{
  "best_metric": 0.2264130413532257,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06816051801993696,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034080259009968474,
      "grad_norm": 10.112625122070312,
      "learning_rate": 1e-05,
      "loss": 0.6867,
      "step": 1
    },
    {
      "epoch": 0.00034080259009968474,
      "eval_loss": 1.805891752243042,
      "eval_runtime": 85.4632,
      "eval_samples_per_second": 57.826,
      "eval_steps_per_second": 14.462,
      "step": 1
    },
    {
      "epoch": 0.0006816051801993695,
      "grad_norm": 16.574304580688477,
      "learning_rate": 2e-05,
      "loss": 0.808,
      "step": 2
    },
    {
      "epoch": 0.0010224077702990543,
      "grad_norm": 17.105018615722656,
      "learning_rate": 3e-05,
      "loss": 0.8031,
      "step": 3
    },
    {
      "epoch": 0.001363210360398739,
      "grad_norm": 9.671582221984863,
      "learning_rate": 4e-05,
      "loss": 0.5171,
      "step": 4
    },
    {
      "epoch": 0.0017040129504984239,
      "grad_norm": 10.87792682647705,
      "learning_rate": 5e-05,
      "loss": 0.3643,
      "step": 5
    },
    {
      "epoch": 0.0020448155405981086,
      "grad_norm": 5.795124530792236,
      "learning_rate": 6e-05,
      "loss": 0.2299,
      "step": 6
    },
    {
      "epoch": 0.0023856181306977932,
      "grad_norm": 1.8813679218292236,
      "learning_rate": 7e-05,
      "loss": 0.1155,
      "step": 7
    },
    {
      "epoch": 0.002726420720797478,
      "grad_norm": 2.014850616455078,
      "learning_rate": 8e-05,
      "loss": 0.1318,
      "step": 8
    },
    {
      "epoch": 0.0030672233108971626,
      "grad_norm": 2.0936801433563232,
      "learning_rate": 9e-05,
      "loss": 0.1499,
      "step": 9
    },
    {
      "epoch": 0.0034080259009968477,
      "grad_norm": 2.4788641929626465,
      "learning_rate": 0.0001,
      "loss": 0.1697,
      "step": 10
    },
    {
      "epoch": 0.0037488284910965324,
      "grad_norm": 2.2220137119293213,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.1447,
      "step": 11
    },
    {
      "epoch": 0.004089631081196217,
      "grad_norm": 2.0284512042999268,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.1415,
      "step": 12
    },
    {
      "epoch": 0.004430433671295902,
      "grad_norm": 2.153362274169922,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.1674,
      "step": 13
    },
    {
      "epoch": 0.0047712362613955865,
      "grad_norm": 4.5698089599609375,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2276,
      "step": 14
    },
    {
      "epoch": 0.005112038851495271,
      "grad_norm": 3.3978638648986816,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.1841,
      "step": 15
    },
    {
      "epoch": 0.005452841441594956,
      "grad_norm": 1.8542648553848267,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1621,
      "step": 16
    },
    {
      "epoch": 0.0057936440316946405,
      "grad_norm": 1.5809046030044556,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.1634,
      "step": 17
    },
    {
      "epoch": 0.006134446621794325,
      "grad_norm": 3.9050400257110596,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.2294,
      "step": 18
    },
    {
      "epoch": 0.006475249211894011,
      "grad_norm": 1.5686297416687012,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.1677,
      "step": 19
    },
    {
      "epoch": 0.0068160518019936955,
      "grad_norm": 1.5679619312286377,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.2146,
      "step": 20
    },
    {
      "epoch": 0.00715685439209338,
      "grad_norm": 1.4527581930160522,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.1714,
      "step": 21
    },
    {
      "epoch": 0.007497656982193065,
      "grad_norm": 1.5882984399795532,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2135,
      "step": 22
    },
    {
      "epoch": 0.007838459572292749,
      "grad_norm": 1.7456451654434204,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.2184,
      "step": 23
    },
    {
      "epoch": 0.008179262162392434,
      "grad_norm": 1.7505229711532593,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.1534,
      "step": 24
    },
    {
      "epoch": 0.00852006475249212,
      "grad_norm": 1.510288119316101,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.1755,
      "step": 25
    },
    {
      "epoch": 0.008860867342591804,
      "grad_norm": 1.6378817558288574,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.2148,
      "step": 26
    },
    {
      "epoch": 0.00920166993269149,
      "grad_norm": 2.1287786960601807,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2388,
      "step": 27
    },
    {
      "epoch": 0.009542472522791173,
      "grad_norm": 1.8834189176559448,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2008,
