{
  "best_metric": 0.5744644999504089,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.3401360544217687,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "grad_norm": 0.4288555681705475,
      "learning_rate": 1e-05,
      "loss": 0.6845,
      "step": 1
    },
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": 0.9164427518844604,
      "eval_runtime": 111.6918,
      "eval_samples_per_second": 8.864,
      "eval_steps_per_second": 2.22,
      "step": 1
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": 0.3755057156085968,
      "learning_rate": 2e-05,
      "loss": 0.5418,
      "step": 2
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 0.5304123163223267,
      "learning_rate": 3e-05,
      "loss": 0.7178,
      "step": 3
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": 0.5340713858604431,
      "learning_rate": 4e-05,
      "loss": 0.7566,
      "step": 4
    },
    {
      "epoch": 0.008503401360544218,
      "grad_norm": 0.43396827578544617,
      "learning_rate": 5e-05,
      "loss": 0.7132,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.37237513065338135,
      "learning_rate": 6e-05,
      "loss": 0.6635,
      "step": 6
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 0.4176798462867737,
      "learning_rate": 7e-05,
      "loss": 0.6521,
      "step": 7
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": 0.5651229023933411,
      "learning_rate": 8e-05,
      "loss": 0.7153,
      "step": 8
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.5334160923957825,
      "learning_rate": 9e-05,
      "loss": 0.6251,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": 0.5003652572631836,
      "learning_rate": 0.0001,
      "loss": 0.6766,
      "step": 10
    },
    {
      "epoch": 0.01870748299319728,
      "grad_norm": 0.4479980170726776,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7534,
      "step": 11
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.6375936269760132,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6739,
      "step": 12
    },
    {
      "epoch": 0.022108843537414966,
      "grad_norm": 0.487513929605484,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6428,
      "step": 13
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.48849838972091675,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6541,
      "step": 14
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 0.4806826412677765,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6939,
      "step": 15
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 0.5073195099830627,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7501,
      "step": 16
    },
    {
      "epoch": 0.02891156462585034,
      "grad_norm": 0.5000447630882263,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6536,
      "step": 17
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.47071903944015503,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6911,
      "step": 18
    },
    {
      "epoch": 0.03231292517006803,
      "grad_norm": 0.5565551519393921,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.82,
      "step": 19
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 0.9839614629745483,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.725,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.5189358592033386,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7584,
      "step": 21
    },
    {
      "epoch": 0.03741496598639456,
      "grad_norm": 0.5448806285858154,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6766,
      "step": 22
    },
    {
      "epoch": 0.0391156462585034,
      "grad_norm": 0.6178721189498901,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8176,
      "step": 23
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.5501227974891663,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7959,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "grad_norm": 0.5394447445869446,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6747,
      "step": 25
    },
    {
      "epoch": 0.04421768707482993,
      "grad_norm": 0.4578421711921692,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7017,
      "step": 26
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.43217867612838745,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7586,
      "step": 27
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.5269436836242676,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7762,
      "step": 28
    },
    {
      "epoch": 0.04931972789115646,
      "grad_norm": 0.5278212428092957,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.752,
      "step": 29
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 0.546906054019928,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7473,
      "step": 30
    },
    {
      "epoch": 0.05272108843537415,
      "grad_norm": 0.5008829236030579,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8632,
      "step": 31
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 0.48663976788520813,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.703,
      "step": 32
    },
    {
      "epoch": 0.05612244897959184,
      "grad_norm": 0.4483780860900879,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6651,
      "step": 33
    },
    {
      "epoch": 0.05782312925170068,
      "grad_norm": 0.49737972021102905,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6696,
      "step": 34
