{
  "best_metric": 0.06903418898582458,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06462557557153244,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032312787785766214,
      "grad_norm": 3.0848917961120605,
      "learning_rate": 1e-05,
      "loss": 1.6114,
      "step": 1
    },
    {
      "epoch": 0.00032312787785766214,
      "eval_loss": 3.03678560256958,
      "eval_runtime": 364.1332,
      "eval_samples_per_second": 14.316,
      "eval_steps_per_second": 3.581,
      "step": 1
    },
    {
      "epoch": 0.0006462557557153243,
      "grad_norm": 3.4082212448120117,
      "learning_rate": 2e-05,
      "loss": 1.9605,
      "step": 2
    },
    {
      "epoch": 0.0009693836335729865,
      "grad_norm": 3.9537131786346436,
      "learning_rate": 3e-05,
      "loss": 2.0449,
      "step": 3
    },
    {
      "epoch": 0.0012925115114306486,
      "grad_norm": 3.5058693885803223,
      "learning_rate": 4e-05,
      "loss": 2.0535,
      "step": 4
    },
    {
      "epoch": 0.0016156393892883109,
      "grad_norm": 2.419360876083374,
      "learning_rate": 5e-05,
      "loss": 1.7273,
      "step": 5
    },
    {
      "epoch": 0.001938767267145973,
      "grad_norm": 2.948573112487793,
      "learning_rate": 6e-05,
      "loss": 1.8006,
      "step": 6
    },
    {
      "epoch": 0.0022618951450036353,
      "grad_norm": 2.8819689750671387,
      "learning_rate": 7e-05,
      "loss": 1.4693,
      "step": 7
    },
    {
      "epoch": 0.002585023022861297,
      "grad_norm": 5.152225494384766,
      "learning_rate": 8e-05,
      "loss": 1.1418,
      "step": 8
    },
    {
      "epoch": 0.0029081509007189595,
      "grad_norm": 4.3640971183776855,
      "learning_rate": 9e-05,
      "loss": 0.8651,
      "step": 9
    },
    {
      "epoch": 0.0032312787785766218,
      "grad_norm": 1.1843187808990479,
      "learning_rate": 0.0001,
      "loss": 0.6901,
      "step": 10
    },
    {
      "epoch": 0.003554406656434284,
      "grad_norm": 2.418196678161621,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6168,
      "step": 11
    },
    {
      "epoch": 0.003877534534291946,
      "grad_norm": 3.5061588287353516,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5335,
      "step": 12
    },
    {
      "epoch": 0.004200662412149608,
      "grad_norm": 1.7243684530258179,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5621,
      "step": 13
    },
    {
      "epoch": 0.0045237902900072706,
      "grad_norm": 0.9006369113922119,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.3937,
      "step": 14
    },
    {
      "epoch": 0.004846918167864932,
      "grad_norm": 0.950775682926178,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.3844,
      "step": 15
    },
    {
      "epoch": 0.005170046045722594,
      "grad_norm": 1.2679424285888672,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4244,
      "step": 16
    },
    {
      "epoch": 0.005493173923580257,
      "grad_norm": 0.8518214225769043,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3656,
      "step": 17
    },
    {
      "epoch": 0.005816301801437919,
      "grad_norm": 0.8720356822013855,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.2831,
      "step": 18
    },
    {
      "epoch": 0.006139429679295582,
      "grad_norm": 0.9024807810783386,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2469,
      "step": 19
    },
    {
      "epoch": 0.0064625575571532435,
      "grad_norm": 0.9114508032798767,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.2396,
      "step": 20
    },
    {
      "epoch": 0.006785685435010905,
      "grad_norm": 0.8610773682594299,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.2885,
      "step": 21
    },
    {
      "epoch": 0.007108813312868568,
      "grad_norm": 0.6697067618370056,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2033,
      "step": 22
    },
    {
      "epoch": 0.00743194119072623,
      "grad_norm": 0.7979234457015991,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.2208,
      "step": 23
    },
    {
      "epoch": 0.007755069068583892,
      "grad_norm": 0.77222740650177,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2273,
      "step": 24
    },
    {
      "epoch": 0.008078196946441555,
      "grad_norm": 0.7511534690856934,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.204,
      "step": 25
    },
    {
      "epoch": 0.008401324824299216,
      "grad_norm": 0.8124529123306274,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.2155,
      "step": 26
    },
    {
      "epoch": 0.008724452702156878,
      "grad_norm": 0.7650706768035889,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.1879,
      "step": 27
    },
    {
      "epoch": 0.009047580580014541,
      "grad_norm": 0.8532075881958008,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2147,
