{
  "best_metric": 0.20135770738124847,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.7699115044247788,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008849557522123894,
      "grad_norm": 0.20639537274837494,
      "learning_rate": 1e-05,
      "loss": 0.287,
      "step": 1
    },
    {
      "epoch": 0.008849557522123894,
      "eval_loss": 0.34084415435791016,
      "eval_runtime": 14.1913,
      "eval_samples_per_second": 13.389,
      "eval_steps_per_second": 3.382,
      "step": 1
    },
    {
      "epoch": 0.017699115044247787,
      "grad_norm": 0.21075405180454254,
      "learning_rate": 2e-05,
      "loss": 0.2703,
      "step": 2
    },
    {
      "epoch": 0.02654867256637168,
      "grad_norm": 0.25006136298179626,
      "learning_rate": 3e-05,
      "loss": 0.2587,
      "step": 3
    },
    {
      "epoch": 0.035398230088495575,
      "grad_norm": 0.2450411468744278,
      "learning_rate": 4e-05,
      "loss": 0.2856,
      "step": 4
    },
    {
      "epoch": 0.04424778761061947,
      "grad_norm": 0.23432810604572296,
      "learning_rate": 5e-05,
      "loss": 0.2344,
      "step": 5
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 0.1882084459066391,
      "learning_rate": 6e-05,
      "loss": 0.2726,
      "step": 6
    },
    {
      "epoch": 0.061946902654867256,
      "grad_norm": 0.19094598293304443,
      "learning_rate": 7e-05,
      "loss": 0.2675,
      "step": 7
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 0.17722730338573456,
      "learning_rate": 8e-05,
      "loss": 0.2526,
      "step": 8
    },
    {
      "epoch": 0.07964601769911504,
      "grad_norm": 0.2199975848197937,
      "learning_rate": 9e-05,
      "loss": 0.2147,
      "step": 9
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 0.19510646164417267,
      "learning_rate": 0.0001,
      "loss": 0.2296,
      "step": 10
    },
    {
      "epoch": 0.09734513274336283,
      "grad_norm": 0.19899819791316986,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.2074,
      "step": 11
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 0.25875481963157654,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2139,
      "step": 12
    },
    {
      "epoch": 0.11504424778761062,
      "grad_norm": 0.21947084367275238,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.2398,
      "step": 13
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 0.25405043363571167,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.1941,
      "step": 14
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": 0.30223211646080017,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.2423,
      "step": 15
    },
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 0.2529599964618683,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2218,
      "step": 16
    },
    {
      "epoch": 0.1504424778761062,
      "grad_norm": 0.2598091959953308,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.2033,
      "step": 17
    },
    {
      "epoch": 0.1592920353982301,
      "grad_norm": 0.19598594307899475,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.2085,
      "step": 18
    },
    {
      "epoch": 0.168141592920354,
      "grad_norm": 0.23252610862255096,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2295,
      "step": 19
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 0.3308466076850891,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1959,
      "step": 20
    },
    {
      "epoch": 0.18584070796460178,
      "grad_norm": 0.27886706590652466,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.1435,
      "step": 21
    },
    {
      "epoch": 0.19469026548672566,
      "grad_norm": 0.4352017939090729,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.1981,
      "step": 22
    },
    {
      "epoch": 0.20353982300884957,
      "grad_norm": 0.3619578182697296,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.178,
      "step": 23
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": 0.3712579309940338,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.1591,
      "step": 24
    },
    {
      "epoch": 0.22123893805309736,
      "grad_norm": 0.3811175227165222,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.1726,
      "step": 25
    },
    {
      "epoch": 0.23008849557522124,
      "grad_norm": 0.5237652063369751,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.1905,
      "step": 26
    },
    {
      "epoch": 0.23893805309734514,
      "grad_norm": 0.6695637702941895,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.1897,
      "step": 27
    },
    {
      "epoch": 0.24778761061946902,
      "grad_norm": 0.9284541606903076,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.1774,
      "step": 28
    },
    {
      "epoch": 0.25663716814159293,
