{
  "best_metric": 0.05454511195421219,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.2656924609764198,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001328462304882099,
      "grad_norm": 1.3991806507110596,
      "learning_rate": 1e-05,
      "loss": 1.2451,
      "step": 1
    },
    {
      "epoch": 0.001328462304882099,
      "eval_loss": 0.9099801778793335,
      "eval_runtime": 42.0554,
      "eval_samples_per_second": 30.151,
      "eval_steps_per_second": 7.538,
      "step": 1
    },
    {
      "epoch": 0.002656924609764198,
      "grad_norm": 1.197432041168213,
      "learning_rate": 2e-05,
      "loss": 0.5518,
      "step": 2
    },
    {
      "epoch": 0.003985386914646297,
      "grad_norm": 1.144295334815979,
      "learning_rate": 3e-05,
      "loss": 0.8168,
      "step": 3
    },
    {
      "epoch": 0.005313849219528396,
      "grad_norm": 1.1892198324203491,
      "learning_rate": 4e-05,
      "loss": 0.9958,
      "step": 4
    },
    {
      "epoch": 0.006642311524410495,
      "grad_norm": 1.2396732568740845,
      "learning_rate": 5e-05,
      "loss": 0.6305,
      "step": 5
    },
    {
      "epoch": 0.007970773829292593,
      "grad_norm": 1.2879739999771118,
      "learning_rate": 6e-05,
      "loss": 0.5989,
      "step": 6
    },
    {
      "epoch": 0.009299236134174693,
      "grad_norm": 1.630868673324585,
      "learning_rate": 7e-05,
      "loss": 0.6053,
      "step": 7
    },
    {
      "epoch": 0.010627698439056792,
      "grad_norm": 1.6003340482711792,
      "learning_rate": 8e-05,
      "loss": 0.4353,
      "step": 8
    },
    {
      "epoch": 0.01195616074393889,
      "grad_norm": 2.563776969909668,
      "learning_rate": 9e-05,
      "loss": 0.2927,
      "step": 9
    },
    {
      "epoch": 0.01328462304882099,
      "grad_norm": 1.628896951675415,
      "learning_rate": 0.0001,
      "loss": 0.3386,
      "step": 10
    },
    {
      "epoch": 0.014613085353703089,
      "grad_norm": 1.5699366331100464,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.3045,
      "step": 11
    },
    {
      "epoch": 0.015941547658585187,
      "grad_norm": 1.328123688697815,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2609,
      "step": 12
    },
    {
      "epoch": 0.017270009963467288,
      "grad_norm": 1.599324107170105,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.1865,
      "step": 13
    },
    {
      "epoch": 0.018598472268349386,
      "grad_norm": 1.4006145000457764,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.1577,
      "step": 14
    },
    {
      "epoch": 0.019926934573231483,
      "grad_norm": 1.027660608291626,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.1287,
      "step": 15
    },
    {
      "epoch": 0.021255396878113585,
      "grad_norm": 1.1444554328918457,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1756,
      "step": 16
    },
    {
      "epoch": 0.022583859182995682,
      "grad_norm": 0.8250659108161926,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.1705,
      "step": 17
    },
    {
      "epoch": 0.02391232148787778,
      "grad_norm": 1.2994184494018555,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1767,
      "step": 18
    },
    {
      "epoch": 0.02524078379275988,
      "grad_norm": 0.9651134014129639,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.1161,
      "step": 19
    },
    {
      "epoch": 0.02656924609764198,
      "grad_norm": 1.0957099199295044,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1397,
      "step": 20
    },
    {
      "epoch": 0.027897708402524077,
      "grad_norm": 0.8373222351074219,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.108,
      "step": 21
    },
    {
      "epoch": 0.029226170707406178,
      "grad_norm": 1.938508152961731,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.16,
      "step": 22
    },
    {
      "epoch": 0.030554633012288276,
      "grad_norm": 1.1585845947265625,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.1239,
      "step": 23
    },
    {
      "epoch": 0.031883095317170373,
      "grad_norm": 0.9152848124504089,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0872,
      "step": 24
    },
    {
      "epoch": 0.033211557622052475,
      "grad_norm": 0.716942548751831,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0809,
      "step": 25
    },
    {
      "epoch": 0.034540019926934576,
      "grad_norm": 0.9917988777160645,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.1373,
      "step": 26
    },
    {
      "epoch": 0.03586848223181667,
      "grad_norm": 0.9087157845497131,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.1231,
      "step": 27
    },
    {
      "epoch": 0.03719694453669877,
      "grad_norm": 0.4621882140636444,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0762,
      "step": 28