      "step": 28
    },
    {
      "epoch": 0.009370708457872202,
      "grad_norm": 0.653527557849884,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1648,
      "step": 29
    },
    {
      "epoch": 0.009693836335729865,
      "grad_norm": 0.6346688866615295,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.1888,
      "step": 30
    },
    {
      "epoch": 0.010016964213587528,
      "grad_norm": 0.6100589036941528,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.1771,
      "step": 31
    },
    {
      "epoch": 0.010340092091445189,
      "grad_norm": 0.7241214513778687,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.1831,
      "step": 32
    },
    {
      "epoch": 0.010663219969302851,
      "grad_norm": 0.5132176876068115,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.1331,
      "step": 33
    },
    {
      "epoch": 0.010986347847160514,
      "grad_norm": 0.5473405122756958,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.1835,
      "step": 34
    },
    {
      "epoch": 0.011309475725018175,
      "grad_norm": 0.6280067563056946,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.1681,
      "step": 35
    },
    {
      "epoch": 0.011632603602875838,
      "grad_norm": 0.6983142495155334,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1614,
      "step": 36
    },
    {
      "epoch": 0.0119557314807335,
      "grad_norm": 0.6600526571273804,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.1698,
      "step": 37
    },
    {
      "epoch": 0.012278859358591163,
      "grad_norm": 3.86894154548645,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.143,
      "step": 38
    },
    {
      "epoch": 0.012601987236448824,
      "grad_norm": 0.6045129895210266,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.1668,
      "step": 39
    },
    {
      "epoch": 0.012925115114306487,
      "grad_norm": 0.4466351866722107,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1077,
      "step": 40
    },
    {
      "epoch": 0.01324824299216415,
      "grad_norm": 0.5276210308074951,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0895,
      "step": 41
    },
    {
      "epoch": 0.01357137087002181,
      "grad_norm": 0.5885831117630005,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.1413,
      "step": 42
    },
    {
      "epoch": 0.013894498747879474,
      "grad_norm": 0.587961733341217,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.1587,
      "step": 43
    },
    {
      "epoch": 0.014217626625737136,
      "grad_norm": 0.6596927046775818,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1235,
      "step": 44
    },
    {
      "epoch": 0.014540754503594797,
      "grad_norm": 0.6219716668128967,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1305,
      "step": 45
    },
    {
      "epoch": 0.01486388238145246,
      "grad_norm": 1.084957480430603,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.1847,
      "step": 46
    },
    {
      "epoch": 0.015187010259310123,
      "grad_norm": 0.5637949705123901,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.1116,
      "step": 47
    },
    {
      "epoch": 0.015510138137167784,
      "grad_norm": 0.7025253176689148,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.115,
      "step": 48
    },
    {
      "epoch": 0.015833266015025445,
      "grad_norm": 0.8570723533630371,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.1472,
      "step": 49
    },
    {
      "epoch": 0.01615639389288311,
      "grad_norm": 1.651252031326294,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2155,
      "step": 50
    },
    {
      "epoch": 0.01615639389288311,
      "eval_loss": 0.17040474712848663,
      "eval_runtime": 366.1493,
      "eval_samples_per_second": 14.237,
      "eval_steps_per_second": 3.561,
      "step": 50
    },
    {
      "epoch": 0.01647952177074077,
      "grad_norm": 1.1109765768051147,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.2743,
      "step": 51
    },
    {
      "epoch": 0.01680264964859843,
      "grad_norm": 0.7078374028205872,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.1849,
      "step": 52
    },
    {
      "epoch": 0.017125777526456096,
      "grad_norm": 0.6006873846054077,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1704,
      "step": 53
    },
    {
      "epoch": 0.017448905404313757,
      "grad_norm": 0.46824806928634644,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.1408,
      "step": 54
    },
    {
      "epoch": 0.017772033282171418,
      "grad_norm": 0.607595682144165,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.156,
      "step": 55
    },
    {
      "epoch": 0.018095161160029082,
      "grad_norm": 0.6533870697021484,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1558,
      "step": 56
    },
    {
      "epoch": 0.018418289037886743,
