{
  "best_metric": 0.7275354266166687,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10064159013712416,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005032079506856208,
      "grad_norm": 0.11089494824409485,
      "learning_rate": 1e-05,
      "loss": 0.4509,
      "step": 1
    },
    {
      "epoch": 0.0005032079506856208,
      "eval_loss": 0.9475297331809998,
      "eval_runtime": 108.9917,
      "eval_samples_per_second": 30.709,
      "eval_steps_per_second": 7.679,
      "step": 1
    },
    {
      "epoch": 0.0010064159013712416,
      "grad_norm": 0.13697780668735504,
      "learning_rate": 2e-05,
      "loss": 0.6929,
      "step": 2
    },
    {
      "epoch": 0.0015096238520568624,
      "grad_norm": 0.11470163613557816,
      "learning_rate": 3e-05,
      "loss": 0.6079,
      "step": 3
    },
    {
      "epoch": 0.0020128318027424832,
      "grad_norm": 0.09494270384311676,
      "learning_rate": 4e-05,
      "loss": 0.572,
      "step": 4
    },
    {
      "epoch": 0.002516039753428104,
      "grad_norm": 0.09147272258996964,
      "learning_rate": 5e-05,
      "loss": 0.5455,
      "step": 5
    },
    {
      "epoch": 0.003019247704113725,
      "grad_norm": 0.09253623336553574,
      "learning_rate": 6e-05,
      "loss": 0.646,
      "step": 6
    },
    {
      "epoch": 0.0035224556547993457,
      "grad_norm": 0.10796216130256653,
      "learning_rate": 7e-05,
      "loss": 0.6016,
      "step": 7
    },
    {
      "epoch": 0.0040256636054849665,
      "grad_norm": 0.10085698962211609,
      "learning_rate": 8e-05,
      "loss": 0.6048,
      "step": 8
    },
    {
      "epoch": 0.004528871556170587,
      "grad_norm": 0.12255082279443741,
      "learning_rate": 9e-05,
      "loss": 0.7375,
      "step": 9
    },
    {
      "epoch": 0.005032079506856208,
      "grad_norm": 0.12754583358764648,
      "learning_rate": 0.0001,
      "loss": 0.7137,
      "step": 10
    },
    {
      "epoch": 0.005535287457541829,
      "grad_norm": 0.10587132722139359,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6694,
      "step": 11
    },
    {
      "epoch": 0.00603849540822745,
      "grad_norm": 0.11355913430452347,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7551,
      "step": 12
    },
    {
      "epoch": 0.0065417033589130705,
      "grad_norm": 0.119578517973423,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7752,
      "step": 13
    },
    {
      "epoch": 0.007044911309598691,
      "grad_norm": 0.12642312049865723,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7661,
      "step": 14
    },
    {
      "epoch": 0.007548119260284312,
      "grad_norm": 0.137640580534935,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7708,
      "step": 15
    },
    {
      "epoch": 0.008051327210969933,
      "grad_norm": 0.11690231412649155,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7485,
      "step": 16
    },
    {
      "epoch": 0.008554535161655554,
      "grad_norm": 0.12925206124782562,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.7728,
      "step": 17
    },
    {
      "epoch": 0.009057743112341175,
      "grad_norm": 0.13023410737514496,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7064,
      "step": 18
    },
    {
      "epoch": 0.009560951063026795,
      "grad_norm": 0.1209554523229599,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7633,
      "step": 19
    },
    {
      "epoch": 0.010064159013712416,
      "grad_norm": 0.11963346600532532,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7406,
      "step": 20
    },
    {
      "epoch": 0.010567366964398037,
      "grad_norm": 0.13651467859745026,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.775,
      "step": 21
    },
    {
      "epoch": 0.011070574915083658,
      "grad_norm": 0.12827056646347046,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7399,
      "step": 22
    },
    {
      "epoch": 0.011573782865769279,
      "grad_norm": 0.1426420658826828,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8255,
      "step": 23
    },
    {
      "epoch": 0.0120769908164549,
      "grad_norm": 0.1348872184753418,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7293,
      "step": 24
    },
    {
      "epoch": 0.01258019876714052,
      "grad_norm": 0.12856493890285492,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7443,
      "step": 25
    },
    {
      "epoch": 0.013083406717826141,
      "grad_norm": 0.15314924716949463,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8005,
      "step": 26
    },
    {
      "epoch": 0.013586614668511762,
      "grad_norm": 0.13596178591251373,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6989,
      "step": 27
    },
    {
      "epoch": 0.014089822619197383,
      "grad_norm": 0.1359986662864685,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7113,
