{
  "best_metric": 0.7525862455368042,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9900990099009901,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": 20.889028549194336,
      "learning_rate": 1e-05,
      "loss": 3.5393,
      "step": 1
    },
    {
      "epoch": 0.0049504950495049506,
      "eval_loss": 3.7349982261657715,
      "eval_runtime": 11.7816,
      "eval_samples_per_second": 28.859,
      "eval_steps_per_second": 7.215,
      "step": 1
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 21.26168441772461,
      "learning_rate": 2e-05,
      "loss": 3.6143,
      "step": 2
    },
    {
      "epoch": 0.01485148514851485,
      "grad_norm": 18.394609451293945,
      "learning_rate": 3e-05,
      "loss": 3.3639,
      "step": 3
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 9.790448188781738,
      "learning_rate": 4e-05,
      "loss": 2.8165,
      "step": 4
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 9.769190788269043,
      "learning_rate": 5e-05,
      "loss": 2.3687,
      "step": 5
    },
    {
      "epoch": 0.0297029702970297,
      "grad_norm": 6.409893989562988,
      "learning_rate": 6e-05,
      "loss": 2.1518,
      "step": 6
    },
    {
      "epoch": 0.034653465346534656,
      "grad_norm": 4.260265827178955,
      "learning_rate": 7e-05,
      "loss": 2.0897,
      "step": 7
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 3.4917781352996826,
      "learning_rate": 8e-05,
      "loss": 2.0015,
      "step": 8
    },
    {
      "epoch": 0.04455445544554455,
      "grad_norm": 2.7451415061950684,
      "learning_rate": 9e-05,
      "loss": 1.8687,
      "step": 9
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 2.565915822982788,
      "learning_rate": 0.0001,
      "loss": 1.7035,
      "step": 10
    },
    {
      "epoch": 0.054455445544554455,
      "grad_norm": 2.953639507293701,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.6278,
      "step": 11
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 2.333908796310425,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.5477,
      "step": 12
    },
    {
      "epoch": 0.06435643564356436,
      "grad_norm": 1.7549824714660645,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4412,
      "step": 13
    },
    {
      "epoch": 0.06930693069306931,
      "grad_norm": 1.9975674152374268,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.4049,
      "step": 14
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 1.9610612392425537,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4513,
      "step": 15
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 1.7269662618637085,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.372,
      "step": 16
    },
    {
      "epoch": 0.08415841584158416,
      "grad_norm": 2.0188004970550537,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.4042,
      "step": 17
    },
    {
      "epoch": 0.0891089108910891,
      "grad_norm": 1.6433409452438354,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3232,
      "step": 18
    },
    {
      "epoch": 0.09405940594059406,
      "grad_norm": 1.6771759986877441,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1293,
      "step": 19
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 1.5171518325805664,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2385,
      "step": 20
    },
    {
      "epoch": 0.10396039603960396,
      "grad_norm": 1.4821891784667969,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1397,
      "step": 21
    },
    {
      "epoch": 0.10891089108910891,
      "grad_norm": 1.335679531097412,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1482,
      "step": 22
    },
    {
      "epoch": 0.11386138613861387,
      "grad_norm": 3.401068925857544,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0406,
      "step": 23
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 1.414135217666626,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5833,
      "step": 24
    },
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 1.771116018295288,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5121,
      "step": 25
    },
    {
      "epoch": 0.12871287128712872,
      "grad_norm": 1.559127688407898,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.5258,
      "step": 26
    },
    {
      "epoch": 0.13366336633663367,
      "grad_norm": 1.6080549955368042,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4425,
      "step": 27
    },
    {
      "epoch": 0.13861386138613863,
      "grad_norm": 3.9027740955352783,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4279,
      "step": 28
    },
    {
      "epoch": 0.14356435643564355,
      "grad_norm": 1.7093394994735718,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3058,
      "step": 29
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 0.9017412662506104,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.2713,
      "step": 30
    },
    {
      "epoch": 0.15346534653465346,
      "grad_norm": 1.7826130390167236,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.322,
      "step": 31
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.7511072158813477,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2362,
      "step": 32
    },
    {
      "epoch": 0.16336633663366337,
      "grad_norm": 2.9152824878692627,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2667,
      "step": 33
    },
    {
      "epoch": 0.16831683168316833,
      "grad_norm": 2.223916530609131,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.237,
