{
  "best_metric": 0.7564756870269775,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.022200638268350215,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011100319134175107,
      "grad_norm": 2.46205735206604,
      "learning_rate": 1e-05,
      "loss": 1.2577,
      "step": 1
    },
    {
      "epoch": 0.00011100319134175107,
      "eval_loss": 2.9744057655334473,
      "eval_runtime": 1141.4331,
      "eval_samples_per_second": 13.293,
      "eval_steps_per_second": 3.324,
      "step": 1
    },
    {
      "epoch": 0.00022200638268350214,
      "grad_norm": 2.9185256958007812,
      "learning_rate": 2e-05,
      "loss": 1.506,
      "step": 2
    },
    {
      "epoch": 0.0003330095740252532,
      "grad_norm": 2.96941876411438,
      "learning_rate": 3e-05,
      "loss": 1.481,
      "step": 3
    },
    {
      "epoch": 0.0004440127653670043,
      "grad_norm": 2.581153392791748,
      "learning_rate": 4e-05,
      "loss": 1.5443,
      "step": 4
    },
    {
      "epoch": 0.0005550159567087554,
      "grad_norm": 2.7623963356018066,
      "learning_rate": 5e-05,
      "loss": 1.5787,
      "step": 5
    },
    {
      "epoch": 0.0006660191480505064,
      "grad_norm": 2.6426663398742676,
      "learning_rate": 6e-05,
      "loss": 1.4454,
      "step": 6
    },
    {
      "epoch": 0.0007770223393922575,
      "grad_norm": 2.1133389472961426,
      "learning_rate": 7e-05,
      "loss": 1.2349,
      "step": 7
    },
    {
      "epoch": 0.0008880255307340086,
      "grad_norm": 2.273888349533081,
      "learning_rate": 8e-05,
      "loss": 1.253,
      "step": 8
    },
    {
      "epoch": 0.0009990287220757598,
      "grad_norm": 2.109757661819458,
      "learning_rate": 9e-05,
      "loss": 1.0575,
      "step": 9
    },
    {
      "epoch": 0.0011100319134175107,
      "grad_norm": 1.8438607454299927,
      "learning_rate": 0.0001,
      "loss": 0.9085,
      "step": 10
    },
    {
      "epoch": 0.001221035104759262,
      "grad_norm": 1.6636931896209717,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9911,
      "step": 11
    },
    {
      "epoch": 0.0013320382961010129,
      "grad_norm": 1.52732515335083,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9625,
      "step": 12
    },
    {
      "epoch": 0.001443041487442764,
      "grad_norm": 1.211435079574585,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7835,
      "step": 13
    },
    {
      "epoch": 0.001554044678784515,
      "grad_norm": 1.4507479667663574,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.908,
      "step": 14
    },
    {
      "epoch": 0.0016650478701262662,
      "grad_norm": 1.6412380933761597,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9051,
      "step": 15
    },
    {
      "epoch": 0.0017760510614680172,
      "grad_norm": 1.461786150932312,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9719,
      "step": 16
    },
    {
      "epoch": 0.0018870542528097683,
      "grad_norm": 1.4119453430175781,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9492,
      "step": 17
    },
    {
      "epoch": 0.0019980574441515195,
      "grad_norm": 1.231529712677002,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.858,
      "step": 18
    },
    {
      "epoch": 0.0021090606354932703,
      "grad_norm": 1.0582536458969116,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7127,
      "step": 19
    },
    {
      "epoch": 0.0022200638268350214,
      "grad_norm": 1.2853320837020874,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8858,
      "step": 20
    },
    {
      "epoch": 0.0023310670181767726,
      "grad_norm": 1.1679506301879883,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7529,
      "step": 21
    },
    {
      "epoch": 0.002442070209518524,
      "grad_norm": 1.2692056894302368,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8864,
      "step": 22
    },
    {
      "epoch": 0.0025530734008602745,
      "grad_norm": 1.2956397533416748,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.85,
      "step": 23
    },
    {
      "epoch": 0.0026640765922020257,
      "grad_norm": 1.4673477411270142,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9242,
      "step": 24
    },
    {
      "epoch": 0.002775079783543777,
      "grad_norm": 1.3525632619857788,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9741,
      "step": 25
    },
    {
      "epoch": 0.002886082974885528,
      "grad_norm": 1.9216840267181396,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.045,
      "step": 26
    },
    {
      "epoch": 0.002997086166227279,
      "grad_norm": 1.4240648746490479,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8114,
      "step": 27
    },
    {
      "epoch": 0.00310808935756903,
      "grad_norm": 1.5814491510391235,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7554,
      "step": 28