      "step": 28
    },
    {
      "epoch": 0.014593030569883004,
      "grad_norm": 0.15764488279819489,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8275,
      "step": 29
    },
    {
      "epoch": 0.015096238520568624,
      "grad_norm": 0.14812134206295013,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7772,
      "step": 30
    },
    {
      "epoch": 0.015599446471254245,
      "grad_norm": 0.17374853789806366,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7448,
      "step": 31
    },
    {
      "epoch": 0.016102654421939866,
      "grad_norm": 0.1859665960073471,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7514,
      "step": 32
    },
    {
      "epoch": 0.01660586237262549,
      "grad_norm": 0.1799079328775406,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8057,
      "step": 33
    },
    {
      "epoch": 0.017109070323311108,
      "grad_norm": 0.18952247500419617,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.7833,
      "step": 34
    },
    {
      "epoch": 0.01761227827399673,
      "grad_norm": 0.1861303150653839,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7221,
      "step": 35
    },
    {
      "epoch": 0.01811548622468235,
      "grad_norm": 0.20794929563999176,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7306,
      "step": 36
    },
    {
      "epoch": 0.018618694175367972,
      "grad_norm": 0.18528755009174347,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7416,
      "step": 37
    },
    {
      "epoch": 0.01912190212605359,
      "grad_norm": 0.1950317919254303,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7498,
      "step": 38
    },
    {
      "epoch": 0.019625110076739213,
      "grad_norm": 0.2363661676645279,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8568,
      "step": 39
    },
    {
      "epoch": 0.020128318027424832,
      "grad_norm": 0.24882489442825317,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8257,
      "step": 40
    },
    {
      "epoch": 0.020631525978110455,
      "grad_norm": 0.22711476683616638,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8734,
      "step": 41
    },
    {
      "epoch": 0.021134733928796074,
      "grad_norm": 0.24530361592769623,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8059,
      "step": 42
    },
    {
      "epoch": 0.021637941879481697,
      "grad_norm": 0.32730892300605774,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.9457,
      "step": 43
    },
    {
      "epoch": 0.022141149830167316,
      "grad_norm": 0.30625611543655396,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9027,
      "step": 44
    },
    {
      "epoch": 0.022644357780852938,
      "grad_norm": 0.3409554362297058,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.0112,
      "step": 45
    },
    {
      "epoch": 0.023147565731538557,
      "grad_norm": 0.338459849357605,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.1034,
      "step": 46
    },
    {
      "epoch": 0.02365077368222418,
      "grad_norm": 0.3196316659450531,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8768,
      "step": 47
    },
    {
      "epoch": 0.0241539816329098,
      "grad_norm": 0.45284125208854675,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0378,
      "step": 48
    },
    {
      "epoch": 0.02465718958359542,
      "grad_norm": 0.4794355034828186,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.0116,
      "step": 49
    },
    {
      "epoch": 0.02516039753428104,
      "grad_norm": 0.7119191884994507,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.2563,
      "step": 50
    },
    {
      "epoch": 0.02516039753428104,
      "eval_loss": 0.7825813293457031,
      "eval_runtime": 109.0596,
      "eval_samples_per_second": 30.69,
      "eval_steps_per_second": 7.675,
      "step": 50
    },
    {
      "epoch": 0.025663605484966663,
      "grad_norm": 0.23233357071876526,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5027,
      "step": 51
    },
    {
      "epoch": 0.026166813435652282,
      "grad_norm": 0.22573114931583405,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5608,
      "step": 52
    },
    {
      "epoch": 0.026670021386337905,
      "grad_norm": 0.1670915186405182,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5056,
      "step": 53
    },
    {
      "epoch": 0.027173229337023524,
      "grad_norm": 0.128662109375,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5223,
      "step": 54
    },
    {
      "epoch": 0.027676437287709146,
      "grad_norm": 0.15088199079036713,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6293,
      "step": 55
    },
    {
      "epoch": 0.028179645238394765,
      "grad_norm": 0.15873658657073975,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6692,
      "step": 56
    },
    {
      "epoch": 0.028682853189080388,