      "grad_norm": 0.12385310232639313,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2302,
      "step": 29
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 0.14987072348594666,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.21,
      "step": 30
    },
    {
      "epoch": 0.2743362831858407,
      "grad_norm": 0.17606878280639648,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.2232,
      "step": 31
    },
    {
      "epoch": 0.2831858407079646,
      "grad_norm": 0.17997772991657257,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2471,
      "step": 32
    },
    {
      "epoch": 0.2920353982300885,
      "grad_norm": 0.16720440983772278,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.2307,
      "step": 33
    },
    {
      "epoch": 0.3008849557522124,
      "grad_norm": 0.15251833200454712,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2366,
      "step": 34
    },
    {
      "epoch": 0.30973451327433627,
      "grad_norm": 0.15290291607379913,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2215,
      "step": 35
    },
    {
      "epoch": 0.3185840707964602,
      "grad_norm": 0.15778782963752747,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2045,
      "step": 36
    },
    {
      "epoch": 0.3274336283185841,
      "grad_norm": 0.16759589314460754,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.259,
      "step": 37
    },
    {
      "epoch": 0.336283185840708,
      "grad_norm": 0.21276544034481049,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.2068,
      "step": 38
    },
    {
      "epoch": 0.34513274336283184,
      "grad_norm": 0.1922285258769989,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2178,
      "step": 39
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.36880335211753845,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1783,
      "step": 40
    },
    {
      "epoch": 0.36283185840707965,
      "grad_norm": 0.20980305969715118,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.1853,
      "step": 41
    },
    {
      "epoch": 0.37168141592920356,
      "grad_norm": 0.1848260909318924,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.2306,
      "step": 42
    },
    {
      "epoch": 0.3805309734513274,
      "grad_norm": 0.2167561799287796,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.1959,
      "step": 43
    },
    {
      "epoch": 0.3893805309734513,
      "grad_norm": 0.21164308488368988,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2479,
      "step": 44
    },
    {
      "epoch": 0.39823008849557523,
      "grad_norm": 0.2198123037815094,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1818,
      "step": 45
    },
    {
      "epoch": 0.40707964601769914,
      "grad_norm": 0.19381862878799438,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1826,
      "step": 46
    },
    {
      "epoch": 0.415929203539823,
      "grad_norm": 0.3231579065322876,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.1963,
      "step": 47
    },
    {
      "epoch": 0.4247787610619469,
      "grad_norm": 0.2906438112258911,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.186,
      "step": 48
    },
    {
      "epoch": 0.4336283185840708,
      "grad_norm": 0.3493298888206482,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.2127,
      "step": 49
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 0.30707991123199463,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2082,
      "step": 50
    },
    {
      "epoch": 0.4424778761061947,
      "eval_loss": 0.20608103275299072,
      "eval_runtime": 14.7661,
      "eval_samples_per_second": 12.867,
      "eval_steps_per_second": 3.251,
      "step": 50
    },
    {
      "epoch": 0.45132743362831856,
      "grad_norm": 0.4123724400997162,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1713,
      "step": 51
    },
    {
      "epoch": 0.46017699115044247,
      "grad_norm": 0.2903163433074951,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.1824,
      "step": 52
    },
    {
      "epoch": 0.4690265486725664,
      "grad_norm": 0.4626249074935913,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1856,
      "step": 53
    },
    {
      "epoch": 0.4778761061946903,
      "grad_norm": 0.46229955554008484,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.1454,
      "step": 54
    },
    {
      "epoch": 0.48672566371681414,
      "grad_norm": 0.6982957720756531,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1369,
      "step": 55
    },
    {
      "epoch": 0.49557522123893805,
      "grad_norm": 0.6811181902885437,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1476,
      "step": 56
    },
    {
      "epoch": 0.504424778761062,
      "grad_norm": 0.09460745751857758,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2034,