      "grad_norm": 0.5653566122055054,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.1519,
      "step": 57
    },
    {
      "epoch": 0.018741416915744404,
      "grad_norm": 0.5329752564430237,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1414,
      "step": 58
    },
    {
      "epoch": 0.01906454479360207,
      "grad_norm": 0.4753928482532501,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1466,
      "step": 59
    },
    {
      "epoch": 0.01938767267145973,
      "grad_norm": 0.41759729385375977,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.1502,
      "step": 60
    },
    {
      "epoch": 0.01971080054931739,
      "grad_norm": 0.4564923942089081,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1302,
      "step": 61
    },
    {
      "epoch": 0.020033928427175055,
      "grad_norm": 0.5023769736289978,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1304,
      "step": 62
    },
    {
      "epoch": 0.020357056305032716,
      "grad_norm": 0.4274086654186249,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.11,
      "step": 63
    },
    {
      "epoch": 0.020680184182890377,
      "grad_norm": 0.48943373560905457,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1195,
      "step": 64
    },
    {
      "epoch": 0.02100331206074804,
      "grad_norm": 1.2140369415283203,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0953,
      "step": 65
    },
    {
      "epoch": 0.021326439938605703,
      "grad_norm": 0.6015234589576721,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1819,
      "step": 66
    },
    {
      "epoch": 0.021649567816463364,
      "grad_norm": 1.5427082777023315,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0892,
      "step": 67
    },
    {
      "epoch": 0.021972695694321028,
      "grad_norm": 0.4848945438861847,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1304,
      "step": 68
    },
    {
      "epoch": 0.02229582357217869,
      "grad_norm": 0.3890538215637207,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0753,
      "step": 69
    },
    {
      "epoch": 0.02261895145003635,
      "grad_norm": 0.5242356657981873,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.1413,
      "step": 70
    },
    {
      "epoch": 0.022942079327894015,
      "grad_norm": 0.4723387658596039,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.1146,
      "step": 71
    },
    {
      "epoch": 0.023265207205751676,
      "grad_norm": 0.3772827982902527,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1061,
      "step": 72
    },
    {
      "epoch": 0.023588335083609337,
      "grad_norm": 0.4396408498287201,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0924,
      "step": 73
    },
    {
      "epoch": 0.023911462961467,
      "grad_norm": 0.4412914216518402,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0936,
      "step": 74
    },
    {
      "epoch": 0.024234590839324662,
      "grad_norm": 0.4144344925880432,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0926,
      "step": 75
    },
    {
      "epoch": 0.024557718717182327,
      "grad_norm": 0.4863596260547638,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.1267,
      "step": 76
    },
    {
      "epoch": 0.024880846595039988,
      "grad_norm": 0.5235720276832581,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.1202,
      "step": 77
    },
    {
      "epoch": 0.02520397447289765,
      "grad_norm": 0.3919348120689392,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0956,
      "step": 78
    },
    {
      "epoch": 0.025527102350755313,
      "grad_norm": 0.2920311987400055,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0746,
      "step": 79
    },
    {
      "epoch": 0.025850230228612974,
      "grad_norm": 0.4613044857978821,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1015,
      "step": 80
    },
    {
      "epoch": 0.026173358106470635,
      "grad_norm": 0.36731651425361633,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.1003,
      "step": 81
    },
    {
      "epoch": 0.0264964859843283,
      "grad_norm": 0.36551782488822937,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0575,
      "step": 82
    },
    {
      "epoch": 0.02681961386218596,
      "grad_norm": 0.3591379225254059,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0833,
      "step": 83
    },
    {
      "epoch": 0.02714274174004362,
      "grad_norm": 0.4948481321334839,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0945,
      "step": 84
    },
    {
      "epoch": 0.027465869617901286,
      "grad_norm": 0.49430689215660095,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0905,
      "step": 85
    },
    {
      "epoch": 0.027788997495758947,
      "grad_norm": 0.5038220286369324,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0766,
      "step": 86
    },