    },
    {
      "epoch": 0.003219092548910781,
      "grad_norm": 1.2749347686767578,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7537,
      "step": 29
    },
    {
      "epoch": 0.0033300957402525324,
      "grad_norm": 1.3637299537658691,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7823,
      "step": 30
    },
    {
      "epoch": 0.003441098931594283,
      "grad_norm": 1.722434401512146,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9274,
      "step": 31
    },
    {
      "epoch": 0.0035521021229360343,
      "grad_norm": 1.5786689519882202,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9189,
      "step": 32
    },
    {
      "epoch": 0.0036631053142777855,
      "grad_norm": 1.5733418464660645,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.725,
      "step": 33
    },
    {
      "epoch": 0.0037741085056195367,
      "grad_norm": 1.8876582384109497,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9021,
      "step": 34
    },
    {
      "epoch": 0.003885111696961288,
      "grad_norm": 1.4569281339645386,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8872,
      "step": 35
    },
    {
      "epoch": 0.003996114888303039,
      "grad_norm": 1.510157823562622,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8128,
      "step": 36
    },
    {
      "epoch": 0.00410711807964479,
      "grad_norm": 1.4462164640426636,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8201,
      "step": 37
    },
    {
      "epoch": 0.0042181212709865405,
      "grad_norm": 1.422254204750061,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8283,
      "step": 38
    },
    {
      "epoch": 0.004329124462328292,
      "grad_norm": 1.3379862308502197,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.5971,
      "step": 39
    },
    {
      "epoch": 0.004440127653670043,
      "grad_norm": 1.3725043535232544,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8118,
      "step": 40
    },
    {
      "epoch": 0.0045511308450117945,
      "grad_norm": 1.5491840839385986,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7418,
      "step": 41
    },
    {
      "epoch": 0.004662134036353545,
      "grad_norm": 1.6002413034439087,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8428,
      "step": 42
    },
    {
      "epoch": 0.004773137227695296,
      "grad_norm": 1.6917510032653809,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9056,
      "step": 43
    },
    {
      "epoch": 0.004884140419037048,
      "grad_norm": 1.7446221113204956,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8666,
      "step": 44
    },
    {
      "epoch": 0.004995143610378798,
      "grad_norm": 2.7468857765197754,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8409,
      "step": 45
    },
    {
      "epoch": 0.005106146801720549,
      "grad_norm": 2.0201501846313477,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.792,
      "step": 46
    },
    {
      "epoch": 0.005217149993062301,
      "grad_norm": 1.940047025680542,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6652,
      "step": 47
    },
    {
      "epoch": 0.0053281531844040515,
      "grad_norm": 1.9866968393325806,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6353,
      "step": 48
    },
    {
      "epoch": 0.005439156375745803,
      "grad_norm": 2.8619282245635986,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.8224,
      "step": 49
    },
    {
      "epoch": 0.005550159567087554,
      "grad_norm": 2.674960136413574,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.608,
      "step": 50
    },
    {
      "epoch": 0.005550159567087554,
      "eval_loss": 0.8254091143608093,
      "eval_runtime": 1145.681,
      "eval_samples_per_second": 13.244,
      "eval_steps_per_second": 3.312,
      "step": 50
    },
    {
      "epoch": 0.005661162758429305,
      "grad_norm": 1.0036686658859253,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.953,
      "step": 51
    },
    {
      "epoch": 0.005772165949771056,
      "grad_norm": 1.0603018999099731,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8554,
      "step": 52
    },
    {
      "epoch": 0.005883169141112807,
      "grad_norm": 0.8736121654510498,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8861,
      "step": 53
    },
    {
      "epoch": 0.005994172332454558,
      "grad_norm": 0.9409048557281494,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8456,
      "step": 54
    },
    {
      "epoch": 0.006105175523796309,
      "grad_norm": 0.9477500915527344,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8381,
      "step": 55
    },
    {
      "epoch": 0.00621617871513806,
      "grad_norm": 1.1850745677947998,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8929,
      "step": 56
    },
    {
      "epoch": 0.006327181906479812,