      "step": 57
    },
    {
      "epoch": 0.5132743362831859,
      "grad_norm": 0.11980939656496048,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2113,
      "step": 58
    },
    {
      "epoch": 0.5221238938053098,
      "grad_norm": 0.1482318490743637,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2506,
      "step": 59
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.14911016821861267,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2473,
      "step": 60
    },
    {
      "epoch": 0.5398230088495575,
      "grad_norm": 0.14893217384815216,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.2099,
      "step": 61
    },
    {
      "epoch": 0.5486725663716814,
      "grad_norm": 0.16002821922302246,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.195,
      "step": 62
    },
    {
      "epoch": 0.5575221238938053,
      "grad_norm": 0.12558835744857788,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.1794,
      "step": 63
    },
    {
      "epoch": 0.5663716814159292,
      "grad_norm": 0.14984652400016785,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1839,
      "step": 64
    },
    {
      "epoch": 0.5752212389380531,
      "grad_norm": 0.1728339046239853,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2042,
      "step": 65
    },
    {
      "epoch": 0.584070796460177,
      "grad_norm": 0.16859066486358643,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1774,
      "step": 66
    },
    {
      "epoch": 0.5929203539823009,
      "grad_norm": 0.14884759485721588,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1654,
      "step": 67
    },
    {
      "epoch": 0.6017699115044248,
      "grad_norm": 0.19001953303813934,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1713,
      "step": 68
    },
    {
      "epoch": 0.6106194690265486,
      "grad_norm": 0.16848327219486237,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.1793,
      "step": 69
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 0.14906561374664307,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.2197,
      "step": 70
    },
    {
      "epoch": 0.6283185840707964,
      "grad_norm": 0.19290651381015778,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2029,
      "step": 71
    },
    {
      "epoch": 0.6371681415929203,
      "grad_norm": 0.16997268795967102,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1752,
      "step": 72
    },
    {
      "epoch": 0.6460176991150443,
      "grad_norm": 0.1547616422176361,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.1969,
      "step": 73
    },
    {
      "epoch": 0.6548672566371682,
      "grad_norm": 0.23133845627307892,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1979,
      "step": 74
    },
    {
      "epoch": 0.6637168141592921,
      "grad_norm": 0.18196874856948853,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.2,
      "step": 75
    },
    {
      "epoch": 0.672566371681416,
      "grad_norm": 0.22695907950401306,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.1907,
      "step": 76
    },
    {
      "epoch": 0.6814159292035398,
      "grad_norm": 0.22677533328533173,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.1802,
      "step": 77
    },
    {
      "epoch": 0.6902654867256637,
      "grad_norm": 0.2533175051212311,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1409,
      "step": 78
    },
    {
      "epoch": 0.6991150442477876,
      "grad_norm": 0.24189487099647522,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.1747,
      "step": 79
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.35351356863975525,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1475,
      "step": 80
    },
    {
      "epoch": 0.7168141592920354,
      "grad_norm": 0.385288804769516,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.1849,
      "step": 81
    },
    {
      "epoch": 0.7256637168141593,
      "grad_norm": 0.37728816270828247,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.1568,
      "step": 82
    },
    {
      "epoch": 0.7345132743362832,
      "grad_norm": 0.684324324131012,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.1697,
      "step": 83
    },
    {
      "epoch": 0.7433628318584071,
      "grad_norm": 0.6510435342788696,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1895,
      "step": 84
    },
    {
      "epoch": 0.7522123893805309,
      "grad_norm": 0.12220598757266998,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2151,
      "step": 85
    },
    {
      "epoch": 0.7610619469026548,
      "grad_norm": 0.13955652713775635,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1768,
      "step": 86
    },
    {
      "epoch": 0.7699115044247787,