    {
      "epoch": 0.028112125373616608,
      "grad_norm": 0.46767106652259827,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0918,
      "step": 87
    },
    {
      "epoch": 0.028435253251474273,
      "grad_norm": 0.47734349966049194,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1032,
      "step": 88
    },
    {
      "epoch": 0.028758381129331934,
      "grad_norm": 0.4050719439983368,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0775,
      "step": 89
    },
    {
      "epoch": 0.029081509007189595,
      "grad_norm": 0.7349752187728882,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0959,
      "step": 90
    },
    {
      "epoch": 0.02940463688504726,
      "grad_norm": 0.444937139749527,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0964,
      "step": 91
    },
    {
      "epoch": 0.02972776476290492,
      "grad_norm": 0.5027516484260559,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0859,
      "step": 92
    },
    {
      "epoch": 0.03005089264076258,
      "grad_norm": 0.5471087098121643,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.11,
      "step": 93
    },
    {
      "epoch": 0.030374020518620246,
      "grad_norm": 0.5404782891273499,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.1233,
      "step": 94
    },
    {
      "epoch": 0.030697148396477907,
      "grad_norm": 0.37752440571784973,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0596,
      "step": 95
    },
    {
      "epoch": 0.031020276274335568,
      "grad_norm": 0.4467316269874573,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0649,
      "step": 96
    },
    {
      "epoch": 0.03134340415219323,
      "grad_norm": 0.4350702166557312,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0673,
      "step": 97
    },
    {
      "epoch": 0.03166653203005089,
      "grad_norm": 0.34127622842788696,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0622,
      "step": 98
    },
    {
      "epoch": 0.03198965990790856,
      "grad_norm": 0.5703495740890503,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0712,
      "step": 99
    },
    {
      "epoch": 0.03231278778576622,
      "grad_norm": 0.6635679006576538,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0926,
      "step": 100
    },
    {
      "epoch": 0.03231278778576622,
      "eval_loss": 0.10626650601625443,
      "eval_runtime": 366.3307,
      "eval_samples_per_second": 14.23,
      "eval_steps_per_second": 3.56,
      "step": 100
    },
    {
      "epoch": 0.03263591566362388,
      "grad_norm": 0.5676780939102173,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.1475,
      "step": 101
    },
    {
      "epoch": 0.03295904354148154,
      "grad_norm": 0.585024356842041,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.1504,
      "step": 102
    },
    {
      "epoch": 0.0332821714193392,
      "grad_norm": 0.4668387770652771,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.1143,
      "step": 103
    },
    {
      "epoch": 0.03360529929719686,
      "grad_norm": 0.5734906792640686,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1173,
      "step": 104
    },
    {
      "epoch": 0.03392842717505453,
      "grad_norm": 0.40861037373542786,
      "learning_rate": 5e-05,
      "loss": 0.1063,
      "step": 105
    },
    {
      "epoch": 0.03425155505291219,
      "grad_norm": 0.5824266672134399,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1149,
      "step": 106
    },
    {
      "epoch": 0.03457468293076985,
      "grad_norm": 0.47003471851348877,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0845,
      "step": 107
    },
    {
      "epoch": 0.034897810808627514,
      "grad_norm": 0.41306978464126587,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1056,
      "step": 108
    },
    {
      "epoch": 0.035220938686485175,
      "grad_norm": 0.37225106358528137,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1007,
      "step": 109
    },
    {
      "epoch": 0.035544066564342836,
      "grad_norm": 0.4392073452472687,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1147,
      "step": 110
    },
    {
      "epoch": 0.0358671944422005,
      "grad_norm": 0.4432167112827301,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0796,
      "step": 111
    },
    {
      "epoch": 0.036190322320058164,
      "grad_norm": 0.32287082076072693,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0822,
      "step": 112
    },
    {
      "epoch": 0.036513450197915825,
      "grad_norm": 0.32965928316116333,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0944,
      "step": 113
    },
    {
      "epoch": 0.036836578075773486,
      "grad_norm": 0.3577788472175598,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0822,
      "step": 114
    },
    {
      "epoch": 0.03715970595363115,
