436357364058495,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.092180217503884,
      "grad_norm": 0.005320776253938675,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.09321595028482652,
      "grad_norm": 0.006014833692461252,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.09425168306576903,
      "grad_norm": 0.005240185651928186,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.09528741584671155,
      "grad_norm": 0.004645434208214283,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.09632314862765406,
      "grad_norm": 0.005407446529716253,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.09735888140859658,
      "grad_norm": 0.005347494501620531,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.0983946141895391,
      "grad_norm": 0.004623935092240572,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.09943034697048161,
      "grad_norm": 0.005007303785532713,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.10046607975142413,
      "grad_norm": 0.004760530777275562,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.10150181253236665,
      "grad_norm": 0.0046646567061543465,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.10253754531330916,
      "grad_norm": 0.004948300775140524,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.10357327809425168,
      "grad_norm": 0.004574000369757414,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.10357327809425168,
      "eval_loss": 11.5,
      "eval_runtime": 7.3476,
      "eval_samples_per_second": 221.298,
      "eval_steps_per_second": 55.392,
      "step": 100
    },
    {
      "epoch": 0.1046090108751942,
      "grad_norm": 0.006246717181056738,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.10564474365613671,
      "grad_norm": 0.005163326859474182,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.10668047643707923,
      "grad_norm": 0.004129266366362572,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.10771620921802175,
      "grad_norm": 0.00251843873411417,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.10875194199896426,
      "grad_norm": 0.004422592464834452,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.10978767477990678,
      "grad_norm": 0.005128004588186741,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.1108234075608493,
      "grad_norm": 0.005420781672000885,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.11185914034179181,
      "grad_norm": 0.004918310791254044,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.11289487312273433,
      "grad_norm": 0.006114252842962742,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.11393060590367685,
      "grad_norm": 0.005137663800269365,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.11496633868461936,
      "grad_norm": 0.006155834998935461,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.11600207146556188,
      "grad_norm": 0.005608555395156145,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.1170378042465044,
      "grad_norm": 0.0059499884955585,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.11807353702744691,
      "grad_norm": 0.005027272738516331,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.11910926980838944,
      "grad_norm": 0.005771612282842398,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.12014500258933196,
      "grad_norm": 0.0048508429899811745,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.12118073537027448,
      "grad_norm": 0.0048544448800385,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.12221646815121699,
      "grad_norm": 0.005823877174407244,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.12325220093215951,
      "grad_norm": 0.005015385337173939,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.12428793371310203,
      "grad_norm": 0.005397338420152664,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.12532366649404453,
      "grad_norm": 0.005846671760082245,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.12635939927498704,
      "grad_norm": 0.005613440647721291,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.12739513205592956,
      "grad_norm": 0.005896589253097773,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.12843086483687208,
      "grad_norm": 0.0057438816875219345,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.1294665976178146,
      "grad_norm": 0.006123644765466452,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.1305023303987571,
      "grad_norm": 0.0059859114699065685,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.13153806317969963,
      "grad_norm": 0.006107951048761606,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.13257379596064214,
      "grad_norm": 0.00592269329354167,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.13360952874158466,
      "grad_norm": 0.0057358513586223125,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.13464526152252718,
      "grad_norm": 0.00435055373236537,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.1356809943034697,
      "grad_norm": 0.005028912331908941,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.1367167270844122,
      "grad_norm": 0.0045160166919231415,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.13775245986535473,
      "grad_norm": 0.003881213953718543,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.13878819264629724,
      "grad_norm": 0.004682949744164944,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.13982392542723976,
      "grad_norm": 0.005440264008939266,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.14085965820818228,
      "grad_norm": 0.004985838662832975,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.1418953909891248,
      "grad_norm": 0.005595916882157326,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.14293112377006734,
      "grad_norm": 0.005077510606497526,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.14396685655100985,
      "grad_norm": 0.005714558530598879,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.14500258933195237,
      "grad_norm": 0.005599339492619038,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.14603832211289489,
      "grad_norm": 0.005822756327688694,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.1470740548938374,
      "grad_norm": 0.004427429288625717,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 0.14810978767477992,
      "grad_norm": 0.0051300544291734695,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 0.14914552045572244,
      "grad_norm": 0.005937750451266766,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 0.15018125323666495,
      "grad_norm": 0.005371814593672752,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.15121698601760747,