      "grad_norm": 0.14337973296642303,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2366,
      "step": 87
    },
    {
      "epoch": 0.7787610619469026,
      "grad_norm": 0.15308284759521484,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.2057,
      "step": 88
    },
    {
      "epoch": 0.7876106194690266,
      "grad_norm": 0.13122722506523132,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.194,
      "step": 89
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 0.14602717757225037,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1873,
      "step": 90
    },
    {
      "epoch": 0.8053097345132744,
      "grad_norm": 0.1327785700559616,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1927,
      "step": 91
    },
    {
      "epoch": 0.8141592920353983,
      "grad_norm": 0.18131089210510254,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2167,
      "step": 92
    },
    {
      "epoch": 0.8230088495575221,
      "grad_norm": 0.14427438378334045,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1995,
      "step": 93
    },
    {
      "epoch": 0.831858407079646,
      "grad_norm": 0.183364138007164,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.1858,
      "step": 94
    },
    {
      "epoch": 0.8407079646017699,
      "grad_norm": 0.2019575834274292,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2105,
      "step": 95
    },
    {
      "epoch": 0.8495575221238938,
      "grad_norm": 0.16826970875263214,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1702,
      "step": 96
    },
    {
      "epoch": 0.8584070796460177,
      "grad_norm": 0.1582728922367096,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.1772,
      "step": 97
    },
    {
      "epoch": 0.8672566371681416,
      "grad_norm": 0.16862809658050537,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.209,
      "step": 98
    },
    {
      "epoch": 0.8761061946902655,
      "grad_norm": 0.17828485369682312,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2172,
      "step": 99
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 0.20762793719768524,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.1776,
      "step": 100
    },
    {
      "epoch": 0.8849557522123894,
      "eval_loss": 0.20135770738124847,
      "eval_runtime": 15.0829,
      "eval_samples_per_second": 12.597,
      "eval_steps_per_second": 3.182,
      "step": 100
    },
    {
      "epoch": 0.8938053097345132,
      "grad_norm": 0.22724394500255585,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2206,
      "step": 101
    },
    {
      "epoch": 0.9026548672566371,
      "grad_norm": 0.25747108459472656,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.178,
      "step": 102
    },
    {
      "epoch": 0.911504424778761,
      "grad_norm": 0.25320595502853394,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2044,
      "step": 103
    },
    {
      "epoch": 0.9203539823008849,
      "grad_norm": 0.24142207205295563,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.2054,
      "step": 104
    },
    {
      "epoch": 0.9292035398230089,
      "grad_norm": 0.23097047209739685,
      "learning_rate": 5e-05,
      "loss": 0.1869,
      "step": 105
    },
    {
      "epoch": 0.9380530973451328,
      "grad_norm": 0.21751967072486877,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2012,
      "step": 106
    },
    {
      "epoch": 0.9469026548672567,
      "grad_norm": 0.2848917245864868,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2065,
      "step": 107
    },
    {
      "epoch": 0.9557522123893806,
      "grad_norm": 0.330407053232193,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1547,
      "step": 108
    },
    {
      "epoch": 0.9646017699115044,
      "grad_norm": 0.3268877863883972,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1604,
      "step": 109
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 0.36891889572143555,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1299,
      "step": 110
    },
    {
      "epoch": 0.9823008849557522,
      "grad_norm": 0.5621342062950134,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.1801,
      "step": 111
    },
    {
      "epoch": 0.9911504424778761,
      "grad_norm": 0.6283679604530334,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1876,
      "step": 112
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.20243556797504425,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2144,
      "step": 113
    },
    {
      "epoch": 1.008849557522124,
      "grad_norm": 0.07589446753263474,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2007,
      "step": 114
    },
    {
      "epoch": 1.0176991150442478,
      "grad_norm": 0.1025092825293541,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.1919,
      "step": 115
    },
    {