      "step": 28
    },
    {
      "epoch": 0.009883275112890859,
      "grad_norm": 1.9032727479934692,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2306,
      "step": 29
    },
    {
      "epoch": 0.010224077702990542,
      "grad_norm": 2.5579235553741455,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.2387,
      "step": 30
    },
    {
      "epoch": 0.010564880293090228,
      "grad_norm": 2.015166759490967,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.2126,
      "step": 31
    },
    {
      "epoch": 0.010905682883189912,
      "grad_norm": 2.2278385162353516,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2216,
      "step": 32
    },
    {
      "epoch": 0.011246485473289597,
      "grad_norm": 3.2181928157806396,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.3127,
      "step": 33
    },
    {
      "epoch": 0.011587288063389281,
      "grad_norm": 2.3226587772369385,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3001,
      "step": 34
    },
    {
      "epoch": 0.011928090653488967,
      "grad_norm": 1.7328068017959595,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2373,
      "step": 35
    },
    {
      "epoch": 0.01226889324358865,
      "grad_norm": 1.9611934423446655,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2868,
      "step": 36
    },
    {
      "epoch": 0.012609695833688336,
      "grad_norm": 2.184612989425659,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.3385,
      "step": 37
    },
    {
      "epoch": 0.012950498423788022,
      "grad_norm": 2.998408079147339,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4287,
      "step": 38
    },
    {
      "epoch": 0.013291301013887705,
      "grad_norm": 2.097137689590454,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.3002,
      "step": 39
    },
    {
      "epoch": 0.013632103603987391,
      "grad_norm": 2.743513345718384,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.3541,
      "step": 40
    },
    {
      "epoch": 0.013972906194087075,
      "grad_norm": 2.7991886138916016,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3648,
      "step": 41
    },
    {
      "epoch": 0.01431370878418676,
      "grad_norm": 2.7873311042785645,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.3911,
      "step": 42
    },
    {
      "epoch": 0.014654511374286444,
      "grad_norm": 3.0299744606018066,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4062,
      "step": 43
    },
    {
      "epoch": 0.01499531396438613,
      "grad_norm": 3.0446531772613525,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4443,
      "step": 44
    },
    {
      "epoch": 0.015336116554485813,
      "grad_norm": 3.243168354034424,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.425,
      "step": 45
    },
    {
      "epoch": 0.015676919144585497,
      "grad_norm": 3.139435291290283,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.4884,
      "step": 46
    },
    {
      "epoch": 0.016017721734685183,
      "grad_norm": 3.3464131355285645,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.4394,
      "step": 47
    },
    {
      "epoch": 0.01635852432478487,
      "grad_norm": 3.060849189758301,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4326,
      "step": 48
    },
    {
      "epoch": 0.016699326914884554,
      "grad_norm": 4.429244518280029,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6691,
      "step": 49
    },
    {
      "epoch": 0.01704012950498424,
      "grad_norm": 4.166114807128906,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6339,
      "step": 50
    },
    {
      "epoch": 0.01704012950498424,
      "eval_loss": 0.2583087086677551,
      "eval_runtime": 85.6648,
      "eval_samples_per_second": 57.69,
      "eval_steps_per_second": 14.428,
      "step": 50
    },
    {
      "epoch": 0.01738093209508392,
      "grad_norm": 1.1023403406143188,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1076,
      "step": 51
    },
    {
      "epoch": 0.017721734685183607,
      "grad_norm": 1.395970344543457,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0984,
      "step": 52
    },
    {
      "epoch": 0.018062537275283293,
      "grad_norm": 1.8364086151123047,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1402,
      "step": 53
    },
    {
      "epoch": 0.01840333986538298,
      "grad_norm": 1.1525346040725708,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.1447,
      "step": 54
    },
    {
      "epoch": 0.01874414245548266,
      "grad_norm": 1.1990833282470703,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1585,
      "step": 55
    },
    {
      "epoch": 0.019084945045582346,
      "grad_norm": 1.125974416732788,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1299,
      "step": 56
    },
    {
      "epoch": 0.01942574763568203,