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.4909127950668335,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7849,
      "step": 35
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 0.4665275514125824,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6704,
      "step": 36
    },
    {
      "epoch": 0.06292517006802721,
      "grad_norm": 0.4938236176967621,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7845,
      "step": 37
    },
    {
      "epoch": 0.06462585034013606,
      "grad_norm": 0.5744200348854065,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8345,
      "step": 38
    },
    {
      "epoch": 0.0663265306122449,
      "grad_norm": 0.5112040042877197,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7174,
      "step": 39
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 0.5870174765586853,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6792,
      "step": 40
    },
    {
      "epoch": 0.06972789115646258,
      "grad_norm": 0.5259171724319458,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6749,
      "step": 41
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.6003683805465698,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8423,
      "step": 42
    },
    {
      "epoch": 0.07312925170068027,
      "grad_norm": 0.5393774509429932,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.715,
      "step": 43
    },
    {
      "epoch": 0.07482993197278912,
      "grad_norm": 0.5619723200798035,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6994,
      "step": 44
    },
    {
      "epoch": 0.07653061224489796,
      "grad_norm": 0.5511630773544312,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.658,
      "step": 45
    },
    {
      "epoch": 0.0782312925170068,
      "grad_norm": 0.634554922580719,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7105,
      "step": 46
    },
    {
      "epoch": 0.07993197278911565,
      "grad_norm": 0.6505147814750671,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6276,
      "step": 47
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.6368511319160461,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6673,
      "step": 48
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.5481855869293213,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6081,
      "step": 49
    },
    {
      "epoch": 0.08503401360544217,
      "grad_norm": 0.6749992966651917,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6231,
      "step": 50
    },
    {
      "epoch": 0.08503401360544217,
      "eval_loss": 0.6676458120346069,
      "eval_runtime": 112.997,
      "eval_samples_per_second": 8.761,
      "eval_steps_per_second": 2.195,
      "step": 50
    },
    {
      "epoch": 0.08673469387755102,
      "grad_norm": 0.3151683509349823,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4879,
      "step": 51
    },
    {
      "epoch": 0.08843537414965986,
      "grad_norm": 0.34208595752716064,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5187,
      "step": 52
    },
    {
      "epoch": 0.09013605442176871,
      "grad_norm": 0.31240901350975037,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5334,
      "step": 53
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 0.3087746202945709,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5827,
      "step": 54
    },
    {
      "epoch": 0.0935374149659864,
      "grad_norm": 0.33480334281921387,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6414,
      "step": 55
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.30743226408958435,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5044,
      "step": 56
    },
    {
      "epoch": 0.09693877551020408,
      "grad_norm": 0.3301539421081543,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.6126,
      "step": 57
    },
    {
      "epoch": 0.09863945578231292,
      "grad_norm": 0.3428323566913605,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.672,
      "step": 58
    },
    {
      "epoch": 0.10034013605442177,
      "grad_norm": 0.39286720752716064,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.633,
      "step": 59
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.39227160811424255,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6392,
      "step": 60
    },
    {
      "epoch": 0.10374149659863946,
      "grad_norm": 0.3543809652328491,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.583,
      "step": 61
    },
    {
      "epoch": 0.1054421768707483,
      "grad_norm": 0.35992977023124695,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5585,
      "step": 62
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.42198336124420166,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6447,
      "step": 63
    },
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 0.3661971092224121,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6061,
      "step": 64
    },
    {
      "epoch": 0.11054421768707483,
      "grad_norm": 0.9924163222312927,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7473,
      "step": 65
    },
    {
      "epoch": 0.11224489795918367,
      "grad_norm": 0.460999995470047,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6401,
      "step": 66
    },
    {
      "epoch": 0.11394557823129252,
      "grad_norm": 0.44477346539497375,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6628,
      "step": 67
    },
    {
      "epoch": 0.11564625850340136,
      "grad_norm": 0.5578277111053467,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8071,