      "grad_norm": 1.0310847759246826,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8982,
      "step": 57
    },
    {
      "epoch": 0.006438185097821562,
      "grad_norm": 1.0277560949325562,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8895,
      "step": 58
    },
    {
      "epoch": 0.006549188289163313,
      "grad_norm": 0.8867915868759155,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7826,
      "step": 59
    },
    {
      "epoch": 0.006660191480505065,
      "grad_norm": 1.078498125076294,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8777,
      "step": 60
    },
    {
      "epoch": 0.0067711946718468155,
      "grad_norm": 0.9189152717590332,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7924,
      "step": 61
    },
    {
      "epoch": 0.006882197863188566,
      "grad_norm": 1.011573314666748,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9122,
      "step": 62
    },
    {
      "epoch": 0.006993201054530318,
      "grad_norm": 1.0407687425613403,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8104,
      "step": 63
    },
    {
      "epoch": 0.007104204245872069,
      "grad_norm": 1.0033093690872192,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9252,
      "step": 64
    },
    {
      "epoch": 0.00721520743721382,
      "grad_norm": 0.919106662273407,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7244,
      "step": 65
    },
    {
      "epoch": 0.007326210628555571,
      "grad_norm": 0.9753147959709167,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7824,
      "step": 66
    },
    {
      "epoch": 0.007437213819897322,
      "grad_norm": 0.9869587421417236,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7801,
      "step": 67
    },
    {
      "epoch": 0.007548217011239073,
      "grad_norm": 1.0366357564926147,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.821,
      "step": 68
    },
    {
      "epoch": 0.007659220202580824,
      "grad_norm": 1.1145334243774414,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8619,
      "step": 69
    },
    {
      "epoch": 0.007770223393922576,
      "grad_norm": 1.2978206872940063,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9037,
      "step": 70
    },
    {
      "epoch": 0.007881226585264326,
      "grad_norm": 1.1509613990783691,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7544,
      "step": 71
    },
    {
      "epoch": 0.007992229776606078,
      "grad_norm": 1.0371291637420654,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7826,
      "step": 72
    },
    {
      "epoch": 0.008103232967947828,
      "grad_norm": 1.0573813915252686,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7808,
      "step": 73
    },
    {
      "epoch": 0.00821423615928958,
      "grad_norm": 1.2486634254455566,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6838,
      "step": 74
    },
    {
      "epoch": 0.008325239350631331,
      "grad_norm": 1.2400583028793335,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.8826,
      "step": 75
    },
    {
      "epoch": 0.008436242541973081,
      "grad_norm": 1.0707412958145142,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7261,
      "step": 76
    },
    {
      "epoch": 0.008547245733314833,
      "grad_norm": 1.325318455696106,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9285,
      "step": 77
    },
    {
      "epoch": 0.008658248924656584,
      "grad_norm": 1.3431965112686157,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9954,
      "step": 78
    },
    {
      "epoch": 0.008769252115998334,
      "grad_norm": 1.395011305809021,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8256,
      "step": 79
    },
    {
      "epoch": 0.008880255307340086,
      "grad_norm": 1.2236677408218384,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8649,
      "step": 80
    },
    {
      "epoch": 0.008991258498681837,
      "grad_norm": 1.3813550472259521,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7499,
      "step": 81
    },
    {
      "epoch": 0.009102261690023589,
      "grad_norm": 1.1952629089355469,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7567,
      "step": 82
    },
    {
      "epoch": 0.009213264881365339,
      "grad_norm": 1.1774139404296875,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5969,
      "step": 83
    },
    {
      "epoch": 0.00932426807270709,
      "grad_norm": 1.3768928050994873,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7333,
      "step": 84
    },
    {
      "epoch": 0.009435271264048842,
      "grad_norm": 1.5121829509735107,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8053,
      "step": 85
    },
    {
      "epoch": 0.009546274455390592,
      "grad_norm": 1.3658143281936646,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8026,
      "step": 86
    },
    {
