{
  "best_metric": 0.7847399711608887,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03376667229444538,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016883336147222692,
      "grad_norm": 3.849463701248169,
      "learning_rate": 1e-05,
      "loss": 2.4461,
      "step": 1
    },
    {
      "epoch": 0.00016883336147222692,
      "eval_loss": 3.3982229232788086,
      "eval_runtime": 881.3824,
      "eval_samples_per_second": 11.319,
      "eval_steps_per_second": 2.83,
      "step": 1
    },
    {
      "epoch": 0.00033766672294445384,
      "grad_norm": 5.695353984832764,
      "learning_rate": 2e-05,
      "loss": 3.6065,
      "step": 2
    },
    {
      "epoch": 0.0005065000844166807,
      "grad_norm": 6.332581996917725,
      "learning_rate": 3e-05,
      "loss": 3.7241,
      "step": 3
    },
    {
      "epoch": 0.0006753334458889077,
      "grad_norm": 6.2144951820373535,
      "learning_rate": 4e-05,
      "loss": 3.9696,
      "step": 4
    },
    {
      "epoch": 0.0008441668073611346,
      "grad_norm": 6.039239883422852,
      "learning_rate": 5e-05,
      "loss": 4.316,
      "step": 5
    },
    {
      "epoch": 0.0010130001688333614,
      "grad_norm": 7.331217288970947,
      "learning_rate": 6e-05,
      "loss": 4.1988,
      "step": 6
    },
    {
      "epoch": 0.0011818335303055885,
      "grad_norm": 7.4885783195495605,
      "learning_rate": 7e-05,
      "loss": 3.9168,
      "step": 7
    },
    {
      "epoch": 0.0013506668917778154,
      "grad_norm": 5.616000175476074,
      "learning_rate": 8e-05,
      "loss": 3.1674,
      "step": 8
    },
    {
      "epoch": 0.0015195002532500423,
      "grad_norm": 4.106837749481201,
      "learning_rate": 9e-05,
      "loss": 2.1279,
      "step": 9
    },
    {
      "epoch": 0.0016883336147222692,
      "grad_norm": 3.812676429748535,
      "learning_rate": 0.0001,
      "loss": 1.7256,
      "step": 10
    },
    {
      "epoch": 0.001857166976194496,
      "grad_norm": 4.8242034912109375,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.4044,
      "step": 11
    },
    {
      "epoch": 0.0020260003376667227,
      "grad_norm": 5.186927318572998,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1623,
      "step": 12
    },
    {
      "epoch": 0.00219483369913895,
      "grad_norm": 4.764554500579834,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1815,
      "step": 13
    },
    {
      "epoch": 0.002363667060611177,
      "grad_norm": 3.2220687866210938,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1757,
      "step": 14
    },
    {
      "epoch": 0.002532500422083404,
      "grad_norm": 2.6980035305023193,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9044,
      "step": 15
    },
    {
      "epoch": 0.0027013337835556307,
      "grad_norm": 2.1073098182678223,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7845,
      "step": 16
    },
    {
      "epoch": 0.0028701671450278576,
      "grad_norm": 3.517987012863159,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.066,
      "step": 17
    },
    {
      "epoch": 0.0030390005065000845,
      "grad_norm": 3.219632625579834,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0002,
      "step": 18
    },
    {
      "epoch": 0.0032078338679723114,
      "grad_norm": 2.434115171432495,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.2283,
      "step": 19
    },
    {
      "epoch": 0.0033766672294445383,
      "grad_norm": 2.167182445526123,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8855,
      "step": 20
    },
    {
      "epoch": 0.003545500590916765,
      "grad_norm": 1.807060718536377,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6582,
      "step": 21
    },
    {
      "epoch": 0.003714333952388992,
      "grad_norm": 1.9861624240875244,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8867,
      "step": 22
    },
    {
      "epoch": 0.003883167313861219,
      "grad_norm": 1.9444828033447266,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7171,
      "step": 23
    },
    {
      "epoch": 0.0040520006753334455,
      "grad_norm": 1.7773791551589966,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8493,
      "step": 24
    },
    {
      "epoch": 0.004220834036805673,
      "grad_norm": 2.631251096725464,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.923,
      "step": 25
    },
    {
      "epoch": 0.0043896673982779,
      "grad_norm": 2.191289186477661,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8715,
      "step": 26
    },
    {
      "epoch": 0.004558500759750127,
      "grad_norm": 1.8620015382766724,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7842,
      "step": 27
    },
    {
      "epoch": 0.004727334121222354,
      "grad_norm": 1.879298210144043,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9556,
      "step": 28