      "epoch": 1.0265486725663717,
      "grad_norm": 0.10404093563556671,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.2213,
      "step": 116
    },
    {
      "epoch": 1.0353982300884956,
      "grad_norm": 0.10783980041742325,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1907,
      "step": 117
    },
    {
      "epoch": 1.0442477876106195,
      "grad_norm": 0.10934851318597794,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1709,
      "step": 118
    },
    {
      "epoch": 1.0530973451327434,
      "grad_norm": 0.10865036398172379,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.17,
      "step": 119
    },
    {
      "epoch": 1.0619469026548674,
      "grad_norm": 0.11573055386543274,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1939,
      "step": 120
    },
    {
      "epoch": 1.0707964601769913,
      "grad_norm": 0.10828419774770737,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.1257,
      "step": 121
    },
    {
      "epoch": 1.079646017699115,
      "grad_norm": 0.11404699087142944,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1957,
      "step": 122
    },
    {
      "epoch": 1.0884955752212389,
      "grad_norm": 0.1280486136674881,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.1696,
      "step": 123
    },
    {
      "epoch": 1.0973451327433628,
      "grad_norm": 0.12781524658203125,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1474,
      "step": 124
    },
    {
      "epoch": 1.1061946902654867,
      "grad_norm": 0.1389768272638321,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.1627,
      "step": 125
    },
    {
      "epoch": 1.1150442477876106,
      "grad_norm": 0.1442885845899582,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1538,
      "step": 126
    },
    {
      "epoch": 1.1238938053097345,
      "grad_norm": 0.18789228796958923,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.1427,
      "step": 127
    },
    {
      "epoch": 1.1327433628318584,
      "grad_norm": 0.20793196558952332,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1487,
      "step": 128
    },
    {
      "epoch": 1.1415929203539823,
      "grad_norm": 0.1436079740524292,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.1866,
      "step": 129
    },
    {
      "epoch": 1.1504424778761062,
      "grad_norm": 0.16067735850811005,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1704,
      "step": 130
    },
    {
      "epoch": 1.1592920353982301,
      "grad_norm": 0.151552215218544,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.1458,
      "step": 131
    },
    {
      "epoch": 1.168141592920354,
      "grad_norm": 0.22586102783679962,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1808,
      "step": 132
    },
    {
      "epoch": 1.176991150442478,
      "grad_norm": 0.14333344995975494,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1168,
      "step": 133
    },
    {
      "epoch": 1.1858407079646018,
      "grad_norm": 0.30307701230049133,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.1609,
      "step": 134
    },
    {
      "epoch": 1.1946902654867257,
      "grad_norm": 0.2346026450395584,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.1487,
      "step": 135
    },
    {
      "epoch": 1.2035398230088497,
      "grad_norm": 0.1818697452545166,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1192,
      "step": 136
    },
    {
      "epoch": 1.2123893805309733,
      "grad_norm": 0.20106592774391174,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0769,
      "step": 137
    },
    {
      "epoch": 1.2212389380530975,
      "grad_norm": 0.29448115825653076,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1002,
      "step": 138
    },
    {
      "epoch": 1.2300884955752212,
      "grad_norm": 0.30981120467185974,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0847,
      "step": 139
    },
    {
      "epoch": 1.238938053097345,
      "grad_norm": 0.2598690092563629,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0828,
      "step": 140
    },
    {
      "epoch": 1.247787610619469,
      "grad_norm": 0.26595327258110046,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0568,
      "step": 141
    },
    {
      "epoch": 1.2566371681415929,
      "grad_norm": 0.09937412291765213,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2261,
      "step": 142
    },
    {
      "epoch": 1.2654867256637168,
      "grad_norm": 0.10356372594833374,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1699,
      "step": 143
    },
    {
      "epoch": 1.2743362831858407,
      "grad_norm": 0.12513922154903412,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.185,
      "step": 144
    },
    {
      "epoch": 1.2831858407079646,