      "step": 68
    },
    {
      "epoch": 0.11734693877551021,
      "grad_norm": 0.5175428986549377,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6935,
      "step": 69
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.46672293543815613,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6407,
      "step": 70
    },
    {
      "epoch": 0.12074829931972789,
      "grad_norm": 0.5326968431472778,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6025,
      "step": 71
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.4657076299190521,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6035,
      "step": 72
    },
    {
      "epoch": 0.12414965986394558,
      "grad_norm": 0.4984128773212433,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.763,
      "step": 73
    },
    {
      "epoch": 0.12585034013605442,
      "grad_norm": 0.45834386348724365,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6547,
      "step": 74
    },
    {
      "epoch": 0.12755102040816327,
      "grad_norm": 0.4205828905105591,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6141,
      "step": 75
    },
    {
      "epoch": 0.1292517006802721,
      "grad_norm": 0.4301142990589142,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6754,
      "step": 76
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 0.4987786114215851,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7245,
      "step": 77
    },
    {
      "epoch": 0.1326530612244898,
      "grad_norm": 0.4795130789279938,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6346,
      "step": 78
    },
    {
      "epoch": 0.13435374149659865,
      "grad_norm": 0.4848536252975464,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.609,
      "step": 79
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 0.4452188313007355,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6112,
      "step": 80
    },
    {
      "epoch": 0.1377551020408163,
      "grad_norm": 0.493058979511261,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7213,
      "step": 81
    },
    {
      "epoch": 0.13945578231292516,
      "grad_norm": 0.4795525074005127,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6832,
      "step": 82
    },
    {
      "epoch": 0.141156462585034,
      "grad_norm": 0.5488741397857666,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6608,
      "step": 83
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.48007699847221375,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6215,
      "step": 84
    },
    {
      "epoch": 0.1445578231292517,
      "grad_norm": 0.5367547869682312,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7459,
      "step": 85
    },
    {
      "epoch": 0.14625850340136054,
      "grad_norm": 0.522371232509613,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6639,
      "step": 86
    },
    {
      "epoch": 0.14795918367346939,
      "grad_norm": 0.5369559526443481,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6981,
      "step": 87
    },
    {
      "epoch": 0.14965986394557823,
      "grad_norm": 0.5416675806045532,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.62,
      "step": 88
    },
    {
      "epoch": 0.15136054421768708,
      "grad_norm": 0.5710650682449341,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6622,
      "step": 89
    },
    {
      "epoch": 0.15306122448979592,
      "grad_norm": 0.5949693322181702,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.6813,
      "step": 90
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 0.5561469197273254,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6575,
      "step": 91
    },
    {
      "epoch": 0.1564625850340136,
      "grad_norm": 0.4868173897266388,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6355,
      "step": 92
    },
    {
      "epoch": 0.15816326530612246,
      "grad_norm": 0.5106202960014343,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5961,
      "step": 93
    },
    {
      "epoch": 0.1598639455782313,
      "grad_norm": 0.610733687877655,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.658,
      "step": 94
    },
    {
      "epoch": 0.16156462585034015,
      "grad_norm": 0.6049282550811768,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7078,
      "step": 95
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.6332781314849854,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6183,
      "step": 96
    },
    {
      "epoch": 0.1649659863945578,
      "grad_norm": 0.623099148273468,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5613,
      "step": 97
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.6980010271072388,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6378,
      "step": 98
    },
    {
      "epoch": 0.1683673469387755,
      "grad_norm": 0.7664418816566467,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5699,
      "step": 99
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 0.7114914655685425,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5215,
      "step": 100
    },
    {
      "epoch": 0.17006802721088435,
      "eval_loss": 0.616676390171051,
      "eval_runtime": 112.9885,
      "eval_samples_per_second": 8.762,
      "eval_steps_per_second": 2.195,
      "step": 100
    },
    {
      "epoch": 0.1717687074829932,
      "grad_norm": 0.30999696254730225,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4943,
      "step": 101