      "grad_norm": 1.1139682531356812,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.1337,
      "step": 57
    },
    {
      "epoch": 0.019766550225781717,
      "grad_norm": 0.9555790424346924,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1422,
      "step": 58
    },
    {
      "epoch": 0.0201073528158814,
      "grad_norm": 0.9790615439414978,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.124,
      "step": 59
    },
    {
      "epoch": 0.020448155405981085,
      "grad_norm": 1.3050878047943115,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.1384,
      "step": 60
    },
    {
      "epoch": 0.02078895799608077,
      "grad_norm": 1.617673397064209,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1676,
      "step": 61
    },
    {
      "epoch": 0.021129760586180456,
      "grad_norm": 0.9874286651611328,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1339,
      "step": 62
    },
    {
      "epoch": 0.02147056317628014,
      "grad_norm": 1.2194032669067383,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.1503,
      "step": 63
    },
    {
      "epoch": 0.021811365766379823,
      "grad_norm": 1.2597358226776123,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1623,
      "step": 64
    },
    {
      "epoch": 0.02215216835647951,
      "grad_norm": 1.2206122875213623,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.1467,
      "step": 65
    },
    {
      "epoch": 0.022492970946579195,
      "grad_norm": 1.3576979637145996,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1842,
      "step": 66
    },
    {
      "epoch": 0.02283377353667888,
      "grad_norm": 1.3525456190109253,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.155,
      "step": 67
    },
    {
      "epoch": 0.023174576126778562,
      "grad_norm": 1.3363933563232422,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1846,
      "step": 68
    },
    {
      "epoch": 0.023515378716878248,
      "grad_norm": 1.5964032411575317,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.2037,
      "step": 69
    },
    {
      "epoch": 0.023856181306977933,
      "grad_norm": 1.477401614189148,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.193,
      "step": 70
    },
    {
      "epoch": 0.02419698389707762,
      "grad_norm": 1.4301406145095825,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.179,
      "step": 71
    },
    {
      "epoch": 0.0245377864871773,
      "grad_norm": 1.189510464668274,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1555,
      "step": 72
    },
    {
      "epoch": 0.024878589077276986,
      "grad_norm": 1.9414318799972534,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.1898,
      "step": 73
    },
    {
      "epoch": 0.025219391667376672,
      "grad_norm": 1.1906410455703735,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1672,
      "step": 74
    },
    {
      "epoch": 0.025560194257476358,
      "grad_norm": 1.4622491598129272,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.1884,
      "step": 75
    },
    {
      "epoch": 0.025900996847576043,
      "grad_norm": 1.439713478088379,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.1893,
      "step": 76
    },
    {
      "epoch": 0.026241799437675725,
      "grad_norm": 1.2294472455978394,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.1794,
      "step": 77
    },
    {
      "epoch": 0.02658260202777541,
      "grad_norm": 1.4370533227920532,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1993,
      "step": 78
    },
    {
      "epoch": 0.026923404617875096,
      "grad_norm": 1.698076844215393,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.2424,
      "step": 79
    },
    {
      "epoch": 0.027264207207974782,
      "grad_norm": 4.689236164093018,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1822,
      "step": 80
    },
    {
      "epoch": 0.027605009798074464,
      "grad_norm": 1.5401798486709595,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.2026,
      "step": 81
    },
    {
      "epoch": 0.02794581238817415,
      "grad_norm": 1.7758527994155884,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.2174,
      "step": 82
    },
    {
      "epoch": 0.028286614978273835,
      "grad_norm": 1.9021817445755005,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2594,
      "step": 83
    },
    {
      "epoch": 0.02862741756837352,
      "grad_norm": 2.2710535526275635,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2903,
      "step": 84
    },
    {
      "epoch": 0.028968220158473203,
      "grad_norm": 2.1698338985443115,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2464,
      "step": 85
    },
    {
      "epoch": 0.029309022748572888,
      "grad_norm": 2.2273144721984863,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3332,