    },
    {
      "epoch": 0.00489616748269458,
      "grad_norm": 1.416264295578003,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8276,
      "step": 29
    },
    {
      "epoch": 0.005065000844166808,
      "grad_norm": 1.8057156801223755,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9073,
      "step": 30
    },
    {
      "epoch": 0.005233834205639034,
      "grad_norm": 1.7162365913391113,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7562,
      "step": 31
    },
    {
      "epoch": 0.0054026675671112615,
      "grad_norm": 2.3616795539855957,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8783,
      "step": 32
    },
    {
      "epoch": 0.005571500928583488,
      "grad_norm": 1.530067801475525,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6838,
      "step": 33
    },
    {
      "epoch": 0.005740334290055715,
      "grad_norm": 1.7116398811340332,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8878,
      "step": 34
    },
    {
      "epoch": 0.005909167651527942,
      "grad_norm": 2.174961566925049,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9902,
      "step": 35
    },
    {
      "epoch": 0.006078001013000169,
      "grad_norm": 2.057046413421631,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8688,
      "step": 36
    },
    {
      "epoch": 0.0062468343744723955,
      "grad_norm": 1.7510759830474854,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6986,
      "step": 37
    },
    {
      "epoch": 0.006415667735944623,
      "grad_norm": 1.767291784286499,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7792,
      "step": 38
    },
    {
      "epoch": 0.006584501097416849,
      "grad_norm": 1.9842058420181274,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.0662,
      "step": 39
    },
    {
      "epoch": 0.006753334458889077,
      "grad_norm": 1.774396538734436,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6261,
      "step": 40
    },
    {
      "epoch": 0.006922167820361303,
      "grad_norm": 1.7279595136642456,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7258,
      "step": 41
    },
    {
      "epoch": 0.00709100118183353,
      "grad_norm": 1.6297577619552612,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8846,
      "step": 42
    },
    {
      "epoch": 0.007259834543305757,
      "grad_norm": 1.8428339958190918,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8927,
      "step": 43
    },
    {
      "epoch": 0.007428667904777984,
      "grad_norm": 1.7163454294204712,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8374,
      "step": 44
    },
    {
      "epoch": 0.007597501266250211,
      "grad_norm": 1.7556861639022827,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9037,
      "step": 45
    },
    {
      "epoch": 0.007766334627722438,
      "grad_norm": 1.6809866428375244,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.63,
      "step": 46
    },
    {
      "epoch": 0.007935167989194665,
      "grad_norm": 2.198270082473755,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8895,
      "step": 47
    },
    {
      "epoch": 0.008104001350666891,
      "grad_norm": 1.5430370569229126,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6967,
      "step": 48
    },
    {
      "epoch": 0.008272834712139118,
      "grad_norm": 1.5906932353973389,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9653,
      "step": 49
    },
    {
      "epoch": 0.008441668073611346,
      "grad_norm": 1.865241289138794,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8579,
      "step": 50
    },
    {
      "epoch": 0.008441668073611346,
      "eval_loss": 0.9460362792015076,
      "eval_runtime": 886.5506,
      "eval_samples_per_second": 11.253,
      "eval_steps_per_second": 2.813,
      "step": 50
    },
    {
      "epoch": 0.008610501435083573,
      "grad_norm": 2.527874708175659,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2257,
      "step": 51
    },
    {
      "epoch": 0.0087793347965558,
      "grad_norm": 2.3811306953430176,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1528,
      "step": 52
    },
    {
      "epoch": 0.008948168158028026,
      "grad_norm": 3.124645471572876,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.5662,
      "step": 53
    },
    {
      "epoch": 0.009117001519500253,
      "grad_norm": 2.324634313583374,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2929,
      "step": 54
    },
    {
      "epoch": 0.00928583488097248,
      "grad_norm": 2.5402510166168213,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2665,
      "step": 55
    },
    {
      "epoch": 0.009454668242444708,
      "grad_norm": 2.582869291305542,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.4459,
      "step": 56
    },
    {
      "epoch": 0.009623501603916933,