      "grad_norm": 0.005310214590281248,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 0.15225271879854999,
      "grad_norm": 0.005048289895057678,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 0.1532884515794925,
      "grad_norm": 0.004475567489862442,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 0.15432418436043502,
      "grad_norm": 0.00500202551484108,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 0.15535991714137753,
      "grad_norm": 0.004190859384834766,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.15535991714137753,
      "eval_loss": 11.5,
      "eval_runtime": 7.3818,
      "eval_samples_per_second": 220.271,
      "eval_steps_per_second": 55.135,
      "step": 150
    },
    {
      "epoch": 0.15639564992232005,
      "grad_norm": 0.00494543369859457,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 0.15743138270326257,
      "grad_norm": 0.005335058551281691,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 0.15846711548420508,
      "grad_norm": 0.005374191794544458,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 0.1595028482651476,
      "grad_norm": 0.004993338603526354,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 0.16053858104609012,
      "grad_norm": 0.0033338870853185654,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.16157431382703263,
      "grad_norm": 0.004990480374544859,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 0.16261004660797515,
      "grad_norm": 0.004457120783627033,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 0.16364577938891767,
      "grad_norm": 0.006042328663170338,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 0.16468151216986018,
      "grad_norm": 0.004797046538442373,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 0.1657172449508027,
      "grad_norm": 0.00584887620061636,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.16675297773174522,
      "grad_norm": 0.005885629914700985,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 0.16778871051268773,
      "grad_norm": 0.006426781881600618,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 0.16882444329363025,
      "grad_norm": 0.0053910245187580585,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 0.16986017607457277,
      "grad_norm": 0.006142829079180956,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 0.17089590885551528,
      "grad_norm": 0.0041061630472540855,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.1719316416364578,
      "grad_norm": 0.005760208237916231,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 0.17296737441740032,
      "grad_norm": 0.005370947066694498,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 0.17400310719834283,
      "grad_norm": 0.005592199973762035,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 0.17503883997928535,
      "grad_norm": 0.005933375097811222,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 0.17607457276022787,
      "grad_norm": 0.005211621522903442,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.17711030554117038,
      "grad_norm": 0.005365594290196896,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 0.1781460383221129,
      "grad_norm": 0.005427377298474312,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 0.17918177110305541,
      "grad_norm": 0.005726740695536137,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 0.18021750388399793,
      "grad_norm": 0.005221592728048563,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 0.18125323666494045,
      "grad_norm": 0.006290689576417208,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.18228896944588296,
      "grad_norm": 0.006047503557056189,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 0.18332470222682548,
      "grad_norm": 0.006112964358180761,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 0.184360435007768,
      "grad_norm": 0.005677494220435619,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 0.18539616778871051,
      "grad_norm": 0.005709968041628599,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 0.18643190056965303,
      "grad_norm": 0.004902000073343515,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.18746763335059555,
      "grad_norm": 0.004955052398145199,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 0.18850336613153806,
      "grad_norm": 0.003700100816786289,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 0.18953909891248058,
      "grad_norm": 0.004430252127349377,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 0.1905748316934231,
      "grad_norm": 0.004325200337916613,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 0.1916105644743656,
      "grad_norm": 0.0054402644746005535,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.19264629725530813,
      "grad_norm": 0.005286505911499262,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 0.19368203003625065,
      "grad_norm": 0.006111959461122751,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 0.19471776281719316,
      "grad_norm": 0.005616979673504829,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 0.19575349559813568,
      "grad_norm": 0.005729826167225838,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 0.1967892283790782,
      "grad_norm": 0.00528825493529439,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.1978249611600207,
      "grad_norm": 0.004411572590470314,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 0.19886069394096323,
      "grad_norm": 0.0041148788295686245,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 0.19989642672190575,
      "grad_norm": 0.005613051354885101,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 0.20093215950284826,
      "grad_norm": 0.005378162954002619,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 0.20196789228379078,
      "grad_norm": 0.0053197829984128475,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.2030036250647333,
      "grad_norm": 0.0054170601069927216,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 0.2040393578456758,
      "grad_norm": 0.0058584497310221195,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 0.20507509062661833,
      "grad_norm": 0.004644473548978567,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 0.20611082340756084,
      "grad_norm": 0.005280728917568922,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 0.20714655618850336,
      "grad_norm": 0.0041040522046387196,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.20714655618850336,
      "eval_loss": 11.5,
      "eval_runtime": 7.35,
      "eval_samples_per_second": 221.225,
      "eval_steps_per_second": 55.374,
      "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
}