      "step": 86
    },
    {
      "epoch": 0.029649825338672574,
      "grad_norm": 2.147589683532715,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.2777,
      "step": 87
    },
    {
      "epoch": 0.02999062792877226,
      "grad_norm": 2.711846351623535,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3768,
      "step": 88
    },
    {
      "epoch": 0.030331430518871945,
      "grad_norm": 2.5668892860412598,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3517,
      "step": 89
    },
    {
      "epoch": 0.030672233108971627,
      "grad_norm": 2.508510112762451,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3959,
      "step": 90
    },
    {
      "epoch": 0.031013035699071313,
      "grad_norm": 2.696938991546631,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3638,
      "step": 91
    },
    {
      "epoch": 0.031353838289170995,
      "grad_norm": 3.255873918533325,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3756,
      "step": 92
    },
    {
      "epoch": 0.03169464087927068,
      "grad_norm": 2.7637245655059814,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.3561,
      "step": 93
    },
    {
      "epoch": 0.032035443469370366,
      "grad_norm": 2.5270402431488037,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3361,
      "step": 94
    },
    {
      "epoch": 0.03237624605947005,
      "grad_norm": 3.232232093811035,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3971,
      "step": 95
    },
    {
      "epoch": 0.03271704864956974,
      "grad_norm": 3.035440683364868,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.524,
      "step": 96
    },
    {
      "epoch": 0.03305785123966942,
      "grad_norm": 2.7762949466705322,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.397,
      "step": 97
    },
    {
      "epoch": 0.03339865382976911,
      "grad_norm": 3.5465805530548096,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6334,
      "step": 98
    },
    {
      "epoch": 0.033739456419868794,
      "grad_norm": 3.025351047515869,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.535,
      "step": 99
    },
    {
      "epoch": 0.03408025900996848,
      "grad_norm": 4.136836528778076,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.831,
      "step": 100
    },
    {
      "epoch": 0.03408025900996848,
      "eval_loss": 0.24166643619537354,
      "eval_runtime": 85.7269,
      "eval_samples_per_second": 57.648,
      "eval_steps_per_second": 14.418,
      "step": 100
    },
    {
      "epoch": 0.03442106160006816,
      "grad_norm": 1.235883355140686,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0973,
      "step": 101
    },
    {
      "epoch": 0.03476186419016784,
      "grad_norm": 0.6498129367828369,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0981,
      "step": 102
    },
    {
      "epoch": 0.03510266678026753,
      "grad_norm": 0.7633674144744873,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.1238,
      "step": 103
    },
    {
      "epoch": 0.035443469370367214,
      "grad_norm": 0.8347234129905701,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1084,
      "step": 104
    },
    {
      "epoch": 0.0357842719604669,
      "grad_norm": 0.7094018459320068,
      "learning_rate": 5e-05,
      "loss": 0.1028,
      "step": 105
    },
    {
      "epoch": 0.036125074550566585,
      "grad_norm": 0.8028544187545776,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1148,
      "step": 106
    },
    {
      "epoch": 0.03646587714066627,
      "grad_norm": 0.9271275997161865,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.1541,
      "step": 107
    },
    {
      "epoch": 0.03680667973076596,
      "grad_norm": 0.8605714440345764,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1584,
      "step": 108
    },
    {
      "epoch": 0.037147482320865635,
      "grad_norm": 0.8175486326217651,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1303,
      "step": 109
    },
    {
      "epoch": 0.03748828491096532,
      "grad_norm": 0.9535459876060486,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.136,
      "step": 110
    },
    {
      "epoch": 0.037829087501065006,
      "grad_norm": 1.0156004428863525,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.1387,
      "step": 111
    },
    {
      "epoch": 0.03816989009116469,
      "grad_norm": 0.7917398810386658,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1178,
      "step": 112
    },
    {
      "epoch": 0.03851069268126438,
      "grad_norm": 0.8329923748970032,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.1222,
      "step": 113
    },
    {
      "epoch": 0.03885149527136406,
      "grad_norm": 1.031361699104309,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1637,
      "step": 114
    },
    {
      "epoch": 0.03919229786146375,