      "step": 34
    },
    {
      "epoch": 0.17326732673267325,
      "grad_norm": 2.588901996612549,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2132,
      "step": 35
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 2.0806081295013428,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2071,
      "step": 36
    },
    {
      "epoch": 0.18316831683168316,
      "grad_norm": 0.6990413665771484,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2156,
      "step": 37
    },
    {
      "epoch": 0.18811881188118812,
      "grad_norm": 2.2965922355651855,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3234,
      "step": 38
    },
    {
      "epoch": 0.19306930693069307,
      "grad_norm": 0.6369208693504333,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2595,
      "step": 39
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 3.079641819000244,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2381,
      "step": 40
    },
    {
      "epoch": 0.20297029702970298,
      "grad_norm": 1.7295466661453247,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.1722,
      "step": 41
    },
    {
      "epoch": 0.2079207920792079,
      "grad_norm": 1.573925256729126,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3489,
      "step": 42
    },
    {
      "epoch": 0.21287128712871287,
      "grad_norm": 0.7078859210014343,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2405,
      "step": 43
    },
    {
      "epoch": 0.21782178217821782,
      "grad_norm": 0.5808983445167542,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1244,
      "step": 44
    },
    {
      "epoch": 0.22277227722772278,
      "grad_norm": 0.5173713564872742,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1108,
      "step": 45
    },
    {
      "epoch": 0.22772277227722773,
      "grad_norm": 5.590060234069824,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.5615,
      "step": 46
    },
    {
      "epoch": 0.23267326732673269,
      "grad_norm": 0.6795454025268555,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0628,
      "step": 47
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.6396032571792603,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0737,
      "step": 48
    },
    {
      "epoch": 0.24257425742574257,
      "grad_norm": 3.0945487022399902,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.1065,
      "step": 49
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 1.3605676889419556,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0244,
      "step": 50
    },
    {
      "epoch": 0.24752475247524752,
      "eval_loss": 1.3265188932418823,
      "eval_runtime": 11.9523,
      "eval_samples_per_second": 28.446,
      "eval_steps_per_second": 7.112,
      "step": 50
    },
    {
      "epoch": 0.2524752475247525,
      "grad_norm": 9.238303184509277,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.4896,
      "step": 51
    },
    {
      "epoch": 0.25742574257425743,
      "grad_norm": 6.570976734161377,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.4533,
      "step": 52
    },
    {
      "epoch": 0.2623762376237624,
      "grad_norm": 5.021652698516846,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.1246,
      "step": 53
    },
    {
      "epoch": 0.26732673267326734,
      "grad_norm": 3.885449171066284,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.9098,
      "step": 54
    },
    {
      "epoch": 0.2722772277227723,
      "grad_norm": 2.989067792892456,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.7711,
      "step": 55
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 2.8051862716674805,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.6852,
      "step": 56
    },
    {
      "epoch": 0.28217821782178215,
      "grad_norm": 2.3033998012542725,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.7031,
      "step": 57
    },
    {
      "epoch": 0.2871287128712871,
      "grad_norm": 2.118183135986328,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5325,
      "step": 58
    },
    {
      "epoch": 0.29207920792079206,
      "grad_norm": 1.5579206943511963,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.5672,
      "step": 59
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 1.6536222696304321,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.5044,
      "step": 60
    },
    {
      "epoch": 0.30198019801980197,
      "grad_norm": 1.4146463871002197,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.503,
      "step": 61
    },
    {
      "epoch": 0.3069306930693069,
      "grad_norm": 1.6667075157165527,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.4621,
      "step": 62
    },
    {
      "epoch": 0.3118811881188119,
      "grad_norm": 1.310285210609436,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3546,
      "step": 63
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 1.309004306793213,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.3942,
      "step": 64
    },
    {
      "epoch": 0.3217821782178218,
      "grad_norm": 0.9789683818817139,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2836,
      "step": 65
    },
    {
      "epoch": 0.32673267326732675,
      "grad_norm": 1.1585150957107544,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.2857,
      "step": 66
    },
    {
      "epoch": 0.3316831683168317,
      "grad_norm": 1.2389944791793823,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2627,