      "epoch": 0.009657277646732344,
      "grad_norm": 1.400071620941162,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6916,
      "step": 87
    },
    {
      "epoch": 0.009768280838074095,
      "grad_norm": 1.3228888511657715,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7051,
      "step": 88
    },
    {
      "epoch": 0.009879284029415845,
      "grad_norm": 1.5070359706878662,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8033,
      "step": 89
    },
    {
      "epoch": 0.009990287220757597,
      "grad_norm": 1.335098147392273,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7683,
      "step": 90
    },
    {
      "epoch": 0.010101290412099348,
      "grad_norm": 1.4469175338745117,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5573,
      "step": 91
    },
    {
      "epoch": 0.010212293603441098,
      "grad_norm": 1.5435446500778198,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7527,
      "step": 92
    },
    {
      "epoch": 0.01032329679478285,
      "grad_norm": 1.571133017539978,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.797,
      "step": 93
    },
    {
      "epoch": 0.010434299986124601,
      "grad_norm": 1.4781806468963623,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7084,
      "step": 94
    },
    {
      "epoch": 0.010545303177466351,
      "grad_norm": 1.586531162261963,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7317,
      "step": 95
    },
    {
      "epoch": 0.010656306368808103,
      "grad_norm": 1.778027892112732,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6611,
      "step": 96
    },
    {
      "epoch": 0.010767309560149855,
      "grad_norm": 1.9934014081954956,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.0245,
      "step": 97
    },
    {
      "epoch": 0.010878312751491606,
      "grad_norm": 2.2396204471588135,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8315,
      "step": 98
    },
    {
      "epoch": 0.010989315942833356,
      "grad_norm": 2.139233350753784,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6726,
      "step": 99
    },
    {
      "epoch": 0.011100319134175108,
      "grad_norm": 2.108496904373169,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6403,
      "step": 100
    },
    {
      "epoch": 0.011100319134175108,
      "eval_loss": 0.8000498414039612,
      "eval_runtime": 1145.8791,
      "eval_samples_per_second": 13.241,
      "eval_steps_per_second": 3.311,
      "step": 100
    },
    {
      "epoch": 0.01121132232551686,
      "grad_norm": 0.9548881649971008,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9997,
      "step": 101
    },
    {
      "epoch": 0.01132232551685861,
      "grad_norm": 0.9524307250976562,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7981,
      "step": 102
    },
    {
      "epoch": 0.01143332870820036,
      "grad_norm": 0.7759146094322205,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7778,
      "step": 103
    },
    {
      "epoch": 0.011544331899542112,
      "grad_norm": 0.8394144773483276,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8345,
      "step": 104
    },
    {
      "epoch": 0.011655335090883862,
      "grad_norm": 0.8525381684303284,
      "learning_rate": 5e-05,
      "loss": 0.7855,
      "step": 105
    },
    {
      "epoch": 0.011766338282225614,
      "grad_norm": 0.7555638551712036,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7991,
      "step": 106
    },
    {
      "epoch": 0.011877341473567365,
      "grad_norm": 0.8012582063674927,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7975,
      "step": 107
    },
    {
      "epoch": 0.011988344664909115,
      "grad_norm": 0.8859834671020508,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7675,
      "step": 108
    },
    {
      "epoch": 0.012099347856250867,
      "grad_norm": 0.8139801621437073,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7521,
      "step": 109
    },
    {
      "epoch": 0.012210351047592619,
      "grad_norm": 0.9739270806312561,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8728,
      "step": 110
    },
    {
      "epoch": 0.01232135423893437,
      "grad_norm": 0.9866568446159363,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8775,
      "step": 111
    },
    {
      "epoch": 0.01243235743027612,
      "grad_norm": 0.8560431599617004,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8013,
      "step": 112
    },
    {
      "epoch": 0.012543360621617872,
      "grad_norm": 0.7876772880554199,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6903,
      "step": 113
    },
    {
      "epoch": 0.012654363812959623,
      "grad_norm": 0.9936425685882568,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8773,
      "step": 114
    },
    {
      "epoch": 0.012765367004301373,