      "grad_norm": 3.372885227203369,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.1894,
      "step": 57
    },
    {
      "epoch": 0.00979233496538916,
      "grad_norm": 3.7564709186553955,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.4704,
      "step": 58
    },
    {
      "epoch": 0.009961168326861388,
      "grad_norm": 3.4480788707733154,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.2335,
      "step": 59
    },
    {
      "epoch": 0.010130001688333615,
      "grad_norm": 2.5441832542419434,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8252,
      "step": 60
    },
    {
      "epoch": 0.010298835049805841,
      "grad_norm": 1.7472666501998901,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7839,
      "step": 61
    },
    {
      "epoch": 0.010467668411278068,
      "grad_norm": 2.0212197303771973,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.0538,
      "step": 62
    },
    {
      "epoch": 0.010636501772750296,
      "grad_norm": 1.967132568359375,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.0502,
      "step": 63
    },
    {
      "epoch": 0.010805335134222523,
      "grad_norm": 1.8603830337524414,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9288,
      "step": 64
    },
    {
      "epoch": 0.010974168495694749,
      "grad_norm": 2.5796523094177246,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0388,
      "step": 65
    },
    {
      "epoch": 0.011143001857166976,
      "grad_norm": 1.6884537935256958,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7689,
      "step": 66
    },
    {
      "epoch": 0.011311835218639203,
      "grad_norm": 1.7151753902435303,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.747,
      "step": 67
    },
    {
      "epoch": 0.01148066858011143,
      "grad_norm": 1.6992590427398682,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9301,
      "step": 68
    },
    {
      "epoch": 0.011649501941583656,
      "grad_norm": 1.5921964645385742,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8427,
      "step": 69
    },
    {
      "epoch": 0.011818335303055883,
      "grad_norm": 1.7600631713867188,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.772,
      "step": 70
    },
    {
      "epoch": 0.01198716866452811,
      "grad_norm": 1.8869719505310059,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.8268,
      "step": 71
    },
    {
      "epoch": 0.012156002026000338,
      "grad_norm": 1.5142515897750854,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7392,
      "step": 72
    },
    {
      "epoch": 0.012324835387472564,
      "grad_norm": 1.2986984252929688,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7559,
      "step": 73
    },
    {
      "epoch": 0.012493668748944791,
      "grad_norm": 1.4033241271972656,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.723,
      "step": 74
    },
    {
      "epoch": 0.012662502110417018,
      "grad_norm": 1.5931016206741333,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.9087,
      "step": 75
    },
    {
      "epoch": 0.012831335471889246,
      "grad_norm": 1.3667229413986206,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6597,
      "step": 76
    },
    {
      "epoch": 0.013000168833361473,
      "grad_norm": 1.2968295812606812,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7618,
      "step": 77
    },
    {
      "epoch": 0.013169002194833699,
      "grad_norm": 1.6322628259658813,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.0552,
      "step": 78
    },
    {
      "epoch": 0.013337835556305926,
      "grad_norm": 1.3570328950881958,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.8135,
      "step": 79
    },
    {
      "epoch": 0.013506668917778153,
      "grad_norm": 1.4668830633163452,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.807,
      "step": 80
    },
    {
      "epoch": 0.01367550227925038,
      "grad_norm": 1.2611284255981445,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7806,
      "step": 81
    },
    {
      "epoch": 0.013844335640722606,
      "grad_norm": 1.5085538625717163,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9675,
      "step": 82
    },
    {
      "epoch": 0.014013169002194834,
      "grad_norm": 1.2213258743286133,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5111,
      "step": 83
    },
    {
      "epoch": 0.01418200236366706,
      "grad_norm": 1.3988815546035767,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8008,
      "step": 84
    },
    {
      "epoch": 0.014350835725139288,
      "grad_norm": 1.7688928842544556,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.9845,
      "step": 85
    },
    {
      "epoch": 0.014519669086611514,
      "grad_norm": 1.4307734966278076,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6767,
      "step": 86
    },
    {