      "grad_norm": 0.2836371660232544,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0691,
      "step": 115
    },
    {
      "epoch": 0.03748283383148881,
      "grad_norm": 0.3925090432167053,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1143,
      "step": 116
    },
    {
      "epoch": 0.037805961709346476,
      "grad_norm": 0.33732157945632935,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0896,
      "step": 117
    },
    {
      "epoch": 0.03812908958720414,
      "grad_norm": 0.35552817583084106,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0857,
      "step": 118
    },
    {
      "epoch": 0.0384522174650618,
      "grad_norm": 0.4994976818561554,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0914,
      "step": 119
    },
    {
      "epoch": 0.03877534534291946,
      "grad_norm": 0.33763742446899414,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0622,
      "step": 120
    },
    {
      "epoch": 0.03909847322077712,
      "grad_norm": 0.3153921961784363,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0736,
      "step": 121
    },
    {
      "epoch": 0.03942160109863478,
      "grad_norm": 0.3290238678455353,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0564,
      "step": 122
    },
    {
      "epoch": 0.03974472897649245,
      "grad_norm": 0.35626235604286194,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0801,
      "step": 123
    },
    {
      "epoch": 0.04006785685435011,
      "grad_norm": 0.36998510360717773,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0873,
      "step": 124
    },
    {
      "epoch": 0.04039098473220777,
      "grad_norm": 0.48902133107185364,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0933,
      "step": 125
    },
    {
      "epoch": 0.04071411261006543,
      "grad_norm": 0.3316888213157654,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0665,
      "step": 126
    },
    {
      "epoch": 0.04103724048792309,
      "grad_norm": 0.3331412076950073,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0667,
      "step": 127
    },
    {
      "epoch": 0.041360368365780754,
      "grad_norm": 0.36715954542160034,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0747,
      "step": 128
    },
    {
      "epoch": 0.04168349624363842,
      "grad_norm": 0.520473301410675,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0738,
      "step": 129
    },
    {
      "epoch": 0.04200662412149608,
      "grad_norm": 0.3248518407344818,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0612,
      "step": 130
    },
    {
      "epoch": 0.042329751999353744,
      "grad_norm": 0.4131891429424286,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.096,
      "step": 131
    },
    {
      "epoch": 0.042652879877211405,
      "grad_norm": 0.43788546323776245,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0859,
      "step": 132
    },
    {
      "epoch": 0.042976007755069066,
      "grad_norm": 0.4722546339035034,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1087,
      "step": 133
    },
    {
      "epoch": 0.04329913563292673,
      "grad_norm": 0.3699047267436981,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0498,
      "step": 134
    },
    {
      "epoch": 0.043622263510784395,
      "grad_norm": 0.37380972504615784,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.068,
      "step": 135
    },
    {
      "epoch": 0.043945391388642056,
      "grad_norm": 0.390256404876709,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0717,
      "step": 136
    },
    {
      "epoch": 0.04426851926649972,
      "grad_norm": 0.35162919759750366,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0545,
      "step": 137
    },
    {
      "epoch": 0.04459164714435738,
      "grad_norm": 0.2525109648704529,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0359,
      "step": 138
    },
    {
      "epoch": 0.04491477502221504,
      "grad_norm": 0.3911828398704529,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0776,
      "step": 139
    },
    {
      "epoch": 0.0452379029000727,
      "grad_norm": 0.3903822600841522,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0898,
      "step": 140
    },
    {
      "epoch": 0.04556103077793037,
      "grad_norm": 0.3434182405471802,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.05,
      "step": 141
    },
    {
      "epoch": 0.04588415865578803,
      "grad_norm": 0.4747754633426666,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0724,
      "step": 142
    },
    {
      "epoch": 0.04620728653364569,
      "grad_norm": 0.3391111195087433,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0733,
      "step": 143
    },
    {
      "epoch": 0.04653041441150335,
      "grad_norm": 0.3657680153846741,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0811,
      "step": 144
    },