    },
    {
      "epoch": 0.03852540684158087,
      "grad_norm": 1.1974875926971436,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.099,
      "step": 29
    },
    {
      "epoch": 0.03985386914646297,
      "grad_norm": 0.6985036730766296,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0772,
      "step": 30
    },
    {
      "epoch": 0.04118233145134507,
      "grad_norm": 0.6680667400360107,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.082,
      "step": 31
    },
    {
      "epoch": 0.04251079375622717,
      "grad_norm": 0.6564874649047852,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0691,
      "step": 32
    },
    {
      "epoch": 0.043839256061109264,
      "grad_norm": 0.5068350434303284,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0566,
      "step": 33
    },
    {
      "epoch": 0.045167718365991365,
      "grad_norm": 0.5241013765335083,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.051,
      "step": 34
    },
    {
      "epoch": 0.046496180670873466,
      "grad_norm": 1.0206941366195679,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.1009,
      "step": 35
    },
    {
      "epoch": 0.04782464297575556,
      "grad_norm": 0.936644434928894,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0895,
      "step": 36
    },
    {
      "epoch": 0.04915310528063766,
      "grad_norm": 1.2153074741363525,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0833,
      "step": 37
    },
    {
      "epoch": 0.05048156758551976,
      "grad_norm": 1.9132487773895264,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.1536,
      "step": 38
    },
    {
      "epoch": 0.05181002989040186,
      "grad_norm": 1.4385014772415161,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.1551,
      "step": 39
    },
    {
      "epoch": 0.05313849219528396,
      "grad_norm": 1.128587245941162,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1262,
      "step": 40
    },
    {
      "epoch": 0.05446695450016606,
      "grad_norm": 0.6382101774215698,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0608,
      "step": 41
    },
    {
      "epoch": 0.055795416805048154,
      "grad_norm": 0.5120552182197571,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0495,
      "step": 42
    },
    {
      "epoch": 0.057123879109930255,
      "grad_norm": 0.6968569755554199,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0713,
      "step": 43
    },
    {
      "epoch": 0.058452341414812356,
      "grad_norm": 0.5472718477249146,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0618,
      "step": 44
    },
    {
      "epoch": 0.05978080371969445,
      "grad_norm": 1.030089020729065,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1089,
      "step": 45
    },
    {
      "epoch": 0.06110926602457655,
      "grad_norm": 1.0972938537597656,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1525,
      "step": 46
    },
    {
      "epoch": 0.06243772832945865,
      "grad_norm": 0.699333906173706,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0547,
      "step": 47
    },
    {
      "epoch": 0.06376619063434075,
      "grad_norm": 1.0085898637771606,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0849,
      "step": 48
    },
    {
      "epoch": 0.06509465293922286,
      "grad_norm": 1.6594712734222412,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.1065,
      "step": 49
    },
    {
      "epoch": 0.06642311524410495,
      "grad_norm": 2.0280661582946777,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.1971,
      "step": 50
    },
    {
      "epoch": 0.06642311524410495,
      "eval_loss": 0.11900235712528229,
      "eval_runtime": 42.6792,
      "eval_samples_per_second": 29.71,
      "eval_steps_per_second": 7.428,
      "step": 50
    },
    {
      "epoch": 0.06775157754898704,
      "grad_norm": 1.0781126022338867,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.703,
      "step": 51
    },
    {
      "epoch": 0.06908003985386915,
      "grad_norm": 0.5772373676300049,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.1285,
      "step": 52
    },
    {
      "epoch": 0.07040850215875125,
      "grad_norm": 0.6747174859046936,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5229,
      "step": 53
    },
    {
      "epoch": 0.07173696446363334,
      "grad_norm": 0.535176157951355,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4737,
      "step": 54
    },
    {
      "epoch": 0.07306542676851545,
      "grad_norm": 0.7472483515739441,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1224,
      "step": 55
    },
    {
      "epoch": 0.07439388907339754,
      "grad_norm": 0.6163215637207031,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.103,
      "step": 56
    },
    {
      "epoch": 0.07572235137827964,