      "epoch": 0.014688502448083741,
      "grad_norm": 1.2613621950149536,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6631,
      "step": 87
    },
    {
      "epoch": 0.014857335809555968,
      "grad_norm": 1.5682814121246338,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8971,
      "step": 88
    },
    {
      "epoch": 0.015026169171028196,
      "grad_norm": 1.5317356586456299,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7153,
      "step": 89
    },
    {
      "epoch": 0.015195002532500421,
      "grad_norm": 1.4265722036361694,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9454,
      "step": 90
    },
    {
      "epoch": 0.015363835893972649,
      "grad_norm": 1.250709056854248,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6061,
      "step": 91
    },
    {
      "epoch": 0.015532669255444876,
      "grad_norm": 1.2432376146316528,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5643,
      "step": 92
    },
    {
      "epoch": 0.015701502616917103,
      "grad_norm": 1.2736859321594238,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4339,
      "step": 93
    },
    {
      "epoch": 0.01587033597838933,
      "grad_norm": 1.7765361070632935,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.691,
      "step": 94
    },
    {
      "epoch": 0.016039169339861558,
      "grad_norm": 1.2529189586639404,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.609,
      "step": 95
    },
    {
      "epoch": 0.016208002701333782,
      "grad_norm": 1.5277594327926636,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8555,
      "step": 96
    },
    {
      "epoch": 0.01637683606280601,
      "grad_norm": 1.5225499868392944,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8603,
      "step": 97
    },
    {
      "epoch": 0.016545669424278237,
      "grad_norm": 1.3415627479553223,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7007,
      "step": 98
    },
    {
      "epoch": 0.016714502785750464,
      "grad_norm": 1.5738972425460815,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.8551,
      "step": 99
    },
    {
      "epoch": 0.01688333614722269,
      "grad_norm": 1.8908401727676392,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9389,
      "step": 100
    },
    {
      "epoch": 0.01688333614722269,
      "eval_loss": 0.8369559645652771,
      "eval_runtime": 886.9258,
      "eval_samples_per_second": 11.248,
      "eval_steps_per_second": 2.812,
      "step": 100
    },
    {
      "epoch": 0.01705216950869492,
      "grad_norm": 2.309119939804077,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.0562,
      "step": 101
    },
    {
      "epoch": 0.017221002870167146,
      "grad_norm": 1.9471321105957031,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.2728,
      "step": 102
    },
    {
      "epoch": 0.017389836231639373,
      "grad_norm": 1.8358919620513916,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8638,
      "step": 103
    },
    {
      "epoch": 0.0175586695931116,
      "grad_norm": 1.6327322721481323,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8712,
      "step": 104
    },
    {
      "epoch": 0.017727502954583824,
      "grad_norm": 1.6338852643966675,
      "learning_rate": 5e-05,
      "loss": 1.0191,
      "step": 105
    },
    {
      "epoch": 0.01789633631605605,
      "grad_norm": 1.4984872341156006,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9121,
      "step": 106
    },
    {
      "epoch": 0.01806516967752828,
      "grad_norm": 1.9310578107833862,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0677,
      "step": 107
    },
    {
      "epoch": 0.018234003039000506,
      "grad_norm": 3.252025842666626,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.1416,
      "step": 108
    },
    {
      "epoch": 0.018402836400472734,
      "grad_norm": 2.5221469402313232,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.1219,
      "step": 109
    },
    {
      "epoch": 0.01857166976194496,
      "grad_norm": 1.588010311126709,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.0613,
      "step": 110
    },
    {
      "epoch": 0.01874050312341719,
      "grad_norm": 1.481406331062317,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9039,
      "step": 111
    },
    {
      "epoch": 0.018909336484889416,
      "grad_norm": 1.544911503791809,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.0348,
      "step": 112
    },
    {
      "epoch": 0.01907816984636164,
      "grad_norm": 1.6578634977340698,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.9406,
      "step": 113
    },
    {
      "epoch": 0.019247003207833867,
      "grad_norm": 1.396926999092102,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7814,
      "step": 114
    },
    {
      "epoch": 0.019415836569306094,
