{
  "best_metric": 1.3400603532791138,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.8648018648018647,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009324009324009324,
      "grad_norm": 0.8977329730987549,
      "learning_rate": 1e-05,
      "loss": 2.6031,
      "step": 1
    },
    {
      "epoch": 0.009324009324009324,
      "eval_loss": 4.63709831237793,
      "eval_runtime": 23.4786,
      "eval_samples_per_second": 7.709,
      "eval_steps_per_second": 1.959,
      "step": 1
    },
    {
      "epoch": 0.018648018648018648,
      "grad_norm": 0.9511700868606567,
      "learning_rate": 2e-05,
      "loss": 2.6018,
      "step": 2
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 0.7955926060676575,
      "learning_rate": 3e-05,
      "loss": 2.5984,
      "step": 3
    },
    {
      "epoch": 0.037296037296037296,
      "grad_norm": 0.7194857597351074,
      "learning_rate": 4e-05,
      "loss": 2.6467,
      "step": 4
    },
    {
      "epoch": 0.046620046620046623,
      "grad_norm": 0.605427086353302,
      "learning_rate": 5e-05,
      "loss": 2.5624,
      "step": 5
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.5001047253608704,
      "learning_rate": 6e-05,
      "loss": 2.5784,
      "step": 6
    },
    {
      "epoch": 0.06526806526806526,
      "grad_norm": 0.3669719398021698,
      "learning_rate": 7e-05,
      "loss": 2.5043,
      "step": 7
    },
    {
      "epoch": 0.07459207459207459,
      "grad_norm": 5.817723274230957,
      "learning_rate": 8e-05,
      "loss": 3.2399,
      "step": 8
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 6.294182777404785,
      "learning_rate": 9e-05,
      "loss": 3.9129,
      "step": 9
    },
    {
      "epoch": 0.09324009324009325,
      "grad_norm": 7.2702717781066895,
      "learning_rate": 0.0001,
      "loss": 3.5954,
      "step": 10
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 3.845817804336548,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.7348,
      "step": 11
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 3.017914056777954,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.4259,
      "step": 12
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 3.6076159477233887,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.0082,
      "step": 13
    },
    {
      "epoch": 0.13053613053613053,
      "grad_norm": 2.906186103820801,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8302,
      "step": 14
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 3.59165620803833,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7249,
      "step": 15
    },
    {
      "epoch": 0.14918414918414918,
      "grad_norm": 3.738245964050293,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.3016,
      "step": 16
    },
    {
      "epoch": 0.1585081585081585,
      "grad_norm": 3.137873649597168,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9898,
      "step": 17
    },
    {
      "epoch": 0.16783216783216784,
      "grad_norm": 6.596942901611328,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8707,
      "step": 18
    },
    {
      "epoch": 0.17715617715617715,
      "grad_norm": 3.585325002670288,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5419,
      "step": 19
    },
    {
      "epoch": 0.1864801864801865,
      "grad_norm": 16.28446388244629,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.3614,
      "step": 20
    },
    {
      "epoch": 0.1958041958041958,
      "grad_norm": 14.581011772155762,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.8654,
      "step": 21
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 14.074675559997559,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.4478,
      "step": 22
    },
    {
      "epoch": 0.21445221445221446,
      "grad_norm": 24.37031364440918,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3925,
      "step": 23
    },
    {
      "epoch": 0.22377622377622378,
      "grad_norm": 17.747961044311523,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.1389,
      "step": 24
    },
    {
      "epoch": 0.2331002331002331,
      "grad_norm": 14.189725875854492,
      "learning_rate": 9.847001329696653e-05,
      "loss": 8.717,
      "step": 25
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 11.175613403320312,
      "learning_rate": 9.826044551386744e-05,
      "loss": 7.0109,
      "step": 26
    },
    {
      "epoch": 0.2517482517482518,
      "grad_norm": 11.548452377319336,
      "learning_rate": 9.803768380684242e-05,
      "loss": 5.9307,
      "step": 27
    },
    {
      "epoch": 0.26107226107226106,
      "grad_norm": 5.655531883239746,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.5551,
      "step": 28
    },
    {
      "epoch": 0.2703962703962704,
      "grad_norm": 3.675208330154419,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.91,
      "step": 29
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 3.5003762245178223,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.4675,
      "step": 30
    },
    {
      "epoch": 0.289044289044289,
      "grad_norm": 2.752429723739624,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.3052,
      "step": 31
    },
    {
      "epoch": 0.29836829836829837,
      "grad_norm": 1.6919887065887451,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.0493,
      "step": 32
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.1324936151504517,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.8612,
      "step": 33
    },
    {
      "epoch": 0.317016317016317,