    },
    {
      "epoch": 0.17346938775510204,
      "grad_norm": 0.33026978373527527,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.475,
      "step": 102
    },
    {
      "epoch": 0.17517006802721088,
      "grad_norm": 0.3227093517780304,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5703,
      "step": 103
    },
    {
      "epoch": 0.17687074829931973,
      "grad_norm": 0.30380678176879883,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5357,
      "step": 104
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.3293682932853699,
      "learning_rate": 5e-05,
      "loss": 0.515,
      "step": 105
    },
    {
      "epoch": 0.18027210884353742,
      "grad_norm": 0.2937142252922058,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4658,
      "step": 106
    },
    {
      "epoch": 0.18197278911564627,
      "grad_norm": 0.329475462436676,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5588,
      "step": 107
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 0.35816866159439087,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.5495,
      "step": 108
    },
    {
      "epoch": 0.18537414965986396,
      "grad_norm": 0.32772010564804077,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5153,
      "step": 109
    },
    {
      "epoch": 0.1870748299319728,
      "grad_norm": 0.37260547280311584,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6024,
      "step": 110
    },
    {
      "epoch": 0.18877551020408162,
      "grad_norm": 0.35291603207588196,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5448,
      "step": 111
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.42649102210998535,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.62,
      "step": 112
    },
    {
      "epoch": 0.1921768707482993,
      "grad_norm": 0.42369765043258667,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.5771,
      "step": 113
    },
    {
      "epoch": 0.19387755102040816,
      "grad_norm": 0.3675820827484131,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.538,
      "step": 114
    },
    {
      "epoch": 0.195578231292517,
      "grad_norm": 0.4110804498195648,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5575,
      "step": 115
    },
    {
      "epoch": 0.19727891156462585,
      "grad_norm": 1.0988695621490479,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6389,
      "step": 116
    },
    {
      "epoch": 0.1989795918367347,
      "grad_norm": 0.48625174164772034,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.57,
      "step": 117
    },
    {
      "epoch": 0.20068027210884354,
      "grad_norm": 0.44558244943618774,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.592,
      "step": 118
    },
    {
      "epoch": 0.20238095238095238,
      "grad_norm": 0.49839475750923157,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.71,
      "step": 119
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.48313164710998535,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6153,
      "step": 120
    },
    {
      "epoch": 0.20578231292517007,
      "grad_norm": 0.4937128722667694,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6136,
      "step": 121
    },
    {
      "epoch": 0.20748299319727892,
      "grad_norm": 0.4950511157512665,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7182,
      "step": 122
    },
    {
      "epoch": 0.20918367346938777,
      "grad_norm": 0.5093518495559692,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6388,
      "step": 123
    },
    {
      "epoch": 0.2108843537414966,
      "grad_norm": 0.47881636023521423,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7196,
      "step": 124
    },
    {
      "epoch": 0.21258503401360543,
      "grad_norm": 0.45933425426483154,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6208,
      "step": 125
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.40398073196411133,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5207,
      "step": 126
    },
    {
      "epoch": 0.21598639455782312,
      "grad_norm": 0.4384560286998749,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5923,
      "step": 127
    },
    {
      "epoch": 0.21768707482993196,
      "grad_norm": 0.4191487729549408,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5489,
      "step": 128
    },
    {
      "epoch": 0.2193877551020408,
      "grad_norm": 0.4510822594165802,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.556,
      "step": 129
    },
    {
      "epoch": 0.22108843537414966,
      "grad_norm": 0.5315272212028503,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6579,
      "step": 130
    },
    {
      "epoch": 0.2227891156462585,
      "grad_norm": 0.49571457505226135,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6506,
      "step": 131
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": 0.4333937466144562,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6326,
      "step": 132
    },
    {
      "epoch": 0.2261904761904762,
      "grad_norm": 0.49664804339408875,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5756,
      "step": 133
    },
    {
      "epoch": 0.22789115646258504,
      "grad_norm": 0.639265239238739,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5645,
      "step": 134
    },
    {
      "epoch": 0.22959183673469388,
      "grad_norm": 0.49606576561927795,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6321,
      "step": 135
    },