    {
      "epoch": 0.04685354228936101,
      "grad_norm": 0.2696090638637543,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0379,
      "step": 145
    },
    {
      "epoch": 0.04717667016721867,
      "grad_norm": 0.4774753153324127,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0819,
      "step": 146
    },
    {
      "epoch": 0.04749979804507634,
      "grad_norm": 0.4513331651687622,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0621,
      "step": 147
    },
    {
      "epoch": 0.047822925922934,
      "grad_norm": 0.3730250298976898,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0609,
      "step": 148
    },
    {
      "epoch": 0.04814605380079166,
      "grad_norm": 0.6400455236434937,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0833,
      "step": 149
    },
    {
      "epoch": 0.048469181678649324,
      "grad_norm": 0.6213532090187073,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0618,
      "step": 150
    },
    {
      "epoch": 0.048469181678649324,
      "eval_loss": 0.07553370296955109,
      "eval_runtime": 366.4081,
      "eval_samples_per_second": 14.227,
      "eval_steps_per_second": 3.559,
      "step": 150
    },
    {
      "epoch": 0.048792309556506985,
      "grad_norm": 0.2926478385925293,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0653,
      "step": 151
    },
    {
      "epoch": 0.04911543743436465,
      "grad_norm": 0.38548150658607483,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1036,
      "step": 152
    },
    {
      "epoch": 0.049438565312222314,
      "grad_norm": 0.43106555938720703,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1232,
      "step": 153
    },
    {
      "epoch": 0.049761693190079975,
      "grad_norm": 0.4741581082344055,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0886,
      "step": 154
    },
    {
      "epoch": 0.050084821067937636,
      "grad_norm": 0.45233720541000366,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0758,
      "step": 155
    },
    {
      "epoch": 0.0504079489457953,
      "grad_norm": 0.48990124464035034,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.118,
      "step": 156
    },
    {
      "epoch": 0.05073107682365296,
      "grad_norm": 0.3919442892074585,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.1098,
      "step": 157
    },
    {
      "epoch": 0.051054204701510626,
      "grad_norm": 0.4114181399345398,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0996,
      "step": 158
    },
    {
      "epoch": 0.05137733257936829,
      "grad_norm": 0.36848145723342896,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0932,
      "step": 159
    },
    {
      "epoch": 0.05170046045722595,
      "grad_norm": 0.34357205033302307,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0898,
      "step": 160
    },
    {
      "epoch": 0.05202358833508361,
      "grad_norm": 0.36756712198257446,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0775,
      "step": 161
    },
    {
      "epoch": 0.05234671621294127,
      "grad_norm": 0.4343879818916321,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1048,
      "step": 162
    },
    {
      "epoch": 0.05266984409079893,
      "grad_norm": 0.3662625849246979,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0862,
      "step": 163
    },
    {
      "epoch": 0.0529929719686566,
      "grad_norm": 0.35093265771865845,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0818,
      "step": 164
    },
    {
      "epoch": 0.05331609984651426,
      "grad_norm": 0.33757466077804565,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0865,
      "step": 165
    },
    {
      "epoch": 0.05363922772437192,
      "grad_norm": 0.29732653498649597,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0517,
      "step": 166
    },
    {
      "epoch": 0.05396235560222958,
      "grad_norm": 0.28539735078811646,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0536,
      "step": 167
    },
    {
      "epoch": 0.05428548348008724,
      "grad_norm": 0.3322267532348633,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0807,
      "step": 168
    },
    {
      "epoch": 0.054608611357944904,
      "grad_norm": 0.2661389708518982,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0581,
      "step": 169
    },
    {
      "epoch": 0.05493173923580257,
      "grad_norm": 0.30726733803749084,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0683,
      "step": 170
    },
    {
      "epoch": 0.05525486711366023,
      "grad_norm": 0.3910558521747589,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0733,
      "step": 171
    },
    {
      "epoch": 0.055577994991517894,
      "grad_norm": 0.37618038058280945,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.087,
      "step": 172
    },
    {
      "epoch": 0.055901122869375555,