      "grad_norm": 1.2513482570648193,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.9087,
      "step": 34
    },
    {
      "epoch": 0.32634032634032634,
      "grad_norm": 3.8437435626983643,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.0674,
      "step": 35
    },
    {
      "epoch": 0.3356643356643357,
      "grad_norm": 4.014515399932861,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.8748,
      "step": 36
    },
    {
      "epoch": 0.34498834498834496,
      "grad_norm": 3.297264575958252,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.7609,
      "step": 37
    },
    {
      "epoch": 0.3543123543123543,
      "grad_norm": 2.6173219680786133,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2908,
      "step": 38
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.533371925354004,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.239,
      "step": 39
    },
    {
      "epoch": 0.372960372960373,
      "grad_norm": 2.510262966156006,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1313,
      "step": 40
    },
    {
      "epoch": 0.3822843822843823,
      "grad_norm": 2.7417259216308594,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.3819,
      "step": 41
    },
    {
      "epoch": 0.3916083916083916,
      "grad_norm": 3.1663944721221924,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.261,
      "step": 42
    },
    {
      "epoch": 0.40093240093240096,
      "grad_norm": 2.8110852241516113,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0831,
      "step": 43
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 2.5184485912323,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8579,
      "step": 44
    },
    {
      "epoch": 0.4195804195804196,
      "grad_norm": 1.5449906587600708,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6003,
      "step": 45
    },
    {
      "epoch": 0.4289044289044289,
      "grad_norm": 8.891263961791992,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.0681,
      "step": 46
    },
    {
      "epoch": 0.4382284382284382,
      "grad_norm": 10.303458213806152,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.6736,
      "step": 47
    },
    {
      "epoch": 0.44755244755244755,
      "grad_norm": 28.11035919189453,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.3585,
      "step": 48
    },
    {
      "epoch": 0.4568764568764569,
      "grad_norm": 23.559791564941406,
      "learning_rate": 8.995939984474624e-05,
      "loss": 9.0986,
      "step": 49
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 20.81884765625,
      "learning_rate": 8.945702546981969e-05,
      "loss": 8.4983,
      "step": 50
    },
    {
      "epoch": 0.4662004662004662,
      "eval_loss": 3.679175853729248,
      "eval_runtime": 23.8007,
      "eval_samples_per_second": 7.605,
      "eval_steps_per_second": 1.933,
      "step": 50
    },
    {
      "epoch": 0.4755244755244755,
      "grad_norm": 14.169259071350098,
      "learning_rate": 8.894386393810563e-05,
      "loss": 6.7589,
      "step": 51
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 10.79922866821289,
      "learning_rate": 8.842005554284296e-05,
      "loss": 5.839,
      "step": 52
    },
    {
      "epoch": 0.49417249417249415,
      "grad_norm": 7.365059852600098,
      "learning_rate": 8.788574348801675e-05,
      "loss": 5.1844,
      "step": 53
    },
    {
      "epoch": 0.5034965034965035,
      "grad_norm": 5.431877136230469,
      "learning_rate": 8.73410738492077e-05,
      "loss": 4.4004,
      "step": 54
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 4.072169303894043,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.8542,
      "step": 55
    },
    {
      "epoch": 0.5221445221445221,
      "grad_norm": 2.8445355892181396,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.3803,
      "step": 56
    },
    {
      "epoch": 0.5314685314685315,
      "grad_norm": 1.870168924331665,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.1133,
      "step": 57
    },
    {
      "epoch": 0.5407925407925408,
      "grad_norm": 1.7074593305587769,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.9577,
      "step": 58
    },
    {
      "epoch": 0.5501165501165501,
      "grad_norm": 1.2201054096221924,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.8116,
      "step": 59
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.8424943089485168,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.5907,
      "step": 60
    },
    {
      "epoch": 0.5687645687645687,
      "grad_norm": 3.318760871887207,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.1399,
      "step": 61
    },
    {
      "epoch": 0.578088578088578,
      "grad_norm": 2.6667368412017822,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.4138,
      "step": 62
    },
    {
      "epoch": 0.5874125874125874,
      "grad_norm": 2.4689431190490723,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3283,
      "step": 63
    },
    {
      "epoch": 0.5967365967365967,
      "grad_norm": 2.8287274837493896,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.4397,
      "step": 64
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.5585992336273193,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1102,
      "step": 65
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.7219605445861816,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9008,
      "step": 66
    },
    {
      "epoch": 0.6247086247086248,