      "grad_norm": 0.42457133531570435,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.1453,
      "step": 57
    },
    {
      "epoch": 0.07705081368316175,
      "grad_norm": 0.5095568895339966,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1568,
      "step": 58
    },
    {
      "epoch": 0.07837927598804384,
      "grad_norm": 0.7824573516845703,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0956,
      "step": 59
    },
    {
      "epoch": 0.07970773829292593,
      "grad_norm": 0.36281490325927734,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0558,
      "step": 60
    },
    {
      "epoch": 0.08103620059780804,
      "grad_norm": 0.4386594593524933,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0521,
      "step": 61
    },
    {
      "epoch": 0.08236466290269014,
      "grad_norm": 0.5395628213882446,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1142,
      "step": 62
    },
    {
      "epoch": 0.08369312520757223,
      "grad_norm": 0.48043733835220337,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.1323,
      "step": 63
    },
    {
      "epoch": 0.08502158751245434,
      "grad_norm": 0.6430375576019287,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0717,
      "step": 64
    },
    {
      "epoch": 0.08635004981733643,
      "grad_norm": 0.4558599591255188,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0496,
      "step": 65
    },
    {
      "epoch": 0.08767851212221853,
      "grad_norm": 0.49606719613075256,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0422,
      "step": 66
    },
    {
      "epoch": 0.08900697442710064,
      "grad_norm": 0.2688433527946472,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0482,
      "step": 67
    },
    {
      "epoch": 0.09033543673198273,
      "grad_norm": 0.3562898337841034,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0986,
      "step": 68
    },
    {
      "epoch": 0.09166389903686482,
      "grad_norm": 0.31984731554985046,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0541,
      "step": 69
    },
    {
      "epoch": 0.09299236134174693,
      "grad_norm": 0.46406444907188416,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0495,
      "step": 70
    },
    {
      "epoch": 0.09432082364662903,
      "grad_norm": 0.4022379219532013,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0517,
      "step": 71
    },
    {
      "epoch": 0.09564928595151112,
      "grad_norm": 0.5326384902000427,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0338,
      "step": 72
    },
    {
      "epoch": 0.09697774825639323,
      "grad_norm": 0.5483595728874207,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0465,
      "step": 73
    },
    {
      "epoch": 0.09830621056127532,
      "grad_norm": 0.4839358627796173,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0488,
      "step": 74
    },
    {
      "epoch": 0.09963467286615742,
      "grad_norm": 0.39490216970443726,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0368,
      "step": 75
    },
    {
      "epoch": 0.10096313517103953,
      "grad_norm": 0.3183744251728058,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0427,
      "step": 76
    },
    {
      "epoch": 0.10229159747592162,
      "grad_norm": 0.3132561147212982,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0519,
      "step": 77
    },
    {
      "epoch": 0.10362005978080371,
      "grad_norm": 0.5553680062294006,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0499,
      "step": 78
    },
    {
      "epoch": 0.10494852208568582,
      "grad_norm": 0.4570114016532898,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0475,
      "step": 79
    },
    {
      "epoch": 0.10627698439056792,
      "grad_norm": 0.46708357334136963,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0382,
      "step": 80
    },
    {
      "epoch": 0.10760544669545001,
      "grad_norm": 0.4337405264377594,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0348,
      "step": 81
    },
    {
      "epoch": 0.10893390900033212,
      "grad_norm": 0.32262760400772095,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0325,
      "step": 82
    },
    {
      "epoch": 0.11026237130521421,
      "grad_norm": 0.33860889077186584,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0339,
      "step": 83
    },
    {
      "epoch": 0.11159083361009631,
      "grad_norm": 0.5378628969192505,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0346,
      "step": 84
    },
    {
      "epoch": 0.11291929591497842,
      "grad_norm": 0.444441556930542,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0254,
      "step": 85
    },
    {
      "epoch": 0.11424775821986051,
      "grad_norm": 0.45231154561042786,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0407,
      "step": 86
    },
    {