      "grad_norm": 0.888233482837677,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8006,
      "step": 115
    },
    {
      "epoch": 0.012876370195643125,
      "grad_norm": 1.7261533737182617,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8066,
      "step": 116
    },
    {
      "epoch": 0.012987373386984876,
      "grad_norm": 0.8280375599861145,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7376,
      "step": 117
    },
    {
      "epoch": 0.013098376578326626,
      "grad_norm": 0.944814145565033,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8482,
      "step": 118
    },
    {
      "epoch": 0.013209379769668378,
      "grad_norm": 0.8955385088920593,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7321,
      "step": 119
    },
    {
      "epoch": 0.01332038296101013,
      "grad_norm": 0.9717075824737549,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8521,
      "step": 120
    },
    {
      "epoch": 0.01343138615235188,
      "grad_norm": 1.0090442895889282,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8109,
      "step": 121
    },
    {
      "epoch": 0.013542389343693631,
      "grad_norm": 0.9781575202941895,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6706,
      "step": 122
    },
    {
      "epoch": 0.013653392535035383,
      "grad_norm": 0.9317004680633545,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7469,
      "step": 123
    },
    {
      "epoch": 0.013764395726377133,
      "grad_norm": 1.0925298929214478,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7327,
      "step": 124
    },
    {
      "epoch": 0.013875398917718884,
      "grad_norm": 1.1367082595825195,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8619,
      "step": 125
    },
    {
      "epoch": 0.013986402109060636,
      "grad_norm": 1.0657652616500854,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.762,
      "step": 126
    },
    {
      "epoch": 0.014097405300402387,
      "grad_norm": 1.2131907939910889,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.855,
      "step": 127
    },
    {
      "epoch": 0.014208408491744137,
      "grad_norm": 1.1185275316238403,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7924,
      "step": 128
    },
    {
      "epoch": 0.014319411683085889,
      "grad_norm": 1.0810774564743042,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7749,
      "step": 129
    },
    {
      "epoch": 0.01443041487442764,
      "grad_norm": 1.1585290431976318,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.832,
      "step": 130
    },
    {
      "epoch": 0.01454141806576939,
      "grad_norm": 1.3194619417190552,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8636,
      "step": 131
    },
    {
      "epoch": 0.014652421257111142,
      "grad_norm": 1.165088415145874,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6905,
      "step": 132
    },
    {
      "epoch": 0.014763424448452894,
      "grad_norm": 1.3448327779769897,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8639,
      "step": 133
    },
    {
      "epoch": 0.014874427639794643,
      "grad_norm": 1.3206565380096436,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.858,
      "step": 134
    },
    {
      "epoch": 0.014985430831136395,
      "grad_norm": 1.3232163190841675,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8556,
      "step": 135
    },
    {
      "epoch": 0.015096434022478147,
      "grad_norm": 1.536351203918457,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.83,
      "step": 136
    },
    {
      "epoch": 0.015207437213819897,
      "grad_norm": 1.3677195310592651,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8433,
      "step": 137
    },
    {
      "epoch": 0.015318440405161648,
      "grad_norm": 1.368539571762085,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.815,
      "step": 138
    },
    {
      "epoch": 0.0154294435965034,
      "grad_norm": 1.2523564100265503,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7776,
      "step": 139
    },
    {
      "epoch": 0.015540446787845151,
      "grad_norm": 1.5745289325714111,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.8687,
      "step": 140
    },
    {
      "epoch": 0.015651449979186903,
      "grad_norm": 1.360909104347229,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6858,
      "step": 141
    },
    {
      "epoch": 0.015762453170528653,
      "grad_norm": 1.4736465215682983,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7617,
      "step": 142
    },
    {
      "epoch": 0.015873456361870403,
      "grad_norm": 1.7552369832992554,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7585,
      "step": 143
    },
    {
      "epoch": 0.015984459553212156,
      "grad_norm": 1.5908312797546387,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7162,
      "step": 144
    },
    {