      "grad_norm": 0.4201327860355377,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0956,
      "step": 173
    },
    {
      "epoch": 0.056224250747233216,
      "grad_norm": 0.3308406472206116,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0605,
      "step": 174
    },
    {
      "epoch": 0.05654737862509088,
      "grad_norm": 0.3730684816837311,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.067,
      "step": 175
    },
    {
      "epoch": 0.056870506502948545,
      "grad_norm": 0.39362606406211853,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0967,
      "step": 176
    },
    {
      "epoch": 0.057193634380806206,
      "grad_norm": 0.411339670419693,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0779,
      "step": 177
    },
    {
      "epoch": 0.05751676225866387,
      "grad_norm": 0.2625620365142822,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.063,
      "step": 178
    },
    {
      "epoch": 0.05783989013652153,
      "grad_norm": 0.3191346228122711,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0566,
      "step": 179
    },
    {
      "epoch": 0.05816301801437919,
      "grad_norm": 0.370079904794693,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0641,
      "step": 180
    },
    {
      "epoch": 0.05848614589223685,
      "grad_norm": 0.25920650362968445,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0579,
      "step": 181
    },
    {
      "epoch": 0.05880927377009452,
      "grad_norm": 0.2454715222120285,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0344,
      "step": 182
    },
    {
      "epoch": 0.05913240164795218,
      "grad_norm": 0.31150022149086,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0611,
      "step": 183
    },
    {
      "epoch": 0.05945552952580984,
      "grad_norm": 0.31014448404312134,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0522,
      "step": 184
    },
    {
      "epoch": 0.0597786574036675,
      "grad_norm": 0.24095036089420319,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0307,
      "step": 185
    },
    {
      "epoch": 0.06010178528152516,
      "grad_norm": 0.31386157870292664,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0538,
      "step": 186
    },
    {
      "epoch": 0.06042491315938282,
      "grad_norm": 0.2709448039531708,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0494,
      "step": 187
    },
    {
      "epoch": 0.06074804103724049,
      "grad_norm": 0.3662849962711334,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0606,
      "step": 188
    },
    {
      "epoch": 0.06107116891509815,
      "grad_norm": 0.33949288725852966,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0467,
      "step": 189
    },
    {
      "epoch": 0.06139429679295581,
      "grad_norm": 0.3181162476539612,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0549,
      "step": 190
    },
    {
      "epoch": 0.061717424670813474,
      "grad_norm": 0.3944844603538513,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0681,
      "step": 191
    },
    {
      "epoch": 0.062040552548671135,
      "grad_norm": 0.2859078645706177,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0616,
      "step": 192
    },
    {
      "epoch": 0.062363680426528796,
      "grad_norm": 0.4732500910758972,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0446,
      "step": 193
    },
    {
      "epoch": 0.06268680830438646,
      "grad_norm": 0.36734500527381897,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0462,
      "step": 194
    },
    {
      "epoch": 0.06300993618224413,
      "grad_norm": 0.3554672300815582,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0588,
      "step": 195
    },
    {
      "epoch": 0.06333306406010178,
      "grad_norm": 0.3695184886455536,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0346,
      "step": 196
    },
    {
      "epoch": 0.06365619193795945,
      "grad_norm": 0.39029330015182495,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0466,
      "step": 197
    },
    {
      "epoch": 0.06397931981581712,
      "grad_norm": 0.5003397464752197,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0713,
      "step": 198
    },
    {
      "epoch": 0.06430244769367477,
      "grad_norm": 0.634792149066925,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.085,
      "step": 199
    },
    {
      "epoch": 0.06462557557153244,
      "grad_norm": 0.8271347284317017,
      "learning_rate": 0.0,
      "loss": 0.1393,
      "step": 200
    },
    {
      "epoch": 0.06462557557153244,
      "eval_loss": 0.06903418898582458,
      "eval_runtime": 366.3262,
      "eval_samples_per_second": 14.23,
      "eval_steps_per_second": 3.56,
      "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": 2.664317787958149e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}