      "grad_norm": 2.0111963748931885,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.0702,
      "step": 115
    },
    {
      "epoch": 0.01958466993077832,
      "grad_norm": 1.6271594762802124,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7437,
      "step": 116
    },
    {
      "epoch": 0.01975350329225055,
      "grad_norm": 1.3694459199905396,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.8132,
      "step": 117
    },
    {
      "epoch": 0.019922336653722776,
      "grad_norm": 1.2598122358322144,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7013,
      "step": 118
    },
    {
      "epoch": 0.020091170015195003,
      "grad_norm": 2.0196268558502197,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8114,
      "step": 119
    },
    {
      "epoch": 0.02026000337666723,
      "grad_norm": 1.645904302597046,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.815,
      "step": 120
    },
    {
      "epoch": 0.020428836738139455,
      "grad_norm": 1.4597923755645752,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9244,
      "step": 121
    },
    {
      "epoch": 0.020597670099611682,
      "grad_norm": 1.4114335775375366,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.846,
      "step": 122
    },
    {
      "epoch": 0.02076650346108391,
      "grad_norm": 1.5119738578796387,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8818,
      "step": 123
    },
    {
      "epoch": 0.020935336822556137,
      "grad_norm": 1.2906166315078735,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8119,
      "step": 124
    },
    {
      "epoch": 0.021104170184028364,
      "grad_norm": 1.3219757080078125,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7751,
      "step": 125
    },
    {
      "epoch": 0.02127300354550059,
      "grad_norm": 1.519602656364441,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.9958,
      "step": 126
    },
    {
      "epoch": 0.02144183690697282,
      "grad_norm": 2.499793767929077,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7331,
      "step": 127
    },
    {
      "epoch": 0.021610670268445046,
      "grad_norm": 1.1942400932312012,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7065,
      "step": 128
    },
    {
      "epoch": 0.021779503629917273,
      "grad_norm": 1.4653667211532593,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.785,
      "step": 129
    },
    {
      "epoch": 0.021948336991389497,
      "grad_norm": 1.1760514974594116,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6945,
      "step": 130
    },
    {
      "epoch": 0.022117170352861724,
      "grad_norm": 1.3386503458023071,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8579,
      "step": 131
    },
    {
      "epoch": 0.022286003714333952,
      "grad_norm": 1.5647889375686646,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.931,
      "step": 132
    },
    {
      "epoch": 0.02245483707580618,
      "grad_norm": 1.057132601737976,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.4611,
      "step": 133
    },
    {
      "epoch": 0.022623670437278406,
      "grad_norm": 1.3188056945800781,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.846,
      "step": 134
    },
    {
      "epoch": 0.022792503798750634,
      "grad_norm": 1.0865601301193237,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.5526,
      "step": 135
    },
    {
      "epoch": 0.02296133716022286,
      "grad_norm": 1.130301594734192,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5778,
      "step": 136
    },
    {
      "epoch": 0.02313017052169509,
      "grad_norm": 1.066878080368042,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.4716,
      "step": 137
    },
    {
      "epoch": 0.023299003883167312,
      "grad_norm": 1.337842583656311,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7182,
      "step": 138
    },
    {
      "epoch": 0.02346783724463954,
      "grad_norm": 1.1486904621124268,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6569,
      "step": 139
    },
    {
      "epoch": 0.023636670606111767,
      "grad_norm": 1.944471836090088,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6197,
      "step": 140
    },
    {
      "epoch": 0.023805503967583994,
      "grad_norm": 1.816693663597107,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8685,
      "step": 141
    },
    {
      "epoch": 0.02397433732905622,
      "grad_norm": 1.0516061782836914,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.512,
      "step": 142
    },
    {
      "epoch": 0.02414317069052845,
      "grad_norm": 1.251572847366333,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5527,
      "step": 143
    },
    {
      "epoch": 0.024312004052000676,
      "grad_norm": 1.2740178108215332,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5643,
      "step": 144
    },