      "grad_norm": 0.16415560245513916,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7164,
      "step": 57
    },
    {
      "epoch": 0.029186061139766007,
      "grad_norm": 0.16069954633712769,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7214,
      "step": 58
    },
    {
      "epoch": 0.02968926909045163,
      "grad_norm": 0.12133229523897171,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6924,
      "step": 59
    },
    {
      "epoch": 0.03019247704113725,
      "grad_norm": 0.12897957861423492,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.707,
      "step": 60
    },
    {
      "epoch": 0.03069568499182287,
      "grad_norm": 0.11956129223108292,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6473,
      "step": 61
    },
    {
      "epoch": 0.03119889294250849,
      "grad_norm": 0.12122786790132523,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7121,
      "step": 62
    },
    {
      "epoch": 0.03170210089319411,
      "grad_norm": 0.13581089675426483,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7767,
      "step": 63
    },
    {
      "epoch": 0.03220530884387973,
      "grad_norm": 0.11350779980421066,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6711,
      "step": 64
    },
    {
      "epoch": 0.03270851679456535,
      "grad_norm": 0.1122126430273056,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7292,
      "step": 65
    },
    {
      "epoch": 0.03321172474525098,
      "grad_norm": 0.13209980726242065,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7055,
      "step": 66
    },
    {
      "epoch": 0.033714932695936596,
      "grad_norm": 0.12379534542560577,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7467,
      "step": 67
    },
    {
      "epoch": 0.034218140646622215,
      "grad_norm": 0.12720420956611633,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7393,
      "step": 68
    },
    {
      "epoch": 0.034721348597307834,
      "grad_norm": 0.14425255358219147,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7591,
      "step": 69
    },
    {
      "epoch": 0.03522455654799346,
      "grad_norm": 0.12099296599626541,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6971,
      "step": 70
    },
    {
      "epoch": 0.03572776449867908,
      "grad_norm": 0.12772992253303528,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6776,
      "step": 71
    },
    {
      "epoch": 0.0362309724493647,
      "grad_norm": 0.12644952535629272,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7323,
      "step": 72
    },
    {
      "epoch": 0.03673418040005032,
      "grad_norm": 0.13073988258838654,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7587,
      "step": 73
    },
    {
      "epoch": 0.037237388350735943,
      "grad_norm": 0.12914054095745087,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7199,
      "step": 74
    },
    {
      "epoch": 0.03774059630142156,
      "grad_norm": 0.1345658302307129,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7532,
      "step": 75
    },
    {
      "epoch": 0.03824380425210718,
      "grad_norm": 0.1373067945241928,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7698,
      "step": 76
    },
    {
      "epoch": 0.0387470122027928,
      "grad_norm": 0.12877635657787323,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.701,
      "step": 77
    },
    {
      "epoch": 0.03925022015347843,
      "grad_norm": 0.1489383727312088,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7672,
      "step": 78
    },
    {
      "epoch": 0.039753428104164046,
      "grad_norm": 0.1302322894334793,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7165,
      "step": 79
    },
    {
      "epoch": 0.040256636054849665,
      "grad_norm": 0.1638227254152298,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6797,
      "step": 80
    },
    {
      "epoch": 0.04075984400553529,
      "grad_norm": 0.15397989749908447,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.752,
      "step": 81
    },
    {
      "epoch": 0.04126305195622091,
      "grad_norm": 0.16103407740592957,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7569,
      "step": 82
    },
    {
      "epoch": 0.04176625990690653,
      "grad_norm": 0.15292704105377197,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7804,
      "step": 83
    },
    {
      "epoch": 0.04226946785759215,
      "grad_norm": 0.1656564325094223,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7629,
      "step": 84
    },
    {
      "epoch": 0.042772675808277774,
      "grad_norm": 0.18749134242534637,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7342,
      "step": 85
    },
    {
      "epoch": 0.04327588375896339,
      "grad_norm": 0.159772589802742,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6726,
      "step": 86
    },