      "grad_norm": 1.2186564207077026,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.1662,
      "step": 115
    },
    {
      "epoch": 0.039533100451563434,
      "grad_norm": 1.2201515436172485,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.138,
      "step": 116
    },
    {
      "epoch": 0.03987390304166312,
      "grad_norm": 1.0448981523513794,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1557,
      "step": 117
    },
    {
      "epoch": 0.0402147056317628,
      "grad_norm": 1.1961780786514282,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1556,
      "step": 118
    },
    {
      "epoch": 0.040555508221862484,
      "grad_norm": 1.270186185836792,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.1521,
      "step": 119
    },
    {
      "epoch": 0.04089631081196217,
      "grad_norm": 1.1370314359664917,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1457,
      "step": 120
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 1.4064781665802002,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.1626,
      "step": 121
    },
    {
      "epoch": 0.04157791599216154,
      "grad_norm": 1.4352271556854248,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1932,
      "step": 122
    },
    {
      "epoch": 0.041918718582261226,
      "grad_norm": 1.5670093297958374,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.1425,
      "step": 123
    },
    {
      "epoch": 0.04225952117236091,
      "grad_norm": 1.7051527500152588,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.196,
      "step": 124
    },
    {
      "epoch": 0.0426003237624606,
      "grad_norm": 1.7579431533813477,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2326,
      "step": 125
    },
    {
      "epoch": 0.04294112635256028,
      "grad_norm": 1.5878770351409912,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1966,
      "step": 126
    },
    {
      "epoch": 0.04328192894265996,
      "grad_norm": 1.7958312034606934,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2154,
      "step": 127
    },
    {
      "epoch": 0.04362273153275965,
      "grad_norm": 1.8705836534500122,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2157,
      "step": 128
    },
    {
      "epoch": 0.04396353412285933,
      "grad_norm": 1.7443896532058716,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.1986,
      "step": 129
    },
    {
      "epoch": 0.04430433671295902,
      "grad_norm": 1.5546051263809204,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.2106,
      "step": 130
    },
    {
      "epoch": 0.044645139303058703,
      "grad_norm": 1.6522784233093262,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.1908,
      "step": 131
    },
    {
      "epoch": 0.04498594189315839,
      "grad_norm": 1.8296899795532227,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2705,
      "step": 132
    },
    {
      "epoch": 0.045326744483258075,
      "grad_norm": 2.412189245223999,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2817,
      "step": 133
    },
    {
      "epoch": 0.04566754707335776,
      "grad_norm": 2.0074946880340576,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2653,
      "step": 134
    },
    {
      "epoch": 0.046008349663457446,
      "grad_norm": 1.8142625093460083,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2803,
      "step": 135
    },
    {
      "epoch": 0.046349152253557124,
      "grad_norm": 1.8797671794891357,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2666,
      "step": 136
    },
    {
      "epoch": 0.04668995484365681,
      "grad_norm": 2.587186813354492,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3274,
      "step": 137
    },
    {
      "epoch": 0.047030757433756495,
      "grad_norm": 2.242689371109009,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.342,
      "step": 138
    },
    {
      "epoch": 0.04737156002385618,
      "grad_norm": 2.457597017288208,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3436,
      "step": 139
    },
    {
      "epoch": 0.047712362613955867,
      "grad_norm": 2.2661545276641846,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3063,
      "step": 140
    },
    {
      "epoch": 0.04805316520405555,
      "grad_norm": 2.6748502254486084,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.3555,
      "step": 141
    },
    {
      "epoch": 0.04839396779415524,
      "grad_norm": 2.7535431385040283,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.393,
      "step": 142
    },
    {
      "epoch": 0.04873477038425492,
      "grad_norm": 2.534428834915161,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3616,
      "step": 143
    },
    {
      "epoch": 0.0490755729743546,
      "grad_norm": 2.5574092864990234,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3596,
      "step": 144
    },