      "step": 67
    },
    {
      "epoch": 0.33663366336633666,
      "grad_norm": 0.9247581958770752,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.3218,
      "step": 68
    },
    {
      "epoch": 0.3415841584158416,
      "grad_norm": 0.9074732065200806,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.231,
      "step": 69
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 0.6744720935821533,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2527,
      "step": 70
    },
    {
      "epoch": 0.35148514851485146,
      "grad_norm": 0.9764498472213745,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2569,
      "step": 71
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 0.718451738357544,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1321,
      "step": 72
    },
    {
      "epoch": 0.3613861386138614,
      "grad_norm": 0.8860244154930115,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7447,
      "step": 73
    },
    {
      "epoch": 0.36633663366336633,
      "grad_norm": 0.9214662909507751,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9297,
      "step": 74
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 0.6523160934448242,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5588,
      "step": 75
    },
    {
      "epoch": 0.37623762376237624,
      "grad_norm": 1.1410491466522217,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6153,
      "step": 76
    },
    {
      "epoch": 0.3811881188118812,
      "grad_norm": 0.6512343883514404,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5373,
      "step": 77
    },
    {
      "epoch": 0.38613861386138615,
      "grad_norm": 0.7517393827438354,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4309,
      "step": 78
    },
    {
      "epoch": 0.3910891089108911,
      "grad_norm": 0.7369263172149658,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5441,
      "step": 79
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 2.3449153900146484,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3733,
      "step": 80
    },
    {
      "epoch": 0.400990099009901,
      "grad_norm": 1.9192917346954346,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3332,
      "step": 81
    },
    {
      "epoch": 0.40594059405940597,
      "grad_norm": 0.9456062316894531,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.2345,
      "step": 82
    },
    {
      "epoch": 0.41089108910891087,
      "grad_norm": 0.5418946743011475,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3012,
      "step": 83
    },
    {
      "epoch": 0.4158415841584158,
      "grad_norm": 0.9894408583641052,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2562,
      "step": 84
    },
    {
      "epoch": 0.4207920792079208,
      "grad_norm": 0.7907643914222717,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.215,
      "step": 85
    },
    {
      "epoch": 0.42574257425742573,
      "grad_norm": 1.175679326057434,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2139,
      "step": 86
    },
    {
      "epoch": 0.4306930693069307,
      "grad_norm": 1.7521584033966064,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2175,
      "step": 87
    },
    {
      "epoch": 0.43564356435643564,
      "grad_norm": 0.7604097723960876,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2511,
      "step": 88
    },
    {
      "epoch": 0.4405940594059406,
      "grad_norm": 0.5363180041313171,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.2638,
      "step": 89
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 1.884865641593933,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1844,
      "step": 90
    },
    {
      "epoch": 0.4504950495049505,
      "grad_norm": 1.3572901487350464,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1634,
      "step": 91
    },
    {
      "epoch": 0.45544554455445546,
      "grad_norm": 0.4982083737850189,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2684,
      "step": 92
    },
    {
      "epoch": 0.4603960396039604,
      "grad_norm": 2.566551446914673,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4807,
      "step": 93
    },
    {
      "epoch": 0.46534653465346537,
      "grad_norm": 0.3549148142337799,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.182,
      "step": 94
    },
    {
      "epoch": 0.47029702970297027,
      "grad_norm": 0.9232348203659058,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0669,
      "step": 95
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.6755154132843018,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.4396,
      "step": 96
    },
    {
      "epoch": 0.4801980198019802,
      "grad_norm": 0.8277949690818787,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0785,
      "step": 97
    },
    {
      "epoch": 0.48514851485148514,
      "grad_norm": 0.6418360471725464,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0308,
      "step": 98
    },
    {
      "epoch": 0.4900990099009901,
      "grad_norm": 0.5624637603759766,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.034,
      "step": 99
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 0.30850523710250854,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0055,
      "step": 100
    },
    {
      "epoch": 0.49504950495049505,
      "eval_loss": 1.1272268295288086,
      "eval_runtime": 11.9658,
      "eval_samples_per_second": 28.414,
      "eval_steps_per_second": 7.104,
      "step": 100