      "epoch": 0.1155762205247426,
      "grad_norm": 0.8925038576126099,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0585,
      "step": 87
    },
    {
      "epoch": 0.11690468282962471,
      "grad_norm": 0.4468405842781067,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0374,
      "step": 88
    },
    {
      "epoch": 0.1182331451345068,
      "grad_norm": 0.7678568363189697,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0535,
      "step": 89
    },
    {
      "epoch": 0.1195616074393889,
      "grad_norm": 0.6535559296607971,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0443,
      "step": 90
    },
    {
      "epoch": 0.12089006974427101,
      "grad_norm": 0.474445104598999,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0423,
      "step": 91
    },
    {
      "epoch": 0.1222185320491531,
      "grad_norm": 0.24763274192810059,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0224,
      "step": 92
    },
    {
      "epoch": 0.12354699435403521,
      "grad_norm": 0.26658034324645996,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0138,
      "step": 93
    },
    {
      "epoch": 0.1248754566589173,
      "grad_norm": 0.497882217168808,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0155,
      "step": 94
    },
    {
      "epoch": 0.1262039189637994,
      "grad_norm": 0.6259251236915588,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0436,
      "step": 95
    },
    {
      "epoch": 0.1275323812686815,
      "grad_norm": 0.5058514475822449,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0614,
      "step": 96
    },
    {
      "epoch": 0.1288608435735636,
      "grad_norm": 0.4634997546672821,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0353,
      "step": 97
    },
    {
      "epoch": 0.1301893058784457,
      "grad_norm": 0.8413709402084351,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0231,
      "step": 98
    },
    {
      "epoch": 0.1315177681833278,
      "grad_norm": 1.695737361907959,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0651,
      "step": 99
    },
    {
      "epoch": 0.1328462304882099,
      "grad_norm": 0.9100179672241211,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0864,
      "step": 100
    },
    {
      "epoch": 0.1328462304882099,
      "eval_loss": 0.08105120807886124,
      "eval_runtime": 42.6574,
      "eval_samples_per_second": 29.725,
      "eval_steps_per_second": 7.431,
      "step": 100
    },
    {
      "epoch": 0.134174692793092,
      "grad_norm": 1.1371718645095825,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7466,
      "step": 101
    },
    {
      "epoch": 0.1355031550979741,
      "grad_norm": 1.5924078226089478,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.1355,
      "step": 102
    },
    {
      "epoch": 0.13683161740285618,
      "grad_norm": 0.583022952079773,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4989,
      "step": 103
    },
    {
      "epoch": 0.1381600797077383,
      "grad_norm": 0.39132171869277954,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3831,
      "step": 104
    },
    {
      "epoch": 0.1394885420126204,
      "grad_norm": 0.45017603039741516,
      "learning_rate": 5e-05,
      "loss": 0.0665,
      "step": 105
    },
    {
      "epoch": 0.1408170043175025,
      "grad_norm": 0.41307318210601807,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0953,
      "step": 106
    },
    {
      "epoch": 0.1421454666223846,
      "grad_norm": 0.5252862572669983,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.1099,
      "step": 107
    },
    {
      "epoch": 0.14347392892726668,
      "grad_norm": 0.5178684592247009,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0542,
      "step": 108
    },
    {
      "epoch": 0.14480239123214877,
      "grad_norm": 0.22396919131278992,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0258,
      "step": 109
    },
    {
      "epoch": 0.1461308535370309,
      "grad_norm": 0.2528194487094879,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0321,
      "step": 110
    },
    {
      "epoch": 0.147459315841913,
      "grad_norm": 0.3601865768432617,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0454,
      "step": 111
    },
    {
      "epoch": 0.14878777814679509,
      "grad_norm": 0.347805380821228,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0772,
      "step": 112
    },
    {
      "epoch": 0.15011624045167718,
      "grad_norm": 0.40513965487480164,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0485,
      "step": 113
    },
    {
      "epoch": 0.15144470275655927,
      "grad_norm": 0.333831787109375,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0254,
      "step": 114
    },
    {
      "epoch": 0.15277316506144137,
      "grad_norm": 0.20879682898521423,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0191,