    {
      "epoch": 0.23129251700680273,
      "grad_norm": 0.619802713394165,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.744,
      "step": 136
    },
    {
      "epoch": 0.23299319727891157,
      "grad_norm": 0.5166471004486084,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5125,
      "step": 137
    },
    {
      "epoch": 0.23469387755102042,
      "grad_norm": 0.5217966437339783,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6602,
      "step": 138
    },
    {
      "epoch": 0.23639455782312926,
      "grad_norm": 0.5699508786201477,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6796,
      "step": 139
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.5439802408218384,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.632,
      "step": 140
    },
    {
      "epoch": 0.23979591836734693,
      "grad_norm": 0.6157355904579163,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6693,
      "step": 141
    },
    {
      "epoch": 0.24149659863945577,
      "grad_norm": 0.553881824016571,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5841,
      "step": 142
    },
    {
      "epoch": 0.24319727891156462,
      "grad_norm": 0.6117890477180481,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.69,
      "step": 143
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.579740583896637,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5628,
      "step": 144
    },
    {
      "epoch": 0.2465986394557823,
      "grad_norm": 0.6042082905769348,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6166,
      "step": 145
    },
    {
      "epoch": 0.24829931972789115,
      "grad_norm": 0.7273824214935303,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6413,
      "step": 146
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6818268299102783,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5849,
      "step": 147
    },
    {
      "epoch": 0.25170068027210885,
      "grad_norm": 0.6800457835197449,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5959,
      "step": 148
    },
    {
      "epoch": 0.2534013605442177,
      "grad_norm": 0.6328475475311279,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5479,
      "step": 149
    },
    {
      "epoch": 0.25510204081632654,
      "grad_norm": 0.77385014295578,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5426,
      "step": 150
    },
    {
      "epoch": 0.25510204081632654,
      "eval_loss": 0.58595871925354,
      "eval_runtime": 113.034,
      "eval_samples_per_second": 8.758,
      "eval_steps_per_second": 2.194,
      "step": 150
    },
    {
      "epoch": 0.2568027210884354,
      "grad_norm": 0.2590750455856323,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.456,
      "step": 151
    },
    {
      "epoch": 0.2585034013605442,
      "grad_norm": 0.27804961800575256,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.454,
      "step": 152
    },
    {
      "epoch": 0.2602040816326531,
      "grad_norm": 0.3585802912712097,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.492,
      "step": 153
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.3204173743724823,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5437,
      "step": 154
    },
    {
      "epoch": 0.26360544217687076,
      "grad_norm": 0.3290875256061554,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4682,
      "step": 155
    },
    {
      "epoch": 0.2653061224489796,
      "grad_norm": 0.3465502858161926,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5286,
      "step": 156
    },
    {
      "epoch": 0.26700680272108845,
      "grad_norm": 0.3424157202243805,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.5416,
      "step": 157
    },
    {
      "epoch": 0.2687074829931973,
      "grad_norm": 0.34820106625556946,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5598,
      "step": 158
    },
    {
      "epoch": 0.27040816326530615,
      "grad_norm": 0.38742437958717346,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5809,
      "step": 159
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 0.3976348340511322,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6014,
      "step": 160
    },
    {
      "epoch": 0.27380952380952384,
      "grad_norm": 0.3813357353210449,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5257,
      "step": 161
    },
    {
      "epoch": 0.2755102040816326,
      "grad_norm": 0.377094566822052,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5146,
      "step": 162
    },
    {
      "epoch": 0.27721088435374147,
      "grad_norm": 0.44850313663482666,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.6231,
      "step": 163
    },
    {
      "epoch": 0.2789115646258503,
      "grad_norm": 0.42010563611984253,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.5482,
      "step": 164
    },
    {
      "epoch": 0.28061224489795916,
      "grad_norm": 0.39332419633865356,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4581,
      "step": 165
    },
    {
      "epoch": 0.282312925170068,
      "grad_norm": 0.4281606674194336,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.4938,
      "step": 166
    },
    {
      "epoch": 0.28401360544217685,
      "grad_norm": 0.471218466758728,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6423,
      "step": 167
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.47609323263168335,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.602,