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.707830905914307,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.1817,
      "step": 101
    },
    {
      "epoch": 0.504950495049505,
      "grad_norm": 6.410693168640137,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.2738,
      "step": 102
    },
    {
      "epoch": 0.5099009900990099,
      "grad_norm": 4.449878692626953,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.968,
      "step": 103
    },
    {
      "epoch": 0.5148514851485149,
      "grad_norm": 3.4005818367004395,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.7405,
      "step": 104
    },
    {
      "epoch": 0.5198019801980198,
      "grad_norm": 3.4762346744537354,
      "learning_rate": 5e-05,
      "loss": 1.6752,
      "step": 105
    },
    {
      "epoch": 0.5247524752475248,
      "grad_norm": 2.954038619995117,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.602,
      "step": 106
    },
    {
      "epoch": 0.5297029702970297,
      "grad_norm": 1.5150116682052612,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.5233,
      "step": 107
    },
    {
      "epoch": 0.5346534653465347,
      "grad_norm": 1.7035818099975586,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.6571,
      "step": 108
    },
    {
      "epoch": 0.5396039603960396,
      "grad_norm": 1.3371613025665283,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.5324,
      "step": 109
    },
    {
      "epoch": 0.5445544554455446,
      "grad_norm": 1.377061128616333,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4141,
      "step": 110
    },
    {
      "epoch": 0.5495049504950495,
      "grad_norm": 1.411737084388733,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3941,
      "step": 111
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.486677646636963,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.4367,
      "step": 112
    },
    {
      "epoch": 0.5594059405940595,
      "grad_norm": 1.4869188070297241,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.4784,
      "step": 113
    },
    {
      "epoch": 0.5643564356435643,
      "grad_norm": 1.1387174129486084,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.1801,
      "step": 114
    },
    {
      "epoch": 0.5693069306930693,
      "grad_norm": 1.1888401508331299,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.2918,
      "step": 115
    },
    {
      "epoch": 0.5742574257425742,
      "grad_norm": 0.9332290887832642,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.1455,
      "step": 116
    },
    {
      "epoch": 0.5792079207920792,
      "grad_norm": 1.0592069625854492,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.2266,
      "step": 117
    },
    {
      "epoch": 0.5841584158415841,
      "grad_norm": 1.1162588596343994,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.3497,
      "step": 118
    },
    {
      "epoch": 0.5891089108910891,
      "grad_norm": 0.9670184254646301,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.217,
      "step": 119
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 1.1078919172286987,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.0999,
      "step": 120
    },
    {
      "epoch": 0.599009900990099,
      "grad_norm": 0.9475307464599609,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.364,
      "step": 121
    },
    {
      "epoch": 0.6039603960396039,
      "grad_norm": 0.7737333178520203,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.1482,
      "step": 122
    },
    {
      "epoch": 0.6089108910891089,
      "grad_norm": 1.6723988056182861,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.811,
      "step": 123
    },
    {
      "epoch": 0.6138613861386139,
      "grad_norm": 1.5611482858657837,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8339,
      "step": 124
    },
    {
      "epoch": 0.6188118811881188,
      "grad_norm": 0.856518030166626,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5835,
      "step": 125
    },
    {
      "epoch": 0.6237623762376238,
      "grad_norm": 1.3354092836380005,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5243,
      "step": 126
    },
    {
      "epoch": 0.6287128712871287,
      "grad_norm": 0.6484349966049194,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5933,
      "step": 127
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 0.7693326473236084,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5468,
      "step": 128
    },
    {
      "epoch": 0.6386138613861386,
      "grad_norm": 0.6562953591346741,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3959,
      "step": 129
    },
    {
      "epoch": 0.6435643564356436,
      "grad_norm": 0.8123564720153809,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5317,
      "step": 130
    },
    {
      "epoch": 0.6485148514851485,
      "grad_norm": 0.5336838364601135,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3596,
      "step": 131
    },
    {
      "epoch": 0.6534653465346535,
      "grad_norm": 0.625294029712677,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3092,
      "step": 132
    },
    {
      "epoch": 0.6584158415841584,
      "grad_norm": 1.097829818725586,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.257,
      "step": 133
    },
    {
      "epoch": 0.6633663366336634,
      "grad_norm": 0.7594442367553711,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2689,
      "step": 134
    },
    {
      "epoch": 0.6683168316831684,