      "step": 115
    },
    {
      "epoch": 0.1541016273663235,
      "grad_norm": 0.16467632353305817,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0205,
      "step": 116
    },
    {
      "epoch": 0.15543008967120558,
      "grad_norm": 0.2767382264137268,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0979,
      "step": 117
    },
    {
      "epoch": 0.15675855197608768,
      "grad_norm": 0.22532938420772552,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0377,
      "step": 118
    },
    {
      "epoch": 0.15808701428096977,
      "grad_norm": 0.31513097882270813,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0286,
      "step": 119
    },
    {
      "epoch": 0.15941547658585187,
      "grad_norm": 0.3159446120262146,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0349,
      "step": 120
    },
    {
      "epoch": 0.16074393889073396,
      "grad_norm": 0.23927819728851318,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0207,
      "step": 121
    },
    {
      "epoch": 0.16207240119561608,
      "grad_norm": 0.6338226199150085,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0377,
      "step": 122
    },
    {
      "epoch": 0.16340086350049818,
      "grad_norm": 0.19847874343395233,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0232,
      "step": 123
    },
    {
      "epoch": 0.16472932580538027,
      "grad_norm": 0.14756368100643158,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0238,
      "step": 124
    },
    {
      "epoch": 0.16605778811026237,
      "grad_norm": 0.20325902104377747,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0321,
      "step": 125
    },
    {
      "epoch": 0.16738625041514446,
      "grad_norm": 0.2516387701034546,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0397,
      "step": 126
    },
    {
      "epoch": 0.16871471272002658,
      "grad_norm": 0.2062210738658905,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0303,
      "step": 127
    },
    {
      "epoch": 0.17004317502490868,
      "grad_norm": 0.16277751326560974,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0288,
      "step": 128
    },
    {
      "epoch": 0.17137163732979077,
      "grad_norm": 0.14115796983242035,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0154,
      "step": 129
    },
    {
      "epoch": 0.17270009963467287,
      "grad_norm": 0.13580194115638733,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.019,
      "step": 130
    },
    {
      "epoch": 0.17402856193955496,
      "grad_norm": 0.2283146232366562,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0197,
      "step": 131
    },
    {
      "epoch": 0.17535702424443705,
      "grad_norm": 0.269546777009964,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0246,
      "step": 132
    },
    {
      "epoch": 0.17668548654931918,
      "grad_norm": 0.20228517055511475,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0233,
      "step": 133
    },
    {
      "epoch": 0.17801394885420127,
      "grad_norm": 0.33714768290519714,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0234,
      "step": 134
    },
    {
      "epoch": 0.17934241115908336,
      "grad_norm": 0.26348862051963806,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0262,
      "step": 135
    },
    {
      "epoch": 0.18067087346396546,
      "grad_norm": 0.3661670684814453,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0277,
      "step": 136
    },
    {
      "epoch": 0.18199933576884755,
      "grad_norm": 0.39337673783302307,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.038,
      "step": 137
    },
    {
      "epoch": 0.18332779807372965,
      "grad_norm": 0.34191054105758667,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.027,
      "step": 138
    },
    {
      "epoch": 0.18465626037861177,
      "grad_norm": 0.48681437969207764,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0295,
      "step": 139
    },
    {
      "epoch": 0.18598472268349386,
      "grad_norm": 0.36476197838783264,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.023,
      "step": 140
    },
    {
      "epoch": 0.18731318498837596,
      "grad_norm": 0.2999372184276581,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0243,
      "step": 141
    },
    {
      "epoch": 0.18864164729325805,
      "grad_norm": 0.09500729292631149,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0103,
      "step": 142
    },
    {
      "epoch": 0.18997010959814015,
      "grad_norm": 0.10636153072118759,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.007,
      "step": 143
    },
    {
      "epoch": 0.19129857190302224,
      "grad_norm": 0.10174880176782608,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0048,
      "step": 144
    },
    {