    {
      "epoch": 0.04941637556445429,
      "grad_norm": 3.1051957607269287,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.4864,
      "step": 145
    },
    {
      "epoch": 0.04975717815455397,
      "grad_norm": 2.9984631538391113,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5202,
      "step": 146
    },
    {
      "epoch": 0.05009798074465366,
      "grad_norm": 3.080761432647705,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5294,
      "step": 147
    },
    {
      "epoch": 0.050438783334753344,
      "grad_norm": 3.5587918758392334,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5392,
      "step": 148
    },
    {
      "epoch": 0.05077958592485303,
      "grad_norm": 2.8504817485809326,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5237,
      "step": 149
    },
    {
      "epoch": 0.051120388514952715,
      "grad_norm": 3.3930535316467285,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5827,
      "step": 150
    },
    {
      "epoch": 0.051120388514952715,
      "eval_loss": 0.22856363654136658,
      "eval_runtime": 85.6253,
      "eval_samples_per_second": 57.717,
      "eval_steps_per_second": 14.435,
      "step": 150
    },
    {
      "epoch": 0.0514611911050524,
      "grad_norm": 0.8811352252960205,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0796,
      "step": 151
    },
    {
      "epoch": 0.051801993695152086,
      "grad_norm": 0.7284087538719177,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.104,
      "step": 152
    },
    {
      "epoch": 0.052142796285251765,
      "grad_norm": 0.7784352898597717,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0942,
      "step": 153
    },
    {
      "epoch": 0.05248359887535145,
      "grad_norm": 0.9148712754249573,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.106,
      "step": 154
    },
    {
      "epoch": 0.052824401465451136,
      "grad_norm": 1.0495636463165283,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1117,
      "step": 155
    },
    {
      "epoch": 0.05316520405555082,
      "grad_norm": 0.8066428303718567,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.094,
      "step": 156
    },
    {
      "epoch": 0.05350600664565051,
      "grad_norm": 0.8946762681007385,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.113,
      "step": 157
    },
    {
      "epoch": 0.05384680923575019,
      "grad_norm": 0.84164959192276,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0896,
      "step": 158
    },
    {
      "epoch": 0.05418761182584988,
      "grad_norm": 1.0463051795959473,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.1231,
      "step": 159
    },
    {
      "epoch": 0.054528414415949564,
      "grad_norm": 1.1035903692245483,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1452,
      "step": 160
    },
    {
      "epoch": 0.05486921700604925,
      "grad_norm": 1.0031118392944336,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.1294,
      "step": 161
    },
    {
      "epoch": 0.05521001959614893,
      "grad_norm": 0.9999609589576721,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.113,
      "step": 162
    },
    {
      "epoch": 0.05555082218624861,
      "grad_norm": 1.0519417524337769,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1358,
      "step": 163
    },
    {
      "epoch": 0.0558916247763483,
      "grad_norm": 1.3999334573745728,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1873,
      "step": 164
    },
    {
      "epoch": 0.056232427366447985,
      "grad_norm": 1.320312738418579,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.1662,
      "step": 165
    },
    {
      "epoch": 0.05657322995654767,
      "grad_norm": 1.1652400493621826,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1402,
      "step": 166
    },
    {
      "epoch": 0.056914032546647356,
      "grad_norm": 1.1076191663742065,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.1337,
      "step": 167
    },
    {
      "epoch": 0.05725483513674704,
      "grad_norm": 1.340041995048523,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1389,
      "step": 168
    },
    {
      "epoch": 0.05759563772684673,
      "grad_norm": 1.3158775568008423,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.151,
      "step": 169
    },
    {
      "epoch": 0.057936440316946405,
      "grad_norm": 1.6075414419174194,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1494,
      "step": 170
    },
    {
      "epoch": 0.05827724290704609,
      "grad_norm": 1.2262078523635864,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.1629,
      "step": 171
    },
    {
      "epoch": 0.058618045497145777,
      "grad_norm": 1.2682536840438843,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.1429,
      "step": 172
    },
    {
      "epoch": 0.05895884808724546,