      "grad_norm": 0.1366388350725174,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1896,
      "step": 145
    },
    {
      "epoch": 1.2920353982300885,
      "grad_norm": 0.13733847439289093,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1558,
      "step": 146
    },
    {
      "epoch": 1.3008849557522124,
      "grad_norm": 0.14412392675876617,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.1775,
      "step": 147
    },
    {
      "epoch": 1.3097345132743363,
      "grad_norm": 0.14187094569206238,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1823,
      "step": 148
    },
    {
      "epoch": 1.3185840707964602,
      "grad_norm": 0.1554545760154724,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1697,
      "step": 149
    },
    {
      "epoch": 1.3274336283185841,
      "grad_norm": 0.16226574778556824,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.1671,
      "step": 150
    },
    {
      "epoch": 1.3274336283185841,
      "eval_loss": 0.20537112653255463,
      "eval_runtime": 14.2345,
      "eval_samples_per_second": 13.348,
      "eval_steps_per_second": 3.372,
      "step": 150
    },
    {
      "epoch": 1.336283185840708,
      "grad_norm": 0.1457233428955078,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1479,
      "step": 151
    },
    {
      "epoch": 1.3451327433628317,
      "grad_norm": 0.16633647680282593,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1638,
      "step": 152
    },
    {
      "epoch": 1.3539823008849559,
      "grad_norm": 0.17691099643707275,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1295,
      "step": 153
    },
    {
      "epoch": 1.3628318584070795,
      "grad_norm": 0.17503945529460907,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1493,
      "step": 154
    },
    {
      "epoch": 1.3716814159292037,
      "grad_norm": 0.1622057557106018,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1688,
      "step": 155
    },
    {
      "epoch": 1.3805309734513274,
      "grad_norm": 0.23045311868190765,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1787,
      "step": 156
    },
    {
      "epoch": 1.3893805309734513,
      "grad_norm": 0.1623087227344513,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.1629,
      "step": 157
    },
    {
      "epoch": 1.3982300884955752,
      "grad_norm": 0.177036851644516,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1342,
      "step": 158
    },
    {
      "epoch": 1.407079646017699,
      "grad_norm": 0.17767557501792908,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.1707,
      "step": 159
    },
    {
      "epoch": 1.415929203539823,
      "grad_norm": 0.1629488468170166,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1465,
      "step": 160
    },
    {
      "epoch": 1.424778761061947,
      "grad_norm": 0.2114926278591156,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.1517,
      "step": 161
    },
    {
      "epoch": 1.4336283185840708,
      "grad_norm": 0.2246023565530777,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1222,
      "step": 162
    },
    {
      "epoch": 1.4424778761061947,
      "grad_norm": 0.19133539497852325,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1035,
      "step": 163
    },
    {
      "epoch": 1.4513274336283186,
      "grad_norm": 0.2458537369966507,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.123,
      "step": 164
    },
    {
      "epoch": 1.4601769911504425,
      "grad_norm": 0.22594396770000458,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.1133,
      "step": 165
    },
    {
      "epoch": 1.4690265486725664,
      "grad_norm": 0.34753674268722534,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0738,
      "step": 166
    },
    {
      "epoch": 1.4778761061946903,
      "grad_norm": 0.48241710662841797,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0982,
      "step": 167
    },
    {
      "epoch": 1.4867256637168142,
      "grad_norm": 0.5305927395820618,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1073,
      "step": 168
    },
    {
      "epoch": 1.495575221238938,
      "grad_norm": 0.5349655151367188,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0796,
      "step": 169
    },
    {
      "epoch": 1.504424778761062,
      "grad_norm": 0.10294822603464127,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1859,
      "step": 170
    },
    {
      "epoch": 1.5132743362831858,
      "grad_norm": 0.11213697493076324,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.1956,
      "step": 171
    },
    {
      "epoch": 1.5221238938053099,
      "grad_norm": 0.12202180176973343,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2251,
      "step": 172
    },
    {
      "epoch": 1.5309734513274336,