      "grad_norm": 3.725984811782837,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.419,
      "step": 67
    },
    {
      "epoch": 0.634032634032634,
      "grad_norm": 4.503452301025391,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.3957,
      "step": 68
    },
    {
      "epoch": 0.6433566433566433,
      "grad_norm": 4.065217971801758,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.3913,
      "step": 69
    },
    {
      "epoch": 0.6526806526806527,
      "grad_norm": 2.7257111072540283,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.939,
      "step": 70
    },
    {
      "epoch": 0.662004662004662,
      "grad_norm": 2.493581771850586,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7629,
      "step": 71
    },
    {
      "epoch": 0.6713286713286714,
      "grad_norm": 1.505328893661499,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5906,
      "step": 72
    },
    {
      "epoch": 0.6806526806526807,
      "grad_norm": 3.5360922813415527,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.0241,
      "step": 73
    },
    {
      "epoch": 0.6899766899766899,
      "grad_norm": 7.737525463104248,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.312,
      "step": 74
    },
    {
      "epoch": 0.6993006993006993,
      "grad_norm": 8.461692810058594,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.996,
      "step": 75
    },
    {
      "epoch": 0.7086247086247086,
      "grad_norm": 2.365105390548706,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.6277,
      "step": 76
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 1.4679630994796753,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.7152,
      "step": 77
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.3809874057769775,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.7745,
      "step": 78
    },
    {
      "epoch": 0.7365967365967366,
      "grad_norm": 0.6759855151176453,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.604,
      "step": 79
    },
    {
      "epoch": 0.745920745920746,
      "grad_norm": 0.44534364342689514,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.6232,
      "step": 80
    },
    {
      "epoch": 0.7552447552447552,
      "grad_norm": 0.33566996455192566,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.5459,
      "step": 81
    },
    {
      "epoch": 0.7645687645687645,
      "grad_norm": 0.2763979434967041,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.5477,
      "step": 82
    },
    {
      "epoch": 0.7738927738927739,
      "grad_norm": 0.26413217186927795,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.5415,
      "step": 83
    },
    {
      "epoch": 0.7832167832167832,
      "grad_norm": 0.2807287871837616,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.5198,
      "step": 84
    },
    {
      "epoch": 0.7925407925407926,
      "grad_norm": 0.29398876428604126,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.4776,
      "step": 85
    },
    {
      "epoch": 0.8018648018648019,
      "grad_norm": 8.44844913482666,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9432,
      "step": 86
    },
    {
      "epoch": 0.8111888111888111,
      "grad_norm": 6.937229633331299,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.4197,
      "step": 87
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 6.435008525848389,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.1675,
      "step": 88
    },
    {
      "epoch": 0.8298368298368298,
      "grad_norm": 4.50892972946167,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.648,
      "step": 89
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 2.8915388584136963,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.328,
      "step": 90
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 3.5234341621398926,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1271,
      "step": 91
    },
    {
      "epoch": 0.8578088578088578,
      "grad_norm": 3.8853113651275635,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0174,
      "step": 92
    },
    {
      "epoch": 0.8671328671328671,
      "grad_norm": 6.351526260375977,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9312,
      "step": 93
    },
    {
      "epoch": 0.8764568764568764,
      "grad_norm": 7.617507457733154,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.92,
      "step": 94
    },
    {
      "epoch": 0.8857808857808858,
      "grad_norm": 5.657171726226807,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.725,
      "step": 95
    },
    {
      "epoch": 0.8951048951048951,
      "grad_norm": 4.201667308807373,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5595,
      "step": 96
    },
    {
      "epoch": 0.9044289044289044,
      "grad_norm": 4.911362648010254,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5435,
      "step": 97
    },
    {
      "epoch": 0.9137529137529138,
      "grad_norm": 10.220386505126953,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.326,
      "step": 98
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 15.135976791381836,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.9811,
      "step": 99
    },
    {
      "epoch": 0.9324009324009324,
      "grad_norm": 23.320337295532227,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.0347,
      "step": 100
    },
    {
      "epoch": 0.9324009324009324,
      "eval_loss": 1.5415750741958618,
      "eval_runtime": 24.0659,
      "eval_samples_per_second": 7.521,
      "eval_steps_per_second": 1.911,