    {
      "epoch": 0.04377909170964901,
      "grad_norm": 0.19694285094738007,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8074,
      "step": 87
    },
    {
      "epoch": 0.04428229966033463,
      "grad_norm": 0.19535323977470398,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8028,
      "step": 88
    },
    {
      "epoch": 0.04478550761102026,
      "grad_norm": 0.19837376475334167,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7762,
      "step": 89
    },
    {
      "epoch": 0.045288715561705876,
      "grad_norm": 0.19611485302448273,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.757,
      "step": 90
    },
    {
      "epoch": 0.045791923512391496,
      "grad_norm": 0.21543379127979279,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.749,
      "step": 91
    },
    {
      "epoch": 0.046295131463077115,
      "grad_norm": 0.24316658079624176,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.8411,
      "step": 92
    },
    {
      "epoch": 0.04679833941376274,
      "grad_norm": 0.5825835466384888,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.8895,
      "step": 93
    },
    {
      "epoch": 0.04730154736444836,
      "grad_norm": 0.2559880018234253,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.8822,
      "step": 94
    },
    {
      "epoch": 0.04780475531513398,
      "grad_norm": 0.28130990266799927,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.8853,
      "step": 95
    },
    {
      "epoch": 0.0483079632658196,
      "grad_norm": 0.3243025839328766,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8538,
      "step": 96
    },
    {
      "epoch": 0.048811171216505224,
      "grad_norm": 0.3163517415523529,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.004,
      "step": 97
    },
    {
      "epoch": 0.04931437916719084,
      "grad_norm": 0.3108052909374237,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8196,
      "step": 98
    },
    {
      "epoch": 0.04981758711787646,
      "grad_norm": 0.40163445472717285,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.051,
      "step": 99
    },
    {
      "epoch": 0.05032079506856208,
      "grad_norm": 0.5705707669258118,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.0355,
      "step": 100
    },
    {
      "epoch": 0.05032079506856208,
      "eval_loss": 0.7396858334541321,
      "eval_runtime": 109.1645,
      "eval_samples_per_second": 30.66,
      "eval_steps_per_second": 7.667,
      "step": 100
    },
    {
      "epoch": 0.05082400301924771,
      "grad_norm": 0.1098746582865715,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6163,
      "step": 101
    },
    {
      "epoch": 0.051327210969933326,
      "grad_norm": 0.099557064473629,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5237,
      "step": 102
    },
    {
      "epoch": 0.051830418920618945,
      "grad_norm": 0.09129441529512405,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4726,
      "step": 103
    },
    {
      "epoch": 0.052333626871304564,
      "grad_norm": 0.08337600529193878,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5092,
      "step": 104
    },
    {
      "epoch": 0.05283683482199019,
      "grad_norm": 0.09488656371831894,
      "learning_rate": 5e-05,
      "loss": 0.5281,
      "step": 105
    },
    {
      "epoch": 0.05334004277267581,
      "grad_norm": 0.10297906398773193,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5875,
      "step": 106
    },
    {
      "epoch": 0.05384325072336143,
      "grad_norm": 0.11365678161382675,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6468,
      "step": 107
    },
    {
      "epoch": 0.05434645867404705,
      "grad_norm": 0.11643990129232407,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.663,
      "step": 108
    },
    {
      "epoch": 0.054849666624732674,
      "grad_norm": 0.12148042023181915,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6596,
      "step": 109
    },
    {
      "epoch": 0.05535287457541829,
      "grad_norm": 0.10783781111240387,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6624,
      "step": 110
    },
    {
      "epoch": 0.05585608252610391,
      "grad_norm": 0.10216180235147476,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6303,
      "step": 111
    },
    {
      "epoch": 0.05635929047678953,
      "grad_norm": 0.11392393708229065,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6785,
      "step": 112
    },
    {
      "epoch": 0.05686249842747516,
      "grad_norm": 0.11666851490736008,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7169,
      "step": 113
    },
    {
      "epoch": 0.057365706378160776,
      "grad_norm": 0.10292133688926697,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6471,
      "step": 114
    },
    {
      "epoch": 0.057868914328846395,