      "grad_norm": 0.9300341010093689,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2529,
      "step": 135
    },
    {
      "epoch": 0.6732673267326733,
      "grad_norm": 0.5532457232475281,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2745,
      "step": 136
    },
    {
      "epoch": 0.6782178217821783,
      "grad_norm": 0.5950554013252258,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.1601,
      "step": 137
    },
    {
      "epoch": 0.6831683168316832,
      "grad_norm": 0.32259735465049744,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2153,
      "step": 138
    },
    {
      "epoch": 0.6881188118811881,
      "grad_norm": 0.8154951930046082,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3287,
      "step": 139
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 1.9147334098815918,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1517,
      "step": 140
    },
    {
      "epoch": 0.698019801980198,
      "grad_norm": 2.727153778076172,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.1685,
      "step": 141
    },
    {
      "epoch": 0.7029702970297029,
      "grad_norm": 0.5829383134841919,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2525,
      "step": 142
    },
    {
      "epoch": 0.7079207920792079,
      "grad_norm": 1.4054803848266602,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.434,
      "step": 143
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.5979534983634949,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.1916,
      "step": 144
    },
    {
      "epoch": 0.7178217821782178,
      "grad_norm": 0.9944595098495483,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0801,
      "step": 145
    },
    {
      "epoch": 0.7227722772277227,
      "grad_norm": 2.1379313468933105,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.4176,
      "step": 146
    },
    {
      "epoch": 0.7277227722772277,
      "grad_norm": 0.639751672744751,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0892,
      "step": 147
    },
    {
      "epoch": 0.7326732673267327,
      "grad_norm": 0.5407268404960632,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0681,
      "step": 148
    },
    {
      "epoch": 0.7376237623762376,
      "grad_norm": 2.7356350421905518,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0245,
      "step": 149
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 0.7852569222450256,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0065,
      "step": 150
    },
    {
      "epoch": 0.7425742574257426,
      "eval_loss": 0.9014630317687988,
      "eval_runtime": 11.9563,
      "eval_samples_per_second": 28.437,
      "eval_steps_per_second": 7.109,
      "step": 150
    },
    {
      "epoch": 0.7475247524752475,
      "grad_norm": 4.09850549697876,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.7303,
      "step": 151
    },
    {
      "epoch": 0.7524752475247525,
      "grad_norm": 4.280149459838867,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.742,
      "step": 152
    },
    {
      "epoch": 0.7574257425742574,
      "grad_norm": 2.548163890838623,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.569,
      "step": 153
    },
    {
      "epoch": 0.7623762376237624,
      "grad_norm": 2.8171985149383545,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.72,
      "step": 154
    },
    {
      "epoch": 0.7673267326732673,
      "grad_norm": 2.392066478729248,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5568,
      "step": 155
    },
    {
      "epoch": 0.7722772277227723,
      "grad_norm": 2.8121585845947266,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.6447,
      "step": 156
    },
    {
      "epoch": 0.7772277227722773,
      "grad_norm": 2.0464634895324707,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.6135,
      "step": 157
    },
    {
      "epoch": 0.7821782178217822,
      "grad_norm": 1.519126057624817,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.4576,
      "step": 158
    },
    {
      "epoch": 0.7871287128712872,
      "grad_norm": 1.9354864358901978,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.5859,
      "step": 159
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.6400994062423706,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.4614,
      "step": 160
    },
    {
      "epoch": 0.7970297029702971,
      "grad_norm": 1.6981539726257324,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.3857,
      "step": 161
    },
    {
      "epoch": 0.801980198019802,
      "grad_norm": 1.5528744459152222,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.5043,
      "step": 162
    },
    {
      "epoch": 0.806930693069307,
      "grad_norm": 0.95765620470047,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.4524,
      "step": 163
    },
    {
      "epoch": 0.8118811881188119,
      "grad_norm": 1.5400218963623047,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.4524,
      "step": 164
    },
    {
      "epoch": 0.8168316831683168,
      "grad_norm": 0.8697559237480164,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.384,
      "step": 165
    },
    {
      "epoch": 0.8217821782178217,
      "grad_norm": 1.1770048141479492,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.3513,
      "step": 166
    },
    {
      "epoch": 0.8267326732673267,
      "grad_norm": 0.8466335535049438,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.2511,
      "step": 167
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 0.7576436996459961,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.2223,