      "step": 100
    },
    {
      "epoch": 0.9417249417249417,
      "grad_norm": 0.7756141424179077,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.5391,
      "step": 101
    },
    {
      "epoch": 0.951048951048951,
      "grad_norm": 0.39648714661598206,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.529,
      "step": 102
    },
    {
      "epoch": 0.9603729603729604,
      "grad_norm": 0.3116510212421417,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.5183,
      "step": 103
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.5462058186531067,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.3001,
      "step": 104
    },
    {
      "epoch": 0.9790209790209791,
      "grad_norm": 0.2573853135108948,
      "learning_rate": 5e-05,
      "loss": 2.4165,
      "step": 105
    },
    {
      "epoch": 0.9883449883449883,
      "grad_norm": 2.5073468685150146,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7608,
      "step": 106
    },
    {
      "epoch": 0.9976689976689976,
      "grad_norm": 2.181105375289917,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.6846,
      "step": 107
    },
    {
      "epoch": 1.006993006993007,
      "grad_norm": 2.314100742340088,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.3176,
      "step": 108
    },
    {
      "epoch": 1.0163170163170163,
      "grad_norm": 0.20674610137939453,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.4221,
      "step": 109
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.23333650827407837,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.443,
      "step": 110
    },
    {
      "epoch": 1.034965034965035,
      "grad_norm": 0.19740326702594757,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.4656,
      "step": 111
    },
    {
      "epoch": 1.0442890442890442,
      "grad_norm": 0.19940629601478577,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.4696,
      "step": 112
    },
    {
      "epoch": 1.0536130536130537,
      "grad_norm": 0.18616272509098053,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.4765,
      "step": 113
    },
    {
      "epoch": 1.062937062937063,
      "grad_norm": 0.28805771470069885,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.9951,
      "step": 114
    },
    {
      "epoch": 1.0722610722610724,
      "grad_norm": 2.9031519889831543,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6892,
      "step": 115
    },
    {
      "epoch": 1.0815850815850816,
      "grad_norm": 3.404639720916748,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7612,
      "step": 116
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 2.939525842666626,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7471,
      "step": 117
    },
    {
      "epoch": 1.1002331002331003,
      "grad_norm": 2.4093847274780273,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6132,
      "step": 118
    },
    {
      "epoch": 1.1095571095571095,
      "grad_norm": 1.7852245569229126,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.52,
      "step": 119
    },
    {
      "epoch": 1.118881118881119,
      "grad_norm": 1.481847882270813,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4409,
      "step": 120
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 3.0913021564483643,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7696,
      "step": 121
    },
    {
      "epoch": 1.1375291375291376,
      "grad_norm": 4.304544925689697,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.9574,
      "step": 122
    },
    {
      "epoch": 1.1468531468531469,
      "grad_norm": 4.037679195404053,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.0098,
      "step": 123
    },
    {
      "epoch": 1.156177156177156,
      "grad_norm": 3.653125286102295,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9481,
      "step": 124
    },
    {
      "epoch": 1.1655011655011656,
      "grad_norm": 2.9725422859191895,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.8054,
      "step": 125
    },
    {
      "epoch": 1.1748251748251748,
      "grad_norm": 2.4829540252685547,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7603,
      "step": 126
    },
    {
      "epoch": 1.1841491841491842,
      "grad_norm": 3.3553013801574707,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.0013,
      "step": 127
    },
    {
      "epoch": 1.1934731934731935,
      "grad_norm": 4.9270339012146,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.229,
      "step": 128
    },
    {
      "epoch": 1.2027972027972027,
      "grad_norm": 3.9740164279937744,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.3492,
      "step": 129
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 5.056183338165283,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2088,
      "step": 130
    },
    {
      "epoch": 1.2214452214452214,
      "grad_norm": 1.3563992977142334,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.2151,
      "step": 131
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.32926884293556213,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.3034,
      "step": 132
    },
    {
      "epoch": 1.24009324009324,
      "grad_norm": 0.465352326631546,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.5416,
      "step": 133
    },
    {
      "epoch": 1.2494172494172493,
      "grad_norm": 0.24992136657238007,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.1603,
      "step": 134
    },
    {
      "epoch": 1.2587412587412588,