      "epoch": 0.016095462744553906,
      "grad_norm": 1.4336963891983032,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7521,
      "step": 145
    },
    {
      "epoch": 0.016206465935895656,
      "grad_norm": 1.3816375732421875,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5573,
      "step": 146
    },
    {
      "epoch": 0.01631746912723741,
      "grad_norm": 2.1245291233062744,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.903,
      "step": 147
    },
    {
      "epoch": 0.01642847231857916,
      "grad_norm": 1.5307954549789429,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6457,
      "step": 148
    },
    {
      "epoch": 0.01653947550992091,
      "grad_norm": 1.8521398305892944,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5851,
      "step": 149
    },
    {
      "epoch": 0.016650478701262662,
      "grad_norm": 2.9574155807495117,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5597,
      "step": 150
    },
    {
      "epoch": 0.016650478701262662,
      "eval_loss": 0.763370931148529,
      "eval_runtime": 1145.7489,
      "eval_samples_per_second": 13.243,
      "eval_steps_per_second": 3.311,
      "step": 150
    },
    {
      "epoch": 0.016761481892604412,
      "grad_norm": 0.5705669522285461,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.8143,
      "step": 151
    },
    {
      "epoch": 0.016872485083946162,
      "grad_norm": 0.7938715815544128,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8332,
      "step": 152
    },
    {
      "epoch": 0.016983488275287915,
      "grad_norm": 0.6518698930740356,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7732,
      "step": 153
    },
    {
      "epoch": 0.017094491466629665,
      "grad_norm": 0.6880605816841125,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7927,
      "step": 154
    },
    {
      "epoch": 0.017205494657971415,
      "grad_norm": 0.7354186177253723,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7558,
      "step": 155
    },
    {
      "epoch": 0.01731649784931317,
      "grad_norm": 0.7295877933502197,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7673,
      "step": 156
    },
    {
      "epoch": 0.01742750104065492,
      "grad_norm": 0.74038165807724,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.697,
      "step": 157
    },
    {
      "epoch": 0.01753850423199667,
      "grad_norm": 0.7655072808265686,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.8203,
      "step": 158
    },
    {
      "epoch": 0.01764950742333842,
      "grad_norm": 0.7224744558334351,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.6659,
      "step": 159
    },
    {
      "epoch": 0.01776051061468017,
      "grad_norm": 0.7613934278488159,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.697,
      "step": 160
    },
    {
      "epoch": 0.01787151380602192,
      "grad_norm": 0.858565092086792,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8102,
      "step": 161
    },
    {
      "epoch": 0.017982516997363675,
      "grad_norm": 0.8788639307022095,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7872,
      "step": 162
    },
    {
      "epoch": 0.018093520188705425,
      "grad_norm": 0.8154757618904114,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7837,
      "step": 163
    },
    {
      "epoch": 0.018204523380047178,
      "grad_norm": 0.9190912246704102,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7901,
      "step": 164
    },
    {
      "epoch": 0.018315526571388928,
      "grad_norm": 0.8907411098480225,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7717,
      "step": 165
    },
    {
      "epoch": 0.018426529762730678,
      "grad_norm": 0.9676344394683838,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.818,
      "step": 166
    },
    {
      "epoch": 0.01853753295407243,
      "grad_norm": 0.9463810920715332,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.8879,
      "step": 167
    },
    {
      "epoch": 0.01864853614541418,
      "grad_norm": 0.9944425225257874,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8445,
      "step": 168
    },
    {
      "epoch": 0.01875953933675593,
      "grad_norm": 0.8990952968597412,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.721,
      "step": 169
    },
    {
      "epoch": 0.018870542528097684,
      "grad_norm": 0.8375579714775085,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6993,
      "step": 170
    },
    {
      "epoch": 0.018981545719439434,
      "grad_norm": 1.0556035041809082,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.8153,
      "step": 171
    },
    {
      "epoch": 0.019092548910781184,
      "grad_norm": 1.1603304147720337,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8289,
      "step": 172
    },
    {
      "epoch": 0.019203552102122937,