      "grad_norm": 0.11152872443199158,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7274,
      "step": 115
    },
    {
      "epoch": 0.058372122279532014,
      "grad_norm": 0.11710900068283081,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7558,
      "step": 116
    },
    {
      "epoch": 0.05887533023021764,
      "grad_norm": 0.11335055530071259,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.722,
      "step": 117
    },
    {
      "epoch": 0.05937853818090326,
      "grad_norm": 0.1274121254682541,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7701,
      "step": 118
    },
    {
      "epoch": 0.05988174613158888,
      "grad_norm": 0.11273667216300964,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.704,
      "step": 119
    },
    {
      "epoch": 0.0603849540822745,
      "grad_norm": 0.1252250075340271,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7608,
      "step": 120
    },
    {
      "epoch": 0.06088816203296012,
      "grad_norm": 0.13627642393112183,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.821,
      "step": 121
    },
    {
      "epoch": 0.06139136998364574,
      "grad_norm": 0.12167434394359589,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7096,
      "step": 122
    },
    {
      "epoch": 0.06189457793433136,
      "grad_norm": 0.13027212023735046,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7451,
      "step": 123
    },
    {
      "epoch": 0.06239778588501698,
      "grad_norm": 0.12933766841888428,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6616,
      "step": 124
    },
    {
      "epoch": 0.0629009938357026,
      "grad_norm": 0.12440498173236847,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7026,
      "step": 125
    },
    {
      "epoch": 0.06340420178638823,
      "grad_norm": 0.1246756985783577,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6907,
      "step": 126
    },
    {
      "epoch": 0.06390740973707384,
      "grad_norm": 0.13212141394615173,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7264,
      "step": 127
    },
    {
      "epoch": 0.06441061768775946,
      "grad_norm": 0.15022921562194824,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7384,
      "step": 128
    },
    {
      "epoch": 0.06491382563844508,
      "grad_norm": 0.14498133957386017,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8368,
      "step": 129
    },
    {
      "epoch": 0.0654170335891307,
      "grad_norm": 0.1467330902814865,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7219,
      "step": 130
    },
    {
      "epoch": 0.06592024153981633,
      "grad_norm": 0.1421375721693039,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7486,
      "step": 131
    },
    {
      "epoch": 0.06642344949050195,
      "grad_norm": 0.15086165070533752,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7313,
      "step": 132
    },
    {
      "epoch": 0.06692665744118757,
      "grad_norm": 0.181017205119133,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7543,
      "step": 133
    },
    {
      "epoch": 0.06742986539187319,
      "grad_norm": 0.19382889568805695,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8022,
      "step": 134
    },
    {
      "epoch": 0.06793307334255881,
      "grad_norm": 0.18195609748363495,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7355,
      "step": 135
    },
    {
      "epoch": 0.06843628129324443,
      "grad_norm": 0.19928300380706787,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8159,
      "step": 136
    },
    {
      "epoch": 0.06893948924393005,
      "grad_norm": 0.18659967184066772,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7014,
      "step": 137
    },
    {
      "epoch": 0.06944269719461567,
      "grad_norm": 0.19270138442516327,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7555,
      "step": 138
    },
    {
      "epoch": 0.0699459051453013,
      "grad_norm": 0.21642041206359863,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7202,
      "step": 139
    },
    {
      "epoch": 0.07044911309598692,
      "grad_norm": 0.2072923630475998,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7878,
      "step": 140
    },
    {
      "epoch": 0.07095232104667254,
      "grad_norm": 0.25658684968948364,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8116,
      "step": 141
    },
    {
      "epoch": 0.07145552899735816,
      "grad_norm": 0.2894022762775421,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8676,
      "step": 142
    },
    {
      "epoch": 0.07195873694804378,
      "grad_norm": 0.26026374101638794,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8868,
      "step": 143
    },
    {
      "epoch": 0.0724619448987294,
      "grad_norm": 0.27932849526405334,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8082,
      "step": 144
    },