      "grad_norm": 0.1780441850423813,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.3744,
      "step": 135
    },
    {
      "epoch": 1.2680652680652682,
      "grad_norm": 0.1778908669948578,
      "learning_rate": 2.547882480847461e-05,
      "loss": 2.4787,
      "step": 136
    },
    {
      "epoch": 1.2773892773892774,
      "grad_norm": 0.17417168617248535,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.318,
      "step": 137
    },
    {
      "epoch": 1.2867132867132867,
      "grad_norm": 0.1559688001871109,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.4448,
      "step": 138
    },
    {
      "epoch": 1.2960372960372961,
      "grad_norm": 0.19666261970996857,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.4507,
      "step": 139
    },
    {
      "epoch": 1.3053613053613053,
      "grad_norm": 0.19044345617294312,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.4791,
      "step": 140
    },
    {
      "epoch": 1.3146853146853146,
      "grad_norm": 0.4497004747390747,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.5452,
      "step": 141
    },
    {
      "epoch": 1.324009324009324,
      "grad_norm": 1.9758671522140503,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5469,
      "step": 142
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 2.2137508392333984,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6532,
      "step": 143
    },
    {
      "epoch": 1.3426573426573427,
      "grad_norm": 2.20041823387146,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.7457,
      "step": 144
    },
    {
      "epoch": 1.351981351981352,
      "grad_norm": 1.956243872642517,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6918,
      "step": 145
    },
    {
      "epoch": 1.3613053613053614,
      "grad_norm": 1.8825136423110962,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7284,
      "step": 146
    },
    {
      "epoch": 1.3706293706293706,
      "grad_norm": 1.8443814516067505,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6243,
      "step": 147
    },
    {
      "epoch": 1.3799533799533799,
      "grad_norm": 0.9278972148895264,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5002,
      "step": 148
    },
    {
      "epoch": 1.3892773892773893,
      "grad_norm": 1.3522188663482666,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5504,
      "step": 149
    },
    {
      "epoch": 1.3986013986013985,
      "grad_norm": 1.3058701753616333,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5784,
      "step": 150
    },
    {
      "epoch": 1.3986013986013985,
      "eval_loss": 1.380373239517212,
      "eval_runtime": 23.8392,
      "eval_samples_per_second": 7.593,
      "eval_steps_per_second": 1.93,
      "step": 150
    },
    {
      "epoch": 1.407925407925408,
      "grad_norm": 1.6771668195724487,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5514,
      "step": 151
    },
    {
      "epoch": 1.4172494172494172,
      "grad_norm": 1.3433727025985718,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.5601,
      "step": 152
    },
    {
      "epoch": 1.4265734265734267,
      "grad_norm": 1.3194711208343506,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.6221,
      "step": 153
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 4.940863132476807,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.4071,
      "step": 154
    },
    {
      "epoch": 1.4452214452214451,
      "grad_norm": 3.8188374042510986,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.074,
      "step": 155
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.7156231999397278,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1568,
      "step": 156
    },
    {
      "epoch": 1.4638694638694638,
      "grad_norm": 0.6744435429573059,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.2694,
      "step": 157
    },
    {
      "epoch": 1.4731934731934733,
      "grad_norm": 0.4265668988227844,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.7918,
      "step": 158
    },
    {
      "epoch": 1.4825174825174825,
      "grad_norm": 0.5339131355285645,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.0344,
      "step": 159
    },
    {
      "epoch": 1.491841491841492,
      "grad_norm": 0.19210335612297058,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.1183,
      "step": 160
    },
    {
      "epoch": 1.5011655011655012,
      "grad_norm": 0.16120505332946777,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 2.2688,
      "step": 161
    },
    {
      "epoch": 1.5104895104895104,
      "grad_norm": 0.15891562402248383,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.5504,
      "step": 162
    },
    {
      "epoch": 1.5198135198135199,
      "grad_norm": 0.16509626805782318,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.2899,
      "step": 163
    },
    {
      "epoch": 1.529137529137529,
      "grad_norm": 0.1635676622390747,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.5342,
      "step": 164
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.17039430141448975,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.37,
      "step": 165
    },
    {
      "epoch": 1.5477855477855478,
      "grad_norm": 0.15272369980812073,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.4179,
      "step": 166
    },
    {
      "epoch": 1.5571095571095572,
      "grad_norm": 0.22614268958568573,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.9081,
      "step": 167
    },
    {
      "epoch": 1.5664335664335665,