      "grad_norm": 1.2855504751205444,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.1669,
      "step": 173
    },
    {
      "epoch": 0.05929965067734515,
      "grad_norm": 1.256393313407898,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.1483,
      "step": 174
    },
    {
      "epoch": 0.05964045326744483,
      "grad_norm": 1.406902551651001,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.193,
      "step": 175
    },
    {
      "epoch": 0.05998125585754452,
      "grad_norm": 1.5259534120559692,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.2119,
      "step": 176
    },
    {
      "epoch": 0.060322058447644204,
      "grad_norm": 1.6255565881729126,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.174,
      "step": 177
    },
    {
      "epoch": 0.06066286103774389,
      "grad_norm": 1.5963611602783203,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2023,
      "step": 178
    },
    {
      "epoch": 0.06100366362784357,
      "grad_norm": 1.727860450744629,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2095,
      "step": 179
    },
    {
      "epoch": 0.061344466217943254,
      "grad_norm": 1.4752610921859741,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.206,
      "step": 180
    },
    {
      "epoch": 0.06168526880804294,
      "grad_norm": 1.7509859800338745,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2459,
      "step": 181
    },
    {
      "epoch": 0.062026071398142625,
      "grad_norm": 1.8969165086746216,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2643,
      "step": 182
    },
    {
      "epoch": 0.06236687398824231,
      "grad_norm": 1.7981839179992676,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2294,
      "step": 183
    },
    {
      "epoch": 0.06270767657834199,
      "grad_norm": 2.0366127490997314,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2465,
      "step": 184
    },
    {
      "epoch": 0.06304847916844168,
      "grad_norm": 1.8432413339614868,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2797,
      "step": 185
    },
    {
      "epoch": 0.06338928175854136,
      "grad_norm": 2.002347469329834,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.2715,
      "step": 186
    },
    {
      "epoch": 0.06373008434864105,
      "grad_norm": 2.398376703262329,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3057,
      "step": 187
    },
    {
      "epoch": 0.06407088693874073,
      "grad_norm": 1.919861078262329,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2324,
      "step": 188
    },
    {
      "epoch": 0.06441168952884042,
      "grad_norm": 2.617582321166992,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3448,
      "step": 189
    },
    {
      "epoch": 0.0647524921189401,
      "grad_norm": 2.9287805557250977,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3732,
      "step": 190
    },
    {
      "epoch": 0.0650932947090398,
      "grad_norm": 2.7495343685150146,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3368,
      "step": 191
    },
    {
      "epoch": 0.06543409729913947,
      "grad_norm": 2.5695743560791016,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3594,
      "step": 192
    },
    {
      "epoch": 0.06577489988923915,
      "grad_norm": 3.5732622146606445,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.4818,
      "step": 193
    },
    {
      "epoch": 0.06611570247933884,
      "grad_norm": 2.845581293106079,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4201,
      "step": 194
    },
    {
      "epoch": 0.06645650506943852,
      "grad_norm": 2.856619358062744,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3538,
      "step": 195
    },
    {
      "epoch": 0.06679730765953822,
      "grad_norm": 3.0025062561035156,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4901,
      "step": 196
    },
    {
      "epoch": 0.0671381102496379,
      "grad_norm": 3.233950614929199,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.4864,
      "step": 197
    },
    {
      "epoch": 0.06747891283973759,
      "grad_norm": 3.309993267059326,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4807,
      "step": 198
    },
    {
      "epoch": 0.06781971542983727,
      "grad_norm": 3.495408773422241,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.531,
      "step": 199
    },
    {
      "epoch": 0.06816051801993696,
      "grad_norm": 3.5929596424102783,
      "learning_rate": 0.0,
      "loss": 0.5227,
      "step": 200
    },
    {
      "epoch": 0.06816051801993696,
      "eval_loss": 0.2264130413532257,
      "eval_runtime": 85.8445,
      "eval_samples_per_second": 57.569,
      "eval_steps_per_second": 14.398,
      "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": 1.54569648635904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}