    {
      "epoch": 0.024480837413472904,
      "grad_norm": 1.373628854751587,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6859,
      "step": 145
    },
    {
      "epoch": 0.024649670774945127,
      "grad_norm": 1.6355210542678833,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6886,
      "step": 146
    },
    {
      "epoch": 0.024818504136417355,
      "grad_norm": 1.305099606513977,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6772,
      "step": 147
    },
    {
      "epoch": 0.024987337497889582,
      "grad_norm": 1.3299963474273682,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.635,
      "step": 148
    },
    {
      "epoch": 0.02515617085936181,
      "grad_norm": 2.00677227973938,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8408,
      "step": 149
    },
    {
      "epoch": 0.025325004220834037,
      "grad_norm": 1.5598353147506714,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9071,
      "step": 150
    },
    {
      "epoch": 0.025325004220834037,
      "eval_loss": 0.7902956008911133,
      "eval_runtime": 886.2264,
      "eval_samples_per_second": 11.257,
      "eval_steps_per_second": 2.814,
      "step": 150
    },
    {
      "epoch": 0.025493837582306264,
      "grad_norm": 1.2902171611785889,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9519,
      "step": 151
    },
    {
      "epoch": 0.02566267094377849,
      "grad_norm": 1.6426546573638916,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.9875,
      "step": 152
    },
    {
      "epoch": 0.02583150430525072,
      "grad_norm": 1.2995145320892334,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7499,
      "step": 153
    },
    {
      "epoch": 0.026000337666722946,
      "grad_norm": 1.1217262744903564,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.6222,
      "step": 154
    },
    {
      "epoch": 0.02616917102819517,
      "grad_norm": 1.907186508178711,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0484,
      "step": 155
    },
    {
      "epoch": 0.026338004389667397,
      "grad_norm": 2.2877156734466553,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.3179,
      "step": 156
    },
    {
      "epoch": 0.026506837751139625,
      "grad_norm": 1.6355077028274536,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.796,
      "step": 157
    },
    {
      "epoch": 0.026675671112611852,
      "grad_norm": 2.380509853363037,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.0684,
      "step": 158
    },
    {
      "epoch": 0.02684450447408408,
      "grad_norm": 1.5580389499664307,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9366,
      "step": 159
    },
    {
      "epoch": 0.027013337835556307,
      "grad_norm": 1.1080050468444824,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7408,
      "step": 160
    },
    {
      "epoch": 0.027182171197028534,
      "grad_norm": 1.0910242795944214,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7924,
      "step": 161
    },
    {
      "epoch": 0.02735100455850076,
      "grad_norm": 1.2202306985855103,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8415,
      "step": 162
    },
    {
      "epoch": 0.027519837919972985,
      "grad_norm": 1.4118188619613647,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.861,
      "step": 163
    },
    {
      "epoch": 0.027688671281445212,
      "grad_norm": 1.0251755714416504,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7031,
      "step": 164
    },
    {
      "epoch": 0.02785750464291744,
      "grad_norm": 1.1560112237930298,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7236,
      "step": 165
    },
    {
      "epoch": 0.028026338004389667,
      "grad_norm": 1.1609209775924683,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7584,
      "step": 166
    },
    {
      "epoch": 0.028195171365861894,
      "grad_norm": 1.1667463779449463,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6749,
      "step": 167
    },
    {
      "epoch": 0.02836400472733412,
      "grad_norm": 1.4253780841827393,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8709,
      "step": 168
    },
    {
      "epoch": 0.02853283808880635,
      "grad_norm": 1.3915703296661377,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8286,
      "step": 169
    },
    {
      "epoch": 0.028701671450278576,
      "grad_norm": 1.151399850845337,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7926,
      "step": 170
    },
    {
      "epoch": 0.028870504811750804,
      "grad_norm": 1.495931625366211,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.0879,
      "step": 171
    },
    {
      "epoch": 0.029039338173223028,
      "grad_norm": 1.6609318256378174,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.9641,
      "step": 172
    },
    {
      "epoch": 0.029208171534695255,