      "grad_norm": 0.9727008938789368,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6605,
      "step": 173
    },
    {
      "epoch": 0.019314555293464687,
      "grad_norm": 1.4717906713485718,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8865,
      "step": 174
    },
    {
      "epoch": 0.019425558484806437,
      "grad_norm": 1.0308983325958252,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7769,
      "step": 175
    },
    {
      "epoch": 0.01953656167614819,
      "grad_norm": 1.0141948461532593,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7555,
      "step": 176
    },
    {
      "epoch": 0.01964756486748994,
      "grad_norm": 1.141520380973816,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.883,
      "step": 177
    },
    {
      "epoch": 0.01975856805883169,
      "grad_norm": 1.2374851703643799,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.9166,
      "step": 178
    },
    {
      "epoch": 0.019869571250173444,
      "grad_norm": 1.1877533197402954,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7506,
      "step": 179
    },
    {
      "epoch": 0.019980574441515193,
      "grad_norm": 1.2082701921463013,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7716,
      "step": 180
    },
    {
      "epoch": 0.020091577632856943,
      "grad_norm": 1.3170320987701416,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8647,
      "step": 181
    },
    {
      "epoch": 0.020202580824198697,
      "grad_norm": 0.9791188836097717,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6261,
      "step": 182
    },
    {
      "epoch": 0.020313584015540447,
      "grad_norm": 1.2046897411346436,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7236,
      "step": 183
    },
    {
      "epoch": 0.020424587206882196,
      "grad_norm": 1.2107791900634766,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.8182,
      "step": 184
    },
    {
      "epoch": 0.02053559039822395,
      "grad_norm": 1.3451091051101685,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.8793,
      "step": 185
    },
    {
      "epoch": 0.0206465935895657,
      "grad_norm": 1.3159432411193848,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7977,
      "step": 186
    },
    {
      "epoch": 0.02075759678090745,
      "grad_norm": 1.3294883966445923,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.771,
      "step": 187
    },
    {
      "epoch": 0.020868599972249203,
      "grad_norm": 1.486621618270874,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6302,
      "step": 188
    },
    {
      "epoch": 0.020979603163590953,
      "grad_norm": 1.2656733989715576,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8048,
      "step": 189
    },
    {
      "epoch": 0.021090606354932703,
      "grad_norm": 1.5385503768920898,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.794,
      "step": 190
    },
    {
      "epoch": 0.021201609546274456,
      "grad_norm": 1.473299503326416,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8443,
      "step": 191
    },
    {
      "epoch": 0.021312612737616206,
      "grad_norm": 1.5102007389068604,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7908,
      "step": 192
    },
    {
      "epoch": 0.02142361592895796,
      "grad_norm": 1.3541548252105713,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.681,
      "step": 193
    },
    {
      "epoch": 0.02153461912029971,
      "grad_norm": 1.9007542133331299,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6512,
      "step": 194
    },
    {
      "epoch": 0.02164562231164146,
      "grad_norm": 1.628554344177246,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7478,
      "step": 195
    },
    {
      "epoch": 0.021756625502983212,
      "grad_norm": 1.6045345067977905,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7084,
      "step": 196
    },
    {
      "epoch": 0.021867628694324962,
      "grad_norm": 1.9932445287704468,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8174,
      "step": 197
    },
    {
      "epoch": 0.021978631885666712,
      "grad_norm": 2.0245158672332764,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7201,
      "step": 198
    },
    {
      "epoch": 0.022089635077008465,
      "grad_norm": 1.7372196912765503,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5644,
      "step": 199
    },
    {
      "epoch": 0.022200638268350215,
      "grad_norm": 1.8568713665008545,
      "learning_rate": 0.0,
      "loss": 0.5159,
      "step": 200
    },
    {
      "epoch": 0.022200638268350215,
      "eval_loss": 0.7564756870269775,
      "eval_runtime": 1145.4627,
      "eval_samples_per_second": 13.246,
      "eval_steps_per_second": 3.312,
      "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": 3.0207984414385766e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}