      "epoch": 0.19262703420790436,
      "grad_norm": 0.2297191023826599,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0121,
      "step": 145
    },
    {
      "epoch": 0.19395549651278646,
      "grad_norm": 0.33161962032318115,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0222,
      "step": 146
    },
    {
      "epoch": 0.19528395881766855,
      "grad_norm": 0.33965668082237244,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0171,
      "step": 147
    },
    {
      "epoch": 0.19661242112255065,
      "grad_norm": 0.22097115218639374,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0189,
      "step": 148
    },
    {
      "epoch": 0.19794088342743274,
      "grad_norm": 0.40826693177223206,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0259,
      "step": 149
    },
    {
      "epoch": 0.19926934573231483,
      "grad_norm": 0.8257744312286377,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0501,
      "step": 150
    },
    {
      "epoch": 0.19926934573231483,
      "eval_loss": 0.06432381272315979,
      "eval_runtime": 42.6024,
      "eval_samples_per_second": 29.764,
      "eval_steps_per_second": 7.441,
      "step": 150
    },
    {
      "epoch": 0.20059780803719696,
      "grad_norm": 1.0977755784988403,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.6293,
      "step": 151
    },
    {
      "epoch": 0.20192627034207905,
      "grad_norm": 4.156855583190918,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1889,
      "step": 152
    },
    {
      "epoch": 0.20325473264696114,
      "grad_norm": 1.3626656532287598,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.4359,
      "step": 153
    },
    {
      "epoch": 0.20458319495184324,
      "grad_norm": 0.7843526601791382,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4311,
      "step": 154
    },
    {
      "epoch": 0.20591165725672533,
      "grad_norm": 0.35689395666122437,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0538,
      "step": 155
    },
    {
      "epoch": 0.20724011956160743,
      "grad_norm": 0.23235024511814117,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.051,
      "step": 156
    },
    {
      "epoch": 0.20856858186648955,
      "grad_norm": 0.277398943901062,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.08,
      "step": 157
    },
    {
      "epoch": 0.20989704417137164,
      "grad_norm": 0.17385900020599365,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0541,
      "step": 158
    },
    {
      "epoch": 0.21122550647625374,
      "grad_norm": 0.1877421736717224,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0209,
      "step": 159
    },
    {
      "epoch": 0.21255396878113583,
      "grad_norm": 0.17007097601890564,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0261,
      "step": 160
    },
    {
      "epoch": 0.21388243108601793,
      "grad_norm": 0.13775795698165894,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0338,
      "step": 161
    },
    {
      "epoch": 0.21521089339090002,
      "grad_norm": 0.25240927934646606,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0784,
      "step": 162
    },
    {
      "epoch": 0.21653935569578214,
      "grad_norm": 0.3839789032936096,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0309,
      "step": 163
    },
    {
      "epoch": 0.21786781800066424,
      "grad_norm": 0.21821452677249908,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0166,
      "step": 164
    },
    {
      "epoch": 0.21919628030554633,
      "grad_norm": 0.1908707171678543,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0172,
      "step": 165
    },
    {
      "epoch": 0.22052474261042843,
      "grad_norm": 0.1220911517739296,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0211,
      "step": 166
    },
    {
      "epoch": 0.22185320491531052,
      "grad_norm": 0.13067792356014252,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0513,
      "step": 167
    },
    {
      "epoch": 0.22318166722019261,
      "grad_norm": 0.27329322695732117,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0225,
      "step": 168
    },
    {
      "epoch": 0.22451012952507474,
      "grad_norm": 0.3294951617717743,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0167,
      "step": 169
    },
    {
      "epoch": 0.22583859182995683,
      "grad_norm": 0.3428938686847687,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0158,
      "step": 170
    },
    {
      "epoch": 0.22716705413483892,
      "grad_norm": 0.5282211899757385,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0118,
      "step": 171
    },
    {
      "epoch": 0.22849551643972102,
      "grad_norm": 0.40836387872695923,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0153,
      "step": 172
    },
    {
      "epoch": 0.2298239787446031,