      "grad_norm": 2.136772632598877,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.444,
      "step": 168
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 1.702525019645691,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5884,
      "step": 169
    },
    {
      "epoch": 1.5850815850815851,
      "grad_norm": 1.8669508695602417,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6079,
      "step": 170
    },
    {
      "epoch": 1.5944055944055944,
      "grad_norm": 1.7652667760849,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6054,
      "step": 171
    },
    {
      "epoch": 1.6037296037296036,
      "grad_norm": 1.7122447490692139,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5896,
      "step": 172
    },
    {
      "epoch": 1.613053613053613,
      "grad_norm": 1.0438684225082397,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.5495,
      "step": 173
    },
    {
      "epoch": 1.6223776223776225,
      "grad_norm": 1.013310432434082,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4282,
      "step": 174
    },
    {
      "epoch": 1.6317016317016317,
      "grad_norm": 0.982435941696167,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5052,
      "step": 175
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.9753938317298889,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4844,
      "step": 176
    },
    {
      "epoch": 1.6503496503496504,
      "grad_norm": 1.2100294828414917,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.5041,
      "step": 177
    },
    {
      "epoch": 1.6596736596736597,
      "grad_norm": 1.1595643758773804,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4877,
      "step": 178
    },
    {
      "epoch": 1.6689976689976689,
      "grad_norm": 1.2613807916641235,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.584,
      "step": 179
    },
    {
      "epoch": 1.6783216783216783,
      "grad_norm": 5.210282325744629,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.2929,
      "step": 180
    },
    {
      "epoch": 1.6876456876456878,
      "grad_norm": 5.074240684509277,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2233,
      "step": 181
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 1.3932987451553345,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.4976,
      "step": 182
    },
    {
      "epoch": 1.7062937062937062,
      "grad_norm": 1.4931566715240479,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.0926,
      "step": 183
    },
    {
      "epoch": 1.7156177156177157,
      "grad_norm": 0.33435967564582825,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.6921,
      "step": 184
    },
    {
      "epoch": 1.724941724941725,
      "grad_norm": 0.47099363803863525,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.2493,
      "step": 185
    },
    {
      "epoch": 1.7342657342657342,
      "grad_norm": 0.16402220726013184,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.8686,
      "step": 186
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.16763973236083984,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.453,
      "step": 187
    },
    {
      "epoch": 1.752913752913753,
      "grad_norm": 0.15244829654693604,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.4183,
      "step": 188
    },
    {
      "epoch": 1.762237762237762,
      "grad_norm": 0.16161195933818817,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.3768,
      "step": 189
    },
    {
      "epoch": 1.7715617715617715,
      "grad_norm": 0.15747272968292236,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.5085,
      "step": 190
    },
    {
      "epoch": 1.780885780885781,
      "grad_norm": 0.1563844531774521,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.3737,
      "step": 191
    },
    {
      "epoch": 1.7902097902097902,
      "grad_norm": 0.16912737488746643,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.5687,
      "step": 192
    },
    {
      "epoch": 1.7995337995337994,
      "grad_norm": 1.899337887763977,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8727,
      "step": 193
    },
    {
      "epoch": 1.808857808857809,
      "grad_norm": 1.6409616470336914,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5639,
      "step": 194
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.640459656715393,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.564,
      "step": 195
    },
    {
      "epoch": 1.8275058275058274,
      "grad_norm": 1.6778132915496826,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5442,
      "step": 196
    },
    {
      "epoch": 1.8368298368298368,
      "grad_norm": 1.605709433555603,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.556,
      "step": 197
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.6580415964126587,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5516,
      "step": 198
    },
    {
      "epoch": 1.8554778554778555,
      "grad_norm": 1.6640994548797607,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5591,
      "step": 199
    },
    {
      "epoch": 1.8648018648018647,
      "grad_norm": 0.7570514678955078,
      "learning_rate": 0.0,
      "loss": 0.5456,
      "step": 200
    },
    {
      "epoch": 1.8648018648018647,
      "eval_loss": 1.3400603532791138,
      "eval_runtime": 24.131,
      "eval_samples_per_second": 7.501,
      "eval_steps_per_second": 1.906,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.044657884097413e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}