      "grad_norm": 0.1253415048122406,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.1898,
      "step": 173
    },
    {
      "epoch": 1.5398230088495575,
      "grad_norm": 0.12054889649152756,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.202,
      "step": 174
    },
    {
      "epoch": 1.5486725663716814,
      "grad_norm": 0.15695643424987793,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2027,
      "step": 175
    },
    {
      "epoch": 1.5575221238938053,
      "grad_norm": 0.1559077501296997,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.163,
      "step": 176
    },
    {
      "epoch": 1.5663716814159292,
      "grad_norm": 0.14091414213180542,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.1694,
      "step": 177
    },
    {
      "epoch": 1.575221238938053,
      "grad_norm": 0.15416966378688812,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.1775,
      "step": 178
    },
    {
      "epoch": 1.584070796460177,
      "grad_norm": 0.15196822583675385,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.1868,
      "step": 179
    },
    {
      "epoch": 1.592920353982301,
      "grad_norm": 0.16568799316883087,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1412,
      "step": 180
    },
    {
      "epoch": 1.6017699115044248,
      "grad_norm": 0.16400931775569916,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1763,
      "step": 181
    },
    {
      "epoch": 1.6106194690265485,
      "grad_norm": 0.19451814889907837,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.138,
      "step": 182
    },
    {
      "epoch": 1.6194690265486726,
      "grad_norm": 0.16744844615459442,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2039,
      "step": 183
    },
    {
      "epoch": 1.6283185840707963,
      "grad_norm": 0.16755437850952148,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2158,
      "step": 184
    },
    {
      "epoch": 1.6371681415929205,
      "grad_norm": 0.1991066336631775,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1388,
      "step": 185
    },
    {
      "epoch": 1.6460176991150441,
      "grad_norm": 0.1611371636390686,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1483,
      "step": 186
    },
    {
      "epoch": 1.6548672566371683,
      "grad_norm": 0.16671857237815857,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.1249,
      "step": 187
    },
    {
      "epoch": 1.663716814159292,
      "grad_norm": 0.19241225719451904,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1399,
      "step": 188
    },
    {
      "epoch": 1.672566371681416,
      "grad_norm": 0.19909925758838654,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.1436,
      "step": 189
    },
    {
      "epoch": 1.6814159292035398,
      "grad_norm": 0.2518151104450226,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1196,
      "step": 190
    },
    {
      "epoch": 1.6902654867256637,
      "grad_norm": 0.21058769524097443,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.1325,
      "step": 191
    },
    {
      "epoch": 1.6991150442477876,
      "grad_norm": 0.33680981397628784,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.1332,
      "step": 192
    },
    {
      "epoch": 1.7079646017699115,
      "grad_norm": 0.2551138699054718,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.1008,
      "step": 193
    },
    {
      "epoch": 1.7168141592920354,
      "grad_norm": 0.27922606468200684,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.089,
      "step": 194
    },
    {
      "epoch": 1.7256637168141593,
      "grad_norm": 0.2368880957365036,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.1068,
      "step": 195
    },
    {
      "epoch": 1.7345132743362832,
      "grad_norm": 0.6221703886985779,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0808,
      "step": 196
    },
    {
      "epoch": 1.7433628318584071,
      "grad_norm": 0.8940281867980957,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0567,
      "step": 197
    },
    {
      "epoch": 1.752212389380531,
      "grad_norm": 0.08936067670583725,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.212,
      "step": 198
    },
    {
      "epoch": 1.7610619469026547,
      "grad_norm": 0.1024467796087265,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.1578,
      "step": 199
    },
    {
      "epoch": 1.7699115044247788,
      "grad_norm": 0.13019438087940216,
      "learning_rate": 0.0,
      "loss": 0.2094,
      "step": 200
    },
    {
      "epoch": 1.7699115044247788,
      "eval_loss": 0.20174625515937805,
      "eval_runtime": 15.0583,
      "eval_samples_per_second": 12.618,
      "eval_steps_per_second": 3.188,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9122057636675584e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}