    {
      "epoch": 0.07296515284941502,
      "grad_norm": 0.3154858350753784,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.045,
      "step": 145
    },
    {
      "epoch": 0.07346836080010063,
      "grad_norm": 0.3096054494380951,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.9731,
      "step": 146
    },
    {
      "epoch": 0.07397156875078627,
      "grad_norm": 0.3147416114807129,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8451,
      "step": 147
    },
    {
      "epoch": 0.07447477670147189,
      "grad_norm": 0.3300391137599945,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.9076,
      "step": 148
    },
    {
      "epoch": 0.0749779846521575,
      "grad_norm": 0.43164920806884766,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.9813,
      "step": 149
    },
    {
      "epoch": 0.07548119260284313,
      "grad_norm": 0.7585984468460083,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9656,
      "step": 150
    },
    {
      "epoch": 0.07548119260284313,
      "eval_loss": 0.7296414971351624,
      "eval_runtime": 109.0233,
      "eval_samples_per_second": 30.7,
      "eval_steps_per_second": 7.677,
      "step": 150
    },
    {
      "epoch": 0.07598440055352874,
      "grad_norm": 0.07944902032613754,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4718,
      "step": 151
    },
    {
      "epoch": 0.07648760850421436,
      "grad_norm": 0.07683669030666351,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4638,
      "step": 152
    },
    {
      "epoch": 0.07699081645489998,
      "grad_norm": 0.07896019518375397,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.468,
      "step": 153
    },
    {
      "epoch": 0.0774940244055856,
      "grad_norm": 0.08617918193340302,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5851,
      "step": 154
    },
    {
      "epoch": 0.07799723235627123,
      "grad_norm": 0.08189351111650467,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.5152,
      "step": 155
    },
    {
      "epoch": 0.07850044030695685,
      "grad_norm": 0.08880002051591873,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5194,
      "step": 156
    },
    {
      "epoch": 0.07900364825764247,
      "grad_norm": 0.09169723093509674,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6038,
      "step": 157
    },
    {
      "epoch": 0.07950685620832809,
      "grad_norm": 0.11644299328327179,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.6902,
      "step": 158
    },
    {
      "epoch": 0.08001006415901371,
      "grad_norm": 0.1154027134180069,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.6403,
      "step": 159
    },
    {
      "epoch": 0.08051327210969933,
      "grad_norm": 0.11812397092580795,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.649,
      "step": 160
    },
    {
      "epoch": 0.08101648006038495,
      "grad_norm": 0.12437030673027039,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7149,
      "step": 161
    },
    {
      "epoch": 0.08151968801107058,
      "grad_norm": 0.10191845148801804,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6491,
      "step": 162
    },
    {
      "epoch": 0.0820228959617562,
      "grad_norm": 0.10935676842927933,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.6038,
      "step": 163
    },
    {
      "epoch": 0.08252610391244182,
      "grad_norm": 0.10928207635879517,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.68,
      "step": 164
    },
    {
      "epoch": 0.08302931186312744,
      "grad_norm": 0.12067196518182755,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6662,
      "step": 165
    },
    {
      "epoch": 0.08353251981381306,
      "grad_norm": 0.12127915024757385,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6937,
      "step": 166
    },
    {
      "epoch": 0.08403572776449868,
      "grad_norm": 0.12778066098690033,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6759,
      "step": 167
    },
    {
      "epoch": 0.0845389357151843,
      "grad_norm": 0.12904375791549683,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6526,
      "step": 168
    },
    {
      "epoch": 0.08504214366586992,
      "grad_norm": 0.1531040370464325,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8169,
      "step": 169
    },
    {
      "epoch": 0.08554535161655555,
      "grad_norm": 0.14304374158382416,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.73,
      "step": 170
    },
    {
      "epoch": 0.08604855956724117,
      "grad_norm": 0.1392136663198471,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6827,
      "step": 171
    },
    {
      "epoch": 0.08655176751792679,
      "grad_norm": 0.12628431618213654,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7238,
      "step": 172
    },
    {
      "epoch": 0.0870549754686124,