      "step": 168
    },
    {
      "epoch": 0.28741496598639454,
      "grad_norm": 0.4727756977081299,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6474,
      "step": 169
    },
    {
      "epoch": 0.2891156462585034,
      "grad_norm": 0.4952782094478607,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5451,
      "step": 170
    },
    {
      "epoch": 0.29081632653061223,
      "grad_norm": 0.5326199531555176,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6134,
      "step": 171
    },
    {
      "epoch": 0.2925170068027211,
      "grad_norm": 0.5766266584396362,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6727,
      "step": 172
    },
    {
      "epoch": 0.2942176870748299,
      "grad_norm": 0.4269533157348633,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.61,
      "step": 173
    },
    {
      "epoch": 0.29591836734693877,
      "grad_norm": 0.47664526104927063,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6136,
      "step": 174
    },
    {
      "epoch": 0.2976190476190476,
      "grad_norm": 0.427399605512619,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.588,
      "step": 175
    },
    {
      "epoch": 0.29931972789115646,
      "grad_norm": 0.43902742862701416,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5535,
      "step": 176
    },
    {
      "epoch": 0.3010204081632653,
      "grad_norm": 0.44347235560417175,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6258,
      "step": 177
    },
    {
      "epoch": 0.30272108843537415,
      "grad_norm": 0.4775888919830322,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7049,
      "step": 178
    },
    {
      "epoch": 0.304421768707483,
      "grad_norm": 0.43406784534454346,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5305,
      "step": 179
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 0.5827739834785461,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6625,
      "step": 180
    },
    {
      "epoch": 0.3078231292517007,
      "grad_norm": 0.5661402344703674,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.659,
      "step": 181
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.4977942407131195,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6163,
      "step": 182
    },
    {
      "epoch": 0.3112244897959184,
      "grad_norm": 0.43116286396980286,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.506,
      "step": 183
    },
    {
      "epoch": 0.3129251700680272,
      "grad_norm": 0.5250166058540344,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6421,
      "step": 184
    },
    {
      "epoch": 0.31462585034013607,
      "grad_norm": 0.4839404225349426,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6135,
      "step": 185
    },
    {
      "epoch": 0.3163265306122449,
      "grad_norm": 0.6262943744659424,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6366,
      "step": 186
    },
    {
      "epoch": 0.31802721088435376,
      "grad_norm": 0.5653702616691589,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7065,
      "step": 187
    },
    {
      "epoch": 0.3197278911564626,
      "grad_norm": 0.5952920913696289,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.652,
      "step": 188
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.5292506217956543,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.607,
      "step": 189
    },
    {
      "epoch": 0.3231292517006803,
      "grad_norm": 0.5688542723655701,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6142,
      "step": 190
    },
    {
      "epoch": 0.32482993197278914,
      "grad_norm": 0.6382482647895813,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6657,
      "step": 191
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.6008819341659546,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5813,
      "step": 192
    },
    {
      "epoch": 0.3282312925170068,
      "grad_norm": 0.5935477018356323,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5664,
      "step": 193
    },
    {
      "epoch": 0.3299319727891156,
      "grad_norm": 0.5567658543586731,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5685,
      "step": 194
    },
    {
      "epoch": 0.33163265306122447,
      "grad_norm": 0.6635259389877319,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5879,
      "step": 195
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.6662435531616211,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5891,
      "step": 196
    },
    {
      "epoch": 0.33503401360544216,
      "grad_norm": 0.5589507818222046,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.4879,
      "step": 197
    },
    {
      "epoch": 0.336734693877551,
      "grad_norm": 0.6105138659477234,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4384,
      "step": 198
    },
    {
      "epoch": 0.33843537414965985,
      "grad_norm": 0.7239654064178467,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5403,
      "step": 199
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 0.7754726409912109,
      "learning_rate": 0.0,
      "loss": 0.4461,
      "step": 200
    },
    {
      "epoch": 0.3401360544217687,
      "eval_loss": 0.5744644999504089,
      "eval_runtime": 113.0243,
      "eval_samples_per_second": 8.759,
      "eval_steps_per_second": 2.194,
      "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": 4.5293120201844326e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}