      "grad_norm": 0.2435687780380249,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0151,
      "step": 173
    },
    {
      "epoch": 0.2311524410494852,
      "grad_norm": 0.21181601285934448,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0157,
      "step": 174
    },
    {
      "epoch": 0.23248090335436733,
      "grad_norm": 0.1964411586523056,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0211,
      "step": 175
    },
    {
      "epoch": 0.23380936565924942,
      "grad_norm": 0.2581467628479004,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0309,
      "step": 176
    },
    {
      "epoch": 0.23513782796413152,
      "grad_norm": 0.22652262449264526,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0248,
      "step": 177
    },
    {
      "epoch": 0.2364662902690136,
      "grad_norm": 0.1209903433918953,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0171,
      "step": 178
    },
    {
      "epoch": 0.2377947525738957,
      "grad_norm": 0.1888657659292221,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0125,
      "step": 179
    },
    {
      "epoch": 0.2391232148787778,
      "grad_norm": 0.2876337170600891,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0151,
      "step": 180
    },
    {
      "epoch": 0.24045167718365992,
      "grad_norm": 0.27109870314598083,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0228,
      "step": 181
    },
    {
      "epoch": 0.24178013948854202,
      "grad_norm": 0.3069908320903778,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.021,
      "step": 182
    },
    {
      "epoch": 0.2431086017934241,
      "grad_norm": 0.32163870334625244,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0196,
      "step": 183
    },
    {
      "epoch": 0.2444370640983062,
      "grad_norm": 0.25406724214553833,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0109,
      "step": 184
    },
    {
      "epoch": 0.2457655264031883,
      "grad_norm": 0.14866866171360016,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.012,
      "step": 185
    },
    {
      "epoch": 0.24709398870807042,
      "grad_norm": 0.1713647097349167,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0106,
      "step": 186
    },
    {
      "epoch": 0.24842245101295252,
      "grad_norm": 0.15642642974853516,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0212,
      "step": 187
    },
    {
      "epoch": 0.2497509133178346,
      "grad_norm": 0.12522074580192566,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0181,
      "step": 188
    },
    {
      "epoch": 0.2510793756227167,
      "grad_norm": 0.12683938443660736,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0104,
      "step": 189
    },
    {
      "epoch": 0.2524078379275988,
      "grad_norm": 0.13343316316604614,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0157,
      "step": 190
    },
    {
      "epoch": 0.2537363002324809,
      "grad_norm": 0.09389553964138031,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0136,
      "step": 191
    },
    {
      "epoch": 0.255064762537363,
      "grad_norm": 0.10069895535707474,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0177,
      "step": 192
    },
    {
      "epoch": 0.2563932248422451,
      "grad_norm": 0.10658153146505356,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0087,
      "step": 193
    },
    {
      "epoch": 0.2577216871471272,
      "grad_norm": 0.08448031544685364,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0043,
      "step": 194
    },
    {
      "epoch": 0.2590501494520093,
      "grad_norm": 0.09968773275613785,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0095,
      "step": 195
    },
    {
      "epoch": 0.2603786117568914,
      "grad_norm": 0.17727267742156982,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0119,
      "step": 196
    },
    {
      "epoch": 0.2617070740617735,
      "grad_norm": 0.09958542138338089,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0082,
      "step": 197
    },
    {
      "epoch": 0.2630355363666556,
      "grad_norm": 0.11090965569019318,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0158,
      "step": 198
    },
    {
      "epoch": 0.2643639986715377,
      "grad_norm": 0.17949454486370087,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0141,
      "step": 199
    },
    {
      "epoch": 0.2656924609764198,
      "grad_norm": 0.21061138808727264,
      "learning_rate": 0.0,
      "loss": 0.0221,
      "step": 200
    },
    {
      "epoch": 0.2656924609764198,
      "eval_loss": 0.05454511195421219,
      "eval_runtime": 42.6119,
      "eval_samples_per_second": 29.757,
      "eval_steps_per_second": 7.439,
      "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": 7.226038350249984e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}