      "grad_norm": 0.1263248473405838,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7122,
      "step": 173
    },
    {
      "epoch": 0.08755818341929802,
      "grad_norm": 0.13488441705703735,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7229,
      "step": 174
    },
    {
      "epoch": 0.08806139136998364,
      "grad_norm": 0.1466904580593109,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7516,
      "step": 175
    },
    {
      "epoch": 0.08856459932066926,
      "grad_norm": 0.1369139701128006,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.718,
      "step": 176
    },
    {
      "epoch": 0.08906780727135488,
      "grad_norm": 0.1475687175989151,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7005,
      "step": 177
    },
    {
      "epoch": 0.08957101522204051,
      "grad_norm": 0.14835146069526672,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7492,
      "step": 178
    },
    {
      "epoch": 0.09007422317272613,
      "grad_norm": 0.15017321705818176,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.747,
      "step": 179
    },
    {
      "epoch": 0.09057743112341175,
      "grad_norm": 0.154312863945961,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.7025,
      "step": 180
    },
    {
      "epoch": 0.09108063907409737,
      "grad_norm": 0.15754878520965576,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7161,
      "step": 181
    },
    {
      "epoch": 0.09158384702478299,
      "grad_norm": 0.1584862917661667,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7642,
      "step": 182
    },
    {
      "epoch": 0.09208705497546861,
      "grad_norm": 0.15700611472129822,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6947,
      "step": 183
    },
    {
      "epoch": 0.09259026292615423,
      "grad_norm": 0.17075471580028534,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7225,
      "step": 184
    },
    {
      "epoch": 0.09309347087683985,
      "grad_norm": 0.1717851310968399,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7353,
      "step": 185
    },
    {
      "epoch": 0.09359667882752548,
      "grad_norm": 0.18180491030216217,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7807,
      "step": 186
    },
    {
      "epoch": 0.0940998867782111,
      "grad_norm": 0.19917936623096466,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.736,
      "step": 187
    },
    {
      "epoch": 0.09460309472889672,
      "grad_norm": 0.18067017197608948,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7377,
      "step": 188
    },
    {
      "epoch": 0.09510630267958234,
      "grad_norm": 0.23977646231651306,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8037,
      "step": 189
    },
    {
      "epoch": 0.09560951063026796,
      "grad_norm": 0.2480328381061554,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.8329,
      "step": 190
    },
    {
      "epoch": 0.09611271858095358,
      "grad_norm": 0.26312291622161865,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.9024,
      "step": 191
    },
    {
      "epoch": 0.0966159265316392,
      "grad_norm": 0.24597567319869995,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7976,
      "step": 192
    },
    {
      "epoch": 0.09711913448232481,
      "grad_norm": 0.2826707661151886,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8701,
      "step": 193
    },
    {
      "epoch": 0.09762234243301045,
      "grad_norm": 0.24611374735832214,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7436,
      "step": 194
    },
    {
      "epoch": 0.09812555038369607,
      "grad_norm": 0.2964339256286621,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.9456,
      "step": 195
    },
    {
      "epoch": 0.09862875833438169,
      "grad_norm": 0.3165876567363739,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.8959,
      "step": 196
    },
    {
      "epoch": 0.0991319662850673,
      "grad_norm": 0.358869343996048,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.9205,
      "step": 197
    },
    {
      "epoch": 0.09963517423575292,
      "grad_norm": 0.31060120463371277,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.8219,
      "step": 198
    },
    {
      "epoch": 0.10013838218643854,
      "grad_norm": 0.38945379853248596,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.9157,
      "step": 199
    },
    {
      "epoch": 0.10064159013712416,
      "grad_norm": 0.555557131767273,
      "learning_rate": 0.0,
      "loss": 0.9965,
      "step": 200
    },
    {
      "epoch": 0.10064159013712416,
      "eval_loss": 0.7275354266166687,
      "eval_runtime": 109.444,
      "eval_samples_per_second": 30.582,
      "eval_steps_per_second": 7.648,
      "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": 7.155799226843136e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}