      "grad_norm": 1.1750178337097168,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7217,
      "step": 173
    },
    {
      "epoch": 0.029377004896167482,
      "grad_norm": 1.2321311235427856,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8485,
      "step": 174
    },
    {
      "epoch": 0.02954583825763971,
      "grad_norm": 1.1647535562515259,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6323,
      "step": 175
    },
    {
      "epoch": 0.029714671619111937,
      "grad_norm": 1.1627222299575806,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7031,
      "step": 176
    },
    {
      "epoch": 0.029883504980584164,
      "grad_norm": 1.1513265371322632,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7444,
      "step": 177
    },
    {
      "epoch": 0.03005233834205639,
      "grad_norm": 1.0242998600006104,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6086,
      "step": 178
    },
    {
      "epoch": 0.03022117170352862,
      "grad_norm": 1.0469578504562378,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.664,
      "step": 179
    },
    {
      "epoch": 0.030390005065000843,
      "grad_norm": 1.2075523138046265,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5492,
      "step": 180
    },
    {
      "epoch": 0.03055883842647307,
      "grad_norm": 1.0868726968765259,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7107,
      "step": 181
    },
    {
      "epoch": 0.030727671787945297,
      "grad_norm": 1.2776423692703247,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.807,
      "step": 182
    },
    {
      "epoch": 0.030896505149417525,
      "grad_norm": 1.4211896657943726,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8227,
      "step": 183
    },
    {
      "epoch": 0.031065338510889752,
      "grad_norm": 1.1772956848144531,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.717,
      "step": 184
    },
    {
      "epoch": 0.03123417187236198,
      "grad_norm": 1.4948289394378662,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7835,
      "step": 185
    },
    {
      "epoch": 0.03140300523383421,
      "grad_norm": 1.501604676246643,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.779,
      "step": 186
    },
    {
      "epoch": 0.031571838595306434,
      "grad_norm": 1.0823994874954224,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5885,
      "step": 187
    },
    {
      "epoch": 0.03174067195677866,
      "grad_norm": 1.4669153690338135,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.8588,
      "step": 188
    },
    {
      "epoch": 0.03190950531825089,
      "grad_norm": 1.077918291091919,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.5865,
      "step": 189
    },
    {
      "epoch": 0.032078338679723116,
      "grad_norm": 1.1504334211349487,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6375,
      "step": 190
    },
    {
      "epoch": 0.03224717204119534,
      "grad_norm": 1.2647700309753418,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.7639,
      "step": 191
    },
    {
      "epoch": 0.032416005402667564,
      "grad_norm": 1.2374051809310913,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5646,
      "step": 192
    },
    {
      "epoch": 0.03258483876413979,
      "grad_norm": 1.139468789100647,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.509,
      "step": 193
    },
    {
      "epoch": 0.03275367212561202,
      "grad_norm": 1.1362189054489136,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5795,
      "step": 194
    },
    {
      "epoch": 0.032922505487084246,
      "grad_norm": 1.141852617263794,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4069,
      "step": 195
    },
    {
      "epoch": 0.03309133884855647,
      "grad_norm": 1.3960946798324585,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5808,
      "step": 196
    },
    {
      "epoch": 0.0332601722100287,
      "grad_norm": 1.824180245399475,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.8102,
      "step": 197
    },
    {
      "epoch": 0.03342900557150093,
      "grad_norm": 1.2594473361968994,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6993,
      "step": 198
    },
    {
      "epoch": 0.033597838932973155,
      "grad_norm": 1.2905774116516113,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7243,
      "step": 199
    },
    {
      "epoch": 0.03376667229444538,
      "grad_norm": 1.6729393005371094,
      "learning_rate": 0.0,
      "loss": 0.9118,
      "step": 200
    },
    {
      "epoch": 0.03376667229444538,
      "eval_loss": 0.7847399711608887,
      "eval_runtime": 887.0861,
      "eval_samples_per_second": 11.246,
      "eval_steps_per_second": 2.811,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5261504903184384e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}