      "step": 168
    },
    {
      "epoch": 0.8366336633663366,
      "grad_norm": 0.7452197074890137,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2158,
      "step": 169
    },
    {
      "epoch": 0.8415841584158416,
      "grad_norm": 1.0680936574935913,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2596,
      "step": 170
    },
    {
      "epoch": 0.8465346534653465,
      "grad_norm": 0.9159606099128723,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.2646,
      "step": 171
    },
    {
      "epoch": 0.8514851485148515,
      "grad_norm": 0.7841719388961792,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8372,
      "step": 172
    },
    {
      "epoch": 0.8564356435643564,
      "grad_norm": 0.8984805345535278,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6485,
      "step": 173
    },
    {
      "epoch": 0.8613861386138614,
      "grad_norm": 1.0949512720108032,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6186,
      "step": 174
    },
    {
      "epoch": 0.8663366336633663,
      "grad_norm": 0.6956310272216797,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.448,
      "step": 175
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 0.824193000793457,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6783,
      "step": 176
    },
    {
      "epoch": 0.8762376237623762,
      "grad_norm": 0.653308093547821,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.4651,
      "step": 177
    },
    {
      "epoch": 0.8811881188118812,
      "grad_norm": 1.6485530138015747,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3541,
      "step": 178
    },
    {
      "epoch": 0.8861386138613861,
      "grad_norm": 2.8014025688171387,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.511,
      "step": 179
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 0.5839876532554626,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.2956,
      "step": 180
    },
    {
      "epoch": 0.8960396039603961,
      "grad_norm": 1.7760860919952393,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2228,
      "step": 181
    },
    {
      "epoch": 0.900990099009901,
      "grad_norm": 2.1453676223754883,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2935,
      "step": 182
    },
    {
      "epoch": 0.905940594059406,
      "grad_norm": 0.9148148894309998,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.289,
      "step": 183
    },
    {
      "epoch": 0.9108910891089109,
      "grad_norm": 1.7343684434890747,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2746,
      "step": 184
    },
    {
      "epoch": 0.9158415841584159,
      "grad_norm": 2.2850189208984375,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1898,
      "step": 185
    },
    {
      "epoch": 0.9207920792079208,
      "grad_norm": 2.712374210357666,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1168,
      "step": 186
    },
    {
      "epoch": 0.9257425742574258,
      "grad_norm": 1.4264570474624634,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.2863,
      "step": 187
    },
    {
      "epoch": 0.9306930693069307,
      "grad_norm": 0.8380259871482849,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2185,
      "step": 188
    },
    {
      "epoch": 0.9356435643564357,
      "grad_norm": 2.7513175010681152,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2733,
      "step": 189
    },
    {
      "epoch": 0.9405940594059405,
      "grad_norm": 5.271636486053467,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1853,
      "step": 190
    },
    {
      "epoch": 0.9455445544554455,
      "grad_norm": 3.287186861038208,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2576,
      "step": 191
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.8500413298606873,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4185,
      "step": 192
    },
    {
      "epoch": 0.9554455445544554,
      "grad_norm": 1.4667712450027466,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3277,
      "step": 193
    },
    {
      "epoch": 0.9603960396039604,
      "grad_norm": 9.328044891357422,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.228,
      "step": 194
    },
    {
      "epoch": 0.9653465346534653,
      "grad_norm": 9.019041061401367,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2156,
      "step": 195
    },
    {
      "epoch": 0.9702970297029703,
      "grad_norm": 4.423496723175049,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3753,
      "step": 196
    },
    {
      "epoch": 0.9752475247524752,
      "grad_norm": 10.901346206665039,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.3433,
      "step": 197
    },
    {
      "epoch": 0.9801980198019802,
      "grad_norm": 16.1439266204834,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2546,
      "step": 198
    },
    {
      "epoch": 0.9851485148514851,
      "grad_norm": 18.18013572692871,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3057,
      "step": 199
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 18.753570556640625,
      "learning_rate": 0.0,
      "loss": 0.3151,
      "step": 200
    },
    {
      "epoch": 0.9900990099009901,
      "eval_loss": 0.7525862455368042,
      "eval_runtime": 11.9574,
      "eval_samples_per_second": 28.434,
      "eval_steps_per_second": 7.109,
      "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": 8.10155117641728e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}